summaryrefslogtreecommitdiff
path: root/tools/testing
diff options
context:
space:
mode:
Diffstat (limited to 'tools/testing')
-rw-r--r--tools/testing/kunit/configs/arch_uml.config5
-rwxr-xr-xtools/testing/kunit/kunit.py4
-rw-r--r--tools/testing/kunit/kunit_parser.py8
-rw-r--r--tools/testing/kunit/qemu_configs/mips.py18
-rw-r--r--tools/testing/kunit/qemu_configs/mips64.py19
-rw-r--r--tools/testing/kunit/qemu_configs/mips64el.py19
-rw-r--r--tools/testing/kunit/qemu_configs/mipsel.py18
-rw-r--r--tools/testing/kunit/test_data/test_is_test_passed-kselftest.log3
-rw-r--r--tools/testing/radix-tree/maple.c524
-rw-r--r--tools/testing/scatterlist/linux/mm.h1
-rw-r--r--tools/testing/selftests/Makefile2
-rw-r--r--tools/testing/selftests/alsa/mixer-test.c8
-rw-r--r--tools/testing/selftests/alsa/pcm-test.c8
-rw-r--r--tools/testing/selftests/arm64/abi/hwcap.c22
-rw-r--r--tools/testing/selftests/arm64/abi/tpidr2.c14
-rw-r--r--tools/testing/selftests/arm64/bti/assembler.h1
-rw-r--r--tools/testing/selftests/arm64/fp/fp-ptrace.c1
-rw-r--r--tools/testing/selftests/arm64/fp/fp-stress.c6
-rw-r--r--tools/testing/selftests/arm64/fp/kernel-test.c4
-rw-r--r--tools/testing/selftests/arm64/fp/sve-ptrace.c104
-rw-r--r--tools/testing/selftests/arm64/fp/vec-syscfg.c1
-rw-r--r--tools/testing/selftests/arm64/fp/zt-ptrace.c1
-rw-r--r--tools/testing/selftests/arm64/gcs/Makefile6
-rw-r--r--tools/testing/selftests/arm64/gcs/basic-gcs.c12
-rw-r--r--tools/testing/selftests/arm64/gcs/gcs-locking.c1
-rw-r--r--tools/testing/selftests/arm64/gcs/gcs-stress.c2
-rw-r--r--tools/testing/selftests/arm64/pauth/exec_target.c7
-rw-r--r--tools/testing/selftests/bpf/.gitignore1
-rw-r--r--tools/testing/selftests/bpf/DENYLIST.s390x1
-rw-r--r--tools/testing/selftests/bpf/Makefile43
-rw-r--r--tools/testing/selftests/bpf/bench.c22
-rw-r--r--tools/testing/selftests/bpf/bench.h1
-rw-r--r--tools/testing/selftests/bpf/benchs/bench_lpm_trie_map.c555
-rw-r--r--tools/testing/selftests/bpf/benchs/bench_sockmap.c5
-rw-r--r--tools/testing/selftests/bpf/benchs/bench_trigger.c61
-rwxr-xr-xtools/testing/selftests/bpf/benchs/run_bench_trigger.sh4
-rw-r--r--tools/testing/selftests/bpf/bpf_experimental.h54
-rw-r--r--tools/testing/selftests/bpf/bpf_kfuncs.h3
-rw-r--r--tools/testing/selftests/bpf/bpf_util.h3
-rw-r--r--tools/testing/selftests/bpf/cgroup_helpers.c20
-rw-r--r--tools/testing/selftests/bpf/cgroup_helpers.h1
-rw-r--r--tools/testing/selftests/bpf/config1
-rw-r--r--tools/testing/selftests/bpf/config.aarch6412
-rw-r--r--tools/testing/selftests/bpf/config.ppc64el1
-rw-r--r--tools/testing/selftests/bpf/config.riscv641
-rw-r--r--tools/testing/selftests/bpf/config.s390x11
-rw-r--r--tools/testing/selftests/bpf/config.x86_645
-rw-r--r--tools/testing/selftests/bpf/network_helpers.c2
-rw-r--r--tools/testing/selftests/bpf/prog_tests/align.c178
-rw-r--r--tools/testing/selftests/bpf/prog_tests/arena_spin_lock.c13
-rw-r--r--tools/testing/selftests/bpf/prog_tests/atomics.c10
-rw-r--r--tools/testing/selftests/bpf/prog_tests/attach_probe.c28
-rw-r--r--tools/testing/selftests/bpf/prog_tests/bpf_cookie.c3
-rw-r--r--tools/testing/selftests/bpf/prog_tests/btf_dump.c2
-rw-r--r--tools/testing/selftests/bpf/prog_tests/cgroup_xattr.c2
-rw-r--r--tools/testing/selftests/bpf/prog_tests/cgrp_kfunc.c71
-rw-r--r--tools/testing/selftests/bpf/prog_tests/dynptr.c2
-rw-r--r--tools/testing/selftests/bpf/prog_tests/fd_array.c2
-rw-r--r--tools/testing/selftests/bpf/prog_tests/fentry_fexit.c15
-rw-r--r--tools/testing/selftests/bpf/prog_tests/fentry_test.c9
-rw-r--r--tools/testing/selftests/bpf/prog_tests/fexit_test.c9
-rw-r--r--tools/testing/selftests/bpf/prog_tests/free_timer.c4
-rw-r--r--tools/testing/selftests/bpf/prog_tests/kernel_flag.c2
-rw-r--r--tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c247
-rw-r--r--tools/testing/selftests/bpf/prog_tests/map_excl.c54
-rw-r--r--tools/testing/selftests/bpf/prog_tests/module_attach.c2
-rw-r--r--tools/testing/selftests/bpf/prog_tests/pinning_devmap_reuse.c50
-rw-r--r--tools/testing/selftests/bpf/prog_tests/prog_tests_framework.c125
-rw-r--r--tools/testing/selftests/bpf/prog_tests/reg_bounds.c4
-rw-r--r--tools/testing/selftests/bpf/prog_tests/res_spin_lock.c16
-rw-r--r--tools/testing/selftests/bpf/prog_tests/spin_lock.c12
-rw-r--r--tools/testing/selftests/bpf/prog_tests/stacktrace_build_id.c2
-rw-r--r--tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c2
-rw-r--r--tools/testing/selftests/bpf/prog_tests/stacktrace_map.c71
-rw-r--r--tools/testing/selftests/bpf/prog_tests/stacktrace_map_raw_tp.c4
-rw-r--r--tools/testing/selftests/bpf/prog_tests/stacktrace_map_skip.c2
-rw-r--r--tools/testing/selftests/bpf/prog_tests/stream.c131
-rw-r--r--tools/testing/selftests/bpf/prog_tests/string_kfuncs.c1
-rw-r--r--tools/testing/selftests/bpf/prog_tests/task_local_data.h386
-rw-r--r--tools/testing/selftests/bpf/prog_tests/task_work_stress.c130
-rw-r--r--tools/testing/selftests/bpf/prog_tests/test_struct_ops_id_ops_mapping.c74
-rw-r--r--tools/testing/selftests/bpf/prog_tests/test_task_local_data.c297
-rw-r--r--tools/testing/selftests/bpf/prog_tests/test_task_work.c157
-rw-r--r--tools/testing/selftests/bpf/prog_tests/test_veristat.c44
-rw-r--r--tools/testing/selftests/bpf/prog_tests/timer.c38
-rw-r--r--tools/testing/selftests/bpf/prog_tests/timer_crash.c4
-rw-r--r--tools/testing/selftests/bpf/prog_tests/timer_lockup.c4
-rw-r--r--tools/testing/selftests/bpf/prog_tests/timer_mim.c4
-rw-r--r--tools/testing/selftests/bpf/prog_tests/tracing_struct.c29
-rw-r--r--tools/testing/selftests/bpf/prog_tests/uprobe.c156
-rw-r--r--tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c484
-rw-r--r--tools/testing/selftests/bpf/prog_tests/usdt.c121
-rw-r--r--tools/testing/selftests/bpf/prog_tests/verifier.c4
-rw-r--r--tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c222
-rw-r--r--tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c31
-rw-r--r--tools/testing/selftests/bpf/prog_tests/xdp_pull_data.c179
-rw-r--r--tools/testing/selftests/bpf/progs/arena_atomics.c9
-rw-r--r--tools/testing/selftests/bpf/progs/arena_spin_lock.c5
-rw-r--r--tools/testing/selftests/bpf/progs/bpf_arena_spin_lock.h4
-rw-r--r--tools/testing/selftests/bpf/progs/bpf_cc_cubic.c2
-rw-r--r--tools/testing/selftests/bpf/progs/bpf_dctcp.c2
-rw-r--r--tools/testing/selftests/bpf/progs/bpf_iter_udp4.c3
-rw-r--r--tools/testing/selftests/bpf/progs/bpf_iter_udp6.c4
-rw-r--r--tools/testing/selftests/bpf/progs/bpf_misc.h24
-rw-r--r--tools/testing/selftests/bpf/progs/bpf_test_utils.h18
-rw-r--r--tools/testing/selftests/bpf/progs/cgroup_read_xattr.c2
-rw-r--r--tools/testing/selftests/bpf/progs/cgrp_kfunc_success.c12
-rw-r--r--tools/testing/selftests/bpf/progs/crypto_sanity.c46
-rw-r--r--tools/testing/selftests/bpf/progs/dynptr_fail.c258
-rw-r--r--tools/testing/selftests/bpf/progs/dynptr_success.c55
-rw-r--r--tools/testing/selftests/bpf/progs/exceptions_assert.c34
-rw-r--r--tools/testing/selftests/bpf/progs/freplace_connect_v4_prog.c2
-rw-r--r--tools/testing/selftests/bpf/progs/iters_state_safety.c6
-rw-r--r--tools/testing/selftests/bpf/progs/iters_task_failure.c4
-rw-r--r--tools/testing/selftests/bpf/progs/iters_testmod.c46
-rw-r--r--tools/testing/selftests/bpf/progs/iters_testmod_seq.c6
-rw-r--r--tools/testing/selftests/bpf/progs/kprobe_write_ctx.c22
-rw-r--r--tools/testing/selftests/bpf/progs/linked_list_fail.c5
-rw-r--r--tools/testing/selftests/bpf/progs/loop1.c7
-rw-r--r--tools/testing/selftests/bpf/progs/loop2.c7
-rw-r--r--tools/testing/selftests/bpf/progs/loop3.c7
-rw-r--r--tools/testing/selftests/bpf/progs/loop6.c21
-rw-r--r--tools/testing/selftests/bpf/progs/lpm_trie.h30
-rw-r--r--tools/testing/selftests/bpf/progs/lpm_trie_bench.c230
-rw-r--r--tools/testing/selftests/bpf/progs/lpm_trie_map.c19
-rw-r--r--tools/testing/selftests/bpf/progs/map_excl.c34
-rw-r--r--tools/testing/selftests/bpf/progs/mem_rdonly_untrusted.c4
-rw-r--r--tools/testing/selftests/bpf/progs/mptcp_subflow.c2
-rw-r--r--tools/testing/selftests/bpf/progs/rbtree_search.c2
-rw-r--r--tools/testing/selftests/bpf/progs/stacktrace_map.c (renamed from tools/testing/selftests/bpf/progs/test_stacktrace_map.c)2
-rw-r--r--tools/testing/selftests/bpf/progs/stream.c158
-rw-r--r--tools/testing/selftests/bpf/progs/string_kfuncs_failure1.c6
-rw-r--r--tools/testing/selftests/bpf/progs/string_kfuncs_failure2.c1
-rw-r--r--tools/testing/selftests/bpf/progs/string_kfuncs_success.c13
-rw-r--r--tools/testing/selftests/bpf/progs/struct_ops_id_ops_mapping1.c59
-rw-r--r--tools/testing/selftests/bpf/progs/struct_ops_id_ops_mapping2.c59
-rw-r--r--tools/testing/selftests/bpf/progs/struct_ops_kptr_return.c2
-rw-r--r--tools/testing/selftests/bpf/progs/struct_ops_refcounted.c2
-rw-r--r--tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy1.c3
-rw-r--r--tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy2.c3
-rw-r--r--tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy3.c3
-rw-r--r--tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy_fentry.c3
-rw-r--r--tools/testing/selftests/bpf/progs/task_local_data.bpf.h237
-rw-r--r--tools/testing/selftests/bpf/progs/task_work.c107
-rw-r--r--tools/testing/selftests/bpf/progs/task_work_fail.c96
-rw-r--r--tools/testing/selftests/bpf/progs/task_work_stress.c73
-rw-r--r--tools/testing/selftests/bpf/progs/test_cls_redirect.c6
-rw-r--r--tools/testing/selftests/bpf/progs/test_cls_redirect_dynptr.c2
-rw-r--r--tools/testing/selftests/bpf/progs/test_overhead.c5
-rw-r--r--tools/testing/selftests/bpf/progs/test_pinning_devmap.c20
-rw-r--r--tools/testing/selftests/bpf/progs/test_task_local_data.c65
-rw-r--r--tools/testing/selftests/bpf/progs/test_tcp_hdr_options.c5
-rw-r--r--tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c1
-rw-r--r--tools/testing/selftests/bpf/progs/test_uprobe.c38
-rw-r--r--tools/testing/selftests/bpf/progs/test_usdt.c31
-rw-r--r--tools/testing/selftests/bpf/progs/test_xdp_devmap_tailcall.c29
-rw-r--r--tools/testing/selftests/bpf/progs/test_xdp_meta.c419
-rw-r--r--tools/testing/selftests/bpf/progs/test_xdp_pull_data.c48
-rw-r--r--tools/testing/selftests/bpf/progs/timer_interrupt.c48
-rw-r--r--tools/testing/selftests/bpf/progs/tracing_struct.c33
-rw-r--r--tools/testing/selftests/bpf/progs/trigger_bench.c12
-rw-r--r--tools/testing/selftests/bpf/progs/uprobe_syscall.c4
-rw-r--r--tools/testing/selftests/bpf/progs/uprobe_syscall_executed.c60
-rw-r--r--tools/testing/selftests/bpf/progs/uretprobe_stack.c4
-rw-r--r--tools/testing/selftests/bpf/progs/verifier_arena_large.c1
-rw-r--r--tools/testing/selftests/bpf/progs/verifier_bounds.c79
-rw-r--r--tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c27
-rw-r--r--tools/testing/selftests/bpf/progs/verifier_ctx.c32
-rw-r--r--tools/testing/selftests/bpf/progs/verifier_global_ptr_args.c4
-rw-r--r--tools/testing/selftests/bpf/progs/verifier_ldsx.c178
-rw-r--r--tools/testing/selftests/bpf/progs/verifier_live_stack.c294
-rw-r--r--tools/testing/selftests/bpf/progs/verifier_loops1.c21
-rw-r--r--tools/testing/selftests/bpf/progs/verifier_map_ptr.c7
-rw-r--r--tools/testing/selftests/bpf/progs/verifier_may_goto_1.c38
-rw-r--r--tools/testing/selftests/bpf/progs/verifier_mul.c38
-rw-r--r--tools/testing/selftests/bpf/progs/verifier_precision.c16
-rw-r--r--tools/testing/selftests/bpf/progs/verifier_scalar_ids.c12
-rw-r--r--tools/testing/selftests/bpf/progs/verifier_sock.c48
-rw-r--r--tools/testing/selftests/bpf/progs/verifier_spill_fill.c40
-rw-r--r--tools/testing/selftests/bpf/progs/verifier_subprog_precision.c6
-rw-r--r--tools/testing/selftests/bpf/progs/verifier_var_off.c6
-rw-r--r--tools/testing/selftests/bpf/test_kmods/Makefile2
-rw-r--r--tools/testing/selftests/bpf/test_kmods/bpf_test_rqspinlock.c209
-rw-r--r--tools/testing/selftests/bpf/test_kmods/bpf_testmod.c166
-rw-r--r--tools/testing/selftests/bpf/test_kmods/bpf_testmod.h6
-rw-r--r--tools/testing/selftests/bpf/test_kmods/bpf_testmod_kfunc.h4
-rw-r--r--tools/testing/selftests/bpf/test_lirc_mode2_user.c2
-rw-r--r--tools/testing/selftests/bpf/test_loader.c300
-rw-r--r--tools/testing/selftests/bpf/test_progs.c13
-rw-r--r--tools/testing/selftests/bpf/test_progs.h17
-rw-r--r--tools/testing/selftests/bpf/test_sockmap.c2
-rw-r--r--tools/testing/selftests/bpf/test_tcpnotify_user.c20
-rwxr-xr-xtools/testing/selftests/bpf/test_xsk.sh2
-rw-r--r--tools/testing/selftests/bpf/testing_helpers.c14
-rw-r--r--tools/testing/selftests/bpf/testing_helpers.h1
-rw-r--r--tools/testing/selftests/bpf/trace_helpers.c234
-rw-r--r--tools/testing/selftests/bpf/trace_helpers.h3
-rw-r--r--tools/testing/selftests/bpf/usdt.h545
-rw-r--r--tools/testing/selftests/bpf/verifier/bpf_st_mem.c4
-rw-r--r--tools/testing/selftests/bpf/verifier/calls.c8
-rwxr-xr-xtools/testing/selftests/bpf/verify_sig_setup.sh11
-rw-r--r--tools/testing/selftests/bpf/veristat.c56
-rw-r--r--tools/testing/selftests/bpf/xdping.c2
-rw-r--r--tools/testing/selftests/bpf/xsk.h4
-rw-r--r--tools/testing/selftests/bpf/xskxceiver.c14
-rw-r--r--tools/testing/selftests/cgroup/lib/cgroup_util.c12
-rw-r--r--tools/testing/selftests/cgroup/lib/include/cgroup_util.h1
-rw-r--r--tools/testing/selftests/cgroup/test_freezer.c663
-rw-r--r--tools/testing/selftests/cgroup/test_pids.c3
-rw-r--r--tools/testing/selftests/damon/Makefile2
-rw-r--r--tools/testing/selftests/damon/access_memory_even.c1
-rwxr-xr-xtools/testing/selftests/damon/sysfs_no_op_commit_break.py72
-rw-r--r--tools/testing/selftests/drivers/net/.gitignore1
-rw-r--r--tools/testing/selftests/drivers/net/Makefile10
-rw-r--r--tools/testing/selftests/drivers/net/bonding/Makefile4
-rwxr-xr-xtools/testing/selftests/drivers/net/bonding/bond_ipsec_offload.sh156
-rwxr-xr-xtools/testing/selftests/drivers/net/bonding/bond_lacp_prio.sh108
-rwxr-xr-xtools/testing/selftests/drivers/net/bonding/bond_options.sh197
-rw-r--r--tools/testing/selftests/drivers/net/bonding/bond_topo_2d1c.sh3
-rw-r--r--tools/testing/selftests/drivers/net/bonding/bond_topo_3d1c.sh2
-rw-r--r--tools/testing/selftests/drivers/net/bonding/config5
-rw-r--r--tools/testing/selftests/drivers/net/config5
-rwxr-xr-xtools/testing/selftests/drivers/net/hds.py39
-rw-r--r--tools/testing/selftests/drivers/net/hw/Makefile2
-rw-r--r--tools/testing/selftests/drivers/net/hw/config2
-rwxr-xr-xtools/testing/selftests/drivers/net/hw/csum.py4
-rwxr-xr-xtools/testing/selftests/drivers/net/hw/devmem.py14
-rw-r--r--tools/testing/selftests/drivers/net/hw/lib/py/__init__.py4
-rw-r--r--tools/testing/selftests/drivers/net/hw/ncdevmem.c856
-rwxr-xr-xtools/testing/selftests/drivers/net/hw/nic_timestamp.py113
-rwxr-xr-xtools/testing/selftests/drivers/net/hw/rss_ctx.py18
-rwxr-xr-xtools/testing/selftests/drivers/net/hw/rss_flow_label.py167
-rwxr-xr-xtools/testing/selftests/drivers/net/hw/tso.py11
-rw-r--r--tools/testing/selftests/drivers/net/lib/py/__init__.py6
-rw-r--r--tools/testing/selftests/drivers/net/lib/py/env.py45
-rw-r--r--tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh10
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/devlink_trap_policer.sh9
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/qos_ets_strict.sh12
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/qos_max_descriptors.sh9
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh12
-rw-r--r--tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh6
-rwxr-xr-xtools/testing/selftests/drivers/net/napi_threaded.py34
-rwxr-xr-xtools/testing/selftests/drivers/net/netcons_cmdline.sh55
-rwxr-xr-xtools/testing/selftests/drivers/net/psp.py627
-rw-r--r--tools/testing/selftests/drivers/net/psp_responder.c483
-rwxr-xr-xtools/testing/selftests/drivers/net/stats.py35
-rw-r--r--tools/testing/selftests/drivers/net/team/Makefile6
-rw-r--r--tools/testing/selftests/drivers/net/team/config1
-rwxr-xr-xtools/testing/selftests/drivers/net/team/options.sh188
-rwxr-xr-xtools/testing/selftests/drivers/net/xdp.py75
-rw-r--r--tools/testing/selftests/filesystems/.gitignore1
-rw-r--r--tools/testing/selftests/filesystems/Makefile2
-rw-r--r--tools/testing/selftests/filesystems/fclog.c130
-rw-r--r--tools/testing/selftests/filesystems/mount-notify/mount-notify_test.c17
-rw-r--r--tools/testing/selftests/filesystems/mount-notify/mount-notify_test_ns.c18
-rw-r--r--tools/testing/selftests/futex/functional/Makefile8
-rw-r--r--tools/testing/selftests/futex/functional/futex_numa.c3
-rw-r--r--tools/testing/selftests/futex/functional/futex_numa_mpol.c100
-rw-r--r--tools/testing/selftests/futex/functional/futex_priv_hash.c67
-rw-r--r--tools/testing/selftests/futex/functional/futex_requeue.c76
-rw-r--r--tools/testing/selftests/futex/functional/futex_requeue_pi.c266
-rw-r--r--tools/testing/selftests/futex/functional/futex_requeue_pi_mismatched_ops.c86
-rw-r--r--tools/testing/selftests/futex/functional/futex_requeue_pi_signal_restart.c129
-rw-r--r--tools/testing/selftests/futex/functional/futex_wait.c103
-rw-r--r--tools/testing/selftests/futex/functional/futex_wait_private_mapped_file.c83
-rw-r--r--tools/testing/selftests/futex/functional/futex_wait_timeout.c139
-rw-r--r--tools/testing/selftests/futex/functional/futex_wait_uninitialized_heap.c76
-rw-r--r--tools/testing/selftests/futex/functional/futex_wait_wouldblock.c76
-rw-r--r--tools/testing/selftests/futex/functional/futex_waitv.c99
-rwxr-xr-xtools/testing/selftests/futex/functional/run.sh62
-rw-r--r--tools/testing/selftests/futex/include/futextest.h11
-rw-r--r--tools/testing/selftests/futex/include/logging.h148
-rw-r--r--tools/testing/selftests/iommu/iommufd_fail_nth.c2
-rw-r--r--tools/testing/selftests/kexec/.gitignore2
-rw-r--r--tools/testing/selftests/kho/init.c13
-rwxr-xr-xtools/testing/selftests/kho/vmtest.sh28
-rw-r--r--tools/testing/selftests/kselftest.h22
-rw-r--r--tools/testing/selftests/kselftest_harness.h13
-rw-r--r--tools/testing/selftests/kselftest_harness/Makefile1
-rw-r--r--tools/testing/selftests/landlock/audit.h6
-rw-r--r--tools/testing/selftests/landlock/common.h4
-rw-r--r--tools/testing/selftests/lib.mk5
-rw-r--r--tools/testing/selftests/mm/.gitignore2
-rw-r--r--tools/testing/selftests/mm/Makefile5
-rw-r--r--tools/testing/selftests/mm/cow.c13
-rw-r--r--tools/testing/selftests/mm/gup_test.c2
-rw-r--r--tools/testing/selftests/mm/hmm-tests.c5
-rw-r--r--tools/testing/selftests/mm/hugepage-mremap.c16
-rw-r--r--tools/testing/selftests/mm/khugepaged.c2
-rw-r--r--tools/testing/selftests/mm/ksm_functional_tests.c199
-rw-r--r--tools/testing/selftests/mm/madv_populate.c21
-rw-r--r--tools/testing/selftests/mm/mremap_test.c6
-rw-r--r--tools/testing/selftests/mm/pagemap_ioctl.c24
-rw-r--r--tools/testing/selftests/mm/pfnmap.c48
-rw-r--r--tools/testing/selftests/mm/pkey-helpers.h3
-rw-r--r--tools/testing/selftests/mm/pkey_sighandler_tests.c2
-rw-r--r--tools/testing/selftests/mm/prctl_thp_disable.c291
-rw-r--r--tools/testing/selftests/mm/protection_keys.c6
-rw-r--r--tools/testing/selftests/mm/rmap.c433
-rwxr-xr-xtools/testing/selftests/mm/run_vmtests.sh31
-rw-r--r--tools/testing/selftests/mm/soft-dirty.c5
-rw-r--r--tools/testing/selftests/mm/split_huge_page_test.c469
-rwxr-xr-xtools/testing/selftests/mm/test_vmalloc.sh6
-rw-r--r--tools/testing/selftests/mm/thp_settings.c9
-rw-r--r--tools/testing/selftests/mm/thp_settings.h1
-rw-r--r--tools/testing/selftests/mm/thuge-gen.c11
-rw-r--r--tools/testing/selftests/mm/uffd-common.c271
-rw-r--r--tools/testing/selftests/mm/uffd-common.h78
-rw-r--r--tools/testing/selftests/mm/uffd-stress.c243
-rw-r--r--tools/testing/selftests/mm/uffd-unit-tests.c559
-rw-r--r--tools/testing/selftests/mm/uffd-wp-mremap.c29
-rw-r--r--tools/testing/selftests/mm/va_high_addr_switch.c4
-rwxr-xr-xtools/testing/selftests/mm/va_high_addr_switch.sh37
-rw-r--r--tools/testing/selftests/mm/virtual_address_range.c13
-rw-r--r--tools/testing/selftests/mm/vm_util.c167
-rw-r--r--tools/testing/selftests/mm/vm_util.h18
-rw-r--r--tools/testing/selftests/namespaces/.gitignore3
-rw-r--r--tools/testing/selftests/namespaces/Makefile7
-rw-r--r--tools/testing/selftests/namespaces/config7
-rw-r--r--tools/testing/selftests/namespaces/file_handle_test.c1429
-rw-r--r--tools/testing/selftests/namespaces/init_ino_test.c61
-rw-r--r--tools/testing/selftests/namespaces/nsid_test.c986
-rw-r--r--tools/testing/selftests/net/.gitignore2
-rw-r--r--tools/testing/selftests/net/Makefile13
-rw-r--r--tools/testing/selftests/net/af_unix/Makefile2
-rw-r--r--tools/testing/selftests/net/af_unix/scm_inq.c26
-rw-r--r--tools/testing/selftests/net/af_unix/scm_pidfd.c2
-rw-r--r--tools/testing/selftests/net/af_unix/scm_rights.c28
-rw-r--r--tools/testing/selftests/net/bind_bhash.c4
-rwxr-xr-xtools/testing/selftests/net/bpf_offload.py4
-rwxr-xr-xtools/testing/selftests/net/broadcast_ether_dst.sh83
-rw-r--r--tools/testing/selftests/net/can/config3
-rw-r--r--tools/testing/selftests/net/cmsg_sender.c10
-rw-r--r--tools/testing/selftests/net/config1
-rwxr-xr-xtools/testing/selftests/net/fcnal-ipv4.sh2
-rwxr-xr-xtools/testing/selftests/net/fcnal-ipv6.sh2
-rwxr-xr-xtools/testing/selftests/net/fcnal-other.sh2
-rwxr-xr-xtools/testing/selftests/net/fcnal-test.sh435
-rwxr-xr-xtools/testing/selftests/net/fdb_notify.sh26
-rwxr-xr-xtools/testing/selftests/net/fib_nexthops.sh52
-rw-r--r--tools/testing/selftests/net/forwarding/Makefile5
-rw-r--r--tools/testing/selftests/net/forwarding/README15
-rwxr-xr-xtools/testing/selftests/net/forwarding/bridge_activity_notify.sh170
-rwxr-xr-xtools/testing/selftests/net/forwarding/bridge_fdb_local_vlan_0.sh387
-rwxr-xr-xtools/testing/selftests/net/forwarding/custom_multipath_hash.sh2
-rwxr-xr-xtools/testing/selftests/net/forwarding/gre_custom_multipath_hash.sh2
-rwxr-xr-xtools/testing/selftests/net/forwarding/ip6_forward_instats_vrf.sh6
-rwxr-xr-xtools/testing/selftests/net/forwarding/ip6gre_custom_multipath_hash.sh2
-rw-r--r--tools/testing/selftests/net/forwarding/lib.sh50
-rwxr-xr-xtools/testing/selftests/net/forwarding/mirror_gre_bridge_1q_lag.sh2
-rwxr-xr-xtools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh4
-rw-r--r--tools/testing/selftests/net/forwarding/sch_ets_core.sh9
-rwxr-xr-xtools/testing/selftests/net/forwarding/sch_red.sh12
-rw-r--r--tools/testing/selftests/net/forwarding/sch_tbf_core.sh6
-rwxr-xr-xtools/testing/selftests/net/forwarding/vxlan_bridge_1q_mc_ul.sh141
-rwxr-xr-xtools/testing/selftests/net/forwarding/vxlan_reserved.sh33
-rw-r--r--tools/testing/selftests/net/gro.c58
-rwxr-xr-xtools/testing/selftests/net/gro.sh2
-rw-r--r--tools/testing/selftests/net/ipv6_fragmentation.c114
-rw-r--r--tools/testing/selftests/net/lib.sh72
-rw-r--r--tools/testing/selftests/net/lib/py/__init__.py2
-rw-r--r--tools/testing/selftests/net/lib/py/ksft.py10
-rw-r--r--tools/testing/selftests/net/lib/py/utils.py45
-rw-r--r--tools/testing/selftests/net/lib/py/ynl.py5
-rw-r--r--tools/testing/selftests/net/lib/sh/defer.sh20
-rw-r--r--tools/testing/selftests/net/lib/xdp_native.bpf.c98
-rwxr-xr-xtools/testing/selftests/net/mptcp/diag.sh2
-rw-r--r--tools/testing/selftests/net/mptcp/mptcp_connect.c11
-rwxr-xr-xtools/testing/selftests/net/mptcp/mptcp_connect.sh8
-rw-r--r--tools/testing/selftests/net/mptcp/mptcp_inq.c9
-rwxr-xr-xtools/testing/selftests/net/mptcp/mptcp_join.sh230
-rw-r--r--tools/testing/selftests/net/mptcp/mptcp_lib.sh2
-rw-r--r--tools/testing/selftests/net/mptcp/mptcp_sockopt.c25
-rwxr-xr-xtools/testing/selftests/net/mptcp/mptcp_sockopt.sh2
-rwxr-xr-xtools/testing/selftests/net/mptcp/pm_netlink.sh5
-rw-r--r--tools/testing/selftests/net/mptcp/pm_nl_ctl.c25
-rwxr-xr-xtools/testing/selftests/net/mptcp/simult_flows.sh2
-rwxr-xr-xtools/testing/selftests/net/mptcp/userspace_pm.sh16
-rw-r--r--tools/testing/selftests/net/netfilter/config1
-rwxr-xr-xtools/testing/selftests/net/netfilter/conntrack_clash.sh2
-rwxr-xr-xtools/testing/selftests/net/netfilter/conntrack_resize.sh5
-rwxr-xr-xtools/testing/selftests/net/netfilter/nft_concat_range.sh56
-rwxr-xr-xtools/testing/selftests/net/netfilter/nft_flowtable.sh113
-rwxr-xr-xtools/testing/selftests/net/netfilter/nft_nat.sh4
-rw-r--r--tools/testing/selftests/net/netfilter/udpclash.c2
-rw-r--r--tools/testing/selftests/net/netlink-dumps.c43
-rwxr-xr-xtools/testing/selftests/net/openvswitch/openvswitch.sh88
-rw-r--r--tools/testing/selftests/net/openvswitch/ovs-dpctl.py2
-rw-r--r--tools/testing/selftests/net/ovpn/ovpn-cli.c3
-rwxr-xr-xtools/testing/selftests/net/packetdrill/defaults.sh3
-rwxr-xr-xtools/testing/selftests/net/packetdrill/ksft_runner.sh53
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_close_no_rst.pkt32
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_fastopen_server_basic-cookie-not-reqd.pkt32
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_fastopen_server_basic-no-setsockopt.pkt21
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_fastopen_server_basic-non-tfo-listener.pkt26
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_fastopen_server_basic-pure-syn-data.pkt50
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_fastopen_server_basic-rw.pkt23
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_fastopen_server_basic-zero-payload.pkt26
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_fastopen_server_client-ack-dropped-then-recovery-ms-timestamps.pkt46
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_fastopen_server_experimental_option.pkt37
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_fastopen_server_fin-close-socket.pkt30
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_fastopen_server_icmp-before-accept.pkt49
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_fastopen_server_reset-after-accept.pkt37
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_fastopen_server_reset-before-accept.pkt32
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_fastopen_server_reset-close-with-unread-data.pkt32
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_fastopen_server_reset-non-tfo-socket.pkt37
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_fastopen_server_sockopt-fastopen-key.pkt74
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_fastopen_server_trigger-rst-listener-closed.pkt21
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_fastopen_server_trigger-rst-reconnect.pkt30
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_fastopen_server_trigger-rst-unread-data-closed.pkt23
-rwxr-xr-xtools/testing/selftests/net/pmtu.sh9
-rw-r--r--tools/testing/selftests/net/psock_lib.h4
-rw-r--r--tools/testing/selftests/net/psock_tpacket.c4
-rwxr-xr-xtools/testing/selftests/net/route_hint.sh79
-rwxr-xr-xtools/testing/selftests/net/rps_default_mask.sh12
-rwxr-xr-xtools/testing/selftests/net/rtnetlink.sh15
-rw-r--r--tools/testing/selftests/net/socket.c11
-rw-r--r--tools/testing/selftests/net/tcp_port_share.c258
-rwxr-xr-xtools/testing/selftests/net/test_bridge_backup_port.sh31
-rwxr-xr-xtools/testing/selftests/net/test_vxlan_fdb_changelink.sh8
-rwxr-xr-xtools/testing/selftests/net/test_vxlan_nh.sh223
-rwxr-xr-xtools/testing/selftests/net/tfo_passive.sh2
-rw-r--r--tools/testing/selftests/net/tls.c21
-rwxr-xr-xtools/testing/selftests/net/traceroute.sh250
-rwxr-xr-xtools/testing/selftests/net/vlan_bridge_binding.sh44
-rw-r--r--tools/testing/selftests/net/ynl.mk5
-rw-r--r--tools/testing/selftests/nolibc/Makefile.nolibc17
-rw-r--r--tools/testing/selftests/nolibc/nolibc-test.c6
-rw-r--r--tools/testing/selftests/perf_events/watermark_signal.c2
-rw-r--r--tools/testing/selftests/pidfd/config1
-rw-r--r--tools/testing/selftests/powerpc/include/instructions.h2
-rw-r--r--tools/testing/selftests/proc/.gitignore1
-rw-r--r--tools/testing/selftests/proc/Makefile1
-rw-r--r--tools/testing/selftests/proc/proc-maps-race.c65
-rw-r--r--tools/testing/selftests/proc/proc-pidns.c211
-rw-r--r--tools/testing/selftests/riscv/README24
-rw-r--r--tools/testing/selftests/rseq/rseq.c8
-rw-r--r--tools/testing/selftests/seccomp/seccomp_bpf.c238
-rw-r--r--tools/testing/selftests/tc-testing/tc-tests/actions/police.json2
-rw-r--r--tools/testing/selftests/thermal/intel/workload_hint/workload_hint_test.c2
-rw-r--r--tools/testing/selftests/ublk/Makefile1
-rw-r--r--tools/testing/selftests/ublk/kublk.c32
-rwxr-xr-xtools/testing/selftests/ublk/test_generic_01.sh4
-rwxr-xr-xtools/testing/selftests/ublk/test_generic_02.sh4
-rwxr-xr-xtools/testing/selftests/ublk/test_generic_12.sh4
-rwxr-xr-xtools/testing/selftests/ublk/test_generic_13.sh20
-rwxr-xr-xtools/testing/selftests/ublk/test_null_01.sh4
-rwxr-xr-xtools/testing/selftests/ublk/test_null_02.sh4
-rwxr-xr-xtools/testing/selftests/ublk/test_stress_05.sh4
-rw-r--r--tools/testing/selftests/ublk/utils.h2
-rw-r--r--tools/testing/selftests/vDSO/.gitignore1
-rw-r--r--tools/testing/selftests/vDSO/Makefile2
-rw-r--r--tools/testing/selftests/vDSO/vdso_call.h7
-rw-r--r--tools/testing/selftests/vDSO/vdso_test_abi.c101
-rw-r--r--tools/testing/selftests/vDSO/vdso_test_clock_getres.c123
-rw-r--r--tools/testing/selftests/watchdog/watchdog-test.c6
-rw-r--r--tools/testing/selftests/wireguard/qemu/kernel.config8
-rw-r--r--tools/testing/selftests/zram/README1
-rw-r--r--tools/testing/shared/linux.c120
-rw-r--r--tools/testing/shared/linux/maple_tree.h6
-rw-r--r--tools/testing/shared/maple-shared.h11
-rw-r--r--tools/testing/shared/maple-shim.c7
-rw-r--r--tools/testing/shared/shared.mk6
-rw-r--r--tools/testing/vma/linux/atomic.h17
-rw-r--r--tools/testing/vma/vma_internal.h344
-rw-r--r--tools/testing/vsock/util.c1
466 files changed, 22295 insertions, 4984 deletions
diff --git a/tools/testing/kunit/configs/arch_uml.config b/tools/testing/kunit/configs/arch_uml.config
index 54ad8972681a..28edf816aa70 100644
--- a/tools/testing/kunit/configs/arch_uml.config
+++ b/tools/testing/kunit/configs/arch_uml.config
@@ -1,8 +1,7 @@
# Config options which are added to UML builds by default
-# Enable virtio/pci, as a lot of tests require it.
-CONFIG_VIRTIO_UML=y
-CONFIG_UML_PCI_OVER_VIRTIO=y
+# Enable pci, as a lot of tests require it.
+CONFIG_KUNIT_UML_PCI=y
# Enable FORTIFY_SOURCE for wider checking.
CONFIG_FORTIFY_SOURCE=y
diff --git a/tools/testing/kunit/kunit.py b/tools/testing/kunit/kunit.py
index 7f9ae55fd6d5..cd99c1956331 100755
--- a/tools/testing/kunit/kunit.py
+++ b/tools/testing/kunit/kunit.py
@@ -228,7 +228,7 @@ def parse_tests(request: KunitParseRequest, metadata: kunit_json.Metadata, input
fake_test.counts.passed = 1
output: Iterable[str] = input_data
- if request.raw_output == 'all':
+ if request.raw_output == 'all' or request.raw_output == 'full':
pass
elif request.raw_output == 'kunit':
output = kunit_parser.extract_tap_lines(output)
@@ -425,7 +425,7 @@ def add_parse_opts(parser: argparse.ArgumentParser) -> None:
parser.add_argument('--raw_output', help='If set don\'t parse output from kernel. '
'By default, filters to just KUnit output. Use '
'--raw_output=all to show everything',
- type=str, nargs='?', const='all', default=None, choices=['all', 'kunit'])
+ type=str, nargs='?', const='all', default=None, choices=['all', 'full', 'kunit'])
parser.add_argument('--json',
nargs='?',
help='Prints parsed test results as JSON to stdout or a file if '
diff --git a/tools/testing/kunit/kunit_parser.py b/tools/testing/kunit/kunit_parser.py
index c176487356e6..333cd3a4a56b 100644
--- a/tools/testing/kunit/kunit_parser.py
+++ b/tools/testing/kunit/kunit_parser.py
@@ -352,9 +352,9 @@ def parse_test_plan(lines: LineStream, test: Test) -> bool:
lines.pop()
return True
-TEST_RESULT = re.compile(r'^\s*(ok|not ok) ([0-9]+) (- )?([^#]*)( # .*)?$')
+TEST_RESULT = re.compile(r'^\s*(ok|not ok) ([0-9]+) ?(- )?([^#]*)( # .*)?$')
-TEST_RESULT_SKIP = re.compile(r'^\s*(ok|not ok) ([0-9]+) (- )?(.*) # SKIP(.*)$')
+TEST_RESULT_SKIP = re.compile(r'^\s*(ok|not ok) ([0-9]+) ?(- )?(.*) # SKIP ?(.*)$')
def peek_test_name_match(lines: LineStream, test: Test) -> bool:
"""
@@ -379,6 +379,8 @@ def peek_test_name_match(lines: LineStream, test: Test) -> bool:
if not match:
return False
name = match.group(4)
+ if not name:
+ return False
return name == test.name
def parse_test_result(lines: LineStream, test: Test,
@@ -416,7 +418,7 @@ def parse_test_result(lines: LineStream, test: Test,
# Set name of test object
if skip_match:
- test.name = skip_match.group(4)
+ test.name = skip_match.group(4) or skip_match.group(5)
else:
test.name = match.group(4)
diff --git a/tools/testing/kunit/qemu_configs/mips.py b/tools/testing/kunit/qemu_configs/mips.py
new file mode 100644
index 000000000000..8899ac157b30
--- /dev/null
+++ b/tools/testing/kunit/qemu_configs/mips.py
@@ -0,0 +1,18 @@
+# SPDX-License-Identifier: GPL-2.0
+
+from ..qemu_config import QemuArchParams
+
+QEMU_ARCH = QemuArchParams(linux_arch='mips',
+ kconfig='''
+CONFIG_32BIT=y
+CONFIG_CPU_BIG_ENDIAN=y
+CONFIG_MIPS_MALTA=y
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_POWER_RESET=y
+CONFIG_POWER_RESET_SYSCON=y
+''',
+ qemu_arch='mips',
+ kernel_path='vmlinuz',
+ kernel_command_line='console=ttyS0',
+ extra_qemu_params=['-M', 'malta'])
diff --git a/tools/testing/kunit/qemu_configs/mips64.py b/tools/testing/kunit/qemu_configs/mips64.py
new file mode 100644
index 000000000000..1478aed05b94
--- /dev/null
+++ b/tools/testing/kunit/qemu_configs/mips64.py
@@ -0,0 +1,19 @@
+# SPDX-License-Identifier: GPL-2.0
+
+from ..qemu_config import QemuArchParams
+
+QEMU_ARCH = QemuArchParams(linux_arch='mips',
+ kconfig='''
+CONFIG_CPU_MIPS64_R2=y
+CONFIG_64BIT=y
+CONFIG_CPU_BIG_ENDIAN=y
+CONFIG_MIPS_MALTA=y
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_POWER_RESET=y
+CONFIG_POWER_RESET_SYSCON=y
+''',
+ qemu_arch='mips64',
+ kernel_path='vmlinuz',
+ kernel_command_line='console=ttyS0',
+ extra_qemu_params=['-M', 'malta', '-cpu', '5KEc'])
diff --git a/tools/testing/kunit/qemu_configs/mips64el.py b/tools/testing/kunit/qemu_configs/mips64el.py
new file mode 100644
index 000000000000..300c711d7a82
--- /dev/null
+++ b/tools/testing/kunit/qemu_configs/mips64el.py
@@ -0,0 +1,19 @@
+# SPDX-License-Identifier: GPL-2.0
+
+from ..qemu_config import QemuArchParams
+
+QEMU_ARCH = QemuArchParams(linux_arch='mips',
+ kconfig='''
+CONFIG_CPU_MIPS64_R2=y
+CONFIG_64BIT=y
+CONFIG_CPU_LITTLE_ENDIAN=y
+CONFIG_MIPS_MALTA=y
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_POWER_RESET=y
+CONFIG_POWER_RESET_SYSCON=y
+''',
+ qemu_arch='mips64el',
+ kernel_path='vmlinuz',
+ kernel_command_line='console=ttyS0',
+ extra_qemu_params=['-M', 'malta', '-cpu', '5KEc'])
diff --git a/tools/testing/kunit/qemu_configs/mipsel.py b/tools/testing/kunit/qemu_configs/mipsel.py
new file mode 100644
index 000000000000..3d3543315b45
--- /dev/null
+++ b/tools/testing/kunit/qemu_configs/mipsel.py
@@ -0,0 +1,18 @@
+# SPDX-License-Identifier: GPL-2.0
+
+from ..qemu_config import QemuArchParams
+
+QEMU_ARCH = QemuArchParams(linux_arch='mips',
+ kconfig='''
+CONFIG_32BIT=y
+CONFIG_CPU_LITTLE_ENDIAN=y
+CONFIG_MIPS_MALTA=y
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_POWER_RESET=y
+CONFIG_POWER_RESET_SYSCON=y
+''',
+ qemu_arch='mipsel',
+ kernel_path='vmlinuz',
+ kernel_command_line='console=ttyS0',
+ extra_qemu_params=['-M', 'malta'])
diff --git a/tools/testing/kunit/test_data/test_is_test_passed-kselftest.log b/tools/testing/kunit/test_data/test_is_test_passed-kselftest.log
index 65d3f27feaf2..30d9ef18bcec 100644
--- a/tools/testing/kunit/test_data/test_is_test_passed-kselftest.log
+++ b/tools/testing/kunit/test_data/test_is_test_passed-kselftest.log
@@ -1,5 +1,5 @@
TAP version 13
-1..2
+1..3
# selftests: membarrier: membarrier_test_single_thread
# TAP version 13
# 1..2
@@ -12,3 +12,4 @@ ok 1 selftests: membarrier: membarrier_test_single_thread
# ok 1 sys_membarrier available
# ok 2 sys membarrier invalid command test: command = -1, flags = 0, errno = 22. Failed as expected
ok 2 selftests: membarrier: membarrier_test_multi_thread
+ok 3 # SKIP selftests: membarrier: membarrier_test_multi_thread
diff --git a/tools/testing/radix-tree/maple.c b/tools/testing/radix-tree/maple.c
index 172700fb7784..5c1b18e3ed21 100644
--- a/tools/testing/radix-tree/maple.c
+++ b/tools/testing/radix-tree/maple.c
@@ -8,14 +8,6 @@
* difficult to handle in kernel tests.
*/
-#define CONFIG_DEBUG_MAPLE_TREE
-#define CONFIG_MAPLE_SEARCH
-#define MAPLE_32BIT (MAPLE_NODE_SLOTS > 31)
-#include "test.h"
-#include <stdlib.h>
-#include <time.h>
-#include <linux/init.h>
-
#define module_init(x)
#define module_exit(x)
#define MODULE_AUTHOR(x)
@@ -23,7 +15,9 @@
#define MODULE_LICENSE(x)
#define dump_stack() assert(0)
-#include "../../../lib/maple_tree.c"
+#include "test.h"
+
+#include "../shared/maple-shim.c"
#include "../../../lib/test_maple_tree.c"
#define RCU_RANGE_COUNT 1000
@@ -63,430 +57,6 @@ struct rcu_reader_struct {
struct rcu_test_struct2 *test;
};
-static int get_alloc_node_count(struct ma_state *mas)
-{
- int count = 1;
- struct maple_alloc *node = mas->alloc;
-
- if (!node || ((unsigned long)node & 0x1))
- return 0;
- while (node->node_count) {
- count += node->node_count;
- node = node->slot[0];
- }
- return count;
-}
-
-static void check_mas_alloc_node_count(struct ma_state *mas)
-{
- mas_node_count_gfp(mas, MAPLE_ALLOC_SLOTS + 1, GFP_KERNEL);
- mas_node_count_gfp(mas, MAPLE_ALLOC_SLOTS + 3, GFP_KERNEL);
- MT_BUG_ON(mas->tree, get_alloc_node_count(mas) != mas->alloc->total);
- mas_destroy(mas);
-}
-
-/*
- * check_new_node() - Check the creation of new nodes and error path
- * verification.
- */
-static noinline void __init check_new_node(struct maple_tree *mt)
-{
-
- struct maple_node *mn, *mn2, *mn3;
- struct maple_alloc *smn;
- struct maple_node *nodes[100];
- int i, j, total;
-
- MA_STATE(mas, mt, 0, 0);
-
- check_mas_alloc_node_count(&mas);
-
- /* Try allocating 3 nodes */
- mtree_lock(mt);
- mt_set_non_kernel(0);
- /* request 3 nodes to be allocated. */
- mas_node_count(&mas, 3);
- /* Allocation request of 3. */
- MT_BUG_ON(mt, mas_alloc_req(&mas) != 3);
- /* Allocate failed. */
- MT_BUG_ON(mt, mas.node != MA_ERROR(-ENOMEM));
- MT_BUG_ON(mt, !mas_nomem(&mas, GFP_KERNEL));
-
- MT_BUG_ON(mt, mas_allocated(&mas) != 3);
- mn = mas_pop_node(&mas);
- MT_BUG_ON(mt, not_empty(mn));
- MT_BUG_ON(mt, mn == NULL);
- MT_BUG_ON(mt, mas.alloc == NULL);
- MT_BUG_ON(mt, mas.alloc->slot[0] == NULL);
- mas_push_node(&mas, mn);
- mas_reset(&mas);
- mas_destroy(&mas);
- mtree_unlock(mt);
-
-
- /* Try allocating 1 node, then 2 more */
- mtree_lock(mt);
- /* Set allocation request to 1. */
- mas_set_alloc_req(&mas, 1);
- /* Check Allocation request of 1. */
- MT_BUG_ON(mt, mas_alloc_req(&mas) != 1);
- mas_set_err(&mas, -ENOMEM);
- /* Validate allocation request. */
- MT_BUG_ON(mt, !mas_nomem(&mas, GFP_KERNEL));
- /* Eat the requested node. */
- mn = mas_pop_node(&mas);
- MT_BUG_ON(mt, not_empty(mn));
- MT_BUG_ON(mt, mn == NULL);
- MT_BUG_ON(mt, mn->slot[0] != NULL);
- MT_BUG_ON(mt, mn->slot[1] != NULL);
- MT_BUG_ON(mt, mas_allocated(&mas) != 0);
-
- mn->parent = ma_parent_ptr(mn);
- ma_free_rcu(mn);
- mas.status = ma_start;
- mas_destroy(&mas);
- /* Allocate 3 nodes, will fail. */
- mas_node_count(&mas, 3);
- /* Drop the lock and allocate 3 nodes. */
- mas_nomem(&mas, GFP_KERNEL);
- /* Ensure 3 are allocated. */
- MT_BUG_ON(mt, mas_allocated(&mas) != 3);
- /* Allocation request of 0. */
- MT_BUG_ON(mt, mas_alloc_req(&mas) != 0);
-
- MT_BUG_ON(mt, mas.alloc == NULL);
- MT_BUG_ON(mt, mas.alloc->slot[0] == NULL);
- MT_BUG_ON(mt, mas.alloc->slot[1] == NULL);
- /* Ensure we counted 3. */
- MT_BUG_ON(mt, mas_allocated(&mas) != 3);
- /* Free. */
- mas_reset(&mas);
- mas_destroy(&mas);
-
- /* Set allocation request to 1. */
- mas_set_alloc_req(&mas, 1);
- MT_BUG_ON(mt, mas_alloc_req(&mas) != 1);
- mas_set_err(&mas, -ENOMEM);
- /* Validate allocation request. */
- MT_BUG_ON(mt, !mas_nomem(&mas, GFP_KERNEL));
- MT_BUG_ON(mt, mas_allocated(&mas) != 1);
- /* Check the node is only one node. */
- mn = mas_pop_node(&mas);
- MT_BUG_ON(mt, not_empty(mn));
- MT_BUG_ON(mt, mas_allocated(&mas) != 0);
- MT_BUG_ON(mt, mn == NULL);
- MT_BUG_ON(mt, mn->slot[0] != NULL);
- MT_BUG_ON(mt, mn->slot[1] != NULL);
- MT_BUG_ON(mt, mas_allocated(&mas) != 0);
- mas_push_node(&mas, mn);
- MT_BUG_ON(mt, mas_allocated(&mas) != 1);
- MT_BUG_ON(mt, mas.alloc->node_count);
-
- mas_set_alloc_req(&mas, 2); /* request 2 more. */
- MT_BUG_ON(mt, mas_alloc_req(&mas) != 2);
- mas_set_err(&mas, -ENOMEM);
- MT_BUG_ON(mt, !mas_nomem(&mas, GFP_KERNEL));
- MT_BUG_ON(mt, mas_allocated(&mas) != 3);
- MT_BUG_ON(mt, mas.alloc == NULL);
- MT_BUG_ON(mt, mas.alloc->slot[0] == NULL);
- MT_BUG_ON(mt, mas.alloc->slot[1] == NULL);
- for (i = 2; i >= 0; i--) {
- mn = mas_pop_node(&mas);
- MT_BUG_ON(mt, mas_allocated(&mas) != i);
- MT_BUG_ON(mt, !mn);
- MT_BUG_ON(mt, not_empty(mn));
- mn->parent = ma_parent_ptr(mn);
- ma_free_rcu(mn);
- }
-
- total = 64;
- mas_set_alloc_req(&mas, total); /* request 2 more. */
- MT_BUG_ON(mt, mas_alloc_req(&mas) != total);
- mas_set_err(&mas, -ENOMEM);
- MT_BUG_ON(mt, !mas_nomem(&mas, GFP_KERNEL));
- for (i = total; i > 0; i--) {
- unsigned int e = 0; /* expected node_count */
-
- if (!MAPLE_32BIT) {
- if (i >= 35)
- e = i - 34;
- else if (i >= 5)
- e = i - 4;
- else if (i >= 2)
- e = i - 1;
- } else {
- if (i >= 4)
- e = i - 3;
- else if (i >= 1)
- e = i - 1;
- else
- e = 0;
- }
-
- MT_BUG_ON(mt, mas.alloc->node_count != e);
- mn = mas_pop_node(&mas);
- MT_BUG_ON(mt, not_empty(mn));
- MT_BUG_ON(mt, mas_allocated(&mas) != i - 1);
- MT_BUG_ON(mt, !mn);
- mn->parent = ma_parent_ptr(mn);
- ma_free_rcu(mn);
- }
-
- total = 100;
- for (i = 1; i < total; i++) {
- mas_set_alloc_req(&mas, i);
- mas_set_err(&mas, -ENOMEM);
- MT_BUG_ON(mt, !mas_nomem(&mas, GFP_KERNEL));
- for (j = i; j > 0; j--) {
- mn = mas_pop_node(&mas);
- MT_BUG_ON(mt, mas_allocated(&mas) != j - 1);
- MT_BUG_ON(mt, !mn);
- MT_BUG_ON(mt, not_empty(mn));
- mas_push_node(&mas, mn);
- MT_BUG_ON(mt, mas_allocated(&mas) != j);
- mn = mas_pop_node(&mas);
- MT_BUG_ON(mt, not_empty(mn));
- MT_BUG_ON(mt, mas_allocated(&mas) != j - 1);
- mn->parent = ma_parent_ptr(mn);
- ma_free_rcu(mn);
- }
- MT_BUG_ON(mt, mas_allocated(&mas) != 0);
-
- mas_set_alloc_req(&mas, i);
- mas_set_err(&mas, -ENOMEM);
- MT_BUG_ON(mt, !mas_nomem(&mas, GFP_KERNEL));
- for (j = 0; j <= i/2; j++) {
- MT_BUG_ON(mt, mas_allocated(&mas) != i - j);
- nodes[j] = mas_pop_node(&mas);
- MT_BUG_ON(mt, mas_allocated(&mas) != i - j - 1);
- }
-
- while (j) {
- j--;
- mas_push_node(&mas, nodes[j]);
- MT_BUG_ON(mt, mas_allocated(&mas) != i - j);
- }
- MT_BUG_ON(mt, mas_allocated(&mas) != i);
- for (j = 0; j <= i/2; j++) {
- MT_BUG_ON(mt, mas_allocated(&mas) != i - j);
- mn = mas_pop_node(&mas);
- MT_BUG_ON(mt, not_empty(mn));
- mn->parent = ma_parent_ptr(mn);
- ma_free_rcu(mn);
- MT_BUG_ON(mt, mas_allocated(&mas) != i - j - 1);
- }
- mas_reset(&mas);
- MT_BUG_ON(mt, mas_nomem(&mas, GFP_KERNEL));
- mas_destroy(&mas);
-
- }
-
- /* Set allocation request. */
- total = 500;
- mas_node_count(&mas, total);
- /* Drop the lock and allocate the nodes. */
- mas_nomem(&mas, GFP_KERNEL);
- MT_BUG_ON(mt, !mas.alloc);
- i = 1;
- smn = mas.alloc;
- while (i < total) {
- for (j = 0; j < MAPLE_ALLOC_SLOTS; j++) {
- i++;
- MT_BUG_ON(mt, !smn->slot[j]);
- if (i == total)
- break;
- }
- smn = smn->slot[0]; /* next. */
- }
- MT_BUG_ON(mt, mas_allocated(&mas) != total);
- mas_reset(&mas);
- mas_destroy(&mas); /* Free. */
-
- MT_BUG_ON(mt, mas_allocated(&mas) != 0);
- for (i = 1; i < 128; i++) {
- mas_node_count(&mas, i); /* Request */
- mas_nomem(&mas, GFP_KERNEL); /* Fill request */
- MT_BUG_ON(mt, mas_allocated(&mas) != i); /* check request filled */
- for (j = i; j > 0; j--) { /*Free the requests */
- mn = mas_pop_node(&mas); /* get the next node. */
- MT_BUG_ON(mt, mn == NULL);
- MT_BUG_ON(mt, not_empty(mn));
- mn->parent = ma_parent_ptr(mn);
- ma_free_rcu(mn);
- }
- MT_BUG_ON(mt, mas_allocated(&mas) != 0);
- }
-
- for (i = 1; i < MAPLE_NODE_MASK + 1; i++) {
- MA_STATE(mas2, mt, 0, 0);
- mas_node_count(&mas, i); /* Request */
- mas_nomem(&mas, GFP_KERNEL); /* Fill request */
- MT_BUG_ON(mt, mas_allocated(&mas) != i); /* check request filled */
- for (j = 1; j <= i; j++) { /* Move the allocations to mas2 */
- mn = mas_pop_node(&mas); /* get the next node. */
- MT_BUG_ON(mt, mn == NULL);
- MT_BUG_ON(mt, not_empty(mn));
- mas_push_node(&mas2, mn);
- MT_BUG_ON(mt, mas_allocated(&mas2) != j);
- }
- MT_BUG_ON(mt, mas_allocated(&mas) != 0);
- MT_BUG_ON(mt, mas_allocated(&mas2) != i);
-
- for (j = i; j > 0; j--) { /*Free the requests */
- MT_BUG_ON(mt, mas_allocated(&mas2) != j);
- mn = mas_pop_node(&mas2); /* get the next node. */
- MT_BUG_ON(mt, mn == NULL);
- MT_BUG_ON(mt, not_empty(mn));
- mn->parent = ma_parent_ptr(mn);
- ma_free_rcu(mn);
- }
- MT_BUG_ON(mt, mas_allocated(&mas2) != 0);
- }
-
-
- MT_BUG_ON(mt, mas_allocated(&mas) != 0);
- mas_node_count(&mas, MAPLE_ALLOC_SLOTS + 1); /* Request */
- MT_BUG_ON(mt, mas.node != MA_ERROR(-ENOMEM));
- MT_BUG_ON(mt, !mas_nomem(&mas, GFP_KERNEL));
- MT_BUG_ON(mt, mas_allocated(&mas) != MAPLE_ALLOC_SLOTS + 1);
- MT_BUG_ON(mt, mas.alloc->node_count != MAPLE_ALLOC_SLOTS);
-
- mn = mas_pop_node(&mas); /* get the next node. */
- MT_BUG_ON(mt, mn == NULL);
- MT_BUG_ON(mt, not_empty(mn));
- MT_BUG_ON(mt, mas_allocated(&mas) != MAPLE_ALLOC_SLOTS);
- MT_BUG_ON(mt, mas.alloc->node_count != MAPLE_ALLOC_SLOTS - 1);
-
- mas_push_node(&mas, mn);
- MT_BUG_ON(mt, mas_allocated(&mas) != MAPLE_ALLOC_SLOTS + 1);
- MT_BUG_ON(mt, mas.alloc->node_count != MAPLE_ALLOC_SLOTS);
-
- /* Check the limit of pop/push/pop */
- mas_node_count(&mas, MAPLE_ALLOC_SLOTS + 2); /* Request */
- MT_BUG_ON(mt, mas_alloc_req(&mas) != 1);
- MT_BUG_ON(mt, mas.node != MA_ERROR(-ENOMEM));
- MT_BUG_ON(mt, !mas_nomem(&mas, GFP_KERNEL));
- MT_BUG_ON(mt, mas_alloc_req(&mas));
- MT_BUG_ON(mt, mas.alloc->node_count != 1);
- MT_BUG_ON(mt, mas_allocated(&mas) != MAPLE_ALLOC_SLOTS + 2);
- mn = mas_pop_node(&mas);
- MT_BUG_ON(mt, not_empty(mn));
- MT_BUG_ON(mt, mas_allocated(&mas) != MAPLE_ALLOC_SLOTS + 1);
- MT_BUG_ON(mt, mas.alloc->node_count != MAPLE_ALLOC_SLOTS);
- mas_push_node(&mas, mn);
- MT_BUG_ON(mt, mas.alloc->node_count != 1);
- MT_BUG_ON(mt, mas_allocated(&mas) != MAPLE_ALLOC_SLOTS + 2);
- mn = mas_pop_node(&mas);
- MT_BUG_ON(mt, not_empty(mn));
- mn->parent = ma_parent_ptr(mn);
- ma_free_rcu(mn);
- for (i = 1; i <= MAPLE_ALLOC_SLOTS + 1; i++) {
- mn = mas_pop_node(&mas);
- MT_BUG_ON(mt, not_empty(mn));
- mn->parent = ma_parent_ptr(mn);
- ma_free_rcu(mn);
- }
- MT_BUG_ON(mt, mas_allocated(&mas) != 0);
-
-
- for (i = 3; i < MAPLE_NODE_MASK * 3; i++) {
- mas.node = MA_ERROR(-ENOMEM);
- mas_node_count(&mas, i); /* Request */
- mas_nomem(&mas, GFP_KERNEL); /* Fill request */
- mn = mas_pop_node(&mas); /* get the next node. */
- mas_push_node(&mas, mn); /* put it back */
- mas_destroy(&mas);
-
- mas.node = MA_ERROR(-ENOMEM);
- mas_node_count(&mas, i); /* Request */
- mas_nomem(&mas, GFP_KERNEL); /* Fill request */
- mn = mas_pop_node(&mas); /* get the next node. */
- mn2 = mas_pop_node(&mas); /* get the next node. */
- mas_push_node(&mas, mn); /* put them back */
- mas_push_node(&mas, mn2);
- mas_destroy(&mas);
-
- mas.node = MA_ERROR(-ENOMEM);
- mas_node_count(&mas, i); /* Request */
- mas_nomem(&mas, GFP_KERNEL); /* Fill request */
- mn = mas_pop_node(&mas); /* get the next node. */
- mn2 = mas_pop_node(&mas); /* get the next node. */
- mn3 = mas_pop_node(&mas); /* get the next node. */
- mas_push_node(&mas, mn); /* put them back */
- mas_push_node(&mas, mn2);
- mas_push_node(&mas, mn3);
- mas_destroy(&mas);
-
- mas.node = MA_ERROR(-ENOMEM);
- mas_node_count(&mas, i); /* Request */
- mas_nomem(&mas, GFP_KERNEL); /* Fill request */
- mn = mas_pop_node(&mas); /* get the next node. */
- mn->parent = ma_parent_ptr(mn);
- ma_free_rcu(mn);
- mas_destroy(&mas);
-
- mas.node = MA_ERROR(-ENOMEM);
- mas_node_count(&mas, i); /* Request */
- mas_nomem(&mas, GFP_KERNEL); /* Fill request */
- mn = mas_pop_node(&mas); /* get the next node. */
- mn->parent = ma_parent_ptr(mn);
- ma_free_rcu(mn);
- mn = mas_pop_node(&mas); /* get the next node. */
- mn->parent = ma_parent_ptr(mn);
- ma_free_rcu(mn);
- mn = mas_pop_node(&mas); /* get the next node. */
- mn->parent = ma_parent_ptr(mn);
- ma_free_rcu(mn);
- mas_destroy(&mas);
- }
-
- mas.node = MA_ERROR(-ENOMEM);
- mas_node_count(&mas, 5); /* Request */
- mas_nomem(&mas, GFP_KERNEL); /* Fill request */
- MT_BUG_ON(mt, mas_allocated(&mas) != 5);
- mas.node = MA_ERROR(-ENOMEM);
- mas_node_count(&mas, 10); /* Request */
- mas_nomem(&mas, GFP_KERNEL); /* Fill request */
- mas.status = ma_start;
- MT_BUG_ON(mt, mas_allocated(&mas) != 10);
- mas_destroy(&mas);
-
- mas.node = MA_ERROR(-ENOMEM);
- mas_node_count(&mas, MAPLE_ALLOC_SLOTS - 1); /* Request */
- mas_nomem(&mas, GFP_KERNEL); /* Fill request */
- MT_BUG_ON(mt, mas_allocated(&mas) != MAPLE_ALLOC_SLOTS - 1);
- mas.node = MA_ERROR(-ENOMEM);
- mas_node_count(&mas, 10 + MAPLE_ALLOC_SLOTS - 1); /* Request */
- mas_nomem(&mas, GFP_KERNEL); /* Fill request */
- mas.status = ma_start;
- MT_BUG_ON(mt, mas_allocated(&mas) != 10 + MAPLE_ALLOC_SLOTS - 1);
- mas_destroy(&mas);
-
- mas.node = MA_ERROR(-ENOMEM);
- mas_node_count(&mas, MAPLE_ALLOC_SLOTS + 1); /* Request */
- mas_nomem(&mas, GFP_KERNEL); /* Fill request */
- MT_BUG_ON(mt, mas_allocated(&mas) != MAPLE_ALLOC_SLOTS + 1);
- mas.node = MA_ERROR(-ENOMEM);
- mas_node_count(&mas, MAPLE_ALLOC_SLOTS * 2 + 2); /* Request */
- mas_nomem(&mas, GFP_KERNEL); /* Fill request */
- mas.status = ma_start;
- MT_BUG_ON(mt, mas_allocated(&mas) != MAPLE_ALLOC_SLOTS * 2 + 2);
- mas_destroy(&mas);
-
- mas.node = MA_ERROR(-ENOMEM);
- mas_node_count(&mas, MAPLE_ALLOC_SLOTS * 2 + 1); /* Request */
- mas_nomem(&mas, GFP_KERNEL); /* Fill request */
- MT_BUG_ON(mt, mas_allocated(&mas) != MAPLE_ALLOC_SLOTS * 2 + 1);
- mas.node = MA_ERROR(-ENOMEM);
- mas_node_count(&mas, MAPLE_ALLOC_SLOTS * 3 + 2); /* Request */
- mas_nomem(&mas, GFP_KERNEL); /* Fill request */
- mas.status = ma_start;
- MT_BUG_ON(mt, mas_allocated(&mas) != MAPLE_ALLOC_SLOTS * 3 + 2);
- mas_destroy(&mas);
-
- mtree_unlock(mt);
-}
-
/*
* Check erasing including RCU.
*/
@@ -35455,17 +35025,6 @@ static void check_dfs_preorder(struct maple_tree *mt)
MT_BUG_ON(mt, count != e);
mtree_destroy(mt);
- mt_init_flags(mt, MT_FLAGS_ALLOC_RANGE);
- mas_reset(&mas);
- mt_zero_nr_tallocated();
- mt_set_non_kernel(200);
- mas_expected_entries(&mas, max);
- for (count = 0; count <= max; count++) {
- mas.index = mas.last = count;
- mas_store(&mas, xa_mk_value(count));
- MT_BUG_ON(mt, mas_is_err(&mas));
- }
- mas_destroy(&mas);
rcu_barrier();
/*
* pr_info(" ->seq test of 0-%lu %luK in %d active (%d total)\n",
@@ -35524,6 +35083,18 @@ static unsigned char get_vacant_height(struct ma_wr_state *wr_mas, void *entry)
return vacant_height;
}
+static int mas_allocated(struct ma_state *mas)
+{
+ int total = 0;
+
+ if (mas->alloc)
+ total++;
+
+ if (mas->sheaf)
+ total += kmem_cache_sheaf_size(mas->sheaf);
+
+ return total;
+}
/* Preallocation testing */
static noinline void __init check_prealloc(struct maple_tree *mt)
{
@@ -35542,7 +35113,10 @@ static noinline void __init check_prealloc(struct maple_tree *mt)
/* Spanning store */
mas_set_range(&mas, 470, 500);
- MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0);
+
+ mas_wr_preallocate(&wr_mas, ptr);
+ MT_BUG_ON(mt, mas.store_type != wr_spanning_store);
+ MT_BUG_ON(mt, mas_is_err(&mas));
allocated = mas_allocated(&mas);
height = mas_mt_height(&mas);
vacant_height = get_vacant_height(&wr_mas, ptr);
@@ -35552,6 +35126,7 @@ static noinline void __init check_prealloc(struct maple_tree *mt)
allocated = mas_allocated(&mas);
MT_BUG_ON(mt, allocated != 0);
+ mas_wr_preallocate(&wr_mas, ptr);
MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0);
allocated = mas_allocated(&mas);
height = mas_mt_height(&mas);
@@ -35597,20 +35172,6 @@ static noinline void __init check_prealloc(struct maple_tree *mt)
height = mas_mt_height(&mas);
vacant_height = get_vacant_height(&wr_mas, ptr);
MT_BUG_ON(mt, allocated != 1 + (height - vacant_height) * 3);
- mn = mas_pop_node(&mas);
- MT_BUG_ON(mt, mas_allocated(&mas) != allocated - 1);
- mas_push_node(&mas, mn);
- MT_BUG_ON(mt, mas_allocated(&mas) != allocated);
- MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0);
- mas_destroy(&mas);
- allocated = mas_allocated(&mas);
- MT_BUG_ON(mt, allocated != 0);
-
- MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0);
- allocated = mas_allocated(&mas);
- height = mas_mt_height(&mas);
- vacant_height = get_vacant_height(&wr_mas, ptr);
- MT_BUG_ON(mt, allocated != 1 + (height - vacant_height) * 3);
mas_store_prealloc(&mas, ptr);
MT_BUG_ON(mt, mas_allocated(&mas) != 0);
@@ -36327,13 +35888,18 @@ extern void test_kmem_cache_bulk(void);
static inline void check_spanning_store_height(struct maple_tree *mt)
{
int index = 0;
+ int last = 140;
MA_STATE(mas, mt, 0, 0);
mas_lock(&mas);
while (mt_height(mt) != 3) {
mas_store_gfp(&mas, xa_mk_value(index), GFP_KERNEL);
mas_set(&mas, ++index);
}
- mas_set_range(&mas, 90, 140);
+
+ if (MAPLE_32BIT)
+ last = 155; /* 32 bit higher branching factor. */
+
+ mas_set_range(&mas, 90, last);
mas_store_gfp(&mas, xa_mk_value(index), GFP_KERNEL);
MT_BUG_ON(mt, mas_mt_height(&mas) != 2);
mas_unlock(&mas);
@@ -36406,11 +35972,17 @@ static void check_nomem_writer_race(struct maple_tree *mt)
check_load(mt, 6, xa_mk_value(0xC));
mtree_unlock(mt);
+ mt_set_non_kernel(0);
/* test for the same race but with mas_store_gfp() */
mtree_store_range(mt, 0, 5, xa_mk_value(0xA), GFP_KERNEL);
mtree_store_range(mt, 6, 10, NULL, GFP_KERNEL);
mas_set_range(&mas, 0, 5);
+
+ /* setup writer 2 that will trigger the race condition */
+ mt_set_private(mt);
+ mt_set_callback(writer2);
+
mtree_lock(mt);
mas_store_gfp(&mas, NULL, GFP_KERNEL);
@@ -36428,6 +36000,7 @@ static void check_nomem_writer_race(struct maple_tree *mt)
*/
static inline int check_vma_modification(struct maple_tree *mt)
{
+#if defined(CONFIG_64BIT)
MA_STATE(mas, mt, 0, 0);
mtree_lock(mt);
@@ -36451,30 +36024,11 @@ static inline int check_vma_modification(struct maple_tree *mt)
mas_destroy(&mas);
mtree_unlock(mt);
+#endif
+
return 0;
}
-/*
- * test to check that bulk stores do not use wr_rebalance as the store
- * type.
- */
-static inline void check_bulk_rebalance(struct maple_tree *mt)
-{
- MA_STATE(mas, mt, ULONG_MAX, ULONG_MAX);
- int max = 10;
-
- build_full_tree(mt, 0, 2);
-
- /* erase every entry in the tree */
- do {
- /* set up bulk store mode */
- mas_expected_entries(&mas, max);
- mas_erase(&mas);
- MT_BUG_ON(mt, mas.store_type == wr_rebalance);
- } while (mas_prev(&mas, 0) != NULL);
-
- mas_destroy(&mas);
-}
void farmer_tests(void)
{
@@ -36487,10 +36041,6 @@ void farmer_tests(void)
check_vma_modification(&tree);
mtree_destroy(&tree);
- mt_init(&tree);
- check_bulk_rebalance(&tree);
- mtree_destroy(&tree);
-
tree.ma_root = xa_mk_value(0);
mt_dump(&tree, mt_dump_dec);
@@ -36550,10 +36100,6 @@ void farmer_tests(void)
check_erase_testset(&tree);
mtree_destroy(&tree);
- mt_init_flags(&tree, 0);
- check_new_node(&tree);
- mtree_destroy(&tree);
-
if (!MAPLE_32BIT) {
mt_init_flags(&tree, MT_FLAGS_ALLOC_RANGE);
check_rcu_simulated(&tree);
diff --git a/tools/testing/scatterlist/linux/mm.h b/tools/testing/scatterlist/linux/mm.h
index 5bd9e6e80625..121ae78d6e88 100644
--- a/tools/testing/scatterlist/linux/mm.h
+++ b/tools/testing/scatterlist/linux/mm.h
@@ -51,7 +51,6 @@ static inline unsigned long page_to_phys(struct page *page)
#define page_to_pfn(page) ((unsigned long)(page) / PAGE_SIZE)
#define pfn_to_page(pfn) (void *)((pfn) * PAGE_SIZE)
-#define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n))
#define __min(t1, t2, min1, min2, x, y) ({ \
t1 min1 = (x); \
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index 030da61dbff3..a2d8e1093b00 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -314,7 +314,7 @@ gen_tar: install
@echo "Created ${TAR_PATH}"
clean:
- @for TARGET in $(TARGETS); do \
+ @for TARGET in $(TARGETS) $(INSTALL_DEP_TARGETS); do \
BUILD_TARGET=$$BUILD/$$TARGET; \
$(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET clean;\
done;
diff --git a/tools/testing/selftests/alsa/mixer-test.c b/tools/testing/selftests/alsa/mixer-test.c
index 2a4b2662035e..e113dafa5c24 100644
--- a/tools/testing/selftests/alsa/mixer-test.c
+++ b/tools/testing/selftests/alsa/mixer-test.c
@@ -53,10 +53,10 @@ struct ctl_data {
struct ctl_data *next;
};
-int num_cards = 0;
-int num_controls = 0;
-struct card_data *card_list = NULL;
-struct ctl_data *ctl_list = NULL;
+int num_cards;
+int num_controls;
+struct card_data *card_list;
+struct ctl_data *ctl_list;
static void find_controls(void)
{
diff --git a/tools/testing/selftests/alsa/pcm-test.c b/tools/testing/selftests/alsa/pcm-test.c
index dbd7c222ce93..ce92548670c8 100644
--- a/tools/testing/selftests/alsa/pcm-test.c
+++ b/tools/testing/selftests/alsa/pcm-test.c
@@ -30,7 +30,7 @@ struct card_data {
struct card_data *next;
};
-struct card_data *card_list = NULL;
+struct card_data *card_list;
struct pcm_data {
snd_pcm_t *handle;
@@ -43,10 +43,10 @@ struct pcm_data {
struct pcm_data *next;
};
-struct pcm_data *pcm_list = NULL;
+struct pcm_data *pcm_list;
-int num_missing = 0;
-struct pcm_data *pcm_missing = NULL;
+int num_missing;
+struct pcm_data *pcm_missing;
snd_config_t *default_pcm_config;
diff --git a/tools/testing/selftests/arm64/abi/hwcap.c b/tools/testing/selftests/arm64/abi/hwcap.c
index 002ec38a8bbb..3b96d090c5eb 100644
--- a/tools/testing/selftests/arm64/abi/hwcap.c
+++ b/tools/testing/selftests/arm64/abi/hwcap.c
@@ -17,6 +17,8 @@
#include <asm/sigcontext.h>
#include <asm/unistd.h>
+#include <linux/auxvec.h>
+
#include "../../kselftest.h"
#define TESTS_PER_HWCAP 3
@@ -55,7 +57,6 @@ static void cmpbr_sigill(void)
/* Not implemented, too complicated and unreliable anyway */
}
-
static void crc32_sigill(void)
{
/* CRC32W W0, W0, W1 */
@@ -169,6 +170,18 @@ static void lse128_sigill(void)
: "cc", "memory");
}
+static void lsfe_sigill(void)
+{
+ float __attribute__ ((aligned (16))) mem;
+ register float *memp asm ("x0") = &mem;
+
+ /* STFADD H0, [X0] */
+ asm volatile(".inst 0x7c20801f"
+ : "+r" (memp)
+ :
+ : "memory");
+}
+
static void lut_sigill(void)
{
/* LUTI2 V0.16B, { V0.16B }, V[0] */
@@ -763,6 +776,13 @@ static const struct hwcap_data {
.sigill_fn = lse128_sigill,
},
{
+ .name = "LSFE",
+ .at_hwcap = AT_HWCAP3,
+ .hwcap_bit = HWCAP3_LSFE,
+ .cpuinfo = "lsfe",
+ .sigill_fn = lsfe_sigill,
+ },
+ {
.name = "LUT",
.at_hwcap = AT_HWCAP2,
.hwcap_bit = HWCAP2_LUT,
diff --git a/tools/testing/selftests/arm64/abi/tpidr2.c b/tools/testing/selftests/arm64/abi/tpidr2.c
index f58a9f89b952..1703543fb7c7 100644
--- a/tools/testing/selftests/arm64/abi/tpidr2.c
+++ b/tools/testing/selftests/arm64/abi/tpidr2.c
@@ -182,16 +182,16 @@ static int write_clone_read(void)
}
for (;;) {
- waiting = wait4(ret, &status, __WCLONE, NULL);
+ waiting = waitpid(ret, &status, __WCLONE);
if (waiting < 0) {
if (errno == EINTR)
continue;
- ksft_print_msg("wait4() failed: %d\n", errno);
+ ksft_print_msg("waitpid() failed: %d\n", errno);
return 0;
}
if (waiting != ret) {
- ksft_print_msg("wait4() returned wrong PID %d\n",
+ ksft_print_msg("waitpid() returned wrong PID %d\n",
waiting);
return 0;
}
@@ -227,10 +227,10 @@ int main(int argc, char **argv)
ret = open("/proc/sys/abi/sme_default_vector_length", O_RDONLY, 0);
if (ret >= 0) {
ksft_test_result(default_value(), "default_value\n");
- ksft_test_result(write_read, "write_read\n");
- ksft_test_result(write_sleep_read, "write_sleep_read\n");
- ksft_test_result(write_fork_read, "write_fork_read\n");
- ksft_test_result(write_clone_read, "write_clone_read\n");
+ ksft_test_result(write_read(), "write_read\n");
+ ksft_test_result(write_sleep_read(), "write_sleep_read\n");
+ ksft_test_result(write_fork_read(), "write_fork_read\n");
+ ksft_test_result(write_clone_read(), "write_clone_read\n");
} else {
ksft_print_msg("SME support not present\n");
diff --git a/tools/testing/selftests/arm64/bti/assembler.h b/tools/testing/selftests/arm64/bti/assembler.h
index 04e7b72880ef..141cdcbf0b8f 100644
--- a/tools/testing/selftests/arm64/bti/assembler.h
+++ b/tools/testing/selftests/arm64/bti/assembler.h
@@ -14,7 +14,6 @@
#define GNU_PROPERTY_AARCH64_FEATURE_1_BTI (1U << 0)
#define GNU_PROPERTY_AARCH64_FEATURE_1_PAC (1U << 1)
-
.macro startfn name:req
.globl \name
\name:
diff --git a/tools/testing/selftests/arm64/fp/fp-ptrace.c b/tools/testing/selftests/arm64/fp/fp-ptrace.c
index cdd7a45c045d..a85c19e9524e 100644
--- a/tools/testing/selftests/arm64/fp/fp-ptrace.c
+++ b/tools/testing/selftests/arm64/fp/fp-ptrace.c
@@ -1568,7 +1568,6 @@ static void run_sve_tests(void)
&test_config);
}
}
-
}
static void run_sme_tests(void)
diff --git a/tools/testing/selftests/arm64/fp/fp-stress.c b/tools/testing/selftests/arm64/fp/fp-stress.c
index 74e23208b94c..9349aa630c84 100644
--- a/tools/testing/selftests/arm64/fp/fp-stress.c
+++ b/tools/testing/selftests/arm64/fp/fp-stress.c
@@ -105,8 +105,8 @@ static void child_start(struct child_data *child, const char *program)
/*
* Read from the startup pipe, there should be no data
- * and we should block until it is closed. We just
- * carry on on error since this isn't super critical.
+ * and we should block until it is closed. We just
+ * carry-on on error since this isn't super critical.
*/
ret = read(3, &i, sizeof(i));
if (ret < 0)
@@ -549,7 +549,7 @@ int main(int argc, char **argv)
evs = calloc(tests, sizeof(*evs));
if (!evs)
- ksft_exit_fail_msg("Failed to allocated %d epoll events\n",
+ ksft_exit_fail_msg("Failed to allocate %d epoll events\n",
tests);
for (i = 0; i < cpus; i++) {
diff --git a/tools/testing/selftests/arm64/fp/kernel-test.c b/tools/testing/selftests/arm64/fp/kernel-test.c
index e3cec3723ffa..0c40007d1282 100644
--- a/tools/testing/selftests/arm64/fp/kernel-test.c
+++ b/tools/testing/selftests/arm64/fp/kernel-test.c
@@ -188,13 +188,13 @@ static bool create_socket(void)
ref = malloc(digest_len);
if (!ref) {
- printf("Failed to allocated %d byte reference\n", digest_len);
+ printf("Failed to allocate %d byte reference\n", digest_len);
return false;
}
digest = malloc(digest_len);
if (!digest) {
- printf("Failed to allocated %d byte digest\n", digest_len);
+ printf("Failed to allocate %d byte digest\n", digest_len);
return false;
}
diff --git a/tools/testing/selftests/arm64/fp/sve-ptrace.c b/tools/testing/selftests/arm64/fp/sve-ptrace.c
index b22303778fb0..e0fc3a001e28 100644
--- a/tools/testing/selftests/arm64/fp/sve-ptrace.c
+++ b/tools/testing/selftests/arm64/fp/sve-ptrace.c
@@ -66,7 +66,7 @@ static const struct vec_type vec_types[] = {
};
#define VL_TESTS (((TEST_VQ_MAX - SVE_VQ_MIN) + 1) * 4)
-#define FLAG_TESTS 2
+#define FLAG_TESTS 4
#define FPSIMD_TESTS 2
#define EXPECTED_TESTS ((VL_TESTS + FLAG_TESTS + FPSIMD_TESTS) * ARRAY_SIZE(vec_types))
@@ -95,19 +95,27 @@ static int do_child(void)
static int get_fpsimd(pid_t pid, struct user_fpsimd_state *fpsimd)
{
struct iovec iov;
+ int ret;
iov.iov_base = fpsimd;
iov.iov_len = sizeof(*fpsimd);
- return ptrace(PTRACE_GETREGSET, pid, NT_PRFPREG, &iov);
+ ret = ptrace(PTRACE_GETREGSET, pid, NT_PRFPREG, &iov);
+ if (ret == -1)
+ ksft_perror("ptrace(PTRACE_GETREGSET)");
+ return ret;
}
static int set_fpsimd(pid_t pid, struct user_fpsimd_state *fpsimd)
{
struct iovec iov;
+ int ret;
iov.iov_base = fpsimd;
iov.iov_len = sizeof(*fpsimd);
- return ptrace(PTRACE_SETREGSET, pid, NT_PRFPREG, &iov);
+ ret = ptrace(PTRACE_SETREGSET, pid, NT_PRFPREG, &iov);
+ if (ret == -1)
+ ksft_perror("ptrace(PTRACE_SETREGSET)");
+ return ret;
}
static struct user_sve_header *get_sve(pid_t pid, const struct vec_type *type,
@@ -115,8 +123,9 @@ static struct user_sve_header *get_sve(pid_t pid, const struct vec_type *type,
{
struct user_sve_header *sve;
void *p;
- size_t sz = sizeof *sve;
+ size_t sz = sizeof(*sve);
struct iovec iov;
+ int ret;
while (1) {
if (*size < sz) {
@@ -132,8 +141,11 @@ static struct user_sve_header *get_sve(pid_t pid, const struct vec_type *type,
iov.iov_base = *buf;
iov.iov_len = sz;
- if (ptrace(PTRACE_GETREGSET, pid, type->regset, &iov))
+ ret = ptrace(PTRACE_GETREGSET, pid, type->regset, &iov);
+ if (ret) {
+ ksft_perror("ptrace(PTRACE_GETREGSET)");
goto error;
+ }
sve = *buf;
if (sve->size <= sz)
@@ -152,10 +164,46 @@ static int set_sve(pid_t pid, const struct vec_type *type,
const struct user_sve_header *sve)
{
struct iovec iov;
+ int ret;
iov.iov_base = (void *)sve;
iov.iov_len = sve->size;
- return ptrace(PTRACE_SETREGSET, pid, type->regset, &iov);
+ ret = ptrace(PTRACE_SETREGSET, pid, type->regset, &iov);
+ if (ret == -1)
+ ksft_perror("ptrace(PTRACE_SETREGSET)");
+ return ret;
+}
+
+/* A read operation fails */
+static void read_fails(pid_t child, const struct vec_type *type)
+{
+ struct user_sve_header *new_sve = NULL;
+ size_t new_sve_size = 0;
+ void *ret;
+
+ ret = get_sve(child, type, (void **)&new_sve, &new_sve_size);
+
+ ksft_test_result(ret == NULL, "%s unsupported read fails\n",
+ type->name);
+
+ free(new_sve);
+}
+
+/* A write operation fails */
+static void write_fails(pid_t child, const struct vec_type *type)
+{
+ struct user_sve_header sve;
+ int ret;
+
+ /* Just the header, no data */
+ memset(&sve, 0, sizeof(sve));
+ sve.size = sizeof(sve);
+ sve.flags = SVE_PT_REGS_SVE;
+ sve.vl = SVE_VL_MIN;
+ ret = set_sve(child, type, &sve);
+
+ ksft_test_result(ret != 0, "%s unsupported write fails\n",
+ type->name);
}
/* Validate setting and getting the inherit flag */
@@ -270,6 +318,25 @@ static void check_u32(unsigned int vl, const char *reg,
}
}
+/* Set out of range VLs */
+static void ptrace_set_vl_ranges(pid_t child, const struct vec_type *type)
+{
+ struct user_sve_header sve;
+ int ret;
+
+ memset(&sve, 0, sizeof(sve));
+ sve.flags = SVE_PT_REGS_SVE;
+ sve.size = sizeof(sve);
+
+ ret = set_sve(child, type, &sve);
+ ksft_test_result(ret != 0, "%s Set invalid VL 0\n", type->name);
+
+ sve.vl = SVE_VL_MAX + SVE_VQ_BYTES;
+ ret = set_sve(child, type, &sve);
+ ksft_test_result(ret != 0, "%s Set invalid VL %d\n", type->name,
+ SVE_VL_MAX + SVE_VQ_BYTES);
+}
+
/* Access the FPSIMD registers via the SVE regset */
static void ptrace_sve_fpsimd(pid_t child, const struct vec_type *type)
{
@@ -683,6 +750,20 @@ static int do_parent(pid_t child)
}
for (i = 0; i < ARRAY_SIZE(vec_types); i++) {
+ /*
+ * If the vector type isn't supported reads and writes
+ * should fail.
+ */
+ if (!(getauxval(vec_types[i].hwcap_type) & vec_types[i].hwcap)) {
+ read_fails(child, &vec_types[i]);
+ write_fails(child, &vec_types[i]);
+ } else {
+ ksft_test_result_skip("%s unsupported read fails\n",
+ vec_types[i].name);
+ ksft_test_result_skip("%s unsupported write fails\n",
+ vec_types[i].name);
+ }
+
/* FPSIMD via SVE regset */
if (getauxval(vec_types[i].hwcap_type) & vec_types[i].hwcap) {
ptrace_sve_fpsimd(child, &vec_types[i]);
@@ -703,6 +784,17 @@ static int do_parent(pid_t child)
vec_types[i].name);
}
+ /* Setting out of bounds VLs should fail */
+ if (getauxval(vec_types[i].hwcap_type) & vec_types[i].hwcap) {
+ ptrace_set_vl_ranges(child, &vec_types[i]);
+ } else {
+ ksft_test_result_skip("%s Set invalid VL 0\n",
+ vec_types[i].name);
+ ksft_test_result_skip("%s Set invalid VL %d\n",
+ vec_types[i].name,
+ SVE_VL_MAX + SVE_VQ_BYTES);
+ }
+
/* Step through every possible VQ */
for (vq = SVE_VQ_MIN; vq <= TEST_VQ_MAX; vq++) {
vl = sve_vl_from_vq(vq);
diff --git a/tools/testing/selftests/arm64/fp/vec-syscfg.c b/tools/testing/selftests/arm64/fp/vec-syscfg.c
index ea9c7d47790f..2d75d342eeb9 100644
--- a/tools/testing/selftests/arm64/fp/vec-syscfg.c
+++ b/tools/testing/selftests/arm64/fp/vec-syscfg.c
@@ -690,7 +690,6 @@ static inline void smstop(void)
asm volatile("msr S0_3_C4_C6_3, xzr");
}
-
/*
* Verify we can change the SVE vector length while SME is active and
* continue to use SME afterwards.
diff --git a/tools/testing/selftests/arm64/fp/zt-ptrace.c b/tools/testing/selftests/arm64/fp/zt-ptrace.c
index 584b8d59b7ea..a7f34040fbf1 100644
--- a/tools/testing/selftests/arm64/fp/zt-ptrace.c
+++ b/tools/testing/selftests/arm64/fp/zt-ptrace.c
@@ -108,7 +108,6 @@ static int get_zt(pid_t pid, char zt[ZT_SIG_REG_BYTES])
return ptrace(PTRACE_GETREGSET, pid, NT_ARM_ZT, &iov);
}
-
static int set_zt(pid_t pid, const char zt[ZT_SIG_REG_BYTES])
{
struct iovec iov;
diff --git a/tools/testing/selftests/arm64/gcs/Makefile b/tools/testing/selftests/arm64/gcs/Makefile
index d2f3497a9103..1fbbf0ca1f02 100644
--- a/tools/testing/selftests/arm64/gcs/Makefile
+++ b/tools/testing/selftests/arm64/gcs/Makefile
@@ -14,11 +14,11 @@ LDLIBS+=-lpthread
include ../../lib.mk
$(OUTPUT)/basic-gcs: basic-gcs.c
- $(CC) -g -fno-asynchronous-unwind-tables -fno-ident -s -Os -nostdlib \
- -static -include ../../../../include/nolibc/nolibc.h \
+ $(CC) $(CFLAGS) -fno-asynchronous-unwind-tables -fno-ident -s -nostdlib -nostdinc \
+ -static -I../../../../include/nolibc -include ../../../../include/nolibc/nolibc.h \
-I../../../../../usr/include \
-std=gnu99 -I../.. -g \
- -ffreestanding -Wall $^ -o $@ -lgcc
+ -ffreestanding $^ -o $@ -lgcc
$(OUTPUT)/gcs-stress-thread: gcs-stress-thread.S
$(CC) -nostdlib $^ -o $@
diff --git a/tools/testing/selftests/arm64/gcs/basic-gcs.c b/tools/testing/selftests/arm64/gcs/basic-gcs.c
index 54f9c888249d..250977abc398 100644
--- a/tools/testing/selftests/arm64/gcs/basic-gcs.c
+++ b/tools/testing/selftests/arm64/gcs/basic-gcs.c
@@ -10,6 +10,7 @@
#include <sys/mman.h>
#include <asm/mman.h>
+#include <asm/hwcap.h>
#include <linux/sched.h>
#include "kselftest.h"
@@ -386,14 +387,13 @@ int main(void)
ksft_print_header();
- /*
- * We don't have getauxval() with nolibc so treat a failure to
- * read GCS state as a lack of support and skip.
- */
+ if (!(getauxval(AT_HWCAP) & HWCAP_GCS))
+ ksft_exit_skip("SKIP GCS not supported\n");
+
ret = my_syscall5(__NR_prctl, PR_GET_SHADOW_STACK_STATUS,
&gcs_mode, 0, 0, 0);
if (ret != 0)
- ksft_exit_skip("Failed to read GCS state: %d\n", ret);
+ ksft_exit_fail_msg("Failed to read GCS state: %d\n", ret);
if (!(gcs_mode & PR_SHADOW_STACK_ENABLE)) {
gcs_mode = PR_SHADOW_STACK_ENABLE;
@@ -410,7 +410,7 @@ int main(void)
}
/* One last test: disable GCS, we can do this one time */
- my_syscall5(__NR_prctl, PR_SET_SHADOW_STACK_STATUS, 0, 0, 0, 0);
+ ret = my_syscall5(__NR_prctl, PR_SET_SHADOW_STACK_STATUS, 0, 0, 0, 0);
if (ret != 0)
ksft_print_msg("Failed to disable GCS: %d\n", ret);
diff --git a/tools/testing/selftests/arm64/gcs/gcs-locking.c b/tools/testing/selftests/arm64/gcs/gcs-locking.c
index 989f75a491b7..1e6abb136ffd 100644
--- a/tools/testing/selftests/arm64/gcs/gcs-locking.c
+++ b/tools/testing/selftests/arm64/gcs/gcs-locking.c
@@ -165,7 +165,6 @@ TEST_F(valid_modes, lock_enable_disable_others)
ASSERT_EQ(ret, 0);
ASSERT_EQ(mode, PR_SHADOW_STACK_ALL_MODES);
-
ret = my_syscall2(__NR_prctl, PR_SET_SHADOW_STACK_STATUS,
variant->mode);
ASSERT_EQ(ret, 0);
diff --git a/tools/testing/selftests/arm64/gcs/gcs-stress.c b/tools/testing/selftests/arm64/gcs/gcs-stress.c
index bbc7f4950c13..cf316d78ea97 100644
--- a/tools/testing/selftests/arm64/gcs/gcs-stress.c
+++ b/tools/testing/selftests/arm64/gcs/gcs-stress.c
@@ -433,7 +433,7 @@ int main(int argc, char **argv)
evs = calloc(tests, sizeof(*evs));
if (!evs)
- ksft_exit_fail_msg("Failed to allocated %d epoll events\n",
+ ksft_exit_fail_msg("Failed to allocate %d epoll events\n",
tests);
for (i = 0; i < gcs_threads; i++)
diff --git a/tools/testing/selftests/arm64/pauth/exec_target.c b/tools/testing/selftests/arm64/pauth/exec_target.c
index 4435600ca400..e597861b26d6 100644
--- a/tools/testing/selftests/arm64/pauth/exec_target.c
+++ b/tools/testing/selftests/arm64/pauth/exec_target.c
@@ -13,7 +13,12 @@ int main(void)
unsigned long hwcaps;
size_t val;
- fread(&val, sizeof(size_t), 1, stdin);
+ size_t size = fread(&val, sizeof(size_t), 1, stdin);
+
+ if (size != 1) {
+ fprintf(stderr, "Could not read input from stdin\n");
+ return EXIT_FAILURE;
+ }
/* don't try to execute illegal (unimplemented) instructions) caller
* should have checked this and keep worker simple
diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index 3d8378972d26..be1ee7ba7ce0 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -44,3 +44,4 @@ xdp_redirect_multi
xdp_synproxy
xdp_hw_metadata
xdp_features
+verification_cert.h
diff --git a/tools/testing/selftests/bpf/DENYLIST.s390x b/tools/testing/selftests/bpf/DENYLIST.s390x
index 3ebd77206f98..a17baf8c6fd7 100644
--- a/tools/testing/selftests/bpf/DENYLIST.s390x
+++ b/tools/testing/selftests/bpf/DENYLIST.s390x
@@ -2,4 +2,3 @@
# Alphabetical order
get_stack_raw_tp # user_stack corrupted user stack (no backchain userspace)
stacktrace_build_id # compare_map_keys stackid_hmap vs. stackmap err -2 errno 2 (?)
-verifier_iterating_callbacks
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 4863106034df..f00587d4ede6 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -120,7 +120,7 @@ TEST_PROGS_EXTENDED := \
test_bpftool.py
TEST_KMODS := bpf_testmod.ko bpf_test_no_cfi.ko bpf_test_modorder_x.ko \
- bpf_test_modorder_y.ko
+ bpf_test_modorder_y.ko bpf_test_rqspinlock.ko
TEST_KMOD_TARGETS = $(addprefix $(OUTPUT)/,$(TEST_KMODS))
# Compile but not part of 'make run_tests'
@@ -137,7 +137,7 @@ TEST_GEN_PROGS_EXTENDED = \
xdping \
xskxceiver
-TEST_GEN_FILES += liburandom_read.so urandom_read sign-file uprobe_multi
+TEST_GEN_FILES += $(TEST_KMODS) liburandom_read.so urandom_read sign-file uprobe_multi
ifneq ($(V),1)
submake_extras := feature_display=0
@@ -398,7 +398,7 @@ $(HOST_BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile) \
DESTDIR=$(HOST_SCRATCH_DIR)/ prefix= all install_headers
endif
-# vmlinux.h is first dumped to a temprorary file and then compared to
+# vmlinux.h is first dumped to a temporary file and then compared to
# the previous version. This helps to avoid unnecessary re-builds of
# $(TRUNNER_BPF_OBJS)
$(INCLUDE_DIR)/vmlinux.h: $(VMLINUX_BTF) $(BPFTOOL) | $(INCLUDE_DIR)
@@ -496,15 +496,16 @@ LINKED_SKELS := test_static_linked.skel.h linked_funcs.skel.h \
test_subskeleton.skel.h test_subskeleton_lib.skel.h \
test_usdt.skel.h
-LSKELS := fentry_test.c fexit_test.c fexit_sleep.c atomics.c \
- trace_printk.c trace_vprintk.c map_ptr_kern.c \
+LSKELS := fexit_sleep.c trace_printk.c trace_vprintk.c map_ptr_kern.c \
core_kern.c core_kern_overflow.c test_ringbuf.c \
test_ringbuf_n.c test_ringbuf_map_key.c test_ringbuf_write.c
+LSKELS_SIGNED := fentry_test.c fexit_test.c atomics.c
+
# Generate both light skeleton and libbpf skeleton for these
LSKELS_EXTRA := test_ksyms_module.c test_ksyms_weak.c kfunc_call_test.c \
kfunc_call_test_subprog.c
-SKEL_BLACKLIST += $$(LSKELS)
+SKEL_BLACKLIST += $$(LSKELS) $$(LSKELS_SIGNED)
test_static_linked.skel.h-deps := test_static_linked1.bpf.o test_static_linked2.bpf.o
linked_funcs.skel.h-deps := linked_funcs1.bpf.o linked_funcs2.bpf.o
@@ -535,6 +536,7 @@ HEADERS_FOR_BPF_OBJS := $(wildcard $(BPFDIR)/*.bpf.h) \
# $2 - test runner extra "flavor" (e.g., no_alu32, cpuv4, bpf_gcc, etc)
define DEFINE_TEST_RUNNER
+LSKEL_SIGN := -S -k $(PRIVATE_KEY) -i $(VERIFICATION_CERT)
TRUNNER_OUTPUT := $(OUTPUT)$(if $2,/)$2
TRUNNER_BINARY := $1$(if $2,-)$2
TRUNNER_TEST_OBJS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.test.o, \
@@ -550,6 +552,7 @@ TRUNNER_BPF_SKELS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.skel.h, \
$$(TRUNNER_BPF_SRCS)))
TRUNNER_BPF_LSKELS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.lskel.h, $$(LSKELS) $$(LSKELS_EXTRA))
TRUNNER_BPF_SKELS_LINKED := $$(addprefix $$(TRUNNER_OUTPUT)/,$(LINKED_SKELS))
+TRUNNER_BPF_LSKELS_SIGNED := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.lskel.h, $$(LSKELS_SIGNED))
TEST_GEN_FILES += $$(TRUNNER_BPF_OBJS)
# Evaluate rules now with extra TRUNNER_XXX variables above already defined
@@ -604,6 +607,15 @@ $(TRUNNER_BPF_LSKELS): %.lskel.h: %.bpf.o $(BPFTOOL) | $(TRUNNER_OUTPUT)
$(Q)$$(BPFTOOL) gen skeleton -L $$(<:.o=.llinked3.o) name $$(notdir $$(<:.bpf.o=_lskel)) > $$@
$(Q)rm -f $$(<:.o=.llinked1.o) $$(<:.o=.llinked2.o) $$(<:.o=.llinked3.o)
+$(TRUNNER_BPF_LSKELS_SIGNED): %.lskel.h: %.bpf.o $(BPFTOOL) | $(TRUNNER_OUTPUT)
+ $$(call msg,GEN-SKEL,$(TRUNNER_BINARY) (signed),$$@)
+ $(Q)$$(BPFTOOL) gen object $$(<:.o=.llinked1.o) $$<
+ $(Q)$$(BPFTOOL) gen object $$(<:.o=.llinked2.o) $$(<:.o=.llinked1.o)
+ $(Q)$$(BPFTOOL) gen object $$(<:.o=.llinked3.o) $$(<:.o=.llinked2.o)
+ $(Q)diff $$(<:.o=.llinked2.o) $$(<:.o=.llinked3.o)
+ $(Q)$$(BPFTOOL) gen skeleton $(LSKEL_SIGN) $$(<:.o=.llinked3.o) name $$(notdir $$(<:.bpf.o=_lskel)) > $$@
+ $(Q)rm -f $$(<:.o=.llinked1.o) $$(<:.o=.llinked2.o) $$(<:.o=.llinked3.o)
+
$(LINKED_BPF_OBJS): %: $(TRUNNER_OUTPUT)/%
# .SECONDEXPANSION here allows to correctly expand %-deps variables as prerequisites
@@ -653,6 +665,7 @@ $(TRUNNER_TEST_OBJS:.o=.d): $(TRUNNER_OUTPUT)/%.test.d: \
$(TRUNNER_EXTRA_HDRS) \
$(TRUNNER_BPF_SKELS) \
$(TRUNNER_BPF_LSKELS) \
+ $(TRUNNER_BPF_LSKELS_SIGNED) \
$(TRUNNER_BPF_SKELS_LINKED) \
$$(BPFOBJ) | $(TRUNNER_OUTPUT)
@@ -667,6 +680,7 @@ $(foreach N,$(patsubst $(TRUNNER_OUTPUT)/%.o,%,$(TRUNNER_EXTRA_OBJS)), \
$(TRUNNER_EXTRA_OBJS): $(TRUNNER_OUTPUT)/%.o: \
%.c \
$(TRUNNER_EXTRA_HDRS) \
+ $(VERIFY_SIG_HDR) \
$(TRUNNER_TESTS_HDR) \
$$(BPFOBJ) | $(TRUNNER_OUTPUT)
$$(call msg,EXT-OBJ,$(TRUNNER_BINARY),$$@)
@@ -697,6 +711,18 @@ $(OUTPUT)/$(TRUNNER_BINARY): $(TRUNNER_TEST_OBJS) \
endef
+VERIFY_SIG_SETUP := $(CURDIR)/verify_sig_setup.sh
+VERIFY_SIG_HDR := verification_cert.h
+VERIFICATION_CERT := $(BUILD_DIR)/signing_key.der
+PRIVATE_KEY := $(BUILD_DIR)/signing_key.pem
+
+$(VERIFICATION_CERT) $(PRIVATE_KEY): $(VERIFY_SIG_SETUP)
+ $(Q)mkdir -p $(BUILD_DIR)
+ $(Q)$(VERIFY_SIG_SETUP) genkey $(BUILD_DIR)
+
+$(VERIFY_SIG_HDR): $(VERIFICATION_CERT)
+ $(Q)xxd -i -n test_progs_verification_cert $< > $@
+
# Define test_progs test runner.
TRUNNER_TESTS_DIR := prog_tests
TRUNNER_BPF_PROGS_DIR := progs
@@ -716,6 +742,7 @@ TRUNNER_EXTRA_SOURCES := test_progs.c \
disasm.c \
disasm_helpers.c \
json_writer.c \
+ $(VERIFY_SIG_HDR) \
flow_dissector_load.h \
ip_check_defrag_frags.h
TRUNNER_EXTRA_FILES := $(OUTPUT)/urandom_read \
@@ -725,7 +752,7 @@ TRUNNER_EXTRA_FILES := $(OUTPUT)/urandom_read \
$(OUTPUT)/uprobe_multi \
$(TEST_KMOD_TARGETS) \
ima_setup.sh \
- verify_sig_setup.sh \
+ $(VERIFY_SIG_SETUP) \
$(wildcard progs/btf_dump_test_case_*.c) \
$(wildcard progs/*.bpf.o)
TRUNNER_BPF_BUILD_RULE := CLANG_BPF_BUILD_RULE
@@ -816,6 +843,7 @@ $(OUTPUT)/bench_bpf_hashmap_lookup.o: $(OUTPUT)/bpf_hashmap_lookup.skel.h
$(OUTPUT)/bench_htab_mem.o: $(OUTPUT)/htab_mem_bench.skel.h
$(OUTPUT)/bench_bpf_crypto.o: $(OUTPUT)/crypto_bench.skel.h
$(OUTPUT)/bench_sockmap.o: $(OUTPUT)/bench_sockmap_prog.skel.h
+$(OUTPUT)/bench_lpm_trie_map.o: $(OUTPUT)/lpm_trie_bench.skel.h $(OUTPUT)/lpm_trie_map.skel.h
$(OUTPUT)/bench.o: bench.h testing_helpers.h $(BPFOBJ)
$(OUTPUT)/bench: LDLIBS += -lm
$(OUTPUT)/bench: $(OUTPUT)/bench.o \
@@ -837,6 +865,7 @@ $(OUTPUT)/bench: $(OUTPUT)/bench.o \
$(OUTPUT)/bench_htab_mem.o \
$(OUTPUT)/bench_bpf_crypto.o \
$(OUTPUT)/bench_sockmap.o \
+ $(OUTPUT)/bench_lpm_trie_map.o \
#
$(call msg,BINARY,,$@)
$(Q)$(CC) $(CFLAGS) $(LDFLAGS) $(filter %.a %.o,$^) $(LDLIBS) -o $@
diff --git a/tools/testing/selftests/bpf/bench.c b/tools/testing/selftests/bpf/bench.c
index ddd73d06a1eb..bd29bb2e6cb5 100644
--- a/tools/testing/selftests/bpf/bench.c
+++ b/tools/testing/selftests/bpf/bench.c
@@ -284,6 +284,7 @@ extern struct argp bench_htab_mem_argp;
extern struct argp bench_trigger_batch_argp;
extern struct argp bench_crypto_argp;
extern struct argp bench_sockmap_argp;
+extern struct argp bench_lpm_trie_map_argp;
static const struct argp_child bench_parsers[] = {
{ &bench_ringbufs_argp, 0, "Ring buffers benchmark", 0 },
@@ -299,6 +300,7 @@ static const struct argp_child bench_parsers[] = {
{ &bench_trigger_batch_argp, 0, "BPF triggering benchmark", 0 },
{ &bench_crypto_argp, 0, "bpf crypto benchmark", 0 },
{ &bench_sockmap_argp, 0, "bpf sockmap benchmark", 0 },
+ { &bench_lpm_trie_map_argp, 0, "LPM trie map benchmark", 0 },
{},
};
@@ -499,7 +501,7 @@ extern const struct bench bench_rename_rawtp;
extern const struct bench bench_rename_fentry;
extern const struct bench bench_rename_fexit;
-/* pure counting benchmarks to establish theoretical lmits */
+/* pure counting benchmarks to establish theoretical limits */
extern const struct bench bench_trig_usermode_count;
extern const struct bench bench_trig_syscall_count;
extern const struct bench bench_trig_kernel_count;
@@ -510,6 +512,8 @@ extern const struct bench bench_trig_kretprobe;
extern const struct bench bench_trig_kprobe_multi;
extern const struct bench bench_trig_kretprobe_multi;
extern const struct bench bench_trig_fentry;
+extern const struct bench bench_trig_kprobe_multi_all;
+extern const struct bench bench_trig_kretprobe_multi_all;
extern const struct bench bench_trig_fexit;
extern const struct bench bench_trig_fmodret;
extern const struct bench bench_trig_tp;
@@ -558,6 +562,13 @@ extern const struct bench bench_htab_mem;
extern const struct bench bench_crypto_encrypt;
extern const struct bench bench_crypto_decrypt;
extern const struct bench bench_sockmap;
+extern const struct bench bench_lpm_trie_noop;
+extern const struct bench bench_lpm_trie_baseline;
+extern const struct bench bench_lpm_trie_lookup;
+extern const struct bench bench_lpm_trie_insert;
+extern const struct bench bench_lpm_trie_update;
+extern const struct bench bench_lpm_trie_delete;
+extern const struct bench bench_lpm_trie_free;
static const struct bench *benchs[] = {
&bench_count_global,
@@ -578,6 +589,8 @@ static const struct bench *benchs[] = {
&bench_trig_kprobe_multi,
&bench_trig_kretprobe_multi,
&bench_trig_fentry,
+ &bench_trig_kprobe_multi_all,
+ &bench_trig_kretprobe_multi_all,
&bench_trig_fexit,
&bench_trig_fmodret,
&bench_trig_tp,
@@ -625,6 +638,13 @@ static const struct bench *benchs[] = {
&bench_crypto_encrypt,
&bench_crypto_decrypt,
&bench_sockmap,
+ &bench_lpm_trie_noop,
+ &bench_lpm_trie_baseline,
+ &bench_lpm_trie_lookup,
+ &bench_lpm_trie_insert,
+ &bench_lpm_trie_update,
+ &bench_lpm_trie_delete,
+ &bench_lpm_trie_free,
};
static void find_benchmark(void)
diff --git a/tools/testing/selftests/bpf/bench.h b/tools/testing/selftests/bpf/bench.h
index 005c401b3e22..bea323820ffb 100644
--- a/tools/testing/selftests/bpf/bench.h
+++ b/tools/testing/selftests/bpf/bench.h
@@ -46,6 +46,7 @@ struct bench_res {
unsigned long gp_ns;
unsigned long gp_ct;
unsigned int stime;
+ unsigned long duration_ns;
};
struct bench {
diff --git a/tools/testing/selftests/bpf/benchs/bench_lpm_trie_map.c b/tools/testing/selftests/bpf/benchs/bench_lpm_trie_map.c
new file mode 100644
index 000000000000..246f6cb3387d
--- /dev/null
+++ b/tools/testing/selftests/bpf/benchs/bench_lpm_trie_map.c
@@ -0,0 +1,555 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Cloudflare */
+
+/*
+ * All of these benchmarks operate on tries with keys in the range
+ * [0, args.nr_entries), i.e. there are no gaps or partially filled
+ * branches of the trie for any key < args.nr_entries.
+ *
+ * This gives an idea of worst-case behaviour.
+ */
+
+#include <argp.h>
+#include <linux/time64.h>
+#include <linux/if_ether.h>
+#include "lpm_trie_bench.skel.h"
+#include "lpm_trie_map.skel.h"
+#include "bench.h"
+#include "testing_helpers.h"
+#include "progs/lpm_trie.h"
+
+static struct ctx {
+ struct lpm_trie_bench *bench;
+} ctx;
+
+static struct {
+ __u32 nr_entries;
+ __u32 prefixlen;
+ bool random;
+} args = {
+ .nr_entries = 0,
+ .prefixlen = 32,
+ .random = false,
+};
+
+enum {
+ ARG_NR_ENTRIES = 9000,
+ ARG_PREFIX_LEN,
+ ARG_RANDOM,
+};
+
+static const struct argp_option opts[] = {
+ { "nr_entries", ARG_NR_ENTRIES, "NR_ENTRIES", 0,
+ "Number of unique entries in the LPM trie" },
+ { "prefix_len", ARG_PREFIX_LEN, "PREFIX_LEN", 0,
+ "Number of prefix bits to use in the LPM trie" },
+ { "random", ARG_RANDOM, NULL, 0, "Access random keys during op" },
+ {},
+};
+
+static error_t lpm_parse_arg(int key, char *arg, struct argp_state *state)
+{
+ long ret;
+
+ switch (key) {
+ case ARG_NR_ENTRIES:
+ ret = strtol(arg, NULL, 10);
+ if (ret < 1 || ret > UINT_MAX) {
+ fprintf(stderr, "Invalid nr_entries count.");
+ argp_usage(state);
+ }
+ args.nr_entries = ret;
+ break;
+ case ARG_PREFIX_LEN:
+ ret = strtol(arg, NULL, 10);
+ if (ret < 1 || ret > UINT_MAX) {
+ fprintf(stderr, "Invalid prefix_len value.");
+ argp_usage(state);
+ }
+ args.prefixlen = ret;
+ break;
+ case ARG_RANDOM:
+ args.random = true;
+ break;
+ default:
+ return ARGP_ERR_UNKNOWN;
+ }
+ return 0;
+}
+
+const struct argp bench_lpm_trie_map_argp = {
+ .options = opts,
+ .parser = lpm_parse_arg,
+};
+
+static void validate_common(void)
+{
+ if (env.consumer_cnt != 0) {
+ fprintf(stderr, "benchmark doesn't support consumer\n");
+ exit(1);
+ }
+
+ if (args.nr_entries == 0) {
+ fprintf(stderr, "Missing --nr_entries parameter\n");
+ exit(1);
+ }
+
+ if ((1UL << args.prefixlen) < args.nr_entries) {
+ fprintf(stderr, "prefix_len value too small for nr_entries\n");
+ exit(1);
+ }
+}
+
+static void lpm_insert_validate(void)
+{
+ validate_common();
+
+ if (env.producer_cnt != 1) {
+ fprintf(stderr, "lpm-trie-insert requires a single producer\n");
+ exit(1);
+ }
+
+ if (args.random) {
+ fprintf(stderr, "lpm-trie-insert does not support --random\n");
+ exit(1);
+ }
+}
+
+static void lpm_delete_validate(void)
+{
+ validate_common();
+
+ if (env.producer_cnt != 1) {
+ fprintf(stderr, "lpm-trie-delete requires a single producer\n");
+ exit(1);
+ }
+
+ if (args.random) {
+ fprintf(stderr, "lpm-trie-delete does not support --random\n");
+ exit(1);
+ }
+}
+
+static void lpm_free_validate(void)
+{
+ validate_common();
+
+ if (env.producer_cnt != 1) {
+ fprintf(stderr, "lpm-trie-free requires a single producer\n");
+ exit(1);
+ }
+
+ if (args.random) {
+ fprintf(stderr, "lpm-trie-free does not support --random\n");
+ exit(1);
+ }
+}
+
+static struct trie_key *keys;
+static __u32 *vals;
+
+static void fill_map(int map_fd)
+{
+ int err;
+
+ DECLARE_LIBBPF_OPTS(bpf_map_batch_opts, opts,
+ .elem_flags = 0,
+ .flags = 0,
+ );
+
+ err = bpf_map_update_batch(map_fd, keys, vals, &args.nr_entries, &opts);
+ if (err) {
+ fprintf(stderr, "failed to batch update keys to map: %d\n",
+ -err);
+ exit(1);
+ }
+}
+
+static void empty_map(int map_fd)
+{
+ int err;
+
+ DECLARE_LIBBPF_OPTS(bpf_map_batch_opts, opts,
+ .elem_flags = 0,
+ .flags = 0,
+ );
+
+ err = bpf_map_delete_batch(map_fd, keys, &args.nr_entries, &opts);
+ if (err) {
+ fprintf(stderr, "failed to batch delete keys for map: %d\n",
+ -err);
+ exit(1);
+ }
+}
+
+static void attach_prog(void)
+{
+ int i;
+
+ ctx.bench = lpm_trie_bench__open_and_load();
+ if (!ctx.bench) {
+ fprintf(stderr, "failed to open skeleton\n");
+ exit(1);
+ }
+
+ ctx.bench->bss->nr_entries = args.nr_entries;
+ ctx.bench->bss->prefixlen = args.prefixlen;
+ ctx.bench->bss->random = args.random;
+
+ if (lpm_trie_bench__attach(ctx.bench)) {
+ fprintf(stderr, "failed to attach skeleton\n");
+ exit(1);
+ }
+
+ keys = calloc(args.nr_entries, sizeof(*keys));
+ vals = calloc(args.nr_entries, sizeof(*vals));
+
+ for (i = 0; i < args.nr_entries; i++) {
+ struct trie_key *k = &keys[i];
+ __u32 *v = &vals[i];
+
+ k->prefixlen = args.prefixlen;
+ k->data = i;
+ *v = 1;
+ }
+}
+
+static void attach_prog_and_fill_map(void)
+{
+ int fd;
+
+ attach_prog();
+
+ fd = bpf_map__fd(ctx.bench->maps.trie_map);
+ fill_map(fd);
+}
+
+static void lpm_noop_setup(void)
+{
+ attach_prog();
+ ctx.bench->bss->op = LPM_OP_NOOP;
+}
+
+static void lpm_baseline_setup(void)
+{
+ attach_prog();
+ ctx.bench->bss->op = LPM_OP_BASELINE;
+}
+
+static void lpm_lookup_setup(void)
+{
+ attach_prog_and_fill_map();
+ ctx.bench->bss->op = LPM_OP_LOOKUP;
+}
+
+static void lpm_insert_setup(void)
+{
+ attach_prog();
+ ctx.bench->bss->op = LPM_OP_INSERT;
+}
+
+static void lpm_update_setup(void)
+{
+ attach_prog_and_fill_map();
+ ctx.bench->bss->op = LPM_OP_UPDATE;
+}
+
+static void lpm_delete_setup(void)
+{
+ attach_prog_and_fill_map();
+ ctx.bench->bss->op = LPM_OP_DELETE;
+}
+
+static void lpm_free_setup(void)
+{
+ attach_prog();
+ ctx.bench->bss->op = LPM_OP_FREE;
+}
+
+static void lpm_measure(struct bench_res *res)
+{
+ res->hits = atomic_swap(&ctx.bench->bss->hits, 0);
+ res->duration_ns = atomic_swap(&ctx.bench->bss->duration_ns, 0);
+}
+
+static void bench_reinit_map(void)
+{
+ int fd = bpf_map__fd(ctx.bench->maps.trie_map);
+
+ switch (ctx.bench->bss->op) {
+ case LPM_OP_INSERT:
+ /* trie_map needs to be emptied */
+ empty_map(fd);
+ break;
+ case LPM_OP_DELETE:
+ /* trie_map needs to be refilled */
+ fill_map(fd);
+ break;
+ default:
+ fprintf(stderr, "Unexpected REINIT return code for op %d\n",
+ ctx.bench->bss->op);
+ exit(1);
+ }
+}
+
+/* For NOOP, BASELINE, LOOKUP, INSERT, UPDATE, and DELETE */
+static void *lpm_producer(void *unused __always_unused)
+{
+ int err;
+ char in[ETH_HLEN]; /* unused */
+
+ LIBBPF_OPTS(bpf_test_run_opts, opts, .data_in = in,
+ .data_size_in = sizeof(in), .repeat = 1, );
+
+ while (true) {
+ int fd = bpf_program__fd(ctx.bench->progs.run_bench);
+ err = bpf_prog_test_run_opts(fd, &opts);
+ if (err) {
+ fprintf(stderr, "failed to run BPF prog: %d\n", err);
+ exit(1);
+ }
+
+ /* Check for kernel error code */
+ if ((int)opts.retval < 0) {
+ fprintf(stderr, "BPF prog returned error: %d\n",
+ opts.retval);
+ exit(1);
+ }
+
+ switch (opts.retval) {
+ case LPM_BENCH_SUCCESS:
+ break;
+ case LPM_BENCH_REINIT_MAP:
+ bench_reinit_map();
+ break;
+ default:
+ fprintf(stderr, "Unexpected BPF prog return code %d for op %d\n",
+ opts.retval, ctx.bench->bss->op);
+ exit(1);
+ }
+ }
+
+ return NULL;
+}
+
+static void *lpm_free_producer(void *unused __always_unused)
+{
+ while (true) {
+ struct lpm_trie_map *skel;
+
+ skel = lpm_trie_map__open_and_load();
+ if (!skel) {
+ fprintf(stderr, "failed to open skeleton\n");
+ exit(1);
+ }
+
+ fill_map(bpf_map__fd(skel->maps.trie_free_map));
+ lpm_trie_map__destroy(skel);
+ }
+
+ return NULL;
+}
+
+/*
+ * The standard bench op_report_*() functions assume measurements are
+ * taken over a 1-second interval but operations that modify the map
+ * (INSERT, DELETE, and FREE) cannot run indefinitely without
+ * "resetting" the map to the initial state. Depending on the size of
+ * the map, this likely needs to happen before the 1-second timer fires.
+ *
+ * Calculate the fraction of a second over which the op measurement was
+ * taken (to ignore any time spent doing the reset) and report the
+ * throughput results per second.
+ */
+static void frac_second_report_progress(int iter, struct bench_res *res,
+ long delta_ns, double rate_divisor,
+ char rate)
+{
+ double hits_per_sec, hits_per_prod;
+
+ hits_per_sec = res->hits / rate_divisor /
+ (res->duration_ns / (double)NSEC_PER_SEC);
+ hits_per_prod = hits_per_sec / env.producer_cnt;
+
+ printf("Iter %3d (%7.3lfus): ", iter,
+ (delta_ns - NSEC_PER_SEC) / 1000.0);
+ printf("hits %8.3lf%c/s (%7.3lf%c/prod)\n", hits_per_sec, rate,
+ hits_per_prod, rate);
+}
+
+static void frac_second_report_final(struct bench_res res[], int res_cnt,
+ double lat_divisor, double rate_divisor,
+ char rate, const char *unit)
+{
+ double hits_mean = 0.0, hits_stddev = 0.0;
+ double latency = 0.0;
+ int i;
+
+ for (i = 0; i < res_cnt; i++) {
+ double val = res[i].hits / rate_divisor /
+ (res[i].duration_ns / (double)NSEC_PER_SEC);
+ hits_mean += val / (0.0 + res_cnt);
+ latency += res[i].duration_ns / res[i].hits / (0.0 + res_cnt);
+ }
+
+ if (res_cnt > 1) {
+ for (i = 0; i < res_cnt; i++) {
+ double val =
+ res[i].hits / rate_divisor /
+ (res[i].duration_ns / (double)NSEC_PER_SEC);
+ hits_stddev += (hits_mean - val) * (hits_mean - val) /
+ (res_cnt - 1.0);
+ }
+
+ hits_stddev = sqrt(hits_stddev);
+ }
+ printf("Summary: throughput %8.3lf \u00B1 %5.3lf %c ops/s (%7.3lf%c ops/prod), ",
+ hits_mean, hits_stddev, rate, hits_mean / env.producer_cnt,
+ rate);
+ printf("latency %8.3lf %s/op\n",
+ latency / lat_divisor / env.producer_cnt, unit);
+}
+
+static void insert_ops_report_progress(int iter, struct bench_res *res,
+ long delta_ns)
+{
+ double rate_divisor = 1000000.0;
+ char rate = 'M';
+
+ frac_second_report_progress(iter, res, delta_ns, rate_divisor, rate);
+}
+
+static void delete_ops_report_progress(int iter, struct bench_res *res,
+ long delta_ns)
+{
+ double rate_divisor = 1000000.0;
+ char rate = 'M';
+
+ frac_second_report_progress(iter, res, delta_ns, rate_divisor, rate);
+}
+
+static void free_ops_report_progress(int iter, struct bench_res *res,
+ long delta_ns)
+{
+ double rate_divisor = 1000.0;
+ char rate = 'K';
+
+ frac_second_report_progress(iter, res, delta_ns, rate_divisor, rate);
+}
+
+static void insert_ops_report_final(struct bench_res res[], int res_cnt)
+{
+ double lat_divisor = 1.0;
+ double rate_divisor = 1000000.0;
+ const char *unit = "ns";
+ char rate = 'M';
+
+ frac_second_report_final(res, res_cnt, lat_divisor, rate_divisor, rate,
+ unit);
+}
+
+static void delete_ops_report_final(struct bench_res res[], int res_cnt)
+{
+ double lat_divisor = 1.0;
+ double rate_divisor = 1000000.0;
+ const char *unit = "ns";
+ char rate = 'M';
+
+ frac_second_report_final(res, res_cnt, lat_divisor, rate_divisor, rate,
+ unit);
+}
+
+static void free_ops_report_final(struct bench_res res[], int res_cnt)
+{
+ double lat_divisor = 1000000.0;
+ double rate_divisor = 1000.0;
+ const char *unit = "ms";
+ char rate = 'K';
+
+ frac_second_report_final(res, res_cnt, lat_divisor, rate_divisor, rate,
+ unit);
+}
+
+/* noop bench measures harness-overhead */
+const struct bench bench_lpm_trie_noop = {
+ .name = "lpm-trie-noop",
+ .argp = &bench_lpm_trie_map_argp,
+ .validate = validate_common,
+ .setup = lpm_noop_setup,
+ .producer_thread = lpm_producer,
+ .measure = lpm_measure,
+ .report_progress = ops_report_progress,
+ .report_final = ops_report_final,
+};
+
+/* baseline overhead for lookup and update */
+const struct bench bench_lpm_trie_baseline = {
+ .name = "lpm-trie-baseline",
+ .argp = &bench_lpm_trie_map_argp,
+ .validate = validate_common,
+ .setup = lpm_baseline_setup,
+ .producer_thread = lpm_producer,
+ .measure = lpm_measure,
+ .report_progress = ops_report_progress,
+ .report_final = ops_report_final,
+};
+
+/* measure cost of doing a lookup on existing entries in a full trie */
+const struct bench bench_lpm_trie_lookup = {
+ .name = "lpm-trie-lookup",
+ .argp = &bench_lpm_trie_map_argp,
+ .validate = validate_common,
+ .setup = lpm_lookup_setup,
+ .producer_thread = lpm_producer,
+ .measure = lpm_measure,
+ .report_progress = ops_report_progress,
+ .report_final = ops_report_final,
+};
+
+/* measure cost of inserting new entries into an empty trie */
+const struct bench bench_lpm_trie_insert = {
+ .name = "lpm-trie-insert",
+ .argp = &bench_lpm_trie_map_argp,
+ .validate = lpm_insert_validate,
+ .setup = lpm_insert_setup,
+ .producer_thread = lpm_producer,
+ .measure = lpm_measure,
+ .report_progress = insert_ops_report_progress,
+ .report_final = insert_ops_report_final,
+};
+
+/* measure cost of updating existing entries in a full trie */
+const struct bench bench_lpm_trie_update = {
+ .name = "lpm-trie-update",
+ .argp = &bench_lpm_trie_map_argp,
+ .validate = validate_common,
+ .setup = lpm_update_setup,
+ .producer_thread = lpm_producer,
+ .measure = lpm_measure,
+ .report_progress = ops_report_progress,
+ .report_final = ops_report_final,
+};
+
+/* measure cost of deleting existing entries from a full trie */
+const struct bench bench_lpm_trie_delete = {
+ .name = "lpm-trie-delete",
+ .argp = &bench_lpm_trie_map_argp,
+ .validate = lpm_delete_validate,
+ .setup = lpm_delete_setup,
+ .producer_thread = lpm_producer,
+ .measure = lpm_measure,
+ .report_progress = delete_ops_report_progress,
+ .report_final = delete_ops_report_final,
+};
+
+/* measure cost of freeing a full trie */
+const struct bench bench_lpm_trie_free = {
+ .name = "lpm-trie-free",
+ .argp = &bench_lpm_trie_map_argp,
+ .validate = lpm_free_validate,
+ .setup = lpm_free_setup,
+ .producer_thread = lpm_free_producer,
+ .measure = lpm_measure,
+ .report_progress = free_ops_report_progress,
+ .report_final = free_ops_report_final,
+};
diff --git a/tools/testing/selftests/bpf/benchs/bench_sockmap.c b/tools/testing/selftests/bpf/benchs/bench_sockmap.c
index 8ebf563a67a2..cfc072aa7fff 100644
--- a/tools/testing/selftests/bpf/benchs/bench_sockmap.c
+++ b/tools/testing/selftests/bpf/benchs/bench_sockmap.c
@@ -10,6 +10,7 @@
#include <argp.h>
#include "bench.h"
#include "bench_sockmap_prog.skel.h"
+#include "bpf_util.h"
#define FILE_SIZE (128 * 1024)
#define DATA_REPEAT_SIZE 10
@@ -124,8 +125,8 @@ static void bench_sockmap_prog_destroy(void)
{
int i;
- for (i = 0; i < sizeof(ctx.fds); i++) {
- if (ctx.fds[0] > 0)
+ for (i = 0; i < ARRAY_SIZE(ctx.fds); i++) {
+ if (ctx.fds[i] > 0)
close(ctx.fds[i]);
}
diff --git a/tools/testing/selftests/bpf/benchs/bench_trigger.c b/tools/testing/selftests/bpf/benchs/bench_trigger.c
index 82327657846e..1e2aff007c2a 100644
--- a/tools/testing/selftests/bpf/benchs/bench_trigger.c
+++ b/tools/testing/selftests/bpf/benchs/bench_trigger.c
@@ -226,6 +226,65 @@ static void trigger_fentry_setup(void)
attach_bpf(ctx.skel->progs.bench_trigger_fentry);
}
+static void attach_ksyms_all(struct bpf_program *empty, bool kretprobe)
+{
+ LIBBPF_OPTS(bpf_kprobe_multi_opts, opts);
+ char **syms = NULL;
+ size_t cnt = 0;
+
+ /* Some recursive functions will be skipped in
+ * bpf_get_ksyms -> skip_entry, as they can introduce sufficient
+ * overhead. However, it's difficut to skip all the recursive
+ * functions for a debug kernel.
+ *
+ * So, don't run the kprobe-multi-all and kretprobe-multi-all on
+ * a debug kernel.
+ */
+ if (bpf_get_ksyms(&syms, &cnt, true)) {
+ fprintf(stderr, "failed to get ksyms\n");
+ exit(1);
+ }
+
+ opts.syms = (const char **) syms;
+ opts.cnt = cnt;
+ opts.retprobe = kretprobe;
+ /* attach empty to all the kernel functions except bpf_get_numa_node_id. */
+ if (!bpf_program__attach_kprobe_multi_opts(empty, NULL, &opts)) {
+ fprintf(stderr, "failed to attach bpf_program__attach_kprobe_multi_opts to all\n");
+ exit(1);
+ }
+}
+
+static void trigger_kprobe_multi_all_setup(void)
+{
+ struct bpf_program *prog, *empty;
+
+ setup_ctx();
+ empty = ctx.skel->progs.bench_kprobe_multi_empty;
+ prog = ctx.skel->progs.bench_trigger_kprobe_multi;
+ bpf_program__set_autoload(empty, true);
+ bpf_program__set_autoload(prog, true);
+ load_ctx();
+
+ attach_ksyms_all(empty, false);
+ attach_bpf(prog);
+}
+
+static void trigger_kretprobe_multi_all_setup(void)
+{
+ struct bpf_program *prog, *empty;
+
+ setup_ctx();
+ empty = ctx.skel->progs.bench_kretprobe_multi_empty;
+ prog = ctx.skel->progs.bench_trigger_kretprobe_multi;
+ bpf_program__set_autoload(empty, true);
+ bpf_program__set_autoload(prog, true);
+ load_ctx();
+
+ attach_ksyms_all(empty, true);
+ attach_bpf(prog);
+}
+
static void trigger_fexit_setup(void)
{
setup_ctx();
@@ -512,6 +571,8 @@ BENCH_TRIG_KERNEL(kretprobe, "kretprobe");
BENCH_TRIG_KERNEL(kprobe_multi, "kprobe-multi");
BENCH_TRIG_KERNEL(kretprobe_multi, "kretprobe-multi");
BENCH_TRIG_KERNEL(fentry, "fentry");
+BENCH_TRIG_KERNEL(kprobe_multi_all, "kprobe-multi-all");
+BENCH_TRIG_KERNEL(kretprobe_multi_all, "kretprobe-multi-all");
BENCH_TRIG_KERNEL(fexit, "fexit");
BENCH_TRIG_KERNEL(fmodret, "fmodret");
BENCH_TRIG_KERNEL(tp, "tp");
diff --git a/tools/testing/selftests/bpf/benchs/run_bench_trigger.sh b/tools/testing/selftests/bpf/benchs/run_bench_trigger.sh
index a690f5a68b6b..f7573708a0c3 100755
--- a/tools/testing/selftests/bpf/benchs/run_bench_trigger.sh
+++ b/tools/testing/selftests/bpf/benchs/run_bench_trigger.sh
@@ -6,8 +6,8 @@ def_tests=( \
usermode-count kernel-count syscall-count \
fentry fexit fmodret \
rawtp tp \
- kprobe kprobe-multi \
- kretprobe kretprobe-multi \
+ kprobe kprobe-multi kprobe-multi-all \
+ kretprobe kretprobe-multi kretprobe-multi-all \
)
tests=("$@")
diff --git a/tools/testing/selftests/bpf/bpf_experimental.h b/tools/testing/selftests/bpf/bpf_experimental.h
index da7e230f2781..d89eda3fd8a3 100644
--- a/tools/testing/selftests/bpf/bpf_experimental.h
+++ b/tools/testing/selftests/bpf/bpf_experimental.h
@@ -599,4 +599,58 @@ extern void bpf_iter_dmabuf_destroy(struct bpf_iter_dmabuf *it) __weak __ksym;
extern int bpf_cgroup_read_xattr(struct cgroup *cgroup, const char *name__str,
struct bpf_dynptr *value_p) __weak __ksym;
+#define PREEMPT_BITS 8
+#define SOFTIRQ_BITS 8
+#define HARDIRQ_BITS 4
+#define NMI_BITS 4
+
+#define PREEMPT_SHIFT 0
+#define SOFTIRQ_SHIFT (PREEMPT_SHIFT + PREEMPT_BITS)
+#define HARDIRQ_SHIFT (SOFTIRQ_SHIFT + SOFTIRQ_BITS)
+#define NMI_SHIFT (HARDIRQ_SHIFT + HARDIRQ_BITS)
+
+#define __IRQ_MASK(x) ((1UL << (x))-1)
+
+#define SOFTIRQ_MASK (__IRQ_MASK(SOFTIRQ_BITS) << SOFTIRQ_SHIFT)
+#define HARDIRQ_MASK (__IRQ_MASK(HARDIRQ_BITS) << HARDIRQ_SHIFT)
+#define NMI_MASK (__IRQ_MASK(NMI_BITS) << NMI_SHIFT)
+
+extern bool CONFIG_PREEMPT_RT __kconfig __weak;
+#ifdef bpf_target_x86
+extern const int __preempt_count __ksym;
+#endif
+
+struct task_struct___preempt_rt {
+ int softirq_disable_cnt;
+} __attribute__((preserve_access_index));
+
+static inline int get_preempt_count(void)
+{
+#if defined(bpf_target_x86)
+ return *(int *) bpf_this_cpu_ptr(&__preempt_count);
+#elif defined(bpf_target_arm64)
+ return bpf_get_current_task_btf()->thread_info.preempt.count;
+#endif
+ return 0;
+}
+
+/* Description
+ * Report whether it is in interrupt context. Only works on the following archs:
+ * * x86
+ * * arm64
+ */
+static inline int bpf_in_interrupt(void)
+{
+ struct task_struct___preempt_rt *tsk;
+ int pcnt;
+
+ pcnt = get_preempt_count();
+ if (!CONFIG_PREEMPT_RT)
+ return pcnt & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_MASK);
+
+ tsk = (void *) bpf_get_current_task_btf();
+ return (pcnt & (NMI_MASK | HARDIRQ_MASK)) |
+ (tsk->softirq_disable_cnt & SOFTIRQ_MASK);
+}
+
#endif
diff --git a/tools/testing/selftests/bpf/bpf_kfuncs.h b/tools/testing/selftests/bpf/bpf_kfuncs.h
index 9386dfe8b884..794d44d19c88 100644
--- a/tools/testing/selftests/bpf/bpf_kfuncs.h
+++ b/tools/testing/selftests/bpf/bpf_kfuncs.h
@@ -19,6 +19,9 @@ extern int bpf_dynptr_from_skb(struct __sk_buff *skb, __u64 flags,
extern int bpf_dynptr_from_xdp(struct xdp_md *xdp, __u64 flags,
struct bpf_dynptr *ptr__uninit) __ksym __weak;
+extern int bpf_dynptr_from_skb_meta(struct __sk_buff *skb, __u64 flags,
+ struct bpf_dynptr *ptr__uninit) __ksym __weak;
+
/* Description
* Obtain a read-only pointer to the dynptr's data
* Returns
diff --git a/tools/testing/selftests/bpf/bpf_util.h b/tools/testing/selftests/bpf/bpf_util.h
index 5f6963a320d7..4bc2d25f33e1 100644
--- a/tools/testing/selftests/bpf/bpf_util.h
+++ b/tools/testing/selftests/bpf/bpf_util.h
@@ -67,6 +67,9 @@ static inline void bpf_strlcpy(char *dst, const char *src, size_t sz)
#define sys_gettid() syscall(SYS_gettid)
#endif
+/* and poison usage to ensure it does not creep back in. */
+#pragma GCC poison gettid
+
#ifndef ENOTSUPP
#define ENOTSUPP 524
#endif
diff --git a/tools/testing/selftests/bpf/cgroup_helpers.c b/tools/testing/selftests/bpf/cgroup_helpers.c
index 15f626014872..20cede4db3ce 100644
--- a/tools/testing/selftests/bpf/cgroup_helpers.c
+++ b/tools/testing/selftests/bpf/cgroup_helpers.c
@@ -412,6 +412,26 @@ void remove_cgroup(const char *relative_path)
log_err("rmdiring cgroup %s .. %s", relative_path, cgroup_path);
}
+/*
+ * remove_cgroup_pid() - Remove a cgroup setup by process identified by PID
+ * @relative_path: The cgroup path, relative to the workdir, to remove
+ * @pid: PID to be used to find cgroup_path
+ *
+ * This function expects a cgroup to already be created, relative to the cgroup
+ * work dir. It also expects the cgroup doesn't have any children or live
+ * processes and it removes the cgroup.
+ *
+ * On failure, it will print an error to stderr.
+ */
+void remove_cgroup_pid(const char *relative_path, int pid)
+{
+ char cgroup_path[PATH_MAX + 1];
+
+ format_cgroup_path_pid(cgroup_path, relative_path, pid);
+ if (rmdir(cgroup_path))
+ log_err("rmdiring cgroup %s .. %s", relative_path, cgroup_path);
+}
+
/**
* create_and_get_cgroup() - Create a cgroup, relative to workdir, and get the FD
* @relative_path: The cgroup path, relative to the workdir, to join
diff --git a/tools/testing/selftests/bpf/cgroup_helpers.h b/tools/testing/selftests/bpf/cgroup_helpers.h
index 182e1ac36c95..3857304be874 100644
--- a/tools/testing/selftests/bpf/cgroup_helpers.h
+++ b/tools/testing/selftests/bpf/cgroup_helpers.h
@@ -19,6 +19,7 @@ int cgroup_setup_and_join(const char *relative_path);
int get_root_cgroup(void);
int create_and_get_cgroup(const char *relative_path);
void remove_cgroup(const char *relative_path);
+void remove_cgroup_pid(const char *relative_path, int pid);
unsigned long long get_cgroup_id(const char *relative_path);
int get_cgroup1_hierarchy_id(const char *subsys_name);
diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config
index 8916ab814a3e..70b28c1e653e 100644
--- a/tools/testing/selftests/bpf/config
+++ b/tools/testing/selftests/bpf/config
@@ -61,6 +61,7 @@ CONFIG_MPLS_IPTUNNEL=y
CONFIG_MPLS_ROUTING=y
CONFIG_MPTCP=y
CONFIG_NET_ACT_GACT=y
+CONFIG_NET_ACT_MIRRED=y
CONFIG_NET_ACT_SKBMOD=y
CONFIG_NET_CLS=y
CONFIG_NET_CLS_ACT=y
diff --git a/tools/testing/selftests/bpf/config.aarch64 b/tools/testing/selftests/bpf/config.aarch64
index e1495a4bbc99..7efad36ceb26 100644
--- a/tools/testing/selftests/bpf/config.aarch64
+++ b/tools/testing/selftests/bpf/config.aarch64
@@ -31,10 +31,7 @@ CONFIG_COMPAT=y
CONFIG_CPUSETS=y
CONFIG_CRASH_DUMP=y
CONFIG_CRYPTO_USER_API_RNG=y
-CONFIG_CRYPTO_USER_API_SKCIPHER=y
CONFIG_DEBUG_ATOMIC_SLEEP=y
-CONFIG_DEBUG_INFO_BTF=y
-CONFIG_DEBUG_INFO_DWARF4=y
CONFIG_DEBUG_INFO_REDUCED=n
CONFIG_DEBUG_LIST=y
CONFIG_DEBUG_LOCKDEP=y
@@ -46,7 +43,6 @@ CONFIG_DETECT_HUNG_TASK=y
CONFIG_DEVTMPFS_MOUNT=y
CONFIG_DEVTMPFS=y
CONFIG_DRM=y
-CONFIG_DUMMY=y
CONFIG_EXPERT=y
CONFIG_EXT4_FS_POSIX_ACL=y
CONFIG_EXT4_FS_SECURITY=y
@@ -70,13 +66,11 @@ CONFIG_HZ_100=y
CONFIG_IDLE_PAGE_TRACKING=y
CONFIG_IKHEADERS=y
CONFIG_INET6_ESP=y
-CONFIG_INET_ESP=y
CONFIG_INET=y
CONFIG_INPUT_EVDEV=y
CONFIG_IP_ADVANCED_ROUTER=y
CONFIG_IP_MULTICAST=y
CONFIG_IP_MULTIPLE_TABLES=y
-CONFIG_IP_NF_IPTABLES=y
CONFIG_IPV6_SEG6_LWTUNNEL=y
CONFIG_IPVLAN=y
CONFIG_JUMP_LABEL=y
@@ -97,22 +91,18 @@ CONFIG_MEMORY_HOTPLUG=y
CONFIG_MEMORY_HOTREMOVE=y
CONFIG_NAMESPACES=y
CONFIG_NET_ACT_BPF=y
-CONFIG_NET_ACT_GACT=y
CONFIG_NETDEVICES=y
CONFIG_NETFILTER_XT_MATCH_BPF=y
CONFIG_NETFILTER_XT_TARGET_MARK=y
CONFIG_NET_KEY=y
-CONFIG_NET_SCH_FQ=y
CONFIG_NET_VRF=y
CONFIG_NET=y
-CONFIG_NF_TABLES=y
CONFIG_NLMON=y
CONFIG_NO_HZ_IDLE=y
CONFIG_NR_CPUS=256
CONFIG_NUMA=y
CONFIG_OVERLAY_FS=y
CONFIG_PACKET_DIAG=y
-CONFIG_PACKET=y
CONFIG_PANIC_ON_OOPS=y
CONFIG_PARTITION_ADVANCED=y
CONFIG_PCI_HOST_GENERIC=y
@@ -149,7 +139,6 @@ CONFIG_TASK_XACCT=y
CONFIG_TCG_TIS=y
CONFIG_TCG_TPM=y
CONFIG_TCP_CONG_ADVANCED=y
-CONFIG_TCP_CONG_DCTCP=y
CONFIG_TLS=y
CONFIG_TMPFS_POSIX_ACL=y
CONFIG_TMPFS=y
@@ -161,6 +150,5 @@ CONFIG_UPROBES=y
CONFIG_USER_NS=y
CONFIG_VETH=y
CONFIG_VLAN_8021Q=y
-CONFIG_VSOCKETS=y
CONFIG_VSOCKETS_LOOPBACK=y
CONFIG_XFRM_USER=y
diff --git a/tools/testing/selftests/bpf/config.ppc64el b/tools/testing/selftests/bpf/config.ppc64el
index 9acf389dc4ce..b53afb5e0b71 100644
--- a/tools/testing/selftests/bpf/config.ppc64el
+++ b/tools/testing/selftests/bpf/config.ppc64el
@@ -54,7 +54,6 @@ CONFIG_NET=y
CONFIG_NO_HZ_IDLE=y
CONFIG_NONPORTABLE=y
CONFIG_NR_CPUS=256
-CONFIG_PACKET=y
CONFIG_PANIC_ON_OOPS=y
CONFIG_PARTITION_ADVANCED=y
CONFIG_PCI_HOST_GENERIC=y
diff --git a/tools/testing/selftests/bpf/config.riscv64 b/tools/testing/selftests/bpf/config.riscv64
index bb7043a80e1a..7bee24a79a71 100644
--- a/tools/testing/selftests/bpf/config.riscv64
+++ b/tools/testing/selftests/bpf/config.riscv64
@@ -48,7 +48,6 @@ CONFIG_NET_VRF=y
CONFIG_NONPORTABLE=y
CONFIG_NO_HZ_IDLE=y
CONFIG_NR_CPUS=256
-CONFIG_PACKET=y
CONFIG_PANIC_ON_OOPS=y
CONFIG_PARTITION_ADVANCED=y
CONFIG_PCI=y
diff --git a/tools/testing/selftests/bpf/config.s390x b/tools/testing/selftests/bpf/config.s390x
index 26c3bc2ce11d..db61878148e4 100644
--- a/tools/testing/selftests/bpf/config.s390x
+++ b/tools/testing/selftests/bpf/config.s390x
@@ -22,10 +22,7 @@ CONFIG_CHECKPOINT_RESTORE=y
CONFIG_CPUSETS=y
CONFIG_CRASH_DUMP=y
CONFIG_CRYPTO_USER_API_RNG=y
-CONFIG_CRYPTO_USER_API_SKCIPHER=y
CONFIG_DEBUG_ATOMIC_SLEEP=y
-CONFIG_DEBUG_INFO_BTF=y
-CONFIG_DEBUG_INFO_DWARF4=y
CONFIG_DEBUG_LIST=y
CONFIG_DEBUG_LOCKDEP=y
CONFIG_DEBUG_NOTIFIERS=y
@@ -56,11 +53,9 @@ CONFIG_IDLE_PAGE_TRACKING=y
CONFIG_IKHEADERS=y
CONFIG_INET6_ESP=y
CONFIG_INET=y
-CONFIG_INET_ESP=y
CONFIG_IP_ADVANCED_ROUTER=y
CONFIG_IP_MULTICAST=y
CONFIG_IP_MULTIPLE_TABLES=y
-CONFIG_IP_NF_IPTABLES=y
CONFIG_IPV6_SEG6_LWTUNNEL=y
CONFIG_IPVLAN=y
CONFIG_JUMP_LABEL=y
@@ -83,18 +78,14 @@ CONFIG_MEMORY_HOTREMOVE=y
CONFIG_NAMESPACES=y
CONFIG_NET=y
CONFIG_NET_ACT_BPF=y
-CONFIG_NET_ACT_GACT=y
CONFIG_NET_KEY=y
-CONFIG_NET_SCH_FQ=y
CONFIG_NET_VRF=y
CONFIG_NETDEVICES=y
CONFIG_NETFILTER_XT_MATCH_BPF=y
CONFIG_NETFILTER_XT_TARGET_MARK=y
-CONFIG_NF_TABLES=y
CONFIG_NO_HZ_IDLE=y
CONFIG_NR_CPUS=256
CONFIG_NUMA=y
-CONFIG_PACKET=y
CONFIG_PANIC_ON_OOPS=y
CONFIG_PARTITION_ADVANCED=y
CONFIG_PCI=y
@@ -119,7 +110,6 @@ CONFIG_TASK_IO_ACCOUNTING=y
CONFIG_TASK_XACCT=y
CONFIG_TASKSTATS=y
CONFIG_TCP_CONG_ADVANCED=y
-CONFIG_TCP_CONG_DCTCP=y
CONFIG_TLS=y
CONFIG_TMPFS=y
CONFIG_TMPFS_POSIX_ACL=y
@@ -131,6 +121,5 @@ CONFIG_UPROBES=y
CONFIG_USER_NS=y
CONFIG_VETH=y
CONFIG_VLAN_8021Q=y
-CONFIG_VSOCKETS=y
CONFIG_VSOCKETS_LOOPBACK=y
CONFIG_XFRM_USER=y
diff --git a/tools/testing/selftests/bpf/config.x86_64 b/tools/testing/selftests/bpf/config.x86_64
index 5e713ef7caa3..42ad817b00ae 100644
--- a/tools/testing/selftests/bpf/config.x86_64
+++ b/tools/testing/selftests/bpf/config.x86_64
@@ -44,7 +44,6 @@ CONFIG_CRYPTO_SEQIV=y
CONFIG_CRYPTO_XXHASH=y
CONFIG_DCB=y
CONFIG_DEBUG_ATOMIC_SLEEP=y
-CONFIG_DEBUG_INFO_BTF=y
CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
CONFIG_DEBUG_MEMORY_INIT=y
CONFIG_DEFAULT_FQ_CODEL=y
@@ -104,12 +103,10 @@ CONFIG_HZ_1000=y
CONFIG_INET=y
CONFIG_INPUT_EVDEV=y
CONFIG_INTEL_POWERCLAMP=y
-CONFIG_IP6_NF_IPTABLES=y
CONFIG_IP_ADVANCED_ROUTER=y
CONFIG_IP_MROUTE=y
CONFIG_IP_MULTICAST=y
CONFIG_IP_MULTIPLE_TABLES=y
-CONFIG_IP_NF_IPTABLES=y
CONFIG_IP_PIMSM_V1=y
CONFIG_IP_PIMSM_V2=y
CONFIG_IP_ROUTE_MULTIPATH=y
@@ -162,7 +159,6 @@ CONFIG_NUMA=y
CONFIG_NUMA_BALANCING=y
CONFIG_NVMEM=y
CONFIG_OSF_PARTITION=y
-CONFIG_PACKET=y
CONFIG_PANIC_ON_OOPS=y
CONFIG_PARTITION_ADVANCED=y
CONFIG_PCI=y
@@ -220,7 +216,6 @@ CONFIG_VALIDATE_FS_PARSER=y
CONFIG_VETH=y
CONFIG_VIRT_DRIVERS=y
CONFIG_VLAN_8021Q=y
-CONFIG_VSOCKETS=y
CONFIG_VSOCKETS_LOOPBACK=y
CONFIG_X86_ACPI_CPUFREQ=y
CONFIG_X86_CPUID=y
diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c
index 72b5c174ab3b..cdf7b6641444 100644
--- a/tools/testing/selftests/bpf/network_helpers.c
+++ b/tools/testing/selftests/bpf/network_helpers.c
@@ -457,7 +457,7 @@ int append_tid(char *str, size_t sz)
if (end + 8 > sz)
return -1;
- sprintf(&str[end], "%07d", gettid());
+ sprintf(&str[end], "%07ld", sys_gettid());
str[end + 7] = '\0';
return 0;
diff --git a/tools/testing/selftests/bpf/prog_tests/align.c b/tools/testing/selftests/bpf/prog_tests/align.c
index 1d53a8561ee2..24c509ce4e5b 100644
--- a/tools/testing/selftests/bpf/prog_tests/align.c
+++ b/tools/testing/selftests/bpf/prog_tests/align.c
@@ -42,11 +42,11 @@ static struct bpf_align_test tests[] = {
.matches = {
{0, "R1", "ctx()"},
{0, "R10", "fp0"},
- {0, "R3_w", "2"},
- {1, "R3_w", "4"},
- {2, "R3_w", "8"},
- {3, "R3_w", "16"},
- {4, "R3_w", "32"},
+ {0, "R3", "2"},
+ {1, "R3", "4"},
+ {2, "R3", "8"},
+ {3, "R3", "16"},
+ {4, "R3", "32"},
},
},
{
@@ -70,17 +70,17 @@ static struct bpf_align_test tests[] = {
.matches = {
{0, "R1", "ctx()"},
{0, "R10", "fp0"},
- {0, "R3_w", "1"},
- {1, "R3_w", "2"},
- {2, "R3_w", "4"},
- {3, "R3_w", "8"},
- {4, "R3_w", "16"},
- {5, "R3_w", "1"},
- {6, "R4_w", "32"},
- {7, "R4_w", "16"},
- {8, "R4_w", "8"},
- {9, "R4_w", "4"},
- {10, "R4_w", "2"},
+ {0, "R3", "1"},
+ {1, "R3", "2"},
+ {2, "R3", "4"},
+ {3, "R3", "8"},
+ {4, "R3", "16"},
+ {5, "R3", "1"},
+ {6, "R4", "32"},
+ {7, "R4", "16"},
+ {8, "R4", "8"},
+ {9, "R4", "4"},
+ {10, "R4", "2"},
},
},
{
@@ -99,12 +99,12 @@ static struct bpf_align_test tests[] = {
.matches = {
{0, "R1", "ctx()"},
{0, "R10", "fp0"},
- {0, "R3_w", "4"},
- {1, "R3_w", "8"},
- {2, "R3_w", "10"},
- {3, "R4_w", "8"},
- {4, "R4_w", "12"},
- {5, "R4_w", "14"},
+ {0, "R3", "4"},
+ {1, "R3", "8"},
+ {2, "R3", "10"},
+ {3, "R4", "8"},
+ {4, "R4", "12"},
+ {5, "R4", "14"},
},
},
{
@@ -121,10 +121,10 @@ static struct bpf_align_test tests[] = {
.matches = {
{0, "R1", "ctx()"},
{0, "R10", "fp0"},
- {0, "R3_w", "7"},
- {1, "R3_w", "7"},
- {2, "R3_w", "14"},
- {3, "R3_w", "56"},
+ {0, "R3", "7"},
+ {1, "R3", "7"},
+ {2, "R3", "14"},
+ {3, "R3", "56"},
},
},
@@ -162,19 +162,19 @@ static struct bpf_align_test tests[] = {
},
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.matches = {
- {6, "R0_w", "pkt(off=8,r=8)"},
- {6, "R3_w", "var_off=(0x0; 0xff)"},
- {7, "R3_w", "var_off=(0x0; 0x1fe)"},
- {8, "R3_w", "var_off=(0x0; 0x3fc)"},
- {9, "R3_w", "var_off=(0x0; 0x7f8)"},
- {10, "R3_w", "var_off=(0x0; 0xff0)"},
- {12, "R3_w", "pkt_end()"},
- {17, "R4_w", "var_off=(0x0; 0xff)"},
- {18, "R4_w", "var_off=(0x0; 0x1fe0)"},
- {19, "R4_w", "var_off=(0x0; 0xff0)"},
- {20, "R4_w", "var_off=(0x0; 0x7f8)"},
- {21, "R4_w", "var_off=(0x0; 0x3fc)"},
- {22, "R4_w", "var_off=(0x0; 0x1fe)"},
+ {6, "R0", "pkt(off=8,r=8)"},
+ {6, "R3", "var_off=(0x0; 0xff)"},
+ {7, "R3", "var_off=(0x0; 0x1fe)"},
+ {8, "R3", "var_off=(0x0; 0x3fc)"},
+ {9, "R3", "var_off=(0x0; 0x7f8)"},
+ {10, "R3", "var_off=(0x0; 0xff0)"},
+ {12, "R3", "pkt_end()"},
+ {17, "R4", "var_off=(0x0; 0xff)"},
+ {18, "R4", "var_off=(0x0; 0x1fe0)"},
+ {19, "R4", "var_off=(0x0; 0xff0)"},
+ {20, "R4", "var_off=(0x0; 0x7f8)"},
+ {21, "R4", "var_off=(0x0; 0x3fc)"},
+ {22, "R4", "var_off=(0x0; 0x1fe)"},
},
},
{
@@ -195,16 +195,16 @@ static struct bpf_align_test tests[] = {
},
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.matches = {
- {6, "R3_w", "var_off=(0x0; 0xff)"},
- {7, "R4_w", "var_off=(0x0; 0xff)"},
- {8, "R4_w", "var_off=(0x0; 0xff)"},
- {9, "R4_w", "var_off=(0x0; 0xff)"},
- {10, "R4_w", "var_off=(0x0; 0x1fe)"},
- {11, "R4_w", "var_off=(0x0; 0xff)"},
- {12, "R4_w", "var_off=(0x0; 0x3fc)"},
- {13, "R4_w", "var_off=(0x0; 0xff)"},
- {14, "R4_w", "var_off=(0x0; 0x7f8)"},
- {15, "R4_w", "var_off=(0x0; 0xff0)"},
+ {6, "R3", "var_off=(0x0; 0xff)"},
+ {7, "R4", "var_off=(0x0; 0xff)"},
+ {8, "R4", "var_off=(0x0; 0xff)"},
+ {9, "R4", "var_off=(0x0; 0xff)"},
+ {10, "R4", "var_off=(0x0; 0x1fe)"},
+ {11, "R4", "var_off=(0x0; 0xff)"},
+ {12, "R4", "var_off=(0x0; 0x3fc)"},
+ {13, "R4", "var_off=(0x0; 0xff)"},
+ {14, "R4", "var_off=(0x0; 0x7f8)"},
+ {15, "R4", "var_off=(0x0; 0xff0)"},
},
},
{
@@ -235,14 +235,14 @@ static struct bpf_align_test tests[] = {
},
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.matches = {
- {2, "R5_w", "pkt(r=0)"},
- {4, "R5_w", "pkt(off=14,r=0)"},
- {5, "R4_w", "pkt(off=14,r=0)"},
+ {2, "R5", "pkt(r=0)"},
+ {4, "R5", "pkt(off=14,r=0)"},
+ {5, "R4", "pkt(off=14,r=0)"},
{9, "R2", "pkt(r=18)"},
{10, "R5", "pkt(off=14,r=18)"},
- {10, "R4_w", "var_off=(0x0; 0xff)"},
- {13, "R4_w", "var_off=(0x0; 0xffff)"},
- {14, "R4_w", "var_off=(0x0; 0xffff)"},
+ {10, "R4", "var_off=(0x0; 0xff)"},
+ {13, "R4", "var_off=(0x0; 0xffff)"},
+ {14, "R4", "var_off=(0x0; 0xffff)"},
},
},
{
@@ -299,12 +299,12 @@ static struct bpf_align_test tests[] = {
/* Calculated offset in R6 has unknown value, but known
* alignment of 4.
*/
- {6, "R2_w", "pkt(r=8)"},
- {7, "R6_w", "var_off=(0x0; 0x3fc)"},
+ {6, "R2", "pkt(r=8)"},
+ {7, "R6", "var_off=(0x0; 0x3fc)"},
/* Offset is added to packet pointer R5, resulting in
* known fixed offset, and variable offset from R6.
*/
- {11, "R5_w", "pkt(id=1,off=14,"},
+ {11, "R5", "pkt(id=1,off=14,"},
/* At the time the word size load is performed from R5,
* it's total offset is NET_IP_ALIGN + reg->off (0) +
* reg->aux_off (14) which is 16. Then the variable
@@ -320,12 +320,12 @@ static struct bpf_align_test tests[] = {
* instruction to validate R5 state. We also check
* that R4 is what it should be in such case.
*/
- {18, "R4_w", "var_off=(0x0; 0x3fc)"},
- {18, "R5_w", "var_off=(0x0; 0x3fc)"},
+ {18, "R4", "var_off=(0x0; 0x3fc)"},
+ {18, "R5", "var_off=(0x0; 0x3fc)"},
/* Constant offset is added to R5, resulting in
* reg->off of 14.
*/
- {19, "R5_w", "pkt(id=2,off=14,"},
+ {19, "R5", "pkt(id=2,off=14,"},
/* At the time the word size load is performed from R5,
* its total fixed offset is NET_IP_ALIGN + reg->off
* (14) which is 16. Then the variable offset is 4-byte
@@ -337,21 +337,21 @@ static struct bpf_align_test tests[] = {
/* Constant offset is added to R5 packet pointer,
* resulting in reg->off value of 14.
*/
- {26, "R5_w", "pkt(off=14,r=8)"},
+ {26, "R5", "pkt(off=14,r=8)"},
/* Variable offset is added to R5, resulting in a
* variable offset of (4n). See comment for insn #18
* for R4 = R5 trick.
*/
- {28, "R4_w", "var_off=(0x0; 0x3fc)"},
- {28, "R5_w", "var_off=(0x0; 0x3fc)"},
+ {28, "R4", "var_off=(0x0; 0x3fc)"},
+ {28, "R5", "var_off=(0x0; 0x3fc)"},
/* Constant is added to R5 again, setting reg->off to 18. */
- {29, "R5_w", "pkt(id=3,off=18,"},
+ {29, "R5", "pkt(id=3,off=18,"},
/* And once more we add a variable; resulting var_off
* is still (4n), fixed offset is not changed.
* Also, we create a new reg->id.
*/
- {31, "R4_w", "var_off=(0x0; 0x7fc)"},
- {31, "R5_w", "var_off=(0x0; 0x7fc)"},
+ {31, "R4", "var_off=(0x0; 0x7fc)"},
+ {31, "R5", "var_off=(0x0; 0x7fc)"},
/* At the time the word size load is performed from R5,
* its total fixed offset is NET_IP_ALIGN + reg->off (18)
* which is 20. Then the variable offset is (4n), so
@@ -397,12 +397,12 @@ static struct bpf_align_test tests[] = {
/* Calculated offset in R6 has unknown value, but known
* alignment of 4.
*/
- {6, "R2_w", "pkt(r=8)"},
- {7, "R6_w", "var_off=(0x0; 0x3fc)"},
+ {6, "R2", "pkt(r=8)"},
+ {7, "R6", "var_off=(0x0; 0x3fc)"},
/* Adding 14 makes R6 be (4n+2) */
- {8, "R6_w", "var_off=(0x2; 0x7fc)"},
+ {8, "R6", "var_off=(0x2; 0x7fc)"},
/* Packet pointer has (4n+2) offset */
- {11, "R5_w", "var_off=(0x2; 0x7fc)"},
+ {11, "R5", "var_off=(0x2; 0x7fc)"},
{12, "R4", "var_off=(0x2; 0x7fc)"},
/* At the time the word size load is performed from R5,
* its total fixed offset is NET_IP_ALIGN + reg->off (0)
@@ -414,11 +414,11 @@ static struct bpf_align_test tests[] = {
/* Newly read value in R6 was shifted left by 2, so has
* known alignment of 4.
*/
- {17, "R6_w", "var_off=(0x0; 0x3fc)"},
+ {17, "R6", "var_off=(0x0; 0x3fc)"},
/* Added (4n) to packet pointer's (4n+2) var_off, giving
* another (4n+2).
*/
- {19, "R5_w", "var_off=(0x2; 0xffc)"},
+ {19, "R5", "var_off=(0x2; 0xffc)"},
{20, "R4", "var_off=(0x2; 0xffc)"},
/* At the time the word size load is performed from R5,
* its total fixed offset is NET_IP_ALIGN + reg->off (0)
@@ -459,18 +459,18 @@ static struct bpf_align_test tests[] = {
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.result = REJECT,
.matches = {
- {3, "R5_w", "pkt_end()"},
+ {3, "R5", "pkt_end()"},
/* (ptr - ptr) << 2 == unknown, (4n) */
- {5, "R5_w", "var_off=(0x0; 0xfffffffffffffffc)"},
+ {5, "R5", "var_off=(0x0; 0xfffffffffffffffc)"},
/* (4n) + 14 == (4n+2). We blow our bounds, because
* the add could overflow.
*/
- {6, "R5_w", "var_off=(0x2; 0xfffffffffffffffc)"},
+ {6, "R5", "var_off=(0x2; 0xfffffffffffffffc)"},
/* Checked s>=0 */
{9, "R5", "var_off=(0x2; 0x7ffffffffffffffc)"},
/* packet pointer + nonnegative (4n+2) */
- {11, "R6_w", "var_off=(0x2; 0x7ffffffffffffffc)"},
- {12, "R4_w", "var_off=(0x2; 0x7ffffffffffffffc)"},
+ {11, "R6", "var_off=(0x2; 0x7ffffffffffffffc)"},
+ {12, "R4", "var_off=(0x2; 0x7ffffffffffffffc)"},
/* NET_IP_ALIGN + (4n+2) == (4n), alignment is fine.
* We checked the bounds, but it might have been able
* to overflow if the packet pointer started in the
@@ -478,7 +478,7 @@ static struct bpf_align_test tests[] = {
* So we did not get a 'range' on R6, and the access
* attempt will fail.
*/
- {15, "R6_w", "var_off=(0x2; 0x7ffffffffffffffc)"},
+ {15, "R6", "var_off=(0x2; 0x7ffffffffffffffc)"},
}
},
{
@@ -513,12 +513,12 @@ static struct bpf_align_test tests[] = {
/* Calculated offset in R6 has unknown value, but known
* alignment of 4.
*/
- {6, "R2_w", "pkt(r=8)"},
- {8, "R6_w", "var_off=(0x0; 0x3fc)"},
+ {6, "R2", "pkt(r=8)"},
+ {8, "R6", "var_off=(0x0; 0x3fc)"},
/* Adding 14 makes R6 be (4n+2) */
- {9, "R6_w", "var_off=(0x2; 0x7fc)"},
+ {9, "R6", "var_off=(0x2; 0x7fc)"},
/* New unknown value in R7 is (4n) */
- {10, "R7_w", "var_off=(0x0; 0x3fc)"},
+ {10, "R7", "var_off=(0x0; 0x3fc)"},
/* Subtracting it from R6 blows our unsigned bounds */
{11, "R6", "var_off=(0x2; 0xfffffffffffffffc)"},
/* Checked s>= 0 */
@@ -566,16 +566,16 @@ static struct bpf_align_test tests[] = {
/* Calculated offset in R6 has unknown value, but known
* alignment of 4.
*/
- {6, "R2_w", "pkt(r=8)"},
- {9, "R6_w", "var_off=(0x0; 0x3c)"},
+ {6, "R2", "pkt(r=8)"},
+ {9, "R6", "var_off=(0x0; 0x3c)"},
/* Adding 14 makes R6 be (4n+2) */
- {10, "R6_w", "var_off=(0x2; 0x7c)"},
+ {10, "R6", "var_off=(0x2; 0x7c)"},
/* Subtracting from packet pointer overflows ubounds */
- {13, "R5_w", "var_off=(0xffffffffffffff82; 0x7c)"},
+ {13, "R5", "var_off=(0xffffffffffffff82; 0x7c)"},
/* New unknown value in R7 is (4n), >= 76 */
- {14, "R7_w", "var_off=(0x0; 0x7fc)"},
+ {14, "R7", "var_off=(0x0; 0x7fc)"},
/* Adding it to packet pointer gives nice bounds again */
- {16, "R5_w", "var_off=(0x2; 0x7fc)"},
+ {16, "R5", "var_off=(0x2; 0x7fc)"},
/* At the time the word size load is performed from R5,
* its total fixed offset is NET_IP_ALIGN + reg->off (0)
* which is 2. Then the variable offset is (4n+2), so
diff --git a/tools/testing/selftests/bpf/prog_tests/arena_spin_lock.c b/tools/testing/selftests/bpf/prog_tests/arena_spin_lock.c
index 0223fce4db2b..693fd86fbde6 100644
--- a/tools/testing/selftests/bpf/prog_tests/arena_spin_lock.c
+++ b/tools/testing/selftests/bpf/prog_tests/arena_spin_lock.c
@@ -40,8 +40,13 @@ static void *spin_lock_thread(void *arg)
err = bpf_prog_test_run_opts(prog_fd, &topts);
ASSERT_OK(err, "test_run err");
+
+ if (topts.retval == -EOPNOTSUPP)
+ goto end;
+
ASSERT_EQ((int)topts.retval, 0, "test_run retval");
+end:
pthread_exit(arg);
}
@@ -63,6 +68,7 @@ static void test_arena_spin_lock_size(int size)
skel = arena_spin_lock__open_and_load();
if (!ASSERT_OK_PTR(skel, "arena_spin_lock__open_and_load"))
return;
+
if (skel->data->test_skip == 2) {
test__skip();
goto end;
@@ -86,6 +92,13 @@ static void test_arena_spin_lock_size(int size)
goto end_barrier;
}
+ if (skel->data->test_skip == 3) {
+ printf("%s:SKIP: CONFIG_NR_CPUS exceed the maximum supported by arena spinlock\n",
+ __func__);
+ test__skip();
+ goto end_barrier;
+ }
+
ASSERT_EQ(skel->bss->counter, repeat * nthreads, "check counter value");
end_barrier:
diff --git a/tools/testing/selftests/bpf/prog_tests/atomics.c b/tools/testing/selftests/bpf/prog_tests/atomics.c
index 13e101f370a1..92b5f378bfb8 100644
--- a/tools/testing/selftests/bpf/prog_tests/atomics.c
+++ b/tools/testing/selftests/bpf/prog_tests/atomics.c
@@ -165,11 +165,17 @@ static void test_xchg(struct atomics_lskel *skel)
void test_atomics(void)
{
struct atomics_lskel *skel;
+ int err;
- skel = atomics_lskel__open_and_load();
- if (!ASSERT_OK_PTR(skel, "atomics skeleton load"))
+ skel = atomics_lskel__open();
+ if (!ASSERT_OK_PTR(skel, "atomics skeleton open"))
return;
+ skel->keyring_id = KEY_SPEC_SESSION_KEYRING;
+ err = atomics_lskel__load(skel);
+ if (!ASSERT_OK(err, "atomics skeleton load"))
+ goto cleanup;
+
if (skel->data->skip_tests) {
printf("%s:SKIP:no ENABLE_ATOMICS_TESTS (missing Clang BPF atomics support)",
__func__);
diff --git a/tools/testing/selftests/bpf/prog_tests/attach_probe.c b/tools/testing/selftests/bpf/prog_tests/attach_probe.c
index cabc51c2ca6b..9e77e5da7097 100644
--- a/tools/testing/selftests/bpf/prog_tests/attach_probe.c
+++ b/tools/testing/selftests/bpf/prog_tests/attach_probe.c
@@ -3,6 +3,7 @@
#include "test_attach_kprobe_sleepable.skel.h"
#include "test_attach_probe_manual.skel.h"
#include "test_attach_probe.skel.h"
+#include "kprobe_write_ctx.skel.h"
/* this is how USDT semaphore is actually defined, except volatile modifier */
volatile unsigned short uprobe_ref_ctr __attribute__((unused)) __attribute((section(".probes")));
@@ -201,6 +202,31 @@ cleanup:
test_attach_probe_manual__destroy(skel);
}
+#ifdef __x86_64__
+/* attach kprobe/kretprobe long event name testings */
+static void test_attach_kprobe_write_ctx(void)
+{
+ struct kprobe_write_ctx *skel = NULL;
+ struct bpf_link *link = NULL;
+
+ skel = kprobe_write_ctx__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "kprobe_write_ctx__open_and_load"))
+ return;
+
+ link = bpf_program__attach_kprobe_opts(skel->progs.kprobe_write_ctx,
+ "bpf_fentry_test1", NULL);
+ if (!ASSERT_ERR_PTR(link, "bpf_program__attach_kprobe_opts"))
+ bpf_link__destroy(link);
+
+ kprobe_write_ctx__destroy(skel);
+}
+#else
+static void test_attach_kprobe_write_ctx(void)
+{
+ test__skip();
+}
+#endif
+
static void test_attach_probe_auto(struct test_attach_probe *skel)
{
struct bpf_link *uprobe_err_link;
@@ -406,6 +432,8 @@ void test_attach_probe(void)
test_attach_uprobe_long_event_name();
if (test__start_subtest("kprobe-long_name"))
test_attach_kprobe_long_event_name();
+ if (test__start_subtest("kprobe-write-ctx"))
+ test_attach_kprobe_write_ctx();
cleanup:
test_attach_probe__destroy(skel);
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c b/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c
index 4a0670c056ba..75f4dff7d042 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c
@@ -450,8 +450,7 @@ static void pe_subtest(struct test_bpf_cookie *skel)
attr.size = sizeof(attr);
attr.type = PERF_TYPE_SOFTWARE;
attr.config = PERF_COUNT_SW_CPU_CLOCK;
- attr.freq = 1;
- attr.sample_freq = 10000;
+ attr.sample_period = 100000;
pfd = syscall(__NR_perf_event_open, &attr, -1, 0, -1, PERF_FLAG_FD_CLOEXEC);
if (!ASSERT_GE(pfd, 0, "perf_fd"))
goto cleanup;
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_dump.c b/tools/testing/selftests/bpf/prog_tests/btf_dump.c
index 82903585c870..10cba526d3e6 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_dump.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_dump.c
@@ -63,7 +63,7 @@ static int test_btf_dump_case(int n, struct btf_dump_test_case *t)
/* tests with t->known_ptr_sz have no "long" or "unsigned long" type,
* so it's impossible to determine correct pointer size; but if they
- * do, it should be 8 regardless of host architecture, becaues BPF
+ * do, it should be 8 regardless of host architecture, because BPF
* target is always 64-bit
*/
if (!t->known_ptr_sz) {
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_xattr.c b/tools/testing/selftests/bpf/prog_tests/cgroup_xattr.c
index e0dd966e4a3e..5ad904e9d15d 100644
--- a/tools/testing/selftests/bpf/prog_tests/cgroup_xattr.c
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_xattr.c
@@ -44,7 +44,7 @@ static void test_read_cgroup_xattr(void)
if (!ASSERT_OK_PTR(skel, "read_cgroupfs_xattr__open_and_load"))
goto out;
- skel->bss->target_pid = gettid();
+ skel->bss->target_pid = sys_gettid();
if (!ASSERT_OK(read_cgroupfs_xattr__attach(skel), "read_cgroupfs_xattr__attach"))
goto out;
diff --git a/tools/testing/selftests/bpf/prog_tests/cgrp_kfunc.c b/tools/testing/selftests/bpf/prog_tests/cgrp_kfunc.c
index adda85f97058..4b42fbc96efc 100644
--- a/tools/testing/selftests/bpf/prog_tests/cgrp_kfunc.c
+++ b/tools/testing/selftests/bpf/prog_tests/cgrp_kfunc.c
@@ -4,6 +4,8 @@
#define _GNU_SOURCE
#include <cgroup_helpers.h>
#include <test_progs.h>
+#include <sched.h>
+#include <sys/wait.h>
#include "cgrp_kfunc_failure.skel.h"
#include "cgrp_kfunc_success.skel.h"
@@ -87,6 +89,72 @@ static const char * const success_tests[] = {
"test_cgrp_from_id",
};
+static void test_cgrp_from_id_ns(void)
+{
+ LIBBPF_OPTS(bpf_test_run_opts, opts);
+ struct cgrp_kfunc_success *skel;
+ struct bpf_program *prog;
+ int pid, pipe_fd[2];
+
+ skel = open_load_cgrp_kfunc_skel();
+ if (!ASSERT_OK_PTR(skel, "open_load_skel"))
+ return;
+
+ if (!ASSERT_OK(skel->bss->err, "pre_mkdir_err"))
+ goto cleanup;
+
+ prog = skel->progs.test_cgrp_from_id_ns;
+
+ if (!ASSERT_OK(pipe(pipe_fd), "pipe"))
+ goto cleanup;
+
+ pid = fork();
+ if (!ASSERT_GE(pid, 0, "fork result")) {
+ close(pipe_fd[0]);
+ close(pipe_fd[1]);
+ goto cleanup;
+ }
+
+ if (pid == 0) {
+ int ret = 0;
+
+ close(pipe_fd[0]);
+
+ if (!ASSERT_GE(cgroup_setup_and_join("cgrp_from_id_ns"), 0, "join cgroup"))
+ exit(1);
+
+ if (!ASSERT_OK(unshare(CLONE_NEWCGROUP), "unshare cgns"))
+ exit(1);
+
+ ret = bpf_prog_test_run_opts(bpf_program__fd(prog), &opts);
+ if (!ASSERT_OK(ret, "test run ret"))
+ exit(1);
+
+ if (!ASSERT_OK(opts.retval, "test run retval"))
+ exit(1);
+
+ if (!ASSERT_EQ(write(pipe_fd[1], &ret, sizeof(ret)), sizeof(ret), "write pipe"))
+ exit(1);
+
+ exit(0);
+ } else {
+ int res;
+
+ close(pipe_fd[1]);
+
+ ASSERT_EQ(read(pipe_fd[0], &res, sizeof(res)), sizeof(res), "read res");
+ ASSERT_EQ(waitpid(pid, NULL, 0), pid, "wait on child");
+
+ remove_cgroup_pid("cgrp_from_id_ns", pid);
+
+ ASSERT_OK(res, "result from run");
+ }
+
+ close(pipe_fd[0]);
+cleanup:
+ cgrp_kfunc_success__destroy(skel);
+}
+
void test_cgrp_kfunc(void)
{
int i, err;
@@ -102,6 +170,9 @@ void test_cgrp_kfunc(void)
run_success_test(success_tests[i]);
}
+ if (test__start_subtest("test_cgrp_from_id_ns"))
+ test_cgrp_from_id_ns();
+
RUN_TESTS(cgrp_kfunc_failure);
cleanup:
diff --git a/tools/testing/selftests/bpf/prog_tests/dynptr.c b/tools/testing/selftests/bpf/prog_tests/dynptr.c
index 9b2d9ceda210..b9f86cb91e81 100644
--- a/tools/testing/selftests/bpf/prog_tests/dynptr.c
+++ b/tools/testing/selftests/bpf/prog_tests/dynptr.c
@@ -32,6 +32,8 @@ static struct {
{"test_ringbuf", SETUP_SYSCALL_SLEEP},
{"test_skb_readonly", SETUP_SKB_PROG},
{"test_dynptr_skb_data", SETUP_SKB_PROG},
+ {"test_dynptr_skb_meta_data", SETUP_SKB_PROG},
+ {"test_dynptr_skb_meta_flags", SETUP_SKB_PROG},
{"test_adjust", SETUP_SYSCALL_SLEEP},
{"test_adjust_err", SETUP_SYSCALL_SLEEP},
{"test_zero_size_dynptr", SETUP_SYSCALL_SLEEP},
diff --git a/tools/testing/selftests/bpf/prog_tests/fd_array.c b/tools/testing/selftests/bpf/prog_tests/fd_array.c
index 241b2c8c6e0f..c534b4d5f9da 100644
--- a/tools/testing/selftests/bpf/prog_tests/fd_array.c
+++ b/tools/testing/selftests/bpf/prog_tests/fd_array.c
@@ -293,7 +293,7 @@ static int get_btf_id_by_fd(int btf_fd, __u32 *id)
* 1) Create a new btf, it's referenced only by a file descriptor, so refcnt=1
* 2) Load a BPF prog with fd_array[0] = btf_fd; now btf's refcnt=2
* 3) Close the btf_fd, now refcnt=1
- * Wait and check that BTF stil exists.
+ * Wait and check that BTF still exists.
*/
static void check_fd_array_cnt__referenced_btfs(void)
{
diff --git a/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c b/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c
index 130f5b82d2e6..5ef1804e44df 100644
--- a/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c
+++ b/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c
@@ -12,13 +12,24 @@ void test_fentry_fexit(void)
int err, prog_fd, i;
LIBBPF_OPTS(bpf_test_run_opts, topts);
- fentry_skel = fentry_test_lskel__open_and_load();
+ fentry_skel = fentry_test_lskel__open();
if (!ASSERT_OK_PTR(fentry_skel, "fentry_skel_load"))
goto close_prog;
- fexit_skel = fexit_test_lskel__open_and_load();
+
+ fentry_skel->keyring_id = KEY_SPEC_SESSION_KEYRING;
+ err = fentry_test_lskel__load(fentry_skel);
+ if (!ASSERT_OK(err, "fentry_skel_load"))
+ goto close_prog;
+
+ fexit_skel = fexit_test_lskel__open();
if (!ASSERT_OK_PTR(fexit_skel, "fexit_skel_load"))
goto close_prog;
+ fexit_skel->keyring_id = KEY_SPEC_SESSION_KEYRING;
+ err = fexit_test_lskel__load(fexit_skel);
+ if (!ASSERT_OK(err, "fexit_skel_load"))
+ goto close_prog;
+
err = fentry_test_lskel__attach(fentry_skel);
if (!ASSERT_OK(err, "fentry_attach"))
goto close_prog;
diff --git a/tools/testing/selftests/bpf/prog_tests/fentry_test.c b/tools/testing/selftests/bpf/prog_tests/fentry_test.c
index aee1bc77a17f..ec882328eb59 100644
--- a/tools/testing/selftests/bpf/prog_tests/fentry_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/fentry_test.c
@@ -43,8 +43,13 @@ static void fentry_test(void)
struct fentry_test_lskel *fentry_skel = NULL;
int err;
- fentry_skel = fentry_test_lskel__open_and_load();
- if (!ASSERT_OK_PTR(fentry_skel, "fentry_skel_load"))
+ fentry_skel = fentry_test_lskel__open();
+ if (!ASSERT_OK_PTR(fentry_skel, "fentry_skel_open"))
+ goto cleanup;
+
+ fentry_skel->keyring_id = KEY_SPEC_SESSION_KEYRING;
+ err = fentry_test_lskel__load(fentry_skel);
+ if (!ASSERT_OK(err, "fentry_skel_load"))
goto cleanup;
err = fentry_test_common(fentry_skel);
diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_test.c b/tools/testing/selftests/bpf/prog_tests/fexit_test.c
index 1c13007e37dd..94eed753560c 100644
--- a/tools/testing/selftests/bpf/prog_tests/fexit_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/fexit_test.c
@@ -43,8 +43,13 @@ static void fexit_test(void)
struct fexit_test_lskel *fexit_skel = NULL;
int err;
- fexit_skel = fexit_test_lskel__open_and_load();
- if (!ASSERT_OK_PTR(fexit_skel, "fexit_skel_load"))
+ fexit_skel = fexit_test_lskel__open();
+ if (!ASSERT_OK_PTR(fexit_skel, "fexit_skel_open"))
+ goto cleanup;
+
+ fexit_skel->keyring_id = KEY_SPEC_SESSION_KEYRING;
+ err = fexit_test_lskel__load(fexit_skel);
+ if (!ASSERT_OK(err, "fexit_skel_load"))
goto cleanup;
err = fexit_test_common(fexit_skel);
diff --git a/tools/testing/selftests/bpf/prog_tests/free_timer.c b/tools/testing/selftests/bpf/prog_tests/free_timer.c
index b7b77a6b2979..0de8facca4c5 100644
--- a/tools/testing/selftests/bpf/prog_tests/free_timer.c
+++ b/tools/testing/selftests/bpf/prog_tests/free_timer.c
@@ -124,6 +124,10 @@ void test_free_timer(void)
int err;
skel = free_timer__open_and_load();
+ if (!skel && errno == EOPNOTSUPP) {
+ test__skip();
+ return;
+ }
if (!ASSERT_OK_PTR(skel, "open_load"))
return;
diff --git a/tools/testing/selftests/bpf/prog_tests/kernel_flag.c b/tools/testing/selftests/bpf/prog_tests/kernel_flag.c
index a133354ac9bc..97b00c7efe94 100644
--- a/tools/testing/selftests/bpf/prog_tests/kernel_flag.c
+++ b/tools/testing/selftests/bpf/prog_tests/kernel_flag.c
@@ -16,7 +16,7 @@ void test_kernel_flag(void)
if (!ASSERT_OK_PTR(lsm_skel, "lsm_skel"))
return;
- lsm_skel->bss->monitored_tid = gettid();
+ lsm_skel->bss->monitored_tid = sys_gettid();
ret = test_kernel_flag__attach(lsm_skel);
if (!ASSERT_OK(ret, "test_kernel_flag__attach"))
diff --git a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c
index e19ef509ebf8..6cfaa978bc9a 100644
--- a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c
@@ -7,6 +7,7 @@
#include "kprobe_multi_session.skel.h"
#include "kprobe_multi_session_cookie.skel.h"
#include "kprobe_multi_verifier.skel.h"
+#include "kprobe_write_ctx.skel.h"
#include "bpf/libbpf_internal.h"
#include "bpf/hashmap.h"
@@ -422,220 +423,6 @@ static void test_unique_match(void)
kprobe_multi__destroy(skel);
}
-static size_t symbol_hash(long key, void *ctx __maybe_unused)
-{
- return str_hash((const char *) key);
-}
-
-static bool symbol_equal(long key1, long key2, void *ctx __maybe_unused)
-{
- return strcmp((const char *) key1, (const char *) key2) == 0;
-}
-
-static bool is_invalid_entry(char *buf, bool kernel)
-{
- if (kernel && strchr(buf, '['))
- return true;
- if (!kernel && !strchr(buf, '['))
- return true;
- return false;
-}
-
-static bool skip_entry(char *name)
-{
- /*
- * We attach to almost all kernel functions and some of them
- * will cause 'suspicious RCU usage' when fprobe is attached
- * to them. Filter out the current culprits - arch_cpu_idle
- * default_idle and rcu_* functions.
- */
- if (!strcmp(name, "arch_cpu_idle"))
- return true;
- if (!strcmp(name, "default_idle"))
- return true;
- if (!strncmp(name, "rcu_", 4))
- return true;
- if (!strcmp(name, "bpf_dispatcher_xdp_func"))
- return true;
- if (!strncmp(name, "__ftrace_invalid_address__",
- sizeof("__ftrace_invalid_address__") - 1))
- return true;
- return false;
-}
-
-/* Do comparision by ignoring '.llvm.<hash>' suffixes. */
-static int compare_name(const char *name1, const char *name2)
-{
- const char *res1, *res2;
- int len1, len2;
-
- res1 = strstr(name1, ".llvm.");
- res2 = strstr(name2, ".llvm.");
- len1 = res1 ? res1 - name1 : strlen(name1);
- len2 = res2 ? res2 - name2 : strlen(name2);
-
- if (len1 == len2)
- return strncmp(name1, name2, len1);
- if (len1 < len2)
- return strncmp(name1, name2, len1) <= 0 ? -1 : 1;
- return strncmp(name1, name2, len2) >= 0 ? 1 : -1;
-}
-
-static int load_kallsyms_compare(const void *p1, const void *p2)
-{
- return compare_name(((const struct ksym *)p1)->name, ((const struct ksym *)p2)->name);
-}
-
-static int search_kallsyms_compare(const void *p1, const struct ksym *p2)
-{
- return compare_name(p1, p2->name);
-}
-
-static int get_syms(char ***symsp, size_t *cntp, bool kernel)
-{
- size_t cap = 0, cnt = 0;
- char *name = NULL, *ksym_name, **syms = NULL;
- struct hashmap *map;
- struct ksyms *ksyms;
- struct ksym *ks;
- char buf[256];
- FILE *f;
- int err = 0;
-
- ksyms = load_kallsyms_custom_local(load_kallsyms_compare);
- if (!ASSERT_OK_PTR(ksyms, "load_kallsyms_custom_local"))
- return -EINVAL;
-
- /*
- * The available_filter_functions contains many duplicates,
- * but other than that all symbols are usable in kprobe multi
- * interface.
- * Filtering out duplicates by using hashmap__add, which won't
- * add existing entry.
- */
-
- if (access("/sys/kernel/tracing/trace", F_OK) == 0)
- f = fopen("/sys/kernel/tracing/available_filter_functions", "r");
- else
- f = fopen("/sys/kernel/debug/tracing/available_filter_functions", "r");
-
- if (!f)
- return -EINVAL;
-
- map = hashmap__new(symbol_hash, symbol_equal, NULL);
- if (IS_ERR(map)) {
- err = libbpf_get_error(map);
- goto error;
- }
-
- while (fgets(buf, sizeof(buf), f)) {
- if (is_invalid_entry(buf, kernel))
- continue;
-
- free(name);
- if (sscanf(buf, "%ms$*[^\n]\n", &name) != 1)
- continue;
- if (skip_entry(name))
- continue;
-
- ks = search_kallsyms_custom_local(ksyms, name, search_kallsyms_compare);
- if (!ks) {
- err = -EINVAL;
- goto error;
- }
-
- ksym_name = ks->name;
- err = hashmap__add(map, ksym_name, 0);
- if (err == -EEXIST) {
- err = 0;
- continue;
- }
- if (err)
- goto error;
-
- err = libbpf_ensure_mem((void **) &syms, &cap,
- sizeof(*syms), cnt + 1);
- if (err)
- goto error;
-
- syms[cnt++] = ksym_name;
- }
-
- *symsp = syms;
- *cntp = cnt;
-
-error:
- free(name);
- fclose(f);
- hashmap__free(map);
- if (err)
- free(syms);
- return err;
-}
-
-static int get_addrs(unsigned long **addrsp, size_t *cntp, bool kernel)
-{
- unsigned long *addr, *addrs, *tmp_addrs;
- int err = 0, max_cnt, inc_cnt;
- char *name = NULL;
- size_t cnt = 0;
- char buf[256];
- FILE *f;
-
- if (access("/sys/kernel/tracing/trace", F_OK) == 0)
- f = fopen("/sys/kernel/tracing/available_filter_functions_addrs", "r");
- else
- f = fopen("/sys/kernel/debug/tracing/available_filter_functions_addrs", "r");
-
- if (!f)
- return -ENOENT;
-
- /* In my local setup, the number of entries is 50k+ so Let us initially
- * allocate space to hold 64k entries. If 64k is not enough, incrementally
- * increase 1k each time.
- */
- max_cnt = 65536;
- inc_cnt = 1024;
- addrs = malloc(max_cnt * sizeof(long));
- if (addrs == NULL) {
- err = -ENOMEM;
- goto error;
- }
-
- while (fgets(buf, sizeof(buf), f)) {
- if (is_invalid_entry(buf, kernel))
- continue;
-
- free(name);
- if (sscanf(buf, "%p %ms$*[^\n]\n", &addr, &name) != 2)
- continue;
- if (skip_entry(name))
- continue;
-
- if (cnt == max_cnt) {
- max_cnt += inc_cnt;
- tmp_addrs = realloc(addrs, max_cnt);
- if (!tmp_addrs) {
- err = -ENOMEM;
- goto error;
- }
- addrs = tmp_addrs;
- }
-
- addrs[cnt++] = (unsigned long)addr;
- }
-
- *addrsp = addrs;
- *cntp = cnt;
-
-error:
- free(name);
- fclose(f);
- if (err)
- free(addrs);
- return err;
-}
-
static void do_bench_test(struct kprobe_multi_empty *skel, struct bpf_kprobe_multi_opts *opts)
{
long attach_start_ns, attach_end_ns;
@@ -670,7 +457,7 @@ static void test_kprobe_multi_bench_attach(bool kernel)
char **syms = NULL;
size_t cnt = 0;
- if (!ASSERT_OK(get_syms(&syms, &cnt, kernel), "get_syms"))
+ if (!ASSERT_OK(bpf_get_ksyms(&syms, &cnt, kernel), "bpf_get_ksyms"))
return;
skel = kprobe_multi_empty__open_and_load();
@@ -696,13 +483,13 @@ static void test_kprobe_multi_bench_attach_addr(bool kernel)
size_t cnt = 0;
int err;
- err = get_addrs(&addrs, &cnt, kernel);
+ err = bpf_get_addrs(&addrs, &cnt, kernel);
if (err == -ENOENT) {
test__skip();
return;
}
- if (!ASSERT_OK(err, "get_addrs"))
+ if (!ASSERT_OK(err, "bpf_get_addrs"))
return;
skel = kprobe_multi_empty__open_and_load();
@@ -753,6 +540,30 @@ cleanup:
kprobe_multi_override__destroy(skel);
}
+#ifdef __x86_64__
+static void test_attach_write_ctx(void)
+{
+ struct kprobe_write_ctx *skel = NULL;
+ struct bpf_link *link = NULL;
+
+ skel = kprobe_write_ctx__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "kprobe_write_ctx__open_and_load"))
+ return;
+
+ link = bpf_program__attach_kprobe_opts(skel->progs.kprobe_multi_write_ctx,
+ "bpf_fentry_test1", NULL);
+ if (!ASSERT_ERR_PTR(link, "bpf_program__attach_kprobe_opts"))
+ bpf_link__destroy(link);
+
+ kprobe_write_ctx__destroy(skel);
+}
+#else
+static void test_attach_write_ctx(void)
+{
+ test__skip();
+}
+#endif
+
void serial_test_kprobe_multi_bench_attach(void)
{
if (test__start_subtest("kernel"))
@@ -792,5 +603,7 @@ void test_kprobe_multi_test(void)
test_session_cookie_skel_api();
if (test__start_subtest("unique_match"))
test_unique_match();
+ if (test__start_subtest("attach_write_ctx"))
+ test_attach_write_ctx();
RUN_TESTS(kprobe_multi_verifier);
}
diff --git a/tools/testing/selftests/bpf/prog_tests/map_excl.c b/tools/testing/selftests/bpf/prog_tests/map_excl.c
new file mode 100644
index 000000000000..6bdc6d6de0da
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/map_excl.c
@@ -0,0 +1,54 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2025 Google LLC. */
+#define _GNU_SOURCE
+#include <unistd.h>
+#include <sys/syscall.h>
+#include <test_progs.h>
+#include <bpf/btf.h>
+
+#include "map_excl.skel.h"
+
+static void test_map_excl_allowed(void)
+{
+ struct map_excl *skel = map_excl__open();
+ int err;
+
+ err = bpf_map__set_exclusive_program(skel->maps.excl_map, skel->progs.should_have_access);
+ if (!ASSERT_OK(err, "bpf_map__set_exclusive_program"))
+ goto out;
+
+ bpf_program__set_autoload(skel->progs.should_have_access, true);
+ bpf_program__set_autoload(skel->progs.should_not_have_access, false);
+
+ err = map_excl__load(skel);
+ ASSERT_OK(err, "map_excl__load");
+out:
+ map_excl__destroy(skel);
+}
+
+static void test_map_excl_denied(void)
+{
+ struct map_excl *skel = map_excl__open();
+ int err;
+
+ err = bpf_map__set_exclusive_program(skel->maps.excl_map, skel->progs.should_have_access);
+ if (!ASSERT_OK(err, "bpf_map__make_exclusive"))
+ goto out;
+
+ bpf_program__set_autoload(skel->progs.should_have_access, false);
+ bpf_program__set_autoload(skel->progs.should_not_have_access, true);
+
+ err = map_excl__load(skel);
+ ASSERT_EQ(err, -EACCES, "exclusive map access not denied\n");
+out:
+ map_excl__destroy(skel);
+
+}
+
+void test_map_excl(void)
+{
+ if (test__start_subtest("map_excl_allowed"))
+ test_map_excl_allowed();
+ if (test__start_subtest("map_excl_denied"))
+ test_map_excl_denied();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/module_attach.c b/tools/testing/selftests/bpf/prog_tests/module_attach.c
index 6d391d95f96e..70fa7ae93173 100644
--- a/tools/testing/selftests/bpf/prog_tests/module_attach.c
+++ b/tools/testing/selftests/bpf/prog_tests/module_attach.c
@@ -90,7 +90,7 @@ void test_module_attach(void)
test_module_attach__detach(skel);
- /* attach fentry/fexit and make sure it get's module reference */
+ /* attach fentry/fexit and make sure it gets module reference */
link = bpf_program__attach(skel->progs.handle_fentry);
if (!ASSERT_OK_PTR(link, "attach_fentry"))
goto cleanup;
diff --git a/tools/testing/selftests/bpf/prog_tests/pinning_devmap_reuse.c b/tools/testing/selftests/bpf/prog_tests/pinning_devmap_reuse.c
new file mode 100644
index 000000000000..9ae49b587f3e
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/pinning_devmap_reuse.c
@@ -0,0 +1,50 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
+#include <test_progs.h>
+
+
+#include "test_pinning_devmap.skel.h"
+
+void test_pinning_devmap_reuse(void)
+{
+ const char *pinpath1 = "/sys/fs/bpf/pinmap1";
+ const char *pinpath2 = "/sys/fs/bpf/pinmap2";
+ struct test_pinning_devmap *skel1 = NULL, *skel2 = NULL;
+ int err;
+ DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts);
+
+ /* load the object a first time */
+ skel1 = test_pinning_devmap__open_and_load();
+ if (!ASSERT_OK_PTR(skel1, "skel_load1"))
+ goto out;
+
+ /* load the object a second time, re-using the pinned map */
+ skel2 = test_pinning_devmap__open_and_load();
+ if (!ASSERT_OK_PTR(skel2, "skel_load2"))
+ goto out;
+
+ /* we can close the reference safely without
+ * the map's refcount falling to 0
+ */
+ test_pinning_devmap__destroy(skel1);
+ skel1 = NULL;
+
+ /* now, swap the pins */
+ err = renameat2(0, pinpath1, 0, pinpath2, RENAME_EXCHANGE);
+ if (!ASSERT_OK(err, "swap pins"))
+ goto out;
+
+ /* load the object again, this time the re-use should fail */
+ skel1 = test_pinning_devmap__open_and_load();
+ if (!ASSERT_ERR_PTR(skel1, "skel_load3"))
+ goto out;
+
+out:
+ unlink(pinpath1);
+ unlink(pinpath2);
+ test_pinning_devmap__destroy(skel1);
+ test_pinning_devmap__destroy(skel2);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/prog_tests_framework.c b/tools/testing/selftests/bpf/prog_tests/prog_tests_framework.c
index 14f2796076e0..7607cfc2408c 100644
--- a/tools/testing/selftests/bpf/prog_tests/prog_tests_framework.c
+++ b/tools/testing/selftests/bpf/prog_tests/prog_tests_framework.c
@@ -54,3 +54,128 @@ void test_prog_tests_framework(void)
return;
clear_test_state(state);
}
+
+static void dummy_emit(const char *buf, bool force) {}
+
+void test_prog_tests_framework_expected_msgs(void)
+{
+ struct expected_msgs msgs;
+ int i, j, error_cnt;
+ const struct {
+ const char *name;
+ const char *log;
+ const char *expected;
+ struct expect_msg *pats;
+ } cases[] = {
+ {
+ .name = "simple-ok",
+ .log = "aaabbbccc",
+ .pats = (struct expect_msg[]) {
+ { .substr = "aaa" },
+ { .substr = "ccc" },
+ {}
+ }
+ },
+ {
+ .name = "simple-fail",
+ .log = "aaabbbddd",
+ .expected = "MATCHED SUBSTR: 'aaa'\n"
+ "EXPECTED SUBSTR: 'ccc'\n",
+ .pats = (struct expect_msg[]) {
+ { .substr = "aaa" },
+ { .substr = "ccc" },
+ {}
+ }
+ },
+ {
+ .name = "negative-ok-mid",
+ .log = "aaabbbccc",
+ .pats = (struct expect_msg[]) {
+ { .substr = "aaa" },
+ { .substr = "foo", .negative = true },
+ { .substr = "bar", .negative = true },
+ { .substr = "ccc" },
+ {}
+ }
+ },
+ {
+ .name = "negative-ok-tail",
+ .log = "aaabbbccc",
+ .pats = (struct expect_msg[]) {
+ { .substr = "aaa" },
+ { .substr = "foo", .negative = true },
+ {}
+ }
+ },
+ {
+ .name = "negative-ok-head",
+ .log = "aaabbbccc",
+ .pats = (struct expect_msg[]) {
+ { .substr = "foo", .negative = true },
+ { .substr = "ccc" },
+ {}
+ }
+ },
+ {
+ .name = "negative-fail-head",
+ .log = "aaabbbccc",
+ .expected = "UNEXPECTED SUBSTR: 'aaa'\n",
+ .pats = (struct expect_msg[]) {
+ { .substr = "aaa", .negative = true },
+ { .substr = "bbb" },
+ {}
+ }
+ },
+ {
+ .name = "negative-fail-tail",
+ .log = "aaabbbccc",
+ .expected = "UNEXPECTED SUBSTR: 'ccc'\n",
+ .pats = (struct expect_msg[]) {
+ { .substr = "bbb" },
+ { .substr = "ccc", .negative = true },
+ {}
+ }
+ },
+ {
+ .name = "negative-fail-mid-1",
+ .log = "aaabbbccc",
+ .expected = "UNEXPECTED SUBSTR: 'bbb'\n",
+ .pats = (struct expect_msg[]) {
+ { .substr = "aaa" },
+ { .substr = "bbb", .negative = true },
+ { .substr = "ccc" },
+ {}
+ }
+ },
+ {
+ .name = "negative-fail-mid-2",
+ .log = "aaabbb222ccc",
+ .expected = "UNEXPECTED SUBSTR: '222'\n",
+ .pats = (struct expect_msg[]) {
+ { .substr = "aaa" },
+ { .substr = "222", .negative = true },
+ { .substr = "bbb", .negative = true },
+ { .substr = "ccc" },
+ {}
+ }
+ }
+ };
+
+ for (i = 0; i < ARRAY_SIZE(cases); i++) {
+ if (test__start_subtest(cases[i].name)) {
+ error_cnt = env.subtest_state->error_cnt;
+ msgs.patterns = cases[i].pats;
+ msgs.cnt = 0;
+ for (j = 0; cases[i].pats[j].substr; j++)
+ msgs.cnt++;
+ validate_msgs(cases[i].log, &msgs, dummy_emit);
+ fflush(stderr);
+ env.subtest_state->error_cnt = error_cnt;
+ if (cases[i].expected)
+ ASSERT_HAS_SUBSTR(env.subtest_state->log_buf, cases[i].expected, "expected output");
+ else
+ ASSERT_STREQ(env.subtest_state->log_buf, "", "expected no output");
+ test__end_subtest();
+ }
+ }
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/reg_bounds.c b/tools/testing/selftests/bpf/prog_tests/reg_bounds.c
index e261b0e872db..d93a0c7b1786 100644
--- a/tools/testing/selftests/bpf/prog_tests/reg_bounds.c
+++ b/tools/testing/selftests/bpf/prog_tests/reg_bounds.c
@@ -623,7 +623,7 @@ static void range_cond(enum num_t t, struct range x, struct range y,
*newx = range(t, x.a, x.b);
*newy = range(t, y.a + 1, y.b);
} else if (x.a == x.b && x.b == y.b) {
- /* X is a constant matching rigth side of Y */
+ /* X is a constant matching right side of Y */
*newx = range(t, x.a, x.b);
*newy = range(t, y.a, y.b - 1);
} else if (y.a == y.b && x.a == y.a) {
@@ -631,7 +631,7 @@ static void range_cond(enum num_t t, struct range x, struct range y,
*newx = range(t, x.a + 1, x.b);
*newy = range(t, y.a, y.b);
} else if (y.a == y.b && x.b == y.b) {
- /* Y is a constant matching rigth side of X */
+ /* Y is a constant matching right side of X */
*newx = range(t, x.a, x.b - 1);
*newy = range(t, y.a, y.b);
} else {
diff --git a/tools/testing/selftests/bpf/prog_tests/res_spin_lock.c b/tools/testing/selftests/bpf/prog_tests/res_spin_lock.c
index 0703e987df89..8c6c2043a432 100644
--- a/tools/testing/selftests/bpf/prog_tests/res_spin_lock.c
+++ b/tools/testing/selftests/bpf/prog_tests/res_spin_lock.c
@@ -99,3 +99,19 @@ end:
res_spin_lock__destroy(skel);
return;
}
+
+void serial_test_res_spin_lock_stress(void)
+{
+ if (libbpf_num_possible_cpus() < 3) {
+ test__skip();
+ return;
+ }
+
+ ASSERT_OK(load_module("bpf_test_rqspinlock.ko", false), "load module AA");
+ sleep(5);
+ unload_module("bpf_test_rqspinlock", false);
+
+ ASSERT_OK(load_module_params("bpf_test_rqspinlock.ko", "test_ab=1", false), "load module ABBA");
+ sleep(5);
+ unload_module("bpf_test_rqspinlock", false);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/spin_lock.c b/tools/testing/selftests/bpf/prog_tests/spin_lock.c
index e3ea5dc2f697..254fbfeab06a 100644
--- a/tools/testing/selftests/bpf/prog_tests/spin_lock.c
+++ b/tools/testing/selftests/bpf/prog_tests/spin_lock.c
@@ -13,22 +13,22 @@ static struct {
const char *err_msg;
} spin_lock_fail_tests[] = {
{ "lock_id_kptr_preserve",
- "5: (bf) r1 = r0 ; R0_w=ptr_foo(id=2,ref_obj_id=2) "
- "R1_w=ptr_foo(id=2,ref_obj_id=2) refs=2\n6: (85) call bpf_this_cpu_ptr#154\n"
+ "5: (bf) r1 = r0 ; R0=ptr_foo(id=2,ref_obj_id=2) "
+ "R1=ptr_foo(id=2,ref_obj_id=2) refs=2\n6: (85) call bpf_this_cpu_ptr#154\n"
"R1 type=ptr_ expected=percpu_ptr_" },
{ "lock_id_global_zero",
- "; R1_w=map_value(map=.data.A,ks=4,vs=4)\n2: (85) call bpf_this_cpu_ptr#154\n"
+ "; R1=map_value(map=.data.A,ks=4,vs=4)\n2: (85) call bpf_this_cpu_ptr#154\n"
"R1 type=map_value expected=percpu_ptr_" },
{ "lock_id_mapval_preserve",
"[0-9]\\+: (bf) r1 = r0 ;"
- " R0_w=map_value(id=1,map=array_map,ks=4,vs=8)"
- " R1_w=map_value(id=1,map=array_map,ks=4,vs=8)\n"
+ " R0=map_value(id=1,map=array_map,ks=4,vs=8)"
+ " R1=map_value(id=1,map=array_map,ks=4,vs=8)\n"
"[0-9]\\+: (85) call bpf_this_cpu_ptr#154\n"
"R1 type=map_value expected=percpu_ptr_" },
{ "lock_id_innermapval_preserve",
"[0-9]\\+: (bf) r1 = r0 ;"
" R0=map_value(id=2,ks=4,vs=8)"
- " R1_w=map_value(id=2,ks=4,vs=8)\n"
+ " R1=map_value(id=2,ks=4,vs=8)\n"
"[0-9]\\+: (85) call bpf_this_cpu_ptr#154\n"
"R1 type=map_value expected=percpu_ptr_" },
{ "lock_id_mismatch_kptr_kptr", "bpf_spin_unlock of different lock" },
diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id.c
index b7ba5cd47d96..271b5cc9fc01 100644
--- a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id.c
+++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id.c
@@ -39,7 +39,7 @@ retry:
bpf_map_update_elem(control_map_fd, &key, &val, 0);
/* for every element in stackid_hmap, we can find a corresponding one
- * in stackmap, and vise versa.
+ * in stackmap, and vice versa.
*/
err = compare_map_keys(stackid_hmap_fd, stackmap_fd);
if (CHECK(err, "compare_map_keys stackid_hmap vs. stackmap",
diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c
index 0832fd787457..b277dddd5af7 100644
--- a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c
+++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c
@@ -66,7 +66,7 @@ retry:
bpf_map_update_elem(control_map_fd, &key, &val, 0);
/* for every element in stackid_hmap, we can find a corresponding one
- * in stackmap, and vise versa.
+ * in stackmap, and vice versa.
*/
err = compare_map_keys(stackid_hmap_fd, stackmap_fd);
if (CHECK(err, "compare_map_keys stackid_hmap vs. stackmap",
diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_map.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_map.c
index df59e4ae2951..c23b97414813 100644
--- a/tools/testing/selftests/bpf/prog_tests/stacktrace_map.c
+++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_map.c
@@ -1,46 +1,27 @@
// SPDX-License-Identifier: GPL-2.0
#include <test_progs.h>
+#include "stacktrace_map.skel.h"
void test_stacktrace_map(void)
{
+ struct stacktrace_map *skel;
int control_map_fd, stackid_hmap_fd, stackmap_fd, stack_amap_fd;
- const char *prog_name = "oncpu";
- int err, prog_fd, stack_trace_len;
- const char *file = "./test_stacktrace_map.bpf.o";
- __u32 key, val, duration = 0;
- struct bpf_program *prog;
- struct bpf_object *obj;
- struct bpf_link *link;
+ int err, stack_trace_len;
+ __u32 key, val, stack_id, duration = 0;
+ __u64 stack[PERF_MAX_STACK_DEPTH];
- err = bpf_prog_test_load(file, BPF_PROG_TYPE_TRACEPOINT, &obj, &prog_fd);
- if (CHECK(err, "prog_load", "err %d errno %d\n", err, errno))
+ skel = stacktrace_map__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "skel_open_and_load"))
return;
- prog = bpf_object__find_program_by_name(obj, prog_name);
- if (CHECK(!prog, "find_prog", "prog '%s' not found\n", prog_name))
- goto close_prog;
-
- link = bpf_program__attach_tracepoint(prog, "sched", "sched_switch");
- if (!ASSERT_OK_PTR(link, "attach_tp"))
- goto close_prog;
-
- /* find map fds */
- control_map_fd = bpf_find_map(__func__, obj, "control_map");
- if (CHECK_FAIL(control_map_fd < 0))
- goto disable_pmu;
-
- stackid_hmap_fd = bpf_find_map(__func__, obj, "stackid_hmap");
- if (CHECK_FAIL(stackid_hmap_fd < 0))
- goto disable_pmu;
-
- stackmap_fd = bpf_find_map(__func__, obj, "stackmap");
- if (CHECK_FAIL(stackmap_fd < 0))
- goto disable_pmu;
-
- stack_amap_fd = bpf_find_map(__func__, obj, "stack_amap");
- if (CHECK_FAIL(stack_amap_fd < 0))
- goto disable_pmu;
+ control_map_fd = bpf_map__fd(skel->maps.control_map);
+ stackid_hmap_fd = bpf_map__fd(skel->maps.stackid_hmap);
+ stackmap_fd = bpf_map__fd(skel->maps.stackmap);
+ stack_amap_fd = bpf_map__fd(skel->maps.stack_amap);
+ err = stacktrace_map__attach(skel);
+ if (!ASSERT_OK(err, "skel_attach"))
+ goto out;
/* give some time for bpf program run */
sleep(1);
@@ -50,26 +31,32 @@ void test_stacktrace_map(void)
bpf_map_update_elem(control_map_fd, &key, &val, 0);
/* for every element in stackid_hmap, we can find a corresponding one
- * in stackmap, and vise versa.
+ * in stackmap, and vice versa.
*/
err = compare_map_keys(stackid_hmap_fd, stackmap_fd);
if (CHECK(err, "compare_map_keys stackid_hmap vs. stackmap",
"err %d errno %d\n", err, errno))
- goto disable_pmu;
+ goto out;
err = compare_map_keys(stackmap_fd, stackid_hmap_fd);
if (CHECK(err, "compare_map_keys stackmap vs. stackid_hmap",
"err %d errno %d\n", err, errno))
- goto disable_pmu;
+ goto out;
stack_trace_len = PERF_MAX_STACK_DEPTH * sizeof(__u64);
err = compare_stack_ips(stackmap_fd, stack_amap_fd, stack_trace_len);
if (CHECK(err, "compare_stack_ips stackmap vs. stack_amap",
"err %d errno %d\n", err, errno))
- goto disable_pmu;
-
-disable_pmu:
- bpf_link__destroy(link);
-close_prog:
- bpf_object__close(obj);
+ goto out;
+
+ stack_id = skel->bss->stack_id;
+ err = bpf_map_lookup_and_delete_elem(stackmap_fd, &stack_id, stack);
+ if (!ASSERT_OK(err, "lookup and delete target stack_id"))
+ goto out;
+
+ err = bpf_map_lookup_elem(stackmap_fd, &stack_id, stack);
+ if (!ASSERT_EQ(err, -ENOENT, "lookup deleted stack_id"))
+ goto out;
+out:
+ stacktrace_map__destroy(skel);
}
diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_map_raw_tp.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_map_raw_tp.c
index c6ef06f55cdb..e985d51d3d47 100644
--- a/tools/testing/selftests/bpf/prog_tests/stacktrace_map_raw_tp.c
+++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_map_raw_tp.c
@@ -5,7 +5,7 @@ void test_stacktrace_map_raw_tp(void)
{
const char *prog_name = "oncpu";
int control_map_fd, stackid_hmap_fd, stackmap_fd;
- const char *file = "./test_stacktrace_map.bpf.o";
+ const char *file = "./stacktrace_map.bpf.o";
__u32 key, val, duration = 0;
int err, prog_fd;
struct bpf_program *prog;
@@ -46,7 +46,7 @@ void test_stacktrace_map_raw_tp(void)
bpf_map_update_elem(control_map_fd, &key, &val, 0);
/* for every element in stackid_hmap, we can find a corresponding one
- * in stackmap, and vise versa.
+ * in stackmap, and vice versa.
*/
err = compare_map_keys(stackid_hmap_fd, stackmap_fd);
if (CHECK(err, "compare_map_keys stackid_hmap vs. stackmap",
diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_map_skip.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_map_skip.c
index 1932b1e0685c..dc2ccf6a14d1 100644
--- a/tools/testing/selftests/bpf/prog_tests/stacktrace_map_skip.c
+++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_map_skip.c
@@ -40,7 +40,7 @@ void test_stacktrace_map_skip(void)
skel->bss->control = 1;
/* for every element in stackid_hmap, we can find a corresponding one
- * in stackmap, and vise versa.
+ * in stackmap, and vice versa.
*/
err = compare_map_keys(stackid_hmap_fd, stackmap_fd);
if (!ASSERT_OK(err, "compare_map_keys stackid_hmap vs. stackmap"))
diff --git a/tools/testing/selftests/bpf/prog_tests/stream.c b/tools/testing/selftests/bpf/prog_tests/stream.c
index d9f0185dca61..c3cce5c292bd 100644
--- a/tools/testing/selftests/bpf/prog_tests/stream.c
+++ b/tools/testing/selftests/bpf/prog_tests/stream.c
@@ -2,7 +2,6 @@
/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
#include <test_progs.h>
#include <sys/mman.h>
-#include <regex.h>
#include "stream.skel.h"
#include "stream_fail.skel.h"
@@ -18,87 +17,6 @@ void test_stream_success(void)
return;
}
-struct {
- int prog_off;
- const char *errstr;
-} stream_error_arr[] = {
- {
- offsetof(struct stream, progs.stream_cond_break),
- "ERROR: Timeout detected for may_goto instruction\n"
- "CPU: [0-9]+ UID: 0 PID: [0-9]+ Comm: .*\n"
- "Call trace:\n"
- "([a-zA-Z_][a-zA-Z0-9_]*\\+0x[0-9a-fA-F]+/0x[0-9a-fA-F]+\n"
- "|[ \t]+[^\n]+\n)*",
- },
- {
- offsetof(struct stream, progs.stream_deadlock),
- "ERROR: AA or ABBA deadlock detected for bpf_res_spin_lock\n"
- "Attempted lock = (0x[0-9a-fA-F]+)\n"
- "Total held locks = 1\n"
- "Held lock\\[ 0\\] = \\1\n" // Lock address must match
- "CPU: [0-9]+ UID: 0 PID: [0-9]+ Comm: .*\n"
- "Call trace:\n"
- "([a-zA-Z_][a-zA-Z0-9_]*\\+0x[0-9a-fA-F]+/0x[0-9a-fA-F]+\n"
- "|[ \t]+[^\n]+\n)*",
- },
-};
-
-static int match_regex(const char *pattern, const char *string)
-{
- int err, rc;
- regex_t re;
-
- err = regcomp(&re, pattern, REG_EXTENDED | REG_NEWLINE);
- if (err)
- return -1;
- rc = regexec(&re, string, 0, NULL, 0);
- regfree(&re);
- return rc == 0 ? 1 : 0;
-}
-
-void test_stream_errors(void)
-{
- LIBBPF_OPTS(bpf_test_run_opts, opts);
- LIBBPF_OPTS(bpf_prog_stream_read_opts, ropts);
- struct stream *skel;
- int ret, prog_fd;
- char buf[1024];
-
- skel = stream__open_and_load();
- if (!ASSERT_OK_PTR(skel, "stream__open_and_load"))
- return;
-
- for (int i = 0; i < ARRAY_SIZE(stream_error_arr); i++) {
- struct bpf_program **prog;
-
- prog = (struct bpf_program **)(((char *)skel) + stream_error_arr[i].prog_off);
- prog_fd = bpf_program__fd(*prog);
- ret = bpf_prog_test_run_opts(prog_fd, &opts);
- ASSERT_OK(ret, "ret");
- ASSERT_OK(opts.retval, "retval");
-
-#if !defined(__x86_64__)
- ASSERT_TRUE(1, "Timed may_goto unsupported, skip.");
- if (i == 0) {
- ret = bpf_prog_stream_read(prog_fd, 2, buf, sizeof(buf), &ropts);
- ASSERT_EQ(ret, 0, "stream read");
- continue;
- }
-#endif
-
- ret = bpf_prog_stream_read(prog_fd, BPF_STREAM_STDERR, buf, sizeof(buf), &ropts);
- ASSERT_GT(ret, 0, "stream read");
- ASSERT_LE(ret, 1023, "len for buf");
- buf[ret] = '\0';
-
- ret = match_regex(stream_error_arr[i].errstr, buf);
- if (!ASSERT_TRUE(ret == 1, "regex match"))
- fprintf(stderr, "Output from stream:\n%s\n", buf);
- }
-
- stream__destroy(skel);
-}
-
void test_stream_syscall(void)
{
LIBBPF_OPTS(bpf_test_run_opts, opts);
@@ -139,3 +57,52 @@ void test_stream_syscall(void)
stream__destroy(skel);
}
+
+static void test_address(struct bpf_program *prog, unsigned long *fault_addr_p)
+{
+ LIBBPF_OPTS(bpf_test_run_opts, opts);
+ LIBBPF_OPTS(bpf_prog_stream_read_opts, ropts);
+ int ret, prog_fd;
+ char fault_addr[64];
+ char buf[1024];
+
+ prog_fd = bpf_program__fd(prog);
+
+ ret = bpf_prog_test_run_opts(prog_fd, &opts);
+ ASSERT_OK(ret, "ret");
+ ASSERT_OK(opts.retval, "retval");
+
+ sprintf(fault_addr, "0x%lx", *fault_addr_p);
+
+ ret = bpf_prog_stream_read(prog_fd, BPF_STREAM_STDERR, buf, sizeof(buf), &ropts);
+ ASSERT_GT(ret, 0, "stream read");
+ ASSERT_LE(ret, 1023, "len for buf");
+ buf[ret] = '\0';
+
+ if (!ASSERT_HAS_SUBSTR(buf, fault_addr, "fault_addr")) {
+ fprintf(stderr, "Output from stream:\n%s\n", buf);
+ fprintf(stderr, "Fault Addr: %s\n", fault_addr);
+ }
+}
+
+void test_stream_arena_fault_address(void)
+{
+ struct stream *skel;
+
+#if !defined(__x86_64__) && !defined(__aarch64__)
+ printf("%s:SKIP: arena fault reporting not supported\n", __func__);
+ test__skip();
+ return;
+#endif
+
+ skel = stream__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "stream__open_and_load"))
+ return;
+
+ if (test__start_subtest("read_fault"))
+ test_address(skel->progs.stream_arena_read_fault, &skel->bss->fault_addr);
+ if (test__start_subtest("write_fault"))
+ test_address(skel->progs.stream_arena_write_fault, &skel->bss->fault_addr);
+
+ stream__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/string_kfuncs.c b/tools/testing/selftests/bpf/prog_tests/string_kfuncs.c
index 35af8044d059..4d66fad3c8bd 100644
--- a/tools/testing/selftests/bpf/prog_tests/string_kfuncs.c
+++ b/tools/testing/selftests/bpf/prog_tests/string_kfuncs.c
@@ -8,6 +8,7 @@
static const char * const test_cases[] = {
"strcmp",
+ "strcasecmp",
"strchr",
"strchrnul",
"strnchr",
diff --git a/tools/testing/selftests/bpf/prog_tests/task_local_data.h b/tools/testing/selftests/bpf/prog_tests/task_local_data.h
new file mode 100644
index 000000000000..2de38776a2d4
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/task_local_data.h
@@ -0,0 +1,386 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __TASK_LOCAL_DATA_H
+#define __TASK_LOCAL_DATA_H
+
+#include <errno.h>
+#include <fcntl.h>
+#include <sched.h>
+#include <stdatomic.h>
+#include <stddef.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+
+#ifdef TLD_FREE_DATA_ON_THREAD_EXIT
+#include <pthread.h>
+#endif
+
+#include <bpf/bpf.h>
+
+/*
+ * OPTIONS
+ *
+ * Define the option before including the header
+ *
+ * TLD_FREE_DATA_ON_THREAD_EXIT - Frees memory on thread exit automatically
+ *
+ * Thread-specific memory for storing TLD is allocated lazily on the first call to
+ * tld_get_data(). The thread that calls it must also call tld_free() on thread exit
+ * to prevent memory leak. Pthread will be included if the option is defined. A pthread
+ * key will be registered with a destructor that calls tld_free().
+ *
+ *
+ * TLD_DYN_DATA_SIZE - The maximum size of memory allocated for TLDs created dynamically
+ * (default: 64 bytes)
+ *
+ * A TLD can be defined statically using TLD_DEFINE_KEY() or created on the fly using
+ * tld_create_key(). As the total size of TLDs created with tld_create_key() cannot be
+ * possibly known statically, a memory area of size TLD_DYN_DATA_SIZE will be allocated
+ * for these TLDs. This additional memory is allocated for every thread that calls
+ * tld_get_data() even if no tld_create_key are actually called, so be mindful of
+ * potential memory wastage. Use TLD_DEFINE_KEY() whenever possible as just enough memory
+ * will be allocated for TLDs created with it.
+ *
+ *
+ * TLD_NAME_LEN - The maximum length of the name of a TLD (default: 62)
+ *
+ * Setting TLD_NAME_LEN will affect the maximum number of TLDs a process can store,
+ * TLD_MAX_DATA_CNT.
+ *
+ *
+ * TLD_DATA_USE_ALIGNED_ALLOC - Always use aligned_alloc() instead of malloc()
+ *
+ * When allocating the memory for storing TLDs, we need to make sure there is a memory
+ * region of the X bytes within a page. This is due to the limit posed by UPTR: memory
+ * pinned to the kernel cannot exceed a page nor can it cross the page boundary. The
+ * library normally calls malloc(2*X) given X bytes of total TLDs, and only uses
+ * aligned_alloc(PAGE_SIZE, X) when X >= PAGE_SIZE / 2. This is to reduce memory wastage
+ * as not all memory allocator can use the exact amount of memory requested to fulfill
+ * aligned_alloc(). For example, some may round the size up to the alignment. Enable the
+ * option to always use aligned_alloc() if the implementation has low memory overhead.
+ */
+
+#define TLD_PAGE_SIZE getpagesize()
+#define TLD_PAGE_MASK (~(TLD_PAGE_SIZE - 1))
+
+#define TLD_ROUND_MASK(x, y) ((__typeof__(x))((y) - 1))
+#define TLD_ROUND_UP(x, y) ((((x) - 1) | TLD_ROUND_MASK(x, y)) + 1)
+
+#define TLD_READ_ONCE(x) (*(volatile typeof(x) *)&(x))
+
+#ifndef TLD_DYN_DATA_SIZE
+#define TLD_DYN_DATA_SIZE 64
+#endif
+
+#define TLD_MAX_DATA_CNT (TLD_PAGE_SIZE / sizeof(struct tld_metadata) - 1)
+
+#ifndef TLD_NAME_LEN
+#define TLD_NAME_LEN 62
+#endif
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+typedef struct {
+ __s16 off;
+} tld_key_t;
+
+struct tld_metadata {
+ char name[TLD_NAME_LEN];
+ _Atomic __u16 size;
+};
+
+struct tld_meta_u {
+ _Atomic __u8 cnt;
+ __u16 size;
+ struct tld_metadata metadata[];
+};
+
+struct tld_data_u {
+ __u64 start; /* offset of tld_data_u->data in a page */
+ char data[];
+};
+
+struct tld_map_value {
+ void *data;
+ struct tld_meta_u *meta;
+};
+
+struct tld_meta_u * _Atomic tld_meta_p __attribute__((weak));
+__thread struct tld_data_u *tld_data_p __attribute__((weak));
+__thread void *tld_data_alloc_p __attribute__((weak));
+
+#ifdef TLD_FREE_DATA_ON_THREAD_EXIT
+pthread_key_t tld_pthread_key __attribute__((weak));
+
+static void tld_free(void);
+
+static void __tld_thread_exit_handler(void *unused)
+{
+ tld_free();
+}
+#endif
+
+static int __tld_init_meta_p(void)
+{
+ struct tld_meta_u *meta, *uninit = NULL;
+ int err = 0;
+
+ meta = (struct tld_meta_u *)aligned_alloc(TLD_PAGE_SIZE, TLD_PAGE_SIZE);
+ if (!meta) {
+ err = -ENOMEM;
+ goto out;
+ }
+
+ memset(meta, 0, TLD_PAGE_SIZE);
+ meta->size = TLD_DYN_DATA_SIZE;
+
+ if (!atomic_compare_exchange_strong(&tld_meta_p, &uninit, meta)) {
+ free(meta);
+ goto out;
+ }
+
+#ifdef TLD_FREE_DATA_ON_THREAD_EXIT
+ pthread_key_create(&tld_pthread_key, __tld_thread_exit_handler);
+#endif
+out:
+ return err;
+}
+
+static int __tld_init_data_p(int map_fd)
+{
+ bool use_aligned_alloc = false;
+ struct tld_map_value map_val;
+ struct tld_data_u *data;
+ void *data_alloc = NULL;
+ int err, tid_fd = -1;
+
+ tid_fd = syscall(SYS_pidfd_open, sys_gettid(), O_EXCL);
+ if (tid_fd < 0) {
+ err = -errno;
+ goto out;
+ }
+
+#ifdef TLD_DATA_USE_ALIGNED_ALLOC
+ use_aligned_alloc = true;
+#endif
+
+ /*
+ * tld_meta_p->size = TLD_DYN_DATA_SIZE +
+ * total size of TLDs defined via TLD_DEFINE_KEY()
+ */
+ data_alloc = (use_aligned_alloc || tld_meta_p->size * 2 >= TLD_PAGE_SIZE) ?
+ aligned_alloc(TLD_PAGE_SIZE, tld_meta_p->size) :
+ malloc(tld_meta_p->size * 2);
+ if (!data_alloc) {
+ err = -ENOMEM;
+ goto out;
+ }
+
+ /*
+ * Always pass a page-aligned address to UPTR since the size of tld_map_value::data
+ * is a page in BTF. If data_alloc spans across two pages, use the page that contains large
+ * enough memory.
+ */
+ if (TLD_PAGE_SIZE - (~TLD_PAGE_MASK & (intptr_t)data_alloc) >= tld_meta_p->size) {
+ map_val.data = (void *)(TLD_PAGE_MASK & (intptr_t)data_alloc);
+ data = data_alloc;
+ data->start = (~TLD_PAGE_MASK & (intptr_t)data_alloc) +
+ offsetof(struct tld_data_u, data);
+ } else {
+ map_val.data = (void *)(TLD_ROUND_UP((intptr_t)data_alloc, TLD_PAGE_SIZE));
+ data = (void *)(TLD_ROUND_UP((intptr_t)data_alloc, TLD_PAGE_SIZE));
+ data->start = offsetof(struct tld_data_u, data);
+ }
+ map_val.meta = TLD_READ_ONCE(tld_meta_p);
+
+ err = bpf_map_update_elem(map_fd, &tid_fd, &map_val, 0);
+ if (err) {
+ free(data_alloc);
+ goto out;
+ }
+
+ tld_data_p = data;
+ tld_data_alloc_p = data_alloc;
+#ifdef TLD_FREE_DATA_ON_THREAD_EXIT
+ pthread_setspecific(tld_pthread_key, (void *)1);
+#endif
+out:
+ if (tid_fd >= 0)
+ close(tid_fd);
+ return err;
+}
+
+static tld_key_t __tld_create_key(const char *name, size_t size, bool dyn_data)
+{
+ int err, i, sz, off = 0;
+ __u8 cnt;
+
+ if (!TLD_READ_ONCE(tld_meta_p)) {
+ err = __tld_init_meta_p();
+ if (err)
+ return (tld_key_t){err};
+ }
+
+ for (i = 0; i < TLD_MAX_DATA_CNT; i++) {
+retry:
+ cnt = atomic_load(&tld_meta_p->cnt);
+ if (i < cnt) {
+ /* A metadata is not ready until size is updated with a non-zero value */
+ while (!(sz = atomic_load(&tld_meta_p->metadata[i].size)))
+ sched_yield();
+
+ if (!strncmp(tld_meta_p->metadata[i].name, name, TLD_NAME_LEN))
+ return (tld_key_t){-EEXIST};
+
+ off += TLD_ROUND_UP(sz, 8);
+ continue;
+ }
+
+ /*
+ * TLD_DEFINE_KEY() is given memory upto a page while at most
+ * TLD_DYN_DATA_SIZE is allocated for tld_create_key()
+ */
+ if (dyn_data) {
+ if (off + TLD_ROUND_UP(size, 8) > tld_meta_p->size)
+ return (tld_key_t){-E2BIG};
+ } else {
+ if (off + TLD_ROUND_UP(size, 8) > TLD_PAGE_SIZE - sizeof(struct tld_data_u))
+ return (tld_key_t){-E2BIG};
+ tld_meta_p->size += TLD_ROUND_UP(size, 8);
+ }
+
+ /*
+ * Only one tld_create_key() can increase the current cnt by one and
+ * takes the latest available slot. Other threads will check again if a new
+ * TLD can still be added, and then compete for the new slot after the
+ * succeeding thread update the size.
+ */
+ if (!atomic_compare_exchange_strong(&tld_meta_p->cnt, &cnt, cnt + 1))
+ goto retry;
+
+ strncpy(tld_meta_p->metadata[i].name, name, TLD_NAME_LEN);
+ atomic_store(&tld_meta_p->metadata[i].size, size);
+ return (tld_key_t){(__s16)off};
+ }
+
+ return (tld_key_t){-ENOSPC};
+}
+
+/**
+ * TLD_DEFINE_KEY() - Define a TLD and a global variable key associated with the TLD.
+ *
+ * @name: The name of the TLD
+ * @size: The size of the TLD
+ * @key: The variable name of the key. Cannot exceed TLD_NAME_LEN
+ *
+ * The macro can only be used in file scope.
+ *
+ * A global variable key of opaque type, tld_key_t, will be declared and initialized before
+ * main() starts. Use tld_key_is_err() or tld_key_err_or_zero() later to check if the key
+ * creation succeeded. Pass the key to tld_get_data() to get a pointer to the TLD.
+ * bpf programs can also fetch the same key by name.
+ *
+ * The total size of TLDs created using TLD_DEFINE_KEY() cannot exceed a page. Just
+ * enough memory will be allocated for each thread on the first call to tld_get_data().
+ */
+#define TLD_DEFINE_KEY(key, name, size) \
+tld_key_t key; \
+ \
+__attribute__((constructor)) \
+void __tld_define_key_##key(void) \
+{ \
+ key = __tld_create_key(name, size, false); \
+}
+
+/**
+ * tld_create_key() - Create a TLD and return a key associated with the TLD.
+ *
+ * @name: The name the TLD
+ * @size: The size of the TLD
+ *
+ * Return an opaque object key. Use tld_key_is_err() or tld_key_err_or_zero() to check
+ * if the key creation succeeded. Pass the key to tld_get_data() to get a pointer to
+ * locate the TLD. bpf programs can also fetch the same key by name.
+ *
+ * Use tld_create_key() only when a TLD needs to be created dynamically (e.g., @name is
+ * not known statically or a TLD needs to be created conditionally)
+ *
+ * An additional TLD_DYN_DATA_SIZE bytes are allocated per-thread to accommodate TLDs
+ * created dynamically with tld_create_key(). Since only a user page is pinned to the
+ * kernel, when TLDs created with TLD_DEFINE_KEY() uses more than TLD_PAGE_SIZE -
+ * TLD_DYN_DATA_SIZE, the buffer size will be limited to the rest of the page.
+ */
+__attribute__((unused))
+static tld_key_t tld_create_key(const char *name, size_t size)
+{
+ return __tld_create_key(name, size, true);
+}
+
+__attribute__((unused))
+static inline bool tld_key_is_err(tld_key_t key)
+{
+ return key.off < 0;
+}
+
+__attribute__((unused))
+static inline int tld_key_err_or_zero(tld_key_t key)
+{
+ return tld_key_is_err(key) ? key.off : 0;
+}
+
+/**
+ * tld_get_data() - Get a pointer to the TLD associated with the given key of the
+ * calling thread.
+ *
+ * @map_fd: A file descriptor of tld_data_map, the underlying BPF task local storage map
+ * of task local data.
+ * @key: A key object created by TLD_DEFINE_KEY() or tld_create_key().
+ *
+ * Return a pointer to the TLD if the key is valid; NULL if not enough memory for TLD
+ * for this thread, or the key is invalid. The returned pointer is guaranteed to be 8-byte
+ * aligned.
+ *
+ * Threads that call tld_get_data() must call tld_free() on exit to prevent
+ * memory leak if TLD_FREE_DATA_ON_THREAD_EXIT is not defined.
+ */
+__attribute__((unused))
+static void *tld_get_data(int map_fd, tld_key_t key)
+{
+ if (!TLD_READ_ONCE(tld_meta_p))
+ return NULL;
+
+ /* tld_data_p is allocated on the first invocation of tld_get_data() */
+ if (!tld_data_p && __tld_init_data_p(map_fd))
+ return NULL;
+
+ return tld_data_p->data + key.off;
+}
+
+/**
+ * tld_free() - Free task local data memory of the calling thread
+ *
+ * For the calling thread, all pointers to TLDs acquired before will become invalid.
+ *
+ * Users must call tld_free() on thread exit to prevent memory leak. Alternatively,
+ * define TLD_FREE_DATA_ON_THREAD_EXIT and a thread exit handler will be registered
+ * to free the memory automatically.
+ */
+__attribute__((unused))
+static void tld_free(void)
+{
+ if (tld_data_alloc_p) {
+ free(tld_data_alloc_p);
+ tld_data_alloc_p = NULL;
+ tld_data_p = NULL;
+ }
+}
+
+#ifdef __cplusplus
+} /* extern "C" */
+#endif
+
+#endif /* __TASK_LOCAL_DATA_H */
diff --git a/tools/testing/selftests/bpf/prog_tests/task_work_stress.c b/tools/testing/selftests/bpf/prog_tests/task_work_stress.c
new file mode 100644
index 000000000000..450d17d91a56
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/task_work_stress.c
@@ -0,0 +1,130 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+#include <test_progs.h>
+#include <string.h>
+#include <stdio.h>
+#include "task_work_stress.skel.h"
+#include <linux/bpf.h>
+#include <linux/perf_event.h>
+#include <sys/syscall.h>
+#include <time.h>
+#include <stdlib.h>
+#include <stdatomic.h>
+
+struct test_data {
+ int prog_fd;
+ atomic_int exit;
+};
+
+void *runner(void *test_data)
+{
+ struct test_data *td = test_data;
+ int err = 0;
+ LIBBPF_OPTS(bpf_test_run_opts, opts);
+
+ while (!err && !atomic_load(&td->exit))
+ err = bpf_prog_test_run_opts(td->prog_fd, &opts);
+
+ return NULL;
+}
+
+static int get_env_int(const char *str, int def)
+{
+ const char *s = getenv(str);
+ char *end;
+ int retval;
+
+ if (!s || !*s)
+ return def;
+ errno = 0;
+ retval = strtol(s, &end, 10);
+ if (errno || *end || retval < 0)
+ return def;
+ return retval;
+}
+
+static void task_work_run(bool enable_delete)
+{
+ struct task_work_stress *skel;
+ struct bpf_program *scheduler, *deleter;
+ int nthreads = 16;
+ int test_time_s = get_env_int("BPF_TASK_WORK_TEST_TIME", 1);
+ pthread_t tid[nthreads], tid_del;
+ bool started[nthreads], started_del = false;
+ struct test_data td_sched = { .exit = 0 }, td_del = { .exit = 1 };
+ int i, err;
+
+ skel = task_work_stress__open();
+ if (!ASSERT_OK_PTR(skel, "task_work__open"))
+ return;
+
+ scheduler = bpf_object__find_program_by_name(skel->obj, "schedule_task_work");
+ bpf_program__set_autoload(scheduler, true);
+
+ deleter = bpf_object__find_program_by_name(skel->obj, "delete_task_work");
+ bpf_program__set_autoload(deleter, true);
+
+ err = task_work_stress__load(skel);
+ if (!ASSERT_OK(err, "skel_load"))
+ goto cleanup;
+
+ for (i = 0; i < nthreads; ++i)
+ started[i] = false;
+
+ td_sched.prog_fd = bpf_program__fd(scheduler);
+ for (i = 0; i < nthreads; ++i) {
+ if (pthread_create(&tid[i], NULL, runner, &td_sched) != 0) {
+ fprintf(stderr, "could not start thread");
+ goto cancel;
+ }
+ started[i] = true;
+ }
+
+ if (enable_delete)
+ atomic_store(&td_del.exit, 0);
+
+ td_del.prog_fd = bpf_program__fd(deleter);
+ if (pthread_create(&tid_del, NULL, runner, &td_del) != 0) {
+ fprintf(stderr, "could not start thread");
+ goto cancel;
+ }
+ started_del = true;
+
+ /* Run stress test for some time */
+ sleep(test_time_s);
+
+cancel:
+ atomic_store(&td_sched.exit, 1);
+ atomic_store(&td_del.exit, 1);
+ for (i = 0; i < nthreads; ++i) {
+ if (started[i])
+ pthread_join(tid[i], NULL);
+ }
+
+ if (started_del)
+ pthread_join(tid_del, NULL);
+
+ ASSERT_GT(skel->bss->callback_scheduled, 0, "work scheduled");
+ /* Some scheduling attempts should have failed due to contention */
+ ASSERT_GT(skel->bss->schedule_error, 0, "schedule error");
+
+ if (enable_delete) {
+ /* If delete thread is enabled, it has cancelled some callbacks */
+ ASSERT_GT(skel->bss->delete_success, 0, "delete success");
+ ASSERT_LT(skel->bss->callback_success, skel->bss->callback_scheduled, "callbacks");
+ } else {
+ /* Without delete thread number of scheduled callbacks is the same as fired */
+ ASSERT_EQ(skel->bss->callback_success, skel->bss->callback_scheduled, "callbacks");
+ }
+
+cleanup:
+ task_work_stress__destroy(skel);
+}
+
+void test_task_work_stress(void)
+{
+ if (test__start_subtest("no_delete"))
+ task_work_run(false);
+ if (test__start_subtest("with_delete"))
+ task_work_run(true);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/test_struct_ops_id_ops_mapping.c b/tools/testing/selftests/bpf/prog_tests/test_struct_ops_id_ops_mapping.c
new file mode 100644
index 000000000000..fd8762ba4b67
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/test_struct_ops_id_ops_mapping.c
@@ -0,0 +1,74 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+#include "struct_ops_id_ops_mapping1.skel.h"
+#include "struct_ops_id_ops_mapping2.skel.h"
+
+static void test_st_ops_id_ops_mapping(void)
+{
+ struct struct_ops_id_ops_mapping1 *skel1 = NULL;
+ struct struct_ops_id_ops_mapping2 *skel2 = NULL;
+ struct bpf_map_info info = {};
+ __u32 len = sizeof(info);
+ int err, pid, prog1_fd, prog2_fd;
+
+ skel1 = struct_ops_id_ops_mapping1__open_and_load();
+ if (!ASSERT_OK_PTR(skel1, "struct_ops_id_ops_mapping1__open"))
+ goto out;
+
+ skel2 = struct_ops_id_ops_mapping2__open_and_load();
+ if (!ASSERT_OK_PTR(skel2, "struct_ops_id_ops_mapping2__open"))
+ goto out;
+
+ err = bpf_map_get_info_by_fd(bpf_map__fd(skel1->maps.st_ops_map),
+ &info, &len);
+ if (!ASSERT_OK(err, "bpf_map_get_info_by_fd"))
+ goto out;
+
+ skel1->bss->st_ops_id = info.id;
+
+ err = bpf_map_get_info_by_fd(bpf_map__fd(skel2->maps.st_ops_map),
+ &info, &len);
+ if (!ASSERT_OK(err, "bpf_map_get_info_by_fd"))
+ goto out;
+
+ skel2->bss->st_ops_id = info.id;
+
+ err = struct_ops_id_ops_mapping1__attach(skel1);
+ if (!ASSERT_OK(err, "struct_ops_id_ops_mapping1__attach"))
+ goto out;
+
+ err = struct_ops_id_ops_mapping2__attach(skel2);
+ if (!ASSERT_OK(err, "struct_ops_id_ops_mapping2__attach"))
+ goto out;
+
+ /* run tracing prog that calls .test_1 and checks return */
+ pid = getpid();
+ skel1->bss->test_pid = pid;
+ skel2->bss->test_pid = pid;
+ sys_gettid();
+ skel1->bss->test_pid = 0;
+ skel2->bss->test_pid = 0;
+
+ /* run syscall_prog that calls .test_1 and checks return */
+ prog1_fd = bpf_program__fd(skel1->progs.syscall_prog);
+ err = bpf_prog_test_run_opts(prog1_fd, NULL);
+ ASSERT_OK(err, "bpf_prog_test_run_opts");
+
+ prog2_fd = bpf_program__fd(skel2->progs.syscall_prog);
+ err = bpf_prog_test_run_opts(prog2_fd, NULL);
+ ASSERT_OK(err, "bpf_prog_test_run_opts");
+
+ ASSERT_EQ(skel1->bss->test_err, 0, "skel1->bss->test_err");
+ ASSERT_EQ(skel2->bss->test_err, 0, "skel2->bss->test_err");
+
+out:
+ struct_ops_id_ops_mapping1__destroy(skel1);
+ struct_ops_id_ops_mapping2__destroy(skel2);
+}
+
+void test_struct_ops_id_ops_mapping(void)
+{
+ if (test__start_subtest("st_ops_id_ops_mapping"))
+ test_st_ops_id_ops_mapping();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/test_task_local_data.c b/tools/testing/selftests/bpf/prog_tests/test_task_local_data.c
new file mode 100644
index 000000000000..9fd6306b455c
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/test_task_local_data.c
@@ -0,0 +1,297 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <pthread.h>
+#include <bpf/btf.h>
+#include <test_progs.h>
+
+#define TLD_FREE_DATA_ON_THREAD_EXIT
+#define TLD_DYN_DATA_SIZE 4096
+#include "task_local_data.h"
+
+struct test_tld_struct {
+ __u64 a;
+ __u64 b;
+ __u64 c;
+ __u64 d;
+};
+
+#include "test_task_local_data.skel.h"
+
+TLD_DEFINE_KEY(value0_key, "value0", sizeof(int));
+
+/*
+ * Reset task local data between subtests by clearing metadata other
+ * than the statically defined value0. This is safe as subtests run
+ * sequentially. Users of task local data library should not touch
+ * library internal.
+ */
+static void reset_tld(void)
+{
+ if (TLD_READ_ONCE(tld_meta_p)) {
+ /* Remove TLDs created by tld_create_key() */
+ tld_meta_p->cnt = 1;
+ tld_meta_p->size = TLD_DYN_DATA_SIZE;
+ memset(&tld_meta_p->metadata[1], 0,
+ (TLD_MAX_DATA_CNT - 1) * sizeof(struct tld_metadata));
+ }
+}
+
+/* Serialize access to bpf program's global variables */
+static pthread_mutex_t global_mutex;
+
+static tld_key_t *tld_keys;
+
+#define TEST_BASIC_THREAD_NUM 32
+
+void *test_task_local_data_basic_thread(void *arg)
+{
+ LIBBPF_OPTS(bpf_test_run_opts, opts);
+ struct test_task_local_data *skel = (struct test_task_local_data *)arg;
+ int fd, err, tid, *value0, *value1;
+ struct test_tld_struct *value2;
+
+ fd = bpf_map__fd(skel->maps.tld_data_map);
+
+ value0 = tld_get_data(fd, value0_key);
+ if (!ASSERT_OK_PTR(value0, "tld_get_data"))
+ goto out;
+
+ value1 = tld_get_data(fd, tld_keys[1]);
+ if (!ASSERT_OK_PTR(value1, "tld_get_data"))
+ goto out;
+
+ value2 = tld_get_data(fd, tld_keys[2]);
+ if (!ASSERT_OK_PTR(value2, "tld_get_data"))
+ goto out;
+
+ tid = sys_gettid();
+
+ *value0 = tid + 0;
+ *value1 = tid + 1;
+ value2->a = tid + 2;
+ value2->b = tid + 3;
+ value2->c = tid + 4;
+ value2->d = tid + 5;
+
+ pthread_mutex_lock(&global_mutex);
+ /* Run task_main that read task local data and save to global variables */
+ err = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.task_main), &opts);
+ ASSERT_OK(err, "run task_main");
+ ASSERT_OK(opts.retval, "task_main retval");
+
+ ASSERT_EQ(skel->bss->test_value0, tid + 0, "tld_get_data value0");
+ ASSERT_EQ(skel->bss->test_value1, tid + 1, "tld_get_data value1");
+ ASSERT_EQ(skel->bss->test_value2.a, tid + 2, "tld_get_data value2.a");
+ ASSERT_EQ(skel->bss->test_value2.b, tid + 3, "tld_get_data value2.b");
+ ASSERT_EQ(skel->bss->test_value2.c, tid + 4, "tld_get_data value2.c");
+ ASSERT_EQ(skel->bss->test_value2.d, tid + 5, "tld_get_data value2.d");
+ pthread_mutex_unlock(&global_mutex);
+
+ /* Make sure valueX are indeed local to threads */
+ ASSERT_EQ(*value0, tid + 0, "value0");
+ ASSERT_EQ(*value1, tid + 1, "value1");
+ ASSERT_EQ(value2->a, tid + 2, "value2.a");
+ ASSERT_EQ(value2->b, tid + 3, "value2.b");
+ ASSERT_EQ(value2->c, tid + 4, "value2.c");
+ ASSERT_EQ(value2->d, tid + 5, "value2.d");
+
+ *value0 = tid + 5;
+ *value1 = tid + 4;
+ value2->a = tid + 3;
+ value2->b = tid + 2;
+ value2->c = tid + 1;
+ value2->d = tid + 0;
+
+ /* Run task_main again */
+ pthread_mutex_lock(&global_mutex);
+ err = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.task_main), &opts);
+ ASSERT_OK(err, "run task_main");
+ ASSERT_OK(opts.retval, "task_main retval");
+
+ ASSERT_EQ(skel->bss->test_value0, tid + 5, "tld_get_data value0");
+ ASSERT_EQ(skel->bss->test_value1, tid + 4, "tld_get_data value1");
+ ASSERT_EQ(skel->bss->test_value2.a, tid + 3, "tld_get_data value2.a");
+ ASSERT_EQ(skel->bss->test_value2.b, tid + 2, "tld_get_data value2.b");
+ ASSERT_EQ(skel->bss->test_value2.c, tid + 1, "tld_get_data value2.c");
+ ASSERT_EQ(skel->bss->test_value2.d, tid + 0, "tld_get_data value2.d");
+ pthread_mutex_unlock(&global_mutex);
+
+out:
+ pthread_exit(NULL);
+}
+
+static void test_task_local_data_basic(void)
+{
+ struct test_task_local_data *skel;
+ pthread_t thread[TEST_BASIC_THREAD_NUM];
+ char dummy_key_name[TLD_NAME_LEN];
+ tld_key_t key;
+ int i, err;
+
+ reset_tld();
+
+ ASSERT_OK(pthread_mutex_init(&global_mutex, NULL), "pthread_mutex_init");
+
+ skel = test_task_local_data__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "skel_open_and_load"))
+ return;
+
+ tld_keys = calloc(TLD_MAX_DATA_CNT, sizeof(tld_key_t));
+ if (!ASSERT_OK_PTR(tld_keys, "calloc tld_keys"))
+ goto out;
+
+ ASSERT_FALSE(tld_key_is_err(value0_key), "TLD_DEFINE_KEY");
+ tld_keys[1] = tld_create_key("value1", sizeof(int));
+ ASSERT_FALSE(tld_key_is_err(tld_keys[1]), "tld_create_key");
+ tld_keys[2] = tld_create_key("value2", sizeof(struct test_tld_struct));
+ ASSERT_FALSE(tld_key_is_err(tld_keys[2]), "tld_create_key");
+
+ /*
+ * Shouldn't be able to store data exceed a page. Create a TLD just big
+ * enough to exceed a page. TLDs already created are int value0, int
+ * value1, and struct test_tld_struct value2.
+ */
+ key = tld_create_key("value_not_exist",
+ TLD_PAGE_SIZE - 2 * sizeof(int) - sizeof(struct test_tld_struct) + 1);
+ ASSERT_EQ(tld_key_err_or_zero(key), -E2BIG, "tld_create_key");
+
+ key = tld_create_key("value2", sizeof(struct test_tld_struct));
+ ASSERT_EQ(tld_key_err_or_zero(key), -EEXIST, "tld_create_key");
+
+ /* Shouldn't be able to create the (TLD_MAX_DATA_CNT+1)-th TLD */
+ for (i = 3; i < TLD_MAX_DATA_CNT; i++) {
+ snprintf(dummy_key_name, TLD_NAME_LEN, "dummy_value%d", i);
+ tld_keys[i] = tld_create_key(dummy_key_name, sizeof(int));
+ ASSERT_FALSE(tld_key_is_err(tld_keys[i]), "tld_create_key");
+ }
+ key = tld_create_key("value_not_exist", sizeof(struct test_tld_struct));
+ ASSERT_EQ(tld_key_err_or_zero(key), -ENOSPC, "tld_create_key");
+
+ /* Access TLDs from multiple threads and check if they are thread-specific */
+ for (i = 0; i < TEST_BASIC_THREAD_NUM; i++) {
+ err = pthread_create(&thread[i], NULL, test_task_local_data_basic_thread, skel);
+ if (!ASSERT_OK(err, "pthread_create"))
+ goto out;
+ }
+
+out:
+ for (i = 0; i < TEST_BASIC_THREAD_NUM; i++)
+ pthread_join(thread[i], NULL);
+
+ if (tld_keys) {
+ free(tld_keys);
+ tld_keys = NULL;
+ }
+ tld_free();
+ test_task_local_data__destroy(skel);
+}
+
+#define TEST_RACE_THREAD_NUM (TLD_MAX_DATA_CNT - 3)
+
+void *test_task_local_data_race_thread(void *arg)
+{
+ int err = 0, id = (intptr_t)arg;
+ char key_name[32];
+ tld_key_t key;
+
+ key = tld_create_key("value_not_exist", TLD_PAGE_SIZE + 1);
+ if (tld_key_err_or_zero(key) != -E2BIG) {
+ err = 1;
+ goto out;
+ }
+
+ /* Only one thread will succeed in creating value1 */
+ key = tld_create_key("value1", sizeof(int));
+ if (!tld_key_is_err(key))
+ tld_keys[1] = key;
+
+ /* Only one thread will succeed in creating value2 */
+ key = tld_create_key("value2", sizeof(struct test_tld_struct));
+ if (!tld_key_is_err(key))
+ tld_keys[2] = key;
+
+ snprintf(key_name, 32, "thread_%d", id);
+ tld_keys[id] = tld_create_key(key_name, sizeof(int));
+ if (tld_key_is_err(tld_keys[id]))
+ err = 2;
+out:
+ return (void *)(intptr_t)err;
+}
+
+static void test_task_local_data_race(void)
+{
+ LIBBPF_OPTS(bpf_test_run_opts, opts);
+ pthread_t thread[TEST_RACE_THREAD_NUM];
+ struct test_task_local_data *skel;
+ int fd, i, j, err, *data;
+ void *ret = NULL;
+
+ skel = test_task_local_data__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "skel_open_and_load"))
+ return;
+
+ tld_keys = calloc(TLD_MAX_DATA_CNT, sizeof(tld_key_t));
+ if (!ASSERT_OK_PTR(tld_keys, "calloc tld_keys"))
+ goto out;
+
+ fd = bpf_map__fd(skel->maps.tld_data_map);
+
+ ASSERT_FALSE(tld_key_is_err(value0_key), "TLD_DEFINE_KEY");
+ tld_keys[0] = value0_key;
+
+ for (j = 0; j < 100; j++) {
+ reset_tld();
+
+ for (i = 0; i < TEST_RACE_THREAD_NUM; i++) {
+ /*
+ * Try to make tld_create_key() race with each other. Call
+ * tld_create_key(), both valid and invalid, from different threads.
+ */
+ err = pthread_create(&thread[i], NULL, test_task_local_data_race_thread,
+ (void *)(intptr_t)(i + 3));
+ if (CHECK_FAIL(err))
+ break;
+ }
+
+ /* Wait for all tld_create_key() to return */
+ for (i = 0; i < TEST_RACE_THREAD_NUM; i++) {
+ pthread_join(thread[i], &ret);
+ if (CHECK_FAIL(ret))
+ break;
+ }
+
+ /* Write a unique number to each TLD */
+ for (i = 0; i < TLD_MAX_DATA_CNT; i++) {
+ data = tld_get_data(fd, tld_keys[i]);
+ if (CHECK_FAIL(!data))
+ break;
+ *data = i;
+ }
+
+ /* Read TLDs and check the value to see if any address collides with another */
+ for (i = 0; i < TLD_MAX_DATA_CNT; i++) {
+ data = tld_get_data(fd, tld_keys[i]);
+ if (CHECK_FAIL(*data != i))
+ break;
+ }
+
+ /* Run task_main to make sure no invalid TLDs are added */
+ err = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.task_main), &opts);
+ ASSERT_OK(err, "run task_main");
+ ASSERT_OK(opts.retval, "task_main retval");
+ }
+out:
+ if (tld_keys) {
+ free(tld_keys);
+ tld_keys = NULL;
+ }
+ tld_free();
+ test_task_local_data__destroy(skel);
+}
+
+void test_task_local_data(void)
+{
+ if (test__start_subtest("task_local_data_basic"))
+ test_task_local_data_basic();
+ if (test__start_subtest("task_local_data_race"))
+ test_task_local_data_race();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/test_task_work.c b/tools/testing/selftests/bpf/prog_tests/test_task_work.c
new file mode 100644
index 000000000000..774b31a5f6ca
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/test_task_work.c
@@ -0,0 +1,157 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+#include <test_progs.h>
+#include <string.h>
+#include <stdio.h>
+#include "task_work.skel.h"
+#include "task_work_fail.skel.h"
+#include <linux/bpf.h>
+#include <linux/perf_event.h>
+#include <sys/syscall.h>
+#include <time.h>
+
+static int perf_event_open(__u32 type, __u64 config, int pid)
+{
+ struct perf_event_attr attr = {
+ .type = type,
+ .config = config,
+ .size = sizeof(struct perf_event_attr),
+ .sample_period = 100000,
+ };
+
+ return syscall(__NR_perf_event_open, &attr, pid, -1, -1, 0);
+}
+
+struct elem {
+ char data[128];
+ struct bpf_task_work tw;
+};
+
+static int verify_map(struct bpf_map *map, const char *expected_data)
+{
+ int err;
+ struct elem value;
+ int processed_values = 0;
+ int k, sz;
+
+ sz = bpf_map__max_entries(map);
+ for (k = 0; k < sz; ++k) {
+ err = bpf_map__lookup_elem(map, &k, sizeof(int), &value, sizeof(struct elem), 0);
+ if (err)
+ continue;
+ if (!ASSERT_EQ(strcmp(expected_data, value.data), 0, "map data")) {
+ fprintf(stderr, "expected '%s', found '%s' in %s map", expected_data,
+ value.data, bpf_map__name(map));
+ return 2;
+ }
+ processed_values++;
+ }
+
+ return processed_values == 0;
+}
+
+static void task_work_run(const char *prog_name, const char *map_name)
+{
+ struct task_work *skel;
+ struct bpf_program *prog;
+ struct bpf_map *map;
+ struct bpf_link *link = NULL;
+ int err, pe_fd = -1, pid, status, pipefd[2];
+ char user_string[] = "hello world";
+
+ if (!ASSERT_NEQ(pipe(pipefd), -1, "pipe"))
+ return;
+
+ pid = fork();
+ if (pid == 0) {
+ __u64 num = 1;
+ int i;
+ char buf;
+
+ close(pipefd[1]);
+ read(pipefd[0], &buf, sizeof(buf));
+ close(pipefd[0]);
+
+ for (i = 0; i < 10000; ++i)
+ num *= time(0) % 7;
+ (void)num;
+ exit(0);
+ }
+ if (!ASSERT_GT(pid, 0, "fork() failed")) {
+ close(pipefd[0]);
+ close(pipefd[1]);
+ return;
+ }
+
+ skel = task_work__open();
+ if (!ASSERT_OK_PTR(skel, "task_work__open"))
+ return;
+
+ bpf_object__for_each_program(prog, skel->obj) {
+ bpf_program__set_autoload(prog, false);
+ }
+
+ prog = bpf_object__find_program_by_name(skel->obj, prog_name);
+ if (!ASSERT_OK_PTR(prog, "prog_name"))
+ goto cleanup;
+ bpf_program__set_autoload(prog, true);
+ skel->bss->user_ptr = (char *)user_string;
+
+ err = task_work__load(skel);
+ if (!ASSERT_OK(err, "skel_load"))
+ goto cleanup;
+
+ pe_fd = perf_event_open(PERF_TYPE_HARDWARE, PERF_COUNT_HW_CPU_CYCLES, pid);
+ if (pe_fd == -1 && (errno == ENOENT || errno == EOPNOTSUPP)) {
+ printf("%s:SKIP:no PERF_COUNT_HW_CPU_CYCLES\n", __func__);
+ test__skip();
+ goto cleanup;
+ }
+ if (!ASSERT_NEQ(pe_fd, -1, "pe_fd")) {
+ fprintf(stderr, "perf_event_open errno: %d, pid: %d\n", errno, pid);
+ goto cleanup;
+ }
+
+ link = bpf_program__attach_perf_event(prog, pe_fd);
+ if (!ASSERT_OK_PTR(link, "attach_perf_event"))
+ goto cleanup;
+
+ /* perf event fd ownership is passed to bpf_link */
+ pe_fd = -1;
+ close(pipefd[0]);
+ write(pipefd[1], user_string, 1);
+ close(pipefd[1]);
+ /* Wait to collect some samples */
+ waitpid(pid, &status, 0);
+ pid = 0;
+ map = bpf_object__find_map_by_name(skel->obj, map_name);
+ if (!ASSERT_OK_PTR(map, "find map_name"))
+ goto cleanup;
+ if (!ASSERT_OK(verify_map(map, user_string), "verify map"))
+ goto cleanup;
+cleanup:
+ if (pe_fd >= 0)
+ close(pe_fd);
+ bpf_link__destroy(link);
+ task_work__destroy(skel);
+ if (pid > 0) {
+ close(pipefd[0]);
+ write(pipefd[1], user_string, 1);
+ close(pipefd[1]);
+ waitpid(pid, &status, 0);
+ }
+}
+
+void test_task_work(void)
+{
+ if (test__start_subtest("test_task_work_hash_map"))
+ task_work_run("oncpu_hash_map", "hmap");
+
+ if (test__start_subtest("test_task_work_array_map"))
+ task_work_run("oncpu_array_map", "arrmap");
+
+ if (test__start_subtest("test_task_work_lru_map"))
+ task_work_run("oncpu_lru_map", "lrumap");
+
+ RUN_TESTS(task_work_fail);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/test_veristat.c b/tools/testing/selftests/bpf/prog_tests/test_veristat.c
index 367f47e4a936..b38c16b4247f 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_veristat.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_veristat.c
@@ -75,26 +75,26 @@ static void test_set_global_vars_succeeds(void)
" -vl2 > %s", fix->veristat, fix->tmpfile);
read(fix->fd, fix->output, fix->sz);
- __CHECK_STR("_w=0xf000000000000001 ", "var_s64 = 0xf000000000000001");
- __CHECK_STR("_w=0xfedcba9876543210 ", "var_u64 = 0xfedcba9876543210");
- __CHECK_STR("_w=0x80000000 ", "var_s32 = -0x80000000");
- __CHECK_STR("_w=0x76543210 ", "var_u32 = 0x76543210");
- __CHECK_STR("_w=0x8000 ", "var_s16 = -32768");
- __CHECK_STR("_w=0xecec ", "var_u16 = 60652");
- __CHECK_STR("_w=128 ", "var_s8 = -128");
- __CHECK_STR("_w=255 ", "var_u8 = 255");
- __CHECK_STR("_w=11 ", "var_ea = EA2");
- __CHECK_STR("_w=12 ", "var_eb = EB2");
- __CHECK_STR("_w=13 ", "var_ec = EC2");
- __CHECK_STR("_w=1 ", "var_b = 1");
- __CHECK_STR("_w=170 ", "struct1[2].struct2[1][2].u.var_u8[2]=170");
- __CHECK_STR("_w=0xaaaa ", "union1.var_u16 = 0xaaaa");
- __CHECK_STR("_w=171 ", "arr[3]= 171");
- __CHECK_STR("_w=172 ", "arr[EA2] =172");
- __CHECK_STR("_w=10 ", "enum_arr[EC2]=EA3");
- __CHECK_STR("_w=173 ", "matrix[31][7][11]=173");
- __CHECK_STR("_w=174 ", "struct1[2].struct2[1][2].u.mat[5][3]=174");
- __CHECK_STR("_w=175 ", "struct11[7][5].struct2[0][1].u.mat[3][0]=175");
+ __CHECK_STR("=0xf000000000000001 ", "var_s64 = 0xf000000000000001");
+ __CHECK_STR("=0xfedcba9876543210 ", "var_u64 = 0xfedcba9876543210");
+ __CHECK_STR("=0x80000000 ", "var_s32 = -0x80000000");
+ __CHECK_STR("=0x76543210 ", "var_u32 = 0x76543210");
+ __CHECK_STR("=0x8000 ", "var_s16 = -32768");
+ __CHECK_STR("=0xecec ", "var_u16 = 60652");
+ __CHECK_STR("=128 ", "var_s8 = -128");
+ __CHECK_STR("=255 ", "var_u8 = 255");
+ __CHECK_STR("=11 ", "var_ea = EA2");
+ __CHECK_STR("=12 ", "var_eb = EB2");
+ __CHECK_STR("=13 ", "var_ec = EC2");
+ __CHECK_STR("=1 ", "var_b = 1");
+ __CHECK_STR("=170 ", "struct1[2].struct2[1][2].u.var_u8[2]=170");
+ __CHECK_STR("=0xaaaa ", "union1.var_u16 = 0xaaaa");
+ __CHECK_STR("=171 ", "arr[3]= 171");
+ __CHECK_STR("=172 ", "arr[EA2] =172");
+ __CHECK_STR("=10 ", "enum_arr[EC2]=EA3");
+ __CHECK_STR("=173 ", "matrix[31][7][11]=173");
+ __CHECK_STR("=174 ", "struct1[2].struct2[1][2].u.mat[5][3]=174");
+ __CHECK_STR("=175 ", "struct11[7][5].struct2[0][1].u.mat[3][0]=175");
out:
teardown_fixture(fix);
@@ -117,8 +117,8 @@ static void test_set_global_vars_from_file_succeeds(void)
SYS(out, "%s set_global_vars.bpf.o -G \"@%s\" -vl2 > %s",
fix->veristat, input_file, fix->tmpfile);
read(fix->fd, fix->output, fix->sz);
- __CHECK_STR("_w=0x8000 ", "var_s16 = -32768");
- __CHECK_STR("_w=0xecec ", "var_u16 = 60652");
+ __CHECK_STR("=0x8000 ", "var_s16 = -32768");
+ __CHECK_STR("=0xecec ", "var_u16 = 60652");
out:
close(fd);
diff --git a/tools/testing/selftests/bpf/prog_tests/timer.c b/tools/testing/selftests/bpf/prog_tests/timer.c
index d66687f1ee6a..34f9ccce2602 100644
--- a/tools/testing/selftests/bpf/prog_tests/timer.c
+++ b/tools/testing/selftests/bpf/prog_tests/timer.c
@@ -3,6 +3,7 @@
#include <test_progs.h>
#include "timer.skel.h"
#include "timer_failure.skel.h"
+#include "timer_interrupt.skel.h"
#define NUM_THR 8
@@ -86,6 +87,10 @@ void serial_test_timer(void)
int err;
timer_skel = timer__open_and_load();
+ if (!timer_skel && errno == EOPNOTSUPP) {
+ test__skip();
+ return;
+ }
if (!ASSERT_OK_PTR(timer_skel, "timer_skel_load"))
return;
@@ -95,3 +100,36 @@ void serial_test_timer(void)
RUN_TESTS(timer_failure);
}
+
+void test_timer_interrupt(void)
+{
+ struct timer_interrupt *skel = NULL;
+ int err, prog_fd;
+ LIBBPF_OPTS(bpf_test_run_opts, opts);
+
+ skel = timer_interrupt__open_and_load();
+ if (!skel && errno == EOPNOTSUPP) {
+ test__skip();
+ return;
+ }
+ if (!ASSERT_OK_PTR(skel, "timer_interrupt__open_and_load"))
+ return;
+
+ err = timer_interrupt__attach(skel);
+ if (!ASSERT_OK(err, "timer_interrupt__attach"))
+ goto out;
+
+ prog_fd = bpf_program__fd(skel->progs.test_timer_interrupt);
+ err = bpf_prog_test_run_opts(prog_fd, &opts);
+ if (!ASSERT_OK(err, "bpf_prog_test_run_opts"))
+ goto out;
+
+ usleep(50);
+
+ ASSERT_EQ(skel->bss->in_interrupt, 0, "in_interrupt");
+ if (skel->bss->preempt_count)
+ ASSERT_NEQ(skel->bss->in_interrupt_cb, 0, "in_interrupt_cb");
+
+out:
+ timer_interrupt__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/timer_crash.c b/tools/testing/selftests/bpf/prog_tests/timer_crash.c
index f74b82305da8..b841597c8a3a 100644
--- a/tools/testing/selftests/bpf/prog_tests/timer_crash.c
+++ b/tools/testing/selftests/bpf/prog_tests/timer_crash.c
@@ -12,6 +12,10 @@ static void test_timer_crash_mode(int mode)
struct timer_crash *skel;
skel = timer_crash__open_and_load();
+ if (!skel && errno == EOPNOTSUPP) {
+ test__skip();
+ return;
+ }
if (!ASSERT_OK_PTR(skel, "timer_crash__open_and_load"))
return;
skel->bss->pid = getpid();
diff --git a/tools/testing/selftests/bpf/prog_tests/timer_lockup.c b/tools/testing/selftests/bpf/prog_tests/timer_lockup.c
index 1a2f99596916..eb303fa1e09a 100644
--- a/tools/testing/selftests/bpf/prog_tests/timer_lockup.c
+++ b/tools/testing/selftests/bpf/prog_tests/timer_lockup.c
@@ -59,6 +59,10 @@ void test_timer_lockup(void)
}
skel = timer_lockup__open_and_load();
+ if (!skel && errno == EOPNOTSUPP) {
+ test__skip();
+ return;
+ }
if (!ASSERT_OK_PTR(skel, "timer_lockup__open_and_load"))
return;
diff --git a/tools/testing/selftests/bpf/prog_tests/timer_mim.c b/tools/testing/selftests/bpf/prog_tests/timer_mim.c
index 9ff7843909e7..c930c7d7105b 100644
--- a/tools/testing/selftests/bpf/prog_tests/timer_mim.c
+++ b/tools/testing/selftests/bpf/prog_tests/timer_mim.c
@@ -65,6 +65,10 @@ void serial_test_timer_mim(void)
goto cleanup;
timer_skel = timer_mim__open_and_load();
+ if (!timer_skel && errno == EOPNOTSUPP) {
+ test__skip();
+ return;
+ }
if (!ASSERT_OK_PTR(timer_skel, "timer_skel_load"))
goto cleanup;
diff --git a/tools/testing/selftests/bpf/prog_tests/tracing_struct.c b/tools/testing/selftests/bpf/prog_tests/tracing_struct.c
index 19e68d4b3532..6f8c0bfb0415 100644
--- a/tools/testing/selftests/bpf/prog_tests/tracing_struct.c
+++ b/tools/testing/selftests/bpf/prog_tests/tracing_struct.c
@@ -112,10 +112,39 @@ destroy_skel:
tracing_struct_many_args__destroy(skel);
}
+static void test_union_args(void)
+{
+ struct tracing_struct *skel;
+ int err;
+
+ skel = tracing_struct__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "tracing_struct__open_and_load"))
+ return;
+
+ err = tracing_struct__attach(skel);
+ if (!ASSERT_OK(err, "tracing_struct__attach"))
+ goto out;
+
+ ASSERT_OK(trigger_module_test_read(256), "trigger_read");
+
+ ASSERT_EQ(skel->bss->ut1_a_a, 1, "ut1:a.arg.a");
+ ASSERT_EQ(skel->bss->ut1_b, 4, "ut1:b");
+ ASSERT_EQ(skel->bss->ut1_c, 5, "ut1:c");
+
+ ASSERT_EQ(skel->bss->ut2_a, 6, "ut2:a");
+ ASSERT_EQ(skel->bss->ut2_b_a, 2, "ut2:b.arg.a");
+ ASSERT_EQ(skel->bss->ut2_b_b, 3, "ut2:b.arg.b");
+
+out:
+ tracing_struct__destroy(skel);
+}
+
void test_tracing_struct(void)
{
if (test__start_subtest("struct_args"))
test_struct_args();
if (test__start_subtest("struct_many_args"))
test_struct_many_args();
+ if (test__start_subtest("union_args"))
+ test_union_args();
}
diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe.c b/tools/testing/selftests/bpf/prog_tests/uprobe.c
index cf3e0e7a64fa..86404476c1da 100644
--- a/tools/testing/selftests/bpf/prog_tests/uprobe.c
+++ b/tools/testing/selftests/bpf/prog_tests/uprobe.c
@@ -2,6 +2,7 @@
/* Copyright (c) 2023 Hengqi Chen */
#include <test_progs.h>
+#include <asm/ptrace.h>
#include "test_uprobe.skel.h"
static FILE *urand_spawn(int *pid)
@@ -33,7 +34,7 @@ static int urand_trigger(FILE **urand_pipe)
return exit_code;
}
-void test_uprobe(void)
+static void test_uprobe_attach(void)
{
LIBBPF_OPTS(bpf_uprobe_opts, uprobe_opts);
struct test_uprobe *skel;
@@ -93,3 +94,156 @@ cleanup:
pclose(urand_pipe);
test_uprobe__destroy(skel);
}
+
+#ifdef __x86_64__
+__naked __maybe_unused unsigned long uprobe_regs_change_trigger(void)
+{
+ asm volatile (
+ "ret\n"
+ );
+}
+
+static __naked void uprobe_regs_change(struct pt_regs *before, struct pt_regs *after)
+{
+ asm volatile (
+ "movq %r11, 48(%rdi)\n"
+ "movq %r10, 56(%rdi)\n"
+ "movq %r9, 64(%rdi)\n"
+ "movq %r8, 72(%rdi)\n"
+ "movq %rax, 80(%rdi)\n"
+ "movq %rcx, 88(%rdi)\n"
+ "movq %rdx, 96(%rdi)\n"
+ "movq %rsi, 104(%rdi)\n"
+ "movq %rdi, 112(%rdi)\n"
+
+ /* save 2nd argument */
+ "pushq %rsi\n"
+ "call uprobe_regs_change_trigger\n"
+
+ /* save return value and load 2nd argument pointer to rax */
+ "pushq %rax\n"
+ "movq 8(%rsp), %rax\n"
+
+ "movq %r11, 48(%rax)\n"
+ "movq %r10, 56(%rax)\n"
+ "movq %r9, 64(%rax)\n"
+ "movq %r8, 72(%rax)\n"
+ "movq %rcx, 88(%rax)\n"
+ "movq %rdx, 96(%rax)\n"
+ "movq %rsi, 104(%rax)\n"
+ "movq %rdi, 112(%rax)\n"
+
+ /* restore return value and 2nd argument */
+ "pop %rax\n"
+ "pop %rsi\n"
+
+ "movq %rax, 80(%rsi)\n"
+ "ret\n"
+ );
+}
+
+static void regs_common(void)
+{
+ struct pt_regs before = {}, after = {}, expected = {
+ .rax = 0xc0ffe,
+ .rcx = 0xbad,
+ .rdx = 0xdead,
+ .r8 = 0x8,
+ .r9 = 0x9,
+ .r10 = 0x10,
+ .r11 = 0x11,
+ .rdi = 0x12,
+ .rsi = 0x13,
+ };
+ LIBBPF_OPTS(bpf_uprobe_opts, uprobe_opts);
+ struct test_uprobe *skel;
+
+ skel = test_uprobe__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "skel_open"))
+ return;
+
+ skel->bss->my_pid = getpid();
+ skel->bss->regs = expected;
+
+ uprobe_opts.func_name = "uprobe_regs_change_trigger";
+ skel->links.test_regs_change = bpf_program__attach_uprobe_opts(skel->progs.test_regs_change,
+ -1,
+ "/proc/self/exe",
+ 0 /* offset */,
+ &uprobe_opts);
+ if (!ASSERT_OK_PTR(skel->links.test_regs_change, "bpf_program__attach_uprobe_opts"))
+ goto cleanup;
+
+ uprobe_regs_change(&before, &after);
+
+ ASSERT_EQ(after.rax, expected.rax, "ax");
+ ASSERT_EQ(after.rcx, expected.rcx, "cx");
+ ASSERT_EQ(after.rdx, expected.rdx, "dx");
+ ASSERT_EQ(after.r8, expected.r8, "r8");
+ ASSERT_EQ(after.r9, expected.r9, "r9");
+ ASSERT_EQ(after.r10, expected.r10, "r10");
+ ASSERT_EQ(after.r11, expected.r11, "r11");
+ ASSERT_EQ(after.rdi, expected.rdi, "rdi");
+ ASSERT_EQ(after.rsi, expected.rsi, "rsi");
+
+cleanup:
+ test_uprobe__destroy(skel);
+}
+
+static noinline unsigned long uprobe_regs_change_ip_1(void)
+{
+ return 0xc0ffee;
+}
+
+static noinline unsigned long uprobe_regs_change_ip_2(void)
+{
+ return 0xdeadbeef;
+}
+
+static void regs_ip(void)
+{
+ LIBBPF_OPTS(bpf_uprobe_opts, uprobe_opts);
+ struct test_uprobe *skel;
+ unsigned long ret;
+
+ skel = test_uprobe__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "skel_open"))
+ return;
+
+ skel->bss->my_pid = getpid();
+ skel->bss->ip = (unsigned long) uprobe_regs_change_ip_2;
+
+ uprobe_opts.func_name = "uprobe_regs_change_ip_1";
+ skel->links.test_regs_change_ip = bpf_program__attach_uprobe_opts(
+ skel->progs.test_regs_change_ip,
+ -1,
+ "/proc/self/exe",
+ 0 /* offset */,
+ &uprobe_opts);
+ if (!ASSERT_OK_PTR(skel->links.test_regs_change_ip, "bpf_program__attach_uprobe_opts"))
+ goto cleanup;
+
+ ret = uprobe_regs_change_ip_1();
+ ASSERT_EQ(ret, 0xdeadbeef, "ret");
+
+cleanup:
+ test_uprobe__destroy(skel);
+}
+
+static void test_uprobe_regs_change(void)
+{
+ if (test__start_subtest("regs_change_common"))
+ regs_common();
+ if (test__start_subtest("regs_change_ip"))
+ regs_ip();
+}
+#else
+static void test_uprobe_regs_change(void) { }
+#endif
+
+void test_uprobe(void)
+{
+ if (test__start_subtest("attach"))
+ test_uprobe_attach();
+ test_uprobe_regs_change();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c b/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c
index b17dc39a23db..6d75ede16e7c 100644
--- a/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c
+++ b/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c
@@ -8,22 +8,31 @@
#include <asm/ptrace.h>
#include <linux/compiler.h>
#include <linux/stringify.h>
+#include <linux/kernel.h>
#include <sys/wait.h>
#include <sys/syscall.h>
#include <sys/prctl.h>
#include <asm/prctl.h>
#include "uprobe_syscall.skel.h"
#include "uprobe_syscall_executed.skel.h"
+#include "bpf/libbpf_internal.h"
-__naked unsigned long uretprobe_regs_trigger(void)
+#define USDT_NOP .byte 0x0f, 0x1f, 0x44, 0x00, 0x00
+#include "usdt.h"
+
+#pragma GCC diagnostic ignored "-Wattributes"
+
+__attribute__((aligned(16)))
+__nocf_check __weak __naked unsigned long uprobe_regs_trigger(void)
{
asm volatile (
+ ".byte 0x0f, 0x1f, 0x44, 0x00, 0x00\n" /* nop5 */
"movq $0xdeadbeef, %rax\n"
"ret\n"
);
}
-__naked void uretprobe_regs(struct pt_regs *before, struct pt_regs *after)
+__naked void uprobe_regs(struct pt_regs *before, struct pt_regs *after)
{
asm volatile (
"movq %r15, 0(%rdi)\n"
@@ -44,15 +53,17 @@ __naked void uretprobe_regs(struct pt_regs *before, struct pt_regs *after)
"movq $0, 120(%rdi)\n" /* orig_rax */
"movq $0, 128(%rdi)\n" /* rip */
"movq $0, 136(%rdi)\n" /* cs */
+ "pushq %rax\n"
"pushf\n"
"pop %rax\n"
"movq %rax, 144(%rdi)\n" /* eflags */
+ "pop %rax\n"
"movq %rsp, 152(%rdi)\n" /* rsp */
"movq $0, 160(%rdi)\n" /* ss */
/* save 2nd argument */
"pushq %rsi\n"
- "call uretprobe_regs_trigger\n"
+ "call uprobe_regs_trigger\n"
/* save return value and load 2nd argument pointer to rax */
"pushq %rax\n"
@@ -92,25 +103,37 @@ __naked void uretprobe_regs(struct pt_regs *before, struct pt_regs *after)
);
}
-static void test_uretprobe_regs_equal(void)
+static void test_uprobe_regs_equal(bool retprobe)
{
+ LIBBPF_OPTS(bpf_uprobe_opts, opts,
+ .retprobe = retprobe,
+ );
struct uprobe_syscall *skel = NULL;
struct pt_regs before = {}, after = {};
unsigned long *pb = (unsigned long *) &before;
unsigned long *pa = (unsigned long *) &after;
unsigned long *pp;
+ unsigned long offset;
unsigned int i, cnt;
- int err;
+
+ offset = get_uprobe_offset(&uprobe_regs_trigger);
+ if (!ASSERT_GE(offset, 0, "get_uprobe_offset"))
+ return;
skel = uprobe_syscall__open_and_load();
if (!ASSERT_OK_PTR(skel, "uprobe_syscall__open_and_load"))
goto cleanup;
- err = uprobe_syscall__attach(skel);
- if (!ASSERT_OK(err, "uprobe_syscall__attach"))
+ skel->links.probe = bpf_program__attach_uprobe_opts(skel->progs.probe,
+ 0, "/proc/self/exe", offset, &opts);
+ if (!ASSERT_OK_PTR(skel->links.probe, "bpf_program__attach_uprobe_opts"))
goto cleanup;
- uretprobe_regs(&before, &after);
+ /* make sure uprobe gets optimized */
+ if (!retprobe)
+ uprobe_regs_trigger();
+
+ uprobe_regs(&before, &after);
pp = (unsigned long *) &skel->bss->regs;
cnt = sizeof(before)/sizeof(*pb);
@@ -119,7 +142,7 @@ static void test_uretprobe_regs_equal(void)
unsigned int offset = i * sizeof(unsigned long);
/*
- * Check register before and after uretprobe_regs_trigger call
+ * Check register before and after uprobe_regs_trigger call
* that triggers the uretprobe.
*/
switch (offset) {
@@ -133,7 +156,7 @@ static void test_uretprobe_regs_equal(void)
/*
* Check register seen from bpf program and register after
- * uretprobe_regs_trigger call
+ * uprobe_regs_trigger call (with rax exception, check below).
*/
switch (offset) {
/*
@@ -146,6 +169,15 @@ static void test_uretprobe_regs_equal(void)
case offsetof(struct pt_regs, rsp):
case offsetof(struct pt_regs, ss):
break;
+ /*
+ * uprobe does not see return value in rax, it needs to see the
+ * original (before) rax value
+ */
+ case offsetof(struct pt_regs, rax):
+ if (!retprobe) {
+ ASSERT_EQ(pp[i], pb[i], "uprobe rax prog-before value check");
+ break;
+ }
default:
if (!ASSERT_EQ(pp[i], pa[i], "register prog-after value check"))
fprintf(stdout, "failed register offset %u\n", offset);
@@ -175,7 +207,7 @@ static int write_bpf_testmod_uprobe(unsigned long offset)
return ret != n ? (int) ret : 0;
}
-static void test_uretprobe_regs_change(void)
+static void test_regs_change(void)
{
struct pt_regs before = {}, after = {};
unsigned long *pb = (unsigned long *) &before;
@@ -183,13 +215,16 @@ static void test_uretprobe_regs_change(void)
unsigned long cnt = sizeof(before)/sizeof(*pb);
unsigned int i, err, offset;
- offset = get_uprobe_offset(uretprobe_regs_trigger);
+ offset = get_uprobe_offset(uprobe_regs_trigger);
err = write_bpf_testmod_uprobe(offset);
if (!ASSERT_OK(err, "register_uprobe"))
return;
- uretprobe_regs(&before, &after);
+ /* make sure uprobe gets optimized */
+ uprobe_regs_trigger();
+
+ uprobe_regs(&before, &after);
err = write_bpf_testmod_uprobe(0);
if (!ASSERT_OK(err, "unregister_uprobe"))
@@ -252,6 +287,7 @@ static void test_uretprobe_syscall_call(void)
);
struct uprobe_syscall_executed *skel;
int pid, status, err, go[2], c = 0;
+ struct bpf_link *link;
if (!ASSERT_OK(pipe(go), "pipe"))
return;
@@ -277,11 +313,14 @@ static void test_uretprobe_syscall_call(void)
_exit(0);
}
- skel->links.test = bpf_program__attach_uprobe_multi(skel->progs.test, pid,
- "/proc/self/exe",
- "uretprobe_syscall_call", &opts);
- if (!ASSERT_OK_PTR(skel->links.test, "bpf_program__attach_uprobe_multi"))
+ skel->bss->pid = pid;
+
+ link = bpf_program__attach_uprobe_multi(skel->progs.test_uretprobe_multi,
+ pid, "/proc/self/exe",
+ "uretprobe_syscall_call", &opts);
+ if (!ASSERT_OK_PTR(link, "bpf_program__attach_uprobe_multi"))
goto cleanup;
+ skel->links.test_uretprobe_multi = link;
/* kick the child */
write(go[1], &c, 1);
@@ -301,6 +340,256 @@ cleanup:
close(go[0]);
}
+#define TRAMP "[uprobes-trampoline]"
+
+__attribute__((aligned(16)))
+__nocf_check __weak __naked void uprobe_test(void)
+{
+ asm volatile (" \n"
+ ".byte 0x0f, 0x1f, 0x44, 0x00, 0x00 \n"
+ "ret \n"
+ );
+}
+
+__attribute__((aligned(16)))
+__nocf_check __weak void usdt_test(void)
+{
+ USDT(optimized_uprobe, usdt);
+}
+
+static int find_uprobes_trampoline(void *tramp_addr)
+{
+ void *start, *end;
+ char line[128];
+ int ret = -1;
+ FILE *maps;
+
+ maps = fopen("/proc/self/maps", "r");
+ if (!maps) {
+ fprintf(stderr, "cannot open maps\n");
+ return -1;
+ }
+
+ while (fgets(line, sizeof(line), maps)) {
+ int m = -1;
+
+ /* We care only about private r-x mappings. */
+ if (sscanf(line, "%p-%p r-xp %*x %*x:%*x %*u %n", &start, &end, &m) != 2)
+ continue;
+ if (m < 0)
+ continue;
+ if (!strncmp(&line[m], TRAMP, sizeof(TRAMP)-1) && (start == tramp_addr)) {
+ ret = 0;
+ break;
+ }
+ }
+
+ fclose(maps);
+ return ret;
+}
+
+static unsigned char nop5[5] = { 0x0f, 0x1f, 0x44, 0x00, 0x00 };
+
+static void *find_nop5(void *fn)
+{
+ int i;
+
+ for (i = 0; i < 10; i++) {
+ if (!memcmp(nop5, fn + i, 5))
+ return fn + i;
+ }
+ return NULL;
+}
+
+typedef void (__attribute__((nocf_check)) *trigger_t)(void);
+
+static void *check_attach(struct uprobe_syscall_executed *skel, trigger_t trigger,
+ void *addr, int executed)
+{
+ struct __arch_relative_insn {
+ __u8 op;
+ __s32 raddr;
+ } __packed *call;
+ void *tramp = NULL;
+
+ /* Uprobe gets optimized after first trigger, so let's press twice. */
+ trigger();
+ trigger();
+
+ /* Make sure bpf program got executed.. */
+ ASSERT_EQ(skel->bss->executed, executed, "executed");
+
+ /* .. and check the trampoline is as expected. */
+ call = (struct __arch_relative_insn *) addr;
+ tramp = (void *) (call + 1) + call->raddr;
+ ASSERT_EQ(call->op, 0xe8, "call");
+ ASSERT_OK(find_uprobes_trampoline(tramp), "uprobes_trampoline");
+
+ return tramp;
+}
+
+static void check_detach(void *addr, void *tramp)
+{
+ /* [uprobes_trampoline] stays after detach */
+ ASSERT_OK(find_uprobes_trampoline(tramp), "uprobes_trampoline");
+ ASSERT_OK(memcmp(addr, nop5, 5), "nop5");
+}
+
+static void check(struct uprobe_syscall_executed *skel, struct bpf_link *link,
+ trigger_t trigger, void *addr, int executed)
+{
+ void *tramp;
+
+ tramp = check_attach(skel, trigger, addr, executed);
+ bpf_link__destroy(link);
+ check_detach(addr, tramp);
+}
+
+static void test_uprobe_legacy(void)
+{
+ struct uprobe_syscall_executed *skel = NULL;
+ LIBBPF_OPTS(bpf_uprobe_opts, opts,
+ .retprobe = true,
+ );
+ struct bpf_link *link;
+ unsigned long offset;
+
+ offset = get_uprobe_offset(&uprobe_test);
+ if (!ASSERT_GE(offset, 0, "get_uprobe_offset"))
+ goto cleanup;
+
+ /* uprobe */
+ skel = uprobe_syscall_executed__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "uprobe_syscall_executed__open_and_load"))
+ return;
+
+ skel->bss->pid = getpid();
+
+ link = bpf_program__attach_uprobe_opts(skel->progs.test_uprobe,
+ 0, "/proc/self/exe", offset, NULL);
+ if (!ASSERT_OK_PTR(link, "bpf_program__attach_uprobe_opts"))
+ goto cleanup;
+
+ check(skel, link, uprobe_test, uprobe_test, 2);
+
+ /* uretprobe */
+ skel->bss->executed = 0;
+
+ link = bpf_program__attach_uprobe_opts(skel->progs.test_uretprobe,
+ 0, "/proc/self/exe", offset, &opts);
+ if (!ASSERT_OK_PTR(link, "bpf_program__attach_uprobe_opts"))
+ goto cleanup;
+
+ check(skel, link, uprobe_test, uprobe_test, 2);
+
+cleanup:
+ uprobe_syscall_executed__destroy(skel);
+}
+
+static void test_uprobe_multi(void)
+{
+ struct uprobe_syscall_executed *skel = NULL;
+ LIBBPF_OPTS(bpf_uprobe_multi_opts, opts);
+ struct bpf_link *link;
+ unsigned long offset;
+
+ offset = get_uprobe_offset(&uprobe_test);
+ if (!ASSERT_GE(offset, 0, "get_uprobe_offset"))
+ goto cleanup;
+
+ opts.offsets = &offset;
+ opts.cnt = 1;
+
+ skel = uprobe_syscall_executed__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "uprobe_syscall_executed__open_and_load"))
+ return;
+
+ skel->bss->pid = getpid();
+
+ /* uprobe.multi */
+ link = bpf_program__attach_uprobe_multi(skel->progs.test_uprobe_multi,
+ 0, "/proc/self/exe", NULL, &opts);
+ if (!ASSERT_OK_PTR(link, "bpf_program__attach_uprobe_multi"))
+ goto cleanup;
+
+ check(skel, link, uprobe_test, uprobe_test, 2);
+
+ /* uretprobe.multi */
+ skel->bss->executed = 0;
+ opts.retprobe = true;
+ link = bpf_program__attach_uprobe_multi(skel->progs.test_uretprobe_multi,
+ 0, "/proc/self/exe", NULL, &opts);
+ if (!ASSERT_OK_PTR(link, "bpf_program__attach_uprobe_multi"))
+ goto cleanup;
+
+ check(skel, link, uprobe_test, uprobe_test, 2);
+
+cleanup:
+ uprobe_syscall_executed__destroy(skel);
+}
+
+static void test_uprobe_session(void)
+{
+ struct uprobe_syscall_executed *skel = NULL;
+ LIBBPF_OPTS(bpf_uprobe_multi_opts, opts,
+ .session = true,
+ );
+ struct bpf_link *link;
+ unsigned long offset;
+
+ offset = get_uprobe_offset(&uprobe_test);
+ if (!ASSERT_GE(offset, 0, "get_uprobe_offset"))
+ goto cleanup;
+
+ opts.offsets = &offset;
+ opts.cnt = 1;
+
+ skel = uprobe_syscall_executed__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "uprobe_syscall_executed__open_and_load"))
+ return;
+
+ skel->bss->pid = getpid();
+
+ link = bpf_program__attach_uprobe_multi(skel->progs.test_uprobe_session,
+ 0, "/proc/self/exe", NULL, &opts);
+ if (!ASSERT_OK_PTR(link, "bpf_program__attach_uprobe_multi"))
+ goto cleanup;
+
+ check(skel, link, uprobe_test, uprobe_test, 4);
+
+cleanup:
+ uprobe_syscall_executed__destroy(skel);
+}
+
+static void test_uprobe_usdt(void)
+{
+ struct uprobe_syscall_executed *skel;
+ struct bpf_link *link;
+ void *addr;
+
+ errno = 0;
+ addr = find_nop5(usdt_test);
+ if (!ASSERT_OK_PTR(addr, "find_nop5"))
+ return;
+
+ skel = uprobe_syscall_executed__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "uprobe_syscall_executed__open_and_load"))
+ return;
+
+ skel->bss->pid = getpid();
+
+ link = bpf_program__attach_usdt(skel->progs.test_usdt,
+ -1 /* all PIDs */, "/proc/self/exe",
+ "optimized_uprobe", "usdt", NULL);
+ if (!ASSERT_OK_PTR(link, "bpf_program__attach_usdt"))
+ goto cleanup;
+
+ check(skel, link, usdt_test, addr, 2);
+
+cleanup:
+ uprobe_syscall_executed__destroy(skel);
+}
+
/*
* Borrowed from tools/testing/selftests/x86/test_shadow_stack.c.
*
@@ -343,43 +632,172 @@ static void test_uretprobe_shadow_stack(void)
return;
}
- /* Run all of the uretprobe tests. */
- test_uretprobe_regs_equal();
- test_uretprobe_regs_change();
+ /* Run all the tests with shadow stack in place. */
+
+ test_uprobe_regs_equal(false);
+ test_uprobe_regs_equal(true);
test_uretprobe_syscall_call();
+ test_uprobe_legacy();
+ test_uprobe_multi();
+ test_uprobe_session();
+ test_uprobe_usdt();
+
+ test_regs_change();
+
ARCH_PRCTL(ARCH_SHSTK_DISABLE, ARCH_SHSTK_SHSTK);
}
-#else
-static void test_uretprobe_regs_equal(void)
+
+static volatile bool race_stop;
+
+static USDT_DEFINE_SEMA(race);
+
+static void *worker_trigger(void *arg)
{
- test__skip();
+ unsigned long rounds = 0;
+
+ while (!race_stop) {
+ uprobe_test();
+ rounds++;
+ }
+
+ printf("tid %d trigger rounds: %lu\n", gettid(), rounds);
+ return NULL;
}
-static void test_uretprobe_regs_change(void)
+static void *worker_attach(void *arg)
{
- test__skip();
+ LIBBPF_OPTS(bpf_uprobe_opts, opts);
+ struct uprobe_syscall_executed *skel;
+ unsigned long rounds = 0, offset;
+ const char *sema[2] = {
+ __stringify(USDT_SEMA(race)),
+ NULL,
+ };
+ unsigned long *ref;
+ int err;
+
+ offset = get_uprobe_offset(&uprobe_test);
+ if (!ASSERT_GE(offset, 0, "get_uprobe_offset"))
+ return NULL;
+
+ err = elf_resolve_syms_offsets("/proc/self/exe", 1, (const char **) &sema, &ref, STT_OBJECT);
+ if (!ASSERT_OK(err, "elf_resolve_syms_offsets_sema"))
+ return NULL;
+
+ opts.ref_ctr_offset = *ref;
+
+ skel = uprobe_syscall_executed__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "uprobe_syscall_executed__open_and_load"))
+ return NULL;
+
+ skel->bss->pid = getpid();
+
+ while (!race_stop) {
+ skel->links.test_uprobe = bpf_program__attach_uprobe_opts(skel->progs.test_uprobe,
+ 0, "/proc/self/exe", offset, &opts);
+ if (!ASSERT_OK_PTR(skel->links.test_uprobe, "bpf_program__attach_uprobe_opts"))
+ break;
+
+ bpf_link__destroy(skel->links.test_uprobe);
+ skel->links.test_uprobe = NULL;
+ rounds++;
+ }
+
+ printf("tid %d attach rounds: %lu hits: %d\n", gettid(), rounds, skel->bss->executed);
+ uprobe_syscall_executed__destroy(skel);
+ free(ref);
+ return NULL;
}
-static void test_uretprobe_syscall_call(void)
+static useconds_t race_msec(void)
{
- test__skip();
+ char *env;
+
+ env = getenv("BPF_SELFTESTS_UPROBE_SYSCALL_RACE_MSEC");
+ if (env)
+ return atoi(env);
+
+ /* default duration is 500ms */
+ return 500;
}
-static void test_uretprobe_shadow_stack(void)
+static void test_uprobe_race(void)
{
- test__skip();
+ int err, i, nr_threads;
+ pthread_t *threads;
+
+ nr_threads = libbpf_num_possible_cpus();
+ if (!ASSERT_GT(nr_threads, 0, "libbpf_num_possible_cpus"))
+ return;
+ nr_threads = max(2, nr_threads);
+
+ threads = alloca(sizeof(*threads) * nr_threads);
+ if (!ASSERT_OK_PTR(threads, "malloc"))
+ return;
+
+ for (i = 0; i < nr_threads; i++) {
+ err = pthread_create(&threads[i], NULL, i % 2 ? worker_trigger : worker_attach,
+ NULL);
+ if (!ASSERT_OK(err, "pthread_create"))
+ goto cleanup;
+ }
+
+ usleep(race_msec() * 1000);
+
+cleanup:
+ race_stop = true;
+ for (nr_threads = i, i = 0; i < nr_threads; i++)
+ pthread_join(threads[i], NULL);
+
+ ASSERT_FALSE(USDT_SEMA_IS_ACTIVE(race), "race_semaphore");
}
+
+#ifndef __NR_uprobe
+#define __NR_uprobe 336
#endif
-void test_uprobe_syscall(void)
+static void test_uprobe_error(void)
+{
+ long err = syscall(__NR_uprobe);
+
+ ASSERT_EQ(err, -1, "error");
+ ASSERT_EQ(errno, ENXIO, "errno");
+}
+
+static void __test_uprobe_syscall(void)
{
if (test__start_subtest("uretprobe_regs_equal"))
- test_uretprobe_regs_equal();
- if (test__start_subtest("uretprobe_regs_change"))
- test_uretprobe_regs_change();
+ test_uprobe_regs_equal(true);
if (test__start_subtest("uretprobe_syscall_call"))
test_uretprobe_syscall_call();
if (test__start_subtest("uretprobe_shadow_stack"))
test_uretprobe_shadow_stack();
+ if (test__start_subtest("uprobe_legacy"))
+ test_uprobe_legacy();
+ if (test__start_subtest("uprobe_multi"))
+ test_uprobe_multi();
+ if (test__start_subtest("uprobe_session"))
+ test_uprobe_session();
+ if (test__start_subtest("uprobe_usdt"))
+ test_uprobe_usdt();
+ if (test__start_subtest("uprobe_race"))
+ test_uprobe_race();
+ if (test__start_subtest("uprobe_error"))
+ test_uprobe_error();
+ if (test__start_subtest("uprobe_regs_equal"))
+ test_uprobe_regs_equal(false);
+ if (test__start_subtest("regs_change"))
+ test_regs_change();
+}
+#else
+static void __test_uprobe_syscall(void)
+{
+ test__skip();
+}
+#endif
+
+void test_uprobe_syscall(void)
+{
+ __test_uprobe_syscall();
}
diff --git a/tools/testing/selftests/bpf/prog_tests/usdt.c b/tools/testing/selftests/bpf/prog_tests/usdt.c
index 9057e983cc54..4f7f45e69315 100644
--- a/tools/testing/selftests/bpf/prog_tests/usdt.c
+++ b/tools/testing/selftests/bpf/prog_tests/usdt.c
@@ -40,12 +40,79 @@ static void __always_inline trigger_func(int x) {
}
}
-static void subtest_basic_usdt(void)
+#if defined(__x86_64__) || defined(__i386__)
+/*
+ * SIB (Scale-Index-Base) addressing format: "size@(base_reg, index_reg, scale)"
+ * - 'size' is the size in bytes of the array element, and its sign indicates
+ * whether the type is signed (negative) or unsigned (positive).
+ * - 'base_reg' is the register holding the base address, normally rdx or edx
+ * - 'index_reg' is the register holding the index, normally rax or eax
+ * - 'scale' is the scaling factor (typically 1, 2, 4, or 8), which matches the
+ * size of the element type.
+ *
+ * For example, for an array of 'short' (signed 2-byte elements), the SIB spec would be:
+ * - size: -2 (negative because 'short' is signed)
+ * - scale: 2 (since sizeof(short) == 2)
+ *
+ * The resulting SIB format: "-2@(%%rdx,%%rax,2)" for x86_64, "-2@(%%edx,%%eax,2)" for i386
+ */
+static volatile short array[] = {-1, -2, -3, -4};
+
+#if defined(__x86_64__)
+#define USDT_SIB_ARG_SPEC -2@(%%rdx,%%rax,2)
+#else
+#define USDT_SIB_ARG_SPEC -2@(%%edx,%%eax,2)
+#endif
+
+unsigned short test_usdt_sib_semaphore SEC(".probes");
+
+static void trigger_sib_spec(void)
+{
+ /*
+ * Force SIB addressing with inline assembly.
+ *
+ * You must compile with -std=gnu99 or -std=c99 to use the
+ * STAP_PROBE_ASM macro.
+ *
+ * The STAP_PROBE_ASM macro generates a quoted string that gets
+ * inserted between the surrounding assembly instructions. In this
+ * case, USDT_SIB_ARG_SPEC is embedded directly into the instruction
+ * stream, creating a probe point between the asm statement boundaries.
+ * It works fine with gcc/clang.
+ *
+ * Register constraints:
+ * - "d"(array): Binds the 'array' variable to %rdx or %edx register
+ * - "a"(0): Binds the constant 0 to %rax or %eax register
+ * These ensure that when USDT_SIB_ARG_SPEC references %%rdx(%edx) and
+ * %%rax(%eax), they contain the expected values for SIB addressing.
+ *
+ * The "memory" clobber prevents the compiler from reordering memory
+ * accesses around the probe point, ensuring that the probe behavior
+ * is predictable and consistent.
+ */
+ asm volatile(
+ STAP_PROBE_ASM(test, usdt_sib, USDT_SIB_ARG_SPEC)
+ :
+ : "d"(array), "a"(0)
+ : "memory"
+ );
+}
+#endif
+
+static void subtest_basic_usdt(bool optimized)
{
LIBBPF_OPTS(bpf_usdt_opts, opts);
struct test_usdt *skel;
struct test_usdt__bss *bss;
- int err, i;
+ int err, i, called;
+ const __u64 expected_cookie = 0xcafedeadbeeffeed;
+
+#define TRIGGER(x) ({ \
+ trigger_func(x); \
+ if (optimized) \
+ trigger_func(x); \
+ optimized ? 2 : 1; \
+ })
skel = test_usdt__open_and_load();
if (!ASSERT_OK_PTR(skel, "skel_open"))
@@ -59,20 +126,29 @@ static void subtest_basic_usdt(void)
goto cleanup;
/* usdt0 won't be auto-attached */
- opts.usdt_cookie = 0xcafedeadbeeffeed;
+ opts.usdt_cookie = expected_cookie;
skel->links.usdt0 = bpf_program__attach_usdt(skel->progs.usdt0,
0 /*self*/, "/proc/self/exe",
"test", "usdt0", &opts);
if (!ASSERT_OK_PTR(skel->links.usdt0, "usdt0_link"))
goto cleanup;
- trigger_func(1);
+#if defined(__x86_64__) || defined(__i386__)
+ opts.usdt_cookie = expected_cookie;
+ skel->links.usdt_sib = bpf_program__attach_usdt(skel->progs.usdt_sib,
+ 0 /*self*/, "/proc/self/exe",
+ "test", "usdt_sib", &opts);
+ if (!ASSERT_OK_PTR(skel->links.usdt_sib, "usdt_sib_link"))
+ goto cleanup;
+#endif
+
+ alled = TRIGGER(1);
- ASSERT_EQ(bss->usdt0_called, 1, "usdt0_called");
- ASSERT_EQ(bss->usdt3_called, 1, "usdt3_called");
- ASSERT_EQ(bss->usdt12_called, 1, "usdt12_called");
+ ASSERT_EQ(bss->usdt0_called, called, "usdt0_called");
+ ASSERT_EQ(bss->usdt3_called, called, "usdt3_called");
+ ASSERT_EQ(bss->usdt12_called, called, "usdt12_called");
- ASSERT_EQ(bss->usdt0_cookie, 0xcafedeadbeeffeed, "usdt0_cookie");
+ ASSERT_EQ(bss->usdt0_cookie, expected_cookie, "usdt0_cookie");
ASSERT_EQ(bss->usdt0_arg_cnt, 0, "usdt0_arg_cnt");
ASSERT_EQ(bss->usdt0_arg_ret, -ENOENT, "usdt0_arg_ret");
ASSERT_EQ(bss->usdt0_arg_size, -ENOENT, "usdt0_arg_size");
@@ -119,11 +195,11 @@ static void subtest_basic_usdt(void)
* bpf_program__attach_usdt() handles this properly and attaches to
* all possible places of USDT invocation.
*/
- trigger_func(2);
+ called += TRIGGER(2);
- ASSERT_EQ(bss->usdt0_called, 2, "usdt0_called");
- ASSERT_EQ(bss->usdt3_called, 2, "usdt3_called");
- ASSERT_EQ(bss->usdt12_called, 2, "usdt12_called");
+ ASSERT_EQ(bss->usdt0_called, called, "usdt0_called");
+ ASSERT_EQ(bss->usdt3_called, called, "usdt3_called");
+ ASSERT_EQ(bss->usdt12_called, called, "usdt12_called");
/* only check values that depend on trigger_func()'s input value */
ASSERT_EQ(bss->usdt3_args[0], 2, "usdt3_arg1");
@@ -142,9 +218,9 @@ static void subtest_basic_usdt(void)
if (!ASSERT_OK_PTR(skel->links.usdt3, "usdt3_reattach"))
goto cleanup;
- trigger_func(3);
+ called += TRIGGER(3);
- ASSERT_EQ(bss->usdt3_called, 3, "usdt3_called");
+ ASSERT_EQ(bss->usdt3_called, called, "usdt3_called");
/* this time usdt3 has custom cookie */
ASSERT_EQ(bss->usdt3_cookie, 0xBADC00C51E, "usdt3_cookie");
ASSERT_EQ(bss->usdt3_arg_cnt, 3, "usdt3_arg_cnt");
@@ -156,8 +232,19 @@ static void subtest_basic_usdt(void)
ASSERT_EQ(bss->usdt3_args[1], 42, "usdt3_arg2");
ASSERT_EQ(bss->usdt3_args[2], (uintptr_t)&bla, "usdt3_arg3");
+#if defined(__x86_64__) || defined(__i386__)
+ trigger_sib_spec();
+ ASSERT_EQ(bss->usdt_sib_called, 1, "usdt_sib_called");
+ ASSERT_EQ(bss->usdt_sib_cookie, expected_cookie, "usdt_sib_cookie");
+ ASSERT_EQ(bss->usdt_sib_arg_cnt, 1, "usdt_sib_arg_cnt");
+ ASSERT_EQ(bss->usdt_sib_arg, nums[0], "usdt_sib_arg");
+ ASSERT_EQ(bss->usdt_sib_arg_ret, 0, "usdt_sib_arg_ret");
+ ASSERT_EQ(bss->usdt_sib_arg_size, sizeof(nums[0]), "usdt_sib_arg_size");
+#endif
+
cleanup:
test_usdt__destroy(skel);
+#undef TRIGGER
}
unsigned short test_usdt_100_semaphore SEC(".probes");
@@ -425,7 +512,11 @@ cleanup:
void test_usdt(void)
{
if (test__start_subtest("basic"))
- subtest_basic_usdt();
+ subtest_basic_usdt(false);
+#ifdef __x86_64__
+ if (test__start_subtest("basic_optimized"))
+ subtest_basic_usdt(true);
+#endif
if (test__start_subtest("multispec"))
subtest_multispec_usdt();
if (test__start_subtest("urand_auto_attach"))
diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c
index 77ec95d4ffaa..28e81161e6fc 100644
--- a/tools/testing/selftests/bpf/prog_tests/verifier.c
+++ b/tools/testing/selftests/bpf/prog_tests/verifier.c
@@ -46,6 +46,7 @@
#include "verifier_ldsx.skel.h"
#include "verifier_leak_ptr.skel.h"
#include "verifier_linked_scalars.skel.h"
+#include "verifier_live_stack.skel.h"
#include "verifier_load_acquire.skel.h"
#include "verifier_loops1.skel.h"
#include "verifier_lwt.skel.h"
@@ -59,6 +60,7 @@
#include "verifier_meta_access.skel.h"
#include "verifier_movsx.skel.h"
#include "verifier_mtu.skel.h"
+#include "verifier_mul.skel.h"
#include "verifier_netfilter_ctx.skel.h"
#include "verifier_netfilter_retcode.skel.h"
#include "verifier_bpf_fastcall.skel.h"
@@ -183,6 +185,7 @@ void test_verifier_ld_ind(void) { RUN(verifier_ld_ind); }
void test_verifier_ldsx(void) { RUN(verifier_ldsx); }
void test_verifier_leak_ptr(void) { RUN(verifier_leak_ptr); }
void test_verifier_linked_scalars(void) { RUN(verifier_linked_scalars); }
+void test_verifier_live_stack(void) { RUN(verifier_live_stack); }
void test_verifier_loops1(void) { RUN(verifier_loops1); }
void test_verifier_lwt(void) { RUN(verifier_lwt); }
void test_verifier_map_in_map(void) { RUN(verifier_map_in_map); }
@@ -194,6 +197,7 @@ void test_verifier_may_goto_1(void) { RUN(verifier_may_goto_1); }
void test_verifier_may_goto_2(void) { RUN(verifier_may_goto_2); }
void test_verifier_meta_access(void) { RUN(verifier_meta_access); }
void test_verifier_movsx(void) { RUN(verifier_movsx); }
+void test_verifier_mul(void) { RUN(verifier_mul); }
void test_verifier_netfilter_ctx(void) { RUN(verifier_netfilter_ctx); }
void test_verifier_netfilter_retcode(void) { RUN(verifier_netfilter_retcode); }
void test_verifier_bpf_fastcall(void) { RUN(verifier_bpf_fastcall); }
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c b/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c
index b9d9f0a502ce..178292d1251a 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c
@@ -9,6 +9,7 @@
#define TX_NETNS "xdp_context_tx"
#define RX_NETNS "xdp_context_rx"
#define TAP_NAME "tap0"
+#define DUMMY_NAME "dum0"
#define TAP_NETNS "xdp_context_tuntap"
#define TEST_PAYLOAD_LEN 32
@@ -96,9 +97,7 @@ void test_xdp_context_test_run(void)
/* Meta data must be 255 bytes or smaller */
test_xdp_context_error(prog_fd, opts, 0, 256, sizeof(data), 0, 0, 0);
- /* Total size of data must match data_end - data_meta */
- test_xdp_context_error(prog_fd, opts, 0, sizeof(__u32),
- sizeof(data) - 1, 0, 0, 0);
+ /* Total size of data must be data_end - data_meta or larger */
test_xdp_context_error(prog_fd, opts, 0, sizeof(__u32),
sizeof(data) + 1, 0, 0, 0);
@@ -156,15 +155,30 @@ err:
return -1;
}
-static void assert_test_result(struct test_xdp_meta *skel)
+static int write_test_packet(int tap_fd)
+{
+ __u8 packet[sizeof(struct ethhdr) + TEST_PAYLOAD_LEN];
+ int n;
+
+ /* The ethernet header doesn't need to be valid for this test */
+ memset(packet, 0, sizeof(struct ethhdr));
+ memcpy(packet + sizeof(struct ethhdr), test_payload, TEST_PAYLOAD_LEN);
+
+ n = write(tap_fd, packet, sizeof(packet));
+ if (!ASSERT_EQ(n, sizeof(packet), "write packet"))
+ return -1;
+
+ return 0;
+}
+
+static void assert_test_result(const struct bpf_map *result_map)
{
int err;
__u32 map_key = 0;
__u8 map_value[TEST_PAYLOAD_LEN];
- err = bpf_map__lookup_elem(skel->maps.test_result, &map_key,
- sizeof(map_key), &map_value,
- TEST_PAYLOAD_LEN, BPF_ANY);
+ err = bpf_map__lookup_elem(result_map, &map_key, sizeof(map_key),
+ &map_value, TEST_PAYLOAD_LEN, BPF_ANY);
if (!ASSERT_OK(err, "lookup test_result"))
return;
@@ -172,6 +186,18 @@ static void assert_test_result(struct test_xdp_meta *skel)
"test_result map contains test payload");
}
+static bool clear_test_result(struct bpf_map *result_map)
+{
+ const __u8 v[sizeof(test_payload)] = {};
+ const __u32 k = 0;
+ int err;
+
+ err = bpf_map__update_elem(result_map, &k, sizeof(k), v, sizeof(v), BPF_ANY);
+ ASSERT_OK(err, "update test_result");
+
+ return err == 0;
+}
+
void test_xdp_context_veth(void)
{
LIBBPF_OPTS(bpf_tc_hook, tc_hook, .attach_point = BPF_TC_INGRESS);
@@ -248,7 +274,7 @@ void test_xdp_context_veth(void)
if (!ASSERT_OK(ret, "send_test_packet"))
goto close;
- assert_test_result(skel);
+ assert_test_result(skel->maps.test_result);
close:
close_netns(nstoken);
@@ -257,17 +283,21 @@ close:
netns_free(tx_ns);
}
-void test_xdp_context_tuntap(void)
+static void test_tuntap(struct bpf_program *xdp_prog,
+ struct bpf_program *tc_prio_1_prog,
+ struct bpf_program *tc_prio_2_prog,
+ struct bpf_map *result_map)
{
LIBBPF_OPTS(bpf_tc_hook, tc_hook, .attach_point = BPF_TC_INGRESS);
LIBBPF_OPTS(bpf_tc_opts, tc_opts, .handle = 1, .priority = 1);
struct netns_obj *ns = NULL;
- struct test_xdp_meta *skel = NULL;
- __u8 packet[sizeof(struct ethhdr) + TEST_PAYLOAD_LEN];
int tap_fd = -1;
int tap_ifindex;
int ret;
+ if (!clear_test_result(result_map))
+ return;
+
ns = netns_new(TAP_NETNS, true);
if (!ASSERT_OK_PTR(ns, "create and open ns"))
return;
@@ -278,10 +308,6 @@ void test_xdp_context_tuntap(void)
SYS(close, "ip link set dev " TAP_NAME " up");
- skel = test_xdp_meta__open_and_load();
- if (!ASSERT_OK_PTR(skel, "open and load skeleton"))
- goto close;
-
tap_ifindex = if_nametoindex(TAP_NAME);
if (!ASSERT_GE(tap_ifindex, 0, "if_nametoindex"))
goto close;
@@ -291,33 +317,175 @@ void test_xdp_context_tuntap(void)
if (!ASSERT_OK(ret, "bpf_tc_hook_create"))
goto close;
- tc_opts.prog_fd = bpf_program__fd(skel->progs.ing_cls);
+ tc_opts.prog_fd = bpf_program__fd(tc_prio_1_prog);
ret = bpf_tc_attach(&tc_hook, &tc_opts);
if (!ASSERT_OK(ret, "bpf_tc_attach"))
goto close;
- ret = bpf_xdp_attach(tap_ifindex, bpf_program__fd(skel->progs.ing_xdp),
+ if (tc_prio_2_prog) {
+ LIBBPF_OPTS(bpf_tc_opts, tc_opts, .handle = 1, .priority = 2,
+ .prog_fd = bpf_program__fd(tc_prio_2_prog));
+
+ ret = bpf_tc_attach(&tc_hook, &tc_opts);
+ if (!ASSERT_OK(ret, "bpf_tc_attach"))
+ goto close;
+ }
+
+ ret = bpf_xdp_attach(tap_ifindex, bpf_program__fd(xdp_prog),
0, NULL);
if (!ASSERT_GE(ret, 0, "bpf_xdp_attach"))
goto close;
- /* The ethernet header is not relevant for this test and doesn't need to
- * be meaningful.
- */
- struct ethhdr eth = { 0 };
+ ret = write_test_packet(tap_fd);
+ if (!ASSERT_OK(ret, "write_test_packet"))
+ goto close;
- memcpy(packet, &eth, sizeof(eth));
- memcpy(packet + sizeof(eth), test_payload, TEST_PAYLOAD_LEN);
+ assert_test_result(result_map);
+
+close:
+ if (tap_fd >= 0)
+ close(tap_fd);
+ netns_free(ns);
+}
+
+/* Write a packet to a tap dev and copy it to ingress of a dummy dev */
+static void test_tuntap_mirred(struct bpf_program *xdp_prog,
+ struct bpf_program *tc_prog,
+ bool *test_pass)
+{
+ LIBBPF_OPTS(bpf_tc_hook, tc_hook, .attach_point = BPF_TC_INGRESS);
+ LIBBPF_OPTS(bpf_tc_opts, tc_opts, .handle = 1, .priority = 1);
+ struct netns_obj *ns = NULL;
+ int dummy_ifindex;
+ int tap_fd = -1;
+ int tap_ifindex;
+ int ret;
+
+ *test_pass = false;
+
+ ns = netns_new(TAP_NETNS, true);
+ if (!ASSERT_OK_PTR(ns, "netns_new"))
+ return;
- ret = write(tap_fd, packet, sizeof(packet));
- if (!ASSERT_EQ(ret, sizeof(packet), "write packet"))
+ /* Setup dummy interface */
+ SYS(close, "ip link add name " DUMMY_NAME " type dummy");
+ SYS(close, "ip link set dev " DUMMY_NAME " up");
+
+ dummy_ifindex = if_nametoindex(DUMMY_NAME);
+ if (!ASSERT_GE(dummy_ifindex, 0, "if_nametoindex"))
goto close;
- assert_test_result(skel);
+ tc_hook.ifindex = dummy_ifindex;
+ ret = bpf_tc_hook_create(&tc_hook);
+ if (!ASSERT_OK(ret, "bpf_tc_hook_create"))
+ goto close;
+
+ tc_opts.prog_fd = bpf_program__fd(tc_prog);
+ ret = bpf_tc_attach(&tc_hook, &tc_opts);
+ if (!ASSERT_OK(ret, "bpf_tc_attach"))
+ goto close;
+
+ /* Setup TAP interface */
+ tap_fd = open_tuntap(TAP_NAME, true);
+ if (!ASSERT_GE(tap_fd, 0, "open_tuntap"))
+ goto close;
+
+ SYS(close, "ip link set dev " TAP_NAME " up");
+
+ tap_ifindex = if_nametoindex(TAP_NAME);
+ if (!ASSERT_GE(tap_ifindex, 0, "if_nametoindex"))
+ goto close;
+
+ ret = bpf_xdp_attach(tap_ifindex, bpf_program__fd(xdp_prog), 0, NULL);
+ if (!ASSERT_GE(ret, 0, "bpf_xdp_attach"))
+ goto close;
+
+ /* Copy all packets received from TAP to dummy ingress */
+ SYS(close, "tc qdisc add dev " TAP_NAME " clsact");
+ SYS(close, "tc filter add dev " TAP_NAME " ingress "
+ "protocol all matchall "
+ "action mirred ingress mirror dev " DUMMY_NAME);
+
+ /* Receive a packet on TAP */
+ ret = write_test_packet(tap_fd);
+ if (!ASSERT_OK(ret, "write_test_packet"))
+ goto close;
+
+ ASSERT_TRUE(*test_pass, "test_pass");
close:
if (tap_fd >= 0)
close(tap_fd);
- test_xdp_meta__destroy(skel);
netns_free(ns);
}
+
+void test_xdp_context_tuntap(void)
+{
+ struct test_xdp_meta *skel = NULL;
+
+ skel = test_xdp_meta__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "open and load skeleton"))
+ return;
+
+ if (test__start_subtest("data_meta"))
+ test_tuntap(skel->progs.ing_xdp,
+ skel->progs.ing_cls,
+ NULL, /* tc prio 2 */
+ skel->maps.test_result);
+ if (test__start_subtest("dynptr_read"))
+ test_tuntap(skel->progs.ing_xdp,
+ skel->progs.ing_cls_dynptr_read,
+ NULL, /* tc prio 2 */
+ skel->maps.test_result);
+ if (test__start_subtest("dynptr_slice"))
+ test_tuntap(skel->progs.ing_xdp,
+ skel->progs.ing_cls_dynptr_slice,
+ NULL, /* tc prio 2 */
+ skel->maps.test_result);
+ if (test__start_subtest("dynptr_write"))
+ test_tuntap(skel->progs.ing_xdp_zalloc_meta,
+ skel->progs.ing_cls_dynptr_write,
+ skel->progs.ing_cls_dynptr_read,
+ skel->maps.test_result);
+ if (test__start_subtest("dynptr_slice_rdwr"))
+ test_tuntap(skel->progs.ing_xdp_zalloc_meta,
+ skel->progs.ing_cls_dynptr_slice_rdwr,
+ skel->progs.ing_cls_dynptr_slice,
+ skel->maps.test_result);
+ if (test__start_subtest("dynptr_offset"))
+ test_tuntap(skel->progs.ing_xdp_zalloc_meta,
+ skel->progs.ing_cls_dynptr_offset_wr,
+ skel->progs.ing_cls_dynptr_offset_rd,
+ skel->maps.test_result);
+ if (test__start_subtest("dynptr_offset_oob"))
+ test_tuntap(skel->progs.ing_xdp,
+ skel->progs.ing_cls_dynptr_offset_oob,
+ skel->progs.ing_cls,
+ skel->maps.test_result);
+ if (test__start_subtest("clone_data_meta_empty_on_data_write"))
+ test_tuntap_mirred(skel->progs.ing_xdp,
+ skel->progs.clone_data_meta_empty_on_data_write,
+ &skel->bss->test_pass);
+ if (test__start_subtest("clone_data_meta_empty_on_meta_write"))
+ test_tuntap_mirred(skel->progs.ing_xdp,
+ skel->progs.clone_data_meta_empty_on_meta_write,
+ &skel->bss->test_pass);
+ if (test__start_subtest("clone_dynptr_empty_on_data_slice_write"))
+ test_tuntap_mirred(skel->progs.ing_xdp,
+ skel->progs.clone_dynptr_empty_on_data_slice_write,
+ &skel->bss->test_pass);
+ if (test__start_subtest("clone_dynptr_empty_on_meta_slice_write"))
+ test_tuntap_mirred(skel->progs.ing_xdp,
+ skel->progs.clone_dynptr_empty_on_meta_slice_write,
+ &skel->bss->test_pass);
+ if (test__start_subtest("clone_dynptr_rdonly_before_data_dynptr_write"))
+ test_tuntap_mirred(skel->progs.ing_xdp,
+ skel->progs.clone_dynptr_rdonly_before_data_dynptr_write,
+ &skel->bss->test_pass);
+ if (test__start_subtest("clone_dynptr_rdonly_before_meta_dynptr_write"))
+ test_tuntap_mirred(skel->progs.ing_xdp,
+ skel->progs.clone_dynptr_rdonly_before_meta_dynptr_write,
+ &skel->bss->test_pass);
+
+ test_xdp_meta__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c
index 461ab18705d5..a8ab05216c38 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c
@@ -7,6 +7,7 @@
#include <test_progs.h>
#include "test_xdp_devmap_helpers.skel.h"
+#include "test_xdp_devmap_tailcall.skel.h"
#include "test_xdp_with_devmap_frags_helpers.skel.h"
#include "test_xdp_with_devmap_helpers.skel.h"
@@ -107,6 +108,29 @@ static void test_neg_xdp_devmap_helpers(void)
}
}
+static void test_xdp_devmap_tailcall(enum bpf_attach_type prog_dev,
+ enum bpf_attach_type prog_tail,
+ bool expect_reject)
+{
+ struct test_xdp_devmap_tailcall *skel;
+ int err;
+
+ skel = test_xdp_devmap_tailcall__open();
+ if (!ASSERT_OK_PTR(skel, "test_xdp_devmap_tailcall__open"))
+ return;
+
+ bpf_program__set_expected_attach_type(skel->progs.xdp_devmap, prog_dev);
+ bpf_program__set_expected_attach_type(skel->progs.xdp_entry, prog_tail);
+
+ err = test_xdp_devmap_tailcall__load(skel);
+ if (expect_reject)
+ ASSERT_ERR(err, "test_xdp_devmap_tailcall__load");
+ else
+ ASSERT_OK(err, "test_xdp_devmap_tailcall__load");
+
+ test_xdp_devmap_tailcall__destroy(skel);
+}
+
static void test_xdp_with_devmap_frags_helpers(void)
{
struct test_xdp_with_devmap_frags_helpers *skel;
@@ -238,8 +262,13 @@ void serial_test_xdp_devmap_attach(void)
if (test__start_subtest("DEVMAP with frags programs in entries"))
test_xdp_with_devmap_frags_helpers();
- if (test__start_subtest("Verifier check of DEVMAP programs"))
+ if (test__start_subtest("Verifier check of DEVMAP programs")) {
test_neg_xdp_devmap_helpers();
+ test_xdp_devmap_tailcall(BPF_XDP_DEVMAP, BPF_XDP_DEVMAP, false);
+ test_xdp_devmap_tailcall(0, 0, true);
+ test_xdp_devmap_tailcall(BPF_XDP_DEVMAP, 0, true);
+ test_xdp_devmap_tailcall(0, BPF_XDP_DEVMAP, true);
+ }
if (test__start_subtest("DEVMAP with programs in entries on veth"))
test_xdp_with_devmap_helpers_veth();
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_pull_data.c b/tools/testing/selftests/bpf/prog_tests/xdp_pull_data.c
new file mode 100644
index 000000000000..efa350d04ec5
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_pull_data.c
@@ -0,0 +1,179 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+#include <network_helpers.h>
+#include "test_xdp_pull_data.skel.h"
+
+#define PULL_MAX (1 << 31)
+#define PULL_PLUS_ONE (1 << 30)
+
+#define XDP_PACKET_HEADROOM 256
+
+/* Find headroom and tailroom occupied by struct xdp_frame and struct
+ * skb_shared_info so that we can calculate the maximum pull lengths for
+ * test cases. They might not be the real size of the structures due to
+ * cache alignment.
+ */
+static int find_xdp_sizes(struct test_xdp_pull_data *skel, int frame_sz)
+{
+ LIBBPF_OPTS(bpf_test_run_opts, topts);
+ struct xdp_md ctx = {};
+ int prog_fd, err;
+ __u8 *buf;
+
+ buf = calloc(frame_sz, sizeof(__u8));
+ if (!ASSERT_OK_PTR(buf, "calloc buf"))
+ return -ENOMEM;
+
+ topts.data_in = buf;
+ topts.data_out = buf;
+ topts.data_size_in = frame_sz;
+ topts.data_size_out = frame_sz;
+ /* Pass a data_end larger than the linear space available to make sure
+ * bpf_prog_test_run_xdp() will fill the linear data area so that
+ * xdp_find_sizes can infer the size of struct skb_shared_info
+ */
+ ctx.data_end = frame_sz;
+ topts.ctx_in = &ctx;
+ topts.ctx_out = &ctx;
+ topts.ctx_size_in = sizeof(ctx);
+ topts.ctx_size_out = sizeof(ctx);
+
+ prog_fd = bpf_program__fd(skel->progs.xdp_find_sizes);
+ err = bpf_prog_test_run_opts(prog_fd, &topts);
+ ASSERT_OK(err, "bpf_prog_test_run_opts");
+
+ free(buf);
+
+ return err;
+}
+
+/* xdp_pull_data_prog will directly read a marker 0xbb stored at buf[1024]
+ * so caller expecting XDP_PASS should always pass pull_len no less than 1024
+ */
+static void run_test(struct test_xdp_pull_data *skel, int retval,
+ int frame_sz, int buff_len, int meta_len, int data_len,
+ int pull_len)
+{
+ LIBBPF_OPTS(bpf_test_run_opts, topts);
+ struct xdp_md ctx = {};
+ int prog_fd, err;
+ __u8 *buf;
+
+ buf = calloc(buff_len, sizeof(__u8));
+ if (!ASSERT_OK_PTR(buf, "calloc buf"))
+ return;
+
+ buf[meta_len + 1023] = 0xaa;
+ buf[meta_len + 1024] = 0xbb;
+ buf[meta_len + 1025] = 0xcc;
+
+ topts.data_in = buf;
+ topts.data_out = buf;
+ topts.data_size_in = buff_len;
+ topts.data_size_out = buff_len;
+ ctx.data = meta_len;
+ ctx.data_end = meta_len + data_len;
+ topts.ctx_in = &ctx;
+ topts.ctx_out = &ctx;
+ topts.ctx_size_in = sizeof(ctx);
+ topts.ctx_size_out = sizeof(ctx);
+
+ skel->bss->data_len = data_len;
+ if (pull_len & PULL_MAX) {
+ int headroom = XDP_PACKET_HEADROOM - meta_len - skel->bss->xdpf_sz;
+ int tailroom = frame_sz - XDP_PACKET_HEADROOM -
+ data_len - skel->bss->sinfo_sz;
+
+ pull_len = pull_len & PULL_PLUS_ONE ? 1 : 0;
+ pull_len += headroom + tailroom + data_len;
+ }
+ skel->bss->pull_len = pull_len;
+
+ prog_fd = bpf_program__fd(skel->progs.xdp_pull_data_prog);
+ err = bpf_prog_test_run_opts(prog_fd, &topts);
+ ASSERT_OK(err, "bpf_prog_test_run_opts");
+ ASSERT_EQ(topts.retval, retval, "xdp_pull_data_prog retval");
+
+ if (retval == XDP_DROP)
+ goto out;
+
+ ASSERT_EQ(ctx.data_end, meta_len + pull_len, "linear data size");
+ ASSERT_EQ(topts.data_size_out, buff_len, "linear + non-linear data size");
+ /* Make sure data around xdp->data_end was not messed up by
+ * bpf_xdp_pull_data()
+ */
+ ASSERT_EQ(buf[meta_len + 1023], 0xaa, "data[1023]");
+ ASSERT_EQ(buf[meta_len + 1024], 0xbb, "data[1024]");
+ ASSERT_EQ(buf[meta_len + 1025], 0xcc, "data[1025]");
+out:
+ free(buf);
+}
+
+static void test_xdp_pull_data_basic(void)
+{
+ u32 pg_sz, max_meta_len, max_data_len;
+ struct test_xdp_pull_data *skel;
+
+ skel = test_xdp_pull_data__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "test_xdp_pull_data__open_and_load"))
+ return;
+
+ pg_sz = sysconf(_SC_PAGE_SIZE);
+
+ if (find_xdp_sizes(skel, pg_sz))
+ goto out;
+
+ max_meta_len = XDP_PACKET_HEADROOM - skel->bss->xdpf_sz;
+ max_data_len = pg_sz - XDP_PACKET_HEADROOM - skel->bss->sinfo_sz;
+
+ /* linear xdp pkt, pull 0 byte */
+ run_test(skel, XDP_PASS, pg_sz, 2048, 0, 2048, 2048);
+
+ /* multi-buf pkt, pull results in linear xdp pkt */
+ run_test(skel, XDP_PASS, pg_sz, 2048, 0, 1024, 2048);
+
+ /* multi-buf pkt, pull 1 byte to linear data area */
+ run_test(skel, XDP_PASS, pg_sz, 9000, 0, 1024, 1025);
+
+ /* multi-buf pkt, pull 0 byte to linear data area */
+ run_test(skel, XDP_PASS, pg_sz, 9000, 0, 1025, 1025);
+
+ /* multi-buf pkt, empty linear data area, pull requires memmove */
+ run_test(skel, XDP_PASS, pg_sz, 9000, 0, 0, PULL_MAX);
+
+ /* multi-buf pkt, no headroom */
+ run_test(skel, XDP_PASS, pg_sz, 9000, max_meta_len, 1024, PULL_MAX);
+
+ /* multi-buf pkt, no tailroom, pull requires memmove */
+ run_test(skel, XDP_PASS, pg_sz, 9000, 0, max_data_len, PULL_MAX);
+
+ /* Test cases with invalid pull length */
+
+ /* linear xdp pkt, pull more than total data len */
+ run_test(skel, XDP_DROP, pg_sz, 2048, 0, 2048, 2049);
+
+ /* multi-buf pkt with no space left in linear data area */
+ run_test(skel, XDP_DROP, pg_sz, 9000, max_meta_len, max_data_len,
+ PULL_MAX | PULL_PLUS_ONE);
+
+ /* multi-buf pkt, empty linear data area */
+ run_test(skel, XDP_DROP, pg_sz, 9000, 0, 0, PULL_MAX | PULL_PLUS_ONE);
+
+ /* multi-buf pkt, no headroom */
+ run_test(skel, XDP_DROP, pg_sz, 9000, max_meta_len, 1024,
+ PULL_MAX | PULL_PLUS_ONE);
+
+ /* multi-buf pkt, no tailroom */
+ run_test(skel, XDP_DROP, pg_sz, 9000, 0, max_data_len,
+ PULL_MAX | PULL_PLUS_ONE);
+
+out:
+ test_xdp_pull_data__destroy(skel);
+}
+
+void test_xdp_pull_data(void)
+{
+ if (test__start_subtest("xdp_pull_data"))
+ test_xdp_pull_data_basic();
+}
diff --git a/tools/testing/selftests/bpf/progs/arena_atomics.c b/tools/testing/selftests/bpf/progs/arena_atomics.c
index a52feff98112..d1841aac94a2 100644
--- a/tools/testing/selftests/bpf/progs/arena_atomics.c
+++ b/tools/testing/selftests/bpf/progs/arena_atomics.c
@@ -28,7 +28,8 @@ bool skip_all_tests = true;
#if defined(ENABLE_ATOMICS_TESTS) && \
defined(__BPF_FEATURE_ADDR_SPACE_CAST) && \
- (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86))
+ (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \
+ (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64))
bool skip_lacq_srel_tests __attribute((__section__(".data"))) = false;
#else
bool skip_lacq_srel_tests = true;
@@ -314,7 +315,8 @@ int load_acquire(const void *ctx)
{
#if defined(ENABLE_ATOMICS_TESTS) && \
defined(__BPF_FEATURE_ADDR_SPACE_CAST) && \
- (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86))
+ (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \
+ (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64))
#define LOAD_ACQUIRE_ARENA(SIZEOP, SIZE, SRC, DST) \
{ asm volatile ( \
@@ -365,7 +367,8 @@ int store_release(const void *ctx)
{
#if defined(ENABLE_ATOMICS_TESTS) && \
defined(__BPF_FEATURE_ADDR_SPACE_CAST) && \
- (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86))
+ (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \
+ (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64))
#define STORE_RELEASE_ARENA(SIZEOP, DST, VAL) \
{ asm volatile ( \
diff --git a/tools/testing/selftests/bpf/progs/arena_spin_lock.c b/tools/testing/selftests/bpf/progs/arena_spin_lock.c
index c4500c37f85e..086b57a426cf 100644
--- a/tools/testing/selftests/bpf/progs/arena_spin_lock.c
+++ b/tools/testing/selftests/bpf/progs/arena_spin_lock.c
@@ -37,8 +37,11 @@ int prog(void *ctx)
#if defined(ENABLE_ATOMICS_TESTS) && defined(__BPF_FEATURE_ADDR_SPACE_CAST)
unsigned long flags;
- if ((ret = arena_spin_lock_irqsave(&lock, flags)))
+ if ((ret = arena_spin_lock_irqsave(&lock, flags))) {
+ if (ret == -EOPNOTSUPP)
+ test_skip = 3;
return ret;
+ }
if (counter != limit)
counter++;
bpf_repeat(cs_count);
diff --git a/tools/testing/selftests/bpf/progs/bpf_arena_spin_lock.h b/tools/testing/selftests/bpf/progs/bpf_arena_spin_lock.h
index d67466c1ff77..f90531cf3ee5 100644
--- a/tools/testing/selftests/bpf/progs/bpf_arena_spin_lock.h
+++ b/tools/testing/selftests/bpf/progs/bpf_arena_spin_lock.h
@@ -302,7 +302,7 @@ int arena_spin_lock_slowpath(arena_spinlock_t __arena __arg_arena *lock, u32 val
* barriers.
*/
if (val & _Q_LOCKED_MASK)
- smp_cond_load_acquire_label(&lock->locked, !VAL, release_err);
+ (void)smp_cond_load_acquire_label(&lock->locked, !VAL, release_err);
/*
* take ownership and clear the pending bit.
@@ -380,7 +380,7 @@ queue:
/* Link @node into the waitqueue. */
WRITE_ONCE(prev->next, node);
- arch_mcs_spin_lock_contended_label(&node->locked, release_node_err);
+ (void)arch_mcs_spin_lock_contended_label(&node->locked, release_node_err);
/*
* While waiting for the MCS lock, the next pointer may have
diff --git a/tools/testing/selftests/bpf/progs/bpf_cc_cubic.c b/tools/testing/selftests/bpf/progs/bpf_cc_cubic.c
index 1654a530aa3d..4e51785e7606 100644
--- a/tools/testing/selftests/bpf/progs/bpf_cc_cubic.c
+++ b/tools/testing/selftests/bpf/progs/bpf_cc_cubic.c
@@ -101,7 +101,7 @@ static void tcp_cwnd_reduction(struct sock *sk, int newly_acked_sacked,
tp->snd_cwnd = pkts_in_flight + sndcnt;
}
-/* Decide wheather to run the increase function of congestion control. */
+/* Decide whether to run the increase function of congestion control. */
static bool tcp_may_raise_cwnd(const struct sock *sk, const int flag)
{
if (tcp_sk(sk)->reordering > TCP_REORDERING)
diff --git a/tools/testing/selftests/bpf/progs/bpf_dctcp.c b/tools/testing/selftests/bpf/progs/bpf_dctcp.c
index 7cd73e75f52a..32c511bcd60b 100644
--- a/tools/testing/selftests/bpf/progs/bpf_dctcp.c
+++ b/tools/testing/selftests/bpf/progs/bpf_dctcp.c
@@ -1,7 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2019 Facebook */
-/* WARNING: This implemenation is not necessarily the same
+/* WARNING: This implementation is not necessarily the same
* as the tcp_dctcp.c. The purpose is mainly for testing
* the kernel BPF logic.
*/
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_udp4.c b/tools/testing/selftests/bpf/progs/bpf_iter_udp4.c
index ffbd4b116d17..23b2aa2604de 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_udp4.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_udp4.c
@@ -64,7 +64,8 @@ int dump_udp4(struct bpf_iter__udp *ctx)
0, 0L, 0, ctx->uid, 0,
sock_i_ino(&inet->sk),
inet->sk.sk_refcnt.refs.counter, udp_sk,
- inet->sk.sk_drops.counter);
+ udp_sk->drop_counters.drops0.counter +
+ udp_sk->drop_counters.drops1.counter);
return 0;
}
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_udp6.c b/tools/testing/selftests/bpf/progs/bpf_iter_udp6.c
index 47ff7754f4fd..c48b05aa2a4b 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_udp6.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_udp6.c
@@ -72,7 +72,7 @@ int dump_udp6(struct bpf_iter__udp *ctx)
0, 0L, 0, ctx->uid, 0,
sock_i_ino(&inet->sk),
inet->sk.sk_refcnt.refs.counter, udp_sk,
- inet->sk.sk_drops.counter);
-
+ udp_sk->drop_counters.drops0.counter +
+ udp_sk->drop_counters.drops1.counter);
return 0;
}
diff --git a/tools/testing/selftests/bpf/progs/bpf_misc.h b/tools/testing/selftests/bpf/progs/bpf_misc.h
index c1cfd297aabf..a7a1a684eed1 100644
--- a/tools/testing/selftests/bpf/progs/bpf_misc.h
+++ b/tools/testing/selftests/bpf/progs/bpf_misc.h
@@ -33,7 +33,20 @@
* e.g. "foo{{[0-9]+}}" matches strings like "foo007".
* Extended POSIX regular expression syntax is allowed
* inside the brackets.
+ * __not_msg Message not expected to be found in verifier log.
+ * If __msg_not is situated between __msg tags
+ * framework matches __msg tags first, and then
+ * checks that __msg_not is not present in a portion of
+ * a log between bracketing __msg tags.
+ * Same regex syntax as for __msg is supported.
* __msg_unpriv Same as __msg but for unprivileged mode.
+ * __not_msg_unpriv Same as __not_msg but for unprivileged mode.
+ *
+ * __stderr Message expected to be found in bpf stderr stream. The
+ * same regex rules apply like __msg.
+ * __stderr_unpriv Same as __stderr but for unpriveleged mode.
+ * __stdout Same as __stderr but for stdout stream.
+ * __stdout_unpriv Same as __stdout but for unpriveleged mode.
*
* __xlated Expect a line in a disassembly log after verifier applies rewrites.
* Multiple __xlated attributes could be specified.
@@ -115,12 +128,14 @@
* __caps_unpriv Specify the capabilities that should be set when running the test.
*/
#define __msg(msg) __attribute__((btf_decl_tag("comment:test_expect_msg=" XSTR(__COUNTER__) "=" msg)))
+#define __not_msg(msg) __attribute__((btf_decl_tag("comment:test_expect_not_msg=" XSTR(__COUNTER__) "=" msg)))
#define __xlated(msg) __attribute__((btf_decl_tag("comment:test_expect_xlated=" XSTR(__COUNTER__) "=" msg)))
#define __jited(msg) __attribute__((btf_decl_tag("comment:test_jited=" XSTR(__COUNTER__) "=" msg)))
#define __failure __attribute__((btf_decl_tag("comment:test_expect_failure")))
#define __success __attribute__((btf_decl_tag("comment:test_expect_success")))
#define __description(desc) __attribute__((btf_decl_tag("comment:test_description=" desc)))
#define __msg_unpriv(msg) __attribute__((btf_decl_tag("comment:test_expect_msg_unpriv=" XSTR(__COUNTER__) "=" msg)))
+#define __not_msg_unpriv(msg) __attribute__((btf_decl_tag("comment:test_expect_not_msg_unpriv=" XSTR(__COUNTER__) "=" msg)))
#define __xlated_unpriv(msg) __attribute__((btf_decl_tag("comment:test_expect_xlated_unpriv=" XSTR(__COUNTER__) "=" msg)))
#define __jited_unpriv(msg) __attribute__((btf_decl_tag("comment:test_jited=" XSTR(__COUNTER__) "=" msg)))
#define __failure_unpriv __attribute__((btf_decl_tag("comment:test_expect_failure_unpriv")))
@@ -136,9 +151,14 @@
#define __arch_x86_64 __arch("X86_64")
#define __arch_arm64 __arch("ARM64")
#define __arch_riscv64 __arch("RISCV64")
+#define __arch_s390x __arch("s390x")
#define __caps_unpriv(caps) __attribute__((btf_decl_tag("comment:test_caps_unpriv=" EXPAND_QUOTE(caps))))
#define __load_if_JITed() __attribute__((btf_decl_tag("comment:load_mode=jited")))
#define __load_if_no_JITed() __attribute__((btf_decl_tag("comment:load_mode=no_jited")))
+#define __stderr(msg) __attribute__((btf_decl_tag("comment:test_expect_stderr=" XSTR(__COUNTER__) "=" msg)))
+#define __stderr_unpriv(msg) __attribute__((btf_decl_tag("comment:test_expect_stderr_unpriv=" XSTR(__COUNTER__) "=" msg)))
+#define __stdout(msg) __attribute__((btf_decl_tag("comment:test_expect_stdout=" XSTR(__COUNTER__) "=" msg)))
+#define __stdout_unpriv(msg) __attribute__((btf_decl_tag("comment:test_expect_stdout_unpriv=" XSTR(__COUNTER__) "=" msg)))
/* Define common capabilities tested using __caps_unpriv */
#define CAP_NET_ADMIN 12
@@ -156,6 +176,10 @@
#define __imm_ptr(name) [name]"r"(&name)
#define __imm_insn(name, expr) [name]"i"(*(long *)&(expr))
+#define sizeof_field(TYPE, MEMBER) sizeof((((TYPE *)0)->MEMBER))
+#define offsetofend(TYPE, MEMBER) \
+ (offsetof(TYPE, MEMBER) + sizeof_field(TYPE, MEMBER))
+
/* Magic constants used with __retval() */
#define POINTER_VALUE 0xbadcafe
#define TEST_DATA_LEN 64
diff --git a/tools/testing/selftests/bpf/progs/bpf_test_utils.h b/tools/testing/selftests/bpf/progs/bpf_test_utils.h
new file mode 100644
index 000000000000..f4e67b492dd2
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_test_utils.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __BPF_TEST_UTILS_H__
+#define __BPF_TEST_UTILS_H__
+
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+/* Clobber as many native registers and stack slots as possible. */
+static __always_inline void clobber_regs_stack(void)
+{
+ char tmp_str[] = "123456789";
+ unsigned long tmp;
+
+ bpf_strtoul(tmp_str, sizeof(tmp_str), 0, &tmp);
+ __sink(tmp);
+}
+
+#endif
diff --git a/tools/testing/selftests/bpf/progs/cgroup_read_xattr.c b/tools/testing/selftests/bpf/progs/cgroup_read_xattr.c
index 092db1d0435e..88e13e17ec9e 100644
--- a/tools/testing/selftests/bpf/progs/cgroup_read_xattr.c
+++ b/tools/testing/selftests/bpf/progs/cgroup_read_xattr.c
@@ -73,7 +73,7 @@ int BPF_PROG(use_css_iter_non_sleepable)
}
SEC("lsm.s/socket_connect")
-__failure __msg("expected an RCU CS")
+__failure __msg("kernel func bpf_iter_css_new requires RCU critical section protection")
int BPF_PROG(use_css_iter_sleepable_missing_rcu_lock)
{
u64 cgrp_id = bpf_get_current_cgroup_id();
diff --git a/tools/testing/selftests/bpf/progs/cgrp_kfunc_success.c b/tools/testing/selftests/bpf/progs/cgrp_kfunc_success.c
index 5354455a01be..02d8f160ca0e 100644
--- a/tools/testing/selftests/bpf/progs/cgrp_kfunc_success.c
+++ b/tools/testing/selftests/bpf/progs/cgrp_kfunc_success.c
@@ -221,3 +221,15 @@ int BPF_PROG(test_cgrp_from_id, struct cgroup *cgrp, const char *path)
return 0;
}
+
+SEC("syscall")
+int test_cgrp_from_id_ns(void *ctx)
+{
+ struct cgroup *cg;
+
+ cg = bpf_cgroup_from_id(1);
+ if (!cg)
+ return 42;
+ bpf_cgroup_release(cg);
+ return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/crypto_sanity.c b/tools/testing/selftests/bpf/progs/crypto_sanity.c
index 645be6cddf36..dfd8a258f14a 100644
--- a/tools/testing/selftests/bpf/progs/crypto_sanity.c
+++ b/tools/testing/selftests/bpf/progs/crypto_sanity.c
@@ -14,7 +14,7 @@ unsigned char key[256] = {};
u16 udp_test_port = 7777;
u32 authsize, key_len;
char algo[128] = {};
-char dst[16] = {};
+char dst[16] = {}, dst_bad[8] = {};
int status;
static int skb_dynptr_validate(struct __sk_buff *skb, struct bpf_dynptr *psrc)
@@ -59,10 +59,9 @@ int skb_crypto_setup(void *ctx)
.authsize = authsize,
};
struct bpf_crypto_ctx *cctx;
- int err = 0;
+ int err;
status = 0;
-
if (key_len > 256) {
status = -EINVAL;
return 0;
@@ -70,8 +69,8 @@ int skb_crypto_setup(void *ctx)
__builtin_memcpy(&params.algo, algo, sizeof(algo));
__builtin_memcpy(&params.key, key, sizeof(key));
- cctx = bpf_crypto_ctx_create(&params, sizeof(params), &err);
+ cctx = bpf_crypto_ctx_create(&params, sizeof(params), &err);
if (!cctx) {
status = err;
return 0;
@@ -80,7 +79,6 @@ int skb_crypto_setup(void *ctx)
err = crypto_ctx_insert(cctx);
if (err && err != -EEXIST)
status = err;
-
return 0;
}
@@ -92,6 +90,7 @@ int decrypt_sanity(struct __sk_buff *skb)
struct bpf_dynptr psrc, pdst;
int err;
+ status = 0;
err = skb_dynptr_validate(skb, &psrc);
if (err < 0) {
status = err;
@@ -110,13 +109,23 @@ int decrypt_sanity(struct __sk_buff *skb)
return TC_ACT_SHOT;
}
- /* dst is a global variable to make testing part easier to check. In real
- * production code, a percpu map should be used to store the result.
+ /* Check also bad case where the dst buffer is smaller than the
+ * skb's linear section.
+ */
+ bpf_dynptr_from_mem(dst_bad, sizeof(dst_bad), 0, &pdst);
+ status = bpf_crypto_decrypt(ctx, &psrc, &pdst, NULL);
+ if (!status)
+ status = -EIO;
+ if (status != -EINVAL)
+ goto err;
+
+ /* dst is a global variable to make testing part easier to check.
+ * In real production code, a percpu map should be used to store
+ * the result.
*/
bpf_dynptr_from_mem(dst, sizeof(dst), 0, &pdst);
-
status = bpf_crypto_decrypt(ctx, &psrc, &pdst, NULL);
-
+err:
return TC_ACT_SHOT;
}
@@ -129,7 +138,6 @@ int encrypt_sanity(struct __sk_buff *skb)
int err;
status = 0;
-
err = skb_dynptr_validate(skb, &psrc);
if (err < 0) {
status = err;
@@ -148,13 +156,23 @@ int encrypt_sanity(struct __sk_buff *skb)
return TC_ACT_SHOT;
}
- /* dst is a global variable to make testing part easier to check. In real
- * production code, a percpu map should be used to store the result.
+ /* Check also bad case where the dst buffer is smaller than the
+ * skb's linear section.
+ */
+ bpf_dynptr_from_mem(dst_bad, sizeof(dst_bad), 0, &pdst);
+ status = bpf_crypto_encrypt(ctx, &psrc, &pdst, NULL);
+ if (!status)
+ status = -EIO;
+ if (status != -EINVAL)
+ goto err;
+
+ /* dst is a global variable to make testing part easier to check.
+ * In real production code, a percpu map should be used to store
+ * the result.
*/
bpf_dynptr_from_mem(dst, sizeof(dst), 0, &pdst);
-
status = bpf_crypto_encrypt(ctx, &psrc, &pdst, NULL);
-
+err:
return TC_ACT_SHOT;
}
diff --git a/tools/testing/selftests/bpf/progs/dynptr_fail.c b/tools/testing/selftests/bpf/progs/dynptr_fail.c
index bd8f15229f5c..dda6a8dada82 100644
--- a/tools/testing/selftests/bpf/progs/dynptr_fail.c
+++ b/tools/testing/selftests/bpf/progs/dynptr_fail.c
@@ -269,6 +269,26 @@ int data_slice_out_of_bounds_skb(struct __sk_buff *skb)
return SK_PASS;
}
+/* A metadata slice can't be accessed out of bounds */
+SEC("?tc")
+__failure __msg("value is outside of the allowed memory range")
+int data_slice_out_of_bounds_skb_meta(struct __sk_buff *skb)
+{
+ struct bpf_dynptr meta;
+ __u8 *md;
+
+ bpf_dynptr_from_skb_meta(skb, 0, &meta);
+
+ md = bpf_dynptr_slice_rdwr(&meta, 0, NULL, sizeof(*md));
+ if (!md)
+ return SK_DROP;
+
+ /* this should fail */
+ *(md + 1) = 42;
+
+ return SK_PASS;
+}
+
SEC("?raw_tp")
__failure __msg("value is outside of the allowed memory range")
int data_slice_out_of_bounds_map_value(void *ctx)
@@ -1089,6 +1109,26 @@ int skb_invalid_slice_write(struct __sk_buff *skb)
return SK_PASS;
}
+/* bpf_dynptr_slice()s are read-only and cannot be written to */
+SEC("?tc")
+__failure __msg("R{{[0-9]+}} cannot write into rdonly_mem")
+int skb_meta_invalid_slice_write(struct __sk_buff *skb)
+{
+ struct bpf_dynptr meta;
+ __u8 *md;
+
+ bpf_dynptr_from_skb_meta(skb, 0, &meta);
+
+ md = bpf_dynptr_slice(&meta, 0, NULL, sizeof(*md));
+ if (!md)
+ return SK_DROP;
+
+ /* this should fail */
+ *md = 42;
+
+ return SK_PASS;
+}
+
/* The read-only data slice is invalidated whenever a helper changes packet data */
SEC("?tc")
__failure __msg("invalid mem access 'scalar'")
@@ -1192,6 +1232,188 @@ int skb_invalid_data_slice4(struct __sk_buff *skb)
return SK_PASS;
}
+/* Read-only skb data slice is invalidated on write to skb metadata */
+SEC("?tc")
+__failure __msg("invalid mem access 'scalar'")
+int ro_skb_slice_invalid_after_metadata_write(struct __sk_buff *skb)
+{
+ struct bpf_dynptr data, meta;
+ __u8 *d;
+
+ bpf_dynptr_from_skb(skb, 0, &data);
+ bpf_dynptr_from_skb_meta(skb, 0, &meta);
+
+ d = bpf_dynptr_slice(&data, 0, NULL, sizeof(*d));
+ if (!d)
+ return SK_DROP;
+
+ bpf_dynptr_write(&meta, 0, "x", 1, 0);
+
+ /* this should fail */
+ val = *d;
+
+ return SK_PASS;
+}
+
+/* Read-write skb data slice is invalidated on write to skb metadata */
+SEC("?tc")
+__failure __msg("invalid mem access 'scalar'")
+int rw_skb_slice_invalid_after_metadata_write(struct __sk_buff *skb)
+{
+ struct bpf_dynptr data, meta;
+ __u8 *d;
+
+ bpf_dynptr_from_skb(skb, 0, &data);
+ bpf_dynptr_from_skb_meta(skb, 0, &meta);
+
+ d = bpf_dynptr_slice_rdwr(&data, 0, NULL, sizeof(*d));
+ if (!d)
+ return SK_DROP;
+
+ bpf_dynptr_write(&meta, 0, "x", 1, 0);
+
+ /* this should fail */
+ *d = 42;
+
+ return SK_PASS;
+}
+
+/* Read-only skb metadata slice is invalidated on write to skb data */
+SEC("?tc")
+__failure __msg("invalid mem access 'scalar'")
+int ro_skb_meta_slice_invalid_after_payload_write(struct __sk_buff *skb)
+{
+ struct bpf_dynptr data, meta;
+ __u8 *md;
+
+ bpf_dynptr_from_skb(skb, 0, &data);
+ bpf_dynptr_from_skb_meta(skb, 0, &meta);
+
+ md = bpf_dynptr_slice(&meta, 0, NULL, sizeof(*md));
+ if (!md)
+ return SK_DROP;
+
+ bpf_dynptr_write(&data, 0, "x", 1, 0);
+
+ /* this should fail */
+ val = *md;
+
+ return SK_PASS;
+}
+
+/* Read-write skb metadata slice is invalidated on write to skb data slice */
+SEC("?tc")
+__failure __msg("invalid mem access 'scalar'")
+int rw_skb_meta_slice_invalid_after_payload_write(struct __sk_buff *skb)
+{
+ struct bpf_dynptr data, meta;
+ __u8 *md;
+
+ bpf_dynptr_from_skb(skb, 0, &data);
+ bpf_dynptr_from_skb_meta(skb, 0, &meta);
+
+ md = bpf_dynptr_slice_rdwr(&meta, 0, NULL, sizeof(*md));
+ if (!md)
+ return SK_DROP;
+
+ bpf_dynptr_write(&data, 0, "x", 1, 0);
+
+ /* this should fail */
+ *md = 42;
+
+ return SK_PASS;
+}
+
+/* Read-only skb metadata slice is invalidated whenever a helper changes packet data */
+SEC("?tc")
+__failure __msg("invalid mem access 'scalar'")
+int ro_skb_meta_slice_invalid_after_payload_helper(struct __sk_buff *skb)
+{
+ struct bpf_dynptr meta;
+ __u8 *md;
+
+ bpf_dynptr_from_skb_meta(skb, 0, &meta);
+
+ md = bpf_dynptr_slice(&meta, 0, NULL, sizeof(*md));
+ if (!md)
+ return SK_DROP;
+
+ if (bpf_skb_pull_data(skb, skb->len))
+ return SK_DROP;
+
+ /* this should fail */
+ val = *md;
+
+ return SK_PASS;
+}
+
+/* Read-write skb metadata slice is invalidated whenever a helper changes packet data */
+SEC("?tc")
+__failure __msg("invalid mem access 'scalar'")
+int rw_skb_meta_slice_invalid_after_payload_helper(struct __sk_buff *skb)
+{
+ struct bpf_dynptr meta;
+ __u8 *md;
+
+ bpf_dynptr_from_skb_meta(skb, 0, &meta);
+
+ md = bpf_dynptr_slice_rdwr(&meta, 0, NULL, sizeof(*md));
+ if (!md)
+ return SK_DROP;
+
+ if (bpf_skb_pull_data(skb, skb->len))
+ return SK_DROP;
+
+ /* this should fail */
+ *md = 42;
+
+ return SK_PASS;
+}
+
+/* Read-only skb metadata slice is invalidated on write to skb metadata */
+SEC("?tc")
+__failure __msg("invalid mem access 'scalar'")
+int ro_skb_meta_slice_invalid_after_metadata_write(struct __sk_buff *skb)
+{
+ struct bpf_dynptr meta;
+ __u8 *md;
+
+ bpf_dynptr_from_skb_meta(skb, 0, &meta);
+
+ md = bpf_dynptr_slice(&meta, 0, NULL, sizeof(*md));
+ if (!md)
+ return SK_DROP;
+
+ bpf_dynptr_write(&meta, 0, "x", 1, 0);
+
+ /* this should fail */
+ val = *md;
+
+ return SK_PASS;
+}
+
+/* Read-write skb metadata slice is invalidated on write to skb metadata */
+SEC("?tc")
+__failure __msg("invalid mem access 'scalar'")
+int rw_skb_meta_slice_invalid_after_metadata_write(struct __sk_buff *skb)
+{
+ struct bpf_dynptr meta;
+ __u8 *md;
+
+ bpf_dynptr_from_skb_meta(skb, 0, &meta);
+
+ md = bpf_dynptr_slice_rdwr(&meta, 0, NULL, sizeof(*md));
+ if (!md)
+ return SK_DROP;
+
+ bpf_dynptr_write(&meta, 0, "x", 1, 0);
+
+ /* this should fail */
+ *md = 42;
+
+ return SK_PASS;
+}
+
/* The read-only data slice is invalidated whenever a helper changes packet data */
SEC("?xdp")
__failure __msg("invalid mem access 'scalar'")
@@ -1255,6 +1477,19 @@ int skb_invalid_ctx(void *ctx)
return 0;
}
+/* Only supported prog type can create skb_meta-type dynptrs */
+SEC("?raw_tp")
+__failure __msg("calling kernel function bpf_dynptr_from_skb_meta is not allowed")
+int skb_meta_invalid_ctx(void *ctx)
+{
+ struct bpf_dynptr meta;
+
+ /* this should fail */
+ bpf_dynptr_from_skb_meta(ctx, 0, &meta);
+
+ return 0;
+}
+
SEC("fentry/skb_tx_error")
__failure __msg("must be referenced or trusted")
int BPF_PROG(skb_invalid_ctx_fentry, void *skb)
@@ -1665,6 +1900,29 @@ int clone_skb_packet_data(struct __sk_buff *skb)
return 0;
}
+/* A skb clone's metadata slice becomes invalid anytime packet data changes */
+SEC("?tc")
+__failure __msg("invalid mem access 'scalar'")
+int clone_skb_packet_meta(struct __sk_buff *skb)
+{
+ struct bpf_dynptr clone, meta;
+ __u8 *md;
+
+ bpf_dynptr_from_skb_meta(skb, 0, &meta);
+ bpf_dynptr_clone(&meta, &clone);
+ md = bpf_dynptr_slice_rdwr(&clone, 0, NULL, sizeof(*md));
+ if (!md)
+ return SK_DROP;
+
+ if (bpf_skb_pull_data(skb, skb->len))
+ return SK_DROP;
+
+ /* this should fail */
+ *md = 42;
+
+ return 0;
+}
+
/* A xdp clone's data slices should be invalid anytime packet data changes */
SEC("?xdp")
__failure __msg("invalid mem access 'scalar'")
diff --git a/tools/testing/selftests/bpf/progs/dynptr_success.c b/tools/testing/selftests/bpf/progs/dynptr_success.c
index 8315273cb900..127dea342e5a 100644
--- a/tools/testing/selftests/bpf/progs/dynptr_success.c
+++ b/tools/testing/selftests/bpf/progs/dynptr_success.c
@@ -211,6 +211,61 @@ int test_dynptr_skb_data(struct __sk_buff *skb)
return 1;
}
+SEC("?tc")
+int test_dynptr_skb_meta_data(struct __sk_buff *skb)
+{
+ struct bpf_dynptr meta;
+ __u8 *md;
+ int ret;
+
+ err = 1;
+ ret = bpf_dynptr_from_skb_meta(skb, 0, &meta);
+ if (ret)
+ return 1;
+
+ /* This should return NULL. Must use bpf_dynptr_slice API */
+ err = 2;
+ md = bpf_dynptr_data(&meta, 0, sizeof(*md));
+ if (md)
+ return 1;
+
+ err = 0;
+ return 1;
+}
+
+/* Check that skb metadata dynptr ops don't accept any flags. */
+SEC("?tc")
+int test_dynptr_skb_meta_flags(struct __sk_buff *skb)
+{
+ const __u64 INVALID_FLAGS = ~0ULL;
+ struct bpf_dynptr meta;
+ __u8 buf;
+ int ret;
+
+ err = 1;
+ ret = bpf_dynptr_from_skb_meta(skb, INVALID_FLAGS, &meta);
+ if (ret != -EINVAL)
+ return 1;
+
+ err = 2;
+ ret = bpf_dynptr_from_skb_meta(skb, 0, &meta);
+ if (ret)
+ return 1;
+
+ err = 3;
+ ret = bpf_dynptr_read(&buf, 0, &meta, 0, INVALID_FLAGS);
+ if (ret != -EINVAL)
+ return 1;
+
+ err = 4;
+ ret = bpf_dynptr_write(&meta, 0, &buf, 0, INVALID_FLAGS);
+ if (ret != -EINVAL)
+ return 1;
+
+ err = 0;
+ return 1;
+}
+
SEC("tp/syscalls/sys_enter_nanosleep")
int test_adjust(void *ctx)
{
diff --git a/tools/testing/selftests/bpf/progs/exceptions_assert.c b/tools/testing/selftests/bpf/progs/exceptions_assert.c
index 5e0a1ca96d4e..a01c2736890f 100644
--- a/tools/testing/selftests/bpf/progs/exceptions_assert.c
+++ b/tools/testing/selftests/bpf/progs/exceptions_assert.c
@@ -18,43 +18,43 @@
return *(u64 *)num; \
}
-__msg(": R0_w=0xffffffff80000000")
+__msg(": R0=0xffffffff80000000")
check_assert(s64, ==, eq_int_min, INT_MIN);
-__msg(": R0_w=0x7fffffff")
+__msg(": R0=0x7fffffff")
check_assert(s64, ==, eq_int_max, INT_MAX);
-__msg(": R0_w=0")
+__msg(": R0=0")
check_assert(s64, ==, eq_zero, 0);
-__msg(": R0_w=0x8000000000000000 R1_w=0x8000000000000000")
+__msg(": R0=0x8000000000000000 R1=0x8000000000000000")
check_assert(s64, ==, eq_llong_min, LLONG_MIN);
-__msg(": R0_w=0x7fffffffffffffff R1_w=0x7fffffffffffffff")
+__msg(": R0=0x7fffffffffffffff R1=0x7fffffffffffffff")
check_assert(s64, ==, eq_llong_max, LLONG_MAX);
-__msg(": R0_w=scalar(id=1,smax=0x7ffffffe)")
+__msg(": R0=scalar(id=1,smax=0x7ffffffe)")
check_assert(s64, <, lt_pos, INT_MAX);
-__msg(": R0_w=scalar(id=1,smax=-1,umin=0x8000000000000000,var_off=(0x8000000000000000; 0x7fffffffffffffff))")
+__msg(": R0=scalar(id=1,smax=-1,umin=0x8000000000000000,var_off=(0x8000000000000000; 0x7fffffffffffffff))")
check_assert(s64, <, lt_zero, 0);
-__msg(": R0_w=scalar(id=1,smax=0xffffffff7fffffff")
+__msg(": R0=scalar(id=1,smax=0xffffffff7fffffff")
check_assert(s64, <, lt_neg, INT_MIN);
-__msg(": R0_w=scalar(id=1,smax=0x7fffffff)")
+__msg(": R0=scalar(id=1,smax=0x7fffffff)")
check_assert(s64, <=, le_pos, INT_MAX);
-__msg(": R0_w=scalar(id=1,smax=0)")
+__msg(": R0=scalar(id=1,smax=0)")
check_assert(s64, <=, le_zero, 0);
-__msg(": R0_w=scalar(id=1,smax=0xffffffff80000000")
+__msg(": R0=scalar(id=1,smax=0xffffffff80000000")
check_assert(s64, <=, le_neg, INT_MIN);
-__msg(": R0_w=scalar(id=1,smin=umin=0x80000000,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))")
+__msg(": R0=scalar(id=1,smin=umin=0x80000000,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))")
check_assert(s64, >, gt_pos, INT_MAX);
-__msg(": R0_w=scalar(id=1,smin=umin=1,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))")
+__msg(": R0=scalar(id=1,smin=umin=1,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))")
check_assert(s64, >, gt_zero, 0);
-__msg(": R0_w=scalar(id=1,smin=0xffffffff80000001")
+__msg(": R0=scalar(id=1,smin=0xffffffff80000001")
check_assert(s64, >, gt_neg, INT_MIN);
-__msg(": R0_w=scalar(id=1,smin=umin=0x7fffffff,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))")
+__msg(": R0=scalar(id=1,smin=umin=0x7fffffff,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))")
check_assert(s64, >=, ge_pos, INT_MAX);
-__msg(": R0_w=scalar(id=1,smin=0,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))")
+__msg(": R0=scalar(id=1,smin=0,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))")
check_assert(s64, >=, ge_zero, 0);
-__msg(": R0_w=scalar(id=1,smin=0xffffffff80000000")
+__msg(": R0=scalar(id=1,smin=0xffffffff80000000")
check_assert(s64, >=, ge_neg, INT_MIN);
SEC("?tc")
diff --git a/tools/testing/selftests/bpf/progs/freplace_connect_v4_prog.c b/tools/testing/selftests/bpf/progs/freplace_connect_v4_prog.c
index 544e5ac90461..d09bbd8ae8a8 100644
--- a/tools/testing/selftests/bpf/progs/freplace_connect_v4_prog.c
+++ b/tools/testing/selftests/bpf/progs/freplace_connect_v4_prog.c
@@ -12,7 +12,7 @@
SEC("freplace/connect_v4_prog")
int new_connect_v4_prog(struct bpf_sock_addr *ctx)
{
- // return value thats in invalid range
+ // return value that's in invalid range
return 255;
}
diff --git a/tools/testing/selftests/bpf/progs/iters_state_safety.c b/tools/testing/selftests/bpf/progs/iters_state_safety.c
index f41257eadbb2..d273b46dfc7c 100644
--- a/tools/testing/selftests/bpf/progs/iters_state_safety.c
+++ b/tools/testing/selftests/bpf/progs/iters_state_safety.c
@@ -30,7 +30,7 @@ int force_clang_to_emit_btf_for_externs(void *ctx)
SEC("?raw_tp")
__success __log_level(2)
-__msg("fp-8_w=iter_num(ref_id=1,state=active,depth=0)")
+__msg("fp-8=iter_num(ref_id=1,state=active,depth=0)")
int create_and_destroy(void *ctx)
{
struct bpf_iter_num iter;
@@ -196,7 +196,7 @@ int leak_iter_from_subprog_fail(void *ctx)
SEC("?raw_tp")
__success __log_level(2)
-__msg("fp-8_w=iter_num(ref_id=1,state=active,depth=0)")
+__msg("fp-8=iter_num(ref_id=1,state=active,depth=0)")
int valid_stack_reuse(void *ctx)
{
struct bpf_iter_num iter;
@@ -345,7 +345,7 @@ int __naked read_from_iter_slot_fail(void)
"r3 = 1000;"
"call %[bpf_iter_num_new];"
- /* attemp to leak bpf_iter_num state */
+ /* attempt to leak bpf_iter_num state */
"r7 = *(u64 *)(r6 + 0);"
"r8 = *(u64 *)(r6 + 8);"
diff --git a/tools/testing/selftests/bpf/progs/iters_task_failure.c b/tools/testing/selftests/bpf/progs/iters_task_failure.c
index 6b1588d70652..fe3663dedbe1 100644
--- a/tools/testing/selftests/bpf/progs/iters_task_failure.c
+++ b/tools/testing/selftests/bpf/progs/iters_task_failure.c
@@ -15,7 +15,7 @@ void bpf_rcu_read_lock(void) __ksym;
void bpf_rcu_read_unlock(void) __ksym;
SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
-__failure __msg("expected an RCU CS when using bpf_iter_task_next")
+__failure __msg("kernel func bpf_iter_task_new requires RCU critical section protection")
int BPF_PROG(iter_tasks_without_lock)
{
struct task_struct *pos;
@@ -27,7 +27,7 @@ int BPF_PROG(iter_tasks_without_lock)
}
SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
-__failure __msg("expected an RCU CS when using bpf_iter_css_next")
+__failure __msg("kernel func bpf_iter_css_new requires RCU critical section protection")
int BPF_PROG(iter_css_without_lock)
{
u64 cg_id = bpf_get_current_cgroup_id();
diff --git a/tools/testing/selftests/bpf/progs/iters_testmod.c b/tools/testing/selftests/bpf/progs/iters_testmod.c
index 9e4b45201e69..5379e9960ffd 100644
--- a/tools/testing/selftests/bpf/progs/iters_testmod.c
+++ b/tools/testing/selftests/bpf/progs/iters_testmod.c
@@ -123,3 +123,49 @@ out:
bpf_iter_num_destroy(&num_it);
return 0;
}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+__failure __msg("kernel func bpf_kfunc_ret_rcu_test requires RCU critical section protection")
+int iter_ret_rcu_test_protected(const void *ctx)
+{
+ struct task_struct *p;
+
+ p = bpf_kfunc_ret_rcu_test();
+ return p->pid;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+__failure __msg("R1 type=rcu_ptr_or_null_ expected=")
+int iter_ret_rcu_test_type(const void *ctx)
+{
+ struct task_struct *p;
+
+ bpf_rcu_read_lock();
+ p = bpf_kfunc_ret_rcu_test();
+ bpf_this_cpu_ptr(p);
+ bpf_rcu_read_unlock();
+ return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+__failure __msg("kernel func bpf_kfunc_ret_rcu_test_nostruct requires RCU critical section protection")
+int iter_ret_rcu_test_protected_nostruct(const void *ctx)
+{
+ void *p;
+
+ p = bpf_kfunc_ret_rcu_test_nostruct(4);
+ return *(int *)p;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+__failure __msg("R1 type=rdonly_rcu_mem_or_null expected=")
+int iter_ret_rcu_test_type_nostruct(const void *ctx)
+{
+ void *p;
+
+ bpf_rcu_read_lock();
+ p = bpf_kfunc_ret_rcu_test_nostruct(4);
+ bpf_this_cpu_ptr(p);
+ bpf_rcu_read_unlock();
+ return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/iters_testmod_seq.c b/tools/testing/selftests/bpf/progs/iters_testmod_seq.c
index 6543d5b6e0a9..83791348bed5 100644
--- a/tools/testing/selftests/bpf/progs/iters_testmod_seq.c
+++ b/tools/testing/selftests/bpf/progs/iters_testmod_seq.c
@@ -20,7 +20,7 @@ __s64 res_empty;
SEC("raw_tp/sys_enter")
__success __log_level(2)
-__msg("fp-16_w=iter_testmod_seq(ref_id=1,state=active,depth=0)")
+__msg("fp-16=iter_testmod_seq(ref_id=1,state=active,depth=0)")
__msg("fp-16=iter_testmod_seq(ref_id=1,state=drained,depth=0)")
__msg("call bpf_iter_testmod_seq_destroy")
int testmod_seq_empty(const void *ctx)
@@ -38,7 +38,7 @@ __s64 res_full;
SEC("raw_tp/sys_enter")
__success __log_level(2)
-__msg("fp-16_w=iter_testmod_seq(ref_id=1,state=active,depth=0)")
+__msg("fp-16=iter_testmod_seq(ref_id=1,state=active,depth=0)")
__msg("fp-16=iter_testmod_seq(ref_id=1,state=drained,depth=0)")
__msg("call bpf_iter_testmod_seq_destroy")
int testmod_seq_full(const void *ctx)
@@ -58,7 +58,7 @@ static volatile int zero = 0;
SEC("raw_tp/sys_enter")
__success __log_level(2)
-__msg("fp-16_w=iter_testmod_seq(ref_id=1,state=active,depth=0)")
+__msg("fp-16=iter_testmod_seq(ref_id=1,state=active,depth=0)")
__msg("fp-16=iter_testmod_seq(ref_id=1,state=drained,depth=0)")
__msg("call bpf_iter_testmod_seq_destroy")
int testmod_seq_truncated(const void *ctx)
diff --git a/tools/testing/selftests/bpf/progs/kprobe_write_ctx.c b/tools/testing/selftests/bpf/progs/kprobe_write_ctx.c
new file mode 100644
index 000000000000..f77aef0474d3
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/kprobe_write_ctx.c
@@ -0,0 +1,22 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+#if defined(__TARGET_ARCH_x86)
+SEC("kprobe")
+int kprobe_write_ctx(struct pt_regs *ctx)
+{
+ ctx->ax = 0;
+ return 0;
+}
+
+SEC("kprobe.multi")
+int kprobe_multi_write_ctx(struct pt_regs *ctx)
+{
+ ctx->ax = 0;
+ return 0;
+}
+#endif
diff --git a/tools/testing/selftests/bpf/progs/linked_list_fail.c b/tools/testing/selftests/bpf/progs/linked_list_fail.c
index 6438982b928b..ddd26d1a083f 100644
--- a/tools/testing/selftests/bpf/progs/linked_list_fail.c
+++ b/tools/testing/selftests/bpf/progs/linked_list_fail.c
@@ -226,8 +226,7 @@ int obj_new_no_composite(void *ctx)
SEC("?tc")
int obj_new_no_struct(void *ctx)
{
-
- bpf_obj_new(union { int data; unsigned udata; });
+ (void)bpf_obj_new(union { int data; unsigned udata; });
return 0;
}
@@ -252,7 +251,7 @@ int new_null_ret(void *ctx)
SEC("?tc")
int obj_new_acq(void *ctx)
{
- bpf_obj_new(struct foo);
+ (void)bpf_obj_new(struct foo);
return 0;
}
diff --git a/tools/testing/selftests/bpf/progs/loop1.c b/tools/testing/selftests/bpf/progs/loop1.c
index 50e66772c046..b0fa26fb4760 100644
--- a/tools/testing/selftests/bpf/progs/loop1.c
+++ b/tools/testing/selftests/bpf/progs/loop1.c
@@ -1,11 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
// Copyright (c) 2019 Facebook
-#include <linux/sched.h>
-#include <linux/ptrace.h>
-#include <stdint.h>
-#include <stddef.h>
-#include <stdbool.h>
-#include <linux/bpf.h>
+#include "vmlinux.h"
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_tracing.h>
diff --git a/tools/testing/selftests/bpf/progs/loop2.c b/tools/testing/selftests/bpf/progs/loop2.c
index 947bb7e988c2..0227409d4b0e 100644
--- a/tools/testing/selftests/bpf/progs/loop2.c
+++ b/tools/testing/selftests/bpf/progs/loop2.c
@@ -1,11 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
// Copyright (c) 2019 Facebook
-#include <linux/sched.h>
-#include <linux/ptrace.h>
-#include <stdint.h>
-#include <stddef.h>
-#include <stdbool.h>
-#include <linux/bpf.h>
+#include "vmlinux.h"
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_tracing.h>
diff --git a/tools/testing/selftests/bpf/progs/loop3.c b/tools/testing/selftests/bpf/progs/loop3.c
index 717dab14322b..5d1c9a775e6b 100644
--- a/tools/testing/selftests/bpf/progs/loop3.c
+++ b/tools/testing/selftests/bpf/progs/loop3.c
@@ -1,11 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
// Copyright (c) 2019 Facebook
-#include <linux/sched.h>
-#include <linux/ptrace.h>
-#include <stdint.h>
-#include <stddef.h>
-#include <stdbool.h>
-#include <linux/bpf.h>
+#include "vmlinux.h"
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_tracing.h>
diff --git a/tools/testing/selftests/bpf/progs/loop6.c b/tools/testing/selftests/bpf/progs/loop6.c
index e4ff97fbcce1..dd36aff4fba3 100644
--- a/tools/testing/selftests/bpf/progs/loop6.c
+++ b/tools/testing/selftests/bpf/progs/loop6.c
@@ -1,8 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
-#include <linux/ptrace.h>
-#include <stddef.h>
-#include <linux/bpf.h>
+#include <vmlinux.h>
+#include <bpf/bpf_core_read.h>
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_tracing.h>
#include "bpf_misc.h"
@@ -26,12 +25,6 @@ char _license[] SEC("license") = "GPL";
#define SG_CHAIN 0x01UL
#define SG_END 0x02UL
-struct scatterlist {
- unsigned long page_link;
- unsigned int offset;
- unsigned int length;
-};
-
#define sg_is_chain(sg) ((sg)->page_link & SG_CHAIN)
#define sg_is_last(sg) ((sg)->page_link & SG_END)
#define sg_chain_ptr(sg) \
@@ -62,7 +55,7 @@ static inline struct scatterlist *get_sgp(struct scatterlist **sgs, int i)
return sgp;
}
-int config = 0;
+int run_once = 0;
int result = 0;
SEC("kprobe/virtqueue_add_sgs")
@@ -73,14 +66,14 @@ int BPF_KPROBE(trace_virtqueue_add_sgs, void *unused, struct scatterlist **sgs,
__u64 length1 = 0, length2 = 0;
unsigned int i, n, len;
- if (config != 0)
+ if (run_once != 0)
return 0;
for (i = 0; (i < VIRTIO_MAX_SGS) && (i < out_sgs); i++) {
__sink(out_sgs);
for (n = 0, sgp = get_sgp(sgs, i); sgp && (n < SG_MAX);
sgp = __sg_next(sgp)) {
- bpf_probe_read_kernel(&len, sizeof(len), &sgp->length);
+ len = BPF_CORE_READ(sgp, length);
length1 += len;
n++;
}
@@ -90,13 +83,13 @@ int BPF_KPROBE(trace_virtqueue_add_sgs, void *unused, struct scatterlist **sgs,
__sink(in_sgs);
for (n = 0, sgp = get_sgp(sgs, i); sgp && (n < SG_MAX);
sgp = __sg_next(sgp)) {
- bpf_probe_read_kernel(&len, sizeof(len), &sgp->length);
+ len = BPF_CORE_READ(sgp, length);
length2 += len;
n++;
}
}
- config = 1;
+ run_once = 1;
result = length2 - length1;
return 0;
}
diff --git a/tools/testing/selftests/bpf/progs/lpm_trie.h b/tools/testing/selftests/bpf/progs/lpm_trie.h
new file mode 100644
index 000000000000..76aa5821807f
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/lpm_trie.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef __PROGS_LPM_TRIE_H
+#define __PROGS_LPM_TRIE_H
+
+struct trie_key {
+ __u32 prefixlen;
+ __u32 data;
+};
+
+/* Benchmark operations */
+enum {
+ LPM_OP_NOOP = 0,
+ LPM_OP_BASELINE,
+ LPM_OP_LOOKUP,
+ LPM_OP_INSERT,
+ LPM_OP_UPDATE,
+ LPM_OP_DELETE,
+ LPM_OP_FREE
+};
+
+/*
+ * Return values from run_bench.
+ *
+ * Negative values are also allowed and represent kernel error codes.
+ */
+#define LPM_BENCH_SUCCESS 0
+#define LPM_BENCH_REINIT_MAP 1 /* Reset trie to initial state for current op */
+
+#endif
diff --git a/tools/testing/selftests/bpf/progs/lpm_trie_bench.c b/tools/testing/selftests/bpf/progs/lpm_trie_bench.c
new file mode 100644
index 000000000000..a0e6ebd5507a
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/lpm_trie_bench.c
@@ -0,0 +1,230 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Cloudflare */
+
+#include <vmlinux.h>
+#include <errno.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
+#include "bpf_misc.h"
+#include "bpf_atomic.h"
+#include "progs/lpm_trie.h"
+
+#define BPF_OBJ_NAME_LEN 16U
+#define MAX_ENTRIES 100000000
+#define NR_LOOPS 10000
+
+char _license[] SEC("license") = "GPL";
+
+/* Filled by userspace. See fill_map() in bench_lpm_trie_map.c */
+struct {
+ __uint(type, BPF_MAP_TYPE_LPM_TRIE);
+ __type(key, struct trie_key);
+ __type(value, __u32);
+ __uint(map_flags, BPF_F_NO_PREALLOC);
+ __uint(max_entries, MAX_ENTRIES);
+} trie_map SEC(".maps");
+
+long hits;
+long duration_ns;
+
+/* Configured from userspace */
+__u32 nr_entries;
+__u32 prefixlen;
+bool random;
+__u8 op;
+
+static __u64 latency_free_start;
+
+SEC("fentry/bpf_map_free_deferred")
+int BPF_PROG(trie_free_entry, struct work_struct *work)
+{
+ struct bpf_map *map = container_of(work, struct bpf_map, work);
+ char name[BPF_OBJ_NAME_LEN];
+ u32 map_type;
+
+ map_type = BPF_CORE_READ(map, map_type);
+ if (map_type != BPF_MAP_TYPE_LPM_TRIE)
+ return 0;
+
+ /*
+ * Ideally we'd have access to the map ID but that's already
+ * freed before we enter trie_free().
+ */
+ BPF_CORE_READ_STR_INTO(&name, map, name);
+ if (bpf_strncmp(name, BPF_OBJ_NAME_LEN, "trie_free_map"))
+ return 0;
+
+ latency_free_start = bpf_ktime_get_ns();
+
+ return 0;
+}
+
+SEC("fexit/bpf_map_free_deferred")
+int BPF_PROG(trie_free_exit, struct work_struct *work)
+{
+ __u64 val;
+
+ if (!latency_free_start)
+ return 0;
+
+ val = bpf_ktime_get_ns() - latency_free_start;
+ latency_free_start = 0;
+
+ __sync_add_and_fetch(&duration_ns, val);
+ __sync_add_and_fetch(&hits, 1);
+
+ return 0;
+}
+
+static __u32 cur_key;
+
+static __always_inline void generate_key(struct trie_key *key)
+{
+ key->prefixlen = prefixlen;
+
+ if (random)
+ key->data = bpf_get_prandom_u32() % nr_entries;
+ else
+ key->data = cur_key++ % nr_entries;
+}
+
+static int noop(__u32 index, __u32 *unused)
+{
+ return 0;
+}
+
+static int baseline(__u32 index, __u32 *unused)
+{
+ struct trie_key key;
+ __u32 blackbox = 0;
+
+ generate_key(&key);
+ /* Avoid compiler optimizing out the modulo */
+ barrier_var(blackbox);
+ blackbox = READ_ONCE(key.data);
+
+ return 0;
+}
+
+static int lookup(__u32 index, int *retval)
+{
+ struct trie_key key;
+
+ generate_key(&key);
+ if (!bpf_map_lookup_elem(&trie_map, &key)) {
+ *retval = -ENOENT;
+ return 1;
+ }
+
+ return 0;
+}
+
+static int insert(__u32 index, int *retval)
+{
+ struct trie_key key;
+ u32 val = 1;
+ int err;
+
+ generate_key(&key);
+ err = bpf_map_update_elem(&trie_map, &key, &val, BPF_NOEXIST);
+ if (err) {
+ *retval = err;
+ return 1;
+ }
+
+ /* Is this the last entry? */
+ if (key.data == nr_entries - 1) {
+ /* For atomicity concerns, see the comment in delete() */
+ *retval = LPM_BENCH_REINIT_MAP;
+ return 1;
+ }
+
+ return 0;
+}
+
+static int update(__u32 index, int *retval)
+{
+ struct trie_key key;
+ u32 val = 1;
+ int err;
+
+ generate_key(&key);
+ err = bpf_map_update_elem(&trie_map, &key, &val, BPF_EXIST);
+ if (err) {
+ *retval = err;
+ return 1;
+ }
+
+ return 0;
+}
+
+static int delete(__u32 index, int *retval)
+{
+ struct trie_key key;
+ int err;
+
+ generate_key(&key);
+ err = bpf_map_delete_elem(&trie_map, &key);
+ if (err) {
+ *retval = err;
+ return 1;
+ }
+
+ /* Do we need to refill the map? */
+ if (key.data == nr_entries - 1) {
+ /*
+ * Atomicity isn't required because DELETE only supports
+ * one producer running concurrently. What we need is a
+ * way to track how many entries have been deleted from
+ * the trie between consecutive invocations of the BPF
+ * prog because a single bpf_loop() call might not
+ * delete all entries, e.g. when NR_LOOPS < nr_entries.
+ */
+ *retval = LPM_BENCH_REINIT_MAP;
+ return 1;
+ }
+
+ return 0;
+}
+
+SEC("xdp")
+int BPF_PROG(run_bench)
+{
+ int err = LPM_BENCH_SUCCESS;
+ u64 start, delta;
+ int loops;
+
+ start = bpf_ktime_get_ns();
+
+ switch (op) {
+ case LPM_OP_NOOP:
+ loops = bpf_loop(NR_LOOPS, noop, NULL, 0);
+ break;
+ case LPM_OP_BASELINE:
+ loops = bpf_loop(NR_LOOPS, baseline, NULL, 0);
+ break;
+ case LPM_OP_LOOKUP:
+ loops = bpf_loop(NR_LOOPS, lookup, &err, 0);
+ break;
+ case LPM_OP_INSERT:
+ loops = bpf_loop(NR_LOOPS, insert, &err, 0);
+ break;
+ case LPM_OP_UPDATE:
+ loops = bpf_loop(NR_LOOPS, update, &err, 0);
+ break;
+ case LPM_OP_DELETE:
+ loops = bpf_loop(NR_LOOPS, delete, &err, 0);
+ break;
+ default:
+ bpf_printk("invalid benchmark operation\n");
+ return -1;
+ }
+
+ delta = bpf_ktime_get_ns() - start;
+
+ __sync_add_and_fetch(&duration_ns, delta);
+ __sync_add_and_fetch(&hits, loops);
+
+ return err;
+}
diff --git a/tools/testing/selftests/bpf/progs/lpm_trie_map.c b/tools/testing/selftests/bpf/progs/lpm_trie_map.c
new file mode 100644
index 000000000000..6e60d686b664
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/lpm_trie_map.c
@@ -0,0 +1,19 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+#define MAX_ENTRIES 100000000
+
+struct trie_key {
+ __u32 prefixlen;
+ __u32 data;
+};
+
+struct {
+ __uint(type, BPF_MAP_TYPE_LPM_TRIE);
+ __type(key, struct trie_key);
+ __type(value, __u32);
+ __uint(map_flags, BPF_F_NO_PREALLOC);
+ __uint(max_entries, MAX_ENTRIES);
+} trie_free_map SEC(".maps");
diff --git a/tools/testing/selftests/bpf/progs/map_excl.c b/tools/testing/selftests/bpf/progs/map_excl.c
new file mode 100644
index 000000000000..d461684728e4
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/map_excl.c
@@ -0,0 +1,34 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2025 Google LLC. */
+#include <linux/bpf.h>
+#include <time.h>
+#include <bpf/bpf_helpers.h>
+
+#include "bpf_misc.h"
+
+struct {
+ __uint(type, BPF_MAP_TYPE_ARRAY);
+ __type(key, __u32);
+ __type(value, __u32);
+ __uint(max_entries, 1);
+} excl_map SEC(".maps");
+
+char _license[] SEC("license") = "GPL";
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+int should_have_access(void *ctx)
+{
+ int key = 0, value = 0xdeadbeef;
+
+ bpf_map_update_elem(&excl_map, &key, &value, 0);
+ return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+int should_not_have_access(void *ctx)
+{
+ int key = 0, value = 0xdeadbeef;
+
+ bpf_map_update_elem(&excl_map, &key, &value, 0);
+ return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/mem_rdonly_untrusted.c b/tools/testing/selftests/bpf/progs/mem_rdonly_untrusted.c
index 4f94c971ae86..3b984b6ae7c0 100644
--- a/tools/testing/selftests/bpf/progs/mem_rdonly_untrusted.c
+++ b/tools/testing/selftests/bpf/progs/mem_rdonly_untrusted.c
@@ -8,8 +8,8 @@
SEC("tp_btf/sys_enter")
__success
__log_level(2)
-__msg("r8 = *(u64 *)(r7 +0) ; R7_w=ptr_nameidata(off={{[0-9]+}}) R8_w=rdonly_untrusted_mem(sz=0)")
-__msg("r9 = *(u8 *)(r8 +0) ; R8_w=rdonly_untrusted_mem(sz=0) R9_w=scalar")
+__msg("r8 = *(u64 *)(r7 +0) ; R7=ptr_nameidata(off={{[0-9]+}}) R8=rdonly_untrusted_mem(sz=0)")
+__msg("r9 = *(u8 *)(r8 +0) ; R8=rdonly_untrusted_mem(sz=0) R9=scalar")
int btf_id_to_ptr_mem(void *ctx)
{
struct task_struct *task;
diff --git a/tools/testing/selftests/bpf/progs/mptcp_subflow.c b/tools/testing/selftests/bpf/progs/mptcp_subflow.c
index 70302477e326..41389e579578 100644
--- a/tools/testing/selftests/bpf/progs/mptcp_subflow.c
+++ b/tools/testing/selftests/bpf/progs/mptcp_subflow.c
@@ -117,7 +117,7 @@ int _getsockopt_subflow(struct bpf_sockopt *ctx)
return 1;
msk = bpf_core_cast(sk, struct mptcp_sock);
- if (msk->pm.subflows != 1) {
+ if (msk->pm.extra_subflows != 1) {
ctx->retval = -1;
return 1;
}
diff --git a/tools/testing/selftests/bpf/progs/rbtree_search.c b/tools/testing/selftests/bpf/progs/rbtree_search.c
index 098ef970fac1..b05565d1db0d 100644
--- a/tools/testing/selftests/bpf/progs/rbtree_search.c
+++ b/tools/testing/selftests/bpf/progs/rbtree_search.c
@@ -183,7 +183,7 @@ long test_##op##_spinlock_##dolock(void *ctx) \
}
/*
- * Use a spearate MSG macro instead of passing to TEST_XXX(..., MSG)
+ * Use a separate MSG macro instead of passing to TEST_XXX(..., MSG)
* to ensure the message itself is not in the bpf prog lineinfo
* which the verifier includes in its log.
* Otherwise, the test_loader will incorrectly match the prog lineinfo
diff --git a/tools/testing/selftests/bpf/progs/test_stacktrace_map.c b/tools/testing/selftests/bpf/progs/stacktrace_map.c
index 47568007b668..0c77df05be7f 100644
--- a/tools/testing/selftests/bpf/progs/test_stacktrace_map.c
+++ b/tools/testing/selftests/bpf/progs/stacktrace_map.c
@@ -50,6 +50,7 @@ struct sched_switch_args {
int next_prio;
};
+__u32 stack_id;
SEC("tracepoint/sched/sched_switch")
int oncpu(struct sched_switch_args *ctx)
{
@@ -64,6 +65,7 @@ int oncpu(struct sched_switch_args *ctx)
/* The size of stackmap and stackid_hmap should be the same */
key = bpf_get_stackid(ctx, &stackmap, 0);
if ((int)key >= 0) {
+ stack_id = key;
bpf_map_update_elem(&stackid_hmap, &key, &val, 0);
stack_p = bpf_map_lookup_elem(&stack_amap, &key);
if (stack_p)
diff --git a/tools/testing/selftests/bpf/progs/stream.c b/tools/testing/selftests/bpf/progs/stream.c
index 35790897dc87..4a5bd852f10c 100644
--- a/tools/testing/selftests/bpf/progs/stream.c
+++ b/tools/testing/selftests/bpf/progs/stream.c
@@ -5,6 +5,7 @@
#include <bpf/bpf_helpers.h>
#include "bpf_misc.h"
#include "bpf_experimental.h"
+#include "bpf_arena_common.h"
struct arr_elem {
struct bpf_res_spin_lock lock;
@@ -17,10 +18,29 @@ struct {
__type(value, struct arr_elem);
} arrmap SEC(".maps");
+struct {
+ __uint(type, BPF_MAP_TYPE_ARENA);
+ __uint(map_flags, BPF_F_MMAPABLE);
+ __uint(max_entries, 1); /* number of pages */
+} arena SEC(".maps");
+
+struct elem {
+ struct bpf_timer timer;
+};
+
+struct {
+ __uint(type, BPF_MAP_TYPE_ARRAY);
+ __uint(max_entries, 1);
+ __type(key, int);
+ __type(value, struct elem);
+} array SEC(".maps");
+
#define ENOSPC 28
#define _STR "xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
int size;
+u64 fault_addr;
+void *arena_ptr;
SEC("syscall")
__success __retval(0)
@@ -37,7 +57,15 @@ int stream_exhaust(void *ctx)
}
SEC("syscall")
+__arch_x86_64
+__arch_arm64
+__arch_s390x
__success __retval(0)
+__stderr("ERROR: Timeout detected for may_goto instruction")
+__stderr("CPU: {{[0-9]+}} UID: 0 PID: {{[0-9]+}} Comm: {{.*}}")
+__stderr("Call trace:\n"
+"{{([a-zA-Z_][a-zA-Z0-9_]*\\+0x[0-9a-fA-F]+/0x[0-9a-fA-F]+\n"
+"|[ \t]+[^\n]+\n)*}}")
int stream_cond_break(void *ctx)
{
while (can_loop)
@@ -47,6 +75,15 @@ int stream_cond_break(void *ctx)
SEC("syscall")
__success __retval(0)
+__stderr("ERROR: AA or ABBA deadlock detected for bpf_res_spin_lock")
+__stderr("{{Attempted lock = (0x[0-9a-fA-F]+)\n"
+"Total held locks = 1\n"
+"Held lock\\[ 0\\] = \\1}}")
+__stderr("...")
+__stderr("CPU: {{[0-9]+}} UID: 0 PID: {{[0-9]+}} Comm: {{.*}}")
+__stderr("Call trace:\n"
+"{{([a-zA-Z_][a-zA-Z0-9_]*\\+0x[0-9a-fA-F]+/0x[0-9a-fA-F]+\n"
+"|[ \t]+[^\n]+\n)*}}")
int stream_deadlock(void *ctx)
{
struct bpf_res_spin_lock *lock, *nlock;
@@ -76,4 +113,125 @@ int stream_syscall(void *ctx)
return 0;
}
+SEC("syscall")
+__arch_x86_64
+__arch_arm64
+__success __retval(0)
+__stderr("ERROR: Arena WRITE access at unmapped address 0x{{.*}}")
+__stderr("CPU: {{[0-9]+}} UID: 0 PID: {{[0-9]+}} Comm: {{.*}}")
+__stderr("Call trace:\n"
+"{{([a-zA-Z_][a-zA-Z0-9_]*\\+0x[0-9a-fA-F]+/0x[0-9a-fA-F]+\n"
+"|[ \t]+[^\n]+\n)*}}")
+int stream_arena_write_fault(void *ctx)
+{
+ struct bpf_arena *ptr = (void *)&arena;
+ u64 user_vm_start;
+
+ /* Prevent GCC bounds warning: casting &arena to struct bpf_arena *
+ * triggers bounds checking since the map definition is smaller than struct
+ * bpf_arena. barrier_var() makes the pointer opaque to GCC, preventing the
+ * bounds analysis
+ */
+ barrier_var(ptr);
+ user_vm_start = ptr->user_vm_start;
+ fault_addr = user_vm_start + 0x7fff;
+ bpf_addr_space_cast(user_vm_start, 0, 1);
+ asm volatile (
+ "r1 = %0;"
+ "r2 = 1;"
+ "*(u32 *)(r1 + 0x7fff) = r2;"
+ :
+ : "r" (user_vm_start)
+ : "r1", "r2"
+ );
+ return 0;
+}
+
+SEC("syscall")
+__arch_x86_64
+__arch_arm64
+__success __retval(0)
+__stderr("ERROR: Arena READ access at unmapped address 0x{{.*}}")
+__stderr("CPU: {{[0-9]+}} UID: 0 PID: {{[0-9]+}} Comm: {{.*}}")
+__stderr("Call trace:\n"
+"{{([a-zA-Z_][a-zA-Z0-9_]*\\+0x[0-9a-fA-F]+/0x[0-9a-fA-F]+\n"
+"|[ \t]+[^\n]+\n)*}}")
+int stream_arena_read_fault(void *ctx)
+{
+ struct bpf_arena *ptr = (void *)&arena;
+ u64 user_vm_start;
+
+ /* Prevent GCC bounds warning: casting &arena to struct bpf_arena *
+ * triggers bounds checking since the map definition is smaller than struct
+ * bpf_arena. barrier_var() makes the pointer opaque to GCC, preventing the
+ * bounds analysis
+ */
+ barrier_var(ptr);
+ user_vm_start = ptr->user_vm_start;
+ fault_addr = user_vm_start + 0x7fff;
+ bpf_addr_space_cast(user_vm_start, 0, 1);
+ asm volatile (
+ "r1 = %0;"
+ "r1 = *(u32 *)(r1 + 0x7fff);"
+ :
+ : "r" (user_vm_start)
+ : "r1"
+ );
+ return 0;
+}
+
+static __noinline void subprog(void)
+{
+ int __arena *addr = (int __arena *)0xdeadbeef;
+
+ arena_ptr = &arena;
+ *addr = 1;
+}
+
+SEC("syscall")
+__arch_x86_64
+__arch_arm64
+__success __retval(0)
+__stderr("ERROR: Arena WRITE access at unmapped address 0x{{.*}}")
+__stderr("CPU: {{[0-9]+}} UID: 0 PID: {{[0-9]+}} Comm: {{.*}}")
+__stderr("Call trace:\n"
+"{{([a-zA-Z_][a-zA-Z0-9_]*\\+0x[0-9a-fA-F]+/0x[0-9a-fA-F]+\n"
+"|[ \t]+[^\n]+\n)*}}")
+int stream_arena_subprog_fault(void *ctx)
+{
+ subprog();
+ return 0;
+}
+
+static __noinline int timer_cb(void *map, int *key, struct bpf_timer *timer)
+{
+ int __arena *addr = (int __arena *)0xdeadbeef;
+
+ arena_ptr = &arena;
+ *addr = 1;
+ return 0;
+}
+
+SEC("syscall")
+__arch_x86_64
+__arch_arm64
+__success __retval(0)
+__stderr("ERROR: Arena WRITE access at unmapped address 0x{{.*}}")
+__stderr("CPU: {{[0-9]+}} UID: 0 PID: {{[0-9]+}} Comm: {{.*}}")
+__stderr("Call trace:\n"
+"{{([a-zA-Z_][a-zA-Z0-9_]*\\+0x[0-9a-fA-F]+/0x[0-9a-fA-F]+\n"
+"|[ \t]+[^\n]+\n)*}}")
+int stream_arena_callback_fault(void *ctx)
+{
+ struct bpf_timer *arr_timer;
+
+ arr_timer = bpf_map_lookup_elem(&array, &(int){0});
+ if (!arr_timer)
+ return 0;
+ bpf_timer_init(arr_timer, &array, 1);
+ bpf_timer_set_callback(arr_timer, timer_cb);
+ bpf_timer_start(arr_timer, 0, 0);
+ return 0;
+}
+
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/string_kfuncs_failure1.c b/tools/testing/selftests/bpf/progs/string_kfuncs_failure1.c
index 53af438bd998..99d72c68f76a 100644
--- a/tools/testing/selftests/bpf/progs/string_kfuncs_failure1.c
+++ b/tools/testing/selftests/bpf/progs/string_kfuncs_failure1.c
@@ -31,6 +31,8 @@ char *invalid_kern_ptr = (char *)-1;
/* Passing NULL to string kfuncs (treated as a userspace ptr) */
SEC("syscall") __retval(USER_PTR_ERR) int test_strcmp_null1(void *ctx) { return bpf_strcmp(NULL, "hello"); }
SEC("syscall") __retval(USER_PTR_ERR)int test_strcmp_null2(void *ctx) { return bpf_strcmp("hello", NULL); }
+SEC("syscall") __retval(USER_PTR_ERR) int test_strcasecmp_null1(void *ctx) { return bpf_strcasecmp(NULL, "HELLO"); }
+SEC("syscall") __retval(USER_PTR_ERR)int test_strcasecmp_null2(void *ctx) { return bpf_strcasecmp("HELLO", NULL); }
SEC("syscall") __retval(USER_PTR_ERR)int test_strchr_null(void *ctx) { return bpf_strchr(NULL, 'a'); }
SEC("syscall") __retval(USER_PTR_ERR)int test_strchrnul_null(void *ctx) { return bpf_strchrnul(NULL, 'a'); }
SEC("syscall") __retval(USER_PTR_ERR)int test_strnchr_null(void *ctx) { return bpf_strnchr(NULL, 1, 'a'); }
@@ -49,6 +51,8 @@ SEC("syscall") __retval(USER_PTR_ERR)int test_strnstr_null2(void *ctx) { return
/* Passing userspace ptr to string kfuncs */
SEC("syscall") __retval(USER_PTR_ERR) int test_strcmp_user_ptr1(void *ctx) { return bpf_strcmp(user_ptr, "hello"); }
SEC("syscall") __retval(USER_PTR_ERR) int test_strcmp_user_ptr2(void *ctx) { return bpf_strcmp("hello", user_ptr); }
+SEC("syscall") __retval(USER_PTR_ERR) int test_strcasecmp_user_ptr1(void *ctx) { return bpf_strcasecmp(user_ptr, "HELLO"); }
+SEC("syscall") __retval(USER_PTR_ERR) int test_strcasecmp_user_ptr2(void *ctx) { return bpf_strcasecmp("HELLO", user_ptr); }
SEC("syscall") __retval(USER_PTR_ERR) int test_strchr_user_ptr(void *ctx) { return bpf_strchr(user_ptr, 'a'); }
SEC("syscall") __retval(USER_PTR_ERR) int test_strchrnul_user_ptr(void *ctx) { return bpf_strchrnul(user_ptr, 'a'); }
SEC("syscall") __retval(USER_PTR_ERR) int test_strnchr_user_ptr(void *ctx) { return bpf_strnchr(user_ptr, 1, 'a'); }
@@ -69,6 +73,8 @@ SEC("syscall") __retval(USER_PTR_ERR) int test_strnstr_user_ptr2(void *ctx) { re
/* Passing invalid kernel ptr to string kfuncs should always return -EFAULT */
SEC("syscall") __retval(-EFAULT) int test_strcmp_pagefault1(void *ctx) { return bpf_strcmp(invalid_kern_ptr, "hello"); }
SEC("syscall") __retval(-EFAULT) int test_strcmp_pagefault2(void *ctx) { return bpf_strcmp("hello", invalid_kern_ptr); }
+SEC("syscall") __retval(-EFAULT) int test_strcasecmp_pagefault1(void *ctx) { return bpf_strcasecmp(invalid_kern_ptr, "HELLO"); }
+SEC("syscall") __retval(-EFAULT) int test_strcasecmp_pagefault2(void *ctx) { return bpf_strcasecmp("HELLO", invalid_kern_ptr); }
SEC("syscall") __retval(-EFAULT) int test_strchr_pagefault(void *ctx) { return bpf_strchr(invalid_kern_ptr, 'a'); }
SEC("syscall") __retval(-EFAULT) int test_strchrnul_pagefault(void *ctx) { return bpf_strchrnul(invalid_kern_ptr, 'a'); }
SEC("syscall") __retval(-EFAULT) int test_strnchr_pagefault(void *ctx) { return bpf_strnchr(invalid_kern_ptr, 1, 'a'); }
diff --git a/tools/testing/selftests/bpf/progs/string_kfuncs_failure2.c b/tools/testing/selftests/bpf/progs/string_kfuncs_failure2.c
index 89fb4669b0e9..e41cc5601994 100644
--- a/tools/testing/selftests/bpf/progs/string_kfuncs_failure2.c
+++ b/tools/testing/selftests/bpf/progs/string_kfuncs_failure2.c
@@ -7,6 +7,7 @@
char long_str[XATTR_SIZE_MAX + 1];
SEC("syscall") int test_strcmp_too_long(void *ctx) { return bpf_strcmp(long_str, long_str); }
+SEC("syscall") int test_strcasecmp_too_long(void *ctx) { return bpf_strcasecmp(long_str, long_str); }
SEC("syscall") int test_strchr_too_long(void *ctx) { return bpf_strchr(long_str, 'b'); }
SEC("syscall") int test_strchrnul_too_long(void *ctx) { return bpf_strchrnul(long_str, 'b'); }
SEC("syscall") int test_strnchr_too_long(void *ctx) { return bpf_strnchr(long_str, sizeof(long_str), 'b'); }
diff --git a/tools/testing/selftests/bpf/progs/string_kfuncs_success.c b/tools/testing/selftests/bpf/progs/string_kfuncs_success.c
index 46697f381878..2e3498e37b9c 100644
--- a/tools/testing/selftests/bpf/progs/string_kfuncs_success.c
+++ b/tools/testing/selftests/bpf/progs/string_kfuncs_success.c
@@ -12,6 +12,11 @@ char str[] = "hello world";
/* Functional tests */
__test(0) int test_strcmp_eq(void *ctx) { return bpf_strcmp(str, "hello world"); }
__test(1) int test_strcmp_neq(void *ctx) { return bpf_strcmp(str, "hello"); }
+__test(0) int test_strcasecmp_eq1(void *ctx) { return bpf_strcasecmp(str, "hello world"); }
+__test(0) int test_strcasecmp_eq2(void *ctx) { return bpf_strcasecmp(str, "HELLO WORLD"); }
+__test(0) int test_strcasecmp_eq3(void *ctx) { return bpf_strcasecmp(str, "HELLO world"); }
+__test(1) int test_strcasecmp_neq1(void *ctx) { return bpf_strcasecmp(str, "hello"); }
+__test(1) int test_strcasecmp_neq2(void *ctx) { return bpf_strcasecmp(str, "HELLO"); }
__test(1) int test_strchr_found(void *ctx) { return bpf_strchr(str, 'e'); }
__test(11) int test_strchr_null(void *ctx) { return bpf_strchr(str, '\0'); }
__test(-ENOENT) int test_strchr_notfound(void *ctx) { return bpf_strchr(str, 'x'); }
@@ -30,8 +35,12 @@ __test(2) int test_strcspn(void *ctx) { return bpf_strcspn(str, "lo"); }
__test(6) int test_strstr_found(void *ctx) { return bpf_strstr(str, "world"); }
__test(-ENOENT) int test_strstr_notfound(void *ctx) { return bpf_strstr(str, "hi"); }
__test(0) int test_strstr_empty(void *ctx) { return bpf_strstr(str, ""); }
-__test(0) int test_strnstr_found(void *ctx) { return bpf_strnstr(str, "hello", 6); }
-__test(-ENOENT) int test_strnstr_notfound(void *ctx) { return bpf_strnstr(str, "hi", 10); }
+__test(0) int test_strnstr_found1(void *ctx) { return bpf_strnstr("", "", 0); }
+__test(0) int test_strnstr_found2(void *ctx) { return bpf_strnstr(str, "hello", 5); }
+__test(0) int test_strnstr_found3(void *ctx) { return bpf_strnstr(str, "hello", 6); }
+__test(-ENOENT) int test_strnstr_notfound1(void *ctx) { return bpf_strnstr(str, "hi", 10); }
+__test(-ENOENT) int test_strnstr_notfound2(void *ctx) { return bpf_strnstr(str, "hello", 4); }
+__test(-ENOENT) int test_strnstr_notfound3(void *ctx) { return bpf_strnstr("", "a", 0); }
__test(0) int test_strnstr_empty(void *ctx) { return bpf_strnstr(str, "", 1); }
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_id_ops_mapping1.c b/tools/testing/selftests/bpf/progs/struct_ops_id_ops_mapping1.c
new file mode 100644
index 000000000000..ad8bb546c9bf
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/struct_ops_id_ops_mapping1.c
@@ -0,0 +1,59 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+#include "../test_kmods/bpf_testmod.h"
+#include "../test_kmods/bpf_testmod_kfunc.h"
+
+char _license[] SEC("license") = "GPL";
+
+#define bpf_kfunc_multi_st_ops_test_1(args) bpf_kfunc_multi_st_ops_test_1(args, st_ops_id)
+int st_ops_id;
+
+int test_pid;
+int test_err;
+
+#define MAP1_MAGIC 1234
+
+SEC("struct_ops")
+int BPF_PROG(test_1, struct st_ops_args *args)
+{
+ return MAP1_MAGIC;
+}
+
+SEC("tp_btf/sys_enter")
+int BPF_PROG(sys_enter, struct pt_regs *regs, long id)
+{
+ struct st_ops_args args = {};
+ struct task_struct *task;
+ int ret;
+
+ task = bpf_get_current_task_btf();
+ if (!test_pid || task->pid != test_pid)
+ return 0;
+
+ ret = bpf_kfunc_multi_st_ops_test_1(&args);
+ if (ret != MAP1_MAGIC)
+ test_err++;
+
+ return 0;
+}
+
+SEC("syscall")
+int syscall_prog(void *ctx)
+{
+ struct st_ops_args args = {};
+ int ret;
+
+ ret = bpf_kfunc_multi_st_ops_test_1(&args);
+ if (ret != MAP1_MAGIC)
+ test_err++;
+
+ return 0;
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_multi_st_ops st_ops_map = {
+ .test_1 = (void *)test_1,
+};
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_id_ops_mapping2.c b/tools/testing/selftests/bpf/progs/struct_ops_id_ops_mapping2.c
new file mode 100644
index 000000000000..cea1a2f4b62f
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/struct_ops_id_ops_mapping2.c
@@ -0,0 +1,59 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+#include "../test_kmods/bpf_testmod.h"
+#include "../test_kmods/bpf_testmod_kfunc.h"
+
+char _license[] SEC("license") = "GPL";
+
+#define bpf_kfunc_multi_st_ops_test_1(args) bpf_kfunc_multi_st_ops_test_1(args, st_ops_id)
+int st_ops_id;
+
+int test_pid;
+int test_err;
+
+#define MAP2_MAGIC 4567
+
+SEC("struct_ops")
+int BPF_PROG(test_1, struct st_ops_args *args)
+{
+ return MAP2_MAGIC;
+}
+
+SEC("tp_btf/sys_enter")
+int BPF_PROG(sys_enter, struct pt_regs *regs, long id)
+{
+ struct st_ops_args args = {};
+ struct task_struct *task;
+ int ret;
+
+ task = bpf_get_current_task_btf();
+ if (!test_pid || task->pid != test_pid)
+ return 0;
+
+ ret = bpf_kfunc_multi_st_ops_test_1(&args);
+ if (ret != MAP2_MAGIC)
+ test_err++;
+
+ return 0;
+}
+
+SEC("syscall")
+int syscall_prog(void *ctx)
+{
+ struct st_ops_args args = {};
+ int ret;
+
+ ret = bpf_kfunc_multi_st_ops_test_1(&args);
+ if (ret != MAP2_MAGIC)
+ test_err++;
+
+ return 0;
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_multi_st_ops st_ops_map = {
+ .test_1 = (void *)test_1,
+};
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_kptr_return.c b/tools/testing/selftests/bpf/progs/struct_ops_kptr_return.c
index 36386b3c23a1..2b98b7710816 100644
--- a/tools/testing/selftests/bpf/progs/struct_ops_kptr_return.c
+++ b/tools/testing/selftests/bpf/progs/struct_ops_kptr_return.c
@@ -9,7 +9,7 @@ void bpf_task_release(struct task_struct *p) __ksym;
/* This test struct_ops BPF programs returning referenced kptr. The verifier should
* allow a referenced kptr or a NULL pointer to be returned. A referenced kptr to task
- * here is acquried automatically as the task argument is tagged with "__ref".
+ * here is acquired automatically as the task argument is tagged with "__ref".
*/
SEC("struct_ops/test_return_ref_kptr")
struct task_struct *BPF_PROG(kptr_return, int dummy,
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_refcounted.c b/tools/testing/selftests/bpf/progs/struct_ops_refcounted.c
index 76dcb6089d7f..9c0a65466356 100644
--- a/tools/testing/selftests/bpf/progs/struct_ops_refcounted.c
+++ b/tools/testing/selftests/bpf/progs/struct_ops_refcounted.c
@@ -9,7 +9,7 @@ __attribute__((nomerge)) extern void bpf_task_release(struct task_struct *p) __k
/* This is a test BPF program that uses struct_ops to access a referenced
* kptr argument. This is a test for the verifier to ensure that it
- * 1) recongnizes the task as a referenced object (i.e., ref_obj_id > 0), and
+ * 1) recognizes the task as a referenced object (i.e., ref_obj_id > 0), and
* 2) the same reference can be acquired from multiple paths as long as it
* has not been released.
*/
diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy1.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy1.c
index 327ca395e860..d556b19413d7 100644
--- a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy1.c
+++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy1.c
@@ -2,6 +2,7 @@
#include <linux/bpf.h>
#include <bpf/bpf_helpers.h>
#include "bpf_legacy.h"
+#include "bpf_test_utils.h"
struct {
__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
@@ -24,6 +25,8 @@ int entry(struct __sk_buff *skb)
{
int ret = 1;
+ clobber_regs_stack();
+
count++;
subprog_tail(skb);
subprog_tail(skb);
diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy2.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy2.c
index 72fd0d577506..ae94c9c70ab7 100644
--- a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy2.c
+++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy2.c
@@ -2,6 +2,7 @@
#include <linux/bpf.h>
#include <bpf/bpf_helpers.h>
#include "bpf_misc.h"
+#include "bpf_test_utils.h"
int classifier_0(struct __sk_buff *skb);
int classifier_1(struct __sk_buff *skb);
@@ -60,6 +61,8 @@ int tailcall_bpf2bpf_hierarchy_2(struct __sk_buff *skb)
{
int ret = 0;
+ clobber_regs_stack();
+
subprog_tail0(skb);
subprog_tail1(skb);
diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy3.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy3.c
index a7fb91cb05b7..56b6b0099840 100644
--- a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy3.c
+++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy3.c
@@ -2,6 +2,7 @@
#include <linux/bpf.h>
#include <bpf/bpf_helpers.h>
#include "bpf_misc.h"
+#include "bpf_test_utils.h"
int classifier_0(struct __sk_buff *skb);
@@ -53,6 +54,8 @@ int tailcall_bpf2bpf_hierarchy_3(struct __sk_buff *skb)
{
int ret = 0;
+ clobber_regs_stack();
+
bpf_tail_call_static(skb, &jmp_table0, 0);
__sink(ret);
diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy_fentry.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy_fentry.c
index c87f9ca982d3..5261395713cd 100644
--- a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy_fentry.c
+++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy_fentry.c
@@ -4,6 +4,7 @@
#include "vmlinux.h"
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_tracing.h>
+#include "bpf_test_utils.h"
struct {
__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
@@ -24,6 +25,8 @@ int subprog_tail(void *ctx)
SEC("fentry/dummy")
int BPF_PROG(fentry, struct sk_buff *skb)
{
+ clobber_regs_stack();
+
count++;
subprog_tail(ctx);
subprog_tail(ctx);
diff --git a/tools/testing/selftests/bpf/progs/task_local_data.bpf.h b/tools/testing/selftests/bpf/progs/task_local_data.bpf.h
new file mode 100644
index 000000000000..432fff2af844
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/task_local_data.bpf.h
@@ -0,0 +1,237 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __TASK_LOCAL_DATA_BPF_H
+#define __TASK_LOCAL_DATA_BPF_H
+
+/*
+ * Task local data is a library that facilitates sharing per-task data
+ * between user space and bpf programs.
+ *
+ *
+ * USAGE
+ *
+ * A TLD, an entry of data in task local data, first needs to be created by the
+ * user space. This is done by calling user space API, TLD_DEFINE_KEY() or
+ * tld_create_key(), with the name of the TLD and the size.
+ *
+ * TLD_DEFINE_KEY(prio, "priority", sizeof(int));
+ *
+ * or
+ *
+ * void func_call(...) {
+ * tld_key_t prio, in_cs;
+ *
+ * prio = tld_create_key("priority", sizeof(int));
+ * in_cs = tld_create_key("in_critical_section", sizeof(bool));
+ * ...
+ *
+ * A key associated with the TLD, which has an opaque type tld_key_t, will be
+ * initialized or returned. It can be used to get a pointer to the TLD in the
+ * user space by calling tld_get_data().
+ *
+ * In a bpf program, tld_object_init() first needs to be called to initialized a
+ * tld_object on the stack. Then, TLDs can be accessed by calling tld_get_data().
+ * The API will try to fetch the key by the name and use it to locate the data.
+ * A pointer to the TLD will be returned. It also caches the key in a task local
+ * storage map, tld_key_map, whose value type, struct tld_keys, must be defined
+ * by the developer.
+ *
+ * struct tld_keys {
+ * tld_key_t prio;
+ * tld_key_t in_cs;
+ * };
+ *
+ * SEC("struct_ops")
+ * void prog(struct task_struct task, ...)
+ * {
+ * struct tld_object tld_obj;
+ * int err, *p;
+ *
+ * err = tld_object_init(task, &tld_obj);
+ * if (err)
+ * return;
+ *
+ * p = tld_get_data(&tld_obj, prio, "priority", sizeof(int));
+ * if (p)
+ * // do something depending on *p
+ */
+#include <errno.h>
+#include <bpf/bpf_helpers.h>
+
+#define TLD_ROUND_MASK(x, y) ((__typeof__(x))((y) - 1))
+#define TLD_ROUND_UP(x, y) ((((x) - 1) | TLD_ROUND_MASK(x, y)) + 1)
+
+#define TLD_MAX_DATA_CNT (__PAGE_SIZE / sizeof(struct tld_metadata) - 1)
+
+#ifndef TLD_NAME_LEN
+#define TLD_NAME_LEN 62
+#endif
+
+#ifndef TLD_KEY_MAP_CREATE_RETRY
+#define TLD_KEY_MAP_CREATE_RETRY 10
+#endif
+
+typedef struct {
+ __s16 off;
+} tld_key_t;
+
+struct tld_metadata {
+ char name[TLD_NAME_LEN];
+ __u16 size;
+};
+
+struct tld_meta_u {
+ __u8 cnt;
+ __u16 size;
+ struct tld_metadata metadata[TLD_MAX_DATA_CNT];
+};
+
+struct tld_data_u {
+ __u64 start; /* offset of tld_data_u->data in a page */
+ char data[__PAGE_SIZE - sizeof(__u64)];
+};
+
+struct tld_map_value {
+ struct tld_data_u __uptr *data;
+ struct tld_meta_u __uptr *meta;
+};
+
+typedef struct tld_uptr_dummy {
+ struct tld_data_u data[0];
+ struct tld_meta_u meta[0];
+} *tld_uptr_dummy_t;
+
+struct tld_object {
+ struct tld_map_value *data_map;
+ struct tld_keys *key_map;
+ /*
+ * Force the compiler to generate the actual definition of tld_meta_u
+ * and tld_data_u in BTF. Without it, tld_meta_u and u_tld_data will
+ * be BTF_KIND_FWD.
+ */
+ tld_uptr_dummy_t dummy[0];
+};
+
+/*
+ * Map value of tld_key_map for caching keys. Must be defined by the developer.
+ * Members should be tld_key_t and passed to the 3rd argument of tld_fetch_key().
+ */
+struct tld_keys;
+
+struct {
+ __uint(type, BPF_MAP_TYPE_TASK_STORAGE);
+ __uint(map_flags, BPF_F_NO_PREALLOC);
+ __type(key, int);
+ __type(value, struct tld_map_value);
+} tld_data_map SEC(".maps");
+
+struct {
+ __uint(type, BPF_MAP_TYPE_TASK_STORAGE);
+ __uint(map_flags, BPF_F_NO_PREALLOC);
+ __type(key, int);
+ __type(value, struct tld_keys);
+} tld_key_map SEC(".maps");
+
+/**
+ * tld_object_init() - Initialize a tld_object.
+ *
+ * @task: The task_struct of the target task
+ * @tld_obj: A pointer to a tld_object to be initialized
+ *
+ * Return 0 on success; -ENODATA if the user space did not initialize task local data
+ * for the current task through tld_get_data(); -ENOMEM if the creation of tld_key_map
+ * fails
+ */
+__attribute__((unused))
+static int tld_object_init(struct task_struct *task, struct tld_object *tld_obj)
+{
+ int i;
+
+ tld_obj->data_map = bpf_task_storage_get(&tld_data_map, task, 0, 0);
+ if (!tld_obj->data_map)
+ return -ENODATA;
+
+ bpf_for(i, 0, TLD_KEY_MAP_CREATE_RETRY) {
+ tld_obj->key_map = bpf_task_storage_get(&tld_key_map, task, 0,
+ BPF_LOCAL_STORAGE_GET_F_CREATE);
+ if (likely(tld_obj->key_map))
+ break;
+ }
+ if (!tld_obj->key_map)
+ return -ENOMEM;
+
+ return 0;
+}
+
+/*
+ * Return the offset of TLD if @name is found. Otherwise, return the current TLD count
+ * using the nonpositive range so that the next tld_get_data() can skip fetching key if
+ * no new TLD is added or start comparing name from the first newly added TLD.
+ */
+__attribute__((unused))
+static int __tld_fetch_key(struct tld_object *tld_obj, const char *name, int i_start)
+{
+ struct tld_metadata *metadata;
+ int i, cnt, start, off = 0;
+
+ if (!tld_obj->data_map || !tld_obj->data_map->data || !tld_obj->data_map->meta)
+ return 0;
+
+ start = tld_obj->data_map->data->start;
+ cnt = tld_obj->data_map->meta->cnt;
+ metadata = tld_obj->data_map->meta->metadata;
+
+ bpf_for(i, 0, cnt) {
+ if (i >= TLD_MAX_DATA_CNT)
+ break;
+
+ if (i >= i_start && !bpf_strncmp(metadata[i].name, TLD_NAME_LEN, name))
+ return start + off;
+
+ off += TLD_ROUND_UP(metadata[i].size, 8);
+ }
+
+ return -cnt;
+}
+
+/**
+ * tld_get_data() - Retrieve a pointer to the TLD associated with the name.
+ *
+ * @tld_obj: A pointer to a valid tld_object initialized by tld_object_init()
+ * @key: The cached key of the TLD in tld_key_map
+ * @name: The name of the key associated with a TLD
+ * @size: The size of the TLD. Must be a known constant value
+ *
+ * Return a pointer to the TLD associated with @name; NULL if not found or @size is too
+ * big. @key is used to cache the key if the TLD is found to speed up subsequent calls.
+ * It should be defined as an member of tld_keys of tld_key_t type by the developer.
+ */
+#define tld_get_data(tld_obj, key, name, size) \
+ ({ \
+ void *data = NULL, *_data = (tld_obj)->data_map->data; \
+ long off = (tld_obj)->key_map->key.off; \
+ int cnt; \
+ \
+ if (likely(_data)) { \
+ if (likely(off > 0)) { \
+ barrier_var(off); \
+ if (likely(off < __PAGE_SIZE - size)) \
+ data = _data + off; \
+ } else { \
+ cnt = -(off); \
+ if (likely((tld_obj)->data_map->meta) && \
+ cnt < (tld_obj)->data_map->meta->cnt) { \
+ off = __tld_fetch_key(tld_obj, name, cnt); \
+ (tld_obj)->key_map->key.off = off; \
+ \
+ if (likely(off < __PAGE_SIZE - size)) { \
+ barrier_var(off); \
+ if (off > 0) \
+ data = _data + off; \
+ } \
+ } \
+ } \
+ } \
+ data; \
+ })
+
+#endif
diff --git a/tools/testing/selftests/bpf/progs/task_work.c b/tools/testing/selftests/bpf/progs/task_work.c
new file mode 100644
index 000000000000..23217f06a3ec
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/task_work.c
@@ -0,0 +1,107 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+
+#include <vmlinux.h>
+#include <string.h>
+#include <stdbool.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+#include "errno.h"
+
+char _license[] SEC("license") = "GPL";
+
+const void *user_ptr = NULL;
+
+struct elem {
+ char data[128];
+ struct bpf_task_work tw;
+};
+
+struct {
+ __uint(type, BPF_MAP_TYPE_HASH);
+ __uint(map_flags, BPF_F_NO_PREALLOC);
+ __uint(max_entries, 1);
+ __type(key, int);
+ __type(value, struct elem);
+} hmap SEC(".maps");
+
+struct {
+ __uint(type, BPF_MAP_TYPE_ARRAY);
+ __uint(max_entries, 1);
+ __type(key, int);
+ __type(value, struct elem);
+} arrmap SEC(".maps");
+
+struct {
+ __uint(type, BPF_MAP_TYPE_LRU_HASH);
+ __uint(max_entries, 1);
+ __type(key, int);
+ __type(value, struct elem);
+} lrumap SEC(".maps");
+
+static int process_work(struct bpf_map *map, void *key, void *value)
+{
+ struct elem *work = value;
+
+ bpf_copy_from_user_str(work->data, sizeof(work->data), (const void *)user_ptr, 0);
+ return 0;
+}
+
+int key = 0;
+
+SEC("perf_event")
+int oncpu_hash_map(struct pt_regs *args)
+{
+ struct elem empty_work = { .data = { 0 } };
+ struct elem *work;
+ struct task_struct *task;
+ int err;
+
+ task = bpf_get_current_task_btf();
+ err = bpf_map_update_elem(&hmap, &key, &empty_work, BPF_NOEXIST);
+ if (err)
+ return 0;
+ work = bpf_map_lookup_elem(&hmap, &key);
+ if (!work)
+ return 0;
+
+ bpf_task_work_schedule_resume(task, &work->tw, &hmap, process_work, NULL);
+ return 0;
+}
+
+SEC("perf_event")
+int oncpu_array_map(struct pt_regs *args)
+{
+ struct elem *work;
+ struct task_struct *task;
+
+ task = bpf_get_current_task_btf();
+ work = bpf_map_lookup_elem(&arrmap, &key);
+ if (!work)
+ return 0;
+ bpf_task_work_schedule_signal(task, &work->tw, &arrmap, process_work, NULL);
+ return 0;
+}
+
+SEC("perf_event")
+int oncpu_lru_map(struct pt_regs *args)
+{
+ struct elem empty_work = { .data = { 0 } };
+ struct elem *work;
+ struct task_struct *task;
+ int err;
+
+ task = bpf_get_current_task_btf();
+ work = bpf_map_lookup_elem(&lrumap, &key);
+ if (work)
+ return 0;
+ err = bpf_map_update_elem(&lrumap, &key, &empty_work, BPF_NOEXIST);
+ if (err)
+ return 0;
+ work = bpf_map_lookup_elem(&lrumap, &key);
+ if (!work || work->data[0])
+ return 0;
+ bpf_task_work_schedule_resume(task, &work->tw, &lrumap, process_work, NULL);
+ return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/task_work_fail.c b/tools/testing/selftests/bpf/progs/task_work_fail.c
new file mode 100644
index 000000000000..77fe8f28facd
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/task_work_fail.c
@@ -0,0 +1,96 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+
+#include <vmlinux.h>
+#include <string.h>
+#include <stdbool.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+const void *user_ptr = NULL;
+
+struct elem {
+ char data[128];
+ struct bpf_task_work tw;
+};
+
+struct {
+ __uint(type, BPF_MAP_TYPE_HASH);
+ __uint(map_flags, BPF_F_NO_PREALLOC);
+ __uint(max_entries, 1);
+ __type(key, int);
+ __type(value, struct elem);
+} hmap SEC(".maps");
+
+struct {
+ __uint(type, BPF_MAP_TYPE_ARRAY);
+ __uint(max_entries, 1);
+ __type(key, int);
+ __type(value, struct elem);
+} arrmap SEC(".maps");
+
+static int process_work(struct bpf_map *map, void *key, void *value)
+{
+ struct elem *work = value;
+
+ bpf_copy_from_user_str(work->data, sizeof(work->data), (const void *)user_ptr, 0);
+ return 0;
+}
+
+int key = 0;
+
+SEC("perf_event")
+__failure __msg("doesn't match map pointer in R3")
+int mismatch_map(struct pt_regs *args)
+{
+ struct elem *work;
+ struct task_struct *task;
+
+ task = bpf_get_current_task_btf();
+ work = bpf_map_lookup_elem(&arrmap, &key);
+ if (!work)
+ return 0;
+ bpf_task_work_schedule_resume(task, &work->tw, &hmap, process_work, NULL);
+ return 0;
+}
+
+SEC("perf_event")
+__failure __msg("arg#1 doesn't point to a map value")
+int no_map_task_work(struct pt_regs *args)
+{
+ struct task_struct *task;
+ struct bpf_task_work tw;
+
+ task = bpf_get_current_task_btf();
+ bpf_task_work_schedule_resume(task, &tw, &hmap, process_work, NULL);
+ return 0;
+}
+
+SEC("perf_event")
+__failure __msg("Possibly NULL pointer passed to trusted arg1")
+int task_work_null(struct pt_regs *args)
+{
+ struct task_struct *task;
+
+ task = bpf_get_current_task_btf();
+ bpf_task_work_schedule_resume(task, NULL, &hmap, process_work, NULL);
+ return 0;
+}
+
+SEC("perf_event")
+__failure __msg("Possibly NULL pointer passed to trusted arg2")
+int map_null(struct pt_regs *args)
+{
+ struct elem *work;
+ struct task_struct *task;
+
+ task = bpf_get_current_task_btf();
+ work = bpf_map_lookup_elem(&arrmap, &key);
+ if (!work)
+ return 0;
+ bpf_task_work_schedule_resume(task, &work->tw, NULL, process_work, NULL);
+ return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/task_work_stress.c b/tools/testing/selftests/bpf/progs/task_work_stress.c
new file mode 100644
index 000000000000..90fca06fff56
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/task_work_stress.c
@@ -0,0 +1,73 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+
+#include <vmlinux.h>
+#include <string.h>
+#include <stdbool.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+
+#define ENTRIES 128
+
+char _license[] SEC("license") = "GPL";
+
+__u64 callback_scheduled = 0;
+__u64 callback_success = 0;
+__u64 schedule_error = 0;
+__u64 delete_success = 0;
+
+struct elem {
+ __u32 count;
+ struct bpf_task_work tw;
+};
+
+struct {
+ __uint(type, BPF_MAP_TYPE_HASH);
+ __uint(map_flags, BPF_F_NO_PREALLOC);
+ __uint(max_entries, ENTRIES);
+ __type(key, int);
+ __type(value, struct elem);
+} hmap SEC(".maps");
+
+static int process_work(struct bpf_map *map, void *key, void *value)
+{
+ __sync_fetch_and_add(&callback_success, 1);
+ return 0;
+}
+
+SEC("syscall")
+int schedule_task_work(void *ctx)
+{
+ struct elem empty_work = {.count = 0};
+ struct elem *work;
+ int key = 0, err;
+
+ key = bpf_ktime_get_ns() % ENTRIES;
+ work = bpf_map_lookup_elem(&hmap, &key);
+ if (!work) {
+ bpf_map_update_elem(&hmap, &key, &empty_work, BPF_NOEXIST);
+ work = bpf_map_lookup_elem(&hmap, &key);
+ if (!work)
+ return 0;
+ }
+ err = bpf_task_work_schedule_signal(bpf_get_current_task_btf(), &work->tw, &hmap,
+ process_work, NULL);
+ if (err)
+ __sync_fetch_and_add(&schedule_error, 1);
+ else
+ __sync_fetch_and_add(&callback_scheduled, 1);
+ return 0;
+}
+
+SEC("syscall")
+int delete_task_work(void *ctx)
+{
+ int key = 0, err;
+
+ key = bpf_get_prandom_u32() % ENTRIES;
+ err = bpf_map_delete_elem(&hmap, &key);
+ if (!err)
+ __sync_fetch_and_add(&delete_success, 1);
+ return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_cls_redirect.c b/tools/testing/selftests/bpf/progs/test_cls_redirect.c
index f344c6835e84..26a53e54b8fa 100644
--- a/tools/testing/selftests/bpf/progs/test_cls_redirect.c
+++ b/tools/testing/selftests/bpf/progs/test_cls_redirect.c
@@ -22,6 +22,7 @@
#include "bpf_compiler.h"
#include "test_cls_redirect.h"
+#include "bpf_misc.h"
#pragma GCC diagnostic ignored "-Waddress-of-packed-member"
@@ -31,9 +32,6 @@
#define INLINING __always_inline
#endif
-#define offsetofend(TYPE, MEMBER) \
- (offsetof(TYPE, MEMBER) + sizeof((((TYPE *)0)->MEMBER)))
-
#define IP_OFFSET_MASK (0x1FFF)
#define IP_MF (0x2000)
@@ -129,7 +127,7 @@ typedef uint8_t *net_ptr __attribute__((align_value(8)));
typedef struct buf {
struct __sk_buff *skb;
net_ptr head;
- /* NB: tail musn't have alignment other than 1, otherwise
+ /* NB: tail mustn't have alignment other than 1, otherwise
* LLVM will go and eliminate code, e.g. when checking packet lengths.
*/
uint8_t *const tail;
diff --git a/tools/testing/selftests/bpf/progs/test_cls_redirect_dynptr.c b/tools/testing/selftests/bpf/progs/test_cls_redirect_dynptr.c
index d0f7670351e5..dfd4a2710391 100644
--- a/tools/testing/selftests/bpf/progs/test_cls_redirect_dynptr.c
+++ b/tools/testing/selftests/bpf/progs/test_cls_redirect_dynptr.c
@@ -494,7 +494,7 @@ static ret_t get_next_hop(struct bpf_dynptr *dynptr, __u64 *offset, encap_header
*offset += sizeof(*next_hop);
- /* Skip the remainig next hops (may be zero). */
+ /* Skip the remaining next hops (may be zero). */
return skip_next_hops(offset, encap->unigue.hop_count - encap->unigue.next_hop - 1);
}
diff --git a/tools/testing/selftests/bpf/progs/test_overhead.c b/tools/testing/selftests/bpf/progs/test_overhead.c
index abb7344b531f..5edf3cdc213d 100644
--- a/tools/testing/selftests/bpf/progs/test_overhead.c
+++ b/tools/testing/selftests/bpf/progs/test_overhead.c
@@ -1,9 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2019 Facebook */
-#include <stdbool.h>
-#include <stddef.h>
-#include <linux/bpf.h>
-#include <linux/ptrace.h>
+#include "vmlinux.h"
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_tracing.h>
diff --git a/tools/testing/selftests/bpf/progs/test_pinning_devmap.c b/tools/testing/selftests/bpf/progs/test_pinning_devmap.c
new file mode 100644
index 000000000000..c855f8f87eff
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_pinning_devmap.c
@@ -0,0 +1,20 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+struct {
+ __uint(type, BPF_MAP_TYPE_DEVMAP);
+ __uint(max_entries, 1);
+ __type(key, __u32);
+ __type(value, __u32);
+ __uint(pinning, LIBBPF_PIN_BY_NAME);
+} pinmap1 SEC(".maps");
+
+struct {
+ __uint(type, BPF_MAP_TYPE_DEVMAP);
+ __uint(max_entries, 2);
+ __type(key, __u32);
+ __type(value, __u32);
+ __uint(pinning, LIBBPF_PIN_BY_NAME);
+} pinmap2 SEC(".maps");
diff --git a/tools/testing/selftests/bpf/progs/test_task_local_data.c b/tools/testing/selftests/bpf/progs/test_task_local_data.c
new file mode 100644
index 000000000000..fffafc013044
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_task_local_data.c
@@ -0,0 +1,65 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <vmlinux.h>
+#include <errno.h>
+#include <bpf/bpf_helpers.h>
+
+#include "task_local_data.bpf.h"
+
+struct tld_keys {
+ tld_key_t value0;
+ tld_key_t value1;
+ tld_key_t value2;
+ tld_key_t value_not_exist;
+};
+
+struct test_tld_struct {
+ __u64 a;
+ __u64 b;
+ __u64 c;
+ __u64 d;
+};
+
+int test_value0;
+int test_value1;
+struct test_tld_struct test_value2;
+
+SEC("syscall")
+int task_main(void *ctx)
+{
+ struct tld_object tld_obj;
+ struct test_tld_struct *struct_p;
+ struct task_struct *task;
+ int err, *int_p;
+
+ task = bpf_get_current_task_btf();
+ err = tld_object_init(task, &tld_obj);
+ if (err)
+ return 1;
+
+ int_p = tld_get_data(&tld_obj, value0, "value0", sizeof(int));
+ if (int_p)
+ test_value0 = *int_p;
+ else
+ return 2;
+
+ int_p = tld_get_data(&tld_obj, value1, "value1", sizeof(int));
+ if (int_p)
+ test_value1 = *int_p;
+ else
+ return 3;
+
+ struct_p = tld_get_data(&tld_obj, value2, "value2", sizeof(struct test_tld_struct));
+ if (struct_p)
+ test_value2 = *struct_p;
+ else
+ return 4;
+
+ int_p = tld_get_data(&tld_obj, value_not_exist, "value_not_exist", sizeof(int));
+ if (int_p)
+ return 5;
+
+ return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_tcp_hdr_options.c b/tools/testing/selftests/bpf/progs/test_tcp_hdr_options.c
index 5f4e87ee949a..1ecdf4c54de4 100644
--- a/tools/testing/selftests/bpf/progs/test_tcp_hdr_options.c
+++ b/tools/testing/selftests/bpf/progs/test_tcp_hdr_options.c
@@ -14,10 +14,7 @@
#include <bpf/bpf_endian.h>
#define BPF_PROG_TEST_TCP_HDR_OPTIONS
#include "test_tcp_hdr_options.h"
-
-#ifndef sizeof_field
-#define sizeof_field(TYPE, MEMBER) sizeof((((TYPE *)0)->MEMBER))
-#endif
+#include "bpf_misc.h"
__u8 test_kind = TCPOPT_EXP;
__u16 test_magic = 0xeB9F;
diff --git a/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c b/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c
index 540181c115a8..ef00d38b0a8d 100644
--- a/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c
@@ -23,7 +23,6 @@ struct {
struct {
__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
- __uint(max_entries, 2);
__type(key, int);
__type(value, __u32);
} perf_event_map SEC(".maps");
diff --git a/tools/testing/selftests/bpf/progs/test_uprobe.c b/tools/testing/selftests/bpf/progs/test_uprobe.c
index 896c88a4960d..12f4065fca20 100644
--- a/tools/testing/selftests/bpf/progs/test_uprobe.c
+++ b/tools/testing/selftests/bpf/progs/test_uprobe.c
@@ -59,3 +59,41 @@ int BPF_UPROBE(test4)
test4_result = 1;
return 0;
}
+
+#if defined(__TARGET_ARCH_x86)
+struct pt_regs regs;
+
+SEC("uprobe")
+int BPF_UPROBE(test_regs_change)
+{
+ pid_t pid = bpf_get_current_pid_tgid() >> 32;
+
+ if (pid != my_pid)
+ return 0;
+
+ ctx->ax = regs.ax;
+ ctx->cx = regs.cx;
+ ctx->dx = regs.dx;
+ ctx->r8 = regs.r8;
+ ctx->r9 = regs.r9;
+ ctx->r10 = regs.r10;
+ ctx->r11 = regs.r11;
+ ctx->di = regs.di;
+ ctx->si = regs.si;
+ return 0;
+}
+
+unsigned long ip;
+
+SEC("uprobe")
+int BPF_UPROBE(test_regs_change_ip)
+{
+ pid_t pid = bpf_get_current_pid_tgid() >> 32;
+
+ if (pid != my_pid)
+ return 0;
+
+ ctx->ip = ip;
+ return 0;
+}
+#endif
diff --git a/tools/testing/selftests/bpf/progs/test_usdt.c b/tools/testing/selftests/bpf/progs/test_usdt.c
index 096488f47fbc..a78c87537b07 100644
--- a/tools/testing/selftests/bpf/progs/test_usdt.c
+++ b/tools/testing/selftests/bpf/progs/test_usdt.c
@@ -107,4 +107,35 @@ int BPF_USDT(usdt12, int a1, int a2, long a3, long a4, unsigned a5,
return 0;
}
+int usdt_sib_called;
+u64 usdt_sib_cookie;
+int usdt_sib_arg_cnt;
+int usdt_sib_arg_ret;
+short usdt_sib_arg;
+int usdt_sib_arg_size;
+
+/*
+ * usdt_sib is only tested on x86-related architectures, so it requires
+ * manual attach since auto-attach will panic tests under other architectures
+ */
+SEC("usdt")
+int usdt_sib(struct pt_regs *ctx)
+{
+ long tmp;
+
+ if (my_pid != (bpf_get_current_pid_tgid() >> 32))
+ return 0;
+
+ __sync_fetch_and_add(&usdt_sib_called, 1);
+
+ usdt_sib_cookie = bpf_usdt_cookie(ctx);
+ usdt_sib_arg_cnt = bpf_usdt_arg_cnt(ctx);
+
+ usdt_sib_arg_ret = bpf_usdt_arg(ctx, 0, &tmp);
+ usdt_sib_arg = (short)tmp;
+ usdt_sib_arg_size = bpf_usdt_arg_size(ctx, 0);
+
+ return 0;
+}
+
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_devmap_tailcall.c b/tools/testing/selftests/bpf/progs/test_xdp_devmap_tailcall.c
new file mode 100644
index 000000000000..814e2a980e97
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_xdp_devmap_tailcall.c
@@ -0,0 +1,29 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+SEC("xdp")
+int xdp_devmap(struct xdp_md *ctx)
+{
+ return ctx->egress_ifindex;
+}
+
+struct {
+ __uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+ __uint(max_entries, 1);
+ __uint(key_size, sizeof(__u32));
+ __array(values, int (void *));
+} xdp_map SEC(".maps") = {
+ .values = {
+ [0] = (void *)&xdp_devmap,
+ },
+};
+
+SEC("xdp")
+int xdp_entry(struct xdp_md *ctx)
+{
+ bpf_tail_call(ctx, &xdp_map, 0);
+ return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_meta.c b/tools/testing/selftests/bpf/progs/test_xdp_meta.c
index fcf6ca14f2ea..d79cb74b571e 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp_meta.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_meta.c
@@ -1,8 +1,11 @@
+#include <stdbool.h>
#include <linux/bpf.h>
+#include <linux/errno.h>
#include <linux/if_ether.h>
#include <linux/pkt_cls.h>
#include <bpf/bpf_helpers.h>
+#include "bpf_kfuncs.h"
#define META_SIZE 32
@@ -23,6 +26,8 @@ struct {
__uint(value_size, META_SIZE);
} test_result SEC(".maps");
+bool test_pass;
+
SEC("tc")
int ing_cls(struct __sk_buff *ctx)
{
@@ -40,6 +45,231 @@ int ing_cls(struct __sk_buff *ctx)
return TC_ACT_SHOT;
}
+/* Read from metadata using bpf_dynptr_read helper */
+SEC("tc")
+int ing_cls_dynptr_read(struct __sk_buff *ctx)
+{
+ struct bpf_dynptr meta;
+ const __u32 zero = 0;
+ __u8 *dst;
+
+ dst = bpf_map_lookup_elem(&test_result, &zero);
+ if (!dst)
+ return TC_ACT_SHOT;
+
+ bpf_dynptr_from_skb_meta(ctx, 0, &meta);
+ bpf_dynptr_read(dst, META_SIZE, &meta, 0, 0);
+
+ return TC_ACT_SHOT;
+}
+
+/* Write to metadata using bpf_dynptr_write helper */
+SEC("tc")
+int ing_cls_dynptr_write(struct __sk_buff *ctx)
+{
+ struct bpf_dynptr data, meta;
+ __u8 *src;
+
+ bpf_dynptr_from_skb(ctx, 0, &data);
+ src = bpf_dynptr_slice(&data, sizeof(struct ethhdr), NULL, META_SIZE);
+ if (!src)
+ return TC_ACT_SHOT;
+
+ bpf_dynptr_from_skb_meta(ctx, 0, &meta);
+ bpf_dynptr_write(&meta, 0, src, META_SIZE, 0);
+
+ return TC_ACT_UNSPEC; /* pass */
+}
+
+/* Read from metadata using read-only dynptr slice */
+SEC("tc")
+int ing_cls_dynptr_slice(struct __sk_buff *ctx)
+{
+ struct bpf_dynptr meta;
+ const __u32 zero = 0;
+ __u8 *dst, *src;
+
+ dst = bpf_map_lookup_elem(&test_result, &zero);
+ if (!dst)
+ return TC_ACT_SHOT;
+
+ bpf_dynptr_from_skb_meta(ctx, 0, &meta);
+ src = bpf_dynptr_slice(&meta, 0, NULL, META_SIZE);
+ if (!src)
+ return TC_ACT_SHOT;
+
+ __builtin_memcpy(dst, src, META_SIZE);
+
+ return TC_ACT_SHOT;
+}
+
+/* Write to metadata using writeable dynptr slice */
+SEC("tc")
+int ing_cls_dynptr_slice_rdwr(struct __sk_buff *ctx)
+{
+ struct bpf_dynptr data, meta;
+ __u8 *src, *dst;
+
+ bpf_dynptr_from_skb(ctx, 0, &data);
+ src = bpf_dynptr_slice(&data, sizeof(struct ethhdr), NULL, META_SIZE);
+ if (!src)
+ return TC_ACT_SHOT;
+
+ bpf_dynptr_from_skb_meta(ctx, 0, &meta);
+ dst = bpf_dynptr_slice_rdwr(&meta, 0, NULL, META_SIZE);
+ if (!dst)
+ return TC_ACT_SHOT;
+
+ __builtin_memcpy(dst, src, META_SIZE);
+
+ return TC_ACT_UNSPEC; /* pass */
+}
+
+/* Read skb metadata in chunks from various offsets in different ways. */
+SEC("tc")
+int ing_cls_dynptr_offset_rd(struct __sk_buff *ctx)
+{
+ struct bpf_dynptr meta;
+ const __u32 chunk_len = META_SIZE / 4;
+ const __u32 zero = 0;
+ __u8 *dst, *src;
+
+ dst = bpf_map_lookup_elem(&test_result, &zero);
+ if (!dst)
+ return TC_ACT_SHOT;
+
+ /* 1. Regular read */
+ bpf_dynptr_from_skb_meta(ctx, 0, &meta);
+ bpf_dynptr_read(dst, chunk_len, &meta, 0, 0);
+ dst += chunk_len;
+
+ /* 2. Read from an offset-adjusted dynptr */
+ bpf_dynptr_adjust(&meta, chunk_len, bpf_dynptr_size(&meta));
+ bpf_dynptr_read(dst, chunk_len, &meta, 0, 0);
+ dst += chunk_len;
+
+ /* 3. Read at an offset */
+ bpf_dynptr_read(dst, chunk_len, &meta, chunk_len, 0);
+ dst += chunk_len;
+
+ /* 4. Read from a slice starting at an offset */
+ src = bpf_dynptr_slice(&meta, 2 * chunk_len, NULL, chunk_len);
+ if (!src)
+ return TC_ACT_SHOT;
+ __builtin_memcpy(dst, src, chunk_len);
+
+ return TC_ACT_SHOT;
+}
+
+/* Write skb metadata in chunks at various offsets in different ways. */
+SEC("tc")
+int ing_cls_dynptr_offset_wr(struct __sk_buff *ctx)
+{
+ const __u32 chunk_len = META_SIZE / 4;
+ __u8 payload[META_SIZE];
+ struct bpf_dynptr meta;
+ __u8 *dst, *src;
+
+ bpf_skb_load_bytes(ctx, sizeof(struct ethhdr), payload, sizeof(payload));
+ src = payload;
+
+ /* 1. Regular write */
+ bpf_dynptr_from_skb_meta(ctx, 0, &meta);
+ bpf_dynptr_write(&meta, 0, src, chunk_len, 0);
+ src += chunk_len;
+
+ /* 2. Write to an offset-adjusted dynptr */
+ bpf_dynptr_adjust(&meta, chunk_len, bpf_dynptr_size(&meta));
+ bpf_dynptr_write(&meta, 0, src, chunk_len, 0);
+ src += chunk_len;
+
+ /* 3. Write at an offset */
+ bpf_dynptr_write(&meta, chunk_len, src, chunk_len, 0);
+ src += chunk_len;
+
+ /* 4. Write to a slice starting at an offset */
+ dst = bpf_dynptr_slice_rdwr(&meta, 2 * chunk_len, NULL, chunk_len);
+ if (!dst)
+ return TC_ACT_SHOT;
+ __builtin_memcpy(dst, src, chunk_len);
+
+ return TC_ACT_UNSPEC; /* pass */
+}
+
+/* Pass an OOB offset to dynptr read, write, adjust, slice. */
+SEC("tc")
+int ing_cls_dynptr_offset_oob(struct __sk_buff *ctx)
+{
+ struct bpf_dynptr meta;
+ __u8 md, *p;
+ int err;
+
+ err = bpf_dynptr_from_skb_meta(ctx, 0, &meta);
+ if (err)
+ goto fail;
+
+ /* read offset OOB */
+ err = bpf_dynptr_read(&md, sizeof(md), &meta, META_SIZE, 0);
+ if (err != -E2BIG)
+ goto fail;
+
+ /* write offset OOB */
+ err = bpf_dynptr_write(&meta, META_SIZE, &md, sizeof(md), 0);
+ if (err != -E2BIG)
+ goto fail;
+
+ /* adjust end offset OOB */
+ err = bpf_dynptr_adjust(&meta, 0, META_SIZE + 1);
+ if (err != -ERANGE)
+ goto fail;
+
+ /* adjust start offset OOB */
+ err = bpf_dynptr_adjust(&meta, META_SIZE + 1, META_SIZE + 1);
+ if (err != -ERANGE)
+ goto fail;
+
+ /* slice offset OOB */
+ p = bpf_dynptr_slice(&meta, META_SIZE, NULL, sizeof(*p));
+ if (p)
+ goto fail;
+
+ /* slice rdwr offset OOB */
+ p = bpf_dynptr_slice_rdwr(&meta, META_SIZE, NULL, sizeof(*p));
+ if (p)
+ goto fail;
+
+ return TC_ACT_UNSPEC;
+fail:
+ return TC_ACT_SHOT;
+}
+
+/* Reserve and clear space for metadata but don't populate it */
+SEC("xdp")
+int ing_xdp_zalloc_meta(struct xdp_md *ctx)
+{
+ struct ethhdr *eth = ctx_ptr(ctx, data);
+ __u8 *meta;
+ int ret;
+
+ /* Drop any non-test packets */
+ if (eth + 1 > ctx_ptr(ctx, data_end))
+ return XDP_DROP;
+ if (eth->h_proto != 0)
+ return XDP_DROP;
+
+ ret = bpf_xdp_adjust_meta(ctx, -META_SIZE);
+ if (ret < 0)
+ return XDP_DROP;
+
+ meta = ctx_ptr(ctx, data_meta);
+ if (meta + META_SIZE > ctx_ptr(ctx, data))
+ return XDP_DROP;
+
+ __builtin_memset(meta, 0, META_SIZE);
+
+ return XDP_PASS;
+}
+
SEC("xdp")
int ing_xdp(struct xdp_md *ctx)
{
@@ -73,4 +303,193 @@ int ing_xdp(struct xdp_md *ctx)
return XDP_PASS;
}
+/*
+ * Check that skb->data_meta..skb->data is empty if prog writes to packet
+ * _payload_ using packet pointers. Applies only to cloned skbs.
+ */
+SEC("tc")
+int clone_data_meta_empty_on_data_write(struct __sk_buff *ctx)
+{
+ struct ethhdr *eth = ctx_ptr(ctx, data);
+
+ if (eth + 1 > ctx_ptr(ctx, data_end))
+ goto out;
+ /* Ignore non-test packets */
+ if (eth->h_proto != 0)
+ goto out;
+
+ /* Expect no metadata */
+ if (ctx->data_meta != ctx->data)
+ goto out;
+
+ /* Packet write to trigger unclone in prologue */
+ eth->h_proto = 42;
+
+ test_pass = true;
+out:
+ return TC_ACT_SHOT;
+}
+
+/*
+ * Check that skb->data_meta..skb->data is empty if prog writes to packet
+ * _metadata_ using packet pointers. Applies only to cloned skbs.
+ */
+SEC("tc")
+int clone_data_meta_empty_on_meta_write(struct __sk_buff *ctx)
+{
+ struct ethhdr *eth = ctx_ptr(ctx, data);
+ __u8 *md = ctx_ptr(ctx, data_meta);
+
+ if (eth + 1 > ctx_ptr(ctx, data_end))
+ goto out;
+ /* Ignore non-test packets */
+ if (eth->h_proto != 0)
+ goto out;
+
+ if (md + 1 > ctx_ptr(ctx, data)) {
+ /* Expect no metadata */
+ test_pass = true;
+ } else {
+ /* Metadata write to trigger unclone in prologue */
+ *md = 42;
+ }
+out:
+ return TC_ACT_SHOT;
+}
+
+/*
+ * Check that skb_meta dynptr is writable but empty if prog writes to packet
+ * _payload_ using a dynptr slice. Applies only to cloned skbs.
+ */
+SEC("tc")
+int clone_dynptr_empty_on_data_slice_write(struct __sk_buff *ctx)
+{
+ struct bpf_dynptr data, meta;
+ struct ethhdr *eth;
+
+ bpf_dynptr_from_skb(ctx, 0, &data);
+ eth = bpf_dynptr_slice_rdwr(&data, 0, NULL, sizeof(*eth));
+ if (!eth)
+ goto out;
+ /* Ignore non-test packets */
+ if (eth->h_proto != 0)
+ goto out;
+
+ /* Expect no metadata */
+ bpf_dynptr_from_skb_meta(ctx, 0, &meta);
+ if (bpf_dynptr_is_rdonly(&meta) || bpf_dynptr_size(&meta) > 0)
+ goto out;
+
+ /* Packet write to trigger unclone in prologue */
+ eth->h_proto = 42;
+
+ test_pass = true;
+out:
+ return TC_ACT_SHOT;
+}
+
+/*
+ * Check that skb_meta dynptr is writable but empty if prog writes to packet
+ * _metadata_ using a dynptr slice. Applies only to cloned skbs.
+ */
+SEC("tc")
+int clone_dynptr_empty_on_meta_slice_write(struct __sk_buff *ctx)
+{
+ struct bpf_dynptr data, meta;
+ const struct ethhdr *eth;
+ __u8 *md;
+
+ bpf_dynptr_from_skb(ctx, 0, &data);
+ eth = bpf_dynptr_slice(&data, 0, NULL, sizeof(*eth));
+ if (!eth)
+ goto out;
+ /* Ignore non-test packets */
+ if (eth->h_proto != 0)
+ goto out;
+
+ /* Expect no metadata */
+ bpf_dynptr_from_skb_meta(ctx, 0, &meta);
+ if (bpf_dynptr_is_rdonly(&meta) || bpf_dynptr_size(&meta) > 0)
+ goto out;
+
+ /* Metadata write to trigger unclone in prologue */
+ bpf_dynptr_from_skb_meta(ctx, 0, &meta);
+ md = bpf_dynptr_slice_rdwr(&meta, 0, NULL, sizeof(*md));
+ if (md)
+ *md = 42;
+
+ test_pass = true;
+out:
+ return TC_ACT_SHOT;
+}
+
+/*
+ * Check that skb_meta dynptr is read-only before prog writes to packet payload
+ * using dynptr_write helper. Applies only to cloned skbs.
+ */
+SEC("tc")
+int clone_dynptr_rdonly_before_data_dynptr_write(struct __sk_buff *ctx)
+{
+ struct bpf_dynptr data, meta;
+ const struct ethhdr *eth;
+
+ bpf_dynptr_from_skb(ctx, 0, &data);
+ eth = bpf_dynptr_slice(&data, 0, NULL, sizeof(*eth));
+ if (!eth)
+ goto out;
+ /* Ignore non-test packets */
+ if (eth->h_proto != 0)
+ goto out;
+
+ /* Expect read-only metadata before unclone */
+ bpf_dynptr_from_skb_meta(ctx, 0, &meta);
+ if (!bpf_dynptr_is_rdonly(&meta) || bpf_dynptr_size(&meta) != META_SIZE)
+ goto out;
+
+ /* Helper write to payload will unclone the packet */
+ bpf_dynptr_write(&data, offsetof(struct ethhdr, h_proto), "x", 1, 0);
+
+ /* Expect no metadata after unclone */
+ bpf_dynptr_from_skb_meta(ctx, 0, &meta);
+ if (bpf_dynptr_is_rdonly(&meta) || bpf_dynptr_size(&meta) != 0)
+ goto out;
+
+ test_pass = true;
+out:
+ return TC_ACT_SHOT;
+}
+
+/*
+ * Check that skb_meta dynptr is read-only if prog writes to packet
+ * metadata using dynptr_write helper. Applies only to cloned skbs.
+ */
+SEC("tc")
+int clone_dynptr_rdonly_before_meta_dynptr_write(struct __sk_buff *ctx)
+{
+ struct bpf_dynptr data, meta;
+ const struct ethhdr *eth;
+
+ bpf_dynptr_from_skb(ctx, 0, &data);
+ eth = bpf_dynptr_slice(&data, 0, NULL, sizeof(*eth));
+ if (!eth)
+ goto out;
+ /* Ignore non-test packets */
+ if (eth->h_proto != 0)
+ goto out;
+
+ /* Expect read-only metadata */
+ bpf_dynptr_from_skb_meta(ctx, 0, &meta);
+ if (!bpf_dynptr_is_rdonly(&meta) || bpf_dynptr_size(&meta) != META_SIZE)
+ goto out;
+
+ /* Metadata write. Expect failure. */
+ bpf_dynptr_from_skb_meta(ctx, 0, &meta);
+ if (bpf_dynptr_write(&meta, 0, "x", 1, 0) != -EINVAL)
+ goto out;
+
+ test_pass = true;
+out:
+ return TC_ACT_SHOT;
+}
+
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_pull_data.c b/tools/testing/selftests/bpf/progs/test_xdp_pull_data.c
new file mode 100644
index 000000000000..c41a21413eaa
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_xdp_pull_data.c
@@ -0,0 +1,48 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+
+int xdpf_sz;
+int sinfo_sz;
+int data_len;
+int pull_len;
+
+#define XDP_PACKET_HEADROOM 256
+
+SEC("xdp.frags")
+int xdp_find_sizes(struct xdp_md *ctx)
+{
+ xdpf_sz = sizeof(struct xdp_frame);
+ sinfo_sz = __PAGE_SIZE - XDP_PACKET_HEADROOM -
+ (ctx->data_end - ctx->data);
+
+ return XDP_PASS;
+}
+
+SEC("xdp.frags")
+int xdp_pull_data_prog(struct xdp_md *ctx)
+{
+ __u8 *data_end = (void *)(long)ctx->data_end;
+ __u8 *data = (void *)(long)ctx->data;
+ __u8 *val_p;
+ int err;
+
+ if (data_len != data_end - data)
+ return XDP_DROP;
+
+ err = bpf_xdp_pull_data(ctx, pull_len);
+ if (err)
+ return XDP_DROP;
+
+ val_p = (void *)(long)ctx->data + 1024;
+ if (val_p + 1 > (void *)(long)ctx->data_end)
+ return XDP_DROP;
+
+ if (*val_p != 0xbb)
+ return XDP_DROP;
+
+ return XDP_PASS;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/timer_interrupt.c b/tools/testing/selftests/bpf/progs/timer_interrupt.c
new file mode 100644
index 000000000000..19180a455f40
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/timer_interrupt.c
@@ -0,0 +1,48 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_experimental.h"
+
+char _license[] SEC("license") = "GPL";
+
+#define CLOCK_MONOTONIC 1
+
+int preempt_count;
+int in_interrupt;
+int in_interrupt_cb;
+
+struct elem {
+ struct bpf_timer t;
+};
+
+struct {
+ __uint(type, BPF_MAP_TYPE_ARRAY);
+ __uint(max_entries, 1);
+ __type(key, int);
+ __type(value, struct elem);
+} array SEC(".maps");
+
+static int timer_in_interrupt(void *map, int *key, struct bpf_timer *timer)
+{
+ preempt_count = get_preempt_count();
+ in_interrupt_cb = bpf_in_interrupt();
+ return 0;
+}
+
+SEC("fentry/bpf_fentry_test1")
+int BPF_PROG(test_timer_interrupt)
+{
+ struct bpf_timer *timer;
+ int key = 0;
+
+ timer = bpf_map_lookup_elem(&array, &key);
+ if (!timer)
+ return 0;
+
+ in_interrupt = bpf_in_interrupt();
+ bpf_timer_init(timer, &array, CLOCK_MONOTONIC);
+ bpf_timer_set_callback(timer, timer_in_interrupt);
+ bpf_timer_start(timer, 0, 0);
+ return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/tracing_struct.c b/tools/testing/selftests/bpf/progs/tracing_struct.c
index c435a3a8328a..d460732e2023 100644
--- a/tools/testing/selftests/bpf/progs/tracing_struct.c
+++ b/tools/testing/selftests/bpf/progs/tracing_struct.c
@@ -18,6 +18,18 @@ struct bpf_testmod_struct_arg_3 {
int b[];
};
+union bpf_testmod_union_arg_1 {
+ char a;
+ short b;
+ struct bpf_testmod_struct_arg_1 arg;
+};
+
+union bpf_testmod_union_arg_2 {
+ int a;
+ long b;
+ struct bpf_testmod_struct_arg_2 arg;
+};
+
long t1_a_a, t1_a_b, t1_b, t1_c, t1_ret, t1_nregs;
__u64 t1_reg0, t1_reg1, t1_reg2, t1_reg3;
long t2_a, t2_b_a, t2_b_b, t2_c, t2_ret;
@@ -26,6 +38,9 @@ long t4_a_a, t4_b, t4_c, t4_d, t4_e_a, t4_e_b, t4_ret;
long t5_ret;
int t6;
+long ut1_a_a, ut1_b, ut1_c;
+long ut2_a, ut2_b_a, ut2_b_b;
+
SEC("fentry/bpf_testmod_test_struct_arg_1")
int BPF_PROG2(test_struct_arg_1, struct bpf_testmod_struct_arg_2, a, int, b, int, c)
{
@@ -130,4 +145,22 @@ int BPF_PROG2(test_struct_arg_11, struct bpf_testmod_struct_arg_3 *, a)
return 0;
}
+SEC("fexit/bpf_testmod_test_union_arg_1")
+int BPF_PROG2(test_union_arg_1, union bpf_testmod_union_arg_1, a, int, b, int, c)
+{
+ ut1_a_a = a.arg.a;
+ ut1_b = b;
+ ut1_c = c;
+ return 0;
+}
+
+SEC("fexit/bpf_testmod_test_union_arg_2")
+int BPF_PROG2(test_union_arg_2, int, a, union bpf_testmod_union_arg_2, b)
+{
+ ut2_a = a;
+ ut2_b_a = b.arg.a;
+ ut2_b_b = b.arg.b;
+ return 0;
+}
+
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/trigger_bench.c b/tools/testing/selftests/bpf/progs/trigger_bench.c
index 044a6d78923e..3d5f30c29ae3 100644
--- a/tools/testing/selftests/bpf/progs/trigger_bench.c
+++ b/tools/testing/selftests/bpf/progs/trigger_bench.c
@@ -97,6 +97,12 @@ int bench_trigger_kprobe_multi(void *ctx)
return 0;
}
+SEC("?kprobe.multi/bpf_get_numa_node_id")
+int bench_kprobe_multi_empty(void *ctx)
+{
+ return 0;
+}
+
SEC("?kretprobe.multi/bpf_get_numa_node_id")
int bench_trigger_kretprobe_multi(void *ctx)
{
@@ -104,6 +110,12 @@ int bench_trigger_kretprobe_multi(void *ctx)
return 0;
}
+SEC("?kretprobe.multi/bpf_get_numa_node_id")
+int bench_kretprobe_multi_empty(void *ctx)
+{
+ return 0;
+}
+
SEC("?fentry/bpf_get_numa_node_id")
int bench_trigger_fentry(void *ctx)
{
diff --git a/tools/testing/selftests/bpf/progs/uprobe_syscall.c b/tools/testing/selftests/bpf/progs/uprobe_syscall.c
index 8a4fa6c7ef59..e08c31669e5a 100644
--- a/tools/testing/selftests/bpf/progs/uprobe_syscall.c
+++ b/tools/testing/selftests/bpf/progs/uprobe_syscall.c
@@ -7,8 +7,8 @@ struct pt_regs regs;
char _license[] SEC("license") = "GPL";
-SEC("uretprobe//proc/self/exe:uretprobe_regs_trigger")
-int uretprobe(struct pt_regs *ctx)
+SEC("uprobe")
+int probe(struct pt_regs *ctx)
{
__builtin_memcpy(&regs, ctx, sizeof(regs));
return 0;
diff --git a/tools/testing/selftests/bpf/progs/uprobe_syscall_executed.c b/tools/testing/selftests/bpf/progs/uprobe_syscall_executed.c
index 0d7f1a7db2e2..915d38591bf6 100644
--- a/tools/testing/selftests/bpf/progs/uprobe_syscall_executed.c
+++ b/tools/testing/selftests/bpf/progs/uprobe_syscall_executed.c
@@ -1,6 +1,8 @@
// SPDX-License-Identifier: GPL-2.0
#include "vmlinux.h"
#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/usdt.bpf.h>
#include <string.h>
struct pt_regs regs;
@@ -8,10 +10,64 @@ struct pt_regs regs;
char _license[] SEC("license") = "GPL";
int executed = 0;
+int pid;
+
+SEC("uprobe")
+int BPF_UPROBE(test_uprobe)
+{
+ if (bpf_get_current_pid_tgid() >> 32 != pid)
+ return 0;
+
+ executed++;
+ return 0;
+}
+
+SEC("uretprobe")
+int BPF_URETPROBE(test_uretprobe)
+{
+ if (bpf_get_current_pid_tgid() >> 32 != pid)
+ return 0;
+
+ executed++;
+ return 0;
+}
+
+SEC("uprobe.multi")
+int test_uprobe_multi(struct pt_regs *ctx)
+{
+ if (bpf_get_current_pid_tgid() >> 32 != pid)
+ return 0;
+
+ executed++;
+ return 0;
+}
SEC("uretprobe.multi")
-int test(struct pt_regs *regs)
+int test_uretprobe_multi(struct pt_regs *ctx)
+{
+ if (bpf_get_current_pid_tgid() >> 32 != pid)
+ return 0;
+
+ executed++;
+ return 0;
+}
+
+SEC("uprobe.session")
+int test_uprobe_session(struct pt_regs *ctx)
{
- executed = 1;
+ if (bpf_get_current_pid_tgid() >> 32 != pid)
+ return 0;
+
+ executed++;
+ return 0;
+}
+
+SEC("usdt")
+int test_usdt(struct pt_regs *ctx)
+{
+ if (bpf_get_current_pid_tgid() >> 32 != pid)
+ return 0;
+
+ executed++;
return 0;
}
diff --git a/tools/testing/selftests/bpf/progs/uretprobe_stack.c b/tools/testing/selftests/bpf/progs/uretprobe_stack.c
index 9fdcf396b8f4..a2951e2f1711 100644
--- a/tools/testing/selftests/bpf/progs/uretprobe_stack.c
+++ b/tools/testing/selftests/bpf/progs/uretprobe_stack.c
@@ -26,8 +26,8 @@ int usdt_len;
SEC("uprobe//proc/self/exe:target_1")
int BPF_UPROBE(uprobe_1)
{
- /* target_1 is recursive wit depth of 2, so we capture two separate
- * stack traces, depending on which occurence it is
+ /* target_1 is recursive with depth of 2, so we capture two separate
+ * stack traces, depending on which occurrence it is
*/
static bool recur = false;
diff --git a/tools/testing/selftests/bpf/progs/verifier_arena_large.c b/tools/testing/selftests/bpf/progs/verifier_arena_large.c
index 9dbdf123542d..f19e15400b3e 100644
--- a/tools/testing/selftests/bpf/progs/verifier_arena_large.c
+++ b/tools/testing/selftests/bpf/progs/verifier_arena_large.c
@@ -240,6 +240,7 @@ int big_alloc2(void *ctx)
return 5;
bpf_arena_free_pages(&arena, (void __arena *)pg, 2);
page[i] = NULL;
+ barrier();
page[i + 1] = NULL;
cond_break;
}
diff --git a/tools/testing/selftests/bpf/progs/verifier_bounds.c b/tools/testing/selftests/bpf/progs/verifier_bounds.c
index 87a2c60d86e6..0a72e0228ea9 100644
--- a/tools/testing/selftests/bpf/progs/verifier_bounds.c
+++ b/tools/testing/selftests/bpf/progs/verifier_bounds.c
@@ -926,7 +926,7 @@ l1_%=: r0 = 0; \
SEC("socket")
__description("bounds check for non const xor src dst")
__success __log_level(2)
-__msg("5: (af) r0 ^= r6 ; R0_w=scalar(smin=smin32=0,smax=umax=smax32=umax32=431,var_off=(0x0; 0x1af))")
+__msg("5: (af) r0 ^= r6 ; R0=scalar(smin=smin32=0,smax=umax=smax32=umax32=431,var_off=(0x0; 0x1af))")
__naked void non_const_xor_src_dst(void)
{
asm volatile (" \
@@ -947,7 +947,7 @@ __naked void non_const_xor_src_dst(void)
SEC("socket")
__description("bounds check for non const or src dst")
__success __log_level(2)
-__msg("5: (4f) r0 |= r6 ; R0_w=scalar(smin=smin32=0,smax=umax=smax32=umax32=431,var_off=(0x0; 0x1af))")
+__msg("5: (4f) r0 |= r6 ; R0=scalar(smin=smin32=0,smax=umax=smax32=umax32=431,var_off=(0x0; 0x1af))")
__naked void non_const_or_src_dst(void)
{
asm volatile (" \
@@ -968,7 +968,7 @@ __naked void non_const_or_src_dst(void)
SEC("socket")
__description("bounds check for non const mul regs")
__success __log_level(2)
-__msg("5: (2f) r0 *= r6 ; R0_w=scalar(smin=smin32=0,smax=umax=smax32=umax32=3825,var_off=(0x0; 0xfff))")
+__msg("5: (2f) r0 *= r6 ; R0=scalar(smin=smin32=0,smax=umax=smax32=umax32=3825,var_off=(0x0; 0xfff))")
__naked void non_const_mul_regs(void)
{
asm volatile (" \
@@ -1241,7 +1241,7 @@ l0_%=: r0 = 0; \
SEC("tc")
__description("multiply mixed sign bounds. test 1")
__success __log_level(2)
-__msg("r6 *= r7 {{.*}}; R6_w=scalar(smin=umin=0x1bc16d5cd4927ee1,smax=umax=0x1bc16d674ec80000,smax32=0x7ffffeff,umax32=0xfffffeff,var_off=(0x1bc16d4000000000; 0x3ffffffeff))")
+__msg("r6 *= r7 {{.*}}; R6=scalar(smin=umin=0x1bc16d5cd4927ee1,smax=umax=0x1bc16d674ec80000,smax32=0x7ffffeff,umax32=0xfffffeff,var_off=(0x1bc16d4000000000; 0x3ffffffeff))")
__naked void mult_mixed0_sign(void)
{
asm volatile (
@@ -1264,7 +1264,7 @@ __naked void mult_mixed0_sign(void)
SEC("tc")
__description("multiply mixed sign bounds. test 2")
__success __log_level(2)
-__msg("r6 *= r7 {{.*}}; R6_w=scalar(smin=smin32=-100,smax=smax32=200)")
+__msg("r6 *= r7 {{.*}}; R6=scalar(smin=smin32=-100,smax=smax32=200)")
__naked void mult_mixed1_sign(void)
{
asm volatile (
@@ -1287,7 +1287,7 @@ __naked void mult_mixed1_sign(void)
SEC("tc")
__description("multiply negative bounds")
__success __log_level(2)
-__msg("r6 *= r7 {{.*}}; R6_w=scalar(smin=umin=smin32=umin32=0x3ff280b0,smax=umax=smax32=umax32=0x3fff0001,var_off=(0x3ff00000; 0xf81ff))")
+__msg("r6 *= r7 {{.*}}; R6=scalar(smin=umin=smin32=umin32=0x3ff280b0,smax=umax=smax32=umax32=0x3fff0001,var_off=(0x3ff00000; 0xf81ff))")
__naked void mult_sign_bounds(void)
{
asm volatile (
@@ -1311,7 +1311,7 @@ __naked void mult_sign_bounds(void)
SEC("tc")
__description("multiply bounds that don't cross signed boundary")
__success __log_level(2)
-__msg("r8 *= r6 {{.*}}; R6_w=scalar(smin=smin32=0,smax=umax=smax32=umax32=11,var_off=(0x0; 0xb)) R8_w=scalar(smin=0,smax=umax=0x7b96bb0a94a3a7cd,var_off=(0x0; 0x7fffffffffffffff))")
+__msg("r8 *= r6 {{.*}}; R6=scalar(smin=smin32=0,smax=umax=smax32=umax32=11,var_off=(0x0; 0xb)) R8=scalar(smin=0,smax=umax=0x7b96bb0a94a3a7cd,var_off=(0x0; 0x7fffffffffffffff))")
__naked void mult_no_sign_crossing(void)
{
asm volatile (
@@ -1331,7 +1331,7 @@ __naked void mult_no_sign_crossing(void)
SEC("tc")
__description("multiplication overflow, result in unbounded reg. test 1")
__success __log_level(2)
-__msg("r6 *= r7 {{.*}}; R6_w=scalar()")
+__msg("r6 *= r7 {{.*}}; R6=scalar()")
__naked void mult_unsign_ovf(void)
{
asm volatile (
@@ -1353,7 +1353,7 @@ __naked void mult_unsign_ovf(void)
SEC("tc")
__description("multiplication overflow, result in unbounded reg. test 2")
__success __log_level(2)
-__msg("r6 *= r7 {{.*}}; R6_w=scalar()")
+__msg("r6 *= r7 {{.*}}; R6=scalar()")
__naked void mult_sign_ovf(void)
{
asm volatile (
@@ -1376,7 +1376,7 @@ __naked void mult_sign_ovf(void)
SEC("socket")
__description("64-bit addition, all outcomes overflow")
__success __log_level(2)
-__msg("5: (0f) r3 += r3 {{.*}} R3_w=scalar(umin=0x4000000000000000,umax=0xfffffffffffffffe)")
+__msg("5: (0f) r3 += r3 {{.*}} R3=scalar(umin=0x4000000000000000,umax=0xfffffffffffffffe)")
__retval(0)
__naked void add64_full_overflow(void)
{
@@ -1396,7 +1396,7 @@ __naked void add64_full_overflow(void)
SEC("socket")
__description("64-bit addition, partial overflow, result in unbounded reg")
__success __log_level(2)
-__msg("4: (0f) r3 += r3 {{.*}} R3_w=scalar()")
+__msg("4: (0f) r3 += r3 {{.*}} R3=scalar()")
__retval(0)
__naked void add64_partial_overflow(void)
{
@@ -1416,7 +1416,7 @@ __naked void add64_partial_overflow(void)
SEC("socket")
__description("32-bit addition overflow, all outcomes overflow")
__success __log_level(2)
-__msg("4: (0c) w3 += w3 {{.*}} R3_w=scalar(smin=umin=umin32=0x40000000,smax=umax=umax32=0xfffffffe,var_off=(0x0; 0xffffffff))")
+__msg("4: (0c) w3 += w3 {{.*}} R3=scalar(smin=umin=umin32=0x40000000,smax=umax=umax32=0xfffffffe,var_off=(0x0; 0xffffffff))")
__retval(0)
__naked void add32_full_overflow(void)
{
@@ -1436,7 +1436,7 @@ __naked void add32_full_overflow(void)
SEC("socket")
__description("32-bit addition, partial overflow, result in unbounded u32 bounds")
__success __log_level(2)
-__msg("4: (0c) w3 += w3 {{.*}} R3_w=scalar(smin=0,smax=umax=0xffffffff,var_off=(0x0; 0xffffffff))")
+__msg("4: (0c) w3 += w3 {{.*}} R3=scalar(smin=0,smax=umax=0xffffffff,var_off=(0x0; 0xffffffff))")
__retval(0)
__naked void add32_partial_overflow(void)
{
@@ -1456,7 +1456,7 @@ __naked void add32_partial_overflow(void)
SEC("socket")
__description("64-bit subtraction, all outcomes underflow")
__success __log_level(2)
-__msg("6: (1f) r3 -= r1 {{.*}} R3_w=scalar(umin=1,umax=0x8000000000000000)")
+__msg("6: (1f) r3 -= r1 {{.*}} R3=scalar(umin=1,umax=0x8000000000000000)")
__retval(0)
__naked void sub64_full_overflow(void)
{
@@ -1477,7 +1477,7 @@ __naked void sub64_full_overflow(void)
SEC("socket")
__description("64-bit subtraction, partial overflow, result in unbounded reg")
__success __log_level(2)
-__msg("3: (1f) r3 -= r2 {{.*}} R3_w=scalar()")
+__msg("3: (1f) r3 -= r2 {{.*}} R3=scalar()")
__retval(0)
__naked void sub64_partial_overflow(void)
{
@@ -1496,7 +1496,7 @@ __naked void sub64_partial_overflow(void)
SEC("socket")
__description("32-bit subtraction overflow, all outcomes underflow")
__success __log_level(2)
-__msg("5: (1c) w3 -= w1 {{.*}} R3_w=scalar(smin=umin=umin32=1,smax=umax=umax32=0x80000000,var_off=(0x0; 0xffffffff))")
+__msg("5: (1c) w3 -= w1 {{.*}} R3=scalar(smin=umin=umin32=1,smax=umax=umax32=0x80000000,var_off=(0x0; 0xffffffff))")
__retval(0)
__naked void sub32_full_overflow(void)
{
@@ -1517,7 +1517,7 @@ __naked void sub32_full_overflow(void)
SEC("socket")
__description("32-bit subtraction, partial overflow, result in unbounded u32 bounds")
__success __log_level(2)
-__msg("3: (1c) w3 -= w2 {{.*}} R3_w=scalar(smin=0,smax=umax=0xffffffff,var_off=(0x0; 0xffffffff))")
+__msg("3: (1c) w3 -= w2 {{.*}} R3=scalar(smin=0,smax=umax=0xffffffff,var_off=(0x0; 0xffffffff))")
__retval(0)
__naked void sub32_partial_overflow(void)
{
@@ -1617,7 +1617,7 @@ l0_%=: r0 = 0; \
SEC("socket")
__description("bounds deduction cross sign boundary, positive overlap")
__success __log_level(2) __flag(BPF_F_TEST_REG_INVARIANTS)
-__msg("3: (2d) if r0 > r1 {{.*}} R0_w=scalar(smin=smin32=0,smax=umax=smax32=umax32=127,var_off=(0x0; 0x7f))")
+__msg("3: (2d) if r0 > r1 {{.*}} R0=scalar(smin=smin32=0,smax=umax=smax32=umax32=127,var_off=(0x0; 0x7f))")
__retval(0)
__naked void bounds_deduct_positive_overlap(void)
{
@@ -1650,7 +1650,7 @@ l0_%=: r0 = 0; \
SEC("socket")
__description("bounds deduction cross sign boundary, two overlaps")
__failure __flag(BPF_F_TEST_REG_INVARIANTS)
-__msg("3: (2d) if r0 > r1 {{.*}} R0_w=scalar(smin=smin32=-128,smax=smax32=127,umax=0xffffffffffffff80)")
+__msg("3: (2d) if r0 > r1 {{.*}} R0=scalar(smin=smin32=-128,smax=smax32=127,umax=0xffffffffffffff80)")
__msg("frame pointer is read only")
__naked void bounds_deduct_two_overlaps(void)
{
@@ -1668,4 +1668,45 @@ l0_%=: r0 = 0; \
: __clobber_all);
}
+SEC("socket")
+__description("dead jne branch due to disagreeing tnums")
+__success __log_level(2)
+__naked void jne_disagreeing_tnums(void *ctx)
+{
+ asm volatile(" \
+ call %[bpf_get_prandom_u32]; \
+ w0 = w0; \
+ r0 >>= 30; \
+ r0 <<= 30; \
+ r1 = r0; \
+ r1 += 1024; \
+ if r1 != r0 goto +1; \
+ r10 = 0; \
+ exit; \
+" :
+ : __imm(bpf_get_prandom_u32)
+ : __clobber_all);
+}
+
+SEC("socket")
+__description("dead jeq branch due to disagreeing tnums")
+__success __log_level(2)
+__naked void jeq_disagreeing_tnums(void *ctx)
+{
+ asm volatile(" \
+ call %[bpf_get_prandom_u32]; \
+ w0 = w0; \
+ r0 >>= 30; \
+ r0 <<= 30; \
+ r1 = r0; \
+ r1 += 1024; \
+ if r1 == r0 goto +1; \
+ exit; \
+ r10 = 0; \
+ exit; \
+" :
+ : __imm(bpf_get_prandom_u32)
+ : __clobber_all);
+}
+
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c b/tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c
index c258b0722e04..fb4fa465d67c 100644
--- a/tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c
+++ b/tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c
@@ -660,19 +660,24 @@ __naked void may_goto_interaction_x86_64(void)
SEC("raw_tp")
__arch_arm64
-__log_level(4) __msg("stack depth 16")
-/* may_goto counter at -16 */
-__xlated("0: *(u64 *)(r10 -16) =")
-__xlated("1: r1 = 1")
-__xlated("2: call bpf_get_smp_processor_id")
+__log_level(4) __msg("stack depth 24")
+/* may_goto counter at -24 */
+__xlated("0: *(u64 *)(r10 -24) =")
+/* may_goto timestamp at -16 */
+__xlated("1: *(u64 *)(r10 -16) =")
+__xlated("2: r1 = 1")
+__xlated("3: call bpf_get_smp_processor_id")
/* may_goto expansion starts */
-__xlated("3: r11 = *(u64 *)(r10 -16)")
-__xlated("4: if r11 == 0x0 goto pc+3")
-__xlated("5: r11 -= 1")
-__xlated("6: *(u64 *)(r10 -16) = r11")
+__xlated("4: r11 = *(u64 *)(r10 -24)")
+__xlated("5: if r11 == 0x0 goto pc+6")
+__xlated("6: r11 -= 1")
+__xlated("7: if r11 != 0x0 goto pc+2")
+__xlated("8: r11 = -24")
+__xlated("9: call unknown")
+__xlated("10: *(u64 *)(r10 -24) = r11")
/* may_goto expansion ends */
-__xlated("7: *(u64 *)(r10 -8) = r1")
-__xlated("8: exit")
+__xlated("11: *(u64 *)(r10 -8) = r1")
+__xlated("12: exit")
__success
__naked void may_goto_interaction_arm64(void)
{
diff --git a/tools/testing/selftests/bpf/progs/verifier_ctx.c b/tools/testing/selftests/bpf/progs/verifier_ctx.c
index 424463094760..5ebf7d9bcc55 100644
--- a/tools/testing/selftests/bpf/progs/verifier_ctx.c
+++ b/tools/testing/selftests/bpf/progs/verifier_ctx.c
@@ -5,8 +5,6 @@
#include <bpf/bpf_helpers.h>
#include "bpf_misc.h"
-#define sizeof_field(TYPE, MEMBER) sizeof((((TYPE *)0)->MEMBER))
-
SEC("tc")
__description("context stores via BPF_ATOMIC")
__failure __msg("BPF_ATOMIC stores into R1 ctx is not allowed")
@@ -264,4 +262,34 @@ narrow_load("sockops", bpf_sock_ops, skb_hwtstamp);
unaligned_access("flow_dissector", __sk_buff, data);
unaligned_access("netfilter", bpf_nf_ctx, skb);
+#define padding_access(type, ctx, prev_field, sz) \
+ SEC(type) \
+ __description("access on " #ctx " padding after " #prev_field) \
+ __naked void padding_ctx_access_##ctx(void) \
+ { \
+ asm volatile (" \
+ r1 = *(u%[size] *)(r1 + %[off]); \
+ r0 = 0; \
+ exit;" \
+ : \
+ : __imm_const(size, sz * 8), \
+ __imm_const(off, offsetofend(struct ctx, prev_field)) \
+ : __clobber_all); \
+ }
+
+__failure __msg("invalid bpf_context access")
+padding_access("cgroup/bind4", bpf_sock_addr, msg_src_ip6[3], 4);
+
+__success
+padding_access("sk_lookup", bpf_sk_lookup, remote_port, 2);
+
+__failure __msg("invalid bpf_context access")
+padding_access("tc", __sk_buff, tstamp_type, 2);
+
+__failure __msg("invalid bpf_context access")
+padding_access("cgroup/post_bind4", bpf_sock, dst_port, 2);
+
+__failure __msg("invalid bpf_context access")
+padding_access("sk_reuseport", sk_reuseport_md, hash, 4);
+
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_global_ptr_args.c b/tools/testing/selftests/bpf/progs/verifier_global_ptr_args.c
index 181da86ba5f0..6630a92b1b47 100644
--- a/tools/testing/selftests/bpf/progs/verifier_global_ptr_args.c
+++ b/tools/testing/selftests/bpf/progs/verifier_global_ptr_args.c
@@ -215,7 +215,7 @@ __weak int subprog_untrusted(const volatile struct task_struct *restrict task __
SEC("tp_btf/sys_enter")
__success
__log_level(2)
-__msg("r1 = {{.*}}; {{.*}}R1_w=trusted_ptr_task_struct()")
+__msg("r1 = {{.*}}; {{.*}}R1=trusted_ptr_task_struct()")
__msg("Func#1 ('subprog_untrusted') is global and assumed valid.")
__msg("Validating subprog_untrusted() func#1...")
__msg(": R1=untrusted_ptr_task_struct")
@@ -278,7 +278,7 @@ __weak int subprog_enum_untrusted(enum bpf_attach_type *p __arg_untrusted)
SEC("tp_btf/sys_enter")
__success
__log_level(2)
-__msg("r1 = {{.*}}; {{.*}}R1_w=trusted_ptr_task_struct()")
+__msg("r1 = {{.*}}; {{.*}}R1=trusted_ptr_task_struct()")
__msg("Func#1 ('subprog_void_untrusted') is global and assumed valid.")
__msg("Validating subprog_void_untrusted() func#1...")
__msg(": R1=rdonly_untrusted_mem(sz=0)")
diff --git a/tools/testing/selftests/bpf/progs/verifier_ldsx.c b/tools/testing/selftests/bpf/progs/verifier_ldsx.c
index 52edee41caf6..c8494b682c31 100644
--- a/tools/testing/selftests/bpf/progs/verifier_ldsx.c
+++ b/tools/testing/selftests/bpf/progs/verifier_ldsx.c
@@ -3,6 +3,7 @@
#include <linux/bpf.h>
#include <bpf/bpf_helpers.h>
#include "bpf_misc.h"
+#include "bpf_arena_common.h"
#if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \
(defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) || \
@@ -10,6 +11,12 @@
defined(__TARGET_ARCH_loongarch)) && \
__clang_major__ >= 18
+struct {
+ __uint(type, BPF_MAP_TYPE_ARENA);
+ __uint(map_flags, BPF_F_MMAPABLE);
+ __uint(max_entries, 1);
+} arena SEC(".maps");
+
SEC("socket")
__description("LDSX, S8")
__success __success_unpriv __retval(-2)
@@ -65,7 +72,7 @@ __naked void ldsx_s32(void)
SEC("socket")
__description("LDSX, S8 range checking, privileged")
__log_level(2) __success __retval(1)
-__msg("R1_w=scalar(smin=smin32=-128,smax=smax32=127)")
+__msg("R1=scalar(smin=smin32=-128,smax=smax32=127)")
__naked void ldsx_s8_range_priv(void)
{
asm volatile (
@@ -256,6 +263,175 @@ __naked void ldsx_ctx_8(void)
: __clobber_all);
}
+SEC("syscall")
+__description("Arena LDSX Disasm")
+__success
+__arch_x86_64
+__jited("movslq 0x10(%rax,%r12), %r14")
+__jited("movswq 0x18(%rax,%r12), %r14")
+__jited("movsbq 0x20(%rax,%r12), %r14")
+__jited("movslq 0x10(%rdi,%r12), %r15")
+__jited("movswq 0x18(%rdi,%r12), %r15")
+__jited("movsbq 0x20(%rdi,%r12), %r15")
+__arch_arm64
+__jited("add x11, x7, x28")
+__jited("ldrsw x21, [x11, #0x10]")
+__jited("add x11, x7, x28")
+__jited("ldrsh x21, [x11, #0x18]")
+__jited("add x11, x7, x28")
+__jited("ldrsb x21, [x11, #0x20]")
+__jited("add x11, x0, x28")
+__jited("ldrsw x22, [x11, #0x10]")
+__jited("add x11, x0, x28")
+__jited("ldrsh x22, [x11, #0x18]")
+__jited("add x11, x0, x28")
+__jited("ldrsb x22, [x11, #0x20]")
+__naked void arena_ldsx_disasm(void *ctx)
+{
+ asm volatile (
+ "r1 = %[arena] ll;"
+ "r2 = 0;"
+ "r3 = 1;"
+ "r4 = %[numa_no_node];"
+ "r5 = 0;"
+ "call %[bpf_arena_alloc_pages];"
+ "r0 = addr_space_cast(r0, 0x0, 0x1);"
+ "r1 = r0;"
+ "r8 = *(s32 *)(r0 + 16);"
+ "r8 = *(s16 *)(r0 + 24);"
+ "r8 = *(s8 *)(r0 + 32);"
+ "r9 = *(s32 *)(r1 + 16);"
+ "r9 = *(s16 *)(r1 + 24);"
+ "r9 = *(s8 *)(r1 + 32);"
+ "r0 = 0;"
+ "exit;"
+ :: __imm(bpf_arena_alloc_pages),
+ __imm_addr(arena),
+ __imm_const(numa_no_node, NUMA_NO_NODE)
+ : __clobber_all
+ );
+}
+
+SEC("syscall")
+__description("Arena LDSX Exception")
+__success __retval(0)
+__arch_x86_64
+__arch_arm64
+__naked void arena_ldsx_exception(void *ctx)
+{
+ asm volatile (
+ "r1 = %[arena] ll;"
+ "r0 = 0xdeadbeef;"
+ "r0 = addr_space_cast(r0, 0x0, 0x1);"
+ "r1 = 0x3fe;"
+ "*(u64 *)(r0 + 0) = r1;"
+ "r0 = *(s8 *)(r0 + 0);"
+ "exit;"
+ :
+ : __imm_addr(arena)
+ : __clobber_all
+ );
+}
+
+SEC("syscall")
+__description("Arena LDSX, S8")
+__success __retval(-1)
+__arch_x86_64
+__arch_arm64
+__naked void arena_ldsx_s8(void *ctx)
+{
+ asm volatile (
+ "r1 = %[arena] ll;"
+ "r2 = 0;"
+ "r3 = 1;"
+ "r4 = %[numa_no_node];"
+ "r5 = 0;"
+ "call %[bpf_arena_alloc_pages];"
+ "r0 = addr_space_cast(r0, 0x0, 0x1);"
+ "r1 = 0x3fe;"
+ "*(u64 *)(r0 + 0) = r1;"
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+ "r0 = *(s8 *)(r0 + 0);"
+#else
+ "r0 = *(s8 *)(r0 + 7);"
+#endif
+ "r0 >>= 1;"
+ "exit;"
+ :: __imm(bpf_arena_alloc_pages),
+ __imm_addr(arena),
+ __imm_const(numa_no_node, NUMA_NO_NODE)
+ : __clobber_all
+ );
+}
+
+SEC("syscall")
+__description("Arena LDSX, S16")
+__success __retval(-1)
+__arch_x86_64
+__arch_arm64
+__naked void arena_ldsx_s16(void *ctx)
+{
+ asm volatile (
+ "r1 = %[arena] ll;"
+ "r2 = 0;"
+ "r3 = 1;"
+ "r4 = %[numa_no_node];"
+ "r5 = 0;"
+ "call %[bpf_arena_alloc_pages];"
+ "r0 = addr_space_cast(r0, 0x0, 0x1);"
+ "r1 = 0x3fffe;"
+ "*(u64 *)(r0 + 0) = r1;"
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+ "r0 = *(s16 *)(r0 + 0);"
+#else
+ "r0 = *(s16 *)(r0 + 6);"
+#endif
+ "r0 >>= 1;"
+ "exit;"
+ :: __imm(bpf_arena_alloc_pages),
+ __imm_addr(arena),
+ __imm_const(numa_no_node, NUMA_NO_NODE)
+ : __clobber_all
+ );
+}
+
+SEC("syscall")
+__description("Arena LDSX, S32")
+__success __retval(-1)
+__arch_x86_64
+__arch_arm64
+__naked void arena_ldsx_s32(void *ctx)
+{
+ asm volatile (
+ "r1 = %[arena] ll;"
+ "r2 = 0;"
+ "r3 = 1;"
+ "r4 = %[numa_no_node];"
+ "r5 = 0;"
+ "call %[bpf_arena_alloc_pages];"
+ "r0 = addr_space_cast(r0, 0x0, 0x1);"
+ "r1 = 0xfffffffe;"
+ "*(u64 *)(r0 + 0) = r1;"
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+ "r0 = *(s32 *)(r0 + 0);"
+#else
+ "r0 = *(s32 *)(r0 + 4);"
+#endif
+ "r0 >>= 1;"
+ "exit;"
+ :: __imm(bpf_arena_alloc_pages),
+ __imm_addr(arena),
+ __imm_const(numa_no_node, NUMA_NO_NODE)
+ : __clobber_all
+ );
+}
+
+/* to retain debug info for BTF generation */
+void kfunc_root(void)
+{
+ bpf_arena_alloc_pages(0, 0, 0, 0, 0);
+}
+
#else
SEC("socket")
diff --git a/tools/testing/selftests/bpf/progs/verifier_live_stack.c b/tools/testing/selftests/bpf/progs/verifier_live_stack.c
new file mode 100644
index 000000000000..c0e808509268
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_live_stack.c
@@ -0,0 +1,294 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+struct {
+ __uint(type, BPF_MAP_TYPE_HASH);
+ __uint(max_entries, 1);
+ __type(key, int);
+ __type(value, long long);
+} map SEC(".maps");
+
+SEC("socket")
+__log_level(2)
+__msg("(0) frame 0 insn 2 +written -8")
+__msg("(0) frame 0 insn 1 +live -24")
+__msg("(0) frame 0 insn 1 +written -8")
+__msg("(0) frame 0 insn 0 +live -8,-24")
+__msg("(0) frame 0 insn 0 +written -8")
+__msg("(0) live stack update done in 2 iterations")
+__naked void simple_read_simple_write(void)
+{
+ asm volatile (
+ "r1 = *(u64 *)(r10 - 8);"
+ "r2 = *(u64 *)(r10 - 24);"
+ "*(u64 *)(r10 - 8) = r1;"
+ "r0 = 0;"
+ "exit;"
+ ::: __clobber_all);
+}
+
+SEC("socket")
+__log_level(2)
+__msg("(0) frame 0 insn 1 +live -8")
+__not_msg("(0) frame 0 insn 1 +written")
+__msg("(0) live stack update done in 2 iterations")
+__msg("(0) frame 0 insn 1 +live -16")
+__msg("(0) frame 0 insn 1 +written -32")
+__msg("(0) live stack update done in 2 iterations")
+__naked void read_write_join(void)
+{
+ asm volatile (
+ "call %[bpf_get_prandom_u32];"
+ "if r0 > 42 goto 1f;"
+ "r0 = *(u64 *)(r10 - 8);"
+ "*(u64 *)(r10 - 32) = r0;"
+ "*(u64 *)(r10 - 40) = r0;"
+ "exit;"
+"1:"
+ "r0 = *(u64 *)(r10 - 16);"
+ "*(u64 *)(r10 - 32) = r0;"
+ "exit;"
+ :: __imm(bpf_get_prandom_u32)
+ : __clobber_all);
+}
+
+SEC("socket")
+__log_level(2)
+__msg("2: (25) if r0 > 0x2a goto pc+1")
+__msg("7: (95) exit")
+__msg("(0) frame 0 insn 2 +written -16")
+__msg("(0) live stack update done in 2 iterations")
+__msg("7: (95) exit")
+__not_msg("(0) frame 0 insn 2")
+__msg("(0) live stack update done in 1 iterations")
+__naked void must_write_not_same_slot(void)
+{
+ asm volatile (
+ "call %[bpf_get_prandom_u32];"
+ "r1 = -8;"
+ "if r0 > 42 goto 1f;"
+ "r1 = -16;"
+"1:"
+ "r2 = r10;"
+ "r2 += r1;"
+ "*(u64 *)(r2 + 0) = r0;"
+ "exit;"
+ :: __imm(bpf_get_prandom_u32)
+ : __clobber_all);
+}
+
+SEC("socket")
+__log_level(2)
+__msg("(0) frame 0 insn 0 +written -8,-16")
+__msg("(0) live stack update done in 2 iterations")
+__msg("(0) frame 0 insn 0 +written -8")
+__msg("(0) live stack update done in 2 iterations")
+__naked void must_write_not_same_type(void)
+{
+ asm volatile (
+ "*(u64*)(r10 - 8) = 0;"
+ "r2 = r10;"
+ "r2 += -8;"
+ "r1 = %[map] ll;"
+ "call %[bpf_map_lookup_elem];"
+ "if r0 != 0 goto 1f;"
+ "r0 = r10;"
+ "r0 += -16;"
+"1:"
+ "*(u64 *)(r0 + 0) = 42;"
+ "exit;"
+ :
+ : __imm(bpf_get_prandom_u32),
+ __imm(bpf_map_lookup_elem),
+ __imm_addr(map)
+ : __clobber_all);
+}
+
+SEC("socket")
+__log_level(2)
+__msg("(2,4) frame 0 insn 4 +written -8")
+__msg("(2,4) live stack update done in 2 iterations")
+__msg("(0) frame 0 insn 2 +written -8")
+__msg("(0) live stack update done in 2 iterations")
+__naked void caller_stack_write(void)
+{
+ asm volatile (
+ "r1 = r10;"
+ "r1 += -8;"
+ "call write_first_param;"
+ "exit;"
+ ::: __clobber_all);
+}
+
+static __used __naked void write_first_param(void)
+{
+ asm volatile (
+ "*(u64 *)(r1 + 0) = 7;"
+ "r0 = 0;"
+ "exit;"
+ ::: __clobber_all);
+}
+
+SEC("socket")
+__log_level(2)
+/* caller_stack_read() function */
+__msg("2: .12345.... (85) call pc+4")
+__msg("5: .12345.... (85) call pc+1")
+__msg("6: 0......... (95) exit")
+/* read_first_param() function */
+__msg("7: .1........ (79) r0 = *(u64 *)(r1 +0)")
+__msg("8: 0......... (95) exit")
+/* update for callsite at (2) */
+__msg("(2,7) frame 0 insn 7 +live -8")
+__msg("(2,7) live stack update done in 2 iterations")
+__msg("(0) frame 0 insn 2 +live -8")
+__msg("(0) live stack update done in 2 iterations")
+/* update for callsite at (5) */
+__msg("(5,7) frame 0 insn 7 +live -16")
+__msg("(5,7) live stack update done in 2 iterations")
+__msg("(0) frame 0 insn 5 +live -16")
+__msg("(0) live stack update done in 2 iterations")
+__naked void caller_stack_read(void)
+{
+ asm volatile (
+ "r1 = r10;"
+ "r1 += -8;"
+ "call read_first_param;"
+ "r1 = r10;"
+ "r1 += -16;"
+ "call read_first_param;"
+ "exit;"
+ ::: __clobber_all);
+}
+
+static __used __naked void read_first_param(void)
+{
+ asm volatile (
+ "r0 = *(u64 *)(r1 + 0);"
+ "exit;"
+ ::: __clobber_all);
+}
+
+SEC("socket")
+__flag(BPF_F_TEST_STATE_FREQ)
+__log_level(2)
+/* read_first_param2() function */
+__msg(" 9: .1........ (79) r0 = *(u64 *)(r1 +0)")
+__msg("10: .......... (b7) r0 = 0")
+__msg("11: 0......... (05) goto pc+0")
+__msg("12: 0......... (95) exit")
+/*
+ * The purpose of the test is to check that checkpoint in
+ * read_first_param2() stops path traversal. This will only happen if
+ * verifier understands that fp[0]-8 at insn (12) is not alive.
+ */
+__msg("12: safe")
+__msg("processed 20 insns")
+__naked void caller_stack_pruning(void)
+{
+ asm volatile (
+ "call %[bpf_get_prandom_u32];"
+ "if r0 == 42 goto 1f;"
+ "r0 = %[map] ll;"
+"1:"
+ "*(u64 *)(r10 - 8) = r0;"
+ "r1 = r10;"
+ "r1 += -8;"
+ /*
+ * fp[0]-8 is either pointer to map or a scalar,
+ * preventing state pruning at checkpoint created for call.
+ */
+ "call read_first_param2;"
+ "exit;"
+ :
+ : __imm(bpf_get_prandom_u32),
+ __imm_addr(map)
+ : __clobber_all);
+}
+
+static __used __naked void read_first_param2(void)
+{
+ asm volatile (
+ "r0 = *(u64 *)(r1 + 0);"
+ "r0 = 0;"
+ /*
+ * Checkpoint at goto +0 should fire,
+ * as caller stack fp[0]-8 is not alive at this point.
+ */
+ "goto +0;"
+ "exit;"
+ ::: __clobber_all);
+}
+
+SEC("socket")
+__flag(BPF_F_TEST_STATE_FREQ)
+__failure
+__msg("R1 type=scalar expected=map_ptr")
+__naked void caller_stack_pruning_callback(void)
+{
+ asm volatile (
+ "r0 = %[map] ll;"
+ "*(u64 *)(r10 - 8) = r0;"
+ "r1 = 2;"
+ "r2 = loop_cb ll;"
+ "r3 = r10;"
+ "r3 += -8;"
+ "r4 = 0;"
+ /*
+ * fp[0]-8 is either pointer to map or a scalar,
+ * preventing state pruning at checkpoint created for call.
+ */
+ "call %[bpf_loop];"
+ "r0 = 42;"
+ "exit;"
+ :
+ : __imm(bpf_get_prandom_u32),
+ __imm(bpf_loop),
+ __imm_addr(map)
+ : __clobber_all);
+}
+
+static __used __naked void loop_cb(void)
+{
+ asm volatile (
+ /*
+ * Checkpoint at function entry should not fire, as caller
+ * stack fp[0]-8 is alive at this point.
+ */
+ "r6 = r2;"
+ "r1 = *(u64 *)(r6 + 0);"
+ "*(u64*)(r10 - 8) = 7;"
+ "r2 = r10;"
+ "r2 += -8;"
+ "call %[bpf_map_lookup_elem];"
+ /*
+ * This should stop verifier on a second loop iteration,
+ * but only if verifier correctly maintains that fp[0]-8
+ * is still alive.
+ */
+ "*(u64 *)(r6 + 0) = 0;"
+ "r0 = 0;"
+ "exit;"
+ :
+ : __imm(bpf_map_lookup_elem),
+ __imm(bpf_get_prandom_u32)
+ : __clobber_all);
+}
+
+/*
+ * Because of a bug in verifier.c:compute_postorder()
+ * the program below overflowed traversal queue in that function.
+ */
+SEC("socket")
+__naked void syzbot_postorder_bug1(void)
+{
+ asm volatile (
+ "r0 = 0;"
+ "if r0 != 0 goto -1;"
+ "exit;"
+ ::: __clobber_all);
+}
diff --git a/tools/testing/selftests/bpf/progs/verifier_loops1.c b/tools/testing/selftests/bpf/progs/verifier_loops1.c
index e07b43b78fd2..fbdde80e7b90 100644
--- a/tools/testing/selftests/bpf/progs/verifier_loops1.c
+++ b/tools/testing/selftests/bpf/progs/verifier_loops1.c
@@ -283,4 +283,25 @@ exit_%=: \
: __clobber_all);
}
+/*
+ * This test case triggered a bug in verifier.c:maybe_exit_scc().
+ * Speculative execution path reaches stack access instruction,
+ * stops and triggers maybe_exit_scc() w/o accompanying maybe_enter_scc() call.
+ */
+SEC("socket")
+__arch_x86_64
+__caps_unpriv(CAP_BPF)
+__naked void maybe_exit_scc_bug1(void)
+{
+ asm volatile (
+ "r0 = 100;"
+"1:"
+ /* Speculative execution path reaches and stops here. */
+ "*(u64 *)(r10 - 512) = r0;"
+ /* Condition is always false, but verifier speculatively executes the true branch. */
+ "if r0 <= 0x0 goto 1b;"
+ "exit;"
+ ::: __clobber_all);
+}
+
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_map_ptr.c b/tools/testing/selftests/bpf/progs/verifier_map_ptr.c
index 11a079145966..e2767d27d8aa 100644
--- a/tools/testing/selftests/bpf/progs/verifier_map_ptr.c
+++ b/tools/testing/selftests/bpf/progs/verifier_map_ptr.c
@@ -70,10 +70,13 @@ __naked void bpf_map_ptr_write_rejected(void)
: __clobber_all);
}
+/* The first element of struct bpf_map is a SHA256 hash of 32 bytes, accessing
+ * into this array is valid. The opts field is now at offset 33.
+ */
SEC("socket")
__description("bpf_map_ptr: read non-existent field rejected")
__failure
-__msg("cannot access ptr member ops with moff 0 in struct bpf_map with off 1 size 4")
+__msg("cannot access ptr member ops with moff 32 in struct bpf_map with off 33 size 4")
__failure_unpriv
__msg_unpriv("access is allowed only to CAP_PERFMON and CAP_SYS_ADMIN")
__flag(BPF_F_ANY_ALIGNMENT)
@@ -82,7 +85,7 @@ __naked void read_non_existent_field_rejected(void)
asm volatile (" \
r6 = 0; \
r1 = %[map_array_48b] ll; \
- r6 = *(u32*)(r1 + 1); \
+ r6 = *(u32*)(r1 + 33); \
r0 = 1; \
exit; \
" :
diff --git a/tools/testing/selftests/bpf/progs/verifier_may_goto_1.c b/tools/testing/selftests/bpf/progs/verifier_may_goto_1.c
index 3966d827f288..6d1edaef9213 100644
--- a/tools/testing/selftests/bpf/progs/verifier_may_goto_1.c
+++ b/tools/testing/selftests/bpf/progs/verifier_may_goto_1.c
@@ -9,6 +9,8 @@
SEC("raw_tp")
__description("may_goto 0")
__arch_x86_64
+__arch_s390x
+__arch_arm64
__xlated("0: r0 = 1")
__xlated("1: exit")
__success
@@ -27,6 +29,8 @@ __naked void may_goto_simple(void)
SEC("raw_tp")
__description("batch 2 of may_goto 0")
__arch_x86_64
+__arch_s390x
+__arch_arm64
__xlated("0: r0 = 1")
__xlated("1: exit")
__success
@@ -47,6 +51,8 @@ __naked void may_goto_batch_0(void)
SEC("raw_tp")
__description("may_goto batch with offsets 2/1/0")
__arch_x86_64
+__arch_s390x
+__arch_arm64
__xlated("0: r0 = 1")
__xlated("1: exit")
__success
@@ -69,8 +75,10 @@ __naked void may_goto_batch_1(void)
}
SEC("raw_tp")
-__description("may_goto batch with offsets 2/0 - x86_64")
+__description("may_goto batch with offsets 2/0")
__arch_x86_64
+__arch_s390x
+__arch_arm64
__xlated("0: *(u64 *)(r10 -16) = 65535")
__xlated("1: *(u64 *)(r10 -8) = 0")
__xlated("2: r11 = *(u64 *)(r10 -16)")
@@ -84,33 +92,7 @@ __xlated("9: r0 = 1")
__xlated("10: r0 = 2")
__xlated("11: exit")
__success
-__naked void may_goto_batch_2_x86_64(void)
-{
- asm volatile (
- ".8byte %[may_goto1];"
- ".8byte %[may_goto3];"
- "r0 = 1;"
- "r0 = 2;"
- "exit;"
- :
- : __imm_insn(may_goto1, BPF_RAW_INSN(BPF_JMP | BPF_JCOND, 0, 0, 2 /* offset */, 0)),
- __imm_insn(may_goto3, BPF_RAW_INSN(BPF_JMP | BPF_JCOND, 0, 0, 0 /* offset */, 0))
- : __clobber_all);
-}
-
-SEC("raw_tp")
-__description("may_goto batch with offsets 2/0 - arm64")
-__arch_arm64
-__xlated("0: *(u64 *)(r10 -8) = 8388608")
-__xlated("1: r11 = *(u64 *)(r10 -8)")
-__xlated("2: if r11 == 0x0 goto pc+3")
-__xlated("3: r11 -= 1")
-__xlated("4: *(u64 *)(r10 -8) = r11")
-__xlated("5: r0 = 1")
-__xlated("6: r0 = 2")
-__xlated("7: exit")
-__success
-__naked void may_goto_batch_2_arm64(void)
+__naked void may_goto_batch_2(void)
{
asm volatile (
".8byte %[may_goto1];"
diff --git a/tools/testing/selftests/bpf/progs/verifier_mul.c b/tools/testing/selftests/bpf/progs/verifier_mul.c
new file mode 100644
index 000000000000..7145fe3351d5
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_mul.c
@@ -0,0 +1,38 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Nandakumar Edamana */
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+
+/* Intended to test the abstract multiplication technique(s) used by
+ * the verifier. Using assembly to avoid compiler optimizations.
+ */
+SEC("fentry/bpf_fentry_test1")
+void BPF_PROG(mul_precise, int x)
+{
+ /* First, force the verifier to be uncertain about the value:
+ * unsigned int a = (bpf_get_prandom_u32() & 0x2) | 0x1;
+ *
+ * Assuming the verifier is using tnum, a must be tnum{.v=0x1, .m=0x2}.
+ * Then a * 0x3 would be m0m1 (m for uncertain). Added imprecision
+ * would cause the following to fail, because the required return value
+ * is 0:
+ * return (a * 0x3) & 0x4);
+ */
+ asm volatile ("\
+ call %[bpf_get_prandom_u32];\
+ r0 &= 0x2;\
+ r0 |= 0x1;\
+ r0 *= 0x3;\
+ r0 &= 0x4;\
+ if r0 != 0 goto l0_%=;\
+ r0 = 0;\
+ goto l1_%=;\
+l0_%=:\
+ r0 = 1;\
+l1_%=:\
+" :
+ : __imm(bpf_get_prandom_u32)
+ : __clobber_all);
+}
diff --git a/tools/testing/selftests/bpf/progs/verifier_precision.c b/tools/testing/selftests/bpf/progs/verifier_precision.c
index 73fee2aec698..1fe090cd6744 100644
--- a/tools/testing/selftests/bpf/progs/verifier_precision.c
+++ b/tools/testing/selftests/bpf/progs/verifier_precision.c
@@ -144,21 +144,21 @@ SEC("?raw_tp")
__success __log_level(2)
/*
* Without the bug fix there will be no history between "last_idx 3 first_idx 3"
- * and "parent state regs=" lines. "R0_w=6" parts are here to help anchor
+ * and "parent state regs=" lines. "R0=6" parts are here to help anchor
* expected log messages to the one specific mark_chain_precision operation.
*
* This is quite fragile: if verifier checkpointing heuristic changes, this
* might need adjusting.
*/
-__msg("2: (07) r0 += 1 ; R0_w=6")
+__msg("2: (07) r0 += 1 ; R0=6")
__msg("3: (35) if r0 >= 0xa goto pc+1")
__msg("mark_precise: frame0: last_idx 3 first_idx 3 subseq_idx -1")
__msg("mark_precise: frame0: regs=r0 stack= before 2: (07) r0 += 1")
__msg("mark_precise: frame0: regs=r0 stack= before 1: (07) r0 += 1")
__msg("mark_precise: frame0: regs=r0 stack= before 4: (05) goto pc-4")
__msg("mark_precise: frame0: regs=r0 stack= before 3: (35) if r0 >= 0xa goto pc+1")
-__msg("mark_precise: frame0: parent state regs= stack=: R0_rw=P4")
-__msg("3: R0_w=6")
+__msg("mark_precise: frame0: parent state regs= stack=: R0=P4")
+__msg("3: R0=6")
__naked int state_loop_first_last_equal(void)
{
asm volatile (
@@ -233,8 +233,8 @@ __naked void bpf_cond_op_not_r10(void)
SEC("lsm.s/socket_connect")
__success __log_level(2)
-__msg("0: (b7) r0 = 1 ; R0_w=1")
-__msg("1: (84) w0 = -w0 ; R0_w=0xffffffff")
+__msg("0: (b7) r0 = 1 ; R0=1")
+__msg("1: (84) w0 = -w0 ; R0=0xffffffff")
__msg("mark_precise: frame0: last_idx 2 first_idx 0 subseq_idx -1")
__msg("mark_precise: frame0: regs=r0 stack= before 1: (84) w0 = -w0")
__msg("mark_precise: frame0: regs=r0 stack= before 0: (b7) r0 = 1")
@@ -268,8 +268,8 @@ __naked int bpf_neg_3(void)
SEC("lsm.s/socket_connect")
__success __log_level(2)
-__msg("0: (b7) r0 = 1 ; R0_w=1")
-__msg("1: (87) r0 = -r0 ; R0_w=-1")
+__msg("0: (b7) r0 = 1 ; R0=1")
+__msg("1: (87) r0 = -r0 ; R0=-1")
__msg("mark_precise: frame0: last_idx 2 first_idx 0 subseq_idx -1")
__msg("mark_precise: frame0: regs=r0 stack= before 1: (87) r0 = -r0")
__msg("mark_precise: frame0: regs=r0 stack= before 0: (b7) r0 = 1")
diff --git a/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c b/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c
index 7c5e5e6d10eb..c0ce690ddb68 100644
--- a/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c
+++ b/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c
@@ -349,11 +349,11 @@ __naked void precision_two_ids(void)
SEC("socket")
__success __log_level(2)
__flag(BPF_F_TEST_STATE_FREQ)
-/* check thar r0 and r6 have different IDs after 'if',
+/* check that r0 and r6 have different IDs after 'if',
* collect_linked_regs() can't tie more than 6 registers for a single insn.
*/
__msg("8: (25) if r0 > 0x7 goto pc+0 ; R0=scalar(id=1")
-__msg("9: (bf) r6 = r6 ; R6_w=scalar(id=2")
+__msg("9: (bf) r6 = r6 ; R6=scalar(id=2")
/* check that r{0-5} are marked precise after 'if' */
__msg("frame0: regs=r0 stack= before 8: (25) if r0 > 0x7 goto pc+0")
__msg("frame0: parent state regs=r0,r1,r2,r3,r4,r5 stack=:")
@@ -779,12 +779,12 @@ __success
__retval(0)
/* Check that verifier believes r1/r0 are zero at exit */
__log_level(2)
-__msg("4: (77) r1 >>= 32 ; R1_w=0")
-__msg("5: (bf) r0 = r1 ; R0_w=0 R1_w=0")
+__msg("4: (77) r1 >>= 32 ; R1=0")
+__msg("5: (bf) r0 = r1 ; R0=0 R1=0")
__msg("6: (95) exit")
__msg("from 3 to 4")
-__msg("4: (77) r1 >>= 32 ; R1_w=0")
-__msg("5: (bf) r0 = r1 ; R0_w=0 R1_w=0")
+__msg("4: (77) r1 >>= 32 ; R1=0")
+__msg("5: (bf) r0 = r1 ; R0=0 R1=0")
__msg("6: (95) exit")
/* Verify that statements to randomize upper half of r1 had not been
* generated.
diff --git a/tools/testing/selftests/bpf/progs/verifier_sock.c b/tools/testing/selftests/bpf/progs/verifier_sock.c
index 0d5e56dffabb..2b4610b53382 100644
--- a/tools/testing/selftests/bpf/progs/verifier_sock.c
+++ b/tools/testing/selftests/bpf/progs/verifier_sock.c
@@ -1,14 +1,10 @@
// SPDX-License-Identifier: GPL-2.0
/* Converted from tools/testing/selftests/bpf/verifier/sock.c */
-#include <linux/bpf.h>
+#include "vmlinux.h"
#include <bpf/bpf_helpers.h>
#include "bpf_misc.h"
-#define sizeof_field(TYPE, MEMBER) sizeof((((TYPE *)0)->MEMBER))
-#define offsetofend(TYPE, MEMBER) \
- (offsetof(TYPE, MEMBER) + sizeof_field(TYPE, MEMBER))
-
struct {
__uint(type, BPF_MAP_TYPE_REUSEPORT_SOCKARRAY);
__uint(max_entries, 1);
@@ -1073,6 +1069,48 @@ int invalidate_pkt_pointers_from_global_func(struct __sk_buff *sk)
}
__noinline
+long xdp_pull_data2(struct xdp_md *x, __u32 len)
+{
+ return bpf_xdp_pull_data(x, len);
+}
+
+__noinline
+long xdp_pull_data1(struct xdp_md *x, __u32 len)
+{
+ return xdp_pull_data2(x, len);
+}
+
+/* global function calls bpf_xdp_pull_data(), which invalidates packet
+ * pointers established before global function call.
+ */
+SEC("xdp")
+__failure __msg("invalid mem access")
+int invalidate_xdp_pkt_pointers_from_global_func(struct xdp_md *x)
+{
+ int *p = (void *)(long)x->data;
+
+ if ((void *)(p + 1) > (void *)(long)x->data_end)
+ return XDP_DROP;
+ xdp_pull_data1(x, 0);
+ *p = 42; /* this is unsafe */
+ return XDP_PASS;
+}
+
+/* XDP packet changing kfunc calls invalidate packet pointers */
+SEC("xdp")
+__failure __msg("invalid mem access")
+int invalidate_xdp_pkt_pointers(struct xdp_md *x)
+{
+ int *p = (void *)(long)x->data;
+
+ if ((void *)(p + 1) > (void *)(long)x->data_end)
+ return XDP_DROP;
+ bpf_xdp_pull_data(x, 0);
+ *p = 42; /* this is unsafe */
+ return XDP_PASS;
+}
+
+__noinline
int tail_call(struct __sk_buff *sk)
{
bpf_tail_call_static(sk, &jmp_table, 0);
diff --git a/tools/testing/selftests/bpf/progs/verifier_spill_fill.c b/tools/testing/selftests/bpf/progs/verifier_spill_fill.c
index 1e5a511e8494..7a13dbd794b2 100644
--- a/tools/testing/selftests/bpf/progs/verifier_spill_fill.c
+++ b/tools/testing/selftests/bpf/progs/verifier_spill_fill.c
@@ -506,17 +506,17 @@ SEC("raw_tp")
__log_level(2)
__success
/* fp-8 is spilled IMPRECISE value zero (represented by a zero value fake reg) */
-__msg("2: (7a) *(u64 *)(r10 -8) = 0 ; R10=fp0 fp-8_w=0")
+__msg("2: (7a) *(u64 *)(r10 -8) = 0 ; R10=fp0 fp-8=0")
/* but fp-16 is spilled IMPRECISE zero const reg */
-__msg("4: (7b) *(u64 *)(r10 -16) = r0 ; R0_w=0 R10=fp0 fp-16_w=0")
+__msg("4: (7b) *(u64 *)(r10 -16) = r0 ; R0=0 R10=fp0 fp-16=0")
/* validate that assigning R2 from STACK_SPILL with zero value doesn't mark register
* precise immediately; if necessary, it will be marked precise later
*/
-__msg("6: (71) r2 = *(u8 *)(r10 -1) ; R2_w=0 R10=fp0 fp-8_w=0")
+__msg("6: (71) r2 = *(u8 *)(r10 -1) ; R2=0 R10=fp0 fp-8=0")
/* similarly, when R2 is assigned from spilled register, it is initially
* imprecise, but will be marked precise later once it is used in precise context
*/
-__msg("10: (71) r2 = *(u8 *)(r10 -9) ; R2_w=0 R10=fp0 fp-16_w=0")
+__msg("10: (71) r2 = *(u8 *)(r10 -9) ; R2=0 R10=fp0 fp-16=0")
__msg("11: (0f) r1 += r2")
__msg("mark_precise: frame0: last_idx 11 first_idx 0 subseq_idx -1")
__msg("mark_precise: frame0: regs=r2 stack= before 10: (71) r2 = *(u8 *)(r10 -9)")
@@ -598,7 +598,7 @@ __log_level(2)
__success
/* fp-4 is STACK_ZERO */
__msg("2: (62) *(u32 *)(r10 -4) = 0 ; R10=fp0 fp-8=0000????")
-__msg("4: (71) r2 = *(u8 *)(r10 -1) ; R2_w=0 R10=fp0 fp-8=0000????")
+__msg("4: (71) r2 = *(u8 *)(r10 -1) ; R2=0 R10=fp0 fp-8=0000????")
__msg("5: (0f) r1 += r2")
__msg("mark_precise: frame0: last_idx 5 first_idx 0 subseq_idx -1")
__msg("mark_precise: frame0: regs=r2 stack= before 4: (71) r2 = *(u8 *)(r10 -1)")
@@ -640,25 +640,25 @@ SEC("raw_tp")
__log_level(2) __flag(BPF_F_TEST_STATE_FREQ)
__success
/* make sure fp-8 is IMPRECISE fake register spill */
-__msg("3: (7a) *(u64 *)(r10 -8) = 1 ; R10=fp0 fp-8_w=1")
+__msg("3: (7a) *(u64 *)(r10 -8) = 1 ; R10=fp0 fp-8=1")
/* and fp-16 is spilled IMPRECISE const reg */
-__msg("5: (7b) *(u64 *)(r10 -16) = r0 ; R0_w=1 R10=fp0 fp-16_w=1")
+__msg("5: (7b) *(u64 *)(r10 -16) = r0 ; R0=1 R10=fp0 fp-16=1")
/* validate load from fp-8, which was initialized using BPF_ST_MEM */
-__msg("8: (79) r2 = *(u64 *)(r10 -8) ; R2_w=1 R10=fp0 fp-8=1")
+__msg("8: (79) r2 = *(u64 *)(r10 -8) ; R2=1 R10=fp0 fp-8=1")
__msg("9: (0f) r1 += r2")
__msg("mark_precise: frame0: last_idx 9 first_idx 7 subseq_idx -1")
__msg("mark_precise: frame0: regs=r2 stack= before 8: (79) r2 = *(u64 *)(r10 -8)")
__msg("mark_precise: frame0: regs= stack=-8 before 7: (bf) r1 = r6")
/* note, fp-8 is precise, fp-16 is not yet precise, we'll get there */
-__msg("mark_precise: frame0: parent state regs= stack=-8: R0_w=1 R1=ctx() R6_r=map_value(map=.data.two_byte_,ks=4,vs=2) R10=fp0 fp-8_rw=P1 fp-16_w=1")
+__msg("mark_precise: frame0: parent state regs= stack=-8: R0=1 R1=ctx() R6=map_value(map=.data.two_byte_,ks=4,vs=2) R10=fp0 fp-8=P1 fp-16=1")
__msg("mark_precise: frame0: last_idx 6 first_idx 3 subseq_idx 7")
__msg("mark_precise: frame0: regs= stack=-8 before 6: (05) goto pc+0")
__msg("mark_precise: frame0: regs= stack=-8 before 5: (7b) *(u64 *)(r10 -16) = r0")
__msg("mark_precise: frame0: regs= stack=-8 before 4: (b7) r0 = 1")
__msg("mark_precise: frame0: regs= stack=-8 before 3: (7a) *(u64 *)(r10 -8) = 1")
-__msg("10: R1_w=map_value(map=.data.two_byte_,ks=4,vs=2,off=1) R2_w=1")
+__msg("10: R1=map_value(map=.data.two_byte_,ks=4,vs=2,off=1) R2=1")
/* validate load from fp-16, which was initialized using BPF_STX_MEM */
-__msg("12: (79) r2 = *(u64 *)(r10 -16) ; R2_w=1 R10=fp0 fp-16=1")
+__msg("12: (79) r2 = *(u64 *)(r10 -16) ; R2=1 R10=fp0 fp-16=1")
__msg("13: (0f) r1 += r2")
__msg("mark_precise: frame0: last_idx 13 first_idx 7 subseq_idx -1")
__msg("mark_precise: frame0: regs=r2 stack= before 12: (79) r2 = *(u64 *)(r10 -16)")
@@ -668,12 +668,12 @@ __msg("mark_precise: frame0: regs= stack=-16 before 9: (0f) r1 += r2")
__msg("mark_precise: frame0: regs= stack=-16 before 8: (79) r2 = *(u64 *)(r10 -8)")
__msg("mark_precise: frame0: regs= stack=-16 before 7: (bf) r1 = r6")
/* now both fp-8 and fp-16 are precise, very good */
-__msg("mark_precise: frame0: parent state regs= stack=-16: R0_w=1 R1=ctx() R6_r=map_value(map=.data.two_byte_,ks=4,vs=2) R10=fp0 fp-8_rw=P1 fp-16_rw=P1")
+__msg("mark_precise: frame0: parent state regs= stack=-16: R0=1 R1=ctx() R6=map_value(map=.data.two_byte_,ks=4,vs=2) R10=fp0 fp-8=P1 fp-16=P1")
__msg("mark_precise: frame0: last_idx 6 first_idx 3 subseq_idx 7")
__msg("mark_precise: frame0: regs= stack=-16 before 6: (05) goto pc+0")
__msg("mark_precise: frame0: regs= stack=-16 before 5: (7b) *(u64 *)(r10 -16) = r0")
__msg("mark_precise: frame0: regs=r0 stack= before 4: (b7) r0 = 1")
-__msg("14: R1_w=map_value(map=.data.two_byte_,ks=4,vs=2,off=1) R2_w=1")
+__msg("14: R1=map_value(map=.data.two_byte_,ks=4,vs=2,off=1) R2=1")
__naked void stack_load_preserves_const_precision(void)
{
asm volatile (
@@ -719,22 +719,22 @@ __success
/* make sure fp-8 is 32-bit FAKE subregister spill */
__msg("3: (62) *(u32 *)(r10 -8) = 1 ; R10=fp0 fp-8=????1")
/* but fp-16 is spilled IMPRECISE zero const reg */
-__msg("5: (63) *(u32 *)(r10 -16) = r0 ; R0_w=1 R10=fp0 fp-16=????1")
+__msg("5: (63) *(u32 *)(r10 -16) = r0 ; R0=1 R10=fp0 fp-16=????1")
/* validate load from fp-8, which was initialized using BPF_ST_MEM */
-__msg("8: (61) r2 = *(u32 *)(r10 -8) ; R2_w=1 R10=fp0 fp-8=????1")
+__msg("8: (61) r2 = *(u32 *)(r10 -8) ; R2=1 R10=fp0 fp-8=????1")
__msg("9: (0f) r1 += r2")
__msg("mark_precise: frame0: last_idx 9 first_idx 7 subseq_idx -1")
__msg("mark_precise: frame0: regs=r2 stack= before 8: (61) r2 = *(u32 *)(r10 -8)")
__msg("mark_precise: frame0: regs= stack=-8 before 7: (bf) r1 = r6")
-__msg("mark_precise: frame0: parent state regs= stack=-8: R0_w=1 R1=ctx() R6_r=map_value(map=.data.two_byte_,ks=4,vs=2) R10=fp0 fp-8_r=????P1 fp-16=????1")
+__msg("mark_precise: frame0: parent state regs= stack=-8: R0=1 R1=ctx() R6=map_value(map=.data.two_byte_,ks=4,vs=2) R10=fp0 fp-8=????P1 fp-16=????1")
__msg("mark_precise: frame0: last_idx 6 first_idx 3 subseq_idx 7")
__msg("mark_precise: frame0: regs= stack=-8 before 6: (05) goto pc+0")
__msg("mark_precise: frame0: regs= stack=-8 before 5: (63) *(u32 *)(r10 -16) = r0")
__msg("mark_precise: frame0: regs= stack=-8 before 4: (b7) r0 = 1")
__msg("mark_precise: frame0: regs= stack=-8 before 3: (62) *(u32 *)(r10 -8) = 1")
-__msg("10: R1_w=map_value(map=.data.two_byte_,ks=4,vs=2,off=1) R2_w=1")
+__msg("10: R1=map_value(map=.data.two_byte_,ks=4,vs=2,off=1) R2=1")
/* validate load from fp-16, which was initialized using BPF_STX_MEM */
-__msg("12: (61) r2 = *(u32 *)(r10 -16) ; R2_w=1 R10=fp0 fp-16=????1")
+__msg("12: (61) r2 = *(u32 *)(r10 -16) ; R2=1 R10=fp0 fp-16=????1")
__msg("13: (0f) r1 += r2")
__msg("mark_precise: frame0: last_idx 13 first_idx 7 subseq_idx -1")
__msg("mark_precise: frame0: regs=r2 stack= before 12: (61) r2 = *(u32 *)(r10 -16)")
@@ -743,12 +743,12 @@ __msg("mark_precise: frame0: regs= stack=-16 before 10: (73) *(u8 *)(r1 +0) = r2
__msg("mark_precise: frame0: regs= stack=-16 before 9: (0f) r1 += r2")
__msg("mark_precise: frame0: regs= stack=-16 before 8: (61) r2 = *(u32 *)(r10 -8)")
__msg("mark_precise: frame0: regs= stack=-16 before 7: (bf) r1 = r6")
-__msg("mark_precise: frame0: parent state regs= stack=-16: R0_w=1 R1=ctx() R6_r=map_value(map=.data.two_byte_,ks=4,vs=2) R10=fp0 fp-8_r=????P1 fp-16_r=????P1")
+__msg("mark_precise: frame0: parent state regs= stack=-16: R0=1 R1=ctx() R6=map_value(map=.data.two_byte_,ks=4,vs=2) R10=fp0 fp-8=????P1 fp-16=????P1")
__msg("mark_precise: frame0: last_idx 6 first_idx 3 subseq_idx 7")
__msg("mark_precise: frame0: regs= stack=-16 before 6: (05) goto pc+0")
__msg("mark_precise: frame0: regs= stack=-16 before 5: (63) *(u32 *)(r10 -16) = r0")
__msg("mark_precise: frame0: regs=r0 stack= before 4: (b7) r0 = 1")
-__msg("14: R1_w=map_value(map=.data.two_byte_,ks=4,vs=2,off=1) R2_w=1")
+__msg("14: R1=map_value(map=.data.two_byte_,ks=4,vs=2,off=1) R2=1")
__naked void stack_load_preserves_const_precision_subreg(void)
{
asm volatile (
diff --git a/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c b/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c
index 9d415f7ce599..ac3e418c2a96 100644
--- a/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c
+++ b/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c
@@ -105,7 +105,7 @@ __msg("mark_precise: frame0: regs=r0 stack= before 4: (27) r0 *= 4")
__msg("mark_precise: frame0: regs=r0 stack= before 3: (57) r0 &= 3")
__msg("mark_precise: frame0: regs=r0 stack= before 10: (95) exit")
__msg("mark_precise: frame1: regs=r0 stack= before 9: (bf) r0 = (s8)r10")
-__msg("7: R0_w=scalar")
+__msg("7: R0=scalar")
__naked int fp_precise_subprog_result(void)
{
asm volatile (
@@ -141,7 +141,7 @@ __msg("mark_precise: frame1: regs=r0 stack= before 10: (bf) r0 = (s8)r1")
* anyways, at which point we'll break precision chain
*/
__msg("mark_precise: frame1: regs=r1 stack= before 9: (bf) r1 = r10")
-__msg("7: R0_w=scalar")
+__msg("7: R0=scalar")
__naked int sneaky_fp_precise_subprog_result(void)
{
asm volatile (
@@ -681,7 +681,7 @@ __msg("mark_precise: frame0: last_idx 10 first_idx 7 subseq_idx -1")
__msg("mark_precise: frame0: regs=r7 stack= before 9: (bf) r1 = r8")
__msg("mark_precise: frame0: regs=r7 stack= before 8: (27) r7 *= 4")
__msg("mark_precise: frame0: regs=r7 stack= before 7: (79) r7 = *(u64 *)(r10 -8)")
-__msg("mark_precise: frame0: parent state regs= stack=-8: R0_w=2 R6_w=1 R8_rw=map_value(map=.data.vals,ks=4,vs=16) R10=fp0 fp-8_rw=P1")
+__msg("mark_precise: frame0: parent state regs= stack=-8: R0=2 R6=1 R8=map_value(map=.data.vals,ks=4,vs=16) R10=fp0 fp-8=P1")
__msg("mark_precise: frame0: last_idx 18 first_idx 0 subseq_idx 7")
__msg("mark_precise: frame0: regs= stack=-8 before 18: (95) exit")
__msg("mark_precise: frame1: regs= stack= before 17: (0f) r0 += r2")
diff --git a/tools/testing/selftests/bpf/progs/verifier_var_off.c b/tools/testing/selftests/bpf/progs/verifier_var_off.c
index 1d36d01b746e..f345466bca68 100644
--- a/tools/testing/selftests/bpf/progs/verifier_var_off.c
+++ b/tools/testing/selftests/bpf/progs/verifier_var_off.c
@@ -114,8 +114,8 @@ __naked void stack_write_priv_vs_unpriv(void)
}
/* Similar to the previous test, but this time also perform a read from the
- * address written to with a variable offset. The read is allowed, showing that,
- * after a variable-offset write, a priviledged program can read the slots that
+ * address written to with a variable offet. The read is allowed, showing that,
+ * after a variable-offset write, a privileged program can read the slots that
* were in the range of that write (even if the verifier doesn't actually know if
* the slot being read was really written to or not.
*
@@ -157,7 +157,7 @@ __naked void stack_write_followed_by_read(void)
SEC("socket")
__description("variable-offset stack write clobbers spilled regs")
__failure
-/* In the priviledged case, dereferencing a spilled-and-then-filled
+/* In the privileged case, dereferencing a spilled-and-then-filled
* register is rejected because the previous variable offset stack
* write might have overwritten the spilled pointer (i.e. we lose track
* of the spilled register when we analyze the write).
diff --git a/tools/testing/selftests/bpf/test_kmods/Makefile b/tools/testing/selftests/bpf/test_kmods/Makefile
index d4e50c4509c9..63c4d3f6a12f 100644
--- a/tools/testing/selftests/bpf/test_kmods/Makefile
+++ b/tools/testing/selftests/bpf/test_kmods/Makefile
@@ -8,7 +8,7 @@ Q = @
endif
MODULES = bpf_testmod.ko bpf_test_no_cfi.ko bpf_test_modorder_x.ko \
- bpf_test_modorder_y.ko
+ bpf_test_modorder_y.ko bpf_test_rqspinlock.ko
$(foreach m,$(MODULES),$(eval obj-m += $(m:.ko=.o)))
diff --git a/tools/testing/selftests/bpf/test_kmods/bpf_test_rqspinlock.c b/tools/testing/selftests/bpf/test_kmods/bpf_test_rqspinlock.c
new file mode 100644
index 000000000000..769206fc70e4
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_kmods/bpf_test_rqspinlock.c
@@ -0,0 +1,209 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+#include <linux/sched.h>
+#include <linux/smp.h>
+#include <linux/delay.h>
+#include <linux/module.h>
+#include <linux/prandom.h>
+#include <asm/rqspinlock.h>
+#include <linux/perf_event.h>
+#include <linux/kthread.h>
+#include <linux/atomic.h>
+#include <linux/slab.h>
+
+static struct perf_event_attr hw_attr = {
+ .type = PERF_TYPE_HARDWARE,
+ .config = PERF_COUNT_HW_CPU_CYCLES,
+ .size = sizeof(struct perf_event_attr),
+ .pinned = 1,
+ .disabled = 1,
+ .sample_period = 100000,
+};
+
+static rqspinlock_t lock_a;
+static rqspinlock_t lock_b;
+
+static struct perf_event **rqsl_evts;
+static int rqsl_nevts;
+
+static bool test_ab = false;
+module_param(test_ab, bool, 0644);
+MODULE_PARM_DESC(test_ab, "Test ABBA situations instead of AA situations");
+
+static struct task_struct **rqsl_threads;
+static int rqsl_nthreads;
+static atomic_t rqsl_ready_cpus = ATOMIC_INIT(0);
+
+static int pause = 0;
+
+static bool nmi_locks_a(int cpu)
+{
+ return (cpu & 1) && test_ab;
+}
+
+static int rqspinlock_worker_fn(void *arg)
+{
+ int cpu = smp_processor_id();
+ unsigned long flags;
+ int ret;
+
+ if (cpu) {
+ atomic_inc(&rqsl_ready_cpus);
+
+ while (!kthread_should_stop()) {
+ if (READ_ONCE(pause)) {
+ msleep(1000);
+ continue;
+ }
+ if (nmi_locks_a(cpu))
+ ret = raw_res_spin_lock_irqsave(&lock_b, flags);
+ else
+ ret = raw_res_spin_lock_irqsave(&lock_a, flags);
+ mdelay(20);
+ if (nmi_locks_a(cpu) && !ret)
+ raw_res_spin_unlock_irqrestore(&lock_b, flags);
+ else if (!ret)
+ raw_res_spin_unlock_irqrestore(&lock_a, flags);
+ cpu_relax();
+ }
+ return 0;
+ }
+
+ while (!kthread_should_stop()) {
+ int expected = rqsl_nthreads > 0 ? rqsl_nthreads - 1 : 0;
+ int ready = atomic_read(&rqsl_ready_cpus);
+
+ if (ready == expected && !READ_ONCE(pause)) {
+ for (int i = 0; i < rqsl_nevts; i++)
+ perf_event_enable(rqsl_evts[i]);
+ pr_err("Waiting 5 secs to pause the test\n");
+ msleep(1000 * 5);
+ WRITE_ONCE(pause, 1);
+ pr_err("Paused the test\n");
+ } else {
+ msleep(1000);
+ cpu_relax();
+ }
+ }
+ return 0;
+}
+
+static void nmi_cb(struct perf_event *event, struct perf_sample_data *data,
+ struct pt_regs *regs)
+{
+ int cpu = smp_processor_id();
+ unsigned long flags;
+ int ret;
+
+ if (!cpu || READ_ONCE(pause))
+ return;
+
+ if (nmi_locks_a(cpu))
+ ret = raw_res_spin_lock_irqsave(&lock_a, flags);
+ else
+ ret = raw_res_spin_lock_irqsave(test_ab ? &lock_b : &lock_a, flags);
+
+ mdelay(10);
+
+ if (nmi_locks_a(cpu) && !ret)
+ raw_res_spin_unlock_irqrestore(&lock_a, flags);
+ else if (!ret)
+ raw_res_spin_unlock_irqrestore(test_ab ? &lock_b : &lock_a, flags);
+}
+
+static void free_rqsl_threads(void)
+{
+ int i;
+
+ if (rqsl_threads) {
+ for_each_online_cpu(i) {
+ if (rqsl_threads[i])
+ kthread_stop(rqsl_threads[i]);
+ }
+ kfree(rqsl_threads);
+ }
+}
+
+static void free_rqsl_evts(void)
+{
+ int i;
+
+ if (rqsl_evts) {
+ for (i = 0; i < rqsl_nevts; i++) {
+ if (rqsl_evts[i])
+ perf_event_release_kernel(rqsl_evts[i]);
+ }
+ kfree(rqsl_evts);
+ }
+}
+
+static int bpf_test_rqspinlock_init(void)
+{
+ int i, ret;
+ int ncpus = num_online_cpus();
+
+ pr_err("Mode = %s\n", test_ab ? "ABBA" : "AA");
+
+ if (ncpus < 3)
+ return -ENOTSUPP;
+
+ raw_res_spin_lock_init(&lock_a);
+ raw_res_spin_lock_init(&lock_b);
+
+ rqsl_evts = kcalloc(ncpus - 1, sizeof(*rqsl_evts), GFP_KERNEL);
+ if (!rqsl_evts)
+ return -ENOMEM;
+ rqsl_nevts = ncpus - 1;
+
+ for (i = 1; i < ncpus; i++) {
+ struct perf_event *e;
+
+ e = perf_event_create_kernel_counter(&hw_attr, i, NULL, nmi_cb, NULL);
+ if (IS_ERR(e)) {
+ ret = PTR_ERR(e);
+ goto err_perf_events;
+ }
+ rqsl_evts[i - 1] = e;
+ }
+
+ rqsl_threads = kcalloc(ncpus, sizeof(*rqsl_threads), GFP_KERNEL);
+ if (!rqsl_threads) {
+ ret = -ENOMEM;
+ goto err_perf_events;
+ }
+ rqsl_nthreads = ncpus;
+
+ for_each_online_cpu(i) {
+ struct task_struct *t;
+
+ t = kthread_create(rqspinlock_worker_fn, NULL, "rqsl_w/%d", i);
+ if (IS_ERR(t)) {
+ ret = PTR_ERR(t);
+ goto err_threads_create;
+ }
+ kthread_bind(t, i);
+ rqsl_threads[i] = t;
+ wake_up_process(t);
+ }
+ return 0;
+
+err_threads_create:
+ free_rqsl_threads();
+err_perf_events:
+ free_rqsl_evts();
+ return ret;
+}
+
+module_init(bpf_test_rqspinlock_init);
+
+static void bpf_test_rqspinlock_exit(void)
+{
+ free_rqsl_threads();
+ free_rqsl_evts();
+}
+
+module_exit(bpf_test_rqspinlock_exit);
+
+MODULE_AUTHOR("Kumar Kartikeya Dwivedi");
+MODULE_DESCRIPTION("BPF rqspinlock stress test module");
+MODULE_LICENSE("GPL");
diff --git a/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c b/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c
index e9e918cdf31f..8074bc5f6f20 100644
--- a/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c
+++ b/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c
@@ -62,6 +62,18 @@ struct bpf_testmod_struct_arg_5 {
long d;
};
+union bpf_testmod_union_arg_1 {
+ char a;
+ short b;
+ struct bpf_testmod_struct_arg_1 arg;
+};
+
+union bpf_testmod_union_arg_2 {
+ int a;
+ long b;
+ struct bpf_testmod_struct_arg_2 arg;
+};
+
__bpf_hook_start();
noinline int
@@ -129,6 +141,20 @@ bpf_testmod_test_struct_arg_9(u64 a, void *b, short c, int d, void *e, char f,
}
noinline int
+bpf_testmod_test_union_arg_1(union bpf_testmod_union_arg_1 a, int b, int c)
+{
+ bpf_testmod_test_struct_arg_result = a.arg.a + b + c;
+ return bpf_testmod_test_struct_arg_result;
+}
+
+noinline int
+bpf_testmod_test_union_arg_2(int a, union bpf_testmod_union_arg_2 b)
+{
+ bpf_testmod_test_struct_arg_result = a + b.arg.a + b.arg.b;
+ return bpf_testmod_test_struct_arg_result;
+}
+
+noinline int
bpf_testmod_test_arg_ptr_to_struct(struct bpf_testmod_struct_arg_1 *a) {
bpf_testmod_test_struct_arg_result = a->a;
return bpf_testmod_test_struct_arg_result;
@@ -218,6 +244,16 @@ __bpf_kfunc void bpf_kfunc_rcu_task_test(struct task_struct *ptr)
{
}
+__bpf_kfunc struct task_struct *bpf_kfunc_ret_rcu_test(void)
+{
+ return NULL;
+}
+
+__bpf_kfunc int *bpf_kfunc_ret_rcu_test_nostruct(int rdonly_buf_size)
+{
+ return NULL;
+}
+
__bpf_kfunc struct bpf_testmod_ctx *
bpf_testmod_ctx_create(int *err)
{
@@ -398,6 +434,8 @@ bpf_testmod_test_read(struct file *file, struct kobject *kobj,
struct bpf_testmod_struct_arg_3 *struct_arg3;
struct bpf_testmod_struct_arg_4 struct_arg4 = {21, 22};
struct bpf_testmod_struct_arg_5 struct_arg5 = {23, 24, 25, 26};
+ union bpf_testmod_union_arg_1 union_arg1 = { .arg = {1} };
+ union bpf_testmod_union_arg_2 union_arg2 = { .arg = {2, 3} };
int i = 1;
while (bpf_testmod_return_ptr(i))
@@ -415,6 +453,9 @@ bpf_testmod_test_read(struct file *file, struct kobject *kobj,
(void)bpf_testmod_test_struct_arg_9(16, (void *)17, 18, 19, (void *)20,
21, 22, struct_arg5, 27);
+ (void)bpf_testmod_test_union_arg_1(union_arg1, 4, 5);
+ (void)bpf_testmod_test_union_arg_2(6, union_arg2);
+
(void)bpf_testmod_test_arg_ptr_to_struct(&struct_arg1_2);
(void)trace_bpf_testmod_test_raw_tp_null_tp(NULL);
@@ -501,14 +542,20 @@ static struct bin_attribute bin_attr_bpf_testmod_file __ro_after_init = {
#ifdef __x86_64__
static int
+uprobe_handler(struct uprobe_consumer *self, struct pt_regs *regs, __u64 *data)
+{
+ regs->cx = 0x87654321feebdaed;
+ return 0;
+}
+
+static int
uprobe_ret_handler(struct uprobe_consumer *self, unsigned long func,
struct pt_regs *regs, __u64 *data)
{
regs->ax = 0x12345678deadbeef;
- regs->cx = 0x87654321feebdaed;
regs->r11 = (u64) -1;
- return true;
+ return 0;
}
struct testmod_uprobe {
@@ -520,6 +567,7 @@ struct testmod_uprobe {
static DEFINE_MUTEX(testmod_uprobe_mutex);
static struct testmod_uprobe uprobe = {
+ .consumer.handler = uprobe_handler,
.consumer.ret_handler = uprobe_ret_handler,
};
@@ -623,6 +671,8 @@ BTF_ID_FLAGS(func, bpf_kfunc_trusted_vma_test, KF_TRUSTED_ARGS)
BTF_ID_FLAGS(func, bpf_kfunc_trusted_task_test, KF_TRUSTED_ARGS)
BTF_ID_FLAGS(func, bpf_kfunc_trusted_num_test, KF_TRUSTED_ARGS)
BTF_ID_FLAGS(func, bpf_kfunc_rcu_task_test, KF_RCU)
+BTF_ID_FLAGS(func, bpf_kfunc_ret_rcu_test, KF_RET_NULL | KF_RCU_PROTECTED)
+BTF_ID_FLAGS(func, bpf_kfunc_ret_rcu_test_nostruct, KF_RET_NULL | KF_RCU_PROTECTED)
BTF_ID_FLAGS(func, bpf_testmod_ctx_create, KF_ACQUIRE | KF_RET_NULL)
BTF_ID_FLAGS(func, bpf_testmod_ctx_release, KF_RELEASE)
BTF_ID_FLAGS(func, bpf_testmod_ops3_call_test_1)
@@ -1057,6 +1107,8 @@ __bpf_kfunc int bpf_kfunc_st_ops_inc10(struct st_ops_args *args)
return args->a;
}
+__bpf_kfunc int bpf_kfunc_multi_st_ops_test_1(struct st_ops_args *args, u32 id);
+
BTF_KFUNCS_START(bpf_testmod_check_kfunc_ids)
BTF_ID_FLAGS(func, bpf_testmod_test_mod_kfunc)
BTF_ID_FLAGS(func, bpf_kfunc_call_test1)
@@ -1097,6 +1149,7 @@ BTF_ID_FLAGS(func, bpf_kfunc_st_ops_test_prologue, KF_TRUSTED_ARGS | KF_SLEEPABL
BTF_ID_FLAGS(func, bpf_kfunc_st_ops_test_epilogue, KF_TRUSTED_ARGS | KF_SLEEPABLE)
BTF_ID_FLAGS(func, bpf_kfunc_st_ops_test_pro_epilogue, KF_TRUSTED_ARGS | KF_SLEEPABLE)
BTF_ID_FLAGS(func, bpf_kfunc_st_ops_inc10, KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_kfunc_multi_st_ops_test_1, KF_TRUSTED_ARGS)
BTF_KFUNCS_END(bpf_testmod_check_kfunc_ids)
static int bpf_testmod_ops_init(struct btf *btf)
@@ -1528,6 +1581,114 @@ static struct bpf_struct_ops testmod_st_ops = {
.owner = THIS_MODULE,
};
+struct hlist_head multi_st_ops_list;
+static DEFINE_SPINLOCK(multi_st_ops_lock);
+
+static int multi_st_ops_init(struct btf *btf)
+{
+ spin_lock_init(&multi_st_ops_lock);
+ INIT_HLIST_HEAD(&multi_st_ops_list);
+
+ return 0;
+}
+
+static int multi_st_ops_init_member(const struct btf_type *t,
+ const struct btf_member *member,
+ void *kdata, const void *udata)
+{
+ return 0;
+}
+
+static struct bpf_testmod_multi_st_ops *multi_st_ops_find_nolock(u32 id)
+{
+ struct bpf_testmod_multi_st_ops *st_ops;
+
+ hlist_for_each_entry(st_ops, &multi_st_ops_list, node) {
+ if (st_ops->id == id)
+ return st_ops;
+ }
+
+ return NULL;
+}
+
+int bpf_kfunc_multi_st_ops_test_1(struct st_ops_args *args, u32 id)
+{
+ struct bpf_testmod_multi_st_ops *st_ops;
+ unsigned long flags;
+ int ret = -1;
+
+ spin_lock_irqsave(&multi_st_ops_lock, flags);
+ st_ops = multi_st_ops_find_nolock(id);
+ if (st_ops)
+ ret = st_ops->test_1(args);
+ spin_unlock_irqrestore(&multi_st_ops_lock, flags);
+
+ return ret;
+}
+
+static int multi_st_ops_reg(void *kdata, struct bpf_link *link)
+{
+ struct bpf_testmod_multi_st_ops *st_ops =
+ (struct bpf_testmod_multi_st_ops *)kdata;
+ unsigned long flags;
+ int err = 0;
+ u32 id;
+
+ if (!st_ops->test_1)
+ return -EINVAL;
+
+ id = bpf_struct_ops_id(kdata);
+
+ spin_lock_irqsave(&multi_st_ops_lock, flags);
+ if (multi_st_ops_find_nolock(id)) {
+ pr_err("multi_st_ops(id:%d) has already been registered\n", id);
+ err = -EEXIST;
+ goto unlock;
+ }
+
+ st_ops->id = id;
+ hlist_add_head(&st_ops->node, &multi_st_ops_list);
+unlock:
+ spin_unlock_irqrestore(&multi_st_ops_lock, flags);
+
+ return err;
+}
+
+static void multi_st_ops_unreg(void *kdata, struct bpf_link *link)
+{
+ struct bpf_testmod_multi_st_ops *st_ops;
+ unsigned long flags;
+ u32 id;
+
+ id = bpf_struct_ops_id(kdata);
+
+ spin_lock_irqsave(&multi_st_ops_lock, flags);
+ st_ops = multi_st_ops_find_nolock(id);
+ if (st_ops)
+ hlist_del(&st_ops->node);
+ spin_unlock_irqrestore(&multi_st_ops_lock, flags);
+}
+
+static int bpf_testmod_multi_st_ops__test_1(struct st_ops_args *args)
+{
+ return 0;
+}
+
+static struct bpf_testmod_multi_st_ops multi_st_ops_cfi_stubs = {
+ .test_1 = bpf_testmod_multi_st_ops__test_1,
+};
+
+struct bpf_struct_ops testmod_multi_st_ops = {
+ .verifier_ops = &bpf_testmod_verifier_ops,
+ .init = multi_st_ops_init,
+ .init_member = multi_st_ops_init_member,
+ .reg = multi_st_ops_reg,
+ .unreg = multi_st_ops_unreg,
+ .cfi_stubs = &multi_st_ops_cfi_stubs,
+ .name = "bpf_testmod_multi_st_ops",
+ .owner = THIS_MODULE,
+};
+
extern int bpf_fentry_test1(int a);
static int bpf_testmod_init(void)
@@ -1550,6 +1711,7 @@ static int bpf_testmod_init(void)
ret = ret ?: register_bpf_struct_ops(&bpf_testmod_ops2, bpf_testmod_ops2);
ret = ret ?: register_bpf_struct_ops(&bpf_testmod_ops3, bpf_testmod_ops3);
ret = ret ?: register_bpf_struct_ops(&testmod_st_ops, bpf_testmod_st_ops);
+ ret = ret ?: register_bpf_struct_ops(&testmod_multi_st_ops, bpf_testmod_multi_st_ops);
ret = ret ?: register_btf_id_dtor_kfuncs(bpf_testmod_dtors,
ARRAY_SIZE(bpf_testmod_dtors),
THIS_MODULE);
diff --git a/tools/testing/selftests/bpf/test_kmods/bpf_testmod.h b/tools/testing/selftests/bpf/test_kmods/bpf_testmod.h
index c9fab51f16e2..f6e492f9d042 100644
--- a/tools/testing/selftests/bpf/test_kmods/bpf_testmod.h
+++ b/tools/testing/selftests/bpf/test_kmods/bpf_testmod.h
@@ -116,4 +116,10 @@ struct bpf_testmod_st_ops {
struct module *owner;
};
+struct bpf_testmod_multi_st_ops {
+ int (*test_1)(struct st_ops_args *args);
+ struct hlist_node node;
+ int id;
+};
+
#endif /* _BPF_TESTMOD_H */
diff --git a/tools/testing/selftests/bpf/test_kmods/bpf_testmod_kfunc.h b/tools/testing/selftests/bpf/test_kmods/bpf_testmod_kfunc.h
index b58817938deb..4df6fa6a92cb 100644
--- a/tools/testing/selftests/bpf/test_kmods/bpf_testmod_kfunc.h
+++ b/tools/testing/selftests/bpf/test_kmods/bpf_testmod_kfunc.h
@@ -158,5 +158,9 @@ void bpf_kfunc_trusted_vma_test(struct vm_area_struct *ptr) __ksym;
void bpf_kfunc_trusted_task_test(struct task_struct *ptr) __ksym;
void bpf_kfunc_trusted_num_test(int *ptr) __ksym;
void bpf_kfunc_rcu_task_test(struct task_struct *ptr) __ksym;
+struct task_struct *bpf_kfunc_ret_rcu_test(void) __ksym;
+int *bpf_kfunc_ret_rcu_test_nostruct(int rdonly_buf_size) __ksym;
+
+int bpf_kfunc_multi_st_ops_test_1(struct st_ops_args *args, u32 id) __ksym;
#endif /* _BPF_TESTMOD_KFUNC_H */
diff --git a/tools/testing/selftests/bpf/test_lirc_mode2_user.c b/tools/testing/selftests/bpf/test_lirc_mode2_user.c
index 4694422aa76c..88e4aeab21b7 100644
--- a/tools/testing/selftests/bpf/test_lirc_mode2_user.c
+++ b/tools/testing/selftests/bpf/test_lirc_mode2_user.c
@@ -74,7 +74,7 @@ int main(int argc, char **argv)
/* Let's try detach it before it was ever attached */
ret = bpf_prog_detach2(progfd, lircfd, BPF_LIRC_MODE2);
- if (ret != -1 || errno != ENOENT) {
+ if (ret != -ENOENT) {
printf("bpf_prog_detach2 not attached should fail: %m\n");
return 1;
}
diff --git a/tools/testing/selftests/bpf/test_loader.c b/tools/testing/selftests/bpf/test_loader.c
index 78423cf89e01..74ecc281bb8c 100644
--- a/tools/testing/selftests/bpf/test_loader.c
+++ b/tools/testing/selftests/bpf/test_loader.c
@@ -2,7 +2,6 @@
/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */
#include <linux/capability.h>
#include <stdlib.h>
-#include <regex.h>
#include <test_progs.h>
#include <bpf/btf.h>
@@ -20,10 +19,12 @@
#define TEST_TAG_EXPECT_FAILURE "comment:test_expect_failure"
#define TEST_TAG_EXPECT_SUCCESS "comment:test_expect_success"
#define TEST_TAG_EXPECT_MSG_PFX "comment:test_expect_msg="
+#define TEST_TAG_EXPECT_NOT_MSG_PFX "comment:test_expect_not_msg="
#define TEST_TAG_EXPECT_XLATED_PFX "comment:test_expect_xlated="
#define TEST_TAG_EXPECT_FAILURE_UNPRIV "comment:test_expect_failure_unpriv"
#define TEST_TAG_EXPECT_SUCCESS_UNPRIV "comment:test_expect_success_unpriv"
#define TEST_TAG_EXPECT_MSG_PFX_UNPRIV "comment:test_expect_msg_unpriv="
+#define TEST_TAG_EXPECT_NOT_MSG_PFX_UNPRIV "comment:test_expect_not_msg_unpriv="
#define TEST_TAG_EXPECT_XLATED_PFX_UNPRIV "comment:test_expect_xlated_unpriv="
#define TEST_TAG_LOG_LEVEL_PFX "comment:test_log_level="
#define TEST_TAG_PROG_FLAGS_PFX "comment:test_prog_flags="
@@ -38,6 +39,10 @@
#define TEST_TAG_JITED_PFX_UNPRIV "comment:test_jited_unpriv="
#define TEST_TAG_CAPS_UNPRIV "comment:test_caps_unpriv="
#define TEST_TAG_LOAD_MODE_PFX "comment:load_mode="
+#define TEST_TAG_EXPECT_STDERR_PFX "comment:test_expect_stderr="
+#define TEST_TAG_EXPECT_STDERR_PFX_UNPRIV "comment:test_expect_stderr_unpriv="
+#define TEST_TAG_EXPECT_STDOUT_PFX "comment:test_expect_stdout="
+#define TEST_TAG_EXPECT_STDOUT_PFX_UNPRIV "comment:test_expect_stdout_unpriv="
/* Warning: duplicated in bpf_misc.h */
#define POINTER_VALUE 0xbadcafe
@@ -61,24 +66,14 @@ enum load_mode {
NO_JITED = 1 << 1,
};
-struct expect_msg {
- const char *substr; /* substring match */
- regex_t regex;
- bool is_regex;
- bool on_next_line;
-};
-
-struct expected_msgs {
- struct expect_msg *patterns;
- size_t cnt;
-};
-
struct test_subspec {
char *name;
bool expect_failure;
struct expected_msgs expect_msgs;
struct expected_msgs expect_xlated;
struct expected_msgs jited;
+ struct expected_msgs stderr;
+ struct expected_msgs stdout;
int retval;
bool execute;
__u64 caps;
@@ -139,6 +134,10 @@ static void free_test_spec(struct test_spec *spec)
free_msgs(&spec->unpriv.expect_xlated);
free_msgs(&spec->priv.jited);
free_msgs(&spec->unpriv.jited);
+ free_msgs(&spec->unpriv.stderr);
+ free_msgs(&spec->priv.stderr);
+ free_msgs(&spec->unpriv.stdout);
+ free_msgs(&spec->priv.stdout);
free(spec->priv.name);
free(spec->unpriv.name);
@@ -206,7 +205,8 @@ static int compile_regex(const char *pattern, regex_t *regex)
return 0;
}
-static int __push_msg(const char *pattern, bool on_next_line, struct expected_msgs *msgs)
+static int __push_msg(const char *pattern, bool on_next_line, bool negative,
+ struct expected_msgs *msgs)
{
struct expect_msg *msg;
void *tmp;
@@ -222,6 +222,7 @@ static int __push_msg(const char *pattern, bool on_next_line, struct expected_ms
msg = &msgs->patterns[msgs->cnt];
msg->on_next_line = on_next_line;
msg->substr = pattern;
+ msg->negative = negative;
msg->is_regex = false;
if (strstr(pattern, "{{")) {
err = compile_regex(pattern, &msg->regex);
@@ -240,16 +241,16 @@ static int clone_msgs(struct expected_msgs *from, struct expected_msgs *to)
for (i = 0; i < from->cnt; i++) {
msg = &from->patterns[i];
- err = __push_msg(msg->substr, msg->on_next_line, to);
+ err = __push_msg(msg->substr, msg->on_next_line, msg->negative, to);
if (err)
return err;
}
return 0;
}
-static int push_msg(const char *substr, struct expected_msgs *msgs)
+static int push_msg(const char *substr, bool negative, struct expected_msgs *msgs)
{
- return __push_msg(substr, false, msgs);
+ return __push_msg(substr, false, negative, msgs);
}
static int push_disasm_msg(const char *regex_str, bool *on_next_line, struct expected_msgs *msgs)
@@ -260,7 +261,7 @@ static int push_disasm_msg(const char *regex_str, bool *on_next_line, struct exp
*on_next_line = false;
return 0;
}
- err = __push_msg(regex_str, *on_next_line, msgs);
+ err = __push_msg(regex_str, *on_next_line, false, msgs);
if (err)
return err;
*on_next_line = true;
@@ -374,6 +375,7 @@ enum arch {
ARCH_X86_64 = 0x2,
ARCH_ARM64 = 0x4,
ARCH_RISCV64 = 0x8,
+ ARCH_S390X = 0x10,
};
static int get_current_arch(void)
@@ -384,6 +386,8 @@ static int get_current_arch(void)
return ARCH_ARM64;
#elif defined(__riscv) && __riscv_xlen == 64
return ARCH_RISCV64;
+#elif defined(__s390x__)
+ return ARCH_S390X;
#endif
return ARCH_UNKNOWN;
}
@@ -404,6 +408,10 @@ static int parse_test_spec(struct test_loader *tester,
bool xlated_on_next_line = true;
bool unpriv_jit_on_next_line;
bool jit_on_next_line;
+ bool stderr_on_next_line = true;
+ bool unpriv_stderr_on_next_line = true;
+ bool stdout_on_next_line = true;
+ bool unpriv_stdout_on_next_line = true;
bool collect_jit = false;
int func_id, i, err = 0;
u32 arch_mask = 0;
@@ -465,12 +473,22 @@ static int parse_test_spec(struct test_loader *tester,
spec->auxiliary = true;
spec->mode_mask |= UNPRIV;
} else if ((msg = skip_dynamic_pfx(s, TEST_TAG_EXPECT_MSG_PFX))) {
- err = push_msg(msg, &spec->priv.expect_msgs);
+ err = push_msg(msg, false, &spec->priv.expect_msgs);
+ if (err)
+ goto cleanup;
+ spec->mode_mask |= PRIV;
+ } else if ((msg = skip_dynamic_pfx(s, TEST_TAG_EXPECT_NOT_MSG_PFX))) {
+ err = push_msg(msg, true, &spec->priv.expect_msgs);
if (err)
goto cleanup;
spec->mode_mask |= PRIV;
} else if ((msg = skip_dynamic_pfx(s, TEST_TAG_EXPECT_MSG_PFX_UNPRIV))) {
- err = push_msg(msg, &spec->unpriv.expect_msgs);
+ err = push_msg(msg, false, &spec->unpriv.expect_msgs);
+ if (err)
+ goto cleanup;
+ spec->mode_mask |= UNPRIV;
+ } else if ((msg = skip_dynamic_pfx(s, TEST_TAG_EXPECT_NOT_MSG_PFX_UNPRIV))) {
+ err = push_msg(msg, true, &spec->unpriv.expect_msgs);
if (err)
goto cleanup;
spec->mode_mask |= UNPRIV;
@@ -565,8 +583,10 @@ static int parse_test_spec(struct test_loader *tester,
arch = ARCH_ARM64;
} else if (strcmp(val, "RISCV64") == 0) {
arch = ARCH_RISCV64;
+ } else if (strcmp(val, "s390x") == 0) {
+ arch = ARCH_S390X;
} else {
- PRINT_FAIL("bad arch spec: '%s'", val);
+ PRINT_FAIL("bad arch spec: '%s'\n", val);
err = -EINVAL;
goto cleanup;
}
@@ -593,6 +613,26 @@ static int parse_test_spec(struct test_loader *tester,
err = -EINVAL;
goto cleanup;
}
+ } else if ((msg = skip_dynamic_pfx(s, TEST_TAG_EXPECT_STDERR_PFX))) {
+ err = push_disasm_msg(msg, &stderr_on_next_line,
+ &spec->priv.stderr);
+ if (err)
+ goto cleanup;
+ } else if ((msg = skip_dynamic_pfx(s, TEST_TAG_EXPECT_STDERR_PFX_UNPRIV))) {
+ err = push_disasm_msg(msg, &unpriv_stderr_on_next_line,
+ &spec->unpriv.stderr);
+ if (err)
+ goto cleanup;
+ } else if ((msg = skip_dynamic_pfx(s, TEST_TAG_EXPECT_STDOUT_PFX))) {
+ err = push_disasm_msg(msg, &stdout_on_next_line,
+ &spec->priv.stdout);
+ if (err)
+ goto cleanup;
+ } else if ((msg = skip_dynamic_pfx(s, TEST_TAG_EXPECT_STDOUT_PFX_UNPRIV))) {
+ err = push_disasm_msg(msg, &unpriv_stdout_on_next_line,
+ &spec->unpriv.stdout);
+ if (err)
+ goto cleanup;
}
}
@@ -646,6 +686,10 @@ static int parse_test_spec(struct test_loader *tester,
clone_msgs(&spec->priv.expect_xlated, &spec->unpriv.expect_xlated);
if (spec->unpriv.jited.cnt == 0)
clone_msgs(&spec->priv.jited, &spec->unpriv.jited);
+ if (spec->unpriv.stderr.cnt == 0)
+ clone_msgs(&spec->priv.stderr, &spec->unpriv.stderr);
+ if (spec->unpriv.stdout.cnt == 0)
+ clone_msgs(&spec->priv.stdout, &spec->unpriv.stdout);
}
spec->valid = true;
@@ -707,44 +751,155 @@ static void emit_jited(const char *jited, bool force)
fprintf(stdout, "JITED:\n=============\n%s=============\n", jited);
}
-static void validate_msgs(char *log_buf, struct expected_msgs *msgs,
- void (*emit_fn)(const char *buf, bool force))
+static void emit_stderr(const char *stderr, bool force)
{
- const char *log = log_buf, *prev_match;
+ if (!force && env.verbosity == VERBOSE_NONE)
+ return;
+ fprintf(stdout, "STDERR:\n=============\n%s=============\n", stderr);
+}
+
+static void emit_stdout(const char *bpf_stdout, bool force)
+{
+ if (!force && env.verbosity == VERBOSE_NONE)
+ return;
+ fprintf(stdout, "STDOUT:\n=============\n%s=============\n", bpf_stdout);
+}
+
+static const char *match_msg(struct expect_msg *msg, const char **log)
+{
+ const char *match = NULL;
regmatch_t reg_match[1];
- int prev_match_line;
- int match_line;
- int i, j, err;
+ int err;
+
+ if (!msg->is_regex) {
+ match = strstr(*log, msg->substr);
+ if (match)
+ *log = match + strlen(msg->substr);
+ } else {
+ err = regexec(&msg->regex, *log, 1, reg_match, 0);
+ if (err == 0) {
+ match = *log + reg_match[0].rm_so;
+ *log += reg_match[0].rm_eo;
+ }
+ }
+ return match;
+}
+
+static int count_lines(const char *start, const char *end)
+{
+ const char *tmp;
+ int n = 0;
+
+ for (tmp = start; tmp < end; ++tmp)
+ if (*tmp == '\n')
+ n++;
+ return n;
+}
+
+struct match {
+ const char *start;
+ const char *end;
+ int line;
+};
+
+/*
+ * Positive messages are matched sequentially, each next message
+ * is looked for starting from the end of a previous matched one.
+ */
+static void match_positive_msgs(const char *log, struct expected_msgs *msgs, struct match *matches)
+{
+ const char *prev_match;
+ int i, line;
- prev_match_line = -1;
- match_line = 0;
prev_match = log;
+ line = 0;
for (i = 0; i < msgs->cnt; i++) {
struct expect_msg *msg = &msgs->patterns[i];
- const char *match = NULL, *pat_status;
- bool wrong_line = false;
-
- if (!msg->is_regex) {
- match = strstr(log, msg->substr);
- if (match)
- log = match + strlen(msg->substr);
- } else {
- err = regexec(&msg->regex, log, 1, reg_match, 0);
- if (err == 0) {
- match = log + reg_match[0].rm_so;
- log += reg_match[0].rm_eo;
+ const char *match = NULL;
+
+ if (msg->negative)
+ continue;
+
+ match = match_msg(msg, &log);
+ if (match) {
+ line += count_lines(prev_match, match);
+ matches[i].start = match;
+ matches[i].end = log;
+ matches[i].line = line;
+ prev_match = match;
+ }
+ }
+}
+
+/*
+ * Each negative messages N located between positive messages P1 and P2
+ * is matched in the span P1.end .. P2.start. Consequently, negative messages
+ * are unordered within the span.
+ */
+static void match_negative_msgs(const char *log, struct expected_msgs *msgs, struct match *matches)
+{
+ const char *start = log, *end, *next, *match;
+ const char *log_end = log + strlen(log);
+ int i, j, next_positive;
+
+ for (i = 0; i < msgs->cnt; i++) {
+ struct expect_msg *msg = &msgs->patterns[i];
+
+ /* positive message bumps span start */
+ if (!msg->negative) {
+ start = matches[i].end ?: start;
+ continue;
+ }
+
+ /* count stride of negative patterns and adjust span end */
+ end = log_end;
+ for (next_positive = i + 1; next_positive < msgs->cnt; next_positive++) {
+ if (!msgs->patterns[next_positive].negative) {
+ end = matches[next_positive].start;
+ break;
}
}
- if (match) {
- for (; prev_match < match; ++prev_match)
- if (*prev_match == '\n')
- ++match_line;
- wrong_line = msg->on_next_line && prev_match_line >= 0 &&
- prev_match_line + 1 != match_line;
+ /* try matching negative messages within identified span */
+ for (j = i; j < next_positive; j++) {
+ next = start;
+ match = match_msg(msg, &next);
+ if (match && next <= end) {
+ matches[j].start = match;
+ matches[j].end = next;
+ }
}
- if (!match || wrong_line) {
+ /* -1 to account for i++ */
+ i = next_positive - 1;
+ }
+}
+
+void validate_msgs(const char *log_buf, struct expected_msgs *msgs,
+ void (*emit_fn)(const char *buf, bool force))
+{
+ struct match matches[msgs->cnt];
+ struct match *prev_match = NULL;
+ int i, j;
+
+ memset(matches, 0, sizeof(*matches) * msgs->cnt);
+ match_positive_msgs(log_buf, msgs, matches);
+ match_negative_msgs(log_buf, msgs, matches);
+
+ for (i = 0; i < msgs->cnt; i++) {
+ struct expect_msg *msg = &msgs->patterns[i];
+ struct match *match = &matches[i];
+ const char *pat_status;
+ bool unexpected;
+ bool wrong_line;
+ bool no_match;
+
+ no_match = !msg->negative && !match->start;
+ wrong_line = !msg->negative &&
+ msg->on_next_line &&
+ prev_match && prev_match->line + 1 != match->line;
+ unexpected = msg->negative && match->start;
+ if (no_match || wrong_line || unexpected) {
PRINT_FAIL("expect_msg\n");
if (env.verbosity == VERBOSE_NONE)
emit_fn(log_buf, true /*force*/);
@@ -754,8 +909,10 @@ static void validate_msgs(char *log_buf, struct expected_msgs *msgs,
pat_status = "MATCHED ";
else if (wrong_line)
pat_status = "WRONG LINE";
- else
+ else if (no_match)
pat_status = "EXPECTED ";
+ else
+ pat_status = "UNEXPECTED";
msg = &msgs->patterns[j];
fprintf(stderr, "%s %s: '%s'\n",
pat_status,
@@ -765,12 +922,13 @@ static void validate_msgs(char *log_buf, struct expected_msgs *msgs,
if (wrong_line) {
fprintf(stderr,
"expecting match at line %d, actual match is at line %d\n",
- prev_match_line + 1, match_line);
+ prev_match->line + 1, match->line);
}
break;
}
- prev_match_line = match_line;
+ if (!msg->negative)
+ prev_match = match;
}
}
@@ -929,6 +1087,19 @@ out:
return err;
}
+/* Read the bpf stream corresponding to the stream_id */
+static int get_stream(int stream_id, int prog_fd, char *text, size_t text_sz)
+{
+ LIBBPF_OPTS(bpf_prog_stream_read_opts, ropts);
+ int ret;
+
+ ret = bpf_prog_stream_read(prog_fd, stream_id, text, text_sz, &ropts);
+ ASSERT_GT(ret, 0, "stream read");
+ text[ret] = '\0';
+
+ return ret;
+}
+
/* this function is forced noinline and has short generic name to look better
* in test_progs output (in case of a failure)
*/
@@ -1083,7 +1254,7 @@ void run_subtest(struct test_loader *tester,
link = bpf_map__attach_struct_ops(map);
if (!link) {
PRINT_FAIL("bpf_map__attach_struct_ops failed for map %s: err=%d\n",
- bpf_map__name(map), err);
+ bpf_map__name(map), -errno);
goto tobj_cleanup;
}
links[links_cnt++] = link;
@@ -1103,6 +1274,31 @@ void run_subtest(struct test_loader *tester,
PRINT_FAIL("Unexpected retval: %d != %d\n", retval, subspec->retval);
goto tobj_cleanup;
}
+
+ if (subspec->stderr.cnt) {
+ err = get_stream(2, bpf_program__fd(tprog),
+ tester->log_buf, tester->log_buf_sz);
+ if (err <= 0) {
+ PRINT_FAIL("Unexpected retval from get_stream(): %d, errno = %d\n",
+ err, errno);
+ goto tobj_cleanup;
+ }
+ emit_stderr(tester->log_buf, false /*force*/);
+ validate_msgs(tester->log_buf, &subspec->stderr, emit_stderr);
+ }
+
+ if (subspec->stdout.cnt) {
+ err = get_stream(1, bpf_program__fd(tprog),
+ tester->log_buf, tester->log_buf_sz);
+ if (err <= 0) {
+ PRINT_FAIL("Unexpected retval from get_stream(): %d, errno = %d\n",
+ err, errno);
+ goto tobj_cleanup;
+ }
+ emit_stdout(tester->log_buf, false /*force*/);
+ validate_msgs(tester->log_buf, &subspec->stdout, emit_stdout);
+ }
+
/* redo bpf_map__attach_struct_ops for each test */
while (links_cnt > 0)
bpf_link__destroy(links[--links_cnt]);
diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index 309d9d4a8ace..02a85dda30e6 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -14,12 +14,14 @@
#include <netinet/in.h>
#include <sys/select.h>
#include <sys/socket.h>
+#include <linux/keyctl.h>
#include <sys/un.h>
#include <bpf/btf.h>
#include <time.h>
#include "json_writer.h"
#include "network_helpers.h"
+#include "verification_cert.h"
/* backtrace() and backtrace_symbols_fd() are glibc specific,
* use header file when glibc is available and provide stub
@@ -1928,6 +1930,13 @@ static void free_test_states(void)
}
}
+static __u32 register_session_key(const char *key_data, size_t key_data_size)
+{
+ return syscall(__NR_add_key, "asymmetric", "libbpf_session_key",
+ (const void *)key_data, key_data_size,
+ KEY_SPEC_SESSION_KEYRING);
+}
+
int main(int argc, char **argv)
{
static const struct argp argp = {
@@ -1961,6 +1970,10 @@ int main(int argc, char **argv)
/* Use libbpf 1.0 API mode */
libbpf_set_strict_mode(LIBBPF_STRICT_ALL);
libbpf_set_print(libbpf_print_fn);
+ err = register_session_key((const char *)test_progs_verification_cert,
+ test_progs_verification_cert_len);
+ if (err < 0)
+ return err;
traffic_monitor_set_print(traffic_monitor_print_fn);
diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h
index df2222a1806f..eebfc18cdcd2 100644
--- a/tools/testing/selftests/bpf/test_progs.h
+++ b/tools/testing/selftests/bpf/test_progs.h
@@ -7,6 +7,7 @@
#include <errno.h>
#include <string.h>
#include <assert.h>
+#include <regex.h>
#include <stdlib.h>
#include <stdarg.h>
#include <time.h>
@@ -546,4 +547,20 @@ extern void test_loader_fini(struct test_loader *tester);
test_loader_fini(&tester); \
})
+struct expect_msg {
+ const char *substr; /* substring match */
+ regex_t regex;
+ bool is_regex;
+ bool on_next_line;
+ bool negative;
+};
+
+struct expected_msgs {
+ struct expect_msg *patterns;
+ size_t cnt;
+};
+
+void validate_msgs(const char *log_buf, struct expected_msgs *msgs,
+ void (*emit_fn)(const char *buf, bool force));
+
#endif /* __TEST_PROGS_H */
diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c
index fd2da2234cc9..76568db7a664 100644
--- a/tools/testing/selftests/bpf/test_sockmap.c
+++ b/tools/testing/selftests/bpf/test_sockmap.c
@@ -1372,7 +1372,7 @@ run:
} else
fprintf(stderr, "unknown test\n");
out:
- /* Detatch and zero all the maps */
+ /* Detach and zero all the maps */
bpf_prog_detach2(bpf_program__fd(progs[3]), cg_fd, BPF_CGROUP_SOCK_OPS);
for (i = 0; i < ARRAY_SIZE(links); i++) {
diff --git a/tools/testing/selftests/bpf/test_tcpnotify_user.c b/tools/testing/selftests/bpf/test_tcpnotify_user.c
index 595194453ff8..35b4893ccdf8 100644
--- a/tools/testing/selftests/bpf/test_tcpnotify_user.c
+++ b/tools/testing/selftests/bpf/test_tcpnotify_user.c
@@ -15,20 +15,18 @@
#include <bpf/libbpf.h>
#include <sys/ioctl.h>
#include <linux/rtnetlink.h>
-#include <signal.h>
#include <linux/perf_event.h>
-#include <linux/err.h>
-#include "bpf_util.h"
#include "cgroup_helpers.h"
#include "test_tcpnotify.h"
-#include "trace_helpers.h"
#include "testing_helpers.h"
#define SOCKET_BUFFER_SIZE (getpagesize() < 8192L ? getpagesize() : 8192L)
pthread_t tid;
+static bool exit_thread;
+
int rx_callbacks;
static void dummyfn(void *ctx, int cpu, void *data, __u32 size)
@@ -45,7 +43,7 @@ void tcp_notifier_poller(struct perf_buffer *pb)
{
int err;
- while (1) {
+ while (!exit_thread) {
err = perf_buffer__poll(pb, 100);
if (err < 0 && err != -EINTR) {
printf("failed perf_buffer__poll: %d\n", err);
@@ -78,15 +76,10 @@ int main(int argc, char **argv)
int error = EXIT_FAILURE;
struct bpf_object *obj;
char test_script[80];
- cpu_set_t cpuset;
__u32 key = 0;
libbpf_set_strict_mode(LIBBPF_STRICT_ALL);
- CPU_ZERO(&cpuset);
- CPU_SET(0, &cpuset);
- pthread_setaffinity_np(pthread_self(), sizeof(cpu_set_t), &cpuset);
-
cg_fd = cgroup_setup_and_join(cg_path);
if (cg_fd < 0)
goto err;
@@ -151,6 +144,13 @@ int main(int argc, char **argv)
sleep(10);
+ exit_thread = true;
+ int ret = pthread_join(tid, NULL);
+ if (ret) {
+ printf("FAILED: pthread_join\n");
+ goto err;
+ }
+
if (verify_result(&g)) {
printf("FAILED: Wrong stats Expected %d calls, got %d\n",
g.ncalls, rx_callbacks);
diff --git a/tools/testing/selftests/bpf/test_xsk.sh b/tools/testing/selftests/bpf/test_xsk.sh
index 65aafe0003db..62db060298a4 100755
--- a/tools/testing/selftests/bpf/test_xsk.sh
+++ b/tools/testing/selftests/bpf/test_xsk.sh
@@ -241,4 +241,6 @@ done
if [ $failures -eq 0 ]; then
echo "All tests successful!"
+else
+ exit 1
fi
diff --git a/tools/testing/selftests/bpf/testing_helpers.c b/tools/testing/selftests/bpf/testing_helpers.c
index 5e9f16683be5..16eb37e5bad6 100644
--- a/tools/testing/selftests/bpf/testing_helpers.c
+++ b/tools/testing/selftests/bpf/testing_helpers.c
@@ -399,7 +399,7 @@ int unload_module(const char *name, bool verbose)
return 0;
}
-int load_module(const char *path, bool verbose)
+static int __load_module(const char *path, const char *param_values, bool verbose)
{
int fd;
@@ -411,7 +411,7 @@ int load_module(const char *path, bool verbose)
fprintf(stdout, "Can't find %s kernel module: %d\n", path, -errno);
return -ENOENT;
}
- if (finit_module(fd, "", 0)) {
+ if (finit_module(fd, param_values, 0)) {
fprintf(stdout, "Failed to load %s into the kernel: %d\n", path, -errno);
close(fd);
return -EINVAL;
@@ -423,6 +423,16 @@ int load_module(const char *path, bool verbose)
return 0;
}
+int load_module_params(const char *path, const char *param_values, bool verbose)
+{
+ return __load_module(path, param_values, verbose);
+}
+
+int load_module(const char *path, bool verbose)
+{
+ return __load_module(path, "", verbose);
+}
+
int unload_bpf_testmod(bool verbose)
{
return unload_module("bpf_testmod", verbose);
diff --git a/tools/testing/selftests/bpf/testing_helpers.h b/tools/testing/selftests/bpf/testing_helpers.h
index 46d7f7089f63..eb20d3772218 100644
--- a/tools/testing/selftests/bpf/testing_helpers.h
+++ b/tools/testing/selftests/bpf/testing_helpers.h
@@ -39,6 +39,7 @@ int kern_sync_rcu(void);
int finit_module(int fd, const char *param_values, int flags);
int delete_module(const char *name, int flags);
int load_module(const char *path, bool verbose);
+int load_module_params(const char *path, const char *param_values, bool verbose);
int unload_module(const char *name, bool verbose);
static inline __u64 get_time_ns(void)
diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c
index 81943c6254e6..171987627f3a 100644
--- a/tools/testing/selftests/bpf/trace_helpers.c
+++ b/tools/testing/selftests/bpf/trace_helpers.c
@@ -17,7 +17,9 @@
#include <linux/limits.h>
#include <libelf.h>
#include <gelf.h>
+#include "bpf/hashmap.h"
#include "bpf/libbpf_internal.h"
+#include "bpf_util.h"
#define TRACEFS_PIPE "/sys/kernel/tracing/trace_pipe"
#define DEBUGFS_PIPE "/sys/kernel/debug/tracing/trace_pipe"
@@ -519,3 +521,235 @@ void read_trace_pipe(void)
{
read_trace_pipe_iter(trace_pipe_cb, NULL, 0);
}
+
+static size_t symbol_hash(long key, void *ctx __maybe_unused)
+{
+ return str_hash((const char *) key);
+}
+
+static bool symbol_equal(long key1, long key2, void *ctx __maybe_unused)
+{
+ return strcmp((const char *) key1, (const char *) key2) == 0;
+}
+
+static bool is_invalid_entry(char *buf, bool kernel)
+{
+ if (kernel && strchr(buf, '['))
+ return true;
+ if (!kernel && !strchr(buf, '['))
+ return true;
+ return false;
+}
+
+static const char * const trace_blacklist[] = {
+ "migrate_disable",
+ "migrate_enable",
+ "rcu_read_unlock_strict",
+ "preempt_count_add",
+ "preempt_count_sub",
+ "__rcu_read_lock",
+ "__rcu_read_unlock",
+ "bpf_get_numa_node_id",
+};
+
+static bool skip_entry(char *name)
+{
+ int i;
+
+ /*
+ * We attach to almost all kernel functions and some of them
+ * will cause 'suspicious RCU usage' when fprobe is attached
+ * to them. Filter out the current culprits - arch_cpu_idle
+ * default_idle and rcu_* functions.
+ */
+ if (!strcmp(name, "arch_cpu_idle"))
+ return true;
+ if (!strcmp(name, "default_idle"))
+ return true;
+ if (!strncmp(name, "rcu_", 4))
+ return true;
+ if (!strcmp(name, "bpf_dispatcher_xdp_func"))
+ return true;
+ if (!strncmp(name, "__ftrace_invalid_address__",
+ sizeof("__ftrace_invalid_address__") - 1))
+ return true;
+
+ for (i = 0; i < ARRAY_SIZE(trace_blacklist); i++) {
+ if (!strcmp(name, trace_blacklist[i]))
+ return true;
+ }
+
+ return false;
+}
+
+/* Do comparison by ignoring '.llvm.<hash>' suffixes. */
+static int compare_name(const char *name1, const char *name2)
+{
+ const char *res1, *res2;
+ int len1, len2;
+
+ res1 = strstr(name1, ".llvm.");
+ res2 = strstr(name2, ".llvm.");
+ len1 = res1 ? res1 - name1 : strlen(name1);
+ len2 = res2 ? res2 - name2 : strlen(name2);
+
+ if (len1 == len2)
+ return strncmp(name1, name2, len1);
+ if (len1 < len2)
+ return strncmp(name1, name2, len1) <= 0 ? -1 : 1;
+ return strncmp(name1, name2, len2) >= 0 ? 1 : -1;
+}
+
+static int load_kallsyms_compare(const void *p1, const void *p2)
+{
+ return compare_name(((const struct ksym *)p1)->name, ((const struct ksym *)p2)->name);
+}
+
+static int search_kallsyms_compare(const void *p1, const struct ksym *p2)
+{
+ return compare_name(p1, p2->name);
+}
+
+int bpf_get_ksyms(char ***symsp, size_t *cntp, bool kernel)
+{
+ size_t cap = 0, cnt = 0;
+ char *name = NULL, *ksym_name, **syms = NULL;
+ struct hashmap *map;
+ struct ksyms *ksyms;
+ struct ksym *ks;
+ char buf[256];
+ FILE *f;
+ int err = 0;
+
+ ksyms = load_kallsyms_custom_local(load_kallsyms_compare);
+ if (!ksyms)
+ return -EINVAL;
+
+ /*
+ * The available_filter_functions contains many duplicates,
+ * but other than that all symbols are usable to trace.
+ * Filtering out duplicates by using hashmap__add, which won't
+ * add existing entry.
+ */
+
+ if (access("/sys/kernel/tracing/trace", F_OK) == 0)
+ f = fopen("/sys/kernel/tracing/available_filter_functions", "r");
+ else
+ f = fopen("/sys/kernel/debug/tracing/available_filter_functions", "r");
+
+ if (!f)
+ return -EINVAL;
+
+ map = hashmap__new(symbol_hash, symbol_equal, NULL);
+ if (IS_ERR(map)) {
+ err = libbpf_get_error(map);
+ goto error;
+ }
+
+ while (fgets(buf, sizeof(buf), f)) {
+ if (is_invalid_entry(buf, kernel))
+ continue;
+
+ free(name);
+ if (sscanf(buf, "%ms$*[^\n]\n", &name) != 1)
+ continue;
+ if (skip_entry(name))
+ continue;
+
+ ks = search_kallsyms_custom_local(ksyms, name, search_kallsyms_compare);
+ if (!ks) {
+ err = -EINVAL;
+ goto error;
+ }
+
+ ksym_name = ks->name;
+ err = hashmap__add(map, ksym_name, 0);
+ if (err == -EEXIST) {
+ err = 0;
+ continue;
+ }
+ if (err)
+ goto error;
+
+ err = libbpf_ensure_mem((void **) &syms, &cap,
+ sizeof(*syms), cnt + 1);
+ if (err)
+ goto error;
+
+ syms[cnt++] = ksym_name;
+ }
+
+ *symsp = syms;
+ *cntp = cnt;
+
+error:
+ free(name);
+ fclose(f);
+ hashmap__free(map);
+ if (err)
+ free(syms);
+ return err;
+}
+
+int bpf_get_addrs(unsigned long **addrsp, size_t *cntp, bool kernel)
+{
+ unsigned long *addr, *addrs, *tmp_addrs;
+ int err = 0, max_cnt, inc_cnt;
+ char *name = NULL;
+ size_t cnt = 0;
+ char buf[256];
+ FILE *f;
+
+ if (access("/sys/kernel/tracing/trace", F_OK) == 0)
+ f = fopen("/sys/kernel/tracing/available_filter_functions_addrs", "r");
+ else
+ f = fopen("/sys/kernel/debug/tracing/available_filter_functions_addrs", "r");
+
+ if (!f)
+ return -ENOENT;
+
+ /* In my local setup, the number of entries is 50k+ so Let us initially
+ * allocate space to hold 64k entries. If 64k is not enough, incrementally
+ * increase 1k each time.
+ */
+ max_cnt = 65536;
+ inc_cnt = 1024;
+ addrs = malloc(max_cnt * sizeof(long));
+ if (addrs == NULL) {
+ err = -ENOMEM;
+ goto error;
+ }
+
+ while (fgets(buf, sizeof(buf), f)) {
+ if (is_invalid_entry(buf, kernel))
+ continue;
+
+ free(name);
+ if (sscanf(buf, "%p %ms$*[^\n]\n", &addr, &name) != 2)
+ continue;
+ if (skip_entry(name))
+ continue;
+
+ if (cnt == max_cnt) {
+ max_cnt += inc_cnt;
+ tmp_addrs = realloc(addrs, max_cnt);
+ if (!tmp_addrs) {
+ err = -ENOMEM;
+ goto error;
+ }
+ addrs = tmp_addrs;
+ }
+
+ addrs[cnt++] = (unsigned long)addr;
+ }
+
+ *addrsp = addrs;
+ *cntp = cnt;
+
+error:
+ free(name);
+ fclose(f);
+ if (err)
+ free(addrs);
+ return err;
+}
diff --git a/tools/testing/selftests/bpf/trace_helpers.h b/tools/testing/selftests/bpf/trace_helpers.h
index 2ce873c9f9aa..9437bdd4afa5 100644
--- a/tools/testing/selftests/bpf/trace_helpers.h
+++ b/tools/testing/selftests/bpf/trace_helpers.h
@@ -41,4 +41,7 @@ ssize_t get_rel_offset(uintptr_t addr);
int read_build_id(const char *path, char *build_id, size_t size);
+int bpf_get_ksyms(char ***symsp, size_t *cntp, bool kernel);
+int bpf_get_addrs(unsigned long **addrsp, size_t *cntp, bool kernel);
+
#endif
diff --git a/tools/testing/selftests/bpf/usdt.h b/tools/testing/selftests/bpf/usdt.h
new file mode 100644
index 000000000000..549d1f774810
--- /dev/null
+++ b/tools/testing/selftests/bpf/usdt.h
@@ -0,0 +1,545 @@
+// SPDX-License-Identifier: BSD-2-Clause
+/*
+ * This single-header library defines a collection of variadic macros for
+ * defining and triggering USDTs (User Statically-Defined Tracepoints):
+ *
+ * - For USDTs without associated semaphore:
+ * USDT(group, name, args...)
+ *
+ * - For USDTs with implicit (transparent to the user) semaphore:
+ * USDT_WITH_SEMA(group, name, args...)
+ * USDT_IS_ACTIVE(group, name)
+ *
+ * - For USDTs with explicit (user-defined and provided) semaphore:
+ * USDT_WITH_EXPLICIT_SEMA(sema, group, name, args...)
+ * USDT_SEMA_IS_ACTIVE(sema)
+ *
+ * all of which emit a NOP instruction into the instruction stream, and so
+ * have *zero* overhead for the surrounding code. USDTs are identified by
+ * a combination of `group` and `name` identifiers, which is used by external
+ * tracing tooling (tracers) for identifying exact USDTs of interest.
+ *
+ * USDTs can have an associated (2-byte) activity counter (USDT semaphore),
+ * automatically maintained by Linux kernel whenever any correctly written
+ * BPF-based tracer is attached to the USDT. This USDT semaphore can be used
+ * to check whether there is a need to do any extra data collection and
+ * processing for a given USDT (if necessary), and otherwise avoid extra work
+ * for a common case of USDT not being traced ("active").
+ *
+ * See documentation for USDT_WITH_SEMA()/USDT_IS_ACTIVE() or
+ * USDT_WITH_EXPLICIT_SEMA()/USDT_SEMA_IS_ACTIVE() APIs below for details on
+ * working with USDTs with implicitly or explicitly associated
+ * USDT semaphores, respectively.
+ *
+ * There is also some additional data recorded into an auxiliary note
+ * section. The data in the note section describes the operands, in terms of
+ * size and location, used by tracing tooling to know where to find USDT
+ * arguments. Each location is encoded as an assembler operand string.
+ * Tracing tools (bpftrace and BPF-based tracers, systemtap, etc) insert
+ * breakpoints on top of the nop, and decode the location operand-strings,
+ * like an assembler, to find the values being passed.
+ *
+ * The operand strings are selected by the compiler for each operand.
+ * They are constrained by inline-assembler codes.The default is:
+ *
+ * #define USDT_ARG_CONSTRAINT nor
+ *
+ * This is a good default if the operands tend to be integral and
+ * moderate in number (smaller than number of registers). In other
+ * cases, the compiler may report "'asm' requires impossible reload" or
+ * similar. In this case, consider simplifying the macro call (fewer
+ * and simpler operands), reduce optimization, or override the default
+ * constraints string via:
+ *
+ * #define USDT_ARG_CONSTRAINT g
+ * #include <usdt.h>
+ *
+ * For some historical description of USDT v3 format (the one used by this
+ * library and generally recognized and assumed by BPF-based tracing tools)
+ * see [0]. The more formal specification can be found at [1]. Additional
+ * argument constraints information can be found at [2].
+ *
+ * Original SystemTap's sys/sdt.h implementation ([3]) was used as a base for
+ * this USDT library implementation. Current implementation differs *a lot* in
+ * terms of exposed user API and general usability, which was the main goal
+ * and focus of the reimplementation work. Nevertheless, underlying recorded
+ * USDT definitions are fully binary compatible and any USDT-based tooling
+ * should work equally well with USDTs defined by either SystemTap's or this
+ * library's USDT implementation.
+ *
+ * [0] https://ecos.sourceware.org/ml/systemtap/2010-q3/msg00145.html
+ * [1] https://sourceware.org/systemtap/wiki/UserSpaceProbeImplementation
+ * [2] https://gcc.gnu.org/onlinedocs/gcc/Constraints.html
+ * [3] https://sourceware.org/git/?p=systemtap.git;a=blob;f=includes/sys/sdt.h
+ */
+#ifndef __USDT_H
+#define __USDT_H
+
+/*
+ * Changelog:
+ *
+ * 0.1.0
+ * -----
+ * - Initial release
+ */
+#define USDT_MAJOR_VERSION 0
+#define USDT_MINOR_VERSION 1
+#define USDT_PATCH_VERSION 0
+
+/* C++20 and C23 added __VA_OPT__ as a standard replacement for non-standard `##__VA_ARGS__` extension */
+#if (defined(__STDC_VERSION__) && __STDC_VERSION__ > 201710L) || (defined(__cplusplus) && __cplusplus > 201703L)
+#define __usdt_va_opt 1
+#define __usdt_va_args(...) __VA_OPT__(,) __VA_ARGS__
+#else
+#define __usdt_va_args(...) , ##__VA_ARGS__
+#endif
+
+/*
+ * Trigger USDT with `group`:`name` identifier and pass through `args` as its
+ * arguments. Zero arguments are acceptable as well. No USDT semaphore is
+ * associated with this USDT.
+ *
+ * Such "semaphoreless" USDTs are commonly used when there is no extra data
+ * collection or processing needed to collect and prepare USDT arguments and
+ * they are just available in the surrounding code. USDT() macro will just
+ * record their locations in CPU registers or in memory for tracing tooling to
+ * be able to access them, if necessary.
+ */
+#ifdef __usdt_va_opt
+#define USDT(group, name, ...) \
+ __usdt_probe(group, name, __usdt_sema_none, 0 __VA_OPT__(,) __VA_ARGS__)
+#else
+#define USDT(group, name, ...) \
+ __usdt_probe(group, name, __usdt_sema_none, 0, ##__VA_ARGS__)
+#endif
+
+/*
+ * Trigger USDT with `group`:`name` identifier and pass through `args` as its
+ * arguments. Zero arguments are acceptable as well. USDT also get an
+ * implicitly-defined associated USDT semaphore, which will be "activated" by
+ * tracing tooling and can be used to check whether USDT is being actively
+ * observed.
+ *
+ * USDTs with semaphore are commonly used when there is a need to perform
+ * additional data collection and processing to prepare USDT arguments, which
+ * otherwise might not be necessary for the rest of application logic. In such
+ * case, USDT semaphore can be used to avoid unnecessary extra work. If USDT
+ * is not traced (which is presumed to be a common situation), the associated
+ * USDT semaphore is "inactive", and so there is no need to waste resources to
+ * prepare USDT arguments. Use USDT_IS_ACTIVE(group, name) to check whether
+ * USDT is "active".
+ *
+ * N.B. There is an inherent (albeit short) gap between checking whether USDT
+ * is active and triggering corresponding USDT, in which external tracer can
+ * be attached to an USDT and activate USDT semaphore after the activity check.
+ * If such a race occurs, tracers might miss one USDT execution. Tracers are
+ * expected to accommodate such possibility and this is expected to not be
+ * a problem for applications and tracers.
+ *
+ * N.B. Implicit USDT semaphore defined by USDT_WITH_SEMA() is contained
+ * within a single executable or shared library and is not shared outside
+ * them. I.e., if you use USDT_WITH_SEMA() with the same USDT group and name
+ * identifier across executable and shared library, it will work and won't
+ * conflict, per se, but will define independent USDT semaphores, one for each
+ * shared library/executable in which USDT_WITH_SEMA(group, name) is used.
+ * That is, if you attach to this USDT in one shared library (or executable),
+ * then only USDT semaphore within that shared library (or executable) will be
+ * updated by the kernel, while other libraries (or executable) will not see
+ * activated USDT semaphore. In short, it's best to use unique USDT group:name
+ * identifiers across different shared libraries (and, equivalently, between
+ * executable and shared library). This is advanced consideration and is
+ * rarely (if ever) seen in practice, but just to avoid surprises this is
+ * called out here. (Static libraries become a part of final executable, once
+ * linked by linker, so the above considerations don't apply to them.)
+ */
+#ifdef __usdt_va_opt
+#define USDT_WITH_SEMA(group, name, ...) \
+ __usdt_probe(group, name, \
+ __usdt_sema_implicit, __usdt_sema_name(group, name) \
+ __VA_OPT__(,) __VA_ARGS__)
+#else
+#define USDT_WITH_SEMA(group, name, ...) \
+ __usdt_probe(group, name, \
+ __usdt_sema_implicit, __usdt_sema_name(group, name), \
+ ##__VA_ARGS__)
+#endif
+
+struct usdt_sema { volatile unsigned short active; };
+
+/*
+ * Check if USDT with `group`:`name` identifier is "active" (i.e., whether it
+ * is attached to by external tracing tooling and is actively observed).
+ *
+ * This macro can be used to decide whether any additional and potentially
+ * expensive data collection or processing should be done to pass extra
+ * information into the given USDT. It is assumed that USDT is triggered with
+ * USDT_WITH_SEMA() macro which will implicitly define associated USDT
+ * semaphore. (If one needs more control over USDT semaphore, see
+ * USDT_DEFINE_SEMA() and USDT_WITH_EXPLICIT_SEMA() macros below.)
+ *
+ * N.B. Such checks are necessarily racy and speculative. Between checking
+ * whether USDT is active and triggering the USDT itself, tracer can be
+ * detached with no notification. This race should be extremely rare and worst
+ * case should result in one-time wasted extra data collection and processing.
+ */
+#define USDT_IS_ACTIVE(group, name) ({ \
+ extern struct usdt_sema __usdt_sema_name(group, name) \
+ __usdt_asm_name(__usdt_sema_name(group, name)); \
+ __usdt_sema_implicit(__usdt_sema_name(group, name)); \
+ __usdt_sema_name(group, name).active > 0; \
+})
+
+/*
+ * APIs for working with user-defined explicit USDT semaphores.
+ *
+ * This is a less commonly used advanced API for use cases in which user needs
+ * an explicit control over (potentially shared across multiple USDTs) USDT
+ * semaphore instance. This can be used when there is a group of logically
+ * related USDTs that all need extra data collection and processing whenever
+ * any of a family of related USDTs are "activated" (i.e., traced). In such
+ * a case, all such related USDTs will be associated with the same shared USDT
+ * semaphore defined with USDT_DEFINE_SEMA() and the USDTs themselves will be
+ * triggered with USDT_WITH_EXPLICIT_SEMA() macros, taking an explicit extra
+ * USDT semaphore identifier as an extra parameter.
+ */
+
+/**
+ * Underlying C global variable name for user-defined USDT semaphore with
+ * `sema` identifier. Could be useful for debugging, but normally shouldn't be
+ * used explicitly.
+ */
+#define USDT_SEMA(sema) __usdt_sema_##sema
+
+/*
+ * Define storage for user-defined USDT semaphore `sema`.
+ *
+ * Should be used only once in non-header source file to let compiler allocate
+ * space for the semaphore variable. Just like with any other global variable.
+ *
+ * This macro can be used anywhere where global variable declaration is
+ * allowed. Just like with global variable definitions, there should be only
+ * one definition of user-defined USDT semaphore with given `sema` identifier,
+ * otherwise compiler or linker will complain about duplicate variable
+ * definition.
+ *
+ * For C++, it is allowed to use USDT_DEFINE_SEMA() both in global namespace
+ * and inside namespaces (including nested namespaces). Just make sure that
+ * USDT_DECLARE_SEMA() is placed within the namespace where this semaphore is
+ * referenced, or any of its parent namespaces, so the C++ language-level
+ * identifier is visible to the code that needs to reference the semaphore.
+ * At the lowest layer, USDT semaphores have global naming and visibility
+ * (they have a corresponding `__usdt_sema_<name>` symbol, which can be linked
+ * against from C or C++ code, if necessary). To keep it simple, putting
+ * USDT_DECLARE_SEMA() declarations into global namespaces is the simplest
+ * no-brainer solution. All these aspects are irrelevant for plain C, because
+ * C doesn't have namespaces and everything is always in the global namespace.
+ *
+ * N.B. Due to USDT metadata being recorded in non-allocatable ELF note
+ * section, it has limitations when it comes to relocations, which, in
+ * practice, means that it's not possible to correctly share USDT semaphores
+ * between main executable and shared libraries, or even between multiple
+ * shared libraries. USDT semaphore has to be contained to individual shared
+ * library or executable to avoid unpleasant surprises with half-working USDT
+ * semaphores. We enforce this by marking semaphore ELF symbols as having
+ * a hidden visibility. This is quite an advanced use case and consideration
+ * and for most users this should have no consequences whatsoever.
+ */
+#define USDT_DEFINE_SEMA(sema) \
+ struct usdt_sema __usdt_sema_sec USDT_SEMA(sema) \
+ __usdt_asm_name(USDT_SEMA(sema)) \
+ __attribute__((visibility("hidden"))) = { 0 }
+
+/*
+ * Declare extern reference to user-defined USDT semaphore `sema`.
+ *
+ * Refers to a variable defined in another compilation unit by
+ * USDT_DEFINE_SEMA() and allows to use the same USDT semaphore across
+ * multiple compilation units (i.e., .c and .cpp files).
+ *
+ * See USDT_DEFINE_SEMA() notes above for C++ language usage peculiarities.
+ */
+#define USDT_DECLARE_SEMA(sema) \
+ extern struct usdt_sema USDT_SEMA(sema) __usdt_asm_name(USDT_SEMA(sema))
+
+/*
+ * Check if user-defined USDT semaphore `sema` is "active" (i.e., whether it
+ * is attached to by external tracing tooling and is actively observed).
+ *
+ * This macro can be used to decide whether any additional and potentially
+ * expensive data collection or processing should be done to pass extra
+ * information into USDT(s) associated with USDT semaphore `sema`.
+ *
+ * N.B. Such checks are necessarily racy. Between checking the state of USDT
+ * semaphore and triggering associated USDT(s), the active tracer might attach
+ * or detach. This race should be extremely rare and worst case should result
+ * in one-time missed USDT event or wasted extra data collection and
+ * processing. USDT-using tracers should be written with this in mind and is
+ * not a concern of the application defining USDTs with associated semaphore.
+ */
+#define USDT_SEMA_IS_ACTIVE(sema) (USDT_SEMA(sema).active > 0)
+
+/*
+ * Invoke USDT specified by `group` and `name` identifiers and associate
+ * explicitly user-defined semaphore `sema` with it. Pass through `args` as
+ * USDT arguments. `args` are optional and zero arguments are acceptable.
+ *
+ * Semaphore is defined with the help of USDT_DEFINE_SEMA() macro and can be
+ * checked whether active with USDT_SEMA_IS_ACTIVE().
+ */
+#ifdef __usdt_va_opt
+#define USDT_WITH_EXPLICIT_SEMA(sema, group, name, ...) \
+ __usdt_probe(group, name, __usdt_sema_explicit, USDT_SEMA(sema), ##__VA_ARGS__)
+#else
+#define USDT_WITH_EXPLICIT_SEMA(sema, group, name, ...) \
+ __usdt_probe(group, name, __usdt_sema_explicit, USDT_SEMA(sema) __VA_OPT__(,) __VA_ARGS__)
+#endif
+
+/*
+ * Adjustable implementation aspects
+ */
+#ifndef USDT_ARG_CONSTRAINT
+#if defined __powerpc__
+#define USDT_ARG_CONSTRAINT nZr
+#elif defined __arm__
+#define USDT_ARG_CONSTRAINT g
+#elif defined __loongarch__
+#define USDT_ARG_CONSTRAINT nmr
+#else
+#define USDT_ARG_CONSTRAINT nor
+#endif
+#endif /* USDT_ARG_CONSTRAINT */
+
+#ifndef USDT_NOP
+#if defined(__ia64__) || defined(__s390__) || defined(__s390x__)
+#define USDT_NOP nop 0
+#else
+#define USDT_NOP nop
+#endif
+#endif /* USDT_NOP */
+
+/*
+ * Implementation details
+ */
+/* USDT name for implicitly-defined USDT semaphore, derived from group:name */
+#define __usdt_sema_name(group, name) __usdt_sema_##group##__##name
+/* ELF section into which USDT semaphores are put */
+#define __usdt_sema_sec __attribute__((section(".probes")))
+
+#define __usdt_concat(a, b) a ## b
+#define __usdt_apply(fn, n) __usdt_concat(fn, n)
+
+#ifndef __usdt_nth
+#define __usdt_nth(_, _1, _2, _3, _4, _5, _6, _7, _8, _9, _10, _11, _12, N, ...) N
+#endif
+
+#ifndef __usdt_narg
+#ifdef __usdt_va_opt
+#define __usdt_narg(...) __usdt_nth(_ __VA_OPT__(,) __VA_ARGS__, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0)
+#else
+#define __usdt_narg(...) __usdt_nth(_, ##__VA_ARGS__, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0)
+#endif
+#endif /* __usdt_narg */
+
+#define __usdt_hash #
+#define __usdt_str_(x) #x
+#define __usdt_str(x) __usdt_str_(x)
+
+#ifndef __usdt_asm_name
+#define __usdt_asm_name(name) __asm__(__usdt_str(name))
+#endif
+
+#define __usdt_asm0() "\n"
+#define __usdt_asm1(x) __usdt_str(x) "\n"
+#define __usdt_asm2(x, ...) __usdt_str(x) "," __usdt_asm1(__VA_ARGS__)
+#define __usdt_asm3(x, ...) __usdt_str(x) "," __usdt_asm2(__VA_ARGS__)
+#define __usdt_asm4(x, ...) __usdt_str(x) "," __usdt_asm3(__VA_ARGS__)
+#define __usdt_asm5(x, ...) __usdt_str(x) "," __usdt_asm4(__VA_ARGS__)
+#define __usdt_asm6(x, ...) __usdt_str(x) "," __usdt_asm5(__VA_ARGS__)
+#define __usdt_asm7(x, ...) __usdt_str(x) "," __usdt_asm6(__VA_ARGS__)
+#define __usdt_asm8(x, ...) __usdt_str(x) "," __usdt_asm7(__VA_ARGS__)
+#define __usdt_asm9(x, ...) __usdt_str(x) "," __usdt_asm8(__VA_ARGS__)
+#define __usdt_asm10(x, ...) __usdt_str(x) "," __usdt_asm9(__VA_ARGS__)
+#define __usdt_asm11(x, ...) __usdt_str(x) "," __usdt_asm10(__VA_ARGS__)
+#define __usdt_asm12(x, ...) __usdt_str(x) "," __usdt_asm11(__VA_ARGS__)
+#define __usdt_asm(...) __usdt_apply(__usdt_asm, __usdt_narg(__VA_ARGS__))(__VA_ARGS__)
+
+#ifdef __LP64__
+#define __usdt_asm_addr .8byte
+#else
+#define __usdt_asm_addr .4byte
+#endif
+
+#define __usdt_asm_strz_(x) __usdt_asm1(.asciz #x)
+#define __usdt_asm_strz(x) __usdt_asm_strz_(x)
+#define __usdt_asm_str_(x) __usdt_asm1(.ascii #x)
+#define __usdt_asm_str(x) __usdt_asm_str_(x)
+
+/* "semaphoreless" USDT case */
+#ifndef __usdt_sema_none
+#define __usdt_sema_none(sema)
+#endif
+
+/* implicitly defined __usdt_sema__group__name semaphore (using weak symbols) */
+#ifndef __usdt_sema_implicit
+#define __usdt_sema_implicit(sema) \
+ __asm__ __volatile__ ( \
+ __usdt_asm1(.ifndef sema) \
+ __usdt_asm3( .pushsection .probes, "aw", "progbits") \
+ __usdt_asm1( .weak sema) \
+ __usdt_asm1( .hidden sema) \
+ __usdt_asm1( .align 2) \
+ __usdt_asm1(sema:) \
+ __usdt_asm1( .zero 2) \
+ __usdt_asm2( .type sema, @object) \
+ __usdt_asm2( .size sema, 2) \
+ __usdt_asm1( .popsection) \
+ __usdt_asm1(.endif) \
+ );
+#endif
+
+/* externally defined semaphore using USDT_DEFINE_SEMA() and passed explicitly by user */
+#ifndef __usdt_sema_explicit
+#define __usdt_sema_explicit(sema) \
+ __asm__ __volatile__ ("" :: "m" (sema));
+#endif
+
+/* main USDT definition (nop and .note.stapsdt metadata) */
+#define __usdt_probe(group, name, sema_def, sema, ...) do { \
+ sema_def(sema) \
+ __asm__ __volatile__ ( \
+ __usdt_asm( 990: USDT_NOP) \
+ __usdt_asm3( .pushsection .note.stapsdt, "", "note") \
+ __usdt_asm1( .balign 4) \
+ __usdt_asm3( .4byte 992f-991f,994f-993f,3) \
+ __usdt_asm1(991: .asciz "stapsdt") \
+ __usdt_asm1(992: .balign 4) \
+ __usdt_asm1(993: __usdt_asm_addr 990b) \
+ __usdt_asm1( __usdt_asm_addr _.stapsdt.base) \
+ __usdt_asm1( __usdt_asm_addr sema) \
+ __usdt_asm_strz(group) \
+ __usdt_asm_strz(name) \
+ __usdt_asm_args(__VA_ARGS__) \
+ __usdt_asm1( .ascii "\0") \
+ __usdt_asm1(994: .balign 4) \
+ __usdt_asm1( .popsection) \
+ __usdt_asm1(.ifndef _.stapsdt.base) \
+ __usdt_asm5( .pushsection .stapsdt.base,"aG","progbits",.stapsdt.base,comdat)\
+ __usdt_asm1( .weak _.stapsdt.base) \
+ __usdt_asm1( .hidden _.stapsdt.base) \
+ __usdt_asm1(_.stapsdt.base:) \
+ __usdt_asm1( .space 1) \
+ __usdt_asm2( .size _.stapsdt.base, 1) \
+ __usdt_asm1( .popsection) \
+ __usdt_asm1(.endif) \
+ :: __usdt_asm_ops(__VA_ARGS__) \
+ ); \
+} while (0)
+
+/*
+ * NB: gdb PR24541 highlighted an unspecified corner of the sdt.h
+ * operand note format.
+ *
+ * The named register may be a longer or shorter (!) alias for the
+ * storage where the value in question is found. For example, on
+ * i386, 64-bit value may be put in register pairs, and a register
+ * name stored would identify just one of them. Previously, gcc was
+ * asked to emit the %w[id] (16-bit alias of some registers holding
+ * operands), even when a wider 32-bit value was used.
+ *
+ * Bottom line: the byte-width given before the @ sign governs. If
+ * there is a mismatch between that width and that of the named
+ * register, then a sys/sdt.h note consumer may need to employ
+ * architecture-specific heuristics to figure out where the compiler
+ * has actually put the complete value.
+ */
+#if defined(__powerpc__) || defined(__powerpc64__)
+#define __usdt_argref(id) %I[id]%[id]
+#elif defined(__i386__)
+#define __usdt_argref(id) %k[id] /* gcc.gnu.org/PR80115 sourceware.org/PR24541 */
+#else
+#define __usdt_argref(id) %[id]
+#endif
+
+#define __usdt_asm_arg(n) __usdt_asm_str(%c[__usdt_asz##n]) \
+ __usdt_asm1(.ascii "@") \
+ __usdt_asm_str(__usdt_argref(__usdt_aval##n))
+
+#define __usdt_asm_args0 /* no arguments */
+#define __usdt_asm_args1 __usdt_asm_arg(1)
+#define __usdt_asm_args2 __usdt_asm_args1 __usdt_asm1(.ascii " ") __usdt_asm_arg(2)
+#define __usdt_asm_args3 __usdt_asm_args2 __usdt_asm1(.ascii " ") __usdt_asm_arg(3)
+#define __usdt_asm_args4 __usdt_asm_args3 __usdt_asm1(.ascii " ") __usdt_asm_arg(4)
+#define __usdt_asm_args5 __usdt_asm_args4 __usdt_asm1(.ascii " ") __usdt_asm_arg(5)
+#define __usdt_asm_args6 __usdt_asm_args5 __usdt_asm1(.ascii " ") __usdt_asm_arg(6)
+#define __usdt_asm_args7 __usdt_asm_args6 __usdt_asm1(.ascii " ") __usdt_asm_arg(7)
+#define __usdt_asm_args8 __usdt_asm_args7 __usdt_asm1(.ascii " ") __usdt_asm_arg(8)
+#define __usdt_asm_args9 __usdt_asm_args8 __usdt_asm1(.ascii " ") __usdt_asm_arg(9)
+#define __usdt_asm_args10 __usdt_asm_args9 __usdt_asm1(.ascii " ") __usdt_asm_arg(10)
+#define __usdt_asm_args11 __usdt_asm_args10 __usdt_asm1(.ascii " ") __usdt_asm_arg(11)
+#define __usdt_asm_args12 __usdt_asm_args11 __usdt_asm1(.ascii " ") __usdt_asm_arg(12)
+#define __usdt_asm_args(...) __usdt_apply(__usdt_asm_args, __usdt_narg(__VA_ARGS__))
+
+#define __usdt_is_arr(x) (__builtin_classify_type(x) == 14 || __builtin_classify_type(x) == 5)
+#define __usdt_arg_size(x) (__usdt_is_arr(x) ? sizeof(void *) : sizeof(x))
+
+/*
+ * We can't use __builtin_choose_expr() in C++, so fall back to table-based
+ * signedness determination for known types, utilizing templates magic.
+ */
+#ifdef __cplusplus
+
+#define __usdt_is_signed(x) (!__usdt_is_arr(x) && __usdt_t<__typeof(x)>::is_signed)
+
+#include <cstddef>
+
+template<typename T> struct __usdt_t { static const bool is_signed = false; };
+template<typename A> struct __usdt_t<A[]> : public __usdt_t<A *> {};
+template<typename A, size_t N> struct __usdt_t<A[N]> : public __usdt_t<A *> {};
+
+#define __usdt_def_signed(T) \
+template<> struct __usdt_t<T> { static const bool is_signed = true; }; \
+template<> struct __usdt_t<const T> { static const bool is_signed = true; }; \
+template<> struct __usdt_t<volatile T> { static const bool is_signed = true; }; \
+template<> struct __usdt_t<const volatile T> { static const bool is_signed = true; }
+#define __usdt_maybe_signed(T) \
+template<> struct __usdt_t<T> { static const bool is_signed = (T)-1 < (T)1; }; \
+template<> struct __usdt_t<const T> { static const bool is_signed = (T)-1 < (T)1; }; \
+template<> struct __usdt_t<volatile T> { static const bool is_signed = (T)-1 < (T)1; }; \
+template<> struct __usdt_t<const volatile T> { static const bool is_signed = (T)-1 < (T)1; }
+
+__usdt_def_signed(signed char);
+__usdt_def_signed(short);
+__usdt_def_signed(int);
+__usdt_def_signed(long);
+__usdt_def_signed(long long);
+__usdt_maybe_signed(char);
+__usdt_maybe_signed(wchar_t);
+
+#else /* !__cplusplus */
+
+#define __usdt_is_inttype(x) (__builtin_classify_type(x) >= 1 && __builtin_classify_type(x) <= 4)
+#define __usdt_inttype(x) __typeof(__builtin_choose_expr(__usdt_is_inttype(x), (x), 0U))
+#define __usdt_is_signed(x) ((__usdt_inttype(x))-1 < (__usdt_inttype(x))1)
+
+#endif /* __cplusplus */
+
+#define __usdt_asm_op(n, x) \
+ [__usdt_asz##n] "n" ((__usdt_is_signed(x) ? (int)-1 : 1) * (int)__usdt_arg_size(x)), \
+ [__usdt_aval##n] __usdt_str(USDT_ARG_CONSTRAINT)(x)
+
+#define __usdt_asm_ops0() [__usdt_dummy] "g" (0)
+#define __usdt_asm_ops1(x) __usdt_asm_op(1, x)
+#define __usdt_asm_ops2(a,x) __usdt_asm_ops1(a), __usdt_asm_op(2, x)
+#define __usdt_asm_ops3(a,b,x) __usdt_asm_ops2(a,b), __usdt_asm_op(3, x)
+#define __usdt_asm_ops4(a,b,c,x) __usdt_asm_ops3(a,b,c), __usdt_asm_op(4, x)
+#define __usdt_asm_ops5(a,b,c,d,x) __usdt_asm_ops4(a,b,c,d), __usdt_asm_op(5, x)
+#define __usdt_asm_ops6(a,b,c,d,e,x) __usdt_asm_ops5(a,b,c,d,e), __usdt_asm_op(6, x)
+#define __usdt_asm_ops7(a,b,c,d,e,f,x) __usdt_asm_ops6(a,b,c,d,e,f), __usdt_asm_op(7, x)
+#define __usdt_asm_ops8(a,b,c,d,e,f,g,x) __usdt_asm_ops7(a,b,c,d,e,f,g), __usdt_asm_op(8, x)
+#define __usdt_asm_ops9(a,b,c,d,e,f,g,h,x) __usdt_asm_ops8(a,b,c,d,e,f,g,h), __usdt_asm_op(9, x)
+#define __usdt_asm_ops10(a,b,c,d,e,f,g,h,i,x) __usdt_asm_ops9(a,b,c,d,e,f,g,h,i), __usdt_asm_op(10, x)
+#define __usdt_asm_ops11(a,b,c,d,e,f,g,h,i,j,x) __usdt_asm_ops10(a,b,c,d,e,f,g,h,i,j), __usdt_asm_op(11, x)
+#define __usdt_asm_ops12(a,b,c,d,e,f,g,h,i,j,k,x) __usdt_asm_ops11(a,b,c,d,e,f,g,h,i,j,k), __usdt_asm_op(12, x)
+#define __usdt_asm_ops(...) __usdt_apply(__usdt_asm_ops, __usdt_narg(__VA_ARGS__))(__VA_ARGS__)
+
+#endif /* __USDT_H */
diff --git a/tools/testing/selftests/bpf/verifier/bpf_st_mem.c b/tools/testing/selftests/bpf/verifier/bpf_st_mem.c
index b616575c3b00..ce13002c7a19 100644
--- a/tools/testing/selftests/bpf/verifier/bpf_st_mem.c
+++ b/tools/testing/selftests/bpf/verifier/bpf_st_mem.c
@@ -93,7 +93,7 @@
.expected_attach_type = BPF_SK_LOOKUP,
.result = VERBOSE_ACCEPT,
.runs = -1,
- .errstr = "0: (7a) *(u64 *)(r10 -8) = -44 ; R10=fp0 fp-8_w=-44\
+ .errstr = "0: (7a) *(u64 *)(r10 -8) = -44 ; R10=fp0 fp-8=-44\
2: (c5) if r0 s< 0x0 goto pc+2\
- R0_w=-44",
+ R0=-44",
},
diff --git a/tools/testing/selftests/bpf/verifier/calls.c b/tools/testing/selftests/bpf/verifier/calls.c
index f3492efc8834..c8d640802cce 100644
--- a/tools/testing/selftests/bpf/verifier/calls.c
+++ b/tools/testing/selftests/bpf/verifier/calls.c
@@ -1375,7 +1375,7 @@
BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
/* write into map value */
BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0),
- /* fetch secound map_value_ptr from the stack */
+ /* fetch second map_value_ptr from the stack */
BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -16),
BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
/* write into map value */
@@ -1439,7 +1439,7 @@
/* second time with fp-16 */
BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 4),
BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2),
- /* fetch secound map_value_ptr from the stack */
+ /* fetch second map_value_ptr from the stack */
BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_7, 0),
/* write into map value */
BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0),
@@ -1493,7 +1493,7 @@
/* second time with fp-16 */
BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 4),
BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
- /* fetch secound map_value_ptr from the stack */
+ /* fetch second map_value_ptr from the stack */
BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_7, 0),
/* write into map value */
BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0),
@@ -2380,7 +2380,7 @@
*/
BPF_JMP_REG(BPF_JGT, BPF_REG_6, BPF_REG_7, 1),
BPF_MOV64_REG(BPF_REG_9, BPF_REG_8),
- /* r9 = *r9 ; verifier get's to this point via two paths:
+ /* r9 = *r9 ; verifier gets to this point via two paths:
* ; (I) one including r9 = r8, verified first;
* ; (II) one excluding r9 = r8, verified next.
* ; After load of *r9 to r9 the frame[0].fp[-24].id == r9.id.
diff --git a/tools/testing/selftests/bpf/verify_sig_setup.sh b/tools/testing/selftests/bpf/verify_sig_setup.sh
index f2cac42298ba..09179fb551f0 100755
--- a/tools/testing/selftests/bpf/verify_sig_setup.sh
+++ b/tools/testing/selftests/bpf/verify_sig_setup.sh
@@ -32,7 +32,7 @@ usage()
exit 1
}
-setup()
+genkey()
{
local tmp_dir="$1"
@@ -45,9 +45,14 @@ setup()
openssl x509 -in ${tmp_dir}/signing_key.pem -out \
${tmp_dir}/signing_key.der -outform der
+}
- key_id=$(cat ${tmp_dir}/signing_key.der | keyctl padd asymmetric ebpf_testing_key @s)
+setup()
+{
+ local tmp_dir="$1"
+ genkey "${tmp_dir}"
+ key_id=$(cat ${tmp_dir}/signing_key.der | keyctl padd asymmetric ebpf_testing_key @s)
keyring_id=$(keyctl newring ebpf_testing_keyring @s)
keyctl link $key_id $keyring_id
}
@@ -105,6 +110,8 @@ main()
if [[ "${action}" == "setup" ]]; then
setup "${tmp_dir}"
+ elif [[ "${action}" == "genkey" ]]; then
+ genkey "${tmp_dir}"
elif [[ "${action}" == "cleanup" ]]; then
cleanup "${tmp_dir}"
elif [[ "${action}" == "fsverity-create-sign" ]]; then
diff --git a/tools/testing/selftests/bpf/veristat.c b/tools/testing/selftests/bpf/veristat.c
index d532dd82a3a8..e962f133250c 100644
--- a/tools/testing/selftests/bpf/veristat.c
+++ b/tools/testing/selftests/bpf/veristat.c
@@ -181,6 +181,12 @@ struct var_preset {
bool applied;
};
+enum dump_mode {
+ DUMP_NONE = 0,
+ DUMP_XLATED = 1,
+ DUMP_JITED = 2,
+};
+
static struct env {
char **filenames;
int filename_cnt;
@@ -227,6 +233,7 @@ static struct env {
char orig_cgroup[PATH_MAX];
char stat_cgroup[PATH_MAX];
int memory_peak_fd;
+ __u32 dump_mode;
} env;
static int libbpf_print_fn(enum libbpf_print_level level, const char *format, va_list args)
@@ -271,6 +278,7 @@ const char argp_program_doc[] =
enum {
OPT_LOG_FIXED = 1000,
OPT_LOG_SIZE = 1001,
+ OPT_DUMP = 1002,
};
static const struct argp_option opts[] = {
@@ -295,6 +303,7 @@ static const struct argp_option opts[] = {
"Force BPF verifier failure on register invariant violation (BPF_F_TEST_REG_INVARIANTS program flag)" },
{ "top-src-lines", 'S', "N", 0, "Emit N most frequent source code lines" },
{ "set-global-vars", 'G', "GLOBAL", 0, "Set global variables provided in the expression, for example \"var1 = 1\"" },
+ { "dump", OPT_DUMP, "DUMP_MODE", OPTION_ARG_OPTIONAL, "Print BPF program dump (xlated, jited)" },
{},
};
@@ -427,6 +436,16 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state)
return err;
}
break;
+ case OPT_DUMP:
+ if (!arg || strcasecmp(arg, "xlated") == 0) {
+ env.dump_mode |= DUMP_XLATED;
+ } else if (strcasecmp(arg, "jited") == 0) {
+ env.dump_mode |= DUMP_JITED;
+ } else {
+ fprintf(stderr, "Unrecognized dump mode '%s'\n", arg);
+ return -EINVAL;
+ }
+ break;
default:
return ARGP_ERR_UNKNOWN;
}
@@ -1554,6 +1573,36 @@ static int parse_rvalue(const char *val, struct rvalue *rvalue)
return 0;
}
+static void dump(__u32 prog_id, enum dump_mode mode, const char *file_name, const char *prog_name)
+{
+ char command[64], buf[4096];
+ FILE *fp;
+ int status;
+
+ status = system("command -v bpftool > /dev/null 2>&1");
+ if (status != 0) {
+ fprintf(stderr, "bpftool is not available, can't print program dump\n");
+ return;
+ }
+ snprintf(command, sizeof(command), "bpftool prog dump %s id %u",
+ mode == DUMP_JITED ? "jited" : "xlated", prog_id);
+ fp = popen(command, "r");
+ if (!fp) {
+ fprintf(stderr, "bpftool failed with error: %d\n", errno);
+ return;
+ }
+
+ printf("DUMP (%s) %s/%s:\n", mode == DUMP_JITED ? "JITED" : "XLATED", file_name, prog_name);
+ while (fgets(buf, sizeof(buf), fp))
+ fputs(buf, stdout);
+ fprintf(stdout, "\n");
+
+ if (ferror(fp))
+ fprintf(stderr, "Failed to dump BPF prog with error: %d\n", errno);
+
+ pclose(fp);
+}
+
static int process_prog(const char *filename, struct bpf_object *obj, struct bpf_program *prog)
{
const char *base_filename = basename(strdupa(filename));
@@ -1630,8 +1679,13 @@ static int process_prog(const char *filename, struct bpf_object *obj, struct bpf
memset(&info, 0, info_len);
fd = bpf_program__fd(prog);
- if (fd > 0 && bpf_prog_get_info_by_fd(fd, &info, &info_len) == 0)
+ if (fd > 0 && bpf_prog_get_info_by_fd(fd, &info, &info_len) == 0) {
stats->stats[JITED_SIZE] = info.jited_prog_len;
+ if (env.dump_mode & DUMP_JITED)
+ dump(info.id, DUMP_JITED, base_filename, prog_name);
+ if (env.dump_mode & DUMP_XLATED)
+ dump(info.id, DUMP_XLATED, base_filename, prog_name);
+ }
parse_verif_log(buf, buf_sz, stats);
diff --git a/tools/testing/selftests/bpf/xdping.c b/tools/testing/selftests/bpf/xdping.c
index 1503a1d2faa0..9ed8c796645d 100644
--- a/tools/testing/selftests/bpf/xdping.c
+++ b/tools/testing/selftests/bpf/xdping.c
@@ -155,7 +155,7 @@ int main(int argc, char **argv)
}
if (!server) {
- /* Only supports IPv4; see hints initiailization above. */
+ /* Only supports IPv4; see hints initialization above. */
if (getaddrinfo(argv[optind], NULL, &hints, &a) || !a) {
fprintf(stderr, "Could not resolve %s\n", argv[optind]);
return 1;
diff --git a/tools/testing/selftests/bpf/xsk.h b/tools/testing/selftests/bpf/xsk.h
index 93c2cc413cfc..48729da142c2 100644
--- a/tools/testing/selftests/bpf/xsk.h
+++ b/tools/testing/selftests/bpf/xsk.h
@@ -93,8 +93,8 @@ static inline __u32 xsk_prod_nb_free(struct xsk_ring_prod *r, __u32 nb)
/* Refresh the local tail pointer.
* cached_cons is r->size bigger than the real consumer pointer so
* that this addition can be avoided in the more frequently
- * executed code that computs free_entries in the beginning of
- * this function. Without this optimization it whould have been
+ * executed code that computes free_entries in the beginning of
+ * this function. Without this optimization it would have been
* free_entries = r->cached_prod - r->cached_cons + r->size.
*/
r->cached_cons = __atomic_load_n(r->consumer, __ATOMIC_ACQUIRE);
diff --git a/tools/testing/selftests/bpf/xskxceiver.c b/tools/testing/selftests/bpf/xskxceiver.c
index a29de0713f19..352adc8df2d1 100644
--- a/tools/testing/selftests/bpf/xskxceiver.c
+++ b/tools/testing/selftests/bpf/xskxceiver.c
@@ -2276,25 +2276,13 @@ static int testapp_xdp_metadata_copy(struct test_spec *test)
{
struct xsk_xdp_progs *skel_rx = test->ifobj_rx->xdp_progs;
struct xsk_xdp_progs *skel_tx = test->ifobj_tx->xdp_progs;
- struct bpf_map *data_map;
- int count = 0;
- int key = 0;
test_spec_set_xdp_prog(test, skel_rx->progs.xsk_xdp_populate_metadata,
skel_tx->progs.xsk_xdp_populate_metadata,
skel_rx->maps.xsk, skel_tx->maps.xsk);
test->ifobj_rx->use_metadata = true;
- data_map = bpf_object__find_map_by_name(skel_rx->obj, "xsk_xdp_.bss");
- if (!data_map || !bpf_map__is_internal(data_map)) {
- ksft_print_msg("Error: could not find bss section of XDP program\n");
- return TEST_FAILURE;
- }
-
- if (bpf_map_update_elem(bpf_map__fd(data_map), &key, &count, BPF_ANY)) {
- ksft_print_msg("Error: could not update count element\n");
- return TEST_FAILURE;
- }
+ skel_rx->bss->count = 0;
return testapp_validate_traffic(test);
}
diff --git a/tools/testing/selftests/cgroup/lib/cgroup_util.c b/tools/testing/selftests/cgroup/lib/cgroup_util.c
index 0e89fcff4d05..44c52f620fda 100644
--- a/tools/testing/selftests/cgroup/lib/cgroup_util.c
+++ b/tools/testing/selftests/cgroup/lib/cgroup_util.c
@@ -522,6 +522,18 @@ int proc_mount_contains(const char *option)
return strstr(buf, option) != NULL;
}
+int cgroup_feature(const char *feature)
+{
+ char buf[PAGE_SIZE];
+ ssize_t read;
+
+ read = read_text("/sys/kernel/cgroup/features", buf, sizeof(buf));
+ if (read < 0)
+ return read;
+
+ return strstr(buf, feature) != NULL;
+}
+
ssize_t proc_read_text(int pid, bool thread, const char *item, char *buf, size_t size)
{
char path[PATH_MAX];
diff --git a/tools/testing/selftests/cgroup/lib/include/cgroup_util.h b/tools/testing/selftests/cgroup/lib/include/cgroup_util.h
index c69cab66254b..9dc90a1b386d 100644
--- a/tools/testing/selftests/cgroup/lib/include/cgroup_util.h
+++ b/tools/testing/selftests/cgroup/lib/include/cgroup_util.h
@@ -60,6 +60,7 @@ extern int cg_run_nowait(const char *cgroup,
extern int cg_wait_for_proc_count(const char *cgroup, int count);
extern int cg_killall(const char *cgroup);
int proc_mount_contains(const char *option);
+int cgroup_feature(const char *feature);
extern ssize_t proc_read_text(int pid, bool thread, const char *item, char *buf, size_t size);
extern int proc_read_strstr(int pid, bool thread, const char *item, const char *needle);
extern pid_t clone_into_cgroup(int cgroup_fd);
diff --git a/tools/testing/selftests/cgroup/test_freezer.c b/tools/testing/selftests/cgroup/test_freezer.c
index 8730645d363a..dfb763819581 100644
--- a/tools/testing/selftests/cgroup/test_freezer.c
+++ b/tools/testing/selftests/cgroup/test_freezer.c
@@ -804,6 +804,662 @@ cleanup:
return ret;
}
+/*
+ * Get the current frozen_usec for the cgroup.
+ */
+static long cg_check_freezetime(const char *cgroup)
+{
+ return cg_read_key_long(cgroup, "cgroup.stat.local",
+ "frozen_usec ");
+}
+
+/*
+ * Test that the freeze time will behave as expected for an empty cgroup.
+ */
+static int test_cgfreezer_time_empty(const char *root)
+{
+ int ret = KSFT_FAIL;
+ char *cgroup = NULL;
+ long prev, curr;
+
+ cgroup = cg_name(root, "cg_time_test_empty");
+ if (!cgroup)
+ goto cleanup;
+
+ /*
+ * 1) Create an empty cgroup and check that its freeze time
+ * is 0.
+ */
+ if (cg_create(cgroup))
+ goto cleanup;
+
+ curr = cg_check_freezetime(cgroup);
+ if (curr < 0) {
+ ret = KSFT_SKIP;
+ goto cleanup;
+ }
+ if (curr > 0) {
+ debug("Expect time (%ld) to be 0\n", curr);
+ goto cleanup;
+ }
+
+ if (cg_freeze_nowait(cgroup, true))
+ goto cleanup;
+
+ /*
+ * 2) Sleep for 1000 us. Check that the freeze time is at
+ * least 1000 us.
+ */
+ usleep(1000);
+ curr = cg_check_freezetime(cgroup);
+ if (curr < 1000) {
+ debug("Expect time (%ld) to be at least 1000 us\n",
+ curr);
+ goto cleanup;
+ }
+
+ /*
+ * 3) Unfreeze the cgroup. Check that the freeze time is
+ * larger than at 2).
+ */
+ if (cg_freeze_nowait(cgroup, false))
+ goto cleanup;
+ prev = curr;
+ curr = cg_check_freezetime(cgroup);
+ if (curr <= prev) {
+ debug("Expect time (%ld) to be more than previous check (%ld)\n",
+ curr, prev);
+ goto cleanup;
+ }
+
+ /*
+ * 4) Check the freeze time again to ensure that it has not
+ * changed.
+ */
+ prev = curr;
+ curr = cg_check_freezetime(cgroup);
+ if (curr != prev) {
+ debug("Expect time (%ld) to be unchanged from previous check (%ld)\n",
+ curr, prev);
+ goto cleanup;
+ }
+
+ ret = KSFT_PASS;
+
+cleanup:
+ if (cgroup)
+ cg_destroy(cgroup);
+ free(cgroup);
+ return ret;
+}
+
+/*
+ * A simple test for cgroup freezer time accounting. This test follows
+ * the same flow as test_cgfreezer_time_empty, but with a single process
+ * in the cgroup.
+ */
+static int test_cgfreezer_time_simple(const char *root)
+{
+ int ret = KSFT_FAIL;
+ char *cgroup = NULL;
+ long prev, curr;
+
+ cgroup = cg_name(root, "cg_time_test_simple");
+ if (!cgroup)
+ goto cleanup;
+
+ /*
+ * 1) Create a cgroup and check that its freeze time is 0.
+ */
+ if (cg_create(cgroup))
+ goto cleanup;
+
+ curr = cg_check_freezetime(cgroup);
+ if (curr < 0) {
+ ret = KSFT_SKIP;
+ goto cleanup;
+ }
+ if (curr > 0) {
+ debug("Expect time (%ld) to be 0\n", curr);
+ goto cleanup;
+ }
+
+ /*
+ * 2) Populate the cgroup with one child and check that the
+ * freeze time is still 0.
+ */
+ cg_run_nowait(cgroup, child_fn, NULL);
+ prev = curr;
+ curr = cg_check_freezetime(cgroup);
+ if (curr > prev) {
+ debug("Expect time (%ld) to be 0\n", curr);
+ goto cleanup;
+ }
+
+ if (cg_freeze_nowait(cgroup, true))
+ goto cleanup;
+
+ /*
+ * 3) Sleep for 1000 us. Check that the freeze time is at
+ * least 1000 us.
+ */
+ usleep(1000);
+ prev = curr;
+ curr = cg_check_freezetime(cgroup);
+ if (curr < 1000) {
+ debug("Expect time (%ld) to be at least 1000 us\n",
+ curr);
+ goto cleanup;
+ }
+
+ /*
+ * 4) Unfreeze the cgroup. Check that the freeze time is
+ * larger than at 3).
+ */
+ if (cg_freeze_nowait(cgroup, false))
+ goto cleanup;
+ prev = curr;
+ curr = cg_check_freezetime(cgroup);
+ if (curr <= prev) {
+ debug("Expect time (%ld) to be more than previous check (%ld)\n",
+ curr, prev);
+ goto cleanup;
+ }
+
+ /*
+ * 5) Sleep for 1000 us. Check that the freeze time is the
+ * same as at 4).
+ */
+ usleep(1000);
+ prev = curr;
+ curr = cg_check_freezetime(cgroup);
+ if (curr != prev) {
+ debug("Expect time (%ld) to be unchanged from previous check (%ld)\n",
+ curr, prev);
+ goto cleanup;
+ }
+
+ ret = KSFT_PASS;
+
+cleanup:
+ if (cgroup)
+ cg_destroy(cgroup);
+ free(cgroup);
+ return ret;
+}
+
+/*
+ * Test that freezer time accounting works as expected, even while we're
+ * populating a cgroup with processes.
+ */
+static int test_cgfreezer_time_populate(const char *root)
+{
+ int ret = KSFT_FAIL;
+ char *cgroup = NULL;
+ long prev, curr;
+ int i;
+
+ cgroup = cg_name(root, "cg_time_test_populate");
+ if (!cgroup)
+ goto cleanup;
+
+ if (cg_create(cgroup))
+ goto cleanup;
+
+ curr = cg_check_freezetime(cgroup);
+ if (curr < 0) {
+ ret = KSFT_SKIP;
+ goto cleanup;
+ }
+ if (curr > 0) {
+ debug("Expect time (%ld) to be 0\n", curr);
+ goto cleanup;
+ }
+
+ /*
+ * 1) Populate the cgroup with 100 processes. Check that
+ * the freeze time is 0.
+ */
+ for (i = 0; i < 100; i++)
+ cg_run_nowait(cgroup, child_fn, NULL);
+ prev = curr;
+ curr = cg_check_freezetime(cgroup);
+ if (curr != prev) {
+ debug("Expect time (%ld) to be 0\n", curr);
+ goto cleanup;
+ }
+
+ /*
+ * 2) Wait for the group to become fully populated. Check
+ * that the freeze time is 0.
+ */
+ if (cg_wait_for_proc_count(cgroup, 100))
+ goto cleanup;
+ prev = curr;
+ curr = cg_check_freezetime(cgroup);
+ if (curr != prev) {
+ debug("Expect time (%ld) to be 0\n", curr);
+ goto cleanup;
+ }
+
+ /*
+ * 3) Freeze the cgroup and then populate it with 100 more
+ * processes. Check that the freeze time continues to grow.
+ */
+ if (cg_freeze_nowait(cgroup, true))
+ goto cleanup;
+ prev = curr;
+ curr = cg_check_freezetime(cgroup);
+ if (curr <= prev) {
+ debug("Expect time (%ld) to be more than previous check (%ld)\n",
+ curr, prev);
+ goto cleanup;
+ }
+
+ for (i = 0; i < 100; i++)
+ cg_run_nowait(cgroup, child_fn, NULL);
+ prev = curr;
+ curr = cg_check_freezetime(cgroup);
+ if (curr <= prev) {
+ debug("Expect time (%ld) to be more than previous check (%ld)\n",
+ curr, prev);
+ goto cleanup;
+ }
+
+ /*
+ * 4) Wait for the group to become fully populated. Check
+ * that the freeze time is larger than at 3).
+ */
+ if (cg_wait_for_proc_count(cgroup, 200))
+ goto cleanup;
+ prev = curr;
+ curr = cg_check_freezetime(cgroup);
+ if (curr <= prev) {
+ debug("Expect time (%ld) to be more than previous check (%ld)\n",
+ curr, prev);
+ goto cleanup;
+ }
+
+ /*
+ * 5) Unfreeze the cgroup. Check that the freeze time is
+ * larger than at 4).
+ */
+ if (cg_freeze_nowait(cgroup, false))
+ goto cleanup;
+ prev = curr;
+ curr = cg_check_freezetime(cgroup);
+ if (curr <= prev) {
+ debug("Expect time (%ld) to be more than previous check (%ld)\n",
+ curr, prev);
+ goto cleanup;
+ }
+
+ /*
+ * 6) Kill the processes. Check that the freeze time is the
+ * same as it was at 5).
+ */
+ if (cg_killall(cgroup))
+ goto cleanup;
+ prev = curr;
+ curr = cg_check_freezetime(cgroup);
+ if (curr != prev) {
+ debug("Expect time (%ld) to be unchanged from previous check (%ld)\n",
+ curr, prev);
+ goto cleanup;
+ }
+
+ /*
+ * 7) Freeze and unfreeze the cgroup. Check that the freeze
+ * time is larger than it was at 6).
+ */
+ if (cg_freeze_nowait(cgroup, true))
+ goto cleanup;
+ if (cg_freeze_nowait(cgroup, false))
+ goto cleanup;
+ prev = curr;
+ curr = cg_check_freezetime(cgroup);
+ if (curr <= prev) {
+ debug("Expect time (%ld) to be more than previous check (%ld)\n",
+ curr, prev);
+ goto cleanup;
+ }
+
+ ret = KSFT_PASS;
+
+cleanup:
+ if (cgroup)
+ cg_destroy(cgroup);
+ free(cgroup);
+ return ret;
+}
+
+/*
+ * Test that frozen time for a cgroup continues to work as expected,
+ * even as processes are migrated. Frozen cgroup A's freeze time should
+ * continue to increase and running cgroup B's should stay 0.
+ */
+static int test_cgfreezer_time_migrate(const char *root)
+{
+ long prev_A, curr_A, curr_B;
+ char *cgroup[2] = {0};
+ int ret = KSFT_FAIL;
+ int pid;
+
+ cgroup[0] = cg_name(root, "cg_time_test_migrate_A");
+ if (!cgroup[0])
+ goto cleanup;
+
+ cgroup[1] = cg_name(root, "cg_time_test_migrate_B");
+ if (!cgroup[1])
+ goto cleanup;
+
+ if (cg_create(cgroup[0]))
+ goto cleanup;
+
+ if (cg_check_freezetime(cgroup[0]) < 0) {
+ ret = KSFT_SKIP;
+ goto cleanup;
+ }
+
+ if (cg_create(cgroup[1]))
+ goto cleanup;
+
+ pid = cg_run_nowait(cgroup[0], child_fn, NULL);
+ if (pid < 0)
+ goto cleanup;
+
+ if (cg_wait_for_proc_count(cgroup[0], 1))
+ goto cleanup;
+
+ curr_A = cg_check_freezetime(cgroup[0]);
+ if (curr_A) {
+ debug("Expect time (%ld) to be 0\n", curr_A);
+ goto cleanup;
+ }
+ curr_B = cg_check_freezetime(cgroup[1]);
+ if (curr_B) {
+ debug("Expect time (%ld) to be 0\n", curr_B);
+ goto cleanup;
+ }
+
+ /*
+ * Freeze cgroup A.
+ */
+ if (cg_freeze_wait(cgroup[0], true))
+ goto cleanup;
+ prev_A = curr_A;
+ curr_A = cg_check_freezetime(cgroup[0]);
+ if (curr_A <= prev_A) {
+ debug("Expect time (%ld) to be > 0\n", curr_A);
+ goto cleanup;
+ }
+
+ /*
+ * Migrate from A (frozen) to B (running).
+ */
+ if (cg_enter(cgroup[1], pid))
+ goto cleanup;
+
+ usleep(1000);
+ curr_B = cg_check_freezetime(cgroup[1]);
+ if (curr_B) {
+ debug("Expect time (%ld) to be 0\n", curr_B);
+ goto cleanup;
+ }
+
+ prev_A = curr_A;
+ curr_A = cg_check_freezetime(cgroup[0]);
+ if (curr_A <= prev_A) {
+ debug("Expect time (%ld) to be more than previous check (%ld)\n",
+ curr_A, prev_A);
+ goto cleanup;
+ }
+
+ ret = KSFT_PASS;
+
+cleanup:
+ if (cgroup[0])
+ cg_destroy(cgroup[0]);
+ free(cgroup[0]);
+ if (cgroup[1])
+ cg_destroy(cgroup[1]);
+ free(cgroup[1]);
+ return ret;
+}
+
+/*
+ * The test creates a cgroup and freezes it. Then it creates a child cgroup.
+ * After that it checks that the child cgroup has a non-zero freeze time
+ * that is less than the parent's. Next, it freezes the child, unfreezes
+ * the parent, and sleeps. Finally, it checks that the child's freeze
+ * time has grown larger than the parent's.
+ */
+static int test_cgfreezer_time_parent(const char *root)
+{
+ char *parent, *child = NULL;
+ int ret = KSFT_FAIL;
+ long ptime, ctime;
+
+ parent = cg_name(root, "cg_test_parent_A");
+ if (!parent)
+ goto cleanup;
+
+ child = cg_name(parent, "cg_test_parent_B");
+ if (!child)
+ goto cleanup;
+
+ if (cg_create(parent))
+ goto cleanup;
+
+ if (cg_check_freezetime(parent) < 0) {
+ ret = KSFT_SKIP;
+ goto cleanup;
+ }
+
+ if (cg_freeze_wait(parent, true))
+ goto cleanup;
+
+ usleep(1000);
+ if (cg_create(child))
+ goto cleanup;
+
+ if (cg_check_frozen(child, true))
+ goto cleanup;
+
+ /*
+ * Since the parent was frozen the entire time the child cgroup
+ * was being created, we expect the parent's freeze time to be
+ * larger than the child's.
+ *
+ * Ideally, we would be able to check both times simultaneously,
+ * but here we get the child's after we get the parent's.
+ */
+ ptime = cg_check_freezetime(parent);
+ ctime = cg_check_freezetime(child);
+ if (ptime <= ctime) {
+ debug("Expect ptime (%ld) > ctime (%ld)\n", ptime, ctime);
+ goto cleanup;
+ }
+
+ if (cg_freeze_nowait(child, true))
+ goto cleanup;
+
+ if (cg_freeze_wait(parent, false))
+ goto cleanup;
+
+ if (cg_check_frozen(child, true))
+ goto cleanup;
+
+ usleep(100000);
+
+ ctime = cg_check_freezetime(child);
+ ptime = cg_check_freezetime(parent);
+
+ if (ctime <= ptime) {
+ debug("Expect ctime (%ld) > ptime (%ld)\n", ctime, ptime);
+ goto cleanup;
+ }
+
+ ret = KSFT_PASS;
+
+cleanup:
+ if (child)
+ cg_destroy(child);
+ free(child);
+ if (parent)
+ cg_destroy(parent);
+ free(parent);
+ return ret;
+}
+
+/*
+ * The test creates a parent cgroup and a child cgroup. Then, it freezes
+ * the child and checks that the child's freeze time is greater than the
+ * parent's, which should be zero.
+ */
+static int test_cgfreezer_time_child(const char *root)
+{
+ char *parent, *child = NULL;
+ int ret = KSFT_FAIL;
+ long ptime, ctime;
+
+ parent = cg_name(root, "cg_test_child_A");
+ if (!parent)
+ goto cleanup;
+
+ child = cg_name(parent, "cg_test_child_B");
+ if (!child)
+ goto cleanup;
+
+ if (cg_create(parent))
+ goto cleanup;
+
+ if (cg_check_freezetime(parent) < 0) {
+ ret = KSFT_SKIP;
+ goto cleanup;
+ }
+
+ if (cg_create(child))
+ goto cleanup;
+
+ if (cg_freeze_wait(child, true))
+ goto cleanup;
+
+ ctime = cg_check_freezetime(child);
+ ptime = cg_check_freezetime(parent);
+ if (ptime != 0) {
+ debug("Expect ptime (%ld) to be 0\n", ptime);
+ goto cleanup;
+ }
+
+ if (ctime <= ptime) {
+ debug("Expect ctime (%ld) <= ptime (%ld)\n", ctime, ptime);
+ goto cleanup;
+ }
+
+ ret = KSFT_PASS;
+
+cleanup:
+ if (child)
+ cg_destroy(child);
+ free(child);
+ if (parent)
+ cg_destroy(parent);
+ free(parent);
+ return ret;
+}
+
+/*
+ * The test creates the following hierarchy:
+ * A
+ * |
+ * B
+ * |
+ * C
+ *
+ * Then it freezes the cgroups in the order C, B, A.
+ * Then it unfreezes the cgroups in the order A, B, C.
+ * Then it checks that C's freeze time is larger than B's and
+ * that B's is larger than A's.
+ */
+static int test_cgfreezer_time_nested(const char *root)
+{
+ char *cgroup[3] = {0};
+ int ret = KSFT_FAIL;
+ long time[3] = {0};
+ int i;
+
+ cgroup[0] = cg_name(root, "cg_test_time_A");
+ if (!cgroup[0])
+ goto cleanup;
+
+ cgroup[1] = cg_name(cgroup[0], "B");
+ if (!cgroup[1])
+ goto cleanup;
+
+ cgroup[2] = cg_name(cgroup[1], "C");
+ if (!cgroup[2])
+ goto cleanup;
+
+ if (cg_create(cgroup[0]))
+ goto cleanup;
+
+ if (cg_check_freezetime(cgroup[0]) < 0) {
+ ret = KSFT_SKIP;
+ goto cleanup;
+ }
+
+ if (cg_create(cgroup[1]))
+ goto cleanup;
+
+ if (cg_create(cgroup[2]))
+ goto cleanup;
+
+ if (cg_freeze_nowait(cgroup[2], true))
+ goto cleanup;
+
+ if (cg_freeze_nowait(cgroup[1], true))
+ goto cleanup;
+
+ if (cg_freeze_nowait(cgroup[0], true))
+ goto cleanup;
+
+ usleep(1000);
+
+ if (cg_freeze_nowait(cgroup[0], false))
+ goto cleanup;
+
+ if (cg_freeze_nowait(cgroup[1], false))
+ goto cleanup;
+
+ if (cg_freeze_nowait(cgroup[2], false))
+ goto cleanup;
+
+ time[2] = cg_check_freezetime(cgroup[2]);
+ time[1] = cg_check_freezetime(cgroup[1]);
+ time[0] = cg_check_freezetime(cgroup[0]);
+
+ if (time[2] <= time[1]) {
+ debug("Expect C's time (%ld) > B's time (%ld)", time[2], time[1]);
+ goto cleanup;
+ }
+
+ if (time[1] <= time[0]) {
+ debug("Expect B's time (%ld) > A's time (%ld)", time[1], time[0]);
+ goto cleanup;
+ }
+
+ ret = KSFT_PASS;
+
+cleanup:
+ for (i = 2; i >= 0 && cgroup[i]; i--) {
+ cg_destroy(cgroup[i]);
+ free(cgroup[i]);
+ }
+
+ return ret;
+}
+
#define T(x) { x, #x }
struct cgfreezer_test {
int (*fn)(const char *root);
@@ -819,6 +1475,13 @@ struct cgfreezer_test {
T(test_cgfreezer_stopped),
T(test_cgfreezer_ptraced),
T(test_cgfreezer_vfork),
+ T(test_cgfreezer_time_empty),
+ T(test_cgfreezer_time_simple),
+ T(test_cgfreezer_time_populate),
+ T(test_cgfreezer_time_migrate),
+ T(test_cgfreezer_time_parent),
+ T(test_cgfreezer_time_child),
+ T(test_cgfreezer_time_nested),
};
#undef T
diff --git a/tools/testing/selftests/cgroup/test_pids.c b/tools/testing/selftests/cgroup/test_pids.c
index 9ecb83c6cc5c..d8a1d1cd5007 100644
--- a/tools/testing/selftests/cgroup/test_pids.c
+++ b/tools/testing/selftests/cgroup/test_pids.c
@@ -77,6 +77,9 @@ static int test_pids_events(const char *root)
char *cg_parent = NULL, *cg_child = NULL;
int pid;
+ if (cgroup_feature("pids_localevents") <= 0)
+ return KSFT_SKIP;
+
cg_parent = cg_name(root, "pids_parent");
cg_child = cg_name(cg_parent, "pids_child");
if (!cg_parent || !cg_child)
diff --git a/tools/testing/selftests/damon/Makefile b/tools/testing/selftests/damon/Makefile
index 9a3499827d4b..2180c328a825 100644
--- a/tools/testing/selftests/damon/Makefile
+++ b/tools/testing/selftests/damon/Makefile
@@ -5,6 +5,7 @@ TEST_GEN_FILES += access_memory access_memory_even
TEST_FILES = _damon_sysfs.py
TEST_FILES += drgn_dump_damon_status.py
+TEST_FILES += _common.sh
# functionality tests
TEST_PROGS += sysfs.sh
@@ -18,6 +19,7 @@ TEST_PROGS += reclaim.sh lru_sort.sh
TEST_PROGS += sysfs_update_removed_scheme_dir.sh
TEST_PROGS += sysfs_update_schemes_tried_regions_hang.py
TEST_PROGS += sysfs_memcg_path_leak.sh
+TEST_PROGS += sysfs_no_op_commit_break.py
EXTRA_CLEAN = __pycache__
diff --git a/tools/testing/selftests/damon/access_memory_even.c b/tools/testing/selftests/damon/access_memory_even.c
index a9f4e9aaf3a9..93f3a71bcfd4 100644
--- a/tools/testing/selftests/damon/access_memory_even.c
+++ b/tools/testing/selftests/damon/access_memory_even.c
@@ -9,7 +9,6 @@
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
-#include <time.h>
int main(int argc, char *argv[])
{
diff --git a/tools/testing/selftests/damon/sysfs_no_op_commit_break.py b/tools/testing/selftests/damon/sysfs_no_op_commit_break.py
new file mode 100755
index 000000000000..2c65cffe6b54
--- /dev/null
+++ b/tools/testing/selftests/damon/sysfs_no_op_commit_break.py
@@ -0,0 +1,72 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+import json
+import os
+import subprocess
+import sys
+
+import _damon_sysfs
+
+def dump_damon_status_dict(pid):
+ try:
+ subprocess.check_output(['which', 'drgn'], stderr=subprocess.DEVNULL)
+ except:
+ return None, 'drgn not found'
+ file_dir = os.path.dirname(os.path.abspath(__file__))
+ dump_script = os.path.join(file_dir, 'drgn_dump_damon_status.py')
+ rc = subprocess.call(['drgn', dump_script, pid, 'damon_dump_output'],
+ stderr=subprocess.DEVNULL)
+
+ if rc != 0:
+ return None, f'drgn fail: return code({rc})'
+ try:
+ with open('damon_dump_output', 'r') as f:
+ return json.load(f), None
+ except Exception as e:
+ return None, 'json.load fail (%s)' % e
+
+def main():
+ kdamonds = _damon_sysfs.Kdamonds(
+ [_damon_sysfs.Kdamond(
+ contexts=[_damon_sysfs.DamonCtx(
+ schemes=[_damon_sysfs.Damos(
+ ops_filters=[
+ _damon_sysfs.DamosFilter(
+ type_='anon',
+ matching=True,
+ allow=True,
+ )
+ ]
+ )],
+ )])]
+ )
+
+ err = kdamonds.start()
+ if err is not None:
+ print('kdamond start failed: %s' % err)
+ exit(1)
+
+ before_commit_status, err = \
+ dump_damon_status_dict(kdamonds.kdamonds[0].pid)
+ if err is not None:
+ print('before-commit status dump failed: %s' % err)
+ exit(1)
+
+ kdamonds.kdamonds[0].commit()
+
+ after_commit_status, err = \
+ dump_damon_status_dict(kdamonds.kdamonds[0].pid)
+ if err is not None:
+ print('after-commit status dump failed: %s' % err)
+ exit(1)
+
+ if before_commit_status != after_commit_status:
+ print(f'before: {json.dumps(before_commit_status, indent=2)}')
+ print(f'after: {json.dumps(after_commit_status, indent=2)}')
+ exit(1)
+
+ kdamonds.stop()
+
+if __name__ == '__main__':
+ main()
diff --git a/tools/testing/selftests/drivers/net/.gitignore b/tools/testing/selftests/drivers/net/.gitignore
index d634d8395d90..585ecb4d5dc4 100644
--- a/tools/testing/selftests/drivers/net/.gitignore
+++ b/tools/testing/selftests/drivers/net/.gitignore
@@ -1,2 +1,3 @@
# SPDX-License-Identifier: GPL-2.0-only
napi_id_helper
+psp_responder
diff --git a/tools/testing/selftests/drivers/net/Makefile b/tools/testing/selftests/drivers/net/Makefile
index 984ece05f7f9..bd3af9a34e2f 100644
--- a/tools/testing/selftests/drivers/net/Makefile
+++ b/tools/testing/selftests/drivers/net/Makefile
@@ -19,6 +19,7 @@ TEST_PROGS := \
netcons_sysdata.sh \
netpoll_basic.py \
ping.py \
+ psp.py \
queues.py \
stats.py \
shaper.py \
@@ -26,4 +27,13 @@ TEST_PROGS := \
xdp.py \
# end of TEST_PROGS
+# YNL files, must be before "include ..lib.mk"
+YNL_GEN_FILES := psp_responder
+TEST_GEN_FILES += $(YNL_GEN_FILES)
+
include ../../lib.mk
+
+# YNL build
+YNL_GENS := psp
+
+include ../../net/ynl.mk
diff --git a/tools/testing/selftests/drivers/net/bonding/Makefile b/tools/testing/selftests/drivers/net/bonding/Makefile
index 44b98f17f8ff..2f095cf67d9a 100644
--- a/tools/testing/selftests/drivers/net/bonding/Makefile
+++ b/tools/testing/selftests/drivers/net/bonding/Makefile
@@ -11,7 +11,9 @@ TEST_PROGS := \
bond_options.sh \
bond-eth-type-change.sh \
bond_macvlan_ipvlan.sh \
- bond_passive_lacp.sh
+ bond_passive_lacp.sh \
+ bond_lacp_prio.sh
+ bond_ipsec_offload.sh
TEST_FILES := \
lag_lib.sh \
diff --git a/tools/testing/selftests/drivers/net/bonding/bond_ipsec_offload.sh b/tools/testing/selftests/drivers/net/bonding/bond_ipsec_offload.sh
new file mode 100755
index 000000000000..f09e100232c7
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/bonding/bond_ipsec_offload.sh
@@ -0,0 +1,156 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# IPsec over bonding offload test:
+#
+# +----------------+
+# | bond0 |
+# | | |
+# | eth0 eth1 |
+# +---+-------+----+
+#
+# We use netdevsim instead of physical interfaces
+#-------------------------------------------------------------------
+# Example commands
+# ip x s add proto esp src 192.0.2.1 dst 192.0.2.2 \
+# spi 0x07 mode transport reqid 0x07 replay-window 32 \
+# aead 'rfc4106(gcm(aes))' 1234567890123456dcba 128 \
+# sel src 192.0.2.1/24 dst 192.0.2.2/24
+# offload dev bond0 dir out
+# ip x p add dir out src 192.0.2.1/24 dst 192.0.2.2/24 \
+# tmpl proto esp src 192.0.2.1 dst 192.0.2.2 \
+# spi 0x07 mode transport reqid 0x07
+#
+#-------------------------------------------------------------------
+
+lib_dir=$(dirname "$0")
+# shellcheck disable=SC1091
+source "$lib_dir"/../../../net/lib.sh
+srcip=192.0.2.1
+dstip=192.0.2.2
+ipsec0=/sys/kernel/debug/netdevsim/netdevsim0/ports/0/ipsec
+ipsec1=/sys/kernel/debug/netdevsim/netdevsim0/ports/1/ipsec
+active_slave=""
+
+# shellcheck disable=SC2317
+active_slave_changed()
+{
+ local old_active_slave=$1
+ local new_active_slave
+
+ # shellcheck disable=SC2154
+ new_active_slave=$(ip -n "${ns}" -d -j link show bond0 | \
+ jq -r ".[].linkinfo.info_data.active_slave")
+ [ "$new_active_slave" != "$old_active_slave" ] && [ "$new_active_slave" != "null" ]
+}
+
+test_offload()
+{
+ # use ping to exercise the Tx path
+ ip netns exec "$ns" ping -I bond0 -c 3 -W 1 -i 0 "$dstip" >/dev/null
+
+ active_slave=$(ip -n "${ns}" -d -j link show bond0 | \
+ jq -r ".[].linkinfo.info_data.active_slave")
+
+ if [ "$active_slave" = "$nic0" ]; then
+ sysfs=$ipsec0
+ elif [ "$active_slave" = "$nic1" ]; then
+ sysfs=$ipsec1
+ else
+ check_err 1 "bond_ipsec_offload invalid active_slave $active_slave"
+ fi
+
+ # The tx/rx order in sysfs may changed after failover
+ grep -q "SA count=2 tx=3" "$sysfs" && grep -q "tx ipaddr=$dstip" "$sysfs"
+ check_err $? "incorrect tx count with link ${active_slave}"
+
+ log_test bond_ipsec_offload "active_slave ${active_slave}"
+}
+
+setup_env()
+{
+ if ! mount | grep -q debugfs; then
+ mount -t debugfs none /sys/kernel/debug/ &> /dev/null
+ defer umount /sys/kernel/debug/
+
+ fi
+
+ # setup netdevsim since dummy/veth dev doesn't have offload support
+ if [ ! -w /sys/bus/netdevsim/new_device ] ; then
+ if ! modprobe -q netdevsim; then
+ echo "SKIP: can't load netdevsim for ipsec offload"
+ # shellcheck disable=SC2154
+ exit "$ksft_skip"
+ fi
+ defer modprobe -r netdevsim
+ fi
+
+ setup_ns ns
+ defer cleanup_ns "$ns"
+}
+
+setup_bond()
+{
+ ip -n "$ns" link add bond0 type bond mode active-backup miimon 100
+ ip -n "$ns" addr add "$srcip/24" dev bond0
+ ip -n "$ns" link set bond0 up
+
+ echo "0 2" | ip netns exec "$ns" tee /sys/bus/netdevsim/new_device >/dev/null
+ nic0=$(ip netns exec "$ns" ls /sys/bus/netdevsim/devices/netdevsim0/net | head -n 1)
+ nic1=$(ip netns exec "$ns" ls /sys/bus/netdevsim/devices/netdevsim0/net | tail -n 1)
+ ip -n "$ns" link set "$nic0" master bond0
+ ip -n "$ns" link set "$nic1" master bond0
+
+ # we didn't create a peer, make sure we can Tx by adding a permanent
+ # neighbour this need to be added after enslave
+ ip -n "$ns" neigh add "$dstip" dev bond0 lladdr 00:11:22:33:44:55
+
+ # create offloaded SAs, both in and out
+ ip -n "$ns" x p add dir out src "$srcip/24" dst "$dstip/24" \
+ tmpl proto esp src "$srcip" dst "$dstip" spi 9 \
+ mode transport reqid 42
+
+ ip -n "$ns" x p add dir in src "$dstip/24" dst "$srcip/24" \
+ tmpl proto esp src "$dstip" dst "$srcip" spi 9 \
+ mode transport reqid 42
+
+ ip -n "$ns" x s add proto esp src "$srcip" dst "$dstip" spi 9 \
+ mode transport reqid 42 aead "rfc4106(gcm(aes))" \
+ 0x3132333435363738393031323334353664636261 128 \
+ sel src "$srcip/24" dst "$dstip/24" \
+ offload dev bond0 dir out
+
+ ip -n "$ns" x s add proto esp src "$dstip" dst "$srcip" spi 9 \
+ mode transport reqid 42 aead "rfc4106(gcm(aes))" \
+ 0x3132333435363738393031323334353664636261 128 \
+ sel src "$dstip/24" dst "$srcip/24" \
+ offload dev bond0 dir in
+
+ # does offload show up in ip output
+ lines=$(ip -n "$ns" x s list | grep -c "crypto offload parameters: dev bond0 dir")
+ if [ "$lines" -ne 2 ] ; then
+ check_err 1 "bond_ipsec_offload SA offload missing from list output"
+ fi
+}
+
+trap defer_scopes_cleanup EXIT
+setup_env
+setup_bond
+
+# start Offload testing
+test_offload
+
+# do failover and re-test
+ip -n "$ns" link set "$active_slave" down
+slowwait 5 active_slave_changed "$active_slave"
+test_offload
+
+# make sure offload get removed from driver
+ip -n "$ns" x s flush
+ip -n "$ns" x p flush
+line0=$(grep -c "SA count=0" "$ipsec0")
+line1=$(grep -c "SA count=0" "$ipsec1")
+[ "$line0" -ne 1 ] || [ "$line1" -ne 1 ]
+check_fail $? "bond_ipsec_offload SA not removed from driver"
+
+exit "$EXIT_STATUS"
diff --git a/tools/testing/selftests/drivers/net/bonding/bond_lacp_prio.sh b/tools/testing/selftests/drivers/net/bonding/bond_lacp_prio.sh
new file mode 100755
index 000000000000..a483d505c6a8
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/bonding/bond_lacp_prio.sh
@@ -0,0 +1,108 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Testing if bond lacp per port priority works
+#
+# Switch (s_ns) Backup Switch (b_ns)
+# +-------------------------+ +-------------------------+
+# | bond0 | | bond0 |
+# | + | | + |
+# | eth0 | eth1 | | eth0 | eth1 |
+# | +---+---+ | | +---+---+ |
+# | | | | | | | |
+# +-------------------------+ +-------------------------+
+# | | | |
+# +-----------------------------------------------------+
+# | | | | | |
+# | +-------+---------+---------+-------+ |
+# | eth0 eth1 | eth2 eth3 |
+# | + |
+# | bond0 |
+# +-----------------------------------------------------+
+# Client (c_ns)
+
+lib_dir=$(dirname "$0")
+# shellcheck disable=SC1091
+source "$lib_dir"/../../../net/lib.sh
+
+setup_links()
+{
+ # shellcheck disable=SC2154
+ ip -n "${c_ns}" link add eth0 type veth peer name eth0 netns "${s_ns}"
+ ip -n "${c_ns}" link add eth1 type veth peer name eth1 netns "${s_ns}"
+ # shellcheck disable=SC2154
+ ip -n "${c_ns}" link add eth2 type veth peer name eth0 netns "${b_ns}"
+ ip -n "${c_ns}" link add eth3 type veth peer name eth1 netns "${b_ns}"
+
+ ip -n "${c_ns}" link add bond0 type bond mode 802.3ad miimon 100 \
+ lacp_rate fast ad_select actor_port_prio
+ ip -n "${s_ns}" link add bond0 type bond mode 802.3ad miimon 100 \
+ lacp_rate fast
+ ip -n "${b_ns}" link add bond0 type bond mode 802.3ad miimon 100 \
+ lacp_rate fast
+
+ ip -n "${c_ns}" link set eth0 master bond0
+ ip -n "${c_ns}" link set eth1 master bond0
+ ip -n "${c_ns}" link set eth2 master bond0
+ ip -n "${c_ns}" link set eth3 master bond0
+ ip -n "${s_ns}" link set eth0 master bond0
+ ip -n "${s_ns}" link set eth1 master bond0
+ ip -n "${b_ns}" link set eth0 master bond0
+ ip -n "${b_ns}" link set eth1 master bond0
+
+ ip -n "${c_ns}" link set bond0 up
+ ip -n "${s_ns}" link set bond0 up
+ ip -n "${b_ns}" link set bond0 up
+}
+
+test_port_prio_setting()
+{
+ RET=0
+ ip -n "${c_ns}" link set eth0 type bond_slave actor_port_prio 1000
+ prio=$(cmd_jq "ip -n ${c_ns} -d -j link show eth0" \
+ ".[].linkinfo.info_slave_data.actor_port_prio")
+ [ "$prio" -ne 1000 ] && RET=1
+ ip -n "${c_ns}" link set eth2 type bond_slave actor_port_prio 10
+ prio=$(cmd_jq "ip -n ${c_ns} -d -j link show eth2" \
+ ".[].linkinfo.info_slave_data.actor_port_prio")
+ [ "$prio" -ne 10 ] && RET=1
+}
+
+test_agg_reselect()
+{
+ local bond_agg_id slave_agg_id
+ local expect_slave="$1"
+ RET=0
+
+ # Trigger link state change to reselect the aggregator
+ ip -n "${c_ns}" link set eth1 down
+ sleep 0.5
+ ip -n "${c_ns}" link set eth1 up
+ sleep 0.5
+
+ bond_agg_id=$(cmd_jq "ip -n ${c_ns} -d -j link show bond0" \
+ ".[].linkinfo.info_data.ad_info.aggregator")
+ slave_agg_id=$(cmd_jq "ip -n ${c_ns} -d -j link show $expect_slave" \
+ ".[].linkinfo.info_slave_data.ad_aggregator_id")
+ # shellcheck disable=SC2034
+ [ "${bond_agg_id}" -ne "${slave_agg_id}" ] && \
+ RET=1
+}
+
+trap cleanup_all_ns EXIT
+setup_ns c_ns s_ns b_ns
+setup_links
+
+test_port_prio_setting
+log_test "bond 802.3ad" "actor_port_prio setting"
+
+test_agg_reselect eth0
+log_test "bond 802.3ad" "actor_port_prio select"
+
+# Change the actor port prio and re-test
+ip -n "${c_ns}" link set eth0 type bond_slave actor_port_prio 10
+ip -n "${c_ns}" link set eth2 type bond_slave actor_port_prio 1000
+test_agg_reselect eth2
+log_test "bond 802.3ad" "actor_port_prio switch"
+
+exit "${EXIT_STATUS}"
diff --git a/tools/testing/selftests/drivers/net/bonding/bond_options.sh b/tools/testing/selftests/drivers/net/bonding/bond_options.sh
index 7bc148889ca7..187b478d0ddf 100755
--- a/tools/testing/selftests/drivers/net/bonding/bond_options.sh
+++ b/tools/testing/selftests/drivers/net/bonding/bond_options.sh
@@ -7,6 +7,8 @@ ALL_TESTS="
prio
arp_validate
num_grat_arp
+ fail_over_mac
+ vlan_over_bond
"
lib_dir=$(dirname "$0")
@@ -352,8 +354,8 @@ garp_test()
exp_num=$(echo "${param}" | cut -f6 -d ' ')
active_slave=$(cmd_jq "ip -n ${s_ns} -d -j link show bond0" ".[].linkinfo.info_data.active_slave")
- slowwait_for_counter $((exp_num + 5)) $exp_num \
- tc_rule_handle_stats_get "dev s${active_slave#eth} ingress" 101 ".packets" "-n ${g_ns}"
+ slowwait_for_counter $((exp_num + 5)) $exp_num tc_rule_handle_stats_get \
+ "dev s${active_slave#eth} ingress" 101 ".packets" "-n ${g_ns}" &> /dev/null
# check result
real_num=$(tc_rule_handle_stats_get "dev s${active_slave#eth} ingress" 101 ".packets" "-n ${g_ns}")
@@ -376,6 +378,197 @@ num_grat_arp()
done
}
+check_all_mac_same()
+{
+ RET=0
+ # all slaves should have same mac address (with the first port's mac)
+ local bond_mac=$(ip -n "$s_ns" -j link show bond0 | jq -r '.[]["address"]')
+ local eth0_mac=$(ip -n "$s_ns" -j link show eth0 | jq -r '.[]["address"]')
+ local eth1_mac=$(ip -n "$s_ns" -j link show eth1 | jq -r '.[]["address"]')
+ local eth2_mac=$(ip -n "$s_ns" -j link show eth2 | jq -r '.[]["address"]')
+ if [ "$bond_mac" != "${mac[0]}" ] || [ "$eth0_mac" != "$bond_mac" ] || \
+ [ "$eth1_mac" != "$bond_mac" ] || [ "$eth2_mac" != "$bond_mac" ]; then
+ RET=1
+ fi
+}
+
+check_bond_mac_same_with_first()
+{
+ RET=0
+ # bond mac address should be same with the first added slave
+ local bond_mac=$(ip -n "$s_ns" -j link show bond0 | jq -r '.[]["address"]')
+ if [ "$bond_mac" != "${mac[0]}" ]; then
+ RET=1
+ fi
+}
+
+check_bond_mac_same_with_active()
+{
+ RET=0
+ # bond mac address should be same with active slave
+ local bond_mac=$(ip -n "$s_ns" -j link show bond0 | jq -r '.[]["address"]')
+ local active_slave=$(cmd_jq "ip -n ${s_ns} -d -j link show bond0" ".[].linkinfo.info_data.active_slave")
+ local active_slave_mac=$(ip -n "$s_ns" -j link show "$active_slave" | jq -r '.[]["address"]')
+ if [ "$bond_mac" != "$active_slave_mac" ]; then
+ RET=1
+ fi
+}
+
+check_backup_slave_mac_not_change()
+{
+ RET=0
+ # backup slave's mac address is not changed
+ if ip -n "$s_ns" -d -j link show type bond_slave | jq -e '.[]
+ | select(.linkinfo.info_slave_data.state=="BACKUP")
+ | select(.address != .linkinfo.info_slave_data.perm_hwaddr)' &> /dev/null; then
+ RET=1
+ fi
+}
+
+check_backup_slave_mac_inherit()
+{
+ local backup_mac
+ RET=0
+
+ # backup slaves should use mac[1] or mac[2]
+ local backup_macs=$(ip -n "$s_ns" -d -j link show type bond_slave | \
+ jq -r '.[] | select(.linkinfo.info_slave_data.state=="BACKUP") | .address')
+ for backup_mac in $backup_macs; do
+ if [ "$backup_mac" != "${mac[1]}" ] && [ "$backup_mac" != "${mac[2]}" ]; then
+ RET=1
+ fi
+ done
+}
+
+check_first_slave_random_mac()
+{
+ RET=0
+ # remove the first added slave and added it back
+ ip -n "$s_ns" link set eth0 nomaster
+ ip -n "$s_ns" link set eth0 master bond0
+
+ # the first slave should use random mac address
+ eth0_mac=$(ip -n "$s_ns" -j link show eth0 | jq -r '.[]["address"]')
+ [ "$eth0_mac" = "${mac[0]}" ] && RET=1
+ log_test "bond fail_over_mac follow" "random first slave mac"
+
+ # remove the first slave, the permanent MAC address should be restored back
+ ip -n "$s_ns" link set eth0 nomaster
+ eth0_mac=$(ip -n "$s_ns" -j link show eth0 | jq -r '.[]["address"]')
+ [ "$eth0_mac" != "${mac[0]}" ] && RET=1
+}
+
+do_active_backup_failover()
+{
+ local active_slave=$(cmd_jq "ip -n ${s_ns} -d -j link show bond0" ".[].linkinfo.info_data.active_slave")
+ ip -n ${s_ns} link set ${active_slave} down
+ slowwait 2 active_slave_changed $active_slave
+ ip -n ${s_ns} link set ${active_slave} up
+}
+
+fail_over_mac()
+{
+ # Bring down the first interface on the switch to force the bond to
+ # select another active interface instead of the first one that joined.
+ ip -n "$g_ns" link set s0 down
+
+ # fail_over_mac none
+ bond_reset "mode active-backup miimon 100 fail_over_mac 0"
+ check_all_mac_same
+ log_test "fail_over_mac 0" "all slaves have same mac"
+ do_active_backup_failover
+ check_all_mac_same
+ log_test "fail_over_mac 0" "failover: all slaves have same mac"
+
+ # fail_over_mac active
+ bond_reset "mode active-backup miimon 100 fail_over_mac 1"
+ check_bond_mac_same_with_active
+ log_test "fail_over_mac 1" "bond mac is same with active slave mac"
+ check_backup_slave_mac_not_change
+ log_test "fail_over_mac 1" "backup slave mac is not changed"
+ do_active_backup_failover
+ check_bond_mac_same_with_active
+ log_test "fail_over_mac 1" "failover: bond mac is same with active slave mac"
+ check_backup_slave_mac_not_change
+ log_test "fail_over_mac 1" "failover: backup slave mac is not changed"
+
+ # fail_over_mac follow
+ bond_reset "mode active-backup miimon 100 fail_over_mac 2"
+ check_bond_mac_same_with_first
+ log_test "fail_over_mac 2" "bond mac is same with first slave mac"
+ check_bond_mac_same_with_active
+ log_test "fail_over_mac 2" "bond mac is same with active slave mac"
+ check_backup_slave_mac_inherit
+ log_test "fail_over_mac 2" "backup slave mac inherit"
+ do_active_backup_failover
+ check_bond_mac_same_with_first
+ log_test "fail_over_mac 2" "failover: bond mac is same with first slave mac"
+ check_bond_mac_same_with_active
+ log_test "fail_over_mac 2" "failover: bond mac is same with active slave mac"
+ check_backup_slave_mac_inherit
+ log_test "fail_over_mac 2" "failover: backup slave mac inherit"
+ check_first_slave_random_mac
+ log_test "fail_over_mac 2" "first slave mac random"
+}
+
+vlan_over_bond_arp()
+{
+ local mode="$1"
+ RET=0
+
+ bond_reset "mode $mode arp_interval 100 arp_ip_target 192.0.3.10"
+ ip -n "${s_ns}" link add bond0.3 link bond0 type vlan id 3
+ ip -n "${s_ns}" link set bond0.3 up
+ ip -n "${s_ns}" addr add 192.0.3.1/24 dev bond0.3
+ ip -n "${s_ns}" addr add 2001:db8::3:1/64 dev bond0.3
+
+ slowwait_for_counter 5 5 tc_rule_handle_stats_get \
+ "dev eth0.3 ingress" 101 ".packets" "-n ${c_ns}" &> /dev/null || RET=1
+ log_test "vlan over bond arp" "$mode"
+}
+
+vlan_over_bond_ns()
+{
+ local mode="$1"
+ RET=0
+
+ if skip_ns; then
+ log_test_skip "vlan_over_bond ns" "$mode"
+ return 0
+ fi
+
+ bond_reset "mode $mode arp_interval 100 ns_ip6_target 2001:db8::3:10"
+ ip -n "${s_ns}" link add bond0.3 link bond0 type vlan id 3
+ ip -n "${s_ns}" link set bond0.3 up
+ ip -n "${s_ns}" addr add 192.0.3.1/24 dev bond0.3
+ ip -n "${s_ns}" addr add 2001:db8::3:1/64 dev bond0.3
+
+ slowwait_for_counter 5 5 tc_rule_handle_stats_get \
+ "dev eth0.3 ingress" 102 ".packets" "-n ${c_ns}" &> /dev/null || RET=1
+ log_test "vlan over bond ns" "$mode"
+}
+
+vlan_over_bond()
+{
+ # add vlan 3 for client
+ ip -n "${c_ns}" link add eth0.3 link eth0 type vlan id 3
+ ip -n "${c_ns}" link set eth0.3 up
+ ip -n "${c_ns}" addr add 192.0.3.10/24 dev eth0.3
+ ip -n "${c_ns}" addr add 2001:db8::3:10/64 dev eth0.3
+
+ # Add tc rule to check the vlan pkts
+ tc -n "${c_ns}" qdisc add dev eth0.3 clsact
+ tc -n "${c_ns}" filter add dev eth0.3 ingress protocol arp \
+ handle 101 flower skip_hw arp_op request \
+ arp_sip 192.0.3.1 arp_tip 192.0.3.10 action pass
+ tc -n "${c_ns}" filter add dev eth0.3 ingress protocol ipv6 \
+ handle 102 flower skip_hw ip_proto icmpv6 \
+ type 135 src_ip 2001:db8::3:1 action pass
+
+ vlan_over_bond_arp "active-backup"
+ vlan_over_bond_ns "active-backup"
+}
+
trap cleanup EXIT
setup_prepare
diff --git a/tools/testing/selftests/drivers/net/bonding/bond_topo_2d1c.sh b/tools/testing/selftests/drivers/net/bonding/bond_topo_2d1c.sh
index 195ef83cfbf1..167aa4a4a12a 100644
--- a/tools/testing/selftests/drivers/net/bonding/bond_topo_2d1c.sh
+++ b/tools/testing/selftests/drivers/net/bonding/bond_topo_2d1c.sh
@@ -39,6 +39,8 @@ g_ip4="192.0.2.254"
s_ip6="2001:db8::1"
c_ip6="2001:db8::10"
g_ip6="2001:db8::254"
+mac[0]="00:0a:0b:0c:0d:01"
+mac[1]="00:0a:0b:0c:0d:02"
gateway_create()
{
@@ -62,6 +64,7 @@ server_create()
for i in $(seq 0 1); do
ip -n ${s_ns} link add eth${i} type veth peer name s${i} netns ${g_ns}
+ ip -n "${s_ns}" link set "eth${i}" addr "${mac[$i]}"
ip -n ${g_ns} link set s${i} up
ip -n ${g_ns} link set s${i} master br0
diff --git a/tools/testing/selftests/drivers/net/bonding/bond_topo_3d1c.sh b/tools/testing/selftests/drivers/net/bonding/bond_topo_3d1c.sh
index 3a1333d9a85b..23a2932301cc 100644
--- a/tools/testing/selftests/drivers/net/bonding/bond_topo_3d1c.sh
+++ b/tools/testing/selftests/drivers/net/bonding/bond_topo_3d1c.sh
@@ -26,6 +26,7 @@
# +-------------------------------------+
source bond_topo_2d1c.sh
+mac[2]="00:0a:0b:0c:0d:03"
setup_prepare()
{
@@ -36,6 +37,7 @@ setup_prepare()
# Add the extra device as we use 3 down links for bond0
local i=2
ip -n ${s_ns} link add eth${i} type veth peer name s${i} netns ${g_ns}
+ ip -n "${s_ns}" link set "eth${i}" addr "${mac[$i]}"
ip -n ${g_ns} link set s${i} up
ip -n ${g_ns} link set s${i} master br0
ip -n ${s_ns} link set eth${i} master bond0
diff --git a/tools/testing/selftests/drivers/net/bonding/config b/tools/testing/selftests/drivers/net/bonding/config
index 4d16a69ffc65..e5b7a8db4dfa 100644
--- a/tools/testing/selftests/drivers/net/bonding/config
+++ b/tools/testing/selftests/drivers/net/bonding/config
@@ -10,3 +10,8 @@ CONFIG_NET_CLS_MATCHALL=m
CONFIG_NET_SCH_INGRESS=y
CONFIG_NLMON=y
CONFIG_VETH=y
+CONFIG_VLAN_8021Q=m
+CONFIG_INET_ESP=y
+CONFIG_INET_ESP_OFFLOAD=y
+CONFIG_XFRM_USER=m
+CONFIG_NETDEVSIM=m
diff --git a/tools/testing/selftests/drivers/net/config b/tools/testing/selftests/drivers/net/config
index f27172ddee0a..601431248d5b 100644
--- a/tools/testing/selftests/drivers/net/config
+++ b/tools/testing/selftests/drivers/net/config
@@ -1,6 +1,9 @@
+CONFIG_CONFIGFS_FS=y
+CONFIG_DEBUG_INFO_BTF=y
+CONFIG_DEBUG_INFO_BTF_MODULES=n
+CONFIG_INET_PSP=y
CONFIG_IPV6=y
CONFIG_NETDEVSIM=m
-CONFIG_CONFIGFS_FS=y
CONFIG_NETCONSOLE=m
CONFIG_NETCONSOLE_DYNAMIC=y
CONFIG_NETCONSOLE_EXTENDED_LOG=y
diff --git a/tools/testing/selftests/drivers/net/hds.py b/tools/testing/selftests/drivers/net/hds.py
index 7c90a040ce45..a2011474e625 100755
--- a/tools/testing/selftests/drivers/net/hds.py
+++ b/tools/testing/selftests/drivers/net/hds.py
@@ -3,6 +3,7 @@
import errno
import os
+from typing import Union
from lib.py import ksft_run, ksft_exit, ksft_eq, ksft_raises, KsftSkipEx
from lib.py import CmdExitFailure, EthtoolFamily, NlError
from lib.py import NetDrvEnv
@@ -58,7 +59,39 @@ def get_hds_thresh(cfg, netnl) -> None:
if 'hds-thresh' not in rings:
raise KsftSkipEx('hds-thresh not supported by device')
+
+def _hds_reset(cfg, netnl, rings) -> None:
+ cur = netnl.rings_get({'header': {'dev-index': cfg.ifindex}})
+
+ arg = {'header': {'dev-index': cfg.ifindex}}
+ if cur.get('tcp-data-split') != rings.get('tcp-data-split'):
+ # Try to reset to "unknown" first, we don't know if the setting
+ # was the default or user chose it. Default seems more likely.
+ arg['tcp-data-split'] = "unknown"
+ netnl.rings_set(arg)
+ cur = netnl.rings_get({'header': {'dev-index': cfg.ifindex}})
+ if cur['tcp-data-split'] == rings['tcp-data-split']:
+ del arg['tcp-data-split']
+ else:
+ # Try the explicit setting
+ arg['tcp-data-split'] = rings['tcp-data-split']
+ if cur.get('hds-thresh') != rings.get('hds-thresh'):
+ arg['hds-thresh'] = rings['hds-thresh']
+ if len(arg) > 1:
+ netnl.rings_set(arg)
+
+
+def _defer_reset_hds(cfg, netnl) -> Union[dict, None]:
+ try:
+ rings = netnl.rings_get({'header': {'dev-index': cfg.ifindex}})
+ if 'hds-thresh' in rings or 'tcp-data-split' in rings:
+ defer(_hds_reset, cfg, netnl, rings)
+ except NlError as e:
+ pass
+
+
def set_hds_enable(cfg, netnl) -> None:
+ _defer_reset_hds(cfg, netnl)
try:
netnl.rings_set({'header': {'dev-index': cfg.ifindex}, 'tcp-data-split': 'enabled'})
except NlError as e:
@@ -76,6 +109,7 @@ def set_hds_enable(cfg, netnl) -> None:
ksft_eq('enabled', rings['tcp-data-split'])
def set_hds_disable(cfg, netnl) -> None:
+ _defer_reset_hds(cfg, netnl)
try:
netnl.rings_set({'header': {'dev-index': cfg.ifindex}, 'tcp-data-split': 'disabled'})
except NlError as e:
@@ -93,6 +127,7 @@ def set_hds_disable(cfg, netnl) -> None:
ksft_eq('disabled', rings['tcp-data-split'])
def set_hds_thresh_zero(cfg, netnl) -> None:
+ _defer_reset_hds(cfg, netnl)
try:
netnl.rings_set({'header': {'dev-index': cfg.ifindex}, 'hds-thresh': 0})
except NlError as e:
@@ -110,6 +145,7 @@ def set_hds_thresh_zero(cfg, netnl) -> None:
ksft_eq(0, rings['hds-thresh'])
def set_hds_thresh_random(cfg, netnl) -> None:
+ _defer_reset_hds(cfg, netnl)
try:
rings = netnl.rings_get({'header': {'dev-index': cfg.ifindex}})
except NlError as e:
@@ -140,6 +176,7 @@ def set_hds_thresh_random(cfg, netnl) -> None:
ksft_eq(hds_thresh, rings['hds-thresh'])
def set_hds_thresh_max(cfg, netnl) -> None:
+ _defer_reset_hds(cfg, netnl)
try:
rings = netnl.rings_get({'header': {'dev-index': cfg.ifindex}})
except NlError as e:
@@ -157,6 +194,7 @@ def set_hds_thresh_max(cfg, netnl) -> None:
ksft_eq(rings['hds-thresh'], rings['hds-thresh-max'])
def set_hds_thresh_gt(cfg, netnl) -> None:
+ _defer_reset_hds(cfg, netnl)
try:
rings = netnl.rings_get({'header': {'dev-index': cfg.ifindex}})
except NlError as e:
@@ -178,6 +216,7 @@ def set_xdp(cfg, netnl) -> None:
"""
mode = _get_hds_mode(cfg, netnl)
if mode == 'enabled':
+ _defer_reset_hds(cfg, netnl)
netnl.rings_set({'header': {'dev-index': cfg.ifindex},
'tcp-data-split': 'unknown'})
diff --git a/tools/testing/selftests/drivers/net/hw/Makefile b/tools/testing/selftests/drivers/net/hw/Makefile
index fdc97355588c..ee09a40d532c 100644
--- a/tools/testing/selftests/drivers/net/hw/Makefile
+++ b/tools/testing/selftests/drivers/net/hw/Makefile
@@ -15,9 +15,11 @@ TEST_PROGS = \
iou-zcrx.py \
irq.py \
loopback.sh \
+ nic_timestamp.py \
pp_alloc_fail.py \
rss_api.py \
rss_ctx.py \
+ rss_flow_label.py \
rss_input_xfrm.py \
tso.py \
xsk_reconfig.py \
diff --git a/tools/testing/selftests/drivers/net/hw/config b/tools/testing/selftests/drivers/net/hw/config
index 88ae719e6f8f..e8a06aa1471c 100644
--- a/tools/testing/selftests/drivers/net/hw/config
+++ b/tools/testing/selftests/drivers/net/hw/config
@@ -1,5 +1,7 @@
+CONFIG_IO_URING=y
CONFIG_IPV6=y
CONFIG_IPV6_GRE=y
CONFIG_NET_IPGRE=y
CONFIG_NET_IPGRE_DEMUX=y
+CONFIG_UDMABUF=y
CONFIG_VXLAN=y
diff --git a/tools/testing/selftests/drivers/net/hw/csum.py b/tools/testing/selftests/drivers/net/hw/csum.py
index cd23af875317..3e3a89a34afe 100755
--- a/tools/testing/selftests/drivers/net/hw/csum.py
+++ b/tools/testing/selftests/drivers/net/hw/csum.py
@@ -17,7 +17,7 @@ def test_receive(cfg, ipver="6", extra_args=None):
ip_args = f"-{ipver} -S {cfg.remote_addr_v[ipver]} -D {cfg.addr_v[ipver]}"
rx_cmd = f"{cfg.bin_local} -i {cfg.ifname} -n 100 {ip_args} -r 1 -R {extra_args}"
- tx_cmd = f"{cfg.bin_remote} -i {cfg.ifname} -n 100 {ip_args} -r 1 -T {extra_args}"
+ tx_cmd = f"{cfg.bin_remote} -i {cfg.remote_ifname} -n 100 {ip_args} -r 1 -T {extra_args}"
with bkg(rx_cmd, exit_wait=True):
wait_port_listen(34000, proto="udp")
@@ -37,7 +37,7 @@ def test_transmit(cfg, ipver="6", extra_args=None):
if extra_args != "-U -Z":
extra_args += " -r 1"
- rx_cmd = f"{cfg.bin_remote} -i {cfg.ifname} -L 1 -n 100 {ip_args} -R {extra_args}"
+ rx_cmd = f"{cfg.bin_remote} -i {cfg.remote_ifname} -L 1 -n 100 {ip_args} -R {extra_args}"
tx_cmd = f"{cfg.bin_local} -i {cfg.ifname} -L 1 -n 100 {ip_args} -T {extra_args}"
with bkg(rx_cmd, host=cfg.remote, exit_wait=True):
diff --git a/tools/testing/selftests/drivers/net/hw/devmem.py b/tools/testing/selftests/drivers/net/hw/devmem.py
index baa2f24240ba..45c2d49d55b6 100755
--- a/tools/testing/selftests/drivers/net/hw/devmem.py
+++ b/tools/testing/selftests/drivers/net/hw/devmem.py
@@ -24,7 +24,7 @@ def check_rx(cfg) -> None:
require_devmem(cfg)
port = rand_port()
- socat = f"socat -u - TCP{cfg.addr_ipver}:{cfg.addr}:{port},bind={cfg.remote_addr}:{port}"
+ socat = f"socat -u - TCP{cfg.addr_ipver}:{cfg.baddr}:{port},bind={cfg.remote_baddr}:{port}"
listen_cmd = f"{cfg.bin_local} -l -f {cfg.ifname} -s {cfg.addr} -p {port} -c {cfg.remote_addr} -v 7"
with bkg(listen_cmd, exit_wait=True) as ncdevmem:
@@ -42,9 +42,9 @@ def check_tx(cfg) -> None:
port = rand_port()
listen_cmd = f"socat -U - TCP{cfg.addr_ipver}-LISTEN:{port}"
- with bkg(listen_cmd) as socat:
- wait_port_listen(port)
- cmd(f"echo -e \"hello\\nworld\"| {cfg.bin_remote} -f {cfg.ifname} -s {cfg.addr} -p {port}", host=cfg.remote, shell=True)
+ with bkg(listen_cmd, host=cfg.remote, exit_wait=True) as socat:
+ wait_port_listen(port, host=cfg.remote)
+ cmd(f"echo -e \"hello\\nworld\"| {cfg.bin_local} -f {cfg.ifname} -s {cfg.remote_addr} -p {port}", shell=True)
ksft_eq(socat.stdout.strip(), "hello\nworld")
@@ -56,9 +56,9 @@ def check_tx_chunks(cfg) -> None:
port = rand_port()
listen_cmd = f"socat -U - TCP{cfg.addr_ipver}-LISTEN:{port}"
- with bkg(listen_cmd, exit_wait=True) as socat:
- wait_port_listen(port)
- cmd(f"echo -e \"hello\\nworld\"| {cfg.bin_remote} -f {cfg.ifname} -s {cfg.addr} -p {port} -z 3", host=cfg.remote, shell=True)
+ with bkg(listen_cmd, host=cfg.remote, exit_wait=True) as socat:
+ wait_port_listen(port, host=cfg.remote)
+ cmd(f"echo -e \"hello\\nworld\"| {cfg.bin_local} -f {cfg.ifname} -s {cfg.remote_addr} -p {port} -z 3", shell=True)
ksft_eq(socat.stdout.strip(), "hello\nworld")
diff --git a/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py b/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py
index 1462a339a74b..0ceb297e7757 100644
--- a/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py
+++ b/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py
@@ -13,7 +13,7 @@ try:
# Import one by one to avoid pylint false positives
from net.lib.py import EthtoolFamily, NetdevFamily, NetshaperFamily, \
- NlError, RtnlFamily, DevlinkFamily
+ NlError, RtnlFamily, DevlinkFamily, PSPFamily
from net.lib.py import CmdExitFailure
from net.lib.py import bkg, cmd, defer, ethtool, fd_read_timeout, ip, \
rand_port, tool, wait_port_listen
@@ -22,7 +22,7 @@ try:
from net.lib.py import ksft_disruptive, ksft_exit, ksft_pr, ksft_run, \
ksft_setup
from net.lib.py import ksft_eq, ksft_ge, ksft_in, ksft_is, ksft_lt, \
- ksft_ne, ksft_not_in, ksft_raises, ksft_true
+ ksft_ne, ksft_not_in, ksft_raises, ksft_true, ksft_gt, ksft_not_none
from net.lib.py import NetNSEnter
from drivers.net.lib.py import GenerateTraffic
from drivers.net.lib.py import NetDrvEnv, NetDrvEpEnv
diff --git a/tools/testing/selftests/drivers/net/hw/ncdevmem.c b/tools/testing/selftests/drivers/net/hw/ncdevmem.c
index 72f828021f83..3288ed04ce08 100644
--- a/tools/testing/selftests/drivers/net/hw/ncdevmem.c
+++ b/tools/testing/selftests/drivers/net/hw/ncdevmem.c
@@ -39,6 +39,7 @@
#define __EXPORTED_HEADERS__
#include <linux/uio.h>
+#include <stdarg.h>
#include <stdio.h>
#include <stdlib.h>
#include <unistd.h>
@@ -97,6 +98,10 @@ static unsigned int dmabuf_id;
static uint32_t tx_dmabuf_id;
static int waittime_ms = 500;
+/* System state loaded by current_config_load() */
+#define MAX_FLOWS 8
+static int ntuple_ids[MAX_FLOWS] = { -1, -1, -1, -1, -1, -1, -1, -1, };
+
struct memory_buffer {
int fd;
size_t size;
@@ -115,6 +120,21 @@ struct memory_provider {
size_t off, int n);
};
+static void pr_err(const char *fmt, ...)
+{
+ va_list args;
+
+ fprintf(stderr, "%s: ", TEST_PREFIX);
+
+ va_start(args, fmt);
+ vfprintf(stderr, fmt, args);
+ va_end(args);
+
+ if (errno != 0)
+ fprintf(stderr, ": %s", strerror(errno));
+ fprintf(stderr, "\n");
+}
+
static struct memory_buffer *udmabuf_alloc(size_t size)
{
struct udmabuf_create create;
@@ -123,27 +143,33 @@ static struct memory_buffer *udmabuf_alloc(size_t size)
ctx = malloc(sizeof(*ctx));
if (!ctx)
- error(1, ENOMEM, "malloc failed");
+ return NULL;
ctx->size = size;
ctx->devfd = open("/dev/udmabuf", O_RDWR);
- if (ctx->devfd < 0)
- error(1, errno,
- "%s: [skip,no-udmabuf: Unable to access DMA buffer device file]\n",
- TEST_PREFIX);
+ if (ctx->devfd < 0) {
+ pr_err("[skip,no-udmabuf: Unable to access DMA buffer device file]");
+ goto err_free_ctx;
+ }
ctx->memfd = memfd_create("udmabuf-test", MFD_ALLOW_SEALING);
- if (ctx->memfd < 0)
- error(1, errno, "%s: [skip,no-memfd]\n", TEST_PREFIX);
+ if (ctx->memfd < 0) {
+ pr_err("[skip,no-memfd]");
+ goto err_close_dev;
+ }
ret = fcntl(ctx->memfd, F_ADD_SEALS, F_SEAL_SHRINK);
- if (ret < 0)
- error(1, errno, "%s: [skip,fcntl-add-seals]\n", TEST_PREFIX);
+ if (ret < 0) {
+ pr_err("[skip,fcntl-add-seals]");
+ goto err_close_memfd;
+ }
ret = ftruncate(ctx->memfd, size);
- if (ret == -1)
- error(1, errno, "%s: [FAIL,memfd-truncate]\n", TEST_PREFIX);
+ if (ret == -1) {
+ pr_err("[FAIL,memfd-truncate]");
+ goto err_close_memfd;
+ }
memset(&create, 0, sizeof(create));
@@ -151,15 +177,29 @@ static struct memory_buffer *udmabuf_alloc(size_t size)
create.offset = 0;
create.size = size;
ctx->fd = ioctl(ctx->devfd, UDMABUF_CREATE, &create);
- if (ctx->fd < 0)
- error(1, errno, "%s: [FAIL, create udmabuf]\n", TEST_PREFIX);
+ if (ctx->fd < 0) {
+ pr_err("[FAIL, create udmabuf]");
+ goto err_close_fd;
+ }
ctx->buf_mem = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_SHARED,
ctx->fd, 0);
- if (ctx->buf_mem == MAP_FAILED)
- error(1, errno, "%s: [FAIL, map udmabuf]\n", TEST_PREFIX);
+ if (ctx->buf_mem == MAP_FAILED) {
+ pr_err("[FAIL, map udmabuf]");
+ goto err_close_fd;
+ }
return ctx;
+
+err_close_fd:
+ close(ctx->fd);
+err_close_memfd:
+ close(ctx->memfd);
+err_close_dev:
+ close(ctx->devfd);
+err_free_ctx:
+ free(ctx);
+ return NULL;
}
static void udmabuf_free(struct memory_buffer *ctx)
@@ -217,7 +257,7 @@ static void print_nonzero_bytes(void *ptr, size_t size)
putchar(p[i]);
}
-void validate_buffer(void *line, size_t size)
+int validate_buffer(void *line, size_t size)
{
static unsigned char seed = 1;
unsigned char *ptr = line;
@@ -232,8 +272,10 @@ void validate_buffer(void *line, size_t size)
"Failed validation: expected=%u, actual=%u, index=%lu\n",
expected, ptr[i], i);
errors++;
- if (errors > 20)
- error(1, 0, "validation failed.");
+ if (errors > 20) {
+ pr_err("validation failed");
+ return -1;
+ }
}
seed++;
if (seed == do_validation)
@@ -241,6 +283,86 @@ void validate_buffer(void *line, size_t size)
}
fprintf(stdout, "Validated buffer\n");
+ return 0;
+}
+
+static int
+__run_command(char *out, size_t outlen, const char *cmd, va_list args)
+{
+ char command[256];
+ FILE *fp;
+
+ vsnprintf(command, sizeof(command), cmd, args);
+
+ fprintf(stderr, "Running: %s\n", command);
+ fp = popen(command, "r");
+ if (!fp)
+ return -1;
+ if (out) {
+ size_t len;
+
+ if (!fgets(out, outlen, fp))
+ return -1;
+
+ /* Remove trailing newline if present */
+ len = strlen(out);
+ if (len && out[len - 1] == '\n')
+ out[len - 1] = '\0';
+ }
+ return pclose(fp);
+}
+
+static int run_command(const char *cmd, ...)
+{
+ va_list args;
+ int ret;
+
+ va_start(args, cmd);
+ ret = __run_command(NULL, 0, cmd, args);
+ va_end(args);
+
+ return ret;
+}
+
+static int ethtool_add_flow(const char *format, ...)
+{
+ char local_output[256], cmd[256];
+ const char *id_start;
+ int flow_idx, ret;
+ char *endptr;
+ long flow_id;
+ va_list args;
+
+ for (flow_idx = 0; flow_idx < MAX_FLOWS; flow_idx++)
+ if (ntuple_ids[flow_idx] == -1)
+ break;
+ if (flow_idx == MAX_FLOWS) {
+ fprintf(stderr, "Error: too many flows\n");
+ return -1;
+ }
+
+ snprintf(cmd, sizeof(cmd), "ethtool -N %s %s", ifname, format);
+
+ va_start(args, format);
+ ret = __run_command(local_output, sizeof(local_output), cmd, args);
+ va_end(args);
+
+ if (ret != 0)
+ return ret;
+
+ /* Extract the ID from the output */
+ id_start = strstr(local_output, "Added rule with ID ");
+ if (!id_start)
+ return -1;
+ id_start += strlen("Added rule with ID ");
+
+ flow_id = strtol(id_start, &endptr, 10);
+ if (endptr == id_start || flow_id < 0 || flow_id > INT_MAX)
+ return -1;
+
+ fprintf(stderr, "Added flow rule with ID %ld\n", flow_id);
+ ntuple_ids[flow_idx] = flow_id;
+ return flow_id;
}
static int rxq_num(int ifindex)
@@ -270,29 +392,17 @@ static int rxq_num(int ifindex)
return num;
}
-#define run_command(cmd, ...) \
- ({ \
- char command[256]; \
- memset(command, 0, sizeof(command)); \
- snprintf(command, sizeof(command), cmd, ##__VA_ARGS__); \
- fprintf(stderr, "Running: %s\n", command); \
- system(command); \
- })
-
-static int reset_flow_steering(void)
+static void reset_flow_steering(void)
{
- /* Depending on the NIC, toggling ntuple off and on might not
- * be allowed. Additionally, attempting to delete existing filters
- * will fail if no filters are present. Therefore, do not enforce
- * the exit status.
- */
-
- run_command("sudo ethtool -K %s ntuple off >&2", ifname);
- run_command("sudo ethtool -K %s ntuple on >&2", ifname);
- run_command(
- "sudo ethtool -n %s | grep 'Filter:' | awk '{print $2}' | xargs -n1 ethtool -N %s delete >&2",
- ifname, ifname);
- return 0;
+ int i;
+
+ for (i = 0; i < MAX_FLOWS; i++) {
+ if (ntuple_ids[i] == -1)
+ continue;
+ run_command("ethtool -N %s delete %d",
+ ifname, ntuple_ids[i]);
+ ntuple_ids[i] = -1;
+ }
}
static const char *tcp_data_split_str(int val)
@@ -309,7 +419,81 @@ static const char *tcp_data_split_str(int val)
}
}
-static int configure_headersplit(bool on)
+static struct ethtool_rings_get_rsp *get_ring_config(void)
+{
+ struct ethtool_rings_get_req *get_req;
+ struct ethtool_rings_get_rsp *get_rsp;
+ struct ynl_error yerr;
+ struct ynl_sock *ys;
+
+ ys = ynl_sock_create(&ynl_ethtool_family, &yerr);
+ if (!ys) {
+ fprintf(stderr, "YNL: %s\n", yerr.msg);
+ return NULL;
+ }
+
+ get_req = ethtool_rings_get_req_alloc();
+ ethtool_rings_get_req_set_header_dev_index(get_req, ifindex);
+ get_rsp = ethtool_rings_get(ys, get_req);
+ ethtool_rings_get_req_free(get_req);
+
+ ynl_sock_destroy(ys);
+
+ return get_rsp;
+}
+
+static void restore_ring_config(const struct ethtool_rings_get_rsp *config)
+{
+ struct ethtool_rings_get_req *get_req;
+ struct ethtool_rings_get_rsp *get_rsp;
+ struct ethtool_rings_set_req *req;
+ struct ynl_error yerr;
+ struct ynl_sock *ys;
+ int ret;
+
+ if (!config)
+ return;
+
+ ys = ynl_sock_create(&ynl_ethtool_family, &yerr);
+ if (!ys) {
+ fprintf(stderr, "YNL: %s\n", yerr.msg);
+ return;
+ }
+
+ req = ethtool_rings_set_req_alloc();
+ ethtool_rings_set_req_set_header_dev_index(req, ifindex);
+ ethtool_rings_set_req_set_tcp_data_split(req,
+ ETHTOOL_TCP_DATA_SPLIT_UNKNOWN);
+ if (config->_present.hds_thresh)
+ ethtool_rings_set_req_set_hds_thresh(req, config->hds_thresh);
+
+ ret = ethtool_rings_set(ys, req);
+ if (ret < 0)
+ fprintf(stderr, "YNL restoring HDS cfg: %s\n", ys->err.msg);
+
+ get_req = ethtool_rings_get_req_alloc();
+ ethtool_rings_get_req_set_header_dev_index(get_req, ifindex);
+ get_rsp = ethtool_rings_get(ys, get_req);
+ ethtool_rings_get_req_free(get_req);
+
+ /* use explicit value if UKNOWN didn't give us the previous */
+ if (get_rsp->tcp_data_split != config->tcp_data_split) {
+ ethtool_rings_set_req_set_tcp_data_split(req,
+ config->tcp_data_split);
+ ret = ethtool_rings_set(ys, req);
+ if (ret < 0)
+ fprintf(stderr, "YNL restoring expl HDS cfg: %s\n",
+ ys->err.msg);
+ }
+
+ ethtool_rings_get_rsp_free(get_rsp);
+ ethtool_rings_set_req_free(req);
+
+ ynl_sock_destroy(ys);
+}
+
+static int
+configure_headersplit(const struct ethtool_rings_get_rsp *old, bool on)
{
struct ethtool_rings_get_req *get_req;
struct ethtool_rings_get_rsp *get_rsp;
@@ -326,8 +510,15 @@ static int configure_headersplit(bool on)
req = ethtool_rings_set_req_alloc();
ethtool_rings_set_req_set_header_dev_index(req, ifindex);
- /* 0 - off, 1 - auto, 2 - on */
- ethtool_rings_set_req_set_tcp_data_split(req, on ? 2 : 0);
+ if (on) {
+ ethtool_rings_set_req_set_tcp_data_split(req,
+ ETHTOOL_TCP_DATA_SPLIT_ENABLED);
+ if (old->_present.hds_thresh)
+ ethtool_rings_set_req_set_hds_thresh(req, 0);
+ } else {
+ ethtool_rings_set_req_set_tcp_data_split(req,
+ ETHTOOL_TCP_DATA_SPLIT_UNKNOWN);
+ }
ret = ethtool_rings_set(ys, req);
if (ret < 0)
fprintf(stderr, "YNL failed: %s\n", ys->err.msg);
@@ -351,12 +542,103 @@ static int configure_headersplit(bool on)
static int configure_rss(void)
{
- return run_command("sudo ethtool -X %s equal %d >&2", ifname, start_queue);
+ return run_command("ethtool -X %s equal %d >&2", ifname, start_queue);
+}
+
+static void reset_rss(void)
+{
+ run_command("ethtool -X %s default >&2", ifname, start_queue);
}
-static int configure_channels(unsigned int rx, unsigned int tx)
+static int check_changing_channels(unsigned int rx, unsigned int tx)
{
- return run_command("sudo ethtool -L %s rx %u tx %u", ifname, rx, tx);
+ struct ethtool_channels_get_req *gchan;
+ struct ethtool_channels_set_req *schan;
+ struct ethtool_channels_get_rsp *chan;
+ struct ynl_error yerr;
+ struct ynl_sock *ys;
+ int ret;
+
+ fprintf(stderr, "setting channel count rx:%u tx:%u\n", rx, tx);
+
+ ys = ynl_sock_create(&ynl_ethtool_family, &yerr);
+ if (!ys) {
+ fprintf(stderr, "YNL: %s\n", yerr.msg);
+ return -1;
+ }
+
+ gchan = ethtool_channels_get_req_alloc();
+ if (!gchan) {
+ ret = -1;
+ goto exit_close_sock;
+ }
+
+ ethtool_channels_get_req_set_header_dev_index(gchan, ifindex);
+ chan = ethtool_channels_get(ys, gchan);
+ ethtool_channels_get_req_free(gchan);
+ if (!chan) {
+ fprintf(stderr, "YNL get channels: %s\n", ys->err.msg);
+ ret = -1;
+ goto exit_close_sock;
+ }
+
+ schan = ethtool_channels_set_req_alloc();
+ if (!schan) {
+ ret = -1;
+ goto exit_free_chan;
+ }
+
+ ethtool_channels_set_req_set_header_dev_index(schan, ifindex);
+
+ if (chan->_present.combined_count) {
+ if (chan->_present.rx_count || chan->_present.tx_count) {
+ ethtool_channels_set_req_set_rx_count(schan, 0);
+ ethtool_channels_set_req_set_tx_count(schan, 0);
+ }
+
+ if (rx == tx) {
+ ethtool_channels_set_req_set_combined_count(schan, rx);
+ } else if (rx > tx) {
+ ethtool_channels_set_req_set_combined_count(schan, tx);
+ ethtool_channels_set_req_set_rx_count(schan, rx - tx);
+ } else {
+ ethtool_channels_set_req_set_combined_count(schan, rx);
+ ethtool_channels_set_req_set_tx_count(schan, tx - rx);
+ }
+
+ } else if (chan->_present.rx_count) {
+ ethtool_channels_set_req_set_rx_count(schan, rx);
+ ethtool_channels_set_req_set_tx_count(schan, tx);
+ } else {
+ fprintf(stderr, "Error: device has neither combined nor rx channels\n");
+ ret = -1;
+ goto exit_free_schan;
+ }
+
+ ret = ethtool_channels_set(ys, schan);
+ if (ret) {
+ fprintf(stderr, "YNL set channels: %s\n", ys->err.msg);
+ } else {
+ /* We were expecting a failure, go back to previous settings */
+ ethtool_channels_set_req_set_combined_count(schan,
+ chan->combined_count);
+ ethtool_channels_set_req_set_rx_count(schan, chan->rx_count);
+ ethtool_channels_set_req_set_tx_count(schan, chan->tx_count);
+
+ ret = ethtool_channels_set(ys, schan);
+ if (ret)
+ fprintf(stderr, "YNL un-setting channels: %s\n",
+ ys->err.msg);
+ }
+
+exit_free_schan:
+ ethtool_channels_set_req_free(schan);
+exit_free_chan:
+ ethtool_channels_get_rsp_free(chan);
+exit_close_sock:
+ ynl_sock_destroy(ys);
+
+ return ret;
}
static int configure_flow_steering(struct sockaddr_in6 *server_sin)
@@ -364,6 +646,7 @@ static int configure_flow_steering(struct sockaddr_in6 *server_sin)
const char *type = "tcp6";
const char *server_addr;
char buf[40];
+ int flow_id;
inet_ntop(AF_INET6, &server_sin->sin6_addr, buf, sizeof(buf));
server_addr = buf;
@@ -374,23 +657,22 @@ static int configure_flow_steering(struct sockaddr_in6 *server_sin)
}
/* Try configure 5-tuple */
- if (run_command("sudo ethtool -N %s flow-type %s %s %s dst-ip %s %s %s dst-port %s queue %d >&2",
- ifname,
- type,
- client_ip ? "src-ip" : "",
- client_ip ?: "",
- server_addr,
- client_ip ? "src-port" : "",
- client_ip ? port : "",
- port, start_queue))
+ flow_id = ethtool_add_flow("flow-type %s %s %s dst-ip %s %s %s dst-port %s queue %d",
+ type,
+ client_ip ? "src-ip" : "",
+ client_ip ?: "",
+ server_addr,
+ client_ip ? "src-port" : "",
+ client_ip ? port : "",
+ port, start_queue);
+ if (flow_id < 0) {
/* If that fails, try configure 3-tuple */
- if (run_command("sudo ethtool -N %s flow-type %s dst-ip %s dst-port %s queue %d >&2",
- ifname,
- type,
- server_addr,
- port, start_queue))
+ flow_id = ethtool_add_flow("flow-type %s dst-ip %s dst-port %s queue %d",
+ type, server_addr, port, start_queue);
+ if (flow_id < 0)
/* If that fails, return error */
return -1;
+ }
return 0;
}
@@ -405,6 +687,7 @@ static int bind_rx_queue(unsigned int ifindex, unsigned int dmabuf_fd,
*ys = ynl_sock_create(&ynl_netdev_family, &yerr);
if (!*ys) {
+ netdev_queue_id_free(queues);
fprintf(stderr, "YNL: %s\n", yerr.msg);
return -1;
}
@@ -483,18 +766,24 @@ err_close:
return -1;
}
-static void enable_reuseaddr(int fd)
+static int enable_reuseaddr(int fd)
{
int opt = 1;
int ret;
ret = setsockopt(fd, SOL_SOCKET, SO_REUSEPORT, &opt, sizeof(opt));
- if (ret)
- error(1, errno, "%s: [FAIL, SO_REUSEPORT]\n", TEST_PREFIX);
+ if (ret) {
+ pr_err("SO_REUSEPORT failed");
+ return -1;
+ }
ret = setsockopt(fd, SOL_SOCKET, SO_REUSEADDR, &opt, sizeof(opt));
- if (ret)
- error(1, errno, "%s: [FAIL, SO_REUSEADDR]\n", TEST_PREFIX);
+ if (ret) {
+ pr_err("SO_REUSEADDR failed");
+ return -1;
+ }
+
+ return 0;
}
static int parse_address(const char *str, int port, struct sockaddr_in6 *sin6)
@@ -537,6 +826,7 @@ static struct netdev_queue_id *create_queues(void)
static int do_server(struct memory_buffer *mem)
{
+ struct ethtool_rings_get_rsp *ring_config;
char ctrl_data[sizeof(int) * 20000];
size_t non_page_aligned_frags = 0;
struct sockaddr_in6 client_addr;
@@ -548,54 +838,72 @@ static int do_server(struct memory_buffer *mem)
char *tmp_mem = NULL;
struct ynl_sock *ys;
char iobuf[819200];
+ int ret, err = -1;
char buffer[256];
int socket_fd;
int client_fd;
- int ret;
ret = parse_address(server_ip, atoi(port), &server_sin);
- if (ret < 0)
- error(1, 0, "parse server address");
+ if (ret < 0) {
+ pr_err("parse server address");
+ return -1;
+ }
- if (reset_flow_steering())
- error(1, 0, "Failed to reset flow steering\n");
+ ring_config = get_ring_config();
+ if (!ring_config) {
+ pr_err("Failed to get current ring configuration");
+ return -1;
+ }
- if (configure_headersplit(1))
- error(1, 0, "Failed to enable TCP header split\n");
+ if (configure_headersplit(ring_config, 1)) {
+ pr_err("Failed to enable TCP header split");
+ goto err_free_ring_config;
+ }
/* Configure RSS to divert all traffic from our devmem queues */
- if (configure_rss())
- error(1, 0, "Failed to configure rss\n");
+ if (configure_rss()) {
+ pr_err("Failed to configure rss");
+ goto err_reset_headersplit;
+ }
/* Flow steer our devmem flows to start_queue */
- if (configure_flow_steering(&server_sin))
- error(1, 0, "Failed to configure flow steering\n");
-
- sleep(1);
+ if (configure_flow_steering(&server_sin)) {
+ pr_err("Failed to configure flow steering");
+ goto err_reset_rss;
+ }
- if (bind_rx_queue(ifindex, mem->fd, create_queues(), num_queues, &ys))
- error(1, 0, "Failed to bind\n");
+ if (bind_rx_queue(ifindex, mem->fd, create_queues(), num_queues, &ys)) {
+ pr_err("Failed to bind");
+ goto err_reset_flow_steering;
+ }
tmp_mem = malloc(mem->size);
if (!tmp_mem)
- error(1, ENOMEM, "malloc failed");
+ goto err_unbind;
socket_fd = socket(AF_INET6, SOCK_STREAM, 0);
- if (socket_fd < 0)
- error(1, errno, "%s: [FAIL, create socket]\n", TEST_PREFIX);
+ if (socket_fd < 0) {
+ pr_err("Failed to create socket");
+ goto err_free_tmp;
+ }
- enable_reuseaddr(socket_fd);
+ if (enable_reuseaddr(socket_fd))
+ goto err_close_socket;
fprintf(stderr, "binding to address %s:%d\n", server_ip,
ntohs(server_sin.sin6_port));
ret = bind(socket_fd, &server_sin, sizeof(server_sin));
- if (ret)
- error(1, errno, "%s: [FAIL, bind]\n", TEST_PREFIX);
+ if (ret) {
+ pr_err("Failed to bind");
+ goto err_close_socket;
+ }
ret = listen(socket_fd, 1);
- if (ret)
- error(1, errno, "%s: [FAIL, listen]\n", TEST_PREFIX);
+ if (ret) {
+ pr_err("Failed to listen");
+ goto err_close_socket;
+ }
client_addr_len = sizeof(client_addr);
@@ -604,6 +912,10 @@ static int do_server(struct memory_buffer *mem)
fprintf(stderr, "Waiting or connection on %s:%d\n", buffer,
ntohs(server_sin.sin6_port));
client_fd = accept(socket_fd, &client_addr, &client_addr_len);
+ if (client_fd < 0) {
+ pr_err("Failed to accept");
+ goto err_close_socket;
+ }
inet_ntop(AF_INET6, &client_addr.sin6_addr, buffer,
sizeof(buffer));
@@ -631,10 +943,15 @@ static int do_server(struct memory_buffer *mem)
continue;
if (ret < 0) {
perror("recvmsg");
+ if (errno == EFAULT) {
+ pr_err("received EFAULT, won't recover");
+ goto err_close_client;
+ }
continue;
}
if (ret == 0) {
- fprintf(stderr, "client exited\n");
+ errno = 0;
+ pr_err("client exited");
goto cleanup;
}
@@ -672,9 +989,10 @@ static int do_server(struct memory_buffer *mem)
dmabuf_cmsg->frag_size, dmabuf_cmsg->frag_token,
total_received, dmabuf_cmsg->dmabuf_id);
- if (dmabuf_cmsg->dmabuf_id != dmabuf_id)
- error(1, 0,
- "received on wrong dmabuf_id: flow steering error\n");
+ if (dmabuf_cmsg->dmabuf_id != dmabuf_id) {
+ pr_err("received on wrong dmabuf_id: flow steering error");
+ goto err_close_client;
+ }
if (dmabuf_cmsg->frag_size % getpagesize())
non_page_aligned_frags++;
@@ -685,22 +1003,27 @@ static int do_server(struct memory_buffer *mem)
dmabuf_cmsg->frag_offset,
dmabuf_cmsg->frag_size);
- if (do_validation)
- validate_buffer(tmp_mem,
- dmabuf_cmsg->frag_size);
- else
+ if (do_validation) {
+ if (validate_buffer(tmp_mem,
+ dmabuf_cmsg->frag_size))
+ goto err_close_client;
+ } else {
print_nonzero_bytes(tmp_mem,
dmabuf_cmsg->frag_size);
+ }
ret = setsockopt(client_fd, SOL_SOCKET,
SO_DEVMEM_DONTNEED, &token,
sizeof(token));
- if (ret != 1)
- error(1, 0,
- "SO_DEVMEM_DONTNEED not enough tokens");
+ if (ret != 1) {
+ pr_err("SO_DEVMEM_DONTNEED not enough tokens");
+ goto err_close_client;
+ }
+ }
+ if (!is_devmem) {
+ pr_err("flow steering error");
+ goto err_close_client;
}
- if (!is_devmem)
- error(1, 0, "flow steering error\n");
fprintf(stderr, "total_received=%lu\n", total_received);
}
@@ -711,54 +1034,121 @@ static int do_server(struct memory_buffer *mem)
page_aligned_frags, non_page_aligned_frags);
cleanup:
+ err = 0;
- free(tmp_mem);
+err_close_client:
close(client_fd);
+err_close_socket:
close(socket_fd);
+err_free_tmp:
+ free(tmp_mem);
+err_unbind:
ynl_sock_destroy(ys);
-
- return 0;
+err_reset_flow_steering:
+ reset_flow_steering();
+err_reset_rss:
+ reset_rss();
+err_reset_headersplit:
+ restore_ring_config(ring_config);
+err_free_ring_config:
+ ethtool_rings_get_rsp_free(ring_config);
+ return err;
}
-void run_devmem_tests(void)
+int run_devmem_tests(void)
{
+ struct ethtool_rings_get_rsp *ring_config;
+ struct netdev_queue_id *queues;
struct memory_buffer *mem;
struct ynl_sock *ys;
+ int err = -1;
mem = provider->alloc(getpagesize() * NUM_PAGES);
+ if (!mem) {
+ pr_err("Failed to allocate memory buffer");
+ return -1;
+ }
+
+ ring_config = get_ring_config();
+ if (!ring_config) {
+ pr_err("Failed to get current ring configuration");
+ goto err_free_mem;
+ }
/* Configure RSS to divert all traffic from our devmem queues */
- if (configure_rss())
- error(1, 0, "rss error\n");
+ if (configure_rss()) {
+ pr_err("rss error");
+ goto err_free_ring_config;
+ }
+
+ if (configure_headersplit(ring_config, 1)) {
+ pr_err("Failed to configure header split");
+ goto err_reset_rss;
+ }
+
+ queues = netdev_queue_id_alloc(num_queues);
+ if (!queues) {
+ pr_err("Failed to allocate empty queues array");
+ goto err_reset_headersplit;
+ }
+
+ if (!bind_rx_queue(ifindex, mem->fd, queues, num_queues, &ys)) {
+ pr_err("Binding empty queues array should have failed");
+ goto err_unbind;
+ }
- if (configure_headersplit(1))
- error(1, 0, "Failed to configure header split\n");
+ if (configure_headersplit(ring_config, 0)) {
+ pr_err("Failed to configure header split");
+ goto err_reset_headersplit;
+ }
- if (!bind_rx_queue(ifindex, mem->fd,
- calloc(num_queues, sizeof(struct netdev_queue_id)),
- num_queues, &ys))
- error(1, 0, "Binding empty queues array should have failed\n");
+ queues = create_queues();
+ if (!queues) {
+ pr_err("Failed to create queues");
+ goto err_reset_headersplit;
+ }
- if (configure_headersplit(0))
- error(1, 0, "Failed to configure header split\n");
+ if (!bind_rx_queue(ifindex, mem->fd, queues, num_queues, &ys)) {
+ pr_err("Configure dmabuf with header split off should have failed");
+ goto err_unbind;
+ }
- if (!bind_rx_queue(ifindex, mem->fd, create_queues(), num_queues, &ys))
- error(1, 0, "Configure dmabuf with header split off should have failed\n");
+ if (configure_headersplit(ring_config, 1)) {
+ pr_err("Failed to configure header split");
+ goto err_reset_headersplit;
+ }
- if (configure_headersplit(1))
- error(1, 0, "Failed to configure header split\n");
+ queues = create_queues();
+ if (!queues) {
+ pr_err("Failed to create queues");
+ goto err_reset_headersplit;
+ }
- if (bind_rx_queue(ifindex, mem->fd, create_queues(), num_queues, &ys))
- error(1, 0, "Failed to bind\n");
+ if (bind_rx_queue(ifindex, mem->fd, queues, num_queues, &ys)) {
+ pr_err("Failed to bind");
+ goto err_reset_headersplit;
+ }
/* Deactivating a bound queue should not be legal */
- if (!configure_channels(num_queues, num_queues - 1))
- error(1, 0, "Deactivating a bound queue should be illegal.\n");
+ if (!check_changing_channels(num_queues, num_queues)) {
+ pr_err("Deactivating a bound queue should be illegal");
+ goto err_unbind;
+ }
- /* Closing the netlink socket does an implicit unbind */
- ynl_sock_destroy(ys);
+ err = 0;
+ goto err_unbind;
+err_unbind:
+ ynl_sock_destroy(ys);
+err_reset_headersplit:
+ restore_ring_config(ring_config);
+err_reset_rss:
+ reset_rss();
+err_free_ring_config:
+ ethtool_rings_get_rsp_free(ring_config);
+err_free_mem:
provider->free(mem);
+ return err;
}
static uint64_t gettimeofday_ms(void)
@@ -778,13 +1168,15 @@ static int do_poll(int fd)
pfd.fd = fd;
ret = poll(&pfd, 1, waittime_ms);
- if (ret == -1)
- error(1, errno, "poll");
+ if (ret == -1) {
+ pr_err("poll");
+ return -1;
+ }
return ret && (pfd.revents & POLLERR);
}
-static void wait_compl(int fd)
+static int wait_compl(int fd)
{
int64_t tstop = gettimeofday_ms() + waittime_ms;
char control[CMSG_SPACE(100)] = {};
@@ -798,18 +1190,23 @@ static void wait_compl(int fd)
msg.msg_controllen = sizeof(control);
while (gettimeofday_ms() < tstop) {
- if (!do_poll(fd))
+ ret = do_poll(fd);
+ if (ret < 0)
+ return ret;
+ if (!ret)
continue;
ret = recvmsg(fd, &msg, MSG_ERRQUEUE);
if (ret < 0) {
if (errno == EAGAIN)
continue;
- error(1, errno, "recvmsg(MSG_ERRQUEUE)");
- return;
+ pr_err("recvmsg(MSG_ERRQUEUE)");
+ return -1;
+ }
+ if (msg.msg_flags & MSG_CTRUNC) {
+ pr_err("MSG_CTRUNC");
+ return -1;
}
- if (msg.msg_flags & MSG_CTRUNC)
- error(1, 0, "MSG_CTRUNC\n");
for (cm = CMSG_FIRSTHDR(&msg); cm; cm = CMSG_NXTHDR(&msg, cm)) {
if (cm->cmsg_level != SOL_IP &&
@@ -823,20 +1220,25 @@ static void wait_compl(int fd)
continue;
serr = (void *)CMSG_DATA(cm);
- if (serr->ee_origin != SO_EE_ORIGIN_ZEROCOPY)
- error(1, 0, "wrong origin %u", serr->ee_origin);
- if (serr->ee_errno != 0)
- error(1, 0, "wrong errno %d", serr->ee_errno);
+ if (serr->ee_origin != SO_EE_ORIGIN_ZEROCOPY) {
+ pr_err("wrong origin %u", serr->ee_origin);
+ return -1;
+ }
+ if (serr->ee_errno != 0) {
+ pr_err("wrong errno %d", serr->ee_errno);
+ return -1;
+ }
hi = serr->ee_data;
lo = serr->ee_info;
fprintf(stderr, "tx complete [%d,%d]\n", lo, hi);
- return;
+ return 0;
}
}
- error(1, 0, "did not receive tx completion");
+ pr_err("did not receive tx completion");
+ return -1;
}
static int do_client(struct memory_buffer *mem)
@@ -850,50 +1252,69 @@ static int do_client(struct memory_buffer *mem)
ssize_t line_size = 0;
struct cmsghdr *cmsg;
char *line = NULL;
+ int ret, err = -1;
size_t len = 0;
int socket_fd;
__u32 ddmabuf;
int opt = 1;
- int ret;
ret = parse_address(server_ip, atoi(port), &server_sin);
- if (ret < 0)
- error(1, 0, "parse server address");
+ if (ret < 0) {
+ pr_err("parse server address");
+ return -1;
+ }
+
+ if (client_ip) {
+ ret = parse_address(client_ip, atoi(port), &client_sin);
+ if (ret < 0) {
+ pr_err("parse client address");
+ return ret;
+ }
+ }
socket_fd = socket(AF_INET6, SOCK_STREAM, 0);
- if (socket_fd < 0)
- error(1, socket_fd, "create socket");
+ if (socket_fd < 0) {
+ pr_err("create socket");
+ return -1;
+ }
- enable_reuseaddr(socket_fd);
+ if (enable_reuseaddr(socket_fd))
+ goto err_close_socket;
ret = setsockopt(socket_fd, SOL_SOCKET, SO_BINDTODEVICE, ifname,
strlen(ifname) + 1);
- if (ret)
- error(1, errno, "bindtodevice");
+ if (ret) {
+ pr_err("bindtodevice");
+ goto err_close_socket;
+ }
- if (bind_tx_queue(ifindex, mem->fd, &ys))
- error(1, 0, "Failed to bind\n");
+ if (bind_tx_queue(ifindex, mem->fd, &ys)) {
+ pr_err("Failed to bind");
+ goto err_close_socket;
+ }
if (client_ip) {
- ret = parse_address(client_ip, atoi(port), &client_sin);
- if (ret < 0)
- error(1, 0, "parse client address");
-
ret = bind(socket_fd, &client_sin, sizeof(client_sin));
- if (ret)
- error(1, errno, "bind");
+ if (ret) {
+ pr_err("bind");
+ goto err_unbind;
+ }
}
ret = setsockopt(socket_fd, SOL_SOCKET, SO_ZEROCOPY, &opt, sizeof(opt));
- if (ret)
- error(1, errno, "set sock opt");
+ if (ret) {
+ pr_err("set sock opt");
+ goto err_unbind;
+ }
fprintf(stderr, "Connect to %s %d (via %s)\n", server_ip,
ntohs(server_sin.sin6_port), ifname);
ret = connect(socket_fd, &server_sin, sizeof(server_sin));
- if (ret)
- error(1, errno, "connect");
+ if (ret) {
+ pr_err("connect");
+ goto err_unbind;
+ }
while (1) {
free(line);
@@ -906,10 +1327,11 @@ static int do_client(struct memory_buffer *mem)
if (max_chunk) {
msg.msg_iovlen =
(line_size + max_chunk - 1) / max_chunk;
- if (msg.msg_iovlen > MAX_IOV)
- error(1, 0,
- "can't partition %zd bytes into maximum of %d chunks",
- line_size, MAX_IOV);
+ if (msg.msg_iovlen > MAX_IOV) {
+ pr_err("can't partition %zd bytes into maximum of %d chunks",
+ line_size, MAX_IOV);
+ goto err_free_line;
+ }
for (int i = 0; i < msg.msg_iovlen; i++) {
iov[i].iov_base = (void *)(i * max_chunk);
@@ -940,34 +1362,40 @@ static int do_client(struct memory_buffer *mem)
*((__u32 *)CMSG_DATA(cmsg)) = ddmabuf;
ret = sendmsg(socket_fd, &msg, MSG_ZEROCOPY);
- if (ret < 0)
- error(1, errno, "Failed sendmsg");
+ if (ret < 0) {
+ pr_err("Failed sendmsg");
+ goto err_free_line;
+ }
fprintf(stderr, "sendmsg_ret=%d\n", ret);
- if (ret != line_size)
- error(1, errno, "Did not send all bytes %d vs %zd", ret,
- line_size);
+ if (ret != line_size) {
+ pr_err("Did not send all bytes %d vs %zd", ret, line_size);
+ goto err_free_line;
+ }
- wait_compl(socket_fd);
+ if (wait_compl(socket_fd))
+ goto err_free_line;
}
fprintf(stderr, "%s: tx ok\n", TEST_PREFIX);
+ err = 0;
+
+err_free_line:
free(line);
+err_unbind:
+ ynl_sock_destroy(ys);
+err_close_socket:
close(socket_fd);
-
- if (ys)
- ynl_sock_destroy(ys);
-
- return 0;
+ return err;
}
int main(int argc, char *argv[])
{
struct memory_buffer *mem;
int is_server = 0, opt;
- int ret;
+ int ret, err = 1;
while ((opt = getopt(argc, argv, "ls:c:p:v:q:t:f:z:")) != -1) {
switch (opt) {
@@ -1004,8 +1432,10 @@ int main(int argc, char *argv[])
}
}
- if (!ifname)
- error(1, 0, "Missing -f argument\n");
+ if (!ifname) {
+ pr_err("Missing -f argument");
+ return 1;
+ }
ifindex = if_nametoindex(ifname);
@@ -1014,33 +1444,41 @@ int main(int argc, char *argv[])
if (!server_ip && !client_ip) {
if (start_queue < 0 && num_queues < 0) {
num_queues = rxq_num(ifindex);
- if (num_queues < 0)
- error(1, 0, "couldn't detect number of queues\n");
- if (num_queues < 2)
- error(1, 0,
- "number of device queues is too low\n");
+ if (num_queues < 0) {
+ pr_err("couldn't detect number of queues");
+ return 1;
+ }
+ if (num_queues < 2) {
+ pr_err("number of device queues is too low");
+ return 1;
+ }
/* make sure can bind to multiple queues */
start_queue = num_queues / 2;
num_queues /= 2;
}
- if (start_queue < 0 || num_queues < 0)
- error(1, 0, "Both -t and -q are required\n");
+ if (start_queue < 0 || num_queues < 0) {
+ pr_err("Both -t and -q are required");
+ return 1;
+ }
- run_devmem_tests();
- return 0;
+ return run_devmem_tests();
}
if (start_queue < 0 && num_queues < 0) {
num_queues = rxq_num(ifindex);
- if (num_queues < 2)
- error(1, 0, "number of device queues is too low\n");
+ if (num_queues < 2) {
+ pr_err("number of device queues is too low");
+ return 1;
+ }
num_queues = 1;
start_queue = rxq_num(ifindex) - num_queues;
- if (start_queue < 0)
- error(1, 0, "couldn't detect number of queues\n");
+ if (start_queue < 0) {
+ pr_err("couldn't detect number of queues");
+ return 1;
+ }
fprintf(stderr, "using queues %d..%d\n", start_queue, start_queue + num_queues);
}
@@ -1048,21 +1486,39 @@ int main(int argc, char *argv[])
for (; optind < argc; optind++)
fprintf(stderr, "extra arguments: %s\n", argv[optind]);
- if (start_queue < 0)
- error(1, 0, "Missing -t argument\n");
+ if (start_queue < 0) {
+ pr_err("Missing -t argument");
+ return 1;
+ }
- if (num_queues < 0)
- error(1, 0, "Missing -q argument\n");
+ if (num_queues < 0) {
+ pr_err("Missing -q argument");
+ return 1;
+ }
- if (!server_ip)
- error(1, 0, "Missing -s argument\n");
+ if (!server_ip) {
+ pr_err("Missing -s argument");
+ return 1;
+ }
- if (!port)
- error(1, 0, "Missing -p argument\n");
+ if (!port) {
+ pr_err("Missing -p argument");
+ return 1;
+ }
mem = provider->alloc(getpagesize() * NUM_PAGES);
+ if (!mem) {
+ pr_err("Failed to allocate memory buffer");
+ return 1;
+ }
+
ret = is_server ? do_server(mem) : do_client(mem);
- provider->free(mem);
+ if (ret)
+ goto err_free_mem;
- return ret;
+ err = 0;
+
+err_free_mem:
+ provider->free(mem);
+ return err;
}
diff --git a/tools/testing/selftests/drivers/net/hw/nic_timestamp.py b/tools/testing/selftests/drivers/net/hw/nic_timestamp.py
new file mode 100755
index 000000000000..c1e943d53f19
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/hw/nic_timestamp.py
@@ -0,0 +1,113 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+"""
+Tests related to configuration of HW timestamping
+"""
+
+import errno
+from lib.py import ksft_run, ksft_exit, ksft_ge, ksft_eq, KsftSkipEx
+from lib.py import NetDrvEnv, EthtoolFamily, NlError
+
+
+def __get_hwtimestamp_support(cfg):
+ """ Retrieve supported configuration information """
+
+ try:
+ tsinfo = cfg.ethnl.tsinfo_get({'header': {'dev-name': cfg.ifname}})
+ except NlError as e:
+ if e.error == errno.EOPNOTSUPP:
+ raise KsftSkipEx("timestamping configuration is not supported") from e
+ raise
+
+ ctx = {}
+ tx = tsinfo.get('tx-types', {})
+ rx = tsinfo.get('rx-filters', {})
+
+ bits = tx.get('bits', {})
+ ctx['tx'] = bits.get('bit', [])
+ bits = rx.get('bits', {})
+ ctx['rx'] = bits.get('bit', [])
+ return ctx
+
+
+def __get_hwtimestamp_config(cfg):
+ """ Retrieve current TS configuration information """
+
+ try:
+ tscfg = cfg.ethnl.tsconfig_get({'header': {'dev-name': cfg.ifname}})
+ except NlError as e:
+ if e.error == errno.EOPNOTSUPP:
+ raise KsftSkipEx("timestamping configuration is not supported via netlink") from e
+ raise
+ return tscfg
+
+
+def __set_hwtimestamp_config(cfg, ts):
+ """ Setup new TS configuration information """
+
+ ts['header'] = {'dev-name': cfg.ifname}
+ try:
+ res = cfg.ethnl.tsconfig_set(ts)
+ except NlError as e:
+ if e.error == errno.EOPNOTSUPP:
+ raise KsftSkipEx("timestamping configuration is not supported via netlink") from e
+ raise
+ return res
+
+
+def test_hwtstamp_tx(cfg):
+ """
+ Test TX timestamp configuration.
+ The driver should apply provided config and report back proper state.
+ """
+
+ orig_tscfg = __get_hwtimestamp_config(cfg)
+ ts = __get_hwtimestamp_support(cfg)
+ tx = ts['tx']
+ for t in tx:
+ tscfg = orig_tscfg
+ tscfg['tx-types']['bits']['bit'] = [t]
+ res = __set_hwtimestamp_config(cfg, tscfg)
+ if res is None:
+ res = __get_hwtimestamp_config(cfg)
+ ksft_eq(res['tx-types']['bits']['bit'], [t])
+ __set_hwtimestamp_config(cfg, orig_tscfg)
+
+
+def test_hwtstamp_rx(cfg):
+ """
+ Test RX timestamp configuration.
+ The filter configuration is taken from the list of supported filters.
+ The driver should apply the config without error and report back proper state.
+ Some extension of the timestamping scope is allowed for PTP filters.
+ """
+
+ orig_tscfg = __get_hwtimestamp_config(cfg)
+ ts = __get_hwtimestamp_support(cfg)
+ rx = ts['rx']
+ for r in rx:
+ tscfg = orig_tscfg
+ tscfg['rx-filters']['bits']['bit'] = [r]
+ res = __set_hwtimestamp_config(cfg, tscfg)
+ if res is None:
+ res = __get_hwtimestamp_config(cfg)
+ if r['index'] == 0 or r['index'] == 1:
+ ksft_eq(res['rx-filters']['bits']['bit'][0]['index'], r['index'])
+ else:
+ # the driver can fallback to some value which has higher coverage for timestamping
+ ksft_ge(res['rx-filters']['bits']['bit'][0]['index'], r['index'])
+ __set_hwtimestamp_config(cfg, orig_tscfg)
+
+
+def main() -> None:
+ """ Ksft boiler plate main """
+
+ with NetDrvEnv(__file__, nsim_test=False) as cfg:
+ cfg.ethnl = EthtoolFamily()
+ ksft_run([test_hwtstamp_tx, test_hwtstamp_rx], args=(cfg,))
+ ksft_exit()
+
+
+if __name__ == "__main__":
+ main()
diff --git a/tools/testing/selftests/drivers/net/hw/rss_ctx.py b/tools/testing/selftests/drivers/net/hw/rss_ctx.py
index 7bb552f8b182..ed7e405682f0 100755
--- a/tools/testing/selftests/drivers/net/hw/rss_ctx.py
+++ b/tools/testing/selftests/drivers/net/hw/rss_ctx.py
@@ -118,7 +118,7 @@ def test_rss_key_indir(cfg):
qcnt = len(_get_rx_cnts(cfg))
if qcnt < 3:
- KsftSkipEx("Device has fewer than 3 queues (or doesn't support queue stats)")
+ raise KsftSkipEx("Device has fewer than 3 queues (or doesn't support queue stats)")
data = get_rss(cfg)
want_keys = ['rss-hash-key', 'rss-hash-function', 'rss-indirection-table']
@@ -178,8 +178,13 @@ def test_rss_key_indir(cfg):
cnts = _get_rx_cnts(cfg)
GenerateTraffic(cfg).wait_pkts_and_stop(20000)
cnts = _get_rx_cnts(cfg, prev=cnts)
- # First two queues get less traffic than all the rest
- ksft_lt(sum(cnts[:2]), sum(cnts[2:]), "traffic distributed: " + str(cnts))
+ if qcnt > 4:
+ # First two queues get less traffic than all the rest
+ ksft_lt(sum(cnts[:2]), sum(cnts[2:]),
+ "traffic distributed: " + str(cnts))
+ else:
+ # When queue count is low make sure third queue got significant pkts
+ ksft_ge(cnts[2], 3500, "traffic distributed: " + str(cnts))
def test_rss_queue_reconfigure(cfg, main_ctx=True):
@@ -335,19 +340,20 @@ def test_hitless_key_update(cfg):
data = get_rss(cfg)
key_len = len(data['rss-hash-key'])
- key = _rss_key_rand(key_len)
+ ethnl = EthtoolFamily()
+ key = random.randbytes(key_len)
tgen = GenerateTraffic(cfg)
try:
errors0, carrier0 = get_drop_err_sum(cfg)
t0 = datetime.datetime.now()
- ethtool(f"-X {cfg.ifname} hkey " + _rss_key_str(key))
+ ethnl.rss_set({"header": {"dev-index": cfg.ifindex}, "hkey": key})
t1 = datetime.datetime.now()
errors1, carrier1 = get_drop_err_sum(cfg)
finally:
tgen.wait_pkts_and_stop(5000)
- ksft_lt((t1 - t0).total_seconds(), 0.2)
+ ksft_lt((t1 - t0).total_seconds(), 0.15)
ksft_eq(errors1 - errors1, 0)
ksft_eq(carrier1 - carrier0, 0)
diff --git a/tools/testing/selftests/drivers/net/hw/rss_flow_label.py b/tools/testing/selftests/drivers/net/hw/rss_flow_label.py
new file mode 100755
index 000000000000..6fa95fe27c47
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/hw/rss_flow_label.py
@@ -0,0 +1,167 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+"""
+Tests for RSS hashing on IPv6 Flow Label.
+"""
+
+import glob
+import os
+import socket
+from lib.py import CmdExitFailure
+from lib.py import ksft_run, ksft_exit, ksft_eq, ksft_ge, ksft_in, \
+ ksft_not_in, ksft_raises, KsftSkipEx
+from lib.py import bkg, cmd, defer, fd_read_timeout, rand_port
+from lib.py import NetDrvEpEnv
+
+
+def _check_system(cfg):
+ if not hasattr(socket, "SO_INCOMING_CPU"):
+ raise KsftSkipEx("socket.SO_INCOMING_CPU was added in Python 3.11")
+
+ qcnt = len(glob.glob(f"/sys/class/net/{cfg.ifname}/queues/rx-*"))
+ if qcnt < 2:
+ raise KsftSkipEx(f"Local has only {qcnt} queues")
+
+ for f in [f"/sys/class/net/{cfg.ifname}/queues/rx-0/rps_flow_cnt",
+ f"/sys/class/net/{cfg.ifname}/queues/rx-0/rps_cpus"]:
+ try:
+ with open(f, 'r') as fp:
+ setting = fp.read().strip()
+ # CPU mask will be zeros and commas
+ if setting.replace("0", "").replace(",", ""):
+ raise KsftSkipEx(f"RPS/RFS is configured: {f}: {setting}")
+ except FileNotFoundError:
+ pass
+
+ # 1 is the default, if someone changed it we probably shouldn"t mess with it
+ af = cmd("cat /proc/sys/net/ipv6/auto_flowlabels", host=cfg.remote).stdout
+ if af.strip() != "1":
+ raise KsftSkipEx("Remote does not have auto_flowlabels enabled")
+
+
+def _ethtool_get_cfg(cfg, fl_type):
+ descr = cmd(f"ethtool -n {cfg.ifname} rx-flow-hash {fl_type}").stdout
+
+ converter = {
+ "IP SA": "s",
+ "IP DA": "d",
+ "L3 proto": "t",
+ "L4 bytes 0 & 1 [TCP/UDP src port]": "f",
+ "L4 bytes 2 & 3 [TCP/UDP dst port]": "n",
+ "IPv6 Flow Label": "l",
+ }
+
+ ret = ""
+ for line in descr.split("\n")[1:-2]:
+ # if this raises we probably need to add more keys to converter above
+ ret += converter[line]
+ return ret
+
+
+def _traffic(cfg, one_sock, one_cpu):
+ local_port = rand_port(socket.SOCK_DGRAM)
+ remote_port = rand_port(socket.SOCK_DGRAM)
+
+ sock = socket.socket(socket.AF_INET6, socket.SOCK_DGRAM)
+ sock.bind(("", local_port))
+ sock.connect((cfg.remote_addr_v["6"], 0))
+ if one_sock:
+ send = f"exec 5<>/dev/udp/{cfg.addr_v['6']}/{local_port}; " \
+ "for i in `seq 20`; do echo a >&5; sleep 0.02; done; exec 5>&-"
+ else:
+ send = "for i in `seq 20`; do echo a | socat -t0.02 - UDP6:" \
+ f"[{cfg.addr_v['6']}]:{local_port},sourceport={remote_port}; done"
+
+ cpus = set()
+ with bkg(send, shell=True, host=cfg.remote, exit_wait=True):
+ for _ in range(20):
+ fd_read_timeout(sock.fileno(), 1)
+ cpu = sock.getsockopt(socket.SOL_SOCKET, socket.SO_INCOMING_CPU)
+ cpus.add(cpu)
+
+ if one_cpu:
+ ksft_eq(len(cpus), 1,
+ f"{one_sock=} - expected one CPU, got traffic on: {cpus=}")
+ else:
+ ksft_ge(len(cpus), 2,
+ f"{one_sock=} - expected many CPUs, got traffic on: {cpus=}")
+
+
+def test_rss_flow_label(cfg):
+ """
+ Test hashing on IPv6 flow label. Send traffic over a single socket
+ and over multiple sockets. Depend on the remote having auto-label
+ enabled so that it randomizes the label per socket.
+ """
+
+ cfg.require_ipver("6")
+ cfg.require_cmd("socat", remote=True)
+ _check_system(cfg)
+
+ # Enable flow label hashing for UDP6
+ initial = _ethtool_get_cfg(cfg, "udp6")
+ no_lbl = initial.replace("l", "")
+ if "l" not in initial:
+ try:
+ cmd(f"ethtool -N {cfg.ifname} rx-flow-hash udp6 l{no_lbl}")
+ except CmdExitFailure as exc:
+ raise KsftSkipEx("Device doesn't support Flow Label for UDP6") from exc
+
+ defer(cmd, f"ethtool -N {cfg.ifname} rx-flow-hash udp6 {initial}")
+
+ _traffic(cfg, one_sock=True, one_cpu=True)
+ _traffic(cfg, one_sock=False, one_cpu=False)
+
+ # Disable it, we should see no hashing (reset was already defer()ed)
+ cmd(f"ethtool -N {cfg.ifname} rx-flow-hash udp6 {no_lbl}")
+
+ _traffic(cfg, one_sock=False, one_cpu=True)
+
+
+def _check_v4_flow_types(cfg):
+ for fl_type in ["tcp4", "udp4", "ah4", "esp4", "sctp4"]:
+ try:
+ cur = cmd(f"ethtool -n {cfg.ifname} rx-flow-hash {fl_type}").stdout
+ ksft_not_in("Flow Label", cur,
+ comment=f"{fl_type=} has Flow Label:" + cur)
+ except CmdExitFailure:
+ # Probably does not support this flow type
+ pass
+
+
+def test_rss_flow_label_6only(cfg):
+ """
+ Test interactions with IPv4 flow types. It should not be possible to set
+ IPv6 Flow Label hashing for an IPv4 flow type. The Flow Label should also
+ not appear in the IPv4 "current config".
+ """
+
+ with ksft_raises(CmdExitFailure) as cm:
+ cmd(f"ethtool -N {cfg.ifname} rx-flow-hash tcp4 sdfnl")
+ ksft_in("Invalid argument", cm.exception.cmd.stderr)
+
+ _check_v4_flow_types(cfg)
+
+ # Try to enable Flow Labels and check again, in case it leaks thru
+ initial = _ethtool_get_cfg(cfg, "udp6")
+ changed = initial.replace("l", "") if "l" in initial else initial + "l"
+
+ cmd(f"ethtool -N {cfg.ifname} rx-flow-hash udp6 {changed}")
+ restore = defer(cmd, f"ethtool -N {cfg.ifname} rx-flow-hash udp6 {initial}")
+
+ _check_v4_flow_types(cfg)
+ restore.exec()
+ _check_v4_flow_types(cfg)
+
+
+def main() -> None:
+ with NetDrvEpEnv(__file__, nsim_test=False) as cfg:
+ ksft_run([test_rss_flow_label,
+ test_rss_flow_label_6only],
+ args=(cfg, ))
+ ksft_exit()
+
+
+if __name__ == "__main__":
+ main()
diff --git a/tools/testing/selftests/drivers/net/hw/tso.py b/tools/testing/selftests/drivers/net/hw/tso.py
index c13dd5efa27a..0998e68ebaf0 100755
--- a/tools/testing/selftests/drivers/net/hw/tso.py
+++ b/tools/testing/selftests/drivers/net/hw/tso.py
@@ -60,16 +60,17 @@ def run_one_stream(cfg, ipver, remote_v4, remote_v6, should_lso):
sock_wait_drain(sock)
qstat_new = cfg.netnl.qstats_get({"ifindex": cfg.ifindex}, dump=True)[0]
- # No math behind the 10 here, but try to catch cases where
- # TCP falls back to non-LSO.
- ksft_lt(tcp_sock_get_retrans(sock), 10)
- sock.close()
-
# Check that at least 90% of the data was sent as LSO packets.
# System noise may cause false negatives. Also header overheads
# will add up to 5% of extra packes... The check is best effort.
total_lso_wire = len(buf) * 0.90 // cfg.dev["mtu"]
total_lso_super = len(buf) * 0.90 // cfg.dev["tso_max_size"]
+
+ # Make sure we have order of magnitude more LSO packets than
+ # retransmits, in case TCP retransmitted all the LSO packets.
+ ksft_lt(tcp_sock_get_retrans(sock), total_lso_wire / 4)
+ sock.close()
+
if should_lso:
if cfg.have_stat_super_count:
ksft_ge(qstat_new['tx-hw-gso-packets'] -
diff --git a/tools/testing/selftests/drivers/net/lib/py/__init__.py b/tools/testing/selftests/drivers/net/lib/py/__init__.py
index 8711c67ad658..2a645415c4ca 100644
--- a/tools/testing/selftests/drivers/net/lib/py/__init__.py
+++ b/tools/testing/selftests/drivers/net/lib/py/__init__.py
@@ -12,16 +12,16 @@ try:
# Import one by one to avoid pylint false positives
from net.lib.py import EthtoolFamily, NetdevFamily, NetshaperFamily, \
- NlError, RtnlFamily, DevlinkFamily
+ NlError, RtnlFamily, DevlinkFamily, PSPFamily
from net.lib.py import CmdExitFailure
from net.lib.py import bkg, cmd, bpftool, bpftrace, defer, ethtool, \
- fd_read_timeout, ip, rand_port, tool, wait_port_listen
+ fd_read_timeout, ip, rand_port, tool, wait_port_listen, wait_file
from net.lib.py import fd_read_timeout
from net.lib.py import KsftSkipEx, KsftFailEx, KsftXfailEx
from net.lib.py import ksft_disruptive, ksft_exit, ksft_pr, ksft_run, \
ksft_setup
from net.lib.py import ksft_eq, ksft_ge, ksft_in, ksft_is, ksft_lt, \
- ksft_ne, ksft_not_in, ksft_raises, ksft_true
+ ksft_ne, ksft_not_in, ksft_raises, ksft_true, ksft_gt, ksft_not_none
except ModuleNotFoundError as e:
ksft_pr("Failed importing `net` library from kernel sources")
ksft_pr(str(e))
diff --git a/tools/testing/selftests/drivers/net/lib/py/env.py b/tools/testing/selftests/drivers/net/lib/py/env.py
index 1b8bd648048f..01be3d9b9720 100644
--- a/tools/testing/selftests/drivers/net/lib/py/env.py
+++ b/tools/testing/selftests/drivers/net/lib/py/env.py
@@ -4,7 +4,7 @@ import os
import time
from pathlib import Path
from lib.py import KsftSkipEx, KsftXfailEx
-from lib.py import ksft_setup
+from lib.py import ksft_setup, wait_file
from lib.py import cmd, ethtool, ip, CmdExitFailure
from lib.py import NetNS, NetdevSimDev
from .remote import Remote
@@ -25,6 +25,9 @@ class NetDrvEnvBase:
self.env = self._load_env_file()
+ # Following attrs must be set be inheriting classes
+ self.dev = None
+
def _load_env_file(self):
env = os.environ.copy()
@@ -48,6 +51,22 @@ class NetDrvEnvBase:
env[pair[0]] = pair[1]
return ksft_setup(env)
+ def __del__(self):
+ pass
+
+ def __enter__(self):
+ ip(f"link set dev {self.dev['ifname']} up")
+ wait_file(f"/sys/class/net/{self.dev['ifname']}/carrier",
+ lambda x: x.strip() == "1")
+
+ return self
+
+ def __exit__(self, ex_type, ex_value, ex_tb):
+ """
+ __exit__ gets called at the end of a "with" block.
+ """
+ self.__del__()
+
class NetDrvEnv(NetDrvEnvBase):
"""
@@ -72,17 +91,6 @@ class NetDrvEnv(NetDrvEnvBase):
self.ifname = self.dev['ifname']
self.ifindex = self.dev['ifindex']
- def __enter__(self):
- ip(f"link set dev {self.dev['ifname']} up")
-
- return self
-
- def __exit__(self, ex_type, ex_value, ex_tb):
- """
- __exit__ gets called at the end of a "with" block.
- """
- self.__del__()
-
def __del__(self):
if self._ns:
self._ns.remove()
@@ -219,15 +227,6 @@ class NetDrvEpEnv(NetDrvEnvBase):
raise Exception("Can't resolve remote interface name, multiple interfaces match")
return v6[0]["ifname"] if v6 else v4[0]["ifname"]
- def __enter__(self):
- return self
-
- def __exit__(self, ex_type, ex_value, ex_tb):
- """
- __exit__ gets called at the end of a "with" block.
- """
- self.__del__()
-
def __del__(self):
if self._ns:
self._ns.remove()
@@ -246,6 +245,10 @@ class NetDrvEpEnv(NetDrvEnvBase):
if not self.addr_v[ipver] or not self.remote_addr_v[ipver]:
raise KsftSkipEx(f"Test requires IPv{ipver} connectivity")
+ def require_nsim(self):
+ if self._ns is None:
+ raise KsftXfailEx("Test only works on netdevsim")
+
def _require_cmd(self, comm, key, host=None):
cached = self._required_cmd.get(comm, {})
if cached.get(key) is None:
diff --git a/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh b/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh
index b6071e80ebbb..8e1085e89647 100644
--- a/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh
+++ b/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh
@@ -148,12 +148,20 @@ function create_dynamic_target() {
# Generate the command line argument for netconsole following:
# netconsole=[+][src-port]@[src-ip]/[<dev>],[tgt-port]@<tgt-ip>/[tgt-macaddr]
function create_cmdline_str() {
+ local BINDMODE=${1:-"ifname"}
+ if [ "${BINDMODE}" == "ifname" ]
+ then
+ SRCDEV=${SRCIF}
+ else
+ SRCDEV=$(mac_get "${SRCIF}")
+ fi
+
DSTMAC=$(ip netns exec "${NAMESPACE}" \
ip link show "${DSTIF}" | awk '/ether/ {print $2}')
SRCPORT="1514"
TGTPORT="6666"
- echo "netconsole=\"+${SRCPORT}@${SRCIP}/${SRCIF},${TGTPORT}@${DSTIP}/${DSTMAC}\""
+ echo "netconsole=\"+${SRCPORT}@${SRCIP}/${SRCDEV},${TGTPORT}@${DSTIP}/${DSTMAC}\""
}
# Do not append the release to the header of the message
diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_policer.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_policer.sh
index 29a672c2270f..e212ad8ccef6 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_policer.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_policer.sh
@@ -44,8 +44,7 @@ source $lib_dir/devlink_lib.sh
h1_create()
{
- simple_if_init $h1 192.0.2.1/24
- defer simple_if_fini $h1 192.0.2.1/24
+ adf_simple_if_init $h1 192.0.2.1/24
mtu_set $h1 10000
defer mtu_restore $h1
@@ -56,8 +55,7 @@ h1_create()
h2_create()
{
- simple_if_init $h2 198.51.100.1/24
- defer simple_if_fini $h2 198.51.100.1/24
+ adf_simple_if_init $h2 198.51.100.1/24
mtu_set $h2 10000
defer mtu_restore $h2
@@ -106,8 +104,7 @@ setup_prepare()
# Reload to ensure devlink-trap settings are back to default.
defer devlink_reload
- vrf_prepare
- defer vrf_cleanup
+ adf_vrf_prepare
h1_create
h2_create
diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_ets_strict.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_ets_strict.sh
index d5b6f2cc9a29..9ca340c5f3a6 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/qos_ets_strict.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/qos_ets_strict.sh
@@ -57,8 +57,7 @@ source qos_lib.sh
h1_create()
{
- simple_if_init $h1
- defer simple_if_fini $h1
+ adf_simple_if_init $h1
mtu_set $h1 10000
defer mtu_restore $h1
@@ -70,8 +69,7 @@ h1_create()
h2_create()
{
- simple_if_init $h2
- defer simple_if_fini $h2
+ adf_simple_if_init $h2
mtu_set $h2 10000
defer mtu_restore $h2
@@ -83,8 +81,7 @@ h2_create()
h3_create()
{
- simple_if_init $h3
- defer simple_if_fini $h3
+ adf_simple_if_init $h3
mtu_set $h3 10000
defer mtu_restore $h3
@@ -225,8 +222,7 @@ setup_prepare()
h3mac=$(mac_get $h3)
- vrf_prepare
- defer vrf_cleanup
+ adf_vrf_prepare
h1_create
h2_create
diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_max_descriptors.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_max_descriptors.sh
index 2b5d2c2751d5..a4a25637fe2a 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/qos_max_descriptors.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/qos_max_descriptors.sh
@@ -68,8 +68,7 @@ mlxsw_only_on_spectrum 2+ || exit
h1_create()
{
- simple_if_init $h1
- defer simple_if_fini $h1
+ adf_simple_if_init $h1
vlan_create $h1 111 v$h1 192.0.2.33/28
defer vlan_destroy $h1 111
@@ -78,8 +77,7 @@ h1_create()
h2_create()
{
- simple_if_init $h2
- defer simple_if_fini $h2
+ adf_simple_if_init $h2
vlan_create $h2 111 v$h2 192.0.2.34/28
defer vlan_destroy $h2 111
@@ -178,8 +176,7 @@ setup_prepare()
h2mac=$(mac_get $h2)
- vrf_prepare
- defer vrf_cleanup
+ adf_vrf_prepare
h1_create
h2_create
diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh
index cd4a5c21360c..d8f8ae8533cd 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh
@@ -72,8 +72,7 @@ source qos_lib.sh
h1_create()
{
- simple_if_init $h1 192.0.2.65/28
- defer simple_if_fini $h1 192.0.2.65/28
+ adf_simple_if_init $h1 192.0.2.65/28
mtu_set $h1 10000
defer mtu_restore $h1
@@ -81,8 +80,7 @@ h1_create()
h2_create()
{
- simple_if_init $h2
- defer simple_if_fini $h2
+ adf_simple_if_init $h2
mtu_set $h2 10000
defer mtu_restore $h2
@@ -94,8 +92,7 @@ h2_create()
h3_create()
{
- simple_if_init $h3 192.0.2.66/28
- defer simple_if_fini $h3 192.0.2.66/28
+ adf_simple_if_init $h3 192.0.2.66/28
mtu_set $h3 10000
defer mtu_restore $h3
@@ -196,8 +193,7 @@ setup_prepare()
h3mac=$(mac_get $h3)
- vrf_prepare
- defer vrf_cleanup
+ adf_vrf_prepare
h1_create
h2_create
diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh
index 537d6baa77b7..47d2ffcf366e 100644
--- a/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh
@@ -100,8 +100,7 @@ host_create()
local dev=$1; shift
local host=$1; shift
- simple_if_init $dev
- defer simple_if_fini $dev
+ adf_simple_if_init $dev
mtu_set $dev 10000
defer mtu_restore $dev
@@ -250,8 +249,7 @@ setup_prepare()
h3_mac=$(mac_get $h3)
- vrf_prepare
- defer vrf_cleanup
+ adf_vrf_prepare
h1_create
h2_create
diff --git a/tools/testing/selftests/drivers/net/napi_threaded.py b/tools/testing/selftests/drivers/net/napi_threaded.py
index 9699a100a87d..f4be72b2145a 100755
--- a/tools/testing/selftests/drivers/net/napi_threaded.py
+++ b/tools/testing/selftests/drivers/net/napi_threaded.py
@@ -24,7 +24,8 @@ def _assert_napi_threaded_disabled(nl, napi_id) -> None:
def _set_threaded_state(cfg, threaded) -> None:
- cmd(f"echo {threaded} > /sys/class/net/{cfg.ifname}/threaded")
+ with open(f"/sys/class/net/{cfg.ifname}/threaded", "wb") as fp:
+ fp.write(str(threaded).encode('utf-8'))
def _setup_deferred_cleanup(cfg) -> None:
@@ -38,6 +39,34 @@ def _setup_deferred_cleanup(cfg) -> None:
return combined
+def napi_init(cfg, nl) -> None:
+ """
+ Test that threaded state (in the persistent NAPI config) gets updated
+ even when NAPI with given ID is not allocated at the time.
+ """
+
+ qcnt = _setup_deferred_cleanup(cfg)
+
+ _set_threaded_state(cfg, 1)
+ cmd(f"ethtool -L {cfg.ifname} combined 1")
+ _set_threaded_state(cfg, 0)
+ cmd(f"ethtool -L {cfg.ifname} combined {qcnt}")
+
+ napis = nl.napi_get({'ifindex': cfg.ifindex}, dump=True)
+ for napi in napis:
+ ksft_eq(napi['threaded'], 'disabled')
+ ksft_eq(napi.get('pid'), None)
+
+ cmd(f"ethtool -L {cfg.ifname} combined 1")
+ _set_threaded_state(cfg, 1)
+ cmd(f"ethtool -L {cfg.ifname} combined {qcnt}")
+
+ napis = nl.napi_get({'ifindex': cfg.ifindex}, dump=True)
+ for napi in napis:
+ ksft_eq(napi['threaded'], 'enabled')
+ ksft_ne(napi.get('pid'), None)
+
+
def enable_dev_threaded_disable_napi_threaded(cfg, nl) -> None:
"""
Test that when napi threaded is enabled at device level and
@@ -103,7 +132,8 @@ def main() -> None:
""" Ksft boiler plate main """
with NetDrvEnv(__file__, queue_count=2) as cfg:
- ksft_run([change_num_queues,
+ ksft_run([napi_init,
+ change_num_queues,
enable_dev_threaded_disable_napi_threaded],
args=(cfg, NetdevFamily()))
ksft_exit()
diff --git a/tools/testing/selftests/drivers/net/netcons_cmdline.sh b/tools/testing/selftests/drivers/net/netcons_cmdline.sh
index ad2fb8b1c463..d1d23dc67f99 100755
--- a/tools/testing/selftests/drivers/net/netcons_cmdline.sh
+++ b/tools/testing/selftests/drivers/net/netcons_cmdline.sh
@@ -19,9 +19,6 @@ check_netconsole_module
modprobe netdevsim 2> /dev/null || true
rmmod netconsole 2> /dev/null || true
-# The content of kmsg will be save to the following file
-OUTPUT_FILE="/tmp/${TARGET}"
-
# Check for basic system dependency and exit if not found
# check_for_dependencies
# Set current loglevel to KERN_INFO(6), and default to KERN_NOTICE(5)
@@ -30,23 +27,39 @@ echo "6 5" > /proc/sys/kernel/printk
trap do_cleanup EXIT
# Create one namespace and two interfaces
set_network
-# Create the command line for netconsole, with the configuration from the
-# function above
-CMDLINE="$(create_cmdline_str)"
-
-# Load the module, with the cmdline set
-modprobe netconsole "${CMDLINE}"
-
-# Listed for netconsole port inside the namespace and destination interface
-listen_port_and_save_to "${OUTPUT_FILE}" &
-# Wait for socat to start and listen to the port.
-wait_local_port_listen "${NAMESPACE}" "${PORT}" udp
-# Send the message
-echo "${MSG}: ${TARGET}" > /dev/kmsg
-# Wait until socat saves the file to disk
-busywait "${BUSYWAIT_TIMEOUT}" test -s "${OUTPUT_FILE}"
-# Make sure the message was received in the dst part
-# and exit
-validate_msg "${OUTPUT_FILE}"
+
+# Run the test twice, with different cmdline parameters
+for BINDMODE in "ifname" "mac"
+do
+ echo "Running with bind mode: ${BINDMODE}" >&2
+ # Create the command line for netconsole, with the configuration from
+ # the function above
+ CMDLINE=$(create_cmdline_str "${BINDMODE}")
+
+ # The content of kmsg will be save to the following file
+ OUTPUT_FILE="/tmp/${TARGET}-${BINDMODE}"
+
+ # Load the module, with the cmdline set
+ modprobe netconsole "${CMDLINE}"
+
+ # Listed for netconsole port inside the namespace and destination
+ # interface
+ listen_port_and_save_to "${OUTPUT_FILE}" &
+ # Wait for socat to start and listen to the port.
+ wait_local_port_listen "${NAMESPACE}" "${PORT}" udp
+ # Send the message
+ echo "${MSG}: ${TARGET}" > /dev/kmsg
+ # Wait until socat saves the file to disk
+ busywait "${BUSYWAIT_TIMEOUT}" test -s "${OUTPUT_FILE}"
+ # Make sure the message was received in the dst part
+ # and exit
+ validate_msg "${OUTPUT_FILE}"
+
+ # kill socat in case it is still running
+ pkill_socat
+ # Unload the module
+ rmmod netconsole
+ echo "${BINDMODE} : Test passed" >&2
+done
exit "${ksft_pass}"
diff --git a/tools/testing/selftests/drivers/net/psp.py b/tools/testing/selftests/drivers/net/psp.py
new file mode 100755
index 000000000000..4ae7a785ff10
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/psp.py
@@ -0,0 +1,627 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+"""Test suite for PSP capable drivers."""
+
+import errno
+import fcntl
+import socket
+import struct
+import termios
+import time
+
+from lib.py import defer
+from lib.py import ksft_run, ksft_exit, ksft_pr
+from lib.py import ksft_true, ksft_eq, ksft_ne, ksft_gt, ksft_raises
+from lib.py import ksft_not_none
+from lib.py import KsftSkipEx
+from lib.py import NetDrvEpEnv, PSPFamily, NlError
+from lib.py import bkg, rand_port, wait_port_listen
+
+
+def _get_outq(s):
+ one = b'\0' * 4
+ outq = fcntl.ioctl(s.fileno(), termios.TIOCOUTQ, one)
+ return struct.unpack("I", outq)[0]
+
+
+def _send_with_ack(cfg, msg):
+ cfg.comm_sock.send(msg)
+ response = cfg.comm_sock.recv(4)
+ if response != b'ack\0':
+ raise RuntimeError("Unexpected server response", response)
+
+
+def _remote_read_len(cfg):
+ cfg.comm_sock.send(b'read len\0')
+ return int(cfg.comm_sock.recv(1024)[:-1].decode('utf-8'))
+
+
+def _make_clr_conn(cfg, ipver=None):
+ _send_with_ack(cfg, b'conn clr\0')
+ remote_addr = cfg.remote_addr_v[ipver] if ipver else cfg.remote_addr
+ s = socket.create_connection((remote_addr, cfg.comm_port), )
+ return s
+
+
+def _make_psp_conn(cfg, version=0, ipver=None):
+ _send_with_ack(cfg, b'conn psp\0' + struct.pack('BB', version, version))
+ remote_addr = cfg.remote_addr_v[ipver] if ipver else cfg.remote_addr
+ s = socket.create_connection((remote_addr, cfg.comm_port), )
+ return s
+
+
+def _close_conn(cfg, s):
+ _send_with_ack(cfg, b'data close\0')
+ s.close()
+
+
+def _close_psp_conn(cfg, s):
+ _close_conn(cfg, s)
+
+
+def _spi_xchg(s, rx):
+ s.send(struct.pack('I', rx['spi']) + rx['key'])
+ tx = s.recv(4 + len(rx['key']))
+ return {
+ 'spi': struct.unpack('I', tx[:4])[0],
+ 'key': tx[4:]
+ }
+
+
+def _send_careful(cfg, s, rounds):
+ data = b'0123456789' * 200
+ for i in range(rounds):
+ n = 0
+ for _ in range(10): # allow 10 retries
+ try:
+ n += s.send(data[n:], socket.MSG_DONTWAIT)
+ if n == len(data):
+ break
+ except BlockingIOError:
+ time.sleep(0.05)
+ else:
+ rlen = _remote_read_len(cfg)
+ outq = _get_outq(s)
+ report = f'sent: {i * len(data) + n} remote len: {rlen} outq: {outq}'
+ raise RuntimeError(report)
+
+ return len(data) * rounds
+
+
+def _check_data_rx(cfg, exp_len):
+ read_len = -1
+ for _ in range(30):
+ cfg.comm_sock.send(b'read len\0')
+ read_len = int(cfg.comm_sock.recv(1024)[:-1].decode('utf-8'))
+ if read_len == exp_len:
+ break
+ time.sleep(0.01)
+ ksft_eq(read_len, exp_len)
+
+
+def _check_data_outq(s, exp_len, force_wait=False):
+ outq = 0
+ for _ in range(10):
+ outq = _get_outq(s)
+ if not force_wait and outq == exp_len:
+ break
+ time.sleep(0.01)
+ ksft_eq(outq, exp_len)
+
+#
+# Test case boiler plate
+#
+
+def _init_psp_dev(cfg):
+ if not hasattr(cfg, 'psp_dev_id'):
+ # Figure out which local device we are testing against
+ for dev in cfg.pspnl.dev_get({}, dump=True):
+ if dev['ifindex'] == cfg.ifindex:
+ cfg.psp_info = dev
+ cfg.psp_dev_id = cfg.psp_info['id']
+ break
+ else:
+ raise KsftSkipEx("No PSP devices found")
+
+ # Enable PSP if necessary
+ cap = cfg.psp_info['psp-versions-cap']
+ ena = cfg.psp_info['psp-versions-ena']
+ if cap != ena:
+ cfg.pspnl.dev_set({'id': cfg.psp_dev_id, 'psp-versions-ena': cap})
+ defer(cfg.pspnl.dev_set, {'id': cfg.psp_dev_id,
+ 'psp-versions-ena': ena })
+
+#
+# Test cases
+#
+
+def dev_list_devices(cfg):
+ """ Dump all devices """
+ _init_psp_dev(cfg)
+
+ devices = cfg.pspnl.dev_get({}, dump=True)
+
+ found = False
+ for dev in devices:
+ found |= dev['id'] == cfg.psp_dev_id
+ ksft_true(found)
+
+
+def dev_get_device(cfg):
+ """ Get the device we intend to use """
+ _init_psp_dev(cfg)
+
+ dev = cfg.pspnl.dev_get({'id': cfg.psp_dev_id})
+ ksft_eq(dev['id'], cfg.psp_dev_id)
+
+
+def dev_get_device_bad(cfg):
+ """ Test getting device which doesn't exist """
+ raised = False
+ try:
+ cfg.pspnl.dev_get({'id': 1234567})
+ except NlError as e:
+ ksft_eq(e.nl_msg.error, -errno.ENODEV)
+ raised = True
+ ksft_true(raised)
+
+
+def dev_rotate(cfg):
+ """ Test key rotation """
+ _init_psp_dev(cfg)
+
+ rot = cfg.pspnl.key_rotate({"id": cfg.psp_dev_id})
+ ksft_eq(rot['id'], cfg.psp_dev_id)
+ rot = cfg.pspnl.key_rotate({"id": cfg.psp_dev_id})
+ ksft_eq(rot['id'], cfg.psp_dev_id)
+
+
+def dev_rotate_spi(cfg):
+ """ Test key rotation and SPI check """
+ _init_psp_dev(cfg)
+
+ top_a = top_b = 0
+ with socket.socket(socket.AF_INET6, socket.SOCK_STREAM) as s:
+ assoc_a = cfg.pspnl.rx_assoc({"version": 0,
+ "dev-id": cfg.psp_dev_id,
+ "sock-fd": s.fileno()})
+ top_a = assoc_a['rx-key']['spi'] >> 31
+ s.close()
+ rot = cfg.pspnl.key_rotate({"id": cfg.psp_dev_id})
+ with socket.socket(socket.AF_INET6, socket.SOCK_STREAM) as s:
+ ksft_eq(rot['id'], cfg.psp_dev_id)
+ assoc_b = cfg.pspnl.rx_assoc({"version": 0,
+ "dev-id": cfg.psp_dev_id,
+ "sock-fd": s.fileno()})
+ top_b = assoc_b['rx-key']['spi'] >> 31
+ s.close()
+ ksft_ne(top_a, top_b)
+
+
+def assoc_basic(cfg):
+ """ Test creating associations """
+ _init_psp_dev(cfg)
+
+ with socket.socket(socket.AF_INET6, socket.SOCK_STREAM) as s:
+ assoc = cfg.pspnl.rx_assoc({"version": 0,
+ "dev-id": cfg.psp_dev_id,
+ "sock-fd": s.fileno()})
+ ksft_eq(assoc['dev-id'], cfg.psp_dev_id)
+ ksft_gt(assoc['rx-key']['spi'], 0)
+ ksft_eq(len(assoc['rx-key']['key']), 16)
+
+ assoc = cfg.pspnl.tx_assoc({"dev-id": cfg.psp_dev_id,
+ "version": 0,
+ "tx-key": assoc['rx-key'],
+ "sock-fd": s.fileno()})
+ ksft_eq(len(assoc), 0)
+ s.close()
+
+
+def assoc_bad_dev(cfg):
+ """ Test creating associations with bad device ID """
+ _init_psp_dev(cfg)
+
+ with socket.socket(socket.AF_INET6, socket.SOCK_STREAM) as s:
+ with ksft_raises(NlError) as cm:
+ cfg.pspnl.rx_assoc({"version": 0,
+ "dev-id": cfg.psp_dev_id + 1234567,
+ "sock-fd": s.fileno()})
+ ksft_eq(cm.exception.nl_msg.error, -errno.ENODEV)
+
+
+def assoc_sk_only_conn(cfg):
+ """ Test creating associations based on socket """
+ _init_psp_dev(cfg)
+
+ with _make_clr_conn(cfg) as s:
+ assoc = cfg.pspnl.rx_assoc({"version": 0,
+ "sock-fd": s.fileno()})
+ ksft_eq(assoc['dev-id'], cfg.psp_dev_id)
+ cfg.pspnl.tx_assoc({"version": 0,
+ "tx-key": assoc['rx-key'],
+ "sock-fd": s.fileno()})
+ _close_conn(cfg, s)
+
+
+def assoc_sk_only_mismatch(cfg):
+ """ Test creating associations based on socket (dev mismatch) """
+ _init_psp_dev(cfg)
+
+ with _make_clr_conn(cfg) as s:
+ with ksft_raises(NlError) as cm:
+ cfg.pspnl.rx_assoc({"version": 0,
+ "dev-id": cfg.psp_dev_id + 1234567,
+ "sock-fd": s.fileno()})
+ the_exception = cm.exception
+ ksft_eq(the_exception.nl_msg.extack['bad-attr'], ".dev-id")
+ ksft_eq(the_exception.nl_msg.error, -errno.EINVAL)
+
+
+def assoc_sk_only_mismatch_tx(cfg):
+ """ Test creating associations based on socket (dev mismatch) """
+ _init_psp_dev(cfg)
+
+ with _make_clr_conn(cfg) as s:
+ with ksft_raises(NlError) as cm:
+ assoc = cfg.pspnl.rx_assoc({"version": 0,
+ "sock-fd": s.fileno()})
+ cfg.pspnl.tx_assoc({"version": 0,
+ "tx-key": assoc['rx-key'],
+ "dev-id": cfg.psp_dev_id + 1234567,
+ "sock-fd": s.fileno()})
+ the_exception = cm.exception
+ ksft_eq(the_exception.nl_msg.extack['bad-attr'], ".dev-id")
+ ksft_eq(the_exception.nl_msg.error, -errno.EINVAL)
+
+
+def assoc_sk_only_unconn(cfg):
+ """ Test creating associations based on socket (unconnected, should fail) """
+ _init_psp_dev(cfg)
+
+ with socket.socket(socket.AF_INET6, socket.SOCK_STREAM) as s:
+ with ksft_raises(NlError) as cm:
+ cfg.pspnl.rx_assoc({"version": 0,
+ "sock-fd": s.fileno()})
+ the_exception = cm.exception
+ ksft_eq(the_exception.nl_msg.extack['miss-type'], "dev-id")
+ ksft_eq(the_exception.nl_msg.error, -errno.EINVAL)
+
+
+def assoc_version_mismatch(cfg):
+ """ Test creating associations where Rx and Tx PSP versions do not match """
+ _init_psp_dev(cfg)
+
+ versions = list(cfg.psp_info['psp-versions-cap'])
+ if len(versions) < 2:
+ raise KsftSkipEx("Not enough PSP versions supported by the device for the test")
+
+ # Translate versions to integers
+ versions = [cfg.pspnl.consts["version"].entries[v].value for v in versions]
+
+ with socket.socket(socket.AF_INET6, socket.SOCK_STREAM) as s:
+ rx = cfg.pspnl.rx_assoc({"version": versions[0],
+ "dev-id": cfg.psp_dev_id,
+ "sock-fd": s.fileno()})
+
+ for version in versions[1:]:
+ with ksft_raises(NlError) as cm:
+ cfg.pspnl.tx_assoc({"dev-id": cfg.psp_dev_id,
+ "version": version,
+ "tx-key": rx['rx-key'],
+ "sock-fd": s.fileno()})
+ the_exception = cm.exception
+ ksft_eq(the_exception.nl_msg.error, -errno.EINVAL)
+
+
+def assoc_twice(cfg):
+ """ Test reusing Tx assoc for two sockets """
+ _init_psp_dev(cfg)
+
+ def rx_assoc_check(s):
+ assoc = cfg.pspnl.rx_assoc({"version": 0,
+ "dev-id": cfg.psp_dev_id,
+ "sock-fd": s.fileno()})
+ ksft_eq(assoc['dev-id'], cfg.psp_dev_id)
+ ksft_gt(assoc['rx-key']['spi'], 0)
+ ksft_eq(len(assoc['rx-key']['key']), 16)
+
+ return assoc
+
+ with socket.socket(socket.AF_INET6, socket.SOCK_STREAM) as s:
+ assoc = rx_assoc_check(s)
+ tx = cfg.pspnl.tx_assoc({"dev-id": cfg.psp_dev_id,
+ "version": 0,
+ "tx-key": assoc['rx-key'],
+ "sock-fd": s.fileno()})
+ ksft_eq(len(tx), 0)
+
+ # Use the same Tx assoc second time
+ with socket.socket(socket.AF_INET6, socket.SOCK_STREAM) as s2:
+ rx_assoc_check(s2)
+ tx = cfg.pspnl.tx_assoc({"dev-id": cfg.psp_dev_id,
+ "version": 0,
+ "tx-key": assoc['rx-key'],
+ "sock-fd": s2.fileno()})
+ ksft_eq(len(tx), 0)
+
+ s.close()
+
+
+def _data_basic_send(cfg, version, ipver):
+ """ Test basic data send """
+ _init_psp_dev(cfg)
+
+ # Version 0 is required by spec, don't let it skip
+ if version:
+ name = cfg.pspnl.consts["version"].entries_by_val[version].name
+ if name not in cfg.psp_info['psp-versions-cap']:
+ with socket.socket(socket.AF_INET6, socket.SOCK_STREAM) as s:
+ with ksft_raises(NlError) as cm:
+ cfg.pspnl.rx_assoc({"version": version,
+ "dev-id": cfg.psp_dev_id,
+ "sock-fd": s.fileno()})
+ ksft_eq(cm.exception.nl_msg.error, -errno.EOPNOTSUPP)
+ raise KsftSkipEx("PSP version not supported", name)
+
+ s = _make_psp_conn(cfg, version, ipver)
+
+ rx_assoc = cfg.pspnl.rx_assoc({"version": version,
+ "dev-id": cfg.psp_dev_id,
+ "sock-fd": s.fileno()})
+ rx = rx_assoc['rx-key']
+ tx = _spi_xchg(s, rx)
+
+ cfg.pspnl.tx_assoc({"dev-id": cfg.psp_dev_id,
+ "version": version,
+ "tx-key": tx,
+ "sock-fd": s.fileno()})
+
+ data_len = _send_careful(cfg, s, 100)
+ _check_data_rx(cfg, data_len)
+ _close_psp_conn(cfg, s)
+
+
+def __bad_xfer_do(cfg, s, tx, version='hdr0-aes-gcm-128'):
+ # Make sure we accept the ACK for the SPI before we seal with the bad assoc
+ _check_data_outq(s, 0)
+
+ cfg.pspnl.tx_assoc({"dev-id": cfg.psp_dev_id,
+ "version": version,
+ "tx-key": tx,
+ "sock-fd": s.fileno()})
+
+ data_len = _send_careful(cfg, s, 20)
+ _check_data_outq(s, data_len, force_wait=True)
+ _check_data_rx(cfg, 0)
+ _close_psp_conn(cfg, s)
+
+
+def data_send_bad_key(cfg):
+ """ Test send data with bad key """
+ _init_psp_dev(cfg)
+
+ s = _make_psp_conn(cfg)
+
+ rx_assoc = cfg.pspnl.rx_assoc({"version": 0,
+ "dev-id": cfg.psp_dev_id,
+ "sock-fd": s.fileno()})
+ rx = rx_assoc['rx-key']
+ tx = _spi_xchg(s, rx)
+ tx['key'] = (tx['key'][0] ^ 0xff).to_bytes(1, 'little') + tx['key'][1:]
+ __bad_xfer_do(cfg, s, tx)
+
+
+def data_send_disconnect(cfg):
+ """ Test socket close after sending data """
+ _init_psp_dev(cfg)
+
+ with _make_psp_conn(cfg) as s:
+ assoc = cfg.pspnl.rx_assoc({"version": 0,
+ "sock-fd": s.fileno()})
+ tx = _spi_xchg(s, assoc['rx-key'])
+ cfg.pspnl.tx_assoc({"version": 0,
+ "tx-key": tx,
+ "sock-fd": s.fileno()})
+
+ data_len = _send_careful(cfg, s, 100)
+ _check_data_rx(cfg, data_len)
+
+ s.shutdown(socket.SHUT_RDWR)
+ s.close()
+
+
+def _data_mss_adjust(cfg, ipver):
+ _init_psp_dev(cfg)
+
+ # First figure out what the MSS would be without any adjustments
+ s = _make_clr_conn(cfg, ipver)
+ s.send(b"0123456789abcdef" * 1024)
+ _check_data_rx(cfg, 16 * 1024)
+ mss = s.getsockopt(socket.IPPROTO_TCP, socket.TCP_MAXSEG)
+ _close_conn(cfg, s)
+
+ s = _make_psp_conn(cfg, 0, ipver)
+ try:
+ rx_assoc = cfg.pspnl.rx_assoc({"version": 0,
+ "dev-id": cfg.psp_dev_id,
+ "sock-fd": s.fileno()})
+ rx = rx_assoc['rx-key']
+ tx = _spi_xchg(s, rx)
+
+ rxmss = s.getsockopt(socket.IPPROTO_TCP, socket.TCP_MAXSEG)
+ ksft_eq(mss, rxmss)
+
+ cfg.pspnl.tx_assoc({"dev-id": cfg.psp_dev_id,
+ "version": 0,
+ "tx-key": tx,
+ "sock-fd": s.fileno()})
+
+ txmss = s.getsockopt(socket.IPPROTO_TCP, socket.TCP_MAXSEG)
+ ksft_eq(mss, txmss + 40)
+
+ data_len = _send_careful(cfg, s, 100)
+ _check_data_rx(cfg, data_len)
+ _check_data_outq(s, 0)
+
+ txmss = s.getsockopt(socket.IPPROTO_TCP, socket.TCP_MAXSEG)
+ ksft_eq(mss, txmss + 40)
+ finally:
+ _close_psp_conn(cfg, s)
+
+
+def data_stale_key(cfg):
+ """ Test send on a double-rotated key """
+ _init_psp_dev(cfg)
+
+ s = _make_psp_conn(cfg)
+ try:
+ rx_assoc = cfg.pspnl.rx_assoc({"version": 0,
+ "dev-id": cfg.psp_dev_id,
+ "sock-fd": s.fileno()})
+ rx = rx_assoc['rx-key']
+ tx = _spi_xchg(s, rx)
+
+ cfg.pspnl.tx_assoc({"dev-id": cfg.psp_dev_id,
+ "version": 0,
+ "tx-key": tx,
+ "sock-fd": s.fileno()})
+
+ data_len = _send_careful(cfg, s, 100)
+ _check_data_rx(cfg, data_len)
+ _check_data_outq(s, 0)
+
+ cfg.pspnl.key_rotate({"id": cfg.psp_dev_id})
+ cfg.pspnl.key_rotate({"id": cfg.psp_dev_id})
+
+ s.send(b'0123456789' * 200)
+ _check_data_outq(s, 2000, force_wait=True)
+ finally:
+ _close_psp_conn(cfg, s)
+
+
+def __nsim_psp_rereg(cfg):
+ # The PSP dev ID will change, remember what was there before
+ before = set([x['id'] for x in cfg.pspnl.dev_get({}, dump=True)])
+
+ cfg._ns.nsims[0].dfs_write('psp_rereg', '1')
+
+ after = set([x['id'] for x in cfg.pspnl.dev_get({}, dump=True)])
+
+ new_devs = list(after - before)
+ ksft_eq(len(new_devs), 1)
+ cfg.psp_dev_id = list(after - before)[0]
+
+
+def removal_device_rx(cfg):
+ """ Test removing a netdev / PSD with active Rx assoc """
+
+ # We could technically devlink reload real devices, too
+ # but that kills the control socket. So test this on
+ # netdevsim only for now
+ cfg.require_nsim()
+
+ s = _make_clr_conn(cfg)
+ try:
+ rx_assoc = cfg.pspnl.rx_assoc({"version": 0,
+ "dev-id": cfg.psp_dev_id,
+ "sock-fd": s.fileno()})
+ ksft_not_none(rx_assoc)
+
+ __nsim_psp_rereg(cfg)
+ finally:
+ _close_conn(cfg, s)
+
+
+def removal_device_bi(cfg):
+ """ Test removing a netdev / PSD with active Rx/Tx assoc """
+
+ # We could technically devlink reload real devices, too
+ # but that kills the control socket. So test this on
+ # netdevsim only for now
+ cfg.require_nsim()
+
+ s = _make_clr_conn(cfg)
+ try:
+ rx_assoc = cfg.pspnl.rx_assoc({"version": 0,
+ "dev-id": cfg.psp_dev_id,
+ "sock-fd": s.fileno()})
+ cfg.pspnl.tx_assoc({"dev-id": cfg.psp_dev_id,
+ "version": 0,
+ "tx-key": rx_assoc['rx-key'],
+ "sock-fd": s.fileno()})
+ __nsim_psp_rereg(cfg)
+ finally:
+ _close_conn(cfg, s)
+
+
+def psp_ip_ver_test_builder(name, test_func, psp_ver, ipver):
+ """Build test cases for each combo of PSP version and IP version"""
+ def test_case(cfg):
+ cfg.require_ipver(ipver)
+ test_case.__name__ = f"{name}_v{psp_ver}_ip{ipver}"
+ test_func(cfg, psp_ver, ipver)
+ return test_case
+
+
+def ipver_test_builder(name, test_func, ipver):
+ """Build test cases for each IP version"""
+ def test_case(cfg):
+ cfg.require_ipver(ipver)
+ test_case.__name__ = f"{name}_ip{ipver}"
+ test_func(cfg, ipver)
+ return test_case
+
+
+def main() -> None:
+ """ Ksft boiler plate main """
+
+ with NetDrvEpEnv(__file__) as cfg:
+ cfg.pspnl = PSPFamily()
+
+ # Set up responder and communication sock
+ responder = cfg.remote.deploy("psp_responder")
+
+ cfg.comm_port = rand_port()
+ srv = None
+ try:
+ with bkg(responder + f" -p {cfg.comm_port}", host=cfg.remote,
+ exit_wait=True) as srv:
+ wait_port_listen(cfg.comm_port, host=cfg.remote)
+
+ cfg.comm_sock = socket.create_connection((cfg.remote_addr,
+ cfg.comm_port),
+ timeout=1)
+
+ cases = [
+ psp_ip_ver_test_builder(
+ "data_basic_send", _data_basic_send, version, ipver
+ )
+ for version in range(0, 4)
+ for ipver in ("4", "6")
+ ]
+ cases += [
+ ipver_test_builder("data_mss_adjust", _data_mss_adjust, ipver)
+ for ipver in ("4", "6")
+ ]
+
+ ksft_run(cases=cases, globs=globals(),
+ case_pfx={"dev_", "data_", "assoc_", "removal_"},
+ args=(cfg, ))
+
+ cfg.comm_sock.send(b"exit\0")
+ cfg.comm_sock.close()
+ finally:
+ if srv and (srv.stdout or srv.stderr):
+ ksft_pr("")
+ ksft_pr(f"Responder logs ({srv.ret}):")
+ if srv and srv.stdout:
+ ksft_pr("STDOUT:\n# " + srv.stdout.strip().replace("\n", "\n# "))
+ if srv and srv.stderr:
+ ksft_pr("STDERR:\n# " + srv.stderr.strip().replace("\n", "\n# "))
+ ksft_exit()
+
+
+if __name__ == "__main__":
+ main()
diff --git a/tools/testing/selftests/drivers/net/psp_responder.c b/tools/testing/selftests/drivers/net/psp_responder.c
new file mode 100644
index 000000000000..f309e0d73cbf
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/psp_responder.c
@@ -0,0 +1,483 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <stdio.h>
+#include <string.h>
+#include <sys/poll.h>
+#include <sys/socket.h>
+#include <sys/time.h>
+#include <netinet/in.h>
+#include <unistd.h>
+
+#include <ynl.h>
+
+#include "psp-user.h"
+
+#define dbg(msg...) \
+do { \
+ if (opts->verbose) \
+ fprintf(stderr, "DEBUG: " msg); \
+} while (0)
+
+static bool should_quit;
+
+struct opts {
+ int port;
+ int devid;
+ bool verbose;
+};
+
+enum accept_cfg {
+ ACCEPT_CFG_NONE = 0,
+ ACCEPT_CFG_CLEAR,
+ ACCEPT_CFG_PSP,
+};
+
+static struct {
+ unsigned char tx;
+ unsigned char rx;
+} psp_vers;
+
+static int conn_setup_psp(struct ynl_sock *ys, struct opts *opts, int data_sock)
+{
+ struct psp_rx_assoc_rsp *rsp;
+ struct psp_rx_assoc_req *req;
+ struct psp_tx_assoc_rsp *tsp;
+ struct psp_tx_assoc_req *teq;
+ char info[300];
+ int key_len;
+ ssize_t sz;
+ __u32 spi;
+
+ dbg("create PSP connection\n");
+
+ // Rx assoc alloc
+ req = psp_rx_assoc_req_alloc();
+
+ psp_rx_assoc_req_set_sock_fd(req, data_sock);
+ psp_rx_assoc_req_set_version(req, psp_vers.rx);
+
+ rsp = psp_rx_assoc(ys, req);
+ psp_rx_assoc_req_free(req);
+
+ if (!rsp) {
+ perror("ERROR: failed to Rx assoc");
+ return -1;
+ }
+
+ // SPI exchange
+ key_len = rsp->rx_key._len.key;
+ memcpy(info, &rsp->rx_key.spi, sizeof(spi));
+ memcpy(&info[sizeof(spi)], rsp->rx_key.key, key_len);
+ sz = sizeof(spi) + key_len;
+
+ send(data_sock, info, sz, MSG_WAITALL);
+ psp_rx_assoc_rsp_free(rsp);
+
+ sz = recv(data_sock, info, sz, MSG_WAITALL);
+ if (sz < 0) {
+ perror("ERROR: failed to read PSP key from sock");
+ return -1;
+ }
+ memcpy(&spi, info, sizeof(spi));
+
+ // Setup Tx assoc
+ teq = psp_tx_assoc_req_alloc();
+
+ psp_tx_assoc_req_set_sock_fd(teq, data_sock);
+ psp_tx_assoc_req_set_version(teq, psp_vers.tx);
+ psp_tx_assoc_req_set_tx_key_spi(teq, spi);
+ psp_tx_assoc_req_set_tx_key_key(teq, &info[sizeof(spi)], key_len);
+
+ tsp = psp_tx_assoc(ys, teq);
+ psp_tx_assoc_req_free(teq);
+ if (!tsp) {
+ perror("ERROR: failed to Tx assoc");
+ return -1;
+ }
+ psp_tx_assoc_rsp_free(tsp);
+
+ return 0;
+}
+
+static void send_ack(int sock)
+{
+ send(sock, "ack", 4, MSG_WAITALL);
+}
+
+static void send_err(int sock)
+{
+ send(sock, "err", 4, MSG_WAITALL);
+}
+
+static void send_str(int sock, int value)
+{
+ char buf[128];
+ int ret;
+
+ ret = snprintf(buf, sizeof(buf), "%d", value);
+ send(sock, buf, ret + 1, MSG_WAITALL);
+}
+
+static void
+run_session(struct ynl_sock *ys, struct opts *opts,
+ int server_sock, int comm_sock)
+{
+ enum accept_cfg accept_cfg = ACCEPT_CFG_NONE;
+ struct pollfd pfds[3];
+ size_t data_read = 0;
+ int data_sock = -1;
+
+ while (true) {
+ bool race_close = false;
+ int nfds;
+
+ memset(pfds, 0, sizeof(pfds));
+
+ pfds[0].fd = server_sock;
+ pfds[0].events = POLLIN;
+
+ pfds[1].fd = comm_sock;
+ pfds[1].events = POLLIN;
+
+ nfds = 2;
+ if (data_sock >= 0) {
+ pfds[2].fd = data_sock;
+ pfds[2].events = POLLIN;
+ nfds++;
+ }
+
+ dbg(" ...\n");
+ if (poll(pfds, nfds, -1) < 0) {
+ perror("poll");
+ break;
+ }
+
+ /* data sock */
+ if (pfds[2].revents & POLLIN) {
+ char buf[8192];
+ ssize_t n;
+
+ n = recv(data_sock, buf, sizeof(buf), 0);
+ if (n <= 0) {
+ if (n < 0)
+ perror("data read");
+ close(data_sock);
+ data_sock = -1;
+ dbg("data sock closed\n");
+ } else {
+ data_read += n;
+ dbg("data read %zd\n", data_read);
+ }
+ }
+
+ /* comm sock */
+ if (pfds[1].revents & POLLIN) {
+ static char buf[4096];
+ static ssize_t off;
+ bool consumed;
+ ssize_t n;
+
+ n = recv(comm_sock, &buf[off], sizeof(buf) - off, 0);
+ if (n <= 0) {
+ if (n < 0)
+ perror("comm read");
+ return;
+ }
+
+ off += n;
+ n = off;
+
+#define __consume(sz) \
+ ({ \
+ if (n == (sz)) { \
+ off = 0; \
+ } else { \
+ off -= (sz); \
+ memmove(buf, &buf[(sz)], off); \
+ } \
+ })
+
+#define cmd(_name) \
+ ({ \
+ ssize_t sz = sizeof(_name); \
+ bool match = n >= sz && !memcmp(buf, _name, sz); \
+ \
+ if (match) { \
+ dbg("command: " _name "\n"); \
+ __consume(sz); \
+ } \
+ consumed |= match; \
+ match; \
+ })
+
+ do {
+ consumed = false;
+
+ if (cmd("read len"))
+ send_str(comm_sock, data_read);
+
+ if (cmd("data echo")) {
+ if (data_sock >= 0)
+ send(data_sock, "echo", 5,
+ MSG_WAITALL);
+ else
+ fprintf(stderr, "WARN: echo but no data sock\n");
+ send_ack(comm_sock);
+ }
+ if (cmd("data close")) {
+ if (data_sock >= 0) {
+ close(data_sock);
+ data_sock = -1;
+ send_ack(comm_sock);
+ } else {
+ race_close = true;
+ }
+ }
+ if (cmd("conn psp")) {
+ if (accept_cfg != ACCEPT_CFG_NONE)
+ fprintf(stderr, "WARN: old conn config still set!\n");
+ accept_cfg = ACCEPT_CFG_PSP;
+ send_ack(comm_sock);
+ /* next two bytes are versions */
+ if (off >= 2) {
+ memcpy(&psp_vers, buf, 2);
+ __consume(2);
+ } else {
+ fprintf(stderr, "WARN: short conn psp command!\n");
+ }
+ }
+ if (cmd("conn clr")) {
+ if (accept_cfg != ACCEPT_CFG_NONE)
+ fprintf(stderr, "WARN: old conn config still set!\n");
+ accept_cfg = ACCEPT_CFG_CLEAR;
+ send_ack(comm_sock);
+ }
+ if (cmd("exit"))
+ should_quit = true;
+#undef cmd
+
+ if (!consumed) {
+ fprintf(stderr, "WARN: unknown cmd: [%zd] %s\n",
+ off, buf);
+ }
+ } while (consumed && off);
+ }
+
+ /* server sock */
+ if (pfds[0].revents & POLLIN) {
+ if (data_sock >= 0) {
+ fprintf(stderr, "WARN: new data sock but old one still here\n");
+ close(data_sock);
+ data_sock = -1;
+ }
+ data_sock = accept(server_sock, NULL, NULL);
+ if (data_sock < 0) {
+ perror("accept");
+ continue;
+ }
+ data_read = 0;
+
+ if (accept_cfg == ACCEPT_CFG_CLEAR) {
+ dbg("new data sock: clear\n");
+ /* nothing to do */
+ } else if (accept_cfg == ACCEPT_CFG_PSP) {
+ dbg("new data sock: psp\n");
+ conn_setup_psp(ys, opts, data_sock);
+ } else {
+ fprintf(stderr, "WARN: new data sock but no config\n");
+ }
+ accept_cfg = ACCEPT_CFG_NONE;
+ }
+
+ if (race_close) {
+ if (data_sock >= 0) {
+ /* indeed, ordering problem, handle the close */
+ close(data_sock);
+ data_sock = -1;
+ send_ack(comm_sock);
+ } else {
+ fprintf(stderr, "WARN: close but no data sock\n");
+ send_err(comm_sock);
+ }
+ }
+ }
+ dbg("session ending\n");
+}
+
+static int spawn_server(struct opts *opts)
+{
+ struct sockaddr_in6 addr;
+ int fd;
+
+ fd = socket(AF_INET6, SOCK_STREAM, 0);
+ if (fd < 0) {
+ perror("can't open socket");
+ return -1;
+ }
+
+ memset(&addr, 0, sizeof(addr));
+
+ addr.sin6_family = AF_INET6;
+ addr.sin6_addr = in6addr_any;
+ addr.sin6_port = htons(opts->port);
+
+ if (bind(fd, (struct sockaddr *)&addr, sizeof(addr))) {
+ perror("can't bind socket");
+ return -1;
+ }
+
+ if (listen(fd, 5)) {
+ perror("can't listen");
+ return -1;
+ }
+
+ return fd;
+}
+
+static int run_responder(struct ynl_sock *ys, struct opts *opts)
+{
+ int server_sock, comm;
+
+ server_sock = spawn_server(opts);
+ if (server_sock < 0)
+ return 4;
+
+ while (!should_quit) {
+ comm = accept(server_sock, NULL, NULL);
+ if (comm < 0) {
+ perror("accept failed");
+ } else {
+ run_session(ys, opts, server_sock, comm);
+ close(comm);
+ }
+ }
+
+ return 0;
+}
+
+static void usage(const char *name, const char *miss)
+{
+ if (miss)
+ fprintf(stderr, "Missing argument: %s\n", miss);
+
+ fprintf(stderr, "Usage: %s -p port [-v] [-d psp-dev-id]\n", name);
+ exit(EXIT_FAILURE);
+}
+
+static void parse_cmd_opts(int argc, char **argv, struct opts *opts)
+{
+ int opt;
+
+ while ((opt = getopt(argc, argv, "vp:d:")) != -1) {
+ switch (opt) {
+ case 'v':
+ opts->verbose = 1;
+ break;
+ case 'p':
+ opts->port = atoi(optarg);
+ break;
+ case 'd':
+ opts->devid = atoi(optarg);
+ break;
+ default:
+ usage(argv[0], NULL);
+ }
+ }
+}
+
+static int psp_dev_set_ena(struct ynl_sock *ys, __u32 dev_id, __u32 versions)
+{
+ struct psp_dev_set_req *sreq;
+ struct psp_dev_set_rsp *srsp;
+
+ fprintf(stderr, "Set PSP enable on device %d to 0x%x\n",
+ dev_id, versions);
+
+ sreq = psp_dev_set_req_alloc();
+
+ psp_dev_set_req_set_id(sreq, dev_id);
+ psp_dev_set_req_set_psp_versions_ena(sreq, versions);
+
+ srsp = psp_dev_set(ys, sreq);
+ psp_dev_set_req_free(sreq);
+ if (!srsp)
+ return 10;
+
+ psp_dev_set_rsp_free(srsp);
+ return 0;
+}
+
+int main(int argc, char **argv)
+{
+ struct psp_dev_get_list *dev_list;
+ bool devid_found = false;
+ __u32 ver_ena, ver_cap;
+ struct opts opts = {};
+ struct ynl_error yerr;
+ struct ynl_sock *ys;
+ int first_id = 0;
+ int ret;
+
+ parse_cmd_opts(argc, argv, &opts);
+ if (!opts.port)
+ usage(argv[0], "port"); // exits
+
+ ys = ynl_sock_create(&ynl_psp_family, &yerr);
+ if (!ys) {
+ fprintf(stderr, "YNL: %s\n", yerr.msg);
+ return 1;
+ }
+
+ dev_list = psp_dev_get_dump(ys);
+ if (ynl_dump_empty(dev_list)) {
+ if (ys->err.code)
+ goto err_close;
+ fprintf(stderr, "No PSP devices\n");
+ goto err_close_silent;
+ }
+
+ ynl_dump_foreach(dev_list, d) {
+ if (opts.devid) {
+ devid_found = true;
+ ver_ena = d->psp_versions_ena;
+ ver_cap = d->psp_versions_cap;
+ } else if (!first_id) {
+ first_id = d->id;
+ ver_ena = d->psp_versions_ena;
+ ver_cap = d->psp_versions_cap;
+ } else {
+ fprintf(stderr, "Multiple PSP devices found\n");
+ goto err_close_silent;
+ }
+ }
+ psp_dev_get_list_free(dev_list);
+
+ if (opts.devid && !devid_found) {
+ fprintf(stderr, "PSP device %d requested on cmdline, not found\n",
+ opts.devid);
+ goto err_close_silent;
+ } else if (!opts.devid) {
+ opts.devid = first_id;
+ }
+
+ if (ver_ena != ver_cap) {
+ ret = psp_dev_set_ena(ys, opts.devid, ver_cap);
+ if (ret)
+ goto err_close;
+ }
+
+ ret = run_responder(ys, &opts);
+
+ if (ver_ena != ver_cap && psp_dev_set_ena(ys, opts.devid, ver_ena))
+ fprintf(stderr, "WARN: failed to set the PSP versions back\n");
+
+ ynl_sock_destroy(ys);
+
+ return ret;
+
+err_close:
+ fprintf(stderr, "YNL: %s\n", ys->err.msg);
+err_close_silent:
+ ynl_sock_destroy(ys);
+ return 2;
+}
diff --git a/tools/testing/selftests/drivers/net/stats.py b/tools/testing/selftests/drivers/net/stats.py
index c2bb5d3f1ca1..04d0a2a13e73 100755
--- a/tools/testing/selftests/drivers/net/stats.py
+++ b/tools/testing/selftests/drivers/net/stats.py
@@ -57,6 +57,36 @@ def check_fec(cfg) -> None:
ksft_true(data['stats'], "driver does not report stats")
+def check_fec_hist(cfg) -> None:
+ """
+ Check that drivers which support FEC histogram statistics report
+ reasonable values.
+ """
+
+ try:
+ data = ethnl.fec_get({"header": {"dev-index": cfg.ifindex,
+ "flags": {'stats'}}})
+ except NlError as e:
+ if e.error == errno.EOPNOTSUPP:
+ raise KsftSkipEx("FEC not supported by the device") from e
+ raise
+ if 'stats' not in data:
+ raise KsftSkipEx("FEC stats not supported by the device")
+ if 'hist' not in data['stats']:
+ raise KsftSkipEx("FEC histogram not supported by the device")
+
+ hist = data['stats']['hist']
+ for fec_bin in hist:
+ for key in ['bin-low', 'bin-high', 'bin-val']:
+ ksft_in(key, fec_bin,
+ "Drivers should always report FEC bin range and value")
+ ksft_ge(fec_bin['bin-high'], fec_bin['bin-low'],
+ "FEC bin range should be valid")
+ if 'bin-val-per-lane' in fec_bin:
+ ksft_eq(sum(fec_bin['bin-val-per-lane']), fec_bin['bin-val'],
+ "FEC bin value should be equal to sum of per-plane values")
+
+
def pkt_byte_sum(cfg) -> None:
"""
Check that qstat and interface stats match in value.
@@ -279,8 +309,9 @@ def main() -> None:
""" Ksft boiler plate main """
with NetDrvEnv(__file__, queue_count=100) as cfg:
- ksft_run([check_pause, check_fec, pkt_byte_sum, qstat_by_ifindex,
- check_down, procfs_hammer, procfs_downup_hammer],
+ ksft_run([check_pause, check_fec, check_fec_hist, pkt_byte_sum,
+ qstat_by_ifindex, check_down, procfs_hammer,
+ procfs_downup_hammer],
args=(cfg, ))
ksft_exit()
diff --git a/tools/testing/selftests/drivers/net/team/Makefile b/tools/testing/selftests/drivers/net/team/Makefile
index eaf6938f100e..89d854c7e674 100644
--- a/tools/testing/selftests/drivers/net/team/Makefile
+++ b/tools/testing/selftests/drivers/net/team/Makefile
@@ -1,11 +1,13 @@
# SPDX-License-Identifier: GPL-2.0
# Makefile for net selftests
-TEST_PROGS := dev_addr_lists.sh propagation.sh
+TEST_PROGS := dev_addr_lists.sh propagation.sh options.sh
TEST_INCLUDES := \
../bonding/lag_lib.sh \
../../../net/forwarding/lib.sh \
- ../../../net/lib.sh
+ ../../../net/lib.sh \
+ ../../../net/in_netns.sh \
+ ../../../net/lib/sh/defer.sh
include ../../../lib.mk
diff --git a/tools/testing/selftests/drivers/net/team/config b/tools/testing/selftests/drivers/net/team/config
index 636b3525b679..558e1d0cf565 100644
--- a/tools/testing/selftests/drivers/net/team/config
+++ b/tools/testing/selftests/drivers/net/team/config
@@ -3,4 +3,5 @@ CONFIG_IPV6=y
CONFIG_MACVLAN=y
CONFIG_NETDEVSIM=m
CONFIG_NET_TEAM=y
+CONFIG_NET_TEAM_MODE_ACTIVEBACKUP=y
CONFIG_NET_TEAM_MODE_LOADBALANCE=y
diff --git a/tools/testing/selftests/drivers/net/team/options.sh b/tools/testing/selftests/drivers/net/team/options.sh
new file mode 100755
index 000000000000..44888f32b513
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/team/options.sh
@@ -0,0 +1,188 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# These tests verify basic set and get functionality of the team
+# driver options over netlink.
+
+# Run in private netns.
+test_dir="$(dirname "$0")"
+if [[ $# -eq 0 ]]; then
+ "${test_dir}"/../../../net/in_netns.sh "$0" __subprocess
+ exit $?
+fi
+
+ALL_TESTS="
+ team_test_options
+"
+
+source "${test_dir}/../../../net/lib.sh"
+
+TEAM_PORT="team0"
+MEMBER_PORT="dummy0"
+
+setup()
+{
+ ip link add name "${MEMBER_PORT}" type dummy
+ ip link add name "${TEAM_PORT}" type team
+}
+
+get_and_check_value()
+{
+ local option_name="$1"
+ local expected_value="$2"
+ local port_flag="$3"
+
+ local value_from_get
+
+ if ! value_from_get=$(teamnl "${TEAM_PORT}" getoption "${option_name}" \
+ "${port_flag}"); then
+ echo "Could not get option '${option_name}'" >&2
+ return 1
+ fi
+
+ if [[ "${value_from_get}" != "${expected_value}" ]]; then
+ echo "Incorrect value for option '${option_name}'" >&2
+ echo "get (${value_from_get}) != set (${expected_value})" >&2
+ return 1
+ fi
+}
+
+set_and_check_get()
+{
+ local option_name="$1"
+ local option_value="$2"
+ local port_flag="$3"
+
+ local value_from_get
+
+ if ! teamnl "${TEAM_PORT}" setoption "${option_name}" \
+ "${option_value}" "${port_flag}"; then
+ echo "'setoption ${option_name} ${option_value}' failed" >&2
+ return 1
+ fi
+
+ get_and_check_value "${option_name}" "${option_value}" "${port_flag}"
+ return $?
+}
+
+# Get a "port flag" to pass to the `teamnl` command.
+# E.g. $1="dummy0" -> "port=dummy0",
+# $1="" -> ""
+get_port_flag()
+{
+ local port_name="$1"
+
+ if [[ -n "${port_name}" ]]; then
+ echo "--port=${port_name}"
+ fi
+}
+
+attach_port_if_specified()
+{
+ local port_name="$1"
+
+ if [[ -n "${port_name}" ]]; then
+ ip link set dev "${port_name}" master "${TEAM_PORT}"
+ return $?
+ fi
+}
+
+detach_port_if_specified()
+{
+ local port_name="$1"
+
+ if [[ -n "${port_name}" ]]; then
+ ip link set dev "${port_name}" nomaster
+ return $?
+ fi
+}
+
+# Test that an option's get value matches its set value.
+# Globals:
+# RET - Used by testing infra like `check_err`.
+# EXIT_STATUS - Used by `log_test` for whole script exit value.
+# Arguments:
+# option_name - The name of the option.
+# value_1 - The first value to try setting.
+# value_2 - The second value to try setting.
+# port_name - The (optional) name of the attached port.
+team_test_option()
+{
+ local option_name="$1"
+ local value_1="$2"
+ local value_2="$3"
+ local possible_values="$2 $3 $2"
+ local port_name="$4"
+ local port_flag
+
+ RET=0
+
+ echo "Setting '${option_name}' to '${value_1}' and '${value_2}'"
+
+ attach_port_if_specified "${port_name}"
+ check_err $? "Couldn't attach ${port_name} to master"
+ port_flag=$(get_port_flag "${port_name}")
+
+ # Set and get both possible values.
+ for value in ${possible_values}; do
+ set_and_check_get "${option_name}" "${value}" "${port_flag}"
+ check_err $? "Failed to set '${option_name}' to '${value}'"
+ done
+
+ detach_port_if_specified "${port_name}"
+ check_err $? "Couldn't detach ${port_name} from its master"
+
+ log_test "Set + Get '${option_name}' test"
+}
+
+# Test that getting a non-existant option fails.
+# Globals:
+# RET - Used by testing infra like `check_err`.
+# EXIT_STATUS - Used by `log_test` for whole script exit value.
+# Arguments:
+# option_name - The name of the option.
+# port_name - The (optional) name of the attached port.
+team_test_get_option_fails()
+{
+ local option_name="$1"
+ local port_name="$2"
+ local port_flag
+
+ RET=0
+
+ attach_port_if_specified "${port_name}"
+ check_err $? "Couldn't attach ${port_name} to master"
+ port_flag=$(get_port_flag "${port_name}")
+
+ # Just confirm that getting the value fails.
+ teamnl "${TEAM_PORT}" getoption "${option_name}" "${port_flag}"
+ check_fail $? "Shouldn't be able to get option '${option_name}'"
+
+ detach_port_if_specified "${port_name}"
+
+ log_test "Get '${option_name}' fails"
+}
+
+team_test_options()
+{
+ # Wrong option name behavior.
+ team_test_get_option_fails fake_option1
+ team_test_get_option_fails fake_option2 "${MEMBER_PORT}"
+
+ # Correct set and get behavior.
+ team_test_option mode activebackup loadbalance
+ team_test_option notify_peers_count 0 5
+ team_test_option notify_peers_interval 0 5
+ team_test_option mcast_rejoin_count 0 5
+ team_test_option mcast_rejoin_interval 0 5
+ team_test_option enabled true false "${MEMBER_PORT}"
+ team_test_option user_linkup true false "${MEMBER_PORT}"
+ team_test_option user_linkup_enabled true false "${MEMBER_PORT}"
+ team_test_option priority 10 20 "${MEMBER_PORT}"
+ team_test_option queue_id 0 1 "${MEMBER_PORT}"
+}
+
+require_command teamnl
+setup
+tests_run
+exit "${EXIT_STATUS}"
diff --git a/tools/testing/selftests/drivers/net/xdp.py b/tools/testing/selftests/drivers/net/xdp.py
index 1dd8bf3bf6c9..08fea4230759 100755
--- a/tools/testing/selftests/drivers/net/xdp.py
+++ b/tools/testing/selftests/drivers/net/xdp.py
@@ -112,10 +112,10 @@ def _load_xdp_prog(cfg, bpf_info):
defer(ip, f"link set dev {cfg.remote_ifname} mtu 1500", host=cfg.remote)
cmd(
- f"ip link set dev {cfg.ifname} mtu {bpf_info.mtu} xdp obj {abs_path} sec {bpf_info.xdp_sec}",
+ f"ip link set dev {cfg.ifname} mtu {bpf_info.mtu} xdpdrv obj {abs_path} sec {bpf_info.xdp_sec}",
shell=True
)
- defer(ip, f"link set dev {cfg.ifname} mtu 1500 xdp off")
+ defer(ip, f"link set dev {cfg.ifname} mtu 1500 xdpdrv off")
xdp_info = ip(f"-d link show dev {cfg.ifname}", json=True)[0]
prog_info["id"] = xdp_info["xdp"]["prog"]["id"]
@@ -290,34 +290,78 @@ def test_xdp_native_drop_mb(cfg):
_test_drop(cfg, bpf_info, 8000)
-def test_xdp_native_tx_mb(cfg):
+def _test_xdp_native_tx(cfg, bpf_info, payload_lens):
"""
- Tests the XDP_TX action for a multi-buff case.
+ Tests the XDP_TX action.
Args:
cfg: Configuration object containing network settings.
+ bpf_info: BPFProgInfo object containing the BPF program metadata.
+ payload_lens: Array of packet lengths to send.
"""
cfg.require_cmd("socat", remote=True)
-
- bpf_info = BPFProgInfo("xdp_prog_frags", "xdp_native.bpf.o", "xdp.frags", 9000)
prog_info = _load_xdp_prog(cfg, bpf_info)
port = rand_port()
_set_xdp_map("map_xdp_setup", TestConfig.MODE.value, XDPAction.TX.value)
_set_xdp_map("map_xdp_setup", TestConfig.PORT.value, port)
- test_string = ''.join(random.choice(string.ascii_lowercase) for _ in range(8000))
- rx_udp = f"socat -{cfg.addr_ipver} -T 2 -u UDP-RECV:{port},reuseport STDOUT"
- tx_udp = f"echo {test_string} | socat -t 2 -u STDIN UDP:{cfg.baddr}:{port}"
+ expected_pkts = 0
+ for payload_len in payload_lens:
+ test_string = "".join(
+ random.choice(string.ascii_lowercase) for _ in range(payload_len)
+ )
+
+ rx_udp = f"socat -{cfg.addr_ipver} -T 2 " + \
+ f"-u UDP-RECV:{port},reuseport STDOUT"
+
+ # Writing zero bytes to stdin gets ignored by socat,
+ # but with the shut-null flag socat generates a zero sized packet
+ # when the socket is closed.
+ tx_cmd_suffix = ",shut-null" if payload_len == 0 else ""
+ tx_udp = f"echo -n {test_string} | socat -t 2 " + \
+ f"-u STDIN UDP:{cfg.baddr}:{port}{tx_cmd_suffix}"
+
+ with bkg(rx_udp, host=cfg.remote, exit_wait=True) as rnc:
+ wait_port_listen(port, proto="udp", host=cfg.remote)
+ cmd(tx_udp, host=cfg.remote, shell=True)
+
+ ksft_eq(rnc.stdout.strip(), test_string, "UDP packet exchange failed")
+
+ expected_pkts += 1
+ stats = _get_stats(prog_info["maps"]["map_xdp_stats"])
+ ksft_eq(stats[XDPStats.RX.value], expected_pkts, "RX stats mismatch")
+ ksft_eq(stats[XDPStats.TX.value], expected_pkts, "TX stats mismatch")
+
+
+def test_xdp_native_tx_sb(cfg):
+ """
+ Tests the XDP_TX action for a single-buff case.
+
+ Args:
+ cfg: Configuration object containing network settings.
+ """
+ bpf_info = BPFProgInfo("xdp_prog", "xdp_native.bpf.o", "xdp", 1500)
+
+ # Ensure there's enough room for an ETH / IP / UDP header
+ pkt_hdr_len = 42 if cfg.addr_ipver == "4" else 62
- with bkg(rx_udp, host=cfg.remote, exit_wait=True) as rnc:
- wait_port_listen(port, proto="udp", host=cfg.remote)
- cmd(tx_udp, host=cfg.remote, shell=True)
+ _test_xdp_native_tx(cfg, bpf_info, [0, 1500 // 2, 1500 - pkt_hdr_len])
- stats = _get_stats(prog_info['maps']['map_xdp_stats'])
- ksft_eq(rnc.stdout.strip(), test_string, "UDP packet exchange failed")
- ksft_eq(stats[XDPStats.TX.value], 1, "TX stats mismatch")
+def test_xdp_native_tx_mb(cfg):
+ """
+ Tests the XDP_TX action for a multi-buff case.
+
+ Args:
+ cfg: Configuration object containing network settings.
+ """
+ bpf_info = BPFProgInfo("xdp_prog_frags", "xdp_native.bpf.o",
+ "xdp.frags", 9000)
+ # The first packet ensures we exercise the fragmented code path.
+ # And the subsequent 0-sized packet ensures the driver
+ # reinitializes xdp_buff correctly.
+ _test_xdp_native_tx(cfg, bpf_info, [8000, 0])
def _validate_res(res, offset_lst, pkt_sz_lst):
@@ -644,6 +688,7 @@ def main():
test_xdp_native_pass_mb,
test_xdp_native_drop_sb,
test_xdp_native_drop_mb,
+ test_xdp_native_tx_sb,
test_xdp_native_tx_mb,
test_xdp_native_adjst_tail_grow_data,
test_xdp_native_adjst_tail_shrnk_data,
diff --git a/tools/testing/selftests/filesystems/.gitignore b/tools/testing/selftests/filesystems/.gitignore
index fcbdb1297e24..64ac0dfa46b7 100644
--- a/tools/testing/selftests/filesystems/.gitignore
+++ b/tools/testing/selftests/filesystems/.gitignore
@@ -1,6 +1,7 @@
# SPDX-License-Identifier: GPL-2.0-only
dnotify_test
devpts_pts
+fclog
file_stressor
anon_inode_test
kernfs_test
diff --git a/tools/testing/selftests/filesystems/Makefile b/tools/testing/selftests/filesystems/Makefile
index 73d4650af1a5..85427d7f19b9 100644
--- a/tools/testing/selftests/filesystems/Makefile
+++ b/tools/testing/selftests/filesystems/Makefile
@@ -1,7 +1,7 @@
# SPDX-License-Identifier: GPL-2.0
CFLAGS += $(KHDR_INCLUDES)
-TEST_GEN_PROGS := devpts_pts file_stressor anon_inode_test kernfs_test
+TEST_GEN_PROGS := devpts_pts file_stressor anon_inode_test kernfs_test fclog
TEST_GEN_PROGS_EXTENDED := dnotify_test
include ../lib.mk
diff --git a/tools/testing/selftests/filesystems/fclog.c b/tools/testing/selftests/filesystems/fclog.c
new file mode 100644
index 000000000000..912a8b755c3b
--- /dev/null
+++ b/tools/testing/selftests/filesystems/fclog.c
@@ -0,0 +1,130 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Author: Aleksa Sarai <cyphar@cyphar.com>
+ * Copyright (C) 2025 SUSE LLC.
+ */
+
+#include <assert.h>
+#include <errno.h>
+#include <sched.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/mount.h>
+
+#include "../kselftest_harness.h"
+
+#define ASSERT_ERRNO(expected, _t, seen) \
+ __EXPECT(expected, #expected, \
+ ({__typeof__(seen) _tmp_seen = (seen); \
+ _tmp_seen >= 0 ? _tmp_seen : -errno; }), #seen, _t, 1)
+
+#define ASSERT_ERRNO_EQ(expected, seen) \
+ ASSERT_ERRNO(expected, ==, seen)
+
+#define ASSERT_SUCCESS(seen) \
+ ASSERT_ERRNO(0, <=, seen)
+
+FIXTURE(ns)
+{
+ int host_mntns;
+};
+
+FIXTURE_SETUP(ns)
+{
+ /* Stash the old mntns. */
+ self->host_mntns = open("/proc/self/ns/mnt", O_RDONLY|O_CLOEXEC);
+ ASSERT_SUCCESS(self->host_mntns);
+
+ /* Create a new mount namespace and make it private. */
+ ASSERT_SUCCESS(unshare(CLONE_NEWNS));
+ ASSERT_SUCCESS(mount(NULL, "/", NULL, MS_PRIVATE|MS_REC, NULL));
+}
+
+FIXTURE_TEARDOWN(ns)
+{
+ ASSERT_SUCCESS(setns(self->host_mntns, CLONE_NEWNS));
+ ASSERT_SUCCESS(close(self->host_mntns));
+}
+
+TEST_F(ns, fscontext_log_enodata)
+{
+ int fsfd = fsopen("tmpfs", FSOPEN_CLOEXEC);
+ ASSERT_SUCCESS(fsfd);
+
+ /* A brand new fscontext has no log entries. */
+ char buf[128] = {};
+ for (int i = 0; i < 16; i++)
+ ASSERT_ERRNO_EQ(-ENODATA, read(fsfd, buf, sizeof(buf)));
+
+ ASSERT_SUCCESS(close(fsfd));
+}
+
+TEST_F(ns, fscontext_log_errorfc)
+{
+ int fsfd = fsopen("tmpfs", FSOPEN_CLOEXEC);
+ ASSERT_SUCCESS(fsfd);
+
+ ASSERT_ERRNO_EQ(-EINVAL, fsconfig(fsfd, FSCONFIG_SET_STRING, "invalid-arg", "123", 0));
+
+ char buf[128] = {};
+ ASSERT_SUCCESS(read(fsfd, buf, sizeof(buf)));
+ EXPECT_STREQ("e tmpfs: Unknown parameter 'invalid-arg'\n", buf);
+
+ /* The message has been consumed. */
+ ASSERT_ERRNO_EQ(-ENODATA, read(fsfd, buf, sizeof(buf)));
+ ASSERT_SUCCESS(close(fsfd));
+}
+
+TEST_F(ns, fscontext_log_errorfc_after_fsmount)
+{
+ int fsfd = fsopen("tmpfs", FSOPEN_CLOEXEC);
+ ASSERT_SUCCESS(fsfd);
+
+ ASSERT_ERRNO_EQ(-EINVAL, fsconfig(fsfd, FSCONFIG_SET_STRING, "invalid-arg", "123", 0));
+
+ ASSERT_SUCCESS(fsconfig(fsfd, FSCONFIG_CMD_CREATE, NULL, NULL, 0));
+ int mfd = fsmount(fsfd, FSMOUNT_CLOEXEC, MOUNT_ATTR_NOEXEC | MOUNT_ATTR_NOSUID);
+ ASSERT_SUCCESS(mfd);
+ ASSERT_SUCCESS(move_mount(mfd, "", AT_FDCWD, "/tmp", MOVE_MOUNT_F_EMPTY_PATH));
+
+ /*
+ * The fscontext log should still contain data even after
+ * FSCONFIG_CMD_CREATE and fsmount().
+ */
+ char buf[128] = {};
+ ASSERT_SUCCESS(read(fsfd, buf, sizeof(buf)));
+ EXPECT_STREQ("e tmpfs: Unknown parameter 'invalid-arg'\n", buf);
+
+ /* The message has been consumed. */
+ ASSERT_ERRNO_EQ(-ENODATA, read(fsfd, buf, sizeof(buf)));
+ ASSERT_SUCCESS(close(fsfd));
+}
+
+TEST_F(ns, fscontext_log_emsgsize)
+{
+ int fsfd = fsopen("tmpfs", FSOPEN_CLOEXEC);
+ ASSERT_SUCCESS(fsfd);
+
+ ASSERT_ERRNO_EQ(-EINVAL, fsconfig(fsfd, FSCONFIG_SET_STRING, "invalid-arg", "123", 0));
+
+ char buf[128] = {};
+ /*
+ * Attempting to read a message with too small a buffer should not
+ * result in the message getting consumed.
+ */
+ ASSERT_ERRNO_EQ(-EMSGSIZE, read(fsfd, buf, 0));
+ ASSERT_ERRNO_EQ(-EMSGSIZE, read(fsfd, buf, 1));
+ for (int i = 0; i < 16; i++)
+ ASSERT_ERRNO_EQ(-EMSGSIZE, read(fsfd, buf, 16));
+
+ ASSERT_SUCCESS(read(fsfd, buf, sizeof(buf)));
+ EXPECT_STREQ("e tmpfs: Unknown parameter 'invalid-arg'\n", buf);
+
+ /* The message has been consumed. */
+ ASSERT_ERRNO_EQ(-ENODATA, read(fsfd, buf, sizeof(buf)));
+ ASSERT_SUCCESS(close(fsfd));
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/filesystems/mount-notify/mount-notify_test.c b/tools/testing/selftests/filesystems/mount-notify/mount-notify_test.c
index 63ce708d93ed..e4b7c2b457ee 100644
--- a/tools/testing/selftests/filesystems/mount-notify/mount-notify_test.c
+++ b/tools/testing/selftests/filesystems/mount-notify/mount-notify_test.c
@@ -2,6 +2,13 @@
// Copyright (c) 2025 Miklos Szeredi <miklos@szeredi.hu>
#define _GNU_SOURCE
+
+// Needed for linux/fanotify.h
+typedef struct {
+ int val[2];
+} __kernel_fsid_t;
+#define __kernel_fsid_t __kernel_fsid_t
+
#include <fcntl.h>
#include <sched.h>
#include <stdio.h>
@@ -10,20 +17,12 @@
#include <sys/mount.h>
#include <unistd.h>
#include <sys/syscall.h>
+#include <sys/fanotify.h>
#include "../../kselftest_harness.h"
#include "../statmount/statmount.h"
#include "../utils.h"
-// Needed for linux/fanotify.h
-#ifndef __kernel_fsid_t
-typedef struct {
- int val[2];
-} __kernel_fsid_t;
-#endif
-
-#include <sys/fanotify.h>
-
static const char root_mntpoint_templ[] = "/tmp/mount-notify_test_root.XXXXXX";
static const int mark_cmds[] = {
diff --git a/tools/testing/selftests/filesystems/mount-notify/mount-notify_test_ns.c b/tools/testing/selftests/filesystems/mount-notify/mount-notify_test_ns.c
index 090a5ca65004..9f57ca46e3af 100644
--- a/tools/testing/selftests/filesystems/mount-notify/mount-notify_test_ns.c
+++ b/tools/testing/selftests/filesystems/mount-notify/mount-notify_test_ns.c
@@ -2,6 +2,13 @@
// Copyright (c) 2025 Miklos Szeredi <miklos@szeredi.hu>
#define _GNU_SOURCE
+
+// Needed for linux/fanotify.h
+typedef struct {
+ int val[2];
+} __kernel_fsid_t;
+#define __kernel_fsid_t __kernel_fsid_t
+
#include <fcntl.h>
#include <sched.h>
#include <stdio.h>
@@ -10,21 +17,12 @@
#include <sys/mount.h>
#include <unistd.h>
#include <sys/syscall.h>
+#include <sys/fanotify.h>
#include "../../kselftest_harness.h"
-#include "../../pidfd/pidfd.h"
#include "../statmount/statmount.h"
#include "../utils.h"
-// Needed for linux/fanotify.h
-#ifndef __kernel_fsid_t
-typedef struct {
- int val[2];
-} __kernel_fsid_t;
-#endif
-
-#include <sys/fanotify.h>
-
static const char root_mntpoint_templ[] = "/tmp/mount-notify_test_root.XXXXXX";
static const int mark_types[] = {
diff --git a/tools/testing/selftests/futex/functional/Makefile b/tools/testing/selftests/futex/functional/Makefile
index 8cfb87f7f7c5..490ace1f017e 100644
--- a/tools/testing/selftests/futex/functional/Makefile
+++ b/tools/testing/selftests/futex/functional/Makefile
@@ -1,12 +1,14 @@
# SPDX-License-Identifier: GPL-2.0
+PKG_CONFIG ?= pkg-config
+LIBNUMA_TEST = $(shell sh -c "$(PKG_CONFIG) numa --atleast-version 2.0.16 > /dev/null 2>&1 && echo SUFFICIENT || echo NO")
+
INCLUDES := -I../include -I../../ $(KHDR_INCLUDES)
-CFLAGS := $(CFLAGS) -g -O2 -Wall -pthread $(INCLUDES) $(KHDR_INCLUDES)
+CFLAGS := $(CFLAGS) -g -O2 -Wall -pthread -D_FILE_OFFSET_BITS=64 -D_TIME_BITS=64 $(INCLUDES) $(KHDR_INCLUDES) -DLIBNUMA_VER_$(LIBNUMA_TEST)=1
LDLIBS := -lpthread -lrt -lnuma
LOCAL_HDRS := \
../include/futextest.h \
- ../include/atomic.h \
- ../include/logging.h
+ ../include/atomic.h
TEST_GEN_PROGS := \
futex_wait_timeout \
futex_wait_wouldblock \
diff --git a/tools/testing/selftests/futex/functional/futex_numa.c b/tools/testing/selftests/futex/functional/futex_numa.c
index f29e4d627e79..e0a33510ccb6 100644
--- a/tools/testing/selftests/futex/functional/futex_numa.c
+++ b/tools/testing/selftests/futex/functional/futex_numa.c
@@ -5,9 +5,10 @@
#include <sys/mman.h>
#include <fcntl.h>
#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
#include <time.h>
#include <assert.h>
-#include "logging.h"
#include "futextest.h"
#include "futex2test.h"
diff --git a/tools/testing/selftests/futex/functional/futex_numa_mpol.c b/tools/testing/selftests/futex/functional/futex_numa_mpol.c
index a9ecfb2d3932..d037a3f10ee8 100644
--- a/tools/testing/selftests/futex/functional/futex_numa_mpol.c
+++ b/tools/testing/selftests/futex/functional/futex_numa_mpol.c
@@ -16,9 +16,9 @@
#include <linux/futex.h>
#include <sys/mman.h>
-#include "logging.h"
#include "futextest.h"
#include "futex2test.h"
+#include "../../kselftest_harness.h"
#define MAX_THREADS 64
@@ -77,7 +77,7 @@ static void join_max_threads(void)
}
}
-static void __test_futex(void *futex_ptr, int must_fail, unsigned int futex_flags)
+static void __test_futex(void *futex_ptr, int err_value, unsigned int futex_flags)
{
int to_wake, ret, i, need_exit = 0;
@@ -88,11 +88,17 @@ static void __test_futex(void *futex_ptr, int must_fail, unsigned int futex_flag
do {
ret = futex2_wake(futex_ptr, to_wake, futex_flags);
- if (must_fail) {
- if (ret < 0)
- break;
- ksft_exit_fail_msg("futex2_wake(%d, 0x%x) should fail, but didn't\n",
- to_wake, futex_flags);
+
+ if (err_value) {
+ if (ret >= 0)
+ ksft_exit_fail_msg("futex2_wake(%d, 0x%x) should fail, but didn't\n",
+ to_wake, futex_flags);
+
+ if (errno != err_value)
+ ksft_exit_fail_msg("futex2_wake(%d, 0x%x) expected error was %d, but returned %d (%s)\n",
+ to_wake, futex_flags, err_value, errno, strerror(errno));
+
+ break;
}
if (ret < 0) {
ksft_exit_fail_msg("Failed futex2_wake(%d, 0x%x): %m\n",
@@ -106,12 +112,12 @@ static void __test_futex(void *futex_ptr, int must_fail, unsigned int futex_flag
join_max_threads();
for (i = 0; i < MAX_THREADS; i++) {
- if (must_fail && thread_args[i].result != -1) {
+ if (err_value && thread_args[i].result != -1) {
ksft_print_msg("Thread %d should fail but succeeded (%d)\n",
i, thread_args[i].result);
need_exit = 1;
}
- if (!must_fail && thread_args[i].result != 0) {
+ if (!err_value && thread_args[i].result != 0) {
ksft_print_msg("Thread %d failed (%d)\n", i, thread_args[i].result);
need_exit = 1;
}
@@ -120,58 +126,30 @@ static void __test_futex(void *futex_ptr, int must_fail, unsigned int futex_flag
ksft_exit_fail_msg("Aborting due to earlier errors.\n");
}
-static void test_futex(void *futex_ptr, int must_fail)
+static void test_futex(void *futex_ptr, int err_value)
{
- __test_futex(futex_ptr, must_fail, FUTEX2_SIZE_U32 | FUTEX_PRIVATE_FLAG | FUTEX2_NUMA);
+ __test_futex(futex_ptr, err_value, FUTEX2_SIZE_U32 | FUTEX_PRIVATE_FLAG | FUTEX2_NUMA);
}
-static void test_futex_mpol(void *futex_ptr, int must_fail)
+static void test_futex_mpol(void *futex_ptr, int err_value)
{
- __test_futex(futex_ptr, must_fail, FUTEX2_SIZE_U32 | FUTEX_PRIVATE_FLAG | FUTEX2_NUMA | FUTEX2_MPOL);
+ __test_futex(futex_ptr, err_value, FUTEX2_SIZE_U32 | FUTEX_PRIVATE_FLAG | FUTEX2_NUMA | FUTEX2_MPOL);
}
-static void usage(char *prog)
-{
- printf("Usage: %s\n", prog);
- printf(" -c Use color\n");
- printf(" -h Display this help message\n");
- printf(" -v L Verbosity level: %d=QUIET %d=CRITICAL %d=INFO\n",
- VQUIET, VCRITICAL, VINFO);
-}
-
-int main(int argc, char *argv[])
+TEST(futex_numa_mpol)
{
struct futex32_numa *futex_numa;
- int mem_size, i;
void *futex_ptr;
- int c;
-
- while ((c = getopt(argc, argv, "chv:")) != -1) {
- switch (c) {
- case 'c':
- log_color(1);
- break;
- case 'h':
- usage(basename(argv[0]));
- exit(0);
- break;
- case 'v':
- log_verbosity(atoi(optarg));
- break;
- default:
- usage(basename(argv[0]));
- exit(1);
- }
- }
-
- ksft_print_header();
- ksft_set_plan(1);
+ int mem_size;
mem_size = sysconf(_SC_PAGE_SIZE);
- futex_ptr = mmap(NULL, mem_size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, 0, 0);
+ futex_ptr = mmap(NULL, mem_size * 2, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, 0, 0);
if (futex_ptr == MAP_FAILED)
ksft_exit_fail_msg("mmap() for %d bytes failed\n", mem_size);
+ /* Create an invalid memory region for the "Memory out of range" test */
+ mprotect(futex_ptr + mem_size, mem_size, PROT_NONE);
+
futex_numa = futex_ptr;
ksft_print_msg("Regular test\n");
@@ -182,27 +160,31 @@ int main(int argc, char *argv[])
if (futex_numa->numa == FUTEX_NO_NODE)
ksft_exit_fail_msg("NUMA node is left uninitialized\n");
- ksft_print_msg("Memory too small\n");
- test_futex(futex_ptr + mem_size - 4, 1);
+ /* FUTEX2_NUMA futex must be 8-byte aligned */
+ ksft_print_msg("Mis-aligned futex\n");
+ test_futex(futex_ptr + mem_size - 4, EINVAL);
ksft_print_msg("Memory out of range\n");
- test_futex(futex_ptr + mem_size, 1);
+ test_futex(futex_ptr + mem_size, EFAULT);
futex_numa->numa = FUTEX_NO_NODE;
mprotect(futex_ptr, mem_size, PROT_READ);
ksft_print_msg("Memory, RO\n");
- test_futex(futex_ptr, 1);
+ test_futex(futex_ptr, EFAULT);
mprotect(futex_ptr, mem_size, PROT_NONE);
ksft_print_msg("Memory, no access\n");
- test_futex(futex_ptr, 1);
+ test_futex(futex_ptr, EFAULT);
mprotect(futex_ptr, mem_size, PROT_READ | PROT_WRITE);
ksft_print_msg("Memory back to RW\n");
test_futex(futex_ptr, 0);
+ ksft_test_result_pass("futex2 memory boundary tests passed\n");
+
/* MPOL test. Does not work as expected */
- for (i = 0; i < 4; i++) {
+#ifdef LIBNUMA_VER_SUFFICIENT
+ for (int i = 0; i < 4; i++) {
unsigned long nodemask;
int ret;
@@ -221,15 +203,17 @@ int main(int argc, char *argv[])
ret = futex2_wake(futex_ptr, 0, FUTEX2_SIZE_U32 | FUTEX_PRIVATE_FLAG | FUTEX2_NUMA | FUTEX2_MPOL);
if (ret < 0)
ksft_test_result_fail("Failed to wake 0 with MPOL: %m\n");
- if (0)
- test_futex_mpol(futex_numa, 0);
if (futex_numa->numa != i) {
ksft_exit_fail_msg("Returned NUMA node is %d expected %d\n",
futex_numa->numa, i);
}
}
}
- ksft_test_result_pass("NUMA MPOL tests passed\n");
- ksft_finished();
- return 0;
+ ksft_test_result_pass("futex2 MPOL hints test passed\n");
+#else
+ ksft_test_result_skip("futex2 MPOL hints test requires libnuma 2.0.16+\n");
+#endif
+ munmap(futex_ptr, mem_size * 2);
}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/futex/functional/futex_priv_hash.c b/tools/testing/selftests/futex/functional/futex_priv_hash.c
index aea001ac4946..3b7b5851f290 100644
--- a/tools/testing/selftests/futex/functional/futex_priv_hash.c
+++ b/tools/testing/selftests/futex/functional/futex_priv_hash.c
@@ -14,7 +14,7 @@
#include <linux/prctl.h>
#include <sys/prctl.h>
-#include "logging.h"
+#include "../../kselftest_harness.h"
#define MAX_THREADS 64
@@ -128,46 +128,14 @@ static void futex_dummy_op(void)
ksft_exit_fail_msg("pthread_mutex_timedlock() did not timeout: %d.\n", ret);
}
-static void usage(char *prog)
-{
- printf("Usage: %s\n", prog);
- printf(" -c Use color\n");
- printf(" -g Test global hash instead intead local immutable \n");
- printf(" -h Display this help message\n");
- printf(" -v L Verbosity level: %d=QUIET %d=CRITICAL %d=INFO\n",
- VQUIET, VCRITICAL, VINFO);
-}
-
static const char *test_msg_auto_create = "Automatic hash bucket init on thread creation.\n";
static const char *test_msg_auto_inc = "Automatic increase with more than 16 CPUs\n";
-int main(int argc, char *argv[])
+TEST(priv_hash)
{
int futex_slots1, futex_slotsn, online_cpus;
pthread_mutexattr_t mutex_attr_pi;
int ret, retry = 20;
- int c;
-
- while ((c = getopt(argc, argv, "chv:")) != -1) {
- switch (c) {
- case 'c':
- log_color(1);
- break;
- case 'h':
- usage(basename(argv[0]));
- exit(0);
- break;
- case 'v':
- log_verbosity(atoi(optarg));
- break;
- default:
- usage(basename(argv[0]));
- exit(1);
- }
- }
-
- ksft_print_header();
- ksft_set_plan(21);
ret = pthread_mutexattr_init(&mutex_attr_pi);
ret |= pthread_mutexattr_setprotocol(&mutex_attr_pi, PTHREAD_PRIO_INHERIT);
@@ -189,14 +157,14 @@ int main(int argc, char *argv[])
if (ret != 0)
ksft_exit_fail_msg("pthread_join() failed: %d, %m\n", ret);
- /* First thread, has to initialiaze private hash */
+ /* First thread, has to initialize private hash */
futex_slots1 = futex_hash_slots_get();
if (futex_slots1 <= 0) {
ksft_print_msg("Current hash buckets: %d\n", futex_slots1);
- ksft_exit_fail_msg(test_msg_auto_create);
+ ksft_exit_fail_msg("%s", test_msg_auto_create);
}
- ksft_test_result_pass(test_msg_auto_create);
+ ksft_test_result_pass("%s", test_msg_auto_create);
online_cpus = sysconf(_SC_NPROCESSORS_ONLN);
ret = pthread_barrier_init(&barrier_main, NULL, MAX_THREADS + 1);
@@ -237,11 +205,11 @@ retry_getslots:
}
ksft_print_msg("Expected increase of hash buckets but got: %d -> %d\n",
futex_slots1, futex_slotsn);
- ksft_exit_fail_msg(test_msg_auto_inc);
+ ksft_exit_fail_msg("%s", test_msg_auto_inc);
}
- ksft_test_result_pass(test_msg_auto_inc);
+ ksft_test_result_pass("%s", test_msg_auto_inc);
} else {
- ksft_test_result_skip(test_msg_auto_inc);
+ ksft_test_result_skip("%s", test_msg_auto_inc);
}
ret = pthread_mutex_unlock(&global_lock);
@@ -257,17 +225,17 @@ retry_getslots:
futex_hash_slots_set_verify(2);
join_max_threads();
- ksft_test_result(counter == MAX_THREADS, "Created of waited for %d of %d threads\n",
+ ksft_test_result(counter == MAX_THREADS, "Created and waited for %d of %d threads\n",
counter, MAX_THREADS);
counter = 0;
- /* Once the user set something, auto reisze must be disabled */
+ /* Once the user set something, auto resize must be disabled */
ret = pthread_barrier_init(&barrier_main, NULL, MAX_THREADS);
create_max_threads(thread_lock_fn);
join_max_threads();
ret = futex_hash_slots_get();
- ksft_test_result(ret == 2, "No more auto-resize after manaul setting, got %d\n",
+ ksft_test_result(ret == 2, "No more auto-resize after manual setting, got %d\n",
ret);
futex_hash_slots_set_must_fail(1 << 29);
@@ -280,7 +248,7 @@ retry_getslots:
ret = futex_hash_slots_set(0);
ksft_test_result(ret == 0, "Global hash request\n");
if (ret != 0)
- goto out;
+ return;
futex_hash_slots_set_must_fail(4);
futex_hash_slots_set_must_fail(8);
@@ -289,17 +257,14 @@ retry_getslots:
futex_hash_slots_set_must_fail(6);
ret = pthread_barrier_init(&barrier_main, NULL, MAX_THREADS);
- if (ret != 0) {
+ if (ret != 0)
ksft_exit_fail_msg("pthread_barrier_init failed: %m\n");
- return 1;
- }
+
create_max_threads(thread_lock_fn);
join_max_threads();
ret = futex_hash_slots_get();
ksft_test_result(ret == 0, "Continue to use global hash\n");
-
-out:
- ksft_finished();
- return 0;
}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/futex/functional/futex_requeue.c b/tools/testing/selftests/futex/functional/futex_requeue.c
index 51485be6eb2f..69e2555b6039 100644
--- a/tools/testing/selftests/futex/functional/futex_requeue.c
+++ b/tools/testing/selftests/futex/functional/futex_requeue.c
@@ -7,24 +7,15 @@
#include <pthread.h>
#include <limits.h>
-#include "logging.h"
+
#include "futextest.h"
+#include "../../kselftest_harness.h"
-#define TEST_NAME "futex-requeue"
#define timeout_ns 30000000
#define WAKE_WAIT_US 10000
volatile futex_t *f1;
-void usage(char *prog)
-{
- printf("Usage: %s\n", prog);
- printf(" -c Use color\n");
- printf(" -h Display this help message\n");
- printf(" -v L Verbosity level: %d=QUIET %d=CRITICAL %d=INFO\n",
- VQUIET, VCRITICAL, VINFO);
-}
-
void *waiterfn(void *arg)
{
struct timespec to;
@@ -38,67 +29,49 @@ void *waiterfn(void *arg)
return NULL;
}
-int main(int argc, char *argv[])
+TEST(requeue_single)
{
- pthread_t waiter[10];
- int res, ret = RET_PASS;
- int c, i;
volatile futex_t _f1 = 0;
volatile futex_t f2 = 0;
+ pthread_t waiter[10];
+ int res;
f1 = &_f1;
- while ((c = getopt(argc, argv, "cht:v:")) != -1) {
- switch (c) {
- case 'c':
- log_color(1);
- break;
- case 'h':
- usage(basename(argv[0]));
- exit(0);
- case 'v':
- log_verbosity(atoi(optarg));
- break;
- default:
- usage(basename(argv[0]));
- exit(1);
- }
- }
-
- ksft_print_header();
- ksft_set_plan(2);
- ksft_print_msg("%s: Test futex_requeue\n",
- basename(argv[0]));
-
/*
* Requeue a waiter from f1 to f2, and wake f2.
*/
if (pthread_create(&waiter[0], NULL, waiterfn, NULL))
- error("pthread_create failed\n", errno);
+ ksft_exit_fail_msg("pthread_create failed\n");
usleep(WAKE_WAIT_US);
- info("Requeuing 1 futex from f1 to f2\n");
+ ksft_print_dbg_msg("Requeuing 1 futex from f1 to f2\n");
res = futex_cmp_requeue(f1, 0, &f2, 0, 1, 0);
- if (res != 1) {
+ if (res != 1)
ksft_test_result_fail("futex_requeue simple returned: %d %s\n",
res ? errno : res,
res ? strerror(errno) : "");
- ret = RET_FAIL;
- }
-
- info("Waking 1 futex at f2\n");
+ ksft_print_dbg_msg("Waking 1 futex at f2\n");
res = futex_wake(&f2, 1, 0);
if (res != 1) {
ksft_test_result_fail("futex_requeue simple returned: %d %s\n",
res ? errno : res,
res ? strerror(errno) : "");
- ret = RET_FAIL;
} else {
ksft_test_result_pass("futex_requeue simple succeeds\n");
}
+}
+
+TEST(requeue_multiple)
+{
+ volatile futex_t _f1 = 0;
+ volatile futex_t f2 = 0;
+ pthread_t waiter[10];
+ int res, i;
+ f1 = &_f1;
/*
* Create 10 waiters at f1. At futex_requeue, wake 3 and requeue 7.
@@ -106,31 +79,28 @@ int main(int argc, char *argv[])
*/
for (i = 0; i < 10; i++) {
if (pthread_create(&waiter[i], NULL, waiterfn, NULL))
- error("pthread_create failed\n", errno);
+ ksft_exit_fail_msg("pthread_create failed\n");
}
usleep(WAKE_WAIT_US);
- info("Waking 3 futexes at f1 and requeuing 7 futexes from f1 to f2\n");
+ ksft_print_dbg_msg("Waking 3 futexes at f1 and requeuing 7 futexes from f1 to f2\n");
res = futex_cmp_requeue(f1, 0, &f2, 3, 7, 0);
if (res != 10) {
ksft_test_result_fail("futex_requeue many returned: %d %s\n",
res ? errno : res,
res ? strerror(errno) : "");
- ret = RET_FAIL;
}
- info("Waking INT_MAX futexes at f2\n");
+ ksft_print_dbg_msg("Waking INT_MAX futexes at f2\n");
res = futex_wake(&f2, INT_MAX, 0);
if (res != 7) {
ksft_test_result_fail("futex_requeue many returned: %d %s\n",
res ? errno : res,
res ? strerror(errno) : "");
- ret = RET_FAIL;
} else {
ksft_test_result_pass("futex_requeue many succeeds\n");
}
-
- ksft_print_cnts();
- return ret;
}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/futex/functional/futex_requeue_pi.c b/tools/testing/selftests/futex/functional/futex_requeue_pi.c
index 215c6cb539b4..f299d75848cd 100644
--- a/tools/testing/selftests/futex/functional/futex_requeue_pi.c
+++ b/tools/testing/selftests/futex/functional/futex_requeue_pi.c
@@ -26,11 +26,11 @@
#include <stdlib.h>
#include <signal.h>
#include <string.h>
+
#include "atomic.h"
#include "futextest.h"
-#include "logging.h"
+#include "../../kselftest_harness.h"
-#define TEST_NAME "futex-requeue-pi"
#define MAX_WAKE_ITERS 1000
#define THREAD_MAX 10
#define SIGNAL_PERIOD_US 100
@@ -42,12 +42,6 @@ futex_t f1 = FUTEX_INITIALIZER;
futex_t f2 = FUTEX_INITIALIZER;
futex_t wake_complete = FUTEX_INITIALIZER;
-/* Test option defaults */
-static long timeout_ns;
-static int broadcast;
-static int owner;
-static int locked;
-
struct thread_arg {
long id;
struct timespec *timeout;
@@ -56,18 +50,73 @@ struct thread_arg {
};
#define THREAD_ARG_INITIALIZER { 0, NULL, 0, 0 }
-void usage(char *prog)
+FIXTURE(args)
{
- printf("Usage: %s\n", prog);
- printf(" -b Broadcast wakeup (all waiters)\n");
- printf(" -c Use color\n");
- printf(" -h Display this help message\n");
- printf(" -l Lock the pi futex across requeue\n");
- printf(" -o Use a third party pi futex owner during requeue (cancels -l)\n");
- printf(" -t N Timeout in nanoseconds (default: 0)\n");
- printf(" -v L Verbosity level: %d=QUIET %d=CRITICAL %d=INFO\n",
- VQUIET, VCRITICAL, VINFO);
-}
+};
+
+FIXTURE_SETUP(args)
+{
+};
+
+FIXTURE_TEARDOWN(args)
+{
+};
+
+FIXTURE_VARIANT(args)
+{
+ long timeout_ns;
+ bool broadcast;
+ bool owner;
+ bool locked;
+};
+
+/*
+ * For a given timeout value, this macro creates a test input with all the
+ * possible combinations of valid arguments
+ */
+#define FIXTURE_VARIANT_ADD_TIMEOUT(timeout) \
+ \
+FIXTURE_VARIANT_ADD(args, t_##timeout) \
+{ \
+ .timeout_ns = timeout, \
+}; \
+ \
+FIXTURE_VARIANT_ADD(args, t_##timeout##_broadcast) \
+{ \
+ .timeout_ns = timeout, \
+ .broadcast = true, \
+}; \
+ \
+FIXTURE_VARIANT_ADD(args, t_##timeout##_broadcast_locked) \
+{ \
+ .timeout_ns = timeout, \
+ .broadcast = true, \
+ .locked = true, \
+}; \
+ \
+FIXTURE_VARIANT_ADD(args, t_##timeout##_broadcast_owner) \
+{ \
+ .timeout_ns = timeout, \
+ .broadcast = true, \
+ .owner = true, \
+}; \
+ \
+FIXTURE_VARIANT_ADD(args, t_##timeout##_locked) \
+{ \
+ .timeout_ns = timeout, \
+ .locked = true, \
+}; \
+ \
+FIXTURE_VARIANT_ADD(args, t_##timeout##_owner) \
+{ \
+ .timeout_ns = timeout, \
+ .owner = true, \
+}; \
+
+FIXTURE_VARIANT_ADD_TIMEOUT(0);
+FIXTURE_VARIANT_ADD_TIMEOUT(5000);
+FIXTURE_VARIANT_ADD_TIMEOUT(500000);
+FIXTURE_VARIANT_ADD_TIMEOUT(2000000000);
int create_rt_thread(pthread_t *pth, void*(*func)(void *), void *arg,
int policy, int prio)
@@ -81,26 +130,26 @@ int create_rt_thread(pthread_t *pth, void*(*func)(void *), void *arg,
ret = pthread_attr_setinheritsched(&attr, PTHREAD_EXPLICIT_SCHED);
if (ret) {
- error("pthread_attr_setinheritsched\n", ret);
+ ksft_exit_fail_msg("pthread_attr_setinheritsched\n");
return -1;
}
ret = pthread_attr_setschedpolicy(&attr, policy);
if (ret) {
- error("pthread_attr_setschedpolicy\n", ret);
+ ksft_exit_fail_msg("pthread_attr_setschedpolicy\n");
return -1;
}
schedp.sched_priority = prio;
ret = pthread_attr_setschedparam(&attr, &schedp);
if (ret) {
- error("pthread_attr_setschedparam\n", ret);
+ ksft_exit_fail_msg("pthread_attr_setschedparam\n");
return -1;
}
ret = pthread_create(pth, &attr, func, arg);
if (ret) {
- error("pthread_create\n", ret);
+ ksft_exit_fail_msg("pthread_create\n");
return -1;
}
return 0;
@@ -112,7 +161,7 @@ void *waiterfn(void *arg)
struct thread_arg *args = (struct thread_arg *)arg;
futex_t old_val;
- info("Waiter %ld: running\n", args->id);
+ ksft_print_dbg_msg("Waiter %ld: running\n", args->id);
/* Each thread sleeps for a different amount of time
* This is to avoid races, because we don't lock the
* external mutex here */
@@ -120,26 +169,25 @@ void *waiterfn(void *arg)
old_val = f1;
atomic_inc(&waiters_blocked);
- info("Calling futex_wait_requeue_pi: %p (%u) -> %p\n",
+ ksft_print_dbg_msg("Calling futex_wait_requeue_pi: %p (%u) -> %p\n",
&f1, f1, &f2);
args->ret = futex_wait_requeue_pi(&f1, old_val, &f2, args->timeout,
FUTEX_PRIVATE_FLAG);
- info("waiter %ld woke with %d %s\n", args->id, args->ret,
+ ksft_print_dbg_msg("waiter %ld woke with %d %s\n", args->id, args->ret,
args->ret < 0 ? strerror(errno) : "");
atomic_inc(&waiters_woken);
if (args->ret < 0) {
if (args->timeout && errno == ETIMEDOUT)
args->ret = 0;
else {
- args->ret = RET_ERROR;
- error("futex_wait_requeue_pi\n", errno);
+ ksft_exit_fail_msg("futex_wait_requeue_pi\n");
}
futex_lock_pi(&f2, NULL, 0, FUTEX_PRIVATE_FLAG);
}
futex_unlock_pi(&f2, FUTEX_PRIVATE_FLAG);
- info("Waiter %ld: exiting with %d\n", args->id, args->ret);
+ ksft_print_dbg_msg("Waiter %ld: exiting with %d\n", args->id, args->ret);
pthread_exit((void *)&args->ret);
}
@@ -152,14 +200,14 @@ void *broadcast_wakerfn(void *arg)
int nr_wake = 1;
int i = 0;
- info("Waker: waiting for waiters to block\n");
+ ksft_print_dbg_msg("Waker: waiting for waiters to block\n");
while (waiters_blocked.val < THREAD_MAX)
usleep(1000);
usleep(1000);
- info("Waker: Calling broadcast\n");
+ ksft_print_dbg_msg("Waker: Calling broadcast\n");
if (args->lock) {
- info("Calling FUTEX_LOCK_PI on mutex=%x @ %p\n", f2, &f2);
+ ksft_print_dbg_msg("Calling FUTEX_LOCK_PI on mutex=%x @ %p\n", f2, &f2);
futex_lock_pi(&f2, NULL, 0, FUTEX_PRIVATE_FLAG);
}
continue_requeue:
@@ -167,16 +215,14 @@ void *broadcast_wakerfn(void *arg)
args->ret = futex_cmp_requeue_pi(&f1, old_val, &f2, nr_wake, nr_requeue,
FUTEX_PRIVATE_FLAG);
if (args->ret < 0) {
- args->ret = RET_ERROR;
- error("FUTEX_CMP_REQUEUE_PI failed\n", errno);
+ ksft_exit_fail_msg("FUTEX_CMP_REQUEUE_PI failed\n");
} else if (++i < MAX_WAKE_ITERS) {
task_count += args->ret;
if (task_count < THREAD_MAX - waiters_woken.val)
goto continue_requeue;
} else {
- error("max broadcast iterations (%d) reached with %d/%d tasks woken or requeued\n",
- 0, MAX_WAKE_ITERS, task_count, THREAD_MAX);
- args->ret = RET_ERROR;
+ ksft_exit_fail_msg("max broadcast iterations (%d) reached with %d/%d tasks woken or requeued\n",
+ MAX_WAKE_ITERS, task_count, THREAD_MAX);
}
futex_wake(&wake_complete, 1, FUTEX_PRIVATE_FLAG);
@@ -187,7 +233,7 @@ void *broadcast_wakerfn(void *arg)
if (args->ret > 0)
args->ret = task_count;
- info("Waker: exiting with %d\n", args->ret);
+ ksft_print_dbg_msg("Waker: exiting with %d\n", args->ret);
pthread_exit((void *)&args->ret);
}
@@ -200,20 +246,20 @@ void *signal_wakerfn(void *arg)
int nr_wake = 1;
int i = 0;
- info("Waker: waiting for waiters to block\n");
+ ksft_print_dbg_msg("Waker: waiting for waiters to block\n");
while (waiters_blocked.val < THREAD_MAX)
usleep(1000);
usleep(1000);
while (task_count < THREAD_MAX && waiters_woken.val < THREAD_MAX) {
- info("task_count: %d, waiters_woken: %d\n",
+ ksft_print_dbg_msg("task_count: %d, waiters_woken: %d\n",
task_count, waiters_woken.val);
if (args->lock) {
- info("Calling FUTEX_LOCK_PI on mutex=%x @ %p\n",
- f2, &f2);
+ ksft_print_dbg_msg("Calling FUTEX_LOCK_PI on mutex=%x @ %p\n",
+ f2, &f2);
futex_lock_pi(&f2, NULL, 0, FUTEX_PRIVATE_FLAG);
}
- info("Waker: Calling signal\n");
+ ksft_print_dbg_msg("Waker: Calling signal\n");
/* cond_signal */
old_val = f1;
args->ret = futex_cmp_requeue_pi(&f1, old_val, &f2,
@@ -221,28 +267,23 @@ void *signal_wakerfn(void *arg)
FUTEX_PRIVATE_FLAG);
if (args->ret < 0)
args->ret = -errno;
- info("futex: %x\n", f2);
+ ksft_print_dbg_msg("futex: %x\n", f2);
if (args->lock) {
- info("Calling FUTEX_UNLOCK_PI on mutex=%x @ %p\n",
- f2, &f2);
+ ksft_print_dbg_msg("Calling FUTEX_UNLOCK_PI on mutex=%x @ %p\n",
+ f2, &f2);
futex_unlock_pi(&f2, FUTEX_PRIVATE_FLAG);
}
- info("futex: %x\n", f2);
- if (args->ret < 0) {
- error("FUTEX_CMP_REQUEUE_PI failed\n", errno);
- args->ret = RET_ERROR;
- break;
- }
+ ksft_print_dbg_msg("futex: %x\n", f2);
+ if (args->ret < 0)
+ ksft_exit_fail_msg("FUTEX_CMP_REQUEUE_PI failed\n");
task_count += args->ret;
usleep(SIGNAL_PERIOD_US);
i++;
/* we have to loop at least THREAD_MAX times */
if (i > MAX_WAKE_ITERS + THREAD_MAX) {
- error("max signaling iterations (%d) reached, giving up on pending waiters.\n",
- 0, MAX_WAKE_ITERS + THREAD_MAX);
- args->ret = RET_ERROR;
- break;
+ ksft_exit_fail_msg("max signaling iterations (%d) reached, giving up on pending waiters.\n",
+ MAX_WAKE_ITERS + THREAD_MAX);
}
}
@@ -251,8 +292,8 @@ void *signal_wakerfn(void *arg)
if (args->ret >= 0)
args->ret = task_count;
- info("Waker: exiting with %d\n", args->ret);
- info("Waker: waiters_woken: %d\n", waiters_woken.val);
+ ksft_print_dbg_msg("Waker: exiting with %d\n", args->ret);
+ ksft_print_dbg_msg("Waker: waiters_woken: %d\n", waiters_woken.val);
pthread_exit((void *)&args->ret);
}
@@ -269,35 +310,40 @@ void *third_party_blocker(void *arg)
ret2 = futex_unlock_pi(&f2, FUTEX_PRIVATE_FLAG);
out:
- if (args->ret || ret2) {
- error("third_party_blocker() futex error", 0);
- args->ret = RET_ERROR;
- }
+ if (args->ret || ret2)
+ ksft_exit_fail_msg("third_party_blocker() futex error");
pthread_exit((void *)&args->ret);
}
-int unit_test(int broadcast, long lock, int third_party_owner, long timeout_ns)
+TEST_F(args, futex_requeue_pi)
{
- void *(*wakerfn)(void *) = signal_wakerfn;
struct thread_arg blocker_arg = THREAD_ARG_INITIALIZER;
struct thread_arg waker_arg = THREAD_ARG_INITIALIZER;
pthread_t waiter[THREAD_MAX], waker, blocker;
- struct timespec ts, *tsp = NULL;
+ void *(*wakerfn)(void *) = signal_wakerfn;
+ bool third_party_owner = variant->owner;
+ long timeout_ns = variant->timeout_ns;
+ bool broadcast = variant->broadcast;
struct thread_arg args[THREAD_MAX];
- int *waiter_ret;
- int i, ret = RET_PASS;
+ struct timespec ts, *tsp = NULL;
+ bool lock = variant->locked;
+ int *waiter_ret, i, ret = 0;
+
+ ksft_print_msg(
+ "\tArguments: broadcast=%d locked=%d owner=%d timeout=%ldns\n",
+ broadcast, lock, third_party_owner, timeout_ns);
if (timeout_ns) {
time_t secs;
- info("timeout_ns = %ld\n", timeout_ns);
+ ksft_print_dbg_msg("timeout_ns = %ld\n", timeout_ns);
ret = clock_gettime(CLOCK_MONOTONIC, &ts);
secs = (ts.tv_nsec + timeout_ns) / 1000000000;
ts.tv_nsec = ((int64_t)ts.tv_nsec + timeout_ns) % 1000000000;
ts.tv_sec += secs;
- info("ts.tv_sec = %ld\n", ts.tv_sec);
- info("ts.tv_nsec = %ld\n", ts.tv_nsec);
+ ksft_print_dbg_msg("ts.tv_sec = %ld\n", ts.tv_sec);
+ ksft_print_dbg_msg("ts.tv_nsec = %ld\n", ts.tv_nsec);
tsp = &ts;
}
@@ -307,10 +353,7 @@ int unit_test(int broadcast, long lock, int third_party_owner, long timeout_ns)
if (third_party_owner) {
if (create_rt_thread(&blocker, third_party_blocker,
(void *)&blocker_arg, SCHED_FIFO, 1)) {
- error("Creating third party blocker thread failed\n",
- errno);
- ret = RET_ERROR;
- goto out;
+ ksft_exit_fail_msg("Creating third party blocker thread failed\n");
}
}
@@ -318,20 +361,16 @@ int unit_test(int broadcast, long lock, int third_party_owner, long timeout_ns)
for (i = 0; i < THREAD_MAX; i++) {
args[i].id = i;
args[i].timeout = tsp;
- info("Starting thread %d\n", i);
+ ksft_print_dbg_msg("Starting thread %d\n", i);
if (create_rt_thread(&waiter[i], waiterfn, (void *)&args[i],
SCHED_FIFO, 1)) {
- error("Creating waiting thread failed\n", errno);
- ret = RET_ERROR;
- goto out;
+ ksft_exit_fail_msg("Creating waiting thread failed\n");
}
}
waker_arg.lock = lock;
if (create_rt_thread(&waker, wakerfn, (void *)&waker_arg,
SCHED_FIFO, 1)) {
- error("Creating waker thread failed\n", errno);
- ret = RET_ERROR;
- goto out;
+ ksft_exit_fail_msg("Creating waker thread failed\n");
}
/* Wait for threads to finish */
@@ -345,7 +384,6 @@ int unit_test(int broadcast, long lock, int third_party_owner, long timeout_ns)
pthread_join(blocker, NULL);
pthread_join(waker, NULL);
-out:
if (!ret) {
if (*waiter_ret)
ret = *waiter_ret;
@@ -355,66 +393,8 @@ out:
ret = blocker_arg.ret;
}
- return ret;
+ if (ret)
+ ksft_test_result_fail("fail");
}
-int main(int argc, char *argv[])
-{
- char *test_name;
- int c, ret;
-
- while ((c = getopt(argc, argv, "bchlot:v:")) != -1) {
- switch (c) {
- case 'b':
- broadcast = 1;
- break;
- case 'c':
- log_color(1);
- break;
- case 'h':
- usage(basename(argv[0]));
- exit(0);
- case 'l':
- locked = 1;
- break;
- case 'o':
- owner = 1;
- locked = 0;
- break;
- case 't':
- timeout_ns = atoi(optarg);
- break;
- case 'v':
- log_verbosity(atoi(optarg));
- break;
- default:
- usage(basename(argv[0]));
- exit(1);
- }
- }
-
- ksft_print_header();
- ksft_set_plan(1);
- ksft_print_msg("%s: Test requeue functionality\n", basename(argv[0]));
- ksft_print_msg(
- "\tArguments: broadcast=%d locked=%d owner=%d timeout=%ldns\n",
- broadcast, locked, owner, timeout_ns);
-
- ret = asprintf(&test_name,
- "%s broadcast=%d locked=%d owner=%d timeout=%ldns",
- TEST_NAME, broadcast, locked, owner, timeout_ns);
- if (ret < 0) {
- ksft_print_msg("Failed to generate test name\n");
- test_name = TEST_NAME;
- }
-
- /*
- * FIXME: unit_test is obsolete now that we parse options and the
- * various style of runs are done by run.sh - simplify the code and move
- * unit_test into main()
- */
- ret = unit_test(broadcast, locked, owner, timeout_ns);
-
- print_result(test_name, ret);
- return ret;
-}
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/futex/functional/futex_requeue_pi_mismatched_ops.c b/tools/testing/selftests/futex/functional/futex_requeue_pi_mismatched_ops.c
index d0a4d332ea44..77135a22a583 100644
--- a/tools/testing/selftests/futex/functional/futex_requeue_pi_mismatched_ops.c
+++ b/tools/testing/selftests/futex/functional/futex_requeue_pi_mismatched_ops.c
@@ -23,67 +23,32 @@
#include <stdlib.h>
#include <string.h>
#include <time.h>
-#include "futextest.h"
-#include "logging.h"
-#define TEST_NAME "futex-requeue-pi-mismatched-ops"
+#include "futextest.h"
+#include "../../kselftest_harness.h"
futex_t f1 = FUTEX_INITIALIZER;
futex_t f2 = FUTEX_INITIALIZER;
int child_ret = 0;
-void usage(char *prog)
-{
- printf("Usage: %s\n", prog);
- printf(" -c Use color\n");
- printf(" -h Display this help message\n");
- printf(" -v L Verbosity level: %d=QUIET %d=CRITICAL %d=INFO\n",
- VQUIET, VCRITICAL, VINFO);
-}
-
void *blocking_child(void *arg)
{
child_ret = futex_wait(&f1, f1, NULL, FUTEX_PRIVATE_FLAG);
if (child_ret < 0) {
child_ret = -errno;
- error("futex_wait\n", errno);
+ ksft_exit_fail_msg("futex_wait\n");
}
return (void *)&child_ret;
}
-int main(int argc, char *argv[])
+TEST(requeue_pi_mismatched_ops)
{
- int ret = RET_PASS;
pthread_t child;
- int c;
+ int ret;
- while ((c = getopt(argc, argv, "chv:")) != -1) {
- switch (c) {
- case 'c':
- log_color(1);
- break;
- case 'h':
- usage(basename(argv[0]));
- exit(0);
- case 'v':
- log_verbosity(atoi(optarg));
- break;
- default:
- usage(basename(argv[0]));
- exit(1);
- }
- }
-
- ksft_print_header();
- ksft_set_plan(1);
- ksft_print_msg("%s: Detect mismatched requeue_pi operations\n",
- basename(argv[0]));
+ if (pthread_create(&child, NULL, blocking_child, NULL))
+ ksft_exit_fail_msg("pthread_create\n");
- if (pthread_create(&child, NULL, blocking_child, NULL)) {
- error("pthread_create\n", errno);
- ret = RET_ERROR;
- goto out;
- }
/* Allow the child to block in the kernel. */
sleep(1);
@@ -102,34 +67,27 @@ int main(int argc, char *argv[])
* FUTEX_WAKE.
*/
ret = futex_wake(&f1, 1, FUTEX_PRIVATE_FLAG);
- if (ret == 1) {
- ret = RET_PASS;
- } else if (ret < 0) {
- error("futex_wake\n", errno);
- ret = RET_ERROR;
- } else {
- error("futex_wake did not wake the child\n", 0);
- ret = RET_ERROR;
- }
+ if (ret == 1)
+ ret = 0;
+ else if (ret < 0)
+ ksft_exit_fail_msg("futex_wake\n");
+ else
+ ksft_exit_fail_msg("futex_wake did not wake the child\n");
} else {
- error("futex_cmp_requeue_pi\n", errno);
- ret = RET_ERROR;
+ ksft_exit_fail_msg("futex_cmp_requeue_pi\n");
}
} else if (ret > 0) {
- fail("futex_cmp_requeue_pi failed to detect the mismatch\n");
- ret = RET_FAIL;
+ ksft_test_result_fail("futex_cmp_requeue_pi failed to detect the mismatch\n");
} else {
- error("futex_cmp_requeue_pi found no waiters\n", 0);
- ret = RET_ERROR;
+ ksft_exit_fail_msg("futex_cmp_requeue_pi found no waiters\n");
}
pthread_join(child, NULL);
- if (!ret)
- ret = child_ret;
-
- out:
- /* If the kernel crashes, we shouldn't return at all. */
- print_result(TEST_NAME, ret);
- return ret;
+ if (!ret && !child_ret)
+ ksft_test_result_pass("futex_requeue_pi_mismatched_ops passed\n");
+ else
+ ksft_test_result_pass("futex_requeue_pi_mismatched_ops failed\n");
}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/futex/functional/futex_requeue_pi_signal_restart.c b/tools/testing/selftests/futex/functional/futex_requeue_pi_signal_restart.c
index c6b8f32990c8..e34ee0f9ebcc 100644
--- a/tools/testing/selftests/futex/functional/futex_requeue_pi_signal_restart.c
+++ b/tools/testing/selftests/futex/functional/futex_requeue_pi_signal_restart.c
@@ -24,11 +24,11 @@
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
+
#include "atomic.h"
#include "futextest.h"
-#include "logging.h"
+#include "../../kselftest_harness.h"
-#define TEST_NAME "futex-requeue-pi-signal-restart"
#define DELAY_US 100
futex_t f1 = FUTEX_INITIALIZER;
@@ -37,15 +37,6 @@ atomic_t requeued = ATOMIC_INITIALIZER;
int waiter_ret = 0;
-void usage(char *prog)
-{
- printf("Usage: %s\n", prog);
- printf(" -c Use color\n");
- printf(" -h Display this help message\n");
- printf(" -v L Verbosity level: %d=QUIET %d=CRITICAL %d=INFO\n",
- VQUIET, VCRITICAL, VINFO);
-}
-
int create_rt_thread(pthread_t *pth, void*(*func)(void *), void *arg,
int policy, int prio)
{
@@ -57,35 +48,28 @@ int create_rt_thread(pthread_t *pth, void*(*func)(void *), void *arg,
memset(&schedp, 0, sizeof(schedp));
ret = pthread_attr_setinheritsched(&attr, PTHREAD_EXPLICIT_SCHED);
- if (ret) {
- error("pthread_attr_setinheritsched\n", ret);
- return -1;
- }
+ if (ret)
+ ksft_exit_fail_msg("pthread_attr_setinheritsched\n");
ret = pthread_attr_setschedpolicy(&attr, policy);
- if (ret) {
- error("pthread_attr_setschedpolicy\n", ret);
- return -1;
- }
+ if (ret)
+ ksft_exit_fail_msg("pthread_attr_setschedpolicy\n");
schedp.sched_priority = prio;
ret = pthread_attr_setschedparam(&attr, &schedp);
- if (ret) {
- error("pthread_attr_setschedparam\n", ret);
- return -1;
- }
+ if (ret)
+ ksft_exit_fail_msg("pthread_attr_setschedparam\n");
ret = pthread_create(pth, &attr, func, arg);
- if (ret) {
- error("pthread_create\n", ret);
- return -1;
- }
+ if (ret)
+ ksft_exit_fail_msg("pthread_create\n");
+
return 0;
}
void handle_signal(int signo)
{
- info("signal received %s requeue\n",
+ ksft_print_dbg_msg("signal received %s requeue\n",
requeued.val ? "after" : "prior to");
}
@@ -94,78 +78,46 @@ void *waiterfn(void *arg)
unsigned int old_val;
int res;
- waiter_ret = RET_PASS;
-
- info("Waiter running\n");
- info("Calling FUTEX_LOCK_PI on f2=%x @ %p\n", f2, &f2);
+ ksft_print_dbg_msg("Waiter running\n");
+ ksft_print_dbg_msg("Calling FUTEX_LOCK_PI on f2=%x @ %p\n", f2, &f2);
old_val = f1;
res = futex_wait_requeue_pi(&f1, old_val, &(f2), NULL,
FUTEX_PRIVATE_FLAG);
if (!requeued.val || errno != EWOULDBLOCK) {
- fail("unexpected return from futex_wait_requeue_pi: %d (%s)\n",
+ ksft_test_result_fail("unexpected return from futex_wait_requeue_pi: %d (%s)\n",
res, strerror(errno));
- info("w2:futex: %x\n", f2);
+ ksft_print_dbg_msg("w2:futex: %x\n", f2);
if (!res)
futex_unlock_pi(&f2, FUTEX_PRIVATE_FLAG);
- waiter_ret = RET_FAIL;
}
- info("Waiter exiting with %d\n", waiter_ret);
pthread_exit(NULL);
}
-int main(int argc, char *argv[])
+TEST(futex_requeue_pi_signal_restart)
{
unsigned int old_val;
struct sigaction sa;
pthread_t waiter;
- int c, res, ret = RET_PASS;
-
- while ((c = getopt(argc, argv, "chv:")) != -1) {
- switch (c) {
- case 'c':
- log_color(1);
- break;
- case 'h':
- usage(basename(argv[0]));
- exit(0);
- case 'v':
- log_verbosity(atoi(optarg));
- break;
- default:
- usage(basename(argv[0]));
- exit(1);
- }
- }
-
- ksft_print_header();
- ksft_set_plan(1);
- ksft_print_msg("%s: Test signal handling during requeue_pi\n",
- basename(argv[0]));
- ksft_print_msg("\tArguments: <none>\n");
+ int res;
sa.sa_handler = handle_signal;
sigemptyset(&sa.sa_mask);
sa.sa_flags = 0;
- if (sigaction(SIGUSR1, &sa, NULL)) {
- error("sigaction\n", errno);
- exit(1);
- }
+ if (sigaction(SIGUSR1, &sa, NULL))
+ ksft_exit_fail_msg("sigaction\n");
- info("m1:f2: %x\n", f2);
- info("Creating waiter\n");
+ ksft_print_dbg_msg("m1:f2: %x\n", f2);
+ ksft_print_dbg_msg("Creating waiter\n");
res = create_rt_thread(&waiter, waiterfn, NULL, SCHED_FIFO, 1);
- if (res) {
- error("Creating waiting thread failed", res);
- ret = RET_ERROR;
- goto out;
- }
+ if (res)
+ ksft_exit_fail_msg("Creating waiting thread failed");
- info("Calling FUTEX_LOCK_PI on f2=%x @ %p\n", f2, &f2);
- info("m2:f2: %x\n", f2);
+ ksft_print_dbg_msg("Calling FUTEX_LOCK_PI on f2=%x @ %p\n", f2, &f2);
+ ksft_print_dbg_msg("m2:f2: %x\n", f2);
futex_lock_pi(&f2, 0, 0, FUTEX_PRIVATE_FLAG);
- info("m3:f2: %x\n", f2);
+ ksft_print_dbg_msg("m3:f2: %x\n", f2);
while (1) {
/*
@@ -173,11 +125,11 @@ int main(int argc, char *argv[])
* restart futex_wait_requeue_pi() in the kernel. Wait for the
* waiter to block on f1 again.
*/
- info("Issuing SIGUSR1 to waiter\n");
+ ksft_print_dbg_msg("Issuing SIGUSR1 to waiter\n");
pthread_kill(waiter, SIGUSR1);
usleep(DELAY_US);
- info("Requeueing waiter via FUTEX_CMP_REQUEUE_PI\n");
+ ksft_print_dbg_msg("Requeueing waiter via FUTEX_CMP_REQUEUE_PI\n");
old_val = f1;
res = futex_cmp_requeue_pi(&f1, old_val, &(f2), 1, 0,
FUTEX_PRIVATE_FLAG);
@@ -191,12 +143,10 @@ int main(int argc, char *argv[])
atomic_set(&requeued, 1);
break;
} else if (res < 0) {
- error("FUTEX_CMP_REQUEUE_PI failed\n", errno);
- ret = RET_ERROR;
- break;
+ ksft_exit_fail_msg("FUTEX_CMP_REQUEUE_PI failed\n");
}
}
- info("m4:f2: %x\n", f2);
+ ksft_print_dbg_msg("m4:f2: %x\n", f2);
/*
* Signal the waiter after requeue, waiter should return from
@@ -204,19 +154,14 @@ int main(int argc, char *argv[])
* futex_unlock_pi() can't happen before the signal wakeup is detected
* in the kernel.
*/
- info("Issuing SIGUSR1 to waiter\n");
+ ksft_print_dbg_msg("Issuing SIGUSR1 to waiter\n");
pthread_kill(waiter, SIGUSR1);
- info("Waiting for waiter to return\n");
+ ksft_print_dbg_msg("Waiting for waiter to return\n");
pthread_join(waiter, NULL);
- info("Calling FUTEX_UNLOCK_PI on mutex=%x @ %p\n", f2, &f2);
+ ksft_print_dbg_msg("Calling FUTEX_UNLOCK_PI on mutex=%x @ %p\n", f2, &f2);
futex_unlock_pi(&f2, FUTEX_PRIVATE_FLAG);
- info("m5:f2: %x\n", f2);
-
- out:
- if (ret == RET_PASS && waiter_ret)
- ret = waiter_ret;
-
- print_result(TEST_NAME, ret);
- return ret;
+ ksft_print_dbg_msg("m5:f2: %x\n", f2);
}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/futex/functional/futex_wait.c b/tools/testing/selftests/futex/functional/futex_wait.c
index 685140d9b93d..152ca4612886 100644
--- a/tools/testing/selftests/futex/functional/futex_wait.c
+++ b/tools/testing/selftests/futex/functional/futex_wait.c
@@ -9,25 +9,16 @@
#include <sys/shm.h>
#include <sys/mman.h>
#include <fcntl.h>
-#include "logging.h"
+
#include "futextest.h"
+#include "../../kselftest_harness.h"
-#define TEST_NAME "futex-wait"
#define timeout_ns 30000000
#define WAKE_WAIT_US 10000
#define SHM_PATH "futex_shm_file"
void *futex;
-void usage(char *prog)
-{
- printf("Usage: %s\n", prog);
- printf(" -c Use color\n");
- printf(" -h Display this help message\n");
- printf(" -v L Verbosity level: %d=QUIET %d=CRITICAL %d=INFO\n",
- VQUIET, VCRITICAL, VINFO);
-}
-
static void *waiterfn(void *arg)
{
struct timespec to;
@@ -45,53 +36,37 @@ static void *waiterfn(void *arg)
return NULL;
}
-int main(int argc, char *argv[])
+TEST(private_futex)
{
- int res, ret = RET_PASS, fd, c, shm_id;
- u_int32_t f_private = 0, *shared_data;
unsigned int flags = FUTEX_PRIVATE_FLAG;
+ u_int32_t f_private = 0;
pthread_t waiter;
- void *shm;
+ int res;
futex = &f_private;
- while ((c = getopt(argc, argv, "cht:v:")) != -1) {
- switch (c) {
- case 'c':
- log_color(1);
- break;
- case 'h':
- usage(basename(argv[0]));
- exit(0);
- case 'v':
- log_verbosity(atoi(optarg));
- break;
- default:
- usage(basename(argv[0]));
- exit(1);
- }
- }
-
- ksft_print_header();
- ksft_set_plan(3);
- ksft_print_msg("%s: Test futex_wait\n", basename(argv[0]));
-
/* Testing a private futex */
- info("Calling private futex_wait on futex: %p\n", futex);
+ ksft_print_dbg_msg("Calling private futex_wait on futex: %p\n", futex);
if (pthread_create(&waiter, NULL, waiterfn, (void *) &flags))
- error("pthread_create failed\n", errno);
+ ksft_exit_fail_msg("pthread_create failed\n");
usleep(WAKE_WAIT_US);
- info("Calling private futex_wake on futex: %p\n", futex);
+ ksft_print_dbg_msg("Calling private futex_wake on futex: %p\n", futex);
res = futex_wake(futex, 1, FUTEX_PRIVATE_FLAG);
if (res != 1) {
ksft_test_result_fail("futex_wake private returned: %d %s\n",
errno, strerror(errno));
- ret = RET_FAIL;
} else {
ksft_test_result_pass("futex_wake private succeeds\n");
}
+}
+
+TEST(anon_page)
+{
+ u_int32_t *shared_data;
+ pthread_t waiter;
+ int res, shm_id;
/* Testing an anon page shared memory */
shm_id = shmget(IPC_PRIVATE, 4096, IPC_CREAT | 0666);
@@ -105,67 +80,65 @@ int main(int argc, char *argv[])
*shared_data = 0;
futex = shared_data;
- info("Calling shared (page anon) futex_wait on futex: %p\n", futex);
+ ksft_print_dbg_msg("Calling shared (page anon) futex_wait on futex: %p\n", futex);
if (pthread_create(&waiter, NULL, waiterfn, NULL))
- error("pthread_create failed\n", errno);
+ ksft_exit_fail_msg("pthread_create failed\n");
usleep(WAKE_WAIT_US);
- info("Calling shared (page anon) futex_wake on futex: %p\n", futex);
+ ksft_print_dbg_msg("Calling shared (page anon) futex_wake on futex: %p\n", futex);
res = futex_wake(futex, 1, 0);
if (res != 1) {
ksft_test_result_fail("futex_wake shared (page anon) returned: %d %s\n",
errno, strerror(errno));
- ret = RET_FAIL;
} else {
ksft_test_result_pass("futex_wake shared (page anon) succeeds\n");
}
+ shmdt(shared_data);
+}
+
+TEST(file_backed)
+{
+ u_int32_t f_private = 0;
+ pthread_t waiter;
+ int res, fd;
+ void *shm;
/* Testing a file backed shared memory */
fd = open(SHM_PATH, O_RDWR | O_CREAT, S_IRUSR | S_IWUSR);
- if (fd < 0) {
- perror("open");
- exit(1);
- }
+ if (fd < 0)
+ ksft_exit_fail_msg("open");
- if (ftruncate(fd, sizeof(f_private))) {
- perror("ftruncate");
- exit(1);
- }
+ if (ftruncate(fd, sizeof(f_private)))
+ ksft_exit_fail_msg("ftruncate");
shm = mmap(NULL, sizeof(f_private), PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0);
- if (shm == MAP_FAILED) {
- perror("mmap");
- exit(1);
- }
+ if (shm == MAP_FAILED)
+ ksft_exit_fail_msg("mmap");
memcpy(shm, &f_private, sizeof(f_private));
futex = shm;
- info("Calling shared (file backed) futex_wait on futex: %p\n", futex);
+ ksft_print_dbg_msg("Calling shared (file backed) futex_wait on futex: %p\n", futex);
if (pthread_create(&waiter, NULL, waiterfn, NULL))
- error("pthread_create failed\n", errno);
+ ksft_exit_fail_msg("pthread_create failed\n");
usleep(WAKE_WAIT_US);
- info("Calling shared (file backed) futex_wake on futex: %p\n", futex);
+ ksft_print_dbg_msg("Calling shared (file backed) futex_wake on futex: %p\n", futex);
res = futex_wake(shm, 1, 0);
if (res != 1) {
ksft_test_result_fail("futex_wake shared (file backed) returned: %d %s\n",
errno, strerror(errno));
- ret = RET_FAIL;
} else {
ksft_test_result_pass("futex_wake shared (file backed) succeeds\n");
}
- /* Freeing resources */
- shmdt(shared_data);
munmap(shm, sizeof(f_private));
remove(SHM_PATH);
close(fd);
-
- ksft_print_cnts();
- return ret;
}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/futex/functional/futex_wait_private_mapped_file.c b/tools/testing/selftests/futex/functional/futex_wait_private_mapped_file.c
index fb4148f23fa3..8952ebda14ab 100644
--- a/tools/testing/selftests/futex/functional/futex_wait_private_mapped_file.c
+++ b/tools/testing/selftests/futex/functional/futex_wait_private_mapped_file.c
@@ -27,10 +27,9 @@
#include <libgen.h>
#include <signal.h>
-#include "logging.h"
#include "futextest.h"
+#include "../../kselftest_harness.h"
-#define TEST_NAME "futex-wait-private-mapped-file"
#define PAGE_SZ 4096
char pad[PAGE_SZ] = {1};
@@ -40,86 +39,44 @@ char pad2[PAGE_SZ] = {1};
#define WAKE_WAIT_US 3000000
struct timespec wait_timeout = { .tv_sec = 5, .tv_nsec = 0};
-void usage(char *prog)
-{
- printf("Usage: %s\n", prog);
- printf(" -c Use color\n");
- printf(" -h Display this help message\n");
- printf(" -v L Verbosity level: %d=QUIET %d=CRITICAL %d=INFO\n",
- VQUIET, VCRITICAL, VINFO);
-}
-
void *thr_futex_wait(void *arg)
{
int ret;
- info("futex wait\n");
+ ksft_print_dbg_msg("futex wait\n");
ret = futex_wait(&val, 1, &wait_timeout, 0);
- if (ret && errno != EWOULDBLOCK && errno != ETIMEDOUT) {
- error("futex error.\n", errno);
- print_result(TEST_NAME, RET_ERROR);
- exit(RET_ERROR);
- }
+ if (ret && errno != EWOULDBLOCK && errno != ETIMEDOUT)
+ ksft_exit_fail_msg("futex error.\n");
if (ret && errno == ETIMEDOUT)
- fail("waiter timedout\n");
+ ksft_exit_fail_msg("waiter timedout\n");
- info("futex_wait: ret = %d, errno = %d\n", ret, errno);
+ ksft_print_dbg_msg("futex_wait: ret = %d, errno = %d\n", ret, errno);
return NULL;
}
-int main(int argc, char **argv)
+TEST(wait_private_mapped_file)
{
pthread_t thr;
- int ret = RET_PASS;
int res;
- int c;
-
- while ((c = getopt(argc, argv, "chv:")) != -1) {
- switch (c) {
- case 'c':
- log_color(1);
- break;
- case 'h':
- usage(basename(argv[0]));
- exit(0);
- case 'v':
- log_verbosity(atoi(optarg));
- break;
- default:
- usage(basename(argv[0]));
- exit(1);
- }
- }
-
- ksft_print_header();
- ksft_set_plan(1);
- ksft_print_msg(
- "%s: Test the futex value of private file mappings in FUTEX_WAIT\n",
- basename(argv[0]));
-
- ret = pthread_create(&thr, NULL, thr_futex_wait, NULL);
- if (ret < 0) {
- fprintf(stderr, "pthread_create error\n");
- ret = RET_ERROR;
- goto out;
- }
-
- info("wait a while\n");
+
+ res = pthread_create(&thr, NULL, thr_futex_wait, NULL);
+ if (res < 0)
+ ksft_exit_fail_msg("pthread_create error\n");
+
+ ksft_print_dbg_msg("wait a while\n");
usleep(WAKE_WAIT_US);
val = 2;
res = futex_wake(&val, 1, 0);
- info("futex_wake %d\n", res);
- if (res != 1) {
- fail("FUTEX_WAKE didn't find the waiting thread.\n");
- ret = RET_FAIL;
- }
+ ksft_print_dbg_msg("futex_wake %d\n", res);
+ if (res != 1)
+ ksft_exit_fail_msg("FUTEX_WAKE didn't find the waiting thread.\n");
- info("join\n");
+ ksft_print_dbg_msg("join\n");
pthread_join(thr, NULL);
- out:
- print_result(TEST_NAME, ret);
- return ret;
+ ksft_test_result_pass("wait_private_mapped_file");
}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/futex/functional/futex_wait_timeout.c b/tools/testing/selftests/futex/functional/futex_wait_timeout.c
index d183f878360b..0c8766aced2e 100644
--- a/tools/testing/selftests/futex/functional/futex_wait_timeout.c
+++ b/tools/testing/selftests/futex/functional/futex_wait_timeout.c
@@ -16,26 +16,15 @@
*****************************************************************************/
#include <pthread.h>
+
#include "futextest.h"
#include "futex2test.h"
-#include "logging.h"
-
-#define TEST_NAME "futex-wait-timeout"
+#include "../../kselftest_harness.h"
static long timeout_ns = 100000; /* 100us default timeout */
static futex_t futex_pi;
static pthread_barrier_t barrier;
-void usage(char *prog)
-{
- printf("Usage: %s\n", prog);
- printf(" -c Use color\n");
- printf(" -h Display this help message\n");
- printf(" -t N Timeout in nanoseconds (default: 100,000)\n");
- printf(" -v L Verbosity level: %d=QUIET %d=CRITICAL %d=INFO\n",
- VQUIET, VCRITICAL, VINFO);
-}
-
/*
* Get a PI lock and hold it forever, so the main thread lock_pi will block
* and we can test the timeout
@@ -47,13 +36,13 @@ void *get_pi_lock(void *arg)
ret = futex_lock_pi(&futex_pi, NULL, 0, 0);
if (ret != 0)
- error("futex_lock_pi failed\n", ret);
+ ksft_exit_fail_msg("futex_lock_pi failed\n");
pthread_barrier_wait(&barrier);
/* Blocks forever */
ret = futex_wait(&lock, 0, NULL, 0);
- error("futex_wait failed\n", ret);
+ ksft_exit_fail_msg("futex_wait failed\n");
return NULL;
}
@@ -61,12 +50,11 @@ void *get_pi_lock(void *arg)
/*
* Check if the function returned the expected error
*/
-static void test_timeout(int res, int *ret, char *test_name, int err)
+static void test_timeout(int res, char *test_name, int err)
{
if (!res || errno != err) {
ksft_test_result_fail("%s returned %d\n", test_name,
res < 0 ? errno : res);
- *ret = RET_FAIL;
} else {
ksft_test_result_pass("%s succeeds\n", test_name);
}
@@ -78,10 +66,8 @@ static void test_timeout(int res, int *ret, char *test_name, int err)
static int futex_get_abs_timeout(clockid_t clockid, struct timespec *to,
long timeout_ns)
{
- if (clock_gettime(clockid, to)) {
- error("clock_gettime failed\n", errno);
- return errno;
- }
+ if (clock_gettime(clockid, to))
+ ksft_exit_fail_msg("clock_gettime failed\n");
to->tv_nsec += timeout_ns;
@@ -93,83 +79,66 @@ static int futex_get_abs_timeout(clockid_t clockid, struct timespec *to,
return 0;
}
-int main(int argc, char *argv[])
+TEST(wait_bitset)
{
futex_t f1 = FUTEX_INITIALIZER;
- int res, ret = RET_PASS;
struct timespec to;
- pthread_t thread;
- int c;
- struct futex_waitv waitv = {
- .uaddr = (uintptr_t)&f1,
- .val = f1,
- .flags = FUTEX_32,
- .__reserved = 0
- };
-
- while ((c = getopt(argc, argv, "cht:v:")) != -1) {
- switch (c) {
- case 'c':
- log_color(1);
- break;
- case 'h':
- usage(basename(argv[0]));
- exit(0);
- case 't':
- timeout_ns = atoi(optarg);
- break;
- case 'v':
- log_verbosity(atoi(optarg));
- break;
- default:
- usage(basename(argv[0]));
- exit(1);
- }
- }
-
- ksft_print_header();
- ksft_set_plan(9);
- ksft_print_msg("%s: Block on a futex and wait for timeout\n",
- basename(argv[0]));
- ksft_print_msg("\tArguments: timeout=%ldns\n", timeout_ns);
-
- pthread_barrier_init(&barrier, NULL, 2);
- pthread_create(&thread, NULL, get_pi_lock, NULL);
+ int res;
/* initialize relative timeout */
to.tv_sec = 0;
to.tv_nsec = timeout_ns;
res = futex_wait(&f1, f1, &to, 0);
- test_timeout(res, &ret, "futex_wait relative", ETIMEDOUT);
+ test_timeout(res, "futex_wait relative", ETIMEDOUT);
/* FUTEX_WAIT_BITSET with CLOCK_REALTIME */
if (futex_get_abs_timeout(CLOCK_REALTIME, &to, timeout_ns))
- return RET_FAIL;
+ ksft_test_result_error("get_time error");
res = futex_wait_bitset(&f1, f1, &to, 1, FUTEX_CLOCK_REALTIME);
- test_timeout(res, &ret, "futex_wait_bitset realtime", ETIMEDOUT);
+ test_timeout(res, "futex_wait_bitset realtime", ETIMEDOUT);
/* FUTEX_WAIT_BITSET with CLOCK_MONOTONIC */
if (futex_get_abs_timeout(CLOCK_MONOTONIC, &to, timeout_ns))
- return RET_FAIL;
+ ksft_test_result_error("get_time error");
res = futex_wait_bitset(&f1, f1, &to, 1, 0);
- test_timeout(res, &ret, "futex_wait_bitset monotonic", ETIMEDOUT);
+ test_timeout(res, "futex_wait_bitset monotonic", ETIMEDOUT);
+}
+
+TEST(requeue_pi)
+{
+ futex_t f1 = FUTEX_INITIALIZER;
+ struct timespec to;
+ int res;
/* FUTEX_WAIT_REQUEUE_PI with CLOCK_REALTIME */
if (futex_get_abs_timeout(CLOCK_REALTIME, &to, timeout_ns))
- return RET_FAIL;
+ ksft_test_result_error("get_time error");
res = futex_wait_requeue_pi(&f1, f1, &futex_pi, &to, FUTEX_CLOCK_REALTIME);
- test_timeout(res, &ret, "futex_wait_requeue_pi realtime", ETIMEDOUT);
+ test_timeout(res, "futex_wait_requeue_pi realtime", ETIMEDOUT);
/* FUTEX_WAIT_REQUEUE_PI with CLOCK_MONOTONIC */
if (futex_get_abs_timeout(CLOCK_MONOTONIC, &to, timeout_ns))
- return RET_FAIL;
+ ksft_test_result_error("get_time error");
res = futex_wait_requeue_pi(&f1, f1, &futex_pi, &to, 0);
- test_timeout(res, &ret, "futex_wait_requeue_pi monotonic", ETIMEDOUT);
+ test_timeout(res, "futex_wait_requeue_pi monotonic", ETIMEDOUT);
+
+}
+
+TEST(lock_pi)
+{
+ struct timespec to;
+ pthread_t thread;
+ int res;
+
+ /* Create a thread that will lock forever so any waiter will timeout */
+ pthread_barrier_init(&barrier, NULL, 2);
+ pthread_create(&thread, NULL, get_pi_lock, NULL);
/* Wait until the other thread calls futex_lock_pi() */
pthread_barrier_wait(&barrier);
pthread_barrier_destroy(&barrier);
+
/*
* FUTEX_LOCK_PI with CLOCK_REALTIME
* Due to historical reasons, FUTEX_LOCK_PI supports only realtime
@@ -181,26 +150,38 @@ int main(int argc, char *argv[])
* smaller than realtime and the syscall will timeout immediately.
*/
if (futex_get_abs_timeout(CLOCK_REALTIME, &to, timeout_ns))
- return RET_FAIL;
+ ksft_test_result_error("get_time error");
res = futex_lock_pi(&futex_pi, &to, 0, 0);
- test_timeout(res, &ret, "futex_lock_pi realtime", ETIMEDOUT);
+ test_timeout(res, "futex_lock_pi realtime", ETIMEDOUT);
/* Test operations that don't support FUTEX_CLOCK_REALTIME */
res = futex_lock_pi(&futex_pi, NULL, 0, FUTEX_CLOCK_REALTIME);
- test_timeout(res, &ret, "futex_lock_pi invalid timeout flag", ENOSYS);
+ test_timeout(res, "futex_lock_pi invalid timeout flag", ENOSYS);
+}
+
+TEST(waitv)
+{
+ futex_t f1 = FUTEX_INITIALIZER;
+ struct futex_waitv waitv = {
+ .uaddr = (uintptr_t)&f1,
+ .val = f1,
+ .flags = FUTEX_32,
+ .__reserved = 0,
+ };
+ struct timespec to;
+ int res;
/* futex_waitv with CLOCK_MONOTONIC */
if (futex_get_abs_timeout(CLOCK_MONOTONIC, &to, timeout_ns))
- return RET_FAIL;
+ ksft_test_result_error("get_time error");
res = futex_waitv(&waitv, 1, 0, &to, CLOCK_MONOTONIC);
- test_timeout(res, &ret, "futex_waitv monotonic", ETIMEDOUT);
+ test_timeout(res, "futex_waitv monotonic", ETIMEDOUT);
/* futex_waitv with CLOCK_REALTIME */
if (futex_get_abs_timeout(CLOCK_REALTIME, &to, timeout_ns))
- return RET_FAIL;
+ ksft_test_result_error("get_time error");
res = futex_waitv(&waitv, 1, 0, &to, CLOCK_REALTIME);
- test_timeout(res, &ret, "futex_waitv realtime", ETIMEDOUT);
-
- ksft_print_cnts();
- return ret;
+ test_timeout(res, "futex_waitv realtime", ETIMEDOUT);
}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/futex/functional/futex_wait_uninitialized_heap.c b/tools/testing/selftests/futex/functional/futex_wait_uninitialized_heap.c
index ed9cd07e31c1..ce2301500d83 100644
--- a/tools/testing/selftests/futex/functional/futex_wait_uninitialized_heap.c
+++ b/tools/testing/selftests/futex/functional/futex_wait_uninitialized_heap.c
@@ -29,95 +29,55 @@
#include <linux/futex.h>
#include <libgen.h>
-#include "logging.h"
#include "futextest.h"
+#include "../../kselftest_harness.h"
-#define TEST_NAME "futex-wait-uninitialized-heap"
#define WAIT_US 5000000
static int child_blocked = 1;
-static int child_ret;
+static bool child_ret;
void *buf;
-void usage(char *prog)
-{
- printf("Usage: %s\n", prog);
- printf(" -c Use color\n");
- printf(" -h Display this help message\n");
- printf(" -v L Verbosity level: %d=QUIET %d=CRITICAL %d=INFO\n",
- VQUIET, VCRITICAL, VINFO);
-}
-
void *wait_thread(void *arg)
{
int res;
- child_ret = RET_PASS;
+ child_ret = true;
res = futex_wait(buf, 1, NULL, 0);
child_blocked = 0;
if (res != 0 && errno != EWOULDBLOCK) {
- error("futex failure\n", errno);
- child_ret = RET_ERROR;
+ ksft_exit_fail_msg("futex failure\n");
+ child_ret = false;
}
pthread_exit(NULL);
}
-int main(int argc, char **argv)
+TEST(futex_wait_uninitialized_heap)
{
- int c, ret = RET_PASS;
long page_size;
pthread_t thr;
-
- while ((c = getopt(argc, argv, "chv:")) != -1) {
- switch (c) {
- case 'c':
- log_color(1);
- break;
- case 'h':
- usage(basename(argv[0]));
- exit(0);
- case 'v':
- log_verbosity(atoi(optarg));
- break;
- default:
- usage(basename(argv[0]));
- exit(1);
- }
- }
+ int ret;
page_size = sysconf(_SC_PAGESIZE);
buf = mmap(NULL, page_size, PROT_READ|PROT_WRITE,
MAP_PRIVATE|MAP_ANONYMOUS, 0, 0);
- if (buf == (void *)-1) {
- error("mmap\n", errno);
- exit(1);
- }
-
- ksft_print_header();
- ksft_set_plan(1);
- ksft_print_msg("%s: Test the uninitialized futex value in FUTEX_WAIT\n",
- basename(argv[0]));
-
+ if (buf == (void *)-1)
+ ksft_exit_fail_msg("mmap\n");
ret = pthread_create(&thr, NULL, wait_thread, NULL);
- if (ret) {
- error("pthread_create\n", errno);
- ret = RET_ERROR;
- goto out;
- }
+ if (ret)
+ ksft_exit_fail_msg("pthread_create\n");
- info("waiting %dus for child to return\n", WAIT_US);
+ ksft_print_dbg_msg("waiting %dus for child to return\n", WAIT_US);
usleep(WAIT_US);
- ret = child_ret;
- if (child_blocked) {
- fail("child blocked in kernel\n");
- ret = RET_FAIL;
- }
+ if (child_blocked)
+ ksft_test_result_fail("child blocked in kernel\n");
- out:
- print_result(TEST_NAME, ret);
- return ret;
+ if (!child_ret)
+ ksft_test_result_fail("child error\n");
}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/futex/functional/futex_wait_wouldblock.c b/tools/testing/selftests/futex/functional/futex_wait_wouldblock.c
index 2d8230da9064..36b7a54a4085 100644
--- a/tools/testing/selftests/futex/functional/futex_wait_wouldblock.c
+++ b/tools/testing/selftests/futex/functional/futex_wait_wouldblock.c
@@ -21,72 +21,44 @@
#include <stdlib.h>
#include <string.h>
#include <time.h>
+
#include "futextest.h"
#include "futex2test.h"
-#include "logging.h"
+#include "../../kselftest_harness.h"
-#define TEST_NAME "futex-wait-wouldblock"
#define timeout_ns 100000
-void usage(char *prog)
-{
- printf("Usage: %s\n", prog);
- printf(" -c Use color\n");
- printf(" -h Display this help message\n");
- printf(" -v L Verbosity level: %d=QUIET %d=CRITICAL %d=INFO\n",
- VQUIET, VCRITICAL, VINFO);
-}
-
-int main(int argc, char *argv[])
+TEST(futex_wait_wouldblock)
{
struct timespec to = {.tv_sec = 0, .tv_nsec = timeout_ns};
futex_t f1 = FUTEX_INITIALIZER;
- int res, ret = RET_PASS;
- int c;
- struct futex_waitv waitv = {
- .uaddr = (uintptr_t)&f1,
- .val = f1+1,
- .flags = FUTEX_32,
- .__reserved = 0
- };
+ int res;
- while ((c = getopt(argc, argv, "cht:v:")) != -1) {
- switch (c) {
- case 'c':
- log_color(1);
- break;
- case 'h':
- usage(basename(argv[0]));
- exit(0);
- case 'v':
- log_verbosity(atoi(optarg));
- break;
- default:
- usage(basename(argv[0]));
- exit(1);
- }
- }
-
- ksft_print_header();
- ksft_set_plan(2);
- ksft_print_msg("%s: Test the unexpected futex value in FUTEX_WAIT\n",
- basename(argv[0]));
-
- info("Calling futex_wait on f1: %u @ %p with val=%u\n", f1, &f1, f1+1);
+ ksft_print_dbg_msg("Calling futex_wait on f1: %u @ %p with val=%u\n", f1, &f1, f1+1);
res = futex_wait(&f1, f1+1, &to, FUTEX_PRIVATE_FLAG);
if (!res || errno != EWOULDBLOCK) {
ksft_test_result_fail("futex_wait returned: %d %s\n",
res ? errno : res,
res ? strerror(errno) : "");
- ret = RET_FAIL;
} else {
ksft_test_result_pass("futex_wait\n");
}
+}
- if (clock_gettime(CLOCK_MONOTONIC, &to)) {
- error("clock_gettime failed\n", errno);
- return errno;
- }
+TEST(futex_waitv_wouldblock)
+{
+ struct timespec to = {.tv_sec = 0, .tv_nsec = timeout_ns};
+ futex_t f1 = FUTEX_INITIALIZER;
+ struct futex_waitv waitv = {
+ .uaddr = (uintptr_t)&f1,
+ .val = f1 + 1,
+ .flags = FUTEX_32,
+ .__reserved = 0,
+ };
+ int res;
+
+ if (clock_gettime(CLOCK_MONOTONIC, &to))
+ ksft_exit_fail_msg("clock_gettime failed %d\n", errno);
to.tv_nsec += timeout_ns;
@@ -95,17 +67,15 @@ int main(int argc, char *argv[])
to.tv_nsec -= 1000000000;
}
- info("Calling futex_waitv on f1: %u @ %p with val=%u\n", f1, &f1, f1+1);
+ ksft_print_dbg_msg("Calling futex_waitv on f1: %u @ %p with val=%u\n", f1, &f1, f1+1);
res = futex_waitv(&waitv, 1, 0, &to, CLOCK_MONOTONIC);
if (!res || errno != EWOULDBLOCK) {
ksft_test_result_fail("futex_waitv returned: %d %s\n",
res ? errno : res,
res ? strerror(errno) : "");
- ret = RET_FAIL;
} else {
ksft_test_result_pass("futex_waitv\n");
}
-
- ksft_print_cnts();
- return ret;
}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/futex/functional/futex_waitv.c b/tools/testing/selftests/futex/functional/futex_waitv.c
index a94337f677e1..c684b10eb76e 100644
--- a/tools/testing/selftests/futex/functional/futex_waitv.c
+++ b/tools/testing/selftests/futex/functional/futex_waitv.c
@@ -15,25 +15,16 @@
#include <pthread.h>
#include <stdint.h>
#include <sys/shm.h>
+
#include "futextest.h"
#include "futex2test.h"
-#include "logging.h"
+#include "../../kselftest_harness.h"
-#define TEST_NAME "futex-wait"
#define WAKE_WAIT_US 10000
#define NR_FUTEXES 30
static struct futex_waitv waitv[NR_FUTEXES];
u_int32_t futexes[NR_FUTEXES] = {0};
-void usage(char *prog)
-{
- printf("Usage: %s\n", prog);
- printf(" -c Use color\n");
- printf(" -h Display this help message\n");
- printf(" -v L Verbosity level: %d=QUIET %d=CRITICAL %d=INFO\n",
- VQUIET, VCRITICAL, VINFO);
-}
-
void *waiterfn(void *arg)
{
struct timespec to;
@@ -41,7 +32,7 @@ void *waiterfn(void *arg)
/* setting absolute timeout for futex2 */
if (clock_gettime(CLOCK_MONOTONIC, &to))
- error("gettime64 failed\n", errno);
+ ksft_exit_fail_msg("gettime64 failed\n");
to.tv_sec++;
@@ -57,34 +48,10 @@ void *waiterfn(void *arg)
return NULL;
}
-int main(int argc, char *argv[])
+TEST(private_waitv)
{
pthread_t waiter;
- int res, ret = RET_PASS;
- struct timespec to;
- int c, i;
-
- while ((c = getopt(argc, argv, "cht:v:")) != -1) {
- switch (c) {
- case 'c':
- log_color(1);
- break;
- case 'h':
- usage(basename(argv[0]));
- exit(0);
- case 'v':
- log_verbosity(atoi(optarg));
- break;
- default:
- usage(basename(argv[0]));
- exit(1);
- }
- }
-
- ksft_print_header();
- ksft_set_plan(7);
- ksft_print_msg("%s: Test FUTEX_WAITV\n",
- basename(argv[0]));
+ int res, i;
for (i = 0; i < NR_FUTEXES; i++) {
waitv[i].uaddr = (uintptr_t)&futexes[i];
@@ -95,7 +62,7 @@ int main(int argc, char *argv[])
/* Private waitv */
if (pthread_create(&waiter, NULL, waiterfn, NULL))
- error("pthread_create failed\n", errno);
+ ksft_exit_fail_msg("pthread_create failed\n");
usleep(WAKE_WAIT_US);
@@ -104,10 +71,15 @@ int main(int argc, char *argv[])
ksft_test_result_fail("futex_wake private returned: %d %s\n",
res ? errno : res,
res ? strerror(errno) : "");
- ret = RET_FAIL;
} else {
ksft_test_result_pass("futex_waitv private\n");
}
+}
+
+TEST(shared_waitv)
+{
+ pthread_t waiter;
+ int res, i;
/* Shared waitv */
for (i = 0; i < NR_FUTEXES; i++) {
@@ -128,7 +100,7 @@ int main(int argc, char *argv[])
}
if (pthread_create(&waiter, NULL, waiterfn, NULL))
- error("pthread_create failed\n", errno);
+ ksft_exit_fail_msg("pthread_create failed\n");
usleep(WAKE_WAIT_US);
@@ -137,19 +109,24 @@ int main(int argc, char *argv[])
ksft_test_result_fail("futex_wake shared returned: %d %s\n",
res ? errno : res,
res ? strerror(errno) : "");
- ret = RET_FAIL;
} else {
ksft_test_result_pass("futex_waitv shared\n");
}
for (i = 0; i < NR_FUTEXES; i++)
shmdt(u64_to_ptr(waitv[i].uaddr));
+}
+
+TEST(invalid_flag)
+{
+ struct timespec to;
+ int res;
/* Testing a waiter without FUTEX_32 flag */
waitv[0].flags = FUTEX_PRIVATE_FLAG;
if (clock_gettime(CLOCK_MONOTONIC, &to))
- error("gettime64 failed\n", errno);
+ ksft_exit_fail_msg("gettime64 failed\n");
to.tv_sec++;
@@ -158,17 +135,22 @@ int main(int argc, char *argv[])
ksft_test_result_fail("futex_waitv private returned: %d %s\n",
res ? errno : res,
res ? strerror(errno) : "");
- ret = RET_FAIL;
} else {
ksft_test_result_pass("futex_waitv without FUTEX_32\n");
}
+}
+
+TEST(unaligned_address)
+{
+ struct timespec to;
+ int res;
/* Testing a waiter with an unaligned address */
waitv[0].flags = FUTEX_PRIVATE_FLAG | FUTEX_32;
waitv[0].uaddr = 1;
if (clock_gettime(CLOCK_MONOTONIC, &to))
- error("gettime64 failed\n", errno);
+ ksft_exit_fail_msg("gettime64 failed\n");
to.tv_sec++;
@@ -177,16 +159,21 @@ int main(int argc, char *argv[])
ksft_test_result_fail("futex_wake private returned: %d %s\n",
res ? errno : res,
res ? strerror(errno) : "");
- ret = RET_FAIL;
} else {
ksft_test_result_pass("futex_waitv with an unaligned address\n");
}
+}
+
+TEST(null_address)
+{
+ struct timespec to;
+ int res;
/* Testing a NULL address for waiters.uaddr */
waitv[0].uaddr = 0x00000000;
if (clock_gettime(CLOCK_MONOTONIC, &to))
- error("gettime64 failed\n", errno);
+ ksft_exit_fail_msg("gettime64 failed\n");
to.tv_sec++;
@@ -195,14 +182,13 @@ int main(int argc, char *argv[])
ksft_test_result_fail("futex_waitv private returned: %d %s\n",
res ? errno : res,
res ? strerror(errno) : "");
- ret = RET_FAIL;
} else {
ksft_test_result_pass("futex_waitv NULL address in waitv.uaddr\n");
}
/* Testing a NULL address for *waiters */
if (clock_gettime(CLOCK_MONOTONIC, &to))
- error("gettime64 failed\n", errno);
+ ksft_exit_fail_msg("gettime64 failed\n");
to.tv_sec++;
@@ -211,14 +197,19 @@ int main(int argc, char *argv[])
ksft_test_result_fail("futex_waitv private returned: %d %s\n",
res ? errno : res,
res ? strerror(errno) : "");
- ret = RET_FAIL;
} else {
ksft_test_result_pass("futex_waitv NULL address in *waiters\n");
}
+}
+
+TEST(invalid_clockid)
+{
+ struct timespec to;
+ int res;
/* Testing an invalid clockid */
if (clock_gettime(CLOCK_MONOTONIC, &to))
- error("gettime64 failed\n", errno);
+ ksft_exit_fail_msg("gettime64 failed\n");
to.tv_sec++;
@@ -227,11 +218,9 @@ int main(int argc, char *argv[])
ksft_test_result_fail("futex_waitv private returned: %d %s\n",
res ? errno : res,
res ? strerror(errno) : "");
- ret = RET_FAIL;
} else {
ksft_test_result_pass("futex_waitv invalid clockid\n");
}
-
- ksft_print_cnts();
- return ret;
}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/futex/functional/run.sh b/tools/testing/selftests/futex/functional/run.sh
index 81739849f299..e88545c06d57 100755
--- a/tools/testing/selftests/futex/functional/run.sh
+++ b/tools/testing/selftests/futex/functional/run.sh
@@ -18,74 +18,36 @@
#
###############################################################################
-# Test for a color capable console
-if [ -z "$USE_COLOR" ]; then
- tput setf 7 || tput setaf 7
- if [ $? -eq 0 ]; then
- USE_COLOR=1
- tput sgr0
- fi
-fi
-if [ "$USE_COLOR" -eq 1 ]; then
- COLOR="-c"
-fi
-
-
echo
-# requeue pi testing
-# without timeouts
-./futex_requeue_pi $COLOR
-./futex_requeue_pi $COLOR -b
-./futex_requeue_pi $COLOR -b -l
-./futex_requeue_pi $COLOR -b -o
-./futex_requeue_pi $COLOR -l
-./futex_requeue_pi $COLOR -o
-# with timeouts
-./futex_requeue_pi $COLOR -b -l -t 5000
-./futex_requeue_pi $COLOR -l -t 5000
-./futex_requeue_pi $COLOR -b -l -t 500000
-./futex_requeue_pi $COLOR -l -t 500000
-./futex_requeue_pi $COLOR -b -t 5000
-./futex_requeue_pi $COLOR -t 5000
-./futex_requeue_pi $COLOR -b -t 500000
-./futex_requeue_pi $COLOR -t 500000
-./futex_requeue_pi $COLOR -b -o -t 5000
-./futex_requeue_pi $COLOR -l -t 5000
-./futex_requeue_pi $COLOR -b -o -t 500000
-./futex_requeue_pi $COLOR -l -t 500000
-# with long timeout
-./futex_requeue_pi $COLOR -b -l -t 2000000000
-./futex_requeue_pi $COLOR -l -t 2000000000
-
+./futex_requeue_pi
echo
-./futex_requeue_pi_mismatched_ops $COLOR
+./futex_requeue_pi_mismatched_ops
echo
-./futex_requeue_pi_signal_restart $COLOR
+./futex_requeue_pi_signal_restart
echo
-./futex_wait_timeout $COLOR
+./futex_wait_timeout
echo
-./futex_wait_wouldblock $COLOR
+./futex_wait_wouldblock
echo
-./futex_wait_uninitialized_heap $COLOR
-./futex_wait_private_mapped_file $COLOR
+./futex_wait_uninitialized_heap
+./futex_wait_private_mapped_file
echo
-./futex_wait $COLOR
+./futex_wait
echo
-./futex_requeue $COLOR
+./futex_requeue
echo
-./futex_waitv $COLOR
+./futex_waitv
echo
-./futex_priv_hash $COLOR
-./futex_priv_hash -g $COLOR
+./futex_priv_hash
echo
-./futex_numa_mpol $COLOR
+./futex_numa_mpol
diff --git a/tools/testing/selftests/futex/include/futextest.h b/tools/testing/selftests/futex/include/futextest.h
index 7a5fd1d5355e..3d48e9789d9f 100644
--- a/tools/testing/selftests/futex/include/futextest.h
+++ b/tools/testing/selftests/futex/include/futextest.h
@@ -58,6 +58,17 @@ typedef volatile u_int32_t futex_t;
#define SYS_futex SYS_futex_time64
#endif
+/*
+ * On 32bit systems if we use "-D_FILE_OFFSET_BITS=64 -D_TIME_BITS=64" or if
+ * we are using a newer compiler then the size of the timestamps will be 64bit,
+ * however, the SYS_futex will still point to the 32bit futex system call.
+ */
+#if __SIZEOF_POINTER__ == 4 && defined(SYS_futex_time64) && \
+ defined(_TIME_BITS) && _TIME_BITS == 64
+# undef SYS_futex
+# define SYS_futex SYS_futex_time64
+#endif
+
/**
* futex() - SYS_futex syscall wrapper
* @uaddr: address of first futex
diff --git a/tools/testing/selftests/futex/include/logging.h b/tools/testing/selftests/futex/include/logging.h
deleted file mode 100644
index 874c69ce5cce..000000000000
--- a/tools/testing/selftests/futex/include/logging.h
+++ /dev/null
@@ -1,148 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/******************************************************************************
- *
- * Copyright © International Business Machines Corp., 2009
- *
- * DESCRIPTION
- * Glibc independent futex library for testing kernel functionality.
- *
- * AUTHOR
- * Darren Hart <dvhart@linux.intel.com>
- *
- * HISTORY
- * 2009-Nov-6: Initial version by Darren Hart <dvhart@linux.intel.com>
- *
- *****************************************************************************/
-
-#ifndef _LOGGING_H
-#define _LOGGING_H
-
-#include <stdio.h>
-#include <string.h>
-#include <unistd.h>
-#include <linux/futex.h>
-#include "kselftest.h"
-
-/*
- * Define PASS, ERROR, and FAIL strings with and without color escape
- * sequences, default to no color.
- */
-#define ESC 0x1B, '['
-#define BRIGHT '1'
-#define GREEN '3', '2'
-#define YELLOW '3', '3'
-#define RED '3', '1'
-#define ESCEND 'm'
-#define BRIGHT_GREEN ESC, BRIGHT, ';', GREEN, ESCEND
-#define BRIGHT_YELLOW ESC, BRIGHT, ';', YELLOW, ESCEND
-#define BRIGHT_RED ESC, BRIGHT, ';', RED, ESCEND
-#define RESET_COLOR ESC, '0', 'm'
-static const char PASS_COLOR[] = {BRIGHT_GREEN, ' ', 'P', 'A', 'S', 'S',
- RESET_COLOR, 0};
-static const char ERROR_COLOR[] = {BRIGHT_YELLOW, 'E', 'R', 'R', 'O', 'R',
- RESET_COLOR, 0};
-static const char FAIL_COLOR[] = {BRIGHT_RED, ' ', 'F', 'A', 'I', 'L',
- RESET_COLOR, 0};
-static const char INFO_NORMAL[] = " INFO";
-static const char PASS_NORMAL[] = " PASS";
-static const char ERROR_NORMAL[] = "ERROR";
-static const char FAIL_NORMAL[] = " FAIL";
-const char *INFO = INFO_NORMAL;
-const char *PASS = PASS_NORMAL;
-const char *ERROR = ERROR_NORMAL;
-const char *FAIL = FAIL_NORMAL;
-
-/* Verbosity setting for INFO messages */
-#define VQUIET 0
-#define VCRITICAL 1
-#define VINFO 2
-#define VMAX VINFO
-int _verbose = VCRITICAL;
-
-/* Functional test return codes */
-#define RET_PASS 0
-#define RET_ERROR -1
-#define RET_FAIL -2
-
-/**
- * log_color() - Use colored output for PASS, ERROR, and FAIL strings
- * @use_color: use color (1) or not (0)
- */
-void log_color(int use_color)
-{
- if (use_color) {
- PASS = PASS_COLOR;
- ERROR = ERROR_COLOR;
- FAIL = FAIL_COLOR;
- } else {
- PASS = PASS_NORMAL;
- ERROR = ERROR_NORMAL;
- FAIL = FAIL_NORMAL;
- }
-}
-
-/**
- * log_verbosity() - Set verbosity of test output
- * @verbose: Enable (1) verbose output or not (0)
- *
- * Currently setting verbose=1 will enable INFO messages and 0 will disable
- * them. FAIL and ERROR messages are always displayed.
- */
-void log_verbosity(int level)
-{
- if (level > VMAX)
- level = VMAX;
- else if (level < 0)
- level = 0;
- _verbose = level;
-}
-
-/**
- * print_result() - Print standard PASS | ERROR | FAIL results
- * @ret: the return value to be considered: 0 | RET_ERROR | RET_FAIL
- *
- * print_result() is primarily intended for functional tests.
- */
-void print_result(const char *test_name, int ret)
-{
- switch (ret) {
- case RET_PASS:
- ksft_test_result_pass("%s\n", test_name);
- ksft_print_cnts();
- return;
- case RET_ERROR:
- ksft_test_result_error("%s\n", test_name);
- ksft_print_cnts();
- return;
- case RET_FAIL:
- ksft_test_result_fail("%s\n", test_name);
- ksft_print_cnts();
- return;
- }
-}
-
-/* log level macros */
-#define info(message, vargs...) \
-do { \
- if (_verbose >= VINFO) \
- fprintf(stderr, "\t%s: "message, INFO, ##vargs); \
-} while (0)
-
-#define error(message, err, args...) \
-do { \
- if (_verbose >= VCRITICAL) {\
- if (err) \
- fprintf(stderr, "\t%s: %s: "message, \
- ERROR, strerror(err), ##args); \
- else \
- fprintf(stderr, "\t%s: "message, ERROR, ##args); \
- } \
-} while (0)
-
-#define fail(message, args...) \
-do { \
- if (_verbose >= VCRITICAL) \
- fprintf(stderr, "\t%s: "message, FAIL, ##args); \
-} while (0)
-
-#endif
diff --git a/tools/testing/selftests/iommu/iommufd_fail_nth.c b/tools/testing/selftests/iommu/iommufd_fail_nth.c
index 651fc9f13c08..45c14323a618 100644
--- a/tools/testing/selftests/iommu/iommufd_fail_nth.c
+++ b/tools/testing/selftests/iommu/iommufd_fail_nth.c
@@ -113,7 +113,7 @@ static bool fail_nth_next(struct __test_metadata *_metadata,
* necessarily mean a test failure, just that the limit has to be made
* bigger.
*/
- ASSERT_GT(400, nth_state->iteration);
+ ASSERT_GT(1000, nth_state->iteration);
if (nth_state->iteration != 0) {
ssize_t res;
ssize_t res2;
diff --git a/tools/testing/selftests/kexec/.gitignore b/tools/testing/selftests/kexec/.gitignore
new file mode 100644
index 000000000000..5f3d9e089ae8
--- /dev/null
+++ b/tools/testing/selftests/kexec/.gitignore
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+test_kexec_jump
diff --git a/tools/testing/selftests/kho/init.c b/tools/testing/selftests/kho/init.c
index 8034e24c6bf6..6d9e91d55d68 100644
--- a/tools/testing/selftests/kho/init.c
+++ b/tools/testing/selftests/kho/init.c
@@ -1,22 +1,17 @@
// SPDX-License-Identifier: GPL-2.0
-#ifndef NOLIBC
-#include <errno.h>
#include <stdio.h>
#include <unistd.h>
#include <fcntl.h>
-#include <syscall.h>
+#include <sys/syscall.h>
#include <sys/mount.h>
#include <sys/reboot.h>
-#endif
+#include <linux/kexec.h>
/* from arch/x86/include/asm/setup.h */
#define COMMAND_LINE_SIZE 2048
-/* from include/linux/kexex.h */
-#define KEXEC_FILE_NO_INITRAMFS 0x00000004
-
-#define KHO_FINILIZE "/debugfs/kho/out/finalize"
+#define KHO_FINALIZE "/debugfs/kho/out/finalize"
#define KERNEL_IMAGE "/kernel"
static int mount_filesystems(void)
@@ -32,7 +27,7 @@ static int kho_enable(void)
const char enable[] = "1";
int fd;
- fd = open(KHO_FINILIZE, O_RDWR);
+ fd = open(KHO_FINALIZE, O_RDWR);
if (fd < 0)
return -1;
diff --git a/tools/testing/selftests/kho/vmtest.sh b/tools/testing/selftests/kho/vmtest.sh
index ec70a17bd476..3f6c17166846 100755
--- a/tools/testing/selftests/kho/vmtest.sh
+++ b/tools/testing/selftests/kho/vmtest.sh
@@ -10,7 +10,6 @@ kernel_dir=$(realpath "$test_dir/../../../..")
tmp_dir=$(mktemp -d /tmp/kho-test.XXXXXXXX)
headers_dir="$tmp_dir/usr"
-initrd_dir="$tmp_dir/initrd"
initrd="$tmp_dir/initrd.cpio"
source "$test_dir/../kselftest/ktap_helpers.sh"
@@ -81,19 +80,22 @@ EOF
function mkinitrd() {
local kernel=$1
- mkdir -p "$initrd_dir"/{dev,debugfs,proc}
- sudo mknod "$initrd_dir/dev/console" c 5 1
-
- "$CROSS_COMPILE"gcc -s -static -Os -nostdinc -I"$headers_dir/include" \
- -fno-asynchronous-unwind-tables -fno-ident -nostdlib \
- -include "$test_dir/../../../include/nolibc/nolibc.h" \
- -o "$initrd_dir/init" "$test_dir/init.c" \
-
- cp "$kernel" "$initrd_dir/kernel"
+ "$CROSS_COMPILE"gcc -s -static -Os -nostdinc -nostdlib \
+ -fno-asynchronous-unwind-tables -fno-ident \
+ -I "$headers_dir/include" \
+ -I "$kernel_dir/tools/include/nolibc" \
+ -o "$tmp_dir/init" "$test_dir/init.c"
+
+ cat > "$tmp_dir/cpio_list" <<EOF
+dir /dev 0755 0 0
+dir /proc 0755 0 0
+dir /debugfs 0755 0 0
+nod /dev/console 0600 0 0 c 5 1
+file /init $tmp_dir/init 0755 0 0
+file /kernel $kernel 0644 0 0
+EOF
- pushd "$initrd_dir" &>/dev/null
- find . | cpio -H newc --create > "$initrd" 2>/dev/null
- popd &>/dev/null
+ "$build_dir/usr/gen_init_cpio" "$tmp_dir/cpio_list" > "$initrd"
}
function run_qemu() {
diff --git a/tools/testing/selftests/kselftest.h b/tools/testing/selftests/kselftest.h
index c3b6d2604b1e..afbcf8412ae5 100644
--- a/tools/testing/selftests/kselftest.h
+++ b/tools/testing/selftests/kselftest.h
@@ -54,6 +54,7 @@
#include <stdlib.h>
#include <unistd.h>
#include <stdarg.h>
+#include <stdbool.h>
#include <string.h>
#include <stdio.h>
#include <sys/utsname.h>
@@ -92,6 +93,14 @@
#endif
#define __printf(a, b) __attribute__((format(printf, a, b)))
+#ifndef __always_unused
+#define __always_unused __attribute__((__unused__))
+#endif
+
+#ifndef __maybe_unused
+#define __maybe_unused __attribute__((__unused__))
+#endif
+
/* counters */
struct ksft_count {
unsigned int ksft_pass;
@@ -104,6 +113,7 @@ struct ksft_count {
static struct ksft_count ksft_cnt;
static unsigned int ksft_plan;
+static bool ksft_debug_enabled;
static inline unsigned int ksft_test_num(void)
{
@@ -175,6 +185,18 @@ static inline __printf(1, 2) void ksft_print_msg(const char *msg, ...)
va_end(args);
}
+static inline void ksft_print_dbg_msg(const char *msg, ...)
+{
+ va_list args;
+
+ if (!ksft_debug_enabled)
+ return;
+
+ va_start(args, msg);
+ ksft_print_msg(msg, args);
+ va_end(args);
+}
+
static inline void ksft_perror(const char *msg)
{
ksft_print_msg("%s: %s (%d)\n", msg, strerror(errno), errno);
diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h
index 8516e8434bc4..3f66e862e83e 100644
--- a/tools/testing/selftests/kselftest_harness.h
+++ b/tools/testing/selftests/kselftest_harness.h
@@ -1091,7 +1091,7 @@ static int test_harness_argv_check(int argc, char **argv)
{
int opt;
- while ((opt = getopt(argc, argv, "hlF:f:V:v:t:T:r:")) != -1) {
+ while ((opt = getopt(argc, argv, "dhlF:f:V:v:t:T:r:")) != -1) {
switch (opt) {
case 'f':
case 'F':
@@ -1104,12 +1104,16 @@ static int test_harness_argv_check(int argc, char **argv)
case 'l':
test_harness_list_tests();
return KSFT_SKIP;
+ case 'd':
+ ksft_debug_enabled = true;
+ break;
case 'h':
default:
fprintf(stderr,
- "Usage: %s [-h|-l] [-t|-T|-v|-V|-f|-F|-r name]\n"
+ "Usage: %s [-h|-l|-d] [-t|-T|-v|-V|-f|-F|-r name]\n"
"\t-h print help\n"
"\t-l list all tests\n"
+ "\t-d enable debug prints\n"
"\n"
"\t-t name include test\n"
"\t-T name exclude test\n"
@@ -1142,8 +1146,9 @@ static bool test_enabled(int argc, char **argv,
int opt;
optind = 1;
- while ((opt = getopt(argc, argv, "F:f:V:v:t:T:r:")) != -1) {
- has_positive |= islower(opt);
+ while ((opt = getopt(argc, argv, "dF:f:V:v:t:T:r:")) != -1) {
+ if (opt != 'd')
+ has_positive |= islower(opt);
switch (tolower(opt)) {
case 't':
diff --git a/tools/testing/selftests/kselftest_harness/Makefile b/tools/testing/selftests/kselftest_harness/Makefile
index 0617535a6ce4..d2369c01701a 100644
--- a/tools/testing/selftests/kselftest_harness/Makefile
+++ b/tools/testing/selftests/kselftest_harness/Makefile
@@ -2,6 +2,7 @@
TEST_GEN_PROGS_EXTENDED := harness-selftest
TEST_PROGS := harness-selftest.sh
+TEST_FILES := harness-selftest.expected
EXTRA_CLEAN := harness-selftest.seen
include ../lib.mk
diff --git a/tools/testing/selftests/landlock/audit.h b/tools/testing/selftests/landlock/audit.h
index b16986aa6442..02fd1393947a 100644
--- a/tools/testing/selftests/landlock/audit.h
+++ b/tools/testing/selftests/landlock/audit.h
@@ -20,14 +20,12 @@
#include <sys/time.h>
#include <unistd.h>
+#include "../kselftest.h"
+
#ifndef ARRAY_SIZE
#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]))
#endif
-#ifndef __maybe_unused
-#define __maybe_unused __attribute__((__unused__))
-#endif
-
#define REGEX_LANDLOCK_PREFIX "^audit([0-9.:]\\+): domain=\\([0-9a-f]\\+\\)"
struct audit_filter {
diff --git a/tools/testing/selftests/landlock/common.h b/tools/testing/selftests/landlock/common.h
index 88a3c78f5d98..9acecae36f51 100644
--- a/tools/testing/selftests/landlock/common.h
+++ b/tools/testing/selftests/landlock/common.h
@@ -22,10 +22,6 @@
#define TMP_DIR "tmp"
-#ifndef __maybe_unused
-#define __maybe_unused __attribute__((__unused__))
-#endif
-
/* TEST_F_FORK() should not be used for new tests. */
#define TEST_F_FORK(fixture_name, test_name) TEST_F(fixture_name, test_name)
diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk
index 530390033929..a448fae57831 100644
--- a/tools/testing/selftests/lib.mk
+++ b/tools/testing/selftests/lib.mk
@@ -228,7 +228,10 @@ $(OUTPUT)/%:%.S
$(LINK.S) $^ $(LDLIBS) -o $@
endif
+# Extract the expected header directory
+khdr_output := $(patsubst %/usr/include,%,$(filter %/usr/include,$(KHDR_INCLUDES)))
+
headers:
- $(Q)$(MAKE) -C $(top_srcdir) headers
+ $(Q)$(MAKE) -f $(top_srcdir)/Makefile -C $(khdr_output) headers
.PHONY: run_tests all clean install emit_tests gen_mods_dir clean_mods_dir headers
diff --git a/tools/testing/selftests/mm/.gitignore b/tools/testing/selftests/mm/.gitignore
index e7b23a8a05fe..c2a8586e51a1 100644
--- a/tools/testing/selftests/mm/.gitignore
+++ b/tools/testing/selftests/mm/.gitignore
@@ -58,3 +58,5 @@ pkey_sighandler_tests_32
pkey_sighandler_tests_64
guard-regions
merge
+prctl_thp_disable
+rmap
diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile
index d13b3cef2a2b..eaf9312097f7 100644
--- a/tools/testing/selftests/mm/Makefile
+++ b/tools/testing/selftests/mm/Makefile
@@ -34,6 +34,7 @@ endif
MAKEFLAGS += --no-builtin-rules
CFLAGS = -Wall -O2 -I $(top_srcdir) $(EXTRA_CFLAGS) $(KHDR_INCLUDES) $(TOOLS_INCLUDES)
+CFLAGS += -Wunreachable-code
LDLIBS = -lrt -lpthread -lm
# Some distributions (such as Ubuntu) configure GCC so that _FORTIFY_SOURCE is
@@ -86,6 +87,7 @@ TEST_GEN_FILES += on-fault-limit
TEST_GEN_FILES += pagemap_ioctl
TEST_GEN_FILES += pfnmap
TEST_GEN_FILES += process_madv
+TEST_GEN_FILES += prctl_thp_disable
TEST_GEN_FILES += thuge-gen
TEST_GEN_FILES += transhuge-stress
TEST_GEN_FILES += uffd-stress
@@ -101,6 +103,7 @@ TEST_GEN_FILES += hugetlb_dio
TEST_GEN_FILES += droppable
TEST_GEN_FILES += guard-regions
TEST_GEN_FILES += merge
+TEST_GEN_FILES += rmap
ifneq ($(ARCH),arm64)
TEST_GEN_FILES += soft-dirty
@@ -228,6 +231,8 @@ $(OUTPUT)/ksm_tests: LDLIBS += -lnuma
$(OUTPUT)/migration: LDLIBS += -lnuma
+$(OUTPUT)/rmap: LDLIBS += -lnuma
+
local_config.mk local_config.h: check_config.sh
/bin/sh ./check_config.sh $(CC)
diff --git a/tools/testing/selftests/mm/cow.c b/tools/testing/selftests/mm/cow.c
index c744c603d688..6560c26f47d1 100644
--- a/tools/testing/selftests/mm/cow.c
+++ b/tools/testing/selftests/mm/cow.c
@@ -41,11 +41,6 @@ static size_t hugetlbsizes[10];
static int gup_fd;
static bool has_huge_zeropage;
-static int sz2ord(size_t size)
-{
- return __builtin_ctzll(size / pagesize);
-}
-
static int detect_thp_sizes(size_t sizes[], int max)
{
int count = 0;
@@ -57,7 +52,7 @@ static int detect_thp_sizes(size_t sizes[], int max)
if (!pmdsize)
return 0;
- orders = 1UL << sz2ord(pmdsize);
+ orders = 1UL << sz2ord(pmdsize, pagesize);
orders |= thp_supported_orders();
for (i = 0; orders && count < max; i++) {
@@ -1216,8 +1211,8 @@ static void run_anon_test_case(struct test_case const *test_case)
size_t size = thpsizes[i];
struct thp_settings settings = *thp_current_settings();
- settings.hugepages[sz2ord(pmdsize)].enabled = THP_NEVER;
- settings.hugepages[sz2ord(size)].enabled = THP_ALWAYS;
+ settings.hugepages[sz2ord(pmdsize, pagesize)].enabled = THP_NEVER;
+ settings.hugepages[sz2ord(size, pagesize)].enabled = THP_ALWAYS;
thp_push_settings(&settings);
if (size == pmdsize) {
@@ -1868,7 +1863,7 @@ int main(int argc, char **argv)
if (pmdsize) {
/* Only if THP is supported. */
thp_read_settings(&default_settings);
- default_settings.hugepages[sz2ord(pmdsize)].enabled = THP_INHERIT;
+ default_settings.hugepages[sz2ord(pmdsize, pagesize)].enabled = THP_INHERIT;
thp_save_settings();
thp_push_settings(&default_settings);
diff --git a/tools/testing/selftests/mm/gup_test.c b/tools/testing/selftests/mm/gup_test.c
index bdeaac67ff9a..8900b840c17a 100644
--- a/tools/testing/selftests/mm/gup_test.c
+++ b/tools/testing/selftests/mm/gup_test.c
@@ -139,6 +139,8 @@ int main(int argc, char **argv)
break;
case 'n':
nr_pages = atoi(optarg);
+ if (nr_pages < 0)
+ nr_pages = size / psize();
break;
case 't':
thp = 1;
diff --git a/tools/testing/selftests/mm/hmm-tests.c b/tools/testing/selftests/mm/hmm-tests.c
index 141bf63cbe05..15aadaf24a66 100644
--- a/tools/testing/selftests/mm/hmm-tests.c
+++ b/tools/testing/selftests/mm/hmm-tests.c
@@ -2027,11 +2027,10 @@ TEST_F(hmm, hmm_cow_in_device)
if (pid == -1)
ASSERT_EQ(pid, 0);
if (!pid) {
- /* Child process waitd for SIGTERM from the parent. */
+ /* Child process waits for SIGTERM from the parent. */
while (1) {
}
- perror("Should not reach this\n");
- exit(0);
+ /* Should not reach this */
}
/* Parent process writes to COW pages(s) and gets a
* new copy in system. In case of device private pages,
diff --git a/tools/testing/selftests/mm/hugepage-mremap.c b/tools/testing/selftests/mm/hugepage-mremap.c
index c463d1c09c9b..2bd1dac75c3f 100644
--- a/tools/testing/selftests/mm/hugepage-mremap.c
+++ b/tools/testing/selftests/mm/hugepage-mremap.c
@@ -65,10 +65,20 @@ static void register_region_with_uffd(char *addr, size_t len)
struct uffdio_api uffdio_api;
/* Create and enable userfaultfd object. */
-
uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK);
- if (uffd == -1)
- ksft_exit_fail_msg("userfaultfd: %s\n", strerror(errno));
+ if (uffd == -1) {
+ switch (errno) {
+ case EPERM:
+ ksft_exit_skip("Insufficient permissions, try running as root.\n");
+ break;
+ case ENOSYS:
+ ksft_exit_skip("userfaultfd is not supported/not enabled.\n");
+ break;
+ default:
+ ksft_exit_fail_msg("userfaultfd failed with %s\n", strerror(errno));
+ break;
+ }
+ }
uffdio_api.api = UFFD_API;
uffdio_api.features = 0;
diff --git a/tools/testing/selftests/mm/khugepaged.c b/tools/testing/selftests/mm/khugepaged.c
index a18c50d51141..3fe7ef04ac62 100644
--- a/tools/testing/selftests/mm/khugepaged.c
+++ b/tools/testing/selftests/mm/khugepaged.c
@@ -394,7 +394,7 @@ static void *file_setup_area(int nr_hpages)
perror("open()");
exit(EXIT_FAILURE);
}
- p = mmap(BASE_ADDR, size, PROT_READ | PROT_EXEC,
+ p = mmap(BASE_ADDR, size, PROT_READ,
MAP_PRIVATE, finfo.fd, 0);
if (p == MAP_FAILED || p != BASE_ADDR) {
perror("mmap()");
diff --git a/tools/testing/selftests/mm/ksm_functional_tests.c b/tools/testing/selftests/mm/ksm_functional_tests.c
index d8bd1911dfc0..ac136f04b8d6 100644
--- a/tools/testing/selftests/mm/ksm_functional_tests.c
+++ b/tools/testing/selftests/mm/ksm_functional_tests.c
@@ -38,14 +38,11 @@ enum ksm_merge_mode {
};
static int mem_fd;
-static int ksm_fd;
-static int ksm_full_scans_fd;
-static int proc_self_ksm_stat_fd;
-static int proc_self_ksm_merging_pages_fd;
-static int ksm_use_zero_pages_fd;
static int pagemap_fd;
static size_t pagesize;
+static void init_global_file_handles(void);
+
static bool range_maps_duplicates(char *addr, unsigned long size)
{
unsigned long offs_a, offs_b, pfn_a, pfn_b;
@@ -73,88 +70,6 @@ static bool range_maps_duplicates(char *addr, unsigned long size)
return false;
}
-static long get_my_ksm_zero_pages(void)
-{
- char buf[200];
- char *substr_ksm_zero;
- size_t value_pos;
- ssize_t read_size;
- unsigned long my_ksm_zero_pages;
-
- if (!proc_self_ksm_stat_fd)
- return 0;
-
- read_size = pread(proc_self_ksm_stat_fd, buf, sizeof(buf) - 1, 0);
- if (read_size < 0)
- return -errno;
-
- buf[read_size] = 0;
-
- substr_ksm_zero = strstr(buf, "ksm_zero_pages");
- if (!substr_ksm_zero)
- return 0;
-
- value_pos = strcspn(substr_ksm_zero, "0123456789");
- my_ksm_zero_pages = strtol(substr_ksm_zero + value_pos, NULL, 10);
-
- return my_ksm_zero_pages;
-}
-
-static long get_my_merging_pages(void)
-{
- char buf[10];
- ssize_t ret;
-
- if (proc_self_ksm_merging_pages_fd < 0)
- return proc_self_ksm_merging_pages_fd;
-
- ret = pread(proc_self_ksm_merging_pages_fd, buf, sizeof(buf) - 1, 0);
- if (ret <= 0)
- return -errno;
- buf[ret] = 0;
-
- return strtol(buf, NULL, 10);
-}
-
-static long ksm_get_full_scans(void)
-{
- char buf[10];
- ssize_t ret;
-
- ret = pread(ksm_full_scans_fd, buf, sizeof(buf) - 1, 0);
- if (ret <= 0)
- return -errno;
- buf[ret] = 0;
-
- return strtol(buf, NULL, 10);
-}
-
-static int ksm_merge(void)
-{
- long start_scans, end_scans;
-
- /* Wait for two full scans such that any possible merging happened. */
- start_scans = ksm_get_full_scans();
- if (start_scans < 0)
- return start_scans;
- if (write(ksm_fd, "1", 1) != 1)
- return -errno;
- do {
- end_scans = ksm_get_full_scans();
- if (end_scans < 0)
- return end_scans;
- } while (end_scans < start_scans + 2);
-
- return 0;
-}
-
-static int ksm_unmerge(void)
-{
- if (write(ksm_fd, "2", 1) != 1)
- return -errno;
- return 0;
-}
-
static char *__mmap_and_merge_range(char val, unsigned long size, int prot,
enum ksm_merge_mode mode)
{
@@ -163,12 +78,12 @@ static char *__mmap_and_merge_range(char val, unsigned long size, int prot,
int ret;
/* Stabilize accounting by disabling KSM completely. */
- if (ksm_unmerge()) {
+ if (ksm_stop() < 0) {
ksft_print_msg("Disabling (unmerging) KSM failed\n");
return err_map;
}
- if (get_my_merging_pages() > 0) {
+ if (ksm_get_self_merging_pages() > 0) {
ksft_print_msg("Still pages merged\n");
return err_map;
}
@@ -218,7 +133,7 @@ static char *__mmap_and_merge_range(char val, unsigned long size, int prot,
}
/* Run KSM to trigger merging and wait. */
- if (ksm_merge()) {
+ if (ksm_start() < 0) {
ksft_print_msg("Running KSM failed\n");
goto unmap;
}
@@ -227,7 +142,7 @@ static char *__mmap_and_merge_range(char val, unsigned long size, int prot,
* Check if anything was merged at all. Ignore the zero page that is
* accounted differently (depending on kernel support).
*/
- if (val && !get_my_merging_pages()) {
+ if (val && !ksm_get_self_merging_pages()) {
ksft_print_msg("No pages got merged\n");
goto unmap;
}
@@ -274,6 +189,7 @@ static void test_unmerge(void)
ksft_test_result(!range_maps_duplicates(map, size),
"Pages were unmerged\n");
unmap:
+ ksm_stop();
munmap(map, size);
}
@@ -286,15 +202,12 @@ static void test_unmerge_zero_pages(void)
ksft_print_msg("[RUN] %s\n", __func__);
- if (proc_self_ksm_stat_fd < 0) {
- ksft_test_result_skip("open(\"/proc/self/ksm_stat\") failed\n");
- return;
- }
- if (ksm_use_zero_pages_fd < 0) {
- ksft_test_result_skip("open \"/sys/kernel/mm/ksm/use_zero_pages\" failed\n");
+ if (ksm_get_self_zero_pages() < 0) {
+ ksft_test_result_skip("accessing \"/proc/self/ksm_stat\" failed\n");
return;
}
- if (write(ksm_use_zero_pages_fd, "1", 1) != 1) {
+
+ if (ksm_use_zero_pages() < 0) {
ksft_test_result_skip("write \"/sys/kernel/mm/ksm/use_zero_pages\" failed\n");
return;
}
@@ -306,7 +219,7 @@ static void test_unmerge_zero_pages(void)
/* Check if ksm_zero_pages is updated correctly after KSM merging */
pages_expected = size / pagesize;
- if (pages_expected != get_my_ksm_zero_pages()) {
+ if (pages_expected != ksm_get_self_zero_pages()) {
ksft_test_result_fail("'ksm_zero_pages' updated after merging\n");
goto unmap;
}
@@ -319,7 +232,7 @@ static void test_unmerge_zero_pages(void)
/* Check if ksm_zero_pages is updated correctly after unmerging */
pages_expected /= 2;
- if (pages_expected != get_my_ksm_zero_pages()) {
+ if (pages_expected != ksm_get_self_zero_pages()) {
ksft_test_result_fail("'ksm_zero_pages' updated after unmerging\n");
goto unmap;
}
@@ -329,7 +242,7 @@ static void test_unmerge_zero_pages(void)
*((unsigned int *)&map[offs]) = offs;
/* Now we should have no zeropages remaining. */
- if (get_my_ksm_zero_pages()) {
+ if (ksm_get_self_zero_pages()) {
ksft_test_result_fail("'ksm_zero_pages' updated after write fault\n");
goto unmap;
}
@@ -338,6 +251,7 @@ static void test_unmerge_zero_pages(void)
ksft_test_result(!range_maps_duplicates(map, size),
"KSM zero pages were unmerged\n");
unmap:
+ ksm_stop();
munmap(map, size);
}
@@ -366,6 +280,7 @@ static void test_unmerge_discarded(void)
ksft_test_result(!range_maps_duplicates(map, size),
"Pages were unmerged\n");
unmap:
+ ksm_stop();
munmap(map, size);
}
@@ -452,6 +367,7 @@ static void test_unmerge_uffd_wp(void)
close_uffd:
close(uffd);
unmap:
+ ksm_stop();
munmap(map, size);
}
#endif
@@ -506,27 +422,30 @@ static int test_child_ksm(void)
/* Test if KSM is enabled for the process. */
if (prctl(PR_GET_MEMORY_MERGE, 0, 0, 0, 0) != 1)
- return -1;
+ return 1;
/* Test if merge could really happen. */
map = __mmap_and_merge_range(0xcf, size, PROT_READ | PROT_WRITE, KSM_MERGE_NONE);
if (map == MAP_MERGE_FAIL)
- return -2;
+ return 2;
else if (map == MAP_MERGE_SKIP)
- return -3;
+ return 3;
+ ksm_stop();
munmap(map, size);
return 0;
}
static void test_child_ksm_err(int status)
{
- if (status == -1)
+ if (status == 1)
ksft_test_result_fail("unexpected PR_GET_MEMORY_MERGE result in child\n");
- else if (status == -2)
+ else if (status == 2)
ksft_test_result_fail("Merge in child failed\n");
- else if (status == -3)
+ else if (status == 3)
ksft_test_result_skip("Merge in child skipped\n");
+ else if (status == 4)
+ ksft_test_result_fail("Binary not found\n");
}
/* Verify that prctl ksm flag is inherited. */
@@ -548,6 +467,7 @@ static void test_prctl_fork(void)
child_pid = fork();
if (!child_pid) {
+ init_global_file_handles();
exit(test_child_ksm());
} else if (child_pid < 0) {
ksft_test_result_fail("fork() failed\n");
@@ -595,10 +515,10 @@ static void test_prctl_fork_exec(void)
return;
} else if (child_pid == 0) {
char *prg_name = "./ksm_functional_tests";
- char *argv_for_program[] = { prg_name, FORK_EXEC_CHILD_PRG_NAME };
+ char *argv_for_program[] = { prg_name, FORK_EXEC_CHILD_PRG_NAME, NULL };
execv(prg_name, argv_for_program);
- return;
+ exit(4);
}
if (waitpid(child_pid, &status, 0) > 0) {
@@ -644,6 +564,7 @@ static void test_prctl_unmerge(void)
ksft_test_result(!range_maps_duplicates(map, size),
"Pages were unmerged\n");
unmap:
+ ksm_stop();
munmap(map, size);
}
@@ -677,6 +598,47 @@ static void test_prot_none(void)
ksft_test_result(!range_maps_duplicates(map, size),
"Pages were unmerged\n");
unmap:
+ ksm_stop();
+ munmap(map, size);
+}
+
+static void test_fork_ksm_merging_page_count(void)
+{
+ const unsigned int size = 2 * MiB;
+ char *map;
+ pid_t child_pid;
+ int status;
+
+ ksft_print_msg("[RUN] %s\n", __func__);
+
+ map = mmap_and_merge_range(0xcf, size, PROT_READ | PROT_WRITE, KSM_MERGE_MADVISE);
+ if (map == MAP_FAILED)
+ return;
+
+ child_pid = fork();
+ if (!child_pid) {
+ init_global_file_handles();
+ exit(ksm_get_self_merging_pages());
+ } else if (child_pid < 0) {
+ ksft_test_result_fail("fork() failed\n");
+ goto unmap;
+ }
+
+ if (waitpid(child_pid, &status, 0) < 0) {
+ ksft_test_result_fail("waitpid() failed\n");
+ goto unmap;
+ }
+
+ status = WEXITSTATUS(status);
+ if (status) {
+ ksft_test_result_fail("ksm_merging_page in child: %d\n", status);
+ goto unmap;
+ }
+
+ ksft_test_result_pass("ksm_merging_pages is not inherited after fork\n");
+
+unmap:
+ ksm_stop();
munmap(map, size);
}
@@ -685,24 +647,20 @@ static void init_global_file_handles(void)
mem_fd = open("/proc/self/mem", O_RDWR);
if (mem_fd < 0)
ksft_exit_fail_msg("opening /proc/self/mem failed\n");
- ksm_fd = open("/sys/kernel/mm/ksm/run", O_RDWR);
- if (ksm_fd < 0)
- ksft_exit_skip("open(\"/sys/kernel/mm/ksm/run\") failed\n");
- ksm_full_scans_fd = open("/sys/kernel/mm/ksm/full_scans", O_RDONLY);
- if (ksm_full_scans_fd < 0)
- ksft_exit_skip("open(\"/sys/kernel/mm/ksm/full_scans\") failed\n");
+ if (ksm_stop() < 0)
+ ksft_exit_skip("accessing \"/sys/kernel/mm/ksm/run\") failed\n");
+ if (ksm_get_full_scans() < 0)
+ ksft_exit_skip("accessing \"/sys/kernel/mm/ksm/full_scans\") failed\n");
pagemap_fd = open("/proc/self/pagemap", O_RDONLY);
if (pagemap_fd < 0)
ksft_exit_skip("open(\"/proc/self/pagemap\") failed\n");
- proc_self_ksm_stat_fd = open("/proc/self/ksm_stat", O_RDONLY);
- proc_self_ksm_merging_pages_fd = open("/proc/self/ksm_merging_pages",
- O_RDONLY);
- ksm_use_zero_pages_fd = open("/sys/kernel/mm/ksm/use_zero_pages", O_RDWR);
+ if (ksm_get_self_merging_pages() < 0)
+ ksft_exit_skip("accessing \"/proc/self/ksm_merging_pages\") failed\n");
}
int main(int argc, char **argv)
{
- unsigned int tests = 8;
+ unsigned int tests = 9;
int err;
if (argc > 1 && !strcmp(argv[1], FORK_EXEC_CHILD_PRG_NAME)) {
@@ -734,6 +692,7 @@ int main(int argc, char **argv)
test_prctl_fork();
test_prctl_fork_exec();
test_prctl_unmerge();
+ test_fork_ksm_merging_page_count();
err = ksft_get_fail_cnt();
if (err)
diff --git a/tools/testing/selftests/mm/madv_populate.c b/tools/testing/selftests/mm/madv_populate.c
index b6fabd5c27ed..d8d11bc67ddc 100644
--- a/tools/testing/selftests/mm/madv_populate.c
+++ b/tools/testing/selftests/mm/madv_populate.c
@@ -264,23 +264,6 @@ static void test_softdirty(void)
munmap(addr, SIZE);
}
-static int system_has_softdirty(void)
-{
- /*
- * There is no way to check if the kernel supports soft-dirty, other
- * than by writing to a page and seeing if the bit was set. But the
- * tests are intended to check that the bit gets set when it should, so
- * doing that check would turn a potentially legitimate fail into a
- * skip. Fortunately, we know for sure that arm64 does not support
- * soft-dirty. So for now, let's just use the arch as a corse guide.
- */
-#if defined(__aarch64__)
- return 0;
-#else
- return 1;
-#endif
-}
-
int main(int argc, char **argv)
{
int nr_tests = 16;
@@ -288,7 +271,7 @@ int main(int argc, char **argv)
pagesize = getpagesize();
- if (system_has_softdirty())
+ if (softdirty_supported())
nr_tests += 5;
ksft_print_header();
@@ -300,7 +283,7 @@ int main(int argc, char **argv)
test_holes();
test_populate_read();
test_populate_write();
- if (system_has_softdirty())
+ if (softdirty_supported())
test_softdirty();
err = ksft_get_fail_cnt();
diff --git a/tools/testing/selftests/mm/mremap_test.c b/tools/testing/selftests/mm/mremap_test.c
index 5bd52a951cbd..bf2863b102e3 100644
--- a/tools/testing/selftests/mm/mremap_test.c
+++ b/tools/testing/selftests/mm/mremap_test.c
@@ -846,7 +846,7 @@ static void mremap_move_multi_invalid_vmas(FILE *maps_fp,
}
if (err != EFAULT) {
errno = err;
- perror("mrmeap() unexpected error");
+ perror("mremap() unexpected error");
success = false;
goto out_unmap;
}
@@ -899,7 +899,7 @@ static void mremap_move_multi_invalid_vmas(FILE *maps_fp,
}
if (err != EFAULT) {
errno = err;
- perror("mrmeap() unexpected error");
+ perror("mremap() unexpected error");
success = false;
goto out_unmap;
}
@@ -948,7 +948,7 @@ static void mremap_move_multi_invalid_vmas(FILE *maps_fp,
}
if (err != EFAULT) {
errno = err;
- perror("mrmeap() unexpected error");
+ perror("mremap() unexpected error");
success = false;
goto out_unmap;
}
diff --git a/tools/testing/selftests/mm/pagemap_ioctl.c b/tools/testing/selftests/mm/pagemap_ioctl.c
index e6face7c0166..4fc8e578ec7c 100644
--- a/tools/testing/selftests/mm/pagemap_ioctl.c
+++ b/tools/testing/selftests/mm/pagemap_ioctl.c
@@ -209,7 +209,7 @@ int userfaultfd_tests(void)
wp_addr_range(mem, mem_size);
vec_size = mem_size/page_size;
- vec = malloc(sizeof(struct page_region) * vec_size);
+ vec = calloc(vec_size, sizeof(struct page_region));
written = pagemap_ioctl(mem, mem_size, vec, 1, PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC,
vec_size - 2, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN);
@@ -247,11 +247,11 @@ int sanity_tests_sd(void)
vec_size = num_pages/2;
mem_size = num_pages * page_size;
- vec = malloc(sizeof(struct page_region) * vec_size);
+ vec = calloc(vec_size, sizeof(struct page_region));
if (!vec)
ksft_exit_fail_msg("error nomem\n");
- vec2 = malloc(sizeof(struct page_region) * vec_size);
+ vec2 = calloc(vec_size, sizeof(struct page_region));
if (!vec2)
ksft_exit_fail_msg("error nomem\n");
@@ -436,7 +436,7 @@ int sanity_tests_sd(void)
mem_size = 1050 * page_size;
vec_size = mem_size/(page_size*2);
- vec = malloc(sizeof(struct page_region) * vec_size);
+ vec = calloc(vec_size, sizeof(struct page_region));
if (!vec)
ksft_exit_fail_msg("error nomem\n");
@@ -491,7 +491,7 @@ int sanity_tests_sd(void)
mem_size = 10000 * page_size;
vec_size = 50;
- vec = malloc(sizeof(struct page_region) * vec_size);
+ vec = calloc(vec_size, sizeof(struct page_region));
if (!vec)
ksft_exit_fail_msg("error nomem\n");
@@ -541,7 +541,7 @@ int sanity_tests_sd(void)
vec_size = 1000;
mem_size = vec_size * page_size;
- vec = malloc(sizeof(struct page_region) * vec_size);
+ vec = calloc(vec_size, sizeof(struct page_region));
if (!vec)
ksft_exit_fail_msg("error nomem\n");
@@ -695,8 +695,8 @@ int base_tests(char *prefix, char *mem, unsigned long long mem_size, int skip)
}
vec_size = mem_size/page_size;
- vec = malloc(sizeof(struct page_region) * vec_size);
- vec2 = malloc(sizeof(struct page_region) * vec_size);
+ vec = calloc(vec_size, sizeof(struct page_region));
+ vec2 = calloc(vec_size, sizeof(struct page_region));
/* 1. all new pages must be not be written (dirty) */
written = pagemap_ioctl(mem, mem_size, vec, 1, PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC,
@@ -807,8 +807,8 @@ int hpage_unit_tests(void)
unsigned long long vec_size = map_size/page_size;
struct page_region *vec, *vec2;
- vec = malloc(sizeof(struct page_region) * vec_size);
- vec2 = malloc(sizeof(struct page_region) * vec_size);
+ vec = calloc(vec_size, sizeof(struct page_region));
+ vec2 = calloc(vec_size, sizeof(struct page_region));
if (!vec || !vec2)
ksft_exit_fail_msg("malloc failed\n");
@@ -997,7 +997,7 @@ int unmapped_region_tests(void)
void *start = (void *)0x10000000;
int written, len = 0x00040000;
long vec_size = len / page_size;
- struct page_region *vec = malloc(sizeof(struct page_region) * vec_size);
+ struct page_region *vec = calloc(vec_size, sizeof(struct page_region));
/* 1. Get written pages */
written = pagemap_ioctl(start, len, vec, vec_size, 0, 0,
@@ -1062,7 +1062,7 @@ int sanity_tests(void)
mem_size = 10 * page_size;
vec_size = mem_size / page_size;
- vec = malloc(sizeof(struct page_region) * vec_size);
+ vec = calloc(vec_size, sizeof(struct page_region));
mem = mmap(NULL, mem_size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANON, -1, 0);
if (mem == MAP_FAILED || vec == MAP_FAILED)
ksft_exit_fail_msg("error nomem\n");
diff --git a/tools/testing/selftests/mm/pfnmap.c b/tools/testing/selftests/mm/pfnmap.c
index 866ac023baf5..88659f0a90ea 100644
--- a/tools/testing/selftests/mm/pfnmap.c
+++ b/tools/testing/selftests/mm/pfnmap.c
@@ -1,6 +1,7 @@
// SPDX-License-Identifier: GPL-2.0-only
/*
- * Basic VM_PFNMAP tests relying on mmap() of '/dev/mem'
+ * Basic VM_PFNMAP tests relying on mmap() of input file provided.
+ * Use '/dev/mem' as default.
*
* Copyright 2025, Red Hat, Inc.
*
@@ -25,6 +26,7 @@
#include "vm_util.h"
static sigjmp_buf sigjmp_buf_env;
+static char *file = "/dev/mem";
static void signal_handler(int sig)
{
@@ -51,7 +53,7 @@ static int test_read_access(char *addr, size_t size, size_t pagesize)
return ret;
}
-static int find_ram_target(off_t *phys_addr,
+static int find_ram_target(off_t *offset,
unsigned long long pagesize)
{
unsigned long long start, end;
@@ -91,7 +93,7 @@ static int find_ram_target(off_t *phys_addr,
/* We need two pages. */
if (end > start + 2 * pagesize) {
fclose(file);
- *phys_addr = start;
+ *offset = start;
return 0;
}
}
@@ -100,7 +102,7 @@ static int find_ram_target(off_t *phys_addr,
FIXTURE(pfnmap)
{
- off_t phys_addr;
+ off_t offset;
size_t pagesize;
int dev_mem_fd;
char *addr1;
@@ -113,23 +115,31 @@ FIXTURE_SETUP(pfnmap)
{
self->pagesize = getpagesize();
- /* We'll require two physical pages throughout our tests ... */
- if (find_ram_target(&self->phys_addr, self->pagesize))
- SKIP(return, "Cannot find ram target in '/proc/iomem'\n");
+ if (strncmp(file, "/dev/mem", strlen("/dev/mem")) == 0) {
+ /* We'll require two physical pages throughout our tests ... */
+ if (find_ram_target(&self->offset, self->pagesize))
+ SKIP(return,
+ "Cannot find ram target in '/proc/iomem'\n");
+ } else {
+ self->offset = 0;
+ }
- self->dev_mem_fd = open("/dev/mem", O_RDONLY);
+ self->dev_mem_fd = open(file, O_RDONLY);
if (self->dev_mem_fd < 0)
- SKIP(return, "Cannot open '/dev/mem'\n");
+ SKIP(return, "Cannot open '%s'\n", file);
self->size1 = self->pagesize * 2;
self->addr1 = mmap(NULL, self->size1, PROT_READ, MAP_SHARED,
- self->dev_mem_fd, self->phys_addr);
+ self->dev_mem_fd, self->offset);
if (self->addr1 == MAP_FAILED)
- SKIP(return, "Cannot mmap '/dev/mem'\n");
+ SKIP(return, "Cannot mmap '%s'\n", file);
+
+ if (!check_vmflag_pfnmap(self->addr1))
+ SKIP(return, "Invalid file: '%s'. Not pfnmap'ed\n", file);
/* ... and want to be able to read from them. */
if (test_read_access(self->addr1, self->size1, self->pagesize))
- SKIP(return, "Cannot read-access mmap'ed '/dev/mem'\n");
+ SKIP(return, "Cannot read-access mmap'ed '%s'\n", file);
self->size2 = 0;
self->addr2 = MAP_FAILED;
@@ -182,7 +192,7 @@ TEST_F(pfnmap, munmap_split)
*/
self->size2 = self->pagesize;
self->addr2 = mmap(NULL, self->pagesize, PROT_READ, MAP_SHARED,
- self->dev_mem_fd, self->phys_addr);
+ self->dev_mem_fd, self->offset);
ASSERT_NE(self->addr2, MAP_FAILED);
}
@@ -246,4 +256,14 @@ TEST_F(pfnmap, fork)
ASSERT_EQ(ret, 0);
}
-TEST_HARNESS_MAIN
+int main(int argc, char **argv)
+{
+ for (int i = 1; i < argc; i++) {
+ if (strcmp(argv[i], "--") == 0) {
+ if (i + 1 < argc && strlen(argv[i + 1]) > 0)
+ file = argv[i + 1];
+ return test_harness_run(i, argv);
+ }
+ }
+ return test_harness_run(argc, argv);
+}
diff --git a/tools/testing/selftests/mm/pkey-helpers.h b/tools/testing/selftests/mm/pkey-helpers.h
index ea404f80e6cb..fa15f006fa68 100644
--- a/tools/testing/selftests/mm/pkey-helpers.h
+++ b/tools/testing/selftests/mm/pkey-helpers.h
@@ -84,9 +84,6 @@ extern void abort_hooks(void);
#ifndef noinline
# define noinline __attribute__((noinline))
#endif
-#ifndef __maybe_unused
-# define __maybe_unused __attribute__((__unused__))
-#endif
int sys_pkey_alloc(unsigned long flags, unsigned long init_val);
int sys_pkey_free(unsigned long pkey);
diff --git a/tools/testing/selftests/mm/pkey_sighandler_tests.c b/tools/testing/selftests/mm/pkey_sighandler_tests.c
index b5e076a564c9..302fef54049c 100644
--- a/tools/testing/selftests/mm/pkey_sighandler_tests.c
+++ b/tools/testing/selftests/mm/pkey_sighandler_tests.c
@@ -41,7 +41,7 @@ static siginfo_t siginfo = {0};
* syscall will attempt to access the PLT in order to call a library function
* which is protected by MPK 0 which we don't have access to.
*/
-static inline __always_inline
+static __always_inline
long syscall_raw(long n, long a1, long a2, long a3, long a4, long a5, long a6)
{
unsigned long ret;
diff --git a/tools/testing/selftests/mm/prctl_thp_disable.c b/tools/testing/selftests/mm/prctl_thp_disable.c
new file mode 100644
index 000000000000..84b4a4b345af
--- /dev/null
+++ b/tools/testing/selftests/mm/prctl_thp_disable.c
@@ -0,0 +1,291 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Basic tests for PR_GET/SET_THP_DISABLE prctl calls
+ *
+ * Author(s): Usama Arif <usamaarif642@gmail.com>
+ */
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/mman.h>
+#include <linux/mman.h>
+#include <sys/prctl.h>
+#include <sys/wait.h>
+
+#include "../kselftest_harness.h"
+#include "thp_settings.h"
+#include "vm_util.h"
+
+#ifndef PR_THP_DISABLE_EXCEPT_ADVISED
+#define PR_THP_DISABLE_EXCEPT_ADVISED (1 << 1)
+#endif
+
+enum thp_collapse_type {
+ THP_COLLAPSE_NONE,
+ THP_COLLAPSE_MADV_NOHUGEPAGE,
+ THP_COLLAPSE_MADV_HUGEPAGE, /* MADV_HUGEPAGE before access */
+ THP_COLLAPSE_MADV_COLLAPSE, /* MADV_COLLAPSE after access */
+};
+
+/*
+ * Function to mmap a buffer, fault it in, madvise it appropriately (before
+ * page fault for MADV_HUGE, and after for MADV_COLLAPSE), and check if the
+ * mmap region is huge.
+ * Returns:
+ * 0 if test doesn't give hugepage
+ * 1 if test gives a hugepage
+ * -errno if mmap fails
+ */
+static int test_mmap_thp(enum thp_collapse_type madvise_buf, size_t pmdsize)
+{
+ char *mem, *mmap_mem;
+ size_t mmap_size;
+ int ret;
+
+ /* For alignment purposes, we need twice the THP size. */
+ mmap_size = 2 * pmdsize;
+ mmap_mem = (char *)mmap(NULL, mmap_size, PROT_READ | PROT_WRITE,
+ MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+ if (mmap_mem == MAP_FAILED)
+ return -errno;
+
+ /* We need a THP-aligned memory area. */
+ mem = (char *)(((uintptr_t)mmap_mem + pmdsize) & ~(pmdsize - 1));
+
+ if (madvise_buf == THP_COLLAPSE_MADV_HUGEPAGE)
+ madvise(mem, pmdsize, MADV_HUGEPAGE);
+ else if (madvise_buf == THP_COLLAPSE_MADV_NOHUGEPAGE)
+ madvise(mem, pmdsize, MADV_NOHUGEPAGE);
+
+ /* Ensure memory is allocated */
+ memset(mem, 1, pmdsize);
+
+ if (madvise_buf == THP_COLLAPSE_MADV_COLLAPSE)
+ madvise(mem, pmdsize, MADV_COLLAPSE);
+
+ /* HACK: make sure we have a separate VMA that we can check reliably. */
+ mprotect(mem, pmdsize, PROT_READ);
+
+ ret = check_huge_anon(mem, 1, pmdsize);
+ munmap(mmap_mem, mmap_size);
+ return ret;
+}
+
+static void prctl_thp_disable_completely_test(struct __test_metadata *const _metadata,
+ size_t pmdsize,
+ enum thp_enabled thp_policy)
+{
+ ASSERT_EQ(prctl(PR_GET_THP_DISABLE, NULL, NULL, NULL, NULL), 1);
+
+ /* tests after prctl overrides global policy */
+ ASSERT_EQ(test_mmap_thp(THP_COLLAPSE_NONE, pmdsize), 0);
+
+ ASSERT_EQ(test_mmap_thp(THP_COLLAPSE_MADV_NOHUGEPAGE, pmdsize), 0);
+
+ ASSERT_EQ(test_mmap_thp(THP_COLLAPSE_MADV_HUGEPAGE, pmdsize), 0);
+
+ ASSERT_EQ(test_mmap_thp(THP_COLLAPSE_MADV_COLLAPSE, pmdsize), 0);
+
+ /* Reset to global policy */
+ ASSERT_EQ(prctl(PR_SET_THP_DISABLE, 0, NULL, NULL, NULL), 0);
+
+ /* tests after prctl is cleared, and only global policy is effective */
+ ASSERT_EQ(test_mmap_thp(THP_COLLAPSE_NONE, pmdsize),
+ thp_policy == THP_ALWAYS ? 1 : 0);
+
+ ASSERT_EQ(test_mmap_thp(THP_COLLAPSE_MADV_NOHUGEPAGE, pmdsize), 0);
+
+ ASSERT_EQ(test_mmap_thp(THP_COLLAPSE_MADV_HUGEPAGE, pmdsize),
+ thp_policy == THP_NEVER ? 0 : 1);
+
+ ASSERT_EQ(test_mmap_thp(THP_COLLAPSE_MADV_COLLAPSE, pmdsize), 1);
+}
+
+FIXTURE(prctl_thp_disable_completely)
+{
+ struct thp_settings settings;
+ size_t pmdsize;
+};
+
+FIXTURE_VARIANT(prctl_thp_disable_completely)
+{
+ enum thp_enabled thp_policy;
+};
+
+FIXTURE_VARIANT_ADD(prctl_thp_disable_completely, never)
+{
+ .thp_policy = THP_NEVER,
+};
+
+FIXTURE_VARIANT_ADD(prctl_thp_disable_completely, madvise)
+{
+ .thp_policy = THP_MADVISE,
+};
+
+FIXTURE_VARIANT_ADD(prctl_thp_disable_completely, always)
+{
+ .thp_policy = THP_ALWAYS,
+};
+
+FIXTURE_SETUP(prctl_thp_disable_completely)
+{
+ if (!thp_available())
+ SKIP(return, "Transparent Hugepages not available\n");
+
+ self->pmdsize = read_pmd_pagesize();
+ if (!self->pmdsize)
+ SKIP(return, "Unable to read PMD size\n");
+
+ if (prctl(PR_SET_THP_DISABLE, 1, NULL, NULL, NULL))
+ SKIP(return, "Unable to disable THPs completely for the process\n");
+
+ thp_save_settings();
+ thp_read_settings(&self->settings);
+ self->settings.thp_enabled = variant->thp_policy;
+ self->settings.hugepages[sz2ord(self->pmdsize, getpagesize())].enabled = THP_INHERIT;
+ thp_write_settings(&self->settings);
+}
+
+FIXTURE_TEARDOWN(prctl_thp_disable_completely)
+{
+ thp_restore_settings();
+}
+
+TEST_F(prctl_thp_disable_completely, nofork)
+{
+ prctl_thp_disable_completely_test(_metadata, self->pmdsize, variant->thp_policy);
+}
+
+TEST_F(prctl_thp_disable_completely, fork)
+{
+ int ret = 0;
+ pid_t pid;
+
+ /* Make sure prctl changes are carried across fork */
+ pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (!pid) {
+ prctl_thp_disable_completely_test(_metadata, self->pmdsize, variant->thp_policy);
+ return;
+ }
+
+ wait(&ret);
+ if (WIFEXITED(ret))
+ ret = WEXITSTATUS(ret);
+ else
+ ret = -EINVAL;
+ ASSERT_EQ(ret, 0);
+}
+
+static void prctl_thp_disable_except_madvise_test(struct __test_metadata *const _metadata,
+ size_t pmdsize,
+ enum thp_enabled thp_policy)
+{
+ ASSERT_EQ(prctl(PR_GET_THP_DISABLE, NULL, NULL, NULL, NULL), 3);
+
+ /* tests after prctl overrides global policy */
+ ASSERT_EQ(test_mmap_thp(THP_COLLAPSE_NONE, pmdsize), 0);
+
+ ASSERT_EQ(test_mmap_thp(THP_COLLAPSE_MADV_NOHUGEPAGE, pmdsize), 0);
+
+ ASSERT_EQ(test_mmap_thp(THP_COLLAPSE_MADV_HUGEPAGE, pmdsize),
+ thp_policy == THP_NEVER ? 0 : 1);
+
+ ASSERT_EQ(test_mmap_thp(THP_COLLAPSE_MADV_COLLAPSE, pmdsize), 1);
+
+ /* Reset to global policy */
+ ASSERT_EQ(prctl(PR_SET_THP_DISABLE, 0, NULL, NULL, NULL), 0);
+
+ /* tests after prctl is cleared, and only global policy is effective */
+ ASSERT_EQ(test_mmap_thp(THP_COLLAPSE_NONE, pmdsize),
+ thp_policy == THP_ALWAYS ? 1 : 0);
+
+ ASSERT_EQ(test_mmap_thp(THP_COLLAPSE_MADV_NOHUGEPAGE, pmdsize), 0);
+
+ ASSERT_EQ(test_mmap_thp(THP_COLLAPSE_MADV_HUGEPAGE, pmdsize),
+ thp_policy == THP_NEVER ? 0 : 1);
+
+ ASSERT_EQ(test_mmap_thp(THP_COLLAPSE_MADV_COLLAPSE, pmdsize), 1);
+}
+
+FIXTURE(prctl_thp_disable_except_madvise)
+{
+ struct thp_settings settings;
+ size_t pmdsize;
+};
+
+FIXTURE_VARIANT(prctl_thp_disable_except_madvise)
+{
+ enum thp_enabled thp_policy;
+};
+
+FIXTURE_VARIANT_ADD(prctl_thp_disable_except_madvise, never)
+{
+ .thp_policy = THP_NEVER,
+};
+
+FIXTURE_VARIANT_ADD(prctl_thp_disable_except_madvise, madvise)
+{
+ .thp_policy = THP_MADVISE,
+};
+
+FIXTURE_VARIANT_ADD(prctl_thp_disable_except_madvise, always)
+{
+ .thp_policy = THP_ALWAYS,
+};
+
+FIXTURE_SETUP(prctl_thp_disable_except_madvise)
+{
+ if (!thp_available())
+ SKIP(return, "Transparent Hugepages not available\n");
+
+ self->pmdsize = read_pmd_pagesize();
+ if (!self->pmdsize)
+ SKIP(return, "Unable to read PMD size\n");
+
+ if (prctl(PR_SET_THP_DISABLE, 1, PR_THP_DISABLE_EXCEPT_ADVISED, NULL, NULL))
+ SKIP(return, "Unable to set PR_THP_DISABLE_EXCEPT_ADVISED\n");
+
+ thp_save_settings();
+ thp_read_settings(&self->settings);
+ self->settings.thp_enabled = variant->thp_policy;
+ self->settings.hugepages[sz2ord(self->pmdsize, getpagesize())].enabled = THP_INHERIT;
+ thp_write_settings(&self->settings);
+}
+
+FIXTURE_TEARDOWN(prctl_thp_disable_except_madvise)
+{
+ thp_restore_settings();
+}
+
+TEST_F(prctl_thp_disable_except_madvise, nofork)
+{
+ prctl_thp_disable_except_madvise_test(_metadata, self->pmdsize, variant->thp_policy);
+}
+
+TEST_F(prctl_thp_disable_except_madvise, fork)
+{
+ int ret = 0;
+ pid_t pid;
+
+ /* Make sure prctl changes are carried across fork */
+ pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (!pid) {
+ prctl_thp_disable_except_madvise_test(_metadata, self->pmdsize,
+ variant->thp_policy);
+ return;
+ }
+
+ wait(&ret);
+ if (WIFEXITED(ret))
+ ret = WEXITSTATUS(ret);
+ else
+ ret = -EINVAL;
+ ASSERT_EQ(ret, 0);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/mm/protection_keys.c b/tools/testing/selftests/mm/protection_keys.c
index 23ebec367015..2085982dba69 100644
--- a/tools/testing/selftests/mm/protection_keys.c
+++ b/tools/testing/selftests/mm/protection_keys.c
@@ -557,13 +557,11 @@ int mprotect_pkey(void *ptr, size_t size, unsigned long orig_prot,
int nr_iterations = random() % 100;
int ret;
- while (0) {
+ while (nr_iterations-- >= 0) {
int rpkey = alloc_random_pkey();
ret = sys_mprotect_pkey(ptr, size, orig_prot, pkey);
dprintf1("sys_mprotect_pkey(%p, %zx, prot=0x%lx, pkey=%ld) ret: %d\n",
ptr, size, orig_prot, pkey, ret);
- if (nr_iterations-- < 0)
- break;
dprintf1("%s()::%d, ret: %d pkey_reg: 0x%016llx"
" shadow: 0x%016llx\n",
@@ -1304,7 +1302,7 @@ static void test_mprotect_with_pkey_0(int *ptr, u16 pkey)
static void test_ptrace_of_child(int *ptr, u16 pkey)
{
- __attribute__((__unused__)) int peek_result;
+ __always_unused int peek_result;
pid_t child_pid;
void *ignored = 0;
long ret;
diff --git a/tools/testing/selftests/mm/rmap.c b/tools/testing/selftests/mm/rmap.c
new file mode 100644
index 000000000000..13f7bccfd0a9
--- /dev/null
+++ b/tools/testing/selftests/mm/rmap.c
@@ -0,0 +1,433 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * RMAP functional tests
+ *
+ * Author(s): Wei Yang <richard.weiyang@gmail.com>
+ */
+
+#include "../kselftest_harness.h"
+#include <strings.h>
+#include <pthread.h>
+#include <numa.h>
+#include <numaif.h>
+#include <sys/mman.h>
+#include <sys/prctl.h>
+#include <sys/types.h>
+#include <signal.h>
+#include <time.h>
+#include <sys/sem.h>
+#include <unistd.h>
+#include <fcntl.h>
+
+#include "vm_util.h"
+
+#define TOTAL_LEVEL 5
+#define MAX_CHILDREN 3
+
+#define FAIL_ON_CHECK (1 << 0)
+#define FAIL_ON_WORK (1 << 1)
+
+struct sembuf sem_wait = {0, -1, 0};
+struct sembuf sem_signal = {0, 1, 0};
+
+enum backend_type {
+ ANON,
+ SHM,
+ NORM_FILE,
+};
+
+#define PREFIX "kst_rmap"
+#define MAX_FILENAME_LEN 256
+const char *suffixes[] = {
+ "",
+ "_shm",
+ "_file",
+};
+
+struct global_data;
+typedef int (*work_fn)(struct global_data *data);
+typedef int (*check_fn)(struct global_data *data);
+typedef void (*prepare_fn)(struct global_data *data);
+
+struct global_data {
+ int worker_level;
+
+ int semid;
+ int pipefd[2];
+
+ unsigned int mapsize;
+ unsigned int rand_seed;
+ char *region;
+
+ prepare_fn do_prepare;
+ work_fn do_work;
+ check_fn do_check;
+
+ enum backend_type backend;
+ char filename[MAX_FILENAME_LEN];
+
+ unsigned long *expected_pfn;
+};
+
+/*
+ * Create a process tree with TOTAL_LEVEL height and at most MAX_CHILDREN
+ * children for each.
+ *
+ * It will randomly select one process as 'worker' process which will
+ * 'do_work' until all processes are created. And all other processes will
+ * wait until 'worker' finish its work.
+ */
+void propagate_children(struct __test_metadata *_metadata, struct global_data *data)
+{
+ pid_t root_pid, pid;
+ unsigned int num_child;
+ int status;
+ int ret = 0;
+ int curr_child, worker_child;
+ int curr_level = 1;
+ bool is_worker = true;
+
+ root_pid = getpid();
+repeat:
+ num_child = rand_r(&data->rand_seed) % MAX_CHILDREN + 1;
+ worker_child = is_worker ? rand_r(&data->rand_seed) % num_child : -1;
+
+ for (curr_child = 0; curr_child < num_child; curr_child++) {
+ pid = fork();
+
+ if (pid < 0) {
+ perror("Error: fork\n");
+ } else if (pid == 0) {
+ curr_level++;
+
+ if (curr_child != worker_child)
+ is_worker = false;
+
+ if (curr_level == TOTAL_LEVEL)
+ break;
+
+ data->rand_seed += curr_child;
+ goto repeat;
+ }
+ }
+
+ if (data->do_prepare)
+ data->do_prepare(data);
+
+ close(data->pipefd[1]);
+
+ if (is_worker && curr_level == data->worker_level) {
+ /* This is the worker process, first wait last process created */
+ char buf;
+
+ while (read(data->pipefd[0], &buf, 1) > 0)
+ ;
+
+ if (data->do_work)
+ ret = data->do_work(data);
+
+ /* Kick others */
+ semctl(data->semid, 0, IPC_RMID);
+ } else {
+ /* Wait worker finish */
+ semop(data->semid, &sem_wait, 1);
+ if (data->do_check)
+ ret = data->do_check(data);
+ }
+
+ /* Wait all child to quit */
+ while (wait(&status) > 0) {
+ if (WIFEXITED(status))
+ ret |= WEXITSTATUS(status);
+ }
+
+ if (getpid() == root_pid) {
+ if (ret & FAIL_ON_WORK)
+ SKIP(return, "Failed in worker");
+
+ ASSERT_EQ(ret, 0);
+ } else {
+ exit(ret);
+ }
+}
+
+FIXTURE(migrate)
+{
+ struct global_data data;
+};
+
+FIXTURE_SETUP(migrate)
+{
+ struct global_data *data = &self->data;
+
+ if (numa_available() < 0)
+ SKIP(return, "NUMA not available");
+ if (numa_bitmask_weight(numa_all_nodes_ptr) <= 1)
+ SKIP(return, "Not enough NUMA nodes available");
+
+ data->mapsize = getpagesize();
+
+ data->expected_pfn = mmap(0, sizeof(unsigned long),
+ PROT_READ | PROT_WRITE,
+ MAP_SHARED | MAP_ANONYMOUS, -1, 0);
+ ASSERT_NE(data->expected_pfn, MAP_FAILED);
+
+ /* Prepare semaphore */
+ data->semid = semget(IPC_PRIVATE, 1, 0666 | IPC_CREAT);
+ ASSERT_NE(data->semid, -1);
+ ASSERT_NE(semctl(data->semid, 0, SETVAL, 0), -1);
+
+ /* Prepare pipe */
+ ASSERT_NE(pipe(data->pipefd), -1);
+
+ data->rand_seed = time(NULL);
+ srand(data->rand_seed);
+
+ data->worker_level = rand() % TOTAL_LEVEL + 1;
+
+ data->do_prepare = NULL;
+ data->do_work = NULL;
+ data->do_check = NULL;
+
+ data->backend = ANON;
+};
+
+FIXTURE_TEARDOWN(migrate)
+{
+ struct global_data *data = &self->data;
+
+ if (data->region != MAP_FAILED)
+ munmap(data->region, data->mapsize);
+ data->region = MAP_FAILED;
+ if (data->expected_pfn != MAP_FAILED)
+ munmap(data->expected_pfn, sizeof(unsigned long));
+ data->expected_pfn = MAP_FAILED;
+ semctl(data->semid, 0, IPC_RMID);
+ data->semid = -1;
+
+ close(data->pipefd[0]);
+
+ switch (data->backend) {
+ case ANON:
+ break;
+ case SHM:
+ shm_unlink(data->filename);
+ break;
+ case NORM_FILE:
+ unlink(data->filename);
+ break;
+ }
+}
+
+void access_region(struct global_data *data)
+{
+ /*
+ * Force read "region" to make sure page fault in.
+ */
+ FORCE_READ(*data->region);
+}
+
+int try_to_move_page(char *region)
+{
+ int ret;
+ int node;
+ int status = 0;
+ int failures = 0;
+
+ ret = move_pages(0, 1, (void **)&region, NULL, &status, MPOL_MF_MOVE_ALL);
+ if (ret != 0) {
+ perror("Failed to get original numa");
+ return FAIL_ON_WORK;
+ }
+
+ /* Pick up a different target node */
+ for (node = 0; node <= numa_max_node(); node++) {
+ if (numa_bitmask_isbitset(numa_all_nodes_ptr, node) && node != status)
+ break;
+ }
+
+ if (node > numa_max_node()) {
+ ksft_print_msg("Couldn't find available numa node for testing\n");
+ return FAIL_ON_WORK;
+ }
+
+ while (1) {
+ ret = move_pages(0, 1, (void **)&region, &node, &status, MPOL_MF_MOVE_ALL);
+
+ /* migrate successfully */
+ if (!ret)
+ break;
+
+ /* error happened */
+ if (ret < 0) {
+ ksft_perror("Failed to move pages");
+ return FAIL_ON_WORK;
+ }
+
+ /* migration is best effort; try again */
+ if (++failures >= 100)
+ return FAIL_ON_WORK;
+ }
+
+ return 0;
+}
+
+int move_region(struct global_data *data)
+{
+ int ret;
+ int pagemap_fd;
+
+ ret = try_to_move_page(data->region);
+ if (ret != 0)
+ return ret;
+
+ pagemap_fd = open("/proc/self/pagemap", O_RDONLY);
+ if (pagemap_fd == -1)
+ return FAIL_ON_WORK;
+ *data->expected_pfn = pagemap_get_pfn(pagemap_fd, data->region);
+
+ return 0;
+}
+
+int has_same_pfn(struct global_data *data)
+{
+ unsigned long pfn;
+ int pagemap_fd;
+
+ if (data->region == MAP_FAILED)
+ return 0;
+
+ pagemap_fd = open("/proc/self/pagemap", O_RDONLY);
+ if (pagemap_fd == -1)
+ return FAIL_ON_CHECK;
+
+ pfn = pagemap_get_pfn(pagemap_fd, data->region);
+ if (pfn != *data->expected_pfn)
+ return FAIL_ON_CHECK;
+
+ return 0;
+}
+
+TEST_F(migrate, anon)
+{
+ struct global_data *data = &self->data;
+
+ /* Map an area and fault in */
+ data->region = mmap(0, data->mapsize, PROT_READ | PROT_WRITE,
+ MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+ ASSERT_NE(data->region, MAP_FAILED);
+ memset(data->region, 0xcf, data->mapsize);
+
+ data->do_prepare = access_region;
+ data->do_work = move_region;
+ data->do_check = has_same_pfn;
+
+ propagate_children(_metadata, data);
+}
+
+TEST_F(migrate, shm)
+{
+ int shm_fd;
+ struct global_data *data = &self->data;
+
+ snprintf(data->filename, MAX_FILENAME_LEN, "%s%s", PREFIX, suffixes[SHM]);
+ shm_fd = shm_open(data->filename, O_CREAT | O_RDWR, 0666);
+ ASSERT_NE(shm_fd, -1);
+ ftruncate(shm_fd, data->mapsize);
+ data->backend = SHM;
+
+ /* Map a shared area and fault in */
+ data->region = mmap(0, data->mapsize, PROT_READ | PROT_WRITE,
+ MAP_SHARED, shm_fd, 0);
+ ASSERT_NE(data->region, MAP_FAILED);
+ memset(data->region, 0xcf, data->mapsize);
+ close(shm_fd);
+
+ data->do_prepare = access_region;
+ data->do_work = move_region;
+ data->do_check = has_same_pfn;
+
+ propagate_children(_metadata, data);
+}
+
+TEST_F(migrate, file)
+{
+ int fd;
+ struct global_data *data = &self->data;
+
+ snprintf(data->filename, MAX_FILENAME_LEN, "%s%s", PREFIX, suffixes[NORM_FILE]);
+ fd = open(data->filename, O_CREAT | O_RDWR | O_EXCL, 0666);
+ ASSERT_NE(fd, -1);
+ ftruncate(fd, data->mapsize);
+ data->backend = NORM_FILE;
+
+ /* Map a shared area and fault in */
+ data->region = mmap(0, data->mapsize, PROT_READ | PROT_WRITE,
+ MAP_SHARED, fd, 0);
+ ASSERT_NE(data->region, MAP_FAILED);
+ memset(data->region, 0xcf, data->mapsize);
+ close(fd);
+
+ data->do_prepare = access_region;
+ data->do_work = move_region;
+ data->do_check = has_same_pfn;
+
+ propagate_children(_metadata, data);
+}
+
+void prepare_local_region(struct global_data *data)
+{
+ /* Allocate range and set the same data */
+ data->region = mmap(NULL, data->mapsize, PROT_READ|PROT_WRITE,
+ MAP_PRIVATE|MAP_ANON, -1, 0);
+ if (data->region == MAP_FAILED)
+ return;
+
+ memset(data->region, 0xcf, data->mapsize);
+}
+
+int merge_and_migrate(struct global_data *data)
+{
+ int pagemap_fd;
+ int ret = 0;
+
+ if (data->region == MAP_FAILED)
+ return FAIL_ON_WORK;
+
+ if (ksm_start() < 0)
+ return FAIL_ON_WORK;
+
+ ret = try_to_move_page(data->region);
+
+ pagemap_fd = open("/proc/self/pagemap", O_RDONLY);
+ if (pagemap_fd == -1)
+ return FAIL_ON_WORK;
+ *data->expected_pfn = pagemap_get_pfn(pagemap_fd, data->region);
+
+ return ret;
+}
+
+TEST_F(migrate, ksm)
+{
+ int ret;
+ struct global_data *data = &self->data;
+
+ if (ksm_stop() < 0)
+ SKIP(return, "accessing \"/sys/kernel/mm/ksm/run\") failed");
+ if (ksm_get_full_scans() < 0)
+ SKIP(return, "accessing \"/sys/kernel/mm/ksm/full_scan\") failed");
+
+ ret = prctl(PR_SET_MEMORY_MERGE, 1, 0, 0, 0);
+ if (ret < 0 && errno == EINVAL)
+ SKIP(return, "PR_SET_MEMORY_MERGE not supported");
+ else if (ret)
+ ksft_exit_fail_perror("PR_SET_MEMORY_MERGE=1 failed");
+
+ data->do_prepare = prepare_local_region;
+ data->do_work = merge_and_migrate;
+ data->do_check = has_same_pfn;
+
+ propagate_children(_metadata, data);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh
index 471e539d82b8..d9173f2312b7 100755
--- a/tools/testing/selftests/mm/run_vmtests.sh
+++ b/tools/testing/selftests/mm/run_vmtests.sh
@@ -85,6 +85,8 @@ separated by spaces:
test handling of page fragment allocation and freeing
- vma_merge
test VMA merge cases behave as expected
+- rmap
+ test rmap behaves as expected
example: ./run_vmtests.sh -t "hmm mmap ksm"
EOF
@@ -136,7 +138,7 @@ run_gup_matrix() {
# -n: How many pages to fetch together? 512 is special
# because it's default thp size (or 2M on x86), 123 to
# just test partial gup when hit a huge in whatever form
- for num in "-n 1" "-n 512" "-n 123"; do
+ for num in "-n 1" "-n 512" "-n 123" "-n -1"; do
CATEGORY="gup_test" run_test ./gup_test \
$huge $test_cmd $write $share $num
done
@@ -172,13 +174,13 @@ fi
# set proper nr_hugepages
if [ -n "$freepgs" ] && [ -n "$hpgsize_KB" ]; then
- nr_hugepgs=$(cat /proc/sys/vm/nr_hugepages)
+ orig_nr_hugepgs=$(cat /proc/sys/vm/nr_hugepages)
needpgs=$((needmem_KB / hpgsize_KB))
tries=2
while [ "$tries" -gt 0 ] && [ "$freepgs" -lt "$needpgs" ]; do
lackpgs=$((needpgs - freepgs))
echo 3 > /proc/sys/vm/drop_caches
- if ! echo $((lackpgs + nr_hugepgs)) > /proc/sys/vm/nr_hugepages; then
+ if ! echo $((lackpgs + orig_nr_hugepgs)) > /proc/sys/vm/nr_hugepages; then
echo "Please run this test as root"
exit $ksft_skip
fi
@@ -189,6 +191,7 @@ if [ -n "$freepgs" ] && [ -n "$hpgsize_KB" ]; then
done < /proc/meminfo
tries=$((tries - 1))
done
+ nr_hugepgs=$(cat /proc/sys/vm/nr_hugepages)
if [ "$freepgs" -lt "$needpgs" ]; then
printf "Not enough huge pages available (%d < %d)\n" \
"$freepgs" "$needpgs"
@@ -311,9 +314,11 @@ if $RUN_ALL; then
run_gup_matrix
else
# get_user_pages_fast() benchmark
- CATEGORY="gup_test" run_test ./gup_test -u
+ CATEGORY="gup_test" run_test ./gup_test -u -n 1
+ CATEGORY="gup_test" run_test ./gup_test -u -n -1
# pin_user_pages_fast() benchmark
- CATEGORY="gup_test" run_test ./gup_test -a
+ CATEGORY="gup_test" run_test ./gup_test -a -n 1
+ CATEGORY="gup_test" run_test ./gup_test -a -n -1
fi
# Dump pages 0, 19, and 4096, using pin_user_pages:
CATEGORY="gup_test" run_test ./gup_test -ct -F 0x1 0 19 0x1000
@@ -322,11 +327,15 @@ CATEGORY="gup_test" run_test ./gup_longterm
CATEGORY="userfaultfd" run_test ./uffd-unit-tests
uffd_stress_bin=./uffd-stress
CATEGORY="userfaultfd" run_test ${uffd_stress_bin} anon 20 16
-# Hugetlb tests require source and destination huge pages. Pass in half
-# the size of the free pages we have, which is used for *each*.
+# Hugetlb tests require source and destination huge pages. Pass in almost half
+# the size of the free pages we have, which is used for *each*. An adjustment
+# of (nr_parallel - 1) is done (see nr_parallel in uffd-stress.c) to have some
+# extra hugepages - this is done to prevent the test from failing by racily
+# reserving more hugepages than strictly required.
# uffd-stress expects a region expressed in MiB, so we adjust
# half_ufd_size_MB accordingly.
-half_ufd_size_MB=$(((freepgs * hpgsize_KB) / 1024 / 2))
+adjustment=$(( (31 < (nr_cpus - 1)) ? 31 : (nr_cpus - 1) ))
+half_ufd_size_MB=$((((freepgs - adjustment) * hpgsize_KB) / 1024 / 2))
CATEGORY="userfaultfd" run_test ${uffd_stress_bin} hugetlb "$half_ufd_size_MB" 32
CATEGORY="userfaultfd" run_test ${uffd_stress_bin} hugetlb-private "$half_ufd_size_MB" 32
CATEGORY="userfaultfd" run_test ${uffd_stress_bin} shmem 20 16
@@ -532,6 +541,12 @@ CATEGORY="page_frag" run_test ./test_page_frag.sh aligned
CATEGORY="page_frag" run_test ./test_page_frag.sh nonaligned
+CATEGORY="rmap" run_test ./rmap
+
+if [ "${HAVE_HUGEPAGES}" = 1 ]; then
+ echo "$orig_nr_hugepgs" > /proc/sys/vm/nr_hugepages
+fi
+
echo "SUMMARY: PASS=${count_pass} SKIP=${count_skip} FAIL=${count_fail}" | tap_prefix
echo "1..${count_total}" | tap_output
diff --git a/tools/testing/selftests/mm/soft-dirty.c b/tools/testing/selftests/mm/soft-dirty.c
index 8a3f2b4b2186..4ee4db3750c1 100644
--- a/tools/testing/selftests/mm/soft-dirty.c
+++ b/tools/testing/selftests/mm/soft-dirty.c
@@ -200,8 +200,11 @@ int main(int argc, char **argv)
int pagesize;
ksft_print_header();
- ksft_set_plan(15);
+ if (!softdirty_supported())
+ ksft_exit_skip("soft-dirty is not support\n");
+
+ ksft_set_plan(15);
pagemap_fd = open(PAGEMAP_FILE_PATH, O_RDONLY);
if (pagemap_fd < 0)
ksft_exit_fail_msg("Failed to open %s\n", PAGEMAP_FILE_PATH);
diff --git a/tools/testing/selftests/mm/split_huge_page_test.c b/tools/testing/selftests/mm/split_huge_page_test.c
index 44a3f8a58806..743af3c05190 100644
--- a/tools/testing/selftests/mm/split_huge_page_test.c
+++ b/tools/testing/selftests/mm/split_huge_page_test.c
@@ -25,6 +25,8 @@
uint64_t pagesize;
unsigned int pageshift;
uint64_t pmd_pagesize;
+unsigned int pmd_order;
+int *expected_orders;
#define SPLIT_DEBUGFS "/sys/kernel/debug/split_huge_pages"
#define SMAP_PATH "/proc/self/smaps"
@@ -34,28 +36,225 @@ uint64_t pmd_pagesize;
#define PID_FMT_OFFSET "%d,0x%lx,0x%lx,%d,%d"
#define PATH_FMT "%s,0x%lx,0x%lx,%d"
-#define PFN_MASK ((1UL<<55)-1)
-#define KPF_THP (1UL<<22)
+const char *pagemap_proc = "/proc/self/pagemap";
+const char *kpageflags_proc = "/proc/kpageflags";
+int pagemap_fd;
+int kpageflags_fd;
-int is_backed_by_thp(char *vaddr, int pagemap_file, int kpageflags_file)
+static bool is_backed_by_folio(char *vaddr, int order, int pagemap_fd,
+ int kpageflags_fd)
{
- uint64_t paddr;
- uint64_t page_flags;
+ const uint64_t folio_head_flags = KPF_THP | KPF_COMPOUND_HEAD;
+ const uint64_t folio_tail_flags = KPF_THP | KPF_COMPOUND_TAIL;
+ const unsigned long nr_pages = 1UL << order;
+ unsigned long pfn_head;
+ uint64_t pfn_flags;
+ unsigned long pfn;
+ unsigned long i;
+
+ pfn = pagemap_get_pfn(pagemap_fd, vaddr);
+
+ /* non present page */
+ if (pfn == -1UL)
+ return false;
+
+ if (pageflags_get(pfn, kpageflags_fd, &pfn_flags))
+ goto fail;
+
+ /* check for order-0 pages */
+ if (!order) {
+ if (pfn_flags & (folio_head_flags | folio_tail_flags))
+ return false;
+ return true;
+ }
+
+ /* non THP folio */
+ if (!(pfn_flags & KPF_THP))
+ return false;
+
+ pfn_head = pfn & ~(nr_pages - 1);
+
+ if (pageflags_get(pfn_head, kpageflags_fd, &pfn_flags))
+ goto fail;
+
+ /* head PFN has no compound_head flag set */
+ if ((pfn_flags & folio_head_flags) != folio_head_flags)
+ return false;
+
+ /* check all tail PFN flags */
+ for (i = 1; i < nr_pages; i++) {
+ if (pageflags_get(pfn_head + i, kpageflags_fd, &pfn_flags))
+ goto fail;
+ if ((pfn_flags & folio_tail_flags) != folio_tail_flags)
+ return false;
+ }
+
+ /*
+ * check the PFN after this folio, but if its flags cannot be obtained,
+ * assume this folio has the expected order
+ */
+ if (pageflags_get(pfn_head + nr_pages, kpageflags_fd, &pfn_flags))
+ return true;
+
+ /* If we find another tail page, then the folio is larger. */
+ return (pfn_flags & folio_tail_flags) != folio_tail_flags;
+fail:
+ ksft_exit_fail_msg("Failed to get folio info\n");
+ return false;
+}
+
+static int vaddr_pageflags_get(char *vaddr, int pagemap_fd, int kpageflags_fd,
+ uint64_t *flags)
+{
+ unsigned long pfn;
+
+ pfn = pagemap_get_pfn(pagemap_fd, vaddr);
+
+ /* non-present PFN */
+ if (pfn == -1UL)
+ return 1;
+
+ if (pageflags_get(pfn, kpageflags_fd, flags))
+ return -1;
+
+ return 0;
+}
+
+/*
+ * gather_after_split_folio_orders - scan through [vaddr_start, len) and record
+ * folio orders
+ *
+ * @vaddr_start: start vaddr
+ * @len: range length
+ * @pagemap_fd: file descriptor to /proc/<pid>/pagemap
+ * @kpageflags_fd: file descriptor to /proc/kpageflags
+ * @orders: output folio order array
+ * @nr_orders: folio order array size
+ *
+ * gather_after_split_folio_orders() scan through [vaddr_start, len) and check
+ * all folios within the range and record their orders. All order-0 pages will
+ * be recorded. Non-present vaddr is skipped.
+ *
+ * NOTE: the function is used to check folio orders after a split is performed,
+ * so it assumes [vaddr_start, len) fully maps to after-split folios within that
+ * range.
+ *
+ * Return: 0 - no error, -1 - unhandled cases
+ */
+static int gather_after_split_folio_orders(char *vaddr_start, size_t len,
+ int pagemap_fd, int kpageflags_fd, int orders[], int nr_orders)
+{
+ uint64_t page_flags = 0;
+ int cur_order = -1;
+ char *vaddr;
+
+ if (pagemap_fd == -1 || kpageflags_fd == -1)
+ return -1;
+ if (!orders)
+ return -1;
+ if (nr_orders <= 0)
+ return -1;
+
+ for (vaddr = vaddr_start; vaddr < vaddr_start + len;) {
+ char *next_folio_vaddr;
+ int status;
+
+ status = vaddr_pageflags_get(vaddr, pagemap_fd, kpageflags_fd,
+ &page_flags);
+ if (status < 0)
+ return -1;
+
+ /* skip non present vaddr */
+ if (status == 1) {
+ vaddr += psize();
+ continue;
+ }
- if (pagemap_file) {
- pread(pagemap_file, &paddr, sizeof(paddr),
- ((long)vaddr >> pageshift) * sizeof(paddr));
+ /* all order-0 pages with possible false postive (non folio) */
+ if (!(page_flags & (KPF_COMPOUND_HEAD | KPF_COMPOUND_TAIL))) {
+ orders[0]++;
+ vaddr += psize();
+ continue;
+ }
- if (kpageflags_file) {
- pread(kpageflags_file, &page_flags, sizeof(page_flags),
- (paddr & PFN_MASK) * sizeof(page_flags));
+ /* skip non thp compound pages */
+ if (!(page_flags & KPF_THP)) {
+ vaddr += psize();
+ continue;
+ }
- return !!(page_flags & KPF_THP);
+ /* vpn points to part of a THP at this point */
+ if (page_flags & KPF_COMPOUND_HEAD)
+ cur_order = 1;
+ else {
+ vaddr += psize();
+ continue;
}
+
+ next_folio_vaddr = vaddr + (1UL << (cur_order + pshift()));
+
+ if (next_folio_vaddr >= vaddr_start + len)
+ break;
+
+ while ((status = vaddr_pageflags_get(next_folio_vaddr,
+ pagemap_fd, kpageflags_fd,
+ &page_flags)) >= 0) {
+ /*
+ * non present vaddr, next compound head page, or
+ * order-0 page
+ */
+ if (status == 1 ||
+ (page_flags & KPF_COMPOUND_HEAD) ||
+ !(page_flags & (KPF_COMPOUND_HEAD | KPF_COMPOUND_TAIL))) {
+ if (cur_order < nr_orders) {
+ orders[cur_order]++;
+ cur_order = -1;
+ vaddr = next_folio_vaddr;
+ }
+ break;
+ }
+
+ cur_order++;
+ next_folio_vaddr = vaddr + (1UL << (cur_order + pshift()));
+ }
+
+ if (status < 0)
+ return status;
}
+ if (cur_order > 0 && cur_order < nr_orders)
+ orders[cur_order]++;
return 0;
}
+static int check_after_split_folio_orders(char *vaddr_start, size_t len,
+ int pagemap_fd, int kpageflags_fd, int orders[], int nr_orders)
+{
+ int *vaddr_orders;
+ int status;
+ int i;
+
+ vaddr_orders = (int *)malloc(sizeof(int) * nr_orders);
+
+ if (!vaddr_orders)
+ ksft_exit_fail_msg("Cannot allocate memory for vaddr_orders");
+
+ memset(vaddr_orders, 0, sizeof(int) * nr_orders);
+ status = gather_after_split_folio_orders(vaddr_start, len, pagemap_fd,
+ kpageflags_fd, vaddr_orders, nr_orders);
+ if (status)
+ ksft_exit_fail_msg("gather folio info failed\n");
+
+ for (i = 0; i < nr_orders; i++)
+ if (vaddr_orders[i] != orders[i]) {
+ ksft_print_msg("order %d: expected: %d got %d\n", i,
+ orders[i], vaddr_orders[i]);
+ status = -1;
+ }
+
+ free(vaddr_orders);
+ return status;
+}
+
static void write_file(const char *path, const char *buf, size_t buflen)
{
int fd;
@@ -111,7 +310,7 @@ static void verify_rss_anon_split_huge_page_all_zeroes(char *one_page, int nr_hp
unsigned long rss_anon_before, rss_anon_after;
size_t i;
- if (!check_huge_anon(one_page, 4, pmd_pagesize))
+ if (!check_huge_anon(one_page, nr_hpages, pmd_pagesize))
ksft_exit_fail_msg("No THP is allocated\n");
rss_anon_before = rss_anon();
@@ -135,7 +334,7 @@ static void verify_rss_anon_split_huge_page_all_zeroes(char *one_page, int nr_hp
rss_anon_before, rss_anon_after);
}
-void split_pmd_zero_pages(void)
+static void split_pmd_zero_pages(void)
{
char *one_page;
int nr_hpages = 4;
@@ -147,7 +346,7 @@ void split_pmd_zero_pages(void)
free(one_page);
}
-void split_pmd_thp_to_order(int order)
+static void split_pmd_thp_to_order(int order)
{
char *one_page;
size_t len = 4 * pmd_pagesize;
@@ -173,6 +372,13 @@ void split_pmd_thp_to_order(int order)
if (one_page[i] != (char)i)
ksft_exit_fail_msg("%ld byte corrupted\n", i);
+ memset(expected_orders, 0, sizeof(int) * (pmd_order + 1));
+ expected_orders[order] = 4 << (pmd_order - order);
+
+ if (check_after_split_folio_orders(one_page, len, pagemap_fd,
+ kpageflags_fd, expected_orders,
+ (pmd_order + 1)))
+ ksft_exit_fail_msg("Unexpected THP split\n");
if (!check_huge_anon(one_page, 0, pmd_pagesize))
ksft_exit_fail_msg("Still AnonHugePages not split\n");
@@ -181,90 +387,97 @@ void split_pmd_thp_to_order(int order)
free(one_page);
}
-void split_pte_mapped_thp(void)
+static void split_pte_mapped_thp(void)
{
- char *one_page, *pte_mapped, *pte_mapped2;
- size_t len = 4 * pmd_pagesize;
- uint64_t thp_size;
+ const size_t nr_thps = 4;
+ const size_t thp_area_size = nr_thps * pmd_pagesize;
+ const size_t page_area_size = nr_thps * pagesize;
+ char *thp_area, *tmp, *page_area = MAP_FAILED;
size_t i;
- const char *pagemap_template = "/proc/%d/pagemap";
- const char *kpageflags_proc = "/proc/kpageflags";
- char pagemap_proc[255];
- int pagemap_fd;
- int kpageflags_fd;
- if (snprintf(pagemap_proc, 255, pagemap_template, getpid()) < 0)
- ksft_exit_fail_msg("get pagemap proc error: %s\n", strerror(errno));
+ thp_area = mmap((void *)(1UL << 30), thp_area_size, PROT_READ | PROT_WRITE,
+ MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
+ if (thp_area == MAP_FAILED) {
+ ksft_test_result_fail("Fail to allocate memory: %s\n", strerror(errno));
+ return;
+ }
- pagemap_fd = open(pagemap_proc, O_RDONLY);
- if (pagemap_fd == -1)
- ksft_exit_fail_msg("read pagemap: %s\n", strerror(errno));
+ madvise(thp_area, thp_area_size, MADV_HUGEPAGE);
- kpageflags_fd = open(kpageflags_proc, O_RDONLY);
- if (kpageflags_fd == -1)
- ksft_exit_fail_msg("read kpageflags: %s\n", strerror(errno));
+ for (i = 0; i < thp_area_size; i++)
+ thp_area[i] = (char)i;
- one_page = mmap((void *)(1UL << 30), len, PROT_READ | PROT_WRITE,
- MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
- if (one_page == MAP_FAILED)
- ksft_exit_fail_msg("Fail to allocate memory: %s\n", strerror(errno));
+ if (!check_huge_anon(thp_area, nr_thps, pmd_pagesize)) {
+ ksft_test_result_skip("Not all THPs allocated\n");
+ goto out;
+ }
- madvise(one_page, len, MADV_HUGEPAGE);
+ /*
+ * To challenge spitting code, we will mremap a single page of each
+ * THP (page[i] of thp[i]) in the thp_area into page_area. This will
+ * replace the PMD mappings in the thp_area by PTE mappings first,
+ * but leaving the THP unsplit, to then create a page-sized hole in
+ * the thp_area.
+ * We will then manually trigger splitting of all THPs through the
+ * single mremap'ed pages of each THP in the page_area.
+ */
+ page_area = mmap(NULL, page_area_size, PROT_READ | PROT_WRITE,
+ MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
+ if (page_area == MAP_FAILED) {
+ ksft_test_result_fail("Fail to allocate memory: %s\n", strerror(errno));
+ goto out;
+ }
- for (i = 0; i < len; i++)
- one_page[i] = (char)i;
+ for (i = 0; i < nr_thps; i++) {
+ tmp = mremap(thp_area + pmd_pagesize * i + pagesize * i,
+ pagesize, pagesize, MREMAP_MAYMOVE|MREMAP_FIXED,
+ page_area + pagesize * i);
+ if (tmp != MAP_FAILED)
+ continue;
+ ksft_test_result_fail("mremap failed: %s\n", strerror(errno));
+ goto out;
+ }
- if (!check_huge_anon(one_page, 4, pmd_pagesize))
- ksft_exit_fail_msg("No THP is allocated\n");
+ /*
+ * Verify that our THPs were not split yet. Note that
+ * check_huge_anon() cannot be used as it checks for PMD mappings.
+ */
+ for (i = 0; i < nr_thps; i++) {
+ if (is_backed_by_folio(page_area + i * pagesize, pmd_order,
+ pagemap_fd, kpageflags_fd))
+ continue;
+ ksft_test_result_fail("THP %zu missing after mremap\n", i);
+ goto out;
+ }
- /* remap the first pagesize of first THP */
- pte_mapped = mremap(one_page, pagesize, pagesize, MREMAP_MAYMOVE);
-
- /* remap the Nth pagesize of Nth THP */
- for (i = 1; i < 4; i++) {
- pte_mapped2 = mremap(one_page + pmd_pagesize * i + pagesize * i,
- pagesize, pagesize,
- MREMAP_MAYMOVE|MREMAP_FIXED,
- pte_mapped + pagesize * i);
- if (pte_mapped2 == MAP_FAILED)
- ksft_exit_fail_msg("mremap failed: %s\n", strerror(errno));
- }
-
- /* smap does not show THPs after mremap, use kpageflags instead */
- thp_size = 0;
- for (i = 0; i < pagesize * 4; i++)
- if (i % pagesize == 0 &&
- is_backed_by_thp(&pte_mapped[i], pagemap_fd, kpageflags_fd))
- thp_size++;
-
- if (thp_size != 4)
- ksft_exit_fail_msg("Some THPs are missing during mremap\n");
-
- /* split all remapped THPs */
- write_debugfs(PID_FMT, getpid(), (uint64_t)pte_mapped,
- (uint64_t)pte_mapped + pagesize * 4, 0);
-
- /* smap does not show THPs after mremap, use kpageflags instead */
- thp_size = 0;
- for (i = 0; i < pagesize * 4; i++) {
- if (pte_mapped[i] != (char)i)
- ksft_exit_fail_msg("%ld byte corrupted\n", i);
+ /* Split all THPs through the remapped pages. */
+ write_debugfs(PID_FMT, getpid(), (uint64_t)page_area,
+ (uint64_t)page_area + page_area_size, 0);
- if (i % pagesize == 0 &&
- is_backed_by_thp(&pte_mapped[i], pagemap_fd, kpageflags_fd))
- thp_size++;
+ /* Corruption during mremap or split? */
+ for (i = 0; i < page_area_size; i++) {
+ if (page_area[i] == (char)i)
+ continue;
+ ksft_test_result_fail("%zu byte corrupted\n", i);
+ goto out;
}
- if (thp_size)
- ksft_exit_fail_msg("Still %ld THPs not split\n", thp_size);
+ /* Split failed? */
+ for (i = 0; i < nr_thps; i++) {
+ if (is_backed_by_folio(page_area + i * pagesize, 0,
+ pagemap_fd, kpageflags_fd))
+ continue;
+ ksft_test_result_fail("THP %zu not split\n", i);
+ }
ksft_test_result_pass("Split PTE-mapped huge pages successful\n");
- munmap(one_page, len);
- close(pagemap_fd);
- close(kpageflags_fd);
+out:
+ munmap(thp_area, thp_area_size);
+ if (page_area != MAP_FAILED)
+ munmap(page_area, page_area_size);
}
-void split_file_backed_thp(int order)
+static void split_file_backed_thp(int order)
{
int status;
int fd;
@@ -297,7 +510,7 @@ void split_file_backed_thp(int order)
status = snprintf(testfile, INPUT_MAX, "%s/thp_file", tmpfs_loc);
if (status >= INPUT_MAX) {
- ksft_exit_fail_msg("Fail to create file-backed THP split testing file\n");
+ ksft_print_msg("Fail to create file-backed THP split testing file\n");
goto cleanup;
}
@@ -366,7 +579,7 @@ out:
ksft_exit_fail_msg("Error occurred\n");
}
-bool prepare_thp_fs(const char *xfs_path, char *thp_fs_template,
+static bool prepare_thp_fs(const char *xfs_path, char *thp_fs_template,
const char **thp_fs_loc)
{
if (xfs_path) {
@@ -382,7 +595,7 @@ bool prepare_thp_fs(const char *xfs_path, char *thp_fs_template,
return true;
}
-void cleanup_thp_fs(const char *thp_fs_loc, bool created_tmp)
+static void cleanup_thp_fs(const char *thp_fs_loc, bool created_tmp)
{
int status;
@@ -395,8 +608,8 @@ void cleanup_thp_fs(const char *thp_fs_loc, bool created_tmp)
strerror(errno));
}
-int create_pagecache_thp_and_fd(const char *testfile, size_t fd_size, int *fd,
- char **addr)
+static int create_pagecache_thp_and_fd(const char *testfile, size_t fd_size,
+ int *fd, char **addr)
{
size_t i;
unsigned char buf[1024];
@@ -462,10 +675,11 @@ err_out_unlink:
return -1;
}
-void split_thp_in_pagecache_to_order_at(size_t fd_size, const char *fs_loc,
- int order, int offset)
+static void split_thp_in_pagecache_to_order_at(size_t fd_size,
+ const char *fs_loc, int order, int offset)
{
int fd;
+ char *split_addr;
char *addr;
size_t i;
char testfile[INPUT_MAX];
@@ -479,14 +693,33 @@ void split_thp_in_pagecache_to_order_at(size_t fd_size, const char *fs_loc,
err = create_pagecache_thp_and_fd(testfile, fd_size, &fd, &addr);
if (err)
return;
+
err = 0;
- if (offset == -1)
- write_debugfs(PID_FMT, getpid(), (uint64_t)addr,
- (uint64_t)addr + fd_size, order);
- else
- write_debugfs(PID_FMT_OFFSET, getpid(), (uint64_t)addr,
- (uint64_t)addr + fd_size, order, offset);
+ memset(expected_orders, 0, sizeof(int) * (pmd_order + 1));
+ /*
+ * use [split_addr, split_addr + pagesize) range to split THPs, since
+ * the debugfs function always split a range with pagesize step and
+ * providing a full [addr, addr + fd_size) range can trigger multiple
+ * splits, complicating after-split result checking.
+ */
+ if (offset == -1) {
+ for (split_addr = addr; split_addr < addr + fd_size; split_addr += pmd_pagesize)
+ write_debugfs(PID_FMT, getpid(), (uint64_t)split_addr,
+ (uint64_t)split_addr + pagesize, order);
+
+ expected_orders[order] = fd_size / (pagesize << order);
+ } else {
+ int times = fd_size / pmd_pagesize;
+
+ for (split_addr = addr; split_addr < addr + fd_size; split_addr += pmd_pagesize)
+ write_debugfs(PID_FMT_OFFSET, getpid(), (uint64_t)split_addr,
+ (uint64_t)split_addr + pagesize, order, offset);
+
+ for (i = order + 1; i < pmd_order; i++)
+ expected_orders[i] = times;
+ expected_orders[order] = 2 * times;
+ }
for (i = 0; i < fd_size; i++)
if (*(addr + i) != (char)i) {
@@ -495,6 +728,14 @@ void split_thp_in_pagecache_to_order_at(size_t fd_size, const char *fs_loc,
goto out;
}
+ if (check_after_split_folio_orders(addr, fd_size, pagemap_fd,
+ kpageflags_fd, expected_orders,
+ (pmd_order + 1))) {
+ ksft_print_msg("Unexpected THP split\n");
+ err = 1;
+ goto out;
+ }
+
if (!check_huge_file(addr, 0, pmd_pagesize)) {
ksft_print_msg("Still FilePmdMapped not split\n");
err = EXIT_FAILURE;
@@ -525,6 +766,8 @@ int main(int argc, char **argv)
const char *fs_loc;
bool created_tmp;
int offset;
+ unsigned int nr_pages;
+ unsigned int tests;
ksft_print_header();
@@ -536,38 +779,58 @@ int main(int argc, char **argv)
if (argc > 1)
optional_xfs_path = argv[1];
- ksft_set_plan(1+8+1+9+9+8*4+2);
-
pagesize = getpagesize();
pageshift = ffs(pagesize) - 1;
pmd_pagesize = read_pmd_pagesize();
if (!pmd_pagesize)
ksft_exit_fail_msg("Reading PMD pagesize failed\n");
+ nr_pages = pmd_pagesize / pagesize;
+ pmd_order = sz2ord(pmd_pagesize, pagesize);
+
+ expected_orders = (int *)malloc(sizeof(int) * (pmd_order + 1));
+ if (!expected_orders)
+ ksft_exit_fail_msg("Fail to allocate memory: %s\n", strerror(errno));
+
+ tests = 2 + (pmd_order - 1) + (2 * pmd_order) + (pmd_order - 1) * 4 + 2;
+ ksft_set_plan(tests);
+
+ pagemap_fd = open(pagemap_proc, O_RDONLY);
+ if (pagemap_fd == -1)
+ ksft_exit_fail_msg("read pagemap: %s\n", strerror(errno));
+
+ kpageflags_fd = open(kpageflags_proc, O_RDONLY);
+ if (kpageflags_fd == -1)
+ ksft_exit_fail_msg("read kpageflags: %s\n", strerror(errno));
+
fd_size = 2 * pmd_pagesize;
split_pmd_zero_pages();
- for (i = 0; i < 9; i++)
+ for (i = 0; i < pmd_order; i++)
if (i != 1)
split_pmd_thp_to_order(i);
split_pte_mapped_thp();
- for (i = 0; i < 9; i++)
+ for (i = 0; i < pmd_order; i++)
split_file_backed_thp(i);
created_tmp = prepare_thp_fs(optional_xfs_path, fs_loc_template,
&fs_loc);
- for (i = 8; i >= 0; i--)
+ for (i = pmd_order - 1; i >= 0; i--)
split_thp_in_pagecache_to_order_at(fd_size, fs_loc, i, -1);
- for (i = 0; i < 9; i++)
+ for (i = 0; i < pmd_order; i++)
for (offset = 0;
- offset < pmd_pagesize / pagesize;
- offset += MAX(pmd_pagesize / pagesize / 4, 1 << i))
+ offset < nr_pages;
+ offset += MAX(nr_pages / 4, 1 << i))
split_thp_in_pagecache_to_order_at(fd_size, fs_loc, i, offset);
cleanup_thp_fs(fs_loc, created_tmp);
+ close(pagemap_fd);
+ close(kpageflags_fd);
+ free(expected_orders);
+
ksft_finished();
return 0;
diff --git a/tools/testing/selftests/mm/test_vmalloc.sh b/tools/testing/selftests/mm/test_vmalloc.sh
index d73b846736f1..d39096723fca 100755
--- a/tools/testing/selftests/mm/test_vmalloc.sh
+++ b/tools/testing/selftests/mm/test_vmalloc.sh
@@ -47,14 +47,14 @@ check_test_requirements()
fi
}
-run_perfformance_check()
+run_performance_check()
{
echo "Run performance tests to evaluate how fast vmalloc allocation is."
echo "It runs all test cases on one single CPU with sequential order."
modprobe $DRIVER $PERF_PARAM > /dev/null 2>&1
echo "Done."
- echo "Ccheck the kernel message buffer to see the summary."
+ echo "Check the kernel message buffer to see the summary."
}
run_stability_check()
@@ -160,7 +160,7 @@ function run_test()
usage
else
if [[ "$1" = "performance" ]]; then
- run_perfformance_check
+ run_performance_check
elif [[ "$1" = "stress" ]]; then
run_stability_check
elif [[ "$1" = "smoke" ]]; then
diff --git a/tools/testing/selftests/mm/thp_settings.c b/tools/testing/selftests/mm/thp_settings.c
index bad60ac52874..574bd0f8ae48 100644
--- a/tools/testing/selftests/mm/thp_settings.c
+++ b/tools/testing/selftests/mm/thp_settings.c
@@ -382,10 +382,17 @@ unsigned long thp_shmem_supported_orders(void)
return __thp_supported_orders(true);
}
-bool thp_is_enabled(void)
+bool thp_available(void)
{
if (access(THP_SYSFS, F_OK) != 0)
return false;
+ return true;
+}
+
+bool thp_is_enabled(void)
+{
+ if (!thp_available())
+ return false;
int mode = thp_read_string("enabled", thp_enabled_strings);
diff --git a/tools/testing/selftests/mm/thp_settings.h b/tools/testing/selftests/mm/thp_settings.h
index 6c07f70beee9..76eeb712e5f1 100644
--- a/tools/testing/selftests/mm/thp_settings.h
+++ b/tools/testing/selftests/mm/thp_settings.h
@@ -84,6 +84,7 @@ void thp_set_read_ahead_path(char *path);
unsigned long thp_supported_orders(void);
unsigned long thp_shmem_supported_orders(void);
+bool thp_available(void);
bool thp_is_enabled(void);
#endif /* __THP_SETTINGS_H__ */
diff --git a/tools/testing/selftests/mm/thuge-gen.c b/tools/testing/selftests/mm/thuge-gen.c
index 8e2b08dc5762..4f5e290ff1a6 100644
--- a/tools/testing/selftests/mm/thuge-gen.c
+++ b/tools/testing/selftests/mm/thuge-gen.c
@@ -177,13 +177,16 @@ void find_pagesizes(void)
globfree(&g);
read_sysfs("/proc/sys/kernel/shmmax", &shmmax_val);
- if (shmmax_val < NUM_PAGES * largest)
- ksft_exit_fail_msg("Please do echo %lu > /proc/sys/kernel/shmmax",
- largest * NUM_PAGES);
+ if (shmmax_val < NUM_PAGES * largest) {
+ ksft_print_msg("WARNING: shmmax is too small to run this test.\n");
+ ksft_print_msg("Please run the following command to increase shmmax:\n");
+ ksft_print_msg("echo %lu > /proc/sys/kernel/shmmax\n", largest * NUM_PAGES);
+ ksft_exit_skip("Test skipped due to insufficient shmmax value.\n");
+ }
#if defined(__x86_64__)
if (largest != 1U<<30) {
- ksft_exit_fail_msg("No GB pages available on x86-64\n"
+ ksft_exit_skip("No GB pages available on x86-64\n"
"Please boot with hugepagesz=1G hugepages=%d\n", NUM_PAGES);
}
#endif
diff --git a/tools/testing/selftests/mm/uffd-common.c b/tools/testing/selftests/mm/uffd-common.c
index a37088a23ffe..994fe8c03923 100644
--- a/tools/testing/selftests/mm/uffd-common.c
+++ b/tools/testing/selftests/mm/uffd-common.c
@@ -7,18 +7,29 @@
#include "uffd-common.h"
-#define BASE_PMD_ADDR ((void *)(1UL << 30))
-
-volatile bool test_uffdio_copy_eexist = true;
-unsigned long nr_parallel, nr_pages, nr_pages_per_cpu, page_size;
-char *area_src, *area_src_alias, *area_dst, *area_dst_alias, *area_remap;
-int uffd = -1, uffd_flags, finished, *pipefd, test_type;
-bool map_shared;
-bool test_uffdio_wp = true;
-unsigned long long *count_verify;
uffd_test_ops_t *uffd_test_ops;
uffd_test_case_ops_t *uffd_test_case_ops;
-atomic_bool ready_for_fork;
+
+#define BASE_PMD_ADDR ((void *)(1UL << 30))
+
+/* pthread_mutex_t starts at page offset 0 */
+pthread_mutex_t *area_mutex(char *area, unsigned long nr, uffd_global_test_opts_t *gopts)
+{
+ return (pthread_mutex_t *) (area + nr * gopts->page_size);
+}
+
+/*
+ * count is placed in the page after pthread_mutex_t naturally aligned
+ * to avoid non alignment faults on non-x86 archs.
+ */
+volatile unsigned long long *area_count(char *area, unsigned long nr,
+ uffd_global_test_opts_t *gopts)
+{
+ return (volatile unsigned long long *)
+ ((unsigned long)(area + nr * gopts->page_size +
+ sizeof(pthread_mutex_t) + sizeof(unsigned long long) - 1) &
+ ~(unsigned long)(sizeof(unsigned long long) - 1));
+}
static int uffd_mem_fd_create(off_t mem_size, bool hugetlb)
{
@@ -40,15 +51,15 @@ static int uffd_mem_fd_create(off_t mem_size, bool hugetlb)
return mem_fd;
}
-static void anon_release_pages(char *rel_area)
+static void anon_release_pages(uffd_global_test_opts_t *gopts, char *rel_area)
{
- if (madvise(rel_area, nr_pages * page_size, MADV_DONTNEED))
+ if (madvise(rel_area, gopts->nr_pages * gopts->page_size, MADV_DONTNEED))
err("madvise(MADV_DONTNEED) failed");
}
-static int anon_allocate_area(void **alloc_area, bool is_src)
+static int anon_allocate_area(uffd_global_test_opts_t *gopts, void **alloc_area, bool is_src)
{
- *alloc_area = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE,
+ *alloc_area = mmap(NULL, gopts->nr_pages * gopts->page_size, PROT_READ | PROT_WRITE,
MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
if (*alloc_area == MAP_FAILED) {
*alloc_area = NULL;
@@ -57,31 +68,32 @@ static int anon_allocate_area(void **alloc_area, bool is_src)
return 0;
}
-static void noop_alias_mapping(__u64 *start, size_t len, unsigned long offset)
+static void noop_alias_mapping(uffd_global_test_opts_t *gopts, __u64 *start,
+ size_t len, unsigned long offset)
{
}
-static void hugetlb_release_pages(char *rel_area)
+static void hugetlb_release_pages(uffd_global_test_opts_t *gopts, char *rel_area)
{
- if (!map_shared) {
- if (madvise(rel_area, nr_pages * page_size, MADV_DONTNEED))
+ if (!gopts->map_shared) {
+ if (madvise(rel_area, gopts->nr_pages * gopts->page_size, MADV_DONTNEED))
err("madvise(MADV_DONTNEED) failed");
} else {
- if (madvise(rel_area, nr_pages * page_size, MADV_REMOVE))
+ if (madvise(rel_area, gopts->nr_pages * gopts->page_size, MADV_REMOVE))
err("madvise(MADV_REMOVE) failed");
}
}
-static int hugetlb_allocate_area(void **alloc_area, bool is_src)
+static int hugetlb_allocate_area(uffd_global_test_opts_t *gopts, void **alloc_area, bool is_src)
{
- off_t size = nr_pages * page_size;
+ off_t size = gopts->nr_pages * gopts->page_size;
off_t offset = is_src ? 0 : size;
void *area_alias = NULL;
char **alloc_area_alias;
int mem_fd = uffd_mem_fd_create(size * 2, true);
*alloc_area = mmap(NULL, size, PROT_READ | PROT_WRITE,
- (map_shared ? MAP_SHARED : MAP_PRIVATE) |
+ (gopts->map_shared ? MAP_SHARED : MAP_PRIVATE) |
(is_src ? 0 : MAP_NORESERVE),
mem_fd, offset);
if (*alloc_area == MAP_FAILED) {
@@ -89,7 +101,7 @@ static int hugetlb_allocate_area(void **alloc_area, bool is_src)
return -errno;
}
- if (map_shared) {
+ if (gopts->map_shared) {
area_alias = mmap(NULL, size, PROT_READ | PROT_WRITE,
MAP_SHARED, mem_fd, offset);
if (area_alias == MAP_FAILED)
@@ -97,9 +109,9 @@ static int hugetlb_allocate_area(void **alloc_area, bool is_src)
}
if (is_src) {
- alloc_area_alias = &area_src_alias;
+ alloc_area_alias = &gopts->area_src_alias;
} else {
- alloc_area_alias = &area_dst_alias;
+ alloc_area_alias = &gopts->area_dst_alias;
}
if (area_alias)
*alloc_area_alias = area_alias;
@@ -108,24 +120,25 @@ static int hugetlb_allocate_area(void **alloc_area, bool is_src)
return 0;
}
-static void hugetlb_alias_mapping(__u64 *start, size_t len, unsigned long offset)
+static void hugetlb_alias_mapping(uffd_global_test_opts_t *gopts, __u64 *start,
+ size_t len, unsigned long offset)
{
- if (!map_shared)
+ if (!gopts->map_shared)
return;
- *start = (unsigned long) area_dst_alias + offset;
+ *start = (unsigned long) gopts->area_dst_alias + offset;
}
-static void shmem_release_pages(char *rel_area)
+static void shmem_release_pages(uffd_global_test_opts_t *gopts, char *rel_area)
{
- if (madvise(rel_area, nr_pages * page_size, MADV_REMOVE))
+ if (madvise(rel_area, gopts->nr_pages * gopts->page_size, MADV_REMOVE))
err("madvise(MADV_REMOVE) failed");
}
-static int shmem_allocate_area(void **alloc_area, bool is_src)
+static int shmem_allocate_area(uffd_global_test_opts_t *gopts, void **alloc_area, bool is_src)
{
void *area_alias = NULL;
- size_t bytes = nr_pages * page_size, hpage_size = read_pmd_pagesize();
+ size_t bytes = gopts->nr_pages * gopts->page_size, hpage_size = read_pmd_pagesize();
unsigned long offset = is_src ? 0 : bytes;
char *p = NULL, *p_alias = NULL;
int mem_fd = uffd_mem_fd_create(bytes * 2, false);
@@ -159,22 +172,23 @@ static int shmem_allocate_area(void **alloc_area, bool is_src)
err("mmap of anonymous memory failed at %p", p_alias);
if (is_src)
- area_src_alias = area_alias;
+ gopts->area_src_alias = area_alias;
else
- area_dst_alias = area_alias;
+ gopts->area_dst_alias = area_alias;
close(mem_fd);
return 0;
}
-static void shmem_alias_mapping(__u64 *start, size_t len, unsigned long offset)
+static void shmem_alias_mapping(uffd_global_test_opts_t *gopts, __u64 *start,
+ size_t len, unsigned long offset)
{
- *start = (unsigned long)area_dst_alias + offset;
+ *start = (unsigned long)gopts->area_dst_alias + offset;
}
-static void shmem_check_pmd_mapping(void *p, int expect_nr_hpages)
+static void shmem_check_pmd_mapping(uffd_global_test_opts_t *gopts, void *p, int expect_nr_hpages)
{
- if (!check_huge_shmem(area_dst_alias, expect_nr_hpages,
+ if (!check_huge_shmem(gopts->area_dst_alias, expect_nr_hpages,
read_pmd_pagesize()))
err("Did not find expected %d number of hugepages",
expect_nr_hpages);
@@ -234,18 +248,18 @@ void uffd_stats_report(struct uffd_args *args, int n_cpus)
printf("\n");
}
-int userfaultfd_open(uint64_t *features)
+int userfaultfd_open(uffd_global_test_opts_t *gopts, uint64_t *features)
{
struct uffdio_api uffdio_api;
- uffd = uffd_open(UFFD_FLAGS);
- if (uffd < 0)
+ gopts->uffd = uffd_open(UFFD_FLAGS);
+ if (gopts->uffd < 0)
return -1;
- uffd_flags = fcntl(uffd, F_GETFD, NULL);
+ gopts->uffd_flags = fcntl(gopts->uffd, F_GETFD, NULL);
uffdio_api.api = UFFD_API;
uffdio_api.features = *features;
- if (ioctl(uffd, UFFDIO_API, &uffdio_api))
+ if (ioctl(gopts->uffd, UFFDIO_API, &uffdio_api))
/* Probably lack of CAP_PTRACE? */
return -1;
if (uffdio_api.api != UFFD_API)
@@ -255,59 +269,63 @@ int userfaultfd_open(uint64_t *features)
return 0;
}
-static inline void munmap_area(void **area)
+static inline void munmap_area(uffd_global_test_opts_t *gopts, void **area)
{
if (*area)
- if (munmap(*area, nr_pages * page_size))
+ if (munmap(*area, gopts->nr_pages * gopts->page_size))
err("munmap");
*area = NULL;
}
-void uffd_test_ctx_clear(void)
+void uffd_test_ctx_clear(uffd_global_test_opts_t *gopts)
{
size_t i;
- if (pipefd) {
- for (i = 0; i < nr_parallel * 2; ++i) {
- if (close(pipefd[i]))
+ if (gopts->pipefd) {
+ for (i = 0; i < gopts->nr_parallel * 2; ++i) {
+ if (close(gopts->pipefd[i]))
err("close pipefd");
}
- free(pipefd);
- pipefd = NULL;
+ free(gopts->pipefd);
+ gopts->pipefd = NULL;
}
- if (count_verify) {
- free(count_verify);
- count_verify = NULL;
+ if (gopts->count_verify) {
+ free(gopts->count_verify);
+ gopts->count_verify = NULL;
}
- if (uffd != -1) {
- if (close(uffd))
+ if (gopts->uffd != -1) {
+ if (close(gopts->uffd))
err("close uffd");
- uffd = -1;
+ gopts->uffd = -1;
}
- munmap_area((void **)&area_src);
- munmap_area((void **)&area_src_alias);
- munmap_area((void **)&area_dst);
- munmap_area((void **)&area_dst_alias);
- munmap_area((void **)&area_remap);
+ munmap_area(gopts, (void **)&gopts->area_src);
+ munmap_area(gopts, (void **)&gopts->area_src_alias);
+ munmap_area(gopts, (void **)&gopts->area_dst);
+ munmap_area(gopts, (void **)&gopts->area_dst_alias);
+ munmap_area(gopts, (void **)&gopts->area_remap);
}
-int uffd_test_ctx_init(uint64_t features, const char **errmsg)
+int uffd_test_ctx_init(uffd_global_test_opts_t *gopts, uint64_t features, const char **errmsg)
{
unsigned long nr, cpu;
int ret;
+ gopts->area_src_alias = NULL;
+ gopts->area_dst_alias = NULL;
+ gopts->area_remap = NULL;
+
if (uffd_test_case_ops && uffd_test_case_ops->pre_alloc) {
- ret = uffd_test_case_ops->pre_alloc(errmsg);
+ ret = uffd_test_case_ops->pre_alloc(gopts, errmsg);
if (ret)
return ret;
}
- ret = uffd_test_ops->allocate_area((void **)&area_src, true);
- ret |= uffd_test_ops->allocate_area((void **)&area_dst, false);
+ ret = uffd_test_ops->allocate_area(gopts, (void **) &gopts->area_src, true);
+ ret |= uffd_test_ops->allocate_area(gopts, (void **) &gopts->area_dst, false);
if (ret) {
if (errmsg)
*errmsg = "memory allocation failed";
@@ -315,26 +333,26 @@ int uffd_test_ctx_init(uint64_t features, const char **errmsg)
}
if (uffd_test_case_ops && uffd_test_case_ops->post_alloc) {
- ret = uffd_test_case_ops->post_alloc(errmsg);
+ ret = uffd_test_case_ops->post_alloc(gopts, errmsg);
if (ret)
return ret;
}
- ret = userfaultfd_open(&features);
+ ret = userfaultfd_open(gopts, &features);
if (ret) {
if (errmsg)
*errmsg = "possible lack of privilege";
return ret;
}
- count_verify = malloc(nr_pages * sizeof(unsigned long long));
- if (!count_verify)
+ gopts->count_verify = malloc(gopts->nr_pages * sizeof(unsigned long long));
+ if (!gopts->count_verify)
err("count_verify");
- for (nr = 0; nr < nr_pages; nr++) {
- *area_mutex(area_src, nr) =
+ for (nr = 0; nr < gopts->nr_pages; nr++) {
+ *area_mutex(gopts->area_src, nr, gopts) =
(pthread_mutex_t)PTHREAD_MUTEX_INITIALIZER;
- count_verify[nr] = *area_count(area_src, nr) = 1;
+ gopts->count_verify[nr] = *area_count(gopts->area_src, nr, gopts) = 1;
/*
* In the transition between 255 to 256, powerpc will
* read out of order in my_bcmp and see both bytes as
@@ -342,7 +360,7 @@ int uffd_test_ctx_init(uint64_t features, const char **errmsg)
* after the count, to avoid my_bcmp to trigger false
* positives.
*/
- *(area_count(area_src, nr) + 1) = 1;
+ *(area_count(gopts->area_src, nr, gopts) + 1) = 1;
}
/*
@@ -363,13 +381,13 @@ int uffd_test_ctx_init(uint64_t features, const char **errmsg)
* proactively split the thp and drop any accidentally initialized
* pages within area_dst.
*/
- uffd_test_ops->release_pages(area_dst);
+ uffd_test_ops->release_pages(gopts, gopts->area_dst);
- pipefd = malloc(sizeof(int) * nr_parallel * 2);
- if (!pipefd)
+ gopts->pipefd = malloc(sizeof(int) * gopts->nr_parallel * 2);
+ if (!gopts->pipefd)
err("pipefd");
- for (cpu = 0; cpu < nr_parallel; cpu++)
- if (pipe2(&pipefd[cpu * 2], O_CLOEXEC | O_NONBLOCK))
+ for (cpu = 0; cpu < gopts->nr_parallel; cpu++)
+ if (pipe2(&gopts->pipefd[cpu * 2], O_CLOEXEC | O_NONBLOCK))
err("pipe");
return 0;
@@ -416,9 +434,9 @@ static void continue_range(int ufd, __u64 start, __u64 len, bool wp)
ret, (int64_t) req.mapped);
}
-int uffd_read_msg(int ufd, struct uffd_msg *msg)
+int uffd_read_msg(uffd_global_test_opts_t *gopts, struct uffd_msg *msg)
{
- int ret = read(uffd, msg, sizeof(*msg));
+ int ret = read(gopts->uffd, msg, sizeof(*msg));
if (ret != sizeof(*msg)) {
if (ret < 0) {
@@ -433,7 +451,8 @@ int uffd_read_msg(int ufd, struct uffd_msg *msg)
return 0;
}
-void uffd_handle_page_fault(struct uffd_msg *msg, struct uffd_args *args)
+void uffd_handle_page_fault(uffd_global_test_opts_t *gopts, struct uffd_msg *msg,
+ struct uffd_args *args)
{
unsigned long offset;
@@ -442,7 +461,7 @@ void uffd_handle_page_fault(struct uffd_msg *msg, struct uffd_args *args)
if (msg->arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WP) {
/* Write protect page faults */
- wp_range(uffd, msg->arg.pagefault.address, page_size, false);
+ wp_range(gopts->uffd, msg->arg.pagefault.address, gopts->page_size, false);
args->wp_faults++;
} else if (msg->arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_MINOR) {
uint8_t *area;
@@ -460,12 +479,12 @@ void uffd_handle_page_fault(struct uffd_msg *msg, struct uffd_args *args)
* (UFFD-registered).
*/
- area = (uint8_t *)(area_dst +
- ((char *)msg->arg.pagefault.address -
- area_dst_alias));
- for (b = 0; b < page_size; ++b)
+ area = (uint8_t *)(gopts->area_dst +
+ ((char *)msg->arg.pagefault.address -
+ gopts->area_dst_alias));
+ for (b = 0; b < gopts->page_size; ++b)
area[b] = ~area[b];
- continue_range(uffd, msg->arg.pagefault.address, page_size,
+ continue_range(gopts->uffd, msg->arg.pagefault.address, gopts->page_size,
args->apply_wp);
args->minor_faults++;
} else {
@@ -493,10 +512,10 @@ void uffd_handle_page_fault(struct uffd_msg *msg, struct uffd_args *args)
if (msg->arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WRITE)
err("unexpected write fault");
- offset = (char *)(unsigned long)msg->arg.pagefault.address - area_dst;
- offset &= ~(page_size-1);
+ offset = (char *)(unsigned long)msg->arg.pagefault.address - gopts->area_dst;
+ offset &= ~(gopts->page_size-1);
- if (copy_page(uffd, offset, args->apply_wp))
+ if (copy_page(gopts, offset, args->apply_wp))
args->missing_faults++;
}
}
@@ -504,6 +523,7 @@ void uffd_handle_page_fault(struct uffd_msg *msg, struct uffd_args *args)
void *uffd_poll_thread(void *arg)
{
struct uffd_args *args = (struct uffd_args *)arg;
+ uffd_global_test_opts_t *gopts = args->gopts;
unsigned long cpu = args->cpu;
struct pollfd pollfd[2];
struct uffd_msg msg;
@@ -514,12 +534,12 @@ void *uffd_poll_thread(void *arg)
if (!args->handle_fault)
args->handle_fault = uffd_handle_page_fault;
- pollfd[0].fd = uffd;
+ pollfd[0].fd = gopts->uffd;
pollfd[0].events = POLLIN;
- pollfd[1].fd = pipefd[cpu*2];
+ pollfd[1].fd = gopts->pipefd[cpu*2];
pollfd[1].events = POLLIN;
- ready_for_fork = true;
+ gopts->ready_for_fork = true;
for (;;) {
ret = poll(pollfd, 2, -1);
@@ -537,30 +557,30 @@ void *uffd_poll_thread(void *arg)
}
if (!(pollfd[0].revents & POLLIN))
err("pollfd[0].revents %d", pollfd[0].revents);
- if (uffd_read_msg(uffd, &msg))
+ if (uffd_read_msg(gopts, &msg))
continue;
switch (msg.event) {
default:
err("unexpected msg event %u\n", msg.event);
break;
case UFFD_EVENT_PAGEFAULT:
- args->handle_fault(&msg, args);
+ args->handle_fault(gopts, &msg, args);
break;
case UFFD_EVENT_FORK:
- close(uffd);
- uffd = msg.arg.fork.ufd;
- pollfd[0].fd = uffd;
+ close(gopts->uffd);
+ gopts->uffd = msg.arg.fork.ufd;
+ pollfd[0].fd = gopts->uffd;
break;
case UFFD_EVENT_REMOVE:
uffd_reg.range.start = msg.arg.remove.start;
uffd_reg.range.len = msg.arg.remove.end -
msg.arg.remove.start;
- if (ioctl(uffd, UFFDIO_UNREGISTER, &uffd_reg.range))
+ if (ioctl(gopts->uffd, UFFDIO_UNREGISTER, &uffd_reg.range))
err("remove failure");
break;
case UFFD_EVENT_REMAP:
- area_remap = area_dst; /* save for later unmap */
- area_dst = (char *)(unsigned long)msg.arg.remap.to;
+ gopts->area_remap = gopts->area_dst; /* save for later unmap */
+ gopts->area_dst = (char *)(unsigned long)msg.arg.remap.to;
break;
}
}
@@ -568,17 +588,18 @@ void *uffd_poll_thread(void *arg)
return NULL;
}
-static void retry_copy_page(int ufd, struct uffdio_copy *uffdio_copy,
+static void retry_copy_page(uffd_global_test_opts_t *gopts, struct uffdio_copy *uffdio_copy,
unsigned long offset)
{
- uffd_test_ops->alias_mapping(&uffdio_copy->dst,
+ uffd_test_ops->alias_mapping(gopts,
+ &uffdio_copy->dst,
uffdio_copy->len,
offset);
- if (ioctl(ufd, UFFDIO_COPY, uffdio_copy)) {
+ if (ioctl(gopts->uffd, UFFDIO_COPY, uffdio_copy)) {
/* real retval in ufdio_copy.copy */
if (uffdio_copy->copy != -EEXIST)
err("UFFDIO_COPY retry error: %"PRId64,
- (int64_t)uffdio_copy->copy);
+ (int64_t)uffdio_copy->copy);
} else {
err("UFFDIO_COPY retry unexpected: %"PRId64,
(int64_t)uffdio_copy->copy);
@@ -597,60 +618,60 @@ static void wake_range(int ufd, unsigned long addr, unsigned long len)
addr), exit(1);
}
-int __copy_page(int ufd, unsigned long offset, bool retry, bool wp)
+int __copy_page(uffd_global_test_opts_t *gopts, unsigned long offset, bool retry, bool wp)
{
struct uffdio_copy uffdio_copy;
- if (offset >= nr_pages * page_size)
+ if (offset >= gopts->nr_pages * gopts->page_size)
err("unexpected offset %lu\n", offset);
- uffdio_copy.dst = (unsigned long) area_dst + offset;
- uffdio_copy.src = (unsigned long) area_src + offset;
- uffdio_copy.len = page_size;
+ uffdio_copy.dst = (unsigned long) gopts->area_dst + offset;
+ uffdio_copy.src = (unsigned long) gopts->area_src + offset;
+ uffdio_copy.len = gopts->page_size;
if (wp)
uffdio_copy.mode = UFFDIO_COPY_MODE_WP;
else
uffdio_copy.mode = 0;
uffdio_copy.copy = 0;
- if (ioctl(ufd, UFFDIO_COPY, &uffdio_copy)) {
+ if (ioctl(gopts->uffd, UFFDIO_COPY, &uffdio_copy)) {
/* real retval in ufdio_copy.copy */
if (uffdio_copy.copy != -EEXIST)
err("UFFDIO_COPY error: %"PRId64,
(int64_t)uffdio_copy.copy);
- wake_range(ufd, uffdio_copy.dst, page_size);
- } else if (uffdio_copy.copy != page_size) {
+ wake_range(gopts->uffd, uffdio_copy.dst, gopts->page_size);
+ } else if (uffdio_copy.copy != gopts->page_size) {
err("UFFDIO_COPY error: %"PRId64, (int64_t)uffdio_copy.copy);
} else {
- if (test_uffdio_copy_eexist && retry) {
- test_uffdio_copy_eexist = false;
- retry_copy_page(ufd, &uffdio_copy, offset);
+ if (gopts->test_uffdio_copy_eexist && retry) {
+ gopts->test_uffdio_copy_eexist = false;
+ retry_copy_page(gopts, &uffdio_copy, offset);
}
return 1;
}
return 0;
}
-int copy_page(int ufd, unsigned long offset, bool wp)
+int copy_page(uffd_global_test_opts_t *gopts, unsigned long offset, bool wp)
{
- return __copy_page(ufd, offset, false, wp);
+ return __copy_page(gopts, offset, false, wp);
}
-int move_page(int ufd, unsigned long offset, unsigned long len)
+int move_page(uffd_global_test_opts_t *gopts, unsigned long offset, unsigned long len)
{
struct uffdio_move uffdio_move;
- if (offset + len > nr_pages * page_size)
+ if (offset + len > gopts->nr_pages * gopts->page_size)
err("unexpected offset %lu and length %lu\n", offset, len);
- uffdio_move.dst = (unsigned long) area_dst + offset;
- uffdio_move.src = (unsigned long) area_src + offset;
+ uffdio_move.dst = (unsigned long) gopts->area_dst + offset;
+ uffdio_move.src = (unsigned long) gopts->area_src + offset;
uffdio_move.len = len;
uffdio_move.mode = UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES;
uffdio_move.move = 0;
- if (ioctl(ufd, UFFDIO_MOVE, &uffdio_move)) {
+ if (ioctl(gopts->uffd, UFFDIO_MOVE, &uffdio_move)) {
/* real retval in uffdio_move.move */
if (uffdio_move.move != -EEXIST)
err("UFFDIO_MOVE error: %"PRId64,
(int64_t)uffdio_move.move);
- wake_range(ufd, uffdio_move.dst, len);
+ wake_range(gopts->uffd, uffdio_move.dst, len);
} else if (uffdio_move.move != len) {
err("UFFDIO_MOVE error: %"PRId64, (int64_t)uffdio_move.move);
} else
diff --git a/tools/testing/selftests/mm/uffd-common.h b/tools/testing/selftests/mm/uffd-common.h
index 7700cbfa3975..37d3ca55905f 100644
--- a/tools/testing/selftests/mm/uffd-common.h
+++ b/tools/testing/selftests/mm/uffd-common.h
@@ -56,20 +56,17 @@
#define err(fmt, ...) errexit(1, fmt, ##__VA_ARGS__)
-/* pthread_mutex_t starts at page offset 0 */
-#define area_mutex(___area, ___nr) \
- ((pthread_mutex_t *) ((___area) + (___nr)*page_size))
-/*
- * count is placed in the page after pthread_mutex_t naturally aligned
- * to avoid non alignment faults on non-x86 archs.
- */
-#define area_count(___area, ___nr) \
- ((volatile unsigned long long *) ((unsigned long) \
- ((___area) + (___nr)*page_size + \
- sizeof(pthread_mutex_t) + \
- sizeof(unsigned long long) - 1) & \
- ~(unsigned long)(sizeof(unsigned long long) \
- - 1)))
+struct uffd_global_test_opts {
+ unsigned long nr_parallel, nr_pages, nr_pages_per_cpu, page_size;
+ char *area_src, *area_src_alias, *area_dst, *area_dst_alias, *area_remap;
+ int uffd, uffd_flags, finished, *pipefd, test_type;
+ bool map_shared;
+ bool test_uffdio_wp;
+ unsigned long long *count_verify;
+ volatile bool test_uffdio_copy_eexist;
+ atomic_bool ready_for_fork;
+};
+typedef struct uffd_global_test_opts uffd_global_test_opts_t;
/* Userfaultfd test statistics */
struct uffd_args {
@@ -79,50 +76,55 @@ struct uffd_args {
unsigned long missing_faults;
unsigned long wp_faults;
unsigned long minor_faults;
+ struct uffd_global_test_opts *gopts;
/* A custom fault handler; defaults to uffd_handle_page_fault. */
- void (*handle_fault)(struct uffd_msg *msg, struct uffd_args *args);
+ void (*handle_fault)(struct uffd_global_test_opts *gopts,
+ struct uffd_msg *msg,
+ struct uffd_args *args);
};
struct uffd_test_ops {
- int (*allocate_area)(void **alloc_area, bool is_src);
- void (*release_pages)(char *rel_area);
- void (*alias_mapping)(__u64 *start, size_t len, unsigned long offset);
- void (*check_pmd_mapping)(void *p, int expect_nr_hpages);
+ int (*allocate_area)(uffd_global_test_opts_t *gopts, void **alloc_area, bool is_src);
+ void (*release_pages)(uffd_global_test_opts_t *gopts, char *rel_area);
+ void (*alias_mapping)(uffd_global_test_opts_t *gopts,
+ __u64 *start,
+ size_t len,
+ unsigned long offset);
+ void (*check_pmd_mapping)(uffd_global_test_opts_t *gopts, void *p, int expect_nr_hpages);
};
typedef struct uffd_test_ops uffd_test_ops_t;
struct uffd_test_case_ops {
- int (*pre_alloc)(const char **errmsg);
- int (*post_alloc)(const char **errmsg);
+ int (*pre_alloc)(uffd_global_test_opts_t *gopts, const char **errmsg);
+ int (*post_alloc)(uffd_global_test_opts_t *gopts, const char **errmsg);
};
typedef struct uffd_test_case_ops uffd_test_case_ops_t;
-extern unsigned long nr_parallel, nr_pages, nr_pages_per_cpu, page_size;
-extern char *area_src, *area_src_alias, *area_dst, *area_dst_alias, *area_remap;
-extern int uffd, uffd_flags, finished, *pipefd, test_type;
-extern bool map_shared;
-extern bool test_uffdio_wp;
-extern unsigned long long *count_verify;
-extern volatile bool test_uffdio_copy_eexist;
-extern atomic_bool ready_for_fork;
-
+extern uffd_global_test_opts_t *uffd_gtest_opts;
extern uffd_test_ops_t anon_uffd_test_ops;
extern uffd_test_ops_t shmem_uffd_test_ops;
extern uffd_test_ops_t hugetlb_uffd_test_ops;
extern uffd_test_ops_t *uffd_test_ops;
extern uffd_test_case_ops_t *uffd_test_case_ops;
+pthread_mutex_t *area_mutex(char *area, unsigned long nr, uffd_global_test_opts_t *gopts);
+volatile unsigned long long *area_count(char *area,
+ unsigned long nr,
+ uffd_global_test_opts_t *gopts);
+
void uffd_stats_report(struct uffd_args *args, int n_cpus);
-int uffd_test_ctx_init(uint64_t features, const char **errmsg);
-void uffd_test_ctx_clear(void);
-int userfaultfd_open(uint64_t *features);
-int uffd_read_msg(int ufd, struct uffd_msg *msg);
+int uffd_test_ctx_init(uffd_global_test_opts_t *gopts, uint64_t features, const char **errmsg);
+void uffd_test_ctx_clear(uffd_global_test_opts_t *gopts);
+int userfaultfd_open(uffd_global_test_opts_t *gopts, uint64_t *features);
+int uffd_read_msg(uffd_global_test_opts_t *gopts, struct uffd_msg *msg);
void wp_range(int ufd, __u64 start, __u64 len, bool wp);
-void uffd_handle_page_fault(struct uffd_msg *msg, struct uffd_args *args);
-int __copy_page(int ufd, unsigned long offset, bool retry, bool wp);
-int copy_page(int ufd, unsigned long offset, bool wp);
-int move_page(int ufd, unsigned long offset, unsigned long len);
+void uffd_handle_page_fault(uffd_global_test_opts_t *gopts,
+ struct uffd_msg *msg,
+ struct uffd_args *args);
+int __copy_page(uffd_global_test_opts_t *gopts, unsigned long offset, bool retry, bool wp);
+int copy_page(uffd_global_test_opts_t *gopts, unsigned long offset, bool wp);
+int move_page(uffd_global_test_opts_t *gopts, unsigned long offset, unsigned long len);
void *uffd_poll_thread(void *arg);
int uffd_open_dev(unsigned int flags);
diff --git a/tools/testing/selftests/mm/uffd-stress.c b/tools/testing/selftests/mm/uffd-stress.c
index 40af7f67c407..b51c89e1cd1a 100644
--- a/tools/testing/selftests/mm/uffd-stress.c
+++ b/tools/testing/selftests/mm/uffd-stress.c
@@ -44,6 +44,12 @@ uint64_t features;
#define BOUNCE_VERIFY (1<<2)
#define BOUNCE_POLL (1<<3)
static int bounces;
+/* defined globally for this particular test as the sigalrm handler
+ * depends on test_uffdio_*_eexist.
+ * XXX: define gopts in main() when we figure out a way to deal with
+ * test_uffdio_*_eexist.
+ */
+static uffd_global_test_opts_t *gopts;
/* exercise the test_uffdio_*_eexist every ALARM_INTERVAL_SECS */
#define ALARM_INTERVAL_SECS 10
@@ -51,7 +57,7 @@ static char *zeropage;
pthread_attr_t attr;
#define swap(a, b) \
- do { typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; } while (0)
+ do { __auto_type __tmp = (a); (a) = (b); (b) = __tmp; } while (0)
const char *examples =
"# Run anonymous memory test on 100MiB region with 99999 bounces:\n"
@@ -76,54 +82,58 @@ static void usage(void)
exit(1);
}
-static void uffd_stats_reset(struct uffd_args *args, unsigned long n_cpus)
+static void uffd_stats_reset(uffd_global_test_opts_t *gopts, struct uffd_args *args,
+ unsigned long n_cpus)
{
int i;
for (i = 0; i < n_cpus; i++) {
args[i].cpu = i;
- args[i].apply_wp = test_uffdio_wp;
+ args[i].apply_wp = gopts->test_uffdio_wp;
args[i].missing_faults = 0;
args[i].wp_faults = 0;
args[i].minor_faults = 0;
+ args[i].gopts = gopts;
}
}
static void *locking_thread(void *arg)
{
- unsigned long cpu = (unsigned long) arg;
+ struct uffd_args *args = (struct uffd_args *) arg;
+ uffd_global_test_opts_t *gopts = args->gopts;
+ unsigned long cpu = (unsigned long) args->cpu;
unsigned long page_nr;
unsigned long long count;
if (!(bounces & BOUNCE_RANDOM)) {
page_nr = -bounces;
if (!(bounces & BOUNCE_RACINGFAULTS))
- page_nr += cpu * nr_pages_per_cpu;
+ page_nr += cpu * gopts->nr_pages_per_cpu;
}
- while (!finished) {
+ while (!gopts->finished) {
if (bounces & BOUNCE_RANDOM) {
if (getrandom(&page_nr, sizeof(page_nr), 0) != sizeof(page_nr))
err("getrandom failed");
} else
page_nr += 1;
- page_nr %= nr_pages;
- pthread_mutex_lock(area_mutex(area_dst, page_nr));
- count = *area_count(area_dst, page_nr);
- if (count != count_verify[page_nr])
+ page_nr %= gopts->nr_pages;
+ pthread_mutex_lock(area_mutex(gopts->area_dst, page_nr, gopts));
+ count = *area_count(gopts->area_dst, page_nr, gopts);
+ if (count != gopts->count_verify[page_nr])
err("page_nr %lu memory corruption %llu %llu",
- page_nr, count, count_verify[page_nr]);
+ page_nr, count, gopts->count_verify[page_nr]);
count++;
- *area_count(area_dst, page_nr) = count_verify[page_nr] = count;
- pthread_mutex_unlock(area_mutex(area_dst, page_nr));
+ *area_count(gopts->area_dst, page_nr, gopts) = gopts->count_verify[page_nr] = count;
+ pthread_mutex_unlock(area_mutex(gopts->area_dst, page_nr, gopts));
}
return NULL;
}
-static int copy_page_retry(int ufd, unsigned long offset)
+static int copy_page_retry(uffd_global_test_opts_t *gopts, unsigned long offset)
{
- return __copy_page(ufd, offset, true, test_uffdio_wp);
+ return __copy_page(gopts, offset, true, gopts->test_uffdio_wp);
}
pthread_mutex_t uffd_read_mutex = PTHREAD_MUTEX_INITIALIZER;
@@ -131,15 +141,16 @@ pthread_mutex_t uffd_read_mutex = PTHREAD_MUTEX_INITIALIZER;
static void *uffd_read_thread(void *arg)
{
struct uffd_args *args = (struct uffd_args *)arg;
+ uffd_global_test_opts_t *gopts = args->gopts;
struct uffd_msg msg;
pthread_mutex_unlock(&uffd_read_mutex);
/* from here cancellation is ok */
for (;;) {
- if (uffd_read_msg(uffd, &msg))
+ if (uffd_read_msg(gopts, &msg))
continue;
- uffd_handle_page_fault(&msg, args);
+ uffd_handle_page_fault(gopts, &msg, args);
}
return NULL;
@@ -147,32 +158,34 @@ static void *uffd_read_thread(void *arg)
static void *background_thread(void *arg)
{
- unsigned long cpu = (unsigned long) arg;
+ struct uffd_args *args = (struct uffd_args *) arg;
+ uffd_global_test_opts_t *gopts = args->gopts;
+ unsigned long cpu = (unsigned long) args->cpu;
unsigned long page_nr, start_nr, mid_nr, end_nr;
- start_nr = cpu * nr_pages_per_cpu;
- end_nr = (cpu+1) * nr_pages_per_cpu;
+ start_nr = cpu * gopts->nr_pages_per_cpu;
+ end_nr = (cpu+1) * gopts->nr_pages_per_cpu;
mid_nr = (start_nr + end_nr) / 2;
/* Copy the first half of the pages */
for (page_nr = start_nr; page_nr < mid_nr; page_nr++)
- copy_page_retry(uffd, page_nr * page_size);
+ copy_page_retry(gopts, page_nr * gopts->page_size);
/*
* If we need to test uffd-wp, set it up now. Then we'll have
* at least the first half of the pages mapped already which
* can be write-protected for testing
*/
- if (test_uffdio_wp)
- wp_range(uffd, (unsigned long)area_dst + start_nr * page_size,
- nr_pages_per_cpu * page_size, true);
+ if (gopts->test_uffdio_wp)
+ wp_range(gopts->uffd, (unsigned long)gopts->area_dst + start_nr * gopts->page_size,
+ gopts->nr_pages_per_cpu * gopts->page_size, true);
/*
* Continue the 2nd half of the page copying, handling write
* protection faults if any
*/
for (page_nr = mid_nr; page_nr < end_nr; page_nr++)
- copy_page_retry(uffd, page_nr * page_size);
+ copy_page_retry(gopts, page_nr * gopts->page_size);
return NULL;
}
@@ -180,17 +193,21 @@ static void *background_thread(void *arg)
static int stress(struct uffd_args *args)
{
unsigned long cpu;
- pthread_t locking_threads[nr_parallel];
- pthread_t uffd_threads[nr_parallel];
- pthread_t background_threads[nr_parallel];
+ uffd_global_test_opts_t *gopts = args->gopts;
+ pthread_t locking_threads[gopts->nr_parallel];
+ pthread_t uffd_threads[gopts->nr_parallel];
+ pthread_t background_threads[gopts->nr_parallel];
- finished = 0;
- for (cpu = 0; cpu < nr_parallel; cpu++) {
+ gopts->finished = 0;
+ for (cpu = 0; cpu < gopts->nr_parallel; cpu++) {
if (pthread_create(&locking_threads[cpu], &attr,
- locking_thread, (void *)cpu))
+ locking_thread, (void *)&args[cpu]))
return 1;
if (bounces & BOUNCE_POLL) {
- if (pthread_create(&uffd_threads[cpu], &attr, uffd_poll_thread, &args[cpu]))
+ if (pthread_create(&uffd_threads[cpu],
+ &attr,
+ uffd_poll_thread,
+ (void *) &args[cpu]))
err("uffd_poll_thread create");
} else {
if (pthread_create(&uffd_threads[cpu], &attr,
@@ -200,10 +217,10 @@ static int stress(struct uffd_args *args)
pthread_mutex_lock(&uffd_read_mutex);
}
if (pthread_create(&background_threads[cpu], &attr,
- background_thread, (void *)cpu))
+ background_thread, (void *)&args[cpu]))
return 1;
}
- for (cpu = 0; cpu < nr_parallel; cpu++)
+ for (cpu = 0; cpu < gopts->nr_parallel; cpu++)
if (pthread_join(background_threads[cpu], NULL))
return 1;
@@ -216,17 +233,17 @@ static int stress(struct uffd_args *args)
* UFFDIO_COPY without writing zero pages into area_dst
* because the background threads already completed).
*/
- uffd_test_ops->release_pages(area_src);
+ uffd_test_ops->release_pages(gopts, gopts->area_src);
- finished = 1;
- for (cpu = 0; cpu < nr_parallel; cpu++)
+ gopts->finished = 1;
+ for (cpu = 0; cpu < gopts->nr_parallel; cpu++)
if (pthread_join(locking_threads[cpu], NULL))
return 1;
- for (cpu = 0; cpu < nr_parallel; cpu++) {
+ for (cpu = 0; cpu < gopts->nr_parallel; cpu++) {
char c;
if (bounces & BOUNCE_POLL) {
- if (write(pipefd[cpu*2+1], &c, 1) != 1)
+ if (write(gopts->pipefd[cpu*2+1], &c, 1) != 1)
err("pipefd write error");
if (pthread_join(uffd_threads[cpu],
(void *)&args[cpu]))
@@ -242,26 +259,26 @@ static int stress(struct uffd_args *args)
return 0;
}
-static int userfaultfd_stress(void)
+static int userfaultfd_stress(uffd_global_test_opts_t *gopts)
{
void *area;
unsigned long nr;
- struct uffd_args args[nr_parallel];
- uint64_t mem_size = nr_pages * page_size;
+ struct uffd_args args[gopts->nr_parallel];
+ uint64_t mem_size = gopts->nr_pages * gopts->page_size;
int flags = 0;
- memset(args, 0, sizeof(struct uffd_args) * nr_parallel);
+ memset(args, 0, sizeof(struct uffd_args) * gopts->nr_parallel);
- if (features & UFFD_FEATURE_WP_UNPOPULATED && test_type == TEST_ANON)
+ if (features & UFFD_FEATURE_WP_UNPOPULATED && gopts->test_type == TEST_ANON)
flags = UFFD_FEATURE_WP_UNPOPULATED;
- if (uffd_test_ctx_init(flags, NULL))
+ if (uffd_test_ctx_init(gopts, flags, NULL))
err("context init failed");
- if (posix_memalign(&area, page_size, page_size))
+ if (posix_memalign(&area, gopts->page_size, gopts->page_size))
err("out of memory");
zeropage = area;
- bzero(zeropage, page_size);
+ bzero(zeropage, gopts->page_size);
pthread_mutex_lock(&uffd_read_mutex);
@@ -284,18 +301,18 @@ static int userfaultfd_stress(void)
fflush(stdout);
if (bounces & BOUNCE_POLL)
- fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK);
+ fcntl(gopts->uffd, F_SETFL, gopts->uffd_flags | O_NONBLOCK);
else
- fcntl(uffd, F_SETFL, uffd_flags & ~O_NONBLOCK);
+ fcntl(gopts->uffd, F_SETFL, gopts->uffd_flags & ~O_NONBLOCK);
/* register */
- if (uffd_register(uffd, area_dst, mem_size,
- true, test_uffdio_wp, false))
+ if (uffd_register(gopts->uffd, gopts->area_dst, mem_size,
+ true, gopts->test_uffdio_wp, false))
err("register failure");
- if (area_dst_alias) {
- if (uffd_register(uffd, area_dst_alias, mem_size,
- true, test_uffdio_wp, false))
+ if (gopts->area_dst_alias) {
+ if (uffd_register(gopts->uffd, gopts->area_dst_alias, mem_size,
+ true, gopts->test_uffdio_wp, false))
err("register failure alias");
}
@@ -323,87 +340,88 @@ static int userfaultfd_stress(void)
* MADV_DONTNEED only after the UFFDIO_REGISTER, so it's
* required to MADV_DONTNEED here.
*/
- uffd_test_ops->release_pages(area_dst);
+ uffd_test_ops->release_pages(gopts, gopts->area_dst);
- uffd_stats_reset(args, nr_parallel);
+ uffd_stats_reset(gopts, args, gopts->nr_parallel);
/* bounce pass */
if (stress(args)) {
- uffd_test_ctx_clear();
+ uffd_test_ctx_clear(gopts);
return 1;
}
/* Clear all the write protections if there is any */
- if (test_uffdio_wp)
- wp_range(uffd, (unsigned long)area_dst,
- nr_pages * page_size, false);
+ if (gopts->test_uffdio_wp)
+ wp_range(gopts->uffd, (unsigned long)gopts->area_dst,
+ gopts->nr_pages * gopts->page_size, false);
/* unregister */
- if (uffd_unregister(uffd, area_dst, mem_size))
+ if (uffd_unregister(gopts->uffd, gopts->area_dst, mem_size))
err("unregister failure");
- if (area_dst_alias) {
- if (uffd_unregister(uffd, area_dst_alias, mem_size))
+ if (gopts->area_dst_alias) {
+ if (uffd_unregister(gopts->uffd, gopts->area_dst_alias, mem_size))
err("unregister failure alias");
}
/* verification */
if (bounces & BOUNCE_VERIFY)
- for (nr = 0; nr < nr_pages; nr++)
- if (*area_count(area_dst, nr) != count_verify[nr])
+ for (nr = 0; nr < gopts->nr_pages; nr++)
+ if (*area_count(gopts->area_dst, nr, gopts) !=
+ gopts->count_verify[nr])
err("error area_count %llu %llu %lu\n",
- *area_count(area_src, nr),
- count_verify[nr], nr);
+ *area_count(gopts->area_src, nr, gopts),
+ gopts->count_verify[nr], nr);
/* prepare next bounce */
- swap(area_src, area_dst);
+ swap(gopts->area_src, gopts->area_dst);
- swap(area_src_alias, area_dst_alias);
+ swap(gopts->area_src_alias, gopts->area_dst_alias);
- uffd_stats_report(args, nr_parallel);
+ uffd_stats_report(args, gopts->nr_parallel);
}
- uffd_test_ctx_clear();
+ uffd_test_ctx_clear(gopts);
return 0;
}
-static void set_test_type(const char *type)
+static void set_test_type(uffd_global_test_opts_t *gopts, const char *type)
{
if (!strcmp(type, "anon")) {
- test_type = TEST_ANON;
+ gopts->test_type = TEST_ANON;
uffd_test_ops = &anon_uffd_test_ops;
} else if (!strcmp(type, "hugetlb")) {
- test_type = TEST_HUGETLB;
+ gopts->test_type = TEST_HUGETLB;
uffd_test_ops = &hugetlb_uffd_test_ops;
- map_shared = true;
+ gopts->map_shared = true;
} else if (!strcmp(type, "hugetlb-private")) {
- test_type = TEST_HUGETLB;
+ gopts->test_type = TEST_HUGETLB;
uffd_test_ops = &hugetlb_uffd_test_ops;
} else if (!strcmp(type, "shmem")) {
- map_shared = true;
- test_type = TEST_SHMEM;
+ gopts->map_shared = true;
+ gopts->test_type = TEST_SHMEM;
uffd_test_ops = &shmem_uffd_test_ops;
} else if (!strcmp(type, "shmem-private")) {
- test_type = TEST_SHMEM;
+ gopts->test_type = TEST_SHMEM;
uffd_test_ops = &shmem_uffd_test_ops;
}
}
-static void parse_test_type_arg(const char *raw_type)
+static void parse_test_type_arg(uffd_global_test_opts_t *gopts, const char *raw_type)
{
- set_test_type(raw_type);
+ set_test_type(gopts, raw_type);
- if (!test_type)
+ if (!gopts->test_type)
err("failed to parse test type argument: '%s'", raw_type);
- if (test_type == TEST_HUGETLB)
- page_size = default_huge_page_size();
+ if (gopts->test_type == TEST_HUGETLB)
+ gopts->page_size = default_huge_page_size();
else
- page_size = sysconf(_SC_PAGE_SIZE);
+ gopts->page_size = sysconf(_SC_PAGE_SIZE);
- if (!page_size)
+ if (!gopts->page_size)
err("Unable to determine page size");
- if ((unsigned long) area_count(NULL, 0) + sizeof(unsigned long long) * 2
- > page_size)
+ if ((unsigned long) area_count(NULL, 0, gopts) + sizeof(unsigned long long) * 2
+ > gopts->page_size)
err("Impossible to run this test");
/*
@@ -415,21 +433,21 @@ static void parse_test_type_arg(const char *raw_type)
if (uffd_get_features(&features) && errno == ENOENT)
ksft_exit_skip("failed to get available features (%d)\n", errno);
- test_uffdio_wp = test_uffdio_wp &&
+ gopts->test_uffdio_wp = gopts->test_uffdio_wp &&
(features & UFFD_FEATURE_PAGEFAULT_FLAG_WP);
- if (test_type != TEST_ANON && !(features & UFFD_FEATURE_WP_HUGETLBFS_SHMEM))
- test_uffdio_wp = false;
+ if (gopts->test_type != TEST_ANON && !(features & UFFD_FEATURE_WP_HUGETLBFS_SHMEM))
+ gopts->test_uffdio_wp = false;
- close(uffd);
- uffd = -1;
+ close(gopts->uffd);
+ gopts->uffd = -1;
}
static void sigalrm(int sig)
{
if (sig != SIGALRM)
abort();
- test_uffdio_copy_eexist = true;
+ gopts->test_uffdio_copy_eexist = true;
alarm(ALARM_INTERVAL_SECS);
}
@@ -438,6 +456,8 @@ int main(int argc, char **argv)
unsigned long nr_cpus;
size_t bytes;
+ gopts = (uffd_global_test_opts_t *) malloc(sizeof(uffd_global_test_opts_t));
+
if (argc < 4)
usage();
@@ -445,29 +465,34 @@ int main(int argc, char **argv)
err("failed to arm SIGALRM");
alarm(ALARM_INTERVAL_SECS);
- parse_test_type_arg(argv[1]);
+ parse_test_type_arg(gopts, argv[1]);
bytes = atol(argv[2]) * 1024 * 1024;
- if (test_type == TEST_HUGETLB &&
- get_free_hugepages() < bytes / page_size) {
- printf("skip: Skipping userfaultfd... not enough hugepages\n");
- return KSFT_SKIP;
- }
-
nr_cpus = sysconf(_SC_NPROCESSORS_ONLN);
if (nr_cpus > 32) {
/* Don't let calculation below go to zero. */
ksft_print_msg("_SC_NPROCESSORS_ONLN (%lu) too large, capping nr_threads to 32\n",
nr_cpus);
- nr_parallel = 32;
+ gopts->nr_parallel = 32;
} else {
- nr_parallel = nr_cpus;
+ gopts->nr_parallel = nr_cpus;
+ }
+
+ /*
+ * src and dst each require bytes / page_size number of hugepages.
+ * Ensure nr_parallel - 1 hugepages on top of that to account
+ * for racy extra reservation of hugepages.
+ */
+ if (gopts->test_type == TEST_HUGETLB &&
+ get_free_hugepages() < 2 * (bytes / gopts->page_size) + gopts->nr_parallel - 1) {
+ printf("skip: Skipping userfaultfd... not enough hugepages\n");
+ return KSFT_SKIP;
}
- nr_pages_per_cpu = bytes / page_size / nr_parallel;
- if (!nr_pages_per_cpu) {
+ gopts->nr_pages_per_cpu = bytes / gopts->page_size / gopts->nr_parallel;
+ if (!gopts->nr_pages_per_cpu) {
_err("pages_per_cpu = 0, cannot test (%lu / %lu / %lu)",
- bytes, page_size, nr_parallel);
+ bytes, gopts->page_size, gopts->nr_parallel);
usage();
}
@@ -476,11 +501,11 @@ int main(int argc, char **argv)
_err("invalid bounces");
usage();
}
- nr_pages = nr_pages_per_cpu * nr_parallel;
+ gopts->nr_pages = gopts->nr_pages_per_cpu * gopts->nr_parallel;
printf("nr_pages: %lu, nr_pages_per_cpu: %lu\n",
- nr_pages, nr_pages_per_cpu);
- return userfaultfd_stress();
+ gopts->nr_pages, gopts->nr_pages_per_cpu);
+ return userfaultfd_stress(gopts);
}
#else /* __NR_userfaultfd */
diff --git a/tools/testing/selftests/mm/uffd-unit-tests.c b/tools/testing/selftests/mm/uffd-unit-tests.c
index 50501b38e34e..9e3be2ee7f1b 100644
--- a/tools/testing/selftests/mm/uffd-unit-tests.c
+++ b/tools/testing/selftests/mm/uffd-unit-tests.c
@@ -76,7 +76,7 @@ struct uffd_test_args {
typedef struct uffd_test_args uffd_test_args_t;
/* Returns: UFFD_TEST_* */
-typedef void (*uffd_test_fn)(uffd_test_args_t *);
+typedef void (*uffd_test_fn)(uffd_global_test_opts_t *, uffd_test_args_t *);
typedef struct {
const char *name;
@@ -181,33 +181,6 @@ out:
return 1;
}
-/*
- * This function initializes the global variables. TODO: remove global
- * vars and then remove this.
- */
-static int
-uffd_setup_environment(uffd_test_args_t *args, uffd_test_case_t *test,
- mem_type_t *mem_type, const char **errmsg)
-{
- map_shared = mem_type->shared;
- uffd_test_ops = mem_type->mem_ops;
- uffd_test_case_ops = test->test_case_ops;
-
- if (mem_type->mem_flag & (MEM_HUGETLB_PRIVATE | MEM_HUGETLB))
- page_size = default_huge_page_size();
- else
- page_size = psize();
-
- /* Ensure we have at least 2 pages */
- nr_pages = MAX(UFFD_TEST_MEM_SIZE, page_size * 2) / page_size;
- /* TODO: remove this global var.. it's so ugly */
- nr_parallel = 1;
-
- /* Initialize test arguments */
- args->mem_type = mem_type;
-
- return uffd_test_ctx_init(test->uffd_feature_required, errmsg);
-}
static bool uffd_feature_supported(uffd_test_case_t *test)
{
@@ -237,7 +210,8 @@ static int pagemap_open(void)
} while (0)
typedef struct {
- int parent_uffd, child_uffd;
+ uffd_global_test_opts_t *gopts;
+ int child_uffd;
} fork_event_args;
static void *fork_event_consumer(void *data)
@@ -245,10 +219,10 @@ static void *fork_event_consumer(void *data)
fork_event_args *args = data;
struct uffd_msg msg = { 0 };
- ready_for_fork = true;
+ args->gopts->ready_for_fork = true;
/* Read until a full msg received */
- while (uffd_read_msg(args->parent_uffd, &msg));
+ while (uffd_read_msg(args->gopts, &msg));
if (msg.event != UFFD_EVENT_FORK)
err("wrong message: %u\n", msg.event);
@@ -304,9 +278,9 @@ static void unpin_pages(pin_args *args)
args->pinned = false;
}
-static int pagemap_test_fork(int uffd, bool with_event, bool test_pin)
+static int pagemap_test_fork(uffd_global_test_opts_t *gopts, bool with_event, bool test_pin)
{
- fork_event_args args = { .parent_uffd = uffd, .child_uffd = -1 };
+ fork_event_args args = { .gopts = gopts, .child_uffd = -1 };
pthread_t thread;
pid_t child;
uint64_t value;
@@ -314,10 +288,10 @@ static int pagemap_test_fork(int uffd, bool with_event, bool test_pin)
/* Prepare a thread to resolve EVENT_FORK */
if (with_event) {
- ready_for_fork = false;
+ gopts->ready_for_fork = false;
if (pthread_create(&thread, NULL, fork_event_consumer, &args))
err("pthread_create()");
- while (!ready_for_fork)
+ while (!gopts->ready_for_fork)
; /* Wait for the poll_thread to start executing before forking */
}
@@ -328,14 +302,14 @@ static int pagemap_test_fork(int uffd, bool with_event, bool test_pin)
fd = pagemap_open();
- if (test_pin && pin_pages(&args, area_dst, page_size))
+ if (test_pin && pin_pages(&args, gopts->area_dst, gopts->page_size))
/*
* Normally when reach here we have pinned in
* previous tests, so shouldn't fail anymore
*/
err("pin page failed in child");
- value = pagemap_get_entry(fd, area_dst);
+ value = pagemap_get_entry(fd, gopts->area_dst);
/*
* After fork(), we should handle uffd-wp bit differently:
*
@@ -361,70 +335,70 @@ static int pagemap_test_fork(int uffd, bool with_event, bool test_pin)
return result;
}
-static void uffd_wp_unpopulated_test(uffd_test_args_t *args)
+static void uffd_wp_unpopulated_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *args)
{
uint64_t value;
int pagemap_fd;
- if (uffd_register(uffd, area_dst, nr_pages * page_size,
+ if (uffd_register(gopts->uffd, gopts->area_dst, gopts->nr_pages * gopts->page_size,
false, true, false))
err("register failed");
pagemap_fd = pagemap_open();
/* Test applying pte marker to anon unpopulated */
- wp_range(uffd, (uint64_t)area_dst, page_size, true);
- value = pagemap_get_entry(pagemap_fd, area_dst);
+ wp_range(gopts->uffd, (uint64_t)gopts->area_dst, gopts->page_size, true);
+ value = pagemap_get_entry(pagemap_fd, gopts->area_dst);
pagemap_check_wp(value, true);
/* Test unprotect on anon pte marker */
- wp_range(uffd, (uint64_t)area_dst, page_size, false);
- value = pagemap_get_entry(pagemap_fd, area_dst);
+ wp_range(gopts->uffd, (uint64_t)gopts->area_dst, gopts->page_size, false);
+ value = pagemap_get_entry(pagemap_fd, gopts->area_dst);
pagemap_check_wp(value, false);
/* Test zap on anon marker */
- wp_range(uffd, (uint64_t)area_dst, page_size, true);
- if (madvise(area_dst, page_size, MADV_DONTNEED))
+ wp_range(gopts->uffd, (uint64_t)gopts->area_dst, gopts->page_size, true);
+ if (madvise(gopts->area_dst, gopts->page_size, MADV_DONTNEED))
err("madvise(MADV_DONTNEED) failed");
- value = pagemap_get_entry(pagemap_fd, area_dst);
+ value = pagemap_get_entry(pagemap_fd, gopts->area_dst);
pagemap_check_wp(value, false);
/* Test fault in after marker removed */
- *area_dst = 1;
- value = pagemap_get_entry(pagemap_fd, area_dst);
+ *gopts->area_dst = 1;
+ value = pagemap_get_entry(pagemap_fd, gopts->area_dst);
pagemap_check_wp(value, false);
/* Drop it to make pte none again */
- if (madvise(area_dst, page_size, MADV_DONTNEED))
+ if (madvise(gopts->area_dst, gopts->page_size, MADV_DONTNEED))
err("madvise(MADV_DONTNEED) failed");
/* Test read-zero-page upon pte marker */
- wp_range(uffd, (uint64_t)area_dst, page_size, true);
- *(volatile char *)area_dst;
+ wp_range(gopts->uffd, (uint64_t)gopts->area_dst, gopts->page_size, true);
+ *(volatile char *)gopts->area_dst;
/* Drop it to make pte none again */
- if (madvise(area_dst, page_size, MADV_DONTNEED))
+ if (madvise(gopts->area_dst, gopts->page_size, MADV_DONTNEED))
err("madvise(MADV_DONTNEED) failed");
uffd_test_pass();
}
-static void uffd_wp_fork_test_common(uffd_test_args_t *args,
+static void uffd_wp_fork_test_common(uffd_global_test_opts_t *gopts, uffd_test_args_t *args,
bool with_event)
{
int pagemap_fd;
uint64_t value;
- if (uffd_register(uffd, area_dst, nr_pages * page_size,
+ if (uffd_register(gopts->uffd, gopts->area_dst, gopts->nr_pages * gopts->page_size,
false, true, false))
err("register failed");
pagemap_fd = pagemap_open();
/* Touch the page */
- *area_dst = 1;
- wp_range(uffd, (uint64_t)area_dst, page_size, true);
- value = pagemap_get_entry(pagemap_fd, area_dst);
+ *gopts->area_dst = 1;
+ wp_range(gopts->uffd, (uint64_t)gopts->area_dst, gopts->page_size, true);
+ value = pagemap_get_entry(pagemap_fd, gopts->area_dst);
pagemap_check_wp(value, true);
- if (pagemap_test_fork(uffd, with_event, false)) {
+ if (pagemap_test_fork(gopts, with_event, false)) {
uffd_test_fail("Detected %s uffd-wp bit in child in present pte",
with_event ? "missing" : "stall");
goto out;
@@ -442,79 +416,80 @@ static void uffd_wp_fork_test_common(uffd_test_args_t *args,
* to expose pte markers.
*/
if (args->mem_type->shared) {
- if (madvise(area_dst, page_size, MADV_DONTNEED))
+ if (madvise(gopts->area_dst, gopts->page_size, MADV_DONTNEED))
err("MADV_DONTNEED");
} else {
/*
* NOTE: ignore retval because private-hugetlb doesn't yet
* support swapping, so it could fail.
*/
- madvise(area_dst, page_size, MADV_PAGEOUT);
+ madvise(gopts->area_dst, gopts->page_size, MADV_PAGEOUT);
}
/* Uffd-wp should persist even swapped out */
- value = pagemap_get_entry(pagemap_fd, area_dst);
+ value = pagemap_get_entry(pagemap_fd, gopts->area_dst);
pagemap_check_wp(value, true);
- if (pagemap_test_fork(uffd, with_event, false)) {
+ if (pagemap_test_fork(gopts, with_event, false)) {
uffd_test_fail("Detected %s uffd-wp bit in child in zapped pte",
with_event ? "missing" : "stall");
goto out;
}
/* Unprotect; this tests swap pte modifications */
- wp_range(uffd, (uint64_t)area_dst, page_size, false);
- value = pagemap_get_entry(pagemap_fd, area_dst);
+ wp_range(gopts->uffd, (uint64_t)gopts->area_dst, gopts->page_size, false);
+ value = pagemap_get_entry(pagemap_fd, gopts->area_dst);
pagemap_check_wp(value, false);
/* Fault in the page from disk */
- *area_dst = 2;
- value = pagemap_get_entry(pagemap_fd, area_dst);
+ *gopts->area_dst = 2;
+ value = pagemap_get_entry(pagemap_fd, gopts->area_dst);
pagemap_check_wp(value, false);
uffd_test_pass();
out:
- if (uffd_unregister(uffd, area_dst, nr_pages * page_size))
+ if (uffd_unregister(gopts->uffd, gopts->area_dst, gopts->nr_pages * gopts->page_size))
err("unregister failed");
close(pagemap_fd);
}
-static void uffd_wp_fork_test(uffd_test_args_t *args)
+static void uffd_wp_fork_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *args)
{
- uffd_wp_fork_test_common(args, false);
+ uffd_wp_fork_test_common(gopts, args, false);
}
-static void uffd_wp_fork_with_event_test(uffd_test_args_t *args)
+static void uffd_wp_fork_with_event_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *args)
{
- uffd_wp_fork_test_common(args, true);
+ uffd_wp_fork_test_common(gopts, args, true);
}
-static void uffd_wp_fork_pin_test_common(uffd_test_args_t *args,
+static void uffd_wp_fork_pin_test_common(uffd_global_test_opts_t *gopts,
+ uffd_test_args_t *args,
bool with_event)
{
int pagemap_fd;
pin_args pin_args = {};
- if (uffd_register(uffd, area_dst, page_size, false, true, false))
+ if (uffd_register(gopts->uffd, gopts->area_dst, gopts->page_size, false, true, false))
err("register failed");
pagemap_fd = pagemap_open();
/* Touch the page */
- *area_dst = 1;
- wp_range(uffd, (uint64_t)area_dst, page_size, true);
+ *gopts->area_dst = 1;
+ wp_range(gopts->uffd, (uint64_t)gopts->area_dst, gopts->page_size, true);
/*
* 1. First pin, then fork(). This tests fork() special path when
* doing early CoW if the page is private.
*/
- if (pin_pages(&pin_args, area_dst, page_size)) {
+ if (pin_pages(&pin_args, gopts->area_dst, gopts->page_size)) {
uffd_test_skip("Possibly CONFIG_GUP_TEST missing "
"or unprivileged");
close(pagemap_fd);
- uffd_unregister(uffd, area_dst, page_size);
+ uffd_unregister(gopts->uffd, gopts->area_dst, gopts->page_size);
return;
}
- if (pagemap_test_fork(uffd, with_event, false)) {
+ if (pagemap_test_fork(gopts, with_event, false)) {
uffd_test_fail("Detected %s uffd-wp bit in early CoW of fork()",
with_event ? "missing" : "stall");
unpin_pages(&pin_args);
@@ -527,49 +502,50 @@ static void uffd_wp_fork_pin_test_common(uffd_test_args_t *args,
* 2. First fork(), then pin (in the child, where test_pin==true).
* This tests COR, aka, page unsharing on private memories.
*/
- if (pagemap_test_fork(uffd, with_event, true)) {
+ if (pagemap_test_fork(gopts, with_event, true)) {
uffd_test_fail("Detected %s uffd-wp bit when RO pin",
with_event ? "missing" : "stall");
goto out;
}
uffd_test_pass();
out:
- if (uffd_unregister(uffd, area_dst, page_size))
+ if (uffd_unregister(gopts->uffd, gopts->area_dst, gopts->page_size))
err("register failed");
close(pagemap_fd);
}
-static void uffd_wp_fork_pin_test(uffd_test_args_t *args)
+static void uffd_wp_fork_pin_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *args)
{
- uffd_wp_fork_pin_test_common(args, false);
+ uffd_wp_fork_pin_test_common(gopts, args, false);
}
-static void uffd_wp_fork_pin_with_event_test(uffd_test_args_t *args)
+static void uffd_wp_fork_pin_with_event_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *args)
{
- uffd_wp_fork_pin_test_common(args, true);
+ uffd_wp_fork_pin_test_common(gopts, args, true);
}
-static void check_memory_contents(char *p)
+static void check_memory_contents(uffd_global_test_opts_t *gopts, char *p)
{
unsigned long i, j;
uint8_t expected_byte;
- for (i = 0; i < nr_pages; ++i) {
+ for (i = 0; i < gopts->nr_pages; ++i) {
expected_byte = ~((uint8_t)(i % ((uint8_t)-1)));
- for (j = 0; j < page_size; j++) {
- uint8_t v = *(uint8_t *)(p + (i * page_size) + j);
+ for (j = 0; j < gopts->page_size; j++) {
+ uint8_t v = *(uint8_t *)(p + (i * gopts->page_size) + j);
if (v != expected_byte)
err("unexpected page contents");
}
}
}
-static void uffd_minor_test_common(bool test_collapse, bool test_wp)
+static void uffd_minor_test_common(uffd_global_test_opts_t *gopts, bool test_collapse, bool test_wp)
{
unsigned long p;
pthread_t uffd_mon;
char c;
struct uffd_args args = { 0 };
+ args.gopts = gopts;
/*
* NOTE: MADV_COLLAPSE is not yet compatible with WP, so testing
@@ -577,7 +553,7 @@ static void uffd_minor_test_common(bool test_collapse, bool test_wp)
*/
assert(!(test_collapse && test_wp));
- if (uffd_register(uffd, area_dst_alias, nr_pages * page_size,
+ if (uffd_register(gopts->uffd, gopts->area_dst_alias, gopts->nr_pages * gopts->page_size,
/* NOTE! MADV_COLLAPSE may not work with uffd-wp */
false, test_wp, true))
err("register failure");
@@ -586,9 +562,9 @@ static void uffd_minor_test_common(bool test_collapse, bool test_wp)
* After registering with UFFD, populate the non-UFFD-registered side of
* the shared mapping. This should *not* trigger any UFFD minor faults.
*/
- for (p = 0; p < nr_pages; ++p)
- memset(area_dst + (p * page_size), p % ((uint8_t)-1),
- page_size);
+ for (p = 0; p < gopts->nr_pages; ++p)
+ memset(gopts->area_dst + (p * gopts->page_size), p % ((uint8_t)-1),
+ gopts->page_size);
args.apply_wp = test_wp;
if (pthread_create(&uffd_mon, NULL, uffd_poll_thread, &args))
@@ -600,50 +576,51 @@ static void uffd_minor_test_common(bool test_collapse, bool test_wp)
* fault. uffd_poll_thread will resolve the fault by bit-flipping the
* page's contents, and then issuing a CONTINUE ioctl.
*/
- check_memory_contents(area_dst_alias);
+ check_memory_contents(gopts, gopts->area_dst_alias);
- if (write(pipefd[1], &c, sizeof(c)) != sizeof(c))
+ if (write(gopts->pipefd[1], &c, sizeof(c)) != sizeof(c))
err("pipe write");
if (pthread_join(uffd_mon, NULL))
err("join() failed");
if (test_collapse) {
- if (madvise(area_dst_alias, nr_pages * page_size,
+ if (madvise(gopts->area_dst_alias, gopts->nr_pages * gopts->page_size,
MADV_COLLAPSE)) {
/* It's fine to fail for this one... */
uffd_test_skip("MADV_COLLAPSE failed");
return;
}
- uffd_test_ops->check_pmd_mapping(area_dst,
- nr_pages * page_size /
+ uffd_test_ops->check_pmd_mapping(gopts,
+ gopts->area_dst,
+ gopts->nr_pages * gopts->page_size /
read_pmd_pagesize());
/*
* This won't cause uffd-fault - it purely just makes sure there
* was no corruption.
*/
- check_memory_contents(area_dst_alias);
+ check_memory_contents(gopts, gopts->area_dst_alias);
}
- if (args.missing_faults != 0 || args.minor_faults != nr_pages)
+ if (args.missing_faults != 0 || args.minor_faults != gopts->nr_pages)
uffd_test_fail("stats check error");
else
uffd_test_pass();
}
-void uffd_minor_test(uffd_test_args_t *args)
+void uffd_minor_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *args)
{
- uffd_minor_test_common(false, false);
+ uffd_minor_test_common(gopts, false, false);
}
-void uffd_minor_wp_test(uffd_test_args_t *args)
+void uffd_minor_wp_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *args)
{
- uffd_minor_test_common(false, true);
+ uffd_minor_test_common(gopts, false, true);
}
-void uffd_minor_collapse_test(uffd_test_args_t *args)
+void uffd_minor_collapse_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *args)
{
- uffd_minor_test_common(true, false);
+ uffd_minor_test_common(gopts, true, false);
}
static sigjmp_buf jbuf, *sigbuf;
@@ -678,7 +655,7 @@ static void sighndl(int sig, siginfo_t *siginfo, void *ptr)
* This also tests UFFD_FEATURE_EVENT_FORK event along with the signal
* feature. Using monitor thread, verify no userfault events are generated.
*/
-static int faulting_process(int signal_test, bool wp)
+static int faulting_process(uffd_global_test_opts_t *gopts, int signal_test, bool wp)
{
unsigned long nr, i;
unsigned long long count;
@@ -687,7 +664,7 @@ static int faulting_process(int signal_test, bool wp)
struct sigaction act;
volatile unsigned long signalled = 0;
- split_nr_pages = (nr_pages + 1) / 2;
+ split_nr_pages = (gopts->nr_pages + 1) / 2;
if (signal_test) {
sigbuf = &jbuf;
@@ -701,7 +678,7 @@ static int faulting_process(int signal_test, bool wp)
for (nr = 0; nr < split_nr_pages; nr++) {
volatile int steps = 1;
- unsigned long offset = nr * page_size;
+ unsigned long offset = nr * gopts->page_size;
if (signal_test) {
if (sigsetjmp(*sigbuf, 1) != 0) {
@@ -713,15 +690,15 @@ static int faulting_process(int signal_test, bool wp)
if (steps == 1) {
/* This is a MISSING request */
steps++;
- if (copy_page(uffd, offset, wp))
+ if (copy_page(gopts, offset, wp))
signalled++;
} else {
/* This is a WP request */
assert(steps == 2);
- wp_range(uffd,
- (__u64)area_dst +
+ wp_range(gopts->uffd,
+ (__u64)gopts->area_dst +
offset,
- page_size, false);
+ gopts->page_size, false);
}
} else {
signalled++;
@@ -730,51 +707,53 @@ static int faulting_process(int signal_test, bool wp)
}
}
- count = *area_count(area_dst, nr);
- if (count != count_verify[nr])
+ count = *area_count(gopts->area_dst, nr, gopts);
+ if (count != gopts->count_verify[nr])
err("nr %lu memory corruption %llu %llu\n",
- nr, count, count_verify[nr]);
+ nr, count, gopts->count_verify[nr]);
/*
* Trigger write protection if there is by writing
* the same value back.
*/
- *area_count(area_dst, nr) = count;
+ *area_count(gopts->area_dst, nr, gopts) = count;
}
if (signal_test)
return signalled != split_nr_pages;
- area_dst = mremap(area_dst, nr_pages * page_size, nr_pages * page_size,
- MREMAP_MAYMOVE | MREMAP_FIXED, area_src);
- if (area_dst == MAP_FAILED)
+ gopts->area_dst = mremap(gopts->area_dst, gopts->nr_pages * gopts->page_size,
+ gopts->nr_pages * gopts->page_size,
+ MREMAP_MAYMOVE | MREMAP_FIXED,
+ gopts->area_src);
+ if (gopts->area_dst == MAP_FAILED)
err("mremap");
/* Reset area_src since we just clobbered it */
- area_src = NULL;
+ gopts->area_src = NULL;
- for (; nr < nr_pages; nr++) {
- count = *area_count(area_dst, nr);
- if (count != count_verify[nr]) {
+ for (; nr < gopts->nr_pages; nr++) {
+ count = *area_count(gopts->area_dst, nr, gopts);
+ if (count != gopts->count_verify[nr]) {
err("nr %lu memory corruption %llu %llu\n",
- nr, count, count_verify[nr]);
+ nr, count, gopts->count_verify[nr]);
}
/*
* Trigger write protection if there is by writing
* the same value back.
*/
- *area_count(area_dst, nr) = count;
+ *area_count(gopts->area_dst, nr, gopts) = count;
}
- uffd_test_ops->release_pages(area_dst);
+ uffd_test_ops->release_pages(gopts, gopts->area_dst);
- for (nr = 0; nr < nr_pages; nr++)
- for (i = 0; i < page_size; i++)
- if (*(area_dst + nr * page_size + i) != 0)
+ for (nr = 0; nr < gopts->nr_pages; nr++)
+ for (i = 0; i < gopts->page_size; i++)
+ if (*(gopts->area_dst + nr * gopts->page_size + i) != 0)
err("page %lu offset %lu is not zero", nr, i);
return 0;
}
-static void uffd_sigbus_test_common(bool wp)
+static void uffd_sigbus_test_common(uffd_global_test_opts_t *gopts, bool wp)
{
unsigned long userfaults;
pthread_t uffd_mon;
@@ -782,25 +761,26 @@ static void uffd_sigbus_test_common(bool wp)
int err;
char c;
struct uffd_args args = { 0 };
+ args.gopts = gopts;
- ready_for_fork = false;
+ gopts->ready_for_fork = false;
- fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK);
+ fcntl(gopts->uffd, F_SETFL, gopts->uffd_flags | O_NONBLOCK);
- if (uffd_register(uffd, area_dst, nr_pages * page_size,
+ if (uffd_register(gopts->uffd, gopts->area_dst, gopts->nr_pages * gopts->page_size,
true, wp, false))
err("register failure");
- if (faulting_process(1, wp))
+ if (faulting_process(gopts, 1, wp))
err("faulting process failed");
- uffd_test_ops->release_pages(area_dst);
+ uffd_test_ops->release_pages(gopts, gopts->area_dst);
args.apply_wp = wp;
if (pthread_create(&uffd_mon, NULL, uffd_poll_thread, &args))
err("uffd_poll_thread create");
- while (!ready_for_fork)
+ while (!gopts->ready_for_fork)
; /* Wait for the poll_thread to start executing before forking */
pid = fork();
@@ -808,12 +788,12 @@ static void uffd_sigbus_test_common(bool wp)
err("fork");
if (!pid)
- exit(faulting_process(2, wp));
+ exit(faulting_process(gopts, 2, wp));
waitpid(pid, &err, 0);
if (err)
err("faulting process failed");
- if (write(pipefd[1], &c, sizeof(c)) != sizeof(c))
+ if (write(gopts->pipefd[1], &c, sizeof(c)) != sizeof(c))
err("pipe write");
if (pthread_join(uffd_mon, (void **)&userfaults))
err("pthread_join()");
@@ -824,28 +804,29 @@ static void uffd_sigbus_test_common(bool wp)
uffd_test_pass();
}
-static void uffd_sigbus_test(uffd_test_args_t *args)
+static void uffd_sigbus_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *args)
{
- uffd_sigbus_test_common(false);
+ uffd_sigbus_test_common(gopts, false);
}
-static void uffd_sigbus_wp_test(uffd_test_args_t *args)
+static void uffd_sigbus_wp_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *args)
{
- uffd_sigbus_test_common(true);
+ uffd_sigbus_test_common(gopts, true);
}
-static void uffd_events_test_common(bool wp)
+static void uffd_events_test_common(uffd_global_test_opts_t *gopts, bool wp)
{
pthread_t uffd_mon;
pid_t pid;
int err;
char c;
struct uffd_args args = { 0 };
+ args.gopts = gopts;
- ready_for_fork = false;
+ gopts->ready_for_fork = false;
- fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK);
- if (uffd_register(uffd, area_dst, nr_pages * page_size,
+ fcntl(gopts->uffd, F_SETFL, gopts->uffd_flags | O_NONBLOCK);
+ if (uffd_register(gopts->uffd, gopts->area_dst, gopts->nr_pages * gopts->page_size,
true, wp, false))
err("register failure");
@@ -853,7 +834,7 @@ static void uffd_events_test_common(bool wp)
if (pthread_create(&uffd_mon, NULL, uffd_poll_thread, &args))
err("uffd_poll_thread create");
- while (!ready_for_fork)
+ while (!gopts->ready_for_fork)
; /* Wait for the poll_thread to start executing before forking */
pid = fork();
@@ -861,39 +842,39 @@ static void uffd_events_test_common(bool wp)
err("fork");
if (!pid)
- exit(faulting_process(0, wp));
+ exit(faulting_process(gopts, 0, wp));
waitpid(pid, &err, 0);
if (err)
err("faulting process failed");
- if (write(pipefd[1], &c, sizeof(c)) != sizeof(c))
+ if (write(gopts->pipefd[1], &c, sizeof(c)) != sizeof(c))
err("pipe write");
if (pthread_join(uffd_mon, NULL))
err("pthread_join()");
- if (args.missing_faults != nr_pages)
+ if (args.missing_faults != gopts->nr_pages)
uffd_test_fail("Fault counts wrong");
else
uffd_test_pass();
}
-static void uffd_events_test(uffd_test_args_t *args)
+static void uffd_events_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *args)
{
- uffd_events_test_common(false);
+ uffd_events_test_common(gopts, false);
}
-static void uffd_events_wp_test(uffd_test_args_t *args)
+static void uffd_events_wp_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *args)
{
- uffd_events_test_common(true);
+ uffd_events_test_common(gopts, true);
}
-static void retry_uffdio_zeropage(int ufd,
+static void retry_uffdio_zeropage(uffd_global_test_opts_t *gopts,
struct uffdio_zeropage *uffdio_zeropage)
{
- uffd_test_ops->alias_mapping(&uffdio_zeropage->range.start,
+ uffd_test_ops->alias_mapping(gopts, &uffdio_zeropage->range.start,
uffdio_zeropage->range.len,
0);
- if (ioctl(ufd, UFFDIO_ZEROPAGE, uffdio_zeropage)) {
+ if (ioctl(gopts->uffd, UFFDIO_ZEROPAGE, uffdio_zeropage)) {
if (uffdio_zeropage->zeropage != -EEXIST)
err("UFFDIO_ZEROPAGE error: %"PRId64,
(int64_t)uffdio_zeropage->zeropage);
@@ -903,16 +884,16 @@ static void retry_uffdio_zeropage(int ufd,
}
}
-static bool do_uffdio_zeropage(int ufd, bool has_zeropage)
+static bool do_uffdio_zeropage(uffd_global_test_opts_t *gopts, bool has_zeropage)
{
struct uffdio_zeropage uffdio_zeropage = { 0 };
int ret;
__s64 res;
- uffdio_zeropage.range.start = (unsigned long) area_dst;
- uffdio_zeropage.range.len = page_size;
+ uffdio_zeropage.range.start = (unsigned long) gopts->area_dst;
+ uffdio_zeropage.range.len = gopts->page_size;
uffdio_zeropage.mode = 0;
- ret = ioctl(ufd, UFFDIO_ZEROPAGE, &uffdio_zeropage);
+ ret = ioctl(gopts->uffd, UFFDIO_ZEROPAGE, &uffdio_zeropage);
res = uffdio_zeropage.zeropage;
if (ret) {
/* real retval in ufdio_zeropage.zeropage */
@@ -921,10 +902,10 @@ static bool do_uffdio_zeropage(int ufd, bool has_zeropage)
else if (res != -EINVAL)
err("UFFDIO_ZEROPAGE not -EINVAL");
} else if (has_zeropage) {
- if (res != page_size)
+ if (res != gopts->page_size)
err("UFFDIO_ZEROPAGE unexpected size");
else
- retry_uffdio_zeropage(ufd, &uffdio_zeropage);
+ retry_uffdio_zeropage(gopts, &uffdio_zeropage);
return true;
} else
err("UFFDIO_ZEROPAGE succeeded");
@@ -950,25 +931,29 @@ uffd_register_detect_zeropage(int uffd, void *addr, uint64_t len)
}
/* exercise UFFDIO_ZEROPAGE */
-static void uffd_zeropage_test(uffd_test_args_t *args)
+static void uffd_zeropage_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *args)
{
bool has_zeropage;
int i;
- has_zeropage = uffd_register_detect_zeropage(uffd, area_dst, page_size);
- if (area_dst_alias)
+ has_zeropage = uffd_register_detect_zeropage(gopts->uffd,
+ gopts->area_dst,
+ gopts->page_size);
+ if (gopts->area_dst_alias)
/* Ignore the retval; we already have it */
- uffd_register_detect_zeropage(uffd, area_dst_alias, page_size);
+ uffd_register_detect_zeropage(gopts->uffd, gopts->area_dst_alias, gopts->page_size);
- if (do_uffdio_zeropage(uffd, has_zeropage))
- for (i = 0; i < page_size; i++)
- if (area_dst[i] != 0)
+ if (do_uffdio_zeropage(gopts, has_zeropage))
+ for (i = 0; i < gopts->page_size; i++)
+ if (gopts->area_dst[i] != 0)
err("data non-zero at offset %d\n", i);
- if (uffd_unregister(uffd, area_dst, page_size))
+ if (uffd_unregister(gopts->uffd, gopts->area_dst, gopts->page_size))
err("unregister");
- if (area_dst_alias && uffd_unregister(uffd, area_dst_alias, page_size))
+ if (gopts->area_dst_alias && uffd_unregister(gopts->uffd,
+ gopts->area_dst_alias,
+ gopts->page_size))
err("unregister");
uffd_test_pass();
@@ -987,26 +972,27 @@ static void uffd_register_poison(int uffd, void *addr, uint64_t len)
err("registered area doesn't support COPY and POISON ioctls");
}
-static void do_uffdio_poison(int uffd, unsigned long offset)
+static void do_uffdio_poison(uffd_global_test_opts_t *gopts, unsigned long offset)
{
struct uffdio_poison uffdio_poison = { 0 };
int ret;
__s64 res;
- uffdio_poison.range.start = (unsigned long) area_dst + offset;
- uffdio_poison.range.len = page_size;
+ uffdio_poison.range.start = (unsigned long) gopts->area_dst + offset;
+ uffdio_poison.range.len = gopts->page_size;
uffdio_poison.mode = 0;
- ret = ioctl(uffd, UFFDIO_POISON, &uffdio_poison);
+ ret = ioctl(gopts->uffd, UFFDIO_POISON, &uffdio_poison);
res = uffdio_poison.updated;
if (ret)
err("UFFDIO_POISON error: %"PRId64, (int64_t)res);
- else if (res != page_size)
+ else if (res != gopts->page_size)
err("UFFDIO_POISON unexpected size: %"PRId64, (int64_t)res);
}
-static void uffd_poison_handle_fault(
- struct uffd_msg *msg, struct uffd_args *args)
+static void uffd_poison_handle_fault(uffd_global_test_opts_t *gopts,
+ struct uffd_msg *msg,
+ struct uffd_args *args)
{
unsigned long offset;
@@ -1017,20 +1003,20 @@ static void uffd_poison_handle_fault(
(UFFD_PAGEFAULT_FLAG_WP | UFFD_PAGEFAULT_FLAG_MINOR))
err("unexpected fault type %llu", msg->arg.pagefault.flags);
- offset = (char *)(unsigned long)msg->arg.pagefault.address - area_dst;
- offset &= ~(page_size-1);
+ offset = (char *)(unsigned long)msg->arg.pagefault.address - gopts->area_dst;
+ offset &= ~(gopts->page_size-1);
/* Odd pages -> copy zeroed page; even pages -> poison. */
- if (offset & page_size)
- copy_page(uffd, offset, false);
+ if (offset & gopts->page_size)
+ copy_page(gopts, offset, false);
else
- do_uffdio_poison(uffd, offset);
+ do_uffdio_poison(gopts, offset);
}
/* Make sure to cover odd/even, and minimum duplications */
#define UFFD_POISON_TEST_NPAGES 4
-static void uffd_poison_test(uffd_test_args_t *targs)
+static void uffd_poison_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *targs)
{
pthread_t uffd_mon;
char c;
@@ -1039,15 +1025,17 @@ static void uffd_poison_test(uffd_test_args_t *targs)
unsigned long nr_sigbus = 0;
unsigned long nr, poison_pages = UFFD_POISON_TEST_NPAGES;
- if (nr_pages < poison_pages) {
- uffd_test_skip("Too few pages for POISON test");
+ if (gopts->nr_pages < poison_pages) {
+ uffd_test_skip("Too less pages for POISON test");
return;
}
- fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK);
+ args.gopts = gopts;
+
+ fcntl(gopts->uffd, F_SETFL, gopts->uffd_flags | O_NONBLOCK);
- uffd_register_poison(uffd, area_dst, poison_pages * page_size);
- memset(area_src, 0, poison_pages * page_size);
+ uffd_register_poison(gopts->uffd, gopts->area_dst, poison_pages * gopts->page_size);
+ memset(gopts->area_src, 0, poison_pages * gopts->page_size);
args.handle_fault = uffd_poison_handle_fault;
if (pthread_create(&uffd_mon, NULL, uffd_poll_thread, &args))
@@ -1060,8 +1048,8 @@ static void uffd_poison_test(uffd_test_args_t *targs)
err("sigaction");
for (nr = 0; nr < poison_pages; ++nr) {
- unsigned long offset = nr * page_size;
- const char *bytes = (const char *) area_dst + offset;
+ unsigned long offset = nr * gopts->page_size;
+ const char *bytes = (const char *) gopts->area_dst + offset;
const char *i;
if (sigsetjmp(*sigbuf, 1)) {
@@ -1074,14 +1062,14 @@ static void uffd_poison_test(uffd_test_args_t *targs)
continue;
}
- for (i = bytes; i < bytes + page_size; ++i) {
+ for (i = bytes; i < bytes + gopts->page_size; ++i) {
if (*i)
err("nonzero byte in area_dst (%p) at %p: %u",
- area_dst, i, *i);
+ gopts->area_dst, i, *i);
}
}
- if (write(pipefd[1], &c, sizeof(c)) != sizeof(c))
+ if (write(gopts->pipefd[1], &c, sizeof(c)) != sizeof(c))
err("pipe write");
if (pthread_join(uffd_mon, NULL))
err("pthread_join()");
@@ -1094,7 +1082,9 @@ static void uffd_poison_test(uffd_test_args_t *targs)
}
static void
-uffd_move_handle_fault_common(struct uffd_msg *msg, struct uffd_args *args,
+uffd_move_handle_fault_common(uffd_global_test_opts_t *gopts,
+ struct uffd_msg *msg,
+ struct uffd_args *args,
unsigned long len)
{
unsigned long offset;
@@ -1106,28 +1096,32 @@ uffd_move_handle_fault_common(struct uffd_msg *msg, struct uffd_args *args,
(UFFD_PAGEFAULT_FLAG_WP | UFFD_PAGEFAULT_FLAG_MINOR | UFFD_PAGEFAULT_FLAG_WRITE))
err("unexpected fault type %llu", msg->arg.pagefault.flags);
- offset = (char *)(unsigned long)msg->arg.pagefault.address - area_dst;
+ offset = (char *)(unsigned long)msg->arg.pagefault.address - gopts->area_dst;
offset &= ~(len-1);
- if (move_page(uffd, offset, len))
+ if (move_page(gopts, offset, len))
args->missing_faults++;
}
-static void uffd_move_handle_fault(struct uffd_msg *msg,
+static void uffd_move_handle_fault(uffd_global_test_opts_t *gopts, struct uffd_msg *msg,
struct uffd_args *args)
{
- uffd_move_handle_fault_common(msg, args, page_size);
+ uffd_move_handle_fault_common(gopts, msg, args, gopts->page_size);
}
-static void uffd_move_pmd_handle_fault(struct uffd_msg *msg,
+static void uffd_move_pmd_handle_fault(uffd_global_test_opts_t *gopts, struct uffd_msg *msg,
struct uffd_args *args)
{
- uffd_move_handle_fault_common(msg, args, read_pmd_pagesize());
+ uffd_move_handle_fault_common(gopts, msg, args, read_pmd_pagesize());
}
static void
-uffd_move_test_common(uffd_test_args_t *targs, unsigned long chunk_size,
- void (*handle_fault)(struct uffd_msg *msg, struct uffd_args *args))
+uffd_move_test_common(uffd_global_test_opts_t *gopts,
+ uffd_test_args_t *targs,
+ unsigned long chunk_size,
+ void (*handle_fault)(struct uffd_global_test_opts *gopts,
+ struct uffd_msg *msg, struct uffd_args *args)
+)
{
unsigned long nr;
pthread_t uffd_mon;
@@ -1139,11 +1133,13 @@ uffd_move_test_common(uffd_test_args_t *targs, unsigned long chunk_size,
unsigned long src_offs = 0;
unsigned long dst_offs = 0;
+ args.gopts = gopts;
+
/* Prevent source pages from being mapped more than once */
- if (madvise(area_src, nr_pages * page_size, MADV_DONTFORK))
+ if (madvise(gopts->area_src, gopts->nr_pages * gopts->page_size, MADV_DONTFORK))
err("madvise(MADV_DONTFORK) failure");
- if (uffd_register(uffd, area_dst, nr_pages * page_size,
+ if (uffd_register(gopts->uffd, gopts->area_dst, gopts->nr_pages * gopts->page_size,
true, false, false))
err("register failure");
@@ -1151,22 +1147,22 @@ uffd_move_test_common(uffd_test_args_t *targs, unsigned long chunk_size,
if (pthread_create(&uffd_mon, NULL, uffd_poll_thread, &args))
err("uffd_poll_thread create");
- step_size = chunk_size / page_size;
- step_count = nr_pages / step_size;
+ step_size = chunk_size / gopts->page_size;
+ step_count = gopts->nr_pages / step_size;
- if (chunk_size > page_size) {
- char *aligned_src = ALIGN_UP(area_src, chunk_size);
- char *aligned_dst = ALIGN_UP(area_dst, chunk_size);
+ if (chunk_size > gopts->page_size) {
+ char *aligned_src = ALIGN_UP(gopts->area_src, chunk_size);
+ char *aligned_dst = ALIGN_UP(gopts->area_dst, chunk_size);
- if (aligned_src != area_src || aligned_dst != area_dst) {
- src_offs = (aligned_src - area_src) / page_size;
- dst_offs = (aligned_dst - area_dst) / page_size;
+ if (aligned_src != gopts->area_src || aligned_dst != gopts->area_dst) {
+ src_offs = (aligned_src - gopts->area_src) / gopts->page_size;
+ dst_offs = (aligned_dst - gopts->area_dst) / gopts->page_size;
step_count--;
}
- orig_area_src = area_src;
- orig_area_dst = area_dst;
- area_src = aligned_src;
- area_dst = aligned_dst;
+ orig_area_src = gopts->area_src;
+ orig_area_dst = gopts->area_dst;
+ gopts->area_src = aligned_src;
+ gopts->area_dst = aligned_dst;
}
/*
@@ -1180,34 +1176,34 @@ uffd_move_test_common(uffd_test_args_t *targs, unsigned long chunk_size,
/* Check area_src content */
for (i = 0; i < step_size; i++) {
- count = *area_count(area_src, nr + i);
- if (count != count_verify[src_offs + nr + i])
+ count = *area_count(gopts->area_src, nr + i, gopts);
+ if (count != gopts->count_verify[src_offs + nr + i])
err("nr %lu source memory invalid %llu %llu\n",
- nr + i, count, count_verify[src_offs + nr + i]);
+ nr + i, count, gopts->count_verify[src_offs + nr + i]);
}
/* Faulting into area_dst should move the page or the huge page */
for (i = 0; i < step_size; i++) {
- count = *area_count(area_dst, nr + i);
- if (count != count_verify[dst_offs + nr + i])
+ count = *area_count(gopts->area_dst, nr + i, gopts);
+ if (count != gopts->count_verify[dst_offs + nr + i])
err("nr %lu memory corruption %llu %llu\n",
- nr, count, count_verify[dst_offs + nr + i]);
+ nr, count, gopts->count_verify[dst_offs + nr + i]);
}
/* Re-check area_src content which should be empty */
for (i = 0; i < step_size; i++) {
- count = *area_count(area_src, nr + i);
+ count = *area_count(gopts->area_src, nr + i, gopts);
if (count != 0)
err("nr %lu move failed %llu %llu\n",
- nr, count, count_verify[src_offs + nr + i]);
+ nr, count, gopts->count_verify[src_offs + nr + i]);
}
}
- if (chunk_size > page_size) {
- area_src = orig_area_src;
- area_dst = orig_area_dst;
+ if (chunk_size > gopts->page_size) {
+ gopts->area_src = orig_area_src;
+ gopts->area_dst = orig_area_dst;
}
- if (write(pipefd[1], &c, sizeof(c)) != sizeof(c))
+ if (write(gopts->pipefd[1], &c, sizeof(c)) != sizeof(c))
err("pipe write");
if (pthread_join(uffd_mon, NULL))
err("join() failed");
@@ -1218,24 +1214,24 @@ uffd_move_test_common(uffd_test_args_t *targs, unsigned long chunk_size,
uffd_test_pass();
}
-static void uffd_move_test(uffd_test_args_t *targs)
+static void uffd_move_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *targs)
{
- uffd_move_test_common(targs, page_size, uffd_move_handle_fault);
+ uffd_move_test_common(gopts, targs, gopts->page_size, uffd_move_handle_fault);
}
-static void uffd_move_pmd_test(uffd_test_args_t *targs)
+static void uffd_move_pmd_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *targs)
{
- if (madvise(area_dst, nr_pages * page_size, MADV_HUGEPAGE))
+ if (madvise(gopts->area_dst, gopts->nr_pages * gopts->page_size, MADV_HUGEPAGE))
err("madvise(MADV_HUGEPAGE) failure");
- uffd_move_test_common(targs, read_pmd_pagesize(),
+ uffd_move_test_common(gopts, targs, read_pmd_pagesize(),
uffd_move_pmd_handle_fault);
}
-static void uffd_move_pmd_split_test(uffd_test_args_t *targs)
+static void uffd_move_pmd_split_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *targs)
{
- if (madvise(area_dst, nr_pages * page_size, MADV_NOHUGEPAGE))
+ if (madvise(gopts->area_dst, gopts->nr_pages * gopts->page_size, MADV_NOHUGEPAGE))
err("madvise(MADV_NOHUGEPAGE) failure");
- uffd_move_test_common(targs, read_pmd_pagesize(),
+ uffd_move_test_common(gopts, targs, read_pmd_pagesize(),
uffd_move_pmd_handle_fault);
}
@@ -1295,6 +1291,11 @@ typedef enum {
THR_STATE_UNINTERRUPTIBLE,
} thread_state;
+typedef struct {
+ uffd_global_test_opts_t *gopts;
+ volatile pid_t *pid;
+} mmap_changing_thread_args;
+
static void sleep_short(void)
{
usleep(1000);
@@ -1337,7 +1338,9 @@ static void thread_state_until(pid_t tid, thread_state state)
static void *uffd_mmap_changing_thread(void *opaque)
{
- volatile pid_t *pid = opaque;
+ mmap_changing_thread_args *args = opaque;
+ uffd_global_test_opts_t *gopts = args->gopts;
+ volatile pid_t *pid = args->pid;
int ret;
/* Unfortunately, it's only fetch-able from the thread itself.. */
@@ -1345,21 +1348,21 @@ static void *uffd_mmap_changing_thread(void *opaque)
*pid = syscall(SYS_gettid);
/* Inject an event, this will hang solid until the event read */
- ret = madvise(area_dst, page_size, MADV_REMOVE);
+ ret = madvise(gopts->area_dst, gopts->page_size, MADV_REMOVE);
if (ret)
err("madvise(MADV_REMOVE) failed");
return NULL;
}
-static void uffd_consume_message(int fd)
+static void uffd_consume_message(uffd_global_test_opts_t *gopts)
{
struct uffd_msg msg = { 0 };
- while (uffd_read_msg(fd, &msg));
+ while (uffd_read_msg(gopts, &msg));
}
-static void uffd_mmap_changing_test(uffd_test_args_t *targs)
+static void uffd_mmap_changing_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *targs)
{
/*
* This stores the real PID (which can be different from how tid is
@@ -1368,13 +1371,14 @@ static void uffd_mmap_changing_test(uffd_test_args_t *targs)
pid_t pid = 0;
pthread_t tid;
int ret;
+ mmap_changing_thread_args args = { gopts, &pid };
- if (uffd_register(uffd, area_dst, nr_pages * page_size,
+ if (uffd_register(gopts->uffd, gopts->area_dst, gopts->nr_pages * gopts->page_size,
true, false, false))
err("uffd_register() failed");
/* Create a thread to generate the racy event */
- ret = pthread_create(&tid, NULL, uffd_mmap_changing_thread, &pid);
+ ret = pthread_create(&tid, NULL, uffd_mmap_changing_thread, &args);
if (ret)
err("pthread_create() failed");
@@ -1388,26 +1392,26 @@ static void uffd_mmap_changing_test(uffd_test_args_t *targs)
/* Wait until the thread hangs at REMOVE event */
thread_state_until(pid, THR_STATE_UNINTERRUPTIBLE);
- if (!uffdio_mmap_changing_test_copy(uffd))
+ if (!uffdio_mmap_changing_test_copy(gopts->uffd))
return;
- if (!uffdio_mmap_changing_test_zeropage(uffd))
+ if (!uffdio_mmap_changing_test_zeropage(gopts->uffd))
return;
- if (!uffdio_mmap_changing_test_move(uffd))
+ if (!uffdio_mmap_changing_test_move(gopts->uffd))
return;
- if (!uffdio_mmap_changing_test_poison(uffd))
+ if (!uffdio_mmap_changing_test_poison(gopts->uffd))
return;
- if (!uffdio_mmap_changing_test_continue(uffd))
+ if (!uffdio_mmap_changing_test_continue(gopts->uffd))
return;
/*
* All succeeded above! Recycle everything. Start by reading the
* event so as to kick the thread roll again..
*/
- uffd_consume_message(uffd);
+ uffd_consume_message(gopts);
ret = pthread_join(tid, NULL);
assert(ret == 0);
@@ -1415,10 +1419,10 @@ static void uffd_mmap_changing_test(uffd_test_args_t *targs)
uffd_test_pass();
}
-static int prevent_hugepages(const char **errmsg)
+static int prevent_hugepages(uffd_global_test_opts_t *gopts, const char **errmsg)
{
/* This should be done before source area is populated */
- if (madvise(area_src, nr_pages * page_size, MADV_NOHUGEPAGE)) {
+ if (madvise(gopts->area_src, gopts->nr_pages * gopts->page_size, MADV_NOHUGEPAGE)) {
/* Ignore only if CONFIG_TRANSPARENT_HUGEPAGE=n */
if (errno != EINVAL) {
if (errmsg)
@@ -1429,10 +1433,10 @@ static int prevent_hugepages(const char **errmsg)
return 0;
}
-static int request_hugepages(const char **errmsg)
+static int request_hugepages(uffd_global_test_opts_t *gopts, const char **errmsg)
{
/* This should be done before source area is populated */
- if (madvise(area_src, nr_pages * page_size, MADV_HUGEPAGE)) {
+ if (madvise(gopts->area_src, gopts->nr_pages * gopts->page_size, MADV_HUGEPAGE)) {
if (errmsg) {
*errmsg = (errno == EINVAL) ?
"CONFIG_TRANSPARENT_HUGEPAGE is not set" :
@@ -1456,13 +1460,17 @@ struct uffd_test_case_ops uffd_move_test_pmd_case_ops = {
* Note that _UFFDIO_ZEROPAGE is tested separately in the zeropage test.
*/
static void
-do_register_ioctls_test(uffd_test_args_t *args, bool miss, bool wp, bool minor)
+do_register_ioctls_test(uffd_global_test_opts_t *gopts,
+ uffd_test_args_t *args,
+ bool miss,
+ bool wp,
+ bool minor)
{
uint64_t ioctls = 0, expected = BIT_ULL(_UFFDIO_WAKE);
mem_type_t *mem_type = args->mem_type;
int ret;
- ret = uffd_register_with_ioctls(uffd, area_dst, page_size,
+ ret = uffd_register_with_ioctls(gopts->uffd, gopts->area_dst, gopts->page_size,
miss, wp, minor, &ioctls);
/*
@@ -1493,18 +1501,18 @@ do_register_ioctls_test(uffd_test_args_t *args, bool miss, bool wp, bool minor)
"(miss=%d, wp=%d, minor=%d): expected=0x%"PRIx64", "
"returned=0x%"PRIx64, miss, wp, minor, expected, ioctls);
- if (uffd_unregister(uffd, area_dst, page_size))
+ if (uffd_unregister(gopts->uffd, gopts->area_dst, gopts->page_size))
err("unregister");
}
-static void uffd_register_ioctls_test(uffd_test_args_t *args)
+static void uffd_register_ioctls_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *args)
{
int miss, wp, minor;
for (miss = 0; miss <= 1; miss++)
for (wp = 0; wp <= 1; wp++)
for (minor = 0; minor <= 1; minor++)
- do_register_ioctls_test(args, miss, wp, minor);
+ do_register_ioctls_test(gopts, args, miss, wp, minor);
uffd_test_pass();
}
@@ -1742,6 +1750,28 @@ int main(int argc, char *argv[])
}
for (j = 0; j < n_mems; j++) {
mem_type = &mem_types[j];
+
+ /* Initialize global test options */
+ uffd_global_test_opts_t gopts = { 0 };
+
+ gopts.map_shared = mem_type->shared;
+ uffd_test_ops = mem_type->mem_ops;
+ uffd_test_case_ops = test->test_case_ops;
+
+ if (mem_type->mem_flag & (MEM_HUGETLB_PRIVATE | MEM_HUGETLB))
+ gopts.page_size = default_huge_page_size();
+ else
+ gopts.page_size = psize();
+
+ /* Ensure we have at least 2 pages */
+ gopts.nr_pages = MAX(UFFD_TEST_MEM_SIZE, gopts.page_size * 2)
+ / gopts.page_size;
+
+ gopts.nr_parallel = 1;
+
+ /* Initialize test arguments */
+ args.mem_type = mem_type;
+
if (!(test->mem_targets & mem_type->mem_flag))
continue;
@@ -1756,13 +1786,12 @@ int main(int argc, char *argv[])
uffd_test_skip("feature missing");
continue;
}
- if (uffd_setup_environment(&args, test, mem_type,
- &errmsg)) {
+ if (uffd_test_ctx_init(&gopts, test->uffd_feature_required, &errmsg)) {
uffd_test_skip(errmsg);
continue;
}
- test->uffd_fn(&args);
- uffd_test_ctx_clear();
+ test->uffd_fn(&gopts, &args);
+ uffd_test_ctx_clear(&gopts);
}
}
diff --git a/tools/testing/selftests/mm/uffd-wp-mremap.c b/tools/testing/selftests/mm/uffd-wp-mremap.c
index c2ba7d46c7b4..4e4a591cf527 100644
--- a/tools/testing/selftests/mm/uffd-wp-mremap.c
+++ b/tools/testing/selftests/mm/uffd-wp-mremap.c
@@ -19,11 +19,6 @@ static size_t thpsizes[20];
static int nr_hugetlbsizes;
static size_t hugetlbsizes[10];
-static int sz2ord(size_t size)
-{
- return __builtin_ctzll(size / pagesize);
-}
-
static int detect_thp_sizes(size_t sizes[], int max)
{
int count = 0;
@@ -87,9 +82,9 @@ static void *alloc_one_folio(size_t size, bool private, bool hugetlb)
struct thp_settings settings = *thp_current_settings();
if (private)
- settings.hugepages[sz2ord(size)].enabled = THP_ALWAYS;
+ settings.hugepages[sz2ord(size, pagesize)].enabled = THP_ALWAYS;
else
- settings.shmem_hugepages[sz2ord(size)].enabled = SHMEM_ALWAYS;
+ settings.shmem_hugepages[sz2ord(size, pagesize)].enabled = SHMEM_ALWAYS;
thp_push_settings(&settings);
@@ -157,7 +152,8 @@ static bool range_is_swapped(void *addr, size_t size)
return true;
}
-static void test_one_folio(size_t size, bool private, bool swapout, bool hugetlb)
+static void test_one_folio(uffd_global_test_opts_t *gopts, size_t size, bool private,
+ bool swapout, bool hugetlb)
{
struct uffdio_writeprotect wp_prms;
uint64_t features = 0;
@@ -181,21 +177,21 @@ static void test_one_folio(size_t size, bool private, bool swapout, bool hugetlb
}
/* Register range for uffd-wp. */
- if (userfaultfd_open(&features)) {
+ if (userfaultfd_open(gopts, &features)) {
if (errno == ENOENT)
ksft_test_result_skip("userfaultfd not available\n");
else
ksft_test_result_fail("userfaultfd_open() failed\n");
goto out;
}
- if (uffd_register(uffd, mem, size, false, true, false)) {
+ if (uffd_register(gopts->uffd, mem, size, false, true, false)) {
ksft_test_result_fail("uffd_register() failed\n");
goto out;
}
wp_prms.mode = UFFDIO_WRITEPROTECT_MODE_WP;
wp_prms.range.start = (uintptr_t)mem;
wp_prms.range.len = size;
- if (ioctl(uffd, UFFDIO_WRITEPROTECT, &wp_prms)) {
+ if (ioctl(gopts->uffd, UFFDIO_WRITEPROTECT, &wp_prms)) {
ksft_test_result_fail("ioctl(UFFDIO_WRITEPROTECT) failed\n");
goto out;
}
@@ -242,9 +238,9 @@ static void test_one_folio(size_t size, bool private, bool swapout, bool hugetlb
out:
if (mem)
munmap(mem, size);
- if (uffd >= 0) {
- close(uffd);
- uffd = -1;
+ if (gopts->uffd >= 0) {
+ close(gopts->uffd);
+ gopts->uffd = -1;
}
}
@@ -336,6 +332,7 @@ static const struct testcase testcases[] = {
int main(int argc, char **argv)
{
+ uffd_global_test_opts_t gopts = { 0 };
struct thp_settings settings;
int i, j, plan = 0;
@@ -367,8 +364,8 @@ int main(int argc, char **argv)
const struct testcase *tc = &testcases[i];
for (j = 0; j < *tc->nr_sizes; j++)
- test_one_folio(tc->sizes[j], tc->private, tc->swapout,
- tc->hugetlb);
+ test_one_folio(&gopts, tc->sizes[j], tc->private,
+ tc->swapout, tc->hugetlb);
}
/* If THP is supported, restore original THP settings. */
diff --git a/tools/testing/selftests/mm/va_high_addr_switch.c b/tools/testing/selftests/mm/va_high_addr_switch.c
index 896b3f73fc53..306eba825107 100644
--- a/tools/testing/selftests/mm/va_high_addr_switch.c
+++ b/tools/testing/selftests/mm/va_high_addr_switch.c
@@ -230,10 +230,10 @@ void testcases_init(void)
.msg = "mmap(-1, MAP_HUGETLB) again",
},
{
- .addr = (void *)(addr_switch_hint - pagesize),
+ .addr = (void *)(addr_switch_hint - hugepagesize),
.size = 2 * hugepagesize,
.flags = MAP_HUGETLB | MAP_PRIVATE | MAP_ANONYMOUS,
- .msg = "mmap(addr_switch_hint - pagesize, 2*hugepagesize, MAP_HUGETLB)",
+ .msg = "mmap(addr_switch_hint - hugepagesize, 2*hugepagesize, MAP_HUGETLB)",
.low_addr_required = 1,
.keep_mapped = 1,
},
diff --git a/tools/testing/selftests/mm/va_high_addr_switch.sh b/tools/testing/selftests/mm/va_high_addr_switch.sh
index 325de53966b6..a7d4b02b21dd 100755
--- a/tools/testing/selftests/mm/va_high_addr_switch.sh
+++ b/tools/testing/selftests/mm/va_high_addr_switch.sh
@@ -9,6 +9,7 @@
# Kselftest framework requirement - SKIP code is 4.
ksft_skip=4
+orig_nr_hugepages=0
skip()
{
@@ -76,5 +77,41 @@ check_test_requirements()
esac
}
+save_nr_hugepages()
+{
+ orig_nr_hugepages=$(cat /proc/sys/vm/nr_hugepages)
+}
+
+restore_nr_hugepages()
+{
+ echo "$orig_nr_hugepages" > /proc/sys/vm/nr_hugepages
+}
+
+setup_nr_hugepages()
+{
+ local needpgs=$1
+ while read -r name size unit; do
+ if [ "$name" = "HugePages_Free:" ]; then
+ freepgs="$size"
+ break
+ fi
+ done < /proc/meminfo
+ if [ "$freepgs" -ge "$needpgs" ]; then
+ return
+ fi
+ local hpgs=$((orig_nr_hugepages + needpgs))
+ echo $hpgs > /proc/sys/vm/nr_hugepages
+
+ local nr_hugepgs=$(cat /proc/sys/vm/nr_hugepages)
+ if [ "$nr_hugepgs" != "$hpgs" ]; then
+ restore_nr_hugepages
+ skip "$0: no enough hugepages for testing"
+ fi
+}
+
check_test_requirements
+save_nr_hugepages
+# 4 keep_mapped pages, and one for tmp usage
+setup_nr_hugepages 5
./va_high_addr_switch --run-hugetlb
+restore_nr_hugepages
diff --git a/tools/testing/selftests/mm/virtual_address_range.c b/tools/testing/selftests/mm/virtual_address_range.c
index 169dbd692bf5..81b33d8f78f4 100644
--- a/tools/testing/selftests/mm/virtual_address_range.c
+++ b/tools/testing/selftests/mm/virtual_address_range.c
@@ -44,12 +44,18 @@
* On Arm64 the address space is 256TB and support for
* high mappings up to 4PB virtual address space has
* been added.
+ *
+ * On PowerPC64, the address space up to 128TB can be
+ * mapped without a hint. Addresses beyond 128TB, up to
+ * 4PB, can be mapped with a hint.
+ *
*/
#define NR_CHUNKS_128TB ((128 * SZ_1TB) / MAP_CHUNK_SIZE) /* Number of chunks for 128TB */
#define NR_CHUNKS_256TB (NR_CHUNKS_128TB * 2UL)
#define NR_CHUNKS_384TB (NR_CHUNKS_128TB * 3UL)
#define NR_CHUNKS_3840TB (NR_CHUNKS_128TB * 30UL)
+#define NR_CHUNKS_3968TB (NR_CHUNKS_128TB * 31UL)
#define ADDR_MARK_128TB (1UL << 47) /* First address beyond 128TB */
#define ADDR_MARK_256TB (1UL << 48) /* First address beyond 256TB */
@@ -59,6 +65,11 @@
#define HIGH_ADDR_SHIFT 49
#define NR_CHUNKS_LOW NR_CHUNKS_256TB
#define NR_CHUNKS_HIGH NR_CHUNKS_3840TB
+#elif defined(__PPC64__)
+#define HIGH_ADDR_MARK ADDR_MARK_128TB
+#define HIGH_ADDR_SHIFT 48
+#define NR_CHUNKS_LOW NR_CHUNKS_128TB
+#define NR_CHUNKS_HIGH NR_CHUNKS_3968TB
#else
#define HIGH_ADDR_MARK ADDR_MARK_128TB
#define HIGH_ADDR_SHIFT 48
@@ -227,7 +238,7 @@ int main(int argc, char *argv[])
if (hptr[i] == MAP_FAILED)
break;
- mark_range(ptr[i], MAP_CHUNK_SIZE);
+ mark_range(hptr[i], MAP_CHUNK_SIZE);
validate_addr(hptr[i], 1);
}
hchunks = i;
diff --git a/tools/testing/selftests/mm/vm_util.c b/tools/testing/selftests/mm/vm_util.c
index 9dafa7669ef9..e33cda301dad 100644
--- a/tools/testing/selftests/mm/vm_util.c
+++ b/tools/testing/selftests/mm/vm_util.c
@@ -338,6 +338,19 @@ int detect_hugetlb_page_sizes(size_t sizes[], int max)
return count;
}
+int pageflags_get(unsigned long pfn, int kpageflags_fd, uint64_t *flags)
+{
+ size_t count;
+
+ count = pread(kpageflags_fd, flags, sizeof(*flags),
+ pfn * sizeof(*flags));
+
+ if (count != sizeof(*flags))
+ return -1;
+
+ return 0;
+}
+
/* If `ioctls' non-NULL, the allowed ioctls will be returned into the var */
int uffd_register_with_ioctls(int uffd, void *addr, uint64_t len,
bool miss, bool wp, bool minor, uint64_t *ioctls)
@@ -402,7 +415,7 @@ unsigned long get_free_hugepages(void)
return fhp;
}
-bool check_vmflag_io(void *addr)
+static bool check_vmflag(void *addr, const char *flag)
{
char buffer[MAX_LINE_LENGTH];
const char *flags;
@@ -419,13 +432,40 @@ bool check_vmflag_io(void *addr)
if (!flaglen)
return false;
- if (flaglen == strlen("io") && !memcmp(flags, "io", flaglen))
+ if (flaglen == strlen(flag) && !memcmp(flags, flag, flaglen))
return true;
flags += flaglen;
}
}
+bool check_vmflag_io(void *addr)
+{
+ return check_vmflag(addr, "io");
+}
+
+bool check_vmflag_pfnmap(void *addr)
+{
+ return check_vmflag(addr, "pf");
+}
+
+bool softdirty_supported(void)
+{
+ char *addr;
+ bool supported = false;
+ const size_t pagesize = getpagesize();
+
+ /* New mappings are expected to be marked with VM_SOFTDIRTY (sd). */
+ addr = mmap(0, pagesize, PROT_READ | PROT_WRITE,
+ MAP_ANONYMOUS | MAP_PRIVATE, 0, 0);
+ if (!addr)
+ ksft_exit_fail_msg("mmap failed\n");
+
+ supported = check_vmflag(addr, "sd");
+ munmap(addr, pagesize);
+ return supported;
+}
+
/*
* Open an fd at /proc/$pid/maps and configure procmap_out ready for
* PROCMAP_QUERY query. Returns 0 on success, or an error code otherwise.
@@ -555,3 +595,126 @@ bool detect_huge_zeropage(void)
close(fd);
return enabled;
}
+
+long ksm_get_self_zero_pages(void)
+{
+ int proc_self_ksm_stat_fd;
+ char buf[200];
+ char *substr_ksm_zero;
+ size_t value_pos;
+ ssize_t read_size;
+
+ proc_self_ksm_stat_fd = open("/proc/self/ksm_stat", O_RDONLY);
+ if (proc_self_ksm_stat_fd < 0)
+ return -errno;
+
+ read_size = pread(proc_self_ksm_stat_fd, buf, sizeof(buf) - 1, 0);
+ close(proc_self_ksm_stat_fd);
+ if (read_size < 0)
+ return -errno;
+
+ buf[read_size] = 0;
+
+ substr_ksm_zero = strstr(buf, "ksm_zero_pages");
+ if (!substr_ksm_zero)
+ return 0;
+
+ value_pos = strcspn(substr_ksm_zero, "0123456789");
+ return strtol(substr_ksm_zero + value_pos, NULL, 10);
+}
+
+long ksm_get_self_merging_pages(void)
+{
+ int proc_self_ksm_merging_pages_fd;
+ char buf[10];
+ ssize_t ret;
+
+ proc_self_ksm_merging_pages_fd = open("/proc/self/ksm_merging_pages",
+ O_RDONLY);
+ if (proc_self_ksm_merging_pages_fd < 0)
+ return -errno;
+
+ ret = pread(proc_self_ksm_merging_pages_fd, buf, sizeof(buf) - 1, 0);
+ close(proc_self_ksm_merging_pages_fd);
+ if (ret <= 0)
+ return -errno;
+ buf[ret] = 0;
+
+ return strtol(buf, NULL, 10);
+}
+
+long ksm_get_full_scans(void)
+{
+ int ksm_full_scans_fd;
+ char buf[10];
+ ssize_t ret;
+
+ ksm_full_scans_fd = open("/sys/kernel/mm/ksm/full_scans", O_RDONLY);
+ if (ksm_full_scans_fd < 0)
+ return -errno;
+
+ ret = pread(ksm_full_scans_fd, buf, sizeof(buf) - 1, 0);
+ close(ksm_full_scans_fd);
+ if (ret <= 0)
+ return -errno;
+ buf[ret] = 0;
+
+ return strtol(buf, NULL, 10);
+}
+
+int ksm_use_zero_pages(void)
+{
+ int ksm_use_zero_pages_fd;
+ ssize_t ret;
+
+ ksm_use_zero_pages_fd = open("/sys/kernel/mm/ksm/use_zero_pages", O_RDWR);
+ if (ksm_use_zero_pages_fd < 0)
+ return -errno;
+
+ ret = write(ksm_use_zero_pages_fd, "1", 1);
+ close(ksm_use_zero_pages_fd);
+ return ret == 1 ? 0 : -errno;
+}
+
+int ksm_start(void)
+{
+ int ksm_fd;
+ ssize_t ret;
+ long start_scans, end_scans;
+
+ ksm_fd = open("/sys/kernel/mm/ksm/run", O_RDWR);
+ if (ksm_fd < 0)
+ return -errno;
+
+ /* Wait for two full scans such that any possible merging happened. */
+ start_scans = ksm_get_full_scans();
+ if (start_scans < 0) {
+ close(ksm_fd);
+ return start_scans;
+ }
+ ret = write(ksm_fd, "1", 1);
+ close(ksm_fd);
+ if (ret != 1)
+ return -errno;
+ do {
+ end_scans = ksm_get_full_scans();
+ if (end_scans < 0)
+ return end_scans;
+ } while (end_scans < start_scans + 2);
+
+ return 0;
+}
+
+int ksm_stop(void)
+{
+ int ksm_fd;
+ ssize_t ret;
+
+ ksm_fd = open("/sys/kernel/mm/ksm/run", O_RDWR);
+ if (ksm_fd < 0)
+ return -errno;
+
+ ret = write(ksm_fd, "2", 1);
+ close(ksm_fd);
+ return ret == 1 ? 0 : -errno;
+}
diff --git a/tools/testing/selftests/mm/vm_util.h b/tools/testing/selftests/mm/vm_util.h
index b55d1809debc..26c30fdc0241 100644
--- a/tools/testing/selftests/mm/vm_util.h
+++ b/tools/testing/selftests/mm/vm_util.h
@@ -18,6 +18,9 @@
#define PM_SWAP BIT_ULL(62)
#define PM_PRESENT BIT_ULL(63)
+#define KPF_COMPOUND_HEAD BIT_ULL(15)
+#define KPF_COMPOUND_TAIL BIT_ULL(16)
+#define KPF_THP BIT_ULL(22)
/*
* Ignore the checkpatch warning, we must read from x but don't want to do
* anything with it in order to trigger a read page fault. We therefore must use
@@ -85,6 +88,7 @@ bool check_huge_shmem(void *addr, int nr_hpages, uint64_t hpage_size);
int64_t allocate_transhuge(void *ptr, int pagemap_fd);
unsigned long default_huge_page_size(void);
int detect_hugetlb_page_sizes(size_t sizes[], int max);
+int pageflags_get(unsigned long pfn, int kpageflags_fd, uint64_t *flags);
int uffd_register(int uffd, void *addr, uint64_t len,
bool miss, bool wp, bool minor);
@@ -93,12 +97,14 @@ int uffd_register_with_ioctls(int uffd, void *addr, uint64_t len,
bool miss, bool wp, bool minor, uint64_t *ioctls);
unsigned long get_free_hugepages(void);
bool check_vmflag_io(void *addr);
+bool check_vmflag_pfnmap(void *addr);
int open_procmap(pid_t pid, struct procmap_fd *procmap_out);
int query_procmap(struct procmap_fd *procmap);
bool find_vma_procmap(struct procmap_fd *procmap, void *address);
int close_procmap(struct procmap_fd *procmap);
int write_sysfs(const char *file_path, unsigned long val);
int read_sysfs(const char *file_path, unsigned long *val);
+bool softdirty_supported(void);
static inline int open_self_procmap(struct procmap_fd *procmap_out)
{
@@ -126,9 +132,21 @@ static inline void log_test_result(int result)
ksft_test_result_report(result, "%s\n", test_name);
}
+static inline int sz2ord(size_t size, size_t pagesize)
+{
+ return __builtin_ctzll(size / pagesize);
+}
+
void *sys_mremap(void *old_address, unsigned long old_size,
unsigned long new_size, int flags, void *new_address);
+long ksm_get_self_zero_pages(void);
+long ksm_get_self_merging_pages(void);
+long ksm_get_full_scans(void);
+int ksm_use_zero_pages(void);
+int ksm_start(void);
+int ksm_stop(void);
+
/*
* On ppc64 this will only work with radix 2M hugepage size
*/
diff --git a/tools/testing/selftests/namespaces/.gitignore b/tools/testing/selftests/namespaces/.gitignore
new file mode 100644
index 000000000000..ccfb40837a73
--- /dev/null
+++ b/tools/testing/selftests/namespaces/.gitignore
@@ -0,0 +1,3 @@
+nsid_test
+file_handle_test
+init_ino_test
diff --git a/tools/testing/selftests/namespaces/Makefile b/tools/testing/selftests/namespaces/Makefile
new file mode 100644
index 000000000000..5fe4b3dc07d3
--- /dev/null
+++ b/tools/testing/selftests/namespaces/Makefile
@@ -0,0 +1,7 @@
+# SPDX-License-Identifier: GPL-2.0-only
+CFLAGS += -Wall -O0 -g $(KHDR_INCLUDES) $(TOOLS_INCLUDES)
+
+TEST_GEN_PROGS := nsid_test file_handle_test init_ino_test
+
+include ../lib.mk
+
diff --git a/tools/testing/selftests/namespaces/config b/tools/testing/selftests/namespaces/config
new file mode 100644
index 000000000000..d09836260262
--- /dev/null
+++ b/tools/testing/selftests/namespaces/config
@@ -0,0 +1,7 @@
+CONFIG_UTS_NS=y
+CONFIG_TIME_NS=y
+CONFIG_IPC_NS=y
+CONFIG_USER_NS=y
+CONFIG_PID_NS=y
+CONFIG_NET_NS=y
+CONFIG_CGROUPS=y
diff --git a/tools/testing/selftests/namespaces/file_handle_test.c b/tools/testing/selftests/namespaces/file_handle_test.c
new file mode 100644
index 000000000000..f1bc5773f552
--- /dev/null
+++ b/tools/testing/selftests/namespaces/file_handle_test.c
@@ -0,0 +1,1429 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <errno.h>
+#include <fcntl.h>
+#include <grp.h>
+#include <limits.h>
+#include <sched.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/mount.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include <linux/unistd.h>
+#include "../kselftest_harness.h"
+
+#ifndef FD_NSFS_ROOT
+#define FD_NSFS_ROOT -10003 /* Root of the nsfs filesystem */
+#endif
+
+TEST(nsfs_net_handle)
+{
+ struct file_handle *handle;
+ int mount_id;
+ int ret;
+ int fd;
+ int ns_fd;
+ struct stat st1, st2;
+
+ /* Drop to unprivileged uid/gid */
+ ASSERT_EQ(setresgid(65534, 65534, 65534), 0); /* nogroup */
+ ASSERT_EQ(setresuid(65534, 65534, 65534), 0); /* nobody */
+
+ handle = malloc(sizeof(*handle) + MAX_HANDLE_SZ);
+ ASSERT_NE(handle, NULL);
+
+ /* Open a namespace file descriptor */
+ ns_fd = open("/proc/self/ns/net", O_RDONLY);
+ ASSERT_GE(ns_fd, 0);
+
+ /* Get handle for the namespace */
+ handle->handle_bytes = MAX_HANDLE_SZ;
+ ret = name_to_handle_at(ns_fd, "", handle, &mount_id, AT_EMPTY_PATH);
+ if (ret < 0 && errno == EOPNOTSUPP) {
+ SKIP(free(handle); close(ns_fd);
+ return, "nsfs doesn't support file handles");
+ }
+ ASSERT_EQ(ret, 0);
+ ASSERT_GT(handle->handle_bytes, 0);
+
+ /* Try to open using FD_NSFS_ROOT as unprivileged user */
+ fd = open_by_handle_at(FD_NSFS_ROOT, handle, O_RDONLY);
+ if (fd < 0 && (errno == EINVAL || errno == EOPNOTSUPP)) {
+ SKIP(free(handle); close(ns_fd);
+ return,
+ "open_by_handle_at with FD_NSFS_ROOT not supported");
+ }
+ if (fd < 0 && errno == EPERM) {
+ SKIP(free(handle); close(ns_fd);
+ return,
+ "Permission denied for unprivileged user (expected)");
+ }
+ ASSERT_GE(fd, 0);
+
+ /* Verify we opened the correct namespace */
+ ASSERT_EQ(fstat(ns_fd, &st1), 0);
+ ASSERT_EQ(fstat(fd, &st2), 0);
+ ASSERT_EQ(st1.st_ino, st2.st_ino);
+ ASSERT_EQ(st1.st_dev, st2.st_dev);
+
+ close(fd);
+ close(ns_fd);
+ free(handle);
+}
+
+TEST(nsfs_uts_handle)
+{
+ struct file_handle *handle;
+ int mount_id;
+ int ret;
+ int fd;
+ int ns_fd;
+ struct stat st1, st2;
+
+ /* Drop to unprivileged uid/gid */
+ ASSERT_EQ(setresgid(65534, 65534, 65534), 0); /* nogroup */
+ ASSERT_EQ(setresuid(65534, 65534, 65534), 0); /* nobody */
+
+ handle = malloc(sizeof(*handle) + MAX_HANDLE_SZ);
+ ASSERT_NE(handle, NULL);
+
+ /* Open UTS namespace file descriptor */
+ ns_fd = open("/proc/self/ns/uts", O_RDONLY);
+ ASSERT_GE(ns_fd, 0);
+
+ /* Get handle for the namespace */
+ handle->handle_bytes = MAX_HANDLE_SZ;
+ ret = name_to_handle_at(ns_fd, "", handle, &mount_id, AT_EMPTY_PATH);
+ if (ret < 0 && errno == EOPNOTSUPP) {
+ SKIP(free(handle); close(ns_fd);
+ return, "nsfs doesn't support file handles");
+ }
+ ASSERT_EQ(ret, 0);
+ ASSERT_GT(handle->handle_bytes, 0);
+
+ /* Try to open using FD_NSFS_ROOT */
+ fd = open_by_handle_at(FD_NSFS_ROOT, handle, O_RDONLY);
+ if (fd < 0 && (errno == EINVAL || errno == EOPNOTSUPP)) {
+ SKIP(free(handle); close(ns_fd);
+ return,
+ "open_by_handle_at with FD_NSFS_ROOT not supported");
+ }
+ ASSERT_GE(fd, 0);
+
+ /* Verify we opened the correct namespace */
+ ASSERT_EQ(fstat(ns_fd, &st1), 0);
+ ASSERT_EQ(fstat(fd, &st2), 0);
+ ASSERT_EQ(st1.st_ino, st2.st_ino);
+ ASSERT_EQ(st1.st_dev, st2.st_dev);
+
+ close(fd);
+ close(ns_fd);
+ free(handle);
+}
+
+TEST(nsfs_ipc_handle)
+{
+ struct file_handle *handle;
+ int mount_id;
+ int ret;
+ int fd;
+ int ns_fd;
+ struct stat st1, st2;
+
+ /* Drop to unprivileged uid/gid */
+ ASSERT_EQ(setresgid(65534, 65534, 65534), 0); /* nogroup */
+ ASSERT_EQ(setresuid(65534, 65534, 65534), 0); /* nobody */
+
+ handle = malloc(sizeof(*handle) + MAX_HANDLE_SZ);
+ ASSERT_NE(handle, NULL);
+
+ /* Open IPC namespace file descriptor */
+ ns_fd = open("/proc/self/ns/ipc", O_RDONLY);
+ ASSERT_GE(ns_fd, 0);
+
+ /* Get handle for the namespace */
+ handle->handle_bytes = MAX_HANDLE_SZ;
+ ret = name_to_handle_at(ns_fd, "", handle, &mount_id, AT_EMPTY_PATH);
+ if (ret < 0 && errno == EOPNOTSUPP) {
+ SKIP(free(handle); close(ns_fd);
+ return, "nsfs doesn't support file handles");
+ }
+ ASSERT_EQ(ret, 0);
+ ASSERT_GT(handle->handle_bytes, 0);
+
+ /* Try to open using FD_NSFS_ROOT */
+ fd = open_by_handle_at(FD_NSFS_ROOT, handle, O_RDONLY);
+ if (fd < 0 && (errno == EINVAL || errno == EOPNOTSUPP)) {
+ SKIP(free(handle); close(ns_fd);
+ return,
+ "open_by_handle_at with FD_NSFS_ROOT not supported");
+ }
+ ASSERT_GE(fd, 0);
+
+ /* Verify we opened the correct namespace */
+ ASSERT_EQ(fstat(ns_fd, &st1), 0);
+ ASSERT_EQ(fstat(fd, &st2), 0);
+ ASSERT_EQ(st1.st_ino, st2.st_ino);
+ ASSERT_EQ(st1.st_dev, st2.st_dev);
+
+ close(fd);
+ close(ns_fd);
+ free(handle);
+}
+
+TEST(nsfs_pid_handle)
+{
+ struct file_handle *handle;
+ int mount_id;
+ int ret;
+ int fd;
+ int ns_fd;
+ struct stat st1, st2;
+
+ /* Drop to unprivileged uid/gid */
+ ASSERT_EQ(setresgid(65534, 65534, 65534), 0); /* nogroup */
+ ASSERT_EQ(setresuid(65534, 65534, 65534), 0); /* nobody */
+
+ handle = malloc(sizeof(*handle) + MAX_HANDLE_SZ);
+ ASSERT_NE(handle, NULL);
+
+ /* Open PID namespace file descriptor */
+ ns_fd = open("/proc/self/ns/pid", O_RDONLY);
+ ASSERT_GE(ns_fd, 0);
+
+ /* Get handle for the namespace */
+ handle->handle_bytes = MAX_HANDLE_SZ;
+ ret = name_to_handle_at(ns_fd, "", handle, &mount_id, AT_EMPTY_PATH);
+ if (ret < 0 && errno == EOPNOTSUPP) {
+ SKIP(free(handle); close(ns_fd);
+ return, "nsfs doesn't support file handles");
+ }
+ ASSERT_EQ(ret, 0);
+ ASSERT_GT(handle->handle_bytes, 0);
+
+ /* Try to open using FD_NSFS_ROOT */
+ fd = open_by_handle_at(FD_NSFS_ROOT, handle, O_RDONLY);
+ if (fd < 0 && (errno == EINVAL || errno == EOPNOTSUPP)) {
+ SKIP(free(handle); close(ns_fd);
+ return,
+ "open_by_handle_at with FD_NSFS_ROOT not supported");
+ }
+ ASSERT_GE(fd, 0);
+
+ /* Verify we opened the correct namespace */
+ ASSERT_EQ(fstat(ns_fd, &st1), 0);
+ ASSERT_EQ(fstat(fd, &st2), 0);
+ ASSERT_EQ(st1.st_ino, st2.st_ino);
+ ASSERT_EQ(st1.st_dev, st2.st_dev);
+
+ close(fd);
+ close(ns_fd);
+ free(handle);
+}
+
+TEST(nsfs_mnt_handle)
+{
+ struct file_handle *handle;
+ int mount_id;
+ int ret;
+ int fd;
+ int ns_fd;
+ struct stat st1, st2;
+
+ /* Drop to unprivileged uid/gid */
+ ASSERT_EQ(setresgid(65534, 65534, 65534), 0); /* nogroup */
+ ASSERT_EQ(setresuid(65534, 65534, 65534), 0); /* nobody */
+
+ handle = malloc(sizeof(*handle) + MAX_HANDLE_SZ);
+ ASSERT_NE(handle, NULL);
+
+ /* Open mount namespace file descriptor */
+ ns_fd = open("/proc/self/ns/mnt", O_RDONLY);
+ ASSERT_GE(ns_fd, 0);
+
+ /* Get handle for the namespace */
+ handle->handle_bytes = MAX_HANDLE_SZ;
+ ret = name_to_handle_at(ns_fd, "", handle, &mount_id, AT_EMPTY_PATH);
+ if (ret < 0 && errno == EOPNOTSUPP) {
+ SKIP(free(handle); close(ns_fd);
+ return, "nsfs doesn't support file handles");
+ }
+ ASSERT_EQ(ret, 0);
+ ASSERT_GT(handle->handle_bytes, 0);
+
+ /* Try to open using FD_NSFS_ROOT */
+ fd = open_by_handle_at(FD_NSFS_ROOT, handle, O_RDONLY);
+ if (fd < 0 && (errno == EINVAL || errno == EOPNOTSUPP)) {
+ SKIP(free(handle); close(ns_fd);
+ return,
+ "open_by_handle_at with FD_NSFS_ROOT not supported");
+ }
+ ASSERT_GE(fd, 0);
+
+ /* Verify we opened the correct namespace */
+ ASSERT_EQ(fstat(ns_fd, &st1), 0);
+ ASSERT_EQ(fstat(fd, &st2), 0);
+ ASSERT_EQ(st1.st_ino, st2.st_ino);
+ ASSERT_EQ(st1.st_dev, st2.st_dev);
+
+ close(fd);
+ close(ns_fd);
+ free(handle);
+}
+
+TEST(nsfs_user_handle)
+{
+ struct file_handle *handle;
+ int mount_id;
+ int ret;
+ int fd;
+ int ns_fd;
+ struct stat st1, st2;
+
+ /* Drop to unprivileged uid/gid */
+ ASSERT_EQ(setresgid(65534, 65534, 65534), 0); /* nogroup */
+ ASSERT_EQ(setresuid(65534, 65534, 65534), 0); /* nobody */
+
+ handle = malloc(sizeof(*handle) + MAX_HANDLE_SZ);
+ ASSERT_NE(handle, NULL);
+
+ /* Open user namespace file descriptor */
+ ns_fd = open("/proc/self/ns/user", O_RDONLY);
+ ASSERT_GE(ns_fd, 0);
+
+ /* Get handle for the namespace */
+ handle->handle_bytes = MAX_HANDLE_SZ;
+ ret = name_to_handle_at(ns_fd, "", handle, &mount_id, AT_EMPTY_PATH);
+ if (ret < 0 && errno == EOPNOTSUPP) {
+ SKIP(free(handle); close(ns_fd);
+ return, "nsfs doesn't support file handles");
+ }
+ ASSERT_EQ(ret, 0);
+ ASSERT_GT(handle->handle_bytes, 0);
+
+ /* Try to open using FD_NSFS_ROOT */
+ fd = open_by_handle_at(FD_NSFS_ROOT, handle, O_RDONLY);
+ if (fd < 0 && (errno == EINVAL || errno == EOPNOTSUPP)) {
+ SKIP(free(handle); close(ns_fd);
+ return,
+ "open_by_handle_at with FD_NSFS_ROOT not supported");
+ }
+ ASSERT_GE(fd, 0);
+
+ /* Verify we opened the correct namespace */
+ ASSERT_EQ(fstat(ns_fd, &st1), 0);
+ ASSERT_EQ(fstat(fd, &st2), 0);
+ ASSERT_EQ(st1.st_ino, st2.st_ino);
+ ASSERT_EQ(st1.st_dev, st2.st_dev);
+
+ close(fd);
+ close(ns_fd);
+ free(handle);
+}
+
+TEST(nsfs_cgroup_handle)
+{
+ struct file_handle *handle;
+ int mount_id;
+ int ret;
+ int fd;
+ int ns_fd;
+ struct stat st1, st2;
+
+ /* Drop to unprivileged uid/gid */
+ ASSERT_EQ(setresgid(65534, 65534, 65534), 0); /* nogroup */
+ ASSERT_EQ(setresuid(65534, 65534, 65534), 0); /* nobody */
+
+ handle = malloc(sizeof(*handle) + MAX_HANDLE_SZ);
+ ASSERT_NE(handle, NULL);
+
+ /* Open cgroup namespace file descriptor */
+ ns_fd = open("/proc/self/ns/cgroup", O_RDONLY);
+ if (ns_fd < 0) {
+ SKIP(free(handle); return, "cgroup namespace not available");
+ }
+
+ /* Get handle for the namespace */
+ handle->handle_bytes = MAX_HANDLE_SZ;
+ ret = name_to_handle_at(ns_fd, "", handle, &mount_id, AT_EMPTY_PATH);
+ if (ret < 0 && errno == EOPNOTSUPP) {
+ SKIP(free(handle); close(ns_fd);
+ return, "nsfs doesn't support file handles");
+ }
+ ASSERT_EQ(ret, 0);
+ ASSERT_GT(handle->handle_bytes, 0);
+
+ /* Try to open using FD_NSFS_ROOT */
+ fd = open_by_handle_at(FD_NSFS_ROOT, handle, O_RDONLY);
+ if (fd < 0 && (errno == EINVAL || errno == EOPNOTSUPP)) {
+ SKIP(free(handle); close(ns_fd);
+ return,
+ "open_by_handle_at with FD_NSFS_ROOT not supported");
+ }
+ ASSERT_GE(fd, 0);
+
+ /* Verify we opened the correct namespace */
+ ASSERT_EQ(fstat(ns_fd, &st1), 0);
+ ASSERT_EQ(fstat(fd, &st2), 0);
+ ASSERT_EQ(st1.st_ino, st2.st_ino);
+ ASSERT_EQ(st1.st_dev, st2.st_dev);
+
+ close(fd);
+ close(ns_fd);
+ free(handle);
+}
+
+TEST(nsfs_time_handle)
+{
+ struct file_handle *handle;
+ int mount_id;
+ int ret;
+ int fd;
+ int ns_fd;
+ struct stat st1, st2;
+
+ /* Drop to unprivileged uid/gid */
+ ASSERT_EQ(setresgid(65534, 65534, 65534), 0); /* nogroup */
+ ASSERT_EQ(setresuid(65534, 65534, 65534), 0); /* nobody */
+
+ handle = malloc(sizeof(*handle) + MAX_HANDLE_SZ);
+ ASSERT_NE(handle, NULL);
+
+ /* Open time namespace file descriptor */
+ ns_fd = open("/proc/self/ns/time", O_RDONLY);
+ if (ns_fd < 0) {
+ SKIP(free(handle); return, "time namespace not available");
+ }
+
+ /* Get handle for the namespace */
+ handle->handle_bytes = MAX_HANDLE_SZ;
+ ret = name_to_handle_at(ns_fd, "", handle, &mount_id, AT_EMPTY_PATH);
+ if (ret < 0 && errno == EOPNOTSUPP) {
+ SKIP(free(handle); close(ns_fd);
+ return, "nsfs doesn't support file handles");
+ }
+ ASSERT_EQ(ret, 0);
+ ASSERT_GT(handle->handle_bytes, 0);
+
+ /* Try to open using FD_NSFS_ROOT */
+ fd = open_by_handle_at(FD_NSFS_ROOT, handle, O_RDONLY);
+ if (fd < 0 && (errno == EINVAL || errno == EOPNOTSUPP)) {
+ SKIP(free(handle); close(ns_fd);
+ return,
+ "open_by_handle_at with FD_NSFS_ROOT not supported");
+ }
+ ASSERT_GE(fd, 0);
+
+ /* Verify we opened the correct namespace */
+ ASSERT_EQ(fstat(ns_fd, &st1), 0);
+ ASSERT_EQ(fstat(fd, &st2), 0);
+ ASSERT_EQ(st1.st_ino, st2.st_ino);
+ ASSERT_EQ(st1.st_dev, st2.st_dev);
+
+ close(fd);
+ close(ns_fd);
+ free(handle);
+}
+
+TEST(nsfs_user_net_namespace_isolation)
+{
+ struct file_handle *handle;
+ int mount_id;
+ int ret;
+ int fd;
+ int ns_fd;
+ pid_t pid;
+ int status;
+ int pipefd[2];
+ char result;
+
+ handle = malloc(sizeof(*handle) + MAX_HANDLE_SZ);
+ ASSERT_NE(handle, NULL);
+
+ /* Create pipe for communication */
+ ASSERT_EQ(pipe(pipefd), 0);
+
+ /* Get handle for current network namespace */
+ ns_fd = open("/proc/self/ns/net", O_RDONLY);
+ ASSERT_GE(ns_fd, 0);
+
+ handle->handle_bytes = MAX_HANDLE_SZ;
+ ret = name_to_handle_at(ns_fd, "", handle, &mount_id, AT_EMPTY_PATH);
+ if (ret < 0 && errno == EOPNOTSUPP) {
+ SKIP(free(handle); close(ns_fd); close(pipefd[0]);
+ close(pipefd[1]);
+ return, "nsfs doesn't support file handles");
+ }
+ ASSERT_EQ(ret, 0);
+ close(ns_fd);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ /* Child process */
+ close(pipefd[0]);
+
+ /* First create new user namespace to drop privileges */
+ ret = unshare(CLONE_NEWUSER);
+ if (ret < 0) {
+ write(pipefd[1], "U",
+ 1); /* Unable to create user namespace */
+ close(pipefd[1]);
+ exit(0);
+ }
+
+ /* Write uid/gid mappings to maintain some capabilities */
+ int uid_map_fd = open("/proc/self/uid_map", O_WRONLY);
+ int gid_map_fd = open("/proc/self/gid_map", O_WRONLY);
+ int setgroups_fd = open("/proc/self/setgroups", O_WRONLY);
+
+ if (uid_map_fd < 0 || gid_map_fd < 0 || setgroups_fd < 0) {
+ write(pipefd[1], "M", 1); /* Unable to set mappings */
+ close(pipefd[1]);
+ exit(0);
+ }
+
+ /* Disable setgroups to allow gid mapping */
+ write(setgroups_fd, "deny", 4);
+ close(setgroups_fd);
+
+ /* Map current uid/gid to root in the new namespace */
+ char mapping[64];
+ snprintf(mapping, sizeof(mapping), "0 %d 1", getuid());
+ write(uid_map_fd, mapping, strlen(mapping));
+ close(uid_map_fd);
+
+ snprintf(mapping, sizeof(mapping), "0 %d 1", getgid());
+ write(gid_map_fd, mapping, strlen(mapping));
+ close(gid_map_fd);
+
+ /* Now create new network namespace */
+ ret = unshare(CLONE_NEWNET);
+ if (ret < 0) {
+ write(pipefd[1], "N",
+ 1); /* Unable to create network namespace */
+ close(pipefd[1]);
+ exit(0);
+ }
+
+ /* Try to open parent's network namespace handle from new user+net namespace */
+ fd = open_by_handle_at(FD_NSFS_ROOT, handle, O_RDONLY);
+
+ if (fd >= 0) {
+ /* Should NOT succeed - we're in a different user namespace */
+ write(pipefd[1], "S", 1); /* Unexpected success */
+ close(fd);
+ } else if (errno == ESTALE) {
+ /* Expected: Stale file handle */
+ write(pipefd[1], "P", 1);
+ } else {
+ /* Other error */
+ write(pipefd[1], "F", 1);
+ }
+
+ close(pipefd[1]);
+ exit(0);
+ }
+
+ /* Parent process */
+ close(pipefd[1]);
+ ASSERT_EQ(read(pipefd[0], &result, 1), 1);
+
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFEXITED(status));
+ ASSERT_EQ(WEXITSTATUS(status), 0);
+
+ if (result == 'U') {
+ SKIP(free(handle); close(pipefd[0]);
+ return, "Cannot create new user namespace");
+ }
+ if (result == 'M') {
+ SKIP(free(handle); close(pipefd[0]);
+ return, "Cannot set uid/gid mappings");
+ }
+ if (result == 'N') {
+ SKIP(free(handle); close(pipefd[0]);
+ return, "Cannot create new network namespace");
+ }
+
+ /* Should fail with permission denied since we're in a different user namespace */
+ ASSERT_EQ(result, 'P');
+
+ close(pipefd[0]);
+ free(handle);
+}
+
+TEST(nsfs_user_uts_namespace_isolation)
+{
+ struct file_handle *handle;
+ int mount_id;
+ int ret;
+ int fd;
+ int ns_fd;
+ pid_t pid;
+ int status;
+ int pipefd[2];
+ char result;
+
+ handle = malloc(sizeof(*handle) + MAX_HANDLE_SZ);
+ ASSERT_NE(handle, NULL);
+
+ /* Create pipe for communication */
+ ASSERT_EQ(pipe(pipefd), 0);
+
+ /* Get handle for current UTS namespace */
+ ns_fd = open("/proc/self/ns/uts", O_RDONLY);
+ ASSERT_GE(ns_fd, 0);
+
+ handle->handle_bytes = MAX_HANDLE_SZ;
+ ret = name_to_handle_at(ns_fd, "", handle, &mount_id, AT_EMPTY_PATH);
+ if (ret < 0 && errno == EOPNOTSUPP) {
+ SKIP(free(handle); close(ns_fd); close(pipefd[0]);
+ close(pipefd[1]);
+ return, "nsfs doesn't support file handles");
+ }
+ ASSERT_EQ(ret, 0);
+ close(ns_fd);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ /* Child process */
+ close(pipefd[0]);
+
+ /* First create new user namespace to drop privileges */
+ ret = unshare(CLONE_NEWUSER);
+ if (ret < 0) {
+ write(pipefd[1], "U",
+ 1); /* Unable to create user namespace */
+ close(pipefd[1]);
+ exit(0);
+ }
+
+ /* Write uid/gid mappings to maintain some capabilities */
+ int uid_map_fd = open("/proc/self/uid_map", O_WRONLY);
+ int gid_map_fd = open("/proc/self/gid_map", O_WRONLY);
+ int setgroups_fd = open("/proc/self/setgroups", O_WRONLY);
+
+ if (uid_map_fd < 0 || gid_map_fd < 0 || setgroups_fd < 0) {
+ write(pipefd[1], "M", 1); /* Unable to set mappings */
+ close(pipefd[1]);
+ exit(0);
+ }
+
+ /* Disable setgroups to allow gid mapping */
+ write(setgroups_fd, "deny", 4);
+ close(setgroups_fd);
+
+ /* Map current uid/gid to root in the new namespace */
+ char mapping[64];
+ snprintf(mapping, sizeof(mapping), "0 %d 1", getuid());
+ write(uid_map_fd, mapping, strlen(mapping));
+ close(uid_map_fd);
+
+ snprintf(mapping, sizeof(mapping), "0 %d 1", getgid());
+ write(gid_map_fd, mapping, strlen(mapping));
+ close(gid_map_fd);
+
+ /* Now create new UTS namespace */
+ ret = unshare(CLONE_NEWUTS);
+ if (ret < 0) {
+ write(pipefd[1], "N",
+ 1); /* Unable to create UTS namespace */
+ close(pipefd[1]);
+ exit(0);
+ }
+
+ /* Try to open parent's UTS namespace handle from new user+uts namespace */
+ fd = open_by_handle_at(FD_NSFS_ROOT, handle, O_RDONLY);
+
+ if (fd >= 0) {
+ /* Should NOT succeed - we're in a different user namespace */
+ write(pipefd[1], "S", 1); /* Unexpected success */
+ close(fd);
+ } else if (errno == ESTALE) {
+ /* Expected: Stale file handle */
+ write(pipefd[1], "P", 1);
+ } else {
+ /* Other error */
+ write(pipefd[1], "F", 1);
+ }
+
+ close(pipefd[1]);
+ exit(0);
+ }
+
+ /* Parent process */
+ close(pipefd[1]);
+ ASSERT_EQ(read(pipefd[0], &result, 1), 1);
+
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFEXITED(status));
+ ASSERT_EQ(WEXITSTATUS(status), 0);
+
+ if (result == 'U') {
+ SKIP(free(handle); close(pipefd[0]);
+ return, "Cannot create new user namespace");
+ }
+ if (result == 'M') {
+ SKIP(free(handle); close(pipefd[0]);
+ return, "Cannot set uid/gid mappings");
+ }
+ if (result == 'N') {
+ SKIP(free(handle); close(pipefd[0]);
+ return, "Cannot create new UTS namespace");
+ }
+
+ /* Should fail with ESTALE since we're in a different user namespace */
+ ASSERT_EQ(result, 'P');
+
+ close(pipefd[0]);
+ free(handle);
+}
+
+TEST(nsfs_user_ipc_namespace_isolation)
+{
+ struct file_handle *handle;
+ int mount_id;
+ int ret;
+ int fd;
+ int ns_fd;
+ pid_t pid;
+ int status;
+ int pipefd[2];
+ char result;
+
+ handle = malloc(sizeof(*handle) + MAX_HANDLE_SZ);
+ ASSERT_NE(handle, NULL);
+
+ /* Create pipe for communication */
+ ASSERT_EQ(pipe(pipefd), 0);
+
+ /* Get handle for current IPC namespace */
+ ns_fd = open("/proc/self/ns/ipc", O_RDONLY);
+ ASSERT_GE(ns_fd, 0);
+
+ handle->handle_bytes = MAX_HANDLE_SZ;
+ ret = name_to_handle_at(ns_fd, "", handle, &mount_id, AT_EMPTY_PATH);
+ if (ret < 0 && errno == EOPNOTSUPP) {
+ SKIP(free(handle); close(ns_fd); close(pipefd[0]);
+ close(pipefd[1]);
+ return, "nsfs doesn't support file handles");
+ }
+ ASSERT_EQ(ret, 0);
+ close(ns_fd);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ /* Child process */
+ close(pipefd[0]);
+
+ /* First create new user namespace to drop privileges */
+ ret = unshare(CLONE_NEWUSER);
+ if (ret < 0) {
+ write(pipefd[1], "U",
+ 1); /* Unable to create user namespace */
+ close(pipefd[1]);
+ exit(0);
+ }
+
+ /* Write uid/gid mappings to maintain some capabilities */
+ int uid_map_fd = open("/proc/self/uid_map", O_WRONLY);
+ int gid_map_fd = open("/proc/self/gid_map", O_WRONLY);
+ int setgroups_fd = open("/proc/self/setgroups", O_WRONLY);
+
+ if (uid_map_fd < 0 || gid_map_fd < 0 || setgroups_fd < 0) {
+ write(pipefd[1], "M", 1); /* Unable to set mappings */
+ close(pipefd[1]);
+ exit(0);
+ }
+
+ /* Disable setgroups to allow gid mapping */
+ write(setgroups_fd, "deny", 4);
+ close(setgroups_fd);
+
+ /* Map current uid/gid to root in the new namespace */
+ char mapping[64];
+ snprintf(mapping, sizeof(mapping), "0 %d 1", getuid());
+ write(uid_map_fd, mapping, strlen(mapping));
+ close(uid_map_fd);
+
+ snprintf(mapping, sizeof(mapping), "0 %d 1", getgid());
+ write(gid_map_fd, mapping, strlen(mapping));
+ close(gid_map_fd);
+
+ /* Now create new IPC namespace */
+ ret = unshare(CLONE_NEWIPC);
+ if (ret < 0) {
+ write(pipefd[1], "N",
+ 1); /* Unable to create IPC namespace */
+ close(pipefd[1]);
+ exit(0);
+ }
+
+ /* Try to open parent's IPC namespace handle from new user+ipc namespace */
+ fd = open_by_handle_at(FD_NSFS_ROOT, handle, O_RDONLY);
+
+ if (fd >= 0) {
+ /* Should NOT succeed - we're in a different user namespace */
+ write(pipefd[1], "S", 1); /* Unexpected success */
+ close(fd);
+ } else if (errno == ESTALE) {
+ /* Expected: Stale file handle */
+ write(pipefd[1], "P", 1);
+ } else {
+ /* Other error */
+ write(pipefd[1], "F", 1);
+ }
+
+ close(pipefd[1]);
+ exit(0);
+ }
+
+ /* Parent process */
+ close(pipefd[1]);
+ ASSERT_EQ(read(pipefd[0], &result, 1), 1);
+
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFEXITED(status));
+ ASSERT_EQ(WEXITSTATUS(status), 0);
+
+ if (result == 'U') {
+ SKIP(free(handle); close(pipefd[0]);
+ return, "Cannot create new user namespace");
+ }
+ if (result == 'M') {
+ SKIP(free(handle); close(pipefd[0]);
+ return, "Cannot set uid/gid mappings");
+ }
+ if (result == 'N') {
+ SKIP(free(handle); close(pipefd[0]);
+ return, "Cannot create new IPC namespace");
+ }
+
+ /* Should fail with ESTALE since we're in a different user namespace */
+ ASSERT_EQ(result, 'P');
+
+ close(pipefd[0]);
+ free(handle);
+}
+
+TEST(nsfs_user_mnt_namespace_isolation)
+{
+ struct file_handle *handle;
+ int mount_id;
+ int ret;
+ int fd;
+ int ns_fd;
+ pid_t pid;
+ int status;
+ int pipefd[2];
+ char result;
+
+ handle = malloc(sizeof(*handle) + MAX_HANDLE_SZ);
+ ASSERT_NE(handle, NULL);
+
+ /* Create pipe for communication */
+ ASSERT_EQ(pipe(pipefd), 0);
+
+ /* Get handle for current mount namespace */
+ ns_fd = open("/proc/self/ns/mnt", O_RDONLY);
+ ASSERT_GE(ns_fd, 0);
+
+ handle->handle_bytes = MAX_HANDLE_SZ;
+ ret = name_to_handle_at(ns_fd, "", handle, &mount_id, AT_EMPTY_PATH);
+ if (ret < 0 && errno == EOPNOTSUPP) {
+ SKIP(free(handle); close(ns_fd); close(pipefd[0]);
+ close(pipefd[1]);
+ return, "nsfs doesn't support file handles");
+ }
+ ASSERT_EQ(ret, 0);
+ close(ns_fd);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ /* Child process */
+ close(pipefd[0]);
+
+ /* First create new user namespace to drop privileges */
+ ret = unshare(CLONE_NEWUSER);
+ if (ret < 0) {
+ write(pipefd[1], "U",
+ 1); /* Unable to create user namespace */
+ close(pipefd[1]);
+ exit(0);
+ }
+
+ /* Write uid/gid mappings to maintain some capabilities */
+ int uid_map_fd = open("/proc/self/uid_map", O_WRONLY);
+ int gid_map_fd = open("/proc/self/gid_map", O_WRONLY);
+ int setgroups_fd = open("/proc/self/setgroups", O_WRONLY);
+
+ if (uid_map_fd < 0 || gid_map_fd < 0 || setgroups_fd < 0) {
+ write(pipefd[1], "M", 1); /* Unable to set mappings */
+ close(pipefd[1]);
+ exit(0);
+ }
+
+ /* Disable setgroups to allow gid mapping */
+ write(setgroups_fd, "deny", 4);
+ close(setgroups_fd);
+
+ /* Map current uid/gid to root in the new namespace */
+ char mapping[64];
+ snprintf(mapping, sizeof(mapping), "0 %d 1", getuid());
+ write(uid_map_fd, mapping, strlen(mapping));
+ close(uid_map_fd);
+
+ snprintf(mapping, sizeof(mapping), "0 %d 1", getgid());
+ write(gid_map_fd, mapping, strlen(mapping));
+ close(gid_map_fd);
+
+ /* Now create new mount namespace */
+ ret = unshare(CLONE_NEWNS);
+ if (ret < 0) {
+ write(pipefd[1], "N",
+ 1); /* Unable to create mount namespace */
+ close(pipefd[1]);
+ exit(0);
+ }
+
+ /* Try to open parent's mount namespace handle from new user+mnt namespace */
+ fd = open_by_handle_at(FD_NSFS_ROOT, handle, O_RDONLY);
+
+ if (fd >= 0) {
+ /* Should NOT succeed - we're in a different user namespace */
+ write(pipefd[1], "S", 1); /* Unexpected success */
+ close(fd);
+ } else if (errno == ESTALE) {
+ /* Expected: Stale file handle */
+ write(pipefd[1], "P", 1);
+ } else {
+ /* Other error */
+ write(pipefd[1], "F", 1);
+ }
+
+ close(pipefd[1]);
+ exit(0);
+ }
+
+ /* Parent process */
+ close(pipefd[1]);
+ ASSERT_EQ(read(pipefd[0], &result, 1), 1);
+
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFEXITED(status));
+ ASSERT_EQ(WEXITSTATUS(status), 0);
+
+ if (result == 'U') {
+ SKIP(free(handle); close(pipefd[0]);
+ return, "Cannot create new user namespace");
+ }
+ if (result == 'M') {
+ SKIP(free(handle); close(pipefd[0]);
+ return, "Cannot set uid/gid mappings");
+ }
+ if (result == 'N') {
+ SKIP(free(handle); close(pipefd[0]);
+ return, "Cannot create new mount namespace");
+ }
+
+ /* Should fail with ESTALE since we're in a different user namespace */
+ ASSERT_EQ(result, 'P');
+
+ close(pipefd[0]);
+ free(handle);
+}
+
+TEST(nsfs_user_cgroup_namespace_isolation)
+{
+ struct file_handle *handle;
+ int mount_id;
+ int ret;
+ int fd;
+ int ns_fd;
+ pid_t pid;
+ int status;
+ int pipefd[2];
+ char result;
+
+ handle = malloc(sizeof(*handle) + MAX_HANDLE_SZ);
+ ASSERT_NE(handle, NULL);
+
+ /* Create pipe for communication */
+ ASSERT_EQ(pipe(pipefd), 0);
+
+ /* Get handle for current cgroup namespace */
+ ns_fd = open("/proc/self/ns/cgroup", O_RDONLY);
+ if (ns_fd < 0) {
+ SKIP(free(handle); close(pipefd[0]); close(pipefd[1]);
+ return, "cgroup namespace not available");
+ }
+
+ handle->handle_bytes = MAX_HANDLE_SZ;
+ ret = name_to_handle_at(ns_fd, "", handle, &mount_id, AT_EMPTY_PATH);
+ if (ret < 0 && errno == EOPNOTSUPP) {
+ SKIP(free(handle); close(ns_fd); close(pipefd[0]);
+ close(pipefd[1]);
+ return, "nsfs doesn't support file handles");
+ }
+ ASSERT_EQ(ret, 0);
+ close(ns_fd);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ /* Child process */
+ close(pipefd[0]);
+
+ /* First create new user namespace to drop privileges */
+ ret = unshare(CLONE_NEWUSER);
+ if (ret < 0) {
+ write(pipefd[1], "U",
+ 1); /* Unable to create user namespace */
+ close(pipefd[1]);
+ exit(0);
+ }
+
+ /* Write uid/gid mappings to maintain some capabilities */
+ int uid_map_fd = open("/proc/self/uid_map", O_WRONLY);
+ int gid_map_fd = open("/proc/self/gid_map", O_WRONLY);
+ int setgroups_fd = open("/proc/self/setgroups", O_WRONLY);
+
+ if (uid_map_fd < 0 || gid_map_fd < 0 || setgroups_fd < 0) {
+ write(pipefd[1], "M", 1); /* Unable to set mappings */
+ close(pipefd[1]);
+ exit(0);
+ }
+
+ /* Disable setgroups to allow gid mapping */
+ write(setgroups_fd, "deny", 4);
+ close(setgroups_fd);
+
+ /* Map current uid/gid to root in the new namespace */
+ char mapping[64];
+ snprintf(mapping, sizeof(mapping), "0 %d 1", getuid());
+ write(uid_map_fd, mapping, strlen(mapping));
+ close(uid_map_fd);
+
+ snprintf(mapping, sizeof(mapping), "0 %d 1", getgid());
+ write(gid_map_fd, mapping, strlen(mapping));
+ close(gid_map_fd);
+
+ /* Now create new cgroup namespace */
+ ret = unshare(CLONE_NEWCGROUP);
+ if (ret < 0) {
+ write(pipefd[1], "N",
+ 1); /* Unable to create cgroup namespace */
+ close(pipefd[1]);
+ exit(0);
+ }
+
+ /* Try to open parent's cgroup namespace handle from new user+cgroup namespace */
+ fd = open_by_handle_at(FD_NSFS_ROOT, handle, O_RDONLY);
+
+ if (fd >= 0) {
+ /* Should NOT succeed - we're in a different user namespace */
+ write(pipefd[1], "S", 1); /* Unexpected success */
+ close(fd);
+ } else if (errno == ESTALE) {
+ /* Expected: Stale file handle */
+ write(pipefd[1], "P", 1);
+ } else {
+ /* Other error */
+ write(pipefd[1], "F", 1);
+ }
+
+ close(pipefd[1]);
+ exit(0);
+ }
+
+ /* Parent process */
+ close(pipefd[1]);
+ ASSERT_EQ(read(pipefd[0], &result, 1), 1);
+
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFEXITED(status));
+ ASSERT_EQ(WEXITSTATUS(status), 0);
+
+ if (result == 'U') {
+ SKIP(free(handle); close(pipefd[0]);
+ return, "Cannot create new user namespace");
+ }
+ if (result == 'M') {
+ SKIP(free(handle); close(pipefd[0]);
+ return, "Cannot set uid/gid mappings");
+ }
+ if (result == 'N') {
+ SKIP(free(handle); close(pipefd[0]);
+ return, "Cannot create new cgroup namespace");
+ }
+
+ /* Should fail with ESTALE since we're in a different user namespace */
+ ASSERT_EQ(result, 'P');
+
+ close(pipefd[0]);
+ free(handle);
+}
+
+TEST(nsfs_user_pid_namespace_isolation)
+{
+ struct file_handle *handle;
+ int mount_id;
+ int ret;
+ int fd;
+ int ns_fd;
+ pid_t pid;
+ int status;
+ int pipefd[2];
+ char result;
+
+ handle = malloc(sizeof(*handle) + MAX_HANDLE_SZ);
+ ASSERT_NE(handle, NULL);
+
+ /* Create pipe for communication */
+ ASSERT_EQ(pipe(pipefd), 0);
+
+ /* Get handle for current PID namespace */
+ ns_fd = open("/proc/self/ns/pid", O_RDONLY);
+ ASSERT_GE(ns_fd, 0);
+
+ handle->handle_bytes = MAX_HANDLE_SZ;
+ ret = name_to_handle_at(ns_fd, "", handle, &mount_id, AT_EMPTY_PATH);
+ if (ret < 0 && errno == EOPNOTSUPP) {
+ SKIP(free(handle); close(ns_fd); close(pipefd[0]);
+ close(pipefd[1]);
+ return, "nsfs doesn't support file handles");
+ }
+ ASSERT_EQ(ret, 0);
+ close(ns_fd);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ /* Child process */
+ close(pipefd[0]);
+
+ /* First create new user namespace to drop privileges */
+ ret = unshare(CLONE_NEWUSER);
+ if (ret < 0) {
+ write(pipefd[1], "U",
+ 1); /* Unable to create user namespace */
+ close(pipefd[1]);
+ exit(0);
+ }
+
+ /* Write uid/gid mappings to maintain some capabilities */
+ int uid_map_fd = open("/proc/self/uid_map", O_WRONLY);
+ int gid_map_fd = open("/proc/self/gid_map", O_WRONLY);
+ int setgroups_fd = open("/proc/self/setgroups", O_WRONLY);
+
+ if (uid_map_fd < 0 || gid_map_fd < 0 || setgroups_fd < 0) {
+ write(pipefd[1], "M", 1); /* Unable to set mappings */
+ close(pipefd[1]);
+ exit(0);
+ }
+
+ /* Disable setgroups to allow gid mapping */
+ write(setgroups_fd, "deny", 4);
+ close(setgroups_fd);
+
+ /* Map current uid/gid to root in the new namespace */
+ char mapping[64];
+ snprintf(mapping, sizeof(mapping), "0 %d 1", getuid());
+ write(uid_map_fd, mapping, strlen(mapping));
+ close(uid_map_fd);
+
+ snprintf(mapping, sizeof(mapping), "0 %d 1", getgid());
+ write(gid_map_fd, mapping, strlen(mapping));
+ close(gid_map_fd);
+
+ /* Now create new PID namespace - requires fork to take effect */
+ ret = unshare(CLONE_NEWPID);
+ if (ret < 0) {
+ write(pipefd[1], "N",
+ 1); /* Unable to create PID namespace */
+ close(pipefd[1]);
+ exit(0);
+ }
+
+ /* Fork again for PID namespace to take effect */
+ pid_t child_pid = fork();
+ if (child_pid < 0) {
+ write(pipefd[1], "N",
+ 1); /* Unable to fork in PID namespace */
+ close(pipefd[1]);
+ exit(0);
+ }
+
+ if (child_pid == 0) {
+ /* Grandchild in new PID namespace */
+ /* Try to open parent's PID namespace handle from new user+pid namespace */
+ fd = open_by_handle_at(FD_NSFS_ROOT, handle, O_RDONLY);
+
+ if (fd >= 0) {
+ /* Should NOT succeed - we're in a different user namespace */
+ write(pipefd[1], "S",
+ 1); /* Unexpected success */
+ close(fd);
+ } else if (errno == ESTALE) {
+ /* Expected: Stale file handle */
+ write(pipefd[1], "P", 1);
+ } else {
+ /* Other error */
+ write(pipefd[1], "F", 1);
+ }
+
+ close(pipefd[1]);
+ exit(0);
+ }
+
+ /* Wait for grandchild */
+ waitpid(child_pid, NULL, 0);
+ exit(0);
+ }
+
+ /* Parent process */
+ close(pipefd[1]);
+ ASSERT_EQ(read(pipefd[0], &result, 1), 1);
+
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFEXITED(status));
+ ASSERT_EQ(WEXITSTATUS(status), 0);
+
+ if (result == 'U') {
+ SKIP(free(handle); close(pipefd[0]);
+ return, "Cannot create new user namespace");
+ }
+ if (result == 'M') {
+ SKIP(free(handle); close(pipefd[0]);
+ return, "Cannot set uid/gid mappings");
+ }
+ if (result == 'N') {
+ SKIP(free(handle); close(pipefd[0]);
+ return, "Cannot create new PID namespace");
+ }
+
+ /* Should fail with ESTALE since we're in a different user namespace */
+ ASSERT_EQ(result, 'P');
+
+ close(pipefd[0]);
+ free(handle);
+}
+
+TEST(nsfs_user_time_namespace_isolation)
+{
+ struct file_handle *handle;
+ int mount_id;
+ int ret;
+ int fd;
+ int ns_fd;
+ pid_t pid;
+ int status;
+ int pipefd[2];
+ char result;
+
+ handle = malloc(sizeof(*handle) + MAX_HANDLE_SZ);
+ ASSERT_NE(handle, NULL);
+
+ /* Create pipe for communication */
+ ASSERT_EQ(pipe(pipefd), 0);
+
+ /* Get handle for current time namespace */
+ ns_fd = open("/proc/self/ns/time", O_RDONLY);
+ if (ns_fd < 0) {
+ SKIP(free(handle); close(pipefd[0]); close(pipefd[1]);
+ return, "time namespace not available");
+ }
+
+ handle->handle_bytes = MAX_HANDLE_SZ;
+ ret = name_to_handle_at(ns_fd, "", handle, &mount_id, AT_EMPTY_PATH);
+ if (ret < 0 && errno == EOPNOTSUPP) {
+ SKIP(free(handle); close(ns_fd); close(pipefd[0]);
+ close(pipefd[1]);
+ return, "nsfs doesn't support file handles");
+ }
+ ASSERT_EQ(ret, 0);
+ close(ns_fd);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ /* Child process */
+ close(pipefd[0]);
+
+ /* First create new user namespace to drop privileges */
+ ret = unshare(CLONE_NEWUSER);
+ if (ret < 0) {
+ write(pipefd[1], "U",
+ 1); /* Unable to create user namespace */
+ close(pipefd[1]);
+ exit(0);
+ }
+
+ /* Write uid/gid mappings to maintain some capabilities */
+ int uid_map_fd = open("/proc/self/uid_map", O_WRONLY);
+ int gid_map_fd = open("/proc/self/gid_map", O_WRONLY);
+ int setgroups_fd = open("/proc/self/setgroups", O_WRONLY);
+
+ if (uid_map_fd < 0 || gid_map_fd < 0 || setgroups_fd < 0) {
+ write(pipefd[1], "M", 1); /* Unable to set mappings */
+ close(pipefd[1]);
+ exit(0);
+ }
+
+ /* Disable setgroups to allow gid mapping */
+ write(setgroups_fd, "deny", 4);
+ close(setgroups_fd);
+
+ /* Map current uid/gid to root in the new namespace */
+ char mapping[64];
+ snprintf(mapping, sizeof(mapping), "0 %d 1", getuid());
+ write(uid_map_fd, mapping, strlen(mapping));
+ close(uid_map_fd);
+
+ snprintf(mapping, sizeof(mapping), "0 %d 1", getgid());
+ write(gid_map_fd, mapping, strlen(mapping));
+ close(gid_map_fd);
+
+ /* Now create new time namespace - requires fork to take effect */
+ ret = unshare(CLONE_NEWTIME);
+ if (ret < 0) {
+ write(pipefd[1], "N",
+ 1); /* Unable to create time namespace */
+ close(pipefd[1]);
+ exit(0);
+ }
+
+ /* Fork again for time namespace to take effect */
+ pid_t child_pid = fork();
+ if (child_pid < 0) {
+ write(pipefd[1], "N",
+ 1); /* Unable to fork in time namespace */
+ close(pipefd[1]);
+ exit(0);
+ }
+
+ if (child_pid == 0) {
+ /* Grandchild in new time namespace */
+ /* Try to open parent's time namespace handle from new user+time namespace */
+ fd = open_by_handle_at(FD_NSFS_ROOT, handle, O_RDONLY);
+
+ if (fd >= 0) {
+ /* Should NOT succeed - we're in a different user namespace */
+ write(pipefd[1], "S",
+ 1); /* Unexpected success */
+ close(fd);
+ } else if (errno == ESTALE) {
+ /* Expected: Stale file handle */
+ write(pipefd[1], "P", 1);
+ } else {
+ /* Other error */
+ write(pipefd[1], "F", 1);
+ }
+
+ close(pipefd[1]);
+ exit(0);
+ }
+
+ /* Wait for grandchild */
+ waitpid(child_pid, NULL, 0);
+ exit(0);
+ }
+
+ /* Parent process */
+ close(pipefd[1]);
+ ASSERT_EQ(read(pipefd[0], &result, 1), 1);
+
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFEXITED(status));
+ ASSERT_EQ(WEXITSTATUS(status), 0);
+
+ if (result == 'U') {
+ SKIP(free(handle); close(pipefd[0]);
+ return, "Cannot create new user namespace");
+ }
+ if (result == 'M') {
+ SKIP(free(handle); close(pipefd[0]);
+ return, "Cannot set uid/gid mappings");
+ }
+ if (result == 'N') {
+ SKIP(free(handle); close(pipefd[0]);
+ return, "Cannot create new time namespace");
+ }
+
+ /* Should fail with ESTALE since we're in a different user namespace */
+ ASSERT_EQ(result, 'P');
+
+ close(pipefd[0]);
+ free(handle);
+}
+
+TEST(nsfs_open_flags)
+{
+ struct file_handle *handle;
+ int mount_id;
+ int ret;
+ int fd;
+ int ns_fd;
+
+ handle = malloc(sizeof(*handle) + MAX_HANDLE_SZ);
+ ASSERT_NE(handle, NULL);
+
+ /* Open a namespace file descriptor */
+ ns_fd = open("/proc/self/ns/net", O_RDONLY);
+ ASSERT_GE(ns_fd, 0);
+
+ /* Get handle for the namespace */
+ handle->handle_bytes = MAX_HANDLE_SZ;
+ ret = name_to_handle_at(ns_fd, "", handle, &mount_id, AT_EMPTY_PATH);
+ if (ret < 0 && errno == EOPNOTSUPP) {
+ SKIP(free(handle); close(ns_fd);
+ return, "nsfs doesn't support file handles");
+ }
+ ASSERT_EQ(ret, 0);
+ ASSERT_GT(handle->handle_bytes, 0);
+
+ /* Test invalid flags that should fail */
+ fd = open_by_handle_at(FD_NSFS_ROOT, handle, O_WRONLY);
+ ASSERT_LT(fd, 0);
+ ASSERT_EQ(errno, EPERM);
+
+ fd = open_by_handle_at(FD_NSFS_ROOT, handle, O_RDWR);
+ ASSERT_LT(fd, 0);
+ ASSERT_EQ(errno, EPERM);
+
+ fd = open_by_handle_at(FD_NSFS_ROOT, handle, O_TRUNC);
+ ASSERT_LT(fd, 0);
+ ASSERT_EQ(errno, EPERM);
+
+ fd = open_by_handle_at(FD_NSFS_ROOT, handle, O_DIRECT);
+ ASSERT_LT(fd, 0);
+ ASSERT_EQ(errno, EINVAL);
+
+ fd = open_by_handle_at(FD_NSFS_ROOT, handle, O_TMPFILE);
+ ASSERT_LT(fd, 0);
+ ASSERT_EQ(errno, EINVAL);
+
+ fd = open_by_handle_at(FD_NSFS_ROOT, handle, O_DIRECTORY);
+ ASSERT_LT(fd, 0);
+ ASSERT_EQ(errno, ENOTDIR);
+
+ close(ns_fd);
+ free(handle);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/namespaces/init_ino_test.c b/tools/testing/selftests/namespaces/init_ino_test.c
new file mode 100644
index 000000000000..5b6993c3740b
--- /dev/null
+++ b/tools/testing/selftests/namespaces/init_ino_test.c
@@ -0,0 +1,61 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+// Copyright (c) 2025 Christian Brauner <brauner@kernel.org>
+
+#define _GNU_SOURCE
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <sys/stat.h>
+#include <unistd.h>
+#include <errno.h>
+#include <string.h>
+#include <linux/nsfs.h>
+
+#include "../kselftest_harness.h"
+
+struct ns_info {
+ const char *name;
+ const char *proc_path;
+ unsigned int expected_ino;
+};
+
+static struct ns_info namespaces[] = {
+ { "ipc", "/proc/1/ns/ipc", IPC_NS_INIT_INO },
+ { "uts", "/proc/1/ns/uts", UTS_NS_INIT_INO },
+ { "user", "/proc/1/ns/user", USER_NS_INIT_INO },
+ { "pid", "/proc/1/ns/pid", PID_NS_INIT_INO },
+ { "cgroup", "/proc/1/ns/cgroup", CGROUP_NS_INIT_INO },
+ { "time", "/proc/1/ns/time", TIME_NS_INIT_INO },
+ { "net", "/proc/1/ns/net", NET_NS_INIT_INO },
+ { "mnt", "/proc/1/ns/mnt", MNT_NS_INIT_INO },
+};
+
+TEST(init_namespace_inodes)
+{
+ struct stat st;
+
+ for (int i = 0; i < sizeof(namespaces) / sizeof(namespaces[0]); i++) {
+ int ret = stat(namespaces[i].proc_path, &st);
+
+ /* Some namespaces might not be available (e.g., time namespace on older kernels) */
+ if (ret < 0) {
+ if (errno == ENOENT) {
+ ksft_test_result_skip("%s namespace not available\n",
+ namespaces[i].name);
+ continue;
+ }
+ ASSERT_GE(ret, 0)
+ TH_LOG("Failed to stat %s: %s",
+ namespaces[i].proc_path, strerror(errno));
+ }
+
+ ASSERT_EQ(st.st_ino, namespaces[i].expected_ino)
+ TH_LOG("Namespace %s has inode 0x%lx, expected 0x%x",
+ namespaces[i].name, st.st_ino, namespaces[i].expected_ino);
+
+ ksft_print_msg("Namespace %s: inode 0x%lx matches expected 0x%x\n",
+ namespaces[i].name, st.st_ino, namespaces[i].expected_ino);
+ }
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/namespaces/nsid_test.c b/tools/testing/selftests/namespaces/nsid_test.c
new file mode 100644
index 000000000000..e28accd74a57
--- /dev/null
+++ b/tools/testing/selftests/namespaces/nsid_test.c
@@ -0,0 +1,986 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <assert.h>
+#include <fcntl.h>
+#include <inttypes.h>
+#include <libgen.h>
+#include <limits.h>
+#include <pthread.h>
+#include <string.h>
+#include <sys/mount.h>
+#include <poll.h>
+#include <sys/epoll.h>
+#include <sys/resource.h>
+#include <sys/stat.h>
+#include <sys/socket.h>
+#include <sys/un.h>
+#include <unistd.h>
+#include <linux/fs.h>
+#include <linux/limits.h>
+#include <linux/nsfs.h>
+#include "../kselftest_harness.h"
+
+TEST(nsid_mntns_basic)
+{
+ __u64 mnt_ns_id = 0;
+ int fd_mntns;
+ int ret;
+
+ /* Open the current mount namespace */
+ fd_mntns = open("/proc/self/ns/mnt", O_RDONLY);
+ ASSERT_GE(fd_mntns, 0);
+
+ /* Get the mount namespace ID */
+ ret = ioctl(fd_mntns, NS_GET_MNTNS_ID, &mnt_ns_id);
+ ASSERT_EQ(ret, 0);
+ ASSERT_NE(mnt_ns_id, 0);
+
+ /* Verify we can get the same ID again */
+ __u64 mnt_ns_id2 = 0;
+ ret = ioctl(fd_mntns, NS_GET_ID, &mnt_ns_id2);
+ ASSERT_EQ(ret, 0);
+ ASSERT_EQ(mnt_ns_id, mnt_ns_id2);
+
+ close(fd_mntns);
+}
+
+TEST(nsid_mntns_separate)
+{
+ __u64 parent_mnt_ns_id = 0;
+ __u64 child_mnt_ns_id = 0;
+ int fd_parent_mntns, fd_child_mntns;
+ int ret;
+ pid_t pid;
+ int pipefd[2];
+
+ /* Get parent's mount namespace ID */
+ fd_parent_mntns = open("/proc/self/ns/mnt", O_RDONLY);
+ ASSERT_GE(fd_parent_mntns, 0);
+ ret = ioctl(fd_parent_mntns, NS_GET_ID, &parent_mnt_ns_id);
+ ASSERT_EQ(ret, 0);
+ ASSERT_NE(parent_mnt_ns_id, 0);
+
+ /* Create a pipe for synchronization */
+ ASSERT_EQ(pipe(pipefd), 0);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ /* Child process */
+ close(pipefd[0]);
+
+ /* Create new mount namespace */
+ ret = unshare(CLONE_NEWNS);
+ if (ret != 0) {
+ /* Skip test if we don't have permission */
+ if (errno == EPERM || errno == EACCES) {
+ write(pipefd[1], "S", 1); /* Signal skip */
+ _exit(0);
+ }
+ _exit(1);
+ }
+
+ /* Signal success */
+ write(pipefd[1], "Y", 1);
+ close(pipefd[1]);
+
+ /* Keep namespace alive */
+ pause();
+ _exit(0);
+ }
+
+ /* Parent process */
+ close(pipefd[1]);
+
+ char buf;
+ ASSERT_EQ(read(pipefd[0], &buf, 1), 1);
+ close(pipefd[0]);
+
+ if (buf == 'S') {
+ /* Child couldn't create namespace, skip test */
+ kill(pid, SIGTERM);
+ waitpid(pid, NULL, 0);
+ close(fd_parent_mntns);
+ SKIP(return, "No permission to create mount namespace");
+ }
+
+ ASSERT_EQ(buf, 'Y');
+
+ /* Open child's mount namespace */
+ char path[256];
+ snprintf(path, sizeof(path), "/proc/%d/ns/mnt", pid);
+ fd_child_mntns = open(path, O_RDONLY);
+ ASSERT_GE(fd_child_mntns, 0);
+
+ /* Get child's mount namespace ID */
+ ret = ioctl(fd_child_mntns, NS_GET_ID, &child_mnt_ns_id);
+ ASSERT_EQ(ret, 0);
+ ASSERT_NE(child_mnt_ns_id, 0);
+
+ /* Parent and child should have different mount namespace IDs */
+ ASSERT_NE(parent_mnt_ns_id, child_mnt_ns_id);
+
+ close(fd_parent_mntns);
+ close(fd_child_mntns);
+
+ /* Clean up child process */
+ kill(pid, SIGTERM);
+ waitpid(pid, NULL, 0);
+}
+
+TEST(nsid_cgroupns_basic)
+{
+ __u64 cgroup_ns_id = 0;
+ int fd_cgroupns;
+ int ret;
+
+ /* Open the current cgroup namespace */
+ fd_cgroupns = open("/proc/self/ns/cgroup", O_RDONLY);
+ ASSERT_GE(fd_cgroupns, 0);
+
+ /* Get the cgroup namespace ID */
+ ret = ioctl(fd_cgroupns, NS_GET_ID, &cgroup_ns_id);
+ ASSERT_EQ(ret, 0);
+ ASSERT_NE(cgroup_ns_id, 0);
+
+ /* Verify we can get the same ID again */
+ __u64 cgroup_ns_id2 = 0;
+ ret = ioctl(fd_cgroupns, NS_GET_ID, &cgroup_ns_id2);
+ ASSERT_EQ(ret, 0);
+ ASSERT_EQ(cgroup_ns_id, cgroup_ns_id2);
+
+ close(fd_cgroupns);
+}
+
+TEST(nsid_cgroupns_separate)
+{
+ __u64 parent_cgroup_ns_id = 0;
+ __u64 child_cgroup_ns_id = 0;
+ int fd_parent_cgroupns, fd_child_cgroupns;
+ int ret;
+ pid_t pid;
+ int pipefd[2];
+
+ /* Get parent's cgroup namespace ID */
+ fd_parent_cgroupns = open("/proc/self/ns/cgroup", O_RDONLY);
+ ASSERT_GE(fd_parent_cgroupns, 0);
+ ret = ioctl(fd_parent_cgroupns, NS_GET_ID, &parent_cgroup_ns_id);
+ ASSERT_EQ(ret, 0);
+ ASSERT_NE(parent_cgroup_ns_id, 0);
+
+ /* Create a pipe for synchronization */
+ ASSERT_EQ(pipe(pipefd), 0);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ /* Child process */
+ close(pipefd[0]);
+
+ /* Create new cgroup namespace */
+ ret = unshare(CLONE_NEWCGROUP);
+ if (ret != 0) {
+ /* Skip test if we don't have permission */
+ if (errno == EPERM || errno == EACCES) {
+ write(pipefd[1], "S", 1); /* Signal skip */
+ _exit(0);
+ }
+ _exit(1);
+ }
+
+ /* Signal success */
+ write(pipefd[1], "Y", 1);
+ close(pipefd[1]);
+
+ /* Keep namespace alive */
+ pause();
+ _exit(0);
+ }
+
+ /* Parent process */
+ close(pipefd[1]);
+
+ char buf;
+ ASSERT_EQ(read(pipefd[0], &buf, 1), 1);
+ close(pipefd[0]);
+
+ if (buf == 'S') {
+ /* Child couldn't create namespace, skip test */
+ kill(pid, SIGTERM);
+ waitpid(pid, NULL, 0);
+ close(fd_parent_cgroupns);
+ SKIP(return, "No permission to create cgroup namespace");
+ }
+
+ ASSERT_EQ(buf, 'Y');
+
+ /* Open child's cgroup namespace */
+ char path[256];
+ snprintf(path, sizeof(path), "/proc/%d/ns/cgroup", pid);
+ fd_child_cgroupns = open(path, O_RDONLY);
+ ASSERT_GE(fd_child_cgroupns, 0);
+
+ /* Get child's cgroup namespace ID */
+ ret = ioctl(fd_child_cgroupns, NS_GET_ID, &child_cgroup_ns_id);
+ ASSERT_EQ(ret, 0);
+ ASSERT_NE(child_cgroup_ns_id, 0);
+
+ /* Parent and child should have different cgroup namespace IDs */
+ ASSERT_NE(parent_cgroup_ns_id, child_cgroup_ns_id);
+
+ close(fd_parent_cgroupns);
+ close(fd_child_cgroupns);
+
+ /* Clean up child process */
+ kill(pid, SIGTERM);
+ waitpid(pid, NULL, 0);
+}
+
+TEST(nsid_ipcns_basic)
+{
+ __u64 ipc_ns_id = 0;
+ int fd_ipcns;
+ int ret;
+
+ /* Open the current IPC namespace */
+ fd_ipcns = open("/proc/self/ns/ipc", O_RDONLY);
+ ASSERT_GE(fd_ipcns, 0);
+
+ /* Get the IPC namespace ID */
+ ret = ioctl(fd_ipcns, NS_GET_ID, &ipc_ns_id);
+ ASSERT_EQ(ret, 0);
+ ASSERT_NE(ipc_ns_id, 0);
+
+ /* Verify we can get the same ID again */
+ __u64 ipc_ns_id2 = 0;
+ ret = ioctl(fd_ipcns, NS_GET_ID, &ipc_ns_id2);
+ ASSERT_EQ(ret, 0);
+ ASSERT_EQ(ipc_ns_id, ipc_ns_id2);
+
+ close(fd_ipcns);
+}
+
+TEST(nsid_ipcns_separate)
+{
+ __u64 parent_ipc_ns_id = 0;
+ __u64 child_ipc_ns_id = 0;
+ int fd_parent_ipcns, fd_child_ipcns;
+ int ret;
+ pid_t pid;
+ int pipefd[2];
+
+ /* Get parent's IPC namespace ID */
+ fd_parent_ipcns = open("/proc/self/ns/ipc", O_RDONLY);
+ ASSERT_GE(fd_parent_ipcns, 0);
+ ret = ioctl(fd_parent_ipcns, NS_GET_ID, &parent_ipc_ns_id);
+ ASSERT_EQ(ret, 0);
+ ASSERT_NE(parent_ipc_ns_id, 0);
+
+ /* Create a pipe for synchronization */
+ ASSERT_EQ(pipe(pipefd), 0);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ /* Child process */
+ close(pipefd[0]);
+
+ /* Create new IPC namespace */
+ ret = unshare(CLONE_NEWIPC);
+ if (ret != 0) {
+ /* Skip test if we don't have permission */
+ if (errno == EPERM || errno == EACCES) {
+ write(pipefd[1], "S", 1); /* Signal skip */
+ _exit(0);
+ }
+ _exit(1);
+ }
+
+ /* Signal success */
+ write(pipefd[1], "Y", 1);
+ close(pipefd[1]);
+
+ /* Keep namespace alive */
+ pause();
+ _exit(0);
+ }
+
+ /* Parent process */
+ close(pipefd[1]);
+
+ char buf;
+ ASSERT_EQ(read(pipefd[0], &buf, 1), 1);
+ close(pipefd[0]);
+
+ if (buf == 'S') {
+ /* Child couldn't create namespace, skip test */
+ kill(pid, SIGTERM);
+ waitpid(pid, NULL, 0);
+ close(fd_parent_ipcns);
+ SKIP(return, "No permission to create IPC namespace");
+ }
+
+ ASSERT_EQ(buf, 'Y');
+
+ /* Open child's IPC namespace */
+ char path[256];
+ snprintf(path, sizeof(path), "/proc/%d/ns/ipc", pid);
+ fd_child_ipcns = open(path, O_RDONLY);
+ ASSERT_GE(fd_child_ipcns, 0);
+
+ /* Get child's IPC namespace ID */
+ ret = ioctl(fd_child_ipcns, NS_GET_ID, &child_ipc_ns_id);
+ ASSERT_EQ(ret, 0);
+ ASSERT_NE(child_ipc_ns_id, 0);
+
+ /* Parent and child should have different IPC namespace IDs */
+ ASSERT_NE(parent_ipc_ns_id, child_ipc_ns_id);
+
+ close(fd_parent_ipcns);
+ close(fd_child_ipcns);
+
+ /* Clean up child process */
+ kill(pid, SIGTERM);
+ waitpid(pid, NULL, 0);
+}
+
+TEST(nsid_utsns_basic)
+{
+ __u64 uts_ns_id = 0;
+ int fd_utsns;
+ int ret;
+
+ /* Open the current UTS namespace */
+ fd_utsns = open("/proc/self/ns/uts", O_RDONLY);
+ ASSERT_GE(fd_utsns, 0);
+
+ /* Get the UTS namespace ID */
+ ret = ioctl(fd_utsns, NS_GET_ID, &uts_ns_id);
+ ASSERT_EQ(ret, 0);
+ ASSERT_NE(uts_ns_id, 0);
+
+ /* Verify we can get the same ID again */
+ __u64 uts_ns_id2 = 0;
+ ret = ioctl(fd_utsns, NS_GET_ID, &uts_ns_id2);
+ ASSERT_EQ(ret, 0);
+ ASSERT_EQ(uts_ns_id, uts_ns_id2);
+
+ close(fd_utsns);
+}
+
+TEST(nsid_utsns_separate)
+{
+ __u64 parent_uts_ns_id = 0;
+ __u64 child_uts_ns_id = 0;
+ int fd_parent_utsns, fd_child_utsns;
+ int ret;
+ pid_t pid;
+ int pipefd[2];
+
+ /* Get parent's UTS namespace ID */
+ fd_parent_utsns = open("/proc/self/ns/uts", O_RDONLY);
+ ASSERT_GE(fd_parent_utsns, 0);
+ ret = ioctl(fd_parent_utsns, NS_GET_ID, &parent_uts_ns_id);
+ ASSERT_EQ(ret, 0);
+ ASSERT_NE(parent_uts_ns_id, 0);
+
+ /* Create a pipe for synchronization */
+ ASSERT_EQ(pipe(pipefd), 0);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ /* Child process */
+ close(pipefd[0]);
+
+ /* Create new UTS namespace */
+ ret = unshare(CLONE_NEWUTS);
+ if (ret != 0) {
+ /* Skip test if we don't have permission */
+ if (errno == EPERM || errno == EACCES) {
+ write(pipefd[1], "S", 1); /* Signal skip */
+ _exit(0);
+ }
+ _exit(1);
+ }
+
+ /* Signal success */
+ write(pipefd[1], "Y", 1);
+ close(pipefd[1]);
+
+ /* Keep namespace alive */
+ pause();
+ _exit(0);
+ }
+
+ /* Parent process */
+ close(pipefd[1]);
+
+ char buf;
+ ASSERT_EQ(read(pipefd[0], &buf, 1), 1);
+ close(pipefd[0]);
+
+ if (buf == 'S') {
+ /* Child couldn't create namespace, skip test */
+ kill(pid, SIGTERM);
+ waitpid(pid, NULL, 0);
+ close(fd_parent_utsns);
+ SKIP(return, "No permission to create UTS namespace");
+ }
+
+ ASSERT_EQ(buf, 'Y');
+
+ /* Open child's UTS namespace */
+ char path[256];
+ snprintf(path, sizeof(path), "/proc/%d/ns/uts", pid);
+ fd_child_utsns = open(path, O_RDONLY);
+ ASSERT_GE(fd_child_utsns, 0);
+
+ /* Get child's UTS namespace ID */
+ ret = ioctl(fd_child_utsns, NS_GET_ID, &child_uts_ns_id);
+ ASSERT_EQ(ret, 0);
+ ASSERT_NE(child_uts_ns_id, 0);
+
+ /* Parent and child should have different UTS namespace IDs */
+ ASSERT_NE(parent_uts_ns_id, child_uts_ns_id);
+
+ close(fd_parent_utsns);
+ close(fd_child_utsns);
+
+ /* Clean up child process */
+ kill(pid, SIGTERM);
+ waitpid(pid, NULL, 0);
+}
+
+TEST(nsid_userns_basic)
+{
+ __u64 user_ns_id = 0;
+ int fd_userns;
+ int ret;
+
+ /* Open the current user namespace */
+ fd_userns = open("/proc/self/ns/user", O_RDONLY);
+ ASSERT_GE(fd_userns, 0);
+
+ /* Get the user namespace ID */
+ ret = ioctl(fd_userns, NS_GET_ID, &user_ns_id);
+ ASSERT_EQ(ret, 0);
+ ASSERT_NE(user_ns_id, 0);
+
+ /* Verify we can get the same ID again */
+ __u64 user_ns_id2 = 0;
+ ret = ioctl(fd_userns, NS_GET_ID, &user_ns_id2);
+ ASSERT_EQ(ret, 0);
+ ASSERT_EQ(user_ns_id, user_ns_id2);
+
+ close(fd_userns);
+}
+
+TEST(nsid_userns_separate)
+{
+ __u64 parent_user_ns_id = 0;
+ __u64 child_user_ns_id = 0;
+ int fd_parent_userns, fd_child_userns;
+ int ret;
+ pid_t pid;
+ int pipefd[2];
+
+ /* Get parent's user namespace ID */
+ fd_parent_userns = open("/proc/self/ns/user", O_RDONLY);
+ ASSERT_GE(fd_parent_userns, 0);
+ ret = ioctl(fd_parent_userns, NS_GET_ID, &parent_user_ns_id);
+ ASSERT_EQ(ret, 0);
+ ASSERT_NE(parent_user_ns_id, 0);
+
+ /* Create a pipe for synchronization */
+ ASSERT_EQ(pipe(pipefd), 0);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ /* Child process */
+ close(pipefd[0]);
+
+ /* Create new user namespace */
+ ret = unshare(CLONE_NEWUSER);
+ if (ret != 0) {
+ /* Skip test if we don't have permission */
+ if (errno == EPERM || errno == EACCES) {
+ write(pipefd[1], "S", 1); /* Signal skip */
+ _exit(0);
+ }
+ _exit(1);
+ }
+
+ /* Signal success */
+ write(pipefd[1], "Y", 1);
+ close(pipefd[1]);
+
+ /* Keep namespace alive */
+ pause();
+ _exit(0);
+ }
+
+ /* Parent process */
+ close(pipefd[1]);
+
+ char buf;
+ ASSERT_EQ(read(pipefd[0], &buf, 1), 1);
+ close(pipefd[0]);
+
+ if (buf == 'S') {
+ /* Child couldn't create namespace, skip test */
+ kill(pid, SIGTERM);
+ waitpid(pid, NULL, 0);
+ close(fd_parent_userns);
+ SKIP(return, "No permission to create user namespace");
+ }
+
+ ASSERT_EQ(buf, 'Y');
+
+ /* Open child's user namespace */
+ char path[256];
+ snprintf(path, sizeof(path), "/proc/%d/ns/user", pid);
+ fd_child_userns = open(path, O_RDONLY);
+ ASSERT_GE(fd_child_userns, 0);
+
+ /* Get child's user namespace ID */
+ ret = ioctl(fd_child_userns, NS_GET_ID, &child_user_ns_id);
+ ASSERT_EQ(ret, 0);
+ ASSERT_NE(child_user_ns_id, 0);
+
+ /* Parent and child should have different user namespace IDs */
+ ASSERT_NE(parent_user_ns_id, child_user_ns_id);
+
+ close(fd_parent_userns);
+ close(fd_child_userns);
+
+ /* Clean up child process */
+ kill(pid, SIGTERM);
+ waitpid(pid, NULL, 0);
+}
+
+TEST(nsid_timens_basic)
+{
+ __u64 time_ns_id = 0;
+ int fd_timens;
+ int ret;
+
+ /* Open the current time namespace */
+ fd_timens = open("/proc/self/ns/time", O_RDONLY);
+ if (fd_timens < 0) {
+ SKIP(return, "Time namespaces not supported");
+ }
+
+ /* Get the time namespace ID */
+ ret = ioctl(fd_timens, NS_GET_ID, &time_ns_id);
+ ASSERT_EQ(ret, 0);
+ ASSERT_NE(time_ns_id, 0);
+
+ /* Verify we can get the same ID again */
+ __u64 time_ns_id2 = 0;
+ ret = ioctl(fd_timens, NS_GET_ID, &time_ns_id2);
+ ASSERT_EQ(ret, 0);
+ ASSERT_EQ(time_ns_id, time_ns_id2);
+
+ close(fd_timens);
+}
+
+TEST(nsid_timens_separate)
+{
+ __u64 parent_time_ns_id = 0;
+ __u64 child_time_ns_id = 0;
+ int fd_parent_timens, fd_child_timens;
+ int ret;
+ pid_t pid;
+ int pipefd[2];
+
+ /* Open the current time namespace */
+ fd_parent_timens = open("/proc/self/ns/time", O_RDONLY);
+ if (fd_parent_timens < 0) {
+ SKIP(return, "Time namespaces not supported");
+ }
+
+ /* Get parent's time namespace ID */
+ ret = ioctl(fd_parent_timens, NS_GET_ID, &parent_time_ns_id);
+ ASSERT_EQ(ret, 0);
+ ASSERT_NE(parent_time_ns_id, 0);
+
+ /* Create a pipe for synchronization */
+ ASSERT_EQ(pipe(pipefd), 0);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ /* Child process */
+ close(pipefd[0]);
+
+ /* Create new time namespace */
+ ret = unshare(CLONE_NEWTIME);
+ if (ret != 0) {
+ /* Skip test if we don't have permission */
+ if (errno == EPERM || errno == EACCES || errno == EINVAL) {
+ write(pipefd[1], "S", 1); /* Signal skip */
+ _exit(0);
+ }
+ _exit(1);
+ }
+
+ /* Fork a grandchild to actually enter the new namespace */
+ pid_t grandchild = fork();
+ if (grandchild == 0) {
+ /* Grandchild is in the new namespace */
+ write(pipefd[1], "Y", 1);
+ close(pipefd[1]);
+ pause();
+ _exit(0);
+ } else if (grandchild > 0) {
+ /* Child writes grandchild PID and waits */
+ write(pipefd[1], "Y", 1);
+ write(pipefd[1], &grandchild, sizeof(grandchild));
+ close(pipefd[1]);
+ pause(); /* Keep the parent alive to maintain the grandchild */
+ _exit(0);
+ } else {
+ _exit(1);
+ }
+ }
+
+ /* Parent process */
+ close(pipefd[1]);
+
+ char buf;
+ ASSERT_EQ(read(pipefd[0], &buf, 1), 1);
+
+ if (buf == 'S') {
+ /* Child couldn't create namespace, skip test */
+ kill(pid, SIGTERM);
+ waitpid(pid, NULL, 0);
+ close(fd_parent_timens);
+ close(pipefd[0]);
+ SKIP(return, "Cannot create time namespace");
+ }
+
+ ASSERT_EQ(buf, 'Y');
+
+ pid_t grandchild_pid;
+ ASSERT_EQ(read(pipefd[0], &grandchild_pid, sizeof(grandchild_pid)), sizeof(grandchild_pid));
+ close(pipefd[0]);
+
+ /* Open grandchild's time namespace */
+ char path[256];
+ snprintf(path, sizeof(path), "/proc/%d/ns/time", grandchild_pid);
+ fd_child_timens = open(path, O_RDONLY);
+ ASSERT_GE(fd_child_timens, 0);
+
+ /* Get child's time namespace ID */
+ ret = ioctl(fd_child_timens, NS_GET_ID, &child_time_ns_id);
+ ASSERT_EQ(ret, 0);
+ ASSERT_NE(child_time_ns_id, 0);
+
+ /* Parent and child should have different time namespace IDs */
+ ASSERT_NE(parent_time_ns_id, child_time_ns_id);
+
+ close(fd_parent_timens);
+ close(fd_child_timens);
+
+ /* Clean up child process */
+ kill(pid, SIGTERM);
+ waitpid(pid, NULL, 0);
+}
+
+TEST(nsid_pidns_basic)
+{
+ __u64 pid_ns_id = 0;
+ int fd_pidns;
+ int ret;
+
+ /* Open the current PID namespace */
+ fd_pidns = open("/proc/self/ns/pid", O_RDONLY);
+ ASSERT_GE(fd_pidns, 0);
+
+ /* Get the PID namespace ID */
+ ret = ioctl(fd_pidns, NS_GET_ID, &pid_ns_id);
+ ASSERT_EQ(ret, 0);
+ ASSERT_NE(pid_ns_id, 0);
+
+ /* Verify we can get the same ID again */
+ __u64 pid_ns_id2 = 0;
+ ret = ioctl(fd_pidns, NS_GET_ID, &pid_ns_id2);
+ ASSERT_EQ(ret, 0);
+ ASSERT_EQ(pid_ns_id, pid_ns_id2);
+
+ close(fd_pidns);
+}
+
+TEST(nsid_pidns_separate)
+{
+ __u64 parent_pid_ns_id = 0;
+ __u64 child_pid_ns_id = 0;
+ int fd_parent_pidns, fd_child_pidns;
+ int ret;
+ pid_t pid;
+ int pipefd[2];
+
+ /* Get parent's PID namespace ID */
+ fd_parent_pidns = open("/proc/self/ns/pid", O_RDONLY);
+ ASSERT_GE(fd_parent_pidns, 0);
+ ret = ioctl(fd_parent_pidns, NS_GET_ID, &parent_pid_ns_id);
+ ASSERT_EQ(ret, 0);
+ ASSERT_NE(parent_pid_ns_id, 0);
+
+ /* Create a pipe for synchronization */
+ ASSERT_EQ(pipe(pipefd), 0);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ /* Child process */
+ close(pipefd[0]);
+
+ /* Create new PID namespace */
+ ret = unshare(CLONE_NEWPID);
+ if (ret != 0) {
+ /* Skip test if we don't have permission */
+ if (errno == EPERM || errno == EACCES) {
+ write(pipefd[1], "S", 1); /* Signal skip */
+ _exit(0);
+ }
+ _exit(1);
+ }
+
+ /* Fork a grandchild to actually enter the new namespace */
+ pid_t grandchild = fork();
+ if (grandchild == 0) {
+ /* Grandchild is in the new namespace */
+ write(pipefd[1], "Y", 1);
+ close(pipefd[1]);
+ pause();
+ _exit(0);
+ } else if (grandchild > 0) {
+ /* Child writes grandchild PID and waits */
+ write(pipefd[1], "Y", 1);
+ write(pipefd[1], &grandchild, sizeof(grandchild));
+ close(pipefd[1]);
+ pause(); /* Keep the parent alive to maintain the grandchild */
+ _exit(0);
+ } else {
+ _exit(1);
+ }
+ }
+
+ /* Parent process */
+ close(pipefd[1]);
+
+ char buf;
+ ASSERT_EQ(read(pipefd[0], &buf, 1), 1);
+
+ if (buf == 'S') {
+ /* Child couldn't create namespace, skip test */
+ kill(pid, SIGTERM);
+ waitpid(pid, NULL, 0);
+ close(fd_parent_pidns);
+ close(pipefd[0]);
+ SKIP(return, "No permission to create PID namespace");
+ }
+
+ ASSERT_EQ(buf, 'Y');
+
+ pid_t grandchild_pid;
+ ASSERT_EQ(read(pipefd[0], &grandchild_pid, sizeof(grandchild_pid)), sizeof(grandchild_pid));
+ close(pipefd[0]);
+
+ /* Open grandchild's PID namespace */
+ char path[256];
+ snprintf(path, sizeof(path), "/proc/%d/ns/pid", grandchild_pid);
+ fd_child_pidns = open(path, O_RDONLY);
+ ASSERT_GE(fd_child_pidns, 0);
+
+ /* Get child's PID namespace ID */
+ ret = ioctl(fd_child_pidns, NS_GET_ID, &child_pid_ns_id);
+ ASSERT_EQ(ret, 0);
+ ASSERT_NE(child_pid_ns_id, 0);
+
+ /* Parent and child should have different PID namespace IDs */
+ ASSERT_NE(parent_pid_ns_id, child_pid_ns_id);
+
+ close(fd_parent_pidns);
+ close(fd_child_pidns);
+
+ /* Clean up child process */
+ kill(pid, SIGTERM);
+ waitpid(pid, NULL, 0);
+}
+
+TEST(nsid_netns_basic)
+{
+ __u64 net_ns_id = 0;
+ __u64 netns_cookie = 0;
+ int fd_netns;
+ int sock;
+ socklen_t optlen;
+ int ret;
+
+ /* Open the current network namespace */
+ fd_netns = open("/proc/self/ns/net", O_RDONLY);
+ ASSERT_GE(fd_netns, 0);
+
+ /* Get the network namespace ID via ioctl */
+ ret = ioctl(fd_netns, NS_GET_ID, &net_ns_id);
+ ASSERT_EQ(ret, 0);
+ ASSERT_NE(net_ns_id, 0);
+
+ /* Create a socket to get the SO_NETNS_COOKIE */
+ sock = socket(AF_UNIX, SOCK_STREAM, 0);
+ ASSERT_GE(sock, 0);
+
+ /* Get the network namespace cookie via socket option */
+ optlen = sizeof(netns_cookie);
+ ret = getsockopt(sock, SOL_SOCKET, SO_NETNS_COOKIE, &netns_cookie, &optlen);
+ ASSERT_EQ(ret, 0);
+ ASSERT_EQ(optlen, sizeof(netns_cookie));
+
+ /* The namespace ID and cookie should be identical */
+ ASSERT_EQ(net_ns_id, netns_cookie);
+
+ /* Verify we can get the same ID again */
+ __u64 net_ns_id2 = 0;
+ ret = ioctl(fd_netns, NS_GET_ID, &net_ns_id2);
+ ASSERT_EQ(ret, 0);
+ ASSERT_EQ(net_ns_id, net_ns_id2);
+
+ close(sock);
+ close(fd_netns);
+}
+
+TEST(nsid_netns_separate)
+{
+ __u64 parent_net_ns_id = 0;
+ __u64 parent_netns_cookie = 0;
+ __u64 child_net_ns_id = 0;
+ __u64 child_netns_cookie = 0;
+ int fd_parent_netns, fd_child_netns;
+ int parent_sock, child_sock;
+ socklen_t optlen;
+ int ret;
+ pid_t pid;
+ int pipefd[2];
+
+ /* Get parent's network namespace ID */
+ fd_parent_netns = open("/proc/self/ns/net", O_RDONLY);
+ ASSERT_GE(fd_parent_netns, 0);
+ ret = ioctl(fd_parent_netns, NS_GET_ID, &parent_net_ns_id);
+ ASSERT_EQ(ret, 0);
+ ASSERT_NE(parent_net_ns_id, 0);
+
+ /* Get parent's network namespace cookie */
+ parent_sock = socket(AF_UNIX, SOCK_STREAM, 0);
+ ASSERT_GE(parent_sock, 0);
+ optlen = sizeof(parent_netns_cookie);
+ ret = getsockopt(parent_sock, SOL_SOCKET, SO_NETNS_COOKIE, &parent_netns_cookie, &optlen);
+ ASSERT_EQ(ret, 0);
+
+ /* Verify parent's ID and cookie match */
+ ASSERT_EQ(parent_net_ns_id, parent_netns_cookie);
+
+ /* Create a pipe for synchronization */
+ ASSERT_EQ(pipe(pipefd), 0);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ /* Child process */
+ close(pipefd[0]);
+
+ /* Create new network namespace */
+ ret = unshare(CLONE_NEWNET);
+ if (ret != 0) {
+ /* Skip test if we don't have permission */
+ if (errno == EPERM || errno == EACCES) {
+ write(pipefd[1], "S", 1); /* Signal skip */
+ _exit(0);
+ }
+ _exit(1);
+ }
+
+ /* Signal success */
+ write(pipefd[1], "Y", 1);
+ close(pipefd[1]);
+
+ /* Keep namespace alive */
+ pause();
+ _exit(0);
+ }
+
+ /* Parent process */
+ close(pipefd[1]);
+
+ char buf;
+ ASSERT_EQ(read(pipefd[0], &buf, 1), 1);
+ close(pipefd[0]);
+
+ if (buf == 'S') {
+ /* Child couldn't create namespace, skip test */
+ kill(pid, SIGTERM);
+ waitpid(pid, NULL, 0);
+ close(fd_parent_netns);
+ close(parent_sock);
+ SKIP(return, "No permission to create network namespace");
+ }
+
+ ASSERT_EQ(buf, 'Y');
+
+ /* Open child's network namespace */
+ char path[256];
+ snprintf(path, sizeof(path), "/proc/%d/ns/net", pid);
+ fd_child_netns = open(path, O_RDONLY);
+ ASSERT_GE(fd_child_netns, 0);
+
+ /* Get child's network namespace ID */
+ ret = ioctl(fd_child_netns, NS_GET_ID, &child_net_ns_id);
+ ASSERT_EQ(ret, 0);
+ ASSERT_NE(child_net_ns_id, 0);
+
+ /* Create socket in child's namespace to get cookie */
+ ret = setns(fd_child_netns, CLONE_NEWNET);
+ if (ret == 0) {
+ child_sock = socket(AF_UNIX, SOCK_STREAM, 0);
+ ASSERT_GE(child_sock, 0);
+
+ optlen = sizeof(child_netns_cookie);
+ ret = getsockopt(child_sock, SOL_SOCKET, SO_NETNS_COOKIE, &child_netns_cookie, &optlen);
+ ASSERT_EQ(ret, 0);
+
+ /* Verify child's ID and cookie match */
+ ASSERT_EQ(child_net_ns_id, child_netns_cookie);
+
+ close(child_sock);
+
+ /* Return to parent namespace */
+ setns(fd_parent_netns, CLONE_NEWNET);
+ }
+
+ /* Parent and child should have different network namespace IDs */
+ ASSERT_NE(parent_net_ns_id, child_net_ns_id);
+ if (child_netns_cookie != 0) {
+ ASSERT_NE(parent_netns_cookie, child_netns_cookie);
+ }
+
+ close(fd_parent_netns);
+ close(fd_child_netns);
+ close(parent_sock);
+
+ /* Clean up child process */
+ kill(pid, SIGTERM);
+ waitpid(pid, NULL, 0);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore
index 47c293c2962f..439101b518ee 100644
--- a/tools/testing/selftests/net/.gitignore
+++ b/tools/testing/selftests/net/.gitignore
@@ -16,6 +16,7 @@ ip_local_port_range
ipsec
ipv6_flowlabel
ipv6_flowlabel_mgr
+ipv6_fragmentation
log.txt
msg_oob
msg_zerocopy
@@ -51,6 +52,7 @@ tap
tcp_fastopen_backup_key
tcp_inq
tcp_mmap
+tcp_port_share
tfo
timestamping
tls
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index b31a71f2b372..5d9d96515c4a 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -8,11 +8,12 @@ CFLAGS += -I../
TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh \
rtnetlink.sh xfrm_policy.sh
+TEST_PROGS += fcnal-ipv4.sh fcnal-ipv6.sh fcnal-other.sh
TEST_PROGS += fib_tests.sh fib-onlink-tests.sh pmtu.sh udpgso.sh ip_defrag.sh
TEST_PROGS += udpgso_bench.sh fib_rule_tests.sh msg_zerocopy.sh psock_snd.sh
TEST_PROGS += udpgro_bench.sh 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 += tcp_fastopen_backup_key.sh l2tp.sh traceroute.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
@@ -99,6 +100,7 @@ TEST_GEN_PROGS += bind_wildcard
TEST_GEN_PROGS += bind_timewait
TEST_PROGS += test_vxlan_mdb.sh
TEST_PROGS += test_bridge_neigh_suppress.sh
+TEST_PROGS += test_vxlan_nh.sh
TEST_PROGS += test_vxlan_nolocalbypass.sh
TEST_PROGS += test_bridge_backup_port.sh
TEST_PROGS += test_neigh.sh
@@ -115,14 +117,21 @@ TEST_PROGS += skf_net_off.sh
TEST_GEN_FILES += skf_net_off
TEST_GEN_FILES += tfo
TEST_PROGS += tfo_passive.sh
+TEST_PROGS += broadcast_ether_dst.sh
TEST_PROGS += broadcast_pmtu.sh
TEST_PROGS += ipv6_force_forwarding.sh
+TEST_GEN_PROGS += ipv6_fragmentation
+TEST_PROGS += route_hint.sh
+TEST_GEN_PROGS += tcp_port_share
# YNL files, must be before "include ..lib.mk"
-YNL_GEN_FILES := busy_poller netlink-dumps
+YNL_GEN_FILES := busy_poller
+YNL_GEN_PROGS := netlink-dumps
TEST_GEN_FILES += $(YNL_GEN_FILES)
+TEST_GEN_PROGS += $(YNL_GEN_PROGS)
TEST_FILES := settings
+TEST_FILES += fcnal-test.sh
TEST_FILES += in_netns.sh lib.sh setup_loopback.sh setup_veth.sh
TEST_GEN_FILES += $(patsubst %.c,%.o,$(wildcard *.bpf.c))
diff --git a/tools/testing/selftests/net/af_unix/Makefile b/tools/testing/selftests/net/af_unix/Makefile
index a4b61c6d0290..0a20c98bbcfd 100644
--- a/tools/testing/selftests/net/af_unix/Makefile
+++ b/tools/testing/selftests/net/af_unix/Makefile
@@ -1,4 +1,4 @@
-CFLAGS += $(KHDR_INCLUDES)
+CFLAGS += $(KHDR_INCLUDES) -Wall -Wflex-array-member-not-at-end
TEST_GEN_PROGS := diag_uid msg_oob scm_inq scm_pidfd scm_rights unix_connect
include ../../lib.mk
diff --git a/tools/testing/selftests/net/af_unix/scm_inq.c b/tools/testing/selftests/net/af_unix/scm_inq.c
index 9d22561e7b8f..fc467714387e 100644
--- a/tools/testing/selftests/net/af_unix/scm_inq.c
+++ b/tools/testing/selftests/net/af_unix/scm_inq.c
@@ -11,11 +11,6 @@
#define NR_CHUNKS 100
#define MSG_LEN 256
-struct scm_inq {
- struct cmsghdr cmsghdr;
- int inq;
-};
-
FIXTURE(scm_inq)
{
int fd[2];
@@ -70,35 +65,38 @@ static void send_chunks(struct __test_metadata *_metadata,
static void recv_chunks(struct __test_metadata *_metadata,
FIXTURE_DATA(scm_inq) *self)
{
+ char cmsg_buf[CMSG_SPACE(sizeof(int))];
struct msghdr msg = {};
struct iovec iov = {};
- struct scm_inq cmsg;
+ struct cmsghdr *cmsg;
char buf[MSG_LEN];
int i, ret;
int inq;
msg.msg_iov = &iov;
msg.msg_iovlen = 1;
- msg.msg_control = &cmsg;
- msg.msg_controllen = CMSG_SPACE(sizeof(cmsg.inq));
+ msg.msg_control = cmsg_buf;
+ msg.msg_controllen = sizeof(cmsg_buf);
iov.iov_base = buf;
iov.iov_len = sizeof(buf);
for (i = 0; i < NR_CHUNKS; i++) {
memset(buf, 0, sizeof(buf));
- memset(&cmsg, 0, sizeof(cmsg));
+ memset(cmsg_buf, 0, sizeof(cmsg_buf));
ret = recvmsg(self->fd[1], &msg, 0);
ASSERT_EQ(MSG_LEN, ret);
- ASSERT_NE(NULL, CMSG_FIRSTHDR(&msg));
- ASSERT_EQ(CMSG_LEN(sizeof(cmsg.inq)), cmsg.cmsghdr.cmsg_len);
- ASSERT_EQ(SOL_SOCKET, cmsg.cmsghdr.cmsg_level);
- ASSERT_EQ(SCM_INQ, cmsg.cmsghdr.cmsg_type);
+
+ cmsg = CMSG_FIRSTHDR(&msg);
+ ASSERT_NE(NULL, cmsg);
+ ASSERT_EQ(CMSG_LEN(sizeof(int)), cmsg->cmsg_len);
+ ASSERT_EQ(SOL_SOCKET, cmsg->cmsg_level);
+ ASSERT_EQ(SCM_INQ, cmsg->cmsg_type);
ret = ioctl(self->fd[1], SIOCINQ, &inq);
ASSERT_EQ(0, ret);
- ASSERT_EQ(cmsg.inq, inq);
+ ASSERT_EQ(*(int *)CMSG_DATA(cmsg), inq);
}
}
diff --git a/tools/testing/selftests/net/af_unix/scm_pidfd.c b/tools/testing/selftests/net/af_unix/scm_pidfd.c
index 37e034874034..ef2921988e5f 100644
--- a/tools/testing/selftests/net/af_unix/scm_pidfd.c
+++ b/tools/testing/selftests/net/af_unix/scm_pidfd.c
@@ -137,7 +137,6 @@ struct cmsg_data {
static int parse_cmsg(struct msghdr *msg, struct cmsg_data *res)
{
struct cmsghdr *cmsg;
- int data = 0;
if (msg->msg_flags & (MSG_TRUNC | MSG_CTRUNC)) {
log_err("recvmsg: truncated");
@@ -243,7 +242,6 @@ static int cmsg_check_dead(int fd, int expected_pid)
int data = 0;
char control[CMSG_SPACE(sizeof(struct ucred)) +
CMSG_SPACE(sizeof(int))] = { 0 };
- pid_t client_pid;
struct pidfd_info info = {
.mask = PIDFD_INFO_EXIT,
};
diff --git a/tools/testing/selftests/net/af_unix/scm_rights.c b/tools/testing/selftests/net/af_unix/scm_rights.c
index 8b015f16c03d..914f99d153ce 100644
--- a/tools/testing/selftests/net/af_unix/scm_rights.c
+++ b/tools/testing/selftests/net/af_unix/scm_rights.c
@@ -271,20 +271,11 @@ void __send_fd(struct __test_metadata *_metadata,
{
#define MSG "x"
#define MSGLEN 1
- struct {
- struct cmsghdr cmsghdr;
- int fd[2];
- } cmsg = {
- .cmsghdr = {
- .cmsg_len = CMSG_LEN(sizeof(cmsg.fd)),
- .cmsg_level = SOL_SOCKET,
- .cmsg_type = SCM_RIGHTS,
- },
- .fd = {
- self->fd[inflight * 2],
- self->fd[inflight * 2],
- },
+ int fds[2] = {
+ self->fd[inflight * 2],
+ self->fd[inflight * 2],
};
+ char cmsg_buf[CMSG_SPACE(sizeof(fds))];
struct iovec iov = {
.iov_base = MSG,
.iov_len = MSGLEN,
@@ -294,11 +285,18 @@ void __send_fd(struct __test_metadata *_metadata,
.msg_namelen = 0,
.msg_iov = &iov,
.msg_iovlen = 1,
- .msg_control = &cmsg,
- .msg_controllen = CMSG_SPACE(sizeof(cmsg.fd)),
+ .msg_control = cmsg_buf,
+ .msg_controllen = sizeof(cmsg_buf),
};
+ struct cmsghdr *cmsg;
int ret;
+ cmsg = CMSG_FIRSTHDR(&msg);
+ cmsg->cmsg_level = SOL_SOCKET;
+ cmsg->cmsg_type = SCM_RIGHTS;
+ cmsg->cmsg_len = CMSG_LEN(sizeof(fds));
+ memcpy(CMSG_DATA(cmsg), fds, sizeof(fds));
+
ret = sendmsg(self->fd[receiver * 2 + 1], &msg, variant->flags);
if (variant->disabled) {
diff --git a/tools/testing/selftests/net/bind_bhash.c b/tools/testing/selftests/net/bind_bhash.c
index 57ff67a3751e..da04b0b19b73 100644
--- a/tools/testing/selftests/net/bind_bhash.c
+++ b/tools/testing/selftests/net/bind_bhash.c
@@ -75,7 +75,7 @@ static void *setup(void *arg)
int *array = (int *)arg;
for (i = 0; i < MAX_CONNECTIONS; i++) {
- sock_fd = bind_socket(SO_REUSEADDR | SO_REUSEPORT, setup_addr);
+ sock_fd = bind_socket(SO_REUSEPORT, setup_addr);
if (sock_fd < 0) {
ret = sock_fd;
pthread_exit(&ret);
@@ -103,7 +103,7 @@ int main(int argc, const char *argv[])
setup_addr = use_v6 ? setup_addr_v6 : setup_addr_v4;
- listener_fd = bind_socket(SO_REUSEADDR | SO_REUSEPORT, setup_addr);
+ listener_fd = bind_socket(SO_REUSEPORT, setup_addr);
if (listen(listener_fd, 100) < 0) {
perror("listen failed");
return -1;
diff --git a/tools/testing/selftests/net/bpf_offload.py b/tools/testing/selftests/net/bpf_offload.py
index b2c271b79240..c856d266c8f3 100755
--- a/tools/testing/selftests/net/bpf_offload.py
+++ b/tools/testing/selftests/net/bpf_offload.py
@@ -184,8 +184,8 @@ def bpftool_prog_list(expected=None, ns="", exclude_orphaned=True):
progs = [ p for p in progs if not p['orphaned'] ]
if expected is not None:
if len(progs) != expected:
- fail(True, "%d BPF programs loaded, expected %d" %
- (len(progs), expected))
+ fail(True, "%d BPF programs loaded, expected %d\nLoaded Progs:\n%s" %
+ (len(progs), expected, pp.pformat(progs)))
return progs
def bpftool_map_list(expected=None, ns=""):
diff --git a/tools/testing/selftests/net/broadcast_ether_dst.sh b/tools/testing/selftests/net/broadcast_ether_dst.sh
new file mode 100755
index 000000000000..334a7eca8a80
--- /dev/null
+++ b/tools/testing/selftests/net/broadcast_ether_dst.sh
@@ -0,0 +1,83 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Author: Brett A C Sheffield <bacs@librecast.net>
+# Author: Oscar Maes <oscmaes92@gmail.com>
+#
+# Ensure destination ethernet field is correctly set for
+# broadcast packets
+
+source lib.sh
+
+CLIENT_IP4="192.168.0.1"
+GW_IP4="192.168.0.2"
+
+setup() {
+ setup_ns CLIENT_NS SERVER_NS
+
+ ip -net "${SERVER_NS}" link add link1 type veth \
+ peer name link0 netns "${CLIENT_NS}"
+
+ ip -net "${CLIENT_NS}" link set link0 up
+ ip -net "${CLIENT_NS}" addr add "${CLIENT_IP4}"/24 dev link0
+
+ ip -net "${SERVER_NS}" link set link1 up
+
+ ip -net "${CLIENT_NS}" route add default via "${GW_IP4}"
+ ip netns exec "${CLIENT_NS}" arp -s "${GW_IP4}" 00:11:22:33:44:55
+}
+
+cleanup() {
+ rm -f "${CAPFILE}" "${OUTPUT}"
+ ip -net "${SERVER_NS}" link del link1
+ cleanup_ns "${CLIENT_NS}" "${SERVER_NS}"
+}
+
+test_broadcast_ether_dst() {
+ local rc=0
+ CAPFILE=$(mktemp -u cap.XXXXXXXXXX)
+ OUTPUT=$(mktemp -u out.XXXXXXXXXX)
+
+ echo "Testing ethernet broadcast destination"
+
+ # start tcpdump listening for icmp
+ # tcpdump will exit after receiving a single packet
+ # timeout will kill tcpdump if it is still running after 2s
+ timeout 2s ip netns exec "${CLIENT_NS}" \
+ tcpdump -i link0 -c 1 -w "${CAPFILE}" icmp &> "${OUTPUT}" &
+ pid=$!
+ slowwait 1 grep -qs "listening" "${OUTPUT}"
+
+ # send broadcast ping
+ ip netns exec "${CLIENT_NS}" \
+ ping -W0.01 -c1 -b 255.255.255.255 &> /dev/null
+
+ # wait for tcpdump for exit after receiving packet
+ wait "${pid}"
+
+ # compare ethernet destination field to ff:ff:ff:ff:ff:ff
+ ether_dst=$(tcpdump -r "${CAPFILE}" -tnne 2>/dev/null | \
+ awk '{sub(/,/,"",$3); print $3}')
+ if [[ "${ether_dst}" == "ff:ff:ff:ff:ff:ff" ]]; then
+ echo "[ OK ]"
+ rc="${ksft_pass}"
+ else
+ echo "[FAIL] expected dst ether addr to be ff:ff:ff:ff:ff:ff," \
+ "got ${ether_dst}"
+ rc="${ksft_fail}"
+ fi
+
+ return "${rc}"
+}
+
+if [ ! -x "$(command -v tcpdump)" ]; then
+ echo "SKIP: Could not run test without tcpdump tool"
+ exit "${ksft_skip}"
+fi
+
+trap cleanup EXIT
+
+setup
+test_broadcast_ether_dst
+
+exit $?
diff --git a/tools/testing/selftests/net/can/config b/tools/testing/selftests/net/can/config
new file mode 100644
index 000000000000..188f79796670
--- /dev/null
+++ b/tools/testing/selftests/net/can/config
@@ -0,0 +1,3 @@
+CONFIG_CAN=m
+CONFIG_CAN_DEV=m
+CONFIG_CAN_VCAN=m
diff --git a/tools/testing/selftests/net/cmsg_sender.c b/tools/testing/selftests/net/cmsg_sender.c
index a825e628aee7..ded9b925865e 100644
--- a/tools/testing/selftests/net/cmsg_sender.c
+++ b/tools/testing/selftests/net/cmsg_sender.c
@@ -491,7 +491,8 @@ int main(int argc, char *argv[])
if (err) {
fprintf(stderr, "Can't resolve address [%s]:%s\n",
opt.host, opt.service);
- return ERN_SOCK_CREATE;
+ err = ERN_SOCK_CREATE;
+ goto err_free_buff;
}
if (ai->ai_family == AF_INET6 && opt.sock.proto == IPPROTO_ICMP)
@@ -500,8 +501,8 @@ int main(int argc, char *argv[])
fd = socket(ai->ai_family, opt.sock.type, opt.sock.proto);
if (fd < 0) {
fprintf(stderr, "Can't open socket: %s\n", strerror(errno));
- freeaddrinfo(ai);
- return ERN_RESOLVE;
+ err = ERN_RESOLVE;
+ goto err_free_info;
}
if (opt.sock.proto == IPPROTO_ICMP) {
@@ -574,6 +575,9 @@ int main(int argc, char *argv[])
err_out:
close(fd);
+err_free_info:
freeaddrinfo(ai);
+err_free_buff:
+ free(buf);
return err;
}
diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config
index c24417d0047b..d548611e2698 100644
--- a/tools/testing/selftests/net/config
+++ b/tools/testing/selftests/net/config
@@ -26,6 +26,7 @@ CONFIG_IFB=y
CONFIG_INET_DIAG=y
CONFIG_INET_ESP=y
CONFIG_INET_ESP_OFFLOAD=y
+CONFIG_CRYPTO_SHA1=y
CONFIG_NET_FOU=y
CONFIG_NET_FOU_IP_TUNNELS=y
CONFIG_NETFILTER=y
diff --git a/tools/testing/selftests/net/fcnal-ipv4.sh b/tools/testing/selftests/net/fcnal-ipv4.sh
new file mode 100755
index 000000000000..82f9c867c3e8
--- /dev/null
+++ b/tools/testing/selftests/net/fcnal-ipv4.sh
@@ -0,0 +1,2 @@
+#!/bin/sh
+./fcnal-test.sh -t ipv4
diff --git a/tools/testing/selftests/net/fcnal-ipv6.sh b/tools/testing/selftests/net/fcnal-ipv6.sh
new file mode 100755
index 000000000000..ab1fc7aa3caf
--- /dev/null
+++ b/tools/testing/selftests/net/fcnal-ipv6.sh
@@ -0,0 +1,2 @@
+#!/bin/sh
+./fcnal-test.sh -t ipv6
diff --git a/tools/testing/selftests/net/fcnal-other.sh b/tools/testing/selftests/net/fcnal-other.sh
new file mode 100755
index 000000000000..a840cf80b32e
--- /dev/null
+++ b/tools/testing/selftests/net/fcnal-other.sh
@@ -0,0 +1,2 @@
+#!/bin/sh
+./fcnal-test.sh -t other
diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh
index 4fcc38907e48..844a580ae74e 100755
--- a/tools/testing/selftests/net/fcnal-test.sh
+++ b/tools/testing/selftests/net/fcnal-test.sh
@@ -189,7 +189,7 @@ show_hint()
kill_procs()
{
killall nettest ping ping6 >/dev/null 2>&1
- sleep 1
+ slowwait 2 sh -c 'test -z "$(pgrep '"'^(nettest|ping|ping6)$'"')"'
}
set_ping_group()
@@ -424,6 +424,8 @@ create_ns()
ip netns exec ${ns} sysctl -qw net.ipv6.conf.all.keep_addr_on_down=1
ip netns exec ${ns} sysctl -qw net.ipv6.conf.all.forwarding=1
ip netns exec ${ns} sysctl -qw net.ipv6.conf.default.forwarding=1
+ ip netns exec ${ns} sysctl -qw net.ipv6.conf.default.accept_dad=0
+ ip netns exec ${ns} sysctl -qw net.ipv6.conf.all.accept_dad=0
}
# create veth pair to connect namespaces and apply addresses.
@@ -875,7 +877,7 @@ ipv4_tcp_md5_novrf()
# basic use case
log_start
run_cmd nettest -s -M ${MD5_PW} -m ${NSB_IP} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -r ${NSA_IP} -X ${MD5_PW}
log_test $? 0 "MD5: Single address config"
@@ -883,7 +885,7 @@ ipv4_tcp_md5_novrf()
log_start
show_hint "Should timeout due to MD5 mismatch"
run_cmd nettest -s &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -r ${NSA_IP} -X ${MD5_PW}
log_test $? 2 "MD5: Server no config, client uses password"
@@ -891,7 +893,7 @@ ipv4_tcp_md5_novrf()
log_start
show_hint "Should timeout since client uses wrong password"
run_cmd nettest -s -M ${MD5_PW} -m ${NSB_IP} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -r ${NSA_IP} -X ${MD5_WRONG_PW}
log_test $? 2 "MD5: Client uses wrong password"
@@ -899,7 +901,7 @@ ipv4_tcp_md5_novrf()
log_start
show_hint "Should timeout due to MD5 mismatch"
run_cmd nettest -s -M ${MD5_PW} -m ${NSB_LO_IP} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -r ${NSA_IP} -X ${MD5_PW}
log_test $? 2 "MD5: Client address does not match address configured with password"
@@ -910,7 +912,7 @@ ipv4_tcp_md5_novrf()
# client in prefix
log_start
run_cmd nettest -s -M ${MD5_PW} -m ${NS_NET} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -r ${NSA_IP} -X ${MD5_PW}
log_test $? 0 "MD5: Prefix config"
@@ -918,7 +920,7 @@ ipv4_tcp_md5_novrf()
log_start
show_hint "Should timeout since client uses wrong password"
run_cmd nettest -s -M ${MD5_PW} -m ${NS_NET} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -r ${NSA_IP} -X ${MD5_WRONG_PW}
log_test $? 2 "MD5: Prefix config, client uses wrong password"
@@ -926,7 +928,7 @@ ipv4_tcp_md5_novrf()
log_start
show_hint "Should timeout due to MD5 mismatch"
run_cmd nettest -s -M ${MD5_PW} -m ${NS_NET} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -c ${NSB_LO_IP} -r ${NSA_IP} -X ${MD5_PW}
log_test $? 2 "MD5: Prefix config, client address not in configured prefix"
}
@@ -943,7 +945,7 @@ ipv4_tcp_md5()
# basic use case
log_start
run_cmd nettest -s -I ${VRF} -M ${MD5_PW} -m ${NSB_IP} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -r ${NSA_IP} -X ${MD5_PW}
log_test $? 0 "MD5: VRF: Single address config"
@@ -951,7 +953,7 @@ ipv4_tcp_md5()
log_start
show_hint "Should timeout since server does not have MD5 auth"
run_cmd nettest -s -I ${VRF} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -r ${NSA_IP} -X ${MD5_PW}
log_test $? 2 "MD5: VRF: Server no config, client uses password"
@@ -959,7 +961,7 @@ ipv4_tcp_md5()
log_start
show_hint "Should timeout since client uses wrong password"
run_cmd nettest -s -I ${VRF} -M ${MD5_PW} -m ${NSB_IP} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -r ${NSA_IP} -X ${MD5_WRONG_PW}
log_test $? 2 "MD5: VRF: Client uses wrong password"
@@ -967,7 +969,7 @@ ipv4_tcp_md5()
log_start
show_hint "Should timeout since server config differs from client"
run_cmd nettest -s -I ${VRF} -M ${MD5_PW} -m ${NSB_LO_IP} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -r ${NSA_IP} -X ${MD5_PW}
log_test $? 2 "MD5: VRF: Client address does not match address configured with password"
@@ -978,7 +980,7 @@ ipv4_tcp_md5()
# client in prefix
log_start
run_cmd nettest -s -I ${VRF} -M ${MD5_PW} -m ${NS_NET} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -r ${NSA_IP} -X ${MD5_PW}
log_test $? 0 "MD5: VRF: Prefix config"
@@ -986,7 +988,7 @@ ipv4_tcp_md5()
log_start
show_hint "Should timeout since client uses wrong password"
run_cmd nettest -s -I ${VRF} -M ${MD5_PW} -m ${NS_NET} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -r ${NSA_IP} -X ${MD5_WRONG_PW}
log_test $? 2 "MD5: VRF: Prefix config, client uses wrong password"
@@ -994,7 +996,7 @@ ipv4_tcp_md5()
log_start
show_hint "Should timeout since client address is outside of prefix"
run_cmd nettest -s -I ${VRF} -M ${MD5_PW} -m ${NS_NET} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -c ${NSB_LO_IP} -r ${NSA_IP} -X ${MD5_PW}
log_test $? 2 "MD5: VRF: Prefix config, client address not in configured prefix"
@@ -1005,14 +1007,14 @@ ipv4_tcp_md5()
log_start
run_cmd nettest -s -I ${VRF} -M ${MD5_PW} -m ${NSB_IP} &
run_cmd nettest -s -M ${MD5_WRONG_PW} -m ${NSB_IP} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -r ${NSA_IP} -X ${MD5_PW}
log_test $? 0 "MD5: VRF: Single address config in default VRF and VRF, conn in VRF"
log_start
run_cmd nettest -s -I ${VRF} -M ${MD5_PW} -m ${NSB_IP} &
run_cmd nettest -s -M ${MD5_WRONG_PW} -m ${NSB_IP} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsc nettest -r ${NSA_IP} -X ${MD5_WRONG_PW}
log_test $? 0 "MD5: VRF: Single address config in default VRF and VRF, conn in default VRF"
@@ -1020,7 +1022,7 @@ ipv4_tcp_md5()
show_hint "Should timeout since client in default VRF uses VRF password"
run_cmd nettest -s -I ${VRF} -M ${MD5_PW} -m ${NSB_IP} &
run_cmd nettest -s -M ${MD5_WRONG_PW} -m ${NSB_IP} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsc nettest -r ${NSA_IP} -X ${MD5_PW}
log_test $? 2 "MD5: VRF: Single address config in default VRF and VRF, conn in default VRF with VRF pw"
@@ -1028,21 +1030,21 @@ ipv4_tcp_md5()
show_hint "Should timeout since client in VRF uses default VRF password"
run_cmd nettest -s -I ${VRF} -M ${MD5_PW} -m ${NSB_IP} &
run_cmd nettest -s -M ${MD5_WRONG_PW} -m ${NSB_IP} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -r ${NSA_IP} -X ${MD5_WRONG_PW}
log_test $? 2 "MD5: VRF: Single address config in default VRF and VRF, conn in VRF with default VRF pw"
log_start
run_cmd nettest -s -I ${VRF} -M ${MD5_PW} -m ${NS_NET} &
run_cmd nettest -s -M ${MD5_WRONG_PW} -m ${NS_NET} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -r ${NSA_IP} -X ${MD5_PW}
log_test $? 0 "MD5: VRF: Prefix config in default VRF and VRF, conn in VRF"
log_start
run_cmd nettest -s -I ${VRF} -M ${MD5_PW} -m ${NS_NET} &
run_cmd nettest -s -M ${MD5_WRONG_PW} -m ${NS_NET} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsc nettest -r ${NSA_IP} -X ${MD5_WRONG_PW}
log_test $? 0 "MD5: VRF: Prefix config in default VRF and VRF, conn in default VRF"
@@ -1050,7 +1052,7 @@ ipv4_tcp_md5()
show_hint "Should timeout since client in default VRF uses VRF password"
run_cmd nettest -s -I ${VRF} -M ${MD5_PW} -m ${NS_NET} &
run_cmd nettest -s -M ${MD5_WRONG_PW} -m ${NS_NET} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsc nettest -r ${NSA_IP} -X ${MD5_PW}
log_test $? 2 "MD5: VRF: Prefix config in default VRF and VRF, conn in default VRF with VRF pw"
@@ -1058,7 +1060,7 @@ ipv4_tcp_md5()
show_hint "Should timeout since client in VRF uses default VRF password"
run_cmd nettest -s -I ${VRF} -M ${MD5_PW} -m ${NS_NET} &
run_cmd nettest -s -M ${MD5_WRONG_PW} -m ${NS_NET} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -r ${NSA_IP} -X ${MD5_WRONG_PW}
log_test $? 2 "MD5: VRF: Prefix config in default VRF and VRF, conn in VRF with default VRF pw"
@@ -1082,14 +1084,14 @@ test_ipv4_md5_vrf__vrf_server__no_bind_ifindex()
log_start
show_hint "Simulates applications using VRF without TCP_MD5SIG_FLAG_IFINDEX"
run_cmd nettest -s -I ${VRF} -M ${MD5_PW} -m ${NS_NET} --no-bind-key-ifindex &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -r ${NSA_IP} -X ${MD5_PW}
log_test $? 0 "MD5: VRF: VRF-bound server, unbound key accepts connection"
log_start
show_hint "Binding both the socket and the key is not required but it works"
run_cmd nettest -s -I ${VRF} -M ${MD5_PW} -m ${NS_NET} --force-bind-key-ifindex &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -r ${NSA_IP} -X ${MD5_PW}
log_test $? 0 "MD5: VRF: VRF-bound server, bound key accepts connection"
}
@@ -1103,25 +1105,25 @@ test_ipv4_md5_vrf__global_server__bind_ifindex0()
log_start
run_cmd nettest -s -M ${MD5_PW} -m ${NS_NET} --force-bind-key-ifindex &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -r ${NSA_IP} -X ${MD5_PW}
log_test $? 2 "MD5: VRF: Global server, Key bound to ifindex=0 rejects VRF connection"
log_start
run_cmd nettest -s -M ${MD5_PW} -m ${NS_NET} --force-bind-key-ifindex &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsc nettest -r ${NSA_IP} -X ${MD5_PW}
log_test $? 0 "MD5: VRF: Global server, key bound to ifindex=0 accepts non-VRF connection"
log_start
run_cmd nettest -s -M ${MD5_PW} -m ${NS_NET} --no-bind-key-ifindex &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -r ${NSA_IP} -X ${MD5_PW}
log_test $? 0 "MD5: VRF: Global server, key not bound to ifindex accepts VRF connection"
log_start
run_cmd nettest -s -M ${MD5_PW} -m ${NS_NET} --no-bind-key-ifindex &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsc nettest -r ${NSA_IP} -X ${MD5_PW}
log_test $? 0 "MD5: VRF: Global server, key not bound to ifindex accepts non-VRF connection"
@@ -1193,7 +1195,7 @@ ipv4_tcp_novrf()
do
log_start
run_cmd nettest -s &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -r ${a}
log_test_addr ${a} $? 0 "Global server"
done
@@ -1201,7 +1203,7 @@ ipv4_tcp_novrf()
a=${NSA_IP}
log_start
run_cmd nettest -s -I ${NSA_DEV} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -r ${a}
log_test_addr ${a} $? 0 "Device server"
@@ -1221,13 +1223,13 @@ ipv4_tcp_novrf()
do
log_start
run_cmd_nsb nettest -s &
- sleep 1
+ wait_local_port_listen ${NSB} 12345 tcp
run_cmd nettest -r ${a} -0 ${NSA_IP}
log_test_addr ${a} $? 0 "Client"
log_start
run_cmd_nsb nettest -s &
- sleep 1
+ wait_local_port_listen ${NSB} 12345 tcp
run_cmd nettest -r ${a} -d ${NSA_DEV}
log_test_addr ${a} $? 0 "Client, device bind"
@@ -1249,7 +1251,7 @@ ipv4_tcp_novrf()
do
log_start
run_cmd nettest -s &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd nettest -r ${a} -0 ${a} -1 ${a}
log_test_addr ${a} $? 0 "Global server, local connection"
done
@@ -1257,7 +1259,7 @@ ipv4_tcp_novrf()
a=${NSA_IP}
log_start
run_cmd nettest -s -I ${NSA_DEV} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd nettest -r ${a} -0 ${a}
log_test_addr ${a} $? 0 "Device server, unbound client, local connection"
@@ -1266,7 +1268,7 @@ ipv4_tcp_novrf()
log_start
show_hint "Should fail 'Connection refused' since addresses on loopback are out of device scope"
run_cmd nettest -s -I ${NSA_DEV} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd nettest -r ${a}
log_test_addr ${a} $? 1 "Device server, unbound client, local connection"
done
@@ -1274,7 +1276,7 @@ ipv4_tcp_novrf()
a=${NSA_IP}
log_start
run_cmd nettest -s &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd nettest -r ${a} -0 ${a} -d ${NSA_DEV}
log_test_addr ${a} $? 0 "Global server, device client, local connection"
@@ -1283,7 +1285,7 @@ ipv4_tcp_novrf()
log_start
show_hint "Should fail 'No route to host' since addresses on loopback are out of device scope"
run_cmd nettest -s &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd nettest -r ${a} -d ${NSA_DEV}
log_test_addr ${a} $? 1 "Global server, device client, local connection"
done
@@ -1291,7 +1293,7 @@ ipv4_tcp_novrf()
a=${NSA_IP}
log_start
run_cmd nettest -s -I ${NSA_DEV} -3 ${NSA_DEV} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd nettest -d ${NSA_DEV} -r ${a} -0 ${a}
log_test_addr ${a} $? 0 "Device server, device client, local connection"
@@ -1323,19 +1325,19 @@ ipv4_tcp_vrf()
log_start
show_hint "Should fail 'Connection refused' since global server with VRF is disabled"
run_cmd nettest -s &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -r ${a}
log_test_addr ${a} $? 1 "Global server"
log_start
run_cmd nettest -s -I ${VRF} -3 ${VRF} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -r ${a}
log_test_addr ${a} $? 0 "VRF server"
log_start
run_cmd nettest -s -I ${NSA_DEV} -3 ${NSA_DEV} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -r ${a}
log_test_addr ${a} $? 0 "Device server"
@@ -1352,7 +1354,7 @@ ipv4_tcp_vrf()
log_start
show_hint "Should fail 'Connection refused' since global server with VRF is disabled"
run_cmd nettest -s &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd nettest -r ${a} -d ${NSA_DEV}
log_test_addr ${a} $? 1 "Global server, local connection"
@@ -1374,14 +1376,14 @@ ipv4_tcp_vrf()
log_start
show_hint "client socket should be bound to VRF"
run_cmd nettest -s -3 ${VRF} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -r ${a}
log_test_addr ${a} $? 0 "Global server"
log_start
show_hint "client socket should be bound to VRF"
run_cmd nettest -s -I ${VRF} -3 ${VRF} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -r ${a}
log_test_addr ${a} $? 0 "VRF server"
@@ -1396,7 +1398,7 @@ ipv4_tcp_vrf()
log_start
show_hint "client socket should be bound to device"
run_cmd nettest -s -I ${NSA_DEV} -3 ${NSA_DEV} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -r ${a}
log_test_addr ${a} $? 0 "Device server"
@@ -1406,7 +1408,7 @@ ipv4_tcp_vrf()
log_start
show_hint "Should fail 'Connection refused' since client is not bound to VRF"
run_cmd nettest -s -I ${VRF} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd nettest -r ${a}
log_test_addr ${a} $? 1 "Global server, local connection"
done
@@ -1418,13 +1420,13 @@ ipv4_tcp_vrf()
do
log_start
run_cmd_nsb nettest -s &
- sleep 1
+ wait_local_port_listen ${NSB} 12345 tcp
run_cmd nettest -r ${a} -d ${VRF}
log_test_addr ${a} $? 0 "Client, VRF bind"
log_start
run_cmd_nsb nettest -s &
- sleep 1
+ wait_local_port_listen ${NSB} 12345 tcp
run_cmd nettest -r ${a} -d ${NSA_DEV}
log_test_addr ${a} $? 0 "Client, device bind"
@@ -1443,7 +1445,7 @@ ipv4_tcp_vrf()
do
log_start
run_cmd nettest -s -I ${VRF} -3 ${VRF} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd nettest -r ${a} -d ${VRF} -0 ${a}
log_test_addr ${a} $? 0 "VRF server, VRF client, local connection"
done
@@ -1451,26 +1453,26 @@ ipv4_tcp_vrf()
a=${NSA_IP}
log_start
run_cmd nettest -s -I ${VRF} -3 ${VRF} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd nettest -r ${a} -d ${NSA_DEV} -0 ${a}
log_test_addr ${a} $? 0 "VRF server, device client, local connection"
log_start
show_hint "Should fail 'No route to host' since client is out of VRF scope"
run_cmd nettest -s -I ${VRF} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd nettest -r ${a}
log_test_addr ${a} $? 1 "VRF server, unbound client, local connection"
log_start
run_cmd nettest -s -I ${NSA_DEV} -3 ${NSA_DEV} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd nettest -r ${a} -d ${VRF} -0 ${a}
log_test_addr ${a} $? 0 "Device server, VRF client, local connection"
log_start
run_cmd nettest -s -I ${NSA_DEV} -3 ${NSA_DEV} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd nettest -r ${a} -d ${NSA_DEV} -0 ${a}
log_test_addr ${a} $? 0 "Device server, device client, local connection"
}
@@ -1509,7 +1511,7 @@ ipv4_udp_novrf()
do
log_start
run_cmd nettest -D -s -3 ${NSA_DEV} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd_nsb nettest -D -r ${a}
log_test_addr ${a} $? 0 "Global server"
@@ -1522,7 +1524,7 @@ ipv4_udp_novrf()
a=${NSA_IP}
log_start
run_cmd nettest -D -I ${NSA_DEV} -s -3 ${NSA_DEV} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd_nsb nettest -D -r ${a}
log_test_addr ${a} $? 0 "Device server"
@@ -1533,31 +1535,31 @@ ipv4_udp_novrf()
do
log_start
run_cmd_nsb nettest -D -s &
- sleep 1
+ wait_local_port_listen ${NSB} 12345 udp
run_cmd nettest -D -r ${a} -0 ${NSA_IP}
log_test_addr ${a} $? 0 "Client"
log_start
run_cmd_nsb nettest -D -s &
- sleep 1
+ wait_local_port_listen ${NSB} 12345 udp
run_cmd nettest -D -r ${a} -d ${NSA_DEV} -0 ${NSA_IP}
log_test_addr ${a} $? 0 "Client, device bind"
log_start
run_cmd_nsb nettest -D -s &
- sleep 1
+ wait_local_port_listen ${NSB} 12345 udp
run_cmd nettest -D -r ${a} -d ${NSA_DEV} -C -0 ${NSA_IP}
log_test_addr ${a} $? 0 "Client, device send via cmsg"
log_start
run_cmd_nsb nettest -D -s &
- sleep 1
+ wait_local_port_listen ${NSB} 12345 udp
run_cmd nettest -D -r ${a} -d ${NSA_DEV} -S -0 ${NSA_IP}
log_test_addr ${a} $? 0 "Client, device bind via IP_UNICAST_IF"
log_start
run_cmd_nsb nettest -D -s &
- sleep 1
+ wait_local_port_listen ${NSB} 12345 udp
run_cmd nettest -D -r ${a} -d ${NSA_DEV} -S -0 ${NSA_IP} -U
log_test_addr ${a} $? 0 "Client, device bind via IP_UNICAST_IF, with connect()"
@@ -1580,7 +1582,7 @@ ipv4_udp_novrf()
do
log_start
run_cmd nettest -D -s &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd nettest -D -r ${a} -0 ${a} -1 ${a}
log_test_addr ${a} $? 0 "Global server, local connection"
done
@@ -1588,7 +1590,7 @@ ipv4_udp_novrf()
a=${NSA_IP}
log_start
run_cmd nettest -s -D -I ${NSA_DEV} -3 ${NSA_DEV} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd nettest -D -r ${a}
log_test_addr ${a} $? 0 "Device server, unbound client, local connection"
@@ -1597,7 +1599,7 @@ ipv4_udp_novrf()
log_start
show_hint "Should fail 'Connection refused' since address is out of device scope"
run_cmd nettest -s -D -I ${NSA_DEV} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd nettest -D -r ${a}
log_test_addr ${a} $? 1 "Device server, unbound client, local connection"
done
@@ -1605,25 +1607,25 @@ ipv4_udp_novrf()
a=${NSA_IP}
log_start
run_cmd nettest -s -D &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd nettest -D -d ${NSA_DEV} -r ${a}
log_test_addr ${a} $? 0 "Global server, device client, local connection"
log_start
run_cmd nettest -s -D &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd nettest -D -d ${NSA_DEV} -C -r ${a}
log_test_addr ${a} $? 0 "Global server, device send via cmsg, local connection"
log_start
run_cmd nettest -s -D &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd nettest -D -d ${NSA_DEV} -S -r ${a}
log_test_addr ${a} $? 0 "Global server, device client via IP_UNICAST_IF, local connection"
log_start
run_cmd nettest -s -D &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd nettest -D -d ${NSA_DEV} -S -r ${a} -U
log_test_addr ${a} $? 0 "Global server, device client via IP_UNICAST_IF, local connection, with connect()"
@@ -1636,28 +1638,28 @@ ipv4_udp_novrf()
log_start
show_hint "Should fail since addresses on loopback are out of device scope"
run_cmd nettest -D -s &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd nettest -D -r ${a} -d ${NSA_DEV}
log_test_addr ${a} $? 2 "Global server, device client, local connection"
log_start
show_hint "Should fail since addresses on loopback are out of device scope"
run_cmd nettest -D -s &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd nettest -D -r ${a} -d ${NSA_DEV} -C
log_test_addr ${a} $? 1 "Global server, device send via cmsg, local connection"
log_start
show_hint "Should fail since addresses on loopback are out of device scope"
run_cmd nettest -D -s &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd nettest -D -r ${a} -d ${NSA_DEV} -S
log_test_addr ${a} $? 1 "Global server, device client via IP_UNICAST_IF, local connection"
log_start
show_hint "Should fail since addresses on loopback are out of device scope"
run_cmd nettest -D -s &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd nettest -D -r ${a} -d ${NSA_DEV} -S -U
log_test_addr ${a} $? 1 "Global server, device client via IP_UNICAST_IF, local connection, with connect()"
@@ -1667,7 +1669,7 @@ ipv4_udp_novrf()
a=${NSA_IP}
log_start
run_cmd nettest -D -s -I ${NSA_DEV} -3 ${NSA_DEV} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd nettest -D -d ${NSA_DEV} -r ${a} -0 ${a}
log_test_addr ${a} $? 0 "Device server, device client, local conn"
@@ -1709,19 +1711,19 @@ ipv4_udp_vrf()
log_start
show_hint "Fails because ingress is in a VRF and global server is disabled"
run_cmd nettest -D -s &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd_nsb nettest -D -r ${a}
log_test_addr ${a} $? 1 "Global server"
log_start
run_cmd nettest -D -I ${VRF} -s -3 ${NSA_DEV} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd_nsb nettest -D -r ${a}
log_test_addr ${a} $? 0 "VRF server"
log_start
run_cmd nettest -D -I ${NSA_DEV} -s -3 ${NSA_DEV} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd_nsb nettest -D -r ${a}
log_test_addr ${a} $? 0 "Enslaved device server"
@@ -1733,7 +1735,7 @@ ipv4_udp_vrf()
log_start
show_hint "Should fail 'Connection refused' since global server is out of scope"
run_cmd nettest -D -s &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd nettest -D -d ${VRF} -r ${a}
log_test_addr ${a} $? 1 "Global server, VRF client, local connection"
done
@@ -1741,26 +1743,26 @@ ipv4_udp_vrf()
a=${NSA_IP}
log_start
run_cmd nettest -s -D -I ${VRF} -3 ${NSA_DEV} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd nettest -D -d ${VRF} -r ${a}
log_test_addr ${a} $? 0 "VRF server, VRF client, local conn"
log_start
run_cmd nettest -s -D -I ${VRF} -3 ${NSA_DEV} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd nettest -D -d ${NSA_DEV} -r ${a}
log_test_addr ${a} $? 0 "VRF server, enslaved device client, local connection"
a=${NSA_IP}
log_start
run_cmd nettest -s -D -I ${NSA_DEV} -3 ${NSA_DEV} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd nettest -D -d ${VRF} -r ${a}
log_test_addr ${a} $? 0 "Enslaved device server, VRF client, local conn"
log_start
run_cmd nettest -s -D -I ${NSA_DEV} -3 ${NSA_DEV} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd nettest -D -d ${NSA_DEV} -r ${a}
log_test_addr ${a} $? 0 "Enslaved device server, device client, local conn"
@@ -1775,19 +1777,19 @@ ipv4_udp_vrf()
do
log_start
run_cmd nettest -D -s -3 ${NSA_DEV} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd_nsb nettest -D -r ${a}
log_test_addr ${a} $? 0 "Global server"
log_start
run_cmd nettest -D -I ${VRF} -s -3 ${NSA_DEV} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd_nsb nettest -D -r ${a}
log_test_addr ${a} $? 0 "VRF server"
log_start
run_cmd nettest -D -I ${NSA_DEV} -s -3 ${NSA_DEV} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd_nsb nettest -D -r ${a}
log_test_addr ${a} $? 0 "Enslaved device server"
@@ -1802,13 +1804,13 @@ ipv4_udp_vrf()
#
log_start
run_cmd_nsb nettest -D -s &
- sleep 1
+ wait_local_port_listen ${NSB} 12345 udp
run_cmd nettest -d ${VRF} -D -r ${NSB_IP} -1 ${NSA_IP}
log_test $? 0 "VRF client"
log_start
run_cmd_nsb nettest -D -s &
- sleep 1
+ wait_local_port_listen ${NSB} 12345 udp
run_cmd nettest -d ${NSA_DEV} -D -r ${NSB_IP} -1 ${NSA_IP}
log_test $? 0 "Enslaved device client"
@@ -1829,31 +1831,31 @@ ipv4_udp_vrf()
a=${NSA_IP}
log_start
run_cmd nettest -D -s -3 ${NSA_DEV} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd nettest -D -d ${VRF} -r ${a}
log_test_addr ${a} $? 0 "Global server, VRF client, local conn"
log_start
run_cmd nettest -s -D -I ${VRF} -3 ${NSA_DEV} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd nettest -D -d ${VRF} -r ${a}
log_test_addr ${a} $? 0 "VRF server, VRF client, local conn"
log_start
run_cmd nettest -s -D -I ${VRF} -3 ${NSA_DEV} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd nettest -D -d ${NSA_DEV} -r ${a}
log_test_addr ${a} $? 0 "VRF server, device client, local conn"
log_start
run_cmd nettest -s -D -I ${NSA_DEV} -3 ${NSA_DEV} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd nettest -D -d ${VRF} -r ${a}
log_test_addr ${a} $? 0 "Enslaved device server, VRF client, local conn"
log_start
run_cmd nettest -s -D -I ${NSA_DEV} -3 ${NSA_DEV} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd nettest -D -d ${NSA_DEV} -r ${a}
log_test_addr ${a} $? 0 "Enslaved device server, device client, local conn"
@@ -1861,7 +1863,7 @@ ipv4_udp_vrf()
do
log_start
run_cmd nettest -D -s -3 ${VRF} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd nettest -D -d ${VRF} -r ${a}
log_test_addr ${a} $? 0 "Global server, VRF client, local conn"
done
@@ -1870,7 +1872,7 @@ ipv4_udp_vrf()
do
log_start
run_cmd nettest -s -D -I ${VRF} -3 ${VRF} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd nettest -D -d ${VRF} -r ${a}
log_test_addr ${a} $? 0 "VRF server, VRF client, local conn"
done
@@ -2093,7 +2095,7 @@ ipv4_rt()
do
log_start
run_cmd nettest ${varg} -s &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest ${varg} -r ${a} &
sleep 3
run_cmd ip link del ${VRF}
@@ -2107,7 +2109,7 @@ ipv4_rt()
do
log_start
run_cmd nettest ${varg} -s -I ${VRF} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest ${varg} -r ${a} &
sleep 3
run_cmd ip link del ${VRF}
@@ -2120,7 +2122,7 @@ ipv4_rt()
a=${NSA_IP}
log_start
run_cmd nettest ${varg} -s -I ${NSA_DEV} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest ${varg} -r ${a} &
sleep 3
run_cmd ip link del ${VRF}
@@ -2134,7 +2136,7 @@ ipv4_rt()
#
log_start
run_cmd_nsb nettest ${varg} -s &
- sleep 1
+ wait_local_port_listen ${NSB} 12345 tcp
run_cmd nettest ${varg} -d ${VRF} -r ${NSB_IP} &
sleep 3
run_cmd ip link del ${VRF}
@@ -2145,7 +2147,7 @@ ipv4_rt()
log_start
run_cmd_nsb nettest ${varg} -s &
- sleep 1
+ wait_local_port_listen ${NSB} 12345 tcp
run_cmd nettest ${varg} -d ${NSA_DEV} -r ${NSB_IP} &
sleep 3
run_cmd ip link del ${VRF}
@@ -2161,7 +2163,7 @@ ipv4_rt()
do
log_start
run_cmd nettest ${varg} -s &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd nettest ${varg} -d ${VRF} -r ${a} &
sleep 3
run_cmd ip link del ${VRF}
@@ -2175,7 +2177,7 @@ ipv4_rt()
do
log_start
run_cmd nettest ${varg} -I ${VRF} -s &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd nettest ${varg} -d ${VRF} -r ${a} &
sleep 3
run_cmd ip link del ${VRF}
@@ -2189,7 +2191,7 @@ ipv4_rt()
log_start
run_cmd nettest ${varg} -s &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd nettest ${varg} -d ${NSA_DEV} -r ${a} &
sleep 3
run_cmd ip link del ${VRF}
@@ -2200,7 +2202,7 @@ ipv4_rt()
log_start
run_cmd nettest ${varg} -I ${VRF} -s &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd nettest ${varg} -d ${NSA_DEV} -r ${a} &
sleep 3
run_cmd ip link del ${VRF}
@@ -2211,7 +2213,7 @@ ipv4_rt()
log_start
run_cmd nettest ${varg} -I ${NSA_DEV} -s &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd nettest ${varg} -d ${NSA_DEV} -r ${a} &
sleep 3
run_cmd ip link del ${VRF}
@@ -2561,7 +2563,7 @@ ipv6_tcp_md5_novrf()
# basic use case
log_start
run_cmd nettest -6 -s -M ${MD5_PW} -m ${NSB_IP6} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -6 -r ${NSA_IP6} -X ${MD5_PW}
log_test $? 0 "MD5: Single address config"
@@ -2569,7 +2571,7 @@ ipv6_tcp_md5_novrf()
log_start
show_hint "Should timeout due to MD5 mismatch"
run_cmd nettest -6 -s &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -6 -r ${NSA_IP6} -X ${MD5_PW}
log_test $? 2 "MD5: Server no config, client uses password"
@@ -2577,7 +2579,7 @@ ipv6_tcp_md5_novrf()
log_start
show_hint "Should timeout since client uses wrong password"
run_cmd nettest -6 -s -M ${MD5_PW} -m ${NSB_IP6} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -6 -r ${NSA_IP6} -X ${MD5_WRONG_PW}
log_test $? 2 "MD5: Client uses wrong password"
@@ -2585,7 +2587,7 @@ ipv6_tcp_md5_novrf()
log_start
show_hint "Should timeout due to MD5 mismatch"
run_cmd nettest -6 -s -M ${MD5_PW} -m ${NSB_LO_IP6} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -6 -r ${NSA_IP6} -X ${MD5_PW}
log_test $? 2 "MD5: Client address does not match address configured with password"
@@ -2596,7 +2598,7 @@ ipv6_tcp_md5_novrf()
# client in prefix
log_start
run_cmd nettest -6 -s -M ${MD5_PW} -m ${NS_NET6} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -6 -r ${NSA_IP6} -X ${MD5_PW}
log_test $? 0 "MD5: Prefix config"
@@ -2604,7 +2606,7 @@ ipv6_tcp_md5_novrf()
log_start
show_hint "Should timeout since client uses wrong password"
run_cmd nettest -6 -s -M ${MD5_PW} -m ${NS_NET6} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -6 -r ${NSA_IP6} -X ${MD5_WRONG_PW}
log_test $? 2 "MD5: Prefix config, client uses wrong password"
@@ -2612,7 +2614,7 @@ ipv6_tcp_md5_novrf()
log_start
show_hint "Should timeout due to MD5 mismatch"
run_cmd nettest -6 -s -M ${MD5_PW} -m ${NS_NET6} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -6 -c ${NSB_LO_IP6} -r ${NSA_IP6} -X ${MD5_PW}
log_test $? 2 "MD5: Prefix config, client address not in configured prefix"
}
@@ -2629,7 +2631,7 @@ ipv6_tcp_md5()
# basic use case
log_start
run_cmd nettest -6 -s -I ${VRF} -M ${MD5_PW} -m ${NSB_IP6} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -6 -r ${NSA_IP6} -X ${MD5_PW}
log_test $? 0 "MD5: VRF: Single address config"
@@ -2637,7 +2639,7 @@ ipv6_tcp_md5()
log_start
show_hint "Should timeout since server does not have MD5 auth"
run_cmd nettest -6 -s -I ${VRF} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -6 -r ${NSA_IP6} -X ${MD5_PW}
log_test $? 2 "MD5: VRF: Server no config, client uses password"
@@ -2645,7 +2647,7 @@ ipv6_tcp_md5()
log_start
show_hint "Should timeout since client uses wrong password"
run_cmd nettest -6 -s -I ${VRF} -M ${MD5_PW} -m ${NSB_IP6} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -6 -r ${NSA_IP6} -X ${MD5_WRONG_PW}
log_test $? 2 "MD5: VRF: Client uses wrong password"
@@ -2653,7 +2655,7 @@ ipv6_tcp_md5()
log_start
show_hint "Should timeout since server config differs from client"
run_cmd nettest -6 -s -I ${VRF} -M ${MD5_PW} -m ${NSB_LO_IP6} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -6 -r ${NSA_IP6} -X ${MD5_PW}
log_test $? 2 "MD5: VRF: Client address does not match address configured with password"
@@ -2664,7 +2666,7 @@ ipv6_tcp_md5()
# client in prefix
log_start
run_cmd nettest -6 -s -I ${VRF} -M ${MD5_PW} -m ${NS_NET6} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -6 -r ${NSA_IP6} -X ${MD5_PW}
log_test $? 0 "MD5: VRF: Prefix config"
@@ -2672,7 +2674,7 @@ ipv6_tcp_md5()
log_start
show_hint "Should timeout since client uses wrong password"
run_cmd nettest -6 -s -I ${VRF} -M ${MD5_PW} -m ${NS_NET6} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -6 -r ${NSA_IP6} -X ${MD5_WRONG_PW}
log_test $? 2 "MD5: VRF: Prefix config, client uses wrong password"
@@ -2680,7 +2682,7 @@ ipv6_tcp_md5()
log_start
show_hint "Should timeout since client address is outside of prefix"
run_cmd nettest -6 -s -I ${VRF} -M ${MD5_PW} -m ${NS_NET6} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -6 -c ${NSB_LO_IP6} -r ${NSA_IP6} -X ${MD5_PW}
log_test $? 2 "MD5: VRF: Prefix config, client address not in configured prefix"
@@ -2691,14 +2693,14 @@ ipv6_tcp_md5()
log_start
run_cmd nettest -6 -s -I ${VRF} -M ${MD5_PW} -m ${NSB_IP6} &
run_cmd nettest -6 -s -M ${MD5_WRONG_PW} -m ${NSB_IP6} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -6 -r ${NSA_IP6} -X ${MD5_PW}
log_test $? 0 "MD5: VRF: Single address config in default VRF and VRF, conn in VRF"
log_start
run_cmd nettest -6 -s -I ${VRF} -M ${MD5_PW} -m ${NSB_IP6} &
run_cmd nettest -6 -s -M ${MD5_WRONG_PW} -m ${NSB_IP6} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsc nettest -6 -r ${NSA_IP6} -X ${MD5_WRONG_PW}
log_test $? 0 "MD5: VRF: Single address config in default VRF and VRF, conn in default VRF"
@@ -2706,7 +2708,7 @@ ipv6_tcp_md5()
show_hint "Should timeout since client in default VRF uses VRF password"
run_cmd nettest -6 -s -I ${VRF} -M ${MD5_PW} -m ${NSB_IP6} &
run_cmd nettest -6 -s -M ${MD5_WRONG_PW} -m ${NSB_IP6} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsc nettest -6 -r ${NSA_IP6} -X ${MD5_PW}
log_test $? 2 "MD5: VRF: Single address config in default VRF and VRF, conn in default VRF with VRF pw"
@@ -2714,21 +2716,21 @@ ipv6_tcp_md5()
show_hint "Should timeout since client in VRF uses default VRF password"
run_cmd nettest -6 -s -I ${VRF} -M ${MD5_PW} -m ${NSB_IP6} &
run_cmd nettest -6 -s -M ${MD5_WRONG_PW} -m ${NSB_IP6} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -6 -r ${NSA_IP6} -X ${MD5_WRONG_PW}
log_test $? 2 "MD5: VRF: Single address config in default VRF and VRF, conn in VRF with default VRF pw"
log_start
run_cmd nettest -6 -s -I ${VRF} -M ${MD5_PW} -m ${NS_NET6} &
run_cmd nettest -6 -s -M ${MD5_WRONG_PW} -m ${NS_NET6} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -6 -r ${NSA_IP6} -X ${MD5_PW}
log_test $? 0 "MD5: VRF: Prefix config in default VRF and VRF, conn in VRF"
log_start
run_cmd nettest -6 -s -I ${VRF} -M ${MD5_PW} -m ${NS_NET6} &
run_cmd nettest -6 -s -M ${MD5_WRONG_PW} -m ${NS_NET6} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsc nettest -6 -r ${NSA_IP6} -X ${MD5_WRONG_PW}
log_test $? 0 "MD5: VRF: Prefix config in default VRF and VRF, conn in default VRF"
@@ -2736,7 +2738,7 @@ ipv6_tcp_md5()
show_hint "Should timeout since client in default VRF uses VRF password"
run_cmd nettest -6 -s -I ${VRF} -M ${MD5_PW} -m ${NS_NET6} &
run_cmd nettest -6 -s -M ${MD5_WRONG_PW} -m ${NS_NET6} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsc nettest -6 -r ${NSA_IP6} -X ${MD5_PW}
log_test $? 2 "MD5: VRF: Prefix config in default VRF and VRF, conn in default VRF with VRF pw"
@@ -2744,7 +2746,7 @@ ipv6_tcp_md5()
show_hint "Should timeout since client in VRF uses default VRF password"
run_cmd nettest -6 -s -I ${VRF} -M ${MD5_PW} -m ${NS_NET6} &
run_cmd nettest -6 -s -M ${MD5_WRONG_PW} -m ${NS_NET6} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -6 -r ${NSA_IP6} -X ${MD5_WRONG_PW}
log_test $? 2 "MD5: VRF: Prefix config in default VRF and VRF, conn in VRF with default VRF pw"
@@ -2772,7 +2774,7 @@ ipv6_tcp_novrf()
do
log_start
run_cmd nettest -6 -s &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -6 -r ${a}
log_test_addr ${a} $? 0 "Global server"
done
@@ -2793,7 +2795,7 @@ ipv6_tcp_novrf()
do
log_start
run_cmd_nsb nettest -6 -s &
- sleep 1
+ wait_local_port_listen ${NSB} 12345 tcp
run_cmd nettest -6 -r ${a}
log_test_addr ${a} $? 0 "Client"
done
@@ -2802,7 +2804,7 @@ ipv6_tcp_novrf()
do
log_start
run_cmd_nsb nettest -6 -s &
- sleep 1
+ wait_local_port_listen ${NSB} 12345 tcp
run_cmd nettest -6 -r ${a} -d ${NSA_DEV}
log_test_addr ${a} $? 0 "Client, device bind"
done
@@ -2822,7 +2824,7 @@ ipv6_tcp_novrf()
do
log_start
run_cmd nettest -6 -s &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd nettest -6 -r ${a}
log_test_addr ${a} $? 0 "Global server, local connection"
done
@@ -2830,7 +2832,7 @@ ipv6_tcp_novrf()
a=${NSA_IP6}
log_start
run_cmd nettest -6 -s -I ${NSA_DEV} -3 ${NSA_DEV} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd nettest -6 -r ${a} -0 ${a}
log_test_addr ${a} $? 0 "Device server, unbound client, local connection"
@@ -2839,7 +2841,7 @@ ipv6_tcp_novrf()
log_start
show_hint "Should fail 'Connection refused' since addresses on loopback are out of device scope"
run_cmd nettest -6 -s -I ${NSA_DEV} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd nettest -6 -r ${a}
log_test_addr ${a} $? 1 "Device server, unbound client, local connection"
done
@@ -2847,7 +2849,7 @@ ipv6_tcp_novrf()
a=${NSA_IP6}
log_start
run_cmd nettest -6 -s &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd nettest -6 -r ${a} -d ${NSA_DEV} -0 ${a}
log_test_addr ${a} $? 0 "Global server, device client, local connection"
@@ -2856,7 +2858,7 @@ ipv6_tcp_novrf()
log_start
show_hint "Should fail 'Connection refused' since addresses on loopback are out of device scope"
run_cmd nettest -6 -s &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd nettest -6 -r ${a} -d ${NSA_DEV}
log_test_addr ${a} $? 1 "Global server, device client, local connection"
done
@@ -2865,7 +2867,7 @@ ipv6_tcp_novrf()
do
log_start
run_cmd nettest -6 -s -I ${NSA_DEV} -3 ${NSA_DEV} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd nettest -6 -d ${NSA_DEV} -r ${a}
log_test_addr ${a} $? 0 "Device server, device client, local conn"
done
@@ -2898,7 +2900,7 @@ ipv6_tcp_vrf()
log_start
show_hint "Should fail 'Connection refused' since global server with VRF is disabled"
run_cmd nettest -6 -s &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -6 -r ${a}
log_test_addr ${a} $? 1 "Global server"
done
@@ -2907,7 +2909,7 @@ ipv6_tcp_vrf()
do
log_start
run_cmd nettest -6 -s -I ${VRF} -3 ${VRF} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -6 -r ${a}
log_test_addr ${a} $? 0 "VRF server"
done
@@ -2916,7 +2918,7 @@ ipv6_tcp_vrf()
a=${NSA_LINKIP6}%${NSB_DEV}
log_start
run_cmd nettest -6 -s -I ${VRF} -3 ${NSA_DEV} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -6 -r ${a}
log_test_addr ${a} $? 0 "VRF server"
@@ -2924,7 +2926,7 @@ ipv6_tcp_vrf()
do
log_start
run_cmd nettest -6 -s -I ${NSA_DEV} -3 ${NSA_DEV} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -6 -r ${a}
log_test_addr ${a} $? 0 "Device server"
done
@@ -2943,7 +2945,7 @@ ipv6_tcp_vrf()
log_start
show_hint "Should fail 'Connection refused' since global server with VRF is disabled"
run_cmd nettest -6 -s &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd nettest -6 -r ${a} -d ${NSA_DEV}
log_test_addr ${a} $? 1 "Global server, local connection"
@@ -2964,7 +2966,7 @@ ipv6_tcp_vrf()
do
log_start
run_cmd nettest -6 -s -3 ${VRF} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -6 -r ${a}
log_test_addr ${a} $? 0 "Global server"
done
@@ -2973,7 +2975,7 @@ ipv6_tcp_vrf()
do
log_start
run_cmd nettest -6 -s -I ${VRF} -3 ${VRF} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -6 -r ${a}
log_test_addr ${a} $? 0 "VRF server"
done
@@ -2982,13 +2984,13 @@ ipv6_tcp_vrf()
a=${NSA_LINKIP6}%${NSB_DEV}
log_start
run_cmd nettest -6 -s -3 ${NSA_DEV} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -6 -r ${a}
log_test_addr ${a} $? 0 "Global server"
log_start
run_cmd nettest -6 -s -I ${VRF} -3 ${NSA_DEV} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -6 -r ${a}
log_test_addr ${a} $? 0 "VRF server"
@@ -2996,7 +2998,7 @@ ipv6_tcp_vrf()
do
log_start
run_cmd nettest -6 -s -I ${NSA_DEV} -3 ${NSA_DEV} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -6 -r ${a}
log_test_addr ${a} $? 0 "Device server"
done
@@ -3016,7 +3018,7 @@ ipv6_tcp_vrf()
log_start
show_hint "Fails 'Connection refused' since client is not in VRF"
run_cmd nettest -6 -s -I ${VRF} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd nettest -6 -r ${a}
log_test_addr ${a} $? 1 "Global server, local connection"
done
@@ -3029,7 +3031,7 @@ ipv6_tcp_vrf()
do
log_start
run_cmd_nsb nettest -6 -s &
- sleep 1
+ wait_local_port_listen ${NSB} 12345 tcp
run_cmd nettest -6 -r ${a} -d ${VRF}
log_test_addr ${a} $? 0 "Client, VRF bind"
done
@@ -3038,7 +3040,7 @@ ipv6_tcp_vrf()
log_start
show_hint "Fails since VRF device does not allow linklocal addresses"
run_cmd_nsb nettest -6 -s &
- sleep 1
+ wait_local_port_listen ${NSB} 12345 tcp
run_cmd nettest -6 -r ${a} -d ${VRF}
log_test_addr ${a} $? 1 "Client, VRF bind"
@@ -3046,7 +3048,7 @@ ipv6_tcp_vrf()
do
log_start
run_cmd_nsb nettest -6 -s &
- sleep 1
+ wait_local_port_listen ${NSB} 12345 tcp
run_cmd nettest -6 -r ${a} -d ${NSA_DEV}
log_test_addr ${a} $? 0 "Client, device bind"
done
@@ -3071,7 +3073,7 @@ ipv6_tcp_vrf()
do
log_start
run_cmd nettest -6 -s -I ${VRF} -3 ${VRF} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd nettest -6 -r ${a} -d ${VRF} -0 ${a}
log_test_addr ${a} $? 0 "VRF server, VRF client, local connection"
done
@@ -3079,7 +3081,7 @@ ipv6_tcp_vrf()
a=${NSA_IP6}
log_start
run_cmd nettest -6 -s -I ${VRF} -3 ${VRF} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd nettest -6 -r ${a} -d ${NSA_DEV} -0 ${a}
log_test_addr ${a} $? 0 "VRF server, device client, local connection"
@@ -3087,13 +3089,13 @@ ipv6_tcp_vrf()
log_start
show_hint "Should fail since unbound client is out of VRF scope"
run_cmd nettest -6 -s -I ${VRF} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd nettest -6 -r ${a}
log_test_addr ${a} $? 1 "VRF server, unbound client, local connection"
log_start
run_cmd nettest -6 -s -I ${NSA_DEV} -3 ${NSA_DEV} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd nettest -6 -r ${a} -d ${VRF} -0 ${a}
log_test_addr ${a} $? 0 "Device server, VRF client, local connection"
@@ -3101,7 +3103,7 @@ ipv6_tcp_vrf()
do
log_start
run_cmd nettest -6 -s -I ${NSA_DEV} -3 ${NSA_DEV} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd nettest -6 -r ${a} -d ${NSA_DEV} -0 ${a}
log_test_addr ${a} $? 0 "Device server, device client, local connection"
done
@@ -3141,13 +3143,13 @@ ipv6_udp_novrf()
do
log_start
run_cmd nettest -6 -D -s -3 ${NSA_DEV} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd_nsb nettest -6 -D -r ${a}
log_test_addr ${a} $? 0 "Global server"
log_start
run_cmd nettest -6 -D -I ${NSA_DEV} -s -3 ${NSA_DEV} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd_nsb nettest -6 -D -r ${a}
log_test_addr ${a} $? 0 "Device server"
done
@@ -3155,7 +3157,7 @@ ipv6_udp_novrf()
a=${NSA_LO_IP6}
log_start
run_cmd nettest -6 -D -s -3 ${NSA_DEV} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd_nsb nettest -6 -D -r ${a}
log_test_addr ${a} $? 0 "Global server"
@@ -3165,7 +3167,7 @@ ipv6_udp_novrf()
#log_start
#show_hint "Should fail since loopback address is out of scope"
#run_cmd nettest -6 -D -I ${NSA_DEV} -s -3 ${NSA_DEV} &
- #sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
#run_cmd_nsb nettest -6 -D -r ${a}
#log_test_addr ${a} $? 1 "Device server"
@@ -3185,25 +3187,25 @@ ipv6_udp_novrf()
do
log_start
run_cmd_nsb nettest -6 -D -s &
- sleep 1
+ wait_local_port_listen ${NSB} 12345 udp
run_cmd nettest -6 -D -r ${a} -0 ${NSA_IP6}
log_test_addr ${a} $? 0 "Client"
log_start
run_cmd_nsb nettest -6 -D -s &
- sleep 1
+ wait_local_port_listen ${NSB} 12345 udp
run_cmd nettest -6 -D -r ${a} -d ${NSA_DEV} -0 ${NSA_IP6}
log_test_addr ${a} $? 0 "Client, device bind"
log_start
run_cmd_nsb nettest -6 -D -s &
- sleep 1
+ wait_local_port_listen ${NSB} 12345 udp
run_cmd nettest -6 -D -r ${a} -d ${NSA_DEV} -C -0 ${NSA_IP6}
log_test_addr ${a} $? 0 "Client, device send via cmsg"
log_start
run_cmd_nsb nettest -6 -D -s &
- sleep 1
+ wait_local_port_listen ${NSB} 12345 udp
run_cmd nettest -6 -D -r ${a} -d ${NSA_DEV} -S -0 ${NSA_IP6}
log_test_addr ${a} $? 0 "Client, device bind via IPV6_UNICAST_IF"
@@ -3225,7 +3227,7 @@ ipv6_udp_novrf()
do
log_start
run_cmd nettest -6 -D -s &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd nettest -6 -D -r ${a} -0 ${a} -1 ${a}
log_test_addr ${a} $? 0 "Global server, local connection"
done
@@ -3233,7 +3235,7 @@ ipv6_udp_novrf()
a=${NSA_IP6}
log_start
run_cmd nettest -6 -s -D -I ${NSA_DEV} -3 ${NSA_DEV} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd nettest -6 -D -r ${a}
log_test_addr ${a} $? 0 "Device server, unbound client, local connection"
@@ -3242,7 +3244,7 @@ ipv6_udp_novrf()
log_start
show_hint "Should fail 'Connection refused' since address is out of device scope"
run_cmd nettest -6 -s -D -I ${NSA_DEV} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd nettest -6 -D -r ${a}
log_test_addr ${a} $? 1 "Device server, local connection"
done
@@ -3250,19 +3252,19 @@ ipv6_udp_novrf()
a=${NSA_IP6}
log_start
run_cmd nettest -6 -s -D &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd nettest -6 -D -d ${NSA_DEV} -r ${a}
log_test_addr ${a} $? 0 "Global server, device client, local connection"
log_start
run_cmd nettest -6 -s -D &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd nettest -6 -D -d ${NSA_DEV} -C -r ${a}
log_test_addr ${a} $? 0 "Global server, device send via cmsg, local connection"
log_start
run_cmd nettest -6 -s -D &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd nettest -6 -D -d ${NSA_DEV} -S -r ${a}
log_test_addr ${a} $? 0 "Global server, device client via IPV6_UNICAST_IF, local connection"
@@ -3271,28 +3273,28 @@ ipv6_udp_novrf()
log_start
show_hint "Should fail 'No route to host' since addresses on loopback are out of device scope"
run_cmd nettest -6 -D -s &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd nettest -6 -D -r ${a} -d ${NSA_DEV}
log_test_addr ${a} $? 1 "Global server, device client, local connection"
log_start
show_hint "Should fail 'No route to host' since addresses on loopback are out of device scope"
run_cmd nettest -6 -D -s &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd nettest -6 -D -r ${a} -d ${NSA_DEV} -C
log_test_addr ${a} $? 1 "Global server, device send via cmsg, local connection"
log_start
show_hint "Should fail 'No route to host' since addresses on loopback are out of device scope"
run_cmd nettest -6 -D -s &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd nettest -6 -D -r ${a} -d ${NSA_DEV} -S
log_test_addr ${a} $? 1 "Global server, device client via IP_UNICAST_IF, local connection"
log_start
show_hint "Should fail 'No route to host' since addresses on loopback are out of device scope"
run_cmd nettest -6 -D -s &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd nettest -6 -D -r ${a} -d ${NSA_DEV} -S -U
log_test_addr ${a} $? 1 "Global server, device client via IP_UNICAST_IF, local connection, with connect()"
done
@@ -3300,7 +3302,7 @@ ipv6_udp_novrf()
a=${NSA_IP6}
log_start
run_cmd nettest -6 -D -s -I ${NSA_DEV} -3 ${NSA_DEV} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd nettest -6 -D -d ${NSA_DEV} -r ${a} -0 ${a}
log_test_addr ${a} $? 0 "Device server, device client, local conn"
@@ -3314,7 +3316,7 @@ ipv6_udp_novrf()
run_cmd_nsb ip -6 ro add ${NSA_IP6}/128 dev ${NSB_DEV}
log_start
run_cmd nettest -6 -s -D &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd_nsb nettest -6 -D -r ${NSA_IP6}
log_test $? 0 "UDP in - LLA to GUA"
@@ -3338,7 +3340,7 @@ ipv6_udp_vrf()
log_start
show_hint "Should fail 'Connection refused' since global server is disabled"
run_cmd nettest -6 -D -s &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd_nsb nettest -6 -D -r ${a}
log_test_addr ${a} $? 1 "Global server"
done
@@ -3347,7 +3349,7 @@ ipv6_udp_vrf()
do
log_start
run_cmd nettest -6 -D -I ${VRF} -s -3 ${NSA_DEV} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd_nsb nettest -6 -D -r ${a}
log_test_addr ${a} $? 0 "VRF server"
done
@@ -3356,7 +3358,7 @@ ipv6_udp_vrf()
do
log_start
run_cmd nettest -6 -D -I ${NSA_DEV} -s -3 ${NSA_DEV} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd_nsb nettest -6 -D -r ${a}
log_test_addr ${a} $? 0 "Enslaved device server"
done
@@ -3378,7 +3380,7 @@ ipv6_udp_vrf()
log_start
show_hint "Should fail 'Connection refused' since global server is disabled"
run_cmd nettest -6 -D -s &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd nettest -6 -D -d ${VRF} -r ${a}
log_test_addr ${a} $? 1 "Global server, VRF client, local conn"
done
@@ -3387,7 +3389,7 @@ ipv6_udp_vrf()
do
log_start
run_cmd nettest -6 -D -I ${VRF} -s &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd nettest -6 -D -d ${VRF} -r ${a}
log_test_addr ${a} $? 0 "VRF server, VRF client, local conn"
done
@@ -3396,25 +3398,25 @@ ipv6_udp_vrf()
log_start
show_hint "Should fail 'Connection refused' since global server is disabled"
run_cmd nettest -6 -D -s &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd nettest -6 -D -d ${NSA_DEV} -r ${a}
log_test_addr ${a} $? 1 "Global server, device client, local conn"
log_start
run_cmd nettest -6 -D -I ${VRF} -s -3 ${NSA_DEV} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd nettest -6 -D -d ${NSA_DEV} -r ${a}
log_test_addr ${a} $? 0 "VRF server, device client, local conn"
log_start
run_cmd nettest -6 -D -I ${NSA_DEV} -s -3 ${NSA_DEV} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd nettest -6 -D -d ${VRF} -r ${a}
log_test_addr ${a} $? 0 "Enslaved device server, VRF client, local conn"
log_start
run_cmd nettest -6 -D -I ${NSA_DEV} -s -3 ${NSA_DEV} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd nettest -6 -D -d ${NSA_DEV} -r ${a}
log_test_addr ${a} $? 0 "Enslaved device server, device client, local conn"
@@ -3429,7 +3431,7 @@ ipv6_udp_vrf()
do
log_start
run_cmd nettest -6 -D -s -3 ${NSA_DEV} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd_nsb nettest -6 -D -r ${a}
log_test_addr ${a} $? 0 "Global server"
done
@@ -3438,7 +3440,7 @@ ipv6_udp_vrf()
do
log_start
run_cmd nettest -6 -D -I ${VRF} -s -3 ${NSA_DEV} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd_nsb nettest -6 -D -r ${a}
log_test_addr ${a} $? 0 "VRF server"
done
@@ -3447,7 +3449,7 @@ ipv6_udp_vrf()
do
log_start
run_cmd nettest -6 -D -I ${NSA_DEV} -s -3 ${NSA_DEV} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd_nsb nettest -6 -D -r ${a}
log_test_addr ${a} $? 0 "Enslaved device server"
done
@@ -3465,7 +3467,7 @@ ipv6_udp_vrf()
#
log_start
run_cmd_nsb nettest -6 -D -s &
- sleep 1
+ wait_local_port_listen ${NSB} 12345 udp
run_cmd nettest -6 -D -d ${VRF} -r ${NSB_IP6}
log_test $? 0 "VRF client"
@@ -3476,7 +3478,7 @@ ipv6_udp_vrf()
log_start
run_cmd_nsb nettest -6 -D -s &
- sleep 1
+ wait_local_port_listen ${NSB} 12345 udp
run_cmd nettest -6 -D -d ${NSA_DEV} -r ${NSB_IP6}
log_test $? 0 "Enslaved device client"
@@ -3491,13 +3493,13 @@ ipv6_udp_vrf()
a=${NSA_IP6}
log_start
run_cmd nettest -6 -D -s -3 ${NSA_DEV} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd nettest -6 -D -d ${VRF} -r ${a}
log_test_addr ${a} $? 0 "Global server, VRF client, local conn"
#log_start
run_cmd nettest -6 -D -I ${VRF} -s -3 ${NSA_DEV} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd nettest -6 -D -d ${VRF} -r ${a}
log_test_addr ${a} $? 0 "VRF server, VRF client, local conn"
@@ -3505,13 +3507,13 @@ ipv6_udp_vrf()
a=${VRF_IP6}
log_start
run_cmd nettest -6 -D -s -3 ${VRF} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd nettest -6 -D -d ${VRF} -r ${a}
log_test_addr ${a} $? 0 "Global server, VRF client, local conn"
log_start
run_cmd nettest -6 -D -I ${VRF} -s -3 ${VRF} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd nettest -6 -D -d ${VRF} -r ${a}
log_test_addr ${a} $? 0 "VRF server, VRF client, local conn"
@@ -3527,25 +3529,25 @@ ipv6_udp_vrf()
a=${NSA_IP6}
log_start
run_cmd nettest -6 -D -s -3 ${NSA_DEV} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd nettest -6 -D -d ${NSA_DEV} -r ${a}
log_test_addr ${a} $? 0 "Global server, device client, local conn"
log_start
run_cmd nettest -6 -D -I ${VRF} -s -3 ${NSA_DEV} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd nettest -6 -D -d ${NSA_DEV} -r ${a}
log_test_addr ${a} $? 0 "VRF server, device client, local conn"
log_start
run_cmd nettest -6 -D -I ${NSA_DEV} -s -3 ${NSA_DEV} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd nettest -6 -D -d ${VRF} -r ${a}
log_test_addr ${a} $? 0 "Device server, VRF client, local conn"
log_start
run_cmd nettest -6 -D -I ${NSA_DEV} -s -3 ${NSA_DEV} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd nettest -6 -D -d ${NSA_DEV} -r ${a}
log_test_addr ${a} $? 0 "Device server, device client, local conn"
@@ -3557,7 +3559,7 @@ ipv6_udp_vrf()
# link local addresses
log_start
run_cmd nettest -6 -D -s &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd_nsb nettest -6 -D -d ${NSB_DEV} -r ${NSA_LINKIP6}
log_test $? 0 "Global server, linklocal IP"
@@ -3568,7 +3570,7 @@ ipv6_udp_vrf()
log_start
run_cmd_nsb nettest -6 -D -s &
- sleep 1
+ wait_local_port_listen ${NSB} 12345 udp
run_cmd nettest -6 -D -d ${NSA_DEV} -r ${NSB_LINKIP6}
log_test $? 0 "Enslaved device client, linklocal IP"
@@ -3579,7 +3581,7 @@ ipv6_udp_vrf()
log_start
run_cmd nettest -6 -D -s &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd nettest -6 -D -d ${NSA_DEV} -r ${NSA_LINKIP6}
log_test $? 0 "Enslaved device client, local conn - linklocal IP"
@@ -3592,7 +3594,7 @@ ipv6_udp_vrf()
run_cmd_nsb ip -6 ro add ${NSA_IP6}/128 dev ${NSB_DEV}
log_start
run_cmd nettest -6 -s -D &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 udp
run_cmd_nsb nettest -6 -D -r ${NSA_IP6}
log_test $? 0 "UDP in - LLA to GUA"
@@ -3771,7 +3773,7 @@ ipv6_rt()
do
log_start
run_cmd nettest ${varg} -s &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest ${varg} -r ${a} &
sleep 3
run_cmd ip link del ${VRF}
@@ -3785,7 +3787,7 @@ ipv6_rt()
do
log_start
run_cmd nettest ${varg} -I ${VRF} -s &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest ${varg} -r ${a} &
sleep 3
run_cmd ip link del ${VRF}
@@ -3799,7 +3801,7 @@ ipv6_rt()
do
log_start
run_cmd nettest ${varg} -I ${NSA_DEV} -s &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest ${varg} -r ${a} &
sleep 3
run_cmd ip link del ${VRF}
@@ -3814,7 +3816,7 @@ ipv6_rt()
#
log_start
run_cmd_nsb nettest ${varg} -s &
- sleep 1
+ wait_local_port_listen ${NSB} 12345 tcp
run_cmd nettest ${varg} -d ${VRF} -r ${NSB_IP6} &
sleep 3
run_cmd ip link del ${VRF}
@@ -3825,7 +3827,7 @@ ipv6_rt()
log_start
run_cmd_nsb nettest ${varg} -s &
- sleep 1
+ wait_local_port_listen ${NSB} 12345 tcp
run_cmd nettest ${varg} -d ${NSA_DEV} -r ${NSB_IP6} &
sleep 3
run_cmd ip link del ${VRF}
@@ -3842,7 +3844,7 @@ ipv6_rt()
do
log_start
run_cmd nettest ${varg} -s &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd nettest ${varg} -d ${VRF} -r ${a} &
sleep 3
run_cmd ip link del ${VRF}
@@ -3856,7 +3858,7 @@ ipv6_rt()
do
log_start
run_cmd nettest ${varg} -I ${VRF} -s &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd nettest ${varg} -d ${VRF} -r ${a} &
sleep 3
run_cmd ip link del ${VRF}
@@ -3869,7 +3871,7 @@ ipv6_rt()
a=${NSA_IP6}
log_start
run_cmd nettest ${varg} -s &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd nettest ${varg} -d ${NSA_DEV} -r ${a} &
sleep 3
run_cmd ip link del ${VRF}
@@ -3880,7 +3882,7 @@ ipv6_rt()
log_start
run_cmd nettest ${varg} -I ${VRF} -s &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd nettest ${varg} -d ${NSA_DEV} -r ${a} &
sleep 3
run_cmd ip link del ${VRF}
@@ -3891,7 +3893,7 @@ ipv6_rt()
log_start
run_cmd nettest ${varg} -I ${NSA_DEV} -s &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd nettest ${varg} -d ${NSA_DEV} -r ${a} &
sleep 3
run_cmd ip link del ${VRF}
@@ -3950,7 +3952,7 @@ netfilter_tcp_reset()
do
log_start
run_cmd nettest -s &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -r ${a}
log_test_addr ${a} $? 1 "Global server, reject with TCP-reset on Rx"
done
@@ -3968,7 +3970,7 @@ netfilter_icmp()
do
log_start
run_cmd nettest ${arg} -s &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest ${arg} -r ${a}
log_test_addr ${a} $? 1 "Global ${stype} server, Rx reject icmp-port-unreach"
done
@@ -4007,7 +4009,7 @@ netfilter_tcp6_reset()
do
log_start
run_cmd nettest -6 -s &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -6 -r ${a}
log_test_addr ${a} $? 1 "Global server, reject with TCP-reset on Rx"
done
@@ -4025,7 +4027,7 @@ netfilter_icmp6()
do
log_start
run_cmd nettest -6 -s ${arg} &
- sleep 1
+ wait_local_port_listen ${NSA} 12345 tcp
run_cmd_nsb nettest -6 ${arg} -r ${a}
log_test_addr ${a} $? 1 "Global ${stype} server, Rx reject icmp-port-unreach"
done
@@ -4221,12 +4223,12 @@ use_case_snat_on_vrf()
run_cmd ip6tables -t nat -A POSTROUTING -p tcp -m tcp --dport ${port} -j SNAT --to-source ${NSA_LO_IP6} -o ${VRF}
run_cmd_nsb nettest -s -l ${NSB_IP} -p ${port} &
- sleep 1
+ wait_local_port_listen ${NSB} ${port} tcp
run_cmd nettest -d ${VRF} -r ${NSB_IP} -p ${port}
log_test $? 0 "IPv4 TCP connection over VRF with SNAT"
run_cmd_nsb nettest -6 -s -l ${NSB_IP6} -p ${port} &
- sleep 1
+ wait_local_port_listen ${NSB} ${port} tcp
run_cmd nettest -6 -d ${VRF} -r ${NSB_IP6} -p ${port}
log_test $? 0 "IPv6 TCP connection over VRF with SNAT"
@@ -4272,6 +4274,7 @@ EOF
TESTS_IPV4="ipv4_ping ipv4_tcp ipv4_udp ipv4_bind ipv4_runtime ipv4_netfilter"
TESTS_IPV6="ipv6_ping ipv6_tcp ipv6_udp ipv6_bind ipv6_runtime ipv6_netfilter"
TESTS_OTHER="use_cases"
+# note: each TEST_ group needs a dedicated runner, e.g. fcnal-ipv4.sh
PAUSE_ON_FAIL=no
PAUSE=no
@@ -4302,6 +4305,8 @@ elif [ "$TESTS" = "ipv4" ]; then
TESTS="$TESTS_IPV4"
elif [ "$TESTS" = "ipv6" ]; then
TESTS="$TESTS_IPV6"
+elif [ "$TESTS" = "other" ]; then
+ TESTS="$TESTS_OTHER"
fi
check_gen_prog "nettest"
diff --git a/tools/testing/selftests/net/fdb_notify.sh b/tools/testing/selftests/net/fdb_notify.sh
index c159230c9b62..0b8a2465dd04 100755
--- a/tools/testing/selftests/net/fdb_notify.sh
+++ b/tools/testing/selftests/net/fdb_notify.sh
@@ -40,16 +40,16 @@ do_test_dup()
test_dup_bridge()
{
- ip_link_add br up type bridge vlan_filtering 1
+ adf_ip_link_add br up type bridge vlan_filtering 1
do_test_dup add "bridge" dev br self
do_test_dup del "bridge" dev br self
}
test_dup_vxlan_self()
{
- ip_link_add br up type bridge vlan_filtering 1
- ip_link_add vx up type vxlan id 2000 dstport 4789
- ip_link_set_master vx br
+ adf_ip_link_add br up type bridge vlan_filtering 1
+ adf_ip_link_add vx up type vxlan id 2000 dstport 4789
+ adf_ip_link_set_master vx br
do_test_dup add "vxlan" dev vx self dst 192.0.2.1
do_test_dup del "vxlan" dev vx self dst 192.0.2.1
@@ -57,9 +57,9 @@ test_dup_vxlan_self()
test_dup_vxlan_master()
{
- ip_link_add br up type bridge vlan_filtering 1
- ip_link_add vx up type vxlan id 2000 dstport 4789
- ip_link_set_master vx br
+ adf_ip_link_add br up type bridge vlan_filtering 1
+ adf_ip_link_add vx up type vxlan id 2000 dstport 4789
+ adf_ip_link_set_master vx br
do_test_dup add "vxlan master" dev vx master
do_test_dup del "vxlan master" dev vx master
@@ -67,8 +67,8 @@ test_dup_vxlan_master()
test_dup_macvlan_self()
{
- ip_link_add dd up type dummy
- ip_link_add mv up link dd type macvlan mode passthru
+ adf_ip_link_add dd up type dummy
+ adf_ip_link_add mv up link dd type macvlan mode passthru
do_test_dup add "macvlan self" dev mv self
do_test_dup del "macvlan self" dev mv self
@@ -76,10 +76,10 @@ test_dup_macvlan_self()
test_dup_macvlan_master()
{
- ip_link_add br up type bridge vlan_filtering 1
- ip_link_add dd up type dummy
- ip_link_add mv up link dd type macvlan mode passthru
- ip_link_set_master mv br
+ adf_ip_link_add br up type bridge vlan_filtering 1
+ adf_ip_link_add dd up type dummy
+ adf_ip_link_add mv up link dd type macvlan mode passthru
+ adf_ip_link_set_master mv br
do_test_dup add "macvlan master" dev mv self
do_test_dup del "macvlan master" dev mv self
diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh
index b39f748c2572..2b0a90581e2f 100755
--- a/tools/testing/selftests/net/fib_nexthops.sh
+++ b/tools/testing/selftests/net/fib_nexthops.sh
@@ -467,8 +467,8 @@ ipv6_fdb_grp_fcnal()
log_test $? 0 "Get Fdb nexthop group by id"
# fdb nexthop group can only contain fdb nexthops
- run_cmd "$IP nexthop add id 63 via 2001:db8:91::4"
- run_cmd "$IP nexthop add id 64 via 2001:db8:91::5"
+ run_cmd "$IP nexthop add id 63 via 2001:db8:91::4 dev veth1"
+ run_cmd "$IP nexthop add id 64 via 2001:db8:91::5 dev veth1"
run_cmd "$IP nexthop add id 103 group 63/64 fdb"
log_test $? 2 "Fdb Nexthop group with non-fdb nexthops"
@@ -494,6 +494,26 @@ ipv6_fdb_grp_fcnal()
run_cmd "$IP nexthop add id 69 encap mpls 101 via 2001:db8:91::8 dev veth1 fdb"
log_test $? 2 "Fdb Nexthop with encap"
+ # Replace FDB nexthop to non-FDB and vice versa
+ run_cmd "$IP nexthop add id 70 via 2001:db8:91::2 fdb"
+ run_cmd "$IP nexthop replace id 70 via 2001:db8:91::2 dev veth1"
+ log_test $? 0 "Replace FDB nexthop to non-FDB nexthop"
+ run_cmd "$IP nexthop replace id 70 via 2001:db8:91::2 fdb"
+ log_test $? 0 "Replace non-FDB nexthop to FDB nexthop"
+
+ # Replace FDB nexthop address while in a group
+ run_cmd "$IP nexthop add id 71 group 70 fdb"
+ run_cmd "$IP nexthop replace id 70 via 2001:db8:91::3 fdb"
+ log_test $? 0 "Replace FDB nexthop address while in a group"
+
+ # Cannot replace FDB nexthop to non-FDB and vice versa while in a group
+ run_cmd "$IP nexthop replace id 70 via 2001:db8:91::2 dev veth1"
+ log_test $? 2 "Replace FDB nexthop to non-FDB nexthop while in a group"
+ run_cmd "$IP nexthop add id 72 via 2001:db8:91::2 dev veth1"
+ run_cmd "$IP nexthop add id 73 group 72"
+ run_cmd "$IP nexthop replace id 72 via 2001:db8:91::2 fdb"
+ log_test $? 2 "Replace non-FDB nexthop to FDB nexthop while in a group"
+
run_cmd "$IP link add name vx10 type vxlan id 1010 local 2001:db8:91::9 remote 2001:db8:91::10 dstport 4789 nolearning noudpcsum tos inherit ttl 100"
run_cmd "$BRIDGE fdb add 02:02:00:00:00:13 dev vx10 nhid 102 self"
log_test $? 0 "Fdb mac add with nexthop group"
@@ -547,15 +567,15 @@ ipv4_fdb_grp_fcnal()
log_test $? 0 "Get Fdb nexthop group by id"
# fdb nexthop group can only contain fdb nexthops
- run_cmd "$IP nexthop add id 14 via 172.16.1.2"
- run_cmd "$IP nexthop add id 15 via 172.16.1.3"
+ run_cmd "$IP nexthop add id 14 via 172.16.1.2 dev veth1"
+ run_cmd "$IP nexthop add id 15 via 172.16.1.3 dev veth1"
run_cmd "$IP nexthop add id 103 group 14/15 fdb"
log_test $? 2 "Fdb Nexthop group with non-fdb nexthops"
# Non fdb nexthop group can not contain fdb nexthops
run_cmd "$IP nexthop add id 16 via 172.16.1.2 fdb"
run_cmd "$IP nexthop add id 17 via 172.16.1.3 fdb"
- run_cmd "$IP nexthop add id 104 group 14/15"
+ run_cmd "$IP nexthop add id 104 group 16/17"
log_test $? 2 "Non-Fdb Nexthop group with fdb nexthops"
# fdb nexthop cannot have blackhole
@@ -574,6 +594,26 @@ ipv4_fdb_grp_fcnal()
run_cmd "$IP nexthop add id 17 encap mpls 101 via 172.16.1.2 dev veth1 fdb"
log_test $? 2 "Fdb Nexthop with encap"
+ # Replace FDB nexthop to non-FDB and vice versa
+ run_cmd "$IP nexthop add id 18 via 172.16.1.2 fdb"
+ run_cmd "$IP nexthop replace id 18 via 172.16.1.2 dev veth1"
+ log_test $? 0 "Replace FDB nexthop to non-FDB nexthop"
+ run_cmd "$IP nexthop replace id 18 via 172.16.1.2 fdb"
+ log_test $? 0 "Replace non-FDB nexthop to FDB nexthop"
+
+ # Replace FDB nexthop address while in a group
+ run_cmd "$IP nexthop add id 19 group 18 fdb"
+ run_cmd "$IP nexthop replace id 18 via 172.16.1.3 fdb"
+ log_test $? 0 "Replace FDB nexthop address while in a group"
+
+ # Cannot replace FDB nexthop to non-FDB and vice versa while in a group
+ run_cmd "$IP nexthop replace id 18 via 172.16.1.2 dev veth1"
+ log_test $? 2 "Replace FDB nexthop to non-FDB nexthop while in a group"
+ run_cmd "$IP nexthop add id 20 via 172.16.1.2 dev veth1"
+ run_cmd "$IP nexthop add id 21 group 20"
+ run_cmd "$IP nexthop replace id 20 via 172.16.1.2 fdb"
+ log_test $? 2 "Replace non-FDB nexthop to FDB nexthop while in a group"
+
run_cmd "$IP link add name vx10 type vxlan id 1010 local 10.0.0.1 remote 10.0.0.2 dstport 4789 nolearning noudpcsum tos inherit ttl 100"
run_cmd "$BRIDGE fdb add 02:02:00:00:00:13 dev vx10 nhid 102 self"
log_test $? 0 "Fdb mac add with nexthop group"
@@ -582,7 +622,7 @@ ipv4_fdb_grp_fcnal()
run_cmd "$BRIDGE fdb add 02:02:00:00:00:14 dev vx10 nhid 12 self"
log_test $? 255 "Fdb mac add with nexthop"
- run_cmd "$IP ro add 172.16.0.0/22 nhid 15"
+ run_cmd "$IP ro add 172.16.0.0/22 nhid 16"
log_test $? 2 "Route add with fdb nexthop"
run_cmd "$IP ro add 172.16.0.0/22 nhid 103"
diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile
index d7bb2e80e88c..e6f482a600da 100644
--- a/tools/testing/selftests/net/forwarding/Makefile
+++ b/tools/testing/selftests/net/forwarding/Makefile
@@ -1,8 +1,11 @@
# SPDX-License-Identifier: GPL-2.0+ OR MIT
-TEST_PROGS = bridge_fdb_learning_limit.sh \
+TEST_PROGS = \
+ bridge_activity_notify.sh \
+ bridge_fdb_learning_limit.sh \
bridge_igmp.sh \
bridge_locked_port.sh \
+ bridge_fdb_local_vlan_0.sh \
bridge_mdb.sh \
bridge_mdb_host.sh \
bridge_mdb_max.sh \
diff --git a/tools/testing/selftests/net/forwarding/README b/tools/testing/selftests/net/forwarding/README
index 7b41cff993ad..392a5a91ed37 100644
--- a/tools/testing/selftests/net/forwarding/README
+++ b/tools/testing/selftests/net/forwarding/README
@@ -57,6 +57,21 @@ o Code shall be checked using ShellCheck [1] prior to submission.
1. https://www.shellcheck.net/
+Cleanups
+--------
+
+o lib.sh brings in defer.sh (by way of ../lib.sh) by default. Consider
+ making use of the defer primitive to schedule automatic cleanups. This
+ makes it harder to forget to remove a temporary netdevice, kill a running
+ process or perform other cleanup when the test script is interrupted.
+
+o When adding a helper that dirties the environment, but schedules all
+ necessary cleanups through defer, consider prefixing it adf_ for
+ consistency with lib.sh and ../lib.sh helpers. This serves as an
+ immediately visible bit of documentation about the helper API.
+
+o Definitely do the above for any new code in lib.sh, if practical.
+
Customization
=============
diff --git a/tools/testing/selftests/net/forwarding/bridge_activity_notify.sh b/tools/testing/selftests/net/forwarding/bridge_activity_notify.sh
new file mode 100755
index 000000000000..522a5b1b046c
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/bridge_activity_notify.sh
@@ -0,0 +1,170 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# +-----------------------+ +------------------------+
+# | H1 (vrf) | | H2 (vrf) |
+# | 192.0.2.1/28 | | 192.0.2.2/28 |
+# | + $h1 | | + $h2 |
+# +----|------------------+ +----|-------------------+
+# | |
+# +----|--------------------------------------------------|-------------------+
+# | SW | | |
+# | +--|--------------------------------------------------|-----------------+ |
+# | | + $swp1 BR1 (802.1d) + $swp2 | |
+# | | | |
+# | +-----------------------------------------------------------------------+ |
+# +---------------------------------------------------------------------------+
+
+ALL_TESTS="
+ new_inactive_test
+ existing_active_test
+ norefresh_test
+"
+
+NUM_NETIFS=4
+source lib.sh
+
+h1_create()
+{
+ adf_simple_if_init "$h1" 192.0.2.1/28
+}
+
+h2_create()
+{
+ adf_simple_if_init "$h2" 192.0.2.2/28
+}
+
+switch_create()
+{
+ adf_ip_link_add br1 type bridge vlan_filtering 0 mcast_snooping 0 \
+ ageing_time "$LOW_AGEING_TIME"
+ adf_ip_link_set_up br1
+
+ adf_ip_link_set_master "$swp1" br1
+ adf_ip_link_set_up "$swp1"
+
+ adf_ip_link_set_master "$swp2" br1
+ adf_ip_link_set_up "$swp2"
+}
+
+setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ swp1=${NETIFS[p2]}
+
+ swp2=${NETIFS[p3]}
+ h2=${NETIFS[p4]}
+
+ adf_vrf_prepare
+
+ h1_create
+ h2_create
+ switch_create
+}
+
+fdb_active_wait()
+{
+ local mac=$1; shift
+
+ bridge -d fdb get "$mac" br br1 | grep -q -v "inactive"
+}
+
+fdb_inactive_wait()
+{
+ local mac=$1; shift
+
+ bridge -d fdb get "$mac" br br1 | grep -q "inactive"
+}
+
+new_inactive_test()
+{
+ local mac="00:11:22:33:44:55"
+
+ # Add a new FDB entry as static and inactive and check that it
+ # becomes active upon traffic.
+ RET=0
+
+ bridge fdb add "$mac" dev "$swp1" master static activity_notify inactive
+ bridge -d fdb get "$mac" br br1 | grep -q "inactive"
+ check_err $? "FDB entry not present as \"inactive\" when should"
+
+ $MZ "$h1" -c 1 -p 64 -a "$mac" -b bcast -t ip -q
+
+ busywait "$BUSYWAIT_TIMEOUT" fdb_active_wait "$mac"
+ check_err $? "FDB entry present as \"inactive\" when should not"
+
+ log_test "Transition from inactive to active"
+
+ bridge fdb del "$mac" dev "$swp1" master
+}
+
+existing_active_test()
+{
+ local mac="00:11:22:33:44:55"
+ local ageing_time
+
+ # Enable activity notifications on an existing dynamic FDB entry and
+ # check that it becomes inactive after the ageing time passed.
+ RET=0
+
+ bridge fdb add "$mac" dev "$swp1" master dynamic
+ bridge fdb replace "$mac" dev "$swp1" master static activity_notify norefresh
+
+ bridge -d fdb get "$mac" br br1 | grep -q "activity_notify"
+ check_err $? "FDB entry not present as \"activity_notify\" when should"
+
+ bridge -d fdb get "$mac" br br1 | grep -q "inactive"
+ check_fail $? "FDB entry present as \"inactive\" when should not"
+
+ ageing_time=$(bridge_ageing_time_get br1)
+ slowwait $((ageing_time * 2)) fdb_inactive_wait "$mac"
+ check_err $? "FDB entry not present as \"inactive\" when should"
+
+ log_test "Transition from active to inactive"
+
+ bridge fdb del "$mac" dev "$swp1" master
+}
+
+norefresh_test()
+{
+ local mac="00:11:22:33:44:55"
+ local updated_time
+
+ # Check that the "updated" time is reset when replacing an FDB entry
+ # without the "norefresh" keyword and that it is not reset when
+ # replacing with the "norefresh" keyword.
+ RET=0
+
+ bridge fdb add "$mac" dev "$swp1" master static
+ sleep 1
+
+ bridge fdb replace "$mac" dev "$swp1" master static activity_notify
+ updated_time=$(bridge -d -s -j fdb get "$mac" br br1 | jq '.[]["updated"]')
+ if [[ $updated_time -ne 0 ]]; then
+ check_err 1 "\"updated\" time was not reset when should"
+ fi
+
+ sleep 1
+ bridge fdb replace "$mac" dev "$swp1" master static norefresh
+ updated_time=$(bridge -d -s -j fdb get "$mac" br br1 | jq '.[]["updated"]')
+ if [[ $updated_time -eq 0 ]]; then
+ check_err 1 "\"updated\" time was reset when should not"
+ fi
+
+ log_test "Resetting of \"updated\" time"
+
+ bridge fdb del "$mac" dev "$swp1" master
+}
+
+if ! bridge fdb help 2>&1 | grep -q "activity_notify"; then
+ echo "SKIP: iproute2 too old, missing bridge FDB activity notification control"
+ exit "$ksft_skip"
+fi
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+tests_run
+
+exit "$EXIT_STATUS"
diff --git a/tools/testing/selftests/net/forwarding/bridge_fdb_local_vlan_0.sh b/tools/testing/selftests/net/forwarding/bridge_fdb_local_vlan_0.sh
new file mode 100755
index 000000000000..694de8ba97e4
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/bridge_fdb_local_vlan_0.sh
@@ -0,0 +1,387 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# +-----------------------+ +-----------------------+ +-----------------------+
+# | H1 (vrf) | | H2 (vrf) | | H3 (vrf) |
+# | + $h1 | | + $h2 | | + $h3 |
+# | | 192.0.2.1/28 | | | 192.0.2.2/28 | | | 192.0.2.18/28 |
+# | | 2001:db8:1::1/64 | | | 2001:db8:1::2/64 | | | 2001:db8:2::2/64 |
+# | | | | | | | | |
+# +----|------------------+ +----|------------------+ +----|------------------+
+# | | |
+# +----|-------------------------|-------------------------|------------------+
+# | +--|-------------------------|------------------+ | |
+# | | + $swp1 + $swp2 | + $swp3 |
+# | | | 192.0.2.17/28 |
+# | | BR1 (802.1q) | 2001:db8:2::1/64 |
+# | | 192.0.2.3/28 | |
+# | | 2001:db8:1::3/64 | |
+# | +-----------------------------------------------+ SW |
+# +---------------------------------------------------------------------------+
+#
+#shellcheck disable=SC2317 # SC doesn't see our uses of functions.
+#shellcheck disable=SC2034 # ... and global variables
+
+ALL_TESTS="
+ test_d_no_sharing
+ test_d_sharing
+ test_q_no_sharing
+ test_q_sharing
+ test_addr_set
+"
+
+NUM_NETIFS=6
+source lib.sh
+
+pMAC=00:11:22:33:44:55
+bMAC=00:11:22:33:44:66
+mMAC=00:11:22:33:44:77
+xMAC=00:11:22:33:44:88
+
+host_create()
+{
+ local h=$1; shift
+ local ipv4=$1; shift
+ local ipv6=$1; shift
+
+ adf_simple_if_init "$h" "$ipv4" "$ipv6"
+ adf_ip_route_add vrf "v$h" 192.0.2.16/28 nexthop via 192.0.2.3
+ adf_ip_route_add vrf "v$h" 2001:db8:2::/64 nexthop via 2001:db8:1::3
+}
+
+h3_create()
+{
+ adf_simple_if_init "$h3" 192.0.2.18/28 2001:db8:2::2/64
+ adf_ip_route_add vrf "v$h3" 192.0.2.0/28 nexthop via 192.0.2.17
+ adf_ip_route_add vrf "v$h3" 2001:db8:1::/64 nexthop via 2001:db8:2::1
+
+ tc qdisc add dev "$h3" clsact
+ defer tc qdisc del dev "$h3" clsact
+
+ tc filter add dev "$h3" ingress proto ip pref 104 \
+ flower skip_hw ip_proto udp dst_port 4096 \
+ action pass
+ defer tc filter del dev "$h3" ingress proto ip pref 104
+
+ tc qdisc add dev "$h2" clsact
+ defer tc qdisc del dev "$h2" clsact
+
+ tc filter add dev "$h2" ingress proto ip pref 104 \
+ flower skip_hw ip_proto udp dst_port 4096 \
+ action pass
+ defer tc filter del dev "$h2" ingress proto ip pref 104
+}
+
+switch_create()
+{
+ adf_ip_link_set_up "$swp1"
+
+ adf_ip_link_set_up "$swp2"
+
+ adf_ip_addr_add "$swp3" 192.0.2.17/28
+ adf_ip_addr_add "$swp3" 2001:db8:2::1/64
+ adf_ip_link_set_up "$swp3"
+}
+
+setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ swp1=${NETIFS[p2]}
+
+ swp2=${NETIFS[p3]}
+ h2=${NETIFS[p4]}
+
+ swp3=${NETIFS[p5]}
+ h3=${NETIFS[p6]}
+
+ adf_vrf_prepare
+ adf_forwarding_enable
+
+ host_create "$h1" 192.0.2.1/28 2001:db8:1::1/64
+ host_create "$h2" 192.0.2.2/28 2001:db8:1::2/64
+ h3_create
+
+ switch_create
+}
+
+adf_bridge_configure()
+{
+ local dev
+
+ adf_ip_addr_add br 192.0.2.3/28
+ adf_ip_addr_add br 2001:db8:1::3/64
+
+ adf_bridge_vlan_add dev br vid 1 pvid untagged self
+ adf_bridge_vlan_add dev br vid 2 self
+ adf_bridge_vlan_add dev br vid 3 self
+
+ for dev in "$swp1" "$swp2"; do
+ adf_ip_link_set_master "$dev" br
+ adf_bridge_vlan_add dev "$dev" vid 1 pvid untagged
+ adf_bridge_vlan_add dev "$dev" vid 2
+ adf_bridge_vlan_add dev "$dev" vid 3
+ done
+}
+
+adf_bridge_create()
+{
+ local mac
+
+ adf_ip_link_add br up type bridge vlan_default_pvid 0 "$@"
+ mac=$(mac_get br)
+ adf_bridge_configure
+ adf_ip_link_set_addr br "$mac"
+}
+
+check_fdb_local_vlan_0_support()
+{
+ if adf_ip_link_add XXbr up type bridge vlan_filtering 1 \
+ fdb_local_vlan_0 1 &>/dev/null; then
+ return 0
+ fi
+
+ log_test_skip "FDB sharing" \
+ "iproute 2 or the kernel do not support fdb_local_vlan_0"
+}
+
+check_mac_presence()
+{
+ local should_fail=$1; shift
+ local dev=$1; shift
+ local vlan=$1; shift
+ local mac
+
+ mac=$(mac_get "$dev")
+
+ if ((vlan == 0)); then
+ vlan=null
+ fi
+
+ bridge -j fdb show dev "$dev" |
+ jq -e --arg mac "$mac" --argjson vlan "$vlan" \
+ '.[] | select(.mac == $mac) | select(.vlan == $vlan)' > /dev/null
+ check_err_fail "$should_fail" $? "FDB dev $dev vid $vlan addr $mac exists"
+}
+
+do_sharing_test()
+{
+ local should_fail=$1; shift
+ local what=$1; shift
+ local dev
+
+ RET=0
+
+ for dev in "$swp1" "$swp2" br; do
+ check_mac_presence 0 "$dev" 0
+ check_mac_presence "$should_fail" "$dev" 1
+ check_mac_presence "$should_fail" "$dev" 2
+ check_mac_presence "$should_fail" "$dev" 3
+ done
+
+ log_test "$what"
+}
+
+do_end_to_end_test()
+{
+ local mac=$1; shift
+ local what=$1; shift
+ local probe_dev=${1-$h3}; shift
+ local expect=${1-10}; shift
+
+ local t0
+ local t1
+ local dd
+
+ RET=0
+
+ # In mausezahn, use $dev MAC as the destination MAC. In the MAC sharing
+ # context, that will cause an FDB miss on VLAN 1 and prompt a second
+ # lookup in VLAN 0.
+
+ t0=$(tc_rule_stats_get "$probe_dev" 104 ingress)
+
+ $MZ "$h1" -c 10 -p 64 -a own -b "$mac" \
+ -A 192.0.2.1 -B 192.0.2.18 -t udp "dp=4096,sp=2048" -q
+ sleep 1
+
+ t1=$(tc_rule_stats_get "$probe_dev" 104 ingress)
+ dd=$((t1 - t0))
+
+ ((dd == expect))
+ check_err $? "Expected $expect packets on $probe_dev got $dd"
+
+ log_test "$what"
+}
+
+do_tests()
+{
+ local should_fail=$1; shift
+ local what=$1; shift
+ local swp1_mac
+ local br_mac
+
+ swp1_mac=$(mac_get "$swp1")
+ br_mac=$(mac_get br)
+
+ do_sharing_test "$should_fail" "$what"
+ do_end_to_end_test "$swp1_mac" "$what: end to end, $swp1 MAC"
+ do_end_to_end_test "$br_mac" "$what: end to end, br MAC"
+}
+
+bridge_standard()
+{
+ local vlan_filtering=$1; shift
+
+ if ((vlan_filtering)); then
+ echo 802.1q
+ else
+ echo 802.1d
+ fi
+}
+
+nonexistent_fdb_test()
+{
+ local vlan_filtering=$1; shift
+ local standard
+
+ standard=$(bridge_standard "$vlan_filtering")
+
+ # We expect flooding, so $h2 should get the traffic.
+ do_end_to_end_test "$xMAC" "$standard: Nonexistent FDB" "$h2"
+}
+
+misleading_fdb_test()
+{
+ local vlan_filtering=$1; shift
+ local standard
+
+ standard=$(bridge_standard "$vlan_filtering")
+
+ defer_scope_push
+ # Add an FDB entry on VLAN 0. The lookup on VLAN-aware bridge
+ # shouldn't pick this up even with fdb_local_vlan_0 enabled, so
+ # the traffic should be flooded. This all holds on
+ # vlan_filtering bridge, on non-vlan_filtering one the FDB entry
+ # is expected to be found as usual, no flooding takes place.
+ #
+ # Adding only on VLAN 0 is a bit tricky, because bridge is
+ # trying to be nice and interprets the request as if the FDB
+ # should be added on each VLAN.
+
+ bridge fdb add "$mMAC" dev "$swp1" master
+ bridge fdb del "$mMAC" dev "$swp1" vlan 1 master
+ bridge fdb del "$mMAC" dev "$swp1" vlan 2 master
+ bridge fdb del "$mMAC" dev "$swp1" vlan 3 master
+
+ local expect=$((vlan_filtering ? 10 : 0))
+ do_end_to_end_test "$mMAC" \
+ "$standard: Lookup of non-local MAC on VLAN 0" \
+ "$h2" "$expect"
+ defer_scope_pop
+}
+
+change_mac()
+{
+ local dev=$1; shift
+ local mac=$1; shift
+ local cur_mac
+
+ cur_mac=$(mac_get "$dev")
+
+ log_info "Change $dev MAC $cur_mac -> $mac"
+ adf_ip_link_set_addr "$dev" "$mac"
+ defer log_info "Change $dev MAC back"
+}
+
+do_test_no_sharing()
+{
+ local vlan_filtering=$1; shift
+ local standard
+
+ standard=$(bridge_standard "$vlan_filtering")
+
+ adf_bridge_create vlan_filtering "$vlan_filtering"
+ setup_wait
+
+ do_tests 0 "$standard, no FDB sharing"
+
+ change_mac "$swp1" "$pMAC"
+ change_mac br "$bMAC"
+
+ do_tests 0 "$standard, no FDB sharing after MAC change"
+
+ in_defer_scope check_fdb_local_vlan_0_support || return
+
+ log_info "Set fdb_local_vlan_0=1"
+ ip link set dev br type bridge fdb_local_vlan_0 1
+
+ do_tests 1 "$standard, fdb sharing after toggle"
+}
+
+do_test_sharing()
+{
+ local vlan_filtering=$1; shift
+ local standard
+
+ standard=$(bridge_standard "$vlan_filtering")
+
+ in_defer_scope check_fdb_local_vlan_0_support || return
+
+ adf_bridge_create vlan_filtering "$vlan_filtering" fdb_local_vlan_0 1
+ setup_wait
+
+ do_tests 1 "$standard, FDB sharing"
+
+ nonexistent_fdb_test "$vlan_filtering"
+ misleading_fdb_test "$vlan_filtering"
+
+ change_mac "$swp1" "$pMAC"
+ change_mac br "$bMAC"
+
+ do_tests 1 "$standard, FDB sharing after MAC change"
+
+ log_info "Set fdb_local_vlan_0=0"
+ ip link set dev br type bridge fdb_local_vlan_0 0
+
+ do_tests 0 "$standard, No FDB sharing after toggle"
+}
+
+test_d_no_sharing()
+{
+ do_test_no_sharing 0
+}
+
+test_d_sharing()
+{
+ do_test_sharing 0
+}
+
+test_q_no_sharing()
+{
+ do_test_no_sharing 1
+}
+
+test_q_sharing()
+{
+ do_test_sharing 1
+}
+
+adf_addr_set_bridge_create()
+{
+ adf_ip_link_add br up type bridge vlan_filtering 0
+ adf_ip_link_set_addr br "$(mac_get br)"
+ adf_bridge_configure
+}
+
+test_addr_set()
+{
+ adf_addr_set_bridge_create
+ setup_wait
+
+ do_end_to_end_test "$(mac_get br)" "NET_ADDR_SET: end to end, br MAC"
+}
+
+trap cleanup EXIT
+
+setup_prepare
+tests_run
diff --git a/tools/testing/selftests/net/forwarding/custom_multipath_hash.sh b/tools/testing/selftests/net/forwarding/custom_multipath_hash.sh
index 7d531f7091e6..5dbfab0e23e3 100755
--- a/tools/testing/selftests/net/forwarding/custom_multipath_hash.sh
+++ b/tools/testing/selftests/net/forwarding/custom_multipath_hash.sh
@@ -226,7 +226,7 @@ send_flowlabel()
# Generate 16384 echo requests, each with a random flow label.
ip vrf exec v$h1 sh -c \
"for _ in {1..16384}; do \
- $PING6 2001:db8:4::2 -F 0 -c 1 -q >/dev/null 2>&1; \
+ $PING6 -F 0 -c 1 -q 2001:db8:4::2 >/dev/null 2>&1; \
done"
}
diff --git a/tools/testing/selftests/net/forwarding/gre_custom_multipath_hash.sh b/tools/testing/selftests/net/forwarding/gre_custom_multipath_hash.sh
index dda11a4a9450..b4f17a5bbc61 100755
--- a/tools/testing/selftests/net/forwarding/gre_custom_multipath_hash.sh
+++ b/tools/testing/selftests/net/forwarding/gre_custom_multipath_hash.sh
@@ -321,7 +321,7 @@ send_flowlabel()
# Generate 16384 echo requests, each with a random flow label.
ip vrf exec v$h1 sh -c \
"for _ in {1..16384}; do \
- $PING6 2001:db8:2::2 -F 0 -c 1 -q >/dev/null 2>&1; \
+ $PING6 -F 0 -c 1 -q 2001:db8:2::2 >/dev/null 2>&1; \
done"
}
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 49fa94b53a1c..25036e38043c 100755
--- a/tools/testing/selftests/net/forwarding/ip6_forward_instats_vrf.sh
+++ b/tools/testing/selftests/net/forwarding/ip6_forward_instats_vrf.sh
@@ -95,7 +95,7 @@ ipv6_in_too_big_err()
# Send too big packets
ip vrf exec $vrf_name \
- $PING6 -s 1300 2001:1:2::2 -c 1 -w $PING_TIMEOUT &> /dev/null
+ $PING6 -s 1300 -c 1 -w $PING_TIMEOUT 2001:1:2::2 &> /dev/null
local t1=$(ipv6_stats_get $rtr1 Ip6InTooBigErrors)
test "$((t1 - t0))" -ne 0
@@ -131,7 +131,7 @@ ipv6_in_addr_err()
# Disable forwarding temporary while sending the packet
sysctl -qw net.ipv6.conf.all.forwarding=0
ip vrf exec $vrf_name \
- $PING6 2001:1:2::2 -c 1 -w $PING_TIMEOUT &> /dev/null
+ $PING6 -c 1 -w $PING_TIMEOUT 2001:1:2::2 &> /dev/null
sysctl -qw net.ipv6.conf.all.forwarding=1
local t1=$(ipv6_stats_get $rtr1 Ip6InAddrErrors)
@@ -150,7 +150,7 @@ ipv6_in_discard()
# Add a policy to discard
ip xfrm policy add dst 2001:1:2::2/128 dir fwd action block
ip vrf exec $vrf_name \
- $PING6 2001:1:2::2 -c 1 -w $PING_TIMEOUT &> /dev/null
+ $PING6 -c 1 -w $PING_TIMEOUT 2001:1:2::2 &> /dev/null
ip xfrm policy del dst 2001:1:2::2/128 dir fwd
local t1=$(ipv6_stats_get $rtr1 Ip6InDiscards)
diff --git a/tools/testing/selftests/net/forwarding/ip6gre_custom_multipath_hash.sh b/tools/testing/selftests/net/forwarding/ip6gre_custom_multipath_hash.sh
index e28b4a079e52..b24acfa52a3a 100755
--- a/tools/testing/selftests/net/forwarding/ip6gre_custom_multipath_hash.sh
+++ b/tools/testing/selftests/net/forwarding/ip6gre_custom_multipath_hash.sh
@@ -323,7 +323,7 @@ send_flowlabel()
# Generate 16384 echo requests, each with a random flow label.
ip vrf exec v$h1 sh -c \
"for _ in {1..16384}; do \
- $PING6 2001:db8:2::2 -F 0 -c 1 -q >/dev/null 2>&1; \
+ $PING6 -F 0 -c 1 -q 2001:db8:2::2 >/dev/null 2>&1; \
done"
}
diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index 890b3374dacd..a9034f0bb58b 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -571,30 +571,6 @@ wait_for_dev()
fi
}
-cmd_jq()
-{
- local cmd=$1
- local jq_exp=$2
- local jq_opts=$3
- local ret
- local output
-
- output="$($cmd)"
- # it the command fails, return error right away
- ret=$?
- if [[ $ret -ne 0 ]]; then
- return $ret
- fi
- output=$(echo $output | jq -r $jq_opts "$jq_exp")
- ret=$?
- if [[ $ret -ne 0 ]]; then
- return $ret
- fi
- echo $output
- # return success only in case of non-empty output
- [ ! -z "$output" ]
-}
-
pre_cleanup()
{
if [ "${PAUSE_ON_CLEANUP}" = "yes" ]; then
@@ -623,6 +599,12 @@ vrf_cleanup()
ip -4 rule del pref 32765
}
+adf_vrf_prepare()
+{
+ vrf_prepare
+ defer vrf_cleanup
+}
+
__last_tb_id=0
declare -A __TB_IDS
@@ -735,6 +717,12 @@ simple_if_fini()
vrf_destroy $vrf_name
}
+adf_simple_if_init()
+{
+ simple_if_init "$@"
+ defer simple_if_fini "$@"
+}
+
tunnel_create()
{
local name=$1; shift
@@ -1035,6 +1023,12 @@ forwarding_restore()
sysctl_restore net.ipv4.conf.all.forwarding
}
+adf_forwarding_enable()
+{
+ forwarding_enable
+ defer forwarding_restore
+}
+
declare -A MTU_ORIG
mtu_set()
{
@@ -1291,8 +1285,8 @@ ping_do()
vrf_name=$(master_name_get $if_name)
ip vrf exec $vrf_name \
- $PING $args $dip -c $PING_COUNT -i 0.1 \
- -w $PING_TIMEOUT &> /dev/null
+ $PING $args -c $PING_COUNT -i 0.1 \
+ -w $PING_TIMEOUT $dip &> /dev/null
}
ping_test()
@@ -1322,8 +1316,8 @@ ping6_do()
vrf_name=$(master_name_get $if_name)
ip vrf exec $vrf_name \
- $PING6 $args $dip -c $PING_COUNT -i 0.1 \
- -w $PING_TIMEOUT &> /dev/null
+ $PING6 $args -c $PING_COUNT -i 0.1 \
+ -w $PING_TIMEOUT $dip &> /dev/null
}
ping6_test()
diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q_lag.sh b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q_lag.sh
index a20d22d1df36..8d4ae6c952a1 100755
--- a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q_lag.sh
+++ b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q_lag.sh
@@ -238,7 +238,7 @@ test_lag_slave()
ip neigh flush dev br1
setup_wait_dev $up_dev
setup_wait_dev $host_dev
- $ARPING -I br1 192.0.2.130 -qfc 1
+ $ARPING -I br1 -qfc 1 192.0.2.130
sleep 2
mirror_test vrf-h1 192.0.2.1 192.0.2.18 $host_dev 1 ">= 10"
diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh b/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh
index 1b902cc579f6..a21c771908b3 100755
--- a/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh
+++ b/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh
@@ -196,7 +196,7 @@ test_span_gre_forbidden_egress()
bridge vlan add dev $swp3 vid 555
# Re-prime FDB
- $ARPING -I br1.555 192.0.2.130 -fqc 1
+ $ARPING -I br1.555 -fqc 1 192.0.2.130
sleep 1
quick_test_span_gre_dir $tundev
@@ -290,7 +290,7 @@ test_span_gre_fdb_roaming()
bridge fdb del dev $swp2 $h3mac vlan 555 master 2>/dev/null
# Re-prime FDB
- $ARPING -I br1.555 192.0.2.130 -fqc 1
+ $ARPING -I br1.555 -fqc 1 192.0.2.130
sleep 1
quick_test_span_gre_dir $tundev
diff --git a/tools/testing/selftests/net/forwarding/sch_ets_core.sh b/tools/testing/selftests/net/forwarding/sch_ets_core.sh
index 8f9922c695b0..0453210271dc 100644
--- a/tools/testing/selftests/net/forwarding/sch_ets_core.sh
+++ b/tools/testing/selftests/net/forwarding/sch_ets_core.sh
@@ -165,8 +165,7 @@ h1_create()
{
local i;
- simple_if_init $h1
- defer simple_if_fini $h1
+ adf_simple_if_init $h1
mtu_set $h1 9900
defer mtu_restore $h1
@@ -182,8 +181,7 @@ h2_create()
{
local i
- simple_if_init $h2
- defer simple_if_fini $h2
+ adf_simple_if_init $h2
mtu_set $h2 9900
defer mtu_restore $h2
@@ -251,8 +249,7 @@ setup_prepare()
put=$swp2
hut=$h2
- vrf_prepare
- defer vrf_cleanup
+ adf_vrf_prepare
h1_create
h2_create
diff --git a/tools/testing/selftests/net/forwarding/sch_red.sh b/tools/testing/selftests/net/forwarding/sch_red.sh
index af166662b78a..f2a3d9254642 100755
--- a/tools/testing/selftests/net/forwarding/sch_red.sh
+++ b/tools/testing/selftests/net/forwarding/sch_red.sh
@@ -52,8 +52,7 @@ PKTSZ=1400
h1_create()
{
- simple_if_init $h1 192.0.2.1/28
- defer simple_if_fini $h1 192.0.2.1/28
+ adf_simple_if_init $h1 192.0.2.1/28
mtu_set $h1 10000
defer mtu_restore $h1
@@ -65,8 +64,7 @@ h1_create()
h2_create()
{
- simple_if_init $h2 192.0.2.2/28
- defer simple_if_fini $h2 192.0.2.2/28
+ adf_simple_if_init $h2 192.0.2.2/28
mtu_set $h2 10000
defer mtu_restore $h2
@@ -74,8 +72,7 @@ h2_create()
h3_create()
{
- simple_if_init $h3 192.0.2.3/28
- defer simple_if_fini $h3 192.0.2.3/28
+ adf_simple_if_init $h3 192.0.2.3/28
mtu_set $h3 10000
defer mtu_restore $h3
@@ -125,8 +122,7 @@ setup_prepare()
h3_mac=$(mac_get $h3)
- vrf_prepare
- defer vrf_cleanup
+ adf_vrf_prepare
h1_create
h2_create
diff --git a/tools/testing/selftests/net/forwarding/sch_tbf_core.sh b/tools/testing/selftests/net/forwarding/sch_tbf_core.sh
index ec309a5086bc..070c17faa9e4 100644
--- a/tools/testing/selftests/net/forwarding/sch_tbf_core.sh
+++ b/tools/testing/selftests/net/forwarding/sch_tbf_core.sh
@@ -59,8 +59,7 @@ host_create()
local dev=$1; shift
local host=$1; shift
- simple_if_init $dev
- defer simple_if_fini $dev
+ adf_simple_if_init $dev
mtu_set $dev 10000
defer mtu_restore $dev
@@ -149,8 +148,7 @@ setup_prepare()
h2_mac=$(mac_get $h2)
- vrf_prepare
- defer vrf_cleanup
+ adf_vrf_prepare
h1_create
h2_create
diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1q_mc_ul.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1q_mc_ul.sh
index 462db0b603e7..6a570d256e07 100755
--- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1q_mc_ul.sh
+++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1q_mc_ul.sh
@@ -119,16 +119,15 @@ source lib.sh
h1_create()
{
- simple_if_init "$h1"
- defer simple_if_fini "$h1"
+ adf_simple_if_init "$h1"
- ip_link_add "$h1.10" master "v$h1" link "$h1" type vlan id 10
- ip_link_set_up "$h1.10"
- ip_addr_add "$h1.10" 192.0.2.1/28
+ adf_ip_link_add "$h1.10" master "v$h1" link "$h1" type vlan id 10
+ adf_ip_link_set_up "$h1.10"
+ adf_ip_addr_add "$h1.10" 192.0.2.1/28
- ip_link_add "$h1.20" master "v$h1" link "$h1" type vlan id 20
- ip_link_set_up "$h1.20"
- ip_addr_add "$h1.20" 2001:db8:1::1/64
+ adf_ip_link_add "$h1.20" master "v$h1" link "$h1" type vlan id 20
+ adf_ip_link_set_up "$h1.20"
+ adf_ip_addr_add "$h1.20" 2001:db8:1::1/64
}
install_capture()
@@ -152,51 +151,51 @@ install_capture()
h2_create()
{
# $h2
- ip_link_set_up "$h2"
+ adf_ip_link_set_up "$h2"
# H2
vrf_create "v$h2"
defer vrf_destroy "v$h2"
- ip_link_set_up "v$h2"
+ adf_ip_link_set_up "v$h2"
# br2
- ip_link_add br2 type bridge vlan_filtering 0 mcast_snooping 0
- ip_link_set_master br2 "v$h2"
- ip_link_set_up br2
+ adf_ip_link_add br2 type bridge vlan_filtering 0 mcast_snooping 0
+ adf_ip_link_set_master br2 "v$h2"
+ adf_ip_link_set_up br2
# $h2
- ip_link_set_master "$h2" br2
+ adf_ip_link_set_master "$h2" br2
install_capture "$h2"
# v1$h2
- ip_link_set_up "v1$h2"
- ip_link_set_master "v1$h2" br2
+ adf_ip_link_set_up "v1$h2"
+ adf_ip_link_set_master "v1$h2" br2
}
h3_create()
{
# $h3
- ip_link_set_up "$h3"
+ adf_ip_link_set_up "$h3"
# H3
vrf_create "v$h3"
defer vrf_destroy "v$h3"
- ip_link_set_up "v$h3"
+ adf_ip_link_set_up "v$h3"
# br3
- ip_link_add br3 type bridge vlan_filtering 0 mcast_snooping 0
- ip_link_set_master br3 "v$h3"
- ip_link_set_up br3
+ adf_ip_link_add br3 type bridge vlan_filtering 0 mcast_snooping 0
+ adf_ip_link_set_master br3 "v$h3"
+ adf_ip_link_set_up br3
# $h3
- ip_link_set_master "$h3" br3
+ adf_ip_link_set_master "$h3" br3
install_capture "$h3"
# v1$h3
- ip_link_set_up "v1$h3"
- ip_link_set_master "v1$h3" br3
+ adf_ip_link_set_up "v1$h3"
+ adf_ip_link_set_master "v1$h3" br3
}
switch_create()
@@ -205,35 +204,35 @@ switch_create()
# br1
swp1_mac=$(mac_get "$swp1")
- ip_link_add br1 type bridge vlan_filtering 1 \
+ adf_ip_link_add br1 type bridge vlan_filtering 1 \
vlan_default_pvid 0 mcast_snooping 0
- ip_link_set_addr br1 "$swp1_mac"
- ip_link_set_up br1
+ adf_ip_link_set_addr br1 "$swp1_mac"
+ adf_ip_link_set_up br1
# A dummy to force the IPv6 OIF=0 test to install a suitable MC route on
# $IPMR to be deterministic. Also used for the IPv6 RX!=TX ping test.
- ip_link_add "X$IPMR" up type dummy
+ adf_ip_link_add "X$IPMR" up type dummy
# IPMR
- ip_link_add "$IPMR" up type dummy
- ip_addr_add "$IPMR" 192.0.2.100/28
- ip_addr_add "$IPMR" 2001:db8:4::1/64
+ adf_ip_link_add "$IPMR" up type dummy
+ adf_ip_addr_add "$IPMR" 192.0.2.100/28
+ adf_ip_addr_add "$IPMR" 2001:db8:4::1/64
# $swp1
- ip_link_set_up "$swp1"
- ip_link_set_master "$swp1" br1
- bridge_vlan_add vid 10 dev "$swp1"
- bridge_vlan_add vid 20 dev "$swp1"
+ adf_ip_link_set_up "$swp1"
+ adf_ip_link_set_master "$swp1" br1
+ adf_bridge_vlan_add vid 10 dev "$swp1"
+ adf_bridge_vlan_add vid 20 dev "$swp1"
# $swp2
- ip_link_set_up "$swp2"
- ip_addr_add "$swp2" 192.0.2.33/28
- ip_addr_add "$swp2" 2001:db8:2::1/64
+ adf_ip_link_set_up "$swp2"
+ adf_ip_addr_add "$swp2" 192.0.2.33/28
+ adf_ip_addr_add "$swp2" 2001:db8:2::1/64
# $swp3
- ip_link_set_up "$swp3"
- ip_addr_add "$swp3" 192.0.2.65/28
- ip_addr_add "$swp3" 2001:db8:3::1/64
+ adf_ip_link_set_up "$swp3"
+ adf_ip_addr_add "$swp3" 192.0.2.65/28
+ adf_ip_addr_add "$swp3" 2001:db8:3::1/64
}
vx_create()
@@ -241,11 +240,11 @@ vx_create()
local name=$1; shift
local vid=$1; shift
- ip_link_add "$name" up type vxlan dstport "$VXPORT" \
+ adf_ip_link_add "$name" up type vxlan dstport "$VXPORT" \
nolearning noudpcsum tos inherit ttl 16 \
"$@"
- ip_link_set_master "$name" br1
- bridge_vlan_add vid "$vid" dev "$name" pvid untagged
+ adf_ip_link_set_master "$name" br1
+ adf_bridge_vlan_add vid "$vid" dev "$name" pvid untagged
}
export -f vx_create
@@ -290,39 +289,38 @@ ns_init_common()
local ipv6_host=$1; shift
# v2$h2 / v2$h3
- ip_link_set_up "$if_in"
- ip_addr_add "$if_in" "$ipv4_in"
- ip_addr_add "$if_in" "$ipv6_in"
+ adf_ip_link_set_up "$if_in"
+ adf_ip_addr_add "$if_in" "$ipv4_in"
+ adf_ip_addr_add "$if_in" "$ipv6_in"
# br1
- ip_link_add br1 type bridge vlan_filtering 1 \
+ adf_ip_link_add br1 type bridge vlan_filtering 1 \
vlan_default_pvid 0 mcast_snooping 0
- ip_link_set_up br1
+ adf_ip_link_set_up br1
# vx10, vx20
vx10_create local "${ipv4_in%/*}" group "$GROUP4" dev "$if_in"
vx20_create local "${ipv6_in%/*}" group "$GROUP6" dev "$if_in"
# w1
- ip_link_add w1 type veth peer name w2
- ip_link_set_master w1 br1
- ip_link_set_up w1
- bridge_vlan_add vid 10 dev w1
- bridge_vlan_add vid 20 dev w1
+ adf_ip_link_add w1 type veth peer name w2
+ adf_ip_link_set_master w1 br1
+ adf_ip_link_set_up w1
+ adf_bridge_vlan_add vid 10 dev w1
+ adf_bridge_vlan_add vid 20 dev w1
# w2
- simple_if_init w2
- defer simple_if_fini w2
+ adf_simple_if_init w2
# w2.10
- ip_link_add w2.10 master vw2 link w2 type vlan id 10
- ip_link_set_up w2.10
- ip_addr_add w2.10 "$ipv4_host"
+ adf_ip_link_add w2.10 master vw2 link w2 type vlan id 10
+ adf_ip_link_set_up w2.10
+ adf_ip_addr_add w2.10 "$ipv4_host"
# w2.20
- ip_link_add w2.20 master vw2 link w2 type vlan id 20
- ip_link_set_up w2.20
- ip_addr_add w2.20 "$ipv6_host"
+ adf_ip_link_add w2.20 master vw2 link w2 type vlan id 20
+ adf_ip_link_set_up w2.20
+ adf_ip_addr_add w2.20 "$ipv6_host"
}
export -f ns_init_common
@@ -371,14 +369,11 @@ setup_prepare()
swp3=${NETIFS[p5]}
h3=${NETIFS[p6]}
- vrf_prepare
- defer vrf_cleanup
+ adf_vrf_prepare
+ adf_forwarding_enable
- forwarding_enable
- defer forwarding_restore
-
- ip_link_add "v1$h2" type veth peer name "v2$h2"
- ip_link_add "v1$h3" type veth peer name "v2$h3"
+ adf_ip_link_add "v1$h2" type veth peer name "v2$h2"
+ adf_ip_link_add "v1$h3" type veth peer name "v2$h3"
h1_create
h2_create
@@ -720,7 +715,7 @@ ipv4_mcroute_fdb_oif0_sep()
{
adf_install_sg_sep
- ip_addr_add lo 192.0.2.120/28
+ adf_ip_addr_add lo 192.0.2.120/28
vx10_create_wait local 192.0.2.120 group "$GROUP4" dev "$IPMR" mcroute
bridge fdb del dev vx10 00:00:00:00:00:00
bridge fdb add dev vx10 00:00:00:00:00:00 self static dst "$GROUP4"
@@ -731,7 +726,7 @@ ipv4_mcroute_fdb_oif0_sep_rx()
{
adf_install_sg_sep_rx lo
- ip_addr_add lo 192.0.2.120/28
+ adf_ip_addr_add lo 192.0.2.120/28
vx10_create_wait local 192.0.2.120 group "$GROUP4" dev "$IPMR" mcroute
bridge fdb del dev vx10 00:00:00:00:00:00
bridge fdb add dev vx10 00:00:00:00:00:00 self static dst "$GROUP4"
@@ -742,7 +737,7 @@ ipv4_mcroute_fdb_sep_rx()
{
adf_install_sg_sep_rx lo
- ip_addr_add lo 192.0.2.120/28
+ adf_ip_addr_add lo 192.0.2.120/28
vx10_create_wait local 192.0.2.120 group "$GROUP4" dev "$IPMR" mcroute
bridge fdb del dev vx10 00:00:00:00:00:00
bridge fdb add \
@@ -754,7 +749,7 @@ ipv6_mcroute_fdb_sep_rx()
{
adf_install_sg_sep_rx "X$IPMR"
- ip_addr_add "X$IPMR" 2001:db8:5::1/64
+ adf_ip_addr_add "X$IPMR" 2001:db8:5::1/64
vx20_create_wait local 2001:db8:5::1 group "$GROUP6" dev "$IPMR" mcroute
bridge -6 fdb del dev vx20 00:00:00:00:00:00
bridge -6 fdb add dev vx20 00:00:00:00:00:00 \
diff --git a/tools/testing/selftests/net/forwarding/vxlan_reserved.sh b/tools/testing/selftests/net/forwarding/vxlan_reserved.sh
index 46c31794b91b..709845123727 100755
--- a/tools/testing/selftests/net/forwarding/vxlan_reserved.sh
+++ b/tools/testing/selftests/net/forwarding/vxlan_reserved.sh
@@ -47,8 +47,7 @@ source lib.sh
h1_create()
{
- simple_if_init $h1 192.0.2.1/28
- defer simple_if_fini $h1 192.0.2.1/28
+ adf_simple_if_init $h1 192.0.2.1/28
tc qdisc add dev $h1 clsact
defer tc qdisc del dev $h1 clsact
@@ -60,24 +59,23 @@ h1_create()
switch_create()
{
- ip_link_add br1 type bridge vlan_filtering 0 mcast_snooping 0
+ adf_ip_link_add br1 type bridge vlan_filtering 0 mcast_snooping 0
# Make sure the bridge uses the MAC address of the local port and not
# that of the VxLAN's device.
- ip_link_set_addr br1 $(mac_get $swp1)
- ip_link_set_up br1
+ adf_ip_link_set_addr br1 $(mac_get $swp1)
+ adf_ip_link_set_up br1
- ip_link_set_up $rp1
- ip_addr_add $rp1 192.0.2.17/28
- ip_route_add 192.0.2.32/28 nexthop via 192.0.2.18
+ adf_ip_link_set_up $rp1
+ adf_ip_addr_add $rp1 192.0.2.17/28
+ adf_ip_route_add 192.0.2.32/28 nexthop via 192.0.2.18
- ip_link_set_master $swp1 br1
- ip_link_set_up $swp1
+ adf_ip_link_set_master $swp1 br1
+ adf_ip_link_set_up $swp1
}
vrp2_create()
{
- simple_if_init $rp2 192.0.2.18/28
- defer simple_if_fini $rp2 192.0.2.18/28
+ adf_simple_if_init $rp2 192.0.2.18/28
}
setup_prepare()
@@ -88,11 +86,8 @@ setup_prepare()
rp1=${NETIFS[p3]}
rp2=${NETIFS[p4]}
- vrf_prepare
- defer vrf_cleanup
-
- forwarding_enable
- defer forwarding_restore
+ adf_vrf_prepare
+ adf_forwarding_enable
h1_create
switch_create
@@ -200,10 +195,10 @@ vxlan_ping_do()
vxlan_device_add()
{
- ip_link_add vx1 up type vxlan id 1000 \
+ adf_ip_link_add vx1 up type vxlan id 1000 \
local 192.0.2.17 dstport "$VXPORT" \
nolearning noudpcsum tos inherit ttl 100 "$@"
- ip_link_set_master vx1 br1
+ adf_ip_link_set_master vx1 br1
}
vxlan_all_reserved_bits()
diff --git a/tools/testing/selftests/net/gro.c b/tools/testing/selftests/net/gro.c
index d5824eadea10..2b1d9f2b3e9e 100644
--- a/tools/testing/selftests/net/gro.c
+++ b/tools/testing/selftests/net/gro.c
@@ -93,6 +93,7 @@ static bool tx_socket = true;
static int tcp_offset = -1;
static int total_hdr_len = -1;
static int ethhdr_proto = -1;
+static bool ipip;
static const int num_flush_id_cases = 6;
static void vlog(const char *fmt, ...)
@@ -114,7 +115,9 @@ static void setup_sock_filter(int fd)
int ipproto_off, opt_ipproto_off;
int next_off;
- if (proto == PF_INET)
+ if (ipip)
+ next_off = sizeof(struct iphdr) + offsetof(struct iphdr, protocol);
+ else if (proto == PF_INET)
next_off = offsetof(struct iphdr, protocol);
else
next_off = offsetof(struct ipv6hdr, nexthdr);
@@ -244,7 +247,7 @@ static void fill_datalinklayer(void *buf)
eth->h_proto = ethhdr_proto;
}
-static void fill_networklayer(void *buf, int payload_len)
+static void fill_networklayer(void *buf, int payload_len, int protocol)
{
struct ipv6hdr *ip6h = buf;
struct iphdr *iph = buf;
@@ -254,7 +257,7 @@ static void fill_networklayer(void *buf, int payload_len)
ip6h->version = 6;
ip6h->payload_len = htons(sizeof(struct tcphdr) + payload_len);
- ip6h->nexthdr = IPPROTO_TCP;
+ ip6h->nexthdr = protocol;
ip6h->hop_limit = 8;
if (inet_pton(AF_INET6, addr6_src, &ip6h->saddr) != 1)
error(1, errno, "inet_pton source ip6");
@@ -266,7 +269,7 @@ static void fill_networklayer(void *buf, int payload_len)
iph->version = 4;
iph->ihl = 5;
iph->ttl = 8;
- iph->protocol = IPPROTO_TCP;
+ iph->protocol = protocol;
iph->tot_len = htons(sizeof(struct tcphdr) +
payload_len + sizeof(struct iphdr));
iph->frag_off = htons(0x4000); /* DF = 1, MF = 0 */
@@ -313,9 +316,19 @@ static void create_packet(void *buf, int seq_offset, int ack_offset,
{
memset(buf, 0, total_hdr_len);
memset(buf + total_hdr_len, 'a', payload_len);
+
fill_transportlayer(buf + tcp_offset, seq_offset, ack_offset,
payload_len, fin);
- fill_networklayer(buf + ETH_HLEN, payload_len);
+
+ if (ipip) {
+ fill_networklayer(buf + ETH_HLEN, payload_len + sizeof(struct iphdr),
+ IPPROTO_IPIP);
+ fill_networklayer(buf + ETH_HLEN + sizeof(struct iphdr),
+ payload_len, IPPROTO_TCP);
+ } else {
+ fill_networklayer(buf + ETH_HLEN, payload_len, IPPROTO_TCP);
+ }
+
fill_datalinklayer(buf);
}
@@ -416,6 +429,13 @@ static void recompute_packet(char *buf, char *no_ext, int extlen)
iph->tot_len = htons(ntohs(iph->tot_len) + extlen);
iph->check = 0;
iph->check = checksum_fold(iph, sizeof(struct iphdr), 0);
+
+ if (ipip) {
+ iph += 1;
+ iph->tot_len = htons(ntohs(iph->tot_len) + extlen);
+ iph->check = 0;
+ iph->check = checksum_fold(iph, sizeof(struct iphdr), 0);
+ }
} else {
ip6h->payload_len = htons(ntohs(ip6h->payload_len) + extlen);
}
@@ -670,7 +690,7 @@ static void send_flush_id_case(int fd, struct sockaddr_ll *daddr, int tcase)
iph2->id = htons(9);
break;
- case 3: /* DF=0, Fixed - should not coalesce */
+ case 3: /* DF=0, Fixed - should coalesce */
iph1->frag_off &= ~htons(IP_DF);
iph1->id = htons(8);
@@ -777,7 +797,7 @@ static void send_fragment4(int fd, struct sockaddr_ll *daddr)
*/
memset(buf + total_hdr_len, 'a', PAYLOAD_LEN * 2);
fill_transportlayer(buf + tcp_offset, PAYLOAD_LEN, 0, PAYLOAD_LEN * 2, 0);
- fill_networklayer(buf + ETH_HLEN, PAYLOAD_LEN);
+ fill_networklayer(buf + ETH_HLEN, PAYLOAD_LEN, IPPROTO_TCP);
fill_datalinklayer(buf);
iph->frag_off = htons(0x6000); // DF = 1, MF = 1
@@ -1071,7 +1091,7 @@ static void gro_sender(void)
* and min ipv6hdr size. Like MAX_HDR_SIZE,
* MAX_PAYLOAD is defined with the larger header of the two.
*/
- int offset = proto == PF_INET ? 20 : 0;
+ int offset = (proto == PF_INET && !ipip) ? 20 : 0;
int remainder = (MAX_PAYLOAD + offset) % MSS;
send_large(txfd, &daddr, remainder);
@@ -1188,10 +1208,9 @@ static void gro_receiver(void)
correct_payload[0] = PAYLOAD_LEN * 2;
check_recv_pkts(rxfd, correct_payload, 1);
- printf("DF=0, Fixed - should not coalesce: ");
- correct_payload[0] = PAYLOAD_LEN;
- correct_payload[1] = PAYLOAD_LEN;
- check_recv_pkts(rxfd, correct_payload, 2);
+ printf("DF=0, Fixed - should coalesce: ");
+ correct_payload[0] = PAYLOAD_LEN * 2;
+ check_recv_pkts(rxfd, correct_payload, 1);
printf("DF=1, 2 Incrementing and one fixed - should coalesce only first 2 packets: ");
correct_payload[0] = PAYLOAD_LEN * 2;
@@ -1222,7 +1241,7 @@ static void gro_receiver(void)
check_recv_pkts(rxfd, correct_payload, 2);
}
} else if (strcmp(testname, "large") == 0) {
- int offset = proto == PF_INET ? 20 : 0;
+ int offset = (proto == PF_INET && !ipip) ? 20 : 0;
int remainder = (MAX_PAYLOAD + offset) % MSS;
correct_payload[0] = (MAX_PAYLOAD + offset);
@@ -1251,6 +1270,7 @@ static void parse_args(int argc, char **argv)
{ "iface", required_argument, NULL, 'i' },
{ "ipv4", no_argument, NULL, '4' },
{ "ipv6", no_argument, NULL, '6' },
+ { "ipip", no_argument, NULL, 'e' },
{ "rx", no_argument, NULL, 'r' },
{ "saddr", required_argument, NULL, 's' },
{ "smac", required_argument, NULL, 'S' },
@@ -1260,7 +1280,7 @@ static void parse_args(int argc, char **argv)
};
int c;
- while ((c = getopt_long(argc, argv, "46d:D:i:rs:S:t:v", opts, NULL)) != -1) {
+ while ((c = getopt_long(argc, argv, "46d:D:ei:rs:S:t:v", opts, NULL)) != -1) {
switch (c) {
case '4':
proto = PF_INET;
@@ -1270,6 +1290,11 @@ static void parse_args(int argc, char **argv)
proto = PF_INET6;
ethhdr_proto = htons(ETH_P_IPV6);
break;
+ case 'e':
+ ipip = true;
+ proto = PF_INET;
+ ethhdr_proto = htons(ETH_P_IP);
+ break;
case 'd':
addr4_dst = addr6_dst = optarg;
break;
@@ -1305,7 +1330,10 @@ int main(int argc, char **argv)
{
parse_args(argc, argv);
- if (proto == PF_INET) {
+ if (ipip) {
+ tcp_offset = ETH_HLEN + sizeof(struct iphdr) * 2;
+ total_hdr_len = tcp_offset + sizeof(struct tcphdr);
+ } else if (proto == PF_INET) {
tcp_offset = ETH_HLEN + sizeof(struct iphdr);
total_hdr_len = tcp_offset + sizeof(struct tcphdr);
} else if (proto == PF_INET6) {
diff --git a/tools/testing/selftests/net/gro.sh b/tools/testing/selftests/net/gro.sh
index 9e3f186bc2a1..4c5144c6f652 100755
--- a/tools/testing/selftests/net/gro.sh
+++ b/tools/testing/selftests/net/gro.sh
@@ -4,7 +4,7 @@
readonly SERVER_MAC="aa:00:00:00:00:02"
readonly CLIENT_MAC="aa:00:00:00:00:01"
readonly TESTS=("data" "ack" "flags" "tcp" "ip" "large")
-readonly PROTOS=("ipv4" "ipv6")
+readonly PROTOS=("ipv4" "ipv6" "ipip")
dev=""
test="all"
proto="ipv4"
diff --git a/tools/testing/selftests/net/ipv6_fragmentation.c b/tools/testing/selftests/net/ipv6_fragmentation.c
new file mode 100644
index 000000000000..267ef62b5c72
--- /dev/null
+++ b/tools/testing/selftests/net/ipv6_fragmentation.c
@@ -0,0 +1,114 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Author: Brett A C Sheffield <bacs@librecast.net>
+ *
+ * Kernel selftest for the IPv6 fragmentation regression which affected stable
+ * kernels:
+ *
+ * https://lore.kernel.org/stable/aElivdUXqd1OqgMY@karahi.gladserv.com
+ *
+ * Commit: a18dfa9925b9 ("ipv6: save dontfrag in cork") was backported to stable
+ * without some prerequisite commits.
+ *
+ * This caused a regression when sending IPv6 UDP packets by preventing
+ * fragmentation and instead returning -1 (EMSGSIZE).
+ *
+ * This selftest demonstrates the issue by sending an IPv6 UDP packet to
+ * localhost (::1) on the loopback interface from the autoconfigured link-local
+ * address.
+ *
+ * sendmsg(2) returns bytes sent correctly on a working kernel, and returns -1
+ * (EMSGSIZE) when the regression is present.
+ *
+ * The regression was not present in the mainline kernel, but add this test to
+ * catch similar breakage in future.
+ */
+
+#define _GNU_SOURCE
+
+#include <error.h>
+#include <net/if.h>
+#include <netinet/in.h>
+#include <sched.h>
+#include <stdio.h>
+#include <sys/ioctl.h>
+#include <sys/socket.h>
+#include <unistd.h>
+#include "../kselftest.h"
+
+#define MTU 1500
+#define LARGER_THAN_MTU 8192
+
+static void setup(void)
+{
+ struct ifreq ifr = {
+ .ifr_name = "lo"
+ };
+ int ctl;
+
+ /* we need to set MTU, so do this in a namespace to play nicely */
+ if (unshare(CLONE_NEWNET) == -1)
+ error(KSFT_FAIL, errno, "unshare");
+
+ ctl = socket(AF_LOCAL, SOCK_STREAM, 0);
+ if (ctl == -1)
+ error(KSFT_FAIL, errno, "socket");
+
+ /* ensure MTU is smaller than what we plan to send */
+ ifr.ifr_mtu = MTU;
+ if (ioctl(ctl, SIOCSIFMTU, &ifr) == -1)
+ error(KSFT_FAIL, errno, "ioctl: set MTU");
+
+ /* bring up interface */
+ if (ioctl(ctl, SIOCGIFFLAGS, &ifr) == -1)
+ error(KSFT_FAIL, errno, "ioctl SIOCGIFFLAGS");
+ ifr.ifr_flags = ifr.ifr_flags | IFF_UP;
+ if (ioctl(ctl, SIOCSIFFLAGS, &ifr) == -1)
+ error(KSFT_FAIL, errno, "ioctl: bring interface up");
+
+ if (close(ctl) == -1)
+ error(KSFT_FAIL, errno, "close");
+}
+
+int main(void)
+{
+ struct in6_addr addr = {
+ .s6_addr[15] = 0x01, /* ::1 */
+ };
+ struct sockaddr_in6 sa = {
+ .sin6_family = AF_INET6,
+ .sin6_addr = addr,
+ .sin6_port = htons(9) /* port 9/udp (DISCARD) */
+ };
+ static char buf[LARGER_THAN_MTU] = {0};
+ struct iovec iov = { .iov_base = buf, .iov_len = sizeof(buf) };
+ struct msghdr msg = {
+ .msg_iov = &iov,
+ .msg_iovlen = 1,
+ .msg_name = (struct sockaddr *)&sa,
+ .msg_namelen = sizeof(sa),
+ };
+ ssize_t rc;
+ int s;
+
+ printf("Testing IPv6 fragmentation\n");
+ setup();
+ s = socket(AF_INET6, SOCK_DGRAM, 0);
+send_again:
+ rc = sendmsg(s, &msg, 0);
+ if (rc == -1) {
+ /* if interface wasn't ready, try again */
+ if (errno == EADDRNOTAVAIL) {
+ usleep(1000);
+ goto send_again;
+ }
+ error(KSFT_FAIL, errno, "sendmsg");
+ } else if (rc != LARGER_THAN_MTU) {
+ error(KSFT_FAIL, errno, "sendmsg returned %zi, expected %i",
+ rc, LARGER_THAN_MTU);
+ }
+ printf("[PASS] sendmsg() returned %zi\n", rc);
+ if (close(s) == -1)
+ error(KSFT_FAIL, errno, "close");
+ return KSFT_PASS;
+}
diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh
index c7add0dc4c60..feba4ef69a54 100644
--- a/tools/testing/selftests/net/lib.sh
+++ b/tools/testing/selftests/net/lib.sh
@@ -543,31 +543,31 @@ require_command()
fi
}
-ip_link_add()
+adf_ip_link_add()
{
local name=$1; shift
- ip link add name "$name" "$@"
- defer ip link del dev "$name"
+ ip link add name "$name" "$@" && \
+ defer ip link del dev "$name"
}
-ip_link_set_master()
+adf_ip_link_set_master()
{
local member=$1; shift
local master=$1; shift
- ip link set dev "$member" master "$master"
- defer ip link set dev "$member" nomaster
+ ip link set dev "$member" master "$master" && \
+ defer ip link set dev "$member" nomaster
}
-ip_link_set_addr()
+adf_ip_link_set_addr()
{
local name=$1; shift
local addr=$1; shift
local old_addr=$(mac_get "$name")
- ip link set dev "$name" address "$addr"
- defer ip link set dev "$name" address "$old_addr"
+ ip link set dev "$name" address "$addr" && \
+ defer ip link set dev "$name" address "$old_addr"
}
ip_link_has_flag()
@@ -585,44 +585,44 @@ ip_link_is_up()
ip_link_has_flag "$1" UP
}
-ip_link_set_up()
+adf_ip_link_set_up()
{
local name=$1; shift
if ! ip_link_is_up "$name"; then
- ip link set dev "$name" up
- defer ip link set dev "$name" down
+ ip link set dev "$name" up && \
+ defer ip link set dev "$name" down
fi
}
-ip_link_set_down()
+adf_ip_link_set_down()
{
local name=$1; shift
if ip_link_is_up "$name"; then
- ip link set dev "$name" down
- defer ip link set dev "$name" up
+ ip link set dev "$name" down && \
+ defer ip link set dev "$name" up
fi
}
-ip_addr_add()
+adf_ip_addr_add()
{
local name=$1; shift
- ip addr add dev "$name" "$@"
- defer ip addr del dev "$name" "$@"
+ ip addr add dev "$name" "$@" && \
+ defer ip addr del dev "$name" "$@"
}
-ip_route_add()
+adf_ip_route_add()
{
- ip route add "$@"
- defer ip route del "$@"
+ ip route add "$@" && \
+ defer ip route del "$@"
}
-bridge_vlan_add()
+adf_bridge_vlan_add()
{
- bridge vlan add "$@"
- defer bridge vlan del "$@"
+ bridge vlan add "$@" && \
+ defer bridge vlan del "$@"
}
wait_local_port_listen()
@@ -645,3 +645,27 @@ wait_local_port_listen()
sleep 0.1
done
}
+
+cmd_jq()
+{
+ local cmd=$1
+ local jq_exp=$2
+ local jq_opts=$3
+ local ret
+ local output
+
+ output="$($cmd)"
+ # it the command fails, return error right away
+ ret=$?
+ if [[ $ret -ne 0 ]]; then
+ return $ret
+ fi
+ output=$(echo $output | jq -r $jq_opts "$jq_exp")
+ ret=$?
+ if [[ $ret -ne 0 ]]; then
+ return $ret
+ fi
+ echo $output
+ # return success only in case of non-empty output
+ [ ! -z "$output" ]
+}
diff --git a/tools/testing/selftests/net/lib/py/__init__.py b/tools/testing/selftests/net/lib/py/__init__.py
index 02be28dcc089..997b85cc216a 100644
--- a/tools/testing/selftests/net/lib/py/__init__.py
+++ b/tools/testing/selftests/net/lib/py/__init__.py
@@ -6,4 +6,4 @@ from .netns import NetNS, NetNSEnter
from .nsim import *
from .utils import *
from .ynl import NlError, YnlFamily, EthtoolFamily, NetdevFamily, RtnlFamily, RtnlAddrFamily
-from .ynl import NetshaperFamily, DevlinkFamily
+from .ynl import NetshaperFamily, DevlinkFamily, PSPFamily
diff --git a/tools/testing/selftests/net/lib/py/ksft.py b/tools/testing/selftests/net/lib/py/ksft.py
index 8e35ed12ed9e..83b1574f7719 100644
--- a/tools/testing/selftests/net/lib/py/ksft.py
+++ b/tools/testing/selftests/net/lib/py/ksft.py
@@ -72,6 +72,11 @@ def ksft_true(a, comment=""):
_fail("Check failed", a, "does not eval to True", comment)
+def ksft_not_none(a, comment=""):
+ if a is None:
+ _fail("Check failed", a, "is None", comment)
+
+
def ksft_in(a, b, comment=""):
if a not in b:
_fail("Check failed", a, "not in", b, comment)
@@ -92,6 +97,11 @@ def ksft_ge(a, b, comment=""):
_fail("Check failed", a, "<", b, comment)
+def ksft_gt(a, b, comment=""):
+ if a <= b:
+ _fail("Check failed", a, "<=", b, comment)
+
+
def ksft_lt(a, b, comment=""):
if a >= b:
_fail("Check failed", a, ">=", b, comment)
diff --git a/tools/testing/selftests/net/lib/py/utils.py b/tools/testing/selftests/net/lib/py/utils.py
index f395c90fb0f1..cb40ecef9456 100644
--- a/tools/testing/selftests/net/lib/py/utils.py
+++ b/tools/testing/selftests/net/lib/py/utils.py
@@ -1,9 +1,7 @@
# SPDX-License-Identifier: GPL-2.0
-import errno
import json as _json
import os
-import random
import re
import select
import socket
@@ -21,17 +19,19 @@ def fd_read_timeout(fd, timeout):
rlist, _, _ = select.select([fd], [], [], timeout)
if rlist:
return os.read(fd, 1024)
- else:
- raise TimeoutError("Timeout waiting for fd read")
+ raise TimeoutError("Timeout waiting for fd read")
class cmd:
"""
Execute a command on local or remote host.
+ @shell defaults to false, and class will try to split @comm into a list
+ if it's a string with spaces.
+
Use bkg() instead to run a command in the background.
"""
- def __init__(self, comm, shell=True, fail=True, ns=None, background=False,
+ def __init__(self, comm, shell=None, fail=True, ns=None, background=False,
host=None, timeout=5, ksft_wait=None):
if ns:
comm = f'ip netns exec {ns} ' + comm
@@ -45,6 +45,10 @@ class cmd:
if host:
self.proc = host.cmd(comm)
else:
+ # If user doesn't explicitly request shell try to avoid it.
+ if shell is None and isinstance(comm, str) and ' ' in comm:
+ comm = comm.split()
+
# ksft_wait lets us wait for the background process to fully start,
# we pass an FD to the child process, and wait for it to write back.
# Similarly term_fd tells child it's time to exit.
@@ -111,12 +115,13 @@ class bkg(cmd):
with bkg("my_binary", ksft_wait=5):
"""
- def __init__(self, comm, shell=True, fail=None, ns=None, host=None,
+ def __init__(self, comm, shell=None, fail=None, ns=None, host=None,
exit_wait=False, ksft_wait=None):
super().__init__(comm, background=True,
shell=shell, fail=fail, ns=ns, host=host,
ksft_wait=ksft_wait)
self.terminate = not exit_wait and not ksft_wait
+ self._exit_wait = exit_wait
self.check_fail = fail
if shell and self.terminate:
@@ -127,7 +132,9 @@ class bkg(cmd):
return self
def __exit__(self, ex_type, ex_value, ex_tb):
- return self.process(terminate=self.terminate, fail=self.check_fail)
+ # Force termination on exception
+ terminate = self.terminate or (self._exit_wait and ex_type)
+ return self.process(terminate=terminate, fail=self.check_fail)
global_defer_queue = []
@@ -135,8 +142,6 @@ global_defer_queue = []
class defer:
def __init__(self, func, *args, **kwargs):
- global global_defer_queue
-
if not callable(func):
raise Exception("defer created with un-callable object, did you call the function instead of passing its name?")
@@ -224,11 +229,11 @@ def bpftrace(expr, json=None, ns=None, host=None, timeout=None):
return cmd_obj
-def rand_port(type=socket.SOCK_STREAM):
+def rand_port(stype=socket.SOCK_STREAM):
"""
Get a random unprivileged port.
"""
- with socket.socket(socket.AF_INET6, type) as s:
+ with socket.socket(socket.AF_INET6, stype) as s:
s.bind(("", 0))
return s.getsockname()[1]
@@ -249,3 +254,21 @@ def wait_port_listen(port, proto="tcp", ns=None, host=None, sleep=0.005, deadlin
if time.monotonic() > end:
raise Exception("Waiting for port listen timed out")
time.sleep(sleep)
+
+
+def wait_file(fname, test_fn, sleep=0.005, deadline=5, encoding='utf-8'):
+ """
+ Wait for file contents on the local system to satisfy a condition.
+ test_fn() should take one argument (file contents) and return whether
+ condition is met.
+ """
+ end = time.monotonic() + deadline
+
+ with open(fname, "r", encoding=encoding) as fp:
+ while True:
+ if test_fn(fp.read()):
+ break
+ fp.seek(0)
+ if time.monotonic() > end:
+ raise TimeoutError("Wait for file contents failed", fname)
+ time.sleep(sleep)
diff --git a/tools/testing/selftests/net/lib/py/ynl.py b/tools/testing/selftests/net/lib/py/ynl.py
index 2b3a61ea3bfa..32c223e93b2c 100644
--- a/tools/testing/selftests/net/lib/py/ynl.py
+++ b/tools/testing/selftests/net/lib/py/ynl.py
@@ -61,3 +61,8 @@ class DevlinkFamily(YnlFamily):
def __init__(self, recv_size=0):
super().__init__((SPEC_PATH / Path('devlink.yaml')).as_posix(),
schema='', recv_size=recv_size)
+
+class PSPFamily(YnlFamily):
+ def __init__(self, recv_size=0):
+ super().__init__((SPEC_PATH / Path('psp.yaml')).as_posix(),
+ schema='', recv_size=recv_size)
diff --git a/tools/testing/selftests/net/lib/sh/defer.sh b/tools/testing/selftests/net/lib/sh/defer.sh
index 082f5d38321b..47ab78c4d465 100644
--- a/tools/testing/selftests/net/lib/sh/defer.sh
+++ b/tools/testing/selftests/net/lib/sh/defer.sh
@@ -1,6 +1,10 @@
#!/bin/bash
# SPDX-License-Identifier: GPL-2.0
+# Whether to pause and allow debugging when an executed deferred command has a
+# non-zero exit code.
+: "${DEFER_PAUSE_ON_FAIL:=no}"
+
# map[(scope_id,track,cleanup_id) -> cleanup_command]
# track={d=default | p=priority}
declare -A __DEFER__JOBS
@@ -38,8 +42,20 @@ __defer__run()
local track=$1; shift
local defer_ix=$1; shift
local defer_key=$(__defer__defer_key $track $defer_ix)
+ local ret
+
+ eval ${__DEFER__JOBS[$defer_key]}
+ ret=$?
+
+ if [[ "$DEFER_PAUSE_ON_FAIL" == yes && "$ret" -ne 0 ]]; then
+ echo "Deferred command (track $track index $defer_ix):"
+ echo " ${__DEFER__JOBS[$defer_key]}"
+ echo "... ended with an exit status of $ret"
+ echo "Hit enter to continue, 'q' to quit"
+ read a
+ [[ "$a" == q ]] && exit 1
+ fi
- ${__DEFER__JOBS[$defer_key]}
unset __DEFER__JOBS[$defer_key]
}
@@ -49,7 +65,7 @@ __defer__schedule()
local ndefers=$(__defer__ndefers $track)
local ndefers_key=$(__defer__ndefer_key $track)
local defer_key=$(__defer__defer_key $track $ndefers)
- local defer="$@"
+ local defer="${@@Q}"
__DEFER__JOBS[$defer_key]="$defer"
__DEFER__NJOBS[$ndefers_key]=$((ndefers + 1))
diff --git a/tools/testing/selftests/net/lib/xdp_native.bpf.c b/tools/testing/selftests/net/lib/xdp_native.bpf.c
index 521ba38f2ddd..c368fc045f4b 100644
--- a/tools/testing/selftests/net/lib/xdp_native.bpf.c
+++ b/tools/testing/selftests/net/lib/xdp_native.bpf.c
@@ -14,6 +14,8 @@
#define MAX_PAYLOAD_LEN 5000
#define MAX_HDR_LEN 64
+extern int bpf_xdp_pull_data(struct xdp_md *xdp, __u32 len) __ksym __weak;
+
enum {
XDP_MODE = 0,
XDP_PORT = 1,
@@ -68,30 +70,57 @@ static void record_stats(struct xdp_md *ctx, __u32 stat_type)
static struct udphdr *filter_udphdr(struct xdp_md *ctx, __u16 port)
{
- void *data_end = (void *)(long)ctx->data_end;
- void *data = (void *)(long)ctx->data;
struct udphdr *udph = NULL;
- struct ethhdr *eth = data;
+ void *data, *data_end;
+ struct ethhdr *eth;
+ int err;
+
+ err = bpf_xdp_pull_data(ctx, sizeof(*eth));
+ if (err)
+ return NULL;
+
+ data_end = (void *)(long)ctx->data_end;
+ data = eth = (void *)(long)ctx->data;
if (data + sizeof(*eth) > data_end)
return NULL;
if (eth->h_proto == bpf_htons(ETH_P_IP)) {
- struct iphdr *iph = data + sizeof(*eth);
+ struct iphdr *iph;
+
+ err = bpf_xdp_pull_data(ctx, sizeof(*eth) + sizeof(*iph) +
+ sizeof(*udph));
+ if (err)
+ return NULL;
+
+ data_end = (void *)(long)ctx->data_end;
+ data = (void *)(long)ctx->data;
+
+ iph = data + sizeof(*eth);
if (iph + 1 > (struct iphdr *)data_end ||
iph->protocol != IPPROTO_UDP)
return NULL;
- udph = (void *)eth + sizeof(*iph) + sizeof(*eth);
- } else if (eth->h_proto == bpf_htons(ETH_P_IPV6)) {
- struct ipv6hdr *ipv6h = data + sizeof(*eth);
+ udph = data + sizeof(*iph) + sizeof(*eth);
+ } else if (eth->h_proto == bpf_htons(ETH_P_IPV6)) {
+ struct ipv6hdr *ipv6h;
+
+ err = bpf_xdp_pull_data(ctx, sizeof(*eth) + sizeof(*ipv6h) +
+ sizeof(*udph));
+ if (err)
+ return NULL;
+
+ data_end = (void *)(long)ctx->data_end;
+ data = (void *)(long)ctx->data;
+
+ ipv6h = data + sizeof(*eth);
if (ipv6h + 1 > (struct ipv6hdr *)data_end ||
ipv6h->nexthdr != IPPROTO_UDP)
return NULL;
- udph = (void *)eth + sizeof(*ipv6h) + sizeof(*eth);
+ udph = data + sizeof(*ipv6h) + sizeof(*eth);
} else {
return NULL;
}
@@ -145,17 +174,34 @@ static void swap_machdr(void *data)
static int xdp_mode_tx_handler(struct xdp_md *ctx, __u16 port)
{
- void *data_end = (void *)(long)ctx->data_end;
- void *data = (void *)(long)ctx->data;
struct udphdr *udph = NULL;
- struct ethhdr *eth = data;
+ void *data, *data_end;
+ struct ethhdr *eth;
+ int err;
+
+ err = bpf_xdp_pull_data(ctx, sizeof(*eth));
+ if (err)
+ return XDP_PASS;
+
+ data_end = (void *)(long)ctx->data_end;
+ data = eth = (void *)(long)ctx->data;
if (data + sizeof(*eth) > data_end)
return XDP_PASS;
if (eth->h_proto == bpf_htons(ETH_P_IP)) {
- struct iphdr *iph = data + sizeof(*eth);
- __be32 tmp_ip = iph->saddr;
+ struct iphdr *iph;
+ __be32 tmp_ip;
+
+ err = bpf_xdp_pull_data(ctx, sizeof(*eth) + sizeof(*iph) +
+ sizeof(*udph));
+ if (err)
+ return XDP_PASS;
+
+ data_end = (void *)(long)ctx->data_end;
+ data = (void *)(long)ctx->data;
+
+ iph = data + sizeof(*eth);
if (iph + 1 > (struct iphdr *)data_end ||
iph->protocol != IPPROTO_UDP)
@@ -169,8 +215,10 @@ static int xdp_mode_tx_handler(struct xdp_md *ctx, __u16 port)
return XDP_PASS;
record_stats(ctx, STATS_RX);
+ eth = data;
swap_machdr((void *)eth);
+ tmp_ip = iph->saddr;
iph->saddr = iph->daddr;
iph->daddr = tmp_ip;
@@ -178,9 +226,19 @@ static int xdp_mode_tx_handler(struct xdp_md *ctx, __u16 port)
return XDP_TX;
- } else if (eth->h_proto == bpf_htons(ETH_P_IPV6)) {
- struct ipv6hdr *ipv6h = data + sizeof(*eth);
+ } else if (eth->h_proto == bpf_htons(ETH_P_IPV6)) {
struct in6_addr tmp_ipv6;
+ struct ipv6hdr *ipv6h;
+
+ err = bpf_xdp_pull_data(ctx, sizeof(*eth) + sizeof(*ipv6h) +
+ sizeof(*udph));
+ if (err)
+ return XDP_PASS;
+
+ data_end = (void *)(long)ctx->data_end;
+ data = (void *)(long)ctx->data;
+
+ ipv6h = data + sizeof(*eth);
if (ipv6h + 1 > (struct ipv6hdr *)data_end ||
ipv6h->nexthdr != IPPROTO_UDP)
@@ -194,6 +252,7 @@ static int xdp_mode_tx_handler(struct xdp_md *ctx, __u16 port)
return XDP_PASS;
record_stats(ctx, STATS_RX);
+ eth = data;
swap_machdr((void *)eth);
__builtin_memcpy(&tmp_ipv6, &ipv6h->saddr, sizeof(tmp_ipv6));
@@ -361,7 +420,6 @@ static int xdp_adjst_tail_grow_data(struct xdp_md *ctx, __u16 offset)
static int xdp_adjst_tail(struct xdp_md *ctx, __u16 port)
{
- void *data = (void *)(long)ctx->data;
struct udphdr *udph = NULL;
__s32 *adjust_offset, *val;
__u32 key, hdr_len;
@@ -373,7 +431,8 @@ static int xdp_adjst_tail(struct xdp_md *ctx, __u16 port)
if (!udph)
return XDP_PASS;
- hdr_len = (void *)udph - data + sizeof(struct udphdr);
+ hdr_len = (void *)udph - (void *)(long)ctx->data +
+ sizeof(struct udphdr);
key = XDP_ADJST_OFFSET;
adjust_offset = bpf_map_lookup_elem(&map_xdp_setup, &key);
if (!adjust_offset)
@@ -513,8 +572,6 @@ static int xdp_adjst_head_grow_data(struct xdp_md *ctx, __u64 hdr_len,
static int xdp_head_adjst(struct xdp_md *ctx, __u16 port)
{
- void *data_end = (void *)(long)ctx->data_end;
- void *data = (void *)(long)ctx->data;
struct udphdr *udph_ptr = NULL;
__u32 key, size, hdr_len;
__s32 *val;
@@ -525,7 +582,8 @@ static int xdp_head_adjst(struct xdp_md *ctx, __u16 port)
if (!udph_ptr)
return XDP_PASS;
- hdr_len = (void *)udph_ptr - data + sizeof(struct udphdr);
+ hdr_len = (void *)udph_ptr - (void *)(long)ctx->data +
+ sizeof(struct udphdr);
key = XDP_ADJST_OFFSET;
val = bpf_map_lookup_elem(&map_xdp_setup, &key);
diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh
index 7a3cb4c09e45..d847ff1737c3 100755
--- a/tools/testing/selftests/net/mptcp/diag.sh
+++ b/tools/testing/selftests/net/mptcp/diag.sh
@@ -28,7 +28,7 @@ flush_pids()
}
# This function is used in the cleanup trap
-#shellcheck disable=SC2317
+#shellcheck disable=SC2317,SC2329
cleanup()
{
ip netns pids "${ns}" | xargs --no-run-if-empty kill -SIGKILL &>/dev/null
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c
index 4f07ac9fa207..b148cadb96d0 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c
@@ -1093,6 +1093,7 @@ int main_loop_s(int listensock)
struct pollfd polls;
socklen_t salen;
int remotesock;
+ int err = 0;
int fd = 0;
again:
@@ -1125,7 +1126,7 @@ again:
SOCK_TEST_TCPULP(remotesock, 0);
memset(&winfo, 0, sizeof(winfo));
- copyfd_io(fd, remotesock, 1, true, &winfo);
+ err = copyfd_io(fd, remotesock, 1, true, &winfo);
} else {
perror("accept");
return 1;
@@ -1134,10 +1135,10 @@ again:
if (cfg_input)
close(fd);
- if (--cfg_repeat > 0)
+ if (!err && --cfg_repeat > 0)
goto again;
- return 0;
+ return err;
}
static void init_rng(void)
@@ -1247,7 +1248,7 @@ void xdisconnect(int fd)
else
xerror("bad family");
- strcpy(cmd, "ss -M | grep -q ");
+ strcpy(cmd, "ss -Mnt | grep -q ");
cmdlen = strlen(cmd);
if (!inet_ntop(addr.ss_family, raw_addr, &cmd[cmdlen],
sizeof(cmd) - cmdlen))
@@ -1257,7 +1258,7 @@ void xdisconnect(int fd)
/*
* wait until the pending data is completely flushed and all
- * the MPTCP sockets reached the closed status.
+ * the sockets reached the closed status.
* disconnect will bypass/ignore/drop any pending data.
*/
for (i = 0; ; i += msec_sleep) {
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
index 5e3c56253274..47ecb5b3836e 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
@@ -134,7 +134,7 @@ ns4=""
TEST_GROUP=""
# This function is used in the cleanup trap
-#shellcheck disable=SC2317
+#shellcheck disable=SC2317,SC2329
cleanup()
{
rm -f "$cin_disconnect"
@@ -211,6 +211,11 @@ if $checksum; then
done
fi
+if $capture; then
+ rndh="${ns1:4}"
+ mptcp_lib_pr_info "Packet capture files will have this prefix: ${rndh}-"
+fi
+
set_ethtool_flags() {
local ns="$1"
local dev="$2"
@@ -361,7 +366,6 @@ do_transfer()
if $capture; then
local capuser
- local rndh="${connector_ns:4}"
if [ -z $SUDO_USER ] ; then
capuser=""
else
diff --git a/tools/testing/selftests/net/mptcp/mptcp_inq.c b/tools/testing/selftests/net/mptcp/mptcp_inq.c
index f3bcaa48df8f..8e8f6441ad8b 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_inq.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_inq.c
@@ -502,6 +502,7 @@ static int server(int unixfd)
process_one_client(r, unixfd);
+ close(fd);
return 0;
}
@@ -580,8 +581,12 @@ int main(int argc, char *argv[])
die_perror("pipe");
s = xfork();
- if (s == 0)
- return server(unixfds[1]);
+ if (s == 0) {
+ close(unixfds[0]);
+ ret = server(unixfds[1]);
+ close(unixfds[1]);
+ return ret;
+ }
close(unixfds[1]);
diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 82cae37d9c20..c90d8e8b95cb 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -8,7 +8,7 @@
# ShellCheck incorrectly believes that most of the code here is unreachable
# because it's invoked by variable name, see how the "tests" array is used
-#shellcheck disable=SC2317
+#shellcheck disable=SC2317,SC2329
. "$(dirname "${0}")/mptcp_lib.sh"
@@ -74,6 +74,17 @@ unset join_create_err
unset join_bind_err
unset join_connect_err
+unset fb_ns1
+unset fb_ns2
+unset fb_infinite_map_tx
+unset fb_dss_corruption
+unset fb_simult_conn
+unset fb_mpc_passive
+unset fb_mpc_active
+unset fb_mpc_data
+unset fb_md5_sig
+unset fb_dss
+
# generated using "nfbpf_compile '(ip && (ip[54] & 0xf0) == 0x30) ||
# (ip6 && (ip6[74] & 0xf0) == 0x30)'"
CBPF_MPTCP_SUBOPTION_ADD_ADDR="14,
@@ -347,6 +358,7 @@ reset_with_add_addr_timeout()
tables="${ip6tables}"
fi
+ # set a maximum, to avoid too long timeout with exponential backoff
ip netns exec $ns1 sysctl -q net.mptcp.add_addr_timeout=1
if ! ip netns exec $ns2 $tables -A OUTPUT -p tcp \
@@ -1399,6 +1411,115 @@ chk_join_tx_nr()
print_results "join Tx" ${rc}
}
+chk_fallback_nr()
+{
+ local infinite_map_tx=${fb_infinite_map_tx:-0}
+ local dss_corruption=${fb_dss_corruption:-0}
+ local simult_conn=${fb_simult_conn:-0}
+ local mpc_passive=${fb_mpc_passive:-0}
+ local mpc_active=${fb_mpc_active:-0}
+ local mpc_data=${fb_mpc_data:-0}
+ local md5_sig=${fb_md5_sig:-0}
+ local dss=${fb_dss:-0}
+ local rc=${KSFT_PASS}
+ local ns=$1
+ local count
+
+ count=$(mptcp_lib_get_counter ${!ns} "MPTcpExtInfiniteMapTx")
+ if [ -z "$count" ]; then
+ rc=${KSFT_SKIP}
+ elif [ "$count" != "$infinite_map_tx" ]; then
+ rc=${KSFT_FAIL}
+ print_check "$ns infinite map tx fallback"
+ fail_test "got $count infinite map tx fallback[s] in $ns expected $infinite_map_tx"
+ fi
+
+ count=$(mptcp_lib_get_counter ${!ns} "MPTcpExtDSSCorruptionFallback")
+ if [ -z "$count" ]; then
+ rc=${KSFT_SKIP}
+ elif [ "$count" != "$dss_corruption" ]; then
+ rc=${KSFT_FAIL}
+ print_check "$ns dss corruption fallback"
+ fail_test "got $count dss corruption fallback[s] in $ns expected $dss_corruption"
+ fi
+
+ count=$(mptcp_lib_get_counter ${!ns} "MPTcpExtSimultConnectFallback")
+ if [ -z "$count" ]; then
+ rc=${KSFT_SKIP}
+ elif [ "$count" != "$simult_conn" ]; then
+ rc=${KSFT_FAIL}
+ print_check "$ns simult conn fallback"
+ fail_test "got $count simult conn fallback[s] in $ns expected $simult_conn"
+ fi
+
+ count=$(mptcp_lib_get_counter ${!ns} "MPTcpExtMPCapableFallbackACK")
+ if [ -z "$count" ]; then
+ rc=${KSFT_SKIP}
+ elif [ "$count" != "$mpc_passive" ]; then
+ rc=${KSFT_FAIL}
+ print_check "$ns mpc passive fallback"
+ fail_test "got $count mpc passive fallback[s] in $ns expected $mpc_passive"
+ fi
+
+ count=$(mptcp_lib_get_counter ${!ns} "MPTcpExtMPCapableFallbackSYNACK")
+ if [ -z "$count" ]; then
+ rc=${KSFT_SKIP}
+ elif [ "$count" != "$mpc_active" ]; then
+ rc=${KSFT_FAIL}
+ print_check "$ns mpc active fallback"
+ fail_test "got $count mpc active fallback[s] in $ns expected $mpc_active"
+ fi
+
+ count=$(mptcp_lib_get_counter ${!ns} "MPTcpExtMPCapableDataFallback")
+ if [ -z "$count" ]; then
+ rc=${KSFT_SKIP}
+ elif [ "$count" != "$mpc_data" ]; then
+ rc=${KSFT_FAIL}
+ print_check "$ns mpc data fallback"
+ fail_test "got $count mpc data fallback[s] in $ns expected $mpc_data"
+ fi
+
+ count=$(mptcp_lib_get_counter ${!ns} "MPTcpExtMD5SigFallback")
+ if [ -z "$count" ]; then
+ rc=${KSFT_SKIP}
+ elif [ "$count" != "$md5_sig" ]; then
+ rc=${KSFT_FAIL}
+ print_check "$ns MD5 Sig fallback"
+ fail_test "got $count MD5 Sig fallback[s] in $ns expected $md5_sig"
+ fi
+
+ count=$(mptcp_lib_get_counter ${!ns} "MPTcpExtDssFallback")
+ if [ -z "$count" ]; then
+ rc=${KSFT_SKIP}
+ elif [ "$count" != "$dss" ]; then
+ rc=${KSFT_FAIL}
+ print_check "$ns dss fallback"
+ fail_test "got $count dss fallback[s] in $ns expected $dss"
+ fi
+
+ return $rc
+}
+
+chk_fallback_nr_all()
+{
+ local netns=("ns1" "ns2")
+ local fb_ns=("fb_ns1" "fb_ns2")
+ local rc=${KSFT_PASS}
+
+ for i in 0 1; do
+ if [ -n "${!fb_ns[i]}" ]; then
+ eval "${!fb_ns[i]}" \
+ chk_fallback_nr ${netns[i]} || rc=${?}
+ else
+ chk_fallback_nr ${netns[i]} || rc=${?}
+ fi
+ done
+
+ if [ "${rc}" != "${KSFT_PASS}" ]; then
+ print_results "fallback" ${rc}
+ fi
+}
+
chk_join_nr()
{
local syn_nr=$1
@@ -1484,6 +1605,8 @@ chk_join_nr()
join_syn_tx="${join_syn_tx:-${syn_nr}}" \
chk_join_tx_nr
+ chk_fallback_nr_all
+
if $validate_checksum; then
chk_csum_nr $csum_ns1 $csum_ns2
chk_fail_nr $fail_nr $fail_nr
@@ -1547,7 +1670,6 @@ chk_add_nr()
local tx=""
local rx=""
local count
- local timeout
if [[ $ns_invert = "invert" ]]; then
ns_tx=$ns2
@@ -1556,15 +1678,13 @@ chk_add_nr()
rx=" server"
fi
- timeout=$(ip netns exec ${ns_tx} sysctl -n net.mptcp.add_addr_timeout)
-
print_check "add addr rx${rx}"
count=$(mptcp_lib_get_counter ${ns_rx} "MPTcpExtAddAddr")
if [ -z "$count" ]; then
print_skip
- # if the test configured a short timeout tolerate greater then expected
- # add addrs options, due to retransmissions
- elif [ "$count" != "$add_nr" ] && { [ "$timeout" -gt 1 ] || [ "$count" -lt "$add_nr" ]; }; then
+ # Tolerate more ADD_ADDR then expected (if any), due to retransmissions
+ elif [ "$count" != "$add_nr" ] &&
+ { [ "$add_nr" -eq 0 ] || [ "$count" -lt "$add_nr" ]; }; then
fail_test "got $count ADD_ADDR[s] expected $add_nr"
else
print_ok
@@ -1652,18 +1772,15 @@ chk_add_tx_nr()
{
local add_tx_nr=$1
local echo_tx_nr=$2
- local timeout
local count
- timeout=$(ip netns exec $ns1 sysctl -n net.mptcp.add_addr_timeout)
-
print_check "add addr tx"
count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtAddAddrTx")
if [ -z "$count" ]; then
print_skip
- # if the test configured a short timeout tolerate greater then expected
- # add addrs options, due to retransmissions
- elif [ "$count" != "$add_tx_nr" ] && { [ "$timeout" -gt 1 ] || [ "$count" -lt "$add_tx_nr" ]; }; then
+ # Tolerate more ADD_ADDR then expected (if any), due to retransmissions
+ elif [ "$count" != "$add_tx_nr" ] &&
+ { [ "$add_tx_nr" -eq 0 ] || [ "$count" -lt "$add_tx_nr" ]; }; then
fail_test "got $count ADD_ADDR[s] TX, expected $add_tx_nr"
else
print_ok
@@ -2151,7 +2268,8 @@ signal_address_tests()
pm_nl_add_endpoint $ns1 10.0.3.1 flags signal
pm_nl_add_endpoint $ns1 10.0.4.1 flags signal
pm_nl_set_limits $ns2 3 3
- run_tests $ns1 $ns2 10.0.1.1
+ speed=slow \
+ run_tests $ns1 $ns2 10.0.1.1
chk_join_nr 3 3 3
chk_add_nr 3 3
fi
@@ -2163,7 +2281,8 @@ signal_address_tests()
pm_nl_add_endpoint $ns1 10.0.3.1 flags signal
pm_nl_add_endpoint $ns1 10.0.14.1 flags signal
pm_nl_set_limits $ns2 3 3
- run_tests $ns1 $ns2 10.0.1.1
+ speed=slow \
+ run_tests $ns1 $ns2 10.0.1.1
join_syn_tx=3 \
chk_join_nr 1 1 1
chk_add_nr 3 3
@@ -2201,6 +2320,74 @@ signal_address_tests()
fi
}
+laminar_endp_tests()
+{
+ # no laminar endpoints: routing rules are used
+ if reset_with_tcp_filter "without a laminar endpoint" ns1 10.0.2.2 REJECT &&
+ mptcp_lib_kallsyms_has "mptcp_pm_get_endp_laminar_max$"; then
+ pm_nl_set_limits $ns1 0 2
+ pm_nl_set_limits $ns2 2 2
+ pm_nl_add_endpoint $ns1 10.0.2.1 flags signal
+ run_tests $ns1 $ns2 10.0.1.1
+ join_syn_tx=1 \
+ chk_join_nr 0 0 0
+ chk_add_nr 1 1
+ fi
+
+ # laminar endpoints: this endpoint is used
+ if reset_with_tcp_filter "with a laminar endpoint" ns1 10.0.2.2 REJECT &&
+ mptcp_lib_kallsyms_has "mptcp_pm_get_endp_laminar_max$"; then
+ pm_nl_set_limits $ns1 0 2
+ pm_nl_set_limits $ns2 2 2
+ pm_nl_add_endpoint $ns1 10.0.2.1 flags signal
+ pm_nl_add_endpoint $ns2 10.0.3.2 flags laminar
+ run_tests $ns1 $ns2 10.0.1.1
+ chk_join_nr 1 1 1
+ chk_add_nr 1 1
+ fi
+
+ # laminar endpoints: these endpoints are used
+ if reset_with_tcp_filter "with multiple laminar endpoints" ns1 10.0.2.2 REJECT &&
+ mptcp_lib_kallsyms_has "mptcp_pm_get_endp_laminar_max$"; then
+ pm_nl_set_limits $ns1 0 2
+ pm_nl_set_limits $ns2 2 2
+ pm_nl_add_endpoint $ns1 10.0.2.1 flags signal
+ pm_nl_add_endpoint $ns1 10.0.3.1 flags signal
+ pm_nl_add_endpoint $ns2 dead:beef:3::2 flags laminar
+ pm_nl_add_endpoint $ns2 10.0.3.2 flags laminar
+ pm_nl_add_endpoint $ns2 10.0.4.2 flags laminar
+ run_tests $ns1 $ns2 10.0.1.1
+ chk_join_nr 2 2 2
+ chk_add_nr 2 2
+ fi
+
+ # laminar endpoints: only one endpoint is used
+ if reset_with_tcp_filter "single laminar endpoint" ns1 10.0.2.2 REJECT &&
+ mptcp_lib_kallsyms_has "mptcp_pm_get_endp_laminar_max$"; then
+ pm_nl_set_limits $ns1 0 2
+ pm_nl_set_limits $ns2 2 2
+ pm_nl_add_endpoint $ns1 10.0.2.1 flags signal
+ pm_nl_add_endpoint $ns1 10.0.3.1 flags signal
+ pm_nl_add_endpoint $ns2 10.0.3.2 flags laminar
+ run_tests $ns1 $ns2 10.0.1.1
+ chk_join_nr 1 1 1
+ chk_add_nr 2 2
+ fi
+
+ # laminar endpoints: subflow and laminar flags
+ if reset_with_tcp_filter "sublow + laminar endpoints" ns1 10.0.2.2 REJECT &&
+ mptcp_lib_kallsyms_has "mptcp_pm_get_endp_laminar_max$"; then
+ pm_nl_set_limits $ns1 0 4
+ pm_nl_set_limits $ns2 2 4
+ pm_nl_add_endpoint $ns1 10.0.2.1 flags signal
+ pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow,laminar
+ pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow,laminar
+ run_tests $ns1 $ns2 10.0.1.1
+ chk_join_nr 1 1 1
+ chk_add_nr 1 1
+ fi
+}
+
link_failure_tests()
{
# accept and use add_addr with additional subflows and link loss
@@ -3187,6 +3374,17 @@ deny_join_id0_tests()
run_tests $ns1 $ns2 10.0.1.1
chk_join_nr 1 1 1
fi
+
+ # default limits, server deny join id 0 + signal
+ if reset_with_allow_join_id0 "default limits, server deny join id 0" 0 1; then
+ pm_nl_set_limits $ns1 0 2
+ pm_nl_set_limits $ns2 0 2
+ pm_nl_add_endpoint $ns1 10.0.2.1 flags signal
+ pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow
+ pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow
+ run_tests $ns1 $ns2 10.0.1.1
+ chk_join_nr 2 2 2
+ fi
}
fullmesh_tests()
@@ -3337,6 +3535,7 @@ fail_tests()
join_csum_ns1=+1 join_csum_ns2=+0 \
join_fail_nr=1 join_rst_nr=0 join_infi_nr=1 \
join_corrupted_pkts="$(pedit_action_pkts)" \
+ fb_ns1="fb_dss=1" fb_ns2="fb_infinite_map_tx=1" \
chk_join_nr 0 0 0
chk_fail_nr 1 -1 invert
fi
@@ -3978,6 +4177,7 @@ all_tests_sorted=(
f@subflows_tests
e@subflows_error_tests
s@signal_address_tests
+ L@laminar_endp_tests
l@link_failure_tests
t@add_addr_timeout_tests
r@remove_tests
diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh
index 09cd24b2ae46..d62e653d48b0 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh
@@ -384,7 +384,7 @@ mptcp_lib_make_file() {
mptcp_lib_print_file_err() {
ls -l "${1}" 1>&2
echo "Trailing bytes are: "
- tail -c 27 "${1}"
+ tail -c 32 "${1}" | od -x | head -n2
}
# $1: input file ; $2: output file ; $3: what kind of file
diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c
index e934dd26a59d..286164f7246e 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c
@@ -667,22 +667,26 @@ static void process_one_client(int fd, int pipefd)
do_getsockopts(&s, fd, ret, ret2);
if (s.mptcpi_rcv_delta != (uint64_t)ret + 1)
- xerror("mptcpi_rcv_delta %" PRIu64 ", expect %" PRIu64, s.mptcpi_rcv_delta, ret + 1, s.mptcpi_rcv_delta - ret);
+ xerror("mptcpi_rcv_delta %" PRIu64 ", expect %" PRIu64 ", diff %" PRId64,
+ s.mptcpi_rcv_delta, ret + 1, s.mptcpi_rcv_delta - (ret + 1));
/* be nice when running on top of older kernel */
if (s.pkt_stats_avail) {
if (s.last_sample.mptcpi_bytes_sent != ret2)
- xerror("mptcpi_bytes_sent %" PRIu64 ", expect %" PRIu64,
+ xerror("mptcpi_bytes_sent %" PRIu64 ", expect %" PRIu64
+ ", diff %" PRId64,
s.last_sample.mptcpi_bytes_sent, ret2,
s.last_sample.mptcpi_bytes_sent - ret2);
if (s.last_sample.mptcpi_bytes_received != ret)
- xerror("mptcpi_bytes_received %" PRIu64 ", expect %" PRIu64,
+ xerror("mptcpi_bytes_received %" PRIu64 ", expect %" PRIu64
+ ", diff %" PRId64,
s.last_sample.mptcpi_bytes_received, ret,
s.last_sample.mptcpi_bytes_received - ret);
if (s.last_sample.mptcpi_bytes_acked != ret)
- xerror("mptcpi_bytes_acked %" PRIu64 ", expect %" PRIu64,
- s.last_sample.mptcpi_bytes_acked, ret2,
- s.last_sample.mptcpi_bytes_acked - ret2);
+ xerror("mptcpi_bytes_acked %" PRIu64 ", expect %" PRIu64
+ ", diff %" PRId64,
+ s.last_sample.mptcpi_bytes_acked, ret,
+ s.last_sample.mptcpi_bytes_acked - ret);
}
close(fd);
@@ -722,6 +726,7 @@ static int server(int pipefd)
process_one_client(r, pipefd);
+ close(fd);
return 0;
}
@@ -847,8 +852,12 @@ int main(int argc, char *argv[])
die_perror("pipe");
s = xfork();
- if (s == 0)
- return server(pipefds[1]);
+ if (s == 0) {
+ close(pipefds[0]);
+ ret = server(pipefds[1]);
+ close(pipefds[1]);
+ return ret;
+ }
close(pipefds[1]);
diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh
index 418a903c3a4d..f01989be6e9b 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh
@@ -95,7 +95,7 @@ init()
}
# This function is used in the cleanup trap
-#shellcheck disable=SC2317
+#shellcheck disable=SC2317,SC2329
cleanup()
{
mptcp_lib_ns_exit "${ns1}" "${ns2}" "${ns_sbox}"
diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh
index ac7ec6f94023..ec6a87588191 100755
--- a/tools/testing/selftests/net/mptcp/pm_netlink.sh
+++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh
@@ -32,7 +32,7 @@ ns1=""
err=$(mktemp)
# This function is used in the cleanup trap
-#shellcheck disable=SC2317
+#shellcheck disable=SC2317,SC2329
cleanup()
{
rm -f "${err}"
@@ -70,8 +70,9 @@ format_endpoints() {
mptcp_lib_pm_nl_format_endpoints "${@}"
}
+# This function is invoked indirectly
+#shellcheck disable=SC2317,SC2329
get_endpoint() {
- # shellcheck disable=SC2317 # invoked indirectly
mptcp_lib_pm_nl_get_endpoint "${ns1}" "${@}"
}
diff --git a/tools/testing/selftests/net/mptcp/pm_nl_ctl.c b/tools/testing/selftests/net/mptcp/pm_nl_ctl.c
index 994a556f46c1..65b374232ff5 100644
--- a/tools/testing/selftests/net/mptcp/pm_nl_ctl.c
+++ b/tools/testing/selftests/net/mptcp/pm_nl_ctl.c
@@ -2,6 +2,7 @@
#include <errno.h>
#include <error.h>
+#include <stdbool.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
@@ -113,6 +114,8 @@ static int capture_events(int fd, int event_group)
error(1, errno, "could not join the " MPTCP_PM_EV_GRP_NAME " mcast group");
do {
+ bool server_side = false;
+
FD_ZERO(&rfds);
FD_SET(fd, &rfds);
res_len = NLMSG_ALIGN(sizeof(struct nlmsghdr)) +
@@ -187,11 +190,22 @@ static int capture_events(int fd, int event_group)
else if (attrs->rta_type == MPTCP_ATTR_ERROR)
fprintf(stderr, ",error:%u", *(__u8 *)RTA_DATA(attrs));
else if (attrs->rta_type == MPTCP_ATTR_SERVER_SIDE)
- fprintf(stderr, ",server_side:%u", *(__u8 *)RTA_DATA(attrs));
+ server_side = !!*(__u8 *)RTA_DATA(attrs);
+ else if (attrs->rta_type == MPTCP_ATTR_FLAGS) {
+ __u16 flags = *(__u16 *)RTA_DATA(attrs);
+
+ /* only print when present, easier */
+ if (flags & MPTCP_PM_EV_FLAG_DENY_JOIN_ID0)
+ fprintf(stderr, ",deny_join_id0:1");
+ if (flags & MPTCP_PM_EV_FLAG_SERVER_SIDE)
+ server_side = true;
+ }
attrs = RTA_NEXT(attrs, msg_len);
}
}
+ if (server_side)
+ fprintf(stderr, ",server_side:1");
fprintf(stderr, "\n");
} while (1);
@@ -816,6 +830,8 @@ int add_addr(int fd, int pm_family, int argc, char *argv[])
flags |= MPTCP_PM_ADDR_FLAG_SUBFLOW;
else if (!strcmp(tok, "signal"))
flags |= MPTCP_PM_ADDR_FLAG_SIGNAL;
+ else if (!strcmp(tok, "laminar"))
+ flags |= MPTCP_PM_ADDR_FLAG_LAMINAR;
else if (!strcmp(tok, "backup"))
flags |= MPTCP_PM_ADDR_FLAG_BACKUP;
else if (!strcmp(tok, "fullmesh"))
@@ -1004,6 +1020,13 @@ static void print_addr(struct rtattr *attrs, int len)
printf(",");
}
+ if (flags & MPTCP_PM_ADDR_FLAG_LAMINAR) {
+ printf("laminar");
+ flags &= ~MPTCP_PM_ADDR_FLAG_LAMINAR;
+ if (flags)
+ printf(",");
+ }
+
if (flags & MPTCP_PM_ADDR_FLAG_BACKUP) {
printf("backup");
flags &= ~MPTCP_PM_ADDR_FLAG_BACKUP;
diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh
index 2329c2f8519b..1903e8e84a31 100755
--- a/tools/testing/selftests/net/mptcp/simult_flows.sh
+++ b/tools/testing/selftests/net/mptcp/simult_flows.sh
@@ -35,7 +35,7 @@ usage() {
}
# This function is used in the cleanup trap
-#shellcheck disable=SC2317
+#shellcheck disable=SC2317,SC2329
cleanup()
{
rm -f "$cout" "$sout"
diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh
index 333064b0b5ac..87323942cb8a 100755
--- a/tools/testing/selftests/net/mptcp/userspace_pm.sh
+++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh
@@ -94,7 +94,7 @@ test_fail()
}
# This function is used in the cleanup trap
-#shellcheck disable=SC2317
+#shellcheck disable=SC2317,SC2329
cleanup()
{
print_title "Cleanup"
@@ -201,6 +201,9 @@ make_connection()
is_v6="v4"
fi
+ # set this on the client side only: will not affect the rest
+ ip netns exec "$ns2" sysctl -q net.mptcp.allow_join_initial_addr_port=0
+
:>"$client_evts"
:>"$server_evts"
@@ -223,23 +226,28 @@ make_connection()
local client_token
local client_port
local client_serverside
+ local client_nojoin
local server_token
local server_serverside
+ local server_nojoin
client_token=$(mptcp_lib_evts_get_info token "$client_evts")
client_port=$(mptcp_lib_evts_get_info sport "$client_evts")
client_serverside=$(mptcp_lib_evts_get_info server_side "$client_evts")
+ client_nojoin=$(mptcp_lib_evts_get_info deny_join_id0 "$client_evts")
server_token=$(mptcp_lib_evts_get_info token "$server_evts")
server_serverside=$(mptcp_lib_evts_get_info server_side "$server_evts")
+ server_nojoin=$(mptcp_lib_evts_get_info deny_join_id0 "$server_evts")
print_test "Established IP${is_v6} MPTCP Connection ns2 => ns1"
- if [ "$client_token" != "" ] && [ "$server_token" != "" ] && [ "$client_serverside" = 0 ] &&
- [ "$server_serverside" = 1 ]
+ if [ "${client_token}" != "" ] && [ "${server_token}" != "" ] &&
+ [ "${client_serverside:-0}" = 0 ] && [ "${server_serverside:-0}" = 1 ] &&
+ [ "${client_nojoin:-0}" = 0 ] && [ "${server_nojoin:-0}" = 1 ]
then
test_pass
print_title "Connection info: ${client_addr}:${client_port} -> ${connect_addr}:${app_port}"
else
- test_fail "Expected tokens (c:${client_token} - s:${server_token}) and server (c:${client_serverside} - s:${server_serverside})"
+ test_fail "Expected tokens (c:${client_token} - s:${server_token}), server (c:${client_serverside} - s:${server_serverside}), nojoin (c:${client_nojoin} - s:${server_nojoin})"
mptcp_lib_result_print_all_tap
exit ${KSFT_FAIL}
fi
diff --git a/tools/testing/selftests/net/netfilter/config b/tools/testing/selftests/net/netfilter/config
index 79d5b33966ba..305e46b819cb 100644
--- a/tools/testing/selftests/net/netfilter/config
+++ b/tools/testing/selftests/net/netfilter/config
@@ -13,6 +13,7 @@ CONFIG_BRIDGE_VLAN_FILTERING=y
CONFIG_CGROUP_BPF=y
CONFIG_DUMMY=m
CONFIG_INET_ESP=m
+CONFIG_CRYPTO_SHA1=m
CONFIG_IP_NF_MATCH_RPFILTER=m
CONFIG_IP6_NF_MATCH_RPFILTER=m
CONFIG_IP_NF_IPTABLES=m
diff --git a/tools/testing/selftests/net/netfilter/conntrack_clash.sh b/tools/testing/selftests/net/netfilter/conntrack_clash.sh
index 606a43a60f73..7fc6c5dbd551 100755
--- a/tools/testing/selftests/net/netfilter/conntrack_clash.sh
+++ b/tools/testing/selftests/net/netfilter/conntrack_clash.sh
@@ -99,7 +99,7 @@ run_one_clash_test()
local entries
local cre
- if ! ip netns exec "$ns" ./udpclash $daddr $dport;then
+ if ! ip netns exec "$ns" timeout 30 ./udpclash $daddr $dport;then
echo "INFO: did not receive expected number of replies for $daddr:$dport"
ip netns exec "$ctns" conntrack -S
# don't fail: check if clash resolution triggered after all.
diff --git a/tools/testing/selftests/net/netfilter/conntrack_resize.sh b/tools/testing/selftests/net/netfilter/conntrack_resize.sh
index 788cd56ea4a0..615fe3c6f405 100755
--- a/tools/testing/selftests/net/netfilter/conntrack_resize.sh
+++ b/tools/testing/selftests/net/netfilter/conntrack_resize.sh
@@ -187,7 +187,7 @@ ct_udpclash()
[ -x udpclash ] || return
while [ $now -lt $end ]; do
- ip netns exec "$ns" ./udpclash 127.0.0.1 $((RANDOM%65536)) > /dev/null 2>&1
+ ip netns exec "$ns" timeout 30 ./udpclash 127.0.0.1 $((RANDOM%65536)) > /dev/null 2>&1
now=$(date +%s)
done
@@ -277,6 +277,7 @@ check_taint()
insert_flood()
{
local n="$1"
+ local timeout="$2"
local r=0
r=$((RANDOM%$insert_count))
@@ -302,7 +303,7 @@ test_floodresize_all()
read tainted_then < /proc/sys/kernel/tainted
for n in "$nsclient1" "$nsclient2";do
- insert_flood "$n" &
+ insert_flood "$n" "$timeout" &
done
# resize table constantly while flood/insert/dump/flushs
diff --git a/tools/testing/selftests/net/netfilter/nft_concat_range.sh b/tools/testing/selftests/net/netfilter/nft_concat_range.sh
index 20e76b395c85..ad97c6227f35 100755
--- a/tools/testing/selftests/net/netfilter/nft_concat_range.sh
+++ b/tools/testing/selftests/net/netfilter/nft_concat_range.sh
@@ -29,7 +29,7 @@ TYPES="net_port port_net net6_port port_proto net6_port_mac net6_port_mac_proto
net6_port_net6_port net_port_mac_proto_net"
# Reported bugs, also described by TYPE_ variables below
-BUGS="flush_remove_add reload net_port_proto_match avx2_mismatch"
+BUGS="flush_remove_add reload net_port_proto_match avx2_mismatch doublecreate"
# List of possible paths to pktgen script from kernel tree for performance tests
PKTGEN_SCRIPT_PATHS="
@@ -408,6 +408,18 @@ perf_duration 0
"
+TYPE_doublecreate="
+display cannot create same element twice
+type_spec ipv4_addr . ipv4_addr
+chain_spec ip saddr . ip daddr
+dst addr4
+proto icmp
+
+race_repeat 0
+
+perf_duration 0
+"
+
# Set template for all tests, types and rules are filled in depending on test
set_template='
flush ruleset
@@ -1900,6 +1912,48 @@ test_bug_avx2_mismatch()
fi
}
+test_bug_doublecreate()
+{
+ local elements="1.2.3.4 . 1.2.4.1, 1.2.4.1 . 1.2.3.4"
+ local ret=1
+ local i
+
+ setup veth send_"${proto}" set || return ${ksft_skip}
+
+ add "{ $elements }" || return 1
+ # expected to work: 'add' on existing should be no-op.
+ add "{ $elements }" || return 1
+
+ # 'create' should return an error.
+ if nft create element inet filter test "{ $elements }" 2>/dev/null; then
+ err "Could create an existing element"
+ return 1
+ fi
+nft -f - <<EOF 2>/dev/null
+flush set inet filter test
+create element inet filter test { $elements }
+create element inet filter test { $elements }
+EOF
+ ret=$?
+ if [ $ret -eq 0 ]; then
+ err "Could create element twice in one transaction"
+ err "$(nft -a list ruleset)"
+ return 1
+ fi
+
+nft -f - <<EOF 2>/dev/null
+flush set inet filter test
+create element inet filter test { $elements }
+EOF
+ ret=$?
+ if [ $ret -ne 0 ]; then
+ err "Could not flush and re-create element in one transaction"
+ return 1
+ fi
+
+ return 0
+}
+
test_reported_issues() {
eval test_bug_"${subtest}"
}
diff --git a/tools/testing/selftests/net/netfilter/nft_flowtable.sh b/tools/testing/selftests/net/netfilter/nft_flowtable.sh
index a4ee5496f2a1..45832df98295 100755
--- a/tools/testing/selftests/net/netfilter/nft_flowtable.sh
+++ b/tools/testing/selftests/net/netfilter/nft_flowtable.sh
@@ -20,6 +20,7 @@ ret=0
SOCAT_TIMEOUT=60
nsin=""
+nsin_small=""
ns1out=""
ns2out=""
@@ -36,7 +37,7 @@ cleanup() {
cleanup_all_ns
- rm -f "$nsin" "$ns1out" "$ns2out"
+ rm -f "$nsin" "$nsin_small" "$ns1out" "$ns2out"
[ "$log_netns" -eq 0 ] && sysctl -q net.netfilter.nf_log_all_netns="$log_netns"
}
@@ -72,6 +73,7 @@ lmtu=1500
rmtu=2000
filesize=$((2 * 1024 * 1024))
+filesize_small=$((filesize / 16))
usage(){
echo "nft_flowtable.sh [OPTIONS]"
@@ -89,7 +91,10 @@ do
o) omtu=$OPTARG;;
l) lmtu=$OPTARG;;
r) rmtu=$OPTARG;;
- s) filesize=$OPTARG;;
+ s)
+ filesize=$OPTARG
+ filesize_small=$((OPTARG / 16))
+ ;;
*) usage;;
esac
done
@@ -215,6 +220,7 @@ if ! ip netns exec "$ns2" ping -c 1 -q 10.0.1.99 > /dev/null; then
fi
nsin=$(mktemp)
+nsin_small=$(mktemp)
ns1out=$(mktemp)
ns2out=$(mktemp)
@@ -265,6 +271,7 @@ check_counters()
check_dscp()
{
local what=$1
+ local pmtud="$2"
local ok=1
local counter
@@ -277,37 +284,39 @@ check_dscp()
local pc4z=${counter%*bytes*}
local pc4z=${pc4z#*packets}
+ local failmsg="FAIL: pmtu $pmtu: $what counters do not match, expected"
+
case "$what" in
"dscp_none")
if [ "$pc4" -gt 0 ] || [ "$pc4z" -eq 0 ]; then
- echo "FAIL: dscp counters do not match, expected dscp3 == 0, dscp0 > 0, but got $pc4,$pc4z" 1>&2
+ echo "$failmsg dscp3 == 0, dscp0 > 0, but got $pc4,$pc4z" 1>&2
ret=1
ok=0
fi
;;
"dscp_fwd")
if [ "$pc4" -eq 0 ] || [ "$pc4z" -eq 0 ]; then
- echo "FAIL: dscp counters do not match, expected dscp3 and dscp0 > 0 but got $pc4,$pc4z" 1>&2
+ echo "$failmsg dscp3 and dscp0 > 0 but got $pc4,$pc4z" 1>&2
ret=1
ok=0
fi
;;
"dscp_ingress")
if [ "$pc4" -eq 0 ] || [ "$pc4z" -gt 0 ]; then
- echo "FAIL: dscp counters do not match, expected dscp3 > 0, dscp0 == 0 but got $pc4,$pc4z" 1>&2
+ echo "$failmsg dscp3 > 0, dscp0 == 0 but got $pc4,$pc4z" 1>&2
ret=1
ok=0
fi
;;
"dscp_egress")
if [ "$pc4" -eq 0 ] || [ "$pc4z" -gt 0 ]; then
- echo "FAIL: dscp counters do not match, expected dscp3 > 0, dscp0 == 0 but got $pc4,$pc4z" 1>&2
+ echo "$failmsg dscp3 > 0, dscp0 == 0 but got $pc4,$pc4z" 1>&2
ret=1
ok=0
fi
;;
*)
- echo "FAIL: Unknown DSCP check" 1>&2
+ echo "$failmsg: Unknown DSCP check" 1>&2
ret=1
ok=0
esac
@@ -319,9 +328,9 @@ check_dscp()
check_transfer()
{
- in=$1
- out=$2
- what=$3
+ local in=$1
+ local out=$2
+ local what=$3
if ! cmp "$in" "$out" > /dev/null 2>&1; then
echo "FAIL: file mismatch for $what" 1>&2
@@ -342,25 +351,39 @@ test_tcp_forwarding_ip()
{
local nsa=$1
local nsb=$2
- local dstip=$3
- local dstport=$4
+ local pmtu=$3
+ local dstip=$4
+ local dstport=$5
local lret=0
+ local socatc
+ local socatl
+ local infile="$nsin"
+
+ if [ $pmtu -eq 0 ]; then
+ infile="$nsin_small"
+ fi
- timeout "$SOCAT_TIMEOUT" ip netns exec "$nsb" socat -4 TCP-LISTEN:12345,reuseaddr STDIO < "$nsin" > "$ns2out" &
+ timeout "$SOCAT_TIMEOUT" ip netns exec "$nsb" socat -4 TCP-LISTEN:12345,reuseaddr STDIO < "$infile" > "$ns2out" &
lpid=$!
busywait 1000 listener_ready
- timeout "$SOCAT_TIMEOUT" ip netns exec "$nsa" socat -4 TCP:"$dstip":"$dstport" STDIO < "$nsin" > "$ns1out"
+ timeout "$SOCAT_TIMEOUT" ip netns exec "$nsa" socat -4 TCP:"$dstip":"$dstport" STDIO < "$infile" > "$ns1out"
+ socatc=$?
wait $lpid
+ socatl=$?
- if ! check_transfer "$nsin" "$ns2out" "ns1 -> ns2"; then
+ if [ $socatl -ne 0 ] || [ $socatc -ne 0 ];then
+ rc=1
+ fi
+
+ if ! check_transfer "$infile" "$ns2out" "ns1 -> ns2"; then
lret=1
ret=1
fi
- if ! check_transfer "$nsin" "$ns1out" "ns1 <- ns2"; then
+ if ! check_transfer "$infile" "$ns1out" "ns1 <- ns2"; then
lret=1
ret=1
fi
@@ -370,14 +393,16 @@ test_tcp_forwarding_ip()
test_tcp_forwarding()
{
- test_tcp_forwarding_ip "$1" "$2" 10.0.2.99 12345
+ local pmtu="$3"
+
+ test_tcp_forwarding_ip "$1" "$2" "$pmtu" 10.0.2.99 12345
return $?
}
test_tcp_forwarding_set_dscp()
{
- check_dscp "dscp_none"
+ local pmtu="$3"
ip netns exec "$nsr1" nft -f - <<EOF
table netdev dscpmangle {
@@ -388,8 +413,8 @@ table netdev dscpmangle {
}
EOF
if [ $? -eq 0 ]; then
- test_tcp_forwarding_ip "$1" "$2" 10.0.2.99 12345
- check_dscp "dscp_ingress"
+ test_tcp_forwarding_ip "$1" "$2" "$3" 10.0.2.99 12345
+ check_dscp "dscp_ingress" "$pmtu"
ip netns exec "$nsr1" nft delete table netdev dscpmangle
else
@@ -405,10 +430,10 @@ table netdev dscpmangle {
}
EOF
if [ $? -eq 0 ]; then
- test_tcp_forwarding_ip "$1" "$2" 10.0.2.99 12345
- check_dscp "dscp_egress"
+ test_tcp_forwarding_ip "$1" "$2" "$pmtu" 10.0.2.99 12345
+ check_dscp "dscp_egress" "$pmtu"
- ip netns exec "$nsr1" nft flush table netdev dscpmangle
+ ip netns exec "$nsr1" nft delete table netdev dscpmangle
else
echo "SKIP: Could not load netdev:egress for veth1"
fi
@@ -416,48 +441,53 @@ fi
# partial. If flowtable really works, then both dscp-is-0 and dscp-is-cs3
# counters should have seen packets (before and after ft offload kicks in).
ip netns exec "$nsr1" nft -a insert rule inet filter forward ip dscp set cs3
- test_tcp_forwarding_ip "$1" "$2" 10.0.2.99 12345
- check_dscp "dscp_fwd"
+ test_tcp_forwarding_ip "$1" "$2" "$pmtu" 10.0.2.99 12345
+ check_dscp "dscp_fwd" "$pmtu"
}
test_tcp_forwarding_nat()
{
+ local nsa="$1"
+ local nsb="$2"
+ local pmtu="$3"
+ local what="$4"
local lret
- local pmtu
- test_tcp_forwarding_ip "$1" "$2" 10.0.2.99 12345
- lret=$?
+ [ "$pmtu" -eq 0 ] && what="$what (pmtu disabled)"
- pmtu=$3
- what=$4
+ test_tcp_forwarding_ip "$nsa" "$nsb" "$pmtu" 10.0.2.99 12345
+ lret=$?
if [ "$lret" -eq 0 ] ; then
if [ "$pmtu" -eq 1 ] ;then
- check_counters "flow offload for ns1/ns2 with masquerade and pmtu discovery $what"
+ check_counters "flow offload for ns1/ns2 with masquerade $what"
else
echo "PASS: flow offload for ns1/ns2 with masquerade $what"
fi
- test_tcp_forwarding_ip "$1" "$2" 10.6.6.6 1666
+ test_tcp_forwarding_ip "$1" "$2" "$pmtu" 10.6.6.6 1666
lret=$?
if [ "$pmtu" -eq 1 ] ;then
- check_counters "flow offload for ns1/ns2 with dnat and pmtu discovery $what"
+ check_counters "flow offload for ns1/ns2 with dnat $what"
elif [ "$lret" -eq 0 ] ; then
echo "PASS: flow offload for ns1/ns2 with dnat $what"
fi
+ else
+ echo "FAIL: flow offload for ns1/ns2 with dnat $what"
fi
return $lret
}
make_file "$nsin" "$filesize"
+make_file "$nsin_small" "$filesize_small"
# First test:
# No PMTU discovery, nsr1 is expected to fragment packets from ns1 to ns2 as needed.
# Due to MTU mismatch in both directions, all packets (except small packets like pure
# acks) have to be handled by normal forwarding path. Therefore, packet counters
# are not checked.
-if test_tcp_forwarding "$ns1" "$ns2"; then
+if test_tcp_forwarding "$ns1" "$ns2" 0; then
echo "PASS: flow offloaded for ns1/ns2"
else
echo "FAIL: flow offload for ns1/ns2:" 1>&2
@@ -489,8 +519,9 @@ table ip nat {
}
EOF
+check_dscp "dscp_none" "0"
if ! test_tcp_forwarding_set_dscp "$ns1" "$ns2" 0 ""; then
- echo "FAIL: flow offload for ns1/ns2 with dscp update" 1>&2
+ echo "FAIL: flow offload for ns1/ns2 with dscp update and no pmtu discovery" 1>&2
exit 0
fi
@@ -513,6 +544,14 @@ ip netns exec "$ns2" sysctl net.ipv4.ip_no_pmtu_disc=0 > /dev/null
# For earlier tests (large mtus), packets cannot be handled via flowtable
# (except pure acks and other small packets).
ip netns exec "$nsr1" nft reset counters table inet filter >/dev/null
+ip netns exec "$ns2" nft reset counters table inet filter >/dev/null
+
+if ! test_tcp_forwarding_set_dscp "$ns1" "$ns2" 1 ""; then
+ echo "FAIL: flow offload for ns1/ns2 with dscp update and pmtu discovery" 1>&2
+ exit 0
+fi
+
+ip netns exec "$nsr1" nft reset counters table inet filter >/dev/null
if ! test_tcp_forwarding_nat "$ns1" "$ns2" 1 ""; then
echo "FAIL: flow offload for ns1/ns2 with NAT and pmtu discovery" 1>&2
@@ -644,7 +683,7 @@ ip -net "$ns2" route del 192.168.10.1 via 10.0.2.1
ip -net "$ns2" route add default via 10.0.2.1
ip -net "$ns2" route add default via dead:2::1
-if test_tcp_forwarding "$ns1" "$ns2"; then
+if test_tcp_forwarding "$ns1" "$ns2" 1; then
check_counters "ipsec tunnel mode for ns1/ns2"
else
echo "FAIL: ipsec tunnel mode for ns1/ns2"
@@ -668,7 +707,7 @@ if [ "$1" = "" ]; then
fi
echo "re-run with random mtus and file size: -o $o -l $l -r $r -s $filesize"
- $0 -o "$o" -l "$l" -r "$r" -s "$filesize"
+ $0 -o "$o" -l "$l" -r "$r" -s "$filesize" || ret=1
fi
exit $ret
diff --git a/tools/testing/selftests/net/netfilter/nft_nat.sh b/tools/testing/selftests/net/netfilter/nft_nat.sh
index a954754b99b3..b3ec2d0a3f56 100755
--- a/tools/testing/selftests/net/netfilter/nft_nat.sh
+++ b/tools/testing/selftests/net/netfilter/nft_nat.sh
@@ -569,7 +569,7 @@ test_redirect6()
ip netns exec "$ns0" sysctl net.ipv6.conf.all.forwarding=1 > /dev/null
if ! ip netns exec "$ns2" ping -q -c 1 dead:1::99 > /dev/null;then
- echo "ERROR: cannnot ping $ns1 from $ns2 via ipv6"
+ echo "ERROR: cannot ping $ns1 from $ns2 via ipv6"
lret=1
fi
@@ -859,7 +859,7 @@ EOF
# from router:service bypass connection tracking.
test_port_shadow_notrack "$family"
- # test nat based mitigation: fowarded packets coming from service port
+ # test nat based mitigation: forwarded packets coming from service port
# are masqueraded with random highport.
test_port_shadow_pat "$family"
diff --git a/tools/testing/selftests/net/netfilter/udpclash.c b/tools/testing/selftests/net/netfilter/udpclash.c
index 85c7b906ad08..79de163d61ab 100644
--- a/tools/testing/selftests/net/netfilter/udpclash.c
+++ b/tools/testing/selftests/net/netfilter/udpclash.c
@@ -29,7 +29,7 @@ struct thread_args {
int sockfd;
};
-static int wait = 1;
+static volatile int wait = 1;
static void *thread_main(void *varg)
{
diff --git a/tools/testing/selftests/net/netlink-dumps.c b/tools/testing/selftests/net/netlink-dumps.c
index 07423f256f96..7618ebe528a4 100644
--- a/tools/testing/selftests/net/netlink-dumps.c
+++ b/tools/testing/selftests/net/netlink-dumps.c
@@ -31,9 +31,18 @@ struct ext_ack {
const char *str;
};
-/* 0: no done, 1: done found, 2: extack found, -1: error */
-static int nl_get_extack(char *buf, size_t n, struct ext_ack *ea)
+enum get_ea_ret {
+ ERROR = -1,
+ NO_CTRL = 0,
+ FOUND_DONE,
+ FOUND_ERR,
+ FOUND_EXTACK,
+};
+
+static enum get_ea_ret
+nl_get_extack(char *buf, size_t n, struct ext_ack *ea)
{
+ enum get_ea_ret ret = NO_CTRL;
const struct nlmsghdr *nlh;
const struct nlattr *attr;
ssize_t rem;
@@ -41,15 +50,19 @@ static int nl_get_extack(char *buf, size_t n, struct ext_ack *ea)
for (rem = n; rem > 0; NLMSG_NEXT(nlh, rem)) {
nlh = (struct nlmsghdr *)&buf[n - rem];
if (!NLMSG_OK(nlh, rem))
- return -1;
+ return ERROR;
- if (nlh->nlmsg_type != NLMSG_DONE)
+ if (nlh->nlmsg_type == NLMSG_ERROR)
+ ret = FOUND_ERR;
+ else if (nlh->nlmsg_type == NLMSG_DONE)
+ ret = FOUND_DONE;
+ else
continue;
ea->err = -*(int *)NLMSG_DATA(nlh);
if (!(nlh->nlmsg_flags & NLM_F_ACK_TLVS))
- return 1;
+ return ret;
ynl_attr_for_each(attr, nlh, sizeof(int)) {
switch (ynl_attr_type(attr)) {
@@ -68,10 +81,10 @@ static int nl_get_extack(char *buf, size_t n, struct ext_ack *ea)
}
}
- return 2;
+ return FOUND_EXTACK;
}
- return 0;
+ return ret;
}
static const struct {
@@ -99,9 +112,9 @@ static const struct {
TEST(dump_extack)
{
int netlink_sock;
+ int i, cnt, ret;
char buf[8192];
int one = 1;
- int i, cnt;
ssize_t n;
netlink_sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
@@ -118,7 +131,7 @@ TEST(dump_extack)
ASSERT_EQ(n, 0);
/* Dump so many times we fill up the buffer */
- cnt = 64;
+ cnt = 80;
for (i = 0; i < cnt; i++) {
n = send(netlink_sock, &dump_neigh_bad,
sizeof(dump_neigh_bad), 0);
@@ -140,10 +153,20 @@ TEST(dump_extack)
}
ASSERT_GE(n, (ssize_t)sizeof(struct nlmsghdr));
- EXPECT_EQ(nl_get_extack(buf, n, &ea), 2);
+ ret = nl_get_extack(buf, n, &ea);
+ /* Once we fill the buffer we'll see one ENOBUFS followed
+ * by a number of EBUSYs. Then the last recv() will finally
+ * trigger and complete the dump.
+ */
+ if (ret == FOUND_ERR && (ea.err == ENOBUFS || ea.err == EBUSY))
+ continue;
+ EXPECT_EQ(ret, FOUND_EXTACK);
+ EXPECT_EQ(ea.err, EINVAL);
EXPECT_EQ(ea.attr_offs,
sizeof(struct nlmsghdr) + sizeof(struct ndmsg));
}
+ /* Make sure last message was a full DONE+extack */
+ EXPECT_EQ(ret, FOUND_EXTACK);
}
static const struct {
diff --git a/tools/testing/selftests/net/openvswitch/openvswitch.sh b/tools/testing/selftests/net/openvswitch/openvswitch.sh
index 3c8d3455d8e7..b327d3061ed5 100755
--- a/tools/testing/selftests/net/openvswitch/openvswitch.sh
+++ b/tools/testing/selftests/net/openvswitch/openvswitch.sh
@@ -25,6 +25,7 @@ tests="
nat_related_v4 ip4-nat-related: ICMP related matches work with SNAT
netlink_checks ovsnl: validate netlink attrs and settings
upcall_interfaces ovs: test the upcall interfaces
+ tunnel_metadata ovs: test extraction of tunnel metadata
drop_reason drop: test drop reasons are emitted
psample psample: Sampling packets with psample"
@@ -113,13 +114,13 @@ ovs_add_dp () {
}
ovs_add_if () {
- info "Adding IF to DP: br:$2 if:$3"
- if [ "$4" != "-u" ]; then
- ovs_sbx "$1" python3 $ovs_base/ovs-dpctl.py add-if "$2" "$3" \
- || return 1
+ info "Adding IF to DP: br:$3 if:$4 ($2)"
+ if [ "$5" != "-u" ]; then
+ ovs_sbx "$1" python3 $ovs_base/ovs-dpctl.py add-if \
+ -t "$2" "$3" "$4" || return 1
else
python3 $ovs_base/ovs-dpctl.py add-if \
- -u "$2" "$3" >$ovs_dir/$3.out 2>$ovs_dir/$3.err &
+ -u -t "$2" "$3" "$4" >$ovs_dir/$4.out 2>$ovs_dir/$4.err &
pid=$!
on_exit "ovs_sbx $1 kill -TERM $pid 2>/dev/null"
fi
@@ -166,9 +167,9 @@ ovs_add_netns_and_veths () {
fi
if [ "$7" != "-u" ]; then
- ovs_add_if "$1" "$2" "$4" || return 1
+ ovs_add_if "$1" "netdev" "$2" "$4" || return 1
else
- ovs_add_if "$1" "$2" "$4" -u || return 1
+ ovs_add_if "$1" "netdev" "$2" "$4" -u || return 1
fi
if [ $TRACING -eq 1 ]; then
@@ -756,6 +757,79 @@ test_upcall_interfaces() {
return 0
}
+ovs_add_kernel_tunnel() {
+ local sbxname=$1; shift
+ local ns=$1; shift
+ local tnl_type=$1; shift
+ local name=$1; shift
+ local addr=$1; shift
+
+ info "setting up kernel ${tnl_type} tunnel ${name}"
+ ovs_sbx "${sbxname}" ip -netns ${ns} link add dev ${name} type ${tnl_type} $* || return 1
+ on_exit "ovs_sbx ${sbxname} ip -netns ${ns} link del ${name} >/dev/null 2>&1"
+ ovs_sbx "${sbxname}" ip -netns ${ns} addr add dev ${name} ${addr} || return 1
+ ovs_sbx "${sbxname}" ip -netns ${ns} link set dev ${name} mtu 1450 up || return 1
+}
+
+test_tunnel_metadata() {
+ which arping >/dev/null 2>&1 || return $ksft_skip
+
+ sbxname="test_tunnel_metadata"
+ sbx_add "${sbxname}" || return 1
+
+ info "setting up new DP"
+ ovs_add_dp "${sbxname}" tdp0 -V 2:1 || return 1
+
+ ovs_add_netns_and_veths "${sbxname}" tdp0 tns left0 l0 \
+ 172.31.110.1/24 || return 1
+
+ info "removing veth interface from openvswitch and setting IP"
+ ovs_del_if "${sbxname}" tdp0 left0 || return 1
+ ovs_sbx "${sbxname}" ip addr add 172.31.110.2/24 dev left0 || return 1
+ ovs_sbx "${sbxname}" ip link set left0 up || return 1
+
+ info "setting up tunnel port in openvswitch"
+ ovs_add_if "${sbxname}" "vxlan" tdp0 ovs-vxlan0 -u || return 1
+ on_exit "ovs_sbx ${sbxname} ip link del ovs-vxlan0"
+ ovs_wait ip link show ovs-vxlan0 &>/dev/null || return 1
+ ovs_sbx "${sbxname}" ip link set ovs-vxlan0 up || return 1
+
+ configs=$(echo '
+ 1 172.31.221.1/24 1155332 32 set udpcsum flags\(df\|csum\)
+ 2 172.31.222.1/24 1234567 45 set noudpcsum flags\(df\)
+ 3 172.31.223.1/24 1020304 23 unset udpcsum flags\(csum\)
+ 4 172.31.224.1/24 1357986 15 unset noudpcsum' | sed '/^$/d')
+
+ while read -r i addr id ttl df csum flags; do
+ ovs_add_kernel_tunnel "${sbxname}" tns vxlan vxlan${i} ${addr} \
+ remote 172.31.110.2 id ${id} dstport 4789 \
+ ttl ${ttl} df ${df} ${csum} || return 1
+ done <<< "${configs}"
+
+ ovs_wait grep -q 'listening on upcall packet handler' \
+ ${ovs_dir}/ovs-vxlan0.out || return 1
+
+ info "sending arping"
+ for i in 1 2 3 4; do
+ ovs_sbx "${sbxname}" ip netns exec tns \
+ arping -I vxlan${i} 172.31.22${i}.2 -c 1 \
+ >${ovs_dir}/arping.stdout 2>${ovs_dir}/arping.stderr
+ done
+
+ info "checking that received decapsulated packets carry correct metadata"
+ while read -r i addr id ttl df csum flags; do
+ arp_hdr="arp\\(sip=172.31.22${i}.1,tip=172.31.22${i}.2,op=1,sha="
+ addrs="src=172.31.110.1,dst=172.31.110.2"
+ ports="tp_src=[0-9]*,tp_dst=4789"
+ tnl_md="tunnel\\(tun_id=${id},${addrs},ttl=${ttl},${ports},${flags}\\)"
+
+ ovs_sbx "${sbxname}" grep -qE "MISS upcall.*${tnl_md}.*${arp_hdr}" \
+ ${ovs_dir}/ovs-vxlan0.out || return 1
+ done <<< "${configs}"
+
+ return 0
+}
+
run_test() {
(
tname="$1"
diff --git a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py
index 8a0396bfaf99..b521e0dea506 100644
--- a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py
+++ b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py
@@ -1877,7 +1877,7 @@ class OvsPacket(GenericNetlinkSocket):
elif msg["cmd"] == OvsPacket.OVS_PACKET_CMD_EXECUTE:
up.execute(msg)
else:
- print("Unkonwn cmd: %d" % msg["cmd"])
+ print("Unknown cmd: %d" % msg["cmd"])
except NetlinkError as ne:
raise ne
diff --git a/tools/testing/selftests/net/ovpn/ovpn-cli.c b/tools/testing/selftests/net/ovpn/ovpn-cli.c
index 9201f2905f2c..688a5fa6fdac 100644
--- a/tools/testing/selftests/net/ovpn/ovpn-cli.c
+++ b/tools/testing/selftests/net/ovpn/ovpn-cli.c
@@ -32,9 +32,10 @@
#include <sys/socket.h>
+#include "../../kselftest.h"
+
/* defines to make checkpatch happy */
#define strscpy strncpy
-#define __always_unused __attribute__((__unused__))
/* libnl < 3.5.0 does not set the NLA_F_NESTED on its own, therefore we
* have to explicitly do it to prevent the kernel from failing upon
diff --git a/tools/testing/selftests/net/packetdrill/defaults.sh b/tools/testing/selftests/net/packetdrill/defaults.sh
index 1095a7b22f44..37edd3dc3b07 100755
--- a/tools/testing/selftests/net/packetdrill/defaults.sh
+++ b/tools/testing/selftests/net/packetdrill/defaults.sh
@@ -51,7 +51,8 @@ sysctl -q net.ipv4.tcp_pacing_ss_ratio=200
sysctl -q net.ipv4.tcp_pacing_ca_ratio=120
sysctl -q net.ipv4.tcp_notsent_lowat=4294967295 > /dev/null 2>&1
-sysctl -q net.ipv4.tcp_fastopen=0x70403
+sysctl -q net.ipv4.tcp_fastopen=0x3
+# Use TFO_COOKIE in ksft_runner.sh for this key.
sysctl -q net.ipv4.tcp_fastopen_key=a1a1a1a1-b2b2b2b2-c3c3c3c3-d4d4d4d4
sysctl -q net.ipv4.tcp_syncookies=1
diff --git a/tools/testing/selftests/net/packetdrill/ksft_runner.sh b/tools/testing/selftests/net/packetdrill/ksft_runner.sh
index a7e790af38ff..b34e5cf0112e 100755
--- a/tools/testing/selftests/net/packetdrill/ksft_runner.sh
+++ b/tools/testing/selftests/net/packetdrill/ksft_runner.sh
@@ -3,21 +3,26 @@
source "$(dirname $(realpath $0))/../../kselftest/ktap_helpers.sh"
-readonly ipv4_args=('--ip_version=ipv4 '
- '--local_ip=192.168.0.1 '
- '--gateway_ip=192.168.0.1 '
- '--netmask_ip=255.255.0.0 '
- '--remote_ip=192.0.2.1 '
- '-D CMSG_LEVEL_IP=SOL_IP '
- '-D CMSG_TYPE_RECVERR=IP_RECVERR ')
-
-readonly ipv6_args=('--ip_version=ipv6 '
- '--mtu=1520 '
- '--local_ip=fd3d:0a0b:17d6::1 '
- '--gateway_ip=fd3d:0a0b:17d6:8888::1 '
- '--remote_ip=fd3d:fa7b:d17d::1 '
- '-D CMSG_LEVEL_IP=SOL_IPV6 '
- '-D CMSG_TYPE_RECVERR=IPV6_RECVERR ')
+declare -A ip_args=(
+ [ipv4]="--ip_version=ipv4
+ --local_ip=192.168.0.1
+ --gateway_ip=192.168.0.1
+ --netmask_ip=255.255.0.0
+ --remote_ip=192.0.2.1
+ -D TFO_COOKIE=3021b9d889017eeb
+ -D TFO_COOKIE_ZERO=b7c12350a90dc8f5
+ -D CMSG_LEVEL_IP=SOL_IP
+ -D CMSG_TYPE_RECVERR=IP_RECVERR"
+ [ipv6]="--ip_version=ipv6
+ --mtu=1520
+ --local_ip=fd3d:0a0b:17d6::1
+ --gateway_ip=fd3d:0a0b:17d6:8888::1
+ --remote_ip=fd3d:fa7b:d17d::1
+ -D TFO_COOKIE=c1d1e9742a47a9bc
+ -D TFO_COOKIE_ZERO=82af1a8f9a205c34
+ -D CMSG_LEVEL_IP=SOL_IPV6
+ -D CMSG_TYPE_RECVERR=IPV6_RECVERR"
+)
if [ $# -ne 1 ]; then
ktap_exit_fail_msg "usage: $0 <script>"
@@ -38,12 +43,20 @@ if [[ -n "${KSFT_MACHINE_SLOW}" ]]; then
failfunc=ktap_test_xfail
fi
+ip_versions=$(grep -E '^--ip_version=' $script | cut -d '=' -f 2)
+if [[ -z $ip_versions ]]; then
+ ip_versions="ipv4 ipv6"
+elif [[ ! "$ip_versions" =~ ^ipv[46]$ ]]; then
+ ktap_exit_fail_msg "Too many or unsupported --ip_version: $ip_versions"
+ exit "$KSFT_FAIL"
+fi
+
ktap_print_header
-ktap_set_plan 2
+ktap_set_plan $(echo $ip_versions | wc -w)
-unshare -n packetdrill ${ipv4_args[@]} ${optargs[@]} $script > /dev/null \
- && ktap_test_pass "ipv4" || $failfunc "ipv4"
-unshare -n packetdrill ${ipv6_args[@]} ${optargs[@]} $script > /dev/null \
- && ktap_test_pass "ipv6" || $failfunc "ipv6"
+for ip_version in $ip_versions; do
+ unshare -n packetdrill ${ip_args[$ip_version]} ${optargs[@]} $script > /dev/null \
+ && ktap_test_pass $ip_version || $failfunc $ip_version
+done
ktap_finished
diff --git a/tools/testing/selftests/net/packetdrill/tcp_close_no_rst.pkt b/tools/testing/selftests/net/packetdrill/tcp_close_no_rst.pkt
new file mode 100644
index 000000000000..eef01d5f1118
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_close_no_rst.pkt
@@ -0,0 +1,32 @@
+// SPDX-License-Identifier: GPL-2.0
+
+--mss=1000
+
+`./defaults.sh`
+
+// Initialize connection
+ 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+
+ +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop>
+ +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK>
+ +.1 < . 1:1(0) ack 1 win 32792
+
+
+ +0 accept(3, ..., ...) = 4
+ +0 < . 1:1001(1000) ack 1 win 32792
+ +0 > . 1:1(0) ack 1001
+ +0 read(4, ..., 1000) = 1000
+
+// resend the payload + a FIN
+ +0 < F. 1:1001(1000) ack 1 win 32792
+// Why do we have a delay and no dsack ?
+ +0~+.04 > . 1:1(0) ack 1002
+
+ +0 close(4) = 0
+
+// According to RFC 2525, section 2.17
+// we should _not_ send an RST here, because there was no data to consume.
+ +0 > F. 1:1(0) ack 1002
diff --git a/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_basic-cookie-not-reqd.pkt b/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_basic-cookie-not-reqd.pkt
new file mode 100644
index 000000000000..32aff9bc4052
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_basic-cookie-not-reqd.pkt
@@ -0,0 +1,32 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Basic TFO server test
+//
+// Test TFO_SERVER_COOKIE_NOT_REQD flag on receiving
+// SYN with data but without Fast Open cookie option.
+
+`./defaults.sh
+ ./set_sysctls.py /proc/sys/net/ipv4/tcp_fastopen=0x202`
+
+ 0 socket(..., SOCK_STREAM|SOCK_NONBLOCK, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+ +0 setsockopt(3, SOL_TCP, TCP_FASTOPEN, [1], 4) = 0
+
+// Since TFO_SERVER_COOKIE_NOT_REQD, a TFO socket will be created with
+// the data accepted.
+ +0 < S 0:1000(1000) win 32792 <mss 1460,sackOK,nop,nop>
+ +0 > S. 0:0(0) ack 1001 <mss 1460,nop,nop,sackOK>
+ +0 accept(3, ..., ...) = 4
+ +0 %{ assert (tcpi_options & TCPI_OPT_SYN_DATA) != 0, tcpi_options }%
+ +0 read(4, ..., 1024) = 1000
+
+// Data After SYN will be accepted too.
+ +0 < . 1001:2001(1000) ack 1 win 5840
+ +0 > . 1:1(0) ack 2001
+
+// Should change the implementation later to set the SYN flag as well.
+ +0 read(4, ..., 1024) = 1000
+ +0 write(4, ..., 1000) = 1000
+ +0 > P. 1:1001(1000) ack 2001
diff --git a/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_basic-no-setsockopt.pkt b/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_basic-no-setsockopt.pkt
new file mode 100644
index 000000000000..649997a58099
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_basic-no-setsockopt.pkt
@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Basic TFO server test
+//
+// Test TFO_SERVER_WO_SOCKOPT1 without setsockopt(TCP_FASTOPEN)
+
+`./defaults.sh
+ ./set_sysctls.py /proc/sys/net/ipv4/tcp_fastopen=0x402`
+
+ 0 socket(..., SOCK_STREAM|SOCK_NONBLOCK, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+
+ +0 < S 0:10(10) win 32792 <mss 1460,sackOK,nop,nop,FO TFO_COOKIE,nop,nop>
+ +0 > S. 0:0(0) ack 11 <mss 1460,nop,nop,sackOK>
+
+ +0 accept(3, ..., ...) = 4
+ +0 %{ assert (tcpi_options & TCPI_OPT_SYN_DATA) != 0, tcpi_options }%
+
+ +0 read(4, ..., 512) = 10
diff --git a/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_basic-non-tfo-listener.pkt b/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_basic-non-tfo-listener.pkt
new file mode 100644
index 000000000000..4a00e0d994f2
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_basic-non-tfo-listener.pkt
@@ -0,0 +1,26 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Basic TFO server test
+//
+// Server w/o TCP_FASTOPEN socket option
+
+`./defaults.sh`
+
+ 0 socket(..., SOCK_STREAM|SOCK_NONBLOCK, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+
+ +0 < S 0:10(10) win 32792 <mss 1460,sackOK,FO TFO_COOKIE>
+
+// Data is ignored since TCP_FASTOPEN is not set on the listener
+ +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK>
+
+ +0 accept(3, ..., ...) = -1 EAGAIN (Resource temporarily unavailable)
+
+// The above should block until ack comes in below.
+ +0 < . 1:31(30) ack 1 win 5840
+ +0 accept(3, ..., ...) = 4
+
+ +0 %{ assert (tcpi_options & TCPI_OPT_SYN_DATA) == 0, tcpi_options }%
+ +0 read(4, ..., 512) = 30
diff --git a/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_basic-pure-syn-data.pkt b/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_basic-pure-syn-data.pkt
new file mode 100644
index 000000000000..345ed26ff7f8
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_basic-pure-syn-data.pkt
@@ -0,0 +1,50 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Basic TFO server test
+//
+// Test that TFO-enabled server would not respond SYN-ACK with any TFO option
+// when receiving a pure SYN-data. It should respond a pure SYN-ack.
+
+`./defaults.sh`
+
+ 0 socket(..., SOCK_STREAM|SOCK_NONBLOCK, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+ +0 setsockopt(3, SOL_TCP, TCP_FASTOPEN, [1], 4) = 0
+
+ +0 < S 999000:999040(40) win 32792 <mss 1460,sackOK,TS val 100 ecr 100,nop,wscale 6>
+ +0 > S. 1234:1234(0) ack 999001 <mss 1460,sackOK,TS val 100 ecr 100,nop,wscale 8>
+ +0 < . 1:1(0) ack 1 win 100
+ +0 accept(3, ..., ...) = 4
+ +0 %{ assert (tcpi_options & TCPI_OPT_SYN_DATA) == 0, tcpi_options }%
+ +0 close(3) = 0
+
+// Test ECN-setup SYN with ECN disabled because this has happened in reality
+ +0 socket(..., SOCK_STREAM|SOCK_NONBLOCK, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+ +0 setsockopt(3, SOL_TCP, TCP_FASTOPEN, [1], 4) = 0
+
+ +0 < SEW 999000:999040(40) win 32792 <mss 1460,sackOK,TS val 100 ecr 100,nop,wscale 6>
+ +0 > S. 1234:1234(0) ack 999001 <mss 1460,sackOK,TS val 100 ecr 100,nop,wscale 8>
+ +0 < . 1:1(0) ack 1 win 100
+ +0 accept(3, ..., ...) = 4
+ +0 %{ assert (tcpi_options & TCPI_OPT_SYN_DATA) == 0, tcpi_options }%
+ +0 close(3) = 0
+
+// Test ECN-setup SYN w/ ECN enabled
+ +0 `sysctl -q net.ipv4.tcp_ecn=2`
+ +0 socket(..., SOCK_STREAM|SOCK_NONBLOCK, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+ +0 setsockopt(3, SOL_TCP, TCP_FASTOPEN, [1], 4) = 0
+
+ +0 < SEW 999000:999040(40) win 32792 <mss 1460,sackOK,TS val 100 ecr 100,nop,wscale 6>
+ +0 > SE. 1234:1234(0) ack 999001 <mss 1460,sackOK,TS val 100 ecr 100,nop,wscale 8>
+ +0 < . 1:1(0) ack 1 win 100
+ +0 accept(3, ..., ...) = 4
+ +0 %{ assert (tcpi_options & TCPI_OPT_SYN_DATA) == 0, tcpi_options }%
+ +0 close(3) = 0
diff --git a/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_basic-rw.pkt b/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_basic-rw.pkt
new file mode 100644
index 000000000000..98e6f84497cd
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_basic-rw.pkt
@@ -0,0 +1,23 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Basic TFO server test
+//
+// Test TFO server with SYN that has TFO cookie and data.
+
+`./defaults.sh`
+
+ 0 socket(..., SOCK_STREAM|SOCK_NONBLOCK, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+ +0 setsockopt(3, SOL_TCP, TCP_FASTOPEN, [1], 4) = 0
+
+ +0 < S 0:10(10) win 32792 <mss 1460,sackOK,nop,nop,FO TFO_COOKIE,nop,nop>
+ +0 > S. 0:0(0) ack 11 <mss 1460,nop,nop,sackOK>
+
+ +0 accept(3, ..., ...) = 4
+ +0 %{ assert (tcpi_options & TCPI_OPT_SYN_DATA) != 0, tcpi_options }%
+
+ +0 read(4, ..., 512) = 10
+ +0 write(4, ..., 100) = 100
+ +0 > P. 1:101(100) ack 11
diff --git a/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_basic-zero-payload.pkt b/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_basic-zero-payload.pkt
new file mode 100644
index 000000000000..95b1047ffdd5
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_basic-zero-payload.pkt
@@ -0,0 +1,26 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Basic TFO server test
+//
+// Test zero-payload packet w/ valid TFO cookie - a TFO socket will
+// still be created and accepted but read() will not return until a
+// later pkt with 10 byte.
+
+`./defaults.sh`
+
+ 0 socket(..., SOCK_STREAM|SOCK_NONBLOCK, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+ +0 setsockopt(3, SOL_TCP, TCP_FASTOPEN, [1], 4) = 0
+
+ +0 < S 0:0(0) win 32792 <mss 1460,sackOK,nop,nop,FO TFO_COOKIE,nop,nop>
+ +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK>
+ +0 accept(3, ..., ...) = 4
+ +0 %{ assert (tcpi_options & TCPI_OPT_SYN_DATA) == 0, tcpi_options }%
+
+// A TFO socket is created and is writable.
+ +0 write(4, ..., 100) = 100
+ +0 > P. 1:101(100) ack 1
+ +0...0.300 read(4, ..., 512) = 10
+ +.3 < P. 1:11(10) ack 1 win 5840
diff --git a/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_client-ack-dropped-then-recovery-ms-timestamps.pkt b/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_client-ack-dropped-then-recovery-ms-timestamps.pkt
new file mode 100644
index 000000000000..f75efd51ed0c
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_client-ack-dropped-then-recovery-ms-timestamps.pkt
@@ -0,0 +1,46 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// A reproducer case for a TFO SYNACK RTO undo bug in:
+// 794200d66273 ("tcp: undo cwnd on Fast Open spurious SYNACK retransmit")
+// This sequence that tickles this bug is:
+// - Fast Open server receives TFO SYN with data, sends SYNACK
+// - (client receives SYNACK and sends ACK, but ACK is lost)
+// - server app sends some data packets
+// - (N of the first data packets are lost)
+// - server receives client ACK that has a TS ECR matching first SYNACK,
+// and also SACKs suggesting the first N data packets were lost
+// - server performs undo of SYNACK RTO, then immediately enters recovery
+// - buggy behavior in 794200d66273 then performed an undo that caused
+// the connection to be in a bad state, in CA_Open with retrans_out != 0
+
+// Check that outbound TS Val ticks are as we would expect with 1000 usec per
+// timestamp tick:
+--tcp_ts_tick_usecs=1000
+
+`./defaults.sh`
+
+// Initialize connection
+ 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+ +0 setsockopt(3, SOL_TCP, TCP_FASTOPEN, [1], 4) = 0
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+
+ +0 < S 0:1000(1000) win 65535 <mss 1012,sackOK,TS val 1000 ecr 0,wscale 7,nop,nop,nop,FO TFO_COOKIE>
+ +0 > S. 0:0(0) ack 1001 <mss 1460,sackOK,TS val 2000 ecr 1000,nop,wscale 8>
+ +0 accept(3, ..., ...) = 4
+
+// Application writes more data
+ +.010 write(4, ..., 10000) = 10000
+ +0 > P. 1:5001(5000) ack 1001 <nop,nop,TS val 2010 ecr 1000>
+ +0 > P. 5001:10001(5000) ack 1001 <nop,nop,TS val 2010 ecr 1000>
+ +0 %{ assert tcpi_snd_cwnd == 10, tcpi_snd_cwnd }%
+
+ +0 < . 1001:1001(0) ack 1 win 257 <TS val 1010 ecr 2000,sack 2001:5001>
+ +0 > P. 1:2001(2000) ack 1001 <nop,nop,TS val 2010 ecr 1010>
+ +0 %{ assert tcpi_ca_state == TCP_CA_Recovery, tcpi_ca_state }%
+ +0 %{ assert tcpi_snd_cwnd == 7, tcpi_snd_cwnd }%
+
+ +0 < . 1001:1001(0) ack 1 win 257 <TS val 1011 ecr 2000,sack 2001:6001>
+ +0 %{ assert tcpi_ca_state == TCP_CA_Recovery, tcpi_ca_state }%
+ +0 %{ assert tcpi_snd_cwnd == 7, tcpi_snd_cwnd }%
diff --git a/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_experimental_option.pkt b/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_experimental_option.pkt
new file mode 100644
index 000000000000..c3cb0e8bdcf8
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_experimental_option.pkt
@@ -0,0 +1,37 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Test the Experimental Option
+//
+// SYN w/ FOEXP w/o cookie must generates SYN+ACK w/ FOEXP
+// w/ a valid cookie, and the cookie must be the same one
+// with one generated by IANA FO
+
+`./defaults.sh`
+
+// Request a TFO cookie by Experimental Option
+// This must generate the same TFO_COOKIE
+ 0 socket(..., SOCK_STREAM|SOCK_NONBLOCK, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+ +0 setsockopt(3, SOL_TCP, TCP_FASTOPEN, [1], 4) = 0
+
+ +0 < S 0:10(10) win 32792 <mss 1460,sackOK,nop,nop,FOEXP>
+ +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,FOEXP TFO_COOKIE>
+
+ +0 close(3) = 0
+
+// Test if FOEXP with a valid cookie creates a TFO socket
+ 0 socket(..., SOCK_STREAM|SOCK_NONBLOCK, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+ +0 setsockopt(3, SOL_TCP, TCP_FASTOPEN, [1], 4) = 0
+
+ +0 < S 0:10(10) win 32792 <mss 1460,sackOK,nop,nop,FOEXP TFO_COOKIE>
+ +0 > S. 0:0(0) ack 11 <mss 1460,nop,nop,sackOK>
+
+ +0 accept(3, ..., ...) = 4
+ +0 %{ assert (tcpi_options & TCPI_OPT_SYN_DATA) != 0, tcpi_options }%
+
+ +0 read(4, ..., 512) = 10
diff --git a/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_fin-close-socket.pkt b/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_fin-close-socket.pkt
new file mode 100644
index 000000000000..dc09f8d9a381
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_fin-close-socket.pkt
@@ -0,0 +1,30 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Send a FIN pkt with the ACK bit to a TFO socket.
+// The socket will go to TCP_CLOSE_WAIT state and data can be
+// read until the socket is closed, at which time a FIN will be sent.
+
+`./defaults.sh`
+
+ 0 socket(..., SOCK_STREAM|SOCK_NONBLOCK, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+ +0 setsockopt(3, SOL_TCP, TCP_FASTOPEN, [1], 4) = 0
+
+ +0 < S 0:10(10) win 32792 <mss 1460,sackOK,nop,nop,FO TFO_COOKIE,nop,nop>
+ +0 > S. 0:0(0) ack 11 <mss 1460,nop,nop,sackOK>
+
+// FIN is acked and the socket goes to TCP_CLOSE_WAIT state
+// in tcp_fin() called from tcp_data_queue().
+ +0 < F. 11:11(0) ack 1 win 32792
+ +0 > . 1:1(0) ack 12
+
+ +0 accept(3, ..., ...) = 4
+ +0 %{ assert (tcpi_options & TCPI_OPT_SYN_DATA) != 0, tcpi_options }%
+ +0 %{ assert tcpi_state == TCP_CLOSE_WAIT, tcpi_state }%
+
+ +0 read(4, ..., 512) = 10
+ +0 close(4) = 0
+ +0 > F. 1:1(0) ack 12
+ * > F. 1:1(0) ack 12
diff --git a/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_icmp-before-accept.pkt b/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_icmp-before-accept.pkt
new file mode 100644
index 000000000000..d5543672e2bd
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_icmp-before-accept.pkt
@@ -0,0 +1,49 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Send an ICMP host_unreachable pkt to a pending SYN_RECV req.
+//
+// If it's a TFO req, the ICMP error will cause it to switch
+// to TCP_CLOSE state but remains in the acceptor queue.
+
+--ip_version=ipv4
+
+`./defaults.sh`
+
+ 0 socket(..., SOCK_STREAM|SOCK_NONBLOCK, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+ +0 setsockopt(3, SOL_TCP, TCP_FASTOPEN, [1], 4) = 0
+
+ +0 < S 0:10(10) win 32792 <mss 1460,sackOK,nop,nop,FO TFO_COOKIE,nop,nop>
+ +0 > S. 0:0(0) ack 11 <mss 1460,nop,nop,sackOK>
+
+// Out-of-window icmp is ignored but accounted.
+ +0 `nstat > /dev/null`
+ +0 < icmp unreachable [5000:6000(1000)]
+ +0 `nstat | grep TcpExtOutOfWindowIcmps > /dev/null`
+
+// Valid ICMP unreach.
+ +0 < icmp unreachable host_unreachable [0:10(10)]
+
+// Unlike the non-TFO case, the req is still there to be accepted.
+ +0 accept(3, ..., ...) = 4
+ +0 %{ assert (tcpi_options & TCPI_OPT_SYN_DATA) != 0, tcpi_options }%
+
+// tcp_done_with_error() in tcp_v4_err() sets sk->sk_state
+// to TCP_CLOSE
+ +0 %{ assert tcpi_state == TCP_CLOSE, tcpi_state }%
+
+// The 1st read will succeed and return the data in SYN
+ +0 read(4, ..., 512) = 10
+
+// The 2nd read will fail.
+ +0 read(4, ..., 512) = -1 EHOSTUNREACH (No route to host)
+
+// But is no longer writable because it's in TCP_CLOSE state.
+ +0 write(4, ..., 100) = -1 EPIPE (Broken Pipe)
+
+// inbound pkt will trigger RST because the socket has been moved
+// off the TCP hash tables.
+ +0 < . 1:1(0) ack 1 win 32792
+ +0 > R 1:1(0)
diff --git a/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_reset-after-accept.pkt b/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_reset-after-accept.pkt
new file mode 100644
index 000000000000..040d5547ed80
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_reset-after-accept.pkt
@@ -0,0 +1,37 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Send a RST to a TFO socket after it has been accepted.
+//
+// First read() will return all the data and this is consistent
+// with the non-TFO case. Second read will return -1
+
+`./defaults.sh`
+
+ 0 socket(..., SOCK_STREAM|SOCK_NONBLOCK, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+ +0 setsockopt(3, SOL_TCP, TCP_FASTOPEN, [1], 4) = 0
+
+ +0 < S 0:10(10) win 32792 <mss 1460,sackOK,nop,nop,FO TFO_COOKIE,nop,nop>
+ +0 > S. 0:0(0) ack 11 <mss 1460,nop,nop,sackOK>
+
+ +0 accept(3, ..., ...) = 4
+ +0 %{ assert (tcpi_options & TCPI_OPT_SYN_DATA) != 0, tcpi_options }%
+ +0 %{ assert tcpi_state == TCP_SYN_RECV, tcpi_state }%
+
+// 1st read will return the data from SYN.
+// tcp_reset() sets sk->sk_err to ECONNRESET for SYN_RECV.
+ +0 < R. 11:11(0) win 32792
+ +0 %{ assert tcpi_state == TCP_CLOSE, tcpi_state }%
+
+// This one w/o ACK bit will cause the same effect.
+// +0 < R 11:11(0) win 32792
+// See Step 2 in tcp_validate_incoming().
+
+// found_ok_skb in tcp_recvmsg_locked()
+ +0 read(4, ..., 512) = 10
+
+// !copied && sk->sk_err -> sock_error(sk)
+ +0 read(4, ..., 512) = -1 ECONNRESET (Connection reset by peer)
+ +0 close(4) = 0
diff --git a/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_reset-before-accept.pkt b/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_reset-before-accept.pkt
new file mode 100644
index 000000000000..7f9de6c66cbd
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_reset-before-accept.pkt
@@ -0,0 +1,32 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Send a RST to a TFO socket before it is accepted.
+//
+// The socket won't go away and after it's accepted the data
+// in the SYN pkt can still be read. But that's about all that
+// the acceptor can do with the socket.
+
+`./defaults.sh`
+
+ 0 socket(..., SOCK_STREAM|SOCK_NONBLOCK, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+ +0 setsockopt(3, SOL_TCP, TCP_FASTOPEN, [1], 4) = 0
+
+ +0 < S 0:10(10) win 32792 <mss 1460,sackOK,nop,nop,nop,wscale 7,FO TFO_COOKIE,nop,nop>
+ +0 > S. 0:0(0) ack 11 <mss 1460,nop,nop,sackOK,nop,wscale 8>
+
+// 1st read will return the data from SYN.
+ +0 < R. 11:11(0) win 257
+
+// This one w/o ACK bit will cause the same effect.
+// +0 < R 11:11(0) win 257
+
+ +0 accept(3, ..., ...) = 4
+ +0 %{ assert (tcpi_options & TCPI_OPT_SYN_DATA) != 0, tcpi_options }%
+ +0 %{ assert tcpi_state == TCP_CLOSE, tcpi_state }%
+
+ +0 read(4, ..., 512) = 10
+ +0 read(4, ..., 512) = -1 ECONNRESET (Connection reset by peer)
+ +0 close(4) = 0
diff --git a/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_reset-close-with-unread-data.pkt b/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_reset-close-with-unread-data.pkt
new file mode 100644
index 000000000000..548a87701b5d
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_reset-close-with-unread-data.pkt
@@ -0,0 +1,32 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Send a RST to a TFO socket after it is accepted.
+//
+// The socket will change to TCP_CLOSE state with pending data so
+// write() will fail. Pending data can be still be read and close()
+// won't trigger RST if data is not read
+//
+// 565b7b2d2e63 ("tcp: do not send reset to already closed sockets")
+// https://lore.kernel.org/netdev/4C1A2502.1030502@openvz.org/
+
+`./defaults.sh`
+
+ 0 socket(..., SOCK_STREAM|SOCK_NONBLOCK, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+ +0 setsockopt(3, SOL_TCP, TCP_FASTOPEN, [1], 4) = 0
+
+ +0 < S 0:10(10) win 32792 <mss 1460,sackOK,nop,nop, FO TFO_COOKIE,nop,nop>
+ +0 > S. 0:0(0) ack 11 <mss 1460,nop,nop,sackOK>
+
+ +0 accept(3, ..., ...) = 4
+ +0 %{ assert (tcpi_options & TCPI_OPT_SYN_DATA) != 0, tcpi_options }%
+ +0 %{ assert tcpi_state == TCP_SYN_RECV, tcpi_state }%
+
+// tcp_done() sets sk->sk_state to TCP_CLOSE and clears tp->fastopen_rsk
+ +0 < R. 11:11(0) win 32792
+ +0 %{ assert tcpi_state == TCP_CLOSE, tcpi_state }%
+
+ +0 write(4, ..., 100) = -1 ECONNRESET(Connection reset by peer)
+ +0 close(4) = 0
diff --git a/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_reset-non-tfo-socket.pkt b/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_reset-non-tfo-socket.pkt
new file mode 100644
index 000000000000..20090bf77655
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_reset-non-tfo-socket.pkt
@@ -0,0 +1,37 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Send a RST to a fully established socket with pending data before
+// it is accepted.
+//
+// The socket with pending data won't go away and can still be accepted
+// with data read. But it will be in TCP_CLOSE state.
+
+`./defaults.sh`
+
+ 0 socket(..., SOCK_STREAM|SOCK_NONBLOCK, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+ +0 setsockopt(3, SOL_TCP, TCP_FASTOPEN, [1], 4) = 0
+
+// Invalid cookie, so accept() fails.
+ +0 < S 0:10(10) win 32792 <mss 1460,sackOK,nop,nop,FO aaaaaaaaaaaaaaaa,nop,nop>
+ +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK, FO TFO_COOKIE,nop,nop>
+
+ +0 accept(3, ..., ...) = -1 EAGAIN (Resource temporarily unavailable)
+
+// Complete 3WHS and send data and RST
+ +0 < . 1:1(0) ack 1 win 32792
+ +0 < . 1:11(10) ack 1 win 32792
+ +0 < R. 11:11(0) win 32792
+
+// A valid reset won't make the fully-established socket go away.
+// It's just that the acceptor will get a dead, unusable socket
+// in TCP_CLOSE state.
+ +0 accept(3, ..., ...) = 4
+ +0 %{ assert (tcpi_options & TCPI_OPT_SYN_DATA) == 0, tcpi_options }%
+ +0 %{ assert tcpi_state == TCP_CLOSE, tcpi_state }%
+
+ +0 write(4, ..., 100) = -1 ECONNRESET(Connection reset by peer)
+ +0 read(4, ..., 512) = 10
+ +0 read(4, ..., 512) = 0
diff --git a/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_sockopt-fastopen-key.pkt b/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_sockopt-fastopen-key.pkt
new file mode 100644
index 000000000000..9f52d7de3436
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_sockopt-fastopen-key.pkt
@@ -0,0 +1,74 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Test the server cookie is generated by aes64 encoding of remote and local
+// IP addresses with a master key specified via sockopt TCP_FASTOPEN_KEY
+//
+`./defaults.sh
+ ./set_sysctls.py /proc/sys/net/ipv4/tcp_fastopen_key=00000000-00000000-00000000-00000000`
+
+ 0 socket(..., SOCK_STREAM|SOCK_NONBLOCK, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+
+// Set a key of a1a1a1a1-b2b2b2b2-c3c3c3c3-d4d4d4d4 (big endian).
+// This would produce a cookie of TFO_COOKIE like many other
+// tests (which the same key but set via sysctl).
+ +0 setsockopt(3, SOL_TCP, TCP_FASTOPEN_KEY,
+ "\xa1\xa1\xa1\xa1\xb2\xb2\xb2\xb2\xc3\xc3\xc3\xc3\xd4\xd4\xd4\xd4", 16) = 0
+
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+ +0 setsockopt(3, SOL_TCP, TCP_FASTOPEN, [1], 4) = 0
+
+// Request a valid cookie TFO_COOKIE
+ +0 < S 1428932:1428942(10) win 10000 <mss 1012,nop,nop,FO,sackOK,TS val 1 ecr 0,nop,wscale 7>
+ +0 > S. 0:0(0) ack 1428933 <mss 1460,sackOK,TS val 10000 ecr 1,nop,wscale 8,FO TFO_COOKIE,nop,nop>
+ +0 < . 1:1(0) ack 1 win 257 <nop,nop,TS val 2 ecr 10000>
+ +0 accept(3, ..., ...) = 4
+ +0 %{ assert (tcpi_options & TCPI_OPT_SYN_DATA) == 0, tcpi_options }%
+
+ +0 close(4) = 0
+ +0 > F. 1:1(0) ack 1 <nop,nop,TS val 10001 ecr 2>
+ +0 < F. 1:1(0) ack 2 win 257 <nop,nop,TS val 3 ecr 10001>
+ +0 > . 2:2(0) ack 2 <nop,nop,TS val 10002 ecr 3>
+
+ +0 close(3) = 0
+
+// Restart the listener
+ +0 socket(..., SOCK_STREAM|SOCK_NONBLOCK, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+ +0 setsockopt(3, SOL_TCP, TCP_FASTOPEN, [1], 4) = 0
+
+// Test setting the key in the listen state, and produces an identical cookie
+ +0 setsockopt(3, SOL_TCP, TCP_FASTOPEN_KEY,
+ "\xa1\xa1\xa1\xa1\xb2\xb2\xb2\xb2\xc3\xc3\xc3\xc3\xd4\xd4\xd4\xd4", 16) = 0
+
+ +0 < S 6814000:6815000(1000) win 10000 <mss 1012,nop,nop,FO TFO_COOKIE,sackOK,TS val 10 ecr 0,nop,wscale 7>
+ +0 > S. 0:0(0) ack 6815001 <mss 1460,sackOK,TS val 10000 ecr 10,nop,wscale 8>
+ +0 accept(3, ..., ...) = 4
+ +0 %{ assert (tcpi_options & TCPI_OPT_SYN_DATA) != 0, tcpi_options }%
+ +0 < . 1001:1001(0) ack 1 win 257 <nop,nop,TS val 12 ecr 10000>
+ +0 read(4, ..., 8192) = 1000
+
+ +0 close(4) = 0
+ +0 > F. 1:1(0) ack 1001 <nop,nop,TS val 10101 ecr 12>
+ +0 < F. 1001:1001(0) ack 2 win 257 <nop,nop,TS val 112 ecr 10101>
+ +0 > . 2:2(0) ack 1002 <nop,nop,TS val 10102 ecr 112>
+
+ +0 close(3) = 0
+
+// Restart the listener
+ +0 socket(..., SOCK_STREAM|SOCK_NONBLOCK, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+ +0 setsockopt(3, SOL_TCP, TCP_FASTOPEN, [1], 4) = 0
+
+// Test invalid key length (must be 16 bytes)
+ +0 setsockopt(3, SOL_TCP, TCP_FASTOPEN_KEY, "", 0) = -1 (Invalid Argument)
+ +0 setsockopt(3, SOL_TCP, TCP_FASTOPEN_KEY, "", 3) = -1 (Invalid Argument)
+
+// Previous cookie won't be accepted b/c this listener uses the global key (0-0-0-0)
+ +0 < S 6814000:6815000(1000) win 10000 <mss 1012,nop,nop,FO TFO_COOKIE,sackOK,TS val 10 ecr 0,nop,wscale 7>
+ +0 > S. 0:0(0) ack 6814001 <mss 1460,sackOK,TS val 10000 ecr 10,nop,wscale 8,FO TFO_COOKIE_ZERO,nop,nop>
diff --git a/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_trigger-rst-listener-closed.pkt b/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_trigger-rst-listener-closed.pkt
new file mode 100644
index 000000000000..e82e06da44c9
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_trigger-rst-listener-closed.pkt
@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Close a listener socket with pending TFO child.
+// This will trigger RST pkt to go out.
+
+`./defaults.sh`
+
+ 0 socket(..., SOCK_STREAM|SOCK_NONBLOCK, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+ +0 setsockopt(3, SOL_TCP, TCP_FASTOPEN, [1], 4) = 0
+
+ +0 < S 0:10(10) win 32792 <mss 1460,sackOK,nop,nop,FO TFO_COOKIE,nop,nop>
+ +0 > S. 0:0(0) ack 11 <mss 1460,nop,nop,sackOK>
+
+// RST pkt is generated for each not-yet-accepted TFO child.
+// inet_csk_listen_stop() -> inet_child_forget() -> tcp_disconnect()
+// -> tcp_need_reset() is true for SYN_RECV
+ +0 close(3) = 0
+ +0 > R. 1:1(0) ack 11
diff --git a/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_trigger-rst-reconnect.pkt b/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_trigger-rst-reconnect.pkt
new file mode 100644
index 000000000000..2a148bb14cbf
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_trigger-rst-reconnect.pkt
@@ -0,0 +1,30 @@
+// SPDX-License-Identifier: GPL-2.0
+`./defaults.sh
+ ./set_sysctls.py /proc/sys/net/ipv4/tcp_timestamps=0`
+
+ 0 socket(..., SOCK_STREAM|SOCK_NONBLOCK, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+ +0 setsockopt(3, SOL_TCP, TCP_FASTOPEN, [1], 4) = 0
+
+ +0 < S 0:10(10) win 32792 <mss 1460,nop,nop,sackOK,nop,nop,FO TFO_COOKIE>
+ +0 > S. 0:0(0) ack 11 win 65535 <mss 1460,nop,nop,sackOK>
+
+// sk->sk_state is TCP_SYN_RECV
+ +0 accept(3, ..., ...) = 4
+ +0 %{ assert tcpi_state == TCP_SYN_RECV, tcpi_state }%
+
+// tcp_disconnect() sets sk->sk_state to TCP_CLOSE
+ +0 connect(4, AF_UNSPEC, ...) = 0
+ +0 > R. 1:1(0) ack 11 win 65535
+ +0 %{ assert tcpi_state == TCP_CLOSE, tcpi_state }%
+
+// connect() sets sk->sk_state to TCP_SYN_SENT
+ +0 fcntl(4, F_SETFL, O_RDWR|O_NONBLOCK) = 0
+ +0 connect(4, ..., ...) = -1 EINPROGRESS (Operation is now in progress)
+ +0 > S 0:0(0) win 65535 <mss 1460,nop,nop,sackOK,nop,wscale 8>
+ +0 %{ assert tcpi_state == TCP_SYN_SENT, tcpi_state }%
+
+// tp->fastopen_rsk must be NULL
+ +1 > S 0:0(0) win 65535 <mss 1460,nop,nop,sackOK,nop,wscale 8>
diff --git a/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_trigger-rst-unread-data-closed.pkt b/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_trigger-rst-unread-data-closed.pkt
new file mode 100644
index 000000000000..09fb63f78a0e
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_trigger-rst-unread-data-closed.pkt
@@ -0,0 +1,23 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Close a TFO socket with unread data.
+// This will trigger a RST pkt.
+
+`./defaults.sh`
+
+ 0 socket(..., SOCK_STREAM|SOCK_NONBLOCK, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+ +0 setsockopt(3, SOL_TCP, TCP_FASTOPEN, [1], 4) = 0
+
+ +0 < S 0:10(10) win 32792 <mss 1460,sackOK,nop,nop,FO TFO_COOKIE,nop,nop>
+ +0 > S. 0:0(0) ack 11 <mss 1460,nop,nop,sackOK>
+
+ +0 accept(3, ..., ...) = 4
+ +0 %{ assert (tcpi_options & TCPI_OPT_SYN_DATA) != 0, tcpi_options }%
+ +0 %{ assert tcpi_state == TCP_SYN_RECV, tcpi_state }%
+
+// data_was_unread == true in __tcp_close()
+ +0 close(4) = 0
+ +0 > R. 1:1(0) ack 11
diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index 88e914c4eef9..a3323c21f001 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -1089,10 +1089,11 @@ cleanup() {
cleanup_all_ns
- ip link del veth_A-C 2>/dev/null
- ip link del veth_A-R1 2>/dev/null
- cleanup_del_ovs_internal
- cleanup_del_ovs_vswitchd
+ [ -e "/sys/class/net/veth_A-C" ] && ip link del veth_A-C
+ [ -e "/sys/class/net/veth_A-R1" ] && ip link del veth_A-R1
+ [ -e "/sys/class/net/ovs_br0" ] && cleanup_del_ovs_internal
+ [ -e "/sys/class/net/ovs_br0" ] && cleanup_del_ovs_vswitchd
+
rm -f "$tmpoutfile"
}
diff --git a/tools/testing/selftests/net/psock_lib.h b/tools/testing/selftests/net/psock_lib.h
index 6e4fef560873..067265b0a554 100644
--- a/tools/testing/selftests/net/psock_lib.h
+++ b/tools/testing/selftests/net/psock_lib.h
@@ -22,10 +22,6 @@
#define PORT_BASE 8000
-#ifndef __maybe_unused
-# define __maybe_unused __attribute__ ((__unused__))
-#endif
-
static __maybe_unused void pair_udp_setfilter(int fd)
{
/* the filter below checks for all of the following conditions that
diff --git a/tools/testing/selftests/net/psock_tpacket.c b/tools/testing/selftests/net/psock_tpacket.c
index 221270cee3ea..2938045c5cf9 100644
--- a/tools/testing/selftests/net/psock_tpacket.c
+++ b/tools/testing/selftests/net/psock_tpacket.c
@@ -22,6 +22,7 @@
* - TPACKET_V3: RX_RING
*/
+#undef NDEBUG
#include <stdio.h>
#include <stdlib.h>
#include <sys/types.h>
@@ -33,7 +34,6 @@
#include <ctype.h>
#include <fcntl.h>
#include <unistd.h>
-#include <bits/wordsize.h>
#include <net/ethernet.h>
#include <netinet/ip.h>
#include <arpa/inet.h>
@@ -785,7 +785,7 @@ static int test_kernel_bit_width(void)
static int test_user_bit_width(void)
{
- return __WORDSIZE;
+ return sizeof(long) * 8;
}
static const char *tpacket_str[] = {
diff --git a/tools/testing/selftests/net/route_hint.sh b/tools/testing/selftests/net/route_hint.sh
new file mode 100755
index 000000000000..2db01ece0cc1
--- /dev/null
+++ b/tools/testing/selftests/net/route_hint.sh
@@ -0,0 +1,79 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# This test ensures directed broadcast routes use dst hint mechanism
+
+source lib.sh
+
+CLIENT_IP4="192.168.0.1"
+SERVER_IP4="192.168.0.2"
+BROADCAST_ADDRESS="192.168.0.255"
+
+setup() {
+ setup_ns CLIENT_NS SERVER_NS
+
+ ip -net "${SERVER_NS}" link add link1 type veth peer name link0 netns "${CLIENT_NS}"
+
+ ip -net "${CLIENT_NS}" link set link0 up
+ ip -net "${CLIENT_NS}" addr add "${CLIENT_IP4}/24" dev link0
+
+ ip -net "${SERVER_NS}" link set link1 up
+ ip -net "${SERVER_NS}" addr add "${SERVER_IP4}/24" dev link1
+
+ ip netns exec "${CLIENT_NS}" ethtool -K link0 tcp-segmentation-offload off
+ ip netns exec "${SERVER_NS}" sh -c "echo 500000000 > /sys/class/net/link1/gro_flush_timeout"
+ ip netns exec "${SERVER_NS}" sh -c "echo 1 > /sys/class/net/link1/napi_defer_hard_irqs"
+ ip netns exec "${SERVER_NS}" ethtool -K link1 generic-receive-offload on
+}
+
+cleanup() {
+ ip -net "${SERVER_NS}" link del link1
+ cleanup_ns "${CLIENT_NS}" "${SERVER_NS}"
+}
+
+directed_bcast_hint_test()
+{
+ local rc=0
+
+ echo "Testing for directed broadcast route hint"
+
+ orig_in_brd=$(ip netns exec "${SERVER_NS}" lnstat -j -i1 -c1 | jq '.in_brd')
+ ip netns exec "${CLIENT_NS}" mausezahn link0 -a own -b bcast -A "${CLIENT_IP4}" \
+ -B "${BROADCAST_ADDRESS}" -c1 -t tcp "sp=1-100,dp=1234,s=1,a=0" -p 5 -q
+ sleep 1
+ new_in_brd=$(ip netns exec "${SERVER_NS}" lnstat -j -i1 -c1 | jq '.in_brd')
+
+ res=$(echo "${new_in_brd} - ${orig_in_brd}" | bc)
+
+ if [ "${res}" -lt 100 ]; then
+ echo "[ OK ]"
+ rc="${ksft_pass}"
+ else
+ echo "[FAIL] expected in_brd to be under 100, got ${res}"
+ rc="${ksft_fail}"
+ fi
+
+ return "${rc}"
+}
+
+if [ ! -x "$(command -v mausezahn)" ]; then
+ echo "SKIP: Could not run test without mausezahn tool"
+ exit "${ksft_skip}"
+fi
+
+if [ ! -x "$(command -v jq)" ]; then
+ echo "SKIP: Could not run test without jq tool"
+ exit "${ksft_skip}"
+fi
+
+if [ ! -x "$(command -v bc)" ]; then
+ echo "SKIP: Could not run test without bc tool"
+ exit "${ksft_skip}"
+fi
+
+trap cleanup EXIT
+
+setup
+
+directed_bcast_hint_test
+exit $?
diff --git a/tools/testing/selftests/net/rps_default_mask.sh b/tools/testing/selftests/net/rps_default_mask.sh
index 4287a8529890..b200019b3c80 100755
--- a/tools/testing/selftests/net/rps_default_mask.sh
+++ b/tools/testing/selftests/net/rps_default_mask.sh
@@ -54,16 +54,16 @@ cleanup
echo 1 > /proc/sys/net/core/rps_default_mask
setup
-chk_rps "changing rps_default_mask dont affect existing devices" "" lo $INITIAL_RPS_DEFAULT_MASK
+chk_rps "changing rps_default_mask doesn't affect existing devices" "" lo $INITIAL_RPS_DEFAULT_MASK
echo 3 > /proc/sys/net/core/rps_default_mask
-chk_rps "changing rps_default_mask dont affect existing netns" $NETNS lo 0
+chk_rps "changing rps_default_mask doesn't affect existing netns" $NETNS lo 0
ip link add name $VETH type veth peer netns $NETNS name $VETH
ip link set dev $VETH up
ip -n $NETNS link set dev $VETH up
-chk_rps "changing rps_default_mask affect newly created devices" "" $VETH 3
-chk_rps "changing rps_default_mask don't affect newly child netns[II]" $NETNS $VETH 0
+chk_rps "changing rps_default_mask affects newly created devices" "" $VETH 3
+chk_rps "changing rps_default_mask doesn't affect newly child netns[II]" $NETNS $VETH 0
ip link del dev $VETH
ip netns del $NETNS
@@ -72,8 +72,8 @@ chk_rps "rps_default_mask is 0 by default in child netns" "$NETNS" lo 0
ip netns exec $NETNS sysctl -qw net.core.rps_default_mask=1
ip link add name $VETH type veth peer netns $NETNS name $VETH
-chk_rps "changing rps_default_mask in child ns don't affect the main one" "" lo $INITIAL_RPS_DEFAULT_MASK
+chk_rps "changing rps_default_mask in child ns doesn't affect the main one" "" lo $INITIAL_RPS_DEFAULT_MASK
chk_rps "changing rps_default_mask in child ns affects new childns devices" $NETNS $VETH 1
-chk_rps "changing rps_default_mask in child ns don't affect existing devices" $NETNS lo 0
+chk_rps "changing rps_default_mask in child ns doesn't affect existing devices" $NETNS lo 0
exit $ret
diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh
index d6c00efeb664..dbf77513f617 100755
--- a/tools/testing/selftests/net/rtnetlink.sh
+++ b/tools/testing/selftests/net/rtnetlink.sh
@@ -313,6 +313,8 @@ kci_test_addrlft()
slowwait 5 check_addr_not_exist "$devdummy" "10.23.11."
if [ $? -eq 1 ]; then
+ # troubleshoot the reason for our failure
+ run_cmd ip addr show dev "$devdummy"
check_err 1
end_test "FAIL: preferred_lft addresses remaining"
return
@@ -323,6 +325,11 @@ kci_test_addrlft()
kci_test_promote_secondaries()
{
+ run_cmd ifconfig "$devdummy"
+ if [ $ret -ne 0 ]; then
+ end_test "SKIP: ifconfig not installed"
+ return $ksft_skip
+ fi
promote=$(sysctl -n net.ipv4.conf.$devdummy.promote_secondaries)
sysctl -q net.ipv4.conf.$devdummy.promote_secondaries=1
@@ -519,7 +526,7 @@ kci_test_encap_fou()
run_cmd_fail ip -netns "$testns" fou del port 9999
run_cmd ip -netns "$testns" fou del port 7777
if [ $ret -ne 0 ]; then
- end_test "FAIL: fou"s
+ end_test "FAIL: fou"
return 1
fi
@@ -1201,6 +1208,12 @@ do_test_address_proto()
local ret=0
local err
+ run_cmd_grep 'proto' ip address help
+ if [ $? -ne 0 ];then
+ end_test "SKIP: addr proto ${what}: iproute2 too old"
+ return $ksft_skip
+ fi
+
ip address add dev "$devdummy" "$addr3"
check_err $?
proto=$(address_get_proto "$addr3")
diff --git a/tools/testing/selftests/net/socket.c b/tools/testing/selftests/net/socket.c
index db1aeb8c5d1e..be1080003c61 100644
--- a/tools/testing/selftests/net/socket.c
+++ b/tools/testing/selftests/net/socket.c
@@ -39,6 +39,7 @@ static int run_tests(void)
{
char err_string1[ERR_STRING_SZ];
char err_string2[ERR_STRING_SZ];
+ const char *msg1, *msg2;
int i, err;
err = 0;
@@ -56,13 +57,13 @@ static int run_tests(void)
errno == -s->expect)
continue;
- strerror_r(-s->expect, err_string1, ERR_STRING_SZ);
- strerror_r(errno, err_string2, ERR_STRING_SZ);
+ msg1 = strerror_r(-s->expect, err_string1, ERR_STRING_SZ);
+ msg2 = strerror_r(errno, err_string2, ERR_STRING_SZ);
fprintf(stderr, "socket(%d, %d, %d) expected "
"err (%s) got (%s)\n",
s->domain, s->type, s->protocol,
- err_string1, err_string2);
+ msg1, msg2);
err = -1;
break;
@@ -70,12 +71,12 @@ static int run_tests(void)
close(fd);
if (s->expect < 0) {
- strerror_r(errno, err_string1, ERR_STRING_SZ);
+ msg1 = strerror_r(errno, err_string1, ERR_STRING_SZ);
fprintf(stderr, "socket(%d, %d, %d) expected "
"success got err (%s)\n",
s->domain, s->type, s->protocol,
- err_string1);
+ msg1);
err = -1;
break;
diff --git a/tools/testing/selftests/net/tcp_port_share.c b/tools/testing/selftests/net/tcp_port_share.c
new file mode 100644
index 000000000000..4c39d599dfce
--- /dev/null
+++ b/tools/testing/selftests/net/tcp_port_share.c
@@ -0,0 +1,258 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+// Copyright (c) 2025 Cloudflare, Inc.
+
+/* Tests for TCP port sharing (bind bucket reuse). */
+
+#include <arpa/inet.h>
+#include <net/if.h>
+#include <sys/ioctl.h>
+#include <fcntl.h>
+#include <sched.h>
+#include <stdlib.h>
+
+#include "../kselftest_harness.h"
+
+#define DST_PORT 30000
+#define SRC_PORT 40000
+
+struct sockaddr_inet {
+ union {
+ struct sockaddr_storage ss;
+ struct sockaddr_in6 v6;
+ struct sockaddr_in v4;
+ struct sockaddr sa;
+ };
+ socklen_t len;
+ char str[INET6_ADDRSTRLEN + __builtin_strlen("[]:65535") + 1];
+};
+
+const int one = 1;
+
+static int disconnect(int fd)
+{
+ return connect(fd, &(struct sockaddr){ AF_UNSPEC }, sizeof(struct sockaddr));
+}
+
+static int getsockname_port(int fd)
+{
+ struct sockaddr_inet addr = {};
+ int err;
+
+ addr.len = sizeof(addr);
+ err = getsockname(fd, &addr.sa, &addr.len);
+ if (err)
+ return -1;
+
+ switch (addr.sa.sa_family) {
+ case AF_INET:
+ return ntohs(addr.v4.sin_port);
+ case AF_INET6:
+ return ntohs(addr.v6.sin6_port);
+ default:
+ errno = EAFNOSUPPORT;
+ return -1;
+ }
+}
+
+static void make_inet_addr(int af, const char *ip, __u16 port,
+ struct sockaddr_inet *addr)
+{
+ const char *fmt = "";
+
+ memset(addr, 0, sizeof(*addr));
+
+ switch (af) {
+ case AF_INET:
+ addr->len = sizeof(addr->v4);
+ addr->v4.sin_family = af;
+ addr->v4.sin_port = htons(port);
+ inet_pton(af, ip, &addr->v4.sin_addr);
+ fmt = "%s:%hu";
+ break;
+ case AF_INET6:
+ addr->len = sizeof(addr->v6);
+ addr->v6.sin6_family = af;
+ addr->v6.sin6_port = htons(port);
+ inet_pton(af, ip, &addr->v6.sin6_addr);
+ fmt = "[%s]:%hu";
+ break;
+ }
+
+ snprintf(addr->str, sizeof(addr->str), fmt, ip, port);
+}
+
+FIXTURE(tcp_port_share) {};
+
+FIXTURE_VARIANT(tcp_port_share) {
+ int domain;
+ /* IP to listen on and connect to */
+ const char *dst_ip;
+ /* Primary IP to connect from */
+ const char *src1_ip;
+ /* Secondary IP to connect from */
+ const char *src2_ip;
+ /* IP to bind to in order to block the source port */
+ const char *bind_ip;
+};
+
+FIXTURE_VARIANT_ADD(tcp_port_share, ipv4) {
+ .domain = AF_INET,
+ .dst_ip = "127.0.0.1",
+ .src1_ip = "127.1.1.1",
+ .src2_ip = "127.2.2.2",
+ .bind_ip = "127.3.3.3",
+};
+
+FIXTURE_VARIANT_ADD(tcp_port_share, ipv6) {
+ .domain = AF_INET6,
+ .dst_ip = "::1",
+ .src1_ip = "2001:db8::1",
+ .src2_ip = "2001:db8::2",
+ .bind_ip = "2001:db8::3",
+};
+
+FIXTURE_SETUP(tcp_port_share)
+{
+ int sc;
+
+ ASSERT_EQ(unshare(CLONE_NEWNET), 0);
+ ASSERT_EQ(system("ip link set dev lo up"), 0);
+ ASSERT_EQ(system("ip addr add dev lo 2001:db8::1/32 nodad"), 0);
+ ASSERT_EQ(system("ip addr add dev lo 2001:db8::2/32 nodad"), 0);
+ ASSERT_EQ(system("ip addr add dev lo 2001:db8::3/32 nodad"), 0);
+
+ sc = open("/proc/sys/net/ipv4/ip_local_port_range", O_WRONLY);
+ ASSERT_GE(sc, 0);
+ ASSERT_GT(dprintf(sc, "%hu %hu\n", SRC_PORT, SRC_PORT), 0);
+ ASSERT_EQ(close(sc), 0);
+}
+
+FIXTURE_TEARDOWN(tcp_port_share) {}
+
+/* Verify that an ephemeral port becomes available again after the socket
+ * bound to it and blocking it from reuse is closed.
+ */
+TEST_F(tcp_port_share, can_reuse_port_after_bind_and_close)
+{
+ const typeof(variant) v = variant;
+ struct sockaddr_inet addr;
+ int c1, c2, ln, pb;
+
+ /* Listen on <dst_ip>:<DST_PORT> */
+ ln = socket(v->domain, SOCK_STREAM, 0);
+ ASSERT_GE(ln, 0) TH_LOG("socket(): %m");
+ ASSERT_EQ(setsockopt(ln, SOL_SOCKET, SO_REUSEADDR, &one, sizeof(one)), 0);
+
+ make_inet_addr(v->domain, v->dst_ip, DST_PORT, &addr);
+ ASSERT_EQ(bind(ln, &addr.sa, addr.len), 0) TH_LOG("bind(%s): %m", addr.str);
+ ASSERT_EQ(listen(ln, 2), 0);
+
+ /* Connect from <src1_ip>:<SRC_PORT> */
+ c1 = socket(v->domain, SOCK_STREAM, 0);
+ ASSERT_GE(c1, 0) TH_LOG("socket(): %m");
+ ASSERT_EQ(setsockopt(c1, SOL_IP, IP_BIND_ADDRESS_NO_PORT, &one, sizeof(one)), 0);
+
+ make_inet_addr(v->domain, v->src1_ip, 0, &addr);
+ ASSERT_EQ(bind(c1, &addr.sa, addr.len), 0) TH_LOG("bind(%s): %m", addr.str);
+
+ make_inet_addr(v->domain, v->dst_ip, DST_PORT, &addr);
+ ASSERT_EQ(connect(c1, &addr.sa, addr.len), 0) TH_LOG("connect(%s): %m", addr.str);
+ ASSERT_EQ(getsockname_port(c1), SRC_PORT);
+
+ /* Bind to <bind_ip>:<SRC_PORT>. Block the port from reuse. */
+ pb = socket(v->domain, SOCK_STREAM, 0);
+ ASSERT_GE(pb, 0) TH_LOG("socket(): %m");
+ ASSERT_EQ(setsockopt(pb, SOL_SOCKET, SO_REUSEADDR, &one, sizeof(one)), 0);
+
+ make_inet_addr(v->domain, v->bind_ip, SRC_PORT, &addr);
+ ASSERT_EQ(bind(pb, &addr.sa, addr.len), 0) TH_LOG("bind(%s): %m", addr.str);
+
+ /* Try to connect from <src2_ip>:<SRC_PORT>. Expect failure. */
+ c2 = socket(v->domain, SOCK_STREAM, 0);
+ ASSERT_GE(c2, 0) TH_LOG("socket");
+ ASSERT_EQ(setsockopt(c2, SOL_IP, IP_BIND_ADDRESS_NO_PORT, &one, sizeof(one)), 0);
+
+ make_inet_addr(v->domain, v->src2_ip, 0, &addr);
+ ASSERT_EQ(bind(c2, &addr.sa, addr.len), 0) TH_LOG("bind(%s): %m", addr.str);
+
+ make_inet_addr(v->domain, v->dst_ip, DST_PORT, &addr);
+ ASSERT_EQ(connect(c2, &addr.sa, addr.len), -1) TH_LOG("connect(%s)", addr.str);
+ ASSERT_EQ(errno, EADDRNOTAVAIL) TH_LOG("%m");
+
+ /* Unbind from <bind_ip>:<SRC_PORT>. Unblock the port for reuse. */
+ ASSERT_EQ(close(pb), 0);
+
+ /* Connect again from <src2_ip>:<SRC_PORT> */
+ EXPECT_EQ(connect(c2, &addr.sa, addr.len), 0) TH_LOG("connect(%s): %m", addr.str);
+ EXPECT_EQ(getsockname_port(c2), SRC_PORT);
+
+ ASSERT_EQ(close(c2), 0);
+ ASSERT_EQ(close(c1), 0);
+ ASSERT_EQ(close(ln), 0);
+}
+
+/* Verify that a socket auto-bound during connect() blocks port reuse after
+ * disconnect (connect(AF_UNSPEC)) followed by an explicit port bind().
+ */
+TEST_F(tcp_port_share, port_block_after_disconnect)
+{
+ const typeof(variant) v = variant;
+ struct sockaddr_inet addr;
+ int c1, c2, ln, pb;
+
+ /* Listen on <dst_ip>:<DST_PORT> */
+ ln = socket(v->domain, SOCK_STREAM, 0);
+ ASSERT_GE(ln, 0) TH_LOG("socket(): %m");
+ ASSERT_EQ(setsockopt(ln, SOL_SOCKET, SO_REUSEADDR, &one, sizeof(one)), 0);
+
+ make_inet_addr(v->domain, v->dst_ip, DST_PORT, &addr);
+ ASSERT_EQ(bind(ln, &addr.sa, addr.len), 0) TH_LOG("bind(%s): %m", addr.str);
+ ASSERT_EQ(listen(ln, 2), 0);
+
+ /* Connect from <src1_ip>:<SRC_PORT> */
+ c1 = socket(v->domain, SOCK_STREAM, 0);
+ ASSERT_GE(c1, 0) TH_LOG("socket(): %m");
+ ASSERT_EQ(setsockopt(c1, SOL_IP, IP_BIND_ADDRESS_NO_PORT, &one, sizeof(one)), 0);
+
+ make_inet_addr(v->domain, v->src1_ip, 0, &addr);
+ ASSERT_EQ(bind(c1, &addr.sa, addr.len), 0) TH_LOG("bind(%s): %m", addr.str);
+
+ make_inet_addr(v->domain, v->dst_ip, DST_PORT, &addr);
+ ASSERT_EQ(connect(c1, &addr.sa, addr.len), 0) TH_LOG("connect(%s): %m", addr.str);
+ ASSERT_EQ(getsockname_port(c1), SRC_PORT);
+
+ /* Disconnect the socket and bind it to <bind_ip>:<SRC_PORT> to block the port */
+ ASSERT_EQ(disconnect(c1), 0) TH_LOG("disconnect: %m");
+ ASSERT_EQ(setsockopt(c1, SOL_SOCKET, SO_REUSEADDR, &one, sizeof(one)), 0);
+
+ make_inet_addr(v->domain, v->bind_ip, SRC_PORT, &addr);
+ ASSERT_EQ(bind(c1, &addr.sa, addr.len), 0) TH_LOG("bind(%s): %m", addr.str);
+
+ /* Trigger port-addr bucket state update with another bind() and close() */
+ pb = socket(v->domain, SOCK_STREAM, 0);
+ ASSERT_GE(pb, 0) TH_LOG("socket(): %m");
+ ASSERT_EQ(setsockopt(pb, SOL_SOCKET, SO_REUSEADDR, &one, sizeof(one)), 0);
+
+ make_inet_addr(v->domain, v->bind_ip, SRC_PORT, &addr);
+ ASSERT_EQ(bind(pb, &addr.sa, addr.len), 0) TH_LOG("bind(%s): %m", addr.str);
+
+ ASSERT_EQ(close(pb), 0);
+
+ /* Connect from <src2_ip>:<SRC_PORT>. Expect failure. */
+ c2 = socket(v->domain, SOCK_STREAM, 0);
+ ASSERT_GE(c2, 0) TH_LOG("socket: %m");
+ ASSERT_EQ(setsockopt(c2, SOL_IP, IP_BIND_ADDRESS_NO_PORT, &one, sizeof(one)), 0);
+
+ make_inet_addr(v->domain, v->src2_ip, 0, &addr);
+ ASSERT_EQ(bind(c2, &addr.sa, addr.len), 0) TH_LOG("bind(%s): %m", addr.str);
+
+ make_inet_addr(v->domain, v->dst_ip, DST_PORT, &addr);
+ EXPECT_EQ(connect(c2, &addr.sa, addr.len), -1) TH_LOG("connect(%s)", addr.str);
+ EXPECT_EQ(errno, EADDRNOTAVAIL) TH_LOG("%m");
+
+ ASSERT_EQ(close(c2), 0);
+ ASSERT_EQ(close(c1), 0);
+ ASSERT_EQ(close(ln), 0);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/net/test_bridge_backup_port.sh b/tools/testing/selftests/net/test_bridge_backup_port.sh
index 1b3f89e2b86e..2a7224fe74f2 100755
--- a/tools/testing/selftests/net/test_bridge_backup_port.sh
+++ b/tools/testing/selftests/net/test_bridge_backup_port.sh
@@ -315,6 +315,29 @@ backup_port()
tc_check_packets $sw1 "dev vx0 egress" 101 1
log_test $? 0 "No forwarding out of vx0"
+ # Check that packets are forwarded out of vx0 when swp1 is
+ # administratively down and out of swp1 when it is administratively up
+ # again.
+ run_cmd "ip -n $sw1 link set dev swp1 down"
+ busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 disabled
+ log_test $? 0 "swp1 administratively down"
+
+ run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
+ tc_check_packets $sw1 "dev swp1 egress" 101 3
+ log_test $? 0 "No forwarding out of swp1"
+ tc_check_packets $sw1 "dev vx0 egress" 101 2
+ log_test $? 0 "Forwarding out of vx0"
+
+ run_cmd "ip -n $sw1 link set dev swp1 up"
+ busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 forwarding
+ log_test $? 0 "swp1 administratively up"
+
+ run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
+ tc_check_packets $sw1 "dev swp1 egress" 101 4
+ log_test $? 0 "Forwarding out of swp1"
+ tc_check_packets $sw1 "dev vx0 egress" 101 2
+ log_test $? 0 "No forwarding out of vx0"
+
# Remove vx0 as the backup port of swp1 and check that packets are no
# longer forwarded out of vx0 when swp1 does not have a carrier.
run_cmd "bridge -n $sw1 link set dev swp1 nobackup_port"
@@ -322,9 +345,9 @@ backup_port()
log_test $? 1 "vx0 not configured as backup port of swp1"
run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
- tc_check_packets $sw1 "dev swp1 egress" 101 4
+ tc_check_packets $sw1 "dev swp1 egress" 101 5
log_test $? 0 "Forwarding out of swp1"
- tc_check_packets $sw1 "dev vx0 egress" 101 1
+ tc_check_packets $sw1 "dev vx0 egress" 101 2
log_test $? 0 "No forwarding out of vx0"
run_cmd "ip -n $sw1 link set dev swp1 carrier off"
@@ -332,9 +355,9 @@ backup_port()
log_test $? 0 "swp1 carrier off"
run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
- tc_check_packets $sw1 "dev swp1 egress" 101 4
+ tc_check_packets $sw1 "dev swp1 egress" 101 5
log_test $? 0 "No forwarding out of swp1"
- tc_check_packets $sw1 "dev vx0 egress" 101 1
+ tc_check_packets $sw1 "dev vx0 egress" 101 2
log_test $? 0 "No forwarding out of vx0"
}
diff --git a/tools/testing/selftests/net/test_vxlan_fdb_changelink.sh b/tools/testing/selftests/net/test_vxlan_fdb_changelink.sh
index 062f957950af..8b414d0edada 100755
--- a/tools/testing/selftests/net/test_vxlan_fdb_changelink.sh
+++ b/tools/testing/selftests/net/test_vxlan_fdb_changelink.sh
@@ -21,7 +21,7 @@ test_set_remote()
{
RET=0
- ip_link_add vx up type vxlan id 2000 dstport 4789
+ adf_ip_link_add vx up type vxlan id 2000 dstport 4789
bridge fdb ap dev vx 00:00:00:00:00:00 dst 192.0.2.20 self permanent
bridge fdb ap dev vx 00:00:00:00:00:00 dst 192.0.2.30 self permanent
check_remotes "fdb append"
@@ -74,12 +74,12 @@ test_change_mc_remote()
{
check_command netstat || return
- ip_link_add v1 up type veth peer name v2
- ip_link_set_up v2
+ adf_ip_link_add v1 up type veth peer name v2
+ adf_ip_link_set_up v2
RET=0
- ip_link_add vx up type vxlan dstport 4789 \
+ adf_ip_link_add vx up type vxlan dstport 4789 \
local 192.0.2.1 $(fmt_remote 224.1.1.1) dev v1 vni 1000
check_membership "group=224.1.1.1 fail=0" \
diff --git a/tools/testing/selftests/net/test_vxlan_nh.sh b/tools/testing/selftests/net/test_vxlan_nh.sh
new file mode 100755
index 000000000000..20f3369f776b
--- /dev/null
+++ b/tools/testing/selftests/net/test_vxlan_nh.sh
@@ -0,0 +1,223 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source lib.sh
+TESTS="
+ basic_tx_ipv4
+ basic_tx_ipv6
+ learning
+ proxy_ipv4
+ proxy_ipv6
+"
+VERBOSE=0
+
+################################################################################
+# Utilities
+
+run_cmd()
+{
+ local cmd="$1"
+ local out
+ local stderr="2>/dev/null"
+
+ if [ "$VERBOSE" = "1" ]; then
+ echo "COMMAND: $cmd"
+ stderr=
+ fi
+
+ out=$(eval "$cmd" "$stderr")
+ rc=$?
+ if [ "$VERBOSE" -eq 1 ] && [ -n "$out" ]; then
+ echo " $out"
+ fi
+
+ return $rc
+}
+
+################################################################################
+# Cleanup
+
+exit_cleanup_all()
+{
+ cleanup_all_ns
+ exit "${EXIT_STATUS}"
+}
+
+################################################################################
+# Tests
+
+nh_stats_get()
+{
+ ip -n "$ns1" -s -j nexthop show id 10 | jq ".[][\"group_stats\"][][\"packets\"]"
+}
+
+tc_stats_get()
+{
+ tc_rule_handle_stats_get "dev dummy1 egress" 101 ".packets" "-n $ns1"
+}
+
+basic_tx_common()
+{
+ local af_str=$1; shift
+ local proto=$1; shift
+ local local_addr=$1; shift
+ local plen=$1; shift
+ local remote_addr=$1; shift
+
+ RET=0
+
+ # Test basic Tx functionality. Check that stats are incremented on
+ # both the FDB nexthop group and the egress device.
+
+ run_cmd "ip -n $ns1 link add name dummy1 up type dummy"
+ run_cmd "ip -n $ns1 route add $remote_addr/$plen dev dummy1"
+ run_cmd "tc -n $ns1 qdisc add dev dummy1 clsact"
+ run_cmd "tc -n $ns1 filter add dev dummy1 egress proto $proto pref 1 handle 101 flower ip_proto udp dst_ip $remote_addr dst_port 4789 action pass"
+
+ run_cmd "ip -n $ns1 address add $local_addr/$plen dev lo"
+
+ run_cmd "ip -n $ns1 nexthop add id 1 via $remote_addr fdb"
+ run_cmd "ip -n $ns1 nexthop add id 10 group 1 fdb"
+
+ run_cmd "ip -n $ns1 link add name vx0 up type vxlan id 10010 local $local_addr dstport 4789"
+ run_cmd "bridge -n $ns1 fdb add 00:11:22:33:44:55 dev vx0 self static nhid 10"
+
+ run_cmd "ip netns exec $ns1 mausezahn vx0 -a own -b 00:11:22:33:44:55 -c 1 -q"
+
+ busywait "$BUSYWAIT_TIMEOUT" until_counter_is "== 1" nh_stats_get > /dev/null
+ check_err $? "FDB nexthop group stats did not increase"
+
+ busywait "$BUSYWAIT_TIMEOUT" until_counter_is "== 1" tc_stats_get > /dev/null
+ check_err $? "tc filter stats did not increase"
+
+ log_test "VXLAN FDB nexthop: $af_str basic Tx"
+}
+
+basic_tx_ipv4()
+{
+ basic_tx_common "IPv4" ipv4 192.0.2.1 32 192.0.2.2
+}
+
+basic_tx_ipv6()
+{
+ basic_tx_common "IPv6" ipv6 2001:db8:1::1 128 2001:db8:1::2
+}
+
+learning()
+{
+ RET=0
+
+ # When learning is enabled on the VXLAN device, an incoming packet
+ # might try to refresh an FDB entry that points to an FDB nexthop group
+ # instead of an ordinary remote destination. Check that the kernel does
+ # not crash in this situation.
+
+ run_cmd "ip -n $ns1 address add 192.0.2.1/32 dev lo"
+ run_cmd "ip -n $ns1 address add 192.0.2.2/32 dev lo"
+
+ run_cmd "ip -n $ns1 nexthop add id 1 via 192.0.2.3 fdb"
+ run_cmd "ip -n $ns1 nexthop add id 10 group 1 fdb"
+
+ run_cmd "ip -n $ns1 link add name vx0 up type vxlan id 10010 local 192.0.2.1 dstport 12345 localbypass"
+ run_cmd "ip -n $ns1 link add name vx1 up type vxlan id 10020 local 192.0.2.2 dstport 54321 learning"
+
+ run_cmd "bridge -n $ns1 fdb add 00:11:22:33:44:55 dev vx0 self static dst 192.0.2.2 port 54321 vni 10020"
+ run_cmd "bridge -n $ns1 fdb add 00:aa:bb:cc:dd:ee dev vx1 self static nhid 10"
+
+ run_cmd "ip netns exec $ns1 mausezahn vx0 -a 00:aa:bb:cc:dd:ee -b 00:11:22:33:44:55 -c 1 -q"
+
+ log_test "VXLAN FDB nexthop: learning"
+}
+
+proxy_common()
+{
+ local af_str=$1; shift
+ local local_addr=$1; shift
+ local plen=$1; shift
+ local remote_addr=$1; shift
+ local neigh_addr=$1; shift
+ local ping_cmd=$1; shift
+
+ RET=0
+
+ # When the "proxy" option is enabled on the VXLAN device, the device
+ # will suppress ARP requests and IPv6 Neighbor Solicitation messages if
+ # it is able to reply on behalf of the remote host. That is, if a
+ # matching and valid neighbor entry is configured on the VXLAN device
+ # whose MAC address is not behind the "any" remote (0.0.0.0 / ::). The
+ # FDB entry for the neighbor's MAC address might point to an FDB
+ # nexthop group instead of an ordinary remote destination. Check that
+ # the kernel does not crash in this situation.
+
+ run_cmd "ip -n $ns1 address add $local_addr/$plen dev lo"
+
+ run_cmd "ip -n $ns1 nexthop add id 1 via $remote_addr fdb"
+ run_cmd "ip -n $ns1 nexthop add id 10 group 1 fdb"
+
+ run_cmd "ip -n $ns1 link add name vx0 up type vxlan id 10010 local $local_addr dstport 4789 proxy"
+
+ run_cmd "ip -n $ns1 neigh add $neigh_addr lladdr 00:11:22:33:44:55 nud perm dev vx0"
+
+ run_cmd "bridge -n $ns1 fdb add 00:11:22:33:44:55 dev vx0 self static nhid 10"
+
+ run_cmd "ip netns exec $ns1 $ping_cmd"
+
+ log_test "VXLAN FDB nexthop: $af_str proxy"
+}
+
+proxy_ipv4()
+{
+ proxy_common "IPv4" 192.0.2.1 32 192.0.2.2 192.0.2.3 \
+ "arping -b -c 1 -s 192.0.2.1 -I vx0 192.0.2.3"
+}
+
+proxy_ipv6()
+{
+ proxy_common "IPv6" 2001:db8:1::1 128 2001:db8:1::2 2001:db8:1::3 \
+ "ndisc6 -r 1 -s 2001:db8:1::1 -w 1 2001:db8:1::3 vx0"
+}
+
+################################################################################
+# Usage
+
+usage()
+{
+ cat <<EOF
+usage: ${0##*/} OPTS
+
+ -t <test> Test(s) to run (default: all)
+ (options: $TESTS)
+ -p Pause on fail
+ -v Verbose mode (show commands and output)
+EOF
+}
+
+################################################################################
+# Main
+
+while getopts ":t:pvh" opt; do
+ case $opt in
+ t) TESTS=$OPTARG;;
+ p) PAUSE_ON_FAIL=yes;;
+ v) VERBOSE=$((VERBOSE + 1));;
+ h) usage; exit 0;;
+ *) usage; exit 1;;
+ esac
+done
+
+require_command mausezahn
+require_command arping
+require_command ndisc6
+require_command jq
+
+if ! ip nexthop help 2>&1 | grep -q "stats"; then
+ echo "SKIP: iproute2 ip too old, missing nexthop stats support"
+ exit "$ksft_skip"
+fi
+
+trap exit_cleanup_all EXIT
+
+for t in $TESTS
+do
+ setup_ns ns1; $t; cleanup_all_ns;
+done
diff --git a/tools/testing/selftests/net/tfo_passive.sh b/tools/testing/selftests/net/tfo_passive.sh
index 80bf11fdc046..a4550511830a 100755
--- a/tools/testing/selftests/net/tfo_passive.sh
+++ b/tools/testing/selftests/net/tfo_passive.sh
@@ -95,7 +95,7 @@ wait
res=$(cat $out_file)
rm $out_file
-if [ $res -eq 0 ]; then
+if [ "$res" = "0" ]; then
echo "got invalid NAPI ID from passive TFO socket"
cleanup_ns
exit 1
diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
index 0f5640d8dc7f..e788b84551ca 100644
--- a/tools/testing/selftests/net/tls.c
+++ b/tools/testing/selftests/net/tls.c
@@ -439,6 +439,8 @@ TEST_F(tls, sendfile)
EXPECT_GE(filefd, 0);
fstat(filefd, &st);
EXPECT_GE(sendfile(self->fd, filefd, 0, st.st_size), 0);
+
+ close(filefd);
}
TEST_F(tls, send_then_sendfile)
@@ -460,6 +462,9 @@ TEST_F(tls, send_then_sendfile)
EXPECT_GE(sendfile(self->fd, filefd, 0, st.st_size), 0);
EXPECT_EQ(recv(self->cfd, buf, st.st_size, MSG_WAITALL), st.st_size);
+
+ free(buf);
+ close(filefd);
}
static void chunked_sendfile(struct __test_metadata *_metadata,
@@ -2770,6 +2775,22 @@ TEST_F(tls_err, poll_partial_rec_async)
}
}
+/* Use OOB+large send to trigger copy mode due to memory pressure.
+ * OOB causes a short read.
+ */
+TEST_F(tls_err, oob_pressure)
+{
+ char buf[1<<16];
+ int i;
+
+ memrnd(buf, sizeof(buf));
+
+ EXPECT_EQ(send(self->fd2, buf, 5, MSG_OOB), 5);
+ EXPECT_EQ(send(self->fd2, buf, sizeof(buf), 0), sizeof(buf));
+ for (i = 0; i < 64; i++)
+ EXPECT_EQ(send(self->fd2, buf, 5, MSG_OOB), 5);
+}
+
TEST(non_established) {
struct tls12_crypto_info_aes_gcm_256 tls12;
struct sockaddr_in addr;
diff --git a/tools/testing/selftests/net/traceroute.sh b/tools/testing/selftests/net/traceroute.sh
index 282f14760940..dbb34c7e09ce 100755
--- a/tools/testing/selftests/net/traceroute.sh
+++ b/tools/testing/selftests/net/traceroute.sh
@@ -10,28 +10,6 @@ PAUSE_ON_FAIL=no
################################################################################
#
-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
- [ "$a" = "q" ] && exit 1
- fi
- fi
-}
-
run_cmd()
{
local ns
@@ -203,34 +181,137 @@ setup_traceroute6()
run_traceroute6()
{
- if [ ! -x "$(command -v traceroute6)" ]; then
- echo "SKIP: Could not run IPV6 test without traceroute6"
- return
- fi
-
setup_traceroute6
+ RET=0
+
# traceroute6 host-2 from host-1 (expects 2000:102::2)
run_cmd $h1 "traceroute6 2000:103::4 | grep -q 2000:102::2"
- log_test $? 0 "IPV6 traceroute"
+ check_err $? "traceroute6 did not return 2000:102::2"
+ log_test "IPv6 traceroute"
cleanup_traceroute6
}
################################################################################
+# traceroute6 with VRF test
+#
+# Verify that in this scenario
+#
+# ------------------------ N2
+# | |
+# ------ ------ N3 ----
+# | R1 | | R2 |------|H2|
+# ------ ------ ----
+# | |
+# ------------------------ N1
+# |
+# ----
+# |H1|
+# ----
+#
+# Where H1's default route goes through R1 and R1's default route goes through
+# R2 over N2, traceroute6 from H1 to H2 reports R2's address on N2 and not N1.
+# The interfaces connecting R2 to the different subnets are membmer in a VRF
+# and the intention is to check that traceroute6 does not report the VRF's
+# address.
+#
+# Addresses are assigned as follows:
+#
+# N1: 2000:101::/64
+# N2: 2000:102::/64
+# N3: 2000:103::/64
+#
+# R1's host part of address: 1
+# R2's host part of address: 2
+# H1's host part of address: 3
+# H2's host part of address: 4
+#
+# For example:
+# the IPv6 address of R1's interface on N2 is 2000:102::1/64
+
+cleanup_traceroute6_vrf()
+{
+ cleanup_all_ns
+}
+
+setup_traceroute6_vrf()
+{
+ # Start clean
+ cleanup_traceroute6_vrf
+
+ setup_ns h1 h2 r1 r2
+ create_ns "$h1"
+ create_ns "$h2"
+ create_ns "$r1"
+ create_ns "$r2"
+
+ ip -n "$r2" link add name vrf100 up type vrf table 100
+ ip -n "$r2" addr add 2001:db8:100::1/64 dev vrf100
+
+ # Setup N3
+ connect_ns "$r2" eth3 - 2000:103::2/64 "$h2" eth3 - 2000:103::4/64
+
+ ip -n "$r2" link set dev eth3 master vrf100
+
+ ip -n "$h2" route add default via 2000:103::2
+
+ # Setup N2
+ connect_ns "$r1" eth2 - 2000:102::1/64 "$r2" eth2 - 2000:102::2/64
+
+ ip -n "$r1" route add default via 2000:102::2
+
+ ip -n "$r2" link set dev eth2 master vrf100
+
+ # Setup N1. host-1 and router-2 connect to a bridge in router-1.
+ ip -n "$r1" link add name br100 up type bridge
+ ip -n "$r1" addr add 2000:101::1/64 dev br100
+
+ connect_ns "$h1" eth0 - 2000:101::3/64 "$r1" eth0 - -
+
+ ip -n "$h1" route add default via 2000:101::1
+
+ ip -n "$r1" link set dev eth0 master br100
+
+ connect_ns "$r2" eth1 - 2000:101::2/64 "$r1" eth1 - -
+
+ ip -n "$r2" link set dev eth1 master vrf100
+
+ ip -n "$r1" link set dev eth1 master br100
+
+ # Prime the network
+ ip netns exec "$h1" ping6 -c5 2000:103::4 >/dev/null 2>&1
+}
+
+run_traceroute6_vrf()
+{
+ setup_traceroute6_vrf
+
+ RET=0
+
+ # traceroute6 host-2 from host-1 (expects 2000:102::2)
+ run_cmd "$h1" "traceroute6 2000:103::4 | grep 2000:102::2"
+ check_err $? "traceroute6 did not return 2000:102::2"
+ log_test "IPv6 traceroute with VRF"
+
+ cleanup_traceroute6_vrf
+}
+
+################################################################################
# traceroute test
#
-# Verify that traceroute from H1 to H2 shows 1.0.1.1 in this scenario
+# Verify that traceroute from H1 to H2 shows 1.0.3.1 and 1.0.1.1 when
+# traceroute uses 1.0.3.3 and 1.0.1.3 as the source IP, respectively.
#
-# 1.0.3.1/24
+# 1.0.3.3/24 1.0.3.1/24
# ---- 1.0.1.3/24 1.0.1.1/24 ---- 1.0.2.1/24 1.0.2.4/24 ----
# |H1|--------------------------|R1|--------------------------|H2|
# ---- N1 ---- N2 ----
#
-# where net.ipv4.icmp_errors_use_inbound_ifaddr is set on R1 and
-# 1.0.3.1/24 and 1.0.1.1/24 are respectively R1's primary and secondary
-# address on N1.
-#
+# where net.ipv4.icmp_errors_use_inbound_ifaddr is set on R1 and 1.0.3.1/24 and
+# 1.0.1.1/24 are R1's primary addresses on N1. The kernel is expected to prefer
+# a source address that is on the same subnet as the destination IP of the ICMP
+# error message.
cleanup_traceroute()
{
@@ -250,6 +331,7 @@ setup_traceroute()
connect_ns $h1 eth0 1.0.1.3/24 - \
$router eth1 1.0.3.1/24 -
+ ip -n "$h1" addr add 1.0.3.3/24 dev eth0
ip netns exec $h1 ip route add default via 1.0.1.1
ip netns exec $router ip addr add 1.0.1.1/24 dev eth1
@@ -268,35 +350,107 @@ setup_traceroute()
run_traceroute()
{
- if [ ! -x "$(command -v traceroute)" ]; then
- echo "SKIP: Could not run IPV4 test without traceroute"
- return
- fi
-
setup_traceroute
- # traceroute host-2 from host-1 (expects 1.0.1.1). Takes a while.
- run_cmd $h1 "traceroute 1.0.2.4 | grep -q 1.0.1.1"
- log_test $? 0 "IPV4 traceroute"
+ RET=0
+
+ # traceroute host-2 from host-1. Expect a source IP that is on the same
+ # subnet as destination IP of the ICMP error message.
+ run_cmd "$h1" "traceroute -s 1.0.1.3 1.0.2.4 | grep -q 1.0.1.1"
+ check_err $? "traceroute did not return 1.0.1.1"
+ run_cmd "$h1" "traceroute -s 1.0.3.3 1.0.2.4 | grep -q 1.0.3.1"
+ check_err $? "traceroute did not return 1.0.3.1"
+ log_test "IPv4 traceroute"
cleanup_traceroute
}
################################################################################
+# traceroute with VRF test
+#
+# Verify that traceroute from H1 to H2 shows 1.0.3.1 and 1.0.1.1 when
+# traceroute uses 1.0.3.3 and 1.0.1.3 as the source IP, respectively. The
+# intention is to check that the kernel does not choose an IP assigned to the
+# VRF device, but rather an address from the VRF port (eth1) that received the
+# packet that generates the ICMP error message.
+#
+# 1.0.4.1/24 (vrf100)
+# 1.0.3.3/24 1.0.3.1/24
+# ---- 1.0.1.3/24 1.0.1.1/24 ---- 1.0.2.1/24 1.0.2.4/24 ----
+# |H1|--------------------------|R1|--------------------------|H2|
+# ---- N1 ---- N2 ----
+
+cleanup_traceroute_vrf()
+{
+ cleanup_all_ns
+}
+
+setup_traceroute_vrf()
+{
+ # Start clean
+ cleanup_traceroute_vrf
+
+ setup_ns h1 h2 router
+ create_ns "$h1"
+ create_ns "$h2"
+ create_ns "$router"
+
+ ip -n "$router" link add name vrf100 up type vrf table 100
+ ip -n "$router" addr add 1.0.4.1/24 dev vrf100
+
+ connect_ns "$h1" eth0 1.0.1.3/24 - \
+ "$router" eth1 1.0.1.1/24 -
+
+ ip -n "$h1" addr add 1.0.3.3/24 dev eth0
+ ip -n "$h1" route add default via 1.0.1.1
+
+ ip -n "$router" link set dev eth1 master vrf100
+ ip -n "$router" addr add 1.0.3.1/24 dev eth1
+ ip netns exec "$router" sysctl -qw \
+ net.ipv4.icmp_errors_use_inbound_ifaddr=1
+
+ connect_ns "$h2" eth0 1.0.2.4/24 - \
+ "$router" eth2 1.0.2.1/24 -
+
+ ip -n "$h2" route add default via 1.0.2.1
+
+ ip -n "$router" link set dev eth2 master vrf100
+
+ # Prime the network
+ ip netns exec "$h1" ping -c5 1.0.2.4 >/dev/null 2>&1
+}
+
+run_traceroute_vrf()
+{
+ setup_traceroute_vrf
+
+ RET=0
+
+ # traceroute host-2 from host-1. Expect a source IP that is on the same
+ # subnet as destination IP of the ICMP error message.
+ run_cmd "$h1" "traceroute -s 1.0.1.3 1.0.2.4 | grep 1.0.1.1"
+ check_err $? "traceroute did not return 1.0.1.1"
+ run_cmd "$h1" "traceroute -s 1.0.3.3 1.0.2.4 | grep 1.0.3.1"
+ check_err $? "traceroute did not return 1.0.3.1"
+ log_test "IPv4 traceroute with VRF"
+
+ cleanup_traceroute_vrf
+}
+
+################################################################################
# Run tests
run_tests()
{
run_traceroute6
+ run_traceroute6_vrf
run_traceroute
+ run_traceroute_vrf
}
################################################################################
# main
-declare -i nfail=0
-declare -i nsuccess=0
-
while getopts :pv o
do
case $o in
@@ -306,7 +460,9 @@ do
esac
done
+require_command traceroute6
+require_command traceroute
+
run_tests
-printf "\nTests passed: %3d\n" ${nsuccess}
-printf "Tests failed: %3d\n" ${nfail}
+exit "${EXIT_STATUS}"
diff --git a/tools/testing/selftests/net/vlan_bridge_binding.sh b/tools/testing/selftests/net/vlan_bridge_binding.sh
index e7cb8c678bde..db481af9b6b3 100755
--- a/tools/testing/selftests/net/vlan_bridge_binding.sh
+++ b/tools/testing/selftests/net/vlan_bridge_binding.sh
@@ -18,29 +18,29 @@ setup_prepare()
{
local port
- ip_link_add br up type bridge vlan_filtering 1
+ adf_ip_link_add br up type bridge vlan_filtering 1
for port in d1 d2 d3; do
- ip_link_add $port type veth peer name r$port
- ip_link_set_up $port
- ip_link_set_up r$port
- ip_link_set_master $port br
+ adf_ip_link_add $port type veth peer name r$port
+ adf_ip_link_set_up $port
+ adf_ip_link_set_up r$port
+ adf_ip_link_set_master $port br
done
- bridge_vlan_add vid 11 dev br self
- bridge_vlan_add vid 11 dev d1 master
+ adf_bridge_vlan_add vid 11 dev br self
+ adf_bridge_vlan_add vid 11 dev d1 master
- bridge_vlan_add vid 12 dev br self
- bridge_vlan_add vid 12 dev d2 master
+ adf_bridge_vlan_add vid 12 dev br self
+ adf_bridge_vlan_add vid 12 dev d2 master
- bridge_vlan_add vid 13 dev br self
- bridge_vlan_add vid 13 dev d1 master
- bridge_vlan_add vid 13 dev d2 master
+ adf_bridge_vlan_add vid 13 dev br self
+ adf_bridge_vlan_add vid 13 dev d1 master
+ adf_bridge_vlan_add vid 13 dev d2 master
- bridge_vlan_add vid 14 dev br self
- bridge_vlan_add vid 14 dev d1 master
- bridge_vlan_add vid 14 dev d2 master
- bridge_vlan_add vid 14 dev d3 master
+ adf_bridge_vlan_add vid 14 dev br self
+ adf_bridge_vlan_add vid 14 dev d1 master
+ adf_bridge_vlan_add vid 14 dev d2 master
+ adf_bridge_vlan_add vid 14 dev d3 master
}
operstate_is()
@@ -74,7 +74,7 @@ add_one_vlan()
local link=$1; shift
local id=$1; shift
- ip_link_add $link.$id link $link type vlan id $id "$@"
+ adf_ip_link_add $link.$id link $link type vlan id $id "$@"
}
add_vlans()
@@ -98,7 +98,7 @@ down_netdevs()
local dev
for dev in "$@"; do
- ip_link_set_down $dev
+ adf_ip_link_set_down $dev
done
}
@@ -207,13 +207,13 @@ test_binding_toggle_off()
do_test_binding_off : "on->off"
}
-dfr_set_binding_on()
+adf_set_binding_on()
{
set_vlans type vlan bridge_binding on
defer set_vlans type vlan bridge_binding off
}
-dfr_set_binding_off()
+adf_set_binding_off()
{
set_vlans type vlan bridge_binding off
defer set_vlans type vlan bridge_binding on
@@ -223,14 +223,14 @@ test_binding_toggle_on_when_lower_down()
{
add_vlans bridge_binding off
set_vlans up
- do_test_binding_on dfr_set_binding_on "off->on when lower down"
+ do_test_binding_on adf_set_binding_on "off->on when lower down"
}
test_binding_toggle_off_when_lower_down()
{
add_vlans bridge_binding on
set_vlans up
- do_test_binding_off dfr_set_binding_off "on->off when lower down"
+ do_test_binding_off adf_set_binding_off "on->off when lower down"
}
test_binding_toggle_on_when_upper_down()
diff --git a/tools/testing/selftests/net/ynl.mk b/tools/testing/selftests/net/ynl.mk
index e907c2751956..793a2fc33d9f 100644
--- a/tools/testing/selftests/net/ynl.mk
+++ b/tools/testing/selftests/net/ynl.mk
@@ -5,10 +5,11 @@
# Inputs:
#
# YNL_GENS: families we need in the selftests
-# YNL_PROGS: TEST_PROGS which need YNL (TODO, none exist, yet)
+# YNL_GEN_PROGS: TEST_GEN_PROGS which need YNL
# YNL_GEN_FILES: TEST_GEN_FILES which need YNL
-YNL_OUTPUTS := $(patsubst %,$(OUTPUT)/%,$(YNL_GEN_FILES))
+YNL_OUTPUTS := $(patsubst %,$(OUTPUT)/%,$(YNL_GEN_FILES)) \
+ $(patsubst %,$(OUTPUT)/%,$(YNL_GEN_PROGS))
YNL_SPECS := \
$(patsubst %,$(top_srcdir)/Documentation/netlink/specs/%.yaml,$(YNL_GENS))
diff --git a/tools/testing/selftests/nolibc/Makefile.nolibc b/tools/testing/selftests/nolibc/Makefile.nolibc
index 0fb759ba992e..330e000baeb1 100644
--- a/tools/testing/selftests/nolibc/Makefile.nolibc
+++ b/tools/testing/selftests/nolibc/Makefile.nolibc
@@ -262,19 +262,22 @@ REPORT ?= awk '/\[OK\][\r]*$$/{p++} /\[FAIL\][\r]*$$/{if (!f) printf("\n"); f++
if (f || !p || !done) printf("failure\n"); else if (s) printf("warning\n"); else printf("success\n");; \
printf("\nSee all results in %s\n", ARGV[1]); }'
+# Execute the toplevel kernel Makefile
+KBUILD_MAKE = $(MAKE) -C $(srctree) ARCH=$(ARCH) CROSS_COMPILE=$(CROSS_COMPILE) LLVM=
+
help:
@echo "Supported targets under selftests/nolibc:"
@echo " all call the \"run\" target below"
@echo " help this help"
@echo " sysroot create the nolibc sysroot here (uses \$$ARCH)"
- @echo " nolibc-test build the executable (uses \$$CC and \$$CROSS_COMPILE)"
+ @echo " nolibc-test build the executable (uses \$$CC or \$$CROSS_COMPILE)"
@echo " libc-test build an executable using the compiler's default libc instead"
@echo " run-user runs the executable under QEMU (uses \$$XARCH, \$$TEST)"
@echo " initramfs.cpio prepare the initramfs archive with nolibc-test"
@echo " initramfs prepare the initramfs tree with nolibc-test"
@echo " defconfig create a fresh new default config (uses \$$XARCH)"
- @echo " kernel (re)build the kernel (uses \$$XARCH)"
- @echo " kernel-standalone (re)build the kernel with the initramfs (uses \$$XARCH)"
+ @echo " kernel (re)build the kernel (uses \$$XARCH, \$$CROSS_COMPILE)"
+ @echo " kernel-standalone (re)build the kernel with the initramfs (uses \$$XARCH, \$$CROSS_COMPILE)"
@echo " run runs the kernel in QEMU after building it (uses \$$XARCH, \$$TEST)"
@echo " rerun runs a previously prebuilt kernel in QEMU (uses \$$XARCH, \$$TEST)"
@echo " clean clean the sysroot, initramfs, build and output files"
@@ -340,17 +343,17 @@ initramfs: nolibc-test
$(Q)cp nolibc-test initramfs/init
defconfig:
- $(Q)$(MAKE) -C $(srctree) ARCH=$(ARCH) CC=$(CC) CROSS_COMPILE=$(CROSS_COMPILE) $(DEFCONFIG)
+ $(Q)$(KBUILD_MAKE) $(DEFCONFIG)
$(Q)if [ -n "$(EXTRACONFIG)" ]; then \
$(srctree)/scripts/config --file $(objtree)/.config $(EXTRACONFIG); \
- $(MAKE) -C $(srctree) ARCH=$(ARCH) CC=$(CC) CROSS_COMPILE=$(CROSS_COMPILE) olddefconfig < /dev/null; \
+ $(KBUILD_MAKE) olddefconfig < /dev/null; \
fi
kernel:
- $(Q)$(MAKE) -C $(srctree) ARCH=$(ARCH) CC=$(CC) CROSS_COMPILE=$(CROSS_COMPILE) $(IMAGE_NAME) < /dev/null
+ $(Q)$(KBUILD_MAKE) $(IMAGE_NAME) < /dev/null
kernel-standalone: initramfs
- $(Q)$(MAKE) -C $(srctree) ARCH=$(ARCH) CC=$(CC) CROSS_COMPILE=$(CROSS_COMPILE) $(IMAGE_NAME) CONFIG_INITRAMFS_SOURCE=$(CURDIR)/initramfs < /dev/null
+ $(Q)$(KBUILD_MAKE) $(IMAGE_NAME) CONFIG_INITRAMFS_SOURCE=$(CURDIR)/initramfs < /dev/null
# run the tests after building the kernel
run: kernel initramfs.cpio
diff --git a/tools/testing/selftests/nolibc/nolibc-test.c b/tools/testing/selftests/nolibc/nolibc-test.c
index a297ee0d6d07..29de21595fc9 100644
--- a/tools/testing/selftests/nolibc/nolibc-test.c
+++ b/tools/testing/selftests/nolibc/nolibc-test.c
@@ -196,8 +196,8 @@ int expect_zr(int expr, int llen)
}
-#define EXPECT_NZ(cond, expr, val) \
- do { if (!(cond)) result(llen, SKIPPED); else ret += expect_nz(expr, llen; } while (0)
+#define EXPECT_NZ(cond, expr) \
+ do { if (!(cond)) result(llen, SKIPPED); else ret += expect_nz(expr, llen); } while (0)
static __attribute__((unused))
int expect_nz(int expr, int llen)
@@ -686,7 +686,6 @@ int expect_strtox(int llen, void *func, const char *input, int base, intmax_t ex
#define CASE_TEST(name) \
case __LINE__: llen += printf("%d %s", test, #name);
-/* constructors validate that they are executed in definition order */
__attribute__((constructor))
static void constructor1(void)
{
@@ -1334,6 +1333,7 @@ int run_syscall(int min, int max)
CASE_TEST(chroot_root); EXPECT_SYSZR(euid0, chroot("/")); break;
CASE_TEST(chroot_blah); EXPECT_SYSER(1, chroot("/proc/self/blah"), -1, ENOENT); break;
CASE_TEST(chroot_exe); EXPECT_SYSER(1, chroot(argv0), -1, ENOTDIR); break;
+ CASE_TEST(clock_nanosleep); ts.tv_nsec = -1; EXPECT_EQ(1, EINVAL, clock_nanosleep(CLOCK_REALTIME, 0, &ts, NULL)); break;
CASE_TEST(close_m1); EXPECT_SYSER(1, close(-1), -1, EBADF); break;
CASE_TEST(close_dup); EXPECT_SYSZR(1, close(dup(0))); break;
CASE_TEST(dup_0); tmp = dup(0); EXPECT_SYSNE(1, tmp, -1); close(tmp); break;
diff --git a/tools/testing/selftests/perf_events/watermark_signal.c b/tools/testing/selftests/perf_events/watermark_signal.c
index e03fe1b9bba2..b3a72f0ac522 100644
--- a/tools/testing/selftests/perf_events/watermark_signal.c
+++ b/tools/testing/selftests/perf_events/watermark_signal.c
@@ -17,8 +17,6 @@
#include "../kselftest_harness.h"
-#define __maybe_unused __attribute__((__unused__))
-
static int sigio_count;
static void handle_sigio(int signum __maybe_unused,
diff --git a/tools/testing/selftests/pidfd/config b/tools/testing/selftests/pidfd/config
index 6133524710f7..cf7cc0ce0248 100644
--- a/tools/testing/selftests/pidfd/config
+++ b/tools/testing/selftests/pidfd/config
@@ -4,6 +4,5 @@ CONFIG_USER_NS=y
CONFIG_PID_NS=y
CONFIG_NET_NS=y
CONFIG_TIME_NS=y
-CONFIG_GENERIC_VDSO_TIME_NS=y
CONFIG_CGROUPS=y
CONFIG_CHECKPOINT_RESTORE=y
diff --git a/tools/testing/selftests/powerpc/include/instructions.h b/tools/testing/selftests/powerpc/include/instructions.h
index 4efa6314bd96..864f0c9f1afc 100644
--- a/tools/testing/selftests/powerpc/include/instructions.h
+++ b/tools/testing/selftests/powerpc/include/instructions.h
@@ -67,7 +67,7 @@ static inline int paste_last(void *i)
#define PPC_INST_PASTE_LAST __PASTE(0, 0, 1, 1)
/* This defines the prefixed load/store instructions */
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
# define stringify_in_c(...) __VA_ARGS__
#else
# define __stringify_in_c(...) #__VA_ARGS__
diff --git a/tools/testing/selftests/proc/.gitignore b/tools/testing/selftests/proc/.gitignore
index 243f4537a670..9c9735570abf 100644
--- a/tools/testing/selftests/proc/.gitignore
+++ b/tools/testing/selftests/proc/.gitignore
@@ -19,6 +19,7 @@
/proc-tid0
/proc-uptime-001
/proc-uptime-002
+/proc-pidns
/read
/self
/setns-dcache
diff --git a/tools/testing/selftests/proc/Makefile b/tools/testing/selftests/proc/Makefile
index 2a9547630115..a7de2bb6d8be 100644
--- a/tools/testing/selftests/proc/Makefile
+++ b/tools/testing/selftests/proc/Makefile
@@ -29,5 +29,6 @@ TEST_GEN_PROGS += setns-sysvipc
TEST_GEN_PROGS += thread-self
TEST_GEN_PROGS += proc-multiple-procfs
TEST_GEN_PROGS += proc-fsconfig-hidepid
+TEST_GEN_PROGS += proc-pidns
include ../lib.mk
diff --git a/tools/testing/selftests/proc/proc-maps-race.c b/tools/testing/selftests/proc/proc-maps-race.c
index 94bba4553130..a546475db550 100644
--- a/tools/testing/selftests/proc/proc-maps-race.c
+++ b/tools/testing/selftests/proc/proc-maps-race.c
@@ -32,6 +32,8 @@
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
+#include <linux/fs.h>
+#include <sys/ioctl.h>
#include <sys/mman.h>
#include <sys/stat.h>
#include <sys/types.h>
@@ -317,6 +319,25 @@ static bool capture_mod_pattern(FIXTURE_DATA(proc_maps_race) *self,
strcmp(restored_first_line->text, self->first_line.text) == 0;
}
+static bool query_addr_at(int maps_fd, void *addr,
+ unsigned long *vma_start, unsigned long *vma_end)
+{
+ struct procmap_query q;
+
+ memset(&q, 0, sizeof(q));
+ q.size = sizeof(q);
+ /* Find the VMA at the split address */
+ q.query_addr = (unsigned long long)addr;
+ q.query_flags = 0;
+ if (ioctl(maps_fd, PROCMAP_QUERY, &q))
+ return false;
+
+ *vma_start = q.vma_start;
+ *vma_end = q.vma_end;
+
+ return true;
+}
+
static inline bool split_vma(FIXTURE_DATA(proc_maps_race) *self)
{
return mmap(self->mod_info->addr, self->page_size, self->mod_info->prot | PROT_EXEC,
@@ -559,6 +580,8 @@ TEST_F(proc_maps_race, test_maps_tearing_from_split)
do {
bool last_line_changed;
bool first_line_changed;
+ unsigned long vma_start;
+ unsigned long vma_end;
ASSERT_TRUE(read_boundary_lines(self, &new_last_line, &new_first_line));
@@ -595,6 +618,19 @@ TEST_F(proc_maps_race, test_maps_tearing_from_split)
first_line_changed = strcmp(new_first_line.text, self->first_line.text) != 0;
ASSERT_EQ(last_line_changed, first_line_changed);
+ /* Check if PROCMAP_QUERY ioclt() finds the right VMA */
+ ASSERT_TRUE(query_addr_at(self->maps_fd, mod_info->addr + self->page_size,
+ &vma_start, &vma_end));
+ /*
+ * The vma at the split address can be either the same as
+ * original one (if read before the split) or the same as the
+ * first line in the second page (if read after the split).
+ */
+ ASSERT_TRUE((vma_start == self->last_line.start_addr &&
+ vma_end == self->last_line.end_addr) ||
+ (vma_start == split_first_line.start_addr &&
+ vma_end == split_first_line.end_addr));
+
clock_gettime(CLOCK_MONOTONIC_COARSE, &end_ts);
end_test_iteration(&end_ts, self->verbose);
} while (end_ts.tv_sec - start_ts.tv_sec < self->duration_sec);
@@ -636,6 +672,9 @@ TEST_F(proc_maps_race, test_maps_tearing_from_resize)
clock_gettime(CLOCK_MONOTONIC_COARSE, &start_ts);
start_test_loop(&start_ts, self->verbose);
do {
+ unsigned long vma_start;
+ unsigned long vma_end;
+
ASSERT_TRUE(read_boundary_lines(self, &new_last_line, &new_first_line));
/* Check if we read vmas after shrinking it */
@@ -662,6 +701,16 @@ TEST_F(proc_maps_race, test_maps_tearing_from_resize)
"Expand result invalid", self));
}
+ /* Check if PROCMAP_QUERY ioclt() finds the right VMA */
+ ASSERT_TRUE(query_addr_at(self->maps_fd, mod_info->addr, &vma_start, &vma_end));
+ /*
+ * The vma should stay at the same address and have either the
+ * original size of 3 pages or 1 page if read after shrinking.
+ */
+ ASSERT_TRUE(vma_start == self->last_line.start_addr &&
+ (vma_end - vma_start == self->page_size * 3 ||
+ vma_end - vma_start == self->page_size));
+
clock_gettime(CLOCK_MONOTONIC_COARSE, &end_ts);
end_test_iteration(&end_ts, self->verbose);
} while (end_ts.tv_sec - start_ts.tv_sec < self->duration_sec);
@@ -703,6 +752,9 @@ TEST_F(proc_maps_race, test_maps_tearing_from_remap)
clock_gettime(CLOCK_MONOTONIC_COARSE, &start_ts);
start_test_loop(&start_ts, self->verbose);
do {
+ unsigned long vma_start;
+ unsigned long vma_end;
+
ASSERT_TRUE(read_boundary_lines(self, &new_last_line, &new_first_line));
/* Check if we read vmas after remapping it */
@@ -729,6 +781,19 @@ TEST_F(proc_maps_race, test_maps_tearing_from_remap)
"Remap restore result invalid", self));
}
+ /* Check if PROCMAP_QUERY ioclt() finds the right VMA */
+ ASSERT_TRUE(query_addr_at(self->maps_fd, mod_info->addr + self->page_size,
+ &vma_start, &vma_end));
+ /*
+ * The vma should either stay at the same address and have the
+ * original size of 3 pages or we should find the remapped vma
+ * at the remap destination address with size of 1 page.
+ */
+ ASSERT_TRUE((vma_start == self->last_line.start_addr &&
+ vma_end - vma_start == self->page_size * 3) ||
+ (vma_start == self->last_line.start_addr + self->page_size &&
+ vma_end - vma_start == self->page_size));
+
clock_gettime(CLOCK_MONOTONIC_COARSE, &end_ts);
end_test_iteration(&end_ts, self->verbose);
} while (end_ts.tv_sec - start_ts.tv_sec < self->duration_sec);
diff --git a/tools/testing/selftests/proc/proc-pidns.c b/tools/testing/selftests/proc/proc-pidns.c
new file mode 100644
index 000000000000..52500597f951
--- /dev/null
+++ b/tools/testing/selftests/proc/proc-pidns.c
@@ -0,0 +1,211 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Author: Aleksa Sarai <cyphar@cyphar.com>
+ * Copyright (C) 2025 SUSE LLC.
+ */
+
+#include <assert.h>
+#include <errno.h>
+#include <sched.h>
+#include <stdbool.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <sys/mount.h>
+#include <sys/stat.h>
+#include <sys/prctl.h>
+
+#include "../kselftest_harness.h"
+
+#define ASSERT_ERRNO(expected, _t, seen) \
+ __EXPECT(expected, #expected, \
+ ({__typeof__(seen) _tmp_seen = (seen); \
+ _tmp_seen >= 0 ? _tmp_seen : -errno; }), #seen, _t, 1)
+
+#define ASSERT_ERRNO_EQ(expected, seen) \
+ ASSERT_ERRNO(expected, ==, seen)
+
+#define ASSERT_SUCCESS(seen) \
+ ASSERT_ERRNO(0, <=, seen)
+
+static int touch(char *path)
+{
+ int fd = open(path, O_WRONLY|O_CREAT|O_CLOEXEC, 0644);
+ if (fd < 0)
+ return -1;
+ return close(fd);
+}
+
+FIXTURE(ns)
+{
+ int host_mntns, host_pidns;
+ int dummy_pidns;
+};
+
+FIXTURE_SETUP(ns)
+{
+ /* Stash the old mntns. */
+ self->host_mntns = open("/proc/self/ns/mnt", O_RDONLY|O_CLOEXEC);
+ ASSERT_SUCCESS(self->host_mntns);
+
+ /* Create a new mount namespace and make it private. */
+ ASSERT_SUCCESS(unshare(CLONE_NEWNS));
+ ASSERT_SUCCESS(mount(NULL, "/", NULL, MS_PRIVATE|MS_REC, NULL));
+
+ /*
+ * Create a proper tmpfs that we can use and will disappear once we
+ * leave this mntns.
+ */
+ ASSERT_SUCCESS(mount("tmpfs", "/tmp", "tmpfs", 0, NULL));
+
+ /*
+ * Create a pidns we can use for later tests. We need to fork off a
+ * child so that we get a usable nsfd that we can bind-mount and open.
+ */
+ ASSERT_SUCCESS(mkdir("/tmp/dummy", 0755));
+ ASSERT_SUCCESS(touch("/tmp/dummy/pidns"));
+ ASSERT_SUCCESS(mkdir("/tmp/dummy/proc", 0755));
+
+ self->host_pidns = open("/proc/self/ns/pid", O_RDONLY|O_CLOEXEC);
+ ASSERT_SUCCESS(self->host_pidns);
+ ASSERT_SUCCESS(unshare(CLONE_NEWPID));
+
+ pid_t pid = fork();
+ ASSERT_SUCCESS(pid);
+ if (!pid) {
+ prctl(PR_SET_PDEATHSIG, SIGKILL);
+ ASSERT_SUCCESS(mount("/proc/self/ns/pid", "/tmp/dummy/pidns", NULL, MS_BIND, NULL));
+ ASSERT_SUCCESS(mount("proc", "/tmp/dummy/proc", "proc", 0, NULL));
+ exit(0);
+ }
+
+ int wstatus;
+ ASSERT_EQ(waitpid(pid, &wstatus, 0), pid);
+ ASSERT_TRUE(WIFEXITED(wstatus));
+ ASSERT_EQ(WEXITSTATUS(wstatus), 0);
+
+ ASSERT_SUCCESS(setns(self->host_pidns, CLONE_NEWPID));
+
+ self->dummy_pidns = open("/tmp/dummy/pidns", O_RDONLY|O_CLOEXEC);
+ ASSERT_SUCCESS(self->dummy_pidns);
+}
+
+FIXTURE_TEARDOWN(ns)
+{
+ ASSERT_SUCCESS(setns(self->host_mntns, CLONE_NEWNS));
+ ASSERT_SUCCESS(close(self->host_mntns));
+
+ ASSERT_SUCCESS(close(self->host_pidns));
+ ASSERT_SUCCESS(close(self->dummy_pidns));
+}
+
+TEST_F(ns, pidns_mount_string_path)
+{
+ ASSERT_SUCCESS(mkdir("/tmp/proc-host", 0755));
+ ASSERT_SUCCESS(mount("proc", "/tmp/proc-host", "proc", 0, "pidns=/proc/self/ns/pid"));
+ ASSERT_SUCCESS(access("/tmp/proc-host/self/", X_OK));
+
+ ASSERT_SUCCESS(mkdir("/tmp/proc-dummy", 0755));
+ ASSERT_SUCCESS(mount("proc", "/tmp/proc-dummy", "proc", 0, "pidns=/tmp/dummy/pidns"));
+ ASSERT_ERRNO_EQ(-ENOENT, access("/tmp/proc-dummy/1/", X_OK));
+ ASSERT_ERRNO_EQ(-ENOENT, access("/tmp/proc-dummy/self/", X_OK));
+}
+
+TEST_F(ns, pidns_fsconfig_string_path)
+{
+ int fsfd = fsopen("proc", FSOPEN_CLOEXEC);
+ ASSERT_SUCCESS(fsfd);
+
+ ASSERT_SUCCESS(fsconfig(fsfd, FSCONFIG_SET_STRING, "pidns", "/tmp/dummy/pidns", 0));
+ ASSERT_SUCCESS(fsconfig(fsfd, FSCONFIG_CMD_CREATE, NULL, NULL, 0));
+
+ int mountfd = fsmount(fsfd, FSMOUNT_CLOEXEC, 0);
+ ASSERT_SUCCESS(mountfd);
+
+ ASSERT_ERRNO_EQ(-ENOENT, faccessat(mountfd, "1/", X_OK, 0));
+ ASSERT_ERRNO_EQ(-ENOENT, faccessat(mountfd, "self/", X_OK, 0));
+
+ ASSERT_SUCCESS(close(fsfd));
+ ASSERT_SUCCESS(close(mountfd));
+}
+
+TEST_F(ns, pidns_fsconfig_fd)
+{
+ int fsfd = fsopen("proc", FSOPEN_CLOEXEC);
+ ASSERT_SUCCESS(fsfd);
+
+ ASSERT_SUCCESS(fsconfig(fsfd, FSCONFIG_SET_FD, "pidns", NULL, self->dummy_pidns));
+ ASSERT_SUCCESS(fsconfig(fsfd, FSCONFIG_CMD_CREATE, NULL, NULL, 0));
+
+ int mountfd = fsmount(fsfd, FSMOUNT_CLOEXEC, 0);
+ ASSERT_SUCCESS(mountfd);
+
+ ASSERT_ERRNO_EQ(-ENOENT, faccessat(mountfd, "1/", X_OK, 0));
+ ASSERT_ERRNO_EQ(-ENOENT, faccessat(mountfd, "self/", X_OK, 0));
+
+ ASSERT_SUCCESS(close(fsfd));
+ ASSERT_SUCCESS(close(mountfd));
+}
+
+TEST_F(ns, pidns_reconfigure_remount)
+{
+ ASSERT_SUCCESS(mkdir("/tmp/proc", 0755));
+ ASSERT_SUCCESS(mount("proc", "/tmp/proc", "proc", 0, ""));
+
+ ASSERT_SUCCESS(access("/tmp/proc/1/", X_OK));
+ ASSERT_SUCCESS(access("/tmp/proc/self/", X_OK));
+
+ ASSERT_ERRNO_EQ(-EBUSY, mount(NULL, "/tmp/proc", NULL, MS_REMOUNT, "pidns=/tmp/dummy/pidns"));
+
+ ASSERT_SUCCESS(access("/tmp/proc/1/", X_OK));
+ ASSERT_SUCCESS(access("/tmp/proc/self/", X_OK));
+}
+
+TEST_F(ns, pidns_reconfigure_fsconfig_string_path)
+{
+ int fsfd = fsopen("proc", FSOPEN_CLOEXEC);
+ ASSERT_SUCCESS(fsfd);
+
+ ASSERT_SUCCESS(fsconfig(fsfd, FSCONFIG_CMD_CREATE, NULL, NULL, 0));
+
+ int mountfd = fsmount(fsfd, FSMOUNT_CLOEXEC, 0);
+ ASSERT_SUCCESS(mountfd);
+
+ ASSERT_SUCCESS(faccessat(mountfd, "1/", X_OK, 0));
+ ASSERT_SUCCESS(faccessat(mountfd, "self/", X_OK, 0));
+
+ ASSERT_ERRNO_EQ(-EBUSY, fsconfig(fsfd, FSCONFIG_SET_STRING, "pidns", "/tmp/dummy/pidns", 0));
+ ASSERT_SUCCESS(fsconfig(fsfd, FSCONFIG_CMD_RECONFIGURE, NULL, NULL, 0)); /* noop */
+
+ ASSERT_SUCCESS(faccessat(mountfd, "1/", X_OK, 0));
+ ASSERT_SUCCESS(faccessat(mountfd, "self/", X_OK, 0));
+
+ ASSERT_SUCCESS(close(fsfd));
+ ASSERT_SUCCESS(close(mountfd));
+}
+
+TEST_F(ns, pidns_reconfigure_fsconfig_fd)
+{
+ int fsfd = fsopen("proc", FSOPEN_CLOEXEC);
+ ASSERT_SUCCESS(fsfd);
+
+ ASSERT_SUCCESS(fsconfig(fsfd, FSCONFIG_CMD_CREATE, NULL, NULL, 0));
+
+ int mountfd = fsmount(fsfd, FSMOUNT_CLOEXEC, 0);
+ ASSERT_SUCCESS(mountfd);
+
+ ASSERT_SUCCESS(faccessat(mountfd, "1/", X_OK, 0));
+ ASSERT_SUCCESS(faccessat(mountfd, "self/", X_OK, 0));
+
+ ASSERT_ERRNO_EQ(-EBUSY, fsconfig(fsfd, FSCONFIG_SET_FD, "pidns", NULL, self->dummy_pidns));
+ ASSERT_SUCCESS(fsconfig(fsfd, FSCONFIG_CMD_RECONFIGURE, NULL, NULL, 0)); /* noop */
+
+ ASSERT_SUCCESS(faccessat(mountfd, "1/", X_OK, 0));
+ ASSERT_SUCCESS(faccessat(mountfd, "self/", X_OK, 0));
+
+ ASSERT_SUCCESS(close(fsfd));
+ ASSERT_SUCCESS(close(mountfd));
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/riscv/README b/tools/testing/selftests/riscv/README
new file mode 100644
index 000000000000..443da395da68
--- /dev/null
+++ b/tools/testing/selftests/riscv/README
@@ -0,0 +1,24 @@
+KSelfTest RISC-V
+================
+
+- These tests are riscv specific and so not built or run but just skipped
+ completely when env-variable ARCH is found to be different than 'riscv'.
+
+- Holding true the above, RISC-V KSFT tests can be run within the
+ KSelfTest framework using standard Linux top-level-makefile targets:
+
+ $ make TARGETS=riscv kselftest-clean
+ $ make TARGETS=riscv kselftest
+
+ or
+
+ $ make -C tools/testing/selftests TARGETS=riscv \
+ INSTALL_PATH=<your-installation-path> install
+
+ or, alternatively, only specific riscv/ subtargets can be picked:
+
+ $ make -C tools/testing/selftests TARGETS=riscv RISCV_SUBTARGETS="mm vector" \
+ INSTALL_PATH=<your-installation-path> install
+
+ Further details on building and running KSFT can be found in:
+ Documentation/dev-tools/kselftest.rst
diff --git a/tools/testing/selftests/rseq/rseq.c b/tools/testing/selftests/rseq/rseq.c
index 663a9cef1952..dcac5cbe7933 100644
--- a/tools/testing/selftests/rseq/rseq.c
+++ b/tools/testing/selftests/rseq/rseq.c
@@ -40,9 +40,9 @@
* Define weak versions to play nice with binaries that are statically linked
* against a libc that doesn't support registering its own rseq.
*/
-__weak ptrdiff_t __rseq_offset;
-__weak unsigned int __rseq_size;
-__weak unsigned int __rseq_flags;
+extern __weak ptrdiff_t __rseq_offset;
+extern __weak unsigned int __rseq_size;
+extern __weak unsigned int __rseq_flags;
static const ptrdiff_t *libc_rseq_offset_p = &__rseq_offset;
static const unsigned int *libc_rseq_size_p = &__rseq_size;
@@ -209,7 +209,7 @@ void rseq_init(void)
* libc not having registered a restartable sequence. Try to find the
* symbols if that's the case.
*/
- if (!*libc_rseq_size_p) {
+ if (!libc_rseq_size_p || !*libc_rseq_size_p) {
libc_rseq_offset_p = dlsym(RTLD_NEXT, "__rseq_offset");
libc_rseq_size_p = dlsym(RTLD_NEXT, "__rseq_size");
libc_rseq_flags_p = dlsym(RTLD_NEXT, "__rseq_flags");
diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c
index 61acbd45ffaa..874f17763536 100644
--- a/tools/testing/selftests/seccomp/seccomp_bpf.c
+++ b/tools/testing/selftests/seccomp/seccomp_bpf.c
@@ -24,6 +24,7 @@
#include <linux/filter.h>
#include <sys/prctl.h>
#include <sys/ptrace.h>
+#include <sys/time.h>
#include <sys/user.h>
#include <linux/prctl.h>
#include <linux/ptrace.h>
@@ -73,6 +74,14 @@
#define noinline __attribute__((noinline))
#endif
+#ifndef __nocf_check
+#define __nocf_check __attribute__((nocf_check))
+#endif
+
+#ifndef __naked
+#define __naked __attribute__((__naked__))
+#endif
+
#ifndef PR_SET_NO_NEW_PRIVS
#define PR_SET_NO_NEW_PRIVS 38
#define PR_GET_NO_NEW_PRIVS 39
@@ -3547,6 +3556,10 @@ static void signal_handler(int signal)
perror("write from signal");
}
+static void signal_handler_nop(int signal)
+{
+}
+
TEST(user_notification_signal)
{
pid_t pid;
@@ -4819,6 +4832,132 @@ TEST(user_notification_wait_killable_fatal)
EXPECT_EQ(SIGTERM, WTERMSIG(status));
}
+/* Ensure signals after the reply do not interrupt */
+TEST(user_notification_wait_killable_after_reply)
+{
+ int i, max_iter = 100000;
+ int listener, status;
+ int pipe_fds[2];
+ pid_t pid;
+ long ret;
+
+ ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
+ ASSERT_EQ(0, ret)
+ {
+ TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!");
+ }
+
+ listener = user_notif_syscall(
+ __NR_dup, SECCOMP_FILTER_FLAG_NEW_LISTENER |
+ SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV);
+ ASSERT_GE(listener, 0);
+
+ /*
+ * Used to count invocations. One token is transferred from the child
+ * to the parent per syscall invocation, the parent tries to take
+ * one token per successful RECV. If the syscall is restarted after
+ * RECV the parent will try to get two tokens while the child only
+ * provided one.
+ */
+ ASSERT_EQ(pipe(pipe_fds), 0);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ struct sigaction new_action = {
+ .sa_handler = signal_handler_nop,
+ .sa_flags = SA_RESTART,
+ };
+ struct itimerval timer = {
+ .it_value = { .tv_usec = 1000 },
+ .it_interval = { .tv_usec = 1000 },
+ };
+ char c = 'a';
+
+ close(pipe_fds[0]);
+
+ /* Setup the sigaction with SA_RESTART */
+ if (sigaction(SIGALRM, &new_action, NULL)) {
+ perror("sigaction");
+ exit(1);
+ }
+
+ /*
+ * Kill with SIGALRM repeatedly, to try to hit the race when
+ * handling the syscall.
+ */
+ if (setitimer(ITIMER_REAL, &timer, NULL) < 0)
+ perror("setitimer");
+
+ for (i = 0; i < max_iter; ++i) {
+ int fd;
+
+ /* Send one token per iteration to catch repeats. */
+ if (write(pipe_fds[1], &c, sizeof(c)) != 1) {
+ perror("write");
+ exit(1);
+ }
+
+ fd = syscall(__NR_dup, 0);
+ if (fd < 0) {
+ perror("dup");
+ exit(1);
+ }
+ close(fd);
+ }
+
+ exit(0);
+ }
+
+ close(pipe_fds[1]);
+
+ for (i = 0; i < max_iter; ++i) {
+ struct seccomp_notif req = {};
+ struct seccomp_notif_addfd addfd = {};
+ struct pollfd pfd = {
+ .fd = pipe_fds[0],
+ .events = POLLIN,
+ };
+ char c;
+
+ /*
+ * Try to receive one token. If it failed, one child syscall
+ * was restarted after RECV and needed to be handled twice.
+ */
+ ASSERT_EQ(poll(&pfd, 1, 1000), 1)
+ kill(pid, SIGKILL);
+
+ ASSERT_EQ(read(pipe_fds[0], &c, sizeof(c)), 1)
+ kill(pid, SIGKILL);
+
+ /*
+ * Get the notification, reply to it as fast as possible to test
+ * whether the child wrongly skips going into the non-preemptible
+ * (TASK_KILLABLE) state.
+ */
+ do
+ ret = ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req);
+ while (ret < 0 && errno == ENOENT); /* Accept interruptions before RECV */
+ ASSERT_EQ(ret, 0)
+ kill(pid, SIGKILL);
+
+ addfd.id = req.id;
+ addfd.flags = SECCOMP_ADDFD_FLAG_SEND;
+ addfd.srcfd = 0;
+ ASSERT_GE(ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD, &addfd), 0)
+ kill(pid, SIGKILL);
+ }
+
+ /*
+ * Wait for the process to exit, and make sure the process terminated
+ * with a zero exit code..
+ */
+ EXPECT_EQ(waitpid(pid, &status, 0), pid);
+ EXPECT_EQ(true, WIFEXITED(status));
+ EXPECT_EQ(0, WEXITSTATUS(status));
+}
+
struct tsync_vs_thread_leader_args {
pthread_t leader;
};
@@ -4896,7 +5035,36 @@ TEST(tsync_vs_dead_thread_leader)
EXPECT_EQ(0, status);
}
-noinline int probed(void)
+#ifdef __x86_64__
+
+/*
+ * We need naked probed_uprobe function. Using __nocf_check
+ * check to skip possible endbr64 instruction and ignoring
+ * -Wattributes, otherwise the compilation might fail.
+ */
+#pragma GCC diagnostic push
+#pragma GCC diagnostic ignored "-Wattributes"
+
+__naked __nocf_check noinline int probed_uprobe(void)
+{
+ /*
+ * Optimized uprobe is possible only on top of nop5 instruction.
+ */
+ asm volatile (" \n"
+ ".byte 0x0f, 0x1f, 0x44, 0x00, 0x00 \n"
+ "ret \n"
+ );
+}
+#pragma GCC diagnostic pop
+
+#else
+noinline int probed_uprobe(void)
+{
+ return 1;
+}
+#endif
+
+noinline int probed_uretprobe(void)
{
return 1;
}
@@ -4949,35 +5117,46 @@ static ssize_t get_uprobe_offset(const void *addr)
return found ? (uintptr_t)addr - start + base : -1;
}
-FIXTURE(URETPROBE) {
+FIXTURE(UPROBE) {
int fd;
};
-FIXTURE_VARIANT(URETPROBE) {
+FIXTURE_VARIANT(UPROBE) {
/*
- * All of the URETPROBE behaviors can be tested with either
- * uretprobe attached or not
+ * All of the U(RET)PROBE behaviors can be tested with either
+ * u(ret)probe attached or not
*/
bool attach;
+ /*
+ * Test both uprobe and uretprobe.
+ */
+ bool uretprobe;
+};
+
+FIXTURE_VARIANT_ADD(UPROBE, not_attached) {
+ .attach = false,
+ .uretprobe = false,
};
-FIXTURE_VARIANT_ADD(URETPROBE, attached) {
+FIXTURE_VARIANT_ADD(UPROBE, uprobe_attached) {
.attach = true,
+ .uretprobe = false,
};
-FIXTURE_VARIANT_ADD(URETPROBE, not_attached) {
- .attach = false,
+FIXTURE_VARIANT_ADD(UPROBE, uretprobe_attached) {
+ .attach = true,
+ .uretprobe = true,
};
-FIXTURE_SETUP(URETPROBE)
+FIXTURE_SETUP(UPROBE)
{
const size_t attr_sz = sizeof(struct perf_event_attr);
struct perf_event_attr attr;
ssize_t offset;
int type, bit;
-#ifndef __NR_uretprobe
- SKIP(return, "__NR_uretprobe syscall not defined");
+#if !defined(__NR_uprobe) || !defined(__NR_uretprobe)
+ SKIP(return, "__NR_uprobe ot __NR_uretprobe syscalls not defined");
#endif
if (!variant->attach)
@@ -4987,12 +5166,17 @@ FIXTURE_SETUP(URETPROBE)
type = determine_uprobe_perf_type();
ASSERT_GE(type, 0);
- bit = determine_uprobe_retprobe_bit();
- ASSERT_GE(bit, 0);
- offset = get_uprobe_offset(probed);
+
+ if (variant->uretprobe) {
+ bit = determine_uprobe_retprobe_bit();
+ ASSERT_GE(bit, 0);
+ }
+
+ offset = get_uprobe_offset(variant->uretprobe ? probed_uretprobe : probed_uprobe);
ASSERT_GE(offset, 0);
- attr.config |= 1 << bit;
+ if (variant->uretprobe)
+ attr.config |= 1 << bit;
attr.size = attr_sz;
attr.type = type;
attr.config1 = ptr_to_u64("/proc/self/exe");
@@ -5003,7 +5187,7 @@ FIXTURE_SETUP(URETPROBE)
PERF_FLAG_FD_CLOEXEC);
}
-FIXTURE_TEARDOWN(URETPROBE)
+FIXTURE_TEARDOWN(UPROBE)
{
/* we could call close(self->fd), but we'd need extra filter for
* that and since we are calling _exit right away..
@@ -5017,11 +5201,17 @@ static int run_probed_with_filter(struct sock_fprog *prog)
return -1;
}
- probed();
+ /*
+ * Uprobe is optimized after first hit, so let's hit twice.
+ */
+ probed_uprobe();
+ probed_uprobe();
+
+ probed_uretprobe();
return 0;
}
-TEST_F(URETPROBE, uretprobe_default_allow)
+TEST_F(UPROBE, uprobe_default_allow)
{
struct sock_filter filter[] = {
BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
@@ -5034,7 +5224,7 @@ TEST_F(URETPROBE, uretprobe_default_allow)
ASSERT_EQ(0, run_probed_with_filter(&prog));
}
-TEST_F(URETPROBE, uretprobe_default_block)
+TEST_F(UPROBE, uprobe_default_block)
{
struct sock_filter filter[] = {
BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
@@ -5051,11 +5241,14 @@ TEST_F(URETPROBE, uretprobe_default_block)
ASSERT_EQ(0, run_probed_with_filter(&prog));
}
-TEST_F(URETPROBE, uretprobe_block_uretprobe_syscall)
+TEST_F(UPROBE, uprobe_block_syscall)
{
struct sock_filter filter[] = {
BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
offsetof(struct seccomp_data, nr)),
+#ifdef __NR_uprobe
+ BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_uprobe, 1, 2),
+#endif
#ifdef __NR_uretprobe
BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_uretprobe, 0, 1),
#endif
@@ -5070,11 +5263,14 @@ TEST_F(URETPROBE, uretprobe_block_uretprobe_syscall)
ASSERT_EQ(0, run_probed_with_filter(&prog));
}
-TEST_F(URETPROBE, uretprobe_default_block_with_uretprobe_syscall)
+TEST_F(UPROBE, uprobe_default_block_with_syscall)
{
struct sock_filter filter[] = {
BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
offsetof(struct seccomp_data, nr)),
+#ifdef __NR_uprobe
+ BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_uprobe, 3, 0),
+#endif
#ifdef __NR_uretprobe
BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_uretprobe, 2, 0),
#endif
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/police.json b/tools/testing/selftests/tc-testing/tc-tests/actions/police.json
index 5596f4df0e9f..b2cc6ea74450 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/police.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/police.json
@@ -879,7 +879,7 @@
"cmdUnderTest": "$TC actions add action police pkts_rate 1000 pkts_burst 200 index 1",
"expExitCode": "0",
"verifyCmd": "$TC actions ls action police",
- "matchPattern": "action order [0-9]*: police 0x1 rate 0bit burst 0b mtu 4096Mb pkts_rate 1000 pkts_burst 200",
+ "matchPattern": "action order [0-9]*: police 0x1 rate 0bit burst 0b mtu (4Gb|4096Mb) pkts_rate 1000 pkts_burst 200",
"matchCount": "1",
"teardown": [
"$TC actions flush action police"
diff --git a/tools/testing/selftests/thermal/intel/workload_hint/workload_hint_test.c b/tools/testing/selftests/thermal/intel/workload_hint/workload_hint_test.c
index ba58589a1145..ca2bd03154e4 100644
--- a/tools/testing/selftests/thermal/intel/workload_hint/workload_hint_test.c
+++ b/tools/testing/selftests/thermal/intel/workload_hint/workload_hint_test.c
@@ -144,6 +144,8 @@ int main(int argc, char **argv)
ret = sscanf(index_str, "%d", &index);
if (ret < 0)
break;
+
+ index &= 0x0f;
if (index > WORKLOAD_TYPE_MAX_INDEX)
printf("Invalid workload type index\n");
else
diff --git a/tools/testing/selftests/ublk/Makefile b/tools/testing/selftests/ublk/Makefile
index 5d7f4ecfb816..770269efe42a 100644
--- a/tools/testing/selftests/ublk/Makefile
+++ b/tools/testing/selftests/ublk/Makefile
@@ -20,6 +20,7 @@ TEST_PROGS += test_generic_09.sh
TEST_PROGS += test_generic_10.sh
TEST_PROGS += test_generic_11.sh
TEST_PROGS += test_generic_12.sh
+TEST_PROGS += test_generic_13.sh
TEST_PROGS += test_null_01.sh
TEST_PROGS += test_null_02.sh
diff --git a/tools/testing/selftests/ublk/kublk.c b/tools/testing/selftests/ublk/kublk.c
index b71faba86c3b..6b8123c12a7a 100644
--- a/tools/testing/selftests/ublk/kublk.c
+++ b/tools/testing/selftests/ublk/kublk.c
@@ -1384,21 +1384,23 @@ static int cmd_dev_list(struct dev_ctx *ctx)
static int cmd_dev_get_features(void)
{
#define const_ilog2(x) (63 - __builtin_clzll(x))
+#define FEAT_NAME(f) [const_ilog2(f)] = #f
static const char *feat_map[] = {
- [const_ilog2(UBLK_F_SUPPORT_ZERO_COPY)] = "ZERO_COPY",
- [const_ilog2(UBLK_F_URING_CMD_COMP_IN_TASK)] = "COMP_IN_TASK",
- [const_ilog2(UBLK_F_NEED_GET_DATA)] = "GET_DATA",
- [const_ilog2(UBLK_F_USER_RECOVERY)] = "USER_RECOVERY",
- [const_ilog2(UBLK_F_USER_RECOVERY_REISSUE)] = "RECOVERY_REISSUE",
- [const_ilog2(UBLK_F_UNPRIVILEGED_DEV)] = "UNPRIVILEGED_DEV",
- [const_ilog2(UBLK_F_CMD_IOCTL_ENCODE)] = "CMD_IOCTL_ENCODE",
- [const_ilog2(UBLK_F_USER_COPY)] = "USER_COPY",
- [const_ilog2(UBLK_F_ZONED)] = "ZONED",
- [const_ilog2(UBLK_F_USER_RECOVERY_FAIL_IO)] = "RECOVERY_FAIL_IO",
- [const_ilog2(UBLK_F_UPDATE_SIZE)] = "UPDATE_SIZE",
- [const_ilog2(UBLK_F_AUTO_BUF_REG)] = "AUTO_BUF_REG",
- [const_ilog2(UBLK_F_QUIESCE)] = "QUIESCE",
- [const_ilog2(UBLK_F_PER_IO_DAEMON)] = "PER_IO_DAEMON",
+ FEAT_NAME(UBLK_F_SUPPORT_ZERO_COPY),
+ FEAT_NAME(UBLK_F_URING_CMD_COMP_IN_TASK),
+ FEAT_NAME(UBLK_F_NEED_GET_DATA),
+ FEAT_NAME(UBLK_F_USER_RECOVERY),
+ FEAT_NAME(UBLK_F_USER_RECOVERY_REISSUE),
+ FEAT_NAME(UBLK_F_UNPRIVILEGED_DEV),
+ FEAT_NAME(UBLK_F_CMD_IOCTL_ENCODE),
+ FEAT_NAME(UBLK_F_USER_COPY),
+ FEAT_NAME(UBLK_F_ZONED),
+ FEAT_NAME(UBLK_F_USER_RECOVERY_FAIL_IO),
+ FEAT_NAME(UBLK_F_UPDATE_SIZE),
+ FEAT_NAME(UBLK_F_AUTO_BUF_REG),
+ FEAT_NAME(UBLK_F_QUIESCE),
+ FEAT_NAME(UBLK_F_PER_IO_DAEMON),
+ FEAT_NAME(UBLK_F_BUF_REG_OFF_DAEMON),
};
struct ublk_dev *dev;
__u64 features = 0;
@@ -1425,7 +1427,7 @@ static int cmd_dev_get_features(void)
feat = feat_map[i];
else
feat = "unknown";
- printf("\t%-20s: 0x%llx\n", feat, 1ULL << i);
+ printf("0x%-16llx: %s\n", 1ULL << i, feat);
}
}
diff --git a/tools/testing/selftests/ublk/test_generic_01.sh b/tools/testing/selftests/ublk/test_generic_01.sh
index 9227a208ba53..21a31cd5491a 100755
--- a/tools/testing/selftests/ublk/test_generic_01.sh
+++ b/tools/testing/selftests/ublk/test_generic_01.sh
@@ -10,6 +10,10 @@ if ! _have_program bpftrace; then
exit "$UBLK_SKIP_CODE"
fi
+if ! _have_program fio; then
+ exit "$UBLK_SKIP_CODE"
+fi
+
_prep_test "null" "sequential io order"
dev_id=$(_add_ublk_dev -t null)
diff --git a/tools/testing/selftests/ublk/test_generic_02.sh b/tools/testing/selftests/ublk/test_generic_02.sh
index 3e80121e3bf5..12920768b1a0 100755
--- a/tools/testing/selftests/ublk/test_generic_02.sh
+++ b/tools/testing/selftests/ublk/test_generic_02.sh
@@ -10,6 +10,10 @@ if ! _have_program bpftrace; then
exit "$UBLK_SKIP_CODE"
fi
+if ! _have_program fio; then
+ exit "$UBLK_SKIP_CODE"
+fi
+
_prep_test "null" "sequential io order for MQ"
dev_id=$(_add_ublk_dev -t null -q 2)
diff --git a/tools/testing/selftests/ublk/test_generic_12.sh b/tools/testing/selftests/ublk/test_generic_12.sh
index 7abbb00d251d..b4046201b4d9 100755
--- a/tools/testing/selftests/ublk/test_generic_12.sh
+++ b/tools/testing/selftests/ublk/test_generic_12.sh
@@ -10,6 +10,10 @@ if ! _have_program bpftrace; then
exit "$UBLK_SKIP_CODE"
fi
+if ! _have_program fio; then
+ exit "$UBLK_SKIP_CODE"
+fi
+
_prep_test "null" "do imbalanced load, it should be balanced over I/O threads"
NTHREADS=6
diff --git a/tools/testing/selftests/ublk/test_generic_13.sh b/tools/testing/selftests/ublk/test_generic_13.sh
new file mode 100755
index 000000000000..b7aa90b1cb74
--- /dev/null
+++ b/tools/testing/selftests/ublk/test_generic_13.sh
@@ -0,0 +1,20 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
+
+TID="generic_13"
+ERR_CODE=0
+
+_prep_test "null" "check that feature list is complete"
+
+if ${UBLK_PROG} features | grep -q unknown; then
+ echo "# unknown feature detected!"
+ echo "# did you add a feature and forget to update feat_map in kublk?"
+ echo "# this failure is expected if running an older test suite against"
+ echo "# a newer kernel with new features added"
+ ERR_CODE=255
+fi
+
+_cleanup_test "null"
+_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_null_01.sh b/tools/testing/selftests/ublk/test_null_01.sh
index a34203f72668..c2cb8f7a09fe 100755
--- a/tools/testing/selftests/ublk/test_null_01.sh
+++ b/tools/testing/selftests/ublk/test_null_01.sh
@@ -6,6 +6,10 @@
TID="null_01"
ERR_CODE=0
+if ! _have_program fio; then
+ exit "$UBLK_SKIP_CODE"
+fi
+
_prep_test "null" "basic IO test"
dev_id=$(_add_ublk_dev -t null)
diff --git a/tools/testing/selftests/ublk/test_null_02.sh b/tools/testing/selftests/ublk/test_null_02.sh
index 5633ca876655..8accd35beb55 100755
--- a/tools/testing/selftests/ublk/test_null_02.sh
+++ b/tools/testing/selftests/ublk/test_null_02.sh
@@ -6,6 +6,10 @@
TID="null_02"
ERR_CODE=0
+if ! _have_program fio; then
+ exit "$UBLK_SKIP_CODE"
+fi
+
_prep_test "null" "basic IO test with zero copy"
dev_id=$(_add_ublk_dev -t null -z)
diff --git a/tools/testing/selftests/ublk/test_stress_05.sh b/tools/testing/selftests/ublk/test_stress_05.sh
index 566cfd90d192..274295061042 100755
--- a/tools/testing/selftests/ublk/test_stress_05.sh
+++ b/tools/testing/selftests/ublk/test_stress_05.sh
@@ -5,6 +5,10 @@
TID="stress_05"
ERR_CODE=0
+if ! _have_program fio; then
+ exit "$UBLK_SKIP_CODE"
+fi
+
run_io_and_remove()
{
local size=$1
diff --git a/tools/testing/selftests/ublk/utils.h b/tools/testing/selftests/ublk/utils.h
index 36545d1567f1..a852e0b7153e 100644
--- a/tools/testing/selftests/ublk/utils.h
+++ b/tools/testing/selftests/ublk/utils.h
@@ -2,8 +2,6 @@
#ifndef KUBLK_UTILS_H
#define KUBLK_UTILS_H
-#define __maybe_unused __attribute__((unused))
-
#ifndef min
#define min(a, b) ((a) < (b) ? (a) : (b))
#endif
diff --git a/tools/testing/selftests/vDSO/.gitignore b/tools/testing/selftests/vDSO/.gitignore
index 30d5c8f0e5c7..ba322a353aff 100644
--- a/tools/testing/selftests/vDSO/.gitignore
+++ b/tools/testing/selftests/vDSO/.gitignore
@@ -1,7 +1,6 @@
# SPDX-License-Identifier: GPL-2.0-only
vdso_test
vdso_test_abi
-vdso_test_clock_getres
vdso_test_correctness
vdso_test_gettimeofday
vdso_test_getcpu
diff --git a/tools/testing/selftests/vDSO/Makefile b/tools/testing/selftests/vDSO/Makefile
index 918a2caa070e..e361aca22a74 100644
--- a/tools/testing/selftests/vDSO/Makefile
+++ b/tools/testing/selftests/vDSO/Makefile
@@ -4,7 +4,6 @@ include ../../../scripts/Makefile.arch
TEST_GEN_PROGS := vdso_test_gettimeofday
TEST_GEN_PROGS += vdso_test_getcpu
TEST_GEN_PROGS += vdso_test_abi
-TEST_GEN_PROGS += vdso_test_clock_getres
ifeq ($(ARCH),$(filter $(ARCH),x86 x86_64))
TEST_GEN_PROGS += vdso_standalone_test_x86
endif
@@ -29,7 +28,6 @@ CFLAGS_NOLIBC := -nostdlib -nostdinc -ffreestanding -fno-asynchronous-unwind-tab
$(OUTPUT)/vdso_test_gettimeofday: parse_vdso.c vdso_test_gettimeofday.c
$(OUTPUT)/vdso_test_getcpu: parse_vdso.c vdso_test_getcpu.c
$(OUTPUT)/vdso_test_abi: parse_vdso.c vdso_test_abi.c
-$(OUTPUT)/vdso_test_clock_getres: vdso_test_clock_getres.c
$(OUTPUT)/vdso_standalone_test_x86: vdso_standalone_test_x86.c parse_vdso.c | headers
$(OUTPUT)/vdso_standalone_test_x86: CFLAGS:=$(CFLAGS_NOLIBC) $(CFLAGS)
diff --git a/tools/testing/selftests/vDSO/vdso_call.h b/tools/testing/selftests/vDSO/vdso_call.h
index bb237d771051..e7205584cbdc 100644
--- a/tools/testing/selftests/vDSO/vdso_call.h
+++ b/tools/testing/selftests/vDSO/vdso_call.h
@@ -44,7 +44,6 @@
register long _r6 asm ("r6"); \
register long _r7 asm ("r7"); \
register long _r8 asm ("r8"); \
- register long _rval asm ("r3"); \
\
LOADARGS_##nr(fn, args); \
\
@@ -54,13 +53,13 @@
" bns+ 1f\n" \
" neg 3, 3\n" \
"1:" \
- : "+r" (_r0), "=r" (_r3), "+r" (_r4), "+r" (_r5), \
+ : "+r" (_r0), "+r" (_r3), "+r" (_r4), "+r" (_r5), \
"+r" (_r6), "+r" (_r7), "+r" (_r8) \
- : "r" (_rval) \
+ : \
: "r9", "r10", "r11", "r12", "cr0", "cr1", "cr5", \
"cr6", "cr7", "xer", "lr", "ctr", "memory" \
); \
- _rval; \
+ _r3; \
})
#else
diff --git a/tools/testing/selftests/vDSO/vdso_test_abi.c b/tools/testing/selftests/vDSO/vdso_test_abi.c
index a54424e2336f..238d609a457a 100644
--- a/tools/testing/selftests/vDSO/vdso_test_abi.c
+++ b/tools/testing/selftests/vDSO/vdso_test_abi.c
@@ -26,24 +26,31 @@
static const char *version;
static const char **name;
+/* The same as struct __kernel_timespec */
+struct vdso_timespec64 {
+ uint64_t tv_sec;
+ uint64_t tv_nsec;
+};
+
typedef long (*vdso_gettimeofday_t)(struct timeval *tv, struct timezone *tz);
typedef long (*vdso_clock_gettime_t)(clockid_t clk_id, struct timespec *ts);
+typedef long (*vdso_clock_gettime64_t)(clockid_t clk_id, struct vdso_timespec64 *ts);
typedef long (*vdso_clock_getres_t)(clockid_t clk_id, struct timespec *ts);
typedef time_t (*vdso_time_t)(time_t *t);
-const char *vdso_clock_name[12] = {
- "CLOCK_REALTIME",
- "CLOCK_MONOTONIC",
- "CLOCK_PROCESS_CPUTIME_ID",
- "CLOCK_THREAD_CPUTIME_ID",
- "CLOCK_MONOTONIC_RAW",
- "CLOCK_REALTIME_COARSE",
- "CLOCK_MONOTONIC_COARSE",
- "CLOCK_BOOTTIME",
- "CLOCK_REALTIME_ALARM",
- "CLOCK_BOOTTIME_ALARM",
- "CLOCK_SGI_CYCLE",
- "CLOCK_TAI",
+static const char * const vdso_clock_name[] = {
+ [CLOCK_REALTIME] = "CLOCK_REALTIME",
+ [CLOCK_MONOTONIC] = "CLOCK_MONOTONIC",
+ [CLOCK_PROCESS_CPUTIME_ID] = "CLOCK_PROCESS_CPUTIME_ID",
+ [CLOCK_THREAD_CPUTIME_ID] = "CLOCK_THREAD_CPUTIME_ID",
+ [CLOCK_MONOTONIC_RAW] = "CLOCK_MONOTONIC_RAW",
+ [CLOCK_REALTIME_COARSE] = "CLOCK_REALTIME_COARSE",
+ [CLOCK_MONOTONIC_COARSE] = "CLOCK_MONOTONIC_COARSE",
+ [CLOCK_BOOTTIME] = "CLOCK_BOOTTIME",
+ [CLOCK_REALTIME_ALARM] = "CLOCK_REALTIME_ALARM",
+ [CLOCK_BOOTTIME_ALARM] = "CLOCK_BOOTTIME_ALARM",
+ [10 /* CLOCK_SGI_CYCLE */] = "CLOCK_SGI_CYCLE",
+ [CLOCK_TAI] = "CLOCK_TAI",
};
static void vdso_test_gettimeofday(void)
@@ -70,6 +77,33 @@ static void vdso_test_gettimeofday(void)
}
}
+static void vdso_test_clock_gettime64(clockid_t clk_id)
+{
+ /* Find clock_gettime64. */
+ vdso_clock_gettime64_t vdso_clock_gettime64 =
+ (vdso_clock_gettime64_t)vdso_sym(version, name[5]);
+
+ if (!vdso_clock_gettime64) {
+ ksft_print_msg("Couldn't find %s\n", name[5]);
+ ksft_test_result_skip("%s %s\n", name[5],
+ vdso_clock_name[clk_id]);
+ return;
+ }
+
+ struct vdso_timespec64 ts;
+ long ret = VDSO_CALL(vdso_clock_gettime64, 2, clk_id, &ts);
+
+ if (ret == 0) {
+ ksft_print_msg("The time is %lld.%06lld\n",
+ (long long)ts.tv_sec, (long long)ts.tv_nsec);
+ ksft_test_result_pass("%s %s\n", name[5],
+ vdso_clock_name[clk_id]);
+ } else {
+ ksft_test_result_fail("%s %s\n", name[5],
+ vdso_clock_name[clk_id]);
+ }
+}
+
static void vdso_test_clock_gettime(clockid_t clk_id)
{
/* Find clock_gettime. */
@@ -171,23 +205,23 @@ static inline void vdso_test_clock(clockid_t clock_id)
ksft_print_msg("clock_id: %s\n", vdso_clock_name[clock_id]);
vdso_test_clock_gettime(clock_id);
+ vdso_test_clock_gettime64(clock_id);
vdso_test_clock_getres(clock_id);
}
-#define VDSO_TEST_PLAN 16
+#define VDSO_TEST_PLAN 29
int main(int argc, char **argv)
{
unsigned long sysinfo_ehdr = getauxval(AT_SYSINFO_EHDR);
ksft_print_header();
- ksft_set_plan(VDSO_TEST_PLAN);
- if (!sysinfo_ehdr) {
- ksft_print_msg("AT_SYSINFO_EHDR is not present!\n");
- return KSFT_SKIP;
- }
+ if (!sysinfo_ehdr)
+ ksft_exit_skip("AT_SYSINFO_EHDR is not present!\n");
+
+ ksft_set_plan(VDSO_TEST_PLAN);
version = versions[VDSO_VERSION];
name = (const char **)&names[VDSO_NAMES];
@@ -198,40 +232,17 @@ int main(int argc, char **argv)
vdso_test_gettimeofday();
-#if _POSIX_TIMERS > 0
-
-#ifdef CLOCK_REALTIME
vdso_test_clock(CLOCK_REALTIME);
-#endif
-
-#ifdef CLOCK_BOOTTIME
vdso_test_clock(CLOCK_BOOTTIME);
-#endif
-
-#ifdef CLOCK_TAI
vdso_test_clock(CLOCK_TAI);
-#endif
-
-#ifdef CLOCK_REALTIME_COARSE
vdso_test_clock(CLOCK_REALTIME_COARSE);
-#endif
-
-#ifdef CLOCK_MONOTONIC
vdso_test_clock(CLOCK_MONOTONIC);
-#endif
-
-#ifdef CLOCK_MONOTONIC_RAW
vdso_test_clock(CLOCK_MONOTONIC_RAW);
-#endif
-
-#ifdef CLOCK_MONOTONIC_COARSE
vdso_test_clock(CLOCK_MONOTONIC_COARSE);
-#endif
-
-#endif
+ vdso_test_clock(CLOCK_PROCESS_CPUTIME_ID);
+ vdso_test_clock(CLOCK_THREAD_CPUTIME_ID);
vdso_test_time();
- ksft_print_cnts();
- return ksft_get_fail_cnt() == 0 ? KSFT_PASS : KSFT_FAIL;
+ ksft_finished();
}
diff --git a/tools/testing/selftests/vDSO/vdso_test_clock_getres.c b/tools/testing/selftests/vDSO/vdso_test_clock_getres.c
deleted file mode 100644
index b5d5f59f725a..000000000000
--- a/tools/testing/selftests/vDSO/vdso_test_clock_getres.c
+++ /dev/null
@@ -1,123 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note
-/*
- * vdso_clock_getres.c: Sample code to test clock_getres.
- * Copyright (c) 2019 Arm Ltd.
- *
- * Compile with:
- * gcc -std=gnu99 vdso_clock_getres.c
- *
- * Tested on ARM, ARM64, MIPS32, x86 (32-bit and 64-bit),
- * Power (32-bit and 64-bit), S390x (32-bit and 64-bit).
- * Might work on other architectures.
- */
-
-#define _GNU_SOURCE
-#include <elf.h>
-#include <fcntl.h>
-#include <stdint.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <time.h>
-#include <sys/auxv.h>
-#include <sys/mman.h>
-#include <sys/time.h>
-#include <unistd.h>
-#include <sys/syscall.h>
-
-#include "../kselftest.h"
-
-static long syscall_clock_getres(clockid_t _clkid, struct timespec *_ts)
-{
- long ret;
-
- ret = syscall(SYS_clock_getres, _clkid, _ts);
-
- return ret;
-}
-
-const char *vdso_clock_name[12] = {
- "CLOCK_REALTIME",
- "CLOCK_MONOTONIC",
- "CLOCK_PROCESS_CPUTIME_ID",
- "CLOCK_THREAD_CPUTIME_ID",
- "CLOCK_MONOTONIC_RAW",
- "CLOCK_REALTIME_COARSE",
- "CLOCK_MONOTONIC_COARSE",
- "CLOCK_BOOTTIME",
- "CLOCK_REALTIME_ALARM",
- "CLOCK_BOOTTIME_ALARM",
- "CLOCK_SGI_CYCLE",
- "CLOCK_TAI",
-};
-
-/*
- * This function calls clock_getres in vdso and by system call
- * with different values for clock_id.
- *
- * Example of output:
- *
- * clock_id: CLOCK_REALTIME [PASS]
- * clock_id: CLOCK_BOOTTIME [PASS]
- * clock_id: CLOCK_TAI [PASS]
- * clock_id: CLOCK_REALTIME_COARSE [PASS]
- * clock_id: CLOCK_MONOTONIC [PASS]
- * clock_id: CLOCK_MONOTONIC_RAW [PASS]
- * clock_id: CLOCK_MONOTONIC_COARSE [PASS]
- */
-static inline int vdso_test_clock(unsigned int clock_id)
-{
- struct timespec x, y;
-
- printf("clock_id: %s", vdso_clock_name[clock_id]);
- clock_getres(clock_id, &x);
- syscall_clock_getres(clock_id, &y);
-
- if ((x.tv_sec != y.tv_sec) || (x.tv_nsec != y.tv_nsec)) {
- printf(" [FAIL]\n");
- return KSFT_FAIL;
- }
-
- printf(" [PASS]\n");
- return KSFT_PASS;
-}
-
-int main(int argc, char **argv)
-{
- int ret = 0;
-
-#if _POSIX_TIMERS > 0
-
-#ifdef CLOCK_REALTIME
- ret += vdso_test_clock(CLOCK_REALTIME);
-#endif
-
-#ifdef CLOCK_BOOTTIME
- ret += vdso_test_clock(CLOCK_BOOTTIME);
-#endif
-
-#ifdef CLOCK_TAI
- ret += vdso_test_clock(CLOCK_TAI);
-#endif
-
-#ifdef CLOCK_REALTIME_COARSE
- ret += vdso_test_clock(CLOCK_REALTIME_COARSE);
-#endif
-
-#ifdef CLOCK_MONOTONIC
- ret += vdso_test_clock(CLOCK_MONOTONIC);
-#endif
-
-#ifdef CLOCK_MONOTONIC_RAW
- ret += vdso_test_clock(CLOCK_MONOTONIC_RAW);
-#endif
-
-#ifdef CLOCK_MONOTONIC_COARSE
- ret += vdso_test_clock(CLOCK_MONOTONIC_COARSE);
-#endif
-
-#endif
- if (ret > 0)
- return KSFT_FAIL;
-
- return KSFT_PASS;
-}
diff --git a/tools/testing/selftests/watchdog/watchdog-test.c b/tools/testing/selftests/watchdog/watchdog-test.c
index a1f506ba5578..4f09c5db0c7f 100644
--- a/tools/testing/selftests/watchdog/watchdog-test.c
+++ b/tools/testing/selftests/watchdog/watchdog-test.c
@@ -332,6 +332,12 @@ int main(int argc, char *argv[])
if (oneshot)
goto end;
+ /* Check if WDIOF_KEEPALIVEPING is supported */
+ if (!(info.options & WDIOF_KEEPALIVEPING)) {
+ printf("WDIOC_KEEPALIVE not supported by this device\n");
+ goto end;
+ }
+
printf("Watchdog Ticking Away!\n");
/*
diff --git a/tools/testing/selftests/wireguard/qemu/kernel.config b/tools/testing/selftests/wireguard/qemu/kernel.config
index 0a5381717e9f..936b18be07cf 100644
--- a/tools/testing/selftests/wireguard/qemu/kernel.config
+++ b/tools/testing/selftests/wireguard/qemu/kernel.config
@@ -20,9 +20,10 @@ CONFIG_NETFILTER_XTABLES_LEGACY=y
CONFIG_NETFILTER_XT_NAT=y
CONFIG_NETFILTER_XT_MATCH_LENGTH=y
CONFIG_NETFILTER_XT_MARK=y
-CONFIG_NETFILTER_XT_TARGET_MASQUERADE=m
-CONFIG_IP_NF_TARGET_REJECT=m
-CONFIG_IP6_NF_TARGET_REJECT=m
+CONFIG_NETFILTER_XT_TARGET_MASQUERADE=y
+CONFIG_IP_NF_TARGET_REJECT=y
+CONFIG_IP6_NF_TARGET_REJECT=y
+CONFIG_IP_NF_IPTABLES_LEGACY=y
CONFIG_IP_NF_IPTABLES=y
CONFIG_IP_NF_FILTER=y
CONFIG_IP_NF_MANGLE=y
@@ -48,7 +49,6 @@ CONFIG_JUMP_LABEL=y
CONFIG_FUTEX=y
CONFIG_SHMEM=y
CONFIG_SLUB=y
-CONFIG_SPARSEMEM_VMEMMAP=y
CONFIG_SMP=y
CONFIG_SCHED_SMT=y
CONFIG_SCHED_MC=y
diff --git a/tools/testing/selftests/zram/README b/tools/testing/selftests/zram/README
index 110b34834a6f..82921c75681c 100644
--- a/tools/testing/selftests/zram/README
+++ b/tools/testing/selftests/zram/README
@@ -14,7 +14,6 @@ Statistics for individual zram devices are exported through sysfs nodes at
Kconfig required:
CONFIG_ZRAM=y
CONFIG_CRYPTO_LZ4=y
-CONFIG_ZPOOL=y
CONFIG_ZSMALLOC=y
ZRAM Testcases
diff --git a/tools/testing/shared/linux.c b/tools/testing/shared/linux.c
index 0f97fb0d19e1..8c7257155958 100644
--- a/tools/testing/shared/linux.c
+++ b/tools/testing/shared/linux.c
@@ -16,21 +16,6 @@ int nr_allocated;
int preempt_count;
int test_verbose;
-struct kmem_cache {
- pthread_mutex_t lock;
- unsigned int size;
- unsigned int align;
- int nr_objs;
- void *objs;
- void (*ctor)(void *);
- unsigned int non_kernel;
- unsigned long nr_allocated;
- unsigned long nr_tallocated;
- bool exec_callback;
- void (*callback)(void *);
- void *private;
-};
-
void kmem_cache_set_callback(struct kmem_cache *cachep, void (*callback)(void *))
{
cachep->callback = callback;
@@ -79,7 +64,8 @@ void *kmem_cache_alloc_lru(struct kmem_cache *cachep, struct list_lru *lru,
if (!(gfp & __GFP_DIRECT_RECLAIM)) {
if (!cachep->non_kernel) {
- cachep->exec_callback = true;
+ if (cachep->callback)
+ cachep->exec_callback = true;
return NULL;
}
@@ -152,6 +138,12 @@ void kmem_cache_free_bulk(struct kmem_cache *cachep, size_t size, void **list)
if (kmalloc_verbose)
pr_debug("Bulk free %p[0-%zu]\n", list, size - 1);
+ if (cachep->exec_callback) {
+ if (cachep->callback)
+ cachep->callback(cachep->private);
+ cachep->exec_callback = false;
+ }
+
pthread_mutex_lock(&cachep->lock);
for (int i = 0; i < size; i++)
kmem_cache_free_locked(cachep, list[i]);
@@ -219,6 +211,8 @@ int kmem_cache_alloc_bulk(struct kmem_cache *cachep, gfp_t gfp, size_t size,
for (i = 0; i < size; i++)
__kmem_cache_free_locked(cachep, p[i]);
pthread_mutex_unlock(&cachep->lock);
+ if (cachep->callback)
+ cachep->exec_callback = true;
return 0;
}
@@ -234,26 +228,112 @@ int kmem_cache_alloc_bulk(struct kmem_cache *cachep, gfp_t gfp, size_t size,
}
struct kmem_cache *
-kmem_cache_create(const char *name, unsigned int size, unsigned int align,
- unsigned int flags, void (*ctor)(void *))
+__kmem_cache_create_args(const char *name, unsigned int size,
+ struct kmem_cache_args *args,
+ unsigned int flags)
{
struct kmem_cache *ret = malloc(sizeof(*ret));
pthread_mutex_init(&ret->lock, NULL);
ret->size = size;
- ret->align = align;
+ ret->align = args->align;
+ ret->sheaf_capacity = args->sheaf_capacity;
ret->nr_objs = 0;
ret->nr_allocated = 0;
ret->nr_tallocated = 0;
ret->objs = NULL;
- ret->ctor = ctor;
+ ret->ctor = args->ctor;
ret->non_kernel = 0;
ret->exec_callback = false;
ret->callback = NULL;
ret->private = NULL;
+
return ret;
}
+struct slab_sheaf *
+kmem_cache_prefill_sheaf(struct kmem_cache *s, gfp_t gfp, unsigned int size)
+{
+ struct slab_sheaf *sheaf;
+ unsigned int capacity;
+
+ if (s->exec_callback) {
+ if (s->callback)
+ s->callback(s->private);
+ s->exec_callback = false;
+ }
+
+ capacity = max(size, s->sheaf_capacity);
+
+ sheaf = calloc(1, sizeof(*sheaf) + sizeof(void *) * capacity);
+ if (!sheaf)
+ return NULL;
+
+ sheaf->cache = s;
+ sheaf->capacity = capacity;
+ sheaf->size = kmem_cache_alloc_bulk(s, gfp, size, sheaf->objects);
+ if (!sheaf->size) {
+ free(sheaf);
+ return NULL;
+ }
+
+ return sheaf;
+}
+
+int kmem_cache_refill_sheaf(struct kmem_cache *s, gfp_t gfp,
+ struct slab_sheaf **sheafp, unsigned int size)
+{
+ struct slab_sheaf *sheaf = *sheafp;
+ int refill;
+
+ if (sheaf->size >= size)
+ return 0;
+
+ if (size > sheaf->capacity) {
+ sheaf = kmem_cache_prefill_sheaf(s, gfp, size);
+ if (!sheaf)
+ return -ENOMEM;
+
+ kmem_cache_return_sheaf(s, gfp, *sheafp);
+ *sheafp = sheaf;
+ return 0;
+ }
+
+ refill = kmem_cache_alloc_bulk(s, gfp, size - sheaf->size,
+ &sheaf->objects[sheaf->size]);
+ if (!refill)
+ return -ENOMEM;
+
+ sheaf->size += refill;
+ return 0;
+}
+
+void kmem_cache_return_sheaf(struct kmem_cache *s, gfp_t gfp,
+ struct slab_sheaf *sheaf)
+{
+ if (sheaf->size)
+ kmem_cache_free_bulk(s, sheaf->size, &sheaf->objects[0]);
+
+ free(sheaf);
+}
+
+void *
+kmem_cache_alloc_from_sheaf(struct kmem_cache *s, gfp_t gfp,
+ struct slab_sheaf *sheaf)
+{
+ void *obj;
+
+ if (sheaf->size == 0) {
+ printf("Nothing left in sheaf!\n");
+ return NULL;
+ }
+
+ obj = sheaf->objects[--sheaf->size];
+ sheaf->objects[sheaf->size] = NULL;
+
+ return obj;
+}
+
/*
* Test the test infrastructure for kem_cache_alloc/free and bulk counterparts.
*/
diff --git a/tools/testing/shared/linux/maple_tree.h b/tools/testing/shared/linux/maple_tree.h
index f67d47d32857..7d0fadef0f11 100644
--- a/tools/testing/shared/linux/maple_tree.h
+++ b/tools/testing/shared/linux/maple_tree.h
@@ -1,7 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0+ */
-#define atomic_t int32_t
-#define atomic_inc(x) uatomic_inc(x)
-#define atomic_read(x) uatomic_read(x)
-#define atomic_set(x, y) uatomic_set(x, y)
+#include <linux/atomic.h>
+
#define U8_MAX UCHAR_MAX
#include "../../../../include/linux/maple_tree.h"
diff --git a/tools/testing/shared/maple-shared.h b/tools/testing/shared/maple-shared.h
index dc4d30f3860b..2a1e9a8594a2 100644
--- a/tools/testing/shared/maple-shared.h
+++ b/tools/testing/shared/maple-shared.h
@@ -10,4 +10,15 @@
#include <time.h>
#include "linux/init.h"
+void maple_rcu_cb(struct rcu_head *head);
+#define rcu_cb maple_rcu_cb
+
+#define kfree_rcu(_struct, _memb) \
+do { \
+ typeof(_struct) _p_struct = (_struct); \
+ \
+ call_rcu(&((_p_struct)->_memb), rcu_cb); \
+} while(0);
+
+
#endif /* __MAPLE_SHARED_H__ */
diff --git a/tools/testing/shared/maple-shim.c b/tools/testing/shared/maple-shim.c
index 640df76f483e..16252ee616c0 100644
--- a/tools/testing/shared/maple-shim.c
+++ b/tools/testing/shared/maple-shim.c
@@ -3,5 +3,12 @@
/* Very simple shim around the maple tree. */
#include "maple-shared.h"
+#include <linux/slab.h>
#include "../../../lib/maple_tree.c"
+
+void maple_rcu_cb(struct rcu_head *head) {
+ struct maple_node *node = container_of(head, struct maple_node, rcu);
+
+ kmem_cache_free(maple_node_cache, node);
+}
diff --git a/tools/testing/shared/shared.mk b/tools/testing/shared/shared.mk
index 923ee2492256..5bcdf26c8a9d 100644
--- a/tools/testing/shared/shared.mk
+++ b/tools/testing/shared/shared.mk
@@ -1,7 +1,10 @@
# SPDX-License-Identifier: GPL-2.0
+include ../../scripts/Makefile.arch
-CFLAGS += -I../shared -I. -I../../include -I../../../lib -g -Og -Wall \
+CFLAGS += -I../shared -I. -I../../include -I../../arch/$(SRCARCH)/include \
+ -I../../../lib -g -Og -Wall \
-D_LGPL_SOURCE -fsanitize=address -fsanitize=undefined
+CFLAGS += $(EXTRA_CFLAGS)
LDFLAGS += -fsanitize=address -fsanitize=undefined
LDLIBS += -lpthread -lurcu
LIBS := slab.o find_bit.o bitmap.o hweight.o vsprintf.o
@@ -11,6 +14,7 @@ SHARED_DEPS = Makefile ../shared/shared.mk ../shared/*.h generated/map-shift.h \
generated/bit-length.h generated/autoconf.h \
../../include/linux/*.h \
../../include/asm/*.h \
+ ../../arch/$(SRCARCH)/include/asm/*.h \
../../../include/linux/xarray.h \
../../../include/linux/maple_tree.h \
../../../include/linux/radix-tree.h \
diff --git a/tools/testing/vma/linux/atomic.h b/tools/testing/vma/linux/atomic.h
deleted file mode 100644
index 788c597c4fde..000000000000
--- a/tools/testing/vma/linux/atomic.h
+++ /dev/null
@@ -1,17 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-
-#ifndef _LINUX_ATOMIC_H
-#define _LINUX_ATOMIC_H
-
-#define atomic_t int32_t
-#define atomic_inc(x) uatomic_inc(x)
-#define atomic_read(x) uatomic_read(x)
-#define atomic_set(x, y) uatomic_set(x, y)
-#define U8_MAX UCHAR_MAX
-
-#ifndef atomic_cmpxchg_relaxed
-#define atomic_cmpxchg_relaxed uatomic_cmpxchg
-#define atomic_cmpxchg_release uatomic_cmpxchg
-#endif /* atomic_cmpxchg_relaxed */
-
-#endif /* _LINUX_ATOMIC_H */
diff --git a/tools/testing/vma/vma_internal.h b/tools/testing/vma/vma_internal.h
index 3639aa8dd2b0..dc976a285ad2 100644
--- a/tools/testing/vma/vma_internal.h
+++ b/tools/testing/vma/vma_internal.h
@@ -21,11 +21,13 @@
#include <stdlib.h>
+#include <linux/atomic.h>
#include <linux/list.h>
#include <linux/maple_tree.h>
#include <linux/mm.h>
#include <linux/rbtree.h>
#include <linux/refcount.h>
+#include <linux/slab.h>
extern unsigned long stack_guard_gap;
#ifdef CONFIG_MMU
@@ -249,6 +251,14 @@ struct mutex {};
#define DEFINE_MUTEX(mutexname) \
struct mutex mutexname = {}
+#define DECLARE_BITMAP(name, bits) \
+ unsigned long name[BITS_TO_LONGS(bits)]
+
+#define NUM_MM_FLAG_BITS (64)
+typedef struct {
+ __private DECLARE_BITMAP(__mm_flags, NUM_MM_FLAG_BITS);
+} mm_flags_t;
+
struct mm_struct {
struct maple_tree mm_mt;
int map_count; /* number of VMAs */
@@ -260,7 +270,7 @@ struct mm_struct {
unsigned long def_flags;
- unsigned long flags; /* Must use atomic bitops to access */
+ mm_flags_t flags; /* Must use mm_flags_* helpers to access */
};
struct vm_area_struct;
@@ -274,13 +284,14 @@ struct vm_area_struct;
*/
struct vm_area_desc {
/* Immutable state. */
- struct mm_struct *mm;
+ const struct mm_struct *const mm;
+ struct file *const file; /* May vary from vm_file in stacked callers. */
unsigned long start;
unsigned long end;
/* Mutable fields. Populated with initial state. */
pgoff_t pgoff;
- struct file *file;
+ struct file *vm_file;
vm_flags_t vm_flags;
pgprot_t page_prot;
@@ -467,13 +478,21 @@ struct vm_operations_struct {
struct mempolicy *(*get_policy)(struct vm_area_struct *vma,
unsigned long addr, pgoff_t *ilx);
#endif
+#ifdef CONFIG_FIND_NORMAL_PAGE
/*
- * Called by vm_normal_page() for special PTEs to find the
- * page for @addr. This is useful if the default behavior
- * (using pte_page()) would not find the correct page.
+ * Called by vm_normal_page() for special PTEs in @vma at @addr. This
+ * allows for returning a "normal" page from vm_normal_page() even
+ * though the PTE indicates that the "struct page" either does not exist
+ * or should not be touched: "special".
+ *
+ * Do not add new users: this really only works when a "normal" page
+ * was mapped, but then the PTE got changed to something weird (+
+ * marked special) that would not make pte_pfn() identify the originally
+ * inserted page.
*/
- struct page *(*find_special_page)(struct vm_area_struct *vma,
- unsigned long addr);
+ struct page *(*find_normal_page)(struct vm_area_struct *vma,
+ unsigned long addr);
+#endif /* CONFIG_FIND_NORMAL_PAGE */
};
struct vm_unmapped_area_info {
@@ -509,65 +528,6 @@ struct pagetable_move_control {
.len_in = len_, \
}
-struct kmem_cache_args {
- /**
- * @align: The required alignment for the objects.
- *
- * %0 means no specific alignment is requested.
- */
- unsigned int align;
- /**
- * @useroffset: Usercopy region offset.
- *
- * %0 is a valid offset, when @usersize is non-%0
- */
- unsigned int useroffset;
- /**
- * @usersize: Usercopy region size.
- *
- * %0 means no usercopy region is specified.
- */
- unsigned int usersize;
- /**
- * @freeptr_offset: Custom offset for the free pointer
- * in &SLAB_TYPESAFE_BY_RCU caches
- *
- * By default &SLAB_TYPESAFE_BY_RCU caches place the free pointer
- * outside of the object. This might cause the object to grow in size.
- * Cache creators that have a reason to avoid this can specify a custom
- * free pointer offset in their struct where the free pointer will be
- * placed.
- *
- * Note that placing the free pointer inside the object requires the
- * caller to ensure that no fields are invalidated that are required to
- * guard against object recycling (See &SLAB_TYPESAFE_BY_RCU for
- * details).
- *
- * Using %0 as a value for @freeptr_offset is valid. If @freeptr_offset
- * is specified, %use_freeptr_offset must be set %true.
- *
- * Note that @ctor currently isn't supported with custom free pointers
- * as a @ctor requires an external free pointer.
- */
- unsigned int freeptr_offset;
- /**
- * @use_freeptr_offset: Whether a @freeptr_offset is used.
- */
- bool use_freeptr_offset;
- /**
- * @ctor: A constructor for the objects.
- *
- * The constructor is invoked for each object in a newly allocated slab
- * page. It is the cache user's responsibility to free object in the
- * same state as after calling the constructor, or deal appropriately
- * with any differences between a freshly constructed and a reallocated
- * object.
- *
- * %NULL means no constructor.
- */
- void (*ctor)(void *);
-};
-
static inline void vma_iter_invalidate(struct vma_iterator *vmi)
{
mas_pause(&vmi->mas);
@@ -652,40 +612,6 @@ static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm)
vma->vm_lock_seq = UINT_MAX;
}
-struct kmem_cache {
- const char *name;
- size_t object_size;
- struct kmem_cache_args *args;
-};
-
-static inline struct kmem_cache *__kmem_cache_create(const char *name,
- size_t object_size,
- struct kmem_cache_args *args)
-{
- struct kmem_cache *ret = malloc(sizeof(struct kmem_cache));
-
- ret->name = name;
- ret->object_size = object_size;
- ret->args = args;
-
- return ret;
-}
-
-#define kmem_cache_create(__name, __object_size, __args, ...) \
- __kmem_cache_create((__name), (__object_size), (__args))
-
-static inline void *kmem_cache_alloc(struct kmem_cache *s, gfp_t gfpflags)
-{
- (void)gfpflags;
-
- return calloc(s->object_size, 1);
-}
-
-static inline void kmem_cache_free(struct kmem_cache *s, void *x)
-{
- free(x);
-}
-
/*
* These are defined in vma.h, but sadly vm_stat_account() is referenced by
* kernel/fork.c, so we have to these broadly available there, and temporarily
@@ -842,11 +768,11 @@ static inline unsigned long vma_pages(struct vm_area_struct *vma)
return (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
}
-static inline void fput(struct file *)
+static inline void fput(struct file *file)
{
}
-static inline void mpol_put(struct mempolicy *)
+static inline void mpol_put(struct mempolicy *pol)
{
}
@@ -854,15 +780,15 @@ static inline void lru_add_drain(void)
{
}
-static inline void tlb_gather_mmu(struct mmu_gather *, struct mm_struct *)
+static inline void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm)
{
}
-static inline void update_hiwater_rss(struct mm_struct *)
+static inline void update_hiwater_rss(struct mm_struct *mm)
{
}
-static inline void update_hiwater_vm(struct mm_struct *)
+static inline void update_hiwater_vm(struct mm_struct *mm)
{
}
@@ -871,36 +797,23 @@ static inline void unmap_vmas(struct mmu_gather *tlb, struct ma_state *mas,
unsigned long end_addr, unsigned long tree_end,
bool mm_wr_locked)
{
- (void)tlb;
- (void)mas;
- (void)vma;
- (void)start_addr;
- (void)end_addr;
- (void)tree_end;
- (void)mm_wr_locked;
}
static inline void free_pgtables(struct mmu_gather *tlb, struct ma_state *mas,
struct vm_area_struct *vma, unsigned long floor,
unsigned long ceiling, bool mm_wr_locked)
{
- (void)tlb;
- (void)mas;
- (void)vma;
- (void)floor;
- (void)ceiling;
- (void)mm_wr_locked;
}
-static inline void mapping_unmap_writable(struct address_space *)
+static inline void mapping_unmap_writable(struct address_space *mapping)
{
}
-static inline void flush_dcache_mmap_lock(struct address_space *)
+static inline void flush_dcache_mmap_lock(struct address_space *mapping)
{
}
-static inline void tlb_finish_mmu(struct mmu_gather *)
+static inline void tlb_finish_mmu(struct mmu_gather *tlb)
{
}
@@ -909,7 +822,7 @@ static inline struct file *get_file(struct file *f)
return f;
}
-static inline int vma_dup_policy(struct vm_area_struct *, struct vm_area_struct *)
+static inline int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst)
{
return 0;
}
@@ -936,10 +849,6 @@ static inline void vma_adjust_trans_huge(struct vm_area_struct *vma,
unsigned long end,
struct vm_area_struct *next)
{
- (void)vma;
- (void)start;
- (void)end;
- (void)next;
}
static inline void hugetlb_split(struct vm_area_struct *, unsigned long) {}
@@ -959,51 +868,48 @@ static inline void vm_acct_memory(long pages)
{
}
-static inline void vma_interval_tree_insert(struct vm_area_struct *,
- struct rb_root_cached *)
+static inline void vma_interval_tree_insert(struct vm_area_struct *vma,
+ struct rb_root_cached *rb)
{
}
-static inline void vma_interval_tree_remove(struct vm_area_struct *,
- struct rb_root_cached *)
+static inline void vma_interval_tree_remove(struct vm_area_struct *vma,
+ struct rb_root_cached *rb)
{
}
-static inline void flush_dcache_mmap_unlock(struct address_space *)
+static inline void flush_dcache_mmap_unlock(struct address_space *mapping)
{
}
-static inline void anon_vma_interval_tree_insert(struct anon_vma_chain*,
- struct rb_root_cached *)
+static inline void anon_vma_interval_tree_insert(struct anon_vma_chain *avc,
+ struct rb_root_cached *rb)
{
}
-static inline void anon_vma_interval_tree_remove(struct anon_vma_chain*,
- struct rb_root_cached *)
+static inline void anon_vma_interval_tree_remove(struct anon_vma_chain *avc,
+ struct rb_root_cached *rb)
{
}
-static inline void uprobe_mmap(struct vm_area_struct *)
+static inline void uprobe_mmap(struct vm_area_struct *vma)
{
}
static inline void uprobe_munmap(struct vm_area_struct *vma,
unsigned long start, unsigned long end)
{
- (void)vma;
- (void)start;
- (void)end;
}
-static inline void i_mmap_lock_write(struct address_space *)
+static inline void i_mmap_lock_write(struct address_space *mapping)
{
}
-static inline void anon_vma_lock_write(struct anon_vma *)
+static inline void anon_vma_lock_write(struct anon_vma *anon_vma)
{
}
-static inline void vma_assert_write_locked(struct vm_area_struct *)
+static inline void vma_assert_write_locked(struct vm_area_struct *vma)
{
}
@@ -1013,16 +919,16 @@ static inline void unlink_anon_vmas(struct vm_area_struct *vma)
vma->anon_vma->was_unlinked = true;
}
-static inline void anon_vma_unlock_write(struct anon_vma *)
+static inline void anon_vma_unlock_write(struct anon_vma *anon_vma)
{
}
-static inline void i_mmap_unlock_write(struct address_space *)
+static inline void i_mmap_unlock_write(struct address_space *mapping)
{
}
-static inline void anon_vma_merge(struct vm_area_struct *,
- struct vm_area_struct *)
+static inline void anon_vma_merge(struct vm_area_struct *vma,
+ struct vm_area_struct *next)
{
}
@@ -1031,27 +937,22 @@ static inline int userfaultfd_unmap_prep(struct vm_area_struct *vma,
unsigned long end,
struct list_head *unmaps)
{
- (void)vma;
- (void)start;
- (void)end;
- (void)unmaps;
-
return 0;
}
-static inline void mmap_write_downgrade(struct mm_struct *)
+static inline void mmap_write_downgrade(struct mm_struct *mm)
{
}
-static inline void mmap_read_unlock(struct mm_struct *)
+static inline void mmap_read_unlock(struct mm_struct *mm)
{
}
-static inline void mmap_write_unlock(struct mm_struct *)
+static inline void mmap_write_unlock(struct mm_struct *mm)
{
}
-static inline int mmap_write_lock_killable(struct mm_struct *)
+static inline int mmap_write_lock_killable(struct mm_struct *mm)
{
return 0;
}
@@ -1060,10 +961,6 @@ static inline bool can_modify_mm(struct mm_struct *mm,
unsigned long start,
unsigned long end)
{
- (void)mm;
- (void)start;
- (void)end;
-
return true;
}
@@ -1071,16 +968,13 @@ static inline void arch_unmap(struct mm_struct *mm,
unsigned long start,
unsigned long end)
{
- (void)mm;
- (void)start;
- (void)end;
}
-static inline void mmap_assert_locked(struct mm_struct *)
+static inline void mmap_assert_locked(struct mm_struct *mm)
{
}
-static inline bool mpol_equal(struct mempolicy *, struct mempolicy *)
+static inline bool mpol_equal(struct mempolicy *a, struct mempolicy *b)
{
return true;
}
@@ -1088,63 +982,62 @@ static inline bool mpol_equal(struct mempolicy *, struct mempolicy *)
static inline void khugepaged_enter_vma(struct vm_area_struct *vma,
vm_flags_t vm_flags)
{
- (void)vma;
- (void)vm_flags;
}
-static inline bool mapping_can_writeback(struct address_space *)
+static inline bool mapping_can_writeback(struct address_space *mapping)
{
return true;
}
-static inline bool is_vm_hugetlb_page(struct vm_area_struct *)
+static inline bool is_vm_hugetlb_page(struct vm_area_struct *vma)
{
return false;
}
-static inline bool vma_soft_dirty_enabled(struct vm_area_struct *)
+static inline bool vma_soft_dirty_enabled(struct vm_area_struct *vma)
{
return false;
}
-static inline bool userfaultfd_wp(struct vm_area_struct *)
+static inline bool userfaultfd_wp(struct vm_area_struct *vma)
{
return false;
}
-static inline void mmap_assert_write_locked(struct mm_struct *)
+static inline void mmap_assert_write_locked(struct mm_struct *mm)
{
}
-static inline void mutex_lock(struct mutex *)
+static inline void mutex_lock(struct mutex *lock)
{
}
-static inline void mutex_unlock(struct mutex *)
+static inline void mutex_unlock(struct mutex *lock)
{
}
-static inline bool mutex_is_locked(struct mutex *)
+static inline bool mutex_is_locked(struct mutex *lock)
{
return true;
}
-static inline bool signal_pending(void *)
+static inline bool signal_pending(void *p)
{
return false;
}
-static inline bool is_file_hugepages(struct file *)
+static inline bool is_file_hugepages(struct file *file)
{
return false;
}
-static inline int security_vm_enough_memory_mm(struct mm_struct *, long)
+static inline int security_vm_enough_memory_mm(struct mm_struct *mm, long pages)
{
return 0;
}
-static inline bool may_expand_vm(struct mm_struct *, vm_flags_t, unsigned long)
+static inline bool may_expand_vm(struct mm_struct *mm, vm_flags_t flags,
+ unsigned long npages)
{
return true;
}
@@ -1169,7 +1062,7 @@ static inline void vm_flags_clear(struct vm_area_struct *vma,
vma->__vm_flags &= ~flags;
}
-static inline int shmem_zero_setup(struct vm_area_struct *)
+static inline int shmem_zero_setup(struct vm_area_struct *vma)
{
return 0;
}
@@ -1179,20 +1072,20 @@ static inline void vma_set_anonymous(struct vm_area_struct *vma)
vma->vm_ops = NULL;
}
-static inline void ksm_add_vma(struct vm_area_struct *)
+static inline void ksm_add_vma(struct vm_area_struct *vma)
{
}
-static inline void perf_event_mmap(struct vm_area_struct *)
+static inline void perf_event_mmap(struct vm_area_struct *vma)
{
}
-static inline bool vma_is_dax(struct vm_area_struct *)
+static inline bool vma_is_dax(struct vm_area_struct *vma)
{
return false;
}
-static inline struct vm_area_struct *get_gate_vma(struct mm_struct *)
+static inline struct vm_area_struct *get_gate_vma(struct mm_struct *mm)
{
return NULL;
}
@@ -1217,16 +1110,16 @@ static inline void vma_set_page_prot(struct vm_area_struct *vma)
WRITE_ONCE(vma->vm_page_prot, vm_page_prot);
}
-static inline bool arch_validate_flags(vm_flags_t)
+static inline bool arch_validate_flags(vm_flags_t flags)
{
return true;
}
-static inline void vma_close(struct vm_area_struct *)
+static inline void vma_close(struct vm_area_struct *vma)
{
}
-static inline int mmap_file(struct file *, struct vm_area_struct *)
+static inline int mmap_file(struct file *file, struct vm_area_struct *vma)
{
return 0;
}
@@ -1282,8 +1175,8 @@ static inline bool capable(int cap)
return true;
}
-static inline bool mlock_future_ok(struct mm_struct *mm, vm_flags_t vm_flags,
- unsigned long bytes)
+static inline bool mlock_future_ok(const struct mm_struct *mm,
+ vm_flags_t vm_flags, unsigned long bytes)
{
unsigned long locked_pages, limit_pages;
@@ -1325,6 +1218,13 @@ static inline void userfaultfd_unmap_complete(struct mm_struct *mm,
{
}
+# define ACCESS_PRIVATE(p, member) ((p)->member)
+
+static inline bool mm_flags_test(int flag, const struct mm_struct *mm)
+{
+ return test_bit(flag, ACCESS_PRIVATE(&mm->flags, __mm_flags));
+}
+
/*
* Denies creating a writable executable mapping or gaining executable permissions.
*
@@ -1355,7 +1255,7 @@ static inline void userfaultfd_unmap_complete(struct mm_struct *mm,
static inline bool map_deny_write_exec(unsigned long old, unsigned long new)
{
/* If MDWE is disabled, we have nothing to deny. */
- if (!test_bit(MMF_HAS_MDWE, &current->mm->flags))
+ if (mm_flags_test(MMF_HAS_MDWE, current->mm))
return false;
/* If the new VMA is not executable, we have nothing to deny. */
@@ -1375,21 +1275,12 @@ static inline bool map_deny_write_exec(unsigned long old, unsigned long new)
static inline int mapping_map_writable(struct address_space *mapping)
{
- int c = atomic_read(&mapping->i_mmap_writable);
-
- /* Derived from the raw_atomic_inc_unless_negative() implementation. */
- do {
- if (c < 0)
- return -EPERM;
- } while (!__sync_bool_compare_and_swap(&mapping->i_mmap_writable, c, c+1));
-
- return 0;
+ return atomic_inc_unless_negative(&mapping->i_mmap_writable) ?
+ 0 : -EPERM;
}
static inline unsigned long move_page_tables(struct pagetable_move_control *pmc)
{
- (void)pmc;
-
return 0;
}
@@ -1397,67 +1288,61 @@ static inline void free_pgd_range(struct mmu_gather *tlb,
unsigned long addr, unsigned long end,
unsigned long floor, unsigned long ceiling)
{
- (void)tlb;
- (void)addr;
- (void)end;
- (void)floor;
- (void)ceiling;
}
static inline int ksm_execve(struct mm_struct *mm)
{
- (void)mm;
-
return 0;
}
static inline void ksm_exit(struct mm_struct *mm)
{
- (void)mm;
}
static inline void vma_lock_init(struct vm_area_struct *vma, bool reset_refcnt)
{
- (void)vma;
- (void)reset_refcnt;
+ if (reset_refcnt)
+ refcount_set(&vma->vm_refcnt, 0);
}
static inline void vma_numab_state_init(struct vm_area_struct *vma)
{
- (void)vma;
}
static inline void vma_numab_state_free(struct vm_area_struct *vma)
{
- (void)vma;
}
static inline void dup_anon_vma_name(struct vm_area_struct *orig_vma,
struct vm_area_struct *new_vma)
{
- (void)orig_vma;
- (void)new_vma;
}
static inline void free_anon_vma_name(struct vm_area_struct *vma)
{
- (void)vma;
}
/* Declared in vma.h. */
static inline void set_vma_from_desc(struct vm_area_struct *vma,
struct vm_area_desc *desc);
-static inline struct vm_area_desc *vma_to_desc(struct vm_area_struct *vma,
- struct vm_area_desc *desc);
-
-static int compat_vma_mmap_prepare(struct file *file,
- struct vm_area_struct *vma)
+static inline int __compat_vma_mmap_prepare(const struct file_operations *f_op,
+ struct file *file, struct vm_area_struct *vma)
{
- struct vm_area_desc desc;
+ struct vm_area_desc desc = {
+ .mm = vma->vm_mm,
+ .file = vma->vm_file,
+ .start = vma->vm_start,
+ .end = vma->vm_end,
+
+ .pgoff = vma->vm_pgoff,
+ .vm_file = vma->vm_file,
+ .vm_flags = vma->vm_flags,
+ .page_prot = vma->vm_page_prot,
+ };
int err;
- err = file->f_op->mmap_prepare(vma_to_desc(vma, &desc));
+ err = f_op->mmap_prepare(&desc);
if (err)
return err;
set_vma_from_desc(vma, &desc);
@@ -1465,6 +1350,12 @@ static int compat_vma_mmap_prepare(struct file *file,
return 0;
}
+static inline int compat_vma_mmap_prepare(struct file *file,
+ struct vm_area_struct *vma)
+{
+ return __compat_vma_mmap_prepare(file->f_op, file, vma);
+}
+
/* Did the driver provide valid mmap hook configuration? */
static inline bool can_mmap_file(struct file *file)
{
@@ -1495,7 +1386,6 @@ static inline int vfs_mmap_prepare(struct file *file, struct vm_area_desc *desc)
static inline void fixup_hugetlb_reservations(struct vm_area_struct *vma)
{
- (void)vma;
}
static inline void vma_set_file(struct vm_area_struct *vma, struct file *file)
@@ -1506,13 +1396,13 @@ static inline void vma_set_file(struct vm_area_struct *vma, struct file *file)
fput(file);
}
-static inline bool shmem_file(struct file *)
+static inline bool shmem_file(struct file *file)
{
return false;
}
-static inline vm_flags_t ksm_vma_flags(const struct mm_struct *, const struct file *,
- vm_flags_t vm_flags)
+static inline vm_flags_t ksm_vma_flags(const struct mm_struct *mm,
+ const struct file *file, vm_flags_t vm_flags)
{
return vm_flags;
}
diff --git a/tools/testing/vsock/util.c b/tools/testing/vsock/util.c
index 7b861a8e997a..d843643ced6b 100644
--- a/tools/testing/vsock/util.c
+++ b/tools/testing/vsock/util.c
@@ -756,7 +756,6 @@ void setsockopt_ull_check(int fd, int level, int optname,
fail:
fprintf(stderr, "%s val %llu\n", errmsg, val);
exit(EXIT_FAILURE);
-;
}
/* Set "int" socket option and check that it's indeed set */