summaryrefslogtreecommitdiff
path: root/tools/testing/selftests
diff options
context:
space:
mode:
Diffstat (limited to 'tools/testing/selftests')
-rw-r--r--tools/testing/selftests/.gitignore6
-rw-r--r--tools/testing/selftests/Makefile15
-rw-r--r--tools/testing/selftests/android/Makefile2
-rw-r--r--tools/testing/selftests/android/ion/.gitignore1
-rw-r--r--tools/testing/selftests/android/ion/Makefile2
-rw-r--r--tools/testing/selftests/arm64/signal/.gitignore1
-rw-r--r--tools/testing/selftests/arm64/tags/.gitignore1
-rw-r--r--tools/testing/selftests/bpf/.gitignore7
-rw-r--r--tools/testing/selftests/bpf/Makefile69
-rw-r--r--tools/testing/selftests/bpf/README.rst45
-rw-r--r--tools/testing/selftests/bpf/bench.c465
-rw-r--r--tools/testing/selftests/bpf/bench.h81
-rw-r--r--tools/testing/selftests/bpf/benchs/bench_count.c91
-rw-r--r--tools/testing/selftests/bpf/benchs/bench_rename.c195
-rw-r--r--tools/testing/selftests/bpf/benchs/bench_ringbufs.c566
-rw-r--r--tools/testing/selftests/bpf/benchs/bench_trigger.c167
-rwxr-xr-xtools/testing/selftests/bpf/benchs/run_bench_rename.sh9
-rwxr-xr-xtools/testing/selftests/bpf/benchs/run_bench_ringbufs.sh75
-rwxr-xr-xtools/testing/selftests/bpf/benchs/run_bench_trigger.sh9
-rw-r--r--tools/testing/selftests/bpf/bpf_tcp_helpers.h2
-rw-r--r--tools/testing/selftests/bpf/bpf_trace_helpers.h120
-rw-r--r--tools/testing/selftests/bpf/config4
-rw-r--r--tools/testing/selftests/bpf/include/uapi/linux/types.h23
-rw-r--r--tools/testing/selftests/bpf/map_tests/.gitignore1
-rw-r--r--tools/testing/selftests/bpf/network_helpers.c167
-rw-r--r--tools/testing/selftests/bpf/network_helpers.h42
-rw-r--r--tools/testing/selftests/bpf/prog_tests/.gitignore1
-rw-r--r--tools/testing/selftests/bpf/prog_tests/align.c (renamed from tools/testing/selftests/bpf/test_align.c)109
-rw-r--r--tools/testing/selftests/bpf/prog_tests/bpf_iter.c409
-rw-r--r--tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c110
-rw-r--r--tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c39
-rw-r--r--tools/testing/selftests/bpf/prog_tests/btf_dump.c2
-rw-r--r--tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c49
-rw-r--r--tools/testing/selftests/bpf/prog_tests/cgroup_attach_autodetach.c2
-rw-r--r--tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c2
-rw-r--r--tools/testing/selftests/bpf/prog_tests/cgroup_attach_override.c2
-rw-r--r--tools/testing/selftests/bpf/prog_tests/cgroup_link.c244
-rw-r--r--tools/testing/selftests/bpf/prog_tests/cgroup_skb_sk_lookup.c95
-rw-r--r--tools/testing/selftests/bpf/prog_tests/cls_redirect.c456
-rw-r--r--tools/testing/selftests/bpf/prog_tests/connect_force_port.c166
-rw-r--r--tools/testing/selftests/bpf/prog_tests/core_reloc.c2
-rw-r--r--tools/testing/selftests/bpf/prog_tests/enable_stats.c45
-rw-r--r--tools/testing/selftests/bpf/prog_tests/fentry_fexit.c12
-rw-r--r--tools/testing/selftests/bpf/prog_tests/fentry_test.c14
-rw-r--r--tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c31
-rw-r--r--tools/testing/selftests/bpf/prog_tests/fexit_test.c69
-rw-r--r--tools/testing/selftests/bpf/prog_tests/flow_dissector.c167
-rw-r--r--tools/testing/selftests/bpf/prog_tests/flow_dissector_load_bytes.c1
-rw-r--r--tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c588
-rw-r--r--tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c5
-rw-r--r--tools/testing/selftests/bpf/prog_tests/global_data.c1
-rw-r--r--tools/testing/selftests/bpf/prog_tests/global_data_init.c61
-rw-r--r--tools/testing/selftests/bpf/prog_tests/hashmap.c (renamed from tools/testing/selftests/bpf/test_hashmap.c)280
-rw-r--r--tools/testing/selftests/bpf/prog_tests/kfree_skb.c1
-rw-r--r--tools/testing/selftests/bpf/prog_tests/l4lb_all.c1
-rw-r--r--tools/testing/selftests/bpf/prog_tests/link_pinning.c105
-rw-r--r--tools/testing/selftests/bpf/prog_tests/map_lock.c14
-rw-r--r--tools/testing/selftests/bpf/prog_tests/mmap.c81
-rw-r--r--tools/testing/selftests/bpf/prog_tests/modify_return.c65
-rw-r--r--tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c85
-rw-r--r--tools/testing/selftests/bpf/prog_tests/perf_branches.c170
-rw-r--r--tools/testing/selftests/bpf/prog_tests/perf_buffer.c5
-rw-r--r--tools/testing/selftests/bpf/prog_tests/pkt_access.c1
-rw-r--r--tools/testing/selftests/bpf/prog_tests/pkt_md_access.c1
-rw-r--r--tools/testing/selftests/bpf/prog_tests/prog_run_xattr.c1
-rw-r--r--tools/testing/selftests/bpf/prog_tests/queue_stack_map.c1
-rw-r--r--tools/testing/selftests/bpf/prog_tests/ringbuf.c211
-rw-r--r--tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c102
-rw-r--r--tools/testing/selftests/bpf/prog_tests/section_names.c42
-rw-r--r--tools/testing/selftests/bpf/prog_tests/select_reuseport.c73
-rw-r--r--tools/testing/selftests/bpf/prog_tests/signal_pending.c1
-rw-r--r--tools/testing/selftests/bpf/prog_tests/sk_assign.c328
-rw-r--r--tools/testing/selftests/bpf/prog_tests/skb_ctx.c2
-rw-r--r--tools/testing/selftests/bpf/prog_tests/skb_helpers.c30
-rw-r--r--tools/testing/selftests/bpf/prog_tests/sockmap_basic.c35
-rw-r--r--tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c124
-rw-r--r--tools/testing/selftests/bpf/prog_tests/sockmap_listen.c1635
-rw-r--r--tools/testing/selftests/bpf/prog_tests/spinlock.c14
-rw-r--r--tools/testing/selftests/bpf/prog_tests/tcp_rtt.c110
-rw-r--r--tools/testing/selftests/bpf/prog_tests/test_lsm.c86
-rw-r--r--tools/testing/selftests/bpf/prog_tests/test_overhead.c14
-rw-r--r--tools/testing/selftests/bpf/prog_tests/trampoline_count.c25
-rw-r--r--tools/testing/selftests/bpf/prog_tests/vmlinux.c43
-rw-r--r--tools/testing/selftests/bpf/prog_tests/xdp.c1
-rw-r--r--tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c124
-rw-r--r--tools/testing/selftests/bpf/prog_tests/xdp_attach.c90
-rw-r--r--tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c70
-rw-r--r--tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c97
-rw-r--r--tools/testing/selftests/bpf/prog_tests/xdp_info.c68
-rw-r--r--tools/testing/selftests/bpf/prog_tests/xdp_noinline.c1
-rw-r--r--tools/testing/selftests/bpf/progs/bpf_dctcp.c18
-rw-r--r--tools/testing/selftests/bpf/progs/bpf_flow.c20
-rw-r--r--tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c44
-rw-r--r--tools/testing/selftests/bpf/progs/bpf_iter_ipv6_route.c78
-rw-r--r--tools/testing/selftests/bpf/progs/bpf_iter_netlink.c82
-rw-r--r--tools/testing/selftests/bpf/progs/bpf_iter_task.c41
-rw-r--r--tools/testing/selftests/bpf/progs/bpf_iter_task_file.c44
-rw-r--r--tools/testing/selftests/bpf/progs/bpf_iter_test_kern1.c4
-rw-r--r--tools/testing/selftests/bpf/progs/bpf_iter_test_kern2.c4
-rw-r--r--tools/testing/selftests/bpf/progs/bpf_iter_test_kern3.c33
-rw-r--r--tools/testing/selftests/bpf/progs/bpf_iter_test_kern4.c67
-rw-r--r--tools/testing/selftests/bpf/progs/bpf_iter_test_kern_common.h38
-rw-r--r--tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c2
-rw-r--r--tools/testing/selftests/bpf/progs/cgroup_skb_sk_lookup_kern.c97
-rw-r--r--tools/testing/selftests/bpf/progs/connect4_prog.c107
-rw-r--r--tools/testing/selftests/bpf/progs/connect_force_port4.c83
-rw-r--r--tools/testing/selftests/bpf/progs/connect_force_port6.c94
-rw-r--r--tools/testing/selftests/bpf/progs/core_reloc_types.h2
-rw-r--r--tools/testing/selftests/bpf/progs/fentry_test.c2
-rw-r--r--tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c2
-rw-r--r--tools/testing/selftests/bpf/progs/fexit_bpf2bpf_simple.c2
-rw-r--r--tools/testing/selftests/bpf/progs/fexit_test.c2
-rw-r--r--tools/testing/selftests/bpf/progs/freplace_connect4.c18
-rw-r--r--tools/testing/selftests/bpf/progs/kfree_skb.c2
-rw-r--r--tools/testing/selftests/bpf/progs/lsm.c48
-rw-r--r--tools/testing/selftests/bpf/progs/modify_return.c49
-rw-r--r--tools/testing/selftests/bpf/progs/perfbuf_bench.c33
-rw-r--r--tools/testing/selftests/bpf/progs/ringbuf_bench.c60
-rw-r--r--tools/testing/selftests/bpf/progs/sockmap_parse_prog.c1
-rw-r--r--tools/testing/selftests/bpf/progs/test_attach_probe.c3
-rw-r--r--tools/testing/selftests/bpf/progs/test_btf_haskv.c18
-rw-r--r--tools/testing/selftests/bpf/progs/test_btf_map_in_map.c76
-rw-r--r--tools/testing/selftests/bpf/progs/test_btf_newkv.c18
-rw-r--r--tools/testing/selftests/bpf/progs/test_btf_nokv.c18
-rw-r--r--tools/testing/selftests/bpf/progs/test_cgroup_link.c24
-rw-r--r--tools/testing/selftests/bpf/progs/test_cls_redirect.c1061
-rw-r--r--tools/testing/selftests/bpf/progs/test_cls_redirect.h54
-rw-r--r--tools/testing/selftests/bpf/progs/test_enable_stats.c18
-rw-r--r--tools/testing/selftests/bpf/progs/test_get_stack_rawtp_err.c26
-rw-r--r--tools/testing/selftests/bpf/progs/test_global_data.c2
-rw-r--r--tools/testing/selftests/bpf/progs/test_link_pinning.c25
-rw-r--r--tools/testing/selftests/bpf/progs/test_mmap.c8
-rw-r--r--tools/testing/selftests/bpf/progs/test_ns_current_pid_tgid.c37
-rw-r--r--tools/testing/selftests/bpf/progs/test_obj_id.c14
-rw-r--r--tools/testing/selftests/bpf/progs/test_overhead.c15
-rw-r--r--tools/testing/selftests/bpf/progs/test_perf_branches.c50
-rw-r--r--tools/testing/selftests/bpf/progs/test_perf_buffer.c2
-rw-r--r--tools/testing/selftests/bpf/progs/test_probe_user.c1
-rw-r--r--tools/testing/selftests/bpf/progs/test_ringbuf.c78
-rw-r--r--tools/testing/selftests/bpf/progs/test_ringbuf_multi.c77
-rw-r--r--tools/testing/selftests/bpf/progs/test_sk_assign.c186
-rw-r--r--tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c1
-rw-r--r--tools/testing/selftests/bpf/progs/test_skb_ctx.c2
-rw-r--r--tools/testing/selftests/bpf/progs/test_skb_helpers.c28
-rw-r--r--tools/testing/selftests/bpf/progs/test_skmsg_load_helpers.c47
-rw-r--r--tools/testing/selftests/bpf/progs/test_sockmap_kern.h (renamed from tools/testing/selftests/bpf/test_sockmap_kern.h)204
-rw-r--r--tools/testing/selftests/bpf/progs/test_sockmap_listen.c98
-rw-r--r--tools/testing/selftests/bpf/progs/test_sysctl_prog.c2
-rw-r--r--tools/testing/selftests/bpf/progs/test_trampoline_count.c3
-rw-r--r--tools/testing/selftests/bpf/progs/test_vmlinux.c84
-rw-r--r--tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c33
-rw-r--r--tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_shrink.c (renamed from tools/testing/selftests/bpf/progs/test_adjust_tail.c)12
-rw-r--r--tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c30
-rw-r--r--tools/testing/selftests/bpf/progs/test_xdp_devmap_helpers.c22
-rw-r--r--tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c44
-rw-r--r--tools/testing/selftests/bpf/progs/trigger_bench.c47
-rw-r--r--tools/testing/selftests/bpf/test_bpftool.py178
-rwxr-xr-xtools/testing/selftests/bpf/test_bpftool.sh5
-rw-r--r--tools/testing/selftests/bpf/test_btf.c2
-rw-r--r--tools/testing/selftests/bpf/test_current_pid_tgid_new_ns.c159
-rw-r--r--tools/testing/selftests/bpf/test_maps.c58
-rw-r--r--tools/testing/selftests/bpf/test_progs.c206
-rw-r--r--tools/testing/selftests/bpf/test_progs.h38
-rw-r--r--tools/testing/selftests/bpf/test_sock_addr.c38
-rw-r--r--tools/testing/selftests/bpf/test_sockmap.c1060
-rw-r--r--tools/testing/selftests/bpf/test_verifier.c63
-rw-r--r--tools/testing/selftests/bpf/testing_helpers.c66
-rw-r--r--tools/testing/selftests/bpf/testing_helpers.h5
-rw-r--r--tools/testing/selftests/bpf/trace_helpers.c23
-rw-r--r--tools/testing/selftests/bpf/trace_helpers.h1
-rw-r--r--tools/testing/selftests/bpf/verifier/.gitignore1
-rw-r--r--tools/testing/selftests/bpf/verifier/and.c4
-rw-r--r--tools/testing/selftests/bpf/verifier/array_access.c4
-rw-r--r--tools/testing/selftests/bpf/verifier/bounds.c105
-rw-r--r--tools/testing/selftests/bpf/verifier/bpf_get_stack.c8
-rw-r--r--tools/testing/selftests/bpf/verifier/calls.c18
-rw-r--r--tools/testing/selftests/bpf/verifier/const_or.c8
-rw-r--r--tools/testing/selftests/bpf/verifier/ctx.c105
-rw-r--r--tools/testing/selftests/bpf/verifier/ctx_skb.c47
-rw-r--r--tools/testing/selftests/bpf/verifier/dead_code.c10
-rw-r--r--tools/testing/selftests/bpf/verifier/direct_value_access.c4
-rw-r--r--tools/testing/selftests/bpf/verifier/event_output.c24
-rw-r--r--tools/testing/selftests/bpf/verifier/helper_access_var_len.c46
-rw-r--r--tools/testing/selftests/bpf/verifier/helper_value_access.c42
-rw-r--r--tools/testing/selftests/bpf/verifier/precise.c8
-rw-r--r--tools/testing/selftests/bpf/verifier/prevent_map_lookup.c30
-rw-r--r--tools/testing/selftests/bpf/verifier/ref_tracking.c33
-rw-r--r--tools/testing/selftests/bpf/verifier/sock.c117
-rw-r--r--tools/testing/selftests/bpf/verifier/stack_ptr.c40
-rw-r--r--tools/testing/selftests/bpf/verifier/value_illegal_alu.c1
-rw-r--r--tools/testing/selftests/bpf/verifier/value_or_null.c19
-rw-r--r--tools/testing/selftests/bpf/verifier/value_ptr_arith.c8
-rw-r--r--tools/testing/selftests/breakpoints/.gitignore1
-rw-r--r--tools/testing/selftests/capabilities/.gitignore1
-rw-r--r--tools/testing/selftests/cgroup/.gitignore1
-rw-r--r--tools/testing/selftests/cgroup/Makefile6
-rw-r--r--tools/testing/selftests/cgroup/cgroup_util.c126
-rw-r--r--tools/testing/selftests/cgroup/cgroup_util.h4
-rw-r--r--tools/testing/selftests/cgroup/test_core.c177
-rw-r--r--tools/testing/selftests/clone3/.gitignore1
-rw-r--r--tools/testing/selftests/clone3/clone3_selftests.h19
-rw-r--r--tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c1
-rw-r--r--tools/testing/selftests/drivers/.gitignore1
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/blackhole_routes.sh5
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/devlink_trap_acl_drops.sh151
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/devlink_trap_control.sh688
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/devlink_trap_l2_drops.sh47
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh68
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_exceptions.sh20
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/devlink_trap_policer.sh384
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh6
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan.sh11
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/extack.sh45
-rw-r--r--tools/testing/selftests/drivers/net/mlxsw/mlxsw_lib.sh13
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/qos_defprio.sh18
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/qos_dscp_router.sh30
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh2
-rw-r--r--tools/testing/selftests/drivers/net/mlxsw/router_scale.sh53
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh68
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/sch_ets.sh14
-rw-r--r--tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh533
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh94
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/sch_red_prio.sh5
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/sch_red_root.sh68
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/sharedbuffer.sh222
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/sharedbuffer_configuration.py416
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh5
-rw-r--r--tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower_scale.sh4
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/tc_action_hw_stats.sh130
-rw-r--r--tools/testing/selftests/drivers/net/mlxsw/tc_flower_scale.sh31
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/tc_restrictions.sh318
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/vxlan.sh229
-rwxr-xr-xtools/testing/selftests/drivers/net/netdevsim/devlink.sh43
-rwxr-xr-xtools/testing/selftests/drivers/net/netdevsim/devlink_trap.sh125
-rw-r--r--tools/testing/selftests/efivarfs/.gitignore1
-rw-r--r--tools/testing/selftests/exec/.gitignore2
-rw-r--r--tools/testing/selftests/exec/Makefile3
-rwxr-xr-xtools/testing/selftests/exec/binfmt_script171
-rw-r--r--tools/testing/selftests/exec/execveat.c8
-rw-r--r--tools/testing/selftests/filesystems/.gitignore1
-rw-r--r--tools/testing/selftests/filesystems/binderfs/.gitignore1
-rw-r--r--tools/testing/selftests/filesystems/binderfs/Makefile4
-rw-r--r--tools/testing/selftests/filesystems/binderfs/binderfs_test.c498
-rw-r--r--tools/testing/selftests/filesystems/epoll/.gitignore1
-rw-r--r--tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c213
-rw-r--r--tools/testing/selftests/firmware/Makefile9
-rwxr-xr-xtools/testing/selftests/firmware/fw_filesystem.sh23
-rw-r--r--tools/testing/selftests/firmware/fw_namespace.c151
-rwxr-xr-xtools/testing/selftests/firmware/fw_run_tests.sh4
-rw-r--r--tools/testing/selftests/ftrace/.gitignore1
-rw-r--r--tools/testing/selftests/ftrace/config1
-rwxr-xr-xtools/testing/selftests/ftrace/ftracetest32
-rw-r--r--tools/testing/selftests/ftrace/test.d/event/event-no-pid.tc125
-rw-r--r--tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter-stack.tc5
-rw-r--r--tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter.tc2
-rw-r--r--tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc2
-rw-r--r--tools/testing/selftests/ftrace/test.d/ftrace/func-filter-notrace-pid.tc105
-rw-r--r--tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc5
-rw-r--r--tools/testing/selftests/ftrace/test.d/ftrace/func-filter-stacktrace.tc2
-rw-r--r--tools/testing/selftests/ftrace/test.d/ftrace/func_event_triggers.tc5
-rw-r--r--tools/testing/selftests/ftrace/test.d/ftrace/func_mod_trace.tc2
-rw-r--r--tools/testing/selftests/ftrace/test.d/ftrace/func_profiler.tc5
-rw-r--r--tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc5
-rw-r--r--tools/testing/selftests/ftrace/test.d/ftrace/func_stack_tracer.tc2
-rw-r--r--tools/testing/selftests/ftrace/test.d/ftrace/func_traceonoff_triggers.tc7
-rw-r--r--tools/testing/selftests/ftrace/test.d/ftrace/tracing-error-log.tc2
-rw-r--r--tools/testing/selftests/ftrace/test.d/functions14
-rw-r--r--tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc2
-rw-r--r--tools/testing/selftests/ftrace/test.d/kprobe/kprobe_ftrace.tc2
-rw-r--r--tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc4
-rw-r--r--tools/testing/selftests/ftrace/test.d/preemptirq/irqsoff_tracer.tc9
-rw-r--r--tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-field-variable-support.tc5
-rw-r--r--tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-inter-event-combined-hist.tc5
-rw-r--r--tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-multi-actions-accept.tc5
-rw-r--r--tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmatch-action-hist.tc5
-rw-r--r--tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmatch-onmax-action-hist.tc5
-rw-r--r--tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmax-action-hist.tc5
-rw-r--r--tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-snapshot-action-hist.tc5
-rw-r--r--tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-trace-action-hist.tc5
-rw-r--r--tools/testing/selftests/ftrace/test.d/trigger/trigger-multihist.tc2
-rw-r--r--tools/testing/selftests/futex/functional/.gitignore1
-rwxr-xr-xtools/testing/selftests/gen_kselftest_tar.sh5
-rw-r--r--tools/testing/selftests/gpio/.gitignore1
-rw-r--r--tools/testing/selftests/gpio/Makefile12
-rw-r--r--tools/testing/selftests/ia64/.gitignore1
-rw-r--r--tools/testing/selftests/intel_pstate/.gitignore1
-rw-r--r--tools/testing/selftests/intel_pstate/Makefile2
-rw-r--r--tools/testing/selftests/ipc/.gitignore1
-rw-r--r--tools/testing/selftests/ipc/msgque.c2
-rw-r--r--tools/testing/selftests/ir/.gitignore1
-rw-r--r--tools/testing/selftests/kcmp/.gitignore1
-rwxr-xr-xtools/testing/selftests/kmod/kmod.sh43
-rw-r--r--tools/testing/selftests/kselftest/runner.sh2
-rwxr-xr-xtools/testing/selftests/kselftest_deps.sh272
-rw-r--r--tools/testing/selftests/kselftest_harness.h376
-rw-r--r--tools/testing/selftests/kvm/.gitignore9
-rw-r--r--tools/testing/selftests/kvm/Makefile45
-rw-r--r--tools/testing/selftests/kvm/clear_dirty_log_test.c4
-rw-r--r--tools/testing/selftests/kvm/demand_paging_test.c661
-rw-r--r--tools/testing/selftests/kvm/dirty_log_test.c107
-rw-r--r--tools/testing/selftests/kvm/include/evmcs.h6
-rw-r--r--tools/testing/selftests/kvm/include/kvm_util.h158
-rw-r--r--tools/testing/selftests/kvm/include/test_util.h28
-rw-r--r--tools/testing/selftests/kvm/include/x86_64/processor.h11
-rw-r--r--tools/testing/selftests/kvm/include/x86_64/svm_util.h10
-rw-r--r--tools/testing/selftests/kvm/include/x86_64/vmx.h27
-rw-r--r--tools/testing/selftests/kvm/kvm_create_max_vcpus.c8
-rw-r--r--tools/testing/selftests/kvm/lib/aarch64/processor.c41
-rw-r--r--tools/testing/selftests/kvm/lib/aarch64/ucall.c2
-rw-r--r--tools/testing/selftests/kvm/lib/assert.c6
-rw-r--r--tools/testing/selftests/kvm/lib/io.c12
-rw-r--r--tools/testing/selftests/kvm/lib/kvm_util.c331
-rw-r--r--tools/testing/selftests/kvm/lib/kvm_util_internal.h67
-rw-r--r--tools/testing/selftests/kvm/lib/s390x/processor.c83
-rw-r--r--tools/testing/selftests/kvm/lib/test_util.c93
-rw-r--r--tools/testing/selftests/kvm/lib/x86_64/processor.c201
-rw-r--r--tools/testing/selftests/kvm/lib/x86_64/svm.c2
-rw-r--r--tools/testing/selftests/kvm/lib/x86_64/vmx.c7
-rw-r--r--tools/testing/selftests/kvm/s390x/memop.c2
-rw-r--r--tools/testing/selftests/kvm/s390x/resets.c138
-rw-r--r--tools/testing/selftests/kvm/s390x/sync_regs_test.c13
-rw-r--r--tools/testing/selftests/kvm/set_memory_region_test.c408
-rw-r--r--tools/testing/selftests/kvm/steal_time.c352
-rw-r--r--tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c6
-rw-r--r--tools/testing/selftests/kvm/x86_64/debug_regs.c202
-rw-r--r--tools/testing/selftests/kvm/x86_64/evmcs_test.c35
-rw-r--r--tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c109
-rw-r--r--tools/testing/selftests/kvm/x86_64/mmio_warning_test.c6
-rw-r--r--tools/testing/selftests/kvm/x86_64/platform_info_test.c6
-rw-r--r--tools/testing/selftests/kvm/x86_64/smm_test.c21
-rw-r--r--tools/testing/selftests/kvm/x86_64/state_test.c72
-rw-r--r--tools/testing/selftests/kvm/x86_64/svm_vmcall_test.c6
-rw-r--r--tools/testing/selftests/kvm/x86_64/sync_regs_test.c4
-rw-r--r--tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c4
-rw-r--r--tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c17
-rw-r--r--tools/testing/selftests/kvm/x86_64/vmx_preemption_timer_test.c255
-rw-r--r--tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c4
-rw-r--r--tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c8
-rw-r--r--tools/testing/selftests/kvm/x86_64/xss_msr_test.c2
-rw-r--r--tools/testing/selftests/lib.mk3
-rw-r--r--tools/testing/selftests/lib/config1
-rwxr-xr-xtools/testing/selftests/lkdtm/run.sh22
-rw-r--r--tools/testing/selftests/media_tests/.gitignore1
-rw-r--r--tools/testing/selftests/membarrier/.gitignore1
-rw-r--r--tools/testing/selftests/memfd/.gitignore1
-rw-r--r--tools/testing/selftests/memfd/Makefile22
-rw-r--r--tools/testing/selftests/mount/.gitignore1
-rw-r--r--tools/testing/selftests/mqueue/.gitignore1
-rw-r--r--tools/testing/selftests/net/.gitignore6
-rw-r--r--tools/testing/selftests/net/Makefile5
-rw-r--r--tools/testing/selftests/net/config2
-rwxr-xr-xtools/testing/selftests/net/fib_nexthops.sh593
-rwxr-xr-xtools/testing/selftests/net/fib_tests.sh10
-rw-r--r--tools/testing/selftests/net/forwarding/.gitignore1
-rw-r--r--tools/testing/selftests/net/forwarding/devlink_lib.sh104
-rw-r--r--tools/testing/selftests/net/forwarding/lib.sh88
-rw-r--r--tools/testing/selftests/net/forwarding/mirror_lib.sh6
-rwxr-xr-xtools/testing/selftests/net/forwarding/pedit_dsfield.sh309
-rwxr-xr-xtools/testing/selftests/net/forwarding/sch_ets.sh9
-rw-r--r--tools/testing/selftests/net/forwarding/sch_ets_tests.sh10
-rwxr-xr-xtools/testing/selftests/net/forwarding/skbedit_priority.sh168
-rwxr-xr-xtools/testing/selftests/net/forwarding/tc_actions.sh26
-rw-r--r--tools/testing/selftests/net/forwarding/tc_common.sh32
-rw-r--r--tools/testing/selftests/net/hwtstamp_config.c (renamed from tools/testing/selftests/networking/timestamping/hwtstamp_config.c)0
-rw-r--r--tools/testing/selftests/net/ip_defrag.c8
-rw-r--r--tools/testing/selftests/net/mptcp/.gitignore2
-rw-r--r--tools/testing/selftests/net/mptcp/Makefile7
-rw-r--r--tools/testing/selftests/net/mptcp/mptcp_connect.c71
-rwxr-xr-xtools/testing/selftests/net/mptcp/mptcp_connect.sh24
-rwxr-xr-xtools/testing/selftests/net/mptcp/mptcp_join.sh357
-rwxr-xr-xtools/testing/selftests/net/mptcp/pm_netlink.sh130
-rw-r--r--tools/testing/selftests/net/mptcp/pm_nl_ctl.c616
-rwxr-xr-xtools/testing/selftests/net/pmtu.sh122
-rw-r--r--tools/testing/selftests/net/reuseaddr_ports_exhausted.c162
-rwxr-xr-xtools/testing/selftests/net/reuseaddr_ports_exhausted.sh35
-rw-r--r--tools/testing/selftests/net/rxtimestamp.c (renamed from tools/testing/selftests/networking/timestamping/rxtimestamp.c)0
-rw-r--r--tools/testing/selftests/net/tcp_mmap.c7
-rw-r--r--tools/testing/selftests/net/timestamping.c (renamed from tools/testing/selftests/networking/timestamping/timestamping.c)0
-rw-r--r--tools/testing/selftests/net/tls.c93
-rw-r--r--tools/testing/selftests/net/txtimestamp.c (renamed from tools/testing/selftests/networking/timestamping/txtimestamp.c)179
-rwxr-xr-xtools/testing/selftests/net/txtimestamp.sh (renamed from tools/testing/selftests/networking/timestamping/txtimestamp.sh)33
-rwxr-xr-xtools/testing/selftests/net/vrf-xfrm-tests.sh436
-rw-r--r--tools/testing/selftests/networking/timestamping/.gitignore4
-rw-r--r--tools/testing/selftests/networking/timestamping/Makefile11
-rw-r--r--tools/testing/selftests/networking/timestamping/config2
-rw-r--r--tools/testing/selftests/nsfs/.gitignore1
-rw-r--r--tools/testing/selftests/nsfs/pidns.c2
-rwxr-xr-xtools/testing/selftests/ntb/ntb_test.sh2
-rw-r--r--tools/testing/selftests/openat2/.gitignore1
-rw-r--r--tools/testing/selftests/pid_namespace/.gitignore1
-rw-r--r--tools/testing/selftests/pid_namespace/Makefile8
-rw-r--r--tools/testing/selftests/pid_namespace/config2
-rw-r--r--tools/testing/selftests/pid_namespace/regression_enomem.c45
-rw-r--r--tools/testing/selftests/pidfd/.gitignore2
-rw-r--r--tools/testing/selftests/pidfd/Makefile3
-rw-r--r--tools/testing/selftests/pidfd/config6
-rw-r--r--tools/testing/selftests/pidfd/pidfd.h2
-rw-r--r--tools/testing/selftests/pidfd/pidfd_setns_test.c473
-rw-r--r--tools/testing/selftests/powerpc/Makefile1
-rw-r--r--tools/testing/selftests/powerpc/alignment/.gitignore1
-rw-r--r--tools/testing/selftests/powerpc/benchmarks/.gitignore1
-rw-r--r--tools/testing/selftests/powerpc/benchmarks/Makefile2
-rw-r--r--tools/testing/selftests/powerpc/benchmarks/settings1
-rw-r--r--tools/testing/selftests/powerpc/cache_shape/.gitignore1
-rw-r--r--tools/testing/selftests/powerpc/copyloops/.gitignore1
-rw-r--r--tools/testing/selftests/powerpc/dscr/.gitignore1
-rw-r--r--tools/testing/selftests/powerpc/dscr/Makefile2
-rw-r--r--tools/testing/selftests/powerpc/dscr/settings1
-rwxr-xr-xtools/testing/selftests/powerpc/eeh/eeh-basic.sh5
-rw-r--r--tools/testing/selftests/powerpc/math/.gitignore1
-rw-r--r--tools/testing/selftests/powerpc/mm/.gitignore2
-rw-r--r--tools/testing/selftests/powerpc/nx-gzip/99-nx-gzip.rules1
-rw-r--r--tools/testing/selftests/powerpc/nx-gzip/Makefile8
-rw-r--r--tools/testing/selftests/powerpc/nx-gzip/README45
-rw-r--r--tools/testing/selftests/powerpc/nx-gzip/gunz_test.c1028
-rw-r--r--tools/testing/selftests/powerpc/nx-gzip/gzfht_test.c433
-rw-r--r--tools/testing/selftests/powerpc/nx-gzip/gzip_vas.c316
-rw-r--r--tools/testing/selftests/powerpc/nx-gzip/include/copy-paste.h56
-rw-r--r--tools/testing/selftests/powerpc/nx-gzip/include/crb.h155
-rw-r--r--tools/testing/selftests/powerpc/nx-gzip/include/nx.h38
-rw-r--r--tools/testing/selftests/powerpc/nx-gzip/include/nx_dbg.h95
-rw-r--r--tools/testing/selftests/powerpc/nx-gzip/include/nxu.h650
l---------tools/testing/selftests/powerpc/nx-gzip/include/vas-api.h1
-rwxr-xr-xtools/testing/selftests/powerpc/nx-gzip/nx-gzip-test.sh46
-rw-r--r--tools/testing/selftests/powerpc/pmu/.gitignore2
-rw-r--r--tools/testing/selftests/powerpc/pmu/Makefile8
-rw-r--r--tools/testing/selftests/powerpc/pmu/count_stcx_fail.c161
-rw-r--r--tools/testing/selftests/powerpc/pmu/ebb/.gitignore1
-rw-r--r--tools/testing/selftests/powerpc/pmu/ebb/Makefile1
-rw-r--r--tools/testing/selftests/powerpc/pmu/ebb/trace.h4
-rw-r--r--tools/testing/selftests/powerpc/pmu/loop.S35
-rw-r--r--tools/testing/selftests/powerpc/primitives/.gitignore1
-rw-r--r--tools/testing/selftests/powerpc/ptrace/.gitignore1
-rw-r--r--tools/testing/selftests/powerpc/security/.gitignore1
-rw-r--r--tools/testing/selftests/powerpc/signal/.gitignore2
-rw-r--r--tools/testing/selftests/powerpc/signal/Makefile4
-rw-r--r--tools/testing/selftests/powerpc/signal/settings1
-rw-r--r--tools/testing/selftests/powerpc/signal/sig_sc_double_restart.c174
-rw-r--r--tools/testing/selftests/powerpc/signal/sigreturn_vdso.c127
-rw-r--r--tools/testing/selftests/powerpc/stringloops/.gitignore1
-rw-r--r--tools/testing/selftests/powerpc/switch_endian/.gitignore1
-rw-r--r--tools/testing/selftests/powerpc/syscalls/.gitignore1
-rw-r--r--tools/testing/selftests/powerpc/tm/.gitignore2
-rw-r--r--tools/testing/selftests/powerpc/tm/Makefile6
-rw-r--r--tools/testing/selftests/powerpc/tm/settings1
-rw-r--r--tools/testing/selftests/powerpc/tm/tm-signal-context-force-tm.c74
-rw-r--r--tools/testing/selftests/powerpc/tm/tm-signal-pagefault.c284
-rw-r--r--tools/testing/selftests/powerpc/vphn/.gitignore1
-rw-r--r--tools/testing/selftests/prctl/.gitignore1
-rw-r--r--tools/testing/selftests/proc/.gitignore3
-rw-r--r--tools/testing/selftests/proc/Makefile2
-rw-r--r--tools/testing/selftests/proc/proc-fsconfig-hidepid.c50
-rw-r--r--tools/testing/selftests/proc/proc-multiple-procfs.c48
-rw-r--r--tools/testing/selftests/pstore/.gitignore1
-rwxr-xr-xtools/testing/selftests/pstore/pstore_tests2
-rw-r--r--tools/testing/selftests/ptp/.gitignore1
-rw-r--r--tools/testing/selftests/ptp/testptp.c6
-rw-r--r--tools/testing/selftests/ptrace/.gitignore1
-rw-r--r--tools/testing/selftests/ptrace/Makefile4
-rw-r--r--tools/testing/selftests/ptrace/vmaccess.c86
-rw-r--r--tools/testing/selftests/rcutorture/.gitignore1
-rw-r--r--tools/testing/selftests/rcutorture/bin/functions.sh2
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kcsan-collapse.sh22
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm-find-errors.sh2
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh16
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm-recheck.sh26
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh52
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm.sh13
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/CFLIST3
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/CFcommon2
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/RUDE0110
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/RUDE01.boot1
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/TRACE0111
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/TRACE01.boot1
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/TRACE0211
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/TRACE02.boot1
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/TREE1018
-rw-r--r--tools/testing/selftests/rcutorture/formal/srcu-cbmc/.gitignore1
-rw-r--r--tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/.gitignore1
-rw-r--r--tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/.gitignore1
-rw-r--r--tools/testing/selftests/resctrl/Makefile17
-rw-r--r--tools/testing/selftests/resctrl/README53
-rw-r--r--tools/testing/selftests/resctrl/cache.c272
-rw-r--r--tools/testing/selftests/resctrl/cat_test.c250
-rw-r--r--tools/testing/selftests/resctrl/cqm_test.c176
-rw-r--r--tools/testing/selftests/resctrl/fill_buf.c213
-rw-r--r--tools/testing/selftests/resctrl/mba_test.c171
-rw-r--r--tools/testing/selftests/resctrl/mbm_test.c145
-rw-r--r--tools/testing/selftests/resctrl/resctrl.h107
-rw-r--r--tools/testing/selftests/resctrl/resctrl_tests.c202
-rw-r--r--tools/testing/selftests/resctrl/resctrl_val.c744
-rw-r--r--tools/testing/selftests/resctrl/resctrlfs.c722
-rw-r--r--tools/testing/selftests/rseq/.gitignore1
-rw-r--r--tools/testing/selftests/rtc/.gitignore1
-rw-r--r--tools/testing/selftests/safesetid/.gitignore1
-rw-r--r--tools/testing/selftests/seccomp/.gitignore1
-rw-r--r--tools/testing/selftests/seccomp/Makefile17
-rw-r--r--tools/testing/selftests/seccomp/seccomp_bpf.c98
-rw-r--r--tools/testing/selftests/sigaltstack/.gitignore1
-rw-r--r--tools/testing/selftests/size/.gitignore1
-rw-r--r--tools/testing/selftests/sparc64/drivers/.gitignore1
-rw-r--r--tools/testing/selftests/splice/.gitignore1
-rw-r--r--tools/testing/selftests/sync/.gitignore1
-rw-r--r--tools/testing/selftests/sysctl/config2
-rwxr-xr-xtools/testing/selftests/sysctl/sysctl.sh57
-rw-r--r--tools/testing/selftests/tc-testing/.gitignore1
-rw-r--r--tools/testing/selftests/tc-testing/config6
-rw-r--r--tools/testing/selftests/tc-testing/tc-tests/actions/pedit.json25
-rw-r--r--tools/testing/selftests/tc-testing/tc-tests/filters/basic.json902
-rw-r--r--tools/testing/selftests/tc-testing/tc-tests/filters/tests.json44
-rw-r--r--tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json21
-rw-r--r--tools/testing/selftests/tc-testing/tc-tests/qdiscs/red.json185
-rwxr-xr-xtools/testing/selftests/tc-testing/tdc.py5
-rwxr-xr-xtools/testing/selftests/tc-testing/tdc_batch.py6
-rw-r--r--tools/testing/selftests/timens/.gitignore1
-rw-r--r--tools/testing/selftests/timens/clock_nanosleep.c2
-rw-r--r--tools/testing/selftests/timens/exec.c1
-rw-r--r--tools/testing/selftests/timens/procfs.c1
-rw-r--r--tools/testing/selftests/timens/timens.c3
-rw-r--r--tools/testing/selftests/timens/timens.h13
-rw-r--r--tools/testing/selftests/timens/timer.c6
-rw-r--r--tools/testing/selftests/timens/timerfd.c5
-rw-r--r--tools/testing/selftests/timers/.gitignore1
-rw-r--r--tools/testing/selftests/tmpfs/.gitignore1
-rwxr-xr-xtools/testing/selftests/tpm2/test_smoke.sh10
-rwxr-xr-xtools/testing/selftests/tpm2/test_space.sh8
-rw-r--r--tools/testing/selftests/vDSO/.gitignore3
-rw-r--r--tools/testing/selftests/vDSO/Makefile5
-rw-r--r--tools/testing/selftests/vDSO/parse_vdso.c24
-rw-r--r--tools/testing/selftests/vDSO/parse_vdso.h31
-rw-r--r--tools/testing/selftests/vDSO/vdso_standalone_test_x86.c4
-rw-r--r--tools/testing/selftests/vDSO/vdso_test_getcpu.c54
-rw-r--r--tools/testing/selftests/vDSO/vdso_test_gettimeofday.c (renamed from tools/testing/selftests/vDSO/vdso_test.c)10
-rw-r--r--tools/testing/selftests/vm/.gitignore6
-rw-r--r--tools/testing/selftests/vm/Makefile83
-rw-r--r--tools/testing/selftests/vm/charge_reserved_hugetlb.sh575
-rw-r--r--tools/testing/selftests/vm/config2
-rw-r--r--tools/testing/selftests/vm/gup_benchmark.c15
-rw-r--r--tools/testing/selftests/vm/hmm-tests.c1359
-rw-r--r--tools/testing/selftests/vm/hugetlb_reparenting_test.sh244
-rw-r--r--tools/testing/selftests/vm/khugepaged.c1035
-rw-r--r--tools/testing/selftests/vm/map_hugetlb.c14
-rw-r--r--tools/testing/selftests/vm/mlock2-tests.c233
-rw-r--r--tools/testing/selftests/vm/mremap_dontunmap.c312
-rw-r--r--tools/testing/selftests/vm/pkey-helpers.h225
-rw-r--r--tools/testing/selftests/vm/pkey-powerpc.h133
-rw-r--r--tools/testing/selftests/vm/pkey-x86.h181
-rw-r--r--tools/testing/selftests/vm/protection_keys.c (renamed from tools/testing/selftests/x86/protection_keys.c)696
-rwxr-xr-xtools/testing/selftests/vm/run_vmtests55
-rwxr-xr-xtools/testing/selftests/vm/test_hmm.sh97
-rw-r--r--tools/testing/selftests/vm/userfaultfd.c225
-rw-r--r--tools/testing/selftests/vm/write_hugetlb_memory.sh23
-rw-r--r--tools/testing/selftests/vm/write_to_hugetlbfs.c240
-rw-r--r--tools/testing/selftests/watchdog/.gitignore1
-rwxr-xr-xtools/testing/selftests/wireguard/netns.sh54
-rw-r--r--tools/testing/selftests/wireguard/qemu/.gitignore1
-rw-r--r--tools/testing/selftests/wireguard/qemu/Makefile2
-rw-r--r--tools/testing/selftests/wireguard/qemu/arch/powerpc64le.config1
-rw-r--r--tools/testing/selftests/wireguard/qemu/debug.config2
-rw-r--r--tools/testing/selftests/x86/.gitignore2
-rw-r--r--tools/testing/selftests/x86/Makefile2
-rw-r--r--tools/testing/selftests/x86/pkey-helpers.h219
-rw-r--r--tools/testing/selftests/x86/ptrace_syscall.c8
-rw-r--r--tools/testing/selftests/x86/test_vdso.c5
-rw-r--r--tools/testing/selftests/x86/vdso_restorer.c15
565 files changed, 40080 insertions, 4152 deletions
diff --git a/tools/testing/selftests/.gitignore b/tools/testing/selftests/.gitignore
index 61df01cdf0b2..055a5019b13c 100644
--- a/tools/testing/selftests/.gitignore
+++ b/tools/testing/selftests/.gitignore
@@ -1,6 +1,10 @@
+# SPDX-License-Identifier: GPL-2.0-only
gpiogpio-event-mon
gpiogpio-hammer
gpioinclude/
gpiolsgpio
tpm2/SpaceTest.log
-tpm2/*.pyc
+
+# Python bytecode and cache
+__pycache__/
+*.py[cod]
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index b93fa645ee54..1195bd85af38 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -36,9 +36,9 @@ TARGETS += net
TARGETS += net/forwarding
TARGETS += net/mptcp
TARGETS += netfilter
-TARGETS += networking/timestamping
TARGETS += nsfs
TARGETS += pidfd
+TARGETS += pid_namespace
TARGETS += powerpc
TARGETS += proc
TARGETS += pstore
@@ -92,7 +92,7 @@ override LDFLAGS =
override MAKEFLAGS =
endif
-# Append kselftest to KBUILD_OUTPUT to avoid cluttering
+# Append kselftest to KBUILD_OUTPUT and O to avoid cluttering
# KBUILD_OUTPUT with selftest objects and headers installed
# by selftests Makefile or lib.mk.
ifdef building_out_of_srctree
@@ -100,7 +100,7 @@ override LDFLAGS =
endif
ifneq ($(O),)
- BUILD := $(O)
+ BUILD := $(O)/kselftest
else
ifneq ($(KBUILD_OUTPUT),)
BUILD := $(KBUILD_OUTPUT)/kselftest
@@ -249,10 +249,17 @@ else
$(error Error: set INSTALL_PATH to use install)
endif
+FORMAT ?= .gz
+TAR_PATH = $(abspath ${INSTALL_PATH}/kselftest-packages/kselftest.tar${FORMAT})
+gen_tar: install
+ @mkdir -p ${INSTALL_PATH}/kselftest-packages/
+ @tar caf ${TAR_PATH} --exclude=kselftest-packages -C ${INSTALL_PATH} .
+ @echo "Created ${TAR_PATH}"
+
clean:
@for TARGET in $(TARGETS); do \
BUILD_TARGET=$$BUILD/$$TARGET; \
$(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET clean;\
done;
-.PHONY: khdr all run_tests hotplug run_hotplug clean_hotplug run_pstore_crash install clean
+.PHONY: khdr all run_tests hotplug run_hotplug clean_hotplug run_pstore_crash install clean gen_tar
diff --git a/tools/testing/selftests/android/Makefile b/tools/testing/selftests/android/Makefile
index 7c462714b418..9258306cafe9 100644
--- a/tools/testing/selftests/android/Makefile
+++ b/tools/testing/selftests/android/Makefile
@@ -21,7 +21,7 @@ all:
override define INSTALL_RULE
mkdir -p $(INSTALL_PATH)
- install -t $(INSTALL_PATH) $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES)
+install -t $(INSTALL_PATH) $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES)
@for SUBDIR in $(SUBDIRS); do \
BUILD_TARGET=$(OUTPUT)/$$SUBDIR; \
diff --git a/tools/testing/selftests/android/ion/.gitignore b/tools/testing/selftests/android/ion/.gitignore
index 95e8f4561474..78eae9972bb1 100644
--- a/tools/testing/selftests/android/ion/.gitignore
+++ b/tools/testing/selftests/android/ion/.gitignore
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
ionapp_export
ionapp_import
ionmap_test
diff --git a/tools/testing/selftests/android/ion/Makefile b/tools/testing/selftests/android/ion/Makefile
index 0eb7ab626e1c..42b71f005332 100644
--- a/tools/testing/selftests/android/ion/Makefile
+++ b/tools/testing/selftests/android/ion/Makefile
@@ -17,4 +17,4 @@ include ../../lib.mk
$(OUTPUT)/ionapp_export: ionapp_export.c ipcsocket.c ionutils.c
$(OUTPUT)/ionapp_import: ionapp_import.c ipcsocket.c ionutils.c
-$(OUTPUT)/ionmap_test: ionmap_test.c ionutils.c
+$(OUTPUT)/ionmap_test: ionmap_test.c ionutils.c ipcsocket.c
diff --git a/tools/testing/selftests/arm64/signal/.gitignore b/tools/testing/selftests/arm64/signal/.gitignore
index 3c5b4e8ff894..78c902045ca7 100644
--- a/tools/testing/selftests/arm64/signal/.gitignore
+++ b/tools/testing/selftests/arm64/signal/.gitignore
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
mangle_*
fake_sigreturn_*
!*.[ch]
diff --git a/tools/testing/selftests/arm64/tags/.gitignore b/tools/testing/selftests/arm64/tags/.gitignore
index e8fae8d61ed6..f4f6c5112463 100644
--- a/tools/testing/selftests/arm64/tags/.gitignore
+++ b/tools/testing/selftests/arm64/tags/.gitignore
@@ -1 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
tags_test
diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index ec464859c6b6..1bb204cee853 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
test_verifier
test_maps
test_lru_map
@@ -29,12 +30,12 @@ test_tcpnotify_user
test_libbpf
test_tcp_check_syncookie_user
test_sysctl
-test_hashmap
-test_btf_dump
+test_current_pid_tgid_new_ns
xdping
test_cpp
*.skel.h
/no_alu32
/bpf_gcc
/tools
-
+/runqslower
+/bench
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 257a1aaaa37d..22aaec74ea0a 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -2,6 +2,8 @@
include ../../../../scripts/Kbuild.include
include ../../../scripts/Makefile.arch
+CXX ?= $(CROSS_COMPILE)g++
+
CURDIR := $(abspath .)
TOOLSDIR := $(abspath ../../..)
LIBDIR := $(TOOLSDIR)/lib
@@ -20,8 +22,10 @@ CLANG ?= clang
LLC ?= llc
LLVM_OBJCOPY ?= llvm-objcopy
BPF_GCC ?= $(shell command -v bpf-gcc;)
-CFLAGS += -g -Wall -O2 $(GENFLAGS) -I$(CURDIR) -I$(APIDIR) \
- -I$(INCLUDE_DIR) -I$(GENDIR) -I$(LIBDIR) -I$(TOOLSINCDIR) \
+SAN_CFLAGS ?=
+CFLAGS += -g -rdynamic -Wall -O2 $(GENFLAGS) $(SAN_CFLAGS) \
+ -I$(CURDIR) -I$(INCLUDE_DIR) -I$(GENDIR) -I$(LIBDIR) \
+ -I$(TOOLSINCDIR) -I$(APIDIR) \
-Dbpf_prog_load=bpf_prog_test_load \
-Dbpf_load_program=bpf_test_load_program
LDLIBS += -lcap -lelf -lz -lrt -lpthread
@@ -31,8 +35,9 @@ TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test
test_align test_verifier_log test_dev_cgroup test_tcpbpf_user \
test_sock test_btf test_sockmap get_cgroup_id_user test_socket_cookie \
test_cgroup_storage \
- test_netcnt test_tcpnotify_user test_sock_fields test_sysctl test_hashmap \
- test_progs-no_alu32
+ test_netcnt test_tcpnotify_user test_sock_fields test_sysctl \
+ test_progs-no_alu32 \
+ test_current_pid_tgid_new_ns
# Also test bpf-gcc, if present
ifneq ($(BPF_GCC),)
@@ -62,7 +67,8 @@ TEST_PROGS := test_kmod.sh \
test_tc_tunnel.sh \
test_tc_edt.sh \
test_xdping.sh \
- test_bpftool_build.sh
+ test_bpftool_build.sh \
+ test_bpftool.sh
TEST_PROGS_EXTENDED := with_addr.sh \
with_tunnels.sh \
@@ -73,7 +79,7 @@ TEST_PROGS_EXTENDED := with_addr.sh \
# Compile but not part of 'make run_tests'
TEST_GEN_PROGS_EXTENDED = test_sock_addr test_skb_cgroup_id_user \
flow_dissector_load test_flow_dissector test_tcp_check_syncookie_user \
- test_lirc_mode2_user xdping test_cpp runqslower
+ test_lirc_mode2_user xdping test_cpp runqslower bench
TEST_CUSTOM_PROGS = urandom_read
@@ -128,14 +134,18 @@ $(OUTPUT)/test_stub.o: test_stub.c $(BPFOBJ)
$(call msg,CC,,$@)
$(CC) -c $(CFLAGS) -o $@ $<
-VMLINUX_BTF_PATHS := $(abspath ../../../../vmlinux) \
- /sys/kernel/btf/vmlinux \
- /boot/vmlinux-$(shell uname -r)
-VMLINUX_BTF:= $(firstword $(wildcard $(VMLINUX_BTF_PATHS)))
+VMLINUX_BTF_PATHS := $(if $(O),$(O)/vmlinux) \
+ $(if $(KBUILD_OUTPUT),$(KBUILD_OUTPUT)/vmlinux) \
+ ../../../../vmlinux \
+ /sys/kernel/btf/vmlinux \
+ /boot/vmlinux-$(shell uname -r)
+VMLINUX_BTF := $(abspath $(firstword $(wildcard $(VMLINUX_BTF_PATHS))))
+
$(OUTPUT)/runqslower: $(BPFOBJ)
$(Q)$(MAKE) $(submake_extras) -C $(TOOLSDIR)/bpf/runqslower \
OUTPUT=$(SCRATCH_DIR)/ VMLINUX_BTF=$(VMLINUX_BTF) \
- BPFOBJ=$(BPFOBJ) BPF_INCLUDE=$(INCLUDE_DIR)
+ BPFOBJ=$(BPFOBJ) BPF_INCLUDE=$(INCLUDE_DIR) && \
+ cp $(SCRATCH_DIR)/runqslower $@
$(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED): $(OUTPUT)/test_stub.o $(BPFOBJ)
@@ -171,6 +181,10 @@ $(BUILD_DIR)/libbpf $(BUILD_DIR)/bpftool $(INCLUDE_DIR):
$(call msg,MKDIR,,$@)
mkdir -p $@
+$(INCLUDE_DIR)/vmlinux.h: $(VMLINUX_BTF) | $(BPFTOOL) $(INCLUDE_DIR)
+ $(call msg,GEN,,$@)
+ $(BPFTOOL) btf dump file $(VMLINUX_BTF) format c > $@
+
# Get Clang's default includes on this system, as opposed to those seen by
# '-target bpf'. This fixes "missing" files on some architectures/distros,
# such as asm/byteorder.h, asm/socket.h, asm/sockios.h, sys/cdefs.h etc.
@@ -189,8 +203,8 @@ MENDIAN=$(if $(IS_LITTLE_ENDIAN),-mlittle-endian,-mbig-endian)
CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG))
BPF_CFLAGS = -g -D__TARGET_ARCH_$(SRCARCH) $(MENDIAN) \
- -I$(INCLUDE_DIR) -I$(CURDIR) -I$(CURDIR)/include/uapi \
- -I$(APIDIR) -I$(abspath $(OUTPUT)/../usr/include)
+ -I$(INCLUDE_DIR) -I$(CURDIR) -I$(APIDIR) \
+ -I$(abspath $(OUTPUT)/../usr/include)
CLANG_CFLAGS = $(CLANG_SYS_INCLUDES) \
-Wno-compare-distinct-pointer-types
@@ -209,7 +223,7 @@ define CLANG_BPF_BUILD_RULE
$(call msg,CLNG-LLC,$(TRUNNER_BINARY),$2)
($(CLANG) $3 -O2 -target bpf -emit-llvm \
-c $1 -o - || echo "BPF obj compilation failed") | \
- $(LLC) -mattr=dwarfris -march=bpf -mcpu=probe $4 -filetype=obj -o $2
+ $(LLC) -mattr=dwarfris -march=bpf -mcpu=v3 $4 -filetype=obj -o $2
endef
# Similar to CLANG_BPF_BUILD_RULE, but with disabled alu32
define CLANG_NOALU32_BPF_BUILD_RULE
@@ -223,7 +237,7 @@ define CLANG_NATIVE_BPF_BUILD_RULE
$(call msg,CLNG-BPF,$(TRUNNER_BINARY),$2)
($(CLANG) $3 -O2 -emit-llvm \
-c $1 -o - || echo "BPF obj compilation failed") | \
- $(LLC) -march=bpf -mcpu=probe $4 -filetype=obj -o $2
+ $(LLC) -march=bpf -mcpu=v3 $4 -filetype=obj -o $2
endef
# Build BPF object using GCC
define GCC_BPF_BUILD_RULE
@@ -231,7 +245,7 @@ define GCC_BPF_BUILD_RULE
$(BPF_GCC) $3 $4 -O2 -c $1 -o $2
endef
-SKEL_BLACKLIST := btf__% test_pinning_invalid.c
+SKEL_BLACKLIST := btf__% test_pinning_invalid.c test_sk_assign.c
# Set up extra TRUNNER_XXX "temporary" variables in the environment (relies on
# $eval()) and pass control to DEFINE_TEST_RUNNER_RULES.
@@ -253,6 +267,7 @@ TRUNNER_BPF_OBJS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.o, $$(TRUNNER_BPF_SRCS)
TRUNNER_BPF_SKELS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.skel.h, \
$$(filter-out $(SKEL_BLACKLIST), \
$$(TRUNNER_BPF_SRCS)))
+TEST_GEN_FILES += $$(TRUNNER_BPF_OBJS)
# Evaluate rules now with extra TRUNNER_XXX variables above already defined
$$(eval $$(call DEFINE_TEST_RUNNER_RULES,$1,$2))
@@ -279,6 +294,7 @@ $(TRUNNER_BPF_PROGS_DIR)$(if $2,-)$2-bpfobjs := y
$(TRUNNER_BPF_OBJS): $(TRUNNER_OUTPUT)/%.o: \
$(TRUNNER_BPF_PROGS_DIR)/%.c \
$(TRUNNER_BPF_PROGS_DIR)/*.h \
+ $$(INCLUDE_DIR)/vmlinux.h \
$$(BPFOBJ) | $(TRUNNER_OUTPUT)
$$(call $(TRUNNER_BPF_BUILD_RULE),$$<,$$@, \
$(TRUNNER_BPF_CFLAGS), \
@@ -312,7 +328,7 @@ $(TRUNNER_TEST_OBJS): $(TRUNNER_OUTPUT)/%.test.o: \
$(TRUNNER_BPF_SKELS) \
$$(BPFOBJ) | $(TRUNNER_OUTPUT)
$$(call msg,TEST-OBJ,$(TRUNNER_BINARY),$$@)
- cd $$(@D) && $$(CC) $$(CFLAGS) -c $(CURDIR)/$$< $$(LDLIBS) -o $$(@F)
+ cd $$(@D) && $$(CC) -I. $$(CFLAGS) -c $(CURDIR)/$$< $$(LDLIBS) -o $$(@F)
$(TRUNNER_EXTRA_OBJS): $(TRUNNER_OUTPUT)/%.o: \
%.c \
@@ -341,6 +357,7 @@ endef
TRUNNER_TESTS_DIR := prog_tests
TRUNNER_BPF_PROGS_DIR := progs
TRUNNER_EXTRA_SOURCES := test_progs.c cgroup_helpers.c trace_helpers.c \
+ network_helpers.c testing_helpers.c \
flow_dissector_load.h
TRUNNER_EXTRA_FILES := $(OUTPUT)/urandom_read \
$(wildcard progs/btf_dump_test_case_*.c)
@@ -392,6 +409,24 @@ $(OUTPUT)/test_cpp: test_cpp.cpp $(OUTPUT)/test_core_extern.skel.h $(BPFOBJ)
$(call msg,CXX,,$@)
$(CXX) $(CFLAGS) $^ $(LDLIBS) -o $@
+# Benchmark runner
+$(OUTPUT)/bench_%.o: benchs/bench_%.c bench.h
+ $(call msg,CC,,$@)
+ $(CC) $(CFLAGS) -c $(filter %.c,$^) $(LDLIBS) -o $@
+$(OUTPUT)/bench_rename.o: $(OUTPUT)/test_overhead.skel.h
+$(OUTPUT)/bench_trigger.o: $(OUTPUT)/trigger_bench.skel.h
+$(OUTPUT)/bench_ringbufs.o: $(OUTPUT)/ringbuf_bench.skel.h \
+ $(OUTPUT)/perfbuf_bench.skel.h
+$(OUTPUT)/bench.o: bench.h testing_helpers.h
+$(OUTPUT)/bench: LDLIBS += -lm
+$(OUTPUT)/bench: $(OUTPUT)/bench.o $(OUTPUT)/testing_helpers.o \
+ $(OUTPUT)/bench_count.o \
+ $(OUTPUT)/bench_rename.o \
+ $(OUTPUT)/bench_trigger.o \
+ $(OUTPUT)/bench_ringbufs.o
+ $(call msg,BINARY,,$@)
+ $(CC) $(LDFLAGS) -o $@ $(filter %.a %.o,$^) $(LDLIBS)
+
EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) $(SCRATCH_DIR) \
prog_tests/tests.h map_tests/tests.h verifier/tests.h \
feature \
diff --git a/tools/testing/selftests/bpf/README.rst b/tools/testing/selftests/bpf/README.rst
new file mode 100644
index 000000000000..e885d351595f
--- /dev/null
+++ b/tools/testing/selftests/bpf/README.rst
@@ -0,0 +1,45 @@
+==================
+BPF Selftest Notes
+==================
+General instructions on running selftests can be found in
+`Documentation/bpf/bpf_devel_QA.rst`_.
+
+Additional information about selftest failures are
+documented here.
+
+bpf_iter test failures with clang/llvm 10.0.0
+=============================================
+
+With clang/llvm 10.0.0, the following two bpf_iter tests failed:
+ * ``bpf_iter/ipv6_route``
+ * ``bpf_iter/netlink``
+
+The symptom for ``bpf_iter/ipv6_route`` looks like
+
+.. code-block:: c
+
+ 2: (79) r8 = *(u64 *)(r1 +8)
+ ...
+ 14: (bf) r2 = r8
+ 15: (0f) r2 += r1
+ ; BPF_SEQ_PRINTF(seq, "%pi6 %02x ", &rt->fib6_dst.addr, rt->fib6_dst.plen);
+ 16: (7b) *(u64 *)(r8 +64) = r2
+ only read is supported
+
+The symptom for ``bpf_iter/netlink`` looks like
+
+.. code-block:: c
+
+ ; struct netlink_sock *nlk = ctx->sk;
+ 2: (79) r7 = *(u64 *)(r1 +8)
+ ...
+ 15: (bf) r2 = r7
+ 16: (0f) r2 += r1
+ ; BPF_SEQ_PRINTF(seq, "%pK %-3d ", s, s->sk_protocol);
+ 17: (7b) *(u64 *)(r7 +0) = r2
+ only read is supported
+
+This is due to a llvm BPF backend bug. The fix
+ https://reviews.llvm.org/D78466
+has been pushed to llvm 10.x release branch and will be
+available in 10.0.1. The fix is available in llvm 11.0.0 trunk.
diff --git a/tools/testing/selftests/bpf/bench.c b/tools/testing/selftests/bpf/bench.c
new file mode 100644
index 000000000000..944ad4721c83
--- /dev/null
+++ b/tools/testing/selftests/bpf/bench.c
@@ -0,0 +1,465 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#define _GNU_SOURCE
+#include <argp.h>
+#include <linux/compiler.h>
+#include <sys/time.h>
+#include <sched.h>
+#include <fcntl.h>
+#include <pthread.h>
+#include <sys/sysinfo.h>
+#include <sys/resource.h>
+#include <signal.h>
+#include "bench.h"
+#include "testing_helpers.h"
+
+struct env env = {
+ .warmup_sec = 1,
+ .duration_sec = 5,
+ .affinity = false,
+ .consumer_cnt = 1,
+ .producer_cnt = 1,
+};
+
+static int libbpf_print_fn(enum libbpf_print_level level,
+ const char *format, va_list args)
+{
+ if (level == LIBBPF_DEBUG && !env.verbose)
+ return 0;
+ return vfprintf(stderr, format, args);
+}
+
+static int bump_memlock_rlimit(void)
+{
+ struct rlimit rlim_new = {
+ .rlim_cur = RLIM_INFINITY,
+ .rlim_max = RLIM_INFINITY,
+ };
+
+ return setrlimit(RLIMIT_MEMLOCK, &rlim_new);
+}
+
+void setup_libbpf()
+{
+ int err;
+
+ libbpf_set_print(libbpf_print_fn);
+
+ err = bump_memlock_rlimit();
+ if (err)
+ fprintf(stderr, "failed to increase RLIMIT_MEMLOCK: %d", err);
+}
+
+void hits_drops_report_progress(int iter, struct bench_res *res, long delta_ns)
+{
+ double hits_per_sec, drops_per_sec;
+ double hits_per_prod;
+
+ hits_per_sec = res->hits / 1000000.0 / (delta_ns / 1000000000.0);
+ hits_per_prod = hits_per_sec / env.producer_cnt;
+ drops_per_sec = res->drops / 1000000.0 / (delta_ns / 1000000000.0);
+
+ printf("Iter %3d (%7.3lfus): ",
+ iter, (delta_ns - 1000000000) / 1000.0);
+
+ printf("hits %8.3lfM/s (%7.3lfM/prod), drops %8.3lfM/s\n",
+ hits_per_sec, hits_per_prod, drops_per_sec);
+}
+
+void hits_drops_report_final(struct bench_res res[], int res_cnt)
+{
+ int i;
+ double hits_mean = 0.0, drops_mean = 0.0;
+ double hits_stddev = 0.0, drops_stddev = 0.0;
+
+ for (i = 0; i < res_cnt; i++) {
+ hits_mean += res[i].hits / 1000000.0 / (0.0 + res_cnt);
+ drops_mean += res[i].drops / 1000000.0 / (0.0 + res_cnt);
+ }
+
+ if (res_cnt > 1) {
+ for (i = 0; i < res_cnt; i++) {
+ hits_stddev += (hits_mean - res[i].hits / 1000000.0) *
+ (hits_mean - res[i].hits / 1000000.0) /
+ (res_cnt - 1.0);
+ drops_stddev += (drops_mean - res[i].drops / 1000000.0) *
+ (drops_mean - res[i].drops / 1000000.0) /
+ (res_cnt - 1.0);
+ }
+ hits_stddev = sqrt(hits_stddev);
+ drops_stddev = sqrt(drops_stddev);
+ }
+ printf("Summary: hits %8.3lf \u00B1 %5.3lfM/s (%7.3lfM/prod), ",
+ hits_mean, hits_stddev, hits_mean / env.producer_cnt);
+ printf("drops %8.3lf \u00B1 %5.3lfM/s\n",
+ drops_mean, drops_stddev);
+}
+
+const char *argp_program_version = "benchmark";
+const char *argp_program_bug_address = "<bpf@vger.kernel.org>";
+const char argp_program_doc[] =
+"benchmark Generic benchmarking framework.\n"
+"\n"
+"This tool runs benchmarks.\n"
+"\n"
+"USAGE: benchmark <bench-name>\n"
+"\n"
+"EXAMPLES:\n"
+" # run 'count-local' benchmark with 1 producer and 1 consumer\n"
+" benchmark count-local\n"
+" # run 'count-local' with 16 producer and 8 consumer thread, pinned to CPUs\n"
+" benchmark -p16 -c8 -a count-local\n";
+
+enum {
+ ARG_PROD_AFFINITY_SET = 1000,
+ ARG_CONS_AFFINITY_SET = 1001,
+};
+
+static const struct argp_option opts[] = {
+ { "list", 'l', NULL, 0, "List available benchmarks"},
+ { "duration", 'd', "SEC", 0, "Duration of benchmark, seconds"},
+ { "warmup", 'w', "SEC", 0, "Warm-up period, seconds"},
+ { "producers", 'p', "NUM", 0, "Number of producer threads"},
+ { "consumers", 'c', "NUM", 0, "Number of consumer threads"},
+ { "verbose", 'v', NULL, 0, "Verbose debug output"},
+ { "affinity", 'a', NULL, 0, "Set consumer/producer thread affinity"},
+ { "prod-affinity", ARG_PROD_AFFINITY_SET, "CPUSET", 0,
+ "Set of CPUs for producer threads; implies --affinity"},
+ { "cons-affinity", ARG_CONS_AFFINITY_SET, "CPUSET", 0,
+ "Set of CPUs for consumer threads; implies --affinity"},
+ {},
+};
+
+extern struct argp bench_ringbufs_argp;
+
+static const struct argp_child bench_parsers[] = {
+ { &bench_ringbufs_argp, 0, "Ring buffers benchmark", 0 },
+ {},
+};
+
+static error_t parse_arg(int key, char *arg, struct argp_state *state)
+{
+ static int pos_args;
+
+ switch (key) {
+ case 'v':
+ env.verbose = true;
+ break;
+ case 'l':
+ env.list = true;
+ break;
+ case 'd':
+ env.duration_sec = strtol(arg, NULL, 10);
+ if (env.duration_sec <= 0) {
+ fprintf(stderr, "Invalid duration: %s\n", arg);
+ argp_usage(state);
+ }
+ break;
+ case 'w':
+ env.warmup_sec = strtol(arg, NULL, 10);
+ if (env.warmup_sec <= 0) {
+ fprintf(stderr, "Invalid warm-up duration: %s\n", arg);
+ argp_usage(state);
+ }
+ break;
+ case 'p':
+ env.producer_cnt = strtol(arg, NULL, 10);
+ if (env.producer_cnt <= 0) {
+ fprintf(stderr, "Invalid producer count: %s\n", arg);
+ argp_usage(state);
+ }
+ break;
+ case 'c':
+ env.consumer_cnt = strtol(arg, NULL, 10);
+ if (env.consumer_cnt <= 0) {
+ fprintf(stderr, "Invalid consumer count: %s\n", arg);
+ argp_usage(state);
+ }
+ break;
+ case 'a':
+ env.affinity = true;
+ break;
+ case ARG_PROD_AFFINITY_SET:
+ env.affinity = true;
+ if (parse_num_list(arg, &env.prod_cpus.cpus,
+ &env.prod_cpus.cpus_len)) {
+ fprintf(stderr, "Invalid format of CPU set for producers.");
+ argp_usage(state);
+ }
+ break;
+ case ARG_CONS_AFFINITY_SET:
+ env.affinity = true;
+ if (parse_num_list(arg, &env.cons_cpus.cpus,
+ &env.cons_cpus.cpus_len)) {
+ fprintf(stderr, "Invalid format of CPU set for consumers.");
+ argp_usage(state);
+ }
+ break;
+ case ARGP_KEY_ARG:
+ if (pos_args++) {
+ fprintf(stderr,
+ "Unrecognized positional argument: %s\n", arg);
+ argp_usage(state);
+ }
+ env.bench_name = strdup(arg);
+ break;
+ default:
+ return ARGP_ERR_UNKNOWN;
+ }
+ return 0;
+}
+
+static void parse_cmdline_args(int argc, char **argv)
+{
+ static const struct argp argp = {
+ .options = opts,
+ .parser = parse_arg,
+ .doc = argp_program_doc,
+ .children = bench_parsers,
+ };
+ if (argp_parse(&argp, argc, argv, 0, NULL, NULL))
+ exit(1);
+ if (!env.list && !env.bench_name) {
+ argp_help(&argp, stderr, ARGP_HELP_DOC, "bench");
+ exit(1);
+ }
+}
+
+static void collect_measurements(long delta_ns);
+
+static __u64 last_time_ns;
+static void sigalarm_handler(int signo)
+{
+ long new_time_ns = get_time_ns();
+ long delta_ns = new_time_ns - last_time_ns;
+
+ collect_measurements(delta_ns);
+
+ last_time_ns = new_time_ns;
+}
+
+/* set up periodic 1-second timer */
+static void setup_timer()
+{
+ static struct sigaction sigalarm_action = {
+ .sa_handler = sigalarm_handler,
+ };
+ struct itimerval timer_settings = {};
+ int err;
+
+ last_time_ns = get_time_ns();
+ err = sigaction(SIGALRM, &sigalarm_action, NULL);
+ if (err < 0) {
+ fprintf(stderr, "failed to install SIGALRM handler: %d\n", -errno);
+ exit(1);
+ }
+ timer_settings.it_interval.tv_sec = 1;
+ timer_settings.it_value.tv_sec = 1;
+ err = setitimer(ITIMER_REAL, &timer_settings, NULL);
+ if (err < 0) {
+ fprintf(stderr, "failed to arm interval timer: %d\n", -errno);
+ exit(1);
+ }
+}
+
+static void set_thread_affinity(pthread_t thread, int cpu)
+{
+ cpu_set_t cpuset;
+
+ CPU_ZERO(&cpuset);
+ CPU_SET(cpu, &cpuset);
+ if (pthread_setaffinity_np(thread, sizeof(cpuset), &cpuset)) {
+ fprintf(stderr, "setting affinity to CPU #%d failed: %d\n",
+ cpu, errno);
+ exit(1);
+ }
+}
+
+static int next_cpu(struct cpu_set *cpu_set)
+{
+ if (cpu_set->cpus) {
+ int i;
+
+ /* find next available CPU */
+ for (i = cpu_set->next_cpu; i < cpu_set->cpus_len; i++) {
+ if (cpu_set->cpus[i]) {
+ cpu_set->next_cpu = i + 1;
+ return i;
+ }
+ }
+ fprintf(stderr, "Not enough CPUs specified, need CPU #%d or higher.\n", i);
+ exit(1);
+ }
+
+ return cpu_set->next_cpu++;
+}
+
+static struct bench_state {
+ int res_cnt;
+ struct bench_res *results;
+ pthread_t *consumers;
+ pthread_t *producers;
+} state;
+
+const struct bench *bench = NULL;
+
+extern const struct bench bench_count_global;
+extern const struct bench bench_count_local;
+extern const struct bench bench_rename_base;
+extern const struct bench bench_rename_kprobe;
+extern const struct bench bench_rename_kretprobe;
+extern const struct bench bench_rename_rawtp;
+extern const struct bench bench_rename_fentry;
+extern const struct bench bench_rename_fexit;
+extern const struct bench bench_rename_fmodret;
+extern const struct bench bench_trig_base;
+extern const struct bench bench_trig_tp;
+extern const struct bench bench_trig_rawtp;
+extern const struct bench bench_trig_kprobe;
+extern const struct bench bench_trig_fentry;
+extern const struct bench bench_trig_fmodret;
+extern const struct bench bench_rb_libbpf;
+extern const struct bench bench_rb_custom;
+extern const struct bench bench_pb_libbpf;
+extern const struct bench bench_pb_custom;
+
+static const struct bench *benchs[] = {
+ &bench_count_global,
+ &bench_count_local,
+ &bench_rename_base,
+ &bench_rename_kprobe,
+ &bench_rename_kretprobe,
+ &bench_rename_rawtp,
+ &bench_rename_fentry,
+ &bench_rename_fexit,
+ &bench_rename_fmodret,
+ &bench_trig_base,
+ &bench_trig_tp,
+ &bench_trig_rawtp,
+ &bench_trig_kprobe,
+ &bench_trig_fentry,
+ &bench_trig_fmodret,
+ &bench_rb_libbpf,
+ &bench_rb_custom,
+ &bench_pb_libbpf,
+ &bench_pb_custom,
+};
+
+static void setup_benchmark()
+{
+ int i, err;
+
+ if (!env.bench_name) {
+ fprintf(stderr, "benchmark name is not specified\n");
+ exit(1);
+ }
+
+ for (i = 0; i < ARRAY_SIZE(benchs); i++) {
+ if (strcmp(benchs[i]->name, env.bench_name) == 0) {
+ bench = benchs[i];
+ break;
+ }
+ }
+ if (!bench) {
+ fprintf(stderr, "benchmark '%s' not found\n", env.bench_name);
+ exit(1);
+ }
+
+ printf("Setting up benchmark '%s'...\n", bench->name);
+
+ state.producers = calloc(env.producer_cnt, sizeof(*state.producers));
+ state.consumers = calloc(env.consumer_cnt, sizeof(*state.consumers));
+ state.results = calloc(env.duration_sec + env.warmup_sec + 2,
+ sizeof(*state.results));
+ if (!state.producers || !state.consumers || !state.results)
+ exit(1);
+
+ if (bench->validate)
+ bench->validate();
+ if (bench->setup)
+ bench->setup();
+
+ for (i = 0; i < env.consumer_cnt; i++) {
+ err = pthread_create(&state.consumers[i], NULL,
+ bench->consumer_thread, (void *)(long)i);
+ if (err) {
+ fprintf(stderr, "failed to create consumer thread #%d: %d\n",
+ i, -errno);
+ exit(1);
+ }
+ if (env.affinity)
+ set_thread_affinity(state.consumers[i],
+ next_cpu(&env.cons_cpus));
+ }
+
+ /* unless explicit producer CPU list is specified, continue after
+ * last consumer CPU
+ */
+ if (!env.prod_cpus.cpus)
+ env.prod_cpus.next_cpu = env.cons_cpus.next_cpu;
+
+ for (i = 0; i < env.producer_cnt; i++) {
+ err = pthread_create(&state.producers[i], NULL,
+ bench->producer_thread, (void *)(long)i);
+ if (err) {
+ fprintf(stderr, "failed to create producer thread #%d: %d\n",
+ i, -errno);
+ exit(1);
+ }
+ if (env.affinity)
+ set_thread_affinity(state.producers[i],
+ next_cpu(&env.prod_cpus));
+ }
+
+ printf("Benchmark '%s' started.\n", bench->name);
+}
+
+static pthread_mutex_t bench_done_mtx = PTHREAD_MUTEX_INITIALIZER;
+static pthread_cond_t bench_done = PTHREAD_COND_INITIALIZER;
+
+static void collect_measurements(long delta_ns) {
+ int iter = state.res_cnt++;
+ struct bench_res *res = &state.results[iter];
+
+ bench->measure(res);
+
+ if (bench->report_progress)
+ bench->report_progress(iter, res, delta_ns);
+
+ if (iter == env.duration_sec + env.warmup_sec) {
+ pthread_mutex_lock(&bench_done_mtx);
+ pthread_cond_signal(&bench_done);
+ pthread_mutex_unlock(&bench_done_mtx);
+ }
+}
+
+int main(int argc, char **argv)
+{
+ parse_cmdline_args(argc, argv);
+
+ if (env.list) {
+ int i;
+
+ printf("Available benchmarks:\n");
+ for (i = 0; i < ARRAY_SIZE(benchs); i++) {
+ printf("- %s\n", benchs[i]->name);
+ }
+ return 0;
+ }
+
+ setup_benchmark();
+
+ setup_timer();
+
+ pthread_mutex_lock(&bench_done_mtx);
+ pthread_cond_wait(&bench_done, &bench_done_mtx);
+ pthread_mutex_unlock(&bench_done_mtx);
+
+ if (bench->report_final)
+ /* skip first sample */
+ bench->report_final(state.results + env.warmup_sec,
+ state.res_cnt - env.warmup_sec);
+
+ return 0;
+}
+
diff --git a/tools/testing/selftests/bpf/bench.h b/tools/testing/selftests/bpf/bench.h
new file mode 100644
index 000000000000..c1f48a473b02
--- /dev/null
+++ b/tools/testing/selftests/bpf/bench.h
@@ -0,0 +1,81 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#pragma once
+#include <stdlib.h>
+#include <stdbool.h>
+#include <linux/err.h>
+#include <errno.h>
+#include <unistd.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+#include <math.h>
+#include <time.h>
+#include <sys/syscall.h>
+
+struct cpu_set {
+ bool *cpus;
+ int cpus_len;
+ int next_cpu;
+};
+
+struct env {
+ char *bench_name;
+ int duration_sec;
+ int warmup_sec;
+ bool verbose;
+ bool list;
+ bool affinity;
+ int consumer_cnt;
+ int producer_cnt;
+ struct cpu_set prod_cpus;
+ struct cpu_set cons_cpus;
+};
+
+struct bench_res {
+ long hits;
+ long drops;
+};
+
+struct bench {
+ const char *name;
+ void (*validate)();
+ void (*setup)();
+ void *(*producer_thread)(void *ctx);
+ void *(*consumer_thread)(void *ctx);
+ void (*measure)(struct bench_res* res);
+ void (*report_progress)(int iter, struct bench_res* res, long delta_ns);
+ void (*report_final)(struct bench_res res[], int res_cnt);
+};
+
+struct counter {
+ long value;
+} __attribute__((aligned(128)));
+
+extern struct env env;
+extern const struct bench *bench;
+
+void setup_libbpf();
+void hits_drops_report_progress(int iter, struct bench_res *res, long delta_ns);
+void hits_drops_report_final(struct bench_res res[], int res_cnt);
+
+static inline __u64 get_time_ns() {
+ struct timespec t;
+
+ clock_gettime(CLOCK_MONOTONIC, &t);
+
+ return (u64)t.tv_sec * 1000000000 + t.tv_nsec;
+}
+
+static inline void atomic_inc(long *value)
+{
+ (void)__atomic_add_fetch(value, 1, __ATOMIC_RELAXED);
+}
+
+static inline void atomic_add(long *value, long n)
+{
+ (void)__atomic_add_fetch(value, n, __ATOMIC_RELAXED);
+}
+
+static inline long atomic_swap(long *value, long n)
+{
+ return __atomic_exchange_n(value, n, __ATOMIC_RELAXED);
+}
diff --git a/tools/testing/selftests/bpf/benchs/bench_count.c b/tools/testing/selftests/bpf/benchs/bench_count.c
new file mode 100644
index 000000000000..befba7a82643
--- /dev/null
+++ b/tools/testing/selftests/bpf/benchs/bench_count.c
@@ -0,0 +1,91 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#include "bench.h"
+
+/* COUNT-GLOBAL benchmark */
+
+static struct count_global_ctx {
+ struct counter hits;
+} count_global_ctx;
+
+static void *count_global_producer(void *input)
+{
+ struct count_global_ctx *ctx = &count_global_ctx;
+
+ while (true) {
+ atomic_inc(&ctx->hits.value);
+ }
+ return NULL;
+}
+
+static void *count_global_consumer(void *input)
+{
+ return NULL;
+}
+
+static void count_global_measure(struct bench_res *res)
+{
+ struct count_global_ctx *ctx = &count_global_ctx;
+
+ res->hits = atomic_swap(&ctx->hits.value, 0);
+}
+
+/* COUNT-local benchmark */
+
+static struct count_local_ctx {
+ struct counter *hits;
+} count_local_ctx;
+
+static void count_local_setup()
+{
+ struct count_local_ctx *ctx = &count_local_ctx;
+
+ ctx->hits = calloc(env.consumer_cnt, sizeof(*ctx->hits));
+ if (!ctx->hits)
+ exit(1);
+}
+
+static void *count_local_producer(void *input)
+{
+ struct count_local_ctx *ctx = &count_local_ctx;
+ int idx = (long)input;
+
+ while (true) {
+ atomic_inc(&ctx->hits[idx].value);
+ }
+ return NULL;
+}
+
+static void *count_local_consumer(void *input)
+{
+ return NULL;
+}
+
+static void count_local_measure(struct bench_res *res)
+{
+ struct count_local_ctx *ctx = &count_local_ctx;
+ int i;
+
+ for (i = 0; i < env.producer_cnt; i++) {
+ res->hits += atomic_swap(&ctx->hits[i].value, 0);
+ }
+}
+
+const struct bench bench_count_global = {
+ .name = "count-global",
+ .producer_thread = count_global_producer,
+ .consumer_thread = count_global_consumer,
+ .measure = count_global_measure,
+ .report_progress = hits_drops_report_progress,
+ .report_final = hits_drops_report_final,
+};
+
+const struct bench bench_count_local = {
+ .name = "count-local",
+ .setup = count_local_setup,
+ .producer_thread = count_local_producer,
+ .consumer_thread = count_local_consumer,
+ .measure = count_local_measure,
+ .report_progress = hits_drops_report_progress,
+ .report_final = hits_drops_report_final,
+};
diff --git a/tools/testing/selftests/bpf/benchs/bench_rename.c b/tools/testing/selftests/bpf/benchs/bench_rename.c
new file mode 100644
index 000000000000..e74cff40f4fe
--- /dev/null
+++ b/tools/testing/selftests/bpf/benchs/bench_rename.c
@@ -0,0 +1,195 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#include <fcntl.h>
+#include "bench.h"
+#include "test_overhead.skel.h"
+
+/* BPF triggering benchmarks */
+static struct ctx {
+ struct test_overhead *skel;
+ struct counter hits;
+ int fd;
+} ctx;
+
+static void validate()
+{
+ if (env.producer_cnt != 1) {
+ fprintf(stderr, "benchmark doesn't support multi-producer!\n");
+ exit(1);
+ }
+ if (env.consumer_cnt != 1) {
+ fprintf(stderr, "benchmark doesn't support multi-consumer!\n");
+ exit(1);
+ }
+}
+
+static void *producer(void *input)
+{
+ char buf[] = "test_overhead";
+ int err;
+
+ while (true) {
+ err = write(ctx.fd, buf, sizeof(buf));
+ if (err < 0) {
+ fprintf(stderr, "write failed\n");
+ exit(1);
+ }
+ atomic_inc(&ctx.hits.value);
+ }
+}
+
+static void measure(struct bench_res *res)
+{
+ res->hits = atomic_swap(&ctx.hits.value, 0);
+}
+
+static void setup_ctx()
+{
+ setup_libbpf();
+
+ ctx.skel = test_overhead__open_and_load();
+ if (!ctx.skel) {
+ fprintf(stderr, "failed to open skeleton\n");
+ exit(1);
+ }
+
+ ctx.fd = open("/proc/self/comm", O_WRONLY|O_TRUNC);
+ if (ctx.fd < 0) {
+ fprintf(stderr, "failed to open /proc/self/comm: %d\n", -errno);
+ exit(1);
+ }
+}
+
+static void attach_bpf(struct bpf_program *prog)
+{
+ struct bpf_link *link;
+
+ link = bpf_program__attach(prog);
+ if (IS_ERR(link)) {
+ fprintf(stderr, "failed to attach program!\n");
+ exit(1);
+ }
+}
+
+static void setup_base()
+{
+ setup_ctx();
+}
+
+static void setup_kprobe()
+{
+ setup_ctx();
+ attach_bpf(ctx.skel->progs.prog1);
+}
+
+static void setup_kretprobe()
+{
+ setup_ctx();
+ attach_bpf(ctx.skel->progs.prog2);
+}
+
+static void setup_rawtp()
+{
+ setup_ctx();
+ attach_bpf(ctx.skel->progs.prog3);
+}
+
+static void setup_fentry()
+{
+ setup_ctx();
+ attach_bpf(ctx.skel->progs.prog4);
+}
+
+static void setup_fexit()
+{
+ setup_ctx();
+ attach_bpf(ctx.skel->progs.prog5);
+}
+
+static void setup_fmodret()
+{
+ setup_ctx();
+ attach_bpf(ctx.skel->progs.prog6);
+}
+
+static void *consumer(void *input)
+{
+ return NULL;
+}
+
+const struct bench bench_rename_base = {
+ .name = "rename-base",
+ .validate = validate,
+ .setup = setup_base,
+ .producer_thread = producer,
+ .consumer_thread = consumer,
+ .measure = measure,
+ .report_progress = hits_drops_report_progress,
+ .report_final = hits_drops_report_final,
+};
+
+const struct bench bench_rename_kprobe = {
+ .name = "rename-kprobe",
+ .validate = validate,
+ .setup = setup_kprobe,
+ .producer_thread = producer,
+ .consumer_thread = consumer,
+ .measure = measure,
+ .report_progress = hits_drops_report_progress,
+ .report_final = hits_drops_report_final,
+};
+
+const struct bench bench_rename_kretprobe = {
+ .name = "rename-kretprobe",
+ .validate = validate,
+ .setup = setup_kretprobe,
+ .producer_thread = producer,
+ .consumer_thread = consumer,
+ .measure = measure,
+ .report_progress = hits_drops_report_progress,
+ .report_final = hits_drops_report_final,
+};
+
+const struct bench bench_rename_rawtp = {
+ .name = "rename-rawtp",
+ .validate = validate,
+ .setup = setup_rawtp,
+ .producer_thread = producer,
+ .consumer_thread = consumer,
+ .measure = measure,
+ .report_progress = hits_drops_report_progress,
+ .report_final = hits_drops_report_final,
+};
+
+const struct bench bench_rename_fentry = {
+ .name = "rename-fentry",
+ .validate = validate,
+ .setup = setup_fentry,
+ .producer_thread = producer,
+ .consumer_thread = consumer,
+ .measure = measure,
+ .report_progress = hits_drops_report_progress,
+ .report_final = hits_drops_report_final,
+};
+
+const struct bench bench_rename_fexit = {
+ .name = "rename-fexit",
+ .validate = validate,
+ .setup = setup_fexit,
+ .producer_thread = producer,
+ .consumer_thread = consumer,
+ .measure = measure,
+ .report_progress = hits_drops_report_progress,
+ .report_final = hits_drops_report_final,
+};
+
+const struct bench bench_rename_fmodret = {
+ .name = "rename-fmodret",
+ .validate = validate,
+ .setup = setup_fmodret,
+ .producer_thread = producer,
+ .consumer_thread = consumer,
+ .measure = measure,
+ .report_progress = hits_drops_report_progress,
+ .report_final = hits_drops_report_final,
+};
diff --git a/tools/testing/selftests/bpf/benchs/bench_ringbufs.c b/tools/testing/selftests/bpf/benchs/bench_ringbufs.c
new file mode 100644
index 000000000000..da87c7f31891
--- /dev/null
+++ b/tools/testing/selftests/bpf/benchs/bench_ringbufs.c
@@ -0,0 +1,566 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#include <asm/barrier.h>
+#include <linux/perf_event.h>
+#include <linux/ring_buffer.h>
+#include <sys/epoll.h>
+#include <sys/mman.h>
+#include <argp.h>
+#include <stdlib.h>
+#include "bench.h"
+#include "ringbuf_bench.skel.h"
+#include "perfbuf_bench.skel.h"
+
+static struct {
+ bool back2back;
+ int batch_cnt;
+ bool sampled;
+ int sample_rate;
+ int ringbuf_sz; /* per-ringbuf, in bytes */
+ bool ringbuf_use_output; /* use slower output API */
+ int perfbuf_sz; /* per-CPU size, in pages */
+} args = {
+ .back2back = false,
+ .batch_cnt = 500,
+ .sampled = false,
+ .sample_rate = 500,
+ .ringbuf_sz = 512 * 1024,
+ .ringbuf_use_output = false,
+ .perfbuf_sz = 128,
+};
+
+enum {
+ ARG_RB_BACK2BACK = 2000,
+ ARG_RB_USE_OUTPUT = 2001,
+ ARG_RB_BATCH_CNT = 2002,
+ ARG_RB_SAMPLED = 2003,
+ ARG_RB_SAMPLE_RATE = 2004,
+};
+
+static const struct argp_option opts[] = {
+ { "rb-b2b", ARG_RB_BACK2BACK, NULL, 0, "Back-to-back mode"},
+ { "rb-use-output", ARG_RB_USE_OUTPUT, NULL, 0, "Use bpf_ringbuf_output() instead of bpf_ringbuf_reserve()"},
+ { "rb-batch-cnt", ARG_RB_BATCH_CNT, "CNT", 0, "Set BPF-side record batch count"},
+ { "rb-sampled", ARG_RB_SAMPLED, NULL, 0, "Notification sampling"},
+ { "rb-sample-rate", ARG_RB_SAMPLE_RATE, "RATE", 0, "Notification sample rate"},
+ {},
+};
+
+static error_t parse_arg(int key, char *arg, struct argp_state *state)
+{
+ switch (key) {
+ case ARG_RB_BACK2BACK:
+ args.back2back = true;
+ break;
+ case ARG_RB_USE_OUTPUT:
+ args.ringbuf_use_output = true;
+ break;
+ case ARG_RB_BATCH_CNT:
+ args.batch_cnt = strtol(arg, NULL, 10);
+ if (args.batch_cnt < 0) {
+ fprintf(stderr, "Invalid batch count.");
+ argp_usage(state);
+ }
+ break;
+ case ARG_RB_SAMPLED:
+ args.sampled = true;
+ break;
+ case ARG_RB_SAMPLE_RATE:
+ args.sample_rate = strtol(arg, NULL, 10);
+ if (args.sample_rate < 0) {
+ fprintf(stderr, "Invalid perfbuf sample rate.");
+ argp_usage(state);
+ }
+ break;
+ default:
+ return ARGP_ERR_UNKNOWN;
+ }
+ return 0;
+}
+
+/* exported into benchmark runner */
+const struct argp bench_ringbufs_argp = {
+ .options = opts,
+ .parser = parse_arg,
+};
+
+/* RINGBUF-LIBBPF benchmark */
+
+static struct counter buf_hits;
+
+static inline void bufs_trigger_batch()
+{
+ (void)syscall(__NR_getpgid);
+}
+
+static void bufs_validate()
+{
+ if (env.consumer_cnt != 1) {
+ fprintf(stderr, "rb-libbpf benchmark doesn't support multi-consumer!\n");
+ exit(1);
+ }
+
+ if (args.back2back && env.producer_cnt > 1) {
+ fprintf(stderr, "back-to-back mode makes sense only for single-producer case!\n");
+ exit(1);
+ }
+}
+
+static void *bufs_sample_producer(void *input)
+{
+ if (args.back2back) {
+ /* initial batch to get everything started */
+ bufs_trigger_batch();
+ return NULL;
+ }
+
+ while (true)
+ bufs_trigger_batch();
+ return NULL;
+}
+
+static struct ringbuf_libbpf_ctx {
+ struct ringbuf_bench *skel;
+ struct ring_buffer *ringbuf;
+} ringbuf_libbpf_ctx;
+
+static void ringbuf_libbpf_measure(struct bench_res *res)
+{
+ struct ringbuf_libbpf_ctx *ctx = &ringbuf_libbpf_ctx;
+
+ res->hits = atomic_swap(&buf_hits.value, 0);
+ res->drops = atomic_swap(&ctx->skel->bss->dropped, 0);
+}
+
+static struct ringbuf_bench *ringbuf_setup_skeleton()
+{
+ struct ringbuf_bench *skel;
+
+ setup_libbpf();
+
+ skel = ringbuf_bench__open();
+ if (!skel) {
+ fprintf(stderr, "failed to open skeleton\n");
+ exit(1);
+ }
+
+ skel->rodata->batch_cnt = args.batch_cnt;
+ skel->rodata->use_output = args.ringbuf_use_output ? 1 : 0;
+
+ if (args.sampled)
+ /* record data + header take 16 bytes */
+ skel->rodata->wakeup_data_size = args.sample_rate * 16;
+
+ bpf_map__resize(skel->maps.ringbuf, args.ringbuf_sz);
+
+ if (ringbuf_bench__load(skel)) {
+ fprintf(stderr, "failed to load skeleton\n");
+ exit(1);
+ }
+
+ return skel;
+}
+
+static int buf_process_sample(void *ctx, void *data, size_t len)
+{
+ atomic_inc(&buf_hits.value);
+ return 0;
+}
+
+static void ringbuf_libbpf_setup()
+{
+ struct ringbuf_libbpf_ctx *ctx = &ringbuf_libbpf_ctx;
+ struct bpf_link *link;
+
+ ctx->skel = ringbuf_setup_skeleton();
+ ctx->ringbuf = ring_buffer__new(bpf_map__fd(ctx->skel->maps.ringbuf),
+ buf_process_sample, NULL, NULL);
+ if (!ctx->ringbuf) {
+ fprintf(stderr, "failed to create ringbuf\n");
+ exit(1);
+ }
+
+ link = bpf_program__attach(ctx->skel->progs.bench_ringbuf);
+ if (IS_ERR(link)) {
+ fprintf(stderr, "failed to attach program!\n");
+ exit(1);
+ }
+}
+
+static void *ringbuf_libbpf_consumer(void *input)
+{
+ struct ringbuf_libbpf_ctx *ctx = &ringbuf_libbpf_ctx;
+
+ while (ring_buffer__poll(ctx->ringbuf, -1) >= 0) {
+ if (args.back2back)
+ bufs_trigger_batch();
+ }
+ fprintf(stderr, "ringbuf polling failed!\n");
+ return NULL;
+}
+
+/* RINGBUF-CUSTOM benchmark */
+struct ringbuf_custom {
+ __u64 *consumer_pos;
+ __u64 *producer_pos;
+ __u64 mask;
+ void *data;
+ int map_fd;
+};
+
+static struct ringbuf_custom_ctx {
+ struct ringbuf_bench *skel;
+ struct ringbuf_custom ringbuf;
+ int epoll_fd;
+ struct epoll_event event;
+} ringbuf_custom_ctx;
+
+static void ringbuf_custom_measure(struct bench_res *res)
+{
+ struct ringbuf_custom_ctx *ctx = &ringbuf_custom_ctx;
+
+ res->hits = atomic_swap(&buf_hits.value, 0);
+ res->drops = atomic_swap(&ctx->skel->bss->dropped, 0);
+}
+
+static void ringbuf_custom_setup()
+{
+ struct ringbuf_custom_ctx *ctx = &ringbuf_custom_ctx;
+ const size_t page_size = getpagesize();
+ struct bpf_link *link;
+ struct ringbuf_custom *r;
+ void *tmp;
+ int err;
+
+ ctx->skel = ringbuf_setup_skeleton();
+
+ ctx->epoll_fd = epoll_create1(EPOLL_CLOEXEC);
+ if (ctx->epoll_fd < 0) {
+ fprintf(stderr, "failed to create epoll fd: %d\n", -errno);
+ exit(1);
+ }
+
+ r = &ctx->ringbuf;
+ r->map_fd = bpf_map__fd(ctx->skel->maps.ringbuf);
+ r->mask = args.ringbuf_sz - 1;
+
+ /* Map writable consumer page */
+ tmp = mmap(NULL, page_size, PROT_READ | PROT_WRITE, MAP_SHARED,
+ r->map_fd, 0);
+ if (tmp == MAP_FAILED) {
+ fprintf(stderr, "failed to mmap consumer page: %d\n", -errno);
+ exit(1);
+ }
+ r->consumer_pos = tmp;
+
+ /* Map read-only producer page and data pages. */
+ tmp = mmap(NULL, page_size + 2 * args.ringbuf_sz, PROT_READ, MAP_SHARED,
+ r->map_fd, page_size);
+ if (tmp == MAP_FAILED) {
+ fprintf(stderr, "failed to mmap data pages: %d\n", -errno);
+ exit(1);
+ }
+ r->producer_pos = tmp;
+ r->data = tmp + page_size;
+
+ ctx->event.events = EPOLLIN;
+ err = epoll_ctl(ctx->epoll_fd, EPOLL_CTL_ADD, r->map_fd, &ctx->event);
+ if (err < 0) {
+ fprintf(stderr, "failed to epoll add ringbuf: %d\n", -errno);
+ exit(1);
+ }
+
+ link = bpf_program__attach(ctx->skel->progs.bench_ringbuf);
+ if (IS_ERR(link)) {
+ fprintf(stderr, "failed to attach program\n");
+ exit(1);
+ }
+}
+
+#define RINGBUF_BUSY_BIT (1 << 31)
+#define RINGBUF_DISCARD_BIT (1 << 30)
+#define RINGBUF_META_LEN 8
+
+static inline int roundup_len(__u32 len)
+{
+ /* clear out top 2 bits */
+ len <<= 2;
+ len >>= 2;
+ /* add length prefix */
+ len += RINGBUF_META_LEN;
+ /* round up to 8 byte alignment */
+ return (len + 7) / 8 * 8;
+}
+
+static void ringbuf_custom_process_ring(struct ringbuf_custom *r)
+{
+ unsigned long cons_pos, prod_pos;
+ int *len_ptr, len;
+ bool got_new_data;
+
+ cons_pos = smp_load_acquire(r->consumer_pos);
+ while (true) {
+ got_new_data = false;
+ prod_pos = smp_load_acquire(r->producer_pos);
+ while (cons_pos < prod_pos) {
+ len_ptr = r->data + (cons_pos & r->mask);
+ len = smp_load_acquire(len_ptr);
+
+ /* sample not committed yet, bail out for now */
+ if (len & RINGBUF_BUSY_BIT)
+ return;
+
+ got_new_data = true;
+ cons_pos += roundup_len(len);
+
+ atomic_inc(&buf_hits.value);
+ }
+ if (got_new_data)
+ smp_store_release(r->consumer_pos, cons_pos);
+ else
+ break;
+ };
+}
+
+static void *ringbuf_custom_consumer(void *input)
+{
+ struct ringbuf_custom_ctx *ctx = &ringbuf_custom_ctx;
+ int cnt;
+
+ do {
+ if (args.back2back)
+ bufs_trigger_batch();
+ cnt = epoll_wait(ctx->epoll_fd, &ctx->event, 1, -1);
+ if (cnt > 0)
+ ringbuf_custom_process_ring(&ctx->ringbuf);
+ } while (cnt >= 0);
+ fprintf(stderr, "ringbuf polling failed!\n");
+ return 0;
+}
+
+/* PERFBUF-LIBBPF benchmark */
+static struct perfbuf_libbpf_ctx {
+ struct perfbuf_bench *skel;
+ struct perf_buffer *perfbuf;
+} perfbuf_libbpf_ctx;
+
+static void perfbuf_measure(struct bench_res *res)
+{
+ struct perfbuf_libbpf_ctx *ctx = &perfbuf_libbpf_ctx;
+
+ res->hits = atomic_swap(&buf_hits.value, 0);
+ res->drops = atomic_swap(&ctx->skel->bss->dropped, 0);
+}
+
+static struct perfbuf_bench *perfbuf_setup_skeleton()
+{
+ struct perfbuf_bench *skel;
+
+ setup_libbpf();
+
+ skel = perfbuf_bench__open();
+ if (!skel) {
+ fprintf(stderr, "failed to open skeleton\n");
+ exit(1);
+ }
+
+ skel->rodata->batch_cnt = args.batch_cnt;
+
+ if (perfbuf_bench__load(skel)) {
+ fprintf(stderr, "failed to load skeleton\n");
+ exit(1);
+ }
+
+ return skel;
+}
+
+static enum bpf_perf_event_ret
+perfbuf_process_sample_raw(void *input_ctx, int cpu,
+ struct perf_event_header *e)
+{
+ switch (e->type) {
+ case PERF_RECORD_SAMPLE:
+ atomic_inc(&buf_hits.value);
+ break;
+ case PERF_RECORD_LOST:
+ break;
+ default:
+ return LIBBPF_PERF_EVENT_ERROR;
+ }
+ return LIBBPF_PERF_EVENT_CONT;
+}
+
+static void perfbuf_libbpf_setup()
+{
+ struct perfbuf_libbpf_ctx *ctx = &perfbuf_libbpf_ctx;
+ struct perf_event_attr attr;
+ struct perf_buffer_raw_opts pb_opts = {
+ .event_cb = perfbuf_process_sample_raw,
+ .ctx = (void *)(long)0,
+ .attr = &attr,
+ };
+ struct bpf_link *link;
+
+ ctx->skel = perfbuf_setup_skeleton();
+
+ memset(&attr, 0, sizeof(attr));
+ attr.config = PERF_COUNT_SW_BPF_OUTPUT,
+ attr.type = PERF_TYPE_SOFTWARE;
+ attr.sample_type = PERF_SAMPLE_RAW;
+ /* notify only every Nth sample */
+ if (args.sampled) {
+ attr.sample_period = args.sample_rate;
+ attr.wakeup_events = args.sample_rate;
+ } else {
+ attr.sample_period = 1;
+ attr.wakeup_events = 1;
+ }
+
+ if (args.sample_rate > args.batch_cnt) {
+ fprintf(stderr, "sample rate %d is too high for given batch count %d\n",
+ args.sample_rate, args.batch_cnt);
+ exit(1);
+ }
+
+ ctx->perfbuf = perf_buffer__new_raw(bpf_map__fd(ctx->skel->maps.perfbuf),
+ args.perfbuf_sz, &pb_opts);
+ if (!ctx->perfbuf) {
+ fprintf(stderr, "failed to create perfbuf\n");
+ exit(1);
+ }
+
+ link = bpf_program__attach(ctx->skel->progs.bench_perfbuf);
+ if (IS_ERR(link)) {
+ fprintf(stderr, "failed to attach program\n");
+ exit(1);
+ }
+}
+
+static void *perfbuf_libbpf_consumer(void *input)
+{
+ struct perfbuf_libbpf_ctx *ctx = &perfbuf_libbpf_ctx;
+
+ while (perf_buffer__poll(ctx->perfbuf, -1) >= 0) {
+ if (args.back2back)
+ bufs_trigger_batch();
+ }
+ fprintf(stderr, "perfbuf polling failed!\n");
+ return NULL;
+}
+
+/* PERFBUF-CUSTOM benchmark */
+
+/* copies of internal libbpf definitions */
+struct perf_cpu_buf {
+ struct perf_buffer *pb;
+ void *base; /* mmap()'ed memory */
+ void *buf; /* for reconstructing segmented data */
+ size_t buf_size;
+ int fd;
+ int cpu;
+ int map_key;
+};
+
+struct perf_buffer {
+ perf_buffer_event_fn event_cb;
+ perf_buffer_sample_fn sample_cb;
+ perf_buffer_lost_fn lost_cb;
+ void *ctx; /* passed into callbacks */
+
+ size_t page_size;
+ size_t mmap_size;
+ struct perf_cpu_buf **cpu_bufs;
+ struct epoll_event *events;
+ int cpu_cnt; /* number of allocated CPU buffers */
+ int epoll_fd; /* perf event FD */
+ int map_fd; /* BPF_MAP_TYPE_PERF_EVENT_ARRAY BPF map FD */
+};
+
+static void *perfbuf_custom_consumer(void *input)
+{
+ struct perfbuf_libbpf_ctx *ctx = &perfbuf_libbpf_ctx;
+ struct perf_buffer *pb = ctx->perfbuf;
+ struct perf_cpu_buf *cpu_buf;
+ struct perf_event_mmap_page *header;
+ size_t mmap_mask = pb->mmap_size - 1;
+ struct perf_event_header *ehdr;
+ __u64 data_head, data_tail;
+ size_t ehdr_size;
+ void *base;
+ int i, cnt;
+
+ while (true) {
+ if (args.back2back)
+ bufs_trigger_batch();
+ cnt = epoll_wait(pb->epoll_fd, pb->events, pb->cpu_cnt, -1);
+ if (cnt <= 0) {
+ fprintf(stderr, "perf epoll failed: %d\n", -errno);
+ exit(1);
+ }
+
+ for (i = 0; i < cnt; ++i) {
+ cpu_buf = pb->events[i].data.ptr;
+ header = cpu_buf->base;
+ base = ((void *)header) + pb->page_size;
+
+ data_head = ring_buffer_read_head(header);
+ data_tail = header->data_tail;
+ while (data_head != data_tail) {
+ ehdr = base + (data_tail & mmap_mask);
+ ehdr_size = ehdr->size;
+
+ if (ehdr->type == PERF_RECORD_SAMPLE)
+ atomic_inc(&buf_hits.value);
+
+ data_tail += ehdr_size;
+ }
+ ring_buffer_write_tail(header, data_tail);
+ }
+ }
+ return NULL;
+}
+
+const struct bench bench_rb_libbpf = {
+ .name = "rb-libbpf",
+ .validate = bufs_validate,
+ .setup = ringbuf_libbpf_setup,
+ .producer_thread = bufs_sample_producer,
+ .consumer_thread = ringbuf_libbpf_consumer,
+ .measure = ringbuf_libbpf_measure,
+ .report_progress = hits_drops_report_progress,
+ .report_final = hits_drops_report_final,
+};
+
+const struct bench bench_rb_custom = {
+ .name = "rb-custom",
+ .validate = bufs_validate,
+ .setup = ringbuf_custom_setup,
+ .producer_thread = bufs_sample_producer,
+ .consumer_thread = ringbuf_custom_consumer,
+ .measure = ringbuf_custom_measure,
+ .report_progress = hits_drops_report_progress,
+ .report_final = hits_drops_report_final,
+};
+
+const struct bench bench_pb_libbpf = {
+ .name = "pb-libbpf",
+ .validate = bufs_validate,
+ .setup = perfbuf_libbpf_setup,
+ .producer_thread = bufs_sample_producer,
+ .consumer_thread = perfbuf_libbpf_consumer,
+ .measure = perfbuf_measure,
+ .report_progress = hits_drops_report_progress,
+ .report_final = hits_drops_report_final,
+};
+
+const struct bench bench_pb_custom = {
+ .name = "pb-custom",
+ .validate = bufs_validate,
+ .setup = perfbuf_libbpf_setup,
+ .producer_thread = bufs_sample_producer,
+ .consumer_thread = perfbuf_custom_consumer,
+ .measure = perfbuf_measure,
+ .report_progress = hits_drops_report_progress,
+ .report_final = hits_drops_report_final,
+};
+
diff --git a/tools/testing/selftests/bpf/benchs/bench_trigger.c b/tools/testing/selftests/bpf/benchs/bench_trigger.c
new file mode 100644
index 000000000000..49c22832f216
--- /dev/null
+++ b/tools/testing/selftests/bpf/benchs/bench_trigger.c
@@ -0,0 +1,167 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#include "bench.h"
+#include "trigger_bench.skel.h"
+
+/* BPF triggering benchmarks */
+static struct trigger_ctx {
+ struct trigger_bench *skel;
+} ctx;
+
+static struct counter base_hits;
+
+static void trigger_validate()
+{
+ if (env.consumer_cnt != 1) {
+ fprintf(stderr, "benchmark doesn't support multi-consumer!\n");
+ exit(1);
+ }
+}
+
+static void *trigger_base_producer(void *input)
+{
+ while (true) {
+ (void)syscall(__NR_getpgid);
+ atomic_inc(&base_hits.value);
+ }
+ return NULL;
+}
+
+static void trigger_base_measure(struct bench_res *res)
+{
+ res->hits = atomic_swap(&base_hits.value, 0);
+}
+
+static void *trigger_producer(void *input)
+{
+ while (true)
+ (void)syscall(__NR_getpgid);
+ return NULL;
+}
+
+static void trigger_measure(struct bench_res *res)
+{
+ res->hits = atomic_swap(&ctx.skel->bss->hits, 0);
+}
+
+static void setup_ctx()
+{
+ setup_libbpf();
+
+ ctx.skel = trigger_bench__open_and_load();
+ if (!ctx.skel) {
+ fprintf(stderr, "failed to open skeleton\n");
+ exit(1);
+ }
+}
+
+static void attach_bpf(struct bpf_program *prog)
+{
+ struct bpf_link *link;
+
+ link = bpf_program__attach(prog);
+ if (IS_ERR(link)) {
+ fprintf(stderr, "failed to attach program!\n");
+ exit(1);
+ }
+}
+
+static void trigger_tp_setup()
+{
+ setup_ctx();
+ attach_bpf(ctx.skel->progs.bench_trigger_tp);
+}
+
+static void trigger_rawtp_setup()
+{
+ setup_ctx();
+ attach_bpf(ctx.skel->progs.bench_trigger_raw_tp);
+}
+
+static void trigger_kprobe_setup()
+{
+ setup_ctx();
+ attach_bpf(ctx.skel->progs.bench_trigger_kprobe);
+}
+
+static void trigger_fentry_setup()
+{
+ setup_ctx();
+ attach_bpf(ctx.skel->progs.bench_trigger_fentry);
+}
+
+static void trigger_fmodret_setup()
+{
+ setup_ctx();
+ attach_bpf(ctx.skel->progs.bench_trigger_fmodret);
+}
+
+static void *trigger_consumer(void *input)
+{
+ return NULL;
+}
+
+const struct bench bench_trig_base = {
+ .name = "trig-base",
+ .validate = trigger_validate,
+ .producer_thread = trigger_base_producer,
+ .consumer_thread = trigger_consumer,
+ .measure = trigger_base_measure,
+ .report_progress = hits_drops_report_progress,
+ .report_final = hits_drops_report_final,
+};
+
+const struct bench bench_trig_tp = {
+ .name = "trig-tp",
+ .validate = trigger_validate,
+ .setup = trigger_tp_setup,
+ .producer_thread = trigger_producer,
+ .consumer_thread = trigger_consumer,
+ .measure = trigger_measure,
+ .report_progress = hits_drops_report_progress,
+ .report_final = hits_drops_report_final,
+};
+
+const struct bench bench_trig_rawtp = {
+ .name = "trig-rawtp",
+ .validate = trigger_validate,
+ .setup = trigger_rawtp_setup,
+ .producer_thread = trigger_producer,
+ .consumer_thread = trigger_consumer,
+ .measure = trigger_measure,
+ .report_progress = hits_drops_report_progress,
+ .report_final = hits_drops_report_final,
+};
+
+const struct bench bench_trig_kprobe = {
+ .name = "trig-kprobe",
+ .validate = trigger_validate,
+ .setup = trigger_kprobe_setup,
+ .producer_thread = trigger_producer,
+ .consumer_thread = trigger_consumer,
+ .measure = trigger_measure,
+ .report_progress = hits_drops_report_progress,
+ .report_final = hits_drops_report_final,
+};
+
+const struct bench bench_trig_fentry = {
+ .name = "trig-fentry",
+ .validate = trigger_validate,
+ .setup = trigger_fentry_setup,
+ .producer_thread = trigger_producer,
+ .consumer_thread = trigger_consumer,
+ .measure = trigger_measure,
+ .report_progress = hits_drops_report_progress,
+ .report_final = hits_drops_report_final,
+};
+
+const struct bench bench_trig_fmodret = {
+ .name = "trig-fmodret",
+ .validate = trigger_validate,
+ .setup = trigger_fmodret_setup,
+ .producer_thread = trigger_producer,
+ .consumer_thread = trigger_consumer,
+ .measure = trigger_measure,
+ .report_progress = hits_drops_report_progress,
+ .report_final = hits_drops_report_final,
+};
diff --git a/tools/testing/selftests/bpf/benchs/run_bench_rename.sh b/tools/testing/selftests/bpf/benchs/run_bench_rename.sh
new file mode 100755
index 000000000000..16f774b1cdbe
--- /dev/null
+++ b/tools/testing/selftests/bpf/benchs/run_bench_rename.sh
@@ -0,0 +1,9 @@
+#!/bin/bash
+
+set -eufo pipefail
+
+for i in base kprobe kretprobe rawtp fentry fexit fmodret
+do
+ summary=$(sudo ./bench -w2 -d5 -a rename-$i | tail -n1 | cut -d'(' -f1 | cut -d' ' -f3-)
+ printf "%-10s: %s\n" $i "$summary"
+done
diff --git a/tools/testing/selftests/bpf/benchs/run_bench_ringbufs.sh b/tools/testing/selftests/bpf/benchs/run_bench_ringbufs.sh
new file mode 100755
index 000000000000..af4aa04caba6
--- /dev/null
+++ b/tools/testing/selftests/bpf/benchs/run_bench_ringbufs.sh
@@ -0,0 +1,75 @@
+#!/bin/bash
+
+set -eufo pipefail
+
+RUN_BENCH="sudo ./bench -w3 -d10 -a"
+
+function hits()
+{
+ echo "$*" | sed -E "s/.*hits\s+([0-9]+\.[0-9]+ ± [0-9]+\.[0-9]+M\/s).*/\1/"
+}
+
+function drops()
+{
+ echo "$*" | sed -E "s/.*drops\s+([0-9]+\.[0-9]+ ± [0-9]+\.[0-9]+M\/s).*/\1/"
+}
+
+function header()
+{
+ local len=${#1}
+
+ printf "\n%s\n" "$1"
+ for i in $(seq 1 $len); do printf '='; done
+ printf '\n'
+}
+
+function summarize()
+{
+ bench="$1"
+ summary=$(echo $2 | tail -n1)
+ printf "%-20s %s (drops %s)\n" "$bench" "$(hits $summary)" "$(drops $summary)"
+}
+
+header "Single-producer, parallel producer"
+for b in rb-libbpf rb-custom pb-libbpf pb-custom; do
+ summarize $b "$($RUN_BENCH $b)"
+done
+
+header "Single-producer, parallel producer, sampled notification"
+for b in rb-libbpf rb-custom pb-libbpf pb-custom; do
+ summarize $b "$($RUN_BENCH --rb-sampled $b)"
+done
+
+header "Single-producer, back-to-back mode"
+for b in rb-libbpf rb-custom pb-libbpf pb-custom; do
+ summarize $b "$($RUN_BENCH --rb-b2b $b)"
+ summarize $b-sampled "$($RUN_BENCH --rb-sampled --rb-b2b $b)"
+done
+
+header "Ringbuf back-to-back, effect of sample rate"
+for b in 1 5 10 25 50 100 250 500 1000 2000 3000; do
+ summarize "rb-sampled-$b" "$($RUN_BENCH --rb-b2b --rb-batch-cnt $b --rb-sampled --rb-sample-rate $b rb-custom)"
+done
+header "Perfbuf back-to-back, effect of sample rate"
+for b in 1 5 10 25 50 100 250 500 1000 2000 3000; do
+ summarize "pb-sampled-$b" "$($RUN_BENCH --rb-b2b --rb-batch-cnt $b --rb-sampled --rb-sample-rate $b pb-custom)"
+done
+
+header "Ringbuf back-to-back, reserve+commit vs output"
+summarize "reserve" "$($RUN_BENCH --rb-b2b rb-custom)"
+summarize "output" "$($RUN_BENCH --rb-b2b --rb-use-output rb-custom)"
+
+header "Ringbuf sampled, reserve+commit vs output"
+summarize "reserve-sampled" "$($RUN_BENCH --rb-sampled rb-custom)"
+summarize "output-sampled" "$($RUN_BENCH --rb-sampled --rb-use-output rb-custom)"
+
+header "Single-producer, consumer/producer competing on the same CPU, low batch count"
+for b in rb-libbpf rb-custom pb-libbpf pb-custom; do
+ summarize $b "$($RUN_BENCH --rb-batch-cnt 1 --rb-sample-rate 1 --prod-affinity 0 --cons-affinity 0 $b)"
+done
+
+header "Ringbuf, multi-producer contention"
+for b in 1 2 3 4 8 12 16 20 24 28 32 36 40 44 48 52; do
+ summarize "rb-libbpf nr_prod $b" "$($RUN_BENCH -p$b --rb-batch-cnt 50 rb-libbpf)"
+done
+
diff --git a/tools/testing/selftests/bpf/benchs/run_bench_trigger.sh b/tools/testing/selftests/bpf/benchs/run_bench_trigger.sh
new file mode 100755
index 000000000000..78e83f243294
--- /dev/null
+++ b/tools/testing/selftests/bpf/benchs/run_bench_trigger.sh
@@ -0,0 +1,9 @@
+#!/bin/bash
+
+set -eufo pipefail
+
+for i in base tp rawtp kprobe fentry fmodret
+do
+ summary=$(sudo ./bench -w2 -d5 -a trig-$i | tail -n1 | cut -d'(' -f1 | cut -d' ' -f3-)
+ printf "%-10s: %s\n" $i "$summary"
+done
diff --git a/tools/testing/selftests/bpf/bpf_tcp_helpers.h b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
index 8f21965ffc6c..5bf2fe9b1efa 100644
--- a/tools/testing/selftests/bpf/bpf_tcp_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
@@ -6,7 +6,7 @@
#include <linux/types.h>
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_core_read.h>
-#include "bpf_trace_helpers.h"
+#include <bpf/bpf_tracing.h>
#define BPF_STRUCT_OPS(name, args...) \
SEC("struct_ops/"#name) \
diff --git a/tools/testing/selftests/bpf/bpf_trace_helpers.h b/tools/testing/selftests/bpf/bpf_trace_helpers.h
deleted file mode 100644
index c6f1354d93fb..000000000000
--- a/tools/testing/selftests/bpf/bpf_trace_helpers.h
+++ /dev/null
@@ -1,120 +0,0 @@
-/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
-#ifndef __BPF_TRACE_HELPERS_H
-#define __BPF_TRACE_HELPERS_H
-
-#include <bpf/bpf_helpers.h>
-
-#define ___bpf_concat(a, b) a ## b
-#define ___bpf_apply(fn, n) ___bpf_concat(fn, n)
-#define ___bpf_nth(_, _1, _2, _3, _4, _5, _6, _7, _8, _9, _a, _b, _c, N, ...) N
-#define ___bpf_narg(...) \
- ___bpf_nth(_, ##__VA_ARGS__, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0)
-#define ___bpf_empty(...) \
- ___bpf_nth(_, ##__VA_ARGS__, N, N, N, N, N, N, N, N, N, N, 0)
-
-#define ___bpf_ctx_cast0() ctx
-#define ___bpf_ctx_cast1(x) ___bpf_ctx_cast0(), (void *)ctx[0]
-#define ___bpf_ctx_cast2(x, args...) ___bpf_ctx_cast1(args), (void *)ctx[1]
-#define ___bpf_ctx_cast3(x, args...) ___bpf_ctx_cast2(args), (void *)ctx[2]
-#define ___bpf_ctx_cast4(x, args...) ___bpf_ctx_cast3(args), (void *)ctx[3]
-#define ___bpf_ctx_cast5(x, args...) ___bpf_ctx_cast4(args), (void *)ctx[4]
-#define ___bpf_ctx_cast6(x, args...) ___bpf_ctx_cast5(args), (void *)ctx[5]
-#define ___bpf_ctx_cast7(x, args...) ___bpf_ctx_cast6(args), (void *)ctx[6]
-#define ___bpf_ctx_cast8(x, args...) ___bpf_ctx_cast7(args), (void *)ctx[7]
-#define ___bpf_ctx_cast9(x, args...) ___bpf_ctx_cast8(args), (void *)ctx[8]
-#define ___bpf_ctx_cast10(x, args...) ___bpf_ctx_cast9(args), (void *)ctx[9]
-#define ___bpf_ctx_cast11(x, args...) ___bpf_ctx_cast10(args), (void *)ctx[10]
-#define ___bpf_ctx_cast12(x, args...) ___bpf_ctx_cast11(args), (void *)ctx[11]
-#define ___bpf_ctx_cast(args...) \
- ___bpf_apply(___bpf_ctx_cast, ___bpf_narg(args))(args)
-
-/*
- * BPF_PROG is a convenience wrapper for generic tp_btf/fentry/fexit and
- * similar kinds of BPF programs, that accept input arguments as a single
- * pointer to untyped u64 array, where each u64 can actually be a typed
- * pointer or integer of different size. Instead of requring user to write
- * manual casts and work with array elements by index, BPF_PROG macro
- * allows user to declare a list of named and typed input arguments in the
- * same syntax as for normal C function. All the casting is hidden and
- * performed transparently, while user code can just assume working with
- * function arguments of specified type and name.
- *
- * Original raw context argument is preserved as well as 'ctx' argument.
- * This is useful when using BPF helpers that expect original context
- * as one of the parameters (e.g., for bpf_perf_event_output()).
- */
-#define BPF_PROG(name, args...) \
-name(unsigned long long *ctx); \
-static __always_inline typeof(name(0)) \
-____##name(unsigned long long *ctx, ##args); \
-typeof(name(0)) name(unsigned long long *ctx) \
-{ \
- _Pragma("GCC diagnostic push") \
- _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \
- return ____##name(___bpf_ctx_cast(args)); \
- _Pragma("GCC diagnostic pop") \
-} \
-static __always_inline typeof(name(0)) \
-____##name(unsigned long long *ctx, ##args)
-
-struct pt_regs;
-
-#define ___bpf_kprobe_args0() ctx
-#define ___bpf_kprobe_args1(x) \
- ___bpf_kprobe_args0(), (void *)PT_REGS_PARM1(ctx)
-#define ___bpf_kprobe_args2(x, args...) \
- ___bpf_kprobe_args1(args), (void *)PT_REGS_PARM2(ctx)
-#define ___bpf_kprobe_args3(x, args...) \
- ___bpf_kprobe_args2(args), (void *)PT_REGS_PARM3(ctx)
-#define ___bpf_kprobe_args4(x, args...) \
- ___bpf_kprobe_args3(args), (void *)PT_REGS_PARM4(ctx)
-#define ___bpf_kprobe_args5(x, args...) \
- ___bpf_kprobe_args4(args), (void *)PT_REGS_PARM5(ctx)
-#define ___bpf_kprobe_args(args...) \
- ___bpf_apply(___bpf_kprobe_args, ___bpf_narg(args))(args)
-
-/*
- * BPF_KPROBE serves the same purpose for kprobes as BPF_PROG for
- * tp_btf/fentry/fexit BPF programs. It hides the underlying platform-specific
- * low-level way of getting kprobe input arguments from struct pt_regs, and
- * provides a familiar typed and named function arguments syntax and
- * semantics of accessing kprobe input paremeters.
- *
- * Original struct pt_regs* context is preserved as 'ctx' argument. This might
- * be necessary when using BPF helpers like bpf_perf_event_output().
- */
-#define BPF_KPROBE(name, args...) \
-name(struct pt_regs *ctx); \
-static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args);\
-typeof(name(0)) name(struct pt_regs *ctx) \
-{ \
- _Pragma("GCC diagnostic push") \
- _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \
- return ____##name(___bpf_kprobe_args(args)); \
- _Pragma("GCC diagnostic pop") \
-} \
-static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args)
-
-#define ___bpf_kretprobe_args0() ctx
-#define ___bpf_kretprobe_argsN(x, args...) \
- ___bpf_kprobe_args(args), (void *)PT_REGS_RET(ctx)
-#define ___bpf_kretprobe_args(args...) \
- ___bpf_apply(___bpf_kretprobe_args, ___bpf_empty(args))(args)
-
-/*
- * BPF_KRETPROBE is similar to BPF_KPROBE, except, in addition to listing all
- * input kprobe arguments, one last extra argument has to be specified, which
- * captures kprobe return value.
- */
-#define BPF_KRETPROBE(name, args...) \
-name(struct pt_regs *ctx); \
-static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args);\
-typeof(name(0)) name(struct pt_regs *ctx) \
-{ \
- _Pragma("GCC diagnostic push") \
- _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \
- return ____##name(___bpf_kretprobe_args(args)); \
- _Pragma("GCC diagnostic pop") \
-} \
-static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args)
-#endif
diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config
index 5dc109f4c097..2118e23ac07a 100644
--- a/tools/testing/selftests/bpf/config
+++ b/tools/testing/selftests/bpf/config
@@ -25,6 +25,7 @@ CONFIG_XDP_SOCKETS=y
CONFIG_FTRACE_SYSCALLS=y
CONFIG_IPV6_TUNNEL=y
CONFIG_IPV6_GRE=y
+CONFIG_IPV6_SEG6_BPF=y
CONFIG_NET_FOU=m
CONFIG_NET_FOU_IP_TUNNELS=y
CONFIG_IPV6_FOU=m
@@ -35,3 +36,6 @@ CONFIG_MPLS_ROUTING=m
CONFIG_MPLS_IPTUNNEL=m
CONFIG_IPV6_SIT=m
CONFIG_BPF_JIT=y
+CONFIG_BPF_LSM=y
+CONFIG_SECURITY=y
+CONFIG_LIRC=y
diff --git a/tools/testing/selftests/bpf/include/uapi/linux/types.h b/tools/testing/selftests/bpf/include/uapi/linux/types.h
deleted file mode 100644
index 91fa51a9c31d..000000000000
--- a/tools/testing/selftests/bpf/include/uapi/linux/types.h
+++ /dev/null
@@ -1,23 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _UAPI_LINUX_TYPES_H
-#define _UAPI_LINUX_TYPES_H
-
-#include <asm-generic/int-ll64.h>
-
-/* copied from linux:include/uapi/linux/types.h */
-#define __bitwise
-typedef __u16 __bitwise __le16;
-typedef __u16 __bitwise __be16;
-typedef __u32 __bitwise __le32;
-typedef __u32 __bitwise __be32;
-typedef __u64 __bitwise __le64;
-typedef __u64 __bitwise __be64;
-
-typedef __u16 __bitwise __sum16;
-typedef __u32 __bitwise __wsum;
-
-#define __aligned_u64 __u64 __attribute__((aligned(8)))
-#define __aligned_be64 __be64 __attribute__((aligned(8)))
-#define __aligned_le64 __le64 __attribute__((aligned(8)))
-
-#endif /* _UAPI_LINUX_TYPES_H */
diff --git a/tools/testing/selftests/bpf/map_tests/.gitignore b/tools/testing/selftests/bpf/map_tests/.gitignore
index 45984a364647..89c4a3d37544 100644
--- a/tools/testing/selftests/bpf/map_tests/.gitignore
+++ b/tools/testing/selftests/bpf/map_tests/.gitignore
@@ -1 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
tests.h
diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c
new file mode 100644
index 000000000000..e36dd1a1780d
--- /dev/null
+++ b/tools/testing/selftests/bpf/network_helpers.c
@@ -0,0 +1,167 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <errno.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <string.h>
+#include <unistd.h>
+
+#include <arpa/inet.h>
+
+#include <sys/epoll.h>
+
+#include <linux/err.h>
+#include <linux/in.h>
+#include <linux/in6.h>
+
+#include "bpf_util.h"
+#include "network_helpers.h"
+
+#define clean_errno() (errno == 0 ? "None" : strerror(errno))
+#define log_err(MSG, ...) fprintf(stderr, "(%s:%d: errno: %s) " MSG "\n", \
+ __FILE__, __LINE__, clean_errno(), ##__VA_ARGS__)
+
+struct ipv4_packet pkt_v4 = {
+ .eth.h_proto = __bpf_constant_htons(ETH_P_IP),
+ .iph.ihl = 5,
+ .iph.protocol = IPPROTO_TCP,
+ .iph.tot_len = __bpf_constant_htons(MAGIC_BYTES),
+ .tcp.urg_ptr = 123,
+ .tcp.doff = 5,
+};
+
+struct ipv6_packet pkt_v6 = {
+ .eth.h_proto = __bpf_constant_htons(ETH_P_IPV6),
+ .iph.nexthdr = IPPROTO_TCP,
+ .iph.payload_len = __bpf_constant_htons(MAGIC_BYTES),
+ .tcp.urg_ptr = 123,
+ .tcp.doff = 5,
+};
+
+int start_server_with_port(int family, int type, __u16 port)
+{
+ struct sockaddr_storage addr = {};
+ socklen_t len;
+ int fd;
+
+ if (family == AF_INET) {
+ struct sockaddr_in *sin = (void *)&addr;
+
+ sin->sin_family = AF_INET;
+ sin->sin_port = htons(port);
+ len = sizeof(*sin);
+ } else {
+ struct sockaddr_in6 *sin6 = (void *)&addr;
+
+ sin6->sin6_family = AF_INET6;
+ sin6->sin6_port = htons(port);
+ len = sizeof(*sin6);
+ }
+
+ fd = socket(family, type | SOCK_NONBLOCK, 0);
+ if (fd < 0) {
+ log_err("Failed to create server socket");
+ return -1;
+ }
+
+ if (bind(fd, (const struct sockaddr *)&addr, len) < 0) {
+ log_err("Failed to bind socket");
+ close(fd);
+ return -1;
+ }
+
+ if (type == SOCK_STREAM) {
+ if (listen(fd, 1) < 0) {
+ log_err("Failed to listed on socket");
+ close(fd);
+ return -1;
+ }
+ }
+
+ return fd;
+}
+
+int start_server(int family, int type)
+{
+ return start_server_with_port(family, type, 0);
+}
+
+static const struct timeval timeo_sec = { .tv_sec = 3 };
+static const size_t timeo_optlen = sizeof(timeo_sec);
+
+int connect_to_fd(int family, int type, int server_fd)
+{
+ int fd, save_errno;
+
+ fd = socket(family, type, 0);
+ if (fd < 0) {
+ log_err("Failed to create client socket");
+ return -1;
+ }
+
+ if (connect_fd_to_fd(fd, server_fd) < 0 && errno != EINPROGRESS) {
+ save_errno = errno;
+ close(fd);
+ errno = save_errno;
+ return -1;
+ }
+
+ return fd;
+}
+
+int connect_fd_to_fd(int client_fd, int server_fd)
+{
+ struct sockaddr_storage addr;
+ socklen_t len = sizeof(addr);
+ int save_errno;
+
+ if (setsockopt(client_fd, SOL_SOCKET, SO_RCVTIMEO, &timeo_sec,
+ timeo_optlen)) {
+ log_err("Failed to set SO_RCVTIMEO");
+ return -1;
+ }
+
+ if (getsockname(server_fd, (struct sockaddr *)&addr, &len)) {
+ log_err("Failed to get server addr");
+ return -1;
+ }
+
+ if (connect(client_fd, (const struct sockaddr *)&addr, len) < 0) {
+ if (errno != EINPROGRESS) {
+ save_errno = errno;
+ log_err("Failed to connect to server");
+ errno = save_errno;
+ }
+ return -1;
+ }
+
+ return 0;
+}
+
+int connect_wait(int fd)
+{
+ struct epoll_event ev = {}, events[2];
+ int timeout_ms = 1000;
+ int efd, nfd;
+
+ efd = epoll_create1(EPOLL_CLOEXEC);
+ if (efd < 0) {
+ log_err("Failed to open epoll fd");
+ return -1;
+ }
+
+ ev.events = EPOLLRDHUP | EPOLLOUT;
+ ev.data.fd = fd;
+
+ if (epoll_ctl(efd, EPOLL_CTL_ADD, fd, &ev) < 0) {
+ log_err("Failed to register fd=%d on epoll fd=%d", fd, efd);
+ close(efd);
+ return -1;
+ }
+
+ nfd = epoll_wait(efd, events, ARRAY_SIZE(events), timeout_ms);
+ if (nfd < 0)
+ log_err("Failed to wait for I/O event on epoll fd=%d", efd);
+
+ close(efd);
+ return nfd;
+}
diff --git a/tools/testing/selftests/bpf/network_helpers.h b/tools/testing/selftests/bpf/network_helpers.h
new file mode 100644
index 000000000000..6a8009605670
--- /dev/null
+++ b/tools/testing/selftests/bpf/network_helpers.h
@@ -0,0 +1,42 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __NETWORK_HELPERS_H
+#define __NETWORK_HELPERS_H
+#include <sys/socket.h>
+#include <sys/types.h>
+#include <linux/types.h>
+typedef __u16 __sum16;
+#include <linux/if_ether.h>
+#include <linux/if_packet.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <netinet/tcp.h>
+#include <bpf/bpf_endian.h>
+
+#define MAGIC_VAL 0x1234
+#define NUM_ITER 100000
+#define VIP_NUM 5
+#define MAGIC_BYTES 123
+
+/* ipv4 test vector */
+struct ipv4_packet {
+ struct ethhdr eth;
+ struct iphdr iph;
+ struct tcphdr tcp;
+} __packed;
+extern struct ipv4_packet pkt_v4;
+
+/* ipv6 test vector */
+struct ipv6_packet {
+ struct ethhdr eth;
+ struct ipv6hdr iph;
+ struct tcphdr tcp;
+} __packed;
+extern struct ipv6_packet pkt_v6;
+
+int start_server(int family, int type);
+int start_server_with_port(int family, int type, __u16 port);
+int connect_to_fd(int family, int type, int server_fd);
+int connect_fd_to_fd(int client_fd, int server_fd);
+int connect_wait(int client_fd);
+
+#endif
diff --git a/tools/testing/selftests/bpf/prog_tests/.gitignore b/tools/testing/selftests/bpf/prog_tests/.gitignore
index 45984a364647..89c4a3d37544 100644
--- a/tools/testing/selftests/bpf/prog_tests/.gitignore
+++ b/tools/testing/selftests/bpf/prog_tests/.gitignore
@@ -1 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
tests.h
diff --git a/tools/testing/selftests/bpf/test_align.c b/tools/testing/selftests/bpf/prog_tests/align.c
index 0262f7b374f9..c548aded6585 100644
--- a/tools/testing/selftests/bpf/test_align.c
+++ b/tools/testing/selftests/bpf/prog_tests/align.c
@@ -1,24 +1,5 @@
-#include <asm/types.h>
-#include <linux/types.h>
-#include <stdint.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <unistd.h>
-#include <errno.h>
-#include <string.h>
-#include <stddef.h>
-#include <stdbool.h>
-
-#include <linux/unistd.h>
-#include <linux/filter.h>
-#include <linux/bpf_perf_event.h>
-#include <linux/bpf.h>
-
-#include <bpf/bpf.h>
-
-#include "../../../include/linux/filter.h"
-#include "bpf_rlimit.h"
-#include "bpf_util.h"
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
#define MAX_INSNS 512
#define MAX_MATCHES 16
@@ -359,15 +340,15 @@ static struct bpf_align_test tests[] = {
* is still (4n), fixed offset is not changed.
* Also, we create a new reg->id.
*/
- {29, "R5_w=pkt(id=4,off=18,r=0,umax_value=2040,var_off=(0x0; 0x7fc))"},
+ {29, "R5_w=pkt(id=4,off=18,r=0,umax_value=2040,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
* the total offset is 4-byte aligned and meets the
* load's requirements.
*/
- {33, "R4=pkt(id=4,off=22,r=22,umax_value=2040,var_off=(0x0; 0x7fc))"},
- {33, "R5=pkt(id=4,off=18,r=22,umax_value=2040,var_off=(0x0; 0x7fc))"},
+ {33, "R4=pkt(id=4,off=22,r=22,umax_value=2040,var_off=(0x0; 0x7fc)"},
+ {33, "R5=pkt(id=4,off=18,r=22,umax_value=2040,var_off=(0x0; 0x7fc)"},
},
},
{
@@ -410,15 +391,15 @@ static struct bpf_align_test tests[] = {
/* Adding 14 makes R6 be (4n+2) */
{9, "R6_w=inv(id=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"},
/* Packet pointer has (4n+2) offset */
- {11, "R5_w=pkt(id=1,off=0,r=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"},
- {13, "R4=pkt(id=1,off=4,r=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"},
+ {11, "R5_w=pkt(id=1,off=0,r=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc)"},
+ {13, "R4=pkt(id=1,off=4,r=0,umin_value=14,umax_value=1034,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
* the total offset is 4-byte aligned and meets the
* load's requirements.
*/
- {15, "R5=pkt(id=1,off=0,r=4,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"},
+ {15, "R5=pkt(id=1,off=0,r=4,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc)"},
/* Newly read value in R6 was shifted left by 2, so has
* known alignment of 4.
*/
@@ -426,15 +407,15 @@ static struct bpf_align_test tests[] = {
/* Added (4n) to packet pointer's (4n+2) var_off, giving
* another (4n+2).
*/
- {19, "R5_w=pkt(id=2,off=0,r=0,umin_value=14,umax_value=2054,var_off=(0x2; 0xffc))"},
- {21, "R4=pkt(id=2,off=4,r=0,umin_value=14,umax_value=2054,var_off=(0x2; 0xffc))"},
+ {19, "R5_w=pkt(id=2,off=0,r=0,umin_value=14,umax_value=2054,var_off=(0x2; 0xffc)"},
+ {21, "R4=pkt(id=2,off=4,r=0,umin_value=14,umax_value=2054,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)
* which is 2. Then the variable offset is (4n+2), so
* the total offset is 4-byte aligned and meets the
* load's requirements.
*/
- {23, "R5=pkt(id=2,off=0,r=4,umin_value=14,umax_value=2054,var_off=(0x2; 0xffc))"},
+ {23, "R5=pkt(id=2,off=0,r=4,umin_value=14,umax_value=2054,var_off=(0x2; 0xffc)"},
},
},
{
@@ -469,16 +450,16 @@ static struct bpf_align_test tests[] = {
.matches = {
{4, "R5_w=pkt_end(id=0,off=0,imm=0)"},
/* (ptr - ptr) << 2 == unknown, (4n) */
- {6, "R5_w=inv(id=0,smax_value=9223372036854775804,umax_value=18446744073709551612,var_off=(0x0; 0xfffffffffffffffc))"},
+ {6, "R5_w=inv(id=0,smax_value=9223372036854775804,umax_value=18446744073709551612,var_off=(0x0; 0xfffffffffffffffc)"},
/* (4n) + 14 == (4n+2). We blow our bounds, because
* the add could overflow.
*/
- {7, "R5_w=inv(id=0,var_off=(0x2; 0xfffffffffffffffc))"},
+ {7, "R5_w=inv(id=0,smin_value=-9223372036854775806,smax_value=9223372036854775806,umin_value=2,umax_value=18446744073709551614,var_off=(0x2; 0xfffffffffffffffc)"},
/* Checked s>=0 */
- {9, "R5=inv(id=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc))"},
+ {9, "R5=inv(id=0,umin_value=2,umax_value=9223372034707292158,var_off=(0x2; 0x7fffffff7ffffffc)"},
/* packet pointer + nonnegative (4n+2) */
- {11, "R6_w=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc))"},
- {13, "R4_w=pkt(id=1,off=4,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc))"},
+ {11, "R6_w=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372034707292158,var_off=(0x2; 0x7fffffff7ffffffc)"},
+ {13, "R4_w=pkt(id=1,off=4,r=0,umin_value=2,umax_value=9223372034707292158,var_off=(0x2; 0x7fffffff7ffffffc)"},
/* 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
@@ -486,7 +467,7 @@ static struct bpf_align_test tests[] = {
* So we did not get a 'range' on R6, and the access
* attempt will fail.
*/
- {15, "R6_w=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc))"},
+ {15, "R6_w=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372034707292158,var_off=(0x2; 0x7fffffff7ffffffc)"},
}
},
{
@@ -528,7 +509,7 @@ static struct bpf_align_test tests[] = {
/* New unknown value in R7 is (4n) */
{11, "R7_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
/* Subtracting it from R6 blows our unsigned bounds */
- {12, "R6=inv(id=0,smin_value=-1006,smax_value=1034,var_off=(0x2; 0xfffffffffffffffc))"},
+ {12, "R6=inv(id=0,smin_value=-1006,smax_value=1034,umin_value=2,umax_value=18446744073709551614,var_off=(0x2; 0xfffffffffffffffc)"},
/* Checked s>= 0 */
{14, "R6=inv(id=0,umin_value=2,umax_value=1034,var_off=(0x2; 0x7fc))"},
/* At the time the word size load is performed from R5,
@@ -537,7 +518,8 @@ static struct bpf_align_test tests[] = {
* the total offset is 4-byte aligned and meets the
* load's requirements.
*/
- {20, "R5=pkt(id=1,off=0,r=4,umin_value=2,umax_value=1034,var_off=(0x2; 0x7fc))"},
+ {20, "R5=pkt(id=1,off=0,r=4,umin_value=2,umax_value=1034,var_off=(0x2; 0x7fc)"},
+
},
},
{
@@ -579,18 +561,18 @@ static struct bpf_align_test tests[] = {
/* Adding 14 makes R6 be (4n+2) */
{11, "R6_w=inv(id=0,umin_value=14,umax_value=74,var_off=(0x2; 0x7c))"},
/* Subtracting from packet pointer overflows ubounds */
- {13, "R5_w=pkt(id=1,off=0,r=8,umin_value=18446744073709551542,umax_value=18446744073709551602,var_off=(0xffffffffffffff82; 0x7c))"},
+ {13, "R5_w=pkt(id=1,off=0,r=8,umin_value=18446744073709551542,umax_value=18446744073709551602,var_off=(0xffffffffffffff82; 0x7c)"},
/* New unknown value in R7 is (4n), >= 76 */
{15, "R7_w=inv(id=0,umin_value=76,umax_value=1096,var_off=(0x0; 0x7fc))"},
/* Adding it to packet pointer gives nice bounds again */
- {16, "R5_w=pkt(id=2,off=0,r=0,umin_value=2,umax_value=1082,var_off=(0x2; 0x7fc))"},
+ {16, "R5_w=pkt(id=2,off=0,r=0,umin_value=2,umax_value=1082,var_off=(0x2; 0xfffffffc)"},
/* 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
* the total offset is 4-byte aligned and meets the
* load's requirements.
*/
- {20, "R5=pkt(id=2,off=0,r=4,umin_value=2,umax_value=1082,var_off=(0x2; 0x7fc))"},
+ {20, "R5=pkt(id=2,off=0,r=4,umin_value=2,umax_value=1082,var_off=(0x2; 0xfffffffc)"},
},
},
};
@@ -669,51 +651,16 @@ static int do_test_single(struct bpf_align_test *test)
return ret;
}
-static int do_test(unsigned int from, unsigned int to)
+void test_align(void)
{
- int all_pass = 0;
- int all_fail = 0;
unsigned int i;
- for (i = from; i < to; i++) {
+ for (i = 0; i < ARRAY_SIZE(tests); i++) {
struct bpf_align_test *test = &tests[i];
- int fail;
- printf("Test %3d: %s ... ",
- i, test->descr);
- fail = do_test_single(test);
- if (fail) {
- all_fail++;
- printf("FAIL\n");
- } else {
- all_pass++;
- printf("PASS\n");
- }
- }
- printf("Results: %d pass %d fail\n",
- all_pass, all_fail);
- return all_fail ? EXIT_FAILURE : EXIT_SUCCESS;
-}
+ if (!test__start_subtest(test->descr))
+ continue;
-int main(int argc, char **argv)
-{
- unsigned int from = 0, to = ARRAY_SIZE(tests);
-
- if (argc == 3) {
- unsigned int l = atoi(argv[argc - 2]);
- unsigned int u = atoi(argv[argc - 1]);
-
- if (l < to && u < to) {
- from = l;
- to = u + 1;
- }
- } else if (argc == 2) {
- unsigned int t = atoi(argv[argc - 1]);
-
- if (t < to) {
- from = t;
- to = t + 1;
- }
+ CHECK_FAIL(do_test_single(test));
}
- return do_test(from, to);
}
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
new file mode 100644
index 000000000000..87c29dde1cf9
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
@@ -0,0 +1,409 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#include <test_progs.h>
+#include "bpf_iter_ipv6_route.skel.h"
+#include "bpf_iter_netlink.skel.h"
+#include "bpf_iter_bpf_map.skel.h"
+#include "bpf_iter_task.skel.h"
+#include "bpf_iter_task_file.skel.h"
+#include "bpf_iter_test_kern1.skel.h"
+#include "bpf_iter_test_kern2.skel.h"
+#include "bpf_iter_test_kern3.skel.h"
+#include "bpf_iter_test_kern4.skel.h"
+
+static int duration;
+
+static void test_btf_id_or_null(void)
+{
+ struct bpf_iter_test_kern3 *skel;
+
+ skel = bpf_iter_test_kern3__open_and_load();
+ if (CHECK(skel, "bpf_iter_test_kern3__open_and_load",
+ "skeleton open_and_load unexpectedly succeeded\n")) {
+ bpf_iter_test_kern3__destroy(skel);
+ return;
+ }
+}
+
+static void do_dummy_read(struct bpf_program *prog)
+{
+ struct bpf_link *link;
+ char buf[16] = {};
+ int iter_fd, len;
+
+ link = bpf_program__attach_iter(prog, NULL);
+ if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n"))
+ return;
+
+ iter_fd = bpf_iter_create(bpf_link__fd(link));
+ if (CHECK(iter_fd < 0, "create_iter", "create_iter failed\n"))
+ goto free_link;
+
+ /* not check contents, but ensure read() ends without error */
+ while ((len = read(iter_fd, buf, sizeof(buf))) > 0)
+ ;
+ CHECK(len < 0, "read", "read failed: %s\n", strerror(errno));
+
+ close(iter_fd);
+
+free_link:
+ bpf_link__destroy(link);
+}
+
+static void test_ipv6_route(void)
+{
+ struct bpf_iter_ipv6_route *skel;
+
+ skel = bpf_iter_ipv6_route__open_and_load();
+ if (CHECK(!skel, "bpf_iter_ipv6_route__open_and_load",
+ "skeleton open_and_load failed\n"))
+ return;
+
+ do_dummy_read(skel->progs.dump_ipv6_route);
+
+ bpf_iter_ipv6_route__destroy(skel);
+}
+
+static void test_netlink(void)
+{
+ struct bpf_iter_netlink *skel;
+
+ skel = bpf_iter_netlink__open_and_load();
+ if (CHECK(!skel, "bpf_iter_netlink__open_and_load",
+ "skeleton open_and_load failed\n"))
+ return;
+
+ do_dummy_read(skel->progs.dump_netlink);
+
+ bpf_iter_netlink__destroy(skel);
+}
+
+static void test_bpf_map(void)
+{
+ struct bpf_iter_bpf_map *skel;
+
+ skel = bpf_iter_bpf_map__open_and_load();
+ if (CHECK(!skel, "bpf_iter_bpf_map__open_and_load",
+ "skeleton open_and_load failed\n"))
+ return;
+
+ do_dummy_read(skel->progs.dump_bpf_map);
+
+ bpf_iter_bpf_map__destroy(skel);
+}
+
+static void test_task(void)
+{
+ struct bpf_iter_task *skel;
+
+ skel = bpf_iter_task__open_and_load();
+ if (CHECK(!skel, "bpf_iter_task__open_and_load",
+ "skeleton open_and_load failed\n"))
+ return;
+
+ do_dummy_read(skel->progs.dump_task);
+
+ bpf_iter_task__destroy(skel);
+}
+
+static void test_task_file(void)
+{
+ struct bpf_iter_task_file *skel;
+
+ skel = bpf_iter_task_file__open_and_load();
+ if (CHECK(!skel, "bpf_iter_task_file__open_and_load",
+ "skeleton open_and_load failed\n"))
+ return;
+
+ do_dummy_read(skel->progs.dump_task_file);
+
+ bpf_iter_task_file__destroy(skel);
+}
+
+/* The expected string is less than 16 bytes */
+static int do_read_with_fd(int iter_fd, const char *expected,
+ bool read_one_char)
+{
+ int err = -1, len, read_buf_len, start;
+ char buf[16] = {};
+
+ read_buf_len = read_one_char ? 1 : 16;
+ start = 0;
+ while ((len = read(iter_fd, buf + start, read_buf_len)) > 0) {
+ start += len;
+ if (CHECK(start >= 16, "read", "read len %d\n", len))
+ return -1;
+ read_buf_len = read_one_char ? 1 : 16 - start;
+ }
+ if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno)))
+ return -1;
+
+ err = strcmp(buf, expected);
+ if (CHECK(err, "read", "incorrect read result: buf %s, expected %s\n",
+ buf, expected))
+ return -1;
+
+ return 0;
+}
+
+static void test_anon_iter(bool read_one_char)
+{
+ struct bpf_iter_test_kern1 *skel;
+ struct bpf_link *link;
+ int iter_fd, err;
+
+ skel = bpf_iter_test_kern1__open_and_load();
+ if (CHECK(!skel, "bpf_iter_test_kern1__open_and_load",
+ "skeleton open_and_load failed\n"))
+ return;
+
+ err = bpf_iter_test_kern1__attach(skel);
+ if (CHECK(err, "bpf_iter_test_kern1__attach",
+ "skeleton attach failed\n")) {
+ goto out;
+ }
+
+ link = skel->links.dump_task;
+ iter_fd = bpf_iter_create(bpf_link__fd(link));
+ if (CHECK(iter_fd < 0, "create_iter", "create_iter failed\n"))
+ goto out;
+
+ do_read_with_fd(iter_fd, "abcd", read_one_char);
+ close(iter_fd);
+
+out:
+ bpf_iter_test_kern1__destroy(skel);
+}
+
+static int do_read(const char *path, const char *expected)
+{
+ int err, iter_fd;
+
+ iter_fd = open(path, O_RDONLY);
+ if (CHECK(iter_fd < 0, "open", "open %s failed: %s\n",
+ path, strerror(errno)))
+ return -1;
+
+ err = do_read_with_fd(iter_fd, expected, false);
+ close(iter_fd);
+ return err;
+}
+
+static void test_file_iter(void)
+{
+ const char *path = "/sys/fs/bpf/bpf_iter_test1";
+ struct bpf_iter_test_kern1 *skel1;
+ struct bpf_iter_test_kern2 *skel2;
+ struct bpf_link *link;
+ int err;
+
+ skel1 = bpf_iter_test_kern1__open_and_load();
+ if (CHECK(!skel1, "bpf_iter_test_kern1__open_and_load",
+ "skeleton open_and_load failed\n"))
+ return;
+
+ link = bpf_program__attach_iter(skel1->progs.dump_task, NULL);
+ if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n"))
+ goto out;
+
+ /* unlink this path if it exists. */
+ unlink(path);
+
+ err = bpf_link__pin(link, path);
+ if (CHECK(err, "pin_iter", "pin_iter to %s failed: %d\n", path, err))
+ goto free_link;
+
+ err = do_read(path, "abcd");
+ if (err)
+ goto unlink_path;
+
+ /* file based iterator seems working fine. Let us a link update
+ * of the underlying link and `cat` the iterator again, its content
+ * should change.
+ */
+ skel2 = bpf_iter_test_kern2__open_and_load();
+ if (CHECK(!skel2, "bpf_iter_test_kern2__open_and_load",
+ "skeleton open_and_load failed\n"))
+ goto unlink_path;
+
+ err = bpf_link__update_program(link, skel2->progs.dump_task);
+ if (CHECK(err, "update_prog", "update_prog failed\n"))
+ goto destroy_skel2;
+
+ do_read(path, "ABCD");
+
+destroy_skel2:
+ bpf_iter_test_kern2__destroy(skel2);
+unlink_path:
+ unlink(path);
+free_link:
+ bpf_link__destroy(link);
+out:
+ bpf_iter_test_kern1__destroy(skel1);
+}
+
+static void test_overflow(bool test_e2big_overflow, bool ret1)
+{
+ __u32 map_info_len, total_read_len, expected_read_len;
+ int err, iter_fd, map1_fd, map2_fd, len;
+ struct bpf_map_info map_info = {};
+ struct bpf_iter_test_kern4 *skel;
+ struct bpf_link *link;
+ __u32 page_size;
+ char *buf;
+
+ skel = bpf_iter_test_kern4__open();
+ if (CHECK(!skel, "bpf_iter_test_kern4__open",
+ "skeleton open failed\n"))
+ return;
+
+ /* create two maps: bpf program will only do bpf_seq_write
+ * for these two maps. The goal is one map output almost
+ * fills seq_file buffer and then the other will trigger
+ * overflow and needs restart.
+ */
+ map1_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, 4, 8, 1, 0);
+ if (CHECK(map1_fd < 0, "bpf_create_map",
+ "map_creation failed: %s\n", strerror(errno)))
+ goto out;
+ map2_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, 4, 8, 1, 0);
+ if (CHECK(map2_fd < 0, "bpf_create_map",
+ "map_creation failed: %s\n", strerror(errno)))
+ goto free_map1;
+
+ /* bpf_seq_printf kernel buffer is one page, so one map
+ * bpf_seq_write will mostly fill it, and the other map
+ * will partially fill and then trigger overflow and need
+ * bpf_seq_read restart.
+ */
+ page_size = sysconf(_SC_PAGE_SIZE);
+
+ if (test_e2big_overflow) {
+ skel->rodata->print_len = (page_size + 8) / 8;
+ expected_read_len = 2 * (page_size + 8);
+ } else if (!ret1) {
+ skel->rodata->print_len = (page_size - 8) / 8;
+ expected_read_len = 2 * (page_size - 8);
+ } else {
+ skel->rodata->print_len = 1;
+ expected_read_len = 2 * 8;
+ }
+ skel->rodata->ret1 = ret1;
+
+ if (CHECK(bpf_iter_test_kern4__load(skel),
+ "bpf_iter_test_kern4__load", "skeleton load failed\n"))
+ goto free_map2;
+
+ /* setup filtering map_id in bpf program */
+ map_info_len = sizeof(map_info);
+ err = bpf_obj_get_info_by_fd(map1_fd, &map_info, &map_info_len);
+ if (CHECK(err, "get_map_info", "get map info failed: %s\n",
+ strerror(errno)))
+ goto free_map2;
+ skel->bss->map1_id = map_info.id;
+
+ err = bpf_obj_get_info_by_fd(map2_fd, &map_info, &map_info_len);
+ if (CHECK(err, "get_map_info", "get map info failed: %s\n",
+ strerror(errno)))
+ goto free_map2;
+ skel->bss->map2_id = map_info.id;
+
+ link = bpf_program__attach_iter(skel->progs.dump_bpf_map, NULL);
+ if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n"))
+ goto free_map2;
+
+ iter_fd = bpf_iter_create(bpf_link__fd(link));
+ if (CHECK(iter_fd < 0, "create_iter", "create_iter failed\n"))
+ goto free_link;
+
+ buf = malloc(expected_read_len);
+ if (!buf)
+ goto close_iter;
+
+ /* do read */
+ total_read_len = 0;
+ if (test_e2big_overflow) {
+ while ((len = read(iter_fd, buf, expected_read_len)) > 0)
+ total_read_len += len;
+
+ CHECK(len != -1 || errno != E2BIG, "read",
+ "expected ret -1, errno E2BIG, but get ret %d, error %s\n",
+ len, strerror(errno));
+ goto free_buf;
+ } else if (!ret1) {
+ while ((len = read(iter_fd, buf, expected_read_len)) > 0)
+ total_read_len += len;
+
+ if (CHECK(len < 0, "read", "read failed: %s\n",
+ strerror(errno)))
+ goto free_buf;
+ } else {
+ do {
+ len = read(iter_fd, buf, expected_read_len);
+ if (len > 0)
+ total_read_len += len;
+ } while (len > 0 || len == -EAGAIN);
+
+ if (CHECK(len < 0, "read", "read failed: %s\n",
+ strerror(errno)))
+ goto free_buf;
+ }
+
+ if (CHECK(total_read_len != expected_read_len, "read",
+ "total len %u, expected len %u\n", total_read_len,
+ expected_read_len))
+ goto free_buf;
+
+ if (CHECK(skel->bss->map1_accessed != 1, "map1_accessed",
+ "expected 1 actual %d\n", skel->bss->map1_accessed))
+ goto free_buf;
+
+ if (CHECK(skel->bss->map2_accessed != 2, "map2_accessed",
+ "expected 2 actual %d\n", skel->bss->map2_accessed))
+ goto free_buf;
+
+ CHECK(skel->bss->map2_seqnum1 != skel->bss->map2_seqnum2,
+ "map2_seqnum", "two different seqnum %lld %lld\n",
+ skel->bss->map2_seqnum1, skel->bss->map2_seqnum2);
+
+free_buf:
+ free(buf);
+close_iter:
+ close(iter_fd);
+free_link:
+ bpf_link__destroy(link);
+free_map2:
+ close(map2_fd);
+free_map1:
+ close(map1_fd);
+out:
+ bpf_iter_test_kern4__destroy(skel);
+}
+
+void test_bpf_iter(void)
+{
+ if (test__start_subtest("btf_id_or_null"))
+ test_btf_id_or_null();
+ if (test__start_subtest("ipv6_route"))
+ test_ipv6_route();
+ if (test__start_subtest("netlink"))
+ test_netlink();
+ if (test__start_subtest("bpf_map"))
+ test_bpf_map();
+ if (test__start_subtest("task"))
+ test_task();
+ if (test__start_subtest("task_file"))
+ test_task_file();
+ if (test__start_subtest("anon"))
+ test_anon_iter(false);
+ if (test__start_subtest("anon-read-one-char"))
+ test_anon_iter(true);
+ if (test__start_subtest("file"))
+ test_file_iter();
+ if (test__start_subtest("overflow"))
+ test_overflow(false, false);
+ if (test__start_subtest("overflow-e2big"))
+ test_overflow(true, false);
+ if (test__start_subtest("prog-ret-1"))
+ test_overflow(false, true);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c b/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c
index f10029821e16..7afa4160416f 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c
@@ -1,26 +1,30 @@
// SPDX-License-Identifier: GPL-2.0
#include <test_progs.h>
+#define nr_iters 2
+
void test_bpf_obj_id(void)
{
const __u64 array_magic_value = 0xfaceb00c;
const __u32 array_key = 0;
- const int nr_iters = 2;
const char *file = "./test_obj_id.o";
const char *expected_prog_name = "test_obj_id";
const char *expected_map_name = "test_map_id";
const __u64 nsec_per_sec = 1000000000;
- struct bpf_object *objs[nr_iters];
+ struct bpf_object *objs[nr_iters] = {};
+ struct bpf_link *links[nr_iters] = {};
+ struct bpf_program *prog;
int prog_fds[nr_iters], map_fds[nr_iters];
/* +1 to test for the info_len returned by kernel */
struct bpf_prog_info prog_infos[nr_iters + 1];
struct bpf_map_info map_infos[nr_iters + 1];
+ struct bpf_link_info link_infos[nr_iters + 1];
/* Each prog only uses one map. +1 to test nr_map_ids
* returned by kernel.
*/
__u32 map_ids[nr_iters + 1];
- char jited_insns[128], xlated_insns[128], zeros[128];
+ char jited_insns[128], xlated_insns[128], zeros[128], tp_name[128];
__u32 i, next_id, info_len, nr_id_found, duration = 0;
struct timespec real_time_ts, boot_time_ts;
int err = 0;
@@ -36,14 +40,15 @@ void test_bpf_obj_id(void)
CHECK(err >= 0 || errno != ENOENT,
"get-fd-by-notexist-map-id", "err %d errno %d\n", err, errno);
- for (i = 0; i < nr_iters; i++)
- objs[i] = NULL;
+ err = bpf_link_get_fd_by_id(0);
+ CHECK(err >= 0 || errno != ENOENT,
+ "get-fd-by-notexist-link-id", "err %d errno %d\n", err, errno);
/* Check bpf_obj_get_info_by_fd() */
bzero(zeros, sizeof(zeros));
for (i = 0; i < nr_iters; i++) {
now = time(NULL);
- err = bpf_prog_load(file, BPF_PROG_TYPE_SOCKET_FILTER,
+ err = bpf_prog_load(file, BPF_PROG_TYPE_RAW_TRACEPOINT,
&objs[i], &prog_fds[i]);
/* test_obj_id.o is a dumb prog. It should never fail
* to load.
@@ -60,6 +65,17 @@ void test_bpf_obj_id(void)
if (CHECK_FAIL(err))
goto done;
+ prog = bpf_object__find_program_by_title(objs[i],
+ "raw_tp/sys_enter");
+ if (CHECK_FAIL(!prog))
+ goto done;
+ links[i] = bpf_program__attach(prog);
+ err = libbpf_get_error(links[i]);
+ if (CHECK(err, "prog_attach", "prog #%d, err %d\n", i, err)) {
+ links[i] = NULL;
+ goto done;
+ }
+
/* Check getting map info */
info_len = sizeof(struct bpf_map_info) * 2;
bzero(&map_infos[i], info_len);
@@ -107,7 +123,7 @@ void test_bpf_obj_id(void)
load_time = (real_time_ts.tv_sec - boot_time_ts.tv_sec)
+ (prog_infos[i].load_time / nsec_per_sec);
if (CHECK(err ||
- prog_infos[i].type != BPF_PROG_TYPE_SOCKET_FILTER ||
+ prog_infos[i].type != BPF_PROG_TYPE_RAW_TRACEPOINT ||
info_len != sizeof(struct bpf_prog_info) ||
(env.jit_enabled && !prog_infos[i].jited_prog_len) ||
(env.jit_enabled &&
@@ -120,7 +136,11 @@ void test_bpf_obj_id(void)
*(int *)(long)prog_infos[i].map_ids != map_infos[i].id ||
strcmp((char *)prog_infos[i].name, expected_prog_name),
"get-prog-info(fd)",
- "err %d errno %d i %d type %d(%d) info_len %u(%zu) jit_enabled %d jited_prog_len %u xlated_prog_len %u jited_prog %d xlated_prog %d load_time %lu(%lu) uid %u(%u) nr_map_ids %u(%u) map_id %u(%u) name %s(%s)\n",
+ "err %d errno %d i %d type %d(%d) info_len %u(%zu) "
+ "jit_enabled %d jited_prog_len %u xlated_prog_len %u "
+ "jited_prog %d xlated_prog %d load_time %lu(%lu) "
+ "uid %u(%u) nr_map_ids %u(%u) map_id %u(%u) "
+ "name %s(%s)\n",
err, errno, i,
prog_infos[i].type, BPF_PROG_TYPE_SOCKET_FILTER,
info_len, sizeof(struct bpf_prog_info),
@@ -135,6 +155,33 @@ void test_bpf_obj_id(void)
*(int *)(long)prog_infos[i].map_ids, map_infos[i].id,
prog_infos[i].name, expected_prog_name))
goto done;
+
+ /* Check getting link info */
+ info_len = sizeof(struct bpf_link_info) * 2;
+ bzero(&link_infos[i], info_len);
+ link_infos[i].raw_tracepoint.tp_name = (__u64)&tp_name;
+ link_infos[i].raw_tracepoint.tp_name_len = sizeof(tp_name);
+ err = bpf_obj_get_info_by_fd(bpf_link__fd(links[i]),
+ &link_infos[i], &info_len);
+ if (CHECK(err ||
+ link_infos[i].type != BPF_LINK_TYPE_RAW_TRACEPOINT ||
+ link_infos[i].prog_id != prog_infos[i].id ||
+ link_infos[i].raw_tracepoint.tp_name != (__u64)&tp_name ||
+ strcmp((char *)link_infos[i].raw_tracepoint.tp_name,
+ "sys_enter") ||
+ info_len != sizeof(struct bpf_link_info),
+ "get-link-info(fd)",
+ "err %d errno %d info_len %u(%zu) type %d(%d) id %d "
+ "prog_id %d (%d) tp_name %s(%s)\n",
+ err, errno,
+ info_len, sizeof(struct bpf_link_info),
+ link_infos[i].type, BPF_LINK_TYPE_RAW_TRACEPOINT,
+ link_infos[i].id,
+ link_infos[i].prog_id, prog_infos[i].id,
+ (char *)link_infos[i].raw_tracepoint.tp_name,
+ "sys_enter"))
+ goto done;
+
}
/* Check bpf_prog_get_next_id() */
@@ -247,7 +294,52 @@ void test_bpf_obj_id(void)
"nr_id_found %u(%u)\n",
nr_id_found, nr_iters);
+ /* Check bpf_link_get_next_id() */
+ nr_id_found = 0;
+ next_id = 0;
+ while (!bpf_link_get_next_id(next_id, &next_id)) {
+ struct bpf_link_info link_info;
+ int link_fd, cmp_res;
+
+ info_len = sizeof(link_info);
+ memset(&link_info, 0, info_len);
+
+ link_fd = bpf_link_get_fd_by_id(next_id);
+ if (link_fd < 0 && errno == ENOENT)
+ /* The bpf_link is in the dead row */
+ continue;
+ if (CHECK(link_fd < 0, "get-link-fd(next_id)",
+ "link_fd %d next_id %u errno %d\n",
+ link_fd, next_id, errno))
+ break;
+
+ for (i = 0; i < nr_iters; i++)
+ if (link_infos[i].id == next_id)
+ break;
+
+ if (i == nr_iters)
+ continue;
+
+ nr_id_found++;
+
+ err = bpf_obj_get_info_by_fd(link_fd, &link_info, &info_len);
+ cmp_res = memcmp(&link_info, &link_infos[i],
+ offsetof(struct bpf_link_info, raw_tracepoint));
+ CHECK(err || info_len != sizeof(link_info) || cmp_res,
+ "check get-link-info(next_id->fd)",
+ "err %d errno %d info_len %u(%zu) memcmp %d\n",
+ err, errno, info_len, sizeof(struct bpf_link_info),
+ cmp_res);
+
+ close(link_fd);
+ }
+ CHECK(nr_id_found != nr_iters,
+ "check total link id found by get_next_id",
+ "nr_id_found %u(%u)\n", nr_id_found, nr_iters);
+
done:
- for (i = 0; i < nr_iters; i++)
+ for (i = 0; i < nr_iters; i++) {
+ bpf_link__destroy(links[i]);
bpf_object__close(objs[i]);
+ }
}
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
index 8482bbc67eec..9a8f47fc0b91 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
@@ -11,6 +11,7 @@
static const unsigned int total_bytes = 10 * 1024 * 1024;
static const struct timeval timeo_sec = { .tv_sec = 10 };
static const size_t timeo_optlen = sizeof(timeo_sec);
+static int expected_stg = 0xeB9F;
static int stop, duration;
static int settimeo(int fd)
@@ -88,7 +89,7 @@ done:
return NULL;
}
-static void do_test(const char *tcp_ca)
+static void do_test(const char *tcp_ca, const struct bpf_map *sk_stg_map)
{
struct sockaddr_in6 sa6 = {};
ssize_t nr_recv = 0, bytes = 0;
@@ -126,14 +127,34 @@ static void do_test(const char *tcp_ca)
err = listen(lfd, 1);
if (CHECK(err == -1, "listen", "errno:%d\n", errno))
goto done;
- err = pthread_create(&srv_thread, NULL, server, (void *)(long)lfd);
- if (CHECK(err != 0, "pthread_create", "err:%d\n", err))
- goto done;
+
+ if (sk_stg_map) {
+ err = bpf_map_update_elem(bpf_map__fd(sk_stg_map), &fd,
+ &expected_stg, BPF_NOEXIST);
+ if (CHECK(err, "bpf_map_update_elem(sk_stg_map)",
+ "err:%d errno:%d\n", err, errno))
+ goto done;
+ }
/* connect to server */
err = connect(fd, (struct sockaddr *)&sa6, addrlen);
if (CHECK(err == -1, "connect", "errno:%d\n", errno))
- goto wait_thread;
+ goto done;
+
+ if (sk_stg_map) {
+ int tmp_stg;
+
+ err = bpf_map_lookup_elem(bpf_map__fd(sk_stg_map), &fd,
+ &tmp_stg);
+ if (CHECK(!err || errno != ENOENT,
+ "bpf_map_lookup_elem(sk_stg_map)",
+ "err:%d errno:%d\n", err, errno))
+ goto done;
+ }
+
+ err = pthread_create(&srv_thread, NULL, server, (void *)(long)lfd);
+ if (CHECK(err != 0, "pthread_create", "err:%d errno:%d\n", err, errno))
+ goto done;
/* recv total_bytes */
while (bytes < total_bytes && !READ_ONCE(stop)) {
@@ -149,7 +170,6 @@ static void do_test(const char *tcp_ca)
CHECK(bytes != total_bytes, "recv", "%zd != %u nr_recv:%zd errno:%d\n",
bytes, total_bytes, nr_recv, errno);
-wait_thread:
WRITE_ONCE(stop, 1);
pthread_join(srv_thread, &thread_ret);
CHECK(IS_ERR(thread_ret), "pthread_join", "thread_ret:%ld",
@@ -175,7 +195,7 @@ static void test_cubic(void)
return;
}
- do_test("bpf_cubic");
+ do_test("bpf_cubic", NULL);
bpf_link__destroy(link);
bpf_cubic__destroy(cubic_skel);
@@ -197,7 +217,10 @@ static void test_dctcp(void)
return;
}
- do_test("bpf_dctcp");
+ do_test("bpf_dctcp", dctcp_skel->maps.sk_stg_map);
+ CHECK(dctcp_skel->bss->stg_result != expected_stg,
+ "Unexpected stg_result", "stg_result (%x) != expected_stg (%x)\n",
+ dctcp_skel->bss->stg_result, expected_stg);
bpf_link__destroy(link);
bpf_dctcp__destroy(dctcp_skel);
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_dump.c b/tools/testing/selftests/bpf/prog_tests/btf_dump.c
index 7390d3061065..cb33a7ee4e04 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_dump.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_dump.c
@@ -125,6 +125,6 @@ void test_btf_dump() {
if (!test__start_subtest(t->name))
continue;
- test_btf_dump_case(i, &btf_dump_test_cases[i]);
+ test_btf_dump_case(i, &btf_dump_test_cases[i]);
}
}
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c b/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c
new file mode 100644
index 000000000000..f7ee8fa377ad
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c
@@ -0,0 +1,49 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+
+#include <test_progs.h>
+
+#include "test_btf_map_in_map.skel.h"
+
+void test_btf_map_in_map(void)
+{
+ int duration = 0, err, key = 0, val;
+ struct test_btf_map_in_map* skel;
+
+ skel = test_btf_map_in_map__open_and_load();
+ if (CHECK(!skel, "skel_open", "failed to open&load skeleton\n"))
+ return;
+
+ err = test_btf_map_in_map__attach(skel);
+ if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err))
+ goto cleanup;
+
+ /* inner1 = input, inner2 = input + 1 */
+ val = bpf_map__fd(skel->maps.inner_map1);
+ bpf_map_update_elem(bpf_map__fd(skel->maps.outer_arr), &key, &val, 0);
+ val = bpf_map__fd(skel->maps.inner_map2);
+ bpf_map_update_elem(bpf_map__fd(skel->maps.outer_hash), &key, &val, 0);
+ skel->bss->input = 1;
+ usleep(1);
+
+ bpf_map_lookup_elem(bpf_map__fd(skel->maps.inner_map1), &key, &val);
+ CHECK(val != 1, "inner1", "got %d != exp %d\n", val, 1);
+ bpf_map_lookup_elem(bpf_map__fd(skel->maps.inner_map2), &key, &val);
+ CHECK(val != 2, "inner2", "got %d != exp %d\n", val, 2);
+
+ /* inner1 = input + 1, inner2 = input */
+ val = bpf_map__fd(skel->maps.inner_map2);
+ bpf_map_update_elem(bpf_map__fd(skel->maps.outer_arr), &key, &val, 0);
+ val = bpf_map__fd(skel->maps.inner_map1);
+ bpf_map_update_elem(bpf_map__fd(skel->maps.outer_hash), &key, &val, 0);
+ skel->bss->input = 3;
+ usleep(1);
+
+ bpf_map_lookup_elem(bpf_map__fd(skel->maps.inner_map1), &key, &val);
+ CHECK(val != 4, "inner1", "got %d != exp %d\n", val, 4);
+ bpf_map_lookup_elem(bpf_map__fd(skel->maps.inner_map2), &key, &val);
+ CHECK(val != 3, "inner2", "got %d != exp %d\n", val, 3);
+
+cleanup:
+ test_btf_map_in_map__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_autodetach.c b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_autodetach.c
index 5b13f2c6c402..70e94e783070 100644
--- a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_autodetach.c
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_autodetach.c
@@ -6,7 +6,7 @@
#define PING_CMD "ping -q -c1 -w1 127.0.0.1 > /dev/null"
-char bpf_log_buf[BPF_LOG_BUF_SIZE];
+static char bpf_log_buf[BPF_LOG_BUF_SIZE];
static int prog_load(void)
{
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c
index 2ff21dbce179..139f8e82c7c6 100644
--- a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c
@@ -6,7 +6,7 @@
#define PING_CMD "ping -q -c1 -w1 127.0.0.1 > /dev/null"
-char bpf_log_buf[BPF_LOG_BUF_SIZE];
+static char bpf_log_buf[BPF_LOG_BUF_SIZE];
static int map_fd = -1;
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_override.c b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_override.c
index 9d8cb48b99de..9e96f8d87fea 100644
--- a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_override.c
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_override.c
@@ -8,7 +8,7 @@
#define BAR "/foo/bar/"
#define PING_CMD "ping -q -c1 -w1 127.0.0.1 > /dev/null"
-char bpf_log_buf[BPF_LOG_BUF_SIZE];
+static char bpf_log_buf[BPF_LOG_BUF_SIZE];
static int prog_load(int verdict)
{
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_link.c b/tools/testing/selftests/bpf/prog_tests/cgroup_link.c
new file mode 100644
index 000000000000..6e04f8d1d15b
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_link.c
@@ -0,0 +1,244 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+#include "cgroup_helpers.h"
+#include "test_cgroup_link.skel.h"
+
+static __u32 duration = 0;
+#define PING_CMD "ping -q -c1 -w1 127.0.0.1 > /dev/null"
+
+static struct test_cgroup_link *skel = NULL;
+
+int ping_and_check(int exp_calls, int exp_alt_calls)
+{
+ skel->bss->calls = 0;
+ skel->bss->alt_calls = 0;
+ CHECK_FAIL(system(PING_CMD));
+ if (CHECK(skel->bss->calls != exp_calls, "call_cnt",
+ "exp %d, got %d\n", exp_calls, skel->bss->calls))
+ return -EINVAL;
+ if (CHECK(skel->bss->alt_calls != exp_alt_calls, "alt_call_cnt",
+ "exp %d, got %d\n", exp_alt_calls, skel->bss->alt_calls))
+ return -EINVAL;
+ return 0;
+}
+
+void test_cgroup_link(void)
+{
+ struct {
+ const char *path;
+ int fd;
+ } cgs[] = {
+ { "/cg1" },
+ { "/cg1/cg2" },
+ { "/cg1/cg2/cg3" },
+ { "/cg1/cg2/cg3/cg4" },
+ };
+ int last_cg = ARRAY_SIZE(cgs) - 1, cg_nr = ARRAY_SIZE(cgs);
+ DECLARE_LIBBPF_OPTS(bpf_link_update_opts, link_upd_opts);
+ struct bpf_link *links[ARRAY_SIZE(cgs)] = {}, *tmp_link;
+ __u32 prog_ids[ARRAY_SIZE(cgs)], prog_cnt = 0, attach_flags;
+ int i = 0, err, prog_fd;
+ bool detach_legacy = false;
+
+ skel = test_cgroup_link__open_and_load();
+ if (CHECK(!skel, "skel_open_load", "failed to open/load skeleton\n"))
+ return;
+ prog_fd = bpf_program__fd(skel->progs.egress);
+
+ err = setup_cgroup_environment();
+ if (CHECK(err, "cg_init", "failed: %d\n", err))
+ goto cleanup;
+
+ for (i = 0; i < cg_nr; i++) {
+ cgs[i].fd = create_and_get_cgroup(cgs[i].path);
+ if (CHECK(cgs[i].fd < 0, "cg_create", "fail: %d\n", cgs[i].fd))
+ goto cleanup;
+ }
+
+ err = join_cgroup(cgs[last_cg].path);
+ if (CHECK(err, "cg_join", "fail: %d\n", err))
+ goto cleanup;
+
+ for (i = 0; i < cg_nr; i++) {
+ links[i] = bpf_program__attach_cgroup(skel->progs.egress,
+ cgs[i].fd);
+ if (CHECK(IS_ERR(links[i]), "cg_attach", "i: %d, err: %ld\n",
+ i, PTR_ERR(links[i])))
+ goto cleanup;
+ }
+
+ ping_and_check(cg_nr, 0);
+
+ /* query the number of effective progs and attach flags in root cg */
+ err = bpf_prog_query(cgs[0].fd, BPF_CGROUP_INET_EGRESS,
+ BPF_F_QUERY_EFFECTIVE, &attach_flags, NULL,
+ &prog_cnt);
+ CHECK_FAIL(err);
+ CHECK_FAIL(attach_flags != BPF_F_ALLOW_MULTI);
+ if (CHECK(prog_cnt != 1, "effect_cnt", "exp %d, got %d\n", 1, prog_cnt))
+ goto cleanup;
+
+ /* query the number of effective progs in last cg */
+ err = bpf_prog_query(cgs[last_cg].fd, BPF_CGROUP_INET_EGRESS,
+ BPF_F_QUERY_EFFECTIVE, NULL, NULL,
+ &prog_cnt);
+ CHECK_FAIL(err);
+ CHECK_FAIL(attach_flags != BPF_F_ALLOW_MULTI);
+ if (CHECK(prog_cnt != cg_nr, "effect_cnt", "exp %d, got %d\n",
+ cg_nr, prog_cnt))
+ goto cleanup;
+
+ /* query the effective prog IDs in last cg */
+ err = bpf_prog_query(cgs[last_cg].fd, BPF_CGROUP_INET_EGRESS,
+ BPF_F_QUERY_EFFECTIVE, &attach_flags,
+ prog_ids, &prog_cnt);
+ CHECK_FAIL(err);
+ CHECK_FAIL(attach_flags != BPF_F_ALLOW_MULTI);
+ if (CHECK(prog_cnt != cg_nr, "effect_cnt", "exp %d, got %d\n",
+ cg_nr, prog_cnt))
+ goto cleanup;
+ for (i = 1; i < prog_cnt; i++) {
+ CHECK(prog_ids[i - 1] != prog_ids[i], "prog_id_check",
+ "idx %d, prev id %d, cur id %d\n",
+ i, prog_ids[i - 1], prog_ids[i]);
+ }
+
+ /* detach bottom program and ping again */
+ bpf_link__destroy(links[last_cg]);
+ links[last_cg] = NULL;
+
+ ping_and_check(cg_nr - 1, 0);
+
+ /* mix in with non link-based multi-attachments */
+ err = bpf_prog_attach(prog_fd, cgs[last_cg].fd,
+ BPF_CGROUP_INET_EGRESS, BPF_F_ALLOW_MULTI);
+ if (CHECK(err, "cg_attach_legacy", "errno=%d\n", errno))
+ goto cleanup;
+ detach_legacy = true;
+
+ links[last_cg] = bpf_program__attach_cgroup(skel->progs.egress,
+ cgs[last_cg].fd);
+ if (CHECK(IS_ERR(links[last_cg]), "cg_attach", "err: %ld\n",
+ PTR_ERR(links[last_cg])))
+ goto cleanup;
+
+ ping_and_check(cg_nr + 1, 0);
+
+ /* detach link */
+ bpf_link__destroy(links[last_cg]);
+ links[last_cg] = NULL;
+
+ /* detach legacy */
+ err = bpf_prog_detach2(prog_fd, cgs[last_cg].fd, BPF_CGROUP_INET_EGRESS);
+ if (CHECK(err, "cg_detach_legacy", "errno=%d\n", errno))
+ goto cleanup;
+ detach_legacy = false;
+
+ /* attach legacy exclusive prog attachment */
+ err = bpf_prog_attach(prog_fd, cgs[last_cg].fd,
+ BPF_CGROUP_INET_EGRESS, 0);
+ if (CHECK(err, "cg_attach_exclusive", "errno=%d\n", errno))
+ goto cleanup;
+ detach_legacy = true;
+
+ /* attempt to mix in with multi-attach bpf_link */
+ tmp_link = bpf_program__attach_cgroup(skel->progs.egress,
+ cgs[last_cg].fd);
+ if (CHECK(!IS_ERR(tmp_link), "cg_attach_fail", "unexpected success!\n")) {
+ bpf_link__destroy(tmp_link);
+ goto cleanup;
+ }
+
+ ping_and_check(cg_nr, 0);
+
+ /* detach */
+ err = bpf_prog_detach2(prog_fd, cgs[last_cg].fd, BPF_CGROUP_INET_EGRESS);
+ if (CHECK(err, "cg_detach_legacy", "errno=%d\n", errno))
+ goto cleanup;
+ detach_legacy = false;
+
+ ping_and_check(cg_nr - 1, 0);
+
+ /* attach back link-based one */
+ links[last_cg] = bpf_program__attach_cgroup(skel->progs.egress,
+ cgs[last_cg].fd);
+ if (CHECK(IS_ERR(links[last_cg]), "cg_attach", "err: %ld\n",
+ PTR_ERR(links[last_cg])))
+ goto cleanup;
+
+ ping_and_check(cg_nr, 0);
+
+ /* check legacy exclusive prog can't be attached */
+ err = bpf_prog_attach(prog_fd, cgs[last_cg].fd,
+ BPF_CGROUP_INET_EGRESS, 0);
+ if (CHECK(!err, "cg_attach_exclusive", "unexpected success")) {
+ bpf_prog_detach2(prog_fd, cgs[last_cg].fd, BPF_CGROUP_INET_EGRESS);
+ goto cleanup;
+ }
+
+ /* replace BPF programs inside their links for all but first link */
+ for (i = 1; i < cg_nr; i++) {
+ err = bpf_link__update_program(links[i], skel->progs.egress_alt);
+ if (CHECK(err, "prog_upd", "link #%d\n", i))
+ goto cleanup;
+ }
+
+ ping_and_check(1, cg_nr - 1);
+
+ /* Attempt program update with wrong expected BPF program */
+ link_upd_opts.old_prog_fd = bpf_program__fd(skel->progs.egress_alt);
+ link_upd_opts.flags = BPF_F_REPLACE;
+ err = bpf_link_update(bpf_link__fd(links[0]),
+ bpf_program__fd(skel->progs.egress_alt),
+ &link_upd_opts);
+ if (CHECK(err == 0 || errno != EPERM, "prog_cmpxchg1",
+ "unexpectedly succeeded, err %d, errno %d\n", err, -errno))
+ goto cleanup;
+
+ /* Compare-exchange single link program from egress to egress_alt */
+ link_upd_opts.old_prog_fd = bpf_program__fd(skel->progs.egress);
+ link_upd_opts.flags = BPF_F_REPLACE;
+ err = bpf_link_update(bpf_link__fd(links[0]),
+ bpf_program__fd(skel->progs.egress_alt),
+ &link_upd_opts);
+ if (CHECK(err, "prog_cmpxchg2", "errno %d\n", -errno))
+ goto cleanup;
+
+ /* ping */
+ ping_and_check(0, cg_nr);
+
+ /* close cgroup FDs before detaching links */
+ for (i = 0; i < cg_nr; i++) {
+ if (cgs[i].fd > 0) {
+ close(cgs[i].fd);
+ cgs[i].fd = -1;
+ }
+ }
+
+ /* BPF programs should still get called */
+ ping_and_check(0, cg_nr);
+
+ /* leave cgroup and remove them, don't detach programs */
+ cleanup_cgroup_environment();
+
+ /* BPF programs should have been auto-detached */
+ ping_and_check(0, 0);
+
+cleanup:
+ if (detach_legacy)
+ bpf_prog_detach2(prog_fd, cgs[last_cg].fd,
+ BPF_CGROUP_INET_EGRESS);
+
+ for (i = 0; i < cg_nr; i++) {
+ if (!IS_ERR(links[i]))
+ bpf_link__destroy(links[i]);
+ }
+ test_cgroup_link__destroy(skel);
+
+ for (i = 0; i < cg_nr; i++) {
+ if (cgs[i].fd > 0)
+ close(cgs[i].fd);
+ }
+ cleanup_cgroup_environment();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_skb_sk_lookup.c b/tools/testing/selftests/bpf/prog_tests/cgroup_skb_sk_lookup.c
new file mode 100644
index 000000000000..059047af7df3
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_skb_sk_lookup.c
@@ -0,0 +1,95 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2020 Facebook
+
+#include <test_progs.h>
+
+#include "network_helpers.h"
+#include "cgroup_skb_sk_lookup_kern.skel.h"
+
+static void run_lookup_test(__u16 *g_serv_port, int out_sk)
+{
+ int serv_sk = -1, in_sk = -1, serv_in_sk = -1, err;
+ struct sockaddr_in6 addr = {};
+ socklen_t addr_len = sizeof(addr);
+ __u32 duration = 0;
+
+ serv_sk = start_server(AF_INET6, SOCK_STREAM);
+ if (CHECK(serv_sk < 0, "start_server", "failed to start server\n"))
+ return;
+
+ err = getsockname(serv_sk, (struct sockaddr *)&addr, &addr_len);
+ if (CHECK(err, "getsockname", "errno %d\n", errno))
+ goto cleanup;
+
+ *g_serv_port = addr.sin6_port;
+
+ /* Client outside of test cgroup should fail to connect by timeout. */
+ err = connect_fd_to_fd(out_sk, serv_sk);
+ if (CHECK(!err || errno != EINPROGRESS, "connect_fd_to_fd",
+ "unexpected result err %d errno %d\n", err, errno))
+ goto cleanup;
+
+ err = connect_wait(out_sk);
+ if (CHECK(err, "connect_wait", "unexpected result %d\n", err))
+ goto cleanup;
+
+ /* Client inside test cgroup should connect just fine. */
+ in_sk = connect_to_fd(AF_INET6, SOCK_STREAM, serv_sk);
+ if (CHECK(in_sk < 0, "connect_to_fd", "errno %d\n", errno))
+ goto cleanup;
+
+ serv_in_sk = accept(serv_sk, NULL, NULL);
+ if (CHECK(serv_in_sk < 0, "accept", "errno %d\n", errno))
+ goto cleanup;
+
+cleanup:
+ close(serv_in_sk);
+ close(in_sk);
+ close(serv_sk);
+}
+
+static void run_cgroup_bpf_test(const char *cg_path, int out_sk)
+{
+ struct cgroup_skb_sk_lookup_kern *skel;
+ struct bpf_link *link;
+ __u32 duration = 0;
+ int cgfd = -1;
+
+ skel = cgroup_skb_sk_lookup_kern__open_and_load();
+ if (CHECK(!skel, "skel_open_load", "open_load failed\n"))
+ return;
+
+ cgfd = test__join_cgroup(cg_path);
+ if (CHECK(cgfd < 0, "cgroup_join", "cgroup setup failed\n"))
+ goto cleanup;
+
+ link = bpf_program__attach_cgroup(skel->progs.ingress_lookup, cgfd);
+ if (CHECK(IS_ERR(link), "cgroup_attach", "err: %ld\n", PTR_ERR(link)))
+ goto cleanup;
+
+ run_lookup_test(&skel->bss->g_serv_port, out_sk);
+
+ bpf_link__destroy(link);
+
+cleanup:
+ close(cgfd);
+ cgroup_skb_sk_lookup_kern__destroy(skel);
+}
+
+void test_cgroup_skb_sk_lookup(void)
+{
+ const char *cg_path = "/foo";
+ int out_sk;
+
+ /* Create a socket before joining testing cgroup so that its cgroup id
+ * differs from that of testing cgroup. Moving selftests process to
+ * testing cgroup won't change cgroup id of an already created socket.
+ */
+ out_sk = socket(AF_INET6, SOCK_STREAM | SOCK_NONBLOCK, 0);
+ if (CHECK_FAIL(out_sk < 0))
+ return;
+
+ run_cgroup_bpf_test(cg_path, out_sk);
+
+ close(out_sk);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/cls_redirect.c b/tools/testing/selftests/bpf/prog_tests/cls_redirect.c
new file mode 100644
index 000000000000..f259085cca6a
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/cls_redirect.c
@@ -0,0 +1,456 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+// Copyright (c) 2020 Cloudflare
+
+#define _GNU_SOURCE
+
+#include <arpa/inet.h>
+#include <string.h>
+
+#include <linux/pkt_cls.h>
+
+#include <test_progs.h>
+
+#include "progs/test_cls_redirect.h"
+#include "test_cls_redirect.skel.h"
+
+#define ENCAP_IP INADDR_LOOPBACK
+#define ENCAP_PORT (1234)
+
+struct addr_port {
+ in_port_t port;
+ union {
+ struct in_addr in_addr;
+ struct in6_addr in6_addr;
+ };
+};
+
+struct tuple {
+ int family;
+ struct addr_port src;
+ struct addr_port dst;
+};
+
+static int start_server(const struct sockaddr *addr, socklen_t len, int type)
+{
+ int fd = socket(addr->sa_family, type, 0);
+ if (CHECK_FAIL(fd == -1))
+ return -1;
+ if (CHECK_FAIL(bind(fd, addr, len) == -1))
+ goto err;
+ if (type == SOCK_STREAM && CHECK_FAIL(listen(fd, 128) == -1))
+ goto err;
+
+ return fd;
+
+err:
+ close(fd);
+ return -1;
+}
+
+static int connect_to_server(const struct sockaddr *addr, socklen_t len,
+ int type)
+{
+ int fd = socket(addr->sa_family, type, 0);
+ if (CHECK_FAIL(fd == -1))
+ return -1;
+ if (CHECK_FAIL(connect(fd, addr, len)))
+ goto err;
+
+ return fd;
+
+err:
+ close(fd);
+ return -1;
+}
+
+static bool fill_addr_port(const struct sockaddr *sa, struct addr_port *ap)
+{
+ const struct sockaddr_in6 *in6;
+ const struct sockaddr_in *in;
+
+ switch (sa->sa_family) {
+ case AF_INET:
+ in = (const struct sockaddr_in *)sa;
+ ap->in_addr = in->sin_addr;
+ ap->port = in->sin_port;
+ return true;
+
+ case AF_INET6:
+ in6 = (const struct sockaddr_in6 *)sa;
+ ap->in6_addr = in6->sin6_addr;
+ ap->port = in6->sin6_port;
+ return true;
+
+ default:
+ return false;
+ }
+}
+
+static bool set_up_conn(const struct sockaddr *addr, socklen_t len, int type,
+ int *server, int *conn, struct tuple *tuple)
+{
+ struct sockaddr_storage ss;
+ socklen_t slen = sizeof(ss);
+ struct sockaddr *sa = (struct sockaddr *)&ss;
+
+ *server = start_server(addr, len, type);
+ if (*server < 0)
+ return false;
+
+ if (CHECK_FAIL(getsockname(*server, sa, &slen)))
+ goto close_server;
+
+ *conn = connect_to_server(sa, slen, type);
+ if (*conn < 0)
+ goto close_server;
+
+ /* We want to simulate packets arriving at conn, so we have to
+ * swap src and dst.
+ */
+ slen = sizeof(ss);
+ if (CHECK_FAIL(getsockname(*conn, sa, &slen)))
+ goto close_conn;
+
+ if (CHECK_FAIL(!fill_addr_port(sa, &tuple->dst)))
+ goto close_conn;
+
+ slen = sizeof(ss);
+ if (CHECK_FAIL(getpeername(*conn, sa, &slen)))
+ goto close_conn;
+
+ if (CHECK_FAIL(!fill_addr_port(sa, &tuple->src)))
+ goto close_conn;
+
+ tuple->family = ss.ss_family;
+ return true;
+
+close_conn:
+ close(*conn);
+ *conn = -1;
+close_server:
+ close(*server);
+ *server = -1;
+ return false;
+}
+
+static socklen_t prepare_addr(struct sockaddr_storage *addr, int family)
+{
+ struct sockaddr_in *addr4;
+ struct sockaddr_in6 *addr6;
+
+ switch (family) {
+ case AF_INET:
+ addr4 = (struct sockaddr_in *)addr;
+ memset(addr4, 0, sizeof(*addr4));
+ addr4->sin_family = family;
+ addr4->sin_addr.s_addr = htonl(INADDR_LOOPBACK);
+ return sizeof(*addr4);
+ case AF_INET6:
+ addr6 = (struct sockaddr_in6 *)addr;
+ memset(addr6, 0, sizeof(*addr6));
+ addr6->sin6_family = family;
+ addr6->sin6_addr = in6addr_loopback;
+ return sizeof(*addr6);
+ default:
+ fprintf(stderr, "Invalid family %d", family);
+ return 0;
+ }
+}
+
+static bool was_decapsulated(struct bpf_prog_test_run_attr *tattr)
+{
+ return tattr->data_size_out < tattr->data_size_in;
+}
+
+enum type {
+ UDP,
+ TCP,
+ __NR_KIND,
+};
+
+enum hops {
+ NO_HOPS,
+ ONE_HOP,
+};
+
+enum flags {
+ NONE,
+ SYN,
+ ACK,
+};
+
+enum conn {
+ KNOWN_CONN,
+ UNKNOWN_CONN,
+};
+
+enum result {
+ ACCEPT,
+ FORWARD,
+};
+
+struct test_cfg {
+ enum type type;
+ enum result result;
+ enum conn conn;
+ enum hops hops;
+ enum flags flags;
+};
+
+static int test_str(void *buf, size_t len, const struct test_cfg *test,
+ int family)
+{
+ const char *family_str, *type, *conn, *hops, *result, *flags;
+
+ family_str = "IPv4";
+ if (family == AF_INET6)
+ family_str = "IPv6";
+
+ type = "TCP";
+ if (test->type == UDP)
+ type = "UDP";
+
+ conn = "known";
+ if (test->conn == UNKNOWN_CONN)
+ conn = "unknown";
+
+ hops = "no hops";
+ if (test->hops == ONE_HOP)
+ hops = "one hop";
+
+ result = "accept";
+ if (test->result == FORWARD)
+ result = "forward";
+
+ flags = "none";
+ if (test->flags == SYN)
+ flags = "SYN";
+ else if (test->flags == ACK)
+ flags = "ACK";
+
+ return snprintf(buf, len, "%s %s %s %s (%s, flags: %s)", family_str,
+ type, result, conn, hops, flags);
+}
+
+static struct test_cfg tests[] = {
+ { TCP, ACCEPT, UNKNOWN_CONN, NO_HOPS, SYN },
+ { TCP, ACCEPT, UNKNOWN_CONN, NO_HOPS, ACK },
+ { TCP, FORWARD, UNKNOWN_CONN, ONE_HOP, ACK },
+ { TCP, ACCEPT, KNOWN_CONN, ONE_HOP, ACK },
+ { UDP, ACCEPT, UNKNOWN_CONN, NO_HOPS, NONE },
+ { UDP, FORWARD, UNKNOWN_CONN, ONE_HOP, NONE },
+ { UDP, ACCEPT, KNOWN_CONN, ONE_HOP, NONE },
+};
+
+static void encap_init(encap_headers_t *encap, uint8_t hop_count, uint8_t proto)
+{
+ const uint8_t hlen =
+ (sizeof(struct guehdr) / sizeof(uint32_t)) + hop_count;
+ *encap = (encap_headers_t){
+ .eth = { .h_proto = htons(ETH_P_IP) },
+ .ip = {
+ .ihl = 5,
+ .version = 4,
+ .ttl = IPDEFTTL,
+ .protocol = IPPROTO_UDP,
+ .daddr = htonl(ENCAP_IP)
+ },
+ .udp = {
+ .dest = htons(ENCAP_PORT),
+ },
+ .gue = {
+ .hlen = hlen,
+ .proto_ctype = proto
+ },
+ .unigue = {
+ .hop_count = hop_count
+ },
+ };
+}
+
+static size_t build_input(const struct test_cfg *test, void *const buf,
+ const struct tuple *tuple)
+{
+ in_port_t sport = tuple->src.port;
+ encap_headers_t encap;
+ struct iphdr ip;
+ struct ipv6hdr ipv6;
+ struct tcphdr tcp;
+ struct udphdr udp;
+ struct in_addr next_hop;
+ uint8_t *p = buf;
+ int proto;
+
+ proto = IPPROTO_IPIP;
+ if (tuple->family == AF_INET6)
+ proto = IPPROTO_IPV6;
+
+ encap_init(&encap, test->hops == ONE_HOP ? 1 : 0, proto);
+ p = mempcpy(p, &encap, sizeof(encap));
+
+ if (test->hops == ONE_HOP) {
+ next_hop = (struct in_addr){ .s_addr = htonl(0x7f000002) };
+ p = mempcpy(p, &next_hop, sizeof(next_hop));
+ }
+
+ proto = IPPROTO_TCP;
+ if (test->type == UDP)
+ proto = IPPROTO_UDP;
+
+ switch (tuple->family) {
+ case AF_INET:
+ ip = (struct iphdr){
+ .ihl = 5,
+ .version = 4,
+ .ttl = IPDEFTTL,
+ .protocol = proto,
+ .saddr = tuple->src.in_addr.s_addr,
+ .daddr = tuple->dst.in_addr.s_addr,
+ };
+ p = mempcpy(p, &ip, sizeof(ip));
+ break;
+ case AF_INET6:
+ ipv6 = (struct ipv6hdr){
+ .version = 6,
+ .hop_limit = IPDEFTTL,
+ .nexthdr = proto,
+ .saddr = tuple->src.in6_addr,
+ .daddr = tuple->dst.in6_addr,
+ };
+ p = mempcpy(p, &ipv6, sizeof(ipv6));
+ break;
+ default:
+ return 0;
+ }
+
+ if (test->conn == UNKNOWN_CONN)
+ sport--;
+
+ switch (test->type) {
+ case TCP:
+ tcp = (struct tcphdr){
+ .source = sport,
+ .dest = tuple->dst.port,
+ };
+ if (test->flags == SYN)
+ tcp.syn = true;
+ if (test->flags == ACK)
+ tcp.ack = true;
+ p = mempcpy(p, &tcp, sizeof(tcp));
+ break;
+ case UDP:
+ udp = (struct udphdr){
+ .source = sport,
+ .dest = tuple->dst.port,
+ };
+ p = mempcpy(p, &udp, sizeof(udp));
+ break;
+ default:
+ return 0;
+ }
+
+ return (void *)p - buf;
+}
+
+static void close_fds(int *fds, int n)
+{
+ int i;
+
+ for (i = 0; i < n; i++)
+ if (fds[i] > 0)
+ close(fds[i]);
+}
+
+void test_cls_redirect(void)
+{
+ struct test_cls_redirect *skel = NULL;
+ struct bpf_prog_test_run_attr tattr = {};
+ int families[] = { AF_INET, AF_INET6 };
+ struct sockaddr_storage ss;
+ struct sockaddr *addr;
+ socklen_t slen;
+ int i, j, err;
+
+ int servers[__NR_KIND][ARRAY_SIZE(families)] = {};
+ int conns[__NR_KIND][ARRAY_SIZE(families)] = {};
+ struct tuple tuples[__NR_KIND][ARRAY_SIZE(families)];
+
+ skel = test_cls_redirect__open();
+ if (CHECK_FAIL(!skel))
+ return;
+
+ skel->rodata->ENCAPSULATION_IP = htonl(ENCAP_IP);
+ skel->rodata->ENCAPSULATION_PORT = htons(ENCAP_PORT);
+
+ if (CHECK_FAIL(test_cls_redirect__load(skel)))
+ goto cleanup;
+
+ addr = (struct sockaddr *)&ss;
+ for (i = 0; i < ARRAY_SIZE(families); i++) {
+ slen = prepare_addr(&ss, families[i]);
+ if (CHECK_FAIL(!slen))
+ goto cleanup;
+
+ if (CHECK_FAIL(!set_up_conn(addr, slen, SOCK_DGRAM,
+ &servers[UDP][i], &conns[UDP][i],
+ &tuples[UDP][i])))
+ goto cleanup;
+
+ if (CHECK_FAIL(!set_up_conn(addr, slen, SOCK_STREAM,
+ &servers[TCP][i], &conns[TCP][i],
+ &tuples[TCP][i])))
+ goto cleanup;
+ }
+
+ tattr.prog_fd = bpf_program__fd(skel->progs.cls_redirect);
+ for (i = 0; i < ARRAY_SIZE(tests); i++) {
+ struct test_cfg *test = &tests[i];
+
+ for (j = 0; j < ARRAY_SIZE(families); j++) {
+ struct tuple *tuple = &tuples[test->type][j];
+ char input[256];
+ char tmp[256];
+
+ test_str(tmp, sizeof(tmp), test, tuple->family);
+ if (!test__start_subtest(tmp))
+ continue;
+
+ tattr.data_out = tmp;
+ tattr.data_size_out = sizeof(tmp);
+
+ tattr.data_in = input;
+ tattr.data_size_in = build_input(test, input, tuple);
+ if (CHECK_FAIL(!tattr.data_size_in))
+ continue;
+
+ err = bpf_prog_test_run_xattr(&tattr);
+ if (CHECK_FAIL(err))
+ continue;
+
+ if (tattr.retval != TC_ACT_REDIRECT) {
+ PRINT_FAIL("expected TC_ACT_REDIRECT, got %d\n",
+ tattr.retval);
+ continue;
+ }
+
+ switch (test->result) {
+ case ACCEPT:
+ if (CHECK_FAIL(!was_decapsulated(&tattr)))
+ continue;
+ break;
+ case FORWARD:
+ if (CHECK_FAIL(was_decapsulated(&tattr)))
+ continue;
+ break;
+ default:
+ PRINT_FAIL("unknown result %d\n", test->result);
+ continue;
+ }
+ }
+ }
+
+cleanup:
+ test_cls_redirect__destroy(skel);
+ close_fds((int *)servers, sizeof(servers) / sizeof(servers[0][0]));
+ close_fds((int *)conns, sizeof(conns) / sizeof(conns[0][0]));
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/connect_force_port.c b/tools/testing/selftests/bpf/prog_tests/connect_force_port.c
new file mode 100644
index 000000000000..17bbf76812ca
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/connect_force_port.c
@@ -0,0 +1,166 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+#include "cgroup_helpers.h"
+#include "network_helpers.h"
+
+static int verify_ports(int family, int fd,
+ __u16 expected_local, __u16 expected_peer)
+{
+ struct sockaddr_storage addr;
+ socklen_t len = sizeof(addr);
+ __u16 port;
+
+ if (getsockname(fd, (struct sockaddr *)&addr, &len)) {
+ log_err("Failed to get server addr");
+ return -1;
+ }
+
+ if (family == AF_INET)
+ port = ((struct sockaddr_in *)&addr)->sin_port;
+ else
+ port = ((struct sockaddr_in6 *)&addr)->sin6_port;
+
+ if (ntohs(port) != expected_local) {
+ log_err("Unexpected local port %d, expected %d", ntohs(port),
+ expected_local);
+ return -1;
+ }
+
+ if (getpeername(fd, (struct sockaddr *)&addr, &len)) {
+ log_err("Failed to get peer addr");
+ return -1;
+ }
+
+ if (family == AF_INET)
+ port = ((struct sockaddr_in *)&addr)->sin_port;
+ else
+ port = ((struct sockaddr_in6 *)&addr)->sin6_port;
+
+ if (ntohs(port) != expected_peer) {
+ log_err("Unexpected peer port %d, expected %d", ntohs(port),
+ expected_peer);
+ return -1;
+ }
+
+ return 0;
+}
+
+static int run_test(int cgroup_fd, int server_fd, int family, int type)
+{
+ bool v4 = family == AF_INET;
+ __u16 expected_local_port = v4 ? 22222 : 22223;
+ __u16 expected_peer_port = 60000;
+ struct bpf_prog_load_attr attr = {
+ .file = v4 ? "./connect_force_port4.o" :
+ "./connect_force_port6.o",
+ };
+ struct bpf_program *prog;
+ struct bpf_object *obj;
+ int xlate_fd, fd, err;
+ __u32 duration = 0;
+
+ err = bpf_prog_load_xattr(&attr, &obj, &xlate_fd);
+ if (err) {
+ log_err("Failed to load BPF object");
+ return -1;
+ }
+
+ prog = bpf_object__find_program_by_title(obj, v4 ?
+ "cgroup/connect4" :
+ "cgroup/connect6");
+ if (CHECK(!prog, "find_prog", "connect prog not found\n")) {
+ err = -EIO;
+ goto close_bpf_object;
+ }
+
+ err = bpf_prog_attach(bpf_program__fd(prog), cgroup_fd, v4 ?
+ BPF_CGROUP_INET4_CONNECT :
+ BPF_CGROUP_INET6_CONNECT, 0);
+ if (err) {
+ log_err("Failed to attach BPF program");
+ goto close_bpf_object;
+ }
+
+ prog = bpf_object__find_program_by_title(obj, v4 ?
+ "cgroup/getpeername4" :
+ "cgroup/getpeername6");
+ if (CHECK(!prog, "find_prog", "getpeername prog not found\n")) {
+ err = -EIO;
+ goto close_bpf_object;
+ }
+
+ err = bpf_prog_attach(bpf_program__fd(prog), cgroup_fd, v4 ?
+ BPF_CGROUP_INET4_GETPEERNAME :
+ BPF_CGROUP_INET6_GETPEERNAME, 0);
+ if (err) {
+ log_err("Failed to attach BPF program");
+ goto close_bpf_object;
+ }
+
+ prog = bpf_object__find_program_by_title(obj, v4 ?
+ "cgroup/getsockname4" :
+ "cgroup/getsockname6");
+ if (CHECK(!prog, "find_prog", "getsockname prog not found\n")) {
+ err = -EIO;
+ goto close_bpf_object;
+ }
+
+ err = bpf_prog_attach(bpf_program__fd(prog), cgroup_fd, v4 ?
+ BPF_CGROUP_INET4_GETSOCKNAME :
+ BPF_CGROUP_INET6_GETSOCKNAME, 0);
+ if (err) {
+ log_err("Failed to attach BPF program");
+ goto close_bpf_object;
+ }
+
+ fd = connect_to_fd(family, type, server_fd);
+ if (fd < 0) {
+ err = -1;
+ goto close_bpf_object;
+ }
+
+ err = verify_ports(family, fd, expected_local_port,
+ expected_peer_port);
+ close(fd);
+
+close_bpf_object:
+ bpf_object__close(obj);
+ return err;
+}
+
+void test_connect_force_port(void)
+{
+ int server_fd, cgroup_fd;
+
+ cgroup_fd = test__join_cgroup("/connect_force_port");
+ if (CHECK_FAIL(cgroup_fd < 0))
+ return;
+
+ server_fd = start_server_with_port(AF_INET, SOCK_STREAM, 60123);
+ if (CHECK_FAIL(server_fd < 0))
+ goto close_cgroup_fd;
+ CHECK_FAIL(run_test(cgroup_fd, server_fd, AF_INET, SOCK_STREAM));
+ close(server_fd);
+
+ server_fd = start_server_with_port(AF_INET6, SOCK_STREAM, 60124);
+ if (CHECK_FAIL(server_fd < 0))
+ goto close_cgroup_fd;
+ CHECK_FAIL(run_test(cgroup_fd, server_fd, AF_INET6, SOCK_STREAM));
+ close(server_fd);
+
+ server_fd = start_server_with_port(AF_INET, SOCK_DGRAM, 60123);
+ if (CHECK_FAIL(server_fd < 0))
+ goto close_cgroup_fd;
+ CHECK_FAIL(run_test(cgroup_fd, server_fd, AF_INET, SOCK_DGRAM));
+ close(server_fd);
+
+ server_fd = start_server_with_port(AF_INET6, SOCK_DGRAM, 60124);
+ if (CHECK_FAIL(server_fd < 0))
+ goto close_cgroup_fd;
+ CHECK_FAIL(run_test(cgroup_fd, server_fd, AF_INET6, SOCK_DGRAM));
+ close(server_fd);
+
+close_cgroup_fd:
+ close(cgroup_fd);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/core_reloc.c b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
index 31e177adbdf1..084ed26a7d78 100644
--- a/tools/testing/selftests/bpf/prog_tests/core_reloc.c
+++ b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
@@ -392,7 +392,7 @@ static struct core_reloc_test_case test_cases[] = {
.input = STRUCT_TO_CHAR_PTR(core_reloc_existence___minimal) {
.a = 42,
},
- .input_len = sizeof(struct core_reloc_existence),
+ .input_len = sizeof(struct core_reloc_existence___minimal),
.output = STRUCT_TO_CHAR_PTR(core_reloc_existence_output) {
.a_exists = 1,
.b_exists = 0,
diff --git a/tools/testing/selftests/bpf/prog_tests/enable_stats.c b/tools/testing/selftests/bpf/prog_tests/enable_stats.c
new file mode 100644
index 000000000000..2cb2085917e7
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/enable_stats.c
@@ -0,0 +1,45 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+#include "test_enable_stats.skel.h"
+
+void test_enable_stats(void)
+{
+ struct test_enable_stats *skel;
+ int stats_fd, err, prog_fd;
+ struct bpf_prog_info info;
+ __u32 info_len = sizeof(info);
+ int duration = 0;
+
+ skel = test_enable_stats__open_and_load();
+ if (CHECK(!skel, "skel_open_and_load", "skeleton open/load failed\n"))
+ return;
+
+ stats_fd = bpf_enable_stats(BPF_STATS_RUN_TIME);
+ if (CHECK(stats_fd < 0, "get_stats_fd", "failed %d\n", errno)) {
+ test_enable_stats__destroy(skel);
+ return;
+ }
+
+ err = test_enable_stats__attach(skel);
+ if (CHECK(err, "attach_raw_tp", "err %d\n", err))
+ goto cleanup;
+
+ test_enable_stats__detach(skel);
+
+ prog_fd = bpf_program__fd(skel->progs.test_enable_stats);
+ memset(&info, 0, info_len);
+ err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
+ if (CHECK(err, "get_prog_info",
+ "failed to get bpf_prog_info for fd %d\n", prog_fd))
+ goto cleanup;
+ if (CHECK(info.run_time_ns == 0, "check_stats_enabled",
+ "failed to enable run_time_ns stats\n"))
+ goto cleanup;
+
+ CHECK(info.run_cnt != skel->bss->count, "check_run_cnt_valid",
+ "invalid run_cnt stats\n");
+
+cleanup:
+ test_enable_stats__destroy(skel);
+ close(stats_fd);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c b/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c
index 235ac4f67f5b..83493bd5745c 100644
--- a/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c
+++ b/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c
@@ -1,22 +1,17 @@
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2019 Facebook */
#include <test_progs.h>
-#include "test_pkt_access.skel.h"
#include "fentry_test.skel.h"
#include "fexit_test.skel.h"
void test_fentry_fexit(void)
{
- struct test_pkt_access *pkt_skel = NULL;
struct fentry_test *fentry_skel = NULL;
struct fexit_test *fexit_skel = NULL;
__u64 *fentry_res, *fexit_res;
__u32 duration = 0, retval;
- int err, pkt_fd, i;
+ int err, prog_fd, i;
- pkt_skel = test_pkt_access__open_and_load();
- if (CHECK(!pkt_skel, "pkt_skel_load", "pkt_access skeleton failed\n"))
- return;
fentry_skel = fentry_test__open_and_load();
if (CHECK(!fentry_skel, "fentry_skel_load", "fentry skeleton failed\n"))
goto close_prog;
@@ -31,8 +26,8 @@ void test_fentry_fexit(void)
if (CHECK(err, "fexit_attach", "fexit attach failed: %d\n", err))
goto close_prog;
- pkt_fd = bpf_program__fd(pkt_skel->progs.test_pkt_access);
- err = bpf_prog_test_run(pkt_fd, 1, &pkt_v6, sizeof(pkt_v6),
+ prog_fd = bpf_program__fd(fexit_skel->progs.test1);
+ err = bpf_prog_test_run(prog_fd, 1, NULL, 0,
NULL, NULL, &retval, &duration);
CHECK(err || retval, "ipv6",
"err %d errno %d retval %d duration %d\n",
@@ -49,7 +44,6 @@ void test_fentry_fexit(void)
}
close_prog:
- test_pkt_access__destroy(pkt_skel);
fentry_test__destroy(fentry_skel);
fexit_test__destroy(fexit_skel);
}
diff --git a/tools/testing/selftests/bpf/prog_tests/fentry_test.c b/tools/testing/selftests/bpf/prog_tests/fentry_test.c
index 5cc06021f27d..04ebbf1cb390 100644
--- a/tools/testing/selftests/bpf/prog_tests/fentry_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/fentry_test.c
@@ -1,20 +1,15 @@
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2019 Facebook */
#include <test_progs.h>
-#include "test_pkt_access.skel.h"
#include "fentry_test.skel.h"
void test_fentry_test(void)
{
- struct test_pkt_access *pkt_skel = NULL;
struct fentry_test *fentry_skel = NULL;
- int err, pkt_fd, i;
+ int err, prog_fd, i;
__u32 duration = 0, retval;
__u64 *result;
- pkt_skel = test_pkt_access__open_and_load();
- if (CHECK(!pkt_skel, "pkt_skel_load", "pkt_access skeleton failed\n"))
- return;
fentry_skel = fentry_test__open_and_load();
if (CHECK(!fentry_skel, "fentry_skel_load", "fentry skeleton failed\n"))
goto cleanup;
@@ -23,10 +18,10 @@ void test_fentry_test(void)
if (CHECK(err, "fentry_attach", "fentry attach failed: %d\n", err))
goto cleanup;
- pkt_fd = bpf_program__fd(pkt_skel->progs.test_pkt_access);
- err = bpf_prog_test_run(pkt_fd, 1, &pkt_v6, sizeof(pkt_v6),
+ prog_fd = bpf_program__fd(fentry_skel->progs.test1);
+ err = bpf_prog_test_run(prog_fd, 1, NULL, 0,
NULL, NULL, &retval, &duration);
- CHECK(err || retval, "ipv6",
+ CHECK(err || retval, "test_run",
"err %d errno %d retval %d duration %d\n",
err, errno, retval, duration);
@@ -39,5 +34,4 @@ void test_fentry_test(void)
cleanup:
fentry_test__destroy(fentry_skel);
- test_pkt_access__destroy(pkt_skel);
}
diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
index cde463af7071..a895bfed55db 100644
--- a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
+++ b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
@@ -1,11 +1,13 @@
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2019 Facebook */
#include <test_progs.h>
+#include <network_helpers.h>
static void test_fexit_bpf2bpf_common(const char *obj_file,
const char *target_obj_file,
int prog_cnt,
- const char **prog_name)
+ const char **prog_name,
+ bool run_prog)
{
struct bpf_object *obj = NULL, *pkt_obj;
int err, pkt_fd, i;
@@ -18,7 +20,8 @@ static void test_fexit_bpf2bpf_common(const char *obj_file,
err = bpf_prog_load(target_obj_file, BPF_PROG_TYPE_UNSPEC,
&pkt_obj, &pkt_fd);
- if (CHECK(err, "prog_load sched cls", "err %d errno %d\n", err, errno))
+ if (CHECK(err, "tgt_prog_load", "file %s err %d errno %d\n",
+ target_obj_file, err, errno))
return;
DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts,
.attach_prog_fd = pkt_fd,
@@ -33,7 +36,7 @@ static void test_fexit_bpf2bpf_common(const char *obj_file,
obj = bpf_object__open_file(obj_file, &opts);
if (CHECK(IS_ERR_OR_NULL(obj), "obj_open",
- "failed to open fexit_bpf2bpf: %ld\n",
+ "failed to open %s: %ld\n", obj_file,
PTR_ERR(obj)))
goto close_prog;
@@ -49,6 +52,10 @@ static void test_fexit_bpf2bpf_common(const char *obj_file,
if (CHECK(IS_ERR(link[i]), "attach_trace", "failed to link\n"))
goto close_prog;
}
+
+ if (!run_prog)
+ goto close_prog;
+
data_map = bpf_object__find_map_by_name(obj, "fexit_bp.bss");
if (CHECK(!data_map, "find_data_map", "data map not found\n"))
goto close_prog;
@@ -89,7 +96,7 @@ static void test_target_no_callees(void)
test_fexit_bpf2bpf_common("./fexit_bpf2bpf_simple.o",
"./test_pkt_md_access.o",
ARRAY_SIZE(prog_name),
- prog_name);
+ prog_name, true);
}
static void test_target_yes_callees(void)
@@ -103,7 +110,7 @@ static void test_target_yes_callees(void)
test_fexit_bpf2bpf_common("./fexit_bpf2bpf.o",
"./test_pkt_access.o",
ARRAY_SIZE(prog_name),
- prog_name);
+ prog_name, true);
}
static void test_func_replace(void)
@@ -120,7 +127,18 @@ static void test_func_replace(void)
test_fexit_bpf2bpf_common("./fexit_bpf2bpf.o",
"./test_pkt_access.o",
ARRAY_SIZE(prog_name),
- prog_name);
+ prog_name, true);
+}
+
+static void test_func_replace_verify(void)
+{
+ const char *prog_name[] = {
+ "freplace/do_bind",
+ };
+ test_fexit_bpf2bpf_common("./freplace_connect4.o",
+ "./connect4_prog.o",
+ ARRAY_SIZE(prog_name),
+ prog_name, false);
}
void test_fexit_bpf2bpf(void)
@@ -128,4 +146,5 @@ void test_fexit_bpf2bpf(void)
test_target_no_callees();
test_target_yes_callees();
test_func_replace();
+ test_func_replace_verify();
}
diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_test.c b/tools/testing/selftests/bpf/prog_tests/fexit_test.c
index d2c3655dd7a3..78d7a2765c27 100644
--- a/tools/testing/selftests/bpf/prog_tests/fexit_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/fexit_test.c
@@ -1,64 +1,37 @@
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2019 Facebook */
#include <test_progs.h>
+#include "fexit_test.skel.h"
void test_fexit_test(void)
{
- struct bpf_prog_load_attr attr = {
- .file = "./fexit_test.o",
- };
-
- char prog_name[] = "fexit/bpf_fentry_testX";
- struct bpf_object *obj = NULL, *pkt_obj;
- int err, pkt_fd, kfree_skb_fd, i;
- struct bpf_link *link[6] = {};
- struct bpf_program *prog[6];
+ struct fexit_test *fexit_skel = NULL;
+ int err, prog_fd, i;
__u32 duration = 0, retval;
- struct bpf_map *data_map;
- const int zero = 0;
- u64 result[6];
+ __u64 *result;
- err = bpf_prog_load("./test_pkt_access.o", BPF_PROG_TYPE_SCHED_CLS,
- &pkt_obj, &pkt_fd);
- if (CHECK(err, "prog_load sched cls", "err %d errno %d\n", err, errno))
- return;
- err = bpf_prog_load_xattr(&attr, &obj, &kfree_skb_fd);
- if (CHECK(err, "prog_load fail", "err %d errno %d\n", err, errno))
- goto close_prog;
+ fexit_skel = fexit_test__open_and_load();
+ if (CHECK(!fexit_skel, "fexit_skel_load", "fexit skeleton failed\n"))
+ goto cleanup;
- for (i = 0; i < 6; i++) {
- prog_name[sizeof(prog_name) - 2] = '1' + i;
- prog[i] = bpf_object__find_program_by_title(obj, prog_name);
- if (CHECK(!prog[i], "find_prog", "prog %s not found\n", prog_name))
- goto close_prog;
- link[i] = bpf_program__attach_trace(prog[i]);
- if (CHECK(IS_ERR(link[i]), "attach_trace", "failed to link\n"))
- goto close_prog;
- }
- data_map = bpf_object__find_map_by_name(obj, "fexit_te.bss");
- if (CHECK(!data_map, "find_data_map", "data map not found\n"))
- goto close_prog;
+ err = fexit_test__attach(fexit_skel);
+ if (CHECK(err, "fexit_attach", "fexit attach failed: %d\n", err))
+ goto cleanup;
- err = bpf_prog_test_run(pkt_fd, 1, &pkt_v6, sizeof(pkt_v6),
+ prog_fd = bpf_program__fd(fexit_skel->progs.test1);
+ err = bpf_prog_test_run(prog_fd, 1, NULL, 0,
NULL, NULL, &retval, &duration);
- CHECK(err || retval, "ipv6",
+ CHECK(err || retval, "test_run",
"err %d errno %d retval %d duration %d\n",
err, errno, retval, duration);
- err = bpf_map_lookup_elem(bpf_map__fd(data_map), &zero, &result);
- if (CHECK(err, "get_result",
- "failed to get output data: %d\n", err))
- goto close_prog;
-
- for (i = 0; i < 6; i++)
- if (CHECK(result[i] != 1, "result", "bpf_fentry_test%d failed err %ld\n",
- i + 1, result[i]))
- goto close_prog;
+ result = (__u64 *)fexit_skel->bss;
+ for (i = 0; i < 6; i++) {
+ if (CHECK(result[i] != 1, "result",
+ "fexit_test%d failed err %lld\n", i + 1, result[i]))
+ goto cleanup;
+ }
-close_prog:
- for (i = 0; i < 6; i++)
- if (!IS_ERR_OR_NULL(link[i]))
- bpf_link__destroy(link[i]);
- bpf_object__close(obj);
- bpf_object__close(pkt_obj);
+cleanup:
+ fexit_test__destroy(fexit_skel);
}
diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
index 92563898867c..ea14e3ece812 100644
--- a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
+++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
@@ -1,10 +1,13 @@
// SPDX-License-Identifier: GPL-2.0
#include <test_progs.h>
+#include <network_helpers.h>
#include <error.h>
#include <linux/if.h>
#include <linux/if_tun.h>
#include <sys/uio.h>
+#include "bpf_flow.skel.h"
+
#ifndef IP_MF
#define IP_MF 0x2000
#endif
@@ -100,6 +103,7 @@ struct test {
#define VLAN_HLEN 4
+static __u32 duration;
struct test tests[] = {
{
.name = "ipv4",
@@ -443,17 +447,130 @@ static int ifup(const char *ifname)
return 0;
}
+static int init_prog_array(struct bpf_object *obj, struct bpf_map *prog_array)
+{
+ int i, err, map_fd, prog_fd;
+ struct bpf_program *prog;
+ char prog_name[32];
+
+ map_fd = bpf_map__fd(prog_array);
+ if (map_fd < 0)
+ return -1;
+
+ for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) {
+ snprintf(prog_name, sizeof(prog_name), "flow_dissector/%i", i);
+
+ prog = bpf_object__find_program_by_title(obj, prog_name);
+ if (!prog)
+ return -1;
+
+ prog_fd = bpf_program__fd(prog);
+ if (prog_fd < 0)
+ return -1;
+
+ err = bpf_map_update_elem(map_fd, &i, &prog_fd, BPF_ANY);
+ if (err)
+ return -1;
+ }
+ return 0;
+}
+
+static void run_tests_skb_less(int tap_fd, struct bpf_map *keys)
+{
+ int i, err, keys_fd;
+
+ keys_fd = bpf_map__fd(keys);
+ if (CHECK(keys_fd < 0, "bpf_map__fd", "err %d\n", keys_fd))
+ return;
+
+ for (i = 0; i < ARRAY_SIZE(tests); i++) {
+ /* Keep in sync with 'flags' from eth_get_headlen. */
+ __u32 eth_get_headlen_flags =
+ BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG;
+ struct bpf_prog_test_run_attr tattr = {};
+ struct bpf_flow_keys flow_keys = {};
+ __u32 key = (__u32)(tests[i].keys.sport) << 16 |
+ tests[i].keys.dport;
+
+ /* For skb-less case we can't pass input flags; run
+ * only the tests that have a matching set of flags.
+ */
+
+ if (tests[i].flags != eth_get_headlen_flags)
+ continue;
+
+ err = tx_tap(tap_fd, &tests[i].pkt, sizeof(tests[i].pkt));
+ CHECK(err < 0, "tx_tap", "err %d errno %d\n", err, errno);
+
+ err = bpf_map_lookup_elem(keys_fd, &key, &flow_keys);
+ CHECK_ATTR(err, tests[i].name, "bpf_map_lookup_elem %d\n", err);
+
+ CHECK_ATTR(err, tests[i].name, "skb-less err %d\n", err);
+ CHECK_FLOW_KEYS(tests[i].name, flow_keys, tests[i].keys);
+
+ err = bpf_map_delete_elem(keys_fd, &key);
+ CHECK_ATTR(err, tests[i].name, "bpf_map_delete_elem %d\n", err);
+ }
+}
+
+static void test_skb_less_prog_attach(struct bpf_flow *skel, int tap_fd)
+{
+ int err, prog_fd;
+
+ prog_fd = bpf_program__fd(skel->progs._dissect);
+ if (CHECK(prog_fd < 0, "bpf_program__fd", "err %d\n", prog_fd))
+ return;
+
+ err = bpf_prog_attach(prog_fd, 0, BPF_FLOW_DISSECTOR, 0);
+ if (CHECK(err, "bpf_prog_attach", "err %d errno %d\n", err, errno))
+ return;
+
+ run_tests_skb_less(tap_fd, skel->maps.last_dissection);
+
+ err = bpf_prog_detach(prog_fd, BPF_FLOW_DISSECTOR);
+ CHECK(err, "bpf_prog_detach", "err %d errno %d\n", err, errno);
+}
+
+static void test_skb_less_link_create(struct bpf_flow *skel, int tap_fd)
+{
+ struct bpf_link *link;
+ int err, net_fd;
+
+ net_fd = open("/proc/self/ns/net", O_RDONLY);
+ if (CHECK(net_fd < 0, "open(/proc/self/ns/net)", "err %d\n", errno))
+ return;
+
+ link = bpf_program__attach_netns(skel->progs._dissect, net_fd);
+ if (CHECK(IS_ERR(link), "attach_netns", "err %ld\n", PTR_ERR(link)))
+ goto out_close;
+
+ run_tests_skb_less(tap_fd, skel->maps.last_dissection);
+
+ err = bpf_link__destroy(link);
+ CHECK(err, "bpf_link__destroy", "err %d\n", err);
+out_close:
+ close(net_fd);
+}
+
void test_flow_dissector(void)
{
int i, err, prog_fd, keys_fd = -1, tap_fd;
- struct bpf_object *obj;
- __u32 duration = 0;
+ struct bpf_flow *skel;
- err = bpf_flow_load(&obj, "./bpf_flow.o", "flow_dissector",
- "jmp_table", "last_dissection", &prog_fd, &keys_fd);
- if (CHECK_FAIL(err))
+ skel = bpf_flow__open_and_load();
+ if (CHECK(!skel, "skel", "failed to open/load skeleton\n"))
return;
+ prog_fd = bpf_program__fd(skel->progs._dissect);
+ if (CHECK(prog_fd < 0, "bpf_program__fd", "err %d\n", prog_fd))
+ goto out_destroy_skel;
+ keys_fd = bpf_map__fd(skel->maps.last_dissection);
+ if (CHECK(keys_fd < 0, "bpf_map__fd", "err %d\n", keys_fd))
+ goto out_destroy_skel;
+ err = init_prog_array(skel->obj, skel->maps.jmp_table);
+ if (CHECK(err, "init_prog_array", "err %d\n", err))
+ goto out_destroy_skel;
+
for (i = 0; i < ARRAY_SIZE(tests); i++) {
struct bpf_flow_keys flow_keys;
struct bpf_prog_test_run_attr tattr = {
@@ -486,43 +603,17 @@ void test_flow_dissector(void)
* via BPF map in this case.
*/
- err = bpf_prog_attach(prog_fd, 0, BPF_FLOW_DISSECTOR, 0);
- CHECK(err, "bpf_prog_attach", "err %d errno %d\n", err, errno);
-
tap_fd = create_tap("tap0");
CHECK(tap_fd < 0, "create_tap", "tap_fd %d errno %d\n", tap_fd, errno);
err = ifup("tap0");
CHECK(err, "ifup", "err %d errno %d\n", err, errno);
- for (i = 0; i < ARRAY_SIZE(tests); i++) {
- /* Keep in sync with 'flags' from eth_get_headlen. */
- __u32 eth_get_headlen_flags =
- BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG;
- struct bpf_prog_test_run_attr tattr = {};
- struct bpf_flow_keys flow_keys = {};
- __u32 key = (__u32)(tests[i].keys.sport) << 16 |
- tests[i].keys.dport;
-
- /* For skb-less case we can't pass input flags; run
- * only the tests that have a matching set of flags.
- */
-
- if (tests[i].flags != eth_get_headlen_flags)
- continue;
-
- err = tx_tap(tap_fd, &tests[i].pkt, sizeof(tests[i].pkt));
- CHECK(err < 0, "tx_tap", "err %d errno %d\n", err, errno);
-
- err = bpf_map_lookup_elem(keys_fd, &key, &flow_keys);
- CHECK_ATTR(err, tests[i].name, "bpf_map_lookup_elem %d\n", err);
-
- CHECK_ATTR(err, tests[i].name, "skb-less err %d\n", err);
- CHECK_FLOW_KEYS(tests[i].name, flow_keys, tests[i].keys);
-
- err = bpf_map_delete_elem(keys_fd, &key);
- CHECK_ATTR(err, tests[i].name, "bpf_map_delete_elem %d\n", err);
- }
+ /* Test direct prog attachment */
+ test_skb_less_prog_attach(skel, tap_fd);
+ /* Test indirect prog attachment via link */
+ test_skb_less_link_create(skel, tap_fd);
- bpf_prog_detach(prog_fd, BPF_FLOW_DISSECTOR);
- bpf_object__close(obj);
+ close(tap_fd);
+out_destroy_skel:
+ bpf_flow__destroy(skel);
}
diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector_load_bytes.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector_load_bytes.c
index dc5ef155ec28..0e8a4d2f023d 100644
--- a/tools/testing/selftests/bpf/prog_tests/flow_dissector_load_bytes.c
+++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector_load_bytes.c
@@ -1,5 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
#include <test_progs.h>
+#include <network_helpers.h>
void test_flow_dissector_load_bytes(void)
{
diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c
index 1f51ba66b98b..15cb554a66d8 100644
--- a/tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c
+++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c
@@ -11,6 +11,7 @@
#include <fcntl.h>
#include <sched.h>
#include <stdbool.h>
+#include <sys/stat.h>
#include <unistd.h>
#include <linux/bpf.h>
@@ -18,21 +19,30 @@
#include "test_progs.h"
-static bool is_attached(int netns)
+static int init_net = -1;
+
+static __u32 query_attached_prog_id(int netns)
{
- __u32 cnt;
+ __u32 prog_ids[1] = {};
+ __u32 prog_cnt = ARRAY_SIZE(prog_ids);
int err;
- err = bpf_prog_query(netns, BPF_FLOW_DISSECTOR, 0, NULL, NULL, &cnt);
+ err = bpf_prog_query(netns, BPF_FLOW_DISSECTOR, 0, NULL,
+ prog_ids, &prog_cnt);
if (CHECK_FAIL(err)) {
perror("bpf_prog_query");
- return true; /* fail-safe */
+ return 0;
}
- return cnt > 0;
+ return prog_cnt == 1 ? prog_ids[0] : 0;
+}
+
+static bool prog_is_attached(int netns)
+{
+ return query_attached_prog_id(netns) > 0;
}
-static int load_prog(void)
+static int load_prog(enum bpf_prog_type type)
{
struct bpf_insn prog[] = {
BPF_MOV64_IMM(BPF_REG_0, BPF_OK),
@@ -40,61 +50,566 @@ static int load_prog(void)
};
int fd;
- fd = bpf_load_program(BPF_PROG_TYPE_FLOW_DISSECTOR, prog,
- ARRAY_SIZE(prog), "GPL", 0, NULL, 0);
+ fd = bpf_load_program(type, prog, ARRAY_SIZE(prog), "GPL", 0, NULL, 0);
if (CHECK_FAIL(fd < 0))
perror("bpf_load_program");
return fd;
}
-static void do_flow_dissector_reattach(void)
+static __u32 query_prog_id(int prog)
{
- int prog_fd[2] = { -1, -1 };
+ struct bpf_prog_info info = {};
+ __u32 info_len = sizeof(info);
int err;
- prog_fd[0] = load_prog();
- if (prog_fd[0] < 0)
- return;
+ err = bpf_obj_get_info_by_fd(prog, &info, &info_len);
+ if (CHECK_FAIL(err || info_len != sizeof(info))) {
+ perror("bpf_obj_get_info_by_fd");
+ return 0;
+ }
- prog_fd[1] = load_prog();
- if (prog_fd[1] < 0)
- goto out_close;
+ return info.id;
+}
+
+static int unshare_net(int old_net)
+{
+ int err, new_net;
- err = bpf_prog_attach(prog_fd[0], 0, BPF_FLOW_DISSECTOR, 0);
+ err = unshare(CLONE_NEWNET);
if (CHECK_FAIL(err)) {
- perror("bpf_prog_attach-0");
- goto out_close;
+ perror("unshare(CLONE_NEWNET)");
+ return -1;
+ }
+ new_net = open("/proc/self/ns/net", O_RDONLY);
+ if (CHECK_FAIL(new_net < 0)) {
+ perror("open(/proc/self/ns/net)");
+ setns(old_net, CLONE_NEWNET);
+ return -1;
}
+ return new_net;
+}
+
+static void test_prog_attach_prog_attach(int netns, int prog1, int prog2)
+{
+ int err;
+
+ err = bpf_prog_attach(prog1, 0, BPF_FLOW_DISSECTOR, 0);
+ if (CHECK_FAIL(err)) {
+ perror("bpf_prog_attach(prog1)");
+ return;
+ }
+ CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1));
/* Expect success when attaching a different program */
- err = bpf_prog_attach(prog_fd[1], 0, BPF_FLOW_DISSECTOR, 0);
+ err = bpf_prog_attach(prog2, 0, BPF_FLOW_DISSECTOR, 0);
if (CHECK_FAIL(err)) {
- perror("bpf_prog_attach-1");
+ perror("bpf_prog_attach(prog2) #1");
goto out_detach;
}
+ CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog2));
/* Expect failure when attaching the same program twice */
- err = bpf_prog_attach(prog_fd[1], 0, BPF_FLOW_DISSECTOR, 0);
+ err = bpf_prog_attach(prog2, 0, BPF_FLOW_DISSECTOR, 0);
if (CHECK_FAIL(!err || errno != EINVAL))
- perror("bpf_prog_attach-2");
+ perror("bpf_prog_attach(prog2) #2");
+ CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog2));
out_detach:
err = bpf_prog_detach(0, BPF_FLOW_DISSECTOR);
if (CHECK_FAIL(err))
perror("bpf_prog_detach");
+ CHECK_FAIL(prog_is_attached(netns));
+}
+
+static void test_link_create_link_create(int netns, int prog1, int prog2)
+{
+ DECLARE_LIBBPF_OPTS(bpf_link_create_opts, opts);
+ int link1, link2;
+
+ link1 = bpf_link_create(prog1, netns, BPF_FLOW_DISSECTOR, &opts);
+ if (CHECK_FAIL(link < 0)) {
+ perror("bpf_link_create(prog1)");
+ return;
+ }
+ CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1));
+
+ /* Expect failure creating link when another link exists */
+ errno = 0;
+ link2 = bpf_link_create(prog2, netns, BPF_FLOW_DISSECTOR, &opts);
+ if (CHECK_FAIL(link2 != -1 || errno != E2BIG))
+ perror("bpf_prog_attach(prog2) expected E2BIG");
+ if (link2 != -1)
+ close(link2);
+ CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1));
+
+ close(link1);
+ CHECK_FAIL(prog_is_attached(netns));
+}
+
+static void test_prog_attach_link_create(int netns, int prog1, int prog2)
+{
+ DECLARE_LIBBPF_OPTS(bpf_link_create_opts, opts);
+ int err, link;
+
+ err = bpf_prog_attach(prog1, -1, BPF_FLOW_DISSECTOR, 0);
+ if (CHECK_FAIL(err)) {
+ perror("bpf_prog_attach(prog1)");
+ return;
+ }
+ CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1));
+
+ /* Expect failure creating link when prog attached */
+ errno = 0;
+ link = bpf_link_create(prog2, netns, BPF_FLOW_DISSECTOR, &opts);
+ if (CHECK_FAIL(link != -1 || errno != EEXIST))
+ perror("bpf_link_create(prog2) expected EEXIST");
+ if (link != -1)
+ close(link);
+ CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1));
+
+ err = bpf_prog_detach(-1, BPF_FLOW_DISSECTOR);
+ if (CHECK_FAIL(err))
+ perror("bpf_prog_detach");
+ CHECK_FAIL(prog_is_attached(netns));
+}
+
+static void test_link_create_prog_attach(int netns, int prog1, int prog2)
+{
+ DECLARE_LIBBPF_OPTS(bpf_link_create_opts, opts);
+ int err, link;
+
+ link = bpf_link_create(prog1, netns, BPF_FLOW_DISSECTOR, &opts);
+ if (CHECK_FAIL(link < 0)) {
+ perror("bpf_link_create(prog1)");
+ return;
+ }
+ CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1));
+
+ /* Expect failure attaching prog when link exists */
+ errno = 0;
+ err = bpf_prog_attach(prog2, -1, BPF_FLOW_DISSECTOR, 0);
+ if (CHECK_FAIL(!err || errno != EEXIST))
+ perror("bpf_prog_attach(prog2) expected EEXIST");
+ CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1));
+
+ close(link);
+ CHECK_FAIL(prog_is_attached(netns));
+}
+
+static void test_link_create_prog_detach(int netns, int prog1, int prog2)
+{
+ DECLARE_LIBBPF_OPTS(bpf_link_create_opts, opts);
+ int err, link;
+
+ link = bpf_link_create(prog1, netns, BPF_FLOW_DISSECTOR, &opts);
+ if (CHECK_FAIL(link < 0)) {
+ perror("bpf_link_create(prog1)");
+ return;
+ }
+ CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1));
+
+ /* Expect failure detaching prog when link exists */
+ errno = 0;
+ err = bpf_prog_detach(-1, BPF_FLOW_DISSECTOR);
+ if (CHECK_FAIL(!err || errno != EINVAL))
+ perror("bpf_prog_detach expected EINVAL");
+ CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1));
+
+ close(link);
+ CHECK_FAIL(prog_is_attached(netns));
+}
+
+static void test_prog_attach_detach_query(int netns, int prog1, int prog2)
+{
+ int err;
+
+ err = bpf_prog_attach(prog1, 0, BPF_FLOW_DISSECTOR, 0);
+ if (CHECK_FAIL(err)) {
+ perror("bpf_prog_attach(prog1)");
+ return;
+ }
+ CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1));
+
+ err = bpf_prog_detach(0, BPF_FLOW_DISSECTOR);
+ if (CHECK_FAIL(err)) {
+ perror("bpf_prog_detach");
+ return;
+ }
+
+ /* Expect no prog attached after successful detach */
+ CHECK_FAIL(prog_is_attached(netns));
+}
+
+static void test_link_create_close_query(int netns, int prog1, int prog2)
+{
+ DECLARE_LIBBPF_OPTS(bpf_link_create_opts, opts);
+ int link;
+
+ link = bpf_link_create(prog1, netns, BPF_FLOW_DISSECTOR, &opts);
+ if (CHECK_FAIL(link < 0)) {
+ perror("bpf_link_create(prog1)");
+ return;
+ }
+ CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1));
+
+ close(link);
+ /* Expect no prog attached after closing last link FD */
+ CHECK_FAIL(prog_is_attached(netns));
+}
+
+static void test_link_update_no_old_prog(int netns, int prog1, int prog2)
+{
+ DECLARE_LIBBPF_OPTS(bpf_link_create_opts, create_opts);
+ DECLARE_LIBBPF_OPTS(bpf_link_update_opts, update_opts);
+ int err, link;
+
+ link = bpf_link_create(prog1, netns, BPF_FLOW_DISSECTOR, &create_opts);
+ if (CHECK_FAIL(link < 0)) {
+ perror("bpf_link_create(prog1)");
+ return;
+ }
+ CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1));
+
+ /* Expect success replacing the prog when old prog not specified */
+ update_opts.flags = 0;
+ update_opts.old_prog_fd = 0;
+ err = bpf_link_update(link, prog2, &update_opts);
+ if (CHECK_FAIL(err))
+ perror("bpf_link_update");
+ CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog2));
+
+ close(link);
+ CHECK_FAIL(prog_is_attached(netns));
+}
+
+static void test_link_update_replace_old_prog(int netns, int prog1, int prog2)
+{
+ DECLARE_LIBBPF_OPTS(bpf_link_create_opts, create_opts);
+ DECLARE_LIBBPF_OPTS(bpf_link_update_opts, update_opts);
+ int err, link;
+ link = bpf_link_create(prog1, netns, BPF_FLOW_DISSECTOR, &create_opts);
+ if (CHECK_FAIL(link < 0)) {
+ perror("bpf_link_create(prog1)");
+ return;
+ }
+ CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1));
+
+ /* Expect success F_REPLACE and old prog specified to succeed */
+ update_opts.flags = BPF_F_REPLACE;
+ update_opts.old_prog_fd = prog1;
+ err = bpf_link_update(link, prog2, &update_opts);
+ if (CHECK_FAIL(err))
+ perror("bpf_link_update");
+ CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog2));
+
+ close(link);
+ CHECK_FAIL(prog_is_attached(netns));
+}
+
+static void test_link_update_invalid_opts(int netns, int prog1, int prog2)
+{
+ DECLARE_LIBBPF_OPTS(bpf_link_create_opts, create_opts);
+ DECLARE_LIBBPF_OPTS(bpf_link_update_opts, update_opts);
+ int err, link;
+
+ link = bpf_link_create(prog1, netns, BPF_FLOW_DISSECTOR, &create_opts);
+ if (CHECK_FAIL(link < 0)) {
+ perror("bpf_link_create(prog1)");
+ return;
+ }
+ CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1));
+
+ /* Expect update to fail w/ old prog FD but w/o F_REPLACE*/
+ errno = 0;
+ update_opts.flags = 0;
+ update_opts.old_prog_fd = prog1;
+ err = bpf_link_update(link, prog2, &update_opts);
+ if (CHECK_FAIL(!err || errno != EINVAL)) {
+ perror("bpf_link_update expected EINVAL");
+ goto out_close;
+ }
+ CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1));
+
+ /* Expect update to fail on old prog FD mismatch */
+ errno = 0;
+ update_opts.flags = BPF_F_REPLACE;
+ update_opts.old_prog_fd = prog2;
+ err = bpf_link_update(link, prog2, &update_opts);
+ if (CHECK_FAIL(!err || errno != EPERM)) {
+ perror("bpf_link_update expected EPERM");
+ goto out_close;
+ }
+ CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1));
+
+ /* Expect update to fail for invalid old prog FD */
+ errno = 0;
+ update_opts.flags = BPF_F_REPLACE;
+ update_opts.old_prog_fd = -1;
+ err = bpf_link_update(link, prog2, &update_opts);
+ if (CHECK_FAIL(!err || errno != EBADF)) {
+ perror("bpf_link_update expected EBADF");
+ goto out_close;
+ }
+ CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1));
+
+ /* Expect update to fail with invalid flags */
+ errno = 0;
+ update_opts.flags = BPF_F_ALLOW_MULTI;
+ update_opts.old_prog_fd = 0;
+ err = bpf_link_update(link, prog2, &update_opts);
+ if (CHECK_FAIL(!err || errno != EINVAL))
+ perror("bpf_link_update expected EINVAL");
+ CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1));
+
+out_close:
+ close(link);
+ CHECK_FAIL(prog_is_attached(netns));
+}
+
+static void test_link_update_invalid_prog(int netns, int prog1, int prog2)
+{
+ DECLARE_LIBBPF_OPTS(bpf_link_create_opts, create_opts);
+ DECLARE_LIBBPF_OPTS(bpf_link_update_opts, update_opts);
+ int err, link, prog3;
+
+ link = bpf_link_create(prog1, netns, BPF_FLOW_DISSECTOR, &create_opts);
+ if (CHECK_FAIL(link < 0)) {
+ perror("bpf_link_create(prog1)");
+ return;
+ }
+ CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1));
+
+ /* Expect failure when new prog FD is not valid */
+ errno = 0;
+ update_opts.flags = 0;
+ update_opts.old_prog_fd = 0;
+ err = bpf_link_update(link, -1, &update_opts);
+ if (CHECK_FAIL(!err || errno != EBADF)) {
+ perror("bpf_link_update expected EINVAL");
+ goto out_close_link;
+ }
+ CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1));
+
+ prog3 = load_prog(BPF_PROG_TYPE_SOCKET_FILTER);
+ if (prog3 < 0)
+ goto out_close_link;
+
+ /* Expect failure when new prog FD type doesn't match */
+ errno = 0;
+ update_opts.flags = 0;
+ update_opts.old_prog_fd = 0;
+ err = bpf_link_update(link, prog3, &update_opts);
+ if (CHECK_FAIL(!err || errno != EINVAL))
+ perror("bpf_link_update expected EINVAL");
+ CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1));
+
+ close(prog3);
+out_close_link:
+ close(link);
+ CHECK_FAIL(prog_is_attached(netns));
+}
+
+static void test_link_update_netns_gone(int netns, int prog1, int prog2)
+{
+ DECLARE_LIBBPF_OPTS(bpf_link_create_opts, create_opts);
+ DECLARE_LIBBPF_OPTS(bpf_link_update_opts, update_opts);
+ int err, link, old_net;
+
+ old_net = netns;
+ netns = unshare_net(old_net);
+ if (netns < 0)
+ return;
+
+ link = bpf_link_create(prog1, netns, BPF_FLOW_DISSECTOR, &create_opts);
+ if (CHECK_FAIL(link < 0)) {
+ perror("bpf_link_create(prog1)");
+ return;
+ }
+ CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1));
+
+ close(netns);
+ err = setns(old_net, CLONE_NEWNET);
+ if (CHECK_FAIL(err)) {
+ perror("setns(CLONE_NEWNET)");
+ close(link);
+ return;
+ }
+
+ /* Expect failure when netns destroyed */
+ errno = 0;
+ update_opts.flags = 0;
+ update_opts.old_prog_fd = 0;
+ err = bpf_link_update(link, prog2, &update_opts);
+ if (CHECK_FAIL(!err || errno != ENOLINK))
+ perror("bpf_link_update");
+
+ close(link);
+}
+
+static void test_link_get_info(int netns, int prog1, int prog2)
+{
+ DECLARE_LIBBPF_OPTS(bpf_link_create_opts, create_opts);
+ DECLARE_LIBBPF_OPTS(bpf_link_update_opts, update_opts);
+ struct bpf_link_info info = {};
+ struct stat netns_stat = {};
+ __u32 info_len, link_id;
+ int err, link, old_net;
+
+ old_net = netns;
+ netns = unshare_net(old_net);
+ if (netns < 0)
+ return;
+
+ err = fstat(netns, &netns_stat);
+ if (CHECK_FAIL(err)) {
+ perror("stat(netns)");
+ goto out_resetns;
+ }
+
+ link = bpf_link_create(prog1, netns, BPF_FLOW_DISSECTOR, &create_opts);
+ if (CHECK_FAIL(link < 0)) {
+ perror("bpf_link_create(prog1)");
+ goto out_resetns;
+ }
+
+ info_len = sizeof(info);
+ err = bpf_obj_get_info_by_fd(link, &info, &info_len);
+ if (CHECK_FAIL(err)) {
+ perror("bpf_obj_get_info");
+ goto out_unlink;
+ }
+ CHECK_FAIL(info_len != sizeof(info));
+
+ /* Expect link info to be sane and match prog and netns details */
+ CHECK_FAIL(info.type != BPF_LINK_TYPE_NETNS);
+ CHECK_FAIL(info.id == 0);
+ CHECK_FAIL(info.prog_id != query_prog_id(prog1));
+ CHECK_FAIL(info.netns.netns_ino != netns_stat.st_ino);
+ CHECK_FAIL(info.netns.attach_type != BPF_FLOW_DISSECTOR);
+
+ update_opts.flags = 0;
+ update_opts.old_prog_fd = 0;
+ err = bpf_link_update(link, prog2, &update_opts);
+ if (CHECK_FAIL(err)) {
+ perror("bpf_link_update(prog2)");
+ goto out_unlink;
+ }
+
+ link_id = info.id;
+ info_len = sizeof(info);
+ err = bpf_obj_get_info_by_fd(link, &info, &info_len);
+ if (CHECK_FAIL(err)) {
+ perror("bpf_obj_get_info");
+ goto out_unlink;
+ }
+ CHECK_FAIL(info_len != sizeof(info));
+
+ /* Expect no info change after update except in prog id */
+ CHECK_FAIL(info.type != BPF_LINK_TYPE_NETNS);
+ CHECK_FAIL(info.id != link_id);
+ CHECK_FAIL(info.prog_id != query_prog_id(prog2));
+ CHECK_FAIL(info.netns.netns_ino != netns_stat.st_ino);
+ CHECK_FAIL(info.netns.attach_type != BPF_FLOW_DISSECTOR);
+
+ /* Leave netns link is attached to and close last FD to it */
+ err = setns(old_net, CLONE_NEWNET);
+ if (CHECK_FAIL(err)) {
+ perror("setns(NEWNET)");
+ goto out_unlink;
+ }
+ close(netns);
+ old_net = -1;
+ netns = -1;
+
+ info_len = sizeof(info);
+ err = bpf_obj_get_info_by_fd(link, &info, &info_len);
+ if (CHECK_FAIL(err)) {
+ perror("bpf_obj_get_info");
+ goto out_unlink;
+ }
+ CHECK_FAIL(info_len != sizeof(info));
+
+ /* Expect netns_ino to change to 0 */
+ CHECK_FAIL(info.type != BPF_LINK_TYPE_NETNS);
+ CHECK_FAIL(info.id != link_id);
+ CHECK_FAIL(info.prog_id != query_prog_id(prog2));
+ CHECK_FAIL(info.netns.netns_ino != 0);
+ CHECK_FAIL(info.netns.attach_type != BPF_FLOW_DISSECTOR);
+
+out_unlink:
+ close(link);
+out_resetns:
+ if (old_net != -1)
+ setns(old_net, CLONE_NEWNET);
+ if (netns != -1)
+ close(netns);
+}
+
+static void run_tests(int netns)
+{
+ struct test {
+ const char *test_name;
+ void (*test_func)(int netns, int prog1, int prog2);
+ } tests[] = {
+ { "prog attach, prog attach",
+ test_prog_attach_prog_attach },
+ { "link create, link create",
+ test_link_create_link_create },
+ { "prog attach, link create",
+ test_prog_attach_link_create },
+ { "link create, prog attach",
+ test_link_create_prog_attach },
+ { "link create, prog detach",
+ test_link_create_prog_detach },
+ { "prog attach, detach, query",
+ test_prog_attach_detach_query },
+ { "link create, close, query",
+ test_link_create_close_query },
+ { "link update no old prog",
+ test_link_update_no_old_prog },
+ { "link update with replace old prog",
+ test_link_update_replace_old_prog },
+ { "link update invalid opts",
+ test_link_update_invalid_opts },
+ { "link update invalid prog",
+ test_link_update_invalid_prog },
+ { "link update netns gone",
+ test_link_update_netns_gone },
+ { "link get info",
+ test_link_get_info },
+ };
+ int i, progs[2] = { -1, -1 };
+ char test_name[80];
+
+ for (i = 0; i < ARRAY_SIZE(progs); i++) {
+ progs[i] = load_prog(BPF_PROG_TYPE_FLOW_DISSECTOR);
+ if (progs[i] < 0)
+ goto out_close;
+ }
+
+ for (i = 0; i < ARRAY_SIZE(tests); i++) {
+ snprintf(test_name, sizeof(test_name),
+ "flow dissector %s%s",
+ tests[i].test_name,
+ netns == init_net ? " (init_net)" : "");
+ if (test__start_subtest(test_name))
+ tests[i].test_func(netns, progs[0], progs[1]);
+ }
out_close:
- close(prog_fd[1]);
- close(prog_fd[0]);
+ for (i = 0; i < ARRAY_SIZE(progs); i++) {
+ if (progs[i] != -1)
+ CHECK_FAIL(close(progs[i]));
+ }
}
void test_flow_dissector_reattach(void)
{
- int init_net, self_net, err;
+ int err, new_net, saved_net;
- self_net = open("/proc/self/ns/net", O_RDONLY);
- if (CHECK_FAIL(self_net < 0)) {
+ saved_net = open("/proc/self/ns/net", O_RDONLY);
+ if (CHECK_FAIL(saved_net < 0)) {
perror("open(/proc/self/ns/net");
return;
}
@@ -111,30 +626,29 @@ void test_flow_dissector_reattach(void)
goto out_close;
}
- if (is_attached(init_net)) {
+ if (prog_is_attached(init_net)) {
test__skip();
printf("Can't test with flow dissector attached to init_net\n");
goto out_setns;
}
/* First run tests in root network namespace */
- do_flow_dissector_reattach();
+ run_tests(init_net);
/* Then repeat tests in a non-root namespace */
- err = unshare(CLONE_NEWNET);
- if (CHECK_FAIL(err)) {
- perror("unshare(CLONE_NEWNET)");
+ new_net = unshare_net(init_net);
+ if (new_net < 0)
goto out_setns;
- }
- do_flow_dissector_reattach();
+ run_tests(new_net);
+ close(new_net);
out_setns:
/* Move back to netns we started in. */
- err = setns(self_net, CLONE_NEWNET);
+ err = setns(saved_net, CLONE_NEWNET);
if (CHECK_FAIL(err))
perror("setns(/proc/self/ns/net)");
out_close:
close(init_net);
- close(self_net);
+ close(saved_net);
}
diff --git a/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c b/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c
index eba9a970703b..925722217edf 100644
--- a/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c
+++ b/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c
@@ -82,6 +82,7 @@ static void get_stack_print_output(void *ctx, int cpu, void *data, __u32 size)
void test_get_stack_raw_tp(void)
{
const char *file = "./test_get_stack_rawtp.o";
+ const char *file_err = "./test_get_stack_rawtp_err.o";
const char *prog_name = "raw_tracepoint/sys_enter";
int i, err, prog_fd, exp_cnt = MAX_CNT_RAWTP;
struct perf_buffer_opts pb_opts = {};
@@ -93,6 +94,10 @@ void test_get_stack_raw_tp(void)
struct bpf_map *map;
cpu_set_t cpu_set;
+ err = bpf_prog_load(file_err, BPF_PROG_TYPE_RAW_TRACEPOINT, &obj, &prog_fd);
+ if (CHECK(err >= 0, "prog_load raw tp", "err %d errno %d\n", err, errno))
+ return;
+
err = bpf_prog_load(file, BPF_PROG_TYPE_RAW_TRACEPOINT, &obj, &prog_fd);
if (CHECK(err, "prog_load raw tp", "err %d errno %d\n", err, errno))
return;
diff --git a/tools/testing/selftests/bpf/prog_tests/global_data.c b/tools/testing/selftests/bpf/prog_tests/global_data.c
index c680926fce73..e3cb62b0a110 100644
--- a/tools/testing/selftests/bpf/prog_tests/global_data.c
+++ b/tools/testing/selftests/bpf/prog_tests/global_data.c
@@ -1,5 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
#include <test_progs.h>
+#include <network_helpers.h>
static void test_global_data_number(struct bpf_object *obj, __u32 duration)
{
diff --git a/tools/testing/selftests/bpf/prog_tests/global_data_init.c b/tools/testing/selftests/bpf/prog_tests/global_data_init.c
new file mode 100644
index 000000000000..3bdaa5a40744
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/global_data_init.c
@@ -0,0 +1,61 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+
+void test_global_data_init(void)
+{
+ const char *file = "./test_global_data.o";
+ int err = -ENOMEM, map_fd, zero = 0;
+ __u8 *buff = NULL, *newval = NULL;
+ struct bpf_object *obj;
+ struct bpf_map *map;
+ __u32 duration = 0;
+ size_t sz;
+
+ obj = bpf_object__open_file(file, NULL);
+ if (CHECK_FAIL(!obj))
+ return;
+
+ map = bpf_object__find_map_by_name(obj, "test_glo.rodata");
+ if (CHECK_FAIL(!map || !bpf_map__is_internal(map)))
+ goto out;
+
+ sz = bpf_map__def(map)->value_size;
+ newval = malloc(sz);
+ if (CHECK_FAIL(!newval))
+ goto out;
+
+ memset(newval, 0, sz);
+ /* wrong size, should fail */
+ err = bpf_map__set_initial_value(map, newval, sz - 1);
+ if (CHECK(!err, "reject set initial value wrong size", "err %d\n", err))
+ goto out;
+
+ err = bpf_map__set_initial_value(map, newval, sz);
+ if (CHECK(err, "set initial value", "err %d\n", err))
+ goto out;
+
+ err = bpf_object__load(obj);
+ if (CHECK_FAIL(err))
+ goto out;
+
+ map_fd = bpf_map__fd(map);
+ if (CHECK_FAIL(map_fd < 0))
+ goto out;
+
+ buff = malloc(sz);
+ if (buff)
+ err = bpf_map_lookup_elem(map_fd, &zero, buff);
+ if (CHECK(!buff || err || memcmp(buff, newval, sz),
+ "compare .rodata map data override",
+ "err %d errno %d\n", err, errno))
+ goto out;
+
+ memset(newval, 1, sz);
+ /* object loaded - should fail */
+ err = bpf_map__set_initial_value(map, newval, sz);
+ CHECK(!err, "reject set initial value after load", "err %d\n", err);
+out:
+ free(buff);
+ free(newval);
+ bpf_object__close(obj);
+}
diff --git a/tools/testing/selftests/bpf/test_hashmap.c b/tools/testing/selftests/bpf/prog_tests/hashmap.c
index c490e012c23f..428d488830c6 100644
--- a/tools/testing/selftests/bpf/test_hashmap.c
+++ b/tools/testing/selftests/bpf/prog_tests/hashmap.c
@@ -5,26 +5,17 @@
*
* Copyright (c) 2019 Facebook
*/
-#include <stdio.h>
-#include <errno.h>
-#include <linux/err.h>
+#include "test_progs.h"
#include "bpf/hashmap.h"
-#define CHECK(condition, format...) ({ \
- int __ret = !!(condition); \
- if (__ret) { \
- fprintf(stderr, "%s:%d:FAIL ", __func__, __LINE__); \
- fprintf(stderr, format); \
- } \
- __ret; \
-})
+static int duration = 0;
-size_t hash_fn(const void *k, void *ctx)
+static size_t hash_fn(const void *k, void *ctx)
{
return (long)k;
}
-bool equal_fn(const void *a, const void *b, void *ctx)
+static bool equal_fn(const void *a, const void *b, void *ctx)
{
return (long)a == (long)b;
}
@@ -49,53 +40,55 @@ static inline size_t exp_cap(size_t sz)
#define ELEM_CNT 62
-int test_hashmap_generic(void)
+static void test_hashmap_generic(void)
{
struct hashmap_entry *entry, *tmp;
int err, bkt, found_cnt, i;
long long found_msk;
struct hashmap *map;
- fprintf(stderr, "%s: ", __func__);
-
map = hashmap__new(hash_fn, equal_fn, NULL);
- if (CHECK(IS_ERR(map), "failed to create map: %ld\n", PTR_ERR(map)))
- return 1;
+ if (CHECK(IS_ERR(map), "hashmap__new",
+ "failed to create map: %ld\n", PTR_ERR(map)))
+ return;
for (i = 0; i < ELEM_CNT; i++) {
const void *oldk, *k = (const void *)(long)i;
void *oldv, *v = (void *)(long)(1024 + i);
err = hashmap__update(map, k, v, &oldk, &oldv);
- if (CHECK(err != -ENOENT, "unexpected result: %d\n", err))
- return 1;
+ if (CHECK(err != -ENOENT, "hashmap__update",
+ "unexpected result: %d\n", err))
+ goto cleanup;
if (i % 2) {
err = hashmap__add(map, k, v);
} else {
err = hashmap__set(map, k, v, &oldk, &oldv);
- if (CHECK(oldk != NULL || oldv != NULL,
+ if (CHECK(oldk != NULL || oldv != NULL, "check_kv",
"unexpected k/v: %p=%p\n", oldk, oldv))
- return 1;
+ goto cleanup;
}
- if (CHECK(err, "failed to add k/v %ld = %ld: %d\n",
+ if (CHECK(err, "elem_add", "failed to add k/v %ld = %ld: %d\n",
(long)k, (long)v, err))
- return 1;
+ goto cleanup;
- if (CHECK(!hashmap__find(map, k, &oldv),
+ if (CHECK(!hashmap__find(map, k, &oldv), "elem_find",
"failed to find key %ld\n", (long)k))
- return 1;
- if (CHECK(oldv != v, "found value is wrong: %ld\n", (long)oldv))
- return 1;
+ goto cleanup;
+ if (CHECK(oldv != v, "elem_val",
+ "found value is wrong: %ld\n", (long)oldv))
+ goto cleanup;
}
- if (CHECK(hashmap__size(map) != ELEM_CNT,
+ if (CHECK(hashmap__size(map) != ELEM_CNT, "hashmap__size",
"invalid map size: %zu\n", hashmap__size(map)))
- return 1;
+ goto cleanup;
if (CHECK(hashmap__capacity(map) != exp_cap(hashmap__size(map)),
+ "hashmap_cap",
"unexpected map capacity: %zu\n", hashmap__capacity(map)))
- return 1;
+ goto cleanup;
found_msk = 0;
hashmap__for_each_entry(map, entry, bkt) {
@@ -103,42 +96,47 @@ int test_hashmap_generic(void)
long v = (long)entry->value;
found_msk |= 1ULL << k;
- if (CHECK(v - k != 1024, "invalid k/v pair: %ld = %ld\n", k, v))
- return 1;
+ if (CHECK(v - k != 1024, "check_kv",
+ "invalid k/v pair: %ld = %ld\n", k, v))
+ goto cleanup;
}
- if (CHECK(found_msk != (1ULL << ELEM_CNT) - 1,
+ if (CHECK(found_msk != (1ULL << ELEM_CNT) - 1, "elem_cnt",
"not all keys iterated: %llx\n", found_msk))
- return 1;
+ goto cleanup;
for (i = 0; i < ELEM_CNT; i++) {
const void *oldk, *k = (const void *)(long)i;
void *oldv, *v = (void *)(long)(256 + i);
err = hashmap__add(map, k, v);
- if (CHECK(err != -EEXIST, "unexpected add result: %d\n", err))
- return 1;
+ if (CHECK(err != -EEXIST, "hashmap__add",
+ "unexpected add result: %d\n", err))
+ goto cleanup;
if (i % 2)
err = hashmap__update(map, k, v, &oldk, &oldv);
else
err = hashmap__set(map, k, v, &oldk, &oldv);
- if (CHECK(err, "failed to update k/v %ld = %ld: %d\n",
- (long)k, (long)v, err))
- return 1;
- if (CHECK(!hashmap__find(map, k, &oldv),
+ if (CHECK(err, "elem_upd",
+ "failed to update k/v %ld = %ld: %d\n",
+ (long)k, (long)v, err))
+ goto cleanup;
+ if (CHECK(!hashmap__find(map, k, &oldv), "elem_find",
"failed to find key %ld\n", (long)k))
- return 1;
- if (CHECK(oldv != v, "found value is wrong: %ld\n", (long)oldv))
- return 1;
+ goto cleanup;
+ if (CHECK(oldv != v, "elem_val",
+ "found value is wrong: %ld\n", (long)oldv))
+ goto cleanup;
}
- if (CHECK(hashmap__size(map) != ELEM_CNT,
+ if (CHECK(hashmap__size(map) != ELEM_CNT, "hashmap__size",
"invalid updated map size: %zu\n", hashmap__size(map)))
- return 1;
+ goto cleanup;
if (CHECK(hashmap__capacity(map) != exp_cap(hashmap__size(map)),
+ "hashmap__capacity",
"unexpected map capacity: %zu\n", hashmap__capacity(map)))
- return 1;
+ goto cleanup;
found_msk = 0;
hashmap__for_each_entry_safe(map, entry, tmp, bkt) {
@@ -146,20 +144,21 @@ int test_hashmap_generic(void)
long v = (long)entry->value;
found_msk |= 1ULL << k;
- if (CHECK(v - k != 256,
+ if (CHECK(v - k != 256, "elem_check",
"invalid updated k/v pair: %ld = %ld\n", k, v))
- return 1;
+ goto cleanup;
}
- if (CHECK(found_msk != (1ULL << ELEM_CNT) - 1,
+ if (CHECK(found_msk != (1ULL << ELEM_CNT) - 1, "elem_cnt",
"not all keys iterated after update: %llx\n", found_msk))
- return 1;
+ goto cleanup;
found_cnt = 0;
hashmap__for_each_key_entry(map, entry, (void *)0) {
found_cnt++;
}
- if (CHECK(!found_cnt, "didn't find any entries for key 0\n"))
- return 1;
+ if (CHECK(!found_cnt, "found_cnt",
+ "didn't find any entries for key 0\n"))
+ goto cleanup;
found_msk = 0;
found_cnt = 0;
@@ -173,30 +172,31 @@ int test_hashmap_generic(void)
found_cnt++;
found_msk |= 1ULL << (long)k;
- if (CHECK(!hashmap__delete(map, k, &oldk, &oldv),
+ if (CHECK(!hashmap__delete(map, k, &oldk, &oldv), "elem_del",
"failed to delete k/v %ld = %ld\n",
(long)k, (long)v))
- return 1;
- if (CHECK(oldk != k || oldv != v,
+ goto cleanup;
+ if (CHECK(oldk != k || oldv != v, "check_old",
"invalid deleted k/v: expected %ld = %ld, got %ld = %ld\n",
(long)k, (long)v, (long)oldk, (long)oldv))
- return 1;
- if (CHECK(hashmap__delete(map, k, &oldk, &oldv),
+ goto cleanup;
+ if (CHECK(hashmap__delete(map, k, &oldk, &oldv), "elem_del",
"unexpectedly deleted k/v %ld = %ld\n",
(long)oldk, (long)oldv))
- return 1;
+ goto cleanup;
}
- if (CHECK(!found_cnt || !found_msk,
+ if (CHECK(!found_cnt || !found_msk, "found_entries",
"didn't delete any key entries\n"))
- return 1;
- if (CHECK(hashmap__size(map) != ELEM_CNT - found_cnt,
+ goto cleanup;
+ if (CHECK(hashmap__size(map) != ELEM_CNT - found_cnt, "elem_cnt",
"invalid updated map size (already deleted: %d): %zu\n",
found_cnt, hashmap__size(map)))
- return 1;
+ goto cleanup;
if (CHECK(hashmap__capacity(map) != exp_cap(hashmap__size(map)),
+ "hashmap__capacity",
"unexpected map capacity: %zu\n", hashmap__capacity(map)))
- return 1;
+ goto cleanup;
hashmap__for_each_entry_safe(map, entry, tmp, bkt) {
const void *oldk, *k;
@@ -208,53 +208,56 @@ int test_hashmap_generic(void)
found_cnt++;
found_msk |= 1ULL << (long)k;
- if (CHECK(!hashmap__delete(map, k, &oldk, &oldv),
+ if (CHECK(!hashmap__delete(map, k, &oldk, &oldv), "elem_del",
"failed to delete k/v %ld = %ld\n",
(long)k, (long)v))
- return 1;
- if (CHECK(oldk != k || oldv != v,
+ goto cleanup;
+ if (CHECK(oldk != k || oldv != v, "elem_check",
"invalid old k/v: expect %ld = %ld, got %ld = %ld\n",
(long)k, (long)v, (long)oldk, (long)oldv))
- return 1;
- if (CHECK(hashmap__delete(map, k, &oldk, &oldv),
+ goto cleanup;
+ if (CHECK(hashmap__delete(map, k, &oldk, &oldv), "elem_del",
"unexpectedly deleted k/v %ld = %ld\n",
(long)k, (long)v))
- return 1;
+ goto cleanup;
}
if (CHECK(found_cnt != ELEM_CNT || found_msk != (1ULL << ELEM_CNT) - 1,
+ "found_cnt",
"not all keys were deleted: found_cnt:%d, found_msk:%llx\n",
found_cnt, found_msk))
- return 1;
- if (CHECK(hashmap__size(map) != 0,
+ goto cleanup;
+ if (CHECK(hashmap__size(map) != 0, "hashmap__size",
"invalid updated map size (already deleted: %d): %zu\n",
found_cnt, hashmap__size(map)))
- return 1;
+ goto cleanup;
found_cnt = 0;
hashmap__for_each_entry(map, entry, bkt) {
- CHECK(false, "unexpected map entries left: %ld = %ld\n",
- (long)entry->key, (long)entry->value);
- return 1;
+ CHECK(false, "elem_exists",
+ "unexpected map entries left: %ld = %ld\n",
+ (long)entry->key, (long)entry->value);
+ goto cleanup;
}
- hashmap__free(map);
+ hashmap__clear(map);
hashmap__for_each_entry(map, entry, bkt) {
- CHECK(false, "unexpected map entries left: %ld = %ld\n",
- (long)entry->key, (long)entry->value);
- return 1;
+ CHECK(false, "elem_exists",
+ "unexpected map entries left: %ld = %ld\n",
+ (long)entry->key, (long)entry->value);
+ goto cleanup;
}
- fprintf(stderr, "OK\n");
- return 0;
+cleanup:
+ hashmap__free(map);
}
-size_t collision_hash_fn(const void *k, void *ctx)
+static size_t collision_hash_fn(const void *k, void *ctx)
{
return 0;
}
-int test_hashmap_multimap(void)
+static void test_hashmap_multimap(void)
{
void *k1 = (void *)0, *k2 = (void *)1;
struct hashmap_entry *entry;
@@ -262,121 +265,116 @@ int test_hashmap_multimap(void)
long found_msk;
int err, bkt;
- fprintf(stderr, "%s: ", __func__);
-
/* force collisions */
map = hashmap__new(collision_hash_fn, equal_fn, NULL);
- if (CHECK(IS_ERR(map), "failed to create map: %ld\n", PTR_ERR(map)))
- return 1;
-
+ if (CHECK(IS_ERR(map), "hashmap__new",
+ "failed to create map: %ld\n", PTR_ERR(map)))
+ return;
/* set up multimap:
* [0] -> 1, 2, 4;
* [1] -> 8, 16, 32;
*/
err = hashmap__append(map, k1, (void *)1);
- if (CHECK(err, "failed to add k/v: %d\n", err))
- return 1;
+ if (CHECK(err, "elem_add", "failed to add k/v: %d\n", err))
+ goto cleanup;
err = hashmap__append(map, k1, (void *)2);
- if (CHECK(err, "failed to add k/v: %d\n", err))
- return 1;
+ if (CHECK(err, "elem_add", "failed to add k/v: %d\n", err))
+ goto cleanup;
err = hashmap__append(map, k1, (void *)4);
- if (CHECK(err, "failed to add k/v: %d\n", err))
- return 1;
+ if (CHECK(err, "elem_add", "failed to add k/v: %d\n", err))
+ goto cleanup;
err = hashmap__append(map, k2, (void *)8);
- if (CHECK(err, "failed to add k/v: %d\n", err))
- return 1;
+ if (CHECK(err, "elem_add", "failed to add k/v: %d\n", err))
+ goto cleanup;
err = hashmap__append(map, k2, (void *)16);
- if (CHECK(err, "failed to add k/v: %d\n", err))
- return 1;
+ if (CHECK(err, "elem_add", "failed to add k/v: %d\n", err))
+ goto cleanup;
err = hashmap__append(map, k2, (void *)32);
- if (CHECK(err, "failed to add k/v: %d\n", err))
- return 1;
+ if (CHECK(err, "elem_add", "failed to add k/v: %d\n", err))
+ goto cleanup;
- if (CHECK(hashmap__size(map) != 6,
+ if (CHECK(hashmap__size(map) != 6, "hashmap_size",
"invalid map size: %zu\n", hashmap__size(map)))
- return 1;
+ goto cleanup;
/* verify global iteration still works and sees all values */
found_msk = 0;
hashmap__for_each_entry(map, entry, bkt) {
found_msk |= (long)entry->value;
}
- if (CHECK(found_msk != (1 << 6) - 1,
+ if (CHECK(found_msk != (1 << 6) - 1, "found_msk",
"not all keys iterated: %lx\n", found_msk))
- return 1;
+ goto cleanup;
/* iterate values for key 1 */
found_msk = 0;
hashmap__for_each_key_entry(map, entry, k1) {
found_msk |= (long)entry->value;
}
- if (CHECK(found_msk != (1 | 2 | 4),
+ if (CHECK(found_msk != (1 | 2 | 4), "found_msk",
"invalid k1 values: %lx\n", found_msk))
- return 1;
+ goto cleanup;
/* iterate values for key 2 */
found_msk = 0;
hashmap__for_each_key_entry(map, entry, k2) {
found_msk |= (long)entry->value;
}
- if (CHECK(found_msk != (8 | 16 | 32),
+ if (CHECK(found_msk != (8 | 16 | 32), "found_msk",
"invalid k2 values: %lx\n", found_msk))
- return 1;
+ goto cleanup;
- fprintf(stderr, "OK\n");
- return 0;
+cleanup:
+ hashmap__free(map);
}
-int test_hashmap_empty()
+static void test_hashmap_empty()
{
struct hashmap_entry *entry;
int bkt;
struct hashmap *map;
void *k = (void *)0;
- fprintf(stderr, "%s: ", __func__);
-
/* force collisions */
map = hashmap__new(hash_fn, equal_fn, NULL);
- if (CHECK(IS_ERR(map), "failed to create map: %ld\n", PTR_ERR(map)))
- return 1;
+ if (CHECK(IS_ERR(map), "hashmap__new",
+ "failed to create map: %ld\n", PTR_ERR(map)))
+ goto cleanup;
- if (CHECK(hashmap__size(map) != 0,
+ if (CHECK(hashmap__size(map) != 0, "hashmap__size",
"invalid map size: %zu\n", hashmap__size(map)))
- return 1;
- if (CHECK(hashmap__capacity(map) != 0,
+ goto cleanup;
+ if (CHECK(hashmap__capacity(map) != 0, "hashmap__capacity",
"invalid map capacity: %zu\n", hashmap__capacity(map)))
- return 1;
- if (CHECK(hashmap__find(map, k, NULL), "unexpected find\n"))
- return 1;
- if (CHECK(hashmap__delete(map, k, NULL, NULL), "unexpected delete\n"))
- return 1;
+ goto cleanup;
+ if (CHECK(hashmap__find(map, k, NULL), "elem_find",
+ "unexpected find\n"))
+ goto cleanup;
+ if (CHECK(hashmap__delete(map, k, NULL, NULL), "elem_del",
+ "unexpected delete\n"))
+ goto cleanup;
hashmap__for_each_entry(map, entry, bkt) {
- CHECK(false, "unexpected iterated entry\n");
- return 1;
+ CHECK(false, "elem_found", "unexpected iterated entry\n");
+ goto cleanup;
}
hashmap__for_each_key_entry(map, entry, k) {
- CHECK(false, "unexpected key entry\n");
- return 1;
+ CHECK(false, "key_found", "unexpected key entry\n");
+ goto cleanup;
}
- fprintf(stderr, "OK\n");
- return 0;
+cleanup:
+ hashmap__free(map);
}
-int main(int argc, char **argv)
+void test_hashmap()
{
- bool failed = false;
-
- if (test_hashmap_generic())
- failed = true;
- if (test_hashmap_multimap())
- failed = true;
- if (test_hashmap_empty())
- failed = true;
-
- return failed;
+ if (test__start_subtest("generic"))
+ test_hashmap_generic();
+ if (test__start_subtest("multimap"))
+ test_hashmap_multimap();
+ if (test__start_subtest("empty"))
+ test_hashmap_empty();
}
diff --git a/tools/testing/selftests/bpf/prog_tests/kfree_skb.c b/tools/testing/selftests/bpf/prog_tests/kfree_skb.c
index 7507c8f689bc..42c3a3103c26 100644
--- a/tools/testing/selftests/bpf/prog_tests/kfree_skb.c
+++ b/tools/testing/selftests/bpf/prog_tests/kfree_skb.c
@@ -1,5 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
#include <test_progs.h>
+#include <network_helpers.h>
struct meta {
int ifindex;
diff --git a/tools/testing/selftests/bpf/prog_tests/l4lb_all.c b/tools/testing/selftests/bpf/prog_tests/l4lb_all.c
index eaf64595be88..c2d373e294bb 100644
--- a/tools/testing/selftests/bpf/prog_tests/l4lb_all.c
+++ b/tools/testing/selftests/bpf/prog_tests/l4lb_all.c
@@ -1,5 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
#include <test_progs.h>
+#include <network_helpers.h>
static void test_l4lb(const char *file)
{
diff --git a/tools/testing/selftests/bpf/prog_tests/link_pinning.c b/tools/testing/selftests/bpf/prog_tests/link_pinning.c
new file mode 100644
index 000000000000..a743288cf384
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/link_pinning.c
@@ -0,0 +1,105 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+
+#include <test_progs.h>
+#include <sys/stat.h>
+
+#include "test_link_pinning.skel.h"
+
+static int duration = 0;
+
+void test_link_pinning_subtest(struct bpf_program *prog,
+ struct test_link_pinning__bss *bss)
+{
+ const char *link_pin_path = "/sys/fs/bpf/pinned_link_test";
+ struct stat statbuf = {};
+ struct bpf_link *link;
+ int err, i;
+
+ link = bpf_program__attach(prog);
+ if (CHECK(IS_ERR(link), "link_attach", "err: %ld\n", PTR_ERR(link)))
+ goto cleanup;
+
+ bss->in = 1;
+ usleep(1);
+ CHECK(bss->out != 1, "res_check1", "exp %d, got %d\n", 1, bss->out);
+
+ /* pin link */
+ err = bpf_link__pin(link, link_pin_path);
+ if (CHECK(err, "link_pin", "err: %d\n", err))
+ goto cleanup;
+
+ CHECK(strcmp(link_pin_path, bpf_link__pin_path(link)), "pin_path1",
+ "exp %s, got %s\n", link_pin_path, bpf_link__pin_path(link));
+
+ /* check that link was pinned */
+ err = stat(link_pin_path, &statbuf);
+ if (CHECK(err, "stat_link", "err %d errno %d\n", err, errno))
+ goto cleanup;
+
+ bss->in = 2;
+ usleep(1);
+ CHECK(bss->out != 2, "res_check2", "exp %d, got %d\n", 2, bss->out);
+
+ /* destroy link, pinned link should keep program attached */
+ bpf_link__destroy(link);
+ link = NULL;
+
+ bss->in = 3;
+ usleep(1);
+ CHECK(bss->out != 3, "res_check3", "exp %d, got %d\n", 3, bss->out);
+
+ /* re-open link from BPFFS */
+ link = bpf_link__open(link_pin_path);
+ if (CHECK(IS_ERR(link), "link_open", "err: %ld\n", PTR_ERR(link)))
+ goto cleanup;
+
+ CHECK(strcmp(link_pin_path, bpf_link__pin_path(link)), "pin_path2",
+ "exp %s, got %s\n", link_pin_path, bpf_link__pin_path(link));
+
+ /* unpin link from BPFFS, program still attached */
+ err = bpf_link__unpin(link);
+ if (CHECK(err, "link_unpin", "err: %d\n", err))
+ goto cleanup;
+
+ /* still active, as we have FD open now */
+ bss->in = 4;
+ usleep(1);
+ CHECK(bss->out != 4, "res_check4", "exp %d, got %d\n", 4, bss->out);
+
+ bpf_link__destroy(link);
+ link = NULL;
+
+ /* Validate it's finally detached.
+ * Actual detachment might get delayed a bit, so there is no reliable
+ * way to validate it immediately here, let's count up for long enough
+ * and see if eventually output stops being updated
+ */
+ for (i = 5; i < 10000; i++) {
+ bss->in = i;
+ usleep(1);
+ if (bss->out == i - 1)
+ break;
+ }
+ CHECK(i == 10000, "link_attached", "got to iteration #%d\n", i);
+
+cleanup:
+ if (!IS_ERR(link))
+ bpf_link__destroy(link);
+}
+
+void test_link_pinning(void)
+{
+ struct test_link_pinning* skel;
+
+ skel = test_link_pinning__open_and_load();
+ if (CHECK(!skel, "skel_open", "failed to open skeleton\n"))
+ return;
+
+ if (test__start_subtest("pin_raw_tp"))
+ test_link_pinning_subtest(skel->progs.raw_tp_prog, skel->bss);
+ if (test__start_subtest("pin_tp_btf"))
+ test_link_pinning_subtest(skel->progs.tp_btf_prog, skel->bss);
+
+ test_link_pinning__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/map_lock.c b/tools/testing/selftests/bpf/prog_tests/map_lock.c
index 8f91f1881d11..ce17b1ed8709 100644
--- a/tools/testing/selftests/bpf/prog_tests/map_lock.c
+++ b/tools/testing/selftests/bpf/prog_tests/map_lock.c
@@ -1,5 +1,19 @@
// SPDX-License-Identifier: GPL-2.0
#include <test_progs.h>
+#include <network_helpers.h>
+
+static void *spin_lock_thread(void *arg)
+{
+ __u32 duration, retval;
+ int err, prog_fd = *(u32 *) arg;
+
+ err = bpf_prog_test_run(prog_fd, 10000, &pkt_v4, sizeof(pkt_v4),
+ NULL, NULL, &retval, &duration);
+ CHECK(err || retval, "",
+ "err %d errno %d retval %d duration %d\n",
+ err, errno, retval, duration);
+ pthread_exit(arg);
+}
static void *parallel_map_access(void *arg)
{
diff --git a/tools/testing/selftests/bpf/prog_tests/mmap.c b/tools/testing/selftests/bpf/prog_tests/mmap.c
index 16a814eb4d64..43d0b5578f46 100644
--- a/tools/testing/selftests/bpf/prog_tests/mmap.c
+++ b/tools/testing/selftests/bpf/prog_tests/mmap.c
@@ -19,15 +19,16 @@ void test_mmap(void)
const size_t map_sz = roundup_page(sizeof(struct map_data));
const int zero = 0, one = 1, two = 2, far = 1500;
const long page_size = sysconf(_SC_PAGE_SIZE);
- int err, duration = 0, i, data_map_fd;
+ int err, duration = 0, i, data_map_fd, data_map_id, tmp_fd, rdmap_fd;
struct bpf_map *data_map, *bss_map;
void *bss_mmaped = NULL, *map_mmaped = NULL, *tmp1, *tmp2;
struct test_mmap__bss *bss_data;
+ struct bpf_map_info map_info;
+ __u32 map_info_sz = sizeof(map_info);
struct map_data *map_data;
struct test_mmap *skel;
__u64 val = 0;
-
skel = test_mmap__open_and_load();
if (CHECK(!skel, "skel_open_and_load", "skeleton open/load failed\n"))
return;
@@ -36,6 +37,25 @@ void test_mmap(void)
data_map = skel->maps.data_map;
data_map_fd = bpf_map__fd(data_map);
+ rdmap_fd = bpf_map__fd(skel->maps.rdonly_map);
+ tmp1 = mmap(NULL, 4096, PROT_READ | PROT_WRITE, MAP_SHARED, rdmap_fd, 0);
+ if (CHECK(tmp1 != MAP_FAILED, "rdonly_write_mmap", "unexpected success\n")) {
+ munmap(tmp1, 4096);
+ goto cleanup;
+ }
+ /* now double-check if it's mmap()'able at all */
+ tmp1 = mmap(NULL, 4096, PROT_READ, MAP_SHARED, rdmap_fd, 0);
+ if (CHECK(tmp1 == MAP_FAILED, "rdonly_read_mmap", "failed: %d\n", errno))
+ goto cleanup;
+
+ /* get map's ID */
+ memset(&map_info, 0, map_info_sz);
+ err = bpf_obj_get_info_by_fd(data_map_fd, &map_info, &map_info_sz);
+ if (CHECK(err, "map_get_info", "failed %d\n", errno))
+ goto cleanup;
+ data_map_id = map_info.id;
+
+ /* mmap BSS map */
bss_mmaped = mmap(NULL, bss_sz, PROT_READ | PROT_WRITE, MAP_SHARED,
bpf_map__fd(bss_map), 0);
if (CHECK(bss_mmaped == MAP_FAILED, "bss_mmap",
@@ -98,6 +118,10 @@ void test_mmap(void)
"data_map freeze succeeded: err=%d, errno=%d\n", err, errno))
goto cleanup;
+ err = mprotect(map_mmaped, map_sz, PROT_READ);
+ if (CHECK(err, "mprotect_ro", "mprotect to r/o failed %d\n", errno))
+ goto cleanup;
+
/* unmap R/W mapping */
err = munmap(map_mmaped, map_sz);
map_mmaped = NULL;
@@ -111,6 +135,12 @@ void test_mmap(void)
map_mmaped = NULL;
goto cleanup;
}
+ err = mprotect(map_mmaped, map_sz, PROT_WRITE);
+ if (CHECK(!err, "mprotect_wr", "mprotect() succeeded unexpectedly!\n"))
+ goto cleanup;
+ err = mprotect(map_mmaped, map_sz, PROT_EXEC);
+ if (CHECK(!err, "mprotect_ex", "mprotect() succeeded unexpectedly!\n"))
+ goto cleanup;
map_data = map_mmaped;
/* map/unmap in a loop to test ref counting */
@@ -197,6 +227,53 @@ void test_mmap(void)
CHECK_FAIL(map_data->val[far] != 3 * 321);
munmap(tmp2, 4 * page_size);
+
+ /* map all 4 pages, but with pg_off=1 page, should fail */
+ tmp1 = mmap(NULL, 4 * page_size, PROT_READ, MAP_SHARED | MAP_FIXED,
+ data_map_fd, page_size /* initial page shift */);
+ if (CHECK(tmp1 != MAP_FAILED, "adv_mmap7", "unexpected success")) {
+ munmap(tmp1, 4 * page_size);
+ goto cleanup;
+ }
+
+ tmp1 = mmap(NULL, map_sz, PROT_READ, MAP_SHARED, data_map_fd, 0);
+ if (CHECK(tmp1 == MAP_FAILED, "last_mmap", "failed %d\n", errno))
+ goto cleanup;
+
+ test_mmap__destroy(skel);
+ skel = NULL;
+ CHECK_FAIL(munmap(bss_mmaped, bss_sz));
+ bss_mmaped = NULL;
+ CHECK_FAIL(munmap(map_mmaped, map_sz));
+ map_mmaped = NULL;
+
+ /* map should be still held by active mmap */
+ tmp_fd = bpf_map_get_fd_by_id(data_map_id);
+ if (CHECK(tmp_fd < 0, "get_map_by_id", "failed %d\n", errno)) {
+ munmap(tmp1, map_sz);
+ goto cleanup;
+ }
+ close(tmp_fd);
+
+ /* this should release data map finally */
+ munmap(tmp1, map_sz);
+
+ /* we need to wait for RCU grace period */
+ for (i = 0; i < 10000; i++) {
+ __u32 id = data_map_id - 1;
+ if (bpf_map_get_next_id(id, &id) || id > data_map_id)
+ break;
+ usleep(1);
+ }
+
+ /* should fail to get map FD by non-existing ID */
+ tmp_fd = bpf_map_get_fd_by_id(data_map_id);
+ if (CHECK(tmp_fd >= 0, "get_map_by_id_after",
+ "unexpectedly succeeded %d\n", tmp_fd)) {
+ close(tmp_fd);
+ goto cleanup;
+ }
+
cleanup:
if (bss_mmaped)
CHECK_FAIL(munmap(bss_mmaped, bss_sz));
diff --git a/tools/testing/selftests/bpf/prog_tests/modify_return.c b/tools/testing/selftests/bpf/prog_tests/modify_return.c
new file mode 100644
index 000000000000..97fec70c600b
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/modify_return.c
@@ -0,0 +1,65 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright 2020 Google LLC.
+ */
+
+#include <test_progs.h>
+#include "modify_return.skel.h"
+
+#define LOWER(x) ((x) & 0xffff)
+#define UPPER(x) ((x) >> 16)
+
+
+static void run_test(__u32 input_retval, __u16 want_side_effect, __s16 want_ret)
+{
+ struct modify_return *skel = NULL;
+ int err, prog_fd;
+ __u32 duration = 0, retval;
+ __u16 side_effect;
+ __s16 ret;
+
+ skel = modify_return__open_and_load();
+ if (CHECK(!skel, "skel_load", "modify_return skeleton failed\n"))
+ goto cleanup;
+
+ err = modify_return__attach(skel);
+ if (CHECK(err, "modify_return", "attach failed: %d\n", err))
+ goto cleanup;
+
+ skel->bss->input_retval = input_retval;
+ prog_fd = bpf_program__fd(skel->progs.fmod_ret_test);
+ err = bpf_prog_test_run(prog_fd, 1, NULL, 0, NULL, 0,
+ &retval, &duration);
+
+ CHECK(err, "test_run", "err %d errno %d\n", err, errno);
+
+ side_effect = UPPER(retval);
+ ret = LOWER(retval);
+
+ CHECK(ret != want_ret, "test_run",
+ "unexpected ret: %d, expected: %d\n", ret, want_ret);
+ CHECK(side_effect != want_side_effect, "modify_return",
+ "unexpected side_effect: %d\n", side_effect);
+
+ CHECK(skel->bss->fentry_result != 1, "modify_return",
+ "fentry failed\n");
+ CHECK(skel->bss->fexit_result != 1, "modify_return",
+ "fexit failed\n");
+ CHECK(skel->bss->fmod_ret_result != 1, "modify_return",
+ "fmod_ret failed\n");
+
+cleanup:
+ modify_return__destroy(skel);
+}
+
+void test_modify_return(void)
+{
+ run_test(0 /* input_retval */,
+ 1 /* want_side_effect */,
+ 4 /* want_ret */);
+ run_test(-EINVAL /* input_retval */,
+ 0 /* want_side_effect */,
+ -EINVAL /* want_ret */);
+}
+
diff --git a/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c b/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c
new file mode 100644
index 000000000000..e74dc501b27f
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c
@@ -0,0 +1,85 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Carlos Neira cneirabustos@gmail.com */
+#include <test_progs.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <unistd.h>
+#include <sys/syscall.h>
+
+struct bss {
+ __u64 dev;
+ __u64 ino;
+ __u64 pid_tgid;
+ __u64 user_pid_tgid;
+};
+
+void test_ns_current_pid_tgid(void)
+{
+ const char *probe_name = "raw_tracepoint/sys_enter";
+ const char *file = "test_ns_current_pid_tgid.o";
+ int err, key = 0, duration = 0;
+ struct bpf_link *link = NULL;
+ struct bpf_program *prog;
+ struct bpf_map *bss_map;
+ struct bpf_object *obj;
+ struct bss bss;
+ struct stat st;
+ __u64 id;
+
+ obj = bpf_object__open_file(file, NULL);
+ if (CHECK(IS_ERR(obj), "obj_open", "err %ld\n", PTR_ERR(obj)))
+ return;
+
+ err = bpf_object__load(obj);
+ if (CHECK(err, "obj_load", "err %d errno %d\n", err, errno))
+ goto cleanup;
+
+ bss_map = bpf_object__find_map_by_name(obj, "test_ns_.bss");
+ if (CHECK(!bss_map, "find_bss_map", "failed\n"))
+ goto cleanup;
+
+ prog = bpf_object__find_program_by_title(obj, probe_name);
+ if (CHECK(!prog, "find_prog", "prog '%s' not found\n",
+ probe_name))
+ goto cleanup;
+
+ memset(&bss, 0, sizeof(bss));
+ pid_t tid = syscall(SYS_gettid);
+ pid_t pid = getpid();
+
+ id = (__u64) tid << 32 | pid;
+ bss.user_pid_tgid = id;
+
+ if (CHECK_FAIL(stat("/proc/self/ns/pid", &st))) {
+ perror("Failed to stat /proc/self/ns/pid");
+ goto cleanup;
+ }
+
+ bss.dev = st.st_dev;
+ bss.ino = st.st_ino;
+
+ err = bpf_map_update_elem(bpf_map__fd(bss_map), &key, &bss, 0);
+ if (CHECK(err, "setting_bss", "failed to set bss : %d\n", err))
+ goto cleanup;
+
+ link = bpf_program__attach_raw_tracepoint(prog, "sys_enter");
+ if (CHECK(IS_ERR(link), "attach_raw_tp", "err %ld\n",
+ PTR_ERR(link))) {
+ link = NULL;
+ goto cleanup;
+ }
+
+ /* trigger some syscalls */
+ usleep(1);
+
+ err = bpf_map_lookup_elem(bpf_map__fd(bss_map), &key, &bss);
+ if (CHECK(err, "set_bss", "failed to get bss : %d\n", err))
+ goto cleanup;
+
+ if (CHECK(id != bss.pid_tgid, "Compare user pid/tgid vs. bpf pid/tgid",
+ "User pid/tgid %llu BPF pid/tgid %llu\n", id, bss.pid_tgid))
+ goto cleanup;
+cleanup:
+ bpf_link__destroy(link);
+ bpf_object__close(obj);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/perf_branches.c b/tools/testing/selftests/bpf/prog_tests/perf_branches.c
new file mode 100644
index 000000000000..e35c444902a7
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/perf_branches.c
@@ -0,0 +1,170 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <pthread.h>
+#include <sched.h>
+#include <sys/socket.h>
+#include <test_progs.h>
+#include "bpf/libbpf_internal.h"
+#include "test_perf_branches.skel.h"
+
+static void check_good_sample(struct test_perf_branches *skel)
+{
+ int written_global = skel->bss->written_global_out;
+ int required_size = skel->bss->required_size_out;
+ int written_stack = skel->bss->written_stack_out;
+ int pbe_size = sizeof(struct perf_branch_entry);
+ int duration = 0;
+
+ if (CHECK(!skel->bss->valid, "output not valid",
+ "no valid sample from prog"))
+ return;
+
+ /*
+ * It's hard to validate the contents of the branch entries b/c it
+ * would require some kind of disassembler and also encoding the
+ * valid jump instructions for supported architectures. So just check
+ * the easy stuff for now.
+ */
+ CHECK(required_size <= 0, "read_branches_size", "err %d\n", required_size);
+ CHECK(written_stack < 0, "read_branches_stack", "err %d\n", written_stack);
+ CHECK(written_stack % pbe_size != 0, "read_branches_stack",
+ "stack bytes written=%d not multiple of struct size=%d\n",
+ written_stack, pbe_size);
+ CHECK(written_global < 0, "read_branches_global", "err %d\n", written_global);
+ CHECK(written_global % pbe_size != 0, "read_branches_global",
+ "global bytes written=%d not multiple of struct size=%d\n",
+ written_global, pbe_size);
+ CHECK(written_global < written_stack, "read_branches_size",
+ "written_global=%d < written_stack=%d\n", written_global, written_stack);
+}
+
+static void check_bad_sample(struct test_perf_branches *skel)
+{
+ int written_global = skel->bss->written_global_out;
+ int required_size = skel->bss->required_size_out;
+ int written_stack = skel->bss->written_stack_out;
+ int duration = 0;
+
+ if (CHECK(!skel->bss->valid, "output not valid",
+ "no valid sample from prog"))
+ return;
+
+ CHECK((required_size != -EINVAL && required_size != -ENOENT),
+ "read_branches_size", "err %d\n", required_size);
+ CHECK((written_stack != -EINVAL && written_stack != -ENOENT),
+ "read_branches_stack", "written %d\n", written_stack);
+ CHECK((written_global != -EINVAL && written_global != -ENOENT),
+ "read_branches_global", "written %d\n", written_global);
+}
+
+static void test_perf_branches_common(int perf_fd,
+ void (*cb)(struct test_perf_branches *))
+{
+ struct test_perf_branches *skel;
+ int err, i, duration = 0;
+ bool detached = false;
+ struct bpf_link *link;
+ volatile int j = 0;
+ cpu_set_t cpu_set;
+
+ skel = test_perf_branches__open_and_load();
+ if (CHECK(!skel, "test_perf_branches_load",
+ "perf_branches skeleton failed\n"))
+ return;
+
+ /* attach perf_event */
+ link = bpf_program__attach_perf_event(skel->progs.perf_branches, perf_fd);
+ if (CHECK(IS_ERR(link), "attach_perf_event", "err %ld\n", PTR_ERR(link)))
+ goto out_destroy_skel;
+
+ /* generate some branches on cpu 0 */
+ CPU_ZERO(&cpu_set);
+ CPU_SET(0, &cpu_set);
+ err = pthread_setaffinity_np(pthread_self(), sizeof(cpu_set), &cpu_set);
+ if (CHECK(err, "set_affinity", "cpu #0, err %d\n", err))
+ goto out_destroy;
+ /* spin the loop for a while (random high number) */
+ for (i = 0; i < 1000000; ++i)
+ ++j;
+
+ test_perf_branches__detach(skel);
+ detached = true;
+
+ cb(skel);
+out_destroy:
+ bpf_link__destroy(link);
+out_destroy_skel:
+ if (!detached)
+ test_perf_branches__detach(skel);
+ test_perf_branches__destroy(skel);
+}
+
+static void test_perf_branches_hw(void)
+{
+ struct perf_event_attr attr = {0};
+ int duration = 0;
+ int pfd;
+
+ /* create perf event */
+ attr.size = sizeof(attr);
+ attr.type = PERF_TYPE_HARDWARE;
+ attr.config = PERF_COUNT_HW_CPU_CYCLES;
+ attr.freq = 1;
+ attr.sample_freq = 4000;
+ attr.sample_type = PERF_SAMPLE_BRANCH_STACK;
+ attr.branch_sample_type = PERF_SAMPLE_BRANCH_USER | PERF_SAMPLE_BRANCH_ANY;
+ pfd = syscall(__NR_perf_event_open, &attr, -1, 0, -1, PERF_FLAG_FD_CLOEXEC);
+
+ /*
+ * Some setups don't support branch records (virtual machines, !x86),
+ * so skip test in this case.
+ */
+ if (pfd == -1) {
+ if (errno == ENOENT || errno == EOPNOTSUPP) {
+ printf("%s:SKIP:no PERF_SAMPLE_BRANCH_STACK\n",
+ __func__);
+ test__skip();
+ return;
+ }
+ if (CHECK(pfd < 0, "perf_event_open", "err %d errno %d\n",
+ pfd, errno))
+ return;
+ }
+
+ test_perf_branches_common(pfd, check_good_sample);
+
+ close(pfd);
+}
+
+/*
+ * Tests negative case -- run bpf_read_branch_records() on improperly configured
+ * perf event.
+ */
+static void test_perf_branches_no_hw(void)
+{
+ struct perf_event_attr attr = {0};
+ int duration = 0;
+ int pfd;
+
+ /* create perf event */
+ attr.size = sizeof(attr);
+ attr.type = PERF_TYPE_SOFTWARE;
+ attr.config = PERF_COUNT_SW_CPU_CLOCK;
+ attr.freq = 1;
+ attr.sample_freq = 4000;
+ pfd = syscall(__NR_perf_event_open, &attr, -1, 0, -1, PERF_FLAG_FD_CLOEXEC);
+ if (CHECK(pfd < 0, "perf_event_open", "err %d\n", pfd))
+ return;
+
+ test_perf_branches_common(pfd, check_bad_sample);
+
+ close(pfd);
+}
+
+void test_perf_branches(void)
+{
+ if (test__start_subtest("perf_branches_hw"))
+ test_perf_branches_hw();
+ if (test__start_subtest("perf_branches_no_hw"))
+ test_perf_branches_no_hw();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/perf_buffer.c b/tools/testing/selftests/bpf/prog_tests/perf_buffer.c
index 1450ea2dd4cc..a122ce3b360e 100644
--- a/tools/testing/selftests/bpf/prog_tests/perf_buffer.c
+++ b/tools/testing/selftests/bpf/prog_tests/perf_buffer.c
@@ -6,6 +6,11 @@
#include <test_progs.h>
#include "bpf/libbpf_internal.h"
+/* AddressSanitizer sometimes crashes due to data dereference below, due to
+ * this being mmap()'ed memory. Disable instrumentation with
+ * no_sanitize_address attribute
+ */
+__attribute__((no_sanitize_address))
static void on_sample(void *ctx, int cpu, void *data, __u32 size)
{
int cpu_data = *(int *)data, duration = 0;
diff --git a/tools/testing/selftests/bpf/prog_tests/pkt_access.c b/tools/testing/selftests/bpf/prog_tests/pkt_access.c
index a2537dfa899c..44b514fabccd 100644
--- a/tools/testing/selftests/bpf/prog_tests/pkt_access.c
+++ b/tools/testing/selftests/bpf/prog_tests/pkt_access.c
@@ -1,5 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
#include <test_progs.h>
+#include <network_helpers.h>
void test_pkt_access(void)
{
diff --git a/tools/testing/selftests/bpf/prog_tests/pkt_md_access.c b/tools/testing/selftests/bpf/prog_tests/pkt_md_access.c
index 5f7aea605019..939015cd6dba 100644
--- a/tools/testing/selftests/bpf/prog_tests/pkt_md_access.c
+++ b/tools/testing/selftests/bpf/prog_tests/pkt_md_access.c
@@ -1,5 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
#include <test_progs.h>
+#include <network_helpers.h>
void test_pkt_md_access(void)
{
diff --git a/tools/testing/selftests/bpf/prog_tests/prog_run_xattr.c b/tools/testing/selftests/bpf/prog_tests/prog_run_xattr.c
index 5dd89b941f53..dde2b7ae7bc9 100644
--- a/tools/testing/selftests/bpf/prog_tests/prog_run_xattr.c
+++ b/tools/testing/selftests/bpf/prog_tests/prog_run_xattr.c
@@ -1,5 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
#include <test_progs.h>
+#include <network_helpers.h>
void test_prog_run_xattr(void)
{
diff --git a/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c b/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c
index faccc66f4e39..f47e7b1cb32c 100644
--- a/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c
+++ b/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c
@@ -1,5 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
#include <test_progs.h>
+#include <network_helpers.h>
enum {
QUEUE,
diff --git a/tools/testing/selftests/bpf/prog_tests/ringbuf.c b/tools/testing/selftests/bpf/prog_tests/ringbuf.c
new file mode 100644
index 000000000000..2bba908dfa63
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/ringbuf.c
@@ -0,0 +1,211 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <linux/compiler.h>
+#include <asm/barrier.h>
+#include <test_progs.h>
+#include <sys/mman.h>
+#include <sys/epoll.h>
+#include <time.h>
+#include <sched.h>
+#include <signal.h>
+#include <pthread.h>
+#include <sys/sysinfo.h>
+#include <linux/perf_event.h>
+#include <linux/ring_buffer.h>
+#include "test_ringbuf.skel.h"
+
+#define EDONE 7777
+
+static int duration = 0;
+
+struct sample {
+ int pid;
+ int seq;
+ long value;
+ char comm[16];
+};
+
+static volatile int sample_cnt;
+
+static int process_sample(void *ctx, void *data, size_t len)
+{
+ struct sample *s = data;
+
+ sample_cnt++;
+
+ switch (s->seq) {
+ case 0:
+ CHECK(s->value != 333, "sample1_value", "exp %ld, got %ld\n",
+ 333L, s->value);
+ return 0;
+ case 1:
+ CHECK(s->value != 777, "sample2_value", "exp %ld, got %ld\n",
+ 777L, s->value);
+ return -EDONE;
+ default:
+ /* we don't care about the rest */
+ return 0;
+ }
+}
+
+static struct test_ringbuf *skel;
+static struct ring_buffer *ringbuf;
+
+static void trigger_samples()
+{
+ skel->bss->dropped = 0;
+ skel->bss->total = 0;
+ skel->bss->discarded = 0;
+
+ /* trigger exactly two samples */
+ skel->bss->value = 333;
+ syscall(__NR_getpgid);
+ skel->bss->value = 777;
+ syscall(__NR_getpgid);
+}
+
+static void *poll_thread(void *input)
+{
+ long timeout = (long)input;
+
+ return (void *)(long)ring_buffer__poll(ringbuf, timeout);
+}
+
+void test_ringbuf(void)
+{
+ const size_t rec_sz = BPF_RINGBUF_HDR_SZ + sizeof(struct sample);
+ pthread_t thread;
+ long bg_ret = -1;
+ int err;
+
+ skel = test_ringbuf__open_and_load();
+ if (CHECK(!skel, "skel_open_load", "skeleton open&load failed\n"))
+ return;
+
+ /* only trigger BPF program for current process */
+ skel->bss->pid = getpid();
+
+ ringbuf = ring_buffer__new(bpf_map__fd(skel->maps.ringbuf),
+ process_sample, NULL, NULL);
+ if (CHECK(!ringbuf, "ringbuf_create", "failed to create ringbuf\n"))
+ goto cleanup;
+
+ err = test_ringbuf__attach(skel);
+ if (CHECK(err, "skel_attach", "skeleton attachment failed: %d\n", err))
+ goto cleanup;
+
+ trigger_samples();
+
+ /* 2 submitted + 1 discarded records */
+ CHECK(skel->bss->avail_data != 3 * rec_sz,
+ "err_avail_size", "exp %ld, got %ld\n",
+ 3L * rec_sz, skel->bss->avail_data);
+ CHECK(skel->bss->ring_size != 4096,
+ "err_ring_size", "exp %ld, got %ld\n",
+ 4096L, skel->bss->ring_size);
+ CHECK(skel->bss->cons_pos != 0,
+ "err_cons_pos", "exp %ld, got %ld\n",
+ 0L, skel->bss->cons_pos);
+ CHECK(skel->bss->prod_pos != 3 * rec_sz,
+ "err_prod_pos", "exp %ld, got %ld\n",
+ 3L * rec_sz, skel->bss->prod_pos);
+
+ /* poll for samples */
+ err = ring_buffer__poll(ringbuf, -1);
+
+ /* -EDONE is used as an indicator that we are done */
+ if (CHECK(err != -EDONE, "err_done", "done err: %d\n", err))
+ goto cleanup;
+
+ /* we expect extra polling to return nothing */
+ err = ring_buffer__poll(ringbuf, 0);
+ if (CHECK(err != 0, "extra_samples", "poll result: %d\n", err))
+ goto cleanup;
+
+ CHECK(skel->bss->dropped != 0, "err_dropped", "exp %ld, got %ld\n",
+ 0L, skel->bss->dropped);
+ CHECK(skel->bss->total != 2, "err_total", "exp %ld, got %ld\n",
+ 2L, skel->bss->total);
+ CHECK(skel->bss->discarded != 1, "err_discarded", "exp %ld, got %ld\n",
+ 1L, skel->bss->discarded);
+
+ /* now validate consumer position is updated and returned */
+ trigger_samples();
+ CHECK(skel->bss->cons_pos != 3 * rec_sz,
+ "err_cons_pos", "exp %ld, got %ld\n",
+ 3L * rec_sz, skel->bss->cons_pos);
+ err = ring_buffer__poll(ringbuf, -1);
+ CHECK(err <= 0, "poll_err", "err %d\n", err);
+
+ /* start poll in background w/ long timeout */
+ err = pthread_create(&thread, NULL, poll_thread, (void *)(long)10000);
+ if (CHECK(err, "bg_poll", "pthread_create failed: %d\n", err))
+ goto cleanup;
+
+ /* turn off notifications now */
+ skel->bss->flags = BPF_RB_NO_WAKEUP;
+
+ /* give background thread a bit of a time */
+ usleep(50000);
+ trigger_samples();
+ /* sleeping arbitrarily is bad, but no better way to know that
+ * epoll_wait() **DID NOT** unblock in background thread
+ */
+ usleep(50000);
+ /* background poll should still be blocked */
+ err = pthread_tryjoin_np(thread, (void **)&bg_ret);
+ if (CHECK(err != EBUSY, "try_join", "err %d\n", err))
+ goto cleanup;
+
+ /* BPF side did everything right */
+ CHECK(skel->bss->dropped != 0, "err_dropped", "exp %ld, got %ld\n",
+ 0L, skel->bss->dropped);
+ CHECK(skel->bss->total != 2, "err_total", "exp %ld, got %ld\n",
+ 2L, skel->bss->total);
+ CHECK(skel->bss->discarded != 1, "err_discarded", "exp %ld, got %ld\n",
+ 1L, skel->bss->discarded);
+
+ /* clear flags to return to "adaptive" notification mode */
+ skel->bss->flags = 0;
+
+ /* produce new samples, no notification should be triggered, because
+ * consumer is now behind
+ */
+ trigger_samples();
+
+ /* background poll should still be blocked */
+ err = pthread_tryjoin_np(thread, (void **)&bg_ret);
+ if (CHECK(err != EBUSY, "try_join", "err %d\n", err))
+ goto cleanup;
+
+ /* now force notifications */
+ skel->bss->flags = BPF_RB_FORCE_WAKEUP;
+ sample_cnt = 0;
+ trigger_samples();
+
+ /* now we should get a pending notification */
+ usleep(50000);
+ err = pthread_tryjoin_np(thread, (void **)&bg_ret);
+ if (CHECK(err, "join_bg", "err %d\n", err))
+ goto cleanup;
+
+ if (CHECK(bg_ret != 1, "bg_ret", "epoll_wait result: %ld", bg_ret))
+ goto cleanup;
+
+ /* 3 rounds, 2 samples each */
+ CHECK(sample_cnt != 6, "wrong_sample_cnt",
+ "expected to see %d samples, got %d\n", 6, sample_cnt);
+
+ /* BPF side did everything right */
+ CHECK(skel->bss->dropped != 0, "err_dropped", "exp %ld, got %ld\n",
+ 0L, skel->bss->dropped);
+ CHECK(skel->bss->total != 2, "err_total", "exp %ld, got %ld\n",
+ 2L, skel->bss->total);
+ CHECK(skel->bss->discarded != 1, "err_discarded", "exp %ld, got %ld\n",
+ 1L, skel->bss->discarded);
+
+ test_ringbuf__detach(skel);
+cleanup:
+ ring_buffer__free(ringbuf);
+ test_ringbuf__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c b/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c
new file mode 100644
index 000000000000..78e450609803
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c
@@ -0,0 +1,102 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <test_progs.h>
+#include <sys/epoll.h>
+#include "test_ringbuf_multi.skel.h"
+
+static int duration = 0;
+
+struct sample {
+ int pid;
+ int seq;
+ long value;
+ char comm[16];
+};
+
+static int process_sample(void *ctx, void *data, size_t len)
+{
+ int ring = (unsigned long)ctx;
+ struct sample *s = data;
+
+ switch (s->seq) {
+ case 0:
+ CHECK(ring != 1, "sample1_ring", "exp %d, got %d\n", 1, ring);
+ CHECK(s->value != 333, "sample1_value", "exp %ld, got %ld\n",
+ 333L, s->value);
+ break;
+ case 1:
+ CHECK(ring != 2, "sample2_ring", "exp %d, got %d\n", 2, ring);
+ CHECK(s->value != 777, "sample2_value", "exp %ld, got %ld\n",
+ 777L, s->value);
+ break;
+ default:
+ CHECK(true, "extra_sample", "unexpected sample seq %d, val %ld\n",
+ s->seq, s->value);
+ return -1;
+ }
+
+ return 0;
+}
+
+void test_ringbuf_multi(void)
+{
+ struct test_ringbuf_multi *skel;
+ struct ring_buffer *ringbuf;
+ int err;
+
+ skel = test_ringbuf_multi__open_and_load();
+ if (CHECK(!skel, "skel_open_load", "skeleton open&load failed\n"))
+ return;
+
+ /* only trigger BPF program for current process */
+ skel->bss->pid = getpid();
+
+ ringbuf = ring_buffer__new(bpf_map__fd(skel->maps.ringbuf1),
+ process_sample, (void *)(long)1, NULL);
+ if (CHECK(!ringbuf, "ringbuf_create", "failed to create ringbuf\n"))
+ goto cleanup;
+
+ err = ring_buffer__add(ringbuf, bpf_map__fd(skel->maps.ringbuf2),
+ process_sample, (void *)(long)2);
+ if (CHECK(err, "ringbuf_add", "failed to add another ring\n"))
+ goto cleanup;
+
+ err = test_ringbuf_multi__attach(skel);
+ if (CHECK(err, "skel_attach", "skeleton attachment failed: %d\n", err))
+ goto cleanup;
+
+ /* trigger few samples, some will be skipped */
+ skel->bss->target_ring = 0;
+ skel->bss->value = 333;
+ syscall(__NR_getpgid);
+
+ /* skipped, no ringbuf in slot 1 */
+ skel->bss->target_ring = 1;
+ skel->bss->value = 555;
+ syscall(__NR_getpgid);
+
+ skel->bss->target_ring = 2;
+ skel->bss->value = 777;
+ syscall(__NR_getpgid);
+
+ /* poll for samples, should get 2 ringbufs back */
+ err = ring_buffer__poll(ringbuf, -1);
+ if (CHECK(err != 4, "poll_res", "expected 4 records, got %d\n", err))
+ goto cleanup;
+
+ /* expect extra polling to return nothing */
+ err = ring_buffer__poll(ringbuf, 0);
+ if (CHECK(err < 0, "extra_samples", "poll result: %d\n", err))
+ goto cleanup;
+
+ CHECK(skel->bss->dropped != 0, "err_dropped", "exp %ld, got %ld\n",
+ 0L, skel->bss->dropped);
+ CHECK(skel->bss->skipped != 1, "err_skipped", "exp %ld, got %ld\n",
+ 1L, skel->bss->skipped);
+ CHECK(skel->bss->total != 2, "err_total", "exp %ld, got %ld\n",
+ 2L, skel->bss->total);
+
+cleanup:
+ ring_buffer__free(ringbuf);
+ test_ringbuf_multi__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/section_names.c b/tools/testing/selftests/bpf/prog_tests/section_names.c
index 9d9351dc2ded..713167449c98 100644
--- a/tools/testing/selftests/bpf/prog_tests/section_names.c
+++ b/tools/testing/selftests/bpf/prog_tests/section_names.c
@@ -43,18 +43,18 @@ static struct sec_name_test tests[] = {
{"lwt_seg6local", {0, BPF_PROG_TYPE_LWT_SEG6LOCAL, 0}, {-EINVAL, 0} },
{
"cgroup_skb/ingress",
- {0, BPF_PROG_TYPE_CGROUP_SKB, 0},
+ {0, BPF_PROG_TYPE_CGROUP_SKB, BPF_CGROUP_INET_INGRESS},
{0, BPF_CGROUP_INET_INGRESS},
},
{
"cgroup_skb/egress",
- {0, BPF_PROG_TYPE_CGROUP_SKB, 0},
+ {0, BPF_PROG_TYPE_CGROUP_SKB, BPF_CGROUP_INET_EGRESS},
{0, BPF_CGROUP_INET_EGRESS},
},
{"cgroup/skb", {0, BPF_PROG_TYPE_CGROUP_SKB, 0}, {-EINVAL, 0} },
{
"cgroup/sock",
- {0, BPF_PROG_TYPE_CGROUP_SOCK, 0},
+ {0, BPF_PROG_TYPE_CGROUP_SOCK, BPF_CGROUP_INET_SOCK_CREATE},
{0, BPF_CGROUP_INET_SOCK_CREATE},
},
{
@@ -69,26 +69,38 @@ static struct sec_name_test tests[] = {
},
{
"cgroup/dev",
- {0, BPF_PROG_TYPE_CGROUP_DEVICE, 0},
+ {0, BPF_PROG_TYPE_CGROUP_DEVICE, BPF_CGROUP_DEVICE},
{0, BPF_CGROUP_DEVICE},
},
- {"sockops", {0, BPF_PROG_TYPE_SOCK_OPS, 0}, {0, BPF_CGROUP_SOCK_OPS} },
+ {
+ "sockops",
+ {0, BPF_PROG_TYPE_SOCK_OPS, BPF_CGROUP_SOCK_OPS},
+ {0, BPF_CGROUP_SOCK_OPS},
+ },
{
"sk_skb/stream_parser",
- {0, BPF_PROG_TYPE_SK_SKB, 0},
+ {0, BPF_PROG_TYPE_SK_SKB, BPF_SK_SKB_STREAM_PARSER},
{0, BPF_SK_SKB_STREAM_PARSER},
},
{
"sk_skb/stream_verdict",
- {0, BPF_PROG_TYPE_SK_SKB, 0},
+ {0, BPF_PROG_TYPE_SK_SKB, BPF_SK_SKB_STREAM_VERDICT},
{0, BPF_SK_SKB_STREAM_VERDICT},
},
{"sk_skb", {0, BPF_PROG_TYPE_SK_SKB, 0}, {-EINVAL, 0} },
- {"sk_msg", {0, BPF_PROG_TYPE_SK_MSG, 0}, {0, BPF_SK_MSG_VERDICT} },
- {"lirc_mode2", {0, BPF_PROG_TYPE_LIRC_MODE2, 0}, {0, BPF_LIRC_MODE2} },
+ {
+ "sk_msg",
+ {0, BPF_PROG_TYPE_SK_MSG, BPF_SK_MSG_VERDICT},
+ {0, BPF_SK_MSG_VERDICT},
+ },
+ {
+ "lirc_mode2",
+ {0, BPF_PROG_TYPE_LIRC_MODE2, BPF_LIRC_MODE2},
+ {0, BPF_LIRC_MODE2},
+ },
{
"flow_dissector",
- {0, BPF_PROG_TYPE_FLOW_DISSECTOR, 0},
+ {0, BPF_PROG_TYPE_FLOW_DISSECTOR, BPF_FLOW_DISSECTOR},
{0, BPF_FLOW_DISSECTOR},
},
{
@@ -158,17 +170,17 @@ static void test_prog_type_by_name(const struct sec_name_test *test)
&expected_attach_type);
CHECK(rc != test->expected_load.rc, "check_code",
- "prog: unexpected rc=%d for %s", rc, test->sec_name);
+ "prog: unexpected rc=%d for %s\n", rc, test->sec_name);
if (rc)
return;
CHECK(prog_type != test->expected_load.prog_type, "check_prog_type",
- "prog: unexpected prog_type=%d for %s",
+ "prog: unexpected prog_type=%d for %s\n",
prog_type, test->sec_name);
CHECK(expected_attach_type != test->expected_load.expected_attach_type,
- "check_attach_type", "prog: unexpected expected_attach_type=%d for %s",
+ "check_attach_type", "prog: unexpected expected_attach_type=%d for %s\n",
expected_attach_type, test->sec_name);
}
@@ -180,13 +192,13 @@ static void test_attach_type_by_name(const struct sec_name_test *test)
rc = libbpf_attach_type_by_name(test->sec_name, &attach_type);
CHECK(rc != test->expected_attach.rc, "check_ret",
- "attach: unexpected rc=%d for %s", rc, test->sec_name);
+ "attach: unexpected rc=%d for %s\n", rc, test->sec_name);
if (rc)
return;
CHECK(attach_type != test->expected_attach.attach_type,
- "check_attach_type", "attach: unexpected attach_type=%d for %s",
+ "check_attach_type", "attach: unexpected attach_type=%d for %s\n",
attach_type, test->sec_name);
}
diff --git a/tools/testing/selftests/bpf/prog_tests/select_reuseport.c b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c
index 0800036ed654..821b4146b7b6 100644
--- a/tools/testing/selftests/bpf/prog_tests/select_reuseport.c
+++ b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c
@@ -36,6 +36,7 @@ static int result_map, tmp_index_ovr_map, linum_map, data_check_map;
static __u32 expected_results[NR_RESULTS];
static int sk_fds[REUSEPORT_ARRAY_SIZE];
static int reuseport_array = -1, outer_map = -1;
+static enum bpf_map_type inner_map_type;
static int select_by_skb_data_prog;
static int saved_tcp_syncookie = -1;
static struct bpf_object *obj;
@@ -63,13 +64,15 @@ static union sa46 {
} \
})
-static int create_maps(void)
+static int create_maps(enum bpf_map_type inner_type)
{
struct bpf_create_map_attr attr = {};
+ inner_map_type = inner_type;
+
/* Creating reuseport_array */
attr.name = "reuseport_array";
- attr.map_type = BPF_MAP_TYPE_REUSEPORT_SOCKARRAY;
+ attr.map_type = inner_type;
attr.key_size = sizeof(__u32);
attr.value_size = sizeof(__u32);
attr.max_entries = REUSEPORT_ARRAY_SIZE;
@@ -506,11 +509,6 @@ static void test_syncookie(int type, sa_family_t family)
.pass_on_failure = 0,
};
- if (type != SOCK_STREAM) {
- test__skip();
- return;
- }
-
/*
* +1 for TCP-SYN and
* +1 for the TCP-ACK (ack the syncookie)
@@ -728,12 +726,36 @@ static void cleanup_per_test(bool no_inner_map)
static void cleanup(void)
{
- if (outer_map != -1)
+ if (outer_map != -1) {
close(outer_map);
- if (reuseport_array != -1)
+ outer_map = -1;
+ }
+
+ if (reuseport_array != -1) {
close(reuseport_array);
- if (obj)
+ reuseport_array = -1;
+ }
+
+ if (obj) {
bpf_object__close(obj);
+ obj = NULL;
+ }
+
+ memset(expected_results, 0, sizeof(expected_results));
+}
+
+static const char *maptype_str(enum bpf_map_type type)
+{
+ switch (type) {
+ case BPF_MAP_TYPE_REUSEPORT_SOCKARRAY:
+ return "reuseport_sockarray";
+ case BPF_MAP_TYPE_SOCKMAP:
+ return "sockmap";
+ case BPF_MAP_TYPE_SOCKHASH:
+ return "sockhash";
+ default:
+ return "unknown";
+ }
}
static const char *family_str(sa_family_t family)
@@ -760,7 +782,7 @@ static const char *sotype_str(int sotype)
}
}
-#define TEST_INIT(fn, ...) { fn, #fn, __VA_ARGS__ }
+#define TEST_INIT(fn_, ...) { .fn = fn_, .name = #fn_, __VA_ARGS__ }
static void test_config(int sotype, sa_family_t family, bool inany)
{
@@ -768,12 +790,15 @@ static void test_config(int sotype, sa_family_t family, bool inany)
void (*fn)(int sotype, sa_family_t family);
const char *name;
bool no_inner_map;
+ int need_sotype;
} tests[] = {
- TEST_INIT(test_err_inner_map, true /* no_inner_map */),
+ TEST_INIT(test_err_inner_map,
+ .no_inner_map = true),
TEST_INIT(test_err_skb_data),
TEST_INIT(test_err_sk_select_port),
TEST_INIT(test_pass),
- TEST_INIT(test_syncookie),
+ TEST_INIT(test_syncookie,
+ .need_sotype = SOCK_STREAM),
TEST_INIT(test_pass_on_err),
TEST_INIT(test_detach_bpf),
};
@@ -781,7 +806,11 @@ static void test_config(int sotype, sa_family_t family, bool inany)
const struct test *t;
for (t = tests; t < tests + ARRAY_SIZE(tests); t++) {
- snprintf(s, sizeof(s), "%s/%s %s %s",
+ if (t->need_sotype && t->need_sotype != sotype)
+ continue; /* test not compatible with socket type */
+
+ snprintf(s, sizeof(s), "%s %s/%s %s %s",
+ maptype_str(inner_map_type),
family_str(family), sotype_str(sotype),
inany ? "INANY" : "LOOPBACK", t->name);
@@ -816,13 +845,20 @@ static void test_all(void)
test_config(c->sotype, c->family, c->inany);
}
-void test_select_reuseport(void)
+void test_map_type(enum bpf_map_type mt)
{
- if (create_maps())
+ if (create_maps(mt))
goto out;
if (prepare_bpf_obj())
goto out;
+ test_all();
+out:
+ cleanup();
+}
+
+void test_select_reuseport(void)
+{
saved_tcp_fo = read_int_sysctl(TCP_FO_SYSCTL);
if (saved_tcp_fo < 0)
goto out;
@@ -835,8 +871,9 @@ void test_select_reuseport(void)
if (disable_syncookie())
goto out;
- test_all();
+ test_map_type(BPF_MAP_TYPE_REUSEPORT_SOCKARRAY);
+ test_map_type(BPF_MAP_TYPE_SOCKMAP);
+ test_map_type(BPF_MAP_TYPE_SOCKHASH);
out:
- cleanup();
restore_sysctls();
}
diff --git a/tools/testing/selftests/bpf/prog_tests/signal_pending.c b/tools/testing/selftests/bpf/prog_tests/signal_pending.c
index 996e808f43a2..dfcbddcbe4d3 100644
--- a/tools/testing/selftests/bpf/prog_tests/signal_pending.c
+++ b/tools/testing/selftests/bpf/prog_tests/signal_pending.c
@@ -1,5 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
#include <test_progs.h>
+#include <network_helpers.h>
static void sigalrm_handler(int s) {}
static struct sigaction sigalrm_action = {
diff --git a/tools/testing/selftests/bpf/prog_tests/sk_assign.c b/tools/testing/selftests/bpf/prog_tests/sk_assign.c
new file mode 100644
index 000000000000..47fa04adc147
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/sk_assign.c
@@ -0,0 +1,328 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2018 Facebook
+// Copyright (c) 2019 Cloudflare
+// Copyright (c) 2020 Isovalent, Inc.
+/*
+ * Test that the socket assign program is able to redirect traffic towards a
+ * socket, regardless of whether the port or address destination of the traffic
+ * matches the port.
+ */
+
+#define _GNU_SOURCE
+#include <fcntl.h>
+#include <signal.h>
+#include <stdlib.h>
+#include <unistd.h>
+
+#include "test_progs.h"
+
+#define BIND_PORT 1234
+#define CONNECT_PORT 4321
+#define TEST_DADDR (0xC0A80203)
+#define NS_SELF "/proc/self/ns/net"
+#define SERVER_MAP_PATH "/sys/fs/bpf/tc/globals/server_map"
+
+static const struct timeval timeo_sec = { .tv_sec = 3 };
+static const size_t timeo_optlen = sizeof(timeo_sec);
+static int stop, duration;
+
+static bool
+configure_stack(void)
+{
+ char tc_cmd[BUFSIZ];
+
+ /* Move to a new networking namespace */
+ if (CHECK_FAIL(unshare(CLONE_NEWNET)))
+ return false;
+
+ /* Configure necessary links, routes */
+ if (CHECK_FAIL(system("ip link set dev lo up")))
+ return false;
+ if (CHECK_FAIL(system("ip route add local default dev lo")))
+ return false;
+ if (CHECK_FAIL(system("ip -6 route add local default dev lo")))
+ return false;
+
+ /* Load qdisc, BPF program */
+ if (CHECK_FAIL(system("tc qdisc add dev lo clsact")))
+ return false;
+ sprintf(tc_cmd, "%s %s %s %s", "tc filter add dev lo ingress bpf",
+ "direct-action object-file ./test_sk_assign.o",
+ "section classifier/sk_assign_test",
+ (env.verbosity < VERBOSE_VERY) ? " 2>/dev/null" : "");
+ if (CHECK(system(tc_cmd), "BPF load failed;",
+ "run with -vv for more info\n"))
+ return false;
+
+ return true;
+}
+
+static int
+start_server(const struct sockaddr *addr, socklen_t len, int type)
+{
+ int fd;
+
+ fd = socket(addr->sa_family, type, 0);
+ if (CHECK_FAIL(fd == -1))
+ goto out;
+ if (CHECK_FAIL(setsockopt(fd, SOL_SOCKET, SO_RCVTIMEO, &timeo_sec,
+ timeo_optlen)))
+ goto close_out;
+ if (CHECK_FAIL(bind(fd, addr, len) == -1))
+ goto close_out;
+ if (type == SOCK_STREAM && CHECK_FAIL(listen(fd, 128) == -1))
+ goto close_out;
+
+ goto out;
+close_out:
+ close(fd);
+ fd = -1;
+out:
+ return fd;
+}
+
+static int
+connect_to_server(const struct sockaddr *addr, socklen_t len, int type)
+{
+ int fd = -1;
+
+ fd = socket(addr->sa_family, type, 0);
+ if (CHECK_FAIL(fd == -1))
+ goto out;
+ if (CHECK_FAIL(setsockopt(fd, SOL_SOCKET, SO_SNDTIMEO, &timeo_sec,
+ timeo_optlen)))
+ goto close_out;
+ if (CHECK_FAIL(connect(fd, addr, len)))
+ goto close_out;
+
+ goto out;
+close_out:
+ close(fd);
+ fd = -1;
+out:
+ return fd;
+}
+
+static in_port_t
+get_port(int fd)
+{
+ struct sockaddr_storage ss;
+ socklen_t slen = sizeof(ss);
+ in_port_t port = 0;
+
+ if (CHECK_FAIL(getsockname(fd, (struct sockaddr *)&ss, &slen)))
+ return port;
+
+ switch (ss.ss_family) {
+ case AF_INET:
+ port = ((struct sockaddr_in *)&ss)->sin_port;
+ break;
+ case AF_INET6:
+ port = ((struct sockaddr_in6 *)&ss)->sin6_port;
+ break;
+ default:
+ CHECK(1, "Invalid address family", "%d\n", ss.ss_family);
+ }
+ return port;
+}
+
+static ssize_t
+rcv_msg(int srv_client, int type)
+{
+ struct sockaddr_storage ss;
+ char buf[BUFSIZ];
+ socklen_t slen;
+
+ if (type == SOCK_STREAM)
+ return read(srv_client, &buf, sizeof(buf));
+ else
+ return recvfrom(srv_client, &buf, sizeof(buf), 0,
+ (struct sockaddr *)&ss, &slen);
+}
+
+static int
+run_test(int server_fd, const struct sockaddr *addr, socklen_t len, int type)
+{
+ int client = -1, srv_client = -1;
+ char buf[] = "testing";
+ in_port_t port;
+ int ret = 1;
+
+ client = connect_to_server(addr, len, type);
+ if (client == -1) {
+ perror("Cannot connect to server");
+ goto out;
+ }
+
+ if (type == SOCK_STREAM) {
+ srv_client = accept(server_fd, NULL, NULL);
+ if (CHECK_FAIL(srv_client == -1)) {
+ perror("Can't accept connection");
+ goto out;
+ }
+ } else {
+ srv_client = server_fd;
+ }
+ if (CHECK_FAIL(write(client, buf, sizeof(buf)) != sizeof(buf))) {
+ perror("Can't write on client");
+ goto out;
+ }
+ if (CHECK_FAIL(rcv_msg(srv_client, type) != sizeof(buf))) {
+ perror("Can't read on server");
+ goto out;
+ }
+
+ port = get_port(srv_client);
+ if (CHECK_FAIL(!port))
+ goto out;
+ /* SOCK_STREAM is connected via accept(), so the server's local address
+ * will be the CONNECT_PORT rather than the BIND port that corresponds
+ * to the listen socket. SOCK_DGRAM on the other hand is connectionless
+ * so we can't really do the same check there; the server doesn't ever
+ * create a socket with CONNECT_PORT.
+ */
+ if (type == SOCK_STREAM &&
+ CHECK(port != htons(CONNECT_PORT), "Expected", "port %u but got %u",
+ CONNECT_PORT, ntohs(port)))
+ goto out;
+ else if (type == SOCK_DGRAM &&
+ CHECK(port != htons(BIND_PORT), "Expected",
+ "port %u but got %u", BIND_PORT, ntohs(port)))
+ goto out;
+
+ ret = 0;
+out:
+ close(client);
+ if (srv_client != server_fd)
+ close(srv_client);
+ if (ret)
+ WRITE_ONCE(stop, 1);
+ return ret;
+}
+
+static void
+prepare_addr(struct sockaddr *addr, int family, __u16 port, bool rewrite_addr)
+{
+ struct sockaddr_in *addr4;
+ struct sockaddr_in6 *addr6;
+
+ switch (family) {
+ case AF_INET:
+ addr4 = (struct sockaddr_in *)addr;
+ memset(addr4, 0, sizeof(*addr4));
+ addr4->sin_family = family;
+ addr4->sin_port = htons(port);
+ if (rewrite_addr)
+ addr4->sin_addr.s_addr = htonl(TEST_DADDR);
+ else
+ addr4->sin_addr.s_addr = htonl(INADDR_LOOPBACK);
+ break;
+ case AF_INET6:
+ addr6 = (struct sockaddr_in6 *)addr;
+ memset(addr6, 0, sizeof(*addr6));
+ addr6->sin6_family = family;
+ addr6->sin6_port = htons(port);
+ addr6->sin6_addr = in6addr_loopback;
+ if (rewrite_addr)
+ addr6->sin6_addr.s6_addr32[3] = htonl(TEST_DADDR);
+ break;
+ default:
+ fprintf(stderr, "Invalid family %d", family);
+ }
+}
+
+struct test_sk_cfg {
+ const char *name;
+ int family;
+ struct sockaddr *addr;
+ socklen_t len;
+ int type;
+ bool rewrite_addr;
+};
+
+#define TEST(NAME, FAMILY, TYPE, REWRITE) \
+{ \
+ .name = NAME, \
+ .family = FAMILY, \
+ .addr = (FAMILY == AF_INET) ? (struct sockaddr *)&addr4 \
+ : (struct sockaddr *)&addr6, \
+ .len = (FAMILY == AF_INET) ? sizeof(addr4) : sizeof(addr6), \
+ .type = TYPE, \
+ .rewrite_addr = REWRITE, \
+}
+
+void test_sk_assign(void)
+{
+ struct sockaddr_in addr4;
+ struct sockaddr_in6 addr6;
+ struct test_sk_cfg tests[] = {
+ TEST("ipv4 tcp port redir", AF_INET, SOCK_STREAM, false),
+ TEST("ipv4 tcp addr redir", AF_INET, SOCK_STREAM, true),
+ TEST("ipv6 tcp port redir", AF_INET6, SOCK_STREAM, false),
+ TEST("ipv6 tcp addr redir", AF_INET6, SOCK_STREAM, true),
+ TEST("ipv4 udp port redir", AF_INET, SOCK_DGRAM, false),
+ TEST("ipv4 udp addr redir", AF_INET, SOCK_DGRAM, true),
+ TEST("ipv6 udp port redir", AF_INET6, SOCK_DGRAM, false),
+ TEST("ipv6 udp addr redir", AF_INET6, SOCK_DGRAM, true),
+ };
+ int server = -1;
+ int server_map;
+ int self_net;
+
+ self_net = open(NS_SELF, O_RDONLY);
+ if (CHECK_FAIL(self_net < 0)) {
+ perror("Unable to open "NS_SELF);
+ return;
+ }
+
+ if (!configure_stack()) {
+ perror("configure_stack");
+ goto cleanup;
+ }
+
+ server_map = bpf_obj_get(SERVER_MAP_PATH);
+ if (CHECK_FAIL(server_map < 0)) {
+ perror("Unable to open " SERVER_MAP_PATH);
+ goto cleanup;
+ }
+
+ for (int i = 0; i < ARRAY_SIZE(tests) && !READ_ONCE(stop); i++) {
+ struct test_sk_cfg *test = &tests[i];
+ const struct sockaddr *addr;
+ const int zero = 0;
+ int err;
+
+ if (!test__start_subtest(test->name))
+ continue;
+ prepare_addr(test->addr, test->family, BIND_PORT, false);
+ addr = (const struct sockaddr *)test->addr;
+ server = start_server(addr, test->len, test->type);
+ if (server == -1)
+ goto close;
+
+ err = bpf_map_update_elem(server_map, &zero, &server, BPF_ANY);
+ if (CHECK_FAIL(err)) {
+ perror("Unable to update server_map");
+ goto close;
+ }
+
+ /* connect to unbound ports */
+ prepare_addr(test->addr, test->family, CONNECT_PORT,
+ test->rewrite_addr);
+ if (run_test(server, addr, test->len, test->type))
+ goto close;
+
+ close(server);
+ server = -1;
+ }
+
+close:
+ close(server);
+ close(server_map);
+cleanup:
+ if (CHECK_FAIL(unlink(SERVER_MAP_PATH)))
+ perror("Unable to unlink " SERVER_MAP_PATH);
+ if (CHECK_FAIL(setns(self_net, CLONE_NEWNET)))
+ perror("Failed to setns("NS_SELF")");
+ close(self_net);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/skb_ctx.c b/tools/testing/selftests/bpf/prog_tests/skb_ctx.c
index c6d6b685a946..7021b92af313 100644
--- a/tools/testing/selftests/bpf/prog_tests/skb_ctx.c
+++ b/tools/testing/selftests/bpf/prog_tests/skb_ctx.c
@@ -1,5 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
#include <test_progs.h>
+#include <network_helpers.h>
void test_skb_ctx(void)
{
@@ -14,6 +15,7 @@ void test_skb_ctx(void)
.wire_len = 100,
.gso_segs = 8,
.mark = 9,
+ .gso_size = 10,
};
struct bpf_prog_test_run_attr tattr = {
.data_in = &pkt_v4,
diff --git a/tools/testing/selftests/bpf/prog_tests/skb_helpers.c b/tools/testing/selftests/bpf/prog_tests/skb_helpers.c
new file mode 100644
index 000000000000..f302ad84a298
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/skb_helpers.c
@@ -0,0 +1,30 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+#include <network_helpers.h>
+
+void test_skb_helpers(void)
+{
+ struct __sk_buff skb = {
+ .wire_len = 100,
+ .gso_segs = 8,
+ .gso_size = 10,
+ };
+ struct bpf_prog_test_run_attr tattr = {
+ .data_in = &pkt_v4,
+ .data_size_in = sizeof(pkt_v4),
+ .ctx_in = &skb,
+ .ctx_size_in = sizeof(skb),
+ .ctx_out = &skb,
+ .ctx_size_out = sizeof(skb),
+ };
+ struct bpf_object *obj;
+ int err;
+
+ err = bpf_prog_load("./test_skb_helpers.o", BPF_PROG_TYPE_SCHED_CLS, &obj,
+ &tattr.prog_fd);
+ if (CHECK_ATTR(err, "load", "err %d errno %d\n", err, errno))
+ return;
+ err = bpf_prog_test_run_xattr(&tattr);
+ CHECK_ATTR(err, "len", "err %d errno %d\n", err, errno);
+ bpf_object__close(obj);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
index aa43e0bd210c..96e7b7f84c65 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
@@ -1,7 +1,9 @@
// SPDX-License-Identifier: GPL-2.0
// Copyright (c) 2020 Cloudflare
+#include <error.h>
#include "test_progs.h"
+#include "test_skmsg_load_helpers.skel.h"
#define TCP_REPAIR 19 /* TCP sock is under repair right now */
@@ -70,10 +72,43 @@ out:
close(s);
}
+static void test_skmsg_helpers(enum bpf_map_type map_type)
+{
+ struct test_skmsg_load_helpers *skel;
+ int err, map, verdict;
+
+ skel = test_skmsg_load_helpers__open_and_load();
+ if (CHECK_FAIL(!skel)) {
+ perror("test_skmsg_load_helpers__open_and_load");
+ return;
+ }
+
+ verdict = bpf_program__fd(skel->progs.prog_msg_verdict);
+ map = bpf_map__fd(skel->maps.sock_map);
+
+ err = bpf_prog_attach(verdict, map, BPF_SK_MSG_VERDICT, 0);
+ if (CHECK_FAIL(err)) {
+ perror("bpf_prog_attach");
+ goto out;
+ }
+
+ err = bpf_prog_detach2(verdict, map, BPF_SK_MSG_VERDICT);
+ if (CHECK_FAIL(err)) {
+ perror("bpf_prog_detach2");
+ goto out;
+ }
+out:
+ test_skmsg_load_helpers__destroy(skel);
+}
+
void test_sockmap_basic(void)
{
if (test__start_subtest("sockmap create_update_free"))
test_sockmap_create_update_free(BPF_MAP_TYPE_SOCKMAP);
if (test__start_subtest("sockhash create_update_free"))
test_sockmap_create_update_free(BPF_MAP_TYPE_SOCKHASH);
+ if (test__start_subtest("sockmap sk_msg load helpers"))
+ test_skmsg_helpers(BPF_MAP_TYPE_SOCKMAP);
+ if (test__start_subtest("sockhash sk_msg load helpers"))
+ test_skmsg_helpers(BPF_MAP_TYPE_SOCKHASH);
}
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c b/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c
new file mode 100644
index 000000000000..06b86addc181
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c
@@ -0,0 +1,124 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2020 Cloudflare
+/*
+ * Tests for sockmap/sockhash holding kTLS sockets.
+ */
+
+#include "test_progs.h"
+
+#define MAX_TEST_NAME 80
+#define TCP_ULP 31
+
+static int tcp_server(int family)
+{
+ int err, s;
+
+ s = socket(family, SOCK_STREAM, 0);
+ if (CHECK_FAIL(s == -1)) {
+ perror("socket");
+ return -1;
+ }
+
+ err = listen(s, SOMAXCONN);
+ if (CHECK_FAIL(err)) {
+ perror("listen");
+ return -1;
+ }
+
+ return s;
+}
+
+static int disconnect(int fd)
+{
+ struct sockaddr unspec = { AF_UNSPEC };
+
+ return connect(fd, &unspec, sizeof(unspec));
+}
+
+/* Disconnect (unhash) a kTLS socket after removing it from sockmap. */
+static void test_sockmap_ktls_disconnect_after_delete(int family, int map)
+{
+ struct sockaddr_storage addr = {0};
+ socklen_t len = sizeof(addr);
+ int err, cli, srv, zero = 0;
+
+ srv = tcp_server(family);
+ if (srv == -1)
+ return;
+
+ err = getsockname(srv, (struct sockaddr *)&addr, &len);
+ if (CHECK_FAIL(err)) {
+ perror("getsockopt");
+ goto close_srv;
+ }
+
+ cli = socket(family, SOCK_STREAM, 0);
+ if (CHECK_FAIL(cli == -1)) {
+ perror("socket");
+ goto close_srv;
+ }
+
+ err = connect(cli, (struct sockaddr *)&addr, len);
+ if (CHECK_FAIL(err)) {
+ perror("connect");
+ goto close_cli;
+ }
+
+ err = bpf_map_update_elem(map, &zero, &cli, 0);
+ if (CHECK_FAIL(err)) {
+ perror("bpf_map_update_elem");
+ goto close_cli;
+ }
+
+ err = setsockopt(cli, IPPROTO_TCP, TCP_ULP, "tls", strlen("tls"));
+ if (CHECK_FAIL(err)) {
+ perror("setsockopt(TCP_ULP)");
+ goto close_cli;
+ }
+
+ err = bpf_map_delete_elem(map, &zero);
+ if (CHECK_FAIL(err)) {
+ perror("bpf_map_delete_elem");
+ goto close_cli;
+ }
+
+ err = disconnect(cli);
+ if (CHECK_FAIL(err))
+ perror("disconnect");
+
+close_cli:
+ close(cli);
+close_srv:
+ close(srv);
+}
+
+static void run_tests(int family, enum bpf_map_type map_type)
+{
+ char test_name[MAX_TEST_NAME];
+ int map;
+
+ map = bpf_create_map(map_type, sizeof(int), sizeof(int), 1, 0);
+ if (CHECK_FAIL(map == -1)) {
+ perror("bpf_map_create");
+ return;
+ }
+
+ snprintf(test_name, MAX_TEST_NAME,
+ "sockmap_ktls disconnect_after_delete %s %s",
+ family == AF_INET ? "IPv4" : "IPv6",
+ map_type == BPF_MAP_TYPE_SOCKMAP ? "SOCKMAP" : "SOCKHASH");
+ if (!test__start_subtest(test_name))
+ return;
+
+ test_sockmap_ktls_disconnect_after_delete(family, map);
+
+ close(map);
+}
+
+void test_sockmap_ktls(void)
+{
+ run_tests(AF_INET, BPF_MAP_TYPE_SOCKMAP);
+ run_tests(AF_INET, BPF_MAP_TYPE_SOCKHASH);
+ run_tests(AF_INET6, BPF_MAP_TYPE_SOCKMAP);
+ run_tests(AF_INET6, BPF_MAP_TYPE_SOCKHASH);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
new file mode 100644
index 000000000000..d7d65a700799
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
@@ -0,0 +1,1635 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2020 Cloudflare
+/*
+ * Test suite for SOCKMAP/SOCKHASH holding listening sockets.
+ * Covers:
+ * 1. BPF map operations - bpf_map_{update,lookup delete}_elem
+ * 2. BPF redirect helpers - bpf_{sk,msg}_redirect_map
+ * 3. BPF reuseport helper - bpf_sk_select_reuseport
+ */
+
+#include <linux/compiler.h>
+#include <errno.h>
+#include <error.h>
+#include <limits.h>
+#include <netinet/in.h>
+#include <pthread.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/select.h>
+#include <unistd.h>
+
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+
+#include "bpf_util.h"
+#include "test_progs.h"
+#include "test_sockmap_listen.skel.h"
+
+#define IO_TIMEOUT_SEC 30
+#define MAX_STRERR_LEN 256
+#define MAX_TEST_NAME 80
+
+#define _FAIL(errnum, fmt...) \
+ ({ \
+ error_at_line(0, (errnum), __func__, __LINE__, fmt); \
+ CHECK_FAIL(true); \
+ })
+#define FAIL(fmt...) _FAIL(0, fmt)
+#define FAIL_ERRNO(fmt...) _FAIL(errno, fmt)
+#define FAIL_LIBBPF(err, msg) \
+ ({ \
+ char __buf[MAX_STRERR_LEN]; \
+ libbpf_strerror((err), __buf, sizeof(__buf)); \
+ FAIL("%s: %s", (msg), __buf); \
+ })
+
+/* Wrappers that fail the test on error and report it. */
+
+#define xaccept_nonblock(fd, addr, len) \
+ ({ \
+ int __ret = \
+ accept_timeout((fd), (addr), (len), IO_TIMEOUT_SEC); \
+ if (__ret == -1) \
+ FAIL_ERRNO("accept"); \
+ __ret; \
+ })
+
+#define xbind(fd, addr, len) \
+ ({ \
+ int __ret = bind((fd), (addr), (len)); \
+ if (__ret == -1) \
+ FAIL_ERRNO("bind"); \
+ __ret; \
+ })
+
+#define xclose(fd) \
+ ({ \
+ int __ret = close((fd)); \
+ if (__ret == -1) \
+ FAIL_ERRNO("close"); \
+ __ret; \
+ })
+
+#define xconnect(fd, addr, len) \
+ ({ \
+ int __ret = connect((fd), (addr), (len)); \
+ if (__ret == -1) \
+ FAIL_ERRNO("connect"); \
+ __ret; \
+ })
+
+#define xgetsockname(fd, addr, len) \
+ ({ \
+ int __ret = getsockname((fd), (addr), (len)); \
+ if (__ret == -1) \
+ FAIL_ERRNO("getsockname"); \
+ __ret; \
+ })
+
+#define xgetsockopt(fd, level, name, val, len) \
+ ({ \
+ int __ret = getsockopt((fd), (level), (name), (val), (len)); \
+ if (__ret == -1) \
+ FAIL_ERRNO("getsockopt(" #name ")"); \
+ __ret; \
+ })
+
+#define xlisten(fd, backlog) \
+ ({ \
+ int __ret = listen((fd), (backlog)); \
+ if (__ret == -1) \
+ FAIL_ERRNO("listen"); \
+ __ret; \
+ })
+
+#define xsetsockopt(fd, level, name, val, len) \
+ ({ \
+ int __ret = setsockopt((fd), (level), (name), (val), (len)); \
+ if (__ret == -1) \
+ FAIL_ERRNO("setsockopt(" #name ")"); \
+ __ret; \
+ })
+
+#define xsend(fd, buf, len, flags) \
+ ({ \
+ ssize_t __ret = send((fd), (buf), (len), (flags)); \
+ if (__ret == -1) \
+ FAIL_ERRNO("send"); \
+ __ret; \
+ })
+
+#define xrecv_nonblock(fd, buf, len, flags) \
+ ({ \
+ ssize_t __ret = recv_timeout((fd), (buf), (len), (flags), \
+ IO_TIMEOUT_SEC); \
+ if (__ret == -1) \
+ FAIL_ERRNO("recv"); \
+ __ret; \
+ })
+
+#define xsocket(family, sotype, flags) \
+ ({ \
+ int __ret = socket(family, sotype, flags); \
+ if (__ret == -1) \
+ FAIL_ERRNO("socket"); \
+ __ret; \
+ })
+
+#define xbpf_map_delete_elem(fd, key) \
+ ({ \
+ int __ret = bpf_map_delete_elem((fd), (key)); \
+ if (__ret == -1) \
+ FAIL_ERRNO("map_delete"); \
+ __ret; \
+ })
+
+#define xbpf_map_lookup_elem(fd, key, val) \
+ ({ \
+ int __ret = bpf_map_lookup_elem((fd), (key), (val)); \
+ if (__ret == -1) \
+ FAIL_ERRNO("map_lookup"); \
+ __ret; \
+ })
+
+#define xbpf_map_update_elem(fd, key, val, flags) \
+ ({ \
+ int __ret = bpf_map_update_elem((fd), (key), (val), (flags)); \
+ if (__ret == -1) \
+ FAIL_ERRNO("map_update"); \
+ __ret; \
+ })
+
+#define xbpf_prog_attach(prog, target, type, flags) \
+ ({ \
+ int __ret = \
+ bpf_prog_attach((prog), (target), (type), (flags)); \
+ if (__ret == -1) \
+ FAIL_ERRNO("prog_attach(" #type ")"); \
+ __ret; \
+ })
+
+#define xbpf_prog_detach2(prog, target, type) \
+ ({ \
+ int __ret = bpf_prog_detach2((prog), (target), (type)); \
+ if (__ret == -1) \
+ FAIL_ERRNO("prog_detach2(" #type ")"); \
+ __ret; \
+ })
+
+#define xpthread_create(thread, attr, func, arg) \
+ ({ \
+ int __ret = pthread_create((thread), (attr), (func), (arg)); \
+ errno = __ret; \
+ if (__ret) \
+ FAIL_ERRNO("pthread_create"); \
+ __ret; \
+ })
+
+#define xpthread_join(thread, retval) \
+ ({ \
+ int __ret = pthread_join((thread), (retval)); \
+ errno = __ret; \
+ if (__ret) \
+ FAIL_ERRNO("pthread_join"); \
+ __ret; \
+ })
+
+static int poll_read(int fd, unsigned int timeout_sec)
+{
+ struct timeval timeout = { .tv_sec = timeout_sec };
+ fd_set rfds;
+ int r;
+
+ FD_ZERO(&rfds);
+ FD_SET(fd, &rfds);
+
+ r = select(fd + 1, &rfds, NULL, NULL, &timeout);
+ if (r == 0)
+ errno = ETIME;
+
+ return r == 1 ? 0 : -1;
+}
+
+static int accept_timeout(int fd, struct sockaddr *addr, socklen_t *len,
+ unsigned int timeout_sec)
+{
+ if (poll_read(fd, timeout_sec))
+ return -1;
+
+ return accept(fd, addr, len);
+}
+
+static int recv_timeout(int fd, void *buf, size_t len, int flags,
+ unsigned int timeout_sec)
+{
+ if (poll_read(fd, timeout_sec))
+ return -1;
+
+ return recv(fd, buf, len, flags);
+}
+
+static void init_addr_loopback4(struct sockaddr_storage *ss, socklen_t *len)
+{
+ struct sockaddr_in *addr4 = memset(ss, 0, sizeof(*ss));
+
+ addr4->sin_family = AF_INET;
+ addr4->sin_port = 0;
+ addr4->sin_addr.s_addr = htonl(INADDR_LOOPBACK);
+ *len = sizeof(*addr4);
+}
+
+static void init_addr_loopback6(struct sockaddr_storage *ss, socklen_t *len)
+{
+ struct sockaddr_in6 *addr6 = memset(ss, 0, sizeof(*ss));
+
+ addr6->sin6_family = AF_INET6;
+ addr6->sin6_port = 0;
+ addr6->sin6_addr = in6addr_loopback;
+ *len = sizeof(*addr6);
+}
+
+static void init_addr_loopback(int family, struct sockaddr_storage *ss,
+ socklen_t *len)
+{
+ switch (family) {
+ case AF_INET:
+ init_addr_loopback4(ss, len);
+ return;
+ case AF_INET6:
+ init_addr_loopback6(ss, len);
+ return;
+ default:
+ FAIL("unsupported address family %d", family);
+ }
+}
+
+static inline struct sockaddr *sockaddr(struct sockaddr_storage *ss)
+{
+ return (struct sockaddr *)ss;
+}
+
+static int enable_reuseport(int s, int progfd)
+{
+ int err, one = 1;
+
+ err = xsetsockopt(s, SOL_SOCKET, SO_REUSEPORT, &one, sizeof(one));
+ if (err)
+ return -1;
+ err = xsetsockopt(s, SOL_SOCKET, SO_ATTACH_REUSEPORT_EBPF, &progfd,
+ sizeof(progfd));
+ if (err)
+ return -1;
+
+ return 0;
+}
+
+static int socket_loopback_reuseport(int family, int sotype, int progfd)
+{
+ struct sockaddr_storage addr;
+ socklen_t len;
+ int err, s;
+
+ init_addr_loopback(family, &addr, &len);
+
+ s = xsocket(family, sotype, 0);
+ if (s == -1)
+ return -1;
+
+ if (progfd >= 0)
+ enable_reuseport(s, progfd);
+
+ err = xbind(s, sockaddr(&addr), len);
+ if (err)
+ goto close;
+
+ if (sotype & SOCK_DGRAM)
+ return s;
+
+ err = xlisten(s, SOMAXCONN);
+ if (err)
+ goto close;
+
+ return s;
+close:
+ xclose(s);
+ return -1;
+}
+
+static int socket_loopback(int family, int sotype)
+{
+ return socket_loopback_reuseport(family, sotype, -1);
+}
+
+static void test_insert_invalid(int family, int sotype, int mapfd)
+{
+ u32 key = 0;
+ u64 value;
+ int err;
+
+ value = -1;
+ err = bpf_map_update_elem(mapfd, &key, &value, BPF_NOEXIST);
+ if (!err || errno != EINVAL)
+ FAIL_ERRNO("map_update: expected EINVAL");
+
+ value = INT_MAX;
+ err = bpf_map_update_elem(mapfd, &key, &value, BPF_NOEXIST);
+ if (!err || errno != EBADF)
+ FAIL_ERRNO("map_update: expected EBADF");
+}
+
+static void test_insert_opened(int family, int sotype, int mapfd)
+{
+ u32 key = 0;
+ u64 value;
+ int err, s;
+
+ s = xsocket(family, sotype, 0);
+ if (s == -1)
+ return;
+
+ errno = 0;
+ value = s;
+ err = bpf_map_update_elem(mapfd, &key, &value, BPF_NOEXIST);
+ if (!err || errno != EOPNOTSUPP)
+ FAIL_ERRNO("map_update: expected EOPNOTSUPP");
+
+ xclose(s);
+}
+
+static void test_insert_bound(int family, int sotype, int mapfd)
+{
+ struct sockaddr_storage addr;
+ socklen_t len;
+ u32 key = 0;
+ u64 value;
+ int err, s;
+
+ init_addr_loopback(family, &addr, &len);
+
+ s = xsocket(family, sotype, 0);
+ if (s == -1)
+ return;
+
+ err = xbind(s, sockaddr(&addr), len);
+ if (err)
+ goto close;
+
+ errno = 0;
+ value = s;
+ err = bpf_map_update_elem(mapfd, &key, &value, BPF_NOEXIST);
+ if (!err || errno != EOPNOTSUPP)
+ FAIL_ERRNO("map_update: expected EOPNOTSUPP");
+close:
+ xclose(s);
+}
+
+static void test_insert(int family, int sotype, int mapfd)
+{
+ u64 value;
+ u32 key;
+ int s;
+
+ s = socket_loopback(family, sotype);
+ if (s < 0)
+ return;
+
+ key = 0;
+ value = s;
+ xbpf_map_update_elem(mapfd, &key, &value, BPF_NOEXIST);
+ xclose(s);
+}
+
+static void test_delete_after_insert(int family, int sotype, int mapfd)
+{
+ u64 value;
+ u32 key;
+ int s;
+
+ s = socket_loopback(family, sotype);
+ if (s < 0)
+ return;
+
+ key = 0;
+ value = s;
+ xbpf_map_update_elem(mapfd, &key, &value, BPF_NOEXIST);
+ xbpf_map_delete_elem(mapfd, &key);
+ xclose(s);
+}
+
+static void test_delete_after_close(int family, int sotype, int mapfd)
+{
+ int err, s;
+ u64 value;
+ u32 key;
+
+ s = socket_loopback(family, sotype);
+ if (s < 0)
+ return;
+
+ key = 0;
+ value = s;
+ xbpf_map_update_elem(mapfd, &key, &value, BPF_NOEXIST);
+
+ xclose(s);
+
+ errno = 0;
+ err = bpf_map_delete_elem(mapfd, &key);
+ if (!err || (errno != EINVAL && errno != ENOENT))
+ /* SOCKMAP and SOCKHASH return different error codes */
+ FAIL_ERRNO("map_delete: expected EINVAL/EINVAL");
+}
+
+static void test_lookup_after_insert(int family, int sotype, int mapfd)
+{
+ u64 cookie, value;
+ socklen_t len;
+ u32 key;
+ int s;
+
+ s = socket_loopback(family, sotype);
+ if (s < 0)
+ return;
+
+ key = 0;
+ value = s;
+ xbpf_map_update_elem(mapfd, &key, &value, BPF_NOEXIST);
+
+ len = sizeof(cookie);
+ xgetsockopt(s, SOL_SOCKET, SO_COOKIE, &cookie, &len);
+
+ xbpf_map_lookup_elem(mapfd, &key, &value);
+
+ if (value != cookie) {
+ FAIL("map_lookup: have %#llx, want %#llx",
+ (unsigned long long)value, (unsigned long long)cookie);
+ }
+
+ xclose(s);
+}
+
+static void test_lookup_after_delete(int family, int sotype, int mapfd)
+{
+ int err, s;
+ u64 value;
+ u32 key;
+
+ s = socket_loopback(family, sotype);
+ if (s < 0)
+ return;
+
+ key = 0;
+ value = s;
+ xbpf_map_update_elem(mapfd, &key, &value, BPF_NOEXIST);
+ xbpf_map_delete_elem(mapfd, &key);
+
+ errno = 0;
+ err = bpf_map_lookup_elem(mapfd, &key, &value);
+ if (!err || errno != ENOENT)
+ FAIL_ERRNO("map_lookup: expected ENOENT");
+
+ xclose(s);
+}
+
+static void test_lookup_32_bit_value(int family, int sotype, int mapfd)
+{
+ u32 key, value32;
+ int err, s;
+
+ s = socket_loopback(family, sotype);
+ if (s < 0)
+ return;
+
+ mapfd = bpf_create_map(BPF_MAP_TYPE_SOCKMAP, sizeof(key),
+ sizeof(value32), 1, 0);
+ if (mapfd < 0) {
+ FAIL_ERRNO("map_create");
+ goto close;
+ }
+
+ key = 0;
+ value32 = s;
+ xbpf_map_update_elem(mapfd, &key, &value32, BPF_NOEXIST);
+
+ errno = 0;
+ err = bpf_map_lookup_elem(mapfd, &key, &value32);
+ if (!err || errno != ENOSPC)
+ FAIL_ERRNO("map_lookup: expected ENOSPC");
+
+ xclose(mapfd);
+close:
+ xclose(s);
+}
+
+static void test_update_existing(int family, int sotype, int mapfd)
+{
+ int s1, s2;
+ u64 value;
+ u32 key;
+
+ s1 = socket_loopback(family, sotype);
+ if (s1 < 0)
+ return;
+
+ s2 = socket_loopback(family, sotype);
+ if (s2 < 0)
+ goto close_s1;
+
+ key = 0;
+ value = s1;
+ xbpf_map_update_elem(mapfd, &key, &value, BPF_NOEXIST);
+
+ value = s2;
+ xbpf_map_update_elem(mapfd, &key, &value, BPF_EXIST);
+ xclose(s2);
+close_s1:
+ xclose(s1);
+}
+
+/* Exercise the code path where we destroy child sockets that never
+ * got accept()'ed, aka orphans, when parent socket gets closed.
+ */
+static void test_destroy_orphan_child(int family, int sotype, int mapfd)
+{
+ struct sockaddr_storage addr;
+ socklen_t len;
+ int err, s, c;
+ u64 value;
+ u32 key;
+
+ s = socket_loopback(family, sotype);
+ if (s < 0)
+ return;
+
+ len = sizeof(addr);
+ err = xgetsockname(s, sockaddr(&addr), &len);
+ if (err)
+ goto close_srv;
+
+ key = 0;
+ value = s;
+ xbpf_map_update_elem(mapfd, &key, &value, BPF_NOEXIST);
+
+ c = xsocket(family, sotype, 0);
+ if (c == -1)
+ goto close_srv;
+
+ xconnect(c, sockaddr(&addr), len);
+ xclose(c);
+close_srv:
+ xclose(s);
+}
+
+/* Perform a passive open after removing listening socket from SOCKMAP
+ * to ensure that callbacks get restored properly.
+ */
+static void test_clone_after_delete(int family, int sotype, int mapfd)
+{
+ struct sockaddr_storage addr;
+ socklen_t len;
+ int err, s, c;
+ u64 value;
+ u32 key;
+
+ s = socket_loopback(family, sotype);
+ if (s < 0)
+ return;
+
+ len = sizeof(addr);
+ err = xgetsockname(s, sockaddr(&addr), &len);
+ if (err)
+ goto close_srv;
+
+ key = 0;
+ value = s;
+ xbpf_map_update_elem(mapfd, &key, &value, BPF_NOEXIST);
+ xbpf_map_delete_elem(mapfd, &key);
+
+ c = xsocket(family, sotype, 0);
+ if (c < 0)
+ goto close_srv;
+
+ xconnect(c, sockaddr(&addr), len);
+ xclose(c);
+close_srv:
+ xclose(s);
+}
+
+/* Check that child socket that got created while parent was in a
+ * SOCKMAP, but got accept()'ed only after the parent has been removed
+ * from SOCKMAP, gets cloned without parent psock state or callbacks.
+ */
+static void test_accept_after_delete(int family, int sotype, int mapfd)
+{
+ struct sockaddr_storage addr;
+ const u32 zero = 0;
+ int err, s, c, p;
+ socklen_t len;
+ u64 value;
+
+ s = socket_loopback(family, sotype | SOCK_NONBLOCK);
+ if (s == -1)
+ return;
+
+ len = sizeof(addr);
+ err = xgetsockname(s, sockaddr(&addr), &len);
+ if (err)
+ goto close_srv;
+
+ value = s;
+ err = xbpf_map_update_elem(mapfd, &zero, &value, BPF_NOEXIST);
+ if (err)
+ goto close_srv;
+
+ c = xsocket(family, sotype, 0);
+ if (c == -1)
+ goto close_srv;
+
+ /* Create child while parent is in sockmap */
+ err = xconnect(c, sockaddr(&addr), len);
+ if (err)
+ goto close_cli;
+
+ /* Remove parent from sockmap */
+ err = xbpf_map_delete_elem(mapfd, &zero);
+ if (err)
+ goto close_cli;
+
+ p = xaccept_nonblock(s, NULL, NULL);
+ if (p == -1)
+ goto close_cli;
+
+ /* Check that child sk_user_data is not set */
+ value = p;
+ xbpf_map_update_elem(mapfd, &zero, &value, BPF_NOEXIST);
+
+ xclose(p);
+close_cli:
+ xclose(c);
+close_srv:
+ xclose(s);
+}
+
+/* Check that child socket that got created and accepted while parent
+ * was in a SOCKMAP is cloned without parent psock state or callbacks.
+ */
+static void test_accept_before_delete(int family, int sotype, int mapfd)
+{
+ struct sockaddr_storage addr;
+ const u32 zero = 0, one = 1;
+ int err, s, c, p;
+ socklen_t len;
+ u64 value;
+
+ s = socket_loopback(family, sotype | SOCK_NONBLOCK);
+ if (s == -1)
+ return;
+
+ len = sizeof(addr);
+ err = xgetsockname(s, sockaddr(&addr), &len);
+ if (err)
+ goto close_srv;
+
+ value = s;
+ err = xbpf_map_update_elem(mapfd, &zero, &value, BPF_NOEXIST);
+ if (err)
+ goto close_srv;
+
+ c = xsocket(family, sotype, 0);
+ if (c == -1)
+ goto close_srv;
+
+ /* Create & accept child while parent is in sockmap */
+ err = xconnect(c, sockaddr(&addr), len);
+ if (err)
+ goto close_cli;
+
+ p = xaccept_nonblock(s, NULL, NULL);
+ if (p == -1)
+ goto close_cli;
+
+ /* Check that child sk_user_data is not set */
+ value = p;
+ xbpf_map_update_elem(mapfd, &one, &value, BPF_NOEXIST);
+
+ xclose(p);
+close_cli:
+ xclose(c);
+close_srv:
+ xclose(s);
+}
+
+struct connect_accept_ctx {
+ int sockfd;
+ unsigned int done;
+ unsigned int nr_iter;
+};
+
+static bool is_thread_done(struct connect_accept_ctx *ctx)
+{
+ return READ_ONCE(ctx->done);
+}
+
+static void *connect_accept_thread(void *arg)
+{
+ struct connect_accept_ctx *ctx = arg;
+ struct sockaddr_storage addr;
+ int family, socktype;
+ socklen_t len;
+ int err, i, s;
+
+ s = ctx->sockfd;
+
+ len = sizeof(addr);
+ err = xgetsockname(s, sockaddr(&addr), &len);
+ if (err)
+ goto done;
+
+ len = sizeof(family);
+ err = xgetsockopt(s, SOL_SOCKET, SO_DOMAIN, &family, &len);
+ if (err)
+ goto done;
+
+ len = sizeof(socktype);
+ err = xgetsockopt(s, SOL_SOCKET, SO_TYPE, &socktype, &len);
+ if (err)
+ goto done;
+
+ for (i = 0; i < ctx->nr_iter; i++) {
+ int c, p;
+
+ c = xsocket(family, socktype, 0);
+ if (c < 0)
+ break;
+
+ err = xconnect(c, (struct sockaddr *)&addr, sizeof(addr));
+ if (err) {
+ xclose(c);
+ break;
+ }
+
+ p = xaccept_nonblock(s, NULL, NULL);
+ if (p < 0) {
+ xclose(c);
+ break;
+ }
+
+ xclose(p);
+ xclose(c);
+ }
+done:
+ WRITE_ONCE(ctx->done, 1);
+ return NULL;
+}
+
+static void test_syn_recv_insert_delete(int family, int sotype, int mapfd)
+{
+ struct connect_accept_ctx ctx = { 0 };
+ struct sockaddr_storage addr;
+ socklen_t len;
+ u32 zero = 0;
+ pthread_t t;
+ int err, s;
+ u64 value;
+
+ s = socket_loopback(family, sotype | SOCK_NONBLOCK);
+ if (s < 0)
+ return;
+
+ len = sizeof(addr);
+ err = xgetsockname(s, sockaddr(&addr), &len);
+ if (err)
+ goto close;
+
+ ctx.sockfd = s;
+ ctx.nr_iter = 1000;
+
+ err = xpthread_create(&t, NULL, connect_accept_thread, &ctx);
+ if (err)
+ goto close;
+
+ value = s;
+ while (!is_thread_done(&ctx)) {
+ err = xbpf_map_update_elem(mapfd, &zero, &value, BPF_NOEXIST);
+ if (err)
+ break;
+
+ err = xbpf_map_delete_elem(mapfd, &zero);
+ if (err)
+ break;
+ }
+
+ xpthread_join(t, NULL);
+close:
+ xclose(s);
+}
+
+static void *listen_thread(void *arg)
+{
+ struct sockaddr unspec = { AF_UNSPEC };
+ struct connect_accept_ctx *ctx = arg;
+ int err, i, s;
+
+ s = ctx->sockfd;
+
+ for (i = 0; i < ctx->nr_iter; i++) {
+ err = xlisten(s, 1);
+ if (err)
+ break;
+ err = xconnect(s, &unspec, sizeof(unspec));
+ if (err)
+ break;
+ }
+
+ WRITE_ONCE(ctx->done, 1);
+ return NULL;
+}
+
+static void test_race_insert_listen(int family, int socktype, int mapfd)
+{
+ struct connect_accept_ctx ctx = { 0 };
+ const u32 zero = 0;
+ const int one = 1;
+ pthread_t t;
+ int err, s;
+ u64 value;
+
+ s = xsocket(family, socktype, 0);
+ if (s < 0)
+ return;
+
+ err = xsetsockopt(s, SOL_SOCKET, SO_REUSEADDR, &one, sizeof(one));
+ if (err)
+ goto close;
+
+ ctx.sockfd = s;
+ ctx.nr_iter = 10000;
+
+ err = pthread_create(&t, NULL, listen_thread, &ctx);
+ if (err)
+ goto close;
+
+ value = s;
+ while (!is_thread_done(&ctx)) {
+ err = bpf_map_update_elem(mapfd, &zero, &value, BPF_NOEXIST);
+ /* Expecting EOPNOTSUPP before listen() */
+ if (err && errno != EOPNOTSUPP) {
+ FAIL_ERRNO("map_update");
+ break;
+ }
+
+ err = bpf_map_delete_elem(mapfd, &zero);
+ /* Expecting no entry after unhash on connect(AF_UNSPEC) */
+ if (err && errno != EINVAL && errno != ENOENT) {
+ FAIL_ERRNO("map_delete");
+ break;
+ }
+ }
+
+ xpthread_join(t, NULL);
+close:
+ xclose(s);
+}
+
+static void zero_verdict_count(int mapfd)
+{
+ unsigned int zero = 0;
+ int key;
+
+ key = SK_DROP;
+ xbpf_map_update_elem(mapfd, &key, &zero, BPF_ANY);
+ key = SK_PASS;
+ xbpf_map_update_elem(mapfd, &key, &zero, BPF_ANY);
+}
+
+enum redir_mode {
+ REDIR_INGRESS,
+ REDIR_EGRESS,
+};
+
+static const char *redir_mode_str(enum redir_mode mode)
+{
+ switch (mode) {
+ case REDIR_INGRESS:
+ return "ingress";
+ case REDIR_EGRESS:
+ return "egress";
+ default:
+ return "unknown";
+ }
+}
+
+static void redir_to_connected(int family, int sotype, int sock_mapfd,
+ int verd_mapfd, enum redir_mode mode)
+{
+ const char *log_prefix = redir_mode_str(mode);
+ struct sockaddr_storage addr;
+ int s, c0, c1, p0, p1;
+ unsigned int pass;
+ socklen_t len;
+ int err, n;
+ u64 value;
+ u32 key;
+ char b;
+
+ zero_verdict_count(verd_mapfd);
+
+ s = socket_loopback(family, sotype | SOCK_NONBLOCK);
+ if (s < 0)
+ return;
+
+ len = sizeof(addr);
+ err = xgetsockname(s, sockaddr(&addr), &len);
+ if (err)
+ goto close_srv;
+
+ c0 = xsocket(family, sotype, 0);
+ if (c0 < 0)
+ goto close_srv;
+ err = xconnect(c0, sockaddr(&addr), len);
+ if (err)
+ goto close_cli0;
+
+ p0 = xaccept_nonblock(s, NULL, NULL);
+ if (p0 < 0)
+ goto close_cli0;
+
+ c1 = xsocket(family, sotype, 0);
+ if (c1 < 0)
+ goto close_peer0;
+ err = xconnect(c1, sockaddr(&addr), len);
+ if (err)
+ goto close_cli1;
+
+ p1 = xaccept_nonblock(s, NULL, NULL);
+ if (p1 < 0)
+ goto close_cli1;
+
+ key = 0;
+ value = p0;
+ err = xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST);
+ if (err)
+ goto close_peer1;
+
+ key = 1;
+ value = p1;
+ err = xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST);
+ if (err)
+ goto close_peer1;
+
+ n = write(mode == REDIR_INGRESS ? c1 : p1, "a", 1);
+ if (n < 0)
+ FAIL_ERRNO("%s: write", log_prefix);
+ if (n == 0)
+ FAIL("%s: incomplete write", log_prefix);
+ if (n < 1)
+ goto close_peer1;
+
+ key = SK_PASS;
+ err = xbpf_map_lookup_elem(verd_mapfd, &key, &pass);
+ if (err)
+ goto close_peer1;
+ if (pass != 1)
+ FAIL("%s: want pass count 1, have %d", log_prefix, pass);
+
+ n = read(c0, &b, 1);
+ if (n < 0)
+ FAIL_ERRNO("%s: read", log_prefix);
+ if (n == 0)
+ FAIL("%s: incomplete read", log_prefix);
+
+close_peer1:
+ xclose(p1);
+close_cli1:
+ xclose(c1);
+close_peer0:
+ xclose(p0);
+close_cli0:
+ xclose(c0);
+close_srv:
+ xclose(s);
+}
+
+static void test_skb_redir_to_connected(struct test_sockmap_listen *skel,
+ struct bpf_map *inner_map, int family,
+ int sotype)
+{
+ int verdict = bpf_program__fd(skel->progs.prog_skb_verdict);
+ int parser = bpf_program__fd(skel->progs.prog_skb_parser);
+ int verdict_map = bpf_map__fd(skel->maps.verdict_map);
+ int sock_map = bpf_map__fd(inner_map);
+ int err;
+
+ err = xbpf_prog_attach(parser, sock_map, BPF_SK_SKB_STREAM_PARSER, 0);
+ if (err)
+ return;
+ err = xbpf_prog_attach(verdict, sock_map, BPF_SK_SKB_STREAM_VERDICT, 0);
+ if (err)
+ goto detach;
+
+ redir_to_connected(family, sotype, sock_map, verdict_map,
+ REDIR_INGRESS);
+
+ xbpf_prog_detach2(verdict, sock_map, BPF_SK_SKB_STREAM_VERDICT);
+detach:
+ xbpf_prog_detach2(parser, sock_map, BPF_SK_SKB_STREAM_PARSER);
+}
+
+static void test_msg_redir_to_connected(struct test_sockmap_listen *skel,
+ struct bpf_map *inner_map, int family,
+ int sotype)
+{
+ int verdict = bpf_program__fd(skel->progs.prog_msg_verdict);
+ int verdict_map = bpf_map__fd(skel->maps.verdict_map);
+ int sock_map = bpf_map__fd(inner_map);
+ int err;
+
+ err = xbpf_prog_attach(verdict, sock_map, BPF_SK_MSG_VERDICT, 0);
+ if (err)
+ return;
+
+ redir_to_connected(family, sotype, sock_map, verdict_map, REDIR_EGRESS);
+
+ xbpf_prog_detach2(verdict, sock_map, BPF_SK_MSG_VERDICT);
+}
+
+static void redir_to_listening(int family, int sotype, int sock_mapfd,
+ int verd_mapfd, enum redir_mode mode)
+{
+ const char *log_prefix = redir_mode_str(mode);
+ struct sockaddr_storage addr;
+ int s, c, p, err, n;
+ unsigned int drop;
+ socklen_t len;
+ u64 value;
+ u32 key;
+
+ zero_verdict_count(verd_mapfd);
+
+ s = socket_loopback(family, sotype | SOCK_NONBLOCK);
+ if (s < 0)
+ return;
+
+ len = sizeof(addr);
+ err = xgetsockname(s, sockaddr(&addr), &len);
+ if (err)
+ goto close_srv;
+
+ c = xsocket(family, sotype, 0);
+ if (c < 0)
+ goto close_srv;
+ err = xconnect(c, sockaddr(&addr), len);
+ if (err)
+ goto close_cli;
+
+ p = xaccept_nonblock(s, NULL, NULL);
+ if (p < 0)
+ goto close_cli;
+
+ key = 0;
+ value = s;
+ err = xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST);
+ if (err)
+ goto close_peer;
+
+ key = 1;
+ value = p;
+ err = xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST);
+ if (err)
+ goto close_peer;
+
+ n = write(mode == REDIR_INGRESS ? c : p, "a", 1);
+ if (n < 0 && errno != EACCES)
+ FAIL_ERRNO("%s: write", log_prefix);
+ if (n == 0)
+ FAIL("%s: incomplete write", log_prefix);
+ if (n < 1)
+ goto close_peer;
+
+ key = SK_DROP;
+ err = xbpf_map_lookup_elem(verd_mapfd, &key, &drop);
+ if (err)
+ goto close_peer;
+ if (drop != 1)
+ FAIL("%s: want drop count 1, have %d", log_prefix, drop);
+
+close_peer:
+ xclose(p);
+close_cli:
+ xclose(c);
+close_srv:
+ xclose(s);
+}
+
+static void test_skb_redir_to_listening(struct test_sockmap_listen *skel,
+ struct bpf_map *inner_map, int family,
+ int sotype)
+{
+ int verdict = bpf_program__fd(skel->progs.prog_skb_verdict);
+ int parser = bpf_program__fd(skel->progs.prog_skb_parser);
+ int verdict_map = bpf_map__fd(skel->maps.verdict_map);
+ int sock_map = bpf_map__fd(inner_map);
+ int err;
+
+ err = xbpf_prog_attach(parser, sock_map, BPF_SK_SKB_STREAM_PARSER, 0);
+ if (err)
+ return;
+ err = xbpf_prog_attach(verdict, sock_map, BPF_SK_SKB_STREAM_VERDICT, 0);
+ if (err)
+ goto detach;
+
+ redir_to_listening(family, sotype, sock_map, verdict_map,
+ REDIR_INGRESS);
+
+ xbpf_prog_detach2(verdict, sock_map, BPF_SK_SKB_STREAM_VERDICT);
+detach:
+ xbpf_prog_detach2(parser, sock_map, BPF_SK_SKB_STREAM_PARSER);
+}
+
+static void test_msg_redir_to_listening(struct test_sockmap_listen *skel,
+ struct bpf_map *inner_map, int family,
+ int sotype)
+{
+ int verdict = bpf_program__fd(skel->progs.prog_msg_verdict);
+ int verdict_map = bpf_map__fd(skel->maps.verdict_map);
+ int sock_map = bpf_map__fd(inner_map);
+ int err;
+
+ err = xbpf_prog_attach(verdict, sock_map, BPF_SK_MSG_VERDICT, 0);
+ if (err)
+ return;
+
+ redir_to_listening(family, sotype, sock_map, verdict_map, REDIR_EGRESS);
+
+ xbpf_prog_detach2(verdict, sock_map, BPF_SK_MSG_VERDICT);
+}
+
+static void test_reuseport_select_listening(int family, int sotype,
+ int sock_map, int verd_map,
+ int reuseport_prog)
+{
+ struct sockaddr_storage addr;
+ unsigned int pass;
+ int s, c, err;
+ socklen_t len;
+ u64 value;
+ u32 key;
+
+ zero_verdict_count(verd_map);
+
+ s = socket_loopback_reuseport(family, sotype | SOCK_NONBLOCK,
+ reuseport_prog);
+ if (s < 0)
+ return;
+
+ len = sizeof(addr);
+ err = xgetsockname(s, sockaddr(&addr), &len);
+ if (err)
+ goto close_srv;
+
+ key = 0;
+ value = s;
+ err = xbpf_map_update_elem(sock_map, &key, &value, BPF_NOEXIST);
+ if (err)
+ goto close_srv;
+
+ c = xsocket(family, sotype, 0);
+ if (c < 0)
+ goto close_srv;
+ err = xconnect(c, sockaddr(&addr), len);
+ if (err)
+ goto close_cli;
+
+ if (sotype == SOCK_STREAM) {
+ int p;
+
+ p = xaccept_nonblock(s, NULL, NULL);
+ if (p < 0)
+ goto close_cli;
+ xclose(p);
+ } else {
+ char b = 'a';
+ ssize_t n;
+
+ n = xsend(c, &b, sizeof(b), 0);
+ if (n == -1)
+ goto close_cli;
+
+ n = xrecv_nonblock(s, &b, sizeof(b), 0);
+ if (n == -1)
+ goto close_cli;
+ }
+
+ key = SK_PASS;
+ err = xbpf_map_lookup_elem(verd_map, &key, &pass);
+ if (err)
+ goto close_cli;
+ if (pass != 1)
+ FAIL("want pass count 1, have %d", pass);
+
+close_cli:
+ xclose(c);
+close_srv:
+ xclose(s);
+}
+
+static void test_reuseport_select_connected(int family, int sotype,
+ int sock_map, int verd_map,
+ int reuseport_prog)
+{
+ struct sockaddr_storage addr;
+ int s, c0, c1, p0, err;
+ unsigned int drop;
+ socklen_t len;
+ u64 value;
+ u32 key;
+
+ zero_verdict_count(verd_map);
+
+ s = socket_loopback_reuseport(family, sotype, reuseport_prog);
+ if (s < 0)
+ return;
+
+ /* Populate sock_map[0] to avoid ENOENT on first connection */
+ key = 0;
+ value = s;
+ err = xbpf_map_update_elem(sock_map, &key, &value, BPF_NOEXIST);
+ if (err)
+ goto close_srv;
+
+ len = sizeof(addr);
+ err = xgetsockname(s, sockaddr(&addr), &len);
+ if (err)
+ goto close_srv;
+
+ c0 = xsocket(family, sotype, 0);
+ if (c0 < 0)
+ goto close_srv;
+
+ err = xconnect(c0, sockaddr(&addr), len);
+ if (err)
+ goto close_cli0;
+
+ if (sotype == SOCK_STREAM) {
+ p0 = xaccept_nonblock(s, NULL, NULL);
+ if (p0 < 0)
+ goto close_cli0;
+ } else {
+ p0 = xsocket(family, sotype, 0);
+ if (p0 < 0)
+ goto close_cli0;
+
+ len = sizeof(addr);
+ err = xgetsockname(c0, sockaddr(&addr), &len);
+ if (err)
+ goto close_cli0;
+
+ err = xconnect(p0, sockaddr(&addr), len);
+ if (err)
+ goto close_cli0;
+ }
+
+ /* Update sock_map[0] to redirect to a connected socket */
+ key = 0;
+ value = p0;
+ err = xbpf_map_update_elem(sock_map, &key, &value, BPF_EXIST);
+ if (err)
+ goto close_peer0;
+
+ c1 = xsocket(family, sotype, 0);
+ if (c1 < 0)
+ goto close_peer0;
+
+ len = sizeof(addr);
+ err = xgetsockname(s, sockaddr(&addr), &len);
+ if (err)
+ goto close_srv;
+
+ errno = 0;
+ err = connect(c1, sockaddr(&addr), len);
+ if (sotype == SOCK_DGRAM) {
+ char b = 'a';
+ ssize_t n;
+
+ n = xsend(c1, &b, sizeof(b), 0);
+ if (n == -1)
+ goto close_cli1;
+
+ n = recv_timeout(c1, &b, sizeof(b), 0, IO_TIMEOUT_SEC);
+ err = n == -1;
+ }
+ if (!err || errno != ECONNREFUSED)
+ FAIL_ERRNO("connect: expected ECONNREFUSED");
+
+ key = SK_DROP;
+ err = xbpf_map_lookup_elem(verd_map, &key, &drop);
+ if (err)
+ goto close_cli1;
+ if (drop != 1)
+ FAIL("want drop count 1, have %d", drop);
+
+close_cli1:
+ xclose(c1);
+close_peer0:
+ xclose(p0);
+close_cli0:
+ xclose(c0);
+close_srv:
+ xclose(s);
+}
+
+/* Check that redirecting across reuseport groups is not allowed. */
+static void test_reuseport_mixed_groups(int family, int sotype, int sock_map,
+ int verd_map, int reuseport_prog)
+{
+ struct sockaddr_storage addr;
+ int s1, s2, c, err;
+ unsigned int drop;
+ socklen_t len;
+ u64 value;
+ u32 key;
+
+ zero_verdict_count(verd_map);
+
+ /* Create two listeners, each in its own reuseport group */
+ s1 = socket_loopback_reuseport(family, sotype, reuseport_prog);
+ if (s1 < 0)
+ return;
+
+ s2 = socket_loopback_reuseport(family, sotype, reuseport_prog);
+ if (s2 < 0)
+ goto close_srv1;
+
+ key = 0;
+ value = s1;
+ err = xbpf_map_update_elem(sock_map, &key, &value, BPF_NOEXIST);
+ if (err)
+ goto close_srv2;
+
+ key = 1;
+ value = s2;
+ err = xbpf_map_update_elem(sock_map, &key, &value, BPF_NOEXIST);
+
+ /* Connect to s2, reuseport BPF selects s1 via sock_map[0] */
+ len = sizeof(addr);
+ err = xgetsockname(s2, sockaddr(&addr), &len);
+ if (err)
+ goto close_srv2;
+
+ c = xsocket(family, sotype, 0);
+ if (c < 0)
+ goto close_srv2;
+
+ err = connect(c, sockaddr(&addr), len);
+ if (sotype == SOCK_DGRAM) {
+ char b = 'a';
+ ssize_t n;
+
+ n = xsend(c, &b, sizeof(b), 0);
+ if (n == -1)
+ goto close_cli;
+
+ n = recv_timeout(c, &b, sizeof(b), 0, IO_TIMEOUT_SEC);
+ err = n == -1;
+ }
+ if (!err || errno != ECONNREFUSED) {
+ FAIL_ERRNO("connect: expected ECONNREFUSED");
+ goto close_cli;
+ }
+
+ /* Expect drop, can't redirect outside of reuseport group */
+ key = SK_DROP;
+ err = xbpf_map_lookup_elem(verd_map, &key, &drop);
+ if (err)
+ goto close_cli;
+ if (drop != 1)
+ FAIL("want drop count 1, have %d", drop);
+
+close_cli:
+ xclose(c);
+close_srv2:
+ xclose(s2);
+close_srv1:
+ xclose(s1);
+}
+
+#define TEST(fn, ...) \
+ { \
+ fn, #fn, __VA_ARGS__ \
+ }
+
+static void test_ops_cleanup(const struct bpf_map *map)
+{
+ const struct bpf_map_def *def;
+ int err, mapfd;
+ u32 key;
+
+ def = bpf_map__def(map);
+ mapfd = bpf_map__fd(map);
+
+ for (key = 0; key < def->max_entries; key++) {
+ err = bpf_map_delete_elem(mapfd, &key);
+ if (err && errno != EINVAL && errno != ENOENT)
+ FAIL_ERRNO("map_delete: expected EINVAL/ENOENT");
+ }
+}
+
+static const char *family_str(sa_family_t family)
+{
+ switch (family) {
+ case AF_INET:
+ return "IPv4";
+ case AF_INET6:
+ return "IPv6";
+ default:
+ return "unknown";
+ }
+}
+
+static const char *map_type_str(const struct bpf_map *map)
+{
+ const struct bpf_map_def *def;
+
+ def = bpf_map__def(map);
+ if (IS_ERR(def))
+ return "invalid";
+
+ switch (def->type) {
+ case BPF_MAP_TYPE_SOCKMAP:
+ return "sockmap";
+ case BPF_MAP_TYPE_SOCKHASH:
+ return "sockhash";
+ default:
+ return "unknown";
+ }
+}
+
+static const char *sotype_str(int sotype)
+{
+ switch (sotype) {
+ case SOCK_DGRAM:
+ return "UDP";
+ case SOCK_STREAM:
+ return "TCP";
+ default:
+ return "unknown";
+ }
+}
+
+static void test_ops(struct test_sockmap_listen *skel, struct bpf_map *map,
+ int family, int sotype)
+{
+ const struct op_test {
+ void (*fn)(int family, int sotype, int mapfd);
+ const char *name;
+ int sotype;
+ } tests[] = {
+ /* insert */
+ TEST(test_insert_invalid),
+ TEST(test_insert_opened),
+ TEST(test_insert_bound, SOCK_STREAM),
+ TEST(test_insert),
+ /* delete */
+ TEST(test_delete_after_insert),
+ TEST(test_delete_after_close),
+ /* lookup */
+ TEST(test_lookup_after_insert),
+ TEST(test_lookup_after_delete),
+ TEST(test_lookup_32_bit_value),
+ /* update */
+ TEST(test_update_existing),
+ /* races with insert/delete */
+ TEST(test_destroy_orphan_child, SOCK_STREAM),
+ TEST(test_syn_recv_insert_delete, SOCK_STREAM),
+ TEST(test_race_insert_listen, SOCK_STREAM),
+ /* child clone */
+ TEST(test_clone_after_delete, SOCK_STREAM),
+ TEST(test_accept_after_delete, SOCK_STREAM),
+ TEST(test_accept_before_delete, SOCK_STREAM),
+ };
+ const char *family_name, *map_name, *sotype_name;
+ const struct op_test *t;
+ char s[MAX_TEST_NAME];
+ int map_fd;
+
+ family_name = family_str(family);
+ map_name = map_type_str(map);
+ sotype_name = sotype_str(sotype);
+ map_fd = bpf_map__fd(map);
+
+ for (t = tests; t < tests + ARRAY_SIZE(tests); t++) {
+ snprintf(s, sizeof(s), "%s %s %s %s", map_name, family_name,
+ sotype_name, t->name);
+
+ if (t->sotype != 0 && t->sotype != sotype)
+ continue;
+
+ if (!test__start_subtest(s))
+ continue;
+
+ t->fn(family, sotype, map_fd);
+ test_ops_cleanup(map);
+ }
+}
+
+static void test_redir(struct test_sockmap_listen *skel, struct bpf_map *map,
+ int family, int sotype)
+{
+ const struct redir_test {
+ void (*fn)(struct test_sockmap_listen *skel,
+ struct bpf_map *map, int family, int sotype);
+ const char *name;
+ } tests[] = {
+ TEST(test_skb_redir_to_connected),
+ TEST(test_skb_redir_to_listening),
+ TEST(test_msg_redir_to_connected),
+ TEST(test_msg_redir_to_listening),
+ };
+ const char *family_name, *map_name;
+ const struct redir_test *t;
+ char s[MAX_TEST_NAME];
+
+ family_name = family_str(family);
+ map_name = map_type_str(map);
+
+ for (t = tests; t < tests + ARRAY_SIZE(tests); t++) {
+ snprintf(s, sizeof(s), "%s %s %s", map_name, family_name,
+ t->name);
+
+ if (!test__start_subtest(s))
+ continue;
+
+ t->fn(skel, map, family, sotype);
+ }
+}
+
+static void test_reuseport(struct test_sockmap_listen *skel,
+ struct bpf_map *map, int family, int sotype)
+{
+ const struct reuseport_test {
+ void (*fn)(int family, int sotype, int socket_map,
+ int verdict_map, int reuseport_prog);
+ const char *name;
+ int sotype;
+ } tests[] = {
+ TEST(test_reuseport_select_listening),
+ TEST(test_reuseport_select_connected),
+ TEST(test_reuseport_mixed_groups),
+ };
+ int socket_map, verdict_map, reuseport_prog;
+ const char *family_name, *map_name, *sotype_name;
+ const struct reuseport_test *t;
+ char s[MAX_TEST_NAME];
+
+ family_name = family_str(family);
+ map_name = map_type_str(map);
+ sotype_name = sotype_str(sotype);
+
+ socket_map = bpf_map__fd(map);
+ verdict_map = bpf_map__fd(skel->maps.verdict_map);
+ reuseport_prog = bpf_program__fd(skel->progs.prog_reuseport);
+
+ for (t = tests; t < tests + ARRAY_SIZE(tests); t++) {
+ snprintf(s, sizeof(s), "%s %s %s %s", map_name, family_name,
+ sotype_name, t->name);
+
+ if (t->sotype != 0 && t->sotype != sotype)
+ continue;
+
+ if (!test__start_subtest(s))
+ continue;
+
+ t->fn(family, sotype, socket_map, verdict_map, reuseport_prog);
+ }
+}
+
+static void run_tests(struct test_sockmap_listen *skel, struct bpf_map *map,
+ int family)
+{
+ test_ops(skel, map, family, SOCK_STREAM);
+ test_ops(skel, map, family, SOCK_DGRAM);
+ test_redir(skel, map, family, SOCK_STREAM);
+ test_reuseport(skel, map, family, SOCK_STREAM);
+ test_reuseport(skel, map, family, SOCK_DGRAM);
+}
+
+void test_sockmap_listen(void)
+{
+ struct test_sockmap_listen *skel;
+
+ skel = test_sockmap_listen__open_and_load();
+ if (!skel) {
+ FAIL("skeleton open/load failed");
+ return;
+ }
+
+ skel->bss->test_sockmap = true;
+ run_tests(skel, skel->maps.sock_map, AF_INET);
+ run_tests(skel, skel->maps.sock_map, AF_INET6);
+
+ skel->bss->test_sockmap = false;
+ run_tests(skel, skel->maps.sock_hash, AF_INET);
+ run_tests(skel, skel->maps.sock_hash, AF_INET6);
+
+ test_sockmap_listen__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/spinlock.c b/tools/testing/selftests/bpf/prog_tests/spinlock.c
index 1ae00cd3174e..7577a77a4c4c 100644
--- a/tools/testing/selftests/bpf/prog_tests/spinlock.c
+++ b/tools/testing/selftests/bpf/prog_tests/spinlock.c
@@ -1,5 +1,19 @@
// SPDX-License-Identifier: GPL-2.0
#include <test_progs.h>
+#include <network_helpers.h>
+
+static void *spin_lock_thread(void *arg)
+{
+ __u32 duration, retval;
+ int err, prog_fd = *(u32 *) arg;
+
+ err = bpf_prog_test_run(prog_fd, 10000, &pkt_v4, sizeof(pkt_v4),
+ NULL, NULL, &retval, &duration);
+ CHECK(err || retval, "",
+ "err %d errno %d retval %d duration %d\n",
+ err, errno, retval, duration);
+ pthread_exit(arg);
+}
void test_spinlock(void)
{
diff --git a/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c b/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c
index f4cd60d6fba2..9013a0c01eed 100644
--- a/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c
+++ b/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c
@@ -1,6 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
#include <test_progs.h>
#include "cgroup_helpers.h"
+#include "network_helpers.h"
struct tcp_rtt_storage {
__u32 invoked;
@@ -87,34 +88,6 @@ static int verify_sk(int map_fd, int client_fd, const char *msg, __u32 invoked,
return err;
}
-static int connect_to_server(int server_fd)
-{
- struct sockaddr_storage addr;
- socklen_t len = sizeof(addr);
- int fd;
-
- fd = socket(AF_INET, SOCK_STREAM, 0);
- if (fd < 0) {
- log_err("Failed to create client socket");
- return -1;
- }
-
- if (getsockname(server_fd, (struct sockaddr *)&addr, &len)) {
- log_err("Failed to get server addr");
- goto out;
- }
-
- if (connect(fd, (const struct sockaddr *)&addr, len) < 0) {
- log_err("Fail to connect to server");
- goto out;
- }
-
- return fd;
-
-out:
- close(fd);
- return -1;
-}
static int run_test(int cgroup_fd, int server_fd)
{
@@ -145,7 +118,7 @@ static int run_test(int cgroup_fd, int server_fd)
goto close_bpf_object;
}
- client_fd = connect_to_server(server_fd);
+ client_fd = connect_to_fd(AF_INET, SOCK_STREAM, server_fd);
if (client_fd < 0) {
err = -1;
goto close_bpf_object;
@@ -180,95 +153,22 @@ close_bpf_object:
return err;
}
-static int start_server(void)
-{
- struct sockaddr_in addr = {
- .sin_family = AF_INET,
- .sin_addr.s_addr = htonl(INADDR_LOOPBACK),
- };
- int fd;
-
- fd = socket(AF_INET, SOCK_STREAM, 0);
- if (fd < 0) {
- log_err("Failed to create server socket");
- return -1;
- }
-
- if (bind(fd, (const struct sockaddr *)&addr, sizeof(addr)) < 0) {
- log_err("Failed to bind socket");
- close(fd);
- return -1;
- }
-
- return fd;
-}
-
-static pthread_mutex_t server_started_mtx = PTHREAD_MUTEX_INITIALIZER;
-static pthread_cond_t server_started = PTHREAD_COND_INITIALIZER;
-
-static void *server_thread(void *arg)
-{
- struct sockaddr_storage addr;
- socklen_t len = sizeof(addr);
- int fd = *(int *)arg;
- int client_fd;
- int err;
-
- err = listen(fd, 1);
-
- pthread_mutex_lock(&server_started_mtx);
- pthread_cond_signal(&server_started);
- pthread_mutex_unlock(&server_started_mtx);
-
- if (CHECK_FAIL(err < 0)) {
- perror("Failed to listed on socket");
- return NULL;
- }
-
- client_fd = accept(fd, (struct sockaddr *)&addr, &len);
- if (CHECK_FAIL(client_fd < 0)) {
- perror("Failed to accept client");
- return NULL;
- }
-
- /* Wait for the next connection (that never arrives)
- * to keep this thread alive to prevent calling
- * close() on client_fd.
- */
- if (CHECK_FAIL(accept(fd, (struct sockaddr *)&addr, &len) >= 0)) {
- perror("Unexpected success in second accept");
- return NULL;
- }
-
- close(client_fd);
-
- return NULL;
-}
-
void test_tcp_rtt(void)
{
int server_fd, cgroup_fd;
- pthread_t tid;
cgroup_fd = test__join_cgroup("/tcp_rtt");
if (CHECK_FAIL(cgroup_fd < 0))
return;
- server_fd = start_server();
+ server_fd = start_server(AF_INET, SOCK_STREAM);
if (CHECK_FAIL(server_fd < 0))
goto close_cgroup_fd;
- if (CHECK_FAIL(pthread_create(&tid, NULL, server_thread,
- (void *)&server_fd)))
- goto close_server_fd;
-
- pthread_mutex_lock(&server_started_mtx);
- pthread_cond_wait(&server_started, &server_started_mtx);
- pthread_mutex_unlock(&server_started_mtx);
-
CHECK_FAIL(run_test(cgroup_fd, server_fd));
-close_server_fd:
+
close(server_fd);
+
close_cgroup_fd:
close(cgroup_fd);
}
diff --git a/tools/testing/selftests/bpf/prog_tests/test_lsm.c b/tools/testing/selftests/bpf/prog_tests/test_lsm.c
new file mode 100644
index 000000000000..b17eb2045c1d
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/test_lsm.c
@@ -0,0 +1,86 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright (C) 2020 Google LLC.
+ */
+
+#include <test_progs.h>
+#include <sys/mman.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include <malloc.h>
+#include <stdlib.h>
+
+#include "lsm.skel.h"
+
+char *CMD_ARGS[] = {"true", NULL};
+
+#define GET_PAGE_ADDR(ADDR, PAGE_SIZE) \
+ (char *)(((unsigned long) (ADDR + PAGE_SIZE)) & ~(PAGE_SIZE-1))
+
+int stack_mprotect(void)
+{
+ void *buf;
+ long sz;
+ int ret;
+
+ sz = sysconf(_SC_PAGESIZE);
+ if (sz < 0)
+ return sz;
+
+ buf = alloca(sz * 3);
+ ret = mprotect(GET_PAGE_ADDR(buf, sz), sz,
+ PROT_READ | PROT_WRITE | PROT_EXEC);
+ return ret;
+}
+
+int exec_cmd(int *monitored_pid)
+{
+ int child_pid, child_status;
+
+ child_pid = fork();
+ if (child_pid == 0) {
+ *monitored_pid = getpid();
+ execvp(CMD_ARGS[0], CMD_ARGS);
+ return -EINVAL;
+ } else if (child_pid > 0) {
+ waitpid(child_pid, &child_status, 0);
+ return child_status;
+ }
+
+ return -EINVAL;
+}
+
+void test_test_lsm(void)
+{
+ struct lsm *skel = NULL;
+ int err, duration = 0;
+
+ skel = lsm__open_and_load();
+ if (CHECK(!skel, "skel_load", "lsm skeleton failed\n"))
+ goto close_prog;
+
+ err = lsm__attach(skel);
+ if (CHECK(err, "attach", "lsm attach failed: %d\n", err))
+ goto close_prog;
+
+ err = exec_cmd(&skel->bss->monitored_pid);
+ if (CHECK(err < 0, "exec_cmd", "err %d errno %d\n", err, errno))
+ goto close_prog;
+
+ CHECK(skel->bss->bprm_count != 1, "bprm_count", "bprm_count = %d\n",
+ skel->bss->bprm_count);
+
+ skel->bss->monitored_pid = getpid();
+
+ err = stack_mprotect();
+ if (CHECK(errno != EPERM, "stack_mprotect", "want err=EPERM, got %d\n",
+ errno))
+ goto close_prog;
+
+ CHECK(skel->bss->mprotect_count != 1, "mprotect_count",
+ "mprotect_count = %d\n", skel->bss->mprotect_count);
+
+close_prog:
+ lsm__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/test_overhead.c b/tools/testing/selftests/bpf/prog_tests/test_overhead.c
index 465b371a561d..2702df2b2343 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_overhead.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_overhead.c
@@ -61,9 +61,10 @@ void test_test_overhead(void)
const char *raw_tp_name = "raw_tp/task_rename";
const char *fentry_name = "fentry/__set_task_comm";
const char *fexit_name = "fexit/__set_task_comm";
+ const char *fmodret_name = "fmod_ret/__set_task_comm";
const char *kprobe_func = "__set_task_comm";
struct bpf_program *kprobe_prog, *kretprobe_prog, *raw_tp_prog;
- struct bpf_program *fentry_prog, *fexit_prog;
+ struct bpf_program *fentry_prog, *fexit_prog, *fmodret_prog;
struct bpf_object *obj;
struct bpf_link *link;
int err, duration = 0;
@@ -96,6 +97,10 @@ void test_test_overhead(void)
if (CHECK(!fexit_prog, "find_probe",
"prog '%s' not found\n", fexit_name))
goto cleanup;
+ fmodret_prog = bpf_object__find_program_by_title(obj, fmodret_name);
+ if (CHECK(!fmodret_prog, "find_probe",
+ "prog '%s' not found\n", fmodret_name))
+ goto cleanup;
err = bpf_object__load(obj);
if (CHECK(err, "obj_load", "err %d\n", err))
@@ -142,6 +147,13 @@ void test_test_overhead(void)
goto cleanup;
test_run("fexit");
bpf_link__destroy(link);
+
+ /* attach fmod_ret */
+ link = bpf_program__attach_trace(fmodret_prog);
+ if (CHECK(IS_ERR(link), "attach fmod_ret", "err %ld\n", PTR_ERR(link)))
+ goto cleanup;
+ test_run("fmod_ret");
+ bpf_link__destroy(link);
cleanup:
prctl(PR_SET_NAME, comm, 0L, 0L, 0L);
bpf_object__close(obj);
diff --git a/tools/testing/selftests/bpf/prog_tests/trampoline_count.c b/tools/testing/selftests/bpf/prog_tests/trampoline_count.c
index 1f6ccdaed1ac..781c8d11604b 100644
--- a/tools/testing/selftests/bpf/prog_tests/trampoline_count.c
+++ b/tools/testing/selftests/bpf/prog_tests/trampoline_count.c
@@ -55,31 +55,40 @@ void test_trampoline_count(void)
/* attach 'allowed' 40 trampoline programs */
for (i = 0; i < MAX_TRAMP_PROGS; i++) {
obj = bpf_object__open_file(object, NULL);
- if (CHECK(IS_ERR(obj), "obj_open_file", "err %ld\n", PTR_ERR(obj)))
+ if (CHECK(IS_ERR(obj), "obj_open_file", "err %ld\n", PTR_ERR(obj))) {
+ obj = NULL;
goto cleanup;
+ }
err = bpf_object__load(obj);
if (CHECK(err, "obj_load", "err %d\n", err))
goto cleanup;
inst[i].obj = obj;
+ obj = NULL;
if (rand() % 2) {
- link = load(obj, fentry_name);
- if (CHECK(IS_ERR(link), "attach prog", "err %ld\n", PTR_ERR(link)))
+ link = load(inst[i].obj, fentry_name);
+ if (CHECK(IS_ERR(link), "attach prog", "err %ld\n", PTR_ERR(link))) {
+ link = NULL;
goto cleanup;
+ }
inst[i].link_fentry = link;
} else {
- link = load(obj, fexit_name);
- if (CHECK(IS_ERR(link), "attach prog", "err %ld\n", PTR_ERR(link)))
+ link = load(inst[i].obj, fexit_name);
+ if (CHECK(IS_ERR(link), "attach prog", "err %ld\n", PTR_ERR(link))) {
+ link = NULL;
goto cleanup;
+ }
inst[i].link_fexit = link;
}
}
/* and try 1 extra.. */
obj = bpf_object__open_file(object, NULL);
- if (CHECK(IS_ERR(obj), "obj_open_file", "err %ld\n", PTR_ERR(obj)))
+ if (CHECK(IS_ERR(obj), "obj_open_file", "err %ld\n", PTR_ERR(obj))) {
+ obj = NULL;
goto cleanup;
+ }
err = bpf_object__load(obj);
if (CHECK(err, "obj_load", "err %d\n", err))
@@ -104,7 +113,9 @@ void test_trampoline_count(void)
cleanup_extra:
bpf_object__close(obj);
cleanup:
- while (--i) {
+ if (i >= MAX_TRAMP_PROGS)
+ i = MAX_TRAMP_PROGS - 1;
+ for (; i >= 0; i--) {
bpf_link__destroy(inst[i].link_fentry);
bpf_link__destroy(inst[i].link_fexit);
bpf_object__close(inst[i].obj);
diff --git a/tools/testing/selftests/bpf/prog_tests/vmlinux.c b/tools/testing/selftests/bpf/prog_tests/vmlinux.c
new file mode 100644
index 000000000000..72310cfc6474
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/vmlinux.c
@@ -0,0 +1,43 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+
+#include <test_progs.h>
+#include <time.h>
+#include "test_vmlinux.skel.h"
+
+#define MY_TV_NSEC 1337
+
+static void nsleep()
+{
+ struct timespec ts = { .tv_nsec = MY_TV_NSEC };
+
+ (void)syscall(__NR_nanosleep, &ts, NULL);
+}
+
+void test_vmlinux(void)
+{
+ int duration = 0, err;
+ struct test_vmlinux* skel;
+ struct test_vmlinux__bss *bss;
+
+ skel = test_vmlinux__open_and_load();
+ if (CHECK(!skel, "skel_open", "failed to open skeleton\n"))
+ return;
+ bss = skel->bss;
+
+ err = test_vmlinux__attach(skel);
+ if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err))
+ goto cleanup;
+
+ /* trigger everything */
+ nsleep();
+
+ CHECK(!bss->tp_called, "tp", "not called\n");
+ CHECK(!bss->raw_tp_called, "raw_tp", "not called\n");
+ CHECK(!bss->tp_btf_called, "tp_btf", "not called\n");
+ CHECK(!bss->kprobe_called, "kprobe", "not called\n");
+ CHECK(!bss->fentry_called, "fentry", "not called\n");
+
+cleanup:
+ test_vmlinux__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp.c b/tools/testing/selftests/bpf/prog_tests/xdp.c
index dcb5ecac778e..48921ff74850 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp.c
@@ -1,5 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
#include <test_progs.h>
+#include <network_helpers.h>
void test_xdp(void)
{
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c b/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c
index 3744196d7cba..d5c98f2cb12f 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c
@@ -1,13 +1,14 @@
// SPDX-License-Identifier: GPL-2.0
#include <test_progs.h>
+#include <network_helpers.h>
-void test_xdp_adjust_tail(void)
+void test_xdp_adjust_tail_shrink(void)
{
- const char *file = "./test_adjust_tail.o";
+ const char *file = "./test_xdp_adjust_tail_shrink.o";
+ __u32 duration, retval, size, expect_sz;
struct bpf_object *obj;
- char buf[128];
- __u32 duration, retval, size;
int err, prog_fd;
+ char buf[128];
err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd);
if (CHECK_FAIL(err))
@@ -20,10 +21,121 @@ void test_xdp_adjust_tail(void)
"ipv4", "err %d errno %d retval %d size %d\n",
err, errno, retval, size);
+ expect_sz = sizeof(pkt_v6) - 20; /* Test shrink with 20 bytes */
err = bpf_prog_test_run(prog_fd, 1, &pkt_v6, sizeof(pkt_v6),
buf, &size, &retval, &duration);
- CHECK(err || retval != XDP_TX || size != 54,
- "ipv6", "err %d errno %d retval %d size %d\n",
+ CHECK(err || retval != XDP_TX || size != expect_sz,
+ "ipv6", "err %d errno %d retval %d size %d expect-size %d\n",
+ err, errno, retval, size, expect_sz);
+ bpf_object__close(obj);
+}
+
+void test_xdp_adjust_tail_grow(void)
+{
+ const char *file = "./test_xdp_adjust_tail_grow.o";
+ struct bpf_object *obj;
+ char buf[4096]; /* avoid segfault: large buf to hold grow results */
+ __u32 duration, retval, size, expect_sz;
+ int err, prog_fd;
+
+ err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd);
+ if (CHECK_FAIL(err))
+ return;
+
+ err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4),
+ buf, &size, &retval, &duration);
+ CHECK(err || retval != XDP_DROP,
+ "ipv4", "err %d errno %d retval %d size %d\n",
err, errno, retval, size);
+
+ expect_sz = sizeof(pkt_v6) + 40; /* Test grow with 40 bytes */
+ err = bpf_prog_test_run(prog_fd, 1, &pkt_v6, sizeof(pkt_v6) /* 74 */,
+ buf, &size, &retval, &duration);
+ CHECK(err || retval != XDP_TX || size != expect_sz,
+ "ipv6", "err %d errno %d retval %d size %d expect-size %d\n",
+ err, errno, retval, size, expect_sz);
+
+ bpf_object__close(obj);
+}
+
+void test_xdp_adjust_tail_grow2(void)
+{
+ const char *file = "./test_xdp_adjust_tail_grow.o";
+ char buf[4096]; /* avoid segfault: large buf to hold grow results */
+ int tailroom = 320; /* SKB_DATA_ALIGN(sizeof(struct skb_shared_info))*/;
+ struct bpf_object *obj;
+ int err, cnt, i;
+ int max_grow;
+
+ struct bpf_prog_test_run_attr tattr = {
+ .repeat = 1,
+ .data_in = &buf,
+ .data_out = &buf,
+ .data_size_in = 0, /* Per test */
+ .data_size_out = 0, /* Per test */
+ };
+
+ err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj, &tattr.prog_fd);
+ if (CHECK_ATTR(err, "load", "err %d errno %d\n", err, errno))
+ return;
+
+ /* Test case-64 */
+ memset(buf, 1, sizeof(buf));
+ tattr.data_size_in = 64; /* Determine test case via pkt size */
+ tattr.data_size_out = 128; /* Limit copy_size */
+ /* Kernel side alloc packet memory area that is zero init */
+ err = bpf_prog_test_run_xattr(&tattr);
+
+ CHECK_ATTR(errno != ENOSPC /* Due limit copy_size in bpf_test_finish */
+ || tattr.retval != XDP_TX
+ || tattr.data_size_out != 192, /* Expected grow size */
+ "case-64",
+ "err %d errno %d retval %d size %d\n",
+ err, errno, tattr.retval, tattr.data_size_out);
+
+ /* Extra checks for data contents */
+ CHECK_ATTR(tattr.data_size_out != 192
+ || buf[0] != 1 || buf[63] != 1 /* 0-63 memset to 1 */
+ || buf[64] != 0 || buf[127] != 0 /* 64-127 memset to 0 */
+ || buf[128] != 1 || buf[191] != 1, /*128-191 memset to 1 */
+ "case-64-data",
+ "err %d errno %d retval %d size %d\n",
+ err, errno, tattr.retval, tattr.data_size_out);
+
+ /* Test case-128 */
+ memset(buf, 2, sizeof(buf));
+ tattr.data_size_in = 128; /* Determine test case via pkt size */
+ tattr.data_size_out = sizeof(buf); /* Copy everything */
+ err = bpf_prog_test_run_xattr(&tattr);
+
+ max_grow = 4096 - XDP_PACKET_HEADROOM - tailroom; /* 3520 */
+ CHECK_ATTR(err
+ || tattr.retval != XDP_TX
+ || tattr.data_size_out != max_grow,/* Expect max grow size */
+ "case-128",
+ "err %d errno %d retval %d size %d expect-size %d\n",
+ err, errno, tattr.retval, tattr.data_size_out, max_grow);
+
+ /* Extra checks for data content: Count grow size, will contain zeros */
+ for (i = 0, cnt = 0; i < sizeof(buf); i++) {
+ if (buf[i] == 0)
+ cnt++;
+ }
+ CHECK_ATTR((cnt != (max_grow - tattr.data_size_in)) /* Grow increase */
+ || tattr.data_size_out != max_grow, /* Total grow size */
+ "case-128-data",
+ "err %d errno %d retval %d size %d grow-size %d\n",
+ err, errno, tattr.retval, tattr.data_size_out, cnt);
+
bpf_object__close(obj);
}
+
+void test_xdp_adjust_tail(void)
+{
+ if (test__start_subtest("xdp_adjust_tail_shrink"))
+ test_xdp_adjust_tail_shrink();
+ if (test__start_subtest("xdp_adjust_tail_grow"))
+ test_xdp_adjust_tail_grow();
+ if (test__start_subtest("xdp_adjust_tail_grow2"))
+ test_xdp_adjust_tail_grow2();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_attach.c
new file mode 100644
index 000000000000..15ef3531483e
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_attach.c
@@ -0,0 +1,90 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+
+#define IFINDEX_LO 1
+#define XDP_FLAGS_REPLACE (1U << 4)
+
+void test_xdp_attach(void)
+{
+ __u32 duration = 0, id1, id2, id0 = 0, len;
+ struct bpf_object *obj1, *obj2, *obj3;
+ const char *file = "./test_xdp.o";
+ struct bpf_prog_info info = {};
+ int err, fd1, fd2, fd3;
+ DECLARE_LIBBPF_OPTS(bpf_xdp_set_link_opts, opts,
+ .old_fd = -1);
+
+ len = sizeof(info);
+
+ err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj1, &fd1);
+ if (CHECK_FAIL(err))
+ return;
+ err = bpf_obj_get_info_by_fd(fd1, &info, &len);
+ if (CHECK_FAIL(err))
+ goto out_1;
+ id1 = info.id;
+
+ err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj2, &fd2);
+ if (CHECK_FAIL(err))
+ goto out_1;
+
+ memset(&info, 0, sizeof(info));
+ err = bpf_obj_get_info_by_fd(fd2, &info, &len);
+ if (CHECK_FAIL(err))
+ goto out_2;
+ id2 = info.id;
+
+ err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj3, &fd3);
+ if (CHECK_FAIL(err))
+ goto out_2;
+
+ err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, fd1, XDP_FLAGS_REPLACE,
+ &opts);
+ if (CHECK(err, "load_ok", "initial load failed"))
+ goto out_close;
+
+ err = bpf_get_link_xdp_id(IFINDEX_LO, &id0, 0);
+ if (CHECK(err || id0 != id1, "id1_check",
+ "loaded prog id %u != id1 %u, err %d", id0, id1, err))
+ goto out_close;
+
+ err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, fd2, XDP_FLAGS_REPLACE,
+ &opts);
+ if (CHECK(!err, "load_fail", "load with expected id didn't fail"))
+ goto out;
+
+ opts.old_fd = fd1;
+ err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, fd2, 0, &opts);
+ if (CHECK(err, "replace_ok", "replace valid old_fd failed"))
+ goto out;
+ err = bpf_get_link_xdp_id(IFINDEX_LO, &id0, 0);
+ if (CHECK(err || id0 != id2, "id2_check",
+ "loaded prog id %u != id2 %u, err %d", id0, id2, err))
+ goto out_close;
+
+ err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, fd3, 0, &opts);
+ if (CHECK(!err, "replace_fail", "replace invalid old_fd didn't fail"))
+ goto out;
+
+ err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, -1, 0, &opts);
+ if (CHECK(!err, "remove_fail", "remove invalid old_fd didn't fail"))
+ goto out;
+
+ opts.old_fd = fd2;
+ err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, -1, 0, &opts);
+ if (CHECK(err, "remove_ok", "remove valid old_fd failed"))
+ goto out;
+
+ err = bpf_get_link_xdp_id(IFINDEX_LO, &id0, 0);
+ if (CHECK(err || id0 != 0, "unload_check",
+ "loaded prog id %u != 0, err %d", id0, err))
+ goto out_close;
+out:
+ bpf_set_link_xdp_fd(IFINDEX_LO, -1, 0);
+out_close:
+ bpf_object__close(obj3);
+out_2:
+ bpf_object__close(obj2);
+out_1:
+ bpf_object__close(obj1);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c
index 6b56bdc73ebc..2c6c570b21f8 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c
@@ -1,20 +1,55 @@
// SPDX-License-Identifier: GPL-2.0
#include <test_progs.h>
+#include <network_helpers.h>
#include <net/if.h>
#include "test_xdp.skel.h"
#include "test_xdp_bpf2bpf.skel.h"
+struct meta {
+ int ifindex;
+ int pkt_len;
+};
+
+static void on_sample(void *ctx, int cpu, void *data, __u32 size)
+{
+ int duration = 0;
+ struct meta *meta = (struct meta *)data;
+ struct ipv4_packet *trace_pkt_v4 = data + sizeof(*meta);
+
+ if (CHECK(size < sizeof(pkt_v4) + sizeof(*meta),
+ "check_size", "size %u < %zu\n",
+ size, sizeof(pkt_v4) + sizeof(*meta)))
+ return;
+
+ if (CHECK(meta->ifindex != if_nametoindex("lo"), "check_meta_ifindex",
+ "meta->ifindex = %d\n", meta->ifindex))
+ return;
+
+ if (CHECK(meta->pkt_len != sizeof(pkt_v4), "check_meta_pkt_len",
+ "meta->pkt_len = %zd\n", sizeof(pkt_v4)))
+ return;
+
+ if (CHECK(memcmp(trace_pkt_v4, &pkt_v4, sizeof(pkt_v4)),
+ "check_packet_content", "content not the same\n"))
+ return;
+
+ *(bool *)ctx = true;
+}
+
void test_xdp_bpf2bpf(void)
{
__u32 duration = 0, retval, size;
char buf[128];
int err, pkt_fd, map_fd;
+ bool passed = false;
struct iphdr *iph = (void *)buf + sizeof(struct ethhdr);
struct iptnl_info value4 = {.family = AF_INET};
struct test_xdp *pkt_skel = NULL;
struct test_xdp_bpf2bpf *ftrace_skel = NULL;
struct vip key4 = {.protocol = 6, .family = AF_INET};
- DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts);
+ struct bpf_program *prog;
+ struct perf_buffer *pb = NULL;
+ struct perf_buffer_opts pb_opts = {};
/* Load XDP program to introspect */
pkt_skel = test_xdp__open_and_load();
@@ -27,11 +62,21 @@ void test_xdp_bpf2bpf(void)
bpf_map_update_elem(map_fd, &key4, &value4, 0);
/* Load trace program */
- opts.attach_prog_fd = pkt_fd,
- ftrace_skel = test_xdp_bpf2bpf__open_opts(&opts);
+ ftrace_skel = test_xdp_bpf2bpf__open();
if (CHECK(!ftrace_skel, "__open", "ftrace skeleton failed\n"))
goto out;
+ /* Demonstrate the bpf_program__set_attach_target() API rather than
+ * the load with options, i.e. opts.attach_prog_fd.
+ */
+ prog = ftrace_skel->progs.trace_on_entry;
+ bpf_program__set_expected_attach_type(prog, BPF_TRACE_FENTRY);
+ bpf_program__set_attach_target(prog, pkt_fd, "_xdp_tx_iptunnel");
+
+ prog = ftrace_skel->progs.trace_on_exit;
+ bpf_program__set_expected_attach_type(prog, BPF_TRACE_FEXIT);
+ bpf_program__set_attach_target(prog, pkt_fd, "_xdp_tx_iptunnel");
+
err = test_xdp_bpf2bpf__load(ftrace_skel);
if (CHECK(err, "__load", "ftrace skeleton failed\n"))
goto out;
@@ -40,6 +85,14 @@ void test_xdp_bpf2bpf(void)
if (CHECK(err, "ftrace_attach", "ftrace attach failed: %d\n", err))
goto out;
+ /* Set up perf buffer */
+ pb_opts.sample_cb = on_sample;
+ pb_opts.ctx = &passed;
+ pb = perf_buffer__new(bpf_map__fd(ftrace_skel->maps.perf_buf_map),
+ 1, &pb_opts);
+ if (CHECK(IS_ERR(pb), "perf_buf__new", "err %ld\n", PTR_ERR(pb)))
+ goto out;
+
/* Run test program */
err = bpf_prog_test_run(pkt_fd, 1, &pkt_v4, sizeof(pkt_v4),
buf, &size, &retval, &duration);
@@ -50,6 +103,15 @@ void test_xdp_bpf2bpf(void)
err, errno, retval, size))
goto out;
+ /* Make sure bpf_xdp_output() was triggered and it sent the expected
+ * data to the perf ring buffer.
+ */
+ err = perf_buffer__poll(pb, 100);
+ if (CHECK(err < 0, "perf_buffer__poll", "err %d\n", err))
+ goto out;
+
+ CHECK_FAIL(!passed);
+
/* Verify test results */
if (CHECK(ftrace_skel->bss->test_result_fentry != if_nametoindex("lo"),
"result", "fentry failed err %llu\n",
@@ -60,6 +122,8 @@ void test_xdp_bpf2bpf(void)
"fexit failed err %llu\n", ftrace_skel->bss->test_result_fexit);
out:
+ if (pb)
+ perf_buffer__free(pb);
test_xdp__destroy(pkt_skel);
test_xdp_bpf2bpf__destroy(ftrace_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
new file mode 100644
index 000000000000..d19dbd668f6a
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c
@@ -0,0 +1,97 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <uapi/linux/bpf.h>
+#include <linux/if_link.h>
+#include <test_progs.h>
+
+#include "test_xdp_devmap_helpers.skel.h"
+#include "test_xdp_with_devmap_helpers.skel.h"
+
+#define IFINDEX_LO 1
+
+struct bpf_devmap_val {
+ u32 ifindex; /* device index */
+ union {
+ int fd; /* prog fd on map write */
+ u32 id; /* prog id on map read */
+ } bpf_prog;
+};
+
+void test_xdp_with_devmap_helpers(void)
+{
+ struct test_xdp_with_devmap_helpers *skel;
+ struct bpf_prog_info info = {};
+ struct bpf_devmap_val val = {
+ .ifindex = IFINDEX_LO,
+ };
+ __u32 len = sizeof(info);
+ __u32 duration = 0, idx = 0;
+ int err, dm_fd, map_fd;
+
+
+ skel = test_xdp_with_devmap_helpers__open_and_load();
+ if (CHECK_FAIL(!skel)) {
+ perror("test_xdp_with_devmap_helpers__open_and_load");
+ return;
+ }
+
+ /* can not attach program with DEVMAPs that allow programs
+ * as xdp generic
+ */
+ dm_fd = bpf_program__fd(skel->progs.xdp_redir_prog);
+ err = bpf_set_link_xdp_fd(IFINDEX_LO, dm_fd, XDP_FLAGS_SKB_MODE);
+ CHECK(err == 0, "Generic attach of program with 8-byte devmap",
+ "should have failed\n");
+
+ dm_fd = bpf_program__fd(skel->progs.xdp_dummy_dm);
+ map_fd = bpf_map__fd(skel->maps.dm_ports);
+ err = bpf_obj_get_info_by_fd(dm_fd, &info, &len);
+ if (CHECK_FAIL(err))
+ goto out_close;
+
+ val.bpf_prog.fd = dm_fd;
+ err = bpf_map_update_elem(map_fd, &idx, &val, 0);
+ CHECK(err, "Add program to devmap entry",
+ "err %d errno %d\n", err, errno);
+
+ err = bpf_map_lookup_elem(map_fd, &idx, &val);
+ CHECK(err, "Read devmap entry", "err %d errno %d\n", err, errno);
+ CHECK(info.id != val.bpf_prog.id, "Expected program id in devmap entry",
+ "expected %u read %u\n", info.id, val.bpf_prog.id);
+
+ /* can not attach BPF_XDP_DEVMAP program to a device */
+ err = bpf_set_link_xdp_fd(IFINDEX_LO, dm_fd, XDP_FLAGS_SKB_MODE);
+ CHECK(err == 0, "Attach of BPF_XDP_DEVMAP program",
+ "should have failed\n");
+
+ val.ifindex = 1;
+ val.bpf_prog.fd = bpf_program__fd(skel->progs.xdp_dummy_prog);
+ err = bpf_map_update_elem(map_fd, &idx, &val, 0);
+ CHECK(err == 0, "Add non-BPF_XDP_DEVMAP program to devmap entry",
+ "should have failed\n");
+
+out_close:
+ test_xdp_with_devmap_helpers__destroy(skel);
+}
+
+void test_neg_xdp_devmap_helpers(void)
+{
+ struct test_xdp_devmap_helpers *skel;
+ __u32 duration = 0;
+
+ skel = test_xdp_devmap_helpers__open_and_load();
+ if (CHECK(skel,
+ "Load of XDP program accessing egress ifindex without attach type",
+ "should have failed\n")) {
+ test_xdp_devmap_helpers__destroy(skel);
+ }
+}
+
+
+void test_xdp_devmap_attach(void)
+{
+ if (test__start_subtest("DEVMAP with programs in entries"))
+ test_xdp_with_devmap_helpers();
+
+ if (test__start_subtest("Verifier check of DEVMAP programs"))
+ test_neg_xdp_devmap_helpers();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_info.c b/tools/testing/selftests/bpf/prog_tests/xdp_info.c
new file mode 100644
index 000000000000..d2d7a283d72f
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_info.c
@@ -0,0 +1,68 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/if_link.h>
+#include <test_progs.h>
+
+#define IFINDEX_LO 1
+
+void test_xdp_info(void)
+{
+ __u32 len = sizeof(struct bpf_prog_info), duration = 0, prog_id;
+ const char *file = "./xdp_dummy.o";
+ struct bpf_prog_info info = {};
+ struct bpf_object *obj;
+ int err, prog_fd;
+
+ /* Get prog_id for XDP_ATTACHED_NONE mode */
+
+ err = bpf_get_link_xdp_id(IFINDEX_LO, &prog_id, 0);
+ if (CHECK(err, "get_xdp_none", "errno=%d\n", errno))
+ return;
+ if (CHECK(prog_id, "prog_id_none", "unexpected prog_id=%u\n", prog_id))
+ return;
+
+ err = bpf_get_link_xdp_id(IFINDEX_LO, &prog_id, XDP_FLAGS_SKB_MODE);
+ if (CHECK(err, "get_xdp_none_skb", "errno=%d\n", errno))
+ return;
+ if (CHECK(prog_id, "prog_id_none_skb", "unexpected prog_id=%u\n",
+ prog_id))
+ return;
+
+ /* Setup prog */
+
+ err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd);
+ if (CHECK_FAIL(err))
+ return;
+
+ err = bpf_obj_get_info_by_fd(prog_fd, &info, &len);
+ if (CHECK(err, "get_prog_info", "errno=%d\n", errno))
+ goto out_close;
+
+ err = bpf_set_link_xdp_fd(IFINDEX_LO, prog_fd, XDP_FLAGS_SKB_MODE);
+ if (CHECK(err, "set_xdp_skb", "errno=%d\n", errno))
+ goto out_close;
+
+ /* Get prog_id for single prog mode */
+
+ err = bpf_get_link_xdp_id(IFINDEX_LO, &prog_id, 0);
+ if (CHECK(err, "get_xdp", "errno=%d\n", errno))
+ goto out;
+ if (CHECK(prog_id != info.id, "prog_id", "prog_id not available\n"))
+ goto out;
+
+ err = bpf_get_link_xdp_id(IFINDEX_LO, &prog_id, XDP_FLAGS_SKB_MODE);
+ if (CHECK(err, "get_xdp_skb", "errno=%d\n", errno))
+ goto out;
+ if (CHECK(prog_id != info.id, "prog_id_skb", "prog_id not available\n"))
+ goto out;
+
+ err = bpf_get_link_xdp_id(IFINDEX_LO, &prog_id, XDP_FLAGS_DRV_MODE);
+ if (CHECK(err, "get_xdp_drv", "errno=%d\n", errno))
+ goto out;
+ if (CHECK(prog_id, "prog_id_drv", "unexpected prog_id=%u\n", prog_id))
+ goto out;
+
+out:
+ bpf_set_link_xdp_fd(IFINDEX_LO, -1, 0);
+out_close:
+ bpf_object__close(obj);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_noinline.c b/tools/testing/selftests/bpf/prog_tests/xdp_noinline.c
index c9404e6b226e..f284f72158ef 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_noinline.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_noinline.c
@@ -1,5 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
#include <test_progs.h>
+#include <network_helpers.h>
void test_xdp_noinline(void)
{
diff --git a/tools/testing/selftests/bpf/progs/bpf_dctcp.c b/tools/testing/selftests/bpf/progs/bpf_dctcp.c
index b631fb5032d2..3fb4260570b1 100644
--- a/tools/testing/selftests/bpf/progs/bpf_dctcp.c
+++ b/tools/testing/selftests/bpf/progs/bpf_dctcp.c
@@ -6,14 +6,24 @@
* the kernel BPF logic.
*/
+#include <stddef.h>
#include <linux/bpf.h>
#include <linux/types.h>
#include <bpf/bpf_helpers.h>
-#include "bpf_trace_helpers.h"
+#include <bpf/bpf_tracing.h>
#include "bpf_tcp_helpers.h"
char _license[] SEC("license") = "GPL";
+int stg_result = 0;
+
+struct {
+ __uint(type, BPF_MAP_TYPE_SK_STORAGE);
+ __uint(map_flags, BPF_F_NO_PREALLOC);
+ __type(key, int);
+ __type(value, int);
+} sk_stg_map SEC(".maps");
+
#define DCTCP_MAX_ALPHA 1024U
struct dctcp {
@@ -43,12 +53,18 @@ void BPF_PROG(dctcp_init, struct sock *sk)
{
const struct tcp_sock *tp = tcp_sk(sk);
struct dctcp *ca = inet_csk_ca(sk);
+ int *stg;
ca->prior_rcv_nxt = tp->rcv_nxt;
ca->dctcp_alpha = min(dctcp_alpha_on_init, DCTCP_MAX_ALPHA);
ca->loss_cwnd = 0;
ca->ce_state = 0;
+ stg = bpf_sk_storage_get(&sk_stg_map, (void *)tp, NULL, 0);
+ if (stg) {
+ stg_result = *stg;
+ bpf_sk_storage_delete(&sk_stg_map, (void *)tp);
+ }
dctcp_reset(tp, ca);
}
diff --git a/tools/testing/selftests/bpf/progs/bpf_flow.c b/tools/testing/selftests/bpf/progs/bpf_flow.c
index 9941f0ba471e..de6de9221518 100644
--- a/tools/testing/selftests/bpf/progs/bpf_flow.c
+++ b/tools/testing/selftests/bpf/progs/bpf_flow.c
@@ -20,20 +20,20 @@
#include <bpf/bpf_endian.h>
int _version SEC("version") = 1;
-#define PROG(F) SEC(#F) int bpf_func_##F
+#define PROG(F) PROG_(F, _##F)
+#define PROG_(NUM, NAME) SEC("flow_dissector/"#NUM) int bpf_func##NAME
/* These are the identifiers of the BPF programs that will be used in tail
* calls. Name is limited to 16 characters, with the terminating character and
* bpf_func_ above, we have only 6 to work with, anything after will be cropped.
*/
-enum {
- IP,
- IPV6,
- IPV6OP, /* Destination/Hop-by-Hop Options IPv6 Extension header */
- IPV6FR, /* Fragmentation IPv6 Extension Header */
- MPLS,
- VLAN,
-};
+#define IP 0
+#define IPV6 1
+#define IPV6OP 2 /* Destination/Hop-by-Hop Options IPv6 Ext. Header */
+#define IPV6FR 3 /* Fragmentation IPv6 Extension Header */
+#define MPLS 4
+#define VLAN 5
+#define MAX_PROG 6
#define IP_MF 0x2000
#define IP_OFFSET 0x1FFF
@@ -59,7 +59,7 @@ struct frag_hdr {
struct {
__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
- __uint(max_entries, 8);
+ __uint(max_entries, MAX_PROG);
__uint(key_size, sizeof(__u32));
__uint(value_size, sizeof(__u32));
} jmp_table SEC(".maps");
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c
new file mode 100644
index 000000000000..b57bd6fef208
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c
@@ -0,0 +1,44 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+/* "undefine" structs in vmlinux.h, because we "override" them below */
+#define bpf_iter_meta bpf_iter_meta___not_used
+#define bpf_iter__bpf_map bpf_iter__bpf_map___not_used
+#include "vmlinux.h"
+#undef bpf_iter_meta
+#undef bpf_iter__bpf_map
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct bpf_iter_meta {
+ struct seq_file *seq;
+ __u64 session_id;
+ __u64 seq_num;
+} __attribute__((preserve_access_index));
+
+struct bpf_iter__bpf_map {
+ struct bpf_iter_meta *meta;
+ struct bpf_map *map;
+} __attribute__((preserve_access_index));
+
+SEC("iter/bpf_map")
+int dump_bpf_map(struct bpf_iter__bpf_map *ctx)
+{
+ struct seq_file *seq = ctx->meta->seq;
+ __u64 seq_num = ctx->meta->seq_num;
+ struct bpf_map *map = ctx->map;
+
+ if (map == (void *)0) {
+ BPF_SEQ_PRINTF(seq, " %%%%%% END %%%%%%\n");
+ return 0;
+ }
+
+ if (seq_num == 0)
+ BPF_SEQ_PRINTF(seq, " id refcnt usercnt locked_vm\n");
+
+ BPF_SEQ_PRINTF(seq, "%8u %8ld %8ld %10lu\n", map->id, map->refcnt.counter,
+ map->usercnt.counter,
+ map->memory.user->locked_vm.counter);
+ return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_ipv6_route.c b/tools/testing/selftests/bpf/progs/bpf_iter_ipv6_route.c
new file mode 100644
index 000000000000..c8e9ca74c87b
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_ipv6_route.c
@@ -0,0 +1,78 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+/* "undefine" structs in vmlinux.h, because we "override" them below */
+#define bpf_iter_meta bpf_iter_meta___not_used
+#define bpf_iter__ipv6_route bpf_iter__ipv6_route___not_used
+#include "vmlinux.h"
+#undef bpf_iter_meta
+#undef bpf_iter__ipv6_route
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+struct bpf_iter_meta {
+ struct seq_file *seq;
+ __u64 session_id;
+ __u64 seq_num;
+} __attribute__((preserve_access_index));
+
+struct bpf_iter__ipv6_route {
+ struct bpf_iter_meta *meta;
+ struct fib6_info *rt;
+} __attribute__((preserve_access_index));
+
+char _license[] SEC("license") = "GPL";
+
+extern bool CONFIG_IPV6_SUBTREES __kconfig __weak;
+
+#define RTF_GATEWAY 0x0002
+#define IFNAMSIZ 16
+#define fib_nh_gw_family nh_common.nhc_gw_family
+#define fib_nh_gw6 nh_common.nhc_gw.ipv6
+#define fib_nh_dev nh_common.nhc_dev
+
+SEC("iter/ipv6_route")
+int dump_ipv6_route(struct bpf_iter__ipv6_route *ctx)
+{
+ struct seq_file *seq = ctx->meta->seq;
+ struct fib6_info *rt = ctx->rt;
+ const struct net_device *dev;
+ struct fib6_nh *fib6_nh;
+ unsigned int flags;
+ struct nexthop *nh;
+
+ if (rt == (void *)0)
+ return 0;
+
+ fib6_nh = &rt->fib6_nh[0];
+ flags = rt->fib6_flags;
+
+ /* FIXME: nexthop_is_multipath is not handled here. */
+ nh = rt->nh;
+ if (rt->nh)
+ fib6_nh = &nh->nh_info->fib6_nh;
+
+ BPF_SEQ_PRINTF(seq, "%pi6 %02x ", &rt->fib6_dst.addr, rt->fib6_dst.plen);
+
+ if (CONFIG_IPV6_SUBTREES)
+ BPF_SEQ_PRINTF(seq, "%pi6 %02x ", &rt->fib6_src.addr,
+ rt->fib6_src.plen);
+ else
+ BPF_SEQ_PRINTF(seq, "00000000000000000000000000000000 00 ");
+
+ if (fib6_nh->fib_nh_gw_family) {
+ flags |= RTF_GATEWAY;
+ BPF_SEQ_PRINTF(seq, "%pi6 ", &fib6_nh->fib_nh_gw6);
+ } else {
+ BPF_SEQ_PRINTF(seq, "00000000000000000000000000000000 ");
+ }
+
+ dev = fib6_nh->fib_nh_dev;
+ if (dev)
+ BPF_SEQ_PRINTF(seq, "%08x %08x %08x %08x %8s\n", rt->fib6_metric,
+ rt->fib6_ref.refs.counter, 0, flags, dev->name);
+ else
+ BPF_SEQ_PRINTF(seq, "%08x %08x %08x %08x\n", rt->fib6_metric,
+ rt->fib6_ref.refs.counter, 0, flags);
+
+ return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c b/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c
new file mode 100644
index 000000000000..e7b8753eac0b
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c
@@ -0,0 +1,82 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+/* "undefine" structs in vmlinux.h, because we "override" them below */
+#define bpf_iter_meta bpf_iter_meta___not_used
+#define bpf_iter__netlink bpf_iter__netlink___not_used
+#include "vmlinux.h"
+#undef bpf_iter_meta
+#undef bpf_iter__netlink
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+#define sk_rmem_alloc sk_backlog.rmem_alloc
+#define sk_refcnt __sk_common.skc_refcnt
+
+struct bpf_iter_meta {
+ struct seq_file *seq;
+ __u64 session_id;
+ __u64 seq_num;
+} __attribute__((preserve_access_index));
+
+struct bpf_iter__netlink {
+ struct bpf_iter_meta *meta;
+ struct netlink_sock *sk;
+} __attribute__((preserve_access_index));
+
+static inline struct inode *SOCK_INODE(struct socket *socket)
+{
+ return &container_of(socket, struct socket_alloc, socket)->vfs_inode;
+}
+
+SEC("iter/netlink")
+int dump_netlink(struct bpf_iter__netlink *ctx)
+{
+ struct seq_file *seq = ctx->meta->seq;
+ struct netlink_sock *nlk = ctx->sk;
+ unsigned long group, ino;
+ struct inode *inode;
+ struct socket *sk;
+ struct sock *s;
+
+ if (nlk == (void *)0)
+ return 0;
+
+ if (ctx->meta->seq_num == 0)
+ BPF_SEQ_PRINTF(seq, "sk Eth Pid Groups "
+ "Rmem Wmem Dump Locks Drops "
+ "Inode\n");
+
+ s = &nlk->sk;
+ BPF_SEQ_PRINTF(seq, "%pK %-3d ", s, s->sk_protocol);
+
+ if (!nlk->groups) {
+ group = 0;
+ } else {
+ /* FIXME: temporary use bpf_probe_read here, needs
+ * verifier support to do direct access.
+ */
+ bpf_probe_read(&group, sizeof(group), &nlk->groups[0]);
+ }
+ BPF_SEQ_PRINTF(seq, "%-10u %08x %-8d %-8d %-5d %-8d ",
+ nlk->portid, (u32)group,
+ s->sk_rmem_alloc.counter,
+ s->sk_wmem_alloc.refs.counter - 1,
+ nlk->cb_running, s->sk_refcnt.refs.counter);
+
+ sk = s->sk_socket;
+ if (!sk) {
+ ino = 0;
+ } else {
+ /* FIXME: container_of inside SOCK_INODE has a forced
+ * type conversion, and direct access cannot be used
+ * with current verifier.
+ */
+ inode = SOCK_INODE(sk);
+ bpf_probe_read(&ino, sizeof(ino), &inode->i_ino);
+ }
+ BPF_SEQ_PRINTF(seq, "%-8u %-8lu\n", s->sk_drops.counter, ino);
+
+ return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task.c b/tools/testing/selftests/bpf/progs/bpf_iter_task.c
new file mode 100644
index 000000000000..ee754021f98e
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_task.c
@@ -0,0 +1,41 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+/* "undefine" structs in vmlinux.h, because we "override" them below */
+#define bpf_iter_meta bpf_iter_meta___not_used
+#define bpf_iter__task bpf_iter__task___not_used
+#include "vmlinux.h"
+#undef bpf_iter_meta
+#undef bpf_iter__task
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct bpf_iter_meta {
+ struct seq_file *seq;
+ __u64 session_id;
+ __u64 seq_num;
+} __attribute__((preserve_access_index));
+
+struct bpf_iter__task {
+ struct bpf_iter_meta *meta;
+ struct task_struct *task;
+} __attribute__((preserve_access_index));
+
+SEC("iter/task")
+int dump_task(struct bpf_iter__task *ctx)
+{
+ struct seq_file *seq = ctx->meta->seq;
+ struct task_struct *task = ctx->task;
+
+ if (task == (void *)0) {
+ BPF_SEQ_PRINTF(seq, " === END ===\n");
+ return 0;
+ }
+
+ if (ctx->meta->seq_num == 0)
+ BPF_SEQ_PRINTF(seq, " tgid gid\n");
+
+ BPF_SEQ_PRINTF(seq, "%8d %8d\n", task->tgid, task->pid);
+ return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task_file.c b/tools/testing/selftests/bpf/progs/bpf_iter_task_file.c
new file mode 100644
index 000000000000..0f0ec3db20ba
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_task_file.c
@@ -0,0 +1,44 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+/* "undefine" structs in vmlinux.h, because we "override" them below */
+#define bpf_iter_meta bpf_iter_meta___not_used
+#define bpf_iter__task_file bpf_iter__task_file___not_used
+#include "vmlinux.h"
+#undef bpf_iter_meta
+#undef bpf_iter__task_file
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct bpf_iter_meta {
+ struct seq_file *seq;
+ __u64 session_id;
+ __u64 seq_num;
+} __attribute__((preserve_access_index));
+
+struct bpf_iter__task_file {
+ struct bpf_iter_meta *meta;
+ struct task_struct *task;
+ __u32 fd;
+ struct file *file;
+} __attribute__((preserve_access_index));
+
+SEC("iter/task_file")
+int dump_task_file(struct bpf_iter__task_file *ctx)
+{
+ struct seq_file *seq = ctx->meta->seq;
+ struct task_struct *task = ctx->task;
+ __u32 fd = ctx->fd;
+ struct file *file = ctx->file;
+
+ if (task == (void *)0 || file == (void *)0)
+ return 0;
+
+ if (ctx->meta->seq_num == 0)
+ BPF_SEQ_PRINTF(seq, " tgid gid fd file\n");
+
+ BPF_SEQ_PRINTF(seq, "%8d %8d %8d %lx\n", task->tgid, task->pid, fd,
+ (long)file->f_op);
+ return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern1.c b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern1.c
new file mode 100644
index 000000000000..c71a7c283108
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern1.c
@@ -0,0 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#define START_CHAR 'a'
+#include "bpf_iter_test_kern_common.h"
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern2.c b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern2.c
new file mode 100644
index 000000000000..8bdc8dc07444
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern2.c
@@ -0,0 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#define START_CHAR 'A'
+#include "bpf_iter_test_kern_common.h"
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern3.c b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern3.c
new file mode 100644
index 000000000000..13c2c90c835f
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern3.c
@@ -0,0 +1,33 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#define bpf_iter_meta bpf_iter_meta___not_used
+#define bpf_iter__task bpf_iter__task___not_used
+#include "vmlinux.h"
+#undef bpf_iter_meta
+#undef bpf_iter__task
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct bpf_iter_meta {
+ struct seq_file *seq;
+ __u64 session_id;
+ __u64 seq_num;
+} __attribute__((preserve_access_index));
+
+struct bpf_iter__task {
+ struct bpf_iter_meta *meta;
+ struct task_struct *task;
+} __attribute__((preserve_access_index));
+
+SEC("iter/task")
+int dump_task(struct bpf_iter__task *ctx)
+{
+ struct seq_file *seq = ctx->meta->seq;
+ struct task_struct *task = ctx->task;
+ int tgid;
+
+ tgid = task->tgid;
+ bpf_seq_write(seq, &tgid, sizeof(tgid));
+ return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern4.c b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern4.c
new file mode 100644
index 000000000000..0aa71b333cf3
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern4.c
@@ -0,0 +1,67 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#define bpf_iter_meta bpf_iter_meta___not_used
+#define bpf_iter__bpf_map bpf_iter__bpf_map___not_used
+#include "vmlinux.h"
+#undef bpf_iter_meta
+#undef bpf_iter__bpf_map
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct bpf_iter_meta {
+ struct seq_file *seq;
+ __u64 session_id;
+ __u64 seq_num;
+} __attribute__((preserve_access_index));
+
+struct bpf_iter__bpf_map {
+ struct bpf_iter_meta *meta;
+ struct bpf_map *map;
+} __attribute__((preserve_access_index));
+
+__u32 map1_id = 0, map2_id = 0;
+__u32 map1_accessed = 0, map2_accessed = 0;
+__u64 map1_seqnum = 0, map2_seqnum1 = 0, map2_seqnum2 = 0;
+
+static volatile const __u32 print_len;
+static volatile const __u32 ret1;
+
+SEC("iter/bpf_map")
+int dump_bpf_map(struct bpf_iter__bpf_map *ctx)
+{
+ struct seq_file *seq = ctx->meta->seq;
+ struct bpf_map *map = ctx->map;
+ __u64 seq_num;
+ int i, ret = 0;
+
+ if (map == (void *)0)
+ return 0;
+
+ /* only dump map1_id and map2_id */
+ if (map->id != map1_id && map->id != map2_id)
+ return 0;
+
+ seq_num = ctx->meta->seq_num;
+ if (map->id == map1_id) {
+ map1_seqnum = seq_num;
+ map1_accessed++;
+ }
+
+ if (map->id == map2_id) {
+ if (map2_accessed == 0) {
+ map2_seqnum1 = seq_num;
+ if (ret1)
+ ret = 1;
+ } else {
+ map2_seqnum2 = seq_num;
+ }
+ map2_accessed++;
+ }
+
+ /* fill seq_file buffer */
+ for (i = 0; i < print_len; i++)
+ bpf_seq_write(seq, &seq_num, sizeof(seq_num));
+
+ return ret;
+}
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern_common.h b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern_common.h
new file mode 100644
index 000000000000..dee1339e6905
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern_common.h
@@ -0,0 +1,38 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2020 Facebook */
+/* "undefine" structs in vmlinux.h, because we "override" them below */
+#define bpf_iter_meta bpf_iter_meta___not_used
+#define bpf_iter__task bpf_iter__task___not_used
+#include "vmlinux.h"
+#undef bpf_iter_meta
+#undef bpf_iter__task
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+int count = 0;
+
+struct bpf_iter_meta {
+ struct seq_file *seq;
+ __u64 session_id;
+ __u64 seq_num;
+} __attribute__((preserve_access_index));
+
+struct bpf_iter__task {
+ struct bpf_iter_meta *meta;
+ struct task_struct *task;
+} __attribute__((preserve_access_index));
+
+SEC("iter/task")
+int dump_task(struct bpf_iter__task *ctx)
+{
+ struct seq_file *seq = ctx->meta->seq;
+ char c;
+
+ if (count < 4) {
+ c = START_CHAR + count;
+ bpf_seq_write(seq, &c, sizeof(c));
+ count++;
+ }
+
+ return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c
index d4a02fe44a12..31975c96e2c9 100644
--- a/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c
+++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c
@@ -13,7 +13,7 @@ enum e1 {
enum e2 {
C = 100,
- D = -100,
+ D = 4294967295,
E = 0,
};
diff --git a/tools/testing/selftests/bpf/progs/cgroup_skb_sk_lookup_kern.c b/tools/testing/selftests/bpf/progs/cgroup_skb_sk_lookup_kern.c
new file mode 100644
index 000000000000..3f757e30d7a0
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/cgroup_skb_sk_lookup_kern.c
@@ -0,0 +1,97 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2020 Facebook
+
+#include <linux/bpf.h>
+#include <bpf/bpf_endian.h>
+#include <bpf/bpf_helpers.h>
+
+#include <linux/if_ether.h>
+#include <linux/in.h>
+#include <linux/in6.h>
+#include <linux/ipv6.h>
+#include <linux/tcp.h>
+
+#include <sys/types.h>
+#include <sys/socket.h>
+
+int _version SEC("version") = 1;
+char _license[] SEC("license") = "GPL";
+
+__u16 g_serv_port = 0;
+
+static inline void set_ip(__u32 *dst, const struct in6_addr *src)
+{
+ dst[0] = src->in6_u.u6_addr32[0];
+ dst[1] = src->in6_u.u6_addr32[1];
+ dst[2] = src->in6_u.u6_addr32[2];
+ dst[3] = src->in6_u.u6_addr32[3];
+}
+
+static inline void set_tuple(struct bpf_sock_tuple *tuple,
+ const struct ipv6hdr *ip6h,
+ const struct tcphdr *tcph)
+{
+ set_ip(tuple->ipv6.saddr, &ip6h->daddr);
+ set_ip(tuple->ipv6.daddr, &ip6h->saddr);
+ tuple->ipv6.sport = tcph->dest;
+ tuple->ipv6.dport = tcph->source;
+}
+
+static inline int is_allowed_peer_cg(struct __sk_buff *skb,
+ const struct ipv6hdr *ip6h,
+ const struct tcphdr *tcph)
+{
+ __u64 cgid, acgid, peer_cgid, peer_acgid;
+ struct bpf_sock_tuple tuple;
+ size_t tuple_len = sizeof(tuple.ipv6);
+ struct bpf_sock *peer_sk;
+
+ set_tuple(&tuple, ip6h, tcph);
+
+ peer_sk = bpf_sk_lookup_tcp(skb, &tuple, tuple_len,
+ BPF_F_CURRENT_NETNS, 0);
+ if (!peer_sk)
+ return 0;
+
+ cgid = bpf_skb_cgroup_id(skb);
+ peer_cgid = bpf_sk_cgroup_id(peer_sk);
+
+ acgid = bpf_skb_ancestor_cgroup_id(skb, 2);
+ peer_acgid = bpf_sk_ancestor_cgroup_id(peer_sk, 2);
+
+ bpf_sk_release(peer_sk);
+
+ return cgid && cgid == peer_cgid && acgid && acgid == peer_acgid;
+}
+
+SEC("cgroup_skb/ingress")
+int ingress_lookup(struct __sk_buff *skb)
+{
+ __u32 serv_port_key = 0;
+ struct ipv6hdr ip6h;
+ struct tcphdr tcph;
+
+ if (skb->protocol != bpf_htons(ETH_P_IPV6))
+ return 1;
+
+ /* For SYN packets coming to listening socket skb->remote_port will be
+ * zero, so IPv6/TCP headers are loaded to identify remote peer
+ * instead.
+ */
+ if (bpf_skb_load_bytes(skb, 0, &ip6h, sizeof(ip6h)))
+ return 1;
+
+ if (ip6h.nexthdr != IPPROTO_TCP)
+ return 1;
+
+ if (bpf_skb_load_bytes(skb, sizeof(ip6h), &tcph, sizeof(tcph)))
+ return 1;
+
+ if (!g_serv_port)
+ return 0;
+
+ if (tcph.dest != g_serv_port)
+ return 1;
+
+ return is_allowed_peer_cg(skb, &ip6h, &tcph);
+}
diff --git a/tools/testing/selftests/bpf/progs/connect4_prog.c b/tools/testing/selftests/bpf/progs/connect4_prog.c
index 75085119c5bb..1ab2c5eba86c 100644
--- a/tools/testing/selftests/bpf/progs/connect4_prog.c
+++ b/tools/testing/selftests/bpf/progs/connect4_prog.c
@@ -8,6 +8,9 @@
#include <linux/in.h>
#include <linux/in6.h>
#include <sys/socket.h>
+#include <netinet/tcp.h>
+#include <linux/if.h>
+#include <errno.h>
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_endian.h>
@@ -16,13 +19,95 @@
#define DST_REWRITE_IP4 0x7f000001U
#define DST_REWRITE_PORT4 4444
+#ifndef TCP_CA_NAME_MAX
+#define TCP_CA_NAME_MAX 16
+#endif
+
+#ifndef IFNAMSIZ
+#define IFNAMSIZ 16
+#endif
+
int _version SEC("version") = 1;
+__attribute__ ((noinline))
+int do_bind(struct bpf_sock_addr *ctx)
+{
+ struct sockaddr_in sa = {};
+
+ sa.sin_family = AF_INET;
+ sa.sin_port = bpf_htons(0);
+ sa.sin_addr.s_addr = bpf_htonl(SRC_REWRITE_IP4);
+
+ if (bpf_bind(ctx, (struct sockaddr *)&sa, sizeof(sa)) != 0)
+ return 0;
+
+ return 1;
+}
+
+static __inline int verify_cc(struct bpf_sock_addr *ctx,
+ char expected[TCP_CA_NAME_MAX])
+{
+ char buf[TCP_CA_NAME_MAX];
+ int i;
+
+ if (bpf_getsockopt(ctx, SOL_TCP, TCP_CONGESTION, &buf, sizeof(buf)))
+ return 1;
+
+ for (i = 0; i < TCP_CA_NAME_MAX; i++) {
+ if (buf[i] != expected[i])
+ return 1;
+ if (buf[i] == 0)
+ break;
+ }
+
+ return 0;
+}
+
+static __inline int set_cc(struct bpf_sock_addr *ctx)
+{
+ char reno[TCP_CA_NAME_MAX] = "reno";
+ char cubic[TCP_CA_NAME_MAX] = "cubic";
+
+ if (bpf_setsockopt(ctx, SOL_TCP, TCP_CONGESTION, &reno, sizeof(reno)))
+ return 1;
+ if (verify_cc(ctx, reno))
+ return 1;
+
+ if (bpf_setsockopt(ctx, SOL_TCP, TCP_CONGESTION, &cubic, sizeof(cubic)))
+ return 1;
+ if (verify_cc(ctx, cubic))
+ return 1;
+
+ return 0;
+}
+
+static __inline int bind_to_device(struct bpf_sock_addr *ctx)
+{
+ char veth1[IFNAMSIZ] = "test_sock_addr1";
+ char veth2[IFNAMSIZ] = "test_sock_addr2";
+ char missing[IFNAMSIZ] = "nonexistent_dev";
+ char del_bind[IFNAMSIZ] = "";
+
+ if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE,
+ &veth1, sizeof(veth1)))
+ return 1;
+ if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE,
+ &veth2, sizeof(veth2)))
+ return 1;
+ if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE,
+ &missing, sizeof(missing)) != -ENODEV)
+ return 1;
+ if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE,
+ &del_bind, sizeof(del_bind)))
+ return 1;
+
+ return 0;
+}
+
SEC("cgroup/connect4")
int connect_v4_prog(struct bpf_sock_addr *ctx)
{
struct bpf_sock_tuple tuple = {};
- struct sockaddr_in sa;
struct bpf_sock *sk;
/* Verify that new destination is available. */
@@ -32,6 +117,10 @@ int connect_v4_prog(struct bpf_sock_addr *ctx)
tuple.ipv4.daddr = bpf_htonl(DST_REWRITE_IP4);
tuple.ipv4.dport = bpf_htons(DST_REWRITE_PORT4);
+ /* Bind to device and unbind it. */
+ if (bind_to_device(ctx))
+ return 0;
+
if (ctx->type != SOCK_STREAM && ctx->type != SOCK_DGRAM)
return 0;
else if (ctx->type == SOCK_STREAM)
@@ -52,21 +141,15 @@ int connect_v4_prog(struct bpf_sock_addr *ctx)
bpf_sk_release(sk);
+ /* Rewrite congestion control. */
+ if (ctx->type == SOCK_STREAM && set_cc(ctx))
+ return 0;
+
/* Rewrite destination. */
ctx->user_ip4 = bpf_htonl(DST_REWRITE_IP4);
ctx->user_port = bpf_htons(DST_REWRITE_PORT4);
- /* Rewrite source. */
- memset(&sa, 0, sizeof(sa));
-
- sa.sin_family = AF_INET;
- sa.sin_port = bpf_htons(0);
- sa.sin_addr.s_addr = bpf_htonl(SRC_REWRITE_IP4);
-
- if (bpf_bind(ctx, (struct sockaddr *)&sa, sizeof(sa)) != 0)
- return 0;
-
- return 1;
+ return do_bind(ctx) ? 1 : 0;
}
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/connect_force_port4.c b/tools/testing/selftests/bpf/progs/connect_force_port4.c
new file mode 100644
index 000000000000..7396308677a3
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/connect_force_port4.c
@@ -0,0 +1,83 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <string.h>
+#include <stdbool.h>
+
+#include <linux/bpf.h>
+#include <linux/in.h>
+#include <linux/in6.h>
+#include <sys/socket.h>
+
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+char _license[] SEC("license") = "GPL";
+int _version SEC("version") = 1;
+
+struct svc_addr {
+ __be32 addr;
+ __be16 port;
+};
+
+struct {
+ __uint(type, BPF_MAP_TYPE_SK_STORAGE);
+ __uint(map_flags, BPF_F_NO_PREALLOC);
+ __type(key, int);
+ __type(value, struct svc_addr);
+} service_mapping SEC(".maps");
+
+SEC("cgroup/connect4")
+int connect4(struct bpf_sock_addr *ctx)
+{
+ struct sockaddr_in sa = {};
+ struct svc_addr *orig;
+
+ /* Force local address to 127.0.0.1:22222. */
+ sa.sin_family = AF_INET;
+ sa.sin_port = bpf_htons(22222);
+ sa.sin_addr.s_addr = bpf_htonl(0x7f000001);
+
+ if (bpf_bind(ctx, (struct sockaddr *)&sa, sizeof(sa)) != 0)
+ return 0;
+
+ /* Rewire service 1.2.3.4:60000 to backend 127.0.0.1:60123. */
+ if (ctx->user_port == bpf_htons(60000)) {
+ orig = bpf_sk_storage_get(&service_mapping, ctx->sk, 0,
+ BPF_SK_STORAGE_GET_F_CREATE);
+ if (!orig)
+ return 0;
+
+ orig->addr = ctx->user_ip4;
+ orig->port = ctx->user_port;
+
+ ctx->user_ip4 = bpf_htonl(0x7f000001);
+ ctx->user_port = bpf_htons(60123);
+ }
+ return 1;
+}
+
+SEC("cgroup/getsockname4")
+int getsockname4(struct bpf_sock_addr *ctx)
+{
+ /* Expose local server as 1.2.3.4:60000 to client. */
+ if (ctx->user_port == bpf_htons(60123)) {
+ ctx->user_ip4 = bpf_htonl(0x01020304);
+ ctx->user_port = bpf_htons(60000);
+ }
+ return 1;
+}
+
+SEC("cgroup/getpeername4")
+int getpeername4(struct bpf_sock_addr *ctx)
+{
+ struct svc_addr *orig;
+
+ /* Expose service 1.2.3.4:60000 as peer instead of backend. */
+ if (ctx->user_port == bpf_htons(60123)) {
+ orig = bpf_sk_storage_get(&service_mapping, ctx->sk, 0, 0);
+ if (orig) {
+ ctx->user_ip4 = orig->addr;
+ ctx->user_port = orig->port;
+ }
+ }
+ return 1;
+}
diff --git a/tools/testing/selftests/bpf/progs/connect_force_port6.c b/tools/testing/selftests/bpf/progs/connect_force_port6.c
new file mode 100644
index 000000000000..c1a2b555e9ad
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/connect_force_port6.c
@@ -0,0 +1,94 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <string.h>
+
+#include <linux/bpf.h>
+#include <linux/in.h>
+#include <linux/in6.h>
+#include <sys/socket.h>
+
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+char _license[] SEC("license") = "GPL";
+int _version SEC("version") = 1;
+
+struct svc_addr {
+ __be32 addr[4];
+ __be16 port;
+};
+
+struct {
+ __uint(type, BPF_MAP_TYPE_SK_STORAGE);
+ __uint(map_flags, BPF_F_NO_PREALLOC);
+ __type(key, int);
+ __type(value, struct svc_addr);
+} service_mapping SEC(".maps");
+
+SEC("cgroup/connect6")
+int connect6(struct bpf_sock_addr *ctx)
+{
+ struct sockaddr_in6 sa = {};
+ struct svc_addr *orig;
+
+ /* Force local address to [::1]:22223. */
+ sa.sin6_family = AF_INET6;
+ sa.sin6_port = bpf_htons(22223);
+ sa.sin6_addr.s6_addr32[3] = bpf_htonl(1);
+
+ if (bpf_bind(ctx, (struct sockaddr *)&sa, sizeof(sa)) != 0)
+ return 0;
+
+ /* Rewire service [fc00::1]:60000 to backend [::1]:60124. */
+ if (ctx->user_port == bpf_htons(60000)) {
+ orig = bpf_sk_storage_get(&service_mapping, ctx->sk, 0,
+ BPF_SK_STORAGE_GET_F_CREATE);
+ if (!orig)
+ return 0;
+
+ orig->addr[0] = ctx->user_ip6[0];
+ orig->addr[1] = ctx->user_ip6[1];
+ orig->addr[2] = ctx->user_ip6[2];
+ orig->addr[3] = ctx->user_ip6[3];
+ orig->port = ctx->user_port;
+
+ ctx->user_ip6[0] = 0;
+ ctx->user_ip6[1] = 0;
+ ctx->user_ip6[2] = 0;
+ ctx->user_ip6[3] = bpf_htonl(1);
+ ctx->user_port = bpf_htons(60124);
+ }
+ return 1;
+}
+
+SEC("cgroup/getsockname6")
+int getsockname6(struct bpf_sock_addr *ctx)
+{
+ /* Expose local server as [fc00::1]:60000 to client. */
+ if (ctx->user_port == bpf_htons(60124)) {
+ ctx->user_ip6[0] = bpf_htonl(0xfc000000);
+ ctx->user_ip6[1] = 0;
+ ctx->user_ip6[2] = 0;
+ ctx->user_ip6[3] = bpf_htonl(1);
+ ctx->user_port = bpf_htons(60000);
+ }
+ return 1;
+}
+
+SEC("cgroup/getpeername6")
+int getpeername6(struct bpf_sock_addr *ctx)
+{
+ struct svc_addr *orig;
+
+ /* Expose service [fc00::1]:60000 as peer instead of backend. */
+ if (ctx->user_port == bpf_htons(60124)) {
+ orig = bpf_sk_storage_get(&service_mapping, ctx->sk, 0, 0);
+ if (orig) {
+ ctx->user_ip6[0] = orig->addr[0];
+ ctx->user_ip6[1] = orig->addr[1];
+ ctx->user_ip6[2] = orig->addr[2];
+ ctx->user_ip6[3] = orig->addr[3];
+ ctx->user_port = orig->port;
+ }
+ }
+ return 1;
+}
diff --git a/tools/testing/selftests/bpf/progs/core_reloc_types.h b/tools/testing/selftests/bpf/progs/core_reloc_types.h
index 6d598cfbdb3e..34d84717c946 100644
--- a/tools/testing/selftests/bpf/progs/core_reloc_types.h
+++ b/tools/testing/selftests/bpf/progs/core_reloc_types.h
@@ -379,7 +379,7 @@ struct core_reloc_arrays___equiv_zero_sz_arr {
struct core_reloc_arrays_substruct c[3];
struct core_reloc_arrays_substruct d[1][2];
/* equivalent to flexible array */
- struct core_reloc_arrays_substruct f[0][2];
+ struct core_reloc_arrays_substruct f[][2];
};
struct core_reloc_arrays___fixed_arr {
diff --git a/tools/testing/selftests/bpf/progs/fentry_test.c b/tools/testing/selftests/bpf/progs/fentry_test.c
index 38d3a82144ca..9365b686f84b 100644
--- a/tools/testing/selftests/bpf/progs/fentry_test.c
+++ b/tools/testing/selftests/bpf/progs/fentry_test.c
@@ -2,7 +2,7 @@
/* Copyright (c) 2019 Facebook */
#include <linux/bpf.h>
#include <bpf/bpf_helpers.h>
-#include "bpf_trace_helpers.h"
+#include <bpf/bpf_tracing.h>
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c b/tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c
index c329fccf9842..98e1efe14549 100644
--- a/tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c
+++ b/tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c
@@ -5,7 +5,7 @@
#include <linux/bpf.h>
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_endian.h>
-#include "bpf_trace_helpers.h"
+#include <bpf/bpf_tracing.h>
struct sk_buff {
unsigned int len;
diff --git a/tools/testing/selftests/bpf/progs/fexit_bpf2bpf_simple.c b/tools/testing/selftests/bpf/progs/fexit_bpf2bpf_simple.c
index 92f3fa47cf40..85c0b516d6ee 100644
--- a/tools/testing/selftests/bpf/progs/fexit_bpf2bpf_simple.c
+++ b/tools/testing/selftests/bpf/progs/fexit_bpf2bpf_simple.c
@@ -2,7 +2,7 @@
/* Copyright (c) 2019 Facebook */
#include <linux/bpf.h>
#include <bpf/bpf_helpers.h>
-#include "bpf_trace_helpers.h"
+#include <bpf/bpf_tracing.h>
struct sk_buff {
unsigned int len;
diff --git a/tools/testing/selftests/bpf/progs/fexit_test.c b/tools/testing/selftests/bpf/progs/fexit_test.c
index 348109b9ea07..bd1e17d8024c 100644
--- a/tools/testing/selftests/bpf/progs/fexit_test.c
+++ b/tools/testing/selftests/bpf/progs/fexit_test.c
@@ -2,7 +2,7 @@
/* Copyright (c) 2019 Facebook */
#include <linux/bpf.h>
#include <bpf/bpf_helpers.h>
-#include "bpf_trace_helpers.h"
+#include <bpf/bpf_tracing.h>
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/freplace_connect4.c b/tools/testing/selftests/bpf/progs/freplace_connect4.c
new file mode 100644
index 000000000000..a0ae84230699
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/freplace_connect4.c
@@ -0,0 +1,18 @@
+#include <linux/stddef.h>
+#include <linux/ipv6.h>
+#include <linux/bpf.h>
+#include <linux/in.h>
+#include <sys/socket.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+SEC("freplace/do_bind")
+int new_do_bind(struct bpf_sock_addr *ctx)
+{
+ struct sockaddr_in sa = {};
+
+ bpf_bind(ctx, (struct sockaddr *)&sa, sizeof(sa));
+ return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/kfree_skb.c b/tools/testing/selftests/bpf/progs/kfree_skb.c
index 8f48a909f079..a46a264ce24e 100644
--- a/tools/testing/selftests/bpf/progs/kfree_skb.c
+++ b/tools/testing/selftests/bpf/progs/kfree_skb.c
@@ -4,7 +4,7 @@
#include <stdbool.h>
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_endian.h>
-#include "bpf_trace_helpers.h"
+#include <bpf/bpf_tracing.h>
char _license[] SEC("license") = "GPL";
struct {
diff --git a/tools/testing/selftests/bpf/progs/lsm.c b/tools/testing/selftests/bpf/progs/lsm.c
new file mode 100644
index 000000000000..b4598d4bc4f7
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/lsm.c
@@ -0,0 +1,48 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright 2020 Google LLC.
+ */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <errno.h>
+
+char _license[] SEC("license") = "GPL";
+
+int monitored_pid = 0;
+int mprotect_count = 0;
+int bprm_count = 0;
+
+SEC("lsm/file_mprotect")
+int BPF_PROG(test_int_hook, struct vm_area_struct *vma,
+ unsigned long reqprot, unsigned long prot, int ret)
+{
+ if (ret != 0)
+ return ret;
+
+ __u32 pid = bpf_get_current_pid_tgid() >> 32;
+ int is_stack = 0;
+
+ is_stack = (vma->vm_start <= vma->vm_mm->start_stack &&
+ vma->vm_end >= vma->vm_mm->start_stack);
+
+ if (is_stack && monitored_pid == pid) {
+ mprotect_count++;
+ ret = -EPERM;
+ }
+
+ return ret;
+}
+
+SEC("lsm/bprm_committed_creds")
+int BPF_PROG(test_void_hook, struct linux_binprm *bprm)
+{
+ __u32 pid = bpf_get_current_pid_tgid() >> 32;
+
+ if (monitored_pid == pid)
+ bprm_count++;
+
+ return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/modify_return.c b/tools/testing/selftests/bpf/progs/modify_return.c
new file mode 100644
index 000000000000..8b7466a15c6b
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/modify_return.c
@@ -0,0 +1,49 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright 2020 Google LLC.
+ */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+static int sequence = 0;
+__s32 input_retval = 0;
+
+__u64 fentry_result = 0;
+SEC("fentry/bpf_modify_return_test")
+int BPF_PROG(fentry_test, int a, __u64 b)
+{
+ sequence++;
+ fentry_result = (sequence == 1);
+ return 0;
+}
+
+__u64 fmod_ret_result = 0;
+SEC("fmod_ret/bpf_modify_return_test")
+int BPF_PROG(fmod_ret_test, int a, int *b, int ret)
+{
+ sequence++;
+ /* This is the first fmod_ret program, the ret passed should be 0 */
+ fmod_ret_result = (sequence == 2 && ret == 0);
+ return input_retval;
+}
+
+__u64 fexit_result = 0;
+SEC("fexit/bpf_modify_return_test")
+int BPF_PROG(fexit_test, int a, __u64 b, int ret)
+{
+ sequence++;
+ /* If the input_reval is non-zero a successful modification should have
+ * occurred.
+ */
+ if (input_retval)
+ fexit_result = (sequence == 3 && ret == input_retval);
+ else
+ fexit_result = (sequence == 3 && ret == 4);
+
+ return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/perfbuf_bench.c b/tools/testing/selftests/bpf/progs/perfbuf_bench.c
new file mode 100644
index 000000000000..e5ab4836a641
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/perfbuf_bench.c
@@ -0,0 +1,33 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2020 Facebook
+
+#include <linux/bpf.h>
+#include <stdint.h>
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct {
+ __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
+ __uint(value_size, sizeof(int));
+ __uint(key_size, sizeof(int));
+} perfbuf SEC(".maps");
+
+const volatile int batch_cnt = 0;
+
+long sample_val = 42;
+long dropped __attribute__((aligned(128))) = 0;
+
+SEC("fentry/__x64_sys_getpgid")
+int bench_perfbuf(void *ctx)
+{
+ __u64 *sample;
+ int i;
+
+ for (i = 0; i < batch_cnt; i++) {
+ if (bpf_perf_event_output(ctx, &perfbuf, BPF_F_CURRENT_CPU,
+ &sample_val, sizeof(sample_val)))
+ __sync_add_and_fetch(&dropped, 1);
+ }
+ return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/ringbuf_bench.c b/tools/testing/selftests/bpf/progs/ringbuf_bench.c
new file mode 100644
index 000000000000..123607d314d6
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/ringbuf_bench.c
@@ -0,0 +1,60 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2020 Facebook
+
+#include <linux/bpf.h>
+#include <stdint.h>
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct {
+ __uint(type, BPF_MAP_TYPE_RINGBUF);
+} ringbuf SEC(".maps");
+
+const volatile int batch_cnt = 0;
+const volatile long use_output = 0;
+
+long sample_val = 42;
+long dropped __attribute__((aligned(128))) = 0;
+
+const volatile long wakeup_data_size = 0;
+
+static __always_inline long get_flags()
+{
+ long sz;
+
+ if (!wakeup_data_size)
+ return 0;
+
+ sz = bpf_ringbuf_query(&ringbuf, BPF_RB_AVAIL_DATA);
+ return sz >= wakeup_data_size ? BPF_RB_FORCE_WAKEUP : BPF_RB_NO_WAKEUP;
+}
+
+SEC("fentry/__x64_sys_getpgid")
+int bench_ringbuf(void *ctx)
+{
+ long *sample, flags;
+ int i;
+
+ if (!use_output) {
+ for (i = 0; i < batch_cnt; i++) {
+ sample = bpf_ringbuf_reserve(&ringbuf,
+ sizeof(sample_val), 0);
+ if (!sample) {
+ __sync_add_and_fetch(&dropped, 1);
+ } else {
+ *sample = sample_val;
+ flags = get_flags();
+ bpf_ringbuf_submit(sample, flags);
+ }
+ }
+ } else {
+ for (i = 0; i < batch_cnt; i++) {
+ flags = get_flags();
+ if (bpf_ringbuf_output(&ringbuf, &sample_val,
+ sizeof(sample_val), flags))
+ __sync_add_and_fetch(&dropped, 1);
+ }
+ }
+ return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c b/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c
index a5c6d5903b22..ca283af80d4e 100644
--- a/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c
+++ b/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c
@@ -12,7 +12,6 @@ int bpf_prog1(struct __sk_buff *skb)
__u32 lport = skb->local_port;
__u32 rport = skb->remote_port;
__u8 *d = data;
- __u32 len = (__u32) data_end - (__u32) data;
int err;
if (data + 10 > data_end) {
diff --git a/tools/testing/selftests/bpf/progs/test_attach_probe.c b/tools/testing/selftests/bpf/progs/test_attach_probe.c
index dd8fae6660ab..8056a4c6d918 100644
--- a/tools/testing/selftests/bpf/progs/test_attach_probe.c
+++ b/tools/testing/selftests/bpf/progs/test_attach_probe.c
@@ -4,6 +4,7 @@
#include <linux/ptrace.h>
#include <linux/bpf.h>
#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
int kprobe_res = 0;
int kretprobe_res = 0;
@@ -18,7 +19,7 @@ int handle_kprobe(struct pt_regs *ctx)
}
SEC("kretprobe/sys_nanosleep")
-int handle_kretprobe(struct pt_regs *ctx)
+int BPF_KRETPROBE(handle_kretprobe)
{
kretprobe_res = 2;
return 0;
diff --git a/tools/testing/selftests/bpf/progs/test_btf_haskv.c b/tools/testing/selftests/bpf/progs/test_btf_haskv.c
index 88b0566da13d..31538c9ed193 100644
--- a/tools/testing/selftests/bpf/progs/test_btf_haskv.c
+++ b/tools/testing/selftests/bpf/progs/test_btf_haskv.c
@@ -20,20 +20,12 @@ struct bpf_map_def SEC("maps") btf_map = {
BPF_ANNOTATE_KV_PAIR(btf_map, int, struct ipv_counts);
-struct dummy_tracepoint_args {
- unsigned long long pad;
- struct sock *sock;
-};
-
__attribute__((noinline))
-int test_long_fname_2(struct dummy_tracepoint_args *arg)
+int test_long_fname_2(void)
{
struct ipv_counts *counts;
int key = 0;
- if (!arg->sock)
- return 0;
-
counts = bpf_map_lookup_elem(&btf_map, &key);
if (!counts)
return 0;
@@ -44,15 +36,15 @@ int test_long_fname_2(struct dummy_tracepoint_args *arg)
}
__attribute__((noinline))
-int test_long_fname_1(struct dummy_tracepoint_args *arg)
+int test_long_fname_1(void)
{
- return test_long_fname_2(arg);
+ return test_long_fname_2();
}
SEC("dummy_tracepoint")
-int _dummy_tracepoint(struct dummy_tracepoint_args *arg)
+int _dummy_tracepoint(void *arg)
{
- return test_long_fname_1(arg);
+ return test_long_fname_1();
}
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_btf_map_in_map.c b/tools/testing/selftests/bpf/progs/test_btf_map_in_map.c
new file mode 100644
index 000000000000..e5093796be97
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_btf_map_in_map.c
@@ -0,0 +1,76 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2020 Facebook */
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+struct inner_map {
+ __uint(type, BPF_MAP_TYPE_ARRAY);
+ __uint(max_entries, 1);
+ __type(key, int);
+ __type(value, int);
+} inner_map1 SEC(".maps"),
+ inner_map2 SEC(".maps");
+
+struct outer_arr {
+ __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS);
+ __uint(max_entries, 3);
+ __uint(key_size, sizeof(int));
+ __uint(value_size, sizeof(int));
+ /* it's possible to use anonymous struct as inner map definition here */
+ __array(values, struct {
+ __uint(type, BPF_MAP_TYPE_ARRAY);
+ /* changing max_entries to 2 will fail during load
+ * due to incompatibility with inner_map definition */
+ __uint(max_entries, 1);
+ __type(key, int);
+ __type(value, int);
+ });
+} outer_arr SEC(".maps") = {
+ /* (void *) cast is necessary because we didn't use `struct inner_map`
+ * in __inner(values, ...)
+ * Actually, a conscious effort is required to screw up initialization
+ * of inner map slots, which is a great thing!
+ */
+ .values = { (void *)&inner_map1, 0, (void *)&inner_map2 },
+};
+
+struct outer_hash {
+ __uint(type, BPF_MAP_TYPE_HASH_OF_MAPS);
+ __uint(max_entries, 5);
+ __uint(key_size, sizeof(int));
+ /* Here everything works flawlessly due to reuse of struct inner_map
+ * and compiler will complain at the attempt to use non-inner_map
+ * references below. This is great experience.
+ */
+ __array(values, struct inner_map);
+} outer_hash SEC(".maps") = {
+ .values = {
+ [0] = &inner_map2,
+ [4] = &inner_map1,
+ },
+};
+
+int input = 0;
+
+SEC("raw_tp/sys_enter")
+int handle__sys_enter(void *ctx)
+{
+ struct inner_map *inner_map;
+ int key = 0, val;
+
+ inner_map = bpf_map_lookup_elem(&outer_arr, &key);
+ if (!inner_map)
+ return 1;
+ val = input;
+ bpf_map_update_elem(inner_map, &key, &val, 0);
+
+ inner_map = bpf_map_lookup_elem(&outer_hash, &key);
+ if (!inner_map)
+ return 1;
+ val = input + 1;
+ bpf_map_update_elem(inner_map, &key, &val, 0);
+
+ return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_btf_newkv.c b/tools/testing/selftests/bpf/progs/test_btf_newkv.c
index a924e53c8e9d..6c5560162746 100644
--- a/tools/testing/selftests/bpf/progs/test_btf_newkv.c
+++ b/tools/testing/selftests/bpf/progs/test_btf_newkv.c
@@ -28,20 +28,12 @@ struct {
__type(value, struct ipv_counts);
} btf_map SEC(".maps");
-struct dummy_tracepoint_args {
- unsigned long long pad;
- struct sock *sock;
-};
-
__attribute__((noinline))
-int test_long_fname_2(struct dummy_tracepoint_args *arg)
+int test_long_fname_2(void)
{
struct ipv_counts *counts;
int key = 0;
- if (!arg->sock)
- return 0;
-
counts = bpf_map_lookup_elem(&btf_map, &key);
if (!counts)
return 0;
@@ -57,15 +49,15 @@ int test_long_fname_2(struct dummy_tracepoint_args *arg)
}
__attribute__((noinline))
-int test_long_fname_1(struct dummy_tracepoint_args *arg)
+int test_long_fname_1(void)
{
- return test_long_fname_2(arg);
+ return test_long_fname_2();
}
SEC("dummy_tracepoint")
-int _dummy_tracepoint(struct dummy_tracepoint_args *arg)
+int _dummy_tracepoint(void *arg)
{
- return test_long_fname_1(arg);
+ return test_long_fname_1();
}
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_btf_nokv.c b/tools/testing/selftests/bpf/progs/test_btf_nokv.c
index 983aedd1c072..506da7fd2da2 100644
--- a/tools/testing/selftests/bpf/progs/test_btf_nokv.c
+++ b/tools/testing/selftests/bpf/progs/test_btf_nokv.c
@@ -17,20 +17,12 @@ struct bpf_map_def SEC("maps") btf_map = {
.max_entries = 4,
};
-struct dummy_tracepoint_args {
- unsigned long long pad;
- struct sock *sock;
-};
-
__attribute__((noinline))
-int test_long_fname_2(struct dummy_tracepoint_args *arg)
+int test_long_fname_2(void)
{
struct ipv_counts *counts;
int key = 0;
- if (!arg->sock)
- return 0;
-
counts = bpf_map_lookup_elem(&btf_map, &key);
if (!counts)
return 0;
@@ -41,15 +33,15 @@ int test_long_fname_2(struct dummy_tracepoint_args *arg)
}
__attribute__((noinline))
-int test_long_fname_1(struct dummy_tracepoint_args *arg)
+int test_long_fname_1(void)
{
- return test_long_fname_2(arg);
+ return test_long_fname_2();
}
SEC("dummy_tracepoint")
-int _dummy_tracepoint(struct dummy_tracepoint_args *arg)
+int _dummy_tracepoint(void *arg)
{
- return test_long_fname_1(arg);
+ return test_long_fname_1();
}
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_cgroup_link.c b/tools/testing/selftests/bpf/progs/test_cgroup_link.c
new file mode 100644
index 000000000000..77e47b9e4446
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_cgroup_link.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2020 Facebook
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+int calls = 0;
+int alt_calls = 0;
+
+SEC("cgroup_skb/egress1")
+int egress(struct __sk_buff *skb)
+{
+ __sync_fetch_and_add(&calls, 1);
+ return 1;
+}
+
+SEC("cgroup_skb/egress2")
+int egress_alt(struct __sk_buff *skb)
+{
+ __sync_fetch_and_add(&alt_calls, 1);
+ return 1;
+}
+
+char _license[] SEC("license") = "GPL";
+
diff --git a/tools/testing/selftests/bpf/progs/test_cls_redirect.c b/tools/testing/selftests/bpf/progs/test_cls_redirect.c
new file mode 100644
index 000000000000..f0b72e86bee5
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_cls_redirect.c
@@ -0,0 +1,1061 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+// Copyright (c) 2019, 2020 Cloudflare
+
+#include <stdbool.h>
+#include <stddef.h>
+#include <stdint.h>
+#include <string.h>
+
+#include <linux/bpf.h>
+#include <linux/icmp.h>
+#include <linux/icmpv6.h>
+#include <linux/if_ether.h>
+#include <linux/in.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/pkt_cls.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
+
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+#include "test_cls_redirect.h"
+
+#define offsetofend(TYPE, MEMBER) \
+ (offsetof(TYPE, MEMBER) + sizeof((((TYPE *)0)->MEMBER)))
+
+#define IP_OFFSET_MASK (0x1FFF)
+#define IP_MF (0x2000)
+
+char _license[] SEC("license") = "Dual BSD/GPL";
+
+/**
+ * Destination port and IP used for UDP encapsulation.
+ */
+static volatile const __be16 ENCAPSULATION_PORT;
+static volatile const __be32 ENCAPSULATION_IP;
+
+typedef struct {
+ uint64_t processed_packets_total;
+ uint64_t l3_protocol_packets_total_ipv4;
+ uint64_t l3_protocol_packets_total_ipv6;
+ uint64_t l4_protocol_packets_total_tcp;
+ uint64_t l4_protocol_packets_total_udp;
+ uint64_t accepted_packets_total_syn;
+ uint64_t accepted_packets_total_syn_cookies;
+ uint64_t accepted_packets_total_last_hop;
+ uint64_t accepted_packets_total_icmp_echo_request;
+ uint64_t accepted_packets_total_established;
+ uint64_t forwarded_packets_total_gue;
+ uint64_t forwarded_packets_total_gre;
+
+ uint64_t errors_total_unknown_l3_proto;
+ uint64_t errors_total_unknown_l4_proto;
+ uint64_t errors_total_malformed_ip;
+ uint64_t errors_total_fragmented_ip;
+ uint64_t errors_total_malformed_icmp;
+ uint64_t errors_total_unwanted_icmp;
+ uint64_t errors_total_malformed_icmp_pkt_too_big;
+ uint64_t errors_total_malformed_tcp;
+ uint64_t errors_total_malformed_udp;
+ uint64_t errors_total_icmp_echo_replies;
+ uint64_t errors_total_malformed_encapsulation;
+ uint64_t errors_total_encap_adjust_failed;
+ uint64_t errors_total_encap_buffer_too_small;
+ uint64_t errors_total_redirect_loop;
+} metrics_t;
+
+typedef enum {
+ INVALID = 0,
+ UNKNOWN,
+ ECHO_REQUEST,
+ SYN,
+ SYN_COOKIE,
+ ESTABLISHED,
+} verdict_t;
+
+typedef struct {
+ uint16_t src, dst;
+} flow_ports_t;
+
+_Static_assert(
+ sizeof(flow_ports_t) !=
+ offsetofend(struct bpf_sock_tuple, ipv4.dport) -
+ offsetof(struct bpf_sock_tuple, ipv4.sport) - 1,
+ "flow_ports_t must match sport and dport in struct bpf_sock_tuple");
+_Static_assert(
+ sizeof(flow_ports_t) !=
+ offsetofend(struct bpf_sock_tuple, ipv6.dport) -
+ offsetof(struct bpf_sock_tuple, ipv6.sport) - 1,
+ "flow_ports_t must match sport and dport in struct bpf_sock_tuple");
+
+typedef int ret_t;
+
+/* This is a bit of a hack. We need a return value which allows us to
+ * indicate that the regular flow of the program should continue,
+ * while allowing functions to use XDP_PASS and XDP_DROP, etc.
+ */
+static const ret_t CONTINUE_PROCESSING = -1;
+
+/* Convenience macro to call functions which return ret_t.
+ */
+#define MAYBE_RETURN(x) \
+ do { \
+ ret_t __ret = x; \
+ if (__ret != CONTINUE_PROCESSING) \
+ return __ret; \
+ } while (0)
+
+/* Linux packet pointers are either aligned to NET_IP_ALIGN (aka 2 bytes),
+ * or not aligned if the arch supports efficient unaligned access.
+ *
+ * Since the verifier ensures that eBPF packet accesses follow these rules,
+ * we can tell LLVM to emit code as if we always had a larger alignment.
+ * It will yell at us if we end up on a platform where this is not valid.
+ */
+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
+ * LLVM will go and eliminate code, e.g. when checking packet lengths.
+ */
+ uint8_t *const tail;
+} buf_t;
+
+static size_t buf_off(const buf_t *buf)
+{
+ /* Clang seems to optimize constructs like
+ * a - b + c
+ * if c is known:
+ * r? = c
+ * r? -= b
+ * r? += a
+ *
+ * This is a problem if a and b are packet pointers,
+ * since the verifier allows subtracting two pointers to
+ * get a scalar, but not a scalar and a pointer.
+ *
+ * Use inline asm to break this optimization.
+ */
+ size_t off = (size_t)buf->head;
+ asm("%0 -= %1" : "+r"(off) : "r"(buf->skb->data));
+ return off;
+}
+
+static bool buf_copy(buf_t *buf, void *dst, size_t len)
+{
+ if (bpf_skb_load_bytes(buf->skb, buf_off(buf), dst, len)) {
+ return false;
+ }
+
+ buf->head += len;
+ return true;
+}
+
+static bool buf_skip(buf_t *buf, const size_t len)
+{
+ /* Check whether off + len is valid in the non-linear part. */
+ if (buf_off(buf) + len > buf->skb->len) {
+ return false;
+ }
+
+ buf->head += len;
+ return true;
+}
+
+/* Returns a pointer to the start of buf, or NULL if len is
+ * larger than the remaining data. Consumes len bytes on a successful
+ * call.
+ *
+ * If scratch is not NULL, the function will attempt to load non-linear
+ * data via bpf_skb_load_bytes. On success, scratch is returned.
+ */
+static void *buf_assign(buf_t *buf, const size_t len, void *scratch)
+{
+ if (buf->head + len > buf->tail) {
+ if (scratch == NULL) {
+ return NULL;
+ }
+
+ return buf_copy(buf, scratch, len) ? scratch : NULL;
+ }
+
+ void *ptr = buf->head;
+ buf->head += len;
+ return ptr;
+}
+
+static bool pkt_skip_ipv4_options(buf_t *buf, const struct iphdr *ipv4)
+{
+ if (ipv4->ihl <= 5) {
+ return true;
+ }
+
+ return buf_skip(buf, (ipv4->ihl - 5) * 4);
+}
+
+static bool ipv4_is_fragment(const struct iphdr *ip)
+{
+ uint16_t frag_off = ip->frag_off & bpf_htons(IP_OFFSET_MASK);
+ return (ip->frag_off & bpf_htons(IP_MF)) != 0 || frag_off > 0;
+}
+
+static struct iphdr *pkt_parse_ipv4(buf_t *pkt, struct iphdr *scratch)
+{
+ struct iphdr *ipv4 = buf_assign(pkt, sizeof(*ipv4), scratch);
+ if (ipv4 == NULL) {
+ return NULL;
+ }
+
+ if (ipv4->ihl < 5) {
+ return NULL;
+ }
+
+ if (!pkt_skip_ipv4_options(pkt, ipv4)) {
+ return NULL;
+ }
+
+ return ipv4;
+}
+
+/* Parse the L4 ports from a packet, assuming a layout like TCP or UDP. */
+static bool pkt_parse_icmp_l4_ports(buf_t *pkt, flow_ports_t *ports)
+{
+ if (!buf_copy(pkt, ports, sizeof(*ports))) {
+ return false;
+ }
+
+ /* Ports in the L4 headers are reversed, since we are parsing an ICMP
+ * payload which is going towards the eyeball.
+ */
+ uint16_t dst = ports->src;
+ ports->src = ports->dst;
+ ports->dst = dst;
+ return true;
+}
+
+static uint16_t pkt_checksum_fold(uint32_t csum)
+{
+ /* The highest reasonable value for an IPv4 header
+ * checksum requires two folds, so we just do that always.
+ */
+ csum = (csum & 0xffff) + (csum >> 16);
+ csum = (csum & 0xffff) + (csum >> 16);
+ return (uint16_t)~csum;
+}
+
+static void pkt_ipv4_checksum(struct iphdr *iph)
+{
+ iph->check = 0;
+
+ /* An IP header without options is 20 bytes. Two of those
+ * are the checksum, which we always set to zero. Hence,
+ * the maximum accumulated value is 18 / 2 * 0xffff = 0x8fff7,
+ * which fits in 32 bit.
+ */
+ _Static_assert(sizeof(struct iphdr) == 20, "iphdr must be 20 bytes");
+ uint32_t acc = 0;
+ uint16_t *ipw = (uint16_t *)iph;
+
+#pragma clang loop unroll(full)
+ for (size_t i = 0; i < sizeof(struct iphdr) / 2; i++) {
+ acc += ipw[i];
+ }
+
+ iph->check = pkt_checksum_fold(acc);
+}
+
+static bool pkt_skip_ipv6_extension_headers(buf_t *pkt,
+ const struct ipv6hdr *ipv6,
+ uint8_t *upper_proto,
+ bool *is_fragment)
+{
+ /* We understand five extension headers.
+ * https://tools.ietf.org/html/rfc8200#section-4.1 states that all
+ * headers should occur once, except Destination Options, which may
+ * occur twice. Hence we give up after 6 headers.
+ */
+ struct {
+ uint8_t next;
+ uint8_t len;
+ } exthdr = {
+ .next = ipv6->nexthdr,
+ };
+ *is_fragment = false;
+
+#pragma clang loop unroll(full)
+ for (int i = 0; i < 6; i++) {
+ switch (exthdr.next) {
+ case IPPROTO_FRAGMENT:
+ *is_fragment = true;
+ /* NB: We don't check that hdrlen == 0 as per spec. */
+ /* fallthrough; */
+
+ case IPPROTO_HOPOPTS:
+ case IPPROTO_ROUTING:
+ case IPPROTO_DSTOPTS:
+ case IPPROTO_MH:
+ if (!buf_copy(pkt, &exthdr, sizeof(exthdr))) {
+ return false;
+ }
+
+ /* hdrlen is in 8-octet units, and excludes the first 8 octets. */
+ if (!buf_skip(pkt,
+ (exthdr.len + 1) * 8 - sizeof(exthdr))) {
+ return false;
+ }
+
+ /* Decode next header */
+ break;
+
+ default:
+ /* The next header is not one of the known extension
+ * headers, treat it as the upper layer header.
+ *
+ * This handles IPPROTO_NONE.
+ *
+ * Encapsulating Security Payload (50) and Authentication
+ * Header (51) also end up here (and will trigger an
+ * unknown proto error later). They have a custom header
+ * format and seem too esoteric to care about.
+ */
+ *upper_proto = exthdr.next;
+ return true;
+ }
+ }
+
+ /* We never found an upper layer header. */
+ return false;
+}
+
+/* This function has to be inlined, because the verifier otherwise rejects it
+ * due to returning a pointer to the stack. This is technically correct, since
+ * scratch is allocated on the stack. However, this usage should be safe since
+ * it's the callers stack after all.
+ */
+static inline __attribute__((__always_inline__)) struct ipv6hdr *
+pkt_parse_ipv6(buf_t *pkt, struct ipv6hdr *scratch, uint8_t *proto,
+ bool *is_fragment)
+{
+ struct ipv6hdr *ipv6 = buf_assign(pkt, sizeof(*ipv6), scratch);
+ if (ipv6 == NULL) {
+ return NULL;
+ }
+
+ if (!pkt_skip_ipv6_extension_headers(pkt, ipv6, proto, is_fragment)) {
+ return NULL;
+ }
+
+ return ipv6;
+}
+
+/* Global metrics, per CPU
+ */
+struct bpf_map_def metrics_map SEC("maps") = {
+ .type = BPF_MAP_TYPE_PERCPU_ARRAY,
+ .key_size = sizeof(unsigned int),
+ .value_size = sizeof(metrics_t),
+ .max_entries = 1,
+};
+
+static metrics_t *get_global_metrics(void)
+{
+ uint64_t key = 0;
+ return bpf_map_lookup_elem(&metrics_map, &key);
+}
+
+static ret_t accept_locally(struct __sk_buff *skb, encap_headers_t *encap)
+{
+ const int payload_off =
+ sizeof(*encap) +
+ sizeof(struct in_addr) * encap->unigue.hop_count;
+ int32_t encap_overhead = payload_off - sizeof(struct ethhdr);
+
+ // Changing the ethertype if the encapsulated packet is ipv6
+ if (encap->gue.proto_ctype == IPPROTO_IPV6) {
+ encap->eth.h_proto = bpf_htons(ETH_P_IPV6);
+ }
+
+ if (bpf_skb_adjust_room(skb, -encap_overhead, BPF_ADJ_ROOM_MAC,
+ BPF_F_ADJ_ROOM_FIXED_GSO |
+ BPF_F_ADJ_ROOM_NO_CSUM_RESET) ||
+ bpf_csum_level(skb, BPF_CSUM_LEVEL_DEC))
+ return TC_ACT_SHOT;
+
+ return bpf_redirect(skb->ifindex, BPF_F_INGRESS);
+}
+
+static ret_t forward_with_gre(struct __sk_buff *skb, encap_headers_t *encap,
+ struct in_addr *next_hop, metrics_t *metrics)
+{
+ metrics->forwarded_packets_total_gre++;
+
+ const int payload_off =
+ sizeof(*encap) +
+ sizeof(struct in_addr) * encap->unigue.hop_count;
+ int32_t encap_overhead =
+ payload_off - sizeof(struct ethhdr) - sizeof(struct iphdr);
+ int32_t delta = sizeof(struct gre_base_hdr) - encap_overhead;
+ uint16_t proto = ETH_P_IP;
+
+ /* Loop protection: the inner packet's TTL is decremented as a safeguard
+ * against any forwarding loop. As the only interesting field is the TTL
+ * hop limit for IPv6, it is easier to use bpf_skb_load_bytes/bpf_skb_store_bytes
+ * as they handle the split packets if needed (no need for the data to be
+ * in the linear section).
+ */
+ if (encap->gue.proto_ctype == IPPROTO_IPV6) {
+ proto = ETH_P_IPV6;
+ uint8_t ttl;
+ int rc;
+
+ rc = bpf_skb_load_bytes(
+ skb, payload_off + offsetof(struct ipv6hdr, hop_limit),
+ &ttl, 1);
+ if (rc != 0) {
+ metrics->errors_total_malformed_encapsulation++;
+ return TC_ACT_SHOT;
+ }
+
+ if (ttl == 0) {
+ metrics->errors_total_redirect_loop++;
+ return TC_ACT_SHOT;
+ }
+
+ ttl--;
+ rc = bpf_skb_store_bytes(
+ skb, payload_off + offsetof(struct ipv6hdr, hop_limit),
+ &ttl, 1, 0);
+ if (rc != 0) {
+ metrics->errors_total_malformed_encapsulation++;
+ return TC_ACT_SHOT;
+ }
+ } else {
+ uint8_t ttl;
+ int rc;
+
+ rc = bpf_skb_load_bytes(
+ skb, payload_off + offsetof(struct iphdr, ttl), &ttl,
+ 1);
+ if (rc != 0) {
+ metrics->errors_total_malformed_encapsulation++;
+ return TC_ACT_SHOT;
+ }
+
+ if (ttl == 0) {
+ metrics->errors_total_redirect_loop++;
+ return TC_ACT_SHOT;
+ }
+
+ /* IPv4 also has a checksum to patch. While the TTL is only one byte,
+ * this function only works for 2 and 4 bytes arguments (the result is
+ * the same).
+ */
+ rc = bpf_l3_csum_replace(
+ skb, payload_off + offsetof(struct iphdr, check), ttl,
+ ttl - 1, 2);
+ if (rc != 0) {
+ metrics->errors_total_malformed_encapsulation++;
+ return TC_ACT_SHOT;
+ }
+
+ ttl--;
+ rc = bpf_skb_store_bytes(
+ skb, payload_off + offsetof(struct iphdr, ttl), &ttl, 1,
+ 0);
+ if (rc != 0) {
+ metrics->errors_total_malformed_encapsulation++;
+ return TC_ACT_SHOT;
+ }
+ }
+
+ if (bpf_skb_adjust_room(skb, delta, BPF_ADJ_ROOM_NET,
+ BPF_F_ADJ_ROOM_FIXED_GSO |
+ BPF_F_ADJ_ROOM_NO_CSUM_RESET) ||
+ bpf_csum_level(skb, BPF_CSUM_LEVEL_INC)) {
+ metrics->errors_total_encap_adjust_failed++;
+ return TC_ACT_SHOT;
+ }
+
+ if (bpf_skb_pull_data(skb, sizeof(encap_gre_t))) {
+ metrics->errors_total_encap_buffer_too_small++;
+ return TC_ACT_SHOT;
+ }
+
+ buf_t pkt = {
+ .skb = skb,
+ .head = (uint8_t *)(long)skb->data,
+ .tail = (uint8_t *)(long)skb->data_end,
+ };
+
+ encap_gre_t *encap_gre = buf_assign(&pkt, sizeof(encap_gre_t), NULL);
+ if (encap_gre == NULL) {
+ metrics->errors_total_encap_buffer_too_small++;
+ return TC_ACT_SHOT;
+ }
+
+ encap_gre->ip.protocol = IPPROTO_GRE;
+ encap_gre->ip.daddr = next_hop->s_addr;
+ encap_gre->ip.saddr = ENCAPSULATION_IP;
+ encap_gre->ip.tot_len =
+ bpf_htons(bpf_ntohs(encap_gre->ip.tot_len) + delta);
+ encap_gre->gre.flags = 0;
+ encap_gre->gre.protocol = bpf_htons(proto);
+ pkt_ipv4_checksum((void *)&encap_gre->ip);
+
+ return bpf_redirect(skb->ifindex, 0);
+}
+
+static ret_t forward_to_next_hop(struct __sk_buff *skb, encap_headers_t *encap,
+ struct in_addr *next_hop, metrics_t *metrics)
+{
+ /* swap L2 addresses */
+ /* This assumes that packets are received from a router.
+ * So just swapping the MAC addresses here will make the packet go back to
+ * the router, which will send it to the appropriate machine.
+ */
+ unsigned char temp[ETH_ALEN];
+ memcpy(temp, encap->eth.h_dest, sizeof(temp));
+ memcpy(encap->eth.h_dest, encap->eth.h_source,
+ sizeof(encap->eth.h_dest));
+ memcpy(encap->eth.h_source, temp, sizeof(encap->eth.h_source));
+
+ if (encap->unigue.next_hop == encap->unigue.hop_count - 1 &&
+ encap->unigue.last_hop_gre) {
+ return forward_with_gre(skb, encap, next_hop, metrics);
+ }
+
+ metrics->forwarded_packets_total_gue++;
+ uint32_t old_saddr = encap->ip.saddr;
+ encap->ip.saddr = encap->ip.daddr;
+ encap->ip.daddr = next_hop->s_addr;
+ if (encap->unigue.next_hop < encap->unigue.hop_count) {
+ encap->unigue.next_hop++;
+ }
+
+ /* Remove ip->saddr, add next_hop->s_addr */
+ const uint64_t off = offsetof(typeof(*encap), ip.check);
+ int ret = bpf_l3_csum_replace(skb, off, old_saddr, next_hop->s_addr, 4);
+ if (ret < 0) {
+ return TC_ACT_SHOT;
+ }
+
+ return bpf_redirect(skb->ifindex, 0);
+}
+
+static ret_t skip_next_hops(buf_t *pkt, int n)
+{
+ switch (n) {
+ case 1:
+ if (!buf_skip(pkt, sizeof(struct in_addr)))
+ return TC_ACT_SHOT;
+ case 0:
+ return CONTINUE_PROCESSING;
+
+ default:
+ return TC_ACT_SHOT;
+ }
+}
+
+/* Get the next hop from the GLB header.
+ *
+ * Sets next_hop->s_addr to 0 if there are no more hops left.
+ * pkt is positioned just after the variable length GLB header
+ * iff the call is successful.
+ */
+static ret_t get_next_hop(buf_t *pkt, encap_headers_t *encap,
+ struct in_addr *next_hop)
+{
+ if (encap->unigue.next_hop > encap->unigue.hop_count) {
+ return TC_ACT_SHOT;
+ }
+
+ /* Skip "used" next hops. */
+ MAYBE_RETURN(skip_next_hops(pkt, encap->unigue.next_hop));
+
+ if (encap->unigue.next_hop == encap->unigue.hop_count) {
+ /* No more next hops, we are at the end of the GLB header. */
+ next_hop->s_addr = 0;
+ return CONTINUE_PROCESSING;
+ }
+
+ if (!buf_copy(pkt, next_hop, sizeof(*next_hop))) {
+ return TC_ACT_SHOT;
+ }
+
+ /* Skip the remainig next hops (may be zero). */
+ return skip_next_hops(pkt, encap->unigue.hop_count -
+ encap->unigue.next_hop - 1);
+}
+
+/* Fill a bpf_sock_tuple to be used with the socket lookup functions.
+ * This is a kludge that let's us work around verifier limitations:
+ *
+ * fill_tuple(&t, foo, sizeof(struct iphdr), 123, 321)
+ *
+ * clang will substitue a costant for sizeof, which allows the verifier
+ * to track it's value. Based on this, it can figure out the constant
+ * return value, and calling code works while still being "generic" to
+ * IPv4 and IPv6.
+ */
+static uint64_t fill_tuple(struct bpf_sock_tuple *tuple, void *iph,
+ uint64_t iphlen, uint16_t sport, uint16_t dport)
+{
+ switch (iphlen) {
+ case sizeof(struct iphdr): {
+ struct iphdr *ipv4 = (struct iphdr *)iph;
+ tuple->ipv4.daddr = ipv4->daddr;
+ tuple->ipv4.saddr = ipv4->saddr;
+ tuple->ipv4.sport = sport;
+ tuple->ipv4.dport = dport;
+ return sizeof(tuple->ipv4);
+ }
+
+ case sizeof(struct ipv6hdr): {
+ struct ipv6hdr *ipv6 = (struct ipv6hdr *)iph;
+ memcpy(&tuple->ipv6.daddr, &ipv6->daddr,
+ sizeof(tuple->ipv6.daddr));
+ memcpy(&tuple->ipv6.saddr, &ipv6->saddr,
+ sizeof(tuple->ipv6.saddr));
+ tuple->ipv6.sport = sport;
+ tuple->ipv6.dport = dport;
+ return sizeof(tuple->ipv6);
+ }
+
+ default:
+ return 0;
+ }
+}
+
+static verdict_t classify_tcp(struct __sk_buff *skb,
+ struct bpf_sock_tuple *tuple, uint64_t tuplen,
+ void *iph, struct tcphdr *tcp)
+{
+ struct bpf_sock *sk =
+ bpf_skc_lookup_tcp(skb, tuple, tuplen, BPF_F_CURRENT_NETNS, 0);
+ if (sk == NULL) {
+ return UNKNOWN;
+ }
+
+ if (sk->state != BPF_TCP_LISTEN) {
+ bpf_sk_release(sk);
+ return ESTABLISHED;
+ }
+
+ if (iph != NULL && tcp != NULL) {
+ /* Kludge: we've run out of arguments, but need the length of the ip header. */
+ uint64_t iphlen = sizeof(struct iphdr);
+ if (tuplen == sizeof(tuple->ipv6)) {
+ iphlen = sizeof(struct ipv6hdr);
+ }
+
+ if (bpf_tcp_check_syncookie(sk, iph, iphlen, tcp,
+ sizeof(*tcp)) == 0) {
+ bpf_sk_release(sk);
+ return SYN_COOKIE;
+ }
+ }
+
+ bpf_sk_release(sk);
+ return UNKNOWN;
+}
+
+static verdict_t classify_udp(struct __sk_buff *skb,
+ struct bpf_sock_tuple *tuple, uint64_t tuplen)
+{
+ struct bpf_sock *sk =
+ bpf_sk_lookup_udp(skb, tuple, tuplen, BPF_F_CURRENT_NETNS, 0);
+ if (sk == NULL) {
+ return UNKNOWN;
+ }
+
+ if (sk->state == BPF_TCP_ESTABLISHED) {
+ bpf_sk_release(sk);
+ return ESTABLISHED;
+ }
+
+ bpf_sk_release(sk);
+ return UNKNOWN;
+}
+
+static verdict_t classify_icmp(struct __sk_buff *skb, uint8_t proto,
+ struct bpf_sock_tuple *tuple, uint64_t tuplen,
+ metrics_t *metrics)
+{
+ switch (proto) {
+ case IPPROTO_TCP:
+ return classify_tcp(skb, tuple, tuplen, NULL, NULL);
+
+ case IPPROTO_UDP:
+ return classify_udp(skb, tuple, tuplen);
+
+ default:
+ metrics->errors_total_malformed_icmp++;
+ return INVALID;
+ }
+}
+
+static verdict_t process_icmpv4(buf_t *pkt, metrics_t *metrics)
+{
+ struct icmphdr icmp;
+ if (!buf_copy(pkt, &icmp, sizeof(icmp))) {
+ metrics->errors_total_malformed_icmp++;
+ return INVALID;
+ }
+
+ /* We should never receive encapsulated echo replies. */
+ if (icmp.type == ICMP_ECHOREPLY) {
+ metrics->errors_total_icmp_echo_replies++;
+ return INVALID;
+ }
+
+ if (icmp.type == ICMP_ECHO) {
+ return ECHO_REQUEST;
+ }
+
+ if (icmp.type != ICMP_DEST_UNREACH || icmp.code != ICMP_FRAG_NEEDED) {
+ metrics->errors_total_unwanted_icmp++;
+ return INVALID;
+ }
+
+ struct iphdr _ip4;
+ const struct iphdr *ipv4 = pkt_parse_ipv4(pkt, &_ip4);
+ if (ipv4 == NULL) {
+ metrics->errors_total_malformed_icmp_pkt_too_big++;
+ return INVALID;
+ }
+
+ /* The source address in the outer IP header is from the entity that
+ * originated the ICMP message. Use the original IP header to restore
+ * the correct flow tuple.
+ */
+ struct bpf_sock_tuple tuple;
+ tuple.ipv4.saddr = ipv4->daddr;
+ tuple.ipv4.daddr = ipv4->saddr;
+
+ if (!pkt_parse_icmp_l4_ports(pkt, (flow_ports_t *)&tuple.ipv4.sport)) {
+ metrics->errors_total_malformed_icmp_pkt_too_big++;
+ return INVALID;
+ }
+
+ return classify_icmp(pkt->skb, ipv4->protocol, &tuple,
+ sizeof(tuple.ipv4), metrics);
+}
+
+static verdict_t process_icmpv6(buf_t *pkt, metrics_t *metrics)
+{
+ struct icmp6hdr icmp6;
+ if (!buf_copy(pkt, &icmp6, sizeof(icmp6))) {
+ metrics->errors_total_malformed_icmp++;
+ return INVALID;
+ }
+
+ /* We should never receive encapsulated echo replies. */
+ if (icmp6.icmp6_type == ICMPV6_ECHO_REPLY) {
+ metrics->errors_total_icmp_echo_replies++;
+ return INVALID;
+ }
+
+ if (icmp6.icmp6_type == ICMPV6_ECHO_REQUEST) {
+ return ECHO_REQUEST;
+ }
+
+ if (icmp6.icmp6_type != ICMPV6_PKT_TOOBIG) {
+ metrics->errors_total_unwanted_icmp++;
+ return INVALID;
+ }
+
+ bool is_fragment;
+ uint8_t l4_proto;
+ struct ipv6hdr _ipv6;
+ const struct ipv6hdr *ipv6 =
+ pkt_parse_ipv6(pkt, &_ipv6, &l4_proto, &is_fragment);
+ if (ipv6 == NULL) {
+ metrics->errors_total_malformed_icmp_pkt_too_big++;
+ return INVALID;
+ }
+
+ if (is_fragment) {
+ metrics->errors_total_fragmented_ip++;
+ return INVALID;
+ }
+
+ /* Swap source and dest addresses. */
+ struct bpf_sock_tuple tuple;
+ memcpy(&tuple.ipv6.saddr, &ipv6->daddr, sizeof(tuple.ipv6.saddr));
+ memcpy(&tuple.ipv6.daddr, &ipv6->saddr, sizeof(tuple.ipv6.daddr));
+
+ if (!pkt_parse_icmp_l4_ports(pkt, (flow_ports_t *)&tuple.ipv6.sport)) {
+ metrics->errors_total_malformed_icmp_pkt_too_big++;
+ return INVALID;
+ }
+
+ return classify_icmp(pkt->skb, l4_proto, &tuple, sizeof(tuple.ipv6),
+ metrics);
+}
+
+static verdict_t process_tcp(buf_t *pkt, void *iph, uint64_t iphlen,
+ metrics_t *metrics)
+{
+ metrics->l4_protocol_packets_total_tcp++;
+
+ struct tcphdr _tcp;
+ struct tcphdr *tcp = buf_assign(pkt, sizeof(_tcp), &_tcp);
+ if (tcp == NULL) {
+ metrics->errors_total_malformed_tcp++;
+ return INVALID;
+ }
+
+ if (tcp->syn) {
+ return SYN;
+ }
+
+ struct bpf_sock_tuple tuple;
+ uint64_t tuplen =
+ fill_tuple(&tuple, iph, iphlen, tcp->source, tcp->dest);
+ return classify_tcp(pkt->skb, &tuple, tuplen, iph, tcp);
+}
+
+static verdict_t process_udp(buf_t *pkt, void *iph, uint64_t iphlen,
+ metrics_t *metrics)
+{
+ metrics->l4_protocol_packets_total_udp++;
+
+ struct udphdr _udp;
+ struct udphdr *udph = buf_assign(pkt, sizeof(_udp), &_udp);
+ if (udph == NULL) {
+ metrics->errors_total_malformed_udp++;
+ return INVALID;
+ }
+
+ struct bpf_sock_tuple tuple;
+ uint64_t tuplen =
+ fill_tuple(&tuple, iph, iphlen, udph->source, udph->dest);
+ return classify_udp(pkt->skb, &tuple, tuplen);
+}
+
+static verdict_t process_ipv4(buf_t *pkt, metrics_t *metrics)
+{
+ metrics->l3_protocol_packets_total_ipv4++;
+
+ struct iphdr _ip4;
+ struct iphdr *ipv4 = pkt_parse_ipv4(pkt, &_ip4);
+ if (ipv4 == NULL) {
+ metrics->errors_total_malformed_ip++;
+ return INVALID;
+ }
+
+ if (ipv4->version != 4) {
+ metrics->errors_total_malformed_ip++;
+ return INVALID;
+ }
+
+ if (ipv4_is_fragment(ipv4)) {
+ metrics->errors_total_fragmented_ip++;
+ return INVALID;
+ }
+
+ switch (ipv4->protocol) {
+ case IPPROTO_ICMP:
+ return process_icmpv4(pkt, metrics);
+
+ case IPPROTO_TCP:
+ return process_tcp(pkt, ipv4, sizeof(*ipv4), metrics);
+
+ case IPPROTO_UDP:
+ return process_udp(pkt, ipv4, sizeof(*ipv4), metrics);
+
+ default:
+ metrics->errors_total_unknown_l4_proto++;
+ return INVALID;
+ }
+}
+
+static verdict_t process_ipv6(buf_t *pkt, metrics_t *metrics)
+{
+ metrics->l3_protocol_packets_total_ipv6++;
+
+ uint8_t l4_proto;
+ bool is_fragment;
+ struct ipv6hdr _ipv6;
+ struct ipv6hdr *ipv6 =
+ pkt_parse_ipv6(pkt, &_ipv6, &l4_proto, &is_fragment);
+ if (ipv6 == NULL) {
+ metrics->errors_total_malformed_ip++;
+ return INVALID;
+ }
+
+ if (ipv6->version != 6) {
+ metrics->errors_total_malformed_ip++;
+ return INVALID;
+ }
+
+ if (is_fragment) {
+ metrics->errors_total_fragmented_ip++;
+ return INVALID;
+ }
+
+ switch (l4_proto) {
+ case IPPROTO_ICMPV6:
+ return process_icmpv6(pkt, metrics);
+
+ case IPPROTO_TCP:
+ return process_tcp(pkt, ipv6, sizeof(*ipv6), metrics);
+
+ case IPPROTO_UDP:
+ return process_udp(pkt, ipv6, sizeof(*ipv6), metrics);
+
+ default:
+ metrics->errors_total_unknown_l4_proto++;
+ return INVALID;
+ }
+}
+
+SEC("classifier/cls_redirect")
+int cls_redirect(struct __sk_buff *skb)
+{
+ metrics_t *metrics = get_global_metrics();
+ if (metrics == NULL) {
+ return TC_ACT_SHOT;
+ }
+
+ metrics->processed_packets_total++;
+
+ /* Pass bogus packets as long as we're not sure they're
+ * destined for us.
+ */
+ if (skb->protocol != bpf_htons(ETH_P_IP)) {
+ return TC_ACT_OK;
+ }
+
+ encap_headers_t *encap;
+
+ /* Make sure that all encapsulation headers are available in
+ * the linear portion of the skb. This makes it easy to manipulate them.
+ */
+ if (bpf_skb_pull_data(skb, sizeof(*encap))) {
+ return TC_ACT_OK;
+ }
+
+ buf_t pkt = {
+ .skb = skb,
+ .head = (uint8_t *)(long)skb->data,
+ .tail = (uint8_t *)(long)skb->data_end,
+ };
+
+ encap = buf_assign(&pkt, sizeof(*encap), NULL);
+ if (encap == NULL) {
+ return TC_ACT_OK;
+ }
+
+ if (encap->ip.ihl != 5) {
+ /* We never have any options. */
+ return TC_ACT_OK;
+ }
+
+ if (encap->ip.daddr != ENCAPSULATION_IP ||
+ encap->ip.protocol != IPPROTO_UDP) {
+ return TC_ACT_OK;
+ }
+
+ /* TODO Check UDP length? */
+ if (encap->udp.dest != ENCAPSULATION_PORT) {
+ return TC_ACT_OK;
+ }
+
+ /* We now know that the packet is destined to us, we can
+ * drop bogus ones.
+ */
+ if (ipv4_is_fragment((void *)&encap->ip)) {
+ metrics->errors_total_fragmented_ip++;
+ return TC_ACT_SHOT;
+ }
+
+ if (encap->gue.variant != 0) {
+ metrics->errors_total_malformed_encapsulation++;
+ return TC_ACT_SHOT;
+ }
+
+ if (encap->gue.control != 0) {
+ metrics->errors_total_malformed_encapsulation++;
+ return TC_ACT_SHOT;
+ }
+
+ if (encap->gue.flags != 0) {
+ metrics->errors_total_malformed_encapsulation++;
+ return TC_ACT_SHOT;
+ }
+
+ if (encap->gue.hlen !=
+ sizeof(encap->unigue) / 4 + encap->unigue.hop_count) {
+ metrics->errors_total_malformed_encapsulation++;
+ return TC_ACT_SHOT;
+ }
+
+ if (encap->unigue.version != 0) {
+ metrics->errors_total_malformed_encapsulation++;
+ return TC_ACT_SHOT;
+ }
+
+ if (encap->unigue.reserved != 0) {
+ return TC_ACT_SHOT;
+ }
+
+ struct in_addr next_hop;
+ MAYBE_RETURN(get_next_hop(&pkt, encap, &next_hop));
+
+ if (next_hop.s_addr == 0) {
+ metrics->accepted_packets_total_last_hop++;
+ return accept_locally(skb, encap);
+ }
+
+ verdict_t verdict;
+ switch (encap->gue.proto_ctype) {
+ case IPPROTO_IPIP:
+ verdict = process_ipv4(&pkt, metrics);
+ break;
+
+ case IPPROTO_IPV6:
+ verdict = process_ipv6(&pkt, metrics);
+ break;
+
+ default:
+ metrics->errors_total_unknown_l3_proto++;
+ return TC_ACT_SHOT;
+ }
+
+ switch (verdict) {
+ case INVALID:
+ /* metrics have already been bumped */
+ return TC_ACT_SHOT;
+
+ case UNKNOWN:
+ return forward_to_next_hop(skb, encap, &next_hop, metrics);
+
+ case ECHO_REQUEST:
+ metrics->accepted_packets_total_icmp_echo_request++;
+ break;
+
+ case SYN:
+ if (encap->unigue.forward_syn) {
+ return forward_to_next_hop(skb, encap, &next_hop,
+ metrics);
+ }
+
+ metrics->accepted_packets_total_syn++;
+ break;
+
+ case SYN_COOKIE:
+ metrics->accepted_packets_total_syn_cookies++;
+ break;
+
+ case ESTABLISHED:
+ metrics->accepted_packets_total_established++;
+ break;
+ }
+
+ return accept_locally(skb, encap);
+}
diff --git a/tools/testing/selftests/bpf/progs/test_cls_redirect.h b/tools/testing/selftests/bpf/progs/test_cls_redirect.h
new file mode 100644
index 000000000000..76eab0aacba0
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_cls_redirect.h
@@ -0,0 +1,54 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
+/* Copyright 2019, 2020 Cloudflare */
+
+#include <stdbool.h>
+#include <stddef.h>
+#include <stdint.h>
+#include <string.h>
+
+#include <linux/if_ether.h>
+#include <linux/in.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/udp.h>
+
+struct gre_base_hdr {
+ uint16_t flags;
+ uint16_t protocol;
+} __attribute__((packed));
+
+struct guehdr {
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+ uint8_t hlen : 5, control : 1, variant : 2;
+#else
+ uint8_t variant : 2, control : 1, hlen : 5;
+#endif
+ uint8_t proto_ctype;
+ uint16_t flags;
+};
+
+struct unigue {
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+ uint8_t _r : 2, last_hop_gre : 1, forward_syn : 1, version : 4;
+#else
+ uint8_t version : 4, forward_syn : 1, last_hop_gre : 1, _r : 2;
+#endif
+ uint8_t reserved;
+ uint8_t next_hop;
+ uint8_t hop_count;
+ // Next hops go here
+} __attribute__((packed));
+
+typedef struct {
+ struct ethhdr eth;
+ struct iphdr ip;
+ struct gre_base_hdr gre;
+} __attribute__((packed)) encap_gre_t;
+
+typedef struct {
+ struct ethhdr eth;
+ struct iphdr ip;
+ struct udphdr udp;
+ struct guehdr gue;
+ struct unigue unigue;
+} __attribute__((packed)) encap_headers_t;
diff --git a/tools/testing/selftests/bpf/progs/test_enable_stats.c b/tools/testing/selftests/bpf/progs/test_enable_stats.c
new file mode 100644
index 000000000000..01a002ade529
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_enable_stats.c
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2020 Facebook
+
+#include <linux/bpf.h>
+#include <stdint.h>
+#include <linux/types.h>
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+__u64 count = 0;
+
+SEC("raw_tracepoint/sys_enter")
+int test_enable_stats(void *ctx)
+{
+ count += 1;
+ return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_get_stack_rawtp_err.c b/tools/testing/selftests/bpf/progs/test_get_stack_rawtp_err.c
new file mode 100644
index 000000000000..8941a41c2a55
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_get_stack_rawtp_err.c
@@ -0,0 +1,26 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+#define MAX_STACK_RAWTP 10
+
+SEC("raw_tracepoint/sys_enter")
+int bpf_prog2(void *ctx)
+{
+ __u64 stack[MAX_STACK_RAWTP];
+ int error;
+
+ /* set all the flags which should return -EINVAL */
+ error = bpf_get_stack(ctx, stack, 0, -1);
+ if (error < 0)
+ goto loop;
+
+ return error;
+loop:
+ while (1) {
+ error++;
+ }
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_global_data.c b/tools/testing/selftests/bpf/progs/test_global_data.c
index dd7a4d3dbc0d..1319be1c54ba 100644
--- a/tools/testing/selftests/bpf/progs/test_global_data.c
+++ b/tools/testing/selftests/bpf/progs/test_global_data.c
@@ -68,7 +68,7 @@ static struct foo struct3 = {
bpf_map_update_elem(&result_##map, &key, var, 0); \
} while (0)
-SEC("static_data_load")
+SEC("classifier/static_data_load")
int load_static_data(struct __sk_buff *skb)
{
static const __u64 bar = ~0;
diff --git a/tools/testing/selftests/bpf/progs/test_link_pinning.c b/tools/testing/selftests/bpf/progs/test_link_pinning.c
new file mode 100644
index 000000000000..bbf2a5264dc0
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_link_pinning.c
@@ -0,0 +1,25 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+
+#include <stdbool.h>
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+int in = 0;
+int out = 0;
+
+SEC("raw_tp/sys_enter")
+int raw_tp_prog(const void *ctx)
+{
+ out = in;
+ return 0;
+}
+
+SEC("tp_btf/sys_enter")
+int tp_btf_prog(const void *ctx)
+{
+ out = in;
+ return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_mmap.c b/tools/testing/selftests/bpf/progs/test_mmap.c
index 6239596cd14e..4eb42cff5fe9 100644
--- a/tools/testing/selftests/bpf/progs/test_mmap.c
+++ b/tools/testing/selftests/bpf/progs/test_mmap.c
@@ -9,6 +9,14 @@ char _license[] SEC("license") = "GPL";
struct {
__uint(type, BPF_MAP_TYPE_ARRAY);
+ __uint(max_entries, 4096);
+ __uint(map_flags, BPF_F_MMAPABLE | BPF_F_RDONLY_PROG);
+ __type(key, __u32);
+ __type(value, char);
+} rdonly_map SEC(".maps");
+
+struct {
+ __uint(type, BPF_MAP_TYPE_ARRAY);
__uint(max_entries, 512 * 4); /* at least 4 pages of data */
__uint(map_flags, BPF_F_MMAPABLE);
__type(key, __u32);
diff --git a/tools/testing/selftests/bpf/progs/test_ns_current_pid_tgid.c b/tools/testing/selftests/bpf/progs/test_ns_current_pid_tgid.c
new file mode 100644
index 000000000000..1dca70a6de2f
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_ns_current_pid_tgid.c
@@ -0,0 +1,37 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019 Carlos Neira cneirabustos@gmail.com */
+
+#include <linux/bpf.h>
+#include <stdint.h>
+#include <bpf/bpf_helpers.h>
+
+static volatile struct {
+ __u64 dev;
+ __u64 ino;
+ __u64 pid_tgid;
+ __u64 user_pid_tgid;
+} res;
+
+SEC("raw_tracepoint/sys_enter")
+int trace(void *ctx)
+{
+ __u64 ns_pid_tgid, expected_pid;
+ struct bpf_pidns_info nsdata;
+ __u32 key = 0;
+
+ if (bpf_get_ns_current_pid_tgid(res.dev, res.ino, &nsdata,
+ sizeof(struct bpf_pidns_info)))
+ return 0;
+
+ ns_pid_tgid = (__u64)nsdata.tgid << 32 | nsdata.pid;
+ expected_pid = res.user_pid_tgid;
+
+ if (expected_pid != ns_pid_tgid)
+ return 0;
+
+ res.pid_tgid = ns_pid_tgid;
+
+ return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_obj_id.c b/tools/testing/selftests/bpf/progs/test_obj_id.c
index 98b9de2fafd0..ded71b3ff6b4 100644
--- a/tools/testing/selftests/bpf/progs/test_obj_id.c
+++ b/tools/testing/selftests/bpf/progs/test_obj_id.c
@@ -3,16 +3,8 @@
*/
#include <stddef.h>
#include <linux/bpf.h>
-#include <linux/pkt_cls.h>
#include <bpf/bpf_helpers.h>
-/* It is a dumb bpf program such that it must have no
- * issue to be loaded since testing the verifier is
- * not the focus here.
- */
-
-int _version SEC("version") = 1;
-
struct {
__uint(type, BPF_MAP_TYPE_ARRAY);
__uint(max_entries, 1);
@@ -20,13 +12,13 @@ struct {
__type(value, __u64);
} test_map_id SEC(".maps");
-SEC("test_obj_id_dummy")
-int test_obj_id(struct __sk_buff *skb)
+SEC("raw_tp/sys_enter")
+int test_obj_id(void *ctx)
{
__u32 key = 0;
__u64 *value;
value = bpf_map_lookup_elem(&test_map_id, &key);
- return TC_ACT_OK;
+ return 0;
}
diff --git a/tools/testing/selftests/bpf/progs/test_overhead.c b/tools/testing/selftests/bpf/progs/test_overhead.c
index bfe9fbcb9684..42403d088abc 100644
--- a/tools/testing/selftests/bpf/progs/test_overhead.c
+++ b/tools/testing/selftests/bpf/progs/test_overhead.c
@@ -6,7 +6,6 @@
#include <linux/ptrace.h>
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_tracing.h>
-#include "bpf_trace_helpers.h"
struct task_struct;
@@ -17,11 +16,9 @@ int BPF_KPROBE(prog1, struct task_struct *tsk, const char *buf, bool exec)
}
SEC("kretprobe/__set_task_comm")
-int BPF_KRETPROBE(prog2,
- struct task_struct *tsk, const char *buf, bool exec,
- int ret)
+int BPF_KRETPROBE(prog2, int ret)
{
- return !PT_REGS_PARM1(ctx) && ret;
+ return ret;
}
SEC("raw_tp/task_rename")
@@ -33,12 +30,18 @@ int prog3(struct bpf_raw_tracepoint_args *ctx)
SEC("fentry/__set_task_comm")
int BPF_PROG(prog4, struct task_struct *tsk, const char *buf, bool exec)
{
- return !tsk;
+ return 0;
}
SEC("fexit/__set_task_comm")
int BPF_PROG(prog5, struct task_struct *tsk, const char *buf, bool exec)
{
+ return 0;
+}
+
+SEC("fmod_ret/__set_task_comm")
+int BPF_PROG(prog6, struct task_struct *tsk, const char *buf, bool exec)
+{
return !tsk;
}
diff --git a/tools/testing/selftests/bpf/progs/test_perf_branches.c b/tools/testing/selftests/bpf/progs/test_perf_branches.c
new file mode 100644
index 000000000000..a1ccc831c882
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_perf_branches.c
@@ -0,0 +1,50 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Facebook
+
+#include <stddef.h>
+#include <linux/ptrace.h>
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+int valid = 0;
+int required_size_out = 0;
+int written_stack_out = 0;
+int written_global_out = 0;
+
+struct {
+ __u64 _a;
+ __u64 _b;
+ __u64 _c;
+} fpbe[30] = {0};
+
+SEC("perf_event")
+int perf_branches(void *ctx)
+{
+ __u64 entries[4 * 3] = {0};
+ int required_size, written_stack, written_global;
+
+ /* write to stack */
+ written_stack = bpf_read_branch_records(ctx, entries, sizeof(entries), 0);
+ /* ignore spurious events */
+ if (!written_stack)
+ return 1;
+
+ /* get required size */
+ required_size = bpf_read_branch_records(ctx, NULL, 0,
+ BPF_F_GET_BRANCH_RECORDS_SIZE);
+
+ written_global = bpf_read_branch_records(ctx, fpbe, sizeof(fpbe), 0);
+ /* ignore spurious events */
+ if (!written_global)
+ return 1;
+
+ required_size_out = required_size;
+ written_stack_out = written_stack;
+ written_global_out = written_global;
+ valid = 1;
+
+ return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_perf_buffer.c b/tools/testing/selftests/bpf/progs/test_perf_buffer.c
index ebfcc9f50c35..ad59c4c9aba8 100644
--- a/tools/testing/selftests/bpf/progs/test_perf_buffer.c
+++ b/tools/testing/selftests/bpf/progs/test_perf_buffer.c
@@ -4,7 +4,7 @@
#include <linux/ptrace.h>
#include <linux/bpf.h>
#include <bpf/bpf_helpers.h>
-#include "bpf_trace_helpers.h"
+#include <bpf/bpf_tracing.h>
struct {
__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
diff --git a/tools/testing/selftests/bpf/progs/test_probe_user.c b/tools/testing/selftests/bpf/progs/test_probe_user.c
index d556b1572cc6..89b3532ccc75 100644
--- a/tools/testing/selftests/bpf/progs/test_probe_user.c
+++ b/tools/testing/selftests/bpf/progs/test_probe_user.c
@@ -7,7 +7,6 @@
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_tracing.h>
-#include "bpf_trace_helpers.h"
static struct sockaddr_in old;
diff --git a/tools/testing/selftests/bpf/progs/test_ringbuf.c b/tools/testing/selftests/bpf/progs/test_ringbuf.c
new file mode 100644
index 000000000000..8ba9959b036b
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_ringbuf.c
@@ -0,0 +1,78 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2020 Facebook
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct sample {
+ int pid;
+ int seq;
+ long value;
+ char comm[16];
+};
+
+struct {
+ __uint(type, BPF_MAP_TYPE_RINGBUF);
+ __uint(max_entries, 1 << 12);
+} ringbuf SEC(".maps");
+
+/* inputs */
+int pid = 0;
+long value = 0;
+long flags = 0;
+
+/* outputs */
+long total = 0;
+long discarded = 0;
+long dropped = 0;
+
+long avail_data = 0;
+long ring_size = 0;
+long cons_pos = 0;
+long prod_pos = 0;
+
+/* inner state */
+long seq = 0;
+
+SEC("tp/syscalls/sys_enter_getpgid")
+int test_ringbuf(void *ctx)
+{
+ int cur_pid = bpf_get_current_pid_tgid() >> 32;
+ struct sample *sample;
+ int zero = 0;
+
+ if (cur_pid != pid)
+ return 0;
+
+ sample = bpf_ringbuf_reserve(&ringbuf, sizeof(*sample), 0);
+ if (!sample) {
+ __sync_fetch_and_add(&dropped, 1);
+ return 1;
+ }
+
+ sample->pid = pid;
+ bpf_get_current_comm(sample->comm, sizeof(sample->comm));
+ sample->value = value;
+
+ sample->seq = seq++;
+ __sync_fetch_and_add(&total, 1);
+
+ if (sample->seq & 1) {
+ /* copy from reserved sample to a new one... */
+ bpf_ringbuf_output(&ringbuf, sample, sizeof(*sample), flags);
+ /* ...and then discard reserved sample */
+ bpf_ringbuf_discard(sample, flags);
+ __sync_fetch_and_add(&discarded, 1);
+ } else {
+ bpf_ringbuf_submit(sample, flags);
+ }
+
+ avail_data = bpf_ringbuf_query(&ringbuf, BPF_RB_AVAIL_DATA);
+ ring_size = bpf_ringbuf_query(&ringbuf, BPF_RB_RING_SIZE);
+ cons_pos = bpf_ringbuf_query(&ringbuf, BPF_RB_CONS_POS);
+ prod_pos = bpf_ringbuf_query(&ringbuf, BPF_RB_PROD_POS);
+
+ return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_ringbuf_multi.c b/tools/testing/selftests/bpf/progs/test_ringbuf_multi.c
new file mode 100644
index 000000000000..edf3b6953533
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_ringbuf_multi.c
@@ -0,0 +1,77 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2020 Facebook
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct sample {
+ int pid;
+ int seq;
+ long value;
+ char comm[16];
+};
+
+struct ringbuf_map {
+ __uint(type, BPF_MAP_TYPE_RINGBUF);
+ __uint(max_entries, 1 << 12);
+} ringbuf1 SEC(".maps"),
+ ringbuf2 SEC(".maps");
+
+struct {
+ __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS);
+ __uint(max_entries, 4);
+ __type(key, int);
+ __array(values, struct ringbuf_map);
+} ringbuf_arr SEC(".maps") = {
+ .values = {
+ [0] = &ringbuf1,
+ [2] = &ringbuf2,
+ },
+};
+
+/* inputs */
+int pid = 0;
+int target_ring = 0;
+long value = 0;
+
+/* outputs */
+long total = 0;
+long dropped = 0;
+long skipped = 0;
+
+SEC("tp/syscalls/sys_enter_getpgid")
+int test_ringbuf(void *ctx)
+{
+ int cur_pid = bpf_get_current_pid_tgid() >> 32;
+ struct sample *sample;
+ void *rb;
+ int zero = 0;
+
+ if (cur_pid != pid)
+ return 0;
+
+ rb = bpf_map_lookup_elem(&ringbuf_arr, &target_ring);
+ if (!rb) {
+ skipped += 1;
+ return 1;
+ }
+
+ sample = bpf_ringbuf_reserve(rb, sizeof(*sample), 0);
+ if (!sample) {
+ dropped += 1;
+ return 1;
+ }
+
+ sample->pid = pid;
+ bpf_get_current_comm(sample->comm, sizeof(sample->comm));
+ sample->value = value;
+
+ sample->seq = total;
+ total += 1;
+
+ bpf_ringbuf_submit(sample, 0);
+
+ return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_sk_assign.c b/tools/testing/selftests/bpf/progs/test_sk_assign.c
new file mode 100644
index 000000000000..1ecd987005d2
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_sk_assign.c
@@ -0,0 +1,186 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Cloudflare Ltd.
+// Copyright (c) 2020 Isovalent, Inc.
+
+#include <stddef.h>
+#include <stdbool.h>
+#include <string.h>
+#include <linux/bpf.h>
+#include <linux/if_ether.h>
+#include <linux/in.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/pkt_cls.h>
+#include <linux/tcp.h>
+#include <sys/socket.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+/* Pin map under /sys/fs/bpf/tc/globals/<map name> */
+#define PIN_GLOBAL_NS 2
+
+/* Must match struct bpf_elf_map layout from iproute2 */
+struct {
+ __u32 type;
+ __u32 size_key;
+ __u32 size_value;
+ __u32 max_elem;
+ __u32 flags;
+ __u32 id;
+ __u32 pinning;
+} server_map SEC("maps") = {
+ .type = BPF_MAP_TYPE_SOCKMAP,
+ .size_key = sizeof(int),
+ .size_value = sizeof(__u64),
+ .max_elem = 1,
+ .pinning = PIN_GLOBAL_NS,
+};
+
+int _version SEC("version") = 1;
+char _license[] SEC("license") = "GPL";
+
+/* Fill 'tuple' with L3 info, and attempt to find L4. On fail, return NULL. */
+static inline struct bpf_sock_tuple *
+get_tuple(struct __sk_buff *skb, bool *ipv4, bool *tcp)
+{
+ void *data_end = (void *)(long)skb->data_end;
+ void *data = (void *)(long)skb->data;
+ struct bpf_sock_tuple *result;
+ struct ethhdr *eth;
+ __u64 tuple_len;
+ __u8 proto = 0;
+ __u64 ihl_len;
+
+ eth = (struct ethhdr *)(data);
+ if (eth + 1 > data_end)
+ return NULL;
+
+ if (eth->h_proto == bpf_htons(ETH_P_IP)) {
+ struct iphdr *iph = (struct iphdr *)(data + sizeof(*eth));
+
+ if (iph + 1 > data_end)
+ return NULL;
+ if (iph->ihl != 5)
+ /* Options are not supported */
+ return NULL;
+ ihl_len = iph->ihl * 4;
+ proto = iph->protocol;
+ *ipv4 = true;
+ result = (struct bpf_sock_tuple *)&iph->saddr;
+ } else if (eth->h_proto == bpf_htons(ETH_P_IPV6)) {
+ struct ipv6hdr *ip6h = (struct ipv6hdr *)(data + sizeof(*eth));
+
+ if (ip6h + 1 > data_end)
+ return NULL;
+ ihl_len = sizeof(*ip6h);
+ proto = ip6h->nexthdr;
+ *ipv4 = false;
+ result = (struct bpf_sock_tuple *)&ip6h->saddr;
+ } else {
+ return (struct bpf_sock_tuple *)data;
+ }
+
+ if (proto != IPPROTO_TCP && proto != IPPROTO_UDP)
+ return NULL;
+
+ *tcp = (proto == IPPROTO_TCP);
+ return result;
+}
+
+static inline int
+handle_udp(struct __sk_buff *skb, struct bpf_sock_tuple *tuple, bool ipv4)
+{
+ struct bpf_sock_tuple ln = {0};
+ struct bpf_sock *sk;
+ const int zero = 0;
+ size_t tuple_len;
+ __be16 dport;
+ int ret;
+
+ tuple_len = ipv4 ? sizeof(tuple->ipv4) : sizeof(tuple->ipv6);
+ if ((void *)tuple + tuple_len > (void *)(long)skb->data_end)
+ return TC_ACT_SHOT;
+
+ sk = bpf_sk_lookup_udp(skb, tuple, tuple_len, BPF_F_CURRENT_NETNS, 0);
+ if (sk)
+ goto assign;
+
+ dport = ipv4 ? tuple->ipv4.dport : tuple->ipv6.dport;
+ if (dport != bpf_htons(4321))
+ return TC_ACT_OK;
+
+ sk = bpf_map_lookup_elem(&server_map, &zero);
+ if (!sk)
+ return TC_ACT_SHOT;
+
+assign:
+ ret = bpf_sk_assign(skb, sk, 0);
+ bpf_sk_release(sk);
+ return ret;
+}
+
+static inline int
+handle_tcp(struct __sk_buff *skb, struct bpf_sock_tuple *tuple, bool ipv4)
+{
+ struct bpf_sock_tuple ln = {0};
+ struct bpf_sock *sk;
+ const int zero = 0;
+ size_t tuple_len;
+ __be16 dport;
+ int ret;
+
+ tuple_len = ipv4 ? sizeof(tuple->ipv4) : sizeof(tuple->ipv6);
+ if ((void *)tuple + tuple_len > (void *)(long)skb->data_end)
+ return TC_ACT_SHOT;
+
+ sk = bpf_skc_lookup_tcp(skb, tuple, tuple_len, BPF_F_CURRENT_NETNS, 0);
+ if (sk) {
+ if (sk->state != BPF_TCP_LISTEN)
+ goto assign;
+ bpf_sk_release(sk);
+ }
+
+ dport = ipv4 ? tuple->ipv4.dport : tuple->ipv6.dport;
+ if (dport != bpf_htons(4321))
+ return TC_ACT_OK;
+
+ sk = bpf_map_lookup_elem(&server_map, &zero);
+ if (!sk)
+ return TC_ACT_SHOT;
+
+ if (sk->state != BPF_TCP_LISTEN) {
+ bpf_sk_release(sk);
+ return TC_ACT_SHOT;
+ }
+
+assign:
+ ret = bpf_sk_assign(skb, sk, 0);
+ bpf_sk_release(sk);
+ return ret;
+}
+
+SEC("classifier/sk_assign_test")
+int bpf_sk_assign_test(struct __sk_buff *skb)
+{
+ struct bpf_sock_tuple *tuple, ln = {0};
+ bool ipv4 = false;
+ bool tcp = false;
+ int tuple_len;
+ int ret = 0;
+
+ tuple = get_tuple(skb, &ipv4, &tcp);
+ if (!tuple)
+ return TC_ACT_SHOT;
+
+ /* Note that the verifier socket return type for bpf_skc_lookup_tcp()
+ * differs from bpf_sk_lookup_udp(), so even though the C-level type is
+ * the same here, if we try to share the implementations they will
+ * fail to verify because we're crossing pointer types.
+ */
+ if (tcp)
+ ret = handle_tcp(skb, tuple, ipv4);
+ else
+ ret = handle_udp(skb, tuple, ipv4);
+
+ return ret == 0 ? TC_ACT_OK : TC_ACT_SHOT;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c b/tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c
index d2b38fa6a5b0..e83d0b48d80c 100644
--- a/tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c
@@ -73,6 +73,7 @@ int bpf_sk_lookup_test0(struct __sk_buff *skb)
tuple_len = ipv4 ? sizeof(tuple->ipv4) : sizeof(tuple->ipv6);
sk = bpf_sk_lookup_tcp(skb, tuple, tuple_len, BPF_F_CURRENT_NETNS, 0);
+ bpf_printk("sk=%d\n", sk ? 1 : 0);
if (sk)
bpf_sk_release(sk);
return sk ? TC_ACT_OK : TC_ACT_UNSPEC;
diff --git a/tools/testing/selftests/bpf/progs/test_skb_ctx.c b/tools/testing/selftests/bpf/progs/test_skb_ctx.c
index 202de3938494..b02ea589ce7e 100644
--- a/tools/testing/selftests/bpf/progs/test_skb_ctx.c
+++ b/tools/testing/selftests/bpf/progs/test_skb_ctx.c
@@ -23,6 +23,8 @@ int process(struct __sk_buff *skb)
return 1;
if (skb->gso_segs != 8)
return 1;
+ if (skb->gso_size != 10)
+ return 1;
return 0;
}
diff --git a/tools/testing/selftests/bpf/progs/test_skb_helpers.c b/tools/testing/selftests/bpf/progs/test_skb_helpers.c
new file mode 100644
index 000000000000..bb3fbf1a29e3
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_skb_helpers.c
@@ -0,0 +1,28 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+#define TEST_COMM_LEN 16
+
+struct {
+ __uint(type, BPF_MAP_TYPE_CGROUP_ARRAY);
+ __uint(max_entries, 1);
+ __type(key, u32);
+ __type(value, u32);
+} cgroup_map SEC(".maps");
+
+char _license[] SEC("license") = "GPL";
+
+SEC("classifier/test_skb_helpers")
+int test_skb_helpers(struct __sk_buff *skb)
+{
+ struct task_struct *task;
+ char comm[TEST_COMM_LEN];
+ __u32 tpid;
+
+ task = (struct task_struct *)bpf_get_current_task();
+ bpf_probe_read_kernel(&tpid , sizeof(tpid), &task->tgid);
+ bpf_probe_read_kernel_str(&comm, sizeof(comm), &task->comm);
+ return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_skmsg_load_helpers.c b/tools/testing/selftests/bpf/progs/test_skmsg_load_helpers.c
new file mode 100644
index 000000000000..45e8fc75a739
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_skmsg_load_helpers.c
@@ -0,0 +1,47 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2020 Isovalent, Inc.
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+
+struct {
+ __uint(type, BPF_MAP_TYPE_SOCKMAP);
+ __uint(max_entries, 2);
+ __type(key, __u32);
+ __type(value, __u64);
+} sock_map SEC(".maps");
+
+struct {
+ __uint(type, BPF_MAP_TYPE_SOCKHASH);
+ __uint(max_entries, 2);
+ __type(key, __u32);
+ __type(value, __u64);
+} sock_hash SEC(".maps");
+
+struct {
+ __uint(type, BPF_MAP_TYPE_SK_STORAGE);
+ __uint(map_flags, BPF_F_NO_PREALLOC);
+ __type(key, __u32);
+ __type(value, __u64);
+} socket_storage SEC(".maps");
+
+SEC("sk_msg")
+int prog_msg_verdict(struct sk_msg_md *msg)
+{
+ struct task_struct *task = (struct task_struct *)bpf_get_current_task();
+ int verdict = SK_PASS;
+ __u32 pid, tpid;
+ __u64 *sk_stg;
+
+ pid = bpf_get_current_pid_tgid() >> 32;
+ sk_stg = bpf_sk_storage_get(&socket_storage, msg->sk, 0, BPF_SK_STORAGE_GET_F_CREATE);
+ if (!sk_stg)
+ return SK_DROP;
+ *sk_stg = pid;
+ bpf_probe_read_kernel(&tpid , sizeof(tpid), &task->tgid);
+ if (pid != tpid)
+ verdict = SK_DROP;
+ bpf_sk_storage_delete(&socket_storage, (void *)msg->sk);
+ return verdict;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_sockmap_kern.h b/tools/testing/selftests/bpf/progs/test_sockmap_kern.h
index 9b4d3a68a91a..057036ca1111 100644
--- a/tools/testing/selftests/bpf/test_sockmap_kern.h
+++ b/tools/testing/selftests/bpf/progs/test_sockmap_kern.h
@@ -79,11 +79,18 @@ struct {
struct {
__uint(type, BPF_MAP_TYPE_ARRAY);
- __uint(max_entries, 1);
+ __uint(max_entries, 2);
__type(key, int);
__type(value, int);
} sock_skb_opts SEC(".maps");
+struct {
+ __uint(type, TEST_MAP_TYPE);
+ __uint(max_entries, 20);
+ __uint(key_size, sizeof(int));
+ __uint(value_size, sizeof(int));
+} tls_sock_map SEC(".maps");
+
SEC("sk_skb1")
int bpf_prog1(struct __sk_buff *skb)
{
@@ -110,8 +117,6 @@ int bpf_prog2(struct __sk_buff *skb)
flags = *f;
}
- bpf_printk("sk_skb2: redirect(%iB) flags=%i\n",
- len, flags);
#ifdef SOCKMAP
return bpf_sk_redirect_map(skb, &sock_map, ret, flags);
#else
@@ -120,6 +125,43 @@ int bpf_prog2(struct __sk_buff *skb)
}
+SEC("sk_skb3")
+int bpf_prog3(struct __sk_buff *skb)
+{
+ const int one = 1;
+ int err, *f, ret = SK_PASS;
+ void *data_end;
+ char *c;
+
+ err = bpf_skb_pull_data(skb, 19);
+ if (err)
+ goto tls_out;
+
+ c = (char *)(long)skb->data;
+ data_end = (void *)(long)skb->data_end;
+
+ if (c + 18 < data_end)
+ memcpy(&c[13], "PASS", 4);
+ f = bpf_map_lookup_elem(&sock_skb_opts, &one);
+ if (f && *f) {
+ __u64 flags = 0;
+
+ ret = 0;
+ flags = *f;
+#ifdef SOCKMAP
+ return bpf_sk_redirect_map(skb, &tls_sock_map, ret, flags);
+#else
+ return bpf_sk_redirect_hash(skb, &tls_sock_map, &ret, flags);
+#endif
+ }
+
+ f = bpf_map_lookup_elem(&sock_skb_opts, &one);
+ if (f && *f)
+ ret = SK_DROP;
+tls_out:
+ return ret;
+}
+
SEC("sockops")
int bpf_sockmap(struct bpf_sock_ops *skops)
{
@@ -143,8 +185,6 @@ int bpf_sockmap(struct bpf_sock_ops *skops)
err = bpf_sock_hash_update(skops, &sock_map, &ret,
BPF_NOEXIST);
#endif
- bpf_printk("passive(%i -> %i) map ctx update err: %d\n",
- lport, bpf_ntohl(rport), err);
}
break;
case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB:
@@ -160,8 +200,6 @@ int bpf_sockmap(struct bpf_sock_ops *skops)
err = bpf_sock_hash_update(skops, &sock_map, &ret,
BPF_NOEXIST);
#endif
- bpf_printk("active(%i -> %i) map ctx update err: %d\n",
- lport, bpf_ntohl(rport), err);
}
break;
default:
@@ -199,72 +237,6 @@ int bpf_prog4(struct sk_msg_md *msg)
}
SEC("sk_msg2")
-int bpf_prog5(struct sk_msg_md *msg)
-{
- int zero = 0, one = 1, two = 2, three = 3, four = 4, five = 5;
- int *start, *end, *start_push, *end_push, *start_pop, *pop;
- int *bytes, len1, len2 = 0, len3, len4;
- int err1 = -1, err2 = -1;
-
- bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
- if (bytes)
- err1 = bpf_msg_apply_bytes(msg, *bytes);
- bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero);
- if (bytes)
- err2 = bpf_msg_cork_bytes(msg, *bytes);
- len1 = (__u64)msg->data_end - (__u64)msg->data;
- start = bpf_map_lookup_elem(&sock_bytes, &zero);
- end = bpf_map_lookup_elem(&sock_bytes, &one);
- if (start && end) {
- int err;
-
- bpf_printk("sk_msg2: pull(%i:%i)\n",
- start ? *start : 0, end ? *end : 0);
- err = bpf_msg_pull_data(msg, *start, *end, 0);
- if (err)
- bpf_printk("sk_msg2: pull_data err %i\n",
- err);
- len2 = (__u64)msg->data_end - (__u64)msg->data;
- bpf_printk("sk_msg2: length update %i->%i\n",
- len1, len2);
- }
-
- start_push = bpf_map_lookup_elem(&sock_bytes, &two);
- end_push = bpf_map_lookup_elem(&sock_bytes, &three);
- if (start_push && end_push) {
- int err;
-
- bpf_printk("sk_msg2: push(%i:%i)\n",
- start_push ? *start_push : 0,
- end_push ? *end_push : 0);
- err = bpf_msg_push_data(msg, *start_push, *end_push, 0);
- if (err)
- bpf_printk("sk_msg2: push_data err %i\n", err);
- len3 = (__u64)msg->data_end - (__u64)msg->data;
- bpf_printk("sk_msg2: length push_update %i->%i\n",
- len2 ? len2 : len1, len3);
- }
- start_pop = bpf_map_lookup_elem(&sock_bytes, &four);
- pop = bpf_map_lookup_elem(&sock_bytes, &five);
- if (start_pop && pop) {
- int err;
-
- bpf_printk("sk_msg2: pop(%i@%i)\n",
- start_pop, pop);
- err = bpf_msg_pop_data(msg, *start_pop, *pop, 0);
- if (err)
- bpf_printk("sk_msg2: pop_data err %i\n", err);
- len4 = (__u64)msg->data_end - (__u64)msg->data;
- bpf_printk("sk_msg2: length pop_data %i->%i\n",
- len1 ? len1 : 0, len4);
- }
-
- bpf_printk("sk_msg2: data length %i err1 %i err2 %i\n",
- len1, err1, err2);
- return SK_PASS;
-}
-
-SEC("sk_msg3")
int bpf_prog6(struct sk_msg_md *msg)
{
int zero = 0, one = 1, two = 2, three = 3, four = 4, five = 5, key = 0;
@@ -305,86 +277,7 @@ int bpf_prog6(struct sk_msg_md *msg)
#endif
}
-SEC("sk_msg4")
-int bpf_prog7(struct sk_msg_md *msg)
-{
- int *bytes, *start, *end, *start_push, *end_push, *start_pop, *pop, *f;
- int zero = 0, one = 1, two = 2, three = 3, four = 4, five = 5;
- int len1, len2 = 0, len3, len4;
- int err1 = 0, err2 = 0, key = 0;
- __u64 flags = 0;
-
- int err;
- bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
- if (bytes)
- err1 = bpf_msg_apply_bytes(msg, *bytes);
- bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero);
- if (bytes)
- err2 = bpf_msg_cork_bytes(msg, *bytes);
- len1 = (__u64)msg->data_end - (__u64)msg->data;
-
- start = bpf_map_lookup_elem(&sock_bytes, &zero);
- end = bpf_map_lookup_elem(&sock_bytes, &one);
- if (start && end) {
- bpf_printk("sk_msg2: pull(%i:%i)\n",
- start ? *start : 0, end ? *end : 0);
- err = bpf_msg_pull_data(msg, *start, *end, 0);
- if (err)
- bpf_printk("sk_msg2: pull_data err %i\n",
- err);
- len2 = (__u64)msg->data_end - (__u64)msg->data;
- bpf_printk("sk_msg2: length update %i->%i\n",
- len1, len2);
- }
-
- start_push = bpf_map_lookup_elem(&sock_bytes, &two);
- end_push = bpf_map_lookup_elem(&sock_bytes, &three);
- if (start_push && end_push) {
- bpf_printk("sk_msg4: push(%i:%i)\n",
- start_push ? *start_push : 0,
- end_push ? *end_push : 0);
- err = bpf_msg_push_data(msg, *start_push, *end_push, 0);
- if (err)
- bpf_printk("sk_msg4: push_data err %i\n",
- err);
- len3 = (__u64)msg->data_end - (__u64)msg->data;
- bpf_printk("sk_msg4: length push_update %i->%i\n",
- len2 ? len2 : len1, len3);
- }
-
- start_pop = bpf_map_lookup_elem(&sock_bytes, &four);
- pop = bpf_map_lookup_elem(&sock_bytes, &five);
- if (start_pop && pop) {
- int err;
-
- bpf_printk("sk_msg4: pop(%i@%i)\n",
- start_pop, pop);
- err = bpf_msg_pop_data(msg, *start_pop, *pop, 0);
- if (err)
- bpf_printk("sk_msg4: pop_data err %i\n", err);
- len4 = (__u64)msg->data_end - (__u64)msg->data;
- bpf_printk("sk_msg4: length pop_data %i->%i\n",
- len1 ? len1 : 0, len4);
- }
-
-
- f = bpf_map_lookup_elem(&sock_redir_flags, &zero);
- if (f && *f) {
- key = 2;
- flags = *f;
- }
- bpf_printk("sk_msg3: redirect(%iB) flags=%i err=%i\n",
- len1, flags, err1 ? err1 : err2);
-#ifdef SOCKMAP
- err = bpf_msg_redirect_map(msg, &sock_map_redir, key, flags);
-#else
- err = bpf_msg_redirect_hash(msg, &sock_map_redir, &key, flags);
-#endif
- bpf_printk("sk_msg3: err %i\n", err);
- return err;
-}
-
-SEC("sk_msg5")
+SEC("sk_msg3")
int bpf_prog8(struct sk_msg_md *msg)
{
void *data_end = (void *)(long) msg->data_end;
@@ -401,7 +294,7 @@ int bpf_prog8(struct sk_msg_md *msg)
}
return SK_PASS;
}
-SEC("sk_msg6")
+SEC("sk_msg4")
int bpf_prog9(struct sk_msg_md *msg)
{
void *data_end = (void *)(long) msg->data_end;
@@ -419,7 +312,7 @@ int bpf_prog9(struct sk_msg_md *msg)
return SK_PASS;
}
-SEC("sk_msg7")
+SEC("sk_msg5")
int bpf_prog10(struct sk_msg_md *msg)
{
int *bytes, *start, *end, *start_push, *end_push, *start_pop, *pop;
@@ -443,7 +336,6 @@ int bpf_prog10(struct sk_msg_md *msg)
pop = bpf_map_lookup_elem(&sock_bytes, &five);
if (start_pop && pop)
bpf_msg_pop_data(msg, *start_pop, *pop, 0);
- bpf_printk("return sk drop\n");
return SK_DROP;
}
diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_listen.c b/tools/testing/selftests/bpf/progs/test_sockmap_listen.c
new file mode 100644
index 000000000000..a3a366c57ce1
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_sockmap_listen.c
@@ -0,0 +1,98 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2020 Cloudflare
+
+#include <errno.h>
+#include <stdbool.h>
+#include <linux/bpf.h>
+
+#include <bpf/bpf_helpers.h>
+
+struct {
+ __uint(type, BPF_MAP_TYPE_SOCKMAP);
+ __uint(max_entries, 2);
+ __type(key, __u32);
+ __type(value, __u64);
+} sock_map SEC(".maps");
+
+struct {
+ __uint(type, BPF_MAP_TYPE_SOCKHASH);
+ __uint(max_entries, 2);
+ __type(key, __u32);
+ __type(value, __u64);
+} sock_hash SEC(".maps");
+
+struct {
+ __uint(type, BPF_MAP_TYPE_ARRAY);
+ __uint(max_entries, 2);
+ __type(key, int);
+ __type(value, unsigned int);
+} verdict_map SEC(".maps");
+
+static volatile bool test_sockmap; /* toggled by user-space */
+
+SEC("sk_skb/stream_parser")
+int prog_skb_parser(struct __sk_buff *skb)
+{
+ return skb->len;
+}
+
+SEC("sk_skb/stream_verdict")
+int prog_skb_verdict(struct __sk_buff *skb)
+{
+ unsigned int *count;
+ __u32 zero = 0;
+ int verdict;
+
+ if (test_sockmap)
+ verdict = bpf_sk_redirect_map(skb, &sock_map, zero, 0);
+ else
+ verdict = bpf_sk_redirect_hash(skb, &sock_hash, &zero, 0);
+
+ count = bpf_map_lookup_elem(&verdict_map, &verdict);
+ if (count)
+ (*count)++;
+
+ return verdict;
+}
+
+SEC("sk_msg")
+int prog_msg_verdict(struct sk_msg_md *msg)
+{
+ unsigned int *count;
+ __u32 zero = 0;
+ int verdict;
+
+ if (test_sockmap)
+ verdict = bpf_msg_redirect_map(msg, &sock_map, zero, 0);
+ else
+ verdict = bpf_msg_redirect_hash(msg, &sock_hash, &zero, 0);
+
+ count = bpf_map_lookup_elem(&verdict_map, &verdict);
+ if (count)
+ (*count)++;
+
+ return verdict;
+}
+
+SEC("sk_reuseport")
+int prog_reuseport(struct sk_reuseport_md *reuse)
+{
+ unsigned int *count;
+ int err, verdict;
+ __u32 zero = 0;
+
+ if (test_sockmap)
+ err = bpf_sk_select_reuseport(reuse, &sock_map, &zero, 0);
+ else
+ err = bpf_sk_select_reuseport(reuse, &sock_hash, &zero, 0);
+ verdict = err ? SK_DROP : SK_PASS;
+
+ count = bpf_map_lookup_elem(&verdict_map, &verdict);
+ if (count)
+ (*count)++;
+
+ return verdict;
+}
+
+int _version SEC("version") = 1;
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_sysctl_prog.c b/tools/testing/selftests/bpf/progs/test_sysctl_prog.c
index 2d0b0b82a78a..50525235380e 100644
--- a/tools/testing/selftests/bpf/progs/test_sysctl_prog.c
+++ b/tools/testing/selftests/bpf/progs/test_sysctl_prog.c
@@ -45,7 +45,7 @@ int sysctl_tcp_mem(struct bpf_sysctl *ctx)
unsigned long tcp_mem[3] = {0, 0, 0};
char value[MAX_VALUE_STR_LEN];
unsigned char i, off = 0;
- int ret;
+ volatile int ret;
if (ctx->write)
return 0;
diff --git a/tools/testing/selftests/bpf/progs/test_trampoline_count.c b/tools/testing/selftests/bpf/progs/test_trampoline_count.c
index e51e6e3a81c2..f030e469d05b 100644
--- a/tools/testing/selftests/bpf/progs/test_trampoline_count.c
+++ b/tools/testing/selftests/bpf/progs/test_trampoline_count.c
@@ -2,7 +2,8 @@
#include <stdbool.h>
#include <stddef.h>
#include <linux/bpf.h>
-#include "bpf_trace_helpers.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
struct task_struct;
diff --git a/tools/testing/selftests/bpf/progs/test_vmlinux.c b/tools/testing/selftests/bpf/progs/test_vmlinux.c
new file mode 100644
index 000000000000..5611b564d3b1
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_vmlinux.c
@@ -0,0 +1,84 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+
+#include "vmlinux.h"
+#include <asm/unistd.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_core_read.h>
+
+#define MY_TV_NSEC 1337
+
+bool tp_called = false;
+bool raw_tp_called = false;
+bool tp_btf_called = false;
+bool kprobe_called = false;
+bool fentry_called = false;
+
+SEC("tp/syscalls/sys_enter_nanosleep")
+int handle__tp(struct trace_event_raw_sys_enter *args)
+{
+ struct __kernel_timespec *ts;
+
+ if (args->id != __NR_nanosleep)
+ return 0;
+
+ ts = (void *)args->args[0];
+ if (BPF_CORE_READ(ts, tv_nsec) != MY_TV_NSEC)
+ return 0;
+
+ tp_called = true;
+ return 0;
+}
+
+SEC("raw_tp/sys_enter")
+int BPF_PROG(handle__raw_tp, struct pt_regs *regs, long id)
+{
+ struct __kernel_timespec *ts;
+
+ if (id != __NR_nanosleep)
+ return 0;
+
+ ts = (void *)PT_REGS_PARM1_CORE(regs);
+ if (BPF_CORE_READ(ts, tv_nsec) != MY_TV_NSEC)
+ return 0;
+
+ raw_tp_called = true;
+ return 0;
+}
+
+SEC("tp_btf/sys_enter")
+int BPF_PROG(handle__tp_btf, struct pt_regs *regs, long id)
+{
+ struct __kernel_timespec *ts;
+
+ if (id != __NR_nanosleep)
+ return 0;
+
+ ts = (void *)PT_REGS_PARM1_CORE(regs);
+ if (BPF_CORE_READ(ts, tv_nsec) != MY_TV_NSEC)
+ return 0;
+
+ tp_btf_called = true;
+ return 0;
+}
+
+SEC("kprobe/hrtimer_nanosleep")
+int BPF_KPROBE(handle__kprobe,
+ ktime_t rqtp, enum hrtimer_mode mode, clockid_t clockid)
+{
+ if (rqtp == MY_TV_NSEC)
+ kprobe_called = true;
+ return 0;
+}
+
+SEC("fentry/hrtimer_nanosleep")
+int BPF_PROG(handle__fentry,
+ ktime_t rqtp, enum hrtimer_mode mode, clockid_t clockid)
+{
+ if (rqtp == MY_TV_NSEC)
+ fentry_called = true;
+ return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c
new file mode 100644
index 000000000000..3d66599eee2e
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c
@@ -0,0 +1,33 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+SEC("xdp_adjust_tail_grow")
+int _xdp_adjust_tail_grow(struct xdp_md *xdp)
+{
+ void *data_end = (void *)(long)xdp->data_end;
+ void *data = (void *)(long)xdp->data;
+ unsigned int data_len;
+ int offset = 0;
+
+ /* Data length determine test case */
+ data_len = data_end - data;
+
+ if (data_len == 54) { /* sizeof(pkt_v4) */
+ offset = 4096; /* test too large offset */
+ } else if (data_len == 74) { /* sizeof(pkt_v6) */
+ offset = 40;
+ } else if (data_len == 64) {
+ offset = 128;
+ } else if (data_len == 128) {
+ offset = 4096 - 256 - 320 - data_len; /* Max tail grow 3520 */
+ } else {
+ return XDP_ABORTED; /* No matching test */
+ }
+
+ if (bpf_xdp_adjust_tail(xdp, offset))
+ return XDP_DROP;
+ return XDP_TX;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_adjust_tail.c b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_shrink.c
index b7fc85769bdc..22065a9cfb25 100644
--- a/tools/testing/selftests/bpf/progs/test_adjust_tail.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_shrink.c
@@ -1,5 +1,5 @@
-/* SPDX-License-Identifier: GPL-2.0
- * Copyright (c) 2018 Facebook
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2018 Facebook
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of version 2 of the GNU General Public
@@ -11,15 +11,15 @@
int _version SEC("version") = 1;
-SEC("xdp_adjust_tail")
-int _xdp_adjust_tail(struct xdp_md *xdp)
+SEC("xdp_adjust_tail_shrink")
+int _xdp_adjust_tail_shrink(struct xdp_md *xdp)
{
void *data_end = (void *)(long)xdp->data_end;
void *data = (void *)(long)xdp->data;
int offset = 0;
- if (data_end - data == 54)
- offset = 256;
+ if (data_end - data == 54) /* sizeof(pkt_v4) */
+ offset = 256; /* shrink too much */
else
offset = 20;
if (bpf_xdp_adjust_tail(xdp, 0 - offset))
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c b/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c
index cb8a04ab7a78..a038e827f850 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c
@@ -1,7 +1,9 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/bpf.h>
+#include <bpf/bpf_tracing.h>
#include <bpf/bpf_helpers.h>
-#include "bpf_trace_helpers.h"
+
+char _license[] SEC("license") = "GPL";
struct net_device {
/* Structure does not need to contain all entries,
@@ -27,16 +29,38 @@ struct xdp_buff {
struct xdp_rxq_info *rxq;
} __attribute__((preserve_access_index));
+struct meta {
+ int ifindex;
+ int pkt_len;
+};
+
+struct {
+ __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
+ __uint(key_size, sizeof(int));
+ __uint(value_size, sizeof(int));
+} perf_buf_map SEC(".maps");
+
__u64 test_result_fentry = 0;
-SEC("fentry/_xdp_tx_iptunnel")
+SEC("fentry/FUNC")
int BPF_PROG(trace_on_entry, struct xdp_buff *xdp)
{
+ struct meta meta;
+ void *data_end = (void *)(long)xdp->data_end;
+ void *data = (void *)(long)xdp->data;
+
+ meta.ifindex = xdp->rxq->dev->ifindex;
+ meta.pkt_len = data_end - data;
+ bpf_xdp_output(xdp, &perf_buf_map,
+ ((__u64) meta.pkt_len << 32) |
+ BPF_F_CURRENT_CPU,
+ &meta, sizeof(meta));
+
test_result_fentry = xdp->rxq->dev->ifindex;
return 0;
}
__u64 test_result_fexit = 0;
-SEC("fexit/_xdp_tx_iptunnel")
+SEC("fexit/FUNC")
int BPF_PROG(trace_on_exit, struct xdp_buff *xdp, int ret)
{
test_result_fexit = ret;
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_devmap_helpers.c b/tools/testing/selftests/bpf/progs/test_xdp_devmap_helpers.c
new file mode 100644
index 000000000000..e5c0f131c8a7
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_xdp_devmap_helpers.c
@@ -0,0 +1,22 @@
+// SPDX-License-Identifier: GPL-2.0
+/* fails to load without expected_attach_type = BPF_XDP_DEVMAP
+ * because of access to egress_ifindex
+ */
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+
+SEC("xdp_dm_log")
+int xdpdm_devlog(struct xdp_md *ctx)
+{
+ char fmt[] = "devmap redirect: dev %u -> dev %u len %u\n";
+ void *data_end = (void *)(long)ctx->data_end;
+ void *data = (void *)(long)ctx->data;
+ unsigned int len = data_end - data;
+
+ bpf_trace_printk(fmt, sizeof(fmt),
+ ctx->ingress_ifindex, ctx->egress_ifindex, len);
+
+ return XDP_PASS;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c b/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c
new file mode 100644
index 000000000000..deef0e050863
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c
@@ -0,0 +1,44 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+
+struct {
+ __uint(type, BPF_MAP_TYPE_DEVMAP);
+ __uint(key_size, sizeof(__u32));
+ __uint(value_size, sizeof(struct bpf_devmap_val));
+ __uint(max_entries, 4);
+} dm_ports SEC(".maps");
+
+SEC("xdp_redir")
+int xdp_redir_prog(struct xdp_md *ctx)
+{
+ return bpf_redirect_map(&dm_ports, 1, 0);
+}
+
+/* invalid program on DEVMAP entry;
+ * SEC name means expected attach type not set
+ */
+SEC("xdp_dummy")
+int xdp_dummy_prog(struct xdp_md *ctx)
+{
+ return XDP_PASS;
+}
+
+/* valid program on DEVMAP entry via SEC name;
+ * has access to egress and ingress ifindex
+ */
+SEC("xdp_devmap")
+int xdp_dummy_dm(struct xdp_md *ctx)
+{
+ char fmt[] = "devmap redirect: dev %u -> dev %u len %u\n";
+ void *data_end = (void *)(long)ctx->data_end;
+ void *data = (void *)(long)ctx->data;
+ unsigned int len = data_end - data;
+
+ bpf_trace_printk(fmt, sizeof(fmt),
+ ctx->ingress_ifindex, ctx->egress_ifindex, len);
+
+ return XDP_PASS;
+}
+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
new file mode 100644
index 000000000000..8b36b6640e7e
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/trigger_bench.c
@@ -0,0 +1,47 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2020 Facebook
+
+#include <linux/bpf.h>
+#include <asm/unistd.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+long hits = 0;
+
+SEC("tp/syscalls/sys_enter_getpgid")
+int bench_trigger_tp(void *ctx)
+{
+ __sync_add_and_fetch(&hits, 1);
+ return 0;
+}
+
+SEC("raw_tp/sys_enter")
+int BPF_PROG(bench_trigger_raw_tp, struct pt_regs *regs, long id)
+{
+ if (id == __NR_getpgid)
+ __sync_add_and_fetch(&hits, 1);
+ return 0;
+}
+
+SEC("kprobe/__x64_sys_getpgid")
+int bench_trigger_kprobe(void *ctx)
+{
+ __sync_add_and_fetch(&hits, 1);
+ return 0;
+}
+
+SEC("fentry/__x64_sys_getpgid")
+int bench_trigger_fentry(void *ctx)
+{
+ __sync_add_and_fetch(&hits, 1);
+ return 0;
+}
+
+SEC("fmod_ret/__x64_sys_getpgid")
+int bench_trigger_fmodret(void *ctx)
+{
+ __sync_add_and_fetch(&hits, 1);
+ return -22;
+}
diff --git a/tools/testing/selftests/bpf/test_bpftool.py b/tools/testing/selftests/bpf/test_bpftool.py
new file mode 100644
index 000000000000..4fed2dc25c0a
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_bpftool.py
@@ -0,0 +1,178 @@
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (c) 2020 SUSE LLC.
+
+import collections
+import functools
+import json
+import os
+import socket
+import subprocess
+import unittest
+
+
+# Add the source tree of bpftool and /usr/local/sbin to PATH
+cur_dir = os.path.dirname(os.path.realpath(__file__))
+bpftool_dir = os.path.abspath(os.path.join(cur_dir, "..", "..", "..", "..",
+ "tools", "bpf", "bpftool"))
+os.environ["PATH"] = bpftool_dir + ":/usr/local/sbin:" + os.environ["PATH"]
+
+
+class IfaceNotFoundError(Exception):
+ pass
+
+
+class UnprivilegedUserError(Exception):
+ pass
+
+
+def _bpftool(args, json=True):
+ _args = ["bpftool"]
+ if json:
+ _args.append("-j")
+ _args.extend(args)
+
+ return subprocess.check_output(_args)
+
+
+def bpftool(args):
+ return _bpftool(args, json=False).decode("utf-8")
+
+
+def bpftool_json(args):
+ res = _bpftool(args)
+ return json.loads(res)
+
+
+def get_default_iface():
+ for iface in socket.if_nameindex():
+ if iface[1] != "lo":
+ return iface[1]
+ raise IfaceNotFoundError("Could not find any network interface to probe")
+
+
+def default_iface(f):
+ @functools.wraps(f)
+ def wrapper(*args, **kwargs):
+ iface = get_default_iface()
+ return f(*args, iface, **kwargs)
+ return wrapper
+
+
+class TestBpftool(unittest.TestCase):
+ @classmethod
+ def setUpClass(cls):
+ if os.getuid() != 0:
+ raise UnprivilegedUserError(
+ "This test suite needs root privileges")
+
+ @default_iface
+ def test_feature_dev_json(self, iface):
+ unexpected_helpers = [
+ "bpf_probe_write_user",
+ "bpf_trace_printk",
+ ]
+ expected_keys = [
+ "syscall_config",
+ "program_types",
+ "map_types",
+ "helpers",
+ "misc",
+ ]
+
+ res = bpftool_json(["feature", "probe", "dev", iface])
+ # Check if the result has all expected keys.
+ self.assertCountEqual(res.keys(), expected_keys)
+ # Check if unexpected helpers are not included in helpers probes
+ # result.
+ for helpers in res["helpers"].values():
+ for unexpected_helper in unexpected_helpers:
+ self.assertNotIn(unexpected_helper, helpers)
+
+ def test_feature_kernel(self):
+ test_cases = [
+ bpftool_json(["feature", "probe", "kernel"]),
+ bpftool_json(["feature", "probe"]),
+ bpftool_json(["feature"]),
+ ]
+ unexpected_helpers = [
+ "bpf_probe_write_user",
+ "bpf_trace_printk",
+ ]
+ expected_keys = [
+ "syscall_config",
+ "system_config",
+ "program_types",
+ "map_types",
+ "helpers",
+ "misc",
+ ]
+
+ for tc in test_cases:
+ # Check if the result has all expected keys.
+ self.assertCountEqual(tc.keys(), expected_keys)
+ # Check if unexpected helpers are not included in helpers probes
+ # result.
+ for helpers in tc["helpers"].values():
+ for unexpected_helper in unexpected_helpers:
+ self.assertNotIn(unexpected_helper, helpers)
+
+ def test_feature_kernel_full(self):
+ test_cases = [
+ bpftool_json(["feature", "probe", "kernel", "full"]),
+ bpftool_json(["feature", "probe", "full"]),
+ ]
+ expected_helpers = [
+ "bpf_probe_write_user",
+ "bpf_trace_printk",
+ ]
+
+ for tc in test_cases:
+ # Check if expected helpers are included at least once in any
+ # helpers list for any program type. Unfortunately we cannot assume
+ # that they will be included in all program types or a specific
+ # subset of programs. It depends on the kernel version and
+ # configuration.
+ found_helpers = False
+
+ for helpers in tc["helpers"].values():
+ if all(expected_helper in helpers
+ for expected_helper in expected_helpers):
+ found_helpers = True
+ break
+
+ self.assertTrue(found_helpers)
+
+ def test_feature_kernel_full_vs_not_full(self):
+ full_res = bpftool_json(["feature", "probe", "full"])
+ not_full_res = bpftool_json(["feature", "probe"])
+ not_full_set = set()
+ full_set = set()
+
+ for helpers in full_res["helpers"].values():
+ for helper in helpers:
+ full_set.add(helper)
+
+ for helpers in not_full_res["helpers"].values():
+ for helper in helpers:
+ not_full_set.add(helper)
+
+ self.assertCountEqual(full_set - not_full_set,
+ {"bpf_probe_write_user", "bpf_trace_printk"})
+ self.assertCountEqual(not_full_set - full_set, set())
+
+ def test_feature_macros(self):
+ expected_patterns = [
+ r"/\*\*\* System call availability \*\*\*/",
+ r"#define HAVE_BPF_SYSCALL",
+ r"/\*\*\* eBPF program types \*\*\*/",
+ r"#define HAVE.*PROG_TYPE",
+ r"/\*\*\* eBPF map types \*\*\*/",
+ r"#define HAVE.*MAP_TYPE",
+ r"/\*\*\* eBPF helper functions \*\*\*/",
+ r"#define HAVE.*HELPER",
+ r"/\*\*\* eBPF misc features \*\*\*/",
+ ]
+
+ res = bpftool(["feature", "probe", "macros"])
+ for pattern in expected_patterns:
+ self.assertRegex(res, pattern)
diff --git a/tools/testing/selftests/bpf/test_bpftool.sh b/tools/testing/selftests/bpf/test_bpftool.sh
new file mode 100755
index 000000000000..66690778e36d
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_bpftool.sh
@@ -0,0 +1,5 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (c) 2020 SUSE LLC.
+
+python3 -m unittest -v test_bpftool.TestBpftool
diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c
index 8da77cda5f4a..305fae8f80a9 100644
--- a/tools/testing/selftests/bpf/test_btf.c
+++ b/tools/testing/selftests/bpf/test_btf.c
@@ -2854,7 +2854,7 @@ static struct btf_raw_test raw_tests[] = {
.value_type_id = 1,
.max_entries = 4,
.btf_load_err = true,
- .err_str = "vlen != 0",
+ .err_str = "Invalid func linkage",
},
{
diff --git a/tools/testing/selftests/bpf/test_current_pid_tgid_new_ns.c b/tools/testing/selftests/bpf/test_current_pid_tgid_new_ns.c
new file mode 100644
index 000000000000..ed253f252cd0
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_current_pid_tgid_new_ns.c
@@ -0,0 +1,159 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Carlos Neira cneirabustos@gmail.com */
+#define _GNU_SOURCE
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <unistd.h>
+#include <sys/syscall.h>
+#include <sched.h>
+#include <sys/wait.h>
+#include <sys/mount.h>
+#include "test_progs.h"
+
+#define CHECK_NEWNS(condition, tag, format...) ({ \
+ int __ret = !!(condition); \
+ if (__ret) { \
+ printf("%s:FAIL:%s ", __func__, tag); \
+ printf(format); \
+ } else { \
+ printf("%s:PASS:%s\n", __func__, tag); \
+ } \
+ __ret; \
+})
+
+struct bss {
+ __u64 dev;
+ __u64 ino;
+ __u64 pid_tgid;
+ __u64 user_pid_tgid;
+};
+
+int main(int argc, char **argv)
+{
+ pid_t pid;
+ int exit_code = 1;
+ struct stat st;
+
+ printf("Testing bpf_get_ns_current_pid_tgid helper in new ns\n");
+
+ if (stat("/proc/self/ns/pid", &st)) {
+ perror("stat failed on /proc/self/ns/pid ns\n");
+ printf("%s:FAILED\n", argv[0]);
+ return exit_code;
+ }
+
+ if (CHECK_NEWNS(unshare(CLONE_NEWPID | CLONE_NEWNS),
+ "unshare CLONE_NEWPID | CLONE_NEWNS", "error errno=%d\n", errno))
+ return exit_code;
+
+ pid = fork();
+ if (pid == -1) {
+ perror("Fork() failed\n");
+ printf("%s:FAILED\n", argv[0]);
+ return exit_code;
+ }
+
+ if (pid > 0) {
+ int status;
+
+ usleep(5);
+ waitpid(pid, &status, 0);
+ return 0;
+ } else {
+
+ pid = fork();
+ if (pid == -1) {
+ perror("Fork() failed\n");
+ printf("%s:FAILED\n", argv[0]);
+ return exit_code;
+ }
+
+ if (pid > 0) {
+ int status;
+ waitpid(pid, &status, 0);
+ return 0;
+ } else {
+ if (CHECK_NEWNS(mount("none", "/proc", NULL, MS_PRIVATE|MS_REC, NULL),
+ "Unmounting proc", "Cannot umount proc! errno=%d\n", errno))
+ return exit_code;
+
+ if (CHECK_NEWNS(mount("proc", "/proc", "proc", MS_NOSUID|MS_NOEXEC|MS_NODEV, NULL),
+ "Mounting proc", "Cannot mount proc! errno=%d\n", errno))
+ return exit_code;
+
+ const char *probe_name = "raw_tracepoint/sys_enter";
+ const char *file = "test_ns_current_pid_tgid.o";
+ struct bpf_link *link = NULL;
+ struct bpf_program *prog;
+ struct bpf_map *bss_map;
+ struct bpf_object *obj;
+ int exit_code = 1;
+ int err, key = 0;
+ struct bss bss;
+ struct stat st;
+ __u64 id;
+
+ obj = bpf_object__open_file(file, NULL);
+ if (CHECK_NEWNS(IS_ERR(obj), "obj_open", "err %ld\n", PTR_ERR(obj)))
+ return exit_code;
+
+ err = bpf_object__load(obj);
+ if (CHECK_NEWNS(err, "obj_load", "err %d errno %d\n", err, errno))
+ goto cleanup;
+
+ bss_map = bpf_object__find_map_by_name(obj, "test_ns_.bss");
+ if (CHECK_NEWNS(!bss_map, "find_bss_map", "failed\n"))
+ goto cleanup;
+
+ prog = bpf_object__find_program_by_title(obj, probe_name);
+ if (CHECK_NEWNS(!prog, "find_prog", "prog '%s' not found\n",
+ probe_name))
+ goto cleanup;
+
+ memset(&bss, 0, sizeof(bss));
+ pid_t tid = syscall(SYS_gettid);
+ pid_t pid = getpid();
+
+ id = (__u64) tid << 32 | pid;
+ bss.user_pid_tgid = id;
+
+ if (CHECK_NEWNS(stat("/proc/self/ns/pid", &st),
+ "stat new ns", "Failed to stat /proc/self/ns/pid errno=%d\n", errno))
+ goto cleanup;
+
+ bss.dev = st.st_dev;
+ bss.ino = st.st_ino;
+
+ err = bpf_map_update_elem(bpf_map__fd(bss_map), &key, &bss, 0);
+ if (CHECK_NEWNS(err, "setting_bss", "failed to set bss : %d\n", err))
+ goto cleanup;
+
+ link = bpf_program__attach_raw_tracepoint(prog, "sys_enter");
+ if (CHECK_NEWNS(IS_ERR(link), "attach_raw_tp", "err %ld\n",
+ PTR_ERR(link))) {
+ link = NULL;
+ goto cleanup;
+ }
+
+ /* trigger some syscalls */
+ usleep(1);
+
+ err = bpf_map_lookup_elem(bpf_map__fd(bss_map), &key, &bss);
+ if (CHECK_NEWNS(err, "set_bss", "failed to get bss : %d\n", err))
+ goto cleanup;
+
+ if (CHECK_NEWNS(id != bss.pid_tgid, "Compare user pid/tgid vs. bpf pid/tgid",
+ "User pid/tgid %llu BPF pid/tgid %llu\n", id, bss.pid_tgid))
+ goto cleanup;
+
+ exit_code = 0;
+ printf("%s:PASS\n", argv[0]);
+cleanup:
+ if (!link) {
+ bpf_link__destroy(link);
+ link = NULL;
+ }
+ bpf_object__close(obj);
+ }
+ }
+}
diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c
index 02eae1e864c2..6a12a0e01e07 100644
--- a/tools/testing/selftests/bpf/test_maps.c
+++ b/tools/testing/selftests/bpf/test_maps.c
@@ -756,11 +756,7 @@ static void test_sockmap(unsigned int tasks, void *data)
/* Test update without programs */
for (i = 0; i < 6; i++) {
err = bpf_map_update_elem(fd, &i, &sfd[i], BPF_ANY);
- if (i < 2 && !err) {
- printf("Allowed update sockmap '%i:%i' not in ESTABLISHED\n",
- i, sfd[i]);
- goto out_sockmap;
- } else if (i >= 2 && err) {
+ if (err) {
printf("Failed noprog update sockmap '%i:%i'\n",
i, sfd[i]);
goto out_sockmap;
@@ -1398,23 +1394,25 @@ static void test_map_rdonly(void)
key = 1;
value = 1234;
- /* Insert key=1 element. */
+ /* Try to insert key=1 element. */
assert(bpf_map_update_elem(fd, &key, &value, BPF_ANY) == -1 &&
errno == EPERM);
- /* Check that key=2 is not found. */
+ /* Check that key=1 is not found. */
assert(bpf_map_lookup_elem(fd, &key, &value) == -1 && errno == ENOENT);
assert(bpf_map_get_next_key(fd, &key, &value) == -1 && errno == ENOENT);
+
+ close(fd);
}
-static void test_map_wronly(void)
+static void test_map_wronly_hash(void)
{
int fd, key = 0, value = 0;
fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value),
MAP_SIZE, map_flags | BPF_F_WRONLY);
if (fd < 0) {
- printf("Failed to create map for read only test '%s'!\n",
+ printf("Failed to create map for write only test '%s'!\n",
strerror(errno));
exit(1);
}
@@ -1424,9 +1422,49 @@ static void test_map_wronly(void)
/* Insert key=1 element. */
assert(bpf_map_update_elem(fd, &key, &value, BPF_ANY) == 0);
- /* Check that key=2 is not found. */
+ /* Check that reading elements and keys from the map is not allowed. */
assert(bpf_map_lookup_elem(fd, &key, &value) == -1 && errno == EPERM);
assert(bpf_map_get_next_key(fd, &key, &value) == -1 && errno == EPERM);
+
+ close(fd);
+}
+
+static void test_map_wronly_stack_or_queue(enum bpf_map_type map_type)
+{
+ int fd, value = 0;
+
+ assert(map_type == BPF_MAP_TYPE_QUEUE ||
+ map_type == BPF_MAP_TYPE_STACK);
+ fd = bpf_create_map(map_type, 0, sizeof(value), MAP_SIZE,
+ map_flags | BPF_F_WRONLY);
+ /* Stack/Queue maps do not support BPF_F_NO_PREALLOC */
+ if (map_flags & BPF_F_NO_PREALLOC) {
+ assert(fd < 0 && errno == EINVAL);
+ return;
+ }
+ if (fd < 0) {
+ printf("Failed to create map '%s'!\n", strerror(errno));
+ exit(1);
+ }
+
+ value = 1234;
+ assert(bpf_map_update_elem(fd, NULL, &value, BPF_ANY) == 0);
+
+ /* Peek element should fail */
+ assert(bpf_map_lookup_elem(fd, NULL, &value) == -1 && errno == EPERM);
+
+ /* Pop element should fail */
+ assert(bpf_map_lookup_and_delete_elem(fd, NULL, &value) == -1 &&
+ errno == EPERM);
+
+ close(fd);
+}
+
+static void test_map_wronly(void)
+{
+ test_map_wronly_hash();
+ test_map_wronly_stack_or_queue(BPF_MAP_TYPE_STACK);
+ test_map_wronly_stack_or_queue(BPF_MAP_TYPE_QUEUE);
}
static void prepare_reuseport_grp(int type, int map_fd, size_t map_elem_size,
diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index bab1e6f1d8f1..54fa5fa688ce 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -1,11 +1,16 @@
// SPDX-License-Identifier: GPL-2.0-only
/* Copyright (c) 2017 Facebook
*/
+#define _GNU_SOURCE
#include "test_progs.h"
#include "cgroup_helpers.h"
#include "bpf_rlimit.h"
#include <argp.h>
+#include <pthread.h>
+#include <sched.h>
+#include <signal.h>
#include <string.h>
+#include <execinfo.h> /* backtrace */
/* defined in test_progs.h */
struct test_env env = {};
@@ -27,6 +32,20 @@ struct prog_test_def {
int old_error_cnt;
};
+/* Override C runtime library's usleep() implementation to ensure nanosleep()
+ * is always called. Usleep is frequently used in selftests as a way to
+ * trigger kprobe and tracepoints.
+ */
+int usleep(useconds_t usec)
+{
+ struct timespec ts = {
+ .tv_sec = usec / 1000000,
+ .tv_nsec = (usec % 1000000) * 1000,
+ };
+
+ return syscall(__NR_nanosleep, &ts, NULL);
+}
+
static bool should_run(struct test_selector *sel, int num, const char *name)
{
int i;
@@ -74,6 +93,34 @@ static void skip_account(void)
}
}
+static void stdio_restore(void);
+
+/* A bunch of tests set custom affinity per-thread and/or per-process. Reset
+ * it after each test/sub-test.
+ */
+static void reset_affinity() {
+
+ cpu_set_t cpuset;
+ int i, err;
+
+ CPU_ZERO(&cpuset);
+ for (i = 0; i < env.nr_cpus; i++)
+ CPU_SET(i, &cpuset);
+
+ err = sched_setaffinity(0, sizeof(cpuset), &cpuset);
+ if (err < 0) {
+ stdio_restore();
+ fprintf(stderr, "Failed to reset process affinity: %d!\n", err);
+ exit(-1);
+ }
+ err = pthread_setaffinity_np(pthread_self(), sizeof(cpuset), &cpuset);
+ if (err < 0) {
+ stdio_restore();
+ fprintf(stderr, "Failed to reset thread affinity: %d!\n", err);
+ exit(-1);
+ }
+}
+
void test__end_subtest()
{
struct prog_test_def *test = env.test;
@@ -91,6 +138,8 @@ void test__end_subtest()
test->test_num, test->subtest_num,
test->subtest_name, sub_error_cnt ? "FAIL" : "OK");
+ reset_affinity();
+
free(test->subtest_name);
test->subtest_name = NULL;
}
@@ -173,30 +222,13 @@ int test__join_cgroup(const char *path)
return fd;
}
-struct ipv4_packet pkt_v4 = {
- .eth.h_proto = __bpf_constant_htons(ETH_P_IP),
- .iph.ihl = 5,
- .iph.protocol = IPPROTO_TCP,
- .iph.tot_len = __bpf_constant_htons(MAGIC_BYTES),
- .tcp.urg_ptr = 123,
- .tcp.doff = 5,
-};
-
-struct ipv6_packet pkt_v6 = {
- .eth.h_proto = __bpf_constant_htons(ETH_P_IPV6),
- .iph.nexthdr = IPPROTO_TCP,
- .iph.payload_len = __bpf_constant_htons(MAGIC_BYTES),
- .tcp.urg_ptr = 123,
- .tcp.doff = 5,
-};
-
int bpf_find_map(const char *test, struct bpf_object *obj, const char *name)
{
struct bpf_map *map;
map = bpf_object__find_map_by_name(obj, name);
if (!map) {
- printf("%s:FAIL:map '%s' not found\n", test, name);
+ fprintf(stdout, "%s:FAIL:map '%s' not found\n", test, name);
test__fail();
return -1;
}
@@ -302,25 +334,13 @@ int extract_build_id(char *build_id, size_t size)
len = size;
memcpy(build_id, line, len);
build_id[len] = '\0';
+ free(line);
return 0;
err:
fclose(fp);
return -1;
}
-void *spin_lock_thread(void *arg)
-{
- __u32 duration, retval;
- int err, prog_fd = *(u32 *) arg;
-
- err = bpf_prog_test_run(prog_fd, 10000, &pkt_v4, sizeof(pkt_v4),
- NULL, NULL, &retval, &duration);
- CHECK(err || retval, "",
- "err %d errno %d retval %d duration %d\n",
- err, errno, retval, duration);
- pthread_exit(arg);
-}
-
/* extern declarations for test funcs */
#define DEFINE_TEST(name) extern void test_##name(void);
#include <prog_tests/tests.h>
@@ -367,10 +387,22 @@ static int libbpf_print_fn(enum libbpf_print_level level,
{
if (env.verbosity < VERBOSE_VERY && level == LIBBPF_DEBUG)
return 0;
- vprintf(format, args);
+ vfprintf(stdout, format, args);
return 0;
}
+static void free_str_set(const struct str_set *set)
+{
+ int i;
+
+ if (!set)
+ return;
+
+ for (i = 0; i < set->cnt; i++)
+ free((void *)set->strs[i]);
+ free(set->strs);
+}
+
static int parse_str_list(const char *s, struct str_set *set)
{
char *input, *state = NULL, *next, **tmp, **strs = NULL;
@@ -406,66 +438,6 @@ err:
return -ENOMEM;
}
-int parse_num_list(const char *s, struct test_selector *sel)
-{
- int i, set_len = 0, num, start = 0, end = -1;
- bool *set = NULL, *tmp, parsing_end = false;
- char *next;
-
- while (s[0]) {
- errno = 0;
- num = strtol(s, &next, 10);
- if (errno)
- return -errno;
-
- if (parsing_end)
- end = num;
- else
- start = num;
-
- if (!parsing_end && *next == '-') {
- s = next + 1;
- parsing_end = true;
- continue;
- } else if (*next == ',') {
- parsing_end = false;
- s = next + 1;
- end = num;
- } else if (*next == '\0') {
- parsing_end = false;
- s = next;
- end = num;
- } else {
- return -EINVAL;
- }
-
- if (start > end)
- return -EINVAL;
-
- if (end + 1 > set_len) {
- set_len = end + 1;
- tmp = realloc(set, set_len);
- if (!tmp) {
- free(set);
- return -ENOMEM;
- }
- set = tmp;
- }
- for (i = start; i <= end; i++) {
- set[i] = true;
- }
-
- }
-
- if (!set)
- return -EINVAL;
-
- sel->num_set = set;
- sel->num_set_len = set_len;
-
- return 0;
-}
-
extern int extra_prog_load_log_flags;
static error_t parse_arg(int key, char *arg, struct argp_state *state)
@@ -479,13 +451,15 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state)
if (subtest_str) {
*subtest_str = '\0';
if (parse_num_list(subtest_str + 1,
- &env->subtest_selector)) {
+ &env->subtest_selector.num_set,
+ &env->subtest_selector.num_set_len)) {
fprintf(stderr,
"Failed to parse subtest numbers.\n");
return -EINVAL;
}
}
- if (parse_num_list(arg, &env->test_selector)) {
+ if (parse_num_list(arg, &env->test_selector.num_set,
+ &env->test_selector.num_set_len)) {
fprintf(stderr, "Failed to parse test numbers.\n");
return -EINVAL;
}
@@ -613,10 +587,27 @@ int cd_flavor_subdir(const char *exec_name)
if (!flavor)
return 0;
flavor++;
- printf("Switching to flavor '%s' subdirectory...\n", flavor);
+ fprintf(stdout, "Switching to flavor '%s' subdirectory...\n", flavor);
return chdir(flavor);
}
+#define MAX_BACKTRACE_SZ 128
+void crash_handler(int signum)
+{
+ void *bt[MAX_BACKTRACE_SZ];
+ size_t sz;
+
+ sz = backtrace(bt, ARRAY_SIZE(bt));
+
+ if (env.test)
+ dump_test_log(env.test, true);
+ if (env.stdout)
+ stdio_restore();
+
+ fprintf(stderr, "Caught signal #%d!\nStack trace:\n", signum);
+ backtrace_symbols_fd(bt, sz, STDERR_FILENO);
+}
+
int main(int argc, char **argv)
{
static const struct argp argp = {
@@ -624,8 +615,14 @@ int main(int argc, char **argv)
.parser = parse_arg,
.doc = argp_program_doc,
};
+ struct sigaction sigact = {
+ .sa_handler = crash_handler,
+ .sa_flags = SA_RESETHAND,
+ };
int err, i;
+ sigaction(SIGSEGV, &sigact, NULL);
+
err = argp_parse(&argp, argc, argv, 0, NULL, &env);
if (err)
return err;
@@ -639,6 +636,12 @@ int main(int argc, char **argv)
srand(time(NULL));
env.jit_enabled = is_jit_enabled();
+ env.nr_cpus = libbpf_num_possible_cpus();
+ if (env.nr_cpus < 0) {
+ fprintf(stderr, "Failed to get number of CPUs: %d!\n",
+ env.nr_cpus);
+ return -1;
+ }
stdio_hijack();
for (i = 0; i < prog_test_cnt; i++) {
@@ -669,18 +672,19 @@ int main(int argc, char **argv)
test->test_num, test->test_name,
test->error_cnt ? "FAIL" : "OK");
+ reset_affinity();
if (test->need_cgroup_cleanup)
cleanup_cgroup_environment();
}
stdio_restore();
- printf("Summary: %d/%d PASSED, %d SKIPPED, %d FAILED\n",
- env.succ_cnt, env.sub_succ_cnt, env.skip_cnt, env.fail_cnt);
+ fprintf(stdout, "Summary: %d/%d PASSED, %d SKIPPED, %d FAILED\n",
+ env.succ_cnt, env.sub_succ_cnt, env.skip_cnt, env.fail_cnt);
- free(env.test_selector.blacklist.strs);
- free(env.test_selector.whitelist.strs);
+ free_str_set(&env.test_selector.blacklist);
+ free_str_set(&env.test_selector.whitelist);
free(env.test_selector.num_set);
- free(env.subtest_selector.blacklist.strs);
- free(env.subtest_selector.whitelist.strs);
+ free_str_set(&env.subtest_selector.blacklist);
+ free_str_set(&env.subtest_selector.whitelist);
free(env.subtest_selector.num_set);
return env.fail_cnt ? EXIT_FAILURE : EXIT_SUCCESS;
diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h
index bcfa9ef23fda..f4503c926aca 100644
--- a/tools/testing/selftests/bpf/test_progs.h
+++ b/tools/testing/selftests/bpf/test_progs.h
@@ -37,6 +37,7 @@ typedef __u16 __sum16;
#include "bpf_util.h"
#include <bpf/bpf_endian.h>
#include "trace_helpers.h"
+#include "testing_helpers.h"
#include "flow_dissector_load.h"
enum verbosity {
@@ -71,6 +72,7 @@ struct test_env {
FILE *stderr;
char *log_buf;
size_t log_cnt;
+ int nr_cpus;
int succ_cnt; /* successful tests */
int sub_succ_cnt; /* successful sub-tests */
@@ -86,33 +88,22 @@ extern void test__skip(void);
extern void test__fail(void);
extern int test__join_cgroup(const char *path);
-#define MAGIC_BYTES 123
-
-/* ipv4 test vector */
-struct ipv4_packet {
- struct ethhdr eth;
- struct iphdr iph;
- struct tcphdr tcp;
-} __packed;
-extern struct ipv4_packet pkt_v4;
-
-/* ipv6 test vector */
-struct ipv6_packet {
- struct ethhdr eth;
- struct ipv6hdr iph;
- struct tcphdr tcp;
-} __packed;
-extern struct ipv6_packet pkt_v6;
+#define PRINT_FAIL(format...) \
+ ({ \
+ test__fail(); \
+ fprintf(stdout, "%s:FAIL:%d ", __func__, __LINE__); \
+ fprintf(stdout, ##format); \
+ })
#define _CHECK(condition, tag, duration, format...) ({ \
int __ret = !!(condition); \
int __save_errno = errno; \
if (__ret) { \
test__fail(); \
- printf("%s:FAIL:%s ", __func__, tag); \
- printf(format); \
+ fprintf(stdout, "%s:FAIL:%s ", __func__, tag); \
+ fprintf(stdout, ##format); \
} else { \
- printf("%s:PASS:%s %d nsec\n", \
+ fprintf(stdout, "%s:PASS:%s %d nsec\n", \
__func__, tag, duration); \
} \
errno = __save_errno; \
@@ -124,7 +115,7 @@ extern struct ipv6_packet pkt_v6;
int __save_errno = errno; \
if (__ret) { \
test__fail(); \
- printf("%s:FAIL:%d\n", __func__, __LINE__); \
+ fprintf(stdout, "%s:FAIL:%d\n", __func__, __LINE__); \
} \
errno = __save_errno; \
__ret; \
@@ -135,10 +126,6 @@ extern struct ipv6_packet pkt_v6;
#define CHECK_ATTR(condition, tag, format...) \
_CHECK(condition, tag, tattr.duration, format)
-#define MAGIC_VAL 0x1234
-#define NUM_ITER 100000
-#define VIP_NUM 5
-
static inline __u64 ptr_to_u64(const void *ptr)
{
return (__u64) (unsigned long) ptr;
@@ -148,7 +135,6 @@ int bpf_find_map(const char *test, struct bpf_object *obj, const char *name);
int compare_map_keys(int map1_fd, int map2_fd);
int compare_stack_ips(int smap_fd, int amap_fd, int stack_trace_len);
int extract_build_id(char *build_id, size_t size);
-void *spin_lock_thread(void *arg);
#ifdef __x86_64__
#define SYS_NANOSLEEP_KPROBE_NAME "__x64_sys_nanosleep"
diff --git a/tools/testing/selftests/bpf/test_sock_addr.c b/tools/testing/selftests/bpf/test_sock_addr.c
index 61fd95b89af8..0358814c67dc 100644
--- a/tools/testing/selftests/bpf/test_sock_addr.c
+++ b/tools/testing/selftests/bpf/test_sock_addr.c
@@ -677,7 +677,7 @@ static int bind4_prog_load(const struct sock_addr_test *test)
uint8_t u4_addr8[4];
uint16_t u4_addr16[2];
uint32_t u4_addr32;
- } ip4;
+ } ip4, port;
struct sockaddr_in addr4_rw;
if (inet_pton(AF_INET, SERV4_IP, (void *)&ip4) != 1) {
@@ -685,6 +685,8 @@ static int bind4_prog_load(const struct sock_addr_test *test)
return -1;
}
+ port.u4_addr32 = htons(SERV4_PORT);
+
if (mk_sockaddr(AF_INET, SERV4_REWRITE_IP, SERV4_REWRITE_PORT,
(struct sockaddr *)&addr4_rw, sizeof(addr4_rw)) == -1)
return -1;
@@ -696,49 +698,65 @@ static int bind4_prog_load(const struct sock_addr_test *test)
/* if (sk.family == AF_INET && */
BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
offsetof(struct bpf_sock_addr, family)),
- BPF_JMP_IMM(BPF_JNE, BPF_REG_7, AF_INET, 24),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_7, AF_INET, 32),
/* (sk.type == SOCK_DGRAM || sk.type == SOCK_STREAM) && */
BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
offsetof(struct bpf_sock_addr, type)),
BPF_JMP_IMM(BPF_JNE, BPF_REG_7, SOCK_DGRAM, 1),
BPF_JMP_A(1),
- BPF_JMP_IMM(BPF_JNE, BPF_REG_7, SOCK_STREAM, 20),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_7, SOCK_STREAM, 28),
/* 1st_byte_of_user_ip4 == expected && */
BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_6,
offsetof(struct bpf_sock_addr, user_ip4)),
- BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr8[0], 18),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr8[0], 26),
/* 2nd_byte_of_user_ip4 == expected && */
BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_6,
offsetof(struct bpf_sock_addr, user_ip4) + 1),
- BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr8[1], 16),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr8[1], 24),
/* 3rd_byte_of_user_ip4 == expected && */
BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_6,
offsetof(struct bpf_sock_addr, user_ip4) + 2),
- BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr8[2], 14),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr8[2], 22),
/* 4th_byte_of_user_ip4 == expected && */
BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_6,
offsetof(struct bpf_sock_addr, user_ip4) + 3),
- BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr8[3], 12),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr8[3], 20),
/* 1st_half_of_user_ip4 == expected && */
BPF_LDX_MEM(BPF_H, BPF_REG_7, BPF_REG_6,
offsetof(struct bpf_sock_addr, user_ip4)),
- BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr16[0], 10),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr16[0], 18),
/* 2nd_half_of_user_ip4 == expected && */
BPF_LDX_MEM(BPF_H, BPF_REG_7, BPF_REG_6,
offsetof(struct bpf_sock_addr, user_ip4) + 2),
- BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr16[1], 8),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr16[1], 16),
- /* whole_user_ip4 == expected) { */
+ /* whole_user_ip4 == expected && */
BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
offsetof(struct bpf_sock_addr, user_ip4)),
BPF_LD_IMM64(BPF_REG_8, ip4.u4_addr32), /* See [2]. */
+ BPF_JMP_REG(BPF_JNE, BPF_REG_7, BPF_REG_8, 12),
+
+ /* 1st_byte_of_user_port == expected && */
+ BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_6,
+ offsetof(struct bpf_sock_addr, user_port)),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_7, port.u4_addr8[0], 10),
+
+ /* 1st_half_of_user_port == expected && */
+ BPF_LDX_MEM(BPF_H, BPF_REG_7, BPF_REG_6,
+ offsetof(struct bpf_sock_addr, user_port)),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_7, port.u4_addr16[0], 8),
+
+ /* user_port == expected) { */
+ BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
+ offsetof(struct bpf_sock_addr, user_port)),
+ BPF_LD_IMM64(BPF_REG_8, port.u4_addr32), /* See [2]. */
BPF_JMP_REG(BPF_JNE, BPF_REG_7, BPF_REG_8, 4),
/* user_ip4 = addr4_rw.sin_addr */
diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c
index 779e11da979c..37695fc8096a 100644
--- a/tools/testing/selftests/bpf/test_sockmap.c
+++ b/tools/testing/selftests/bpf/test_sockmap.c
@@ -54,7 +54,7 @@ static void running_handler(int a);
#define S1_PORT 10000
#define S2_PORT 10001
-#define BPF_SOCKMAP_FILENAME "test_sockmap_kern.o"
+#define BPF_SOCKMAP_FILENAME "test_sockmap_kern.o"
#define BPF_SOCKHASH_FILENAME "test_sockhash_kern.o"
#define CG_PATH "/sockmap"
@@ -63,14 +63,12 @@ int s1, s2, c1, c2, p1, p2;
int test_cnt;
int passed;
int failed;
-int map_fd[8];
-struct bpf_map *maps[8];
+int map_fd[9];
+struct bpf_map *maps[9];
int prog_fd[11];
int txmsg_pass;
-int txmsg_noisy;
int txmsg_redir;
-int txmsg_redir_noisy;
int txmsg_drop;
int txmsg_apply;
int txmsg_cork;
@@ -81,7 +79,10 @@ int txmsg_end_push;
int txmsg_start_pop;
int txmsg_pop;
int txmsg_ingress;
-int txmsg_skb;
+int txmsg_redir_skb;
+int txmsg_ktls_skb;
+int txmsg_ktls_skb_drop;
+int txmsg_ktls_skb_redir;
int ktls;
int peek_flag;
@@ -89,15 +90,13 @@ static const struct option long_options[] = {
{"help", no_argument, NULL, 'h' },
{"cgroup", required_argument, NULL, 'c' },
{"rate", required_argument, NULL, 'r' },
- {"verbose", no_argument, NULL, 'v' },
+ {"verbose", optional_argument, NULL, 'v' },
{"iov_count", required_argument, NULL, 'i' },
{"length", required_argument, NULL, 'l' },
{"test", required_argument, NULL, 't' },
{"data_test", no_argument, NULL, 'd' },
{"txmsg", no_argument, &txmsg_pass, 1 },
- {"txmsg_noisy", no_argument, &txmsg_noisy, 1 },
{"txmsg_redir", no_argument, &txmsg_redir, 1 },
- {"txmsg_redir_noisy", no_argument, &txmsg_redir_noisy, 1},
{"txmsg_drop", no_argument, &txmsg_drop, 1 },
{"txmsg_apply", required_argument, NULL, 'a'},
{"txmsg_cork", required_argument, NULL, 'k'},
@@ -108,12 +107,108 @@ static const struct option long_options[] = {
{"txmsg_start_pop", required_argument, NULL, 'w'},
{"txmsg_pop", required_argument, NULL, 'x'},
{"txmsg_ingress", no_argument, &txmsg_ingress, 1 },
- {"txmsg_skb", no_argument, &txmsg_skb, 1 },
+ {"txmsg_redir_skb", no_argument, &txmsg_redir_skb, 1 },
{"ktls", no_argument, &ktls, 1 },
{"peek", no_argument, &peek_flag, 1 },
+ {"whitelist", required_argument, NULL, 'n' },
+ {"blacklist", required_argument, NULL, 'b' },
{0, 0, NULL, 0 }
};
+struct test_env {
+ const char *type;
+ const char *subtest;
+ const char *prepend;
+
+ int test_num;
+ int subtest_num;
+
+ int succ_cnt;
+ int fail_cnt;
+ int fail_last;
+};
+
+struct test_env env;
+
+struct sockmap_options {
+ int verbose;
+ bool base;
+ bool sendpage;
+ bool data_test;
+ bool drop_expected;
+ int iov_count;
+ int iov_length;
+ int rate;
+ char *map;
+ char *whitelist;
+ char *blacklist;
+ char *prepend;
+};
+
+struct _test {
+ char *title;
+ void (*tester)(int cg_fd, struct sockmap_options *opt);
+};
+
+static void test_start(void)
+{
+ env.subtest_num++;
+}
+
+static void test_fail(void)
+{
+ env.fail_cnt++;
+}
+
+static void test_pass(void)
+{
+ env.succ_cnt++;
+}
+
+static void test_reset(void)
+{
+ txmsg_start = txmsg_end = 0;
+ txmsg_start_pop = txmsg_pop = 0;
+ txmsg_start_push = txmsg_end_push = 0;
+ txmsg_pass = txmsg_drop = txmsg_redir = 0;
+ txmsg_apply = txmsg_cork = 0;
+ txmsg_ingress = txmsg_redir_skb = 0;
+ txmsg_ktls_skb = txmsg_ktls_skb_drop = txmsg_ktls_skb_redir = 0;
+}
+
+static int test_start_subtest(const struct _test *t, struct sockmap_options *o)
+{
+ env.type = o->map;
+ env.subtest = t->title;
+ env.prepend = o->prepend;
+ env.test_num++;
+ env.subtest_num = 0;
+ env.fail_last = env.fail_cnt;
+ test_reset();
+ return 0;
+}
+
+static void test_end_subtest(void)
+{
+ int error = env.fail_cnt - env.fail_last;
+ int type = strcmp(env.type, BPF_SOCKMAP_FILENAME);
+
+ if (!error)
+ test_pass();
+
+ fprintf(stdout, "#%2d/%2d %8s:%s:%s:%s\n",
+ env.test_num, env.subtest_num,
+ !type ? "sockmap" : "sockhash",
+ env.prepend ? : "",
+ env.subtest, error ? "FAIL" : "OK");
+}
+
+static void test_print_results(void)
+{
+ fprintf(stdout, "Pass: %d Fail: %d\n",
+ env.succ_cnt, env.fail_cnt);
+}
+
static void usage(char *argv[])
{
int i;
@@ -296,7 +391,7 @@ static int sockmap_init_sockets(int verbose)
return errno;
}
- if (verbose) {
+ if (verbose > 1) {
printf("connected sockets: c1 <-> p1, c2 <-> p2\n");
printf("cgroups binding: c1(%i) <-> s1(%i) - - - c2(%i) <-> s2(%i)\n",
c1, s1, c2, s2);
@@ -311,17 +406,6 @@ struct msg_stats {
struct timespec end;
};
-struct sockmap_options {
- int verbose;
- bool base;
- bool sendpage;
- bool data_test;
- bool drop_expected;
- int iov_count;
- int iov_length;
- int rate;
-};
-
static int msg_loop_sendpage(int fd, int iov_length, int cnt,
struct msg_stats *s,
struct sockmap_options *opt)
@@ -345,14 +429,18 @@ static int msg_loop_sendpage(int fd, int iov_length, int cnt,
clock_gettime(CLOCK_MONOTONIC, &s->start);
for (i = 0; i < cnt; i++) {
- int sent = sendfile(fd, fp, NULL, iov_length);
+ int sent;
+
+ errno = 0;
+ sent = sendfile(fd, fp, NULL, iov_length);
if (!drop && sent < 0) {
- perror("send loop error");
+ perror("sendpage loop error");
fclose(file);
return sent;
} else if (drop && sent >= 0) {
- printf("sendpage loop error expected: %i\n", sent);
+ printf("sendpage loop error expected: %i errno %i\n",
+ sent, errno);
fclose(file);
return -EIO;
}
@@ -418,14 +506,41 @@ unwind_iov:
static int msg_verify_data(struct msghdr *msg, int size, int chunk_sz)
{
- int i, j, bytes_cnt = 0;
+ int i, j = 0, bytes_cnt = 0;
unsigned char k = 0;
for (i = 0; i < msg->msg_iovlen; i++) {
unsigned char *d = msg->msg_iov[i].iov_base;
- for (j = 0;
- j < msg->msg_iov[i].iov_len && size; j++) {
+ /* Special case test for skb ingress + ktls */
+ if (i == 0 && txmsg_ktls_skb) {
+ if (msg->msg_iov[i].iov_len < 4)
+ return -EIO;
+ if (txmsg_ktls_skb_redir) {
+ if (memcmp(&d[13], "PASS", 4) != 0) {
+ fprintf(stderr,
+ "detected redirect ktls_skb data error with skb ingress update @iov[%i]:%i \"%02x %02x %02x %02x\" != \"PASS\"\n", i, 0, d[13], d[14], d[15], d[16]);
+ return -EIO;
+ }
+ d[13] = 0;
+ d[14] = 1;
+ d[15] = 2;
+ d[16] = 3;
+ j = 13;
+ } else if (txmsg_ktls_skb) {
+ if (memcmp(d, "PASS", 4) != 0) {
+ fprintf(stderr,
+ "detected ktls_skb data error with skb ingress update @iov[%i]:%i \"%02x %02x %02x %02x\" != \"PASS\"\n", i, 0, d[0], d[1], d[2], d[3]);
+ return -EIO;
+ }
+ d[0] = 0;
+ d[1] = 1;
+ d[2] = 2;
+ d[3] = 3;
+ }
+ }
+
+ for (; j < msg->msg_iov[i].iov_len && size; j++) {
if (d[j] != k++) {
fprintf(stderr,
"detected data corruption @iov[%i]:%i %02x != %02x, %02x ?= %02x\n",
@@ -464,13 +579,18 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
if (tx) {
clock_gettime(CLOCK_MONOTONIC, &s->start);
for (i = 0; i < cnt; i++) {
- int sent = sendmsg(fd, &msg, flags);
+ int sent;
+
+ errno = 0;
+ sent = sendmsg(fd, &msg, flags);
if (!drop && sent < 0) {
- perror("send loop error");
+ perror("sendmsg loop error");
goto out_errno;
} else if (drop && sent >= 0) {
- printf("send loop error expected: %i\n", sent);
+ fprintf(stderr,
+ "sendmsg loop error expected: %i errno %i\n",
+ sent, errno);
errno = -EIO;
goto out_errno;
}
@@ -497,9 +617,10 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
* paths.
*/
total_bytes = (float)iov_count * (float)iov_length * (float)cnt;
- txmsg_pop_total = txmsg_pop;
if (txmsg_apply)
- txmsg_pop_total *= (total_bytes / txmsg_apply);
+ txmsg_pop_total = txmsg_pop * (total_bytes / txmsg_apply);
+ else
+ txmsg_pop_total = txmsg_pop * cnt;
total_bytes -= txmsg_pop_total;
err = clock_gettime(CLOCK_MONOTONIC, &s->start);
if (err < 0)
@@ -633,14 +754,18 @@ static int sendmsg_test(struct sockmap_options *opt)
rxpid = fork();
if (rxpid == 0) {
- if (opt->drop_expected)
- exit(0);
+ iov_buf -= (txmsg_pop - txmsg_start_pop + 1);
+ if (opt->drop_expected || txmsg_ktls_skb_drop)
+ _exit(0);
+
+ if (!iov_buf) /* zero bytes sent case */
+ _exit(0);
if (opt->sendpage)
iov_count = 1;
err = msg_loop(rx_fd, iov_count, iov_buf,
cnt, &s, false, opt);
- if (opt->verbose)
+ if (opt->verbose > 1)
fprintf(stderr,
"msg_loop_rx: iov_count %i iov_buf %i cnt %i err %i\n",
iov_count, iov_buf, cnt, err);
@@ -648,7 +773,7 @@ static int sendmsg_test(struct sockmap_options *opt)
sent_Bps = sentBps(s);
recvd_Bps = recvdBps(s);
}
- if (opt->verbose)
+ if (opt->verbose > 1)
fprintf(stdout,
"rx_sendmsg: TX: %zuB %fB/s %fGB/s RX: %zuB %fB/s %fGB/s %s\n",
s.bytes_sent, sent_Bps, sent_Bps/giga,
@@ -678,7 +803,7 @@ static int sendmsg_test(struct sockmap_options *opt)
sent_Bps = sentBps(s);
recvd_Bps = recvdBps(s);
}
- if (opt->verbose)
+ if (opt->verbose > 1)
fprintf(stdout,
"tx_sendmsg: TX: %zuB %fB/s %f GB/s RX: %zuB %fB/s %fGB/s\n",
s.bytes_sent, sent_Bps, sent_Bps/giga,
@@ -694,14 +819,14 @@ static int sendmsg_test(struct sockmap_options *opt)
if (WIFEXITED(rx_status)) {
err = WEXITSTATUS(rx_status);
if (err) {
- fprintf(stderr, "rx thread exited with err %d. ", err);
+ fprintf(stderr, "rx thread exited with err %d.\n", err);
goto out;
}
}
if (WIFEXITED(tx_status)) {
err = WEXITSTATUS(tx_status);
if (err)
- fprintf(stderr, "tx thread exited with err %d. ", err);
+ fprintf(stderr, "tx thread exited with err %d.\n", err);
}
out:
return err;
@@ -783,6 +908,7 @@ static int forever_ping_pong(int rate, struct sockmap_options *opt)
}
enum {
+ SELFTESTS,
PING_PONG,
SENDMSG,
BASE,
@@ -816,8 +942,28 @@ static int run_options(struct sockmap_options *options, int cg_fd, int test)
return err;
}
+ /* Attach programs to TLS sockmap */
+ if (txmsg_ktls_skb) {
+ err = bpf_prog_attach(prog_fd[0], map_fd[8],
+ BPF_SK_SKB_STREAM_PARSER, 0);
+ if (err) {
+ fprintf(stderr,
+ "ERROR: bpf_prog_attach (TLS sockmap %i->%i): %d (%s)\n",
+ prog_fd[0], map_fd[8], err, strerror(errno));
+ return err;
+ }
+
+ err = bpf_prog_attach(prog_fd[2], map_fd[8],
+ BPF_SK_SKB_STREAM_VERDICT, 0);
+ if (err) {
+ fprintf(stderr, "ERROR: bpf_prog_attach (TLS sockmap): %d (%s)\n",
+ err, strerror(errno));
+ return err;
+ }
+ }
+
/* Attach to cgroups */
- err = bpf_prog_attach(prog_fd[2], cg_fd, BPF_CGROUP_SOCK_OPS, 0);
+ err = bpf_prog_attach(prog_fd[3], cg_fd, BPF_CGROUP_SOCK_OPS, 0);
if (err) {
fprintf(stderr, "ERROR: bpf_prog_attach (groups): %d (%s)\n",
err, strerror(errno));
@@ -833,19 +979,14 @@ run:
/* Attach txmsg program to sockmap */
if (txmsg_pass)
- tx_prog_fd = prog_fd[3];
- else if (txmsg_noisy)
tx_prog_fd = prog_fd[4];
else if (txmsg_redir)
tx_prog_fd = prog_fd[5];
- else if (txmsg_redir_noisy)
- tx_prog_fd = prog_fd[6];
- else if (txmsg_drop)
- tx_prog_fd = prog_fd[9];
- /* apply and cork must be last */
else if (txmsg_apply)
- tx_prog_fd = prog_fd[7];
+ tx_prog_fd = prog_fd[6];
else if (txmsg_cork)
+ tx_prog_fd = prog_fd[7];
+ else if (txmsg_drop)
tx_prog_fd = prog_fd[8];
else
tx_prog_fd = 0;
@@ -870,7 +1011,7 @@ run:
goto out;
}
- if (txmsg_redir || txmsg_redir_noisy)
+ if (txmsg_redir)
redir_fd = c2;
else
redir_fd = c1;
@@ -1018,7 +1159,35 @@ run:
}
}
- if (txmsg_skb) {
+ if (txmsg_ktls_skb) {
+ int ingress = BPF_F_INGRESS;
+
+ i = 0;
+ err = bpf_map_update_elem(map_fd[8], &i, &p2, BPF_ANY);
+ if (err) {
+ fprintf(stderr,
+ "ERROR: bpf_map_update_elem (c1 sockmap): %d (%s)\n",
+ err, strerror(errno));
+ }
+
+ if (txmsg_ktls_skb_redir) {
+ i = 1;
+ err = bpf_map_update_elem(map_fd[7],
+ &i, &ingress, BPF_ANY);
+ if (err) {
+ fprintf(stderr,
+ "ERROR: bpf_map_update_elem (txmsg_ingress): %d (%s)\n",
+ err, strerror(errno));
+ }
+ }
+
+ if (txmsg_ktls_skb_drop) {
+ i = 1;
+ err = bpf_map_update_elem(map_fd[7], &i, &i, BPF_ANY);
+ }
+ }
+
+ if (txmsg_redir_skb) {
int skb_fd = (test == SENDMSG || test == SENDPAGE) ?
p2 : p1;
int ingress = BPF_F_INGRESS;
@@ -1033,8 +1202,7 @@ run:
}
i = 3;
- err = bpf_map_update_elem(map_fd[0],
- &i, &skb_fd, BPF_ANY);
+ err = bpf_map_update_elem(map_fd[0], &i, &skb_fd, BPF_ANY);
if (err) {
fprintf(stderr,
"ERROR: bpf_map_update_elem (c1 sockmap): %d (%s)\n",
@@ -1068,9 +1236,12 @@ run:
fprintf(stderr, "unknown test\n");
out:
/* Detatch and zero all the maps */
- bpf_prog_detach2(prog_fd[2], cg_fd, BPF_CGROUP_SOCK_OPS);
+ bpf_prog_detach2(prog_fd[3], cg_fd, BPF_CGROUP_SOCK_OPS);
bpf_prog_detach2(prog_fd[0], map_fd[0], BPF_SK_SKB_STREAM_PARSER);
bpf_prog_detach2(prog_fd[1], map_fd[0], BPF_SK_SKB_STREAM_VERDICT);
+ bpf_prog_detach2(prog_fd[0], map_fd[8], BPF_SK_SKB_STREAM_PARSER);
+ bpf_prog_detach2(prog_fd[2], map_fd[8], BPF_SK_SKB_STREAM_VERDICT);
+
if (tx_prog_fd >= 0)
bpf_prog_detach2(tx_prog_fd, map_fd[1], BPF_SK_MSG_VERDICT);
@@ -1112,12 +1283,8 @@ static void test_options(char *options)
if (txmsg_pass)
strncat(options, "pass,", OPTSTRING);
- if (txmsg_noisy)
- strncat(options, "pass_noisy,", OPTSTRING);
if (txmsg_redir)
strncat(options, "redir,", OPTSTRING);
- if (txmsg_redir_noisy)
- strncat(options, "redir_noisy,", OPTSTRING);
if (txmsg_drop)
strncat(options, "drop,", OPTSTRING);
if (txmsg_apply) {
@@ -1143,8 +1310,10 @@ static void test_options(char *options)
}
if (txmsg_ingress)
strncat(options, "ingress,", OPTSTRING);
- if (txmsg_skb)
- strncat(options, "skb,", OPTSTRING);
+ if (txmsg_redir_skb)
+ strncat(options, "redir_skb,", OPTSTRING);
+ if (txmsg_ktls_skb)
+ strncat(options, "ktls_skb,", OPTSTRING);
if (ktls)
strncat(options, "ktls,", OPTSTRING);
if (peek_flag)
@@ -1168,416 +1337,317 @@ static int __test_exec(int cgrp, int test, struct sockmap_options *opt)
test_options(options);
- fprintf(stdout,
- "[TEST %i]: (%i, %i, %i, %s, %s): ",
- test_cnt, opt->rate, opt->iov_count, opt->iov_length,
- test_to_str(test), options);
- fflush(stdout);
+ if (opt->verbose) {
+ fprintf(stdout,
+ " [TEST %i]: (%i, %i, %i, %s, %s): ",
+ test_cnt, opt->rate, opt->iov_count, opt->iov_length,
+ test_to_str(test), options);
+ fflush(stdout);
+ }
err = run_options(opt, cgrp, test);
- fprintf(stdout, "%s\n", !err ? "PASS" : "FAILED");
+ if (opt->verbose)
+ fprintf(stdout, " %s\n", !err ? "PASS" : "FAILED");
test_cnt++;
!err ? passed++ : failed++;
free(options);
return err;
}
-static int test_exec(int cgrp, struct sockmap_options *opt)
-{
- int err = __test_exec(cgrp, SENDMSG, opt);
-
- if (err)
- goto out;
-
- err = __test_exec(cgrp, SENDPAGE, opt);
-out:
- return err;
-}
-
-static int test_loop(int cgrp)
-{
- struct sockmap_options opt;
-
- int err, i, l, r;
-
- opt.verbose = 0;
- opt.base = false;
- opt.sendpage = false;
- opt.data_test = false;
- opt.drop_expected = false;
- opt.iov_count = 0;
- opt.iov_length = 0;
- opt.rate = 0;
-
- r = 1;
- for (i = 1; i < 100; i += 33) {
- for (l = 1; l < 100; l += 33) {
- opt.rate = r;
- opt.iov_count = i;
- opt.iov_length = l;
- err = test_exec(cgrp, &opt);
- if (err)
- goto out;
- }
- }
- sched_yield();
-out:
- return err;
-}
-
-static int test_txmsg(int cgrp)
+static void test_exec(int cgrp, struct sockmap_options *opt)
{
+ int type = strcmp(opt->map, BPF_SOCKMAP_FILENAME);
int err;
- txmsg_pass = txmsg_noisy = txmsg_redir_noisy = txmsg_drop = 0;
- txmsg_apply = txmsg_cork = 0;
- txmsg_ingress = txmsg_skb = 0;
-
- txmsg_pass = 1;
- err = test_loop(cgrp);
- txmsg_pass = 0;
- if (err)
- goto out;
-
- txmsg_redir = 1;
- err = test_loop(cgrp);
- txmsg_redir = 0;
- if (err)
- goto out;
-
- txmsg_drop = 1;
- err = test_loop(cgrp);
- txmsg_drop = 0;
- if (err)
- goto out;
-
- txmsg_redir = 1;
- txmsg_ingress = 1;
- err = test_loop(cgrp);
- txmsg_redir = 0;
- txmsg_ingress = 0;
- if (err)
- goto out;
-out:
- txmsg_pass = 0;
- txmsg_redir = 0;
- txmsg_drop = 0;
- return err;
+ if (type == 0) {
+ test_start();
+ err = __test_exec(cgrp, SENDMSG, opt);
+ if (err)
+ test_fail();
+ } else {
+ test_start();
+ err = __test_exec(cgrp, SENDPAGE, opt);
+ if (err)
+ test_fail();
+ }
}
-static int test_send(struct sockmap_options *opt, int cgrp)
+static void test_send_one(struct sockmap_options *opt, int cgrp)
{
- int err;
-
opt->iov_length = 1;
opt->iov_count = 1;
opt->rate = 1;
- err = test_exec(cgrp, opt);
- if (err)
- goto out;
+ test_exec(cgrp, opt);
opt->iov_length = 1;
opt->iov_count = 1024;
opt->rate = 1;
- err = test_exec(cgrp, opt);
- if (err)
- goto out;
+ test_exec(cgrp, opt);
opt->iov_length = 1024;
opt->iov_count = 1;
opt->rate = 1;
- err = test_exec(cgrp, opt);
- if (err)
- goto out;
+ test_exec(cgrp, opt);
- opt->iov_length = 1;
+}
+
+static void test_send_many(struct sockmap_options *opt, int cgrp)
+{
+ opt->iov_length = 3;
opt->iov_count = 1;
opt->rate = 512;
- err = test_exec(cgrp, opt);
- if (err)
- goto out;
-
- opt->iov_length = 256;
- opt->iov_count = 1024;
- opt->rate = 2;
- err = test_exec(cgrp, opt);
- if (err)
- goto out;
+ test_exec(cgrp, opt);
opt->rate = 100;
opt->iov_count = 1;
opt->iov_length = 5;
- err = test_exec(cgrp, opt);
- if (err)
- goto out;
-out:
- sched_yield();
- return err;
+ test_exec(cgrp, opt);
}
-static int test_mixed(int cgrp)
+static void test_send_large(struct sockmap_options *opt, int cgrp)
{
- struct sockmap_options opt = {0};
- int err;
+ opt->iov_length = 256;
+ opt->iov_count = 1024;
+ opt->rate = 2;
+ test_exec(cgrp, opt);
+}
- txmsg_pass = txmsg_noisy = txmsg_redir_noisy = txmsg_drop = 0;
- txmsg_apply = txmsg_cork = 0;
- txmsg_start = txmsg_end = 0;
- txmsg_start_push = txmsg_end_push = 0;
- txmsg_start_pop = txmsg_pop = 0;
+static void test_send(struct sockmap_options *opt, int cgrp)
+{
+ test_send_one(opt, cgrp);
+ test_send_many(opt, cgrp);
+ test_send_large(opt, cgrp);
+ sched_yield();
+}
+static void test_txmsg_pass(int cgrp, struct sockmap_options *opt)
+{
/* Test small and large iov_count values with pass/redir/apply/cork */
txmsg_pass = 1;
- txmsg_redir = 0;
- txmsg_apply = 1;
- txmsg_cork = 0;
- err = test_send(&opt, cgrp);
- if (err)
- goto out;
+ test_send(opt, cgrp);
+}
- txmsg_pass = 1;
- txmsg_redir = 0;
- txmsg_apply = 0;
- txmsg_cork = 1;
- err = test_send(&opt, cgrp);
- if (err)
- goto out;
+static void test_txmsg_redir(int cgrp, struct sockmap_options *opt)
+{
+ txmsg_redir = 1;
+ test_send(opt, cgrp);
+}
- txmsg_pass = 1;
- txmsg_redir = 0;
- txmsg_apply = 1;
- txmsg_cork = 1;
- err = test_send(&opt, cgrp);
- if (err)
- goto out;
+static void test_txmsg_drop(int cgrp, struct sockmap_options *opt)
+{
+ txmsg_drop = 1;
+ test_send(opt, cgrp);
+}
- txmsg_pass = 1;
- txmsg_redir = 0;
- txmsg_apply = 1024;
- txmsg_cork = 0;
- err = test_send(&opt, cgrp);
- if (err)
- goto out;
+static void test_txmsg_ingress_redir(int cgrp, struct sockmap_options *opt)
+{
+ txmsg_pass = txmsg_drop = 0;
+ txmsg_ingress = txmsg_redir = 1;
+ test_send(opt, cgrp);
+}
- txmsg_pass = 1;
- txmsg_redir = 0;
- txmsg_apply = 0;
- txmsg_cork = 1024;
- err = test_send(&opt, cgrp);
- if (err)
- goto out;
+static void test_txmsg_skb(int cgrp, struct sockmap_options *opt)
+{
+ bool data = opt->data_test;
+ int k = ktls;
- txmsg_pass = 1;
- txmsg_redir = 0;
- txmsg_apply = 1024;
- txmsg_cork = 1024;
- err = test_send(&opt, cgrp);
- if (err)
- goto out;
+ opt->data_test = true;
+ ktls = 1;
+ txmsg_pass = txmsg_drop = 0;
+ txmsg_ingress = txmsg_redir = 0;
+ txmsg_ktls_skb = 1;
txmsg_pass = 1;
- txmsg_redir = 0;
- txmsg_cork = 4096;
- txmsg_apply = 4096;
- err = test_send(&opt, cgrp);
- if (err)
- goto out;
- txmsg_pass = 0;
- txmsg_redir = 1;
- txmsg_apply = 1;
- txmsg_cork = 0;
- err = test_send(&opt, cgrp);
- if (err)
- goto out;
+ /* Using data verification so ensure iov layout is
+ * expected from test receiver side. e.g. has enough
+ * bytes to write test code.
+ */
+ opt->iov_length = 100;
+ opt->iov_count = 1;
+ opt->rate = 1;
+ test_exec(cgrp, opt);
- txmsg_pass = 0;
- txmsg_redir = 1;
- txmsg_apply = 0;
- txmsg_cork = 1;
- err = test_send(&opt, cgrp);
- if (err)
- goto out;
+ txmsg_ktls_skb_drop = 1;
+ test_exec(cgrp, opt);
- txmsg_pass = 0;
- txmsg_redir = 1;
- txmsg_apply = 1024;
- txmsg_cork = 0;
- err = test_send(&opt, cgrp);
- if (err)
- goto out;
+ txmsg_ktls_skb_drop = 0;
+ txmsg_ktls_skb_redir = 1;
+ test_exec(cgrp, opt);
- txmsg_pass = 0;
- txmsg_redir = 1;
- txmsg_apply = 0;
- txmsg_cork = 1024;
- err = test_send(&opt, cgrp);
- if (err)
- goto out;
+ opt->data_test = data;
+ ktls = k;
+}
+
+
+/* Test cork with hung data. This tests poor usage patterns where
+ * cork can leave data on the ring if user program is buggy and
+ * doesn't flush them somehow. They do take some time however
+ * because they wait for a timeout. Test pass, redir and cork with
+ * apply logic. Use cork size of 4097 with send_large to avoid
+ * aligning cork size with send size.
+ */
+static void test_txmsg_cork_hangs(int cgrp, struct sockmap_options *opt)
+{
+ txmsg_pass = 1;
+ txmsg_redir = 0;
+ txmsg_cork = 4097;
+ txmsg_apply = 4097;
+ test_send_large(opt, cgrp);
txmsg_pass = 0;
txmsg_redir = 1;
- txmsg_apply = 1024;
- txmsg_cork = 1024;
- err = test_send(&opt, cgrp);
- if (err)
- goto out;
+ txmsg_apply = 0;
+ txmsg_cork = 4097;
+ test_send_large(opt, cgrp);
txmsg_pass = 0;
txmsg_redir = 1;
- txmsg_cork = 4096;
- txmsg_apply = 4096;
- err = test_send(&opt, cgrp);
- if (err)
- goto out;
-out:
- return err;
+ txmsg_apply = 4097;
+ txmsg_cork = 4097;
+ test_send_large(opt, cgrp);
}
-static int test_start_end(int cgrp)
+static void test_txmsg_pull(int cgrp, struct sockmap_options *opt)
{
- struct sockmap_options opt = {0};
- int err, i;
+ /* Test basic start/end */
+ txmsg_start = 1;
+ txmsg_end = 2;
+ test_send(opt, cgrp);
+
+ /* Test >4k pull */
+ txmsg_start = 4096;
+ txmsg_end = 9182;
+ test_send_large(opt, cgrp);
- /* Test basic start/end with lots of iov_count and iov_lengths */
+ /* Test pull + redirect */
+ txmsg_redir = 0;
txmsg_start = 1;
txmsg_end = 2;
- txmsg_start_push = 1;
- txmsg_end_push = 2;
- txmsg_start_pop = 1;
- txmsg_pop = 1;
- err = test_txmsg(cgrp);
- if (err)
- goto out;
+ test_send(opt, cgrp);
- /* Cut a byte of pushed data but leave reamining in place */
+ /* Test pull + cork */
+ txmsg_redir = 0;
+ txmsg_cork = 512;
txmsg_start = 1;
txmsg_end = 2;
- txmsg_start_push = 1;
- txmsg_end_push = 3;
+ test_send_many(opt, cgrp);
+
+ /* Test pull + cork + redirect */
+ txmsg_redir = 1;
+ txmsg_cork = 512;
+ txmsg_start = 1;
+ txmsg_end = 2;
+ test_send_many(opt, cgrp);
+}
+
+static void test_txmsg_pop(int cgrp, struct sockmap_options *opt)
+{
+ /* Test basic pop */
txmsg_start_pop = 1;
- txmsg_pop = 1;
- err = test_txmsg(cgrp);
- if (err)
- goto out;
+ txmsg_pop = 2;
+ test_send_many(opt, cgrp);
- /* Test start/end with cork */
- opt.rate = 16;
- opt.iov_count = 1;
- opt.iov_length = 100;
- txmsg_cork = 1600;
-
- txmsg_start_pop = 0;
- txmsg_pop = 0;
-
- for (i = 99; i <= 1600; i += 500) {
- txmsg_start = 0;
- txmsg_end = i;
- txmsg_start_push = 0;
- txmsg_end_push = i;
- err = test_exec(cgrp, &opt);
- if (err)
- goto out;
- }
+ /* Test pop with >4k */
+ txmsg_start_pop = 4096;
+ txmsg_pop = 4096;
+ test_send_large(opt, cgrp);
- /* Test pop data in middle of cork */
- for (i = 99; i <= 1600; i += 500) {
- txmsg_start_pop = 10;
- txmsg_pop = i;
- err = test_exec(cgrp, &opt);
- if (err)
- goto out;
- }
- txmsg_start_pop = 0;
- txmsg_pop = 0;
-
- /* Test start/end with cork but pull data in middle */
- for (i = 199; i <= 1600; i += 500) {
- txmsg_start = 100;
- txmsg_end = i;
- txmsg_start_push = 100;
- txmsg_end_push = i;
- err = test_exec(cgrp, &opt);
- if (err)
- goto out;
- }
+ /* Test pop + redirect */
+ txmsg_redir = 1;
+ txmsg_start_pop = 1;
+ txmsg_pop = 2;
+ test_send_many(opt, cgrp);
- /* Test start/end with cork pulling last sg entry */
- txmsg_start = 1500;
- txmsg_end = 1600;
- txmsg_start_push = 1500;
- txmsg_end_push = 1600;
- err = test_exec(cgrp, &opt);
- if (err)
- goto out;
+ /* Test pop + cork */
+ txmsg_redir = 0;
+ txmsg_cork = 512;
+ txmsg_start_pop = 1;
+ txmsg_pop = 2;
+ test_send_many(opt, cgrp);
- /* Test pop with cork pulling last sg entry */
- txmsg_start_pop = 1500;
- txmsg_pop = 1600;
- err = test_exec(cgrp, &opt);
- if (err)
- goto out;
- txmsg_start_pop = 0;
- txmsg_pop = 0;
-
- /* Test start/end pull of single byte in last page */
- txmsg_start = 1111;
- txmsg_end = 1112;
- txmsg_start_push = 1111;
- txmsg_end_push = 1112;
- err = test_exec(cgrp, &opt);
- if (err)
- goto out;
+ /* Test pop + redirect + cork */
+ txmsg_redir = 1;
+ txmsg_cork = 4;
+ txmsg_start_pop = 1;
+ txmsg_pop = 2;
+ test_send_many(opt, cgrp);
+}
- /* Test pop of single byte in last page */
- txmsg_start_pop = 1111;
- txmsg_pop = 1112;
- err = test_exec(cgrp, &opt);
- if (err)
- goto out;
+static void test_txmsg_push(int cgrp, struct sockmap_options *opt)
+{
+ /* Test basic push */
+ txmsg_start_push = 1;
+ txmsg_end_push = 1;
+ test_send(opt, cgrp);
- /* Test start/end with end < start */
- txmsg_start = 1111;
- txmsg_end = 0;
- txmsg_start_push = 1111;
- txmsg_end_push = 0;
- err = test_exec(cgrp, &opt);
- if (err)
- goto out;
+ /* Test push 4kB >4k */
+ txmsg_start_push = 4096;
+ txmsg_end_push = 4096;
+ test_send_large(opt, cgrp);
- /* Test start/end with end > data */
- txmsg_start = 0;
- txmsg_end = 1601;
- txmsg_start_push = 0;
- txmsg_end_push = 1601;
- err = test_exec(cgrp, &opt);
- if (err)
- goto out;
+ /* Test push + redirect */
+ txmsg_redir = 1;
+ txmsg_start_push = 1;
+ txmsg_end_push = 2;
+ test_send_many(opt, cgrp);
- /* Test start/end with start > data */
- txmsg_start = 1601;
- txmsg_end = 1600;
- txmsg_start_push = 1601;
- txmsg_end_push = 1600;
- err = test_exec(cgrp, &opt);
- if (err)
- goto out;
+ /* Test push + cork */
+ txmsg_redir = 0;
+ txmsg_cork = 512;
+ txmsg_start_push = 1;
+ txmsg_end_push = 2;
+ test_send_many(opt, cgrp);
+}
- /* Test pop with start > data */
- txmsg_start_pop = 1601;
- txmsg_pop = 1;
- err = test_exec(cgrp, &opt);
- if (err)
- goto out;
+static void test_txmsg_push_pop(int cgrp, struct sockmap_options *opt)
+{
+ txmsg_start_push = 1;
+ txmsg_end_push = 10;
+ txmsg_start_pop = 5;
+ txmsg_pop = 4;
+ test_send_large(opt, cgrp);
+}
- /* Test pop with pop range > data */
- txmsg_start_pop = 1599;
- txmsg_pop = 10;
- err = test_exec(cgrp, &opt);
-out:
- txmsg_start = 0;
- txmsg_end = 0;
- sched_yield();
- return err;
+static void test_txmsg_apply(int cgrp, struct sockmap_options *opt)
+{
+ txmsg_pass = 1;
+ txmsg_redir = 0;
+ txmsg_apply = 1;
+ txmsg_cork = 0;
+ test_send_one(opt, cgrp);
+
+ txmsg_pass = 0;
+ txmsg_redir = 1;
+ txmsg_apply = 1;
+ txmsg_cork = 0;
+ test_send_one(opt, cgrp);
+
+ txmsg_pass = 1;
+ txmsg_redir = 0;
+ txmsg_apply = 1024;
+ txmsg_cork = 0;
+ test_send_large(opt, cgrp);
+
+ txmsg_pass = 0;
+ txmsg_redir = 1;
+ txmsg_apply = 1024;
+ txmsg_cork = 0;
+ test_send_large(opt, cgrp);
+}
+
+static void test_txmsg_cork(int cgrp, struct sockmap_options *opt)
+{
+ txmsg_pass = 1;
+ txmsg_redir = 0;
+ txmsg_apply = 0;
+ txmsg_cork = 1;
+ test_send(opt, cgrp);
+
+ txmsg_pass = 1;
+ txmsg_redir = 0;
+ txmsg_apply = 1;
+ txmsg_cork = 1;
+ test_send(opt, cgrp);
}
char *map_names[] = {
@@ -1589,11 +1659,13 @@ char *map_names[] = {
"sock_bytes",
"sock_redir_flags",
"sock_skb_opts",
+ "tls_sock_map",
};
int prog_attach_type[] = {
BPF_SK_SKB_STREAM_PARSER,
BPF_SK_SKB_STREAM_VERDICT,
+ BPF_SK_SKB_STREAM_VERDICT,
BPF_CGROUP_SOCK_OPS,
BPF_SK_MSG_VERDICT,
BPF_SK_MSG_VERDICT,
@@ -1607,6 +1679,7 @@ int prog_attach_type[] = {
int prog_type[] = {
BPF_PROG_TYPE_SK_SKB,
BPF_PROG_TYPE_SK_SKB,
+ BPF_PROG_TYPE_SK_SKB,
BPF_PROG_TYPE_SOCK_OPS,
BPF_PROG_TYPE_SK_MSG,
BPF_PROG_TYPE_SK_MSG,
@@ -1662,73 +1735,117 @@ static int populate_progs(char *bpf_file)
return 0;
}
-static int __test_suite(int cg_fd, char *bpf_file)
+struct _test test[] = {
+ {"txmsg test passthrough", test_txmsg_pass},
+ {"txmsg test redirect", test_txmsg_redir},
+ {"txmsg test drop", test_txmsg_drop},
+ {"txmsg test ingress redirect", test_txmsg_ingress_redir},
+ {"txmsg test skb", test_txmsg_skb},
+ {"txmsg test apply", test_txmsg_apply},
+ {"txmsg test cork", test_txmsg_cork},
+ {"txmsg test hanging corks", test_txmsg_cork_hangs},
+ {"txmsg test push_data", test_txmsg_push},
+ {"txmsg test pull-data", test_txmsg_pull},
+ {"txmsg test pop-data", test_txmsg_pop},
+ {"txmsg test push/pop data", test_txmsg_push_pop},
+};
+
+static int check_whitelist(struct _test *t, struct sockmap_options *opt)
{
- int err, cleanup = cg_fd;
+ char *entry, *ptr;
+
+ if (!opt->whitelist)
+ return 0;
+ ptr = strdup(opt->whitelist);
+ if (!ptr)
+ return -ENOMEM;
+ entry = strtok(ptr, ",");
+ while (entry) {
+ if ((opt->prepend && strstr(opt->prepend, entry) != 0) ||
+ strstr(opt->map, entry) != 0 ||
+ strstr(t->title, entry) != 0)
+ return 0;
+ entry = strtok(NULL, ",");
+ }
+ return -EINVAL;
+}
- err = populate_progs(bpf_file);
+static int check_blacklist(struct _test *t, struct sockmap_options *opt)
+{
+ char *entry, *ptr;
+
+ if (!opt->blacklist)
+ return -EINVAL;
+ ptr = strdup(opt->blacklist);
+ if (!ptr)
+ return -ENOMEM;
+ entry = strtok(ptr, ",");
+ while (entry) {
+ if ((opt->prepend && strstr(opt->prepend, entry) != 0) ||
+ strstr(opt->map, entry) != 0 ||
+ strstr(t->title, entry) != 0)
+ return 0;
+ entry = strtok(NULL, ",");
+ }
+ return -EINVAL;
+}
+
+static int __test_selftests(int cg_fd, struct sockmap_options *opt)
+{
+ int i, err;
+
+ err = populate_progs(opt->map);
if (err < 0) {
fprintf(stderr, "ERROR: (%i) load bpf failed\n", err);
return err;
}
- if (cg_fd < 0) {
- if (setup_cgroup_environment()) {
- fprintf(stderr, "ERROR: cgroup env failed\n");
- return -EINVAL;
- }
+ /* Tests basic commands and APIs */
+ for (i = 0; i < sizeof(test)/sizeof(struct _test); i++) {
+ struct _test t = test[i];
- cg_fd = create_and_get_cgroup(CG_PATH);
- if (cg_fd < 0) {
- fprintf(stderr,
- "ERROR: (%i) open cg path failed: %s\n",
- cg_fd, optarg);
- return cg_fd;
- }
+ if (check_whitelist(&t, opt) != 0)
+ continue;
+ if (check_blacklist(&t, opt) == 0)
+ continue;
- if (join_cgroup(CG_PATH)) {
- fprintf(stderr, "ERROR: failed to join cgroup\n");
- return -EINVAL;
- }
+ test_start_subtest(&t, opt);
+ t.tester(cg_fd, opt);
+ test_end_subtest();
}
- /* Tests basic commands and APIs with range of iov values */
- txmsg_start = txmsg_end = txmsg_start_push = txmsg_end_push = 0;
- err = test_txmsg(cg_fd);
- if (err)
- goto out;
+ return err;
+}
- /* Tests interesting combinations of APIs used together */
- err = test_mixed(cg_fd);
- if (err)
- goto out;
+static void test_selftests_sockmap(int cg_fd, struct sockmap_options *opt)
+{
+ opt->map = BPF_SOCKMAP_FILENAME;
+ __test_selftests(cg_fd, opt);
+}
- /* Tests pull_data API using start/end API */
- err = test_start_end(cg_fd);
- if (err)
- goto out;
+static void test_selftests_sockhash(int cg_fd, struct sockmap_options *opt)
+{
+ opt->map = BPF_SOCKHASH_FILENAME;
+ __test_selftests(cg_fd, opt);
+}
-out:
- printf("Summary: %i PASSED %i FAILED\n", passed, failed);
- if (cleanup < 0) {
- cleanup_cgroup_environment();
- close(cg_fd);
- }
- return err;
+static void test_selftests_ktls(int cg_fd, struct sockmap_options *opt)
+{
+ opt->map = BPF_SOCKHASH_FILENAME;
+ opt->prepend = "ktls";
+ ktls = 1;
+ __test_selftests(cg_fd, opt);
+ ktls = 0;
}
-static int test_suite(int cg_fd)
+static int test_selftest(int cg_fd, struct sockmap_options *opt)
{
- int err;
- err = __test_suite(cg_fd, BPF_SOCKMAP_FILENAME);
- if (err)
- goto out;
- err = __test_suite(cg_fd, BPF_SOCKHASH_FILENAME);
-out:
- if (cg_fd > -1)
- close(cg_fd);
- return err;
+ test_selftests_sockmap(cg_fd, opt);
+ test_selftests_sockhash(cg_fd, opt);
+ test_selftests_ktls(cg_fd, opt);
+ test_print_results();
+ return 0;
}
int main(int argc, char **argv)
@@ -1737,12 +1854,10 @@ int main(int argc, char **argv)
struct sockmap_options options = {0};
int opt, longindex, err, cg_fd = 0;
char *bpf_file = BPF_SOCKMAP_FILENAME;
- int test = PING_PONG;
-
- if (argc < 2)
- return test_suite(-1);
+ int test = SELFTESTS;
+ bool cg_created = 0;
- while ((opt = getopt_long(argc, argv, ":dhvc:r:i:l:t:p:q:",
+ while ((opt = getopt_long(argc, argv, ":dhv:c:r:i:l:t:p:q:n:b:",
long_options, &longindex)) != -1) {
switch (opt) {
case 's':
@@ -1783,6 +1898,8 @@ int main(int argc, char **argv)
break;
case 'v':
options.verbose = 1;
+ if (optarg)
+ options.verbose = atoi(optarg);
break;
case 'i':
iov_count = atoi(optarg);
@@ -1809,6 +1926,15 @@ int main(int argc, char **argv)
return -1;
}
break;
+ case 'n':
+ options.whitelist = strdup(optarg);
+ if (!options.whitelist)
+ return -ENOMEM;
+ break;
+ case 'b':
+ options.blacklist = strdup(optarg);
+ if (!options.blacklist)
+ return -ENOMEM;
case 0:
break;
case 'h':
@@ -1818,13 +1944,30 @@ int main(int argc, char **argv)
}
}
- if (argc <= 3 && cg_fd)
- return test_suite(cg_fd);
-
if (!cg_fd) {
- fprintf(stderr, "%s requires cgroup option: --cgroup <path>\n",
- argv[0]);
- return -1;
+ if (setup_cgroup_environment()) {
+ fprintf(stderr, "ERROR: cgroup env failed\n");
+ return -EINVAL;
+ }
+
+ cg_fd = create_and_get_cgroup(CG_PATH);
+ if (cg_fd < 0) {
+ fprintf(stderr,
+ "ERROR: (%i) open cg path failed: %s\n",
+ cg_fd, strerror(errno));
+ return cg_fd;
+ }
+
+ if (join_cgroup(CG_PATH)) {
+ fprintf(stderr, "ERROR: failed to join cgroup\n");
+ return -EINVAL;
+ }
+ cg_created = 1;
+ }
+
+ if (test == SELFTESTS) {
+ err = test_selftest(cg_fd, &options);
+ goto out;
}
err = populate_progs(bpf_file);
@@ -1843,6 +1986,13 @@ int main(int argc, char **argv)
options.rate = rate;
err = run_options(&options, cg_fd, test);
+out:
+ if (options.whitelist)
+ free(options.whitelist);
+ if (options.blacklist)
+ free(options.blacklist);
+ if (cg_created)
+ cleanup_cgroup_environment();
close(cg_fd);
return err;
}
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 87eaa49609a0..78a6bae56ea6 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -50,7 +50,7 @@
#define MAX_INSNS BPF_MAXINSNS
#define MAX_TEST_INSNS 1000000
#define MAX_FIXUPS 8
-#define MAX_NR_MAPS 19
+#define MAX_NR_MAPS 20
#define MAX_TEST_RUNS 8
#define POINTER_VALUE 0xcafe4all
#define TEST_DATA_LEN 64
@@ -86,6 +86,7 @@ struct bpf_test {
int fixup_map_array_small[MAX_FIXUPS];
int fixup_sk_storage_map[MAX_FIXUPS];
int fixup_map_event_output[MAX_FIXUPS];
+ int fixup_map_reuseport_array[MAX_FIXUPS];
const char *errstr;
const char *errstr_unpriv;
uint32_t insn_processed;
@@ -637,6 +638,7 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type,
int *fixup_map_array_small = test->fixup_map_array_small;
int *fixup_sk_storage_map = test->fixup_sk_storage_map;
int *fixup_map_event_output = test->fixup_map_event_output;
+ int *fixup_map_reuseport_array = test->fixup_map_reuseport_array;
if (test->fill_helper) {
test->fill_insns = calloc(MAX_TEST_INSNS, sizeof(struct bpf_insn));
@@ -806,12 +808,28 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type,
fixup_map_event_output++;
} while (*fixup_map_event_output);
}
+ if (*fixup_map_reuseport_array) {
+ map_fds[19] = __create_map(BPF_MAP_TYPE_REUSEPORT_SOCKARRAY,
+ sizeof(u32), sizeof(u64), 1, 0);
+ do {
+ prog[*fixup_map_reuseport_array].imm = map_fds[19];
+ fixup_map_reuseport_array++;
+ } while (*fixup_map_reuseport_array);
+ }
}
+struct libcap {
+ struct __user_cap_header_struct hdr;
+ struct __user_cap_data_struct data[2];
+};
+
static int set_admin(bool admin)
{
cap_t caps;
- const cap_value_t cap_val = CAP_SYS_ADMIN;
+ /* need CAP_BPF, CAP_NET_ADMIN, CAP_PERFMON to load progs */
+ const cap_value_t cap_net_admin = CAP_NET_ADMIN;
+ const cap_value_t cap_sys_admin = CAP_SYS_ADMIN;
+ struct libcap *cap;
int ret = -1;
caps = cap_get_proc();
@@ -819,11 +837,26 @@ static int set_admin(bool admin)
perror("cap_get_proc");
return -1;
}
- if (cap_set_flag(caps, CAP_EFFECTIVE, 1, &cap_val,
+ cap = (struct libcap *)caps;
+ if (cap_set_flag(caps, CAP_EFFECTIVE, 1, &cap_sys_admin, CAP_CLEAR)) {
+ perror("cap_set_flag clear admin");
+ goto out;
+ }
+ if (cap_set_flag(caps, CAP_EFFECTIVE, 1, &cap_net_admin,
admin ? CAP_SET : CAP_CLEAR)) {
- perror("cap_set_flag");
+ perror("cap_set_flag set_or_clear net");
goto out;
}
+ /* libcap is likely old and simply ignores CAP_BPF and CAP_PERFMON,
+ * so update effective bits manually
+ */
+ if (admin) {
+ cap->data[1].effective |= 1 << (38 /* CAP_PERFMON */ - 32);
+ cap->data[1].effective |= 1 << (39 /* CAP_BPF */ - 32);
+ } else {
+ cap->data[1].effective &= ~(1 << (38 - 32));
+ cap->data[1].effective &= ~(1 << (39 - 32));
+ }
if (cap_set_proc(caps)) {
perror("cap_set_proc");
goto out;
@@ -943,7 +976,12 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
attr.insns = prog;
attr.insns_cnt = prog_len;
attr.license = "GPL";
- attr.log_level = verbose || expected_ret == VERBOSE_ACCEPT ? 1 : 4;
+ if (verbose)
+ attr.log_level = 1;
+ else if (expected_ret == VERBOSE_ACCEPT)
+ attr.log_level = 2;
+ else
+ attr.log_level = 4;
attr.prog_flags = pflags;
fd_prog = bpf_load_program_xattr(&attr, bpf_vlog, sizeof(bpf_vlog));
@@ -1052,9 +1090,11 @@ fail_log:
static bool is_admin(void)
{
+ cap_flag_value_t net_priv = CAP_CLEAR;
+ bool perfmon_priv = false;
+ bool bpf_priv = false;
+ struct libcap *cap;
cap_t caps;
- cap_flag_value_t sysadmin = CAP_CLEAR;
- const cap_value_t cap_val = CAP_SYS_ADMIN;
#ifdef CAP_IS_SUPPORTED
if (!CAP_IS_SUPPORTED(CAP_SETFCAP)) {
@@ -1067,11 +1107,14 @@ static bool is_admin(void)
perror("cap_get_proc");
return false;
}
- if (cap_get_flag(caps, cap_val, CAP_EFFECTIVE, &sysadmin))
- perror("cap_get_flag");
+ cap = (struct libcap *)caps;
+ bpf_priv = cap->data[1].effective & (1 << (39/* CAP_BPF */ - 32));
+ perfmon_priv = cap->data[1].effective & (1 << (38/* CAP_PERFMON */ - 32));
+ if (cap_get_flag(caps, CAP_NET_ADMIN, CAP_EFFECTIVE, &net_priv))
+ perror("cap_get_flag NET");
if (cap_free(caps))
perror("cap_free");
- return (sysadmin == CAP_SET);
+ return bpf_priv && perfmon_priv && net_priv == CAP_SET;
}
static void get_unpriv_disabled()
diff --git a/tools/testing/selftests/bpf/testing_helpers.c b/tools/testing/selftests/bpf/testing_helpers.c
new file mode 100644
index 000000000000..0af6337a8962
--- /dev/null
+++ b/tools/testing/selftests/bpf/testing_helpers.c
@@ -0,0 +1,66 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+/* Copyright (C) 2020 Facebook, Inc. */
+#include <stdlib.h>
+#include <errno.h>
+#include "testing_helpers.h"
+
+int parse_num_list(const char *s, bool **num_set, int *num_set_len)
+{
+ int i, set_len = 0, new_len, num, start = 0, end = -1;
+ bool *set = NULL, *tmp, parsing_end = false;
+ char *next;
+
+ while (s[0]) {
+ errno = 0;
+ num = strtol(s, &next, 10);
+ if (errno)
+ return -errno;
+
+ if (parsing_end)
+ end = num;
+ else
+ start = num;
+
+ if (!parsing_end && *next == '-') {
+ s = next + 1;
+ parsing_end = true;
+ continue;
+ } else if (*next == ',') {
+ parsing_end = false;
+ s = next + 1;
+ end = num;
+ } else if (*next == '\0') {
+ parsing_end = false;
+ s = next;
+ end = num;
+ } else {
+ return -EINVAL;
+ }
+
+ if (start > end)
+ return -EINVAL;
+
+ if (end + 1 > set_len) {
+ new_len = end + 1;
+ tmp = realloc(set, new_len);
+ if (!tmp) {
+ free(set);
+ return -ENOMEM;
+ }
+ for (i = set_len; i < start; i++)
+ tmp[i] = false;
+ set = tmp;
+ set_len = new_len;
+ }
+ for (i = start; i <= end; i++)
+ set[i] = true;
+ }
+
+ if (!set)
+ return -EINVAL;
+
+ *num_set = set;
+ *num_set_len = set_len;
+
+ return 0;
+}
diff --git a/tools/testing/selftests/bpf/testing_helpers.h b/tools/testing/selftests/bpf/testing_helpers.h
new file mode 100644
index 000000000000..923b51762759
--- /dev/null
+++ b/tools/testing/selftests/bpf/testing_helpers.h
@@ -0,0 +1,5 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+/* Copyright (C) 2020 Facebook, Inc. */
+#include <stdbool.h>
+
+int parse_num_list(const char *s, bool **set, int *set_len);
diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c
index 7f989b3e4e22..4d0e913bbb22 100644
--- a/tools/testing/selftests/bpf/trace_helpers.c
+++ b/tools/testing/selftests/bpf/trace_helpers.c
@@ -4,12 +4,15 @@
#include <string.h>
#include <assert.h>
#include <errno.h>
+#include <fcntl.h>
#include <poll.h>
#include <unistd.h>
#include <linux/perf_event.h>
#include <sys/mman.h>
#include "trace_helpers.h"
+#define DEBUGFS "/sys/kernel/debug/tracing/"
+
#define MAX_SYMS 300000
static struct ksym syms[MAX_SYMS];
static int sym_cnt;
@@ -86,3 +89,23 @@ long ksym_get_addr(const char *name)
return 0;
}
+
+void read_trace_pipe(void)
+{
+ int trace_fd;
+
+ trace_fd = open(DEBUGFS "trace_pipe", O_RDONLY, 0);
+ if (trace_fd < 0)
+ return;
+
+ while (1) {
+ static char buf[4096];
+ ssize_t sz;
+
+ sz = read(trace_fd, buf, sizeof(buf) - 1);
+ if (sz > 0) {
+ buf[sz] = 0;
+ puts(buf);
+ }
+ }
+}
diff --git a/tools/testing/selftests/bpf/trace_helpers.h b/tools/testing/selftests/bpf/trace_helpers.h
index 0383c9b8adc1..25ef597dd03f 100644
--- a/tools/testing/selftests/bpf/trace_helpers.h
+++ b/tools/testing/selftests/bpf/trace_helpers.h
@@ -12,5 +12,6 @@ struct ksym {
int load_kallsyms(void);
struct ksym *ksym_search(long key);
long ksym_get_addr(const char *name);
+void read_trace_pipe(void);
#endif
diff --git a/tools/testing/selftests/bpf/verifier/.gitignore b/tools/testing/selftests/bpf/verifier/.gitignore
index 45984a364647..89c4a3d37544 100644
--- a/tools/testing/selftests/bpf/verifier/.gitignore
+++ b/tools/testing/selftests/bpf/verifier/.gitignore
@@ -1 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
tests.h
diff --git a/tools/testing/selftests/bpf/verifier/and.c b/tools/testing/selftests/bpf/verifier/and.c
index e0fad1548737..d781bc86e100 100644
--- a/tools/testing/selftests/bpf/verifier/and.c
+++ b/tools/testing/selftests/bpf/verifier/and.c
@@ -15,7 +15,7 @@
BPF_EXIT_INSN(),
},
.fixup_map_hash_48b = { 3 },
- .errstr = "R0 max value is outside of the array range",
+ .errstr = "R0 max value is outside of the allowed memory range",
.result = REJECT,
.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
@@ -44,7 +44,7 @@
BPF_EXIT_INSN(),
},
.fixup_map_hash_48b = { 3 },
- .errstr = "R0 max value is outside of the array range",
+ .errstr = "R0 max value is outside of the allowed memory range",
.result = REJECT,
.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
diff --git a/tools/testing/selftests/bpf/verifier/array_access.c b/tools/testing/selftests/bpf/verifier/array_access.c
index f3c33e128709..1c4b1939f5a8 100644
--- a/tools/testing/selftests/bpf/verifier/array_access.c
+++ b/tools/testing/selftests/bpf/verifier/array_access.c
@@ -117,7 +117,7 @@
BPF_EXIT_INSN(),
},
.fixup_map_hash_48b = { 3 },
- .errstr = "R0 min value is outside of the array range",
+ .errstr = "R0 min value is outside of the allowed memory range",
.result = REJECT,
.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
@@ -137,7 +137,7 @@
BPF_EXIT_INSN(),
},
.fixup_map_hash_48b = { 3 },
- .errstr = "R0 unbounded memory access, make sure to bounds check any array access into a map",
+ .errstr = "R0 unbounded memory access, make sure to bounds check any such access",
.result = REJECT,
.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
diff --git a/tools/testing/selftests/bpf/verifier/bounds.c b/tools/testing/selftests/bpf/verifier/bounds.c
index d55f476f2237..4d6645f2874c 100644
--- a/tools/testing/selftests/bpf/verifier/bounds.c
+++ b/tools/testing/selftests/bpf/verifier/bounds.c
@@ -20,7 +20,7 @@
BPF_EXIT_INSN(),
},
.fixup_map_hash_8b = { 3 },
- .errstr = "R0 max value is outside of the array range",
+ .errstr = "R0 max value is outside of the allowed memory range",
.result = REJECT,
},
{
@@ -146,7 +146,7 @@
BPF_EXIT_INSN(),
},
.fixup_map_hash_8b = { 3 },
- .errstr = "R0 min value is outside of the array range",
+ .errstr = "R0 min value is outside of the allowed memory range",
.result = REJECT
},
{
@@ -238,7 +238,7 @@
BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
BPF_LD_MAP_FD(BPF_REG_1, 0),
BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
- BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8),
/* r1 = [0x00, 0xff] */
BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0xffffff80 >> 1),
@@ -253,22 +253,18 @@
* [0xffff'ffff'0000'0080, 0xffff'ffff'ffff'ffff]
*/
BPF_ALU64_IMM(BPF_SUB, BPF_REG_1, 0xffffff80 >> 1),
- /* r1 = 0 or
- * [0x00ff'ffff'ff00'0000, 0x00ff'ffff'ffff'ffff]
- */
- BPF_ALU64_IMM(BPF_RSH, BPF_REG_1, 8),
- /* no-op or OOB pointer computation */
+ /* error on OOB pointer computation */
BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
- /* potentially OOB access */
- BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0),
/* exit */
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
.fixup_map_hash_8b = { 3 },
/* not actually fully unbounded, but the bound is very high */
- .errstr = "R0 unbounded memory access",
- .result = REJECT
+ .errstr_unpriv = "R1 has unknown scalar with mixed signed bounds, pointer arithmetic with it prohibited for !root",
+ .result_unpriv = REJECT,
+ .errstr = "value -4294967168 makes map_value pointer be out of bounds",
+ .result = REJECT,
},
{
"bounds check after truncation of boundary-crossing range (2)",
@@ -278,7 +274,7 @@
BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
BPF_LD_MAP_FD(BPF_REG_1, 0),
BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
- BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8),
/* r1 = [0x00, 0xff] */
BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0xffffff80 >> 1),
@@ -295,22 +291,18 @@
* [0xffff'ffff'0000'0080, 0xffff'ffff'ffff'ffff]
*/
BPF_ALU64_IMM(BPF_SUB, BPF_REG_1, 0xffffff80 >> 1),
- /* r1 = 0 or
- * [0x00ff'ffff'ff00'0000, 0x00ff'ffff'ffff'ffff]
- */
- BPF_ALU64_IMM(BPF_RSH, BPF_REG_1, 8),
- /* no-op or OOB pointer computation */
+ /* error on OOB pointer computation */
BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
- /* potentially OOB access */
- BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0),
/* exit */
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
.fixup_map_hash_8b = { 3 },
/* not actually fully unbounded, but the bound is very high */
- .errstr = "R0 unbounded memory access",
- .result = REJECT
+ .errstr_unpriv = "R1 has unknown scalar with mixed signed bounds, pointer arithmetic with it prohibited for !root",
+ .result_unpriv = REJECT,
+ .errstr = "value -4294967168 makes map_value pointer be out of bounds",
+ .result = REJECT,
},
{
"bounds check after wrapping 32-bit addition",
@@ -362,7 +354,7 @@
BPF_EXIT_INSN(),
},
.fixup_map_hash_8b = { 3 },
- .errstr = "R0 max value is outside of the array range",
+ .errstr = "R0 max value is outside of the allowed memory range",
.result = REJECT
},
{
@@ -411,16 +403,14 @@
BPF_ALU32_IMM(BPF_RSH, BPF_REG_1, 31),
/* r1 = 0xffff'fffe (NOT 0!) */
BPF_ALU32_IMM(BPF_SUB, BPF_REG_1, 2),
- /* computes OOB pointer */
+ /* error on computing OOB pointer */
BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
- /* OOB access */
- BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0),
/* exit */
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
.fixup_map_hash_8b = { 3 },
- .errstr = "R0 invalid mem access",
+ .errstr = "math between map_value pointer and 4294967294 is not allowed",
.result = REJECT,
},
{
@@ -506,3 +496,64 @@
.errstr = "map_value pointer and 1000000000000",
.result = REJECT
},
+{
+ "bounds check mixed 32bit and 64bit arithmetic. test1",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_MOV64_IMM(BPF_REG_1, -1),
+ BPF_ALU64_IMM(BPF_LSH, BPF_REG_1, 32),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 1),
+ /* r1 = 0xffffFFFF00000001 */
+ BPF_JMP32_IMM(BPF_JGT, BPF_REG_1, 1, 3),
+ /* check ALU64 op keeps 32bit bounds */
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 1),
+ BPF_JMP32_IMM(BPF_JGT, BPF_REG_1, 2, 1),
+ BPF_JMP_A(1),
+ /* invalid ldx if bounds are lost above */
+ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, -1),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT
+},
+{
+ "bounds check mixed 32bit and 64bit arithmetic. test2",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_MOV64_IMM(BPF_REG_1, -1),
+ BPF_ALU64_IMM(BPF_LSH, BPF_REG_1, 32),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 1),
+ /* r1 = 0xffffFFFF00000001 */
+ BPF_MOV64_IMM(BPF_REG_2, 3),
+ /* r1 = 0x2 */
+ BPF_ALU32_IMM(BPF_ADD, BPF_REG_1, 1),
+ /* check ALU32 op zero extends 64bit bounds */
+ BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_2, 1),
+ BPF_JMP_A(1),
+ /* invalid ldx if bounds are lost above */
+ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, -1),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT
+},
+{
+ "assigning 32bit bounds to 64bit for wA = 0, wB = wA",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_8, BPF_REG_1,
+ offsetof(struct __sk_buff, data_end)),
+ BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1,
+ offsetof(struct __sk_buff, data)),
+ BPF_MOV32_IMM(BPF_REG_9, 0),
+ BPF_MOV32_REG(BPF_REG_2, BPF_REG_9),
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_7),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_6, BPF_REG_2),
+ BPF_MOV64_REG(BPF_REG_3, BPF_REG_6),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 8),
+ BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_8, 1),
+ BPF_LDX_MEM(BPF_W, BPF_REG_5, BPF_REG_6, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .result = ACCEPT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
diff --git a/tools/testing/selftests/bpf/verifier/bpf_get_stack.c b/tools/testing/selftests/bpf/verifier/bpf_get_stack.c
index f24d50f09dbe..69b048cf46d9 100644
--- a/tools/testing/selftests/bpf/verifier/bpf_get_stack.c
+++ b/tools/testing/selftests/bpf/verifier/bpf_get_stack.c
@@ -9,17 +9,17 @@
BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 28),
BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
- BPF_MOV64_IMM(BPF_REG_9, sizeof(struct test_val)),
+ BPF_MOV64_IMM(BPF_REG_9, sizeof(struct test_val)/2),
BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
BPF_MOV64_REG(BPF_REG_2, BPF_REG_7),
- BPF_MOV64_IMM(BPF_REG_3, sizeof(struct test_val)),
+ BPF_MOV64_IMM(BPF_REG_3, sizeof(struct test_val)/2),
BPF_MOV64_IMM(BPF_REG_4, 256),
BPF_EMIT_CALL(BPF_FUNC_get_stack),
BPF_MOV64_IMM(BPF_REG_1, 0),
BPF_MOV64_REG(BPF_REG_8, BPF_REG_0),
BPF_ALU64_IMM(BPF_LSH, BPF_REG_8, 32),
BPF_ALU64_IMM(BPF_ARSH, BPF_REG_8, 32),
- BPF_JMP_REG(BPF_JSLT, BPF_REG_1, BPF_REG_8, 16),
+ BPF_JMP_REG(BPF_JSGT, BPF_REG_1, BPF_REG_8, 16),
BPF_ALU64_REG(BPF_SUB, BPF_REG_9, BPF_REG_8),
BPF_MOV64_REG(BPF_REG_2, BPF_REG_7),
BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_8),
@@ -29,7 +29,7 @@
BPF_MOV64_REG(BPF_REG_3, BPF_REG_2),
BPF_ALU64_REG(BPF_ADD, BPF_REG_3, BPF_REG_1),
BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
- BPF_MOV64_IMM(BPF_REG_5, sizeof(struct test_val)),
+ BPF_MOV64_IMM(BPF_REG_5, sizeof(struct test_val)/2),
BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_5),
BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 4),
BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
diff --git a/tools/testing/selftests/bpf/verifier/calls.c b/tools/testing/selftests/bpf/verifier/calls.c
index 2d752c4f8d9d..94258c6b5235 100644
--- a/tools/testing/selftests/bpf/verifier/calls.c
+++ b/tools/testing/selftests/bpf/verifier/calls.c
@@ -19,7 +19,7 @@
BPF_MOV64_IMM(BPF_REG_0, 2),
BPF_EXIT_INSN(),
},
- .errstr_unpriv = "function calls to other bpf functions are allowed for root only",
+ .errstr_unpriv = "function calls to other bpf functions are allowed for",
.result_unpriv = REJECT,
.result = ACCEPT,
.retval = 1,
@@ -105,7 +105,7 @@
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.fixup_map_hash_8b = { 16 },
.result = REJECT,
- .errstr = "R0 min value is outside of the array range",
+ .errstr = "R0 min value is outside of the allowed memory range",
},
{
"calls: overlapping caller/callee",
@@ -315,7 +315,7 @@
BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
BPF_EXIT_INSN(),
},
- .errstr_unpriv = "allowed for root only",
+ .errstr_unpriv = "allowed for",
.result_unpriv = REJECT,
.result = ACCEPT,
.retval = POINTER_VALUE,
@@ -346,7 +346,7 @@
BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_2),
BPF_EXIT_INSN(),
},
- .errstr_unpriv = "allowed for root only",
+ .errstr_unpriv = "allowed for",
.result_unpriv = REJECT,
.result = ACCEPT,
.retval = TEST_DATA_LEN + TEST_DATA_LEN - ETH_HLEN - ETH_HLEN,
@@ -397,7 +397,7 @@
BPF_MOV64_IMM(BPF_REG_0, 1),
BPF_EXIT_INSN(),
},
- .errstr_unpriv = "function calls to other bpf functions are allowed for root only",
+ .errstr_unpriv = "function calls to other bpf functions are allowed for",
.fixup_map_hash_48b = { 3 },
.result_unpriv = REJECT,
.result = ACCEPT,
@@ -1064,7 +1064,7 @@
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
- .errstr_unpriv = "allowed for root only",
+ .errstr_unpriv = "allowed for",
.result_unpriv = REJECT,
.errstr = "R0 !read_ok",
.result = REJECT,
@@ -1977,7 +1977,7 @@
BPF_EXIT_INSN(),
},
.prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
- .errstr_unpriv = "function calls to other bpf functions are allowed for root only",
+ .errstr_unpriv = "function calls to other bpf functions are allowed for",
.result_unpriv = REJECT,
.result = ACCEPT,
},
@@ -2003,7 +2003,7 @@
BPF_EXIT_INSN(),
},
.prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
- .errstr_unpriv = "function calls to other bpf functions are allowed for root only",
+ .errstr_unpriv = "function calls to other bpf functions are allowed for",
.errstr = "!read_ok",
.result = REJECT,
},
@@ -2028,7 +2028,7 @@
BPF_EXIT_INSN(),
},
.prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
- .errstr_unpriv = "function calls to other bpf functions are allowed for root only",
+ .errstr_unpriv = "function calls to other bpf functions are allowed for",
.errstr = "!read_ok",
.result = REJECT,
},
diff --git a/tools/testing/selftests/bpf/verifier/const_or.c b/tools/testing/selftests/bpf/verifier/const_or.c
index 84446dfc7c1d..6c214c58e8d4 100644
--- a/tools/testing/selftests/bpf/verifier/const_or.c
+++ b/tools/testing/selftests/bpf/verifier/const_or.c
@@ -6,7 +6,7 @@
BPF_MOV64_IMM(BPF_REG_2, 34),
BPF_ALU64_IMM(BPF_OR, BPF_REG_2, 13),
BPF_MOV64_IMM(BPF_REG_3, 0),
- BPF_EMIT_CALL(BPF_FUNC_probe_read),
+ BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
BPF_EXIT_INSN(),
},
.result = ACCEPT,
@@ -20,7 +20,7 @@
BPF_MOV64_IMM(BPF_REG_2, 34),
BPF_ALU64_IMM(BPF_OR, BPF_REG_2, 24),
BPF_MOV64_IMM(BPF_REG_3, 0),
- BPF_EMIT_CALL(BPF_FUNC_probe_read),
+ BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
BPF_EXIT_INSN(),
},
.errstr = "invalid stack type R1 off=-48 access_size=58",
@@ -36,7 +36,7 @@
BPF_MOV64_IMM(BPF_REG_4, 13),
BPF_ALU64_REG(BPF_OR, BPF_REG_2, BPF_REG_4),
BPF_MOV64_IMM(BPF_REG_3, 0),
- BPF_EMIT_CALL(BPF_FUNC_probe_read),
+ BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
BPF_EXIT_INSN(),
},
.result = ACCEPT,
@@ -51,7 +51,7 @@
BPF_MOV64_IMM(BPF_REG_4, 24),
BPF_ALU64_REG(BPF_OR, BPF_REG_2, BPF_REG_4),
BPF_MOV64_IMM(BPF_REG_3, 0),
- BPF_EMIT_CALL(BPF_FUNC_probe_read),
+ BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
BPF_EXIT_INSN(),
},
.errstr = "invalid stack type R1 off=-48 access_size=58",
diff --git a/tools/testing/selftests/bpf/verifier/ctx.c b/tools/testing/selftests/bpf/verifier/ctx.c
index 92762c08f5e3..93d6b1641481 100644
--- a/tools/testing/selftests/bpf/verifier/ctx.c
+++ b/tools/testing/selftests/bpf/verifier/ctx.c
@@ -91,3 +91,108 @@
.result = REJECT,
.errstr = "variable ctx access var_off=(0x0; 0x4)",
},
+{
+ "pass ctx or null check, 1: ctx",
+ .insns = {
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_get_netns_cookie),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
+ .expected_attach_type = BPF_CGROUP_UDP6_SENDMSG,
+ .result = ACCEPT,
+},
+{
+ "pass ctx or null check, 2: null",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_get_netns_cookie),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
+ .expected_attach_type = BPF_CGROUP_UDP6_SENDMSG,
+ .result = ACCEPT,
+},
+{
+ "pass ctx or null check, 3: 1",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_1, 1),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_get_netns_cookie),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
+ .expected_attach_type = BPF_CGROUP_UDP6_SENDMSG,
+ .result = REJECT,
+ .errstr = "R1 type=inv expected=ctx",
+},
+{
+ "pass ctx or null check, 4: ctx - const",
+ .insns = {
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -612),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_get_netns_cookie),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
+ .expected_attach_type = BPF_CGROUP_UDP6_SENDMSG,
+ .result = REJECT,
+ .errstr = "dereference of modified ctx ptr",
+},
+{
+ "pass ctx or null check, 5: null (connect)",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_get_netns_cookie),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
+ .expected_attach_type = BPF_CGROUP_INET4_CONNECT,
+ .result = ACCEPT,
+},
+{
+ "pass ctx or null check, 6: null (bind)",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_get_netns_cookie),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_CGROUP_SOCK,
+ .expected_attach_type = BPF_CGROUP_INET4_POST_BIND,
+ .result = ACCEPT,
+},
+{
+ "pass ctx or null check, 7: ctx (bind)",
+ .insns = {
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_get_socket_cookie),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_CGROUP_SOCK,
+ .expected_attach_type = BPF_CGROUP_INET4_POST_BIND,
+ .result = ACCEPT,
+},
+{
+ "pass ctx or null check, 8: null (bind)",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_get_socket_cookie),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_CGROUP_SOCK,
+ .expected_attach_type = BPF_CGROUP_INET4_POST_BIND,
+ .result = REJECT,
+ .errstr = "R1 type=inv expected=ctx",
+},
diff --git a/tools/testing/selftests/bpf/verifier/ctx_skb.c b/tools/testing/selftests/bpf/verifier/ctx_skb.c
index d438193804b2..2e16b8e268f2 100644
--- a/tools/testing/selftests/bpf/verifier/ctx_skb.c
+++ b/tools/testing/selftests/bpf/verifier/ctx_skb.c
@@ -1011,6 +1011,53 @@
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
},
{
+ "read gso_size from CGROUP_SKB",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+ offsetof(struct __sk_buff, gso_size)),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+},
+{
+ "read gso_size from CGROUP_SKB",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_1,
+ offsetof(struct __sk_buff, gso_size)),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+},
+{
+ "write gso_size from CGROUP_SKB",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0,
+ offsetof(struct __sk_buff, gso_size)),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .result = REJECT,
+ .result_unpriv = REJECT,
+ .errstr = "invalid bpf_context access off=176 size=4",
+ .prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+},
+{
+ "read gso_size from CLS",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+ offsetof(struct __sk_buff, gso_size)),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+},
+{
"check wire_len is not readable by sockets",
.insns = {
BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
diff --git a/tools/testing/selftests/bpf/verifier/dead_code.c b/tools/testing/selftests/bpf/verifier/dead_code.c
index 50a8a63be4ac..5cf361d8eb1c 100644
--- a/tools/testing/selftests/bpf/verifier/dead_code.c
+++ b/tools/testing/selftests/bpf/verifier/dead_code.c
@@ -85,7 +85,7 @@
BPF_MOV64_IMM(BPF_REG_0, 12),
BPF_EXIT_INSN(),
},
- .errstr_unpriv = "function calls to other bpf functions are allowed for root only",
+ .errstr_unpriv = "function calls to other bpf functions are allowed for",
.result_unpriv = REJECT,
.result = ACCEPT,
.retval = 7,
@@ -103,7 +103,7 @@
BPF_MOV64_IMM(BPF_REG_0, 12),
BPF_EXIT_INSN(),
},
- .errstr_unpriv = "function calls to other bpf functions are allowed for root only",
+ .errstr_unpriv = "function calls to other bpf functions are allowed for",
.result_unpriv = REJECT,
.result = ACCEPT,
.retval = 7,
@@ -121,7 +121,7 @@
BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, -5),
BPF_EXIT_INSN(),
},
- .errstr_unpriv = "function calls to other bpf functions are allowed for root only",
+ .errstr_unpriv = "function calls to other bpf functions are allowed for",
.result_unpriv = REJECT,
.result = ACCEPT,
.retval = 7,
@@ -137,7 +137,7 @@
BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
BPF_EXIT_INSN(),
},
- .errstr_unpriv = "function calls to other bpf functions are allowed for root only",
+ .errstr_unpriv = "function calls to other bpf functions are allowed for",
.result_unpriv = REJECT,
.result = ACCEPT,
.retval = 2,
@@ -152,7 +152,7 @@
BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
BPF_EXIT_INSN(),
},
- .errstr_unpriv = "function calls to other bpf functions are allowed for root only",
+ .errstr_unpriv = "function calls to other bpf functions are allowed for",
.result_unpriv = REJECT,
.result = ACCEPT,
.retval = 2,
diff --git a/tools/testing/selftests/bpf/verifier/direct_value_access.c b/tools/testing/selftests/bpf/verifier/direct_value_access.c
index b9fb28e8e224..988f46a1a4c7 100644
--- a/tools/testing/selftests/bpf/verifier/direct_value_access.c
+++ b/tools/testing/selftests/bpf/verifier/direct_value_access.c
@@ -68,7 +68,7 @@
},
.fixup_map_array_48b = { 1 },
.result = REJECT,
- .errstr = "R1 min value is outside of the array range",
+ .errstr = "R1 min value is outside of the allowed memory range",
},
{
"direct map access, write test 7",
@@ -220,7 +220,7 @@
},
.fixup_map_array_small = { 1 },
.result = REJECT,
- .errstr = "R1 min value is outside of the array range",
+ .errstr = "R1 min value is outside of the allowed memory range",
},
{
"direct map access, write test 19",
diff --git a/tools/testing/selftests/bpf/verifier/event_output.c b/tools/testing/selftests/bpf/verifier/event_output.c
index 130553e19eca..99f8f582c02b 100644
--- a/tools/testing/selftests/bpf/verifier/event_output.c
+++ b/tools/testing/selftests/bpf/verifier/event_output.c
@@ -92,3 +92,27 @@
.result = ACCEPT,
.retval = 1,
},
+{
+ "perfevent for cgroup dev",
+ .insns = { __PERF_EVENT_INSNS__ },
+ .prog_type = BPF_PROG_TYPE_CGROUP_DEVICE,
+ .fixup_map_event_output = { 4 },
+ .result = ACCEPT,
+ .retval = 1,
+},
+{
+ "perfevent for cgroup sysctl",
+ .insns = { __PERF_EVENT_INSNS__ },
+ .prog_type = BPF_PROG_TYPE_CGROUP_SYSCTL,
+ .fixup_map_event_output = { 4 },
+ .result = ACCEPT,
+ .retval = 1,
+},
+{
+ "perfevent for cgroup sockopt",
+ .insns = { __PERF_EVENT_INSNS__ },
+ .prog_type = BPF_PROG_TYPE_CGROUP_SOCKOPT,
+ .fixup_map_event_output = { 4 },
+ .result = ACCEPT,
+ .retval = 1,
+},
diff --git a/tools/testing/selftests/bpf/verifier/helper_access_var_len.c b/tools/testing/selftests/bpf/verifier/helper_access_var_len.c
index 67ab12410050..87c4e7900083 100644
--- a/tools/testing/selftests/bpf/verifier/helper_access_var_len.c
+++ b/tools/testing/selftests/bpf/verifier/helper_access_var_len.c
@@ -19,7 +19,7 @@
BPF_MOV64_IMM(BPF_REG_4, 0),
BPF_JMP_REG(BPF_JGE, BPF_REG_4, BPF_REG_2, 2),
BPF_MOV64_IMM(BPF_REG_3, 0),
- BPF_EMIT_CALL(BPF_FUNC_probe_read),
+ BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
@@ -36,7 +36,7 @@
BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -128),
BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 64),
BPF_MOV64_IMM(BPF_REG_3, 0),
- BPF_EMIT_CALL(BPF_FUNC_probe_read),
+ BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
BPF_EXIT_INSN(),
},
.errstr = "invalid indirect read from stack off -64+0 size 64",
@@ -55,7 +55,7 @@
BPF_MOV64_IMM(BPF_REG_4, 0),
BPF_JMP_REG(BPF_JGE, BPF_REG_4, BPF_REG_2, 2),
BPF_MOV64_IMM(BPF_REG_3, 0),
- BPF_EMIT_CALL(BPF_FUNC_probe_read),
+ BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
@@ -84,7 +84,7 @@
BPF_MOV64_IMM(BPF_REG_4, 0),
BPF_JMP_REG(BPF_JGE, BPF_REG_4, BPF_REG_2, 2),
BPF_MOV64_IMM(BPF_REG_3, 0),
- BPF_EMIT_CALL(BPF_FUNC_probe_read),
+ BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
@@ -112,7 +112,7 @@
BPF_MOV64_IMM(BPF_REG_4, 0),
BPF_JMP_REG(BPF_JSGE, BPF_REG_4, BPF_REG_2, 2),
BPF_MOV64_IMM(BPF_REG_3, 0),
- BPF_EMIT_CALL(BPF_FUNC_probe_read),
+ BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
@@ -132,7 +132,7 @@
BPF_JMP_REG(BPF_JGE, BPF_REG_4, BPF_REG_2, 3),
BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 1),
BPF_MOV64_IMM(BPF_REG_3, 0),
- BPF_EMIT_CALL(BPF_FUNC_probe_read),
+ BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
@@ -152,7 +152,7 @@
BPF_MOV64_IMM(BPF_REG_4, 0),
BPF_JMP_REG(BPF_JGE, BPF_REG_4, BPF_REG_2, 2),
BPF_MOV64_IMM(BPF_REG_3, 0),
- BPF_EMIT_CALL(BPF_FUNC_probe_read),
+ BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
@@ -171,7 +171,7 @@
BPF_MOV64_IMM(BPF_REG_4, 0),
BPF_JMP_REG(BPF_JGE, BPF_REG_4, BPF_REG_2, 2),
BPF_MOV64_IMM(BPF_REG_3, 0),
- BPF_EMIT_CALL(BPF_FUNC_probe_read),
+ BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
@@ -190,7 +190,7 @@
BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -128),
BPF_JMP_IMM(BPF_JGT, BPF_REG_2, 64, 3),
BPF_MOV64_IMM(BPF_REG_3, 0),
- BPF_EMIT_CALL(BPF_FUNC_probe_read),
+ BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
@@ -208,7 +208,7 @@
BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -128),
BPF_JMP_IMM(BPF_JSGT, BPF_REG_2, 64, 3),
BPF_MOV64_IMM(BPF_REG_3, 0),
- BPF_EMIT_CALL(BPF_FUNC_probe_read),
+ BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
@@ -233,7 +233,7 @@
BPF_MOV64_IMM(BPF_REG_4, 0),
BPF_JMP_REG(BPF_JSGE, BPF_REG_4, BPF_REG_2, 2),
BPF_MOV64_IMM(BPF_REG_3, 0),
- BPF_EMIT_CALL(BPF_FUNC_probe_read),
+ BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
@@ -259,7 +259,7 @@
BPF_MOV64_IMM(BPF_REG_4, 0),
BPF_JMP_REG(BPF_JSGE, BPF_REG_4, BPF_REG_2, 2),
BPF_MOV64_IMM(BPF_REG_3, 0),
- BPF_EMIT_CALL(BPF_FUNC_probe_read),
+ BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
@@ -286,7 +286,7 @@
BPF_MOV64_IMM(BPF_REG_4, 0),
BPF_JMP_REG(BPF_JSGE, BPF_REG_4, BPF_REG_2, 2),
BPF_MOV64_IMM(BPF_REG_3, 0),
- BPF_EMIT_CALL(BPF_FUNC_probe_read),
+ BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
@@ -313,12 +313,12 @@
BPF_MOV64_IMM(BPF_REG_4, 0),
BPF_JMP_REG(BPF_JSGE, BPF_REG_4, BPF_REG_2, 2),
BPF_MOV64_IMM(BPF_REG_3, 0),
- BPF_EMIT_CALL(BPF_FUNC_probe_read),
+ BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
.fixup_map_hash_48b = { 4 },
- .errstr = "R1 min value is outside of the array range",
+ .errstr = "R1 min value is outside of the allowed memory range",
.result = REJECT,
.prog_type = BPF_PROG_TYPE_TRACEPOINT,
},
@@ -468,7 +468,7 @@
BPF_MOV64_IMM(BPF_REG_1, 0),
BPF_MOV64_IMM(BPF_REG_2, 0),
BPF_MOV64_IMM(BPF_REG_3, 0),
- BPF_EMIT_CALL(BPF_FUNC_probe_read),
+ BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
BPF_EXIT_INSN(),
},
.errstr = "R1 type=inv expected=fp",
@@ -481,7 +481,7 @@
BPF_MOV64_IMM(BPF_REG_1, 0),
BPF_MOV64_IMM(BPF_REG_2, 1),
BPF_MOV64_IMM(BPF_REG_3, 0),
- BPF_EMIT_CALL(BPF_FUNC_probe_read),
+ BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
BPF_EXIT_INSN(),
},
.errstr = "R1 type=inv expected=fp",
@@ -495,7 +495,7 @@
BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
BPF_MOV64_IMM(BPF_REG_2, 0),
BPF_MOV64_IMM(BPF_REG_3, 0),
- BPF_EMIT_CALL(BPF_FUNC_probe_read),
+ BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
BPF_EXIT_INSN(),
},
.result = ACCEPT,
@@ -513,7 +513,7 @@
BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
BPF_MOV64_IMM(BPF_REG_2, 0),
BPF_MOV64_IMM(BPF_REG_3, 0),
- BPF_EMIT_CALL(BPF_FUNC_probe_read),
+ BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
BPF_EXIT_INSN(),
},
.fixup_map_hash_8b = { 3 },
@@ -534,7 +534,7 @@
BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
BPF_MOV64_IMM(BPF_REG_3, 0),
- BPF_EMIT_CALL(BPF_FUNC_probe_read),
+ BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
BPF_EXIT_INSN(),
},
.fixup_map_hash_8b = { 3 },
@@ -554,7 +554,7 @@
BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_0, 0),
BPF_JMP_IMM(BPF_JGT, BPF_REG_2, 8, 2),
BPF_MOV64_IMM(BPF_REG_3, 0),
- BPF_EMIT_CALL(BPF_FUNC_probe_read),
+ BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
BPF_EXIT_INSN(),
},
.fixup_map_hash_8b = { 3 },
@@ -580,7 +580,7 @@
BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 63),
BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 1),
BPF_MOV64_IMM(BPF_REG_3, 0),
- BPF_EMIT_CALL(BPF_FUNC_probe_read),
+ BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16),
BPF_EXIT_INSN(),
},
@@ -607,7 +607,7 @@
BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 32),
BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 32),
BPF_MOV64_IMM(BPF_REG_3, 0),
- BPF_EMIT_CALL(BPF_FUNC_probe_read),
+ BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16),
BPF_EXIT_INSN(),
},
diff --git a/tools/testing/selftests/bpf/verifier/helper_value_access.c b/tools/testing/selftests/bpf/verifier/helper_value_access.c
index 7572e403ddb9..1c7882ddfa63 100644
--- a/tools/testing/selftests/bpf/verifier/helper_value_access.c
+++ b/tools/testing/selftests/bpf/verifier/helper_value_access.c
@@ -10,7 +10,7 @@
BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
BPF_MOV64_IMM(BPF_REG_2, sizeof(struct test_val)),
BPF_MOV64_IMM(BPF_REG_3, 0),
- BPF_EMIT_CALL(BPF_FUNC_probe_read),
+ BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
BPF_EXIT_INSN(),
},
.fixup_map_hash_48b = { 3 },
@@ -29,7 +29,7 @@
BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
BPF_MOV64_IMM(BPF_REG_2, 8),
BPF_MOV64_IMM(BPF_REG_3, 0),
- BPF_EMIT_CALL(BPF_FUNC_probe_read),
+ BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
BPF_EXIT_INSN(),
},
.fixup_map_hash_48b = { 3 },
@@ -67,7 +67,7 @@
BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
BPF_MOV64_IMM(BPF_REG_2, sizeof(struct test_val) + 8),
BPF_MOV64_IMM(BPF_REG_3, 0),
- BPF_EMIT_CALL(BPF_FUNC_probe_read),
+ BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
BPF_EXIT_INSN(),
},
.fixup_map_hash_48b = { 3 },
@@ -87,7 +87,7 @@
BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
BPF_MOV64_IMM(BPF_REG_2, -8),
BPF_MOV64_IMM(BPF_REG_3, 0),
- BPF_EMIT_CALL(BPF_FUNC_probe_read),
+ BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
BPF_EXIT_INSN(),
},
.fixup_map_hash_48b = { 3 },
@@ -109,7 +109,7 @@
BPF_MOV64_IMM(BPF_REG_2,
sizeof(struct test_val) - offsetof(struct test_val, foo)),
BPF_MOV64_IMM(BPF_REG_3, 0),
- BPF_EMIT_CALL(BPF_FUNC_probe_read),
+ BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
BPF_EXIT_INSN(),
},
.fixup_map_hash_48b = { 3 },
@@ -129,7 +129,7 @@
BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, offsetof(struct test_val, foo)),
BPF_MOV64_IMM(BPF_REG_2, 8),
BPF_MOV64_IMM(BPF_REG_3, 0),
- BPF_EMIT_CALL(BPF_FUNC_probe_read),
+ BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
BPF_EXIT_INSN(),
},
.fixup_map_hash_48b = { 3 },
@@ -170,7 +170,7 @@
BPF_MOV64_IMM(BPF_REG_2,
sizeof(struct test_val) - offsetof(struct test_val, foo) + 8),
BPF_MOV64_IMM(BPF_REG_3, 0),
- BPF_EMIT_CALL(BPF_FUNC_probe_read),
+ BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
BPF_EXIT_INSN(),
},
.fixup_map_hash_48b = { 3 },
@@ -191,7 +191,7 @@
BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, offsetof(struct test_val, foo)),
BPF_MOV64_IMM(BPF_REG_2, -8),
BPF_MOV64_IMM(BPF_REG_3, 0),
- BPF_EMIT_CALL(BPF_FUNC_probe_read),
+ BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
BPF_EXIT_INSN(),
},
.fixup_map_hash_48b = { 3 },
@@ -212,7 +212,7 @@
BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, offsetof(struct test_val, foo)),
BPF_MOV64_IMM(BPF_REG_2, -1),
BPF_MOV64_IMM(BPF_REG_3, 0),
- BPF_EMIT_CALL(BPF_FUNC_probe_read),
+ BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
BPF_EXIT_INSN(),
},
.fixup_map_hash_48b = { 3 },
@@ -235,7 +235,7 @@
BPF_MOV64_IMM(BPF_REG_2,
sizeof(struct test_val) - offsetof(struct test_val, foo)),
BPF_MOV64_IMM(BPF_REG_3, 0),
- BPF_EMIT_CALL(BPF_FUNC_probe_read),
+ BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
BPF_EXIT_INSN(),
},
.fixup_map_hash_48b = { 3 },
@@ -256,7 +256,7 @@
BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
BPF_MOV64_IMM(BPF_REG_2, 8),
BPF_MOV64_IMM(BPF_REG_3, 0),
- BPF_EMIT_CALL(BPF_FUNC_probe_read),
+ BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
BPF_EXIT_INSN(),
},
.fixup_map_hash_48b = { 3 },
@@ -280,7 +280,7 @@
BPF_EXIT_INSN(),
},
.fixup_map_hash_48b = { 3 },
- .errstr = "R1 min value is outside of the array range",
+ .errstr = "R1 min value is outside of the allowed memory range",
.result = REJECT,
.prog_type = BPF_PROG_TYPE_TRACEPOINT,
},
@@ -300,7 +300,7 @@
sizeof(struct test_val) -
offsetof(struct test_val, foo) + 8),
BPF_MOV64_IMM(BPF_REG_3, 0),
- BPF_EMIT_CALL(BPF_FUNC_probe_read),
+ BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
BPF_EXIT_INSN(),
},
.fixup_map_hash_48b = { 3 },
@@ -322,7 +322,7 @@
BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
BPF_MOV64_IMM(BPF_REG_2, -8),
BPF_MOV64_IMM(BPF_REG_3, 0),
- BPF_EMIT_CALL(BPF_FUNC_probe_read),
+ BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
BPF_EXIT_INSN(),
},
.fixup_map_hash_48b = { 3 },
@@ -344,7 +344,7 @@
BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
BPF_MOV64_IMM(BPF_REG_2, -1),
BPF_MOV64_IMM(BPF_REG_3, 0),
- BPF_EMIT_CALL(BPF_FUNC_probe_read),
+ BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
BPF_EXIT_INSN(),
},
.fixup_map_hash_48b = { 3 },
@@ -368,7 +368,7 @@
BPF_MOV64_IMM(BPF_REG_2,
sizeof(struct test_val) - offsetof(struct test_val, foo)),
BPF_MOV64_IMM(BPF_REG_3, 0),
- BPF_EMIT_CALL(BPF_FUNC_probe_read),
+ BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
BPF_EXIT_INSN(),
},
.fixup_map_hash_48b = { 3 },
@@ -390,7 +390,7 @@
BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
BPF_MOV64_IMM(BPF_REG_2, 8),
BPF_MOV64_IMM(BPF_REG_3, 0),
- BPF_EMIT_CALL(BPF_FUNC_probe_read),
+ BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
BPF_EXIT_INSN(),
},
.fixup_map_hash_48b = { 3 },
@@ -415,7 +415,7 @@
BPF_EXIT_INSN(),
},
.fixup_map_hash_48b = { 3 },
- .errstr = "R1 min value is outside of the array range",
+ .errstr = "R1 min value is outside of the allowed memory range",
.result = REJECT,
.prog_type = BPF_PROG_TYPE_TRACEPOINT,
},
@@ -433,7 +433,7 @@
BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
BPF_MOV64_IMM(BPF_REG_2, 1),
BPF_MOV64_IMM(BPF_REG_3, 0),
- BPF_EMIT_CALL(BPF_FUNC_probe_read),
+ BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
BPF_EXIT_INSN(),
},
.fixup_map_hash_48b = { 3 },
@@ -458,7 +458,7 @@
sizeof(struct test_val) -
offsetof(struct test_val, foo) + 1),
BPF_MOV64_IMM(BPF_REG_3, 0),
- BPF_EMIT_CALL(BPF_FUNC_probe_read),
+ BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
BPF_EXIT_INSN(),
},
.fixup_map_hash_48b = { 3 },
@@ -926,7 +926,7 @@
},
.fixup_map_hash_16b = { 3, 10 },
.result = REJECT,
- .errstr = "R2 unbounded memory access, make sure to bounds check any array access into a map",
+ .errstr = "R2 unbounded memory access, make sure to bounds check any such access",
.prog_type = BPF_PROG_TYPE_TRACEPOINT,
},
{
diff --git a/tools/testing/selftests/bpf/verifier/precise.c b/tools/testing/selftests/bpf/verifier/precise.c
index 02151f8c940f..6dc8003ffc70 100644
--- a/tools/testing/selftests/bpf/verifier/precise.c
+++ b/tools/testing/selftests/bpf/verifier/precise.c
@@ -31,14 +31,14 @@
BPF_MOV64_REG(BPF_REG_1, BPF_REG_FP),
BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
BPF_MOV64_IMM(BPF_REG_3, 0),
- BPF_EMIT_CALL(BPF_FUNC_probe_read),
+ BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
BPF_EXIT_INSN(),
},
.prog_type = BPF_PROG_TYPE_TRACEPOINT,
.fixup_map_array_48b = { 1 },
.result = VERBOSE_ACCEPT,
.errstr =
- "26: (85) call bpf_probe_read#4\
+ "26: (85) call bpf_probe_read_kernel#113\
last_idx 26 first_idx 20\
regs=4 stack=0 before 25\
regs=4 stack=0 before 24\
@@ -91,7 +91,7 @@
BPF_MOV64_REG(BPF_REG_1, BPF_REG_FP),
BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
BPF_MOV64_IMM(BPF_REG_3, 0),
- BPF_EMIT_CALL(BPF_FUNC_probe_read),
+ BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
BPF_EXIT_INSN(),
},
.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -99,7 +99,7 @@
.result = VERBOSE_ACCEPT,
.flags = BPF_F_TEST_STATE_FREQ,
.errstr =
- "26: (85) call bpf_probe_read#4\
+ "26: (85) call bpf_probe_read_kernel#113\
last_idx 26 first_idx 22\
regs=4 stack=0 before 25\
regs=4 stack=0 before 24\
diff --git a/tools/testing/selftests/bpf/verifier/prevent_map_lookup.c b/tools/testing/selftests/bpf/verifier/prevent_map_lookup.c
index da7a4b37cb98..fc4e301260f6 100644
--- a/tools/testing/selftests/bpf/verifier/prevent_map_lookup.c
+++ b/tools/testing/selftests/bpf/verifier/prevent_map_lookup.c
@@ -1,34 +1,4 @@
{
- "prevent map lookup in sockmap",
- .insns = {
- BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
- BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
- BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
- BPF_LD_MAP_FD(BPF_REG_1, 0),
- BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
- BPF_EXIT_INSN(),
- },
- .fixup_map_sockmap = { 3 },
- .result = REJECT,
- .errstr = "cannot pass map_type 15 into func bpf_map_lookup_elem",
- .prog_type = BPF_PROG_TYPE_SOCK_OPS,
-},
-{
- "prevent map lookup in sockhash",
- .insns = {
- BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
- BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
- BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
- BPF_LD_MAP_FD(BPF_REG_1, 0),
- BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
- BPF_EXIT_INSN(),
- },
- .fixup_map_sockhash = { 3 },
- .result = REJECT,
- .errstr = "cannot pass map_type 18 into func bpf_map_lookup_elem",
- .prog_type = BPF_PROG_TYPE_SOCK_OPS,
-},
-{
"prevent map lookup in stack trace",
.insns = {
BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
diff --git a/tools/testing/selftests/bpf/verifier/ref_tracking.c b/tools/testing/selftests/bpf/verifier/ref_tracking.c
index 604b46151736..056e0273bf12 100644
--- a/tools/testing/selftests/bpf/verifier/ref_tracking.c
+++ b/tools/testing/selftests/bpf/verifier/ref_tracking.c
@@ -821,3 +821,36 @@
.result = REJECT,
.errstr = "invalid mem access",
},
+{
+ "reference tracking: branch tracking valid pointer null comparison",
+ .insns = {
+ BPF_SK_LOOKUP(sk_lookup_tcp),
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+ BPF_MOV64_IMM(BPF_REG_3, 1),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_6, 0, 1),
+ BPF_MOV64_IMM(BPF_REG_3, 0),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_6, 0, 2),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+ BPF_EMIT_CALL(BPF_FUNC_sk_release),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .result = ACCEPT,
+},
+{
+ "reference tracking: branch tracking valid pointer value comparison",
+ .insns = {
+ BPF_SK_LOOKUP(sk_lookup_tcp),
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+ BPF_MOV64_IMM(BPF_REG_3, 1),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_6, 0, 4),
+ BPF_MOV64_IMM(BPF_REG_3, 0),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_6, 1234, 2),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+ BPF_EMIT_CALL(BPF_FUNC_sk_release),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .errstr = "Unreleased reference",
+ .result = REJECT,
+},
diff --git a/tools/testing/selftests/bpf/verifier/sock.c b/tools/testing/selftests/bpf/verifier/sock.c
index 9ed192e14f5f..b1aac2641498 100644
--- a/tools/testing/selftests/bpf/verifier/sock.c
+++ b/tools/testing/selftests/bpf/verifier/sock.c
@@ -222,7 +222,7 @@
BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
- BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, offsetofend(struct bpf_sock, state)),
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, offsetofend(struct bpf_sock, rx_queue_mapping)),
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
@@ -516,3 +516,118 @@
.prog_type = BPF_PROG_TYPE_XDP,
.result = ACCEPT,
},
+{
+ "bpf_map_lookup_elem(sockmap, &key)",
+ .insns = {
+ BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_sockmap = { 3 },
+ .prog_type = BPF_PROG_TYPE_SK_SKB,
+ .result = REJECT,
+ .errstr = "Unreleased reference id=2 alloc_insn=5",
+},
+{
+ "bpf_map_lookup_elem(sockhash, &key)",
+ .insns = {
+ BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_sockhash = { 3 },
+ .prog_type = BPF_PROG_TYPE_SK_SKB,
+ .result = REJECT,
+ .errstr = "Unreleased reference id=2 alloc_insn=5",
+},
+{
+ "bpf_map_lookup_elem(sockmap, &key); sk->type [fullsock field]; bpf_sk_release(sk)",
+ .insns = {
+ BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+ BPF_EXIT_INSN(),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, type)),
+ BPF_EMIT_CALL(BPF_FUNC_sk_release),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_sockmap = { 3 },
+ .prog_type = BPF_PROG_TYPE_SK_SKB,
+ .result = ACCEPT,
+},
+{
+ "bpf_map_lookup_elem(sockhash, &key); sk->type [fullsock field]; bpf_sk_release(sk)",
+ .insns = {
+ BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+ BPF_EXIT_INSN(),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, type)),
+ BPF_EMIT_CALL(BPF_FUNC_sk_release),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_sockhash = { 3 },
+ .prog_type = BPF_PROG_TYPE_SK_SKB,
+ .result = ACCEPT,
+},
+{
+ "bpf_sk_select_reuseport(ctx, reuseport_array, &key, flags)",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_4, 0),
+ BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0),
+ BPF_MOV64_REG(BPF_REG_3, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, -4),
+ BPF_LD_MAP_FD(BPF_REG_2, 0),
+ BPF_EMIT_CALL(BPF_FUNC_sk_select_reuseport),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_reuseport_array = { 4 },
+ .prog_type = BPF_PROG_TYPE_SK_REUSEPORT,
+ .result = ACCEPT,
+},
+{
+ "bpf_sk_select_reuseport(ctx, sockmap, &key, flags)",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_4, 0),
+ BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0),
+ BPF_MOV64_REG(BPF_REG_3, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, -4),
+ BPF_LD_MAP_FD(BPF_REG_2, 0),
+ BPF_EMIT_CALL(BPF_FUNC_sk_select_reuseport),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_sockmap = { 4 },
+ .prog_type = BPF_PROG_TYPE_SK_REUSEPORT,
+ .result = ACCEPT,
+},
+{
+ "bpf_sk_select_reuseport(ctx, sockhash, &key, flags)",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_4, 0),
+ BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0),
+ BPF_MOV64_REG(BPF_REG_3, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, -4),
+ BPF_LD_MAP_FD(BPF_REG_2, 0),
+ BPF_EMIT_CALL(BPF_FUNC_sk_select_reuseport),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_sockmap = { 4 },
+ .prog_type = BPF_PROG_TYPE_SK_REUSEPORT,
+ .result = ACCEPT,
+},
diff --git a/tools/testing/selftests/bpf/verifier/stack_ptr.c b/tools/testing/selftests/bpf/verifier/stack_ptr.c
index 7276620ef242..8bfeb77c60bd 100644
--- a/tools/testing/selftests/bpf/verifier/stack_ptr.c
+++ b/tools/testing/selftests/bpf/verifier/stack_ptr.c
@@ -315,3 +315,43 @@
},
.result = ACCEPT,
},
+{
+ "store PTR_TO_STACK in R10 to array map using BPF_B",
+ .insns = {
+ /* Load pointer to map. */
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
+ BPF_MOV64_IMM(BPF_REG_0, 2),
+ BPF_EXIT_INSN(),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+ /* Copy R10 to R9. */
+ BPF_MOV64_REG(BPF_REG_9, BPF_REG_10),
+ /* Pollute other registers with unaligned values. */
+ BPF_MOV64_IMM(BPF_REG_2, -1),
+ BPF_MOV64_IMM(BPF_REG_3, -1),
+ BPF_MOV64_IMM(BPF_REG_4, -1),
+ BPF_MOV64_IMM(BPF_REG_5, -1),
+ BPF_MOV64_IMM(BPF_REG_6, -1),
+ BPF_MOV64_IMM(BPF_REG_7, -1),
+ BPF_MOV64_IMM(BPF_REG_8, -1),
+ /* Store both R9 and R10 with BPF_B and read back. */
+ BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_10, 0),
+ BPF_LDX_MEM(BPF_B, BPF_REG_2, BPF_REG_1, 0),
+ BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_9, 0),
+ BPF_LDX_MEM(BPF_B, BPF_REG_3, BPF_REG_1, 0),
+ /* Should read back as same value. */
+ BPF_JMP_REG(BPF_JEQ, BPF_REG_2, BPF_REG_3, 2),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ BPF_MOV64_IMM(BPF_REG_0, 42),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_array_48b = { 3 },
+ .result = ACCEPT,
+ .retval = 42,
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+},
diff --git a/tools/testing/selftests/bpf/verifier/value_illegal_alu.c b/tools/testing/selftests/bpf/verifier/value_illegal_alu.c
index 7f6c232cd842..ed1c2cea1dea 100644
--- a/tools/testing/selftests/bpf/verifier/value_illegal_alu.c
+++ b/tools/testing/selftests/bpf/verifier/value_illegal_alu.c
@@ -88,6 +88,7 @@
BPF_EXIT_INSN(),
},
.fixup_map_hash_48b = { 3 },
+ .errstr_unpriv = "leaking pointer from stack off -8",
.errstr = "R0 invalid mem access 'inv'",
.result = REJECT,
.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
diff --git a/tools/testing/selftests/bpf/verifier/value_or_null.c b/tools/testing/selftests/bpf/verifier/value_or_null.c
index 860d4a71cd83..3ecb70a3d939 100644
--- a/tools/testing/selftests/bpf/verifier/value_or_null.c
+++ b/tools/testing/selftests/bpf/verifier/value_or_null.c
@@ -150,3 +150,22 @@
.result_unpriv = REJECT,
.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
+{
+ "map lookup and null branch prediction",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_1, 10),
+ BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_1, -8),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_6, 0, 2),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_6, 0, 1),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_10, 10),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_hash_8b = { 4 },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .result = ACCEPT,
+},
diff --git a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
index a53d99cebd9f..97ee658e1242 100644
--- a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
+++ b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
@@ -50,7 +50,7 @@
.fixup_map_array_48b = { 8 },
.result = ACCEPT,
.result_unpriv = REJECT,
- .errstr_unpriv = "R0 min value is outside of the array range",
+ .errstr_unpriv = "R0 min value is outside of the allowed memory range",
.retval = 1,
},
{
@@ -325,7 +325,7 @@
},
.fixup_map_array_48b = { 3 },
.result = REJECT,
- .errstr = "R0 min value is outside of the array range",
+ .errstr = "R0 min value is outside of the allowed memory range",
.result_unpriv = REJECT,
.errstr_unpriv = "R0 pointer arithmetic of map value goes out of range",
},
@@ -601,7 +601,7 @@
},
.fixup_map_array_48b = { 3 },
.result = REJECT,
- .errstr = "R1 max value is outside of the array range",
+ .errstr = "R1 max value is outside of the allowed memory range",
.errstr_unpriv = "R1 pointer arithmetic of map value goes out of range",
.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
@@ -726,7 +726,7 @@
},
.fixup_map_array_48b = { 3 },
.result = REJECT,
- .errstr = "R0 min value is outside of the array range",
+ .errstr = "R0 min value is outside of the allowed memory range",
},
{
"map access: value_ptr -= known scalar, 2",
diff --git a/tools/testing/selftests/breakpoints/.gitignore b/tools/testing/selftests/breakpoints/.gitignore
index a23bb4a6f06c..def2e97dab9a 100644
--- a/tools/testing/selftests/breakpoints/.gitignore
+++ b/tools/testing/selftests/breakpoints/.gitignore
@@ -1,2 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0-only
breakpoint_test
step_after_suspend_test
diff --git a/tools/testing/selftests/capabilities/.gitignore b/tools/testing/selftests/capabilities/.gitignore
index b732dd0d4738..426d9adca67c 100644
--- a/tools/testing/selftests/capabilities/.gitignore
+++ b/tools/testing/selftests/capabilities/.gitignore
@@ -1,2 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0-only
test_execve
validate_cap
diff --git a/tools/testing/selftests/cgroup/.gitignore b/tools/testing/selftests/cgroup/.gitignore
index 7f9835624793..aa6de65b0838 100644
--- a/tools/testing/selftests/cgroup/.gitignore
+++ b/tools/testing/selftests/cgroup/.gitignore
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
test_memcontrol
test_core
test_freezer
diff --git a/tools/testing/selftests/cgroup/Makefile b/tools/testing/selftests/cgroup/Makefile
index 66aafe1f5746..967f268fde74 100644
--- a/tools/testing/selftests/cgroup/Makefile
+++ b/tools/testing/selftests/cgroup/Makefile
@@ -11,6 +11,6 @@ TEST_GEN_PROGS += test_freezer
include ../lib.mk
-$(OUTPUT)/test_memcontrol: cgroup_util.c
-$(OUTPUT)/test_core: cgroup_util.c
-$(OUTPUT)/test_freezer: cgroup_util.c
+$(OUTPUT)/test_memcontrol: cgroup_util.c ../clone3/clone3_selftests.h
+$(OUTPUT)/test_core: cgroup_util.c ../clone3/clone3_selftests.h
+$(OUTPUT)/test_freezer: cgroup_util.c ../clone3/clone3_selftests.h
diff --git a/tools/testing/selftests/cgroup/cgroup_util.c b/tools/testing/selftests/cgroup/cgroup_util.c
index 8f7131dcf1ff..8a637ca7d73a 100644
--- a/tools/testing/selftests/cgroup/cgroup_util.c
+++ b/tools/testing/selftests/cgroup/cgroup_util.c
@@ -15,6 +15,7 @@
#include <unistd.h>
#include "cgroup_util.h"
+#include "../clone3/clone3_selftests.h"
static ssize_t read_text(const char *path, char *buf, size_t max_len)
{
@@ -331,12 +332,112 @@ int cg_run(const char *cgroup,
}
}
+pid_t clone_into_cgroup(int cgroup_fd)
+{
+#ifdef CLONE_ARGS_SIZE_VER2
+ pid_t pid;
+
+ struct clone_args args = {
+ .flags = CLONE_INTO_CGROUP,
+ .exit_signal = SIGCHLD,
+ .cgroup = cgroup_fd,
+ };
+
+ pid = sys_clone3(&args, sizeof(struct clone_args));
+ /*
+ * Verify that this is a genuine test failure:
+ * ENOSYS -> clone3() not available
+ * E2BIG -> CLONE_INTO_CGROUP not available
+ */
+ if (pid < 0 && (errno == ENOSYS || errno == E2BIG))
+ goto pretend_enosys;
+
+ return pid;
+
+pretend_enosys:
+#endif
+ errno = ENOSYS;
+ return -ENOSYS;
+}
+
+int clone_reap(pid_t pid, int options)
+{
+ int ret;
+ siginfo_t info = {
+ .si_signo = 0,
+ };
+
+again:
+ ret = waitid(P_PID, pid, &info, options | __WALL | __WNOTHREAD);
+ if (ret < 0) {
+ if (errno == EINTR)
+ goto again;
+ return -1;
+ }
+
+ if (options & WEXITED) {
+ if (WIFEXITED(info.si_status))
+ return WEXITSTATUS(info.si_status);
+ }
+
+ if (options & WSTOPPED) {
+ if (WIFSTOPPED(info.si_status))
+ return WSTOPSIG(info.si_status);
+ }
+
+ if (options & WCONTINUED) {
+ if (WIFCONTINUED(info.si_status))
+ return 0;
+ }
+
+ return -1;
+}
+
+int dirfd_open_opath(const char *dir)
+{
+ return open(dir, O_DIRECTORY | O_CLOEXEC | O_NOFOLLOW | O_PATH);
+}
+
+#define close_prot_errno(fd) \
+ if (fd >= 0) { \
+ int _e_ = errno; \
+ close(fd); \
+ errno = _e_; \
+ }
+
+static int clone_into_cgroup_run_nowait(const char *cgroup,
+ int (*fn)(const char *cgroup, void *arg),
+ void *arg)
+{
+ int cgroup_fd;
+ pid_t pid;
+
+ cgroup_fd = dirfd_open_opath(cgroup);
+ if (cgroup_fd < 0)
+ return -1;
+
+ pid = clone_into_cgroup(cgroup_fd);
+ close_prot_errno(cgroup_fd);
+ if (pid == 0)
+ exit(fn(cgroup, arg));
+
+ return pid;
+}
+
int cg_run_nowait(const char *cgroup,
int (*fn)(const char *cgroup, void *arg),
void *arg)
{
int pid;
+ pid = clone_into_cgroup_run_nowait(cgroup, fn, arg);
+ if (pid > 0)
+ return pid;
+
+ /* Genuine test failure. */
+ if (pid < 0 && errno != ENOSYS)
+ return -1;
+
pid = fork();
if (pid == 0) {
char buf[64];
@@ -450,3 +551,28 @@ int proc_read_strstr(int pid, bool thread, const char *item, const char *needle)
return strstr(buf, needle) ? 0 : -1;
}
+
+int clone_into_cgroup_run_wait(const char *cgroup)
+{
+ int cgroup_fd;
+ pid_t pid;
+
+ cgroup_fd = dirfd_open_opath(cgroup);
+ if (cgroup_fd < 0)
+ return -1;
+
+ pid = clone_into_cgroup(cgroup_fd);
+ close_prot_errno(cgroup_fd);
+ if (pid < 0)
+ return -1;
+
+ if (pid == 0)
+ exit(EXIT_SUCCESS);
+
+ /*
+ * We don't care whether this fails. We only care whether the initial
+ * clone succeeded.
+ */
+ (void)clone_reap(pid, WEXITED);
+ return 0;
+}
diff --git a/tools/testing/selftests/cgroup/cgroup_util.h b/tools/testing/selftests/cgroup/cgroup_util.h
index 49c54fbdb229..5a1305dd1f0b 100644
--- a/tools/testing/selftests/cgroup/cgroup_util.h
+++ b/tools/testing/selftests/cgroup/cgroup_util.h
@@ -50,3 +50,7 @@ extern int cg_wait_for_proc_count(const char *cgroup, int count);
extern int cg_killall(const char *cgroup);
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);
+extern int clone_reap(pid_t pid, int options);
+extern int clone_into_cgroup_run_wait(const char *cgroup);
+extern int dirfd_open_opath(const char *dir);
diff --git a/tools/testing/selftests/cgroup/test_core.c b/tools/testing/selftests/cgroup/test_core.c
index e19ce940cd6a..3df648c37876 100644
--- a/tools/testing/selftests/cgroup/test_core.c
+++ b/tools/testing/selftests/cgroup/test_core.c
@@ -2,7 +2,10 @@
#include <linux/limits.h>
#include <sys/types.h>
+#include <sys/mman.h>
+#include <sys/wait.h>
#include <unistd.h>
+#include <fcntl.h>
#include <stdio.h>
#include <errno.h>
#include <signal.h>
@@ -12,6 +15,115 @@
#include "../kselftest.h"
#include "cgroup_util.h"
+static int touch_anon(char *buf, size_t size)
+{
+ int fd;
+ char *pos = buf;
+
+ fd = open("/dev/urandom", O_RDONLY);
+ if (fd < 0)
+ return -1;
+
+ while (size > 0) {
+ ssize_t ret = read(fd, pos, size);
+
+ if (ret < 0) {
+ if (errno != EINTR) {
+ close(fd);
+ return -1;
+ }
+ } else {
+ pos += ret;
+ size -= ret;
+ }
+ }
+ close(fd);
+
+ return 0;
+}
+
+static int alloc_and_touch_anon_noexit(const char *cgroup, void *arg)
+{
+ int ppid = getppid();
+ size_t size = (size_t)arg;
+ void *buf;
+
+ buf = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANON,
+ 0, 0);
+ if (buf == MAP_FAILED)
+ return -1;
+
+ if (touch_anon((char *)buf, size)) {
+ munmap(buf, size);
+ return -1;
+ }
+
+ while (getppid() == ppid)
+ sleep(1);
+
+ munmap(buf, size);
+ return 0;
+}
+
+/*
+ * Create a child process that allocates and touches 100MB, then waits to be
+ * killed. Wait until the child is attached to the cgroup, kill all processes
+ * in that cgroup and wait until "cgroup.procs" is empty. At this point try to
+ * destroy the empty cgroup. The test helps detect race conditions between
+ * dying processes leaving the cgroup and cgroup destruction path.
+ */
+static int test_cgcore_destroy(const char *root)
+{
+ int ret = KSFT_FAIL;
+ char *cg_test = NULL;
+ int child_pid;
+ char buf[PAGE_SIZE];
+
+ cg_test = cg_name(root, "cg_test");
+
+ if (!cg_test)
+ goto cleanup;
+
+ for (int i = 0; i < 10; i++) {
+ if (cg_create(cg_test))
+ goto cleanup;
+
+ child_pid = cg_run_nowait(cg_test, alloc_and_touch_anon_noexit,
+ (void *) MB(100));
+
+ if (child_pid < 0)
+ goto cleanup;
+
+ /* wait for the child to enter cgroup */
+ if (cg_wait_for_proc_count(cg_test, 1))
+ goto cleanup;
+
+ if (cg_killall(cg_test))
+ goto cleanup;
+
+ /* wait for cgroup to be empty */
+ while (1) {
+ if (cg_read(cg_test, "cgroup.procs", buf, sizeof(buf)))
+ goto cleanup;
+ if (buf[0] == '\0')
+ break;
+ usleep(1000);
+ }
+
+ if (rmdir(cg_test))
+ goto cleanup;
+
+ if (waitpid(child_pid, NULL, 0) < 0)
+ goto cleanup;
+ }
+ ret = KSFT_PASS;
+cleanup:
+ if (cg_test)
+ cg_destroy(cg_test);
+ free(cg_test);
+ return ret;
+}
+
/*
* A(0) - B(0) - C(1)
* \ D(0)
@@ -25,8 +137,11 @@
static int test_cgcore_populated(const char *root)
{
int ret = KSFT_FAIL;
+ int err;
char *cg_test_a = NULL, *cg_test_b = NULL;
char *cg_test_c = NULL, *cg_test_d = NULL;
+ int cgroup_fd = -EBADF;
+ pid_t pid;
cg_test_a = cg_name(root, "cg_test_a");
cg_test_b = cg_name(root, "cg_test_a/cg_test_b");
@@ -78,6 +193,52 @@ static int test_cgcore_populated(const char *root)
if (cg_read_strcmp(cg_test_d, "cgroup.events", "populated 0\n"))
goto cleanup;
+ /* Test that we can directly clone into a new cgroup. */
+ cgroup_fd = dirfd_open_opath(cg_test_d);
+ if (cgroup_fd < 0)
+ goto cleanup;
+
+ pid = clone_into_cgroup(cgroup_fd);
+ if (pid < 0) {
+ if (errno == ENOSYS)
+ goto cleanup_pass;
+ goto cleanup;
+ }
+
+ if (pid == 0) {
+ if (raise(SIGSTOP))
+ exit(EXIT_FAILURE);
+ exit(EXIT_SUCCESS);
+ }
+
+ err = cg_read_strcmp(cg_test_d, "cgroup.events", "populated 1\n");
+
+ (void)clone_reap(pid, WSTOPPED);
+ (void)kill(pid, SIGCONT);
+ (void)clone_reap(pid, WEXITED);
+
+ if (err)
+ goto cleanup;
+
+ if (cg_read_strcmp(cg_test_d, "cgroup.events", "populated 0\n"))
+ goto cleanup;
+
+ /* Remove cgroup. */
+ if (cg_test_d) {
+ cg_destroy(cg_test_d);
+ free(cg_test_d);
+ cg_test_d = NULL;
+ }
+
+ pid = clone_into_cgroup(cgroup_fd);
+ if (pid < 0)
+ goto cleanup_pass;
+ if (pid == 0)
+ exit(EXIT_SUCCESS);
+ (void)clone_reap(pid, WEXITED);
+ goto cleanup;
+
+cleanup_pass:
ret = KSFT_PASS;
cleanup:
@@ -93,6 +254,8 @@ cleanup:
free(cg_test_c);
free(cg_test_b);
free(cg_test_a);
+ if (cgroup_fd >= 0)
+ close(cgroup_fd);
return ret;
}
@@ -136,6 +299,16 @@ static int test_cgcore_invalid_domain(const char *root)
if (errno != EOPNOTSUPP)
goto cleanup;
+ if (!clone_into_cgroup_run_wait(child))
+ goto cleanup;
+
+ if (errno == ENOSYS)
+ goto cleanup_pass;
+
+ if (errno != EOPNOTSUPP)
+ goto cleanup;
+
+cleanup_pass:
ret = KSFT_PASS;
cleanup:
@@ -345,6 +518,9 @@ static int test_cgcore_internal_process_constraint(const char *root)
if (!cg_enter_current(parent))
goto cleanup;
+ if (!clone_into_cgroup_run_wait(parent))
+ goto cleanup;
+
ret = KSFT_PASS;
cleanup:
@@ -512,6 +688,7 @@ struct corecg_test {
T(test_cgcore_populated),
T(test_cgcore_proc_migration),
T(test_cgcore_thread_migration),
+ T(test_cgcore_destroy),
};
#undef T
diff --git a/tools/testing/selftests/clone3/.gitignore b/tools/testing/selftests/clone3/.gitignore
index 0dc4f32c6cb8..a81085742d40 100644
--- a/tools/testing/selftests/clone3/.gitignore
+++ b/tools/testing/selftests/clone3/.gitignore
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
clone3
clone3_clear_sighand
clone3_set_tid
diff --git a/tools/testing/selftests/clone3/clone3_selftests.h b/tools/testing/selftests/clone3/clone3_selftests.h
index a3f2c8ad8bcc..91c1a78ddb39 100644
--- a/tools/testing/selftests/clone3/clone3_selftests.h
+++ b/tools/testing/selftests/clone3/clone3_selftests.h
@@ -5,12 +5,24 @@
#define _GNU_SOURCE
#include <sched.h>
+#include <linux/sched.h>
+#include <linux/types.h>
#include <stdint.h>
#include <syscall.h>
-#include <linux/types.h>
+#include <sys/wait.h>
+
+#include "../kselftest.h"
#define ptr_to_u64(ptr) ((__u64)((uintptr_t)(ptr)))
+#ifndef CLONE_INTO_CGROUP
+#define CLONE_INTO_CGROUP 0x200000000ULL /* Clone into a specific cgroup given the right permissions. */
+#endif
+
+#ifndef CLONE_ARGS_SIZE_VER0
+#define CLONE_ARGS_SIZE_VER0 64
+#endif
+
#ifndef __NR_clone3
#define __NR_clone3 -1
struct clone_args {
@@ -22,10 +34,13 @@ struct clone_args {
__aligned_u64 stack;
__aligned_u64 stack_size;
__aligned_u64 tls;
+#define CLONE_ARGS_SIZE_VER1 80
__aligned_u64 set_tid;
__aligned_u64 set_tid_size;
+#define CLONE_ARGS_SIZE_VER2 88
+ __aligned_u64 cgroup;
};
-#endif
+#endif /* __NR_clone3 */
static pid_t sys_clone3(struct clone_args *args, size_t size)
{
diff --git a/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c b/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c
index cd5e1f602ac9..909da9cdda97 100644
--- a/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c
+++ b/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c
@@ -351,6 +351,7 @@ static int test_alloc_errors(char *heap_name)
}
printf("Expected error checking passed\n");
+ ret = 0;
out:
if (dmabuf_fd >= 0)
close(dmabuf_fd);
diff --git a/tools/testing/selftests/drivers/.gitignore b/tools/testing/selftests/drivers/.gitignore
index f6aebcc27b76..ca74f2e1c719 100644
--- a/tools/testing/selftests/drivers/.gitignore
+++ b/tools/testing/selftests/drivers/.gitignore
@@ -1 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
/dma-buf/udmabuf
diff --git a/tools/testing/selftests/drivers/net/mlxsw/blackhole_routes.sh b/tools/testing/selftests/drivers/net/mlxsw/blackhole_routes.sh
index 5ba5bef44d5b..bdffe698e1d1 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/blackhole_routes.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/blackhole_routes.sh
@@ -45,6 +45,7 @@ ALL_TESTS="
blackhole_ipv6
"
NUM_NETIFS=4
+: ${TIMEOUT:=20000} # ms
source $lib_dir/tc_common.sh
source $lib_dir/lib.sh
@@ -123,7 +124,7 @@ blackhole_ipv4()
skip_hw dst_ip 198.51.100.1 src_ip 192.0.2.1 ip_proto icmp \
action pass
- ip -4 route show 198.51.100.0/30 | grep -q offload
+ busywait "$TIMEOUT" wait_for_offload ip -4 route show 198.51.100.0/30
check_err $? "route not marked as offloaded when should"
ping_do $h1 198.51.100.1
@@ -147,7 +148,7 @@ blackhole_ipv6()
skip_hw dst_ip 2001:db8:2::1 src_ip 2001:db8:1::1 \
ip_proto icmpv6 action pass
- ip -6 route show 2001:db8:2::/120 | grep -q offload
+ busywait "$TIMEOUT" wait_for_offload ip -6 route show 2001:db8:2::/120
check_err $? "route not marked as offloaded when should"
ping6_do $h1 2001:db8:2::1
diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_acl_drops.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_acl_drops.sh
new file mode 100755
index 000000000000..b32ba5fec59d
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_acl_drops.sh
@@ -0,0 +1,151 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test devlink-trap ACL drops functionality over mlxsw.
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+
+ALL_TESTS="
+ ingress_flow_action_drop_test
+ egress_flow_action_drop_test
+"
+NUM_NETIFS=4
+source $lib_dir/tc_common.sh
+source $lib_dir/lib.sh
+source $lib_dir/devlink_lib.sh
+
+h1_create()
+{
+ simple_if_init $h1
+}
+
+h1_destroy()
+{
+ simple_if_fini $h1
+}
+
+h2_create()
+{
+ simple_if_init $h2
+}
+
+h2_destroy()
+{
+ simple_if_fini $h2
+}
+
+switch_create()
+{
+ ip link add dev br0 type bridge vlan_filtering 1 mcast_snooping 0
+
+ ip link set dev $swp1 master br0
+ ip link set dev $swp2 master br0
+
+ ip link set dev br0 up
+ ip link set dev $swp1 up
+ ip link set dev $swp2 up
+
+ tc qdisc add dev $swp1 clsact
+ tc qdisc add dev $swp2 clsact
+}
+
+switch_destroy()
+{
+ tc qdisc del dev $swp2 clsact
+ tc qdisc del dev $swp1 clsact
+
+ ip link set dev $swp2 down
+ ip link set dev $swp1 down
+
+ ip link del dev br0
+}
+
+setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ swp1=${NETIFS[p2]}
+
+ swp2=${NETIFS[p3]}
+ h2=${NETIFS[p4]}
+
+ h1mac=$(mac_get $h1)
+ h2mac=$(mac_get $h2)
+
+ vrf_prepare
+
+ h1_create
+ h2_create
+
+ switch_create
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ switch_destroy
+
+ h2_destroy
+ h1_destroy
+
+ vrf_cleanup
+}
+
+ingress_flow_action_drop_test()
+{
+ local mz_pid
+
+ tc filter add dev $swp2 egress protocol ip pref 1 handle 101 \
+ flower src_mac $h1mac action pass
+
+ tc filter add dev $swp1 ingress protocol ip pref 1 handle 101 \
+ flower dst_ip 192.0.2.2 action drop
+
+ $MZ $h1 -c 0 -p 100 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
+ -t ip -d 1msec -q &
+ mz_pid=$!
+
+ RET=0
+
+ devlink_trap_drop_test ingress_flow_action_drop $swp2 101
+
+ log_test "ingress_flow_action_drop"
+
+ tc filter del dev $swp1 ingress protocol ip pref 1 handle 101 flower
+
+ devlink_trap_drop_cleanup $mz_pid $swp2 ip 1 101
+}
+
+egress_flow_action_drop_test()
+{
+ local mz_pid
+
+ tc filter add dev $swp2 egress protocol ip pref 2 handle 102 \
+ flower src_mac $h1mac action pass
+
+ tc filter add dev $swp2 egress protocol ip pref 1 handle 101 \
+ flower dst_ip 192.0.2.2 action drop
+
+ $MZ $h1 -c 0 -p 100 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
+ -t ip -d 1msec -q &
+ mz_pid=$!
+
+ RET=0
+
+ devlink_trap_drop_test egress_flow_action_drop $swp2 102
+
+ log_test "egress_flow_action_drop"
+
+ tc filter del dev $swp2 egress protocol ip pref 1 handle 101 flower
+
+ devlink_trap_drop_cleanup $mz_pid $swp2 ip 2 102
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_control.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_control.sh
new file mode 100755
index 000000000000..a37273473c1b
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_control.sh
@@ -0,0 +1,688 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test devlink-trap control trap functionality over mlxsw. Each registered
+# control packet trap is tested to make sure it is triggered under the right
+# conditions.
+#
+# +---------------------------------+
+# | H1 (vrf) |
+# | + $h1 |
+# | | 192.0.2.1/24 |
+# | | 2001:db8:1::1/64 |
+# | | |
+# | | default via 192.0.2.2 |
+# | | default via 2001:db8:1::2 |
+# +----|----------------------------+
+# |
+# +----|----------------------------------------------------------------------+
+# | SW | |
+# | + $rp1 |
+# | 192.0.2.2/24 |
+# | 2001:db8:1::2/64 |
+# | |
+# | 2001:db8:2::2/64 |
+# | 198.51.100.2/24 |
+# | + $rp2 |
+# | | |
+# +----|----------------------------------------------------------------------+
+# |
+# +----|----------------------------+
+# | | default via 198.51.100.2 |
+# | | default via 2001:db8:2::2 |
+# | | |
+# | | 2001:db8:2::1/64 |
+# | | 198.51.100.1/24 |
+# | + $h2 |
+# | H2 (vrf) |
+# +---------------------------------+
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+
+ALL_TESTS="
+ stp_test
+ lacp_test
+ lldp_test
+ igmp_query_test
+ igmp_v1_report_test
+ igmp_v2_report_test
+ igmp_v3_report_test
+ igmp_v2_leave_test
+ mld_query_test
+ mld_v1_report_test
+ mld_v2_report_test
+ mld_v1_done_test
+ ipv4_dhcp_test
+ ipv6_dhcp_test
+ arp_request_test
+ arp_response_test
+ ipv6_neigh_solicit_test
+ ipv6_neigh_advert_test
+ ipv4_bfd_test
+ ipv6_bfd_test
+ ipv4_ospf_test
+ ipv6_ospf_test
+ ipv4_bgp_test
+ ipv6_bgp_test
+ ipv4_vrrp_test
+ ipv6_vrrp_test
+ ipv4_pim_test
+ ipv6_pim_test
+ uc_loopback_test
+ local_route_test
+ external_route_test
+ ipv6_uc_dip_link_local_scope_test
+ ipv4_router_alert_test
+ ipv6_router_alert_test
+ ipv6_dip_all_nodes_test
+ ipv6_dip_all_routers_test
+ ipv6_router_solicit_test
+ ipv6_router_advert_test
+ ipv6_redirect_test
+ ptp_event_test
+ ptp_general_test
+ flow_action_sample_test
+ flow_action_trap_test
+"
+NUM_NETIFS=4
+source $lib_dir/lib.sh
+source $lib_dir/devlink_lib.sh
+
+h1_create()
+{
+ simple_if_init $h1 192.0.2.1/24 2001:db8:1::1/64
+
+ ip -4 route add default vrf v$h1 nexthop via 192.0.2.2
+ ip -6 route add default vrf v$h1 nexthop via 2001:db8:1::2
+}
+
+h1_destroy()
+{
+ ip -6 route del default vrf v$h1 nexthop via 2001:db8:1::2
+ ip -4 route del default vrf v$h1 nexthop via 192.0.2.2
+
+ simple_if_fini $h1 192.0.2.1/24 2001:db8:1::1/64
+}
+
+h2_create()
+{
+ simple_if_init $h2 198.51.100.1/24 2001:db8:2::1/64
+
+ ip -4 route add default vrf v$h2 nexthop via 198.51.100.2
+ ip -6 route add default vrf v$h2 nexthop via 2001:db8:2::2
+}
+
+h2_destroy()
+{
+ ip -6 route del default vrf v$h2 nexthop via 2001:db8:2::2
+ ip -4 route del default vrf v$h2 nexthop via 198.51.100.2
+
+ simple_if_fini $h2 198.51.100.1/24 2001:db8:2::1/64
+}
+
+router_create()
+{
+ ip link set dev $rp1 up
+ ip link set dev $rp2 up
+
+ __addr_add_del $rp1 add 192.0.2.2/24 2001:db8:1::2/64
+ __addr_add_del $rp2 add 198.51.100.2/24 2001:db8:2::2/64
+}
+
+router_destroy()
+{
+ __addr_add_del $rp2 del 198.51.100.2/24 2001:db8:2::2/64
+ __addr_add_del $rp1 del 192.0.2.2/24 2001:db8:1::2/64
+
+ ip link set dev $rp2 down
+ ip link set dev $rp1 down
+}
+
+setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ rp1=${NETIFS[p2]}
+
+ rp2=${NETIFS[p3]}
+ h2=${NETIFS[p4]}
+
+ vrf_prepare
+ forwarding_enable
+
+ h1_create
+ h2_create
+ router_create
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ router_destroy
+ h2_destroy
+ h1_destroy
+
+ forwarding_restore
+ vrf_cleanup
+}
+
+stp_test()
+{
+ devlink_trap_stats_test "STP" "stp" $MZ $h1 -c 1 -t bpdu -q
+}
+
+lacp_payload_get()
+{
+ local source_mac=$1; shift
+ local p
+
+ p=$(:
+ )"01:80:C2:00:00:02:"$( : ETH daddr
+ )"$source_mac:"$( : ETH saddr
+ )"88:09:"$( : ETH type
+ )
+ echo $p
+}
+
+lacp_test()
+{
+ local h1mac=$(mac_get $h1)
+
+ devlink_trap_stats_test "LACP" "lacp" $MZ $h1 -c 1 \
+ $(lacp_payload_get $h1mac) -p 100 -q
+}
+
+lldp_payload_get()
+{
+ local source_mac=$1; shift
+ local p
+
+ p=$(:
+ )"01:80:C2:00:00:0E:"$( : ETH daddr
+ )"$source_mac:"$( : ETH saddr
+ )"88:CC:"$( : ETH type
+ )
+ echo $p
+}
+
+lldp_test()
+{
+ local h1mac=$(mac_get $h1)
+
+ devlink_trap_stats_test "LLDP" "lldp" $MZ $h1 -c 1 \
+ $(lldp_payload_get $h1mac) -p 100 -q
+}
+
+igmp_query_test()
+{
+ # IGMP (IP Protocol 2) Membership Query (Type 0x11)
+ devlink_trap_stats_test "IGMP Membership Query" "igmp_query" \
+ $MZ $h1 -c 1 -a own -b 01:00:5E:00:00:01 \
+ -A 192.0.2.1 -B 224.0.0.1 -t ip proto=2,p=11 -p 100 -q
+}
+
+igmp_v1_report_test()
+{
+ # IGMP (IP Protocol 2) Version 1 Membership Report (Type 0x12)
+ devlink_trap_stats_test "IGMP Version 1 Membership Report" \
+ "igmp_v1_report" $MZ $h1 -c 1 -a own -b 01:00:5E:00:00:01 \
+ -A 192.0.2.1 -B 244.0.0.1 -t ip proto=2,p=12 -p 100 -q
+}
+
+igmp_v2_report_test()
+{
+ # IGMP (IP Protocol 2) Version 2 Membership Report (Type 0x16)
+ devlink_trap_stats_test "IGMP Version 2 Membership Report" \
+ "igmp_v2_report" $MZ $h1 -c 1 -a own -b 01:00:5E:00:00:01 \
+ -A 192.0.2.1 -B 244.0.0.1 -t ip proto=2,p=16 -p 100 -q
+}
+
+igmp_v3_report_test()
+{
+ # IGMP (IP Protocol 2) Version 3 Membership Report (Type 0x22)
+ devlink_trap_stats_test "IGMP Version 3 Membership Report" \
+ "igmp_v3_report" $MZ $h1 -c 1 -a own -b 01:00:5E:00:00:01 \
+ -A 192.0.2.1 -B 244.0.0.1 -t ip proto=2,p=22 -p 100 -q
+}
+
+igmp_v2_leave_test()
+{
+ # IGMP (IP Protocol 2) Version 2 Leave Group (Type 0x17)
+ devlink_trap_stats_test "IGMP Version 2 Leave Group" \
+ "igmp_v2_leave" $MZ $h1 -c 1 -a own -b 01:00:5E:00:00:02 \
+ -A 192.0.2.1 -B 224.0.0.2 -t ip proto=2,p=17 -p 100 -q
+}
+
+mld_payload_get()
+{
+ local type=$1; shift
+ local p
+
+ type=$(printf "%x" $type)
+ p=$(:
+ )"3A:"$( : Next Header - ICMPv6
+ )"00:"$( : Hdr Ext Len
+ )"00:00:00:00:00:00:"$( : Options and Padding
+ )"$type:"$( : ICMPv6.type
+ )"00:"$( : ICMPv6.code
+ )"00:"$( : ICMPv6.checksum
+ )
+ echo $p
+}
+
+mld_query_test()
+{
+ # MLD Multicast Listener Query (Type 130)
+ devlink_trap_stats_test "MLD Multicast Listener Query" "mld_query" \
+ $MZ $h1 -6 -c 1 -A fe80::1 -B ff02::1 \
+ -t ip hop=1,next=0,payload=$(mld_payload_get 130) -p 100 -q
+}
+
+mld_v1_report_test()
+{
+ # MLD Version 1 Multicast Listener Report (Type 131)
+ devlink_trap_stats_test "MLD Version 1 Multicast Listener Report" \
+ "mld_v1_report" $MZ $h1 -6 -c 1 -A fe80::1 -B ff02::16 \
+ -t ip hop=1,next=0,payload=$(mld_payload_get 131) -p 100 -q
+}
+
+mld_v2_report_test()
+{
+ # MLD Version 2 Multicast Listener Report (Type 143)
+ devlink_trap_stats_test "MLD Version 2 Multicast Listener Report" \
+ "mld_v2_report" $MZ $h1 -6 -c 1 -A fe80::1 -B ff02::16 \
+ -t ip hop=1,next=0,payload=$(mld_payload_get 143) -p 100 -q
+}
+
+mld_v1_done_test()
+{
+ # MLD Version 1 Multicast Listener Done (Type 132)
+ devlink_trap_stats_test "MLD Version 1 Multicast Listener Done" \
+ "mld_v1_done" $MZ $h1 -6 -c 1 -A fe80::1 -B ff02::16 \
+ -t ip hop=1,next=0,payload=$(mld_payload_get 132) -p 100 -q
+}
+
+ipv4_dhcp_test()
+{
+ devlink_trap_stats_test "IPv4 DHCP Port 67" "ipv4_dhcp" \
+ $MZ $h1 -c 1 -a own -b bcast -A 0.0.0.0 -B 255.255.255.255 \
+ -t udp sp=68,dp=67 -p 100 -q
+
+ devlink_trap_stats_test "IPv4 DHCP Port 68" "ipv4_dhcp" \
+ $MZ $h1 -c 1 -a own -b $(mac_get $rp1) -A 192.0.2.1 \
+ -B 255.255.255.255 -t udp sp=67,dp=68 -p 100 -q
+}
+
+ipv6_dhcp_test()
+{
+ devlink_trap_stats_test "IPv6 DHCP Port 547" "ipv6_dhcp" \
+ $MZ $h1 -6 -c 1 -A fe80::1 -B ff02::1:2 -t udp sp=546,dp=547 \
+ -p 100 -q
+
+ devlink_trap_stats_test "IPv6 DHCP Port 546" "ipv6_dhcp" \
+ $MZ $h1 -6 -c 1 -A fe80::1 -B ff02::1:2 -t udp sp=547,dp=546 \
+ -p 100 -q
+}
+
+arp_request_test()
+{
+ devlink_trap_stats_test "ARP Request" "arp_request" \
+ $MZ $h1 -c 1 -a own -b bcast -t arp request -p 100 -q
+}
+
+arp_response_test()
+{
+ devlink_trap_stats_test "ARP Response" "arp_response" \
+ $MZ $h1 -c 1 -a own -b $(mac_get $rp1) -t arp reply -p 100 -q
+}
+
+icmpv6_header_get()
+{
+ local type=$1; shift
+ local p
+
+ type=$(printf "%x" $type)
+ p=$(:
+ )"$type:"$( : ICMPv6.type
+ )"00:"$( : ICMPv6.code
+ )"00:"$( : ICMPv6.checksum
+ )
+ echo $p
+}
+
+ipv6_neigh_solicit_test()
+{
+ devlink_trap_stats_test "IPv6 Neighbour Solicitation" \
+ "ipv6_neigh_solicit" $MZ $h1 -6 -c 1 \
+ -A fe80::1 -B ff02::1:ff00:02 \
+ -t ip hop=1,next=58,payload=$(icmpv6_header_get 135) -p 100 -q
+}
+
+ipv6_neigh_advert_test()
+{
+ devlink_trap_stats_test "IPv6 Neighbour Advertisement" \
+ "ipv6_neigh_advert" $MZ $h1 -6 -c 1 -a own -b $(mac_get $rp1) \
+ -A fe80::1 -B 2001:db8:1::2 \
+ -t ip hop=1,next=58,payload=$(icmpv6_header_get 136) -p 100 -q
+}
+
+ipv4_bfd_test()
+{
+ devlink_trap_stats_test "IPv4 BFD Control - Port 3784" "ipv4_bfd" \
+ $MZ $h1 -c 1 -a own -b $(mac_get $rp1) \
+ -A 192.0.2.1 -B 192.0.2.2 -t udp sp=49153,dp=3784 -p 100 -q
+
+ devlink_trap_stats_test "IPv4 BFD Echo - Port 3785" "ipv4_bfd" \
+ $MZ $h1 -c 1 -a own -b $(mac_get $rp1) \
+ -A 192.0.2.1 -B 192.0.2.2 -t udp sp=49153,dp=3785 -p 100 -q
+}
+
+ipv6_bfd_test()
+{
+ devlink_trap_stats_test "IPv6 BFD Control - Port 3784" "ipv6_bfd" \
+ $MZ $h1 -6 -c 1 -a own -b $(mac_get $rp1) \
+ -A 2001:db8:1::1 -B 2001:db8:1::2 \
+ -t udp sp=49153,dp=3784 -p 100 -q
+
+ devlink_trap_stats_test "IPv6 BFD Echo - Port 3785" "ipv6_bfd" \
+ $MZ $h1 -6 -c 1 -a own -b $(mac_get $rp1) \
+ -A 2001:db8:1::1 -B 2001:db8:1::2 \
+ -t udp sp=49153,dp=3785 -p 100 -q
+}
+
+ipv4_ospf_test()
+{
+ devlink_trap_stats_test "IPv4 OSPF - Multicast" "ipv4_ospf" \
+ $MZ $h1 -c 1 -a own -b 01:00:5e:00:00:05 \
+ -A 192.0.2.1 -B 224.0.0.5 -t ip proto=89 -p 100 -q
+
+ devlink_trap_stats_test "IPv4 OSPF - Unicast" "ipv4_ospf" \
+ $MZ $h1 -c 1 -a own -b $(mac_get $rp1) \
+ -A 192.0.2.1 -B 192.0.2.2 -t ip proto=89 -p 100 -q
+}
+
+ipv6_ospf_test()
+{
+ devlink_trap_stats_test "IPv6 OSPF - Multicast" "ipv6_ospf" \
+ $MZ $h1 -6 -c 1 -a own -b 33:33:00:00:00:05 \
+ -A fe80::1 -B ff02::5 -t ip next=89 -p 100 -q
+
+ devlink_trap_stats_test "IPv6 OSPF - Unicast" "ipv6_ospf" \
+ $MZ $h1 -6 -c 1 -a own -b $(mac_get $rp1) \
+ -A 2001:db8:1::1 -B 2001:db8:1::2 -t ip next=89 -p 100 -q
+}
+
+ipv4_bgp_test()
+{
+ devlink_trap_stats_test "IPv4 BGP" "ipv4_bgp" \
+ $MZ $h1 -c 1 -a own -b $(mac_get $rp1) \
+ -A 192.0.2.1 -B 192.0.2.2 -t tcp sp=54321,dp=179,flags=rst \
+ -p 100 -q
+}
+
+ipv6_bgp_test()
+{
+ devlink_trap_stats_test "IPv6 BGP" "ipv6_bgp" \
+ $MZ $h1 -6 -c 1 -a own -b $(mac_get $rp1) \
+ -A 2001:db8:1::1 -B 2001:db8:1::2 \
+ -t tcp sp=54321,dp=179,flags=rst -p 100 -q
+}
+
+ipv4_vrrp_test()
+{
+ devlink_trap_stats_test "IPv4 VRRP" "ipv4_vrrp" \
+ $MZ $h1 -c 1 -a own -b 01:00:5e:00:00:12 \
+ -A 192.0.2.1 -B 224.0.0.18 -t ip proto=112 -p 100 -q
+}
+
+ipv6_vrrp_test()
+{
+ devlink_trap_stats_test "IPv6 VRRP" "ipv6_vrrp" \
+ $MZ $h1 -6 -c 1 -a own -b 33:33:00:00:00:12 \
+ -A fe80::1 -B ff02::12 -t ip next=112 -p 100 -q
+}
+
+ipv4_pim_test()
+{
+ devlink_trap_stats_test "IPv4 PIM - Multicast" "ipv4_pim" \
+ $MZ $h1 -c 1 -a own -b 01:00:5e:00:00:0d \
+ -A 192.0.2.1 -B 224.0.0.13 -t ip proto=103 -p 100 -q
+
+ devlink_trap_stats_test "IPv4 PIM - Unicast" "ipv4_pim" \
+ $MZ $h1 -c 1 -a own -b $(mac_get $rp1) \
+ -A 192.0.2.1 -B 192.0.2.2 -t ip proto=103 -p 100 -q
+}
+
+ipv6_pim_test()
+{
+ devlink_trap_stats_test "IPv6 PIM - Multicast" "ipv6_pim" \
+ $MZ $h1 -6 -c 1 -a own -b 33:33:00:00:00:0d \
+ -A fe80::1 -B ff02::d -t ip next=103 -p 100 -q
+
+ devlink_trap_stats_test "IPv6 PIM - Unicast" "ipv6_pim" \
+ $MZ $h1 -6 -c 1 -a own -b $(mac_get $rp1) \
+ -A fe80::1 -B 2001:db8:1::2 -t ip next=103 -p 100 -q
+}
+
+uc_loopback_test()
+{
+ # Add neighbours to the fake destination IPs, so that the packets are
+ # routed in the device and not trapped due to an unresolved neighbour
+ # exception.
+ ip -4 neigh add 192.0.2.3 lladdr 00:11:22:33:44:55 nud permanent \
+ dev $rp1
+ ip -6 neigh add 2001:db8:1::3 lladdr 00:11:22:33:44:55 nud permanent \
+ dev $rp1
+
+ devlink_trap_stats_test "IPv4 Unicast Loopback" "uc_loopback" \
+ $MZ $h1 -c 1 -a own -b $(mac_get $rp1) \
+ -A 192.0.2.1 -B 192.0.2.3 -t udp sp=54321,dp=12345 -p 100 -q
+
+ devlink_trap_stats_test "IPv6 Unicast Loopback" "uc_loopback" \
+ $MZ $h1 -6 -c 1 -a own -b $(mac_get $rp1) \
+ -A 2001:db8:1::1 -B 2001:db8:1::3 -t udp sp=54321,dp=12345 \
+ -p 100 -q
+
+ ip -6 neigh del 2001:db8:1::3 dev $rp1
+ ip -4 neigh del 192.0.2.3 dev $rp1
+}
+
+local_route_test()
+{
+ # Use a fake source IP to prevent the trap from being triggered twice
+ # when the router sends back a port unreachable message.
+ devlink_trap_stats_test "IPv4 Local Route" "local_route" \
+ $MZ $h1 -c 1 -a own -b $(mac_get $rp1) \
+ -A 192.0.2.3 -B 192.0.2.2 -t udp sp=54321,dp=12345 -p 100 -q
+
+ devlink_trap_stats_test "IPv6 Local Route" "local_route" \
+ $MZ $h1 -6 -c 1 -a own -b $(mac_get $rp1) \
+ -A 2001:db8:1::3 -B 2001:db8:1::2 -t udp sp=54321,sp=12345 \
+ -p 100 -q
+}
+
+external_route_test()
+{
+ # Add a dummy device through which the incoming packets should be
+ # routed.
+ ip link add name dummy10 up type dummy
+ ip address add 203.0.113.1/24 dev dummy10
+ ip -6 address add 2001:db8:10::1/64 dev dummy10
+
+ devlink_trap_stats_test "IPv4 External Route" "external_route" \
+ $MZ $h1 -c 1 -a own -b $(mac_get $rp1) \
+ -A 192.0.2.1 -B 203.0.113.2 -t udp sp=54321,dp=12345 -p 100 -q
+
+ devlink_trap_stats_test "IPv6 External Route" "external_route" \
+ $MZ $h1 -6 -c 1 -a own -b $(mac_get $rp1) \
+ -A 2001:db8:1::1 -B 2001:db8:10::2 -t udp sp=54321,sp=12345 \
+ -p 100 -q
+
+ ip -6 address del 2001:db8:10::1/64 dev dummy10
+ ip address del 203.0.113.1/24 dev dummy10
+ ip link del dev dummy10
+}
+
+ipv6_uc_dip_link_local_scope_test()
+{
+ # Add a dummy link-local prefix route to allow the packet to be routed.
+ ip -6 route add fe80:1::/64 dev $rp2
+
+ devlink_trap_stats_test \
+ "IPv6 Unicast Destination IP With Link-Local Scope" \
+ "ipv6_uc_dip_link_local_scope" \
+ $MZ $h1 -6 -c 1 -a own -b $(mac_get $rp1) \
+ -A fe80::1 -B fe80:1::2 -t udp sp=54321,sp=12345 \
+ -p 100 -q
+
+ ip -6 route del fe80:1::/64 dev $rp2
+}
+
+ipv4_router_alert_get()
+{
+ local p
+
+ # https://en.wikipedia.org/wiki/IPv4#Options
+ p=$(:
+ )"94:"$( : Option Number
+ )"04:"$( : Option Length
+ )"00:00:"$( : Option Data
+ )
+ echo $p
+}
+
+ipv4_router_alert_test()
+{
+ devlink_trap_stats_test "IPv4 Router Alert" "ipv4_router_alert" \
+ $MZ $h1 -c 1 -a own -b $(mac_get $rp1) \
+ -A 192.0.2.1 -B 198.51.100.3 \
+ -t ip option=$(ipv4_router_alert_get) -p 100 -q
+}
+
+ipv6_router_alert_get()
+{
+ local p
+
+ # https://en.wikipedia.org/wiki/IPv6_packet#Hop-by-hop_options_and_destination_options
+ # https://tools.ietf.org/html/rfc2711#section-2.1
+ p=$(:
+ )"11:"$( : Next Header - UDP
+ )"00:"$( : Hdr Ext Len
+ )"05:02:00:00:00:00:"$( : Option Data
+ )
+ echo $p
+}
+
+ipv6_router_alert_test()
+{
+ devlink_trap_stats_test "IPv6 Router Alert" "ipv6_router_alert" \
+ $MZ $h1 -6 -c 1 -a own -b $(mac_get $rp1) \
+ -A 2001:db8:1::1 -B 2001:db8:1::3 \
+ -t ip next=0,payload=$(ipv6_router_alert_get) -p 100 -q
+}
+
+ipv6_dip_all_nodes_test()
+{
+ devlink_trap_stats_test "IPv6 Destination IP \"All Nodes Address\"" \
+ "ipv6_dip_all_nodes" \
+ $MZ $h1 -6 -c 1 -a own -b 33:33:00:00:00:01 \
+ -A 2001:db8:1::1 -B ff02::1 -t udp sp=12345,dp=54321 -p 100 -q
+}
+
+ipv6_dip_all_routers_test()
+{
+ devlink_trap_stats_test "IPv6 Destination IP \"All Routers Address\"" \
+ "ipv6_dip_all_routers" \
+ $MZ $h1 -6 -c 1 -a own -b 33:33:00:00:00:02 \
+ -A 2001:db8:1::1 -B ff02::2 -t udp sp=12345,dp=54321 -p 100 -q
+}
+
+ipv6_router_solicit_test()
+{
+ devlink_trap_stats_test "IPv6 Router Solicitation" \
+ "ipv6_router_solicit" \
+ $MZ $h1 -6 -c 1 -a own -b 33:33:00:00:00:02 \
+ -A fe80::1 -B ff02::2 \
+ -t ip hop=1,next=58,payload=$(icmpv6_header_get 133) -p 100 -q
+}
+
+ipv6_router_advert_test()
+{
+ devlink_trap_stats_test "IPv6 Router Advertisement" \
+ "ipv6_router_advert" \
+ $MZ $h1 -6 -c 1 -a own -b 33:33:00:00:00:01 \
+ -A fe80::1 -B ff02::1 \
+ -t ip hop=1,next=58,payload=$(icmpv6_header_get 134) -p 100 -q
+}
+
+ipv6_redirect_test()
+{
+ devlink_trap_stats_test "IPv6 Redirect Message" \
+ "ipv6_redirect" \
+ $MZ $h1 -6 -c 1 -a own -b $(mac_get $rp1) \
+ -A fe80::1 -B 2001:db8:1::2 \
+ -t ip hop=1,next=58,payload=$(icmpv6_header_get 137) -p 100 -q
+}
+
+ptp_event_test()
+{
+ # PTP is only supported on Spectrum-1, for now.
+ [[ "$DEVLINK_VIDDID" != "15b3:cb84" ]] && return
+
+ # PTP Sync (0)
+ devlink_trap_stats_test "PTP Time-Critical Event Message" "ptp_event" \
+ $MZ $h1 -c 1 -a own -b 01:00:5e:00:01:81 \
+ -A 192.0.2.1 -B 224.0.1.129 \
+ -t udp sp=12345,dp=319,payload=10 -p 100 -q
+}
+
+ptp_general_test()
+{
+ # PTP is only supported on Spectrum-1, for now.
+ [[ "$DEVLINK_VIDDID" != "15b3:cb84" ]] && return
+
+ # PTP Announce (b)
+ devlink_trap_stats_test "PTP General Message" "ptp_general" \
+ $MZ $h1 -c 1 -a own -b 01:00:5e:00:01:81 \
+ -A 192.0.2.1 -B 224.0.1.129 \
+ -t udp sp=12345,dp=320,payload=1b -p 100 -q
+}
+
+flow_action_sample_test()
+{
+ # Install a filter that samples every incoming packet.
+ tc qdisc add dev $rp1 clsact
+ tc filter add dev $rp1 ingress proto all pref 1 handle 101 matchall \
+ skip_sw action sample rate 1 group 1
+
+ devlink_trap_stats_test "Flow Sampling" "flow_action_sample" \
+ $MZ $h1 -c 1 -a own -b $(mac_get $rp1) \
+ -A 192.0.2.1 -B 198.51.100.1 -t udp sp=12345,dp=54321 -p 100 -q
+
+ tc filter del dev $rp1 ingress proto all pref 1 handle 101 matchall
+ tc qdisc del dev $rp1 clsact
+}
+
+flow_action_trap_test()
+{
+ # Install a filter that traps a specific flow.
+ tc qdisc add dev $rp1 clsact
+ tc filter add dev $rp1 ingress proto ip pref 1 handle 101 flower \
+ skip_sw ip_proto udp src_port 12345 dst_port 54321 action trap
+
+ devlink_trap_stats_test "Flow Trapping (Logging)" "flow_action_trap" \
+ $MZ $h1 -c 1 -a own -b $(mac_get $rp1) \
+ -A 192.0.2.1 -B 198.51.100.1 -t udp sp=12345,dp=54321 -p 100 -q
+
+ tc filter del dev $rp1 ingress proto ip pref 1 handle 101 flower
+ tc qdisc del dev $rp1 clsact
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l2_drops.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l2_drops.sh
index 58cdbfb608e9..a4c2812e9807 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l2_drops.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l2_drops.sh
@@ -96,7 +96,6 @@ source_mac_is_multicast_test()
{
local trap_name="source_mac_is_multicast"
local smac=01:02:03:04:05:06
- local group_name="l2_drops"
local mz_pid
tc filter add dev $swp2 egress protocol ip pref 1 handle 101 \
@@ -107,18 +106,17 @@ source_mac_is_multicast_test()
RET=0
- devlink_trap_drop_test $trap_name $group_name $swp2
+ devlink_trap_drop_test $trap_name $swp2 101
log_test "Source MAC is multicast"
- devlink_trap_drop_cleanup $mz_pid $swp2 ip
+ devlink_trap_drop_cleanup $mz_pid $swp2 ip 1 101
}
__vlan_tag_mismatch_test()
{
local trap_name="vlan_tag_mismatch"
local dmac=de:ad:be:ef:13:37
- local group_name="l2_drops"
local opt=$1; shift
local mz_pid
@@ -132,7 +130,7 @@ __vlan_tag_mismatch_test()
$MZ $h1 "$opt" -c 0 -p 100 -a own -b $dmac -t ip -d 1msec -q &
mz_pid=$!
- devlink_trap_drop_test $trap_name $group_name $swp2
+ devlink_trap_drop_test $trap_name $swp2 101
# Add PVID and make sure packets are no longer dropped.
bridge vlan add vid 1 dev $swp1 pvid untagged master
@@ -140,7 +138,7 @@ __vlan_tag_mismatch_test()
devlink_trap_stats_idle_test $trap_name
check_err $? "Trap stats not idle when packets should not be dropped"
- devlink_trap_group_stats_idle_test $group_name
+ devlink_trap_group_stats_idle_test $(devlink_trap_group_get $trap_name)
check_err $? "Trap group stats not idle with when packets should not be dropped"
tc_check_packets "dev $swp2 egress" 101 0
@@ -148,7 +146,7 @@ __vlan_tag_mismatch_test()
devlink_trap_action_set $trap_name "drop"
- devlink_trap_drop_cleanup $mz_pid $swp2 ip
+ devlink_trap_drop_cleanup $mz_pid $swp2 ip 1 101
}
vlan_tag_mismatch_untagged_test()
@@ -179,7 +177,6 @@ ingress_vlan_filter_test()
{
local trap_name="ingress_vlan_filter"
local dmac=de:ad:be:ef:13:37
- local group_name="l2_drops"
local mz_pid
local vid=10
@@ -193,7 +190,7 @@ ingress_vlan_filter_test()
$MZ $h1 -Q $vid -c 0 -p 100 -a own -b $dmac -t ip -d 1msec -q &
mz_pid=$!
- devlink_trap_drop_test $trap_name $group_name $swp2
+ devlink_trap_drop_test $trap_name $swp2 101
# Add the VLAN on the bridge port and make sure packets are no longer
# dropped.
@@ -202,7 +199,7 @@ ingress_vlan_filter_test()
devlink_trap_stats_idle_test $trap_name
check_err $? "Trap stats not idle when packets should not be dropped"
- devlink_trap_group_stats_idle_test $group_name
+ devlink_trap_group_stats_idle_test $(devlink_trap_group_get $trap_name)
check_err $? "Trap group stats not idle with when packets should not be dropped"
tc_check_packets "dev $swp2 egress" 101 0
@@ -212,7 +209,7 @@ ingress_vlan_filter_test()
log_test "Ingress VLAN filter"
- devlink_trap_drop_cleanup $mz_pid $swp2 ip
+ devlink_trap_drop_cleanup $mz_pid $swp2 ip 1 101
bridge vlan del vid $vid dev $swp1 master
bridge vlan del vid $vid dev $swp2 master
@@ -222,7 +219,6 @@ __ingress_stp_filter_test()
{
local trap_name="ingress_spanning_tree_filter"
local dmac=de:ad:be:ef:13:37
- local group_name="l2_drops"
local state=$1; shift
local mz_pid
local vid=20
@@ -237,7 +233,7 @@ __ingress_stp_filter_test()
$MZ $h1 -Q $vid -c 0 -p 100 -a own -b $dmac -t ip -d 1msec -q &
mz_pid=$!
- devlink_trap_drop_test $trap_name $group_name $swp2
+ devlink_trap_drop_test $trap_name $swp2 101
# Change STP state to forwarding and make sure packets are no longer
# dropped.
@@ -246,7 +242,7 @@ __ingress_stp_filter_test()
devlink_trap_stats_idle_test $trap_name
check_err $? "Trap stats not idle when packets should not be dropped"
- devlink_trap_group_stats_idle_test $group_name
+ devlink_trap_group_stats_idle_test $(devlink_trap_group_get $trap_name)
check_err $? "Trap group stats not idle with when packets should not be dropped"
tc_check_packets "dev $swp2 egress" 101 0
@@ -254,7 +250,7 @@ __ingress_stp_filter_test()
devlink_trap_action_set $trap_name "drop"
- devlink_trap_drop_cleanup $mz_pid $swp2 ip
+ devlink_trap_drop_cleanup $mz_pid $swp2 ip 1 101
bridge vlan del vid $vid dev $swp1 master
bridge vlan del vid $vid dev $swp2 master
@@ -292,7 +288,6 @@ port_list_is_empty_uc_test()
{
local trap_name="port_list_is_empty"
local dmac=de:ad:be:ef:13:37
- local group_name="l2_drops"
local mz_pid
# Disable unicast flooding on both ports, so that packets cannot egress
@@ -308,7 +303,7 @@ port_list_is_empty_uc_test()
$MZ $h1 -c 0 -p 100 -a own -b $dmac -t ip -d 1msec -q &
mz_pid=$!
- devlink_trap_drop_test $trap_name $group_name $swp2
+ devlink_trap_drop_test $trap_name $swp2 101
# Allow packets to be flooded to one port.
ip link set dev $swp2 type bridge_slave flood on
@@ -316,7 +311,7 @@ port_list_is_empty_uc_test()
devlink_trap_stats_idle_test $trap_name
check_err $? "Trap stats not idle when packets should not be dropped"
- devlink_trap_group_stats_idle_test $group_name
+ devlink_trap_group_stats_idle_test $(devlink_trap_group_get $trap_name)
check_err $? "Trap group stats not idle with when packets should not be dropped"
tc_check_packets "dev $swp2 egress" 101 0
@@ -326,7 +321,7 @@ port_list_is_empty_uc_test()
log_test "Port list is empty - unicast"
- devlink_trap_drop_cleanup $mz_pid $swp2 ip
+ devlink_trap_drop_cleanup $mz_pid $swp2 ip 1 101
ip link set dev $swp1 type bridge_slave flood on
}
@@ -335,7 +330,6 @@ port_list_is_empty_mc_test()
{
local trap_name="port_list_is_empty"
local dmac=01:00:5e:00:00:01
- local group_name="l2_drops"
local dip=239.0.0.1
local mz_pid
@@ -354,7 +348,7 @@ port_list_is_empty_mc_test()
$MZ $h1 -c 0 -p 100 -a own -b $dmac -t ip -B $dip -d 1msec -q &
mz_pid=$!
- devlink_trap_drop_test $trap_name $group_name $swp2
+ devlink_trap_drop_test $trap_name $swp2 101
# Allow packets to be flooded to one port.
ip link set dev $swp2 type bridge_slave mcast_flood on
@@ -362,7 +356,7 @@ port_list_is_empty_mc_test()
devlink_trap_stats_idle_test $trap_name
check_err $? "Trap stats not idle when packets should not be dropped"
- devlink_trap_group_stats_idle_test $group_name
+ devlink_trap_group_stats_idle_test $(devlink_trap_group_get $trap_name)
check_err $? "Trap group stats not idle with when packets should not be dropped"
tc_check_packets "dev $swp2 egress" 101 0
@@ -372,7 +366,7 @@ port_list_is_empty_mc_test()
log_test "Port list is empty - multicast"
- devlink_trap_drop_cleanup $mz_pid $swp2 ip
+ devlink_trap_drop_cleanup $mz_pid $swp2 ip 1 101
ip link set dev $swp1 type bridge_slave mcast_flood on
}
@@ -387,7 +381,6 @@ port_loopback_filter_uc_test()
{
local trap_name="port_loopback_filter"
local dmac=de:ad:be:ef:13:37
- local group_name="l2_drops"
local mz_pid
# Make sure packets can only egress the input port.
@@ -401,7 +394,7 @@ port_loopback_filter_uc_test()
$MZ $h1 -c 0 -p 100 -a own -b $dmac -t ip -d 1msec -q &
mz_pid=$!
- devlink_trap_drop_test $trap_name $group_name $swp2
+ devlink_trap_drop_test $trap_name $swp2 101
# Allow packets to be flooded.
ip link set dev $swp2 type bridge_slave flood on
@@ -409,7 +402,7 @@ port_loopback_filter_uc_test()
devlink_trap_stats_idle_test $trap_name
check_err $? "Trap stats not idle when packets should not be dropped"
- devlink_trap_group_stats_idle_test $group_name
+ devlink_trap_group_stats_idle_test $(devlink_trap_group_get $trap_name)
check_err $? "Trap group stats not idle with when packets should not be dropped"
tc_check_packets "dev $swp2 egress" 101 0
@@ -419,7 +412,7 @@ port_loopback_filter_uc_test()
log_test "Port loopback filter - unicast"
- devlink_trap_drop_cleanup $mz_pid $swp2 ip
+ devlink_trap_drop_cleanup $mz_pid $swp2 ip 1 101
}
port_loopback_filter_test()
diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh
index d88d8e47d11b..f5abb1ebd392 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh
@@ -161,7 +161,6 @@ ping_check()
non_ip_test()
{
local trap_name="non_ip"
- local group_name="l3_drops"
local mz_pid
RET=0
@@ -176,11 +175,11 @@ non_ip_test()
00:00 de:ad:be:ef" &
mz_pid=$!
- devlink_trap_drop_test $trap_name $group_name $rp2
+ devlink_trap_drop_test $trap_name $rp2 101
log_test "Non IP"
- devlink_trap_drop_cleanup $mz_pid $rp2 "ip"
+ devlink_trap_drop_cleanup $mz_pid $rp2 "ip" 1 101
}
__uc_dip_over_mc_dmac_test()
@@ -190,7 +189,6 @@ __uc_dip_over_mc_dmac_test()
local dip=$1; shift
local flags=${1:-""}; shift
local trap_name="uc_dip_over_mc_dmac"
- local group_name="l3_drops"
local dmac=01:02:03:04:05:06
local mz_pid
@@ -206,11 +204,11 @@ __uc_dip_over_mc_dmac_test()
-B $dip -d 1msec -q &
mz_pid=$!
- devlink_trap_drop_test $trap_name $group_name $rp2
+ devlink_trap_drop_test $trap_name $rp2 101
log_test "Unicast destination IP over multicast destination MAC: $desc"
- devlink_trap_drop_cleanup $mz_pid $rp2 $proto
+ devlink_trap_drop_cleanup $mz_pid $rp2 $proto 1 101
}
uc_dip_over_mc_dmac_test()
@@ -227,7 +225,6 @@ __sip_is_loopback_test()
local dip=$1; shift
local flags=${1:-""}; shift
local trap_name="sip_is_loopback_address"
- local group_name="l3_drops"
local mz_pid
RET=0
@@ -242,11 +239,11 @@ __sip_is_loopback_test()
-b $rp1mac -B $dip -d 1msec -q &
mz_pid=$!
- devlink_trap_drop_test $trap_name $group_name $rp2
+ devlink_trap_drop_test $trap_name $rp2 101
log_test "Source IP is loopback address: $desc"
- devlink_trap_drop_cleanup $mz_pid $rp2 $proto
+ devlink_trap_drop_cleanup $mz_pid $rp2 $proto 1 101
}
sip_is_loopback_test()
@@ -262,7 +259,6 @@ __dip_is_loopback_test()
local dip=$1; shift
local flags=${1:-""}; shift
local trap_name="dip_is_loopback_address"
- local group_name="l3_drops"
local mz_pid
RET=0
@@ -277,11 +273,11 @@ __dip_is_loopback_test()
-B $dip -d 1msec -q &
mz_pid=$!
- devlink_trap_drop_test $trap_name $group_name $rp2
+ devlink_trap_drop_test $trap_name $rp2 101
log_test "Destination IP is loopback address: $desc"
- devlink_trap_drop_cleanup $mz_pid $rp2 $proto
+ devlink_trap_drop_cleanup $mz_pid $rp2 $proto 1 101
}
dip_is_loopback_test()
@@ -298,7 +294,6 @@ __sip_is_mc_test()
local dip=$1; shift
local flags=${1:-""}; shift
local trap_name="sip_is_mc"
- local group_name="l3_drops"
local mz_pid
RET=0
@@ -313,11 +308,11 @@ __sip_is_mc_test()
-b $rp1mac -B $dip -d 1msec -q &
mz_pid=$!
- devlink_trap_drop_test $trap_name $group_name $rp2
+ devlink_trap_drop_test $trap_name $rp2 101
log_test "Source IP is multicast: $desc"
- devlink_trap_drop_cleanup $mz_pid $rp2 $proto
+ devlink_trap_drop_cleanup $mz_pid $rp2 $proto 1 101
}
sip_is_mc_test()
@@ -329,7 +324,6 @@ sip_is_mc_test()
ipv4_sip_is_limited_bc_test()
{
local trap_name="ipv4_sip_is_limited_bc"
- local group_name="l3_drops"
local sip=255.255.255.255
local mz_pid
@@ -345,11 +339,11 @@ ipv4_sip_is_limited_bc_test()
-B $h2_ipv4 -d 1msec -q &
mz_pid=$!
- devlink_trap_drop_test $trap_name $group_name $rp2
+ devlink_trap_drop_test $trap_name $rp2 101
log_test "IPv4 source IP is limited broadcast"
- devlink_trap_drop_cleanup $mz_pid $rp2 "ip"
+ devlink_trap_drop_cleanup $mz_pid $rp2 "ip" 1 101
}
ipv4_payload_get()
@@ -382,7 +376,6 @@ __ipv4_header_corrupted_test()
local ihl=$1; shift
local checksum=$1; shift
local trap_name="ip_header_corrupted"
- local group_name="l3_drops"
local payload
local mz_pid
@@ -399,11 +392,11 @@ __ipv4_header_corrupted_test()
$MZ $h1 -c 0 -d 1msec -a $h1mac -b $rp1mac -q p=$payload &
mz_pid=$!
- devlink_trap_drop_test $trap_name $group_name $rp2
+ devlink_trap_drop_test $trap_name $rp2 101
log_test "IP header corrupted: $desc: IPv4"
- devlink_trap_drop_cleanup $mz_pid $rp2 "ip"
+ devlink_trap_drop_cleanup $mz_pid $rp2 "ip" 1 101
}
ipv6_payload_get()
@@ -429,7 +422,6 @@ __ipv6_header_corrupted_test()
local desc=$1; shift
local ipver=$1; shift
local trap_name="ip_header_corrupted"
- local group_name="l3_drops"
local payload
local mz_pid
@@ -446,11 +438,11 @@ __ipv6_header_corrupted_test()
$MZ $h1 -c 0 -d 1msec -a $h1mac -b $rp1mac -q p=$payload &
mz_pid=$!
- devlink_trap_drop_test $trap_name $group_name $rp2
+ devlink_trap_drop_test $trap_name $rp2 101
log_test "IP header corrupted: $desc: IPv6"
- devlink_trap_drop_cleanup $mz_pid $rp2 "ip"
+ devlink_trap_drop_cleanup $mz_pid $rp2 "ip" 1 101
}
ip_header_corrupted_test()
@@ -469,7 +461,6 @@ ip_header_corrupted_test()
ipv6_mc_dip_reserved_scope_test()
{
local trap_name="ipv6_mc_dip_reserved_scope"
- local group_name="l3_drops"
local dip=FF00::
local mz_pid
@@ -485,17 +476,16 @@ ipv6_mc_dip_reserved_scope_test()
"33:33:00:00:00:00" -B $dip -d 1msec -q &
mz_pid=$!
- devlink_trap_drop_test $trap_name $group_name $rp2
+ devlink_trap_drop_test $trap_name $rp2 101
log_test "IPv6 multicast destination IP reserved scope"
- devlink_trap_drop_cleanup $mz_pid $rp2 "ipv6"
+ devlink_trap_drop_cleanup $mz_pid $rp2 "ipv6" 1 101
}
ipv6_mc_dip_interface_local_scope_test()
{
local trap_name="ipv6_mc_dip_interface_local_scope"
- local group_name="l3_drops"
local dip=FF01::
local mz_pid
@@ -511,11 +501,11 @@ ipv6_mc_dip_interface_local_scope_test()
"33:33:00:00:00:00" -B $dip -d 1msec -q &
mz_pid=$!
- devlink_trap_drop_test $trap_name $group_name $rp2
+ devlink_trap_drop_test $trap_name $rp2 101
log_test "IPv6 multicast destination IP interface-local scope"
- devlink_trap_drop_cleanup $mz_pid $rp2 "ipv6"
+ devlink_trap_drop_cleanup $mz_pid $rp2 "ipv6" 1 101
}
__blackhole_route_test()
@@ -526,7 +516,6 @@ __blackhole_route_test()
local dip=$1; shift
local ip_proto=${1:-"icmp"}; shift
local trap_name="blackhole_route"
- local group_name="l3_drops"
local mz_pid
RET=0
@@ -542,10 +531,10 @@ __blackhole_route_test()
-B $dip -d 1msec -q &
mz_pid=$!
- devlink_trap_drop_test $trap_name $group_name $rp2
+ devlink_trap_drop_test $trap_name $rp2 101
log_test "Blackhole route: IPv$flags"
- devlink_trap_drop_cleanup $mz_pid $rp2 $proto
+ devlink_trap_drop_cleanup $mz_pid $rp2 $proto 1 101
ip -$flags route del blackhole $subnet
}
@@ -558,7 +547,6 @@ blackhole_route_test()
irif_disabled_test()
{
local trap_name="irif_disabled"
- local group_name="l3_drops"
local t0_packets t0_bytes
local t1_packets t1_bytes
local mz_pid
@@ -613,7 +601,6 @@ irif_disabled_test()
erif_disabled_test()
{
local trap_name="erif_disabled"
- local group_name="l3_drops"
local t0_packets t0_bytes
local t1_packets t1_bytes
local mz_pid
@@ -641,13 +628,9 @@ erif_disabled_test()
mz_pid=$!
sleep 5
- # In order to see this trap we need a route that points to disabled RIF.
- # When ipv6 address is flushed, there is a delay and the routes are
- # deleted before the RIF and we cannot get state that we have route
- # to disabled RIF.
- # Delete IPv6 address first and then check this trap with flushing IPv4.
- ip -6 add flush dev br0
- ip -4 add flush dev br0
+ # Unlinking the port from the bridge will disable the RIF associated
+ # with br0 as it is no longer an upper of any mlxsw port.
+ ip link set dev $rp1 nomaster
t1_packets=$(devlink_trap_rx_packets_get $trap_name)
t1_bytes=$(devlink_trap_rx_bytes_get $trap_name)
@@ -659,7 +642,6 @@ erif_disabled_test()
log_test "Egress RIF disabled"
kill $mz_pid && wait $mz_pid &> /dev/null
- ip link set dev $rp1 nomaster
__addr_add_del $rp1 add 192.0.2.2/24 2001:db8:1::2/64
ip link del dev br0 type bridge
devlink_trap_action_set $trap_name "drop"
diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_exceptions.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_exceptions.sh
index 2bc6df42d597..1fedfc9da434 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_exceptions.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_exceptions.sh
@@ -169,7 +169,6 @@ trap_action_check()
mtu_value_is_too_small_test()
{
local trap_name="mtu_value_is_too_small"
- local group_name="l3_drops"
local expected_action="trap"
local mz_pid
@@ -191,7 +190,7 @@ mtu_value_is_too_small_test()
-B 198.51.100.1 -q &
mz_pid=$!
- devlink_trap_exception_test $trap_name $group_name
+ devlink_trap_exception_test $trap_name
tc_check_packets_hitting "dev $h1 ingress" 101
check_err $? "Packets were not received to h1"
@@ -208,7 +207,6 @@ __ttl_value_is_too_small_test()
{
local ttl_val=$1; shift
local trap_name="ttl_value_is_too_small"
- local group_name="l3_drops"
local expected_action="trap"
local mz_pid
@@ -227,7 +225,7 @@ __ttl_value_is_too_small_test()
-b $rp1mac -B 198.51.100.1 -q &
mz_pid=$!
- devlink_trap_exception_test $trap_name $group_name
+ devlink_trap_exception_test $trap_name
tc_check_packets_hitting "dev $h1 ingress" 101
check_err $? "Packets were not received to h1"
@@ -271,7 +269,6 @@ __mc_reverse_path_forwarding_test()
local proto=$1; shift
local flags=${1:-""}; shift
local trap_name="mc_reverse_path_forwarding"
- local group_name="l3_drops"
local expected_action="trap"
local mz_pid
@@ -292,7 +289,7 @@ __mc_reverse_path_forwarding_test()
mz_pid=$!
- devlink_trap_exception_test $trap_name $group_name
+ devlink_trap_exception_test $trap_name
tc_check_packets "dev $rp2 egress" 101 0
check_err $? "Packets were not dropped"
@@ -322,7 +319,6 @@ __reject_route_test()
local unreachable=$1; shift
local flags=${1:-""}; shift
local trap_name="reject_route"
- local group_name="l3_drops"
local expected_action="trap"
local mz_pid
@@ -341,7 +337,7 @@ __reject_route_test()
-B $dst_ip -q &
mz_pid=$!
- devlink_trap_exception_test $trap_name $group_name
+ devlink_trap_exception_test $trap_name
tc_check_packets_hitting "dev $h1 ingress" 101
check_err $? "ICMP packet was not received to h1"
@@ -370,7 +366,6 @@ __host_miss_test()
local desc=$1; shift
local dip=$1; shift
local trap_name="unresolved_neigh"
- local group_name="l3_drops"
local expected_action="trap"
local mz_pid
@@ -405,7 +400,6 @@ __invalid_nexthop_test()
local subnet=$1; shift
local via_add=$1; shift
local trap_name="unresolved_neigh"
- local group_name="l3_drops"
local expected_action="trap"
local mz_pid
@@ -494,7 +488,6 @@ vrf_without_routes_destroy()
ipv4_lpm_miss_test()
{
local trap_name="ipv4_lpm_miss"
- local group_name="l3_drops"
local expected_action="trap"
local mz_pid
@@ -511,7 +504,7 @@ ipv4_lpm_miss_test()
-B 203.0.113.1 -q &
mz_pid=$!
- devlink_trap_exception_test $trap_name $group_name
+ devlink_trap_exception_test $trap_name
log_test "LPM miss: IPv4"
@@ -522,7 +515,6 @@ ipv4_lpm_miss_test()
ipv6_lpm_miss_test()
{
local trap_name="ipv6_lpm_miss"
- local group_name="l3_drops"
local expected_action="trap"
local mz_pid
@@ -539,7 +531,7 @@ ipv6_lpm_miss_test()
-B 2001:db8::1 -q &
mz_pid=$!
- devlink_trap_exception_test $trap_name $group_name
+ devlink_trap_exception_test $trap_name
log_test "LPM miss: IPv6"
diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_policer.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_policer.sh
new file mode 100755
index 000000000000..47edf099a17e
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_policer.sh
@@ -0,0 +1,384 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test devlink-trap policer functionality over mlxsw.
+
+# +---------------------------------+
+# | H1 (vrf) |
+# | + $h1 |
+# | | 192.0.2.1/24 |
+# | | |
+# | | default via 192.0.2.2 |
+# +----|----------------------------+
+# |
+# +----|----------------------------------------------------------------------+
+# | SW | |
+# | + $rp1 |
+# | 192.0.2.2/24 |
+# | |
+# | 198.51.100.2/24 |
+# | + $rp2 |
+# | | |
+# +----|----------------------------------------------------------------------+
+# |
+# +----|----------------------------+
+# | | default via 198.51.100.2 |
+# | | |
+# | | 198.51.100.1/24 |
+# | + $h2 |
+# | H2 (vrf) |
+# +---------------------------------+
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+
+ALL_TESTS="
+ rate_limits_test
+ burst_limits_test
+ rate_test
+ burst_test
+"
+NUM_NETIFS=4
+source $lib_dir/tc_common.sh
+source $lib_dir/lib.sh
+source $lib_dir/devlink_lib.sh
+
+h1_create()
+{
+ simple_if_init $h1 192.0.2.1/24
+ mtu_set $h1 10000
+
+ ip -4 route add default vrf v$h1 nexthop via 192.0.2.2
+}
+
+h1_destroy()
+{
+ ip -4 route del default vrf v$h1 nexthop via 192.0.2.2
+
+ mtu_restore $h1
+ simple_if_fini $h1 192.0.2.1/24
+}
+
+h2_create()
+{
+ simple_if_init $h2 198.51.100.1/24
+ mtu_set $h2 10000
+
+ ip -4 route add default vrf v$h2 nexthop via 198.51.100.2
+}
+
+h2_destroy()
+{
+ ip -4 route del default vrf v$h2 nexthop via 198.51.100.2
+
+ mtu_restore $h2
+ simple_if_fini $h2 198.51.100.1/24
+}
+
+router_create()
+{
+ ip link set dev $rp1 up
+ ip link set dev $rp2 up
+
+ __addr_add_del $rp1 add 192.0.2.2/24
+ __addr_add_del $rp2 add 198.51.100.2/24
+ mtu_set $rp1 10000
+ mtu_set $rp2 10000
+
+ ip -4 route add blackhole 198.51.100.100
+
+ devlink trap set $DEVLINK_DEV trap blackhole_route action trap
+}
+
+router_destroy()
+{
+ devlink trap set $DEVLINK_DEV trap blackhole_route action drop
+
+ ip -4 route del blackhole 198.51.100.100
+
+ mtu_restore $rp2
+ mtu_restore $rp1
+ __addr_add_del $rp2 del 198.51.100.2/24
+ __addr_add_del $rp1 del 192.0.2.2/24
+
+ ip link set dev $rp2 down
+ ip link set dev $rp1 down
+}
+
+setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ rp1=${NETIFS[p2]}
+
+ rp2=${NETIFS[p3]}
+ h2=${NETIFS[p4]}
+
+ rp1_mac=$(mac_get $rp1)
+
+ vrf_prepare
+
+ h1_create
+ h2_create
+
+ router_create
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ router_destroy
+
+ h2_destroy
+ h1_destroy
+
+ vrf_cleanup
+
+ # Reload to ensure devlink-trap settings are back to default.
+ devlink_reload
+}
+
+rate_limits_test()
+{
+ RET=0
+
+ devlink trap policer set $DEVLINK_DEV policer 1 rate 0 &> /dev/null
+ check_fail $? "Policer rate was changed to rate lower than limit"
+ devlink trap policer set $DEVLINK_DEV policer 1 \
+ rate 2000000001 &> /dev/null
+ check_fail $? "Policer rate was changed to rate higher than limit"
+
+ devlink trap policer set $DEVLINK_DEV policer 1 rate 1
+ check_err $? "Failed to set policer rate to minimum"
+ devlink trap policer set $DEVLINK_DEV policer 1 rate 2000000000
+ check_err $? "Failed to set policer rate to maximum"
+
+ log_test "Trap policer rate limits"
+}
+
+burst_limits_test()
+{
+ RET=0
+
+ devlink trap policer set $DEVLINK_DEV policer 1 burst 0 &> /dev/null
+ check_fail $? "Policer burst size was changed to 0"
+ devlink trap policer set $DEVLINK_DEV policer 1 burst 17 &> /dev/null
+ check_fail $? "Policer burst size was changed to burst size that is not power of 2"
+ devlink trap policer set $DEVLINK_DEV policer 1 burst 8 &> /dev/null
+ check_fail $? "Policer burst size was changed to burst size lower than limit"
+ devlink trap policer set $DEVLINK_DEV policer 1 \
+ burst $((2**25)) &> /dev/null
+ check_fail $? "Policer burst size was changed to burst size higher than limit"
+
+ devlink trap policer set $DEVLINK_DEV policer 1 burst 16
+ check_err $? "Failed to set policer burst size to minimum"
+ devlink trap policer set $DEVLINK_DEV policer 1 burst $((2**24))
+ check_err $? "Failed to set policer burst size to maximum"
+
+ log_test "Trap policer burst size limits"
+}
+
+trap_rate_get()
+{
+ local t0 t1
+
+ t0=$(devlink_trap_rx_packets_get blackhole_route)
+ sleep 10
+ t1=$(devlink_trap_rx_packets_get blackhole_route)
+
+ echo $(((t1 - t0) / 10))
+}
+
+policer_drop_rate_get()
+{
+ local id=$1; shift
+ local t0 t1
+
+ t0=$(devlink_trap_policer_rx_dropped_get $id)
+ sleep 10
+ t1=$(devlink_trap_policer_rx_dropped_get $id)
+
+ echo $(((t1 - t0) / 10))
+}
+
+__rate_test()
+{
+ local rate pct drop_rate
+ local id=$1; shift
+
+ RET=0
+
+ devlink trap policer set $DEVLINK_DEV policer $id rate 1000 burst 16
+ devlink trap group set $DEVLINK_DEV group l3_drops policer $id
+
+ # Send packets at highest possible rate and make sure they are dropped
+ # by the policer. Make sure measured received rate is about 1000 pps
+ log_info "=== Tx rate: Highest, Policer rate: 1000 pps ==="
+
+ start_traffic $h1 192.0.2.1 198.51.100.100 $rp1_mac
+
+ sleep 5 # Take measurements when rate is stable
+
+ rate=$(trap_rate_get)
+ pct=$((100 * (rate - 1000) / 1000))
+ ((-5 <= pct && pct <= 5))
+ check_err $? "Expected rate 1000 pps, got $rate pps, which is $pct% off. Required accuracy is +-5%"
+ log_info "Expected rate 1000 pps, measured rate $rate pps"
+
+ drop_rate=$(policer_drop_rate_get $id)
+ (( drop_rate > 0 ))
+ check_err $? "Expected non-zero policer drop rate, got 0"
+ log_info "Measured policer drop rate of $drop_rate pps"
+
+ stop_traffic
+
+ # Send packets at a rate of 1000 pps and make sure they are not dropped
+ # by the policer
+ log_info "=== Tx rate: 1000 pps, Policer rate: 1000 pps ==="
+
+ start_traffic $h1 192.0.2.1 198.51.100.100 $rp1_mac -d 1msec
+
+ sleep 5 # Take measurements when rate is stable
+
+ drop_rate=$(policer_drop_rate_get $id)
+ (( drop_rate == 0 ))
+ check_err $? "Expected zero policer drop rate, got a drop rate of $drop_rate pps"
+ log_info "Measured policer drop rate of $drop_rate pps"
+
+ stop_traffic
+
+ # Unbind the policer and send packets at highest possible rate. Make
+ # sure they are not dropped by the policer and that the measured
+ # received rate is higher than 1000 pps
+ log_info "=== Tx rate: Highest, Policer rate: No policer ==="
+
+ devlink trap group set $DEVLINK_DEV group l3_drops nopolicer
+
+ start_traffic $h1 192.0.2.1 198.51.100.100 $rp1_mac
+
+ rate=$(trap_rate_get)
+ (( rate > 1000 ))
+ check_err $? "Expected rate higher than 1000 pps, got $rate pps"
+ log_info "Measured rate $rate pps"
+
+ drop_rate=$(policer_drop_rate_get $id)
+ (( drop_rate == 0 ))
+ check_err $? "Expected zero policer drop rate, got a drop rate of $drop_rate pps"
+ log_info "Measured policer drop rate of $drop_rate pps"
+
+ stop_traffic
+
+ log_test "Trap policer rate"
+}
+
+rate_test()
+{
+ local id
+
+ for id in $(devlink_trap_policer_ids_get); do
+ echo
+ log_info "Running rate test for policer $id"
+ __rate_test $id
+ done
+}
+
+__burst_test()
+{
+ local t0_rx t0_drop t1_rx t1_drop rx drop
+ local id=$1; shift
+
+ RET=0
+
+ devlink trap policer set $DEVLINK_DEV policer $id rate 1000 burst 32
+ devlink trap group set $DEVLINK_DEV group l3_drops policer $id
+
+ # Send a burst of 64 packets and make sure that about 32 are received
+ # and the rest are dropped by the policer
+ log_info "=== Tx burst size: 64, Policer burst size: 32 pps ==="
+
+ t0_rx=$(devlink_trap_rx_packets_get blackhole_route)
+ t0_drop=$(devlink_trap_policer_rx_dropped_get $id)
+
+ start_traffic $h1 192.0.2.1 198.51.100.100 $rp1_mac -c 64
+
+ t1_rx=$(devlink_trap_rx_packets_get blackhole_route)
+ t1_drop=$(devlink_trap_policer_rx_dropped_get $id)
+
+ rx=$((t1_rx - t0_rx))
+ pct=$((100 * (rx - 32) / 32))
+ ((-20 <= pct && pct <= 20))
+ check_err $? "Expected burst size of 32 packets, got $rx packets, which is $pct% off. Required accuracy is +-20%"
+ log_info "Expected burst size of 32 packets, measured burst size of $rx packets"
+
+ drop=$((t1_drop - t0_drop))
+ (( drop > 0 ))
+ check_err $? "Expected non-zero policer drops, got 0"
+ log_info "Measured policer drops of $drop packets"
+
+ # Send a burst of 16 packets and make sure that 16 are received
+ # and that none are dropped by the policer
+ log_info "=== Tx burst size: 16, Policer burst size: 32 pps ==="
+
+ t0_rx=$(devlink_trap_rx_packets_get blackhole_route)
+ t0_drop=$(devlink_trap_policer_rx_dropped_get $id)
+
+ start_traffic $h1 192.0.2.1 198.51.100.100 $rp1_mac -c 16
+
+ t1_rx=$(devlink_trap_rx_packets_get blackhole_route)
+ t1_drop=$(devlink_trap_policer_rx_dropped_get $id)
+
+ rx=$((t1_rx - t0_rx))
+ (( rx == 16 ))
+ check_err $? "Expected burst size of 16 packets, got $rx packets"
+ log_info "Expected burst size of 16 packets, measured burst size of $rx packets"
+
+ drop=$((t1_drop - t0_drop))
+ (( drop == 0 ))
+ check_err $? "Expected zero policer drops, got $drop"
+ log_info "Measured policer drops of $drop packets"
+
+ # Unbind the policer and send a burst of 64 packets. Make sure that
+ # 64 packets are received and that none are dropped by the policer
+ log_info "=== Tx burst size: 64, Policer burst size: No policer ==="
+
+ devlink trap group set $DEVLINK_DEV group l3_drops nopolicer
+
+ t0_rx=$(devlink_trap_rx_packets_get blackhole_route)
+ t0_drop=$(devlink_trap_policer_rx_dropped_get $id)
+
+ start_traffic $h1 192.0.2.1 198.51.100.100 $rp1_mac -c 64
+
+ t1_rx=$(devlink_trap_rx_packets_get blackhole_route)
+ t1_drop=$(devlink_trap_policer_rx_dropped_get $id)
+
+ rx=$((t1_rx - t0_rx))
+ (( rx == 64 ))
+ check_err $? "Expected burst size of 64 packets, got $rx packets"
+ log_info "Expected burst size of 64 packets, measured burst size of $rx packets"
+
+ drop=$((t1_drop - t0_drop))
+ (( drop == 0 ))
+ check_err $? "Expected zero policer drops, got $drop"
+ log_info "Measured policer drops of $drop packets"
+
+ log_test "Trap policer burst size"
+}
+
+burst_test()
+{
+ local id
+
+ for id in $(devlink_trap_policer_ids_get); do
+ echo
+ log_info "Running burst size test for policer $id"
+ __burst_test $id
+ done
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh
index 039629bb92a3..8817851da7a9 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh
@@ -140,7 +140,6 @@ ecn_payload_get()
ecn_decap_test()
{
local trap_name="decap_error"
- local group_name="tunnel_drops"
local desc=$1; shift
local ecn_desc=$1; shift
local outer_tos=$1; shift
@@ -161,7 +160,7 @@ ecn_decap_test()
mz_pid=$!
- devlink_trap_exception_test $trap_name $group_name
+ devlink_trap_exception_test $trap_name
tc_check_packets "dev $swp1 egress" 101 0
check_err $? "Packets were not dropped"
@@ -200,7 +199,6 @@ ipip_payload_get()
no_matching_tunnel_test()
{
local trap_name="decap_error"
- local group_name="tunnel_drops"
local desc=$1; shift
local sip=$1; shift
local mz_pid
@@ -218,7 +216,7 @@ no_matching_tunnel_test()
-A $sip -B 192.0.2.65 -t ip len=48,proto=47,p=$payload -q &
mz_pid=$!
- devlink_trap_exception_test $trap_name $group_name
+ devlink_trap_exception_test $trap_name
tc_check_packets "dev $swp1 egress" 101 0
check_err $? "Packets were not dropped"
diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan.sh
index fd19161dd4ec..10e0f3dbc930 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan.sh
@@ -159,7 +159,6 @@ ecn_payload_get()
ecn_decap_test()
{
local trap_name="decap_error"
- local group_name="tunnel_drops"
local desc=$1; shift
local ecn_desc=$1; shift
local outer_tos=$1; shift
@@ -177,7 +176,7 @@ ecn_decap_test()
-t udp sp=12345,dp=$VXPORT,tos=$outer_tos,p=$payload -q &
mz_pid=$!
- devlink_trap_exception_test $trap_name $group_name
+ devlink_trap_exception_test $trap_name
tc_check_packets "dev $swp1 egress" 101 0
check_err $? "Packets were not dropped"
@@ -228,7 +227,6 @@ short_payload_get()
corrupted_packet_test()
{
local trap_name="decap_error"
- local group_name="tunnel_drops"
local desc=$1; shift
local payload_get=$1; shift
local mz_pid
@@ -246,7 +244,7 @@ corrupted_packet_test()
-B 192.0.2.17 -t udp sp=12345,dp=$VXPORT,p=$payload -q &
mz_pid=$!
- devlink_trap_exception_test $trap_name $group_name
+ devlink_trap_exception_test $trap_name
tc_check_packets "dev $swp1 egress" 101 0
check_err $? "Packets were not dropped"
@@ -297,7 +295,6 @@ mc_smac_payload_get()
overlay_smac_is_mc_test()
{
local trap_name="overlay_smac_is_mc"
- local group_name="tunnel_drops"
local mz_pid
RET=0
@@ -314,11 +311,11 @@ overlay_smac_is_mc_test()
-B 192.0.2.17 -t udp sp=12345,dp=$VXPORT,p=$payload -q &
mz_pid=$!
- devlink_trap_drop_test $trap_name $group_name $swp1
+ devlink_trap_drop_test $trap_name $swp1 101
log_test "Overlay source MAC is multicast"
- devlink_trap_drop_cleanup $mz_pid $swp1 "ip"
+ devlink_trap_drop_cleanup $mz_pid $swp1 "ip" 1 101
}
trap cleanup EXIT
diff --git a/tools/testing/selftests/drivers/net/mlxsw/extack.sh b/tools/testing/selftests/drivers/net/mlxsw/extack.sh
index d72d8488a3b2..7a0a99c1d22f 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/extack.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/extack.sh
@@ -8,7 +8,8 @@ lib_dir=$(dirname $0)/../../../net/forwarding
ALL_TESTS="
netdev_pre_up_test
vxlan_vlan_add_test
- port_vlan_add_test
+ vxlan_bridge_create_test
+ bridge_create_test
"
NUM_NETIFS=2
source $lib_dir/lib.sh
@@ -106,32 +107,56 @@ vxlan_vlan_add_test()
ip link del dev br1
}
-port_vlan_add_test()
+vxlan_bridge_create_test()
{
RET=0
- ip link add name br1 up type bridge vlan_filtering 1 mcast_snooping 0
-
# Unsupported configuration: mlxsw demands VXLAN with "noudpcsum".
ip link add name vx1 up type vxlan id 1000 \
local 192.0.2.17 remote 192.0.2.18 \
dstport 4789 tos inherit ttl 100
- ip link set dev $swp1 master br1
- check_err $?
-
- bridge vlan del dev $swp1 vid 1
+ # Test with VLAN-aware bridge.
+ ip link add name br1 up type bridge vlan_filtering 1 mcast_snooping 0
ip link set dev vx1 master br1
+
+ ip link set dev $swp1 master br1 2>&1 > /dev/null \
+ | grep -q mlxsw_spectrum
check_err $?
- bridge vlan add dev $swp1 vid 1 pvid untagged 2>&1 >/dev/null \
+ # Test with VLAN-unaware bridge.
+ ip link set dev br1 type bridge vlan_filtering 0
+
+ ip link set dev $swp1 master br1 2>&1 > /dev/null \
| grep -q mlxsw_spectrum
check_err $?
- log_test "extack - map VLAN at port"
+ log_test "extack - bridge creation with VXLAN"
+ ip link del dev br1
ip link del dev vx1
+}
+
+bridge_create_test()
+{
+ RET=0
+
+ ip link add name br1 up type bridge vlan_filtering 1
+ ip link add name br2 up type bridge vlan_filtering 1
+
+ ip link set dev $swp1 master br1
+ check_err $?
+
+ # Only one VLAN-aware bridge is supported, so this should fail with
+ # an extack.
+ ip link set dev $swp2 master br2 2>&1 > /dev/null \
+ | grep -q mlxsw_spectrum
+ check_err $?
+
+ log_test "extack - multiple VLAN-aware bridges creation"
+
+ ip link del dev br2
ip link del dev br1
}
diff --git a/tools/testing/selftests/drivers/net/mlxsw/mlxsw_lib.sh b/tools/testing/selftests/drivers/net/mlxsw/mlxsw_lib.sh
new file mode 100644
index 000000000000..cbe50f260a40
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/mlxsw_lib.sh
@@ -0,0 +1,13 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+##############################################################################
+# Defines
+
+if [[ ! -v MLXSW_CHIP ]]; then
+ MLXSW_CHIP=$(devlink -j dev info $DEVLINK_DEV | jq -r '.[][]["driver"]')
+ if [ -z "$MLXSW_CHIP" ]; then
+ echo "SKIP: Device $DEVLINK_DEV doesn't support devlink info command"
+ exit 1
+ fi
+fi
diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_defprio.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_defprio.sh
index eff6393ce974..71066bc4b886 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/qos_defprio.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/qos_defprio.sh
@@ -114,23 +114,12 @@ ping_ipv4()
ping_test $h1 192.0.2.2
}
-wait_for_packets()
-{
- local t0=$1; shift
- local prio_observe=$1; shift
-
- local t1=$(ethtool_stats_get $swp1 rx_frames_prio_$prio_observe)
- local delta=$((t1 - t0))
- echo $delta
- ((delta >= 10))
-}
-
__test_defprio()
{
local prio_install=$1; shift
local prio_observe=$1; shift
- local delta
local key
+ local t1
local i
RET=0
@@ -139,9 +128,10 @@ __test_defprio()
local t0=$(ethtool_stats_get $swp1 rx_frames_prio_$prio_observe)
mausezahn -q $h1 -d 100m -c 10 -t arp reply
- delta=$(busywait "$HIT_TIMEOUT" wait_for_packets $t0 $prio_observe)
+ t1=$(busywait "$HIT_TIMEOUT" until_counter_is ">= $((t0 + 10))" \
+ ethtool_stats_get $swp1 rx_frames_prio_$prio_observe)
- check_err $? "Default priority $prio_install/$prio_observe: Expected to capture 10 packets, got $delta."
+ check_err $? "Default priority $prio_install/$prio_observe: Expected to capture 10 packets, got $((t1 - t0))."
log_test "Default priority $prio_install/$prio_observe"
defprio_uninstall $swp1 $prio_install
diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_router.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_router.sh
index c745ce3befee..4cb2aa65278a 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_router.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_router.sh
@@ -31,6 +31,7 @@ ALL_TESTS="
ping_ipv4
test_update
test_no_update
+ test_pedit_norewrite
test_dscp_leftover
"
@@ -56,6 +57,11 @@ zero()
echo 0
}
+three()
+{
+ echo 3
+}
+
h1_create()
{
simple_if_init $h1 192.0.2.1/28
@@ -103,6 +109,9 @@ switch_create()
simple_if_init $swp1 192.0.2.2/28
__simple_if_init $swp2 v$swp1 192.0.2.17/28
+ tc qdisc add dev $swp1 clsact
+ tc qdisc add dev $swp2 clsact
+
lldptool -T -i $swp1 -V APP $(dscp_map 0) >/dev/null
lldptool -T -i $swp2 -V APP $(dscp_map 0) >/dev/null
lldpad_app_wait_set $swp1
@@ -115,6 +124,9 @@ switch_destroy()
lldptool -T -i $swp1 -V APP -d $(dscp_map 0) >/dev/null
lldpad_app_wait_del
+ tc qdisc del dev $swp2 clsact
+ tc qdisc del dev $swp1 clsact
+
__simple_if_fini $swp2 192.0.2.17/28
simple_if_fini $swp1 192.0.2.2/28
}
@@ -223,18 +235,36 @@ __test_update()
test_update()
{
+ echo "Test net.ipv4.ip_forward_update_priority=1"
__test_update 1 reprioritize
}
test_no_update()
{
+ echo "Test net.ipv4.ip_forward_update_priority=0"
__test_update 0 echo
}
+# Test that when DSCP is updated in pedit, the DSCP rewrite is turned off.
+test_pedit_norewrite()
+{
+ echo "Test no DSCP rewrite after DSCP is updated by pedit"
+
+ tc filter add dev $swp1 ingress handle 101 pref 1 prot ip flower \
+ action pedit ex munge ip dsfield set $((3 << 2)) retain 0xfc \
+ action skbedit priority 3
+
+ __test_update 0 three
+
+ tc filter del dev $swp1 ingress pref 1
+}
+
# Test that when the last APP rule is removed, the prio->DSCP map is properly
# set to zeroes, and that the last APP rule does not stay active in the ASIC.
test_dscp_leftover()
{
+ echo "Test that last removed DSCP rule is deconfigured correctly"
+
lldptool -T -i $swp2 -V APP -d $(dscp_map 0) >/dev/null
lldpad_app_wait_del
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 24dd8ed48580..b025daea062d 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh
@@ -300,7 +300,7 @@ test_uc_aware()
local i
for ((i = 0; i < attempts; ++i)); do
- if $ARPING -c 1 -I $h1 -b 192.0.2.66 -q -w 0.1; then
+ if $ARPING -c 1 -I $h1 -b 192.0.2.66 -q -w 1; then
((passes++))
fi
diff --git a/tools/testing/selftests/drivers/net/mlxsw/router_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/router_scale.sh
index d231649b4f01..e93878d42596 100644
--- a/tools/testing/selftests/drivers/net/mlxsw/router_scale.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/router_scale.sh
@@ -2,16 +2,15 @@
# SPDX-License-Identifier: GPL-2.0
ROUTER_NUM_NETIFS=4
+: ${TIMEOUT:=20000} # ms
router_h1_create()
{
simple_if_init $h1 192.0.1.1/24
- ip route add 193.0.0.0/8 via 192.0.1.2 dev $h1
}
router_h1_destroy()
{
- ip route del 193.0.0.0/8 via 192.0.1.2 dev $h1
simple_if_fini $h1 192.0.1.1/24
}
@@ -64,13 +63,15 @@ router_setup_prepare()
router_create
}
-router_offload_validate()
+wait_for_routes()
{
- local route_count=$1
- local offloaded_count
+ local t0=$1; shift
+ local route_count=$1; shift
- offloaded_count=$(ip route | grep -o 'offload' | wc -l)
- [[ $offloaded_count -ge $route_count ]]
+ local t1=$(ip route | grep -o 'offload' | wc -l)
+ local delta=$((t1 - t0))
+ echo $delta
+ [[ $delta -ge $route_count ]]
}
router_routes_create()
@@ -90,8 +91,8 @@ router_routes_create()
break 3
fi
- echo route add 193.${i}.${j}.${k}/32 via \
- 192.0.2.1 dev $rp2 >> $ROUTE_FILE
+ echo route add 193.${i}.${j}.${k}/32 dev $rp2 \
+ >> $ROUTE_FILE
((count++))
done
done
@@ -111,45 +112,19 @@ router_test()
{
local route_count=$1
local should_fail=$2
- local count=0
+ local delta
RET=0
+ local t0=$(ip route | grep -o 'offload' | wc -l)
router_routes_create $route_count
+ delta=$(busywait "$TIMEOUT" wait_for_routes $t0 $route_count)
- router_offload_validate $route_count
- check_err_fail $should_fail $? "Offload of $route_count routes"
+ check_err_fail $should_fail $? "Offload routes: Expected $route_count, got $delta."
if [[ $RET -ne 0 ]] || [[ $should_fail -eq 1 ]]; then
return
fi
- tc filter add dev $h2 ingress protocol ip pref 1 flower \
- skip_sw dst_ip 193.0.0.0/8 action drop
-
- for i in {0..255}
- do
- for j in {0..255}
- do
- for k in {0..255}
- do
- if [[ $count -eq $route_count ]]; then
- break 3
- fi
-
- $MZ $h1 -c 1 -p 64 -a $h1mac -b $rp1mac \
- -A 192.0.1.1 -B 193.${i}.${j}.${k} \
- -t ip -q
- ((count++))
- done
- done
- done
-
- tc_check_packets "dev $h2 ingress" 1 $route_count
- check_err $? "Offload mismatch"
-
- tc filter del dev $h2 ingress protocol ip pref 1 flower \
- skip_sw dst_ip 193.0.0.0/8 action drop
-
router_routes_destroy
}
diff --git a/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh b/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh
index 5c39e5f6a480..f4031002d5e9 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh
@@ -32,6 +32,7 @@ ALL_TESTS="
devlink_reload_test
"
NUM_NETIFS=2
+: ${TIMEOUT:=20000} # ms
source $lib_dir/lib.sh
source $lib_dir/devlink_lib.sh
@@ -360,20 +361,24 @@ vlan_rif_refcount_test()
ip link add link br0 name br0.10 up type vlan id 10
ip -6 address add 2001:db8:1::1/64 dev br0.10
- ip -6 route get fibmatch 2001:db8:1::2 dev br0.10 | grep -q offload
+ busywait "$TIMEOUT" wait_for_offload \
+ ip -6 route get fibmatch 2001:db8:1::2 dev br0.10
check_err $? "vlan rif was not created before adding port to vlan"
bridge vlan add vid 10 dev $swp1
- ip -6 route get fibmatch 2001:db8:1::2 dev br0.10 | grep -q offload
+ busywait "$TIMEOUT" wait_for_offload \
+ ip -6 route get fibmatch 2001:db8:1::2 dev br0.10
check_err $? "vlan rif was destroyed after adding port to vlan"
bridge vlan del vid 10 dev $swp1
- ip -6 route get fibmatch 2001:db8:1::2 dev br0.10 | grep -q offload
+ busywait "$TIMEOUT" wait_for_offload \
+ ip -6 route get fibmatch 2001:db8:1::2 dev br0.10
check_err $? "vlan rif was destroyed after removing port from vlan"
ip link set dev $swp1 nomaster
- ip -6 route get fibmatch 2001:db8:1::2 dev br0.10 | grep -q offload
- check_fail $? "vlan rif was not destroyed after unlinking port from bridge"
+ busywait "$TIMEOUT" not wait_for_offload \
+ ip -6 route get fibmatch 2001:db8:1::2 dev br0.10
+ check_err $? "vlan rif was not destroyed after unlinking port from bridge"
log_test "vlan rif refcount"
@@ -401,22 +406,28 @@ subport_rif_refcount_test()
ip -6 address add 2001:db8:1::1/64 dev bond1
ip -6 address add 2001:db8:2::1/64 dev bond1.10
- ip -6 route get fibmatch 2001:db8:1::2 dev bond1 | grep -q offload
+ busywait "$TIMEOUT" wait_for_offload \
+ ip -6 route get fibmatch 2001:db8:1::2 dev bond1
check_err $? "subport rif was not created on lag device"
- ip -6 route get fibmatch 2001:db8:2::2 dev bond1.10 | grep -q offload
+ busywait "$TIMEOUT" wait_for_offload \
+ ip -6 route get fibmatch 2001:db8:2::2 dev bond1.10
check_err $? "subport rif was not created on vlan device"
ip link set dev $swp1 nomaster
- ip -6 route get fibmatch 2001:db8:1::2 dev bond1 | grep -q offload
+ busywait "$TIMEOUT" wait_for_offload \
+ ip -6 route get fibmatch 2001:db8:1::2 dev bond1
check_err $? "subport rif of lag device was destroyed when should not"
- ip -6 route get fibmatch 2001:db8:2::2 dev bond1.10 | grep -q offload
+ busywait "$TIMEOUT" wait_for_offload \
+ ip -6 route get fibmatch 2001:db8:2::2 dev bond1.10
check_err $? "subport rif of vlan device was destroyed when should not"
ip link set dev $swp2 nomaster
- ip -6 route get fibmatch 2001:db8:1::2 dev bond1 | grep -q offload
- check_fail $? "subport rif of lag device was not destroyed when should"
- ip -6 route get fibmatch 2001:db8:2::2 dev bond1.10 | grep -q offload
- check_fail $? "subport rif of vlan device was not destroyed when should"
+ busywait "$TIMEOUT" not wait_for_offload \
+ ip -6 route get fibmatch 2001:db8:1::2 dev bond1
+ check_err $? "subport rif of lag device was not destroyed when should"
+ busywait "$TIMEOUT" not wait_for_offload \
+ ip -6 route get fibmatch 2001:db8:2::2 dev bond1.10
+ check_err $? "subport rif of vlan device was not destroyed when should"
log_test "subport rif refcount"
@@ -575,7 +586,8 @@ bridge_extern_learn_test()
bridge fdb add de:ad:be:ef:13:37 dev $swp1 master extern_learn
- bridge fdb show brport $swp1 | grep de:ad:be:ef:13:37 | grep -q offload
+ busywait "$TIMEOUT" wait_for_offload \
+ bridge fdb show brport $swp1 de:ad:be:ef:13:37
check_err $? "fdb entry not marked as offloaded when should"
log_test "externally learned fdb entry"
@@ -595,9 +607,11 @@ neigh_offload_test()
ip -6 neigh add 2001:db8:1::2 lladdr de:ad:be:ef:13:37 nud perm \
dev $swp1
- ip -4 neigh show dev $swp1 | grep 192.0.2.2 | grep -q offload
+ busywait "$TIMEOUT" wait_for_offload \
+ ip -4 neigh show dev $swp1 192.0.2.2
check_err $? "ipv4 neigh entry not marked as offloaded when should"
- ip -6 neigh show dev $swp1 | grep 2001:db8:1::2 | grep -q offload
+ busywait "$TIMEOUT" wait_for_offload \
+ ip -6 neigh show dev $swp1 2001:db8:1::2
check_err $? "ipv6 neigh entry not marked as offloaded when should"
log_test "neighbour offload indication"
@@ -623,25 +637,31 @@ nexthop_offload_test()
ip -6 route add 2001:db8:2::/64 vrf v$swp1 \
nexthop via 2001:db8:1::2 dev $swp1
- ip -4 route show 198.51.100.0/24 vrf v$swp1 | grep -q offload
+ busywait "$TIMEOUT" wait_for_offload \
+ ip -4 route show 198.51.100.0/24 vrf v$swp1
check_err $? "ipv4 nexthop not marked as offloaded when should"
- ip -6 route show 2001:db8:2::/64 vrf v$swp1 | grep -q offload
+ busywait "$TIMEOUT" wait_for_offload \
+ ip -6 route show 2001:db8:2::/64 vrf v$swp1
check_err $? "ipv6 nexthop not marked as offloaded when should"
ip link set dev $swp2 down
sleep 1
- ip -4 route show 198.51.100.0/24 vrf v$swp1 | grep -q offload
- check_fail $? "ipv4 nexthop marked as offloaded when should not"
- ip -6 route show 2001:db8:2::/64 vrf v$swp1 | grep -q offload
- check_fail $? "ipv6 nexthop marked as offloaded when should not"
+ busywait "$TIMEOUT" not wait_for_offload \
+ ip -4 route show 198.51.100.0/24 vrf v$swp1
+ check_err $? "ipv4 nexthop marked as offloaded when should not"
+ busywait "$TIMEOUT" not wait_for_offload \
+ ip -6 route show 2001:db8:2::/64 vrf v$swp1
+ check_err $? "ipv6 nexthop marked as offloaded when should not"
ip link set dev $swp2 up
setup_wait
- ip -4 route show 198.51.100.0/24 vrf v$swp1 | grep -q offload
+ busywait "$TIMEOUT" wait_for_offload \
+ ip -4 route show 198.51.100.0/24 vrf v$swp1
check_err $? "ipv4 nexthop not marked as offloaded after neigh add"
- ip -6 route show 2001:db8:2::/64 vrf v$swp1 | grep -q offload
+ busywait "$TIMEOUT" wait_for_offload \
+ ip -6 route show 2001:db8:2::/64 vrf v$swp1
check_err $? "ipv6 nexthop not marked as offloaded after neigh add"
log_test "nexthop offload indication"
diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_ets.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_ets.sh
index c9fc4d4885c1..94c37124a840 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/sch_ets.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/sch_ets.sh
@@ -56,11 +56,19 @@ switch_destroy()
}
# Callback from sch_ets_tests.sh
-get_stats()
+collect_stats()
{
- local band=$1; shift
+ local -a streams=("$@")
+ local stream
- ethtool_stats_get "$h2" rx_octets_prio_$band
+ # Wait for qdisc counter update so that we don't get it mid-way through.
+ busywait_for_counter 1000 +1 \
+ qdisc_parent_stats_get $swp2 10:$((${streams[0]} + 1)) .bytes \
+ > /dev/null
+
+ for stream in ${streams[@]}; do
+ qdisc_parent_stats_get $swp2 10:$((stream + 1)) .bytes
+ done
}
bail_on_lldpad
diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh
new file mode 100644
index 000000000000..0d347d48c112
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh
@@ -0,0 +1,533 @@
+# SPDX-License-Identifier: GPL-2.0
+
+# This test sends a >1Gbps stream of traffic from H1, to the switch, which
+# forwards it to a 1Gbps port. This 1Gbps stream is then looped back to the
+# switch and forwarded to the port under test $swp3, which is also 1Gbps.
+#
+# This way, $swp3 should be 100% filled with traffic without any of it spilling
+# to the backlog. Any extra packets sent should almost 1:1 go to backlog. That
+# is what H2 is used for--it sends the extra traffic to create backlog.
+#
+# A RED Qdisc is installed on $swp3. The configuration is such that the minimum
+# and maximum size are 1 byte apart, so there is a very clear border under which
+# no marking or dropping takes place, and above which everything is marked or
+# dropped.
+#
+# The test uses the buffer build-up behavior to test the installed RED.
+#
+# In order to test WRED, $swp3 actually contains RED under PRIO, with two
+# different configurations. Traffic is prioritized using 802.1p and relies on
+# the implicit mlxsw configuration, where packet priority is taken 1:1 from the
+# 802.1p marking.
+#
+# +--------------------------+ +--------------------------+
+# | H1 | | H2 |
+# | + $h1.10 | | + $h2.10 |
+# | | 192.0.2.1/28 | | | 192.0.2.2/28 |
+# | | | | | |
+# | | $h1.11 + | | | $h2.11 + |
+# | | 192.0.2.17/28 | | | | 192.0.2.18/28 | |
+# | | | | | | | |
+# | \______ ______/ | | \______ ______/ |
+# | \ / | | \ / |
+# | + $h1 | | + $h2 |
+# +-------------|------------+ +-------------|------------+
+# | >1Gbps |
+# +-------------|------------------------------------------------|------------+
+# | SW + $swp1 + $swp2 |
+# | _______/ \___________ ___________/ \_______ |
+# | / \ / \ |
+# | +-|-----------------+ | +-|-----------------+ | |
+# | | + $swp1.10 | | | + $swp2.10 | | |
+# | | | | .-------------+ $swp5.10 | | |
+# | | BR1_10 | | | | | | |
+# | | | | | | BR2_10 | | |
+# | | + $swp2.10 | | | | | | |
+# | +-|-----------------+ | | | + $swp3.10 | | |
+# | | | | +-|-----------------+ | |
+# | | +-----------------|-+ | | +-----------------|-+ |
+# | | | $swp1.11 + | | | | $swp2.11 + | |
+# | | | | | .-----------------+ $swp5.11 | |
+# | | | BR1_11 | | | | | | |
+# | | | | | | | | BR2_11 | |
+# | | | $swp2.11 + | | | | | | |
+# | | +-----------------|-+ | | | | $swp3.11 + | |
+# | | | | | | +-----------------|-+ |
+# | \_______ ___________/ | | \___________ _______/ |
+# | \ / \ / \ / |
+# | + $swp4 + $swp5 + $swp3 |
+# +-------------|----------------------|-------------------------|------------+
+# | | | 1Gbps
+# \________1Gbps_________/ |
+# +----------------------------|------------+
+# | H3 + $h3 |
+# | _____________________/ \_______ |
+# | / \ |
+# | | | |
+# | + $h3.10 $h3.11 + |
+# | 192.0.2.3/28 192.0.2.19/28 |
+# +-----------------------------------------+
+
+NUM_NETIFS=8
+CHECK_TC="yes"
+lib_dir=$(dirname $0)/../../../net/forwarding
+source $lib_dir/lib.sh
+source $lib_dir/devlink_lib.sh
+source qos_lib.sh
+
+ipaddr()
+{
+ local host=$1; shift
+ local vlan=$1; shift
+
+ echo 192.0.2.$((16 * (vlan - 10) + host))
+}
+
+host_create()
+{
+ local dev=$1; shift
+ local host=$1; shift
+
+ simple_if_init $dev
+ mtu_set $dev 10000
+
+ vlan_create $dev 10 v$dev $(ipaddr $host 10)/28
+ ip link set dev $dev.10 type vlan egress 0:0
+
+ vlan_create $dev 11 v$dev $(ipaddr $host 11)/28
+ ip link set dev $dev.11 type vlan egress 0:1
+}
+
+host_destroy()
+{
+ local dev=$1; shift
+
+ vlan_destroy $dev 11
+ vlan_destroy $dev 10
+ mtu_restore $dev
+ simple_if_fini $dev
+}
+
+h1_create()
+{
+ host_create $h1 1
+}
+
+h1_destroy()
+{
+ host_destroy $h1
+}
+
+h2_create()
+{
+ host_create $h2 2
+
+ # Some of the tests in this suite use multicast traffic. As this traffic
+ # enters BR2_10 resp. BR2_11, it is flooded to all other ports. Thus
+ # e.g. traffic ingressing through $swp2 is flooded to $swp3 (the
+ # intended destination) and $swp5 (which is intended as ingress for
+ # another stream of traffic).
+ #
+ # This is generally not a problem, but if the $swp5 throughput is lower
+ # than $swp2 throughput, there will be a build-up at $swp5. That may
+ # cause packets to fail to queue up at $swp3 due to shared buffer
+ # quotas, and the test to spuriously fail.
+ #
+ # Prevent this by setting the speed of $h2 to 1Gbps.
+
+ ethtool -s $h2 speed 1000 autoneg off
+}
+
+h2_destroy()
+{
+ ethtool -s $h2 autoneg on
+ host_destroy $h2
+}
+
+h3_create()
+{
+ host_create $h3 3
+ ethtool -s $h3 speed 1000 autoneg off
+}
+
+h3_destroy()
+{
+ ethtool -s $h3 autoneg on
+ host_destroy $h3
+}
+
+switch_create()
+{
+ local intf
+ local vlan
+
+ ip link add dev br1_10 type bridge
+ ip link add dev br1_11 type bridge
+
+ ip link add dev br2_10 type bridge
+ ip link add dev br2_11 type bridge
+
+ for intf in $swp1 $swp2 $swp3 $swp4 $swp5; do
+ ip link set dev $intf up
+ mtu_set $intf 10000
+ done
+
+ for intf in $swp1 $swp4; do
+ for vlan in 10 11; do
+ vlan_create $intf $vlan
+ ip link set dev $intf.$vlan master br1_$vlan
+ ip link set dev $intf.$vlan up
+ done
+ done
+
+ for intf in $swp2 $swp3 $swp5; do
+ for vlan in 10 11; do
+ vlan_create $intf $vlan
+ ip link set dev $intf.$vlan master br2_$vlan
+ ip link set dev $intf.$vlan up
+ done
+ done
+
+ ip link set dev $swp4.10 type vlan egress 0:0
+ ip link set dev $swp4.11 type vlan egress 0:1
+ for intf in $swp1 $swp2 $swp5; do
+ for vlan in 10 11; do
+ ip link set dev $intf.$vlan type vlan ingress 0:0 1:1
+ done
+ done
+
+ for intf in $swp2 $swp3 $swp4 $swp5; do
+ ethtool -s $intf speed 1000 autoneg off
+ done
+
+ ip link set dev br1_10 up
+ ip link set dev br1_11 up
+ ip link set dev br2_10 up
+ ip link set dev br2_11 up
+
+ local size=$(devlink_pool_size_thtype 0 | cut -d' ' -f 1)
+ devlink_port_pool_th_set $swp3 8 $size
+}
+
+switch_destroy()
+{
+ local intf
+ local vlan
+
+ devlink_port_pool_th_restore $swp3 8
+
+ tc qdisc del dev $swp3 root 2>/dev/null
+
+ ip link set dev br2_11 down
+ ip link set dev br2_10 down
+ ip link set dev br1_11 down
+ ip link set dev br1_10 down
+
+ for intf in $swp5 $swp4 $swp3 $swp2; do
+ ethtool -s $intf autoneg on
+ done
+
+ for intf in $swp5 $swp3 $swp2 $swp4 $swp1; do
+ for vlan in 11 10; do
+ ip link set dev $intf.$vlan down
+ ip link set dev $intf.$vlan nomaster
+ vlan_destroy $intf $vlan
+ done
+
+ mtu_restore $intf
+ ip link set dev $intf down
+ done
+
+ ip link del dev br2_11
+ ip link del dev br2_10
+ ip link del dev br1_11
+ ip link del dev br1_10
+}
+
+setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ swp1=${NETIFS[p2]}
+
+ swp2=${NETIFS[p3]}
+ h2=${NETIFS[p4]}
+
+ swp3=${NETIFS[p5]}
+ h3=${NETIFS[p6]}
+
+ swp4=${NETIFS[p7]}
+ swp5=${NETIFS[p8]}
+
+ h3_mac=$(mac_get $h3)
+
+ vrf_prepare
+
+ h1_create
+ h2_create
+ h3_create
+ switch_create
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ switch_destroy
+ h3_destroy
+ h2_destroy
+ h1_destroy
+
+ vrf_cleanup
+}
+
+ping_ipv4()
+{
+ ping_test $h1.10 $(ipaddr 3 10) " from host 1, vlan 10"
+ ping_test $h1.11 $(ipaddr 3 11) " from host 1, vlan 11"
+ ping_test $h2.10 $(ipaddr 3 10) " from host 2, vlan 10"
+ ping_test $h2.11 $(ipaddr 3 11) " from host 2, vlan 11"
+}
+
+get_tc()
+{
+ local vlan=$1; shift
+
+ echo $((vlan - 10))
+}
+
+get_qdisc_handle()
+{
+ local vlan=$1; shift
+
+ local tc=$(get_tc $vlan)
+ local band=$((8 - tc))
+
+ # Handle is 107: for TC1, 108: for TC0.
+ echo "10$band:"
+}
+
+get_qdisc_backlog()
+{
+ local vlan=$1; shift
+
+ qdisc_stats_get $swp3 $(get_qdisc_handle $vlan) .backlog
+}
+
+get_mc_transmit_queue()
+{
+ local vlan=$1; shift
+
+ local tc=$(($(get_tc $vlan) + 8))
+ ethtool_stats_get $swp3 tc_transmit_queue_tc_$tc
+}
+
+get_nmarked()
+{
+ local vlan=$1; shift
+
+ ethtool_stats_get $swp3 ecn_marked
+}
+
+get_qdisc_npackets()
+{
+ local vlan=$1; shift
+
+ busywait_for_counter 1100 +1 \
+ qdisc_stats_get $swp3 $(get_qdisc_handle $vlan) .packets
+}
+
+# This sends traffic in an attempt to build a backlog of $size. Returns 0 on
+# success. After 10 failed attempts it bails out and returns 1. It dumps the
+# backlog size to stdout.
+build_backlog()
+{
+ local vlan=$1; shift
+ local size=$1; shift
+ local proto=$1; shift
+
+ local tc=$((vlan - 10))
+ local band=$((8 - tc))
+ local cur=-1
+ local i=0
+
+ while :; do
+ local cur=$(busywait 1100 until_counter_is "> $cur" \
+ get_qdisc_backlog $vlan)
+ local diff=$((size - cur))
+ local pkts=$(((diff + 7999) / 8000))
+
+ if ((cur >= size)); then
+ echo $cur
+ return 0
+ elif ((i++ > 10)); then
+ echo $cur
+ return 1
+ fi
+
+ $MZ $h2.$vlan -p 8000 -a own -b $h3_mac \
+ -A $(ipaddr 2 $vlan) -B $(ipaddr 3 $vlan) \
+ -t $proto -q -c $pkts "$@"
+ done
+}
+
+check_marking()
+{
+ local vlan=$1; shift
+ local cond=$1; shift
+
+ local npackets_0=$(get_qdisc_npackets $vlan)
+ local nmarked_0=$(get_nmarked $vlan)
+ sleep 5
+ local npackets_1=$(get_qdisc_npackets $vlan)
+ local nmarked_1=$(get_nmarked $vlan)
+
+ local nmarked_d=$((nmarked_1 - nmarked_0))
+ local npackets_d=$((npackets_1 - npackets_0))
+ local pct=$((100 * nmarked_d / npackets_d))
+
+ echo $pct
+ ((pct $cond))
+}
+
+ecn_test_common()
+{
+ local name=$1; shift
+ local vlan=$1; shift
+ local limit=$1; shift
+ local backlog
+ local pct
+
+ # Build the below-the-limit backlog using UDP. We could use TCP just
+ # fine, but this way we get a proof that UDP is accepted when queue
+ # length is below the limit. The main stream is using TCP, and if the
+ # limit is misconfigured, we would see this traffic being ECN marked.
+ RET=0
+ backlog=$(build_backlog $vlan $((2 * limit / 3)) udp)
+ check_err $? "Could not build the requested backlog"
+ pct=$(check_marking $vlan "== 0")
+ check_err $? "backlog $backlog / $limit Got $pct% marked packets, expected == 0."
+ log_test "TC $((vlan - 10)): $name backlog < limit"
+
+ # Now push TCP, because non-TCP traffic would be early-dropped after the
+ # backlog crosses the limit, and we want to make sure that the backlog
+ # is above the limit.
+ RET=0
+ backlog=$(build_backlog $vlan $((3 * limit / 2)) tcp tos=0x01)
+ check_err $? "Could not build the requested backlog"
+ pct=$(check_marking $vlan ">= 95")
+ check_err $? "backlog $backlog / $limit Got $pct% marked packets, expected >= 95."
+ log_test "TC $((vlan - 10)): $name backlog > limit"
+}
+
+do_ecn_test()
+{
+ local vlan=$1; shift
+ local limit=$1; shift
+ local name=ECN
+
+ start_tcp_traffic $h1.$vlan $(ipaddr 1 $vlan) $(ipaddr 3 $vlan) \
+ $h3_mac tos=0x01
+ sleep 1
+
+ ecn_test_common "$name" $vlan $limit
+
+ # Up there we saw that UDP gets accepted when backlog is below the
+ # limit. Now that it is above, it should all get dropped, and backlog
+ # building should fail.
+ RET=0
+ build_backlog $vlan $((2 * limit)) udp >/dev/null
+ check_fail $? "UDP traffic went into backlog instead of being early-dropped"
+ log_test "TC $((vlan - 10)): $name backlog > limit: UDP early-dropped"
+
+ stop_traffic
+ sleep 1
+}
+
+do_ecn_nodrop_test()
+{
+ local vlan=$1; shift
+ local limit=$1; shift
+ local name="ECN nodrop"
+
+ start_tcp_traffic $h1.$vlan $(ipaddr 1 $vlan) $(ipaddr 3 $vlan) \
+ $h3_mac tos=0x01
+ sleep 1
+
+ ecn_test_common "$name" $vlan $limit
+
+ # Up there we saw that UDP gets accepted when backlog is below the
+ # limit. Now that it is above, in nodrop mode, make sure it goes to
+ # backlog as well.
+ RET=0
+ build_backlog $vlan $((2 * limit)) udp >/dev/null
+ check_err $? "UDP traffic was early-dropped instead of getting into backlog"
+ log_test "TC $((vlan - 10)): $name backlog > limit: UDP not dropped"
+
+ stop_traffic
+ sleep 1
+}
+
+do_red_test()
+{
+ local vlan=$1; shift
+ local limit=$1; shift
+ local backlog
+ local pct
+
+ # Use ECN-capable TCP to verify there's no marking even though the queue
+ # is above limit.
+ start_tcp_traffic $h1.$vlan $(ipaddr 1 $vlan) $(ipaddr 3 $vlan) \
+ $h3_mac tos=0x01
+
+ # Pushing below the queue limit should work.
+ RET=0
+ backlog=$(build_backlog $vlan $((2 * limit / 3)) tcp tos=0x01)
+ check_err $? "Could not build the requested backlog"
+ pct=$(check_marking $vlan "== 0")
+ check_err $? "backlog $backlog / $limit Got $pct% marked packets, expected == 0."
+ log_test "TC $((vlan - 10)): RED backlog < limit"
+
+ # Pushing above should not.
+ RET=0
+ backlog=$(build_backlog $vlan $((3 * limit / 2)) tcp tos=0x01)
+ check_fail $? "Traffic went into backlog instead of being early-dropped"
+ pct=$(check_marking $vlan "== 0")
+ check_err $? "backlog $backlog / $limit Got $pct% marked packets, expected == 0."
+ local diff=$((limit - backlog))
+ pct=$((100 * diff / limit))
+ ((0 <= pct && pct <= 5))
+ check_err $? "backlog $backlog / $limit expected <= 5% distance"
+ log_test "TC $((vlan - 10)): RED backlog > limit"
+
+ stop_traffic
+ sleep 1
+}
+
+do_mc_backlog_test()
+{
+ local vlan=$1; shift
+ local limit=$1; shift
+ local backlog
+ local pct
+
+ RET=0
+
+ start_tcp_traffic $h1.$vlan $(ipaddr 1 $vlan) $(ipaddr 3 $vlan) bc
+ start_tcp_traffic $h2.$vlan $(ipaddr 2 $vlan) $(ipaddr 3 $vlan) bc
+
+ qbl=$(busywait 5000 until_counter_is ">= 500000" \
+ get_qdisc_backlog $vlan)
+ check_err $? "Could not build MC backlog"
+
+ # Verify that we actually see the backlog on BUM TC. Do a busywait as
+ # well, performance blips might cause false fail.
+ local ebl
+ ebl=$(busywait 5000 until_counter_is ">= 500000" \
+ get_mc_transmit_queue $vlan)
+ check_err $? "MC backlog reported by qdisc not visible in ethtool"
+
+ stop_traffic
+ stop_traffic
+
+ log_test "TC $((vlan - 10)): Qdisc reports MC backlog"
+}
diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh
new file mode 100755
index 000000000000..1c36c576613b
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh
@@ -0,0 +1,94 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ALL_TESTS="
+ ping_ipv4
+ ecn_test
+ ecn_nodrop_test
+ red_test
+ mc_backlog_test
+"
+: ${QDISC:=ets}
+source sch_red_core.sh
+
+# do_ecn_test first build 2/3 of the requested backlog and expects no marking,
+# and then builds 3/2 of it and does expect marking. The values of $BACKLOG1 and
+# $BACKLOG2 are far enough not to overlap, so that we can assume that if we do
+# see (do not see) marking, it is actually due to the configuration of that one
+# TC, and not due to configuration of the other TC leaking over.
+BACKLOG1=200000
+BACKLOG2=500000
+
+install_qdisc()
+{
+ local -a args=("$@")
+
+ tc qdisc add dev $swp3 root handle 10: $QDISC \
+ bands 8 priomap 7 6 5 4 3 2 1 0
+ tc qdisc add dev $swp3 parent 10:8 handle 108: red \
+ limit 1000000 min $BACKLOG1 max $((BACKLOG1 + 1)) \
+ probability 1.0 avpkt 8000 burst 38 "${args[@]}"
+ tc qdisc add dev $swp3 parent 10:7 handle 107: red \
+ limit 1000000 min $BACKLOG2 max $((BACKLOG2 + 1)) \
+ probability 1.0 avpkt 8000 burst 63 "${args[@]}"
+ sleep 1
+}
+
+uninstall_qdisc()
+{
+ tc qdisc del dev $swp3 parent 10:7
+ tc qdisc del dev $swp3 parent 10:8
+ tc qdisc del dev $swp3 root
+}
+
+ecn_test()
+{
+ install_qdisc ecn
+
+ do_ecn_test 10 $BACKLOG1
+ do_ecn_test 11 $BACKLOG2
+
+ uninstall_qdisc
+}
+
+ecn_nodrop_test()
+{
+ install_qdisc ecn nodrop
+
+ do_ecn_nodrop_test 10 $BACKLOG1
+ do_ecn_nodrop_test 11 $BACKLOG2
+
+ uninstall_qdisc
+}
+
+red_test()
+{
+ install_qdisc
+
+ do_red_test 10 $BACKLOG1
+ do_red_test 11 $BACKLOG2
+
+ uninstall_qdisc
+}
+
+mc_backlog_test()
+{
+ install_qdisc
+
+ # Note that the backlog numbers here do not correspond to RED
+ # configuration, but are arbitrary.
+ do_mc_backlog_test 10 $BACKLOG1
+ do_mc_backlog_test 11 $BACKLOG2
+
+ uninstall_qdisc
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+bail_on_lldpad
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_prio.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_prio.sh
new file mode 100755
index 000000000000..76820a0e9a1b
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_prio.sh
@@ -0,0 +1,5 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+QDISC=prio
+source sch_red_ets.sh
diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_root.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_root.sh
new file mode 100755
index 000000000000..558667ea11ec
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_root.sh
@@ -0,0 +1,68 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ALL_TESTS="
+ ping_ipv4
+ ecn_test
+ ecn_nodrop_test
+ red_test
+ mc_backlog_test
+"
+source sch_red_core.sh
+
+BACKLOG=300000
+
+install_qdisc()
+{
+ local -a args=("$@")
+
+ tc qdisc add dev $swp3 root handle 108: red \
+ limit 1000000 min $BACKLOG max $((BACKLOG + 1)) \
+ probability 1.0 avpkt 8000 burst 38 "${args[@]}"
+ sleep 1
+}
+
+uninstall_qdisc()
+{
+ tc qdisc del dev $swp3 root
+}
+
+ecn_test()
+{
+ install_qdisc ecn
+ do_ecn_test 10 $BACKLOG
+ uninstall_qdisc
+}
+
+ecn_nodrop_test()
+{
+ install_qdisc ecn nodrop
+ do_ecn_nodrop_test 10 $BACKLOG
+ uninstall_qdisc
+}
+
+red_test()
+{
+ install_qdisc
+ do_red_test 10 $BACKLOG
+ uninstall_qdisc
+}
+
+mc_backlog_test()
+{
+ install_qdisc
+ # Note that the backlog value here does not correspond to RED
+ # configuration, but is arbitrary.
+ do_mc_backlog_test 10 $BACKLOG
+ uninstall_qdisc
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+bail_on_lldpad
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer.sh b/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer.sh
new file mode 100755
index 000000000000..7d9e73a43a49
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer.sh
@@ -0,0 +1,222 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ALL_TESTS="
+ port_pool_test
+ port_tc_ip_test
+ port_tc_arp_test
+"
+
+NUM_NETIFS=2
+source ../../../net/forwarding/lib.sh
+source ../../../net/forwarding/devlink_lib.sh
+source mlxsw_lib.sh
+
+SB_POOL_ING=0
+SB_POOL_EGR_CPU=10
+
+SB_ITC_CPU_IP=2
+SB_ITC_CPU_ARP=2
+SB_ITC=0
+
+h1_create()
+{
+ simple_if_init $h1 192.0.1.1/24
+}
+
+h1_destroy()
+{
+ simple_if_fini $h1 192.0.1.1/24
+}
+
+h2_create()
+{
+ simple_if_init $h2 192.0.1.2/24
+}
+
+h2_destroy()
+{
+ simple_if_fini $h2 192.0.1.2/24
+}
+
+sb_occ_pool_check()
+{
+ local dl_port=$1; shift
+ local pool=$1; shift
+ local exp_max_occ=$1
+ local max_occ
+ local err=0
+
+ max_occ=$(devlink sb -j occupancy show $dl_port \
+ | jq -e ".[][][\"pool\"][\"$pool\"][\"max\"]")
+
+ if [[ "$max_occ" -ne "$exp_max_occ" ]]; then
+ err=1
+ fi
+
+ echo $max_occ
+ return $err
+}
+
+sb_occ_itc_check()
+{
+ local dl_port=$1; shift
+ local itc=$1; shift
+ local exp_max_occ=$1
+ local max_occ
+ local err=0
+
+ max_occ=$(devlink sb -j occupancy show $dl_port \
+ | jq -e ".[][][\"itc\"][\"$itc\"][\"max\"]")
+
+ if [[ "$max_occ" -ne "$exp_max_occ" ]]; then
+ err=1
+ fi
+
+ echo $max_occ
+ return $err
+}
+
+sb_occ_etc_check()
+{
+ local dl_port=$1; shift
+ local etc=$1; shift
+ local exp_max_occ=$1; shift
+ local max_occ
+ local err=0
+
+ max_occ=$(devlink sb -j occupancy show $dl_port \
+ | jq -e ".[][][\"etc\"][\"$etc\"][\"max\"]")
+
+ if [[ "$max_occ" -ne "$exp_max_occ" ]]; then
+ err=1
+ fi
+
+ echo $max_occ
+ return $err
+}
+
+port_pool_test()
+{
+ local exp_max_occ=288
+ local max_occ
+
+ devlink sb occupancy clearmax $DEVLINK_DEV
+
+ $MZ $h1 -c 1 -p 160 -a $h1mac -b $h2mac -A 192.0.1.1 -B 192.0.1.2 \
+ -t ip -q
+
+ devlink sb occupancy snapshot $DEVLINK_DEV
+
+ RET=0
+ max_occ=$(sb_occ_pool_check $dl_port1 $SB_POOL_ING $exp_max_occ)
+ check_err $? "Expected iPool($SB_POOL_ING) max occupancy to be $exp_max_occ, but got $max_occ"
+ log_test "physical port's($h1) ingress pool"
+
+ RET=0
+ max_occ=$(sb_occ_pool_check $dl_port2 $SB_POOL_ING $exp_max_occ)
+ check_err $? "Expected iPool($SB_POOL_ING) max occupancy to be $exp_max_occ, but got $max_occ"
+ log_test "physical port's($h2) ingress pool"
+
+ RET=0
+ max_occ=$(sb_occ_pool_check $cpu_dl_port $SB_POOL_EGR_CPU $exp_max_occ)
+ check_err $? "Expected ePool($SB_POOL_EGR_CPU) max occupancy to be $exp_max_occ, but got $max_occ"
+ log_test "CPU port's egress pool"
+}
+
+port_tc_ip_test()
+{
+ local exp_max_occ=288
+ local max_occ
+
+ devlink sb occupancy clearmax $DEVLINK_DEV
+
+ $MZ $h1 -c 1 -p 160 -a $h1mac -b $h2mac -A 192.0.1.1 -B 192.0.1.2 \
+ -t ip -q
+
+ devlink sb occupancy snapshot $DEVLINK_DEV
+
+ RET=0
+ max_occ=$(sb_occ_itc_check $dl_port2 $SB_ITC $exp_max_occ)
+ check_err $? "Expected ingress TC($SB_ITC) max occupancy to be $exp_max_occ, but got $max_occ"
+ log_test "physical port's($h1) ingress TC - IP packet"
+
+ RET=0
+ max_occ=$(sb_occ_itc_check $dl_port2 $SB_ITC $exp_max_occ)
+ check_err $? "Expected ingress TC($SB_ITC) max occupancy to be $exp_max_occ, but got $max_occ"
+ log_test "physical port's($h2) ingress TC - IP packet"
+
+ RET=0
+ max_occ=$(sb_occ_etc_check $cpu_dl_port $SB_ITC_CPU_IP $exp_max_occ)
+ check_err $? "Expected egress TC($SB_ITC_CPU_IP) max occupancy to be $exp_max_occ, but got $max_occ"
+ log_test "CPU port's egress TC - IP packet"
+}
+
+port_tc_arp_test()
+{
+ local exp_max_occ=96
+ local max_occ
+
+ if [[ $MLXSW_CHIP != "mlxsw_spectrum" ]]; then
+ exp_max_occ=144
+ fi
+
+ devlink sb occupancy clearmax $DEVLINK_DEV
+
+ $MZ $h1 -c 1 -p 160 -a $h1mac -A 192.0.1.1 -t arp -q
+
+ devlink sb occupancy snapshot $DEVLINK_DEV
+
+ RET=0
+ max_occ=$(sb_occ_itc_check $dl_port2 $SB_ITC $exp_max_occ)
+ check_err $? "Expected ingress TC($SB_ITC) max occupancy to be $exp_max_occ, but got $max_occ"
+ log_test "physical port's($h1) ingress TC - ARP packet"
+
+ RET=0
+ max_occ=$(sb_occ_itc_check $dl_port2 $SB_ITC $exp_max_occ)
+ check_err $? "Expected ingress TC($SB_ITC) max occupancy to be $exp_max_occ, but got $max_occ"
+ log_test "physical port's($h2) ingress TC - ARP packet"
+
+ RET=0
+ max_occ=$(sb_occ_etc_check $cpu_dl_port $SB_ITC_CPU_ARP $exp_max_occ)
+ check_err $? "Expected egress TC($SB_ITC_IP2ME) max occupancy to be $exp_max_occ, but got $max_occ"
+ log_test "CPU port's egress TC - ARP packet"
+}
+
+setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ h2=${NETIFS[p2]}
+
+ h1mac=$(mac_get $h1)
+ h2mac=$(mac_get $h2)
+
+ dl_port1=$(devlink_port_by_netdev $h1)
+ dl_port2=$(devlink_port_by_netdev $h2)
+
+ cpu_dl_port=$(devlink_cpu_port_get)
+
+ vrf_prepare
+
+ h1_create
+ h2_create
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ h2_destroy
+ h1_destroy
+
+ vrf_cleanup
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer_configuration.py b/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer_configuration.py
new file mode 100755
index 000000000000..0d4b9327c9b3
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer_configuration.py
@@ -0,0 +1,416 @@
+#!/usr/bin/python
+# SPDX-License-Identifier: GPL-2.0
+
+import subprocess
+import json as j
+import random
+
+
+class SkipTest(Exception):
+ pass
+
+
+class RandomValuePicker:
+ """
+ Class for storing shared buffer configuration. Can handle 3 different
+ objects, pool, tcbind and portpool. Provide an interface to get random
+ values for a specific object type as the follow:
+ 1. Pool:
+ - random size
+
+ 2. TcBind:
+ - random pool number
+ - random threshold
+
+ 3. PortPool:
+ - random threshold
+ """
+ def __init__(self, pools):
+ self._pools = []
+ for pool in pools:
+ self._pools.append(pool)
+
+ def _cell_size(self):
+ return self._pools[0]["cell_size"]
+
+ def _get_static_size(self, th):
+ # For threshold of 16, this works out to be about 12MB on Spectrum-1,
+ # and about 17MB on Spectrum-2.
+ return th * 8000 * self._cell_size()
+
+ def _get_size(self):
+ return self._get_static_size(16)
+
+ def _get_thtype(self):
+ return "static"
+
+ def _get_th(self, pool):
+ # Threshold value could be any integer between 3 to 16
+ th = random.randint(3, 16)
+ if pool["thtype"] == "dynamic":
+ return th
+ else:
+ return self._get_static_size(th)
+
+ def _get_pool(self, direction):
+ ing_pools = []
+ egr_pools = []
+ for pool in self._pools:
+ if pool["type"] == "ingress":
+ ing_pools.append(pool)
+ else:
+ egr_pools.append(pool)
+ if direction == "ingress":
+ arr = ing_pools
+ else:
+ arr = egr_pools
+ return arr[random.randint(0, len(arr) - 1)]
+
+ def get_value(self, objid):
+ if isinstance(objid, Pool):
+ if objid["pool"] in [4, 8, 9, 10]:
+ # The threshold type of pools 4, 8, 9 and 10 cannot be changed
+ raise SkipTest()
+ else:
+ return (self._get_size(), self._get_thtype())
+ if isinstance(objid, TcBind):
+ if objid["tc"] >= 8:
+ # Multicast TCs cannot be changed
+ raise SkipTest()
+ else:
+ pool = self._get_pool(objid["type"])
+ th = self._get_th(pool)
+ pool_n = pool["pool"]
+ return (pool_n, th)
+ if isinstance(objid, PortPool):
+ pool_n = objid["pool"]
+ pool = self._pools[pool_n]
+ assert pool["pool"] == pool_n
+ th = self._get_th(pool)
+ return (th,)
+
+
+class RecordValuePickerException(Exception):
+ pass
+
+
+class RecordValuePicker:
+ """
+ Class for storing shared buffer configuration. Can handle 2 different
+ objects, pool and tcbind. Provide an interface to get the stored values per
+ object type.
+ """
+ def __init__(self, objlist):
+ self._recs = []
+ for item in objlist:
+ self._recs.append({"objid": item, "value": item.var_tuple()})
+
+ def get_value(self, objid):
+ if isinstance(objid, Pool) and objid["pool"] in [4, 8, 9, 10]:
+ # The threshold type of pools 4, 8, 9 and 10 cannot be changed
+ raise SkipTest()
+ if isinstance(objid, TcBind) and objid["tc"] >= 8:
+ # Multicast TCs cannot be changed
+ raise SkipTest()
+ for rec in self._recs:
+ if rec["objid"].weak_eq(objid):
+ return rec["value"]
+ raise RecordValuePickerException()
+
+
+def run_cmd(cmd, json=False):
+ out = subprocess.check_output(cmd, shell=True)
+ if json:
+ return j.loads(out)
+ return out
+
+
+def run_json_cmd(cmd):
+ return run_cmd(cmd, json=True)
+
+
+def log_test(test_name, err_msg=None):
+ if err_msg:
+ print("\t%s" % err_msg)
+ print("TEST: %-80s [FAIL]" % test_name)
+ else:
+ print("TEST: %-80s [ OK ]" % test_name)
+
+
+class CommonItem(dict):
+ varitems = []
+
+ def var_tuple(self):
+ ret = []
+ self.varitems.sort()
+ for key in self.varitems:
+ ret.append(self[key])
+ return tuple(ret)
+
+ def weak_eq(self, other):
+ for key in self:
+ if key in self.varitems:
+ continue
+ if self[key] != other[key]:
+ return False
+ return True
+
+
+class CommonList(list):
+ def get_by(self, by_obj):
+ for item in self:
+ if item.weak_eq(by_obj):
+ return item
+ return None
+
+ def del_by(self, by_obj):
+ for item in self:
+ if item.weak_eq(by_obj):
+ self.remove(item)
+
+
+class Pool(CommonItem):
+ varitems = ["size", "thtype"]
+
+ def dl_set(self, dlname, size, thtype):
+ run_cmd("devlink sb pool set {} sb {} pool {} size {} thtype {}".format(dlname, self["sb"],
+ self["pool"],
+ size, thtype))
+
+
+class PoolList(CommonList):
+ pass
+
+
+def get_pools(dlname, direction=None):
+ d = run_json_cmd("devlink sb pool show -j")
+ pools = PoolList()
+ for pooldict in d["pool"][dlname]:
+ if not direction or direction == pooldict["type"]:
+ pools.append(Pool(pooldict))
+ return pools
+
+
+def do_check_pools(dlname, pools, vp):
+ for pool in pools:
+ pre_pools = get_pools(dlname)
+ try:
+ (size, thtype) = vp.get_value(pool)
+ except SkipTest:
+ continue
+ pool.dl_set(dlname, size, thtype)
+ post_pools = get_pools(dlname)
+ pool = post_pools.get_by(pool)
+
+ err_msg = None
+ if pool["size"] != size:
+ err_msg = "Incorrect pool size (got {}, expected {})".format(pool["size"], size)
+ if pool["thtype"] != thtype:
+ err_msg = "Incorrect pool threshold type (got {}, expected {})".format(pool["thtype"], thtype)
+
+ pre_pools.del_by(pool)
+ post_pools.del_by(pool)
+ if pre_pools != post_pools:
+ err_msg = "Other pool setup changed as well"
+ log_test("pool {} of sb {} set verification".format(pool["pool"],
+ pool["sb"]), err_msg)
+
+
+def check_pools(dlname, pools):
+ # Save defaults
+ record_vp = RecordValuePicker(pools)
+
+ # For each pool, set random size and static threshold type
+ do_check_pools(dlname, pools, RandomValuePicker(pools))
+
+ # Restore defaults
+ do_check_pools(dlname, pools, record_vp)
+
+
+class TcBind(CommonItem):
+ varitems = ["pool", "threshold"]
+
+ def __init__(self, port, d):
+ super(TcBind, self).__init__(d)
+ self["dlportname"] = port.name
+
+ def dl_set(self, pool, th):
+ run_cmd("devlink sb tc bind set {} sb {} tc {} type {} pool {} th {}".format(self["dlportname"],
+ self["sb"],
+ self["tc"],
+ self["type"],
+ pool, th))
+
+
+class TcBindList(CommonList):
+ pass
+
+
+def get_tcbinds(ports, verify_existence=False):
+ d = run_json_cmd("devlink sb tc bind show -j -n")
+ tcbinds = TcBindList()
+ for port in ports:
+ err_msg = None
+ if port.name not in d["tc_bind"] or len(d["tc_bind"][port.name]) == 0:
+ err_msg = "No tc bind for port"
+ else:
+ for tcbinddict in d["tc_bind"][port.name]:
+ tcbinds.append(TcBind(port, tcbinddict))
+ if verify_existence:
+ log_test("tc bind existence for port {} verification".format(port.name), err_msg)
+ return tcbinds
+
+
+def do_check_tcbind(ports, tcbinds, vp):
+ for tcbind in tcbinds:
+ pre_tcbinds = get_tcbinds(ports)
+ try:
+ (pool, th) = vp.get_value(tcbind)
+ except SkipTest:
+ continue
+ tcbind.dl_set(pool, th)
+ post_tcbinds = get_tcbinds(ports)
+ tcbind = post_tcbinds.get_by(tcbind)
+
+ err_msg = None
+ if tcbind["pool"] != pool:
+ err_msg = "Incorrect pool (got {}, expected {})".format(tcbind["pool"], pool)
+ if tcbind["threshold"] != th:
+ err_msg = "Incorrect threshold (got {}, expected {})".format(tcbind["threshold"], th)
+
+ pre_tcbinds.del_by(tcbind)
+ post_tcbinds.del_by(tcbind)
+ if pre_tcbinds != post_tcbinds:
+ err_msg = "Other tc bind setup changed as well"
+ log_test("tc bind {}-{} of sb {} set verification".format(tcbind["dlportname"],
+ tcbind["tc"],
+ tcbind["sb"]), err_msg)
+
+
+def check_tcbind(dlname, ports, pools):
+ tcbinds = get_tcbinds(ports, verify_existence=True)
+
+ # Save defaults
+ record_vp = RecordValuePicker(tcbinds)
+
+ # Bind each port and unicast TC (TCs < 8) to a random pool and a random
+ # threshold
+ do_check_tcbind(ports, tcbinds, RandomValuePicker(pools))
+
+ # Restore defaults
+ do_check_tcbind(ports, tcbinds, record_vp)
+
+
+class PortPool(CommonItem):
+ varitems = ["threshold"]
+
+ def __init__(self, port, d):
+ super(PortPool, self).__init__(d)
+ self["dlportname"] = port.name
+
+ def dl_set(self, th):
+ run_cmd("devlink sb port pool set {} sb {} pool {} th {}".format(self["dlportname"],
+ self["sb"],
+ self["pool"], th))
+
+
+class PortPoolList(CommonList):
+ pass
+
+
+def get_portpools(ports, verify_existence=False):
+ d = run_json_cmd("devlink sb port pool -j -n")
+ portpools = PortPoolList()
+ for port in ports:
+ err_msg = None
+ if port.name not in d["port_pool"] or len(d["port_pool"][port.name]) == 0:
+ err_msg = "No port pool for port"
+ else:
+ for portpooldict in d["port_pool"][port.name]:
+ portpools.append(PortPool(port, portpooldict))
+ if verify_existence:
+ log_test("port pool existence for port {} verification".format(port.name), err_msg)
+ return portpools
+
+
+def do_check_portpool(ports, portpools, vp):
+ for portpool in portpools:
+ pre_portpools = get_portpools(ports)
+ (th,) = vp.get_value(portpool)
+ portpool.dl_set(th)
+ post_portpools = get_portpools(ports)
+ portpool = post_portpools.get_by(portpool)
+
+ err_msg = None
+ if portpool["threshold"] != th:
+ err_msg = "Incorrect threshold (got {}, expected {})".format(portpool["threshold"], th)
+
+ pre_portpools.del_by(portpool)
+ post_portpools.del_by(portpool)
+ if pre_portpools != post_portpools:
+ err_msg = "Other port pool setup changed as well"
+ log_test("port pool {}-{} of sb {} set verification".format(portpool["dlportname"],
+ portpool["pool"],
+ portpool["sb"]), err_msg)
+
+
+def check_portpool(dlname, ports, pools):
+ portpools = get_portpools(ports, verify_existence=True)
+
+ # Save defaults
+ record_vp = RecordValuePicker(portpools)
+
+ # For each port pool, set a random threshold
+ do_check_portpool(ports, portpools, RandomValuePicker(pools))
+
+ # Restore defaults
+ do_check_portpool(ports, portpools, record_vp)
+
+
+class Port:
+ def __init__(self, name):
+ self.name = name
+
+
+class PortList(list):
+ pass
+
+
+def get_ports(dlname):
+ d = run_json_cmd("devlink port show -j")
+ ports = PortList()
+ for name in d["port"]:
+ if name.find(dlname) == 0 and d["port"][name]["flavour"] == "physical":
+ ports.append(Port(name))
+ return ports
+
+
+def get_device():
+ devices_info = run_json_cmd("devlink -j dev info")["info"]
+ for d in devices_info:
+ if "mlxsw_spectrum" in devices_info[d]["driver"]:
+ return d
+ return None
+
+
+class UnavailableDevlinkNameException(Exception):
+ pass
+
+
+def test_sb_configuration():
+ # Use static seed
+ random.seed(0)
+
+ dlname = get_device()
+ if not dlname:
+ raise UnavailableDevlinkNameException()
+
+ ports = get_ports(dlname)
+ pools = get_pools(dlname)
+
+ check_pools(dlname, pools)
+ check_tcbind(dlname, ports, pools)
+ check_portpool(dlname, ports, pools)
+
+
+test_sb_configuration()
diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh
index 7b2acba82a49..fd583a171db7 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh
@@ -8,8 +8,9 @@ source $lib_dir/lib.sh
source $lib_dir/tc_common.sh
source $lib_dir/devlink_lib.sh
-if [ "$DEVLINK_VIDDID" != "15b3:cf6c" ]; then
- echo "SKIP: test is tailored for Mellanox Spectrum-2"
+if [[ "$DEVLINK_VIDDID" != "15b3:cf6c" && \
+ "$DEVLINK_VIDDID" != "15b3:cf70" ]]; then
+ echo "SKIP: test is tailored for Mellanox Spectrum-2 and Spectrum-3"
exit 1
fi
diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower_scale.sh
index a0795227216e..efd798a85931 100644
--- a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower_scale.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower_scale.sh
@@ -8,9 +8,9 @@ tc_flower_get_target()
# The driver associates a counter with each tc filter, which means the
# number of supported filters is bounded by the number of available
# counters.
- # Currently, the driver supports 12K (12,288) flow counters and six of
+ # Currently, the driver supports 30K (30,720) flow counters and six of
# these are used for multicast routing.
- local target=12282
+ local target=30714
if ((! should_fail)); then
echo $target
diff --git a/tools/testing/selftests/drivers/net/mlxsw/tc_action_hw_stats.sh b/tools/testing/selftests/drivers/net/mlxsw/tc_action_hw_stats.sh
new file mode 100755
index 000000000000..20ed98fe5a60
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/tc_action_hw_stats.sh
@@ -0,0 +1,130 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+
+ALL_TESTS="
+ default_hw_stats_test
+ immediate_hw_stats_test
+ delayed_hw_stats_test
+ disabled_hw_stats_test
+"
+NUM_NETIFS=2
+
+source $lib_dir/tc_common.sh
+source $lib_dir/lib.sh
+source $lib_dir/devlink_lib.sh
+
+h1_create()
+{
+ simple_if_init $h1 192.0.2.1/24
+}
+
+h1_destroy()
+{
+ simple_if_fini $h1 192.0.2.1/24
+}
+
+switch_create()
+{
+ simple_if_init $swp1 192.0.2.2/24
+ tc qdisc add dev $swp1 clsact
+}
+
+switch_destroy()
+{
+ tc qdisc del dev $swp1 clsact
+ simple_if_fini $swp1 192.0.2.2/24
+}
+
+hw_stats_test()
+{
+ RET=0
+
+ local name=$1
+ local action_hw_stats=$2
+ local occ_delta=$3
+ local expected_packet_count=$4
+
+ local orig_occ=$(devlink_resource_get "counters" "flow" | jq '.["occ"]')
+
+ tc filter add dev $swp1 ingress protocol ip pref 1 handle 101 flower \
+ skip_sw dst_ip 192.0.2.2 action drop $action_hw_stats
+ check_err $? "Failed to add rule with $name hw_stats"
+
+ local new_occ=$(devlink_resource_get "counters" "flow" | jq '.["occ"]')
+ local expected_occ=$((orig_occ + occ_delta))
+ [ "$new_occ" == "$expected_occ" ]
+ check_err $? "Expected occupancy of $expected_occ, got $new_occ"
+
+ $MZ $h1 -c 1 -p 64 -a $h1mac -b $swp1mac -A 192.0.2.1 -B 192.0.2.2 \
+ -t ip -q
+
+ tc_check_packets "dev $swp1 ingress" 101 $expected_packet_count
+ check_err $? "Did not match incoming packet"
+
+ tc filter del dev $swp1 ingress protocol ip pref 1 handle 101 flower
+
+ log_test "$name hw_stats"
+}
+
+default_hw_stats_test()
+{
+ hw_stats_test "default" "" 2 1
+}
+
+immediate_hw_stats_test()
+{
+ hw_stats_test "immediate" "hw_stats immediate" 2 1
+}
+
+delayed_hw_stats_test()
+{
+ RET=0
+
+ tc filter add dev $swp1 ingress protocol ip pref 1 handle 101 flower \
+ skip_sw dst_ip 192.0.2.2 action drop hw_stats delayed
+ check_fail $? "Unexpected success in adding rule with delayed hw_stats"
+
+ log_test "delayed hw_stats"
+}
+
+disabled_hw_stats_test()
+{
+ hw_stats_test "disabled" "hw_stats disabled" 0 0
+}
+
+setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ swp1=${NETIFS[p2]}
+
+ h1mac=$(mac_get $h1)
+ swp1mac=$(mac_get $swp1)
+
+ vrf_prepare
+
+ h1_create
+ switch_create
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ switch_destroy
+ h1_destroy
+
+ vrf_cleanup
+}
+
+check_tc_action_hw_stats_support
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/drivers/net/mlxsw/tc_flower_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/tc_flower_scale.sh
index a6d733d2a4b4..cc0f07e72cf2 100644
--- a/tools/testing/selftests/drivers/net/mlxsw/tc_flower_scale.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/tc_flower_scale.sh
@@ -2,9 +2,9 @@
# SPDX-License-Identifier: GPL-2.0
# Test for resource limit of offloaded flower rules. The test adds a given
-# number of flower matches for different IPv6 addresses, then generates traffic,
-# and ensures each was hit exactly once. This file contains functions to set up
-# a testing topology and run the test, and is meant to be sourced from a test
+# number of flower matches for different IPv6 addresses, then check the offload
+# indication for all of the tc flower rules. This file contains functions to set
+# up a testing topology and run the test, and is meant to be sourced from a test
# script that calls the testing routine with a given number of rules.
TC_FLOWER_NUM_NETIFS=2
@@ -94,22 +94,15 @@ __tc_flower_test()
tc_flower_rules_create $count $should_fail
- for ((i = 0; i < count; ++i)); do
- $MZ $h1 -q -c 1 -t ip -p 20 -b bc -6 \
- -A 2001:db8:2::1 \
- -B $(tc_flower_addr $i)
- done
-
- MISMATCHES=$(
- tc -j -s filter show dev $h2 ingress |
- jq -r '[ .[] | select(.kind == "flower") | .options |
- values as $rule | .actions[].stats.packets |
- select(. != 1) | "\(.) on \($rule.keys.dst_ip)" ] |
- join(", ")'
- )
-
- test -z "$MISMATCHES"
- check_err $? "Expected to capture 1 packet for each IP, but got $MISMATCHES"
+ offload_count=$(tc -j -s filter show dev $h2 ingress |
+ jq -r '[ .[] | select(.kind == "flower") |
+ .options | .in_hw ]' | jq .[] | wc -l)
+ [[ $((offload_count - 1)) -eq $count ]]
+ if [[ $should_fail -eq 0 ]]; then
+ check_err $? "Offload mismatch"
+ else
+ check_err_fail $should_fail $? "Offload more than expacted"
+ fi
}
tc_flower_test()
diff --git a/tools/testing/selftests/drivers/net/mlxsw/tc_restrictions.sh b/tools/testing/selftests/drivers/net/mlxsw/tc_restrictions.sh
new file mode 100755
index 000000000000..9241250c5921
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/tc_restrictions.sh
@@ -0,0 +1,318 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+
+ALL_TESTS="
+ shared_block_drop_test
+ egress_redirect_test
+ multi_mirror_test
+ matchall_sample_egress_test
+ matchall_mirror_behind_flower_ingress_test
+ matchall_sample_behind_flower_ingress_test
+ matchall_mirror_behind_flower_egress_test
+"
+NUM_NETIFS=2
+
+source $lib_dir/tc_common.sh
+source $lib_dir/lib.sh
+
+switch_create()
+{
+ simple_if_init $swp1 192.0.2.1/24
+ simple_if_init $swp2 192.0.2.2/24
+}
+
+switch_destroy()
+{
+ simple_if_fini $swp2 192.0.2.2/24
+ simple_if_fini $swp1 192.0.2.1/24
+}
+
+shared_block_drop_test()
+{
+ RET=0
+
+ # It is forbidden in mlxsw driver to have mixed-bound
+ # shared block with a drop rule.
+
+ tc qdisc add dev $swp1 ingress_block 22 clsact
+ check_err $? "Failed to create clsact with ingress block"
+
+ tc filter add block 22 protocol ip pref 1 handle 101 flower \
+ skip_sw dst_ip 192.0.2.2 action drop
+ check_err $? "Failed to add drop rule to ingress bound block"
+
+ tc qdisc add dev $swp2 ingress_block 22 clsact
+ check_err $? "Failed to create another clsact with ingress shared block"
+
+ tc qdisc del dev $swp2 clsact
+
+ tc qdisc add dev $swp2 egress_block 22 clsact
+ check_fail $? "Incorrect success to create another clsact with egress shared block"
+
+ tc filter del block 22 protocol ip pref 1 handle 101 flower
+
+ tc qdisc add dev $swp2 egress_block 22 clsact
+ check_err $? "Failed to create another clsact with egress shared block after blocker drop rule removed"
+
+ tc filter add block 22 protocol ip pref 1 handle 101 flower \
+ skip_sw dst_ip 192.0.2.2 action drop
+ check_fail $? "Incorrect success to add drop rule to mixed bound block"
+
+ tc qdisc del dev $swp1 clsact
+
+ tc qdisc add dev $swp1 egress_block 22 clsact
+ check_err $? "Failed to create another clsact with egress shared block"
+
+ tc filter add block 22 protocol ip pref 1 handle 101 flower \
+ skip_sw dst_ip 192.0.2.2 action drop
+ check_err $? "Failed to add drop rule to egress bound shared block"
+
+ tc filter del block 22 protocol ip pref 1 handle 101 flower
+
+ tc qdisc del dev $swp2 clsact
+ tc qdisc del dev $swp1 clsact
+
+ log_test "shared block drop"
+}
+
+egress_redirect_test()
+{
+ RET=0
+
+ # It is forbidden in mlxsw driver to have mirred redirect on
+ # egress-bound block.
+
+ tc qdisc add dev $swp1 ingress_block 22 clsact
+ check_err $? "Failed to create clsact with ingress block"
+
+ tc filter add block 22 protocol ip pref 1 handle 101 flower \
+ skip_sw dst_ip 192.0.2.2 \
+ action mirred egress redirect dev $swp2
+ check_err $? "Failed to add redirect rule to ingress bound block"
+
+ tc qdisc add dev $swp2 ingress_block 22 clsact
+ check_err $? "Failed to create another clsact with ingress shared block"
+
+ tc qdisc del dev $swp2 clsact
+
+ tc qdisc add dev $swp2 egress_block 22 clsact
+ check_fail $? "Incorrect success to create another clsact with egress shared block"
+
+ tc filter del block 22 protocol ip pref 1 handle 101 flower
+
+ tc qdisc add dev $swp2 egress_block 22 clsact
+ check_err $? "Failed to create another clsact with egress shared block after blocker redirect rule removed"
+
+ tc filter add block 22 protocol ip pref 1 handle 101 flower \
+ skip_sw dst_ip 192.0.2.2 \
+ action mirred egress redirect dev $swp2
+ check_fail $? "Incorrect success to add redirect rule to mixed bound block"
+
+ tc qdisc del dev $swp1 clsact
+
+ tc qdisc add dev $swp1 egress_block 22 clsact
+ check_err $? "Failed to create another clsact with egress shared block"
+
+ tc filter add block 22 protocol ip pref 1 handle 101 flower \
+ skip_sw dst_ip 192.0.2.2 \
+ action mirred egress redirect dev $swp2
+ check_fail $? "Incorrect success to add redirect rule to egress bound shared block"
+
+ tc qdisc del dev $swp2 clsact
+
+ tc filter add block 22 protocol ip pref 1 handle 101 flower \
+ skip_sw dst_ip 192.0.2.2 \
+ action mirred egress redirect dev $swp2
+ check_fail $? "Incorrect success to add redirect rule to egress bound block"
+
+ tc qdisc del dev $swp1 clsact
+
+ log_test "shared block drop"
+}
+
+multi_mirror_test()
+{
+ RET=0
+
+ # It is forbidden in mlxsw driver to have multiple mirror
+ # actions in a single rule.
+
+ tc qdisc add dev $swp1 clsact
+
+ tc filter add dev $swp1 ingress protocol ip pref 1 handle 101 flower \
+ skip_sw dst_ip 192.0.2.2 \
+ action mirred egress mirror dev $swp2
+ check_err $? "Failed to add rule with single mirror action"
+
+ tc filter del dev $swp1 ingress protocol ip pref 1 handle 101 flower
+
+ tc filter add dev $swp1 ingress protocol ip pref 1 handle 101 flower \
+ skip_sw dst_ip 192.0.2.2 \
+ action mirred egress mirror dev $swp2 \
+ action mirred egress mirror dev $swp1
+ check_fail $? "Incorrect success to add rule with two mirror actions"
+
+ tc qdisc del dev $swp1 clsact
+
+ log_test "multi mirror"
+}
+
+matchall_sample_egress_test()
+{
+ RET=0
+
+ # It is forbidden in mlxsw driver to have matchall with sample action
+ # bound on egress
+
+ tc qdisc add dev $swp1 clsact
+
+ tc filter add dev $swp1 ingress protocol all pref 1 handle 101 \
+ matchall skip_sw action sample rate 100 group 1
+ check_err $? "Failed to add rule with sample action on ingress"
+
+ tc filter del dev $swp1 ingress protocol all pref 1 handle 101 matchall
+
+ tc filter add dev $swp1 egress protocol all pref 1 handle 101 \
+ matchall skip_sw action sample rate 100 group 1
+ check_fail $? "Incorrect success to add rule with sample action on egress"
+
+ tc qdisc del dev $swp1 clsact
+
+ log_test "matchall sample egress"
+}
+
+matchall_behind_flower_ingress_test()
+{
+ local action=$1
+ local action_args=$2
+
+ RET=0
+
+ # On ingress, all matchall-mirror and matchall-sample
+ # rules have to be in front of the flower rules
+
+ tc qdisc add dev $swp1 clsact
+
+ tc filter add dev $swp1 ingress protocol ip pref 10 handle 101 flower \
+ skip_sw dst_ip 192.0.2.2 action drop
+
+ tc filter add dev $swp1 ingress protocol all pref 9 handle 102 \
+ matchall skip_sw action $action_args
+ check_err $? "Failed to add matchall rule in front of a flower rule"
+
+ tc filter del dev $swp1 ingress protocol all pref 9 handle 102 matchall
+
+ tc filter add dev $swp1 ingress protocol all pref 11 handle 102 \
+ matchall skip_sw action $action_args
+ check_fail $? "Incorrect success to add matchall rule behind a flower rule"
+
+ tc filter del dev $swp1 ingress protocol ip pref 10 handle 101 flower
+
+ tc filter add dev $swp1 ingress protocol all pref 9 handle 102 \
+ matchall skip_sw action $action_args
+
+ tc filter add dev $swp1 ingress protocol ip pref 10 handle 101 flower \
+ skip_sw dst_ip 192.0.2.2 action drop
+ check_err $? "Failed to add flower rule behind a matchall rule"
+
+ tc filter del dev $swp1 ingress protocol ip pref 10 handle 101 flower
+
+ tc filter add dev $swp1 ingress protocol ip pref 8 handle 101 flower \
+ skip_sw dst_ip 192.0.2.2 action drop
+ check_fail $? "Incorrect success to add flower rule in front of a matchall rule"
+
+ tc qdisc del dev $swp1 clsact
+
+ log_test "matchall $action flower ingress"
+}
+
+matchall_mirror_behind_flower_ingress_test()
+{
+ matchall_behind_flower_ingress_test "mirror" "mirred egress mirror dev $swp2"
+}
+
+matchall_sample_behind_flower_ingress_test()
+{
+ matchall_behind_flower_ingress_test "sample" "sample rate 100 group 1"
+}
+
+matchall_behind_flower_egress_test()
+{
+ local action=$1
+ local action_args=$2
+
+ RET=0
+
+ # On egress, all matchall-mirror rules have to be behind the flower rules
+
+ tc qdisc add dev $swp1 clsact
+
+ tc filter add dev $swp1 egress protocol ip pref 10 handle 101 flower \
+ skip_sw dst_ip 192.0.2.2 action drop
+
+ tc filter add dev $swp1 egress protocol all pref 11 handle 102 \
+ matchall skip_sw action $action_args
+ check_err $? "Failed to add matchall rule in front of a flower rule"
+
+ tc filter del dev $swp1 egress protocol all pref 11 handle 102 matchall
+
+ tc filter add dev $swp1 egress protocol all pref 9 handle 102 \
+ matchall skip_sw action $action_args
+ check_fail $? "Incorrect success to add matchall rule behind a flower rule"
+
+ tc filter del dev $swp1 egress protocol ip pref 10 handle 101 flower
+
+ tc filter add dev $swp1 egress protocol all pref 11 handle 102 \
+ matchall skip_sw action $action_args
+
+ tc filter add dev $swp1 egress protocol ip pref 10 handle 101 flower \
+ skip_sw dst_ip 192.0.2.2 action drop
+ check_err $? "Failed to add flower rule behind a matchall rule"
+
+ tc filter del dev $swp1 egress protocol ip pref 10 handle 101 flower
+
+ tc filter add dev $swp1 egress protocol ip pref 12 handle 101 flower \
+ skip_sw dst_ip 192.0.2.2 action drop
+ check_fail $? "Incorrect success to add flower rule in front of a matchall rule"
+
+ tc qdisc del dev $swp1 clsact
+
+ log_test "matchall $action flower egress"
+}
+
+matchall_mirror_behind_flower_egress_test()
+{
+ matchall_behind_flower_egress_test "mirror" "mirred egress mirror dev $swp2"
+}
+
+setup_prepare()
+{
+ swp1=${NETIFS[p1]}
+ swp2=${NETIFS[p2]}
+
+ vrf_prepare
+
+ switch_create
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ switch_destroy
+
+ vrf_cleanup
+}
+
+check_tc_shblock_support
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh b/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh
index 4632f51af7ab..729a86cc4ede 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh
@@ -9,6 +9,7 @@ lib_dir=$(dirname $0)/../../../net/forwarding
ALL_TESTS="sanitization_test offload_indication_test \
sanitization_vlan_aware_test offload_indication_vlan_aware_test"
NUM_NETIFS=2
+: ${TIMEOUT:=20000} # ms
source $lib_dir/lib.sh
setup_prepare()
@@ -470,8 +471,8 @@ offload_indication_fdb_flood_test()
bridge fdb append 00:00:00:00:00:00 dev vxlan0 self dst 198.51.100.2
- bridge fdb show brport vxlan0 | grep 00:00:00:00:00:00 \
- | grep -q offload
+ busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb 00:00:00:00:00:00 \
+ bridge fdb show brport vxlan0
check_err $?
bridge fdb del 00:00:00:00:00:00 dev vxlan0 self
@@ -486,11 +487,11 @@ offload_indication_fdb_bridge_test()
bridge fdb add de:ad:be:ef:13:37 dev vxlan0 self master static \
dst 198.51.100.2
- bridge fdb show brport vxlan0 | grep de:ad:be:ef:13:37 | grep self \
- | grep -q offload
+ busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb \
+ de:ad:be:ef:13:37 self bridge fdb show brport vxlan0
check_err $?
- bridge fdb show brport vxlan0 | grep de:ad:be:ef:13:37 | grep -v self \
- | grep -q offload
+ busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb \
+ de:ad:be:ef:13:37 self -v bridge fdb show brport vxlan0
check_err $?
log_test "vxlan entry offload indication - initial state"
@@ -500,9 +501,9 @@ offload_indication_fdb_bridge_test()
RET=0
bridge fdb del de:ad:be:ef:13:37 dev vxlan0 master
- bridge fdb show brport vxlan0 | grep de:ad:be:ef:13:37 | grep self \
- | grep -q offload
- check_fail $?
+ busywait "$TIMEOUT" not wait_for_offload grep_bridge_fdb \
+ de:ad:be:ef:13:37 self bridge fdb show brport vxlan0
+ check_err $?
log_test "vxlan entry offload indication - after removal from bridge"
@@ -511,11 +512,11 @@ offload_indication_fdb_bridge_test()
RET=0
bridge fdb add de:ad:be:ef:13:37 dev vxlan0 master static
- bridge fdb show brport vxlan0 | grep de:ad:be:ef:13:37 | grep self \
- | grep -q offload
+ busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb \
+ de:ad:be:ef:13:37 self bridge fdb show brport vxlan0
check_err $?
- bridge fdb show brport vxlan0 | grep de:ad:be:ef:13:37 | grep -v self \
- | grep -q offload
+ busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb \
+ de:ad:be:ef:13:37 self -v bridge fdb show brport vxlan0
check_err $?
log_test "vxlan entry offload indication - after re-add to bridge"
@@ -525,9 +526,9 @@ offload_indication_fdb_bridge_test()
RET=0
bridge fdb del de:ad:be:ef:13:37 dev vxlan0 self
- bridge fdb show brport vxlan0 | grep de:ad:be:ef:13:37 | grep -v self \
- | grep -q offload
- check_fail $?
+ busywait "$TIMEOUT" not wait_for_offload grep_bridge_fdb \
+ de:ad:be:ef:13:37 self -v bridge fdb show brport vxlan0
+ check_err $?
log_test "vxlan entry offload indication - after removal from vxlan"
@@ -536,11 +537,11 @@ offload_indication_fdb_bridge_test()
RET=0
bridge fdb add de:ad:be:ef:13:37 dev vxlan0 self dst 198.51.100.2
- bridge fdb show brport vxlan0 | grep de:ad:be:ef:13:37 | grep self \
- | grep -q offload
+ busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb \
+ de:ad:be:ef:13:37 self bridge fdb show brport vxlan0
check_err $?
- bridge fdb show brport vxlan0 | grep de:ad:be:ef:13:37 | grep -v self \
- | grep -q offload
+ busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb \
+ de:ad:be:ef:13:37 self -v bridge fdb show brport vxlan0
check_err $?
log_test "vxlan entry offload indication - after re-add to vxlan"
@@ -558,27 +559,32 @@ offload_indication_decap_route_test()
{
RET=0
- ip route show table local | grep 198.51.100.1 | grep -q offload
+ busywait "$TIMEOUT" wait_for_offload \
+ ip route show table local 198.51.100.1
check_err $?
ip link set dev vxlan0 down
- ip route show table local | grep 198.51.100.1 | grep -q offload
+ busywait "$TIMEOUT" wait_for_offload \
+ ip route show table local 198.51.100.1
check_err $?
ip link set dev vxlan1 down
- ip route show table local | grep 198.51.100.1 | grep -q offload
- check_fail $?
+ busywait "$TIMEOUT" not wait_for_offload \
+ ip route show table local 198.51.100.1
+ check_err $?
log_test "vxlan decap route - vxlan device down"
RET=0
ip link set dev vxlan1 up
- ip route show table local | grep 198.51.100.1 | grep -q offload
+ busywait "$TIMEOUT" wait_for_offload \
+ ip route show table local 198.51.100.1
check_err $?
ip link set dev vxlan0 up
- ip route show table local | grep 198.51.100.1 | grep -q offload
+ busywait "$TIMEOUT" wait_for_offload \
+ ip route show table local 198.51.100.1
check_err $?
log_test "vxlan decap route - vxlan device up"
@@ -586,11 +592,13 @@ offload_indication_decap_route_test()
RET=0
ip address delete 198.51.100.1/32 dev lo
- ip route show table local | grep 198.51.100.1 | grep -q offload
- check_fail $?
+ busywait "$TIMEOUT" not wait_for_offload \
+ ip route show table local 198.51.100.1
+ check_err $?
ip address add 198.51.100.1/32 dev lo
- ip route show table local | grep 198.51.100.1 | grep -q offload
+ busywait "$TIMEOUT" wait_for_offload \
+ ip route show table local 198.51.100.1
check_err $?
log_test "vxlan decap route - add local route"
@@ -598,16 +606,19 @@ offload_indication_decap_route_test()
RET=0
ip link set dev $swp1 nomaster
- ip route show table local | grep 198.51.100.1 | grep -q offload
+ busywait "$TIMEOUT" wait_for_offload \
+ ip route show table local 198.51.100.1
check_err $?
ip link set dev $swp2 nomaster
- ip route show table local | grep 198.51.100.1 | grep -q offload
- check_fail $?
+ busywait "$TIMEOUT" not wait_for_offload \
+ ip route show table local 198.51.100.1
+ check_err $?
ip link set dev $swp1 master br0
ip link set dev $swp2 master br1
- ip route show table local | grep 198.51.100.1 | grep -q offload
+ busywait "$TIMEOUT" wait_for_offload \
+ ip route show table local 198.51.100.1
check_err $?
log_test "vxlan decap route - local ports enslavement"
@@ -615,12 +626,14 @@ offload_indication_decap_route_test()
RET=0
ip link del dev br0
- ip route show table local | grep 198.51.100.1 | grep -q offload
+ busywait "$TIMEOUT" wait_for_offload \
+ ip route show table local 198.51.100.1
check_err $?
ip link del dev br1
- ip route show table local | grep 198.51.100.1 | grep -q offload
- check_fail $?
+ busywait "$TIMEOUT" not wait_for_offload \
+ ip route show table local 198.51.100.1
+ check_err $?
log_test "vxlan decap route - bridge device deletion"
@@ -632,16 +645,19 @@ offload_indication_decap_route_test()
ip link set dev $swp2 master br1
ip link set dev vxlan0 master br0
ip link set dev vxlan1 master br1
- ip route show table local | grep 198.51.100.1 | grep -q offload
+ busywait "$TIMEOUT" wait_for_offload \
+ ip route show table local 198.51.100.1
check_err $?
ip link del dev vxlan0
- ip route show table local | grep 198.51.100.1 | grep -q offload
+ busywait "$TIMEOUT" wait_for_offload \
+ ip route show table local 198.51.100.1
check_err $?
ip link del dev vxlan1
- ip route show table local | grep 198.51.100.1 | grep -q offload
- check_fail $?
+ busywait "$TIMEOUT" not wait_for_offload \
+ ip route show table local 198.51.100.1
+ check_err $?
log_test "vxlan decap route - vxlan device deletion"
@@ -656,12 +672,15 @@ check_fdb_offloaded()
local mac=00:11:22:33:44:55
local zmac=00:00:00:00:00:00
- bridge fdb show dev vxlan0 | grep $mac | grep self | grep -q offload
+ busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb $mac self \
+ bridge fdb show dev vxlan0
check_err $?
- bridge fdb show dev vxlan0 | grep $mac | grep master | grep -q offload
+ busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb $mac master \
+ bridge fdb show dev vxlan0
check_err $?
- bridge fdb show dev vxlan0 | grep $zmac | grep self | grep -q offload
+ busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb $zmac self \
+ bridge fdb show dev vxlan0
check_err $?
}
@@ -672,13 +691,15 @@ check_vxlan_fdb_not_offloaded()
bridge fdb show dev vxlan0 | grep $mac | grep -q self
check_err $?
- bridge fdb show dev vxlan0 | grep $mac | grep self | grep -q offload
- check_fail $?
+ busywait "$TIMEOUT" not wait_for_offload grep_bridge_fdb $mac self \
+ bridge fdb show dev vxlan0
+ check_err $?
bridge fdb show dev vxlan0 | grep $zmac | grep -q self
check_err $?
- bridge fdb show dev vxlan0 | grep $zmac | grep self | grep -q offload
- check_fail $?
+ busywait "$TIMEOUT" not wait_for_offload grep_bridge_fdb $zmac self \
+ bridge fdb show dev vxlan0
+ check_err $?
}
check_bridge_fdb_not_offloaded()
@@ -688,8 +709,9 @@ check_bridge_fdb_not_offloaded()
bridge fdb show dev vxlan0 | grep $mac | grep -q master
check_err $?
- bridge fdb show dev vxlan0 | grep $mac | grep master | grep -q offload
- check_fail $?
+ busywait "$TIMEOUT" not wait_for_offload grep_bridge_fdb $mac master \
+ bridge fdb show dev vxlan0
+ check_err $?
}
__offload_indication_join_vxlan_first()
@@ -771,12 +793,14 @@ __offload_indication_join_vxlan_last()
ip link set dev $swp1 master br0
- bridge fdb show dev vxlan0 | grep $zmac | grep self | grep -q offload
- check_fail $?
+ busywait "$TIMEOUT" not wait_for_offload grep_bridge_fdb $zmac self \
+ bridge fdb show dev vxlan0
+ check_err $?
ip link set dev vxlan0 master br0
- bridge fdb show dev vxlan0 | grep $zmac | grep self | grep -q offload
+ busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb $zmac self \
+ bridge fdb show dev vxlan0
check_err $?
log_test "offload indication - attach vxlan last"
@@ -854,20 +878,26 @@ sanitization_vlan_aware_test()
bridge vlan del vid 10 dev vxlan20
bridge vlan add vid 20 dev vxlan20 pvid untagged
- # Test that offloading of an unsupported tunnel fails when it is
- # triggered by addition of VLAN to a local port
- RET=0
+ # Test that when two VXLAN tunnels with conflicting configurations
+ # (i.e., different TTL) are enslaved to the same VLAN-aware bridge,
+ # then the enslavement of a port to the bridge is denied.
- # TOS must be set to inherit
- ip link set dev vxlan10 type vxlan tos 42
+ # Use the offload indication of the local route to ensure the VXLAN
+ # configuration was correctly rollbacked.
+ ip address add 198.51.100.1/32 dev lo
- ip link set dev $swp1 master br0
- bridge vlan add vid 10 dev $swp1 &> /dev/null
+ ip link set dev vxlan10 type vxlan ttl 10
+ ip link set dev $swp1 master br0 &> /dev/null
check_fail $?
- log_test "vlan-aware - failed vlan addition to a local port"
+ busywait "$TIMEOUT" not wait_for_offload \
+ ip route show table local 198.51.100.1
+ check_err $?
+
+ log_test "vlan-aware - failed enslavement to bridge due to conflict"
- ip link set dev vxlan10 type vxlan tos inherit
+ ip link set dev vxlan10 type vxlan ttl 20
+ ip address del 198.51.100.1/32 dev lo
ip link del dev vxlan20
ip link del dev vxlan10
@@ -924,11 +954,11 @@ offload_indication_vlan_aware_fdb_test()
bridge fdb add de:ad:be:ef:13:37 dev vxlan10 self master static \
dst 198.51.100.2 vlan 10
- bridge fdb show brport vxlan10 | grep de:ad:be:ef:13:37 | grep self \
- | grep -q offload
+ busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb \
+ de:ad:be:ef:13:37 self bridge fdb show brport vxlan10
check_err $?
- bridge fdb show brport vxlan10 | grep de:ad:be:ef:13:37 | grep -v self \
- | grep -q offload
+ busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb \
+ de:ad:be:ef:13:37 self -v bridge fdb show brport vxlan10
check_err $?
log_test "vxlan entry offload indication - initial state"
@@ -938,9 +968,9 @@ offload_indication_vlan_aware_fdb_test()
RET=0
bridge fdb del de:ad:be:ef:13:37 dev vxlan10 master vlan 10
- bridge fdb show brport vxlan10 | grep de:ad:be:ef:13:37 | grep self \
- | grep -q offload
- check_fail $?
+ busywait "$TIMEOUT" not wait_for_offload grep_bridge_fdb \
+ de:ad:be:ef:13:37 self bridge fdb show brport vxlan10
+ check_err $?
log_test "vxlan entry offload indication - after removal from bridge"
@@ -949,11 +979,11 @@ offload_indication_vlan_aware_fdb_test()
RET=0
bridge fdb add de:ad:be:ef:13:37 dev vxlan10 master static vlan 10
- bridge fdb show brport vxlan10 | grep de:ad:be:ef:13:37 | grep self \
- | grep -q offload
+ busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb \
+ de:ad:be:ef:13:37 self bridge fdb show brport vxlan10
check_err $?
- bridge fdb show brport vxlan10 | grep de:ad:be:ef:13:37 | grep -v self \
- | grep -q offload
+ busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb \
+ de:ad:be:ef:13:37 self -v bridge fdb show brport vxlan10
check_err $?
log_test "vxlan entry offload indication - after re-add to bridge"
@@ -963,9 +993,9 @@ offload_indication_vlan_aware_fdb_test()
RET=0
bridge fdb del de:ad:be:ef:13:37 dev vxlan10 self
- bridge fdb show brport vxlan10 | grep de:ad:be:ef:13:37 | grep -v self \
- | grep -q offload
- check_fail $?
+ busywait "$TIMEOUT" not wait_for_offload grep_bridge_fdb \
+ de:ad:be:ef:13:37 self -v bridge fdb show brport vxlan10
+ check_err $?
log_test "vxlan entry offload indication - after removal from vxlan"
@@ -974,11 +1004,11 @@ offload_indication_vlan_aware_fdb_test()
RET=0
bridge fdb add de:ad:be:ef:13:37 dev vxlan10 self dst 198.51.100.2
- bridge fdb show brport vxlan10 | grep de:ad:be:ef:13:37 | grep self \
- | grep -q offload
+ busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb \
+ de:ad:be:ef:13:37 self bridge fdb show brport vxlan10
check_err $?
- bridge fdb show brport vxlan10 | grep de:ad:be:ef:13:37 | grep -v self \
- | grep -q offload
+ busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb \
+ de:ad:be:ef:13:37 self -v bridge fdb show brport vxlan10
check_err $?
log_test "vxlan entry offload indication - after re-add to vxlan"
@@ -990,28 +1020,31 @@ offload_indication_vlan_aware_decap_route_test()
{
RET=0
- ip route show table local | grep 198.51.100.1 | grep -q offload
+ busywait "$TIMEOUT" wait_for_offload \
+ ip route show table local 198.51.100.1
check_err $?
# Toggle PVID flag on one VxLAN device and make sure route is still
# marked as offloaded
bridge vlan add vid 10 dev vxlan10 untagged
- ip route show table local | grep 198.51.100.1 | grep -q offload
+ busywait "$TIMEOUT" wait_for_offload \
+ ip route show table local 198.51.100.1
check_err $?
# Toggle PVID flag on second VxLAN device and make sure route is no
# longer marked as offloaded
bridge vlan add vid 20 dev vxlan20 untagged
- ip route show table local | grep 198.51.100.1 | grep -q offload
- check_fail $?
+ busywait "$TIMEOUT" not wait_for_offload \
+ ip route show table local 198.51.100.1
+ check_err $?
# Toggle PVID flag back and make sure route is marked as offloaded
bridge vlan add vid 10 dev vxlan10 pvid untagged
bridge vlan add vid 20 dev vxlan20 pvid untagged
- ip route show table local | grep 198.51.100.1 | grep -q offload
+ busywait "$TIMEOUT" wait_for_offload ip route show table local 198.51.100.1
check_err $?
log_test "vxlan decap route - vni map/unmap"
@@ -1064,35 +1097,33 @@ offload_indication_vlan_aware_l3vni_test()
ip link set dev vxlan0 master br0
bridge vlan add dev vxlan0 vid 10 pvid untagged
- # No local port or router port is member in the VLAN, so tunnel should
- # not be offloaded
- bridge fdb show brport vxlan0 | grep $zmac | grep self \
- | grep -q offload
- check_fail $? "vxlan tunnel offloaded when should not"
+ busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb $zmac self \
+ bridge fdb show brport vxlan0
+ check_err $? "vxlan tunnel not offloaded when should"
# Configure a VLAN interface and make sure tunnel is offloaded
ip link add link br0 name br10 up type vlan id 10
sysctl_set net.ipv6.conf.br10.disable_ipv6 0
ip -6 address add 2001:db8:1::1/64 dev br10
- bridge fdb show brport vxlan0 | grep $zmac | grep self \
- | grep -q offload
+ busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb $zmac self \
+ bridge fdb show brport vxlan0
check_err $? "vxlan tunnel not offloaded when should"
# Unlink the VXLAN device, make sure tunnel is no longer offloaded,
# then add it back to the bridge and make sure it is offloaded
ip link set dev vxlan0 nomaster
- bridge fdb show brport vxlan0 | grep $zmac | grep self \
- | grep -q offload
- check_fail $? "vxlan tunnel offloaded after unlinked from bridge"
+ busywait "$TIMEOUT" not wait_for_offload grep_bridge_fdb $zmac self \
+ bridge fdb show brport vxlan0
+ check_err $? "vxlan tunnel offloaded after unlinked from bridge"
ip link set dev vxlan0 master br0
- bridge fdb show brport vxlan0 | grep $zmac | grep self \
- | grep -q offload
- check_fail $? "vxlan tunnel offloaded despite no matching vid"
+ busywait "$TIMEOUT" not wait_for_offload grep_bridge_fdb $zmac self \
+ bridge fdb show brport vxlan0
+ check_err $? "vxlan tunnel offloaded despite no matching vid"
bridge vlan add dev vxlan0 vid 10 pvid untagged
- bridge fdb show brport vxlan0 | grep $zmac | grep self \
- | grep -q offload
+ busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb $zmac self \
+ bridge fdb show brport vxlan0
check_err $? "vxlan tunnel not offloaded after adding vid"
log_test "vxlan - l3 vni"
diff --git a/tools/testing/selftests/drivers/net/netdevsim/devlink.sh b/tools/testing/selftests/drivers/net/netdevsim/devlink.sh
index 025a84c2ab5a..de4b32fc4223 100755
--- a/tools/testing/selftests/drivers/net/netdevsim/devlink.sh
+++ b/tools/testing/selftests/drivers/net/netdevsim/devlink.sh
@@ -141,6 +141,44 @@ regions_test()
check_region_snapshot_count dummy post-first-delete 2
+ devlink region new $DL_HANDLE/dummy snapshot 25
+ check_err $? "Failed to create a new snapshot with id 25"
+
+ check_region_snapshot_count dummy post-first-request 3
+
+ devlink region dump $DL_HANDLE/dummy snapshot 25 >> /dev/null
+ check_err $? "Failed to dump snapshot with id 25"
+
+ devlink region read $DL_HANDLE/dummy snapshot 25 addr 0 len 1 >> /dev/null
+ check_err $? "Failed to read snapshot with id 25 (1 byte)"
+
+ devlink region read $DL_HANDLE/dummy snapshot 25 addr 128 len 128 >> /dev/null
+ check_err $? "Failed to read snapshot with id 25 (128 bytes)"
+
+ devlink region read $DL_HANDLE/dummy snapshot 25 addr 128 len $((1<<32)) >> /dev/null
+ check_err $? "Failed to read snapshot with id 25 (oversized)"
+
+ devlink region read $DL_HANDLE/dummy snapshot 25 addr $((1<<32)) len 128 >> /dev/null 2>&1
+ check_fail $? "Bad read of snapshot with id 25 did not fail"
+
+ devlink region del $DL_HANDLE/dummy snapshot 25
+ check_err $? "Failed to delete snapshot with id 25"
+
+ check_region_snapshot_count dummy post-second-delete 2
+
+ sid=$(devlink -j region new $DL_HANDLE/dummy | jq '.[][][][]')
+ check_err $? "Failed to create a new snapshot with id allocated by the kernel"
+
+ check_region_snapshot_count dummy post-first-request 3
+
+ devlink region dump $DL_HANDLE/dummy snapshot $sid >> /dev/null
+ check_err $? "Failed to dump a snapshot with id allocated by the kernel"
+
+ devlink region del $DL_HANDLE/dummy snapshot $sid
+ check_err $? "Failed to delete snapshot with id allocated by the kernel"
+
+ check_region_snapshot_count dummy post-first-request 2
+
log_test "regions test"
}
@@ -367,6 +405,11 @@ dummy_reporter_test()
{
RET=0
+ check_reporter_info dummy healthy 0 0 0 true
+
+ devlink health set $DL_HANDLE reporter dummy auto_recover false
+ check_err $? "Failed to dummy reporter auto_recover option"
+
check_reporter_info dummy healthy 0 0 0 false
local BREAK_MSG="foo bar"
diff --git a/tools/testing/selftests/drivers/net/netdevsim/devlink_trap.sh b/tools/testing/selftests/drivers/net/netdevsim/devlink_trap.sh
index f101ab9441e2..da49ad2761b5 100755
--- a/tools/testing/selftests/drivers/net/netdevsim/devlink_trap.sh
+++ b/tools/testing/selftests/drivers/net/netdevsim/devlink_trap.sh
@@ -16,6 +16,8 @@ ALL_TESTS="
trap_group_action_test
bad_trap_group_test
trap_group_stats_test
+ trap_policer_test
+ trap_policer_bind_test
port_del_test
dev_del_test
"
@@ -23,6 +25,7 @@ NETDEVSIM_PATH=/sys/bus/netdevsim/
DEV_ADDR=1337
DEV=netdevsim${DEV_ADDR}
DEVLINK_DEV=netdevsim/${DEV}
+DEBUGFS_DIR=/sys/kernel/debug/netdevsim/$DEV/
SLEEP_TIME=1
NETDEV=""
NUM_NETIFS=0
@@ -103,6 +106,11 @@ trap_metadata_test()
for trap_name in $(devlink_traps_get); do
devlink_trap_metadata_test $trap_name "input_port"
check_err $? "Input port not reported as metadata of trap $trap_name"
+ if [ $trap_name == "ingress_flow_action_drop" ] ||
+ [ $trap_name == "egress_flow_action_drop" ]; then
+ devlink_trap_metadata_test $trap_name "flow_action_cookie"
+ check_err $? "Flow action cookie not reported as metadata of trap $trap_name"
+ fi
done
log_test "Trap metadata"
@@ -251,6 +259,123 @@ trap_group_stats_test()
log_test "Trap group statistics"
}
+trap_policer_test()
+{
+ local packets_t0
+ local packets_t1
+
+ RET=0
+
+ if [ $(devlink_trap_policers_num_get) -eq 0 ]; then
+ check_err 1 "Failed to dump policers"
+ fi
+
+ devlink trap policer set $DEVLINK_DEV policer 1337 &> /dev/null
+ check_fail $? "Did not get an error for setting a non-existing policer"
+ devlink trap policer show $DEVLINK_DEV policer 1337 &> /dev/null
+ check_fail $? "Did not get an error for getting a non-existing policer"
+
+ devlink trap policer set $DEVLINK_DEV policer 1 rate 2000 burst 16
+ check_err $? "Failed to set valid parameters for a valid policer"
+ if [ $(devlink_trap_policer_rate_get 1) -ne 2000 ]; then
+ check_err 1 "Policer rate was not changed"
+ fi
+ if [ $(devlink_trap_policer_burst_get 1) -ne 16 ]; then
+ check_err 1 "Policer burst size was not changed"
+ fi
+
+ devlink trap policer set $DEVLINK_DEV policer 1 rate 0 &> /dev/null
+ check_fail $? "Policer rate was changed to rate lower than limit"
+ devlink trap policer set $DEVLINK_DEV policer 1 rate 9000 &> /dev/null
+ check_fail $? "Policer rate was changed to rate higher than limit"
+ devlink trap policer set $DEVLINK_DEV policer 1 burst 2 &> /dev/null
+ check_fail $? "Policer burst size was changed to burst size lower than limit"
+ devlink trap policer set $DEVLINK_DEV policer 1 rate 65537 &> /dev/null
+ check_fail $? "Policer burst size was changed to burst size higher than limit"
+ echo "y" > $DEBUGFS_DIR/fail_trap_policer_set
+ devlink trap policer set $DEVLINK_DEV policer 1 rate 3000 &> /dev/null
+ check_fail $? "Managed to set policer rate when should not"
+ echo "n" > $DEBUGFS_DIR/fail_trap_policer_set
+ if [ $(devlink_trap_policer_rate_get 1) -ne 2000 ]; then
+ check_err 1 "Policer rate was changed to an invalid value"
+ fi
+ if [ $(devlink_trap_policer_burst_get 1) -ne 16 ]; then
+ check_err 1 "Policer burst size was changed to an invalid value"
+ fi
+
+ packets_t0=$(devlink_trap_policer_rx_dropped_get 1)
+ sleep .5
+ packets_t1=$(devlink_trap_policer_rx_dropped_get 1)
+ if [ ! $packets_t1 -gt $packets_t0 ]; then
+ check_err 1 "Policer drop counter was not incremented"
+ fi
+
+ echo "y"> $DEBUGFS_DIR/fail_trap_policer_counter_get
+ devlink -s trap policer show $DEVLINK_DEV policer 1 &> /dev/null
+ check_fail $? "Managed to read policer drop counter when should not"
+ echo "n"> $DEBUGFS_DIR/fail_trap_policer_counter_get
+ devlink -s trap policer show $DEVLINK_DEV policer 1 &> /dev/null
+ check_err $? "Did not manage to read policer drop counter when should"
+
+ log_test "Trap policer"
+}
+
+trap_group_check_policer()
+{
+ local group_name=$1; shift
+
+ devlink -j -p trap group show $DEVLINK_DEV group $group_name \
+ | jq -e '.[][][]["policer"]' &> /dev/null
+}
+
+trap_policer_bind_test()
+{
+ RET=0
+
+ devlink trap group set $DEVLINK_DEV group l2_drops policer 1
+ check_err $? "Failed to bind a valid policer"
+ if [ $(devlink_trap_group_policer_get "l2_drops") -ne 1 ]; then
+ check_err 1 "Bound policer was not changed"
+ fi
+
+ devlink trap group set $DEVLINK_DEV group l2_drops policer 1337 \
+ &> /dev/null
+ check_fail $? "Did not get an error for binding a non-existing policer"
+ if [ $(devlink_trap_group_policer_get "l2_drops") -ne 1 ]; then
+ check_err 1 "Bound policer was changed when should not"
+ fi
+
+ devlink trap group set $DEVLINK_DEV group l2_drops policer 0
+ check_err $? "Failed to unbind a policer when using ID 0"
+ trap_group_check_policer "l2_drops"
+ check_fail $? "Trap group has a policer after unbinding with ID 0"
+
+ devlink trap group set $DEVLINK_DEV group l2_drops policer 1
+ check_err $? "Failed to bind a valid policer"
+
+ devlink trap group set $DEVLINK_DEV group l2_drops nopolicer
+ check_err $? "Failed to unbind a policer when using 'nopolicer' keyword"
+ trap_group_check_policer "l2_drops"
+ check_fail $? "Trap group has a policer after unbinding with 'nopolicer' keyword"
+
+ devlink trap group set $DEVLINK_DEV group l2_drops policer 1
+ check_err $? "Failed to bind a valid policer"
+
+ echo "y"> $DEBUGFS_DIR/fail_trap_group_set
+ devlink trap group set $DEVLINK_DEV group l2_drops policer 2 \
+ &> /dev/null
+ check_fail $? "Managed to bind a policer when should not"
+ echo "n"> $DEBUGFS_DIR/fail_trap_group_set
+ devlink trap group set $DEVLINK_DEV group l2_drops policer 2
+ check_err $? "Did not manage to bind a policer when should"
+
+ devlink trap group set $DEVLINK_DEV group l2_drops action drop \
+ policer 1337 &> /dev/null
+ check_fail $? "Did not get an error for partially modified trap group"
+
+ log_test "Trap policer binding"
+}
+
port_del_test()
{
local group_name
diff --git a/tools/testing/selftests/efivarfs/.gitignore b/tools/testing/selftests/efivarfs/.gitignore
index 33618493562b..807407f7f58b 100644
--- a/tools/testing/selftests/efivarfs/.gitignore
+++ b/tools/testing/selftests/efivarfs/.gitignore
@@ -1,2 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0-only
create-read
open-unlink
diff --git a/tools/testing/selftests/exec/.gitignore b/tools/testing/selftests/exec/.gitignore
index b02279da6fa1..94b02a18f230 100644
--- a/tools/testing/selftests/exec/.gitignore
+++ b/tools/testing/selftests/exec/.gitignore
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
subdir*
script*
execveat
@@ -8,3 +9,4 @@ execveat.ephemeral
execveat.denatured
/recursion-depth
xxxxxxxx*
+pipe
diff --git a/tools/testing/selftests/exec/Makefile b/tools/testing/selftests/exec/Makefile
index 33339e31e365..4453b8f8def3 100644
--- a/tools/testing/selftests/exec/Makefile
+++ b/tools/testing/selftests/exec/Makefile
@@ -3,8 +3,9 @@ CFLAGS = -Wall
CFLAGS += -Wno-nonnull
CFLAGS += -D_GNU_SOURCE
+TEST_PROGS := binfmt_script
TEST_GEN_PROGS := execveat
-TEST_GEN_FILES := execveat.symlink execveat.denatured script subdir
+TEST_GEN_FILES := execveat.symlink execveat.denatured script subdir pipe
# Makefile is a run-time dependency, since it's accessed by the execveat test
TEST_FILES := Makefile
diff --git a/tools/testing/selftests/exec/binfmt_script b/tools/testing/selftests/exec/binfmt_script
new file mode 100755
index 000000000000..05f94a741c7a
--- /dev/null
+++ b/tools/testing/selftests/exec/binfmt_script
@@ -0,0 +1,171 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test that truncation of bprm->buf doesn't cause unexpected execs paths, along
+# with various other pathological cases.
+import os, subprocess
+
+# Relevant commits
+#
+# b5372fe5dc84 ("exec: load_script: Do not exec truncated interpreter path")
+# 6eb3c3d0a52d ("exec: increase BINPRM_BUF_SIZE to 256")
+
+# BINPRM_BUF_SIZE
+SIZE=256
+
+NAME_MAX=int(subprocess.check_output(["getconf", "NAME_MAX", "."]))
+
+test_num=0
+
+code='''#!/usr/bin/perl
+print "Executed interpreter! Args:\n";
+print "0 : '$0'\n";
+$counter = 1;
+foreach my $a (@ARGV) {
+ print "$counter : '$a'\n";
+ $counter++;
+}
+'''
+
+##
+# test - produce a binfmt_script hashbang line for testing
+#
+# @size: bytes for bprm->buf line, including hashbang but not newline
+# @good: whether this script is expected to execute correctly
+# @hashbang: the special 2 bytes for running binfmt_script
+# @leading: any leading whitespace before the executable path
+# @root: start of executable pathname
+# @target: end of executable pathname
+# @arg: bytes following the executable pathname
+# @fill: character to fill between @root and @target to reach @size bytes
+# @newline: character to use as newline, not counted towards @size
+# ...
+def test(name, size, good=True, leading="", root="./", target="/perl",
+ fill="A", arg="", newline="\n", hashbang="#!"):
+ global test_num, tests, NAME_MAX
+ test_num += 1
+ if test_num > tests:
+ raise ValueError("more binfmt_script tests than expected! (want %d, expected %d)"
+ % (test_num, tests))
+
+ middle = ""
+ remaining = size - len(hashbang) - len(leading) - len(root) - len(target) - len(arg)
+ # The middle of the pathname must not exceed NAME_MAX
+ while remaining >= NAME_MAX:
+ middle += fill * (NAME_MAX - 1)
+ middle += '/'
+ remaining -= NAME_MAX
+ middle += fill * remaining
+
+ dirpath = root + middle
+ binary = dirpath + target
+ if len(target):
+ os.makedirs(dirpath, mode=0o755, exist_ok=True)
+ open(binary, "w").write(code)
+ os.chmod(binary, 0o755)
+
+ buf=hashbang + leading + root + middle + target + arg + newline
+ if len(newline) > 0:
+ buf += 'echo this is not really perl\n'
+
+ script = "binfmt_script-%s" % (name)
+ open(script, "w").write(buf)
+ os.chmod(script, 0o755)
+
+ proc = subprocess.Popen(["./%s" % (script)], shell=True,
+ stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
+ stdout = proc.communicate()[0]
+
+ if proc.returncode == 0 and b'Executed interpreter' in stdout:
+ if good:
+ print("ok %d - binfmt_script %s (successful good exec)"
+ % (test_num, name))
+ else:
+ print("not ok %d - binfmt_script %s succeeded when it should have failed"
+ % (test_num, name))
+ else:
+ if good:
+ print("not ok %d - binfmt_script %s failed when it should have succeeded (rc:%d)"
+ % (test_num, name, proc.returncode))
+ else:
+ print("ok %d - binfmt_script %s (correctly failed bad exec)"
+ % (test_num, name))
+
+ # Clean up crazy binaries
+ os.unlink(script)
+ if len(target):
+ elements = binary.split('/')
+ os.unlink(binary)
+ elements.pop()
+ while len(elements) > 1:
+ os.rmdir("/".join(elements))
+ elements.pop()
+
+tests=27
+print("TAP version 1.3")
+print("1..%d" % (tests))
+
+### FAIL (8 tests)
+
+# Entire path is well past the BINFMT_BUF_SIZE.
+test(name="too-big", size=SIZE+80, good=False)
+# Path is right at max size, making it impossible to tell if it was truncated.
+test(name="exact", size=SIZE, good=False)
+# Same as above, but with leading whitespace.
+test(name="exact-space", size=SIZE, good=False, leading=" ")
+# Huge buffer of only whitespace.
+test(name="whitespace-too-big", size=SIZE+71, good=False, root="",
+ fill=" ", target="")
+# A good path, but it gets truncated due to leading whitespace.
+test(name="truncated", size=SIZE+17, good=False, leading=" " * 19)
+# Entirely empty except for #!
+test(name="empty", size=2, good=False, root="",
+ fill="", target="", newline="")
+# Within size, but entirely spaces
+test(name="spaces", size=SIZE-1, good=False, root="", fill=" ",
+ target="", newline="")
+# Newline before binary.
+test(name="newline-prefix", size=SIZE-1, good=False, leading="\n",
+ root="", fill=" ", target="")
+
+### ok (19 tests)
+
+# The original test case that was broken by commit:
+# 8099b047ecc4 ("exec: load_script: don't blindly truncate shebang string")
+test(name="test.pl", size=439, leading=" ",
+ root="./nix/store/bwav8kz8b3y471wjsybgzw84mrh4js9-perl-5.28.1/bin",
+ arg=" -I/nix/store/x6yyav38jgr924nkna62q3pkp0dgmzlx-perl5.28.1-File-Slurp-9999.25/lib/perl5/site_perl -I/nix/store/ha8v67sl8dac92r9z07vzr4gv1y9nwqz-perl5.28.1-Net-DBus-1.1.0/lib/perl5/site_perl -I/nix/store/dcrkvnjmwh69ljsvpbdjjdnqgwx90a9d-perl5.28.1-XML-Parser-2.44/lib/perl5/site_perl -I/nix/store/rmji88k2zz7h4zg97385bygcydrf2q8h-perl5.28.1-XML-Twig-3.52/lib/perl5/site_perl")
+# One byte under size, leaving newline visible.
+test(name="one-under", size=SIZE-1)
+# Two bytes under size, leaving newline visible.
+test(name="two-under", size=SIZE-2)
+# Exact size, but trailing whitespace visible instead of newline
+test(name="exact-trunc-whitespace", size=SIZE, arg=" ")
+# Exact size, but trailing space and first arg char visible instead of newline.
+test(name="exact-trunc-arg", size=SIZE, arg=" f")
+# One bute under, with confirmed non-truncated arg since newline now visible.
+test(name="one-under-full-arg", size=SIZE-1, arg=" f")
+# Short read buffer by one byte.
+test(name="one-under-no-nl", size=SIZE-1, newline="")
+# Short read buffer by half buffer size.
+test(name="half-under-no-nl", size=int(SIZE/2), newline="")
+# One byte under with whitespace arg. leaving wenline visible.
+test(name="one-under-trunc-arg", size=SIZE-1, arg=" ")
+# One byte under with whitespace leading. leaving wenline visible.
+test(name="one-under-leading", size=SIZE-1, leading=" ")
+# One byte under with whitespace leading and as arg. leaving newline visible.
+test(name="one-under-leading-trunc-arg", size=SIZE-1, leading=" ", arg=" ")
+# Same as above, but with 2 bytes under
+test(name="two-under-no-nl", size=SIZE-2, newline="")
+test(name="two-under-trunc-arg", size=SIZE-2, arg=" ")
+test(name="two-under-leading", size=SIZE-2, leading=" ")
+test(name="two-under-leading-trunc-arg", size=SIZE-2, leading=" ", arg=" ")
+# Same as above, but with buffer half filled
+test(name="two-under-no-nl", size=int(SIZE/2), newline="")
+test(name="two-under-trunc-arg", size=int(SIZE/2), arg=" ")
+test(name="two-under-leading", size=int(SIZE/2), leading=" ")
+test(name="two-under-lead-trunc-arg", size=int(SIZE/2), leading=" ", arg=" ")
+
+if test_num != tests:
+ raise ValueError("fewer binfmt_script tests than expected! (ran %d, expected %d"
+ % (test_num, tests))
diff --git a/tools/testing/selftests/exec/execveat.c b/tools/testing/selftests/exec/execveat.c
index cbb6efbdb786..67bf7254a48f 100644
--- a/tools/testing/selftests/exec/execveat.c
+++ b/tools/testing/selftests/exec/execveat.c
@@ -5,7 +5,9 @@
* Selftests for execveat(2).
*/
+#ifndef _GNU_SOURCE
#define _GNU_SOURCE /* to get O_PATH, AT_EMPTY_PATH */
+#endif
#include <sys/sendfile.h>
#include <sys/stat.h>
#include <sys/syscall.h>
@@ -311,6 +313,10 @@ static int run_tests(void)
fail += check_execveat_fail(AT_FDCWD, fullname_symlink,
AT_SYMLINK_NOFOLLOW, ELOOP);
+ /* Non-regular file failure */
+ fail += check_execveat_fail(dot_dfd, "pipe", 0, EACCES);
+ unlink("pipe");
+
/* Shell script wrapping executable file: */
/* dfd + path */
fail += check_execveat(subdir_dfd, "../script", 0);
@@ -384,6 +390,8 @@ static void prerequisites(void)
fd = open("subdir.ephemeral/script", O_RDWR|O_CREAT|O_TRUNC, 0755);
write(fd, script, strlen(script));
close(fd);
+
+ mkfifo("pipe", 0755);
}
int main(int argc, char **argv)
diff --git a/tools/testing/selftests/filesystems/.gitignore b/tools/testing/selftests/filesystems/.gitignore
index 8449cf6716ce..f0c0ff20d6cf 100644
--- a/tools/testing/selftests/filesystems/.gitignore
+++ b/tools/testing/selftests/filesystems/.gitignore
@@ -1,2 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0-only
dnotify_test
devpts_pts
diff --git a/tools/testing/selftests/filesystems/binderfs/.gitignore b/tools/testing/selftests/filesystems/binderfs/.gitignore
index 8a5d9bf63dd4..8e5cf9084894 100644
--- a/tools/testing/selftests/filesystems/binderfs/.gitignore
+++ b/tools/testing/selftests/filesystems/binderfs/.gitignore
@@ -1 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
binderfs_test
diff --git a/tools/testing/selftests/filesystems/binderfs/Makefile b/tools/testing/selftests/filesystems/binderfs/Makefile
index 58cb659b56b4..8af25ae96049 100644
--- a/tools/testing/selftests/filesystems/binderfs/Makefile
+++ b/tools/testing/selftests/filesystems/binderfs/Makefile
@@ -1,6 +1,8 @@
# SPDX-License-Identifier: GPL-2.0
-CFLAGS += -I../../../../../usr/include/
+CFLAGS += -I../../../../../usr/include/ -pthread
TEST_GEN_PROGS := binderfs_test
+binderfs_test: binderfs_test.c ../../kselftest.h ../../kselftest_harness.h
+
include ../../lib.mk
diff --git a/tools/testing/selftests/filesystems/binderfs/binderfs_test.c b/tools/testing/selftests/filesystems/binderfs/binderfs_test.c
index 8c2ed962e1c7..8a6b507e34a8 100644
--- a/tools/testing/selftests/filesystems/binderfs/binderfs_test.c
+++ b/tools/testing/selftests/filesystems/binderfs/binderfs_test.c
@@ -3,114 +3,47 @@
#define _GNU_SOURCE
#include <errno.h>
#include <fcntl.h>
+#include <pthread.h>
#include <sched.h>
#include <stdbool.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
+#include <sys/fsuid.h>
#include <sys/ioctl.h>
#include <sys/mount.h>
+#include <sys/socket.h>
#include <sys/stat.h>
+#include <sys/sysinfo.h>
#include <sys/types.h>
+#include <sys/wait.h>
#include <unistd.h>
#include <linux/android/binder.h>
#include <linux/android/binderfs.h>
-#include "../../kselftest.h"
-
-static ssize_t write_nointr(int fd, const void *buf, size_t count)
-{
- ssize_t ret;
-again:
- ret = write(fd, buf, count);
- if (ret < 0 && errno == EINTR)
- goto again;
-
- return ret;
-}
-static void write_to_file(const char *filename, const void *buf, size_t count,
- int allowed_errno)
-{
- int fd, saved_errno;
- ssize_t ret;
+#include "../../kselftest.h"
+#include "../../kselftest_harness.h"
- fd = open(filename, O_WRONLY | O_CLOEXEC);
- if (fd < 0)
- ksft_exit_fail_msg("%s - Failed to open file %s\n",
- strerror(errno), filename);
+#define DEFAULT_THREADS 4
- ret = write_nointr(fd, buf, count);
- if (ret < 0) {
- if (allowed_errno && (errno == allowed_errno)) {
- close(fd);
- return;
- }
+#define PTR_TO_INT(p) ((int)((intptr_t)(p)))
+#define INT_TO_PTR(u) ((void *)((intptr_t)(u)))
- goto on_error;
+#define close_prot_errno_disarm(fd) \
+ if (fd >= 0) { \
+ int _e_ = errno; \
+ close(fd); \
+ errno = _e_; \
+ fd = -EBADF; \
}
- if ((size_t)ret != count)
- goto on_error;
-
- close(fd);
- return;
-
-on_error:
- saved_errno = errno;
- close(fd);
- errno = saved_errno;
-
- if (ret < 0)
- ksft_exit_fail_msg("%s - Failed to write to file %s\n",
- strerror(errno), filename);
-
- ksft_exit_fail_msg("Failed to write to file %s\n", filename);
-}
-
-static void change_to_userns(void)
-{
- int ret;
- uid_t uid;
- gid_t gid;
- /* {g,u}id_map files only allow a max of 4096 bytes written to them */
- char idmap[4096];
-
- uid = getuid();
- gid = getgid();
-
- ret = unshare(CLONE_NEWUSER);
- if (ret < 0)
- ksft_exit_fail_msg("%s - Failed to unshare user namespace\n",
- strerror(errno));
-
- write_to_file("/proc/self/setgroups", "deny", strlen("deny"), ENOENT);
-
- ret = snprintf(idmap, sizeof(idmap), "0 %d 1", uid);
- if (ret < 0 || (size_t)ret >= sizeof(idmap))
- ksft_exit_fail_msg("%s - Failed to prepare uid mapping\n",
- strerror(errno));
-
- write_to_file("/proc/self/uid_map", idmap, strlen(idmap), 0);
-
- ret = snprintf(idmap, sizeof(idmap), "0 %d 1", gid);
- if (ret < 0 || (size_t)ret >= sizeof(idmap))
- ksft_exit_fail_msg("%s - Failed to prepare uid mapping\n",
- strerror(errno));
-
- write_to_file("/proc/self/gid_map", idmap, strlen(idmap), 0);
-
- ret = setgid(0);
- if (ret)
- ksft_exit_fail_msg("%s - Failed to setgid(0)\n",
- strerror(errno));
+#define log_exit(format, ...) \
+ ({ \
+ fprintf(stderr, format "\n", ##__VA_ARGS__); \
+ exit(EXIT_FAILURE); \
+ })
- ret = setuid(0);
- if (ret)
- ksft_exit_fail_msg("%s - Failed to setgid(0)\n",
- strerror(errno));
-}
-
-static void change_to_mountns(void)
+static void change_mountns(void)
{
int ret;
@@ -132,36 +65,31 @@ static void rmdir_protect_errno(const char *dir)
errno = saved_errno;
}
-static void __do_binderfs_test(void)
+static int __do_binderfs_test(void)
{
int fd, ret, saved_errno;
size_t len;
ssize_t wret;
- bool keep = false;
struct binderfs_device device = { 0 };
struct binder_version version = { 0 };
+ char binderfs_mntpt[] = P_tmpdir "/binderfs_XXXXXX",
+ device_path[sizeof(P_tmpdir "/binderfs_XXXXXX/") + BINDERFS_MAX_NAME];
- change_to_mountns();
-
- ret = mkdir("/dev/binderfs", 0755);
- if (ret < 0) {
- if (errno != EEXIST)
- ksft_exit_fail_msg(
- "%s - Failed to create binderfs mountpoint\n",
- strerror(errno));
+ change_mountns();
- keep = true;
- }
+ if (!mkdtemp(binderfs_mntpt))
+ ksft_exit_fail_msg(
+ "%s - Failed to create binderfs mountpoint\n",
+ strerror(errno));
- ret = mount(NULL, "/dev/binderfs", "binder", 0, 0);
+ ret = mount(NULL, binderfs_mntpt, "binder", 0, 0);
if (ret < 0) {
if (errno != ENODEV)
ksft_exit_fail_msg("%s - Failed to mount binderfs\n",
strerror(errno));
- keep ? : rmdir_protect_errno("/dev/binderfs");
- ksft_exit_skip(
- "The Android binderfs filesystem is not available\n");
+ rmdir_protect_errno(binderfs_mntpt);
+ return 1;
}
/* binderfs mount test passed */
@@ -169,7 +97,8 @@ static void __do_binderfs_test(void)
memcpy(device.name, "my-binder", strlen("my-binder"));
- fd = open("/dev/binderfs/binder-control", O_RDONLY | O_CLOEXEC);
+ snprintf(device_path, sizeof(device_path), "%s/binder-control", binderfs_mntpt);
+ fd = open(device_path, O_RDONLY | O_CLOEXEC);
if (fd < 0)
ksft_exit_fail_msg(
"%s - Failed to open binder-control device\n",
@@ -180,7 +109,7 @@ static void __do_binderfs_test(void)
close(fd);
errno = saved_errno;
if (ret < 0) {
- keep ? : rmdir_protect_errno("/dev/binderfs");
+ rmdir_protect_errno(binderfs_mntpt);
ksft_exit_fail_msg(
"%s - Failed to allocate new binder device\n",
strerror(errno));
@@ -193,9 +122,10 @@ static void __do_binderfs_test(void)
/* binder device allocation test passed */
ksft_inc_pass_cnt();
- fd = open("/dev/binderfs/my-binder", O_CLOEXEC | O_RDONLY);
+ snprintf(device_path, sizeof(device_path), "%s/my-binder", binderfs_mntpt);
+ fd = open(device_path, O_CLOEXEC | O_RDONLY);
if (fd < 0) {
- keep ? : rmdir_protect_errno("/dev/binderfs");
+ rmdir_protect_errno(binderfs_mntpt);
ksft_exit_fail_msg("%s - Failed to open my-binder device\n",
strerror(errno));
}
@@ -205,7 +135,7 @@ static void __do_binderfs_test(void)
close(fd);
errno = saved_errno;
if (ret < 0) {
- keep ? : rmdir_protect_errno("/dev/binderfs");
+ rmdir_protect_errno(binderfs_mntpt);
ksft_exit_fail_msg(
"%s - Failed to open perform BINDER_VERSION request\n",
strerror(errno));
@@ -217,9 +147,9 @@ static void __do_binderfs_test(void)
/* binder transaction with binderfs binder device passed */
ksft_inc_pass_cnt();
- ret = unlink("/dev/binderfs/my-binder");
+ ret = unlink(device_path);
if (ret < 0) {
- keep ? : rmdir_protect_errno("/dev/binderfs");
+ rmdir_protect_errno(binderfs_mntpt);
ksft_exit_fail_msg("%s - Failed to delete binder device\n",
strerror(errno));
}
@@ -227,12 +157,13 @@ static void __do_binderfs_test(void)
/* binder device removal passed */
ksft_inc_pass_cnt();
- ret = unlink("/dev/binderfs/binder-control");
+ snprintf(device_path, sizeof(device_path), "%s/binder-control", binderfs_mntpt);
+ ret = unlink(device_path);
if (!ret) {
- keep ? : rmdir_protect_errno("/dev/binderfs");
+ rmdir_protect_errno(binderfs_mntpt);
ksft_exit_fail_msg("Managed to delete binder-control device\n");
} else if (errno != EPERM) {
- keep ? : rmdir_protect_errno("/dev/binderfs");
+ rmdir_protect_errno(binderfs_mntpt);
ksft_exit_fail_msg(
"%s - Failed to delete binder-control device but exited with unexpected error code\n",
strerror(errno));
@@ -242,34 +173,341 @@ static void __do_binderfs_test(void)
ksft_inc_xfail_cnt();
on_error:
- ret = umount2("/dev/binderfs", MNT_DETACH);
- keep ?: rmdir_protect_errno("/dev/binderfs");
+ ret = umount2(binderfs_mntpt, MNT_DETACH);
+ rmdir_protect_errno(binderfs_mntpt);
if (ret < 0)
ksft_exit_fail_msg("%s - Failed to unmount binderfs\n",
strerror(errno));
/* binderfs unmount test passed */
ksft_inc_pass_cnt();
+ return 0;
}
-static void binderfs_test_privileged()
+static int wait_for_pid(pid_t pid)
{
- if (geteuid() != 0)
- ksft_print_msg(
- "Tests are not run as root. Skipping privileged tests\n");
- else
- __do_binderfs_test();
+ int status, ret;
+
+again:
+ ret = waitpid(pid, &status, 0);
+ if (ret == -1) {
+ if (errno == EINTR)
+ goto again;
+
+ return -1;
+ }
+
+ if (!WIFEXITED(status))
+ return -1;
+
+ return WEXITSTATUS(status);
+}
+
+static int setid_userns_root(void)
+{
+ if (setuid(0))
+ return -1;
+ if (setgid(0))
+ return -1;
+
+ setfsuid(0);
+ setfsgid(0);
+
+ return 0;
+}
+
+enum idmap_type {
+ UID_MAP,
+ GID_MAP,
+};
+
+static ssize_t read_nointr(int fd, void *buf, size_t count)
+{
+ ssize_t ret;
+again:
+ ret = read(fd, buf, count);
+ if (ret < 0 && errno == EINTR)
+ goto again;
+
+ return ret;
+}
+
+static ssize_t write_nointr(int fd, const void *buf, size_t count)
+{
+ ssize_t ret;
+again:
+ ret = write(fd, buf, count);
+ if (ret < 0 && errno == EINTR)
+ goto again;
+
+ return ret;
+}
+
+static int write_id_mapping(enum idmap_type type, pid_t pid, const char *buf,
+ size_t buf_size)
+{
+ int fd;
+ int ret;
+ char path[4096];
+
+ if (type == GID_MAP) {
+ int setgroups_fd;
+
+ snprintf(path, sizeof(path), "/proc/%d/setgroups", pid);
+ setgroups_fd = open(path, O_WRONLY | O_CLOEXEC | O_NOFOLLOW);
+ if (setgroups_fd < 0 && errno != ENOENT)
+ return -1;
+
+ if (setgroups_fd >= 0) {
+ ret = write_nointr(setgroups_fd, "deny", sizeof("deny") - 1);
+ close_prot_errno_disarm(setgroups_fd);
+ if (ret != sizeof("deny") - 1)
+ return -1;
+ }
+ }
+
+ switch (type) {
+ case UID_MAP:
+ ret = snprintf(path, sizeof(path), "/proc/%d/uid_map", pid);
+ break;
+ case GID_MAP:
+ ret = snprintf(path, sizeof(path), "/proc/%d/gid_map", pid);
+ break;
+ default:
+ return -1;
+ }
+ if (ret < 0 || ret >= sizeof(path))
+ return -E2BIG;
+
+ fd = open(path, O_WRONLY | O_CLOEXEC | O_NOFOLLOW);
+ if (fd < 0)
+ return -1;
+
+ ret = write_nointr(fd, buf, buf_size);
+ close_prot_errno_disarm(fd);
+ if (ret != buf_size)
+ return -1;
+
+ return 0;
+}
+
+static void change_userns(int syncfds[2])
+{
+ int ret;
+ char buf;
+
+ close_prot_errno_disarm(syncfds[1]);
+
+ ret = unshare(CLONE_NEWUSER);
+ if (ret < 0)
+ ksft_exit_fail_msg("%s - Failed to unshare user namespace\n",
+ strerror(errno));
+
+ ret = write_nointr(syncfds[0], "1", 1);
+ if (ret != 1)
+ ksft_exit_fail_msg("write_nointr() failed\n");
+
+ ret = read_nointr(syncfds[0], &buf, 1);
+ if (ret != 1)
+ ksft_exit_fail_msg("read_nointr() failed\n");
+
+ close_prot_errno_disarm(syncfds[0]);
+
+ if (setid_userns_root())
+ ksft_exit_fail_msg("setid_userns_root() failed");
+}
+
+static void change_idmaps(int syncfds[2], pid_t pid)
+{
+ int ret;
+ char buf;
+ char id_map[4096];
+
+ close_prot_errno_disarm(syncfds[0]);
+
+ ret = read_nointr(syncfds[1], &buf, 1);
+ if (ret != 1)
+ ksft_exit_fail_msg("read_nointr() failed\n");
+
+ snprintf(id_map, sizeof(id_map), "0 %d 1\n", getuid());
+ ret = write_id_mapping(UID_MAP, pid, id_map, strlen(id_map));
+ if (ret)
+ ksft_exit_fail_msg("write_id_mapping(UID_MAP) failed");
+
+ snprintf(id_map, sizeof(id_map), "0 %d 1\n", getgid());
+ ret = write_id_mapping(GID_MAP, pid, id_map, strlen(id_map));
+ if (ret)
+ ksft_exit_fail_msg("write_id_mapping(GID_MAP) failed");
+
+ ret = write_nointr(syncfds[1], "1", 1);
+ if (ret != 1)
+ ksft_exit_fail_msg("write_nointr() failed");
+
+ close_prot_errno_disarm(syncfds[1]);
}
-static void binderfs_test_unprivileged()
+static void *binder_version_thread(void *data)
{
- change_to_userns();
- __do_binderfs_test();
+ int fd = PTR_TO_INT(data);
+ struct binder_version version = { 0 };
+ int ret;
+
+ ret = ioctl(fd, BINDER_VERSION, &version);
+ if (ret < 0)
+ ksft_print_msg("%s - Failed to open perform BINDER_VERSION request\n", strerror(errno));
+
+ pthread_exit(data);
}
-int main(int argc, char *argv[])
+/*
+ * Regression test:
+ * 2669b8b0c798 ("binder: prevent UAF for binderfs devices")
+ * f0fe2c0f050d ("binder: prevent UAF for binderfs devices II")
+ * 211b64e4b5b6 ("binderfs: use refcount for binder control devices too")
+ */
+TEST(binderfs_stress)
{
- binderfs_test_privileged();
- binderfs_test_unprivileged();
- ksft_exit_pass();
+ int fds[1000];
+ int syncfds[2];
+ pid_t pid;
+ int fd, ret;
+ size_t len;
+ struct binderfs_device device = { 0 };
+ char binderfs_mntpt[] = P_tmpdir "/binderfs_XXXXXX",
+ device_path[sizeof(P_tmpdir "/binderfs_XXXXXX/") + BINDERFS_MAX_NAME];
+
+ ret = socketpair(PF_LOCAL, SOCK_STREAM | SOCK_CLOEXEC, 0, syncfds);
+ if (ret < 0)
+ ksft_exit_fail_msg("%s - Failed to create socket pair", strerror(errno));
+
+ pid = fork();
+ if (pid < 0) {
+ close_prot_errno_disarm(syncfds[0]);
+ close_prot_errno_disarm(syncfds[1]);
+ ksft_exit_fail_msg("%s - Failed to fork", strerror(errno));
+ }
+
+ if (pid == 0) {
+ int i, j, k, nthreads;
+ pthread_attr_t attr;
+ pthread_t threads[DEFAULT_THREADS];
+ change_userns(syncfds);
+ change_mountns();
+
+ if (!mkdtemp(binderfs_mntpt))
+ log_exit("%s - Failed to create binderfs mountpoint\n",
+ strerror(errno));
+
+ ret = mount(NULL, binderfs_mntpt, "binder", 0, 0);
+ if (ret < 0)
+ log_exit("%s - Failed to mount binderfs\n", strerror(errno));
+
+ for (int i = 0; i < ARRAY_SIZE(fds); i++) {
+
+ snprintf(device_path, sizeof(device_path),
+ "%s/binder-control", binderfs_mntpt);
+ fd = open(device_path, O_RDONLY | O_CLOEXEC);
+ if (fd < 0)
+ log_exit("%s - Failed to open binder-control device\n", strerror(errno));
+
+ memset(&device, 0, sizeof(device));
+ snprintf(device.name, sizeof(device.name), "%d", i);
+ ret = ioctl(fd, BINDER_CTL_ADD, &device);
+ close_prot_errno_disarm(fd);
+ if (ret < 0)
+ log_exit("%s - Failed to allocate new binder device\n", strerror(errno));
+
+ snprintf(device_path, sizeof(device_path), "%s/%d",
+ binderfs_mntpt, i);
+ fds[i] = open(device_path, O_RDONLY | O_CLOEXEC);
+ if (fds[i] < 0)
+ log_exit("%s - Failed to open binder device\n", strerror(errno));
+ }
+
+ ret = umount2(binderfs_mntpt, MNT_DETACH);
+ rmdir_protect_errno(binderfs_mntpt);
+ if (ret < 0)
+ log_exit("%s - Failed to unmount binderfs\n", strerror(errno));
+
+ nthreads = get_nprocs_conf();
+ if (nthreads > DEFAULT_THREADS)
+ nthreads = DEFAULT_THREADS;
+
+ pthread_attr_init(&attr);
+ for (k = 0; k < ARRAY_SIZE(fds); k++) {
+ for (i = 0; i < nthreads; i++) {
+ ret = pthread_create(&threads[i], &attr, binder_version_thread, INT_TO_PTR(fds[k]));
+ if (ret) {
+ ksft_print_msg("%s - Failed to create thread %d\n", strerror(errno), i);
+ break;
+ }
+ }
+
+ for (j = 0; j < i; j++) {
+ void *fdptr = NULL;
+
+ ret = pthread_join(threads[j], &fdptr);
+ if (ret)
+ ksft_print_msg("%s - Failed to join thread %d for fd %d\n", strerror(errno), j, PTR_TO_INT(fdptr));
+ }
+ }
+ pthread_attr_destroy(&attr);
+
+ for (k = 0; k < ARRAY_SIZE(fds); k++)
+ close(fds[k]);
+
+ exit(EXIT_SUCCESS);
+ }
+
+ change_idmaps(syncfds, pid);
+
+ ret = wait_for_pid(pid);
+ if (ret)
+ ksft_exit_fail_msg("wait_for_pid() failed");
}
+
+TEST(binderfs_test_privileged)
+{
+ if (geteuid() != 0)
+ XFAIL(return, "Tests are not run as root. Skipping privileged tests");
+
+ if (__do_binderfs_test() == 1)
+ XFAIL(return, "The Android binderfs filesystem is not available");
+}
+
+TEST(binderfs_test_unprivileged)
+{
+ int ret;
+ int syncfds[2];
+ pid_t pid;
+
+ ret = socketpair(PF_LOCAL, SOCK_STREAM | SOCK_CLOEXEC, 0, syncfds);
+ if (ret < 0)
+ ksft_exit_fail_msg("%s - Failed to create socket pair", strerror(errno));
+
+ pid = fork();
+ if (pid < 0) {
+ close_prot_errno_disarm(syncfds[0]);
+ close_prot_errno_disarm(syncfds[1]);
+ ksft_exit_fail_msg("%s - Failed to fork", strerror(errno));
+ }
+
+ if (pid == 0) {
+ change_userns(syncfds);
+ if (__do_binderfs_test() == 1)
+ exit(2);
+ exit(EXIT_SUCCESS);
+ }
+
+ change_idmaps(syncfds, pid);
+
+ ret = wait_for_pid(pid);
+ if (ret) {
+ if (ret == 2)
+ XFAIL(return, "The Android binderfs filesystem is not available");
+ else
+ ksft_exit_fail_msg("wait_for_pid() failed");
+ }
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/filesystems/epoll/.gitignore b/tools/testing/selftests/filesystems/epoll/.gitignore
index 9ae8db44ec14..9090157258b1 100644
--- a/tools/testing/selftests/filesystems/epoll/.gitignore
+++ b/tools/testing/selftests/filesystems/epoll/.gitignore
@@ -1 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
epoll_wakeup_test
diff --git a/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c b/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c
index 37a04dab56f0..d979ff14775a 100644
--- a/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c
+++ b/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c
@@ -3,17 +3,19 @@
#define _GNU_SOURCE
#include <poll.h>
#include <unistd.h>
+#include <assert.h>
#include <signal.h>
#include <pthread.h>
#include <sys/epoll.h>
#include <sys/socket.h>
+#include <sys/eventfd.h>
#include "../../kselftest_harness.h"
struct epoll_mtcontext
{
int efd[3];
int sfd[4];
- int count;
+ volatile int count;
pthread_t main;
pthread_t waiter;
@@ -3071,4 +3073,213 @@ TEST(epoll58)
close(ctx.sfd[3]);
}
+static void *epoll59_thread(void *ctx_)
+{
+ struct epoll_mtcontext *ctx = ctx_;
+ struct epoll_event e;
+ int i;
+
+ for (i = 0; i < 100000; i++) {
+ while (ctx->count == 0)
+ ;
+
+ e.events = EPOLLIN | EPOLLERR | EPOLLET;
+ epoll_ctl(ctx->efd[0], EPOLL_CTL_MOD, ctx->sfd[0], &e);
+ ctx->count = 0;
+ }
+
+ return NULL;
+}
+
+/*
+ * t0
+ * (p) \
+ * e0
+ * (et) /
+ * e0
+ *
+ * Based on https://bugzilla.kernel.org/show_bug.cgi?id=205933
+ */
+TEST(epoll59)
+{
+ pthread_t emitter;
+ struct pollfd pfd;
+ struct epoll_event e;
+ struct epoll_mtcontext ctx = { 0 };
+ int i, ret;
+
+ signal(SIGUSR1, signal_handler);
+
+ ctx.efd[0] = epoll_create1(0);
+ ASSERT_GE(ctx.efd[0], 0);
+
+ ctx.sfd[0] = eventfd(1, 0);
+ ASSERT_GE(ctx.sfd[0], 0);
+
+ e.events = EPOLLIN | EPOLLERR | EPOLLET;
+ ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0);
+
+ ASSERT_EQ(pthread_create(&emitter, NULL, epoll59_thread, &ctx), 0);
+
+ for (i = 0; i < 100000; i++) {
+ ret = epoll_wait(ctx.efd[0], &e, 1, 1000);
+ ASSERT_GT(ret, 0);
+
+ while (ctx.count != 0)
+ ;
+ ctx.count = 1;
+ }
+ if (pthread_tryjoin_np(emitter, NULL) < 0) {
+ pthread_kill(emitter, SIGUSR1);
+ pthread_join(emitter, NULL);
+ }
+ close(ctx.efd[0]);
+ close(ctx.sfd[0]);
+}
+
+enum {
+ EPOLL60_EVENTS_NR = 10,
+};
+
+struct epoll60_ctx {
+ volatile int stopped;
+ int ready;
+ int waiters;
+ int epfd;
+ int evfd[EPOLL60_EVENTS_NR];
+};
+
+static void *epoll60_wait_thread(void *ctx_)
+{
+ struct epoll60_ctx *ctx = ctx_;
+ struct epoll_event e;
+ sigset_t sigmask;
+ uint64_t v;
+ int ret;
+
+ /* Block SIGUSR1 */
+ sigemptyset(&sigmask);
+ sigaddset(&sigmask, SIGUSR1);
+ sigprocmask(SIG_SETMASK, &sigmask, NULL);
+
+ /* Prepare empty mask for epoll_pwait() */
+ sigemptyset(&sigmask);
+
+ while (!ctx->stopped) {
+ /* Mark we are ready */
+ __atomic_fetch_add(&ctx->ready, 1, __ATOMIC_ACQUIRE);
+
+ /* Start when all are ready */
+ while (__atomic_load_n(&ctx->ready, __ATOMIC_ACQUIRE) &&
+ !ctx->stopped);
+
+ /* Account this waiter */
+ __atomic_fetch_add(&ctx->waiters, 1, __ATOMIC_ACQUIRE);
+
+ ret = epoll_pwait(ctx->epfd, &e, 1, 2000, &sigmask);
+ if (ret != 1) {
+ /* We expect only signal delivery on stop */
+ assert(ret < 0 && errno == EINTR && "Lost wakeup!\n");
+ assert(ctx->stopped);
+ break;
+ }
+
+ ret = read(e.data.fd, &v, sizeof(v));
+ /* Since we are on ET mode, thus each thread gets its own fd. */
+ assert(ret == sizeof(v));
+
+ __atomic_fetch_sub(&ctx->waiters, 1, __ATOMIC_RELEASE);
+ }
+
+ return NULL;
+}
+
+static inline unsigned long long msecs(void)
+{
+ struct timespec ts;
+ unsigned long long msecs;
+
+ clock_gettime(CLOCK_REALTIME, &ts);
+ msecs = ts.tv_sec * 1000ull;
+ msecs += ts.tv_nsec / 1000000ull;
+
+ return msecs;
+}
+
+static inline int count_waiters(struct epoll60_ctx *ctx)
+{
+ return __atomic_load_n(&ctx->waiters, __ATOMIC_ACQUIRE);
+}
+
+TEST(epoll60)
+{
+ struct epoll60_ctx ctx = { 0 };
+ pthread_t waiters[ARRAY_SIZE(ctx.evfd)];
+ struct epoll_event e;
+ int i, n, ret;
+
+ signal(SIGUSR1, signal_handler);
+
+ ctx.epfd = epoll_create1(0);
+ ASSERT_GE(ctx.epfd, 0);
+
+ /* Create event fds */
+ for (i = 0; i < ARRAY_SIZE(ctx.evfd); i++) {
+ ctx.evfd[i] = eventfd(0, EFD_NONBLOCK);
+ ASSERT_GE(ctx.evfd[i], 0);
+
+ e.events = EPOLLIN | EPOLLET;
+ e.data.fd = ctx.evfd[i];
+ ASSERT_EQ(epoll_ctl(ctx.epfd, EPOLL_CTL_ADD, ctx.evfd[i], &e), 0);
+ }
+
+ /* Create waiter threads */
+ for (i = 0; i < ARRAY_SIZE(waiters); i++)
+ ASSERT_EQ(pthread_create(&waiters[i], NULL,
+ epoll60_wait_thread, &ctx), 0);
+
+ for (i = 0; i < 300; i++) {
+ uint64_t v = 1, ms;
+
+ /* Wait for all to be ready */
+ while (__atomic_load_n(&ctx.ready, __ATOMIC_ACQUIRE) !=
+ ARRAY_SIZE(ctx.evfd))
+ ;
+
+ /* Steady, go */
+ __atomic_fetch_sub(&ctx.ready, ARRAY_SIZE(ctx.evfd),
+ __ATOMIC_ACQUIRE);
+
+ /* Wait all have gone to kernel */
+ while (count_waiters(&ctx) != ARRAY_SIZE(ctx.evfd))
+ ;
+
+ /* 1ms should be enough to schedule away */
+ usleep(1000);
+
+ /* Quickly signal all handles at once */
+ for (n = 0; n < ARRAY_SIZE(ctx.evfd); n++) {
+ ret = write(ctx.evfd[n], &v, sizeof(v));
+ ASSERT_EQ(ret, sizeof(v));
+ }
+
+ /* Busy loop for 1s and wait for all waiters to wake up */
+ ms = msecs();
+ while (count_waiters(&ctx) && msecs() < ms + 1000)
+ ;
+
+ ASSERT_EQ(count_waiters(&ctx), 0);
+ }
+ ctx.stopped = 1;
+ /* Stop waiters */
+ for (i = 0; i < ARRAY_SIZE(waiters); i++)
+ ret = pthread_kill(waiters[i], SIGUSR1);
+ for (i = 0; i < ARRAY_SIZE(waiters); i++)
+ pthread_join(waiters[i], NULL);
+
+ for (i = 0; i < ARRAY_SIZE(waiters); i++)
+ close(ctx.evfd[i]);
+ close(ctx.epfd);
+}
+
TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/firmware/Makefile b/tools/testing/selftests/firmware/Makefile
index 012b2cf69c11..40211cd8f0e6 100644
--- a/tools/testing/selftests/firmware/Makefile
+++ b/tools/testing/selftests/firmware/Makefile
@@ -1,13 +1,10 @@
# SPDX-License-Identifier: GPL-2.0-only
# Makefile for firmware loading selftests
-
-# No binaries, but make sure arg-less "make" doesn't trigger "run_tests"
-all:
+CFLAGS = -Wall \
+ -O2
TEST_PROGS := fw_run_tests.sh
TEST_FILES := fw_fallback.sh fw_filesystem.sh fw_lib.sh
+TEST_GEN_FILES := fw_namespace
include ../lib.mk
-
-# Nothing to clean up.
-clean:
diff --git a/tools/testing/selftests/firmware/fw_filesystem.sh b/tools/testing/selftests/firmware/fw_filesystem.sh
index 56894477c8bd..fcc281373b4d 100755
--- a/tools/testing/selftests/firmware/fw_filesystem.sh
+++ b/tools/testing/selftests/firmware/fw_filesystem.sh
@@ -86,6 +86,29 @@ else
fi
fi
+# Try platform (EFI embedded fw) loading too
+if [ ! -e "$DIR"/trigger_request_platform ]; then
+ echo "$0: firmware loading: platform trigger not present, ignoring test" >&2
+else
+ if printf '\000' >"$DIR"/trigger_request_platform 2> /dev/null; then
+ echo "$0: empty filename should not succeed (platform)" >&2
+ exit 1
+ fi
+
+ # Note we echo a non-existing name, since files on the file-system
+ # are preferred over firmware embedded inside the platform's firmware
+ # The test adds a fake entry with the requested name to the platform's
+ # fw list, so the name does not matter as long as it does not exist
+ if ! echo -n "nope-$NAME" >"$DIR"/trigger_request_platform ; then
+ echo "$0: could not trigger request platform" >&2
+ exit 1
+ fi
+
+ # The test verifies itself that the loaded firmware contents matches
+ # the contents for the fake platform fw entry it added.
+ echo "$0: platform loading works"
+fi
+
### Batched requests tests
test_config_present()
{
diff --git a/tools/testing/selftests/firmware/fw_namespace.c b/tools/testing/selftests/firmware/fw_namespace.c
new file mode 100644
index 000000000000..5ebc1aec7923
--- /dev/null
+++ b/tools/testing/selftests/firmware/fw_namespace.c
@@ -0,0 +1,151 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Test triggering of loading of firmware from different mount
+ * namespaces. Expect firmware to be always loaded from the mount
+ * namespace of PID 1. */
+#define _GNU_SOURCE
+#include <errno.h>
+#include <fcntl.h>
+#include <sched.h>
+#include <stdarg.h>
+#include <stdbool.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>
+
+#ifndef CLONE_NEWNS
+# define CLONE_NEWNS 0x00020000
+#endif
+
+static char *fw_path = NULL;
+
+static void die(char *fmt, ...)
+{
+ va_list ap;
+
+ va_start(ap, fmt);
+ vfprintf(stderr, fmt, ap);
+ va_end(ap);
+ if (fw_path)
+ unlink(fw_path);
+ umount("/lib/firmware");
+ exit(EXIT_FAILURE);
+}
+
+static void trigger_fw(const char *fw_name, const char *sys_path)
+{
+ int fd;
+
+ fd = open(sys_path, O_WRONLY);
+ if (fd < 0)
+ die("open failed: %s\n",
+ strerror(errno));
+ if (write(fd, fw_name, strlen(fw_name)) != strlen(fw_name))
+ exit(EXIT_FAILURE);
+ close(fd);
+}
+
+static void setup_fw(const char *fw_path)
+{
+ int fd;
+ const char fw[] = "ABCD0123";
+
+ fd = open(fw_path, O_WRONLY | O_CREAT, 0600);
+ if (fd < 0)
+ die("open failed: %s\n",
+ strerror(errno));
+ if (write(fd, fw, sizeof(fw) -1) != sizeof(fw) -1)
+ die("write failed: %s\n",
+ strerror(errno));
+ close(fd);
+}
+
+static bool test_fw_in_ns(const char *fw_name, const char *sys_path, bool block_fw_in_parent_ns)
+{
+ pid_t child;
+
+ if (block_fw_in_parent_ns)
+ if (mount("test", "/lib/firmware", "tmpfs", MS_RDONLY, NULL) == -1)
+ die("blocking firmware in parent ns failed\n");
+
+ child = fork();
+ if (child == -1) {
+ die("fork failed: %s\n",
+ strerror(errno));
+ }
+ if (child != 0) { /* parent */
+ pid_t pid;
+ int status;
+
+ pid = waitpid(child, &status, 0);
+ if (pid == -1) {
+ die("waitpid failed: %s\n",
+ strerror(errno));
+ }
+ if (pid != child) {
+ die("waited for %d got %d\n",
+ child, pid);
+ }
+ if (!WIFEXITED(status)) {
+ die("child did not terminate cleanly\n");
+ }
+ if (block_fw_in_parent_ns)
+ umount("/lib/firmware");
+ return WEXITSTATUS(status) == EXIT_SUCCESS ? true : false;
+ }
+
+ if (unshare(CLONE_NEWNS) != 0) {
+ die("unshare(CLONE_NEWNS) failed: %s\n",
+ strerror(errno));
+ }
+ if (mount(NULL, "/", NULL, MS_SLAVE|MS_REC, NULL) == -1)
+ die("remount root in child ns failed\n");
+
+ if (!block_fw_in_parent_ns) {
+ if (mount("test", "/lib/firmware", "tmpfs", MS_RDONLY, NULL) == -1)
+ die("blocking firmware in child ns failed\n");
+ } else
+ umount("/lib/firmware");
+
+ trigger_fw(fw_name, sys_path);
+
+ exit(EXIT_SUCCESS);
+}
+
+int main(int argc, char **argv)
+{
+ const char *fw_name = "test-firmware.bin";
+ char *sys_path;
+ if (argc != 2)
+ die("usage: %s sys_path\n", argv[0]);
+
+ /* Mount tmpfs to /lib/firmware so we don't have to assume
+ that it is writable for us.*/
+ if (mount("test", "/lib/firmware", "tmpfs", 0, NULL) == -1)
+ die("mounting tmpfs to /lib/firmware failed\n");
+
+ sys_path = argv[1];
+ asprintf(&fw_path, "/lib/firmware/%s", fw_name);
+
+ setup_fw(fw_path);
+
+ setvbuf(stdout, NULL, _IONBF, 0);
+ /* Positive case: firmware in PID1 mount namespace */
+ printf("Testing with firmware in parent namespace (assumed to be same file system as PID1)\n");
+ if (!test_fw_in_ns(fw_name, sys_path, false))
+ die("error: failed to access firmware\n");
+
+ /* Negative case: firmware in child mount namespace, expected to fail */
+ printf("Testing with firmware in child namespace\n");
+ if (test_fw_in_ns(fw_name, sys_path, true))
+ die("error: firmware access did not fail\n");
+
+ unlink(fw_path);
+ free(fw_path);
+ umount("/lib/firmware");
+ exit(EXIT_SUCCESS);
+}
diff --git a/tools/testing/selftests/firmware/fw_run_tests.sh b/tools/testing/selftests/firmware/fw_run_tests.sh
index 8e14d555c197..777377078d5e 100755
--- a/tools/testing/selftests/firmware/fw_run_tests.sh
+++ b/tools/testing/selftests/firmware/fw_run_tests.sh
@@ -61,6 +61,10 @@ run_test_config_0003()
check_mods
check_setup
+echo "Running namespace test: "
+$TEST_DIR/fw_namespace $DIR/trigger_request
+echo "OK"
+
if [ -f $FW_FORCE_SYSFS_FALLBACK ]; then
run_test_config_0001
run_test_config_0002
diff --git a/tools/testing/selftests/ftrace/.gitignore b/tools/testing/selftests/ftrace/.gitignore
index 98d8a5a63049..2659417cb2c7 100644
--- a/tools/testing/selftests/ftrace/.gitignore
+++ b/tools/testing/selftests/ftrace/.gitignore
@@ -1 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
logs
diff --git a/tools/testing/selftests/ftrace/config b/tools/testing/selftests/ftrace/config
index c2c8de4fafff..e59d985eeff0 100644
--- a/tools/testing/selftests/ftrace/config
+++ b/tools/testing/selftests/ftrace/config
@@ -11,5 +11,6 @@ CONFIG_PREEMPTIRQ_DELAY_TEST=m
CONFIG_MODULES=y
CONFIG_MODULE_UNLOAD=y
CONFIG_SAMPLES=y
+CONFIG_SAMPLE_FTRACE_DIRECT=m
CONFIG_SAMPLE_TRACE_PRINTK=m
CONFIG_KALLSYMS_ALL=y
diff --git a/tools/testing/selftests/ftrace/ftracetest b/tools/testing/selftests/ftrace/ftracetest
index 063ecb290a5a..a4605b5ee66d 100755
--- a/tools/testing/selftests/ftrace/ftracetest
+++ b/tools/testing/selftests/ftrace/ftracetest
@@ -17,6 +17,7 @@ echo " -v|--verbose Increase verbosity of test messages"
echo " -vv Alias of -v -v (Show all results in stdout)"
echo " -vvv Alias of -v -v -v (Show all commands immediately)"
echo " --fail-unsupported Treat UNSUPPORTED as a failure"
+echo " --fail-unresolved Treat UNRESOLVED as a failure"
echo " -d|--debug Debug mode (trace all shell commands)"
echo " -l|--logdir <dir> Save logs on the <dir>"
echo " If <dir> is -, all logs output in console only"
@@ -29,8 +30,25 @@ err_ret=1
# kselftest skip code is 4
err_skip=4
+# cgroup RT scheduling prevents chrt commands from succeeding, which
+# induces failures in test wakeup tests. Disable for the duration of
+# the tests.
+
+readonly sched_rt_runtime=/proc/sys/kernel/sched_rt_runtime_us
+
+sched_rt_runtime_orig=$(cat $sched_rt_runtime)
+
+setup() {
+ echo -1 > $sched_rt_runtime
+}
+
+cleanup() {
+ echo $sched_rt_runtime_orig > $sched_rt_runtime
+}
+
errexit() { # message
echo "Error: $1" 1>&2
+ cleanup
exit $err_ret
}
@@ -39,6 +57,8 @@ if [ `id -u` -ne 0 ]; then
errexit "this must be run by root user"
fi
+setup
+
# Utilities
absdir() { # file_path
(cd `dirname $1`; pwd)
@@ -93,6 +113,10 @@ parse_opts() { # opts
UNSUPPORTED_RESULT=1
shift 1
;;
+ --fail-unresolved)
+ UNRESOLVED_RESULT=1
+ shift 1
+ ;;
--logdir|-l)
LOG_DIR=$2
shift 2
@@ -157,6 +181,7 @@ KEEP_LOG=0
DEBUG=0
VERBOSE=0
UNSUPPORTED_RESULT=0
+UNRESOLVED_RESULT=0
STOP_FAILURE=0
# Parse command-line options
parse_opts $*
@@ -235,6 +260,7 @@ TOTAL_RESULT=0
INSTANCE=
CASENO=0
+
testcase() { # testfile
CASENO=$((CASENO+1))
desc=`grep "^#[ \t]*description:" $1 | cut -f2 -d:`
@@ -260,7 +286,7 @@ eval_result() { # sigval
$UNRESOLVED)
prlog " [${color_blue}UNRESOLVED${color_reset}]"
UNRESOLVED_CASES="$UNRESOLVED_CASES $CASENO"
- return 1 # this is a kind of bug.. something happened.
+ return $UNRESOLVED_RESULT # depends on use case
;;
$UNTESTED)
prlog " [${color_blue}UNTESTED${color_reset}]"
@@ -273,7 +299,7 @@ eval_result() { # sigval
return $UNSUPPORTED_RESULT # depends on use case
;;
$XFAIL)
- prlog " [${color_red}XFAIL${color_reset}]"
+ prlog " [${color_green}XFAIL${color_reset}]"
XFAILED_CASES="$XFAILED_CASES $CASENO"
return 0
;;
@@ -406,5 +432,7 @@ prlog "# of unsupported: " `echo $UNSUPPORTED_CASES | wc -w`
prlog "# of xfailed: " `echo $XFAILED_CASES | wc -w`
prlog "# of undefined(test bug): " `echo $UNDEFINED_CASES | wc -w`
+cleanup
+
# if no error, return 0
exit $TOTAL_RESULT
diff --git a/tools/testing/selftests/ftrace/test.d/event/event-no-pid.tc b/tools/testing/selftests/ftrace/test.d/event/event-no-pid.tc
new file mode 100644
index 000000000000..f0f366f18d0c
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/event/event-no-pid.tc
@@ -0,0 +1,125 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: event tracing - restricts events based on pid notrace filtering
+# flags: instance
+
+do_reset() {
+ echo > set_event
+ echo > set_event_pid
+ echo > set_event_notrace_pid
+ echo 0 > options/event-fork
+ echo 0 > events/enable
+ clear_trace
+ echo 1 > tracing_on
+}
+
+fail() { #msg
+ cat trace
+ do_reset
+ echo $1
+ exit_fail
+}
+
+count_pid() {
+ pid=$@
+ cat trace | grep -v '^#' | sed -e 's/[^-]*-\([0-9]*\).*/\1/' | grep $pid | wc -l
+}
+
+count_no_pid() {
+ pid=$1
+ cat trace | grep -v '^#' | sed -e 's/[^-]*-\([0-9]*\).*/\1/' | grep -v $pid | wc -l
+}
+
+enable_system() {
+ system=$1
+
+ if [ -d events/$system ]; then
+ echo 1 > events/$system/enable
+ fi
+}
+
+enable_events() {
+ echo 0 > tracing_on
+ # Enable common groups of events, as all events can allow for
+ # events to be traced via scheduling that we don't care to test.
+ enable_system syscalls
+ enable_system rcu
+ enable_system block
+ enable_system exceptions
+ enable_system irq
+ enable_system net
+ enable_system power
+ enable_system signal
+ enable_system sock
+ enable_system timer
+ enable_system thermal
+ echo 1 > tracing_on
+}
+
+if [ ! -f set_event -o ! -d events/sched ]; then
+ echo "event tracing is not supported"
+ exit_unsupported
+fi
+
+if [ ! -f set_event_pid -o ! -f set_event_notrace_pid ]; then
+ echo "event pid notrace filtering is not supported"
+ exit_unsupported
+fi
+
+echo 0 > options/event-fork
+
+do_reset
+
+read mypid rest < /proc/self/stat
+
+echo $mypid > set_event_notrace_pid
+grep -q $mypid set_event_notrace_pid
+
+enable_events
+
+yield
+
+echo 0 > tracing_on
+
+cnt=`count_pid $mypid`
+if [ $cnt -ne 0 ]; then
+ fail "Filtered out task has events"
+fi
+
+cnt=`count_no_pid $mypid`
+if [ $cnt -eq 0 ]; then
+ fail "No other events were recorded"
+fi
+
+do_reset
+
+echo $mypid > set_event_notrace_pid
+echo 1 > options/event-fork
+
+enable_events
+
+yield &
+child=$!
+echo "child = $child"
+wait $child
+
+echo 0 > tracing_on
+
+cnt=`count_pid $mypid`
+if [ $cnt -ne 0 ]; then
+ fail "Filtered out task has events"
+fi
+
+cnt=`count_pid $child`
+if [ $cnt -ne 0 ]; then
+ fail "Child of filtered out taskhas events"
+fi
+
+cnt=`count_no_pid $mypid`
+if [ $cnt -eq 0 ]; then
+ fail "No other events were recorded"
+fi
+
+do_reset
+
+exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter-stack.tc b/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter-stack.tc
index aefab0c66d54..f59853857ad2 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter-stack.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter-stack.tc
@@ -10,10 +10,7 @@ if ! grep -q function_graph available_tracers; then
exit_unsupported
fi
-if [ ! -f set_ftrace_filter ]; then
- echo "set_ftrace_filter not found? Is dynamic ftrace not set?"
- exit_unsupported
-fi
+check_filter_file set_ftrace_filter
do_reset() {
if [ -e /proc/sys/kernel/stack_tracer_enabled ]; then
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter.tc b/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter.tc
index c8a5209f2119..d610f47edd90 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter.tc
@@ -9,6 +9,8 @@ if ! grep -q function_graph available_tracers; then
exit_unsupported
fi
+check_filter_file set_ftrace_filter
+
fail() { # msg
echo $1
exit_fail
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc
index f4e92afab14b..28936f434ee5 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc
@@ -9,6 +9,8 @@ if ! grep -q function available_tracers; then
exit_unsupported
fi
+check_filter_file set_ftrace_filter
+
disable_tracing
clear_trace
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-notrace-pid.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-notrace-pid.tc
new file mode 100644
index 000000000000..71db68a7975f
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-notrace-pid.tc
@@ -0,0 +1,105 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: ftrace - function pid notrace filters
+# flags: instance
+
+# Make sure that function pid matching filter with notrace works.
+
+if ! grep -q function available_tracers; then
+ echo "no function tracer configured"
+ exit_unsupported
+fi
+
+if [ ! -f set_ftrace_notrace_pid ]; then
+ echo "set_ftrace_notrace_pid not found? Is function tracer not set?"
+ exit_unsupported
+fi
+
+check_filter_file set_ftrace_filter
+
+do_function_fork=1
+
+if [ ! -f options/function-fork ]; then
+ do_function_fork=0
+ echo "no option for function-fork found. Option will not be tested."
+fi
+
+read PID _ < /proc/self/stat
+
+if [ $do_function_fork -eq 1 ]; then
+ # default value of function-fork option
+ orig_value=`grep function-fork trace_options`
+fi
+
+do_reset() {
+ if [ $do_function_fork -eq 0 ]; then
+ return
+ fi
+
+ echo > set_ftrace_notrace_pid
+ echo $orig_value > trace_options
+}
+
+fail() { # msg
+ do_reset
+ echo $1
+ exit_fail
+}
+
+do_test() {
+ disable_tracing
+
+ echo do_execve* > set_ftrace_filter
+ echo *do_fork >> set_ftrace_filter
+
+ echo $PID > set_ftrace_notrace_pid
+ echo function > current_tracer
+
+ if [ $do_function_fork -eq 1 ]; then
+ # don't allow children to be traced
+ echo nofunction-fork > trace_options
+ fi
+
+ enable_tracing
+ yield
+
+ count_pid=`cat trace | grep -v ^# | grep $PID | wc -l`
+ count_other=`cat trace | grep -v ^# | grep -v $PID | wc -l`
+
+ # count_pid should be 0
+ if [ $count_pid -ne 0 -o $count_other -eq 0 ]; then
+ fail "PID filtering not working? traced task = $count_pid; other tasks = $count_other "
+ fi
+
+ disable_tracing
+ clear_trace
+
+ if [ $do_function_fork -eq 0 ]; then
+ return
+ fi
+
+ # allow children to be traced
+ echo function-fork > trace_options
+
+ # With pid in both set_ftrace_pid and set_ftrace_notrace_pid
+ # there should not be any tasks traced.
+
+ echo $PID > set_ftrace_pid
+
+ enable_tracing
+ yield
+
+ count_pid=`cat trace | grep -v ^# | grep $PID | wc -l`
+ count_other=`cat trace | grep -v ^# | grep -v $PID | wc -l`
+
+ # both should be zero
+ if [ $count_pid -ne 0 -o $count_other -ne 0 ]; then
+ fail "PID filtering not following fork? traced task = $count_pid; other tasks = $count_other "
+ fi
+}
+
+do_test
+
+do_reset
+
+exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc
index f2ee1e889e13..d58403c4b7cd 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc
@@ -16,10 +16,7 @@ if [ ! -f set_ftrace_pid ]; then
exit_unsupported
fi
-if [ ! -f set_ftrace_filter ]; then
- echo "set_ftrace_filter not found? Is function tracer not set?"
- exit_unsupported
-fi
+check_filter_file set_ftrace_filter
do_function_fork=1
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-stacktrace.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-stacktrace.tc
index 1a52f2883fe0..b2aff786c1a2 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-stacktrace.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-stacktrace.tc
@@ -3,7 +3,7 @@
# description: ftrace - stacktrace filter command
# flags: instance
-[ ! -f set_ftrace_filter ] && exit_unsupported
+check_filter_file set_ftrace_filter
echo _do_fork:stacktrace >> set_ftrace_filter
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_event_triggers.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_event_triggers.tc
index ca2ffd7957f9..e9b1fd534e96 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/func_event_triggers.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_event_triggers.tc
@@ -11,10 +11,7 @@
#
# The triggers are set within the set_ftrace_filter file
-if [ ! -f set_ftrace_filter ]; then
- echo "set_ftrace_filter not found? Is dynamic ftrace not set?"
- exit_unsupported
-fi
+check_filter_file set_ftrace_filter
do_reset() {
reset_ftrace_filter
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_mod_trace.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_mod_trace.tc
index 9330c873f9fe..1a4b4a442d33 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/func_mod_trace.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_mod_trace.tc
@@ -2,7 +2,7 @@
# SPDX-License-Identifier: GPL-2.0
# description: ftrace - function trace on module
-[ ! -f set_ftrace_filter ] && exit_unsupported
+check_filter_file set_ftrace_filter
: "mod: allows to filter a non exist function"
echo 'non_exist_func:mod:non_exist_module' > set_ftrace_filter
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_profiler.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_profiler.tc
index dfbae637c60c..a3dadb6b93b4 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/func_profiler.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_profiler.tc
@@ -18,10 +18,7 @@ if ! grep -q function_graph available_tracers; then
exit_unsupported;
fi
-if [ ! -f set_ftrace_filter ]; then
- echo "set_ftrace_filter not found? Is dynamic ftrace not set?"
- exit_unsupported
-fi
+check_filter_file set_ftrace_filter
if [ ! -f function_profile_enabled ]; then
echo "function_profile_enabled not found, function profiling enabled?"
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc
index 51f6e6146bd9..70bad441fa7d 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc
@@ -10,10 +10,7 @@
#
# The triggers are set within the set_ftrace_filter file
-if [ ! -f set_ftrace_filter ]; then
- echo "set_ftrace_filter not found? Is dynamic ftrace not set?"
- exit_unsupported
-fi
+check_filter_file set_ftrace_filter
fail() { # mesg
echo $1
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_stack_tracer.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_stack_tracer.tc
index b414f0e3c646..51e9e80bc0e6 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/func_stack_tracer.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_stack_tracer.tc
@@ -8,6 +8,8 @@ if [ ! -f stack_trace ]; then
exit_unsupported
fi
+check_filter_file stack_trace_filter
+
echo > stack_trace_filter
echo 0 > stack_max_size
echo 1 > /proc/sys/kernel/stack_tracer_enabled
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_traceonoff_triggers.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_traceonoff_triggers.tc
index 0c04282d33dd..3ed173f2944a 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/func_traceonoff_triggers.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_traceonoff_triggers.tc
@@ -11,10 +11,7 @@
#
# The triggers are set within the set_ftrace_filter file
-if [ ! -f set_ftrace_filter ]; then
- echo "set_ftrace_filter not found? Is dynamic ftrace not set?"
- exit_unsupported
-fi
+check_filter_file set_ftrace_filter
fail() { # mesg
echo $1
@@ -41,7 +38,7 @@ fi
echo '** ENABLE EVENTS'
-echo 1 > events/enable
+echo 1 > events/sched/enable
echo '** ENABLE TRACING'
enable_tracing
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/tracing-error-log.tc b/tools/testing/selftests/ftrace/test.d/ftrace/tracing-error-log.tc
index 021c03fd885d..23465823532b 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/tracing-error-log.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/tracing-error-log.tc
@@ -14,6 +14,8 @@ if [ ! -f set_event ]; then
exit_unsupported
fi
+[ -f error_log ] || exit_unsupported
+
ftrace_errlog_check 'event filter parse error' '((sig >= 10 && sig < 15) || dsig ^== 17) && comm != bash' 'events/signal/signal_generate/filter'
exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/functions b/tools/testing/selftests/ftrace/test.d/functions
index 5d4550591ff9..697c77ef2e2b 100644
--- a/tools/testing/selftests/ftrace/test.d/functions
+++ b/tools/testing/selftests/ftrace/test.d/functions
@@ -1,3 +1,9 @@
+check_filter_file() { # check filter file introduced by dynamic ftrace
+ if [ ! -f "$1" ]; then
+ echo "$1 not found? Is dynamic ftrace not set?"
+ exit_unsupported
+ fi
+}
clear_trace() { # reset trace output
echo > trace
@@ -113,12 +119,14 @@ yield() {
ping $LOCALHOST -c 1 || sleep .001 || usleep 1 || sleep 1
}
+# Since probe event command may include backslash, explicitly use printf "%s"
+# to NOT interpret it.
ftrace_errlog_check() { # err-prefix command-with-error-pos-by-^ command-file
- pos=$(echo -n "${2%^*}" | wc -c) # error position
- command=$(echo "$2" | tr -d ^)
+ pos=$(printf "%s" "${2%^*}" | wc -c) # error position
+ command=$(printf "%s" "$2" | tr -d ^)
echo "Test command: $command"
echo > error_log
- (! echo "$command" >> "$3" ) 2> /dev/null
+ (! printf "%s" "$command" >> "$3" ) 2> /dev/null
grep "$1: error:" -A 3 error_log
N=$(tail -n 1 error_log | wc -c)
# " Command: " and "^\n" => 13
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc
index 1bcb67dcae26..81490ecaaa92 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc
@@ -38,7 +38,7 @@ for width in 64 32 16 8; do
echo 0 > events/kprobes/testprobe/enable
: "Confirm the arguments is recorded in given types correctly"
- ARGS=`grep "testprobe" trace | sed -e 's/.* arg1=\(.*\) arg2=\(.*\) arg3=\(.*\) arg4=\(.*\)/\1 \2 \3 \4/'`
+ ARGS=`grep "testprobe" trace | head -n 1 | sed -e 's/.* arg1=\(.*\) arg2=\(.*\) arg3=\(.*\) arg4=\(.*\)/\1 \2 \3 \4/'`
check_types $ARGS $width
: "Clear event for next loop"
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_ftrace.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_ftrace.tc
index 7650a82db3f5..df5072815b87 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_ftrace.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_ftrace.tc
@@ -5,6 +5,8 @@
[ -f kprobe_events ] || exit_unsupported # this is configurable
grep "function" available_tracers || exit_unsupported # this is configurable
+check_filter_file set_ftrace_filter
+
# prepare
echo nop > current_tracer
echo _do_fork > set_ftrace_filter
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc
index ef1e9bafb098..eb0f4ab4e070 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc
@@ -91,7 +91,9 @@ esac
if grep -q "Create/append/" README && grep -q "imm-value" README; then
echo 'p:kprobes/testevent _do_fork' > kprobe_events
check_error '^r:kprobes/testevent do_exit' # DIFF_PROBE_TYPE
-echo 'p:kprobes/testevent _do_fork abcd=\1' > kprobe_events
+
+# Explicitly use printf "%s" to not interpret \1
+printf "%s" 'p:kprobes/testevent _do_fork abcd=\1' > kprobe_events
check_error 'p:kprobes/testevent _do_fork ^bcd=\1' # DIFF_ARG_TYPE
check_error 'p:kprobes/testevent _do_fork ^abcd=\1:u8' # DIFF_ARG_TYPE
check_error 'p:kprobes/testevent _do_fork ^abcd=\"foo"' # DIFF_ARG_TYPE
diff --git a/tools/testing/selftests/ftrace/test.d/preemptirq/irqsoff_tracer.tc b/tools/testing/selftests/ftrace/test.d/preemptirq/irqsoff_tracer.tc
index cbd174334a48..2b82c80edf69 100644
--- a/tools/testing/selftests/ftrace/test.d/preemptirq/irqsoff_tracer.tc
+++ b/tools/testing/selftests/ftrace/test.d/preemptirq/irqsoff_tracer.tc
@@ -17,7 +17,14 @@ unsup() { #msg
exit_unsupported
}
-modprobe $MOD || unsup "$MOD module not available"
+unres() { #msg
+ reset_tracer
+ rmmod $MOD || true
+ echo $1
+ exit_unresolved
+}
+
+modprobe $MOD || unres "$MOD module not available"
rmmod $MOD
grep -q "preemptoff" available_tracers || unsup "preemptoff tracer not enabled"
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-field-variable-support.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-field-variable-support.tc
index 77be6e1f6e7b..e232059a8ab2 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-field-variable-support.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-field-variable-support.tc
@@ -17,6 +17,11 @@ if [ ! -f synthetic_events ]; then
exit_unsupported
fi
+if [ ! -f events/sched/sched_process_fork/hist ]; then
+ echo "hist trigger is not supported"
+ exit_unsupported
+fi
+
echo "Test field variable support"
echo 'wakeup_latency u64 lat; pid_t pid; int prio; char comm[16]' > synthetic_events
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-inter-event-combined-hist.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-inter-event-combined-hist.tc
index f3eb8aacec0e..07cfcb8157b6 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-inter-event-combined-hist.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-inter-event-combined-hist.tc
@@ -17,6 +17,11 @@ if [ ! -f synthetic_events ]; then
exit_unsupported
fi
+if [ ! -f events/sched/sched_process_fork/hist ]; then
+ echo "hist trigger is not supported"
+ exit_unsupported
+fi
+
echo "Test create synthetic event"
echo 'waking_latency u64 lat pid_t pid' > synthetic_events
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-multi-actions-accept.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-multi-actions-accept.tc
index d281f056f980..73e413c2ca26 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-multi-actions-accept.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-multi-actions-accept.tc
@@ -17,6 +17,11 @@ if [ ! -f synthetic_events ]; then
exit_unsupported
fi
+if [ ! -f events/sched/sched_process_fork/hist ]; then
+ echo "hist trigger is not supported"
+ exit_unsupported
+fi
+
echo "Test multiple actions on hist trigger"
echo 'wakeup_latency u64 lat; pid_t pid' >> synthetic_events
TRIGGER1=events/sched/sched_wakeup/trigger
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmatch-action-hist.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmatch-action-hist.tc
index a708f0e7858a..ebe0ad827f9f 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmatch-action-hist.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmatch-action-hist.tc
@@ -17,6 +17,11 @@ if [ ! -f synthetic_events ]; then
exit_unsupported
fi
+if [ ! -f events/sched/sched_process_fork/hist ]; then
+ echo "hist trigger is not supported"
+ exit_unsupported
+fi
+
echo "Test create synthetic event"
echo 'wakeup_latency u64 lat pid_t pid char comm[16]' > synthetic_events
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmatch-onmax-action-hist.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmatch-onmax-action-hist.tc
index dfce6932d8be..2a2ef767249e 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmatch-onmax-action-hist.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmatch-onmax-action-hist.tc
@@ -17,6 +17,11 @@ if [ ! -f synthetic_events ]; then
exit_unsupported
fi
+if [ ! -f events/sched/sched_process_fork/hist ]; then
+ echo "hist trigger is not supported"
+ exit_unsupported
+fi
+
echo "Test create synthetic event"
echo 'wakeup_latency u64 lat pid_t pid char comm[16]' > synthetic_events
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmax-action-hist.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmax-action-hist.tc
index 0035995c2194..98d73bfb0296 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmax-action-hist.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmax-action-hist.tc
@@ -17,6 +17,11 @@ if [ ! -f synthetic_events ]; then
exit_unsupported
fi
+if [ ! -f events/sched/sched_process_fork/hist ]; then
+ echo "hist trigger is not supported"
+ exit_unsupported
+fi
+
echo "Test create synthetic event"
echo 'wakeup_latency u64 lat pid_t pid char comm[16]' > synthetic_events
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-snapshot-action-hist.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-snapshot-action-hist.tc
index f546c1b66a9b..01b01b9c4e07 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-snapshot-action-hist.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-snapshot-action-hist.tc
@@ -12,6 +12,11 @@ if [ ! -f set_event ]; then
exit_unsupported
fi
+if [ ! -f events/sched/sched_process_fork/hist ]; then
+ echo "hist trigger is not supported"
+ exit_unsupported
+fi
+
if [ ! -f snapshot ]; then
echo "snapshot is not supported"
exit_unsupported
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-trace-action-hist.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-trace-action-hist.tc
index 8021d60aafec..c3baa486aeb4 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-trace-action-hist.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-trace-action-hist.tc
@@ -17,6 +17,11 @@ if [ ! -f synthetic_events ]; then
exit_unsupported
fi
+if [ ! -f events/sched/sched_process_fork/hist ]; then
+ echo "hist trigger is not supported"
+ exit_unsupported
+fi
+
grep -q "trace(<synthetic_event>" README || exit_unsupported # version issue
echo "Test create synthetic event"
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-multihist.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-multihist.tc
index 18fdaab9f570..68ff3f45c720 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-multihist.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-multihist.tc
@@ -23,7 +23,7 @@ if [ ! -f events/sched/sched_process_fork/hist ]; then
exit_unsupported
fi
-echo "Test histogram multiple tiggers"
+echo "Test histogram multiple triggers"
echo 'hist:keys=parent_pid:vals=child_pid' > events/sched/sched_process_fork/trigger
echo 'hist:keys=parent_comm:vals=child_pid' >> events/sched/sched_process_fork/trigger
diff --git a/tools/testing/selftests/futex/functional/.gitignore b/tools/testing/selftests/futex/functional/.gitignore
index a09f57061902..0efcd494daab 100644
--- a/tools/testing/selftests/futex/functional/.gitignore
+++ b/tools/testing/selftests/futex/functional/.gitignore
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
futex_requeue_pi
futex_requeue_pi_mismatched_ops
futex_requeue_pi_signal_restart
diff --git a/tools/testing/selftests/gen_kselftest_tar.sh b/tools/testing/selftests/gen_kselftest_tar.sh
index 8b2b6088540d..4a974bc03385 100755
--- a/tools/testing/selftests/gen_kselftest_tar.sh
+++ b/tools/testing/selftests/gen_kselftest_tar.sh
@@ -49,6 +49,11 @@ main()
# directory
./kselftest_install.sh "$install_dir"
(cd "$install_work"; tar $copts "$dest"/kselftest${ext} $install_name)
+
+ # Don't put the message at the actual end as people may be parsing the
+ # "archive created" line in their scripts.
+ echo -e "\nConsider using 'make gen_tar' instead of this script\n"
+
echo "Kselftest archive kselftest${ext} created!"
# clean up top-level install work directory
diff --git a/tools/testing/selftests/gpio/.gitignore b/tools/testing/selftests/gpio/.gitignore
index 7d14f743d1a4..4c69408f3e84 100644
--- a/tools/testing/selftests/gpio/.gitignore
+++ b/tools/testing/selftests/gpio/.gitignore
@@ -1 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
gpio-mockup-chardev
diff --git a/tools/testing/selftests/gpio/Makefile b/tools/testing/selftests/gpio/Makefile
index 0bb80619db58..32bdc978a711 100644
--- a/tools/testing/selftests/gpio/Makefile
+++ b/tools/testing/selftests/gpio/Makefile
@@ -1,13 +1,13 @@
# SPDX-License-Identifier: GPL-2.0
-MOUNT_CFLAGS := $(shell pkg-config --cflags mount 2>/dev/null)
-MOUNT_LDLIBS := $(shell pkg-config --libs mount 2>/dev/null)
-ifeq ($(MOUNT_LDLIBS),)
-MOUNT_LDLIBS := -lmount -I/usr/include/libmount
+VAR_CFLAGS := $(shell pkg-config --cflags mount 2>/dev/null)
+VAR_LDLIBS := $(shell pkg-config --libs mount 2>/dev/null)
+ifeq ($(VAR_LDLIBS),)
+VAR_LDLIBS := -lmount -I/usr/include/libmount
endif
-CFLAGS += -O2 -g -std=gnu99 -Wall -I../../../../usr/include/ $(MOUNT_CFLAGS)
-LDLIBS += $(MOUNT_LDLIBS)
+CFLAGS += -O2 -g -std=gnu99 -Wall -I../../../../usr/include/ $(VAR_CFLAGS)
+LDLIBS += $(VAR_LDLIBS)
TEST_PROGS := gpio-mockup.sh
TEST_FILES := gpio-mockup-sysfs.sh
diff --git a/tools/testing/selftests/ia64/.gitignore b/tools/testing/selftests/ia64/.gitignore
index ab806edc8732..e962fb2a08d5 100644
--- a/tools/testing/selftests/ia64/.gitignore
+++ b/tools/testing/selftests/ia64/.gitignore
@@ -1 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
aliasing-test
diff --git a/tools/testing/selftests/intel_pstate/.gitignore b/tools/testing/selftests/intel_pstate/.gitignore
index 3bfcbae5fa13..862de222a3f3 100644
--- a/tools/testing/selftests/intel_pstate/.gitignore
+++ b/tools/testing/selftests/intel_pstate/.gitignore
@@ -1,2 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0-only
aperf
msr
diff --git a/tools/testing/selftests/intel_pstate/Makefile b/tools/testing/selftests/intel_pstate/Makefile
index 7340fd6a9a9f..39f0fa2a8fd6 100644
--- a/tools/testing/selftests/intel_pstate/Makefile
+++ b/tools/testing/selftests/intel_pstate/Makefile
@@ -1,6 +1,6 @@
# SPDX-License-Identifier: GPL-2.0
CFLAGS := $(CFLAGS) -Wall -D_GNU_SOURCE
-LDLIBS := $(LDLIBS) -lm
+LDLIBS += -lm
uname_M := $(shell uname -m 2>/dev/null || echo not)
ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/x86/ -e s/x86_64/x86/)
diff --git a/tools/testing/selftests/ipc/.gitignore b/tools/testing/selftests/ipc/.gitignore
index 9af04c9353c0..9ed280e4c704 100644
--- a/tools/testing/selftests/ipc/.gitignore
+++ b/tools/testing/selftests/ipc/.gitignore
@@ -1,2 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0-only
msgque_test
msgque
diff --git a/tools/testing/selftests/ipc/msgque.c b/tools/testing/selftests/ipc/msgque.c
index 4c156aeab6b8..5ec4d9e18806 100644
--- a/tools/testing/selftests/ipc/msgque.c
+++ b/tools/testing/selftests/ipc/msgque.c
@@ -137,7 +137,7 @@ int dump_queue(struct msgque_data *msgque)
for (kern_id = 0; kern_id < 256; kern_id++) {
ret = msgctl(kern_id, MSG_STAT, &ds);
if (ret < 0) {
- if (errno == -EINVAL)
+ if (errno == EINVAL)
continue;
printf("Failed to get stats for IPC queue with id %d\n",
kern_id);
diff --git a/tools/testing/selftests/ir/.gitignore b/tools/testing/selftests/ir/.gitignore
index 070ea0c75fb8..0bbada8c1811 100644
--- a/tools/testing/selftests/ir/.gitignore
+++ b/tools/testing/selftests/ir/.gitignore
@@ -1 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
ir_loopback
diff --git a/tools/testing/selftests/kcmp/.gitignore b/tools/testing/selftests/kcmp/.gitignore
index 5a9b3732b2de..38ccdfe80ef7 100644
--- a/tools/testing/selftests/kcmp/.gitignore
+++ b/tools/testing/selftests/kcmp/.gitignore
@@ -1,2 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0-only
kcmp_test
kcmp-test-file
diff --git a/tools/testing/selftests/kmod/kmod.sh b/tools/testing/selftests/kmod/kmod.sh
index 8b944cf042f6..3702dbcc90a7 100755
--- a/tools/testing/selftests/kmod/kmod.sh
+++ b/tools/testing/selftests/kmod/kmod.sh
@@ -61,6 +61,8 @@ ALL_TESTS="$ALL_TESTS 0006:10:1"
ALL_TESTS="$ALL_TESTS 0007:5:1"
ALL_TESTS="$ALL_TESTS 0008:150:1"
ALL_TESTS="$ALL_TESTS 0009:150:1"
+ALL_TESTS="$ALL_TESTS 0010:1:1"
+ALL_TESTS="$ALL_TESTS 0011:1:1"
# Kselftest framework requirement - SKIP code is 4.
ksft_skip=4
@@ -149,6 +151,7 @@ function load_req_mod()
test_finish()
{
+ echo "$MODPROBE" > /proc/sys/kernel/modprobe
echo "Test completed"
}
@@ -443,6 +446,30 @@ kmod_test_0009()
config_expect_result ${FUNCNAME[0]} SUCCESS
}
+kmod_test_0010()
+{
+ kmod_defaults_driver
+ config_num_threads 1
+ echo "/KMOD_TEST_NONEXISTENT" > /proc/sys/kernel/modprobe
+ config_trigger ${FUNCNAME[0]}
+ config_expect_result ${FUNCNAME[0]} -ENOENT
+ echo "$MODPROBE" > /proc/sys/kernel/modprobe
+}
+
+kmod_test_0011()
+{
+ kmod_defaults_driver
+ config_num_threads 1
+ # This causes the kernel to not even try executing modprobe. The error
+ # code is still -ENOENT like when modprobe doesn't exist, so we can't
+ # easily test for the exact difference. But this still is a useful test
+ # since there was a bug where request_module() returned 0 in this case.
+ echo > /proc/sys/kernel/modprobe
+ config_trigger ${FUNCNAME[0]}
+ config_expect_result ${FUNCNAME[0]} -ENOENT
+ echo "$MODPROBE" > /proc/sys/kernel/modprobe
+}
+
list_tests()
{
echo "Test ID list:"
@@ -460,6 +487,8 @@ list_tests()
echo "0007 x $(get_test_count 0007) - multithreaded tests with default setup test request_module() and get_fs_type()"
echo "0008 x $(get_test_count 0008) - multithreaded - push kmod_concurrent over max_modprobes for request_module()"
echo "0009 x $(get_test_count 0009) - multithreaded - push kmod_concurrent over max_modprobes for get_fs_type()"
+ echo "0010 x $(get_test_count 0010) - test nonexistent modprobe path"
+ echo "0011 x $(get_test_count 0011) - test completely disabling module autoloading"
}
usage()
@@ -505,18 +534,23 @@ function test_num()
fi
}
-function get_test_count()
+function get_test_data()
{
test_num $1
- TEST_DATA=$(echo $ALL_TESTS | awk '{print $'$1'}')
+ local field_num=$(echo $1 | sed 's/^0*//')
+ echo $ALL_TESTS | awk '{print $'$field_num'}'
+}
+
+function get_test_count()
+{
+ TEST_DATA=$(get_test_data $1)
LAST_TWO=${TEST_DATA#*:*}
echo ${LAST_TWO%:*}
}
function get_test_enabled()
{
- test_num $1
- TEST_DATA=$(echo $ALL_TESTS | awk '{print $'$1'}')
+ TEST_DATA=$(get_test_data $1)
echo ${TEST_DATA#*:*:}
}
@@ -611,6 +645,7 @@ test_reqs
allow_user_defaults
load_req_mod
+MODPROBE=$(</proc/sys/kernel/modprobe)
trap "test_finish" EXIT
parse_args $@
diff --git a/tools/testing/selftests/kselftest/runner.sh b/tools/testing/selftests/kselftest/runner.sh
index e84d901f8567..676b3a8b114d 100644
--- a/tools/testing/selftests/kselftest/runner.sh
+++ b/tools/testing/selftests/kselftest/runner.sh
@@ -33,7 +33,7 @@ tap_timeout()
{
# Make sure tests will time out if utility is available.
if [ -x /usr/bin/timeout ] ; then
- /usr/bin/timeout "$kselftest_timeout" "$1"
+ /usr/bin/timeout --foreground "$kselftest_timeout" "$1"
else
"$1"
fi
diff --git a/tools/testing/selftests/kselftest_deps.sh b/tools/testing/selftests/kselftest_deps.sh
new file mode 100755
index 000000000000..bbc04646346b
--- /dev/null
+++ b/tools/testing/selftests/kselftest_deps.sh
@@ -0,0 +1,272 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# kselftest_deps.sh
+#
+# Checks for kselftest build dependencies on the build system.
+# Copyright (c) 2020 Shuah Khan <skhan@linuxfoundation.org>
+#
+#
+
+usage()
+{
+
+echo -e "Usage: $0 -[p] <compiler> [test_name]\n"
+echo -e "\tkselftest_deps.sh [-p] gcc"
+echo -e "\tkselftest_deps.sh [-p] gcc vm"
+echo -e "\tkselftest_deps.sh [-p] aarch64-linux-gnu-gcc"
+echo -e "\tkselftest_deps.sh [-p] aarch64-linux-gnu-gcc vm\n"
+echo "- Should be run in selftests directory in the kernel repo."
+echo "- Checks if Kselftests can be built/cross-built on a system."
+echo "- Parses all test/sub-test Makefile to find library dependencies."
+echo "- Runs compile test on a trivial C file with LDLIBS specified"
+echo " in the test Makefiles to identify missing library dependencies."
+echo "- Prints suggested target list for a system filtering out tests"
+echo " failed the build dependency check from the TARGETS in Selftests"
+echo " main Makefile when optional -p is specified."
+echo "- Prints pass/fail dependency check for each tests/sub-test."
+echo "- Prints pass/fail targets and libraries."
+echo "- Default: runs dependency checks on all tests."
+echo "- Optional test name can be specified to check dependencies for it."
+exit 1
+
+}
+
+# Start main()
+main()
+{
+
+base_dir=`pwd`
+# Make sure we're in the selftests top-level directory.
+if [ $(basename "$base_dir") != "selftests" ]; then
+ echo -e "\tPlease run $0 in"
+ echo -e "\ttools/testing/selftests directory ..."
+ exit 1
+fi
+
+print_targets=0
+
+while getopts "p" arg; do
+ case $arg in
+ p)
+ print_targets=1
+ shift;;
+ esac
+done
+
+if [ $# -eq 0 ]
+then
+ usage
+fi
+
+# Compiler
+CC=$1
+
+tmp_file=$(mktemp).c
+trap "rm -f $tmp_file.o $tmp_file $tmp_file.bin" EXIT
+#echo $tmp_file
+
+pass=$(mktemp).out
+trap "rm -f $pass" EXIT
+#echo $pass
+
+fail=$(mktemp).out
+trap "rm -f $fail" EXIT
+#echo $fail
+
+# Generate tmp source fire for compile test
+cat << "EOF" > $tmp_file
+int main()
+{
+}
+EOF
+
+# Save results
+total_cnt=0
+fail_trgts=()
+fail_libs=()
+fail_cnt=0
+pass_trgts=()
+pass_libs=()
+pass_cnt=0
+
+# Get all TARGETS from selftests Makefile
+targets=$(egrep "^TARGETS +|^TARGETS =" Makefile | cut -d "=" -f2)
+
+# Single test case
+if [ $# -eq 2 ]
+then
+ test=$2/Makefile
+
+ l1_test $test
+ l2_test $test
+ l3_test $test
+
+ print_results $1 $2
+ exit $?
+fi
+
+# Level 1: LDLIBS set static.
+#
+# Find all LDLIBS set statically for all executables built by a Makefile
+# and filter out VAR_LDLIBS to discard the following:
+# gpio/Makefile:LDLIBS += $(VAR_LDLIBS)
+# Append space at the end of the list to append more tests.
+
+l1_tests=$(grep -r --include=Makefile "^LDLIBS" | \
+ grep -v "VAR_LDLIBS" | awk -F: '{print $1}')
+
+# Level 2: LDLIBS set dynamically.
+#
+# Level 2
+# Some tests have multiple valid LDLIBS lines for individual sub-tests
+# that need dependency checks. Find them and append them to the tests
+# e.g: vm/Makefile:$(OUTPUT)/userfaultfd: LDLIBS += -lpthread
+# Filter out VAR_LDLIBS to discard the following:
+# memfd/Makefile:$(OUTPUT)/fuse_mnt: LDLIBS += $(VAR_LDLIBS)
+# Append space at the end of the list to append more tests.
+
+l2_tests=$(grep -r --include=Makefile ": LDLIBS" | \
+ grep -v "VAR_LDLIBS" | awk -F: '{print $1}')
+
+# Level 3
+# gpio, memfd and others use pkg-config to find mount and fuse libs
+# respectively and save it in VAR_LDLIBS. If pkg-config doesn't find
+# any, VAR_LDLIBS set to default.
+# Use the default value and filter out pkg-config for dependency check.
+# e.g:
+# gpio/Makefile
+# VAR_LDLIBS := $(shell pkg-config --libs mount) 2>/dev/null)
+# memfd/Makefile
+# VAR_LDLIBS := $(shell pkg-config fuse --libs 2>/dev/null)
+
+l3_tests=$(grep -r --include=Makefile "^VAR_LDLIBS" | \
+ grep -v "pkg-config" | awk -F: '{print $1}')
+
+#echo $l1_tests
+#echo $l2_1_tests
+#echo $l3_tests
+
+all_tests
+print_results $1 $2
+
+exit $?
+}
+# end main()
+
+all_tests()
+{
+ for test in $l1_tests; do
+ l1_test $test
+ done
+
+ for test in $l2_tests; do
+ l2_test $test
+ done
+
+ for test in $l3_tests; do
+ l3_test $test
+ done
+}
+
+# Use same parsing used for l1_tests and pick libraries this time.
+l1_test()
+{
+ test_libs=$(grep --include=Makefile "^LDLIBS" $test | \
+ grep -v "VAR_LDLIBS" | \
+ sed -e 's/\:/ /' | \
+ sed -e 's/+/ /' | cut -d "=" -f 2)
+
+ check_libs $test $test_libs
+}
+
+# Use same parsing used for l2__tests and pick libraries this time.
+l2_test()
+{
+ test_libs=$(grep --include=Makefile ": LDLIBS" $test | \
+ grep -v "VAR_LDLIBS" | \
+ sed -e 's/\:/ /' | sed -e 's/+/ /' | \
+ cut -d "=" -f 2)
+
+ check_libs $test $test_libs
+}
+
+l3_test()
+{
+ test_libs=$(grep --include=Makefile "^VAR_LDLIBS" $test | \
+ grep -v "pkg-config" | sed -e 's/\:/ /' |
+ sed -e 's/+/ /' | cut -d "=" -f 2)
+
+ check_libs $test $test_libs
+}
+
+check_libs()
+{
+
+if [[ ! -z "${test_libs// }" ]]
+then
+
+ #echo $test_libs
+
+ for lib in $test_libs; do
+
+ let total_cnt+=1
+ $CC -o $tmp_file.bin $lib $tmp_file > /dev/null 2>&1
+ if [ $? -ne 0 ]; then
+ echo "FAIL: $test dependency check: $lib" >> $fail
+ let fail_cnt+=1
+ fail_libs+="$lib "
+ fail_target=$(echo "$test" | cut -d "/" -f1)
+ fail_trgts+="$fail_target "
+ targets=$(echo "$targets" | grep -v "$fail_target")
+ else
+ echo "PASS: $test dependency check passed $lib" >> $pass
+ let pass_cnt+=1
+ pass_libs+="$lib "
+ pass_trgts+="$(echo "$test" | cut -d "/" -f1) "
+ fi
+
+ done
+fi
+}
+
+print_results()
+{
+ echo -e "========================================================";
+ echo -e "Kselftest Dependency Check for [$0 $1 $2] results..."
+
+ if [ $print_targets -ne 0 ]
+ then
+ echo -e "Suggested Selftest Targets for your configuration:"
+ echo -e "$targets";
+ fi
+
+ echo -e "========================================================";
+ echo -e "Checked tests defining LDLIBS dependencies"
+ echo -e "--------------------------------------------------------";
+ echo -e "Total tests with Dependencies:"
+ echo -e "$total_cnt Pass: $pass_cnt Fail: $fail_cnt";
+
+ if [ $pass_cnt -ne 0 ]; then
+ echo -e "--------------------------------------------------------";
+ cat $pass
+ echo -e "--------------------------------------------------------";
+ echo -e "Targets passed build dependency check on system:"
+ echo -e "$(echo "$pass_trgts" | xargs -n1 | sort -u | xargs)"
+ fi
+
+ if [ $fail_cnt -ne 0 ]; then
+ echo -e "--------------------------------------------------------";
+ cat $fail
+ echo -e "--------------------------------------------------------";
+ echo -e "Targets failed build dependency check on system:"
+ echo -e "$(echo "$fail_trgts" | xargs -n1 | sort -u | xargs)"
+ echo -e "--------------------------------------------------------";
+ echo -e "Missing libraries system"
+ echo -e "$(echo "$fail_libs" | xargs -n1 | sort -u | xargs)"
+ fi
+
+ echo -e "--------------------------------------------------------";
+ echo -e "========================================================";
+}
+
+main "$@"
diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h
index 5336b26506ab..c9f03ef93338 100644
--- a/tools/testing/selftests/kselftest_harness.h
+++ b/tools/testing/selftests/kselftest_harness.h
@@ -168,9 +168,17 @@
#define __TEST_IMPL(test_name, _signal) \
static void test_name(struct __test_metadata *_metadata); \
+ static inline void wrapper_##test_name( \
+ struct __test_metadata *_metadata, \
+ struct __fixture_variant_metadata *variant) \
+ { \
+ test_name(_metadata); \
+ } \
static struct __test_metadata _##test_name##_object = \
- { .name = "global." #test_name, \
- .fn = &test_name, .termsig = _signal, \
+ { .name = #test_name, \
+ .fn = &wrapper_##test_name, \
+ .fixture = &_fixture_global, \
+ .termsig = _signal, \
.timeout = TEST_TIMEOUT_DEFAULT, }; \
static void __attribute__((constructor)) _register_##test_name(void) \
{ \
@@ -212,10 +220,13 @@
* populated and cleaned up using FIXTURE_SETUP() and FIXTURE_TEARDOWN().
*/
#define FIXTURE(fixture_name) \
+ FIXTURE_VARIANT(fixture_name); \
+ static struct __fixture_metadata _##fixture_name##_fixture_object = \
+ { .name = #fixture_name, }; \
static void __attribute__((constructor)) \
_register_##fixture_name##_data(void) \
{ \
- __fixture_count++; \
+ __register_fixture(&_##fixture_name##_fixture_object); \
} \
FIXTURE_DATA(fixture_name)
@@ -241,7 +252,10 @@
#define FIXTURE_SETUP(fixture_name) \
void fixture_name##_setup( \
struct __test_metadata __attribute__((unused)) *_metadata, \
- FIXTURE_DATA(fixture_name) __attribute__((unused)) *self)
+ FIXTURE_DATA(fixture_name) __attribute__((unused)) *self, \
+ const FIXTURE_VARIANT(fixture_name) \
+ __attribute__((unused)) *variant)
+
/**
* FIXTURE_TEARDOWN(fixture_name)
* *_metadata* is included so that EXPECT_* and ASSERT_* work correctly.
@@ -264,6 +278,59 @@
FIXTURE_DATA(fixture_name) __attribute__((unused)) *self)
/**
+ * FIXTURE_VARIANT(fixture_name) - Optionally called once per fixture
+ * to declare fixture variant
+ *
+ * @fixture_name: fixture name
+ *
+ * .. code-block:: c
+ *
+ * FIXTURE_VARIANT(datatype name) {
+ * type property1;
+ * ...
+ * };
+ *
+ * Defines type of constant parameters provided to FIXTURE_SETUP() and TEST_F()
+ * as *variant*. Variants allow the same tests to be run with different
+ * arguments.
+ */
+#define FIXTURE_VARIANT(fixture_name) struct _fixture_variant_##fixture_name
+
+/**
+ * FIXTURE_VARIANT_ADD(fixture_name, variant_name) - Called once per fixture
+ * variant to setup and register the data
+ *
+ * @fixture_name: fixture name
+ * @variant_name: name of the parameter set
+ *
+ * .. code-block:: c
+ *
+ * FIXTURE_ADD(datatype name) {
+ * .property1 = val1;
+ * ...
+ * };
+ *
+ * Defines a variant of the test fixture, provided to FIXTURE_SETUP() and
+ * TEST_F() as *variant*. Tests of each fixture will be run once for each
+ * variant.
+ */
+#define FIXTURE_VARIANT_ADD(fixture_name, variant_name) \
+ extern FIXTURE_VARIANT(fixture_name) \
+ _##fixture_name##_##variant_name##_variant; \
+ static struct __fixture_variant_metadata \
+ _##fixture_name##_##variant_name##_object = \
+ { .name = #variant_name, \
+ .data = &_##fixture_name##_##variant_name##_variant}; \
+ static void __attribute__((constructor)) \
+ _register_##fixture_name##_##variant_name(void) \
+ { \
+ __register_fixture_variant(&_##fixture_name##_fixture_object, \
+ &_##fixture_name##_##variant_name##_object); \
+ } \
+ FIXTURE_VARIANT(fixture_name) \
+ _##fixture_name##_##variant_name##_variant =
+
+/**
* TEST_F(fixture_name, test_name) - Emits test registration and helpers for
* fixture-based test cases
*
@@ -293,24 +360,27 @@
#define __TEST_F_IMPL(fixture_name, test_name, signal, tmout) \
static void fixture_name##_##test_name( \
struct __test_metadata *_metadata, \
- FIXTURE_DATA(fixture_name) *self); \
+ FIXTURE_DATA(fixture_name) *self, \
+ const FIXTURE_VARIANT(fixture_name) *variant); \
static inline void wrapper_##fixture_name##_##test_name( \
- struct __test_metadata *_metadata) \
+ struct __test_metadata *_metadata, \
+ struct __fixture_variant_metadata *variant) \
{ \
/* fixture data is alloced, setup, and torn down per call. */ \
FIXTURE_DATA(fixture_name) self; \
memset(&self, 0, sizeof(FIXTURE_DATA(fixture_name))); \
- fixture_name##_setup(_metadata, &self); \
+ fixture_name##_setup(_metadata, &self, variant->data); \
/* Let setup failure terminate early. */ \
if (!_metadata->passed) \
return; \
- fixture_name##_##test_name(_metadata, &self); \
+ fixture_name##_##test_name(_metadata, &self, variant->data); \
fixture_name##_teardown(_metadata, &self); \
} \
static struct __test_metadata \
_##fixture_name##_##test_name##_object = { \
- .name = #fixture_name "." #test_name, \
+ .name = #test_name, \
.fn = &wrapper_##fixture_name##_##test_name, \
+ .fixture = &_##fixture_name##_fixture_object, \
.termsig = signal, \
.timeout = tmout, \
}; \
@@ -321,7 +391,9 @@
} \
static void fixture_name##_##test_name( \
struct __test_metadata __attribute__((unused)) *_metadata, \
- FIXTURE_DATA(fixture_name) __attribute__((unused)) *self)
+ FIXTURE_DATA(fixture_name) __attribute__((unused)) *self, \
+ const FIXTURE_VARIANT(fixture_name) \
+ __attribute__((unused)) *variant)
/**
* TEST_HARNESS_MAIN - Simple wrapper to run the test harness
@@ -631,28 +703,84 @@
} \
} while (0); OPTIONAL_HANDLER(_assert)
+/* List helpers */
+#define __LIST_APPEND(head, item) \
+{ \
+ /* Circular linked list where only prev is circular. */ \
+ if (head == NULL) { \
+ head = item; \
+ item->next = NULL; \
+ item->prev = item; \
+ return; \
+ } \
+ if (__constructor_order == _CONSTRUCTOR_ORDER_FORWARD) { \
+ item->next = NULL; \
+ item->prev = head->prev; \
+ item->prev->next = item; \
+ head->prev = item; \
+ } else { \
+ item->next = head; \
+ item->next->prev = item; \
+ item->prev = item; \
+ head = item; \
+ } \
+}
+
+struct __test_metadata;
+struct __fixture_variant_metadata;
+
+/* Contains all the information about a fixture. */
+struct __fixture_metadata {
+ const char *name;
+ struct __test_metadata *tests;
+ struct __fixture_variant_metadata *variant;
+ struct __fixture_metadata *prev, *next;
+} _fixture_global __attribute__((unused)) = {
+ .name = "global",
+ .prev = &_fixture_global,
+};
+
+static struct __fixture_metadata *__fixture_list = &_fixture_global;
+static int __constructor_order;
+
+#define _CONSTRUCTOR_ORDER_FORWARD 1
+#define _CONSTRUCTOR_ORDER_BACKWARD -1
+
+static inline void __register_fixture(struct __fixture_metadata *f)
+{
+ __LIST_APPEND(__fixture_list, f);
+}
+
+struct __fixture_variant_metadata {
+ const char *name;
+ const void *data;
+ struct __fixture_variant_metadata *prev, *next;
+};
+
+static inline void
+__register_fixture_variant(struct __fixture_metadata *f,
+ struct __fixture_variant_metadata *variant)
+{
+ __LIST_APPEND(f->variant, variant);
+}
+
/* Contains all the information for test execution and status checking. */
struct __test_metadata {
const char *name;
- void (*fn)(struct __test_metadata *);
+ void (*fn)(struct __test_metadata *,
+ struct __fixture_variant_metadata *);
+ pid_t pid; /* pid of test when being run */
+ struct __fixture_metadata *fixture;
int termsig;
int passed;
int trigger; /* extra handler after the evaluation */
- int timeout;
+ int timeout; /* seconds to wait for test timeout */
+ bool timed_out; /* did this test timeout instead of exiting? */
__u8 step;
bool no_print; /* manual trigger when TH_LOG_STREAM is not available */
struct __test_metadata *prev, *next;
};
-/* Storage for the (global) tests to be run. */
-static struct __test_metadata *__test_list;
-static unsigned int __test_count;
-static unsigned int __fixture_count;
-static int __constructor_order;
-
-#define _CONSTRUCTOR_ORDER_FORWARD 1
-#define _CONSTRUCTOR_ORDER_BACKWARD -1
-
/*
* Since constructors are called in reverse order, reverse the test
* list so tests are run in source declaration order.
@@ -664,25 +792,7 @@ static int __constructor_order;
*/
static inline void __register_test(struct __test_metadata *t)
{
- __test_count++;
- /* Circular linked list where only prev is circular. */
- if (__test_list == NULL) {
- __test_list = t;
- t->next = NULL;
- t->prev = t;
- return;
- }
- if (__constructor_order == _CONSTRUCTOR_ORDER_FORWARD) {
- t->next = NULL;
- t->prev = __test_list->prev;
- t->prev->next = t;
- __test_list->prev = t;
- } else {
- t->next = __test_list;
- t->next->prev = t;
- t->prev = t;
- __test_list = t;
- }
+ __LIST_APPEND(t->fixture->tests, t);
}
static inline int __bail(int for_realz, bool no_print, __u8 step)
@@ -695,84 +805,160 @@ static inline int __bail(int for_realz, bool no_print, __u8 step)
return 0;
}
-void __run_test(struct __test_metadata *t)
+struct __test_metadata *__active_test;
+static void __timeout_handler(int sig, siginfo_t *info, void *ucontext)
+{
+ struct __test_metadata *t = __active_test;
+
+ /* Sanity check handler execution environment. */
+ if (!t) {
+ fprintf(TH_LOG_STREAM,
+ "no active test in SIGALRM handler!?\n");
+ abort();
+ }
+ if (sig != SIGALRM || sig != info->si_signo) {
+ fprintf(TH_LOG_STREAM,
+ "%s: SIGALRM handler caught signal %d!?\n",
+ t->name, sig != SIGALRM ? sig : info->si_signo);
+ abort();
+ }
+
+ t->timed_out = true;
+ kill(t->pid, SIGKILL);
+}
+
+void __wait_for_test(struct __test_metadata *t)
{
- pid_t child_pid;
+ struct sigaction action = {
+ .sa_sigaction = __timeout_handler,
+ .sa_flags = SA_SIGINFO,
+ };
+ struct sigaction saved_action;
int status;
+ if (sigaction(SIGALRM, &action, &saved_action)) {
+ t->passed = 0;
+ fprintf(TH_LOG_STREAM,
+ "%s: unable to install SIGALRM handler\n",
+ t->name);
+ return;
+ }
+ __active_test = t;
+ t->timed_out = false;
+ alarm(t->timeout);
+ waitpid(t->pid, &status, 0);
+ alarm(0);
+ if (sigaction(SIGALRM, &saved_action, NULL)) {
+ t->passed = 0;
+ fprintf(TH_LOG_STREAM,
+ "%s: unable to uninstall SIGALRM handler\n",
+ t->name);
+ return;
+ }
+ __active_test = NULL;
+
+ if (t->timed_out) {
+ t->passed = 0;
+ fprintf(TH_LOG_STREAM,
+ "%s: Test terminated by timeout\n", t->name);
+ } else if (WIFEXITED(status)) {
+ t->passed = t->termsig == -1 ? !WEXITSTATUS(status) : 0;
+ if (t->termsig != -1) {
+ fprintf(TH_LOG_STREAM,
+ "%s: Test exited normally "
+ "instead of by signal (code: %d)\n",
+ t->name,
+ WEXITSTATUS(status));
+ } else if (!t->passed) {
+ fprintf(TH_LOG_STREAM,
+ "%s: Test failed at step #%d\n",
+ t->name,
+ WEXITSTATUS(status));
+ }
+ } else if (WIFSIGNALED(status)) {
+ t->passed = 0;
+ if (WTERMSIG(status) == SIGABRT) {
+ fprintf(TH_LOG_STREAM,
+ "%s: Test terminated by assertion\n",
+ t->name);
+ } else if (WTERMSIG(status) == t->termsig) {
+ t->passed = 1;
+ } else {
+ fprintf(TH_LOG_STREAM,
+ "%s: Test terminated unexpectedly "
+ "by signal %d\n",
+ t->name,
+ WTERMSIG(status));
+ }
+ } else {
+ fprintf(TH_LOG_STREAM,
+ "%s: Test ended in some other way [%u]\n",
+ t->name,
+ status);
+ }
+}
+
+void __run_test(struct __fixture_metadata *f,
+ struct __fixture_variant_metadata *variant,
+ struct __test_metadata *t)
+{
+ /* reset test struct */
t->passed = 1;
t->trigger = 0;
- printf("[ RUN ] %s\n", t->name);
- alarm(t->timeout);
- child_pid = fork();
- if (child_pid < 0) {
+ t->step = 0;
+ t->no_print = 0;
+
+ printf("[ RUN ] %s%s%s.%s\n",
+ f->name, variant->name[0] ? "." : "", variant->name, t->name);
+ t->pid = fork();
+ if (t->pid < 0) {
printf("ERROR SPAWNING TEST CHILD\n");
t->passed = 0;
- } else if (child_pid == 0) {
- t->fn(t);
+ } else if (t->pid == 0) {
+ t->fn(t, variant);
/* return the step that failed or 0 */
_exit(t->passed ? 0 : t->step);
} else {
- /* TODO(wad) add timeout support. */
- waitpid(child_pid, &status, 0);
- if (WIFEXITED(status)) {
- t->passed = t->termsig == -1 ? !WEXITSTATUS(status) : 0;
- if (t->termsig != -1) {
- fprintf(TH_LOG_STREAM,
- "%s: Test exited normally "
- "instead of by signal (code: %d)\n",
- t->name,
- WEXITSTATUS(status));
- } else if (!t->passed) {
- fprintf(TH_LOG_STREAM,
- "%s: Test failed at step #%d\n",
- t->name,
- WEXITSTATUS(status));
- }
- } else if (WIFSIGNALED(status)) {
- t->passed = 0;
- if (WTERMSIG(status) == SIGABRT) {
- fprintf(TH_LOG_STREAM,
- "%s: Test terminated by assertion\n",
- t->name);
- } else if (WTERMSIG(status) == t->termsig) {
- t->passed = 1;
- } else {
- fprintf(TH_LOG_STREAM,
- "%s: Test terminated unexpectedly "
- "by signal %d\n",
- t->name,
- WTERMSIG(status));
- }
- } else {
- fprintf(TH_LOG_STREAM,
- "%s: Test ended in some other way [%u]\n",
- t->name,
- status);
- }
+ __wait_for_test(t);
}
- printf("[ %4s ] %s\n", (t->passed ? "OK" : "FAIL"), t->name);
- alarm(0);
+ printf("[ %4s ] %s%s%s.%s\n", (t->passed ? "OK" : "FAIL"),
+ f->name, variant->name[0] ? "." : "", variant->name, t->name);
}
static int test_harness_run(int __attribute__((unused)) argc,
char __attribute__((unused)) **argv)
{
+ struct __fixture_variant_metadata no_variant = { .name = "", };
+ struct __fixture_variant_metadata *v;
+ struct __fixture_metadata *f;
struct __test_metadata *t;
int ret = 0;
+ unsigned int case_count = 0, test_count = 0;
unsigned int count = 0;
unsigned int pass_count = 0;
+ for (f = __fixture_list; f; f = f->next) {
+ for (v = f->variant ?: &no_variant; v; v = v->next) {
+ case_count++;
+ for (t = f->tests; t; t = t->next)
+ test_count++;
+ }
+ }
+
/* TODO(wad) add optional arguments similar to gtest. */
printf("[==========] Running %u tests from %u test cases.\n",
- __test_count, __fixture_count + 1);
- for (t = __test_list; t; t = t->next) {
- count++;
- __run_test(t);
- if (t->passed)
- pass_count++;
- else
- ret = 1;
+ test_count, case_count);
+ for (f = __fixture_list; f; f = f->next) {
+ for (v = f->variant ?: &no_variant; v; v = v->next) {
+ for (t = f->tests; t; t = t->next) {
+ count++;
+ __run_test(f, v, t);
+ if (t->passed)
+ pass_count++;
+ else
+ ret = 1;
+ }
+ }
}
printf("[==========] %u / %u tests passed.\n", pass_count, count);
printf("[ %s ]\n", (ret ? "FAILED" : "PASSED"));
diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index 30072c3f52fb..f159718f90c0 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -1,5 +1,7 @@
-/s390x/sync_regs_test
+# SPDX-License-Identifier: GPL-2.0-only
/s390x/memop
+/s390x/resets
+/s390x/sync_regs_test
/x86_64/cr4_cpuid_sync_test
/x86_64/evmcs_test
/x86_64/hyperv_cpuid
@@ -8,6 +10,8 @@
/x86_64/set_sregs_test
/x86_64/smm_test
/x86_64/state_test
+/x86_64/vmx_preemption_timer_test
+/x86_64/svm_vmcall_test
/x86_64/sync_regs_test
/x86_64/vmx_close_while_nested_test
/x86_64/vmx_dirty_log_test
@@ -15,5 +19,8 @@
/x86_64/vmx_tsc_adjust_test
/x86_64/xss_msr_test
/clear_dirty_log_test
+/demand_paging_test
/dirty_log_test
/kvm_create_max_vcpus
+/set_memory_region_test
+/steal_time
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index d91c53b726e6..b4ff112e5c7e 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -5,9 +5,35 @@ all:
top_srcdir = ../../../..
KSFT_KHDR_INSTALL := 1
+
+# For cross-builds to work, UNAME_M has to map to ARCH and arch specific
+# directories and targets in this Makefile. "uname -m" doesn't map to
+# arch specific sub-directory names.
+#
+# UNAME_M variable to used to run the compiles pointing to the right arch
+# directories and build the right targets for these supported architectures.
+#
+# TEST_GEN_PROGS and LIBKVM are set using UNAME_M variable.
+# LINUX_TOOL_ARCH_INCLUDE is set using ARCH variable.
+#
+# x86_64 targets are named to include x86_64 as a suffix and directories
+# for includes are in x86_64 sub-directory. s390x and aarch64 follow the
+# same convention. "uname -m" doesn't result in the correct mapping for
+# s390x and aarch64.
+#
+# No change necessary for x86_64
UNAME_M := $(shell uname -m)
-LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/sparsebit.c
+# Set UNAME_M for arm64 compile/install to work
+ifeq ($(ARCH),arm64)
+ UNAME_M := aarch64
+endif
+# Set UNAME_M s390x compile/install to work
+ifeq ($(ARCH),s390)
+ UNAME_M := s390x
+endif
+
+LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/sparsebit.c lib/test_util.c
LIBKVM_x86_64 = lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/svm.c lib/x86_64/ucall.c
LIBKVM_aarch64 = lib/aarch64/processor.c lib/aarch64/ucall.c
LIBKVM_s390x = lib/s390x/processor.c lib/s390x/ucall.c
@@ -20,26 +46,36 @@ TEST_GEN_PROGS_x86_64 += x86_64/platform_info_test
TEST_GEN_PROGS_x86_64 += x86_64/set_sregs_test
TEST_GEN_PROGS_x86_64 += x86_64/smm_test
TEST_GEN_PROGS_x86_64 += x86_64/state_test
+TEST_GEN_PROGS_x86_64 += x86_64/vmx_preemption_timer_test
+TEST_GEN_PROGS_x86_64 += x86_64/svm_vmcall_test
TEST_GEN_PROGS_x86_64 += x86_64/sync_regs_test
TEST_GEN_PROGS_x86_64 += x86_64/vmx_close_while_nested_test
TEST_GEN_PROGS_x86_64 += x86_64/vmx_dirty_log_test
TEST_GEN_PROGS_x86_64 += x86_64/vmx_set_nested_state_test
TEST_GEN_PROGS_x86_64 += x86_64/vmx_tsc_adjust_test
TEST_GEN_PROGS_x86_64 += x86_64/xss_msr_test
-TEST_GEN_PROGS_x86_64 += x86_64/svm_vmcall_test
+TEST_GEN_PROGS_x86_64 += x86_64/debug_regs
TEST_GEN_PROGS_x86_64 += clear_dirty_log_test
+TEST_GEN_PROGS_x86_64 += demand_paging_test
TEST_GEN_PROGS_x86_64 += dirty_log_test
TEST_GEN_PROGS_x86_64 += kvm_create_max_vcpus
+TEST_GEN_PROGS_x86_64 += set_memory_region_test
+TEST_GEN_PROGS_x86_64 += steal_time
TEST_GEN_PROGS_aarch64 += clear_dirty_log_test
+TEST_GEN_PROGS_aarch64 += demand_paging_test
TEST_GEN_PROGS_aarch64 += dirty_log_test
TEST_GEN_PROGS_aarch64 += kvm_create_max_vcpus
+TEST_GEN_PROGS_aarch64 += set_memory_region_test
+TEST_GEN_PROGS_aarch64 += steal_time
TEST_GEN_PROGS_s390x = s390x/memop
-TEST_GEN_PROGS_s390x += s390x/sync_regs_test
TEST_GEN_PROGS_s390x += s390x/resets
+TEST_GEN_PROGS_s390x += s390x/sync_regs_test
+TEST_GEN_PROGS_s390x += demand_paging_test
TEST_GEN_PROGS_s390x += dirty_log_test
TEST_GEN_PROGS_s390x += kvm_create_max_vcpus
+TEST_GEN_PROGS_s390x += set_memory_region_test
TEST_GEN_PROGS += $(TEST_GEN_PROGS_$(UNAME_M))
LIBKVM += $(LIBKVM_$(UNAME_M))
@@ -47,7 +83,7 @@ LIBKVM += $(LIBKVM_$(UNAME_M))
INSTALL_HDR_PATH = $(top_srcdir)/usr
LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/
LINUX_TOOL_INCLUDE = $(top_srcdir)/tools/include
-LINUX_TOOL_ARCH_INCLUDE = $(top_srcdir)/tools/arch/x86/include
+LINUX_TOOL_ARCH_INCLUDE = $(top_srcdir)/tools/arch/$(ARCH)/include
CFLAGS += -Wall -Wstrict-prototypes -Wuninitialized -O2 -g -std=gnu99 \
-fno-stack-protector -fno-PIE -I$(LINUX_TOOL_INCLUDE) \
-I$(LINUX_TOOL_ARCH_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude \
@@ -78,6 +114,7 @@ $(LIBKVM_OBJ): $(OUTPUT)/%.o: %.c
$(OUTPUT)/libkvm.a: $(LIBKVM_OBJ)
$(AR) crs $@ $^
+x := $(shell mkdir -p $(sort $(dir $(TEST_GEN_PROGS))))
all: $(STATIC_LIBS)
$(TEST_GEN_PROGS): $(STATIC_LIBS)
diff --git a/tools/testing/selftests/kvm/clear_dirty_log_test.c b/tools/testing/selftests/kvm/clear_dirty_log_test.c
index 749336937d37..11672ec6f74e 100644
--- a/tools/testing/selftests/kvm/clear_dirty_log_test.c
+++ b/tools/testing/selftests/kvm/clear_dirty_log_test.c
@@ -1,2 +1,6 @@
#define USE_CLEAR_DIRTY_LOG
+#define KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE (1 << 0)
+#define KVM_DIRTY_LOG_INITIALLY_SET (1 << 1)
+#define KVM_DIRTY_LOG_MANUAL_CAPS (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \
+ KVM_DIRTY_LOG_INITIALLY_SET)
#include "dirty_log_test.c"
diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c
new file mode 100644
index 000000000000..360cd3ea4cd6
--- /dev/null
+++ b/tools/testing/selftests/kvm/demand_paging_test.c
@@ -0,0 +1,661 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * KVM demand paging test
+ * Adapted from dirty_log_test.c
+ *
+ * Copyright (C) 2018, Red Hat, Inc.
+ * Copyright (C) 2019, Google, Inc.
+ */
+
+#define _GNU_SOURCE /* for program_invocation_name */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <sys/syscall.h>
+#include <unistd.h>
+#include <asm/unistd.h>
+#include <time.h>
+#include <poll.h>
+#include <pthread.h>
+#include <linux/bitmap.h>
+#include <linux/bitops.h>
+#include <linux/userfaultfd.h>
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+
+#ifdef __NR_userfaultfd
+
+/* The memory slot index demand page */
+#define TEST_MEM_SLOT_INDEX 1
+
+/* Default guest test virtual memory offset */
+#define DEFAULT_GUEST_TEST_MEM 0xc0000000
+
+#define DEFAULT_GUEST_TEST_MEM_SIZE (1 << 30) /* 1G */
+
+#ifdef PRINT_PER_PAGE_UPDATES
+#define PER_PAGE_DEBUG(...) printf(__VA_ARGS__)
+#else
+#define PER_PAGE_DEBUG(...) _no_printf(__VA_ARGS__)
+#endif
+
+#ifdef PRINT_PER_VCPU_UPDATES
+#define PER_VCPU_DEBUG(...) printf(__VA_ARGS__)
+#else
+#define PER_VCPU_DEBUG(...) _no_printf(__VA_ARGS__)
+#endif
+
+#define MAX_VCPUS 512
+
+/*
+ * Guest/Host shared variables. Ensure addr_gva2hva() and/or
+ * sync_global_to/from_guest() are used when accessing from
+ * the host. READ/WRITE_ONCE() should also be used with anything
+ * that may change.
+ */
+static uint64_t host_page_size;
+static uint64_t guest_page_size;
+
+static char *guest_data_prototype;
+
+/*
+ * Guest physical memory offset of the testing memory slot.
+ * This will be set to the topmost valid physical address minus
+ * the test memory size.
+ */
+static uint64_t guest_test_phys_mem;
+
+/*
+ * Guest virtual memory offset of the testing memory slot.
+ * Must not conflict with identity mapped test code.
+ */
+static uint64_t guest_test_virt_mem = DEFAULT_GUEST_TEST_MEM;
+
+struct vcpu_args {
+ uint64_t gva;
+ uint64_t pages;
+
+ /* Only used by the host userspace part of the vCPU thread */
+ int vcpu_id;
+ struct kvm_vm *vm;
+};
+
+static struct vcpu_args vcpu_args[MAX_VCPUS];
+
+/*
+ * Continuously write to the first 8 bytes of each page in the demand paging
+ * memory region.
+ */
+static void guest_code(uint32_t vcpu_id)
+{
+ uint64_t gva;
+ uint64_t pages;
+ int i;
+
+ /* Make sure vCPU args data structure is not corrupt. */
+ GUEST_ASSERT(vcpu_args[vcpu_id].vcpu_id == vcpu_id);
+
+ gva = vcpu_args[vcpu_id].gva;
+ pages = vcpu_args[vcpu_id].pages;
+
+ for (i = 0; i < pages; i++) {
+ uint64_t addr = gva + (i * guest_page_size);
+
+ addr &= ~(host_page_size - 1);
+ *(uint64_t *)addr = 0x0123456789ABCDEF;
+ }
+
+ GUEST_SYNC(1);
+}
+
+static void *vcpu_worker(void *data)
+{
+ int ret;
+ struct vcpu_args *args = (struct vcpu_args *)data;
+ struct kvm_vm *vm = args->vm;
+ int vcpu_id = args->vcpu_id;
+ struct kvm_run *run;
+ struct timespec start, end, ts_diff;
+
+ vcpu_args_set(vm, vcpu_id, 1, vcpu_id);
+ run = vcpu_state(vm, vcpu_id);
+
+ clock_gettime(CLOCK_MONOTONIC, &start);
+
+ /* Let the guest access its memory */
+ ret = _vcpu_run(vm, vcpu_id);
+ TEST_ASSERT(ret == 0, "vcpu_run failed: %d\n", ret);
+ if (get_ucall(vm, vcpu_id, NULL) != UCALL_SYNC) {
+ TEST_ASSERT(false,
+ "Invalid guest sync status: exit_reason=%s\n",
+ exit_reason_str(run->exit_reason));
+ }
+
+ clock_gettime(CLOCK_MONOTONIC, &end);
+ ts_diff = timespec_sub(end, start);
+ PER_VCPU_DEBUG("vCPU %d execution time: %ld.%.9lds\n", vcpu_id,
+ ts_diff.tv_sec, ts_diff.tv_nsec);
+
+ return NULL;
+}
+
+#define PAGE_SHIFT_4K 12
+#define PTES_PER_4K_PT 512
+
+static struct kvm_vm *create_vm(enum vm_guest_mode mode, int vcpus,
+ uint64_t vcpu_memory_bytes)
+{
+ struct kvm_vm *vm;
+ uint64_t pages = DEFAULT_GUEST_PHY_PAGES;
+
+ /* Account for a few pages per-vCPU for stacks */
+ pages += DEFAULT_STACK_PGS * vcpus;
+
+ /*
+ * Reserve twice the ammount of memory needed to map the test region and
+ * the page table / stacks region, at 4k, for page tables. Do the
+ * calculation with 4K page size: the smallest of all archs. (e.g., 64K
+ * page size guest will need even less memory for page tables).
+ */
+ pages += (2 * pages) / PTES_PER_4K_PT;
+ pages += ((2 * vcpus * vcpu_memory_bytes) >> PAGE_SHIFT_4K) /
+ PTES_PER_4K_PT;
+ pages = vm_adjust_num_guest_pages(mode, pages);
+
+ pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode));
+
+ vm = _vm_create(mode, pages, O_RDWR);
+ kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
+#ifdef __x86_64__
+ vm_create_irqchip(vm);
+#endif
+ return vm;
+}
+
+static int handle_uffd_page_request(int uffd, uint64_t addr)
+{
+ pid_t tid;
+ struct timespec start;
+ struct timespec end;
+ struct uffdio_copy copy;
+ int r;
+
+ tid = syscall(__NR_gettid);
+
+ copy.src = (uint64_t)guest_data_prototype;
+ copy.dst = addr;
+ copy.len = host_page_size;
+ copy.mode = 0;
+
+ clock_gettime(CLOCK_MONOTONIC, &start);
+
+ r = ioctl(uffd, UFFDIO_COPY, &copy);
+ if (r == -1) {
+ pr_info("Failed Paged in 0x%lx from thread %d with errno: %d\n",
+ addr, tid, errno);
+ return r;
+ }
+
+ clock_gettime(CLOCK_MONOTONIC, &end);
+
+ PER_PAGE_DEBUG("UFFDIO_COPY %d \t%ld ns\n", tid,
+ timespec_to_ns(timespec_sub(end, start)));
+ PER_PAGE_DEBUG("Paged in %ld bytes at 0x%lx from thread %d\n",
+ host_page_size, addr, tid);
+
+ return 0;
+}
+
+bool quit_uffd_thread;
+
+struct uffd_handler_args {
+ int uffd;
+ int pipefd;
+ useconds_t delay;
+};
+
+static void *uffd_handler_thread_fn(void *arg)
+{
+ struct uffd_handler_args *uffd_args = (struct uffd_handler_args *)arg;
+ int uffd = uffd_args->uffd;
+ int pipefd = uffd_args->pipefd;
+ useconds_t delay = uffd_args->delay;
+ int64_t pages = 0;
+ struct timespec start, end, ts_diff;
+
+ clock_gettime(CLOCK_MONOTONIC, &start);
+ while (!quit_uffd_thread) {
+ struct uffd_msg msg;
+ struct pollfd pollfd[2];
+ char tmp_chr;
+ int r;
+ uint64_t addr;
+
+ pollfd[0].fd = uffd;
+ pollfd[0].events = POLLIN;
+ pollfd[1].fd = pipefd;
+ pollfd[1].events = POLLIN;
+
+ r = poll(pollfd, 2, -1);
+ switch (r) {
+ case -1:
+ pr_info("poll err");
+ continue;
+ case 0:
+ continue;
+ case 1:
+ break;
+ default:
+ pr_info("Polling uffd returned %d", r);
+ return NULL;
+ }
+
+ if (pollfd[0].revents & POLLERR) {
+ pr_info("uffd revents has POLLERR");
+ return NULL;
+ }
+
+ if (pollfd[1].revents & POLLIN) {
+ r = read(pollfd[1].fd, &tmp_chr, 1);
+ TEST_ASSERT(r == 1,
+ "Error reading pipefd in UFFD thread\n");
+ return NULL;
+ }
+
+ if (!pollfd[0].revents & POLLIN)
+ continue;
+
+ r = read(uffd, &msg, sizeof(msg));
+ if (r == -1) {
+ if (errno == EAGAIN)
+ continue;
+ pr_info("Read of uffd gor errno %d", errno);
+ return NULL;
+ }
+
+ if (r != sizeof(msg)) {
+ pr_info("Read on uffd returned unexpected size: %d bytes", r);
+ return NULL;
+ }
+
+ if (!(msg.event & UFFD_EVENT_PAGEFAULT))
+ continue;
+
+ if (delay)
+ usleep(delay);
+ addr = msg.arg.pagefault.address;
+ r = handle_uffd_page_request(uffd, addr);
+ if (r < 0)
+ return NULL;
+ pages++;
+ }
+
+ clock_gettime(CLOCK_MONOTONIC, &end);
+ ts_diff = timespec_sub(end, start);
+ PER_VCPU_DEBUG("userfaulted %ld pages over %ld.%.9lds. (%f/sec)\n",
+ pages, ts_diff.tv_sec, ts_diff.tv_nsec,
+ pages / ((double)ts_diff.tv_sec + (double)ts_diff.tv_nsec / 100000000.0));
+
+ return NULL;
+}
+
+static int setup_demand_paging(struct kvm_vm *vm,
+ pthread_t *uffd_handler_thread, int pipefd,
+ useconds_t uffd_delay,
+ struct uffd_handler_args *uffd_args,
+ void *hva, uint64_t len)
+{
+ int uffd;
+ struct uffdio_api uffdio_api;
+ struct uffdio_register uffdio_register;
+
+ uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK);
+ if (uffd == -1) {
+ pr_info("uffd creation failed\n");
+ return -1;
+ }
+
+ uffdio_api.api = UFFD_API;
+ uffdio_api.features = 0;
+ if (ioctl(uffd, UFFDIO_API, &uffdio_api) == -1) {
+ pr_info("ioctl uffdio_api failed\n");
+ return -1;
+ }
+
+ uffdio_register.range.start = (uint64_t)hva;
+ uffdio_register.range.len = len;
+ uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING;
+ if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register) == -1) {
+ pr_info("ioctl uffdio_register failed\n");
+ return -1;
+ }
+
+ if ((uffdio_register.ioctls & UFFD_API_RANGE_IOCTLS) !=
+ UFFD_API_RANGE_IOCTLS) {
+ pr_info("unexpected userfaultfd ioctl set\n");
+ return -1;
+ }
+
+ uffd_args->uffd = uffd;
+ uffd_args->pipefd = pipefd;
+ uffd_args->delay = uffd_delay;
+ pthread_create(uffd_handler_thread, NULL, uffd_handler_thread_fn,
+ uffd_args);
+
+ PER_VCPU_DEBUG("Created uffd thread for HVA range [%p, %p)\n",
+ hva, hva + len);
+
+ return 0;
+}
+
+static void run_test(enum vm_guest_mode mode, bool use_uffd,
+ useconds_t uffd_delay, int vcpus,
+ uint64_t vcpu_memory_bytes)
+{
+ pthread_t *vcpu_threads;
+ pthread_t *uffd_handler_threads = NULL;
+ struct uffd_handler_args *uffd_args = NULL;
+ struct timespec start, end, ts_diff;
+ int *pipefds = NULL;
+ struct kvm_vm *vm;
+ uint64_t guest_num_pages;
+ int vcpu_id;
+ int r;
+
+ vm = create_vm(mode, vcpus, vcpu_memory_bytes);
+
+ guest_page_size = vm_get_page_size(vm);
+
+ TEST_ASSERT(vcpu_memory_bytes % guest_page_size == 0,
+ "Guest memory size is not guest page size aligned.");
+
+ guest_num_pages = (vcpus * vcpu_memory_bytes) / guest_page_size;
+ guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages);
+
+ /*
+ * If there should be more memory in the guest test region than there
+ * can be pages in the guest, it will definitely cause problems.
+ */
+ TEST_ASSERT(guest_num_pages < vm_get_max_gfn(vm),
+ "Requested more guest memory than address space allows.\n"
+ " guest pages: %lx max gfn: %x vcpus: %d wss: %lx]\n",
+ guest_num_pages, vm_get_max_gfn(vm), vcpus,
+ vcpu_memory_bytes);
+
+ host_page_size = getpagesize();
+ TEST_ASSERT(vcpu_memory_bytes % host_page_size == 0,
+ "Guest memory size is not host page size aligned.");
+
+ guest_test_phys_mem = (vm_get_max_gfn(vm) - guest_num_pages) *
+ guest_page_size;
+ guest_test_phys_mem &= ~(host_page_size - 1);
+
+#ifdef __s390x__
+ /* Align to 1M (segment size) */
+ guest_test_phys_mem &= ~((1 << 20) - 1);
+#endif
+
+ pr_info("guest physical test memory offset: 0x%lx\n", guest_test_phys_mem);
+
+ /* Add an extra memory slot for testing demand paging */
+ vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
+ guest_test_phys_mem,
+ TEST_MEM_SLOT_INDEX,
+ guest_num_pages, 0);
+
+ /* Do mapping for the demand paging memory slot */
+ virt_map(vm, guest_test_virt_mem, guest_test_phys_mem, guest_num_pages, 0);
+
+ ucall_init(vm, NULL);
+
+ guest_data_prototype = malloc(host_page_size);
+ TEST_ASSERT(guest_data_prototype,
+ "Failed to allocate buffer for guest data pattern");
+ memset(guest_data_prototype, 0xAB, host_page_size);
+
+ vcpu_threads = malloc(vcpus * sizeof(*vcpu_threads));
+ TEST_ASSERT(vcpu_threads, "Memory allocation failed");
+
+ if (use_uffd) {
+ uffd_handler_threads =
+ malloc(vcpus * sizeof(*uffd_handler_threads));
+ TEST_ASSERT(uffd_handler_threads, "Memory allocation failed");
+
+ uffd_args = malloc(vcpus * sizeof(*uffd_args));
+ TEST_ASSERT(uffd_args, "Memory allocation failed");
+
+ pipefds = malloc(sizeof(int) * vcpus * 2);
+ TEST_ASSERT(pipefds, "Unable to allocate memory for pipefd");
+ }
+
+ for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) {
+ vm_paddr_t vcpu_gpa;
+ void *vcpu_hva;
+
+ vm_vcpu_add_default(vm, vcpu_id, guest_code);
+
+ vcpu_gpa = guest_test_phys_mem + (vcpu_id * vcpu_memory_bytes);
+ PER_VCPU_DEBUG("Added VCPU %d with test mem gpa [%lx, %lx)\n",
+ vcpu_id, vcpu_gpa, vcpu_gpa + vcpu_memory_bytes);
+
+ /* Cache the HVA pointer of the region */
+ vcpu_hva = addr_gpa2hva(vm, vcpu_gpa);
+
+ if (use_uffd) {
+ /*
+ * Set up user fault fd to handle demand paging
+ * requests.
+ */
+ r = pipe2(&pipefds[vcpu_id * 2],
+ O_CLOEXEC | O_NONBLOCK);
+ TEST_ASSERT(!r, "Failed to set up pipefd");
+
+ r = setup_demand_paging(vm,
+ &uffd_handler_threads[vcpu_id],
+ pipefds[vcpu_id * 2],
+ uffd_delay, &uffd_args[vcpu_id],
+ vcpu_hva, vcpu_memory_bytes);
+ if (r < 0)
+ exit(-r);
+ }
+
+#ifdef __x86_64__
+ vcpu_set_cpuid(vm, vcpu_id, kvm_get_supported_cpuid());
+#endif
+
+ vcpu_args[vcpu_id].vm = vm;
+ vcpu_args[vcpu_id].vcpu_id = vcpu_id;
+ vcpu_args[vcpu_id].gva = guest_test_virt_mem +
+ (vcpu_id * vcpu_memory_bytes);
+ vcpu_args[vcpu_id].pages = vcpu_memory_bytes / guest_page_size;
+ }
+
+ /* Export the shared variables to the guest */
+ sync_global_to_guest(vm, host_page_size);
+ sync_global_to_guest(vm, guest_page_size);
+ sync_global_to_guest(vm, vcpu_args);
+
+ pr_info("Finished creating vCPUs and starting uffd threads\n");
+
+ clock_gettime(CLOCK_MONOTONIC, &start);
+
+ for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) {
+ pthread_create(&vcpu_threads[vcpu_id], NULL, vcpu_worker,
+ &vcpu_args[vcpu_id]);
+ }
+
+ pr_info("Started all vCPUs\n");
+
+ /* Wait for the vcpu threads to quit */
+ for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) {
+ pthread_join(vcpu_threads[vcpu_id], NULL);
+ PER_VCPU_DEBUG("Joined thread for vCPU %d\n", vcpu_id);
+ }
+
+ pr_info("All vCPU threads joined\n");
+
+ clock_gettime(CLOCK_MONOTONIC, &end);
+
+ if (use_uffd) {
+ char c;
+
+ /* Tell the user fault fd handler threads to quit */
+ for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) {
+ r = write(pipefds[vcpu_id * 2 + 1], &c, 1);
+ TEST_ASSERT(r == 1, "Unable to write to pipefd");
+
+ pthread_join(uffd_handler_threads[vcpu_id], NULL);
+ }
+ }
+
+ ts_diff = timespec_sub(end, start);
+ pr_info("Total guest execution time: %ld.%.9lds\n",
+ ts_diff.tv_sec, ts_diff.tv_nsec);
+ pr_info("Overall demand paging rate: %f pgs/sec\n",
+ guest_num_pages / ((double)ts_diff.tv_sec + (double)ts_diff.tv_nsec / 100000000.0));
+
+ ucall_uninit(vm);
+ kvm_vm_free(vm);
+
+ free(guest_data_prototype);
+ free(vcpu_threads);
+ if (use_uffd) {
+ free(uffd_handler_threads);
+ free(uffd_args);
+ free(pipefds);
+ }
+}
+
+struct guest_mode {
+ bool supported;
+ bool enabled;
+};
+static struct guest_mode guest_modes[NUM_VM_MODES];
+
+#define guest_mode_init(mode, supported, enabled) ({ \
+ guest_modes[mode] = (struct guest_mode){ supported, enabled }; \
+})
+
+static void help(char *name)
+{
+ int i;
+
+ puts("");
+ printf("usage: %s [-h] [-m mode] [-u] [-d uffd_delay_usec]\n"
+ " [-b memory] [-v vcpus]\n", name);
+ printf(" -m: specify the guest mode ID to test\n"
+ " (default: test all supported modes)\n"
+ " This option may be used multiple times.\n"
+ " Guest mode IDs:\n");
+ for (i = 0; i < NUM_VM_MODES; ++i) {
+ printf(" %d: %s%s\n", i, vm_guest_mode_string(i),
+ guest_modes[i].supported ? " (supported)" : "");
+ }
+ printf(" -u: use User Fault FD to handle vCPU page\n"
+ " faults.\n");
+ printf(" -d: add a delay in usec to the User Fault\n"
+ " FD handler to simulate demand paging\n"
+ " overheads. Ignored without -u.\n");
+ printf(" -b: specify the size of the memory region which should be\n"
+ " demand paged by each vCPU. e.g. 10M or 3G.\n"
+ " Default: 1G\n");
+ printf(" -v: specify the number of vCPUs to run.\n");
+ puts("");
+ exit(0);
+}
+
+int main(int argc, char *argv[])
+{
+ bool mode_selected = false;
+ uint64_t vcpu_memory_bytes = DEFAULT_GUEST_TEST_MEM_SIZE;
+ int vcpus = 1;
+ unsigned int mode;
+ int opt, i;
+ bool use_uffd = false;
+ useconds_t uffd_delay = 0;
+
+#ifdef __x86_64__
+ guest_mode_init(VM_MODE_PXXV48_4K, true, true);
+#endif
+#ifdef __aarch64__
+ guest_mode_init(VM_MODE_P40V48_4K, true, true);
+ guest_mode_init(VM_MODE_P40V48_64K, true, true);
+ {
+ unsigned int limit = kvm_check_cap(KVM_CAP_ARM_VM_IPA_SIZE);
+
+ if (limit >= 52)
+ guest_mode_init(VM_MODE_P52V48_64K, true, true);
+ if (limit >= 48) {
+ guest_mode_init(VM_MODE_P48V48_4K, true, true);
+ guest_mode_init(VM_MODE_P48V48_64K, true, true);
+ }
+ }
+#endif
+#ifdef __s390x__
+ guest_mode_init(VM_MODE_P40V48_4K, true, true);
+#endif
+
+ while ((opt = getopt(argc, argv, "hm:ud:b:v:")) != -1) {
+ switch (opt) {
+ case 'm':
+ if (!mode_selected) {
+ for (i = 0; i < NUM_VM_MODES; ++i)
+ guest_modes[i].enabled = false;
+ mode_selected = true;
+ }
+ mode = strtoul(optarg, NULL, 10);
+ TEST_ASSERT(mode < NUM_VM_MODES,
+ "Guest mode ID %d too big", mode);
+ guest_modes[mode].enabled = true;
+ break;
+ case 'u':
+ use_uffd = true;
+ break;
+ case 'd':
+ uffd_delay = strtoul(optarg, NULL, 0);
+ TEST_ASSERT(uffd_delay >= 0,
+ "A negative UFFD delay is not supported.");
+ break;
+ case 'b':
+ vcpu_memory_bytes = parse_size(optarg);
+ break;
+ case 'v':
+ vcpus = atoi(optarg);
+ TEST_ASSERT(vcpus > 0,
+ "Must have a positive number of vCPUs");
+ TEST_ASSERT(vcpus <= MAX_VCPUS,
+ "This test does not currently support\n"
+ "more than %d vCPUs.", MAX_VCPUS);
+ break;
+ case 'h':
+ default:
+ help(argv[0]);
+ break;
+ }
+ }
+
+ for (i = 0; i < NUM_VM_MODES; ++i) {
+ if (!guest_modes[i].enabled)
+ continue;
+ TEST_ASSERT(guest_modes[i].supported,
+ "Guest mode ID %d (%s) not supported.",
+ i, vm_guest_mode_string(i));
+ run_test(i, use_uffd, uffd_delay, vcpus, vcpu_memory_bytes);
+ }
+
+ return 0;
+}
+
+#else /* __NR_userfaultfd */
+
+#warning "missing __NR_userfaultfd definition"
+
+int main(void)
+{
+ print_skip("__NR_userfaultfd must be present for userfaultfd test");
+ return KSFT_SKIP;
+}
+
+#endif /* __NR_userfaultfd */
diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c
index 5614222a6628..752ec158ac59 100644
--- a/tools/testing/selftests/kvm/dirty_log_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_test.c
@@ -166,24 +166,22 @@ static void *vcpu_worker(void *data)
pages_count += TEST_PAGES_PER_LOOP;
generate_random_array(guest_array, TEST_PAGES_PER_LOOP);
} else {
- TEST_ASSERT(false,
- "Invalid guest sync status: "
- "exit_reason=%s\n",
- exit_reason_str(run->exit_reason));
+ TEST_FAIL("Invalid guest sync status: "
+ "exit_reason=%s\n",
+ exit_reason_str(run->exit_reason));
}
}
- DEBUG("Dirtied %"PRIu64" pages\n", pages_count);
+ pr_info("Dirtied %"PRIu64" pages\n", pages_count);
return NULL;
}
-static void vm_dirty_log_verify(unsigned long *bmap)
+static void vm_dirty_log_verify(enum vm_guest_mode mode, unsigned long *bmap)
{
+ uint64_t step = vm_num_host_pages(mode, 1);
uint64_t page;
uint64_t *value_ptr;
- uint64_t step = host_page_size >= guest_page_size ? 1 :
- guest_page_size / host_page_size;
for (page = 0; page < host_num_pages; page += step) {
value_ptr = host_test_mem + page * host_page_size;
@@ -252,6 +250,8 @@ static struct kvm_vm *create_vm(enum vm_guest_mode mode, uint32_t vcpuid,
struct kvm_vm *vm;
uint64_t extra_pg_pages = extra_mem_pages / 512 * 2;
+ pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode));
+
vm = _vm_create(mode, DEFAULT_GUEST_PHY_PAGES + extra_pg_pages, O_RDWR);
kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
#ifdef __x86_64__
@@ -264,6 +264,10 @@ static struct kvm_vm *create_vm(enum vm_guest_mode mode, uint32_t vcpuid,
#define DIRTY_MEM_BITS 30 /* 1G */
#define PAGE_SHIFT_4K 12
+#ifdef USE_CLEAR_DIRTY_LOG
+static u64 dirty_log_manual_caps;
+#endif
+
static void run_test(enum vm_guest_mode mode, unsigned long iterations,
unsigned long interval, uint64_t phys_offset)
{
@@ -289,14 +293,11 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
* case where the size is not aligned to 64 pages.
*/
guest_num_pages = (1ul << (DIRTY_MEM_BITS -
- vm_get_page_shift(vm))) + 16;
-#ifdef __s390x__
- /* Round up to multiple of 1M (segment size) */
- guest_num_pages = (guest_num_pages + 0xff) & ~0xffUL;
-#endif
+ vm_get_page_shift(vm))) + 3;
+ guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages);
+
host_page_size = getpagesize();
- host_num_pages = (guest_num_pages * guest_page_size) / host_page_size +
- !!((guest_num_pages * guest_page_size) % host_page_size);
+ host_num_pages = vm_num_host_pages(mode, guest_num_pages);
if (!phys_offset) {
guest_test_phys_mem = (vm_get_max_gfn(vm) -
@@ -311,7 +312,7 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
guest_test_phys_mem &= ~((1 << 20) - 1);
#endif
- DEBUG("guest physical test memory offset: 0x%lx\n", guest_test_phys_mem);
+ pr_info("guest physical test memory offset: 0x%lx\n", guest_test_phys_mem);
bmap = bitmap_alloc(host_num_pages);
host_bmap_track = bitmap_alloc(host_num_pages);
@@ -320,7 +321,7 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
struct kvm_enable_cap cap = {};
cap.cap = KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2;
- cap.args[0] = 1;
+ cap.args[0] = dirty_log_manual_caps;
vm_enable_cap(vm, &cap);
#endif
@@ -332,8 +333,7 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
KVM_MEM_LOG_DIRTY_PAGES);
/* Do mapping for the dirty track memory slot */
- virt_map(vm, guest_test_virt_mem, guest_test_phys_mem,
- guest_num_pages * guest_page_size, 0);
+ virt_map(vm, guest_test_virt_mem, guest_test_phys_mem, guest_num_pages, 0);
/* Cache the HVA pointer of the region */
host_test_mem = addr_gpa2hva(vm, (vm_paddr_t)guest_test_phys_mem);
@@ -341,9 +341,7 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
#ifdef __x86_64__
vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
#endif
-#ifdef __aarch64__
ucall_init(vm, NULL);
-#endif
/* Export the shared variables to the guest */
sync_global_to_guest(vm, host_page_size);
@@ -369,7 +367,7 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
kvm_vm_clear_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap, 0,
host_num_pages);
#endif
- vm_dirty_log_verify(bmap);
+ vm_dirty_log_verify(mode, bmap);
iteration++;
sync_global_to_guest(vm, iteration);
}
@@ -378,9 +376,9 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
host_quit = true;
pthread_join(vcpu_thread, NULL);
- DEBUG("Total bits checked: dirty (%"PRIu64"), clear (%"PRIu64"), "
- "track_next (%"PRIu64")\n", host_dirty_count, host_clear_count,
- host_track_next_count);
+ pr_info("Total bits checked: dirty (%"PRIu64"), clear (%"PRIu64"), "
+ "track_next (%"PRIu64")\n", host_dirty_count, host_clear_count,
+ host_track_next_count);
free(bmap);
free(host_bmap_track);
@@ -388,15 +386,14 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
kvm_vm_free(vm);
}
-struct vm_guest_mode_params {
+struct guest_mode {
bool supported;
bool enabled;
};
-struct vm_guest_mode_params vm_guest_mode_params[NUM_VM_MODES];
+static struct guest_mode guest_modes[NUM_VM_MODES];
-#define vm_guest_mode_params_init(mode, supported, enabled) \
-({ \
- vm_guest_mode_params[mode] = (struct vm_guest_mode_params){ supported, enabled }; \
+#define guest_mode_init(mode, supported, enabled) ({ \
+ guest_modes[mode] = (struct guest_mode){ supported, enabled }; \
})
static void help(char *name)
@@ -419,7 +416,7 @@ static void help(char *name)
" Guest mode IDs:\n");
for (i = 0; i < NUM_VM_MODES; ++i) {
printf(" %d: %s%s\n", i, vm_guest_mode_string(i),
- vm_guest_mode_params[i].supported ? " (supported)" : "");
+ guest_modes[i].supported ? " (supported)" : "");
}
puts("");
exit(0);
@@ -433,34 +430,38 @@ int main(int argc, char *argv[])
uint64_t phys_offset = 0;
unsigned int mode;
int opt, i;
-#ifdef __aarch64__
- unsigned int host_ipa_limit;
-#endif
#ifdef USE_CLEAR_DIRTY_LOG
- if (!kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2)) {
- fprintf(stderr, "KVM_CLEAR_DIRTY_LOG not available, skipping tests\n");
+ dirty_log_manual_caps =
+ kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2);
+ if (!dirty_log_manual_caps) {
+ print_skip("KVM_CLEAR_DIRTY_LOG not available");
exit(KSFT_SKIP);
}
+ dirty_log_manual_caps &= (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE |
+ KVM_DIRTY_LOG_INITIALLY_SET);
#endif
#ifdef __x86_64__
- vm_guest_mode_params_init(VM_MODE_PXXV48_4K, true, true);
+ guest_mode_init(VM_MODE_PXXV48_4K, true, true);
#endif
#ifdef __aarch64__
- vm_guest_mode_params_init(VM_MODE_P40V48_4K, true, true);
- vm_guest_mode_params_init(VM_MODE_P40V48_64K, true, true);
-
- host_ipa_limit = kvm_check_cap(KVM_CAP_ARM_VM_IPA_SIZE);
- if (host_ipa_limit >= 52)
- vm_guest_mode_params_init(VM_MODE_P52V48_64K, true, true);
- if (host_ipa_limit >= 48) {
- vm_guest_mode_params_init(VM_MODE_P48V48_4K, true, true);
- vm_guest_mode_params_init(VM_MODE_P48V48_64K, true, true);
+ guest_mode_init(VM_MODE_P40V48_4K, true, true);
+ guest_mode_init(VM_MODE_P40V48_64K, true, true);
+
+ {
+ unsigned int limit = kvm_check_cap(KVM_CAP_ARM_VM_IPA_SIZE);
+
+ if (limit >= 52)
+ guest_mode_init(VM_MODE_P52V48_64K, true, true);
+ if (limit >= 48) {
+ guest_mode_init(VM_MODE_P48V48_4K, true, true);
+ guest_mode_init(VM_MODE_P48V48_64K, true, true);
+ }
}
#endif
#ifdef __s390x__
- vm_guest_mode_params_init(VM_MODE_P40V48_4K, true, true);
+ guest_mode_init(VM_MODE_P40V48_4K, true, true);
#endif
while ((opt = getopt(argc, argv, "hi:I:p:m:")) != -1) {
@@ -477,13 +478,13 @@ int main(int argc, char *argv[])
case 'm':
if (!mode_selected) {
for (i = 0; i < NUM_VM_MODES; ++i)
- vm_guest_mode_params[i].enabled = false;
+ guest_modes[i].enabled = false;
mode_selected = true;
}
mode = strtoul(optarg, NULL, 10);
TEST_ASSERT(mode < NUM_VM_MODES,
"Guest mode ID %d too big", mode);
- vm_guest_mode_params[mode].enabled = true;
+ guest_modes[mode].enabled = true;
break;
case 'h':
default:
@@ -495,15 +496,15 @@ int main(int argc, char *argv[])
TEST_ASSERT(iterations > 2, "Iterations must be greater than two");
TEST_ASSERT(interval > 0, "Interval must be greater than zero");
- DEBUG("Test iterations: %"PRIu64", interval: %"PRIu64" (ms)\n",
- iterations, interval);
+ pr_info("Test iterations: %"PRIu64", interval: %"PRIu64" (ms)\n",
+ iterations, interval);
srandom(time(0));
for (i = 0; i < NUM_VM_MODES; ++i) {
- if (!vm_guest_mode_params[i].enabled)
+ if (!guest_modes[i].enabled)
continue;
- TEST_ASSERT(vm_guest_mode_params[i].supported,
+ TEST_ASSERT(guest_modes[i].supported,
"Guest mode ID %d (%s) not supported.",
i, vm_guest_mode_string(i));
run_test(i, iterations, interval, phys_offset);
diff --git a/tools/testing/selftests/kvm/include/evmcs.h b/tools/testing/selftests/kvm/include/evmcs.h
index 4912d23844bc..a034438b6266 100644
--- a/tools/testing/selftests/kvm/include/evmcs.h
+++ b/tools/testing/selftests/kvm/include/evmcs.h
@@ -16,6 +16,8 @@
#define u32 uint32_t
#define u64 uint64_t
+#define EVMCS_VERSION 1
+
extern bool enable_evmcs;
struct hv_vp_assist_page {
@@ -217,8 +219,8 @@ struct hv_enlightened_vmcs {
#define HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_MASK \
(~((1ull << HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT) - 1))
-struct hv_enlightened_vmcs *current_evmcs;
-struct hv_vp_assist_page *current_vp_assist;
+extern struct hv_enlightened_vmcs *current_evmcs;
+extern struct hv_vp_assist_page *current_vp_assist;
int vcpu_enable_evmcs(struct kvm_vm *vm, int vcpu_id);
diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index ae0d14c2540a..919e161dd289 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -10,13 +10,15 @@
#include "test_util.h"
#include "asm/kvm.h"
+#include "linux/list.h"
#include "linux/kvm.h"
#include <sys/ioctl.h>
#include "sparsebit.h"
-/* Callers of kvm_util only have an incomplete/opaque description of the
+/*
+ * Callers of kvm_util only have an incomplete/opaque description of the
* structure kvm_util is using to maintain the state of a VM.
*/
struct kvm_vm;
@@ -24,12 +26,6 @@ struct kvm_vm;
typedef uint64_t vm_paddr_t; /* Virtual Machine (Guest) physical address */
typedef uint64_t vm_vaddr_t; /* Virtual Machine (Guest) virtual address */
-#ifndef NDEBUG
-#define DEBUG(...) printf(__VA_ARGS__);
-#else
-#define DEBUG(...)
-#endif
-
/* Minimum allocated guest virtual and physical addresses */
#define KVM_UTIL_MIN_VADDR 0x2000
@@ -84,6 +80,23 @@ void kvm_vm_elf_load(struct kvm_vm *vm, const char *filename,
uint32_t data_memslot, uint32_t pgd_memslot);
void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent);
+
+/*
+ * VM VCPU Dump
+ *
+ * Input Args:
+ * stream - Output FILE stream
+ * vm - Virtual Machine
+ * vcpuid - VCPU ID
+ * indent - Left margin indent amount
+ *
+ * Output Args: None
+ *
+ * Return: None
+ *
+ * Dumps the current state of the VCPU specified by @vcpuid, within the VM
+ * given by @vm, to the FILE stream given by @stream.
+ */
void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid,
uint8_t indent);
@@ -100,25 +113,65 @@ int _vcpu_ioctl(struct kvm_vm *vm, uint32_t vcpuid, unsigned long ioctl,
void *arg);
void vm_ioctl(struct kvm_vm *vm, unsigned long ioctl, void *arg);
void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags);
+void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa);
+void vm_mem_region_delete(struct kvm_vm *vm, uint32_t slot);
void vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpuid);
vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min,
uint32_t data_memslot, uint32_t pgd_memslot);
void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
- size_t size, uint32_t pgd_memslot);
+ unsigned int npages, uint32_t pgd_memslot);
void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa);
void *addr_gva2hva(struct kvm_vm *vm, vm_vaddr_t gva);
vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva);
+
+/*
+ * Address Guest Virtual to Guest Physical
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * gva - VM virtual address
+ *
+ * Output Args: None
+ *
+ * Return:
+ * Equivalent VM physical address
+ *
+ * Returns the VM physical address of the translated VM virtual
+ * address given by @gva.
+ */
vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva);
struct kvm_run *vcpu_state(struct kvm_vm *vm, uint32_t vcpuid);
void vcpu_run(struct kvm_vm *vm, uint32_t vcpuid);
int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid);
void vcpu_run_complete_io(struct kvm_vm *vm, uint32_t vcpuid);
+void vcpu_set_guest_debug(struct kvm_vm *vm, uint32_t vcpuid,
+ struct kvm_guest_debug *debug);
void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid,
struct kvm_mp_state *mp_state);
void vcpu_regs_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs);
void vcpu_regs_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs);
+
+/*
+ * VM VCPU Args Set
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * vcpuid - VCPU ID
+ * num - number of arguments
+ * ... - arguments, each of type uint64_t
+ *
+ * Output Args: None
+ *
+ * Return: None
+ *
+ * Sets the first @num function input registers of the VCPU with @vcpuid,
+ * per the C calling convention of the architecture, to the values given
+ * as variable args. Each of the variable args is expected to be of type
+ * uint64_t. The maximum @num can be is specific to the architecture.
+ */
void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...);
+
void vcpu_sregs_get(struct kvm_vm *vm, uint32_t vcpuid,
struct kvm_sregs *sregs);
void vcpu_sregs_set(struct kvm_vm *vm, uint32_t vcpuid,
@@ -147,15 +200,57 @@ int vcpu_nested_state_set(struct kvm_vm *vm, uint32_t vcpuid,
const char *exit_reason_str(unsigned int exit_reason);
void virt_pgd_alloc(struct kvm_vm *vm, uint32_t pgd_memslot);
+
+/*
+ * VM Virtual Page Map
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * vaddr - VM Virtual Address
+ * paddr - VM Physical Address
+ * memslot - Memory region slot for new virtual translation tables
+ *
+ * Output Args: None
+ *
+ * Return: None
+ *
+ * Within @vm, creates a virtual translation for the page starting
+ * at @vaddr to the page starting at @paddr.
+ */
void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
- uint32_t pgd_memslot);
+ uint32_t memslot);
+
vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm, vm_paddr_t paddr_min,
uint32_t memslot);
vm_paddr_t vm_phy_pages_alloc(struct kvm_vm *vm, size_t num,
vm_paddr_t paddr_min, uint32_t memslot);
-struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_size,
+/*
+ * Create a VM with reasonable defaults
+ *
+ * Input Args:
+ * vcpuid - The id of the single VCPU to add to the VM.
+ * extra_mem_pages - The number of extra pages to add (this will
+ * decide how much extra space we will need to
+ * setup the page tables using memslot 0)
+ * guest_code - The vCPU's entry point
+ *
+ * Output Args: None
+ *
+ * Return:
+ * Pointer to opaque structure that describes the created VM.
+ */
+struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages,
void *guest_code);
+
+/*
+ * Adds a vCPU with reasonable defaults (e.g. a stack)
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * vcpuid - The id of the VCPU to add to the VM.
+ * guest_code - The vCPU's entry point
+ */
void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code);
bool vm_is_unrestricted_guest(struct kvm_vm *vm);
@@ -163,6 +258,22 @@ bool vm_is_unrestricted_guest(struct kvm_vm *vm);
unsigned int vm_get_page_size(struct kvm_vm *vm);
unsigned int vm_get_page_shift(struct kvm_vm *vm);
unsigned int vm_get_max_gfn(struct kvm_vm *vm);
+int vm_get_fd(struct kvm_vm *vm);
+
+unsigned int vm_calc_num_guest_pages(enum vm_guest_mode mode, size_t size);
+unsigned int vm_num_host_pages(enum vm_guest_mode mode, unsigned int num_guest_pages);
+unsigned int vm_num_guest_pages(enum vm_guest_mode mode, unsigned int num_host_pages);
+static inline unsigned int
+vm_adjust_num_guest_pages(enum vm_guest_mode mode, unsigned int num_guest_pages)
+{
+ unsigned int n;
+ n = vm_num_guest_pages(mode, vm_num_host_pages(mode, num_guest_pages));
+#ifdef __s390x__
+ /* s390 requires 1M aligned guest sizes */
+ n = (n + 255) & ~255;
+#endif
+ return n;
+}
struct kvm_userspace_memory_region *
kvm_userspace_memory_region_find(struct kvm_vm *vm, uint64_t start,
@@ -203,13 +314,30 @@ void ucall_uninit(struct kvm_vm *vm);
void ucall(uint64_t cmd, int nargs, ...);
uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc);
+#define GUEST_SYNC_ARGS(stage, arg1, arg2, arg3, arg4) \
+ ucall(UCALL_SYNC, 6, "hello", stage, arg1, arg2, arg3, arg4)
#define GUEST_SYNC(stage) ucall(UCALL_SYNC, 2, "hello", stage)
#define GUEST_DONE() ucall(UCALL_DONE, 0)
-#define GUEST_ASSERT(_condition) do { \
- if (!(_condition)) \
- ucall(UCALL_ABORT, 2, \
- "Failed guest assert: " \
- #_condition, __LINE__); \
+#define __GUEST_ASSERT(_condition, _nargs, _args...) do { \
+ if (!(_condition)) \
+ ucall(UCALL_ABORT, 2 + _nargs, \
+ "Failed guest assert: " \
+ #_condition, __LINE__, _args); \
} while (0)
+#define GUEST_ASSERT(_condition) \
+ __GUEST_ASSERT((_condition), 0, 0)
+
+#define GUEST_ASSERT_1(_condition, arg1) \
+ __GUEST_ASSERT((_condition), 1, (arg1))
+
+#define GUEST_ASSERT_2(_condition, arg1, arg2) \
+ __GUEST_ASSERT((_condition), 2, (arg1), (arg2))
+
+#define GUEST_ASSERT_3(_condition, arg1, arg2, arg3) \
+ __GUEST_ASSERT((_condition), 3, (arg1), (arg2), (arg3))
+
+#define GUEST_ASSERT_4(_condition, arg1, arg2, arg3, arg4) \
+ __GUEST_ASSERT((_condition), 4, (arg1), (arg2), (arg3), (arg4))
+
#endif /* SELFTEST_KVM_UTIL_H */
diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h
index a41db6fb7e24..5eb01bf51b86 100644
--- a/tools/testing/selftests/kvm/include/test_util.h
+++ b/tools/testing/selftests/kvm/include/test_util.h
@@ -19,12 +19,28 @@
#include <fcntl.h>
#include "kselftest.h"
+static inline int _no_printf(const char *format, ...) { return 0; }
+
+#ifdef DEBUG
+#define pr_debug(...) printf(__VA_ARGS__)
+#else
+#define pr_debug(...) _no_printf(__VA_ARGS__)
+#endif
+#ifndef QUIET
+#define pr_info(...) printf(__VA_ARGS__)
+#else
+#define pr_info(...) _no_printf(__VA_ARGS__)
+#endif
+
+void print_skip(const char *fmt, ...) __attribute__((format(printf, 1, 2)));
+
ssize_t test_write(int fd, const void *buf, size_t count);
ssize_t test_read(int fd, void *buf, size_t count);
int test_seq_read(const char *path, char **bufp, size_t *sizep);
void test_assert(bool exp, const char *exp_str,
- const char *file, unsigned int line, const char *fmt, ...);
+ const char *file, unsigned int line, const char *fmt, ...)
+ __attribute__((format(printf, 5, 6)));
#define TEST_ASSERT(e, fmt, ...) \
test_assert((e), #e, __FILE__, __LINE__, fmt, ##__VA_ARGS__)
@@ -39,4 +55,14 @@ void test_assert(bool exp, const char *exp_str,
#a, #b, #a, (unsigned long) __a, #b, (unsigned long) __b); \
} while (0)
+#define TEST_FAIL(fmt, ...) \
+ TEST_ASSERT(false, fmt, ##__VA_ARGS__)
+
+size_t parse_size(const char *size);
+
+int64_t timespec_to_ns(struct timespec ts);
+struct timespec timespec_add_ns(struct timespec ts, int64_t ns);
+struct timespec timespec_add(struct timespec ts1, struct timespec ts2);
+struct timespec timespec_sub(struct timespec ts1, struct timespec ts2);
+
#endif /* SELFTEST_KVM_TEST_UTIL_H */
diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h
index 7428513a4c68..82b7fe16a824 100644
--- a/tools/testing/selftests/kvm/include/x86_64/processor.h
+++ b/tools/testing/selftests/kvm/include/x86_64/processor.h
@@ -79,13 +79,16 @@ static inline uint64_t get_desc64_base(const struct desc64 *desc)
static inline uint64_t rdtsc(void)
{
uint32_t eax, edx;
-
+ uint64_t tsc_val;
/*
* The lfence is to wait (on Intel CPUs) until all previous
- * instructions have been executed.
+ * instructions have been executed. If software requires RDTSC to be
+ * executed prior to execution of any subsequent instruction, it can
+ * execute LFENCE immediately after RDTSC
*/
- __asm__ __volatile__("lfence; rdtsc" : "=a"(eax), "=d"(edx));
- return ((uint64_t)edx) << 32 | eax;
+ __asm__ __volatile__("lfence; rdtsc; lfence" : "=a"(eax), "=d"(edx));
+ tsc_val = ((uint64_t)edx) << 32 | eax;
+ return tsc_val;
}
static inline uint64_t rdtscp(uint32_t *aux)
diff --git a/tools/testing/selftests/kvm/include/x86_64/svm_util.h b/tools/testing/selftests/kvm/include/x86_64/svm_util.h
index cd037917fece..674151d24fcf 100644
--- a/tools/testing/selftests/kvm/include/x86_64/svm_util.h
+++ b/tools/testing/selftests/kvm/include/x86_64/svm_util.h
@@ -35,4 +35,14 @@ void generic_svm_setup(struct svm_test_data *svm, void *guest_rip, void *guest_r
void run_guest(struct vmcb *vmcb, uint64_t vmcb_gpa);
void nested_svm_check_supported(void);
+static inline bool cpu_has_svm(void)
+{
+ u32 eax = 0x80000001, ecx;
+
+ asm("cpuid" :
+ "=a" (eax), "=c" (ecx) : "0" (eax) : "ebx", "edx");
+
+ return ecx & CPUID_SVM;
+}
+
#endif /* SELFTEST_KVM_SVM_UTILS_H */
diff --git a/tools/testing/selftests/kvm/include/x86_64/vmx.h b/tools/testing/selftests/kvm/include/x86_64/vmx.h
index 3d27069b9ed9..ccff3e6e2704 100644
--- a/tools/testing/selftests/kvm/include/x86_64/vmx.h
+++ b/tools/testing/selftests/kvm/include/x86_64/vmx.h
@@ -575,6 +575,33 @@ struct vmx_pages {
void *eptp;
};
+union vmx_basic {
+ u64 val;
+ struct {
+ u32 revision;
+ u32 size:13,
+ reserved1:3,
+ width:1,
+ dual:1,
+ type:4,
+ insouts:1,
+ ctrl:1,
+ vm_entry_exception_ctrl:1,
+ reserved2:7;
+ };
+};
+
+union vmx_ctrl_msr {
+ u64 val;
+ struct {
+ u32 set, clr;
+ };
+};
+
+union vmx_basic basic;
+union vmx_ctrl_msr ctrl_pin_rev;
+union vmx_ctrl_msr ctrl_exit_rev;
+
struct vmx_pages *vcpu_alloc_vmx(struct kvm_vm *vm, vm_vaddr_t *p_vmx_gva);
bool prepare_for_vmx_operation(struct vmx_pages *vmx);
void prepare_vmcs(struct vmx_pages *vmx, void *guest_rip, void *guest_rsp);
diff --git a/tools/testing/selftests/kvm/kvm_create_max_vcpus.c b/tools/testing/selftests/kvm/kvm_create_max_vcpus.c
index 6f38c3dc0d56..0299cd81b8ba 100644
--- a/tools/testing/selftests/kvm/kvm_create_max_vcpus.c
+++ b/tools/testing/selftests/kvm/kvm_create_max_vcpus.c
@@ -24,8 +24,8 @@ void test_vcpu_creation(int first_vcpu_id, int num_vcpus)
struct kvm_vm *vm;
int i;
- printf("Testing creating %d vCPUs, with IDs %d...%d.\n",
- num_vcpus, first_vcpu_id, first_vcpu_id + num_vcpus - 1);
+ pr_info("Testing creating %d vCPUs, with IDs %d...%d.\n",
+ num_vcpus, first_vcpu_id, first_vcpu_id + num_vcpus - 1);
vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR);
@@ -41,8 +41,8 @@ int main(int argc, char *argv[])
int kvm_max_vcpu_id = kvm_check_cap(KVM_CAP_MAX_VCPU_ID);
int kvm_max_vcpus = kvm_check_cap(KVM_CAP_MAX_VCPUS);
- printf("KVM_CAP_MAX_VCPU_ID: %d\n", kvm_max_vcpu_id);
- printf("KVM_CAP_MAX_VCPUS: %d\n", kvm_max_vcpus);
+ pr_info("KVM_CAP_MAX_VCPU_ID: %d\n", kvm_max_vcpu_id);
+ pr_info("KVM_CAP_MAX_VCPUS: %d\n", kvm_max_vcpus);
/*
* Upstream KVM prior to 4.8 does not support KVM_CAP_MAX_VCPU_ID.
diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c
index 86036a59a668..2afa6618b396 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/processor.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c
@@ -130,7 +130,7 @@ void _virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pte_index(vm, vaddr) * 8;
break;
default:
- TEST_ASSERT(false, "Page table levels must be 2, 3, or 4");
+ TEST_FAIL("Page table levels must be 2, 3, or 4");
}
*ptep = paddr | 3;
@@ -173,20 +173,19 @@ vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva)
goto unmapped_gva;
break;
default:
- TEST_ASSERT(false, "Page table levels must be 2, 3, or 4");
+ TEST_FAIL("Page table levels must be 2, 3, or 4");
}
return pte_addr(vm, *ptep) + (gva & (vm->page_size - 1));
unmapped_gva:
- TEST_ASSERT(false, "No mapping for vm virtual address, "
- "gva: 0x%lx", gva);
+ TEST_FAIL("No mapping for vm virtual address, gva: 0x%lx", gva);
exit(1);
}
static void pte_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent, uint64_t page, int level)
{
-#ifdef DEBUG_VM
+#ifdef DEBUG
static const char * const type[] = { "", "pud", "pmd", "pte" };
uint64_t pte, *ptep;
@@ -197,7 +196,7 @@ static void pte_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent, uint64_t p
ptep = addr_gpa2hva(vm, pte);
if (!*ptep)
continue;
- printf("%*s%s: %lx: %lx at %p\n", indent, "", type[level], pte, *ptep, ptep);
+ fprintf(stream, "%*s%s: %lx: %lx at %p\n", indent, "", type[level], pte, *ptep, ptep);
pte_dump(stream, vm, indent + 1, pte_addr(vm, *ptep), level + 1);
}
#endif
@@ -215,7 +214,7 @@ void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
ptep = addr_gpa2hva(vm, pgd);
if (!*ptep)
continue;
- printf("%*spgd: %lx: %lx at %p\n", indent, "", pgd, *ptep, ptep);
+ fprintf(stream, "%*spgd: %lx: %lx at %p\n", indent, "", pgd, *ptep, ptep);
pte_dump(stream, vm, indent + 1, pte_addr(vm, *ptep), level);
}
}
@@ -262,11 +261,11 @@ void aarch64_vcpu_setup(struct kvm_vm *vm, int vcpuid, struct kvm_vcpu_init *ini
switch (vm->mode) {
case VM_MODE_P52V48_4K:
- TEST_ASSERT(false, "AArch64 does not support 4K sized pages "
- "with 52-bit physical address ranges");
+ TEST_FAIL("AArch64 does not support 4K sized pages "
+ "with 52-bit physical address ranges");
case VM_MODE_PXXV48_4K:
- TEST_ASSERT(false, "AArch64 does not support 4K sized pages "
- "with ANY-bit physical address ranges");
+ TEST_FAIL("AArch64 does not support 4K sized pages "
+ "with ANY-bit physical address ranges");
case VM_MODE_P52V48_64K:
tcr_el1 |= 1ul << 14; /* TG0 = 64KB */
tcr_el1 |= 6ul << 32; /* IPS = 52 bits */
@@ -288,7 +287,7 @@ void aarch64_vcpu_setup(struct kvm_vm *vm, int vcpuid, struct kvm_vcpu_init *ini
tcr_el1 |= 2ul << 32; /* IPS = 40 bits */
break;
default:
- TEST_ASSERT(false, "Unknown guest mode, mode: 0x%x", vm->mode);
+ TEST_FAIL("Unknown guest mode, mode: 0x%x", vm->mode);
}
sctlr_el1 |= (1 << 0) | (1 << 2) | (1 << 12) /* M | C | I */;
@@ -333,3 +332,21 @@ void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code)
{
aarch64_vcpu_add_default(vm, vcpuid, NULL, guest_code);
}
+
+void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...)
+{
+ va_list ap;
+ int i;
+
+ TEST_ASSERT(num >= 1 && num <= 8, "Unsupported number of args,\n"
+ " num: %u\n", num);
+
+ va_start(ap, num);
+
+ for (i = 0; i < num; i++) {
+ set_reg(vm, vcpuid, ARM64_CORE_REG(regs.regs[i]),
+ va_arg(ap, uint64_t));
+ }
+
+ va_end(ap);
+}
diff --git a/tools/testing/selftests/kvm/lib/aarch64/ucall.c b/tools/testing/selftests/kvm/lib/aarch64/ucall.c
index 6cd91970fbad..c8e0ec20d3bf 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/ucall.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/ucall.c
@@ -62,7 +62,7 @@ void ucall_init(struct kvm_vm *vm, void *arg)
if (ucall_mmio_init(vm, start + offset))
return;
}
- TEST_ASSERT(false, "Can't find a ucall mmio address");
+ TEST_FAIL("Can't find a ucall mmio address");
}
void ucall_uninit(struct kvm_vm *vm)
diff --git a/tools/testing/selftests/kvm/lib/assert.c b/tools/testing/selftests/kvm/lib/assert.c
index d1cf9f6e0e6b..5ebbd0d6b472 100644
--- a/tools/testing/selftests/kvm/lib/assert.c
+++ b/tools/testing/selftests/kvm/lib/assert.c
@@ -82,8 +82,10 @@ test_assert(bool exp, const char *exp_str,
}
va_end(ap);
- if (errno == EACCES)
- ksft_exit_skip("Access denied - Exiting.\n");
+ if (errno == EACCES) {
+ print_skip("Access denied - Exiting");
+ exit(KSFT_SKIP);
+ }
exit(254);
}
diff --git a/tools/testing/selftests/kvm/lib/io.c b/tools/testing/selftests/kvm/lib/io.c
index eaf351cc7e7f..fedb2a741f0b 100644
--- a/tools/testing/selftests/kvm/lib/io.c
+++ b/tools/testing/selftests/kvm/lib/io.c
@@ -61,9 +61,9 @@ ssize_t test_write(int fd, const void *buf, size_t count)
continue;
case 0:
- TEST_ASSERT(false, "Unexpected EOF,\n"
- " rc: %zi num_written: %zi num_left: %zu",
- rc, num_written, num_left);
+ TEST_FAIL("Unexpected EOF,\n"
+ " rc: %zi num_written: %zi num_left: %zu",
+ rc, num_written, num_left);
break;
default:
@@ -138,9 +138,9 @@ ssize_t test_read(int fd, void *buf, size_t count)
break;
case 0:
- TEST_ASSERT(false, "Unexpected EOF,\n"
- " rc: %zi num_read: %zi num_left: %zu",
- rc, num_read, num_left);
+ TEST_FAIL("Unexpected EOF,\n"
+ " rc: %zi num_read: %zi num_left: %zu",
+ rc, num_read, num_left);
break;
default:
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index a6dd0401eb50..c9cede5c7d0d 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -92,7 +92,7 @@ static void vm_open(struct kvm_vm *vm, int perm)
exit(KSFT_SKIP);
if (!kvm_check_cap(KVM_CAP_IMMEDIATE_EXIT)) {
- fprintf(stderr, "immediate_exit not available, skipping test\n");
+ print_skip("immediate_exit not available");
exit(KSFT_SKIP);
}
@@ -113,6 +113,25 @@ const char * const vm_guest_mode_string[] = {
_Static_assert(sizeof(vm_guest_mode_string)/sizeof(char *) == NUM_VM_MODES,
"Missing new mode strings?");
+struct vm_guest_mode_params {
+ unsigned int pa_bits;
+ unsigned int va_bits;
+ unsigned int page_size;
+ unsigned int page_shift;
+};
+
+static const struct vm_guest_mode_params vm_guest_mode_params[] = {
+ { 52, 48, 0x1000, 12 },
+ { 52, 48, 0x10000, 16 },
+ { 48, 48, 0x1000, 12 },
+ { 48, 48, 0x10000, 16 },
+ { 40, 48, 0x1000, 12 },
+ { 40, 48, 0x10000, 16 },
+ { 0, 0, 0x1000, 12 },
+};
+_Static_assert(sizeof(vm_guest_mode_params)/sizeof(struct vm_guest_mode_params) == NUM_VM_MODES,
+ "Missing new mode params?");
+
/*
* VM Create
*
@@ -136,75 +155,57 @@ struct kvm_vm *_vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
{
struct kvm_vm *vm;
- DEBUG("Testing guest mode: %s\n", vm_guest_mode_string(mode));
+ pr_debug("%s: mode='%s' pages='%ld' perm='%d'\n", __func__,
+ vm_guest_mode_string(mode), phy_pages, perm);
vm = calloc(1, sizeof(*vm));
TEST_ASSERT(vm != NULL, "Insufficient Memory");
+ INIT_LIST_HEAD(&vm->vcpus);
+ INIT_LIST_HEAD(&vm->userspace_mem_regions);
+
vm->mode = mode;
vm->type = 0;
+ vm->pa_bits = vm_guest_mode_params[mode].pa_bits;
+ vm->va_bits = vm_guest_mode_params[mode].va_bits;
+ vm->page_size = vm_guest_mode_params[mode].page_size;
+ vm->page_shift = vm_guest_mode_params[mode].page_shift;
+
/* Setup mode specific traits. */
switch (vm->mode) {
case VM_MODE_P52V48_4K:
vm->pgtable_levels = 4;
- vm->pa_bits = 52;
- vm->va_bits = 48;
- vm->page_size = 0x1000;
- vm->page_shift = 12;
break;
case VM_MODE_P52V48_64K:
vm->pgtable_levels = 3;
- vm->pa_bits = 52;
- vm->va_bits = 48;
- vm->page_size = 0x10000;
- vm->page_shift = 16;
break;
case VM_MODE_P48V48_4K:
vm->pgtable_levels = 4;
- vm->pa_bits = 48;
- vm->va_bits = 48;
- vm->page_size = 0x1000;
- vm->page_shift = 12;
break;
case VM_MODE_P48V48_64K:
vm->pgtable_levels = 3;
- vm->pa_bits = 48;
- vm->va_bits = 48;
- vm->page_size = 0x10000;
- vm->page_shift = 16;
break;
case VM_MODE_P40V48_4K:
vm->pgtable_levels = 4;
- vm->pa_bits = 40;
- vm->va_bits = 48;
- vm->page_size = 0x1000;
- vm->page_shift = 12;
break;
case VM_MODE_P40V48_64K:
vm->pgtable_levels = 3;
- vm->pa_bits = 40;
- vm->va_bits = 48;
- vm->page_size = 0x10000;
- vm->page_shift = 16;
break;
case VM_MODE_PXXV48_4K:
#ifdef __x86_64__
kvm_get_cpu_address_width(&vm->pa_bits, &vm->va_bits);
TEST_ASSERT(vm->va_bits == 48, "Linear address width "
"(%d bits) not supported", vm->va_bits);
+ pr_debug("Guest physical address width detected: %d\n",
+ vm->pa_bits);
vm->pgtable_levels = 4;
- vm->page_size = 0x1000;
- vm->page_shift = 12;
- DEBUG("Guest physical address width detected: %d\n",
- vm->pa_bits);
#else
- TEST_ASSERT(false, "VM_MODE_PXXV48_4K not supported on "
- "non-x86 platforms");
+ TEST_FAIL("VM_MODE_PXXV48_4K not supported on non-x86 platforms");
#endif
break;
default:
- TEST_ASSERT(false, "Unknown guest mode, mode: 0x%x", mode);
+ TEST_FAIL("Unknown guest mode, mode: 0x%x", mode);
}
#ifdef __aarch64__
@@ -260,13 +261,12 @@ void kvm_vm_restart(struct kvm_vm *vmp, int perm)
if (vmp->has_irqchip)
vm_create_irqchip(vmp);
- for (region = vmp->userspace_mem_region_head; region;
- region = region->next) {
+ list_for_each_entry(region, &vmp->userspace_mem_regions, list) {
int ret = ioctl(vmp->fd, KVM_SET_USER_MEMORY_REGION, &region->region);
TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION IOCTL failed,\n"
" rc: %i errno: %i\n"
" slot: %u flags: 0x%x\n"
- " guest_phys_addr: 0x%lx size: 0x%lx",
+ " guest_phys_addr: 0x%llx size: 0x%llx",
ret, errno, region->region.slot,
region->region.flags,
region->region.guest_phys_addr,
@@ -281,7 +281,7 @@ void kvm_vm_get_dirty_log(struct kvm_vm *vm, int slot, void *log)
ret = ioctl(vm->fd, KVM_GET_DIRTY_LOG, &args);
TEST_ASSERT(ret == 0, "%s: KVM_GET_DIRTY_LOG failed: %s",
- strerror(-ret));
+ __func__, strerror(-ret));
}
void kvm_vm_clear_dirty_log(struct kvm_vm *vm, int slot, void *log,
@@ -294,7 +294,7 @@ void kvm_vm_clear_dirty_log(struct kvm_vm *vm, int slot, void *log,
ret = ioctl(vm->fd, KVM_CLEAR_DIRTY_LOG, &args);
TEST_ASSERT(ret == 0, "%s: KVM_CLEAR_DIRTY_LOG failed: %s",
- strerror(-ret));
+ __func__, strerror(-ret));
}
/*
@@ -321,8 +321,7 @@ userspace_mem_region_find(struct kvm_vm *vm, uint64_t start, uint64_t end)
{
struct userspace_mem_region *region;
- for (region = vm->userspace_mem_region_head; region;
- region = region->next) {
+ list_for_each_entry(region, &vm->userspace_mem_regions, list) {
uint64_t existing_start = region->region.guest_phys_addr;
uint64_t existing_end = region->region.guest_phys_addr
+ region->region.memory_size - 1;
@@ -380,11 +379,11 @@ kvm_userspace_memory_region_find(struct kvm_vm *vm, uint64_t start,
*/
struct vcpu *vcpu_find(struct kvm_vm *vm, uint32_t vcpuid)
{
- struct vcpu *vcpup;
+ struct vcpu *vcpu;
- for (vcpup = vm->vcpu_head; vcpup; vcpup = vcpup->next) {
- if (vcpup->id == vcpuid)
- return vcpup;
+ list_for_each_entry(vcpu, &vm->vcpus, list) {
+ if (vcpu->id == vcpuid)
+ return vcpu;
}
return NULL;
@@ -394,18 +393,16 @@ struct vcpu *vcpu_find(struct kvm_vm *vm, uint32_t vcpuid)
* VM VCPU Remove
*
* Input Args:
- * vm - Virtual Machine
- * vcpuid - VCPU ID
+ * vcpu - VCPU to remove
*
* Output Args: None
*
* Return: None, TEST_ASSERT failures for all error conditions
*
- * Within the VM specified by vm, removes the VCPU given by vcpuid.
+ * Removes a vCPU from a VM and frees its resources.
*/
-static void vm_vcpu_rm(struct kvm_vm *vm, uint32_t vcpuid)
+static void vm_vcpu_rm(struct vcpu *vcpu)
{
- struct vcpu *vcpu = vcpu_find(vm, vcpuid);
int ret;
ret = munmap(vcpu->state, sizeof(*vcpu->state));
@@ -415,21 +412,17 @@ static void vm_vcpu_rm(struct kvm_vm *vm, uint32_t vcpuid)
TEST_ASSERT(ret == 0, "Close of VCPU fd failed, rc: %i "
"errno: %i", ret, errno);
- if (vcpu->next)
- vcpu->next->prev = vcpu->prev;
- if (vcpu->prev)
- vcpu->prev->next = vcpu->next;
- else
- vm->vcpu_head = vcpu->next;
+ list_del(&vcpu->list);
free(vcpu);
}
void kvm_vm_release(struct kvm_vm *vmp)
{
+ struct vcpu *vcpu, *tmp;
int ret;
- while (vmp->vcpu_head)
- vm_vcpu_rm(vmp, vmp->vcpu_head->id);
+ list_for_each_entry_safe(vcpu, tmp, &vmp->vcpus, list)
+ vm_vcpu_rm(vcpu);
ret = close(vmp->fd);
TEST_ASSERT(ret == 0, "Close of vm fd failed,\n"
@@ -440,35 +433,38 @@ void kvm_vm_release(struct kvm_vm *vmp)
" vmp->kvm_fd: %i rc: %i errno: %i", vmp->kvm_fd, ret, errno);
}
+static void __vm_mem_region_delete(struct kvm_vm *vm,
+ struct userspace_mem_region *region)
+{
+ int ret;
+
+ list_del(&region->list);
+
+ region->region.memory_size = 0;
+ ret = ioctl(vm->fd, KVM_SET_USER_MEMORY_REGION, &region->region);
+ TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION IOCTL failed, "
+ "rc: %i errno: %i", ret, errno);
+
+ sparsebit_free(&region->unused_phy_pages);
+ ret = munmap(region->mmap_start, region->mmap_size);
+ TEST_ASSERT(ret == 0, "munmap failed, rc: %i errno: %i", ret, errno);
+
+ free(region);
+}
+
/*
* Destroys and frees the VM pointed to by vmp.
*/
void kvm_vm_free(struct kvm_vm *vmp)
{
- int ret;
+ struct userspace_mem_region *region, *tmp;
if (vmp == NULL)
return;
/* Free userspace_mem_regions. */
- while (vmp->userspace_mem_region_head) {
- struct userspace_mem_region *region
- = vmp->userspace_mem_region_head;
-
- region->region.memory_size = 0;
- ret = ioctl(vmp->fd, KVM_SET_USER_MEMORY_REGION,
- &region->region);
- TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION IOCTL failed, "
- "rc: %i errno: %i", ret, errno);
-
- vmp->userspace_mem_region_head = region->next;
- sparsebit_free(&region->unused_phy_pages);
- ret = munmap(region->mmap_start, region->mmap_size);
- TEST_ASSERT(ret == 0, "munmap failed, rc: %i errno: %i",
- ret, errno);
-
- free(region);
- }
+ list_for_each_entry_safe(region, tmp, &vmp->userspace_mem_regions, list)
+ __vm_mem_region_delete(vmp, region);
/* Free sparsebit arrays. */
sparsebit_free(&vmp->vpages_valid);
@@ -582,6 +578,10 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
size_t huge_page_size = KVM_UTIL_PGS_PER_HUGEPG * vm->page_size;
size_t alignment;
+ TEST_ASSERT(vm_adjust_num_guest_pages(vm->mode, npages) == npages,
+ "Number of guest pages is not compatible with the host. "
+ "Try npages=%d", vm_adjust_num_guest_pages(vm->mode, npages));
+
TEST_ASSERT((guest_paddr % vm->page_size) == 0, "Guest physical "
"address not on a page boundary.\n"
" guest_paddr: 0x%lx vm->page_size: 0x%x",
@@ -600,7 +600,7 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
region = (struct userspace_mem_region *) userspace_mem_region_find(
vm, guest_paddr, (guest_paddr + npages * vm->page_size) - 1);
if (region != NULL)
- TEST_ASSERT(false, "overlapping userspace_mem_region already "
+ TEST_FAIL("overlapping userspace_mem_region already "
"exists\n"
" requested guest_paddr: 0x%lx npages: 0x%lx "
"page_size: 0x%x\n"
@@ -610,13 +610,11 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
(uint64_t) region->region.memory_size);
/* Confirm no region with the requested slot already exists. */
- for (region = vm->userspace_mem_region_head; region;
- region = region->next) {
- if (region->region.slot == slot)
- break;
- }
- if (region != NULL)
- TEST_ASSERT(false, "A mem region with the requested slot "
+ list_for_each_entry(region, &vm->userspace_mem_regions, list) {
+ if (region->region.slot != slot)
+ continue;
+
+ TEST_FAIL("A mem region with the requested slot "
"already exists.\n"
" requested slot: %u paddr: 0x%lx npages: 0x%lx\n"
" existing slot: %u paddr: 0x%lx size: 0x%lx",
@@ -624,6 +622,7 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
region->region.slot,
(uint64_t) region->region.guest_phys_addr,
(uint64_t) region->region.memory_size);
+ }
/* Allocate and initialize new mem region structure. */
region = calloc(1, sizeof(*region));
@@ -684,10 +683,7 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
guest_paddr, (uint64_t) region->region.memory_size);
/* Add to linked-list of memory regions. */
- if (vm->userspace_mem_region_head)
- vm->userspace_mem_region_head->prev = region;
- region->next = vm->userspace_mem_region_head;
- vm->userspace_mem_region_head = region;
+ list_add(&region->list, &vm->userspace_mem_regions);
}
/*
@@ -710,20 +706,17 @@ memslot2region(struct kvm_vm *vm, uint32_t memslot)
{
struct userspace_mem_region *region;
- for (region = vm->userspace_mem_region_head; region;
- region = region->next) {
+ list_for_each_entry(region, &vm->userspace_mem_regions, list) {
if (region->region.slot == memslot)
- break;
- }
- if (region == NULL) {
- fprintf(stderr, "No mem region with the requested slot found,\n"
- " requested slot: %u\n", memslot);
- fputs("---- vm dump ----\n", stderr);
- vm_dump(stderr, vm, 2);
- TEST_ASSERT(false, "Mem region not found");
+ return region;
}
- return region;
+ fprintf(stderr, "No mem region with the requested slot found,\n"
+ " requested slot: %u\n", memslot);
+ fputs("---- vm dump ----\n", stderr);
+ vm_dump(stderr, vm, 2);
+ TEST_FAIL("Mem region not found");
+ return NULL;
}
/*
@@ -757,6 +750,54 @@ void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags)
}
/*
+ * VM Memory Region Move
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * slot - Slot of the memory region to move
+ * new_gpa - Starting guest physical address
+ *
+ * Output Args: None
+ *
+ * Return: None
+ *
+ * Change the gpa of a memory region.
+ */
+void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa)
+{
+ struct userspace_mem_region *region;
+ int ret;
+
+ region = memslot2region(vm, slot);
+
+ region->region.guest_phys_addr = new_gpa;
+
+ ret = ioctl(vm->fd, KVM_SET_USER_MEMORY_REGION, &region->region);
+
+ TEST_ASSERT(!ret, "KVM_SET_USER_MEMORY_REGION failed\n"
+ "ret: %i errno: %i slot: %u new_gpa: 0x%lx",
+ ret, errno, slot, new_gpa);
+}
+
+/*
+ * VM Memory Region Delete
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * slot - Slot of the memory region to delete
+ *
+ * Output Args: None
+ *
+ * Return: None
+ *
+ * Delete a memory region.
+ */
+void vm_mem_region_delete(struct kvm_vm *vm, uint32_t slot)
+{
+ __vm_mem_region_delete(vm, memslot2region(vm, slot));
+}
+
+/*
* VCPU mmap Size
*
* Input Args: None
@@ -808,7 +849,7 @@ void vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpuid)
/* Confirm a vcpu with the specified id doesn't already exist. */
vcpu = vcpu_find(vm, vcpuid);
if (vcpu != NULL)
- TEST_ASSERT(false, "vcpu with the specified id "
+ TEST_FAIL("vcpu with the specified id "
"already exists,\n"
" requested vcpuid: %u\n"
" existing vcpuid: %u state: %p",
@@ -831,10 +872,7 @@ void vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpuid)
"vcpu id: %u errno: %i", vcpuid, errno);
/* Add to linked-list of VCPUs. */
- if (vm->vcpu_head)
- vm->vcpu_head->prev = vcpu;
- vcpu->next = vm->vcpu_head;
- vm->vcpu_head = vcpu;
+ list_add(&vcpu->list, &vm->vcpus);
}
/*
@@ -901,8 +939,7 @@ static vm_vaddr_t vm_vaddr_unused_gap(struct kvm_vm *vm, size_t sz,
} while (pgidx_start != 0);
no_va_found:
- TEST_ASSERT(false, "No vaddr of specified pages available, "
- "pages: 0x%lx", pages);
+ TEST_FAIL("No vaddr of specified pages available, pages: 0x%lx", pages);
/* NOT REACHED */
return -1;
@@ -982,21 +1019,21 @@ vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min,
* vm - Virtual Machine
* vaddr - Virtuall address to map
* paddr - VM Physical Address
- * size - The size of the range to map
+ * npages - The number of pages to map
* pgd_memslot - Memory region slot for new virtual translation tables
*
* Output Args: None
*
* Return: None
*
- * Within the VM given by vm, creates a virtual translation for the
- * page range starting at vaddr to the page range starting at paddr.
+ * Within the VM given by @vm, creates a virtual translation for
+ * @npages starting at @vaddr to the page range starting at @paddr.
*/
void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
- size_t size, uint32_t pgd_memslot)
+ unsigned int npages, uint32_t pgd_memslot)
{
size_t page_size = vm->page_size;
- size_t npages = size / page_size;
+ size_t size = npages * page_size;
TEST_ASSERT(vaddr + size > vaddr, "Vaddr overflow");
TEST_ASSERT(paddr + size > paddr, "Paddr overflow");
@@ -1028,8 +1065,8 @@ void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa)
{
struct userspace_mem_region *region;
- for (region = vm->userspace_mem_region_head; region;
- region = region->next) {
+
+ list_for_each_entry(region, &vm->userspace_mem_regions, list) {
if ((gpa >= region->region.guest_phys_addr)
&& (gpa <= (region->region.guest_phys_addr
+ region->region.memory_size - 1)))
@@ -1037,7 +1074,7 @@ void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa)
+ (gpa - region->region.guest_phys_addr));
}
- TEST_ASSERT(false, "No vm physical memory at 0x%lx", gpa);
+ TEST_FAIL("No vm physical memory at 0x%lx", gpa);
return NULL;
}
@@ -1061,8 +1098,8 @@ void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa)
vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva)
{
struct userspace_mem_region *region;
- for (region = vm->userspace_mem_region_head; region;
- region = region->next) {
+
+ list_for_each_entry(region, &vm->userspace_mem_regions, list) {
if ((hva >= region->host_mem)
&& (hva <= (region->host_mem
+ region->region.memory_size - 1)))
@@ -1071,8 +1108,7 @@ vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva)
+ (hva - (uintptr_t) region->host_mem));
}
- TEST_ASSERT(false, "No mapping to a guest physical address, "
- "hva: %p", hva);
+ TEST_FAIL("No mapping to a guest physical address, hva: %p", hva);
return -1;
}
@@ -1171,6 +1207,15 @@ void vcpu_run_complete_io(struct kvm_vm *vm, uint32_t vcpuid)
ret, errno);
}
+void vcpu_set_guest_debug(struct kvm_vm *vm, uint32_t vcpuid,
+ struct kvm_guest_debug *debug)
+{
+ struct vcpu *vcpu = vcpu_find(vm, vcpuid);
+ int ret = ioctl(vcpu->fd, KVM_SET_GUEST_DEBUG, debug);
+
+ TEST_ASSERT(ret == 0, "KVM_SET_GUEST_DEBUG failed: %d", ret);
+}
+
/*
* VM VCPU Set MP State
*
@@ -1490,8 +1535,7 @@ void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
fprintf(stream, "%*sfd: %i\n", indent, "", vm->fd);
fprintf(stream, "%*spage_size: 0x%x\n", indent, "", vm->page_size);
fprintf(stream, "%*sMem Regions:\n", indent, "");
- for (region = vm->userspace_mem_region_head; region;
- region = region->next) {
+ list_for_each_entry(region, &vm->userspace_mem_regions, list) {
fprintf(stream, "%*sguest_phys: 0x%lx size: 0x%lx "
"host_virt: %p\n", indent + 2, "",
(uint64_t) region->region.guest_phys_addr,
@@ -1510,7 +1554,7 @@ void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
virt_dump(stream, vm, indent + 4);
}
fprintf(stream, "%*sVCPUs:\n", indent, "");
- for (vcpu = vm->vcpu_head; vcpu; vcpu = vcpu->next)
+ list_for_each_entry(vcpu, &vm->vcpus, list)
vcpu_dump(stream, vm, vcpu->id, indent + 2);
}
@@ -1703,3 +1747,48 @@ unsigned int vm_get_max_gfn(struct kvm_vm *vm)
{
return vm->max_gfn;
}
+
+int vm_get_fd(struct kvm_vm *vm)
+{
+ return vm->fd;
+}
+
+static unsigned int vm_calc_num_pages(unsigned int num_pages,
+ unsigned int page_shift,
+ unsigned int new_page_shift,
+ bool ceil)
+{
+ unsigned int n = 1 << (new_page_shift - page_shift);
+
+ if (page_shift >= new_page_shift)
+ return num_pages * (1 << (page_shift - new_page_shift));
+
+ return num_pages / n + !!(ceil && num_pages % n);
+}
+
+static inline int getpageshift(void)
+{
+ return __builtin_ffs(getpagesize()) - 1;
+}
+
+unsigned int
+vm_num_host_pages(enum vm_guest_mode mode, unsigned int num_guest_pages)
+{
+ return vm_calc_num_pages(num_guest_pages,
+ vm_guest_mode_params[mode].page_shift,
+ getpageshift(), true);
+}
+
+unsigned int
+vm_num_guest_pages(enum vm_guest_mode mode, unsigned int num_host_pages)
+{
+ return vm_calc_num_pages(num_host_pages, getpageshift(),
+ vm_guest_mode_params[mode].page_shift, false);
+}
+
+unsigned int vm_calc_num_guest_pages(enum vm_guest_mode mode, size_t size)
+{
+ unsigned int n;
+ n = DIV_ROUND_UP(size, vm_guest_mode_params[mode].page_size);
+ return vm_adjust_num_guest_pages(mode, n);
+}
diff --git a/tools/testing/selftests/kvm/lib/kvm_util_internal.h b/tools/testing/selftests/kvm/lib/kvm_util_internal.h
index ac50c42750cf..2ef446520748 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util_internal.h
+++ b/tools/testing/selftests/kvm/lib/kvm_util_internal.h
@@ -12,19 +12,7 @@
#define KVM_DEV_PATH "/dev/kvm"
-#ifndef BITS_PER_BYTE
-#define BITS_PER_BYTE 8
-#endif
-
-#ifndef BITS_PER_LONG
-#define BITS_PER_LONG (BITS_PER_BYTE * sizeof(long))
-#endif
-
-#define DIV_ROUND_UP(n, d) (((n) + (d) - 1) / (d))
-#define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_LONG)
-
struct userspace_mem_region {
- struct userspace_mem_region *next, *prev;
struct kvm_userspace_memory_region region;
struct sparsebit *unused_phy_pages;
int fd;
@@ -32,10 +20,11 @@ struct userspace_mem_region {
void *host_mem;
void *mmap_start;
size_t mmap_size;
+ struct list_head list;
};
struct vcpu {
- struct vcpu *next, *prev;
+ struct list_head list;
uint32_t id;
int fd;
struct kvm_run *state;
@@ -52,8 +41,8 @@ struct kvm_vm {
unsigned int pa_bits;
unsigned int va_bits;
uint64_t max_gfn;
- struct vcpu *vcpu_head;
- struct userspace_mem_region *userspace_mem_region_head;
+ struct list_head vcpus;
+ struct list_head userspace_mem_regions;
struct sparsebit *vpages_valid;
struct sparsebit *vpages_mapped;
bool has_irqchip;
@@ -64,8 +53,56 @@ struct kvm_vm {
};
struct vcpu *vcpu_find(struct kvm_vm *vm, uint32_t vcpuid);
+
+/*
+ * Virtual Translation Tables Dump
+ *
+ * Input Args:
+ * stream - Output FILE stream
+ * vm - Virtual Machine
+ * indent - Left margin indent amount
+ *
+ * Output Args: None
+ *
+ * Return: None
+ *
+ * Dumps to the FILE stream given by @stream, the contents of all the
+ * virtual translation tables for the VM given by @vm.
+ */
void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent);
+
+/*
+ * Register Dump
+ *
+ * Input Args:
+ * stream - Output FILE stream
+ * regs - Registers
+ * indent - Left margin indent amount
+ *
+ * Output Args: None
+ *
+ * Return: None
+ *
+ * Dumps the state of the registers given by @regs, to the FILE stream
+ * given by @stream.
+ */
void regs_dump(FILE *stream, struct kvm_regs *regs, uint8_t indent);
+
+/*
+ * System Register Dump
+ *
+ * Input Args:
+ * stream - Output FILE stream
+ * sregs - System registers
+ * indent - Left margin indent amount
+ *
+ * Output Args: None
+ *
+ * Return: None
+ *
+ * Dumps the state of the system registers given by @sregs, to the FILE stream
+ * given by @stream.
+ */
void sregs_dump(FILE *stream, struct kvm_sregs *sregs, uint8_t indent);
struct userspace_mem_region *
diff --git a/tools/testing/selftests/kvm/lib/s390x/processor.c b/tools/testing/selftests/kvm/lib/s390x/processor.c
index 32a02360b1eb..a88c5d665725 100644
--- a/tools/testing/selftests/kvm/lib/s390x/processor.c
+++ b/tools/testing/selftests/kvm/lib/s390x/processor.c
@@ -51,22 +51,6 @@ static uint64_t virt_alloc_region(struct kvm_vm *vm, int ri, uint32_t memslot)
| ((ri < 4 ? (PAGES_PER_REGION - 1) : 0) & REGION_ENTRY_LENGTH);
}
-/*
- * VM Virtual Page Map
- *
- * Input Args:
- * vm - Virtual Machine
- * gva - VM Virtual Address
- * gpa - VM Physical Address
- * memslot - Memory region slot for new virtual translation tables
- *
- * Output Args: None
- *
- * Return: None
- *
- * Within the VM given by vm, creates a virtual translation for the page
- * starting at vaddr to the page starting at paddr.
- */
void virt_pg_map(struct kvm_vm *vm, uint64_t gva, uint64_t gpa,
uint32_t memslot)
{
@@ -107,26 +91,6 @@ void virt_pg_map(struct kvm_vm *vm, uint64_t gva, uint64_t gpa,
entry[idx] = gpa;
}
-/*
- * Address Guest Virtual to Guest Physical
- *
- * Input Args:
- * vm - Virtual Machine
- * gpa - VM virtual address
- *
- * Output Args: None
- *
- * Return:
- * Equivalent VM physical address
- *
- * Translates the VM virtual address given by gva to a VM physical
- * address and then locates the memory region containing the VM
- * physical address, within the VM given by vm. When found, the host
- * virtual address providing the memory to the vm physical address is
- * returned.
- * A TEST_ASSERT failure occurs if no region containing translated
- * VM virtual address exists.
- */
vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva)
{
int ri, idx;
@@ -196,21 +160,6 @@ void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
virt_dump_region(stream, vm, indent, vm->pgd);
}
-/*
- * Create a VM with reasonable defaults
- *
- * Input Args:
- * vcpuid - The id of the single VCPU to add to the VM.
- * extra_mem_pages - The size of extra memories to add (this will
- * decide how much extra space we will need to
- * setup the page tables using mem slot 0)
- * guest_code - The vCPU's entry point
- *
- * Output Args: None
- *
- * Return:
- * Pointer to opaque structure that describes the created VM.
- */
struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages,
void *guest_code)
{
@@ -231,13 +180,6 @@ struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages,
return vm;
}
-/*
- * Adds a vCPU with reasonable defaults (i.e. a stack and initial PSW)
- *
- * Input Args:
- * vcpuid - The id of the VCPU to add to the VM.
- * guest_code - The vCPU's entry point
- */
void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code)
{
size_t stack_size = DEFAULT_STACK_PGS * getpagesize();
@@ -269,9 +211,32 @@ void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code)
run->psw_addr = (uintptr_t)guest_code;
}
+void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...)
+{
+ va_list ap;
+ struct kvm_regs regs;
+ int i;
+
+ TEST_ASSERT(num >= 1 && num <= 5, "Unsupported number of args,\n"
+ " num: %u\n",
+ num);
+
+ va_start(ap, num);
+ vcpu_regs_get(vm, vcpuid, &regs);
+
+ for (i = 0; i < num; i++)
+ regs.gprs[i + 2] = va_arg(ap, uint64_t);
+
+ vcpu_regs_set(vm, vcpuid, &regs);
+ va_end(ap);
+}
+
void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid, uint8_t indent)
{
- struct vcpu *vcpu = vm->vcpu_head;
+ struct vcpu *vcpu = vcpu_find(vm, vcpuid);
+
+ if (!vcpu)
+ return;
fprintf(stream, "%*spstate: psw: 0x%.16llx:0x%.16llx\n",
indent, "", vcpu->state->psw_mask, vcpu->state->psw_addr);
diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c
new file mode 100644
index 000000000000..689e97c27ee2
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/test_util.c
@@ -0,0 +1,93 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * tools/testing/selftests/kvm/lib/test_util.c
+ *
+ * Copyright (C) 2020, Google LLC.
+ */
+#include <stdlib.h>
+#include <ctype.h>
+#include <limits.h>
+#include <assert.h>
+#include "test_util.h"
+
+/*
+ * Parses "[0-9]+[kmgt]?".
+ */
+size_t parse_size(const char *size)
+{
+ size_t base;
+ char *scale;
+ int shift = 0;
+
+ TEST_ASSERT(size && isdigit(size[0]), "Need at least one digit in '%s'", size);
+
+ base = strtoull(size, &scale, 0);
+
+ TEST_ASSERT(base != ULLONG_MAX, "Overflow parsing size!");
+
+ switch (tolower(*scale)) {
+ case 't':
+ shift = 40;
+ break;
+ case 'g':
+ shift = 30;
+ break;
+ case 'm':
+ shift = 20;
+ break;
+ case 'k':
+ shift = 10;
+ break;
+ case 'b':
+ case '\0':
+ shift = 0;
+ break;
+ default:
+ TEST_ASSERT(false, "Unknown size letter %c", *scale);
+ }
+
+ TEST_ASSERT((base << shift) >> shift == base, "Overflow scaling size!");
+
+ return base << shift;
+}
+
+int64_t timespec_to_ns(struct timespec ts)
+{
+ return (int64_t)ts.tv_nsec + 1000000000LL * (int64_t)ts.tv_sec;
+}
+
+struct timespec timespec_add_ns(struct timespec ts, int64_t ns)
+{
+ struct timespec res;
+
+ res.tv_nsec = ts.tv_nsec + ns;
+ res.tv_sec = ts.tv_sec + res.tv_nsec / 1000000000LL;
+ res.tv_nsec %= 1000000000LL;
+
+ return res;
+}
+
+struct timespec timespec_add(struct timespec ts1, struct timespec ts2)
+{
+ int64_t ns1 = timespec_to_ns(ts1);
+ int64_t ns2 = timespec_to_ns(ts2);
+ return timespec_add_ns((struct timespec){0}, ns1 + ns2);
+}
+
+struct timespec timespec_sub(struct timespec ts1, struct timespec ts2)
+{
+ int64_t ns1 = timespec_to_ns(ts1);
+ int64_t ns2 = timespec_to_ns(ts2);
+ return timespec_add_ns((struct timespec){0}, ns1 - ns2);
+}
+
+void print_skip(const char *fmt, ...)
+{
+ va_list ap;
+
+ assert(fmt);
+ va_start(ap, fmt);
+ vprintf(fmt, ap);
+ va_end(ap);
+ puts(", skipping test");
+}
diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c
index 683d3bdb8f6a..f6eb34eaa0d2 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c
@@ -77,20 +77,6 @@ struct pageTableEntry {
uint64_t execute_disable:1;
};
-/* Register Dump
- *
- * Input Args:
- * indent - Left margin indent amount
- * regs - register
- *
- * Output Args:
- * stream - Output FILE stream
- *
- * Return: None
- *
- * Dumps the state of the registers given by regs, to the FILE stream
- * given by steam.
- */
void regs_dump(FILE *stream, struct kvm_regs *regs,
uint8_t indent)
{
@@ -115,19 +101,20 @@ void regs_dump(FILE *stream, struct kvm_regs *regs,
regs->rip, regs->rflags);
}
-/* Segment Dump
+/*
+ * Segment Dump
*
* Input Args:
- * indent - Left margin indent amount
+ * stream - Output FILE stream
* segment - KVM segment
+ * indent - Left margin indent amount
*
- * Output Args:
- * stream - Output FILE stream
+ * Output Args: None
*
* Return: None
*
- * Dumps the state of the KVM segment given by segment, to the FILE stream
- * given by steam.
+ * Dumps the state of the KVM segment given by @segment, to the FILE stream
+ * given by @stream.
*/
static void segment_dump(FILE *stream, struct kvm_segment *segment,
uint8_t indent)
@@ -146,19 +133,20 @@ static void segment_dump(FILE *stream, struct kvm_segment *segment,
segment->unusable, segment->padding);
}
-/* dtable Dump
+/*
+ * dtable Dump
*
* Input Args:
- * indent - Left margin indent amount
+ * stream - Output FILE stream
* dtable - KVM dtable
+ * indent - Left margin indent amount
*
- * Output Args:
- * stream - Output FILE stream
+ * Output Args: None
*
* Return: None
*
- * Dumps the state of the KVM dtable given by dtable, to the FILE stream
- * given by steam.
+ * Dumps the state of the KVM dtable given by @dtable, to the FILE stream
+ * given by @stream.
*/
static void dtable_dump(FILE *stream, struct kvm_dtable *dtable,
uint8_t indent)
@@ -169,20 +157,6 @@ static void dtable_dump(FILE *stream, struct kvm_dtable *dtable,
dtable->padding[0], dtable->padding[1], dtable->padding[2]);
}
-/* System Register Dump
- *
- * Input Args:
- * indent - Left margin indent amount
- * sregs - System registers
- *
- * Output Args:
- * stream - Output FILE stream
- *
- * Return: None
- *
- * Dumps the state of the system registers given by sregs, to the FILE stream
- * given by steam.
- */
void sregs_dump(FILE *stream, struct kvm_sregs *sregs,
uint8_t indent)
{
@@ -240,21 +214,6 @@ void virt_pgd_alloc(struct kvm_vm *vm, uint32_t pgd_memslot)
}
}
-/* VM Virtual Page Map
- *
- * Input Args:
- * vm - Virtual Machine
- * vaddr - VM Virtual Address
- * paddr - VM Physical Address
- * pgd_memslot - Memory region slot for new virtual translation tables
- *
- * Output Args: None
- *
- * Return: None
- *
- * Within the VM given by vm, creates a virtual translation for the page
- * starting at vaddr to the page starting at paddr.
- */
void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
uint32_t pgd_memslot)
{
@@ -326,20 +285,6 @@ void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
pte[index[0]].present = 1;
}
-/* Virtual Translation Tables Dump
- *
- * Input Args:
- * vm - Virtual Machine
- * indent - Left margin indent amount
- *
- * Output Args:
- * stream - Output FILE stream
- *
- * Return: None
- *
- * Dumps to the FILE stream given by stream, the contents of all the
- * virtual translation tables for the VM given by vm.
- */
void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
{
struct pageMapL4Entry *pml4e, *pml4e_start;
@@ -421,7 +366,8 @@ void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
}
}
-/* Set Unusable Segment
+/*
+ * Set Unusable Segment
*
* Input Args: None
*
@@ -430,7 +376,7 @@ void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
*
* Return: None
*
- * Sets the segment register pointed to by segp to an unusable state.
+ * Sets the segment register pointed to by @segp to an unusable state.
*/
static void kvm_seg_set_unusable(struct kvm_segment *segp)
{
@@ -460,7 +406,8 @@ static void kvm_seg_fill_gdt_64bit(struct kvm_vm *vm, struct kvm_segment *segp)
}
-/* Set Long Mode Flat Kernel Code Segment
+/*
+ * Set Long Mode Flat Kernel Code Segment
*
* Input Args:
* vm - VM whose GDT is being filled, or NULL to only write segp
@@ -471,8 +418,8 @@ static void kvm_seg_fill_gdt_64bit(struct kvm_vm *vm, struct kvm_segment *segp)
*
* Return: None
*
- * Sets up the KVM segment pointed to by segp, to be a code segment
- * with the selector value given by selector.
+ * Sets up the KVM segment pointed to by @segp, to be a code segment
+ * with the selector value given by @selector.
*/
static void kvm_seg_set_kernel_code_64bit(struct kvm_vm *vm, uint16_t selector,
struct kvm_segment *segp)
@@ -491,7 +438,8 @@ static void kvm_seg_set_kernel_code_64bit(struct kvm_vm *vm, uint16_t selector,
kvm_seg_fill_gdt_64bit(vm, segp);
}
-/* Set Long Mode Flat Kernel Data Segment
+/*
+ * Set Long Mode Flat Kernel Data Segment
*
* Input Args:
* vm - VM whose GDT is being filled, or NULL to only write segp
@@ -502,8 +450,8 @@ static void kvm_seg_set_kernel_code_64bit(struct kvm_vm *vm, uint16_t selector,
*
* Return: None
*
- * Sets up the KVM segment pointed to by segp, to be a data segment
- * with the selector value given by selector.
+ * Sets up the KVM segment pointed to by @segp, to be a data segment
+ * with the selector value given by @selector.
*/
static void kvm_seg_set_kernel_data_64bit(struct kvm_vm *vm, uint16_t selector,
struct kvm_segment *segp)
@@ -521,24 +469,6 @@ static void kvm_seg_set_kernel_data_64bit(struct kvm_vm *vm, uint16_t selector,
kvm_seg_fill_gdt_64bit(vm, segp);
}
-/* Address Guest Virtual to Guest Physical
- *
- * Input Args:
- * vm - Virtual Machine
- * gpa - VM virtual address
- *
- * Output Args: None
- *
- * Return:
- * Equivalent VM physical address
- *
- * Translates the VM virtual address given by gva to a VM physical
- * address and then locates the memory region containing the VM
- * physical address, within the VM given by vm. When found, the host
- * virtual address providing the memory to the vm physical address is returned.
- * A TEST_ASSERT failure occurs if no region containing translated
- * VM virtual address exists.
- */
vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva)
{
uint16_t index[4];
@@ -576,8 +506,7 @@ vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva)
return (pte[index[0]].address * vm->page_size) + (gva & 0xfffu);
unmapped_gva:
- TEST_ASSERT(false, "No mapping for vm virtual address, "
- "gva: 0x%lx", gva);
+ TEST_FAIL("No mapping for vm virtual address, gva: 0x%lx", gva);
exit(EXIT_FAILURE);
}
@@ -634,18 +563,13 @@ static void vcpu_setup(struct kvm_vm *vm, int vcpuid, int pgd_memslot, int gdt_m
break;
default:
- TEST_ASSERT(false, "Unknown guest mode, mode: 0x%x", vm->mode);
+ TEST_FAIL("Unknown guest mode, mode: 0x%x", vm->mode);
}
sregs.cr3 = vm->pgd;
vcpu_sregs_set(vm, vcpuid, &sregs);
}
-/* Adds a vCPU with reasonable defaults (i.e., a stack)
- *
- * Input Args:
- * vcpuid - The id of the VCPU to add to the VM.
- * guest_code - The vCPU's entry point
- */
+
void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code)
{
struct kvm_mp_state mp_state;
@@ -670,7 +594,8 @@ void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code)
vcpu_set_mp_state(vm, vcpuid, &mp_state);
}
-/* Allocate an instance of struct kvm_cpuid2
+/*
+ * Allocate an instance of struct kvm_cpuid2
*
* Input Args: None
*
@@ -703,7 +628,8 @@ static struct kvm_cpuid2 *allocate_kvm_cpuid2(void)
return cpuid;
}
-/* KVM Supported CPUID Get
+/*
+ * KVM Supported CPUID Get
*
* Input Args: None
*
@@ -735,11 +661,12 @@ struct kvm_cpuid2 *kvm_get_supported_cpuid(void)
return cpuid;
}
-/* Locate a cpuid entry.
+/*
+ * Locate a cpuid entry.
*
* Input Args:
- * cpuid: The cpuid.
* function: The function of the cpuid entry to find.
+ * index: The index of the cpuid entry.
*
* Output Args: None
*
@@ -766,7 +693,8 @@ kvm_get_supported_cpuid_index(uint32_t function, uint32_t index)
return entry;
}
-/* VM VCPU CPUID Set
+/*
+ * VM VCPU CPUID Set
*
* Input Args:
* vm - Virtual Machine
@@ -793,20 +721,6 @@ void vcpu_set_cpuid(struct kvm_vm *vm,
}
-/* Create a VM with reasonable defaults
- *
- * Input Args:
- * vcpuid - The id of the single VCPU to add to the VM.
- * extra_mem_pages - The size of extra memories to add (this will
- * decide how much extra space we will need to
- * setup the page tables using mem slot 0)
- * guest_code - The vCPU's entry point
- *
- * Output Args: None
- *
- * Return:
- * Pointer to opaque structure that describes the created VM.
- */
struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages,
void *guest_code)
{
@@ -837,7 +751,8 @@ struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages,
return vm;
}
-/* VCPU Get MSR
+/*
+ * VCPU Get MSR
*
* Input Args:
* vm - Virtual Machine
@@ -869,7 +784,8 @@ uint64_t vcpu_get_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index)
return buffer.entry.data;
}
-/* _VCPU Set MSR
+/*
+ * _VCPU Set MSR
*
* Input Args:
* vm - Virtual Machine
@@ -902,7 +818,8 @@ int _vcpu_set_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index,
return r;
}
-/* VCPU Set MSR
+/*
+ * VCPU Set MSR
*
* Input Args:
* vm - Virtual Machine
@@ -926,22 +843,6 @@ void vcpu_set_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index,
" rc: %i errno: %i", r, errno);
}
-/* VM VCPU Args Set
- *
- * Input Args:
- * vm - Virtual Machine
- * vcpuid - VCPU ID
- * num - number of arguments
- * ... - arguments, each of type uint64_t
- *
- * Output Args: None
- *
- * Return: None
- *
- * Sets the first num function input arguments to the values
- * given as variable args. Each of the variable args is expected to
- * be of type uint64_t.
- */
void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...)
{
va_list ap;
@@ -976,22 +877,6 @@ void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...)
va_end(ap);
}
-/*
- * VM VCPU Dump
- *
- * Input Args:
- * vm - Virtual Machine
- * vcpuid - VCPU ID
- * indent - Left margin indent amount
- *
- * Output Args:
- * stream - Output FILE stream
- *
- * Return: None
- *
- * Dumps the current state of the VCPU specified by vcpuid, within the VM
- * given by vm, to the FILE stream given by stream.
- */
void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid, uint8_t indent)
{
struct kvm_regs regs;
diff --git a/tools/testing/selftests/kvm/lib/x86_64/svm.c b/tools/testing/selftests/kvm/lib/x86_64/svm.c
index 6e05a8fc3fe0..c42401068373 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/svm.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/svm.c
@@ -154,7 +154,7 @@ void nested_svm_check_supported(void)
kvm_get_supported_cpuid_entry(0x80000001);
if (!(entry->ecx & CPUID_SVM)) {
- fprintf(stderr, "nested SVM not enabled, skipping test\n");
+ print_skip("nested SVM not enabled");
exit(KSFT_SKIP);
}
}
diff --git a/tools/testing/selftests/kvm/lib/x86_64/vmx.c b/tools/testing/selftests/kvm/lib/x86_64/vmx.c
index 7aaa99ca4dbc..4ae104f6ce69 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/vmx.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/vmx.c
@@ -17,6 +17,9 @@
bool enable_evmcs;
+struct hv_enlightened_vmcs *current_evmcs;
+struct hv_vp_assist_page *current_vp_assist;
+
struct eptPageTableEntry {
uint64_t readable:1;
uint64_t writable:1;
@@ -191,7 +194,7 @@ bool load_vmcs(struct vmx_pages *vmx)
if (evmcs_vmptrld(vmx->enlightened_vmcs_gpa,
vmx->enlightened_vmcs))
return false;
- current_evmcs->revision_id = vmcs_revision();
+ current_evmcs->revision_id = EVMCS_VERSION;
}
return true;
@@ -381,7 +384,7 @@ void nested_vmx_check_supported(void)
struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1);
if (!(entry->ecx & CPUID_VMX)) {
- fprintf(stderr, "nested VMX not enabled, skipping test\n");
+ print_skip("nested VMX not enabled");
exit(KSFT_SKIP);
}
}
diff --git a/tools/testing/selftests/kvm/s390x/memop.c b/tools/testing/selftests/kvm/s390x/memop.c
index 9edaa9a134ce..9f49ead380ab 100644
--- a/tools/testing/selftests/kvm/s390x/memop.c
+++ b/tools/testing/selftests/kvm/s390x/memop.c
@@ -40,7 +40,7 @@ int main(int argc, char *argv[])
maxsize = kvm_check_cap(KVM_CAP_S390_MEM_OP);
if (!maxsize) {
- fprintf(stderr, "CAP_S390_MEM_OP not supported -> skip test\n");
+ print_skip("CAP_S390_MEM_OP not supported");
exit(KSFT_SKIP);
}
if (maxsize > sizeof(mem1))
diff --git a/tools/testing/selftests/kvm/s390x/resets.c b/tools/testing/selftests/kvm/s390x/resets.c
index 1485bc6c8999..b143db6d8693 100644
--- a/tools/testing/selftests/kvm/s390x/resets.c
+++ b/tools/testing/selftests/kvm/s390x/resets.c
@@ -20,29 +20,42 @@ struct kvm_s390_irq buf[VCPU_ID + LOCAL_IRQS];
struct kvm_vm *vm;
struct kvm_run *run;
-struct kvm_sync_regs *regs;
-static uint64_t regs_null[16];
-
-static uint64_t crs[16] = { 0x40000ULL,
- 0x42000ULL,
- 0, 0, 0, 0, 0,
- 0x43000ULL,
- 0, 0, 0, 0, 0,
- 0x44000ULL,
- 0, 0
-};
+struct kvm_sync_regs *sync_regs;
+static uint8_t regs_null[512];
static void guest_code_initial(void)
{
- /* Round toward 0 */
- uint32_t fpc = 0x11;
+ /* set several CRs to "safe" value */
+ unsigned long cr2_59 = 0x10; /* enable guarded storage */
+ unsigned long cr8_63 = 0x1; /* monitor mask = 1 */
+ unsigned long cr10 = 1; /* PER START */
+ unsigned long cr11 = -1; /* PER END */
+
/* Dirty registers */
asm volatile (
- " lctlg 0,15,%0\n"
- " sfpc %1\n"
- : : "Q" (crs), "d" (fpc));
- GUEST_SYNC(0);
+ " lghi 2,0x11\n" /* Round toward 0 */
+ " sfpc 2\n" /* set fpc to !=0 */
+ " lctlg 2,2,%0\n"
+ " lctlg 8,8,%1\n"
+ " lctlg 10,10,%2\n"
+ " lctlg 11,11,%3\n"
+ /* now clobber some general purpose regs */
+ " llihh 0,0xffff\n"
+ " llihl 1,0x5555\n"
+ " llilh 2,0xaaaa\n"
+ " llill 3,0x0000\n"
+ /* now clobber a floating point reg */
+ " lghi 4,0x1\n"
+ " cdgbr 0,4\n"
+ /* now clobber an access reg */
+ " sar 9,4\n"
+ /* We embed diag 501 here to control register content */
+ " diag 0,0,0x501\n"
+ :
+ : "m" (cr2_59), "m" (cr8_63), "m" (cr10), "m" (cr11)
+ /* no clobber list as this should not return */
+ );
}
static void test_one_reg(uint64_t id, uint64_t value)
@@ -53,7 +66,7 @@ static void test_one_reg(uint64_t id, uint64_t value)
reg.addr = (uintptr_t)&eval_reg;
reg.id = id;
vcpu_get_reg(vm, VCPU_ID, &reg);
- TEST_ASSERT(eval_reg == value, "value == %s", value);
+ TEST_ASSERT(eval_reg == value, "value == 0x%lx", value);
}
static void assert_noirq(void)
@@ -87,6 +100,31 @@ static void assert_clear(void)
vcpu_fpu_get(vm, VCPU_ID, &fpu);
TEST_ASSERT(!memcmp(&fpu.fprs, regs_null, sizeof(fpu.fprs)), "fprs == 0");
+
+ /* sync regs */
+ TEST_ASSERT(!memcmp(sync_regs->gprs, regs_null, sizeof(sync_regs->gprs)),
+ "gprs0-15 == 0 (sync_regs)");
+
+ TEST_ASSERT(!memcmp(sync_regs->acrs, regs_null, sizeof(sync_regs->acrs)),
+ "acrs0-15 == 0 (sync_regs)");
+
+ TEST_ASSERT(!memcmp(sync_regs->vrs, regs_null, sizeof(sync_regs->vrs)),
+ "vrs0-15 == 0 (sync_regs)");
+}
+
+static void assert_initial_noclear(void)
+{
+ TEST_ASSERT(sync_regs->gprs[0] == 0xffff000000000000UL,
+ "gpr0 == 0xffff000000000000 (sync_regs)");
+ TEST_ASSERT(sync_regs->gprs[1] == 0x0000555500000000UL,
+ "gpr1 == 0x0000555500000000 (sync_regs)");
+ TEST_ASSERT(sync_regs->gprs[2] == 0x00000000aaaa0000UL,
+ "gpr2 == 0x00000000aaaa0000 (sync_regs)");
+ TEST_ASSERT(sync_regs->gprs[3] == 0x0000000000000000UL,
+ "gpr3 == 0x0000000000000000 (sync_regs)");
+ TEST_ASSERT(sync_regs->fprs[0] == 0x3ff0000000000000UL,
+ "fpr0 == 0f1 (sync_regs)");
+ TEST_ASSERT(sync_regs->acrs[9] == 1, "ar9 == 1 (sync_regs)");
}
static void assert_initial(void)
@@ -94,12 +132,32 @@ static void assert_initial(void)
struct kvm_sregs sregs;
struct kvm_fpu fpu;
+ /* KVM_GET_SREGS */
vcpu_sregs_get(vm, VCPU_ID, &sregs);
- TEST_ASSERT(sregs.crs[0] == 0xE0UL, "cr0 == 0xE0");
- TEST_ASSERT(sregs.crs[14] == 0xC2000000UL, "cr14 == 0xC2000000");
+ TEST_ASSERT(sregs.crs[0] == 0xE0UL, "cr0 == 0xE0 (KVM_GET_SREGS)");
+ TEST_ASSERT(sregs.crs[14] == 0xC2000000UL,
+ "cr14 == 0xC2000000 (KVM_GET_SREGS)");
TEST_ASSERT(!memcmp(&sregs.crs[1], regs_null, sizeof(sregs.crs[1]) * 12),
- "cr1-13 == 0");
- TEST_ASSERT(sregs.crs[15] == 0, "cr15 == 0");
+ "cr1-13 == 0 (KVM_GET_SREGS)");
+ TEST_ASSERT(sregs.crs[15] == 0, "cr15 == 0 (KVM_GET_SREGS)");
+
+ /* sync regs */
+ TEST_ASSERT(sync_regs->crs[0] == 0xE0UL, "cr0 == 0xE0 (sync_regs)");
+ TEST_ASSERT(sync_regs->crs[14] == 0xC2000000UL,
+ "cr14 == 0xC2000000 (sync_regs)");
+ TEST_ASSERT(!memcmp(&sync_regs->crs[1], regs_null, 8 * 12),
+ "cr1-13 == 0 (sync_regs)");
+ TEST_ASSERT(sync_regs->crs[15] == 0, "cr15 == 0 (sync_regs)");
+ TEST_ASSERT(sync_regs->fpc == 0, "fpc == 0 (sync_regs)");
+ TEST_ASSERT(sync_regs->todpr == 0, "todpr == 0 (sync_regs)");
+ TEST_ASSERT(sync_regs->cputm == 0, "cputm == 0 (sync_regs)");
+ TEST_ASSERT(sync_regs->ckc == 0, "ckc == 0 (sync_regs)");
+ TEST_ASSERT(sync_regs->pp == 0, "pp == 0 (sync_regs)");
+ TEST_ASSERT(sync_regs->gbea == 1, "gbea == 1 (sync_regs)");
+
+ /* kvm_run */
+ TEST_ASSERT(run->psw_addr == 0, "psw_addr == 0 (kvm_run)");
+ TEST_ASSERT(run->psw_mask == 0, "psw_mask == 0 (kvm_run)");
vcpu_fpu_get(vm, VCPU_ID, &fpu);
TEST_ASSERT(!fpu.fpc, "fpc == 0");
@@ -111,9 +169,19 @@ static void assert_initial(void)
test_one_reg(KVM_REG_S390_CLOCK_COMP, 0);
}
+static void assert_normal_noclear(void)
+{
+ TEST_ASSERT(sync_regs->crs[2] == 0x10, "cr2 == 10 (sync_regs)");
+ TEST_ASSERT(sync_regs->crs[8] == 1, "cr10 == 1 (sync_regs)");
+ TEST_ASSERT(sync_regs->crs[10] == 1, "cr10 == 1 (sync_regs)");
+ TEST_ASSERT(sync_regs->crs[11] == -1, "cr11 == -1 (sync_regs)");
+}
+
static void assert_normal(void)
{
test_one_reg(KVM_REG_S390_PFTOKEN, KVM_S390_PFAULT_TOKEN_INVALID);
+ TEST_ASSERT(sync_regs->pft == KVM_S390_PFAULT_TOKEN_INVALID,
+ "pft == 0xff..... (sync_regs)");
assert_noirq();
}
@@ -134,53 +202,67 @@ static void inject_irq(int cpu_id)
static void test_normal(void)
{
- printf("Testing normal reset\n");
+ pr_info("Testing normal reset\n");
/* Create VM */
vm = vm_create_default(VCPU_ID, 0, guest_code_initial);
run = vcpu_state(vm, VCPU_ID);
- regs = &run->s.regs;
+ sync_regs = &run->s.regs;
vcpu_run(vm, VCPU_ID);
inject_irq(VCPU_ID);
vcpu_ioctl(vm, VCPU_ID, KVM_S390_NORMAL_RESET, 0);
+
+ /* must clears */
assert_normal();
+ /* must not clears */
+ assert_normal_noclear();
+ assert_initial_noclear();
+
kvm_vm_free(vm);
}
static void test_initial(void)
{
- printf("Testing initial reset\n");
+ pr_info("Testing initial reset\n");
vm = vm_create_default(VCPU_ID, 0, guest_code_initial);
run = vcpu_state(vm, VCPU_ID);
- regs = &run->s.regs;
+ sync_regs = &run->s.regs;
vcpu_run(vm, VCPU_ID);
inject_irq(VCPU_ID);
vcpu_ioctl(vm, VCPU_ID, KVM_S390_INITIAL_RESET, 0);
+
+ /* must clears */
assert_normal();
assert_initial();
+ /* must not clears */
+ assert_initial_noclear();
+
kvm_vm_free(vm);
}
static void test_clear(void)
{
- printf("Testing clear reset\n");
+ pr_info("Testing clear reset\n");
vm = vm_create_default(VCPU_ID, 0, guest_code_initial);
run = vcpu_state(vm, VCPU_ID);
- regs = &run->s.regs;
+ sync_regs = &run->s.regs;
vcpu_run(vm, VCPU_ID);
inject_irq(VCPU_ID);
vcpu_ioctl(vm, VCPU_ID, KVM_S390_CLEAR_RESET, 0);
+
+ /* must clears */
assert_normal();
assert_initial();
assert_clear();
+
kvm_vm_free(vm);
}
diff --git a/tools/testing/selftests/kvm/s390x/sync_regs_test.c b/tools/testing/selftests/kvm/s390x/sync_regs_test.c
index b705637ca14b..5731ccf34917 100644
--- a/tools/testing/selftests/kvm/s390x/sync_regs_test.c
+++ b/tools/testing/selftests/kvm/s390x/sync_regs_test.c
@@ -42,6 +42,13 @@ static void guest_code(void)
" values did not match: 0x%llx, 0x%llx\n", \
left->reg, right->reg)
+#define REG_COMPARE32(reg) \
+ TEST_ASSERT(left->reg == right->reg, \
+ "Register " #reg \
+ " values did not match: 0x%x, 0x%x\n", \
+ left->reg, right->reg)
+
+
static void compare_regs(struct kvm_regs *left, struct kvm_sync_regs *right)
{
int i;
@@ -55,7 +62,7 @@ static void compare_sregs(struct kvm_sregs *left, struct kvm_sync_regs *right)
int i;
for (i = 0; i < 16; i++)
- REG_COMPARE(acrs[i]);
+ REG_COMPARE32(acrs[i]);
for (i = 0; i < 16; i++)
REG_COMPARE(crs[i]);
@@ -79,7 +86,7 @@ int main(int argc, char *argv[])
cap = kvm_check_cap(KVM_CAP_SYNC_REGS);
if (!cap) {
- fprintf(stderr, "CAP_SYNC_REGS not supported, skipping test\n");
+ print_skip("CAP_SYNC_REGS not supported");
exit(KSFT_SKIP);
}
@@ -155,7 +162,7 @@ int main(int argc, char *argv[])
"r11 sync regs value incorrect 0x%llx.",
run->s.regs.gprs[11]);
TEST_ASSERT(run->s.regs.acrs[0] == 1 << 11,
- "acr0 sync regs value incorrect 0x%llx.",
+ "acr0 sync regs value incorrect 0x%x.",
run->s.regs.acrs[0]);
vcpu_regs_get(vm, VCPU_ID, &regs);
diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c
new file mode 100644
index 000000000000..b3ece55a2da6
--- /dev/null
+++ b/tools/testing/selftests/kvm/set_memory_region_test.c
@@ -0,0 +1,408 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE /* for program_invocation_short_name */
+#include <fcntl.h>
+#include <pthread.h>
+#include <sched.h>
+#include <semaphore.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+
+#include <linux/compiler.h>
+
+#include <test_util.h>
+#include <kvm_util.h>
+#include <processor.h>
+
+#define VCPU_ID 0
+
+/*
+ * s390x needs at least 1MB alignment, and the x86_64 MOVE/DELETE tests need a
+ * 2MB sized and aligned region so that the initial region corresponds to
+ * exactly one large page.
+ */
+#define MEM_REGION_SIZE 0x200000
+
+#ifdef __x86_64__
+/*
+ * Somewhat arbitrary location and slot, intended to not overlap anything.
+ */
+#define MEM_REGION_GPA 0xc0000000
+#define MEM_REGION_SLOT 10
+
+static const uint64_t MMIO_VAL = 0xbeefull;
+
+extern const uint64_t final_rip_start;
+extern const uint64_t final_rip_end;
+
+static sem_t vcpu_ready;
+
+static inline uint64_t guest_spin_on_val(uint64_t spin_val)
+{
+ uint64_t val;
+
+ do {
+ val = READ_ONCE(*((uint64_t *)MEM_REGION_GPA));
+ } while (val == spin_val);
+
+ GUEST_SYNC(0);
+ return val;
+}
+
+static void *vcpu_worker(void *data)
+{
+ struct kvm_vm *vm = data;
+ struct kvm_run *run;
+ struct ucall uc;
+ uint64_t cmd;
+
+ /*
+ * Loop until the guest is done. Re-enter the guest on all MMIO exits,
+ * which will occur if the guest attempts to access a memslot after it
+ * has been deleted or while it is being moved .
+ */
+ run = vcpu_state(vm, VCPU_ID);
+
+ while (1) {
+ vcpu_run(vm, VCPU_ID);
+
+ if (run->exit_reason == KVM_EXIT_IO) {
+ cmd = get_ucall(vm, VCPU_ID, &uc);
+ if (cmd != UCALL_SYNC)
+ break;
+
+ sem_post(&vcpu_ready);
+ continue;
+ }
+
+ if (run->exit_reason != KVM_EXIT_MMIO)
+ break;
+
+ TEST_ASSERT(!run->mmio.is_write, "Unexpected exit mmio write");
+ TEST_ASSERT(run->mmio.len == 8,
+ "Unexpected exit mmio size = %u", run->mmio.len);
+
+ TEST_ASSERT(run->mmio.phys_addr == MEM_REGION_GPA,
+ "Unexpected exit mmio address = 0x%llx",
+ run->mmio.phys_addr);
+ memcpy(run->mmio.data, &MMIO_VAL, 8);
+ }
+
+ if (run->exit_reason == KVM_EXIT_IO && cmd == UCALL_ABORT)
+ TEST_FAIL("%s at %s:%ld, val = %lu", (const char *)uc.args[0],
+ __FILE__, uc.args[1], uc.args[2]);
+
+ return NULL;
+}
+
+static void wait_for_vcpu(void)
+{
+ struct timespec ts;
+
+ TEST_ASSERT(!clock_gettime(CLOCK_REALTIME, &ts),
+ "clock_gettime() failed: %d\n", errno);
+
+ ts.tv_sec += 2;
+ TEST_ASSERT(!sem_timedwait(&vcpu_ready, &ts),
+ "sem_timedwait() failed: %d\n", errno);
+
+ /* Wait for the vCPU thread to reenter the guest. */
+ usleep(100000);
+}
+
+static struct kvm_vm *spawn_vm(pthread_t *vcpu_thread, void *guest_code)
+{
+ struct kvm_vm *vm;
+ uint64_t *hva;
+ uint64_t gpa;
+
+ vm = vm_create_default(VCPU_ID, 0, guest_code);
+
+ vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
+
+ vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS_THP,
+ MEM_REGION_GPA, MEM_REGION_SLOT,
+ MEM_REGION_SIZE / getpagesize(), 0);
+
+ /*
+ * Allocate and map two pages so that the GPA accessed by guest_code()
+ * stays valid across the memslot move.
+ */
+ gpa = vm_phy_pages_alloc(vm, 2, MEM_REGION_GPA, MEM_REGION_SLOT);
+ TEST_ASSERT(gpa == MEM_REGION_GPA, "Failed vm_phy_pages_alloc\n");
+
+ virt_map(vm, MEM_REGION_GPA, MEM_REGION_GPA, 2, 0);
+
+ /* Ditto for the host mapping so that both pages can be zeroed. */
+ hva = addr_gpa2hva(vm, MEM_REGION_GPA);
+ memset(hva, 0, 2 * 4096);
+
+ pthread_create(vcpu_thread, NULL, vcpu_worker, vm);
+
+ /* Ensure the guest thread is spun up. */
+ wait_for_vcpu();
+
+ return vm;
+}
+
+
+static void guest_code_move_memory_region(void)
+{
+ uint64_t val;
+
+ GUEST_SYNC(0);
+
+ /*
+ * Spin until the memory region is moved to a misaligned address. This
+ * may or may not trigger MMIO, as the window where the memslot is
+ * invalid is quite small.
+ */
+ val = guest_spin_on_val(0);
+ GUEST_ASSERT_1(val == 1 || val == MMIO_VAL, val);
+
+ /* Spin until the memory region is realigned. */
+ val = guest_spin_on_val(MMIO_VAL);
+ GUEST_ASSERT_1(val == 1, val);
+
+ GUEST_DONE();
+}
+
+static void test_move_memory_region(void)
+{
+ pthread_t vcpu_thread;
+ struct kvm_vm *vm;
+ uint64_t *hva;
+
+ vm = spawn_vm(&vcpu_thread, guest_code_move_memory_region);
+
+ hva = addr_gpa2hva(vm, MEM_REGION_GPA);
+
+ /*
+ * Shift the region's base GPA. The guest should not see "2" as the
+ * hva->gpa translation is misaligned, i.e. the guest is accessing a
+ * different host pfn.
+ */
+ vm_mem_region_move(vm, MEM_REGION_SLOT, MEM_REGION_GPA - 4096);
+ WRITE_ONCE(*hva, 2);
+
+ /*
+ * The guest _might_ see an invalid memslot and trigger MMIO, but it's
+ * a tiny window. Spin and defer the sync until the memslot is
+ * restored and guest behavior is once again deterministic.
+ */
+ usleep(100000);
+
+ /*
+ * Note, value in memory needs to be changed *before* restoring the
+ * memslot, else the guest could race the update and see "2".
+ */
+ WRITE_ONCE(*hva, 1);
+
+ /* Restore the original base, the guest should see "1". */
+ vm_mem_region_move(vm, MEM_REGION_SLOT, MEM_REGION_GPA);
+ wait_for_vcpu();
+ /* Defered sync from when the memslot was misaligned (above). */
+ wait_for_vcpu();
+
+ pthread_join(vcpu_thread, NULL);
+
+ kvm_vm_free(vm);
+}
+
+static void guest_code_delete_memory_region(void)
+{
+ uint64_t val;
+
+ GUEST_SYNC(0);
+
+ /* Spin until the memory region is deleted. */
+ val = guest_spin_on_val(0);
+ GUEST_ASSERT_1(val == MMIO_VAL, val);
+
+ /* Spin until the memory region is recreated. */
+ val = guest_spin_on_val(MMIO_VAL);
+ GUEST_ASSERT_1(val == 0, val);
+
+ /* Spin until the memory region is deleted. */
+ val = guest_spin_on_val(0);
+ GUEST_ASSERT_1(val == MMIO_VAL, val);
+
+ asm("1:\n\t"
+ ".pushsection .rodata\n\t"
+ ".global final_rip_start\n\t"
+ "final_rip_start: .quad 1b\n\t"
+ ".popsection");
+
+ /* Spin indefinitely (until the code memslot is deleted). */
+ guest_spin_on_val(MMIO_VAL);
+
+ asm("1:\n\t"
+ ".pushsection .rodata\n\t"
+ ".global final_rip_end\n\t"
+ "final_rip_end: .quad 1b\n\t"
+ ".popsection");
+
+ GUEST_ASSERT_1(0, 0);
+}
+
+static void test_delete_memory_region(void)
+{
+ pthread_t vcpu_thread;
+ struct kvm_regs regs;
+ struct kvm_run *run;
+ struct kvm_vm *vm;
+
+ vm = spawn_vm(&vcpu_thread, guest_code_delete_memory_region);
+
+ /* Delete the memory region, the guest should not die. */
+ vm_mem_region_delete(vm, MEM_REGION_SLOT);
+ wait_for_vcpu();
+
+ /* Recreate the memory region. The guest should see "0". */
+ vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS_THP,
+ MEM_REGION_GPA, MEM_REGION_SLOT,
+ MEM_REGION_SIZE / getpagesize(), 0);
+ wait_for_vcpu();
+
+ /* Delete the region again so that there's only one memslot left. */
+ vm_mem_region_delete(vm, MEM_REGION_SLOT);
+ wait_for_vcpu();
+
+ /*
+ * Delete the primary memslot. This should cause an emulation error or
+ * shutdown due to the page tables getting nuked.
+ */
+ vm_mem_region_delete(vm, 0);
+
+ pthread_join(vcpu_thread, NULL);
+
+ run = vcpu_state(vm, VCPU_ID);
+
+ TEST_ASSERT(run->exit_reason == KVM_EXIT_SHUTDOWN ||
+ run->exit_reason == KVM_EXIT_INTERNAL_ERROR,
+ "Unexpected exit reason = %d", run->exit_reason);
+
+ vcpu_regs_get(vm, VCPU_ID, &regs);
+
+ /*
+ * On AMD, after KVM_EXIT_SHUTDOWN the VMCB has been reinitialized already,
+ * so the instruction pointer would point to the reset vector.
+ */
+ if (run->exit_reason == KVM_EXIT_INTERNAL_ERROR)
+ TEST_ASSERT(regs.rip >= final_rip_start &&
+ regs.rip < final_rip_end,
+ "Bad rip, expected 0x%lx - 0x%lx, got 0x%llx\n",
+ final_rip_start, final_rip_end, regs.rip);
+
+ kvm_vm_free(vm);
+}
+
+static void test_zero_memory_regions(void)
+{
+ struct kvm_run *run;
+ struct kvm_vm *vm;
+
+ pr_info("Testing KVM_RUN with zero added memory regions\n");
+
+ vm = vm_create(VM_MODE_DEFAULT, 0, O_RDWR);
+ vm_vcpu_add(vm, VCPU_ID);
+
+ TEST_ASSERT(!ioctl(vm_get_fd(vm), KVM_SET_NR_MMU_PAGES, 64),
+ "KVM_SET_NR_MMU_PAGES failed, errno = %d\n", errno);
+ vcpu_run(vm, VCPU_ID);
+
+ run = vcpu_state(vm, VCPU_ID);
+ TEST_ASSERT(run->exit_reason == KVM_EXIT_INTERNAL_ERROR,
+ "Unexpected exit_reason = %u\n", run->exit_reason);
+
+ kvm_vm_free(vm);
+}
+#endif /* __x86_64__ */
+
+/*
+ * Test it can be added memory slots up to KVM_CAP_NR_MEMSLOTS, then any
+ * tentative to add further slots should fail.
+ */
+static void test_add_max_memory_regions(void)
+{
+ int ret;
+ struct kvm_vm *vm;
+ uint32_t max_mem_slots;
+ uint32_t slot;
+ uint64_t guest_addr = 0x0;
+ uint64_t mem_reg_npages;
+ void *mem;
+
+ max_mem_slots = kvm_check_cap(KVM_CAP_NR_MEMSLOTS);
+ TEST_ASSERT(max_mem_slots > 0,
+ "KVM_CAP_NR_MEMSLOTS should be greater than 0");
+ pr_info("Allowed number of memory slots: %i\n", max_mem_slots);
+
+ vm = vm_create(VM_MODE_DEFAULT, 0, O_RDWR);
+
+ mem_reg_npages = vm_calc_num_guest_pages(VM_MODE_DEFAULT, MEM_REGION_SIZE);
+
+ /* Check it can be added memory slots up to the maximum allowed */
+ pr_info("Adding slots 0..%i, each memory region with %dK size\n",
+ (max_mem_slots - 1), MEM_REGION_SIZE >> 10);
+ for (slot = 0; slot < max_mem_slots; slot++) {
+ vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
+ guest_addr, slot, mem_reg_npages,
+ 0);
+ guest_addr += MEM_REGION_SIZE;
+ }
+
+ /* Check it cannot be added memory slots beyond the limit */
+ mem = mmap(NULL, MEM_REGION_SIZE, PROT_READ | PROT_WRITE,
+ MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+ TEST_ASSERT(mem != MAP_FAILED, "Failed to mmap() host");
+
+ ret = ioctl(vm_get_fd(vm), KVM_SET_USER_MEMORY_REGION,
+ &(struct kvm_userspace_memory_region) {slot, 0, guest_addr,
+ MEM_REGION_SIZE, (uint64_t) mem});
+ TEST_ASSERT(ret == -1 && errno == EINVAL,
+ "Adding one more memory slot should fail with EINVAL");
+
+ munmap(mem, MEM_REGION_SIZE);
+ kvm_vm_free(vm);
+}
+
+int main(int argc, char *argv[])
+{
+#ifdef __x86_64__
+ int i, loops;
+#endif
+
+ /* Tell stdout not to buffer its content */
+ setbuf(stdout, NULL);
+
+#ifdef __x86_64__
+ /*
+ * FIXME: the zero-memslot test fails on aarch64 and s390x because
+ * KVM_RUN fails with ENOEXEC or EFAULT.
+ */
+ test_zero_memory_regions();
+#endif
+
+ test_add_max_memory_regions();
+
+#ifdef __x86_64__
+ if (argc > 1)
+ loops = atoi(argv[1]);
+ else
+ loops = 10;
+
+ pr_info("Testing MOVE of in-use region, %d loops\n", loops);
+ for (i = 0; i < loops; i++)
+ test_move_memory_region();
+
+ pr_info("Testing DELETE of in-use region, %d loops\n", loops);
+ for (i = 0; i < loops; i++)
+ test_delete_memory_region();
+#endif
+
+ return 0;
+}
diff --git a/tools/testing/selftests/kvm/steal_time.c b/tools/testing/selftests/kvm/steal_time.c
new file mode 100644
index 000000000000..fcc840088c91
--- /dev/null
+++ b/tools/testing/selftests/kvm/steal_time.c
@@ -0,0 +1,352 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * steal/stolen time test
+ *
+ * Copyright (C) 2020, Red Hat, Inc.
+ */
+#define _GNU_SOURCE
+#include <stdio.h>
+#include <time.h>
+#include <sched.h>
+#include <pthread.h>
+#include <linux/kernel.h>
+#include <sys/syscall.h>
+#include <asm/kvm.h>
+#include <asm/kvm_para.h>
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+
+#define NR_VCPUS 4
+#define ST_GPA_BASE (1 << 30)
+#define MIN_RUN_DELAY_NS 200000UL
+
+static void *st_gva[NR_VCPUS];
+static uint64_t guest_stolen_time[NR_VCPUS];
+
+#if defined(__x86_64__)
+
+/* steal_time must have 64-byte alignment */
+#define STEAL_TIME_SIZE ((sizeof(struct kvm_steal_time) + 63) & ~63)
+
+static void check_status(struct kvm_steal_time *st)
+{
+ GUEST_ASSERT(!(READ_ONCE(st->version) & 1));
+ GUEST_ASSERT(READ_ONCE(st->flags) == 0);
+ GUEST_ASSERT(READ_ONCE(st->preempted) == 0);
+}
+
+static void guest_code(int cpu)
+{
+ struct kvm_steal_time *st = st_gva[cpu];
+ uint32_t version;
+
+ GUEST_ASSERT(rdmsr(MSR_KVM_STEAL_TIME) == ((uint64_t)st_gva[cpu] | KVM_MSR_ENABLED));
+
+ memset(st, 0, sizeof(*st));
+ GUEST_SYNC(0);
+
+ check_status(st);
+ WRITE_ONCE(guest_stolen_time[cpu], st->steal);
+ version = READ_ONCE(st->version);
+ check_status(st);
+ GUEST_SYNC(1);
+
+ check_status(st);
+ GUEST_ASSERT(version < READ_ONCE(st->version));
+ WRITE_ONCE(guest_stolen_time[cpu], st->steal);
+ check_status(st);
+ GUEST_DONE();
+}
+
+static void steal_time_init(struct kvm_vm *vm)
+{
+ int i;
+
+ if (!(kvm_get_supported_cpuid_entry(KVM_CPUID_FEATURES)->eax &
+ KVM_FEATURE_STEAL_TIME)) {
+ print_skip("steal-time not supported");
+ exit(KSFT_SKIP);
+ }
+
+ for (i = 0; i < NR_VCPUS; ++i) {
+ int ret;
+
+ vcpu_set_cpuid(vm, i, kvm_get_supported_cpuid());
+
+ /* ST_GPA_BASE is identity mapped */
+ st_gva[i] = (void *)(ST_GPA_BASE + i * STEAL_TIME_SIZE);
+ sync_global_to_guest(vm, st_gva[i]);
+
+ ret = _vcpu_set_msr(vm, i, MSR_KVM_STEAL_TIME, (ulong)st_gva[i] | KVM_STEAL_RESERVED_MASK);
+ TEST_ASSERT(ret == 0, "Bad GPA didn't fail");
+
+ vcpu_set_msr(vm, i, MSR_KVM_STEAL_TIME, (ulong)st_gva[i] | KVM_MSR_ENABLED);
+ }
+}
+
+static void steal_time_dump(struct kvm_vm *vm, uint32_t vcpuid)
+{
+ struct kvm_steal_time *st = addr_gva2hva(vm, (ulong)st_gva[vcpuid]);
+ int i;
+
+ pr_info("VCPU%d:\n", vcpuid);
+ pr_info(" steal: %lld\n", st->steal);
+ pr_info(" version: %d\n", st->version);
+ pr_info(" flags: %d\n", st->flags);
+ pr_info(" preempted: %d\n", st->preempted);
+ pr_info(" u8_pad: ");
+ for (i = 0; i < 3; ++i)
+ pr_info("%d", st->u8_pad[i]);
+ pr_info("\n pad: ");
+ for (i = 0; i < 11; ++i)
+ pr_info("%d", st->pad[i]);
+ pr_info("\n");
+}
+
+#elif defined(__aarch64__)
+
+/* PV_TIME_ST must have 64-byte alignment */
+#define STEAL_TIME_SIZE ((sizeof(struct st_time) + 63) & ~63)
+
+#define SMCCC_ARCH_FEATURES 0x80000001
+#define PV_TIME_FEATURES 0xc5000020
+#define PV_TIME_ST 0xc5000021
+
+struct st_time {
+ uint32_t rev;
+ uint32_t attr;
+ uint64_t st_time;
+};
+
+static int64_t smccc(uint32_t func, uint32_t arg)
+{
+ unsigned long ret;
+
+ asm volatile(
+ "mov x0, %1\n"
+ "mov x1, %2\n"
+ "hvc #0\n"
+ "mov %0, x0\n"
+ : "=r" (ret) : "r" (func), "r" (arg) :
+ "x0", "x1", "x2", "x3");
+
+ return ret;
+}
+
+static void check_status(struct st_time *st)
+{
+ GUEST_ASSERT(READ_ONCE(st->rev) == 0);
+ GUEST_ASSERT(READ_ONCE(st->attr) == 0);
+}
+
+static void guest_code(int cpu)
+{
+ struct st_time *st;
+ int64_t status;
+
+ status = smccc(SMCCC_ARCH_FEATURES, PV_TIME_FEATURES);
+ GUEST_ASSERT(status == 0);
+ status = smccc(PV_TIME_FEATURES, PV_TIME_FEATURES);
+ GUEST_ASSERT(status == 0);
+ status = smccc(PV_TIME_FEATURES, PV_TIME_ST);
+ GUEST_ASSERT(status == 0);
+
+ status = smccc(PV_TIME_ST, 0);
+ GUEST_ASSERT(status != -1);
+ GUEST_ASSERT(status == (ulong)st_gva[cpu]);
+
+ st = (struct st_time *)status;
+ GUEST_SYNC(0);
+
+ check_status(st);
+ WRITE_ONCE(guest_stolen_time[cpu], st->st_time);
+ GUEST_SYNC(1);
+
+ check_status(st);
+ WRITE_ONCE(guest_stolen_time[cpu], st->st_time);
+ GUEST_DONE();
+}
+
+static void steal_time_init(struct kvm_vm *vm)
+{
+ struct kvm_device_attr dev = {
+ .group = KVM_ARM_VCPU_PVTIME_CTRL,
+ .attr = KVM_ARM_VCPU_PVTIME_IPA,
+ };
+ int i, ret;
+
+ ret = _vcpu_ioctl(vm, 0, KVM_HAS_DEVICE_ATTR, &dev);
+ if (ret != 0 && errno == ENXIO) {
+ print_skip("steal-time not supported");
+ exit(KSFT_SKIP);
+ }
+
+ for (i = 0; i < NR_VCPUS; ++i) {
+ uint64_t st_ipa;
+
+ vcpu_ioctl(vm, i, KVM_HAS_DEVICE_ATTR, &dev);
+
+ dev.addr = (uint64_t)&st_ipa;
+
+ /* ST_GPA_BASE is identity mapped */
+ st_gva[i] = (void *)(ST_GPA_BASE + i * STEAL_TIME_SIZE);
+ sync_global_to_guest(vm, st_gva[i]);
+
+ st_ipa = (ulong)st_gva[i] | 1;
+ ret = _vcpu_ioctl(vm, i, KVM_SET_DEVICE_ATTR, &dev);
+ TEST_ASSERT(ret == -1 && errno == EINVAL, "Bad IPA didn't report EINVAL");
+
+ st_ipa = (ulong)st_gva[i];
+ vcpu_ioctl(vm, i, KVM_SET_DEVICE_ATTR, &dev);
+
+ ret = _vcpu_ioctl(vm, i, KVM_SET_DEVICE_ATTR, &dev);
+ TEST_ASSERT(ret == -1 && errno == EEXIST, "Set IPA twice without EEXIST");
+
+ }
+}
+
+static void steal_time_dump(struct kvm_vm *vm, uint32_t vcpuid)
+{
+ struct st_time *st = addr_gva2hva(vm, (ulong)st_gva[vcpuid]);
+
+ pr_info("VCPU%d:\n", vcpuid);
+ pr_info(" rev: %d\n", st->rev);
+ pr_info(" attr: %d\n", st->attr);
+ pr_info(" st_time: %ld\n", st->st_time);
+}
+
+#endif
+
+static long get_run_delay(void)
+{
+ char path[64];
+ long val[2];
+ FILE *fp;
+
+ sprintf(path, "/proc/%ld/schedstat", syscall(SYS_gettid));
+ fp = fopen(path, "r");
+ fscanf(fp, "%ld %ld ", &val[0], &val[1]);
+ fclose(fp);
+
+ return val[1];
+}
+
+static void *do_steal_time(void *arg)
+{
+ struct timespec ts, stop;
+
+ clock_gettime(CLOCK_MONOTONIC, &ts);
+ stop = timespec_add_ns(ts, MIN_RUN_DELAY_NS);
+
+ while (1) {
+ clock_gettime(CLOCK_MONOTONIC, &ts);
+ if (timespec_to_ns(timespec_sub(ts, stop)) >= 0)
+ break;
+ }
+
+ return NULL;
+}
+
+static void run_vcpu(struct kvm_vm *vm, uint32_t vcpuid)
+{
+ struct ucall uc;
+
+ vcpu_args_set(vm, vcpuid, 1, vcpuid);
+
+ vcpu_ioctl(vm, vcpuid, KVM_RUN, NULL);
+
+ switch (get_ucall(vm, vcpuid, &uc)) {
+ case UCALL_SYNC:
+ case UCALL_DONE:
+ break;
+ case UCALL_ABORT:
+ TEST_ASSERT(false, "%s at %s:%ld", (const char *)uc.args[0],
+ __FILE__, uc.args[1]);
+ default:
+ TEST_ASSERT(false, "Unexpected exit: %s",
+ exit_reason_str(vcpu_state(vm, vcpuid)->exit_reason));
+ }
+}
+
+int main(int ac, char **av)
+{
+ struct kvm_vm *vm;
+ pthread_attr_t attr;
+ pthread_t thread;
+ cpu_set_t cpuset;
+ unsigned int gpages;
+ long stolen_time;
+ long run_delay;
+ bool verbose;
+ int i;
+
+ verbose = ac > 1 && (!strncmp(av[1], "-v", 3) || !strncmp(av[1], "--verbose", 10));
+
+ /* Set CPU affinity so we can force preemption of the VCPU */
+ CPU_ZERO(&cpuset);
+ CPU_SET(0, &cpuset);
+ pthread_attr_init(&attr);
+ pthread_attr_setaffinity_np(&attr, sizeof(cpu_set_t), &cpuset);
+ pthread_setaffinity_np(pthread_self(), sizeof(cpu_set_t), &cpuset);
+
+ /* Create a one VCPU guest and an identity mapped memslot for the steal time structure */
+ vm = vm_create_default(0, 0, guest_code);
+ gpages = vm_calc_num_guest_pages(VM_MODE_DEFAULT, STEAL_TIME_SIZE * NR_VCPUS);
+ vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, ST_GPA_BASE, 1, gpages, 0);
+ virt_map(vm, ST_GPA_BASE, ST_GPA_BASE, gpages, 0);
+ ucall_init(vm, NULL);
+
+ /* Add the rest of the VCPUs */
+ for (i = 1; i < NR_VCPUS; ++i)
+ vm_vcpu_add_default(vm, i, guest_code);
+
+ steal_time_init(vm);
+
+ /* Run test on each VCPU */
+ for (i = 0; i < NR_VCPUS; ++i) {
+ /* First VCPU run initializes steal-time */
+ run_vcpu(vm, i);
+
+ /* Second VCPU run, expect guest stolen time to be <= run_delay */
+ run_vcpu(vm, i);
+ sync_global_from_guest(vm, guest_stolen_time[i]);
+ stolen_time = guest_stolen_time[i];
+ run_delay = get_run_delay();
+ TEST_ASSERT(stolen_time <= run_delay,
+ "Expected stolen time <= %ld, got %ld",
+ run_delay, stolen_time);
+
+ /* Steal time from the VCPU. The steal time thread has the same CPU affinity as the VCPUs. */
+ run_delay = get_run_delay();
+ pthread_create(&thread, &attr, do_steal_time, NULL);
+ do
+ pthread_yield();
+ while (get_run_delay() - run_delay < MIN_RUN_DELAY_NS);
+ pthread_join(thread, NULL);
+ run_delay = get_run_delay() - run_delay;
+ TEST_ASSERT(run_delay >= MIN_RUN_DELAY_NS,
+ "Expected run_delay >= %ld, got %ld",
+ MIN_RUN_DELAY_NS, run_delay);
+
+ /* Run VCPU again to confirm stolen time is consistent with run_delay */
+ run_vcpu(vm, i);
+ sync_global_from_guest(vm, guest_stolen_time[i]);
+ stolen_time = guest_stolen_time[i] - stolen_time;
+ TEST_ASSERT(stolen_time >= run_delay,
+ "Expected stolen time >= %ld, got %ld",
+ run_delay, stolen_time);
+
+ if (verbose) {
+ pr_info("VCPU%d: total-stolen-time=%ld test-stolen-time=%ld", i,
+ guest_stolen_time[i], stolen_time);
+ if (stolen_time == run_delay)
+ pr_info(" (BONUS: guest test-stolen-time even exactly matches test-run_delay)");
+ pr_info("\n");
+ steal_time_dump(vm, i);
+ }
+ }
+
+ return 0;
+}
diff --git a/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c b/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c
index 63cc9c3f5ab6..140e91901582 100644
--- a/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c
+++ b/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c
@@ -72,7 +72,7 @@ int main(int argc, char *argv[])
entry = kvm_get_supported_cpuid_entry(1);
if (!(entry->ecx & X86_FEATURE_XSAVE)) {
- printf("XSAVE feature not supported, skipping test\n");
+ print_skip("XSAVE feature not supported");
return 0;
}
@@ -101,12 +101,12 @@ int main(int argc, char *argv[])
vcpu_sregs_set(vm, VCPU_ID, &sregs);
break;
case UCALL_ABORT:
- TEST_ASSERT(false, "Guest CR4 bit (OSXSAVE) unsynchronized with CPUID bit.");
+ TEST_FAIL("Guest CR4 bit (OSXSAVE) unsynchronized with CPUID bit.");
break;
case UCALL_DONE:
goto done;
default:
- TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd);
+ TEST_FAIL("Unknown ucall %lu", uc.cmd);
}
}
diff --git a/tools/testing/selftests/kvm/x86_64/debug_regs.c b/tools/testing/selftests/kvm/x86_64/debug_regs.c
new file mode 100644
index 000000000000..8162c58a1234
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/debug_regs.c
@@ -0,0 +1,202 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * KVM guest debug register tests
+ *
+ * Copyright (C) 2020, Red Hat, Inc.
+ */
+#include <stdio.h>
+#include <string.h>
+#include "kvm_util.h"
+#include "processor.h"
+
+#define VCPU_ID 0
+
+#define DR6_BD (1 << 13)
+#define DR7_GD (1 << 13)
+
+/* For testing data access debug BP */
+uint32_t guest_value;
+
+extern unsigned char sw_bp, hw_bp, write_data, ss_start, bd_start;
+
+static void guest_code(void)
+{
+ /*
+ * Software BP tests.
+ *
+ * NOTE: sw_bp need to be before the cmd here, because int3 is an
+ * exception rather than a normal trap for KVM_SET_GUEST_DEBUG (we
+ * capture it using the vcpu exception bitmap).
+ */
+ asm volatile("sw_bp: int3");
+
+ /* Hardware instruction BP test */
+ asm volatile("hw_bp: nop");
+
+ /* Hardware data BP test */
+ asm volatile("mov $1234,%%rax;\n\t"
+ "mov %%rax,%0;\n\t write_data:"
+ : "=m" (guest_value) : : "rax");
+
+ /* Single step test, covers 2 basic instructions and 2 emulated */
+ asm volatile("ss_start: "
+ "xor %%rax,%%rax\n\t"
+ "cpuid\n\t"
+ "movl $0x1a0,%%ecx\n\t"
+ "rdmsr\n\t"
+ : : : "rax", "ecx");
+
+ /* DR6.BD test */
+ asm volatile("bd_start: mov %%dr0, %%rax" : : : "rax");
+ GUEST_DONE();
+}
+
+#define CLEAR_DEBUG() memset(&debug, 0, sizeof(debug))
+#define APPLY_DEBUG() vcpu_set_guest_debug(vm, VCPU_ID, &debug)
+#define CAST_TO_RIP(v) ((unsigned long long)&(v))
+#define SET_RIP(v) do { \
+ vcpu_regs_get(vm, VCPU_ID, &regs); \
+ regs.rip = (v); \
+ vcpu_regs_set(vm, VCPU_ID, &regs); \
+ } while (0)
+#define MOVE_RIP(v) SET_RIP(regs.rip + (v));
+
+int main(void)
+{
+ struct kvm_guest_debug debug;
+ unsigned long long target_dr6, target_rip;
+ struct kvm_regs regs;
+ struct kvm_run *run;
+ struct kvm_vm *vm;
+ struct ucall uc;
+ uint64_t cmd;
+ int i;
+ /* Instruction lengths starting at ss_start */
+ int ss_size[4] = {
+ 3, /* xor */
+ 2, /* cpuid */
+ 5, /* mov */
+ 2, /* rdmsr */
+ };
+
+ if (!kvm_check_cap(KVM_CAP_SET_GUEST_DEBUG)) {
+ print_skip("KVM_CAP_SET_GUEST_DEBUG not supported");
+ return 0;
+ }
+
+ vm = vm_create_default(VCPU_ID, 0, guest_code);
+ vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
+ run = vcpu_state(vm, VCPU_ID);
+
+ /* Test software BPs - int3 */
+ CLEAR_DEBUG();
+ debug.control = KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP;
+ APPLY_DEBUG();
+ vcpu_run(vm, VCPU_ID);
+ TEST_ASSERT(run->exit_reason == KVM_EXIT_DEBUG &&
+ run->debug.arch.exception == BP_VECTOR &&
+ run->debug.arch.pc == CAST_TO_RIP(sw_bp),
+ "INT3: exit %d exception %d rip 0x%llx (should be 0x%llx)",
+ run->exit_reason, run->debug.arch.exception,
+ run->debug.arch.pc, CAST_TO_RIP(sw_bp));
+ MOVE_RIP(1);
+
+ /* Test instruction HW BP over DR[0-3] */
+ for (i = 0; i < 4; i++) {
+ CLEAR_DEBUG();
+ debug.control = KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_HW_BP;
+ debug.arch.debugreg[i] = CAST_TO_RIP(hw_bp);
+ debug.arch.debugreg[7] = 0x400 | (1UL << (2*i+1));
+ APPLY_DEBUG();
+ vcpu_run(vm, VCPU_ID);
+ target_dr6 = 0xffff0ff0 | (1UL << i);
+ TEST_ASSERT(run->exit_reason == KVM_EXIT_DEBUG &&
+ run->debug.arch.exception == DB_VECTOR &&
+ run->debug.arch.pc == CAST_TO_RIP(hw_bp) &&
+ run->debug.arch.dr6 == target_dr6,
+ "INS_HW_BP (DR%d): exit %d exception %d rip 0x%llx "
+ "(should be 0x%llx) dr6 0x%llx (should be 0x%llx)",
+ i, run->exit_reason, run->debug.arch.exception,
+ run->debug.arch.pc, CAST_TO_RIP(hw_bp),
+ run->debug.arch.dr6, target_dr6);
+ }
+ /* Skip "nop" */
+ MOVE_RIP(1);
+
+ /* Test data access HW BP over DR[0-3] */
+ for (i = 0; i < 4; i++) {
+ CLEAR_DEBUG();
+ debug.control = KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_HW_BP;
+ debug.arch.debugreg[i] = CAST_TO_RIP(guest_value);
+ debug.arch.debugreg[7] = 0x00000400 | (1UL << (2*i+1)) |
+ (0x000d0000UL << (4*i));
+ APPLY_DEBUG();
+ vcpu_run(vm, VCPU_ID);
+ target_dr6 = 0xffff0ff0 | (1UL << i);
+ TEST_ASSERT(run->exit_reason == KVM_EXIT_DEBUG &&
+ run->debug.arch.exception == DB_VECTOR &&
+ run->debug.arch.pc == CAST_TO_RIP(write_data) &&
+ run->debug.arch.dr6 == target_dr6,
+ "DATA_HW_BP (DR%d): exit %d exception %d rip 0x%llx "
+ "(should be 0x%llx) dr6 0x%llx (should be 0x%llx)",
+ i, run->exit_reason, run->debug.arch.exception,
+ run->debug.arch.pc, CAST_TO_RIP(write_data),
+ run->debug.arch.dr6, target_dr6);
+ /* Rollback the 4-bytes "mov" */
+ MOVE_RIP(-7);
+ }
+ /* Skip the 4-bytes "mov" */
+ MOVE_RIP(7);
+
+ /* Test single step */
+ target_rip = CAST_TO_RIP(ss_start);
+ target_dr6 = 0xffff4ff0ULL;
+ vcpu_regs_get(vm, VCPU_ID, &regs);
+ for (i = 0; i < (sizeof(ss_size) / sizeof(ss_size[0])); i++) {
+ target_rip += ss_size[i];
+ CLEAR_DEBUG();
+ debug.control = KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_SINGLESTEP;
+ debug.arch.debugreg[7] = 0x00000400;
+ APPLY_DEBUG();
+ vcpu_run(vm, VCPU_ID);
+ TEST_ASSERT(run->exit_reason == KVM_EXIT_DEBUG &&
+ run->debug.arch.exception == DB_VECTOR &&
+ run->debug.arch.pc == target_rip &&
+ run->debug.arch.dr6 == target_dr6,
+ "SINGLE_STEP[%d]: exit %d exception %d rip 0x%llx "
+ "(should be 0x%llx) dr6 0x%llx (should be 0x%llx)",
+ i, run->exit_reason, run->debug.arch.exception,
+ run->debug.arch.pc, target_rip, run->debug.arch.dr6,
+ target_dr6);
+ }
+
+ /* Finally test global disable */
+ CLEAR_DEBUG();
+ debug.control = KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_HW_BP;
+ debug.arch.debugreg[7] = 0x400 | DR7_GD;
+ APPLY_DEBUG();
+ vcpu_run(vm, VCPU_ID);
+ target_dr6 = 0xffff0ff0 | DR6_BD;
+ TEST_ASSERT(run->exit_reason == KVM_EXIT_DEBUG &&
+ run->debug.arch.exception == DB_VECTOR &&
+ run->debug.arch.pc == CAST_TO_RIP(bd_start) &&
+ run->debug.arch.dr6 == target_dr6,
+ "DR7.GD: exit %d exception %d rip 0x%llx "
+ "(should be 0x%llx) dr6 0x%llx (should be 0x%llx)",
+ run->exit_reason, run->debug.arch.exception,
+ run->debug.arch.pc, target_rip, run->debug.arch.dr6,
+ target_dr6);
+
+ /* Disable all debug controls, run to the end */
+ CLEAR_DEBUG();
+ APPLY_DEBUG();
+
+ vcpu_run(vm, VCPU_ID);
+ TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "KVM_EXIT_IO");
+ cmd = get_ucall(vm, VCPU_ID, &uc);
+ TEST_ASSERT(cmd == UCALL_DONE, "UCALL_DONE");
+
+ kvm_vm_free(vm);
+
+ return 0;
+}
diff --git a/tools/testing/selftests/kvm/x86_64/evmcs_test.c b/tools/testing/selftests/kvm/x86_64/evmcs_test.c
index 92915e6408e7..e6e62e5e75b2 100644
--- a/tools/testing/selftests/kvm/x86_64/evmcs_test.c
+++ b/tools/testing/selftests/kvm/x86_64/evmcs_test.c
@@ -21,10 +21,10 @@
void l2_guest_code(void)
{
- GUEST_SYNC(6);
-
GUEST_SYNC(7);
+ GUEST_SYNC(8);
+
/* Done, exit to L1 and never come back. */
vmcall();
}
@@ -50,12 +50,17 @@ void l1_guest_code(struct vmx_pages *vmx_pages)
GUEST_SYNC(5);
GUEST_ASSERT(vmptrstz() == vmx_pages->enlightened_vmcs_gpa);
+ current_evmcs->revision_id = -1u;
+ GUEST_ASSERT(vmlaunch());
+ current_evmcs->revision_id = EVMCS_VERSION;
+ GUEST_SYNC(6);
+
GUEST_ASSERT(!vmlaunch());
GUEST_ASSERT(vmptrstz() == vmx_pages->enlightened_vmcs_gpa);
- GUEST_SYNC(8);
+ GUEST_SYNC(9);
GUEST_ASSERT(!vmresume());
GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
- GUEST_SYNC(9);
+ GUEST_SYNC(10);
}
void guest_code(struct vmx_pages *vmx_pages)
@@ -67,6 +72,10 @@ void guest_code(struct vmx_pages *vmx_pages)
l1_guest_code(vmx_pages);
GUEST_DONE();
+
+ /* Try enlightened vmptrld with an incorrect GPA */
+ evmcs_vmptrld(0xdeadbeef, vmx_pages->enlightened_vmcs);
+ GUEST_ASSERT(vmlaunch());
}
int main(int argc, char *argv[])
@@ -87,7 +96,7 @@ int main(int argc, char *argv[])
if (!kvm_check_cap(KVM_CAP_NESTED_STATE) ||
!kvm_check_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS)) {
- printf("capabilities not available, skipping test\n");
+ print_skip("capabilities not available");
exit(KSFT_SKIP);
}
@@ -109,20 +118,20 @@ int main(int argc, char *argv[])
switch (get_ucall(vm, VCPU_ID, &uc)) {
case UCALL_ABORT:
- TEST_ASSERT(false, "%s at %s:%d", (const char *)uc.args[0],
- __FILE__, uc.args[1]);
+ TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0],
+ __FILE__, uc.args[1]);
/* NOT REACHED */
case UCALL_SYNC:
break;
case UCALL_DONE:
- goto done;
+ goto part1_done;
default:
- TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd);
+ TEST_FAIL("Unknown ucall %lu", uc.cmd);
}
/* UCALL_SYNC is handled here. */
TEST_ASSERT(!strcmp((const char *)uc.args[0], "hello") &&
- uc.args[1] == stage, "Unexpected register values vmexit #%lx, got %lx",
+ uc.args[1] == stage, "Stage %d: Unexpected register values vmexit, got %lx",
stage, (ulong)uc.args[1]);
state = vcpu_save_state(vm, VCPU_ID);
@@ -147,6 +156,10 @@ int main(int argc, char *argv[])
(ulong) regs2.rdi, (ulong) regs2.rsi);
}
-done:
+part1_done:
+ _vcpu_run(vm, VCPU_ID);
+ TEST_ASSERT(run->exit_reason == KVM_EXIT_SHUTDOWN,
+ "Unexpected successful VMEnter with invalid eVMCS pointer!");
+
kvm_vm_free(vm);
}
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c b/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c
index 443a2b54645b..4a7967cca281 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c
@@ -26,18 +26,18 @@ static void guest_code(void)
{
}
-static int smt_possible(void)
+static bool smt_possible(void)
{
char buf[16];
FILE *f;
- bool res = 1;
+ bool res = true;
f = fopen("/sys/devices/system/cpu/smt/control", "r");
if (f) {
if (fread(buf, sizeof(*buf), sizeof(buf), f) > 0) {
if (!strncmp(buf, "forceoff", 8) ||
!strncmp(buf, "notsupported", 12))
- res = 0;
+ res = false;
}
fclose(f);
}
@@ -46,29 +46,31 @@ static int smt_possible(void)
}
static void test_hv_cpuid(struct kvm_cpuid2 *hv_cpuid_entries,
- int evmcs_enabled)
+ bool evmcs_enabled)
{
int i;
+ int nent = 9;
+ u32 test_val;
- if (!evmcs_enabled)
- TEST_ASSERT(hv_cpuid_entries->nent == 6,
- "KVM_GET_SUPPORTED_HV_CPUID should return 6 entries"
- " when Enlightened VMCS is disabled (returned %d)",
- hv_cpuid_entries->nent);
- else
- TEST_ASSERT(hv_cpuid_entries->nent == 7,
- "KVM_GET_SUPPORTED_HV_CPUID should return 7 entries"
- " when Enlightened VMCS is enabled (returned %d)",
- hv_cpuid_entries->nent);
+ if (evmcs_enabled)
+ nent += 1; /* 0x4000000A */
+
+ TEST_ASSERT(hv_cpuid_entries->nent == nent,
+ "KVM_GET_SUPPORTED_HV_CPUID should return %d entries"
+ " with evmcs=%d (returned %d)",
+ nent, evmcs_enabled, hv_cpuid_entries->nent);
for (i = 0; i < hv_cpuid_entries->nent; i++) {
struct kvm_cpuid_entry2 *entry = &hv_cpuid_entries->entries[i];
TEST_ASSERT((entry->function >= 0x40000000) &&
- (entry->function <= 0x4000000A),
- "function %lx is our of supported range",
+ (entry->function <= 0x40000082),
+ "function %x is our of supported range",
entry->function);
+ TEST_ASSERT(evmcs_enabled || (entry->function != 0x4000000A),
+ "0x4000000A leaf should not be reported");
+
TEST_ASSERT(entry->index == 0,
".index field should be zero");
@@ -78,12 +80,23 @@ static void test_hv_cpuid(struct kvm_cpuid2 *hv_cpuid_entries,
TEST_ASSERT(!entry->padding[0] && !entry->padding[1] &&
!entry->padding[2], "padding should be zero");
- if (entry->function == 0x40000004) {
- int nononarchcs = !!(entry->eax & (1UL << 18));
+ switch (entry->function) {
+ case 0x40000000:
+ test_val = 0x40000082;
- TEST_ASSERT(nononarchcs == !smt_possible(),
+ TEST_ASSERT(entry->eax == test_val,
+ "Wrong max leaf report in 0x40000000.EAX: %x"
+ " (evmcs=%d)",
+ entry->eax, evmcs_enabled
+ );
+ break;
+ case 0x40000004:
+ test_val = entry->eax & (1UL << 18);
+
+ TEST_ASSERT(!!test_val == !smt_possible(),
"NoNonArchitecturalCoreSharing bit"
" doesn't reflect SMT setting");
+ break;
}
/*
@@ -133,50 +146,44 @@ struct kvm_cpuid2 *kvm_get_supported_hv_cpuid(struct kvm_vm *vm)
int main(int argc, char *argv[])
{
struct kvm_vm *vm;
- int rv;
+ int rv, stage;
struct kvm_cpuid2 *hv_cpuid_entries;
+ bool evmcs_enabled;
/* Tell stdout not to buffer its content */
setbuf(stdout, NULL);
rv = kvm_check_cap(KVM_CAP_HYPERV_CPUID);
if (!rv) {
- fprintf(stderr,
- "KVM_CAP_HYPERV_CPUID not supported, skip test\n");
+ print_skip("KVM_CAP_HYPERV_CPUID not supported");
exit(KSFT_SKIP);
}
- /* Create VM */
- vm = vm_create_default(VCPU_ID, 0, guest_code);
-
- test_hv_cpuid_e2big(vm);
-
- hv_cpuid_entries = kvm_get_supported_hv_cpuid(vm);
- if (!hv_cpuid_entries)
- return 1;
-
- test_hv_cpuid(hv_cpuid_entries, 0);
-
- free(hv_cpuid_entries);
+ for (stage = 0; stage < 3; stage++) {
+ evmcs_enabled = false;
+
+ vm = vm_create_default(VCPU_ID, 0, guest_code);
+ switch (stage) {
+ case 0:
+ test_hv_cpuid_e2big(vm);
+ continue;
+ case 1:
+ break;
+ case 2:
+ if (!kvm_check_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS)) {
+ print_skip("Enlightened VMCS is unsupported");
+ continue;
+ }
+ vcpu_enable_evmcs(vm, VCPU_ID);
+ evmcs_enabled = true;
+ break;
+ }
- if (!kvm_check_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS)) {
- fprintf(stderr,
- "Enlightened VMCS is unsupported, skip related test\n");
- goto vm_free;
+ hv_cpuid_entries = kvm_get_supported_hv_cpuid(vm);
+ test_hv_cpuid(hv_cpuid_entries, evmcs_enabled);
+ free(hv_cpuid_entries);
+ kvm_vm_free(vm);
}
- vcpu_enable_evmcs(vm, VCPU_ID);
-
- hv_cpuid_entries = kvm_get_supported_hv_cpuid(vm);
- if (!hv_cpuid_entries)
- return 1;
-
- test_hv_cpuid(hv_cpuid_entries, 1);
-
- free(hv_cpuid_entries);
-
-vm_free:
- kvm_vm_free(vm);
-
return 0;
}
diff --git a/tools/testing/selftests/kvm/x86_64/mmio_warning_test.c b/tools/testing/selftests/kvm/x86_64/mmio_warning_test.c
index 00bb97d76000..e6480fd5c4bd 100644
--- a/tools/testing/selftests/kvm/x86_64/mmio_warning_test.c
+++ b/tools/testing/selftests/kvm/x86_64/mmio_warning_test.c
@@ -44,7 +44,7 @@ void *thr(void *arg)
struct kvm_run *run = tc->run;
res = ioctl(kvmcpu, KVM_RUN, 0);
- printf("ret1=%d exit_reason=%d suberror=%d\n",
+ pr_info("ret1=%d exit_reason=%d suberror=%d\n",
res, run->exit_reason, run->internal.suberror);
return 0;
@@ -93,12 +93,12 @@ int main(void)
int warnings_before, warnings_after;
if (!is_intel_cpu()) {
- printf("Must be run on an Intel CPU, skipping test\n");
+ print_skip("Must be run on an Intel CPU");
exit(KSFT_SKIP);
}
if (vm_is_unrestricted_guest(NULL)) {
- printf("Unrestricted guest must be disabled, skipping test\n");
+ print_skip("Unrestricted guest must be disabled");
exit(KSFT_SKIP);
}
diff --git a/tools/testing/selftests/kvm/x86_64/platform_info_test.c b/tools/testing/selftests/kvm/x86_64/platform_info_test.c
index f9334bd3cce9..1e89688cbbbf 100644
--- a/tools/testing/selftests/kvm/x86_64/platform_info_test.c
+++ b/tools/testing/selftests/kvm/x86_64/platform_info_test.c
@@ -58,8 +58,7 @@ static void test_msr_platform_info_enabled(struct kvm_vm *vm)
exit_reason_str(run->exit_reason));
get_ucall(vm, VCPU_ID, &uc);
TEST_ASSERT(uc.cmd == UCALL_SYNC,
- "Received ucall other than UCALL_SYNC: %u\n",
- ucall);
+ "Received ucall other than UCALL_SYNC: %lu\n", uc.cmd);
TEST_ASSERT((uc.args[1] & MSR_PLATFORM_INFO_MAX_TURBO_RATIO) ==
MSR_PLATFORM_INFO_MAX_TURBO_RATIO,
"Expected MSR_PLATFORM_INFO to have max turbo ratio mask: %i.",
@@ -89,8 +88,7 @@ int main(int argc, char *argv[])
rv = kvm_check_cap(KVM_CAP_MSR_PLATFORM_INFO);
if (!rv) {
- fprintf(stderr,
- "KVM_CAP_MSR_PLATFORM_INFO not supported, skip test\n");
+ print_skip("KVM_CAP_MSR_PLATFORM_INFO not supported");
exit(KSFT_SKIP);
}
diff --git a/tools/testing/selftests/kvm/x86_64/smm_test.c b/tools/testing/selftests/kvm/x86_64/smm_test.c
index 8c063646f2a0..6f8f478b3ceb 100644
--- a/tools/testing/selftests/kvm/x86_64/smm_test.c
+++ b/tools/testing/selftests/kvm/x86_64/smm_test.c
@@ -17,6 +17,7 @@
#include "kvm_util.h"
#include "vmx.h"
+#include "svm_util.h"
#define VCPU_ID 1
@@ -58,7 +59,7 @@ void self_smi(void)
APIC_DEST_SELF | APIC_INT_ASSERT | APIC_DM_SMI);
}
-void guest_code(struct vmx_pages *vmx_pages)
+void guest_code(void *arg)
{
uint64_t apicbase = rdmsr(MSR_IA32_APICBASE);
@@ -72,8 +73,11 @@ void guest_code(struct vmx_pages *vmx_pages)
sync_with_host(4);
- if (vmx_pages) {
- GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages));
+ if (arg) {
+ if (cpu_has_svm())
+ generic_svm_setup(arg, NULL, NULL);
+ else
+ GUEST_ASSERT(prepare_for_vmx_operation(arg));
sync_with_host(5);
@@ -87,7 +91,7 @@ void guest_code(struct vmx_pages *vmx_pages)
int main(int argc, char *argv[])
{
- vm_vaddr_t vmx_pages_gva = 0;
+ vm_vaddr_t nested_gva = 0;
struct kvm_regs regs;
struct kvm_vm *vm;
@@ -114,10 +118,13 @@ int main(int argc, char *argv[])
vcpu_set_msr(vm, VCPU_ID, MSR_IA32_SMBASE, SMRAM_GPA);
if (kvm_check_cap(KVM_CAP_NESTED_STATE)) {
- vcpu_alloc_vmx(vm, &vmx_pages_gva);
- vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva);
+ if (kvm_get_supported_cpuid_entry(0x80000001)->ecx & CPUID_SVM)
+ vcpu_alloc_svm(vm, &nested_gva);
+ else
+ vcpu_alloc_vmx(vm, &nested_gva);
+ vcpu_args_set(vm, VCPU_ID, 1, nested_gva);
} else {
- printf("will skip SMM test with VMX enabled\n");
+ pr_info("will skip SMM test with VMX enabled\n");
vcpu_args_set(vm, VCPU_ID, 1, 0);
}
diff --git a/tools/testing/selftests/kvm/x86_64/state_test.c b/tools/testing/selftests/kvm/x86_64/state_test.c
index 3ab5ec3da9f4..d43b6f99b66c 100644
--- a/tools/testing/selftests/kvm/x86_64/state_test.c
+++ b/tools/testing/selftests/kvm/x86_64/state_test.c
@@ -18,14 +18,46 @@
#include "kvm_util.h"
#include "processor.h"
#include "vmx.h"
+#include "svm_util.h"
#define VCPU_ID 5
+#define L2_GUEST_STACK_SIZE 256
-void l2_guest_code(void)
+void svm_l2_guest_code(void)
{
+ GUEST_SYNC(4);
+ /* Exit to L1 */
+ vmcall();
GUEST_SYNC(6);
+ /* Done, exit to L1 and never come back. */
+ vmcall();
+}
- /* Exit to L1 */
+static void svm_l1_guest_code(struct svm_test_data *svm)
+{
+ unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
+ struct vmcb *vmcb = svm->vmcb;
+
+ GUEST_ASSERT(svm->vmcb_gpa);
+ /* Prepare for L2 execution. */
+ generic_svm_setup(svm, svm_l2_guest_code,
+ &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+
+ GUEST_SYNC(3);
+ run_guest(vmcb, svm->vmcb_gpa);
+ GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_VMMCALL);
+ GUEST_SYNC(5);
+ vmcb->save.rip += 3;
+ run_guest(vmcb, svm->vmcb_gpa);
+ GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_VMMCALL);
+ GUEST_SYNC(7);
+}
+
+void vmx_l2_guest_code(void)
+{
+ GUEST_SYNC(6);
+
+ /* Exit to L1 */
vmcall();
/* L1 has now set up a shadow VMCS for us. */
@@ -42,10 +74,9 @@ void l2_guest_code(void)
vmcall();
}
-void l1_guest_code(struct vmx_pages *vmx_pages)
+static void vmx_l1_guest_code(struct vmx_pages *vmx_pages)
{
-#define L2_GUEST_STACK_SIZE 64
- unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
+ unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
GUEST_ASSERT(vmx_pages->vmcs_gpa);
GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages));
@@ -56,7 +87,7 @@ void l1_guest_code(struct vmx_pages *vmx_pages)
GUEST_SYNC(4);
GUEST_ASSERT(vmptrstz() == vmx_pages->vmcs_gpa);
- prepare_vmcs(vmx_pages, l2_guest_code,
+ prepare_vmcs(vmx_pages, vmx_l2_guest_code,
&l2_guest_stack[L2_GUEST_STACK_SIZE]);
GUEST_SYNC(5);
@@ -106,20 +137,24 @@ void l1_guest_code(struct vmx_pages *vmx_pages)
GUEST_ASSERT(vmresume());
}
-void guest_code(struct vmx_pages *vmx_pages)
+static void __attribute__((__flatten__)) guest_code(void *arg)
{
GUEST_SYNC(1);
GUEST_SYNC(2);
- if (vmx_pages)
- l1_guest_code(vmx_pages);
+ if (arg) {
+ if (cpu_has_svm())
+ svm_l1_guest_code(arg);
+ else
+ vmx_l1_guest_code(arg);
+ }
GUEST_DONE();
}
int main(int argc, char *argv[])
{
- vm_vaddr_t vmx_pages_gva = 0;
+ vm_vaddr_t nested_gva = 0;
struct kvm_regs regs1, regs2;
struct kvm_vm *vm;
@@ -136,10 +171,13 @@ int main(int argc, char *argv[])
vcpu_regs_get(vm, VCPU_ID, &regs1);
if (kvm_check_cap(KVM_CAP_NESTED_STATE)) {
- vcpu_alloc_vmx(vm, &vmx_pages_gva);
- vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva);
+ if (kvm_get_supported_cpuid_entry(0x80000001)->ecx & CPUID_SVM)
+ vcpu_alloc_svm(vm, &nested_gva);
+ else
+ vcpu_alloc_vmx(vm, &nested_gva);
+ vcpu_args_set(vm, VCPU_ID, 1, nested_gva);
} else {
- printf("will skip nested state checks\n");
+ pr_info("will skip nested state checks\n");
vcpu_args_set(vm, VCPU_ID, 1, 0);
}
@@ -152,20 +190,20 @@ int main(int argc, char *argv[])
switch (get_ucall(vm, VCPU_ID, &uc)) {
case UCALL_ABORT:
- TEST_ASSERT(false, "%s at %s:%d", (const char *)uc.args[0],
- __FILE__, uc.args[1]);
+ TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0],
+ __FILE__, uc.args[1]);
/* NOT REACHED */
case UCALL_SYNC:
break;
case UCALL_DONE:
goto done;
default:
- TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd);
+ TEST_FAIL("Unknown ucall %lu", uc.cmd);
}
/* UCALL_SYNC is handled here. */
TEST_ASSERT(!strcmp((const char *)uc.args[0], "hello") &&
- uc.args[1] == stage, "Unexpected register values vmexit #%lx, got %lx",
+ uc.args[1] == stage, "Stage %d: Unexpected register values vmexit, got %lx",
stage, (ulong)uc.args[1]);
state = vcpu_save_state(vm, VCPU_ID);
diff --git a/tools/testing/selftests/kvm/x86_64/svm_vmcall_test.c b/tools/testing/selftests/kvm/x86_64/svm_vmcall_test.c
index e280f68f6365..0e1adb4e3199 100644
--- a/tools/testing/selftests/kvm/x86_64/svm_vmcall_test.c
+++ b/tools/testing/selftests/kvm/x86_64/svm_vmcall_test.c
@@ -61,16 +61,14 @@ int main(int argc, char *argv[])
switch (get_ucall(vm, VCPU_ID, &uc)) {
case UCALL_ABORT:
- TEST_ASSERT(false, "%s",
- (const char *)uc.args[0]);
+ TEST_FAIL("%s", (const char *)uc.args[0]);
/* NOT REACHED */
case UCALL_SYNC:
break;
case UCALL_DONE:
goto done;
default:
- TEST_ASSERT(false,
- "Unknown ucall 0x%x.", uc.cmd);
+ TEST_FAIL("Unknown ucall 0x%lx.", uc.cmd);
}
}
done:
diff --git a/tools/testing/selftests/kvm/x86_64/sync_regs_test.c b/tools/testing/selftests/kvm/x86_64/sync_regs_test.c
index 5c8224256294..d672f0a473f8 100644
--- a/tools/testing/selftests/kvm/x86_64/sync_regs_test.c
+++ b/tools/testing/selftests/kvm/x86_64/sync_regs_test.c
@@ -91,11 +91,11 @@ int main(int argc, char *argv[])
cap = kvm_check_cap(KVM_CAP_SYNC_REGS);
if ((cap & TEST_SYNC_FIELDS) != TEST_SYNC_FIELDS) {
- fprintf(stderr, "KVM_CAP_SYNC_REGS not supported, skipping test\n");
+ print_skip("KVM_CAP_SYNC_REGS not supported");
exit(KSFT_SKIP);
}
if ((cap & INVALID_SYNC_FIELD) != 0) {
- fprintf(stderr, "The \"invalid\" field is not invalid, skipping test\n");
+ print_skip("The \"invalid\" field is not invalid");
exit(KSFT_SKIP);
}
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c b/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c
index 5dfb53546a26..fe40ade06a49 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c
@@ -78,10 +78,10 @@ int main(int argc, char *argv[])
switch (get_ucall(vm, VCPU_ID, &uc)) {
case UCALL_ABORT:
- TEST_ASSERT(false, "%s", (const char *)uc.args[0]);
+ TEST_FAIL("%s", (const char *)uc.args[0]);
/* NOT REACHED */
default:
- TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd);
+ TEST_FAIL("Unknown ucall %lu", uc.cmd);
}
}
}
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c b/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c
index a223a6401258..e894a638a155 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c
@@ -21,7 +21,7 @@
/* The memory slot index to track dirty pages */
#define TEST_MEM_SLOT_INDEX 1
-#define TEST_MEM_SIZE 3
+#define TEST_MEM_PAGES 3
/* L1 guest test virtual memory offset */
#define GUEST_TEST_MEM 0xc0000000
@@ -91,15 +91,14 @@ int main(int argc, char *argv[])
vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
GUEST_TEST_MEM,
TEST_MEM_SLOT_INDEX,
- TEST_MEM_SIZE,
+ TEST_MEM_PAGES,
KVM_MEM_LOG_DIRTY_PAGES);
/*
* Add an identity map for GVA range [0xc0000000, 0xc0002000). This
* affects both L1 and L2. However...
*/
- virt_map(vm, GUEST_TEST_MEM, GUEST_TEST_MEM,
- TEST_MEM_SIZE * 4096, 0);
+ virt_map(vm, GUEST_TEST_MEM, GUEST_TEST_MEM, TEST_MEM_PAGES, 0);
/*
* ... pages in the L2 GPA range [0xc0001000, 0xc0003000) will map to
@@ -113,11 +112,11 @@ int main(int argc, char *argv[])
nested_map(vmx, vm, NESTED_TEST_MEM1, GUEST_TEST_MEM, 4096, 0);
nested_map(vmx, vm, NESTED_TEST_MEM2, GUEST_TEST_MEM, 4096, 0);
- bmap = bitmap_alloc(TEST_MEM_SIZE);
+ bmap = bitmap_alloc(TEST_MEM_PAGES);
host_test_mem = addr_gpa2hva(vm, GUEST_TEST_MEM);
while (!done) {
- memset(host_test_mem, 0xaa, TEST_MEM_SIZE * 4096);
+ memset(host_test_mem, 0xaa, TEST_MEM_PAGES * 4096);
_vcpu_run(vm, VCPU_ID);
TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
"Unexpected exit reason: %u (%s),\n",
@@ -126,8 +125,8 @@ int main(int argc, char *argv[])
switch (get_ucall(vm, VCPU_ID, &uc)) {
case UCALL_ABORT:
- TEST_ASSERT(false, "%s at %s:%d", (const char *)uc.args[0],
- __FILE__, uc.args[1]);
+ TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0],
+ __FILE__, uc.args[1]);
/* NOT REACHED */
case UCALL_SYNC:
/*
@@ -152,7 +151,7 @@ int main(int argc, char *argv[])
done = true;
break;
default:
- TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd);
+ TEST_FAIL("Unknown ucall %lu", uc.cmd);
}
}
}
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_preemption_timer_test.c b/tools/testing/selftests/kvm/x86_64/vmx_preemption_timer_test.c
new file mode 100644
index 000000000000..cc72b6188ca7
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/vmx_preemption_timer_test.c
@@ -0,0 +1,255 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * VMX-preemption timer test
+ *
+ * Copyright (C) 2020, Google, LLC.
+ *
+ * Test to ensure the VM-Enter after migration doesn't
+ * incorrectly restarts the timer with the full timer
+ * value instead of partially decayed timer value
+ *
+ */
+#define _GNU_SOURCE /* for program_invocation_short_name */
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+
+#include "test_util.h"
+
+#include "kvm_util.h"
+#include "processor.h"
+#include "vmx.h"
+
+#define VCPU_ID 5
+#define PREEMPTION_TIMER_VALUE 100000000ull
+#define PREEMPTION_TIMER_VALUE_THRESHOLD1 80000000ull
+
+u32 vmx_pt_rate;
+bool l2_save_restore_done;
+static u64 l2_vmx_pt_start;
+volatile u64 l2_vmx_pt_finish;
+
+void l2_guest_code(void)
+{
+ u64 vmx_pt_delta;
+
+ vmcall();
+ l2_vmx_pt_start = (rdtsc() >> vmx_pt_rate) << vmx_pt_rate;
+
+ /*
+ * Wait until the 1st threshold has passed
+ */
+ do {
+ l2_vmx_pt_finish = rdtsc();
+ vmx_pt_delta = (l2_vmx_pt_finish - l2_vmx_pt_start) >>
+ vmx_pt_rate;
+ } while (vmx_pt_delta < PREEMPTION_TIMER_VALUE_THRESHOLD1);
+
+ /*
+ * Force L2 through Save and Restore cycle
+ */
+ GUEST_SYNC(1);
+
+ l2_save_restore_done = 1;
+
+ /*
+ * Now wait for the preemption timer to fire and
+ * exit to L1
+ */
+ while ((l2_vmx_pt_finish = rdtsc()))
+ ;
+}
+
+void l1_guest_code(struct vmx_pages *vmx_pages)
+{
+#define L2_GUEST_STACK_SIZE 64
+ unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
+ u64 l1_vmx_pt_start;
+ u64 l1_vmx_pt_finish;
+ u64 l1_tsc_deadline, l2_tsc_deadline;
+
+ GUEST_ASSERT(vmx_pages->vmcs_gpa);
+ GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages));
+ GUEST_ASSERT(load_vmcs(vmx_pages));
+ GUEST_ASSERT(vmptrstz() == vmx_pages->vmcs_gpa);
+
+ prepare_vmcs(vmx_pages, l2_guest_code,
+ &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+
+ /*
+ * Check for Preemption timer support
+ */
+ basic.val = rdmsr(MSR_IA32_VMX_BASIC);
+ ctrl_pin_rev.val = rdmsr(basic.ctrl ? MSR_IA32_VMX_TRUE_PINBASED_CTLS
+ : MSR_IA32_VMX_PINBASED_CTLS);
+ ctrl_exit_rev.val = rdmsr(basic.ctrl ? MSR_IA32_VMX_TRUE_EXIT_CTLS
+ : MSR_IA32_VMX_EXIT_CTLS);
+
+ if (!(ctrl_pin_rev.clr & PIN_BASED_VMX_PREEMPTION_TIMER) ||
+ !(ctrl_exit_rev.clr & VM_EXIT_SAVE_VMX_PREEMPTION_TIMER))
+ return;
+
+ GUEST_ASSERT(!vmlaunch());
+ GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
+ vmwrite(GUEST_RIP, vmreadz(GUEST_RIP) + vmreadz(VM_EXIT_INSTRUCTION_LEN));
+
+ /*
+ * Turn on PIN control and resume the guest
+ */
+ GUEST_ASSERT(!vmwrite(PIN_BASED_VM_EXEC_CONTROL,
+ vmreadz(PIN_BASED_VM_EXEC_CONTROL) |
+ PIN_BASED_VMX_PREEMPTION_TIMER));
+
+ GUEST_ASSERT(!vmwrite(VMX_PREEMPTION_TIMER_VALUE,
+ PREEMPTION_TIMER_VALUE));
+
+ vmx_pt_rate = rdmsr(MSR_IA32_VMX_MISC) & 0x1F;
+
+ l2_save_restore_done = 0;
+
+ l1_vmx_pt_start = (rdtsc() >> vmx_pt_rate) << vmx_pt_rate;
+
+ GUEST_ASSERT(!vmresume());
+
+ l1_vmx_pt_finish = rdtsc();
+
+ /*
+ * Ensure exit from L2 happens after L2 goes through
+ * save and restore
+ */
+ GUEST_ASSERT(l2_save_restore_done);
+
+ /*
+ * Ensure the exit from L2 is due to preemption timer expiry
+ */
+ GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_PREEMPTION_TIMER);
+
+ l1_tsc_deadline = l1_vmx_pt_start +
+ (PREEMPTION_TIMER_VALUE << vmx_pt_rate);
+
+ l2_tsc_deadline = l2_vmx_pt_start +
+ (PREEMPTION_TIMER_VALUE << vmx_pt_rate);
+
+ /*
+ * Sync with the host and pass the l1|l2 pt_expiry_finish times and
+ * tsc deadlines so that host can verify they are as expected
+ */
+ GUEST_SYNC_ARGS(2, l1_vmx_pt_finish, l1_tsc_deadline,
+ l2_vmx_pt_finish, l2_tsc_deadline);
+}
+
+void guest_code(struct vmx_pages *vmx_pages)
+{
+ if (vmx_pages)
+ l1_guest_code(vmx_pages);
+
+ GUEST_DONE();
+}
+
+int main(int argc, char *argv[])
+{
+ vm_vaddr_t vmx_pages_gva = 0;
+
+ struct kvm_regs regs1, regs2;
+ struct kvm_vm *vm;
+ struct kvm_run *run;
+ struct kvm_x86_state *state;
+ struct ucall uc;
+ int stage;
+
+ /*
+ * AMD currently does not implement any VMX features, so for now we
+ * just early out.
+ */
+ nested_vmx_check_supported();
+
+ /* Create VM */
+ vm = vm_create_default(VCPU_ID, 0, guest_code);
+ vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
+ run = vcpu_state(vm, VCPU_ID);
+
+ vcpu_regs_get(vm, VCPU_ID, &regs1);
+
+ if (kvm_check_cap(KVM_CAP_NESTED_STATE)) {
+ vcpu_alloc_vmx(vm, &vmx_pages_gva);
+ vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva);
+ } else {
+ pr_info("will skip vmx preemption timer checks\n");
+ goto done;
+ }
+
+ for (stage = 1;; stage++) {
+ _vcpu_run(vm, VCPU_ID);
+ TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+ "Stage %d: unexpected exit reason: %u (%s),\n",
+ stage, run->exit_reason,
+ exit_reason_str(run->exit_reason));
+
+ switch (get_ucall(vm, VCPU_ID, &uc)) {
+ case UCALL_ABORT:
+ TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0],
+ __FILE__, uc.args[1]);
+ /* NOT REACHED */
+ case UCALL_SYNC:
+ break;
+ case UCALL_DONE:
+ goto done;
+ default:
+ TEST_FAIL("Unknown ucall %lu", uc.cmd);
+ }
+
+ /* UCALL_SYNC is handled here. */
+ TEST_ASSERT(!strcmp((const char *)uc.args[0], "hello") &&
+ uc.args[1] == stage, "Stage %d: Unexpected register values vmexit, got %lx",
+ stage, (ulong)uc.args[1]);
+ /*
+ * If this stage 2 then we should verify the vmx pt expiry
+ * is as expected.
+ * From L1's perspective verify Preemption timer hasn't
+ * expired too early.
+ * From L2's perspective verify Preemption timer hasn't
+ * expired too late.
+ */
+ if (stage == 2) {
+
+ pr_info("Stage %d: L1 PT expiry TSC (%lu) , L1 TSC deadline (%lu)\n",
+ stage, uc.args[2], uc.args[3]);
+
+ pr_info("Stage %d: L2 PT expiry TSC (%lu) , L2 TSC deadline (%lu)\n",
+ stage, uc.args[4], uc.args[5]);
+
+ TEST_ASSERT(uc.args[2] >= uc.args[3],
+ "Stage %d: L1 PT expiry TSC (%lu) < L1 TSC deadline (%lu)",
+ stage, uc.args[2], uc.args[3]);
+
+ TEST_ASSERT(uc.args[4] < uc.args[5],
+ "Stage %d: L2 PT expiry TSC (%lu) > L2 TSC deadline (%lu)",
+ stage, uc.args[4], uc.args[5]);
+ }
+
+ state = vcpu_save_state(vm, VCPU_ID);
+ memset(&regs1, 0, sizeof(regs1));
+ vcpu_regs_get(vm, VCPU_ID, &regs1);
+
+ kvm_vm_release(vm);
+
+ /* Restore state in a new VM. */
+ kvm_vm_restart(vm, O_RDWR);
+ vm_vcpu_add(vm, VCPU_ID);
+ vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
+ vcpu_load_state(vm, VCPU_ID, state);
+ run = vcpu_state(vm, VCPU_ID);
+ free(state);
+
+ memset(&regs2, 0, sizeof(regs2));
+ vcpu_regs_get(vm, VCPU_ID, &regs2);
+ TEST_ASSERT(!memcmp(&regs1, &regs2, sizeof(regs2)),
+ "Unexpected register values after vcpu_load_state; rdi: %lx rsi: %lx",
+ (ulong) regs2.rdi, (ulong) regs2.rsi);
+ }
+
+done:
+ kvm_vm_free(vm);
+}
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c b/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c
index 9ef7fab39d48..54cdefdfb49d 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c
@@ -212,7 +212,7 @@ void test_vmx_nested_state(struct kvm_vm *vm)
test_nested_state(vm, state);
vcpu_nested_state_get(vm, VCPU_ID, state);
TEST_ASSERT(state->size >= sizeof(*state) && state->size <= state_sz,
- "Size must be between %d and %d. The size returned was %d.",
+ "Size must be between %ld and %d. The size returned was %d.",
sizeof(*state), state_sz, state->size);
TEST_ASSERT(state->hdr.vmx.vmxon_pa == -1ull, "vmxon_pa must be -1ull.");
TEST_ASSERT(state->hdr.vmx.vmcs12_pa == -1ull, "vmcs_pa must be -1ull.");
@@ -228,7 +228,7 @@ int main(int argc, char *argv[])
have_evmcs = kvm_check_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS);
if (!kvm_check_cap(KVM_CAP_NESTED_STATE)) {
- printf("KVM_CAP_NESTED_STATE not available, skipping test\n");
+ print_skip("KVM_CAP_NESTED_STATE not available");
exit(KSFT_SKIP);
}
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c
index 69e482a95c47..fbe8417cbc2c 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c
@@ -121,8 +121,8 @@ static void l1_guest_code(struct vmx_pages *vmx_pages)
static void report(int64_t val)
{
- printf("IA32_TSC_ADJUST is %ld (%lld * TSC_ADJUST_VALUE + %lld).\n",
- val, val / TSC_ADJUST_VALUE, val % TSC_ADJUST_VALUE);
+ pr_info("IA32_TSC_ADJUST is %ld (%lld * TSC_ADJUST_VALUE + %lld).\n",
+ val, val / TSC_ADJUST_VALUE, val % TSC_ADJUST_VALUE);
}
int main(int argc, char *argv[])
@@ -150,7 +150,7 @@ int main(int argc, char *argv[])
switch (get_ucall(vm, VCPU_ID, &uc)) {
case UCALL_ABORT:
- TEST_ASSERT(false, "%s", (const char *)uc.args[0]);
+ TEST_FAIL("%s", (const char *)uc.args[0]);
/* NOT REACHED */
case UCALL_SYNC:
report(uc.args[1]);
@@ -158,7 +158,7 @@ int main(int argc, char *argv[])
case UCALL_DONE:
goto done;
default:
- TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd);
+ TEST_FAIL("Unknown ucall %lu", uc.cmd);
}
}
diff --git a/tools/testing/selftests/kvm/x86_64/xss_msr_test.c b/tools/testing/selftests/kvm/x86_64/xss_msr_test.c
index 851ea81b9d9f..3529376747c2 100644
--- a/tools/testing/selftests/kvm/x86_64/xss_msr_test.c
+++ b/tools/testing/selftests/kvm/x86_64/xss_msr_test.c
@@ -51,7 +51,7 @@ int main(int argc, char *argv[])
xss_supported = entry && !!(entry->eax & X86_FEATURE_XSAVES);
}
if (!xss_supported) {
- printf("IA32_XSS is not supported by the vCPU.\n");
+ print_skip("IA32_XSS is not supported by the vCPU");
exit(KSFT_SKIP);
}
diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk
index 3ed0134a764d..b0556c752443 100644
--- a/tools/testing/selftests/lib.mk
+++ b/tools/testing/selftests/lib.mk
@@ -137,7 +137,8 @@ endif
# Selftest makefiles can override those targets by setting
# OVERRIDE_TARGETS = 1.
ifeq ($(OVERRIDE_TARGETS),)
-$(OUTPUT)/%:%.c
+LOCAL_HDRS := $(selfdir)/kselftest_harness.h $(selfdir)/kselftest.h
+$(OUTPUT)/%:%.c $(LOCAL_HDRS)
$(LINK.c) $^ $(LDLIBS) -o $@
$(OUTPUT)/%.o:%.S
diff --git a/tools/testing/selftests/lib/config b/tools/testing/selftests/lib/config
index 14a77ea4a8da..b80ee3f6e265 100644
--- a/tools/testing/selftests/lib/config
+++ b/tools/testing/selftests/lib/config
@@ -2,3 +2,4 @@ CONFIG_TEST_PRINTF=m
CONFIG_TEST_BITMAP=m
CONFIG_PRIME_NUMBERS=m
CONFIG_TEST_STRSCPY=m
+CONFIG_TEST_BITOPS=m
diff --git a/tools/testing/selftests/lkdtm/run.sh b/tools/testing/selftests/lkdtm/run.sh
index dadf819148a4..ee64ff8df8f4 100755
--- a/tools/testing/selftests/lkdtm/run.sh
+++ b/tools/testing/selftests/lkdtm/run.sh
@@ -25,13 +25,13 @@ fi
# Figure out which test to run from our script name.
test=$(basename $0 .sh)
# Look up details about the test from master list of LKDTM tests.
-line=$(egrep '^#?'"$test"'\b' tests.txt)
+line=$(grep -E '^#?'"$test"'\b' tests.txt)
if [ -z "$line" ]; then
echo "Skipped: missing test '$test' in tests.txt"
exit $KSELFTEST_SKIP_TEST
fi
# Check that the test is known to LKDTM.
-if ! egrep -q '^'"$test"'$' "$TRIGGER" ; then
+if ! grep -E -q '^'"$test"'$' "$TRIGGER" ; then
echo "Skipped: test '$test' missing in $TRIGGER!"
exit $KSELFTEST_SKIP_TEST
fi
@@ -59,30 +59,32 @@ if [ -z "$expect" ]; then
expect="call trace:"
fi
-# Clear out dmesg for output reporting
-dmesg -c >/dev/null
-
# Prepare log for report checking
-LOG=$(mktemp --tmpdir -t lkdtm-XXXXXX)
+LOG=$(mktemp --tmpdir -t lkdtm-log-XXXXXX)
+DMESG=$(mktemp --tmpdir -t lkdtm-dmesg-XXXXXX)
cleanup() {
- rm -f "$LOG"
+ rm -f "$LOG" "$DMESG"
}
trap cleanup EXIT
+# Save existing dmesg so we can detect new content below
+dmesg > "$DMESG"
+
# Most shells yell about signals and we're expecting the "cat" process
# to usually be killed by the kernel. So we have to run it in a sub-shell
# and silence errors.
($SHELL -c 'cat <(echo '"$test"') >'"$TRIGGER" 2>/dev/null) || true
# Record and dump the results
-dmesg -c >"$LOG"
+dmesg | diff --changed-group-format='%>' --unchanged-group-format='' "$DMESG" - > "$LOG" || true
+
cat "$LOG"
# Check for expected output
-if egrep -qi "$expect" "$LOG" ; then
+if grep -E -qi "$expect" "$LOG" ; then
echo "$test: saw '$expect': ok"
exit 0
else
- if egrep -qi XFAIL: "$LOG" ; then
+ if grep -E -qi XFAIL: "$LOG" ; then
echo "$test: saw 'XFAIL': [SKIP]"
exit $KSELFTEST_SKIP_TEST
else
diff --git a/tools/testing/selftests/media_tests/.gitignore b/tools/testing/selftests/media_tests/.gitignore
index 8745eba39012..da438e780ffe 100644
--- a/tools/testing/selftests/media_tests/.gitignore
+++ b/tools/testing/selftests/media_tests/.gitignore
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
media_device_test
media_device_open
video_device_test
diff --git a/tools/testing/selftests/membarrier/.gitignore b/tools/testing/selftests/membarrier/.gitignore
index f2f7ec0a99b4..f2fbba178601 100644
--- a/tools/testing/selftests/membarrier/.gitignore
+++ b/tools/testing/selftests/membarrier/.gitignore
@@ -1,2 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0-only
membarrier_test_multi_thread
membarrier_test_single_thread
diff --git a/tools/testing/selftests/memfd/.gitignore b/tools/testing/selftests/memfd/.gitignore
index afe87c40ac80..dd9a051f608e 100644
--- a/tools/testing/selftests/memfd/.gitignore
+++ b/tools/testing/selftests/memfd/.gitignore
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
fuse_mnt
fuse_test
memfd_test
diff --git a/tools/testing/selftests/memfd/Makefile b/tools/testing/selftests/memfd/Makefile
index 53a848109f7b..4da8b565fa32 100644
--- a/tools/testing/selftests/memfd/Makefile
+++ b/tools/testing/selftests/memfd/Makefile
@@ -6,15 +6,25 @@ CFLAGS += -I../../../../usr/include/
TEST_GEN_PROGS := memfd_test
TEST_PROGS := run_fuse_test.sh run_hugetlbfs_test.sh
-TEST_GEN_FILES := fuse_mnt fuse_test
+TEST_GEN_FILES := fuse_test fuse_mnt
-fuse_mnt.o: CFLAGS += $(shell pkg-config fuse --cflags)
+VAR_CFLAGS := $(shell pkg-config fuse --cflags 2>/dev/null)
+ifeq ($(VAR_CFLAGS),)
+VAR_CFLAGS := -D_FILE_OFFSET_BITS=64 -I/usr/include/fuse
+endif
+
+VAR_LDLIBS := $(shell pkg-config fuse --libs 2>/dev/null)
+ifeq ($(VAR_LDLIBS),)
+VAR_LDLIBS := -lfuse -pthread
+endif
+
+fuse_mnt.o: CFLAGS += $(VAR_CFLAGS)
include ../lib.mk
-$(OUTPUT)/fuse_mnt: LDLIBS += $(shell pkg-config fuse --libs)
+$(OUTPUT)/fuse_mnt: LDLIBS += $(VAR_LDLIBS)
-$(OUTPUT)/memfd_test: memfd_test.c common.o
-$(OUTPUT)/fuse_test: fuse_test.c common.o
+$(OUTPUT)/memfd_test: memfd_test.c common.c
+$(OUTPUT)/fuse_test: fuse_test.c common.c
-EXTRA_CLEAN = common.o
+EXTRA_CLEAN = $(OUTPUT)/common.o
diff --git a/tools/testing/selftests/mount/.gitignore b/tools/testing/selftests/mount/.gitignore
index 856ad4107eb3..0bc64a6d4c18 100644
--- a/tools/testing/selftests/mount/.gitignore
+++ b/tools/testing/selftests/mount/.gitignore
@@ -1 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
unprivileged-remount-test
diff --git a/tools/testing/selftests/mqueue/.gitignore b/tools/testing/selftests/mqueue/.gitignore
index d8d42377205a..72ad8ca691c9 100644
--- a/tools/testing/selftests/mqueue/.gitignore
+++ b/tools/testing/selftests/mqueue/.gitignore
@@ -1,2 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0-only
mq_open_tests
mq_perf_tests
diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore
index ecc52d4c034d..742c499328b2 100644
--- a/tools/testing/selftests/net/.gitignore
+++ b/tools/testing/selftests/net/.gitignore
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
msg_zerocopy
socket
psock_fanout
@@ -23,3 +24,8 @@ so_txtime
tcp_fastopen_backup_key
nettest
fin_ack_lat
+reuseaddr_ports_exhausted
+hwtstamp_config
+rxtimestamp
+timestamping
+txtimestamp
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 4c1bd03ffa1c..895ec992b2f1 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -14,6 +14,9 @@ TEST_PROGS += tcp_fastopen_backup_key.sh fcnal-test.sh l2tp.sh traceroute.sh
TEST_PROGS += fin_ack_lat.sh fib_nexthop_multiprefix.sh fib_nexthops.sh
TEST_PROGS += altnames.sh icmp_redirect.sh ip6_gre_headroom.sh
TEST_PROGS += route_localnet.sh
+TEST_PROGS += reuseaddr_ports_exhausted.sh
+TEST_PROGS += txtimestamp.sh
+TEST_PROGS += vrf-xfrm-tests.sh
TEST_PROGS_EXTENDED := in_netns.sh
TEST_GEN_FILES = socket nettest
TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy reuseport_addr_any
@@ -22,6 +25,8 @@ TEST_GEN_FILES += udpgso udpgso_bench_tx udpgso_bench_rx ip_defrag
TEST_GEN_FILES += so_txtime ipv6_flowlabel ipv6_flowlabel_mgr
TEST_GEN_FILES += tcp_fastopen_backup_key
TEST_GEN_FILES += fin_ack_lat
+TEST_GEN_FILES += reuseaddr_ports_exhausted
+TEST_GEN_FILES += hwtstamp_config rxtimestamp timestamping txtimestamp
TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa
TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict tls
diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config
index b8503a8119b0..3b42c06b5985 100644
--- a/tools/testing/selftests/net/config
+++ b/tools/testing/selftests/net/config
@@ -12,6 +12,7 @@ CONFIG_IPV6_VTI=y
CONFIG_DUMMY=y
CONFIG_BRIDGE=y
CONFIG_VLAN_8021Q=y
+CONFIG_IFB=y
CONFIG_NETFILTER=y
CONFIG_NETFILTER_ADVANCED=y
CONFIG_NF_CONNTRACK=m
@@ -27,5 +28,6 @@ CONFIG_NFT_CHAIN_NAT_IPV6=m
CONFIG_NFT_CHAIN_NAT_IPV4=m
CONFIG_NET_SCH_FQ=m
CONFIG_NET_SCH_ETF=m
+CONFIG_NET_SCH_NETEM=y
CONFIG_TEST_BLACKHOLE_DEV=m
CONFIG_KALLSYMS=y
diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh
index 796670ebc65b..dee567f7576a 100755
--- a/tools/testing/selftests/net/fib_nexthops.sh
+++ b/tools/testing/selftests/net/fib_nexthops.sh
@@ -19,8 +19,8 @@ ret=0
ksft_skip=4
# all tests in this script. Can be overridden with -t option
-IPV4_TESTS="ipv4_fcnal ipv4_grp_fcnal ipv4_withv6_fcnal ipv4_fcnal_runtime"
-IPV6_TESTS="ipv6_fcnal ipv6_grp_fcnal ipv6_fcnal_runtime"
+IPV4_TESTS="ipv4_fcnal ipv4_grp_fcnal ipv4_withv6_fcnal ipv4_fcnal_runtime ipv4_large_grp ipv4_compat_mode ipv4_fdb_grp_fcnal ipv4_torture"
+IPV6_TESTS="ipv6_fcnal ipv6_grp_fcnal ipv6_fcnal_runtime ipv6_large_grp ipv6_compat_mode ipv6_fdb_grp_fcnal ipv6_torture"
ALL_TESTS="basic ${IPV4_TESTS} ${IPV6_TESTS}"
TESTS="${ALL_TESTS}"
@@ -146,35 +146,36 @@ setup()
create_ns remote
IP="ip -netns me"
+ BRIDGE="bridge -netns me"
set -e
$IP li add veth1 type veth peer name veth2
$IP li set veth1 up
$IP addr add 172.16.1.1/24 dev veth1
- $IP -6 addr add 2001:db8:91::1/64 dev veth1
+ $IP -6 addr add 2001:db8:91::1/64 dev veth1 nodad
$IP li add veth3 type veth peer name veth4
$IP li set veth3 up
$IP addr add 172.16.2.1/24 dev veth3
- $IP -6 addr add 2001:db8:92::1/64 dev veth3
+ $IP -6 addr add 2001:db8:92::1/64 dev veth3 nodad
$IP li set veth2 netns peer up
ip -netns peer addr add 172.16.1.2/24 dev veth2
- ip -netns peer -6 addr add 2001:db8:91::2/64 dev veth2
+ ip -netns peer -6 addr add 2001:db8:91::2/64 dev veth2 nodad
$IP li set veth4 netns peer up
ip -netns peer addr add 172.16.2.2/24 dev veth4
- ip -netns peer -6 addr add 2001:db8:92::2/64 dev veth4
+ ip -netns peer -6 addr add 2001:db8:92::2/64 dev veth4 nodad
ip -netns remote li add veth5 type veth peer name veth6
ip -netns remote li set veth5 up
ip -netns remote addr add dev veth5 172.16.101.1/24
- ip -netns remote addr add dev veth5 2001:db8:101::1/64
+ ip -netns remote -6 addr add dev veth5 2001:db8:101::1/64 nodad
ip -netns remote ro add 172.16.0.0/22 via 172.16.101.2
ip -netns remote -6 ro add 2001:db8:90::/40 via 2001:db8:101::2
ip -netns remote li set veth6 netns peer up
ip -netns peer addr add dev veth6 172.16.101.2/24
- ip -netns peer addr add dev veth6 2001:db8:101::2/64
+ ip -netns peer -6 addr add dev veth6 2001:db8:101::2/64 nodad
set +e
}
@@ -248,11 +249,247 @@ check_route6()
local expected="$2"
local out
- out=$($IP -6 route ls match ${pfx} 2>/dev/null)
+ out=$($IP -6 route ls match ${pfx} 2>/dev/null | sed -e 's/pref medium//')
check_output "${out}" "${expected}"
}
+check_large_grp()
+{
+ local ipv=$1
+ local ecmp=$2
+ local grpnum=100
+ local nhidstart=100
+ local grpidstart=1000
+ local iter=0
+ local nhidstr=""
+ local grpidstr=""
+ local grpstr=""
+ local ipstr=""
+
+ if [ $ipv -eq 4 ]; then
+ ipstr="172.16.1."
+ else
+ ipstr="2001:db8:91::"
+ fi
+
+ #
+ # Create $grpnum groups with specified $ecmp and dump them
+ #
+
+ # create nexthops with different gateways
+ iter=2
+ while [ $iter -le $(($ecmp + 1)) ]
+ do
+ nhidstr="$(($nhidstart + $iter))"
+ run_cmd "$IP nexthop add id $nhidstr via $ipstr$iter dev veth1"
+ check_nexthop "id $nhidstr" "id $nhidstr via $ipstr$iter dev veth1 scope link"
+
+ if [ $iter -le $ecmp ]; then
+ grpstr+="$nhidstr/"
+ else
+ grpstr+="$nhidstr"
+ fi
+ ((iter++))
+ done
+
+ # create duplicate large ecmp groups
+ iter=0
+ while [ $iter -le $grpnum ]
+ do
+ grpidstr="$(($grpidstart + $iter))"
+ run_cmd "$IP nexthop add id $grpidstr group $grpstr"
+ check_nexthop "id $grpidstr" "id $grpidstr group $grpstr"
+ ((iter++))
+ done
+
+ # dump large groups
+ run_cmd "$IP nexthop list"
+ log_test $? 0 "Dump large (x$ecmp) ecmp groups"
+}
+
+start_ip_monitor()
+{
+ local mtype=$1
+
+ # start the monitor in the background
+ tmpfile=`mktemp /var/run/nexthoptestXXX`
+ mpid=`($IP monitor $mtype > $tmpfile & echo $!) 2>/dev/null`
+ sleep 0.2
+ echo "$mpid $tmpfile"
+}
+
+stop_ip_monitor()
+{
+ local mpid=$1
+ local tmpfile=$2
+ local el=$3
+
+ # check the monitor results
+ kill $mpid
+ lines=`wc -l $tmpfile | cut "-d " -f1`
+ test $lines -eq $el
+ rc=$?
+ rm -rf $tmpfile
+
+ return $rc
+}
+
+check_nexthop_fdb_support()
+{
+ $IP nexthop help 2>&1 | grep -q fdb
+ if [ $? -ne 0 ]; then
+ echo "SKIP: iproute2 too old, missing fdb nexthop support"
+ return $ksft_skip
+ fi
+}
+
+ipv6_fdb_grp_fcnal()
+{
+ local rc
+
+ echo
+ echo "IPv6 fdb groups functional"
+ echo "--------------------------"
+
+ check_nexthop_fdb_support
+ if [ $? -eq $ksft_skip ]; then
+ return $ksft_skip
+ fi
+
+ # create group with multiple nexthops
+ run_cmd "$IP nexthop add id 61 via 2001:db8:91::2 fdb"
+ run_cmd "$IP nexthop add id 62 via 2001:db8:91::3 fdb"
+ run_cmd "$IP nexthop add id 102 group 61/62 fdb"
+ check_nexthop "id 102" "id 102 group 61/62 fdb"
+ log_test $? 0 "Fdb Nexthop group with multiple nexthops"
+
+ ## get nexthop group
+ run_cmd "$IP nexthop get id 102"
+ check_nexthop "id 102" "id 102 group 61/62 fdb"
+ 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 103 group 63/64 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 65 via 2001:db8:91::5 fdb"
+ run_cmd "$IP nexthop add id 66 via 2001:db8:91::6 fdb"
+ run_cmd "$IP nexthop add id 104 group 65/66"
+ log_test $? 2 "Non-Fdb Nexthop group with fdb nexthops"
+
+ # fdb nexthop cannot have blackhole
+ run_cmd "$IP nexthop add id 67 blackhole fdb"
+ log_test $? 2 "Fdb Nexthop with blackhole"
+
+ # fdb nexthop with oif
+ run_cmd "$IP nexthop add id 68 via 2001:db8:91::7 dev veth1 fdb"
+ log_test $? 2 "Fdb Nexthop with oif"
+
+ # fdb nexthop with onlink
+ run_cmd "$IP nexthop add id 68 via 2001:db8:91::7 onlink fdb"
+ log_test $? 2 "Fdb Nexthop with onlink"
+
+ # fdb nexthop with encap
+ run_cmd "$IP nexthop add id 69 encap mpls 101 via 2001:db8:91::8 dev veth1 fdb"
+ log_test $? 2 "Fdb Nexthop with encap"
+
+ run_cmd "$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 $? 0 "Fdb mac add with nexthop group"
+
+ ## fdb nexthops can only reference nexthop groups and not nexthops
+ run_cmd "$BRIDGE fdb add 02:02:00:00:00:14 dev vx10 nhid 61 self"
+ log_test $? 255 "Fdb mac add with nexthop"
+
+ run_cmd "$IP -6 ro add 2001:db8:101::1/128 nhid 66"
+ log_test $? 2 "Route add with fdb nexthop"
+
+ run_cmd "$IP -6 ro add 2001:db8:101::1/128 nhid 103"
+ log_test $? 2 "Route add with fdb nexthop group"
+
+ run_cmd "$IP nexthop del id 102"
+ log_test $? 0 "Fdb nexthop delete"
+
+ $IP link del dev vx10
+}
+
+ipv4_fdb_grp_fcnal()
+{
+ local rc
+
+ echo
+ echo "IPv4 fdb groups functional"
+ echo "--------------------------"
+
+ check_nexthop_fdb_support
+ if [ $? -eq $ksft_skip ]; then
+ return $ksft_skip
+ fi
+
+ # create group with multiple nexthops
+ run_cmd "$IP nexthop add id 12 via 172.16.1.2 fdb"
+ run_cmd "$IP nexthop add id 13 via 172.16.1.3 fdb"
+ run_cmd "$IP nexthop add id 102 group 12/13 fdb"
+ check_nexthop "id 102" "id 102 group 12/13 fdb"
+ log_test $? 0 "Fdb Nexthop group with multiple nexthops"
+
+ # get nexthop group
+ run_cmd "$IP nexthop get id 102"
+ check_nexthop "id 102" "id 102 group 12/13 fdb"
+ 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 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"
+ log_test $? 2 "Non-Fdb Nexthop group with fdb nexthops"
+
+ # fdb nexthop cannot have blackhole
+ run_cmd "$IP nexthop add id 18 blackhole fdb"
+ log_test $? 2 "Fdb Nexthop with blackhole"
+
+ # fdb nexthop with oif
+ run_cmd "$IP nexthop add id 16 via 172.16.1.2 dev veth1 fdb"
+ log_test $? 2 "Fdb Nexthop with oif"
+
+ # fdb nexthop with onlink
+ run_cmd "$IP nexthop add id 16 via 172.16.1.2 onlink fdb"
+ log_test $? 2 "Fdb Nexthop with onlink"
+
+ # fdb nexthop with encap
+ run_cmd "$IP nexthop add id 17 encap mpls 101 via 172.16.1.2 dev veth1 fdb"
+ log_test $? 2 "Fdb Nexthop with encap"
+
+ run_cmd "$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 $? 0 "Fdb mac add with nexthop group"
+
+ # fdb nexthops can only reference nexthop groups and not nexthops
+ run_cmd "$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"
+ log_test $? 2 "Route add with fdb nexthop"
+
+ run_cmd "$IP ro add 172.16.0.0/22 nhid 103"
+ log_test $? 2 "Route add with fdb nexthop group"
+
+ run_cmd "$IP nexthop del id 102"
+ log_test $? 0 "Fdb nexthop delete"
+
+ $IP link del dev vx10
+}
+
################################################################################
# basic operations (add, delete, replace) on nexthops and nexthop groups
#
@@ -423,8 +660,6 @@ ipv6_fcnal_runtime()
echo "IPv6 functional runtime"
echo "-----------------------"
- sleep 5
-
#
# IPv6 - the basics
#
@@ -481,12 +716,12 @@ ipv6_fcnal_runtime()
run_cmd "$IP -6 nexthop add id 85 dev veth1"
run_cmd "$IP ro replace 2001:db8:101::1/128 nhid 85"
log_test $? 0 "IPv6 route with device only nexthop"
- check_route6 "2001:db8:101::1" "2001:db8:101::1 nhid 85 dev veth1 metric 1024 pref medium"
+ check_route6 "2001:db8:101::1" "2001:db8:101::1 nhid 85 dev veth1 metric 1024"
run_cmd "$IP nexthop add id 123 group 81/85"
run_cmd "$IP ro replace 2001:db8:101::1/128 nhid 123"
log_test $? 0 "IPv6 multipath route with nexthop mix - dev only + gw"
- check_route6 "2001:db8:101::1" "2001:db8:101::1 nhid 123 metric 1024 nexthop via 2001:db8:91::2 dev veth1 weight 1 nexthop dev veth1 weight 1 pref medium"
+ check_route6 "2001:db8:101::1" "2001:db8:101::1 nhid 123 metric 1024 nexthop via 2001:db8:91::2 dev veth1 weight 1 nexthop dev veth1 weight 1"
#
# IPv6 route with v4 nexthop - not allowed
@@ -519,6 +754,75 @@ ipv6_fcnal_runtime()
# route with src address and using nexthop - not allowed
}
+ipv6_large_grp()
+{
+ local ecmp=32
+
+ echo
+ echo "IPv6 large groups (x$ecmp)"
+ echo "---------------------"
+
+ check_large_grp 6 $ecmp
+
+ $IP nexthop flush >/dev/null 2>&1
+}
+
+ipv6_del_add_loop1()
+{
+ while :; do
+ $IP nexthop del id 100
+ $IP nexthop add id 100 via 2001:db8:91::2 dev veth1
+ done >/dev/null 2>&1
+}
+
+ipv6_grp_replace_loop()
+{
+ while :; do
+ $IP nexthop replace id 102 group 100/101
+ done >/dev/null 2>&1
+}
+
+ipv6_torture()
+{
+ local pid1
+ local pid2
+ local pid3
+ local pid4
+ local pid5
+
+ echo
+ echo "IPv6 runtime torture"
+ echo "--------------------"
+ if [ ! -x "$(command -v mausezahn)" ]; then
+ echo "SKIP: Could not run test; need mausezahn tool"
+ return
+ fi
+
+ run_cmd "$IP nexthop add id 100 via 2001:db8:91::2 dev veth1"
+ run_cmd "$IP nexthop add id 101 via 2001:db8:92::2 dev veth3"
+ run_cmd "$IP nexthop add id 102 group 100/101"
+ run_cmd "$IP route add 2001:db8:101::1 nhid 102"
+ run_cmd "$IP route add 2001:db8:101::2 nhid 102"
+
+ ipv6_del_add_loop1 &
+ pid1=$!
+ ipv6_grp_replace_loop &
+ pid2=$!
+ ip netns exec me ping -f 2001:db8:101::1 >/dev/null 2>&1 &
+ pid3=$!
+ ip netns exec me ping -f 2001:db8:101::2 >/dev/null 2>&1 &
+ pid4=$!
+ ip netns exec me mausezahn veth1 -B 2001:db8:101::2 -A 2001:db8:91::1 -c 0 -t tcp "dp=1-1023, flags=syn" >/dev/null 2>&1 &
+ pid5=$!
+
+ sleep 300
+ kill -9 $pid1 $pid2 $pid3 $pid4 $pid5
+
+ # if we did not crash, success
+ log_test 0 0 "IPv6 torture test"
+}
+
+
ipv4_fcnal()
{
local rc
@@ -749,6 +1053,29 @@ ipv4_fcnal_runtime()
run_cmd "ip netns exec me ping -c1 -w1 172.16.101.1"
log_test $? 0 "Ping - multipath"
+ run_cmd "$IP ro delete 172.16.101.1/32 nhid 122"
+
+ #
+ # multiple default routes
+ # - tests fib_select_default
+ run_cmd "$IP nexthop add id 501 via 172.16.1.2 dev veth1"
+ run_cmd "$IP ro add default nhid 501"
+ run_cmd "$IP ro add default via 172.16.1.3 dev veth1 metric 20"
+ run_cmd "ip netns exec me ping -c1 -w1 172.16.101.1"
+ log_test $? 0 "Ping - multiple default routes, nh first"
+
+ # flip the order
+ run_cmd "$IP ro del default nhid 501"
+ run_cmd "$IP ro del default via 172.16.1.3 dev veth1 metric 20"
+ run_cmd "$IP ro add default via 172.16.1.2 dev veth1 metric 20"
+ run_cmd "$IP nexthop replace id 501 via 172.16.1.3 dev veth1"
+ run_cmd "$IP ro add default nhid 501 metric 20"
+ run_cmd "ip netns exec me ping -c1 -w1 172.16.101.1"
+ log_test $? 0 "Ping - multiple default routes, nh second"
+
+ run_cmd "$IP nexthop delete nhid 501"
+ run_cmd "$IP ro del default"
+
#
# IPv4 with blackhole nexthops
#
@@ -843,6 +1170,11 @@ ipv4_fcnal_runtime()
$IP neigh sh | grep 'dev veth1'
fi
+ run_cmd "$IP ro del 172.16.101.1/32 via inet6 ${lladdr} dev veth1"
+ run_cmd "$IP -4 ro add default via inet6 ${lladdr} dev veth1"
+ run_cmd "ip netns exec me ping -c1 -w1 172.16.101.1"
+ log_test $? 0 "IPv4 default route with IPv6 gateway"
+
#
# MPLS as an example of LWT encap
#
@@ -857,6 +1189,241 @@ ipv4_fcnal_runtime()
log_test $? 0 "IPv4 route with MPLS encap, v6 gw - check"
}
+ipv4_large_grp()
+{
+ local ecmp=32
+
+ echo
+ echo "IPv4 large groups (x$ecmp)"
+ echo "---------------------"
+
+ check_large_grp 4 $ecmp
+
+ $IP nexthop flush >/dev/null 2>&1
+}
+
+sysctl_nexthop_compat_mode_check()
+{
+ local sysctlname="net.ipv4.nexthop_compat_mode"
+ local lprefix=$1
+
+ IPE="ip netns exec me"
+
+ $IPE sysctl -q $sysctlname 2>&1 >/dev/null
+ if [ $? -ne 0 ]; then
+ echo "SKIP: kernel lacks nexthop compat mode sysctl control"
+ return $ksft_skip
+ fi
+
+ out=$($IPE sysctl $sysctlname 2>/dev/null)
+ log_test $? 0 "$lprefix default nexthop compat mode check"
+ check_output "${out}" "$sysctlname = 1"
+}
+
+sysctl_nexthop_compat_mode_set()
+{
+ local sysctlname="net.ipv4.nexthop_compat_mode"
+ local mode=$1
+ local lprefix=$2
+
+ IPE="ip netns exec me"
+
+ out=$($IPE sysctl -w $sysctlname=$mode)
+ log_test $? 0 "$lprefix set compat mode - $mode"
+ check_output "${out}" "net.ipv4.nexthop_compat_mode = $mode"
+}
+
+ipv6_compat_mode()
+{
+ local rc
+
+ echo
+ echo "IPv6 nexthop api compat mode test"
+ echo "--------------------------------"
+
+ sysctl_nexthop_compat_mode_check "IPv6"
+ if [ $? -eq $ksft_skip ]; then
+ return $ksft_skip
+ fi
+
+ run_cmd "$IP nexthop add id 62 via 2001:db8:91::2 dev veth1"
+ run_cmd "$IP nexthop add id 63 via 2001:db8:91::3 dev veth1"
+ run_cmd "$IP nexthop add id 122 group 62/63"
+ ipmout=$(start_ip_monitor route)
+
+ run_cmd "$IP -6 ro add 2001:db8:101::1/128 nhid 122"
+ # route add notification should contain expanded nexthops
+ stop_ip_monitor $ipmout 3
+ log_test $? 0 "IPv6 compat mode on - route add notification"
+
+ # route dump should contain expanded nexthops
+ check_route6 "2001:db8:101::1" "2001:db8:101::1 nhid 122 metric 1024 nexthop via 2001:db8:91::2 dev veth1 weight 1 nexthop via 2001:db8:91::3 dev veth1 weight 1"
+ log_test $? 0 "IPv6 compat mode on - route dump"
+
+ # change in nexthop group should generate route notification
+ run_cmd "$IP nexthop add id 64 via 2001:db8:91::4 dev veth1"
+ ipmout=$(start_ip_monitor route)
+ run_cmd "$IP nexthop replace id 122 group 62/64"
+ stop_ip_monitor $ipmout 3
+
+ log_test $? 0 "IPv6 compat mode on - nexthop change"
+
+ # set compat mode off
+ sysctl_nexthop_compat_mode_set 0 "IPv6"
+
+ run_cmd "$IP -6 ro del 2001:db8:101::1/128 nhid 122"
+
+ run_cmd "$IP nexthop add id 62 via 2001:db8:91::2 dev veth1"
+ run_cmd "$IP nexthop add id 63 via 2001:db8:91::3 dev veth1"
+ run_cmd "$IP nexthop add id 122 group 62/63"
+ ipmout=$(start_ip_monitor route)
+
+ run_cmd "$IP -6 ro add 2001:db8:101::1/128 nhid 122"
+ # route add notification should not contain expanded nexthops
+ stop_ip_monitor $ipmout 1
+ log_test $? 0 "IPv6 compat mode off - route add notification"
+
+ # route dump should not contain expanded nexthops
+ check_route6 "2001:db8:101::1" "2001:db8:101::1 nhid 122 metric 1024"
+ log_test $? 0 "IPv6 compat mode off - route dump"
+
+ # change in nexthop group should not generate route notification
+ run_cmd "$IP nexthop add id 64 via 2001:db8:91::4 dev veth1"
+ ipmout=$(start_ip_monitor route)
+ run_cmd "$IP nexthop replace id 122 group 62/64"
+ stop_ip_monitor $ipmout 0
+ log_test $? 0 "IPv6 compat mode off - nexthop change"
+
+ # nexthop delete should not generate route notification
+ ipmout=$(start_ip_monitor route)
+ run_cmd "$IP nexthop del id 122"
+ stop_ip_monitor $ipmout 0
+ log_test $? 0 "IPv6 compat mode off - nexthop delete"
+
+ # set compat mode back on
+ sysctl_nexthop_compat_mode_set 1 "IPv6"
+}
+
+ipv4_compat_mode()
+{
+ local rc
+
+ echo
+ echo "IPv4 nexthop api compat mode"
+ echo "----------------------------"
+
+ sysctl_nexthop_compat_mode_check "IPv4"
+ if [ $? -eq $ksft_skip ]; then
+ return $ksft_skip
+ fi
+
+ run_cmd "$IP nexthop add id 21 via 172.16.1.2 dev veth1"
+ run_cmd "$IP nexthop add id 22 via 172.16.1.2 dev veth1"
+ run_cmd "$IP nexthop add id 122 group 21/22"
+ ipmout=$(start_ip_monitor route)
+
+ run_cmd "$IP ro add 172.16.101.1/32 nhid 122"
+ stop_ip_monitor $ipmout 3
+
+ # route add notification should contain expanded nexthops
+ log_test $? 0 "IPv4 compat mode on - route add notification"
+
+ # route dump should contain expanded nexthops
+ check_route "172.16.101.1" "172.16.101.1 nhid 122 nexthop via 172.16.1.2 dev veth1 weight 1 nexthop via 172.16.1.2 dev veth1 weight 1"
+ log_test $? 0 "IPv4 compat mode on - route dump"
+
+ # change in nexthop group should generate route notification
+ run_cmd "$IP nexthop add id 23 via 172.16.1.3 dev veth1"
+ ipmout=$(start_ip_monitor route)
+ run_cmd "$IP nexthop replace id 122 group 21/23"
+ stop_ip_monitor $ipmout 3
+ log_test $? 0 "IPv4 compat mode on - nexthop change"
+
+ sysctl_nexthop_compat_mode_set 0 "IPv4"
+
+ # cleanup
+ run_cmd "$IP ro del 172.16.101.1/32 nhid 122"
+
+ ipmout=$(start_ip_monitor route)
+ run_cmd "$IP ro add 172.16.101.1/32 nhid 122"
+ stop_ip_monitor $ipmout 1
+ # route add notification should not contain expanded nexthops
+ log_test $? 0 "IPv4 compat mode off - route add notification"
+
+ # route dump should not contain expanded nexthops
+ check_route "172.16.101.1" "172.16.101.1 nhid 122"
+ log_test $? 0 "IPv4 compat mode off - route dump"
+
+ # change in nexthop group should not generate route notification
+ ipmout=$(start_ip_monitor route)
+ run_cmd "$IP nexthop replace id 122 group 21/22"
+ stop_ip_monitor $ipmout 0
+ log_test $? 0 "IPv4 compat mode off - nexthop change"
+
+ # nexthop delete should not generate route notification
+ ipmout=$(start_ip_monitor route)
+ run_cmd "$IP nexthop del id 122"
+ stop_ip_monitor $ipmout 0
+ log_test $? 0 "IPv4 compat mode off - nexthop delete"
+
+ sysctl_nexthop_compat_mode_set 1 "IPv4"
+}
+
+ipv4_del_add_loop1()
+{
+ while :; do
+ $IP nexthop del id 100
+ $IP nexthop add id 100 via 172.16.1.2 dev veth1
+ done >/dev/null 2>&1
+}
+
+ipv4_grp_replace_loop()
+{
+ while :; do
+ $IP nexthop replace id 102 group 100/101
+ done >/dev/null 2>&1
+}
+
+ipv4_torture()
+{
+ local pid1
+ local pid2
+ local pid3
+ local pid4
+ local pid5
+
+ echo
+ echo "IPv4 runtime torture"
+ echo "--------------------"
+ if [ ! -x "$(command -v mausezahn)" ]; then
+ echo "SKIP: Could not run test; need mausezahn tool"
+ return
+ fi
+
+ run_cmd "$IP nexthop add id 100 via 172.16.1.2 dev veth1"
+ run_cmd "$IP nexthop add id 101 via 172.16.2.2 dev veth3"
+ run_cmd "$IP nexthop add id 102 group 100/101"
+ run_cmd "$IP route add 172.16.101.1 nhid 102"
+ run_cmd "$IP route add 172.16.101.2 nhid 102"
+
+ ipv4_del_add_loop1 &
+ pid1=$!
+ ipv4_grp_replace_loop &
+ pid2=$!
+ ip netns exec me ping -f 172.16.101.1 >/dev/null 2>&1 &
+ pid3=$!
+ ip netns exec me ping -f 172.16.101.2 >/dev/null 2>&1 &
+ pid4=$!
+ ip netns exec me mausezahn veth1 -B 172.16.101.2 -A 172.16.1.1 -c 0 -t tcp "dp=1-1023, flags=syn" >/dev/null 2>&1 &
+ pid5=$!
+
+ sleep 300
+ kill -9 $pid1 $pid2 $pid3 $pid4 $pid5
+
+ # if we did not crash, success
+ log_test 0 0 "IPv4 torture test"
+}
+
basic()
{
echo
diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh
index b7616704b55e..84205c3a55eb 100755
--- a/tools/testing/selftests/net/fib_tests.sh
+++ b/tools/testing/selftests/net/fib_tests.sh
@@ -618,16 +618,22 @@ fib_nexthop_test()
fib_suppress_test()
{
+ echo
+ echo "FIB rule with suppress_prefixlength"
+ setup
+
$IP link add dummy1 type dummy
$IP link set dummy1 up
$IP -6 route add default dev dummy1
$IP -6 rule add table main suppress_prefixlength 0
- ping -f -c 1000 -W 1 1234::1 || true
+ ping -f -c 1000 -W 1 1234::1 >/dev/null 2>&1
$IP -6 rule del table main suppress_prefixlength 0
$IP link del dummy1
# If we got here without crashing, we're good.
- return 0
+ log_test 0 0 "FIB rule suppress test"
+
+ cleanup
}
################################################################################
diff --git a/tools/testing/selftests/net/forwarding/.gitignore b/tools/testing/selftests/net/forwarding/.gitignore
index a793eef5b876..2dea317f12e7 100644
--- a/tools/testing/selftests/net/forwarding/.gitignore
+++ b/tools/testing/selftests/net/forwarding/.gitignore
@@ -1 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
forwarding.config
diff --git a/tools/testing/selftests/net/forwarding/devlink_lib.sh b/tools/testing/selftests/net/forwarding/devlink_lib.sh
index 40b076983239..f0e6be4c09e9 100644
--- a/tools/testing/selftests/net/forwarding/devlink_lib.sh
+++ b/tools/testing/selftests/net/forwarding/devlink_lib.sh
@@ -35,6 +35,12 @@ if [ $? -ne 0 ]; then
exit 1
fi
+devlink dev help 2>&1 | grep info &> /dev/null
+if [ $? -ne 0 ]; then
+ echo "SKIP: iproute2 too old, missing devlink dev info support"
+ exit 1
+fi
+
##############################################################################
# Devlink helpers
@@ -359,7 +365,9 @@ devlink_trap_group_stats_idle_test()
devlink_trap_exception_test()
{
local trap_name=$1; shift
- local group_name=$1; shift
+ local group_name
+
+ group_name=$(devlink_trap_group_get $trap_name)
devlink_trap_stats_idle_test $trap_name
check_fail $? "Trap stats idle when packets should have been trapped"
@@ -371,8 +379,11 @@ devlink_trap_exception_test()
devlink_trap_drop_test()
{
local trap_name=$1; shift
- local group_name=$1; shift
local dev=$1; shift
+ local handle=$1; shift
+ local group_name
+
+ group_name=$(devlink_trap_group_get $trap_name)
# This is the common part of all the tests. It checks that stats are
# initially idle, then non-idle after changing the trap action and
@@ -383,7 +394,6 @@ devlink_trap_drop_test()
devlink_trap_group_stats_idle_test $group_name
check_err $? "Trap group stats not idle with initial drop action"
-
devlink_trap_action_set $trap_name "trap"
devlink_trap_stats_idle_test $trap_name
check_fail $? "Trap stats idle after setting action to trap"
@@ -397,7 +407,7 @@ devlink_trap_drop_test()
devlink_trap_group_stats_idle_test $group_name
check_err $? "Trap group stats not idle after setting action to drop"
- tc_check_packets "dev $dev egress" 101 0
+ tc_check_packets "dev $dev egress" $handle 0
check_err $? "Packets were not dropped"
}
@@ -406,7 +416,91 @@ devlink_trap_drop_cleanup()
local mz_pid=$1; shift
local dev=$1; shift
local proto=$1; shift
+ local pref=$1; shift
+ local handle=$1; shift
kill $mz_pid && wait $mz_pid &> /dev/null
- tc filter del dev $dev egress protocol $proto pref 1 handle 101 flower
+ tc filter del dev $dev egress protocol $proto pref $pref handle $handle flower
+}
+
+devlink_trap_stats_test()
+{
+ local test_name=$1; shift
+ local trap_name=$1; shift
+ local send_one="$@"
+ local t0_packets
+ local t1_packets
+
+ RET=0
+
+ t0_packets=$(devlink_trap_rx_packets_get $trap_name)
+
+ $send_one && sleep 1
+
+ t1_packets=$(devlink_trap_rx_packets_get $trap_name)
+
+ if [[ $t1_packets -eq $t0_packets ]]; then
+ check_err 1 "Trap stats did not increase"
+ fi
+
+ log_test "$test_name"
+}
+
+devlink_trap_policers_num_get()
+{
+ devlink -j -p trap policer show | jq '.[]["'$DEVLINK_DEV'"] | length'
+}
+
+devlink_trap_policer_rate_get()
+{
+ local policer_id=$1; shift
+
+ devlink -j -p trap policer show $DEVLINK_DEV policer $policer_id \
+ | jq '.[][][]["rate"]'
+}
+
+devlink_trap_policer_burst_get()
+{
+ local policer_id=$1; shift
+
+ devlink -j -p trap policer show $DEVLINK_DEV policer $policer_id \
+ | jq '.[][][]["burst"]'
+}
+
+devlink_trap_policer_rx_dropped_get()
+{
+ local policer_id=$1; shift
+
+ devlink -j -p -s trap policer show $DEVLINK_DEV policer $policer_id \
+ | jq '.[][][]["stats"]["rx"]["dropped"]'
+}
+
+devlink_trap_group_policer_get()
+{
+ local group_name=$1; shift
+
+ devlink -j -p trap group show $DEVLINK_DEV group $group_name \
+ | jq '.[][][]["policer"]'
+}
+
+devlink_trap_policer_ids_get()
+{
+ devlink -j -p trap policer show \
+ | jq '.[]["'$DEVLINK_DEV'"][]["policer"]'
+}
+
+devlink_port_by_netdev()
+{
+ local if_name=$1
+
+ devlink -j port show $if_name | jq -e '.[] | keys' | jq -r '.[]'
+}
+
+devlink_cpu_port_get()
+{
+ local cpu_dl_port_num=$(devlink port list | grep "$DEVLINK_DEV" |
+ grep cpu | cut -d/ -f3 | cut -d: -f1 |
+ sed -n '1p')
+
+ echo "$DEVLINK_DEV/$cpu_dl_port_num"
}
diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index 2f5da414aaa7..977fc2b326a2 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -60,6 +60,15 @@ check_tc_chain_support()
fi
}
+check_tc_action_hw_stats_support()
+{
+ tc actions help 2>&1 | grep -q hw_stats
+ if [[ $? -ne 0 ]]; then
+ echo "SKIP: iproute2 too old; tc is missing action hw_stats support"
+ exit 1
+ fi
+}
+
if [[ "$(id -u)" -ne 0 ]]; then
echo "SKIP: need root privileges"
exit 0
@@ -248,13 +257,40 @@ busywait()
done
}
+not()
+{
+ "$@"
+ [[ $? != 0 ]]
+}
+
+grep_bridge_fdb()
+{
+ local addr=$1; shift
+ local word
+ local flag
+
+ if [ "$1" == "self" ] || [ "$1" == "master" ]; then
+ word=$1; shift
+ if [ "$1" == "-v" ]; then
+ flag=$1; shift
+ fi
+ fi
+
+ $@ | grep $addr | grep $flag "$word"
+}
+
+wait_for_offload()
+{
+ "$@" | grep -q offload
+}
+
until_counter_is()
{
- local value=$1; shift
+ local expr=$1; shift
local current=$("$@")
echo $((current))
- ((current >= value))
+ ((current $expr))
}
busywait_for_counter()
@@ -263,7 +299,7 @@ busywait_for_counter()
local delta=$1; shift
local base=$("$@")
- busywait "$timeout" until_counter_is $((base + delta)) "$@"
+ busywait "$timeout" until_counter_is ">= $((base + delta))" "$@"
}
setup_wait_dev()
@@ -599,6 +635,17 @@ tc_rule_stats_get()
| jq ".[1].options.actions[].stats$selector"
}
+tc_rule_handle_stats_get()
+{
+ local id=$1; shift
+ local handle=$1; shift
+ local selector=${1:-.packets}; shift
+
+ tc -j -s filter show $id \
+ | jq ".[] | select(.options.handle == $handle) | \
+ .options.actions[0].stats$selector"
+}
+
ethtool_stats_get()
{
local dev=$1; shift
@@ -607,6 +654,26 @@ ethtool_stats_get()
ethtool -S $dev | grep "^ *$stat:" | head -n 1 | cut -d: -f2
}
+qdisc_stats_get()
+{
+ local dev=$1; shift
+ local handle=$1; shift
+ local selector=$1; shift
+
+ tc -j -s qdisc show dev "$dev" \
+ | jq '.[] | select(.handle == "'"$handle"'") | '"$selector"
+}
+
+qdisc_parent_stats_get()
+{
+ local dev=$1; shift
+ local parent=$1; shift
+ local selector=$1; shift
+
+ tc -j -s qdisc show dev "$dev" invisible \
+ | jq '.[] | select(.parent == "'"$parent"'") | '"$selector"
+}
+
humanize()
{
local speed=$1; shift
@@ -1132,18 +1199,29 @@ flood_test()
flood_multicast_test $br_port $host1_if $host2_if
}
-start_traffic()
+__start_traffic()
{
+ local proto=$1; shift
local h_in=$1; shift # Where the traffic egresses the host
local sip=$1; shift
local dip=$1; shift
local dmac=$1; shift
$MZ $h_in -p 8000 -A $sip -B $dip -c 0 \
- -a own -b $dmac -t udp -q &
+ -a own -b $dmac -t "$proto" -q "$@" &
sleep 1
}
+start_traffic()
+{
+ __start_traffic udp "$@"
+}
+
+start_tcp_traffic()
+{
+ __start_traffic tcp "$@"
+}
+
stop_traffic()
{
# Suppress noise from killing mausezahn.
diff --git a/tools/testing/selftests/net/forwarding/mirror_lib.sh b/tools/testing/selftests/net/forwarding/mirror_lib.sh
index 00797597fcf5..c33bfd7ba214 100644
--- a/tools/testing/selftests/net/forwarding/mirror_lib.sh
+++ b/tools/testing/selftests/net/forwarding/mirror_lib.sh
@@ -29,11 +29,9 @@ mirror_test()
local pref=$1; shift
local expect=$1; shift
- local ping_timeout=$((PING_TIMEOUT * 5))
local t0=$(tc_rule_stats_get $dev $pref)
- ip vrf exec $vrf_name \
- ${PING} ${sip:+-I $sip} $dip -c 10 -i 0.5 -w $ping_timeout \
- &> /dev/null
+ $MZ $vrf_name ${sip:+-A $sip} -B $dip -a own -b bc -q \
+ -c 10 -d 100ms -t icmp type=8
sleep 0.5
local t1=$(tc_rule_stats_get $dev $pref)
local delta=$((t1 - t0))
diff --git a/tools/testing/selftests/net/forwarding/pedit_dsfield.sh b/tools/testing/selftests/net/forwarding/pedit_dsfield.sh
new file mode 100755
index 000000000000..55eeacf59241
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/pedit_dsfield.sh
@@ -0,0 +1,309 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# This test sends traffic from H1 to H2. Either on ingress of $swp1, or on
+# egress of $swp2, the traffic is acted upon by a pedit action. An ingress
+# filter installed on $h2 verifies that the packet looks like expected.
+#
+# +----------------------+ +----------------------+
+# | H1 | | H2 |
+# | + $h1 | | $h2 + |
+# | | 192.0.2.1/28 | | 192.0.2.2/28 | |
+# +----|-----------------+ +----------------|-----+
+# | |
+# +----|----------------------------------------------------------------|-----+
+# | SW | | |
+# | +-|----------------------------------------------------------------|-+ |
+# | | + $swp1 BR $swp2 + | |
+# | +--------------------------------------------------------------------+ |
+# +---------------------------------------------------------------------------+
+
+ALL_TESTS="
+ ping_ipv4
+ ping_ipv6
+ test_ip_dsfield
+ test_ip_dscp
+ test_ip_ecn
+ test_ip_dscp_ecn
+ test_ip6_dsfield
+ test_ip6_dscp
+ test_ip6_ecn
+"
+
+NUM_NETIFS=4
+source lib.sh
+source tc_common.sh
+
+: ${HIT_TIMEOUT:=2000} # ms
+
+h1_create()
+{
+ simple_if_init $h1 192.0.2.1/28 2001:db8:1::1/64
+}
+
+h1_destroy()
+{
+ simple_if_fini $h1 192.0.2.1/28 2001:db8:1::1/64
+}
+
+h2_create()
+{
+ simple_if_init $h2 192.0.2.2/28 2001:db8:1::2/64
+ tc qdisc add dev $h2 clsact
+}
+
+h2_destroy()
+{
+ tc qdisc del dev $h2 clsact
+ simple_if_fini $h2 192.0.2.2/28 2001:db8:1::2/64
+}
+
+switch_create()
+{
+ ip link add name br1 up type bridge vlan_filtering 1
+ ip link set dev $swp1 master br1
+ ip link set dev $swp1 up
+ ip link set dev $swp2 master br1
+ ip link set dev $swp2 up
+
+ tc qdisc add dev $swp1 clsact
+ tc qdisc add dev $swp2 clsact
+}
+
+switch_destroy()
+{
+ tc qdisc del dev $swp2 clsact
+ tc qdisc del dev $swp1 clsact
+
+ ip link set dev $swp2 nomaster
+ ip link set dev $swp1 nomaster
+ ip link del dev br1
+}
+
+setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ swp1=${NETIFS[p2]}
+
+ swp2=${NETIFS[p3]}
+ h2=${NETIFS[p4]}
+
+ h2mac=$(mac_get $h2)
+
+ vrf_prepare
+ h1_create
+ h2_create
+ switch_create
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ switch_destroy
+ h2_destroy
+ h1_destroy
+ vrf_cleanup
+}
+
+ping_ipv4()
+{
+ ping_test $h1 192.0.2.2
+}
+
+ping_ipv6()
+{
+ ping6_test $h1 2001:db8:1::2
+}
+
+do_test_pedit_dsfield_common()
+{
+ local pedit_locus=$1; shift
+ local pedit_action=$1; shift
+ local mz_flags=$1; shift
+
+ RET=0
+
+ # TOS 125: DSCP 31, ECN 1. Used for testing that the relevant part is
+ # overwritten when zero is selected.
+ $MZ $mz_flags $h1 -c 10 -d 20msec -p 100 \
+ -a own -b $h2mac -q -t tcp tos=0x7d,sp=54321,dp=12345
+
+ local pkts
+ pkts=$(busywait "$TC_HIT_TIMEOUT" until_counter_is ">= 10" \
+ tc_rule_handle_stats_get "dev $h2 ingress" 101)
+ check_err $? "Expected to get 10 packets on test probe, but got $pkts."
+
+ pkts=$(tc_rule_handle_stats_get "$pedit_locus" 101)
+ ((pkts >= 10))
+ check_err $? "Expected to get 10 packets on pedit rule, but got $pkts."
+
+ log_test "$pedit_locus pedit $pedit_action"
+}
+
+do_test_pedit_dsfield()
+{
+ local pedit_locus=$1; shift
+ local pedit_action=$1; shift
+ local match_prot=$1; shift
+ local match_flower=$1; shift
+ local mz_flags=$1; shift
+ local saddr=$1; shift
+ local daddr=$1; shift
+
+ tc filter add $pedit_locus handle 101 pref 1 \
+ flower action pedit ex munge $pedit_action
+ tc filter add dev $h2 ingress handle 101 pref 1 prot $match_prot \
+ flower skip_hw $match_flower action pass
+
+ do_test_pedit_dsfield_common "$pedit_locus" "$pedit_action" "$mz_flags"
+
+ tc filter del dev $h2 ingress pref 1
+ tc filter del $pedit_locus pref 1
+}
+
+do_test_ip_dsfield()
+{
+ local locus=$1; shift
+ local dsfield
+
+ for dsfield in 0 1 2 3 128 252 253 254 255; do
+ do_test_pedit_dsfield "$locus" \
+ "ip dsfield set $dsfield" \
+ ip "ip_tos $dsfield" \
+ "-A 192.0.2.1 -B 192.0.2.2"
+ done
+}
+
+test_ip_dsfield()
+{
+ do_test_ip_dsfield "dev $swp1 ingress"
+ do_test_ip_dsfield "dev $swp2 egress"
+}
+
+do_test_ip_dscp()
+{
+ local locus=$1; shift
+ local dscp
+
+ for dscp in 0 1 2 3 32 61 62 63; do
+ do_test_pedit_dsfield "$locus" \
+ "ip dsfield set $((dscp << 2)) retain 0xfc" \
+ ip "ip_tos $(((dscp << 2) | 1))" \
+ "-A 192.0.2.1 -B 192.0.2.2"
+ done
+}
+
+test_ip_dscp()
+{
+ do_test_ip_dscp "dev $swp1 ingress"
+ do_test_ip_dscp "dev $swp2 egress"
+}
+
+do_test_ip_ecn()
+{
+ local locus=$1; shift
+ local ecn
+
+ for ecn in 0 1 2 3; do
+ do_test_pedit_dsfield "$locus" \
+ "ip dsfield set $ecn retain 0x03" \
+ ip "ip_tos $((124 | $ecn))" \
+ "-A 192.0.2.1 -B 192.0.2.2"
+ done
+}
+
+test_ip_ecn()
+{
+ do_test_ip_ecn "dev $swp1 ingress"
+ do_test_ip_ecn "dev $swp2 egress"
+}
+
+do_test_ip_dscp_ecn()
+{
+ local locus=$1; shift
+
+ tc filter add $locus handle 101 pref 1 \
+ flower action pedit ex munge ip dsfield set 124 retain 0xfc \
+ action pedit ex munge ip dsfield set 1 retain 0x03
+ tc filter add dev $h2 ingress handle 101 pref 1 prot ip \
+ flower skip_hw ip_tos 125 action pass
+
+ do_test_pedit_dsfield_common "$locus" "set DSCP + set ECN" \
+ "-A 192.0.2.1 -B 192.0.2.2"
+
+ tc filter del dev $h2 ingress pref 1
+ tc filter del $locus pref 1
+}
+
+test_ip_dscp_ecn()
+{
+ do_test_ip_dscp_ecn "dev $swp1 ingress"
+ do_test_ip_dscp_ecn "dev $swp2 egress"
+}
+
+do_test_ip6_dsfield()
+{
+ local locus=$1; shift
+ local dsfield
+
+ for dsfield in 0 1 2 3 128 252 253 254 255; do
+ do_test_pedit_dsfield "$locus" \
+ "ip6 traffic_class set $dsfield" \
+ ipv6 "ip_tos $dsfield" \
+ "-6 -A 2001:db8:1::1 -B 2001:db8:1::2"
+ done
+}
+
+test_ip6_dsfield()
+{
+ do_test_ip6_dsfield "dev $swp1 ingress"
+ do_test_ip6_dsfield "dev $swp2 egress"
+}
+
+do_test_ip6_dscp()
+{
+ local locus=$1; shift
+ local dscp
+
+ for dscp in 0 1 2 3 32 61 62 63; do
+ do_test_pedit_dsfield "$locus" \
+ "ip6 traffic_class set $((dscp << 2)) retain 0xfc" \
+ ipv6 "ip_tos $(((dscp << 2) | 1))" \
+ "-6 -A 2001:db8:1::1 -B 2001:db8:1::2"
+ done
+}
+
+test_ip6_dscp()
+{
+ do_test_ip6_dscp "dev $swp1 ingress"
+ do_test_ip6_dscp "dev $swp2 egress"
+}
+
+do_test_ip6_ecn()
+{
+ local locus=$1; shift
+ local ecn
+
+ for ecn in 0 1 2 3; do
+ do_test_pedit_dsfield "$locus" \
+ "ip6 traffic_class set $ecn retain 0x3" \
+ ipv6 "ip_tos $((124 | $ecn))" \
+ "-6 -A 2001:db8:1::1 -B 2001:db8:1::2"
+ done
+}
+
+test_ip6_ecn()
+{
+ do_test_ip6_ecn "dev $swp1 ingress"
+ do_test_ip6_ecn "dev $swp2 egress"
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/sch_ets.sh b/tools/testing/selftests/net/forwarding/sch_ets.sh
index 40e0ad1bc4f2..e60c8b4818cc 100755
--- a/tools/testing/selftests/net/forwarding/sch_ets.sh
+++ b/tools/testing/selftests/net/forwarding/sch_ets.sh
@@ -34,11 +34,14 @@ switch_destroy()
}
# Callback from sch_ets_tests.sh
-get_stats()
+collect_stats()
{
- local stream=$1; shift
+ local -a streams=("$@")
+ local stream
- link_stats_get $h2.1$stream rx bytes
+ for stream in ${streams[@]}; do
+ qdisc_parent_stats_get $swp2 10:$((stream + 1)) .bytes
+ done
}
ets_run
diff --git a/tools/testing/selftests/net/forwarding/sch_ets_tests.sh b/tools/testing/selftests/net/forwarding/sch_ets_tests.sh
index 3c3b204d47e8..cdf689e99458 100644
--- a/tools/testing/selftests/net/forwarding/sch_ets_tests.sh
+++ b/tools/testing/selftests/net/forwarding/sch_ets_tests.sh
@@ -2,7 +2,7 @@
# Global interface:
# $put -- port under test (e.g. $swp2)
-# get_stats($band) -- A function to collect stats for band
+# collect_stats($streams...) -- A function to get stats for individual streams
# ets_start_traffic($band) -- Start traffic for this band
# ets_change_qdisc($op, $dev, $nstrict, $quanta...) -- Add or change qdisc
@@ -94,15 +94,11 @@ __ets_dwrr_test()
sleep 10
- t0=($(for stream in ${streams[@]}; do
- get_stats $stream
- done))
+ t0=($(collect_stats "${streams[@]}"))
sleep 10
- t1=($(for stream in ${streams[@]}; do
- get_stats $stream
- done))
+ t1=($(collect_stats "${streams[@]}"))
d=($(for ((i = 0; i < ${#streams[@]}; i++)); do
echo $((${t1[$i]} - ${t0[$i]}))
done))
diff --git a/tools/testing/selftests/net/forwarding/skbedit_priority.sh b/tools/testing/selftests/net/forwarding/skbedit_priority.sh
new file mode 100755
index 000000000000..e3bd8a6bb8b4
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/skbedit_priority.sh
@@ -0,0 +1,168 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# This test sends traffic from H1 to H2. Either on ingress of $swp1, or on
+# egress of $swp2, the traffic is acted upon by an action skbedit priority. The
+# new priority should be taken into account when classifying traffic on the PRIO
+# qdisc at $swp2. The test verifies that for different priority values, the
+# traffic ends up in expected PRIO band.
+#
+# +----------------------+ +----------------------+
+# | H1 | | H2 |
+# | + $h1 | | $h2 + |
+# | | 192.0.2.1/28 | | 192.0.2.2/28 | |
+# +----|-----------------+ +----------------|-----+
+# | |
+# +----|----------------------------------------------------------------|-----+
+# | SW | | |
+# | +-|----------------------------------------------------------------|-+ |
+# | | + $swp1 BR $swp2 + | |
+# | | PRIO | |
+# | +--------------------------------------------------------------------+ |
+# +---------------------------------------------------------------------------+
+
+ALL_TESTS="
+ ping_ipv4
+ test_ingress
+ test_egress
+"
+
+NUM_NETIFS=4
+source lib.sh
+
+: ${HIT_TIMEOUT:=2000} # ms
+
+h1_create()
+{
+ simple_if_init $h1 192.0.2.1/28
+}
+
+h1_destroy()
+{
+ simple_if_fini $h1 192.0.2.1/28
+}
+
+h2_create()
+{
+ simple_if_init $h2 192.0.2.2/28
+}
+
+h2_destroy()
+{
+ simple_if_fini $h2 192.0.2.2/28
+}
+
+switch_create()
+{
+ ip link add name br1 up type bridge vlan_filtering 1
+ ip link set dev $swp1 master br1
+ ip link set dev $swp1 up
+ ip link set dev $swp2 master br1
+ ip link set dev $swp2 up
+
+ tc qdisc add dev $swp1 clsact
+ tc qdisc add dev $swp2 clsact
+ tc qdisc add dev $swp2 root handle 10: \
+ prio bands 8 priomap 7 6 5 4 3 2 1 0
+}
+
+switch_destroy()
+{
+ tc qdisc del dev $swp2 root
+ tc qdisc del dev $swp2 clsact
+ tc qdisc del dev $swp1 clsact
+
+ ip link set dev $swp2 nomaster
+ ip link set dev $swp1 nomaster
+ ip link del dev br1
+}
+
+setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ swp1=${NETIFS[p2]}
+
+ swp2=${NETIFS[p3]}
+ h2=${NETIFS[p4]}
+
+ h2mac=$(mac_get $h2)
+
+ vrf_prepare
+ h1_create
+ h2_create
+ switch_create
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ switch_destroy
+ h2_destroy
+ h1_destroy
+ vrf_cleanup
+}
+
+ping_ipv4()
+{
+ ping_test $h1 192.0.2.2
+}
+
+test_skbedit_priority_one()
+{
+ local locus=$1; shift
+ local prio=$1; shift
+ local classid=$1; shift
+
+ RET=0
+
+ tc filter add $locus handle 101 pref 1 \
+ flower action skbedit priority $prio
+
+ local pkt0=$(qdisc_parent_stats_get $swp2 $classid .packets)
+ local pkt2=$(tc_rule_handle_stats_get "$locus" 101)
+ $MZ $h1 -t udp "sp=54321,dp=12345" -c 10 -d 20msec -p 100 \
+ -a own -b $h2mac -A 192.0.2.1 -B 192.0.2.2 -q
+
+ local pkt1
+ pkt1=$(busywait "$HIT_TIMEOUT" until_counter_is ">= $((pkt0 + 10))" \
+ qdisc_parent_stats_get $swp2 $classid .packets)
+ check_err $? "Expected to get 10 packets on class $classid, but got $((pkt1 - pkt0))."
+
+ local pkt3=$(tc_rule_handle_stats_get "$locus" 101)
+ ((pkt3 >= pkt2 + 10))
+ check_err $? "Expected to get 10 packets on skbedit rule but got $((pkt3 - pkt2))."
+
+ log_test "$locus skbedit priority $prio -> classid $classid"
+
+ tc filter del $locus pref 1
+}
+
+test_ingress()
+{
+ local prio
+
+ for prio in {0..7}; do
+ test_skbedit_priority_one "dev $swp1 ingress" \
+ $prio 10:$((8 - prio))
+ done
+}
+
+test_egress()
+{
+ local prio
+
+ for prio in {0..7}; do
+ test_skbedit_priority_one "dev $swp2 egress" \
+ $prio 10:$((8 - prio))
+ done
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/tc_actions.sh b/tools/testing/selftests/net/forwarding/tc_actions.sh
index 813d02d1939d..d9eca227136b 100755
--- a/tools/testing/selftests/net/forwarding/tc_actions.sh
+++ b/tools/testing/selftests/net/forwarding/tc_actions.sh
@@ -2,7 +2,8 @@
# SPDX-License-Identifier: GPL-2.0
ALL_TESTS="gact_drop_and_ok_test mirred_egress_redirect_test \
- mirred_egress_mirror_test gact_trap_test"
+ mirred_egress_mirror_test matchall_mirred_egress_mirror_test \
+ gact_trap_test"
NUM_NETIFS=4
source tc_common.sh
source lib.sh
@@ -50,6 +51,9 @@ switch_destroy()
mirred_egress_test()
{
local action=$1
+ local protocol=$2
+ local classifier=$3
+ local classifier_args=$4
RET=0
@@ -62,9 +66,9 @@ mirred_egress_test()
tc_check_packets "dev $h2 ingress" 101 1
check_fail $? "Matched without redirect rule inserted"
- tc filter add dev $swp1 ingress protocol ip pref 1 handle 101 flower \
- $tcflags dst_ip 192.0.2.2 action mirred egress $action \
- dev $swp2
+ tc filter add dev $swp1 ingress protocol $protocol pref 1 handle 101 \
+ $classifier $tcflags $classifier_args \
+ action mirred egress $action dev $swp2
$MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
-t ip -q
@@ -72,10 +76,11 @@ mirred_egress_test()
tc_check_packets "dev $h2 ingress" 101 1
check_err $? "Did not match incoming $action packet"
- tc filter del dev $swp1 ingress protocol ip pref 1 handle 101 flower
+ tc filter del dev $swp1 ingress protocol $protocol pref 1 handle 101 \
+ $classifier
tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower
- log_test "mirred egress $action ($tcflags)"
+ log_test "mirred egress $classifier $action ($tcflags)"
}
gact_drop_and_ok_test()
@@ -187,12 +192,17 @@ cleanup()
mirred_egress_redirect_test()
{
- mirred_egress_test "redirect"
+ mirred_egress_test "redirect" "ip" "flower" "dst_ip 192.0.2.2"
}
mirred_egress_mirror_test()
{
- mirred_egress_test "mirror"
+ mirred_egress_test "mirror" "ip" "flower" "dst_ip 192.0.2.2"
+}
+
+matchall_mirred_egress_mirror_test()
+{
+ mirred_egress_test "mirror" "all" "matchall" ""
}
trap cleanup EXIT
diff --git a/tools/testing/selftests/net/forwarding/tc_common.sh b/tools/testing/selftests/net/forwarding/tc_common.sh
index 64f652633585..0e18e8be6e2a 100644
--- a/tools/testing/selftests/net/forwarding/tc_common.sh
+++ b/tools/testing/selftests/net/forwarding/tc_common.sh
@@ -6,39 +6,14 @@ CHECK_TC="yes"
# Can be overridden by the configuration file. See lib.sh
TC_HIT_TIMEOUT=${TC_HIT_TIMEOUT:=1000} # ms
-__tc_check_packets()
-{
- local id=$1
- local handle=$2
- local count=$3
- local operator=$4
-
- start_time="$(date -u +%s%3N)"
- while true
- do
- cmd_jq "tc -j -s filter show $id" \
- ".[] | select(.options.handle == $handle) | \
- select(.options.actions[0].stats.packets $operator $count)" \
- &> /dev/null
- ret=$?
- if [[ $ret -eq 0 ]]; then
- return $ret
- fi
- current_time="$(date -u +%s%3N)"
- diff=$(expr $current_time - $start_time)
- if [ "$diff" -gt "$TC_HIT_TIMEOUT" ]; then
- return 1
- fi
- done
-}
-
tc_check_packets()
{
local id=$1
local handle=$2
local count=$3
- __tc_check_packets "$id" "$handle" "$count" "=="
+ busywait "$TC_HIT_TIMEOUT" until_counter_is "== $count" \
+ tc_rule_handle_stats_get "$id" "$handle" > /dev/null
}
tc_check_packets_hitting()
@@ -46,5 +21,6 @@ tc_check_packets_hitting()
local id=$1
local handle=$2
- __tc_check_packets "$id" "$handle" 0 ">"
+ busywait "$TC_HIT_TIMEOUT" until_counter_is "> 0" \
+ tc_rule_handle_stats_get "$id" "$handle" > /dev/null
}
diff --git a/tools/testing/selftests/networking/timestamping/hwtstamp_config.c b/tools/testing/selftests/net/hwtstamp_config.c
index e1fdee841021..e1fdee841021 100644
--- a/tools/testing/selftests/networking/timestamping/hwtstamp_config.c
+++ b/tools/testing/selftests/net/hwtstamp_config.c
diff --git a/tools/testing/selftests/net/ip_defrag.c b/tools/testing/selftests/net/ip_defrag.c
index c0c9ecb891e1..f9ed749fd8c7 100644
--- a/tools/testing/selftests/net/ip_defrag.c
+++ b/tools/testing/selftests/net/ip_defrag.c
@@ -192,9 +192,9 @@ static void send_fragment(int fd_raw, struct sockaddr *addr, socklen_t alen,
}
res = sendto(fd_raw, ip_frame, frag_len, 0, addr, alen);
- if (res < 0)
+ if (res < 0 && errno != EPERM)
error(1, errno, "send_fragment");
- if (res != frag_len)
+ if (res >= 0 && res != frag_len)
error(1, 0, "send_fragment: %d vs %d", res, frag_len);
frag_counter++;
@@ -313,9 +313,9 @@ static void send_udp_frags(int fd_raw, struct sockaddr *addr,
iphdr->ip_len = htons(frag_len);
}
res = sendto(fd_raw, ip_frame, frag_len, 0, addr, alen);
- if (res < 0)
+ if (res < 0 && errno != EPERM)
error(1, errno, "sendto overlap: %d", frag_len);
- if (res != frag_len)
+ if (res >= 0 && res != frag_len)
error(1, 0, "sendto overlap: %d vs %d", (int)res, frag_len);
frag_counter++;
}
diff --git a/tools/testing/selftests/net/mptcp/.gitignore b/tools/testing/selftests/net/mptcp/.gitignore
index d72f07642738..260336d5f0b1 100644
--- a/tools/testing/selftests/net/mptcp/.gitignore
+++ b/tools/testing/selftests/net/mptcp/.gitignore
@@ -1,2 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
mptcp_connect
+pm_nl_ctl
*.pcap
diff --git a/tools/testing/selftests/net/mptcp/Makefile b/tools/testing/selftests/net/mptcp/Makefile
index ba450e62dc5b..f50976ee7d44 100644
--- a/tools/testing/selftests/net/mptcp/Makefile
+++ b/tools/testing/selftests/net/mptcp/Makefile
@@ -1,12 +1,13 @@
# SPDX-License-Identifier: GPL-2.0
top_srcdir = ../../../../..
+KSFT_KHDR_INSTALL := 1
-CFLAGS = -Wall -Wl,--no-as-needed -O2 -g
+CFLAGS = -Wall -Wl,--no-as-needed -O2 -g -I$(top_srcdir)/usr/include
-TEST_PROGS := mptcp_connect.sh
+TEST_PROGS := mptcp_connect.sh pm_netlink.sh mptcp_join.sh
-TEST_GEN_FILES = mptcp_connect
+TEST_GEN_FILES = mptcp_connect pm_nl_ctl
TEST_FILES := settings
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c
index 99579c0223c1..cedee5b952ba 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c
@@ -34,8 +34,8 @@ extern int optind;
#define TCP_ULP 31
#endif
+static int poll_timeout = 10 * 1000;
static bool listen_mode;
-static int poll_timeout;
enum cfg_mode {
CFG_MODE_POLL,
@@ -50,11 +50,21 @@ static int cfg_sock_proto = IPPROTO_MPTCP;
static bool tcpulp_audit;
static int pf = AF_INET;
static int cfg_sndbuf;
+static int cfg_rcvbuf;
+static bool cfg_join;
static void die_usage(void)
{
- fprintf(stderr, "Usage: mptcp_connect [-6] [-u] [-s MPTCP|TCP] [-p port] -m mode]"
- "[ -l ] [ -t timeout ] connect_address\n");
+ fprintf(stderr, "Usage: mptcp_connect [-6] [-u] [-s MPTCP|TCP] [-p port] [-m mode]"
+ "[-l] connect_address\n");
+ fprintf(stderr, "\t-6 use ipv6\n");
+ fprintf(stderr, "\t-t num -- set poll timeout to num\n");
+ fprintf(stderr, "\t-S num -- set SO_SNDBUF to num\n");
+ fprintf(stderr, "\t-R num -- set SO_RCVBUF to num\n");
+ fprintf(stderr, "\t-p num -- use port num\n");
+ fprintf(stderr, "\t-m [MPTCP|TCP] -- use tcp or mptcp sockets\n");
+ fprintf(stderr, "\t-s [mmap|poll] -- use poll (default) or mmap\n");
+ fprintf(stderr, "\t-u -- check mptcp ulp\n");
exit(1);
}
@@ -97,6 +107,17 @@ static void xgetaddrinfo(const char *node, const char *service,
}
}
+static void set_rcvbuf(int fd, unsigned int size)
+{
+ int err;
+
+ err = setsockopt(fd, SOL_SOCKET, SO_RCVBUF, &size, sizeof(size));
+ if (err) {
+ perror("set SO_RCVBUF");
+ exit(1);
+ }
+}
+
static void set_sndbuf(int fd, unsigned int size)
{
int err;
@@ -230,6 +251,7 @@ static int sock_connect_mptcp(const char * const remoteaddr,
static size_t do_rnd_write(const int fd, char *buf, const size_t len)
{
+ static bool first = true;
unsigned int do_w;
ssize_t bw;
@@ -237,10 +259,19 @@ static size_t do_rnd_write(const int fd, char *buf, const size_t len)
if (do_w == 0 || do_w > len)
do_w = len;
+ if (cfg_join && first && do_w > 100)
+ do_w = 100;
+
bw = write(fd, buf, do_w);
if (bw < 0)
perror("write");
+ /* let the join handshake complete, before going on */
+ if (cfg_join && first) {
+ usleep(200000);
+ first = false;
+ }
+
return bw;
}
@@ -365,8 +396,11 @@ static int copyfd_io_poll(int infd, int peerfd, int outfd)
break;
/* ... but we still receive.
- * Close our write side.
+ * Close our write side, ev. give some time
+ * for address notification
*/
+ if (cfg_join)
+ usleep(400000);
shutdown(peerfd, SHUT_WR);
} else {
if (errno == EINTR)
@@ -383,6 +417,10 @@ static int copyfd_io_poll(int infd, int peerfd, int outfd)
}
}
+ /* leave some time for late join/announce */
+ if (cfg_join)
+ usleep(400000);
+
close(peerfd);
return 0;
}
@@ -638,7 +676,7 @@ static void maybe_close(int fd)
{
unsigned int r = rand();
- if (r & 1)
+ if (!cfg_join && (r & 1))
close(fd);
}
@@ -704,6 +742,8 @@ int main_loop(void)
check_getpeername_connect(fd);
+ if (cfg_rcvbuf)
+ set_rcvbuf(fd, cfg_rcvbuf);
if (cfg_sndbuf)
set_sndbuf(fd, cfg_sndbuf);
@@ -745,7 +785,7 @@ int parse_mode(const char *mode)
return 0;
}
-int parse_sndbuf(const char *size)
+static int parse_int(const char *size)
{
unsigned long s;
@@ -765,17 +805,19 @@ int parse_sndbuf(const char *size)
die_usage();
}
- cfg_sndbuf = s;
-
- return 0;
+ return (int)s;
}
static void parse_opts(int argc, char **argv)
{
int c;
- while ((c = getopt(argc, argv, "6lp:s:hut:m:b:")) != -1) {
+ while ((c = getopt(argc, argv, "6jlp:s:hut:m:S:R:")) != -1) {
switch (c) {
+ case 'j':
+ cfg_join = true;
+ cfg_mode = CFG_MODE_POLL;
+ break;
case 'l':
listen_mode = true;
break;
@@ -802,8 +844,11 @@ static void parse_opts(int argc, char **argv)
case 'm':
cfg_mode = parse_mode(optarg);
break;
- case 'b':
- cfg_sndbuf = parse_sndbuf(optarg);
+ case 'S':
+ cfg_sndbuf = parse_int(optarg);
+ break;
+ case 'R':
+ cfg_rcvbuf = parse_int(optarg);
break;
}
}
@@ -831,6 +876,8 @@ int main(int argc, char *argv[])
if (fd < 0)
return 1;
+ if (cfg_rcvbuf)
+ set_rcvbuf(fd, cfg_rcvbuf);
if (cfg_sndbuf)
set_sndbuf(fd, cfg_sndbuf);
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
index d573a0feb98d..acf02e156d20 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
@@ -3,7 +3,7 @@
time_start=$(date +%s)
-optstring="b:d:e:l:r:h4cm:"
+optstring="S:R:d:e:l:r:h4cm:"
ret=0
sin=""
sout=""
@@ -19,6 +19,7 @@ tc_loss=$((RANDOM%101))
tc_reorder=""
testmode=""
sndbuf=0
+rcvbuf=0
options_log=true
if [ $tc_loss -eq 100 ];then
@@ -39,7 +40,8 @@ usage() {
echo -e "\t-e: ethtool features to disable, e.g.: \"-e tso -e gso\" (default: randomly disable any of tso/gso/gro)"
echo -e "\t-4: IPv4 only: disable IPv6 tests (default: test both IPv4 and IPv6)"
echo -e "\t-c: capture packets for each test using tcpdump (default: no capture)"
- echo -e "\t-b: set sndbuf value (default: use kernel default)"
+ echo -e "\t-S: set sndbuf value (default: use kernel default)"
+ echo -e "\t-R: set rcvbuf value (default: use kernel default)"
echo -e "\t-m: test mode (poll, sendfile; default: poll)"
}
@@ -73,11 +75,19 @@ while getopts "$optstring" option;do
"c")
capture=true
;;
- "b")
+ "S")
if [ $OPTARG -ge 0 ];then
sndbuf="$OPTARG"
else
- echo "-s requires numeric argument, got \"$OPTARG\"" 1>&2
+ echo "-S requires numeric argument, got \"$OPTARG\"" 1>&2
+ exit 1
+ fi
+ ;;
+ "R")
+ if [ $OPTARG -ge 0 ];then
+ rcvbuf="$OPTARG"
+ else
+ echo "-R requires numeric argument, got \"$OPTARG\"" 1>&2
exit 1
fi
;;
@@ -342,8 +352,12 @@ do_transfer()
port=$((10000+$TEST_COUNT))
TEST_COUNT=$((TEST_COUNT+1))
+ if [ "$rcvbuf" -gt 0 ]; then
+ extra_args="$extra_args -R $rcvbuf"
+ fi
+
if [ "$sndbuf" -gt 0 ]; then
- extra_args="$extra_args -b $sndbuf"
+ extra_args="$extra_args -S $sndbuf"
fi
if [ -n "$testmode" ]; then
diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
new file mode 100755
index 000000000000..dd42c2f692d0
--- /dev/null
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -0,0 +1,357 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ret=0
+sin=""
+sout=""
+cin=""
+cout=""
+ksft_skip=4
+timeout=30
+capture=0
+
+TEST_COUNT=0
+
+init()
+{
+ capout=$(mktemp)
+
+ rndh=$(printf %x $sec)-$(mktemp -u XXXXXX)
+
+ ns1="ns1-$rndh"
+ ns2="ns2-$rndh"
+
+ for netns in "$ns1" "$ns2";do
+ ip netns add $netns || exit $ksft_skip
+ ip -net $netns link set lo up
+ ip netns exec $netns sysctl -q net.mptcp.enabled=1
+ ip netns exec $netns sysctl -q net.ipv4.conf.all.rp_filter=0
+ ip netns exec $netns sysctl -q net.ipv4.conf.default.rp_filter=0
+ done
+
+ # ns1 ns2
+ # ns1eth1 ns2eth1
+ # ns1eth2 ns2eth2
+ # ns1eth3 ns2eth3
+ # ns1eth4 ns2eth4
+
+ for i in `seq 1 4`; do
+ ip link add ns1eth$i netns "$ns1" type veth peer name ns2eth$i netns "$ns2"
+ ip -net "$ns1" addr add 10.0.$i.1/24 dev ns1eth$i
+ ip -net "$ns1" addr add dead:beef:$i::1/64 dev ns1eth$i nodad
+ ip -net "$ns1" link set ns1eth$i up
+
+ ip -net "$ns2" addr add 10.0.$i.2/24 dev ns2eth$i
+ ip -net "$ns2" addr add dead:beef:$i::2/64 dev ns2eth$i nodad
+ ip -net "$ns2" link set ns2eth$i up
+
+ # let $ns2 reach any $ns1 address from any interface
+ ip -net "$ns2" route add default via 10.0.$i.1 dev ns2eth$i metric 10$i
+ done
+}
+
+cleanup_partial()
+{
+ rm -f "$capout"
+
+ for netns in "$ns1" "$ns2"; do
+ ip netns del $netns
+ done
+}
+
+cleanup()
+{
+ rm -f "$cin" "$cout"
+ rm -f "$sin" "$sout"
+ cleanup_partial
+}
+
+reset()
+{
+ cleanup_partial
+ init
+}
+
+for arg in "$@"; do
+ if [ "$arg" = "-c" ]; then
+ capture=1
+ fi
+done
+
+ip -Version > /dev/null 2>&1
+if [ $? -ne 0 ];then
+ echo "SKIP: Could not run test without ip tool"
+ exit $ksft_skip
+fi
+
+
+check_transfer()
+{
+ in=$1
+ out=$2
+ what=$3
+
+ cmp "$in" "$out" > /dev/null 2>&1
+ if [ $? -ne 0 ] ;then
+ echo "[ FAIL ] $what does not match (in, out):"
+ print_file_err "$in"
+ print_file_err "$out"
+
+ return 1
+ fi
+
+ return 0
+}
+
+do_ping()
+{
+ listener_ns="$1"
+ connector_ns="$2"
+ connect_addr="$3"
+
+ ip netns exec ${connector_ns} ping -q -c 1 $connect_addr >/dev/null
+ if [ $? -ne 0 ] ; then
+ echo "$listener_ns -> $connect_addr connectivity [ FAIL ]" 1>&2
+ ret=1
+ fi
+}
+
+do_transfer()
+{
+ listener_ns="$1"
+ connector_ns="$2"
+ cl_proto="$3"
+ srv_proto="$4"
+ connect_addr="$5"
+
+ port=$((10000+$TEST_COUNT))
+ TEST_COUNT=$((TEST_COUNT+1))
+
+ :> "$cout"
+ :> "$sout"
+ :> "$capout"
+
+ if [ $capture -eq 1 ]; then
+ if [ -z $SUDO_USER ] ; then
+ capuser=""
+ else
+ capuser="-Z $SUDO_USER"
+ fi
+
+ capfile="mp_join-${listener_ns}.pcap"
+
+ echo "Capturing traffic for test $TEST_COUNT into $capfile"
+ ip netns exec ${listener_ns} tcpdump -i any -s 65535 -B 32768 $capuser -w $capfile > "$capout" 2>&1 &
+ cappid=$!
+
+ sleep 1
+ fi
+
+ ip netns exec ${listener_ns} ./mptcp_connect -j -t $timeout -l -p $port -s ${srv_proto} 0.0.0.0 < "$sin" > "$sout" &
+ spid=$!
+
+ sleep 1
+
+ ip netns exec ${connector_ns} ./mptcp_connect -j -t $timeout -p $port -s ${cl_proto} $connect_addr < "$cin" > "$cout" &
+ cpid=$!
+
+ wait $cpid
+ retc=$?
+ wait $spid
+ rets=$?
+
+ if [ $capture -eq 1 ]; then
+ sleep 1
+ kill $cappid
+ fi
+
+ if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ]; then
+ echo " client exit code $retc, server $rets" 1>&2
+ echo "\nnetns ${listener_ns} socket stat for $port:" 1>&2
+ ip netns exec ${listener_ns} ss -nita 1>&2 -o "sport = :$port"
+ echo "\nnetns ${connector_ns} socket stat for $port:" 1>&2
+ ip netns exec ${connector_ns} ss -nita 1>&2 -o "dport = :$port"
+
+ cat "$capout"
+ return 1
+ fi
+
+ check_transfer $sin $cout "file received by client"
+ retc=$?
+ check_transfer $cin $sout "file received by server"
+ rets=$?
+
+ if [ $retc -eq 0 ] && [ $rets -eq 0 ];then
+ cat "$capout"
+ return 0
+ fi
+
+ cat "$capout"
+ return 1
+}
+
+make_file()
+{
+ name=$1
+ who=$2
+
+ SIZE=1
+
+ dd if=/dev/urandom of="$name" bs=1024 count=$SIZE 2> /dev/null
+ echo -e "\nMPTCP_TEST_FILE_END_MARKER" >> "$name"
+
+ echo "Created $name (size $SIZE KB) containing data sent by $who"
+}
+
+run_tests()
+{
+ listener_ns="$1"
+ connector_ns="$2"
+ connect_addr="$3"
+ lret=0
+
+ do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP ${connect_addr}
+ lret=$?
+ if [ $lret -ne 0 ]; then
+ ret=$lret
+ return
+ fi
+}
+
+chk_join_nr()
+{
+ local msg="$1"
+ local syn_nr=$2
+ local syn_ack_nr=$3
+ local ack_nr=$4
+ local count
+ local dump_stats
+
+ printf "%-36s %s" "$msg" "syn"
+ count=`ip netns exec $ns1 nstat -as | grep MPTcpExtMPJoinSynRx | awk '{print $2}'`
+ [ -z "$count" ] && count=0
+ if [ "$count" != "$syn_nr" ]; then
+ echo "[fail] got $count JOIN[s] syn expected $syn_nr"
+ ret=1
+ dump_stats=1
+ else
+ echo -n "[ ok ]"
+ fi
+
+ echo -n " - synack"
+ count=`ip netns exec $ns2 nstat -as | grep MPTcpExtMPJoinSynAckRx | awk '{print $2}'`
+ [ -z "$count" ] && count=0
+ if [ "$count" != "$syn_ack_nr" ]; then
+ echo "[fail] got $count JOIN[s] synack expected $syn_ack_nr"
+ ret=1
+ dump_stats=1
+ else
+ echo -n "[ ok ]"
+ fi
+
+ echo -n " - ack"
+ count=`ip netns exec $ns1 nstat -as | grep MPTcpExtMPJoinAckRx | awk '{print $2}'`
+ [ -z "$count" ] && count=0
+ if [ "$count" != "$ack_nr" ]; then
+ echo "[fail] got $count JOIN[s] ack expected $ack_nr"
+ ret=1
+ dump_stats=1
+ else
+ echo "[ ok ]"
+ fi
+ if [ "${dump_stats}" = 1 ]; then
+ echo Server ns stats
+ ip netns exec $ns1 nstat -as | grep MPTcp
+ echo Client ns stats
+ ip netns exec $ns2 nstat -as | grep MPTcp
+ fi
+}
+
+sin=$(mktemp)
+sout=$(mktemp)
+cin=$(mktemp)
+cout=$(mktemp)
+init
+make_file "$cin" "client"
+make_file "$sin" "server"
+trap cleanup EXIT
+
+run_tests $ns1 $ns2 10.0.1.1
+chk_join_nr "no JOIN" "0" "0" "0"
+
+# subflow limted by client
+reset
+ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
+run_tests $ns1 $ns2 10.0.1.1
+chk_join_nr "single subflow, limited by client" 0 0 0
+
+# subflow limted by server
+reset
+ip netns exec $ns2 ./pm_nl_ctl limits 0 1
+ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
+run_tests $ns1 $ns2 10.0.1.1
+chk_join_nr "single subflow, limited by server" 1 1 0
+
+# subflow
+reset
+ip netns exec $ns1 ./pm_nl_ctl limits 0 1
+ip netns exec $ns2 ./pm_nl_ctl limits 0 1
+ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
+run_tests $ns1 $ns2 10.0.1.1
+chk_join_nr "single subflow" 1 1 1
+
+# multiple subflows
+reset
+ip netns exec $ns1 ./pm_nl_ctl limits 0 2
+ip netns exec $ns2 ./pm_nl_ctl limits 0 2
+ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
+ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow
+run_tests $ns1 $ns2 10.0.1.1
+chk_join_nr "multiple subflows" 2 2 2
+
+# multiple subflows limited by serverf
+reset
+ip netns exec $ns1 ./pm_nl_ctl limits 0 1
+ip netns exec $ns2 ./pm_nl_ctl limits 0 2
+ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
+ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow
+run_tests $ns1 $ns2 10.0.1.1
+chk_join_nr "multiple subflows, limited by server" 2 2 1
+
+# add_address, unused
+reset
+ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal
+run_tests $ns1 $ns2 10.0.1.1
+chk_join_nr "unused signal address" 0 0 0
+
+# accept and use add_addr
+reset
+ip netns exec $ns1 ./pm_nl_ctl limits 0 1
+ip netns exec $ns2 ./pm_nl_ctl limits 1 1
+ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal
+run_tests $ns1 $ns2 10.0.1.1
+chk_join_nr "signal address" 1 1 1
+
+# accept and use add_addr with an additional subflow
+# note: signal address in server ns and local addresses in client ns must
+# belong to different subnets or one of the listed local address could be
+# used for 'add_addr' subflow
+reset
+ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal
+ip netns exec $ns1 ./pm_nl_ctl limits 0 2
+ip netns exec $ns2 ./pm_nl_ctl limits 1 2
+ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
+run_tests $ns1 $ns2 10.0.1.1
+chk_join_nr "subflow and signal" 2 2 2
+
+# accept and use add_addr with additional subflows
+reset
+ip netns exec $ns1 ./pm_nl_ctl limits 0 3
+ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal
+ip netns exec $ns2 ./pm_nl_ctl limits 1 3
+ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
+ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags subflow
+run_tests $ns1 $ns2 10.0.1.1
+chk_join_nr "multiple subflows and signal" 3 3 3
+
+exit $ret
diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh
new file mode 100755
index 000000000000..15f4f46ca3a9
--- /dev/null
+++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh
@@ -0,0 +1,130 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ksft_skip=4
+ret=0
+
+usage() {
+ echo "Usage: $0 [ -h ]"
+}
+
+
+while getopts "$optstring" option;do
+ case "$option" in
+ "h")
+ usage $0
+ exit 0
+ ;;
+ "?")
+ usage $0
+ exit 1
+ ;;
+ esac
+done
+
+sec=$(date +%s)
+rndh=$(printf %x $sec)-$(mktemp -u XXXXXX)
+ns1="ns1-$rndh"
+err=$(mktemp)
+ret=0
+
+cleanup()
+{
+ rm -f $err
+ ip netns del $ns1
+}
+
+ip -Version > /dev/null 2>&1
+if [ $? -ne 0 ];then
+ echo "SKIP: Could not run test without ip tool"
+ exit $ksft_skip
+fi
+
+trap cleanup EXIT
+
+ip netns add $ns1 || exit $ksft_skip
+ip -net $ns1 link set lo up
+ip netns exec $ns1 sysctl -q net.mptcp.enabled=1
+
+check()
+{
+ local cmd="$1"
+ local expected="$2"
+ local msg="$3"
+ local out=`$cmd 2>$err`
+ local cmd_ret=$?
+
+ printf "%-50s %s" "$msg"
+ if [ $cmd_ret -ne 0 ]; then
+ echo "[FAIL] command execution '$cmd' stderr "
+ cat $err
+ ret=1
+ elif [ "$out" = "$expected" ]; then
+ echo "[ OK ]"
+ else
+ echo -n "[FAIL] "
+ echo "expected '$expected' got '$out'"
+ ret=1
+ fi
+}
+
+check "ip netns exec $ns1 ./pm_nl_ctl dump" "" "defaults addr list"
+check "ip netns exec $ns1 ./pm_nl_ctl limits" "accept 0
+subflows 0" "defaults limits"
+
+ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.1
+ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.2 flags subflow dev lo
+ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.3 flags signal,backup
+check "ip netns exec $ns1 ./pm_nl_ctl get 1" "id 1 flags 10.0.1.1" "simple add/get addr"
+
+check "ip netns exec $ns1 ./pm_nl_ctl dump" \
+"id 1 flags 10.0.1.1
+id 2 flags subflow dev lo 10.0.1.2
+id 3 flags signal,backup 10.0.1.3" "dump addrs"
+
+ip netns exec $ns1 ./pm_nl_ctl del 2
+check "ip netns exec $ns1 ./pm_nl_ctl get 2" "" "simple del addr"
+check "ip netns exec $ns1 ./pm_nl_ctl dump" \
+"id 1 flags 10.0.1.1
+id 3 flags signal,backup 10.0.1.3" "dump addrs after del"
+
+ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.3
+check "ip netns exec $ns1 ./pm_nl_ctl get 4" "" "duplicate addr"
+
+ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.4 id 10 flags signal
+check "ip netns exec $ns1 ./pm_nl_ctl get 4" "id 4 flags signal 10.0.1.4" "id addr increment"
+
+for i in `seq 5 9`; do
+ ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.$i flags signal >/dev/null 2>&1
+done
+check "ip netns exec $ns1 ./pm_nl_ctl get 9" "id 9 flags signal 10.0.1.9" "hard addr limit"
+check "ip netns exec $ns1 ./pm_nl_ctl get 10" "" "above hard addr limit"
+
+for i in `seq 9 256`; do
+ ip netns exec $ns1 ./pm_nl_ctl del $i
+ ip netns exec $ns1 ./pm_nl_ctl add 10.0.0.9
+done
+check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags 10.0.1.1
+id 3 flags signal,backup 10.0.1.3
+id 4 flags signal 10.0.1.4
+id 5 flags signal 10.0.1.5
+id 6 flags signal 10.0.1.6
+id 7 flags signal 10.0.1.7
+id 8 flags signal 10.0.1.8" "id limit"
+
+ip netns exec $ns1 ./pm_nl_ctl flush
+check "ip netns exec $ns1 ./pm_nl_ctl dump" "" "flush addrs"
+
+ip netns exec $ns1 ./pm_nl_ctl limits 9 1
+check "ip netns exec $ns1 ./pm_nl_ctl limits" "accept 0
+subflows 0" "rcv addrs above hard limit"
+
+ip netns exec $ns1 ./pm_nl_ctl limits 1 9
+check "ip netns exec $ns1 ./pm_nl_ctl limits" "accept 0
+subflows 0" "subflows above hard limit"
+
+ip netns exec $ns1 ./pm_nl_ctl limits 8 8
+check "ip netns exec $ns1 ./pm_nl_ctl limits" "accept 8
+subflows 8" "set limits"
+
+exit $ret
diff --git a/tools/testing/selftests/net/mptcp/pm_nl_ctl.c b/tools/testing/selftests/net/mptcp/pm_nl_ctl.c
new file mode 100644
index 000000000000..b24a2f17d415
--- /dev/null
+++ b/tools/testing/selftests/net/mptcp/pm_nl_ctl.c
@@ -0,0 +1,616 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <errno.h>
+#include <error.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+
+#include <sys/socket.h>
+#include <sys/types.h>
+
+#include <arpa/inet.h>
+#include <net/if.h>
+
+#include <linux/rtnetlink.h>
+#include <linux/genetlink.h>
+
+#include "linux/mptcp.h"
+
+#ifndef MPTCP_PM_NAME
+#define MPTCP_PM_NAME "mptcp_pm"
+#endif
+
+static void syntax(char *argv[])
+{
+ fprintf(stderr, "%s add|get|del|flush|dump|accept [<args>]\n", argv[0]);
+ fprintf(stderr, "\tadd [flags signal|subflow|backup] [id <nr>] [dev <name>] <ip>\n");
+ fprintf(stderr, "\tdel <id>\n");
+ fprintf(stderr, "\tget <id>\n");
+ fprintf(stderr, "\tflush\n");
+ fprintf(stderr, "\tdump\n");
+ fprintf(stderr, "\tlimits [<rcv addr max> <subflow max>]\n");
+ exit(0);
+}
+
+static int init_genl_req(char *data, int family, int cmd, int version)
+{
+ struct nlmsghdr *nh = (void *)data;
+ struct genlmsghdr *gh;
+ int off = 0;
+
+ nh->nlmsg_type = family;
+ nh->nlmsg_flags = NLM_F_REQUEST;
+ nh->nlmsg_len = NLMSG_LENGTH(GENL_HDRLEN);
+ off += NLMSG_ALIGN(sizeof(*nh));
+
+ gh = (void *)(data + off);
+ gh->cmd = cmd;
+ gh->version = version;
+ off += NLMSG_ALIGN(sizeof(*gh));
+ return off;
+}
+
+static void nl_error(struct nlmsghdr *nh)
+{
+ struct nlmsgerr *err = (struct nlmsgerr *)NLMSG_DATA(nh);
+ int len = nh->nlmsg_len - sizeof(*nh);
+ uint32_t off;
+
+ if (len < sizeof(struct nlmsgerr))
+ error(1, 0, "netlink error message truncated %d min %ld", len,
+ sizeof(struct nlmsgerr));
+
+ if (!err->error) {
+ /* check messages from kernel */
+ struct rtattr *attrs = (struct rtattr *)NLMSG_DATA(nh);
+
+ while (RTA_OK(attrs, len)) {
+ if (attrs->rta_type == NLMSGERR_ATTR_MSG)
+ fprintf(stderr, "netlink ext ack msg: %s\n",
+ (char *)RTA_DATA(attrs));
+ if (attrs->rta_type == NLMSGERR_ATTR_OFFS) {
+ memcpy(&off, RTA_DATA(attrs), 4);
+ fprintf(stderr, "netlink err off %d\n",
+ (int)off);
+ }
+ attrs = RTA_NEXT(attrs, len);
+ }
+ } else {
+ fprintf(stderr, "netlink error %d", err->error);
+ }
+}
+
+/* do a netlink command and, if max > 0, fetch the reply */
+static int do_nl_req(int fd, struct nlmsghdr *nh, int len, int max)
+{
+ struct sockaddr_nl nladdr = { .nl_family = AF_NETLINK };
+ socklen_t addr_len;
+ void *data = nh;
+ int rem, ret;
+ int err = 0;
+
+ nh->nlmsg_len = len;
+ ret = sendto(fd, data, len, 0, (void *)&nladdr, sizeof(nladdr));
+ if (ret != len)
+ error(1, errno, "send netlink: %uB != %uB\n", ret, len);
+ if (max == 0)
+ return 0;
+
+ addr_len = sizeof(nladdr);
+ rem = ret = recvfrom(fd, data, max, 0, (void *)&nladdr, &addr_len);
+ if (ret < 0)
+ error(1, errno, "recv netlink: %uB\n", ret);
+
+ /* Beware: the NLMSG_NEXT macro updates the 'rem' argument */
+ for (; NLMSG_OK(nh, rem); nh = NLMSG_NEXT(nh, rem)) {
+ if (nh->nlmsg_type == NLMSG_ERROR) {
+ nl_error(nh);
+ err = 1;
+ }
+ }
+ if (err)
+ error(1, 0, "bailing out due to netlink error[s]");
+ return ret;
+}
+
+static int genl_parse_getfamily(struct nlmsghdr *nlh)
+{
+ struct genlmsghdr *ghdr = NLMSG_DATA(nlh);
+ int len = nlh->nlmsg_len;
+ struct rtattr *attrs;
+
+ if (nlh->nlmsg_type != GENL_ID_CTRL)
+ error(1, errno, "Not a controller message, len=%d type=0x%x\n",
+ nlh->nlmsg_len, nlh->nlmsg_type);
+
+ len -= NLMSG_LENGTH(GENL_HDRLEN);
+
+ if (len < 0)
+ error(1, errno, "wrong controller message len %d\n", len);
+
+ if (ghdr->cmd != CTRL_CMD_NEWFAMILY)
+ error(1, errno, "Unknown controller command %d\n", ghdr->cmd);
+
+ attrs = (struct rtattr *) ((char *) ghdr + GENL_HDRLEN);
+ while (RTA_OK(attrs, len)) {
+ if (attrs->rta_type == CTRL_ATTR_FAMILY_ID)
+ return *(__u16 *)RTA_DATA(attrs);
+ attrs = RTA_NEXT(attrs, len);
+ }
+
+ error(1, errno, "can't find CTRL_ATTR_FAMILY_ID attr");
+ return -1;
+}
+
+static int resolve_mptcp_pm_netlink(int fd)
+{
+ char data[NLMSG_ALIGN(sizeof(struct nlmsghdr)) +
+ NLMSG_ALIGN(sizeof(struct genlmsghdr)) +
+ 1024];
+ struct nlmsghdr *nh;
+ struct rtattr *rta;
+ int namelen;
+ int off = 0;
+
+ memset(data, 0, sizeof(data));
+ nh = (void *)data;
+ off = init_genl_req(data, GENL_ID_CTRL, CTRL_CMD_GETFAMILY, 0);
+
+ rta = (void *)(data + off);
+ namelen = strlen(MPTCP_PM_NAME) + 1;
+ rta->rta_type = CTRL_ATTR_FAMILY_NAME;
+ rta->rta_len = RTA_LENGTH(namelen);
+ memcpy(RTA_DATA(rta), MPTCP_PM_NAME, namelen);
+ off += NLMSG_ALIGN(rta->rta_len);
+
+ do_nl_req(fd, nh, off, sizeof(data));
+ return genl_parse_getfamily((void *)data);
+}
+
+int add_addr(int fd, int pm_family, int argc, char *argv[])
+{
+ char data[NLMSG_ALIGN(sizeof(struct nlmsghdr)) +
+ NLMSG_ALIGN(sizeof(struct genlmsghdr)) +
+ 1024];
+ struct rtattr *rta, *nest;
+ struct nlmsghdr *nh;
+ u_int16_t family;
+ u_int32_t flags;
+ int nest_start;
+ u_int8_t id;
+ int off = 0;
+ int arg;
+
+ memset(data, 0, sizeof(data));
+ nh = (void *)data;
+ off = init_genl_req(data, pm_family, MPTCP_PM_CMD_ADD_ADDR,
+ MPTCP_PM_VER);
+
+ if (argc < 3)
+ syntax(argv);
+
+ nest_start = off;
+ nest = (void *)(data + off);
+ nest->rta_type = NLA_F_NESTED | MPTCP_PM_ATTR_ADDR;
+ nest->rta_len = RTA_LENGTH(0);
+ off += NLMSG_ALIGN(nest->rta_len);
+
+ /* addr data */
+ rta = (void *)(data + off);
+ if (inet_pton(AF_INET, argv[2], RTA_DATA(rta))) {
+ family = AF_INET;
+ rta->rta_type = MPTCP_PM_ADDR_ATTR_ADDR4;
+ rta->rta_len = RTA_LENGTH(4);
+ } else if (inet_pton(AF_INET6, argv[2], RTA_DATA(rta))) {
+ family = AF_INET6;
+ rta->rta_type = MPTCP_PM_ADDR_ATTR_ADDR6;
+ rta->rta_len = RTA_LENGTH(16);
+ } else
+ error(1, errno, "can't parse ip %s", argv[2]);
+ off += NLMSG_ALIGN(rta->rta_len);
+
+ /* family */
+ rta = (void *)(data + off);
+ rta->rta_type = MPTCP_PM_ADDR_ATTR_FAMILY;
+ rta->rta_len = RTA_LENGTH(2);
+ memcpy(RTA_DATA(rta), &family, 2);
+ off += NLMSG_ALIGN(rta->rta_len);
+
+ for (arg = 3; arg < argc; arg++) {
+ if (!strcmp(argv[arg], "flags")) {
+ char *tok, *str;
+
+ /* flags */
+ flags = 0;
+ if (++arg >= argc)
+ error(1, 0, " missing flags value");
+
+ /* do not support flag list yet */
+ for (str = argv[arg]; (tok = strtok(str, ","));
+ str = NULL) {
+ if (!strcmp(tok, "subflow"))
+ flags |= MPTCP_PM_ADDR_FLAG_SUBFLOW;
+ else if (!strcmp(tok, "signal"))
+ flags |= MPTCP_PM_ADDR_FLAG_SIGNAL;
+ else if (!strcmp(tok, "backup"))
+ flags |= MPTCP_PM_ADDR_FLAG_BACKUP;
+ else
+ error(1, errno,
+ "unknown flag %s", argv[arg]);
+ }
+
+ rta = (void *)(data + off);
+ rta->rta_type = MPTCP_PM_ADDR_ATTR_FLAGS;
+ rta->rta_len = RTA_LENGTH(4);
+ memcpy(RTA_DATA(rta), &flags, 4);
+ off += NLMSG_ALIGN(rta->rta_len);
+ } else if (!strcmp(argv[arg], "id")) {
+ if (++arg >= argc)
+ error(1, 0, " missing id value");
+
+ id = atoi(argv[arg]);
+ rta = (void *)(data + off);
+ rta->rta_type = MPTCP_PM_ADDR_ATTR_ID;
+ rta->rta_len = RTA_LENGTH(1);
+ memcpy(RTA_DATA(rta), &id, 1);
+ off += NLMSG_ALIGN(rta->rta_len);
+ } else if (!strcmp(argv[arg], "dev")) {
+ int32_t ifindex;
+
+ if (++arg >= argc)
+ error(1, 0, " missing dev name");
+
+ ifindex = if_nametoindex(argv[arg]);
+ if (!ifindex)
+ error(1, errno, "unknown device %s", argv[arg]);
+
+ rta = (void *)(data + off);
+ rta->rta_type = MPTCP_PM_ADDR_ATTR_IF_IDX;
+ rta->rta_len = RTA_LENGTH(4);
+ memcpy(RTA_DATA(rta), &ifindex, 4);
+ off += NLMSG_ALIGN(rta->rta_len);
+ } else
+ error(1, 0, "unknown keyword %s", argv[arg]);
+ }
+ nest->rta_len = off - nest_start;
+
+ do_nl_req(fd, nh, off, 0);
+ return 0;
+}
+
+int del_addr(int fd, int pm_family, int argc, char *argv[])
+{
+ char data[NLMSG_ALIGN(sizeof(struct nlmsghdr)) +
+ NLMSG_ALIGN(sizeof(struct genlmsghdr)) +
+ 1024];
+ struct rtattr *rta, *nest;
+ struct nlmsghdr *nh;
+ int nest_start;
+ u_int8_t id;
+ int off = 0;
+
+ memset(data, 0, sizeof(data));
+ nh = (void *)data;
+ off = init_genl_req(data, pm_family, MPTCP_PM_CMD_DEL_ADDR,
+ MPTCP_PM_VER);
+
+ /* the only argument is the address id */
+ if (argc != 3)
+ syntax(argv);
+
+ id = atoi(argv[2]);
+
+ nest_start = off;
+ nest = (void *)(data + off);
+ nest->rta_type = NLA_F_NESTED | MPTCP_PM_ATTR_ADDR;
+ nest->rta_len = RTA_LENGTH(0);
+ off += NLMSG_ALIGN(nest->rta_len);
+
+ /* build a dummy addr with only the ID set */
+ rta = (void *)(data + off);
+ rta->rta_type = MPTCP_PM_ADDR_ATTR_ID;
+ rta->rta_len = RTA_LENGTH(1);
+ memcpy(RTA_DATA(rta), &id, 1);
+ off += NLMSG_ALIGN(rta->rta_len);
+ nest->rta_len = off - nest_start;
+
+ do_nl_req(fd, nh, off, 0);
+ return 0;
+}
+
+static void print_addr(struct rtattr *attrs, int len)
+{
+ uint16_t family = 0;
+ char str[1024];
+ uint32_t flags;
+ uint8_t id;
+
+ while (RTA_OK(attrs, len)) {
+ if (attrs->rta_type == MPTCP_PM_ADDR_ATTR_FAMILY)
+ memcpy(&family, RTA_DATA(attrs), 2);
+ if (attrs->rta_type == MPTCP_PM_ADDR_ATTR_ADDR4) {
+ if (family != AF_INET)
+ error(1, errno, "wrong IP (v4) for family %d",
+ family);
+ inet_ntop(AF_INET, RTA_DATA(attrs), str, sizeof(str));
+ printf("%s", str);
+ }
+ if (attrs->rta_type == MPTCP_PM_ADDR_ATTR_ADDR6) {
+ if (family != AF_INET6)
+ error(1, errno, "wrong IP (v6) for family %d",
+ family);
+ inet_ntop(AF_INET6, RTA_DATA(attrs), str, sizeof(str));
+ printf("%s", str);
+ }
+ if (attrs->rta_type == MPTCP_PM_ADDR_ATTR_ID) {
+ memcpy(&id, RTA_DATA(attrs), 1);
+ printf("id %d ", id);
+ }
+ if (attrs->rta_type == MPTCP_PM_ADDR_ATTR_FLAGS) {
+ memcpy(&flags, RTA_DATA(attrs), 4);
+
+ printf("flags ");
+ if (flags & MPTCP_PM_ADDR_FLAG_SIGNAL) {
+ printf("signal");
+ flags &= ~MPTCP_PM_ADDR_FLAG_SIGNAL;
+ if (flags)
+ printf(",");
+ }
+
+ if (flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) {
+ printf("subflow");
+ flags &= ~MPTCP_PM_ADDR_FLAG_SUBFLOW;
+ if (flags)
+ printf(",");
+ }
+
+ if (flags & MPTCP_PM_ADDR_FLAG_BACKUP) {
+ printf("backup");
+ flags &= ~MPTCP_PM_ADDR_FLAG_BACKUP;
+ if (flags)
+ printf(",");
+ }
+
+ /* bump unknown flags, if any */
+ if (flags)
+ printf("0x%x", flags);
+ printf(" ");
+ }
+ if (attrs->rta_type == MPTCP_PM_ADDR_ATTR_IF_IDX) {
+ char name[IF_NAMESIZE], *ret;
+ int32_t ifindex;
+
+ memcpy(&ifindex, RTA_DATA(attrs), 4);
+ ret = if_indextoname(ifindex, name);
+ if (ret)
+ printf("dev %s ", ret);
+ else
+ printf("dev unknown/%d", ifindex);
+ }
+
+ attrs = RTA_NEXT(attrs, len);
+ }
+ printf("\n");
+}
+
+static void print_addrs(struct nlmsghdr *nh, int pm_family, int total_len)
+{
+ struct rtattr *attrs;
+
+ for (; NLMSG_OK(nh, total_len); nh = NLMSG_NEXT(nh, total_len)) {
+ int len = nh->nlmsg_len;
+
+ if (nh->nlmsg_type == NLMSG_DONE)
+ break;
+ if (nh->nlmsg_type == NLMSG_ERROR)
+ nl_error(nh);
+ if (nh->nlmsg_type != pm_family)
+ continue;
+
+ len -= NLMSG_LENGTH(GENL_HDRLEN);
+ attrs = (struct rtattr *) ((char *) NLMSG_DATA(nh) +
+ GENL_HDRLEN);
+ while (RTA_OK(attrs, len)) {
+ if (attrs->rta_type ==
+ (MPTCP_PM_ATTR_ADDR | NLA_F_NESTED))
+ print_addr((void *)RTA_DATA(attrs),
+ attrs->rta_len);
+ attrs = RTA_NEXT(attrs, len);
+ }
+ }
+}
+
+int get_addr(int fd, int pm_family, int argc, char *argv[])
+{
+ char data[NLMSG_ALIGN(sizeof(struct nlmsghdr)) +
+ NLMSG_ALIGN(sizeof(struct genlmsghdr)) +
+ 1024];
+ struct rtattr *rta, *nest;
+ struct nlmsghdr *nh;
+ int nest_start;
+ u_int8_t id;
+ int off = 0;
+
+ memset(data, 0, sizeof(data));
+ nh = (void *)data;
+ off = init_genl_req(data, pm_family, MPTCP_PM_CMD_GET_ADDR,
+ MPTCP_PM_VER);
+
+ /* the only argument is the address id */
+ if (argc != 3)
+ syntax(argv);
+
+ id = atoi(argv[2]);
+
+ nest_start = off;
+ nest = (void *)(data + off);
+ nest->rta_type = NLA_F_NESTED | MPTCP_PM_ATTR_ADDR;
+ nest->rta_len = RTA_LENGTH(0);
+ off += NLMSG_ALIGN(nest->rta_len);
+
+ /* build a dummy addr with only the ID set */
+ rta = (void *)(data + off);
+ rta->rta_type = MPTCP_PM_ADDR_ATTR_ID;
+ rta->rta_len = RTA_LENGTH(1);
+ memcpy(RTA_DATA(rta), &id, 1);
+ off += NLMSG_ALIGN(rta->rta_len);
+ nest->rta_len = off - nest_start;
+
+ print_addrs(nh, pm_family, do_nl_req(fd, nh, off, sizeof(data)));
+ return 0;
+}
+
+int dump_addrs(int fd, int pm_family, int argc, char *argv[])
+{
+ char data[NLMSG_ALIGN(sizeof(struct nlmsghdr)) +
+ NLMSG_ALIGN(sizeof(struct genlmsghdr)) +
+ 1024];
+ pid_t pid = getpid();
+ struct nlmsghdr *nh;
+ int off = 0;
+
+ memset(data, 0, sizeof(data));
+ nh = (void *)data;
+ off = init_genl_req(data, pm_family, MPTCP_PM_CMD_GET_ADDR,
+ MPTCP_PM_VER);
+ nh->nlmsg_flags |= NLM_F_DUMP;
+ nh->nlmsg_seq = 1;
+ nh->nlmsg_pid = pid;
+ nh->nlmsg_len = off;
+
+ print_addrs(nh, pm_family, do_nl_req(fd, nh, off, sizeof(data)));
+ return 0;
+}
+
+int flush_addrs(int fd, int pm_family, int argc, char *argv[])
+{
+ char data[NLMSG_ALIGN(sizeof(struct nlmsghdr)) +
+ NLMSG_ALIGN(sizeof(struct genlmsghdr)) +
+ 1024];
+ struct nlmsghdr *nh;
+ int off = 0;
+
+ memset(data, 0, sizeof(data));
+ nh = (void *)data;
+ off = init_genl_req(data, pm_family, MPTCP_PM_CMD_FLUSH_ADDRS,
+ MPTCP_PM_VER);
+
+ do_nl_req(fd, nh, off, 0);
+ return 0;
+}
+
+static void print_limits(struct nlmsghdr *nh, int pm_family, int total_len)
+{
+ struct rtattr *attrs;
+ uint32_t max;
+
+ for (; NLMSG_OK(nh, total_len); nh = NLMSG_NEXT(nh, total_len)) {
+ int len = nh->nlmsg_len;
+
+ if (nh->nlmsg_type == NLMSG_DONE)
+ break;
+ if (nh->nlmsg_type == NLMSG_ERROR)
+ nl_error(nh);
+ if (nh->nlmsg_type != pm_family)
+ continue;
+
+ len -= NLMSG_LENGTH(GENL_HDRLEN);
+ attrs = (struct rtattr *) ((char *) NLMSG_DATA(nh) +
+ GENL_HDRLEN);
+ while (RTA_OK(attrs, len)) {
+ int type = attrs->rta_type;
+
+ if (type != MPTCP_PM_ATTR_RCV_ADD_ADDRS &&
+ type != MPTCP_PM_ATTR_SUBFLOWS)
+ goto next;
+
+ memcpy(&max, RTA_DATA(attrs), 4);
+ printf("%s %u\n", type == MPTCP_PM_ATTR_SUBFLOWS ?
+ "subflows" : "accept", max);
+
+next:
+ attrs = RTA_NEXT(attrs, len);
+ }
+ }
+}
+
+int get_set_limits(int fd, int pm_family, int argc, char *argv[])
+{
+ char data[NLMSG_ALIGN(sizeof(struct nlmsghdr)) +
+ NLMSG_ALIGN(sizeof(struct genlmsghdr)) +
+ 1024];
+ uint32_t rcv_addr = 0, subflows = 0;
+ int cmd, len = sizeof(data);
+ struct nlmsghdr *nh;
+ int off = 0;
+
+ /* limit */
+ if (argc == 4) {
+ rcv_addr = atoi(argv[2]);
+ subflows = atoi(argv[3]);
+ cmd = MPTCP_PM_CMD_SET_LIMITS;
+ } else {
+ cmd = MPTCP_PM_CMD_GET_LIMITS;
+ }
+
+ memset(data, 0, sizeof(data));
+ nh = (void *)data;
+ off = init_genl_req(data, pm_family, cmd, MPTCP_PM_VER);
+
+ /* limit */
+ if (cmd == MPTCP_PM_CMD_SET_LIMITS) {
+ struct rtattr *rta = (void *)(data + off);
+
+ rta->rta_type = MPTCP_PM_ATTR_RCV_ADD_ADDRS;
+ rta->rta_len = RTA_LENGTH(4);
+ memcpy(RTA_DATA(rta), &rcv_addr, 4);
+ off += NLMSG_ALIGN(rta->rta_len);
+
+ rta = (void *)(data + off);
+ rta->rta_type = MPTCP_PM_ATTR_SUBFLOWS;
+ rta->rta_len = RTA_LENGTH(4);
+ memcpy(RTA_DATA(rta), &subflows, 4);
+ off += NLMSG_ALIGN(rta->rta_len);
+
+ /* do not expect a reply */
+ len = 0;
+ }
+
+ len = do_nl_req(fd, nh, off, len);
+ if (cmd == MPTCP_PM_CMD_GET_LIMITS)
+ print_limits(nh, pm_family, len);
+ return 0;
+}
+
+int main(int argc, char *argv[])
+{
+ int fd, pm_family;
+
+ if (argc < 2)
+ syntax(argv);
+
+ fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_GENERIC);
+ if (fd == -1)
+ error(1, errno, "socket netlink");
+
+ pm_family = resolve_mptcp_pm_netlink(fd);
+
+ if (!strcmp(argv[1], "add"))
+ return add_addr(fd, pm_family, argc, argv);
+ else if (!strcmp(argv[1], "del"))
+ return del_addr(fd, pm_family, argc, argv);
+ else if (!strcmp(argv[1], "flush"))
+ return flush_addrs(fd, pm_family, argc, argv);
+ else if (!strcmp(argv[1], "get"))
+ return get_addr(fd, pm_family, argc, argv);
+ else if (!strcmp(argv[1], "dump"))
+ return dump_addrs(fd, pm_family, argc, argv);
+ else if (!strcmp(argv[1], "limits"))
+ return get_set_limits(fd, pm_family, argc, argv);
+
+ fprintf(stderr, "unknown sub-command: %s", argv[1]);
+ syntax(argv);
+ return 0;
+}
diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index 71a62e7e35b1..77c09cd339c3 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -67,6 +67,10 @@
# Same as pmtu_ipv4_vxlan4, but using a generic UDP IPv4/IPv6
# encapsulation (GUE) over IPv4/IPv6, instead of VXLAN
#
+# - pmtu_ipv{4,6}_ipv{4,6}_exception
+# Same as pmtu_ipv4_vxlan4, but using a IPv4/IPv6 tunnel over IPv4/IPv6,
+# instead of VXLAN
+#
# - pmtu_vti4_exception
# Set up vti tunnel on top of veth, with xfrm states and policies, in two
# namespaces with matching endpoints. Check that route exception is not
@@ -151,6 +155,10 @@ tests="
pmtu_ipv6_gue4_exception IPv6 over gue4: PMTU exceptions 1
pmtu_ipv4_gue6_exception IPv4 over gue6: PMTU exceptions 1
pmtu_ipv6_gue6_exception IPv6 over gue6: PMTU exceptions 1
+ pmtu_ipv4_ipv4_exception IPv4 over IPv4: PMTU exceptions 1
+ pmtu_ipv6_ipv4_exception IPv6 over IPv4: PMTU exceptions 1
+ pmtu_ipv4_ipv6_exception IPv4 over IPv6: PMTU exceptions 1
+ pmtu_ipv6_ipv6_exception IPv6 over IPv6: PMTU exceptions 1
pmtu_vti6_exception vti6: PMTU exceptions 0
pmtu_vti4_exception vti4: PMTU exceptions 0
pmtu_vti4_default_mtu vti4: default MTU assignment 0
@@ -363,6 +371,62 @@ setup_gue66() {
setup_fou_or_gue 6 6 gue
}
+setup_ipvX_over_ipvY() {
+ inner=${1}
+ outer=${2}
+
+ if [ "${outer}" -eq 4 ]; then
+ a_addr="${prefix4}.${a_r1}.1"
+ b_addr="${prefix4}.${b_r1}.1"
+ if [ "${inner}" -eq 4 ]; then
+ type="ipip"
+ mode="ipip"
+ else
+ type="sit"
+ mode="ip6ip"
+ fi
+ else
+ a_addr="${prefix6}:${a_r1}::1"
+ b_addr="${prefix6}:${b_r1}::1"
+ type="ip6tnl"
+ if [ "${inner}" -eq 4 ]; then
+ mode="ipip6"
+ else
+ mode="ip6ip6"
+ fi
+ fi
+
+ run_cmd ${ns_a} ip link add ip_a type ${type} local ${a_addr} remote ${b_addr} mode ${mode} || return 2
+ run_cmd ${ns_b} ip link add ip_b type ${type} local ${b_addr} remote ${a_addr} mode ${mode}
+
+ run_cmd ${ns_a} ip link set ip_a up
+ run_cmd ${ns_b} ip link set ip_b up
+
+ if [ "${inner}" = "4" ]; then
+ run_cmd ${ns_a} ip addr add ${tunnel4_a_addr}/${tunnel4_mask} dev ip_a
+ run_cmd ${ns_b} ip addr add ${tunnel4_b_addr}/${tunnel4_mask} dev ip_b
+ else
+ run_cmd ${ns_a} ip addr add ${tunnel6_a_addr}/${tunnel6_mask} dev ip_a
+ run_cmd ${ns_b} ip addr add ${tunnel6_b_addr}/${tunnel6_mask} dev ip_b
+ fi
+}
+
+setup_ip4ip4() {
+ setup_ipvX_over_ipvY 4 4
+}
+
+setup_ip6ip4() {
+ setup_ipvX_over_ipvY 6 4
+}
+
+setup_ip4ip6() {
+ setup_ipvX_over_ipvY 4 6
+}
+
+setup_ip6ip6() {
+ setup_ipvX_over_ipvY 6 6
+}
+
setup_namespaces() {
for n in ${NS_A} ${NS_B} ${NS_R1} ${NS_R2}; do
ip netns add ${n} || return 1
@@ -908,6 +972,64 @@ test_pmtu_ipv6_gue6_exception() {
test_pmtu_ipvX_over_fouY_or_gueY 6 6 gue
}
+test_pmtu_ipvX_over_ipvY_exception() {
+ inner=${1}
+ outer=${2}
+ ll_mtu=4000
+
+ setup namespaces routing ip${inner}ip${outer} || return 2
+
+ trace "${ns_a}" ip_a "${ns_b}" ip_b \
+ "${ns_a}" veth_A-R1 "${ns_r1}" veth_R1-A \
+ "${ns_b}" veth_B-R1 "${ns_r1}" veth_R1-B
+
+ if [ ${inner} -eq 4 ]; then
+ ping=ping
+ dst=${tunnel4_b_addr}
+ else
+ ping=${ping6}
+ dst=${tunnel6_b_addr}
+ fi
+
+ if [ ${outer} -eq 4 ]; then
+ # IPv4 header
+ exp_mtu=$((${ll_mtu} - 20))
+ else
+ # IPv6 header Option 4
+ exp_mtu=$((${ll_mtu} - 40 - 8))
+ fi
+
+ # Create route exception by exceeding link layer MTU
+ mtu "${ns_a}" veth_A-R1 $((${ll_mtu} + 1000))
+ mtu "${ns_r1}" veth_R1-A $((${ll_mtu} + 1000))
+ mtu "${ns_b}" veth_B-R1 ${ll_mtu}
+ mtu "${ns_r1}" veth_R1-B ${ll_mtu}
+
+ mtu "${ns_a}" ip_a $((${ll_mtu} + 1000)) || return
+ mtu "${ns_b}" ip_b $((${ll_mtu} + 1000)) || return
+ run_cmd ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s $((${ll_mtu} + 500)) ${dst}
+
+ # Check that exception was created
+ pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst})"
+ check_pmtu_value ${exp_mtu} "${pmtu}" "exceeding link layer MTU on ip${inner}ip${outer} interface"
+}
+
+test_pmtu_ipv4_ipv4_exception() {
+ test_pmtu_ipvX_over_ipvY_exception 4 4
+}
+
+test_pmtu_ipv6_ipv4_exception() {
+ test_pmtu_ipvX_over_ipvY_exception 6 4
+}
+
+test_pmtu_ipv4_ipv6_exception() {
+ test_pmtu_ipvX_over_ipvY_exception 4 6
+}
+
+test_pmtu_ipv6_ipv6_exception() {
+ test_pmtu_ipvX_over_ipvY_exception 6 6
+}
+
test_pmtu_vti4_exception() {
setup namespaces veth vti4 xfrm4 || return 2
trace "${ns_a}" veth_a "${ns_b}" veth_b \
diff --git a/tools/testing/selftests/net/reuseaddr_ports_exhausted.c b/tools/testing/selftests/net/reuseaddr_ports_exhausted.c
new file mode 100644
index 000000000000..7b01b7c2ec10
--- /dev/null
+++ b/tools/testing/selftests/net/reuseaddr_ports_exhausted.c
@@ -0,0 +1,162 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Check if we can fully utilize 4-tuples for connect().
+ *
+ * Rules to bind sockets to the same port when all ephemeral ports are
+ * exhausted.
+ *
+ * 1. if there are TCP_LISTEN sockets on the port, fail to bind.
+ * 2. if there are sockets without SO_REUSEADDR, fail to bind.
+ * 3. if SO_REUSEADDR is disabled, fail to bind.
+ * 4. if SO_REUSEADDR is enabled and SO_REUSEPORT is disabled,
+ * succeed to bind.
+ * 5. if SO_REUSEADDR and SO_REUSEPORT are enabled and
+ * there is no socket having the both options and the same EUID,
+ * succeed to bind.
+ * 6. fail to bind.
+ *
+ * Author: Kuniyuki Iwashima <kuniyu@amazon.co.jp>
+ */
+#include <arpa/inet.h>
+#include <netinet/in.h>
+#include <sys/socket.h>
+#include <sys/types.h>
+#include <unistd.h>
+#include "../kselftest_harness.h"
+
+struct reuse_opts {
+ int reuseaddr[2];
+ int reuseport[2];
+};
+
+struct reuse_opts unreusable_opts[12] = {
+ {0, 0, 0, 0},
+ {0, 0, 0, 1},
+ {0, 0, 1, 0},
+ {0, 0, 1, 1},
+ {0, 1, 0, 0},
+ {0, 1, 0, 1},
+ {0, 1, 1, 0},
+ {0, 1, 1, 1},
+ {1, 0, 0, 0},
+ {1, 0, 0, 1},
+ {1, 0, 1, 0},
+ {1, 0, 1, 1},
+};
+
+struct reuse_opts reusable_opts[4] = {
+ {1, 1, 0, 0},
+ {1, 1, 0, 1},
+ {1, 1, 1, 0},
+ {1, 1, 1, 1},
+};
+
+int bind_port(struct __test_metadata *_metadata, int reuseaddr, int reuseport)
+{
+ struct sockaddr_in local_addr;
+ int len = sizeof(local_addr);
+ int fd, ret;
+
+ fd = socket(AF_INET, SOCK_STREAM, 0);
+ ASSERT_NE(-1, fd) TH_LOG("failed to open socket.");
+
+ ret = setsockopt(fd, SOL_SOCKET, SO_REUSEADDR, &reuseaddr, sizeof(int));
+ ASSERT_EQ(0, ret) TH_LOG("failed to setsockopt: SO_REUSEADDR.");
+
+ ret = setsockopt(fd, SOL_SOCKET, SO_REUSEPORT, &reuseport, sizeof(int));
+ ASSERT_EQ(0, ret) TH_LOG("failed to setsockopt: SO_REUSEPORT.");
+
+ local_addr.sin_family = AF_INET;
+ local_addr.sin_addr.s_addr = inet_addr("127.0.0.1");
+ local_addr.sin_port = 0;
+
+ if (bind(fd, (struct sockaddr *)&local_addr, len) == -1) {
+ close(fd);
+ return -1;
+ }
+
+ return fd;
+}
+
+TEST(reuseaddr_ports_exhausted_unreusable)
+{
+ struct reuse_opts *opts;
+ int i, j, fd[2];
+
+ for (i = 0; i < 12; i++) {
+ opts = &unreusable_opts[i];
+
+ for (j = 0; j < 2; j++)
+ fd[j] = bind_port(_metadata, opts->reuseaddr[j], opts->reuseport[j]);
+
+ ASSERT_NE(-1, fd[0]) TH_LOG("failed to bind.");
+ EXPECT_EQ(-1, fd[1]) TH_LOG("should fail to bind.");
+
+ for (j = 0; j < 2; j++)
+ if (fd[j] != -1)
+ close(fd[j]);
+ }
+}
+
+TEST(reuseaddr_ports_exhausted_reusable_same_euid)
+{
+ struct reuse_opts *opts;
+ int i, j, fd[2];
+
+ for (i = 0; i < 4; i++) {
+ opts = &reusable_opts[i];
+
+ for (j = 0; j < 2; j++)
+ fd[j] = bind_port(_metadata, opts->reuseaddr[j], opts->reuseport[j]);
+
+ ASSERT_NE(-1, fd[0]) TH_LOG("failed to bind.");
+
+ if (opts->reuseport[0] && opts->reuseport[1]) {
+ EXPECT_EQ(-1, fd[1]) TH_LOG("should fail to bind because both sockets succeed to be listened.");
+ } else {
+ EXPECT_NE(-1, fd[1]) TH_LOG("should succeed to bind to connect to different destinations.");
+ }
+
+ for (j = 0; j < 2; j++)
+ if (fd[j] != -1)
+ close(fd[j]);
+ }
+}
+
+TEST(reuseaddr_ports_exhausted_reusable_different_euid)
+{
+ struct reuse_opts *opts;
+ int i, j, ret, fd[2];
+ uid_t euid[2] = {10, 20};
+
+ for (i = 0; i < 4; i++) {
+ opts = &reusable_opts[i];
+
+ for (j = 0; j < 2; j++) {
+ ret = seteuid(euid[j]);
+ ASSERT_EQ(0, ret) TH_LOG("failed to seteuid: %d.", euid[j]);
+
+ fd[j] = bind_port(_metadata, opts->reuseaddr[j], opts->reuseport[j]);
+
+ ret = seteuid(0);
+ ASSERT_EQ(0, ret) TH_LOG("failed to seteuid: 0.");
+ }
+
+ ASSERT_NE(-1, fd[0]) TH_LOG("failed to bind.");
+ EXPECT_NE(-1, fd[1]) TH_LOG("should succeed to bind because one socket can be bound in each euid.");
+
+ if (fd[1] != -1) {
+ ret = listen(fd[0], 5);
+ ASSERT_EQ(0, ret) TH_LOG("failed to listen.");
+
+ ret = listen(fd[1], 5);
+ EXPECT_EQ(-1, ret) TH_LOG("should fail to listen because only one uid reserves the port in TCP_LISTEN.");
+ }
+
+ for (j = 0; j < 2; j++)
+ if (fd[j] != -1)
+ close(fd[j]);
+ }
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/net/reuseaddr_ports_exhausted.sh b/tools/testing/selftests/net/reuseaddr_ports_exhausted.sh
new file mode 100755
index 000000000000..20e3a2913d06
--- /dev/null
+++ b/tools/testing/selftests/net/reuseaddr_ports_exhausted.sh
@@ -0,0 +1,35 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Run tests when all ephemeral ports are exhausted.
+#
+# Author: Kuniyuki Iwashima <kuniyu@amazon.co.jp>
+
+set +x
+set -e
+
+readonly NETNS="ns-$(mktemp -u XXXXXX)"
+
+setup() {
+ ip netns add "${NETNS}"
+ ip -netns "${NETNS}" link set lo up
+ ip netns exec "${NETNS}" \
+ sysctl -w net.ipv4.ip_local_port_range="32768 32768" \
+ > /dev/null 2>&1
+ ip netns exec "${NETNS}" \
+ sysctl -w net.ipv4.ip_autobind_reuse=1 > /dev/null 2>&1
+}
+
+cleanup() {
+ ip netns del "${NETNS}"
+}
+
+trap cleanup EXIT
+setup
+
+do_test() {
+ ip netns exec "${NETNS}" ./reuseaddr_ports_exhausted
+}
+
+do_test
+echo "tests done"
diff --git a/tools/testing/selftests/networking/timestamping/rxtimestamp.c b/tools/testing/selftests/net/rxtimestamp.c
index 6dee9e636a95..6dee9e636a95 100644
--- a/tools/testing/selftests/networking/timestamping/rxtimestamp.c
+++ b/tools/testing/selftests/net/rxtimestamp.c
diff --git a/tools/testing/selftests/net/tcp_mmap.c b/tools/testing/selftests/net/tcp_mmap.c
index 35505b31e5cc..4555f88252ba 100644
--- a/tools/testing/selftests/net/tcp_mmap.c
+++ b/tools/testing/selftests/net/tcp_mmap.c
@@ -165,9 +165,10 @@ void *child_thread(void *arg)
socklen_t zc_len = sizeof(zc);
int res;
+ memset(&zc, 0, sizeof(zc));
zc.address = (__u64)((unsigned long)addr);
zc.length = chunk_size;
- zc.recv_skip_hint = 0;
+
res = getsockopt(fd, IPPROTO_TCP, TCP_ZEROCOPY_RECEIVE,
&zc, &zc_len);
if (res == -1)
@@ -281,12 +282,14 @@ static void setup_sockaddr(int domain, const char *str_addr,
static void do_accept(int fdlisten)
{
pthread_attr_t attr;
+ int rcvlowat;
pthread_attr_init(&attr);
pthread_attr_setdetachstate(&attr, PTHREAD_CREATE_DETACHED);
+ rcvlowat = chunk_size;
if (setsockopt(fdlisten, SOL_SOCKET, SO_RCVLOWAT,
- &chunk_size, sizeof(chunk_size)) == -1) {
+ &rcvlowat, sizeof(rcvlowat)) == -1) {
perror("setsockopt SO_RCVLOWAT");
}
diff --git a/tools/testing/selftests/networking/timestamping/timestamping.c b/tools/testing/selftests/net/timestamping.c
index aca3491174a1..aca3491174a1 100644
--- a/tools/testing/selftests/networking/timestamping/timestamping.c
+++ b/tools/testing/selftests/net/timestamping.c
diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
index 0ea44d975b6c..c5282e62df75 100644
--- a/tools/testing/selftests/net/tls.c
+++ b/tools/testing/selftests/net/tls.c
@@ -101,6 +101,21 @@ FIXTURE(tls)
bool notls;
};
+FIXTURE_VARIANT(tls)
+{
+ unsigned int tls_version;
+};
+
+FIXTURE_VARIANT_ADD(tls, 12)
+{
+ .tls_version = TLS_1_2_VERSION,
+};
+
+FIXTURE_VARIANT_ADD(tls, 13)
+{
+ .tls_version = TLS_1_3_VERSION,
+};
+
FIXTURE_SETUP(tls)
{
struct tls12_crypto_info_aes_gcm_128 tls12;
@@ -112,7 +127,7 @@ FIXTURE_SETUP(tls)
len = sizeof(addr);
memset(&tls12, 0, sizeof(tls12));
- tls12.info.version = TLS_1_3_VERSION;
+ tls12.info.version = variant->tls_version;
tls12.info.cipher_type = TLS_CIPHER_AES_GCM_128;
addr.sin_family = AF_INET;
@@ -733,7 +748,7 @@ TEST_F(tls, bidir)
struct tls12_crypto_info_aes_gcm_128 tls12;
memset(&tls12, 0, sizeof(tls12));
- tls12.info.version = TLS_1_3_VERSION;
+ tls12.info.version = variant->tls_version;
tls12.info.cipher_type = TLS_CIPHER_AES_GCM_128;
ret = setsockopt(self->fd, SOL_TLS, TLS_RX, &tls12,
@@ -1258,78 +1273,4 @@ TEST(keysizes) {
close(cfd);
}
-TEST(tls12) {
- int fd, cfd;
- bool notls;
-
- struct tls12_crypto_info_aes_gcm_128 tls12;
- struct sockaddr_in addr;
- socklen_t len;
- int sfd, ret;
-
- notls = false;
- len = sizeof(addr);
-
- memset(&tls12, 0, sizeof(tls12));
- tls12.info.version = TLS_1_2_VERSION;
- tls12.info.cipher_type = TLS_CIPHER_AES_GCM_128;
-
- addr.sin_family = AF_INET;
- addr.sin_addr.s_addr = htonl(INADDR_ANY);
- addr.sin_port = 0;
-
- fd = socket(AF_INET, SOCK_STREAM, 0);
- sfd = socket(AF_INET, SOCK_STREAM, 0);
-
- ret = bind(sfd, &addr, sizeof(addr));
- ASSERT_EQ(ret, 0);
- ret = listen(sfd, 10);
- ASSERT_EQ(ret, 0);
-
- ret = getsockname(sfd, &addr, &len);
- ASSERT_EQ(ret, 0);
-
- ret = connect(fd, &addr, sizeof(addr));
- ASSERT_EQ(ret, 0);
-
- ret = setsockopt(fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls"));
- if (ret != 0) {
- notls = true;
- printf("Failure setting TCP_ULP, testing without tls\n");
- }
-
- if (!notls) {
- ret = setsockopt(fd, SOL_TLS, TLS_TX, &tls12,
- sizeof(tls12));
- ASSERT_EQ(ret, 0);
- }
-
- cfd = accept(sfd, &addr, &len);
- ASSERT_GE(cfd, 0);
-
- if (!notls) {
- ret = setsockopt(cfd, IPPROTO_TCP, TCP_ULP, "tls",
- sizeof("tls"));
- ASSERT_EQ(ret, 0);
-
- ret = setsockopt(cfd, SOL_TLS, TLS_RX, &tls12,
- sizeof(tls12));
- ASSERT_EQ(ret, 0);
- }
-
- close(sfd);
-
- char const *test_str = "test_read";
- int send_len = 10;
- char buf[10];
-
- send_len = strlen(test_str) + 1;
- EXPECT_EQ(send(fd, test_str, send_len, 0), send_len);
- EXPECT_NE(recv(cfd, buf, send_len, 0), -1);
- EXPECT_EQ(memcmp(buf, test_str, send_len), 0);
-
- close(fd);
- close(cfd);
-}
-
TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/networking/timestamping/txtimestamp.c b/tools/testing/selftests/net/txtimestamp.c
index 7e386be47120..011b0da6b033 100644
--- a/tools/testing/selftests/networking/timestamping/txtimestamp.c
+++ b/tools/testing/selftests/net/txtimestamp.c
@@ -41,6 +41,7 @@
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
+#include <sys/epoll.h>
#include <sys/ioctl.h>
#include <sys/select.h>
#include <sys/socket.h>
@@ -49,6 +50,10 @@
#include <time.h>
#include <unistd.h>
+#define NSEC_PER_USEC 1000L
+#define USEC_PER_SEC 1000000L
+#define NSEC_PER_SEC 1000000000LL
+
/* command line parameters */
static int cfg_proto = SOCK_STREAM;
static int cfg_ipproto = IPPROTO_TCP;
@@ -61,12 +66,16 @@ static int cfg_delay_snd;
static int cfg_delay_ack;
static bool cfg_show_payload;
static bool cfg_do_pktinfo;
+static bool cfg_busy_poll;
+static int cfg_sleep_usec = 50 * 1000;
static bool cfg_loop_nodata;
-static bool cfg_no_delay;
static bool cfg_use_cmsg;
static bool cfg_use_pf_packet;
+static bool cfg_use_epoll;
+static bool cfg_epollet;
static bool cfg_do_listen;
static uint16_t dest_port = 9000;
+static bool cfg_print_nsec;
static struct sockaddr_in daddr;
static struct sockaddr_in6 daddr6;
@@ -75,11 +84,48 @@ static struct timespec ts_usr;
static int saved_tskey = -1;
static int saved_tskey_type = -1;
+struct timing_event {
+ int64_t min;
+ int64_t max;
+ int64_t total;
+ int count;
+};
+
+static struct timing_event usr_enq;
+static struct timing_event usr_snd;
+static struct timing_event usr_ack;
+
static bool test_failed;
+static int64_t timespec_to_ns64(struct timespec *ts)
+{
+ return ts->tv_sec * NSEC_PER_SEC + ts->tv_nsec;
+}
+
static int64_t timespec_to_us64(struct timespec *ts)
{
- return ts->tv_sec * 1000 * 1000 + ts->tv_nsec / 1000;
+ return ts->tv_sec * USEC_PER_SEC + ts->tv_nsec / NSEC_PER_USEC;
+}
+
+static void init_timing_event(struct timing_event *te)
+{
+ te->min = INT64_MAX;
+ te->max = 0;
+ te->total = 0;
+ te->count = 0;
+}
+
+static void add_timing_event(struct timing_event *te,
+ struct timespec *t_start, struct timespec *t_end)
+{
+ int64_t ts_delta = timespec_to_ns64(t_end) - timespec_to_ns64(t_start);
+
+ te->count++;
+ if (ts_delta < te->min)
+ te->min = ts_delta;
+ if (ts_delta > te->max)
+ te->max = ts_delta;
+ te->total += ts_delta;
}
static void validate_key(int tskey, int tstype)
@@ -113,25 +159,43 @@ static void validate_timestamp(struct timespec *cur, int min_delay)
start64 = timespec_to_us64(&ts_usr);
if (cur64 < start64 + min_delay || cur64 > start64 + max_delay) {
- fprintf(stderr, "ERROR: delay %lu expected between %d and %d\n",
+ fprintf(stderr, "ERROR: %lu us expected between %d and %d\n",
cur64 - start64, min_delay, max_delay);
test_failed = true;
}
}
+static void __print_ts_delta_formatted(int64_t ts_delta)
+{
+ if (cfg_print_nsec)
+ fprintf(stderr, "%lu ns", ts_delta);
+ else
+ fprintf(stderr, "%lu us", ts_delta / NSEC_PER_USEC);
+}
+
static void __print_timestamp(const char *name, struct timespec *cur,
uint32_t key, int payload_len)
{
+ int64_t ts_delta;
+
if (!(cur->tv_sec | cur->tv_nsec))
return;
- fprintf(stderr, " %s: %lu s %lu us (seq=%u, len=%u)",
- name, cur->tv_sec, cur->tv_nsec / 1000,
- key, payload_len);
-
- if (cur != &ts_usr)
- fprintf(stderr, " (USR %+" PRId64 " us)",
- timespec_to_us64(cur) - timespec_to_us64(&ts_usr));
+ if (cfg_print_nsec)
+ fprintf(stderr, " %s: %lu s %lu ns (seq=%u, len=%u)",
+ name, cur->tv_sec, cur->tv_nsec,
+ key, payload_len);
+ else
+ fprintf(stderr, " %s: %lu s %lu us (seq=%u, len=%u)",
+ name, cur->tv_sec, cur->tv_nsec / NSEC_PER_USEC,
+ key, payload_len);
+
+ if (cur != &ts_usr) {
+ ts_delta = timespec_to_ns64(cur) - timespec_to_ns64(&ts_usr);
+ fprintf(stderr, " (USR +");
+ __print_ts_delta_formatted(ts_delta);
+ fprintf(stderr, ")");
+ }
fprintf(stderr, "\n");
}
@@ -155,14 +219,17 @@ static void print_timestamp(struct scm_timestamping *tss, int tstype,
case SCM_TSTAMP_SCHED:
tsname = " ENQ";
validate_timestamp(&tss->ts[0], 0);
+ add_timing_event(&usr_enq, &ts_usr, &tss->ts[0]);
break;
case SCM_TSTAMP_SND:
tsname = " SND";
validate_timestamp(&tss->ts[0], cfg_delay_snd);
+ add_timing_event(&usr_snd, &ts_usr, &tss->ts[0]);
break;
case SCM_TSTAMP_ACK:
tsname = " ACK";
validate_timestamp(&tss->ts[0], cfg_delay_ack);
+ add_timing_event(&usr_ack, &ts_usr, &tss->ts[0]);
break;
default:
error(1, 0, "unknown timestamp type: %u",
@@ -171,6 +238,21 @@ static void print_timestamp(struct scm_timestamping *tss, int tstype,
__print_timestamp(tsname, &tss->ts[0], tskey, payload_len);
}
+static void print_timing_event(char *name, struct timing_event *te)
+{
+ if (!te->count)
+ return;
+
+ fprintf(stderr, " %s: count=%d", name, te->count);
+ fprintf(stderr, ", avg=");
+ __print_ts_delta_formatted((int64_t)(te->total / te->count));
+ fprintf(stderr, ", min=");
+ __print_ts_delta_formatted(te->min);
+ fprintf(stderr, ", max=");
+ __print_ts_delta_formatted(te->max);
+ fprintf(stderr, "\n");
+}
+
/* TODO: convert to check_and_print payload once API is stable */
static void print_payload(char *data, int len)
{
@@ -198,6 +280,17 @@ static void print_pktinfo(int family, int ifindex, void *saddr, void *daddr)
daddr ? inet_ntop(family, daddr, da, sizeof(da)) : "unknown");
}
+static void __epoll(int epfd)
+{
+ struct epoll_event events;
+ int ret;
+
+ memset(&events, 0, sizeof(events));
+ ret = epoll_wait(epfd, &events, 1, cfg_poll_timeout);
+ if (ret != 1)
+ error(1, errno, "epoll_wait");
+}
+
static void __poll(int fd)
{
struct pollfd pollfd;
@@ -391,7 +484,11 @@ static void do_test(int family, unsigned int report_opt)
struct msghdr msg;
struct iovec iov;
char *buf;
- int fd, i, val = 1, total_len;
+ int fd, i, val = 1, total_len, epfd = 0;
+
+ init_timing_event(&usr_enq);
+ init_timing_event(&usr_snd);
+ init_timing_event(&usr_ack);
total_len = cfg_payload_len;
if (cfg_use_pf_packet || cfg_proto == SOCK_RAW) {
@@ -418,6 +515,20 @@ static void do_test(int family, unsigned int report_opt)
if (fd < 0)
error(1, errno, "socket");
+ if (cfg_use_epoll) {
+ struct epoll_event ev;
+
+ memset(&ev, 0, sizeof(ev));
+ ev.data.fd = fd;
+ if (cfg_epollet)
+ ev.events |= EPOLLET;
+ epfd = epoll_create(1);
+ if (epfd <= 0)
+ error(1, errno, "epoll_create");
+ if (epoll_ctl(epfd, EPOLL_CTL_ADD, fd, &ev))
+ error(1, errno, "epoll_ctl");
+ }
+
/* reset expected key on each new socket */
saved_tskey = -1;
@@ -525,19 +636,28 @@ static void do_test(int family, unsigned int report_opt)
error(1, errno, "send");
/* wait for all errors to be queued, else ACKs arrive OOO */
- if (!cfg_no_delay)
- usleep(50 * 1000);
+ if (cfg_sleep_usec)
+ usleep(cfg_sleep_usec);
- __poll(fd);
+ if (!cfg_busy_poll) {
+ if (cfg_use_epoll)
+ __epoll(epfd);
+ else
+ __poll(fd);
+ }
while (!recv_errmsg(fd)) {}
}
+ print_timing_event("USR-ENQ", &usr_enq);
+ print_timing_event("USR-SND", &usr_snd);
+ print_timing_event("USR-ACK", &usr_ack);
+
if (close(fd))
error(1, errno, "close");
free(buf);
- usleep(100 * 1000);
+ usleep(100 * NSEC_PER_USEC);
}
static void __attribute__((noreturn)) usage(const char *filepath)
@@ -547,18 +667,22 @@ static void __attribute__((noreturn)) usage(const char *filepath)
" -4: only IPv4\n"
" -6: only IPv6\n"
" -h: show this message\n"
+ " -b: busy poll to read from error queue\n"
" -c N: number of packets for each test\n"
" -C: use cmsg to set tstamp recording options\n"
- " -D: no delay between packets\n"
- " -F: poll() waits forever for an event\n"
+ " -e: use level-triggered epoll() instead of poll()\n"
+ " -E: use event-triggered epoll() instead of poll()\n"
+ " -F: poll()/epoll() waits forever for an event\n"
" -I: request PKTINFO\n"
" -l N: send N bytes at a time\n"
" -L listen on hostname and port\n"
" -n: set no-payload option\n"
+ " -N: print timestamps and durations in nsec (instead of usec)\n"
" -p N: connect to port N\n"
" -P: use PF_PACKET\n"
" -r: use raw\n"
" -R: use raw (IP_HDRINCL)\n"
+ " -S N: usec to sleep before reading error queue\n"
" -u: use udp\n"
" -v: validate SND delay (usec)\n"
" -V: validate ACK delay (usec)\n"
@@ -572,7 +696,8 @@ static void parse_opt(int argc, char **argv)
int proto_count = 0;
int c;
- while ((c = getopt(argc, argv, "46c:CDFhIl:Lnp:PrRuv:V:x")) != -1) {
+ while ((c = getopt(argc, argv,
+ "46bc:CeEFhIl:LnNp:PrRS:uv:V:x")) != -1) {
switch (c) {
case '4':
do_ipv6 = 0;
@@ -580,15 +705,21 @@ static void parse_opt(int argc, char **argv)
case '6':
do_ipv4 = 0;
break;
+ case 'b':
+ cfg_busy_poll = true;
+ break;
case 'c':
cfg_num_pkts = strtoul(optarg, NULL, 10);
break;
case 'C':
cfg_use_cmsg = true;
break;
- case 'D':
- cfg_no_delay = true;
+ case 'e':
+ cfg_use_epoll = true;
break;
+ case 'E':
+ cfg_use_epoll = true;
+ cfg_epollet = true;
case 'F':
cfg_poll_timeout = -1;
break;
@@ -604,6 +735,9 @@ static void parse_opt(int argc, char **argv)
case 'n':
cfg_loop_nodata = true;
break;
+ case 'N':
+ cfg_print_nsec = true;
+ break;
case 'p':
dest_port = strtoul(optarg, NULL, 10);
break;
@@ -623,6 +757,9 @@ static void parse_opt(int argc, char **argv)
cfg_proto = SOCK_RAW;
cfg_ipproto = IPPROTO_RAW;
break;
+ case 'S':
+ cfg_sleep_usec = strtoul(optarg, NULL, 10);
+ break;
case 'u':
proto_count++;
cfg_proto = SOCK_DGRAM;
@@ -653,6 +790,8 @@ static void parse_opt(int argc, char **argv)
error(1, 0, "pass -P, -r, -R or -u, not multiple");
if (cfg_do_pktinfo && cfg_use_pf_packet)
error(1, 0, "cannot ask for pktinfo over pf_packet");
+ if (cfg_busy_poll && cfg_use_epoll)
+ error(1, 0, "pass epoll or busy_poll, not both");
if (optind != argc - 1)
error(1, 0, "missing required hostname argument");
diff --git a/tools/testing/selftests/networking/timestamping/txtimestamp.sh b/tools/testing/selftests/net/txtimestamp.sh
index df0d86ca72b7..eea6f5193693 100755
--- a/tools/testing/selftests/networking/timestamping/txtimestamp.sh
+++ b/tools/testing/selftests/net/txtimestamp.sh
@@ -43,15 +43,40 @@ run_test_tcpudpraw() {
}
run_test_all() {
+ setup
run_test_tcpudpraw # setsockopt
run_test_tcpudpraw -C # cmsg
run_test_tcpudpraw -n # timestamp w/o data
+ echo "OK. All tests passed"
+}
+
+run_test_one() {
+ setup
+ ./txtimestamp $@
+}
+
+usage() {
+ echo "Usage: $0 [ -r | --run ] <txtimestamp args> | [ -h | --help ]"
+ echo " (no args) Run all tests"
+ echo " -r|--run Run an individual test with arguments"
+ echo " -h|--help Help"
+}
+
+main() {
+ if [[ $# -eq 0 ]]; then
+ run_test_all
+ else
+ if [[ "$1" = "-r" || "$1" == "--run" ]]; then
+ shift
+ run_test_one $@
+ else
+ usage
+ fi
+ fi
}
if [[ "$(ip netns identify)" == "root" ]]; then
- ../../net/in_netns.sh $0 $@
+ ./in_netns.sh $0 $@
else
- setup
- run_test_all
- echo "OK. All tests passed"
+ main $@
fi
diff --git a/tools/testing/selftests/net/vrf-xfrm-tests.sh b/tools/testing/selftests/net/vrf-xfrm-tests.sh
new file mode 100755
index 000000000000..184da81f554f
--- /dev/null
+++ b/tools/testing/selftests/net/vrf-xfrm-tests.sh
@@ -0,0 +1,436 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Various combinations of VRF with xfrms and qdisc.
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+PAUSE_ON_FAIL=no
+VERBOSE=0
+ret=0
+
+HOST1_4=192.168.1.1
+HOST2_4=192.168.1.2
+HOST1_6=2001:db8:1::1
+HOST2_6=2001:db8:1::2
+
+XFRM1_4=10.0.1.1
+XFRM2_4=10.0.1.2
+XFRM1_6=fc00:1000::1
+XFRM2_6=fc00:1000::2
+IF_ID=123
+
+VRF=red
+TABLE=300
+
+AUTH_1=0xd94fcfea65fddf21dc6e0d24a0253508
+AUTH_2=0xdc6e0d24a0253508d94fcfea65fddf21
+ENC_1=0xfc46c20f8048be9725930ff3fb07ac2a91f0347dffeacf62
+ENC_2=0x3fb07ac2a91f0347dffeacf62fc46c20f8048be9725930ff
+SPI_1=0x02122b77
+SPI_2=0x2b770212
+
+which ping6 > /dev/null 2>&1 && ping6=$(which ping6) || ping6=$(which ping)
+
+################################################################################
+#
+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
+ [ "$a" = "q" ] && exit 1
+ fi
+ fi
+}
+
+run_cmd_host1()
+{
+ local cmd="$*"
+ local out
+ local rc
+
+ if [ "$VERBOSE" = "1" ]; then
+ printf " COMMAND: $cmd\n"
+ fi
+
+ out=$(eval ip netns exec host1 $cmd 2>&1)
+ rc=$?
+ if [ "$VERBOSE" = "1" ]; then
+ if [ -n "$out" ]; then
+ echo
+ echo " $out"
+ fi
+ echo
+ fi
+
+ return $rc
+}
+
+################################################################################
+# create namespaces for hosts and sws
+
+create_vrf()
+{
+ local ns=$1
+ local vrf=$2
+ local table=$3
+
+ if [ -n "${ns}" ]; then
+ ns="-netns ${ns}"
+ fi
+
+ ip ${ns} link add ${vrf} type vrf table ${table}
+ ip ${ns} link set ${vrf} up
+ ip ${ns} route add vrf ${vrf} unreachable default metric 8192
+ ip ${ns} -6 route add vrf ${vrf} unreachable default metric 8192
+
+ ip ${ns} addr add 127.0.0.1/8 dev ${vrf}
+ ip ${ns} -6 addr add ::1 dev ${vrf} nodad
+
+ ip ${ns} ru del pref 0
+ ip ${ns} ru add pref 32765 from all lookup local
+ ip ${ns} -6 ru del pref 0
+ ip ${ns} -6 ru add pref 32765 from all lookup local
+}
+
+create_ns()
+{
+ local ns=$1
+ local addr=$2
+ local addr6=$3
+
+ [ -z "${addr}" ] && addr="-"
+ [ -z "${addr6}" ] && addr6="-"
+
+ ip netns add ${ns}
+
+ ip -netns ${ns} link set lo up
+ if [ "${addr}" != "-" ]; then
+ ip -netns ${ns} addr add dev lo ${addr}
+ fi
+ if [ "${addr6}" != "-" ]; then
+ ip -netns ${ns} -6 addr add dev lo ${addr6}
+ fi
+
+ ip -netns ${ns} ro add unreachable default metric 8192
+ ip -netns ${ns} -6 ro add unreachable default metric 8192
+
+ ip netns exec ${ns} sysctl -qw net.ipv4.ip_forward=1
+ 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
+}
+
+# create veth pair to connect namespaces and apply addresses.
+connect_ns()
+{
+ local ns1=$1
+ local ns1_dev=$2
+ local ns1_addr=$3
+ local ns1_addr6=$4
+ local ns2=$5
+ local ns2_dev=$6
+ local ns2_addr=$7
+ local ns2_addr6=$8
+ local ns1arg
+ local ns2arg
+
+ if [ -n "${ns1}" ]; then
+ ns1arg="-netns ${ns1}"
+ fi
+ if [ -n "${ns2}" ]; then
+ ns2arg="-netns ${ns2}"
+ fi
+
+ ip ${ns1arg} li add ${ns1_dev} type veth peer name tmp
+ ip ${ns1arg} li set ${ns1_dev} up
+ ip ${ns1arg} li set tmp netns ${ns2} name ${ns2_dev}
+ ip ${ns2arg} li set ${ns2_dev} up
+
+ if [ "${ns1_addr}" != "-" ]; then
+ ip ${ns1arg} addr add dev ${ns1_dev} ${ns1_addr}
+ ip ${ns2arg} addr add dev ${ns2_dev} ${ns2_addr}
+ fi
+
+ if [ "${ns1_addr6}" != "-" ]; then
+ ip ${ns1arg} addr add dev ${ns1_dev} ${ns1_addr6} nodad
+ ip ${ns2arg} addr add dev ${ns2_dev} ${ns2_addr6} nodad
+ fi
+}
+
+################################################################################
+
+cleanup()
+{
+ ip netns del host1
+ ip netns del host2
+}
+
+setup()
+{
+ create_ns "host1"
+ create_ns "host2"
+
+ connect_ns "host1" eth0 ${HOST1_4}/24 ${HOST1_6}/64 \
+ "host2" eth0 ${HOST2_4}/24 ${HOST2_6}/64
+
+ create_vrf "host1" ${VRF} ${TABLE}
+ ip -netns host1 link set dev eth0 master ${VRF}
+}
+
+cleanup_xfrm()
+{
+ for ns in host1 host2
+ do
+ for x in state policy
+ do
+ ip -netns ${ns} xfrm ${x} flush
+ ip -6 -netns ${ns} xfrm ${x} flush
+ done
+ done
+}
+
+setup_xfrm()
+{
+ local h1_4=$1
+ local h2_4=$2
+ local h1_6=$3
+ local h2_6=$4
+ local devarg="$5"
+
+ #
+ # policy
+ #
+
+ # host1 - IPv4 out
+ ip -netns host1 xfrm policy add \
+ src ${h1_4} dst ${h2_4} ${devarg} dir out \
+ tmpl src ${HOST1_4} dst ${HOST2_4} proto esp mode tunnel
+
+ # host2 - IPv4 in
+ ip -netns host2 xfrm policy add \
+ src ${h1_4} dst ${h2_4} dir in \
+ tmpl src ${HOST1_4} dst ${HOST2_4} proto esp mode tunnel
+
+ # host1 - IPv4 in
+ ip -netns host1 xfrm policy add \
+ src ${h2_4} dst ${h1_4} ${devarg} dir in \
+ tmpl src ${HOST2_4} dst ${HOST1_4} proto esp mode tunnel
+
+ # host2 - IPv4 out
+ ip -netns host2 xfrm policy add \
+ src ${h2_4} dst ${h1_4} dir out \
+ tmpl src ${HOST2_4} dst ${HOST1_4} proto esp mode tunnel
+
+
+ # host1 - IPv6 out
+ ip -6 -netns host1 xfrm policy add \
+ src ${h1_6} dst ${h2_6} ${devarg} dir out \
+ tmpl src ${HOST1_6} dst ${HOST2_6} proto esp mode tunnel
+
+ # host2 - IPv6 in
+ ip -6 -netns host2 xfrm policy add \
+ src ${h1_6} dst ${h2_6} dir in \
+ tmpl src ${HOST1_6} dst ${HOST2_6} proto esp mode tunnel
+
+ # host1 - IPv6 in
+ ip -6 -netns host1 xfrm policy add \
+ src ${h2_6} dst ${h1_6} ${devarg} dir in \
+ tmpl src ${HOST2_6} dst ${HOST1_6} proto esp mode tunnel
+
+ # host2 - IPv6 out
+ ip -6 -netns host2 xfrm policy add \
+ src ${h2_6} dst ${h1_6} dir out \
+ tmpl src ${HOST2_6} dst ${HOST1_6} proto esp mode tunnel
+
+ #
+ # state
+ #
+ ip -netns host1 xfrm state add src ${HOST1_4} dst ${HOST2_4} \
+ proto esp spi ${SPI_1} reqid 0 mode tunnel \
+ replay-window 4 replay-oseq 0x4 \
+ auth-trunc 'hmac(md5)' ${AUTH_1} 96 \
+ enc 'cbc(des3_ede)' ${ENC_1} \
+ sel src ${h1_4} dst ${h2_4} ${devarg}
+
+ ip -netns host2 xfrm state add src ${HOST1_4} dst ${HOST2_4} \
+ proto esp spi ${SPI_1} reqid 0 mode tunnel \
+ replay-window 4 replay-oseq 0x4 \
+ auth-trunc 'hmac(md5)' ${AUTH_1} 96 \
+ enc 'cbc(des3_ede)' ${ENC_1} \
+ sel src ${h1_4} dst ${h2_4}
+
+
+ ip -netns host1 xfrm state add src ${HOST2_4} dst ${HOST1_4} \
+ proto esp spi ${SPI_2} reqid 0 mode tunnel \
+ replay-window 4 replay-oseq 0x4 \
+ auth-trunc 'hmac(md5)' ${AUTH_2} 96 \
+ enc 'cbc(des3_ede)' ${ENC_2} \
+ sel src ${h2_4} dst ${h1_4} ${devarg}
+
+ ip -netns host2 xfrm state add src ${HOST2_4} dst ${HOST1_4} \
+ proto esp spi ${SPI_2} reqid 0 mode tunnel \
+ replay-window 4 replay-oseq 0x4 \
+ auth-trunc 'hmac(md5)' ${AUTH_2} 96 \
+ enc 'cbc(des3_ede)' ${ENC_2} \
+ sel src ${h2_4} dst ${h1_4}
+
+
+ ip -6 -netns host1 xfrm state add src ${HOST1_6} dst ${HOST2_6} \
+ proto esp spi ${SPI_1} reqid 0 mode tunnel \
+ replay-window 4 replay-oseq 0x4 \
+ auth-trunc 'hmac(md5)' ${AUTH_1} 96 \
+ enc 'cbc(des3_ede)' ${ENC_1} \
+ sel src ${h1_6} dst ${h2_6} ${devarg}
+
+ ip -6 -netns host2 xfrm state add src ${HOST1_6} dst ${HOST2_6} \
+ proto esp spi ${SPI_1} reqid 0 mode tunnel \
+ replay-window 4 replay-oseq 0x4 \
+ auth-trunc 'hmac(md5)' ${AUTH_1} 96 \
+ enc 'cbc(des3_ede)' ${ENC_1} \
+ sel src ${h1_6} dst ${h2_6}
+
+
+ ip -6 -netns host1 xfrm state add src ${HOST2_6} dst ${HOST1_6} \
+ proto esp spi ${SPI_2} reqid 0 mode tunnel \
+ replay-window 4 replay-oseq 0x4 \
+ auth-trunc 'hmac(md5)' ${AUTH_2} 96 \
+ enc 'cbc(des3_ede)' ${ENC_2} \
+ sel src ${h2_6} dst ${h1_6} ${devarg}
+
+ ip -6 -netns host2 xfrm state add src ${HOST2_6} dst ${HOST1_6} \
+ proto esp spi ${SPI_2} reqid 0 mode tunnel \
+ replay-window 4 replay-oseq 0x4 \
+ auth-trunc 'hmac(md5)' ${AUTH_2} 96 \
+ enc 'cbc(des3_ede)' ${ENC_2} \
+ sel src ${h2_6} dst ${h1_6}
+}
+
+cleanup_xfrm_dev()
+{
+ ip -netns host1 li del xfrm0
+ ip -netns host2 addr del ${XFRM2_4}/24 dev eth0
+ ip -netns host2 addr del ${XFRM2_6}/64 dev eth0
+}
+
+setup_xfrm_dev()
+{
+ local vrfarg="vrf ${VRF}"
+
+ ip -netns host1 li add type xfrm dev eth0 if_id ${IF_ID}
+ ip -netns host1 li set xfrm0 ${vrfarg} up
+ ip -netns host1 addr add ${XFRM1_4}/24 dev xfrm0
+ ip -netns host1 addr add ${XFRM1_6}/64 dev xfrm0
+
+ ip -netns host2 addr add ${XFRM2_4}/24 dev eth0
+ ip -netns host2 addr add ${XFRM2_6}/64 dev eth0
+
+ setup_xfrm ${XFRM1_4} ${XFRM2_4} ${XFRM1_6} ${XFRM2_6} "if_id ${IF_ID}"
+}
+
+run_tests()
+{
+ cleanup_xfrm
+
+ # no IPsec
+ run_cmd_host1 ip vrf exec ${VRF} ping -c1 -w1 ${HOST2_4}
+ log_test $? 0 "IPv4 no xfrm policy"
+ run_cmd_host1 ip vrf exec ${VRF} ${ping6} -c1 -w1 ${HOST2_6}
+ log_test $? 0 "IPv6 no xfrm policy"
+
+ # xfrm without VRF in sel
+ setup_xfrm ${HOST1_4} ${HOST2_4} ${HOST1_6} ${HOST2_6}
+ run_cmd_host1 ip vrf exec ${VRF} ping -c1 -w1 ${HOST2_4}
+ log_test $? 0 "IPv4 xfrm policy based on address"
+ run_cmd_host1 ip vrf exec ${VRF} ${ping6} -c1 -w1 ${HOST2_6}
+ log_test $? 0 "IPv6 xfrm policy based on address"
+ cleanup_xfrm
+
+ # xfrm with VRF in sel
+ # Known failure: ipv4 resets the flow oif after the lookup. Fix is
+ # not straightforward.
+ # setup_xfrm ${HOST1_4} ${HOST2_4} ${HOST1_6} ${HOST2_6} "dev ${VRF}"
+ # run_cmd_host1 ip vrf exec ${VRF} ping -c1 -w1 ${HOST2_4}
+ # log_test $? 0 "IPv4 xfrm policy with VRF in selector"
+ run_cmd_host1 ip vrf exec ${VRF} ${ping6} -c1 -w1 ${HOST2_6}
+ log_test $? 0 "IPv6 xfrm policy with VRF in selector"
+ cleanup_xfrm
+
+ # xfrm with enslaved device in sel
+ # Known failures: combined with the above, __xfrm{4,6}_selector_match
+ # needs to consider both l3mdev and enslaved device index.
+ # setup_xfrm ${HOST1_4} ${HOST2_4} ${HOST1_6} ${HOST2_6} "dev eth0"
+ # run_cmd_host1 ip vrf exec ${VRF} ping -c1 -w1 ${HOST2_4}
+ # log_test $? 0 "IPv4 xfrm policy with enslaved device in selector"
+ # run_cmd_host1 ip vrf exec ${VRF} ${ping6} -c1 -w1 ${HOST2_6}
+ # log_test $? 0 "IPv6 xfrm policy with enslaved device in selector"
+ # cleanup_xfrm
+
+ # xfrm device
+ setup_xfrm_dev
+ run_cmd_host1 ip vrf exec ${VRF} ping -c1 -w1 ${XFRM2_4}
+ log_test $? 0 "IPv4 xfrm policy with xfrm device"
+ run_cmd_host1 ip vrf exec ${VRF} ${ping6} -c1 -w1 ${XFRM2_6}
+ log_test $? 0 "IPv6 xfrm policy with xfrm device"
+ cleanup_xfrm_dev
+}
+
+################################################################################
+# usage
+
+usage()
+{
+ cat <<EOF
+usage: ${0##*/} OPTS
+
+ -p Pause on fail
+ -v verbose mode (show commands and output)
+
+done
+EOF
+}
+
+################################################################################
+# main
+
+while getopts :pv o
+do
+ case $o in
+ p) PAUSE_ON_FAIL=yes;;
+ v) VERBOSE=$(($VERBOSE + 1));;
+ h) usage; exit 0;;
+ *) usage; exit 1;;
+ esac
+done
+
+cleanup 2>/dev/null
+setup
+
+echo
+echo "No qdisc on VRF device"
+run_tests
+
+run_cmd_host1 tc qdisc add dev ${VRF} root netem delay 100ms
+echo
+echo "netem qdisc on VRF device"
+run_tests
+
+printf "\nTests passed: %3d\n" ${nsuccess}
+printf "Tests failed: %3d\n" ${nfail}
+
+exit $ret
diff --git a/tools/testing/selftests/networking/timestamping/.gitignore b/tools/testing/selftests/networking/timestamping/.gitignore
deleted file mode 100644
index d9355035e746..000000000000
--- a/tools/testing/selftests/networking/timestamping/.gitignore
+++ /dev/null
@@ -1,4 +0,0 @@
-timestamping
-rxtimestamp
-txtimestamp
-hwtstamp_config
diff --git a/tools/testing/selftests/networking/timestamping/Makefile b/tools/testing/selftests/networking/timestamping/Makefile
deleted file mode 100644
index 1de8bd8ccf5d..000000000000
--- a/tools/testing/selftests/networking/timestamping/Makefile
+++ /dev/null
@@ -1,11 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-CFLAGS += -I../../../../../usr/include
-
-TEST_GEN_FILES := hwtstamp_config rxtimestamp timestamping txtimestamp
-TEST_PROGS := txtimestamp.sh
-
-all: $(TEST_PROGS)
-
-top_srcdir = ../../../../..
-KSFT_KHDR_INSTALL := 1
-include ../../lib.mk
diff --git a/tools/testing/selftests/networking/timestamping/config b/tools/testing/selftests/networking/timestamping/config
deleted file mode 100644
index a13e3169b0a4..000000000000
--- a/tools/testing/selftests/networking/timestamping/config
+++ /dev/null
@@ -1,2 +0,0 @@
-CONFIG_IFB=y
-CONFIG_NET_SCH_NETEM=y
diff --git a/tools/testing/selftests/nsfs/.gitignore b/tools/testing/selftests/nsfs/.gitignore
index 2ab2c824ce86..ed79ebdf286e 100644
--- a/tools/testing/selftests/nsfs/.gitignore
+++ b/tools/testing/selftests/nsfs/.gitignore
@@ -1,2 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0-only
owner
pidns
diff --git a/tools/testing/selftests/nsfs/pidns.c b/tools/testing/selftests/nsfs/pidns.c
index e0d86e1668c0..e3c772c6a7c7 100644
--- a/tools/testing/selftests/nsfs/pidns.c
+++ b/tools/testing/selftests/nsfs/pidns.c
@@ -27,7 +27,7 @@
#define __stack_aligned__ __attribute__((aligned(16)))
struct cr_clone_arg {
char stack[128] __stack_aligned__;
- char stack_ptr[0];
+ char stack_ptr[];
};
static int child(void *args)
diff --git a/tools/testing/selftests/ntb/ntb_test.sh b/tools/testing/selftests/ntb/ntb_test.sh
index 9c60337317c6..020137b61407 100755
--- a/tools/testing/selftests/ntb/ntb_test.sh
+++ b/tools/testing/selftests/ntb/ntb_test.sh
@@ -241,7 +241,7 @@ function get_files_count()
split_remote $LOC
if [[ "$REMOTE" == "" ]]; then
- echo $(ls -1 "$LOC"/${NAME}* 2>/dev/null | wc -l)
+ echo $(ls -1 "$VPATH"/${NAME}* 2>/dev/null | wc -l)
else
echo $(ssh "$REMOTE" "ls -1 \"$VPATH\"/${NAME}* | \
wc -l" 2> /dev/null)
diff --git a/tools/testing/selftests/openat2/.gitignore b/tools/testing/selftests/openat2/.gitignore
index bd68f6c3fd07..82a4846cbc4b 100644
--- a/tools/testing/selftests/openat2/.gitignore
+++ b/tools/testing/selftests/openat2/.gitignore
@@ -1 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
/*_test
diff --git a/tools/testing/selftests/pid_namespace/.gitignore b/tools/testing/selftests/pid_namespace/.gitignore
new file mode 100644
index 000000000000..93ab9d7e5b7e
--- /dev/null
+++ b/tools/testing/selftests/pid_namespace/.gitignore
@@ -0,0 +1 @@
+regression_enomem
diff --git a/tools/testing/selftests/pid_namespace/Makefile b/tools/testing/selftests/pid_namespace/Makefile
new file mode 100644
index 000000000000..dcaefa224ca0
--- /dev/null
+++ b/tools/testing/selftests/pid_namespace/Makefile
@@ -0,0 +1,8 @@
+# SPDX-License-Identifier: GPL-2.0
+CFLAGS += -g -I../../../../usr/include/
+
+TEST_GEN_PROGS := regression_enomem
+
+include ../lib.mk
+
+$(OUTPUT)/regression_enomem: regression_enomem.c ../pidfd/pidfd.h
diff --git a/tools/testing/selftests/pid_namespace/config b/tools/testing/selftests/pid_namespace/config
new file mode 100644
index 000000000000..26cdb27e7dbb
--- /dev/null
+++ b/tools/testing/selftests/pid_namespace/config
@@ -0,0 +1,2 @@
+CONFIG_PID_NS=y
+CONFIG_USER_NS=y
diff --git a/tools/testing/selftests/pid_namespace/regression_enomem.c b/tools/testing/selftests/pid_namespace/regression_enomem.c
new file mode 100644
index 000000000000..73d532556d17
--- /dev/null
+++ b/tools/testing/selftests/pid_namespace/regression_enomem.c
@@ -0,0 +1,45 @@
+#define _GNU_SOURCE
+#include <assert.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <linux/types.h>
+#include <sched.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <syscall.h>
+#include <sys/wait.h>
+
+#include "../kselftest.h"
+#include "../kselftest_harness.h"
+#include "../pidfd/pidfd.h"
+
+/*
+ * Regression test for:
+ * 35f71bc0a09a ("fork: report pid reservation failure properly")
+ * b26ebfe12f34 ("pid: Fix error return value in some cases")
+ */
+TEST(regression_enomem)
+{
+ pid_t pid;
+
+ if (geteuid())
+ EXPECT_EQ(0, unshare(CLONE_NEWUSER));
+
+ EXPECT_EQ(0, unshare(CLONE_NEWPID));
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0)
+ exit(EXIT_SUCCESS);
+
+ EXPECT_EQ(0, wait_for_pid(pid));
+
+ pid = fork();
+ ASSERT_LT(pid, 0);
+ ASSERT_EQ(errno, ENOMEM);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/pidfd/.gitignore b/tools/testing/selftests/pidfd/.gitignore
index 39559d723c41..973198a3ec3d 100644
--- a/tools/testing/selftests/pidfd/.gitignore
+++ b/tools/testing/selftests/pidfd/.gitignore
@@ -1,6 +1,8 @@
+# SPDX-License-Identifier: GPL-2.0-only
pidfd_open_test
pidfd_poll_test
pidfd_test
pidfd_wait
pidfd_fdinfo_test
pidfd_getfd_test
+pidfd_setns_test
diff --git a/tools/testing/selftests/pidfd/Makefile b/tools/testing/selftests/pidfd/Makefile
index 75a545861375..f4a2f28f926b 100644
--- a/tools/testing/selftests/pidfd/Makefile
+++ b/tools/testing/selftests/pidfd/Makefile
@@ -1,7 +1,8 @@
# SPDX-License-Identifier: GPL-2.0-only
CFLAGS += -g -I../../../../usr/include/ -pthread
-TEST_GEN_PROGS := pidfd_test pidfd_fdinfo_test pidfd_open_test pidfd_poll_test pidfd_wait pidfd_getfd_test
+TEST_GEN_PROGS := pidfd_test pidfd_fdinfo_test pidfd_open_test \
+ pidfd_poll_test pidfd_wait pidfd_getfd_test pidfd_setns_test
include ../lib.mk
diff --git a/tools/testing/selftests/pidfd/config b/tools/testing/selftests/pidfd/config
new file mode 100644
index 000000000000..bb11de90c0c9
--- /dev/null
+++ b/tools/testing/selftests/pidfd/config
@@ -0,0 +1,6 @@
+CONFIG_UTS_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/pidfd/pidfd.h b/tools/testing/selftests/pidfd/pidfd.h
index d482515604db..c1921a53dbed 100644
--- a/tools/testing/selftests/pidfd/pidfd.h
+++ b/tools/testing/selftests/pidfd/pidfd.h
@@ -13,6 +13,8 @@
#include <string.h>
#include <syscall.h>
#include <sys/mount.h>
+#include <sys/types.h>
+#include <sys/wait.h>
#include "../kselftest.h"
diff --git a/tools/testing/selftests/pidfd/pidfd_setns_test.c b/tools/testing/selftests/pidfd/pidfd_setns_test.c
new file mode 100644
index 000000000000..133ec5b6cda8
--- /dev/null
+++ b/tools/testing/selftests/pidfd/pidfd_setns_test.c
@@ -0,0 +1,473 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+#include <errno.h>
+#include <fcntl.h>
+#include <limits.h>
+#include <linux/types.h>
+#include <sched.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <syscall.h>
+#include <sys/prctl.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include <sys/socket.h>
+#include <sys/stat.h>
+#include <linux/kcmp.h>
+
+#include "pidfd.h"
+#include "../clone3/clone3_selftests.h"
+#include "../kselftest.h"
+#include "../kselftest_harness.h"
+
+enum {
+ PIDFD_NS_USER,
+ PIDFD_NS_MNT,
+ PIDFD_NS_PID,
+ PIDFD_NS_UTS,
+ PIDFD_NS_IPC,
+ PIDFD_NS_NET,
+ PIDFD_NS_CGROUP,
+ PIDFD_NS_PIDCLD,
+ PIDFD_NS_MAX
+};
+
+const struct ns_info {
+ const char *name;
+ int flag;
+} ns_info[] = {
+ [PIDFD_NS_USER] = { "user", CLONE_NEWUSER, },
+ [PIDFD_NS_MNT] = { "mnt", CLONE_NEWNS, },
+ [PIDFD_NS_PID] = { "pid", CLONE_NEWPID, },
+ [PIDFD_NS_UTS] = { "uts", CLONE_NEWUTS, },
+ [PIDFD_NS_IPC] = { "ipc", CLONE_NEWIPC, },
+ [PIDFD_NS_NET] = { "net", CLONE_NEWNET, },
+ [PIDFD_NS_CGROUP] = { "cgroup", CLONE_NEWCGROUP, },
+ [PIDFD_NS_PIDCLD] = { "pid_for_children", 0, },
+};
+
+FIXTURE(current_nsset)
+{
+ pid_t pid;
+ int pidfd;
+ int nsfds[PIDFD_NS_MAX];
+
+ pid_t child_pid_exited;
+ int child_pidfd_exited;
+
+ pid_t child_pid1;
+ int child_pidfd1;
+ int child_nsfds1[PIDFD_NS_MAX];
+
+ pid_t child_pid2;
+ int child_pidfd2;
+ int child_nsfds2[PIDFD_NS_MAX];
+};
+
+static int sys_waitid(int which, pid_t pid, int options)
+{
+ return syscall(__NR_waitid, which, pid, NULL, options, NULL);
+}
+
+pid_t create_child(int *pidfd, unsigned flags)
+{
+ struct clone_args args = {
+ .flags = CLONE_PIDFD | flags,
+ .exit_signal = SIGCHLD,
+ .pidfd = ptr_to_u64(pidfd),
+ };
+
+ return sys_clone3(&args, sizeof(struct clone_args));
+}
+
+FIXTURE_SETUP(current_nsset)
+{
+ int i, proc_fd, ret;
+
+ for (i = 0; i < PIDFD_NS_MAX; i++) {
+ self->nsfds[i] = -EBADF;
+ self->child_nsfds1[i] = -EBADF;
+ self->child_nsfds2[i] = -EBADF;
+ }
+
+ proc_fd = open("/proc/self/ns", O_DIRECTORY | O_CLOEXEC);
+ ASSERT_GE(proc_fd, 0) {
+ TH_LOG("%m - Failed to open /proc/self/ns");
+ }
+
+ self->pid = getpid();
+ for (i = 0; i < PIDFD_NS_MAX; i++) {
+ const struct ns_info *info = &ns_info[i];
+ self->nsfds[i] = openat(proc_fd, info->name, O_RDONLY | O_CLOEXEC);
+ if (self->nsfds[i] < 0) {
+ EXPECT_EQ(errno, ENOENT) {
+ TH_LOG("%m - Failed to open %s namespace for process %d",
+ info->name, self->pid);
+ }
+ }
+ }
+
+ self->pidfd = sys_pidfd_open(self->pid, 0);
+ EXPECT_GT(self->pidfd, 0) {
+ TH_LOG("%m - Failed to open pidfd for process %d", self->pid);
+ }
+
+ /* Create task that exits right away. */
+ self->child_pid_exited = create_child(&self->child_pidfd_exited,
+ CLONE_NEWUSER | CLONE_NEWNET);
+ EXPECT_GT(self->child_pid_exited, 0);
+
+ if (self->child_pid_exited == 0)
+ _exit(EXIT_SUCCESS);
+
+ ASSERT_EQ(sys_waitid(P_PID, self->child_pid_exited, WEXITED | WNOWAIT), 0);
+
+ self->pidfd = sys_pidfd_open(self->pid, 0);
+ EXPECT_GE(self->pidfd, 0) {
+ TH_LOG("%m - Failed to open pidfd for process %d", self->pid);
+ }
+
+ /* Create tasks that will be stopped. */
+ self->child_pid1 = create_child(&self->child_pidfd1,
+ CLONE_NEWUSER | CLONE_NEWNS |
+ CLONE_NEWCGROUP | CLONE_NEWIPC |
+ CLONE_NEWUTS | CLONE_NEWPID |
+ CLONE_NEWNET);
+ EXPECT_GE(self->child_pid1, 0);
+
+ if (self->child_pid1 == 0) {
+ pause();
+ _exit(EXIT_SUCCESS);
+ }
+
+ self->child_pid2 = create_child(&self->child_pidfd2,
+ CLONE_NEWUSER | CLONE_NEWNS |
+ CLONE_NEWCGROUP | CLONE_NEWIPC |
+ CLONE_NEWUTS | CLONE_NEWPID |
+ CLONE_NEWNET);
+ EXPECT_GE(self->child_pid2, 0);
+
+ if (self->child_pid2 == 0) {
+ pause();
+ _exit(EXIT_SUCCESS);
+ }
+
+ for (i = 0; i < PIDFD_NS_MAX; i++) {
+ char p[100];
+
+ const struct ns_info *info = &ns_info[i];
+
+ self->nsfds[i] = openat(proc_fd, info->name, O_RDONLY | O_CLOEXEC);
+ if (self->nsfds[i] < 0) {
+ EXPECT_EQ(errno, ENOENT) {
+ TH_LOG("%m - Failed to open %s namespace for process %d",
+ info->name, self->pid);
+ }
+ }
+
+ ret = snprintf(p, sizeof(p), "/proc/%d/ns/%s",
+ self->child_pid1, info->name);
+ EXPECT_GT(ret, 0);
+ EXPECT_LT(ret, sizeof(p));
+
+ self->child_nsfds1[i] = open(p, O_RDONLY | O_CLOEXEC);
+ if (self->child_nsfds1[i] < 0) {
+ EXPECT_EQ(errno, ENOENT) {
+ TH_LOG("%m - Failed to open %s namespace for process %d",
+ info->name, self->child_pid1);
+ }
+ }
+
+ ret = snprintf(p, sizeof(p), "/proc/%d/ns/%s",
+ self->child_pid2, info->name);
+ EXPECT_GT(ret, 0);
+ EXPECT_LT(ret, sizeof(p));
+
+ self->child_nsfds2[i] = open(p, O_RDONLY | O_CLOEXEC);
+ if (self->child_nsfds2[i] < 0) {
+ EXPECT_EQ(errno, ENOENT) {
+ TH_LOG("%m - Failed to open %s namespace for process %d",
+ info->name, self->child_pid1);
+ }
+ }
+ }
+
+ close(proc_fd);
+}
+
+FIXTURE_TEARDOWN(current_nsset)
+{
+ int i;
+
+ ASSERT_EQ(sys_pidfd_send_signal(self->child_pidfd1,
+ SIGKILL, NULL, 0), 0);
+ ASSERT_EQ(sys_pidfd_send_signal(self->child_pidfd2,
+ SIGKILL, NULL, 0), 0);
+
+ for (i = 0; i < PIDFD_NS_MAX; i++) {
+ if (self->nsfds[i] >= 0)
+ close(self->nsfds[i]);
+ if (self->child_nsfds1[i] >= 0)
+ close(self->child_nsfds1[i]);
+ if (self->child_nsfds2[i] >= 0)
+ close(self->child_nsfds2[i]);
+ }
+
+ if (self->child_pidfd1 >= 0)
+ EXPECT_EQ(0, close(self->child_pidfd1));
+ if (self->child_pidfd2 >= 0)
+ EXPECT_EQ(0, close(self->child_pidfd2));
+ ASSERT_EQ(sys_waitid(P_PID, self->child_pid_exited, WEXITED), 0);
+ ASSERT_EQ(sys_waitid(P_PID, self->child_pid1, WEXITED), 0);
+ ASSERT_EQ(sys_waitid(P_PID, self->child_pid2, WEXITED), 0);
+}
+
+static int preserve_ns(const int pid, const char *ns)
+{
+ int ret;
+ char path[50];
+
+ ret = snprintf(path, sizeof(path), "/proc/%d/ns/%s", pid, ns);
+ if (ret < 0 || (size_t)ret >= sizeof(path))
+ return -EIO;
+
+ return open(path, O_RDONLY | O_CLOEXEC);
+}
+
+static int in_same_namespace(int ns_fd1, pid_t pid2, const char *ns)
+{
+ int ns_fd2 = -EBADF;
+ int ret = -1;
+ struct stat ns_st1, ns_st2;
+
+ ret = fstat(ns_fd1, &ns_st1);
+ if (ret < 0)
+ return -1;
+
+ ns_fd2 = preserve_ns(pid2, ns);
+ if (ns_fd2 < 0)
+ return -1;
+
+ ret = fstat(ns_fd2, &ns_st2);
+ close(ns_fd2);
+ if (ret < 0)
+ return -1;
+
+ /* processes are in the same namespace */
+ if ((ns_st1.st_dev == ns_st2.st_dev) &&
+ (ns_st1.st_ino == ns_st2.st_ino))
+ return 1;
+
+ /* processes are in different namespaces */
+ return 0;
+}
+
+/* Test that we can't pass garbage to the kernel. */
+TEST_F(current_nsset, invalid_flags)
+{
+ ASSERT_NE(setns(self->pidfd, 0), 0);
+ EXPECT_EQ(errno, EINVAL);
+
+ ASSERT_NE(setns(self->pidfd, -1), 0);
+ EXPECT_EQ(errno, EINVAL);
+
+ ASSERT_NE(setns(self->pidfd, CLONE_VM), 0);
+ EXPECT_EQ(errno, EINVAL);
+
+ ASSERT_NE(setns(self->pidfd, CLONE_NEWUSER | CLONE_VM), 0);
+ EXPECT_EQ(errno, EINVAL);
+}
+
+/* Test that we can't attach to a task that has already exited. */
+TEST_F(current_nsset, pidfd_exited_child)
+{
+ int i;
+ pid_t pid;
+
+ ASSERT_NE(setns(self->child_pidfd_exited, CLONE_NEWUSER | CLONE_NEWNET),
+ 0);
+ EXPECT_EQ(errno, ESRCH);
+
+ pid = getpid();
+ for (i = 0; i < PIDFD_NS_MAX; i++) {
+ const struct ns_info *info = &ns_info[i];
+ /* Verify that we haven't changed any namespaces. */
+ if (self->nsfds[i] >= 0)
+ ASSERT_EQ(in_same_namespace(self->nsfds[i], pid, info->name), 1);
+ }
+}
+
+TEST_F(current_nsset, pidfd_incremental_setns)
+{
+ int i;
+ pid_t pid;
+
+ pid = getpid();
+ for (i = 0; i < PIDFD_NS_MAX; i++) {
+ const struct ns_info *info = &ns_info[i];
+ int nsfd;
+
+ if (self->child_nsfds1[i] < 0)
+ continue;
+
+ if (info->flag) {
+ ASSERT_EQ(setns(self->child_pidfd1, info->flag), 0) {
+ TH_LOG("%m - Failed to setns to %s namespace of %d via pidfd %d",
+ info->name, self->child_pid1,
+ self->child_pidfd1);
+ }
+ }
+
+ /* Verify that we have changed to the correct namespaces. */
+ if (info->flag == CLONE_NEWPID)
+ nsfd = self->nsfds[i];
+ else
+ nsfd = self->child_nsfds1[i];
+ ASSERT_EQ(in_same_namespace(nsfd, pid, info->name), 1) {
+ TH_LOG("setns failed to place us correctly into %s namespace of %d via pidfd %d",
+ info->name, self->child_pid1,
+ self->child_pidfd1);
+ }
+ TH_LOG("Managed to correctly setns to %s namespace of %d via pidfd %d",
+ info->name, self->child_pid1, self->child_pidfd1);
+ }
+}
+
+TEST_F(current_nsset, nsfd_incremental_setns)
+{
+ int i;
+ pid_t pid;
+
+ pid = getpid();
+ for (i = 0; i < PIDFD_NS_MAX; i++) {
+ const struct ns_info *info = &ns_info[i];
+ int nsfd;
+
+ if (self->child_nsfds1[i] < 0)
+ continue;
+
+ if (info->flag) {
+ ASSERT_EQ(setns(self->child_nsfds1[i], info->flag), 0) {
+ TH_LOG("%m - Failed to setns to %s namespace of %d via nsfd %d",
+ info->name, self->child_pid1,
+ self->child_nsfds1[i]);
+ }
+ }
+
+ /* Verify that we have changed to the correct namespaces. */
+ if (info->flag == CLONE_NEWPID)
+ nsfd = self->nsfds[i];
+ else
+ nsfd = self->child_nsfds1[i];
+ ASSERT_EQ(in_same_namespace(nsfd, pid, info->name), 1) {
+ TH_LOG("setns failed to place us correctly into %s namespace of %d via nsfd %d",
+ info->name, self->child_pid1,
+ self->child_nsfds1[i]);
+ }
+ TH_LOG("Managed to correctly setns to %s namespace of %d via nsfd %d",
+ info->name, self->child_pid1, self->child_nsfds1[i]);
+ }
+}
+
+TEST_F(current_nsset, pidfd_one_shot_setns)
+{
+ unsigned flags = 0;
+ int i;
+ pid_t pid;
+
+ for (i = 0; i < PIDFD_NS_MAX; i++) {
+ const struct ns_info *info = &ns_info[i];
+
+ if (self->child_nsfds1[i] < 0)
+ continue;
+
+ flags |= info->flag;
+ TH_LOG("Adding %s namespace of %d to list of namespaces to attach to",
+ info->name, self->child_pid1);
+ }
+
+ ASSERT_EQ(setns(self->child_pidfd1, flags), 0) {
+ TH_LOG("%m - Failed to setns to namespaces of %d",
+ self->child_pid1);
+ }
+
+ pid = getpid();
+ for (i = 0; i < PIDFD_NS_MAX; i++) {
+ const struct ns_info *info = &ns_info[i];
+ int nsfd;
+
+ if (self->child_nsfds1[i] < 0)
+ continue;
+
+ /* Verify that we have changed to the correct namespaces. */
+ if (info->flag == CLONE_NEWPID)
+ nsfd = self->nsfds[i];
+ else
+ nsfd = self->child_nsfds1[i];
+ ASSERT_EQ(in_same_namespace(nsfd, pid, info->name), 1) {
+ TH_LOG("setns failed to place us correctly into %s namespace of %d",
+ info->name, self->child_pid1);
+ }
+ TH_LOG("Managed to correctly setns to %s namespace of %d",
+ info->name, self->child_pid1);
+ }
+}
+
+TEST_F(current_nsset, no_foul_play)
+{
+ unsigned flags = 0;
+ int i;
+
+ for (i = 0; i < PIDFD_NS_MAX; i++) {
+ const struct ns_info *info = &ns_info[i];
+
+ if (self->child_nsfds1[i] < 0)
+ continue;
+
+ flags |= info->flag;
+ if (info->flag) /* No use logging pid_for_children. */
+ TH_LOG("Adding %s namespace of %d to list of namespaces to attach to",
+ info->name, self->child_pid1);
+ }
+
+ ASSERT_EQ(setns(self->child_pidfd1, flags), 0) {
+ TH_LOG("%m - Failed to setns to namespaces of %d vid pidfd %d",
+ self->child_pid1, self->child_pidfd1);
+ }
+
+ /*
+ * Can't setns to a user namespace outside of our hierarchy since we
+ * don't have caps in there and didn't create it. That means that under
+ * no circumstances should we be able to setns to any of the other
+ * ones since they aren't owned by our user namespace.
+ */
+ for (i = 0; i < PIDFD_NS_MAX; i++) {
+ const struct ns_info *info = &ns_info[i];
+
+ if (self->child_nsfds2[i] < 0 || !info->flag)
+ continue;
+
+ ASSERT_NE(setns(self->child_pidfd2, info->flag), 0) {
+ TH_LOG("Managed to setns to %s namespace of %d via pidfd %d",
+ info->name, self->child_pid2,
+ self->child_pidfd2);
+ }
+ TH_LOG("%m - Correctly failed to setns to %s namespace of %d via pidfd %d",
+ info->name, self->child_pid2,
+ self->child_pidfd2);
+
+ ASSERT_NE(setns(self->child_nsfds2[i], info->flag), 0) {
+ TH_LOG("Managed to setns to %s namespace of %d via nsfd %d",
+ info->name, self->child_pid2,
+ self->child_nsfds2[i]);
+ }
+ TH_LOG("%m - Correctly failed to setns to %s namespace of %d via nsfd %d",
+ info->name, self->child_pid2,
+ self->child_nsfds2[i]);
+ }
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/powerpc/Makefile b/tools/testing/selftests/powerpc/Makefile
index 644770c3b754..0830e63818c1 100644
--- a/tools/testing/selftests/powerpc/Makefile
+++ b/tools/testing/selftests/powerpc/Makefile
@@ -19,6 +19,7 @@ SUB_DIRS = alignment \
copyloops \
dscr \
mm \
+ nx-gzip \
pmu \
signal \
primitives \
diff --git a/tools/testing/selftests/powerpc/alignment/.gitignore b/tools/testing/selftests/powerpc/alignment/.gitignore
index 6d4fd014511c..28bc6ca13cc6 100644
--- a/tools/testing/selftests/powerpc/alignment/.gitignore
+++ b/tools/testing/selftests/powerpc/alignment/.gitignore
@@ -1,2 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0-only
copy_first_unaligned
alignment_handler
diff --git a/tools/testing/selftests/powerpc/benchmarks/.gitignore b/tools/testing/selftests/powerpc/benchmarks/.gitignore
index 9161679b1e1a..c9ce13983c99 100644
--- a/tools/testing/selftests/powerpc/benchmarks/.gitignore
+++ b/tools/testing/selftests/powerpc/benchmarks/.gitignore
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
gettimeofday
context_switch
fork
diff --git a/tools/testing/selftests/powerpc/benchmarks/Makefile b/tools/testing/selftests/powerpc/benchmarks/Makefile
index d40300a65b42..a32a6ab89914 100644
--- a/tools/testing/selftests/powerpc/benchmarks/Makefile
+++ b/tools/testing/selftests/powerpc/benchmarks/Makefile
@@ -2,6 +2,8 @@
TEST_GEN_PROGS := gettimeofday context_switch fork mmap_bench futex_bench null_syscall
TEST_GEN_FILES := exec_target
+TEST_FILES := settings
+
CFLAGS += -O2
top_srcdir = ../../../../..
diff --git a/tools/testing/selftests/powerpc/benchmarks/settings b/tools/testing/selftests/powerpc/benchmarks/settings
new file mode 100644
index 000000000000..e7b9417537fb
--- /dev/null
+++ b/tools/testing/selftests/powerpc/benchmarks/settings
@@ -0,0 +1 @@
+timeout=0
diff --git a/tools/testing/selftests/powerpc/cache_shape/.gitignore b/tools/testing/selftests/powerpc/cache_shape/.gitignore
index ec1848434be5..b385eee3012c 100644
--- a/tools/testing/selftests/powerpc/cache_shape/.gitignore
+++ b/tools/testing/selftests/powerpc/cache_shape/.gitignore
@@ -1 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
cache_shape
diff --git a/tools/testing/selftests/powerpc/copyloops/.gitignore b/tools/testing/selftests/powerpc/copyloops/.gitignore
index 12ef5b031974..ddaf140b8255 100644
--- a/tools/testing/selftests/powerpc/copyloops/.gitignore
+++ b/tools/testing/selftests/powerpc/copyloops/.gitignore
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
copyuser_64_t0
copyuser_64_t1
copyuser_64_t2
diff --git a/tools/testing/selftests/powerpc/dscr/.gitignore b/tools/testing/selftests/powerpc/dscr/.gitignore
index b585c6c1564a..1d08b15af697 100644
--- a/tools/testing/selftests/powerpc/dscr/.gitignore
+++ b/tools/testing/selftests/powerpc/dscr/.gitignore
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
dscr_default_test
dscr_explicit_test
dscr_inherit_exec_test
diff --git a/tools/testing/selftests/powerpc/dscr/Makefile b/tools/testing/selftests/powerpc/dscr/Makefile
index 5df476364b4d..cfa6eedcb66c 100644
--- a/tools/testing/selftests/powerpc/dscr/Makefile
+++ b/tools/testing/selftests/powerpc/dscr/Makefile
@@ -3,6 +3,8 @@ TEST_GEN_PROGS := dscr_default_test dscr_explicit_test dscr_user_test \
dscr_inherit_test dscr_inherit_exec_test dscr_sysfs_test \
dscr_sysfs_thread_test
+TEST_FILES := settings
+
top_srcdir = ../../../../..
include ../../lib.mk
diff --git a/tools/testing/selftests/powerpc/dscr/settings b/tools/testing/selftests/powerpc/dscr/settings
new file mode 100644
index 000000000000..e7b9417537fb
--- /dev/null
+++ b/tools/testing/selftests/powerpc/dscr/settings
@@ -0,0 +1 @@
+timeout=0
diff --git a/tools/testing/selftests/powerpc/eeh/eeh-basic.sh b/tools/testing/selftests/powerpc/eeh/eeh-basic.sh
index f988d2f42e8f..8a8d0f456946 100755
--- a/tools/testing/selftests/powerpc/eeh/eeh-basic.sh
+++ b/tools/testing/selftests/powerpc/eeh/eeh-basic.sh
@@ -41,6 +41,11 @@ for dev in `ls -1 /sys/bus/pci/devices/ | grep '\.0$'` ; do
continue;
fi
+ if [ "ahci" = "$(basename $(realpath /sys/bus/pci/devices/$dev/driver))" ] ; then
+ echo "$dev, Skipped: ahci doesn't support recovery"
+ continue
+ fi
+
# Don't inject errosr into an already-frozen PE. This happens with
# PEs that contain multiple PCI devices (e.g. multi-function cards)
# and injecting new errors during the recovery process will probably
diff --git a/tools/testing/selftests/powerpc/math/.gitignore b/tools/testing/selftests/powerpc/math/.gitignore
index 50ded63e25b7..e31ca6f453ed 100644
--- a/tools/testing/selftests/powerpc/math/.gitignore
+++ b/tools/testing/selftests/powerpc/math/.gitignore
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
fpu_syscall
vmx_syscall
fpu_preempt
diff --git a/tools/testing/selftests/powerpc/mm/.gitignore b/tools/testing/selftests/powerpc/mm/.gitignore
index 0ebeaea22641..2ca523255b1b 100644
--- a/tools/testing/selftests/powerpc/mm/.gitignore
+++ b/tools/testing/selftests/powerpc/mm/.gitignore
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
hugetlb_vs_thp_test
subpage_prot
tempfile
@@ -6,3 +7,4 @@ segv_errors
wild_bctr
large_vm_fork_separation
bad_accesses
+tlbie_test
diff --git a/tools/testing/selftests/powerpc/nx-gzip/99-nx-gzip.rules b/tools/testing/selftests/powerpc/nx-gzip/99-nx-gzip.rules
new file mode 100644
index 000000000000..5a7118495cb3
--- /dev/null
+++ b/tools/testing/selftests/powerpc/nx-gzip/99-nx-gzip.rules
@@ -0,0 +1 @@
+SUBSYSTEM=="nxgzip", KERNEL=="nx-gzip", MODE="0666"
diff --git a/tools/testing/selftests/powerpc/nx-gzip/Makefile b/tools/testing/selftests/powerpc/nx-gzip/Makefile
new file mode 100644
index 000000000000..640fad6cc2c7
--- /dev/null
+++ b/tools/testing/selftests/powerpc/nx-gzip/Makefile
@@ -0,0 +1,8 @@
+CFLAGS = -O3 -m64 -I./include
+
+TEST_GEN_FILES := gzfht_test gunz_test
+TEST_PROGS := nx-gzip-test.sh
+
+include ../../lib.mk
+
+$(TEST_GEN_FILES): gzip_vas.c
diff --git a/tools/testing/selftests/powerpc/nx-gzip/README b/tools/testing/selftests/powerpc/nx-gzip/README
new file mode 100644
index 000000000000..9809dbaa1905
--- /dev/null
+++ b/tools/testing/selftests/powerpc/nx-gzip/README
@@ -0,0 +1,45 @@
+Test the nx-gzip function:
+=========================
+
+Verify that following device exists:
+ /dev/crypto/nx-gzip
+If you get a permission error run as sudo or set the device permissions:
+ sudo chmod go+rw /dev/crypto/nx-gzip
+However, chmod may not survive across boots. You may create a udev file such
+as:
+ /etc/udev/rules.d/99-nx-gzip.rules
+
+
+To manually build and run:
+$ gcc -O3 -I./include -o gzfht_test gzfht_test.c gzip_vas.c
+$ gcc -O3 -I./include -o gunz_test gunz_test.c gzip_vas.c
+
+
+Compress any file using Fixed Huffman mode. Output will have a .nx.gz suffix:
+$ ./gzfht_test gzip_vas.c
+file gzip_vas.c read, 6413 bytes
+compressed 6413 to 3124 bytes total, crc32 checksum = abd15e8a
+
+
+Uncompress the previous output. Output will have a .nx.gunzip suffix:
+./gunz_test gzip_vas.c.nx.gz
+gzHeader FLG 0
+00 00 00 00 04 03
+gzHeader MTIME, XFL, OS ignored
+computed checksum abd15e8a isize 0000190d
+stored checksum abd15e8a isize 0000190d
+decomp is complete: fclose
+
+
+Compare two files:
+$ sha1sum gzip_vas.c.nx.gz.nx.gunzip gzip_vas.c
+bf43e3c0c3651f5f22b6f9784cd9b1eeab4120b6 gzip_vas.c.nx.gz.nx.gunzip
+bf43e3c0c3651f5f22b6f9784cd9b1eeab4120b6 gzip_vas.c
+
+
+Note that the code here are intended for testing the nx-gzip hardware function.
+They are not intended for demonstrating performance or compression ratio.
+By being simplistic these selftests expect to allocate the entire set of source
+and target pages in the memory so it needs enough memory to work.
+For more information and source code consider using:
+https://github.com/libnxz/power-gzip
diff --git a/tools/testing/selftests/powerpc/nx-gzip/gunz_test.c b/tools/testing/selftests/powerpc/nx-gzip/gunz_test.c
new file mode 100644
index 000000000000..6ee0fded0391
--- /dev/null
+++ b/tools/testing/selftests/powerpc/nx-gzip/gunz_test.c
@@ -0,0 +1,1028 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+/* P9 gunzip sample code for demonstrating the P9 NX hardware
+ * interface. Not intended for productive uses or for performance or
+ * compression ratio measurements. Note also that /dev/crypto/gzip,
+ * VAS and skiboot support are required
+ *
+ * Copyright 2020 IBM Corp.
+ *
+ * Author: Bulent Abali <abali@us.ibm.com>
+ *
+ * https://github.com/libnxz/power-gzip for zlib api and other utils
+ * Definitions of acronyms used here. See
+ * P9 NX Gzip Accelerator User's Manual for details:
+ * https://github.com/libnxz/power-gzip/blob/develop/doc/power_nx_gzip_um.pdf
+ *
+ * adler/crc: 32 bit checksums appended to stream tail
+ * ce: completion extension
+ * cpb: coprocessor parameter block (metadata)
+ * crb: coprocessor request block (command)
+ * csb: coprocessor status block (status)
+ * dht: dynamic huffman table
+ * dde: data descriptor element (address, length)
+ * ddl: list of ddes
+ * dh/fh: dynamic and fixed huffman types
+ * fc: coprocessor function code
+ * histlen: history/dictionary length
+ * history: sliding window of up to 32KB of data
+ * lzcount: Deflate LZ symbol counts
+ * rembytecnt: remaining byte count
+ * sfbt: source final block type; last block's type during decomp
+ * spbc: source processed byte count
+ * subc: source unprocessed bit count
+ * tebc: target ending bit count; valid bits in the last byte
+ * tpbc: target processed byte count
+ * vas: virtual accelerator switch; the user mode interface
+ */
+
+#define _ISOC11_SOURCE // For aligned_alloc()
+#define _DEFAULT_SOURCE // For endian.h
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <stdint.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <sys/time.h>
+#include <sys/fcntl.h>
+#include <sys/mman.h>
+#include <endian.h>
+#include <bits/endian.h>
+#include <sys/ioctl.h>
+#include <assert.h>
+#include <errno.h>
+#include <signal.h>
+#include "nxu.h"
+#include "nx.h"
+#include "crb.h"
+
+int nx_dbg;
+FILE *nx_gzip_log;
+
+#define NX_MIN(X, Y) (((X) < (Y))?(X):(Y))
+#define NX_MAX(X, Y) (((X) > (Y))?(X):(Y))
+
+#define GETINPC(X) fgetc(X)
+#define FNAME_MAX 1024
+
+/* fifo queue management */
+#define fifo_used_bytes(used) (used)
+#define fifo_free_bytes(used, len) ((len)-(used))
+/* amount of free bytes in the first and last parts */
+#define fifo_free_first_bytes(cur, used, len) ((((cur)+(used)) <= (len)) \
+ ? (len)-((cur)+(used)) : 0)
+#define fifo_free_last_bytes(cur, used, len) ((((cur)+(used)) <= (len)) \
+ ? (cur) : (len)-(used))
+/* amount of used bytes in the first and last parts */
+#define fifo_used_first_bytes(cur, used, len) ((((cur)+(used)) <= (len)) \
+ ? (used) : (len)-(cur))
+#define fifo_used_last_bytes(cur, used, len) ((((cur)+(used)) <= (len)) \
+ ? 0 : ((used)+(cur))-(len))
+/* first and last free parts start here */
+#define fifo_free_first_offset(cur, used) ((cur)+(used))
+#define fifo_free_last_offset(cur, used, len) \
+ fifo_used_last_bytes(cur, used, len)
+/* first and last used parts start here */
+#define fifo_used_first_offset(cur) (cur)
+#define fifo_used_last_offset(cur) (0)
+
+const int fifo_in_len = 1<<24;
+const int fifo_out_len = 1<<24;
+const int page_sz = 1<<16;
+const int line_sz = 1<<7;
+const int window_max = 1<<15;
+
+/*
+ * Adds an (address, len) pair to the list of ddes (ddl) and updates
+ * the base dde. ddl[0] is the only dde in a direct dde which
+ * contains a single (addr,len) pair. For more pairs, ddl[0] becomes
+ * the indirect (base) dde that points to a list of direct ddes.
+ * See Section 6.4 of the NX-gzip user manual for DDE description.
+ * Addr=NULL, len=0 clears the ddl[0]. Returns the total number of
+ * bytes in ddl. Caller is responsible for allocting the array of
+ * nx_dde_t *ddl. If N addresses are required in the scatter-gather
+ * list, the ddl array must have N+1 entries minimum.
+ */
+static inline uint32_t nx_append_dde(struct nx_dde_t *ddl, void *addr,
+ uint32_t len)
+{
+ uint32_t ddecnt;
+ uint32_t bytes;
+
+ if (addr == NULL && len == 0) {
+ clearp_dde(ddl);
+ return 0;
+ }
+
+ NXPRT(fprintf(stderr, "%d: %s addr %p len %x\n", __LINE__, addr,
+ __func__, len));
+
+ /* Number of ddes in the dde list ; == 0 when it is a direct dde */
+ ddecnt = getpnn(ddl, dde_count);
+ bytes = getp32(ddl, ddebc);
+
+ if (ddecnt == 0 && bytes == 0) {
+ /* First dde is unused; make it a direct dde */
+ bytes = len;
+ putp32(ddl, ddebc, bytes);
+ putp64(ddl, ddead, (uint64_t) addr);
+ } else if (ddecnt == 0) {
+ /* Converting direct to indirect dde
+ * ddl[0] becomes head dde of ddl
+ * copy direct to indirect first.
+ */
+ ddl[1] = ddl[0];
+
+ /* Add the new dde next */
+ clear_dde(ddl[2]);
+ put32(ddl[2], ddebc, len);
+ put64(ddl[2], ddead, (uint64_t) addr);
+
+ /* Ddl head points to 2 direct ddes */
+ ddecnt = 2;
+ putpnn(ddl, dde_count, ddecnt);
+ bytes = bytes + len;
+ putp32(ddl, ddebc, bytes);
+ /* Pointer to the first direct dde */
+ putp64(ddl, ddead, (uint64_t) &ddl[1]);
+ } else {
+ /* Append a dde to an existing indirect ddl */
+ ++ddecnt;
+ clear_dde(ddl[ddecnt]);
+ put64(ddl[ddecnt], ddead, (uint64_t) addr);
+ put32(ddl[ddecnt], ddebc, len);
+
+ putpnn(ddl, dde_count, ddecnt);
+ bytes = bytes + len;
+ putp32(ddl, ddebc, bytes); /* byte sum of all dde */
+ }
+ return bytes;
+}
+
+/*
+ * Touch specified number of pages represented in number bytes
+ * beginning from the first buffer in a dde list.
+ * Do not touch the pages past buf_sz-th byte's page.
+ *
+ * Set buf_sz = 0 to touch all pages described by the ddep.
+ */
+static int nx_touch_pages_dde(struct nx_dde_t *ddep, long buf_sz, long page_sz,
+ int wr)
+{
+ uint32_t indirect_count;
+ uint32_t buf_len;
+ long total;
+ uint64_t buf_addr;
+ struct nx_dde_t *dde_list;
+ int i;
+
+ assert(!!ddep);
+
+ indirect_count = getpnn(ddep, dde_count);
+
+ NXPRT(fprintf(stderr, "%s dde_count %d request len ", __func__,
+ indirect_count));
+ NXPRT(fprintf(stderr, "0x%lx\n", buf_sz));
+
+ if (indirect_count == 0) {
+ /* Direct dde */
+ buf_len = getp32(ddep, ddebc);
+ buf_addr = getp64(ddep, ddead);
+
+ NXPRT(fprintf(stderr, "touch direct ddebc 0x%x ddead %p\n",
+ buf_len, (void *)buf_addr));
+
+ if (buf_sz == 0)
+ nxu_touch_pages((void *)buf_addr, buf_len, page_sz, wr);
+ else
+ nxu_touch_pages((void *)buf_addr, NX_MIN(buf_len,
+ buf_sz), page_sz, wr);
+
+ return ERR_NX_OK;
+ }
+
+ /* Indirect dde */
+ if (indirect_count > MAX_DDE_COUNT)
+ return ERR_NX_EXCESSIVE_DDE;
+
+ /* First address of the list */
+ dde_list = (struct nx_dde_t *) getp64(ddep, ddead);
+
+ if (buf_sz == 0)
+ buf_sz = getp32(ddep, ddebc);
+
+ total = 0;
+ for (i = 0; i < indirect_count; i++) {
+ buf_len = get32(dde_list[i], ddebc);
+ buf_addr = get64(dde_list[i], ddead);
+ total += buf_len;
+
+ NXPRT(fprintf(stderr, "touch loop len 0x%x ddead %p total ",
+ buf_len, (void *)buf_addr));
+ NXPRT(fprintf(stderr, "0x%lx\n", total));
+
+ /* Touching fewer pages than encoded in the ddebc */
+ if (total > buf_sz) {
+ buf_len = NX_MIN(buf_len, total - buf_sz);
+ nxu_touch_pages((void *)buf_addr, buf_len, page_sz, wr);
+ NXPRT(fprintf(stderr, "touch loop break len 0x%x ",
+ buf_len));
+ NXPRT(fprintf(stderr, "ddead %p\n", (void *)buf_addr));
+ break;
+ }
+ nxu_touch_pages((void *)buf_addr, buf_len, page_sz, wr);
+ }
+ return ERR_NX_OK;
+}
+
+/*
+ * Src and dst buffers are supplied in scatter gather lists.
+ * NX function code and other parameters supplied in cmdp.
+ */
+static int nx_submit_job(struct nx_dde_t *src, struct nx_dde_t *dst,
+ struct nx_gzip_crb_cpb_t *cmdp, void *handle)
+{
+ uint64_t csbaddr;
+
+ memset((void *)&cmdp->crb.csb, 0, sizeof(cmdp->crb.csb));
+
+ cmdp->crb.source_dde = *src;
+ cmdp->crb.target_dde = *dst;
+
+ /* Status, output byte count in tpbc */
+ csbaddr = ((uint64_t) &cmdp->crb.csb) & csb_address_mask;
+ put64(cmdp->crb, csb_address, csbaddr);
+
+ /* NX reports input bytes in spbc; cleared */
+ cmdp->cpb.out_spbc_comp_wrap = 0;
+ cmdp->cpb.out_spbc_comp_with_count = 0;
+ cmdp->cpb.out_spbc_decomp = 0;
+
+ /* Clear output */
+ put32(cmdp->cpb, out_crc, INIT_CRC);
+ put32(cmdp->cpb, out_adler, INIT_ADLER);
+
+ /* Submit the crb, the job descriptor, to the accelerator. */
+ return nxu_submit_job(cmdp, handle);
+}
+
+int decompress_file(int argc, char **argv, void *devhandle)
+{
+ FILE *inpf = NULL;
+ FILE *outf = NULL;
+
+ int c, expect, i, cc, rc = 0;
+ char gzfname[FNAME_MAX];
+
+ /* Queuing, file ops, byte counting */
+ char *fifo_in, *fifo_out;
+ int used_in, cur_in, used_out, cur_out, read_sz, n;
+ int first_free, last_free, first_used, last_used;
+ int first_offset, last_offset;
+ int write_sz, free_space, source_sz;
+ int source_sz_estimate, target_sz_estimate;
+ uint64_t last_comp_ratio = 0; /* 1000 max */
+ uint64_t total_out = 0;
+ int is_final, is_eof;
+
+ /* nx hardware */
+ int sfbt, subc, spbc, tpbc, nx_ce, fc, resuming = 0;
+ int history_len = 0;
+ struct nx_gzip_crb_cpb_t cmd, *cmdp;
+ struct nx_dde_t *ddl_in;
+ struct nx_dde_t dde_in[6] __aligned(128);
+ struct nx_dde_t *ddl_out;
+ struct nx_dde_t dde_out[6] __aligned(128);
+ int pgfault_retries;
+
+ /* when using mmap'ed files */
+ off_t input_file_offset;
+
+ if (argc > 2) {
+ fprintf(stderr, "usage: %s <fname> or stdin\n", argv[0]);
+ fprintf(stderr, " writes to stdout or <fname>.nx.gunzip\n");
+ return -1;
+ }
+
+ if (argc == 1) {
+ inpf = stdin;
+ outf = stdout;
+ } else if (argc == 2) {
+ char w[1024];
+ char *wp;
+
+ inpf = fopen(argv[1], "r");
+ if (inpf == NULL) {
+ perror(argv[1]);
+ return -1;
+ }
+
+ /* Make a new file name to write to. Ignoring '.gz' */
+ wp = (NULL != (wp = strrchr(argv[1], '/'))) ? (wp+1) : argv[1];
+ strcpy(w, wp);
+ strcat(w, ".nx.gunzip");
+
+ outf = fopen(w, "w");
+ if (outf == NULL) {
+ perror(w);
+ return -1;
+ }
+ }
+
+ /* Decode the gzip header */
+ c = GETINPC(inpf); expect = 0x1f; /* ID1 */
+ if (c != expect)
+ goto err1;
+
+ c = GETINPC(inpf); expect = 0x8b; /* ID2 */
+ if (c != expect)
+ goto err1;
+
+ c = GETINPC(inpf); expect = 0x08; /* CM */
+ if (c != expect)
+ goto err1;
+
+ int flg = GETINPC(inpf); /* FLG */
+
+ if (flg & 0xE0 || flg & 0x4 || flg == EOF)
+ goto err2;
+
+ fprintf(stderr, "gzHeader FLG %x\n", flg);
+
+ /* Read 6 bytes; ignoring the MTIME, XFL, OS fields in this
+ * sample code.
+ */
+ for (i = 0; i < 6; i++) {
+ char tmp[10];
+
+ tmp[i] = GETINPC(inpf);
+ if (tmp[i] == EOF)
+ goto err3;
+ fprintf(stderr, "%02x ", tmp[i]);
+ if (i == 5)
+ fprintf(stderr, "\n");
+ }
+ fprintf(stderr, "gzHeader MTIME, XFL, OS ignored\n");
+
+ /* FNAME */
+ if (flg & 0x8) {
+ int k = 0;
+
+ do {
+ c = GETINPC(inpf);
+ if (c == EOF || k >= FNAME_MAX)
+ goto err3;
+ gzfname[k++] = c;
+ } while (c);
+ fprintf(stderr, "gzHeader FNAME: %s\n", gzfname);
+ }
+
+ /* FHCRC */
+ if (flg & 0x2) {
+ c = GETINPC(inpf);
+ if (c == EOF)
+ goto err3;
+ c = GETINPC(inpf);
+ if (c == EOF)
+ goto err3;
+ fprintf(stderr, "gzHeader FHCRC: ignored\n");
+ }
+
+ used_in = cur_in = used_out = cur_out = 0;
+ is_final = is_eof = 0;
+
+ /* Allocate one page larger to prevent page faults due to NX
+ * overfetching.
+ * Either do this (char*)(uintptr_t)aligned_alloc or use
+ * -std=c11 flag to make the int-to-pointer warning go away.
+ */
+ assert((fifo_in = (char *)(uintptr_t)aligned_alloc(line_sz,
+ fifo_in_len + page_sz)) != NULL);
+ assert((fifo_out = (char *)(uintptr_t)aligned_alloc(line_sz,
+ fifo_out_len + page_sz + line_sz)) != NULL);
+ /* Leave unused space due to history rounding rules */
+ fifo_out = fifo_out + line_sz;
+ nxu_touch_pages(fifo_out, fifo_out_len, page_sz, 1);
+
+ ddl_in = &dde_in[0];
+ ddl_out = &dde_out[0];
+ cmdp = &cmd;
+ memset(&cmdp->crb, 0, sizeof(cmdp->crb));
+
+read_state:
+
+ /* Read from .gz file */
+
+ NXPRT(fprintf(stderr, "read_state:\n"));
+
+ if (is_eof != 0)
+ goto write_state;
+
+ /* We read in to fifo_in in two steps: first: read in to from
+ * cur_in to the end of the buffer. last: if free space wrapped
+ * around, read from fifo_in offset 0 to offset cur_in.
+ */
+
+ /* Reset fifo head to reduce unnecessary wrap arounds */
+ cur_in = (used_in == 0) ? 0 : cur_in;
+
+ /* Free space total is reduced by a gap */
+ free_space = NX_MAX(0, fifo_free_bytes(used_in, fifo_in_len)
+ - line_sz);
+
+ /* Free space may wrap around as first and last */
+ first_free = fifo_free_first_bytes(cur_in, used_in, fifo_in_len);
+ last_free = fifo_free_last_bytes(cur_in, used_in, fifo_in_len);
+
+ /* Start offsets of the free memory */
+ first_offset = fifo_free_first_offset(cur_in, used_in);
+ last_offset = fifo_free_last_offset(cur_in, used_in, fifo_in_len);
+
+ /* Reduce read_sz because of the line_sz gap */
+ read_sz = NX_MIN(free_space, first_free);
+ n = 0;
+ if (read_sz > 0) {
+ /* Read in to offset cur_in + used_in */
+ n = fread(fifo_in + first_offset, 1, read_sz, inpf);
+ used_in = used_in + n;
+ free_space = free_space - n;
+ assert(n <= read_sz);
+ if (n != read_sz) {
+ /* Either EOF or error; exit the read loop */
+ is_eof = 1;
+ goto write_state;
+ }
+ }
+
+ /* If free space wrapped around */
+ if (last_free > 0) {
+ /* Reduce read_sz because of the line_sz gap */
+ read_sz = NX_MIN(free_space, last_free);
+ n = 0;
+ if (read_sz > 0) {
+ n = fread(fifo_in + last_offset, 1, read_sz, inpf);
+ used_in = used_in + n; /* Increase used space */
+ free_space = free_space - n; /* Decrease free space */
+ assert(n <= read_sz);
+ if (n != read_sz) {
+ /* Either EOF or error; exit the read loop */
+ is_eof = 1;
+ goto write_state;
+ }
+ }
+ }
+
+ /* At this point we have used_in bytes in fifo_in with the
+ * data head starting at cur_in and possibly wrapping around.
+ */
+
+write_state:
+
+ /* Write decompressed data to output file */
+
+ NXPRT(fprintf(stderr, "write_state:\n"));
+
+ if (used_out == 0)
+ goto decomp_state;
+
+ /* If fifo_out has data waiting, write it out to the file to
+ * make free target space for the accelerator used bytes in
+ * the first and last parts of fifo_out.
+ */
+
+ first_used = fifo_used_first_bytes(cur_out, used_out, fifo_out_len);
+ last_used = fifo_used_last_bytes(cur_out, used_out, fifo_out_len);
+
+ write_sz = first_used;
+
+ n = 0;
+ if (write_sz > 0) {
+ n = fwrite(fifo_out + cur_out, 1, write_sz, outf);
+ used_out = used_out - n;
+ /* Move head of the fifo */
+ cur_out = (cur_out + n) % fifo_out_len;
+ assert(n <= write_sz);
+ if (n != write_sz) {
+ fprintf(stderr, "error: write\n");
+ rc = -1;
+ goto err5;
+ }
+ }
+
+ if (last_used > 0) { /* If more data available in the last part */
+ write_sz = last_used; /* Keep it here for later */
+ n = 0;
+ if (write_sz > 0) {
+ n = fwrite(fifo_out, 1, write_sz, outf);
+ used_out = used_out - n;
+ cur_out = (cur_out + n) % fifo_out_len;
+ assert(n <= write_sz);
+ if (n != write_sz) {
+ fprintf(stderr, "error: write\n");
+ rc = -1;
+ goto err5;
+ }
+ }
+ }
+
+decomp_state:
+
+ /* NX decompresses input data */
+
+ NXPRT(fprintf(stderr, "decomp_state:\n"));
+
+ if (is_final)
+ goto finish_state;
+
+ /* Address/len lists */
+ clearp_dde(ddl_in);
+ clearp_dde(ddl_out);
+
+ /* FC, CRC, HistLen, Table 6-6 */
+ if (resuming) {
+ /* Resuming a partially decompressed input.
+ * The key to resume is supplying the 32KB
+ * dictionary (history) to NX, which is basically
+ * the last 32KB of output produced.
+ */
+ fc = GZIP_FC_DECOMPRESS_RESUME;
+
+ cmdp->cpb.in_crc = cmdp->cpb.out_crc;
+ cmdp->cpb.in_adler = cmdp->cpb.out_adler;
+
+ /* Round up the history size to quadword. Section 2.10 */
+ history_len = (history_len + 15) / 16;
+ putnn(cmdp->cpb, in_histlen, history_len);
+ history_len = history_len * 16; /* bytes */
+
+ if (history_len > 0) {
+ /* Chain in the history buffer to the DDE list */
+ if (cur_out >= history_len) {
+ nx_append_dde(ddl_in, fifo_out
+ + (cur_out - history_len),
+ history_len);
+ } else {
+ nx_append_dde(ddl_in, fifo_out
+ + ((fifo_out_len + cur_out)
+ - history_len),
+ history_len - cur_out);
+ /* Up to 32KB history wraps around fifo_out */
+ nx_append_dde(ddl_in, fifo_out, cur_out);
+ }
+
+ }
+ } else {
+ /* First decompress job */
+ fc = GZIP_FC_DECOMPRESS;
+
+ history_len = 0;
+ /* Writing 0 clears out subc as well */
+ cmdp->cpb.in_histlen = 0;
+ total_out = 0;
+
+ put32(cmdp->cpb, in_crc, INIT_CRC);
+ put32(cmdp->cpb, in_adler, INIT_ADLER);
+ put32(cmdp->cpb, out_crc, INIT_CRC);
+ put32(cmdp->cpb, out_adler, INIT_ADLER);
+
+ /* Assuming 10% compression ratio initially; use the
+ * most recently measured compression ratio as a
+ * heuristic to estimate the input and output
+ * sizes. If we give too much input, the target buffer
+ * overflows and NX cycles are wasted, and then we
+ * must retry with smaller input size. 1000 is 100%.
+ */
+ last_comp_ratio = 100UL;
+ }
+ cmdp->crb.gzip_fc = 0;
+ putnn(cmdp->crb, gzip_fc, fc);
+
+ /*
+ * NX source buffers
+ */
+ first_used = fifo_used_first_bytes(cur_in, used_in, fifo_in_len);
+ last_used = fifo_used_last_bytes(cur_in, used_in, fifo_in_len);
+
+ if (first_used > 0)
+ nx_append_dde(ddl_in, fifo_in + cur_in, first_used);
+
+ if (last_used > 0)
+ nx_append_dde(ddl_in, fifo_in, last_used);
+
+ /*
+ * NX target buffers
+ */
+ first_free = fifo_free_first_bytes(cur_out, used_out, fifo_out_len);
+ last_free = fifo_free_last_bytes(cur_out, used_out, fifo_out_len);
+
+ /* Reduce output free space amount not to overwrite the history */
+ int target_max = NX_MAX(0, fifo_free_bytes(used_out, fifo_out_len)
+ - (1<<16));
+
+ NXPRT(fprintf(stderr, "target_max %d (0x%x)\n", target_max,
+ target_max));
+
+ first_free = NX_MIN(target_max, first_free);
+ if (first_free > 0) {
+ first_offset = fifo_free_first_offset(cur_out, used_out);
+ nx_append_dde(ddl_out, fifo_out + first_offset, first_free);
+ }
+
+ if (last_free > 0) {
+ last_free = NX_MIN(target_max - first_free, last_free);
+ if (last_free > 0) {
+ last_offset = fifo_free_last_offset(cur_out, used_out,
+ fifo_out_len);
+ nx_append_dde(ddl_out, fifo_out + last_offset,
+ last_free);
+ }
+ }
+
+ /* Target buffer size is used to limit the source data size
+ * based on previous measurements of compression ratio.
+ */
+
+ /* source_sz includes history */
+ source_sz = getp32(ddl_in, ddebc);
+ assert(source_sz > history_len);
+ source_sz = source_sz - history_len;
+
+ /* Estimating how much source is needed to 3/4 fill a
+ * target_max size target buffer. If we overshoot, then NX
+ * must repeat the job with smaller input and we waste
+ * bandwidth. If we undershoot then we use more NX calls than
+ * necessary.
+ */
+
+ source_sz_estimate = ((uint64_t)target_max * last_comp_ratio * 3UL)
+ / 4000;
+
+ if (source_sz_estimate < source_sz) {
+ /* Target might be small, therefore limiting the
+ * source data.
+ */
+ source_sz = source_sz_estimate;
+ target_sz_estimate = target_max;
+ } else {
+ /* Source file might be small, therefore limiting target
+ * touch pages to a smaller value to save processor cycles.
+ */
+ target_sz_estimate = ((uint64_t)source_sz * 1000UL)
+ / (last_comp_ratio + 1);
+ target_sz_estimate = NX_MIN(2 * target_sz_estimate,
+ target_max);
+ }
+
+ source_sz = source_sz + history_len;
+
+ /* Some NX condition codes require submitting the NX job again.
+ * Kernel doesn't handle NX page faults. Expects user code to
+ * touch pages.
+ */
+ pgfault_retries = NX_MAX_FAULTS;
+
+restart_nx:
+
+ putp32(ddl_in, ddebc, source_sz);
+
+ /* Fault in pages */
+ nxu_touch_pages(cmdp, sizeof(struct nx_gzip_crb_cpb_t), page_sz, 1);
+ nx_touch_pages_dde(ddl_in, 0, page_sz, 0);
+ nx_touch_pages_dde(ddl_out, target_sz_estimate, page_sz, 1);
+
+ /* Send job to NX */
+ cc = nx_submit_job(ddl_in, ddl_out, cmdp, devhandle);
+
+ switch (cc) {
+
+ case ERR_NX_TRANSLATION:
+
+ /* We touched the pages ahead of time. In the most common case
+ * we shouldn't be here. But may be some pages were paged out.
+ * Kernel should have placed the faulting address to fsaddr.
+ */
+ NXPRT(fprintf(stderr, "ERR_NX_TRANSLATION %p\n",
+ (void *)cmdp->crb.csb.fsaddr));
+
+ if (pgfault_retries == NX_MAX_FAULTS) {
+ /* Try once with exact number of pages */
+ --pgfault_retries;
+ goto restart_nx;
+ } else if (pgfault_retries > 0) {
+ /* If still faulting try fewer input pages
+ * assuming memory outage
+ */
+ if (source_sz > page_sz)
+ source_sz = NX_MAX(source_sz / 2, page_sz);
+ --pgfault_retries;
+ goto restart_nx;
+ } else {
+ fprintf(stderr, "cannot make progress; too many ");
+ fprintf(stderr, "page fault retries cc= %d\n", cc);
+ rc = -1;
+ goto err5;
+ }
+
+ case ERR_NX_DATA_LENGTH:
+
+ NXPRT(fprintf(stderr, "ERR_NX_DATA_LENGTH; "));
+ NXPRT(fprintf(stderr, "stream may have trailing data\n"));
+
+ /* Not an error in the most common case; it just says
+ * there is trailing data that we must examine.
+ *
+ * CC=3 CE(1)=0 CE(0)=1 indicates partial completion
+ * Fig.6-7 and Table 6-8.
+ */
+ nx_ce = get_csb_ce_ms3b(cmdp->crb.csb);
+
+ if (!csb_ce_termination(nx_ce) &&
+ csb_ce_partial_completion(nx_ce)) {
+ /* Check CPB for more information
+ * spbc and tpbc are valid
+ */
+ sfbt = getnn(cmdp->cpb, out_sfbt); /* Table 6-4 */
+ subc = getnn(cmdp->cpb, out_subc); /* Table 6-4 */
+ spbc = get32(cmdp->cpb, out_spbc_decomp);
+ tpbc = get32(cmdp->crb.csb, tpbc);
+ assert(target_max >= tpbc);
+
+ goto ok_cc3; /* not an error */
+ } else {
+ /* History length error when CE(1)=1 CE(0)=0. */
+ rc = -1;
+ fprintf(stderr, "history length error cc= %d\n", cc);
+ goto err5;
+ }
+
+ case ERR_NX_TARGET_SPACE:
+
+ /* Target buffer not large enough; retry smaller input
+ * data; give at least 1 byte. SPBC/TPBC are not valid.
+ */
+ assert(source_sz > history_len);
+ source_sz = ((source_sz - history_len + 2) / 2) + history_len;
+ NXPRT(fprintf(stderr, "ERR_NX_TARGET_SPACE; retry with "));
+ NXPRT(fprintf(stderr, "smaller input data src %d hist %d\n",
+ source_sz, history_len));
+ goto restart_nx;
+
+ case ERR_NX_OK:
+
+ /* This should not happen for gzip formatted data;
+ * we need trailing crc and isize
+ */
+ fprintf(stderr, "ERR_NX_OK\n");
+ spbc = get32(cmdp->cpb, out_spbc_decomp);
+ tpbc = get32(cmdp->crb.csb, tpbc);
+ assert(target_max >= tpbc);
+ assert(spbc >= history_len);
+ source_sz = spbc - history_len;
+ goto offsets_state;
+
+ default:
+ fprintf(stderr, "error: cc= %d\n", cc);
+ rc = -1;
+ goto err5;
+ }
+
+ok_cc3:
+
+ NXPRT(fprintf(stderr, "cc3: sfbt: %x\n", sfbt));
+
+ assert(spbc > history_len);
+ source_sz = spbc - history_len;
+
+ /* Table 6-4: Source Final Block Type (SFBT) describes the
+ * last processed deflate block and clues the software how to
+ * resume the next job. SUBC indicates how many input bits NX
+ * consumed but did not process. SPBC indicates how many
+ * bytes of source were given to the accelerator including
+ * history bytes.
+ */
+
+ switch (sfbt) {
+ int dhtlen;
+
+ case 0x0: /* Deflate final EOB received */
+
+ /* Calculating the checksum start position. */
+
+ source_sz = source_sz - subc / 8;
+ is_final = 1;
+ break;
+
+ /* Resume decompression cases are below. Basically
+ * indicates where NX has suspended and how to resume
+ * the input stream.
+ */
+
+ case 0x8: /* Within a literal block; use rembytecount */
+ case 0x9: /* Within a literal block; use rembytecount; bfinal=1 */
+
+ /* Supply the partially processed source byte again */
+ source_sz = source_sz - ((subc + 7) / 8);
+
+ /* SUBC LS 3bits: number of bits in the first source byte need
+ * to be processed.
+ * 000 means all 8 bits; Table 6-3
+ * Clear subc, histlen, sfbt, rembytecnt, dhtlen
+ */
+ cmdp->cpb.in_subc = 0;
+ cmdp->cpb.in_sfbt = 0;
+ putnn(cmdp->cpb, in_subc, subc % 8);
+ putnn(cmdp->cpb, in_sfbt, sfbt);
+ putnn(cmdp->cpb, in_rembytecnt, getnn(cmdp->cpb,
+ out_rembytecnt));
+ break;
+
+ case 0xA: /* Within a FH block; */
+ case 0xB: /* Within a FH block; bfinal=1 */
+
+ source_sz = source_sz - ((subc + 7) / 8);
+
+ /* Clear subc, histlen, sfbt, rembytecnt, dhtlen */
+ cmdp->cpb.in_subc = 0;
+ cmdp->cpb.in_sfbt = 0;
+ putnn(cmdp->cpb, in_subc, subc % 8);
+ putnn(cmdp->cpb, in_sfbt, sfbt);
+ break;
+
+ case 0xC: /* Within a DH block; */
+ case 0xD: /* Within a DH block; bfinal=1 */
+
+ source_sz = source_sz - ((subc + 7) / 8);
+
+ /* Clear subc, histlen, sfbt, rembytecnt, dhtlen */
+ cmdp->cpb.in_subc = 0;
+ cmdp->cpb.in_sfbt = 0;
+ putnn(cmdp->cpb, in_subc, subc % 8);
+ putnn(cmdp->cpb, in_sfbt, sfbt);
+
+ dhtlen = getnn(cmdp->cpb, out_dhtlen);
+ putnn(cmdp->cpb, in_dhtlen, dhtlen);
+ assert(dhtlen >= 42);
+
+ /* Round up to a qword */
+ dhtlen = (dhtlen + 127) / 128;
+
+ while (dhtlen > 0) { /* Copy dht from cpb.out to cpb.in */
+ --dhtlen;
+ cmdp->cpb.in_dht[dhtlen] = cmdp->cpb.out_dht[dhtlen];
+ }
+ break;
+
+ case 0xE: /* Within a block header; bfinal=0; */
+ /* Also given if source data exactly ends (SUBC=0) with
+ * EOB code with BFINAL=0. Means the next byte will
+ * contain a block header.
+ */
+ case 0xF: /* within a block header with BFINAL=1. */
+
+ source_sz = source_sz - ((subc + 7) / 8);
+
+ /* Clear subc, histlen, sfbt, rembytecnt, dhtlen */
+ cmdp->cpb.in_subc = 0;
+ cmdp->cpb.in_sfbt = 0;
+ putnn(cmdp->cpb, in_subc, subc % 8);
+ putnn(cmdp->cpb, in_sfbt, sfbt);
+
+ /* Engine did not process any data */
+ if (is_eof && (source_sz == 0))
+ is_final = 1;
+ }
+
+offsets_state:
+
+ /* Adjust the source and target buffer offsets and lengths */
+
+ NXPRT(fprintf(stderr, "offsets_state:\n"));
+
+ /* Delete input data from fifo_in */
+ used_in = used_in - source_sz;
+ cur_in = (cur_in + source_sz) % fifo_in_len;
+ input_file_offset = input_file_offset + source_sz;
+
+ /* Add output data to fifo_out */
+ used_out = used_out + tpbc;
+
+ assert(used_out <= fifo_out_len);
+
+ total_out = total_out + tpbc;
+
+ /* Deflate history is 32KB max. No need to supply more
+ * than 32KB on a resume.
+ */
+ history_len = (total_out > window_max) ? window_max : total_out;
+
+ /* To estimate expected expansion in the next NX job; 500 means 50%.
+ * Deflate best case is around 1 to 1000.
+ */
+ last_comp_ratio = (1000UL * ((uint64_t)source_sz + 1))
+ / ((uint64_t)tpbc + 1);
+ last_comp_ratio = NX_MAX(NX_MIN(1000UL, last_comp_ratio), 1);
+ NXPRT(fprintf(stderr, "comp_ratio %ld source_sz %d spbc %d tpbc %d\n",
+ last_comp_ratio, source_sz, spbc, tpbc));
+
+ resuming = 1;
+
+finish_state:
+
+ NXPRT(fprintf(stderr, "finish_state:\n"));
+
+ if (is_final) {
+ if (used_out)
+ goto write_state; /* More data to write out */
+ else if (used_in < 8) {
+ /* Need at least 8 more bytes containing gzip crc
+ * and isize.
+ */
+ rc = -1;
+ goto err4;
+ } else {
+ /* Compare checksums and exit */
+ int i;
+ unsigned char tail[8];
+ uint32_t cksum, isize;
+
+ for (i = 0; i < 8; i++)
+ tail[i] = fifo_in[(cur_in + i) % fifo_in_len];
+ fprintf(stderr, "computed checksum %08x isize %08x\n",
+ cmdp->cpb.out_crc, (uint32_t) (total_out
+ % (1ULL<<32)));
+ cksum = ((uint32_t) tail[0] | (uint32_t) tail[1]<<8
+ | (uint32_t) tail[2]<<16
+ | (uint32_t) tail[3]<<24);
+ isize = ((uint32_t) tail[4] | (uint32_t) tail[5]<<8
+ | (uint32_t) tail[6]<<16
+ | (uint32_t) tail[7]<<24);
+ fprintf(stderr, "stored checksum %08x isize %08x\n",
+ cksum, isize);
+
+ if (cksum == cmdp->cpb.out_crc && isize == (uint32_t)
+ (total_out % (1ULL<<32))) {
+ rc = 0; goto ok1;
+ } else {
+ rc = -1; goto err4;
+ }
+ }
+ } else
+ goto read_state;
+
+ return -1;
+
+err1:
+ fprintf(stderr, "error: not a gzip file, expect %x, read %x\n",
+ expect, c);
+ return -1;
+
+err2:
+ fprintf(stderr, "error: the FLG byte is wrong or not being handled\n");
+ return -1;
+
+err3:
+ fprintf(stderr, "error: gzip header\n");
+ return -1;
+
+err4:
+ fprintf(stderr, "error: checksum missing or mismatch\n");
+
+err5:
+ok1:
+ fprintf(stderr, "decomp is complete: fclose\n");
+ fclose(outf);
+
+ return rc;
+}
+
+
+int main(int argc, char **argv)
+{
+ int rc;
+ struct sigaction act;
+ void *handle;
+
+ nx_dbg = 0;
+ nx_gzip_log = NULL;
+ act.sa_handler = 0;
+ act.sa_sigaction = nxu_sigsegv_handler;
+ act.sa_flags = SA_SIGINFO;
+ act.sa_restorer = 0;
+ sigemptyset(&act.sa_mask);
+ sigaction(SIGSEGV, &act, NULL);
+
+ handle = nx_function_begin(NX_FUNC_COMP_GZIP, 0);
+ if (!handle) {
+ fprintf(stderr, "Unable to init NX, errno %d\n", errno);
+ exit(-1);
+ }
+
+ rc = decompress_file(argc, argv, handle);
+
+ nx_function_end(handle);
+
+ return rc;
+}
diff --git a/tools/testing/selftests/powerpc/nx-gzip/gzfht_test.c b/tools/testing/selftests/powerpc/nx-gzip/gzfht_test.c
new file mode 100644
index 000000000000..7496a83f9c9d
--- /dev/null
+++ b/tools/testing/selftests/powerpc/nx-gzip/gzfht_test.c
@@ -0,0 +1,433 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+/* P9 gzip sample code for demonstrating the P9 NX hardware interface.
+ * Not intended for productive uses or for performance or compression
+ * ratio measurements. For simplicity of demonstration, this sample
+ * code compresses in to fixed Huffman blocks only (Deflate btype=1)
+ * and has very simple memory management. Dynamic Huffman blocks
+ * (Deflate btype=2) are more involved as detailed in the user guide.
+ * Note also that /dev/crypto/gzip, VAS and skiboot support are
+ * required.
+ *
+ * Copyright 2020 IBM Corp.
+ *
+ * https://github.com/libnxz/power-gzip for zlib api and other utils
+ *
+ * Author: Bulent Abali <abali@us.ibm.com>
+ *
+ * Definitions of acronyms used here. See
+ * P9 NX Gzip Accelerator User's Manual for details:
+ * https://github.com/libnxz/power-gzip/blob/develop/doc/power_nx_gzip_um.pdf
+ *
+ * adler/crc: 32 bit checksums appended to stream tail
+ * ce: completion extension
+ * cpb: coprocessor parameter block (metadata)
+ * crb: coprocessor request block (command)
+ * csb: coprocessor status block (status)
+ * dht: dynamic huffman table
+ * dde: data descriptor element (address, length)
+ * ddl: list of ddes
+ * dh/fh: dynamic and fixed huffman types
+ * fc: coprocessor function code
+ * histlen: history/dictionary length
+ * history: sliding window of up to 32KB of data
+ * lzcount: Deflate LZ symbol counts
+ * rembytecnt: remaining byte count
+ * sfbt: source final block type; last block's type during decomp
+ * spbc: source processed byte count
+ * subc: source unprocessed bit count
+ * tebc: target ending bit count; valid bits in the last byte
+ * tpbc: target processed byte count
+ * vas: virtual accelerator switch; the user mode interface
+ */
+
+#define _ISOC11_SOURCE // For aligned_alloc()
+#define _DEFAULT_SOURCE // For endian.h
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <stdint.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <sys/time.h>
+#include <sys/fcntl.h>
+#include <sys/mman.h>
+#include <endian.h>
+#include <bits/endian.h>
+#include <sys/ioctl.h>
+#include <assert.h>
+#include <errno.h>
+#include <signal.h>
+#include "nxu.h"
+#include "nx.h"
+
+int nx_dbg;
+FILE *nx_gzip_log;
+
+#define NX_MIN(X, Y) (((X) < (Y)) ? (X) : (Y))
+#define FNAME_MAX 1024
+#define FEXT ".nx.gz"
+
+/*
+ * LZ counts returned in the user supplied nx_gzip_crb_cpb_t structure.
+ */
+static int compress_fht_sample(char *src, uint32_t srclen, char *dst,
+ uint32_t dstlen, int with_count,
+ struct nx_gzip_crb_cpb_t *cmdp, void *handle)
+{
+ uint32_t fc;
+
+ assert(!!cmdp);
+
+ put32(cmdp->crb, gzip_fc, 0); /* clear */
+ fc = (with_count) ? GZIP_FC_COMPRESS_RESUME_FHT_COUNT :
+ GZIP_FC_COMPRESS_RESUME_FHT;
+ putnn(cmdp->crb, gzip_fc, fc);
+ putnn(cmdp->cpb, in_histlen, 0); /* resuming with no history */
+ memset((void *) &cmdp->crb.csb, 0, sizeof(cmdp->crb.csb));
+
+ /* Section 6.6 programming notes; spbc may be in two different
+ * places depending on FC.
+ */
+ if (!with_count)
+ put32(cmdp->cpb, out_spbc_comp, 0);
+ else
+ put32(cmdp->cpb, out_spbc_comp_with_count, 0);
+
+ /* Figure 6-3 6-4; CSB location */
+ put64(cmdp->crb, csb_address, 0);
+ put64(cmdp->crb, csb_address,
+ (uint64_t) &cmdp->crb.csb & csb_address_mask);
+
+ /* Source direct dde (scatter-gather list) */
+ clear_dde(cmdp->crb.source_dde);
+ putnn(cmdp->crb.source_dde, dde_count, 0);
+ put32(cmdp->crb.source_dde, ddebc, srclen);
+ put64(cmdp->crb.source_dde, ddead, (uint64_t) src);
+
+ /* Target direct dde (scatter-gather list) */
+ clear_dde(cmdp->crb.target_dde);
+ putnn(cmdp->crb.target_dde, dde_count, 0);
+ put32(cmdp->crb.target_dde, ddebc, dstlen);
+ put64(cmdp->crb.target_dde, ddead, (uint64_t) dst);
+
+ /* Submit the crb, the job descriptor, to the accelerator */
+ return nxu_submit_job(cmdp, handle);
+}
+
+/*
+ * Prepares a blank no filename no timestamp gzip header and returns
+ * the number of bytes written to buf.
+ * Gzip specification at https://tools.ietf.org/html/rfc1952
+ */
+int gzip_header_blank(char *buf)
+{
+ int i = 0;
+
+ buf[i++] = 0x1f; /* ID1 */
+ buf[i++] = 0x8b; /* ID2 */
+ buf[i++] = 0x08; /* CM */
+ buf[i++] = 0x00; /* FLG */
+ buf[i++] = 0x00; /* MTIME */
+ buf[i++] = 0x00; /* MTIME */
+ buf[i++] = 0x00; /* MTIME */
+ buf[i++] = 0x00; /* MTIME */
+ buf[i++] = 0x04; /* XFL 4=fastest */
+ buf[i++] = 0x03; /* OS UNIX */
+
+ return i;
+}
+
+/* Caller must free the allocated buffer return nonzero on error. */
+int read_alloc_input_file(char *fname, char **buf, size_t *bufsize)
+{
+ struct stat statbuf;
+ FILE *fp;
+ char *p;
+ size_t num_bytes;
+
+ if (stat(fname, &statbuf)) {
+ perror(fname);
+ return(-1);
+ }
+ fp = fopen(fname, "r");
+ if (fp == NULL) {
+ perror(fname);
+ return(-1);
+ }
+ assert(NULL != (p = (char *) malloc(statbuf.st_size)));
+ num_bytes = fread(p, 1, statbuf.st_size, fp);
+ if (ferror(fp) || (num_bytes != statbuf.st_size)) {
+ perror(fname);
+ return(-1);
+ }
+ *buf = p;
+ *bufsize = num_bytes;
+ return 0;
+}
+
+/* Returns nonzero on error */
+int write_output_file(char *fname, char *buf, size_t bufsize)
+{
+ FILE *fp;
+ size_t num_bytes;
+
+ fp = fopen(fname, "w");
+ if (fp == NULL) {
+ perror(fname);
+ return(-1);
+ }
+ num_bytes = fwrite(buf, 1, bufsize, fp);
+ if (ferror(fp) || (num_bytes != bufsize)) {
+ perror(fname);
+ return(-1);
+ }
+ fclose(fp);
+ return 0;
+}
+
+/*
+ * Z_SYNC_FLUSH as described in zlib.h.
+ * Returns number of appended bytes
+ */
+int append_sync_flush(char *buf, int tebc, int final)
+{
+ uint64_t flush;
+ int shift = (tebc & 0x7);
+
+ if (tebc > 0) {
+ /* Last byte is partially full */
+ buf = buf - 1;
+ *buf = *buf & (unsigned char) ((1<<tebc)-1);
+ } else
+ *buf = 0;
+ flush = ((0x1ULL & final) << shift) | *buf;
+ shift = shift + 3; /* BFINAL and BTYPE written */
+ shift = (shift <= 8) ? 8 : 16;
+ flush |= (0xFFFF0000ULL) << shift; /* Zero length block */
+ shift = shift + 32;
+ while (shift > 0) {
+ *buf++ = (unsigned char) (flush & 0xffULL);
+ flush = flush >> 8;
+ shift = shift - 8;
+ }
+ return(((tebc > 5) || (tebc == 0)) ? 5 : 4);
+}
+
+/*
+ * Final deflate block bit. This call assumes the block
+ * beginning is byte aligned.
+ */
+static void set_bfinal(void *buf, int bfinal)
+{
+ char *b = buf;
+
+ if (bfinal)
+ *b = *b | (unsigned char) 0x01;
+ else
+ *b = *b & (unsigned char) 0xfe;
+}
+
+int compress_file(int argc, char **argv, void *handle)
+{
+ char *inbuf, *outbuf, *srcbuf, *dstbuf;
+ char outname[FNAME_MAX];
+ uint32_t srclen, dstlen;
+ uint32_t flushlen, chunk;
+ size_t inlen, outlen, dsttotlen, srctotlen;
+ uint32_t crc, spbc, tpbc, tebc;
+ int lzcounts = 0;
+ int cc;
+ int num_hdr_bytes;
+ struct nx_gzip_crb_cpb_t *cmdp;
+ uint32_t pagelen = 65536;
+ int fault_tries = NX_MAX_FAULTS;
+
+ cmdp = (void *)(uintptr_t)
+ aligned_alloc(sizeof(struct nx_gzip_crb_cpb_t),
+ sizeof(struct nx_gzip_crb_cpb_t));
+
+ if (argc != 2) {
+ fprintf(stderr, "usage: %s <fname>\n", argv[0]);
+ exit(-1);
+ }
+ if (read_alloc_input_file(argv[1], &inbuf, &inlen))
+ exit(-1);
+ fprintf(stderr, "file %s read, %ld bytes\n", argv[1], inlen);
+
+ /* Generous output buffer for header/trailer */
+ outlen = 2 * inlen + 1024;
+
+ assert(NULL != (outbuf = (char *)malloc(outlen)));
+ nxu_touch_pages(outbuf, outlen, pagelen, 1);
+
+ /* Compress piecemeal in smallish chunks */
+ chunk = 1<<22;
+
+ /* Write the gzip header to the stream */
+ num_hdr_bytes = gzip_header_blank(outbuf);
+ dstbuf = outbuf + num_hdr_bytes;
+ outlen = outlen - num_hdr_bytes;
+ dsttotlen = num_hdr_bytes;
+
+ srcbuf = inbuf;
+ srctotlen = 0;
+
+ /* Init the CRB, the coprocessor request block */
+ memset(&cmdp->crb, 0, sizeof(cmdp->crb));
+
+ /* Initial gzip crc32 */
+ put32(cmdp->cpb, in_crc, 0);
+
+ while (inlen > 0) {
+
+ /* Submit chunk size source data per job */
+ srclen = NX_MIN(chunk, inlen);
+ /* Supply large target in case data expands */
+ dstlen = NX_MIN(2*srclen, outlen);
+
+ /* Page faults are handled by the user code */
+
+ /* Fault-in pages; an improved code wouldn't touch so
+ * many pages but would try to estimate the
+ * compression ratio and adjust both the src and dst
+ * touch amounts.
+ */
+ nxu_touch_pages(cmdp, sizeof(struct nx_gzip_crb_cpb_t), pagelen,
+ 1);
+ nxu_touch_pages(srcbuf, srclen, pagelen, 0);
+ nxu_touch_pages(dstbuf, dstlen, pagelen, 1);
+
+ cc = compress_fht_sample(
+ srcbuf, srclen,
+ dstbuf, dstlen,
+ lzcounts, cmdp, handle);
+
+ if (cc != ERR_NX_OK && cc != ERR_NX_TPBC_GT_SPBC &&
+ cc != ERR_NX_TRANSLATION) {
+ fprintf(stderr, "nx error: cc= %d\n", cc);
+ exit(-1);
+ }
+
+ /* Page faults are handled by the user code */
+ if (cc == ERR_NX_TRANSLATION) {
+ NXPRT(fprintf(stderr, "page fault: cc= %d, ", cc));
+ NXPRT(fprintf(stderr, "try= %d, fsa= %08llx\n",
+ fault_tries,
+ (unsigned long long) cmdp->crb.csb.fsaddr));
+ fault_tries--;
+ if (fault_tries > 0) {
+ continue;
+ } else {
+ fprintf(stderr, "error: cannot progress; ");
+ fprintf(stderr, "too many faults\n");
+ exit(-1);
+ };
+ }
+
+ fault_tries = NX_MAX_FAULTS; /* Reset for the next chunk */
+
+ inlen = inlen - srclen;
+ srcbuf = srcbuf + srclen;
+ srctotlen = srctotlen + srclen;
+
+ /* Two possible locations for spbc depending on the function
+ * code.
+ */
+ spbc = (!lzcounts) ? get32(cmdp->cpb, out_spbc_comp) :
+ get32(cmdp->cpb, out_spbc_comp_with_count);
+ assert(spbc == srclen);
+
+ /* Target byte count */
+ tpbc = get32(cmdp->crb.csb, tpbc);
+ /* Target ending bit count */
+ tebc = getnn(cmdp->cpb, out_tebc);
+ NXPRT(fprintf(stderr, "compressed chunk %d ", spbc));
+ NXPRT(fprintf(stderr, "to %d bytes, tebc= %d\n", tpbc, tebc));
+
+ if (inlen > 0) { /* More chunks to go */
+ set_bfinal(dstbuf, 0);
+ dstbuf = dstbuf + tpbc;
+ dsttotlen = dsttotlen + tpbc;
+ outlen = outlen - tpbc;
+ /* Round up to the next byte with a flush
+ * block; do not set the BFINAqL bit.
+ */
+ flushlen = append_sync_flush(dstbuf, tebc, 0);
+ dsttotlen = dsttotlen + flushlen;
+ outlen = outlen - flushlen;
+ dstbuf = dstbuf + flushlen;
+ NXPRT(fprintf(stderr, "added sync_flush %d bytes\n",
+ flushlen));
+ } else { /* Done */
+ /* Set the BFINAL bit of the last block per Deflate
+ * specification.
+ */
+ set_bfinal(dstbuf, 1);
+ dstbuf = dstbuf + tpbc;
+ dsttotlen = dsttotlen + tpbc;
+ outlen = outlen - tpbc;
+ }
+
+ /* Resuming crc32 for the next chunk */
+ crc = get32(cmdp->cpb, out_crc);
+ put32(cmdp->cpb, in_crc, crc);
+ crc = be32toh(crc);
+ }
+
+ /* Append crc32 and ISIZE to the end */
+ memcpy(dstbuf, &crc, 4);
+ memcpy(dstbuf+4, &srctotlen, 4);
+ dsttotlen = dsttotlen + 8;
+ outlen = outlen - 8;
+
+ assert(FNAME_MAX > (strlen(argv[1]) + strlen(FEXT)));
+ strcpy(outname, argv[1]);
+ strcat(outname, FEXT);
+ if (write_output_file(outname, outbuf, dsttotlen)) {
+ fprintf(stderr, "write error: %s\n", outname);
+ exit(-1);
+ }
+
+ fprintf(stderr, "compressed %ld to %ld bytes total, ", srctotlen,
+ dsttotlen);
+ fprintf(stderr, "crc32 checksum = %08x\n", crc);
+
+ if (inbuf != NULL)
+ free(inbuf);
+
+ if (outbuf != NULL)
+ free(outbuf);
+
+ return 0;
+}
+
+int main(int argc, char **argv)
+{
+ int rc;
+ struct sigaction act;
+ void *handle;
+
+ nx_dbg = 0;
+ nx_gzip_log = NULL;
+ act.sa_handler = 0;
+ act.sa_sigaction = nxu_sigsegv_handler;
+ act.sa_flags = SA_SIGINFO;
+ act.sa_restorer = 0;
+ sigemptyset(&act.sa_mask);
+ sigaction(SIGSEGV, &act, NULL);
+
+ handle = nx_function_begin(NX_FUNC_COMP_GZIP, 0);
+ if (!handle) {
+ fprintf(stderr, "Unable to init NX, errno %d\n", errno);
+ exit(-1);
+ }
+
+ rc = compress_file(argc, argv, handle);
+
+ nx_function_end(handle);
+
+ return rc;
+}
diff --git a/tools/testing/selftests/powerpc/nx-gzip/gzip_vas.c b/tools/testing/selftests/powerpc/nx-gzip/gzip_vas.c
new file mode 100644
index 000000000000..c055885da40a
--- /dev/null
+++ b/tools/testing/selftests/powerpc/nx-gzip/gzip_vas.c
@@ -0,0 +1,316 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+/*
+ * Copyright 2020 IBM Corp.
+ *
+ * Author: Bulent Abali <abali@us.ibm.com>
+ *
+ */
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <stdint.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <sys/time.h>
+#include <sys/fcntl.h>
+#include <sys/mman.h>
+#include <endian.h>
+#include <bits/endian.h>
+#include <sys/ioctl.h>
+#include <assert.h>
+#include <errno.h>
+#include <signal.h>
+#include "vas-api.h"
+#include "nx.h"
+#include "copy-paste.h"
+#include "nxu.h"
+#include "nx_dbg.h"
+#include <sys/platform/ppc.h>
+
+#define barrier()
+#define hwsync() ({ asm volatile("sync" ::: "memory"); })
+
+#ifndef NX_NO_CPU_PRI
+#define cpu_pri_default() ({ asm volatile ("or 2, 2, 2"); })
+#define cpu_pri_low() ({ asm volatile ("or 31, 31, 31"); })
+#else
+#define cpu_pri_default()
+#define cpu_pri_low()
+#endif
+
+void *nx_fault_storage_address;
+
+struct nx_handle {
+ int fd;
+ int function;
+ void *paste_addr;
+};
+
+static int open_device_nodes(char *devname, int pri, struct nx_handle *handle)
+{
+ int rc, fd;
+ void *addr;
+ struct vas_tx_win_open_attr txattr;
+
+ fd = open(devname, O_RDWR);
+ if (fd < 0) {
+ fprintf(stderr, " open device name %s\n", devname);
+ return -errno;
+ }
+
+ memset(&txattr, 0, sizeof(txattr));
+ txattr.version = 1;
+ txattr.vas_id = pri;
+ rc = ioctl(fd, VAS_TX_WIN_OPEN, (unsigned long)&txattr);
+ if (rc < 0) {
+ fprintf(stderr, "ioctl() n %d, error %d\n", rc, errno);
+ rc = -errno;
+ goto out;
+ }
+
+ addr = mmap(NULL, 4096, PROT_READ|PROT_WRITE, MAP_SHARED, fd, 0ULL);
+ if (addr == MAP_FAILED) {
+ fprintf(stderr, "mmap() failed, errno %d\n", errno);
+ rc = -errno;
+ goto out;
+ }
+ handle->fd = fd;
+ handle->paste_addr = (void *)((char *)addr + 0x400);
+
+ rc = 0;
+out:
+ close(fd);
+ return rc;
+}
+
+void *nx_function_begin(int function, int pri)
+{
+ int rc;
+ char *devname = "/dev/crypto/nx-gzip";
+ struct nx_handle *nxhandle;
+
+ if (function != NX_FUNC_COMP_GZIP) {
+ errno = EINVAL;
+ fprintf(stderr, " NX_FUNC_COMP_GZIP not found\n");
+ return NULL;
+ }
+
+
+ nxhandle = malloc(sizeof(*nxhandle));
+ if (!nxhandle) {
+ errno = ENOMEM;
+ fprintf(stderr, " No memory\n");
+ return NULL;
+ }
+
+ nxhandle->function = function;
+ rc = open_device_nodes(devname, pri, nxhandle);
+ if (rc < 0) {
+ errno = -rc;
+ fprintf(stderr, " open_device_nodes failed\n");
+ return NULL;
+ }
+
+ return nxhandle;
+}
+
+int nx_function_end(void *handle)
+{
+ int rc = 0;
+ struct nx_handle *nxhandle = handle;
+
+ rc = munmap(nxhandle->paste_addr - 0x400, 4096);
+ if (rc < 0) {
+ fprintf(stderr, "munmap() failed, errno %d\n", errno);
+ return rc;
+ }
+ close(nxhandle->fd);
+ free(nxhandle);
+
+ return rc;
+}
+
+static int nx_wait_for_csb(struct nx_gzip_crb_cpb_t *cmdp)
+{
+ long poll = 0;
+ uint64_t t;
+
+ /* Save power and let other threads use the h/w. top may show
+ * 100% but only because OS doesn't know we slowed the this
+ * h/w thread while polling. We're letting other threads have
+ * higher throughput on the core.
+ */
+ cpu_pri_low();
+
+#define CSB_MAX_POLL 200000000UL
+#define USLEEP_TH 300000UL
+
+ t = __ppc_get_timebase();
+
+ while (getnn(cmdp->crb.csb, csb_v) == 0) {
+ ++poll;
+ hwsync();
+
+ cpu_pri_low();
+
+ /* usleep(0) takes around 29000 ticks ~60 us.
+ * 300000 is spinning for about 600 us then
+ * start sleeping.
+ */
+ if ((__ppc_get_timebase() - t) > USLEEP_TH) {
+ cpu_pri_default();
+ usleep(1);
+ }
+
+ if (poll > CSB_MAX_POLL)
+ break;
+
+ /* Fault address from signal handler */
+ if (nx_fault_storage_address) {
+ cpu_pri_default();
+ return -EAGAIN;
+ }
+
+ }
+
+ cpu_pri_default();
+
+ /* hw has updated csb and output buffer */
+ hwsync();
+
+ /* Check CSB flags. */
+ if (getnn(cmdp->crb.csb, csb_v) == 0) {
+ fprintf(stderr, "CSB still not valid after %d polls.\n",
+ (int) poll);
+ prt_err("CSB still not valid after %d polls, giving up.\n",
+ (int) poll);
+ return -ETIMEDOUT;
+ }
+
+ return 0;
+}
+
+static int nxu_run_job(struct nx_gzip_crb_cpb_t *cmdp, void *handle)
+{
+ int i, ret, retries;
+ struct nx_handle *nxhandle = handle;
+
+ assert(handle != NULL);
+ i = 0;
+ retries = 5000;
+ while (i++ < retries) {
+ hwsync();
+ vas_copy(&cmdp->crb, 0);
+ ret = vas_paste(nxhandle->paste_addr, 0);
+ hwsync();
+
+ NXPRT(fprintf(stderr, "Paste attempt %d/%d returns 0x%x\n",
+ i, retries, ret));
+
+ if ((ret == 2) || (ret == 3)) {
+
+ ret = nx_wait_for_csb(cmdp);
+ if (!ret) {
+ goto out;
+ } else if (ret == -EAGAIN) {
+ long x;
+
+ prt_err("Touching address %p, 0x%lx\n",
+ nx_fault_storage_address,
+ *(long *) nx_fault_storage_address);
+ x = *(long *) nx_fault_storage_address;
+ *(long *) nx_fault_storage_address = x;
+ nx_fault_storage_address = 0;
+ continue;
+ } else {
+ prt_err("wait_for_csb() returns %d\n", ret);
+ break;
+ }
+ } else {
+ if (i < 10) {
+ /* spin for few ticks */
+#define SPIN_TH 500UL
+ uint64_t fail_spin;
+
+ fail_spin = __ppc_get_timebase();
+ while ((__ppc_get_timebase() - fail_spin) <
+ SPIN_TH)
+ ;
+ } else {
+ /* sleep */
+ unsigned int pr = 0;
+
+ if (pr++ % 100 == 0) {
+ prt_err("Paste attempt %d/", i);
+ prt_err("%d, failed pid= %d\n", retries,
+ getpid());
+ }
+ usleep(1);
+ }
+ continue;
+ }
+ }
+
+out:
+ cpu_pri_default();
+
+ return ret;
+}
+
+int nxu_submit_job(struct nx_gzip_crb_cpb_t *cmdp, void *handle)
+{
+ int cc;
+
+ cc = nxu_run_job(cmdp, handle);
+
+ if (!cc)
+ cc = getnn(cmdp->crb.csb, csb_cc); /* CC Table 6-8 */
+
+ return cc;
+}
+
+
+void nxu_sigsegv_handler(int sig, siginfo_t *info, void *ctx)
+{
+ fprintf(stderr, "%d: Got signal %d si_code %d, si_addr %p\n", getpid(),
+ sig, info->si_code, info->si_addr);
+
+ nx_fault_storage_address = info->si_addr;
+}
+
+/*
+ * Fault in pages prior to NX job submission. wr=1 may be required to
+ * touch writeable pages. System zero pages do not fault-in the page as
+ * intended. Typically set wr=1 for NX target pages and set wr=0 for NX
+ * source pages.
+ */
+int nxu_touch_pages(void *buf, long buf_len, long page_len, int wr)
+{
+ char *begin = buf;
+ char *end = (char *) buf + buf_len - 1;
+ volatile char t;
+
+ assert(buf_len >= 0 && !!buf);
+
+ NXPRT(fprintf(stderr, "touch %p %p len 0x%lx wr=%d\n", buf,
+ (buf + buf_len), buf_len, wr));
+
+ if (buf_len <= 0 || buf == NULL)
+ return -1;
+
+ do {
+ t = *begin;
+ if (wr)
+ *begin = t;
+ begin = begin + page_len;
+ } while (begin < end);
+
+ /* When buf_sz is small or buf tail is in another page */
+ t = *end;
+ if (wr)
+ *end = t;
+
+ return 0;
+}
diff --git a/tools/testing/selftests/powerpc/nx-gzip/include/copy-paste.h b/tools/testing/selftests/powerpc/nx-gzip/include/copy-paste.h
new file mode 100644
index 000000000000..0db2d6485037
--- /dev/null
+++ b/tools/testing/selftests/powerpc/nx-gzip/include/copy-paste.h
@@ -0,0 +1,56 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+
+/* From asm-compat.h */
+#define __stringify_in_c(...) #__VA_ARGS__
+#define stringify_in_c(...) __stringify_in_c(__VA_ARGS__) " "
+
+/*
+ * Macros taken from arch/powerpc/include/asm/ppc-opcode.h and other
+ * header files.
+ */
+#define ___PPC_RA(a) (((a) & 0x1f) << 16)
+#define ___PPC_RB(b) (((b) & 0x1f) << 11)
+
+#define PPC_INST_COPY 0x7c20060c
+#define PPC_INST_PASTE 0x7c20070d
+
+#define PPC_COPY(a, b) stringify_in_c(.long PPC_INST_COPY | \
+ ___PPC_RA(a) | ___PPC_RB(b))
+#define PPC_PASTE(a, b) stringify_in_c(.long PPC_INST_PASTE | \
+ ___PPC_RA(a) | ___PPC_RB(b))
+#define CR0_SHIFT 28
+#define CR0_MASK 0xF
+/*
+ * Copy/paste instructions:
+ *
+ * copy RA,RB
+ * Copy contents of address (RA) + effective_address(RB)
+ * to internal copy-buffer.
+ *
+ * paste RA,RB
+ * Paste contents of internal copy-buffer to the address
+ * (RA) + effective_address(RB)
+ */
+static inline int vas_copy(void *crb, int offset)
+{
+ asm volatile(PPC_COPY(%0, %1)";"
+ :
+ : "b" (offset), "b" (crb)
+ : "memory");
+
+ return 0;
+}
+
+static inline int vas_paste(void *paste_address, int offset)
+{
+ __u32 cr;
+
+ cr = 0;
+ asm volatile(PPC_PASTE(%1, %2)";"
+ "mfocrf %0, 0x80;"
+ : "=r" (cr)
+ : "b" (offset), "b" (paste_address)
+ : "memory", "cr0");
+
+ return (cr >> CR0_SHIFT) & CR0_MASK;
+}
diff --git a/tools/testing/selftests/powerpc/nx-gzip/include/crb.h b/tools/testing/selftests/powerpc/nx-gzip/include/crb.h
new file mode 100644
index 000000000000..ab101085fa7e
--- /dev/null
+++ b/tools/testing/selftests/powerpc/nx-gzip/include/crb.h
@@ -0,0 +1,155 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef __CRB_H
+#define __CRB_H
+#include <linux/types.h>
+#include "nx.h"
+
+/* CCW 842 CI/FC masks
+ * NX P8 workbook, section 4.3.1, figure 4-6
+ * "CI/FC Boundary by NX CT type"
+ */
+#define CCW_CI_842 (0x00003ff8)
+#define CCW_FC_842 (0x00000007)
+
+/* Chapter 6.5.8 Coprocessor-Completion Block (CCB) */
+
+#define CCB_VALUE (0x3fffffffffffffff)
+#define CCB_ADDRESS (0xfffffffffffffff8)
+#define CCB_CM (0x0000000000000007)
+#define CCB_CM0 (0x0000000000000004)
+#define CCB_CM12 (0x0000000000000003)
+
+#define CCB_CM0_ALL_COMPLETIONS (0x0)
+#define CCB_CM0_LAST_IN_CHAIN (0x4)
+#define CCB_CM12_STORE (0x0)
+#define CCB_CM12_INTERRUPT (0x1)
+
+#define CCB_SIZE (0x10)
+#define CCB_ALIGN CCB_SIZE
+
+struct coprocessor_completion_block {
+ __be64 value;
+ __be64 address;
+} __aligned(CCB_ALIGN);
+
+
+/* Chapter 6.5.7 Coprocessor-Status Block (CSB) */
+
+#define CSB_V (0x80)
+#define CSB_F (0x04)
+#define CSB_CH (0x03)
+#define CSB_CE_INCOMPLETE (0x80)
+#define CSB_CE_TERMINATION (0x40)
+#define CSB_CE_TPBC (0x20)
+
+#define CSB_CC_SUCCESS (0)
+#define CSB_CC_INVALID_ALIGN (1)
+#define CSB_CC_OPERAND_OVERLAP (2)
+#define CSB_CC_DATA_LENGTH (3)
+#define CSB_CC_TRANSLATION (5)
+#define CSB_CC_PROTECTION (6)
+#define CSB_CC_RD_EXTERNAL (7)
+#define CSB_CC_INVALID_OPERAND (8)
+#define CSB_CC_PRIVILEGE (9)
+#define CSB_CC_INTERNAL (10)
+#define CSB_CC_WR_EXTERNAL (12)
+#define CSB_CC_NOSPC (13)
+#define CSB_CC_EXCESSIVE_DDE (14)
+#define CSB_CC_WR_TRANSLATION (15)
+#define CSB_CC_WR_PROTECTION (16)
+#define CSB_CC_UNKNOWN_CODE (17)
+#define CSB_CC_ABORT (18)
+#define CSB_CC_TRANSPORT (20)
+#define CSB_CC_SEGMENTED_DDL (31)
+#define CSB_CC_PROGRESS_POINT (32)
+#define CSB_CC_DDE_OVERFLOW (33)
+#define CSB_CC_SESSION (34)
+#define CSB_CC_PROVISION (36)
+#define CSB_CC_CHAIN (37)
+#define CSB_CC_SEQUENCE (38)
+#define CSB_CC_HW (39)
+
+#define CSB_SIZE (0x10)
+#define CSB_ALIGN CSB_SIZE
+
+struct coprocessor_status_block {
+ __u8 flags;
+ __u8 cs;
+ __u8 cc;
+ __u8 ce;
+ __be32 count;
+ __be64 address;
+} __aligned(CSB_ALIGN);
+
+
+/* Chapter 6.5.10 Data-Descriptor List (DDL)
+ * each list contains one or more Data-Descriptor Entries (DDE)
+ */
+
+#define DDE_P (0x8000)
+
+#define DDE_SIZE (0x10)
+#define DDE_ALIGN DDE_SIZE
+
+struct data_descriptor_entry {
+ __be16 flags;
+ __u8 count;
+ __u8 index;
+ __be32 length;
+ __be64 address;
+} __aligned(DDE_ALIGN);
+
+
+/* Chapter 6.5.2 Coprocessor-Request Block (CRB) */
+
+#define CRB_SIZE (0x80)
+#define CRB_ALIGN (0x100) /* Errata: requires 256 alignment */
+
+
+/* Coprocessor Status Block field
+ * ADDRESS address of CSB
+ * C CCB is valid
+ * AT 0 = addrs are virtual, 1 = addrs are phys
+ * M enable perf monitor
+ */
+#define CRB_CSB_ADDRESS (0xfffffffffffffff0)
+#define CRB_CSB_C (0x0000000000000008)
+#define CRB_CSB_AT (0x0000000000000002)
+#define CRB_CSB_M (0x0000000000000001)
+
+struct coprocessor_request_block {
+ __be32 ccw;
+ __be32 flags;
+ __be64 csb_addr;
+
+ struct data_descriptor_entry source;
+ struct data_descriptor_entry target;
+
+ struct coprocessor_completion_block ccb;
+
+ __u8 reserved[48];
+
+ struct coprocessor_status_block csb;
+} __aligned(CRB_ALIGN);
+
+#define crb_csb_addr(c) __be64_to_cpu(c->csb_addr)
+#define crb_nx_fault_addr(c) __be64_to_cpu(c->stamp.nx.fault_storage_addr)
+#define crb_nx_flags(c) c->stamp.nx.flags
+#define crb_nx_fault_status(c) c->stamp.nx.fault_status
+#define crb_nx_pswid(c) c->stamp.nx.pswid
+
+
+/* RFC02167 Initiate Coprocessor Instructions document
+ * Chapter 8.2.1.1.1 RS
+ * Chapter 8.2.3 Coprocessor Directive
+ * Chapter 8.2.4 Execution
+ *
+ * The CCW must be converted to BE before passing to icswx()
+ */
+
+#define CCW_PS (0xff000000)
+#define CCW_CT (0x00ff0000)
+#define CCW_CD (0x0000ffff)
+#define CCW_CL (0x0000c000)
+
+#endif
diff --git a/tools/testing/selftests/powerpc/nx-gzip/include/nx.h b/tools/testing/selftests/powerpc/nx-gzip/include/nx.h
new file mode 100644
index 000000000000..1abe23fc29e8
--- /dev/null
+++ b/tools/testing/selftests/powerpc/nx-gzip/include/nx.h
@@ -0,0 +1,38 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright 2020 IBM Corp.
+ *
+ */
+#ifndef _NX_H
+#define _NX_H
+
+#include <stdbool.h>
+
+#define NX_FUNC_COMP_842 1
+#define NX_FUNC_COMP_GZIP 2
+
+#ifndef __aligned
+#define __aligned(x) __attribute__((aligned(x)))
+#endif
+
+struct nx842_func_args {
+ bool use_crc;
+ bool decompress; /* true decompress; false compress */
+ bool move_data;
+ int timeout; /* seconds */
+};
+
+struct nxbuf_t {
+ int len;
+ char *buf;
+};
+
+/* @function should be EFT (aka 842), GZIP etc */
+void *nx_function_begin(int function, int pri);
+
+int nx_function(void *handle, struct nxbuf_t *in, struct nxbuf_t *out,
+ void *arg);
+
+int nx_function_end(void *handle);
+
+#endif /* _NX_H */
diff --git a/tools/testing/selftests/powerpc/nx-gzip/include/nx_dbg.h b/tools/testing/selftests/powerpc/nx-gzip/include/nx_dbg.h
new file mode 100644
index 000000000000..16464e19c47f
--- /dev/null
+++ b/tools/testing/selftests/powerpc/nx-gzip/include/nx_dbg.h
@@ -0,0 +1,95 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright 2020 IBM Corporation
+ *
+ */
+
+#ifndef _NXU_DBG_H_
+#define _NXU_DBG_H_
+
+#include <sys/file.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <time.h>
+#include <pthread.h>
+
+extern FILE * nx_gzip_log;
+extern int nx_gzip_trace;
+extern unsigned int nx_gzip_inflate_impl;
+extern unsigned int nx_gzip_deflate_impl;
+extern unsigned int nx_gzip_inflate_flags;
+extern unsigned int nx_gzip_deflate_flags;
+
+extern int nx_dbg;
+pthread_mutex_t mutex_log;
+
+#define nx_gzip_trace_enabled() (nx_gzip_trace & 0x1)
+#define nx_gzip_hw_trace_enabled() (nx_gzip_trace & 0x2)
+#define nx_gzip_sw_trace_enabled() (nx_gzip_trace & 0x4)
+#define nx_gzip_gather_statistics() (nx_gzip_trace & 0x8)
+#define nx_gzip_per_stream_stat() (nx_gzip_trace & 0x10)
+
+#define prt(fmt, ...) do { \
+ pthread_mutex_lock(&mutex_log); \
+ flock(nx_gzip_log->_fileno, LOCK_EX); \
+ time_t t; struct tm *m; time(&t); m = localtime(&t); \
+ fprintf(nx_gzip_log, "[%04d/%02d/%02d %02d:%02d:%02d] " \
+ "pid %d: " fmt, \
+ (int)m->tm_year + 1900, (int)m->tm_mon+1, (int)m->tm_mday, \
+ (int)m->tm_hour, (int)m->tm_min, (int)m->tm_sec, \
+ (int)getpid(), ## __VA_ARGS__); \
+ fflush(nx_gzip_log); \
+ flock(nx_gzip_log->_fileno, LOCK_UN); \
+ pthread_mutex_unlock(&mutex_log); \
+} while (0)
+
+/* Use in case of an error */
+#define prt_err(fmt, ...) do { if (nx_dbg >= 0) { \
+ prt("%s:%u: Error: "fmt, \
+ __FILE__, __LINE__, ## __VA_ARGS__); \
+}} while (0)
+
+/* Use in case of an warning */
+#define prt_warn(fmt, ...) do { if (nx_dbg >= 1) { \
+ prt("%s:%u: Warning: "fmt, \
+ __FILE__, __LINE__, ## __VA_ARGS__); \
+}} while (0)
+
+/* Informational printouts */
+#define prt_info(fmt, ...) do { if (nx_dbg >= 2) { \
+ prt("Info: "fmt, ## __VA_ARGS__); \
+}} while (0)
+
+/* Trace zlib wrapper code */
+#define prt_trace(fmt, ...) do { if (nx_gzip_trace_enabled()) { \
+ prt("### "fmt, ## __VA_ARGS__); \
+}} while (0)
+
+/* Trace statistics */
+#define prt_stat(fmt, ...) do { if (nx_gzip_gather_statistics()) { \
+ prt("### "fmt, ## __VA_ARGS__); \
+}} while (0)
+
+/* Trace zlib hardware implementation */
+#define hw_trace(fmt, ...) do { \
+ if (nx_gzip_hw_trace_enabled()) \
+ fprintf(nx_gzip_log, "hhh " fmt, ## __VA_ARGS__); \
+ } while (0)
+
+/* Trace zlib software implementation */
+#define sw_trace(fmt, ...) do { \
+ if (nx_gzip_sw_trace_enabled()) \
+ fprintf(nx_gzip_log, "sss " fmt, ## __VA_ARGS__); \
+ } while (0)
+
+
+/**
+ * str_to_num - Convert string into number and copy with endings like
+ * KiB for kilobyte
+ * MiB for megabyte
+ * GiB for gigabyte
+ */
+uint64_t str_to_num(char *str);
+void nx_lib_debug(int onoff);
+
+#endif /* _NXU_DBG_H_ */
diff --git a/tools/testing/selftests/powerpc/nx-gzip/include/nxu.h b/tools/testing/selftests/powerpc/nx-gzip/include/nxu.h
new file mode 100644
index 000000000000..20a4e883e0d3
--- /dev/null
+++ b/tools/testing/selftests/powerpc/nx-gzip/include/nxu.h
@@ -0,0 +1,650 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Hardware interface of the NX-GZIP compression accelerator
+ *
+ * Copyright (C) IBM Corporation, 2020
+ *
+ * Author: Bulent Abali <abali@us.ibm.com>
+ *
+ */
+
+#ifndef _NXU_H
+#define _NXU_H
+
+#include <stdint.h>
+#include <endian.h>
+#include "nx.h"
+
+/* deflate */
+#define LLSZ 286
+#define DSZ 30
+
+/* nx */
+#define DHTSZ 18
+#define DHT_MAXSZ 288
+#define MAX_DDE_COUNT 256
+
+/* util */
+#ifdef NXDBG
+#define NXPRT(X) X
+#else
+#define NXPRT(X)
+#endif
+
+#ifdef NXTIMER
+#include <sys/platform/ppc.h>
+#define NX_CLK(X) X
+#define nx_get_time() __ppc_get_timebase()
+#define nx_get_freq() __ppc_get_timebase_freq()
+#else
+#define NX_CLK(X)
+#define nx_get_time() (-1)
+#define nx_get_freq() (-1)
+#endif
+
+#define NX_MAX_FAULTS 500
+
+/*
+ * Definitions of acronyms used here. See
+ * P9 NX Gzip Accelerator User's Manual for details:
+ * https://github.com/libnxz/power-gzip/blob/develop/doc/power_nx_gzip_um.pdf
+ *
+ * adler/crc: 32 bit checksums appended to stream tail
+ * ce: completion extension
+ * cpb: coprocessor parameter block (metadata)
+ * crb: coprocessor request block (command)
+ * csb: coprocessor status block (status)
+ * dht: dynamic huffman table
+ * dde: data descriptor element (address, length)
+ * ddl: list of ddes
+ * dh/fh: dynamic and fixed huffman types
+ * fc: coprocessor function code
+ * histlen: history/dictionary length
+ * history: sliding window of up to 32KB of data
+ * lzcount: Deflate LZ symbol counts
+ * rembytecnt: remaining byte count
+ * sfbt: source final block type; last block's type during decomp
+ * spbc: source processed byte count
+ * subc: source unprocessed bit count
+ * tebc: target ending bit count; valid bits in the last byte
+ * tpbc: target processed byte count
+ * vas: virtual accelerator switch; the user mode interface
+ */
+
+union nx_qw_t {
+ uint32_t word[4];
+ uint64_t dword[2];
+} __aligned(16);
+
+/*
+ * Note: NX registers with fewer than 32 bits are declared by
+ * convention as uint32_t variables in unions. If *_offset and *_mask
+ * are defined for a variable, then use get_ put_ macros to
+ * conveniently access the register fields for endian conversions.
+ */
+
+struct nx_dde_t {
+ /* Data Descriptor Element, Section 6.4 */
+ union {
+ uint32_t dde_count;
+ /* When dde_count == 0 ddead is a pointer to a data buffer;
+ * ddebc is the buffer length bytes.
+ * When dde_count > 0 dde is an indirect dde; ddead is a
+ * pointer to a contiguous list of direct ddes; ddebc is the
+ * total length of all data pointed to by the list of direct
+ * ddes. Note that only one level of indirection is permitted.
+ * See Section 6.4 of the user manual for additional details.
+ */
+ };
+ uint32_t ddebc; /* dde byte count */
+ uint64_t ddead; /* dde address */
+} __aligned(16);
+
+struct nx_csb_t {
+ /* Coprocessor Status Block, Section 6.6 */
+ union {
+ uint32_t csb_v;
+ /* Valid bit. v must be set to 0 by the program
+ * before submitting the coprocessor command.
+ * Software can poll for the v bit
+ */
+
+ uint32_t csb_f;
+ /* 16B CSB size. Written to 0 by DMA when it writes the CPB */
+
+ uint32_t csb_cs;
+ /* cs completion sequence; unused */
+
+ uint32_t csb_cc;
+ /* cc completion code; cc != 0 exception occurred */
+
+ uint32_t csb_ce;
+ /* ce completion extension */
+
+ };
+ uint32_t tpbc;
+ /* target processed byte count TPBC */
+
+ uint64_t fsaddr;
+ /* Section 6.12.1 CSB NonZero error summary. FSA Failing storage
+ * address. Address where error occurred. When available, written
+ * to A field of CSB
+ */
+} __aligned(16);
+
+struct nx_ccb_t {
+ /* Coprocessor Completion Block, Section 6.7 */
+
+ uint32_t reserved[3];
+ union {
+ /* When crb.c==0 (no ccb defined) it is reserved;
+ * When crb.c==1 (ccb defined) it is cm
+ */
+
+ uint32_t ccb_cm;
+ /* Signal interrupt of crb.c==1 and cm==1 */
+
+ uint32_t word;
+ /* generic access to the 32bit word */
+ };
+} __aligned(16);
+
+struct vas_stamped_crb_t {
+ /*
+ * CRB operand of the paste coprocessor instruction is stamped
+ * in quadword 4 with the information shown here as its written
+ * in to the receive FIFO of the coprocessor
+ */
+
+ union {
+ uint32_t vas_buf_num;
+ /* Verification only vas buffer number which correlates to
+ * the low order bits of the atag in the paste command
+ */
+
+ uint32_t send_wc_id;
+ /* Pointer to Send Window Context that provides for NX address
+ * translation information, such as MSR and LPCR bits, job
+ * completion interrupt RA, PSWID, and job utilization counter.
+ */
+
+ };
+ union {
+ uint32_t recv_wc_id;
+ /* Pointer to Receive Window Context. NX uses this to return
+ * credits to a Receive FIFO as entries are dequeued.
+ */
+
+ };
+ uint32_t reserved2;
+ union {
+ uint32_t vas_invalid;
+ /* Invalid bit. If this bit is 1 the CRB is discarded by
+ * NX upon fetching from the receive FIFO. If this bit is 0
+ * the CRB is processed normally. The bit is stamped to 0
+ * by VAS and may be written to 1 by hypervisor while
+ * the CRB is in the receive FIFO (in memory).
+ */
+
+ };
+};
+
+struct nx_stamped_fault_crb_t {
+ /*
+ * A CRB that has a translation fault is stamped by NX in quadword 4
+ * and pasted to the Fault Send Window in VAS.
+ */
+ uint64_t fsa;
+ union {
+ uint32_t nxsf_t;
+ uint32_t nxsf_fs;
+ };
+ uint32_t pswid;
+};
+
+union stamped_crb_t {
+ struct vas_stamped_crb_t vas;
+ struct nx_stamped_fault_crb_t nx;
+};
+
+struct nx_gzip_cpb_t {
+ /*
+ * Coprocessor Parameter Block In/Out are used to pass metadata
+ * to/from accelerator. Tables 6.5 and 6.6 of the user manual.
+ */
+
+ /* CPBInput */
+
+ struct {
+ union {
+ union nx_qw_t qw0;
+ struct {
+ uint32_t in_adler; /* bits 0:31 */
+ uint32_t in_crc; /* bits 32:63 */
+ union {
+ uint32_t in_histlen; /* bits 64:75 */
+ uint32_t in_subc; /* bits 93:95 */
+ };
+ union {
+ /* bits 108:111 */
+ uint32_t in_sfbt;
+ /* bits 112:127 */
+ uint32_t in_rembytecnt;
+ /* bits 116:127 */
+ uint32_t in_dhtlen;
+ };
+ };
+ };
+ union {
+ union nx_qw_t in_dht[DHTSZ]; /* qw[1:18] */
+ char in_dht_char[DHT_MAXSZ]; /* byte access */
+ };
+ union nx_qw_t reserved[5]; /* qw[19:23] */
+ };
+
+ /* CPBOutput */
+
+ volatile struct {
+ union {
+ union nx_qw_t qw24;
+ struct {
+ uint32_t out_adler; /* bits 0:31 qw[24] */
+ uint32_t out_crc; /* bits 32:63 qw[24] */
+ union {
+ /* bits 77:79 qw[24] */
+ uint32_t out_tebc;
+ /* bits 80:95 qw[24] */
+ uint32_t out_subc;
+ };
+ union {
+ /* bits 108:111 qw[24] */
+ uint32_t out_sfbt;
+ /* bits 112:127 qw[24] */
+ uint32_t out_rembytecnt;
+ /* bits 116:127 qw[24] */
+ uint32_t out_dhtlen;
+ };
+ };
+ };
+ union {
+ union nx_qw_t qw25[79]; /* qw[25:103] */
+ /* qw[25] compress no lzcounts or wrap */
+ uint32_t out_spbc_comp_wrap;
+ uint32_t out_spbc_wrap; /* qw[25] wrap */
+ /* qw[25] compress no lzcounts */
+ uint32_t out_spbc_comp;
+ /* 286 LL and 30 D symbol counts */
+ uint32_t out_lzcount[LLSZ+DSZ];
+ struct {
+ union nx_qw_t out_dht[DHTSZ]; /* qw[25:42] */
+ /* qw[43] decompress */
+ uint32_t out_spbc_decomp;
+ };
+ };
+ /* qw[104] compress with lzcounts */
+ uint32_t out_spbc_comp_with_count;
+ };
+} __aligned(128);
+
+struct nx_gzip_crb_t {
+ union { /* byte[0:3] */
+ uint32_t gzip_fc; /* bits[24-31] */
+ };
+ uint32_t reserved1; /* byte[4:7] */
+ union {
+ uint64_t csb_address; /* byte[8:15] */
+ struct {
+ uint32_t reserved2;
+ union {
+ uint32_t crb_c;
+ /* c==0 no ccb defined */
+
+ uint32_t crb_at;
+ /* at==0 address type is ignored;
+ * all addrs effective assumed.
+ */
+
+ };
+ };
+ };
+ struct nx_dde_t source_dde; /* byte[16:31] */
+ struct nx_dde_t target_dde; /* byte[32:47] */
+ volatile struct nx_ccb_t ccb; /* byte[48:63] */
+ volatile union {
+ /* byte[64:239] shift csb by 128 bytes out of the crb; csb was
+ * in crb earlier; JReilly says csb written with partial inject
+ */
+ union nx_qw_t reserved64[11];
+ union stamped_crb_t stamp; /* byte[64:79] */
+ };
+ volatile struct nx_csb_t csb;
+} __aligned(128);
+
+struct nx_gzip_crb_cpb_t {
+ struct nx_gzip_crb_t crb;
+ struct nx_gzip_cpb_t cpb;
+} __aligned(2048);
+
+
+/*
+ * NX hardware convention has the msb bit on the left numbered 0.
+ * The defines below has *_offset defined as the right most bit
+ * position of a field. x of size_mask(x) is the field width in bits.
+ */
+
+#define size_mask(x) ((1U<<(x))-1)
+
+/*
+ * Offsets and Widths within the containing 32 bits of the various NX
+ * gzip hardware registers. Use the getnn/putnn macros to access
+ * these regs
+ */
+
+#define dde_count_mask size_mask(8)
+#define dde_count_offset 23
+
+/* CSB */
+
+#define csb_v_mask size_mask(1)
+#define csb_v_offset 0
+#define csb_f_mask size_mask(1)
+#define csb_f_offset 6
+#define csb_cs_mask size_mask(8)
+#define csb_cs_offset 15
+#define csb_cc_mask size_mask(8)
+#define csb_cc_offset 23
+#define csb_ce_mask size_mask(8)
+#define csb_ce_offset 31
+
+/* CCB */
+
+#define ccb_cm_mask size_mask(3)
+#define ccb_cm_offset 31
+
+/* VAS stamped CRB fields */
+
+#define vas_buf_num_mask size_mask(6)
+#define vas_buf_num_offset 5
+#define send_wc_id_mask size_mask(16)
+#define send_wc_id_offset 31
+#define recv_wc_id_mask size_mask(16)
+#define recv_wc_id_offset 31
+#define vas_invalid_mask size_mask(1)
+#define vas_invalid_offset 31
+
+/* NX stamped fault CRB fields */
+
+#define nxsf_t_mask size_mask(1)
+#define nxsf_t_offset 23
+#define nxsf_fs_mask size_mask(8)
+#define nxsf_fs_offset 31
+
+/* CPB input */
+
+#define in_histlen_mask size_mask(12)
+#define in_histlen_offset 11
+#define in_dhtlen_mask size_mask(12)
+#define in_dhtlen_offset 31
+#define in_subc_mask size_mask(3)
+#define in_subc_offset 31
+#define in_sfbt_mask size_mask(4)
+#define in_sfbt_offset 15
+#define in_rembytecnt_mask size_mask(16)
+#define in_rembytecnt_offset 31
+
+/* CPB output */
+
+#define out_tebc_mask size_mask(3)
+#define out_tebc_offset 15
+#define out_subc_mask size_mask(16)
+#define out_subc_offset 31
+#define out_sfbt_mask size_mask(4)
+#define out_sfbt_offset 15
+#define out_rembytecnt_mask size_mask(16)
+#define out_rembytecnt_offset 31
+#define out_dhtlen_mask size_mask(12)
+#define out_dhtlen_offset 31
+
+/* CRB */
+
+#define gzip_fc_mask size_mask(8)
+#define gzip_fc_offset 31
+#define crb_c_mask size_mask(1)
+#define crb_c_offset 28
+#define crb_at_mask size_mask(1)
+#define crb_at_offset 30
+#define csb_address_mask ~(15UL) /* mask off bottom 4b */
+
+/*
+ * Access macros for the registers. Do not access registers directly
+ * because of the endian conversion. P9 processor may run either as
+ * Little or Big endian. However the NX coprocessor regs are always
+ * big endian.
+ * Use the 32 and 64b macros to access respective
+ * register sizes.
+ * Use nn forms for the register fields shorter than 32 bits.
+ */
+
+#define getnn(ST, REG) ((be32toh(ST.REG) >> (31-REG##_offset)) \
+ & REG##_mask)
+#define getpnn(ST, REG) ((be32toh((ST)->REG) >> (31-REG##_offset)) \
+ & REG##_mask)
+#define get32(ST, REG) (be32toh(ST.REG))
+#define getp32(ST, REG) (be32toh((ST)->REG))
+#define get64(ST, REG) (be64toh(ST.REG))
+#define getp64(ST, REG) (be64toh((ST)->REG))
+
+#define unget32(ST, REG) (get32(ST, REG) & ~((REG##_mask) \
+ << (31-REG##_offset)))
+/* get 32bits less the REG field */
+
+#define ungetp32(ST, REG) (getp32(ST, REG) & ~((REG##_mask) \
+ << (31-REG##_offset)))
+/* get 32bits less the REG field */
+
+#define clear_regs(ST) memset((void *)(&(ST)), 0, sizeof(ST))
+#define clear_dde(ST) do { ST.dde_count = ST.ddebc = 0; ST.ddead = 0; \
+ } while (0)
+#define clearp_dde(ST) do { (ST)->dde_count = (ST)->ddebc = 0; \
+ (ST)->ddead = 0; \
+ } while (0)
+#define clear_struct(ST) memset((void *)(&(ST)), 0, sizeof(ST))
+#define putnn(ST, REG, X) (ST.REG = htobe32(unget32(ST, REG) | (((X) \
+ & REG##_mask) << (31-REG##_offset))))
+#define putpnn(ST, REG, X) ((ST)->REG = htobe32(ungetp32(ST, REG) \
+ | (((X) & REG##_mask) << (31-REG##_offset))))
+
+#define put32(ST, REG, X) (ST.REG = htobe32(X))
+#define putp32(ST, REG, X) ((ST)->REG = htobe32(X))
+#define put64(ST, REG, X) (ST.REG = htobe64(X))
+#define putp64(ST, REG, X) ((ST)->REG = htobe64(X))
+
+/*
+ * Completion extension ce(0) ce(1) ce(2). Bits ce(3-7)
+ * unused. Section 6.6 Figure 6.7.
+ */
+
+#define get_csb_ce(ST) ((uint32_t)getnn(ST, csb_ce))
+#define get_csb_ce_ms3b(ST) (get_csb_ce(ST) >> 5)
+#define put_csb_ce_ms3b(ST, X) putnn(ST, csb_ce, ((uint32_t)(X) << 5))
+
+#define CSB_CE_PARTIAL 0x4
+#define CSB_CE_TERMINATE 0x2
+#define CSB_CE_TPBC_VALID 0x1
+
+#define csb_ce_termination(X) (!!((X) & CSB_CE_TERMINATE))
+/* termination, output buffers may be modified, SPBC/TPBC invalid Fig.6-7 */
+
+#define csb_ce_check_completion(X) (!csb_ce_termination(X))
+/* if not terminated then check full or partial completion */
+
+#define csb_ce_partial_completion(X) (!!((X) & CSB_CE_PARTIAL))
+#define csb_ce_full_completion(X) (!csb_ce_partial_completion(X))
+#define csb_ce_tpbc_valid(X) (!!((X) & CSB_CE_TPBC_VALID))
+/* TPBC indicates successfully stored data count */
+
+#define csb_ce_default_err(X) csb_ce_termination(X)
+/* most error CEs have CE(0)=0 and CE(1)=1 */
+
+#define csb_ce_cc3_partial(X) csb_ce_partial_completion(X)
+/* some CC=3 are partially completed, Table 6-8 */
+
+#define csb_ce_cc64(X) ((X)&(CSB_CE_PARTIAL \
+ | CSB_CE_TERMINATE) == 0)
+/* Compression: when TPBC>SPBC then CC=64 Table 6-8; target didn't
+ * compress smaller than source.
+ */
+
+/* Decompress SFBT combinations Tables 5-3, 6-4, 6-6 */
+
+#define SFBT_BFINAL 0x1
+#define SFBT_LIT 0x4
+#define SFBT_FHT 0x5
+#define SFBT_DHT 0x6
+#define SFBT_HDR 0x7
+
+/*
+ * NX gzip function codes. Table 6.2.
+ * Bits 0:4 are the FC. Bit 5 is used by the DMA controller to
+ * select one of the two Byte Count Limits.
+ */
+
+#define GZIP_FC_LIMIT_MASK 0x01
+#define GZIP_FC_COMPRESS_FHT 0x00
+#define GZIP_FC_COMPRESS_DHT 0x02
+#define GZIP_FC_COMPRESS_FHT_COUNT 0x04
+#define GZIP_FC_COMPRESS_DHT_COUNT 0x06
+#define GZIP_FC_COMPRESS_RESUME_FHT 0x08
+#define GZIP_FC_COMPRESS_RESUME_DHT 0x0a
+#define GZIP_FC_COMPRESS_RESUME_FHT_COUNT 0x0c
+#define GZIP_FC_COMPRESS_RESUME_DHT_COUNT 0x0e
+#define GZIP_FC_DECOMPRESS 0x10
+#define GZIP_FC_DECOMPRESS_SINGLE_BLK_N_SUSPEND 0x12
+#define GZIP_FC_DECOMPRESS_RESUME 0x14
+#define GZIP_FC_DECOMPRESS_RESUME_SINGLE_BLK_N_SUSPEND 0x16
+#define GZIP_FC_WRAP 0x1e
+
+#define fc_is_compress(fc) (((fc) & 0x10) == 0)
+#define fc_has_count(fc) (fc_is_compress(fc) && (((fc) & 0x4) != 0))
+
+/* CSB.CC Error codes */
+
+#define ERR_NX_OK 0
+#define ERR_NX_ALIGNMENT 1
+#define ERR_NX_OPOVERLAP 2
+#define ERR_NX_DATA_LENGTH 3
+#define ERR_NX_TRANSLATION 5
+#define ERR_NX_PROTECTION 6
+#define ERR_NX_EXTERNAL_UE7 7
+#define ERR_NX_INVALID_OP 8
+#define ERR_NX_PRIVILEGE 9
+#define ERR_NX_INTERNAL_UE 10
+#define ERR_NX_EXTERN_UE_WR 12
+#define ERR_NX_TARGET_SPACE 13
+#define ERR_NX_EXCESSIVE_DDE 14
+#define ERR_NX_TRANSL_WR 15
+#define ERR_NX_PROTECT_WR 16
+#define ERR_NX_SUBFUNCTION 17
+#define ERR_NX_FUNC_ABORT 18
+#define ERR_NX_BYTE_MAX 19
+#define ERR_NX_CORRUPT_CRB 20
+#define ERR_NX_INVALID_CRB 21
+#define ERR_NX_INVALID_DDE 30
+#define ERR_NX_SEGMENTED_DDL 31
+#define ERR_NX_DDE_OVERFLOW 33
+#define ERR_NX_TPBC_GT_SPBC 64
+#define ERR_NX_MISSING_CODE 66
+#define ERR_NX_INVALID_DIST 67
+#define ERR_NX_INVALID_DHT 68
+#define ERR_NX_EXTERNAL_UE90 90
+#define ERR_NX_WDOG_TIMER 224
+#define ERR_NX_AT_FAULT 250
+#define ERR_NX_INTR_SERVER 252
+#define ERR_NX_UE253 253
+#define ERR_NX_NO_HW 254
+#define ERR_NX_HUNG_OP 255
+#define ERR_NX_END 256
+
+/* initial values for non-resume operations */
+#define INIT_CRC 0 /* crc32(0L, Z_NULL, 0) */
+#define INIT_ADLER 1 /* adler32(0L, Z_NULL, 0) adler is initialized to 1 */
+
+/* prototypes */
+int nxu_submit_job(struct nx_gzip_crb_cpb_t *c, void *handle);
+
+extern void nxu_sigsegv_handler(int sig, siginfo_t *info, void *ctx);
+extern int nxu_touch_pages(void *buf, long buf_len, long page_len, int wr);
+
+/* caller supplies a print buffer 4*sizeof(crb) */
+
+char *nx_crb_str(struct nx_gzip_crb_t *crb, char *prbuf);
+char *nx_cpb_str(struct nx_gzip_cpb_t *cpb, char *prbuf);
+char *nx_prt_hex(void *cp, int sz, char *prbuf);
+char *nx_lzcount_str(struct nx_gzip_cpb_t *cpb, char *prbuf);
+char *nx_strerror(int e);
+
+#ifdef NX_SIM
+#include <stdio.h>
+int nx_sim_init(void *ctx);
+int nx_sim_end(void *ctx);
+int nxu_run_sim_job(struct nx_gzip_crb_cpb_t *c, void *ctx);
+#endif /* NX_SIM */
+
+/* Deflate stream manipulation */
+
+#define set_final_bit(x) (x |= (unsigned char)1)
+#define clr_final_bit(x) (x &= ~(unsigned char)1)
+
+#define append_empty_fh_blk(p, b) do { *(p) = (2 | (1&(b))); *((p)+1) = 0; \
+ } while (0)
+/* append 10 bits 0000001b 00...... ;
+ * assumes appending starts on a byte boundary; b is the final bit.
+ */
+
+
+#ifdef NX_842
+
+/* 842 Engine */
+
+struct nx_eft_crb_t {
+ union { /* byte[0:3] */
+ uint32_t eft_fc; /* bits[29-31] */
+ };
+ uint32_t reserved1; /* byte[4:7] */
+ union {
+ uint64_t csb_address; /* byte[8:15] */
+ struct {
+ uint32_t reserved2;
+ union {
+ uint32_t crb_c;
+ /* c==0 no ccb defined */
+
+ uint32_t crb_at;
+ /* at==0 address type is ignored;
+ * all addrs effective assumed.
+ */
+
+ };
+ };
+ };
+ struct nx_dde_t source_dde; /* byte[16:31] */
+ struct nx_dde_t target_dde; /* byte[32:47] */
+ struct nx_ccb_t ccb; /* byte[48:63] */
+ union {
+ union nx_qw_t reserved64[3]; /* byte[64:96] */
+ };
+ struct nx_csb_t csb;
+} __aligned(128);
+
+/* 842 CRB */
+
+#define EFT_FC_MASK size_mask(3)
+#define EFT_FC_OFFSET 31
+#define EFT_FC_COMPRESS 0x0
+#define EFT_FC_COMPRESS_WITH_CRC 0x1
+#define EFT_FC_DECOMPRESS 0x2
+#define EFT_FC_DECOMPRESS_WITH_CRC 0x3
+#define EFT_FC_BLK_DATA_MOVE 0x4
+#endif /* NX_842 */
+
+#endif /* _NXU_H */
diff --git a/tools/testing/selftests/powerpc/nx-gzip/include/vas-api.h b/tools/testing/selftests/powerpc/nx-gzip/include/vas-api.h
new file mode 120000
index 000000000000..77fb4c7236d0
--- /dev/null
+++ b/tools/testing/selftests/powerpc/nx-gzip/include/vas-api.h
@@ -0,0 +1 @@
+../../../../../../arch/powerpc/include/uapi/asm/vas-api.h \ No newline at end of file
diff --git a/tools/testing/selftests/powerpc/nx-gzip/nx-gzip-test.sh b/tools/testing/selftests/powerpc/nx-gzip/nx-gzip-test.sh
new file mode 100755
index 000000000000..c7b46c5fd7b3
--- /dev/null
+++ b/tools/testing/selftests/powerpc/nx-gzip/nx-gzip-test.sh
@@ -0,0 +1,46 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0-or-later
+
+if [[ ! -w /dev/crypto/nx-gzip ]]; then
+ echo "Can't access /dev/crypto/nx-gzip, skipping"
+ echo "skip: $0"
+ exit 4
+fi
+
+set -e
+
+function cleanup
+{
+ rm -f nx-tempfile*
+}
+
+trap cleanup EXIT
+
+function test_sizes
+{
+ local n=$1
+ local fname="nx-tempfile.$n"
+
+ for size in 4K 64K 1M 64M
+ do
+ echo "Testing $size ($n) ..."
+ dd if=/dev/urandom of=$fname bs=$size count=1
+ ./gzfht_test $fname
+ ./gunz_test ${fname}.nx.gz
+ done
+}
+
+echo "Doing basic test of different sizes ..."
+test_sizes 0
+
+echo "Running tests in parallel ..."
+for i in {1..16}
+do
+ test_sizes $i &
+done
+
+wait
+
+echo "OK"
+
+exit 0
diff --git a/tools/testing/selftests/powerpc/pmu/.gitignore b/tools/testing/selftests/powerpc/pmu/.gitignore
index e748f336eed3..f69b1e2641a1 100644
--- a/tools/testing/selftests/powerpc/pmu/.gitignore
+++ b/tools/testing/selftests/powerpc/pmu/.gitignore
@@ -1,3 +1,5 @@
+# SPDX-License-Identifier: GPL-2.0-only
count_instructions
l3_bank_test
per_event_excludes
+count_stcx_fail
diff --git a/tools/testing/selftests/powerpc/pmu/Makefile b/tools/testing/selftests/powerpc/pmu/Makefile
index 19046db995fe..904672fb78dd 100644
--- a/tools/testing/selftests/powerpc/pmu/Makefile
+++ b/tools/testing/selftests/powerpc/pmu/Makefile
@@ -2,7 +2,7 @@
noarg:
$(MAKE) -C ../
-TEST_GEN_PROGS := count_instructions l3_bank_test per_event_excludes
+TEST_GEN_PROGS := count_instructions count_stcx_fail l3_bank_test per_event_excludes
EXTRA_SOURCES := ../harness.c event.c lib.c ../utils.c
top_srcdir = ../../../../..
@@ -13,8 +13,12 @@ all: $(TEST_GEN_PROGS) ebb
$(TEST_GEN_PROGS): $(EXTRA_SOURCES)
# loop.S can only be built 64-bit
+$(OUTPUT)/count_instructions: CFLAGS += -m64
$(OUTPUT)/count_instructions: loop.S count_instructions.c $(EXTRA_SOURCES)
- $(CC) $(CFLAGS) -m64 -o $@ $^
+
+$(OUTPUT)/count_stcx_fail: CFLAGS += -m64
+$(OUTPUT)/count_stcx_fail: loop.S $(EXTRA_SOURCES)
+
$(OUTPUT)/per_event_excludes: ../utils.c
diff --git a/tools/testing/selftests/powerpc/pmu/count_stcx_fail.c b/tools/testing/selftests/powerpc/pmu/count_stcx_fail.c
new file mode 100644
index 000000000000..7b4ac4537702
--- /dev/null
+++ b/tools/testing/selftests/powerpc/pmu/count_stcx_fail.c
@@ -0,0 +1,161 @@
+/*
+ * Copyright 2013, Michael Ellerman, IBM Corp.
+ * Licensed under GPLv2.
+ */
+
+#define _GNU_SOURCE
+
+#include <stdio.h>
+#include <stdbool.h>
+#include <string.h>
+#include <sys/prctl.h>
+
+#include "event.h"
+#include "utils.h"
+#include "lib.h"
+
+extern void thirty_two_instruction_loop_with_ll_sc(u64 loops, u64 *ll_sc_target);
+
+static void setup_event(struct event *e, u64 config, int type, char *name)
+{
+ event_init_opts(e, config, type, name);
+
+ e->attr.disabled = 1;
+ e->attr.exclude_kernel = 1;
+ e->attr.exclude_hv = 1;
+ e->attr.exclude_idle = 1;
+}
+
+static int do_count_loop(struct event *events, u64 instructions,
+ u64 overhead, bool report)
+{
+ s64 difference, expected;
+ double percentage;
+ u64 dummy;
+
+ prctl(PR_TASK_PERF_EVENTS_ENABLE);
+
+ /* Run for 1M instructions */
+ thirty_two_instruction_loop_with_ll_sc(instructions >> 5, &dummy);
+
+ prctl(PR_TASK_PERF_EVENTS_DISABLE);
+
+ event_read(&events[0]);
+ event_read(&events[1]);
+ event_read(&events[2]);
+
+ expected = instructions + overhead + (events[2].result.value * 10);
+ difference = events[0].result.value - expected;
+ percentage = (double)difference / events[0].result.value * 100;
+
+ if (report) {
+ printf("-----\n");
+ event_report(&events[0]);
+ event_report(&events[1]);
+ event_report(&events[2]);
+
+ printf("Looped for %llu instructions, overhead %llu\n", instructions, overhead);
+ printf("Expected %llu\n", expected);
+ printf("Actual %llu\n", events[0].result.value);
+ printf("Delta %lld, %f%%\n", difference, percentage);
+ }
+
+ event_reset(&events[0]);
+ event_reset(&events[1]);
+ event_reset(&events[2]);
+
+ if (difference < 0)
+ difference = -difference;
+
+ /* Tolerate a difference below 0.0001 % */
+ difference *= 10000 * 100;
+ if (difference / events[0].result.value)
+ return -1;
+
+ return 0;
+}
+
+/* Count how many instructions it takes to do a null loop */
+static u64 determine_overhead(struct event *events)
+{
+ u64 current, overhead;
+ int i;
+
+ do_count_loop(events, 0, 0, false);
+ overhead = events[0].result.value;
+
+ for (i = 0; i < 100; i++) {
+ do_count_loop(events, 0, 0, false);
+ current = events[0].result.value;
+ if (current < overhead) {
+ printf("Replacing overhead %llu with %llu\n", overhead, current);
+ overhead = current;
+ }
+ }
+
+ return overhead;
+}
+
+#define PM_MRK_STCX_FAIL 0x03e158
+#define PM_STCX_FAIL 0x01e058
+
+static int test_body(void)
+{
+ struct event events[3];
+ u64 overhead;
+
+ setup_event(&events[0], PERF_COUNT_HW_INSTRUCTIONS, PERF_TYPE_HARDWARE, "instructions");
+ setup_event(&events[1], PERF_COUNT_HW_CPU_CYCLES, PERF_TYPE_HARDWARE, "cycles");
+ setup_event(&events[2], PM_STCX_FAIL, PERF_TYPE_RAW, "stcx_fail");
+
+ if (event_open(&events[0])) {
+ perror("perf_event_open");
+ return -1;
+ }
+
+ if (event_open_with_group(&events[1], events[0].fd)) {
+ perror("perf_event_open");
+ return -1;
+ }
+
+ if (event_open_with_group(&events[2], events[0].fd)) {
+ perror("perf_event_open");
+ return -1;
+ }
+
+ overhead = determine_overhead(events);
+ printf("Overhead of null loop: %llu instructions\n", overhead);
+
+ /* Run for 1Mi instructions */
+ FAIL_IF(do_count_loop(events, 1000000, overhead, true));
+
+ /* Run for 10Mi instructions */
+ FAIL_IF(do_count_loop(events, 10000000, overhead, true));
+
+ /* Run for 100Mi instructions */
+ FAIL_IF(do_count_loop(events, 100000000, overhead, true));
+
+ /* Run for 1Bi instructions */
+ FAIL_IF(do_count_loop(events, 1000000000, overhead, true));
+
+ /* Run for 16Bi instructions */
+ FAIL_IF(do_count_loop(events, 16000000000, overhead, true));
+
+ /* Run for 64Bi instructions */
+ FAIL_IF(do_count_loop(events, 64000000000, overhead, true));
+
+ event_close(&events[0]);
+ event_close(&events[1]);
+
+ return 0;
+}
+
+static int count_ll_sc(void)
+{
+ return eat_cpu(test_body);
+}
+
+int main(void)
+{
+ return test_harness(count_ll_sc, "count_ll_sc");
+}
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/.gitignore b/tools/testing/selftests/powerpc/pmu/ebb/.gitignore
index 42bddbed8b64..2920fb39439b 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/.gitignore
+++ b/tools/testing/selftests/powerpc/pmu/ebb/.gitignore
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
reg_access_test
event_attributes_test
cycles_test
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/Makefile b/tools/testing/selftests/powerpc/pmu/ebb/Makefile
index 417306353e07..ca35dd8848b0 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/Makefile
+++ b/tools/testing/selftests/powerpc/pmu/ebb/Makefile
@@ -7,6 +7,7 @@ noarg:
# The EBB handler is 64-bit code and everything links against it
CFLAGS += -m64
+TMPOUT = $(OUTPUT)/
# Toolchains may build PIE by default which breaks the assembly
no-pie-option := $(call try-run, echo 'int main() { return 0; }' | \
$(CC) -Werror $(KBUILD_CPPFLAGS) $(CC_OPTION_CFLAGS) -no-pie -x c - -o "$$TMP", -no-pie)
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/trace.h b/tools/testing/selftests/powerpc/pmu/ebb/trace.h
index 7c0fb5d2bdb1..da2a3be5441f 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/trace.h
+++ b/tools/testing/selftests/powerpc/pmu/ebb/trace.h
@@ -18,7 +18,7 @@ struct trace_entry
{
u8 type;
u8 length;
- u8 data[0];
+ u8 data[];
};
struct trace_buffer
@@ -26,7 +26,7 @@ struct trace_buffer
u64 size;
bool overflow;
void *tail;
- u8 data[0];
+ u8 data[];
};
struct trace_buffer *trace_buffer_allocate(u64 size);
diff --git a/tools/testing/selftests/powerpc/pmu/loop.S b/tools/testing/selftests/powerpc/pmu/loop.S
index 8cc9b5e2c9de..c52ba09b6fed 100644
--- a/tools/testing/selftests/powerpc/pmu/loop.S
+++ b/tools/testing/selftests/powerpc/pmu/loop.S
@@ -41,3 +41,38 @@ FUNC_START(thirty_two_instruction_loop)
subi r3,r3,1
b FUNC_NAME(thirty_two_instruction_loop)
FUNC_END(thirty_two_instruction_loop)
+
+FUNC_START(thirty_two_instruction_loop_with_ll_sc)
+ cmpdi r3,0
+ beqlr
+ addi r5,r5,1
+ addi r5,r5,1
+ addi r5,r5,1 # 5
+ addi r5,r5,1
+ addi r5,r5,1
+ addi r5,r5,1
+ addi r5,r5,1
+1: ldarx r6,0,r4 # 10
+ addi r5,r5,1
+ addi r5,r5,1
+ addi r5,r5,1
+ addi r5,r5,1
+ addi r5,r5,1 # 15
+ addi r5,r5,1
+ addi r5,r5,1
+ stdcx. r6,0,r4
+ bne- 1b
+ addi r5,r5,1 # 20
+ addi r5,r5,1
+ addi r5,r5,1
+ addi r5,r5,1
+ addi r5,r5,1
+ addi r5,r5,1 # 25
+ addi r5,r5,1
+ addi r5,r5,1
+ addi r5,r5,1
+ addi r5,r5,1
+ addi r5,r5,1 # 30
+ subi r3,r3,1
+ b FUNC_NAME(thirty_two_instruction_loop_with_ll_sc)
+FUNC_END(thirty_two_instruction_loop_with_ll_sc)
diff --git a/tools/testing/selftests/powerpc/primitives/.gitignore b/tools/testing/selftests/powerpc/primitives/.gitignore
index 4cc4e31bed1d..1e5c04e24254 100644
--- a/tools/testing/selftests/powerpc/primitives/.gitignore
+++ b/tools/testing/selftests/powerpc/primitives/.gitignore
@@ -1 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
load_unaligned_zeropad
diff --git a/tools/testing/selftests/powerpc/ptrace/.gitignore b/tools/testing/selftests/powerpc/ptrace/.gitignore
index dce19f221c46..0e96150b7c7e 100644
--- a/tools/testing/selftests/powerpc/ptrace/.gitignore
+++ b/tools/testing/selftests/powerpc/ptrace/.gitignore
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
ptrace-gpr
ptrace-tm-gpr
ptrace-tm-spd-gpr
diff --git a/tools/testing/selftests/powerpc/security/.gitignore b/tools/testing/selftests/powerpc/security/.gitignore
index 0b969fba3beb..f795e06f5ae3 100644
--- a/tools/testing/selftests/powerpc/security/.gitignore
+++ b/tools/testing/selftests/powerpc/security/.gitignore
@@ -1 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
rfi_flush
diff --git a/tools/testing/selftests/powerpc/signal/.gitignore b/tools/testing/selftests/powerpc/signal/.gitignore
index dca5852a1546..405b5364044c 100644
--- a/tools/testing/selftests/powerpc/signal/.gitignore
+++ b/tools/testing/selftests/powerpc/signal/.gitignore
@@ -1,3 +1,5 @@
+# SPDX-License-Identifier: GPL-2.0-only
signal
signal_tm
sigfuz
+sigreturn_vdso
diff --git a/tools/testing/selftests/powerpc/signal/Makefile b/tools/testing/selftests/powerpc/signal/Makefile
index 113838fbbe7f..d6ae54663aed 100644
--- a/tools/testing/selftests/powerpc/signal/Makefile
+++ b/tools/testing/selftests/powerpc/signal/Makefile
@@ -1,10 +1,12 @@
# SPDX-License-Identifier: GPL-2.0
-TEST_GEN_PROGS := signal signal_tm sigfuz
+TEST_GEN_PROGS := signal signal_tm sigfuz sigreturn_vdso sig_sc_double_restart
CFLAGS += -maltivec
$(OUTPUT)/signal_tm: CFLAGS += -mhtm
$(OUTPUT)/sigfuz: CFLAGS += -pthread -m64
+TEST_FILES := settings
+
top_srcdir = ../../../../..
include ../../lib.mk
diff --git a/tools/testing/selftests/powerpc/signal/settings b/tools/testing/selftests/powerpc/signal/settings
new file mode 100644
index 000000000000..e7b9417537fb
--- /dev/null
+++ b/tools/testing/selftests/powerpc/signal/settings
@@ -0,0 +1 @@
+timeout=0
diff --git a/tools/testing/selftests/powerpc/signal/sig_sc_double_restart.c b/tools/testing/selftests/powerpc/signal/sig_sc_double_restart.c
new file mode 100644
index 000000000000..e3972264615b
--- /dev/null
+++ b/tools/testing/selftests/powerpc/signal/sig_sc_double_restart.c
@@ -0,0 +1,174 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Test that a syscall does not get restarted twice, handled by trap_norestart()
+ *
+ * Based on Al's description, and a test for the bug fixed in this commit:
+ *
+ * commit 9a81c16b527528ad307843be5571111aa8d35a80
+ * Author: Al Viro <viro@zeniv.linux.org.uk>
+ * Date: Mon Sep 20 21:48:57 2010 +0100
+ *
+ * powerpc: fix double syscall restarts
+ *
+ * Make sigreturn zero regs->trap, make do_signal() do the same on all
+ * paths. As it is, signal interrupting e.g. read() from fd 512 (==
+ * ERESTARTSYS) with another signal getting unblocked when the first
+ * handler finishes will lead to restart one insn earlier than it ought
+ * to. Same for multiple signals with in-kernel handlers interrupting
+ * that sucker at the same time. Same for multiple signals of any kind
+ * interrupting that sucker on 64bit...
+ */
+#define _GNU_SOURCE
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <sys/syscall.h>
+#include <unistd.h>
+#include <signal.h>
+#include <errno.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+
+#include "utils.h"
+
+static void SIGUSR1_handler(int sig)
+{
+ kill(getpid(), SIGUSR2);
+ /*
+ * SIGUSR2 is blocked until the handler exits, at which point it will
+ * be raised again and think there is a restart to be done because the
+ * pending restarted syscall has 512 (ERESTARTSYS) in r3. The second
+ * restart will retreat NIP another 4 bytes to fail case branch.
+ */
+}
+
+static void SIGUSR2_handler(int sig)
+{
+}
+
+static ssize_t raw_read(int fd, void *buf, size_t count)
+{
+ register long nr asm("r0") = __NR_read;
+ register long _fd asm("r3") = fd;
+ register void *_buf asm("r4") = buf;
+ register size_t _count asm("r5") = count;
+
+ asm volatile(
+" b 0f \n"
+" b 1f \n"
+" 0: sc 0 \n"
+" bns 2f \n"
+" neg %0,%0 \n"
+" b 2f \n"
+" 1: \n"
+" li %0,%4 \n"
+" 2: \n"
+ : "+r"(_fd), "+r"(nr), "+r"(_buf), "+r"(_count)
+ : "i"(-ENOANO)
+ : "memory", "r6", "r7", "r8", "r9", "r10", "r11", "r12", "ctr", "cr0");
+
+ if (_fd < 0) {
+ errno = -_fd;
+ _fd = -1;
+ }
+
+ return _fd;
+}
+
+#define DATA "test 123"
+#define DLEN (strlen(DATA)+1)
+
+int test_restart(void)
+{
+ int pipefd[2];
+ pid_t pid;
+ char buf[512];
+
+ if (pipe(pipefd) == -1) {
+ perror("pipe");
+ exit(EXIT_FAILURE);
+ }
+
+ pid = fork();
+ if (pid == -1) {
+ perror("fork");
+ exit(EXIT_FAILURE);
+ }
+
+ if (pid == 0) { /* Child reads from pipe */
+ struct sigaction act;
+ int fd;
+
+ memset(&act, 0, sizeof(act));
+ sigaddset(&act.sa_mask, SIGUSR2);
+ act.sa_handler = SIGUSR1_handler;
+ act.sa_flags = SA_RESTART;
+ if (sigaction(SIGUSR1, &act, NULL) == -1) {
+ perror("sigaction");
+ exit(EXIT_FAILURE);
+ }
+
+ memset(&act, 0, sizeof(act));
+ act.sa_handler = SIGUSR2_handler;
+ act.sa_flags = SA_RESTART;
+ if (sigaction(SIGUSR2, &act, NULL) == -1) {
+ perror("sigaction");
+ exit(EXIT_FAILURE);
+ }
+
+ /* Let's get ERESTARTSYS into r3 */
+ while ((fd = dup(pipefd[0])) != 512) {
+ if (fd == -1) {
+ perror("dup");
+ exit(EXIT_FAILURE);
+ }
+ }
+
+ if (raw_read(fd, buf, 512) == -1) {
+ if (errno == ENOANO) {
+ fprintf(stderr, "Double restart moved restart before sc instruction.\n");
+ _exit(EXIT_FAILURE);
+ }
+ perror("read");
+ exit(EXIT_FAILURE);
+ }
+
+ if (strncmp(buf, DATA, DLEN)) {
+ fprintf(stderr, "bad test string %s\n", buf);
+ exit(EXIT_FAILURE);
+ }
+
+ return 0;
+
+ } else {
+ int wstatus;
+
+ usleep(100000); /* Hack to get reader waiting */
+ kill(pid, SIGUSR1);
+ usleep(100000);
+ if (write(pipefd[1], DATA, DLEN) != DLEN) {
+ perror("write");
+ exit(EXIT_FAILURE);
+ }
+ close(pipefd[0]);
+ close(pipefd[1]);
+ if (wait(&wstatus) == -1) {
+ perror("wait");
+ exit(EXIT_FAILURE);
+ }
+ if (!WIFEXITED(wstatus)) {
+ fprintf(stderr, "child exited abnormally\n");
+ exit(EXIT_FAILURE);
+ }
+
+ FAIL_IF(WEXITSTATUS(wstatus) != EXIT_SUCCESS);
+
+ return 0;
+ }
+}
+
+int main(void)
+{
+ test_harness_set_timeout(10);
+ return test_harness(test_restart, "sig sys restart");
+}
diff --git a/tools/testing/selftests/powerpc/signal/sigreturn_vdso.c b/tools/testing/selftests/powerpc/signal/sigreturn_vdso.c
new file mode 100644
index 000000000000..e282fff0fe25
--- /dev/null
+++ b/tools/testing/selftests/powerpc/signal/sigreturn_vdso.c
@@ -0,0 +1,127 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Test that we can take signals with and without the VDSO mapped, which trigger
+ * different paths in the signal handling code.
+ *
+ * See handle_rt_signal64() and setup_trampoline() in signal_64.c
+ */
+
+#define _GNU_SOURCE
+
+#include <errno.h>
+#include <stdio.h>
+#include <signal.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/mman.h>
+#include <sys/types.h>
+#include <unistd.h>
+
+// Ensure assert() is not compiled out
+#undef NDEBUG
+#include <assert.h>
+
+#include "utils.h"
+
+static int search_proc_maps(char *needle, unsigned long *low, unsigned long *high)
+{
+ unsigned long start, end;
+ static char buf[4096];
+ char name[128];
+ FILE *f;
+ int rc = -1;
+
+ f = fopen("/proc/self/maps", "r");
+ if (!f) {
+ perror("fopen");
+ return -1;
+ }
+
+ while (fgets(buf, sizeof(buf), f)) {
+ rc = sscanf(buf, "%lx-%lx %*c%*c%*c%*c %*x %*d:%*d %*d %127s\n",
+ &start, &end, name);
+ if (rc == 2)
+ continue;
+
+ if (rc != 3) {
+ printf("sscanf errored\n");
+ rc = -1;
+ break;
+ }
+
+ if (strstr(name, needle)) {
+ *low = start;
+ *high = end - 1;
+ rc = 0;
+ break;
+ }
+ }
+
+ fclose(f);
+
+ return rc;
+}
+
+static volatile sig_atomic_t took_signal = 0;
+
+static void sigusr1_handler(int sig)
+{
+ took_signal++;
+}
+
+int test_sigreturn_vdso(void)
+{
+ unsigned long low, high, size;
+ struct sigaction act;
+ char *p;
+
+ act.sa_handler = sigusr1_handler;
+ act.sa_flags = 0;
+ sigemptyset(&act.sa_mask);
+
+ assert(sigaction(SIGUSR1, &act, NULL) == 0);
+
+ // Confirm the VDSO is mapped, and work out where it is
+ assert(search_proc_maps("[vdso]", &low, &high) == 0);
+ size = high - low + 1;
+ printf("VDSO is at 0x%lx-0x%lx (%lu bytes)\n", low, high, size);
+
+ kill(getpid(), SIGUSR1);
+ assert(took_signal == 1);
+ printf("Signal delivered OK with VDSO mapped\n");
+
+ // Remap the VDSO somewhere else
+ p = mmap(NULL, size, PROT_READ|PROT_WRITE, MAP_ANONYMOUS|MAP_PRIVATE, -1, 0);
+ assert(p != MAP_FAILED);
+ assert(mremap((void *)low, size, size, MREMAP_MAYMOVE|MREMAP_FIXED, p) != MAP_FAILED);
+ assert(search_proc_maps("[vdso]", &low, &high) == 0);
+ size = high - low + 1;
+ printf("VDSO moved to 0x%lx-0x%lx (%lu bytes)\n", low, high, size);
+
+ kill(getpid(), SIGUSR1);
+ assert(took_signal == 2);
+ printf("Signal delivered OK with VDSO moved\n");
+
+ assert(munmap((void *)low, size) == 0);
+ printf("Unmapped VDSO\n");
+
+ // Confirm the VDSO is not mapped anymore
+ assert(search_proc_maps("[vdso]", &low, &high) != 0);
+
+ // Make the stack executable
+ assert(search_proc_maps("[stack]", &low, &high) == 0);
+ size = high - low + 1;
+ mprotect((void *)low, size, PROT_READ|PROT_WRITE|PROT_EXEC);
+ printf("Remapped the stack executable\n");
+
+ kill(getpid(), SIGUSR1);
+ assert(took_signal == 3);
+ printf("Signal delivered OK with VDSO unmapped\n");
+
+ return 0;
+}
+
+int main(void)
+{
+ return test_harness(test_sigreturn_vdso, "sigreturn_vdso");
+}
diff --git a/tools/testing/selftests/powerpc/stringloops/.gitignore b/tools/testing/selftests/powerpc/stringloops/.gitignore
index 31a17e0ba884..b0dfc74aa57e 100644
--- a/tools/testing/selftests/powerpc/stringloops/.gitignore
+++ b/tools/testing/selftests/powerpc/stringloops/.gitignore
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
memcmp_64
memcmp_32
strlen
diff --git a/tools/testing/selftests/powerpc/switch_endian/.gitignore b/tools/testing/selftests/powerpc/switch_endian/.gitignore
index 89e762eab676..30e962cf84d1 100644
--- a/tools/testing/selftests/powerpc/switch_endian/.gitignore
+++ b/tools/testing/selftests/powerpc/switch_endian/.gitignore
@@ -1,2 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0-only
switch_endian_test
check-reversed.S
diff --git a/tools/testing/selftests/powerpc/syscalls/.gitignore b/tools/testing/selftests/powerpc/syscalls/.gitignore
index f0f3fcc9d802..b00cab225476 100644
--- a/tools/testing/selftests/powerpc/syscalls/.gitignore
+++ b/tools/testing/selftests/powerpc/syscalls/.gitignore
@@ -1 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
ipc_unmuxed
diff --git a/tools/testing/selftests/powerpc/tm/.gitignore b/tools/testing/selftests/powerpc/tm/.gitignore
index 98f2708d86cc..d8900a0c47a1 100644
--- a/tools/testing/selftests/powerpc/tm/.gitignore
+++ b/tools/testing/selftests/powerpc/tm/.gitignore
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
tm-resched-dscr
tm-syscall
tm-signal-msr-resv
@@ -13,6 +14,7 @@ tm-signal-context-chk-vmx
tm-signal-context-chk-vsx
tm-signal-context-force-tm
tm-signal-sigreturn-nt
+tm-signal-pagefault
tm-vmx-unavail
tm-unavailable
tm-trap
diff --git a/tools/testing/selftests/powerpc/tm/Makefile b/tools/testing/selftests/powerpc/tm/Makefile
index b15a1a325bd0..5881e97c73c1 100644
--- a/tools/testing/selftests/powerpc/tm/Makefile
+++ b/tools/testing/selftests/powerpc/tm/Makefile
@@ -5,7 +5,9 @@ SIGNAL_CONTEXT_CHK_TESTS := tm-signal-context-chk-gpr tm-signal-context-chk-fpu
TEST_GEN_PROGS := tm-resched-dscr tm-syscall tm-signal-msr-resv tm-signal-stack \
tm-vmxcopy tm-fork tm-tar tm-tmspr tm-vmx-unavail tm-unavailable tm-trap \
$(SIGNAL_CONTEXT_CHK_TESTS) tm-sigreturn tm-signal-sigreturn-nt \
- tm-signal-context-force-tm tm-poison
+ tm-signal-context-force-tm tm-poison tm-signal-pagefault
+
+TEST_FILES := settings
top_srcdir = ../../../../..
include ../../lib.mk
@@ -22,6 +24,8 @@ $(OUTPUT)/tm-resched-dscr: ../pmu/lib.c
$(OUTPUT)/tm-unavailable: CFLAGS += -O0 -pthread -m64 -Wno-error=uninitialized -mvsx
$(OUTPUT)/tm-trap: CFLAGS += -O0 -pthread -m64
$(OUTPUT)/tm-signal-context-force-tm: CFLAGS += -pthread -m64
+$(OUTPUT)/tm-signal-pagefault: CFLAGS += -pthread -m64
+$(OUTPUT)/tm-poison: CFLAGS += -m64
SIGNAL_CONTEXT_CHK_TESTS := $(patsubst %,$(OUTPUT)/%,$(SIGNAL_CONTEXT_CHK_TESTS))
$(SIGNAL_CONTEXT_CHK_TESTS): tm-signal.S
diff --git a/tools/testing/selftests/powerpc/tm/settings b/tools/testing/selftests/powerpc/tm/settings
new file mode 100644
index 000000000000..e7b9417537fb
--- /dev/null
+++ b/tools/testing/selftests/powerpc/tm/settings
@@ -0,0 +1 @@
+timeout=0
diff --git a/tools/testing/selftests/powerpc/tm/tm-signal-context-force-tm.c b/tools/testing/selftests/powerpc/tm/tm-signal-context-force-tm.c
index 31717625f318..421cb082f6be 100644
--- a/tools/testing/selftests/powerpc/tm/tm-signal-context-force-tm.c
+++ b/tools/testing/selftests/powerpc/tm/tm-signal-context-force-tm.c
@@ -42,9 +42,10 @@
#endif
/* Setting contexts because the test will crash and we want to recover */
-ucontext_t init_context, main_context;
+ucontext_t init_context;
-static int count, first_time;
+/* count is changed in the signal handler, so it must be volatile */
+static volatile int count;
void usr_signal_handler(int signo, siginfo_t *si, void *uc)
{
@@ -98,11 +99,6 @@ void usr_signal_handler(int signo, siginfo_t *si, void *uc)
void seg_signal_handler(int signo, siginfo_t *si, void *uc)
{
- if (count == COUNT_MAX) {
- /* Return to tm_signal_force_msr() and exit */
- setcontext(&main_context);
- }
-
count++;
/* Reexecute the test */
@@ -126,37 +122,41 @@ void tm_trap_test(void)
*/
getcontext(&init_context);
- /* Allocated an alternative signal stack area */
- ss.ss_sp = mmap(NULL, SIGSTKSZ, PROT_READ | PROT_WRITE,
- MAP_PRIVATE | MAP_ANONYMOUS, 0, 0);
- ss.ss_size = SIGSTKSZ;
- ss.ss_flags = 0;
+ while (count < COUNT_MAX) {
+ /* Allocated an alternative signal stack area */
+ ss.ss_sp = mmap(NULL, SIGSTKSZ, PROT_READ | PROT_WRITE,
+ MAP_PRIVATE | MAP_ANONYMOUS, 0, 0);
+ ss.ss_size = SIGSTKSZ;
+ ss.ss_flags = 0;
- if (ss.ss_sp == (void *)-1) {
- perror("mmap error\n");
- exit(-1);
- }
+ if (ss.ss_sp == (void *)-1) {
+ perror("mmap error\n");
+ exit(-1);
+ }
- /* Force the allocation through a page fault */
- if (madvise(ss.ss_sp, SIGSTKSZ, MADV_DONTNEED)) {
- perror("madvise\n");
- exit(-1);
- }
+ /* Force the allocation through a page fault */
+ if (madvise(ss.ss_sp, SIGSTKSZ, MADV_DONTNEED)) {
+ perror("madvise\n");
+ exit(-1);
+ }
- /* Setting an alternative stack to generate a page fault when
- * the signal is raised.
- */
- if (sigaltstack(&ss, NULL)) {
- perror("sigaltstack\n");
- exit(-1);
+ /*
+ * Setting an alternative stack to generate a page fault when
+ * the signal is raised.
+ */
+ if (sigaltstack(&ss, NULL)) {
+ perror("sigaltstack\n");
+ exit(-1);
+ }
+
+ /* The signal handler will enable MSR_TS */
+ sigaction(SIGUSR1, &usr_sa, NULL);
+ /* If it does not crash, it might segfault, avoid it to retest */
+ sigaction(SIGSEGV, &seg_sa, NULL);
+
+ raise(SIGUSR1);
+ count++;
}
-
- /* The signal handler will enable MSR_TS */
- sigaction(SIGUSR1, &usr_sa, NULL);
- /* If it does not crash, it will segfault, avoid it to retest */
- sigaction(SIGSEGV, &seg_sa, NULL);
-
- raise(SIGUSR1);
}
int tm_signal_context_force_tm(void)
@@ -169,11 +169,7 @@ int tm_signal_context_force_tm(void)
*/
SKIP_IF(!is_ppc64le());
- /* Will get back here after COUNT_MAX interactions */
- getcontext(&main_context);
-
- if (!first_time++)
- tm_trap_test();
+ tm_trap_test();
return EXIT_SUCCESS;
}
diff --git a/tools/testing/selftests/powerpc/tm/tm-signal-pagefault.c b/tools/testing/selftests/powerpc/tm/tm-signal-pagefault.c
new file mode 100644
index 000000000000..5908bc6abe60
--- /dev/null
+++ b/tools/testing/selftests/powerpc/tm/tm-signal-pagefault.c
@@ -0,0 +1,284 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2020, Gustavo Luiz Duarte, IBM Corp.
+ *
+ * This test starts a transaction and triggers a signal, forcing a pagefault to
+ * happen when the kernel signal handling code touches the user signal stack.
+ *
+ * In order to avoid pre-faulting the signal stack memory and to force the
+ * pagefault to happen precisely in the kernel signal handling code, the
+ * pagefault handling is done in userspace using the userfaultfd facility.
+ *
+ * Further pagefaults are triggered by crafting the signal handler's ucontext
+ * to point to additional memory regions managed by the userfaultfd, so using
+ * the same mechanism used to avoid pre-faulting the signal stack memory.
+ *
+ * On failure (bug is present) kernel crashes or never returns control back to
+ * userspace. If bug is not present, tests completes almost immediately.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <linux/userfaultfd.h>
+#include <poll.h>
+#include <unistd.h>
+#include <sys/ioctl.h>
+#include <sys/syscall.h>
+#include <fcntl.h>
+#include <sys/mman.h>
+#include <pthread.h>
+#include <signal.h>
+#include <errno.h>
+
+#include "tm.h"
+
+
+#define UF_MEM_SIZE 655360 /* 10 x 64k pages */
+
+/* Memory handled by userfaultfd */
+static char *uf_mem;
+static size_t uf_mem_offset = 0;
+
+/*
+ * Data that will be copied into the faulting pages (instead of zero-filled
+ * pages). This is used to make the test more reliable and avoid segfaulting
+ * when we return from the signal handler. Since we are making the signal
+ * handler's ucontext point to newly allocated memory, when that memory is
+ * paged-in it will contain the expected content.
+ */
+static char backing_mem[UF_MEM_SIZE];
+
+static size_t pagesize;
+
+/*
+ * Return a chunk of at least 'size' bytes of memory that will be handled by
+ * userfaultfd. If 'backing_data' is not NULL, its content will be save to
+ * 'backing_mem' and then copied into the faulting pages when the page fault
+ * is handled.
+ */
+void *get_uf_mem(size_t size, void *backing_data)
+{
+ void *ret;
+
+ if (uf_mem_offset + size > UF_MEM_SIZE) {
+ fprintf(stderr, "Requesting more uf_mem than expected!\n");
+ exit(EXIT_FAILURE);
+ }
+
+ ret = &uf_mem[uf_mem_offset];
+
+ /* Save the data that will be copied into the faulting page */
+ if (backing_data != NULL)
+ memcpy(&backing_mem[uf_mem_offset], backing_data, size);
+
+ /* Reserve the requested amount of uf_mem */
+ uf_mem_offset += size;
+ /* Keep uf_mem_offset aligned to the page size (round up) */
+ uf_mem_offset = (uf_mem_offset + pagesize - 1) & ~(pagesize - 1);
+
+ return ret;
+}
+
+void *fault_handler_thread(void *arg)
+{
+ struct uffd_msg msg; /* Data read from userfaultfd */
+ long uffd; /* userfaultfd file descriptor */
+ struct uffdio_copy uffdio_copy;
+ struct pollfd pollfd;
+ ssize_t nread, offset;
+
+ uffd = (long) arg;
+
+ for (;;) {
+ pollfd.fd = uffd;
+ pollfd.events = POLLIN;
+ if (poll(&pollfd, 1, -1) == -1) {
+ perror("poll() failed");
+ exit(EXIT_FAILURE);
+ }
+
+ nread = read(uffd, &msg, sizeof(msg));
+ if (nread == 0) {
+ fprintf(stderr, "read(): EOF on userfaultfd\n");
+ exit(EXIT_FAILURE);
+ }
+
+ if (nread == -1) {
+ perror("read() failed");
+ exit(EXIT_FAILURE);
+ }
+
+ /* We expect only one kind of event */
+ if (msg.event != UFFD_EVENT_PAGEFAULT) {
+ fprintf(stderr, "Unexpected event on userfaultfd\n");
+ exit(EXIT_FAILURE);
+ }
+
+ /*
+ * We need to handle page faults in units of pages(!).
+ * So, round faulting address down to page boundary.
+ */
+ uffdio_copy.dst = msg.arg.pagefault.address & ~(pagesize-1);
+
+ offset = (char *) uffdio_copy.dst - uf_mem;
+ uffdio_copy.src = (unsigned long) &backing_mem[offset];
+
+ uffdio_copy.len = pagesize;
+ uffdio_copy.mode = 0;
+ uffdio_copy.copy = 0;
+ if (ioctl(uffd, UFFDIO_COPY, &uffdio_copy) == -1) {
+ perror("ioctl-UFFDIO_COPY failed");
+ exit(EXIT_FAILURE);
+ }
+ }
+}
+
+void setup_uf_mem(void)
+{
+ long uffd; /* userfaultfd file descriptor */
+ pthread_t thr;
+ struct uffdio_api uffdio_api;
+ struct uffdio_register uffdio_register;
+ int ret;
+
+ pagesize = sysconf(_SC_PAGE_SIZE);
+
+ /* Create and enable userfaultfd object */
+ uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK);
+ if (uffd == -1) {
+ perror("userfaultfd() failed");
+ exit(EXIT_FAILURE);
+ }
+ uffdio_api.api = UFFD_API;
+ uffdio_api.features = 0;
+ if (ioctl(uffd, UFFDIO_API, &uffdio_api) == -1) {
+ perror("ioctl-UFFDIO_API failed");
+ exit(EXIT_FAILURE);
+ }
+
+ /*
+ * Create a private anonymous mapping. The memory will be demand-zero
+ * paged, that is, not yet allocated. When we actually touch the memory
+ * the related page will be allocated via the userfaultfd mechanism.
+ */
+ uf_mem = mmap(NULL, UF_MEM_SIZE, PROT_READ | PROT_WRITE,
+ MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+ if (uf_mem == MAP_FAILED) {
+ perror("mmap() failed");
+ exit(EXIT_FAILURE);
+ }
+
+ /*
+ * Register the memory range of the mapping we've just mapped to be
+ * handled by the userfaultfd object. In 'mode' we request to track
+ * missing pages (i.e. pages that have not yet been faulted-in).
+ */
+ uffdio_register.range.start = (unsigned long) uf_mem;
+ uffdio_register.range.len = UF_MEM_SIZE;
+ uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING;
+ if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register) == -1) {
+ perror("ioctl-UFFDIO_REGISTER");
+ exit(EXIT_FAILURE);
+ }
+
+ /* Create a thread that will process the userfaultfd events */
+ ret = pthread_create(&thr, NULL, fault_handler_thread, (void *) uffd);
+ if (ret != 0) {
+ fprintf(stderr, "pthread_create(): Error. Returned %d\n", ret);
+ exit(EXIT_FAILURE);
+ }
+}
+
+/*
+ * Assumption: the signal was delivered while userspace was in transactional or
+ * suspended state, i.e. uc->uc_link != NULL.
+ */
+void signal_handler(int signo, siginfo_t *si, void *uc)
+{
+ ucontext_t *ucp = uc;
+
+ /* Skip 'trap' after returning, otherwise we get a SIGTRAP again */
+ ucp->uc_link->uc_mcontext.regs->nip += 4;
+
+ ucp->uc_mcontext.v_regs =
+ get_uf_mem(sizeof(elf_vrreg_t), ucp->uc_mcontext.v_regs);
+
+ ucp->uc_link->uc_mcontext.v_regs =
+ get_uf_mem(sizeof(elf_vrreg_t), ucp->uc_link->uc_mcontext.v_regs);
+
+ ucp->uc_link = get_uf_mem(sizeof(ucontext_t), ucp->uc_link);
+}
+
+bool have_userfaultfd(void)
+{
+ long rc;
+
+ errno = 0;
+ rc = syscall(__NR_userfaultfd, -1);
+
+ return rc == 0 || errno != ENOSYS;
+}
+
+int tm_signal_pagefault(void)
+{
+ struct sigaction sa;
+ stack_t ss;
+
+ SKIP_IF(!have_htm());
+ SKIP_IF(!have_userfaultfd());
+
+ setup_uf_mem();
+
+ /*
+ * Set an alternative stack that will generate a page fault when the
+ * signal is raised. The page fault will be treated via userfaultfd,
+ * i.e. via fault_handler_thread.
+ */
+ ss.ss_sp = get_uf_mem(SIGSTKSZ, NULL);
+ ss.ss_size = SIGSTKSZ;
+ ss.ss_flags = 0;
+ if (sigaltstack(&ss, NULL) == -1) {
+ perror("sigaltstack() failed");
+ exit(EXIT_FAILURE);
+ }
+
+ sa.sa_flags = SA_SIGINFO | SA_ONSTACK;
+ sa.sa_sigaction = signal_handler;
+ if (sigaction(SIGTRAP, &sa, NULL) == -1) {
+ perror("sigaction() failed");
+ exit(EXIT_FAILURE);
+ }
+
+ /* Trigger a SIGTRAP in transactional state */
+ asm __volatile__(
+ "tbegin.;"
+ "beq 1f;"
+ "trap;"
+ "1: ;"
+ : : : "memory");
+
+ /* Trigger a SIGTRAP in suspended state */
+ asm __volatile__(
+ "tbegin.;"
+ "beq 1f;"
+ "tsuspend.;"
+ "trap;"
+ "tresume.;"
+ "1: ;"
+ : : : "memory");
+
+ return EXIT_SUCCESS;
+}
+
+int main(int argc, char **argv)
+{
+ /*
+ * Depending on kernel config, the TM Bad Thing might not result in a
+ * crash, instead the kernel never returns control back to userspace, so
+ * set a tight timeout. If the test passes it completes almost
+ * immediately.
+ */
+ test_harness_set_timeout(2);
+ return test_harness(tm_signal_pagefault, "tm_signal_pagefault");
+}
diff --git a/tools/testing/selftests/powerpc/vphn/.gitignore b/tools/testing/selftests/powerpc/vphn/.gitignore
index 7c04395010cb..b744aedfd1f2 100644
--- a/tools/testing/selftests/powerpc/vphn/.gitignore
+++ b/tools/testing/selftests/powerpc/vphn/.gitignore
@@ -1 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
test-vphn
diff --git a/tools/testing/selftests/prctl/.gitignore b/tools/testing/selftests/prctl/.gitignore
index 0b5c27447bf6..91af2b631bc9 100644
--- a/tools/testing/selftests/prctl/.gitignore
+++ b/tools/testing/selftests/prctl/.gitignore
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
disable-tsc-ctxt-sw-stress-test
disable-tsc-on-off-stress-test
disable-tsc-test
diff --git a/tools/testing/selftests/proc/.gitignore b/tools/testing/selftests/proc/.gitignore
index 66fab4c58ed4..bed4b5318a86 100644
--- a/tools/testing/selftests/proc/.gitignore
+++ b/tools/testing/selftests/proc/.gitignore
@@ -1,7 +1,10 @@
+# SPDX-License-Identifier: GPL-2.0-only
/fd-001-lookup
/fd-002-posix-eq
/fd-003-kthread
+/proc-fsconfig-hidepid
/proc-loadavg-001
+/proc-multiple-procfs
/proc-pid-vm
/proc-self-map-files-001
/proc-self-map-files-002
diff --git a/tools/testing/selftests/proc/Makefile b/tools/testing/selftests/proc/Makefile
index a8ed0f684829..8be8a03d2973 100644
--- a/tools/testing/selftests/proc/Makefile
+++ b/tools/testing/selftests/proc/Makefile
@@ -19,5 +19,7 @@ TEST_GEN_PROGS += self
TEST_GEN_PROGS += setns-dcache
TEST_GEN_PROGS += setns-sysvipc
TEST_GEN_PROGS += thread-self
+TEST_GEN_PROGS += proc-multiple-procfs
+TEST_GEN_PROGS += proc-fsconfig-hidepid
include ../lib.mk
diff --git a/tools/testing/selftests/proc/proc-fsconfig-hidepid.c b/tools/testing/selftests/proc/proc-fsconfig-hidepid.c
new file mode 100644
index 000000000000..b9af8f537185
--- /dev/null
+++ b/tools/testing/selftests/proc/proc-fsconfig-hidepid.c
@@ -0,0 +1,50 @@
+/*
+ * Copyright © 2020 Alexey Gladkov <gladkov.alexey@gmail.com>
+ *
+ * Permission to use, copy, modify, and distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+#include <assert.h>
+#include <unistd.h>
+#include <stdlib.h>
+#include <errno.h>
+#include <linux/mount.h>
+#include <linux/unistd.h>
+
+static inline int fsopen(const char *fsname, unsigned int flags)
+{
+ return syscall(__NR_fsopen, fsname, flags);
+}
+
+static inline int fsconfig(int fd, unsigned int cmd, const char *key, const void *val, int aux)
+{
+ return syscall(__NR_fsconfig, fd, cmd, key, val, aux);
+}
+
+int main(void)
+{
+ int fsfd, ret;
+ int hidepid = 2;
+
+ assert((fsfd = fsopen("proc", 0)) != -1);
+
+ ret = fsconfig(fsfd, FSCONFIG_SET_BINARY, "hidepid", &hidepid, 0);
+ assert(ret == -1);
+ assert(errno == EINVAL);
+
+ assert(!fsconfig(fsfd, FSCONFIG_SET_STRING, "hidepid", "2", 0));
+ assert(!fsconfig(fsfd, FSCONFIG_SET_STRING, "hidepid", "invisible", 0));
+
+ assert(!close(fsfd));
+
+ return 0;
+}
diff --git a/tools/testing/selftests/proc/proc-multiple-procfs.c b/tools/testing/selftests/proc/proc-multiple-procfs.c
new file mode 100644
index 000000000000..ab912ad95dab
--- /dev/null
+++ b/tools/testing/selftests/proc/proc-multiple-procfs.c
@@ -0,0 +1,48 @@
+/*
+ * Copyright © 2020 Alexey Gladkov <gladkov.alexey@gmail.com>
+ *
+ * Permission to use, copy, modify, and distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+#include <assert.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <sys/mount.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+
+int main(void)
+{
+ struct stat proc_st1, proc_st2;
+ char procbuff[] = "/tmp/proc.XXXXXX/meminfo";
+ char procdir1[] = "/tmp/proc.XXXXXX";
+ char procdir2[] = "/tmp/proc.XXXXXX";
+
+ assert(mkdtemp(procdir1) != NULL);
+ assert(mkdtemp(procdir2) != NULL);
+
+ assert(!mount("proc", procdir1, "proc", 0, "hidepid=1"));
+ assert(!mount("proc", procdir2, "proc", 0, "hidepid=2"));
+
+ snprintf(procbuff, sizeof(procbuff), "%s/meminfo", procdir1);
+ assert(!stat(procbuff, &proc_st1));
+
+ snprintf(procbuff, sizeof(procbuff), "%s/meminfo", procdir2);
+ assert(!stat(procbuff, &proc_st2));
+
+ umount(procdir1);
+ umount(procdir2);
+
+ assert(proc_st1.st_dev != proc_st2.st_dev);
+
+ return 0;
+}
diff --git a/tools/testing/selftests/pstore/.gitignore b/tools/testing/selftests/pstore/.gitignore
index 5a4a26e5464b..9938fb406389 100644
--- a/tools/testing/selftests/pstore/.gitignore
+++ b/tools/testing/selftests/pstore/.gitignore
@@ -1,2 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0-only
logs
*uuid
diff --git a/tools/testing/selftests/pstore/pstore_tests b/tools/testing/selftests/pstore/pstore_tests
index 1cef54458aff..2aa9a3852a84 100755
--- a/tools/testing/selftests/pstore/pstore_tests
+++ b/tools/testing/selftests/pstore/pstore_tests
@@ -10,7 +10,7 @@
. ./common_tests
prlog -n "Checking pstore console is registered ... "
-dmesg | grep -q "console \[pstore"
+dmesg | grep -Eq "console \[(pstore|${backend})"
show_result $?
prlog -n "Checking /dev/pmsg0 exists ... "
diff --git a/tools/testing/selftests/ptp/.gitignore b/tools/testing/selftests/ptp/.gitignore
index f562e49d6917..534ca26eee48 100644
--- a/tools/testing/selftests/ptp/.gitignore
+++ b/tools/testing/selftests/ptp/.gitignore
@@ -1 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
testptp
diff --git a/tools/testing/selftests/ptp/testptp.c b/tools/testing/selftests/ptp/testptp.c
index c0dd10257df5..da7a9dda9490 100644
--- a/tools/testing/selftests/ptp/testptp.c
+++ b/tools/testing/selftests/ptp/testptp.c
@@ -269,14 +269,16 @@ int main(int argc, char *argv[])
" %d programmable periodic signals\n"
" %d pulse per second\n"
" %d programmable pins\n"
- " %d cross timestamping\n",
+ " %d cross timestamping\n"
+ " %d adjust_phase\n",
caps.max_adj,
caps.n_alarm,
caps.n_ext_ts,
caps.n_per_out,
caps.pps,
caps.n_pins,
- caps.cross_timestamping);
+ caps.cross_timestamping,
+ caps.adjust_phase);
}
}
diff --git a/tools/testing/selftests/ptrace/.gitignore b/tools/testing/selftests/ptrace/.gitignore
index cfcc49a7def7..7bebf9534a86 100644
--- a/tools/testing/selftests/ptrace/.gitignore
+++ b/tools/testing/selftests/ptrace/.gitignore
@@ -1,2 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0-only
get_syscall_info
peeksiginfo
diff --git a/tools/testing/selftests/ptrace/Makefile b/tools/testing/selftests/ptrace/Makefile
index c0b7f89f0930..2f1f532c39db 100644
--- a/tools/testing/selftests/ptrace/Makefile
+++ b/tools/testing/selftests/ptrace/Makefile
@@ -1,6 +1,6 @@
# SPDX-License-Identifier: GPL-2.0-only
-CFLAGS += -iquote../../../../include/uapi -Wall
+CFLAGS += -std=c99 -pthread -iquote../../../../include/uapi -Wall
-TEST_GEN_PROGS := get_syscall_info peeksiginfo
+TEST_GEN_PROGS := get_syscall_info peeksiginfo vmaccess
include ../lib.mk
diff --git a/tools/testing/selftests/ptrace/vmaccess.c b/tools/testing/selftests/ptrace/vmaccess.c
new file mode 100644
index 000000000000..4db327b44586
--- /dev/null
+++ b/tools/testing/selftests/ptrace/vmaccess.c
@@ -0,0 +1,86 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright (c) 2020 Bernd Edlinger <bernd.edlinger@hotmail.de>
+ * All rights reserved.
+ *
+ * Check whether /proc/$pid/mem can be accessed without causing deadlocks
+ * when de_thread is blocked with ->cred_guard_mutex held.
+ */
+
+#include "../kselftest_harness.h"
+#include <stdio.h>
+#include <fcntl.h>
+#include <pthread.h>
+#include <signal.h>
+#include <unistd.h>
+#include <sys/ptrace.h>
+
+static void *thread(void *arg)
+{
+ ptrace(PTRACE_TRACEME, 0, 0L, 0L);
+ return NULL;
+}
+
+TEST(vmaccess)
+{
+ int f, pid = fork();
+ char mm[64];
+
+ if (!pid) {
+ pthread_t pt;
+
+ pthread_create(&pt, NULL, thread, NULL);
+ pthread_join(pt, NULL);
+ execlp("true", "true", NULL);
+ }
+
+ sleep(1);
+ sprintf(mm, "/proc/%d/mem", pid);
+ f = open(mm, O_RDONLY);
+ ASSERT_GE(f, 0);
+ close(f);
+ f = kill(pid, SIGCONT);
+ ASSERT_EQ(f, 0);
+}
+
+TEST(attach)
+{
+ int s, k, pid = fork();
+
+ if (!pid) {
+ pthread_t pt;
+
+ pthread_create(&pt, NULL, thread, NULL);
+ pthread_join(pt, NULL);
+ execlp("sleep", "sleep", "2", NULL);
+ }
+
+ sleep(1);
+ k = ptrace(PTRACE_ATTACH, pid, 0L, 0L);
+ ASSERT_EQ(errno, EAGAIN);
+ ASSERT_EQ(k, -1);
+ k = waitpid(-1, &s, WNOHANG);
+ ASSERT_NE(k, -1);
+ ASSERT_NE(k, 0);
+ ASSERT_NE(k, pid);
+ ASSERT_EQ(WIFEXITED(s), 1);
+ ASSERT_EQ(WEXITSTATUS(s), 0);
+ sleep(1);
+ k = ptrace(PTRACE_ATTACH, pid, 0L, 0L);
+ ASSERT_EQ(k, 0);
+ k = waitpid(-1, &s, 0);
+ ASSERT_EQ(k, pid);
+ ASSERT_EQ(WIFSTOPPED(s), 1);
+ ASSERT_EQ(WSTOPSIG(s), SIGSTOP);
+ k = ptrace(PTRACE_DETACH, pid, 0L, 0L);
+ ASSERT_EQ(k, 0);
+ k = waitpid(-1, &s, 0);
+ ASSERT_EQ(k, pid);
+ ASSERT_EQ(WIFEXITED(s), 1);
+ ASSERT_EQ(WEXITSTATUS(s), 0);
+ k = waitpid(-1, NULL, 0);
+ ASSERT_EQ(k, -1);
+ ASSERT_EQ(errno, ECHILD);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/rcutorture/.gitignore b/tools/testing/selftests/rcutorture/.gitignore
index ccc240275d1c..f6cbce77460b 100644
--- a/tools/testing/selftests/rcutorture/.gitignore
+++ b/tools/testing/selftests/rcutorture/.gitignore
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
initrd
b[0-9]*
res
diff --git a/tools/testing/selftests/rcutorture/bin/functions.sh b/tools/testing/selftests/rcutorture/bin/functions.sh
index c3a49fb4d6f6..12810229fddc 100644
--- a/tools/testing/selftests/rcutorture/bin/functions.sh
+++ b/tools/testing/selftests/rcutorture/bin/functions.sh
@@ -12,7 +12,7 @@
# Returns 1 if the specified boot-parameter string tells rcutorture to
# test CPU-hotplug operations.
bootparam_hotplug_cpu () {
- echo "$1" | grep -q "rcutorture\.onoff_"
+ echo "$1" | grep -q "torture\.onoff_"
}
# checkarg --argname argtype $# arg mustmatch cannotmatch
diff --git a/tools/testing/selftests/rcutorture/bin/kcsan-collapse.sh b/tools/testing/selftests/rcutorture/bin/kcsan-collapse.sh
new file mode 100755
index 000000000000..e5cc6b2f195e
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/bin/kcsan-collapse.sh
@@ -0,0 +1,22 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
+#
+# If this was a KCSAN run, collapse the reports in the various console.log
+# files onto pairs of functions.
+#
+# Usage: kcsan-collapse.sh resultsdir
+#
+# Copyright (C) 2020 Facebook, Inc.
+#
+# Authors: Paul E. McKenney <paulmck@kernel.org>
+
+if test -z "$TORTURE_KCONFIG_KCSAN_ARG"
+then
+ exit 0
+fi
+cat $1/*/console.log |
+ grep "BUG: KCSAN: " |
+ sed -e 's/^\[[^]]*] //' |
+ sort |
+ uniq -c |
+ sort -k1nr > $1/kcsan.sum
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh b/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh
index 1871d00bccd7..6f50722f251f 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh
@@ -20,7 +20,9 @@
rundir="${1}"
if test -z "$rundir" -o ! -d "$rundir"
then
+ echo Directory "$rundir" not found.
echo Usage: $0 directory
+ exit 1
fi
editor=${EDITOR-vi}
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh
index 9d9a41625dd9..1706cd4466b4 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh
@@ -41,7 +41,21 @@ else
title="$title ($ngpsps/s)"
fi
echo $title $stopstate $fwdprog
- nclosecalls=`grep --binary-files=text 'torture: Reader Batch' $i/console.log | tail -1 | awk '{for (i=NF-8;i<=NF;i++) sum+=$i; } END {print sum}'`
+ nclosecalls=`grep --binary-files=text 'torture: Reader Batch' $i/console.log | tail -1 | \
+ awk -v sum=0 '
+ {
+ for (i = 0; i <= NF; i++) {
+ sum += $i;
+ if ($i ~ /Batch:/) {
+ sum = 0;
+ i = i + 2;
+ }
+ }
+ }
+
+ END {
+ print sum
+ }'`
if test -z "$nclosecalls"
then
exit 0
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
index e5edd5198725..736f04749b90 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
@@ -13,6 +13,9 @@
#
# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
+T=/tmp/kvm-recheck.sh.$$
+trap 'rm -f $T' 0 2
+
PATH=`pwd`/tools/testing/selftests/rcutorture/bin:$PATH; export PATH
. functions.sh
for rd in "$@"
@@ -67,5 +70,26 @@ do
fi
fi
done
+ if test -f "$rd/kcsan.sum"
+ then
+ if test -s "$rd/kcsan.sum"
+ then
+ echo KCSAN summary in $rd/kcsan.sum
+ else
+ echo Clean KCSAN run in $rd
+ fi
+ fi
done
-EDITOR=echo kvm-find-errors.sh "${@: -1}" > /dev/null 2>&1
+EDITOR=echo kvm-find-errors.sh "${@: -1}" > $T 2>&1
+ret=$?
+builderrors="`tr ' ' '\012' < $T | grep -c '/Make.out.diags'`"
+if test "$builderrors" -gt 0
+then
+ echo $builderrors runs with build errors.
+fi
+runerrors="`tr ' ' '\012' < $T | grep -c '/console.log.diags'`"
+if test "$runerrors" -gt 0
+then
+ echo $runerrors runs with runtime errors.
+fi
+exit $ret
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
index e0352304b98b..6ff611c630d1 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
@@ -44,30 +44,32 @@ then
fi
echo ' ---' `date`: Starting build
echo ' ---' Kconfig fragment at: $config_template >> $resdir/log
-touch $resdir/ConfigFragment.input $resdir/ConfigFragment
-if test -r "$config_dir/CFcommon"
-then
- echo " --- $config_dir/CFcommon" >> $resdir/ConfigFragment.input
- cat < $config_dir/CFcommon >> $resdir/ConfigFragment.input
- config_override.sh $config_dir/CFcommon $config_template > $T/Kc1
- grep '#CHECK#' $config_dir/CFcommon >> $resdir/ConfigFragment
-else
- cp $config_template $T/Kc1
-fi
-echo " --- $config_template" >> $resdir/ConfigFragment.input
-cat $config_template >> $resdir/ConfigFragment.input
-grep '#CHECK#' $config_template >> $resdir/ConfigFragment
-if test -n "$TORTURE_KCONFIG_ARG"
-then
- echo $TORTURE_KCONFIG_ARG | tr -s " " "\012" > $T/cmdline
- echo " --- --kconfig argument" >> $resdir/ConfigFragment.input
- cat $T/cmdline >> $resdir/ConfigFragment.input
- config_override.sh $T/Kc1 $T/cmdline > $T/Kc2
- # Note that "#CHECK#" is not permitted on commandline.
-else
- cp $T/Kc1 $T/Kc2
-fi
-cat $T/Kc2 >> $resdir/ConfigFragment
+touch $resdir/ConfigFragment.input
+
+# Combine additional Kconfig options into an existing set such that
+# newer options win. The first argument is the Kconfig source ID, the
+# second the to-be-updated file within $T, and the third and final the
+# list of additional Kconfig options. Note that a $2.tmp file is
+# created when doing the update.
+config_override_param () {
+ if test -n "$3"
+ then
+ echo $3 | sed -e 's/^ *//' -e 's/ *$//' | tr -s " " "\012" > $T/Kconfig_args
+ echo " --- $1" >> $resdir/ConfigFragment.input
+ cat $T/Kconfig_args >> $resdir/ConfigFragment.input
+ config_override.sh $T/$2 $T/Kconfig_args > $T/$2.tmp
+ mv $T/$2.tmp $T/$2
+ # Note that "#CHECK#" is not permitted on commandline.
+ fi
+}
+
+echo > $T/KcList
+config_override_param "$config_dir/CFcommon" KcList "`cat $config_dir/CFcommon 2> /dev/null`"
+config_override_param "$config_template" KcList "`cat $config_template 2> /dev/null`"
+config_override_param "--kasan options" KcList "$TORTURE_KCONFIG_KASAN_ARG"
+config_override_param "--kcsan options" KcList "$TORTURE_KCONFIG_KCSAN_ARG"
+config_override_param "--kconfig argument" KcList "$TORTURE_KCONFIG_ARG"
+cp $T/KcList $resdir/ConfigFragment
base_resdir=`echo $resdir | sed -e 's/\.[0-9]\+$//'`
if test "$base_resdir" != "$resdir" -a -f $base_resdir/bzImage -a -f $base_resdir/vmlinux
@@ -80,7 +82,7 @@ then
ln -s $base_resdir/.config $resdir # for kvm-recheck.sh
# Arch-independent indicator
touch $resdir/builtkernel
-elif kvm-build.sh $T/Kc2 $resdir
+elif kvm-build.sh $T/KcList $resdir
then
# Had to build a kernel for this test.
QEMU="`identify_qemu vmlinux`"
diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh
index 78d18ab8e954..c279cf9cb010 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm.sh
@@ -31,6 +31,8 @@ TORTURE_DEFCONFIG=defconfig
TORTURE_BOOT_IMAGE=""
TORTURE_INITRD="$KVM/initrd"; export TORTURE_INITRD
TORTURE_KCONFIG_ARG=""
+TORTURE_KCONFIG_KASAN_ARG=""
+TORTURE_KCONFIG_KCSAN_ARG=""
TORTURE_KMAKE_ARG=""
TORTURE_QEMU_MEM=512
TORTURE_SHUTDOWN_GRACE=180
@@ -39,7 +41,7 @@ TORTURE_TRUST_MAKE=""
resdir=""
configs=""
cpus=0
-ds=`date +%Y.%m.%d-%H:%M:%S`
+ds=`date +%Y.%m.%d-%H.%M.%S`
jitter="-1"
usage () {
@@ -133,6 +135,12 @@ do
TORTURE_KCONFIG_ARG="$2"
shift
;;
+ --kasan)
+ TORTURE_KCONFIG_KASAN_ARG="CONFIG_DEBUG_INFO=y CONFIG_KASAN=y"; export TORTURE_KCONFIG_KASAN_ARG
+ ;;
+ --kcsan)
+ TORTURE_KCONFIG_KCSAN_ARG="CONFIG_DEBUG_INFO=y CONFIG_KCSAN=y CONFIG_KCSAN_ASSUME_PLAIN_WRITES_ATOMIC=n CONFIG_KCSAN_REPORT_VALUE_CHANGE_ONLY=n CONFIG_KCSAN_REPORT_ONCE_IN_MS=100000 CONFIG_KCSAN_VERBOSE=y CONFIG_KCSAN_INTERRUPT_WATCHER=y"; export TORTURE_KCONFIG_KCSAN_ARG
+ ;;
--kmake-arg)
checkarg --kmake-arg "(kernel make arguments)" $# "$2" '.*' '^error$'
TORTURE_KMAKE_ARG="$2"
@@ -310,6 +318,8 @@ TORTURE_BUILDONLY="$TORTURE_BUILDONLY"; export TORTURE_BUILDONLY
TORTURE_DEFCONFIG="$TORTURE_DEFCONFIG"; export TORTURE_DEFCONFIG
TORTURE_INITRD="$TORTURE_INITRD"; export TORTURE_INITRD
TORTURE_KCONFIG_ARG="$TORTURE_KCONFIG_ARG"; export TORTURE_KCONFIG_ARG
+TORTURE_KCONFIG_KASAN_ARG="$TORTURE_KCONFIG_KASAN_ARG"; export TORTURE_KCONFIG_KASAN_ARG
+TORTURE_KCONFIG_KCSAN_ARG="$TORTURE_KCONFIG_KCSAN_ARG"; export TORTURE_KCONFIG_KCSAN_ARG
TORTURE_KMAKE_ARG="$TORTURE_KMAKE_ARG"; export TORTURE_KMAKE_ARG
TORTURE_QEMU_CMD="$TORTURE_QEMU_CMD"; export TORTURE_QEMU_CMD
TORTURE_QEMU_INTERACTIVE="$TORTURE_QEMU_INTERACTIVE"; export TORTURE_QEMU_INTERACTIVE
@@ -464,6 +474,7 @@ echo
echo
echo " --- `date` Test summary:"
echo Results directory: $resdir/$ds
+kcsan-collapse.sh $resdir/$ds
kvm-recheck.sh $resdir/$ds
___EOF___
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/CFLIST b/tools/testing/selftests/rcutorture/configs/rcu/CFLIST
index c3c1fb5a9e1f..f2b20db9e296 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/CFLIST
+++ b/tools/testing/selftests/rcutorture/configs/rcu/CFLIST
@@ -14,3 +14,6 @@ TINY02
TASKS01
TASKS02
TASKS03
+RUDE01
+TRACE01
+TRACE02
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/CFcommon b/tools/testing/selftests/rcutorture/configs/rcu/CFcommon
index e19a444a0684..0e92d85313aa 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/CFcommon
+++ b/tools/testing/selftests/rcutorture/configs/rcu/CFcommon
@@ -3,3 +3,5 @@ CONFIG_PRINTK_TIME=y
CONFIG_HYPERVISOR_GUEST=y
CONFIG_PARAVIRT=y
CONFIG_KVM_GUEST=y
+CONFIG_KCSAN_ASSUME_PLAIN_WRITES_ATOMIC=n
+CONFIG_KCSAN_REPORT_VALUE_CHANGE_ONLY=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/RUDE01 b/tools/testing/selftests/rcutorture/configs/rcu/RUDE01
new file mode 100644
index 000000000000..bafe94cbd739
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/rcu/RUDE01
@@ -0,0 +1,10 @@
+CONFIG_SMP=y
+CONFIG_NR_CPUS=2
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+CONFIG_DEBUG_LOCK_ALLOC=y
+CONFIG_PROVE_LOCKING=y
+#CHECK#CONFIG_PROVE_RCU=y
+CONFIG_RCU_EXPERT=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/RUDE01.boot b/tools/testing/selftests/rcutorture/configs/rcu/RUDE01.boot
new file mode 100644
index 000000000000..9363708c9075
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/rcu/RUDE01.boot
@@ -0,0 +1 @@
+rcutorture.torture_type=tasks-rude
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TRACE01 b/tools/testing/selftests/rcutorture/configs/rcu/TRACE01
new file mode 100644
index 000000000000..12e7661b86f5
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TRACE01
@@ -0,0 +1,11 @@
+CONFIG_SMP=y
+CONFIG_NR_CPUS=4
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+CONFIG_DEBUG_LOCK_ALLOC=y
+CONFIG_PROVE_LOCKING=y
+#CHECK#CONFIG_PROVE_RCU=y
+CONFIG_TASKS_TRACE_RCU_READ_MB=y
+CONFIG_RCU_EXPERT=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TRACE01.boot b/tools/testing/selftests/rcutorture/configs/rcu/TRACE01.boot
new file mode 100644
index 000000000000..9675ad632dcc
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TRACE01.boot
@@ -0,0 +1 @@
+rcutorture.torture_type=tasks-tracing
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TRACE02 b/tools/testing/selftests/rcutorture/configs/rcu/TRACE02
new file mode 100644
index 000000000000..b69ed6673c41
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TRACE02
@@ -0,0 +1,11 @@
+CONFIG_SMP=y
+CONFIG_NR_CPUS=4
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+CONFIG_DEBUG_LOCK_ALLOC=n
+CONFIG_PROVE_LOCKING=n
+#CHECK#CONFIG_PROVE_RCU=n
+CONFIG_TASKS_TRACE_RCU_READ_MB=n
+CONFIG_RCU_EXPERT=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TRACE02.boot b/tools/testing/selftests/rcutorture/configs/rcu/TRACE02.boot
new file mode 100644
index 000000000000..9675ad632dcc
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TRACE02.boot
@@ -0,0 +1 @@
+rcutorture.torture_type=tasks-tracing
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE10 b/tools/testing/selftests/rcutorture/configs/rcu/TREE10
new file mode 100644
index 000000000000..7311f84a5876
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE10
@@ -0,0 +1,18 @@
+CONFIG_SMP=y
+CONFIG_NR_CPUS=56
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_HZ_PERIODIC=n
+CONFIG_NO_HZ_IDLE=y
+CONFIG_NO_HZ_FULL=n
+CONFIG_RCU_FAST_NO_HZ=n
+CONFIG_RCU_TRACE=n
+CONFIG_RCU_NOCB_CPU=n
+CONFIG_DEBUG_LOCK_ALLOC=n
+CONFIG_PROVE_LOCKING=n
+#CHECK#CONFIG_PROVE_RCU=n
+CONFIG_DEBUG_OBJECTS=n
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
+CONFIG_RCU_EXPERT=n
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/.gitignore b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/.gitignore
index 712a3d41a325..24e27957efcc 100644
--- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/.gitignore
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/.gitignore
@@ -1 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
srcu.c
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/.gitignore b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/.gitignore
index 1d016e66980a..57d296341304 100644
--- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/.gitignore
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/.gitignore
@@ -1 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
srcu.h
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/.gitignore b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/.gitignore
index f47cb2045f13..d65462d64816 100644
--- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/.gitignore
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/.gitignore
@@ -1 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
*.out
diff --git a/tools/testing/selftests/resctrl/Makefile b/tools/testing/selftests/resctrl/Makefile
new file mode 100644
index 000000000000..d585cc1948cc
--- /dev/null
+++ b/tools/testing/selftests/resctrl/Makefile
@@ -0,0 +1,17 @@
+CC = $(CROSS_COMPILE)gcc
+CFLAGS = -g -Wall
+SRCS=$(wildcard *.c)
+OBJS=$(SRCS:.c=.o)
+
+all: resctrl_tests
+
+$(OBJS): $(SRCS)
+ $(CC) $(CFLAGS) -c $(SRCS)
+
+resctrl_tests: $(OBJS)
+ $(CC) $(CFLAGS) -o $@ $^
+
+.PHONY: clean
+
+clean:
+ $(RM) $(OBJS) resctrl_tests
diff --git a/tools/testing/selftests/resctrl/README b/tools/testing/selftests/resctrl/README
new file mode 100644
index 000000000000..6e5a0ffa18e8
--- /dev/null
+++ b/tools/testing/selftests/resctrl/README
@@ -0,0 +1,53 @@
+resctrl_tests - resctrl file system test suit
+
+Authors:
+ Fenghua Yu <fenghua.yu@intel.com>
+ Sai Praneeth Prakhya <sai.praneeth.prakhya@intel.com>,
+
+resctrl_tests tests various resctrl functionalities and interfaces including
+both software and hardware.
+
+Currently it supports Memory Bandwidth Monitoring test and Memory Bandwidth
+Allocation test on Intel RDT hardware. More tests will be added in the future.
+And the test suit can be extended to cover AMD QoS and ARM MPAM hardware
+as well.
+
+BUILD
+-----
+
+Run "make" to build executable file "resctrl_tests".
+
+RUN
+---
+
+To use resctrl_tests, root or sudoer privileges are required. This is because
+the test needs to mount resctrl file system and change contents in the file
+system.
+
+Executing the test without any parameter will run all supported tests:
+
+ sudo ./resctrl_tests
+
+OVERVIEW OF EXECUTION
+---------------------
+
+A test case has four stages:
+
+ - setup: mount resctrl file system, create group, setup schemata, move test
+ process pids to tasks, start benchmark.
+ - execute: let benchmark run
+ - verify: get resctrl data and verify the data with another source, e.g.
+ perf event.
+ - teardown: umount resctrl and clear temporary files.
+
+ARGUMENTS
+---------
+
+Parameter '-h' shows usage information.
+
+usage: resctrl_tests [-h] [-b "benchmark_cmd [options]"] [-t test list] [-n no_of_bits]
+ -b benchmark_cmd [options]: run specified benchmark for MBM, MBA and CQM default benchmark is builtin fill_buf
+ -t test list: run tests specified in the test list, e.g. -t mbm, mba, cqm, cat
+ -n no_of_bits: run cache tests using specified no of bits in cache bit mask
+ -p cpu_no: specify CPU number to run the test. 1 is default
+ -h: help
diff --git a/tools/testing/selftests/resctrl/cache.c b/tools/testing/selftests/resctrl/cache.c
new file mode 100644
index 000000000000..38dbf4962e33
--- /dev/null
+++ b/tools/testing/selftests/resctrl/cache.c
@@ -0,0 +1,272 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <stdint.h>
+#include "resctrl.h"
+
+struct read_format {
+ __u64 nr; /* The number of events */
+ struct {
+ __u64 value; /* The value of the event */
+ } values[2];
+};
+
+static struct perf_event_attr pea_llc_miss;
+static struct read_format rf_cqm;
+static int fd_lm;
+char llc_occup_path[1024];
+
+static void initialize_perf_event_attr(void)
+{
+ pea_llc_miss.type = PERF_TYPE_HARDWARE;
+ pea_llc_miss.size = sizeof(struct perf_event_attr);
+ pea_llc_miss.read_format = PERF_FORMAT_GROUP;
+ pea_llc_miss.exclude_kernel = 1;
+ pea_llc_miss.exclude_hv = 1;
+ pea_llc_miss.exclude_idle = 1;
+ pea_llc_miss.exclude_callchain_kernel = 1;
+ pea_llc_miss.inherit = 1;
+ pea_llc_miss.exclude_guest = 1;
+ pea_llc_miss.disabled = 1;
+}
+
+static void ioctl_perf_event_ioc_reset_enable(void)
+{
+ ioctl(fd_lm, PERF_EVENT_IOC_RESET, 0);
+ ioctl(fd_lm, PERF_EVENT_IOC_ENABLE, 0);
+}
+
+static int perf_event_open_llc_miss(pid_t pid, int cpu_no)
+{
+ fd_lm = perf_event_open(&pea_llc_miss, pid, cpu_no, -1,
+ PERF_FLAG_FD_CLOEXEC);
+ if (fd_lm == -1) {
+ perror("Error opening leader");
+ ctrlc_handler(0, NULL, NULL);
+ return -1;
+ }
+
+ return 0;
+}
+
+static int initialize_llc_perf(void)
+{
+ memset(&pea_llc_miss, 0, sizeof(struct perf_event_attr));
+ memset(&rf_cqm, 0, sizeof(struct read_format));
+
+ /* Initialize perf_event_attr structures for HW_CACHE_MISSES */
+ initialize_perf_event_attr();
+
+ pea_llc_miss.config = PERF_COUNT_HW_CACHE_MISSES;
+
+ rf_cqm.nr = 1;
+
+ return 0;
+}
+
+static int reset_enable_llc_perf(pid_t pid, int cpu_no)
+{
+ int ret = 0;
+
+ ret = perf_event_open_llc_miss(pid, cpu_no);
+ if (ret < 0)
+ return ret;
+
+ /* Start counters to log values */
+ ioctl_perf_event_ioc_reset_enable();
+
+ return 0;
+}
+
+/*
+ * get_llc_perf: llc cache miss through perf events
+ * @cpu_no: CPU number that the benchmark PID is binded to
+ *
+ * Perf events like HW_CACHE_MISSES could be used to validate number of
+ * cache lines allocated.
+ *
+ * Return: =0 on success. <0 on failure.
+ */
+static int get_llc_perf(unsigned long *llc_perf_miss)
+{
+ __u64 total_misses;
+
+ /* Stop counters after one span to get miss rate */
+
+ ioctl(fd_lm, PERF_EVENT_IOC_DISABLE, 0);
+
+ if (read(fd_lm, &rf_cqm, sizeof(struct read_format)) == -1) {
+ perror("Could not get llc misses through perf");
+
+ return -1;
+ }
+
+ total_misses = rf_cqm.values[0].value;
+
+ close(fd_lm);
+
+ *llc_perf_miss = total_misses;
+
+ return 0;
+}
+
+/*
+ * Get LLC Occupancy as reported by RESCTRL FS
+ * For CQM,
+ * 1. If con_mon grp and mon grp given, then read from mon grp in
+ * con_mon grp
+ * 2. If only con_mon grp given, then read from con_mon grp
+ * 3. If both not given, then read from root con_mon grp
+ * For CAT,
+ * 1. If con_mon grp given, then read from it
+ * 2. If con_mon grp not given, then read from root con_mon grp
+ *
+ * Return: =0 on success. <0 on failure.
+ */
+static int get_llc_occu_resctrl(unsigned long *llc_occupancy)
+{
+ FILE *fp;
+
+ fp = fopen(llc_occup_path, "r");
+ if (!fp) {
+ perror("Failed to open results file");
+
+ return errno;
+ }
+ if (fscanf(fp, "%lu", llc_occupancy) <= 0) {
+ perror("Could not get llc occupancy");
+ fclose(fp);
+
+ return -1;
+ }
+ fclose(fp);
+
+ return 0;
+}
+
+/*
+ * print_results_cache: the cache results are stored in a file
+ * @filename: file that stores the results
+ * @bm_pid: child pid that runs benchmark
+ * @llc_value: perf miss value /
+ * llc occupancy value reported by resctrl FS
+ *
+ * Return: 0 on success. non-zero on failure.
+ */
+static int print_results_cache(char *filename, int bm_pid,
+ unsigned long llc_value)
+{
+ FILE *fp;
+
+ if (strcmp(filename, "stdio") == 0 || strcmp(filename, "stderr") == 0) {
+ printf("Pid: %d \t LLC_value: %lu\n", bm_pid,
+ llc_value);
+ } else {
+ fp = fopen(filename, "a");
+ if (!fp) {
+ perror("Cannot open results file");
+
+ return errno;
+ }
+ fprintf(fp, "Pid: %d \t llc_value: %lu\n", bm_pid, llc_value);
+ fclose(fp);
+ }
+
+ return 0;
+}
+
+int measure_cache_vals(struct resctrl_val_param *param, int bm_pid)
+{
+ unsigned long llc_perf_miss = 0, llc_occu_resc = 0, llc_value = 0;
+ int ret;
+
+ /*
+ * Measure cache miss from perf.
+ */
+ if (!strcmp(param->resctrl_val, "cat")) {
+ ret = get_llc_perf(&llc_perf_miss);
+ if (ret < 0)
+ return ret;
+ llc_value = llc_perf_miss;
+ }
+
+ /*
+ * Measure llc occupancy from resctrl.
+ */
+ if (!strcmp(param->resctrl_val, "cqm")) {
+ ret = get_llc_occu_resctrl(&llc_occu_resc);
+ if (ret < 0)
+ return ret;
+ llc_value = llc_occu_resc;
+ }
+ ret = print_results_cache(param->filename, bm_pid, llc_value);
+ if (ret)
+ return ret;
+
+ return 0;
+}
+
+/*
+ * cache_val: execute benchmark and measure LLC occupancy resctrl
+ * and perf cache miss for the benchmark
+ * @param: parameters passed to cache_val()
+ *
+ * Return: 0 on success. non-zero on failure.
+ */
+int cat_val(struct resctrl_val_param *param)
+{
+ int malloc_and_init_memory = 1, memflush = 1, operation = 0, ret = 0;
+ char *resctrl_val = param->resctrl_val;
+ pid_t bm_pid;
+
+ if (strcmp(param->filename, "") == 0)
+ sprintf(param->filename, "stdio");
+
+ bm_pid = getpid();
+
+ /* Taskset benchmark to specified cpu */
+ ret = taskset_benchmark(bm_pid, param->cpu_no);
+ if (ret)
+ return ret;
+
+ /* Write benchmark to specified con_mon grp, mon_grp in resctrl FS*/
+ ret = write_bm_pid_to_resctrl(bm_pid, param->ctrlgrp, param->mongrp,
+ resctrl_val);
+ if (ret)
+ return ret;
+
+ if ((strcmp(resctrl_val, "cat") == 0)) {
+ ret = initialize_llc_perf();
+ if (ret)
+ return ret;
+ }
+
+ /* Test runs until the callback setup() tells the test to stop. */
+ while (1) {
+ if (strcmp(resctrl_val, "cat") == 0) {
+ ret = param->setup(1, param);
+ if (ret) {
+ ret = 0;
+ break;
+ }
+ ret = reset_enable_llc_perf(bm_pid, param->cpu_no);
+ if (ret)
+ break;
+
+ if (run_fill_buf(param->span, malloc_and_init_memory,
+ memflush, operation, resctrl_val)) {
+ fprintf(stderr, "Error-running fill buffer\n");
+ ret = -1;
+ break;
+ }
+
+ sleep(1);
+ ret = measure_cache_vals(param, bm_pid);
+ if (ret)
+ break;
+ } else {
+ break;
+ }
+ }
+
+ return ret;
+}
diff --git a/tools/testing/selftests/resctrl/cat_test.c b/tools/testing/selftests/resctrl/cat_test.c
new file mode 100644
index 000000000000..5da43767b973
--- /dev/null
+++ b/tools/testing/selftests/resctrl/cat_test.c
@@ -0,0 +1,250 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Cache Allocation Technology (CAT) test
+ *
+ * Copyright (C) 2018 Intel Corporation
+ *
+ * Authors:
+ * Sai Praneeth Prakhya <sai.praneeth.prakhya@intel.com>,
+ * Fenghua Yu <fenghua.yu@intel.com>
+ */
+#include "resctrl.h"
+#include <unistd.h>
+
+#define RESULT_FILE_NAME1 "result_cat1"
+#define RESULT_FILE_NAME2 "result_cat2"
+#define NUM_OF_RUNS 5
+#define MAX_DIFF_PERCENT 4
+#define MAX_DIFF 1000000
+
+int count_of_bits;
+char cbm_mask[256];
+unsigned long long_mask;
+unsigned long cache_size;
+
+/*
+ * Change schemata. Write schemata to specified
+ * con_mon grp, mon_grp in resctrl FS.
+ * Run 5 times in order to get average values.
+ */
+static int cat_setup(int num, ...)
+{
+ struct resctrl_val_param *p;
+ char schemata[64];
+ va_list param;
+ int ret = 0;
+
+ va_start(param, num);
+ p = va_arg(param, struct resctrl_val_param *);
+ va_end(param);
+
+ /* Run NUM_OF_RUNS times */
+ if (p->num_of_runs >= NUM_OF_RUNS)
+ return -1;
+
+ if (p->num_of_runs == 0) {
+ sprintf(schemata, "%lx", p->mask);
+ ret = write_schemata(p->ctrlgrp, schemata, p->cpu_no,
+ p->resctrl_val);
+ }
+ p->num_of_runs++;
+
+ return ret;
+}
+
+static void show_cache_info(unsigned long sum_llc_perf_miss, int no_of_bits,
+ unsigned long span)
+{
+ unsigned long allocated_cache_lines = span / 64;
+ unsigned long avg_llc_perf_miss = 0;
+ float diff_percent;
+
+ avg_llc_perf_miss = sum_llc_perf_miss / (NUM_OF_RUNS - 1);
+ diff_percent = ((float)allocated_cache_lines - avg_llc_perf_miss) /
+ allocated_cache_lines * 100;
+
+ printf("%sok CAT: cache miss rate within %d%%\n",
+ !is_amd && abs((int)diff_percent) > MAX_DIFF_PERCENT ?
+ "not " : "", MAX_DIFF_PERCENT);
+ tests_run++;
+ printf("# Percent diff=%d\n", abs((int)diff_percent));
+ printf("# Number of bits: %d\n", no_of_bits);
+ printf("# Avg_llc_perf_miss: %lu\n", avg_llc_perf_miss);
+ printf("# Allocated cache lines: %lu\n", allocated_cache_lines);
+}
+
+static int check_results(struct resctrl_val_param *param)
+{
+ char *token_array[8], temp[512];
+ unsigned long sum_llc_perf_miss = 0;
+ int runs = 0, no_of_bits = 0;
+ FILE *fp;
+
+ printf("# Checking for pass/fail\n");
+ fp = fopen(param->filename, "r");
+ if (!fp) {
+ perror("# Cannot open file");
+
+ return errno;
+ }
+
+ while (fgets(temp, sizeof(temp), fp)) {
+ char *token = strtok(temp, ":\t");
+ int fields = 0;
+
+ while (token) {
+ token_array[fields++] = token;
+ token = strtok(NULL, ":\t");
+ }
+ /*
+ * Discard the first value which is inaccurate due to monitoring
+ * setup transition phase.
+ */
+ if (runs > 0)
+ sum_llc_perf_miss += strtoul(token_array[3], NULL, 0);
+ runs++;
+ }
+
+ fclose(fp);
+ no_of_bits = count_bits(param->mask);
+
+ show_cache_info(sum_llc_perf_miss, no_of_bits, param->span);
+
+ return 0;
+}
+
+void cat_test_cleanup(void)
+{
+ remove(RESULT_FILE_NAME1);
+ remove(RESULT_FILE_NAME2);
+}
+
+int cat_perf_miss_val(int cpu_no, int n, char *cache_type)
+{
+ unsigned long l_mask, l_mask_1;
+ int ret, pipefd[2], sibling_cpu_no;
+ char pipe_message;
+ pid_t bm_pid;
+
+ cache_size = 0;
+
+ ret = remount_resctrlfs(true);
+ if (ret)
+ return ret;
+
+ if (!validate_resctrl_feature_request("cat"))
+ return -1;
+
+ /* Get default cbm mask for L3/L2 cache */
+ ret = get_cbm_mask(cache_type);
+ if (ret)
+ return ret;
+
+ long_mask = strtoul(cbm_mask, NULL, 16);
+
+ /* Get L3/L2 cache size */
+ ret = get_cache_size(cpu_no, cache_type, &cache_size);
+ if (ret)
+ return ret;
+ printf("cache size :%lu\n", cache_size);
+
+ /* Get max number of bits from default-cabm mask */
+ count_of_bits = count_bits(long_mask);
+
+ if (n < 1 || n > count_of_bits - 1) {
+ printf("Invalid input value for no_of_bits n!\n");
+ printf("Please Enter value in range 1 to %d\n",
+ count_of_bits - 1);
+ return -1;
+ }
+
+ /* Get core id from same socket for running another thread */
+ sibling_cpu_no = get_core_sibling(cpu_no);
+ if (sibling_cpu_no < 0)
+ return -1;
+
+ struct resctrl_val_param param = {
+ .resctrl_val = "cat",
+ .cpu_no = cpu_no,
+ .mum_resctrlfs = 0,
+ .setup = cat_setup,
+ };
+
+ l_mask = long_mask >> n;
+ l_mask_1 = ~l_mask & long_mask;
+
+ /* Set param values for parent thread which will be allocated bitmask
+ * with (max_bits - n) bits
+ */
+ param.span = cache_size * (count_of_bits - n) / count_of_bits;
+ strcpy(param.ctrlgrp, "c2");
+ strcpy(param.mongrp, "m2");
+ strcpy(param.filename, RESULT_FILE_NAME2);
+ param.mask = l_mask;
+ param.num_of_runs = 0;
+
+ if (pipe(pipefd)) {
+ perror("# Unable to create pipe");
+ return errno;
+ }
+
+ bm_pid = fork();
+
+ /* Set param values for child thread which will be allocated bitmask
+ * with n bits
+ */
+ if (bm_pid == 0) {
+ param.mask = l_mask_1;
+ strcpy(param.ctrlgrp, "c1");
+ strcpy(param.mongrp, "m1");
+ param.span = cache_size * n / count_of_bits;
+ strcpy(param.filename, RESULT_FILE_NAME1);
+ param.num_of_runs = 0;
+ param.cpu_no = sibling_cpu_no;
+ }
+
+ remove(param.filename);
+
+ ret = cat_val(&param);
+ if (ret)
+ return ret;
+
+ ret = check_results(&param);
+ if (ret)
+ return ret;
+
+ if (bm_pid == 0) {
+ /* Tell parent that child is ready */
+ close(pipefd[0]);
+ pipe_message = 1;
+ if (write(pipefd[1], &pipe_message, sizeof(pipe_message)) <
+ sizeof(pipe_message)) {
+ close(pipefd[1]);
+ perror("# failed signaling parent process");
+ return errno;
+ }
+
+ close(pipefd[1]);
+ while (1)
+ ;
+ } else {
+ /* Parent waits for child to be ready. */
+ close(pipefd[1]);
+ pipe_message = 0;
+ while (pipe_message != 1) {
+ if (read(pipefd[0], &pipe_message,
+ sizeof(pipe_message)) < sizeof(pipe_message)) {
+ perror("# failed reading from child process");
+ break;
+ }
+ }
+ close(pipefd[0]);
+ kill(bm_pid, SIGKILL);
+ }
+
+ cat_test_cleanup();
+ if (bm_pid)
+ umount_resctrlfs();
+
+ return 0;
+}
diff --git a/tools/testing/selftests/resctrl/cqm_test.c b/tools/testing/selftests/resctrl/cqm_test.c
new file mode 100644
index 000000000000..c8756152bd61
--- /dev/null
+++ b/tools/testing/selftests/resctrl/cqm_test.c
@@ -0,0 +1,176 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Cache Monitoring Technology (CQM) test
+ *
+ * Copyright (C) 2018 Intel Corporation
+ *
+ * Authors:
+ * Sai Praneeth Prakhya <sai.praneeth.prakhya@intel.com>,
+ * Fenghua Yu <fenghua.yu@intel.com>
+ */
+#include "resctrl.h"
+#include <unistd.h>
+
+#define RESULT_FILE_NAME "result_cqm"
+#define NUM_OF_RUNS 5
+#define MAX_DIFF 2000000
+#define MAX_DIFF_PERCENT 15
+
+int count_of_bits;
+char cbm_mask[256];
+unsigned long long_mask;
+unsigned long cache_size;
+
+static int cqm_setup(int num, ...)
+{
+ struct resctrl_val_param *p;
+ va_list param;
+
+ va_start(param, num);
+ p = va_arg(param, struct resctrl_val_param *);
+ va_end(param);
+
+ /* Run NUM_OF_RUNS times */
+ if (p->num_of_runs >= NUM_OF_RUNS)
+ return -1;
+
+ p->num_of_runs++;
+
+ return 0;
+}
+
+static void show_cache_info(unsigned long sum_llc_occu_resc, int no_of_bits,
+ unsigned long span)
+{
+ unsigned long avg_llc_occu_resc = 0;
+ float diff_percent;
+ long avg_diff = 0;
+ bool res;
+
+ avg_llc_occu_resc = sum_llc_occu_resc / (NUM_OF_RUNS - 1);
+ avg_diff = (long)abs(span - avg_llc_occu_resc);
+
+ diff_percent = (((float)span - avg_llc_occu_resc) / span) * 100;
+
+ if ((abs((int)diff_percent) <= MAX_DIFF_PERCENT) ||
+ (abs(avg_diff) <= MAX_DIFF))
+ res = true;
+ else
+ res = false;
+
+ printf("%sok CQM: diff within %d, %d\%%\n", res ? "" : "not",
+ MAX_DIFF, (int)MAX_DIFF_PERCENT);
+
+ printf("# diff: %ld\n", avg_diff);
+ printf("# percent diff=%d\n", abs((int)diff_percent));
+ printf("# Results are displayed in (Bytes)\n");
+ printf("# Number of bits: %d\n", no_of_bits);
+ printf("# Avg_llc_occu_resc: %lu\n", avg_llc_occu_resc);
+ printf("# llc_occu_exp (span): %lu\n", span);
+
+ tests_run++;
+}
+
+static int check_results(struct resctrl_val_param *param, int no_of_bits)
+{
+ char *token_array[8], temp[512];
+ unsigned long sum_llc_occu_resc = 0;
+ int runs = 0;
+ FILE *fp;
+
+ printf("# checking for pass/fail\n");
+ fp = fopen(param->filename, "r");
+ if (!fp) {
+ perror("# Error in opening file\n");
+
+ return errno;
+ }
+
+ while (fgets(temp, 1024, fp)) {
+ char *token = strtok(temp, ":\t");
+ int fields = 0;
+
+ while (token) {
+ token_array[fields++] = token;
+ token = strtok(NULL, ":\t");
+ }
+
+ /* Field 3 is llc occ resc value */
+ if (runs > 0)
+ sum_llc_occu_resc += strtoul(token_array[3], NULL, 0);
+ runs++;
+ }
+ fclose(fp);
+ show_cache_info(sum_llc_occu_resc, no_of_bits, param->span);
+
+ return 0;
+}
+
+void cqm_test_cleanup(void)
+{
+ remove(RESULT_FILE_NAME);
+}
+
+int cqm_resctrl_val(int cpu_no, int n, char **benchmark_cmd)
+{
+ int ret, mum_resctrlfs;
+
+ cache_size = 0;
+ mum_resctrlfs = 1;
+
+ ret = remount_resctrlfs(mum_resctrlfs);
+ if (ret)
+ return ret;
+
+ if (!validate_resctrl_feature_request("cqm"))
+ return -1;
+
+ ret = get_cbm_mask("L3");
+ if (ret)
+ return ret;
+
+ long_mask = strtoul(cbm_mask, NULL, 16);
+
+ ret = get_cache_size(cpu_no, "L3", &cache_size);
+ if (ret)
+ return ret;
+ printf("cache size :%lu\n", cache_size);
+
+ count_of_bits = count_bits(long_mask);
+
+ if (n < 1 || n > count_of_bits) {
+ printf("Invalid input value for numbr_of_bits n!\n");
+ printf("Please Enter value in range 1 to %d\n", count_of_bits);
+ return -1;
+ }
+
+ struct resctrl_val_param param = {
+ .resctrl_val = "cqm",
+ .ctrlgrp = "c1",
+ .mongrp = "m1",
+ .cpu_no = cpu_no,
+ .mum_resctrlfs = 0,
+ .filename = RESULT_FILE_NAME,
+ .mask = ~(long_mask << n) & long_mask,
+ .span = cache_size * n / count_of_bits,
+ .num_of_runs = 0,
+ .setup = cqm_setup,
+ };
+
+ if (strcmp(benchmark_cmd[0], "fill_buf") == 0)
+ sprintf(benchmark_cmd[1], "%lu", param.span);
+
+ remove(RESULT_FILE_NAME);
+
+ ret = resctrl_val(benchmark_cmd, &param);
+ if (ret)
+ return ret;
+
+ ret = check_results(&param, n);
+ if (ret)
+ return ret;
+
+ cqm_test_cleanup();
+
+ return 0;
+}
diff --git a/tools/testing/selftests/resctrl/fill_buf.c b/tools/testing/selftests/resctrl/fill_buf.c
new file mode 100644
index 000000000000..79c611c99a3d
--- /dev/null
+++ b/tools/testing/selftests/resctrl/fill_buf.c
@@ -0,0 +1,213 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * fill_buf benchmark
+ *
+ * Copyright (C) 2018 Intel Corporation
+ *
+ * Authors:
+ * Sai Praneeth Prakhya <sai.praneeth.prakhya@intel.com>,
+ * Fenghua Yu <fenghua.yu@intel.com>
+ */
+#include <stdio.h>
+#include <unistd.h>
+#include <stdlib.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <inttypes.h>
+#include <malloc.h>
+#include <string.h>
+
+#include "resctrl.h"
+
+#define CL_SIZE (64)
+#define PAGE_SIZE (4 * 1024)
+#define MB (1024 * 1024)
+
+static unsigned char *startptr;
+
+static void sb(void)
+{
+#if defined(__i386) || defined(__x86_64)
+ asm volatile("sfence\n\t"
+ : : : "memory");
+#endif
+}
+
+static void ctrl_handler(int signo)
+{
+ free(startptr);
+ printf("\nEnding\n");
+ sb();
+ exit(EXIT_SUCCESS);
+}
+
+static void cl_flush(void *p)
+{
+#if defined(__i386) || defined(__x86_64)
+ asm volatile("clflush (%0)\n\t"
+ : : "r"(p) : "memory");
+#endif
+}
+
+static void mem_flush(void *p, size_t s)
+{
+ char *cp = (char *)p;
+ size_t i = 0;
+
+ s = s / CL_SIZE; /* mem size in cache llines */
+
+ for (i = 0; i < s; i++)
+ cl_flush(&cp[i * CL_SIZE]);
+
+ sb();
+}
+
+static void *malloc_and_init_memory(size_t s)
+{
+ uint64_t *p64;
+ size_t s64;
+
+ void *p = memalign(PAGE_SIZE, s);
+
+ p64 = (uint64_t *)p;
+ s64 = s / sizeof(uint64_t);
+
+ while (s64 > 0) {
+ *p64 = (uint64_t)rand();
+ p64 += (CL_SIZE / sizeof(uint64_t));
+ s64 -= (CL_SIZE / sizeof(uint64_t));
+ }
+
+ return p;
+}
+
+static int fill_one_span_read(unsigned char *start_ptr, unsigned char *end_ptr)
+{
+ unsigned char sum, *p;
+
+ sum = 0;
+ p = start_ptr;
+ while (p < end_ptr) {
+ sum += *p;
+ p += (CL_SIZE / 2);
+ }
+
+ return sum;
+}
+
+static
+void fill_one_span_write(unsigned char *start_ptr, unsigned char *end_ptr)
+{
+ unsigned char *p;
+
+ p = start_ptr;
+ while (p < end_ptr) {
+ *p = '1';
+ p += (CL_SIZE / 2);
+ }
+}
+
+static int fill_cache_read(unsigned char *start_ptr, unsigned char *end_ptr,
+ char *resctrl_val)
+{
+ int ret = 0;
+ FILE *fp;
+
+ while (1) {
+ ret = fill_one_span_read(start_ptr, end_ptr);
+ if (!strcmp(resctrl_val, "cat"))
+ break;
+ }
+
+ /* Consume read result so that reading memory is not optimized out. */
+ fp = fopen("/dev/null", "w");
+ if (!fp)
+ perror("Unable to write to /dev/null");
+ fprintf(fp, "Sum: %d ", ret);
+ fclose(fp);
+
+ return 0;
+}
+
+static int fill_cache_write(unsigned char *start_ptr, unsigned char *end_ptr,
+ char *resctrl_val)
+{
+ while (1) {
+ fill_one_span_write(start_ptr, end_ptr);
+ if (!strcmp(resctrl_val, "cat"))
+ break;
+ }
+
+ return 0;
+}
+
+static int
+fill_cache(unsigned long long buf_size, int malloc_and_init, int memflush,
+ int op, char *resctrl_val)
+{
+ unsigned char *start_ptr, *end_ptr;
+ unsigned long long i;
+ int ret;
+
+ if (malloc_and_init)
+ start_ptr = malloc_and_init_memory(buf_size);
+ else
+ start_ptr = malloc(buf_size);
+
+ if (!start_ptr)
+ return -1;
+
+ startptr = start_ptr;
+ end_ptr = start_ptr + buf_size;
+
+ /*
+ * It's better to touch the memory once to avoid any compiler
+ * optimizations
+ */
+ if (!malloc_and_init) {
+ for (i = 0; i < buf_size; i++)
+ *start_ptr++ = (unsigned char)rand();
+ }
+
+ start_ptr = startptr;
+
+ /* Flush the memory before using to avoid "cache hot pages" effect */
+ if (memflush)
+ mem_flush(start_ptr, buf_size);
+
+ if (op == 0)
+ ret = fill_cache_read(start_ptr, end_ptr, resctrl_val);
+ else
+ ret = fill_cache_write(start_ptr, end_ptr, resctrl_val);
+
+ if (ret) {
+ printf("\n Error in fill cache read/write...\n");
+ return -1;
+ }
+
+ free(startptr);
+
+ return 0;
+}
+
+int run_fill_buf(unsigned long span, int malloc_and_init_memory,
+ int memflush, int op, char *resctrl_val)
+{
+ unsigned long long cache_size = span;
+ int ret;
+
+ /* set up ctrl-c handler */
+ if (signal(SIGINT, ctrl_handler) == SIG_ERR)
+ printf("Failed to catch SIGINT!\n");
+ if (signal(SIGHUP, ctrl_handler) == SIG_ERR)
+ printf("Failed to catch SIGHUP!\n");
+
+ ret = fill_cache(cache_size, malloc_and_init_memory, memflush, op,
+ resctrl_val);
+ if (ret) {
+ printf("\n Error in fill cache\n");
+ return -1;
+ }
+
+ return 0;
+}
diff --git a/tools/testing/selftests/resctrl/mba_test.c b/tools/testing/selftests/resctrl/mba_test.c
new file mode 100644
index 000000000000..7bf8eaa6204b
--- /dev/null
+++ b/tools/testing/selftests/resctrl/mba_test.c
@@ -0,0 +1,171 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Memory Bandwidth Allocation (MBA) test
+ *
+ * Copyright (C) 2018 Intel Corporation
+ *
+ * Authors:
+ * Sai Praneeth Prakhya <sai.praneeth.prakhya@intel.com>,
+ * Fenghua Yu <fenghua.yu@intel.com>
+ */
+#include "resctrl.h"
+
+#define RESULT_FILE_NAME "result_mba"
+#define NUM_OF_RUNS 5
+#define MAX_DIFF 300
+#define ALLOCATION_MAX 100
+#define ALLOCATION_MIN 10
+#define ALLOCATION_STEP 10
+
+/*
+ * Change schemata percentage from 100 to 10%. Write schemata to specified
+ * con_mon grp, mon_grp in resctrl FS.
+ * For each allocation, run 5 times in order to get average values.
+ */
+static int mba_setup(int num, ...)
+{
+ static int runs_per_allocation, allocation = 100;
+ struct resctrl_val_param *p;
+ char allocation_str[64];
+ va_list param;
+
+ va_start(param, num);
+ p = va_arg(param, struct resctrl_val_param *);
+ va_end(param);
+
+ if (runs_per_allocation >= NUM_OF_RUNS)
+ runs_per_allocation = 0;
+
+ /* Only set up schemata once every NUM_OF_RUNS of allocations */
+ if (runs_per_allocation++ != 0)
+ return 0;
+
+ if (allocation < ALLOCATION_MIN || allocation > ALLOCATION_MAX)
+ return -1;
+
+ sprintf(allocation_str, "%d", allocation);
+
+ write_schemata(p->ctrlgrp, allocation_str, p->cpu_no, p->resctrl_val);
+ allocation -= ALLOCATION_STEP;
+
+ return 0;
+}
+
+static void show_mba_info(unsigned long *bw_imc, unsigned long *bw_resc)
+{
+ int allocation, runs;
+ bool failed = false;
+
+ printf("# Results are displayed in (MB)\n");
+ /* Memory bandwidth from 100% down to 10% */
+ for (allocation = 0; allocation < ALLOCATION_MAX / ALLOCATION_STEP;
+ allocation++) {
+ unsigned long avg_bw_imc, avg_bw_resc;
+ unsigned long sum_bw_imc = 0, sum_bw_resc = 0;
+ unsigned long avg_diff;
+
+ /*
+ * The first run is discarded due to inaccurate value from
+ * phase transition.
+ */
+ for (runs = NUM_OF_RUNS * allocation + 1;
+ runs < NUM_OF_RUNS * allocation + NUM_OF_RUNS ; runs++) {
+ sum_bw_imc += bw_imc[runs];
+ sum_bw_resc += bw_resc[runs];
+ }
+
+ avg_bw_imc = sum_bw_imc / (NUM_OF_RUNS - 1);
+ avg_bw_resc = sum_bw_resc / (NUM_OF_RUNS - 1);
+ avg_diff = labs((long)(avg_bw_resc - avg_bw_imc));
+
+ printf("%sok MBA schemata percentage %u smaller than %d %%\n",
+ avg_diff > MAX_DIFF ? "not " : "",
+ ALLOCATION_MAX - ALLOCATION_STEP * allocation,
+ MAX_DIFF);
+ tests_run++;
+ printf("# avg_diff: %lu\n", avg_diff);
+ printf("# avg_bw_imc: %lu\n", avg_bw_imc);
+ printf("# avg_bw_resc: %lu\n", avg_bw_resc);
+ if (avg_diff > MAX_DIFF)
+ failed = true;
+ }
+
+ printf("%sok schemata change using MBA%s\n", failed ? "not " : "",
+ failed ? " # at least one test failed" : "");
+ tests_run++;
+}
+
+static int check_results(void)
+{
+ char *token_array[8], output[] = RESULT_FILE_NAME, temp[512];
+ unsigned long bw_imc[1024], bw_resc[1024];
+ int runs;
+ FILE *fp;
+
+ fp = fopen(output, "r");
+ if (!fp) {
+ perror(output);
+
+ return errno;
+ }
+
+ runs = 0;
+ while (fgets(temp, sizeof(temp), fp)) {
+ char *token = strtok(temp, ":\t");
+ int fields = 0;
+
+ while (token) {
+ token_array[fields++] = token;
+ token = strtok(NULL, ":\t");
+ }
+
+ /* Field 3 is perf imc value */
+ bw_imc[runs] = strtoul(token_array[3], NULL, 0);
+ /* Field 5 is resctrl value */
+ bw_resc[runs] = strtoul(token_array[5], NULL, 0);
+ runs++;
+ }
+
+ fclose(fp);
+
+ show_mba_info(bw_imc, bw_resc);
+
+ return 0;
+}
+
+void mba_test_cleanup(void)
+{
+ remove(RESULT_FILE_NAME);
+}
+
+int mba_schemata_change(int cpu_no, char *bw_report, char **benchmark_cmd)
+{
+ struct resctrl_val_param param = {
+ .resctrl_val = "mba",
+ .ctrlgrp = "c1",
+ .mongrp = "m1",
+ .cpu_no = cpu_no,
+ .mum_resctrlfs = 1,
+ .filename = RESULT_FILE_NAME,
+ .bw_report = bw_report,
+ .setup = mba_setup
+ };
+ int ret;
+
+ remove(RESULT_FILE_NAME);
+
+ if (!validate_resctrl_feature_request("mba"))
+ return -1;
+
+ ret = resctrl_val(benchmark_cmd, &param);
+ if (ret)
+ return ret;
+
+ ret = check_results();
+ if (ret)
+ return ret;
+
+ mba_test_cleanup();
+
+ return 0;
+}
diff --git a/tools/testing/selftests/resctrl/mbm_test.c b/tools/testing/selftests/resctrl/mbm_test.c
new file mode 100644
index 000000000000..4700f7453f81
--- /dev/null
+++ b/tools/testing/selftests/resctrl/mbm_test.c
@@ -0,0 +1,145 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Memory Bandwidth Monitoring (MBM) test
+ *
+ * Copyright (C) 2018 Intel Corporation
+ *
+ * Authors:
+ * Sai Praneeth Prakhya <sai.praneeth.prakhya@intel.com>,
+ * Fenghua Yu <fenghua.yu@intel.com>
+ */
+#include "resctrl.h"
+
+#define RESULT_FILE_NAME "result_mbm"
+#define MAX_DIFF 300
+#define NUM_OF_RUNS 5
+
+static void
+show_bw_info(unsigned long *bw_imc, unsigned long *bw_resc, int span)
+{
+ unsigned long avg_bw_imc = 0, avg_bw_resc = 0;
+ unsigned long sum_bw_imc = 0, sum_bw_resc = 0;
+ long avg_diff = 0;
+ int runs;
+
+ /*
+ * Discard the first value which is inaccurate due to monitoring setup
+ * transition phase.
+ */
+ for (runs = 1; runs < NUM_OF_RUNS ; runs++) {
+ sum_bw_imc += bw_imc[runs];
+ sum_bw_resc += bw_resc[runs];
+ }
+
+ avg_bw_imc = sum_bw_imc / 4;
+ avg_bw_resc = sum_bw_resc / 4;
+ avg_diff = avg_bw_resc - avg_bw_imc;
+
+ printf("%sok MBM: diff within %d%%\n",
+ labs(avg_diff) > MAX_DIFF ? "not " : "", MAX_DIFF);
+ tests_run++;
+ printf("# avg_diff: %lu\n", labs(avg_diff));
+ printf("# Span (MB): %d\n", span);
+ printf("# avg_bw_imc: %lu\n", avg_bw_imc);
+ printf("# avg_bw_resc: %lu\n", avg_bw_resc);
+}
+
+static int check_results(int span)
+{
+ unsigned long bw_imc[NUM_OF_RUNS], bw_resc[NUM_OF_RUNS];
+ char temp[1024], *token_array[8];
+ char output[] = RESULT_FILE_NAME;
+ int runs;
+ FILE *fp;
+
+ printf("# Checking for pass/fail\n");
+
+ fp = fopen(output, "r");
+ if (!fp) {
+ perror(output);
+
+ return errno;
+ }
+
+ runs = 0;
+ while (fgets(temp, sizeof(temp), fp)) {
+ char *token = strtok(temp, ":\t");
+ int i = 0;
+
+ while (token) {
+ token_array[i++] = token;
+ token = strtok(NULL, ":\t");
+ }
+
+ bw_resc[runs] = strtoul(token_array[5], NULL, 0);
+ bw_imc[runs] = strtoul(token_array[3], NULL, 0);
+ runs++;
+ }
+
+ show_bw_info(bw_imc, bw_resc, span);
+
+ fclose(fp);
+
+ return 0;
+}
+
+static int mbm_setup(int num, ...)
+{
+ struct resctrl_val_param *p;
+ static int num_of_runs;
+ va_list param;
+ int ret = 0;
+
+ /* Run NUM_OF_RUNS times */
+ if (num_of_runs++ >= NUM_OF_RUNS)
+ return -1;
+
+ va_start(param, num);
+ p = va_arg(param, struct resctrl_val_param *);
+ va_end(param);
+
+ /* Set up shemata with 100% allocation on the first run. */
+ if (num_of_runs == 0)
+ ret = write_schemata(p->ctrlgrp, "100", p->cpu_no,
+ p->resctrl_val);
+
+ return ret;
+}
+
+void mbm_test_cleanup(void)
+{
+ remove(RESULT_FILE_NAME);
+}
+
+int mbm_bw_change(int span, int cpu_no, char *bw_report, char **benchmark_cmd)
+{
+ struct resctrl_val_param param = {
+ .resctrl_val = "mbm",
+ .ctrlgrp = "c1",
+ .mongrp = "m1",
+ .span = span,
+ .cpu_no = cpu_no,
+ .mum_resctrlfs = 1,
+ .filename = RESULT_FILE_NAME,
+ .bw_report = bw_report,
+ .setup = mbm_setup
+ };
+ int ret;
+
+ remove(RESULT_FILE_NAME);
+
+ if (!validate_resctrl_feature_request("mbm"))
+ return -1;
+
+ ret = resctrl_val(benchmark_cmd, &param);
+ if (ret)
+ return ret;
+
+ ret = check_results(span);
+ if (ret)
+ return ret;
+
+ mbm_test_cleanup();
+
+ return 0;
+}
diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h
new file mode 100644
index 000000000000..39bf59c6b9c5
--- /dev/null
+++ b/tools/testing/selftests/resctrl/resctrl.h
@@ -0,0 +1,107 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#define _GNU_SOURCE
+#ifndef RESCTRL_H
+#define RESCTRL_H
+#include <stdio.h>
+#include <stdarg.h>
+#include <math.h>
+#include <errno.h>
+#include <sched.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <string.h>
+#include <signal.h>
+#include <dirent.h>
+#include <stdbool.h>
+#include <sys/stat.h>
+#include <sys/ioctl.h>
+#include <sys/mount.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <sys/select.h>
+#include <sys/time.h>
+#include <sys/eventfd.h>
+#include <asm/unistd.h>
+#include <linux/perf_event.h>
+
+#define MB (1024 * 1024)
+#define RESCTRL_PATH "/sys/fs/resctrl"
+#define PHYS_ID_PATH "/sys/devices/system/cpu/cpu"
+#define CBM_MASK_PATH "/sys/fs/resctrl/info"
+
+#define PARENT_EXIT(err_msg) \
+ do { \
+ perror(err_msg); \
+ kill(ppid, SIGKILL); \
+ exit(EXIT_FAILURE); \
+ } while (0)
+
+/*
+ * resctrl_val_param: resctrl test parameters
+ * @resctrl_val: Resctrl feature (Eg: mbm, mba.. etc)
+ * @ctrlgrp: Name of the control monitor group (con_mon grp)
+ * @mongrp: Name of the monitor group (mon grp)
+ * @cpu_no: CPU number to which the benchmark would be binded
+ * @span: Memory bytes accessed in each benchmark iteration
+ * @mum_resctrlfs: Should the resctrl FS be remounted?
+ * @filename: Name of file to which the o/p should be written
+ * @bw_report: Bandwidth report type (reads vs writes)
+ * @setup: Call back function to setup test environment
+ */
+struct resctrl_val_param {
+ char *resctrl_val;
+ char ctrlgrp[64];
+ char mongrp[64];
+ int cpu_no;
+ unsigned long span;
+ int mum_resctrlfs;
+ char filename[64];
+ char *bw_report;
+ unsigned long mask;
+ int num_of_runs;
+ int (*setup)(int num, ...);
+};
+
+pid_t bm_pid, ppid;
+int tests_run;
+
+char llc_occup_path[1024];
+bool is_amd;
+
+bool check_resctrlfs_support(void);
+int filter_dmesg(void);
+int remount_resctrlfs(bool mum_resctrlfs);
+int get_resource_id(int cpu_no, int *resource_id);
+int umount_resctrlfs(void);
+int validate_bw_report_request(char *bw_report);
+bool validate_resctrl_feature_request(char *resctrl_val);
+char *fgrep(FILE *inf, const char *str);
+int taskset_benchmark(pid_t bm_pid, int cpu_no);
+void run_benchmark(int signum, siginfo_t *info, void *ucontext);
+int write_schemata(char *ctrlgrp, char *schemata, int cpu_no,
+ char *resctrl_val);
+int write_bm_pid_to_resctrl(pid_t bm_pid, char *ctrlgrp, char *mongrp,
+ char *resctrl_val);
+int perf_event_open(struct perf_event_attr *hw_event, pid_t pid, int cpu,
+ int group_fd, unsigned long flags);
+int run_fill_buf(unsigned long span, int malloc_and_init_memory, int memflush,
+ int op, char *resctrl_va);
+int resctrl_val(char **benchmark_cmd, struct resctrl_val_param *param);
+int mbm_bw_change(int span, int cpu_no, char *bw_report, char **benchmark_cmd);
+void tests_cleanup(void);
+void mbm_test_cleanup(void);
+int mba_schemata_change(int cpu_no, char *bw_report, char **benchmark_cmd);
+void mba_test_cleanup(void);
+int get_cbm_mask(char *cache_type);
+int get_cache_size(int cpu_no, char *cache_type, unsigned long *cache_size);
+void ctrlc_handler(int signum, siginfo_t *info, void *ptr);
+int cat_val(struct resctrl_val_param *param);
+void cat_test_cleanup(void);
+int cat_perf_miss_val(int cpu_no, int no_of_bits, char *cache_type);
+int cqm_resctrl_val(int cpu_no, int n, char **benchmark_cmd);
+unsigned int count_bits(unsigned long n);
+void cqm_test_cleanup(void);
+int get_core_sibling(int cpu_no);
+int measure_cache_vals(struct resctrl_val_param *param, int bm_pid);
+
+#endif /* RESCTRL_H */
diff --git a/tools/testing/selftests/resctrl/resctrl_tests.c b/tools/testing/selftests/resctrl/resctrl_tests.c
new file mode 100644
index 000000000000..425cc85ac883
--- /dev/null
+++ b/tools/testing/selftests/resctrl/resctrl_tests.c
@@ -0,0 +1,202 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Resctrl tests
+ *
+ * Copyright (C) 2018 Intel Corporation
+ *
+ * Authors:
+ * Sai Praneeth Prakhya <sai.praneeth.prakhya@intel.com>,
+ * Fenghua Yu <fenghua.yu@intel.com>
+ */
+#include "resctrl.h"
+
+#define BENCHMARK_ARGS 64
+#define BENCHMARK_ARG_SIZE 64
+
+bool is_amd;
+
+void detect_amd(void)
+{
+ FILE *inf = fopen("/proc/cpuinfo", "r");
+ char *res;
+
+ if (!inf)
+ return;
+
+ res = fgrep(inf, "vendor_id");
+
+ if (res) {
+ char *s = strchr(res, ':');
+
+ is_amd = s && !strcmp(s, ": AuthenticAMD\n");
+ free(res);
+ }
+ fclose(inf);
+}
+
+static void cmd_help(void)
+{
+ printf("usage: resctrl_tests [-h] [-b \"benchmark_cmd [options]\"] [-t test list] [-n no_of_bits]\n");
+ printf("\t-b benchmark_cmd [options]: run specified benchmark for MBM, MBA and CQM");
+ printf("\t default benchmark is builtin fill_buf\n");
+ printf("\t-t test list: run tests specified in the test list, ");
+ printf("e.g. -t mbm, mba, cqm, cat\n");
+ printf("\t-n no_of_bits: run cache tests using specified no of bits in cache bit mask\n");
+ printf("\t-p cpu_no: specify CPU number to run the test. 1 is default\n");
+ printf("\t-h: help\n");
+}
+
+void tests_cleanup(void)
+{
+ mbm_test_cleanup();
+ mba_test_cleanup();
+ cqm_test_cleanup();
+ cat_test_cleanup();
+}
+
+int main(int argc, char **argv)
+{
+ bool has_ben = false, mbm_test = true, mba_test = true, cqm_test = true;
+ int res, c, cpu_no = 1, span = 250, argc_new = argc, i, no_of_bits = 5;
+ char *benchmark_cmd[BENCHMARK_ARGS], bw_report[64], bm_type[64];
+ char benchmark_cmd_area[BENCHMARK_ARGS][BENCHMARK_ARG_SIZE];
+ int ben_ind, ben_count;
+ bool cat_test = true;
+
+ for (i = 0; i < argc; i++) {
+ if (strcmp(argv[i], "-b") == 0) {
+ ben_ind = i + 1;
+ ben_count = argc - ben_ind;
+ argc_new = ben_ind - 1;
+ has_ben = true;
+ break;
+ }
+ }
+
+ while ((c = getopt(argc_new, argv, "ht:b:")) != -1) {
+ char *token;
+
+ switch (c) {
+ case 't':
+ token = strtok(optarg, ",");
+
+ mbm_test = false;
+ mba_test = false;
+ cqm_test = false;
+ cat_test = false;
+ while (token) {
+ if (!strcmp(token, "mbm")) {
+ mbm_test = true;
+ } else if (!strcmp(token, "mba")) {
+ mba_test = true;
+ } else if (!strcmp(token, "cqm")) {
+ cqm_test = true;
+ } else if (!strcmp(token, "cat")) {
+ cat_test = true;
+ } else {
+ printf("invalid argument\n");
+
+ return -1;
+ }
+ token = strtok(NULL, ":\t");
+ }
+ break;
+ case 'p':
+ cpu_no = atoi(optarg);
+ break;
+ case 'n':
+ no_of_bits = atoi(optarg);
+ break;
+ case 'h':
+ cmd_help();
+
+ return 0;
+ default:
+ printf("invalid argument\n");
+
+ return -1;
+ }
+ }
+
+ printf("TAP version 13\n");
+
+ /*
+ * Typically we need root privileges, because:
+ * 1. We write to resctrl FS
+ * 2. We execute perf commands
+ */
+ if (geteuid() != 0)
+ printf("# WARNING: not running as root, tests may fail.\n");
+
+ /* Detect AMD vendor */
+ detect_amd();
+
+ if (has_ben) {
+ /* Extract benchmark command from command line. */
+ for (i = ben_ind; i < argc; i++) {
+ benchmark_cmd[i - ben_ind] = benchmark_cmd_area[i];
+ sprintf(benchmark_cmd[i - ben_ind], "%s", argv[i]);
+ }
+ benchmark_cmd[ben_count] = NULL;
+ } else {
+ /* If no benchmark is given by "-b" argument, use fill_buf. */
+ for (i = 0; i < 6; i++)
+ benchmark_cmd[i] = benchmark_cmd_area[i];
+
+ strcpy(benchmark_cmd[0], "fill_buf");
+ sprintf(benchmark_cmd[1], "%d", span);
+ strcpy(benchmark_cmd[2], "1");
+ strcpy(benchmark_cmd[3], "1");
+ strcpy(benchmark_cmd[4], "0");
+ strcpy(benchmark_cmd[5], "");
+ benchmark_cmd[6] = NULL;
+ }
+
+ sprintf(bw_report, "reads");
+ sprintf(bm_type, "fill_buf");
+
+ check_resctrlfs_support();
+ filter_dmesg();
+
+ if (!is_amd && mbm_test) {
+ printf("# Starting MBM BW change ...\n");
+ if (!has_ben)
+ sprintf(benchmark_cmd[5], "%s", "mba");
+ res = mbm_bw_change(span, cpu_no, bw_report, benchmark_cmd);
+ printf("%sok MBM: bw change\n", res ? "not " : "");
+ mbm_test_cleanup();
+ tests_run++;
+ }
+
+ if (!is_amd && mba_test) {
+ printf("# Starting MBA Schemata change ...\n");
+ if (!has_ben)
+ sprintf(benchmark_cmd[1], "%d", span);
+ res = mba_schemata_change(cpu_no, bw_report, benchmark_cmd);
+ printf("%sok MBA: schemata change\n", res ? "not " : "");
+ mba_test_cleanup();
+ tests_run++;
+ }
+
+ if (cqm_test) {
+ printf("# Starting CQM test ...\n");
+ if (!has_ben)
+ sprintf(benchmark_cmd[5], "%s", "cqm");
+ res = cqm_resctrl_val(cpu_no, no_of_bits, benchmark_cmd);
+ printf("%sok CQM: test\n", res ? "not " : "");
+ cqm_test_cleanup();
+ tests_run++;
+ }
+
+ if (cat_test) {
+ printf("# Starting CAT test ...\n");
+ res = cat_perf_miss_val(cpu_no, no_of_bits, "L3");
+ printf("%sok CAT: test\n", res ? "not " : "");
+ tests_run++;
+ cat_test_cleanup();
+ }
+
+ printf("1..%d\n", tests_run);
+
+ return 0;
+}
diff --git a/tools/testing/selftests/resctrl/resctrl_val.c b/tools/testing/selftests/resctrl/resctrl_val.c
new file mode 100644
index 000000000000..520fea3606d1
--- /dev/null
+++ b/tools/testing/selftests/resctrl/resctrl_val.c
@@ -0,0 +1,744 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Memory bandwidth monitoring and allocation library
+ *
+ * Copyright (C) 2018 Intel Corporation
+ *
+ * Authors:
+ * Sai Praneeth Prakhya <sai.praneeth.prakhya@intel.com>,
+ * Fenghua Yu <fenghua.yu@intel.com>
+ */
+#include "resctrl.h"
+
+#define UNCORE_IMC "uncore_imc"
+#define READ_FILE_NAME "events/cas_count_read"
+#define WRITE_FILE_NAME "events/cas_count_write"
+#define DYN_PMU_PATH "/sys/bus/event_source/devices"
+#define SCALE 0.00006103515625
+#define MAX_IMCS 20
+#define MAX_TOKENS 5
+#define READ 0
+#define WRITE 1
+#define CON_MON_MBM_LOCAL_BYTES_PATH \
+ "%s/%s/mon_groups/%s/mon_data/mon_L3_%02d/mbm_local_bytes"
+
+#define CON_MBM_LOCAL_BYTES_PATH \
+ "%s/%s/mon_data/mon_L3_%02d/mbm_local_bytes"
+
+#define MON_MBM_LOCAL_BYTES_PATH \
+ "%s/mon_groups/%s/mon_data/mon_L3_%02d/mbm_local_bytes"
+
+#define MBM_LOCAL_BYTES_PATH \
+ "%s/mon_data/mon_L3_%02d/mbm_local_bytes"
+
+#define CON_MON_LCC_OCCUP_PATH \
+ "%s/%s/mon_groups/%s/mon_data/mon_L3_%02d/llc_occupancy"
+
+#define CON_LCC_OCCUP_PATH \
+ "%s/%s/mon_data/mon_L3_%02d/llc_occupancy"
+
+#define MON_LCC_OCCUP_PATH \
+ "%s/mon_groups/%s/mon_data/mon_L3_%02d/llc_occupancy"
+
+#define LCC_OCCUP_PATH \
+ "%s/mon_data/mon_L3_%02d/llc_occupancy"
+
+struct membw_read_format {
+ __u64 value; /* The value of the event */
+ __u64 time_enabled; /* if PERF_FORMAT_TOTAL_TIME_ENABLED */
+ __u64 time_running; /* if PERF_FORMAT_TOTAL_TIME_RUNNING */
+ __u64 id; /* if PERF_FORMAT_ID */
+};
+
+struct imc_counter_config {
+ __u32 type;
+ __u64 event;
+ __u64 umask;
+ struct perf_event_attr pe;
+ struct membw_read_format return_value;
+ int fd;
+};
+
+static char mbm_total_path[1024];
+static int imcs;
+static struct imc_counter_config imc_counters_config[MAX_IMCS][2];
+
+void membw_initialize_perf_event_attr(int i, int j)
+{
+ memset(&imc_counters_config[i][j].pe, 0,
+ sizeof(struct perf_event_attr));
+ imc_counters_config[i][j].pe.type = imc_counters_config[i][j].type;
+ imc_counters_config[i][j].pe.size = sizeof(struct perf_event_attr);
+ imc_counters_config[i][j].pe.disabled = 1;
+ imc_counters_config[i][j].pe.inherit = 1;
+ imc_counters_config[i][j].pe.exclude_guest = 0;
+ imc_counters_config[i][j].pe.config =
+ imc_counters_config[i][j].umask << 8 |
+ imc_counters_config[i][j].event;
+ imc_counters_config[i][j].pe.sample_type = PERF_SAMPLE_IDENTIFIER;
+ imc_counters_config[i][j].pe.read_format =
+ PERF_FORMAT_TOTAL_TIME_ENABLED | PERF_FORMAT_TOTAL_TIME_RUNNING;
+}
+
+void membw_ioctl_perf_event_ioc_reset_enable(int i, int j)
+{
+ ioctl(imc_counters_config[i][j].fd, PERF_EVENT_IOC_RESET, 0);
+ ioctl(imc_counters_config[i][j].fd, PERF_EVENT_IOC_ENABLE, 0);
+}
+
+void membw_ioctl_perf_event_ioc_disable(int i, int j)
+{
+ ioctl(imc_counters_config[i][j].fd, PERF_EVENT_IOC_DISABLE, 0);
+}
+
+/*
+ * get_event_and_umask: Parse config into event and umask
+ * @cas_count_cfg: Config
+ * @count: iMC number
+ * @op: Operation (read/write)
+ */
+void get_event_and_umask(char *cas_count_cfg, int count, bool op)
+{
+ char *token[MAX_TOKENS];
+ int i = 0;
+
+ strcat(cas_count_cfg, ",");
+ token[0] = strtok(cas_count_cfg, "=,");
+
+ for (i = 1; i < MAX_TOKENS; i++)
+ token[i] = strtok(NULL, "=,");
+
+ for (i = 0; i < MAX_TOKENS; i++) {
+ if (!token[i])
+ break;
+ if (strcmp(token[i], "event") == 0) {
+ if (op == READ)
+ imc_counters_config[count][READ].event =
+ strtol(token[i + 1], NULL, 16);
+ else
+ imc_counters_config[count][WRITE].event =
+ strtol(token[i + 1], NULL, 16);
+ }
+ if (strcmp(token[i], "umask") == 0) {
+ if (op == READ)
+ imc_counters_config[count][READ].umask =
+ strtol(token[i + 1], NULL, 16);
+ else
+ imc_counters_config[count][WRITE].umask =
+ strtol(token[i + 1], NULL, 16);
+ }
+ }
+}
+
+static int open_perf_event(int i, int cpu_no, int j)
+{
+ imc_counters_config[i][j].fd =
+ perf_event_open(&imc_counters_config[i][j].pe, -1, cpu_no, -1,
+ PERF_FLAG_FD_CLOEXEC);
+
+ if (imc_counters_config[i][j].fd == -1) {
+ fprintf(stderr, "Error opening leader %llx\n",
+ imc_counters_config[i][j].pe.config);
+
+ return -1;
+ }
+
+ return 0;
+}
+
+/* Get type and config (read and write) of an iMC counter */
+static int read_from_imc_dir(char *imc_dir, int count)
+{
+ char cas_count_cfg[1024], imc_counter_cfg[1024], imc_counter_type[1024];
+ FILE *fp;
+
+ /* Get type of iMC counter */
+ sprintf(imc_counter_type, "%s%s", imc_dir, "type");
+ fp = fopen(imc_counter_type, "r");
+ if (!fp) {
+ perror("Failed to open imc counter type file");
+
+ return -1;
+ }
+ if (fscanf(fp, "%u", &imc_counters_config[count][READ].type) <= 0) {
+ perror("Could not get imc type");
+ fclose(fp);
+
+ return -1;
+ }
+ fclose(fp);
+
+ imc_counters_config[count][WRITE].type =
+ imc_counters_config[count][READ].type;
+
+ /* Get read config */
+ sprintf(imc_counter_cfg, "%s%s", imc_dir, READ_FILE_NAME);
+ fp = fopen(imc_counter_cfg, "r");
+ if (!fp) {
+ perror("Failed to open imc config file");
+
+ return -1;
+ }
+ if (fscanf(fp, "%s", cas_count_cfg) <= 0) {
+ perror("Could not get imc cas count read");
+ fclose(fp);
+
+ return -1;
+ }
+ fclose(fp);
+
+ get_event_and_umask(cas_count_cfg, count, READ);
+
+ /* Get write config */
+ sprintf(imc_counter_cfg, "%s%s", imc_dir, WRITE_FILE_NAME);
+ fp = fopen(imc_counter_cfg, "r");
+ if (!fp) {
+ perror("Failed to open imc config file");
+
+ return -1;
+ }
+ if (fscanf(fp, "%s", cas_count_cfg) <= 0) {
+ perror("Could not get imc cas count write");
+ fclose(fp);
+
+ return -1;
+ }
+ fclose(fp);
+
+ get_event_and_umask(cas_count_cfg, count, WRITE);
+
+ return 0;
+}
+
+/*
+ * A system can have 'n' number of iMC (Integrated Memory Controller)
+ * counters, get that 'n'. For each iMC counter get it's type and config.
+ * Also, each counter has two configs, one for read and the other for write.
+ * A config again has two parts, event and umask.
+ * Enumerate all these details into an array of structures.
+ *
+ * Return: >= 0 on success. < 0 on failure.
+ */
+static int num_of_imcs(void)
+{
+ unsigned int count = 0;
+ char imc_dir[512];
+ struct dirent *ep;
+ int ret;
+ DIR *dp;
+
+ dp = opendir(DYN_PMU_PATH);
+ if (dp) {
+ while ((ep = readdir(dp))) {
+ if (strstr(ep->d_name, UNCORE_IMC)) {
+ sprintf(imc_dir, "%s/%s/", DYN_PMU_PATH,
+ ep->d_name);
+ ret = read_from_imc_dir(imc_dir, count);
+ if (ret) {
+ closedir(dp);
+
+ return ret;
+ }
+ count++;
+ }
+ }
+ closedir(dp);
+ if (count == 0) {
+ perror("Unable find iMC counters!\n");
+
+ return -1;
+ }
+ } else {
+ perror("Unable to open PMU directory!\n");
+
+ return -1;
+ }
+
+ return count;
+}
+
+static int initialize_mem_bw_imc(void)
+{
+ int imc, j;
+
+ imcs = num_of_imcs();
+ if (imcs <= 0)
+ return imcs;
+
+ /* Initialize perf_event_attr structures for all iMC's */
+ for (imc = 0; imc < imcs; imc++) {
+ for (j = 0; j < 2; j++)
+ membw_initialize_perf_event_attr(imc, j);
+ }
+
+ return 0;
+}
+
+/*
+ * get_mem_bw_imc: Memory band width as reported by iMC counters
+ * @cpu_no: CPU number that the benchmark PID is binded to
+ * @bw_report: Bandwidth report type (reads, writes)
+ *
+ * Memory B/W utilized by a process on a socket can be calculated using
+ * iMC counters. Perf events are used to read these counters.
+ *
+ * Return: >= 0 on success. < 0 on failure.
+ */
+static float get_mem_bw_imc(int cpu_no, char *bw_report)
+{
+ float reads, writes, of_mul_read, of_mul_write;
+ int imc, j, ret;
+
+ /* Start all iMC counters to log values (both read and write) */
+ reads = 0, writes = 0, of_mul_read = 1, of_mul_write = 1;
+ for (imc = 0; imc < imcs; imc++) {
+ for (j = 0; j < 2; j++) {
+ ret = open_perf_event(imc, cpu_no, j);
+ if (ret)
+ return -1;
+ }
+ for (j = 0; j < 2; j++)
+ membw_ioctl_perf_event_ioc_reset_enable(imc, j);
+ }
+
+ sleep(1);
+
+ /* Stop counters after a second to get results (both read and write) */
+ for (imc = 0; imc < imcs; imc++) {
+ for (j = 0; j < 2; j++)
+ membw_ioctl_perf_event_ioc_disable(imc, j);
+ }
+
+ /*
+ * Get results which are stored in struct type imc_counter_config
+ * Take over flow into consideration before calculating total b/w
+ */
+ for (imc = 0; imc < imcs; imc++) {
+ struct imc_counter_config *r =
+ &imc_counters_config[imc][READ];
+ struct imc_counter_config *w =
+ &imc_counters_config[imc][WRITE];
+
+ if (read(r->fd, &r->return_value,
+ sizeof(struct membw_read_format)) == -1) {
+ perror("Couldn't get read b/w through iMC");
+
+ return -1;
+ }
+
+ if (read(w->fd, &w->return_value,
+ sizeof(struct membw_read_format)) == -1) {
+ perror("Couldn't get write bw through iMC");
+
+ return -1;
+ }
+
+ __u64 r_time_enabled = r->return_value.time_enabled;
+ __u64 r_time_running = r->return_value.time_running;
+
+ if (r_time_enabled != r_time_running)
+ of_mul_read = (float)r_time_enabled /
+ (float)r_time_running;
+
+ __u64 w_time_enabled = w->return_value.time_enabled;
+ __u64 w_time_running = w->return_value.time_running;
+
+ if (w_time_enabled != w_time_running)
+ of_mul_write = (float)w_time_enabled /
+ (float)w_time_running;
+ reads += r->return_value.value * of_mul_read * SCALE;
+ writes += w->return_value.value * of_mul_write * SCALE;
+ }
+
+ for (imc = 0; imc < imcs; imc++) {
+ close(imc_counters_config[imc][READ].fd);
+ close(imc_counters_config[imc][WRITE].fd);
+ }
+
+ if (strcmp(bw_report, "reads") == 0)
+ return reads;
+
+ if (strcmp(bw_report, "writes") == 0)
+ return writes;
+
+ return (reads + writes);
+}
+
+void set_mbm_path(const char *ctrlgrp, const char *mongrp, int resource_id)
+{
+ if (ctrlgrp && mongrp)
+ sprintf(mbm_total_path, CON_MON_MBM_LOCAL_BYTES_PATH,
+ RESCTRL_PATH, ctrlgrp, mongrp, resource_id);
+ else if (!ctrlgrp && mongrp)
+ sprintf(mbm_total_path, MON_MBM_LOCAL_BYTES_PATH, RESCTRL_PATH,
+ mongrp, resource_id);
+ else if (ctrlgrp && !mongrp)
+ sprintf(mbm_total_path, CON_MBM_LOCAL_BYTES_PATH, RESCTRL_PATH,
+ ctrlgrp, resource_id);
+ else if (!ctrlgrp && !mongrp)
+ sprintf(mbm_total_path, MBM_LOCAL_BYTES_PATH, RESCTRL_PATH,
+ resource_id);
+}
+
+/*
+ * initialize_mem_bw_resctrl: Appropriately populate "mbm_total_path"
+ * @ctrlgrp: Name of the control monitor group (con_mon grp)
+ * @mongrp: Name of the monitor group (mon grp)
+ * @cpu_no: CPU number that the benchmark PID is binded to
+ * @resctrl_val: Resctrl feature (Eg: mbm, mba.. etc)
+ */
+static void initialize_mem_bw_resctrl(const char *ctrlgrp, const char *mongrp,
+ int cpu_no, char *resctrl_val)
+{
+ int resource_id;
+
+ if (get_resource_id(cpu_no, &resource_id) < 0) {
+ perror("Could not get resource_id");
+ return;
+ }
+
+ if (strcmp(resctrl_val, "mbm") == 0)
+ set_mbm_path(ctrlgrp, mongrp, resource_id);
+
+ if ((strcmp(resctrl_val, "mba") == 0)) {
+ if (ctrlgrp)
+ sprintf(mbm_total_path, CON_MBM_LOCAL_BYTES_PATH,
+ RESCTRL_PATH, ctrlgrp, resource_id);
+ else
+ sprintf(mbm_total_path, MBM_LOCAL_BYTES_PATH,
+ RESCTRL_PATH, resource_id);
+ }
+}
+
+/*
+ * Get MBM Local bytes as reported by resctrl FS
+ * For MBM,
+ * 1. If con_mon grp and mon grp are given, then read from con_mon grp's mon grp
+ * 2. If only con_mon grp is given, then read from con_mon grp
+ * 3. If both are not given, then read from root con_mon grp
+ * For MBA,
+ * 1. If con_mon grp is given, then read from it
+ * 2. If con_mon grp is not given, then read from root con_mon grp
+ */
+static unsigned long get_mem_bw_resctrl(void)
+{
+ unsigned long mbm_total = 0;
+ FILE *fp;
+
+ fp = fopen(mbm_total_path, "r");
+ if (!fp) {
+ perror("Failed to open total bw file");
+
+ return -1;
+ }
+ if (fscanf(fp, "%lu", &mbm_total) <= 0) {
+ perror("Could not get mbm local bytes");
+ fclose(fp);
+
+ return -1;
+ }
+ fclose(fp);
+
+ return mbm_total;
+}
+
+pid_t bm_pid, ppid;
+
+void ctrlc_handler(int signum, siginfo_t *info, void *ptr)
+{
+ kill(bm_pid, SIGKILL);
+ umount_resctrlfs();
+ tests_cleanup();
+ printf("Ending\n\n");
+
+ exit(EXIT_SUCCESS);
+}
+
+/*
+ * print_results_bw: the memory bandwidth results are stored in a file
+ * @filename: file that stores the results
+ * @bm_pid: child pid that runs benchmark
+ * @bw_imc: perf imc counter value
+ * @bw_resc: memory bandwidth value
+ *
+ * Return: 0 on success. non-zero on failure.
+ */
+static int print_results_bw(char *filename, int bm_pid, float bw_imc,
+ unsigned long bw_resc)
+{
+ unsigned long diff = fabs(bw_imc - bw_resc);
+ FILE *fp;
+
+ if (strcmp(filename, "stdio") == 0 || strcmp(filename, "stderr") == 0) {
+ printf("Pid: %d \t Mem_BW_iMC: %f \t ", bm_pid, bw_imc);
+ printf("Mem_BW_resc: %lu \t Difference: %lu\n", bw_resc, diff);
+ } else {
+ fp = fopen(filename, "a");
+ if (!fp) {
+ perror("Cannot open results file");
+
+ return errno;
+ }
+ if (fprintf(fp, "Pid: %d \t Mem_BW_iMC: %f \t Mem_BW_resc: %lu \t Difference: %lu\n",
+ bm_pid, bw_imc, bw_resc, diff) <= 0) {
+ fclose(fp);
+ perror("Could not log results.");
+
+ return errno;
+ }
+ fclose(fp);
+ }
+
+ return 0;
+}
+
+static void set_cqm_path(const char *ctrlgrp, const char *mongrp, char sock_num)
+{
+ if (strlen(ctrlgrp) && strlen(mongrp))
+ sprintf(llc_occup_path, CON_MON_LCC_OCCUP_PATH, RESCTRL_PATH,
+ ctrlgrp, mongrp, sock_num);
+ else if (!strlen(ctrlgrp) && strlen(mongrp))
+ sprintf(llc_occup_path, MON_LCC_OCCUP_PATH, RESCTRL_PATH,
+ mongrp, sock_num);
+ else if (strlen(ctrlgrp) && !strlen(mongrp))
+ sprintf(llc_occup_path, CON_LCC_OCCUP_PATH, RESCTRL_PATH,
+ ctrlgrp, sock_num);
+ else if (!strlen(ctrlgrp) && !strlen(mongrp))
+ sprintf(llc_occup_path, LCC_OCCUP_PATH, RESCTRL_PATH, sock_num);
+}
+
+/*
+ * initialize_llc_occu_resctrl: Appropriately populate "llc_occup_path"
+ * @ctrlgrp: Name of the control monitor group (con_mon grp)
+ * @mongrp: Name of the monitor group (mon grp)
+ * @cpu_no: CPU number that the benchmark PID is binded to
+ * @resctrl_val: Resctrl feature (Eg: cat, cqm.. etc)
+ */
+static void initialize_llc_occu_resctrl(const char *ctrlgrp, const char *mongrp,
+ int cpu_no, char *resctrl_val)
+{
+ int resource_id;
+
+ if (get_resource_id(cpu_no, &resource_id) < 0) {
+ perror("# Unable to resource_id");
+ return;
+ }
+
+ if (strcmp(resctrl_val, "cqm") == 0)
+ set_cqm_path(ctrlgrp, mongrp, resource_id);
+}
+
+static int
+measure_vals(struct resctrl_val_param *param, unsigned long *bw_resc_start)
+{
+ unsigned long bw_imc, bw_resc, bw_resc_end;
+ int ret;
+
+ /*
+ * Measure memory bandwidth from resctrl and from
+ * another source which is perf imc value or could
+ * be something else if perf imc event is not available.
+ * Compare the two values to validate resctrl value.
+ * It takes 1sec to measure the data.
+ */
+ bw_imc = get_mem_bw_imc(param->cpu_no, param->bw_report);
+ if (bw_imc <= 0)
+ return bw_imc;
+
+ bw_resc_end = get_mem_bw_resctrl();
+ if (bw_resc_end <= 0)
+ return bw_resc_end;
+
+ bw_resc = (bw_resc_end - *bw_resc_start) / MB;
+ ret = print_results_bw(param->filename, bm_pid, bw_imc, bw_resc);
+ if (ret)
+ return ret;
+
+ *bw_resc_start = bw_resc_end;
+
+ return 0;
+}
+
+/*
+ * resctrl_val: execute benchmark and measure memory bandwidth on
+ * the benchmark
+ * @benchmark_cmd: benchmark command and its arguments
+ * @param: parameters passed to resctrl_val()
+ *
+ * Return: 0 on success. non-zero on failure.
+ */
+int resctrl_val(char **benchmark_cmd, struct resctrl_val_param *param)
+{
+ char *resctrl_val = param->resctrl_val;
+ unsigned long bw_resc_start = 0;
+ struct sigaction sigact;
+ int ret = 0, pipefd[2];
+ char pipe_message = 0;
+ union sigval value;
+
+ if (strcmp(param->filename, "") == 0)
+ sprintf(param->filename, "stdio");
+
+ if ((strcmp(resctrl_val, "mba")) == 0 ||
+ (strcmp(resctrl_val, "mbm")) == 0) {
+ ret = validate_bw_report_request(param->bw_report);
+ if (ret)
+ return ret;
+ }
+
+ ret = remount_resctrlfs(param->mum_resctrlfs);
+ if (ret)
+ return ret;
+
+ /*
+ * If benchmark wasn't successfully started by child, then child should
+ * kill parent, so save parent's pid
+ */
+ ppid = getpid();
+
+ if (pipe(pipefd)) {
+ perror("# Unable to create pipe");
+
+ return -1;
+ }
+
+ /*
+ * Fork to start benchmark, save child's pid so that it can be killed
+ * when needed
+ */
+ bm_pid = fork();
+ if (bm_pid == -1) {
+ perror("# Unable to fork");
+
+ return -1;
+ }
+
+ if (bm_pid == 0) {
+ /*
+ * Mask all signals except SIGUSR1, parent uses SIGUSR1 to
+ * start benchmark
+ */
+ sigfillset(&sigact.sa_mask);
+ sigdelset(&sigact.sa_mask, SIGUSR1);
+
+ sigact.sa_sigaction = run_benchmark;
+ sigact.sa_flags = SA_SIGINFO;
+
+ /* Register for "SIGUSR1" signal from parent */
+ if (sigaction(SIGUSR1, &sigact, NULL))
+ PARENT_EXIT("Can't register child for signal");
+
+ /* Tell parent that child is ready */
+ close(pipefd[0]);
+ pipe_message = 1;
+ if (write(pipefd[1], &pipe_message, sizeof(pipe_message)) <
+ sizeof(pipe_message)) {
+ perror("# failed signaling parent process");
+ close(pipefd[1]);
+ return -1;
+ }
+ close(pipefd[1]);
+
+ /* Suspend child until delivery of "SIGUSR1" from parent */
+ sigsuspend(&sigact.sa_mask);
+
+ PARENT_EXIT("Child is done");
+ }
+
+ printf("# benchmark PID: %d\n", bm_pid);
+
+ /*
+ * Register CTRL-C handler for parent, as it has to kill benchmark
+ * before exiting
+ */
+ sigact.sa_sigaction = ctrlc_handler;
+ sigemptyset(&sigact.sa_mask);
+ sigact.sa_flags = SA_SIGINFO;
+ if (sigaction(SIGINT, &sigact, NULL) ||
+ sigaction(SIGHUP, &sigact, NULL)) {
+ perror("# sigaction");
+ ret = errno;
+ goto out;
+ }
+
+ value.sival_ptr = benchmark_cmd;
+
+ /* Taskset benchmark to specified cpu */
+ ret = taskset_benchmark(bm_pid, param->cpu_no);
+ if (ret)
+ goto out;
+
+ /* Write benchmark to specified control&monitoring grp in resctrl FS */
+ ret = write_bm_pid_to_resctrl(bm_pid, param->ctrlgrp, param->mongrp,
+ resctrl_val);
+ if (ret)
+ goto out;
+
+ if ((strcmp(resctrl_val, "mbm") == 0) ||
+ (strcmp(resctrl_val, "mba") == 0)) {
+ ret = initialize_mem_bw_imc();
+ if (ret)
+ goto out;
+
+ initialize_mem_bw_resctrl(param->ctrlgrp, param->mongrp,
+ param->cpu_no, resctrl_val);
+ } else if (strcmp(resctrl_val, "cqm") == 0)
+ initialize_llc_occu_resctrl(param->ctrlgrp, param->mongrp,
+ param->cpu_no, resctrl_val);
+
+ /* Parent waits for child to be ready. */
+ close(pipefd[1]);
+ while (pipe_message != 1) {
+ if (read(pipefd[0], &pipe_message, sizeof(pipe_message)) <
+ sizeof(pipe_message)) {
+ perror("# failed reading message from child process");
+ close(pipefd[0]);
+ goto out;
+ }
+ }
+ close(pipefd[0]);
+
+ /* Signal child to start benchmark */
+ if (sigqueue(bm_pid, SIGUSR1, value) == -1) {
+ perror("# sigqueue SIGUSR1 to child");
+ ret = errno;
+ goto out;
+ }
+
+ /* Give benchmark enough time to fully run */
+ sleep(1);
+
+ /* Test runs until the callback setup() tells the test to stop. */
+ while (1) {
+ if ((strcmp(resctrl_val, "mbm") == 0) ||
+ (strcmp(resctrl_val, "mba") == 0)) {
+ ret = param->setup(1, param);
+ if (ret) {
+ ret = 0;
+ break;
+ }
+
+ ret = measure_vals(param, &bw_resc_start);
+ if (ret)
+ break;
+ } else if (strcmp(resctrl_val, "cqm") == 0) {
+ ret = param->setup(1, param);
+ if (ret) {
+ ret = 0;
+ break;
+ }
+ sleep(1);
+ ret = measure_cache_vals(param, bm_pid);
+ if (ret)
+ break;
+ } else {
+ break;
+ }
+ }
+
+out:
+ kill(bm_pid, SIGKILL);
+ umount_resctrlfs();
+
+ return ret;
+}
diff --git a/tools/testing/selftests/resctrl/resctrlfs.c b/tools/testing/selftests/resctrl/resctrlfs.c
new file mode 100644
index 000000000000..19c0ec4045a4
--- /dev/null
+++ b/tools/testing/selftests/resctrl/resctrlfs.c
@@ -0,0 +1,722 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Basic resctrl file system operations
+ *
+ * Copyright (C) 2018 Intel Corporation
+ *
+ * Authors:
+ * Sai Praneeth Prakhya <sai.praneeth.prakhya@intel.com>,
+ * Fenghua Yu <fenghua.yu@intel.com>
+ */
+#include "resctrl.h"
+
+int tests_run;
+
+static int find_resctrl_mount(char *buffer)
+{
+ FILE *mounts;
+ char line[256], *fs, *mntpoint;
+
+ mounts = fopen("/proc/mounts", "r");
+ if (!mounts) {
+ perror("/proc/mounts");
+ return -ENXIO;
+ }
+ while (!feof(mounts)) {
+ if (!fgets(line, 256, mounts))
+ break;
+ fs = strtok(line, " \t");
+ if (!fs)
+ continue;
+ mntpoint = strtok(NULL, " \t");
+ if (!mntpoint)
+ continue;
+ fs = strtok(NULL, " \t");
+ if (!fs)
+ continue;
+ if (strcmp(fs, "resctrl"))
+ continue;
+
+ fclose(mounts);
+ if (buffer)
+ strncpy(buffer, mntpoint, 256);
+
+ return 0;
+ }
+
+ fclose(mounts);
+
+ return -ENOENT;
+}
+
+char cbm_mask[256];
+
+/*
+ * remount_resctrlfs - Remount resctrl FS at /sys/fs/resctrl
+ * @mum_resctrlfs: Should the resctrl FS be remounted?
+ *
+ * If not mounted, mount it.
+ * If mounted and mum_resctrlfs then remount resctrl FS.
+ * If mounted and !mum_resctrlfs then noop
+ *
+ * Return: 0 on success, non-zero on failure
+ */
+int remount_resctrlfs(bool mum_resctrlfs)
+{
+ char mountpoint[256];
+ int ret;
+
+ ret = find_resctrl_mount(mountpoint);
+ if (ret)
+ strcpy(mountpoint, RESCTRL_PATH);
+
+ if (!ret && mum_resctrlfs && umount(mountpoint)) {
+ printf("not ok unmounting \"%s\"\n", mountpoint);
+ perror("# umount");
+ tests_run++;
+ }
+
+ if (!ret && !mum_resctrlfs)
+ return 0;
+
+ ret = mount("resctrl", RESCTRL_PATH, "resctrl", 0, NULL);
+ printf("%sok mounting resctrl to \"%s\"\n", ret ? "not " : "",
+ RESCTRL_PATH);
+ if (ret)
+ perror("# mount");
+
+ tests_run++;
+
+ return ret;
+}
+
+int umount_resctrlfs(void)
+{
+ if (umount(RESCTRL_PATH)) {
+ perror("# Unable to umount resctrl");
+
+ return errno;
+ }
+
+ return 0;
+}
+
+/*
+ * get_resource_id - Get socket number/l3 id for a specified CPU
+ * @cpu_no: CPU number
+ * @resource_id: Socket number or l3_id
+ *
+ * Return: >= 0 on success, < 0 on failure.
+ */
+int get_resource_id(int cpu_no, int *resource_id)
+{
+ char phys_pkg_path[1024];
+ FILE *fp;
+
+ if (is_amd)
+ sprintf(phys_pkg_path, "%s%d/cache/index3/id",
+ PHYS_ID_PATH, cpu_no);
+ else
+ sprintf(phys_pkg_path, "%s%d/topology/physical_package_id",
+ PHYS_ID_PATH, cpu_no);
+
+ fp = fopen(phys_pkg_path, "r");
+ if (!fp) {
+ perror("Failed to open physical_package_id");
+
+ return -1;
+ }
+ if (fscanf(fp, "%d", resource_id) <= 0) {
+ perror("Could not get socket number or l3 id");
+ fclose(fp);
+
+ return -1;
+ }
+ fclose(fp);
+
+ return 0;
+}
+
+/*
+ * get_cache_size - Get cache size for a specified CPU
+ * @cpu_no: CPU number
+ * @cache_type: Cache level L2/L3
+ * @cache_size: pointer to cache_size
+ *
+ * Return: = 0 on success, < 0 on failure.
+ */
+int get_cache_size(int cpu_no, char *cache_type, unsigned long *cache_size)
+{
+ char cache_path[1024], cache_str[64];
+ int length, i, cache_num;
+ FILE *fp;
+
+ if (!strcmp(cache_type, "L3")) {
+ cache_num = 3;
+ } else if (!strcmp(cache_type, "L2")) {
+ cache_num = 2;
+ } else {
+ perror("Invalid cache level");
+ return -1;
+ }
+
+ sprintf(cache_path, "/sys/bus/cpu/devices/cpu%d/cache/index%d/size",
+ cpu_no, cache_num);
+ fp = fopen(cache_path, "r");
+ if (!fp) {
+ perror("Failed to open cache size");
+
+ return -1;
+ }
+ if (fscanf(fp, "%s", cache_str) <= 0) {
+ perror("Could not get cache_size");
+ fclose(fp);
+
+ return -1;
+ }
+ fclose(fp);
+
+ length = (int)strlen(cache_str);
+
+ *cache_size = 0;
+
+ for (i = 0; i < length; i++) {
+ if ((cache_str[i] >= '0') && (cache_str[i] <= '9'))
+
+ *cache_size = *cache_size * 10 + (cache_str[i] - '0');
+
+ else if (cache_str[i] == 'K')
+
+ *cache_size = *cache_size * 1024;
+
+ else if (cache_str[i] == 'M')
+
+ *cache_size = *cache_size * 1024 * 1024;
+
+ else
+ break;
+ }
+
+ return 0;
+}
+
+#define CORE_SIBLINGS_PATH "/sys/bus/cpu/devices/cpu"
+
+/*
+ * get_cbm_mask - Get cbm mask for given cache
+ * @cache_type: Cache level L2/L3
+ *
+ * Mask is stored in cbm_mask which is global variable.
+ *
+ * Return: = 0 on success, < 0 on failure.
+ */
+int get_cbm_mask(char *cache_type)
+{
+ char cbm_mask_path[1024];
+ FILE *fp;
+
+ sprintf(cbm_mask_path, "%s/%s/cbm_mask", CBM_MASK_PATH, cache_type);
+
+ fp = fopen(cbm_mask_path, "r");
+ if (!fp) {
+ perror("Failed to open cache level");
+
+ return -1;
+ }
+ if (fscanf(fp, "%s", cbm_mask) <= 0) {
+ perror("Could not get max cbm_mask");
+ fclose(fp);
+
+ return -1;
+ }
+ fclose(fp);
+
+ return 0;
+}
+
+/*
+ * get_core_sibling - Get sibling core id from the same socket for given CPU
+ * @cpu_no: CPU number
+ *
+ * Return: > 0 on success, < 0 on failure.
+ */
+int get_core_sibling(int cpu_no)
+{
+ char core_siblings_path[1024], cpu_list_str[64];
+ int sibling_cpu_no = -1;
+ FILE *fp;
+
+ sprintf(core_siblings_path, "%s%d/topology/core_siblings_list",
+ CORE_SIBLINGS_PATH, cpu_no);
+
+ fp = fopen(core_siblings_path, "r");
+ if (!fp) {
+ perror("Failed to open core siblings path");
+
+ return -1;
+ }
+ if (fscanf(fp, "%s", cpu_list_str) <= 0) {
+ perror("Could not get core_siblings list");
+ fclose(fp);
+
+ return -1;
+ }
+ fclose(fp);
+
+ char *token = strtok(cpu_list_str, "-,");
+
+ while (token) {
+ sibling_cpu_no = atoi(token);
+ /* Skipping core 0 as we don't want to run test on core 0 */
+ if (sibling_cpu_no != 0)
+ break;
+ token = strtok(NULL, "-,");
+ }
+
+ return sibling_cpu_no;
+}
+
+/*
+ * taskset_benchmark - Taskset PID (i.e. benchmark) to a specified cpu
+ * @bm_pid: PID that should be binded
+ * @cpu_no: CPU number at which the PID would be binded
+ *
+ * Return: 0 on success, non-zero on failure
+ */
+int taskset_benchmark(pid_t bm_pid, int cpu_no)
+{
+ cpu_set_t my_set;
+
+ CPU_ZERO(&my_set);
+ CPU_SET(cpu_no, &my_set);
+
+ if (sched_setaffinity(bm_pid, sizeof(cpu_set_t), &my_set)) {
+ perror("Unable to taskset benchmark");
+
+ return -1;
+ }
+
+ return 0;
+}
+
+/*
+ * run_benchmark - Run a specified benchmark or fill_buf (default benchmark)
+ * in specified signal. Direct benchmark stdio to /dev/null.
+ * @signum: signal number
+ * @info: signal info
+ * @ucontext: user context in signal handling
+ *
+ * Return: void
+ */
+void run_benchmark(int signum, siginfo_t *info, void *ucontext)
+{
+ int operation, ret, malloc_and_init_memory, memflush;
+ unsigned long span, buffer_span;
+ char **benchmark_cmd;
+ char resctrl_val[64];
+ FILE *fp;
+
+ benchmark_cmd = info->si_ptr;
+
+ /*
+ * Direct stdio of child to /dev/null, so that only parent writes to
+ * stdio (console)
+ */
+ fp = freopen("/dev/null", "w", stdout);
+ if (!fp)
+ PARENT_EXIT("Unable to direct benchmark status to /dev/null");
+
+ if (strcmp(benchmark_cmd[0], "fill_buf") == 0) {
+ /* Execute default fill_buf benchmark */
+ span = strtoul(benchmark_cmd[1], NULL, 10);
+ malloc_and_init_memory = atoi(benchmark_cmd[2]);
+ memflush = atoi(benchmark_cmd[3]);
+ operation = atoi(benchmark_cmd[4]);
+ sprintf(resctrl_val, "%s", benchmark_cmd[5]);
+
+ if (strcmp(resctrl_val, "cqm") != 0)
+ buffer_span = span * MB;
+ else
+ buffer_span = span;
+
+ if (run_fill_buf(buffer_span, malloc_and_init_memory, memflush,
+ operation, resctrl_val))
+ fprintf(stderr, "Error in running fill buffer\n");
+ } else {
+ /* Execute specified benchmark */
+ ret = execvp(benchmark_cmd[0], benchmark_cmd);
+ if (ret)
+ perror("wrong\n");
+ }
+
+ fclose(stdout);
+ PARENT_EXIT("Unable to run specified benchmark");
+}
+
+/*
+ * create_grp - Create a group only if one doesn't exist
+ * @grp_name: Name of the group
+ * @grp: Full path and name of the group
+ * @parent_grp: Full path and name of the parent group
+ *
+ * Return: 0 on success, non-zero on failure
+ */
+static int create_grp(const char *grp_name, char *grp, const char *parent_grp)
+{
+ int found_grp = 0;
+ struct dirent *ep;
+ DIR *dp;
+
+ /*
+ * At this point, we are guaranteed to have resctrl FS mounted and if
+ * length of grp_name == 0, it means, user wants to use root con_mon
+ * grp, so do nothing
+ */
+ if (strlen(grp_name) == 0)
+ return 0;
+
+ /* Check if requested grp exists or not */
+ dp = opendir(parent_grp);
+ if (dp) {
+ while ((ep = readdir(dp)) != NULL) {
+ if (strcmp(ep->d_name, grp_name) == 0)
+ found_grp = 1;
+ }
+ closedir(dp);
+ } else {
+ perror("Unable to open resctrl for group");
+
+ return -1;
+ }
+
+ /* Requested grp doesn't exist, hence create it */
+ if (found_grp == 0) {
+ if (mkdir(grp, 0) == -1) {
+ perror("Unable to create group");
+
+ return -1;
+ }
+ }
+
+ return 0;
+}
+
+static int write_pid_to_tasks(char *tasks, pid_t pid)
+{
+ FILE *fp;
+
+ fp = fopen(tasks, "w");
+ if (!fp) {
+ perror("Failed to open tasks file");
+
+ return -1;
+ }
+ if (fprintf(fp, "%d\n", pid) < 0) {
+ perror("Failed to wr pid to tasks file");
+ fclose(fp);
+
+ return -1;
+ }
+ fclose(fp);
+
+ return 0;
+}
+
+/*
+ * write_bm_pid_to_resctrl - Write a PID (i.e. benchmark) to resctrl FS
+ * @bm_pid: PID that should be written
+ * @ctrlgrp: Name of the control monitor group (con_mon grp)
+ * @mongrp: Name of the monitor group (mon grp)
+ * @resctrl_val: Resctrl feature (Eg: mbm, mba.. etc)
+ *
+ * If a con_mon grp is requested, create it and write pid to it, otherwise
+ * write pid to root con_mon grp.
+ * If a mon grp is requested, create it and write pid to it, otherwise
+ * pid is not written, this means that pid is in con_mon grp and hence
+ * should consult con_mon grp's mon_data directory for results.
+ *
+ * Return: 0 on success, non-zero on failure
+ */
+int write_bm_pid_to_resctrl(pid_t bm_pid, char *ctrlgrp, char *mongrp,
+ char *resctrl_val)
+{
+ char controlgroup[128], monitorgroup[512], monitorgroup_p[256];
+ char tasks[1024];
+ int ret = 0;
+
+ if (strlen(ctrlgrp))
+ sprintf(controlgroup, "%s/%s", RESCTRL_PATH, ctrlgrp);
+ else
+ sprintf(controlgroup, "%s", RESCTRL_PATH);
+
+ /* Create control and monitoring group and write pid into it */
+ ret = create_grp(ctrlgrp, controlgroup, RESCTRL_PATH);
+ if (ret)
+ goto out;
+ sprintf(tasks, "%s/tasks", controlgroup);
+ ret = write_pid_to_tasks(tasks, bm_pid);
+ if (ret)
+ goto out;
+
+ /* Create mon grp and write pid into it for "mbm" and "cqm" test */
+ if ((strcmp(resctrl_val, "cqm") == 0) ||
+ (strcmp(resctrl_val, "mbm") == 0)) {
+ if (strlen(mongrp)) {
+ sprintf(monitorgroup_p, "%s/mon_groups", controlgroup);
+ sprintf(monitorgroup, "%s/%s", monitorgroup_p, mongrp);
+ ret = create_grp(mongrp, monitorgroup, monitorgroup_p);
+ if (ret)
+ goto out;
+
+ sprintf(tasks, "%s/mon_groups/%s/tasks",
+ controlgroup, mongrp);
+ ret = write_pid_to_tasks(tasks, bm_pid);
+ if (ret)
+ goto out;
+ }
+ }
+
+out:
+ printf("%sok writing benchmark parameters to resctrl FS\n",
+ ret ? "not " : "");
+ if (ret)
+ perror("# writing to resctrlfs");
+
+ tests_run++;
+
+ return ret;
+}
+
+/*
+ * write_schemata - Update schemata of a con_mon grp
+ * @ctrlgrp: Name of the con_mon grp
+ * @schemata: Schemata that should be updated to
+ * @cpu_no: CPU number that the benchmark PID is binded to
+ * @resctrl_val: Resctrl feature (Eg: mbm, mba.. etc)
+ *
+ * Update schemata of a con_mon grp *only* if requested resctrl feature is
+ * allocation type
+ *
+ * Return: 0 on success, non-zero on failure
+ */
+int write_schemata(char *ctrlgrp, char *schemata, int cpu_no, char *resctrl_val)
+{
+ char controlgroup[1024], schema[1024], reason[64];
+ int resource_id, ret = 0;
+ FILE *fp;
+
+ if ((strcmp(resctrl_val, "mba") != 0) &&
+ (strcmp(resctrl_val, "cat") != 0) &&
+ (strcmp(resctrl_val, "cqm") != 0))
+ return -ENOENT;
+
+ if (!schemata) {
+ printf("# Skipping empty schemata update\n");
+
+ return -1;
+ }
+
+ if (get_resource_id(cpu_no, &resource_id) < 0) {
+ sprintf(reason, "Failed to get resource id");
+ ret = -1;
+
+ goto out;
+ }
+
+ if (strlen(ctrlgrp) != 0)
+ sprintf(controlgroup, "%s/%s/schemata", RESCTRL_PATH, ctrlgrp);
+ else
+ sprintf(controlgroup, "%s/schemata", RESCTRL_PATH);
+
+ if (!strcmp(resctrl_val, "cat") || !strcmp(resctrl_val, "cqm"))
+ sprintf(schema, "%s%d%c%s", "L3:", resource_id, '=', schemata);
+ if (strcmp(resctrl_val, "mba") == 0)
+ sprintf(schema, "%s%d%c%s", "MB:", resource_id, '=', schemata);
+
+ fp = fopen(controlgroup, "w");
+ if (!fp) {
+ sprintf(reason, "Failed to open control group");
+ ret = -1;
+
+ goto out;
+ }
+
+ if (fprintf(fp, "%s\n", schema) < 0) {
+ sprintf(reason, "Failed to write schemata in control group");
+ fclose(fp);
+ ret = -1;
+
+ goto out;
+ }
+ fclose(fp);
+
+out:
+ printf("%sok Write schema \"%s\" to resctrl FS%s%s\n",
+ ret ? "not " : "", schema, ret ? " # " : "",
+ ret ? reason : "");
+ tests_run++;
+
+ return ret;
+}
+
+bool check_resctrlfs_support(void)
+{
+ FILE *inf = fopen("/proc/filesystems", "r");
+ DIR *dp;
+ char *res;
+ bool ret = false;
+
+ if (!inf)
+ return false;
+
+ res = fgrep(inf, "nodev\tresctrl\n");
+
+ if (res) {
+ ret = true;
+ free(res);
+ }
+
+ fclose(inf);
+
+ printf("%sok kernel supports resctrl filesystem\n", ret ? "" : "not ");
+ tests_run++;
+
+ dp = opendir(RESCTRL_PATH);
+ printf("%sok resctrl mountpoint \"%s\" exists\n",
+ dp ? "" : "not ", RESCTRL_PATH);
+ if (dp)
+ closedir(dp);
+ tests_run++;
+
+ printf("# resctrl filesystem %s mounted\n",
+ find_resctrl_mount(NULL) ? "not" : "is");
+
+ return ret;
+}
+
+char *fgrep(FILE *inf, const char *str)
+{
+ char line[256];
+ int slen = strlen(str);
+
+ while (!feof(inf)) {
+ if (!fgets(line, 256, inf))
+ break;
+ if (strncmp(line, str, slen))
+ continue;
+
+ return strdup(line);
+ }
+
+ return NULL;
+}
+
+/*
+ * validate_resctrl_feature_request - Check if requested feature is valid.
+ * @resctrl_val: Requested feature
+ *
+ * Return: 0 on success, non-zero on failure
+ */
+bool validate_resctrl_feature_request(char *resctrl_val)
+{
+ FILE *inf = fopen("/proc/cpuinfo", "r");
+ bool found = false;
+ char *res;
+
+ if (!inf)
+ return false;
+
+ res = fgrep(inf, "flags");
+
+ if (res) {
+ char *s = strchr(res, ':');
+
+ found = s && !strstr(s, resctrl_val);
+ free(res);
+ }
+ fclose(inf);
+
+ return found;
+}
+
+int filter_dmesg(void)
+{
+ char line[1024];
+ FILE *fp;
+ int pipefds[2];
+ pid_t pid;
+ int ret;
+
+ ret = pipe(pipefds);
+ if (ret) {
+ perror("pipe");
+ return ret;
+ }
+ pid = fork();
+ if (pid == 0) {
+ close(pipefds[0]);
+ dup2(pipefds[1], STDOUT_FILENO);
+ execlp("dmesg", "dmesg", NULL);
+ perror("executing dmesg");
+ exit(1);
+ }
+ close(pipefds[1]);
+ fp = fdopen(pipefds[0], "r");
+ if (!fp) {
+ perror("fdopen(pipe)");
+ kill(pid, SIGTERM);
+
+ return -1;
+ }
+
+ while (fgets(line, 1024, fp)) {
+ if (strstr(line, "intel_rdt:"))
+ printf("# dmesg: %s", line);
+ if (strstr(line, "resctrl:"))
+ printf("# dmesg: %s", line);
+ }
+ fclose(fp);
+ waitpid(pid, NULL, 0);
+
+ return 0;
+}
+
+int validate_bw_report_request(char *bw_report)
+{
+ if (strcmp(bw_report, "reads") == 0)
+ return 0;
+ if (strcmp(bw_report, "writes") == 0)
+ return 0;
+ if (strcmp(bw_report, "nt-writes") == 0) {
+ strcpy(bw_report, "writes");
+ return 0;
+ }
+ if (strcmp(bw_report, "total") == 0)
+ return 0;
+
+ fprintf(stderr, "Requested iMC B/W report type unavailable\n");
+
+ return -1;
+}
+
+int perf_event_open(struct perf_event_attr *hw_event, pid_t pid, int cpu,
+ int group_fd, unsigned long flags)
+{
+ int ret;
+
+ ret = syscall(__NR_perf_event_open, hw_event, pid, cpu,
+ group_fd, flags);
+ return ret;
+}
+
+unsigned int count_bits(unsigned long n)
+{
+ unsigned int count = 0;
+
+ while (n) {
+ count += n & 1;
+ n >>= 1;
+ }
+
+ return count;
+}
diff --git a/tools/testing/selftests/rseq/.gitignore b/tools/testing/selftests/rseq/.gitignore
index cc610da7e369..5910888ebfe1 100644
--- a/tools/testing/selftests/rseq/.gitignore
+++ b/tools/testing/selftests/rseq/.gitignore
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
basic_percpu_ops_test
basic_test
basic_rseq_op_test
diff --git a/tools/testing/selftests/rtc/.gitignore b/tools/testing/selftests/rtc/.gitignore
index d0ad44f6294a..fb2d533aa575 100644
--- a/tools/testing/selftests/rtc/.gitignore
+++ b/tools/testing/selftests/rtc/.gitignore
@@ -1,2 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0-only
rtctest
setdate
diff --git a/tools/testing/selftests/safesetid/.gitignore b/tools/testing/selftests/safesetid/.gitignore
index 9c1a629bca01..25d3db172907 100644
--- a/tools/testing/selftests/safesetid/.gitignore
+++ b/tools/testing/selftests/safesetid/.gitignore
@@ -1 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
safesetid-test
diff --git a/tools/testing/selftests/seccomp/.gitignore b/tools/testing/selftests/seccomp/.gitignore
index 5af29d3a1b0a..dec678577f9c 100644
--- a/tools/testing/selftests/seccomp/.gitignore
+++ b/tools/testing/selftests/seccomp/.gitignore
@@ -1,2 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0-only
seccomp_bpf
seccomp_benchmark
diff --git a/tools/testing/selftests/seccomp/Makefile b/tools/testing/selftests/seccomp/Makefile
index 1760b3e39730..0ebfe8b0e147 100644
--- a/tools/testing/selftests/seccomp/Makefile
+++ b/tools/testing/selftests/seccomp/Makefile
@@ -1,17 +1,6 @@
# SPDX-License-Identifier: GPL-2.0
-all:
-
-include ../lib.mk
-
-.PHONY: all clean
-
-BINARIES := seccomp_bpf seccomp_benchmark
CFLAGS += -Wl,-no-as-needed -Wall
+LDFLAGS += -lpthread
-seccomp_bpf: seccomp_bpf.c ../kselftest_harness.h
- $(CC) $(CFLAGS) $(LDFLAGS) $< -lpthread -o $@
-
-TEST_PROGS += $(BINARIES)
-EXTRA_CLEAN := $(BINARIES)
-
-all: $(BINARIES)
+TEST_GEN_PROGS := seccomp_bpf seccomp_benchmark
+include ../lib.mk
diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c
index ee1b727ede04..c0aa46ce14f6 100644
--- a/tools/testing/selftests/seccomp/seccomp_bpf.c
+++ b/tools/testing/selftests/seccomp/seccomp_bpf.c
@@ -212,6 +212,10 @@ struct seccomp_notif_sizes {
#define SECCOMP_USER_NOTIF_FLAG_CONTINUE 0x00000001
#endif
+#ifndef SECCOMP_FILTER_FLAG_TSYNC_ESRCH
+#define SECCOMP_FILTER_FLAG_TSYNC_ESRCH (1UL << 4)
+#endif
+
#ifndef seccomp
int seccomp(unsigned int op, unsigned int flags, void *args)
{
@@ -909,7 +913,7 @@ TEST(ERRNO_order)
EXPECT_EQ(12, errno);
}
-FIXTURE_DATA(TRAP) {
+FIXTURE(TRAP) {
struct sock_fprog prog;
};
@@ -1020,7 +1024,7 @@ TEST_F(TRAP, handler)
EXPECT_NE(0, (unsigned long)sigsys->_call_addr);
}
-FIXTURE_DATA(precedence) {
+FIXTURE(precedence) {
struct sock_fprog allow;
struct sock_fprog log;
struct sock_fprog trace;
@@ -1509,7 +1513,7 @@ void tracer_poke(struct __test_metadata *_metadata, pid_t tracee, int status,
EXPECT_EQ(0, ret);
}
-FIXTURE_DATA(TRACE_poke) {
+FIXTURE(TRACE_poke) {
struct sock_fprog prog;
pid_t tracer;
long poked;
@@ -1817,7 +1821,7 @@ void tracer_ptrace(struct __test_metadata *_metadata, pid_t tracee,
change_syscall(_metadata, tracee, -1, -ESRCH);
}
-FIXTURE_DATA(TRACE_syscall) {
+FIXTURE(TRACE_syscall) {
struct sock_fprog prog;
pid_t tracer, mytid, mypid, parent;
};
@@ -2187,7 +2191,8 @@ TEST(detect_seccomp_filter_flags)
unsigned int flags[] = { SECCOMP_FILTER_FLAG_TSYNC,
SECCOMP_FILTER_FLAG_LOG,
SECCOMP_FILTER_FLAG_SPEC_ALLOW,
- SECCOMP_FILTER_FLAG_NEW_LISTENER };
+ SECCOMP_FILTER_FLAG_NEW_LISTENER,
+ SECCOMP_FILTER_FLAG_TSYNC_ESRCH };
unsigned int exclusive[] = {
SECCOMP_FILTER_FLAG_TSYNC,
SECCOMP_FILTER_FLAG_NEW_LISTENER };
@@ -2321,7 +2326,7 @@ struct tsync_sibling {
} \
} while (0)
-FIXTURE_DATA(TSYNC) {
+FIXTURE(TSYNC) {
struct sock_fprog root_prog, apply_prog;
struct tsync_sibling sibling[TSYNC_SIBLINGS];
sem_t started;
@@ -2645,6 +2650,55 @@ TEST_F(TSYNC, two_siblings_with_one_divergence)
EXPECT_EQ(SIBLING_EXIT_UNKILLED, (long)status);
}
+TEST_F(TSYNC, two_siblings_with_one_divergence_no_tid_in_err)
+{
+ long ret, flags;
+ void *status;
+
+ ASSERT_EQ(0, prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0)) {
+ TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!");
+ }
+
+ ret = seccomp(SECCOMP_SET_MODE_FILTER, 0, &self->root_prog);
+ ASSERT_NE(ENOSYS, errno) {
+ TH_LOG("Kernel does not support seccomp syscall!");
+ }
+ ASSERT_EQ(0, ret) {
+ TH_LOG("Kernel does not support SECCOMP_SET_MODE_FILTER!");
+ }
+ self->sibling[0].diverge = 1;
+ tsync_start_sibling(&self->sibling[0]);
+ tsync_start_sibling(&self->sibling[1]);
+
+ while (self->sibling_count < TSYNC_SIBLINGS) {
+ sem_wait(&self->started);
+ self->sibling_count++;
+ }
+
+ flags = SECCOMP_FILTER_FLAG_TSYNC | \
+ SECCOMP_FILTER_FLAG_TSYNC_ESRCH;
+ ret = seccomp(SECCOMP_SET_MODE_FILTER, flags, &self->apply_prog);
+ ASSERT_EQ(ESRCH, errno) {
+ TH_LOG("Did not return ESRCH for diverged sibling.");
+ }
+ ASSERT_EQ(-1, ret) {
+ TH_LOG("Did not fail on diverged sibling.");
+ }
+
+ /* Wake the threads */
+ pthread_mutex_lock(&self->mutex);
+ ASSERT_EQ(0, pthread_cond_broadcast(&self->cond)) {
+ TH_LOG("cond broadcast non-zero");
+ }
+ pthread_mutex_unlock(&self->mutex);
+
+ /* Ensure they are both unkilled. */
+ PTHREAD_JOIN(self->sibling[0].tid, &status);
+ EXPECT_EQ(SIBLING_EXIT_UNKILLED, (long)status);
+ PTHREAD_JOIN(self->sibling[1].tid, &status);
+ EXPECT_EQ(SIBLING_EXIT_UNKILLED, (long)status);
+}
+
TEST_F(TSYNC, two_siblings_not_under_filter)
{
long ret, sib;
@@ -2749,12 +2803,13 @@ TEST(syscall_restart)
offsetof(struct seccomp_data, nr)),
#ifdef __NR_sigreturn
- BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_sigreturn, 6, 0),
+ BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_sigreturn, 7, 0),
#endif
- BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_read, 5, 0),
- BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_exit, 4, 0),
- BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_rt_sigreturn, 3, 0),
- BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_nanosleep, 4, 0),
+ BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_read, 6, 0),
+ BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_exit, 5, 0),
+ BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_rt_sigreturn, 4, 0),
+ BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_nanosleep, 5, 0),
+ BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_clock_nanosleep, 4, 0),
BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_restart_syscall, 4, 0),
/* Allow __NR_write for easy logging. */
@@ -2841,7 +2896,8 @@ TEST(syscall_restart)
ASSERT_EQ(PTRACE_EVENT_SECCOMP, (status >> 16));
ASSERT_EQ(0, ptrace(PTRACE_GETEVENTMSG, child_pid, NULL, &msg));
ASSERT_EQ(0x100, msg);
- EXPECT_EQ(__NR_nanosleep, get_syscall(_metadata, child_pid));
+ ret = get_syscall(_metadata, child_pid);
+ EXPECT_TRUE(ret == __NR_nanosleep || ret == __NR_clock_nanosleep);
/* Might as well check siginfo for sanity while we're here. */
ASSERT_EQ(0, ptrace(PTRACE_GETSIGINFO, child_pid, NULL, &info));
@@ -3196,6 +3252,24 @@ TEST(user_notification_basic)
EXPECT_EQ(0, WEXITSTATUS(status));
}
+TEST(user_notification_with_tsync)
+{
+ int ret;
+ unsigned int flags;
+
+ /* these were exclusive */
+ flags = SECCOMP_FILTER_FLAG_NEW_LISTENER |
+ SECCOMP_FILTER_FLAG_TSYNC;
+ ASSERT_EQ(-1, user_trap_syscall(__NR_getppid, flags));
+ ASSERT_EQ(EINVAL, errno);
+
+ /* but now they're not */
+ flags |= SECCOMP_FILTER_FLAG_TSYNC_ESRCH;
+ ret = user_trap_syscall(__NR_getppid, flags);
+ close(ret);
+ ASSERT_LE(0, ret);
+}
+
TEST(user_notification_kill_in_middle)
{
pid_t pid;
diff --git a/tools/testing/selftests/sigaltstack/.gitignore b/tools/testing/selftests/sigaltstack/.gitignore
index 35897b0a3f44..50a19a8888ce 100644
--- a/tools/testing/selftests/sigaltstack/.gitignore
+++ b/tools/testing/selftests/sigaltstack/.gitignore
@@ -1 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
sas
diff --git a/tools/testing/selftests/size/.gitignore b/tools/testing/selftests/size/.gitignore
index 189b7818de34..923e18eed1a0 100644
--- a/tools/testing/selftests/size/.gitignore
+++ b/tools/testing/selftests/size/.gitignore
@@ -1 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
get_size
diff --git a/tools/testing/selftests/sparc64/drivers/.gitignore b/tools/testing/selftests/sparc64/drivers/.gitignore
index 90e835ed74e6..0331f77373b5 100644
--- a/tools/testing/selftests/sparc64/drivers/.gitignore
+++ b/tools/testing/selftests/sparc64/drivers/.gitignore
@@ -1 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
adi-test
diff --git a/tools/testing/selftests/splice/.gitignore b/tools/testing/selftests/splice/.gitignore
index 1e23fefd68e8..d5a2da428752 100644
--- a/tools/testing/selftests/splice/.gitignore
+++ b/tools/testing/selftests/splice/.gitignore
@@ -1 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
default_file_splice_read
diff --git a/tools/testing/selftests/sync/.gitignore b/tools/testing/selftests/sync/.gitignore
index f5091e7792f2..f1152357712f 100644
--- a/tools/testing/selftests/sync/.gitignore
+++ b/tools/testing/selftests/sync/.gitignore
@@ -1 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
sync_test
diff --git a/tools/testing/selftests/sysctl/config b/tools/testing/selftests/sysctl/config
index 6ca14800d755..fc263efd1fad 100644
--- a/tools/testing/selftests/sysctl/config
+++ b/tools/testing/selftests/sysctl/config
@@ -1 +1 @@
-CONFIG_TEST_SYSCTL=y
+CONFIG_TEST_SYSCTL=m
diff --git a/tools/testing/selftests/sysctl/sysctl.sh b/tools/testing/selftests/sysctl/sysctl.sh
index 6a970b127c9b..19515dcb7d04 100755
--- a/tools/testing/selftests/sysctl/sysctl.sh
+++ b/tools/testing/selftests/sysctl/sysctl.sh
@@ -39,16 +39,7 @@ ALL_TESTS="$ALL_TESTS 0003:1:1:int_0002"
ALL_TESTS="$ALL_TESTS 0004:1:1:uint_0001"
ALL_TESTS="$ALL_TESTS 0005:3:1:int_0003"
ALL_TESTS="$ALL_TESTS 0006:50:1:bitmap_0001"
-
-test_modprobe()
-{
- if [ ! -d $DIR ]; then
- echo "$0: $DIR not present" >&2
- echo "You must have the following enabled in your kernel:" >&2
- cat $TEST_DIR/config >&2
- exit $ksft_skip
- fi
-}
+ALL_TESTS="$ALL_TESTS 0007:1:1:boot_int"
function allow_user_defaults()
{
@@ -122,13 +113,15 @@ test_reqs()
function load_req_mod()
{
- if [ ! -d $DIR ]; then
+ if [ ! -d $SYSCTL ]; then
if ! modprobe -q -n $TEST_DRIVER; then
echo "$0: module $TEST_DRIVER not found [SKIP]"
+ echo "You must set CONFIG_TEST_SYSCTL=m in your kernel" >&2
exit $ksft_skip
fi
modprobe $TEST_DRIVER
if [ $? -ne 0 ]; then
+ echo "$0: modprobe $TEST_DRIVER failed."
exit
fi
fi
@@ -752,6 +745,46 @@ sysctl_test_0006()
run_bitmaptest
}
+sysctl_test_0007()
+{
+ TARGET="${SYSCTL}/boot_int"
+ if [ ! -f $TARGET ]; then
+ echo "Skipping test for $TARGET as it is not present ..."
+ return $ksft_skip
+ fi
+
+ if [ -d $DIR ]; then
+ echo "Boot param test only possible sysctl_test is built-in, not module:"
+ cat $TEST_DIR/config >&2
+ return $ksft_skip
+ fi
+
+ echo -n "Testing if $TARGET is set to 1 ..."
+ ORIG=$(cat "${TARGET}")
+
+ if [ x$ORIG = "x1" ]; then
+ echo "ok"
+ return 0
+ fi
+ echo "FAIL"
+ echo "Checking if /proc/cmdline contains setting of the expected parameter ..."
+ if [ ! -f /proc/cmdline ]; then
+ echo "/proc/cmdline does not exist, test inconclusive"
+ return 0
+ fi
+
+ FOUND=$(grep -c "sysctl[./]debug[./]test_sysctl[./]boot_int=1" /proc/cmdline)
+ if [ $FOUND = "1" ]; then
+ echo "Kernel param found but $TARGET is not 1, TEST FAILED"
+ rc=1
+ test_rc
+ fi
+
+ echo "Skipping test, expected kernel parameter missing."
+ echo "To perform this test, make sure kernel is booted with parameter: sysctl.debug.test_sysctl.boot_int=1"
+ return $ksft_skip
+}
+
list_tests()
{
echo "Test ID list:"
@@ -766,6 +799,7 @@ list_tests()
echo "0004 x $(get_test_count 0004) - tests proc_douintvec()"
echo "0005 x $(get_test_count 0005) - tests proc_douintvec() array"
echo "0006 x $(get_test_count 0006) - tests proc_do_large_bitmap()"
+ echo "0007 x $(get_test_count 0007) - tests setting sysctl from kernel boot param"
}
usage()
@@ -929,7 +963,6 @@ test_reqs
allow_user_defaults
check_production_sysctl_writes_strict
load_req_mod
-test_modprobe
trap "test_finish" EXIT
diff --git a/tools/testing/selftests/tc-testing/.gitignore b/tools/testing/selftests/tc-testing/.gitignore
index c26d72e0166f..d52f65de23b4 100644
--- a/tools/testing/selftests/tc-testing/.gitignore
+++ b/tools/testing/selftests/tc-testing/.gitignore
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
__pycache__/
*.pyc
plugins/
diff --git a/tools/testing/selftests/tc-testing/config b/tools/testing/selftests/tc-testing/config
index c03af4600281..c33a7aac27ff 100644
--- a/tools/testing/selftests/tc-testing/config
+++ b/tools/testing/selftests/tc-testing/config
@@ -31,6 +31,7 @@ CONFIG_NET_EMATCH_U32=m
CONFIG_NET_EMATCH_META=m
CONFIG_NET_EMATCH_TEXT=m
CONFIG_NET_EMATCH_IPSET=m
+CONFIG_NET_EMATCH_CANID=m
CONFIG_NET_EMATCH_IPT=m
CONFIG_NET_CLS_ACT=y
CONFIG_NET_ACT_POLICE=m
@@ -58,3 +59,8 @@ CONFIG_NET_IFE_SKBPRIO=m
CONFIG_NET_IFE_SKBTCINDEX=m
CONFIG_NET_SCH_FIFO=y
CONFIG_NET_SCH_ETS=m
+
+#
+## Network testing
+#
+CONFIG_CAN=m
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/pedit.json b/tools/testing/selftests/tc-testing/tc-tests/actions/pedit.json
index f8ea6f5fa8e9..72cdc3c800a5 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/pedit.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/pedit.json
@@ -1472,6 +1472,31 @@
]
},
{
+ "id": "94bb",
+ "name": "Add pedit action with LAYERED_OP ip6 traffic_class",
+ "category": [
+ "actions",
+ "pedit",
+ "layered_op"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action pedit",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action pedit ex munge ip6 traffic_class set 0x40 continue",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions list action pedit",
+ "matchPattern": "ipv6\\+0: val 04000000 mask f00fffff",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action pedit"
+ ]
+ },
+ {
"id": "6f5e",
"name": "Add pedit action with LAYERED_OP ip6 flow_lbl",
"category": [
diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/basic.json b/tools/testing/selftests/tc-testing/tc-tests/filters/basic.json
index 98a20faf3198..e788c114a484 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/filters/basic.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/filters/basic.json
@@ -372,5 +372,907 @@
"teardown": [
"$TC qdisc del dev $DEV1 ingress"
]
+ },
+ {
+ "id": "bae4",
+ "name": "Add basic filter with u32 ematch u8/zero offset and default action",
+ "category": [
+ "filter",
+ "basic"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$TC qdisc add dev $DEV1 ingress"
+ ],
+ "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u8 0x11 0x0f at 0)' classid 1:1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic",
+ "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(01000000/0f000000 at 0\\)",
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DEV1 ingress"
+ ]
+ },
+ {
+ "id": "e6cb",
+ "name": "Add basic filter with u32 ematch u8/zero offset and invalid value >0xFF",
+ "category": [
+ "filter",
+ "basic"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$TC qdisc add dev $DEV1 ingress"
+ ],
+ "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u8 0x1122 0x0f at 0)' classid 1:1",
+ "expExitCode": "1",
+ "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic",
+ "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(11220000/0f000000 at 0\\)",
+ "matchCount": "0",
+ "teardown": [
+ "$TC qdisc del dev $DEV1 ingress"
+ ]
+ },
+ {
+ "id": "7727",
+ "name": "Add basic filter with u32 ematch u8/positive offset and default action",
+ "category": [
+ "filter",
+ "basic"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$TC qdisc add dev $DEV1 ingress"
+ ],
+ "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u8 0x77 0x1f at 12)' classid 1:1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic",
+ "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(17000000/1f000000 at 12\\)",
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DEV1 ingress"
+ ]
+ },
+ {
+ "id": "a429",
+ "name": "Add basic filter with u32 ematch u8/invalid mask >0xFF",
+ "category": [
+ "filter",
+ "basic"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$TC qdisc add dev $DEV1 ingress"
+ ],
+ "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u8 0x77 0xff00 at 12)' classid 1:1",
+ "expExitCode": "1",
+ "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic",
+ "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(77000000/ff000000 at 12\\)",
+ "matchCount": "0",
+ "teardown": [
+ "$TC qdisc del dev $DEV1 ingress"
+ ]
+ },
+ {
+ "id": "8373",
+ "name": "Add basic filter with u32 ematch u8/missing offset",
+ "category": [
+ "filter",
+ "basic"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$TC qdisc add dev $DEV1 ingress"
+ ],
+ "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u8 0x77 0xff at)' classid 1:1",
+ "expExitCode": "1",
+ "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic",
+ "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(77000000 at 12\\)",
+ "matchCount": "0",
+ "teardown": [
+ "$TC qdisc del dev $DEV1 ingress"
+ ]
+ },
+ {
+ "id": "ab8e",
+ "name": "Add basic filter with u32 ematch u8/missing AT keyword",
+ "category": [
+ "filter",
+ "basic"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$TC qdisc add dev $DEV1 ingress"
+ ],
+ "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u8 0x77 0xff 0)' classid 1:1",
+ "expExitCode": "1",
+ "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic",
+ "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(77000000 at 12\\)",
+ "matchCount": "0",
+ "teardown": [
+ "$TC qdisc del dev $DEV1 ingress"
+ ]
+ },
+ {
+ "id": "712d",
+ "name": "Add basic filter with u32 ematch u8/missing value",
+ "category": [
+ "filter",
+ "basic"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$TC qdisc add dev $DEV1 ingress"
+ ],
+ "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u8 at 12)' classid 1:1",
+ "expExitCode": "1",
+ "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic",
+ "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(at 12\\)",
+ "matchCount": "0",
+ "teardown": [
+ "$TC qdisc del dev $DEV1 ingress"
+ ]
+ },
+ {
+ "id": "350f",
+ "name": "Add basic filter with u32 ematch u8/non-numeric value",
+ "category": [
+ "filter",
+ "basic"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$TC qdisc add dev $DEV1 ingress"
+ ],
+ "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u8 zero 0xff at 0)' classid 1:1",
+ "expExitCode": "1",
+ "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic",
+ "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(00000000/ff000000 at 0\\)",
+ "matchCount": "0",
+ "teardown": [
+ "$TC qdisc del dev $DEV1 ingress"
+ ]
+ },
+ {
+ "id": "e28f",
+ "name": "Add basic filter with u32 ematch u8/non-numeric mask",
+ "category": [
+ "filter",
+ "basic"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$TC qdisc add dev $DEV1 ingress"
+ ],
+ "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u8 0x11 mask at 0)' classid 1:1",
+ "expExitCode": "1",
+ "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic",
+ "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(11000000/00000000 at 0\\)",
+ "matchCount": "0",
+ "teardown": [
+ "$TC qdisc del dev $DEV1 ingress"
+ ]
+ },
+ {
+ "id": "6d5f",
+ "name": "Add basic filter with u32 ematch u8/negative offset and default action",
+ "category": [
+ "filter",
+ "basic"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$TC qdisc add dev $DEV1 ingress"
+ ],
+ "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u8 0xaa 0xf0 at -14)' classid 1:1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic",
+ "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(0000a000/0000f000 at -16\\)",
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DEV1 ingress"
+ ]
+ },
+ {
+ "id": "12dc",
+ "name": "Add basic filter with u32 ematch u8/nexthdr+ offset and default action",
+ "category": [
+ "filter",
+ "basic"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$TC qdisc add dev $DEV1 ingress"
+ ],
+ "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u8 0xaa 0xf0 at nexthdr+0)' classid 1:1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic",
+ "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(a0000000/f0000000 at nexthdr\\+0\\)",
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DEV1 ingress"
+ ]
+ },
+ {
+ "id": "1d85",
+ "name": "Add basic filter with u32 ematch u16/zero offset and default action",
+ "category": [
+ "filter",
+ "basic"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$TC qdisc add dev $DEV1 ingress"
+ ],
+ "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u16 0x1122 0xffff at 0)' classid 1:1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic",
+ "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(11220000/ffff0000 at 0\\)",
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DEV1 ingress"
+ ]
+ },
+ {
+ "id": "3672",
+ "name": "Add basic filter with u32 ematch u16/zero offset and invalid value >0xFFFF",
+ "category": [
+ "filter",
+ "basic"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$TC qdisc add dev $DEV1 ingress"
+ ],
+ "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u16 0x112233 0xffff at 0)' classid 1:1",
+ "expExitCode": "1",
+ "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic",
+ "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(11223300/ffff0000 at 0\\)",
+ "matchCount": "0",
+ "teardown": [
+ "$TC qdisc del dev $DEV1 ingress"
+ ]
+ },
+ {
+ "id": "7fb0",
+ "name": "Add basic filter with u32 ematch u16/positive offset and default action",
+ "category": [
+ "filter",
+ "basic"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$TC qdisc add dev $DEV1 ingress"
+ ],
+ "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u16 0x7788 0x1fff at 12)' classid 1:1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic",
+ "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(17880000/1fff0000 at 12\\)",
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DEV1 ingress"
+ ]
+ },
+ {
+ "id": "19af",
+ "name": "Add basic filter with u32 ematch u16/invalid mask >0xFFFF",
+ "category": [
+ "filter",
+ "basic"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$TC qdisc add dev $DEV1 ingress"
+ ],
+ "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u16 0x7788 0xffffffff at 12)' classid 1:1",
+ "expExitCode": "1",
+ "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic",
+ "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(77880000/ffffffff at 12\\)",
+ "matchCount": "0",
+ "teardown": [
+ "$TC qdisc del dev $DEV1 ingress"
+ ]
+ },
+ {
+ "id": "446d",
+ "name": "Add basic filter with u32 ematch u16/missing offset",
+ "category": [
+ "filter",
+ "basic"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$TC qdisc add dev $DEV1 ingress"
+ ],
+ "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u16 0x7788 0xffff at)' classid 1:1",
+ "expExitCode": "1",
+ "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic",
+ "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(77880000 at 12\\)",
+ "matchCount": "0",
+ "teardown": [
+ "$TC qdisc del dev $DEV1 ingress"
+ ]
+ },
+ {
+ "id": "151b",
+ "name": "Add basic filter with u32 ematch u16/missing AT keyword",
+ "category": [
+ "filter",
+ "basic"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$TC qdisc add dev $DEV1 ingress"
+ ],
+ "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u16 0x7788 0xffff 0)' classid 1:1",
+ "expExitCode": "1",
+ "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic",
+ "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(77880000/ffff0000 at 0\\)",
+ "matchCount": "0",
+ "teardown": [
+ "$TC qdisc del dev $DEV1 ingress"
+ ]
+ },
+ {
+ "id": "bb23",
+ "name": "Add basic filter with u32 ematch u16/missing value",
+ "category": [
+ "filter",
+ "basic"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$TC qdisc add dev $DEV1 ingress"
+ ],
+ "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u16 at 12)' classid 1:1",
+ "expExitCode": "1",
+ "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic",
+ "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(at 12\\)",
+ "matchCount": "0",
+ "teardown": [
+ "$TC qdisc del dev $DEV1 ingress"
+ ]
+ },
+ {
+ "id": "decc",
+ "name": "Add basic filter with u32 ematch u16/non-numeric value",
+ "category": [
+ "filter",
+ "basic"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$TC qdisc add dev $DEV1 ingress"
+ ],
+ "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u16 zero 0xffff at 0)' classid 1:1",
+ "expExitCode": "1",
+ "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic",
+ "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(00000000/ffff0000 at 0\\)",
+ "matchCount": "0",
+ "teardown": [
+ "$TC qdisc del dev $DEV1 ingress"
+ ]
+ },
+ {
+ "id": "e988",
+ "name": "Add basic filter with u32 ematch u16/non-numeric mask",
+ "category": [
+ "filter",
+ "basic"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$TC qdisc add dev $DEV1 ingress"
+ ],
+ "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u8 0x1122 mask at 0)' classid 1:1",
+ "expExitCode": "1",
+ "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic",
+ "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(11220000/00000000 at 0\\)",
+ "matchCount": "0",
+ "teardown": [
+ "$TC qdisc del dev $DEV1 ingress"
+ ]
+ },
+ {
+ "id": "07d8",
+ "name": "Add basic filter with u32 ematch u16/negative offset and default action",
+ "category": [
+ "filter",
+ "basic"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$TC qdisc add dev $DEV1 ingress"
+ ],
+ "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u16 0xaabb 0xffff at -12)' classid 1:1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic",
+ "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(aabb0000/ffff0000 at -12\\)",
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DEV1 ingress"
+ ]
+ },
+ {
+ "id": "f474",
+ "name": "Add basic filter with u32 ematch u16/nexthdr+ offset and default action",
+ "category": [
+ "filter",
+ "basic"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$TC qdisc add dev $DEV1 ingress"
+ ],
+ "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u16 0xaabb 0xf0f0 at nexthdr+0)' classid 1:1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic",
+ "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(a0b00000/f0f00000 at nexthdr\\+0\\)",
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DEV1 ingress"
+ ]
+ },
+ {
+ "id": "47a0",
+ "name": "Add basic filter with u32 ematch u32/zero offset and default action",
+ "category": [
+ "filter",
+ "basic"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$TC qdisc add dev $DEV1 ingress"
+ ],
+ "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u32 0xaabbccdd 0xffffffff at 0)' classid 1:1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic",
+ "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(aabbccdd/ffffffff at 0\\)",
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DEV1 ingress"
+ ]
+ },
+ {
+ "id": "849f",
+ "name": "Add basic filter with u32 ematch u32/positive offset and default action",
+ "category": [
+ "filter",
+ "basic"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$TC qdisc add dev $DEV1 ingress"
+ ],
+ "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u32 0x11227788 0x1ffff0f0 at 12)' classid 1:1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic",
+ "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(11227080/1ffff0f0 at 12\\)",
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DEV1 ingress"
+ ]
+ },
+ {
+ "id": "d288",
+ "name": "Add basic filter with u32 ematch u32/missing offset",
+ "category": [
+ "filter",
+ "basic"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$TC qdisc add dev $DEV1 ingress"
+ ],
+ "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u32 0x11227788 0xffffffff at)' classid 1:1",
+ "expExitCode": "1",
+ "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic",
+ "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(11227788/ffffffff at 12\\)",
+ "matchCount": "0",
+ "teardown": [
+ "$TC qdisc del dev $DEV1 ingress"
+ ]
+ },
+ {
+ "id": "4998",
+ "name": "Add basic filter with u32 ematch u32/missing AT keyword",
+ "category": [
+ "filter",
+ "basic"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$TC qdisc add dev $DEV1 ingress"
+ ],
+ "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u32 0x77889900 0xfffff0f0 0)' classid 1:1",
+ "expExitCode": "1",
+ "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic",
+ "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(77889900/fffff0f0 at 0\\)",
+ "matchCount": "0",
+ "teardown": [
+ "$TC qdisc del dev $DEV1 ingress"
+ ]
+ },
+ {
+ "id": "1f0a",
+ "name": "Add basic filter with u32 ematch u32/missing value",
+ "category": [
+ "filter",
+ "basic"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$TC qdisc add dev $DEV1 ingress"
+ ],
+ "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u32 at 12)' classid 1:1",
+ "expExitCode": "1",
+ "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic",
+ "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(at 12\\)",
+ "matchCount": "0",
+ "teardown": [
+ "$TC qdisc del dev $DEV1 ingress"
+ ]
+ },
+ {
+ "id": "848e",
+ "name": "Add basic filter with u32 ematch u32/non-numeric value",
+ "category": [
+ "filter",
+ "basic"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$TC qdisc add dev $DEV1 ingress"
+ ],
+ "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u32 zero 0xffff at 0)' classid 1:1",
+ "expExitCode": "1",
+ "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic",
+ "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(00000000/ffff0000 at 0\\)",
+ "matchCount": "0",
+ "teardown": [
+ "$TC qdisc del dev $DEV1 ingress"
+ ]
+ },
+ {
+ "id": "f748",
+ "name": "Add basic filter with u32 ematch u32/non-numeric mask",
+ "category": [
+ "filter",
+ "basic"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$TC qdisc add dev $DEV1 ingress"
+ ],
+ "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u32 0x11223344 mask at 0)' classid 1:1",
+ "expExitCode": "1",
+ "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic",
+ "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(11223344/00000000 at 0\\)",
+ "matchCount": "0",
+ "teardown": [
+ "$TC qdisc del dev $DEV1 ingress"
+ ]
+ },
+ {
+ "id": "55a6",
+ "name": "Add basic filter with u32 ematch u32/negative offset and default action",
+ "category": [
+ "filter",
+ "basic"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$TC qdisc add dev $DEV1 ingress"
+ ],
+ "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u32 0xaabbccdd 0xff00ff00 at -12)' classid 1:1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic",
+ "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(aa00cc00/ff00ff00 at -12\\)",
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DEV1 ingress"
+ ]
+ },
+ {
+ "id": "7282",
+ "name": "Add basic filter with u32 ematch u32/nexthdr+ offset and default action",
+ "category": [
+ "filter",
+ "basic"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$TC qdisc add dev $DEV1 ingress"
+ ],
+ "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u32 0xaabbccdd 0xffffffff at nexthdr+0)' classid 1:1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic",
+ "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(aabbccdd/ffffffff at nexthdr\\+0\\)",
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DEV1 ingress"
+ ]
+ },
+ {
+ "id": "b2b6",
+ "name": "Add basic filter with canid ematch and single SFF",
+ "category": [
+ "filter",
+ "basic"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$TC qdisc add dev $DEV1 ingress"
+ ],
+ "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'canid(sff 1)' classid 1:1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic",
+ "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*canid\\(sff 0x1\\)",
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DEV1 ingress"
+ ]
+ },
+ {
+ "id": "f67f",
+ "name": "Add basic filter with canid ematch and single SFF with mask",
+ "category": [
+ "filter",
+ "basic"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$TC qdisc add dev $DEV1 ingress"
+ ],
+ "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'canid(sff 0xaabb:0x00ff)' classid 1:1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic",
+ "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*canid\\(sff 0x2BB:0xFF\\)",
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DEV1 ingress"
+ ]
+ },
+ {
+ "id": "bd5c",
+ "name": "Add basic filter with canid ematch and multiple SFF",
+ "category": [
+ "filter",
+ "basic"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$TC qdisc add dev $DEV1 ingress"
+ ],
+ "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'canid(sff 1 sff 2 sff 3)' classid 1:1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic",
+ "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*canid\\(sff 0x1 sff 0x2 sff 0x3\\)",
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DEV1 ingress"
+ ]
+ },
+ {
+ "id": "83c7",
+ "name": "Add basic filter with canid ematch and multiple SFF with masks",
+ "category": [
+ "filter",
+ "basic"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$TC qdisc add dev $DEV1 ingress"
+ ],
+ "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'canid(sff 0xaa:0x01 sff 0xbb:0x02 sff 0xcc:0x03)' classid 1:1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic",
+ "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*canid\\(sff 0xAA:0x1 sff 0xBB:0x2 sff 0xCC:0x3\\)",
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DEV1 ingress"
+ ]
+ },
+ {
+ "id": "a8f5",
+ "name": "Add basic filter with canid ematch and single EFF",
+ "category": [
+ "filter",
+ "basic"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$TC qdisc add dev $DEV1 ingress"
+ ],
+ "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'canid(eff 1)' classid 1:1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic",
+ "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*canid\\(eff 0x1\\)",
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DEV1 ingress"
+ ]
+ },
+ {
+ "id": "98ae",
+ "name": "Add basic filter with canid ematch and single EFF with mask",
+ "category": [
+ "filter",
+ "basic"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$TC qdisc add dev $DEV1 ingress"
+ ],
+ "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'canid(eff 0xaabb:0xf1f1)' classid 1:1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic",
+ "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*canid\\(eff 0xAABB:0xF1F1\\)",
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DEV1 ingress"
+ ]
+ },
+ {
+ "id": "6056",
+ "name": "Add basic filter with canid ematch and multiple EFF",
+ "category": [
+ "filter",
+ "basic"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$TC qdisc add dev $DEV1 ingress"
+ ],
+ "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'canid(eff 1 eff 2 eff 3)' classid 1:1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic",
+ "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*canid\\(eff 0x1 eff 0x2 eff 0x3\\)",
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DEV1 ingress"
+ ]
+ },
+ {
+ "id": "d188",
+ "name": "Add basic filter with canid ematch and multiple EFF with masks",
+ "category": [
+ "filter",
+ "basic"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$TC qdisc add dev $DEV1 ingress"
+ ],
+ "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'canid(eff 0xaa:0x01 eff 0xbb:0x02 eff 0xcc:0x03)' classid 1:1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic",
+ "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*canid\\(eff 0xAA:0x1 eff 0xBB:0x2 eff 0xCC:0x3\\)",
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DEV1 ingress"
+ ]
+ },
+ {
+ "id": "25d1",
+ "name": "Add basic filter with canid ematch and a combination of SFF/EFF",
+ "category": [
+ "filter",
+ "basic"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$TC qdisc add dev $DEV1 ingress"
+ ],
+ "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'canid(sff 0x01 eff 0x02)' classid 1:1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic",
+ "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*canid\\(eff 0x2 sff 0x1\\)",
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DEV1 ingress"
+ ]
+ },
+ {
+ "id": "b438",
+ "name": "Add basic filter with canid ematch and a combination of SFF/EFF with masks",
+ "category": [
+ "filter",
+ "basic"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$TC qdisc add dev $DEV1 ingress"
+ ],
+ "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'canid(sff 0x01:0xf eff 0x02:0xf)' classid 1:1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic",
+ "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*canid\\(eff 0x2:0xF sff 0x1:0xF\\)",
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DEV1 ingress"
+ ]
}
]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json b/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json
index 8877f7b2b809..bb543bf69d69 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json
@@ -32,7 +32,7 @@
"setup": [
"$TC qdisc add dev $DEV2 ingress"
],
- "cmdUnderTest": "$TC filter add dev $DEV2 protocol ip pref 1 parent ffff: handle 0xffffffff flower action ok",
+ "cmdUnderTest": "$TC filter add dev $DEV2 protocol ip pref 1 ingress handle 0xffffffff flower action ok",
"expExitCode": "0",
"verifyCmd": "$TC filter show dev $DEV2 ingress",
"matchPattern": "filter protocol ip pref 1 flower.*handle 0xffffffff",
@@ -77,9 +77,9 @@
},
"setup": [
"$TC qdisc add dev $DEV2 ingress",
- "$TC filter add dev $DEV2 protocol ip prio 1 parent ffff: flower dst_mac e4:11:22:11:4a:51 src_mac e4:11:22:11:4a:50 ip_proto tcp src_ip 1.1.1.1 dst_ip 2.2.2.2 action drop"
+ "$TC filter add dev $DEV2 protocol ip prio 1 ingress flower dst_mac e4:11:22:11:4a:51 src_mac e4:11:22:11:4a:50 ip_proto tcp src_ip 1.1.1.1 dst_ip 2.2.2.2 action drop"
],
- "cmdUnderTest": "$TC filter add dev $DEV2 protocol ip prio 1 parent ffff: flower dst_mac e4:11:22:11:4a:51 src_mac e4:11:22:11:4a:50 ip_proto tcp src_ip 1.1.1.1 dst_ip 2.2.2.2 action drop",
+ "cmdUnderTest": "$TC filter add dev $DEV2 protocol ip prio 1 ingress flower dst_mac e4:11:22:11:4a:51 src_mac e4:11:22:11:4a:50 ip_proto tcp src_ip 1.1.1.1 dst_ip 2.2.2.2 action drop",
"expExitCode": "2",
"verifyCmd": "$TC -s filter show dev $DEV2 ingress",
"matchPattern": "filter protocol ip pref 1 flower chain 0 handle",
@@ -87,5 +87,43 @@
"teardown": [
"$TC qdisc del dev $DEV2 ingress"
]
+ },
+ {
+ "id": "7c65",
+ "name": "Add flower filter and then terse dump it",
+ "category": [
+ "filter",
+ "flower"
+ ],
+ "setup": [
+ "$TC qdisc add dev $DEV2 ingress"
+ ],
+ "cmdUnderTest": "$TC filter add dev $DEV2 protocol ip pref 1 ingress flower dst_mac e4:11:22:11:4a:51 action drop",
+ "expExitCode": "0",
+ "verifyCmd": "$TC filter show terse dev $DEV2 ingress",
+ "matchPattern": "filter protocol ip pref 1 flower.*handle",
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DEV2 ingress"
+ ]
+ },
+ {
+ "id": "d45e",
+ "name": "Add flower filter and verify that terse dump doesn't output filter key",
+ "category": [
+ "filter",
+ "flower"
+ ],
+ "setup": [
+ "$TC qdisc add dev $DEV2 ingress"
+ ],
+ "cmdUnderTest": "$TC filter add dev $DEV2 protocol ip pref 1 ingress flower dst_mac e4:11:22:11:4a:51 action drop",
+ "expExitCode": "0",
+ "verifyCmd": "$TC filter show terse dev $DEV2 ingress",
+ "matchPattern": " dst_mac e4:11:22:11:4a:51",
+ "matchCount": "0",
+ "teardown": [
+ "$TC qdisc del dev $DEV2 ingress"
+ ]
}
]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json
new file mode 100644
index 000000000000..1cda2e11b3ad
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json
@@ -0,0 +1,21 @@
+[
+ {
+ "id": "83be",
+ "name": "Create FQ-PIE with invalid number of flows",
+ "category": [
+ "qdisc",
+ "fq_pie"
+ ],
+ "setup": [
+ "$IP link add dev $DUMMY type dummy || /bin/true"
+ ],
+ "cmdUnderTest": "$TC qdisc add dev $DUMMY root fq_pie flows 65536",
+ "expExitCode": "2",
+ "verifyCmd": "$TC qdisc show dev $DUMMY",
+ "matchPattern": "qdisc",
+ "matchCount": "0",
+ "teardown": [
+ "$IP link del dev $DUMMY"
+ ]
+ }
+]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/red.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/red.json
new file mode 100644
index 000000000000..0703a2a255eb
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/red.json
@@ -0,0 +1,185 @@
+[
+ {
+ "id": "8b6e",
+ "name": "Create RED with no flags",
+ "category": [
+ "qdisc",
+ "red"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$IP link add dev $DUMMY type dummy || /bin/true"
+ ],
+ "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root red limit 1M avpkt 1500 min 100K max 300K",
+ "expExitCode": "0",
+ "verifyCmd": "$TC qdisc show dev $DUMMY",
+ "matchPattern": "qdisc red 1: root .* limit 1Mb min 100Kb max 300Kb $",
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DUMMY handle 1: root",
+ "$IP link del dev $DUMMY type dummy"
+ ]
+ },
+ {
+ "id": "342e",
+ "name": "Create RED with adaptive flag",
+ "category": [
+ "qdisc",
+ "red"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$IP link add dev $DUMMY type dummy || /bin/true"
+ ],
+ "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root red adaptive limit 1M avpkt 1500 min 100K max 300K",
+ "expExitCode": "0",
+ "verifyCmd": "$TC qdisc show dev $DUMMY",
+ "matchPattern": "qdisc red 1: root .* limit 1Mb min 100Kb max 300Kb adaptive $",
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DUMMY handle 1: root",
+ "$IP link del dev $DUMMY type dummy"
+ ]
+ },
+ {
+ "id": "2d4b",
+ "name": "Create RED with ECN flag",
+ "category": [
+ "qdisc",
+ "red"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$IP link add dev $DUMMY type dummy || /bin/true"
+ ],
+ "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root red ecn limit 1M avpkt 1500 min 100K max 300K",
+ "expExitCode": "0",
+ "verifyCmd": "$TC qdisc show dev $DUMMY",
+ "matchPattern": "qdisc red 1: root .* limit 1Mb min 100Kb max 300Kb ecn $",
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DUMMY handle 1: root",
+ "$IP link del dev $DUMMY type dummy"
+ ]
+ },
+ {
+ "id": "650f",
+ "name": "Create RED with flags ECN, adaptive",
+ "category": [
+ "qdisc",
+ "red"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$IP link add dev $DUMMY type dummy || /bin/true"
+ ],
+ "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root red ecn adaptive limit 1M avpkt 1500 min 100K max 300K",
+ "expExitCode": "0",
+ "verifyCmd": "$TC qdisc show dev $DUMMY",
+ "matchPattern": "qdisc red 1: root .* limit 1Mb min 100Kb max 300Kb ecn adaptive $",
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DUMMY handle 1: root",
+ "$IP link del dev $DUMMY type dummy"
+ ]
+ },
+ {
+ "id": "5f15",
+ "name": "Create RED with flags ECN, harddrop",
+ "category": [
+ "qdisc",
+ "red"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$IP link add dev $DUMMY type dummy || /bin/true"
+ ],
+ "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root red ecn harddrop limit 1M avpkt 1500 min 100K max 300K",
+ "expExitCode": "0",
+ "verifyCmd": "$TC qdisc show dev $DUMMY",
+ "matchPattern": "qdisc red 1: root .* limit 1Mb min 100Kb max 300Kb ecn harddrop $",
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DUMMY handle 1: root",
+ "$IP link del dev $DUMMY type dummy"
+ ]
+ },
+ {
+ "id": "53e8",
+ "name": "Create RED with flags ECN, nodrop",
+ "category": [
+ "qdisc",
+ "red"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$IP link add dev $DUMMY type dummy || /bin/true"
+ ],
+ "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root red ecn nodrop limit 1M avpkt 1500 min 100K max 300K",
+ "expExitCode": "0",
+ "verifyCmd": "$TC qdisc show dev $DUMMY",
+ "matchPattern": "qdisc red 1: root .* limit 1Mb min 100Kb max 300Kb ecn nodrop $",
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DUMMY handle 1: root",
+ "$IP link del dev $DUMMY type dummy"
+ ]
+ },
+ {
+ "id": "d091",
+ "name": "Fail to create RED with only nodrop flag",
+ "category": [
+ "qdisc",
+ "red"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$IP link add dev $DUMMY type dummy || /bin/true"
+ ],
+ "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root red nodrop limit 1M avpkt 1500 min 100K max 300K",
+ "expExitCode": "2",
+ "verifyCmd": "$TC qdisc show dev $DUMMY",
+ "matchPattern": "qdisc red",
+ "matchCount": "0",
+ "teardown": [
+ "$IP link del dev $DUMMY type dummy"
+ ]
+ },
+ {
+ "id": "af8e",
+ "name": "Create RED with flags ECN, nodrop, harddrop",
+ "category": [
+ "qdisc",
+ "red"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$IP link add dev $DUMMY type dummy || /bin/true"
+ ],
+ "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root red ecn harddrop nodrop limit 1M avpkt 1500 min 100K max 300K",
+ "expExitCode": "0",
+ "verifyCmd": "$TC qdisc show dev $DUMMY",
+ "matchPattern": "qdisc red 1: root .* limit 1Mb min 100Kb max 300Kb ecn harddrop nodrop $",
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DUMMY handle 1: root",
+ "$IP link del dev $DUMMY type dummy"
+ ]
+ }
+]
diff --git a/tools/testing/selftests/tc-testing/tdc.py b/tools/testing/selftests/tc-testing/tdc.py
index e566c70e64a1..a3e43189d940 100755
--- a/tools/testing/selftests/tc-testing/tdc.py
+++ b/tools/testing/selftests/tc-testing/tdc.py
@@ -713,9 +713,8 @@ def set_operation_mode(pm, parser, args, remaining):
exit(0)
if args.list:
- if args.list:
- list_test_cases(alltests)
- exit(0)
+ list_test_cases(alltests)
+ exit(0)
if len(alltests):
req_plugins = pm.get_required_plugins(alltests)
diff --git a/tools/testing/selftests/tc-testing/tdc_batch.py b/tools/testing/selftests/tc-testing/tdc_batch.py
index 6a2bd2cf528e..995f66ce43eb 100755
--- a/tools/testing/selftests/tc-testing/tdc_batch.py
+++ b/tools/testing/selftests/tc-testing/tdc_batch.py
@@ -72,21 +72,21 @@ mac_prefix = args.mac_prefix
def format_add_filter(device, prio, handle, skip, src_mac, dst_mac,
share_action):
- return ("filter add dev {} {} protocol ip parent ffff: handle {} "
+ return ("filter add dev {} {} protocol ip ingress handle {} "
" flower {} src_mac {} dst_mac {} action drop {}".format(
device, prio, handle, skip, src_mac, dst_mac, share_action))
def format_rep_filter(device, prio, handle, skip, src_mac, dst_mac,
share_action):
- return ("filter replace dev {} {} protocol ip parent ffff: handle {} "
+ return ("filter replace dev {} {} protocol ip ingress handle {} "
" flower {} src_mac {} dst_mac {} action drop {}".format(
device, prio, handle, skip, src_mac, dst_mac, share_action))
def format_del_filter(device, prio, handle, skip, src_mac, dst_mac,
share_action):
- return ("filter del dev {} {} protocol ip parent ffff: handle {} "
+ return ("filter del dev {} {} protocol ip ingress handle {} "
"flower".format(device, prio, handle))
diff --git a/tools/testing/selftests/timens/.gitignore b/tools/testing/selftests/timens/.gitignore
index 789f21e81028..2e43851b47c1 100644
--- a/tools/testing/selftests/timens/.gitignore
+++ b/tools/testing/selftests/timens/.gitignore
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
clock_nanosleep
exec
gettime_perf
diff --git a/tools/testing/selftests/timens/clock_nanosleep.c b/tools/testing/selftests/timens/clock_nanosleep.c
index 8e7b7c72ef65..72d41b955fb2 100644
--- a/tools/testing/selftests/timens/clock_nanosleep.c
+++ b/tools/testing/selftests/timens/clock_nanosleep.c
@@ -119,7 +119,7 @@ int main(int argc, char *argv[])
ksft_set_plan(4);
- check_config_posix_timers();
+ check_supported_timers();
if (unshare_timens())
return 1;
diff --git a/tools/testing/selftests/timens/exec.c b/tools/testing/selftests/timens/exec.c
index 87b47b557a7a..e40dc5be2f66 100644
--- a/tools/testing/selftests/timens/exec.c
+++ b/tools/testing/selftests/timens/exec.c
@@ -11,7 +11,6 @@
#include <sys/wait.h>
#include <time.h>
#include <unistd.h>
-#include <time.h>
#include <string.h>
#include "log.h"
diff --git a/tools/testing/selftests/timens/procfs.c b/tools/testing/selftests/timens/procfs.c
index 43d93f4006b9..7f14f0fdac84 100644
--- a/tools/testing/selftests/timens/procfs.c
+++ b/tools/testing/selftests/timens/procfs.c
@@ -12,7 +12,6 @@
#include <sys/types.h>
#include <time.h>
#include <unistd.h>
-#include <time.h>
#include "log.h"
#include "timens.h"
diff --git a/tools/testing/selftests/timens/timens.c b/tools/testing/selftests/timens/timens.c
index 559d26e21ba0..52b6a1185f52 100644
--- a/tools/testing/selftests/timens/timens.c
+++ b/tools/testing/selftests/timens/timens.c
@@ -10,7 +10,6 @@
#include <sys/types.h>
#include <time.h>
#include <unistd.h>
-#include <time.h>
#include <string.h>
#include "log.h"
@@ -156,7 +155,7 @@ int main(int argc, char *argv[])
nscheck();
- check_config_posix_timers();
+ check_supported_timers();
ksft_set_plan(ARRAY_SIZE(clocks) * 2);
diff --git a/tools/testing/selftests/timens/timens.h b/tools/testing/selftests/timens/timens.h
index e09e7e39bc52..d4fc52d47146 100644
--- a/tools/testing/selftests/timens/timens.h
+++ b/tools/testing/selftests/timens/timens.h
@@ -14,15 +14,26 @@
#endif
static int config_posix_timers = true;
+static int config_alarm_timers = true;
-static inline void check_config_posix_timers(void)
+static inline void check_supported_timers(void)
{
+ struct timespec ts;
+
if (timer_create(-1, 0, 0) == -1 && errno == ENOSYS)
config_posix_timers = false;
+
+ if (clock_gettime(CLOCK_BOOTTIME_ALARM, &ts) == -1 && errno == EINVAL)
+ config_alarm_timers = false;
}
static inline bool check_skip(int clockid)
{
+ if (!config_alarm_timers && clockid == CLOCK_BOOTTIME_ALARM) {
+ ksft_test_result_skip("CLOCK_BOOTTIME_ALARM isn't supported\n");
+ return true;
+ }
+
if (config_posix_timers)
return false;
diff --git a/tools/testing/selftests/timens/timer.c b/tools/testing/selftests/timens/timer.c
index 0cca7aafc4bd..5e7f0051bd7b 100644
--- a/tools/testing/selftests/timens/timer.c
+++ b/tools/testing/selftests/timens/timer.c
@@ -11,7 +11,6 @@
#include <stdio.h>
#include <stdint.h>
#include <signal.h>
-#include <time.h>
#include "log.h"
#include "timens.h"
@@ -23,6 +22,9 @@ int run_test(int clockid, struct timespec now)
timer_t fd;
int i;
+ if (check_skip(clockid))
+ return 0;
+
for (i = 0; i < 2; i++) {
struct sigevent sevp = {.sigev_notify = SIGEV_NONE};
int flags = 0;
@@ -75,6 +77,8 @@ int main(int argc, char *argv[])
nscheck();
+ check_supported_timers();
+
ksft_set_plan(3);
clock_gettime(CLOCK_MONOTONIC, &mtime_now);
diff --git a/tools/testing/selftests/timens/timerfd.c b/tools/testing/selftests/timens/timerfd.c
index eff1ec5ff215..9edd43d6b2c1 100644
--- a/tools/testing/selftests/timens/timerfd.c
+++ b/tools/testing/selftests/timens/timerfd.c
@@ -28,6 +28,9 @@ int run_test(int clockid, struct timespec now)
long long elapsed;
int fd, i;
+ if (check_skip(clockid))
+ return 0;
+
if (tclock_gettime(clockid, &now))
return pr_perror("clock_gettime(%d)", clockid);
@@ -81,6 +84,8 @@ int main(int argc, char *argv[])
nscheck();
+ check_supported_timers();
+
ksft_set_plan(3);
clock_gettime(CLOCK_MONOTONIC, &mtime_now);
diff --git a/tools/testing/selftests/timers/.gitignore b/tools/testing/selftests/timers/.gitignore
index 32a9eadb2d4e..bb5326ff900b 100644
--- a/tools/testing/selftests/timers/.gitignore
+++ b/tools/testing/selftests/timers/.gitignore
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
alarmtimer-suspend
change_skew
clocksource-switch
diff --git a/tools/testing/selftests/tmpfs/.gitignore b/tools/testing/selftests/tmpfs/.gitignore
index a96838fad74d..b1afaa925905 100644
--- a/tools/testing/selftests/tmpfs/.gitignore
+++ b/tools/testing/selftests/tmpfs/.gitignore
@@ -1 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
/bug-link-o-tmpfile
diff --git a/tools/testing/selftests/tpm2/test_smoke.sh b/tools/testing/selftests/tpm2/test_smoke.sh
index b630c7b5950a..663062701d5a 100755
--- a/tools/testing/selftests/tpm2/test_smoke.sh
+++ b/tools/testing/selftests/tpm2/test_smoke.sh
@@ -1,17 +1,13 @@
#!/bin/bash
# SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause)
-self.flags = flags
# Kselftest framework requirement - SKIP code is 4.
ksft_skip=4
+[ -f /dev/tpm0 ] || exit $ksft_skip
-if [ -f /dev/tpm0 ] ; then
- python -m unittest -v tpm2_tests.SmokeTest
- python -m unittest -v tpm2_tests.AsyncTest
-else
- exit $ksft_skip
-fi
+python -m unittest -v tpm2_tests.SmokeTest
+python -m unittest -v tpm2_tests.AsyncTest
CLEAR_CMD=$(which tpm2_clear)
if [ -n $CLEAR_CMD ]; then
diff --git a/tools/testing/selftests/tpm2/test_space.sh b/tools/testing/selftests/tpm2/test_space.sh
index 180b469c53b4..36c9d030a1c6 100755
--- a/tools/testing/selftests/tpm2/test_space.sh
+++ b/tools/testing/selftests/tpm2/test_space.sh
@@ -4,8 +4,6 @@
# Kselftest framework requirement - SKIP code is 4.
ksft_skip=4
-if [ -f /dev/tpmrm0 ] ; then
- python -m unittest -v tpm2_tests.SpaceTest
-else
- exit $ksft_skip
-fi
+[ -f /dev/tpmrm0 ] || exit $ksft_skip
+
+python -m unittest -v tpm2_tests.SpaceTest
diff --git a/tools/testing/selftests/vDSO/.gitignore b/tools/testing/selftests/vDSO/.gitignore
index 133bf9ee986c..5eb64d41e541 100644
--- a/tools/testing/selftests/vDSO/.gitignore
+++ b/tools/testing/selftests/vDSO/.gitignore
@@ -1,2 +1,5 @@
+# SPDX-License-Identifier: GPL-2.0-only
vdso_test
+vdso_test_gettimeofday
+vdso_test_getcpu
vdso_standalone_test_x86
diff --git a/tools/testing/selftests/vDSO/Makefile b/tools/testing/selftests/vDSO/Makefile
index 9e03d61f52fd..0069f2f83f86 100644
--- a/tools/testing/selftests/vDSO/Makefile
+++ b/tools/testing/selftests/vDSO/Makefile
@@ -4,7 +4,7 @@ include ../lib.mk
uname_M := $(shell uname -m 2>/dev/null || echo not)
ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/x86/ -e s/x86_64/x86/)
-TEST_GEN_PROGS := $(OUTPUT)/vdso_test
+TEST_GEN_PROGS := $(OUTPUT)/vdso_test_gettimeofday $(OUTPUT)/vdso_test_getcpu
ifeq ($(ARCH),x86)
TEST_GEN_PROGS += $(OUTPUT)/vdso_standalone_test_x86
endif
@@ -17,7 +17,8 @@ LDLIBS += -lgcc_s
endif
all: $(TEST_GEN_PROGS)
-$(OUTPUT)/vdso_test: parse_vdso.c vdso_test.c
+$(OUTPUT)/vdso_test_gettimeofday: parse_vdso.c vdso_test_gettimeofday.c
+$(OUTPUT)/vdso_test_getcpu: parse_vdso.c vdso_test_getcpu.c
$(OUTPUT)/vdso_standalone_test_x86: vdso_standalone_test_x86.c parse_vdso.c
$(CC) $(CFLAGS) $(CFLAGS_vdso_standalone_test_x86) \
vdso_standalone_test_x86.c parse_vdso.c \
diff --git a/tools/testing/selftests/vDSO/parse_vdso.c b/tools/testing/selftests/vDSO/parse_vdso.c
index 1dbb4b87268f..413f75620a35 100644
--- a/tools/testing/selftests/vDSO/parse_vdso.c
+++ b/tools/testing/selftests/vDSO/parse_vdso.c
@@ -21,29 +21,7 @@
#include <limits.h>
#include <elf.h>
-/*
- * To use this vDSO parser, first call one of the vdso_init_* functions.
- * If you've already parsed auxv, then pass the value of AT_SYSINFO_EHDR
- * to vdso_init_from_sysinfo_ehdr. Otherwise pass auxv to vdso_init_from_auxv.
- * Then call vdso_sym for each symbol you want. For example, to look up
- * gettimeofday on x86_64, use:
- *
- * <some pointer> = vdso_sym("LINUX_2.6", "gettimeofday");
- * or
- * <some pointer> = vdso_sym("LINUX_2.6", "__vdso_gettimeofday");
- *
- * vdso_sym will return 0 if the symbol doesn't exist or if the init function
- * failed or was not called. vdso_sym is a little slow, so its return value
- * should be cached.
- *
- * vdso_sym is threadsafe; the init functions are not.
- *
- * These are the prototypes:
- */
-extern void vdso_init_from_auxv(void *auxv);
-extern void vdso_init_from_sysinfo_ehdr(uintptr_t base);
-extern void *vdso_sym(const char *version, const char *name);
-
+#include "parse_vdso.h"
/* And here's the code. */
#ifndef ELF_BITS
diff --git a/tools/testing/selftests/vDSO/parse_vdso.h b/tools/testing/selftests/vDSO/parse_vdso.h
new file mode 100644
index 000000000000..de0453067d7c
--- /dev/null
+++ b/tools/testing/selftests/vDSO/parse_vdso.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef PARSE_VDSO_H
+#define PARSE_VDSO_H
+
+#include <stdint.h>
+
+/*
+ * To use this vDSO parser, first call one of the vdso_init_* functions.
+ * If you've already parsed auxv, then pass the value of AT_SYSINFO_EHDR
+ * to vdso_init_from_sysinfo_ehdr. Otherwise pass auxv to vdso_init_from_auxv.
+ * Then call vdso_sym for each symbol you want. For example, to look up
+ * gettimeofday on x86_64, use:
+ *
+ * <some pointer> = vdso_sym("LINUX_2.6", "gettimeofday");
+ * or
+ * <some pointer> = vdso_sym("LINUX_2.6", "__vdso_gettimeofday");
+ *
+ * vdso_sym will return 0 if the symbol doesn't exist or if the init function
+ * failed or was not called. vdso_sym is a little slow, so its return value
+ * should be cached.
+ *
+ * vdso_sym is threadsafe; the init functions are not.
+ *
+ * These are the prototypes:
+ */
+void *vdso_sym(const char *version, const char *name);
+void vdso_init_from_sysinfo_ehdr(uintptr_t base);
+void vdso_init_from_auxv(void *auxv);
+
+#endif
diff --git a/tools/testing/selftests/vDSO/vdso_standalone_test_x86.c b/tools/testing/selftests/vDSO/vdso_standalone_test_x86.c
index 5ac4b00acfbc..8a44ff973ee1 100644
--- a/tools/testing/selftests/vDSO/vdso_standalone_test_x86.c
+++ b/tools/testing/selftests/vDSO/vdso_standalone_test_x86.c
@@ -16,9 +16,7 @@
#include <unistd.h>
#include <stdint.h>
-extern void *vdso_sym(const char *version, const char *name);
-extern void vdso_init_from_sysinfo_ehdr(uintptr_t base);
-extern void vdso_init_from_auxv(void *auxv);
+#include "parse_vdso.h"
/* We need a libc functions... */
int strcmp(const char *a, const char *b)
diff --git a/tools/testing/selftests/vDSO/vdso_test_getcpu.c b/tools/testing/selftests/vDSO/vdso_test_getcpu.c
new file mode 100644
index 000000000000..fc25ede131b8
--- /dev/null
+++ b/tools/testing/selftests/vDSO/vdso_test_getcpu.c
@@ -0,0 +1,54 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * vdso_test_getcpu.c: Sample code to test parse_vdso.c and vDSO getcpu()
+ *
+ * Copyright (c) 2020 Arm Ltd
+ */
+
+#include <stdint.h>
+#include <elf.h>
+#include <stdio.h>
+#include <sys/auxv.h>
+#include <sys/time.h>
+
+#include "../kselftest.h"
+#include "parse_vdso.h"
+
+const char *version = "LINUX_2.6";
+const char *name = "__vdso_getcpu";
+
+struct getcpu_cache;
+typedef long (*getcpu_t)(unsigned int *, unsigned int *,
+ struct getcpu_cache *);
+
+int main(int argc, char **argv)
+{
+ unsigned long sysinfo_ehdr;
+ unsigned int cpu, node;
+ getcpu_t get_cpu;
+ long ret;
+
+ sysinfo_ehdr = getauxval(AT_SYSINFO_EHDR);
+ if (!sysinfo_ehdr) {
+ printf("AT_SYSINFO_EHDR is not present!\n");
+ return KSFT_SKIP;
+ }
+
+ vdso_init_from_sysinfo_ehdr(getauxval(AT_SYSINFO_EHDR));
+
+ get_cpu = (getcpu_t)vdso_sym(version, name);
+ if (!get_cpu) {
+ printf("Could not find %s\n", name);
+ return KSFT_SKIP;
+ }
+
+ ret = get_cpu(&cpu, &node, 0);
+ if (ret == 0) {
+ printf("Running on CPU %u node %u\n", cpu, node);
+ } else {
+ printf("%s failed\n", name);
+ return KSFT_FAIL;
+ }
+
+ return 0;
+}
diff --git a/tools/testing/selftests/vDSO/vdso_test.c b/tools/testing/selftests/vDSO/vdso_test_gettimeofday.c
index 719d5a6bd664..8ccc73ed8240 100644
--- a/tools/testing/selftests/vDSO/vdso_test.c
+++ b/tools/testing/selftests/vDSO/vdso_test_gettimeofday.c
@@ -1,10 +1,11 @@
// SPDX-License-Identifier: GPL-2.0-only
/*
- * vdso_test.c: Sample code to test parse_vdso.c
+ * vdso_test_gettimeofday.c: Sample code to test parse_vdso.c and
+ * vDSO gettimeofday()
* Copyright (c) 2014 Andy Lutomirski
*
* Compile with:
- * gcc -std=gnu99 vdso_test.c parse_vdso.c
+ * gcc -std=gnu99 vdso_test_gettimeofday.c parse_vdso_gettimeofday.c
*
* Tested on x86, 32-bit and 64-bit. It may work on other architectures, too.
*/
@@ -16,10 +17,7 @@
#include <sys/time.h>
#include "../kselftest.h"
-
-extern void *vdso_sym(const char *version, const char *name);
-extern void vdso_init_from_sysinfo_ehdr(uintptr_t base);
-extern void vdso_init_from_auxv(void *auxv);
+#include "parse_vdso.h"
/*
* ARM64's vDSO exports its gettimeofday() implementation with a different
diff --git a/tools/testing/selftests/vm/.gitignore b/tools/testing/selftests/vm/.gitignore
index 31b3c98b6d34..849e8226395a 100644
--- a/tools/testing/selftests/vm/.gitignore
+++ b/tools/testing/selftests/vm/.gitignore
@@ -1,12 +1,16 @@
+# SPDX-License-Identifier: GPL-2.0-only
hugepage-mmap
hugepage-shm
+khugepaged
map_hugetlb
map_populate
thuge-gen
compaction_test
mlock2-tests
+mremap_dontunmap
on-fault-limit
transhuge-stress
+protection_keys
userfaultfd
mlock-intersect-test
mlock-random-test
@@ -14,3 +18,5 @@ virtual_address_range
gup_benchmark
va_128TBswitch
map_fixed_noreplace
+write_to_hugetlbfs
+hmm-tests
diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile
index 7f9a8a8c31da..a9026706d597 100644
--- a/tools/testing/selftests/vm/Makefile
+++ b/tools/testing/selftests/vm/Makefile
@@ -1,12 +1,13 @@
# SPDX-License-Identifier: GPL-2.0
# Makefile for vm selftests
uname_M := $(shell uname -m 2>/dev/null || echo not)
-ARCH ?= $(shell echo $(uname_M) | sed -e 's/aarch64.*/arm64/')
+MACHINE ?= $(shell echo $(uname_M) | sed -e 's/aarch64.*/arm64/')
CFLAGS = -Wall -I ../../../../usr/include $(EXTRA_CFLAGS)
LDLIBS = -lrt
TEST_GEN_FILES = compaction_test
TEST_GEN_FILES += gup_benchmark
+TEST_GEN_FILES += hmm-tests
TEST_GEN_FILES += hugepage-mmap
TEST_GEN_FILES += hugepage-shm
TEST_GEN_FILES += map_hugetlb
@@ -14,14 +15,41 @@ TEST_GEN_FILES += map_fixed_noreplace
TEST_GEN_FILES += map_populate
TEST_GEN_FILES += mlock-random-test
TEST_GEN_FILES += mlock2-tests
+TEST_GEN_FILES += mremap_dontunmap
TEST_GEN_FILES += on-fault-limit
TEST_GEN_FILES += thuge-gen
TEST_GEN_FILES += transhuge-stress
TEST_GEN_FILES += userfaultfd
+TEST_GEN_FILES += khugepaged
-ifneq (,$(filter $(ARCH),arm64 ia64 mips64 parisc64 ppc64 riscv64 s390x sh64 sparc64 x86_64))
+ifeq ($(ARCH),x86_64)
+CAN_BUILD_I386 := $(shell ./../x86/check_cc.sh $(CC) ../x86/trivial_32bit_program.c -m32)
+CAN_BUILD_X86_64 := $(shell ./../x86/check_cc.sh $(CC) ../x86/trivial_64bit_program.c)
+CAN_BUILD_WITH_NOPIE := $(shell ./../x86/check_cc.sh $(CC) ../x86/trivial_program.c -no-pie)
+
+TARGETS := protection_keys
+BINARIES_32 := $(TARGETS:%=%_32)
+BINARIES_64 := $(TARGETS:%=%_64)
+
+ifeq ($(CAN_BUILD_WITH_NOPIE),1)
+CFLAGS += -no-pie
+endif
+
+ifeq ($(CAN_BUILD_I386),1)
+TEST_GEN_FILES += $(BINARIES_32)
+endif
+
+ifeq ($(CAN_BUILD_X86_64),1)
+TEST_GEN_FILES += $(BINARIES_64)
+endif
+else
+TEST_GEN_FILES += protection_keys
+endif
+
+ifneq (,$(filter $(MACHINE),arm64 ia64 mips64 parisc64 ppc64 ppc64le riscv64 s390x sh64 sparc64 x86_64))
TEST_GEN_FILES += va_128TBswitch
TEST_GEN_FILES += virtual_address_range
+TEST_GEN_FILES += write_to_hugetlbfs
endif
TEST_PROGS := run_vmtests
@@ -31,6 +59,57 @@ TEST_FILES := test_vmalloc.sh
KSFT_KHDR_INSTALL := 1
include ../lib.mk
+$(OUTPUT)/hmm-tests: LDLIBS += -lhugetlbfs -lpthread
+
+ifeq ($(ARCH),x86_64)
+BINARIES_32 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_32))
+BINARIES_64 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_64))
+
+define gen-target-rule-32
+$(1) $(1)_32: $(OUTPUT)/$(1)_32
+.PHONY: $(1) $(1)_32
+endef
+
+define gen-target-rule-64
+$(1) $(1)_64: $(OUTPUT)/$(1)_64
+.PHONY: $(1) $(1)_64
+endef
+
+ifeq ($(CAN_BUILD_I386),1)
+$(BINARIES_32): CFLAGS += -m32
+$(BINARIES_32): LDLIBS += -lrt -ldl -lm
+$(BINARIES_32): %_32: %.c
+ $(CC) $(CFLAGS) $(EXTRA_CFLAGS) $(notdir $^) $(LDLIBS) -o $@
+$(foreach t,$(TARGETS),$(eval $(call gen-target-rule-32,$(t))))
+endif
+
+ifeq ($(CAN_BUILD_X86_64),1)
+$(BINARIES_64): CFLAGS += -m64
+$(BINARIES_64): LDLIBS += -lrt -ldl
+$(BINARIES_64): %_64: %.c
+ $(CC) $(CFLAGS) $(EXTRA_CFLAGS) $(notdir $^) $(LDLIBS) -o $@
+$(foreach t,$(TARGETS),$(eval $(call gen-target-rule-64,$(t))))
+endif
+
+# x86_64 users should be encouraged to install 32-bit libraries
+ifeq ($(CAN_BUILD_I386)$(CAN_BUILD_X86_64),01)
+all: warn_32bit_failure
+
+warn_32bit_failure:
+ @echo "Warning: you seem to have a broken 32-bit build" 2>&1; \
+ echo "environment. This will reduce test coverage of 64-bit" 2>&1; \
+ echo "kernels. If you are using a Debian-like distribution," 2>&1; \
+ echo "try:"; 2>&1; \
+ echo ""; \
+ echo " apt-get install gcc-multilib libc6-i386 libc6-dev-i386"; \
+ echo ""; \
+ echo "If you are using a Fedora-like distribution, try:"; \
+ echo ""; \
+ echo " yum install glibc-devel.*i686"; \
+ exit 0;
+endif
+endif
+
$(OUTPUT)/userfaultfd: LDLIBS += -lpthread
$(OUTPUT)/mlock-random-test: LDLIBS += -lcap
diff --git a/tools/testing/selftests/vm/charge_reserved_hugetlb.sh b/tools/testing/selftests/vm/charge_reserved_hugetlb.sh
new file mode 100644
index 000000000000..18d33684faad
--- /dev/null
+++ b/tools/testing/selftests/vm/charge_reserved_hugetlb.sh
@@ -0,0 +1,575 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+
+set -e
+
+if [[ $(id -u) -ne 0 ]]; then
+ echo "This test must be run as root. Skipping..."
+ exit 0
+fi
+
+fault_limit_file=limit_in_bytes
+reservation_limit_file=rsvd.limit_in_bytes
+fault_usage_file=usage_in_bytes
+reservation_usage_file=rsvd.usage_in_bytes
+
+if [[ "$1" == "-cgroup-v2" ]]; then
+ cgroup2=1
+ fault_limit_file=max
+ reservation_limit_file=rsvd.max
+ fault_usage_file=current
+ reservation_usage_file=rsvd.current
+fi
+
+cgroup_path=/dev/cgroup/memory
+if [[ ! -e $cgroup_path ]]; then
+ mkdir -p $cgroup_path
+ if [[ $cgroup2 ]]; then
+ mount -t cgroup2 none $cgroup_path
+ else
+ mount -t cgroup memory,hugetlb $cgroup_path
+ fi
+fi
+
+if [[ $cgroup2 ]]; then
+ echo "+hugetlb" >/dev/cgroup/memory/cgroup.subtree_control
+fi
+
+function cleanup() {
+ if [[ $cgroup2 ]]; then
+ echo $$ >$cgroup_path/cgroup.procs
+ else
+ echo $$ >$cgroup_path/tasks
+ fi
+
+ if [[ -e /mnt/huge ]]; then
+ rm -rf /mnt/huge/*
+ umount /mnt/huge || echo error
+ rmdir /mnt/huge
+ fi
+ if [[ -e $cgroup_path/hugetlb_cgroup_test ]]; then
+ rmdir $cgroup_path/hugetlb_cgroup_test
+ fi
+ if [[ -e $cgroup_path/hugetlb_cgroup_test1 ]]; then
+ rmdir $cgroup_path/hugetlb_cgroup_test1
+ fi
+ if [[ -e $cgroup_path/hugetlb_cgroup_test2 ]]; then
+ rmdir $cgroup_path/hugetlb_cgroup_test2
+ fi
+ echo 0 >/proc/sys/vm/nr_hugepages
+ echo CLEANUP DONE
+}
+
+function expect_equal() {
+ local expected="$1"
+ local actual="$2"
+ local error="$3"
+
+ if [[ "$expected" != "$actual" ]]; then
+ echo "expected ($expected) != actual ($actual): $3"
+ cleanup
+ exit 1
+ fi
+}
+
+function get_machine_hugepage_size() {
+ hpz=$(grep -i hugepagesize /proc/meminfo)
+ kb=${hpz:14:-3}
+ mb=$(($kb / 1024))
+ echo $mb
+}
+
+MB=$(get_machine_hugepage_size)
+
+function setup_cgroup() {
+ local name="$1"
+ local cgroup_limit="$2"
+ local reservation_limit="$3"
+
+ mkdir $cgroup_path/$name
+
+ echo writing cgroup limit: "$cgroup_limit"
+ echo "$cgroup_limit" >$cgroup_path/$name/hugetlb.${MB}MB.$fault_limit_file
+
+ echo writing reseravation limit: "$reservation_limit"
+ echo "$reservation_limit" > \
+ $cgroup_path/$name/hugetlb.${MB}MB.$reservation_limit_file
+
+ if [ -e "$cgroup_path/$name/cpuset.cpus" ]; then
+ echo 0 >$cgroup_path/$name/cpuset.cpus
+ fi
+ if [ -e "$cgroup_path/$name/cpuset.mems" ]; then
+ echo 0 >$cgroup_path/$name/cpuset.mems
+ fi
+}
+
+function wait_for_hugetlb_memory_to_get_depleted() {
+ local cgroup="$1"
+ local path="/dev/cgroup/memory/$cgroup/hugetlb.${MB}MB.$reservation_usage_file"
+ # Wait for hugetlbfs memory to get depleted.
+ while [ $(cat $path) != 0 ]; do
+ echo Waiting for hugetlb memory to get depleted.
+ cat $path
+ sleep 0.5
+ done
+}
+
+function wait_for_hugetlb_memory_to_get_reserved() {
+ local cgroup="$1"
+ local size="$2"
+
+ local path="/dev/cgroup/memory/$cgroup/hugetlb.${MB}MB.$reservation_usage_file"
+ # Wait for hugetlbfs memory to get written.
+ while [ $(cat $path) != $size ]; do
+ echo Waiting for hugetlb memory reservation to reach size $size.
+ cat $path
+ sleep 0.5
+ done
+}
+
+function wait_for_hugetlb_memory_to_get_written() {
+ local cgroup="$1"
+ local size="$2"
+
+ local path="/dev/cgroup/memory/$cgroup/hugetlb.${MB}MB.$fault_usage_file"
+ # Wait for hugetlbfs memory to get written.
+ while [ $(cat $path) != $size ]; do
+ echo Waiting for hugetlb memory to reach size $size.
+ cat $path
+ sleep 0.5
+ done
+}
+
+function write_hugetlbfs_and_get_usage() {
+ local cgroup="$1"
+ local size="$2"
+ local populate="$3"
+ local write="$4"
+ local path="$5"
+ local method="$6"
+ local private="$7"
+ local expect_failure="$8"
+ local reserve="$9"
+
+ # Function return values.
+ reservation_failed=0
+ oom_killed=0
+ hugetlb_difference=0
+ reserved_difference=0
+
+ local hugetlb_usage=$cgroup_path/$cgroup/hugetlb.${MB}MB.$fault_usage_file
+ local reserved_usage=$cgroup_path/$cgroup/hugetlb.${MB}MB.$reservation_usage_file
+
+ local hugetlb_before=$(cat $hugetlb_usage)
+ local reserved_before=$(cat $reserved_usage)
+
+ echo
+ echo Starting:
+ echo hugetlb_usage="$hugetlb_before"
+ echo reserved_usage="$reserved_before"
+ echo expect_failure is "$expect_failure"
+
+ output=$(mktemp)
+ set +e
+ if [[ "$method" == "1" ]] || [[ "$method" == 2 ]] ||
+ [[ "$private" == "-r" ]] && [[ "$expect_failure" != 1 ]]; then
+
+ bash write_hugetlb_memory.sh "$size" "$populate" "$write" \
+ "$cgroup" "$path" "$method" "$private" "-l" "$reserve" 2>&1 | tee $output &
+
+ local write_result=$?
+ local write_pid=$!
+
+ until grep -q -i "DONE" $output; do
+ echo waiting for DONE signal.
+ if ! ps $write_pid > /dev/null
+ then
+ echo "FAIL: The write died"
+ cleanup
+ exit 1
+ fi
+ sleep 0.5
+ done
+
+ echo ================= write_hugetlb_memory.sh output is:
+ cat $output
+ echo ================= end output.
+
+ if [[ "$populate" == "-o" ]] || [[ "$write" == "-w" ]]; then
+ wait_for_hugetlb_memory_to_get_written "$cgroup" "$size"
+ elif [[ "$reserve" != "-n" ]]; then
+ wait_for_hugetlb_memory_to_get_reserved "$cgroup" "$size"
+ else
+ # This case doesn't produce visible effects, but we still have
+ # to wait for the async process to start and execute...
+ sleep 0.5
+ fi
+
+ echo write_result is $write_result
+ else
+ bash write_hugetlb_memory.sh "$size" "$populate" "$write" \
+ "$cgroup" "$path" "$method" "$private" "$reserve"
+ local write_result=$?
+
+ if [[ "$reserve" != "-n" ]]; then
+ wait_for_hugetlb_memory_to_get_reserved "$cgroup" "$size"
+ fi
+ fi
+ set -e
+
+ if [[ "$write_result" == 1 ]]; then
+ reservation_failed=1
+ fi
+
+ # On linus/master, the above process gets SIGBUS'd on oomkill, with
+ # return code 135. On earlier kernels, it gets actual oomkill, with return
+ # code 137, so just check for both conditions in case we're testing
+ # against an earlier kernel.
+ if [[ "$write_result" == 135 ]] || [[ "$write_result" == 137 ]]; then
+ oom_killed=1
+ fi
+
+ local hugetlb_after=$(cat $hugetlb_usage)
+ local reserved_after=$(cat $reserved_usage)
+
+ echo After write:
+ echo hugetlb_usage="$hugetlb_after"
+ echo reserved_usage="$reserved_after"
+
+ hugetlb_difference=$(($hugetlb_after - $hugetlb_before))
+ reserved_difference=$(($reserved_after - $reserved_before))
+}
+
+function cleanup_hugetlb_memory() {
+ set +e
+ local cgroup="$1"
+ if [[ "$(pgrep -f write_to_hugetlbfs)" != "" ]]; then
+ echo killing write_to_hugetlbfs
+ killall -2 write_to_hugetlbfs
+ wait_for_hugetlb_memory_to_get_depleted $cgroup
+ fi
+ set -e
+
+ if [[ -e /mnt/huge ]]; then
+ rm -rf /mnt/huge/*
+ umount /mnt/huge
+ rmdir /mnt/huge
+ fi
+}
+
+function run_test() {
+ local size=$(($1 * ${MB} * 1024 * 1024))
+ local populate="$2"
+ local write="$3"
+ local cgroup_limit=$(($4 * ${MB} * 1024 * 1024))
+ local reservation_limit=$(($5 * ${MB} * 1024 * 1024))
+ local nr_hugepages="$6"
+ local method="$7"
+ local private="$8"
+ local expect_failure="$9"
+ local reserve="${10}"
+
+ # Function return values.
+ hugetlb_difference=0
+ reserved_difference=0
+ reservation_failed=0
+ oom_killed=0
+
+ echo nr hugepages = "$nr_hugepages"
+ echo "$nr_hugepages" >/proc/sys/vm/nr_hugepages
+
+ setup_cgroup "hugetlb_cgroup_test" "$cgroup_limit" "$reservation_limit"
+
+ mkdir -p /mnt/huge
+ mount -t hugetlbfs -o pagesize=${MB}M,size=256M none /mnt/huge
+
+ write_hugetlbfs_and_get_usage "hugetlb_cgroup_test" "$size" "$populate" \
+ "$write" "/mnt/huge/test" "$method" "$private" "$expect_failure" \
+ "$reserve"
+
+ cleanup_hugetlb_memory "hugetlb_cgroup_test"
+
+ local final_hugetlb=$(cat $cgroup_path/hugetlb_cgroup_test/hugetlb.${MB}MB.$fault_usage_file)
+ local final_reservation=$(cat $cgroup_path/hugetlb_cgroup_test/hugetlb.${MB}MB.$reservation_usage_file)
+
+ echo $hugetlb_difference
+ echo $reserved_difference
+ expect_equal "0" "$final_hugetlb" "final hugetlb is not zero"
+ expect_equal "0" "$final_reservation" "final reservation is not zero"
+}
+
+function run_multiple_cgroup_test() {
+ local size1="$1"
+ local populate1="$2"
+ local write1="$3"
+ local cgroup_limit1="$4"
+ local reservation_limit1="$5"
+
+ local size2="$6"
+ local populate2="$7"
+ local write2="$8"
+ local cgroup_limit2="$9"
+ local reservation_limit2="${10}"
+
+ local nr_hugepages="${11}"
+ local method="${12}"
+ local private="${13}"
+ local expect_failure="${14}"
+ local reserve="${15}"
+
+ # Function return values.
+ hugetlb_difference1=0
+ reserved_difference1=0
+ reservation_failed1=0
+ oom_killed1=0
+
+ hugetlb_difference2=0
+ reserved_difference2=0
+ reservation_failed2=0
+ oom_killed2=0
+
+ echo nr hugepages = "$nr_hugepages"
+ echo "$nr_hugepages" >/proc/sys/vm/nr_hugepages
+
+ setup_cgroup "hugetlb_cgroup_test1" "$cgroup_limit1" "$reservation_limit1"
+ setup_cgroup "hugetlb_cgroup_test2" "$cgroup_limit2" "$reservation_limit2"
+
+ mkdir -p /mnt/huge
+ mount -t hugetlbfs -o pagesize=${MB}M,size=256M none /mnt/huge
+
+ write_hugetlbfs_and_get_usage "hugetlb_cgroup_test1" "$size1" \
+ "$populate1" "$write1" "/mnt/huge/test1" "$method" "$private" \
+ "$expect_failure" "$reserve"
+
+ hugetlb_difference1=$hugetlb_difference
+ reserved_difference1=$reserved_difference
+ reservation_failed1=$reservation_failed
+ oom_killed1=$oom_killed
+
+ local cgroup1_hugetlb_usage=$cgroup_path/hugetlb_cgroup_test1/hugetlb.${MB}MB.$fault_usage_file
+ local cgroup1_reservation_usage=$cgroup_path/hugetlb_cgroup_test1/hugetlb.${MB}MB.$reservation_usage_file
+ local cgroup2_hugetlb_usage=$cgroup_path/hugetlb_cgroup_test2/hugetlb.${MB}MB.$fault_usage_file
+ local cgroup2_reservation_usage=$cgroup_path/hugetlb_cgroup_test2/hugetlb.${MB}MB.$reservation_usage_file
+
+ local usage_before_second_write=$(cat $cgroup1_hugetlb_usage)
+ local reservation_usage_before_second_write=$(cat $cgroup1_reservation_usage)
+
+ write_hugetlbfs_and_get_usage "hugetlb_cgroup_test2" "$size2" \
+ "$populate2" "$write2" "/mnt/huge/test2" "$method" "$private" \
+ "$expect_failure" "$reserve"
+
+ hugetlb_difference2=$hugetlb_difference
+ reserved_difference2=$reserved_difference
+ reservation_failed2=$reservation_failed
+ oom_killed2=$oom_killed
+
+ expect_equal "$usage_before_second_write" \
+ "$(cat $cgroup1_hugetlb_usage)" "Usage changed."
+ expect_equal "$reservation_usage_before_second_write" \
+ "$(cat $cgroup1_reservation_usage)" "Reservation usage changed."
+
+ cleanup_hugetlb_memory
+
+ local final_hugetlb=$(cat $cgroup1_hugetlb_usage)
+ local final_reservation=$(cat $cgroup1_reservation_usage)
+
+ expect_equal "0" "$final_hugetlb" \
+ "hugetlbt_cgroup_test1 final hugetlb is not zero"
+ expect_equal "0" "$final_reservation" \
+ "hugetlbt_cgroup_test1 final reservation is not zero"
+
+ local final_hugetlb=$(cat $cgroup2_hugetlb_usage)
+ local final_reservation=$(cat $cgroup2_reservation_usage)
+
+ expect_equal "0" "$final_hugetlb" \
+ "hugetlb_cgroup_test2 final hugetlb is not zero"
+ expect_equal "0" "$final_reservation" \
+ "hugetlb_cgroup_test2 final reservation is not zero"
+}
+
+cleanup
+
+for populate in "" "-o"; do
+ for method in 0 1 2; do
+ for private in "" "-r"; do
+ for reserve in "" "-n"; do
+
+ # Skip mmap(MAP_HUGETLB | MAP_SHARED). Doesn't seem to be supported.
+ if [[ "$method" == 1 ]] && [[ "$private" == "" ]]; then
+ continue
+ fi
+
+ # Skip populated shmem tests. Doesn't seem to be supported.
+ if [[ "$method" == 2"" ]] && [[ "$populate" == "-o" ]]; then
+ continue
+ fi
+
+ if [[ "$method" == 2"" ]] && [[ "$reserve" == "-n" ]]; then
+ continue
+ fi
+
+ cleanup
+ echo
+ echo
+ echo
+ echo Test normal case.
+ echo private=$private, populate=$populate, method=$method, reserve=$reserve
+ run_test 5 "$populate" "" 10 10 10 "$method" "$private" "0" "$reserve"
+
+ echo Memory charged to hugtlb=$hugetlb_difference
+ echo Memory charged to reservation=$reserved_difference
+
+ if [[ "$populate" == "-o" ]]; then
+ expect_equal "$((5 * $MB * 1024 * 1024))" "$hugetlb_difference" \
+ "Reserved memory charged to hugetlb cgroup."
+ else
+ expect_equal "0" "$hugetlb_difference" \
+ "Reserved memory charged to hugetlb cgroup."
+ fi
+
+ if [[ "$reserve" != "-n" ]] || [[ "$populate" == "-o" ]]; then
+ expect_equal "$((5 * $MB * 1024 * 1024))" "$reserved_difference" \
+ "Reserved memory not charged to reservation usage."
+ else
+ expect_equal "0" "$reserved_difference" \
+ "Reserved memory not charged to reservation usage."
+ fi
+
+ echo 'PASS'
+
+ cleanup
+ echo
+ echo
+ echo
+ echo Test normal case with write.
+ echo private=$private, populate=$populate, method=$method, reserve=$reserve
+ run_test 5 "$populate" '-w' 5 5 10 "$method" "$private" "0" "$reserve"
+
+ echo Memory charged to hugtlb=$hugetlb_difference
+ echo Memory charged to reservation=$reserved_difference
+
+ expect_equal "$((5 * $MB * 1024 * 1024))" "$hugetlb_difference" \
+ "Reserved memory charged to hugetlb cgroup."
+
+ expect_equal "$((5 * $MB * 1024 * 1024))" "$reserved_difference" \
+ "Reserved memory not charged to reservation usage."
+
+ echo 'PASS'
+
+ cleanup
+ continue
+ echo
+ echo
+ echo
+ echo Test more than reservation case.
+ echo private=$private, populate=$populate, method=$method, reserve=$reserve
+
+ if [ "$reserve" != "-n" ]; then
+ run_test "5" "$populate" '' "10" "2" "10" "$method" "$private" "1" \
+ "$reserve"
+
+ expect_equal "1" "$reservation_failed" "Reservation succeeded."
+ fi
+
+ echo 'PASS'
+
+ cleanup
+
+ echo
+ echo
+ echo
+ echo Test more than cgroup limit case.
+ echo private=$private, populate=$populate, method=$method, reserve=$reserve
+
+ # Not sure if shm memory can be cleaned up when the process gets sigbus'd.
+ if [[ "$method" != 2 ]]; then
+ run_test 5 "$populate" "-w" 2 10 10 "$method" "$private" "1" "$reserve"
+
+ expect_equal "1" "$oom_killed" "Not oom killed."
+ fi
+ echo 'PASS'
+
+ cleanup
+
+ echo
+ echo
+ echo
+ echo Test normal case, multiple cgroups.
+ echo private=$private, populate=$populate, method=$method, reserve=$reserve
+ run_multiple_cgroup_test "3" "$populate" "" "10" "10" "5" \
+ "$populate" "" "10" "10" "10" \
+ "$method" "$private" "0" "$reserve"
+
+ echo Memory charged to hugtlb1=$hugetlb_difference1
+ echo Memory charged to reservation1=$reserved_difference1
+ echo Memory charged to hugtlb2=$hugetlb_difference2
+ echo Memory charged to reservation2=$reserved_difference2
+
+ if [[ "$reserve" != "-n" ]] || [[ "$populate" == "-o" ]]; then
+ expect_equal "3" "$reserved_difference1" \
+ "Incorrect reservations charged to cgroup 1."
+
+ expect_equal "5" "$reserved_difference2" \
+ "Incorrect reservation charged to cgroup 2."
+
+ else
+ expect_equal "0" "$reserved_difference1" \
+ "Incorrect reservations charged to cgroup 1."
+
+ expect_equal "0" "$reserved_difference2" \
+ "Incorrect reservation charged to cgroup 2."
+ fi
+
+ if [[ "$populate" == "-o" ]]; then
+ expect_equal "3" "$hugetlb_difference1" \
+ "Incorrect hugetlb charged to cgroup 1."
+
+ expect_equal "5" "$hugetlb_difference2" \
+ "Incorrect hugetlb charged to cgroup 2."
+
+ else
+ expect_equal "0" "$hugetlb_difference1" \
+ "Incorrect hugetlb charged to cgroup 1."
+
+ expect_equal "0" "$hugetlb_difference2" \
+ "Incorrect hugetlb charged to cgroup 2."
+ fi
+ echo 'PASS'
+
+ cleanup
+ echo
+ echo
+ echo
+ echo Test normal case with write, multiple cgroups.
+ echo private=$private, populate=$populate, method=$method, reserve=$reserve
+ run_multiple_cgroup_test "3" "$populate" "-w" "10" "10" "5" \
+ "$populate" "-w" "10" "10" "10" \
+ "$method" "$private" "0" "$reserve"
+
+ echo Memory charged to hugtlb1=$hugetlb_difference1
+ echo Memory charged to reservation1=$reserved_difference1
+ echo Memory charged to hugtlb2=$hugetlb_difference2
+ echo Memory charged to reservation2=$reserved_difference2
+
+ expect_equal "3" "$hugetlb_difference1" \
+ "Incorrect hugetlb charged to cgroup 1."
+
+ expect_equal "3" "$reserved_difference1" \
+ "Incorrect reservation charged to cgroup 1."
+
+ expect_equal "5" "$hugetlb_difference2" \
+ "Incorrect hugetlb charged to cgroup 2."
+
+ expect_equal "5" "$reserved_difference2" \
+ "Incorrected reservation charged to cgroup 2."
+ echo 'PASS'
+
+ cleanup
+
+ done # reserve
+ done # private
+ done # populate
+done # method
+
+umount $cgroup_path
+rmdir $cgroup_path
diff --git a/tools/testing/selftests/vm/config b/tools/testing/selftests/vm/config
index 93b90a9b1eeb..3ba674b64fa9 100644
--- a/tools/testing/selftests/vm/config
+++ b/tools/testing/selftests/vm/config
@@ -1,3 +1,5 @@
CONFIG_SYSVIPC=y
CONFIG_USERFAULTFD=y
CONFIG_TEST_VMALLOC=m
+CONFIG_DEVICE_PRIVATE=y
+CONFIG_TEST_HMM=m
diff --git a/tools/testing/selftests/vm/gup_benchmark.c b/tools/testing/selftests/vm/gup_benchmark.c
index 389327e9b30a..43b4dfe161a2 100644
--- a/tools/testing/selftests/vm/gup_benchmark.c
+++ b/tools/testing/selftests/vm/gup_benchmark.c
@@ -18,6 +18,10 @@
#define GUP_LONGTERM_BENCHMARK _IOWR('g', 2, struct gup_benchmark)
#define GUP_BENCHMARK _IOWR('g', 3, struct gup_benchmark)
+/* Similar to above, but use FOLL_PIN instead of FOLL_GET. */
+#define PIN_FAST_BENCHMARK _IOWR('g', 4, struct gup_benchmark)
+#define PIN_BENCHMARK _IOWR('g', 5, struct gup_benchmark)
+
/* Just the flags we need, copied from mm.h: */
#define FOLL_WRITE 0x01 /* check pte is writable */
@@ -40,8 +44,14 @@ int main(int argc, char **argv)
char *file = "/dev/zero";
char *p;
- while ((opt = getopt(argc, argv, "m:r:n:f:tTLUwSH")) != -1) {
+ while ((opt = getopt(argc, argv, "m:r:n:f:abtTLUuwSH")) != -1) {
switch (opt) {
+ case 'a':
+ cmd = PIN_FAST_BENCHMARK;
+ break;
+ case 'b':
+ cmd = PIN_BENCHMARK;
+ break;
case 'm':
size = atoi(optarg) * MB;
break;
@@ -63,6 +73,9 @@ int main(int argc, char **argv)
case 'U':
cmd = GUP_BENCHMARK;
break;
+ case 'u':
+ cmd = GUP_FAST_BENCHMARK;
+ break;
case 'w':
write = 1;
break;
diff --git a/tools/testing/selftests/vm/hmm-tests.c b/tools/testing/selftests/vm/hmm-tests.c
new file mode 100644
index 000000000000..79db22604019
--- /dev/null
+++ b/tools/testing/selftests/vm/hmm-tests.c
@@ -0,0 +1,1359 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * HMM stands for Heterogeneous Memory Management, it is a helper layer inside
+ * the linux kernel to help device drivers mirror a process address space in
+ * the device. This allows the device to use the same address space which
+ * makes communication and data exchange a lot easier.
+ *
+ * This framework's sole purpose is to exercise various code paths inside
+ * the kernel to make sure that HMM performs as expected and to flush out any
+ * bugs.
+ */
+
+#include "../kselftest_harness.h"
+
+#include <errno.h>
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdint.h>
+#include <unistd.h>
+#include <strings.h>
+#include <time.h>
+#include <pthread.h>
+#include <hugetlbfs.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <sys/mman.h>
+#include <sys/ioctl.h>
+
+/*
+ * This is a private UAPI to the kernel test module so it isn't exported
+ * in the usual include/uapi/... directory.
+ */
+#include "../../../../lib/test_hmm_uapi.h"
+
+struct hmm_buffer {
+ void *ptr;
+ void *mirror;
+ unsigned long size;
+ int fd;
+ uint64_t cpages;
+ uint64_t faults;
+};
+
+#define TWOMEG (1 << 21)
+#define HMM_BUFFER_SIZE (1024 << 12)
+#define HMM_PATH_MAX 64
+#define NTIMES 256
+
+#define ALIGN(x, a) (((x) + (a - 1)) & (~((a) - 1)))
+
+FIXTURE(hmm)
+{
+ int fd;
+ unsigned int page_size;
+ unsigned int page_shift;
+};
+
+FIXTURE(hmm2)
+{
+ int fd0;
+ int fd1;
+ unsigned int page_size;
+ unsigned int page_shift;
+};
+
+static int hmm_open(int unit)
+{
+ char pathname[HMM_PATH_MAX];
+ int fd;
+
+ snprintf(pathname, sizeof(pathname), "/dev/hmm_dmirror%d", unit);
+ fd = open(pathname, O_RDWR, 0);
+ if (fd < 0)
+ fprintf(stderr, "could not open hmm dmirror driver (%s)\n",
+ pathname);
+ return fd;
+}
+
+FIXTURE_SETUP(hmm)
+{
+ self->page_size = sysconf(_SC_PAGE_SIZE);
+ self->page_shift = ffs(self->page_size) - 1;
+
+ self->fd = hmm_open(0);
+ ASSERT_GE(self->fd, 0);
+}
+
+FIXTURE_SETUP(hmm2)
+{
+ self->page_size = sysconf(_SC_PAGE_SIZE);
+ self->page_shift = ffs(self->page_size) - 1;
+
+ self->fd0 = hmm_open(0);
+ ASSERT_GE(self->fd0, 0);
+ self->fd1 = hmm_open(1);
+ ASSERT_GE(self->fd1, 0);
+}
+
+FIXTURE_TEARDOWN(hmm)
+{
+ int ret = close(self->fd);
+
+ ASSERT_EQ(ret, 0);
+ self->fd = -1;
+}
+
+FIXTURE_TEARDOWN(hmm2)
+{
+ int ret = close(self->fd0);
+
+ ASSERT_EQ(ret, 0);
+ self->fd0 = -1;
+
+ ret = close(self->fd1);
+ ASSERT_EQ(ret, 0);
+ self->fd1 = -1;
+}
+
+static int hmm_dmirror_cmd(int fd,
+ unsigned long request,
+ struct hmm_buffer *buffer,
+ unsigned long npages)
+{
+ struct hmm_dmirror_cmd cmd;
+ int ret;
+
+ /* Simulate a device reading system memory. */
+ cmd.addr = (__u64)buffer->ptr;
+ cmd.ptr = (__u64)buffer->mirror;
+ cmd.npages = npages;
+
+ for (;;) {
+ ret = ioctl(fd, request, &cmd);
+ if (ret == 0)
+ break;
+ if (errno == EINTR)
+ continue;
+ return -errno;
+ }
+ buffer->cpages = cmd.cpages;
+ buffer->faults = cmd.faults;
+
+ return 0;
+}
+
+static void hmm_buffer_free(struct hmm_buffer *buffer)
+{
+ if (buffer == NULL)
+ return;
+
+ if (buffer->ptr)
+ munmap(buffer->ptr, buffer->size);
+ free(buffer->mirror);
+ free(buffer);
+}
+
+/*
+ * Create a temporary file that will be deleted on close.
+ */
+static int hmm_create_file(unsigned long size)
+{
+ char path[HMM_PATH_MAX];
+ int fd;
+
+ strcpy(path, "/tmp");
+ fd = open(path, O_TMPFILE | O_EXCL | O_RDWR, 0600);
+ if (fd >= 0) {
+ int r;
+
+ do {
+ r = ftruncate(fd, size);
+ } while (r == -1 && errno == EINTR);
+ if (!r)
+ return fd;
+ close(fd);
+ }
+ return -1;
+}
+
+/*
+ * Return a random unsigned number.
+ */
+static unsigned int hmm_random(void)
+{
+ static int fd = -1;
+ unsigned int r;
+
+ if (fd < 0) {
+ fd = open("/dev/urandom", O_RDONLY);
+ if (fd < 0) {
+ fprintf(stderr, "%s:%d failed to open /dev/urandom\n",
+ __FILE__, __LINE__);
+ return ~0U;
+ }
+ }
+ read(fd, &r, sizeof(r));
+ return r;
+}
+
+static void hmm_nanosleep(unsigned int n)
+{
+ struct timespec t;
+
+ t.tv_sec = 0;
+ t.tv_nsec = n;
+ nanosleep(&t, NULL);
+}
+
+/*
+ * Simple NULL test of device open/close.
+ */
+TEST_F(hmm, open_close)
+{
+}
+
+/*
+ * Read private anonymous memory.
+ */
+TEST_F(hmm, anon_read)
+{
+ struct hmm_buffer *buffer;
+ unsigned long npages;
+ unsigned long size;
+ unsigned long i;
+ int *ptr;
+ int ret;
+ int val;
+
+ npages = ALIGN(HMM_BUFFER_SIZE, self->page_size) >> self->page_shift;
+ ASSERT_NE(npages, 0);
+ size = npages << self->page_shift;
+
+ buffer = malloc(sizeof(*buffer));
+ ASSERT_NE(buffer, NULL);
+
+ buffer->fd = -1;
+ buffer->size = size;
+ buffer->mirror = malloc(size);
+ ASSERT_NE(buffer->mirror, NULL);
+
+ buffer->ptr = mmap(NULL, size,
+ PROT_READ | PROT_WRITE,
+ MAP_PRIVATE | MAP_ANONYMOUS,
+ buffer->fd, 0);
+ ASSERT_NE(buffer->ptr, MAP_FAILED);
+
+ /*
+ * Initialize buffer in system memory but leave the first two pages
+ * zero (pte_none and pfn_zero).
+ */
+ i = 2 * self->page_size / sizeof(*ptr);
+ for (ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+ ptr[i] = i;
+
+ /* Set buffer permission to read-only. */
+ ret = mprotect(buffer->ptr, size, PROT_READ);
+ ASSERT_EQ(ret, 0);
+
+ /* Populate the CPU page table with a special zero page. */
+ val = *(int *)(buffer->ptr + self->page_size);
+ ASSERT_EQ(val, 0);
+
+ /* Simulate a device reading system memory. */
+ ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_READ, buffer, npages);
+ ASSERT_EQ(ret, 0);
+ ASSERT_EQ(buffer->cpages, npages);
+ ASSERT_EQ(buffer->faults, 1);
+
+ /* Check what the device read. */
+ ptr = buffer->mirror;
+ for (i = 0; i < 2 * self->page_size / sizeof(*ptr); ++i)
+ ASSERT_EQ(ptr[i], 0);
+ for (; i < size / sizeof(*ptr); ++i)
+ ASSERT_EQ(ptr[i], i);
+
+ hmm_buffer_free(buffer);
+}
+
+/*
+ * Read private anonymous memory which has been protected with
+ * mprotect() PROT_NONE.
+ */
+TEST_F(hmm, anon_read_prot)
+{
+ struct hmm_buffer *buffer;
+ unsigned long npages;
+ unsigned long size;
+ unsigned long i;
+ int *ptr;
+ int ret;
+
+ npages = ALIGN(HMM_BUFFER_SIZE, self->page_size) >> self->page_shift;
+ ASSERT_NE(npages, 0);
+ size = npages << self->page_shift;
+
+ buffer = malloc(sizeof(*buffer));
+ ASSERT_NE(buffer, NULL);
+
+ buffer->fd = -1;
+ buffer->size = size;
+ buffer->mirror = malloc(size);
+ ASSERT_NE(buffer->mirror, NULL);
+
+ buffer->ptr = mmap(NULL, size,
+ PROT_READ | PROT_WRITE,
+ MAP_PRIVATE | MAP_ANONYMOUS,
+ buffer->fd, 0);
+ ASSERT_NE(buffer->ptr, MAP_FAILED);
+
+ /* Initialize buffer in system memory. */
+ for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+ ptr[i] = i;
+
+ /* Initialize mirror buffer so we can verify it isn't written. */
+ for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i)
+ ptr[i] = -i;
+
+ /* Protect buffer from reading. */
+ ret = mprotect(buffer->ptr, size, PROT_NONE);
+ ASSERT_EQ(ret, 0);
+
+ /* Simulate a device reading system memory. */
+ ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_READ, buffer, npages);
+ ASSERT_EQ(ret, -EFAULT);
+
+ /* Allow CPU to read the buffer so we can check it. */
+ ret = mprotect(buffer->ptr, size, PROT_READ);
+ ASSERT_EQ(ret, 0);
+ for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+ ASSERT_EQ(ptr[i], i);
+
+ /* Check what the device read. */
+ for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i)
+ ASSERT_EQ(ptr[i], -i);
+
+ hmm_buffer_free(buffer);
+}
+
+/*
+ * Write private anonymous memory.
+ */
+TEST_F(hmm, anon_write)
+{
+ struct hmm_buffer *buffer;
+ unsigned long npages;
+ unsigned long size;
+ unsigned long i;
+ int *ptr;
+ int ret;
+
+ npages = ALIGN(HMM_BUFFER_SIZE, self->page_size) >> self->page_shift;
+ ASSERT_NE(npages, 0);
+ size = npages << self->page_shift;
+
+ buffer = malloc(sizeof(*buffer));
+ ASSERT_NE(buffer, NULL);
+
+ buffer->fd = -1;
+ buffer->size = size;
+ buffer->mirror = malloc(size);
+ ASSERT_NE(buffer->mirror, NULL);
+
+ buffer->ptr = mmap(NULL, size,
+ PROT_READ | PROT_WRITE,
+ MAP_PRIVATE | MAP_ANONYMOUS,
+ buffer->fd, 0);
+ ASSERT_NE(buffer->ptr, MAP_FAILED);
+
+ /* Initialize data that the device will write to buffer->ptr. */
+ for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i)
+ ptr[i] = i;
+
+ /* Simulate a device writing system memory. */
+ ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_WRITE, buffer, npages);
+ ASSERT_EQ(ret, 0);
+ ASSERT_EQ(buffer->cpages, npages);
+ ASSERT_EQ(buffer->faults, 1);
+
+ /* Check what the device wrote. */
+ for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+ ASSERT_EQ(ptr[i], i);
+
+ hmm_buffer_free(buffer);
+}
+
+/*
+ * Write private anonymous memory which has been protected with
+ * mprotect() PROT_READ.
+ */
+TEST_F(hmm, anon_write_prot)
+{
+ struct hmm_buffer *buffer;
+ unsigned long npages;
+ unsigned long size;
+ unsigned long i;
+ int *ptr;
+ int ret;
+
+ npages = ALIGN(HMM_BUFFER_SIZE, self->page_size) >> self->page_shift;
+ ASSERT_NE(npages, 0);
+ size = npages << self->page_shift;
+
+ buffer = malloc(sizeof(*buffer));
+ ASSERT_NE(buffer, NULL);
+
+ buffer->fd = -1;
+ buffer->size = size;
+ buffer->mirror = malloc(size);
+ ASSERT_NE(buffer->mirror, NULL);
+
+ buffer->ptr = mmap(NULL, size,
+ PROT_READ,
+ MAP_PRIVATE | MAP_ANONYMOUS,
+ buffer->fd, 0);
+ ASSERT_NE(buffer->ptr, MAP_FAILED);
+
+ /* Simulate a device reading a zero page of memory. */
+ ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_READ, buffer, 1);
+ ASSERT_EQ(ret, 0);
+ ASSERT_EQ(buffer->cpages, 1);
+ ASSERT_EQ(buffer->faults, 1);
+
+ /* Initialize data that the device will write to buffer->ptr. */
+ for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i)
+ ptr[i] = i;
+
+ /* Simulate a device writing system memory. */
+ ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_WRITE, buffer, npages);
+ ASSERT_EQ(ret, -EPERM);
+
+ /* Check what the device wrote. */
+ for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+ ASSERT_EQ(ptr[i], 0);
+
+ /* Now allow writing and see that the zero page is replaced. */
+ ret = mprotect(buffer->ptr, size, PROT_WRITE | PROT_READ);
+ ASSERT_EQ(ret, 0);
+
+ /* Simulate a device writing system memory. */
+ ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_WRITE, buffer, npages);
+ ASSERT_EQ(ret, 0);
+ ASSERT_EQ(buffer->cpages, npages);
+ ASSERT_EQ(buffer->faults, 1);
+
+ /* Check what the device wrote. */
+ for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+ ASSERT_EQ(ptr[i], i);
+
+ hmm_buffer_free(buffer);
+}
+
+/*
+ * Check that a device writing an anonymous private mapping
+ * will copy-on-write if a child process inherits the mapping.
+ */
+TEST_F(hmm, anon_write_child)
+{
+ struct hmm_buffer *buffer;
+ unsigned long npages;
+ unsigned long size;
+ unsigned long i;
+ int *ptr;
+ pid_t pid;
+ int child_fd;
+ int ret;
+
+ npages = ALIGN(HMM_BUFFER_SIZE, self->page_size) >> self->page_shift;
+ ASSERT_NE(npages, 0);
+ size = npages << self->page_shift;
+
+ buffer = malloc(sizeof(*buffer));
+ ASSERT_NE(buffer, NULL);
+
+ buffer->fd = -1;
+ buffer->size = size;
+ buffer->mirror = malloc(size);
+ ASSERT_NE(buffer->mirror, NULL);
+
+ buffer->ptr = mmap(NULL, size,
+ PROT_READ | PROT_WRITE,
+ MAP_PRIVATE | MAP_ANONYMOUS,
+ buffer->fd, 0);
+ ASSERT_NE(buffer->ptr, MAP_FAILED);
+
+ /* Initialize buffer->ptr so we can tell if it is written. */
+ for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+ ptr[i] = i;
+
+ /* Initialize data that the device will write to buffer->ptr. */
+ for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i)
+ ptr[i] = -i;
+
+ pid = fork();
+ if (pid == -1)
+ ASSERT_EQ(pid, 0);
+ if (pid != 0) {
+ waitpid(pid, &ret, 0);
+ ASSERT_EQ(WIFEXITED(ret), 1);
+
+ /* Check that the parent's buffer did not change. */
+ for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+ ASSERT_EQ(ptr[i], i);
+ return;
+ }
+
+ /* Check that we see the parent's values. */
+ for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+ ASSERT_EQ(ptr[i], i);
+ for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i)
+ ASSERT_EQ(ptr[i], -i);
+
+ /* The child process needs its own mirror to its own mm. */
+ child_fd = hmm_open(0);
+ ASSERT_GE(child_fd, 0);
+
+ /* Simulate a device writing system memory. */
+ ret = hmm_dmirror_cmd(child_fd, HMM_DMIRROR_WRITE, buffer, npages);
+ ASSERT_EQ(ret, 0);
+ ASSERT_EQ(buffer->cpages, npages);
+ ASSERT_EQ(buffer->faults, 1);
+
+ /* Check what the device wrote. */
+ for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+ ASSERT_EQ(ptr[i], -i);
+
+ close(child_fd);
+ exit(0);
+}
+
+/*
+ * Check that a device writing an anonymous shared mapping
+ * will not copy-on-write if a child process inherits the mapping.
+ */
+TEST_F(hmm, anon_write_child_shared)
+{
+ struct hmm_buffer *buffer;
+ unsigned long npages;
+ unsigned long size;
+ unsigned long i;
+ int *ptr;
+ pid_t pid;
+ int child_fd;
+ int ret;
+
+ npages = ALIGN(HMM_BUFFER_SIZE, self->page_size) >> self->page_shift;
+ ASSERT_NE(npages, 0);
+ size = npages << self->page_shift;
+
+ buffer = malloc(sizeof(*buffer));
+ ASSERT_NE(buffer, NULL);
+
+ buffer->fd = -1;
+ buffer->size = size;
+ buffer->mirror = malloc(size);
+ ASSERT_NE(buffer->mirror, NULL);
+
+ buffer->ptr = mmap(NULL, size,
+ PROT_READ | PROT_WRITE,
+ MAP_SHARED | MAP_ANONYMOUS,
+ buffer->fd, 0);
+ ASSERT_NE(buffer->ptr, MAP_FAILED);
+
+ /* Initialize buffer->ptr so we can tell if it is written. */
+ for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+ ptr[i] = i;
+
+ /* Initialize data that the device will write to buffer->ptr. */
+ for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i)
+ ptr[i] = -i;
+
+ pid = fork();
+ if (pid == -1)
+ ASSERT_EQ(pid, 0);
+ if (pid != 0) {
+ waitpid(pid, &ret, 0);
+ ASSERT_EQ(WIFEXITED(ret), 1);
+
+ /* Check that the parent's buffer did change. */
+ for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+ ASSERT_EQ(ptr[i], -i);
+ return;
+ }
+
+ /* Check that we see the parent's values. */
+ for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+ ASSERT_EQ(ptr[i], i);
+ for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i)
+ ASSERT_EQ(ptr[i], -i);
+
+ /* The child process needs its own mirror to its own mm. */
+ child_fd = hmm_open(0);
+ ASSERT_GE(child_fd, 0);
+
+ /* Simulate a device writing system memory. */
+ ret = hmm_dmirror_cmd(child_fd, HMM_DMIRROR_WRITE, buffer, npages);
+ ASSERT_EQ(ret, 0);
+ ASSERT_EQ(buffer->cpages, npages);
+ ASSERT_EQ(buffer->faults, 1);
+
+ /* Check what the device wrote. */
+ for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+ ASSERT_EQ(ptr[i], -i);
+
+ close(child_fd);
+ exit(0);
+}
+
+/*
+ * Write private anonymous huge page.
+ */
+TEST_F(hmm, anon_write_huge)
+{
+ struct hmm_buffer *buffer;
+ unsigned long npages;
+ unsigned long size;
+ unsigned long i;
+ void *old_ptr;
+ void *map;
+ int *ptr;
+ int ret;
+
+ size = 2 * TWOMEG;
+
+ buffer = malloc(sizeof(*buffer));
+ ASSERT_NE(buffer, NULL);
+
+ buffer->fd = -1;
+ buffer->size = size;
+ buffer->mirror = malloc(size);
+ ASSERT_NE(buffer->mirror, NULL);
+
+ buffer->ptr = mmap(NULL, size,
+ PROT_READ | PROT_WRITE,
+ MAP_PRIVATE | MAP_ANONYMOUS,
+ buffer->fd, 0);
+ ASSERT_NE(buffer->ptr, MAP_FAILED);
+
+ size = TWOMEG;
+ npages = size >> self->page_shift;
+ map = (void *)ALIGN((uintptr_t)buffer->ptr, size);
+ ret = madvise(map, size, MADV_HUGEPAGE);
+ ASSERT_EQ(ret, 0);
+ old_ptr = buffer->ptr;
+ buffer->ptr = map;
+
+ /* Initialize data that the device will write to buffer->ptr. */
+ for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i)
+ ptr[i] = i;
+
+ /* Simulate a device writing system memory. */
+ ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_WRITE, buffer, npages);
+ ASSERT_EQ(ret, 0);
+ ASSERT_EQ(buffer->cpages, npages);
+ ASSERT_EQ(buffer->faults, 1);
+
+ /* Check what the device wrote. */
+ for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+ ASSERT_EQ(ptr[i], i);
+
+ buffer->ptr = old_ptr;
+ hmm_buffer_free(buffer);
+}
+
+/*
+ * Write huge TLBFS page.
+ */
+TEST_F(hmm, anon_write_hugetlbfs)
+{
+ struct hmm_buffer *buffer;
+ unsigned long npages;
+ unsigned long size;
+ unsigned long i;
+ int *ptr;
+ int ret;
+ long pagesizes[4];
+ int n, idx;
+
+ /* Skip test if we can't allocate a hugetlbfs page. */
+
+ n = gethugepagesizes(pagesizes, 4);
+ if (n <= 0)
+ return;
+ for (idx = 0; --n > 0; ) {
+ if (pagesizes[n] < pagesizes[idx])
+ idx = n;
+ }
+ size = ALIGN(TWOMEG, pagesizes[idx]);
+ npages = size >> self->page_shift;
+
+ buffer = malloc(sizeof(*buffer));
+ ASSERT_NE(buffer, NULL);
+
+ buffer->ptr = get_hugepage_region(size, GHR_STRICT);
+ if (buffer->ptr == NULL) {
+ free(buffer);
+ return;
+ }
+
+ buffer->fd = -1;
+ buffer->size = size;
+ buffer->mirror = malloc(size);
+ ASSERT_NE(buffer->mirror, NULL);
+
+ /* Initialize data that the device will write to buffer->ptr. */
+ for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i)
+ ptr[i] = i;
+
+ /* Simulate a device writing system memory. */
+ ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_WRITE, buffer, npages);
+ ASSERT_EQ(ret, 0);
+ ASSERT_EQ(buffer->cpages, npages);
+ ASSERT_EQ(buffer->faults, 1);
+
+ /* Check what the device wrote. */
+ for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+ ASSERT_EQ(ptr[i], i);
+
+ free_hugepage_region(buffer->ptr);
+ buffer->ptr = NULL;
+ hmm_buffer_free(buffer);
+}
+
+/*
+ * Read mmap'ed file memory.
+ */
+TEST_F(hmm, file_read)
+{
+ struct hmm_buffer *buffer;
+ unsigned long npages;
+ unsigned long size;
+ unsigned long i;
+ int *ptr;
+ int ret;
+ int fd;
+ ssize_t len;
+
+ npages = ALIGN(HMM_BUFFER_SIZE, self->page_size) >> self->page_shift;
+ ASSERT_NE(npages, 0);
+ size = npages << self->page_shift;
+
+ fd = hmm_create_file(size);
+ ASSERT_GE(fd, 0);
+
+ buffer = malloc(sizeof(*buffer));
+ ASSERT_NE(buffer, NULL);
+
+ buffer->fd = fd;
+ buffer->size = size;
+ buffer->mirror = malloc(size);
+ ASSERT_NE(buffer->mirror, NULL);
+
+ /* Write initial contents of the file. */
+ for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i)
+ ptr[i] = i;
+ len = pwrite(fd, buffer->mirror, size, 0);
+ ASSERT_EQ(len, size);
+ memset(buffer->mirror, 0, size);
+
+ buffer->ptr = mmap(NULL, size,
+ PROT_READ,
+ MAP_SHARED,
+ buffer->fd, 0);
+ ASSERT_NE(buffer->ptr, MAP_FAILED);
+
+ /* Simulate a device reading system memory. */
+ ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_READ, buffer, npages);
+ ASSERT_EQ(ret, 0);
+ ASSERT_EQ(buffer->cpages, npages);
+ ASSERT_EQ(buffer->faults, 1);
+
+ /* Check what the device read. */
+ for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i)
+ ASSERT_EQ(ptr[i], i);
+
+ hmm_buffer_free(buffer);
+}
+
+/*
+ * Write mmap'ed file memory.
+ */
+TEST_F(hmm, file_write)
+{
+ struct hmm_buffer *buffer;
+ unsigned long npages;
+ unsigned long size;
+ unsigned long i;
+ int *ptr;
+ int ret;
+ int fd;
+ ssize_t len;
+
+ npages = ALIGN(HMM_BUFFER_SIZE, self->page_size) >> self->page_shift;
+ ASSERT_NE(npages, 0);
+ size = npages << self->page_shift;
+
+ fd = hmm_create_file(size);
+ ASSERT_GE(fd, 0);
+
+ buffer = malloc(sizeof(*buffer));
+ ASSERT_NE(buffer, NULL);
+
+ buffer->fd = fd;
+ buffer->size = size;
+ buffer->mirror = malloc(size);
+ ASSERT_NE(buffer->mirror, NULL);
+
+ buffer->ptr = mmap(NULL, size,
+ PROT_READ | PROT_WRITE,
+ MAP_SHARED,
+ buffer->fd, 0);
+ ASSERT_NE(buffer->ptr, MAP_FAILED);
+
+ /* Initialize data that the device will write to buffer->ptr. */
+ for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i)
+ ptr[i] = i;
+
+ /* Simulate a device writing system memory. */
+ ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_WRITE, buffer, npages);
+ ASSERT_EQ(ret, 0);
+ ASSERT_EQ(buffer->cpages, npages);
+ ASSERT_EQ(buffer->faults, 1);
+
+ /* Check what the device wrote. */
+ for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+ ASSERT_EQ(ptr[i], i);
+
+ /* Check that the device also wrote the file. */
+ len = pread(fd, buffer->mirror, size, 0);
+ ASSERT_EQ(len, size);
+ for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i)
+ ASSERT_EQ(ptr[i], i);
+
+ hmm_buffer_free(buffer);
+}
+
+/*
+ * Migrate anonymous memory to device private memory.
+ */
+TEST_F(hmm, migrate)
+{
+ struct hmm_buffer *buffer;
+ unsigned long npages;
+ unsigned long size;
+ unsigned long i;
+ int *ptr;
+ int ret;
+
+ npages = ALIGN(HMM_BUFFER_SIZE, self->page_size) >> self->page_shift;
+ ASSERT_NE(npages, 0);
+ size = npages << self->page_shift;
+
+ buffer = malloc(sizeof(*buffer));
+ ASSERT_NE(buffer, NULL);
+
+ buffer->fd = -1;
+ buffer->size = size;
+ buffer->mirror = malloc(size);
+ ASSERT_NE(buffer->mirror, NULL);
+
+ buffer->ptr = mmap(NULL, size,
+ PROT_READ | PROT_WRITE,
+ MAP_PRIVATE | MAP_ANONYMOUS,
+ buffer->fd, 0);
+ ASSERT_NE(buffer->ptr, MAP_FAILED);
+
+ /* Initialize buffer in system memory. */
+ for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+ ptr[i] = i;
+
+ /* Migrate memory to device. */
+ ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_MIGRATE, buffer, npages);
+ ASSERT_EQ(ret, 0);
+ ASSERT_EQ(buffer->cpages, npages);
+
+ /* Check what the device read. */
+ for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i)
+ ASSERT_EQ(ptr[i], i);
+
+ hmm_buffer_free(buffer);
+}
+
+/*
+ * Migrate anonymous memory to device private memory and fault it back to system
+ * memory.
+ */
+TEST_F(hmm, migrate_fault)
+{
+ struct hmm_buffer *buffer;
+ unsigned long npages;
+ unsigned long size;
+ unsigned long i;
+ int *ptr;
+ int ret;
+
+ npages = ALIGN(HMM_BUFFER_SIZE, self->page_size) >> self->page_shift;
+ ASSERT_NE(npages, 0);
+ size = npages << self->page_shift;
+
+ buffer = malloc(sizeof(*buffer));
+ ASSERT_NE(buffer, NULL);
+
+ buffer->fd = -1;
+ buffer->size = size;
+ buffer->mirror = malloc(size);
+ ASSERT_NE(buffer->mirror, NULL);
+
+ buffer->ptr = mmap(NULL, size,
+ PROT_READ | PROT_WRITE,
+ MAP_PRIVATE | MAP_ANONYMOUS,
+ buffer->fd, 0);
+ ASSERT_NE(buffer->ptr, MAP_FAILED);
+
+ /* Initialize buffer in system memory. */
+ for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+ ptr[i] = i;
+
+ /* Migrate memory to device. */
+ ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_MIGRATE, buffer, npages);
+ ASSERT_EQ(ret, 0);
+ ASSERT_EQ(buffer->cpages, npages);
+
+ /* Check what the device read. */
+ for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i)
+ ASSERT_EQ(ptr[i], i);
+
+ /* Fault pages back to system memory and check them. */
+ for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+ ASSERT_EQ(ptr[i], i);
+
+ hmm_buffer_free(buffer);
+}
+
+/*
+ * Try to migrate various memory types to device private memory.
+ */
+TEST_F(hmm2, migrate_mixed)
+{
+ struct hmm_buffer *buffer;
+ unsigned long npages;
+ unsigned long size;
+ int *ptr;
+ unsigned char *p;
+ int ret;
+ int val;
+
+ npages = 6;
+ size = npages << self->page_shift;
+
+ buffer = malloc(sizeof(*buffer));
+ ASSERT_NE(buffer, NULL);
+
+ buffer->fd = -1;
+ buffer->size = size;
+ buffer->mirror = malloc(size);
+ ASSERT_NE(buffer->mirror, NULL);
+
+ /* Reserve a range of addresses. */
+ buffer->ptr = mmap(NULL, size,
+ PROT_NONE,
+ MAP_PRIVATE | MAP_ANONYMOUS,
+ buffer->fd, 0);
+ ASSERT_NE(buffer->ptr, MAP_FAILED);
+ p = buffer->ptr;
+
+ /* Migrating a protected area should be an error. */
+ ret = hmm_dmirror_cmd(self->fd1, HMM_DMIRROR_MIGRATE, buffer, npages);
+ ASSERT_EQ(ret, -EINVAL);
+
+ /* Punch a hole after the first page address. */
+ ret = munmap(buffer->ptr + self->page_size, self->page_size);
+ ASSERT_EQ(ret, 0);
+
+ /* We expect an error if the vma doesn't cover the range. */
+ ret = hmm_dmirror_cmd(self->fd1, HMM_DMIRROR_MIGRATE, buffer, 3);
+ ASSERT_EQ(ret, -EINVAL);
+
+ /* Page 2 will be a read-only zero page. */
+ ret = mprotect(buffer->ptr + 2 * self->page_size, self->page_size,
+ PROT_READ);
+ ASSERT_EQ(ret, 0);
+ ptr = (int *)(buffer->ptr + 2 * self->page_size);
+ val = *ptr + 3;
+ ASSERT_EQ(val, 3);
+
+ /* Page 3 will be read-only. */
+ ret = mprotect(buffer->ptr + 3 * self->page_size, self->page_size,
+ PROT_READ | PROT_WRITE);
+ ASSERT_EQ(ret, 0);
+ ptr = (int *)(buffer->ptr + 3 * self->page_size);
+ *ptr = val;
+ ret = mprotect(buffer->ptr + 3 * self->page_size, self->page_size,
+ PROT_READ);
+ ASSERT_EQ(ret, 0);
+
+ /* Page 4-5 will be read-write. */
+ ret = mprotect(buffer->ptr + 4 * self->page_size, 2 * self->page_size,
+ PROT_READ | PROT_WRITE);
+ ASSERT_EQ(ret, 0);
+ ptr = (int *)(buffer->ptr + 4 * self->page_size);
+ *ptr = val;
+ ptr = (int *)(buffer->ptr + 5 * self->page_size);
+ *ptr = val;
+
+ /* Now try to migrate pages 2-5 to device 1. */
+ buffer->ptr = p + 2 * self->page_size;
+ ret = hmm_dmirror_cmd(self->fd1, HMM_DMIRROR_MIGRATE, buffer, 4);
+ ASSERT_EQ(ret, 0);
+ ASSERT_EQ(buffer->cpages, 4);
+
+ /* Page 5 won't be migrated to device 0 because it's on device 1. */
+ buffer->ptr = p + 5 * self->page_size;
+ ret = hmm_dmirror_cmd(self->fd0, HMM_DMIRROR_MIGRATE, buffer, 1);
+ ASSERT_EQ(ret, -ENOENT);
+ buffer->ptr = p;
+
+ buffer->ptr = p;
+ hmm_buffer_free(buffer);
+}
+
+/*
+ * Migrate anonymous memory to device private memory and fault it back to system
+ * memory multiple times.
+ */
+TEST_F(hmm, migrate_multiple)
+{
+ struct hmm_buffer *buffer;
+ unsigned long npages;
+ unsigned long size;
+ unsigned long i;
+ unsigned long c;
+ int *ptr;
+ int ret;
+
+ npages = ALIGN(HMM_BUFFER_SIZE, self->page_size) >> self->page_shift;
+ ASSERT_NE(npages, 0);
+ size = npages << self->page_shift;
+
+ for (c = 0; c < NTIMES; c++) {
+ buffer = malloc(sizeof(*buffer));
+ ASSERT_NE(buffer, NULL);
+
+ buffer->fd = -1;
+ buffer->size = size;
+ buffer->mirror = malloc(size);
+ ASSERT_NE(buffer->mirror, NULL);
+
+ buffer->ptr = mmap(NULL, size,
+ PROT_READ | PROT_WRITE,
+ MAP_PRIVATE | MAP_ANONYMOUS,
+ buffer->fd, 0);
+ ASSERT_NE(buffer->ptr, MAP_FAILED);
+
+ /* Initialize buffer in system memory. */
+ for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+ ptr[i] = i;
+
+ /* Migrate memory to device. */
+ ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_MIGRATE, buffer,
+ npages);
+ ASSERT_EQ(ret, 0);
+ ASSERT_EQ(buffer->cpages, npages);
+
+ /* Check what the device read. */
+ for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i)
+ ASSERT_EQ(ptr[i], i);
+
+ /* Fault pages back to system memory and check them. */
+ for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+ ASSERT_EQ(ptr[i], i);
+
+ hmm_buffer_free(buffer);
+ }
+}
+
+/*
+ * Read anonymous memory multiple times.
+ */
+TEST_F(hmm, anon_read_multiple)
+{
+ struct hmm_buffer *buffer;
+ unsigned long npages;
+ unsigned long size;
+ unsigned long i;
+ unsigned long c;
+ int *ptr;
+ int ret;
+
+ npages = ALIGN(HMM_BUFFER_SIZE, self->page_size) >> self->page_shift;
+ ASSERT_NE(npages, 0);
+ size = npages << self->page_shift;
+
+ for (c = 0; c < NTIMES; c++) {
+ buffer = malloc(sizeof(*buffer));
+ ASSERT_NE(buffer, NULL);
+
+ buffer->fd = -1;
+ buffer->size = size;
+ buffer->mirror = malloc(size);
+ ASSERT_NE(buffer->mirror, NULL);
+
+ buffer->ptr = mmap(NULL, size,
+ PROT_READ | PROT_WRITE,
+ MAP_PRIVATE | MAP_ANONYMOUS,
+ buffer->fd, 0);
+ ASSERT_NE(buffer->ptr, MAP_FAILED);
+
+ /* Initialize buffer in system memory. */
+ for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+ ptr[i] = i + c;
+
+ /* Simulate a device reading system memory. */
+ ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_READ, buffer,
+ npages);
+ ASSERT_EQ(ret, 0);
+ ASSERT_EQ(buffer->cpages, npages);
+ ASSERT_EQ(buffer->faults, 1);
+
+ /* Check what the device read. */
+ for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i)
+ ASSERT_EQ(ptr[i], i + c);
+
+ hmm_buffer_free(buffer);
+ }
+}
+
+void *unmap_buffer(void *p)
+{
+ struct hmm_buffer *buffer = p;
+
+ /* Delay for a bit and then unmap buffer while it is being read. */
+ hmm_nanosleep(hmm_random() % 32000);
+ munmap(buffer->ptr + buffer->size / 2, buffer->size / 2);
+ buffer->ptr = NULL;
+
+ return NULL;
+}
+
+/*
+ * Try reading anonymous memory while it is being unmapped.
+ */
+TEST_F(hmm, anon_teardown)
+{
+ unsigned long npages;
+ unsigned long size;
+ unsigned long c;
+ void *ret;
+
+ npages = ALIGN(HMM_BUFFER_SIZE, self->page_size) >> self->page_shift;
+ ASSERT_NE(npages, 0);
+ size = npages << self->page_shift;
+
+ for (c = 0; c < NTIMES; ++c) {
+ pthread_t thread;
+ struct hmm_buffer *buffer;
+ unsigned long i;
+ int *ptr;
+ int rc;
+
+ buffer = malloc(sizeof(*buffer));
+ ASSERT_NE(buffer, NULL);
+
+ buffer->fd = -1;
+ buffer->size = size;
+ buffer->mirror = malloc(size);
+ ASSERT_NE(buffer->mirror, NULL);
+
+ buffer->ptr = mmap(NULL, size,
+ PROT_READ | PROT_WRITE,
+ MAP_PRIVATE | MAP_ANONYMOUS,
+ buffer->fd, 0);
+ ASSERT_NE(buffer->ptr, MAP_FAILED);
+
+ /* Initialize buffer in system memory. */
+ for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+ ptr[i] = i + c;
+
+ rc = pthread_create(&thread, NULL, unmap_buffer, buffer);
+ ASSERT_EQ(rc, 0);
+
+ /* Simulate a device reading system memory. */
+ rc = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_READ, buffer,
+ npages);
+ if (rc == 0) {
+ ASSERT_EQ(buffer->cpages, npages);
+ ASSERT_EQ(buffer->faults, 1);
+
+ /* Check what the device read. */
+ for (i = 0, ptr = buffer->mirror;
+ i < size / sizeof(*ptr);
+ ++i)
+ ASSERT_EQ(ptr[i], i + c);
+ }
+
+ pthread_join(thread, &ret);
+ hmm_buffer_free(buffer);
+ }
+}
+
+/*
+ * Test memory snapshot without faulting in pages accessed by the device.
+ */
+TEST_F(hmm2, snapshot)
+{
+ struct hmm_buffer *buffer;
+ unsigned long npages;
+ unsigned long size;
+ int *ptr;
+ unsigned char *p;
+ unsigned char *m;
+ int ret;
+ int val;
+
+ npages = 7;
+ size = npages << self->page_shift;
+
+ buffer = malloc(sizeof(*buffer));
+ ASSERT_NE(buffer, NULL);
+
+ buffer->fd = -1;
+ buffer->size = size;
+ buffer->mirror = malloc(npages);
+ ASSERT_NE(buffer->mirror, NULL);
+
+ /* Reserve a range of addresses. */
+ buffer->ptr = mmap(NULL, size,
+ PROT_NONE,
+ MAP_PRIVATE | MAP_ANONYMOUS,
+ buffer->fd, 0);
+ ASSERT_NE(buffer->ptr, MAP_FAILED);
+ p = buffer->ptr;
+
+ /* Punch a hole after the first page address. */
+ ret = munmap(buffer->ptr + self->page_size, self->page_size);
+ ASSERT_EQ(ret, 0);
+
+ /* Page 2 will be read-only zero page. */
+ ret = mprotect(buffer->ptr + 2 * self->page_size, self->page_size,
+ PROT_READ);
+ ASSERT_EQ(ret, 0);
+ ptr = (int *)(buffer->ptr + 2 * self->page_size);
+ val = *ptr + 3;
+ ASSERT_EQ(val, 3);
+
+ /* Page 3 will be read-only. */
+ ret = mprotect(buffer->ptr + 3 * self->page_size, self->page_size,
+ PROT_READ | PROT_WRITE);
+ ASSERT_EQ(ret, 0);
+ ptr = (int *)(buffer->ptr + 3 * self->page_size);
+ *ptr = val;
+ ret = mprotect(buffer->ptr + 3 * self->page_size, self->page_size,
+ PROT_READ);
+ ASSERT_EQ(ret, 0);
+
+ /* Page 4-6 will be read-write. */
+ ret = mprotect(buffer->ptr + 4 * self->page_size, 3 * self->page_size,
+ PROT_READ | PROT_WRITE);
+ ASSERT_EQ(ret, 0);
+ ptr = (int *)(buffer->ptr + 4 * self->page_size);
+ *ptr = val;
+
+ /* Page 5 will be migrated to device 0. */
+ buffer->ptr = p + 5 * self->page_size;
+ ret = hmm_dmirror_cmd(self->fd0, HMM_DMIRROR_MIGRATE, buffer, 1);
+ ASSERT_EQ(ret, 0);
+ ASSERT_EQ(buffer->cpages, 1);
+
+ /* Page 6 will be migrated to device 1. */
+ buffer->ptr = p + 6 * self->page_size;
+ ret = hmm_dmirror_cmd(self->fd1, HMM_DMIRROR_MIGRATE, buffer, 1);
+ ASSERT_EQ(ret, 0);
+ ASSERT_EQ(buffer->cpages, 1);
+
+ /* Simulate a device snapshotting CPU pagetables. */
+ buffer->ptr = p;
+ ret = hmm_dmirror_cmd(self->fd0, HMM_DMIRROR_SNAPSHOT, buffer, npages);
+ ASSERT_EQ(ret, 0);
+ ASSERT_EQ(buffer->cpages, npages);
+
+ /* Check what the device saw. */
+ m = buffer->mirror;
+ ASSERT_EQ(m[0], HMM_DMIRROR_PROT_ERROR);
+ ASSERT_EQ(m[1], HMM_DMIRROR_PROT_ERROR);
+ ASSERT_EQ(m[2], HMM_DMIRROR_PROT_ZERO | HMM_DMIRROR_PROT_READ);
+ ASSERT_EQ(m[3], HMM_DMIRROR_PROT_READ);
+ ASSERT_EQ(m[4], HMM_DMIRROR_PROT_WRITE);
+ ASSERT_EQ(m[5], HMM_DMIRROR_PROT_DEV_PRIVATE_LOCAL |
+ HMM_DMIRROR_PROT_WRITE);
+ ASSERT_EQ(m[6], HMM_DMIRROR_PROT_NONE);
+
+ hmm_buffer_free(buffer);
+}
+
+/*
+ * Test two devices reading the same memory (double mapped).
+ */
+TEST_F(hmm2, double_map)
+{
+ struct hmm_buffer *buffer;
+ unsigned long npages;
+ unsigned long size;
+ unsigned long i;
+ int *ptr;
+ int ret;
+
+ npages = 6;
+ size = npages << self->page_shift;
+
+ buffer = malloc(sizeof(*buffer));
+ ASSERT_NE(buffer, NULL);
+
+ buffer->fd = -1;
+ buffer->size = size;
+ buffer->mirror = malloc(npages);
+ ASSERT_NE(buffer->mirror, NULL);
+
+ /* Reserve a range of addresses. */
+ buffer->ptr = mmap(NULL, size,
+ PROT_READ | PROT_WRITE,
+ MAP_PRIVATE | MAP_ANONYMOUS,
+ buffer->fd, 0);
+ ASSERT_NE(buffer->ptr, MAP_FAILED);
+
+ /* Initialize buffer in system memory. */
+ for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+ ptr[i] = i;
+
+ /* Make region read-only. */
+ ret = mprotect(buffer->ptr, size, PROT_READ);
+ ASSERT_EQ(ret, 0);
+
+ /* Simulate device 0 reading system memory. */
+ ret = hmm_dmirror_cmd(self->fd0, HMM_DMIRROR_READ, buffer, npages);
+ ASSERT_EQ(ret, 0);
+ ASSERT_EQ(buffer->cpages, npages);
+ ASSERT_EQ(buffer->faults, 1);
+
+ /* Check what the device read. */
+ for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i)
+ ASSERT_EQ(ptr[i], i);
+
+ /* Simulate device 1 reading system memory. */
+ ret = hmm_dmirror_cmd(self->fd1, HMM_DMIRROR_READ, buffer, npages);
+ ASSERT_EQ(ret, 0);
+ ASSERT_EQ(buffer->cpages, npages);
+ ASSERT_EQ(buffer->faults, 1);
+
+ /* Check what the device read. */
+ for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i)
+ ASSERT_EQ(ptr[i], i);
+
+ /* Punch a hole after the first page address. */
+ ret = munmap(buffer->ptr + self->page_size, self->page_size);
+ ASSERT_EQ(ret, 0);
+
+ hmm_buffer_free(buffer);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/vm/hugetlb_reparenting_test.sh b/tools/testing/selftests/vm/hugetlb_reparenting_test.sh
new file mode 100644
index 000000000000..d11d1febccc3
--- /dev/null
+++ b/tools/testing/selftests/vm/hugetlb_reparenting_test.sh
@@ -0,0 +1,244 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+set -e
+
+if [[ $(id -u) -ne 0 ]]; then
+ echo "This test must be run as root. Skipping..."
+ exit 0
+fi
+
+usage_file=usage_in_bytes
+
+if [[ "$1" == "-cgroup-v2" ]]; then
+ cgroup2=1
+ usage_file=current
+fi
+
+CGROUP_ROOT='/dev/cgroup/memory'
+MNT='/mnt/huge/'
+
+if [[ ! -e $CGROUP_ROOT ]]; then
+ mkdir -p $CGROUP_ROOT
+ if [[ $cgroup2 ]]; then
+ mount -t cgroup2 none $CGROUP_ROOT
+ sleep 1
+ echo "+hugetlb +memory" >$CGROUP_ROOT/cgroup.subtree_control
+ else
+ mount -t cgroup memory,hugetlb $CGROUP_ROOT
+ fi
+fi
+
+function get_machine_hugepage_size() {
+ hpz=$(grep -i hugepagesize /proc/meminfo)
+ kb=${hpz:14:-3}
+ mb=$(($kb / 1024))
+ echo $mb
+}
+
+MB=$(get_machine_hugepage_size)
+
+function cleanup() {
+ echo cleanup
+ set +e
+ rm -rf "$MNT"/* 2>/dev/null
+ umount "$MNT" 2>/dev/null
+ rmdir "$MNT" 2>/dev/null
+ rmdir "$CGROUP_ROOT"/a/b 2>/dev/null
+ rmdir "$CGROUP_ROOT"/a 2>/dev/null
+ rmdir "$CGROUP_ROOT"/test1 2>/dev/null
+ echo 0 >/proc/sys/vm/nr_hugepages
+ set -e
+}
+
+function assert_state() {
+ local expected_a="$1"
+ local expected_a_hugetlb="$2"
+ local expected_b=""
+ local expected_b_hugetlb=""
+
+ if [ ! -z ${3:-} ] && [ ! -z ${4:-} ]; then
+ expected_b="$3"
+ expected_b_hugetlb="$4"
+ fi
+ local tolerance=$((5 * 1024 * 1024))
+
+ local actual_a
+ actual_a="$(cat "$CGROUP_ROOT"/a/memory.$usage_file)"
+ if [[ $actual_a -lt $(($expected_a - $tolerance)) ]] ||
+ [[ $actual_a -gt $(($expected_a + $tolerance)) ]]; then
+ echo actual a = $((${actual_a%% *} / 1024 / 1024)) MB
+ echo expected a = $((${expected_a%% *} / 1024 / 1024)) MB
+ echo fail
+
+ cleanup
+ exit 1
+ fi
+
+ local actual_a_hugetlb
+ actual_a_hugetlb="$(cat "$CGROUP_ROOT"/a/hugetlb.${MB}MB.$usage_file)"
+ if [[ $actual_a_hugetlb -lt $(($expected_a_hugetlb - $tolerance)) ]] ||
+ [[ $actual_a_hugetlb -gt $(($expected_a_hugetlb + $tolerance)) ]]; then
+ echo actual a hugetlb = $((${actual_a_hugetlb%% *} / 1024 / 1024)) MB
+ echo expected a hugetlb = $((${expected_a_hugetlb%% *} / 1024 / 1024)) MB
+ echo fail
+
+ cleanup
+ exit 1
+ fi
+
+ if [[ -z "$expected_b" || -z "$expected_b_hugetlb" ]]; then
+ return
+ fi
+
+ local actual_b
+ actual_b="$(cat "$CGROUP_ROOT"/a/b/memory.$usage_file)"
+ if [[ $actual_b -lt $(($expected_b - $tolerance)) ]] ||
+ [[ $actual_b -gt $(($expected_b + $tolerance)) ]]; then
+ echo actual b = $((${actual_b%% *} / 1024 / 1024)) MB
+ echo expected b = $((${expected_b%% *} / 1024 / 1024)) MB
+ echo fail
+
+ cleanup
+ exit 1
+ fi
+
+ local actual_b_hugetlb
+ actual_b_hugetlb="$(cat "$CGROUP_ROOT"/a/b/hugetlb.${MB}MB.$usage_file)"
+ if [[ $actual_b_hugetlb -lt $(($expected_b_hugetlb - $tolerance)) ]] ||
+ [[ $actual_b_hugetlb -gt $(($expected_b_hugetlb + $tolerance)) ]]; then
+ echo actual b hugetlb = $((${actual_b_hugetlb%% *} / 1024 / 1024)) MB
+ echo expected b hugetlb = $((${expected_b_hugetlb%% *} / 1024 / 1024)) MB
+ echo fail
+
+ cleanup
+ exit 1
+ fi
+}
+
+function setup() {
+ echo 100 >/proc/sys/vm/nr_hugepages
+ mkdir "$CGROUP_ROOT"/a
+ sleep 1
+ if [[ $cgroup2 ]]; then
+ echo "+hugetlb +memory" >$CGROUP_ROOT/a/cgroup.subtree_control
+ else
+ echo 0 >$CGROUP_ROOT/a/cpuset.mems
+ echo 0 >$CGROUP_ROOT/a/cpuset.cpus
+ fi
+
+ mkdir "$CGROUP_ROOT"/a/b
+
+ if [[ ! $cgroup2 ]]; then
+ echo 0 >$CGROUP_ROOT/a/b/cpuset.mems
+ echo 0 >$CGROUP_ROOT/a/b/cpuset.cpus
+ fi
+
+ mkdir -p "$MNT"
+ mount -t hugetlbfs none "$MNT"
+}
+
+write_hugetlbfs() {
+ local cgroup="$1"
+ local path="$2"
+ local size="$3"
+
+ if [[ $cgroup2 ]]; then
+ echo $$ >$CGROUP_ROOT/$cgroup/cgroup.procs
+ else
+ echo 0 >$CGROUP_ROOT/$cgroup/cpuset.mems
+ echo 0 >$CGROUP_ROOT/$cgroup/cpuset.cpus
+ echo $$ >"$CGROUP_ROOT/$cgroup/tasks"
+ fi
+ ./write_to_hugetlbfs -p "$path" -s "$size" -m 0 -o
+ if [[ $cgroup2 ]]; then
+ echo $$ >$CGROUP_ROOT/cgroup.procs
+ else
+ echo $$ >"$CGROUP_ROOT/tasks"
+ fi
+ echo
+}
+
+set -e
+
+size=$((${MB} * 1024 * 1024 * 25)) # 50MB = 25 * 2MB hugepages.
+
+cleanup
+
+echo
+echo
+echo Test charge, rmdir, uncharge
+setup
+echo mkdir
+mkdir $CGROUP_ROOT/test1
+
+echo write
+write_hugetlbfs test1 "$MNT"/test $size
+
+echo rmdir
+rmdir $CGROUP_ROOT/test1
+mkdir $CGROUP_ROOT/test1
+
+echo uncharge
+rm -rf /mnt/huge/*
+
+cleanup
+
+echo done
+echo
+echo
+if [[ ! $cgroup2 ]]; then
+ echo "Test parent and child hugetlb usage"
+ setup
+
+ echo write
+ write_hugetlbfs a "$MNT"/test $size
+
+ echo Assert memory charged correctly for parent use.
+ assert_state 0 $size 0 0
+
+ write_hugetlbfs a/b "$MNT"/test2 $size
+
+ echo Assert memory charged correctly for child use.
+ assert_state 0 $(($size * 2)) 0 $size
+
+ rmdir "$CGROUP_ROOT"/a/b
+ sleep 5
+ echo Assert memory reparent correctly.
+ assert_state 0 $(($size * 2))
+
+ rm -rf "$MNT"/*
+ umount "$MNT"
+ echo Assert memory uncharged correctly.
+ assert_state 0 0
+
+ cleanup
+fi
+
+echo
+echo
+echo "Test child only hugetlb usage"
+echo setup
+setup
+
+echo write
+write_hugetlbfs a/b "$MNT"/test2 $size
+
+echo Assert memory charged correctly for child only use.
+assert_state 0 $(($size)) 0 $size
+
+rmdir "$CGROUP_ROOT"/a/b
+echo Assert memory reparent correctly.
+assert_state 0 $size
+
+rm -rf "$MNT"/*
+umount "$MNT"
+echo Assert memory uncharged correctly.
+assert_state 0 0
+
+cleanup
+
+echo ALL PASS
+
+umount $CGROUP_ROOT
+rm -rf $CGROUP_ROOT
diff --git a/tools/testing/selftests/vm/khugepaged.c b/tools/testing/selftests/vm/khugepaged.c
new file mode 100644
index 000000000000..51b89cedd09d
--- /dev/null
+++ b/tools/testing/selftests/vm/khugepaged.c
@@ -0,0 +1,1035 @@
+#define _GNU_SOURCE
+#include <fcntl.h>
+#include <limits.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdbool.h>
+#include <string.h>
+#include <unistd.h>
+
+#include <sys/mman.h>
+#include <sys/wait.h>
+
+#ifndef MADV_PAGEOUT
+#define MADV_PAGEOUT 21
+#endif
+
+#define BASE_ADDR ((void *)(1UL << 30))
+static unsigned long hpage_pmd_size;
+static unsigned long page_size;
+static int hpage_pmd_nr;
+
+#define THP_SYSFS "/sys/kernel/mm/transparent_hugepage/"
+#define PID_SMAPS "/proc/self/smaps"
+
+enum thp_enabled {
+ THP_ALWAYS,
+ THP_MADVISE,
+ THP_NEVER,
+};
+
+static const char *thp_enabled_strings[] = {
+ "always",
+ "madvise",
+ "never",
+ NULL
+};
+
+enum thp_defrag {
+ THP_DEFRAG_ALWAYS,
+ THP_DEFRAG_DEFER,
+ THP_DEFRAG_DEFER_MADVISE,
+ THP_DEFRAG_MADVISE,
+ THP_DEFRAG_NEVER,
+};
+
+static const char *thp_defrag_strings[] = {
+ "always",
+ "defer",
+ "defer+madvise",
+ "madvise",
+ "never",
+ NULL
+};
+
+enum shmem_enabled {
+ SHMEM_ALWAYS,
+ SHMEM_WITHIN_SIZE,
+ SHMEM_ADVISE,
+ SHMEM_NEVER,
+ SHMEM_DENY,
+ SHMEM_FORCE,
+};
+
+static const char *shmem_enabled_strings[] = {
+ "always",
+ "within_size",
+ "advise",
+ "never",
+ "deny",
+ "force",
+ NULL
+};
+
+struct khugepaged_settings {
+ bool defrag;
+ unsigned int alloc_sleep_millisecs;
+ unsigned int scan_sleep_millisecs;
+ unsigned int max_ptes_none;
+ unsigned int max_ptes_swap;
+ unsigned int max_ptes_shared;
+ unsigned long pages_to_scan;
+};
+
+struct settings {
+ enum thp_enabled thp_enabled;
+ enum thp_defrag thp_defrag;
+ enum shmem_enabled shmem_enabled;
+ bool debug_cow;
+ bool use_zero_page;
+ struct khugepaged_settings khugepaged;
+};
+
+static struct settings default_settings = {
+ .thp_enabled = THP_MADVISE,
+ .thp_defrag = THP_DEFRAG_ALWAYS,
+ .shmem_enabled = SHMEM_NEVER,
+ .debug_cow = 0,
+ .use_zero_page = 0,
+ .khugepaged = {
+ .defrag = 1,
+ .alloc_sleep_millisecs = 10,
+ .scan_sleep_millisecs = 10,
+ },
+};
+
+static struct settings saved_settings;
+static bool skip_settings_restore;
+
+static int exit_status;
+
+static void success(const char *msg)
+{
+ printf(" \e[32m%s\e[0m\n", msg);
+}
+
+static void fail(const char *msg)
+{
+ printf(" \e[31m%s\e[0m\n", msg);
+ exit_status++;
+}
+
+static int read_file(const char *path, char *buf, size_t buflen)
+{
+ int fd;
+ ssize_t numread;
+
+ fd = open(path, O_RDONLY);
+ if (fd == -1)
+ return 0;
+
+ numread = read(fd, buf, buflen - 1);
+ if (numread < 1) {
+ close(fd);
+ return 0;
+ }
+
+ buf[numread] = '\0';
+ close(fd);
+
+ return (unsigned int) numread;
+}
+
+static int write_file(const char *path, const char *buf, size_t buflen)
+{
+ int fd;
+ ssize_t numwritten;
+
+ fd = open(path, O_WRONLY);
+ if (fd == -1)
+ return 0;
+
+ numwritten = write(fd, buf, buflen - 1);
+ close(fd);
+ if (numwritten < 1)
+ return 0;
+
+ return (unsigned int) numwritten;
+}
+
+static int read_string(const char *name, const char *strings[])
+{
+ char path[PATH_MAX];
+ char buf[256];
+ char *c;
+ int ret;
+
+ ret = snprintf(path, PATH_MAX, THP_SYSFS "%s", name);
+ if (ret >= PATH_MAX) {
+ printf("%s: Pathname is too long\n", __func__);
+ exit(EXIT_FAILURE);
+ }
+
+ if (!read_file(path, buf, sizeof(buf))) {
+ perror(path);
+ exit(EXIT_FAILURE);
+ }
+
+ c = strchr(buf, '[');
+ if (!c) {
+ printf("%s: Parse failure\n", __func__);
+ exit(EXIT_FAILURE);
+ }
+
+ c++;
+ memmove(buf, c, sizeof(buf) - (c - buf));
+
+ c = strchr(buf, ']');
+ if (!c) {
+ printf("%s: Parse failure\n", __func__);
+ exit(EXIT_FAILURE);
+ }
+ *c = '\0';
+
+ ret = 0;
+ while (strings[ret]) {
+ if (!strcmp(strings[ret], buf))
+ return ret;
+ ret++;
+ }
+
+ printf("Failed to parse %s\n", name);
+ exit(EXIT_FAILURE);
+}
+
+static void write_string(const char *name, const char *val)
+{
+ char path[PATH_MAX];
+ int ret;
+
+ ret = snprintf(path, PATH_MAX, THP_SYSFS "%s", name);
+ if (ret >= PATH_MAX) {
+ printf("%s: Pathname is too long\n", __func__);
+ exit(EXIT_FAILURE);
+ }
+
+ if (!write_file(path, val, strlen(val) + 1)) {
+ perror(path);
+ exit(EXIT_FAILURE);
+ }
+}
+
+static const unsigned long read_num(const char *name)
+{
+ char path[PATH_MAX];
+ char buf[21];
+ int ret;
+
+ ret = snprintf(path, PATH_MAX, THP_SYSFS "%s", name);
+ if (ret >= PATH_MAX) {
+ printf("%s: Pathname is too long\n", __func__);
+ exit(EXIT_FAILURE);
+ }
+
+ ret = read_file(path, buf, sizeof(buf));
+ if (ret < 0) {
+ perror("read_file(read_num)");
+ exit(EXIT_FAILURE);
+ }
+
+ return strtoul(buf, NULL, 10);
+}
+
+static void write_num(const char *name, unsigned long num)
+{
+ char path[PATH_MAX];
+ char buf[21];
+ int ret;
+
+ ret = snprintf(path, PATH_MAX, THP_SYSFS "%s", name);
+ if (ret >= PATH_MAX) {
+ printf("%s: Pathname is too long\n", __func__);
+ exit(EXIT_FAILURE);
+ }
+
+ sprintf(buf, "%ld", num);
+ if (!write_file(path, buf, strlen(buf) + 1)) {
+ perror(path);
+ exit(EXIT_FAILURE);
+ }
+}
+
+static void write_settings(struct settings *settings)
+{
+ struct khugepaged_settings *khugepaged = &settings->khugepaged;
+
+ write_string("enabled", thp_enabled_strings[settings->thp_enabled]);
+ write_string("defrag", thp_defrag_strings[settings->thp_defrag]);
+ write_string("shmem_enabled",
+ shmem_enabled_strings[settings->shmem_enabled]);
+ write_num("debug_cow", settings->debug_cow);
+ write_num("use_zero_page", settings->use_zero_page);
+
+ write_num("khugepaged/defrag", khugepaged->defrag);
+ write_num("khugepaged/alloc_sleep_millisecs",
+ khugepaged->alloc_sleep_millisecs);
+ write_num("khugepaged/scan_sleep_millisecs",
+ khugepaged->scan_sleep_millisecs);
+ write_num("khugepaged/max_ptes_none", khugepaged->max_ptes_none);
+ write_num("khugepaged/max_ptes_swap", khugepaged->max_ptes_swap);
+ write_num("khugepaged/max_ptes_shared", khugepaged->max_ptes_shared);
+ write_num("khugepaged/pages_to_scan", khugepaged->pages_to_scan);
+}
+
+static void restore_settings(int sig)
+{
+ if (skip_settings_restore)
+ goto out;
+
+ printf("Restore THP and khugepaged settings...");
+ write_settings(&saved_settings);
+ success("OK");
+ if (sig)
+ exit(EXIT_FAILURE);
+out:
+ exit(exit_status);
+}
+
+static void save_settings(void)
+{
+ printf("Save THP and khugepaged settings...");
+ saved_settings = (struct settings) {
+ .thp_enabled = read_string("enabled", thp_enabled_strings),
+ .thp_defrag = read_string("defrag", thp_defrag_strings),
+ .shmem_enabled =
+ read_string("shmem_enabled", shmem_enabled_strings),
+ .debug_cow = read_num("debug_cow"),
+ .use_zero_page = read_num("use_zero_page"),
+ };
+ saved_settings.khugepaged = (struct khugepaged_settings) {
+ .defrag = read_num("khugepaged/defrag"),
+ .alloc_sleep_millisecs =
+ read_num("khugepaged/alloc_sleep_millisecs"),
+ .scan_sleep_millisecs =
+ read_num("khugepaged/scan_sleep_millisecs"),
+ .max_ptes_none = read_num("khugepaged/max_ptes_none"),
+ .max_ptes_swap = read_num("khugepaged/max_ptes_swap"),
+ .max_ptes_shared = read_num("khugepaged/max_ptes_shared"),
+ .pages_to_scan = read_num("khugepaged/pages_to_scan"),
+ };
+ success("OK");
+
+ signal(SIGTERM, restore_settings);
+ signal(SIGINT, restore_settings);
+ signal(SIGHUP, restore_settings);
+ signal(SIGQUIT, restore_settings);
+}
+
+static void adjust_settings(void)
+{
+
+ printf("Adjust settings...");
+ write_settings(&default_settings);
+ success("OK");
+}
+
+#define MAX_LINE_LENGTH 500
+
+static bool check_for_pattern(FILE *fp, char *pattern, char *buf)
+{
+ while (fgets(buf, MAX_LINE_LENGTH, fp) != NULL) {
+ if (!strncmp(buf, pattern, strlen(pattern)))
+ return true;
+ }
+ return false;
+}
+
+static bool check_huge(void *addr)
+{
+ bool thp = false;
+ int ret;
+ FILE *fp;
+ char buffer[MAX_LINE_LENGTH];
+ char addr_pattern[MAX_LINE_LENGTH];
+
+ ret = snprintf(addr_pattern, MAX_LINE_LENGTH, "%08lx-",
+ (unsigned long) addr);
+ if (ret >= MAX_LINE_LENGTH) {
+ printf("%s: Pattern is too long\n", __func__);
+ exit(EXIT_FAILURE);
+ }
+
+
+ fp = fopen(PID_SMAPS, "r");
+ if (!fp) {
+ printf("%s: Failed to open file %s\n", __func__, PID_SMAPS);
+ exit(EXIT_FAILURE);
+ }
+ if (!check_for_pattern(fp, addr_pattern, buffer))
+ goto err_out;
+
+ ret = snprintf(addr_pattern, MAX_LINE_LENGTH, "AnonHugePages:%10ld kB",
+ hpage_pmd_size >> 10);
+ if (ret >= MAX_LINE_LENGTH) {
+ printf("%s: Pattern is too long\n", __func__);
+ exit(EXIT_FAILURE);
+ }
+ /*
+ * Fetch the AnonHugePages: in the same block and check whether it got
+ * the expected number of hugeepages next.
+ */
+ if (!check_for_pattern(fp, "AnonHugePages:", buffer))
+ goto err_out;
+
+ if (strncmp(buffer, addr_pattern, strlen(addr_pattern)))
+ goto err_out;
+
+ thp = true;
+err_out:
+ fclose(fp);
+ return thp;
+}
+
+
+static bool check_swap(void *addr, unsigned long size)
+{
+ bool swap = false;
+ int ret;
+ FILE *fp;
+ char buffer[MAX_LINE_LENGTH];
+ char addr_pattern[MAX_LINE_LENGTH];
+
+ ret = snprintf(addr_pattern, MAX_LINE_LENGTH, "%08lx-",
+ (unsigned long) addr);
+ if (ret >= MAX_LINE_LENGTH) {
+ printf("%s: Pattern is too long\n", __func__);
+ exit(EXIT_FAILURE);
+ }
+
+
+ fp = fopen(PID_SMAPS, "r");
+ if (!fp) {
+ printf("%s: Failed to open file %s\n", __func__, PID_SMAPS);
+ exit(EXIT_FAILURE);
+ }
+ if (!check_for_pattern(fp, addr_pattern, buffer))
+ goto err_out;
+
+ ret = snprintf(addr_pattern, MAX_LINE_LENGTH, "Swap:%19ld kB",
+ size >> 10);
+ if (ret >= MAX_LINE_LENGTH) {
+ printf("%s: Pattern is too long\n", __func__);
+ exit(EXIT_FAILURE);
+ }
+ /*
+ * Fetch the Swap: in the same block and check whether it got
+ * the expected number of hugeepages next.
+ */
+ if (!check_for_pattern(fp, "Swap:", buffer))
+ goto err_out;
+
+ if (strncmp(buffer, addr_pattern, strlen(addr_pattern)))
+ goto err_out;
+
+ swap = true;
+err_out:
+ fclose(fp);
+ return swap;
+}
+
+static void *alloc_mapping(void)
+{
+ void *p;
+
+ p = mmap(BASE_ADDR, hpage_pmd_size, PROT_READ | PROT_WRITE,
+ MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
+ if (p != BASE_ADDR) {
+ printf("Failed to allocate VMA at %p\n", BASE_ADDR);
+ exit(EXIT_FAILURE);
+ }
+
+ return p;
+}
+
+static void fill_memory(int *p, unsigned long start, unsigned long end)
+{
+ int i;
+
+ for (i = start / page_size; i < end / page_size; i++)
+ p[i * page_size / sizeof(*p)] = i + 0xdead0000;
+}
+
+static void validate_memory(int *p, unsigned long start, unsigned long end)
+{
+ int i;
+
+ for (i = start / page_size; i < end / page_size; i++) {
+ if (p[i * page_size / sizeof(*p)] != i + 0xdead0000) {
+ printf("Page %d is corrupted: %#x\n",
+ i, p[i * page_size / sizeof(*p)]);
+ exit(EXIT_FAILURE);
+ }
+ }
+}
+
+#define TICK 500000
+static bool wait_for_scan(const char *msg, char *p)
+{
+ int full_scans;
+ int timeout = 6; /* 3 seconds */
+
+ /* Sanity check */
+ if (check_huge(p)) {
+ printf("Unexpected huge page\n");
+ exit(EXIT_FAILURE);
+ }
+
+ madvise(p, hpage_pmd_size, MADV_HUGEPAGE);
+
+ /* Wait until the second full_scan completed */
+ full_scans = read_num("khugepaged/full_scans") + 2;
+
+ printf("%s...", msg);
+ while (timeout--) {
+ if (check_huge(p))
+ break;
+ if (read_num("khugepaged/full_scans") >= full_scans)
+ break;
+ printf(".");
+ usleep(TICK);
+ }
+
+ madvise(p, hpage_pmd_size, MADV_NOHUGEPAGE);
+
+ return !timeout;
+}
+
+static void alloc_at_fault(void)
+{
+ struct settings settings = default_settings;
+ char *p;
+
+ settings.thp_enabled = THP_ALWAYS;
+ write_settings(&settings);
+
+ p = alloc_mapping();
+ *p = 1;
+ printf("Allocate huge page on fault...");
+ if (check_huge(p))
+ success("OK");
+ else
+ fail("Fail");
+
+ write_settings(&default_settings);
+
+ madvise(p, page_size, MADV_DONTNEED);
+ printf("Split huge PMD on MADV_DONTNEED...");
+ if (!check_huge(p))
+ success("OK");
+ else
+ fail("Fail");
+ munmap(p, hpage_pmd_size);
+}
+
+static void collapse_full(void)
+{
+ void *p;
+
+ p = alloc_mapping();
+ fill_memory(p, 0, hpage_pmd_size);
+ if (wait_for_scan("Collapse fully populated PTE table", p))
+ fail("Timeout");
+ else if (check_huge(p))
+ success("OK");
+ else
+ fail("Fail");
+ validate_memory(p, 0, hpage_pmd_size);
+ munmap(p, hpage_pmd_size);
+}
+
+static void collapse_empty(void)
+{
+ void *p;
+
+ p = alloc_mapping();
+ if (wait_for_scan("Do not collapse empty PTE table", p))
+ fail("Timeout");
+ else if (check_huge(p))
+ fail("Fail");
+ else
+ success("OK");
+ munmap(p, hpage_pmd_size);
+}
+
+static void collapse_single_pte_entry(void)
+{
+ void *p;
+
+ p = alloc_mapping();
+ fill_memory(p, 0, page_size);
+ if (wait_for_scan("Collapse PTE table with single PTE entry present", p))
+ fail("Timeout");
+ else if (check_huge(p))
+ success("OK");
+ else
+ fail("Fail");
+ validate_memory(p, 0, page_size);
+ munmap(p, hpage_pmd_size);
+}
+
+static void collapse_max_ptes_none(void)
+{
+ int max_ptes_none = hpage_pmd_nr / 2;
+ struct settings settings = default_settings;
+ void *p;
+
+ settings.khugepaged.max_ptes_none = max_ptes_none;
+ write_settings(&settings);
+
+ p = alloc_mapping();
+
+ fill_memory(p, 0, (hpage_pmd_nr - max_ptes_none - 1) * page_size);
+ if (wait_for_scan("Do not collapse with max_ptes_none exceeded", p))
+ fail("Timeout");
+ else if (check_huge(p))
+ fail("Fail");
+ else
+ success("OK");
+ validate_memory(p, 0, (hpage_pmd_nr - max_ptes_none - 1) * page_size);
+
+ fill_memory(p, 0, (hpage_pmd_nr - max_ptes_none) * page_size);
+ if (wait_for_scan("Collapse with max_ptes_none PTEs empty", p))
+ fail("Timeout");
+ else if (check_huge(p))
+ success("OK");
+ else
+ fail("Fail");
+ validate_memory(p, 0, (hpage_pmd_nr - max_ptes_none) * page_size);
+
+ munmap(p, hpage_pmd_size);
+ write_settings(&default_settings);
+}
+
+static void collapse_swapin_single_pte(void)
+{
+ void *p;
+ p = alloc_mapping();
+ fill_memory(p, 0, hpage_pmd_size);
+
+ printf("Swapout one page...");
+ if (madvise(p, page_size, MADV_PAGEOUT)) {
+ perror("madvise(MADV_PAGEOUT)");
+ exit(EXIT_FAILURE);
+ }
+ if (check_swap(p, page_size)) {
+ success("OK");
+ } else {
+ fail("Fail");
+ goto out;
+ }
+
+ if (wait_for_scan("Collapse with swapping in single PTE entry", p))
+ fail("Timeout");
+ else if (check_huge(p))
+ success("OK");
+ else
+ fail("Fail");
+ validate_memory(p, 0, hpage_pmd_size);
+out:
+ munmap(p, hpage_pmd_size);
+}
+
+static void collapse_max_ptes_swap(void)
+{
+ int max_ptes_swap = read_num("khugepaged/max_ptes_swap");
+ void *p;
+
+ p = alloc_mapping();
+
+ fill_memory(p, 0, hpage_pmd_size);
+ printf("Swapout %d of %d pages...", max_ptes_swap + 1, hpage_pmd_nr);
+ if (madvise(p, (max_ptes_swap + 1) * page_size, MADV_PAGEOUT)) {
+ perror("madvise(MADV_PAGEOUT)");
+ exit(EXIT_FAILURE);
+ }
+ if (check_swap(p, (max_ptes_swap + 1) * page_size)) {
+ success("OK");
+ } else {
+ fail("Fail");
+ goto out;
+ }
+
+ if (wait_for_scan("Do not collapse with max_ptes_swap exceeded", p))
+ fail("Timeout");
+ else if (check_huge(p))
+ fail("Fail");
+ else
+ success("OK");
+ validate_memory(p, 0, hpage_pmd_size);
+
+ fill_memory(p, 0, hpage_pmd_size);
+ printf("Swapout %d of %d pages...", max_ptes_swap, hpage_pmd_nr);
+ if (madvise(p, max_ptes_swap * page_size, MADV_PAGEOUT)) {
+ perror("madvise(MADV_PAGEOUT)");
+ exit(EXIT_FAILURE);
+ }
+ if (check_swap(p, max_ptes_swap * page_size)) {
+ success("OK");
+ } else {
+ fail("Fail");
+ goto out;
+ }
+
+ if (wait_for_scan("Collapse with max_ptes_swap pages swapped out", p))
+ fail("Timeout");
+ else if (check_huge(p))
+ success("OK");
+ else
+ fail("Fail");
+ validate_memory(p, 0, hpage_pmd_size);
+out:
+ munmap(p, hpage_pmd_size);
+}
+
+static void collapse_single_pte_entry_compound(void)
+{
+ void *p;
+
+ p = alloc_mapping();
+
+ printf("Allocate huge page...");
+ madvise(p, hpage_pmd_size, MADV_HUGEPAGE);
+ fill_memory(p, 0, hpage_pmd_size);
+ if (check_huge(p))
+ success("OK");
+ else
+ fail("Fail");
+ madvise(p, hpage_pmd_size, MADV_NOHUGEPAGE);
+
+ printf("Split huge page leaving single PTE mapping compound page...");
+ madvise(p + page_size, hpage_pmd_size - page_size, MADV_DONTNEED);
+ if (!check_huge(p))
+ success("OK");
+ else
+ fail("Fail");
+
+ if (wait_for_scan("Collapse PTE table with single PTE mapping compound page", p))
+ fail("Timeout");
+ else if (check_huge(p))
+ success("OK");
+ else
+ fail("Fail");
+ validate_memory(p, 0, page_size);
+ munmap(p, hpage_pmd_size);
+}
+
+static void collapse_full_of_compound(void)
+{
+ void *p;
+
+ p = alloc_mapping();
+
+ printf("Allocate huge page...");
+ madvise(p, hpage_pmd_size, MADV_HUGEPAGE);
+ fill_memory(p, 0, hpage_pmd_size);
+ if (check_huge(p))
+ success("OK");
+ else
+ fail("Fail");
+
+ printf("Split huge page leaving single PTE page table full of compound pages...");
+ madvise(p, page_size, MADV_NOHUGEPAGE);
+ madvise(p, hpage_pmd_size, MADV_NOHUGEPAGE);
+ if (!check_huge(p))
+ success("OK");
+ else
+ fail("Fail");
+
+ if (wait_for_scan("Collapse PTE table full of compound pages", p))
+ fail("Timeout");
+ else if (check_huge(p))
+ success("OK");
+ else
+ fail("Fail");
+ validate_memory(p, 0, hpage_pmd_size);
+ munmap(p, hpage_pmd_size);
+}
+
+static void collapse_compound_extreme(void)
+{
+ void *p;
+ int i;
+
+ p = alloc_mapping();
+ for (i = 0; i < hpage_pmd_nr; i++) {
+ printf("\rConstruct PTE page table full of different PTE-mapped compound pages %3d/%d...",
+ i + 1, hpage_pmd_nr);
+
+ madvise(BASE_ADDR, hpage_pmd_size, MADV_HUGEPAGE);
+ fill_memory(BASE_ADDR, 0, hpage_pmd_size);
+ if (!check_huge(BASE_ADDR)) {
+ printf("Failed to allocate huge page\n");
+ exit(EXIT_FAILURE);
+ }
+ madvise(BASE_ADDR, hpage_pmd_size, MADV_NOHUGEPAGE);
+
+ p = mremap(BASE_ADDR - i * page_size,
+ i * page_size + hpage_pmd_size,
+ (i + 1) * page_size,
+ MREMAP_MAYMOVE | MREMAP_FIXED,
+ BASE_ADDR + 2 * hpage_pmd_size);
+ if (p == MAP_FAILED) {
+ perror("mremap+unmap");
+ exit(EXIT_FAILURE);
+ }
+
+ p = mremap(BASE_ADDR + 2 * hpage_pmd_size,
+ (i + 1) * page_size,
+ (i + 1) * page_size + hpage_pmd_size,
+ MREMAP_MAYMOVE | MREMAP_FIXED,
+ BASE_ADDR - (i + 1) * page_size);
+ if (p == MAP_FAILED) {
+ perror("mremap+alloc");
+ exit(EXIT_FAILURE);
+ }
+ }
+
+ munmap(BASE_ADDR, hpage_pmd_size);
+ fill_memory(p, 0, hpage_pmd_size);
+ if (!check_huge(p))
+ success("OK");
+ else
+ fail("Fail");
+
+ if (wait_for_scan("Collapse PTE table full of different compound pages", p))
+ fail("Timeout");
+ else if (check_huge(p))
+ success("OK");
+ else
+ fail("Fail");
+
+ validate_memory(p, 0, hpage_pmd_size);
+ munmap(p, hpage_pmd_size);
+}
+
+static void collapse_fork(void)
+{
+ int wstatus;
+ void *p;
+
+ p = alloc_mapping();
+
+ printf("Allocate small page...");
+ fill_memory(p, 0, page_size);
+ if (!check_huge(p))
+ success("OK");
+ else
+ fail("Fail");
+
+ printf("Share small page over fork()...");
+ if (!fork()) {
+ /* Do not touch settings on child exit */
+ skip_settings_restore = true;
+ exit_status = 0;
+
+ if (!check_huge(p))
+ success("OK");
+ else
+ fail("Fail");
+
+ fill_memory(p, page_size, 2 * page_size);
+
+ if (wait_for_scan("Collapse PTE table with single page shared with parent process", p))
+ fail("Timeout");
+ else if (check_huge(p))
+ success("OK");
+ else
+ fail("Fail");
+
+ validate_memory(p, 0, page_size);
+ munmap(p, hpage_pmd_size);
+ exit(exit_status);
+ }
+
+ wait(&wstatus);
+ exit_status += WEXITSTATUS(wstatus);
+
+ printf("Check if parent still has small page...");
+ if (!check_huge(p))
+ success("OK");
+ else
+ fail("Fail");
+ validate_memory(p, 0, page_size);
+ munmap(p, hpage_pmd_size);
+}
+
+static void collapse_fork_compound(void)
+{
+ int wstatus;
+ void *p;
+
+ p = alloc_mapping();
+
+ printf("Allocate huge page...");
+ madvise(p, hpage_pmd_size, MADV_HUGEPAGE);
+ fill_memory(p, 0, hpage_pmd_size);
+ if (check_huge(p))
+ success("OK");
+ else
+ fail("Fail");
+
+ printf("Share huge page over fork()...");
+ if (!fork()) {
+ /* Do not touch settings on child exit */
+ skip_settings_restore = true;
+ exit_status = 0;
+
+ if (check_huge(p))
+ success("OK");
+ else
+ fail("Fail");
+
+ printf("Split huge page PMD in child process...");
+ madvise(p, page_size, MADV_NOHUGEPAGE);
+ madvise(p, hpage_pmd_size, MADV_NOHUGEPAGE);
+ if (!check_huge(p))
+ success("OK");
+ else
+ fail("Fail");
+ fill_memory(p, 0, page_size);
+
+ write_num("khugepaged/max_ptes_shared", hpage_pmd_nr - 1);
+ if (wait_for_scan("Collapse PTE table full of compound pages in child", p))
+ fail("Timeout");
+ else if (check_huge(p))
+ success("OK");
+ else
+ fail("Fail");
+ write_num("khugepaged/max_ptes_shared",
+ default_settings.khugepaged.max_ptes_shared);
+
+ validate_memory(p, 0, hpage_pmd_size);
+ munmap(p, hpage_pmd_size);
+ exit(exit_status);
+ }
+
+ wait(&wstatus);
+ exit_status += WEXITSTATUS(wstatus);
+
+ printf("Check if parent still has huge page...");
+ if (check_huge(p))
+ success("OK");
+ else
+ fail("Fail");
+ validate_memory(p, 0, hpage_pmd_size);
+ munmap(p, hpage_pmd_size);
+}
+
+static void collapse_max_ptes_shared()
+{
+ int max_ptes_shared = read_num("khugepaged/max_ptes_shared");
+ int wstatus;
+ void *p;
+
+ p = alloc_mapping();
+
+ printf("Allocate huge page...");
+ madvise(p, hpage_pmd_size, MADV_HUGEPAGE);
+ fill_memory(p, 0, hpage_pmd_size);
+ if (check_huge(p))
+ success("OK");
+ else
+ fail("Fail");
+
+ printf("Share huge page over fork()...");
+ if (!fork()) {
+ /* Do not touch settings on child exit */
+ skip_settings_restore = true;
+ exit_status = 0;
+
+ if (check_huge(p))
+ success("OK");
+ else
+ fail("Fail");
+
+ printf("Trigger CoW on page %d of %d...",
+ hpage_pmd_nr - max_ptes_shared - 1, hpage_pmd_nr);
+ fill_memory(p, 0, (hpage_pmd_nr - max_ptes_shared - 1) * page_size);
+ if (!check_huge(p))
+ success("OK");
+ else
+ fail("Fail");
+
+ if (wait_for_scan("Do not collapse with max_ptes_shared exceeded", p))
+ fail("Timeout");
+ else if (!check_huge(p))
+ success("OK");
+ else
+ fail("Fail");
+
+ printf("Trigger CoW on page %d of %d...",
+ hpage_pmd_nr - max_ptes_shared, hpage_pmd_nr);
+ fill_memory(p, 0, (hpage_pmd_nr - max_ptes_shared) * page_size);
+ if (!check_huge(p))
+ success("OK");
+ else
+ fail("Fail");
+
+
+ if (wait_for_scan("Collapse with max_ptes_shared PTEs shared", p))
+ fail("Timeout");
+ else if (check_huge(p))
+ success("OK");
+ else
+ fail("Fail");
+
+ validate_memory(p, 0, hpage_pmd_size);
+ munmap(p, hpage_pmd_size);
+ exit(exit_status);
+ }
+
+ wait(&wstatus);
+ exit_status += WEXITSTATUS(wstatus);
+
+ printf("Check if parent still has huge page...");
+ if (check_huge(p))
+ success("OK");
+ else
+ fail("Fail");
+ validate_memory(p, 0, hpage_pmd_size);
+ munmap(p, hpage_pmd_size);
+}
+
+int main(void)
+{
+ setbuf(stdout, NULL);
+
+ page_size = getpagesize();
+ hpage_pmd_size = read_num("hpage_pmd_size");
+ hpage_pmd_nr = hpage_pmd_size / page_size;
+
+ default_settings.khugepaged.max_ptes_none = hpage_pmd_nr - 1;
+ default_settings.khugepaged.max_ptes_swap = hpage_pmd_nr / 8;
+ default_settings.khugepaged.max_ptes_shared = hpage_pmd_nr / 2;
+ default_settings.khugepaged.pages_to_scan = hpage_pmd_nr * 8;
+
+ save_settings();
+ adjust_settings();
+
+ alloc_at_fault();
+ collapse_full();
+ collapse_empty();
+ collapse_single_pte_entry();
+ collapse_max_ptes_none();
+ collapse_swapin_single_pte();
+ collapse_max_ptes_swap();
+ collapse_single_pte_entry_compound();
+ collapse_full_of_compound();
+ collapse_compound_extreme();
+ collapse_fork();
+ collapse_fork_compound();
+ collapse_max_ptes_shared();
+
+ restore_settings(0);
+}
diff --git a/tools/testing/selftests/vm/map_hugetlb.c b/tools/testing/selftests/vm/map_hugetlb.c
index 5a2d7b8efc40..6af951900aa3 100644
--- a/tools/testing/selftests/vm/map_hugetlb.c
+++ b/tools/testing/selftests/vm/map_hugetlb.c
@@ -45,20 +45,20 @@ static void check_bytes(char *addr)
printf("First hex is %x\n", *((unsigned int *)addr));
}
-static void write_bytes(char *addr)
+static void write_bytes(char *addr, size_t length)
{
unsigned long i;
- for (i = 0; i < LENGTH; i++)
+ for (i = 0; i < length; i++)
*(addr + i) = (char)i;
}
-static int read_bytes(char *addr)
+static int read_bytes(char *addr, size_t length)
{
unsigned long i;
check_bytes(addr);
- for (i = 0; i < LENGTH; i++)
+ for (i = 0; i < length; i++)
if (*(addr + i) != (char)i) {
printf("Mismatch at %lu\n", i);
return 1;
@@ -96,11 +96,11 @@ int main(int argc, char **argv)
printf("Returned address is %p\n", addr);
check_bytes(addr);
- write_bytes(addr);
- ret = read_bytes(addr);
+ write_bytes(addr, length);
+ ret = read_bytes(addr, length);
/* munmap() length of MAP_HUGETLB memory must be hugepage aligned */
- if (munmap(addr, LENGTH)) {
+ if (munmap(addr, length)) {
perror("munmap");
exit(1);
}
diff --git a/tools/testing/selftests/vm/mlock2-tests.c b/tools/testing/selftests/vm/mlock2-tests.c
index 637b6d0ac0d0..11b2301f3aa3 100644
--- a/tools/testing/selftests/vm/mlock2-tests.c
+++ b/tools/testing/selftests/vm/mlock2-tests.c
@@ -67,59 +67,6 @@ out:
return ret;
}
-static uint64_t get_pageflags(unsigned long addr)
-{
- FILE *file;
- uint64_t pfn;
- unsigned long offset;
-
- file = fopen("/proc/self/pagemap", "r");
- if (!file) {
- perror("fopen pagemap");
- _exit(1);
- }
-
- offset = addr / getpagesize() * sizeof(pfn);
-
- if (fseek(file, offset, SEEK_SET)) {
- perror("fseek pagemap");
- _exit(1);
- }
-
- if (fread(&pfn, sizeof(pfn), 1, file) != 1) {
- perror("fread pagemap");
- _exit(1);
- }
-
- fclose(file);
- return pfn;
-}
-
-static uint64_t get_kpageflags(unsigned long pfn)
-{
- uint64_t flags;
- FILE *file;
-
- file = fopen("/proc/kpageflags", "r");
- if (!file) {
- perror("fopen kpageflags");
- _exit(1);
- }
-
- if (fseek(file, pfn * sizeof(flags), SEEK_SET)) {
- perror("fseek kpageflags");
- _exit(1);
- }
-
- if (fread(&flags, sizeof(flags), 1, file) != 1) {
- perror("fread kpageflags");
- _exit(1);
- }
-
- fclose(file);
- return flags;
-}
-
#define VMFLAGS "VmFlags:"
static bool is_vmflag_set(unsigned long addr, const char *vmflag)
@@ -159,19 +106,13 @@ out:
#define RSS "Rss:"
#define LOCKED "lo"
-static bool is_vma_lock_on_fault(unsigned long addr)
+static unsigned long get_value_for_name(unsigned long addr, const char *name)
{
- bool ret = false;
- bool locked;
- FILE *smaps = NULL;
- unsigned long vma_size, vma_rss;
char *line = NULL;
- char *value;
size_t size = 0;
-
- locked = is_vmflag_set(addr, LOCKED);
- if (!locked)
- goto out;
+ char *value_ptr;
+ FILE *smaps = NULL;
+ unsigned long value = -1UL;
smaps = seek_to_smaps_entry(addr);
if (!smaps) {
@@ -180,112 +121,70 @@ static bool is_vma_lock_on_fault(unsigned long addr)
}
while (getline(&line, &size, smaps) > 0) {
- if (!strstr(line, SIZE)) {
+ if (!strstr(line, name)) {
free(line);
line = NULL;
size = 0;
continue;
}
- value = line + strlen(SIZE);
- if (sscanf(value, "%lu kB", &vma_size) < 1) {
+ value_ptr = line + strlen(name);
+ if (sscanf(value_ptr, "%lu kB", &value) < 1) {
printf("Unable to parse smaps entry for Size\n");
goto out;
}
break;
}
- while (getline(&line, &size, smaps) > 0) {
- if (!strstr(line, RSS)) {
- free(line);
- line = NULL;
- size = 0;
- continue;
- }
-
- value = line + strlen(RSS);
- if (sscanf(value, "%lu kB", &vma_rss) < 1) {
- printf("Unable to parse smaps entry for Rss\n");
- goto out;
- }
- break;
- }
-
- ret = locked && (vma_rss < vma_size);
out:
- free(line);
if (smaps)
fclose(smaps);
- return ret;
+ free(line);
+ return value;
}
-#define PRESENT_BIT 0x8000000000000000ULL
-#define PFN_MASK 0x007FFFFFFFFFFFFFULL
-#define UNEVICTABLE_BIT (1UL << 18)
-
-static int lock_check(char *map)
+static bool is_vma_lock_on_fault(unsigned long addr)
{
- unsigned long page_size = getpagesize();
- uint64_t page1_flags, page2_flags;
+ bool locked;
+ unsigned long vma_size, vma_rss;
- page1_flags = get_pageflags((unsigned long)map);
- page2_flags = get_pageflags((unsigned long)map + page_size);
+ locked = is_vmflag_set(addr, LOCKED);
+ if (!locked)
+ return false;
- /* Both pages should be present */
- if (((page1_flags & PRESENT_BIT) == 0) ||
- ((page2_flags & PRESENT_BIT) == 0)) {
- printf("Failed to make both pages present\n");
- return 1;
- }
+ vma_size = get_value_for_name(addr, SIZE);
+ vma_rss = get_value_for_name(addr, RSS);
- page1_flags = get_kpageflags(page1_flags & PFN_MASK);
- page2_flags = get_kpageflags(page2_flags & PFN_MASK);
+ /* only one page is faulted in */
+ return (vma_rss < vma_size);
+}
- /* Both pages should be unevictable */
- if (((page1_flags & UNEVICTABLE_BIT) == 0) ||
- ((page2_flags & UNEVICTABLE_BIT) == 0)) {
- printf("Failed to make both pages unevictable\n");
- return 1;
- }
+#define PRESENT_BIT 0x8000000000000000ULL
+#define PFN_MASK 0x007FFFFFFFFFFFFFULL
+#define UNEVICTABLE_BIT (1UL << 18)
- if (!is_vmflag_set((unsigned long)map, LOCKED)) {
- printf("VMA flag %s is missing on page 1\n", LOCKED);
- return 1;
- }
+static int lock_check(unsigned long addr)
+{
+ bool locked;
+ unsigned long vma_size, vma_rss;
- if (!is_vmflag_set((unsigned long)map + page_size, LOCKED)) {
- printf("VMA flag %s is missing on page 2\n", LOCKED);
- return 1;
- }
+ locked = is_vmflag_set(addr, LOCKED);
+ if (!locked)
+ return false;
- return 0;
+ vma_size = get_value_for_name(addr, SIZE);
+ vma_rss = get_value_for_name(addr, RSS);
+
+ return (vma_rss == vma_size);
}
static int unlock_lock_check(char *map)
{
- unsigned long page_size = getpagesize();
- uint64_t page1_flags, page2_flags;
-
- page1_flags = get_pageflags((unsigned long)map);
- page2_flags = get_pageflags((unsigned long)map + page_size);
- page1_flags = get_kpageflags(page1_flags & PFN_MASK);
- page2_flags = get_kpageflags(page2_flags & PFN_MASK);
-
- if ((page1_flags & UNEVICTABLE_BIT) || (page2_flags & UNEVICTABLE_BIT)) {
- printf("A page is still marked unevictable after unlock\n");
- return 1;
- }
-
if (is_vmflag_set((unsigned long)map, LOCKED)) {
printf("VMA flag %s is present on page 1 after unlock\n", LOCKED);
return 1;
}
- if (is_vmflag_set((unsigned long)map + page_size, LOCKED)) {
- printf("VMA flag %s is present on page 2 after unlock\n", LOCKED);
- return 1;
- }
-
return 0;
}
@@ -311,7 +210,7 @@ static int test_mlock_lock()
goto unmap;
}
- if (lock_check(map))
+ if (!lock_check((unsigned long)map))
goto unmap;
/* Now unlock and recheck attributes */
@@ -330,64 +229,18 @@ out:
static int onfault_check(char *map)
{
- unsigned long page_size = getpagesize();
- uint64_t page1_flags, page2_flags;
-
- page1_flags = get_pageflags((unsigned long)map);
- page2_flags = get_pageflags((unsigned long)map + page_size);
-
- /* Neither page should be present */
- if ((page1_flags & PRESENT_BIT) || (page2_flags & PRESENT_BIT)) {
- printf("Pages were made present by MLOCK_ONFAULT\n");
- return 1;
- }
-
*map = 'a';
- page1_flags = get_pageflags((unsigned long)map);
- page2_flags = get_pageflags((unsigned long)map + page_size);
-
- /* Only page 1 should be present */
- if ((page1_flags & PRESENT_BIT) == 0) {
- printf("Page 1 is not present after fault\n");
- return 1;
- } else if (page2_flags & PRESENT_BIT) {
- printf("Page 2 was made present\n");
- return 1;
- }
-
- page1_flags = get_kpageflags(page1_flags & PFN_MASK);
-
- /* Page 1 should be unevictable */
- if ((page1_flags & UNEVICTABLE_BIT) == 0) {
- printf("Failed to make faulted page unevictable\n");
- return 1;
- }
-
if (!is_vma_lock_on_fault((unsigned long)map)) {
printf("VMA is not marked for lock on fault\n");
return 1;
}
- if (!is_vma_lock_on_fault((unsigned long)map + page_size)) {
- printf("VMA is not marked for lock on fault\n");
- return 1;
- }
-
return 0;
}
static int unlock_onfault_check(char *map)
{
unsigned long page_size = getpagesize();
- uint64_t page1_flags;
-
- page1_flags = get_pageflags((unsigned long)map);
- page1_flags = get_kpageflags(page1_flags & PFN_MASK);
-
- if (page1_flags & UNEVICTABLE_BIT) {
- printf("Page 1 is still marked unevictable after unlock\n");
- return 1;
- }
if (is_vma_lock_on_fault((unsigned long)map) ||
is_vma_lock_on_fault((unsigned long)map + page_size)) {
@@ -445,7 +298,6 @@ static int test_lock_onfault_of_present()
char *map;
int ret = 1;
unsigned long page_size = getpagesize();
- uint64_t page1_flags, page2_flags;
map = mmap(NULL, 2 * page_size, PROT_READ | PROT_WRITE,
MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
@@ -465,17 +317,6 @@ static int test_lock_onfault_of_present()
goto unmap;
}
- page1_flags = get_pageflags((unsigned long)map);
- page2_flags = get_pageflags((unsigned long)map + page_size);
- page1_flags = get_kpageflags(page1_flags & PFN_MASK);
- page2_flags = get_kpageflags(page2_flags & PFN_MASK);
-
- /* Page 1 should be unevictable */
- if ((page1_flags & UNEVICTABLE_BIT) == 0) {
- printf("Failed to make present page unevictable\n");
- goto unmap;
- }
-
if (!is_vma_lock_on_fault((unsigned long)map) ||
!is_vma_lock_on_fault((unsigned long)map + page_size)) {
printf("VMA with present pages is not marked lock on fault\n");
@@ -507,7 +348,7 @@ static int test_munlockall()
goto out;
}
- if (lock_check(map))
+ if (!lock_check((unsigned long)map))
goto unmap;
if (munlockall()) {
@@ -549,7 +390,7 @@ static int test_munlockall()
goto out;
}
- if (lock_check(map))
+ if (!lock_check((unsigned long)map))
goto unmap;
if (munlockall()) {
diff --git a/tools/testing/selftests/vm/mremap_dontunmap.c b/tools/testing/selftests/vm/mremap_dontunmap.c
new file mode 100644
index 000000000000..3a7b5ef0b0c6
--- /dev/null
+++ b/tools/testing/selftests/vm/mremap_dontunmap.c
@@ -0,0 +1,312 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Tests for mremap w/ MREMAP_DONTUNMAP.
+ *
+ * Copyright 2020, Brian Geffon <bgeffon@google.com>
+ */
+#define _GNU_SOURCE
+#include <sys/mman.h>
+#include <errno.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+
+#include "../kselftest.h"
+
+#ifndef MREMAP_DONTUNMAP
+#define MREMAP_DONTUNMAP 4
+#endif
+
+unsigned long page_size;
+char *page_buffer;
+
+static void dump_maps(void)
+{
+ char cmd[32];
+
+ snprintf(cmd, sizeof(cmd), "cat /proc/%d/maps", getpid());
+ system(cmd);
+}
+
+#define BUG_ON(condition, description) \
+ do { \
+ if (condition) { \
+ fprintf(stderr, "[FAIL]\t%s():%d\t%s:%s\n", __func__, \
+ __LINE__, (description), strerror(errno)); \
+ dump_maps(); \
+ exit(1); \
+ } \
+ } while (0)
+
+// Try a simple operation for to "test" for kernel support this prevents
+// reporting tests as failed when it's run on an older kernel.
+static int kernel_support_for_mremap_dontunmap()
+{
+ int ret = 0;
+ unsigned long num_pages = 1;
+ void *source_mapping = mmap(NULL, num_pages * page_size, PROT_NONE,
+ MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+ BUG_ON(source_mapping == MAP_FAILED, "mmap");
+
+ // This simple remap should only fail if MREMAP_DONTUNMAP isn't
+ // supported.
+ void *dest_mapping =
+ mremap(source_mapping, num_pages * page_size, num_pages * page_size,
+ MREMAP_DONTUNMAP | MREMAP_MAYMOVE, 0);
+ if (dest_mapping == MAP_FAILED) {
+ ret = errno;
+ } else {
+ BUG_ON(munmap(dest_mapping, num_pages * page_size) == -1,
+ "unable to unmap destination mapping");
+ }
+
+ BUG_ON(munmap(source_mapping, num_pages * page_size) == -1,
+ "unable to unmap source mapping");
+ return ret;
+}
+
+// This helper will just validate that an entire mapping contains the expected
+// byte.
+static int check_region_contains_byte(void *addr, unsigned long size, char byte)
+{
+ BUG_ON(size & (page_size - 1),
+ "check_region_contains_byte expects page multiples");
+ BUG_ON((unsigned long)addr & (page_size - 1),
+ "check_region_contains_byte expects page alignment");
+
+ memset(page_buffer, byte, page_size);
+
+ unsigned long num_pages = size / page_size;
+ unsigned long i;
+
+ // Compare each page checking that it contains our expected byte.
+ for (i = 0; i < num_pages; ++i) {
+ int ret =
+ memcmp(addr + (i * page_size), page_buffer, page_size);
+ if (ret) {
+ return ret;
+ }
+ }
+
+ return 0;
+}
+
+// this test validates that MREMAP_DONTUNMAP moves the pagetables while leaving
+// the source mapping mapped.
+static void mremap_dontunmap_simple()
+{
+ unsigned long num_pages = 5;
+
+ void *source_mapping =
+ mmap(NULL, num_pages * page_size, PROT_READ | PROT_WRITE,
+ MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+ BUG_ON(source_mapping == MAP_FAILED, "mmap");
+
+ memset(source_mapping, 'a', num_pages * page_size);
+
+ // Try to just move the whole mapping anywhere (not fixed).
+ void *dest_mapping =
+ mremap(source_mapping, num_pages * page_size, num_pages * page_size,
+ MREMAP_DONTUNMAP | MREMAP_MAYMOVE, NULL);
+ BUG_ON(dest_mapping == MAP_FAILED, "mremap");
+
+ // Validate that the pages have been moved, we know they were moved if
+ // the dest_mapping contains a's.
+ BUG_ON(check_region_contains_byte
+ (dest_mapping, num_pages * page_size, 'a') != 0,
+ "pages did not migrate");
+ BUG_ON(check_region_contains_byte
+ (source_mapping, num_pages * page_size, 0) != 0,
+ "source should have no ptes");
+
+ BUG_ON(munmap(dest_mapping, num_pages * page_size) == -1,
+ "unable to unmap destination mapping");
+ BUG_ON(munmap(source_mapping, num_pages * page_size) == -1,
+ "unable to unmap source mapping");
+}
+
+// This test validates MREMAP_DONTUNMAP will move page tables to a specific
+// destination using MREMAP_FIXED, also while validating that the source
+// remains intact.
+static void mremap_dontunmap_simple_fixed()
+{
+ unsigned long num_pages = 5;
+
+ // Since we want to guarantee that we can remap to a point, we will
+ // create a mapping up front.
+ void *dest_mapping =
+ mmap(NULL, num_pages * page_size, PROT_READ | PROT_WRITE,
+ MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+ BUG_ON(dest_mapping == MAP_FAILED, "mmap");
+ memset(dest_mapping, 'X', num_pages * page_size);
+
+ void *source_mapping =
+ mmap(NULL, num_pages * page_size, PROT_READ | PROT_WRITE,
+ MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+ BUG_ON(source_mapping == MAP_FAILED, "mmap");
+ memset(source_mapping, 'a', num_pages * page_size);
+
+ void *remapped_mapping =
+ mremap(source_mapping, num_pages * page_size, num_pages * page_size,
+ MREMAP_FIXED | MREMAP_DONTUNMAP | MREMAP_MAYMOVE,
+ dest_mapping);
+ BUG_ON(remapped_mapping == MAP_FAILED, "mremap");
+ BUG_ON(remapped_mapping != dest_mapping,
+ "mremap should have placed the remapped mapping at dest_mapping");
+
+ // The dest mapping will have been unmap by mremap so we expect the Xs
+ // to be gone and replaced with a's.
+ BUG_ON(check_region_contains_byte
+ (dest_mapping, num_pages * page_size, 'a') != 0,
+ "pages did not migrate");
+
+ // And the source mapping will have had its ptes dropped.
+ BUG_ON(check_region_contains_byte
+ (source_mapping, num_pages * page_size, 0) != 0,
+ "source should have no ptes");
+
+ BUG_ON(munmap(dest_mapping, num_pages * page_size) == -1,
+ "unable to unmap destination mapping");
+ BUG_ON(munmap(source_mapping, num_pages * page_size) == -1,
+ "unable to unmap source mapping");
+}
+
+// This test validates that we can MREMAP_DONTUNMAP for a portion of an
+// existing mapping.
+static void mremap_dontunmap_partial_mapping()
+{
+ /*
+ * source mapping:
+ * --------------
+ * | aaaaaaaaaa |
+ * --------------
+ * to become:
+ * --------------
+ * | aaaaa00000 |
+ * --------------
+ * With the destination mapping containing 5 pages of As.
+ * ---------
+ * | aaaaa |
+ * ---------
+ */
+ unsigned long num_pages = 10;
+ void *source_mapping =
+ mmap(NULL, num_pages * page_size, PROT_READ | PROT_WRITE,
+ MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+ BUG_ON(source_mapping == MAP_FAILED, "mmap");
+ memset(source_mapping, 'a', num_pages * page_size);
+
+ // We will grab the last 5 pages of the source and move them.
+ void *dest_mapping =
+ mremap(source_mapping + (5 * page_size), 5 * page_size,
+ 5 * page_size,
+ MREMAP_DONTUNMAP | MREMAP_MAYMOVE, NULL);
+ BUG_ON(dest_mapping == MAP_FAILED, "mremap");
+
+ // We expect the first 5 pages of the source to contain a's and the
+ // final 5 pages to contain zeros.
+ BUG_ON(check_region_contains_byte(source_mapping, 5 * page_size, 'a') !=
+ 0, "first 5 pages of source should have original pages");
+ BUG_ON(check_region_contains_byte
+ (source_mapping + (5 * page_size), 5 * page_size, 0) != 0,
+ "final 5 pages of source should have no ptes");
+
+ // Finally we expect the destination to have 5 pages worth of a's.
+ BUG_ON(check_region_contains_byte(dest_mapping, 5 * page_size, 'a') !=
+ 0, "dest mapping should contain ptes from the source");
+
+ BUG_ON(munmap(dest_mapping, 5 * page_size) == -1,
+ "unable to unmap destination mapping");
+ BUG_ON(munmap(source_mapping, num_pages * page_size) == -1,
+ "unable to unmap source mapping");
+}
+
+// This test validates that we can remap over only a portion of a mapping.
+static void mremap_dontunmap_partial_mapping_overwrite(void)
+{
+ /*
+ * source mapping:
+ * ---------
+ * |aaaaa|
+ * ---------
+ * dest mapping initially:
+ * -----------
+ * |XXXXXXXXXX|
+ * ------------
+ * Source to become:
+ * ---------
+ * |00000|
+ * ---------
+ * With the destination mapping containing 5 pages of As.
+ * ------------
+ * |aaaaaXXXXX|
+ * ------------
+ */
+ void *source_mapping =
+ mmap(NULL, 5 * page_size, PROT_READ | PROT_WRITE,
+ MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+ BUG_ON(source_mapping == MAP_FAILED, "mmap");
+ memset(source_mapping, 'a', 5 * page_size);
+
+ void *dest_mapping =
+ mmap(NULL, 10 * page_size, PROT_READ | PROT_WRITE,
+ MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+ BUG_ON(dest_mapping == MAP_FAILED, "mmap");
+ memset(dest_mapping, 'X', 10 * page_size);
+
+ // We will grab the last 5 pages of the source and move them.
+ void *remapped_mapping =
+ mremap(source_mapping, 5 * page_size,
+ 5 * page_size,
+ MREMAP_DONTUNMAP | MREMAP_MAYMOVE | MREMAP_FIXED, dest_mapping);
+ BUG_ON(dest_mapping == MAP_FAILED, "mremap");
+ BUG_ON(dest_mapping != remapped_mapping, "expected to remap to dest_mapping");
+
+ BUG_ON(check_region_contains_byte(source_mapping, 5 * page_size, 0) !=
+ 0, "first 5 pages of source should have no ptes");
+
+ // Finally we expect the destination to have 5 pages worth of a's.
+ BUG_ON(check_region_contains_byte(dest_mapping, 5 * page_size, 'a') != 0,
+ "dest mapping should contain ptes from the source");
+
+ // Finally the last 5 pages shouldn't have been touched.
+ BUG_ON(check_region_contains_byte(dest_mapping + (5 * page_size),
+ 5 * page_size, 'X') != 0,
+ "dest mapping should have retained the last 5 pages");
+
+ BUG_ON(munmap(dest_mapping, 10 * page_size) == -1,
+ "unable to unmap destination mapping");
+ BUG_ON(munmap(source_mapping, 5 * page_size) == -1,
+ "unable to unmap source mapping");
+}
+
+int main(void)
+{
+ page_size = sysconf(_SC_PAGE_SIZE);
+
+ // test for kernel support for MREMAP_DONTUNMAP skipping the test if
+ // not.
+ if (kernel_support_for_mremap_dontunmap() != 0) {
+ printf("No kernel support for MREMAP_DONTUNMAP\n");
+ return KSFT_SKIP;
+ }
+
+ // Keep a page sized buffer around for when we need it.
+ page_buffer =
+ mmap(NULL, page_size, PROT_READ | PROT_WRITE,
+ MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+ BUG_ON(page_buffer == MAP_FAILED, "unable to mmap a page.");
+
+ mremap_dontunmap_simple();
+ mremap_dontunmap_simple_fixed();
+ mremap_dontunmap_partial_mapping();
+ mremap_dontunmap_partial_mapping_overwrite();
+
+ BUG_ON(munmap(page_buffer, page_size) == -1,
+ "unable to unmap page buffer");
+
+ printf("OK\n");
+ return 0;
+}
diff --git a/tools/testing/selftests/vm/pkey-helpers.h b/tools/testing/selftests/vm/pkey-helpers.h
new file mode 100644
index 000000000000..622a85848f61
--- /dev/null
+++ b/tools/testing/selftests/vm/pkey-helpers.h
@@ -0,0 +1,225 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _PKEYS_HELPER_H
+#define _PKEYS_HELPER_H
+#define _GNU_SOURCE
+#include <string.h>
+#include <stdarg.h>
+#include <stdio.h>
+#include <stdint.h>
+#include <stdbool.h>
+#include <signal.h>
+#include <assert.h>
+#include <stdlib.h>
+#include <ucontext.h>
+#include <sys/mman.h>
+
+/* Define some kernel-like types */
+#define u8 __u8
+#define u16 __u16
+#define u32 __u32
+#define u64 __u64
+
+#define PTR_ERR_ENOTSUP ((void *)-ENOTSUP)
+
+#ifndef DEBUG_LEVEL
+#define DEBUG_LEVEL 0
+#endif
+#define DPRINT_IN_SIGNAL_BUF_SIZE 4096
+extern int dprint_in_signal;
+extern char dprint_in_signal_buffer[DPRINT_IN_SIGNAL_BUF_SIZE];
+
+extern int test_nr;
+extern int iteration_nr;
+
+#ifdef __GNUC__
+__attribute__((format(printf, 1, 2)))
+#endif
+static inline void sigsafe_printf(const char *format, ...)
+{
+ va_list ap;
+
+ if (!dprint_in_signal) {
+ va_start(ap, format);
+ vprintf(format, ap);
+ va_end(ap);
+ } else {
+ int ret;
+ /*
+ * No printf() functions are signal-safe.
+ * They deadlock easily. Write the format
+ * string to get some output, even if
+ * incomplete.
+ */
+ ret = write(1, format, strlen(format));
+ if (ret < 0)
+ exit(1);
+ }
+}
+#define dprintf_level(level, args...) do { \
+ if (level <= DEBUG_LEVEL) \
+ sigsafe_printf(args); \
+} while (0)
+#define dprintf0(args...) dprintf_level(0, args)
+#define dprintf1(args...) dprintf_level(1, args)
+#define dprintf2(args...) dprintf_level(2, args)
+#define dprintf3(args...) dprintf_level(3, args)
+#define dprintf4(args...) dprintf_level(4, args)
+
+extern void abort_hooks(void);
+#define pkey_assert(condition) do { \
+ if (!(condition)) { \
+ dprintf0("assert() at %s::%d test_nr: %d iteration: %d\n", \
+ __FILE__, __LINE__, \
+ test_nr, iteration_nr); \
+ dprintf0("errno at assert: %d", errno); \
+ abort_hooks(); \
+ exit(__LINE__); \
+ } \
+} while (0)
+
+__attribute__((noinline)) int read_ptr(int *ptr);
+void expected_pkey_fault(int pkey);
+int sys_pkey_alloc(unsigned long flags, unsigned long init_val);
+int sys_pkey_free(unsigned long pkey);
+int mprotect_pkey(void *ptr, size_t size, unsigned long orig_prot,
+ unsigned long pkey);
+void record_pkey_malloc(void *ptr, long size, int prot);
+
+#if defined(__i386__) || defined(__x86_64__) /* arch */
+#include "pkey-x86.h"
+#elif defined(__powerpc64__) /* arch */
+#include "pkey-powerpc.h"
+#else /* arch */
+#error Architecture not supported
+#endif /* arch */
+
+#define PKEY_MASK (PKEY_DISABLE_ACCESS | PKEY_DISABLE_WRITE)
+
+static inline u64 set_pkey_bits(u64 reg, int pkey, u64 flags)
+{
+ u32 shift = pkey_bit_position(pkey);
+ /* mask out bits from pkey in old value */
+ reg &= ~((u64)PKEY_MASK << shift);
+ /* OR in new bits for pkey */
+ reg |= (flags & PKEY_MASK) << shift;
+ return reg;
+}
+
+static inline u64 get_pkey_bits(u64 reg, int pkey)
+{
+ u32 shift = pkey_bit_position(pkey);
+ /*
+ * shift down the relevant bits to the lowest two, then
+ * mask off all the other higher bits
+ */
+ return ((reg >> shift) & PKEY_MASK);
+}
+
+extern u64 shadow_pkey_reg;
+
+static inline u64 _read_pkey_reg(int line)
+{
+ u64 pkey_reg = __read_pkey_reg();
+
+ dprintf4("read_pkey_reg(line=%d) pkey_reg: %016llx"
+ " shadow: %016llx\n",
+ line, pkey_reg, shadow_pkey_reg);
+ assert(pkey_reg == shadow_pkey_reg);
+
+ return pkey_reg;
+}
+
+#define read_pkey_reg() _read_pkey_reg(__LINE__)
+
+static inline void write_pkey_reg(u64 pkey_reg)
+{
+ dprintf4("%s() changing %016llx to %016llx\n", __func__,
+ __read_pkey_reg(), pkey_reg);
+ /* will do the shadow check for us: */
+ read_pkey_reg();
+ __write_pkey_reg(pkey_reg);
+ shadow_pkey_reg = pkey_reg;
+ dprintf4("%s(%016llx) pkey_reg: %016llx\n", __func__,
+ pkey_reg, __read_pkey_reg());
+}
+
+/*
+ * These are technically racy. since something could
+ * change PKEY register between the read and the write.
+ */
+static inline void __pkey_access_allow(int pkey, int do_allow)
+{
+ u64 pkey_reg = read_pkey_reg();
+ int bit = pkey * 2;
+
+ if (do_allow)
+ pkey_reg &= (1<<bit);
+ else
+ pkey_reg |= (1<<bit);
+
+ dprintf4("pkey_reg now: %016llx\n", read_pkey_reg());
+ write_pkey_reg(pkey_reg);
+}
+
+static inline void __pkey_write_allow(int pkey, int do_allow_write)
+{
+ u64 pkey_reg = read_pkey_reg();
+ int bit = pkey * 2 + 1;
+
+ if (do_allow_write)
+ pkey_reg &= (1<<bit);
+ else
+ pkey_reg |= (1<<bit);
+
+ write_pkey_reg(pkey_reg);
+ dprintf4("pkey_reg now: %016llx\n", read_pkey_reg());
+}
+
+#define ARRAY_SIZE(x) (sizeof(x) / sizeof(*(x)))
+#define ALIGN_UP(x, align_to) (((x) + ((align_to)-1)) & ~((align_to)-1))
+#define ALIGN_DOWN(x, align_to) ((x) & ~((align_to)-1))
+#define ALIGN_PTR_UP(p, ptr_align_to) \
+ ((typeof(p))ALIGN_UP((unsigned long)(p), ptr_align_to))
+#define ALIGN_PTR_DOWN(p, ptr_align_to) \
+ ((typeof(p))ALIGN_DOWN((unsigned long)(p), ptr_align_to))
+#define __stringify_1(x...) #x
+#define __stringify(x...) __stringify_1(x)
+
+static inline u32 *siginfo_get_pkey_ptr(siginfo_t *si)
+{
+#ifdef si_pkey
+ return &si->si_pkey;
+#else
+ return (u32 *)(((u8 *)si) + si_pkey_offset);
+#endif
+}
+
+static inline int kernel_has_pkeys(void)
+{
+ /* try allocating a key and see if it succeeds */
+ int ret = sys_pkey_alloc(0, 0);
+ if (ret <= 0) {
+ return 0;
+ }
+ sys_pkey_free(ret);
+ return 1;
+}
+
+static inline int is_pkeys_supported(void)
+{
+ /* check if the cpu supports pkeys */
+ if (!cpu_has_pkeys()) {
+ dprintf1("SKIP: %s: no CPU support\n", __func__);
+ return 0;
+ }
+
+ /* check if the kernel supports pkeys */
+ if (!kernel_has_pkeys()) {
+ dprintf1("SKIP: %s: no kernel support\n", __func__);
+ return 0;
+ }
+
+ return 1;
+}
+
+#endif /* _PKEYS_HELPER_H */
diff --git a/tools/testing/selftests/vm/pkey-powerpc.h b/tools/testing/selftests/vm/pkey-powerpc.h
new file mode 100644
index 000000000000..1ebb586b2fbc
--- /dev/null
+++ b/tools/testing/selftests/vm/pkey-powerpc.h
@@ -0,0 +1,133 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _PKEYS_POWERPC_H
+#define _PKEYS_POWERPC_H
+
+#ifndef SYS_mprotect_key
+# define SYS_mprotect_key 386
+#endif
+#ifndef SYS_pkey_alloc
+# define SYS_pkey_alloc 384
+# define SYS_pkey_free 385
+#endif
+#define REG_IP_IDX PT_NIP
+#define REG_TRAPNO PT_TRAP
+#define gregs gp_regs
+#define fpregs fp_regs
+#define si_pkey_offset 0x20
+
+#undef PKEY_DISABLE_ACCESS
+#define PKEY_DISABLE_ACCESS 0x3 /* disable read and write */
+
+#undef PKEY_DISABLE_WRITE
+#define PKEY_DISABLE_WRITE 0x2
+
+#define NR_PKEYS 32
+#define NR_RESERVED_PKEYS_4K 27 /* pkey-0, pkey-1, exec-only-pkey
+ and 24 other keys that cannot be
+ represented in the PTE */
+#define NR_RESERVED_PKEYS_64K_3KEYS 3 /* PowerNV and KVM: pkey-0,
+ pkey-1 and exec-only key */
+#define NR_RESERVED_PKEYS_64K_4KEYS 4 /* PowerVM: pkey-0, pkey-1,
+ pkey-31 and exec-only key */
+#define PKEY_BITS_PER_PKEY 2
+#define HPAGE_SIZE (1UL << 24)
+#define PAGE_SIZE sysconf(_SC_PAGESIZE)
+
+static inline u32 pkey_bit_position(int pkey)
+{
+ return (NR_PKEYS - pkey - 1) * PKEY_BITS_PER_PKEY;
+}
+
+static inline u64 __read_pkey_reg(void)
+{
+ u64 pkey_reg;
+
+ asm volatile("mfspr %0, 0xd" : "=r" (pkey_reg));
+
+ return pkey_reg;
+}
+
+static inline void __write_pkey_reg(u64 pkey_reg)
+{
+ u64 amr = pkey_reg;
+
+ dprintf4("%s() changing %016llx to %016llx\n",
+ __func__, __read_pkey_reg(), pkey_reg);
+
+ asm volatile("isync; mtspr 0xd, %0; isync"
+ : : "r" ((unsigned long)(amr)) : "memory");
+
+ dprintf4("%s() pkey register after changing %016llx to %016llx\n",
+ __func__, __read_pkey_reg(), pkey_reg);
+}
+
+static inline int cpu_has_pkeys(void)
+{
+ /* No simple way to determine this */
+ return 1;
+}
+
+static inline bool arch_is_powervm()
+{
+ struct stat buf;
+
+ if ((stat("/sys/firmware/devicetree/base/ibm,partition-name", &buf) == 0) &&
+ (stat("/sys/firmware/devicetree/base/hmc-managed?", &buf) == 0) &&
+ (stat("/sys/firmware/devicetree/base/chosen/qemu,graphic-width", &buf) == -1) )
+ return true;
+
+ return false;
+}
+
+static inline int get_arch_reserved_keys(void)
+{
+ if (sysconf(_SC_PAGESIZE) == 4096)
+ return NR_RESERVED_PKEYS_4K;
+ else
+ if (arch_is_powervm())
+ return NR_RESERVED_PKEYS_64K_4KEYS;
+ else
+ return NR_RESERVED_PKEYS_64K_3KEYS;
+}
+
+void expect_fault_on_read_execonly_key(void *p1, int pkey)
+{
+ /*
+ * powerpc does not allow userspace to change permissions of exec-only
+ * keys since those keys are not allocated by userspace. The signal
+ * handler wont be able to reset the permissions, which means the code
+ * will infinitely continue to segfault here.
+ */
+ return;
+}
+
+/* 4-byte instructions * 16384 = 64K page */
+#define __page_o_noops() asm(".rept 16384 ; nop; .endr")
+
+void *malloc_pkey_with_mprotect_subpage(long size, int prot, u16 pkey)
+{
+ void *ptr;
+ int ret;
+
+ dprintf1("doing %s(size=%ld, prot=0x%x, pkey=%d)\n", __func__,
+ size, prot, pkey);
+ pkey_assert(pkey < NR_PKEYS);
+ ptr = mmap(NULL, size, prot, MAP_ANONYMOUS|MAP_PRIVATE, -1, 0);
+ pkey_assert(ptr != (void *)-1);
+
+ ret = syscall(__NR_subpage_prot, ptr, size, NULL);
+ if (ret) {
+ perror("subpage_perm");
+ return PTR_ERR_ENOTSUP;
+ }
+
+ ret = mprotect_pkey((void *)ptr, PAGE_SIZE, prot, pkey);
+ pkey_assert(!ret);
+ record_pkey_malloc(ptr, size, prot);
+
+ dprintf1("%s() for pkey %d @ %p\n", __func__, pkey, ptr);
+ return ptr;
+}
+
+#endif /* _PKEYS_POWERPC_H */
diff --git a/tools/testing/selftests/vm/pkey-x86.h b/tools/testing/selftests/vm/pkey-x86.h
new file mode 100644
index 000000000000..3be20f5d5275
--- /dev/null
+++ b/tools/testing/selftests/vm/pkey-x86.h
@@ -0,0 +1,181 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _PKEYS_X86_H
+#define _PKEYS_X86_H
+
+#ifdef __i386__
+
+#ifndef SYS_mprotect_key
+# define SYS_mprotect_key 380
+#endif
+
+#ifndef SYS_pkey_alloc
+# define SYS_pkey_alloc 381
+# define SYS_pkey_free 382
+#endif
+
+#define REG_IP_IDX REG_EIP
+#define si_pkey_offset 0x14
+
+#else
+
+#ifndef SYS_mprotect_key
+# define SYS_mprotect_key 329
+#endif
+
+#ifndef SYS_pkey_alloc
+# define SYS_pkey_alloc 330
+# define SYS_pkey_free 331
+#endif
+
+#define REG_IP_IDX REG_RIP
+#define si_pkey_offset 0x20
+
+#endif
+
+#ifndef PKEY_DISABLE_ACCESS
+# define PKEY_DISABLE_ACCESS 0x1
+#endif
+
+#ifndef PKEY_DISABLE_WRITE
+# define PKEY_DISABLE_WRITE 0x2
+#endif
+
+#define NR_PKEYS 16
+#define NR_RESERVED_PKEYS 2 /* pkey-0 and exec-only-pkey */
+#define PKEY_BITS_PER_PKEY 2
+#define HPAGE_SIZE (1UL<<21)
+#define PAGE_SIZE 4096
+#define MB (1<<20)
+
+static inline void __page_o_noops(void)
+{
+ /* 8-bytes of instruction * 512 bytes = 1 page */
+ asm(".rept 512 ; nopl 0x7eeeeeee(%eax) ; .endr");
+}
+
+static inline u64 __read_pkey_reg(void)
+{
+ unsigned int eax, edx;
+ unsigned int ecx = 0;
+ unsigned pkey_reg;
+
+ asm volatile(".byte 0x0f,0x01,0xee\n\t"
+ : "=a" (eax), "=d" (edx)
+ : "c" (ecx));
+ pkey_reg = eax;
+ return pkey_reg;
+}
+
+static inline void __write_pkey_reg(u64 pkey_reg)
+{
+ unsigned int eax = pkey_reg;
+ unsigned int ecx = 0;
+ unsigned int edx = 0;
+
+ dprintf4("%s() changing %016llx to %016llx\n", __func__,
+ __read_pkey_reg(), pkey_reg);
+ asm volatile(".byte 0x0f,0x01,0xef\n\t"
+ : : "a" (eax), "c" (ecx), "d" (edx));
+ assert(pkey_reg == __read_pkey_reg());
+}
+
+static inline void __cpuid(unsigned int *eax, unsigned int *ebx,
+ unsigned int *ecx, unsigned int *edx)
+{
+ /* ecx is often an input as well as an output. */
+ asm volatile(
+ "cpuid;"
+ : "=a" (*eax),
+ "=b" (*ebx),
+ "=c" (*ecx),
+ "=d" (*edx)
+ : "0" (*eax), "2" (*ecx));
+}
+
+/* Intel-defined CPU features, CPUID level 0x00000007:0 (ecx) */
+#define X86_FEATURE_PKU (1<<3) /* Protection Keys for Userspace */
+#define X86_FEATURE_OSPKE (1<<4) /* OS Protection Keys Enable */
+
+static inline int cpu_has_pkeys(void)
+{
+ unsigned int eax;
+ unsigned int ebx;
+ unsigned int ecx;
+ unsigned int edx;
+
+ eax = 0x7;
+ ecx = 0x0;
+ __cpuid(&eax, &ebx, &ecx, &edx);
+
+ if (!(ecx & X86_FEATURE_PKU)) {
+ dprintf2("cpu does not have PKU\n");
+ return 0;
+ }
+ if (!(ecx & X86_FEATURE_OSPKE)) {
+ dprintf2("cpu does not have OSPKE\n");
+ return 0;
+ }
+ return 1;
+}
+
+static inline u32 pkey_bit_position(int pkey)
+{
+ return pkey * PKEY_BITS_PER_PKEY;
+}
+
+#define XSTATE_PKEY_BIT (9)
+#define XSTATE_PKEY 0x200
+
+int pkey_reg_xstate_offset(void)
+{
+ unsigned int eax;
+ unsigned int ebx;
+ unsigned int ecx;
+ unsigned int edx;
+ int xstate_offset;
+ int xstate_size;
+ unsigned long XSTATE_CPUID = 0xd;
+ int leaf;
+
+ /* assume that XSTATE_PKEY is set in XCR0 */
+ leaf = XSTATE_PKEY_BIT;
+ {
+ eax = XSTATE_CPUID;
+ ecx = leaf;
+ __cpuid(&eax, &ebx, &ecx, &edx);
+
+ if (leaf == XSTATE_PKEY_BIT) {
+ xstate_offset = ebx;
+ xstate_size = eax;
+ }
+ }
+
+ if (xstate_size == 0) {
+ printf("could not find size/offset of PKEY in xsave state\n");
+ return 0;
+ }
+
+ return xstate_offset;
+}
+
+static inline int get_arch_reserved_keys(void)
+{
+ return NR_RESERVED_PKEYS;
+}
+
+void expect_fault_on_read_execonly_key(void *p1, int pkey)
+{
+ int ptr_contents;
+
+ ptr_contents = read_ptr(p1);
+ dprintf2("ptr (%p) contents@%d: %x\n", p1, __LINE__, ptr_contents);
+ expected_pkey_fault(pkey);
+}
+
+void *malloc_pkey_with_mprotect_subpage(long size, int prot, u16 pkey)
+{
+ return PTR_ERR_ENOTSUP;
+}
+
+#endif /* _PKEYS_X86_H */
diff --git a/tools/testing/selftests/x86/protection_keys.c b/tools/testing/selftests/vm/protection_keys.c
index 480995bceefa..fc19addcb5c8 100644
--- a/tools/testing/selftests/x86/protection_keys.c
+++ b/tools/testing/selftests/vm/protection_keys.c
@@ -1,11 +1,11 @@
// SPDX-License-Identifier: GPL-2.0
/*
- * Tests x86 Memory Protection Keys (see Documentation/core-api/protection-keys.rst)
+ * Tests Memory Protection Keys (see Documentation/vm/protection-keys.txt)
*
* There are examples in here of:
* * how to set protection keys on memory
- * * how to set/clear bits in PKRU (the rights register)
- * * how to handle SEGV_PKRU signals and extract pkey-relevant
+ * * how to set/clear bits in pkey registers (the rights register)
+ * * how to handle SEGV_PKUERR signals and extract pkey-relevant
* information from the siginfo
*
* Things to add:
@@ -22,8 +22,10 @@
* gcc -m32 -o protection_keys_32 -O2 -g -std=gnu99 -pthread -Wall protection_keys.c -lrt -ldl -lm
*/
#define _GNU_SOURCE
+#define __SANE_USERSPACE_TYPES__
#include <errno.h>
#include <linux/futex.h>
+#include <time.h>
#include <sys/time.h>
#include <sys/syscall.h>
#include <string.h>
@@ -48,34 +50,10 @@
int iteration_nr = 1;
int test_nr;
-unsigned int shadow_pkru;
-
-#define HPAGE_SIZE (1UL<<21)
-#define ARRAY_SIZE(x) (sizeof(x) / sizeof(*(x)))
-#define ALIGN_UP(x, align_to) (((x) + ((align_to)-1)) & ~((align_to)-1))
-#define ALIGN_DOWN(x, align_to) ((x) & ~((align_to)-1))
-#define ALIGN_PTR_UP(p, ptr_align_to) ((typeof(p))ALIGN_UP((unsigned long)(p), ptr_align_to))
-#define ALIGN_PTR_DOWN(p, ptr_align_to) ((typeof(p))ALIGN_DOWN((unsigned long)(p), ptr_align_to))
-#define __stringify_1(x...) #x
-#define __stringify(x...) __stringify_1(x)
-
-#define PTR_ERR_ENOTSUP ((void *)-ENOTSUP)
-
+u64 shadow_pkey_reg;
int dprint_in_signal;
char dprint_in_signal_buffer[DPRINT_IN_SIGNAL_BUF_SIZE];
-extern void abort_hooks(void);
-#define pkey_assert(condition) do { \
- if (!(condition)) { \
- dprintf0("assert() at %s::%d test_nr: %d iteration: %d\n", \
- __FILE__, __LINE__, \
- test_nr, iteration_nr); \
- dprintf0("errno at assert: %d", errno); \
- abort_hooks(); \
- exit(__LINE__); \
- } \
-} while (0)
-
void cat_into_file(char *str, char *file)
{
int fd = open(file, O_RDWR);
@@ -158,12 +136,6 @@ void abort_hooks(void)
#endif
}
-static inline void __page_o_noops(void)
-{
- /* 8-bytes of instruction * 512 bytes = 1 page */
- asm(".rept 512 ; nopl 0x7eeeeeee(%eax) ; .endr");
-}
-
/*
* This attempts to have roughly a page of instructions followed by a few
* instructions that do a write, and another page of instructions. That
@@ -174,7 +146,12 @@ static inline void __page_o_noops(void)
* will then fault, which makes sure that the fault code handles
* execute-only memory properly.
*/
+#ifdef __powerpc64__
+/* This way, both 4K and 64K alignment are maintained */
+__attribute__((__aligned__(65536)))
+#else
__attribute__((__aligned__(PAGE_SIZE)))
+#endif
void lots_o_noops_around_write(int *write_to_me)
{
dprintf3("running %s()\n", __func__);
@@ -186,51 +163,134 @@ void lots_o_noops_around_write(int *write_to_me)
dprintf3("%s() done\n", __func__);
}
-/* Define some kernel-like types */
-#define u8 uint8_t
-#define u16 uint16_t
-#define u32 uint32_t
-#define u64 uint64_t
+void dump_mem(void *dumpme, int len_bytes)
+{
+ char *c = (void *)dumpme;
+ int i;
-#ifdef __i386__
+ for (i = 0; i < len_bytes; i += sizeof(u64)) {
+ u64 *ptr = (u64 *)(c + i);
+ dprintf1("dump[%03d][@%p]: %016llx\n", i, ptr, *ptr);
+ }
+}
-#ifndef SYS_mprotect_key
-# define SYS_mprotect_key 380
-#endif
+static u32 hw_pkey_get(int pkey, unsigned long flags)
+{
+ u64 pkey_reg = __read_pkey_reg();
-#ifndef SYS_pkey_alloc
-# define SYS_pkey_alloc 381
-# define SYS_pkey_free 382
-#endif
+ dprintf1("%s(pkey=%d, flags=%lx) = %x / %d\n",
+ __func__, pkey, flags, 0, 0);
+ dprintf2("%s() raw pkey_reg: %016llx\n", __func__, pkey_reg);
-#define REG_IP_IDX REG_EIP
-#define si_pkey_offset 0x14
+ return (u32) get_pkey_bits(pkey_reg, pkey);
+}
-#else
+static int hw_pkey_set(int pkey, unsigned long rights, unsigned long flags)
+{
+ u32 mask = (PKEY_DISABLE_ACCESS|PKEY_DISABLE_WRITE);
+ u64 old_pkey_reg = __read_pkey_reg();
+ u64 new_pkey_reg;
-#ifndef SYS_mprotect_key
-# define SYS_mprotect_key 329
-#endif
+ /* make sure that 'rights' only contains the bits we expect: */
+ assert(!(rights & ~mask));
-#ifndef SYS_pkey_alloc
-# define SYS_pkey_alloc 330
-# define SYS_pkey_free 331
-#endif
+ /* modify bits accordingly in old pkey_reg and assign it */
+ new_pkey_reg = set_pkey_bits(old_pkey_reg, pkey, rights);
-#define REG_IP_IDX REG_RIP
-#define si_pkey_offset 0x20
+ __write_pkey_reg(new_pkey_reg);
-#endif
+ dprintf3("%s(pkey=%d, rights=%lx, flags=%lx) = %x"
+ " pkey_reg now: %016llx old_pkey_reg: %016llx\n",
+ __func__, pkey, rights, flags, 0, __read_pkey_reg(),
+ old_pkey_reg);
+ return 0;
+}
-void dump_mem(void *dumpme, int len_bytes)
+void pkey_disable_set(int pkey, int flags)
{
- char *c = (void *)dumpme;
- int i;
+ unsigned long syscall_flags = 0;
+ int ret;
+ int pkey_rights;
+ u64 orig_pkey_reg = read_pkey_reg();
- for (i = 0; i < len_bytes; i += sizeof(u64)) {
- u64 *ptr = (u64 *)(c + i);
- dprintf1("dump[%03d][@%p]: %016jx\n", i, ptr, *ptr);
- }
+ dprintf1("START->%s(%d, 0x%x)\n", __func__,
+ pkey, flags);
+ pkey_assert(flags & (PKEY_DISABLE_ACCESS | PKEY_DISABLE_WRITE));
+
+ pkey_rights = hw_pkey_get(pkey, syscall_flags);
+
+ dprintf1("%s(%d) hw_pkey_get(%d): %x\n", __func__,
+ pkey, pkey, pkey_rights);
+
+ pkey_assert(pkey_rights >= 0);
+
+ pkey_rights |= flags;
+
+ ret = hw_pkey_set(pkey, pkey_rights, syscall_flags);
+ assert(!ret);
+ /* pkey_reg and flags have the same format */
+ shadow_pkey_reg = set_pkey_bits(shadow_pkey_reg, pkey, pkey_rights);
+ dprintf1("%s(%d) shadow: 0x%016llx\n",
+ __func__, pkey, shadow_pkey_reg);
+
+ pkey_assert(ret >= 0);
+
+ pkey_rights = hw_pkey_get(pkey, syscall_flags);
+ dprintf1("%s(%d) hw_pkey_get(%d): %x\n", __func__,
+ pkey, pkey, pkey_rights);
+
+ dprintf1("%s(%d) pkey_reg: 0x%016llx\n",
+ __func__, pkey, read_pkey_reg());
+ if (flags)
+ pkey_assert(read_pkey_reg() >= orig_pkey_reg);
+ dprintf1("END<---%s(%d, 0x%x)\n", __func__,
+ pkey, flags);
+}
+
+void pkey_disable_clear(int pkey, int flags)
+{
+ unsigned long syscall_flags = 0;
+ int ret;
+ int pkey_rights = hw_pkey_get(pkey, syscall_flags);
+ u64 orig_pkey_reg = read_pkey_reg();
+
+ pkey_assert(flags & (PKEY_DISABLE_ACCESS | PKEY_DISABLE_WRITE));
+
+ dprintf1("%s(%d) hw_pkey_get(%d): %x\n", __func__,
+ pkey, pkey, pkey_rights);
+ pkey_assert(pkey_rights >= 0);
+
+ pkey_rights &= ~flags;
+
+ ret = hw_pkey_set(pkey, pkey_rights, 0);
+ shadow_pkey_reg = set_pkey_bits(shadow_pkey_reg, pkey, pkey_rights);
+ pkey_assert(ret >= 0);
+
+ pkey_rights = hw_pkey_get(pkey, syscall_flags);
+ dprintf1("%s(%d) hw_pkey_get(%d): %x\n", __func__,
+ pkey, pkey, pkey_rights);
+
+ dprintf1("%s(%d) pkey_reg: 0x%016llx\n", __func__,
+ pkey, read_pkey_reg());
+ if (flags)
+ assert(read_pkey_reg() <= orig_pkey_reg);
+}
+
+void pkey_write_allow(int pkey)
+{
+ pkey_disable_clear(pkey, PKEY_DISABLE_WRITE);
+}
+void pkey_write_deny(int pkey)
+{
+ pkey_disable_set(pkey, PKEY_DISABLE_WRITE);
+}
+void pkey_access_allow(int pkey)
+{
+ pkey_disable_clear(pkey, PKEY_DISABLE_ACCESS);
+}
+void pkey_access_deny(int pkey)
+{
+ pkey_disable_set(pkey, PKEY_DISABLE_ACCESS);
}
/* Failed address bound checks: */
@@ -255,7 +315,7 @@ static char *si_code_str(int si_code)
return "UNKNOWN";
}
-int pkru_faults;
+int pkey_faults;
int last_si_pkey = -1;
void signal_handler(int signum, siginfo_t *si, void *vucontext)
{
@@ -263,24 +323,28 @@ void signal_handler(int signum, siginfo_t *si, void *vucontext)
int trapno;
unsigned long ip;
char *fpregs;
- u32 *pkru_ptr;
+#if defined(__i386__) || defined(__x86_64__) /* arch */
+ u32 *pkey_reg_ptr;
+ int pkey_reg_offset;
+#endif /* arch */
u64 siginfo_pkey;
u32 *si_pkey_ptr;
- int pkru_offset;
- fpregset_t fpregset;
dprint_in_signal = 1;
dprintf1(">>>>===============SIGSEGV============================\n");
- dprintf1("%s()::%d, pkru: 0x%x shadow: %x\n", __func__, __LINE__,
- __rdpkru(), shadow_pkru);
+ dprintf1("%s()::%d, pkey_reg: 0x%016llx shadow: %016llx\n",
+ __func__, __LINE__,
+ __read_pkey_reg(), shadow_pkey_reg);
trapno = uctxt->uc_mcontext.gregs[REG_TRAPNO];
ip = uctxt->uc_mcontext.gregs[REG_IP_IDX];
- fpregset = uctxt->uc_mcontext.fpregs;
- fpregs = (void *)fpregset;
+ fpregs = (char *) uctxt->uc_mcontext.fpregs;
- dprintf2("%s() trapno: %d ip: 0x%lx info->si_code: %s/%d\n", __func__,
- trapno, ip, si_code_str(si->si_code), si->si_code);
+ dprintf2("%s() trapno: %d ip: 0x%016lx info->si_code: %s/%d\n",
+ __func__, trapno, ip, si_code_str(si->si_code),
+ si->si_code);
+
+#if defined(__i386__) || defined(__x86_64__) /* arch */
#ifdef __i386__
/*
* 32-bit has some extra padding so that userspace can tell whether
@@ -288,20 +352,22 @@ void signal_handler(int signum, siginfo_t *si, void *vucontext)
* state. We just assume that it is here.
*/
fpregs += 0x70;
-#endif
- pkru_offset = pkru_xstate_offset();
- pkru_ptr = (void *)(&fpregs[pkru_offset]);
+#endif /* i386 */
+ pkey_reg_offset = pkey_reg_xstate_offset();
+ pkey_reg_ptr = (void *)(&fpregs[pkey_reg_offset]);
- dprintf1("siginfo: %p\n", si);
- dprintf1(" fpregs: %p\n", fpregs);
/*
- * If we got a PKRU fault, we *HAVE* to have at least one bit set in
+ * If we got a PKEY fault, we *HAVE* to have at least one bit set in
* here.
*/
- dprintf1("pkru_xstate_offset: %d\n", pkru_xstate_offset());
+ dprintf1("pkey_reg_xstate_offset: %d\n", pkey_reg_xstate_offset());
if (DEBUG_LEVEL > 4)
- dump_mem(pkru_ptr - 128, 256);
- pkey_assert(*pkru_ptr);
+ dump_mem(pkey_reg_ptr - 128, 256);
+ pkey_assert(*pkey_reg_ptr);
+#endif /* arch */
+
+ dprintf1("siginfo: %p\n", si);
+ dprintf1(" fpregs: %p\n", fpregs);
if ((si->si_code == SEGV_MAPERR) ||
(si->si_code == SEGV_ACCERR) ||
@@ -310,20 +376,29 @@ void signal_handler(int signum, siginfo_t *si, void *vucontext)
exit(4);
}
- si_pkey_ptr = (u32 *)(((u8 *)si) + si_pkey_offset);
+ si_pkey_ptr = siginfo_get_pkey_ptr(si);
dprintf1("si_pkey_ptr: %p\n", si_pkey_ptr);
dump_mem((u8 *)si_pkey_ptr - 8, 24);
siginfo_pkey = *si_pkey_ptr;
pkey_assert(siginfo_pkey < NR_PKEYS);
last_si_pkey = siginfo_pkey;
- dprintf1("signal pkru from xsave: %08x\n", *pkru_ptr);
- /* need __rdpkru() version so we do not do shadow_pkru checking */
- dprintf1("signal pkru from pkru: %08x\n", __rdpkru());
- dprintf1("pkey from siginfo: %jx\n", siginfo_pkey);
- *(u64 *)pkru_ptr = 0x00000000;
- dprintf1("WARNING: set PRKU=0 to allow faulting instruction to continue\n");
- pkru_faults++;
+ /*
+ * need __read_pkey_reg() version so we do not do shadow_pkey_reg
+ * checking
+ */
+ dprintf1("signal pkey_reg from pkey_reg: %016llx\n",
+ __read_pkey_reg());
+ dprintf1("pkey from siginfo: %016llx\n", siginfo_pkey);
+#if defined(__i386__) || defined(__x86_64__) /* arch */
+ dprintf1("signal pkey_reg from xsave: %08x\n", *pkey_reg_ptr);
+ *(u64 *)pkey_reg_ptr = 0x00000000;
+ dprintf1("WARNING: set PKEY_REG=0 to allow faulting instruction to continue\n");
+#elif defined(__powerpc64__) /* arch */
+ /* restore access and let the faulting instruction continue */
+ pkey_access_allow(siginfo_pkey);
+#endif /* arch */
+ pkey_faults++;
dprintf1("<<<<==================================================\n");
dprint_in_signal = 0;
}
@@ -391,143 +466,6 @@ pid_t fork_lazy_child(void)
return forkret;
}
-#ifndef PKEY_DISABLE_ACCESS
-# define PKEY_DISABLE_ACCESS 0x1
-#endif
-
-#ifndef PKEY_DISABLE_WRITE
-# define PKEY_DISABLE_WRITE 0x2
-#endif
-
-static u32 hw_pkey_get(int pkey, unsigned long flags)
-{
- u32 mask = (PKEY_DISABLE_ACCESS|PKEY_DISABLE_WRITE);
- u32 pkru = __rdpkru();
- u32 shifted_pkru;
- u32 masked_pkru;
-
- dprintf1("%s(pkey=%d, flags=%lx) = %x / %d\n",
- __func__, pkey, flags, 0, 0);
- dprintf2("%s() raw pkru: %x\n", __func__, pkru);
-
- shifted_pkru = (pkru >> (pkey * PKRU_BITS_PER_PKEY));
- dprintf2("%s() shifted_pkru: %x\n", __func__, shifted_pkru);
- masked_pkru = shifted_pkru & mask;
- dprintf2("%s() masked pkru: %x\n", __func__, masked_pkru);
- /*
- * shift down the relevant bits to the lowest two, then
- * mask off all the other high bits.
- */
- return masked_pkru;
-}
-
-static int hw_pkey_set(int pkey, unsigned long rights, unsigned long flags)
-{
- u32 mask = (PKEY_DISABLE_ACCESS|PKEY_DISABLE_WRITE);
- u32 old_pkru = __rdpkru();
- u32 new_pkru;
-
- /* make sure that 'rights' only contains the bits we expect: */
- assert(!(rights & ~mask));
-
- /* copy old pkru */
- new_pkru = old_pkru;
- /* mask out bits from pkey in old value: */
- new_pkru &= ~(mask << (pkey * PKRU_BITS_PER_PKEY));
- /* OR in new bits for pkey: */
- new_pkru |= (rights << (pkey * PKRU_BITS_PER_PKEY));
-
- __wrpkru(new_pkru);
-
- dprintf3("%s(pkey=%d, rights=%lx, flags=%lx) = %x pkru now: %x old_pkru: %x\n",
- __func__, pkey, rights, flags, 0, __rdpkru(), old_pkru);
- return 0;
-}
-
-void pkey_disable_set(int pkey, int flags)
-{
- unsigned long syscall_flags = 0;
- int ret;
- int pkey_rights;
- u32 orig_pkru = rdpkru();
-
- dprintf1("START->%s(%d, 0x%x)\n", __func__,
- pkey, flags);
- pkey_assert(flags & (PKEY_DISABLE_ACCESS | PKEY_DISABLE_WRITE));
-
- pkey_rights = hw_pkey_get(pkey, syscall_flags);
-
- dprintf1("%s(%d) hw_pkey_get(%d): %x\n", __func__,
- pkey, pkey, pkey_rights);
- pkey_assert(pkey_rights >= 0);
-
- pkey_rights |= flags;
-
- ret = hw_pkey_set(pkey, pkey_rights, syscall_flags);
- assert(!ret);
- /*pkru and flags have the same format */
- shadow_pkru |= flags << (pkey * 2);
- dprintf1("%s(%d) shadow: 0x%x\n", __func__, pkey, shadow_pkru);
-
- pkey_assert(ret >= 0);
-
- pkey_rights = hw_pkey_get(pkey, syscall_flags);
- dprintf1("%s(%d) hw_pkey_get(%d): %x\n", __func__,
- pkey, pkey, pkey_rights);
-
- dprintf1("%s(%d) pkru: 0x%x\n", __func__, pkey, rdpkru());
- if (flags)
- pkey_assert(rdpkru() > orig_pkru);
- dprintf1("END<---%s(%d, 0x%x)\n", __func__,
- pkey, flags);
-}
-
-void pkey_disable_clear(int pkey, int flags)
-{
- unsigned long syscall_flags = 0;
- int ret;
- int pkey_rights = hw_pkey_get(pkey, syscall_flags);
- u32 orig_pkru = rdpkru();
-
- pkey_assert(flags & (PKEY_DISABLE_ACCESS | PKEY_DISABLE_WRITE));
-
- dprintf1("%s(%d) hw_pkey_get(%d): %x\n", __func__,
- pkey, pkey, pkey_rights);
- pkey_assert(pkey_rights >= 0);
-
- pkey_rights |= flags;
-
- ret = hw_pkey_set(pkey, pkey_rights, 0);
- /* pkru and flags have the same format */
- shadow_pkru &= ~(flags << (pkey * 2));
- pkey_assert(ret >= 0);
-
- pkey_rights = hw_pkey_get(pkey, syscall_flags);
- dprintf1("%s(%d) hw_pkey_get(%d): %x\n", __func__,
- pkey, pkey, pkey_rights);
-
- dprintf1("%s(%d) pkru: 0x%x\n", __func__, pkey, rdpkru());
- if (flags)
- assert(rdpkru() > orig_pkru);
-}
-
-void pkey_write_allow(int pkey)
-{
- pkey_disable_clear(pkey, PKEY_DISABLE_WRITE);
-}
-void pkey_write_deny(int pkey)
-{
- pkey_disable_set(pkey, PKEY_DISABLE_WRITE);
-}
-void pkey_access_allow(int pkey)
-{
- pkey_disable_clear(pkey, PKEY_DISABLE_ACCESS);
-}
-void pkey_access_deny(int pkey)
-{
- pkey_disable_set(pkey, PKEY_DISABLE_ACCESS);
-}
-
int sys_mprotect_pkey(void *ptr, size_t size, unsigned long orig_prot,
unsigned long pkey)
{
@@ -561,33 +499,44 @@ int alloc_pkey(void)
int ret;
unsigned long init_val = 0x0;
- dprintf1("alloc_pkey()::%d, pkru: 0x%x shadow: %x\n",
- __LINE__, __rdpkru(), shadow_pkru);
+ dprintf1("%s()::%d, pkey_reg: 0x%016llx shadow: %016llx\n",
+ __func__, __LINE__, __read_pkey_reg(), shadow_pkey_reg);
ret = sys_pkey_alloc(0, init_val);
/*
- * pkey_alloc() sets PKRU, so we need to reflect it in
- * shadow_pkru:
+ * pkey_alloc() sets PKEY register, so we need to reflect it in
+ * shadow_pkey_reg:
*/
- dprintf4("alloc_pkey()::%d, ret: %d pkru: 0x%x shadow: 0x%x\n",
- __LINE__, ret, __rdpkru(), shadow_pkru);
+ dprintf4("%s()::%d, ret: %d pkey_reg: 0x%016llx"
+ " shadow: 0x%016llx\n",
+ __func__, __LINE__, ret, __read_pkey_reg(),
+ shadow_pkey_reg);
if (ret) {
/* clear both the bits: */
- shadow_pkru &= ~(0x3 << (ret * 2));
- dprintf4("alloc_pkey()::%d, ret: %d pkru: 0x%x shadow: 0x%x\n",
- __LINE__, ret, __rdpkru(), shadow_pkru);
+ shadow_pkey_reg = set_pkey_bits(shadow_pkey_reg, ret,
+ ~PKEY_MASK);
+ dprintf4("%s()::%d, ret: %d pkey_reg: 0x%016llx"
+ " shadow: 0x%016llx\n",
+ __func__,
+ __LINE__, ret, __read_pkey_reg(),
+ shadow_pkey_reg);
/*
* move the new state in from init_val
- * (remember, we cheated and init_val == pkru format)
+ * (remember, we cheated and init_val == pkey_reg format)
*/
- shadow_pkru |= (init_val << (ret * 2));
+ shadow_pkey_reg = set_pkey_bits(shadow_pkey_reg, ret,
+ init_val);
}
- dprintf4("alloc_pkey()::%d, ret: %d pkru: 0x%x shadow: 0x%x\n",
- __LINE__, ret, __rdpkru(), shadow_pkru);
- dprintf1("alloc_pkey()::%d errno: %d\n", __LINE__, errno);
+ dprintf4("%s()::%d, ret: %d pkey_reg: 0x%016llx"
+ " shadow: 0x%016llx\n",
+ __func__, __LINE__, ret, __read_pkey_reg(),
+ shadow_pkey_reg);
+ dprintf1("%s()::%d errno: %d\n", __func__, __LINE__, errno);
/* for shadow checking: */
- rdpkru();
- dprintf4("alloc_pkey()::%d, ret: %d pkru: 0x%x shadow: 0x%x\n",
- __LINE__, ret, __rdpkru(), shadow_pkru);
+ read_pkey_reg();
+ dprintf4("%s()::%d, ret: %d pkey_reg: 0x%016llx"
+ " shadow: 0x%016llx\n",
+ __func__, __LINE__, ret, __read_pkey_reg(),
+ shadow_pkey_reg);
return ret;
}
@@ -612,10 +561,10 @@ int alloc_random_pkey(void)
int nr_alloced = 0;
int random_index;
memset(alloced_pkeys, 0, sizeof(alloced_pkeys));
+ srand((unsigned int)time(NULL));
/* allocate every possible key and make a note of which ones we got */
max_nr_pkey_allocs = NR_PKEYS;
- max_nr_pkey_allocs = 1;
for (i = 0; i < max_nr_pkey_allocs; i++) {
int new_pkey = alloc_pkey();
if (new_pkey < 0)
@@ -638,8 +587,9 @@ int alloc_random_pkey(void)
free_ret = sys_pkey_free(alloced_pkeys[i]);
pkey_assert(!free_ret);
}
- dprintf1("%s()::%d, ret: %d pkru: 0x%x shadow: 0x%x\n", __func__,
- __LINE__, ret, __rdpkru(), shadow_pkru);
+ dprintf1("%s()::%d, ret: %d pkey_reg: 0x%016llx"
+ " shadow: 0x%016llx\n", __func__,
+ __LINE__, ret, __read_pkey_reg(), shadow_pkey_reg);
return ret;
}
@@ -657,11 +607,15 @@ int mprotect_pkey(void *ptr, size_t size, unsigned long orig_prot,
if (nr_iterations-- < 0)
break;
- dprintf1("%s()::%d, ret: %d pkru: 0x%x shadow: 0x%x\n", __func__,
- __LINE__, ret, __rdpkru(), shadow_pkru);
+ dprintf1("%s()::%d, ret: %d pkey_reg: 0x%016llx"
+ " shadow: 0x%016llx\n",
+ __func__, __LINE__, ret, __read_pkey_reg(),
+ shadow_pkey_reg);
sys_pkey_free(rpkey);
- dprintf1("%s()::%d, ret: %d pkru: 0x%x shadow: 0x%x\n", __func__,
- __LINE__, ret, __rdpkru(), shadow_pkru);
+ dprintf1("%s()::%d, ret: %d pkey_reg: 0x%016llx"
+ " shadow: 0x%016llx\n",
+ __func__, __LINE__, ret, __read_pkey_reg(),
+ shadow_pkey_reg);
}
pkey_assert(pkey < NR_PKEYS);
@@ -669,8 +623,9 @@ int mprotect_pkey(void *ptr, size_t size, unsigned long orig_prot,
dprintf1("mprotect_pkey(%p, %zx, prot=0x%lx, pkey=%ld) ret: %d\n",
ptr, size, orig_prot, pkey, ret);
pkey_assert(!ret);
- dprintf1("%s()::%d, ret: %d pkru: 0x%x shadow: 0x%x\n", __func__,
- __LINE__, ret, __rdpkru(), shadow_pkru);
+ dprintf1("%s()::%d, ret: %d pkey_reg: 0x%016llx"
+ " shadow: 0x%016llx\n", __func__,
+ __LINE__, ret, __read_pkey_reg(), shadow_pkey_reg);
return ret;
}
@@ -752,7 +707,7 @@ void *malloc_pkey_with_mprotect(long size, int prot, u16 pkey)
void *ptr;
int ret;
- rdpkru();
+ read_pkey_reg();
dprintf1("doing %s(size=%ld, prot=0x%x, pkey=%d)\n", __func__,
size, prot, pkey);
pkey_assert(pkey < NR_PKEYS);
@@ -761,7 +716,7 @@ void *malloc_pkey_with_mprotect(long size, int prot, u16 pkey)
ret = mprotect_pkey((void *)ptr, PAGE_SIZE, prot, pkey);
pkey_assert(!ret);
record_pkey_malloc(ptr, size, prot);
- rdpkru();
+ read_pkey_reg();
dprintf1("%s() for pkey %d @ %p\n", __func__, pkey, ptr);
return ptr;
@@ -798,12 +753,15 @@ void *malloc_pkey_anon_huge(long size, int prot, u16 pkey)
}
int hugetlb_setup_ok;
+#define SYSFS_FMT_NR_HUGE_PAGES "/sys/kernel/mm/hugepages/hugepages-%ldkB/nr_hugepages"
#define GET_NR_HUGE_PAGES 10
void setup_hugetlbfs(void)
{
int err;
int fd;
- char buf[] = "123";
+ char buf[256];
+ long hpagesz_kb;
+ long hpagesz_mb;
if (geteuid() != 0) {
fprintf(stderr, "WARNING: not run as root, can not do hugetlb test\n");
@@ -814,11 +772,16 @@ void setup_hugetlbfs(void)
/*
* Now go make sure that we got the pages and that they
- * are 2M pages. Someone might have made 1G the default.
+ * are PMD-level pages. Someone might have made PUD-level
+ * pages the default.
*/
- fd = open("/sys/kernel/mm/hugepages/hugepages-2048kB/nr_hugepages", O_RDONLY);
+ hpagesz_kb = HPAGE_SIZE / 1024;
+ hpagesz_mb = hpagesz_kb / 1024;
+ sprintf(buf, SYSFS_FMT_NR_HUGE_PAGES, hpagesz_kb);
+ fd = open(buf, O_RDONLY);
if (fd < 0) {
- perror("opening sysfs 2M hugetlb config");
+ fprintf(stderr, "opening sysfs %ldM hugetlb config: %s\n",
+ hpagesz_mb, strerror(errno));
return;
}
@@ -826,13 +789,14 @@ void setup_hugetlbfs(void)
err = read(fd, buf, sizeof(buf)-1);
close(fd);
if (err <= 0) {
- perror("reading sysfs 2M hugetlb config");
+ fprintf(stderr, "reading sysfs %ldM hugetlb config: %s\n",
+ hpagesz_mb, strerror(errno));
return;
}
if (atoi(buf) != GET_NR_HUGE_PAGES) {
- fprintf(stderr, "could not confirm 2M pages, got: '%s' expected %d\n",
- buf, GET_NR_HUGE_PAGES);
+ fprintf(stderr, "could not confirm %ldM pages, got: '%s' expected %d\n",
+ hpagesz_mb, buf, GET_NR_HUGE_PAGES);
return;
}
@@ -886,6 +850,7 @@ void *malloc_pkey_mmap_dax(long size, int prot, u16 pkey)
void *(*pkey_malloc[])(long size, int prot, u16 pkey) = {
malloc_pkey_with_mprotect,
+ malloc_pkey_with_mprotect_subpage,
malloc_pkey_anon_huge,
malloc_pkey_hugetlb
/* can not do direct with the pkey_mprotect() API:
@@ -924,14 +889,14 @@ void *malloc_pkey(long size, int prot, u16 pkey)
return ret;
}
-int last_pkru_faults;
+int last_pkey_faults;
#define UNKNOWN_PKEY -2
-void expected_pk_fault(int pkey)
+void expected_pkey_fault(int pkey)
{
- dprintf2("%s(): last_pkru_faults: %d pkru_faults: %d\n",
- __func__, last_pkru_faults, pkru_faults);
+ dprintf2("%s(): last_pkey_faults: %d pkey_faults: %d\n",
+ __func__, last_pkey_faults, pkey_faults);
dprintf2("%s(%d): last_si_pkey: %d\n", __func__, pkey, last_si_pkey);
- pkey_assert(last_pkru_faults + 1 == pkru_faults);
+ pkey_assert(last_pkey_faults + 1 == pkey_faults);
/*
* For exec-only memory, we do not know the pkey in
@@ -940,24 +905,28 @@ void expected_pk_fault(int pkey)
if (pkey != UNKNOWN_PKEY)
pkey_assert(last_si_pkey == pkey);
+#if defined(__i386__) || defined(__x86_64__) /* arch */
/*
- * The signal handler shold have cleared out PKRU to let the
+ * The signal handler shold have cleared out PKEY register to let the
* test program continue. We now have to restore it.
*/
- if (__rdpkru() != 0)
+ if (__read_pkey_reg() != 0)
+#else /* arch */
+ if (__read_pkey_reg() != shadow_pkey_reg)
+#endif /* arch */
pkey_assert(0);
- __wrpkru(shadow_pkru);
- dprintf1("%s() set PKRU=%x to restore state after signal nuked it\n",
- __func__, shadow_pkru);
- last_pkru_faults = pkru_faults;
+ __write_pkey_reg(shadow_pkey_reg);
+ dprintf1("%s() set pkey_reg=%016llx to restore state after signal "
+ "nuked it\n", __func__, shadow_pkey_reg);
+ last_pkey_faults = pkey_faults;
last_si_pkey = -1;
}
-#define do_not_expect_pk_fault(msg) do { \
- if (last_pkru_faults != pkru_faults) \
- dprintf0("unexpected PK fault: %s\n", msg); \
- pkey_assert(last_pkru_faults == pkru_faults); \
+#define do_not_expect_pkey_fault(msg) do { \
+ if (last_pkey_faults != pkey_faults) \
+ dprintf0("unexpected PKey fault: %s\n", msg); \
+ pkey_assert(last_pkey_faults == pkey_faults); \
} while (0)
int test_fds[10] = { -1 };
@@ -1000,6 +969,58 @@ __attribute__((noinline)) int read_ptr(int *ptr)
return *ptr;
}
+void test_pkey_alloc_free_attach_pkey0(int *ptr, u16 pkey)
+{
+ int i, err;
+ int max_nr_pkey_allocs;
+ int alloced_pkeys[NR_PKEYS];
+ int nr_alloced = 0;
+ long size;
+
+ pkey_assert(pkey_last_malloc_record);
+ size = pkey_last_malloc_record->size;
+ /*
+ * This is a bit of a hack. But mprotect() requires
+ * huge-page-aligned sizes when operating on hugetlbfs.
+ * So, make sure that we use something that's a multiple
+ * of a huge page when we can.
+ */
+ if (size >= HPAGE_SIZE)
+ size = HPAGE_SIZE;
+
+ /* allocate every possible key and make sure key-0 never got allocated */
+ max_nr_pkey_allocs = NR_PKEYS;
+ for (i = 0; i < max_nr_pkey_allocs; i++) {
+ int new_pkey = alloc_pkey();
+ pkey_assert(new_pkey != 0);
+
+ if (new_pkey < 0)
+ break;
+ alloced_pkeys[nr_alloced++] = new_pkey;
+ }
+ /* free all the allocated keys */
+ for (i = 0; i < nr_alloced; i++) {
+ int free_ret;
+
+ if (!alloced_pkeys[i])
+ continue;
+ free_ret = sys_pkey_free(alloced_pkeys[i]);
+ pkey_assert(!free_ret);
+ }
+
+ /* attach key-0 in various modes */
+ err = sys_mprotect_pkey(ptr, size, PROT_READ, 0);
+ pkey_assert(!err);
+ err = sys_mprotect_pkey(ptr, size, PROT_WRITE, 0);
+ pkey_assert(!err);
+ err = sys_mprotect_pkey(ptr, size, PROT_EXEC, 0);
+ pkey_assert(!err);
+ err = sys_mprotect_pkey(ptr, size, PROT_READ|PROT_WRITE, 0);
+ pkey_assert(!err);
+ err = sys_mprotect_pkey(ptr, size, PROT_READ|PROT_WRITE|PROT_EXEC, 0);
+ pkey_assert(!err);
+}
+
void test_read_of_write_disabled_region(int *ptr, u16 pkey)
{
int ptr_contents;
@@ -1015,26 +1036,67 @@ void test_read_of_access_disabled_region(int *ptr, u16 pkey)
int ptr_contents;
dprintf1("disabling access to PKEY[%02d], doing read @ %p\n", pkey, ptr);
- rdpkru();
+ read_pkey_reg();
+ pkey_access_deny(pkey);
+ ptr_contents = read_ptr(ptr);
+ dprintf1("*ptr: %d\n", ptr_contents);
+ expected_pkey_fault(pkey);
+}
+
+void test_read_of_access_disabled_region_with_page_already_mapped(int *ptr,
+ u16 pkey)
+{
+ int ptr_contents;
+
+ dprintf1("disabling access to PKEY[%02d], doing read @ %p\n",
+ pkey, ptr);
+ ptr_contents = read_ptr(ptr);
+ dprintf1("reading ptr before disabling the read : %d\n",
+ ptr_contents);
+ read_pkey_reg();
pkey_access_deny(pkey);
ptr_contents = read_ptr(ptr);
dprintf1("*ptr: %d\n", ptr_contents);
- expected_pk_fault(pkey);
+ expected_pkey_fault(pkey);
}
+
+void test_write_of_write_disabled_region_with_page_already_mapped(int *ptr,
+ u16 pkey)
+{
+ *ptr = __LINE__;
+ dprintf1("disabling write access; after accessing the page, "
+ "to PKEY[%02d], doing write\n", pkey);
+ pkey_write_deny(pkey);
+ *ptr = __LINE__;
+ expected_pkey_fault(pkey);
+}
+
void test_write_of_write_disabled_region(int *ptr, u16 pkey)
{
dprintf1("disabling write access to PKEY[%02d], doing write\n", pkey);
pkey_write_deny(pkey);
*ptr = __LINE__;
- expected_pk_fault(pkey);
+ expected_pkey_fault(pkey);
}
void test_write_of_access_disabled_region(int *ptr, u16 pkey)
{
dprintf1("disabling access to PKEY[%02d], doing write\n", pkey);
pkey_access_deny(pkey);
*ptr = __LINE__;
- expected_pk_fault(pkey);
+ expected_pkey_fault(pkey);
}
+
+void test_write_of_access_disabled_region_with_page_already_mapped(int *ptr,
+ u16 pkey)
+{
+ *ptr = __LINE__;
+ dprintf1("disabling access; after accessing the page, "
+ " to PKEY[%02d], doing write\n", pkey);
+ pkey_access_deny(pkey);
+ *ptr = __LINE__;
+ expected_pkey_fault(pkey);
+}
+
void test_kernel_write_of_access_disabled_region(int *ptr, u16 pkey)
{
int ret;
@@ -1160,9 +1222,11 @@ void test_pkey_alloc_exhaust(int *ptr, u16 pkey)
int new_pkey;
dprintf1("%s() alloc loop: %d\n", __func__, i);
new_pkey = alloc_pkey();
- dprintf4("%s()::%d, err: %d pkru: 0x%x shadow: 0x%x\n", __func__,
- __LINE__, err, __rdpkru(), shadow_pkru);
- rdpkru(); /* for shadow checking */
+ dprintf4("%s()::%d, err: %d pkey_reg: 0x%016llx"
+ " shadow: 0x%016llx\n",
+ __func__, __LINE__, err, __read_pkey_reg(),
+ shadow_pkey_reg);
+ read_pkey_reg(); /* for shadow checking */
dprintf2("%s() errno: %d ENOSPC: %d\n", __func__, errno, ENOSPC);
if ((new_pkey == -1) && (errno == ENOSPC)) {
dprintf2("%s() failed to allocate pkey after %d tries\n",
@@ -1188,6 +1252,7 @@ void test_pkey_alloc_exhaust(int *ptr, u16 pkey)
dprintf3("%s()::%d\n", __func__, __LINE__);
/*
+ * On x86:
* There are 16 pkeys supported in hardware. Three are
* allocated by the time we get here:
* 1. The default key (0)
@@ -1195,13 +1260,21 @@ void test_pkey_alloc_exhaust(int *ptr, u16 pkey)
* 3. One allocated by the test code and passed in via
* 'pkey' to this function.
* Ensure that we can allocate at least another 13 (16-3).
+ *
+ * On powerpc:
+ * There are either 5, 28, 29 or 32 pkeys supported in
+ * hardware depending on the page size (4K or 64K) and
+ * platform (powernv or powervm). Four are allocated by
+ * the time we get here. These include pkey-0, pkey-1,
+ * exec-only pkey and the one allocated by the test code.
+ * Ensure that we can allocate the remaining.
*/
- pkey_assert(i >= NR_PKEYS-3);
+ pkey_assert(i >= (NR_PKEYS - get_arch_reserved_keys() - 1));
for (i = 0; i < nr_allocated_pkeys; i++) {
err = sys_pkey_free(allocated_pkeys[i]);
pkey_assert(!err);
- rdpkru(); /* for shadow checking */
+ read_pkey_reg(); /* for shadow checking */
}
}
@@ -1287,7 +1360,7 @@ void test_ptrace_of_child(int *ptr, u16 pkey)
pkey_assert(ret != -1);
/* Now access from the current task, and expect an exception: */
peek_result = read_ptr(ptr);
- expected_pk_fault(pkey);
+ expected_pkey_fault(pkey);
/*
* Try to access the NON-pkey-protected "plain_ptr" via ptrace:
@@ -1297,7 +1370,7 @@ void test_ptrace_of_child(int *ptr, u16 pkey)
pkey_assert(ret != -1);
/* Now access from the current task, and expect NO exception: */
peek_result = read_ptr(plain_ptr);
- do_not_expect_pk_fault("read plain pointer after ptrace");
+ do_not_expect_pkey_fault("read plain pointer after ptrace");
ret = ptrace(PTRACE_DETACH, child_pid, ignored, 0);
pkey_assert(ret != -1);
@@ -1347,17 +1420,15 @@ void test_executing_on_unreadable_memory(int *ptr, u16 pkey)
pkey_assert(!ret);
pkey_access_deny(pkey);
- dprintf2("pkru: %x\n", rdpkru());
+ dprintf2("pkey_reg: %016llx\n", read_pkey_reg());
/*
* Make sure this is an *instruction* fault
*/
madvise(p1, PAGE_SIZE, MADV_DONTNEED);
lots_o_noops_around_write(&scratch);
- do_not_expect_pk_fault("executing on PROT_EXEC memory");
- ptr_contents = read_ptr(p1);
- dprintf2("ptr (%p) contents@%d: %x\n", p1, __LINE__, ptr_contents);
- expected_pk_fault(pkey);
+ do_not_expect_pkey_fault("executing on PROT_EXEC memory");
+ expect_fault_on_read_execonly_key(p1, pkey);
}
void test_implicit_mprotect_exec_only_memory(int *ptr, u16 pkey)
@@ -1378,15 +1449,13 @@ void test_implicit_mprotect_exec_only_memory(int *ptr, u16 pkey)
ret = mprotect(p1, PAGE_SIZE, PROT_EXEC);
pkey_assert(!ret);
- dprintf2("pkru: %x\n", rdpkru());
+ dprintf2("pkey_reg: %016llx\n", read_pkey_reg());
/* Make sure this is an *instruction* fault */
madvise(p1, PAGE_SIZE, MADV_DONTNEED);
lots_o_noops_around_write(&scratch);
- do_not_expect_pk_fault("executing on PROT_EXEC memory");
- ptr_contents = read_ptr(p1);
- dprintf2("ptr (%p) contents@%d: %x\n", p1, __LINE__, ptr_contents);
- expected_pk_fault(UNKNOWN_PKEY);
+ do_not_expect_pkey_fault("executing on PROT_EXEC memory");
+ expect_fault_on_read_execonly_key(p1, UNKNOWN_PKEY);
/*
* Put the memory back to non-PROT_EXEC. Should clear the
@@ -1400,7 +1469,7 @@ void test_implicit_mprotect_exec_only_memory(int *ptr, u16 pkey)
ret = mprotect(p1, PAGE_SIZE, PROT_READ|PROT_EXEC);
pkey_assert(!ret);
ptr_contents = read_ptr(p1);
- do_not_expect_pk_fault("plain read on recently PROT_EXEC area");
+ do_not_expect_pkey_fault("plain read on recently PROT_EXEC area");
}
void test_mprotect_pkey_on_unsupported_cpu(int *ptr, u16 pkey)
@@ -1408,7 +1477,7 @@ void test_mprotect_pkey_on_unsupported_cpu(int *ptr, u16 pkey)
int size = PAGE_SIZE;
int sret;
- if (cpu_has_pku()) {
+ if (cpu_has_pkeys()) {
dprintf1("SKIP: %s: no CPU support\n", __func__);
return;
}
@@ -1420,8 +1489,11 @@ void test_mprotect_pkey_on_unsupported_cpu(int *ptr, u16 pkey)
void (*pkey_tests[])(int *ptr, u16 pkey) = {
test_read_of_write_disabled_region,
test_read_of_access_disabled_region,
+ test_read_of_access_disabled_region_with_page_already_mapped,
test_write_of_write_disabled_region,
+ test_write_of_write_disabled_region_with_page_already_mapped,
test_write_of_access_disabled_region,
+ test_write_of_access_disabled_region_with_page_already_mapped,
test_kernel_write_of_access_disabled_region,
test_kernel_write_of_write_disabled_region,
test_kernel_gup_of_access_disabled_region,
@@ -1433,6 +1505,7 @@ void (*pkey_tests[])(int *ptr, u16 pkey) = {
test_pkey_syscalls_on_non_allocated_pkey,
test_pkey_syscalls_bad_args,
test_pkey_alloc_exhaust,
+ test_pkey_alloc_free_attach_pkey0,
};
void run_tests_once(void)
@@ -1442,7 +1515,7 @@ void run_tests_once(void)
for (test_nr = 0; test_nr < ARRAY_SIZE(pkey_tests); test_nr++) {
int pkey;
- int orig_pkru_faults = pkru_faults;
+ int orig_pkey_faults = pkey_faults;
dprintf1("======================\n");
dprintf1("test %d preparing...\n", test_nr);
@@ -1457,8 +1530,8 @@ void run_tests_once(void)
free_pkey_malloc(ptr);
sys_pkey_free(pkey);
- dprintf1("pkru_faults: %d\n", pkru_faults);
- dprintf1("orig_pkru_faults: %d\n", orig_pkru_faults);
+ dprintf1("pkey_faults: %d\n", pkey_faults);
+ dprintf1("orig_pkey_faults: %d\n", orig_pkey_faults);
tracing_off();
close_test_fds();
@@ -1471,18 +1544,19 @@ void run_tests_once(void)
void pkey_setup_shadow(void)
{
- shadow_pkru = __rdpkru();
+ shadow_pkey_reg = __read_pkey_reg();
}
int main(void)
{
int nr_iterations = 22;
+ int pkeys_supported = is_pkeys_supported();
setup_handlers();
- printf("has pku: %d\n", cpu_has_pku());
+ printf("has pkeys: %d\n", pkeys_supported);
- if (!cpu_has_pku()) {
+ if (!pkeys_supported) {
int size = PAGE_SIZE;
int *ptr;
@@ -1495,7 +1569,7 @@ int main(void)
}
pkey_setup_shadow();
- printf("startup pkru: %x\n", rdpkru());
+ printf("startup pkey_reg: %016llx\n", read_pkey_reg());
setup_hugetlbfs();
while (nr_iterations-- > 0)
diff --git a/tools/testing/selftests/vm/run_vmtests b/tools/testing/selftests/vm/run_vmtests
index f33714843198..a3f4f30f0a2e 100755
--- a/tools/testing/selftests/vm/run_vmtests
+++ b/tools/testing/selftests/vm/run_vmtests
@@ -59,7 +59,7 @@ else
fi
#filter 64bit architectures
-ARCH64STR="arm64 ia64 mips64 parisc64 ppc64 riscv64 s390x sh64 sparc64 x86_64"
+ARCH64STR="arm64 ia64 mips64 parisc64 ppc64 ppc64le riscv64 s390x sh64 sparc64 x86_64"
if [ -z $ARCH ]; then
ARCH=`uname -m 2>/dev/null | sed -e 's/aarch64.*/arm64/'`
fi
@@ -123,6 +123,28 @@ else
echo "[PASS]"
fi
+echo "--------------------------------------------"
+echo "running 'gup_benchmark -U' (normal/slow gup)"
+echo "--------------------------------------------"
+./gup_benchmark -U
+if [ $? -ne 0 ]; then
+ echo "[FAIL]"
+ exitcode=1
+else
+ echo "[PASS]"
+fi
+
+echo "------------------------------------------"
+echo "running gup_benchmark -b (pin_user_pages)"
+echo "------------------------------------------"
+./gup_benchmark -b
+if [ $? -ne 0 ]; then
+ echo "[FAIL]"
+ exitcode=1
+else
+ echo "[PASS]"
+fi
+
echo "-------------------"
echo "running userfaultfd"
echo "-------------------"
@@ -270,4 +292,35 @@ else
exitcode=1
fi
+echo "------------------------------------"
+echo "running MREMAP_DONTUNMAP smoke test"
+echo "------------------------------------"
+./mremap_dontunmap
+ret_val=$?
+
+if [ $ret_val -eq 0 ]; then
+ echo "[PASS]"
+elif [ $ret_val -eq $ksft_skip ]; then
+ echo "[SKIP]"
+ exitcode=$ksft_skip
+else
+ echo "[FAIL]"
+ exitcode=1
+fi
+
+echo "running HMM smoke test"
+echo "------------------------------------"
+./test_hmm.sh smoke
+ret_val=$?
+
+if [ $ret_val -eq 0 ]; then
+ echo "[PASS]"
+elif [ $ret_val -eq $ksft_skip ]; then
+ echo "[SKIP]"
+ exitcode=$ksft_skip
+else
+ echo "[FAIL]"
+ exitcode=1
+fi
+
exit $exitcode
diff --git a/tools/testing/selftests/vm/test_hmm.sh b/tools/testing/selftests/vm/test_hmm.sh
new file mode 100755
index 000000000000..0647b525a625
--- /dev/null
+++ b/tools/testing/selftests/vm/test_hmm.sh
@@ -0,0 +1,97 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright (C) 2018 Uladzislau Rezki (Sony) <urezki@gmail.com>
+#
+# This is a test script for the kernel test driver to analyse vmalloc
+# allocator. Therefore it is just a kernel module loader. You can specify
+# and pass different parameters in order to:
+# a) analyse performance of vmalloc allocations;
+# b) stressing and stability check of vmalloc subsystem.
+
+TEST_NAME="test_hmm"
+DRIVER="test_hmm"
+
+# 1 if fails
+exitcode=1
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+check_test_requirements()
+{
+ uid=$(id -u)
+ if [ $uid -ne 0 ]; then
+ echo "$0: Must be run as root"
+ exit $ksft_skip
+ fi
+
+ if ! which modprobe > /dev/null 2>&1; then
+ echo "$0: You need modprobe installed"
+ exit $ksft_skip
+ fi
+
+ if ! modinfo $DRIVER > /dev/null 2>&1; then
+ echo "$0: You must have the following enabled in your kernel:"
+ echo "CONFIG_TEST_HMM=m"
+ exit $ksft_skip
+ fi
+}
+
+load_driver()
+{
+ modprobe $DRIVER > /dev/null 2>&1
+ if [ $? == 0 ]; then
+ major=$(awk "\$2==\"HMM_DMIRROR\" {print \$1}" /proc/devices)
+ mknod /dev/hmm_dmirror0 c $major 0
+ mknod /dev/hmm_dmirror1 c $major 1
+ fi
+}
+
+unload_driver()
+{
+ modprobe -r $DRIVER > /dev/null 2>&1
+ rm -f /dev/hmm_dmirror?
+}
+
+run_smoke()
+{
+ echo "Running smoke test. Note, this test provides basic coverage."
+
+ load_driver
+ $(dirname "${BASH_SOURCE[0]}")/hmm-tests
+ unload_driver
+}
+
+usage()
+{
+ echo -n "Usage: $0"
+ echo
+ echo "Example usage:"
+ echo
+ echo "# Shows help message"
+ echo "./${TEST_NAME}.sh"
+ echo
+ echo "# Smoke testing"
+ echo "./${TEST_NAME}.sh smoke"
+ echo
+ exit 0
+}
+
+function run_test()
+{
+ if [ $# -eq 0 ]; then
+ usage
+ else
+ if [ "$1" = "smoke" ]; then
+ run_smoke
+ else
+ usage
+ fi
+ fi
+}
+
+check_test_requirements
+run_test $@
+
+exit 0
diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c
index d3362777a425..61e5cfeb1350 100644
--- a/tools/testing/selftests/vm/userfaultfd.c
+++ b/tools/testing/selftests/vm/userfaultfd.c
@@ -54,6 +54,7 @@
#include <linux/userfaultfd.h>
#include <setjmp.h>
#include <stdbool.h>
+#include <assert.h>
#include "../kselftest.h"
@@ -76,6 +77,8 @@ static int test_type;
#define ALARM_INTERVAL_SECS 10
static volatile bool test_uffdio_copy_eexist = true;
static volatile bool test_uffdio_zeropage_eexist = true;
+/* Whether to test uffd write-protection */
+static bool test_uffdio_wp = false;
static bool map_shared;
static int huge_fd;
@@ -86,6 +89,13 @@ static char *area_src, *area_src_alias, *area_dst, *area_dst_alias;
static char *zeropage;
pthread_attr_t attr;
+/* Userfaultfd test statistics */
+struct uffd_stats {
+ int cpu;
+ unsigned long missing_faults;
+ unsigned long wp_faults;
+};
+
/* pthread_mutex_t starts at page offset 0 */
#define area_mutex(___area, ___nr) \
((pthread_mutex_t *) ((___area) + (___nr)*page_size))
@@ -125,6 +135,37 @@ static void usage(void)
exit(1);
}
+static void uffd_stats_reset(struct uffd_stats *uffd_stats,
+ unsigned long n_cpus)
+{
+ int i;
+
+ for (i = 0; i < n_cpus; i++) {
+ uffd_stats[i].cpu = i;
+ uffd_stats[i].missing_faults = 0;
+ uffd_stats[i].wp_faults = 0;
+ }
+}
+
+static void uffd_stats_report(struct uffd_stats *stats, int n_cpus)
+{
+ int i;
+ unsigned long long miss_total = 0, wp_total = 0;
+
+ for (i = 0; i < n_cpus; i++) {
+ miss_total += stats[i].missing_faults;
+ wp_total += stats[i].wp_faults;
+ }
+
+ printf("userfaults: %llu missing (", miss_total);
+ for (i = 0; i < n_cpus; i++)
+ printf("%lu+", stats[i].missing_faults);
+ printf("\b), %llu wp (", wp_total);
+ for (i = 0; i < n_cpus; i++)
+ printf("%lu+", stats[i].wp_faults);
+ printf("\b)\n");
+}
+
static int anon_release_pages(char *rel_area)
{
int ret = 0;
@@ -245,10 +286,15 @@ struct uffd_test_ops {
void (*alias_mapping)(__u64 *start, size_t len, unsigned long offset);
};
-#define ANON_EXPECTED_IOCTLS ((1 << _UFFDIO_WAKE) | \
+#define SHMEM_EXPECTED_IOCTLS ((1 << _UFFDIO_WAKE) | \
(1 << _UFFDIO_COPY) | \
(1 << _UFFDIO_ZEROPAGE))
+#define ANON_EXPECTED_IOCTLS ((1 << _UFFDIO_WAKE) | \
+ (1 << _UFFDIO_COPY) | \
+ (1 << _UFFDIO_ZEROPAGE) | \
+ (1 << _UFFDIO_WRITEPROTECT))
+
static struct uffd_test_ops anon_uffd_test_ops = {
.expected_ioctls = ANON_EXPECTED_IOCTLS,
.allocate_area = anon_allocate_area,
@@ -257,7 +303,7 @@ static struct uffd_test_ops anon_uffd_test_ops = {
};
static struct uffd_test_ops shmem_uffd_test_ops = {
- .expected_ioctls = ANON_EXPECTED_IOCTLS,
+ .expected_ioctls = SHMEM_EXPECTED_IOCTLS,
.allocate_area = shmem_allocate_area,
.release_pages = shmem_release_pages,
.alias_mapping = noop_alias_mapping,
@@ -281,6 +327,21 @@ static int my_bcmp(char *str1, char *str2, size_t n)
return 0;
}
+static void wp_range(int ufd, __u64 start, __u64 len, bool wp)
+{
+ struct uffdio_writeprotect prms = { 0 };
+
+ /* Write protection page faults */
+ prms.range.start = start;
+ prms.range.len = len;
+ /* Undo write-protect, do wakeup after that */
+ prms.mode = wp ? UFFDIO_WRITEPROTECT_MODE_WP : 0;
+
+ if (ioctl(ufd, UFFDIO_WRITEPROTECT, &prms))
+ fprintf(stderr, "clear WP failed for address 0x%Lx\n",
+ start), exit(1);
+}
+
static void *locking_thread(void *arg)
{
unsigned long cpu = (unsigned long) arg;
@@ -419,7 +480,10 @@ static int __copy_page(int ufd, unsigned long offset, bool retry)
uffdio_copy.dst = (unsigned long) area_dst + offset;
uffdio_copy.src = (unsigned long) area_src + offset;
uffdio_copy.len = page_size;
- uffdio_copy.mode = 0;
+ if (test_uffdio_wp)
+ uffdio_copy.mode = UFFDIO_COPY_MODE_WP;
+ else
+ uffdio_copy.mode = 0;
uffdio_copy.copy = 0;
if (ioctl(ufd, UFFDIO_COPY, &uffdio_copy)) {
/* real retval in ufdio_copy.copy */
@@ -467,8 +531,8 @@ static int uffd_read_msg(int ufd, struct uffd_msg *msg)
return 0;
}
-/* Return 1 if page fault handled by us; otherwise 0 */
-static int uffd_handle_page_fault(struct uffd_msg *msg)
+static void uffd_handle_page_fault(struct uffd_msg *msg,
+ struct uffd_stats *stats)
{
unsigned long offset;
@@ -476,25 +540,32 @@ static int uffd_handle_page_fault(struct uffd_msg *msg)
fprintf(stderr, "unexpected msg event %u\n",
msg->event), exit(1);
- if (bounces & BOUNCE_VERIFY &&
- msg->arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WRITE)
- fprintf(stderr, "unexpected write fault\n"), exit(1);
+ if (msg->arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WP) {
+ wp_range(uffd, msg->arg.pagefault.address, page_size, false);
+ stats->wp_faults++;
+ } else {
+ /* Missing page faults */
+ if (bounces & BOUNCE_VERIFY &&
+ msg->arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WRITE)
+ fprintf(stderr, "unexpected write fault\n"), exit(1);
- offset = (char *)(unsigned long)msg->arg.pagefault.address - area_dst;
- offset &= ~(page_size-1);
+ offset = (char *)(unsigned long)msg->arg.pagefault.address - area_dst;
+ offset &= ~(page_size-1);
- return copy_page(uffd, offset);
+ if (copy_page(uffd, offset))
+ stats->missing_faults++;
+ }
}
static void *uffd_poll_thread(void *arg)
{
- unsigned long cpu = (unsigned long) arg;
+ struct uffd_stats *stats = (struct uffd_stats *)arg;
+ unsigned long cpu = stats->cpu;
struct pollfd pollfd[2];
struct uffd_msg msg;
struct uffdio_register uffd_reg;
int ret;
char tmp_chr;
- unsigned long userfaults = 0;
pollfd[0].fd = uffd;
pollfd[0].events = POLLIN;
@@ -524,7 +595,7 @@ static void *uffd_poll_thread(void *arg)
msg.event), exit(1);
break;
case UFFD_EVENT_PAGEFAULT:
- userfaults += uffd_handle_page_fault(&msg);
+ uffd_handle_page_fault(&msg, stats);
break;
case UFFD_EVENT_FORK:
close(uffd);
@@ -543,50 +614,67 @@ static void *uffd_poll_thread(void *arg)
break;
}
}
- return (void *)userfaults;
+
+ return NULL;
}
pthread_mutex_t uffd_read_mutex = PTHREAD_MUTEX_INITIALIZER;
static void *uffd_read_thread(void *arg)
{
- unsigned long *this_cpu_userfaults;
+ struct uffd_stats *stats = (struct uffd_stats *)arg;
struct uffd_msg msg;
- this_cpu_userfaults = (unsigned long *) arg;
- *this_cpu_userfaults = 0;
-
pthread_mutex_unlock(&uffd_read_mutex);
/* from here cancellation is ok */
for (;;) {
if (uffd_read_msg(uffd, &msg))
continue;
- (*this_cpu_userfaults) += uffd_handle_page_fault(&msg);
+ uffd_handle_page_fault(&msg, stats);
}
- return (void *)NULL;
+
+ return NULL;
}
static void *background_thread(void *arg)
{
unsigned long cpu = (unsigned long) arg;
- unsigned long page_nr;
+ 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;
+ mid_nr = (start_nr + end_nr) / 2;
- for (page_nr = cpu * nr_pages_per_cpu;
- page_nr < (cpu+1) * nr_pages_per_cpu;
- page_nr++)
+ /* 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);
+
+ /*
+ * 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);
+
+ /*
+ * 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);
return NULL;
}
-static int stress(unsigned long *userfaults)
+static int stress(struct uffd_stats *uffd_stats)
{
unsigned long cpu;
pthread_t locking_threads[nr_cpus];
pthread_t uffd_threads[nr_cpus];
pthread_t background_threads[nr_cpus];
- void **_userfaults = (void **) userfaults;
finished = 0;
for (cpu = 0; cpu < nr_cpus; cpu++) {
@@ -595,12 +683,13 @@ static int stress(unsigned long *userfaults)
return 1;
if (bounces & BOUNCE_POLL) {
if (pthread_create(&uffd_threads[cpu], &attr,
- uffd_poll_thread, (void *)cpu))
+ uffd_poll_thread,
+ (void *)&uffd_stats[cpu]))
return 1;
} else {
if (pthread_create(&uffd_threads[cpu], &attr,
uffd_read_thread,
- &_userfaults[cpu]))
+ (void *)&uffd_stats[cpu]))
return 1;
pthread_mutex_lock(&uffd_read_mutex);
}
@@ -637,7 +726,8 @@ static int stress(unsigned long *userfaults)
fprintf(stderr, "pipefd write error\n");
return 1;
}
- if (pthread_join(uffd_threads[cpu], &_userfaults[cpu]))
+ if (pthread_join(uffd_threads[cpu],
+ (void *)&uffd_stats[cpu]))
return 1;
} else {
if (pthread_cancel(uffd_threads[cpu]))
@@ -735,17 +825,31 @@ static int faulting_process(int signal_test)
}
for (nr = 0; nr < split_nr_pages; nr++) {
+ int steps = 1;
+ unsigned long offset = nr * page_size;
+
if (signal_test) {
if (sigsetjmp(*sigbuf, 1) != 0) {
- if (nr == lastnr) {
+ if (steps == 1 && nr == lastnr) {
fprintf(stderr, "Signal repeated\n");
return 1;
}
lastnr = nr;
if (signal_test == 1) {
- if (copy_page(uffd, nr * page_size))
- signalled++;
+ if (steps == 1) {
+ /* This is a MISSING request */
+ steps++;
+ if (copy_page(uffd, offset))
+ signalled++;
+ } else {
+ /* This is a WP request */
+ assert(steps == 2);
+ wp_range(uffd,
+ (__u64)area_dst +
+ offset,
+ page_size, false);
+ }
} else {
signalled++;
continue;
@@ -758,8 +862,13 @@ static int faulting_process(int signal_test)
fprintf(stderr,
"nr %lu memory corruption %Lu %Lu\n",
nr, count,
- count_verify[nr]), exit(1);
- }
+ count_verify[nr]);
+ }
+ /*
+ * Trigger write protection if there is by writting
+ * the same value back.
+ */
+ *area_count(area_dst, nr) = count;
}
if (signal_test)
@@ -781,6 +890,11 @@ static int faulting_process(int signal_test)
nr, count,
count_verify[nr]), exit(1);
}
+ /*
+ * Trigger write protection if there is by writting
+ * the same value back.
+ */
+ *area_count(area_dst, nr) = count;
}
if (uffd_test_ops->release_pages(area_dst))
@@ -884,6 +998,8 @@ static int userfaultfd_zeropage_test(void)
uffdio_register.range.start = (unsigned long) area_dst;
uffdio_register.range.len = nr_pages * page_size;
uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING;
+ if (test_uffdio_wp)
+ uffdio_register.mode |= UFFDIO_REGISTER_MODE_WP;
if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register))
fprintf(stderr, "register failure\n"), exit(1);
@@ -908,11 +1024,11 @@ static int userfaultfd_events_test(void)
{
struct uffdio_register uffdio_register;
unsigned long expected_ioctls;
- unsigned long userfaults;
pthread_t uffd_mon;
int err, features;
pid_t pid;
char c;
+ struct uffd_stats stats = { 0 };
printf("testing events (fork, remap, remove): ");
fflush(stdout);
@@ -929,6 +1045,8 @@ static int userfaultfd_events_test(void)
uffdio_register.range.start = (unsigned long) area_dst;
uffdio_register.range.len = nr_pages * page_size;
uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING;
+ if (test_uffdio_wp)
+ uffdio_register.mode |= UFFDIO_REGISTER_MODE_WP;
if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register))
fprintf(stderr, "register failure\n"), exit(1);
@@ -939,7 +1057,7 @@ static int userfaultfd_events_test(void)
"unexpected missing ioctl for anon memory\n"),
exit(1);
- if (pthread_create(&uffd_mon, &attr, uffd_poll_thread, NULL))
+ if (pthread_create(&uffd_mon, &attr, uffd_poll_thread, &stats))
perror("uffd_poll_thread create"), exit(1);
pid = fork();
@@ -955,13 +1073,14 @@ static int userfaultfd_events_test(void)
if (write(pipefd[1], &c, sizeof(c)) != sizeof(c))
perror("pipe write"), exit(1);
- if (pthread_join(uffd_mon, (void **)&userfaults))
+ if (pthread_join(uffd_mon, NULL))
return 1;
close(uffd);
- printf("userfaults: %ld\n", userfaults);
- return userfaults != nr_pages;
+ uffd_stats_report(&stats, 1);
+
+ return stats.missing_faults != nr_pages;
}
static int userfaultfd_sig_test(void)
@@ -973,6 +1092,7 @@ static int userfaultfd_sig_test(void)
int err, features;
pid_t pid;
char c;
+ struct uffd_stats stats = { 0 };
printf("testing signal delivery: ");
fflush(stdout);
@@ -988,6 +1108,8 @@ static int userfaultfd_sig_test(void)
uffdio_register.range.start = (unsigned long) area_dst;
uffdio_register.range.len = nr_pages * page_size;
uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING;
+ if (test_uffdio_wp)
+ uffdio_register.mode |= UFFDIO_REGISTER_MODE_WP;
if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register))
fprintf(stderr, "register failure\n"), exit(1);
@@ -1004,7 +1126,7 @@ static int userfaultfd_sig_test(void)
if (uffd_test_ops->release_pages(area_dst))
return 1;
- if (pthread_create(&uffd_mon, &attr, uffd_poll_thread, NULL))
+ if (pthread_create(&uffd_mon, &attr, uffd_poll_thread, &stats))
perror("uffd_poll_thread create"), exit(1);
pid = fork();
@@ -1030,6 +1152,7 @@ static int userfaultfd_sig_test(void)
close(uffd);
return userfaults != 0;
}
+
static int userfaultfd_stress(void)
{
void *area;
@@ -1038,7 +1161,7 @@ static int userfaultfd_stress(void)
struct uffdio_register uffdio_register;
unsigned long cpu;
int err;
- unsigned long userfaults[nr_cpus];
+ struct uffd_stats uffd_stats[nr_cpus];
uffd_test_ops->allocate_area((void **)&area_src);
if (!area_src)
@@ -1119,6 +1242,8 @@ static int userfaultfd_stress(void)
uffdio_register.range.start = (unsigned long) area_dst;
uffdio_register.range.len = nr_pages * page_size;
uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING;
+ if (test_uffdio_wp)
+ uffdio_register.mode |= UFFDIO_REGISTER_MODE_WP;
if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) {
fprintf(stderr, "register failure\n");
return 1;
@@ -1167,10 +1292,17 @@ static int userfaultfd_stress(void)
if (uffd_test_ops->release_pages(area_dst))
return 1;
+ uffd_stats_reset(uffd_stats, nr_cpus);
+
/* bounce pass */
- if (stress(userfaults))
+ if (stress(uffd_stats))
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);
+
/* unregister */
if (ioctl(uffd, UFFDIO_UNREGISTER, &uffdio_register.range)) {
fprintf(stderr, "unregister failure\n");
@@ -1209,10 +1341,7 @@ static int userfaultfd_stress(void)
area_src_alias = area_dst_alias;
area_dst_alias = tmp_area;
- printf("userfaults:");
- for (cpu = 0; cpu < nr_cpus; cpu++)
- printf(" %lu", userfaults[cpu]);
- printf("\n");
+ uffd_stats_report(uffd_stats, nr_cpus);
}
if (err)
@@ -1252,6 +1381,8 @@ static void set_test_type(const char *type)
if (!strcmp(type, "anon")) {
test_type = TEST_ANON;
uffd_test_ops = &anon_uffd_test_ops;
+ /* Only enable write-protect test for anonymous test */
+ test_uffdio_wp = true;
} else if (!strcmp(type, "hugetlb")) {
test_type = TEST_HUGETLB;
uffd_test_ops = &hugetlb_uffd_test_ops;
diff --git a/tools/testing/selftests/vm/write_hugetlb_memory.sh b/tools/testing/selftests/vm/write_hugetlb_memory.sh
new file mode 100644
index 000000000000..d3d0d108924d
--- /dev/null
+++ b/tools/testing/selftests/vm/write_hugetlb_memory.sh
@@ -0,0 +1,23 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+
+set -e
+
+size=$1
+populate=$2
+write=$3
+cgroup=$4
+path=$5
+method=$6
+private=$7
+want_sleep=$8
+reserve=$9
+
+echo "Putting task in cgroup '$cgroup'"
+echo $$ > /dev/cgroup/memory/"$cgroup"/cgroup.procs
+
+echo "Method is $method"
+
+set +e
+./write_to_hugetlbfs -p "$path" -s "$size" "$write" "$populate" -m "$method" \
+ "$private" "$want_sleep" "$reserve"
diff --git a/tools/testing/selftests/vm/write_to_hugetlbfs.c b/tools/testing/selftests/vm/write_to_hugetlbfs.c
new file mode 100644
index 000000000000..6a2caba19ee1
--- /dev/null
+++ b/tools/testing/selftests/vm/write_to_hugetlbfs.c
@@ -0,0 +1,240 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * This program reserves and uses hugetlb memory, supporting a bunch of
+ * scenarios needed by the charged_reserved_hugetlb.sh test.
+ */
+
+#include <err.h>
+#include <errno.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <sys/types.h>
+#include <sys/shm.h>
+#include <sys/stat.h>
+#include <sys/mman.h>
+
+/* Global definitions. */
+enum method {
+ HUGETLBFS,
+ MMAP_MAP_HUGETLB,
+ SHM,
+ MAX_METHOD
+};
+
+
+/* Global variables. */
+static const char *self;
+static char *shmaddr;
+static int shmid;
+
+/*
+ * Show usage and exit.
+ */
+static void exit_usage(void)
+{
+ printf("Usage: %s -p <path to hugetlbfs file> -s <size to map> "
+ "[-m <0=hugetlbfs | 1=mmap(MAP_HUGETLB)>] [-l] [-r] "
+ "[-o] [-w] [-n]\n",
+ self);
+ exit(EXIT_FAILURE);
+}
+
+void sig_handler(int signo)
+{
+ printf("Received %d.\n", signo);
+ if (signo == SIGINT) {
+ printf("Deleting the memory\n");
+ if (shmdt((const void *)shmaddr) != 0) {
+ perror("Detach failure");
+ shmctl(shmid, IPC_RMID, NULL);
+ exit(4);
+ }
+
+ shmctl(shmid, IPC_RMID, NULL);
+ printf("Done deleting the memory\n");
+ }
+ exit(2);
+}
+
+int main(int argc, char **argv)
+{
+ int fd = 0;
+ int key = 0;
+ int *ptr = NULL;
+ int c = 0;
+ int size = 0;
+ char path[256] = "";
+ enum method method = MAX_METHOD;
+ int want_sleep = 0, private = 0;
+ int populate = 0;
+ int write = 0;
+ int reserve = 1;
+
+ if (signal(SIGINT, sig_handler) == SIG_ERR)
+ err(1, "\ncan't catch SIGINT\n");
+
+ /* Parse command-line arguments. */
+ setvbuf(stdout, NULL, _IONBF, 0);
+ self = argv[0];
+
+ while ((c = getopt(argc, argv, "s:p:m:owlrn")) != -1) {
+ switch (c) {
+ case 's':
+ size = atoi(optarg);
+ break;
+ case 'p':
+ strncpy(path, optarg, sizeof(path));
+ break;
+ case 'm':
+ if (atoi(optarg) >= MAX_METHOD) {
+ errno = EINVAL;
+ perror("Invalid -m.");
+ exit_usage();
+ }
+ method = atoi(optarg);
+ break;
+ case 'o':
+ populate = 1;
+ break;
+ case 'w':
+ write = 1;
+ break;
+ case 'l':
+ want_sleep = 1;
+ break;
+ case 'r':
+ private
+ = 1;
+ break;
+ case 'n':
+ reserve = 0;
+ break;
+ default:
+ errno = EINVAL;
+ perror("Invalid arg");
+ exit_usage();
+ }
+ }
+
+ if (strncmp(path, "", sizeof(path)) != 0) {
+ printf("Writing to this path: %s\n", path);
+ } else {
+ errno = EINVAL;
+ perror("path not found");
+ exit_usage();
+ }
+
+ if (size != 0) {
+ printf("Writing this size: %d\n", size);
+ } else {
+ errno = EINVAL;
+ perror("size not found");
+ exit_usage();
+ }
+
+ if (!populate)
+ printf("Not populating.\n");
+ else
+ printf("Populating.\n");
+
+ if (!write)
+ printf("Not writing to memory.\n");
+
+ if (method == MAX_METHOD) {
+ errno = EINVAL;
+ perror("-m Invalid");
+ exit_usage();
+ } else
+ printf("Using method=%d\n", method);
+
+ if (!private)
+ printf("Shared mapping.\n");
+ else
+ printf("Private mapping.\n");
+
+ if (!reserve)
+ printf("NO_RESERVE mapping.\n");
+ else
+ printf("RESERVE mapping.\n");
+
+ switch (method) {
+ case HUGETLBFS:
+ printf("Allocating using HUGETLBFS.\n");
+ fd = open(path, O_CREAT | O_RDWR, 0777);
+ if (fd == -1)
+ err(1, "Failed to open file.");
+
+ ptr = mmap(NULL, size, PROT_READ | PROT_WRITE,
+ (private ? MAP_PRIVATE : MAP_SHARED) |
+ (populate ? MAP_POPULATE : 0) |
+ (reserve ? 0 : MAP_NORESERVE),
+ fd, 0);
+
+ if (ptr == MAP_FAILED) {
+ close(fd);
+ err(1, "Error mapping the file");
+ }
+ break;
+ case MMAP_MAP_HUGETLB:
+ printf("Allocating using MAP_HUGETLB.\n");
+ ptr = mmap(NULL, size, PROT_READ | PROT_WRITE,
+ (private ? (MAP_PRIVATE | MAP_ANONYMOUS) :
+ MAP_SHARED) |
+ MAP_HUGETLB | (populate ? MAP_POPULATE : 0) |
+ (reserve ? 0 : MAP_NORESERVE),
+ -1, 0);
+
+ if (ptr == MAP_FAILED)
+ err(1, "mmap");
+
+ printf("Returned address is %p\n", ptr);
+ break;
+ case SHM:
+ printf("Allocating using SHM.\n");
+ shmid = shmget(key, size,
+ SHM_HUGETLB | IPC_CREAT | SHM_R | SHM_W);
+ if (shmid < 0) {
+ shmid = shmget(++key, size,
+ SHM_HUGETLB | IPC_CREAT | SHM_R | SHM_W);
+ if (shmid < 0)
+ err(1, "shmget");
+ }
+ printf("shmid: 0x%x, shmget key:%d\n", shmid, key);
+
+ ptr = shmat(shmid, NULL, 0);
+ if (ptr == (int *)-1) {
+ perror("Shared memory attach failure");
+ shmctl(shmid, IPC_RMID, NULL);
+ exit(2);
+ }
+ printf("shmaddr: %p\n", ptr);
+
+ break;
+ default:
+ errno = EINVAL;
+ err(1, "Invalid method.");
+ }
+
+ if (write) {
+ printf("Writing to memory.\n");
+ memset(ptr, 1, size);
+ }
+
+ if (want_sleep) {
+ /* Signal to caller that we're done. */
+ printf("DONE\n");
+
+ /* Hold memory until external kill signal is delivered. */
+ while (1)
+ sleep(100);
+ }
+
+ if (method == HUGETLBFS)
+ close(fd);
+
+ return 0;
+}
diff --git a/tools/testing/selftests/watchdog/.gitignore b/tools/testing/selftests/watchdog/.gitignore
index 5aac51575c7e..61d7b89cdbca 100644
--- a/tools/testing/selftests/watchdog/.gitignore
+++ b/tools/testing/selftests/watchdog/.gitignore
@@ -1 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
watchdog-test
diff --git a/tools/testing/selftests/wireguard/netns.sh b/tools/testing/selftests/wireguard/netns.sh
index 936e1ca9410e..17a1f53ceba0 100755
--- a/tools/testing/selftests/wireguard/netns.sh
+++ b/tools/testing/selftests/wireguard/netns.sh
@@ -48,8 +48,11 @@ cleanup() {
exec 2>/dev/null
printf "$orig_message_cost" > /proc/sys/net/core/message_cost
ip0 link del dev wg0
+ ip0 link del dev wg1
ip1 link del dev wg0
+ ip1 link del dev wg1
ip2 link del dev wg0
+ ip2 link del dev wg1
local to_kill="$(ip netns pids $netns0) $(ip netns pids $netns1) $(ip netns pids $netns2)"
[[ -n $to_kill ]] && kill $to_kill
pp ip netns del $netns1
@@ -77,18 +80,20 @@ ip0 link set wg0 netns $netns2
key1="$(pp wg genkey)"
key2="$(pp wg genkey)"
key3="$(pp wg genkey)"
+key4="$(pp wg genkey)"
pub1="$(pp wg pubkey <<<"$key1")"
pub2="$(pp wg pubkey <<<"$key2")"
pub3="$(pp wg pubkey <<<"$key3")"
+pub4="$(pp wg pubkey <<<"$key4")"
psk="$(pp wg genpsk)"
[[ -n $key1 && -n $key2 && -n $psk ]]
configure_peers() {
ip1 addr add 192.168.241.1/24 dev wg0
- ip1 addr add fd00::1/24 dev wg0
+ ip1 addr add fd00::1/112 dev wg0
ip2 addr add 192.168.241.2/24 dev wg0
- ip2 addr add fd00::2/24 dev wg0
+ ip2 addr add fd00::2/112 dev wg0
n1 wg set wg0 \
private-key <(echo "$key1") \
@@ -230,9 +235,38 @@ n1 ping -W 1 -c 1 192.168.241.2
n1 wg set wg0 private-key <(echo "$key3")
n2 wg set wg0 peer "$pub3" preshared-key <(echo "$psk") allowed-ips 192.168.241.1/32 peer "$pub1" remove
n1 ping -W 1 -c 1 192.168.241.2
+n2 wg set wg0 peer "$pub3" remove
+
+# Test that we can route wg through wg
+ip1 addr flush dev wg0
+ip2 addr flush dev wg0
+ip1 addr add fd00::5:1/112 dev wg0
+ip2 addr add fd00::5:2/112 dev wg0
+n1 wg set wg0 private-key <(echo "$key1") peer "$pub2" preshared-key <(echo "$psk") allowed-ips fd00::5:2/128 endpoint 127.0.0.1:2
+n2 wg set wg0 private-key <(echo "$key2") listen-port 2 peer "$pub1" preshared-key <(echo "$psk") allowed-ips fd00::5:1/128 endpoint 127.212.121.99:9998
+ip1 link add wg1 type wireguard
+ip2 link add wg1 type wireguard
+ip1 addr add 192.168.241.1/24 dev wg1
+ip1 addr add fd00::1/112 dev wg1
+ip2 addr add 192.168.241.2/24 dev wg1
+ip2 addr add fd00::2/112 dev wg1
+ip1 link set mtu 1340 up dev wg1
+ip2 link set mtu 1340 up dev wg1
+n1 wg set wg1 listen-port 5 private-key <(echo "$key3") peer "$pub4" allowed-ips 192.168.241.2/32,fd00::2/128 endpoint [fd00::5:2]:5
+n2 wg set wg1 listen-port 5 private-key <(echo "$key4") peer "$pub3" allowed-ips 192.168.241.1/32,fd00::1/128 endpoint [fd00::5:1]:5
+tests
+# Try to set up a routing loop between the two namespaces
+ip1 link set netns $netns0 dev wg1
+ip0 addr add 192.168.241.1/24 dev wg1
+ip0 link set up dev wg1
+n0 ping -W 1 -c 1 192.168.241.2
+n1 wg set wg0 peer "$pub2" endpoint 192.168.241.2:7
+ip2 link del wg0
+ip2 link del wg1
+! n0 ping -W 1 -c 10 -f 192.168.241.2 || false # Should not crash kernel
+ip0 link del wg1
ip1 link del wg0
-ip2 link del wg0
# Test using NAT. We now change the topology to this:
# ┌────────────────────────────────────────┐ ┌────────────────────────────────────────────────┐ ┌────────────────────────────────────────┐
@@ -282,6 +316,20 @@ pp sleep 3
n2 ping -W 1 -c 1 192.168.241.1
n1 wg set wg0 peer "$pub2" persistent-keepalive 0
+# Test that onion routing works, even when it loops
+n1 wg set wg0 peer "$pub3" allowed-ips 192.168.242.2/32 endpoint 192.168.241.2:5
+ip1 addr add 192.168.242.1/24 dev wg0
+ip2 link add wg1 type wireguard
+ip2 addr add 192.168.242.2/24 dev wg1
+n2 wg set wg1 private-key <(echo "$key3") listen-port 5 peer "$pub1" allowed-ips 192.168.242.1/32
+ip2 link set wg1 up
+n1 ping -W 1 -c 1 192.168.242.2
+ip2 link del wg1
+n1 wg set wg0 peer "$pub3" endpoint 192.168.242.2:5
+! n1 ping -W 1 -c 1 192.168.242.2 || false # Should not crash kernel
+n1 wg set wg0 peer "$pub3" remove
+ip1 addr del 192.168.242.1/24 dev wg0
+
# Do a wg-quick(8)-style policy routing for the default route, making sure vethc has a v6 address to tease out bugs.
ip1 -6 addr add fc00::9/96 dev vethc
ip1 -6 route add default via fc00::1
diff --git a/tools/testing/selftests/wireguard/qemu/.gitignore b/tools/testing/selftests/wireguard/qemu/.gitignore
index 415b542a9d59..bfa15e6feb2f 100644
--- a/tools/testing/selftests/wireguard/qemu/.gitignore
+++ b/tools/testing/selftests/wireguard/qemu/.gitignore
@@ -1,2 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0-only
build/
distfiles/
diff --git a/tools/testing/selftests/wireguard/qemu/Makefile b/tools/testing/selftests/wireguard/qemu/Makefile
index 90598a425c18..4bdd6c1a19d3 100644
--- a/tools/testing/selftests/wireguard/qemu/Makefile
+++ b/tools/testing/selftests/wireguard/qemu/Makefile
@@ -44,7 +44,7 @@ endef
$(eval $(call tar_download,MUSL,musl,1.2.0,.tar.gz,https://musl.libc.org/releases/,c6de7b191139142d3f9a7b5b702c9cae1b5ee6e7f57e582da9328629408fd4e8))
$(eval $(call tar_download,IPERF,iperf,3.7,.tar.gz,https://downloads.es.net/pub/iperf/,d846040224317caf2f75c843d309a950a7db23f9b44b94688ccbe557d6d1710c))
$(eval $(call tar_download,BASH,bash,5.0,.tar.gz,https://ftp.gnu.org/gnu/bash/,b4a80f2ac66170b2913efbfb9f2594f1f76c7b1afd11f799e22035d63077fb4d))
-$(eval $(call tar_download,IPROUTE2,iproute2,5.4.0,.tar.xz,https://www.kernel.org/pub/linux/utils/net/iproute2/,fe97aa60a0d4c5ac830be18937e18dc3400ca713a33a89ad896ff1e3d46086ae))
+$(eval $(call tar_download,IPROUTE2,iproute2,5.6.0,.tar.xz,https://www.kernel.org/pub/linux/utils/net/iproute2/,1b5b0e25ce6e23da7526ea1da044e814ad85ba761b10dd29c2b027c056b04692))
$(eval $(call tar_download,IPTABLES,iptables,1.8.4,.tar.bz2,https://www.netfilter.org/projects/iptables/files/,993a3a5490a544c2cbf2ef15cf7e7ed21af1845baf228318d5c36ef8827e157c))
$(eval $(call tar_download,NMAP,nmap,7.80,.tar.bz2,https://nmap.org/dist/,fcfa5a0e42099e12e4bf7a68ebe6fde05553383a682e816a7ec9256ab4773faa))
$(eval $(call tar_download,IPUTILS,iputils,s20190709,.tar.gz,https://github.com/iputils/iputils/archive/s20190709.tar.gz/#,a15720dd741d7538dd2645f9f516d193636ae4300ff7dbc8bfca757bf166490a))
diff --git a/tools/testing/selftests/wireguard/qemu/arch/powerpc64le.config b/tools/testing/selftests/wireguard/qemu/arch/powerpc64le.config
index 990c510a9cfa..f52f1e2bc7f6 100644
--- a/tools/testing/selftests/wireguard/qemu/arch/powerpc64le.config
+++ b/tools/testing/selftests/wireguard/qemu/arch/powerpc64le.config
@@ -10,3 +10,4 @@ CONFIG_CMDLINE_BOOL=y
CONFIG_CMDLINE="console=hvc0 wg.success=hvc1"
CONFIG_SECTION_MISMATCH_WARN_ONLY=y
CONFIG_FRAME_WARN=1280
+CONFIG_THREAD_SHIFT=14
diff --git a/tools/testing/selftests/wireguard/qemu/debug.config b/tools/testing/selftests/wireguard/qemu/debug.config
index 5909e7ef2a5c..b50c2085c1ac 100644
--- a/tools/testing/selftests/wireguard/qemu/debug.config
+++ b/tools/testing/selftests/wireguard/qemu/debug.config
@@ -25,7 +25,6 @@ CONFIG_KASAN=y
CONFIG_KASAN_INLINE=y
CONFIG_UBSAN=y
CONFIG_UBSAN_SANITIZE_ALL=y
-CONFIG_UBSAN_NO_ALIGNMENT=y
CONFIG_UBSAN_NULL=y
CONFIG_DEBUG_KMEMLEAK=y
CONFIG_DEBUG_KMEMLEAK_EARLY_LOG_SIZE=8192
@@ -58,7 +57,6 @@ CONFIG_RCU_EQS_DEBUG=y
CONFIG_USER_STACKTRACE_SUPPORT=y
CONFIG_DEBUG_SG=y
CONFIG_DEBUG_NOTIFIERS=y
-CONFIG_DOUBLEFAULT=y
CONFIG_X86_DEBUG_FPU=y
CONFIG_DEBUG_SECTION_MISMATCH=y
CONFIG_DEBUG_PAGEALLOC=y
diff --git a/tools/testing/selftests/x86/.gitignore b/tools/testing/selftests/x86/.gitignore
index 7757f73ff9a3..1aaef5bf119a 100644
--- a/tools/testing/selftests/x86/.gitignore
+++ b/tools/testing/selftests/x86/.gitignore
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
*_32
*_64
single_step_syscall
@@ -11,5 +12,4 @@ ldt_gdt
iopl
mpx-mini-test
ioperm
-protection_keys
test_vdso
diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile
index 5d49bfec1e9a..5f16821c7f63 100644
--- a/tools/testing/selftests/x86/Makefile
+++ b/tools/testing/selftests/x86/Makefile
@@ -12,7 +12,7 @@ CAN_BUILD_WITH_NOPIE := $(shell ./check_cc.sh $(CC) trivial_program.c -no-pie)
TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt test_mremap_vdso \
check_initial_reg_state sigreturn iopl ioperm \
- protection_keys test_vdso test_vsyscall mov_ss_trap \
+ test_vdso test_vsyscall mov_ss_trap \
syscall_arg_fault
TARGETS_C_32BIT_ONLY := entry_from_vm86 test_syscall_vdso unwind_vdso \
test_FCMOV test_FCOMI test_FISTTP \
diff --git a/tools/testing/selftests/x86/pkey-helpers.h b/tools/testing/selftests/x86/pkey-helpers.h
deleted file mode 100644
index 254e5436bdd9..000000000000
--- a/tools/testing/selftests/x86/pkey-helpers.h
+++ /dev/null
@@ -1,219 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _PKEYS_HELPER_H
-#define _PKEYS_HELPER_H
-#define _GNU_SOURCE
-#include <string.h>
-#include <stdarg.h>
-#include <stdio.h>
-#include <stdint.h>
-#include <stdbool.h>
-#include <signal.h>
-#include <assert.h>
-#include <stdlib.h>
-#include <ucontext.h>
-#include <sys/mman.h>
-
-#define NR_PKEYS 16
-#define PKRU_BITS_PER_PKEY 2
-
-#ifndef DEBUG_LEVEL
-#define DEBUG_LEVEL 0
-#endif
-#define DPRINT_IN_SIGNAL_BUF_SIZE 4096
-extern int dprint_in_signal;
-extern char dprint_in_signal_buffer[DPRINT_IN_SIGNAL_BUF_SIZE];
-static inline void sigsafe_printf(const char *format, ...)
-{
- va_list ap;
-
- if (!dprint_in_signal) {
- va_start(ap, format);
- vprintf(format, ap);
- va_end(ap);
- } else {
- int ret;
- /*
- * No printf() functions are signal-safe.
- * They deadlock easily. Write the format
- * string to get some output, even if
- * incomplete.
- */
- ret = write(1, format, strlen(format));
- if (ret < 0)
- exit(1);
- }
-}
-#define dprintf_level(level, args...) do { \
- if (level <= DEBUG_LEVEL) \
- sigsafe_printf(args); \
-} while (0)
-#define dprintf0(args...) dprintf_level(0, args)
-#define dprintf1(args...) dprintf_level(1, args)
-#define dprintf2(args...) dprintf_level(2, args)
-#define dprintf3(args...) dprintf_level(3, args)
-#define dprintf4(args...) dprintf_level(4, args)
-
-extern unsigned int shadow_pkru;
-static inline unsigned int __rdpkru(void)
-{
- unsigned int eax, edx;
- unsigned int ecx = 0;
- unsigned int pkru;
-
- asm volatile(".byte 0x0f,0x01,0xee\n\t"
- : "=a" (eax), "=d" (edx)
- : "c" (ecx));
- pkru = eax;
- return pkru;
-}
-
-static inline unsigned int _rdpkru(int line)
-{
- unsigned int pkru = __rdpkru();
-
- dprintf4("rdpkru(line=%d) pkru: %x shadow: %x\n",
- line, pkru, shadow_pkru);
- assert(pkru == shadow_pkru);
-
- return pkru;
-}
-
-#define rdpkru() _rdpkru(__LINE__)
-
-static inline void __wrpkru(unsigned int pkru)
-{
- unsigned int eax = pkru;
- unsigned int ecx = 0;
- unsigned int edx = 0;
-
- dprintf4("%s() changing %08x to %08x\n", __func__, __rdpkru(), pkru);
- asm volatile(".byte 0x0f,0x01,0xef\n\t"
- : : "a" (eax), "c" (ecx), "d" (edx));
- assert(pkru == __rdpkru());
-}
-
-static inline void wrpkru(unsigned int pkru)
-{
- dprintf4("%s() changing %08x to %08x\n", __func__, __rdpkru(), pkru);
- /* will do the shadow check for us: */
- rdpkru();
- __wrpkru(pkru);
- shadow_pkru = pkru;
- dprintf4("%s(%08x) pkru: %08x\n", __func__, pkru, __rdpkru());
-}
-
-/*
- * These are technically racy. since something could
- * change PKRU between the read and the write.
- */
-static inline void __pkey_access_allow(int pkey, int do_allow)
-{
- unsigned int pkru = rdpkru();
- int bit = pkey * 2;
-
- if (do_allow)
- pkru &= (1<<bit);
- else
- pkru |= (1<<bit);
-
- dprintf4("pkru now: %08x\n", rdpkru());
- wrpkru(pkru);
-}
-
-static inline void __pkey_write_allow(int pkey, int do_allow_write)
-{
- long pkru = rdpkru();
- int bit = pkey * 2 + 1;
-
- if (do_allow_write)
- pkru &= (1<<bit);
- else
- pkru |= (1<<bit);
-
- wrpkru(pkru);
- dprintf4("pkru now: %08x\n", rdpkru());
-}
-
-#define PROT_PKEY0 0x10 /* protection key value (bit 0) */
-#define PROT_PKEY1 0x20 /* protection key value (bit 1) */
-#define PROT_PKEY2 0x40 /* protection key value (bit 2) */
-#define PROT_PKEY3 0x80 /* protection key value (bit 3) */
-
-#define PAGE_SIZE 4096
-#define MB (1<<20)
-
-static inline void __cpuid(unsigned int *eax, unsigned int *ebx,
- unsigned int *ecx, unsigned int *edx)
-{
- /* ecx is often an input as well as an output. */
- asm volatile(
- "cpuid;"
- : "=a" (*eax),
- "=b" (*ebx),
- "=c" (*ecx),
- "=d" (*edx)
- : "0" (*eax), "2" (*ecx));
-}
-
-/* Intel-defined CPU features, CPUID level 0x00000007:0 (ecx) */
-#define X86_FEATURE_PKU (1<<3) /* Protection Keys for Userspace */
-#define X86_FEATURE_OSPKE (1<<4) /* OS Protection Keys Enable */
-
-static inline int cpu_has_pku(void)
-{
- unsigned int eax;
- unsigned int ebx;
- unsigned int ecx;
- unsigned int edx;
-
- eax = 0x7;
- ecx = 0x0;
- __cpuid(&eax, &ebx, &ecx, &edx);
-
- if (!(ecx & X86_FEATURE_PKU)) {
- dprintf2("cpu does not have PKU\n");
- return 0;
- }
- if (!(ecx & X86_FEATURE_OSPKE)) {
- dprintf2("cpu does not have OSPKE\n");
- return 0;
- }
- return 1;
-}
-
-#define XSTATE_PKRU_BIT (9)
-#define XSTATE_PKRU 0x200
-
-int pkru_xstate_offset(void)
-{
- unsigned int eax;
- unsigned int ebx;
- unsigned int ecx;
- unsigned int edx;
- int xstate_offset;
- int xstate_size;
- unsigned long XSTATE_CPUID = 0xd;
- int leaf;
-
- /* assume that XSTATE_PKRU is set in XCR0 */
- leaf = XSTATE_PKRU_BIT;
- {
- eax = XSTATE_CPUID;
- ecx = leaf;
- __cpuid(&eax, &ebx, &ecx, &edx);
-
- if (leaf == XSTATE_PKRU_BIT) {
- xstate_offset = ebx;
- xstate_size = eax;
- }
- }
-
- if (xstate_size == 0) {
- printf("could not find size/offset of PKRU in xsave state\n");
- return 0;
- }
-
- return xstate_offset;
-}
-
-#endif /* _PKEYS_HELPER_H */
diff --git a/tools/testing/selftests/x86/ptrace_syscall.c b/tools/testing/selftests/x86/ptrace_syscall.c
index 6f22238f3217..12aaa063196e 100644
--- a/tools/testing/selftests/x86/ptrace_syscall.c
+++ b/tools/testing/selftests/x86/ptrace_syscall.c
@@ -414,8 +414,12 @@ int main()
#if defined(__i386__) && (!defined(__GLIBC__) || __GLIBC__ > 2 || __GLIBC_MINOR__ >= 16)
vsyscall32 = (void *)getauxval(AT_SYSINFO);
- printf("[RUN]\tCheck AT_SYSINFO return regs\n");
- test_sys32_regs(do_full_vsyscall32);
+ if (vsyscall32) {
+ printf("[RUN]\tCheck AT_SYSINFO return regs\n");
+ test_sys32_regs(do_full_vsyscall32);
+ } else {
+ printf("[SKIP]\tAT_SYSINFO is not available\n");
+ }
#endif
test_ptrace_syscall_restart();
diff --git a/tools/testing/selftests/x86/test_vdso.c b/tools/testing/selftests/x86/test_vdso.c
index 35edd61d1663..42052db0f870 100644
--- a/tools/testing/selftests/x86/test_vdso.c
+++ b/tools/testing/selftests/x86/test_vdso.c
@@ -259,6 +259,11 @@ static void test_one_clock_gettime(int clock, const char *name)
static void test_clock_gettime(void)
{
+ if (!vdso_clock_gettime) {
+ printf("[SKIP]\tNo vDSO, so skipping clock_gettime() tests\n");
+ return;
+ }
+
for (int clock = 0; clock < sizeof(clocknames) / sizeof(clocknames[0]);
clock++) {
test_one_clock_gettime(clock, clocknames[clock]);
diff --git a/tools/testing/selftests/x86/vdso_restorer.c b/tools/testing/selftests/x86/vdso_restorer.c
index 29a5c94c4b50..fe99f2434155 100644
--- a/tools/testing/selftests/x86/vdso_restorer.c
+++ b/tools/testing/selftests/x86/vdso_restorer.c
@@ -15,6 +15,7 @@
#include <err.h>
#include <stdio.h>
+#include <dlfcn.h>
#include <string.h>
#include <signal.h>
#include <unistd.h>
@@ -46,11 +47,23 @@ int main()
int nerrs = 0;
struct real_sigaction sa;
+ void *vdso = dlopen("linux-vdso.so.1",
+ RTLD_LAZY | RTLD_LOCAL | RTLD_NOLOAD);
+ if (!vdso)
+ vdso = dlopen("linux-gate.so.1",
+ RTLD_LAZY | RTLD_LOCAL | RTLD_NOLOAD);
+ if (!vdso) {
+ printf("[SKIP]\tFailed to find vDSO. Tests are not expected to work.\n");
+ return 0;
+ }
+
memset(&sa, 0, sizeof(sa));
sa.handler = handler_with_siginfo;
sa.flags = SA_SIGINFO;
sa.restorer = NULL; /* request kernel-provided restorer */
+ printf("[RUN]\tRaise a signal, SA_SIGINFO, sa.restorer == NULL\n");
+
if (syscall(SYS_rt_sigaction, SIGUSR1, &sa, NULL, 8) != 0)
err(1, "raw rt_sigaction syscall");
@@ -63,6 +76,8 @@ int main()
nerrs++;
}
+ printf("[RUN]\tRaise a signal, !SA_SIGINFO, sa.restorer == NULL\n");
+
sa.flags = 0;
sa.handler = handler_without_siginfo;
if (syscall(SYS_sigaction, SIGUSR1, &sa, 0) != 0)