summaryrefslogtreecommitdiffstats
path: root/tools
diff options
context:
space:
mode:
Diffstat (limited to 'tools')
-rw-r--r--tools/arch/arm64/include/uapi/asm/kvm.h12
-rw-r--r--tools/arch/arm64/include/uapi/asm/unistd.h1
-rw-r--r--tools/arch/x86/include/asm/cpufeatures.h2
-rw-r--r--tools/arch/x86/include/asm/disabled-features.h8
-rw-r--r--tools/arch/x86/include/asm/msr-index.h2
-rw-r--r--tools/arch/x86/include/uapi/asm/kvm.h1
-rw-r--r--tools/arch/x86/lib/x86-opcode-map.txt17
-rw-r--r--tools/bootconfig/include/linux/memblock.h12
-rw-r--r--tools/bootconfig/include/linux/printk.h5
-rw-r--r--tools/bootconfig/main.c79
-rw-r--r--tools/bootconfig/samples/bad-mixed-kv1.bconf3
-rw-r--r--tools/bootconfig/samples/bad-mixed-kv2.bconf3
-rw-r--r--tools/bootconfig/samples/bad-samekey.bconf6
-rwxr-xr-xtools/bootconfig/test-bootconfig.sh25
-rw-r--r--tools/bpf/bpftool/.gitignore2
-rw-r--r--tools/bpf/bpftool/Documentation/bpftool-feature.rst19
-rw-r--r--tools/bpf/bpftool/Documentation/bpftool-prog.rst22
-rw-r--r--tools/bpf/bpftool/Documentation/bpftool-struct_ops.rst116
-rw-r--r--tools/bpf/bpftool/Makefile36
-rw-r--r--tools/bpf/bpftool/bash-completion/bpftool110
-rw-r--r--tools/bpf/bpftool/btf.c5
-rw-r--r--tools/bpf/bpftool/btf_dumper.c199
-rw-r--r--tools/bpf/bpftool/common.c40
-rw-r--r--tools/bpf/bpftool/feature.c283
-rw-r--r--tools/bpf/bpftool/main.c10
-rw-r--r--tools/bpf/bpftool/main.h12
-rw-r--r--tools/bpf/bpftool/map.c2
-rw-r--r--tools/bpf/bpftool/prog.c458
-rw-r--r--tools/bpf/bpftool/skeleton/profiler.bpf.c119
-rw-r--r--tools/bpf/bpftool/skeleton/profiler.h46
-rw-r--r--tools/bpf/bpftool/struct_ops.c596
-rw-r--r--tools/bpf/runqslower/runqslower.bpf.c4
-rw-r--r--tools/build/feature/Makefile9
-rw-r--r--tools/build/feature/test-clang-bpf-global-var.c4
-rw-r--r--tools/edid/1024x768.S43
-rw-r--r--tools/edid/1280x1024.S43
-rw-r--r--tools/edid/1600x1200.S43
-rw-r--r--tools/edid/1680x1050.S43
-rw-r--r--tools/edid/1920x1080.S43
-rw-r--r--tools/edid/800x600.S40
-rw-r--r--tools/edid/Makefile37
-rw-r--r--tools/edid/edid.S274
-rw-r--r--tools/edid/hex1
-rw-r--r--tools/include/linux/irqflags.h12
-rw-r--r--tools/include/uapi/asm-generic/mman-common.h2
-rw-r--r--tools/include/uapi/asm-generic/unistd.h7
-rw-r--r--tools/include/uapi/asm/errno.h14
-rw-r--r--tools/include/uapi/drm/i915_drm.h32
-rw-r--r--tools/include/uapi/linux/bpf.h340
-rw-r--r--tools/include/uapi/linux/fcntl.h2
-rw-r--r--tools/include/uapi/linux/fscrypt.h14
-rw-r--r--tools/include/uapi/linux/if_link.h6
-rw-r--r--tools/include/uapi/linux/in.h2
-rw-r--r--tools/include/uapi/linux/kvm.h5
-rw-r--r--tools/include/uapi/linux/openat2.h39
-rw-r--r--tools/include/uapi/linux/perf_event.h8
-rw-r--r--tools/include/uapi/linux/prctl.h4
-rw-r--r--tools/include/uapi/linux/sched.h6
-rw-r--r--tools/include/uapi/linux/types.h (renamed from tools/testing/selftests/bpf/include/uapi/linux/types.h)0
-rw-r--r--tools/include/uapi/sound/asound.h155
-rw-r--r--tools/lib/api/fs/Build1
-rw-r--r--tools/lib/api/fs/cgroup.c67
-rw-r--r--tools/lib/api/fs/fs.h2
-rw-r--r--tools/lib/bpf/bpf.c37
-rw-r--r--tools/lib/bpf/bpf.h19
-rw-r--r--tools/lib/bpf/bpf_tracing.h223
-rw-r--r--tools/lib/bpf/btf.c20
-rw-r--r--tools/lib/bpf/btf_dump.c10
-rw-r--r--tools/lib/bpf/libbpf.c332
-rw-r--r--tools/lib/bpf/libbpf.h31
-rw-r--r--tools/lib/bpf/libbpf.map19
-rw-r--r--tools/lib/bpf/libbpf_probes.c1
-rw-r--r--tools/lib/bpf/netlink.c34
-rw-r--r--tools/lib/bpf/xsk.c16
-rw-r--r--tools/lib/perf/Documentation/examples/counting.c83
-rw-r--r--tools/lib/traceevent/event-parse.c2
-rw-r--r--tools/objtool/Build5
-rw-r--r--tools/objtool/builtin-check.c3
-rw-r--r--tools/objtool/builtin.h2
-rw-r--r--tools/objtool/check.c269
-rw-r--r--tools/objtool/check.h2
-rw-r--r--tools/objtool/elf.c281
-rw-r--r--tools/objtool/elf.h51
-rw-r--r--tools/objtool/orc_gen.c9
-rw-r--r--tools/objtool/special.c4
-rw-r--r--tools/objtool/warn.h2
-rw-r--r--tools/perf/Documentation/Makefile5
-rw-r--r--tools/perf/Documentation/intel-pt.txt992
-rw-r--r--tools/perf/Documentation/perf-config.txt74
-rw-r--r--tools/perf/Documentation/perf-inject.txt3
-rw-r--r--tools/perf/Documentation/perf-intel-pt.txt1007
-rw-r--r--tools/perf/Documentation/perf-record.txt2
-rw-r--r--tools/perf/Documentation/perf-report.txt3
-rw-r--r--tools/perf/Documentation/perf-script.txt2
-rw-r--r--tools/perf/Documentation/perf-stat.txt9
-rw-r--r--tools/perf/Makefile2
-rw-r--r--tools/perf/arch/arm/util/cs-etm.c18
-rw-r--r--tools/perf/arch/arm64/util/arm-spe.c37
-rw-r--r--tools/perf/arch/arm64/util/header.c63
-rw-r--r--tools/perf/arch/arm64/util/perf_regs.c2
-rw-r--r--tools/perf/arch/powerpc/entry/syscalls/syscall.tbl2
-rw-r--r--tools/perf/arch/powerpc/util/perf_regs.c4
-rw-r--r--tools/perf/arch/x86/entry/syscalls/syscall_64.tbl2
-rw-r--r--tools/perf/arch/x86/tests/insn-x86-dat-32.c112
-rw-r--r--tools/perf/arch/x86/tests/insn-x86-dat-64.c196
-rw-r--r--tools/perf/arch/x86/tests/insn-x86-dat-src.c236
-rw-r--r--tools/perf/arch/x86/util/auxtrace.c14
-rw-r--r--tools/perf/arch/x86/util/event.c12
-rw-r--r--tools/perf/arch/x86/util/header.c4
-rw-r--r--tools/perf/arch/x86/util/intel-bts.c41
-rw-r--r--tools/perf/arch/x86/util/intel-pt.c47
-rw-r--r--tools/perf/arch/x86/util/machine.c6
-rw-r--r--tools/perf/arch/x86/util/perf_regs.c8
-rw-r--r--tools/perf/arch/x86/util/pmu.c6
-rw-r--r--tools/perf/bench/bench.h4
-rw-r--r--tools/perf/bench/epoll-ctl.c8
-rw-r--r--tools/perf/bench/epoll-wait.c12
-rw-r--r--tools/perf/bench/futex-hash.c13
-rw-r--r--tools/perf/bench/futex-lock-pi.c12
-rw-r--r--tools/perf/bench/futex-requeue.c1
-rw-r--r--tools/perf/bench/futex-wake-parallel.c1
-rw-r--r--tools/perf/bench/futex-wake.c5
-rw-r--r--tools/perf/builtin-annotate.c4
-rw-r--r--tools/perf/builtin-diff.c24
-rw-r--r--tools/perf/builtin-probe.c6
-rw-r--r--tools/perf/builtin-report.c32
-rw-r--r--tools/perf/builtin-script.c70
-rw-r--r--tools/perf/builtin-stat.c4
-rw-r--r--tools/perf/builtin-top.c8
-rw-r--r--tools/perf/builtin-trace.c4
-rwxr-xr-xtools/perf/check-headers.sh1
-rw-r--r--tools/perf/include/bpf/pid_filter.h2
-rw-r--r--tools/perf/include/bpf/stdio.h2
-rw-r--r--tools/perf/include/bpf/unistd.h2
-rw-r--r--tools/perf/pmu-events/arch/s390/cf_z15/crypto6.json8
-rw-r--r--tools/perf/pmu-events/arch/s390/cf_z15/extended.json30
-rw-r--r--tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json3
-rw-r--r--tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json3
-rw-r--r--tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json3
-rw-r--r--tools/perf/pmu-events/jevents.c34
-rw-r--r--tools/perf/pmu-events/jevents.h2
-rw-r--r--tools/perf/pmu-events/pmu-events.h1
-rw-r--r--tools/perf/scripts/perl/check-perf-trace.pl6
-rw-r--r--tools/perf/scripts/perl/failed-syscalls.pl2
-rw-r--r--tools/perf/scripts/perl/rw-by-file.pl6
-rw-r--r--tools/perf/scripts/perl/rw-by-pid.pl10
-rw-r--r--tools/perf/scripts/perl/rwtop.pl10
-rw-r--r--tools/perf/scripts/perl/wakeup-latency.pl6
-rw-r--r--tools/perf/tests/bp_account.c2
-rw-r--r--tools/perf/tests/builtin-test.c5
-rw-r--r--tools/perf/tests/expr.c10
-rw-r--r--tools/perf/tests/sample-parsing.c7
-rw-r--r--tools/perf/tests/shell/lib/probe_vfs_getname.sh2
-rw-r--r--tools/perf/trace/beauty/beauty.h2
-rw-r--r--tools/perf/trace/beauty/prctl.c3
-rw-r--r--tools/perf/ui/browsers/annotate.c19
-rw-r--r--tools/perf/ui/gtk/annotate.c2
-rw-r--r--tools/perf/util/Build11
-rw-r--r--tools/perf/util/annotate.c196
-rw-r--r--tools/perf/util/annotate.h10
-rw-r--r--tools/perf/util/auxtrace.c22
-rw-r--r--tools/perf/util/auxtrace.h6
-rw-r--r--tools/perf/util/block-info.c109
-rw-r--r--tools/perf/util/block-info.h9
-rw-r--r--tools/perf/util/branch.h22
-rw-r--r--tools/perf/util/cgroup.c63
-rw-r--r--tools/perf/util/config.c12
-rw-r--r--tools/perf/util/config.h1
-rw-r--r--tools/perf/util/cs-etm.c159
-rw-r--r--tools/perf/util/env.c4
-rw-r--r--tools/perf/util/event.h1
-rw-r--r--tools/perf/util/evsel.c20
-rw-r--r--tools/perf/util/evsel.h6
-rw-r--r--tools/perf/util/expr.c112
-rw-r--r--tools/perf/util/expr.h8
-rw-r--r--tools/perf/util/expr.l114
-rw-r--r--tools/perf/util/expr.y185
-rw-r--r--tools/perf/util/header.c37
-rw-r--r--tools/perf/util/hist.c3
-rw-r--r--tools/perf/util/intel-pt.c2
-rw-r--r--tools/perf/util/llvm-utils.c3
-rw-r--r--tools/perf/util/machine.c61
-rw-r--r--tools/perf/util/map.c27
-rw-r--r--tools/perf/util/metricgroup.c109
-rw-r--r--tools/perf/util/mmap.c21
-rw-r--r--tools/perf/util/parse-events.c56
-rw-r--r--tools/perf/util/perf_event_attr_fprintf.c1
-rw-r--r--tools/perf/util/probe-file.c31
-rw-r--r--tools/perf/util/probe-finder.c11
-rw-r--r--tools/perf/util/scripting-engines/trace-event-python.c30
-rw-r--r--tools/perf/util/session.c8
-rw-r--r--tools/perf/util/setup.py10
-rw-r--r--tools/perf/util/stat-display.c39
-rw-r--r--tools/perf/util/stat-shadow.c10
-rw-r--r--tools/perf/util/stat.h1
-rw-r--r--tools/perf/util/symbol.c30
-rw-r--r--tools/perf/util/synthetic-events.c7
-rw-r--r--tools/perf/util/util.c18
-rw-r--r--tools/perf/util/util.h2
-rw-r--r--tools/power/cpupower/utils/idle_monitor/amd_fam14h_idle.c2
-rw-r--r--tools/power/cpupower/utils/idle_monitor/cpuidle_sysfs.c2
-rw-r--r--tools/power/cpupower/utils/idle_monitor/cpupower-monitor.c2
-rw-r--r--tools/power/cpupower/utils/idle_monitor/cpupower-monitor.h2
-rw-r--r--tools/power/x86/intel-speed-select/isst-config.c583
-rw-r--r--tools/power/x86/intel-speed-select/isst-core.c117
-rw-r--r--tools/power/x86/intel-speed-select/isst-display.c278
-rw-r--r--tools/power/x86/intel-speed-select/isst.h12
-rwxr-xr-xtools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py1
-rw-r--r--tools/power/x86/turbostat/Makefile2
-rw-r--r--tools/power/x86/turbostat/turbostat.c142
-rw-r--r--tools/scripts/Makefile.include5
-rw-r--r--tools/spi/Makefile2
-rw-r--r--tools/spi/spidev_test.c14
-rwxr-xr-xtools/testing/ktest/ktest.pl16
-rw-r--r--tools/testing/ktest/sample.conf22
-rwxr-xr-xtools/testing/kunit/kunit.py12
-rw-r--r--tools/testing/kunit/kunit_kernel.py28
-rw-r--r--tools/testing/selftests/.gitignore5
-rw-r--r--tools/testing/selftests/Makefile14
-rw-r--r--tools/testing/selftests/bpf/.gitignore1
-rw-r--r--tools/testing/selftests/bpf/Makefile33
-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/config2
-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/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/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_test.c69
-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_init.c61
-rw-r--r--tools/testing/selftests/bpf/prog_tests/link_pinning.c105
-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.c88
-rw-r--r--tools/testing/selftests/bpf/prog_tests/perf_branches.c170
-rw-r--r--tools/testing/selftests/bpf/prog_tests/select_reuseport.c75
-rw-r--r--tools/testing/selftests/bpf/prog_tests/send_signal_sched_switch.c60
-rw-r--r--tools/testing/selftests/bpf/prog_tests/sk_assign.c309
-rw-r--r--tools/testing/selftests/bpf/prog_tests/skb_ctx.c1
-rw-r--r--tools/testing/selftests/bpf/prog_tests/sockmap_basic.c5
-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/tcp_rtt.c32
-rw-r--r--tools/testing/selftests/bpf/prog_tests/test_lsm.c86
-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_attach.c62
-rw-r--r--tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c69
-rw-r--r--tools/testing/selftests/bpf/progs/bpf_dctcp.c18
-rw-r--r--tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c2
-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/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/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_cgroup_link.c24
-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_ns_current_pid_tgid.c37
-rw-r--r--tools/testing/selftests/bpf/progs/test_overhead.c7
-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_send_signal_kern.c6
-rw-r--r--tools/testing/selftests/bpf/progs/test_sk_assign.c204
-rw-r--r--tools/testing/selftests/bpf/progs/test_skb_ctx.c2
-rw-r--r--tools/testing/selftests/bpf/progs/test_sockmap_listen.c98
-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_bpf2bpf.c30
-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.c42
-rw-r--r--tools/testing/selftests/bpf/test_current_pid_tgid_new_ns.c159
-rw-r--r--tools/testing/selftests/bpf/test_maps.c6
-rw-r--r--tools/testing/selftests/bpf/test_progs.c102
-rw-r--r--tools/testing/selftests/bpf/test_progs.h9
-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/bounds.c57
-rw-r--r--tools/testing/selftests/bpf/verifier/bpf_get_stack.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/jmp32.c15
-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_l2_drops.sh28
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh55
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/devlink_trap_policer.sh384
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan.sh4
-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
-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
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/tc_flower_restrictions.sh186
-rw-r--r--tools/testing/selftests/drivers/net/mlxsw/tc_flower_scale.sh31
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/vxlan.sh229
-rwxr-xr-xtools/testing/selftests/drivers/net/netdevsim/devlink.sh15
-rwxr-xr-xtools/testing/selftests/drivers/net/netdevsim/devlink_trap.sh121
-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/Makefile2
-rw-r--r--tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc8
-rw-r--r--tools/testing/selftests/futex/functional/Makefile2
-rw-r--r--tools/testing/selftests/kvm/Makefile3
-rw-r--r--tools/testing/selftests/kvm/include/x86_64/processor.h44
-rw-r--r--tools/testing/selftests/kvm/include/x86_64/svm.h297
-rw-r--r--tools/testing/selftests/kvm/include/x86_64/svm_util.h38
-rw-r--r--tools/testing/selftests/kvm/lib/x86_64/svm.c161
-rw-r--r--tools/testing/selftests/kvm/lib/x86_64/vmx.c6
-rw-r--r--tools/testing/selftests/kvm/x86_64/svm_vmcall_test.c79
-rw-r--r--tools/testing/selftests/lib.mk23
-rw-r--r--tools/testing/selftests/livepatch/Makefile2
-rw-r--r--tools/testing/selftests/lkdtm/.gitignore2
-rw-r--r--tools/testing/selftests/net/.gitignore5
-rw-r--r--tools/testing/selftests/net/Makefile12
-rw-r--r--tools/testing/selftests/net/config2
-rwxr-xr-xtools/testing/selftests/net/fib_tests.sh40
-rw-r--r--tools/testing/selftests/net/forwarding/Makefile76
-rw-r--r--tools/testing/selftests/net/forwarding/devlink_lib.sh72
-rw-r--r--[-rwxr-xr-x]tools/testing/selftests/net/forwarding/ethtool_lib.sh0
-rw-r--r--tools/testing/selftests/net/forwarding/lib.sh88
-rwxr-xr-xtools/testing/selftests/net/forwarding/mirror_gre.sh25
-rwxr-xr-xtools/testing/selftests/net/forwarding/pedit_dsfield.sh238
-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
-rw-r--r--tools/testing/selftests/net/forwarding/tc_common.sh32
-rwxr-xr-xtools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh6
-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/mptcp/.gitignore1
-rw-r--r--tools/testing/selftests/net/mptcp/Makefile9
-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
-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/reuseport_addr_any.c4
-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/timestamping.c (renamed from tools/testing/selftests/networking/timestamping/timestamping.c)0
-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
-rw-r--r--tools/testing/selftests/netfilter/Makefile6
-rw-r--r--tools/testing/selftests/netfilter/config6
-rw-r--r--tools/testing/selftests/netfilter/nf-queue.c352
-rwxr-xr-xtools/testing/selftests/netfilter/nft_concat_range.sh55
-rwxr-xr-xtools/testing/selftests/netfilter/nft_queue.sh332
-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/openat2/helpers.c2
-rw-r--r--tools/testing/selftests/openat2/resolve_test.c2
-rw-r--r--tools/testing/selftests/pidfd/.gitignore1
-rw-r--r--tools/testing/selftests/rcutorture/bin/functions.sh2
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm-find-errors.sh2
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm-recheck.sh17
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm.sh2
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/CFcommon2
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/TREE1018
-rw-r--r--tools/testing/selftests/rseq/Makefile4
-rw-r--r--tools/testing/selftests/rtc/Makefile4
-rw-r--r--tools/testing/selftests/seccomp/seccomp_bpf.c74
-rw-r--r--tools/testing/selftests/tc-testing/config7
-rw-r--r--tools/testing/selftests/tc-testing/tc-tests/filters/basic.json902
-rw-r--r--tools/testing/selftests/tc-testing/tc-tests/qdiscs/red.json185
-rw-r--r--tools/testing/selftests/timens/Makefile2
-rwxr-xr-xtools/testing/selftests/tpm2/test_smoke.sh13
-rwxr-xr-xtools/testing/selftests/tpm2/test_space.sh9
-rwxr-xr-xtools/testing/selftests/vm/run_vmtests33
-rwxr-xr-xtools/testing/selftests/wireguard/netns.sh26
-rw-r--r--tools/testing/selftests/wireguard/qemu/Makefile40
-rw-r--r--tools/testing/selftests/wireguard/qemu/init.c1
-rw-r--r--tools/testing/selftests/wireguard/qemu/kernel.config1
-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
-rw-r--r--tools/testing/vsock/vsock_test.c77
402 files changed, 20945 insertions, 3671 deletions
diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h
index 820e5751ada7..ba85bb23f060 100644
--- a/tools/arch/arm64/include/uapi/asm/kvm.h
+++ b/tools/arch/arm64/include/uapi/asm/kvm.h
@@ -220,10 +220,18 @@ struct kvm_vcpu_events {
#define KVM_REG_ARM_PTIMER_CVAL ARM64_SYS_REG(3, 3, 14, 2, 2)
#define KVM_REG_ARM_PTIMER_CNT ARM64_SYS_REG(3, 3, 14, 0, 1)
-/* EL0 Virtual Timer Registers */
+/*
+ * EL0 Virtual Timer Registers
+ *
+ * WARNING:
+ * KVM_REG_ARM_TIMER_CVAL and KVM_REG_ARM_TIMER_CNT are not defined
+ * with the appropriate register encodings. Their values have been
+ * accidentally swapped. As this is set API, the definitions here
+ * must be used, rather than ones derived from the encodings.
+ */
#define KVM_REG_ARM_TIMER_CTL ARM64_SYS_REG(3, 3, 14, 3, 1)
-#define KVM_REG_ARM_TIMER_CNT ARM64_SYS_REG(3, 3, 14, 3, 2)
#define KVM_REG_ARM_TIMER_CVAL ARM64_SYS_REG(3, 3, 14, 0, 2)
+#define KVM_REG_ARM_TIMER_CNT ARM64_SYS_REG(3, 3, 14, 3, 2)
/* KVM-as-firmware specific pseudo-registers */
#define KVM_REG_ARM_FW (0x0014 << KVM_REG_ARM_COPROC_SHIFT)
diff --git a/tools/arch/arm64/include/uapi/asm/unistd.h b/tools/arch/arm64/include/uapi/asm/unistd.h
index 4703d218663a..f83a70e07df8 100644
--- a/tools/arch/arm64/include/uapi/asm/unistd.h
+++ b/tools/arch/arm64/include/uapi/asm/unistd.h
@@ -19,5 +19,6 @@
#define __ARCH_WANT_NEW_STAT
#define __ARCH_WANT_SET_GET_RLIMIT
#define __ARCH_WANT_TIME32_SYSCALLS
+#define __ARCH_WANT_SYS_CLONE3
#include <asm-generic/unistd.h>
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index e9b62498fe75..f3327cb56edf 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -220,6 +220,7 @@
#define X86_FEATURE_ZEN ( 7*32+28) /* "" CPU is AMD family 0x17 (Zen) */
#define X86_FEATURE_L1TF_PTEINV ( 7*32+29) /* "" L1TF workaround PTE inversion */
#define X86_FEATURE_IBRS_ENHANCED ( 7*32+30) /* Enhanced IBRS */
+#define X86_FEATURE_MSR_IA32_FEAT_CTL ( 7*32+31) /* "" MSR IA32_FEAT_CTL configured */
/* Virtualization flags: Linux defined, word 8 */
#define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */
@@ -357,6 +358,7 @@
/* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */
#define X86_FEATURE_AVX512_4VNNIW (18*32+ 2) /* AVX-512 Neural Network Instructions */
#define X86_FEATURE_AVX512_4FMAPS (18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */
+#define X86_FEATURE_FSRM (18*32+ 4) /* Fast Short Rep Mov */
#define X86_FEATURE_AVX512_VP2INTERSECT (18*32+ 8) /* AVX-512 Intersect for D/Q */
#define X86_FEATURE_MD_CLEAR (18*32+10) /* VERW clears CPU buffers */
#define X86_FEATURE_TSX_FORCE_ABORT (18*32+13) /* "" TSX_FORCE_ABORT */
diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h
index 8e1d0bb46361..4ea8584682f9 100644
--- a/tools/arch/x86/include/asm/disabled-features.h
+++ b/tools/arch/x86/include/asm/disabled-features.h
@@ -10,12 +10,6 @@
* cpu_feature_enabled().
*/
-#ifdef CONFIG_X86_INTEL_MPX
-# define DISABLE_MPX 0
-#else
-# define DISABLE_MPX (1<<(X86_FEATURE_MPX & 31))
-#endif
-
#ifdef CONFIG_X86_SMAP
# define DISABLE_SMAP 0
#else
@@ -74,7 +68,7 @@
#define DISABLED_MASK6 0
#define DISABLED_MASK7 (DISABLE_PTI)
#define DISABLED_MASK8 0
-#define DISABLED_MASK9 (DISABLE_MPX|DISABLE_SMAP)
+#define DISABLED_MASK9 (DISABLE_SMAP)
#define DISABLED_MASK10 0
#define DISABLED_MASK11 0
#define DISABLED_MASK12 0
diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index ebe1685e92dd..d5e517d1c3dd 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -512,6 +512,8 @@
#define MSR_K7_HWCR 0xc0010015
#define MSR_K7_HWCR_SMMLOCK_BIT 0
#define MSR_K7_HWCR_SMMLOCK BIT_ULL(MSR_K7_HWCR_SMMLOCK_BIT)
+#define MSR_K7_HWCR_IRPERF_EN_BIT 30
+#define MSR_K7_HWCR_IRPERF_EN BIT_ULL(MSR_K7_HWCR_IRPERF_EN_BIT)
#define MSR_K7_FID_VID_CTL 0xc0010041
#define MSR_K7_FID_VID_STATUS 0xc0010042
diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index 503d3f42da16..3f3f780c8c65 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -390,6 +390,7 @@ struct kvm_sync_regs {
#define KVM_STATE_NESTED_GUEST_MODE 0x00000001
#define KVM_STATE_NESTED_RUN_PENDING 0x00000002
#define KVM_STATE_NESTED_EVMCS 0x00000004
+#define KVM_STATE_NESTED_MTF_PENDING 0x00000008
#define KVM_STATE_NESTED_SMM_GUEST_MODE 0x00000001
#define KVM_STATE_NESTED_SMM_VMXON 0x00000002
diff --git a/tools/arch/x86/lib/x86-opcode-map.txt b/tools/arch/x86/lib/x86-opcode-map.txt
index 53adc1762ec0..ec31f5b60323 100644
--- a/tools/arch/x86/lib/x86-opcode-map.txt
+++ b/tools/arch/x86/lib/x86-opcode-map.txt
@@ -366,7 +366,7 @@ AVXcode: 1
1b: BNDCN Gv,Ev (F2) | BNDMOV Ev,Gv (66) | BNDMK Gv,Ev (F3) | BNDSTX Ev,Gv
1c: Grp20 (1A),(1C)
1d:
-1e:
+1e: Grp21 (1A)
1f: NOP Ev
# 0x0f 0x20-0x2f
20: MOV Rd,Cd
@@ -803,8 +803,8 @@ f0: MOVBE Gy,My | MOVBE Gw,Mw (66) | CRC32 Gd,Eb (F2) | CRC32 Gd,Eb (66&F2)
f1: MOVBE My,Gy | MOVBE Mw,Gw (66) | CRC32 Gd,Ey (F2) | CRC32 Gd,Ew (66&F2)
f2: ANDN Gy,By,Ey (v)
f3: Grp17 (1A)
-f5: BZHI Gy,Ey,By (v) | PEXT Gy,By,Ey (F3),(v) | PDEP Gy,By,Ey (F2),(v)
-f6: ADCX Gy,Ey (66) | ADOX Gy,Ey (F3) | MULX By,Gy,rDX,Ey (F2),(v)
+f5: BZHI Gy,Ey,By (v) | PEXT Gy,By,Ey (F3),(v) | PDEP Gy,By,Ey (F2),(v) | WRUSSD/Q My,Gy (66)
+f6: ADCX Gy,Ey (66) | ADOX Gy,Ey (F3) | MULX By,Gy,rDX,Ey (F2),(v) | WRSSD/Q My,Gy
f7: BEXTR Gy,Ey,By (v) | SHLX Gy,Ey,By (66),(v) | SARX Gy,Ey,By (F3),(v) | SHRX Gy,Ey,By (F2),(v)
f8: MOVDIR64B Gv,Mdqq (66) | ENQCMD Gv,Mdqq (F2) | ENQCMDS Gv,Mdqq (F3)
f9: MOVDIRI My,Gy
@@ -970,7 +970,7 @@ GrpTable: Grp7
2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B) | VMFUNC (100),(11B) | XEND (101)(11B) | XTEST (110)(11B) | ENCLU (111),(11B)
3: LIDT Ms
4: SMSW Mw/Rv
-5: rdpkru (110),(11B) | wrpkru (111),(11B)
+5: rdpkru (110),(11B) | wrpkru (111),(11B) | SAVEPREVSSP (F3),(010),(11B) | RSTORSSP Mq (F3) | SETSSBSY (F3),(000),(11B)
6: LMSW Ew
7: INVLPG Mb | SWAPGS (o64),(000),(11B) | RDTSCP (001),(11B)
EndTable
@@ -1041,8 +1041,8 @@ GrpTable: Grp15
2: vldmxcsr Md (v1) | WRFSBASE Ry (F3),(11B)
3: vstmxcsr Md (v1) | WRGSBASE Ry (F3),(11B)
4: XSAVE | ptwrite Ey (F3),(11B)
-5: XRSTOR | lfence (11B)
-6: XSAVEOPT | clwb (66) | mfence (11B) | TPAUSE Rd (66),(11B) | UMONITOR Rv (F3),(11B) | UMWAIT Rd (F2),(11B)
+5: XRSTOR | lfence (11B) | INCSSPD/Q Ry (F3),(11B)
+6: XSAVEOPT | clwb (66) | mfence (11B) | TPAUSE Rd (66),(11B) | UMONITOR Rv (F3),(11B) | UMWAIT Rd (F2),(11B) | CLRSSBSY Mq (F3)
7: clflush | clflushopt (66) | sfence (11B)
EndTable
@@ -1077,6 +1077,11 @@ GrpTable: Grp20
0: cldemote Mb
EndTable
+GrpTable: Grp21
+1: RDSSPD/Q Ry (F3),(11B)
+7: ENDBR64 (F3),(010),(11B) | ENDBR32 (F3),(011),(11B)
+EndTable
+
# AMD's Prefetch Group
GrpTable: GrpP
0: PREFETCH
diff --git a/tools/bootconfig/include/linux/memblock.h b/tools/bootconfig/include/linux/memblock.h
new file mode 100644
index 000000000000..7862f217d85d
--- /dev/null
+++ b/tools/bootconfig/include/linux/memblock.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _XBC_LINUX_MEMBLOCK_H
+#define _XBC_LINUX_MEMBLOCK_H
+
+#include <stdlib.h>
+
+#define __pa(addr) (addr)
+#define SMP_CACHE_BYTES 0
+#define memblock_alloc(size, align) malloc(size)
+#define memblock_free(paddr, size) free(paddr)
+
+#endif
diff --git a/tools/bootconfig/include/linux/printk.h b/tools/bootconfig/include/linux/printk.h
index 017bcd6912a5..036e667596eb 100644
--- a/tools/bootconfig/include/linux/printk.h
+++ b/tools/bootconfig/include/linux/printk.h
@@ -4,10 +4,7 @@
#include <stdio.h>
-/* controllable printf */
-extern int pr_output;
-#define printk(fmt, ...) \
- (pr_output ? printf(fmt, __VA_ARGS__) : 0)
+#define printk(fmt, ...) printf(fmt, ##__VA_ARGS__)
#define pr_err printk
#define pr_warn printk
diff --git a/tools/bootconfig/main.c b/tools/bootconfig/main.c
index 47f488458328..a9b97814d1a9 100644
--- a/tools/bootconfig/main.c
+++ b/tools/bootconfig/main.c
@@ -14,8 +14,6 @@
#include <linux/kernel.h>
#include <linux/bootconfig.h>
-int pr_output = 1;
-
static int xbc_show_array(struct xbc_node *node)
{
const char *val;
@@ -131,16 +129,27 @@ int load_xbc_from_initrd(int fd, char **buf)
struct stat stat;
int ret;
u32 size = 0, csum = 0, rcsum;
+ char magic[BOOTCONFIG_MAGIC_LEN];
ret = fstat(fd, &stat);
if (ret < 0)
return -errno;
- if (stat.st_size < 8)
+ if (stat.st_size < 8 + BOOTCONFIG_MAGIC_LEN)
return 0;
- if (lseek(fd, -8, SEEK_END) < 0) {
- printf("Failed to lseek: %d\n", -errno);
+ if (lseek(fd, -BOOTCONFIG_MAGIC_LEN, SEEK_END) < 0) {
+ pr_err("Failed to lseek: %d\n", -errno);
+ return -errno;
+ }
+ if (read(fd, magic, BOOTCONFIG_MAGIC_LEN) < 0)
+ return -errno;
+ /* Check the bootconfig magic bytes */
+ if (memcmp(magic, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN) != 0)
+ return 0;
+
+ if (lseek(fd, -(8 + BOOTCONFIG_MAGIC_LEN), SEEK_END) < 0) {
+ pr_err("Failed to lseek: %d\n", -errno);
return -errno;
}
@@ -150,12 +159,15 @@ int load_xbc_from_initrd(int fd, char **buf)
if (read(fd, &csum, sizeof(u32)) < 0)
return -errno;
- /* Wrong size, maybe no boot config here */
- if (stat.st_size < size + 8)
- return 0;
+ /* Wrong size error */
+ if (stat.st_size < size + 8 + BOOTCONFIG_MAGIC_LEN) {
+ pr_err("bootconfig size is too big\n");
+ return -E2BIG;
+ }
- if (lseek(fd, stat.st_size - 8 - size, SEEK_SET) < 0) {
- printf("Failed to lseek: %d\n", -errno);
+ if (lseek(fd, stat.st_size - (size + 8 + BOOTCONFIG_MAGIC_LEN),
+ SEEK_SET) < 0) {
+ pr_err("Failed to lseek: %d\n", -errno);
return -errno;
}
@@ -163,17 +175,17 @@ int load_xbc_from_initrd(int fd, char **buf)
if (ret < 0)
return ret;
- /* Wrong Checksum, maybe no boot config here */
+ /* Wrong Checksum */
rcsum = checksum((unsigned char *)*buf, size);
if (csum != rcsum) {
- printf("checksum error: %d != %d\n", csum, rcsum);
- return 0;
+ pr_err("checksum error: %d != %d\n", csum, rcsum);
+ return -EINVAL;
}
ret = xbc_init(*buf);
- /* Wrong data, maybe no boot config here */
+ /* Wrong data */
if (ret < 0)
- return 0;
+ return ret;
return size;
}
@@ -185,13 +197,13 @@ int show_xbc(const char *path)
fd = open(path, O_RDONLY);
if (fd < 0) {
- printf("Failed to open initrd %s: %d\n", path, fd);
+ pr_err("Failed to open initrd %s: %d\n", path, fd);
return -errno;
}
ret = load_xbc_from_initrd(fd, &buf);
if (ret < 0)
- printf("Failed to load a boot config from initrd: %d\n", ret);
+ pr_err("Failed to load a boot config from initrd: %d\n", ret);
else
xbc_show_compact_tree();
@@ -209,24 +221,19 @@ int delete_xbc(const char *path)
fd = open(path, O_RDWR);
if (fd < 0) {
- printf("Failed to open initrd %s: %d\n", path, fd);
+ pr_err("Failed to open initrd %s: %d\n", path, fd);
return -errno;
}
- /*
- * Suppress error messages in xbc_init() because it can be just a
- * data which concidentally matches the size and checksum footer.
- */
- pr_output = 0;
size = load_xbc_from_initrd(fd, &buf);
- pr_output = 1;
if (size < 0) {
ret = size;
- printf("Failed to load a boot config from initrd: %d\n", ret);
+ pr_err("Failed to load a boot config from initrd: %d\n", ret);
} else if (size > 0) {
ret = fstat(fd, &stat);
if (!ret)
- ret = ftruncate(fd, stat.st_size - size - 8);
+ ret = ftruncate(fd, stat.st_size
+ - size - 8 - BOOTCONFIG_MAGIC_LEN);
if (ret)
ret = -errno;
} /* Ignore if there is no boot config in initrd */
@@ -245,7 +252,7 @@ int apply_xbc(const char *path, const char *xbc_path)
ret = load_xbc_file(xbc_path, &buf);
if (ret < 0) {
- printf("Failed to load %s : %d\n", xbc_path, ret);
+ pr_err("Failed to load %s : %d\n", xbc_path, ret);
return ret;
}
size = strlen(buf) + 1;
@@ -262,7 +269,7 @@ int apply_xbc(const char *path, const char *xbc_path)
/* Check the data format */
ret = xbc_init(buf);
if (ret < 0) {
- printf("Failed to parse %s: %d\n", xbc_path, ret);
+ pr_err("Failed to parse %s: %d\n", xbc_path, ret);
free(data);
free(buf);
return ret;
@@ -279,20 +286,26 @@ int apply_xbc(const char *path, const char *xbc_path)
/* Remove old boot config if exists */
ret = delete_xbc(path);
if (ret < 0) {
- printf("Failed to delete previous boot config: %d\n", ret);
+ pr_err("Failed to delete previous boot config: %d\n", ret);
return ret;
}
/* Apply new one */
fd = open(path, O_RDWR | O_APPEND);
if (fd < 0) {
- printf("Failed to open %s: %d\n", path, fd);
+ pr_err("Failed to open %s: %d\n", path, fd);
return fd;
}
/* TODO: Ensure the @path is initramfs/initrd image */
ret = write(fd, data, size + 8);
if (ret < 0) {
- printf("Failed to apply a boot config: %d\n", ret);
+ pr_err("Failed to apply a boot config: %d\n", ret);
+ return ret;
+ }
+ /* Write a magic word of the bootconfig */
+ ret = write(fd, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN);
+ if (ret < 0) {
+ pr_err("Failed to apply a boot config magic: %d\n", ret);
return ret;
}
close(fd);
@@ -334,12 +347,12 @@ int main(int argc, char **argv)
}
if (apply && delete) {
- printf("Error: You can not specify both -a and -d at once.\n");
+ pr_err("Error: You can not specify both -a and -d at once.\n");
return usage();
}
if (optind >= argc) {
- printf("Error: No initrd is specified.\n");
+ pr_err("Error: No initrd is specified.\n");
return usage();
}
diff --git a/tools/bootconfig/samples/bad-mixed-kv1.bconf b/tools/bootconfig/samples/bad-mixed-kv1.bconf
new file mode 100644
index 000000000000..1761547dd05c
--- /dev/null
+++ b/tools/bootconfig/samples/bad-mixed-kv1.bconf
@@ -0,0 +1,3 @@
+# value -> subkey pattern
+key = value
+key.subkey = another-value
diff --git a/tools/bootconfig/samples/bad-mixed-kv2.bconf b/tools/bootconfig/samples/bad-mixed-kv2.bconf
new file mode 100644
index 000000000000..6b32e0c3878c
--- /dev/null
+++ b/tools/bootconfig/samples/bad-mixed-kv2.bconf
@@ -0,0 +1,3 @@
+# subkey -> value pattern
+key.subkey = value
+key = another-value
diff --git a/tools/bootconfig/samples/bad-samekey.bconf b/tools/bootconfig/samples/bad-samekey.bconf
new file mode 100644
index 000000000000..e8d983a4563c
--- /dev/null
+++ b/tools/bootconfig/samples/bad-samekey.bconf
@@ -0,0 +1,6 @@
+# Same key value is not allowed
+key {
+ foo = value
+ bar = value2
+}
+key.foo = value
diff --git a/tools/bootconfig/test-bootconfig.sh b/tools/bootconfig/test-bootconfig.sh
index 87725e8723f8..1411f4c3454f 100755
--- a/tools/bootconfig/test-bootconfig.sh
+++ b/tools/bootconfig/test-bootconfig.sh
@@ -9,7 +9,7 @@ TEMPCONF=`mktemp temp-XXXX.bconf`
NG=0
cleanup() {
- rm -f $INITRD $TEMPCONF
+ rm -f $INITRD $TEMPCONF $OUTFILE
exit $NG
}
@@ -49,7 +49,7 @@ xpass $BOOTCONF -a $TEMPCONF $INITRD
new_size=$(stat -c %s $INITRD)
echo "File size check"
-xpass test $new_size -eq $(expr $bconf_size + $initrd_size + 9)
+xpass test $new_size -eq $(expr $bconf_size + $initrd_size + 9 + 12)
echo "Apply command repeat test"
xpass $BOOTCONF -a $TEMPCONF $INITRD
@@ -64,6 +64,14 @@ echo "File size check"
new_size=$(stat -c %s $INITRD)
xpass test $new_size -eq $initrd_size
+echo "No error messge while applying"
+OUTFILE=`mktemp tempout-XXXX`
+dd if=/dev/zero of=$INITRD bs=4096 count=1
+printf " \0\0\0 \0\0\0" >> $INITRD
+$BOOTCONF -a $TEMPCONF $INITRD > $OUTFILE 2>&1
+xfail grep -i "failed" $OUTFILE
+xfail grep -i "error" $OUTFILE
+
echo "Max node number check"
echo -n > $TEMPCONF
@@ -87,6 +95,19 @@ truncate -s 32764 $TEMPCONF
echo "\"" >> $TEMPCONF # add 2 bytes + terminal ('\"\n\0')
xpass $BOOTCONF -a $TEMPCONF $INITRD
+echo "Adding same-key values"
+cat > $TEMPCONF << EOF
+key = bar, baz
+key += qux
+EOF
+echo > $INITRD
+
+xpass $BOOTCONF -a $TEMPCONF $INITRD
+$BOOTCONF $INITRD > $OUTFILE
+xpass grep -q "bar" $OUTFILE
+xpass grep -q "baz" $OUTFILE
+xpass grep -q "qux" $OUTFILE
+
echo "=== expected failure cases ==="
for i in samples/bad-* ; do
xfail $BOOTCONF -a $i $INITRD
diff --git a/tools/bpf/bpftool/.gitignore b/tools/bpf/bpftool/.gitignore
index b13926432b84..8d6e8901ed2b 100644
--- a/tools/bpf/bpftool/.gitignore
+++ b/tools/bpf/bpftool/.gitignore
@@ -1,7 +1,9 @@
*.d
+/_bpftool
/bpftool
bpftool*.8
bpf-helpers.*
FEATURE-DUMP.bpftool
feature
libbpf
+profiler.skel.h
diff --git a/tools/bpf/bpftool/Documentation/bpftool-feature.rst b/tools/bpf/bpftool/Documentation/bpftool-feature.rst
index 4d08f35034a2..b04156cfd7a3 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-feature.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-feature.rst
@@ -19,19 +19,24 @@ SYNOPSIS
FEATURE COMMANDS
================
-| **bpftool** **feature probe** [*COMPONENT*] [**macros** [**prefix** *PREFIX*]]
+| **bpftool** **feature probe** [*COMPONENT*] [**full**] [**macros** [**prefix** *PREFIX*]]
| **bpftool** **feature help**
|
| *COMPONENT* := { **kernel** | **dev** *NAME* }
DESCRIPTION
===========
- **bpftool feature probe** [**kernel**] [**macros** [**prefix** *PREFIX*]]
+ **bpftool feature probe** [**kernel**] [**full**] [**macros** [**prefix** *PREFIX*]]
Probe the running kernel and dump a number of eBPF-related
parameters, such as availability of the **bpf()** system call,
JIT status, eBPF program types availability, eBPF helper
functions availability, and more.
+ By default, bpftool **does not run probes** for
+ **bpf_probe_write_user**\ () and **bpf_trace_printk**\()
+ helpers which print warnings to kernel logs. To enable them
+ and run all probes, the **full** keyword should be used.
+
If the **macros** keyword (but not the **-j** option) is
passed, a subset of the output is dumped as a list of
**#define** macros that are ready to be included in a C
@@ -44,16 +49,12 @@ DESCRIPTION
Keyword **kernel** can be omitted. If no probe target is
specified, probing the kernel is the default behaviour.
- Note that when probed, some eBPF helpers (e.g.
- **bpf_trace_printk**\ () or **bpf_probe_write_user**\ ()) may
- print warnings to kernel logs.
-
- **bpftool feature probe dev** *NAME* [**macros** [**prefix** *PREFIX*]]
+ **bpftool feature probe dev** *NAME* [**full**] [**macros** [**prefix** *PREFIX*]]
Probe network device for supported eBPF features and dump
results to the console.
- The two keywords **macros** and **prefix** have the same
- role as when probing the kernel.
+ The keywords **full**, **macros** and **prefix** have the
+ same role as when probing the kernel.
**bpftool feature help**
Print short help message.
diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
index 64ddf8a4c518..9f19404f470e 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
@@ -30,6 +30,7 @@ PROG COMMANDS
| **bpftool** **prog detach** *PROG* *ATTACH_TYPE* [*MAP*]
| **bpftool** **prog tracelog**
| **bpftool** **prog run** *PROG* **data_in** *FILE* [**data_out** *FILE* [**data_size_out** *L*]] [**ctx_in** *FILE* [**ctx_out** *FILE* [**ctx_size_out** *M*]]] [**repeat** *N*]
+| **bpftool** **prog profile** *PROG* [**duration** *DURATION*] *METRICs*
| **bpftool** **prog help**
|
| *MAP* := { **id** *MAP_ID* | **pinned** *FILE* }
@@ -42,11 +43,15 @@ PROG COMMANDS
| **cgroup/bind4** | **cgroup/bind6** | **cgroup/post_bind4** | **cgroup/post_bind6** |
| **cgroup/connect4** | **cgroup/connect6** | **cgroup/sendmsg4** | **cgroup/sendmsg6** |
| **cgroup/recvmsg4** | **cgroup/recvmsg6** | **cgroup/sysctl** |
-| **cgroup/getsockopt** | **cgroup/setsockopt**
+| **cgroup/getsockopt** | **cgroup/setsockopt** |
+| **struct_ops** | **fentry** | **fexit** | **freplace**
| }
| *ATTACH_TYPE* := {
| **msg_verdict** | **stream_verdict** | **stream_parser** | **flow_dissector**
| }
+| *METRIC* := {
+| **cycles** | **instructions** | **l1d_loads** | **llc_misses**
+| }
DESCRIPTION
@@ -188,6 +193,12 @@ DESCRIPTION
not all of them can take the **ctx_in**/**ctx_out**
arguments. bpftool does not perform checks on program types.
+ **bpftool prog profile** *PROG* [**duration** *DURATION*] *METRICs*
+ Profile *METRICs* for bpf program *PROG* for *DURATION*
+ seconds or until user hits Ctrl-C. *DURATION* is optional.
+ If *DURATION* is not specified, the profiling will run up to
+ UINT_MAX seconds.
+
**bpftool prog help**
Print short help message.
@@ -310,6 +321,15 @@ EXAMPLES
**# rm /sys/fs/bpf/xdp1**
+|
+| **# bpftool prog profile id 337 duration 10 cycles instructions llc_misses**
+
+::
+ 51397 run_cnt
+ 40176203 cycles (83.05%)
+ 42518139 instructions # 1.06 insns per cycle (83.39%)
+ 123 llc_misses # 2.89 LLC misses per million insns (83.15%)
+
SEE ALSO
========
**bpf**\ (2),
diff --git a/tools/bpf/bpftool/Documentation/bpftool-struct_ops.rst b/tools/bpf/bpftool/Documentation/bpftool-struct_ops.rst
new file mode 100644
index 000000000000..f045cc89dd6d
--- /dev/null
+++ b/tools/bpf/bpftool/Documentation/bpftool-struct_ops.rst
@@ -0,0 +1,116 @@
+==================
+bpftool-struct_ops
+==================
+-------------------------------------------------------------------------------
+tool to register/unregister/introspect BPF struct_ops
+-------------------------------------------------------------------------------
+
+:Manual section: 8
+
+SYNOPSIS
+========
+
+ **bpftool** [*OPTIONS*] **struct_ops** *COMMAND*
+
+ *OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] }
+
+ *COMMANDS* :=
+ { **show** | **list** | **dump** | **register** | **unregister** | **help** }
+
+STRUCT_OPS COMMANDS
+===================
+
+| **bpftool** **struct_ops { show | list }** [*STRUCT_OPS_MAP*]
+| **bpftool** **struct_ops dump** [*STRUCT_OPS_MAP*]
+| **bpftool** **struct_ops register** *OBJ*
+| **bpftool** **struct_ops unregister** *STRUCT_OPS_MAP*
+| **bpftool** **struct_ops help**
+|
+| *STRUCT_OPS_MAP* := { **id** *STRUCT_OPS_MAP_ID* | **name** *STRUCT_OPS_MAP_NAME* }
+| *OBJ* := /a/file/of/bpf_struct_ops.o
+
+
+DESCRIPTION
+===========
+ **bpftool struct_ops { show | list }** [*STRUCT_OPS_MAP*]
+ Show brief information about the struct_ops in the system.
+ If *STRUCT_OPS_MAP* is specified, it shows information only
+ for the given struct_ops. Otherwise, it lists all struct_ops
+ currently existing in the system.
+
+ Output will start with struct_ops map ID, followed by its map
+ name and its struct_ops's kernel type.
+
+ **bpftool struct_ops dump** [*STRUCT_OPS_MAP*]
+ Dump details information about the struct_ops in the system.
+ If *STRUCT_OPS_MAP* is specified, it dumps information only
+ for the given struct_ops. Otherwise, it dumps all struct_ops
+ currently existing in the system.
+
+ **bpftool struct_ops register** *OBJ*
+ Register bpf struct_ops from *OBJ*. All struct_ops under
+ the ELF section ".struct_ops" will be registered to
+ its kernel subsystem.
+
+ **bpftool struct_ops unregister** *STRUCT_OPS_MAP*
+ Unregister the *STRUCT_OPS_MAP* from the kernel subsystem.
+
+ **bpftool struct_ops help**
+ Print short help message.
+
+OPTIONS
+=======
+ -h, --help
+ Print short generic help message (similar to **bpftool help**).
+
+ -V, --version
+ Print version number (similar to **bpftool version**).
+
+ -j, --json
+ Generate JSON output. For commands that cannot produce JSON, this
+ option has no effect.
+
+ -p, --pretty
+ Generate human-readable JSON output. Implies **-j**.
+
+ -d, --debug
+ Print all logs available, even debug-level information. This
+ includes logs from libbpf as well as from the verifier, when
+ attempting to load programs.
+
+EXAMPLES
+========
+**# bpftool struct_ops show**
+
+::
+
+ 100: dctcp tcp_congestion_ops
+ 105: cubic tcp_congestion_ops
+
+**# bpftool struct_ops unregister id 105**
+
+::
+
+ Unregistered tcp_congestion_ops cubic id 105
+
+**# bpftool struct_ops register bpf_cubic.o**
+
+::
+
+ Registered tcp_congestion_ops cubic id 110
+
+
+SEE ALSO
+========
+ **bpf**\ (2),
+ **bpf-helpers**\ (7),
+ **bpftool**\ (8),
+ **bpftool-prog**\ (8),
+ **bpftool-map**\ (8),
+ **bpftool-cgroup**\ (8),
+ **bpftool-feature**\ (8),
+ **bpftool-net**\ (8),
+ **bpftool-perf**\ (8),
+ **bpftool-btf**\ (8)
+ **bpftool-gen**\ (8)
+
diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile
index c4e810335810..f584d1fdfc64 100644
--- a/tools/bpf/bpftool/Makefile
+++ b/tools/bpf/bpftool/Makefile
@@ -59,10 +59,12 @@ LIBS = $(LIBBPF) -lelf -lz
INSTALL ?= install
RM ?= rm -f
+CLANG ?= clang
FEATURE_USER = .bpftool
-FEATURE_TESTS = libbfd disassembler-four-args reallocarray zlib
-FEATURE_DISPLAY = libbfd disassembler-four-args zlib
+FEATURE_TESTS = libbfd disassembler-four-args reallocarray zlib \
+ clang-bpf-global-var
+FEATURE_DISPLAY = libbfd disassembler-four-args zlib clang-bpf-global-var
check_feat := 1
NON_CHECK_FEAT_TARGETS := clean uninstall doc doc-clean doc-install doc-uninstall
@@ -110,14 +112,39 @@ SRCS += $(BFD_SRCS)
endif
OBJS = $(patsubst %.c,$(OUTPUT)%.o,$(SRCS)) $(OUTPUT)disasm.o
+_OBJS = $(filter-out $(OUTPUT)prog.o,$(OBJS)) $(OUTPUT)_prog.o
+
+ifeq ($(feature-clang-bpf-global-var),1)
+ __OBJS = $(OBJS)
+else
+ __OBJS = $(_OBJS)
+endif
+
+$(OUTPUT)_prog.o: prog.c
+ $(QUIET_CC)$(COMPILE.c) -MMD -DBPFTOOL_WITHOUT_SKELETONS -o $@ $<
+
+$(OUTPUT)_bpftool: $(_OBJS) $(LIBBPF)
+ $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) -o $@ $(_OBJS) $(LIBS)
+
+skeleton/profiler.bpf.o: skeleton/profiler.bpf.c $(LIBBPF)
+ $(QUIET_CLANG)$(CLANG) \
+ -I$(srctree)/tools/include/uapi/ \
+ -I$(LIBBPF_PATH) -I$(srctree)/tools/lib \
+ -g -O2 -target bpf -c $< -o $@
+
+profiler.skel.h: $(OUTPUT)_bpftool skeleton/profiler.bpf.o
+ $(QUIET_GEN)$(OUTPUT)./_bpftool gen skeleton skeleton/profiler.bpf.o > $@
+
+$(OUTPUT)prog.o: prog.c profiler.skel.h
+ $(QUIET_CC)$(COMPILE.c) -MMD -o $@ $<
$(OUTPUT)disasm.o: $(srctree)/kernel/bpf/disasm.c
$(QUIET_CC)$(COMPILE.c) -MMD -o $@ $<
$(OUTPUT)feature.o: | zdep
-$(OUTPUT)bpftool: $(OBJS) $(LIBBPF)
- $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) -o $@ $(OBJS) $(LIBS)
+$(OUTPUT)bpftool: $(__OBJS) $(LIBBPF)
+ $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) -o $@ $(__OBJS) $(LIBS)
$(OUTPUT)%.o: %.c
$(QUIET_CC)$(COMPILE.c) -MMD -o $@ $<
@@ -125,6 +152,7 @@ $(OUTPUT)%.o: %.c
clean: $(LIBBPF)-clean
$(call QUIET_CLEAN, bpftool)
$(Q)$(RM) -- $(OUTPUT)bpftool $(OUTPUT)*.o $(OUTPUT)*.d
+ $(Q)$(RM) -- $(OUTPUT)_bpftool profiler.skel.h skeleton/profiler.bpf.o
$(Q)$(RM) -r -- $(OUTPUT)libbpf/
$(call QUIET_CLEAN, core-gen)
$(Q)$(RM) -- $(OUTPUT)FEATURE-DUMP.bpftool
diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool
index 754d8395e451..45ee99b159e2 100644
--- a/tools/bpf/bpftool/bash-completion/bpftool
+++ b/tools/bpf/bpftool/bash-completion/bpftool
@@ -337,6 +337,7 @@ _bpftool()
local PROG_TYPE='id pinned tag name'
local MAP_TYPE='id pinned name'
+ local METRIC_TYPE='cycles instructions l1d_loads llc_misses'
case $command in
show|list)
[[ $prev != "$command" ]] && return 0
@@ -388,7 +389,7 @@ _bpftool()
_bpftool_get_prog_ids
;;
name)
- _bpftool_get_map_names
+ _bpftool_get_prog_names
;;
pinned)
_filedir
@@ -469,7 +470,8 @@ _bpftool()
cgroup/recvmsg4 cgroup/recvmsg6 \
cgroup/post_bind4 cgroup/post_bind6 \
cgroup/sysctl cgroup/getsockopt \
- cgroup/setsockopt" -- \
+ cgroup/setsockopt struct_ops \
+ fentry fexit freplace" -- \
"$cur" ) )
return 0
;;
@@ -497,9 +499,51 @@ _bpftool()
tracelog)
return 0
;;
+ profile)
+ case $cword in
+ 3)
+ COMPREPLY=( $( compgen -W "$PROG_TYPE" -- "$cur" ) )
+ return 0
+ ;;
+ 4)
+ case $prev in
+ id)
+ _bpftool_get_prog_ids
+ ;;
+ name)
+ _bpftool_get_prog_names
+ ;;
+ pinned)
+ _filedir
+ ;;
+ esac
+ return 0
+ ;;
+ 5)
+ COMPREPLY=( $( compgen -W "$METRIC_TYPE duration" -- "$cur" ) )
+ return 0
+ ;;
+ 6)
+ case $prev in
+ duration)
+ return 0
+ ;;
+ *)
+ COMPREPLY=( $( compgen -W "$METRIC_TYPE" -- "$cur" ) )
+ return 0
+ ;;
+ esac
+ return 0
+ ;;
+ *)
+ COMPREPLY=( $( compgen -W "$METRIC_TYPE" -- "$cur" ) )
+ return 0
+ ;;
+ esac
+ ;;
run)
- if [[ ${#words[@]} -lt 5 ]]; then
- _filedir
+ if [[ ${#words[@]} -eq 4 ]]; then
+ COMPREPLY=( $( compgen -W "$PROG_TYPE" -- "$cur" ) )
return 0
fi
case $prev in
@@ -507,6 +551,10 @@ _bpftool()
_bpftool_get_prog_ids
return 0
;;
+ name)
+ _bpftool_get_prog_names
+ return 0
+ ;;
data_in|data_out|ctx_in|ctx_out)
_filedir
return 0
@@ -524,7 +572,35 @@ _bpftool()
*)
[[ $prev == $object ]] && \
COMPREPLY=( $( compgen -W 'dump help pin attach detach \
- load loadall show list tracelog run' -- "$cur" ) )
+ load loadall show list tracelog run profile' -- "$cur" ) )
+ ;;
+ esac
+ ;;
+ struct_ops)
+ local STRUCT_OPS_TYPE='id name'
+ case $command in
+ show|list|dump|unregister)
+ case $prev in
+ $command)
+ COMPREPLY=( $( compgen -W "$STRUCT_OPS_TYPE" -- "$cur" ) )
+ ;;
+ id)
+ _bpftool_get_map_ids_for_type struct_ops
+ ;;
+ name)
+ _bpftool_get_map_names_for_type struct_ops
+ ;;
+ esac
+ return 0
+ ;;
+ register)
+ _filedir
+ return 0
+ ;;
+ *)
+ [[ $prev == $object ]] && \
+ COMPREPLY=( $( compgen -W 'register unregister show list dump help' \
+ -- "$cur" ) )
;;
esac
;;
@@ -712,11 +788,17 @@ _bpftool()
esac
;;
pin)
- if [[ $prev == "$command" ]]; then
- COMPREPLY=( $( compgen -W "$PROG_TYPE" -- "$cur" ) )
- else
- _filedir
- fi
+ case $prev in
+ $command)
+ COMPREPLY=( $( compgen -W "$MAP_TYPE" -- "$cur" ) )
+ ;;
+ id)
+ _bpftool_get_map_ids
+ ;;
+ name)
+ _bpftool_get_map_names
+ ;;
+ esac
return 0
;;
event_pipe)
@@ -843,7 +925,7 @@ _bpftool()
case $command in
skeleton)
_filedir
- ;;
+ ;;
*)
[[ $prev == $object ]] && \
COMPREPLY=( $( compgen -W 'skeleton help' -- "$cur" ) )
@@ -943,6 +1025,9 @@ _bpftool()
id)
_bpftool_get_prog_ids
;;
+ name)
+ _bpftool_get_prog_names
+ ;;
pinned)
_filedir
;;
@@ -983,11 +1068,12 @@ _bpftool()
probe)
[[ $prev == "prefix" ]] && return 0
if _bpftool_search_list 'macros'; then
- COMPREPLY+=( $( compgen -W 'prefix' -- "$cur" ) )
+ _bpftool_once_attr 'prefix'
else
COMPREPLY+=( $( compgen -W 'macros' -- "$cur" ) )
fi
_bpftool_one_of_list 'kernel dev'
+ _bpftool_once_attr 'full'
return 0
;;
*)
diff --git a/tools/bpf/bpftool/btf.c b/tools/bpf/bpftool/btf.c
index b3745ed711ba..bcaf55b59498 100644
--- a/tools/bpf/bpftool/btf.c
+++ b/tools/bpf/bpftool/btf.c
@@ -389,6 +389,9 @@ static int dump_btf_c(const struct btf *btf,
if (IS_ERR(d))
return PTR_ERR(d);
+ printf("#ifndef __VMLINUX_H__\n");
+ printf("#define __VMLINUX_H__\n");
+ printf("\n");
printf("#ifndef BPF_NO_PRESERVE_ACCESS_INDEX\n");
printf("#pragma clang attribute push (__attribute__((preserve_access_index)), apply_to = record)\n");
printf("#endif\n\n");
@@ -412,6 +415,8 @@ static int dump_btf_c(const struct btf *btf,
printf("#ifndef BPF_NO_PRESERVE_ACCESS_INDEX\n");
printf("#pragma clang attribute pop\n");
printf("#endif\n");
+ printf("\n");
+ printf("#endif /* __VMLINUX_H__ */\n");
done:
btf_dump__free(d);
diff --git a/tools/bpf/bpftool/btf_dumper.c b/tools/bpf/bpftool/btf_dumper.c
index 01cc52b834fa..497807bec675 100644
--- a/tools/bpf/bpftool/btf_dumper.c
+++ b/tools/bpf/bpftool/btf_dumper.c
@@ -4,11 +4,13 @@
#include <ctype.h>
#include <stdio.h> /* for (FILE *) used by json_writer */
#include <string.h>
+#include <unistd.h>
#include <asm/byteorder.h>
#include <linux/bitops.h>
#include <linux/btf.h>
#include <linux/err.h>
#include <bpf/btf.h>
+#include <bpf/bpf.h>
#include "json_writer.h"
#include "main.h"
@@ -22,13 +24,102 @@
static int btf_dumper_do_type(const struct btf_dumper *d, __u32 type_id,
__u8 bit_offset, const void *data);
-static void btf_dumper_ptr(const void *data, json_writer_t *jw,
- bool is_plain_text)
+static int btf_dump_func(const struct btf *btf, char *func_sig,
+ const struct btf_type *func_proto,
+ const struct btf_type *func, int pos, int size);
+
+static int dump_prog_id_as_func_ptr(const struct btf_dumper *d,
+ const struct btf_type *func_proto,
+ __u32 prog_id)
{
- if (is_plain_text)
- jsonw_printf(jw, "%p", *(void **)data);
+ struct bpf_prog_info_linear *prog_info = NULL;
+ const struct btf_type *func_type;
+ const char *prog_name = NULL;
+ struct bpf_func_info *finfo;
+ struct btf *prog_btf = NULL;
+ struct bpf_prog_info *info;
+ int prog_fd, func_sig_len;
+ char prog_str[1024];
+
+ /* Get the ptr's func_proto */
+ func_sig_len = btf_dump_func(d->btf, prog_str, func_proto, NULL, 0,
+ sizeof(prog_str));
+ if (func_sig_len == -1)
+ return -1;
+
+ if (!prog_id)
+ goto print;
+
+ /* Get the bpf_prog's name. Obtain from func_info. */
+ prog_fd = bpf_prog_get_fd_by_id(prog_id);
+ if (prog_fd == -1)
+ goto print;
+
+ prog_info = bpf_program__get_prog_info_linear(prog_fd,
+ 1UL << BPF_PROG_INFO_FUNC_INFO);
+ close(prog_fd);
+ if (IS_ERR(prog_info)) {
+ prog_info = NULL;
+ goto print;
+ }
+ info = &prog_info->info;
+
+ if (!info->btf_id || !info->nr_func_info ||
+ btf__get_from_id(info->btf_id, &prog_btf))
+ goto print;
+ finfo = (struct bpf_func_info *)info->func_info;
+ func_type = btf__type_by_id(prog_btf, finfo->type_id);
+ if (!func_type || !btf_is_func(func_type))
+ goto print;
+
+ prog_name = btf__name_by_offset(prog_btf, func_type->name_off);
+
+print:
+ if (!prog_id)
+ snprintf(&prog_str[func_sig_len],
+ sizeof(prog_str) - func_sig_len, " 0");
+ else if (prog_name)
+ snprintf(&prog_str[func_sig_len],
+ sizeof(prog_str) - func_sig_len,
+ " %s/prog_id:%u", prog_name, prog_id);
else
- jsonw_printf(jw, "%lu", *(unsigned long *)data);
+ snprintf(&prog_str[func_sig_len],
+ sizeof(prog_str) - func_sig_len,
+ " <unknown_prog_name>/prog_id:%u", prog_id);
+
+ prog_str[sizeof(prog_str) - 1] = '\0';
+ jsonw_string(d->jw, prog_str);
+ btf__free(prog_btf);
+ free(prog_info);
+ return 0;
+}
+
+static void btf_dumper_ptr(const struct btf_dumper *d,
+ const struct btf_type *t,
+ const void *data)
+{
+ unsigned long value = *(unsigned long *)data;
+ const struct btf_type *ptr_type;
+ __s32 ptr_type_id;
+
+ if (!d->prog_id_as_func_ptr || value > UINT32_MAX)
+ goto print_ptr_value;
+
+ ptr_type_id = btf__resolve_type(d->btf, t->type);
+ if (ptr_type_id < 0)
+ goto print_ptr_value;
+ ptr_type = btf__type_by_id(d->btf, ptr_type_id);
+ if (!ptr_type || !btf_is_func_proto(ptr_type))
+ goto print_ptr_value;
+
+ if (!dump_prog_id_as_func_ptr(d, ptr_type, value))
+ return;
+
+print_ptr_value:
+ if (d->is_plain_text)
+ jsonw_printf(d->jw, "%p", (void *)value);
+ else
+ jsonw_printf(d->jw, "%lu", value);
}
static int btf_dumper_modifier(const struct btf_dumper *d, __u32 type_id,
@@ -43,9 +134,78 @@ static int btf_dumper_modifier(const struct btf_dumper *d, __u32 type_id,
return btf_dumper_do_type(d, actual_type_id, bit_offset, data);
}
-static void btf_dumper_enum(const void *data, json_writer_t *jw)
+static int btf_dumper_enum(const struct btf_dumper *d,
+ const struct btf_type *t,
+ const void *data)
+{
+ const struct btf_enum *enums = btf_enum(t);
+ __s64 value;
+ __u16 i;
+
+ switch (t->size) {
+ case 8:
+ value = *(__s64 *)data;
+ break;
+ case 4:
+ value = *(__s32 *)data;
+ break;
+ case 2:
+ value = *(__s16 *)data;
+ break;
+ case 1:
+ value = *(__s8 *)data;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ for (i = 0; i < btf_vlen(t); i++) {
+ if (value == enums[i].val) {
+ jsonw_string(d->jw,
+ btf__name_by_offset(d->btf,
+ enums[i].name_off));
+ return 0;
+ }
+ }
+
+ jsonw_int(d->jw, value);
+ return 0;
+}
+
+static bool is_str_array(const struct btf *btf, const struct btf_array *arr,
+ const char *s)
{
- jsonw_printf(jw, "%d", *(int *)data);
+ const struct btf_type *elem_type;
+ const char *end_s;
+
+ if (!arr->nelems)
+ return false;
+
+ elem_type = btf__type_by_id(btf, arr->type);
+ /* Not skipping typedef. typedef to char does not count as
+ * a string now.
+ */
+ while (elem_type && btf_is_mod(elem_type))
+ elem_type = btf__type_by_id(btf, elem_type->type);
+
+ if (!elem_type || !btf_is_int(elem_type) || elem_type->size != 1)
+ return false;
+
+ if (btf_int_encoding(elem_type) != BTF_INT_CHAR &&
+ strcmp("char", btf__name_by_offset(btf, elem_type->name_off)))
+ return false;
+
+ end_s = s + arr->nelems;
+ while (s < end_s) {
+ if (!*s)
+ return true;
+ if (*s <= 0x1f || *s >= 0x7f)
+ return false;
+ s++;
+ }
+
+ /* '\0' is not found */
+ return false;
}
static int btf_dumper_array(const struct btf_dumper *d, __u32 type_id,
@@ -57,6 +217,11 @@ static int btf_dumper_array(const struct btf_dumper *d, __u32 type_id,
int ret = 0;
__u32 i;
+ if (is_str_array(d->btf, arr, data)) {
+ jsonw_string(d->jw, data);
+ return 0;
+ }
+
elem_size = btf__resolve_size(d->btf, arr->type);
if (elem_size < 0)
return elem_size;
@@ -366,10 +531,9 @@ static int btf_dumper_do_type(const struct btf_dumper *d, __u32 type_id,
case BTF_KIND_ARRAY:
return btf_dumper_array(d, type_id, data);
case BTF_KIND_ENUM:
- btf_dumper_enum(data, d->jw);
- return 0;
+ return btf_dumper_enum(d, t, data);
case BTF_KIND_PTR:
- btf_dumper_ptr(data, d->jw, d->is_plain_text);
+ btf_dumper_ptr(d, t, data);
return 0;
case BTF_KIND_UNKN:
jsonw_printf(d->jw, "(unknown)");
@@ -414,10 +578,6 @@ int btf_dumper_type(const struct btf_dumper *d, __u32 type_id,
return -1; \
} while (0)
-static int btf_dump_func(const struct btf *btf, char *func_sig,
- const struct btf_type *func_proto,
- const struct btf_type *func, int pos, int size);
-
static int __btf_dumper_type_only(const struct btf *btf, __u32 type_id,
char *func_sig, int pos, int size)
{
@@ -526,8 +686,15 @@ static int btf_dump_func(const struct btf *btf, char *func_sig,
BTF_PRINT_ARG(", ");
if (arg->type) {
BTF_PRINT_TYPE(arg->type);
- BTF_PRINT_ARG("%s",
- btf__name_by_offset(btf, arg->name_off));
+ if (arg->name_off)
+ BTF_PRINT_ARG("%s",
+ btf__name_by_offset(btf, arg->name_off));
+ else if (pos && func_sig[pos - 1] == ' ')
+ /* Remove unnecessary space for
+ * FUNC_PROTO that does not have
+ * arg->name_off
+ */
+ func_sig[--pos] = '\0';
} else {
BTF_PRINT_ARG("...");
}
diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c
index b75b8ec5469c..f2223dbdfb0a 100644
--- a/tools/bpf/bpftool/common.c
+++ b/tools/bpf/bpftool/common.c
@@ -211,39 +211,14 @@ int do_pin_fd(int fd, const char *name)
return err;
}
-int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(__u32))
+int do_pin_any(int argc, char **argv, int (*get_fd)(int *, char ***))
{
- unsigned int id;
- char *endptr;
int err;
int fd;
- if (argc < 3) {
- p_err("too few arguments, id ID and FILE path is required");
- return -1;
- } else if (argc > 3) {
- p_err("too many arguments");
- return -1;
- }
-
- if (!is_prefix(*argv, "id")) {
- p_err("expected 'id' got %s", *argv);
- return -1;
- }
- NEXT_ARG();
-
- id = strtoul(*argv, &endptr, 0);
- if (*endptr) {
- p_err("can't parse %s as ID", *argv);
- return -1;
- }
- NEXT_ARG();
-
- fd = get_fd_by_id(id);
- if (fd < 0) {
- p_err("can't open object by id (%u): %s", id, strerror(errno));
- return -1;
- }
+ fd = get_fd(&argc, &argv);
+ if (fd < 0)
+ return fd;
err = do_pin_fd(fd, *argv);
@@ -597,3 +572,10 @@ int parse_u32_arg(int *argc, char ***argv, __u32 *val, const char *what)
return 0;
}
+
+int __printf(2, 0)
+print_all_levels(__maybe_unused enum libbpf_print_level level,
+ const char *format, va_list args)
+{
+ return vfprintf(stderr, format, args);
+}
diff --git a/tools/bpf/bpftool/feature.c b/tools/bpf/bpftool/feature.c
index 941873d778d8..88718ee6a438 100644
--- a/tools/bpf/bpftool/feature.c
+++ b/tools/bpf/bpftool/feature.c
@@ -112,18 +112,12 @@ print_start_section(const char *json_title, const char *plain_title,
}
}
-static void
-print_end_then_start_section(const char *json_title, const char *plain_title,
- const char *define_comment,
- const char *define_prefix)
+static void print_end_section(void)
{
if (json_output)
jsonw_end_object(json_wtr);
else
printf("\n");
-
- print_start_section(json_title, plain_title, define_comment,
- define_prefix);
}
/* Probing functions */
@@ -520,13 +514,38 @@ probe_map_type(enum bpf_map_type map_type, const char *define_prefix,
}
static void
+probe_helper_for_progtype(enum bpf_prog_type prog_type, bool supported_type,
+ const char *define_prefix, unsigned int id,
+ const char *ptype_name, __u32 ifindex)
+{
+ bool res;
+
+ if (!supported_type)
+ res = false;
+ else
+ res = bpf_probe_helper(id, prog_type, ifindex);
+
+ if (json_output) {
+ if (res)
+ jsonw_string(json_wtr, helper_name[id]);
+ } else if (define_prefix) {
+ printf("#define %sBPF__PROG_TYPE_%s__HELPER_%s %s\n",
+ define_prefix, ptype_name, helper_name[id],
+ res ? "1" : "0");
+ } else {
+ if (res)
+ printf("\n\t- %s", helper_name[id]);
+ }
+}
+
+static void
probe_helpers_for_progtype(enum bpf_prog_type prog_type, bool supported_type,
- const char *define_prefix, __u32 ifindex)
+ const char *define_prefix, bool full_mode,
+ __u32 ifindex)
{
const char *ptype_name = prog_type_name[prog_type];
char feat_name[128];
unsigned int id;
- bool res;
if (ifindex)
/* Only test helpers for offload-able program types */
@@ -548,21 +567,19 @@ probe_helpers_for_progtype(enum bpf_prog_type prog_type, bool supported_type,
}
for (id = 1; id < ARRAY_SIZE(helper_name); id++) {
- if (!supported_type)
- res = false;
- else
- res = bpf_probe_helper(id, prog_type, ifindex);
-
- if (json_output) {
- if (res)
- jsonw_string(json_wtr, helper_name[id]);
- } else if (define_prefix) {
- printf("#define %sBPF__PROG_TYPE_%s__HELPER_%s %s\n",
- define_prefix, ptype_name, helper_name[id],
- res ? "1" : "0");
- } else {
- if (res)
- printf("\n\t- %s", helper_name[id]);
+ /* Skip helper functions which emit dmesg messages when not in
+ * the full mode.
+ */
+ switch (id) {
+ case BPF_FUNC_trace_printk:
+ case BPF_FUNC_probe_write_user:
+ if (!full_mode)
+ continue;
+ /* fallthrough */
+ default:
+ probe_helper_for_progtype(prog_type, supported_type,
+ define_prefix, id, ptype_name,
+ ifindex);
}
}
@@ -584,13 +601,132 @@ probe_large_insn_limit(const char *define_prefix, __u32 ifindex)
res, define_prefix);
}
+static void
+section_system_config(enum probe_component target, const char *define_prefix)
+{
+ switch (target) {
+ case COMPONENT_KERNEL:
+ case COMPONENT_UNSPEC:
+ if (define_prefix)
+ break;
+
+ print_start_section("system_config",
+ "Scanning system configuration...",
+ NULL, /* define_comment never used here */
+ NULL); /* define_prefix always NULL here */
+ if (check_procfs()) {
+ probe_unprivileged_disabled();
+ probe_jit_enable();
+ probe_jit_harden();
+ probe_jit_kallsyms();
+ probe_jit_limit();
+ } else {
+ p_info("/* procfs not mounted, skipping related probes */");
+ }
+ probe_kernel_image_config();
+ print_end_section();
+ break;
+ default:
+ break;
+ }
+}
+
+static bool section_syscall_config(const char *define_prefix)
+{
+ bool res;
+
+ print_start_section("syscall_config",
+ "Scanning system call availability...",
+ "/*** System call availability ***/",
+ define_prefix);
+ res = probe_bpf_syscall(define_prefix);
+ print_end_section();
+
+ return res;
+}
+
+static void
+section_program_types(bool *supported_types, const char *define_prefix,
+ __u32 ifindex)
+{
+ unsigned int i;
+
+ print_start_section("program_types",
+ "Scanning eBPF program types...",
+ "/*** eBPF program types ***/",
+ define_prefix);
+
+ for (i = BPF_PROG_TYPE_UNSPEC + 1; i < ARRAY_SIZE(prog_type_name); i++)
+ probe_prog_type(i, supported_types, define_prefix, ifindex);
+
+ print_end_section();
+}
+
+static void section_map_types(const char *define_prefix, __u32 ifindex)
+{
+ unsigned int i;
+
+ print_start_section("map_types",
+ "Scanning eBPF map types...",
+ "/*** eBPF map types ***/",
+ define_prefix);
+
+ for (i = BPF_MAP_TYPE_UNSPEC + 1; i < map_type_name_size; i++)
+ probe_map_type(i, define_prefix, ifindex);
+
+ print_end_section();
+}
+
+static void
+section_helpers(bool *supported_types, const char *define_prefix,
+ bool full_mode, __u32 ifindex)
+{
+ unsigned int i;
+
+ print_start_section("helpers",
+ "Scanning eBPF helper functions...",
+ "/*** eBPF helper functions ***/",
+ define_prefix);
+
+ if (define_prefix)
+ printf("/*\n"
+ " * Use %sHAVE_PROG_TYPE_HELPER(prog_type_name, helper_name)\n"
+ " * to determine if <helper_name> is available for <prog_type_name>,\n"
+ " * e.g.\n"
+ " * #if %sHAVE_PROG_TYPE_HELPER(xdp, bpf_redirect)\n"
+ " * // do stuff with this helper\n"
+ " * #elif\n"
+ " * // use a workaround\n"
+ " * #endif\n"
+ " */\n"
+ "#define %sHAVE_PROG_TYPE_HELPER(prog_type, helper) \\\n"
+ " %sBPF__PROG_TYPE_ ## prog_type ## __HELPER_ ## helper\n",
+ define_prefix, define_prefix, define_prefix,
+ define_prefix);
+ for (i = BPF_PROG_TYPE_UNSPEC + 1; i < ARRAY_SIZE(prog_type_name); i++)
+ probe_helpers_for_progtype(i, supported_types[i],
+ define_prefix, full_mode, ifindex);
+
+ print_end_section();
+}
+
+static void section_misc(const char *define_prefix, __u32 ifindex)
+{
+ print_start_section("misc",
+ "Scanning miscellaneous eBPF features...",
+ "/*** eBPF misc features ***/",
+ define_prefix);
+ probe_large_insn_limit(define_prefix, ifindex);
+ print_end_section();
+}
+
static int do_probe(int argc, char **argv)
{
enum probe_component target = COMPONENT_UNSPEC;
const char *define_prefix = NULL;
bool supported_types[128] = {};
+ bool full_mode = false;
__u32 ifindex = 0;
- unsigned int i;
char *ifname;
/* Detection assumes user has sufficient privileges (CAP_SYS_ADMIN).
@@ -629,6 +765,9 @@ static int do_probe(int argc, char **argv)
strerror(errno));
return -1;
}
+ } else if (is_prefix(*argv, "full")) {
+ full_mode = true;
+ NEXT_ARG();
} else if (is_prefix(*argv, "macros") && !define_prefix) {
define_prefix = "";
NEXT_ARG();
@@ -658,97 +797,19 @@ static int do_probe(int argc, char **argv)
jsonw_start_object(json_wtr);
}
- switch (target) {
- case COMPONENT_KERNEL:
- case COMPONENT_UNSPEC:
- if (define_prefix)
- break;
-
- print_start_section("system_config",
- "Scanning system configuration...",
- NULL, /* define_comment never used here */
- NULL); /* define_prefix always NULL here */
- if (check_procfs()) {
- probe_unprivileged_disabled();
- probe_jit_enable();
- probe_jit_harden();
- probe_jit_kallsyms();
- probe_jit_limit();
- } else {
- p_info("/* procfs not mounted, skipping related probes */");
- }
- probe_kernel_image_config();
- if (json_output)
- jsonw_end_object(json_wtr);
- else
- printf("\n");
- break;
- default:
- break;
- }
-
- print_start_section("syscall_config",
- "Scanning system call availability...",
- "/*** System call availability ***/",
- define_prefix);
-
- if (!probe_bpf_syscall(define_prefix))
+ section_system_config(target, define_prefix);
+ if (!section_syscall_config(define_prefix))
/* bpf() syscall unavailable, don't probe other BPF features */
goto exit_close_json;
-
- print_end_then_start_section("program_types",
- "Scanning eBPF program types...",
- "/*** eBPF program types ***/",
- define_prefix);
-
- for (i = BPF_PROG_TYPE_UNSPEC + 1; i < ARRAY_SIZE(prog_type_name); i++)
- probe_prog_type(i, supported_types, define_prefix, ifindex);
-
- print_end_then_start_section("map_types",
- "Scanning eBPF map types...",
- "/*** eBPF map types ***/",
- define_prefix);
-
- for (i = BPF_MAP_TYPE_UNSPEC + 1; i < map_type_name_size; i++)
- probe_map_type(i, define_prefix, ifindex);
-
- print_end_then_start_section("helpers",
- "Scanning eBPF helper functions...",
- "/*** eBPF helper functions ***/",
- define_prefix);
-
- if (define_prefix)
- printf("/*\n"
- " * Use %sHAVE_PROG_TYPE_HELPER(prog_type_name, helper_name)\n"
- " * to determine if <helper_name> is available for <prog_type_name>,\n"
- " * e.g.\n"
- " * #if %sHAVE_PROG_TYPE_HELPER(xdp, bpf_redirect)\n"
- " * // do stuff with this helper\n"
- " * #elif\n"
- " * // use a workaround\n"
- " * #endif\n"
- " */\n"
- "#define %sHAVE_PROG_TYPE_HELPER(prog_type, helper) \\\n"
- " %sBPF__PROG_TYPE_ ## prog_type ## __HELPER_ ## helper\n",
- define_prefix, define_prefix, define_prefix,
- define_prefix);
- for (i = BPF_PROG_TYPE_UNSPEC + 1; i < ARRAY_SIZE(prog_type_name); i++)
- probe_helpers_for_progtype(i, supported_types[i],
- define_prefix, ifindex);
-
- print_end_then_start_section("misc",
- "Scanning miscellaneous eBPF features...",
- "/*** eBPF misc features ***/",
- define_prefix);
- probe_large_insn_limit(define_prefix, ifindex);
+ section_program_types(supported_types, define_prefix, ifindex);
+ section_map_types(define_prefix, ifindex);
+ section_helpers(supported_types, define_prefix, full_mode, ifindex);
+ section_misc(define_prefix, ifindex);
exit_close_json:
- if (json_output) {
- /* End current "section" of probes */
- jsonw_end_object(json_wtr);
+ if (json_output)
/* End root object */
jsonw_end_object(json_wtr);
- }
return 0;
}
@@ -761,7 +822,7 @@ static int do_help(int argc, char **argv)
}
fprintf(stderr,
- "Usage: %s %s probe [COMPONENT] [macros [prefix PREFIX]]\n"
+ "Usage: %s %s probe [COMPONENT] [full] [macros [prefix PREFIX]]\n"
" %s %s help\n"
"\n"
" COMPONENT := { kernel | dev NAME }\n"
diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c
index 6d41bbfc6459..466c269eabdd 100644
--- a/tools/bpf/bpftool/main.c
+++ b/tools/bpf/bpftool/main.c
@@ -58,7 +58,7 @@ static int do_help(int argc, char **argv)
" %s batch file FILE\n"
" %s version\n"
"\n"
- " OBJECT := { prog | map | cgroup | perf | net | feature | btf | gen }\n"
+ " OBJECT := { prog | map | cgroup | perf | net | feature | btf | gen | struct_ops }\n"
" " HELP_SPEC_OPTIONS "\n"
"",
bin_name, bin_name, bin_name);
@@ -79,13 +79,6 @@ static int do_version(int argc, char **argv)
return 0;
}
-static int __printf(2, 0)
-print_all_levels(__maybe_unused enum libbpf_print_level level,
- const char *format, va_list args)
-{
- return vfprintf(stderr, format, args);
-}
-
int cmd_select(const struct cmd *cmds, int argc, char **argv,
int (*help)(int argc, char **argv))
{
@@ -228,6 +221,7 @@ static const struct cmd cmds[] = {
{ "feature", do_feature },
{ "btf", do_btf },
{ "gen", do_gen },
+ { "struct_ops", do_struct_ops },
{ "version", do_version },
{ 0 }
};
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index 4e75b58d3989..86f14ce26fd7 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -14,6 +14,8 @@
#include <linux/hashtable.h>
#include <tools/libc_compat.h>
+#include <bpf/libbpf.h>
+
#include "json_writer.h"
#define ptr_to_u64(ptr) ((__u64)(unsigned long)(ptr))
@@ -76,6 +78,9 @@ static const char * const prog_type_name[] = {
[BPF_PROG_TYPE_CGROUP_SYSCTL] = "cgroup_sysctl",
[BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE] = "raw_tracepoint_writable",
[BPF_PROG_TYPE_CGROUP_SOCKOPT] = "cgroup_sockopt",
+ [BPF_PROG_TYPE_TRACING] = "tracing",
+ [BPF_PROG_TYPE_STRUCT_OPS] = "struct_ops",
+ [BPF_PROG_TYPE_EXT] = "ext",
};
extern const char * const map_type_name[];
@@ -143,7 +148,7 @@ char *get_fdinfo(int fd, const char *key);
int open_obj_pinned(char *path, bool quiet);
int open_obj_pinned_any(char *path, enum bpf_obj_type exp_type);
int mount_bpffs_for_pin(const char *name);
-int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(__u32));
+int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(int *, char ***));
int do_pin_fd(int fd, const char *name);
int do_prog(int argc, char **arg);
@@ -156,6 +161,7 @@ int do_tracelog(int argc, char **arg);
int do_feature(int argc, char **argv);
int do_btf(int argc, char **argv);
int do_gen(int argc, char **argv);
+int do_struct_ops(int argc, char **argv);
int parse_u32_arg(int *argc, char ***argv, __u32 *val, const char *what);
int prog_parse_fd(int *argc, char ***argv);
@@ -200,6 +206,7 @@ struct btf_dumper {
const struct btf *btf;
json_writer_t *jw;
bool is_plain_text;
+ bool prog_id_as_func_ptr;
};
/* btf_dumper_type - print data along with type information
@@ -226,4 +233,7 @@ struct tcmsg;
int do_xdp_dump(struct ifinfomsg *ifinfo, struct nlattr **tb);
int do_filter_dump(struct tcmsg *ifinfo, struct nlattr **tb, const char *kind,
const char *devname, int ifindex);
+
+int print_all_levels(__maybe_unused enum libbpf_print_level level,
+ const char *format, va_list args);
#endif
diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index e6c85680b34d..693a632f6813 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -1384,7 +1384,7 @@ static int do_pin(int argc, char **argv)
{
int err;
- err = do_pin_any(argc, argv, bpf_map_get_fd_by_id);
+ err = do_pin_any(argc, argv, map_parse_fd);
if (!err && json_output)
jsonw_null(json_wtr);
return err;
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index b352ab041160..f6a5974a7b0a 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -4,6 +4,7 @@
#define _GNU_SOURCE
#include <errno.h>
#include <fcntl.h>
+#include <signal.h>
#include <stdarg.h>
#include <stdio.h>
#include <stdlib.h>
@@ -11,10 +12,13 @@
#include <time.h>
#include <unistd.h>
#include <net/if.h>
+#include <sys/ioctl.h>
#include <sys/types.h>
#include <sys/stat.h>
+#include <sys/syscall.h>
#include <linux/err.h>
+#include <linux/perf_event.h>
#include <linux/sizes.h>
#include <bpf/bpf.h>
@@ -809,7 +813,7 @@ static int do_pin(int argc, char **argv)
{
int err;
- err = do_pin_any(argc, argv, bpf_prog_get_fd_by_id);
+ err = do_pin_any(argc, argv, prog_parse_fd);
if (!err && json_output)
jsonw_null(json_wtr);
return err;
@@ -1243,6 +1247,25 @@ free_data_in:
return err;
}
+static int
+get_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type,
+ enum bpf_attach_type *expected_attach_type)
+{
+ libbpf_print_fn_t print_backup;
+ int ret;
+
+ ret = libbpf_prog_type_by_name(name, prog_type, expected_attach_type);
+ if (!ret)
+ return ret;
+
+ /* libbpf_prog_type_by_name() failed, let's re-run with debug level */
+ print_backup = libbpf_set_print(print_all_levels);
+ ret = libbpf_prog_type_by_name(name, prog_type, expected_attach_type);
+ libbpf_set_print(print_backup);
+
+ return ret;
+}
+
static int load_with_options(int argc, char **argv, bool first_prog_only)
{
enum bpf_prog_type common_prog_type = BPF_PROG_TYPE_UNSPEC;
@@ -1292,8 +1315,8 @@ static int load_with_options(int argc, char **argv, bool first_prog_only)
strcat(type, *argv);
strcat(type, "/");
- err = libbpf_prog_type_by_name(type, &common_prog_type,
- &expected_attach_type);
+ err = get_prog_type_by_name(type, &common_prog_type,
+ &expected_attach_type);
free(type);
if (err < 0)
goto err_free_reuse_maps;
@@ -1392,8 +1415,8 @@ static int load_with_options(int argc, char **argv, bool first_prog_only)
if (prog_type == BPF_PROG_TYPE_UNSPEC) {
const char *sec_name = bpf_program__title(pos, false);
- err = libbpf_prog_type_by_name(sec_name, &prog_type,
- &expected_attach_type);
+ err = get_prog_type_by_name(sec_name, &prog_type,
+ &expected_attach_type);
if (err < 0)
goto err_close_obj;
}
@@ -1537,6 +1560,422 @@ static int do_loadall(int argc, char **argv)
return load_with_options(argc, argv, false);
}
+#ifdef BPFTOOL_WITHOUT_SKELETONS
+
+static int do_profile(int argc, char **argv)
+{
+ p_err("bpftool prog profile command is not supported. Please build bpftool with clang >= 10.0.0");
+ return 0;
+}
+
+#else /* BPFTOOL_WITHOUT_SKELETONS */
+
+#include "profiler.skel.h"
+
+struct profile_metric {
+ const char *name;
+ struct bpf_perf_event_value val;
+ struct perf_event_attr attr;
+ bool selected;
+
+ /* calculate ratios like instructions per cycle */
+ const int ratio_metric; /* 0 for N/A, 1 for index 0 (cycles) */
+ const char *ratio_desc;
+ const float ratio_mul;
+} metrics[] = {
+ {
+ .name = "cycles",
+ .attr = {
+ .type = PERF_TYPE_HARDWARE,
+ .config = PERF_COUNT_HW_CPU_CYCLES,
+ .exclude_user = 1,
+ },
+ },
+ {
+ .name = "instructions",
+ .attr = {
+ .type = PERF_TYPE_HARDWARE,
+ .config = PERF_COUNT_HW_INSTRUCTIONS,
+ .exclude_user = 1,
+ },
+ .ratio_metric = 1,
+ .ratio_desc = "insns per cycle",
+ .ratio_mul = 1.0,
+ },
+ {
+ .name = "l1d_loads",
+ .attr = {
+ .type = PERF_TYPE_HW_CACHE,
+ .config =
+ PERF_COUNT_HW_CACHE_L1D |
+ (PERF_COUNT_HW_CACHE_OP_READ << 8) |
+ (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16),
+ .exclude_user = 1,
+ },
+ },
+ {
+ .name = "llc_misses",
+ .attr = {
+ .type = PERF_TYPE_HW_CACHE,
+ .config =
+ PERF_COUNT_HW_CACHE_LL |
+ (PERF_COUNT_HW_CACHE_OP_READ << 8) |
+ (PERF_COUNT_HW_CACHE_RESULT_MISS << 16),
+ .exclude_user = 1
+ },
+ .ratio_metric = 2,
+ .ratio_desc = "LLC misses per million insns",
+ .ratio_mul = 1e6,
+ },
+};
+
+static __u64 profile_total_count;
+
+#define MAX_NUM_PROFILE_METRICS 4
+
+static int profile_parse_metrics(int argc, char **argv)
+{
+ unsigned int metric_cnt;
+ int selected_cnt = 0;
+ unsigned int i;
+
+ metric_cnt = sizeof(metrics) / sizeof(struct profile_metric);
+
+ while (argc > 0) {
+ for (i = 0; i < metric_cnt; i++) {
+ if (is_prefix(argv[0], metrics[i].name)) {
+ if (!metrics[i].selected)
+ selected_cnt++;
+ metrics[i].selected = true;
+ break;
+ }
+ }
+ if (i == metric_cnt) {
+ p_err("unknown metric %s", argv[0]);
+ return -1;
+ }
+ NEXT_ARG();
+ }
+ if (selected_cnt > MAX_NUM_PROFILE_METRICS) {
+ p_err("too many (%d) metrics, please specify no more than %d metrics at at time",
+ selected_cnt, MAX_NUM_PROFILE_METRICS);
+ return -1;
+ }
+ return selected_cnt;
+}
+
+static void profile_read_values(struct profiler_bpf *obj)
+{
+ __u32 m, cpu, num_cpu = obj->rodata->num_cpu;
+ int reading_map_fd, count_map_fd;
+ __u64 counts[num_cpu];
+ __u32 key = 0;
+ int err;
+
+ reading_map_fd = bpf_map__fd(obj->maps.accum_readings);
+ count_map_fd = bpf_map__fd(obj->maps.counts);
+ if (reading_map_fd < 0 || count_map_fd < 0) {
+ p_err("failed to get fd for map");
+ return;
+ }
+
+ err = bpf_map_lookup_elem(count_map_fd, &key, counts);
+ if (err) {
+ p_err("failed to read count_map: %s", strerror(errno));
+ return;
+ }
+
+ profile_total_count = 0;
+ for (cpu = 0; cpu < num_cpu; cpu++)
+ profile_total_count += counts[cpu];
+
+ for (m = 0; m < ARRAY_SIZE(metrics); m++) {
+ struct bpf_perf_event_value values[num_cpu];
+
+ if (!metrics[m].selected)
+ continue;
+
+ err = bpf_map_lookup_elem(reading_map_fd, &key, values);
+ if (err) {
+ p_err("failed to read reading_map: %s",
+ strerror(errno));
+ return;
+ }
+ for (cpu = 0; cpu < num_cpu; cpu++) {
+ metrics[m].val.counter += values[cpu].counter;
+ metrics[m].val.enabled += values[cpu].enabled;
+ metrics[m].val.running += values[cpu].running;
+ }
+ key++;
+ }
+}
+
+static void profile_print_readings_json(void)
+{
+ __u32 m;
+
+ jsonw_start_array(json_wtr);
+ for (m = 0; m < ARRAY_SIZE(metrics); m++) {
+ if (!metrics[m].selected)
+ continue;
+ jsonw_start_object(json_wtr);
+ jsonw_string_field(json_wtr, "metric", metrics[m].name);
+ jsonw_lluint_field(json_wtr, "run_cnt", profile_total_count);
+ jsonw_lluint_field(json_wtr, "value", metrics[m].val.counter);
+ jsonw_lluint_field(json_wtr, "enabled", metrics[m].val.enabled);
+ jsonw_lluint_field(json_wtr, "running", metrics[m].val.running);
+
+ jsonw_end_object(json_wtr);
+ }
+ jsonw_end_array(json_wtr);
+}
+
+static void profile_print_readings_plain(void)
+{
+ __u32 m;
+
+ printf("\n%18llu %-20s\n", profile_total_count, "run_cnt");
+ for (m = 0; m < ARRAY_SIZE(metrics); m++) {
+ struct bpf_perf_event_value *val = &metrics[m].val;
+ int r;
+
+ if (!metrics[m].selected)
+ continue;
+ printf("%18llu %-20s", val->counter, metrics[m].name);
+
+ r = metrics[m].ratio_metric - 1;
+ if (r >= 0 && metrics[r].selected &&
+ metrics[r].val.counter > 0) {
+ printf("# %8.2f %-30s",
+ val->counter * metrics[m].ratio_mul /
+ metrics[r].val.counter,
+ metrics[m].ratio_desc);
+ } else {
+ printf("%-41s", "");
+ }
+
+ if (val->enabled > val->running)
+ printf("(%4.2f%%)",
+ val->running * 100.0 / val->enabled);
+ printf("\n");
+ }
+}
+
+static void profile_print_readings(void)
+{
+ if (json_output)
+ profile_print_readings_json();
+ else
+ profile_print_readings_plain();
+}
+
+static char *profile_target_name(int tgt_fd)
+{
+ struct bpf_prog_info_linear *info_linear;
+ struct bpf_func_info *func_info;
+ const struct btf_type *t;
+ char *name = NULL;
+ struct btf *btf;
+
+ info_linear = bpf_program__get_prog_info_linear(
+ tgt_fd, 1UL << BPF_PROG_INFO_FUNC_INFO);
+ if (IS_ERR_OR_NULL(info_linear)) {
+ p_err("failed to get info_linear for prog FD %d", tgt_fd);
+ return NULL;
+ }
+
+ if (info_linear->info.btf_id == 0 ||
+ btf__get_from_id(info_linear->info.btf_id, &btf)) {
+ p_err("prog FD %d doesn't have valid btf", tgt_fd);
+ goto out;
+ }
+
+ func_info = (struct bpf_func_info *)(info_linear->info.func_info);
+ t = btf__type_by_id(btf, func_info[0].type_id);
+ if (!t) {
+ p_err("btf %d doesn't have type %d",
+ info_linear->info.btf_id, func_info[0].type_id);
+ goto out;
+ }
+ name = strdup(btf__name_by_offset(btf, t->name_off));
+out:
+ free(info_linear);
+ return name;
+}
+
+static struct profiler_bpf *profile_obj;
+static int profile_tgt_fd = -1;
+static char *profile_tgt_name;
+static int *profile_perf_events;
+static int profile_perf_event_cnt;
+
+static void profile_close_perf_events(struct profiler_bpf *obj)
+{
+ int i;
+
+ for (i = profile_perf_event_cnt - 1; i >= 0; i--)
+ close(profile_perf_events[i]);
+
+ free(profile_perf_events);
+ profile_perf_event_cnt = 0;
+}
+
+static int profile_open_perf_events(struct profiler_bpf *obj)
+{
+ unsigned int cpu, m;
+ int map_fd, pmu_fd;
+
+ profile_perf_events = calloc(
+ sizeof(int), obj->rodata->num_cpu * obj->rodata->num_metric);
+ if (!profile_perf_events) {
+ p_err("failed to allocate memory for perf_event array: %s",
+ strerror(errno));
+ return -1;
+ }
+ map_fd = bpf_map__fd(obj->maps.events);
+ if (map_fd < 0) {
+ p_err("failed to get fd for events map");
+ return -1;
+ }
+
+ for (m = 0; m < ARRAY_SIZE(metrics); m++) {
+ if (!metrics[m].selected)
+ continue;
+ for (cpu = 0; cpu < obj->rodata->num_cpu; cpu++) {
+ pmu_fd = syscall(__NR_perf_event_open, &metrics[m].attr,
+ -1/*pid*/, cpu, -1/*group_fd*/, 0);
+ if (pmu_fd < 0 ||
+ bpf_map_update_elem(map_fd, &profile_perf_event_cnt,
+ &pmu_fd, BPF_ANY) ||
+ ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0)) {
+ p_err("failed to create event %s on cpu %d",
+ metrics[m].name, cpu);
+ return -1;
+ }
+ profile_perf_events[profile_perf_event_cnt++] = pmu_fd;
+ }
+ }
+ return 0;
+}
+
+static void profile_print_and_cleanup(void)
+{
+ profile_close_perf_events(profile_obj);
+ profile_read_values(profile_obj);
+ profile_print_readings();
+ profiler_bpf__destroy(profile_obj);
+
+ close(profile_tgt_fd);
+ free(profile_tgt_name);
+}
+
+static void int_exit(int signo)
+{
+ profile_print_and_cleanup();
+ exit(0);
+}
+
+static int do_profile(int argc, char **argv)
+{
+ int num_metric, num_cpu, err = -1;
+ struct bpf_program *prog;
+ unsigned long duration;
+ char *endptr;
+
+ /* we at least need two args for the prog and one metric */
+ if (!REQ_ARGS(3))
+ return -EINVAL;
+
+ /* parse target fd */
+ profile_tgt_fd = prog_parse_fd(&argc, &argv);
+ if (profile_tgt_fd < 0) {
+ p_err("failed to parse fd");
+ return -1;
+ }
+
+ /* parse profiling optional duration */
+ if (argc > 2 && is_prefix(argv[0], "duration")) {
+ NEXT_ARG();
+ duration = strtoul(*argv, &endptr, 0);
+ if (*endptr)
+ usage();
+ NEXT_ARG();
+ } else {
+ duration = UINT_MAX;
+ }
+
+ num_metric = profile_parse_metrics(argc, argv);
+ if (num_metric <= 0)
+ goto out;
+
+ num_cpu = libbpf_num_possible_cpus();
+ if (num_cpu <= 0) {
+ p_err("failed to identify number of CPUs");
+ goto out;
+ }
+
+ profile_obj = profiler_bpf__open();
+ if (!profile_obj) {
+ p_err("failed to open and/or load BPF object");
+ goto out;
+ }
+
+ profile_obj->rodata->num_cpu = num_cpu;
+ profile_obj->rodata->num_metric = num_metric;
+
+ /* adjust map sizes */
+ bpf_map__resize(profile_obj->maps.events, num_metric * num_cpu);
+ bpf_map__resize(profile_obj->maps.fentry_readings, num_metric);
+ bpf_map__resize(profile_obj->maps.accum_readings, num_metric);
+ bpf_map__resize(profile_obj->maps.counts, 1);
+
+ /* change target name */
+ profile_tgt_name = profile_target_name(profile_tgt_fd);
+ if (!profile_tgt_name)
+ goto out;
+
+ bpf_object__for_each_program(prog, profile_obj->obj) {
+ err = bpf_program__set_attach_target(prog, profile_tgt_fd,
+ profile_tgt_name);
+ if (err) {
+ p_err("failed to set attach target\n");
+ goto out;
+ }
+ }
+
+ set_max_rlimit();
+ err = profiler_bpf__load(profile_obj);
+ if (err) {
+ p_err("failed to load profile_obj");
+ goto out;
+ }
+
+ err = profile_open_perf_events(profile_obj);
+ if (err)
+ goto out;
+
+ err = profiler_bpf__attach(profile_obj);
+ if (err) {
+ p_err("failed to attach profile_obj");
+ goto out;
+ }
+ signal(SIGINT, int_exit);
+
+ sleep(duration);
+ profile_print_and_cleanup();
+ return 0;
+
+out:
+ profile_close_perf_events(profile_obj);
+ if (profile_obj)
+ profiler_bpf__destroy(profile_obj);
+ close(profile_tgt_fd);
+ free(profile_tgt_name);
+ return err;
+}
+
+#endif /* BPFTOOL_WITHOUT_SKELETONS */
+
static int do_help(int argc, char **argv)
{
if (json_output) {
@@ -1560,6 +1999,7 @@ static int do_help(int argc, char **argv)
" [data_out FILE [data_size_out L]] \\\n"
" [ctx_in FILE [ctx_out FILE [ctx_size_out M]]] \\\n"
" [repeat N]\n"
+ " %s %s profile PROG [duration DURATION] METRICs\n"
" %s %s tracelog\n"
" %s %s help\n"
"\n"
@@ -1573,16 +2013,17 @@ static int do_help(int argc, char **argv)
" cgroup/bind4 | cgroup/bind6 | cgroup/post_bind4 |\n"
" cgroup/post_bind6 | cgroup/connect4 | cgroup/connect6 |\n"
" cgroup/sendmsg4 | cgroup/sendmsg6 | cgroup/recvmsg4 |\n"
- " cgroup/recvmsg6 | cgroup/getsockopt |\n"
- " cgroup/setsockopt }\n"
+ " cgroup/recvmsg6 | cgroup/getsockopt | cgroup/setsockopt |\n"
+ " struct_ops | fentry | fexit | freplace }\n"
" ATTACH_TYPE := { msg_verdict | stream_verdict | stream_parser |\n"
" flow_dissector }\n"
+ " METRIC := { cycles | instructions | l1d_loads | llc_misses }\n"
" " HELP_SPEC_OPTIONS "\n"
"",
bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2],
bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2],
bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2],
- bin_name, argv[-2]);
+ bin_name, argv[-2], bin_name, argv[-2]);
return 0;
}
@@ -1599,6 +2040,7 @@ static const struct cmd cmds[] = {
{ "detach", do_detach },
{ "tracelog", do_tracelog },
{ "run", do_run },
+ { "profile", do_profile },
{ 0 }
};
diff --git a/tools/bpf/bpftool/skeleton/profiler.bpf.c b/tools/bpf/bpftool/skeleton/profiler.bpf.c
new file mode 100644
index 000000000000..20034c12f7c5
--- /dev/null
+++ b/tools/bpf/bpftool/skeleton/profiler.bpf.c
@@ -0,0 +1,119 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2020 Facebook
+#include "profiler.h"
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+/* map of perf event fds, num_cpu * num_metric entries */
+struct {
+ __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
+ __uint(key_size, sizeof(u32));
+ __uint(value_size, sizeof(int));
+} events SEC(".maps");
+
+/* readings at fentry */
+struct {
+ __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+ __uint(key_size, sizeof(u32));
+ __uint(value_size, sizeof(struct bpf_perf_event_value));
+} fentry_readings SEC(".maps");
+
+/* accumulated readings */
+struct {
+ __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+ __uint(key_size, sizeof(u32));
+ __uint(value_size, sizeof(struct bpf_perf_event_value));
+} accum_readings SEC(".maps");
+
+/* sample counts, one per cpu */
+struct {
+ __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+ __uint(key_size, sizeof(u32));
+ __uint(value_size, sizeof(u64));
+} counts SEC(".maps");
+
+const volatile __u32 num_cpu = 1;
+const volatile __u32 num_metric = 1;
+#define MAX_NUM_MATRICS 4
+
+SEC("fentry/XXX")
+int BPF_PROG(fentry_XXX)
+{
+ struct bpf_perf_event_value *ptrs[MAX_NUM_MATRICS];
+ u32 key = bpf_get_smp_processor_id();
+ u32 i;
+
+ /* look up before reading, to reduce error */
+ for (i = 0; i < num_metric && i < MAX_NUM_MATRICS; i++) {
+ u32 flag = i;
+
+ ptrs[i] = bpf_map_lookup_elem(&fentry_readings, &flag);
+ if (!ptrs[i])
+ return 0;
+ }
+
+ for (i = 0; i < num_metric && i < MAX_NUM_MATRICS; i++) {
+ struct bpf_perf_event_value reading;
+ int err;
+
+ err = bpf_perf_event_read_value(&events, key, &reading,
+ sizeof(reading));
+ if (err)
+ return 0;
+ *(ptrs[i]) = reading;
+ key += num_cpu;
+ }
+
+ return 0;
+}
+
+static inline void
+fexit_update_maps(u32 id, struct bpf_perf_event_value *after)
+{
+ struct bpf_perf_event_value *before, diff, *accum;
+
+ before = bpf_map_lookup_elem(&fentry_readings, &id);
+ /* only account samples with a valid fentry_reading */
+ if (before && before->counter) {
+ struct bpf_perf_event_value *accum;
+
+ diff.counter = after->counter - before->counter;
+ diff.enabled = after->enabled - before->enabled;
+ diff.running = after->running - before->running;
+
+ accum = bpf_map_lookup_elem(&accum_readings, &id);
+ if (accum) {
+ accum->counter += diff.counter;
+ accum->enabled += diff.enabled;
+ accum->running += diff.running;
+ }
+ }
+}
+
+SEC("fexit/XXX")
+int BPF_PROG(fexit_XXX)
+{
+ struct bpf_perf_event_value readings[MAX_NUM_MATRICS];
+ u32 cpu = bpf_get_smp_processor_id();
+ u32 i, one = 1, zero = 0;
+ int err;
+ u64 *count;
+
+ /* read all events before updating the maps, to reduce error */
+ for (i = 0; i < num_metric && i < MAX_NUM_MATRICS; i++) {
+ err = bpf_perf_event_read_value(&events, cpu + i * num_cpu,
+ readings + i, sizeof(*readings));
+ if (err)
+ return 0;
+ }
+ count = bpf_map_lookup_elem(&counts, &zero);
+ if (count) {
+ *count += 1;
+ for (i = 0; i < num_metric && i < MAX_NUM_MATRICS; i++)
+ fexit_update_maps(i, &readings[i]);
+ }
+ return 0;
+}
+
+char LICENSE[] SEC("license") = "GPL";
diff --git a/tools/bpf/bpftool/skeleton/profiler.h b/tools/bpf/bpftool/skeleton/profiler.h
new file mode 100644
index 000000000000..1f767e9510f7
--- /dev/null
+++ b/tools/bpf/bpftool/skeleton/profiler.h
@@ -0,0 +1,46 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+#ifndef __PROFILER_H
+#define __PROFILER_H
+
+/* useful typedefs from vmlinux.h */
+
+typedef signed char __s8;
+typedef unsigned char __u8;
+typedef short int __s16;
+typedef short unsigned int __u16;
+typedef int __s32;
+typedef unsigned int __u32;
+typedef long long int __s64;
+typedef long long unsigned int __u64;
+
+typedef __s8 s8;
+typedef __u8 u8;
+typedef __s16 s16;
+typedef __u16 u16;
+typedef __s32 s32;
+typedef __u32 u32;
+typedef __s64 s64;
+typedef __u64 u64;
+
+enum {
+ false = 0,
+ true = 1,
+};
+
+#ifdef __CHECKER__
+#define __bitwise__ __attribute__((bitwise))
+#else
+#define __bitwise__
+#endif
+
+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;
+
+#endif /* __PROFILER_H */
diff --git a/tools/bpf/bpftool/struct_ops.c b/tools/bpf/bpftool/struct_ops.c
new file mode 100644
index 000000000000..2a7befbd11ad
--- /dev/null
+++ b/tools/bpf/bpftool/struct_ops.c
@@ -0,0 +1,596 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+/* Copyright (C) 2020 Facebook */
+
+#include <errno.h>
+#include <stdio.h>
+#include <unistd.h>
+
+#include <linux/err.h>
+
+#include <bpf/bpf.h>
+#include <bpf/btf.h>
+#include <bpf/libbpf.h>
+
+#include "json_writer.h"
+#include "main.h"
+
+#define STRUCT_OPS_VALUE_PREFIX "bpf_struct_ops_"
+
+static const struct btf_type *map_info_type;
+static __u32 map_info_alloc_len;
+static struct btf *btf_vmlinux;
+static __s32 map_info_type_id;
+
+struct res {
+ unsigned int nr_maps;
+ unsigned int nr_errs;
+};
+
+static const struct btf *get_btf_vmlinux(void)
+{
+ if (btf_vmlinux)
+ return btf_vmlinux;
+
+ btf_vmlinux = libbpf_find_kernel_btf();
+ if (IS_ERR(btf_vmlinux))
+ p_err("struct_ops requires kernel CONFIG_DEBUG_INFO_BTF=y");
+
+ return btf_vmlinux;
+}
+
+static const char *get_kern_struct_ops_name(const struct bpf_map_info *info)
+{
+ const struct btf *kern_btf;
+ const struct btf_type *t;
+ const char *st_ops_name;
+
+ kern_btf = get_btf_vmlinux();
+ if (IS_ERR(kern_btf))
+ return "<btf_vmlinux_not_found>";
+
+ t = btf__type_by_id(kern_btf, info->btf_vmlinux_value_type_id);
+ st_ops_name = btf__name_by_offset(kern_btf, t->name_off);
+ st_ops_name += strlen(STRUCT_OPS_VALUE_PREFIX);
+
+ return st_ops_name;
+}
+
+static __s32 get_map_info_type_id(void)
+{
+ const struct btf *kern_btf;
+
+ if (map_info_type_id)
+ return map_info_type_id;
+
+ kern_btf = get_btf_vmlinux();
+ if (IS_ERR(kern_btf)) {
+ map_info_type_id = PTR_ERR(kern_btf);
+ return map_info_type_id;
+ }
+
+ map_info_type_id = btf__find_by_name_kind(kern_btf, "bpf_map_info",
+ BTF_KIND_STRUCT);
+ if (map_info_type_id < 0) {
+ p_err("can't find bpf_map_info from btf_vmlinux");
+ return map_info_type_id;
+ }
+ map_info_type = btf__type_by_id(kern_btf, map_info_type_id);
+
+ /* Ensure map_info_alloc() has at least what the bpftool needs */
+ map_info_alloc_len = map_info_type->size;
+ if (map_info_alloc_len < sizeof(struct bpf_map_info))
+ map_info_alloc_len = sizeof(struct bpf_map_info);
+
+ return map_info_type_id;
+}
+
+/* If the subcmd needs to print out the bpf_map_info,
+ * it should always call map_info_alloc to allocate
+ * a bpf_map_info object instead of allocating it
+ * on the stack.
+ *
+ * map_info_alloc() will take the running kernel's btf
+ * into account. i.e. it will consider the
+ * sizeof(struct bpf_map_info) of the running kernel.
+ *
+ * It will enable the "struct_ops" cmd to print the latest
+ * "struct bpf_map_info".
+ *
+ * [ Recall that "struct_ops" requires the kernel's btf to
+ * be available ]
+ */
+static struct bpf_map_info *map_info_alloc(__u32 *alloc_len)
+{
+ struct bpf_map_info *info;
+
+ if (get_map_info_type_id() < 0)
+ return NULL;
+
+ info = calloc(1, map_info_alloc_len);
+ if (!info)
+ p_err("mem alloc failed");
+ else
+ *alloc_len = map_info_alloc_len;
+
+ return info;
+}
+
+/* It iterates all struct_ops maps of the system.
+ * It returns the fd in "*res_fd" and map_info in "*info".
+ * In the very first iteration, info->id should be 0.
+ * An optional map "*name" filter can be specified.
+ * The filter can be made more flexible in the future.
+ * e.g. filter by kernel-struct-ops-name, regex-name, glob-name, ...etc.
+ *
+ * Return value:
+ * 1: A struct_ops map found. It is returned in "*res_fd" and "*info".
+ * The caller can continue to call get_next in the future.
+ * 0: No struct_ops map is returned.
+ * All struct_ops map has been found.
+ * -1: Error and the caller should abort the iteration.
+ */
+static int get_next_struct_ops_map(const char *name, int *res_fd,
+ struct bpf_map_info *info, __u32 info_len)
+{
+ __u32 id = info->id;
+ int err, fd;
+
+ while (true) {
+ err = bpf_map_get_next_id(id, &id);
+ if (err) {
+ if (errno == ENOENT)
+ return 0;
+ p_err("can't get next map: %s", strerror(errno));
+ return -1;
+ }
+
+ fd = bpf_map_get_fd_by_id(id);
+ if (fd < 0) {
+ if (errno == ENOENT)
+ continue;
+ p_err("can't get map by id (%u): %s",
+ id, strerror(errno));
+ return -1;
+ }
+
+ err = bpf_obj_get_info_by_fd(fd, info, &info_len);
+ if (err) {
+ p_err("can't get map info: %s", strerror(errno));
+ close(fd);
+ return -1;
+ }
+
+ if (info->type == BPF_MAP_TYPE_STRUCT_OPS &&
+ (!name || !strcmp(name, info->name))) {
+ *res_fd = fd;
+ return 1;
+ }
+ close(fd);
+ }
+}
+
+static int cmd_retval(const struct res *res, bool must_have_one_map)
+{
+ if (res->nr_errs || (!res->nr_maps && must_have_one_map))
+ return -1;
+
+ return 0;
+}
+
+/* "data" is the work_func private storage */
+typedef int (*work_func)(int fd, const struct bpf_map_info *info, void *data,
+ struct json_writer *wtr);
+
+/* Find all struct_ops map in the system.
+ * Filter out by "name" (if specified).
+ * Then call "func(fd, info, data, wtr)" on each struct_ops map found.
+ */
+static struct res do_search(const char *name, work_func func, void *data,
+ struct json_writer *wtr)
+{
+ struct bpf_map_info *info;
+ struct res res = {};
+ __u32 info_len;
+ int fd, err;
+
+ info = map_info_alloc(&info_len);
+ if (!info) {
+ res.nr_errs++;
+ return res;
+ }
+
+ if (wtr)
+ jsonw_start_array(wtr);
+ while ((err = get_next_struct_ops_map(name, &fd, info, info_len)) == 1) {
+ res.nr_maps++;
+ err = func(fd, info, data, wtr);
+ if (err)
+ res.nr_errs++;
+ close(fd);
+ }
+ if (wtr)
+ jsonw_end_array(wtr);
+
+ if (err)
+ res.nr_errs++;
+
+ if (!wtr && name && !res.nr_errs && !res.nr_maps)
+ /* It is not printing empty [].
+ * Thus, needs to specifically say nothing found
+ * for "name" here.
+ */
+ p_err("no struct_ops found for %s", name);
+ else if (!wtr && json_output && !res.nr_errs)
+ /* The "func()" above is not writing any json (i.e. !wtr
+ * test here).
+ *
+ * However, "-j" is enabled and there is no errs here,
+ * so call json_null() as the current convention of
+ * other cmds.
+ */
+ jsonw_null(json_wtr);
+
+ free(info);
+ return res;
+}
+
+static struct res do_one_id(const char *id_str, work_func func, void *data,
+ struct json_writer *wtr)
+{
+ struct bpf_map_info *info;
+ struct res res = {};
+ unsigned long id;
+ __u32 info_len;
+ char *endptr;
+ int fd;
+
+ id = strtoul(id_str, &endptr, 0);
+ if (*endptr || !id || id > UINT32_MAX) {
+ p_err("invalid id %s", id_str);
+ res.nr_errs++;
+ return res;
+ }
+
+ fd = bpf_map_get_fd_by_id(id);
+ if (fd == -1) {
+ p_err("can't get map by id (%lu): %s", id, strerror(errno));
+ res.nr_errs++;
+ return res;
+ }
+
+ info = map_info_alloc(&info_len);
+ if (!info) {
+ res.nr_errs++;
+ goto done;
+ }
+
+ if (bpf_obj_get_info_by_fd(fd, info, &info_len)) {
+ p_err("can't get map info: %s", strerror(errno));
+ res.nr_errs++;
+ goto done;
+ }
+
+ if (info->type != BPF_MAP_TYPE_STRUCT_OPS) {
+ p_err("%s id %u is not a struct_ops map", info->name, info->id);
+ res.nr_errs++;
+ goto done;
+ }
+
+ res.nr_maps++;
+
+ if (func(fd, info, data, wtr))
+ res.nr_errs++;
+ else if (!wtr && json_output)
+ /* The "func()" above is not writing any json (i.e. !wtr
+ * test here).
+ *
+ * However, "-j" is enabled and there is no errs here,
+ * so call json_null() as the current convention of
+ * other cmds.
+ */
+ jsonw_null(json_wtr);
+
+done:
+ free(info);
+ close(fd);
+
+ return res;
+}
+
+static struct res do_work_on_struct_ops(const char *search_type,
+ const char *search_term,
+ work_func func, void *data,
+ struct json_writer *wtr)
+{
+ if (search_type) {
+ if (is_prefix(search_type, "id"))
+ return do_one_id(search_term, func, data, wtr);
+ else if (!is_prefix(search_type, "name"))
+ usage();
+ }
+
+ return do_search(search_term, func, data, wtr);
+}
+
+static int __do_show(int fd, const struct bpf_map_info *info, void *data,
+ struct json_writer *wtr)
+{
+ if (wtr) {
+ jsonw_start_object(wtr);
+ jsonw_uint_field(wtr, "id", info->id);
+ jsonw_string_field(wtr, "name", info->name);
+ jsonw_string_field(wtr, "kernel_struct_ops",
+ get_kern_struct_ops_name(info));
+ jsonw_end_object(wtr);
+ } else {
+ printf("%u: %-15s %-32s\n", info->id, info->name,
+ get_kern_struct_ops_name(info));
+ }
+
+ return 0;
+}
+
+static int do_show(int argc, char **argv)
+{
+ const char *search_type = NULL, *search_term = NULL;
+ struct res res;
+
+ if (argc && argc != 2)
+ usage();
+
+ if (argc == 2) {
+ search_type = GET_ARG();
+ search_term = GET_ARG();
+ }
+
+ res = do_work_on_struct_ops(search_type, search_term, __do_show,
+ NULL, json_wtr);
+
+ return cmd_retval(&res, !!search_term);
+}
+
+static int __do_dump(int fd, const struct bpf_map_info *info, void *data,
+ struct json_writer *wtr)
+{
+ struct btf_dumper *d = (struct btf_dumper *)data;
+ const struct btf_type *struct_ops_type;
+ const struct btf *kern_btf = d->btf;
+ const char *struct_ops_name;
+ int zero = 0;
+ void *value;
+
+ /* note: d->jw == wtr */
+
+ kern_btf = d->btf;
+
+ /* The kernel supporting BPF_MAP_TYPE_STRUCT_OPS must have
+ * btf_vmlinux_value_type_id.
+ */
+ struct_ops_type = btf__type_by_id(kern_btf,
+ info->btf_vmlinux_value_type_id);
+ struct_ops_name = btf__name_by_offset(kern_btf,
+ struct_ops_type->name_off);
+ value = calloc(1, info->value_size);
+ if (!value) {
+ p_err("mem alloc failed");
+ return -1;
+ }
+
+ if (bpf_map_lookup_elem(fd, &zero, value)) {
+ p_err("can't lookup struct_ops map %s id %u",
+ info->name, info->id);
+ free(value);
+ return -1;
+ }
+
+ jsonw_start_object(wtr);
+ jsonw_name(wtr, "bpf_map_info");
+ btf_dumper_type(d, map_info_type_id, (void *)info);
+ jsonw_end_object(wtr);
+
+ jsonw_start_object(wtr);
+ jsonw_name(wtr, struct_ops_name);
+ btf_dumper_type(d, info->btf_vmlinux_value_type_id, value);
+ jsonw_end_object(wtr);
+
+ free(value);
+
+ return 0;
+}
+
+static int do_dump(int argc, char **argv)
+{
+ const char *search_type = NULL, *search_term = NULL;
+ json_writer_t *wtr = json_wtr;
+ const struct btf *kern_btf;
+ struct btf_dumper d = {};
+ struct res res;
+
+ if (argc && argc != 2)
+ usage();
+
+ if (argc == 2) {
+ search_type = GET_ARG();
+ search_term = GET_ARG();
+ }
+
+ kern_btf = get_btf_vmlinux();
+ if (IS_ERR(kern_btf))
+ return -1;
+
+ if (!json_output) {
+ wtr = jsonw_new(stdout);
+ if (!wtr) {
+ p_err("can't create json writer");
+ return -1;
+ }
+ jsonw_pretty(wtr, true);
+ }
+
+ d.btf = kern_btf;
+ d.jw = wtr;
+ d.is_plain_text = !json_output;
+ d.prog_id_as_func_ptr = true;
+
+ res = do_work_on_struct_ops(search_type, search_term, __do_dump, &d,
+ wtr);
+
+ if (!json_output)
+ jsonw_destroy(&wtr);
+
+ return cmd_retval(&res, !!search_term);
+}
+
+static int __do_unregister(int fd, const struct bpf_map_info *info, void *data,
+ struct json_writer *wtr)
+{
+ int zero = 0;
+
+ if (bpf_map_delete_elem(fd, &zero)) {
+ p_err("can't unload %s %s id %u: %s",
+ get_kern_struct_ops_name(info), info->name,
+ info->id, strerror(errno));
+ return -1;
+ }
+
+ p_info("Unregistered %s %s id %u",
+ get_kern_struct_ops_name(info), info->name,
+ info->id);
+
+ return 0;
+}
+
+static int do_unregister(int argc, char **argv)
+{
+ const char *search_type, *search_term;
+ struct res res;
+
+ if (argc != 2)
+ usage();
+
+ search_type = GET_ARG();
+ search_term = GET_ARG();
+
+ res = do_work_on_struct_ops(search_type, search_term,
+ __do_unregister, NULL, NULL);
+
+ return cmd_retval(&res, true);
+}
+
+static int do_register(int argc, char **argv)
+{
+ const struct bpf_map_def *def;
+ struct bpf_map_info info = {};
+ __u32 info_len = sizeof(info);
+ int nr_errs = 0, nr_maps = 0;
+ struct bpf_object *obj;
+ struct bpf_link *link;
+ struct bpf_map *map;
+ const char *file;
+
+ if (argc != 1)
+ usage();
+
+ file = GET_ARG();
+
+ obj = bpf_object__open(file);
+ if (IS_ERR_OR_NULL(obj))
+ return -1;
+
+ set_max_rlimit();
+
+ if (bpf_object__load(obj)) {
+ bpf_object__close(obj);
+ return -1;
+ }
+
+ bpf_object__for_each_map(map, obj) {
+ def = bpf_map__def(map);
+ if (def->type != BPF_MAP_TYPE_STRUCT_OPS)
+ continue;
+
+ link = bpf_map__attach_struct_ops(map);
+ if (IS_ERR(link)) {
+ p_err("can't register struct_ops %s: %s",
+ bpf_map__name(map),
+ strerror(-PTR_ERR(link)));
+ nr_errs++;
+ continue;
+ }
+ nr_maps++;
+
+ bpf_link__disconnect(link);
+ bpf_link__destroy(link);
+
+ if (!bpf_obj_get_info_by_fd(bpf_map__fd(map), &info,
+ &info_len))
+ p_info("Registered %s %s id %u",
+ get_kern_struct_ops_name(&info),
+ bpf_map__name(map),
+ info.id);
+ else
+ /* Not p_err. The struct_ops was attached
+ * successfully.
+ */
+ p_info("Registered %s but can't find id: %s",
+ bpf_map__name(map), strerror(errno));
+ }
+
+ bpf_object__close(obj);
+
+ if (nr_errs)
+ return -1;
+
+ if (!nr_maps) {
+ p_err("no struct_ops found in %s", file);
+ return -1;
+ }
+
+ if (json_output)
+ jsonw_null(json_wtr);
+
+ return 0;
+}
+
+static int do_help(int argc, char **argv)
+{
+ if (json_output) {
+ jsonw_null(json_wtr);
+ return 0;
+ }
+
+ fprintf(stderr,
+ "Usage: %s %s { show | list } [STRUCT_OPS_MAP]\n"
+ " %s %s dump [STRUCT_OPS_MAP]\n"
+ " %s %s register OBJ\n"
+ " %s %s unregister STRUCT_OPS_MAP\n"
+ " %s %s help\n"
+ "\n"
+ " OPTIONS := { {-j|--json} [{-p|--pretty}] }\n"
+ " STRUCT_OPS_MAP := [ id STRUCT_OPS_MAP_ID | name STRUCT_OPS_MAP_NAME ]\n",
+ bin_name, argv[-2], bin_name, argv[-2],
+ bin_name, argv[-2], bin_name, argv[-2],
+ bin_name, argv[-2]);
+
+ return 0;
+}
+
+static const struct cmd cmds[] = {
+ { "show", do_show },
+ { "list", do_show },
+ { "register", do_register },
+ { "unregister", do_unregister },
+ { "dump", do_dump },
+ { "help", do_help },
+ { 0 }
+};
+
+int do_struct_ops(int argc, char **argv)
+{
+ int err;
+
+ err = cmd_select(cmds, argc, argv, do_help);
+
+ btf__free(btf_vmlinux);
+ return err;
+}
diff --git a/tools/bpf/runqslower/runqslower.bpf.c b/tools/bpf/runqslower/runqslower.bpf.c
index 48a39f72fadf..1f18a409f044 100644
--- a/tools/bpf/runqslower/runqslower.bpf.c
+++ b/tools/bpf/runqslower/runqslower.bpf.c
@@ -5,9 +5,7 @@
#include "runqslower.h"
#define TASK_RUNNING 0
-
-#define BPF_F_INDEX_MASK 0xffffffffULL
-#define BPF_F_CURRENT_CPU BPF_F_INDEX_MASK
+#define BPF_F_CURRENT_CPU 0xffffffffULL
const volatile __u64 min_us = 0;
const volatile pid_t targ_pid = 0;
diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index 7ac0d8088565..ab8e89a7009c 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -67,7 +67,8 @@ FILES= \
test-llvm.bin \
test-llvm-version.bin \
test-libaio.bin \
- test-libzstd.bin
+ test-libzstd.bin \
+ test-clang-bpf-global-var.bin
FILES := $(addprefix $(OUTPUT),$(FILES))
@@ -75,6 +76,7 @@ CC ?= $(CROSS_COMPILE)gcc
CXX ?= $(CROSS_COMPILE)g++
PKG_CONFIG ?= $(CROSS_COMPILE)pkg-config
LLVM_CONFIG ?= llvm-config
+CLANG ?= clang
all: $(FILES)
@@ -321,6 +323,11 @@ $(OUTPUT)test-libaio.bin:
$(OUTPUT)test-libzstd.bin:
$(BUILD) -lzstd
+$(OUTPUT)test-clang-bpf-global-var.bin:
+ $(CLANG) -S -g -target bpf -o - $(patsubst %.bin,%.c,$(@F)) | \
+ grep BTF_KIND_VAR
+
+
###############################
clean:
diff --git a/tools/build/feature/test-clang-bpf-global-var.c b/tools/build/feature/test-clang-bpf-global-var.c
new file mode 100644
index 000000000000..221f1481d52e
--- /dev/null
+++ b/tools/build/feature/test-clang-bpf-global-var.c
@@ -0,0 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2020 Facebook
+
+volatile int global_value_for_test = 1;
diff --git a/tools/edid/1024x768.S b/tools/edid/1024x768.S
new file mode 100644
index 000000000000..4aed3f9ab88a
--- /dev/null
+++ b/tools/edid/1024x768.S
@@ -0,0 +1,43 @@
+/*
+ 1024x768.S: EDID data set for standard 1024x768 60 Hz monitor
+
+ Copyright (C) 2011 Carsten Emde <C.Emde@osadl.org>
+
+ This program is free software; you can redistribute it and/or
+ modify it under the terms of the GNU General Public License
+ as published by the Free Software Foundation; either version 2
+ of the License, or (at your option) any later version.
+
+ This program is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program; if not, write to the Free Software
+ Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
+*/
+
+/* EDID */
+#define VERSION 1
+#define REVISION 3
+
+/* Display */
+#define CLOCK 65000 /* kHz */
+#define XPIX 1024
+#define YPIX 768
+#define XY_RATIO XY_RATIO_4_3
+#define XBLANK 320
+#define YBLANK 38
+#define XOFFSET 8
+#define XPULSE 144
+#define YOFFSET 3
+#define YPULSE 6
+#define DPI 72
+#define VFREQ 60 /* Hz */
+#define TIMING_NAME "Linux XGA"
+#define ESTABLISHED_TIMING2_BITS 0x08 /* Bit 3 -> 1024x768 @60 Hz */
+#define HSYNC_POL 0
+#define VSYNC_POL 0
+
+#include "edid.S"
diff --git a/tools/edid/1280x1024.S b/tools/edid/1280x1024.S
new file mode 100644
index 000000000000..b26dd424cad7
--- /dev/null
+++ b/tools/edid/1280x1024.S
@@ -0,0 +1,43 @@
+/*
+ 1280x1024.S: EDID data set for standard 1280x1024 60 Hz monitor
+
+ Copyright (C) 2011 Carsten Emde <C.Emde@osadl.org>
+
+ This program is free software; you can redistribute it and/or
+ modify it under the terms of the GNU General Public License
+ as published by the Free Software Foundation; either version 2
+ of the License, or (at your option) any later version.
+
+ This program is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program; if not, write to the Free Software
+ Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
+*/
+
+/* EDID */
+#define VERSION 1
+#define REVISION 3
+
+/* Display */
+#define CLOCK 108000 /* kHz */
+#define XPIX 1280
+#define YPIX 1024
+#define XY_RATIO XY_RATIO_5_4
+#define XBLANK 408
+#define YBLANK 42
+#define XOFFSET 48
+#define XPULSE 112
+#define YOFFSET 1
+#define YPULSE 3
+#define DPI 72
+#define VFREQ 60 /* Hz */
+#define TIMING_NAME "Linux SXGA"
+/* No ESTABLISHED_TIMINGx_BITS */
+#define HSYNC_POL 1
+#define VSYNC_POL 1
+
+#include "edid.S"
diff --git a/tools/edid/1600x1200.S b/tools/edid/1600x1200.S
new file mode 100644
index 000000000000..0d091b282768
--- /dev/null
+++ b/tools/edid/1600x1200.S
@@ -0,0 +1,43 @@
+/*
+ 1600x1200.S: EDID data set for standard 1600x1200 60 Hz monitor
+
+ Copyright (C) 2013 Carsten Emde <C.Emde@osadl.org>
+
+ This program is free software; you can redistribute it and/or
+ modify it under the terms of the GNU General Public License
+ as published by the Free Software Foundation; either version 2
+ of the License, or (at your option) any later version.
+
+ This program is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program; if not, write to the Free Software
+ Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
+*/
+
+/* EDID */
+#define VERSION 1
+#define REVISION 3
+
+/* Display */
+#define CLOCK 162000 /* kHz */
+#define XPIX 1600
+#define YPIX 1200
+#define XY_RATIO XY_RATIO_4_3
+#define XBLANK 560
+#define YBLANK 50
+#define XOFFSET 64
+#define XPULSE 192
+#define YOFFSET 1
+#define YPULSE 3
+#define DPI 72
+#define VFREQ 60 /* Hz */
+#define TIMING_NAME "Linux UXGA"
+/* No ESTABLISHED_TIMINGx_BITS */
+#define HSYNC_POL 1
+#define VSYNC_POL 1
+
+#include "edid.S"
diff --git a/tools/edid/1680x1050.S b/tools/edid/1680x1050.S
new file mode 100644
index 000000000000..7dfed9a33eab
--- /dev/null
+++ b/tools/edid/1680x1050.S
@@ -0,0 +1,43 @@
+/*
+ 1680x1050.S: EDID data set for standard 1680x1050 60 Hz monitor
+
+ Copyright (C) 2012 Carsten Emde <C.Emde@osadl.org>
+
+ This program is free software; you can redistribute it and/or
+ modify it under the terms of the GNU General Public License
+ as published by the Free Software Foundation; either version 2
+ of the License, or (at your option) any later version.
+
+ This program is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program; if not, write to the Free Software
+ Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
+*/
+
+/* EDID */
+#define VERSION 1
+#define REVISION 3
+
+/* Display */
+#define CLOCK 146250 /* kHz */
+#define XPIX 1680
+#define YPIX 1050
+#define XY_RATIO XY_RATIO_16_10
+#define XBLANK 560
+#define YBLANK 39
+#define XOFFSET 104
+#define XPULSE 176
+#define YOFFSET 3
+#define YPULSE 6
+#define DPI 96
+#define VFREQ 60 /* Hz */
+#define TIMING_NAME "Linux WSXGA"
+/* No ESTABLISHED_TIMINGx_BITS */
+#define HSYNC_POL 1
+#define VSYNC_POL 1
+
+#include "edid.S"
diff --git a/tools/edid/1920x1080.S b/tools/edid/1920x1080.S
new file mode 100644
index 000000000000..d6ffbba28e95
--- /dev/null
+++ b/tools/edid/1920x1080.S
@@ -0,0 +1,43 @@
+/*
+ 1920x1080.S: EDID data set for standard 1920x1080 60 Hz monitor
+
+ Copyright (C) 2012 Carsten Emde <C.Emde@osadl.org>
+
+ This program is free software; you can redistribute it and/or
+ modify it under the terms of the GNU General Public License
+ as published by the Free Software Foundation; either version 2
+ of the License, or (at your option) any later version.
+
+ This program is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program; if not, write to the Free Software
+ Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
+*/
+
+/* EDID */
+#define VERSION 1
+#define REVISION 3
+
+/* Display */
+#define CLOCK 148500 /* kHz */
+#define XPIX 1920
+#define YPIX 1080
+#define XY_RATIO XY_RATIO_16_9
+#define XBLANK 280
+#define YBLANK 45
+#define XOFFSET 88
+#define XPULSE 44
+#define YOFFSET 4
+#define YPULSE 5
+#define DPI 96
+#define VFREQ 60 /* Hz */
+#define TIMING_NAME "Linux FHD"
+/* No ESTABLISHED_TIMINGx_BITS */
+#define HSYNC_POL 1
+#define VSYNC_POL 1
+
+#include "edid.S"
diff --git a/tools/edid/800x600.S b/tools/edid/800x600.S
new file mode 100644
index 000000000000..a5616588de08
--- /dev/null
+++ b/tools/edid/800x600.S
@@ -0,0 +1,40 @@
+/*
+ 800x600.S: EDID data set for standard 800x600 60 Hz monitor
+
+ Copyright (C) 2011 Carsten Emde <C.Emde@osadl.org>
+ Copyright (C) 2014 Linaro Limited
+
+ This program is free software; you can redistribute it and/or
+ modify it under the terms of the GNU General Public License
+ as published by the Free Software Foundation; either version 2
+ of the License, or (at your option) any later version.
+
+ This program is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU General Public License for more details.
+*/
+
+/* EDID */
+#define VERSION 1
+#define REVISION 3
+
+/* Display */
+#define CLOCK 40000 /* kHz */
+#define XPIX 800
+#define YPIX 600
+#define XY_RATIO XY_RATIO_4_3
+#define XBLANK 256
+#define YBLANK 28
+#define XOFFSET 40
+#define XPULSE 128
+#define YOFFSET 1
+#define YPULSE 4
+#define DPI 72
+#define VFREQ 60 /* Hz */
+#define TIMING_NAME "Linux SVGA"
+#define ESTABLISHED_TIMING1_BITS 0x01 /* Bit 0: 800x600 @ 60Hz */
+#define HSYNC_POL 1
+#define VSYNC_POL 1
+
+#include "edid.S"
diff --git a/tools/edid/Makefile b/tools/edid/Makefile
new file mode 100644
index 000000000000..85a927dfab02
--- /dev/null
+++ b/tools/edid/Makefile
@@ -0,0 +1,37 @@
+
+SOURCES := $(wildcard [0-9]*x[0-9]*.S)
+
+BIN := $(patsubst %.S, %.bin, $(SOURCES))
+
+IHEX := $(patsubst %.S, %.bin.ihex, $(SOURCES))
+
+CODE := $(patsubst %.S, %.c, $(SOURCES))
+
+all: $(BIN) $(IHEX) $(CODE)
+
+clean:
+ @rm -f *.o *.bin.ihex *.bin *.c
+
+%.o: %.S
+ @cc -c $^
+
+%.bin.nocrc: %.o
+ @objcopy -Obinary $^ $@
+
+%.crc: %.bin.nocrc
+ @list=$$(for i in `seq 1 127`; do head -c$$i $^ | tail -c1 \
+ | hexdump -v -e '/1 "%02X+"'; done); \
+ echo "ibase=16;100-($${list%?})%100" | bc >$@
+
+%.p: %.crc %.S
+ @cc -c -DCRC="$$(cat $*.crc)" -o $@ $*.S
+
+%.bin: %.p
+ @objcopy -Obinary $^ $@
+
+%.bin.ihex: %.p
+ @objcopy -Oihex $^ $@
+ @dos2unix $@ 2>/dev/null
+
+%.c: %.bin
+ @echo "{" >$@; hexdump -f hex $^ >>$@; echo "};" >>$@
diff --git a/tools/edid/edid.S b/tools/edid/edid.S
new file mode 100644
index 000000000000..c3d13815526d
--- /dev/null
+++ b/tools/edid/edid.S
@@ -0,0 +1,274 @@
+/*
+ edid.S: EDID data template
+
+ Copyright (C) 2012 Carsten Emde <C.Emde@osadl.org>
+
+ This program is free software; you can redistribute it and/or
+ modify it under the terms of the GNU General Public License
+ as published by the Free Software Foundation; either version 2
+ of the License, or (at your option) any later version.
+
+ This program is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program; if not, write to the Free Software
+ Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
+*/
+
+
+/* Manufacturer */
+#define MFG_LNX1 'L'
+#define MFG_LNX2 'N'
+#define MFG_LNX3 'X'
+#define SERIAL 0
+#define YEAR 2012
+#define WEEK 5
+
+/* EDID 1.3 standard definitions */
+#define XY_RATIO_16_10 0b00
+#define XY_RATIO_4_3 0b01
+#define XY_RATIO_5_4 0b10
+#define XY_RATIO_16_9 0b11
+
+/* Provide defaults for the timing bits */
+#ifndef ESTABLISHED_TIMING1_BITS
+#define ESTABLISHED_TIMING1_BITS 0x00
+#endif
+#ifndef ESTABLISHED_TIMING2_BITS
+#define ESTABLISHED_TIMING2_BITS 0x00
+#endif
+#ifndef ESTABLISHED_TIMING3_BITS
+#define ESTABLISHED_TIMING3_BITS 0x00
+#endif
+
+#define mfgname2id(v1,v2,v3) \
+ ((((v1-'@')&0x1f)<<10)+(((v2-'@')&0x1f)<<5)+((v3-'@')&0x1f))
+#define swap16(v1) ((v1>>8)+((v1&0xff)<<8))
+#define lsbs2(v1,v2) (((v1&0x0f)<<4)+(v2&0x0f))
+#define msbs2(v1,v2) ((((v1>>8)&0x0f)<<4)+((v2>>8)&0x0f))
+#define msbs4(v1,v2,v3,v4) \
+ ((((v1>>8)&0x03)<<6)+(((v2>>8)&0x03)<<4)+\
+ (((v3>>4)&0x03)<<2)+((v4>>4)&0x03))
+#define pixdpi2mm(pix,dpi) ((pix*25)/dpi)
+#define xsize pixdpi2mm(XPIX,DPI)
+#define ysize pixdpi2mm(YPIX,DPI)
+
+ .data
+
+/* Fixed header pattern */
+header: .byte 0x00,0xff,0xff,0xff,0xff,0xff,0xff,0x00
+
+mfg_id: .hword swap16(mfgname2id(MFG_LNX1, MFG_LNX2, MFG_LNX3))
+
+prod_code: .hword 0
+
+/* Serial number. 32 bits, little endian. */
+serial_number: .long SERIAL
+
+/* Week of manufacture */
+week: .byte WEEK
+
+/* Year of manufacture, less 1990. (1990-2245)
+ If week=255, it is the model year instead */
+year: .byte YEAR-1990
+
+version: .byte VERSION /* EDID version, usually 1 (for 1.3) */
+revision: .byte REVISION /* EDID revision, usually 3 (for 1.3) */
+
+/* If Bit 7=1 Digital input. If set, the following bit definitions apply:
+ Bits 6-1 Reserved, must be 0
+ Bit 0 Signal is compatible with VESA DFP 1.x TMDS CRGB,
+ 1 pixel per clock, up to 8 bits per color, MSB aligned,
+ If Bit 7=0 Analog input. If clear, the following bit definitions apply:
+ Bits 6-5 Video white and sync levels, relative to blank
+ 00=+0.7/-0.3 V; 01=+0.714/-0.286 V;
+ 10=+1.0/-0.4 V; 11=+0.7/0 V
+ Bit 4 Blank-to-black setup (pedestal) expected
+ Bit 3 Separate sync supported
+ Bit 2 Composite sync (on HSync) supported
+ Bit 1 Sync on green supported
+ Bit 0 VSync pulse must be serrated when somposite or
+ sync-on-green is used. */
+video_parms: .byte 0x6d
+
+/* Maximum horizontal image size, in centimetres
+ (max 292 cm/115 in at 16:9 aspect ratio) */
+max_hor_size: .byte xsize/10
+
+/* Maximum vertical image size, in centimetres.
+ If either byte is 0, undefined (e.g. projector) */
+max_vert_size: .byte ysize/10
+
+/* Display gamma, minus 1, times 100 (range 1.00-3.5 */
+gamma: .byte 120
+
+/* Bit 7 DPMS standby supported
+ Bit 6 DPMS suspend supported
+ Bit 5 DPMS active-off supported
+ Bits 4-3 Display type: 00=monochrome; 01=RGB colour;
+ 10=non-RGB multicolour; 11=undefined
+ Bit 2 Standard sRGB colour space. Bytes 25-34 must contain
+ sRGB standard values.
+ Bit 1 Preferred timing mode specified in descriptor block 1.
+ Bit 0 GTF supported with default parameter values. */
+dsp_features: .byte 0xea
+
+/* Chromaticity coordinates. */
+/* Red and green least-significant bits
+ Bits 7-6 Red x value least-significant 2 bits
+ Bits 5-4 Red y value least-significant 2 bits
+ Bits 3-2 Green x value lst-significant 2 bits
+ Bits 1-0 Green y value least-significant 2 bits */
+red_green_lsb: .byte 0x5e
+
+/* Blue and white least-significant 2 bits */
+blue_white_lsb: .byte 0xc0
+
+/* Red x value most significant 8 bits.
+ 0-255 encodes 0-0.996 (255/256); 0-0.999 (1023/1024) with lsbits */
+red_x_msb: .byte 0xa4
+
+/* Red y value most significant 8 bits */
+red_y_msb: .byte 0x59
+
+/* Green x and y value most significant 8 bits */
+green_x_y_msb: .byte 0x4a,0x98
+
+/* Blue x and y value most significant 8 bits */
+blue_x_y_msb: .byte 0x25,0x20
+
+/* Default white point x and y value most significant 8 bits */
+white_x_y_msb: .byte 0x50,0x54
+
+/* Established timings */
+/* Bit 7 720x400 @ 70 Hz
+ Bit 6 720x400 @ 88 Hz
+ Bit 5 640x480 @ 60 Hz
+ Bit 4 640x480 @ 67 Hz
+ Bit 3 640x480 @ 72 Hz
+ Bit 2 640x480 @ 75 Hz
+ Bit 1 800x600 @ 56 Hz
+ Bit 0 800x600 @ 60 Hz */
+estbl_timing1: .byte ESTABLISHED_TIMING1_BITS
+
+/* Bit 7 800x600 @ 72 Hz
+ Bit 6 800x600 @ 75 Hz
+ Bit 5 832x624 @ 75 Hz
+ Bit 4 1024x768 @ 87 Hz, interlaced (1024x768)
+ Bit 3 1024x768 @ 60 Hz
+ Bit 2 1024x768 @ 72 Hz
+ Bit 1 1024x768 @ 75 Hz
+ Bit 0 1280x1024 @ 75 Hz */
+estbl_timing2: .byte ESTABLISHED_TIMING2_BITS
+
+/* Bit 7 1152x870 @ 75 Hz (Apple Macintosh II)
+ Bits 6-0 Other manufacturer-specific display mod */
+estbl_timing3: .byte ESTABLISHED_TIMING3_BITS
+
+/* Standard timing */
+/* X resolution, less 31, divided by 8 (256-2288 pixels) */
+std_xres: .byte (XPIX/8)-31
+/* Y resolution, X:Y pixel ratio
+ Bits 7-6 X:Y pixel ratio: 00=16:10; 01=4:3; 10=5:4; 11=16:9.
+ Bits 5-0 Vertical frequency, less 60 (60-123 Hz) */
+std_vres: .byte (XY_RATIO<<6)+VFREQ-60
+ .fill 7,2,0x0101 /* Unused */
+
+descriptor1:
+/* Pixel clock in 10 kHz units. (0.-655.35 MHz, little-endian) */
+clock: .hword CLOCK/10
+
+/* Horizontal active pixels 8 lsbits (0-4095) */
+x_act_lsb: .byte XPIX&0xff
+/* Horizontal blanking pixels 8 lsbits (0-4095)
+ End of active to start of next active. */
+x_blk_lsb: .byte XBLANK&0xff
+/* Bits 7-4 Horizontal active pixels 4 msbits
+ Bits 3-0 Horizontal blanking pixels 4 msbits */
+x_msbs: .byte msbs2(XPIX,XBLANK)
+
+/* Vertical active lines 8 lsbits (0-4095) */
+y_act_lsb: .byte YPIX&0xff
+/* Vertical blanking lines 8 lsbits (0-4095) */
+y_blk_lsb: .byte YBLANK&0xff
+/* Bits 7-4 Vertical active lines 4 msbits
+ Bits 3-0 Vertical blanking lines 4 msbits */
+y_msbs: .byte msbs2(YPIX,YBLANK)
+
+/* Horizontal sync offset pixels 8 lsbits (0-1023) From blanking start */
+x_snc_off_lsb: .byte XOFFSET&0xff
+/* Horizontal sync pulse width pixels 8 lsbits (0-1023) */
+x_snc_pls_lsb: .byte XPULSE&0xff
+/* Bits 7-4 Vertical sync offset lines 4 lsbits (0-63)
+ Bits 3-0 Vertical sync pulse width lines 4 lsbits (0-63) */
+y_snc_lsb: .byte lsbs2(YOFFSET, YPULSE)
+/* Bits 7-6 Horizontal sync offset pixels 2 msbits
+ Bits 5-4 Horizontal sync pulse width pixels 2 msbits
+ Bits 3-2 Vertical sync offset lines 2 msbits
+ Bits 1-0 Vertical sync pulse width lines 2 msbits */
+xy_snc_msbs: .byte msbs4(XOFFSET,XPULSE,YOFFSET,YPULSE)
+
+/* Horizontal display size, mm, 8 lsbits (0-4095 mm, 161 in) */
+x_dsp_size: .byte xsize&0xff
+
+/* Vertical display size, mm, 8 lsbits (0-4095 mm, 161 in) */
+y_dsp_size: .byte ysize&0xff
+
+/* Bits 7-4 Horizontal display size, mm, 4 msbits
+ Bits 3-0 Vertical display size, mm, 4 msbits */
+dsp_size_mbsb: .byte msbs2(xsize,ysize)
+
+/* Horizontal border pixels (each side; total is twice this) */
+x_border: .byte 0
+/* Vertical border lines (each side; total is twice this) */
+y_border: .byte 0
+
+/* Bit 7 Interlaced
+ Bits 6-5 Stereo mode: 00=No stereo; other values depend on bit 0:
+ Bit 0=0: 01=Field sequential, sync=1 during right; 10=similar,
+ sync=1 during left; 11=4-way interleaved stereo
+ Bit 0=1 2-way interleaved stereo: 01=Right image on even lines;
+ 10=Left image on even lines; 11=side-by-side
+ Bits 4-3 Sync type: 00=Analog composite; 01=Bipolar analog composite;
+ 10=Digital composite (on HSync); 11=Digital separate
+ Bit 2 If digital separate: Vertical sync polarity (1=positive)
+ Other types: VSync serrated (HSync during VSync)
+ Bit 1 If analog sync: Sync on all 3 RGB lines (else green only)
+ Digital: HSync polarity (1=positive)
+ Bit 0 2-way line-interleaved stereo, if bits 4-3 are not 00. */
+features: .byte 0x18+(VSYNC_POL<<2)+(HSYNC_POL<<1)
+
+descriptor2: .byte 0,0 /* Not a detailed timing descriptor */
+ .byte 0 /* Must be zero */
+ .byte 0xff /* Descriptor is monitor serial number (text) */
+ .byte 0 /* Must be zero */
+start1: .ascii "Linux #0"
+end1: .byte 0x0a /* End marker */
+ .fill 12-(end1-start1), 1, 0x20 /* Padded spaces */
+descriptor3: .byte 0,0 /* Not a detailed timing descriptor */
+ .byte 0 /* Must be zero */
+ .byte 0xfd /* Descriptor is monitor range limits */
+ .byte 0 /* Must be zero */
+start2: .byte VFREQ-1 /* Minimum vertical field rate (1-255 Hz) */
+ .byte VFREQ+1 /* Maximum vertical field rate (1-255 Hz) */
+ .byte (CLOCK/(XPIX+XBLANK))-1 /* Minimum horizontal line rate
+ (1-255 kHz) */
+ .byte (CLOCK/(XPIX+XBLANK))+1 /* Maximum horizontal line rate
+ (1-255 kHz) */
+ .byte (CLOCK/10000)+1 /* Maximum pixel clock rate, rounded up
+ to 10 MHz multiple (10-2550 MHz) */
+ .byte 0 /* No extended timing information type */
+end2: .byte 0x0a /* End marker */
+ .fill 12-(end2-start2), 1, 0x20 /* Padded spaces */
+descriptor4: .byte 0,0 /* Not a detailed timing descriptor */
+ .byte 0 /* Must be zero */
+ .byte 0xfc /* Descriptor is text */
+ .byte 0 /* Must be zero */
+start3: .ascii TIMING_NAME
+end3: .byte 0x0a /* End marker */
+ .fill 12-(end3-start3), 1, 0x20 /* Padded spaces */
+extensions: .byte 0 /* Number of extensions to follow */
+checksum: .byte CRC /* Sum of all bytes must be 0 */
diff --git a/tools/edid/hex b/tools/edid/hex
new file mode 100644
index 000000000000..8873ebb618af
--- /dev/null
+++ b/tools/edid/hex
@@ -0,0 +1 @@
+"\t" 8/1 "0x%02x, " "\n"
diff --git a/tools/include/linux/irqflags.h b/tools/include/linux/irqflags.h
index e734da3e5b33..67e01bbadbfe 100644
--- a/tools/include/linux/irqflags.h
+++ b/tools/include/linux/irqflags.h
@@ -2,12 +2,12 @@
#ifndef _LIBLOCKDEP_LINUX_TRACE_IRQFLAGS_H_
#define _LIBLOCKDEP_LINUX_TRACE_IRQFLAGS_H_
-# define trace_hardirq_context(p) 0
-# define trace_softirq_context(p) 0
-# define trace_hardirqs_enabled(p) 0
-# define trace_softirqs_enabled(p) 0
-# define trace_hardirq_enter() do { } while (0)
-# define trace_hardirq_exit() do { } while (0)
+# define lockdep_hardirq_context(p) 0
+# define lockdep_softirq_context(p) 0
+# define lockdep_hardirqs_enabled(p) 0
+# define lockdep_softirqs_enabled(p) 0
+# define lockdep_hardirq_enter() do { } while (0)
+# define lockdep_hardirq_exit() do { } while (0)
# define lockdep_softirq_enter() do { } while (0)
# define lockdep_softirq_exit() do { } while (0)
# define INIT_TRACE_IRQFLAGS
diff --git a/tools/include/uapi/asm-generic/mman-common.h b/tools/include/uapi/asm-generic/mman-common.h
index c160a5354eb6..f94f65d429be 100644
--- a/tools/include/uapi/asm-generic/mman-common.h
+++ b/tools/include/uapi/asm-generic/mman-common.h
@@ -11,6 +11,8 @@
#define PROT_WRITE 0x2 /* page can be written */
#define PROT_EXEC 0x4 /* page can be executed */
#define PROT_SEM 0x8 /* page may be used for atomic ops */
+/* 0x10 reserved for arch-specific use */
+/* 0x20 reserved for arch-specific use */
#define PROT_NONE 0x0 /* page can not be accessed */
#define PROT_GROWSDOWN 0x01000000 /* mprotect flag: extend change to start of growsdown vma */
#define PROT_GROWSUP 0x02000000 /* mprotect flag: extend change to end of growsup vma */
diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
index 1fc8faa6e973..3a3201e4618e 100644
--- a/tools/include/uapi/asm-generic/unistd.h
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -851,8 +851,13 @@ __SYSCALL(__NR_pidfd_open, sys_pidfd_open)
__SYSCALL(__NR_clone3, sys_clone3)
#endif
+#define __NR_openat2 437
+__SYSCALL(__NR_openat2, sys_openat2)
+#define __NR_pidfd_getfd 438
+__SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd)
+
#undef __NR_syscalls
-#define __NR_syscalls 436
+#define __NR_syscalls 439
/*
* 32 bit systems traditionally used different
diff --git a/tools/include/uapi/asm/errno.h b/tools/include/uapi/asm/errno.h
index ce3c5945a1c4..637189ec1ab9 100644
--- a/tools/include/uapi/asm/errno.h
+++ b/tools/include/uapi/asm/errno.h
@@ -1,18 +1,18 @@
/* SPDX-License-Identifier: GPL-2.0 */
#if defined(__i386__) || defined(__x86_64__)
-#include "../../arch/x86/include/uapi/asm/errno.h"
+#include "../../../arch/x86/include/uapi/asm/errno.h"
#elif defined(__powerpc__)
-#include "../../arch/powerpc/include/uapi/asm/errno.h"
+#include "../../../arch/powerpc/include/uapi/asm/errno.h"
#elif defined(__sparc__)
-#include "../../arch/sparc/include/uapi/asm/errno.h"
+#include "../../../arch/sparc/include/uapi/asm/errno.h"
#elif defined(__alpha__)
-#include "../../arch/alpha/include/uapi/asm/errno.h"
+#include "../../../arch/alpha/include/uapi/asm/errno.h"
#elif defined(__mips__)
-#include "../../arch/mips/include/uapi/asm/errno.h"
+#include "../../../arch/mips/include/uapi/asm/errno.h"
#elif defined(__ia64__)
-#include "../../arch/ia64/include/uapi/asm/errno.h"
+#include "../../../arch/ia64/include/uapi/asm/errno.h"
#elif defined(__xtensa__)
-#include "../../arch/xtensa/include/uapi/asm/errno.h"
+#include "../../../arch/xtensa/include/uapi/asm/errno.h"
#else
#include <asm-generic/errno.h>
#endif
diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h
index 5400d7e057f1..829c0a48577f 100644
--- a/tools/include/uapi/drm/i915_drm.h
+++ b/tools/include/uapi/drm/i915_drm.h
@@ -395,6 +395,7 @@ typedef struct _drm_i915_sarea {
#define DRM_IOCTL_I915_GEM_PWRITE DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_PWRITE, struct drm_i915_gem_pwrite)
#define DRM_IOCTL_I915_GEM_MMAP DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_MMAP, struct drm_i915_gem_mmap)
#define DRM_IOCTL_I915_GEM_MMAP_GTT DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_MMAP_GTT, struct drm_i915_gem_mmap_gtt)
+#define DRM_IOCTL_I915_GEM_MMAP_OFFSET DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_MMAP_GTT, struct drm_i915_gem_mmap_offset)
#define DRM_IOCTL_I915_GEM_SET_DOMAIN DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_SET_DOMAIN, struct drm_i915_gem_set_domain)
#define DRM_IOCTL_I915_GEM_SW_FINISH DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_SW_FINISH, struct drm_i915_gem_sw_finish)
#define DRM_IOCTL_I915_GEM_SET_TILING DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_SET_TILING, struct drm_i915_gem_set_tiling)
@@ -793,6 +794,37 @@ struct drm_i915_gem_mmap_gtt {
__u64 offset;
};
+struct drm_i915_gem_mmap_offset {
+ /** Handle for the object being mapped. */
+ __u32 handle;
+ __u32 pad;
+ /**
+ * Fake offset to use for subsequent mmap call
+ *
+ * This is a fixed-size type for 32/64 compatibility.
+ */
+ __u64 offset;
+
+ /**
+ * Flags for extended behaviour.
+ *
+ * It is mandatory that one of the MMAP_OFFSET types
+ * (GTT, WC, WB, UC, etc) should be included.
+ */
+ __u64 flags;
+#define I915_MMAP_OFFSET_GTT 0
+#define I915_MMAP_OFFSET_WC 1
+#define I915_MMAP_OFFSET_WB 2
+#define I915_MMAP_OFFSET_UC 3
+
+ /*
+ * Zero-terminated chain of extensions.
+ *
+ * No current extensions defined; mbz.
+ */
+ __u64 extensions;
+};
+
struct drm_i915_gem_set_domain {
/** Handle for the object */
__u32 handle;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index f1d74a2bd234..2e29a671d67e 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -73,7 +73,7 @@ struct bpf_insn {
/* Key of an a BPF_MAP_TYPE_LPM_TRIE entry */
struct bpf_lpm_trie_key {
__u32 prefixlen; /* up to 32 for AF_INET, 128 for AF_INET6 */
- __u8 data[0]; /* Arbitrary size */
+ __u8 data[]; /* Arbitrary size */
};
struct bpf_cgroup_storage_key {
@@ -111,6 +111,8 @@ enum bpf_cmd {
BPF_MAP_LOOKUP_AND_DELETE_BATCH,
BPF_MAP_UPDATE_BATCH,
BPF_MAP_DELETE_BATCH,
+ BPF_LINK_CREATE,
+ BPF_LINK_UPDATE,
};
enum bpf_map_type {
@@ -181,6 +183,7 @@ enum bpf_prog_type {
BPF_PROG_TYPE_TRACING,
BPF_PROG_TYPE_STRUCT_OPS,
BPF_PROG_TYPE_EXT,
+ BPF_PROG_TYPE_LSM,
};
enum bpf_attach_type {
@@ -210,6 +213,8 @@ enum bpf_attach_type {
BPF_TRACE_RAW_TP,
BPF_TRACE_FENTRY,
BPF_TRACE_FEXIT,
+ BPF_MODIFY_RETURN,
+ BPF_LSM_MAC,
__MAX_BPF_ATTACH_TYPE
};
@@ -325,44 +330,46 @@ enum bpf_attach_type {
#define BPF_PSEUDO_CALL 1
/* flags for BPF_MAP_UPDATE_ELEM command */
-#define BPF_ANY 0 /* create new element or update existing */
-#define BPF_NOEXIST 1 /* create new element if it didn't exist */
-#define BPF_EXIST 2 /* update existing element */
-#define BPF_F_LOCK 4 /* spin_lock-ed map_lookup/map_update */
+enum {
+ BPF_ANY = 0, /* create new element or update existing */
+ BPF_NOEXIST = 1, /* create new element if it didn't exist */
+ BPF_EXIST = 2, /* update existing element */
+ BPF_F_LOCK = 4, /* spin_lock-ed map_lookup/map_update */
+};
/* flags for BPF_MAP_CREATE command */
-#define BPF_F_NO_PREALLOC (1U << 0)
+enum {
+ BPF_F_NO_PREALLOC = (1U << 0),
/* Instead of having one common LRU list in the
* BPF_MAP_TYPE_LRU_[PERCPU_]HASH map, use a percpu LRU list
* which can scale and perform better.
* Note, the LRU nodes (including free nodes) cannot be moved
* across different LRU lists.
*/
-#define BPF_F_NO_COMMON_LRU (1U << 1)
+ BPF_F_NO_COMMON_LRU = (1U << 1),
/* Specify numa node during map creation */
-#define BPF_F_NUMA_NODE (1U << 2)
-
-#define BPF_OBJ_NAME_LEN 16U
+ BPF_F_NUMA_NODE = (1U << 2),
/* Flags for accessing BPF object from syscall side. */
-#define BPF_F_RDONLY (1U << 3)
-#define BPF_F_WRONLY (1U << 4)
+ BPF_F_RDONLY = (1U << 3),
+ BPF_F_WRONLY = (1U << 4),
/* Flag for stack_map, store build_id+offset instead of pointer */
-#define BPF_F_STACK_BUILD_ID (1U << 5)
+ BPF_F_STACK_BUILD_ID = (1U << 5),
/* Zero-initialize hash function seed. This should only be used for testing. */
-#define BPF_F_ZERO_SEED (1U << 6)
+ BPF_F_ZERO_SEED = (1U << 6),
/* Flags for accessing BPF object from program side. */
-#define BPF_F_RDONLY_PROG (1U << 7)
-#define BPF_F_WRONLY_PROG (1U << 8)
+ BPF_F_RDONLY_PROG = (1U << 7),
+ BPF_F_WRONLY_PROG = (1U << 8),
/* Clone map from listener for newly accepted socket */
-#define BPF_F_CLONE (1U << 9)
+ BPF_F_CLONE = (1U << 9),
/* Enable memory-mapping BPF map */
-#define BPF_F_MMAPABLE (1U << 10)
+ BPF_F_MMAPABLE = (1U << 10),
+};
/* Flags for BPF_PROG_QUERY. */
@@ -391,6 +398,8 @@ struct bpf_stack_build_id {
};
};
+#define BPF_OBJ_NAME_LEN 16U
+
union bpf_attr {
struct { /* anonymous struct used by BPF_MAP_CREATE command */
__u32 map_type; /* one of enum bpf_map_type */
@@ -534,7 +543,7 @@ union bpf_attr {
__u32 prog_cnt;
} query;
- struct {
+ struct { /* anonymous struct used by BPF_RAW_TRACEPOINT_OPEN command */
__u64 name;
__u32 prog_fd;
} raw_tracepoint;
@@ -562,6 +571,24 @@ union bpf_attr {
__u64 probe_offset; /* output: probe_offset */
__u64 probe_addr; /* output: probe_addr */
} task_fd_query;
+
+ struct { /* struct used by BPF_LINK_CREATE command */
+ __u32 prog_fd; /* eBPF program to attach */
+ __u32 target_fd; /* object to attach to */
+ __u32 attach_type; /* attach type */
+ __u32 flags; /* extra flags */
+ } link_create;
+
+ struct { /* struct used by BPF_LINK_UPDATE command */
+ __u32 link_fd; /* link fd */
+ /* new program fd to update link with */
+ __u32 new_prog_fd;
+ __u32 flags; /* extra flags */
+ /* expected link's program fd; is specified only if
+ * BPF_F_REPLACE flag is set in flags */
+ __u32 old_prog_fd;
+ } link_update;
+
} __attribute__((aligned(8)));
/* The description below is an attempt at providing documentation to eBPF
@@ -1045,9 +1072,9 @@ union bpf_attr {
* supports redirection to the egress interface, and accepts no
* flag at all.
*
- * The same effect can be attained with the more generic
- * **bpf_redirect_map**\ (), which requires specific maps to be
- * used but offers better performance.
+ * The same effect can also be attained with the more generic
+ * **bpf_redirect_map**\ (), which uses a BPF map to store the
+ * redirect target instead of providing it directly to the helper.
* Return
* For XDP, the helper returns **XDP_REDIRECT** on success or
* **XDP_ABORTED** on error. For other program types, the values
@@ -1611,13 +1638,11 @@ union bpf_attr {
* the caller. Any higher bits in the *flags* argument must be
* unset.
*
- * When used to redirect packets to net devices, this helper
- * provides a high performance increase over **bpf_redirect**\ ().
- * This is due to various implementation details of the underlying
- * mechanisms, one of which is the fact that **bpf_redirect_map**\
- * () tries to send packet as a "bulk" to the device.
+ * See also bpf_redirect(), which only supports redirecting to an
+ * ifindex, but doesn't require a map to do so.
* Return
- * **XDP_REDIRECT** on success, or **XDP_ABORTED** on error.
+ * **XDP_REDIRECT** on success, or the value of the two lower bits
+ * of the **flags* argument on error.
*
* int bpf_sk_redirect_map(struct sk_buff *skb, struct bpf_map *map, u32 key, u64 flags)
* Description
@@ -2892,6 +2917,114 @@ union bpf_attr {
* Obtain the 64bit jiffies
* Return
* The 64 bit jiffies
+ *
+ * int bpf_read_branch_records(struct bpf_perf_event_data *ctx, void *buf, u32 size, u64 flags)
+ * Description
+ * For an eBPF program attached to a perf event, retrieve the
+ * branch records (struct perf_branch_entry) associated to *ctx*
+ * and store it in the buffer pointed by *buf* up to size
+ * *size* bytes.
+ * Return
+ * On success, number of bytes written to *buf*. On error, a
+ * negative value.
+ *
+ * The *flags* can be set to **BPF_F_GET_BRANCH_RECORDS_SIZE** to
+ * instead return the number of bytes required to store all the
+ * branch entries. If this flag is set, *buf* may be NULL.
+ *
+ * **-EINVAL** if arguments invalid or **size** not a multiple
+ * of sizeof(struct perf_branch_entry).
+ *
+ * **-ENOENT** if architecture does not support branch records.
+ *
+ * int bpf_get_ns_current_pid_tgid(u64 dev, u64 ino, struct bpf_pidns_info *nsdata, u32 size)
+ * Description
+ * Returns 0 on success, values for *pid* and *tgid* as seen from the current
+ * *namespace* will be returned in *nsdata*.
+ *
+ * On failure, the returned value is one of the following:
+ *
+ * **-EINVAL** if dev and inum supplied don't match dev_t and inode number
+ * with nsfs of current task, or if dev conversion to dev_t lost high bits.
+ *
+ * **-ENOENT** if pidns does not exists for the current task.
+ *
+ * int bpf_xdp_output(void *ctx, struct bpf_map *map, u64 flags, void *data, u64 size)
+ * Description
+ * Write raw *data* blob into a special BPF perf event held by
+ * *map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. This perf
+ * event must have the following attributes: **PERF_SAMPLE_RAW**
+ * as **sample_type**, **PERF_TYPE_SOFTWARE** as **type**, and
+ * **PERF_COUNT_SW_BPF_OUTPUT** as **config**.
+ *
+ * The *flags* are used to indicate the index in *map* for which
+ * the value must be put, masked with **BPF_F_INDEX_MASK**.
+ * Alternatively, *flags* can be set to **BPF_F_CURRENT_CPU**
+ * to indicate that the index of the current CPU core should be
+ * used.
+ *
+ * The value to write, of *size*, is passed through eBPF stack and
+ * pointed by *data*.
+ *
+ * *ctx* is a pointer to in-kernel struct xdp_buff.
+ *
+ * This helper is similar to **bpf_perf_eventoutput**\ () but
+ * restricted to raw_tracepoint bpf programs.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * u64 bpf_get_netns_cookie(void *ctx)
+ * Description
+ * Retrieve the cookie (generated by the kernel) of the network
+ * namespace the input *ctx* is associated with. The network
+ * namespace cookie remains stable for its lifetime and provides
+ * a global identifier that can be assumed unique. If *ctx* is
+ * NULL, then the helper returns the cookie for the initial
+ * network namespace. The cookie itself is very similar to that
+ * of bpf_get_socket_cookie() helper, but for network namespaces
+ * instead of sockets.
+ * Return
+ * A 8-byte long opaque number.
+ *
+ * u64 bpf_get_current_ancestor_cgroup_id(int ancestor_level)
+ * Description
+ * Return id of cgroup v2 that is ancestor of the cgroup associated
+ * with the current task at the *ancestor_level*. The root cgroup
+ * is at *ancestor_level* zero and each step down the hierarchy
+ * increments the level. If *ancestor_level* == level of cgroup
+ * associated with the current task, then return value will be the
+ * same as that of **bpf_get_current_cgroup_id**\ ().
+ *
+ * The helper is useful to implement policies based on cgroups
+ * that are upper in hierarchy than immediate cgroup associated
+ * with the current task.
+ *
+ * The format of returned id and helper limitations are same as in
+ * **bpf_get_current_cgroup_id**\ ().
+ * Return
+ * The id is returned or 0 in case the id could not be retrieved.
+ *
+ * int bpf_sk_assign(struct sk_buff *skb, struct bpf_sock *sk, u64 flags)
+ * Description
+ * Assign the *sk* to the *skb*. When combined with appropriate
+ * routing configuration to receive the packet towards the socket,
+ * will cause *skb* to be delivered to the specified socket.
+ * Subsequent redirection of *skb* via **bpf_redirect**\ (),
+ * **bpf_clone_redirect**\ () or other methods outside of BPF may
+ * interfere with successful delivery to the socket.
+ *
+ * This operation is only valid from TC ingress path.
+ *
+ * The *flags* argument must be zero.
+ * Return
+ * 0 on success, or a negative errno in case of failure.
+ *
+ * * **-EINVAL** Unsupported flags specified.
+ * * **-ENOENT** Socket is unavailable for assignment.
+ * * **-ENETUNREACH** Socket is unreachable (wrong netns).
+ * * **-EOPNOTSUPP** Unsupported operation, for example a
+ * call from outside of TC ingress.
+ * * **-ESOCKTNOSUPPORT** Socket type not supported (reuseport).
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
@@ -3012,7 +3145,13 @@ union bpf_attr {
FN(probe_read_kernel_str), \
FN(tcp_send_ack), \
FN(send_signal_thread), \
- FN(jiffies64),
+ FN(jiffies64), \
+ FN(read_branch_records), \
+ FN(get_ns_current_pid_tgid), \
+ FN(xdp_output), \
+ FN(get_netns_cookie), \
+ FN(get_current_ancestor_cgroup_id), \
+ FN(sk_assign),
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
* function eBPF program intends to call
@@ -3027,69 +3166,100 @@ enum bpf_func_id {
/* All flags used by eBPF helper functions, placed here. */
/* BPF_FUNC_skb_store_bytes flags. */
-#define BPF_F_RECOMPUTE_CSUM (1ULL << 0)
-#define BPF_F_INVALIDATE_HASH (1ULL << 1)
+enum {
+ BPF_F_RECOMPUTE_CSUM = (1ULL << 0),
+ BPF_F_INVALIDATE_HASH = (1ULL << 1),
+};
/* BPF_FUNC_l3_csum_replace and BPF_FUNC_l4_csum_replace flags.
* First 4 bits are for passing the header field size.
*/
-#define BPF_F_HDR_FIELD_MASK 0xfULL
+enum {
+ BPF_F_HDR_FIELD_MASK = 0xfULL,
+};
/* BPF_FUNC_l4_csum_replace flags. */
-#define BPF_F_PSEUDO_HDR (1ULL << 4)
-#define BPF_F_MARK_MANGLED_0 (1ULL << 5)
-#define BPF_F_MARK_ENFORCE (1ULL << 6)
+enum {
+ BPF_F_PSEUDO_HDR = (1ULL << 4),
+ BPF_F_MARK_MANGLED_0 = (1ULL << 5),
+ BPF_F_MARK_ENFORCE = (1ULL << 6),
+};
/* BPF_FUNC_clone_redirect and BPF_FUNC_redirect flags. */
-#define BPF_F_INGRESS (1ULL << 0)
+enum {
+ BPF_F_INGRESS = (1ULL << 0),
+};
/* BPF_FUNC_skb_set_tunnel_key and BPF_FUNC_skb_get_tunnel_key flags. */
-#define BPF_F_TUNINFO_IPV6 (1ULL << 0)
+enum {
+ BPF_F_TUNINFO_IPV6 = (1ULL << 0),
+};
/* flags for both BPF_FUNC_get_stackid and BPF_FUNC_get_stack. */
-#define BPF_F_SKIP_FIELD_MASK 0xffULL
-#define BPF_F_USER_STACK (1ULL << 8)
+enum {
+ BPF_F_SKIP_FIELD_MASK = 0xffULL,
+ BPF_F_USER_STACK = (1ULL << 8),
/* flags used by BPF_FUNC_get_stackid only. */
-#define BPF_F_FAST_STACK_CMP (1ULL << 9)
-#define BPF_F_REUSE_STACKID (1ULL << 10)
+ BPF_F_FAST_STACK_CMP = (1ULL << 9),
+ BPF_F_REUSE_STACKID = (1ULL << 10),
/* flags used by BPF_FUNC_get_stack only. */
-#define BPF_F_USER_BUILD_ID (1ULL << 11)
+ BPF_F_USER_BUILD_ID = (1ULL << 11),
+};
/* BPF_FUNC_skb_set_tunnel_key flags. */
-#define BPF_F_ZERO_CSUM_TX (1ULL << 1)
-#define BPF_F_DONT_FRAGMENT (1ULL << 2)
-#define BPF_F_SEQ_NUMBER (1ULL << 3)
+enum {
+ BPF_F_ZERO_CSUM_TX = (1ULL << 1),
+ BPF_F_DONT_FRAGMENT = (1ULL << 2),
+ BPF_F_SEQ_NUMBER = (1ULL << 3),
+};
/* BPF_FUNC_perf_event_output, BPF_FUNC_perf_event_read and
* BPF_FUNC_perf_event_read_value flags.
*/
-#define BPF_F_INDEX_MASK 0xffffffffULL
-#define BPF_F_CURRENT_CPU BPF_F_INDEX_MASK
+enum {
+ BPF_F_INDEX_MASK = 0xffffffffULL,
+ BPF_F_CURRENT_CPU = BPF_F_INDEX_MASK,
/* BPF_FUNC_perf_event_output for sk_buff input context. */
-#define BPF_F_CTXLEN_MASK (0xfffffULL << 32)
+ BPF_F_CTXLEN_MASK = (0xfffffULL << 32),
+};
/* Current network namespace */
-#define BPF_F_CURRENT_NETNS (-1L)
+enum {
+ BPF_F_CURRENT_NETNS = (-1L),
+};
/* BPF_FUNC_skb_adjust_room flags. */
-#define BPF_F_ADJ_ROOM_FIXED_GSO (1ULL << 0)
+enum {
+ BPF_F_ADJ_ROOM_FIXED_GSO = (1ULL << 0),
+ BPF_F_ADJ_ROOM_ENCAP_L3_IPV4 = (1ULL << 1),
+ BPF_F_ADJ_ROOM_ENCAP_L3_IPV6 = (1ULL << 2),
+ BPF_F_ADJ_ROOM_ENCAP_L4_GRE = (1ULL << 3),
+ BPF_F_ADJ_ROOM_ENCAP_L4_UDP = (1ULL << 4),
+};
-#define BPF_ADJ_ROOM_ENCAP_L2_MASK 0xff
-#define BPF_ADJ_ROOM_ENCAP_L2_SHIFT 56
+enum {
+ BPF_ADJ_ROOM_ENCAP_L2_MASK = 0xff,
+ BPF_ADJ_ROOM_ENCAP_L2_SHIFT = 56,
+};
-#define BPF_F_ADJ_ROOM_ENCAP_L3_IPV4 (1ULL << 1)
-#define BPF_F_ADJ_ROOM_ENCAP_L3_IPV6 (1ULL << 2)
-#define BPF_F_ADJ_ROOM_ENCAP_L4_GRE (1ULL << 3)
-#define BPF_F_ADJ_ROOM_ENCAP_L4_UDP (1ULL << 4)
#define BPF_F_ADJ_ROOM_ENCAP_L2(len) (((__u64)len & \
BPF_ADJ_ROOM_ENCAP_L2_MASK) \
<< BPF_ADJ_ROOM_ENCAP_L2_SHIFT)
/* BPF_FUNC_sysctl_get_name flags. */
-#define BPF_F_SYSCTL_BASE_NAME (1ULL << 0)
+enum {
+ BPF_F_SYSCTL_BASE_NAME = (1ULL << 0),
+};
/* BPF_FUNC_sk_storage_get flags */
-#define BPF_SK_STORAGE_GET_F_CREATE (1ULL << 0)
+enum {
+ BPF_SK_STORAGE_GET_F_CREATE = (1ULL << 0),
+};
+
+/* BPF_FUNC_read_branch_records flags. */
+enum {
+ BPF_F_GET_BRANCH_RECORDS_SIZE = (1ULL << 0),
+};
/* Mode for BPF_FUNC_skb_adjust_room helper. */
enum bpf_adj_room_mode {
@@ -3155,6 +3325,7 @@ struct __sk_buff {
__u32 wire_len;
__u32 gso_segs;
__bpf_md_ptr(struct bpf_sock *, sk);
+ __u32 gso_size;
};
struct bpf_tunnel_key {
@@ -3507,13 +3678,14 @@ struct bpf_sock_ops {
};
/* Definitions for bpf_sock_ops_cb_flags */
-#define BPF_SOCK_OPS_RTO_CB_FLAG (1<<0)
-#define BPF_SOCK_OPS_RETRANS_CB_FLAG (1<<1)
-#define BPF_SOCK_OPS_STATE_CB_FLAG (1<<2)
-#define BPF_SOCK_OPS_RTT_CB_FLAG (1<<3)
-#define BPF_SOCK_OPS_ALL_CB_FLAGS 0xF /* Mask of all currently
- * supported cb flags
- */
+enum {
+ BPF_SOCK_OPS_RTO_CB_FLAG = (1<<0),
+ BPF_SOCK_OPS_RETRANS_CB_FLAG = (1<<1),
+ BPF_SOCK_OPS_STATE_CB_FLAG = (1<<2),
+ BPF_SOCK_OPS_RTT_CB_FLAG = (1<<3),
+/* Mask of all currently supported cb flags */
+ BPF_SOCK_OPS_ALL_CB_FLAGS = 0xF,
+};
/* List of known BPF sock_ops operators.
* New entries can only be added at the end
@@ -3592,8 +3764,10 @@ enum {
BPF_TCP_MAX_STATES /* Leave at the end! */
};
-#define TCP_BPF_IW 1001 /* Set TCP initial congestion window */
-#define TCP_BPF_SNDCWND_CLAMP 1002 /* Set sndcwnd_clamp */
+enum {
+ TCP_BPF_IW = 1001, /* Set TCP initial congestion window */
+ TCP_BPF_SNDCWND_CLAMP = 1002, /* Set sndcwnd_clamp */
+};
struct bpf_perf_event_value {
__u64 counter;
@@ -3601,12 +3775,16 @@ struct bpf_perf_event_value {
__u64 running;
};
-#define BPF_DEVCG_ACC_MKNOD (1ULL << 0)
-#define BPF_DEVCG_ACC_READ (1ULL << 1)
-#define BPF_DEVCG_ACC_WRITE (1ULL << 2)
+enum {
+ BPF_DEVCG_ACC_MKNOD = (1ULL << 0),
+ BPF_DEVCG_ACC_READ = (1ULL << 1),
+ BPF_DEVCG_ACC_WRITE = (1ULL << 2),
+};
-#define BPF_DEVCG_DEV_BLOCK (1ULL << 0)
-#define BPF_DEVCG_DEV_CHAR (1ULL << 1)
+enum {
+ BPF_DEVCG_DEV_BLOCK = (1ULL << 0),
+ BPF_DEVCG_DEV_CHAR = (1ULL << 1),
+};
struct bpf_cgroup_dev_ctx {
/* access_type encoded as (BPF_DEVCG_ACC_* << 16) | BPF_DEVCG_DEV_* */
@@ -3622,8 +3800,10 @@ struct bpf_raw_tracepoint_args {
/* DIRECT: Skip the FIB rules and go to FIB table associated with device
* OUTPUT: Do lookup from egress perspective; default is ingress
*/
-#define BPF_FIB_LOOKUP_DIRECT (1U << 0)
-#define BPF_FIB_LOOKUP_OUTPUT (1U << 1)
+enum {
+ BPF_FIB_LOOKUP_DIRECT = (1U << 0),
+ BPF_FIB_LOOKUP_OUTPUT = (1U << 1),
+};
enum {
BPF_FIB_LKUP_RET_SUCCESS, /* lookup successful */
@@ -3695,9 +3875,11 @@ enum bpf_task_fd_type {
BPF_FD_TYPE_URETPROBE, /* filename + offset */
};
-#define BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG (1U << 0)
-#define BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL (1U << 1)
-#define BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP (1U << 2)
+enum {
+ BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG = (1U << 0),
+ BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL = (1U << 1),
+ BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP = (1U << 2),
+};
struct bpf_flow_keys {
__u16 nhoff;
@@ -3763,4 +3945,8 @@ struct bpf_sockopt {
__s32 retval;
};
+struct bpf_pidns_info {
+ __u32 pid;
+ __u32 tgid;
+};
#endif /* _UAPI__LINUX_BPF_H__ */
diff --git a/tools/include/uapi/linux/fcntl.h b/tools/include/uapi/linux/fcntl.h
index 1f97b33c840e..ca88b7bce553 100644
--- a/tools/include/uapi/linux/fcntl.h
+++ b/tools/include/uapi/linux/fcntl.h
@@ -3,6 +3,7 @@
#define _UAPI_LINUX_FCNTL_H
#include <asm/fcntl.h>
+#include <linux/openat2.h>
#define F_SETLEASE (F_LINUX_SPECIFIC_BASE + 0)
#define F_GETLEASE (F_LINUX_SPECIFIC_BASE + 1)
@@ -100,5 +101,4 @@
#define AT_RECURSIVE 0x8000 /* Apply to the entire subtree */
-
#endif /* _UAPI_LINUX_FCNTL_H */
diff --git a/tools/include/uapi/linux/fscrypt.h b/tools/include/uapi/linux/fscrypt.h
index 1beb174ad950..0d8a6f47711c 100644
--- a/tools/include/uapi/linux/fscrypt.h
+++ b/tools/include/uapi/linux/fscrypt.h
@@ -8,6 +8,7 @@
#ifndef _UAPI_LINUX_FSCRYPT_H
#define _UAPI_LINUX_FSCRYPT_H
+#include <linux/ioctl.h>
#include <linux/types.h>
/* Encryption policy flags */
@@ -109,11 +110,22 @@ struct fscrypt_key_specifier {
} u;
};
+/*
+ * Payload of Linux keyring key of type "fscrypt-provisioning", referenced by
+ * fscrypt_add_key_arg::key_id as an alternative to fscrypt_add_key_arg::raw.
+ */
+struct fscrypt_provisioning_key_payload {
+ __u32 type;
+ __u32 __reserved;
+ __u8 raw[];
+};
+
/* Struct passed to FS_IOC_ADD_ENCRYPTION_KEY */
struct fscrypt_add_key_arg {
struct fscrypt_key_specifier key_spec;
__u32 raw_size;
- __u32 __reserved[9];
+ __u32 key_id;
+ __u32 __reserved[8];
__u8 raw[];
};
diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h
index 024af2d1d0af..ca6665ea758a 100644
--- a/tools/include/uapi/linux/if_link.h
+++ b/tools/include/uapi/linux/if_link.h
@@ -463,6 +463,7 @@ enum {
IFLA_MACSEC_REPLAY_PROTECT,
IFLA_MACSEC_VALIDATION,
IFLA_MACSEC_PAD,
+ IFLA_MACSEC_OFFLOAD,
__IFLA_MACSEC_MAX,
};
@@ -489,6 +490,7 @@ enum macsec_validation_type {
enum macsec_offload {
MACSEC_OFFLOAD_OFF = 0,
MACSEC_OFFLOAD_PHY = 1,
+ MACSEC_OFFLOAD_MAC = 2,
__MACSEC_OFFLOAD_END,
MACSEC_OFFLOAD_MAX = __MACSEC_OFFLOAD_END - 1,
};
@@ -960,11 +962,12 @@ enum {
#define XDP_FLAGS_SKB_MODE (1U << 1)
#define XDP_FLAGS_DRV_MODE (1U << 2)
#define XDP_FLAGS_HW_MODE (1U << 3)
+#define XDP_FLAGS_REPLACE (1U << 4)
#define XDP_FLAGS_MODES (XDP_FLAGS_SKB_MODE | \
XDP_FLAGS_DRV_MODE | \
XDP_FLAGS_HW_MODE)
#define XDP_FLAGS_MASK (XDP_FLAGS_UPDATE_IF_NOEXIST | \
- XDP_FLAGS_MODES)
+ XDP_FLAGS_MODES | XDP_FLAGS_REPLACE)
/* These are stored into IFLA_XDP_ATTACHED on dump. */
enum {
@@ -984,6 +987,7 @@ enum {
IFLA_XDP_DRV_PROG_ID,
IFLA_XDP_SKB_PROG_ID,
IFLA_XDP_HW_PROG_ID,
+ IFLA_XDP_EXPECTED_FD,
__IFLA_XDP_MAX,
};
diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h
index 1521073b6348..8533bf07450f 100644
--- a/tools/include/uapi/linux/in.h
+++ b/tools/include/uapi/linux/in.h
@@ -74,6 +74,8 @@ enum {
#define IPPROTO_UDPLITE IPPROTO_UDPLITE
IPPROTO_MPLS = 137, /* MPLS in IP (RFC 4023) */
#define IPPROTO_MPLS IPPROTO_MPLS
+ IPPROTO_ETHERNET = 143, /* Ethernet-within-IPv6 Encapsulation */
+#define IPPROTO_ETHERNET IPPROTO_ETHERNET
IPPROTO_RAW = 255, /* Raw IP packets */
#define IPPROTO_RAW IPPROTO_RAW
IPPROTO_MPTCP = 262, /* Multipath TCP connection */
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index f0a16b4adbbd..4b95f9a31a2f 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -1009,6 +1009,7 @@ struct kvm_ppc_resize_hpt {
#define KVM_CAP_PPC_GUEST_DEBUG_SSTEP 176
#define KVM_CAP_ARM_NISV_TO_USER 177
#define KVM_CAP_ARM_INJECT_EXT_DABT 178
+#define KVM_CAP_S390_VCPU_RESETS 179
#ifdef KVM_CAP_IRQ_ROUTING
@@ -1473,6 +1474,10 @@ struct kvm_enc_region {
/* Available with KVM_CAP_ARM_SVE */
#define KVM_ARM_VCPU_FINALIZE _IOW(KVMIO, 0xc2, int)
+/* Available with KVM_CAP_S390_VCPU_RESETS */
+#define KVM_S390_NORMAL_RESET _IO(KVMIO, 0xc3)
+#define KVM_S390_CLEAR_RESET _IO(KVMIO, 0xc4)
+
/* Secure Encrypted Virtualization command */
enum sev_cmd_id {
/* Guest initialization commands */
diff --git a/tools/include/uapi/linux/openat2.h b/tools/include/uapi/linux/openat2.h
new file mode 100644
index 000000000000..58b1eb711360
--- /dev/null
+++ b/tools/include/uapi/linux/openat2.h
@@ -0,0 +1,39 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_LINUX_OPENAT2_H
+#define _UAPI_LINUX_OPENAT2_H
+
+#include <linux/types.h>
+
+/*
+ * Arguments for how openat2(2) should open the target path. If only @flags and
+ * @mode are non-zero, then openat2(2) operates very similarly to openat(2).
+ *
+ * However, unlike openat(2), unknown or invalid bits in @flags result in
+ * -EINVAL rather than being silently ignored. @mode must be zero unless one of
+ * {O_CREAT, O_TMPFILE} are set.
+ *
+ * @flags: O_* flags.
+ * @mode: O_CREAT/O_TMPFILE file mode.
+ * @resolve: RESOLVE_* flags.
+ */
+struct open_how {
+ __u64 flags;
+ __u64 mode;
+ __u64 resolve;
+};
+
+/* how->resolve flags for openat2(2). */
+#define RESOLVE_NO_XDEV 0x01 /* Block mount-point crossings
+ (includes bind-mounts). */
+#define RESOLVE_NO_MAGICLINKS 0x02 /* Block traversal through procfs-style
+ "magic-links". */
+#define RESOLVE_NO_SYMLINKS 0x04 /* Block traversal through all symlinks
+ (implies OEXT_NO_MAGICLINKS) */
+#define RESOLVE_BENEATH 0x08 /* Block "lexical" trickery like
+ "..", symlinks, and absolute
+ paths which escape the dirfd. */
+#define RESOLVE_IN_ROOT 0x10 /* Make all jumps to "/" and ".."
+ be scoped inside the dirfd
+ (similar to chroot(2)). */
+
+#endif /* _UAPI_LINUX_OPENAT2_H */
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index 377d794d3105..397cfd65b3fe 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -181,6 +181,8 @@ enum perf_branch_sample_type_shift {
PERF_SAMPLE_BRANCH_TYPE_SAVE_SHIFT = 16, /* save branch type */
+ PERF_SAMPLE_BRANCH_HW_INDEX_SHIFT = 17, /* save low level index of raw branch records */
+
PERF_SAMPLE_BRANCH_MAX_SHIFT /* non-ABI */
};
@@ -208,6 +210,8 @@ enum perf_branch_sample_type {
PERF_SAMPLE_BRANCH_TYPE_SAVE =
1U << PERF_SAMPLE_BRANCH_TYPE_SAVE_SHIFT,
+ PERF_SAMPLE_BRANCH_HW_INDEX = 1U << PERF_SAMPLE_BRANCH_HW_INDEX_SHIFT,
+
PERF_SAMPLE_BRANCH_MAX = 1U << PERF_SAMPLE_BRANCH_MAX_SHIFT,
};
@@ -853,7 +857,9 @@ enum perf_event_type {
* char data[size];}&& PERF_SAMPLE_RAW
*
* { u64 nr;
- * { u64 from, to, flags } lbr[nr];} && PERF_SAMPLE_BRANCH_STACK
+ * { u64 hw_idx; } && PERF_SAMPLE_BRANCH_HW_INDEX
+ * { u64 from, to, flags } lbr[nr];
+ * } && PERF_SAMPLE_BRANCH_STACK
*
* { u64 abi; # enum perf_sample_regs_abi
* u64 regs[weight(mask)]; } && PERF_SAMPLE_REGS_USER
diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h
index 7da1b37b27aa..07b4f8131e36 100644
--- a/tools/include/uapi/linux/prctl.h
+++ b/tools/include/uapi/linux/prctl.h
@@ -234,4 +234,8 @@ struct prctl_mm_map {
#define PR_GET_TAGGED_ADDR_CTRL 56
# define PR_TAGGED_ADDR_ENABLE (1UL << 0)
+/* Control reclaim behavior when allocating memory */
+#define PR_SET_IO_FLUSHER 57
+#define PR_GET_IO_FLUSHER 58
+
#endif /* _LINUX_PRCTL_H */
diff --git a/tools/include/uapi/linux/sched.h b/tools/include/uapi/linux/sched.h
index 4a0217832464..2e3bc22c6f20 100644
--- a/tools/include/uapi/linux/sched.h
+++ b/tools/include/uapi/linux/sched.h
@@ -36,6 +36,12 @@
/* Flags for the clone3() syscall. */
#define CLONE_CLEAR_SIGHAND 0x100000000ULL /* Clear any signal handler and reset to SIG_DFL. */
+/*
+ * cloning flags intersect with CSIGNAL so can be used with unshare and clone3
+ * syscalls only:
+ */
+#define CLONE_NEWTIME 0x00000080 /* New time namespace */
+
#ifndef __ASSEMBLY__
/**
* struct clone_args - arguments for the clone3 syscall
diff --git a/tools/testing/selftests/bpf/include/uapi/linux/types.h b/tools/include/uapi/linux/types.h
index 91fa51a9c31d..91fa51a9c31d 100644
--- a/tools/testing/selftests/bpf/include/uapi/linux/types.h
+++ b/tools/include/uapi/linux/types.h
diff --git a/tools/include/uapi/sound/asound.h b/tools/include/uapi/sound/asound.h
index df1153cea0b7..535a7229e1d9 100644
--- a/tools/include/uapi/sound/asound.h
+++ b/tools/include/uapi/sound/asound.h
@@ -26,7 +26,9 @@
#if defined(__KERNEL__) || defined(__linux__)
#include <linux/types.h>
+#include <asm/byteorder.h>
#else
+#include <endian.h>
#include <sys/ioctl.h>
#endif
@@ -154,7 +156,7 @@ struct snd_hwdep_dsp_image {
* *
*****************************************************************************/
-#define SNDRV_PCM_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 14)
+#define SNDRV_PCM_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 15)
typedef unsigned long snd_pcm_uframes_t;
typedef signed long snd_pcm_sframes_t;
@@ -301,7 +303,9 @@ typedef int __bitwise snd_pcm_subformat_t;
#define SNDRV_PCM_INFO_DRAIN_TRIGGER 0x40000000 /* internal kernel flag - trigger in drain */
#define SNDRV_PCM_INFO_FIFO_IN_FRAMES 0x80000000 /* internal kernel flag - FIFO size is in frames */
-
+#if (__BITS_PER_LONG == 32 && defined(__USE_TIME_BITS64)) || defined __KERNEL__
+#define __SND_STRUCT_TIME64
+#endif
typedef int __bitwise snd_pcm_state_t;
#define SNDRV_PCM_STATE_OPEN ((__force snd_pcm_state_t) 0) /* stream is open */
@@ -317,8 +321,17 @@ typedef int __bitwise snd_pcm_state_t;
enum {
SNDRV_PCM_MMAP_OFFSET_DATA = 0x00000000,
- SNDRV_PCM_MMAP_OFFSET_STATUS = 0x80000000,
- SNDRV_PCM_MMAP_OFFSET_CONTROL = 0x81000000,
+ SNDRV_PCM_MMAP_OFFSET_STATUS_OLD = 0x80000000,
+ SNDRV_PCM_MMAP_OFFSET_CONTROL_OLD = 0x81000000,
+ SNDRV_PCM_MMAP_OFFSET_STATUS_NEW = 0x82000000,
+ SNDRV_PCM_MMAP_OFFSET_CONTROL_NEW = 0x83000000,
+#ifdef __SND_STRUCT_TIME64
+ SNDRV_PCM_MMAP_OFFSET_STATUS = SNDRV_PCM_MMAP_OFFSET_STATUS_NEW,
+ SNDRV_PCM_MMAP_OFFSET_CONTROL = SNDRV_PCM_MMAP_OFFSET_CONTROL_NEW,
+#else
+ SNDRV_PCM_MMAP_OFFSET_STATUS = SNDRV_PCM_MMAP_OFFSET_STATUS_OLD,
+ SNDRV_PCM_MMAP_OFFSET_CONTROL = SNDRV_PCM_MMAP_OFFSET_CONTROL_OLD,
+#endif
};
union snd_pcm_sync_id {
@@ -456,8 +469,13 @@ enum {
SNDRV_PCM_AUDIO_TSTAMP_TYPE_LAST = SNDRV_PCM_AUDIO_TSTAMP_TYPE_LINK_SYNCHRONIZED
};
+#ifndef __KERNEL__
+/* explicit padding avoids incompatibility between i386 and x86-64 */
+typedef struct { unsigned char pad[sizeof(time_t) - sizeof(int)]; } __time_pad;
+
struct snd_pcm_status {
snd_pcm_state_t state; /* stream state */
+ __time_pad pad1; /* align to timespec */
struct timespec trigger_tstamp; /* time when stream was started/stopped/paused */
struct timespec tstamp; /* reference timestamp */
snd_pcm_uframes_t appl_ptr; /* appl ptr */
@@ -473,17 +491,48 @@ struct snd_pcm_status {
__u32 audio_tstamp_accuracy; /* in ns units, only valid if indicated in audio_tstamp_data */
unsigned char reserved[52-2*sizeof(struct timespec)]; /* must be filled with zero */
};
+#endif
+
+/*
+ * For mmap operations, we need the 64-bit layout, both for compat mode,
+ * and for y2038 compatibility. For 64-bit applications, the two definitions
+ * are identical, so we keep the traditional version.
+ */
+#ifdef __SND_STRUCT_TIME64
+#define __snd_pcm_mmap_status64 snd_pcm_mmap_status
+#define __snd_pcm_mmap_control64 snd_pcm_mmap_control
+#define __snd_pcm_sync_ptr64 snd_pcm_sync_ptr
+#ifdef __KERNEL__
+#define __snd_timespec64 __kernel_timespec
+#else
+#define __snd_timespec64 timespec
+#endif
+struct __snd_timespec {
+ __s32 tv_sec;
+ __s32 tv_nsec;
+};
+#else
+#define __snd_pcm_mmap_status snd_pcm_mmap_status
+#define __snd_pcm_mmap_control snd_pcm_mmap_control
+#define __snd_pcm_sync_ptr snd_pcm_sync_ptr
+#define __snd_timespec timespec
+struct __snd_timespec64 {
+ __s64 tv_sec;
+ __s64 tv_nsec;
+};
-struct snd_pcm_mmap_status {
+#endif
+
+struct __snd_pcm_mmap_status {
snd_pcm_state_t state; /* RO: state - SNDRV_PCM_STATE_XXXX */
int pad1; /* Needed for 64 bit alignment */
snd_pcm_uframes_t hw_ptr; /* RO: hw ptr (0...boundary-1) */
- struct timespec tstamp; /* Timestamp */
+ struct __snd_timespec tstamp; /* Timestamp */
snd_pcm_state_t suspended_state; /* RO: suspended stream state */
- struct timespec audio_tstamp; /* from sample counter or wall clock */
+ struct __snd_timespec audio_tstamp; /* from sample counter or wall clock */
};
-struct snd_pcm_mmap_control {
+struct __snd_pcm_mmap_control {
snd_pcm_uframes_t appl_ptr; /* RW: appl ptr (0...boundary-1) */
snd_pcm_uframes_t avail_min; /* RW: min available frames for wakeup */
};
@@ -492,14 +541,59 @@ struct snd_pcm_mmap_control {
#define SNDRV_PCM_SYNC_PTR_APPL (1<<1) /* get appl_ptr from driver (r/w op) */
#define SNDRV_PCM_SYNC_PTR_AVAIL_MIN (1<<2) /* get avail_min from driver */
-struct snd_pcm_sync_ptr {
+struct __snd_pcm_sync_ptr {
unsigned int flags;
union {
- struct snd_pcm_mmap_status status;
+ struct __snd_pcm_mmap_status status;
+ unsigned char reserved[64];
+ } s;
+ union {
+ struct __snd_pcm_mmap_control control;
+ unsigned char reserved[64];
+ } c;
+};
+
+#if defined(__BYTE_ORDER) ? __BYTE_ORDER == __BIG_ENDIAN : defined(__BIG_ENDIAN)
+typedef char __pad_before_uframe[sizeof(__u64) - sizeof(snd_pcm_uframes_t)];
+typedef char __pad_after_uframe[0];
+#endif
+
+#if defined(__BYTE_ORDER) ? __BYTE_ORDER == __LITTLE_ENDIAN : defined(__LITTLE_ENDIAN)
+typedef char __pad_before_uframe[0];
+typedef char __pad_after_uframe[sizeof(__u64) - sizeof(snd_pcm_uframes_t)];
+#endif
+
+struct __snd_pcm_mmap_status64 {
+ snd_pcm_state_t state; /* RO: state - SNDRV_PCM_STATE_XXXX */
+ __u32 pad1; /* Needed for 64 bit alignment */
+ __pad_before_uframe __pad1;
+ snd_pcm_uframes_t hw_ptr; /* RO: hw ptr (0...boundary-1) */
+ __pad_after_uframe __pad2;
+ struct __snd_timespec64 tstamp; /* Timestamp */
+ snd_pcm_state_t suspended_state;/* RO: suspended stream state */
+ __u32 pad3; /* Needed for 64 bit alignment */
+ struct __snd_timespec64 audio_tstamp; /* sample counter or wall clock */
+};
+
+struct __snd_pcm_mmap_control64 {
+ __pad_before_uframe __pad1;
+ snd_pcm_uframes_t appl_ptr; /* RW: appl ptr (0...boundary-1) */
+ __pad_before_uframe __pad2;
+
+ __pad_before_uframe __pad3;
+ snd_pcm_uframes_t avail_min; /* RW: min available frames for wakeup */
+ __pad_after_uframe __pad4;
+};
+
+struct __snd_pcm_sync_ptr64 {
+ __u32 flags;
+ __u32 pad1;
+ union {
+ struct __snd_pcm_mmap_status64 status;
unsigned char reserved[64];
} s;
union {
- struct snd_pcm_mmap_control control;
+ struct __snd_pcm_mmap_control64 control;
unsigned char reserved[64];
} c;
};
@@ -584,6 +678,8 @@ enum {
#define SNDRV_PCM_IOCTL_STATUS _IOR('A', 0x20, struct snd_pcm_status)
#define SNDRV_PCM_IOCTL_DELAY _IOR('A', 0x21, snd_pcm_sframes_t)
#define SNDRV_PCM_IOCTL_HWSYNC _IO('A', 0x22)
+#define __SNDRV_PCM_IOCTL_SYNC_PTR _IOWR('A', 0x23, struct __snd_pcm_sync_ptr)
+#define __SNDRV_PCM_IOCTL_SYNC_PTR64 _IOWR('A', 0x23, struct __snd_pcm_sync_ptr64)
#define SNDRV_PCM_IOCTL_SYNC_PTR _IOWR('A', 0x23, struct snd_pcm_sync_ptr)
#define SNDRV_PCM_IOCTL_STATUS_EXT _IOWR('A', 0x24, struct snd_pcm_status)
#define SNDRV_PCM_IOCTL_CHANNEL_INFO _IOR('A', 0x32, struct snd_pcm_channel_info)
@@ -614,7 +710,7 @@ enum {
* Raw MIDI section - /dev/snd/midi??
*/
-#define SNDRV_RAWMIDI_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 0)
+#define SNDRV_RAWMIDI_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 1)
enum {
SNDRV_RAWMIDI_STREAM_OUTPUT = 0,
@@ -648,13 +744,16 @@ struct snd_rawmidi_params {
unsigned char reserved[16]; /* reserved for future use */
};
+#ifndef __KERNEL__
struct snd_rawmidi_status {
int stream;
+ __time_pad pad1;
struct timespec tstamp; /* Timestamp */
size_t avail; /* available bytes */
size_t xruns; /* count of overruns since last status (in bytes) */
unsigned char reserved[16]; /* reserved for future use */
};
+#endif
#define SNDRV_RAWMIDI_IOCTL_PVERSION _IOR('W', 0x00, int)
#define SNDRV_RAWMIDI_IOCTL_INFO _IOR('W', 0x01, struct snd_rawmidi_info)
@@ -667,7 +766,7 @@ struct snd_rawmidi_status {
* Timer section - /dev/snd/timer
*/
-#define SNDRV_TIMER_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 6)
+#define SNDRV_TIMER_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 7)
enum {
SNDRV_TIMER_CLASS_NONE = -1,
@@ -761,6 +860,7 @@ struct snd_timer_params {
unsigned char reserved[60]; /* reserved */
};
+#ifndef __KERNEL__
struct snd_timer_status {
struct timespec tstamp; /* Timestamp - last update */
unsigned int resolution; /* current period resolution in ns */
@@ -769,10 +869,11 @@ struct snd_timer_status {
unsigned int queue; /* used queue size */
unsigned char reserved[64]; /* reserved */
};
+#endif
#define SNDRV_TIMER_IOCTL_PVERSION _IOR('T', 0x00, int)
#define SNDRV_TIMER_IOCTL_NEXT_DEVICE _IOWR('T', 0x01, struct snd_timer_id)
-#define SNDRV_TIMER_IOCTL_TREAD _IOW('T', 0x02, int)
+#define SNDRV_TIMER_IOCTL_TREAD_OLD _IOW('T', 0x02, int)
#define SNDRV_TIMER_IOCTL_GINFO _IOWR('T', 0x03, struct snd_timer_ginfo)
#define SNDRV_TIMER_IOCTL_GPARAMS _IOW('T', 0x04, struct snd_timer_gparams)
#define SNDRV_TIMER_IOCTL_GSTATUS _IOWR('T', 0x05, struct snd_timer_gstatus)
@@ -785,6 +886,15 @@ struct snd_timer_status {
#define SNDRV_TIMER_IOCTL_STOP _IO('T', 0xa1)
#define SNDRV_TIMER_IOCTL_CONTINUE _IO('T', 0xa2)
#define SNDRV_TIMER_IOCTL_PAUSE _IO('T', 0xa3)
+#define SNDRV_TIMER_IOCTL_TREAD64 _IOW('T', 0xa4, int)
+
+#if __BITS_PER_LONG == 64
+#define SNDRV_TIMER_IOCTL_TREAD SNDRV_TIMER_IOCTL_TREAD_OLD
+#else
+#define SNDRV_TIMER_IOCTL_TREAD ((sizeof(__kernel_long_t) >= sizeof(time_t)) ? \
+ SNDRV_TIMER_IOCTL_TREAD_OLD : \
+ SNDRV_TIMER_IOCTL_TREAD64)
+#endif
struct snd_timer_read {
unsigned int resolution;
@@ -810,11 +920,15 @@ enum {
SNDRV_TIMER_EVENT_MRESUME = SNDRV_TIMER_EVENT_RESUME + 10,
};
+#ifndef __KERNEL__
struct snd_timer_tread {
int event;
+ __time_pad pad1;
struct timespec tstamp;
unsigned int val;
+ __time_pad pad2;
};
+#endif
/****************************************************************************
* *
@@ -822,7 +936,7 @@ struct snd_timer_tread {
* *
****************************************************************************/
-#define SNDRV_CTL_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 7)
+#define SNDRV_CTL_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 8)
struct snd_ctl_card_info {
int card; /* card number */
@@ -860,7 +974,7 @@ typedef int __bitwise snd_ctl_elem_iface_t;
#define SNDRV_CTL_ELEM_ACCESS_WRITE (1<<1)
#define SNDRV_CTL_ELEM_ACCESS_READWRITE (SNDRV_CTL_ELEM_ACCESS_READ|SNDRV_CTL_ELEM_ACCESS_WRITE)
#define SNDRV_CTL_ELEM_ACCESS_VOLATILE (1<<2) /* control value may be changed without a notification */
-#define SNDRV_CTL_ELEM_ACCESS_TIMESTAMP (1<<3) /* when was control changed */
+// (1 << 3) is unused.
#define SNDRV_CTL_ELEM_ACCESS_TLV_READ (1<<4) /* TLV read is possible */
#define SNDRV_CTL_ELEM_ACCESS_TLV_WRITE (1<<5) /* TLV write is possible */
#define SNDRV_CTL_ELEM_ACCESS_TLV_READWRITE (SNDRV_CTL_ELEM_ACCESS_TLV_READ|SNDRV_CTL_ELEM_ACCESS_TLV_WRITE)
@@ -926,11 +1040,7 @@ struct snd_ctl_elem_info {
} enumerated;
unsigned char reserved[128];
} value;
- union {
- unsigned short d[4]; /* dimensions */
- unsigned short *d_ptr; /* indirect - obsoleted */
- } dimen;
- unsigned char reserved[64-4*sizeof(unsigned short)];
+ unsigned char reserved[64];
};
struct snd_ctl_elem_value {
@@ -955,8 +1065,7 @@ struct snd_ctl_elem_value {
} bytes;
struct snd_aes_iec958 iec958;
} value; /* RO */
- struct timespec tstamp;
- unsigned char reserved[128-sizeof(struct timespec)];
+ unsigned char reserved[128];
};
struct snd_ctl_tlv {
diff --git a/tools/lib/api/fs/Build b/tools/lib/api/fs/Build
index f4ed9629ae85..0f75b28654de 100644
--- a/tools/lib/api/fs/Build
+++ b/tools/lib/api/fs/Build
@@ -1,2 +1,3 @@
libapi-y += fs.o
libapi-y += tracing_path.o
+libapi-y += cgroup.o
diff --git a/tools/lib/api/fs/cgroup.c b/tools/lib/api/fs/cgroup.c
new file mode 100644
index 000000000000..889a6eb4aaca
--- /dev/null
+++ b/tools/lib/api/fs/cgroup.c
@@ -0,0 +1,67 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/stringify.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include "fs.h"
+
+int cgroupfs_find_mountpoint(char *buf, size_t maxlen, const char *subsys)
+{
+ FILE *fp;
+ char mountpoint[PATH_MAX + 1], tokens[PATH_MAX + 1], type[PATH_MAX + 1];
+ char path_v1[PATH_MAX + 1], path_v2[PATH_MAX + 2], *path;
+ char *token, *saved_ptr = NULL;
+
+ fp = fopen("/proc/mounts", "r");
+ if (!fp)
+ return -1;
+
+ /*
+ * in order to handle split hierarchy, we need to scan /proc/mounts
+ * and inspect every cgroupfs mount point to find one that has
+ * perf_event subsystem
+ */
+ path_v1[0] = '\0';
+ path_v2[0] = '\0';
+
+ while (fscanf(fp, "%*s %"__stringify(PATH_MAX)"s %"__stringify(PATH_MAX)"s %"
+ __stringify(PATH_MAX)"s %*d %*d\n",
+ mountpoint, type, tokens) == 3) {
+
+ if (!path_v1[0] && !strcmp(type, "cgroup")) {
+
+ token = strtok_r(tokens, ",", &saved_ptr);
+
+ while (token != NULL) {
+ if (subsys && !strcmp(token, subsys)) {
+ strcpy(path_v1, mountpoint);
+ break;
+ }
+ token = strtok_r(NULL, ",", &saved_ptr);
+ }
+ }
+
+ if (!path_v2[0] && !strcmp(type, "cgroup2"))
+ strcpy(path_v2, mountpoint);
+
+ if (path_v1[0] && path_v2[0])
+ break;
+ }
+ fclose(fp);
+
+ if (path_v1[0])
+ path = path_v1;
+ else if (path_v2[0])
+ path = path_v2;
+ else
+ return -1;
+
+ if (strlen(path) < maxlen) {
+ strcpy(buf, path);
+ return 0;
+ }
+ return -1;
+}
diff --git a/tools/lib/api/fs/fs.h b/tools/lib/api/fs/fs.h
index 92d03b8396b1..936edb95e1f3 100644
--- a/tools/lib/api/fs/fs.h
+++ b/tools/lib/api/fs/fs.h
@@ -28,6 +28,8 @@ FS(bpf_fs)
#undef FS
+int cgroupfs_find_mountpoint(char *buf, size_t maxlen, const char *subsys);
+
int filename__read_int(const char *filename, int *value);
int filename__read_ull(const char *filename, unsigned long long *value);
int filename__read_xll(const char *filename, unsigned long long *value);
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index c6dafe563176..5cc1b0785d18 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -235,7 +235,8 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
memset(&attr, 0, sizeof(attr));
attr.prog_type = load_attr->prog_type;
attr.expected_attach_type = load_attr->expected_attach_type;
- if (attr.prog_type == BPF_PROG_TYPE_STRUCT_OPS) {
+ if (attr.prog_type == BPF_PROG_TYPE_STRUCT_OPS ||
+ attr.prog_type == BPF_PROG_TYPE_LSM) {
attr.attach_btf_id = load_attr->attach_btf_id;
} else if (attr.prog_type == BPF_PROG_TYPE_TRACING ||
attr.prog_type == BPF_PROG_TYPE_EXT) {
@@ -584,6 +585,40 @@ int bpf_prog_detach2(int prog_fd, int target_fd, enum bpf_attach_type type)
return sys_bpf(BPF_PROG_DETACH, &attr, sizeof(attr));
}
+int bpf_link_create(int prog_fd, int target_fd,
+ enum bpf_attach_type attach_type,
+ const struct bpf_link_create_opts *opts)
+{
+ union bpf_attr attr;
+
+ if (!OPTS_VALID(opts, bpf_link_create_opts))
+ return -EINVAL;
+
+ memset(&attr, 0, sizeof(attr));
+ attr.link_create.prog_fd = prog_fd;
+ attr.link_create.target_fd = target_fd;
+ attr.link_create.attach_type = attach_type;
+
+ return sys_bpf(BPF_LINK_CREATE, &attr, sizeof(attr));
+}
+
+int bpf_link_update(int link_fd, int new_prog_fd,
+ const struct bpf_link_update_opts *opts)
+{
+ union bpf_attr attr;
+
+ if (!OPTS_VALID(opts, bpf_link_update_opts))
+ return -EINVAL;
+
+ memset(&attr, 0, sizeof(attr));
+ attr.link_update.link_fd = link_fd;
+ attr.link_update.new_prog_fd = new_prog_fd;
+ attr.link_update.flags = OPTS_GET(opts, flags, 0);
+ attr.link_update.old_prog_fd = OPTS_GET(opts, old_prog_fd, 0);
+
+ return sys_bpf(BPF_LINK_UPDATE, &attr, sizeof(attr));
+}
+
int bpf_prog_query(int target_fd, enum bpf_attach_type type, __u32 query_flags,
__u32 *attach_flags, __u32 *prog_ids, __u32 *prog_cnt)
{
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index b976e77316cc..46d47afdd887 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -168,6 +168,25 @@ LIBBPF_API int bpf_prog_detach(int attachable_fd, enum bpf_attach_type type);
LIBBPF_API int bpf_prog_detach2(int prog_fd, int attachable_fd,
enum bpf_attach_type type);
+struct bpf_link_create_opts {
+ size_t sz; /* size of this struct for forward/backward compatibility */
+};
+#define bpf_link_create_opts__last_field sz
+
+LIBBPF_API int bpf_link_create(int prog_fd, int target_fd,
+ enum bpf_attach_type attach_type,
+ const struct bpf_link_create_opts *opts);
+
+struct bpf_link_update_opts {
+ size_t sz; /* size of this struct for forward/backward compatibility */
+ __u32 flags; /* extra flags */
+ __u32 old_prog_fd; /* expected old program FD */
+};
+#define bpf_link_update_opts__last_field old_prog_fd
+
+LIBBPF_API int bpf_link_update(int link_fd, int new_prog_fd,
+ const struct bpf_link_update_opts *opts);
+
struct bpf_prog_test_run_attr {
int prog_fd;
int repeat;
diff --git a/tools/lib/bpf/bpf_tracing.h b/tools/lib/bpf/bpf_tracing.h
index b0dafe8b4ebc..f3f3c3fb98cb 100644
--- a/tools/lib/bpf/bpf_tracing.h
+++ b/tools/lib/bpf/bpf_tracing.h
@@ -49,7 +49,8 @@
#if defined(bpf_target_x86)
-#ifdef __KERNEL__
+#if defined(__KERNEL__) || defined(__VMLINUX_H__)
+
#define PT_REGS_PARM1(x) ((x)->di)
#define PT_REGS_PARM2(x) ((x)->si)
#define PT_REGS_PARM3(x) ((x)->dx)
@@ -60,7 +61,20 @@
#define PT_REGS_RC(x) ((x)->ax)
#define PT_REGS_SP(x) ((x)->sp)
#define PT_REGS_IP(x) ((x)->ip)
+
+#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), di)
+#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), si)
+#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), dx)
+#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), cx)
+#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), r8)
+#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), sp)
+#define PT_REGS_FP_CORE(x) BPF_CORE_READ((x), bp)
+#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), ax)
+#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), sp)
+#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), ip)
+
#else
+
#ifdef __i386__
/* i386 kernel is built with -mregparm=3 */
#define PT_REGS_PARM1(x) ((x)->eax)
@@ -73,7 +87,20 @@
#define PT_REGS_RC(x) ((x)->eax)
#define PT_REGS_SP(x) ((x)->esp)
#define PT_REGS_IP(x) ((x)->eip)
+
+#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), eax)
+#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), edx)
+#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), ecx)
+#define PT_REGS_PARM4_CORE(x) 0
+#define PT_REGS_PARM5_CORE(x) 0
+#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), esp)
+#define PT_REGS_FP_CORE(x) BPF_CORE_READ((x), ebp)
+#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), eax)
+#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), esp)
+#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), eip)
+
#else
+
#define PT_REGS_PARM1(x) ((x)->rdi)
#define PT_REGS_PARM2(x) ((x)->rsi)
#define PT_REGS_PARM3(x) ((x)->rdx)
@@ -84,6 +111,18 @@
#define PT_REGS_RC(x) ((x)->rax)
#define PT_REGS_SP(x) ((x)->rsp)
#define PT_REGS_IP(x) ((x)->rip)
+
+#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), rdi)
+#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), rsi)
+#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), rdx)
+#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), rcx)
+#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), r8)
+#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), rsp)
+#define PT_REGS_FP_CORE(x) BPF_CORE_READ((x), rbp)
+#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), rax)
+#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), rsp)
+#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), rip)
+
#endif
#endif
@@ -104,6 +143,17 @@ struct pt_regs;
#define PT_REGS_SP(x) (((PT_REGS_S390 *)(x))->gprs[15])
#define PT_REGS_IP(x) (((PT_REGS_S390 *)(x))->psw.addr)
+#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[2])
+#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[3])
+#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[4])
+#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[5])
+#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[6])
+#define PT_REGS_RET_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), grps[14])
+#define PT_REGS_FP_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[11])
+#define PT_REGS_RC_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[2])
+#define PT_REGS_SP_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[15])
+#define PT_REGS_IP_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), pdw.addr)
+
#elif defined(bpf_target_arm)
#define PT_REGS_PARM1(x) ((x)->uregs[0])
@@ -117,6 +167,17 @@ struct pt_regs;
#define PT_REGS_SP(x) ((x)->uregs[13])
#define PT_REGS_IP(x) ((x)->uregs[12])
+#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), uregs[0])
+#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), uregs[1])
+#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), uregs[2])
+#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), uregs[3])
+#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), uregs[4])
+#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), uregs[14])
+#define PT_REGS_FP_CORE(x) BPF_CORE_READ((x), uregs[11])
+#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), uregs[0])
+#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), uregs[13])
+#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), uregs[12])
+
#elif defined(bpf_target_arm64)
/* arm64 provides struct user_pt_regs instead of struct pt_regs to userspace */
@@ -134,6 +195,17 @@ struct pt_regs;
#define PT_REGS_SP(x) (((PT_REGS_ARM64 *)(x))->sp)
#define PT_REGS_IP(x) (((PT_REGS_ARM64 *)(x))->pc)
+#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[0])
+#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[1])
+#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[2])
+#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[3])
+#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[4])
+#define PT_REGS_RET_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[30])
+#define PT_REGS_FP_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[29])
+#define PT_REGS_RC_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[0])
+#define PT_REGS_SP_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), sp)
+#define PT_REGS_IP_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), pc)
+
#elif defined(bpf_target_mips)
#define PT_REGS_PARM1(x) ((x)->regs[4])
@@ -147,6 +219,17 @@ struct pt_regs;
#define PT_REGS_SP(x) ((x)->regs[29])
#define PT_REGS_IP(x) ((x)->cp0_epc)
+#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), regs[4])
+#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), regs[5])
+#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), regs[6])
+#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), regs[7])
+#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), regs[8])
+#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), regs[31])
+#define PT_REGS_FP_CORE(x) BPF_CORE_READ((x), regs[30])
+#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), regs[1])
+#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), regs[29])
+#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), cp0_epc)
+
#elif defined(bpf_target_powerpc)
#define PT_REGS_PARM1(x) ((x)->gpr[3])
@@ -158,6 +241,15 @@ struct pt_regs;
#define PT_REGS_SP(x) ((x)->sp)
#define PT_REGS_IP(x) ((x)->nip)
+#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), gpr[3])
+#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), gpr[4])
+#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), gpr[5])
+#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), gpr[6])
+#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), gpr[7])
+#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), gpr[3])
+#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), sp)
+#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), nip)
+
#elif defined(bpf_target_sparc)
#define PT_REGS_PARM1(x) ((x)->u_regs[UREG_I0])
@@ -169,11 +261,22 @@ struct pt_regs;
#define PT_REGS_RC(x) ((x)->u_regs[UREG_I0])
#define PT_REGS_SP(x) ((x)->u_regs[UREG_FP])
+#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I0])
+#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I1])
+#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I2])
+#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I3])
+#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I4])
+#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I7])
+#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I0])
+#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), u_regs[UREG_FP])
+
/* Should this also be a bpf_target check for the sparc case? */
#if defined(__arch64__)
#define PT_REGS_IP(x) ((x)->tpc)
+#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), tpc)
#else
#define PT_REGS_IP(x) ((x)->pc)
+#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), pc)
#endif
#endif
@@ -192,4 +295,122 @@ struct pt_regs;
(void *)(PT_REGS_FP(ctx) + sizeof(ip))); })
#endif
+#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 __attribute__((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 __attribute__((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 __attribute__((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 __attribute__((always_inline)) typeof(name(0)) \
+____##name(struct pt_regs *ctx, ##args)
+
+#define ___bpf_kretprobe_args0() ctx
+#define ___bpf_kretprobe_args1(x) \
+ ___bpf_kretprobe_args0(), (void *)PT_REGS_RC(ctx)
+#define ___bpf_kretprobe_args(args...) \
+ ___bpf_apply(___bpf_kretprobe_args, ___bpf_narg(args))(args)
+
+/*
+ * BPF_KRETPROBE is similar to BPF_KPROBE, except, it only provides optional
+ * return value (in addition to `struct pt_regs *ctx`), but no input
+ * arguments, because they will be clobbered by the time probed function
+ * returns.
+ */
+#define BPF_KRETPROBE(name, args...) \
+name(struct pt_regs *ctx); \
+static __attribute__((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/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 3d1c25fc97ae..bfef3d606b54 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -657,22 +657,32 @@ int btf__finalize_data(struct bpf_object *obj, struct btf *btf)
int btf__load(struct btf *btf)
{
- __u32 log_buf_size = BPF_LOG_BUF_SIZE;
+ __u32 log_buf_size = 0;
char *log_buf = NULL;
int err = 0;
if (btf->fd >= 0)
return -EEXIST;
- log_buf = malloc(log_buf_size);
- if (!log_buf)
- return -ENOMEM;
+retry_load:
+ if (log_buf_size) {
+ log_buf = malloc(log_buf_size);
+ if (!log_buf)
+ return -ENOMEM;
- *log_buf = 0;
+ *log_buf = 0;
+ }
btf->fd = bpf_load_btf(btf->data, btf->data_size,
log_buf, log_buf_size, false);
if (btf->fd < 0) {
+ if (!log_buf || errno == ENOSPC) {
+ log_buf_size = max((__u32)BPF_LOG_BUF_SIZE,
+ log_buf_size << 1);
+ free(log_buf);
+ goto retry_load;
+ }
+
err = -errno;
pr_warn("Error loading BTF: %s(%d)\n", strerror(errno), errno);
if (*log_buf)
diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c
index bd09ed1710f1..0c28ee82834b 100644
--- a/tools/lib/bpf/btf_dump.c
+++ b/tools/lib/bpf/btf_dump.c
@@ -916,13 +916,13 @@ static void btf_dump_emit_enum_def(struct btf_dump *d, __u32 id,
/* enumerators share namespace with typedef idents */
dup_cnt = btf_dump_name_dups(d, d->ident_names, name);
if (dup_cnt > 1) {
- btf_dump_printf(d, "\n%s%s___%zu = %d,",
+ btf_dump_printf(d, "\n%s%s___%zu = %u,",
pfx(lvl + 1), name, dup_cnt,
- (__s32)v->val);
+ (__u32)v->val);
} else {
- btf_dump_printf(d, "\n%s%s = %d,",
+ btf_dump_printf(d, "\n%s%s = %u,",
pfx(lvl + 1), name,
- (__s32)v->val);
+ (__u32)v->val);
}
}
btf_dump_printf(d, "\n%s}", pfx(lvl));
@@ -1030,7 +1030,7 @@ int btf_dump__emit_type_decl(struct btf_dump *d, __u32 id,
if (!OPTS_VALID(opts, btf_dump_emit_type_decl_opts))
return -EINVAL;
- fname = OPTS_GET(opts, field_name, NULL);
+ fname = OPTS_GET(opts, field_name, "");
lvl = OPTS_GET(opts, indent_level, 0);
btf_dump_emit_type_decl(d, id, fname, lvl);
return 0;
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 514b1a524abb..ff9174282a8c 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -24,6 +24,7 @@
#include <endian.h>
#include <fcntl.h>
#include <errno.h>
+#include <ctype.h>
#include <asm/unistd.h>
#include <linux/err.h>
#include <linux/kernel.h>
@@ -1283,7 +1284,7 @@ static size_t bpf_map_mmap_sz(const struct bpf_map *map)
static char *internal_map_name(struct bpf_object *obj,
enum libbpf_map_type type)
{
- char map_name[BPF_OBJ_NAME_LEN];
+ char map_name[BPF_OBJ_NAME_LEN], *p;
const char *sfx = libbpf_type_to_btf_name[type];
int sfx_len = max((size_t)7, strlen(sfx));
int pfx_len = min((size_t)BPF_OBJ_NAME_LEN - sfx_len - 1,
@@ -1292,6 +1293,11 @@ static char *internal_map_name(struct bpf_object *obj,
snprintf(map_name, sizeof(map_name), "%.*s%.*s", pfx_len, obj->name,
sfx_len, libbpf_type_to_btf_name[type]);
+ /* sanitise map name to characters allowed by kernel */
+ for (p = map_name; *p && p < map_name + sizeof(map_name); p++)
+ if (!isalnum(*p) && *p != '_' && *p != '.')
+ *p = '_';
+
return strdup(map_name);
}
@@ -1839,7 +1845,6 @@ resolve_func_ptr(const struct btf *btf, __u32 id, __u32 *res_id)
* type definition, while using only sizeof(void *) space in ELF data section.
*/
static bool get_map_field_int(const char *map_name, const struct btf *btf,
- const struct btf_type *def,
const struct btf_member *m, __u32 *res)
{
const struct btf_type *t = skip_mods_and_typedefs(btf, m->type, NULL);
@@ -1966,19 +1971,19 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj,
return -EINVAL;
}
if (strcmp(name, "type") == 0) {
- if (!get_map_field_int(map_name, obj->btf, def, m,
+ if (!get_map_field_int(map_name, obj->btf, m,
&map->def.type))
return -EINVAL;
pr_debug("map '%s': found type = %u.\n",
map_name, map->def.type);
} else if (strcmp(name, "max_entries") == 0) {
- if (!get_map_field_int(map_name, obj->btf, def, m,
+ if (!get_map_field_int(map_name, obj->btf, m,
&map->def.max_entries))
return -EINVAL;
pr_debug("map '%s': found max_entries = %u.\n",
map_name, map->def.max_entries);
} else if (strcmp(name, "map_flags") == 0) {
- if (!get_map_field_int(map_name, obj->btf, def, m,
+ if (!get_map_field_int(map_name, obj->btf, m,
&map->def.map_flags))
return -EINVAL;
pr_debug("map '%s': found map_flags = %u.\n",
@@ -1986,8 +1991,7 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj,
} else if (strcmp(name, "key_size") == 0) {
__u32 sz;
- if (!get_map_field_int(map_name, obj->btf, def, m,
- &sz))
+ if (!get_map_field_int(map_name, obj->btf, m, &sz))
return -EINVAL;
pr_debug("map '%s': found key_size = %u.\n",
map_name, sz);
@@ -2029,8 +2033,7 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj,
} else if (strcmp(name, "value_size") == 0) {
__u32 sz;
- if (!get_map_field_int(map_name, obj->btf, def, m,
- &sz))
+ if (!get_map_field_int(map_name, obj->btf, m, &sz))
return -EINVAL;
pr_debug("map '%s': found value_size = %u.\n",
map_name, sz);
@@ -2073,8 +2076,7 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj,
__u32 val;
int err;
- if (!get_map_field_int(map_name, obj->btf, def, m,
- &val))
+ if (!get_map_field_int(map_name, obj->btf, m, &val))
return -EINVAL;
pr_debug("map '%s': found pinning = %u.\n",
map_name, val);
@@ -2278,11 +2280,16 @@ static void bpf_object__sanitize_btf_ext(struct bpf_object *obj)
}
}
-static bool bpf_object__is_btf_mandatory(const struct bpf_object *obj)
+static bool libbpf_needs_btf(const struct bpf_object *obj)
{
return obj->efile.btf_maps_shndx >= 0 ||
- obj->efile.st_ops_shndx >= 0 ||
- obj->nr_extern > 0;
+ obj->efile.st_ops_shndx >= 0 ||
+ obj->nr_extern > 0;
+}
+
+static bool kernel_needs_btf(const struct bpf_object *obj)
+{
+ return obj->efile.st_ops_shndx >= 0;
}
static int bpf_object__init_btf(struct bpf_object *obj,
@@ -2318,7 +2325,7 @@ static int bpf_object__init_btf(struct bpf_object *obj,
}
}
out:
- if (err && bpf_object__is_btf_mandatory(obj)) {
+ if (err && libbpf_needs_btf(obj)) {
pr_warn("BTF is required, but is missing or corrupted.\n");
return err;
}
@@ -2342,7 +2349,7 @@ static int bpf_object__finalize_btf(struct bpf_object *obj)
btf_ext__free(obj->btf_ext);
obj->btf_ext = NULL;
- if (bpf_object__is_btf_mandatory(obj)) {
+ if (libbpf_needs_btf(obj)) {
pr_warn("BTF is required, but is missing or corrupted.\n");
return -ENOENT;
}
@@ -2351,7 +2358,8 @@ static int bpf_object__finalize_btf(struct bpf_object *obj)
static inline bool libbpf_prog_needs_vmlinux_btf(struct bpf_program *prog)
{
- if (prog->type == BPF_PROG_TYPE_STRUCT_OPS)
+ if (prog->type == BPF_PROG_TYPE_STRUCT_OPS ||
+ prog->type == BPF_PROG_TYPE_LSM)
return true;
/* BPF_PROG_TYPE_TRACING programs which do not attach to other programs
@@ -2406,7 +2414,7 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj)
obj->btf_ext = NULL;
}
- if (bpf_object__is_btf_mandatory(obj))
+ if (kernel_needs_btf(obj))
return err;
}
return 0;
@@ -3862,6 +3870,10 @@ static struct ids_vec *bpf_core_find_cands(const struct btf *local_btf,
if (str_is_empty(targ_name))
continue;
+ t = skip_mods_and_typedefs(targ_btf, i, NULL);
+ if (!btf_is_composite(t) && !btf_is_array(t))
+ continue;
+
targ_essent_len = bpf_core_essential_name_len(targ_name);
if (targ_essent_len != local_essent_len)
continue;
@@ -4840,8 +4852,8 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
{
struct bpf_load_program_attr load_attr;
char *cp, errmsg[STRERR_BUFSIZE];
- int log_buf_size = BPF_LOG_BUF_SIZE;
- char *log_buf;
+ size_t log_buf_size = 0;
+ char *log_buf = NULL;
int btf_fd, ret;
if (!insns || !insns_cnt)
@@ -4855,7 +4867,8 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
load_attr.insns = insns;
load_attr.insns_cnt = insns_cnt;
load_attr.license = license;
- if (prog->type == BPF_PROG_TYPE_STRUCT_OPS) {
+ if (prog->type == BPF_PROG_TYPE_STRUCT_OPS ||
+ prog->type == BPF_PROG_TYPE_LSM) {
load_attr.attach_btf_id = prog->attach_btf_id;
} else if (prog->type == BPF_PROG_TYPE_TRACING ||
prog->type == BPF_PROG_TYPE_EXT) {
@@ -4881,22 +4894,28 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
load_attr.prog_flags = prog->prog_flags;
retry_load:
- log_buf = malloc(log_buf_size);
- if (!log_buf)
- pr_warn("Alloc log buffer for bpf loader error, continue without log\n");
+ if (log_buf_size) {
+ log_buf = malloc(log_buf_size);
+ if (!log_buf)
+ return -ENOMEM;
+
+ *log_buf = 0;
+ }
ret = bpf_load_program_xattr(&load_attr, log_buf, log_buf_size);
if (ret >= 0) {
- if (load_attr.log_level)
+ if (log_buf && load_attr.log_level)
pr_debug("verifier log:\n%s", log_buf);
*pfd = ret;
ret = 0;
goto out;
}
- if (errno == ENOSPC) {
- log_buf_size <<= 1;
+ if (!log_buf || errno == ENOSPC) {
+ log_buf_size = max((size_t)BPF_LOG_BUF_SIZE,
+ log_buf_size << 1);
+
free(log_buf);
goto retry_load;
}
@@ -4939,8 +4958,9 @@ int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_ver)
{
int err = 0, fd, i, btf_id;
- if (prog->type == BPF_PROG_TYPE_TRACING ||
- prog->type == BPF_PROG_TYPE_EXT) {
+ if ((prog->type == BPF_PROG_TYPE_TRACING ||
+ prog->type == BPF_PROG_TYPE_LSM ||
+ prog->type == BPF_PROG_TYPE_EXT) && !prog->attach_btf_id) {
btf_id = libbpf_find_attach_btf_id(prog);
if (btf_id <= 0)
return btf_id;
@@ -6179,6 +6199,7 @@ bool bpf_program__is_##NAME(const struct bpf_program *prog) \
} \
BPF_PROG_TYPE_FNS(socket_filter, BPF_PROG_TYPE_SOCKET_FILTER);
+BPF_PROG_TYPE_FNS(lsm, BPF_PROG_TYPE_LSM);
BPF_PROG_TYPE_FNS(kprobe, BPF_PROG_TYPE_KPROBE);
BPF_PROG_TYPE_FNS(sched_cls, BPF_PROG_TYPE_SCHED_CLS);
BPF_PROG_TYPE_FNS(sched_act, BPF_PROG_TYPE_SCHED_ACT);
@@ -6245,6 +6266,8 @@ static struct bpf_link *attach_raw_tp(const struct bpf_sec_def *sec,
struct bpf_program *prog);
static struct bpf_link *attach_trace(const struct bpf_sec_def *sec,
struct bpf_program *prog);
+static struct bpf_link *attach_lsm(const struct bpf_sec_def *sec,
+ struct bpf_program *prog);
struct bpf_sec_def {
const char *sec;
@@ -6284,6 +6307,10 @@ static const struct bpf_sec_def section_defs[] = {
.expected_attach_type = BPF_TRACE_FENTRY,
.is_attach_btf = true,
.attach_fn = attach_trace),
+ SEC_DEF("fmod_ret/", TRACING,
+ .expected_attach_type = BPF_MODIFY_RETURN,
+ .is_attach_btf = true,
+ .attach_fn = attach_trace),
SEC_DEF("fexit/", TRACING,
.expected_attach_type = BPF_TRACE_FEXIT,
.is_attach_btf = true,
@@ -6291,6 +6318,10 @@ static const struct bpf_sec_def section_defs[] = {
SEC_DEF("freplace/", EXT,
.is_attach_btf = true,
.attach_fn = attach_trace),
+ SEC_DEF("lsm/", LSM,
+ .is_attach_btf = true,
+ .expected_attach_type = BPF_LSM_MAC,
+ .attach_fn = attach_lsm),
BPF_PROG_SEC("xdp", BPF_PROG_TYPE_XDP),
BPF_PROG_SEC("perf_event", BPF_PROG_TYPE_PERF_EVENT),
BPF_PROG_SEC("lwt_in", BPF_PROG_TYPE_LWT_IN),
@@ -6553,6 +6584,7 @@ invalid_prog:
}
#define BTF_TRACE_PREFIX "btf_trace_"
+#define BTF_LSM_PREFIX "bpf_lsm_"
#define BTF_MAX_NAME_SIZE 128
static int find_btf_by_prefix_kind(const struct btf *btf, const char *prefix,
@@ -6580,9 +6612,15 @@ static inline int __find_vmlinux_btf_id(struct btf *btf, const char *name,
if (attach_type == BPF_TRACE_RAW_TP)
err = find_btf_by_prefix_kind(btf, BTF_TRACE_PREFIX, name,
BTF_KIND_TYPEDEF);
+ else if (attach_type == BPF_LSM_MAC)
+ err = find_btf_by_prefix_kind(btf, BTF_LSM_PREFIX, name,
+ BTF_KIND_FUNC);
else
err = btf__find_by_name_kind(btf, name, BTF_KIND_FUNC);
+ if (err <= 0)
+ pr_warn("%s is not found in vmlinux BTF\n", name);
+
return err;
}
@@ -6655,8 +6693,6 @@ static int libbpf_find_attach_btf_id(struct bpf_program *prog)
err = __find_vmlinux_btf_id(prog->obj->btf_vmlinux,
name + section_defs[i].len,
attach_type);
- if (err <= 0)
- pr_warn("%s is not found in vmlinux BTF\n", name);
return err;
}
pr_warn("failed to identify btf_id based on ELF section name '%s'\n", name);
@@ -6736,6 +6772,17 @@ void *bpf_map__priv(const struct bpf_map *map)
return map ? map->priv : ERR_PTR(-EINVAL);
}
+int bpf_map__set_initial_value(struct bpf_map *map,
+ const void *data, size_t size)
+{
+ if (!map->mmaped || map->libbpf_type == LIBBPF_MAP_KCONFIG ||
+ size != map->def.value_size || map->fd >= 0)
+ return -EINVAL;
+
+ memcpy(map->mmaped, data, size);
+ return 0;
+}
+
bool bpf_map__is_offload_neutral(const struct bpf_map *map)
{
return map->def.type == BPF_MAP_TYPE_PERF_EVENT_ARRAY;
@@ -6926,9 +6973,17 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
struct bpf_link {
int (*detach)(struct bpf_link *link);
int (*destroy)(struct bpf_link *link);
+ char *pin_path; /* NULL, if not pinned */
+ int fd; /* hook FD, -1 if not applicable */
bool disconnected;
};
+/* Replace link's underlying BPF program with the new one */
+int bpf_link__update_program(struct bpf_link *link, struct bpf_program *prog)
+{
+ return bpf_link_update(bpf_link__fd(link), bpf_program__fd(prog), NULL);
+}
+
/* Release "ownership" of underlying BPF resource (typically, BPF program
* attached to some BPF hook, e.g., tracepoint, kprobe, etc). Disconnected
* link, when destructed through bpf_link__destroy() call won't attempt to
@@ -6955,26 +7010,109 @@ int bpf_link__destroy(struct bpf_link *link)
err = link->detach(link);
if (link->destroy)
link->destroy(link);
+ if (link->pin_path)
+ free(link->pin_path);
free(link);
return err;
}
-struct bpf_link_fd {
- struct bpf_link link; /* has to be at the top of struct */
- int fd; /* hook FD */
-};
+int bpf_link__fd(const struct bpf_link *link)
+{
+ return link->fd;
+}
+
+const char *bpf_link__pin_path(const struct bpf_link *link)
+{
+ return link->pin_path;
+}
+
+static int bpf_link__detach_fd(struct bpf_link *link)
+{
+ return close(link->fd);
+}
+
+struct bpf_link *bpf_link__open(const char *path)
+{
+ struct bpf_link *link;
+ int fd;
+
+ fd = bpf_obj_get(path);
+ if (fd < 0) {
+ fd = -errno;
+ pr_warn("failed to open link at %s: %d\n", path, fd);
+ return ERR_PTR(fd);
+ }
+
+ link = calloc(1, sizeof(*link));
+ if (!link) {
+ close(fd);
+ return ERR_PTR(-ENOMEM);
+ }
+ link->detach = &bpf_link__detach_fd;
+ link->fd = fd;
+
+ link->pin_path = strdup(path);
+ if (!link->pin_path) {
+ bpf_link__destroy(link);
+ return ERR_PTR(-ENOMEM);
+ }
+
+ return link;
+}
+
+int bpf_link__pin(struct bpf_link *link, const char *path)
+{
+ int err;
+
+ if (link->pin_path)
+ return -EBUSY;
+ err = make_parent_dir(path);
+ if (err)
+ return err;
+ err = check_path(path);
+ if (err)
+ return err;
+
+ link->pin_path = strdup(path);
+ if (!link->pin_path)
+ return -ENOMEM;
+
+ if (bpf_obj_pin(link->fd, link->pin_path)) {
+ err = -errno;
+ zfree(&link->pin_path);
+ return err;
+ }
+
+ pr_debug("link fd=%d: pinned at %s\n", link->fd, link->pin_path);
+ return 0;
+}
+
+int bpf_link__unpin(struct bpf_link *link)
+{
+ int err;
+
+ if (!link->pin_path)
+ return -EINVAL;
+
+ err = unlink(link->pin_path);
+ if (err != 0)
+ return -errno;
+
+ pr_debug("link fd=%d: unpinned from %s\n", link->fd, link->pin_path);
+ zfree(&link->pin_path);
+ return 0;
+}
static int bpf_link__detach_perf_event(struct bpf_link *link)
{
- struct bpf_link_fd *l = (void *)link;
int err;
- err = ioctl(l->fd, PERF_EVENT_IOC_DISABLE, 0);
+ err = ioctl(link->fd, PERF_EVENT_IOC_DISABLE, 0);
if (err)
err = -errno;
- close(l->fd);
+ close(link->fd);
return err;
}
@@ -6982,7 +7120,7 @@ struct bpf_link *bpf_program__attach_perf_event(struct bpf_program *prog,
int pfd)
{
char errmsg[STRERR_BUFSIZE];
- struct bpf_link_fd *link;
+ struct bpf_link *link;
int prog_fd, err;
if (pfd < 0) {
@@ -7000,7 +7138,7 @@ struct bpf_link *bpf_program__attach_perf_event(struct bpf_program *prog,
link = calloc(1, sizeof(*link));
if (!link)
return ERR_PTR(-ENOMEM);
- link->link.detach = &bpf_link__detach_perf_event;
+ link->detach = &bpf_link__detach_perf_event;
link->fd = pfd;
if (ioctl(pfd, PERF_EVENT_IOC_SET_BPF, prog_fd) < 0) {
@@ -7019,7 +7157,7 @@ struct bpf_link *bpf_program__attach_perf_event(struct bpf_program *prog,
libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
return ERR_PTR(err);
}
- return (struct bpf_link *)link;
+ return link;
}
/*
@@ -7307,18 +7445,11 @@ out:
return link;
}
-static int bpf_link__detach_fd(struct bpf_link *link)
-{
- struct bpf_link_fd *l = (void *)link;
-
- return close(l->fd);
-}
-
struct bpf_link *bpf_program__attach_raw_tracepoint(struct bpf_program *prog,
const char *tp_name)
{
char errmsg[STRERR_BUFSIZE];
- struct bpf_link_fd *link;
+ struct bpf_link *link;
int prog_fd, pfd;
prog_fd = bpf_program__fd(prog);
@@ -7331,7 +7462,7 @@ struct bpf_link *bpf_program__attach_raw_tracepoint(struct bpf_program *prog,
link = calloc(1, sizeof(*link));
if (!link)
return ERR_PTR(-ENOMEM);
- link->link.detach = &bpf_link__detach_fd;
+ link->detach = &bpf_link__detach_fd;
pfd = bpf_raw_tracepoint_open(tp_name, prog_fd);
if (pfd < 0) {
@@ -7343,7 +7474,7 @@ struct bpf_link *bpf_program__attach_raw_tracepoint(struct bpf_program *prog,
return ERR_PTR(pfd);
}
link->fd = pfd;
- return (struct bpf_link *)link;
+ return link;
}
static struct bpf_link *attach_raw_tp(const struct bpf_sec_def *sec,
@@ -7354,10 +7485,11 @@ static struct bpf_link *attach_raw_tp(const struct bpf_sec_def *sec,
return bpf_program__attach_raw_tracepoint(prog, tp_name);
}
-struct bpf_link *bpf_program__attach_trace(struct bpf_program *prog)
+/* Common logic for all BPF program types that attach to a btf_id */
+static struct bpf_link *bpf_program__attach_btf_id(struct bpf_program *prog)
{
char errmsg[STRERR_BUFSIZE];
- struct bpf_link_fd *link;
+ struct bpf_link *link;
int prog_fd, pfd;
prog_fd = bpf_program__fd(prog);
@@ -7370,13 +7502,13 @@ struct bpf_link *bpf_program__attach_trace(struct bpf_program *prog)
link = calloc(1, sizeof(*link));
if (!link)
return ERR_PTR(-ENOMEM);
- link->link.detach = &bpf_link__detach_fd;
+ link->detach = &bpf_link__detach_fd;
pfd = bpf_raw_tracepoint_open(NULL, prog_fd);
if (pfd < 0) {
pfd = -errno;
free(link);
- pr_warn("program '%s': failed to attach to trace: %s\n",
+ pr_warn("program '%s': failed to attach: %s\n",
bpf_program__title(prog, false),
libbpf_strerror_r(pfd, errmsg, sizeof(errmsg)));
return ERR_PTR(pfd);
@@ -7385,12 +7517,68 @@ struct bpf_link *bpf_program__attach_trace(struct bpf_program *prog)
return (struct bpf_link *)link;
}
+struct bpf_link *bpf_program__attach_trace(struct bpf_program *prog)
+{
+ return bpf_program__attach_btf_id(prog);
+}
+
+struct bpf_link *bpf_program__attach_lsm(struct bpf_program *prog)
+{
+ return bpf_program__attach_btf_id(prog);
+}
+
static struct bpf_link *attach_trace(const struct bpf_sec_def *sec,
struct bpf_program *prog)
{
return bpf_program__attach_trace(prog);
}
+static struct bpf_link *attach_lsm(const struct bpf_sec_def *sec,
+ struct bpf_program *prog)
+{
+ return bpf_program__attach_lsm(prog);
+}
+
+struct bpf_link *
+bpf_program__attach_cgroup(struct bpf_program *prog, int cgroup_fd)
+{
+ const struct bpf_sec_def *sec_def;
+ enum bpf_attach_type attach_type;
+ char errmsg[STRERR_BUFSIZE];
+ struct bpf_link *link;
+ int prog_fd, link_fd;
+
+ prog_fd = bpf_program__fd(prog);
+ if (prog_fd < 0) {
+ pr_warn("program '%s': can't attach before loaded\n",
+ bpf_program__title(prog, false));
+ return ERR_PTR(-EINVAL);
+ }
+
+ link = calloc(1, sizeof(*link));
+ if (!link)
+ return ERR_PTR(-ENOMEM);
+ link->detach = &bpf_link__detach_fd;
+
+ attach_type = bpf_program__get_expected_attach_type(prog);
+ if (!attach_type) {
+ sec_def = find_sec_def(bpf_program__title(prog, false));
+ if (sec_def)
+ attach_type = sec_def->attach_type;
+ }
+ link_fd = bpf_link_create(prog_fd, cgroup_fd, attach_type, NULL);
+ if (link_fd < 0) {
+ link_fd = -errno;
+ free(link);
+ pr_warn("program '%s': failed to attach to cgroup: %s\n",
+ bpf_program__title(prog, false),
+ libbpf_strerror_r(link_fd, errmsg, sizeof(errmsg)));
+ return ERR_PTR(link_fd);
+ }
+ link->fd = link_fd;
+ return link;
+}
+
struct bpf_link *bpf_program__attach(struct bpf_program *prog)
{
const struct bpf_sec_def *sec_def;
@@ -7404,10 +7592,9 @@ struct bpf_link *bpf_program__attach(struct bpf_program *prog)
static int bpf_link__detach_struct_ops(struct bpf_link *link)
{
- struct bpf_link_fd *l = (void *)link;
__u32 zero = 0;
- if (bpf_map_delete_elem(l->fd, &zero))
+ if (bpf_map_delete_elem(link->fd, &zero))
return -errno;
return 0;
@@ -7416,7 +7603,7 @@ static int bpf_link__detach_struct_ops(struct bpf_link *link)
struct bpf_link *bpf_map__attach_struct_ops(struct bpf_map *map)
{
struct bpf_struct_ops *st_ops;
- struct bpf_link_fd *link;
+ struct bpf_link *link;
__u32 i, zero = 0;
int err;
@@ -7448,10 +7635,10 @@ struct bpf_link *bpf_map__attach_struct_ops(struct bpf_map *map)
return ERR_PTR(err);
}
- link->link.detach = bpf_link__detach_struct_ops;
+ link->detach = bpf_link__detach_struct_ops;
link->fd = map->fd;
- return (struct bpf_link *)link;
+ return link;
}
enum bpf_perf_event_ret
@@ -8132,6 +8319,31 @@ void bpf_program__bpil_offs_to_addr(struct bpf_prog_info_linear *info_linear)
}
}
+int bpf_program__set_attach_target(struct bpf_program *prog,
+ int attach_prog_fd,
+ const char *attach_func_name)
+{
+ int btf_id;
+
+ if (!prog || attach_prog_fd < 0 || !attach_func_name)
+ return -EINVAL;
+
+ if (attach_prog_fd)
+ btf_id = libbpf_find_prog_btf_id(attach_func_name,
+ attach_prog_fd);
+ else
+ btf_id = __find_vmlinux_btf_id(prog->obj->btf_vmlinux,
+ attach_func_name,
+ prog->expected_attach_type);
+
+ if (btf_id < 0)
+ return btf_id;
+
+ prog->attach_btf_id = btf_id;
+ prog->attach_prog_fd = attach_prog_fd;
+ return 0;
+}
+
int parse_cpu_mask_str(const char *s, bool **mask, int *mask_sz)
{
int err = 0, n, len, start, end = -1;
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 3fe12c9d1f92..44df1d3e7287 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -219,6 +219,13 @@ LIBBPF_API void bpf_program__unload(struct bpf_program *prog);
struct bpf_link;
+LIBBPF_API struct bpf_link *bpf_link__open(const char *path);
+LIBBPF_API int bpf_link__fd(const struct bpf_link *link);
+LIBBPF_API const char *bpf_link__pin_path(const struct bpf_link *link);
+LIBBPF_API int bpf_link__pin(struct bpf_link *link, const char *path);
+LIBBPF_API int bpf_link__unpin(struct bpf_link *link);
+LIBBPF_API int bpf_link__update_program(struct bpf_link *link,
+ struct bpf_program *prog);
LIBBPF_API void bpf_link__disconnect(struct bpf_link *link);
LIBBPF_API int bpf_link__destroy(struct bpf_link *link);
@@ -240,11 +247,17 @@ bpf_program__attach_tracepoint(struct bpf_program *prog,
LIBBPF_API struct bpf_link *
bpf_program__attach_raw_tracepoint(struct bpf_program *prog,
const char *tp_name);
-
LIBBPF_API struct bpf_link *
bpf_program__attach_trace(struct bpf_program *prog);
+LIBBPF_API struct bpf_link *
+bpf_program__attach_lsm(struct bpf_program *prog);
+LIBBPF_API struct bpf_link *
+bpf_program__attach_cgroup(struct bpf_program *prog, int cgroup_fd);
+
struct bpf_map;
+
LIBBPF_API struct bpf_link *bpf_map__attach_struct_ops(struct bpf_map *map);
+
struct bpf_insn;
/*
@@ -316,6 +329,7 @@ LIBBPF_API int bpf_program__set_socket_filter(struct bpf_program *prog);
LIBBPF_API int bpf_program__set_tracepoint(struct bpf_program *prog);
LIBBPF_API int bpf_program__set_raw_tracepoint(struct bpf_program *prog);
LIBBPF_API int bpf_program__set_kprobe(struct bpf_program *prog);
+LIBBPF_API int bpf_program__set_lsm(struct bpf_program *prog);
LIBBPF_API int bpf_program__set_sched_cls(struct bpf_program *prog);
LIBBPF_API int bpf_program__set_sched_act(struct bpf_program *prog);
LIBBPF_API int bpf_program__set_xdp(struct bpf_program *prog);
@@ -334,10 +348,15 @@ LIBBPF_API void
bpf_program__set_expected_attach_type(struct bpf_program *prog,
enum bpf_attach_type type);
+LIBBPF_API int
+bpf_program__set_attach_target(struct bpf_program *prog, int attach_prog_fd,
+ const char *attach_func_name);
+
LIBBPF_API bool bpf_program__is_socket_filter(const struct bpf_program *prog);
LIBBPF_API bool bpf_program__is_tracepoint(const struct bpf_program *prog);
LIBBPF_API bool bpf_program__is_raw_tracepoint(const struct bpf_program *prog);
LIBBPF_API bool bpf_program__is_kprobe(const struct bpf_program *prog);
+LIBBPF_API bool bpf_program__is_lsm(const struct bpf_program *prog);
LIBBPF_API bool bpf_program__is_sched_cls(const struct bpf_program *prog);
LIBBPF_API bool bpf_program__is_sched_act(const struct bpf_program *prog);
LIBBPF_API bool bpf_program__is_xdp(const struct bpf_program *prog);
@@ -398,6 +417,8 @@ typedef void (*bpf_map_clear_priv_t)(struct bpf_map *, void *);
LIBBPF_API int bpf_map__set_priv(struct bpf_map *map, void *priv,
bpf_map_clear_priv_t clear_priv);
LIBBPF_API void *bpf_map__priv(const struct bpf_map *map);
+LIBBPF_API int bpf_map__set_initial_value(struct bpf_map *map,
+ const void *data, size_t size);
LIBBPF_API int bpf_map__reuse_fd(struct bpf_map *map, int fd);
LIBBPF_API int bpf_map__resize(struct bpf_map *map, __u32 max_entries);
LIBBPF_API bool bpf_map__is_offload_neutral(const struct bpf_map *map);
@@ -435,7 +456,15 @@ struct xdp_link_info {
__u8 attach_mode;
};
+struct bpf_xdp_set_link_opts {
+ size_t sz;
+ __u32 old_fd;
+};
+#define bpf_xdp_set_link_opts__last_field old_fd
+
LIBBPF_API int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags);
+LIBBPF_API int bpf_set_link_xdp_fd_opts(int ifindex, int fd, __u32 flags,
+ const struct bpf_xdp_set_link_opts *opts);
LIBBPF_API int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags);
LIBBPF_API int bpf_get_link_xdp_info(int ifindex, struct xdp_link_info *info,
size_t info_size, __u32 flags);
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index b035122142bb..bb8831605b25 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -235,3 +235,22 @@ LIBBPF_0.0.7 {
btf__align_of;
libbpf_find_kernel_btf;
} LIBBPF_0.0.6;
+
+LIBBPF_0.0.8 {
+ global:
+ bpf_link__fd;
+ bpf_link__open;
+ bpf_link__pin;
+ bpf_link__pin_path;
+ bpf_link__unpin;
+ bpf_link__update_program;
+ bpf_link_create;
+ bpf_link_update;
+ bpf_map__set_initial_value;
+ bpf_program__attach_cgroup;
+ bpf_program__attach_lsm;
+ bpf_program__is_lsm;
+ bpf_program__set_attach_target;
+ bpf_program__set_lsm;
+ bpf_set_link_xdp_fd_opts;
+} LIBBPF_0.0.7;
diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c
index b782ebef6ac9..2c92059c0c90 100644
--- a/tools/lib/bpf/libbpf_probes.c
+++ b/tools/lib/bpf/libbpf_probes.c
@@ -108,6 +108,7 @@ probe_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns,
case BPF_PROG_TYPE_TRACING:
case BPF_PROG_TYPE_STRUCT_OPS:
case BPF_PROG_TYPE_EXT:
+ case BPF_PROG_TYPE_LSM:
default:
break;
}
diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c
index 431bd25c6cdb..18b5319025e1 100644
--- a/tools/lib/bpf/netlink.c
+++ b/tools/lib/bpf/netlink.c
@@ -132,7 +132,8 @@ done:
return ret;
}
-int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
+static int __bpf_set_link_xdp_fd_replace(int ifindex, int fd, int old_fd,
+ __u32 flags)
{
int sock, seq = 0, ret;
struct nlattr *nla, *nla_xdp;
@@ -178,6 +179,14 @@ int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
nla->nla_len += nla_xdp->nla_len;
}
+ if (flags & XDP_FLAGS_REPLACE) {
+ nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len);
+ nla_xdp->nla_type = IFLA_XDP_EXPECTED_FD;
+ nla_xdp->nla_len = NLA_HDRLEN + sizeof(old_fd);
+ memcpy((char *)nla_xdp + NLA_HDRLEN, &old_fd, sizeof(old_fd));
+ nla->nla_len += nla_xdp->nla_len;
+ }
+
req.nh.nlmsg_len += NLA_ALIGN(nla->nla_len);
if (send(sock, &req, req.nh.nlmsg_len, 0) < 0) {
@@ -191,6 +200,29 @@ cleanup:
return ret;
}
+int bpf_set_link_xdp_fd_opts(int ifindex, int fd, __u32 flags,
+ const struct bpf_xdp_set_link_opts *opts)
+{
+ int old_fd = -1;
+
+ if (!OPTS_VALID(opts, bpf_xdp_set_link_opts))
+ return -EINVAL;
+
+ if (OPTS_HAS(opts, old_fd)) {
+ old_fd = OPTS_GET(opts, old_fd, -1);
+ flags |= XDP_FLAGS_REPLACE;
+ }
+
+ return __bpf_set_link_xdp_fd_replace(ifindex, fd,
+ old_fd,
+ flags);
+}
+
+int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
+{
+ return __bpf_set_link_xdp_fd_replace(ifindex, fd, 0, flags);
+}
+
static int __dump_link_nlmsg(struct nlmsghdr *nlh,
libbpf_dump_nlmsg_t dump_link_nlmsg, void *cookie)
{
diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c
index 9807903f121e..f7f4efb70a4c 100644
--- a/tools/lib/bpf/xsk.c
+++ b/tools/lib/bpf/xsk.c
@@ -280,7 +280,11 @@ int xsk_umem__create_v0_0_4(struct xsk_umem **umem_ptr, void *umem_area,
fill->consumer = map + off.fr.consumer;
fill->flags = map + off.fr.flags;
fill->ring = map + off.fr.desc;
- fill->cached_cons = umem->config.fill_size;
+ fill->cached_prod = *fill->producer;
+ /* cached_cons is "size" bigger than the real consumer pointer
+ * See xsk_prod_nb_free
+ */
+ fill->cached_cons = *fill->consumer + umem->config.fill_size;
map = mmap(NULL, off.cr.desc + umem->config.comp_size * sizeof(__u64),
PROT_READ | PROT_WRITE, MAP_SHARED | MAP_POPULATE, umem->fd,
@@ -297,6 +301,8 @@ int xsk_umem__create_v0_0_4(struct xsk_umem **umem_ptr, void *umem_area,
comp->consumer = map + off.cr.consumer;
comp->flags = map + off.cr.flags;
comp->ring = map + off.cr.desc;
+ comp->cached_prod = *comp->producer;
+ comp->cached_cons = *comp->consumer;
*umem_ptr = umem;
return 0;
@@ -672,6 +678,8 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname,
rx->consumer = rx_map + off.rx.consumer;
rx->flags = rx_map + off.rx.flags;
rx->ring = rx_map + off.rx.desc;
+ rx->cached_prod = *rx->producer;
+ rx->cached_cons = *rx->consumer;
}
xsk->rx = rx;
@@ -691,7 +699,11 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname,
tx->consumer = tx_map + off.tx.consumer;
tx->flags = tx_map + off.tx.flags;
tx->ring = tx_map + off.tx.desc;
- tx->cached_cons = xsk->config.tx_size;
+ tx->cached_prod = *tx->producer;
+ /* cached_cons is r->size bigger than the real consumer pointer
+ * See xsk_prod_nb_free
+ */
+ tx->cached_cons = *tx->consumer + xsk->config.tx_size;
}
xsk->tx = tx;
diff --git a/tools/lib/perf/Documentation/examples/counting.c b/tools/lib/perf/Documentation/examples/counting.c
new file mode 100644
index 000000000000..6085693571ef
--- /dev/null
+++ b/tools/lib/perf/Documentation/examples/counting.c
@@ -0,0 +1,83 @@
+#include <linux/perf_event.h>
+#include <perf/evlist.h>
+#include <perf/evsel.h>
+#include <perf/cpumap.h>
+#include <perf/threadmap.h>
+#include <perf/mmap.h>
+#include <perf/core.h>
+#include <perf/event.h>
+#include <stdio.h>
+#include <unistd.h>
+
+static int libperf_print(enum libperf_print_level level,
+ const char *fmt, va_list ap)
+{
+ return vfprintf(stderr, fmt, ap);
+}
+
+int main(int argc, char **argv)
+{
+ int count = 100000, err = 0;
+ struct perf_evlist *evlist;
+ struct perf_evsel *evsel;
+ struct perf_thread_map *threads;
+ struct perf_counts_values counts;
+
+ struct perf_event_attr attr1 = {
+ .type = PERF_TYPE_SOFTWARE,
+ .config = PERF_COUNT_SW_CPU_CLOCK,
+ .read_format = PERF_FORMAT_TOTAL_TIME_ENABLED|PERF_FORMAT_TOTAL_TIME_RUNNING,
+ .disabled = 1,
+ };
+ struct perf_event_attr attr2 = {
+ .type = PERF_TYPE_SOFTWARE,
+ .config = PERF_COUNT_SW_TASK_CLOCK,
+ .read_format = PERF_FORMAT_TOTAL_TIME_ENABLED|PERF_FORMAT_TOTAL_TIME_RUNNING,
+ .disabled = 1,
+ };
+
+ libperf_init(libperf_print);
+ threads = perf_thread_map__new_dummy();
+ if (!threads) {
+ fprintf(stderr, "failed to create threads\n");
+ return -1;
+ }
+ perf_thread_map__set_pid(threads, 0, 0);
+ evlist = perf_evlist__new();
+ if (!evlist) {
+ fprintf(stderr, "failed to create evlist\n");
+ goto out_threads;
+ }
+ evsel = perf_evsel__new(&attr1);
+ if (!evsel) {
+ fprintf(stderr, "failed to create evsel1\n");
+ goto out_evlist;
+ }
+ perf_evlist__add(evlist, evsel);
+ evsel = perf_evsel__new(&attr2);
+ if (!evsel) {
+ fprintf(stderr, "failed to create evsel2\n");
+ goto out_evlist;
+ }
+ perf_evlist__add(evlist, evsel);
+ perf_evlist__set_maps(evlist, NULL, threads);
+ err = perf_evlist__open(evlist);
+ if (err) {
+ fprintf(stderr, "failed to open evsel\n");
+ goto out_evlist;
+ }
+ perf_evlist__enable(evlist);
+ while (count--);
+ perf_evlist__disable(evlist);
+ perf_evlist__for_each_evsel(evlist, evsel) {
+ perf_evsel__read(evsel, 0, 0, &counts);
+ fprintf(stdout, "count %llu, enabled %llu, run %llu\n",
+ counts.val, counts.ena, counts.run);
+ }
+ perf_evlist__close(evlist);
+out_evlist:
+ perf_evlist__delete(evlist);
+out_threads:
+ perf_thread_map__put(threads);
+ return err;
+}
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index beaa8b8c08ff..e1bd2a93c6db 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -5541,7 +5541,7 @@ static void print_event_time(struct tep_handle *tep, struct trace_seq *s,
if (p10 > 1 && p10 < time)
trace_seq_printf(s, "%5llu.%0*llu", time / p10, prec, time % p10);
else
- trace_seq_printf(s, "%12llu\n", time);
+ trace_seq_printf(s, "%12llu", time);
}
struct print_event_type {
diff --git a/tools/objtool/Build b/tools/objtool/Build
index 8dc4f0848362..66f44f5cd2a6 100644
--- a/tools/objtool/Build
+++ b/tools/objtool/Build
@@ -11,6 +11,7 @@ objtool-y += objtool.o
objtool-y += libstring.o
objtool-y += libctype.o
objtool-y += str_error_r.o
+objtool-y += librbtree.o
CFLAGS += -I$(srctree)/tools/lib
@@ -25,3 +26,7 @@ $(OUTPUT)libctype.o: ../lib/ctype.c FORCE
$(OUTPUT)str_error_r.o: ../lib/str_error_r.c FORCE
$(call rule_mkdir)
$(call if_changed_dep,cc_o_c)
+
+$(OUTPUT)librbtree.o: ../lib/rbtree.c FORCE
+ $(call rule_mkdir)
+ $(call if_changed_dep,cc_o_c)
diff --git a/tools/objtool/builtin-check.c b/tools/objtool/builtin-check.c
index c807984a03c1..10fbe75ab43d 100644
--- a/tools/objtool/builtin-check.c
+++ b/tools/objtool/builtin-check.c
@@ -17,7 +17,7 @@
#include "builtin.h"
#include "check.h"
-bool no_fp, no_unreachable, retpoline, module, backtrace, uaccess;
+bool no_fp, no_unreachable, retpoline, module, backtrace, uaccess, stats;
static const char * const check_usage[] = {
"objtool check [<options>] file.o",
@@ -31,6 +31,7 @@ const struct option check_options[] = {
OPT_BOOLEAN('m', "module", &module, "Indicates the object will be part of a kernel module"),
OPT_BOOLEAN('b', "backtrace", &backtrace, "unwind on error"),
OPT_BOOLEAN('a', "uaccess", &uaccess, "enable uaccess checking"),
+ OPT_BOOLEAN('s', "stats", &stats, "print statistics"),
OPT_END(),
};
diff --git a/tools/objtool/builtin.h b/tools/objtool/builtin.h
index a32736f8d2a4..0b907902ee79 100644
--- a/tools/objtool/builtin.h
+++ b/tools/objtool/builtin.h
@@ -8,7 +8,7 @@
#include <subcmd/parse-options.h>
extern const struct option check_options[];
-extern bool no_fp, no_unreachable, retpoline, module, backtrace, uaccess;
+extern bool no_fp, no_unreachable, retpoline, module, backtrace, uaccess, stats;
extern int cmd_check(int argc, const char **argv);
extern int cmd_orc(int argc, const char **argv);
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 4768d91c6d68..8dd01f986fbb 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -72,22 +72,22 @@ static struct instruction *next_insn_same_func(struct objtool_file *file,
return find_insn(file, func->cfunc->sec, func->cfunc->offset);
}
-#define func_for_each_insn_all(file, func, insn) \
+#define func_for_each_insn(file, func, insn) \
for (insn = find_insn(file, func->sec, func->offset); \
insn; \
insn = next_insn_same_func(file, insn))
-#define func_for_each_insn(file, func, insn) \
- for (insn = find_insn(file, func->sec, func->offset); \
+#define sym_for_each_insn(file, sym, insn) \
+ for (insn = find_insn(file, sym->sec, sym->offset); \
insn && &insn->list != &file->insn_list && \
- insn->sec == func->sec && \
- insn->offset < func->offset + func->len; \
+ insn->sec == sym->sec && \
+ insn->offset < sym->offset + sym->len; \
insn = list_next_entry(insn, list))
-#define func_for_each_insn_continue_reverse(file, func, insn) \
+#define sym_for_each_insn_continue_reverse(file, sym, insn) \
for (insn = list_prev_entry(insn, list); \
&insn->list != &file->insn_list && \
- insn->sec == func->sec && insn->offset >= func->offset; \
+ insn->sec == sym->sec && insn->offset >= sym->offset; \
insn = list_prev_entry(insn, list))
#define sec_for_each_insn_from(file, insn) \
@@ -97,14 +97,19 @@ static struct instruction *next_insn_same_func(struct objtool_file *file,
for (insn = next_insn_same_sec(file, insn); insn; \
insn = next_insn_same_sec(file, insn))
+static bool is_static_jump(struct instruction *insn)
+{
+ return insn->type == INSN_JUMP_CONDITIONAL ||
+ insn->type == INSN_JUMP_UNCONDITIONAL;
+}
+
static bool is_sibling_call(struct instruction *insn)
{
/* An indirect jump is either a sibling call or a jump to a table. */
if (insn->type == INSN_JUMP_DYNAMIC)
return list_empty(&insn->alts);
- if (insn->type != INSN_JUMP_CONDITIONAL &&
- insn->type != INSN_JUMP_UNCONDITIONAL)
+ if (!is_static_jump(insn))
return false;
/* add_jump_destinations() sets insn->call_dest for sibling calls. */
@@ -165,7 +170,7 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func,
if (!insn->func)
return false;
- func_for_each_insn_all(file, func, insn) {
+ func_for_each_insn(file, func, insn) {
empty = false;
if (insn->type == INSN_RETURN)
@@ -180,7 +185,7 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func,
* case, the function's dead-end status depends on whether the target
* of the sibling call returns.
*/
- func_for_each_insn_all(file, func, insn) {
+ func_for_each_insn(file, func, insn) {
if (is_sibling_call(insn)) {
struct instruction *dest = insn->jump_dest;
@@ -234,6 +239,7 @@ static int decode_instructions(struct objtool_file *file)
struct symbol *func;
unsigned long offset;
struct instruction *insn;
+ unsigned long nr_insns = 0;
int ret;
for_each_sec(file, sec) {
@@ -269,6 +275,7 @@ static int decode_instructions(struct objtool_file *file)
hash_add(file->insn_hash, &insn->hash, insn->offset);
list_add_tail(&insn->list, &file->insn_list);
+ nr_insns++;
}
list_for_each_entry(func, &sec->symbol_list, list) {
@@ -281,11 +288,14 @@ static int decode_instructions(struct objtool_file *file)
return -1;
}
- func_for_each_insn(file, func, insn)
+ sym_for_each_insn(file, func, insn)
insn->func = func;
}
}
+ if (stats)
+ printf("nr_insns: %lu\n", nr_insns);
+
return 0;
err:
@@ -415,8 +425,8 @@ static void add_ignores(struct objtool_file *file)
break;
case STT_SECTION:
- func = find_symbol_by_offset(rela->sym->sec, rela->addend);
- if (!func || func->type != STT_FUNC)
+ func = find_func_by_offset(rela->sym->sec, rela->addend);
+ if (!func)
continue;
break;
@@ -425,7 +435,7 @@ static void add_ignores(struct objtool_file *file)
continue;
}
- func_for_each_insn_all(file, func, insn)
+ func_for_each_insn(file, func, insn)
insn->ignore = true;
}
}
@@ -478,6 +488,7 @@ static const char *uaccess_safe_builtin[] = {
"__sanitizer_cov_trace_cmp2",
"__sanitizer_cov_trace_cmp4",
"__sanitizer_cov_trace_cmp8",
+ "__sanitizer_cov_trace_switch",
/* UBSAN */
"ubsan_type_mismatch_common",
"__ubsan_handle_type_mismatch",
@@ -553,15 +564,14 @@ static int add_jump_destinations(struct objtool_file *file)
unsigned long dest_off;
for_each_insn(file, insn) {
- if (insn->type != INSN_JUMP_CONDITIONAL &&
- insn->type != INSN_JUMP_UNCONDITIONAL)
+ if (!is_static_jump(insn))
continue;
if (insn->ignore || insn->offset == FAKE_JUMP_OFFSET)
continue;
- rela = find_rela_by_dest_range(insn->sec, insn->offset,
- insn->len);
+ rela = find_rela_by_dest_range(file->elf, insn->sec,
+ insn->offset, insn->len);
if (!rela) {
dest_sec = insn->sec;
dest_off = insn->offset + insn->len + insn->immediate;
@@ -657,14 +667,18 @@ static int add_call_destinations(struct objtool_file *file)
if (insn->type != INSN_CALL)
continue;
- rela = find_rela_by_dest_range(insn->sec, insn->offset,
- insn->len);
+ rela = find_rela_by_dest_range(file->elf, insn->sec,
+ insn->offset, insn->len);
if (!rela) {
dest_off = insn->offset + insn->len + insn->immediate;
- insn->call_dest = find_symbol_by_offset(insn->sec,
- dest_off);
+ insn->call_dest = find_func_by_offset(insn->sec, dest_off);
+ if (!insn->call_dest)
+ insn->call_dest = find_symbol_by_offset(insn->sec, dest_off);
- if (!insn->call_dest && !insn->ignore) {
+ if (insn->ignore)
+ continue;
+
+ if (!insn->call_dest) {
WARN_FUNC("unsupported intra-function call",
insn->sec, insn->offset);
if (retpoline)
@@ -672,11 +686,16 @@ static int add_call_destinations(struct objtool_file *file)
return -1;
}
+ if (insn->func && insn->call_dest->type != STT_FUNC) {
+ WARN_FUNC("unsupported call to non-function",
+ insn->sec, insn->offset);
+ return -1;
+ }
+
} else if (rela->sym->type == STT_SECTION) {
- insn->call_dest = find_symbol_by_offset(rela->sym->sec,
- rela->addend+4);
- if (!insn->call_dest ||
- insn->call_dest->type != STT_FUNC) {
+ insn->call_dest = find_func_by_offset(rela->sym->sec,
+ rela->addend+4);
+ if (!insn->call_dest) {
WARN_FUNC("can't find call dest symbol at %s+0x%x",
insn->sec, insn->offset,
rela->sym->sec->name,
@@ -764,8 +783,28 @@ static int handle_group_alt(struct objtool_file *file,
insn->ignore = orig_insn->ignore_alts;
insn->func = orig_insn->func;
- if (insn->type != INSN_JUMP_CONDITIONAL &&
- insn->type != INSN_JUMP_UNCONDITIONAL)
+ /*
+ * Since alternative replacement code is copy/pasted by the
+ * kernel after applying relocations, generally such code can't
+ * have relative-address relocation references to outside the
+ * .altinstr_replacement section, unless the arch's
+ * alternatives code can adjust the relative offsets
+ * accordingly.
+ *
+ * The x86 alternatives code adjusts the offsets only when it
+ * encounters a branch instruction at the very beginning of the
+ * replacement group.
+ */
+ if ((insn->offset != special_alt->new_off ||
+ (insn->type != INSN_CALL && !is_static_jump(insn))) &&
+ find_rela_by_dest_range(file->elf, insn->sec, insn->offset, insn->len)) {
+
+ WARN_FUNC("unsupported relocation in alternatives section",
+ insn->sec, insn->offset);
+ return -1;
+ }
+
+ if (!is_static_jump(insn))
continue;
if (!insn->immediate)
@@ -1001,7 +1040,7 @@ static struct rela *find_jump_table(struct objtool_file *file,
struct instruction *insn)
{
struct rela *text_rela, *table_rela;
- struct instruction *orig_insn = insn;
+ struct instruction *dest_insn, *orig_insn = insn;
struct section *table_sec;
unsigned long table_offset;
@@ -1028,8 +1067,8 @@ static struct rela *find_jump_table(struct objtool_file *file,
break;
/* look for a relocation which references .rodata */
- text_rela = find_rela_by_dest_range(insn->sec, insn->offset,
- insn->len);
+ text_rela = find_rela_by_dest_range(file->elf, insn->sec,
+ insn->offset, insn->len);
if (!text_rela || text_rela->sym->type != STT_SECTION ||
!text_rela->sym->sec->rodata)
continue;
@@ -1053,10 +1092,17 @@ static struct rela *find_jump_table(struct objtool_file *file,
strcmp(table_sec->name, C_JUMP_TABLE_SECTION))
continue;
- /* Each table entry has a rela associated with it. */
- table_rela = find_rela_by_dest(table_sec, table_offset);
+ /*
+ * Each table entry has a rela associated with it. The rela
+ * should reference text in the same function as the original
+ * instruction.
+ */
+ table_rela = find_rela_by_dest(file->elf, table_sec, table_offset);
if (!table_rela)
continue;
+ dest_insn = find_insn(file, table_rela->sym->sec, table_rela->addend);
+ if (!dest_insn || !dest_insn->func || dest_insn->func->pfunc != func)
+ continue;
/*
* Use of RIP-relative switch jumps is quite rare, and
@@ -1082,7 +1128,7 @@ static void mark_func_jump_tables(struct objtool_file *file,
struct instruction *insn, *last = NULL;
struct rela *rela;
- func_for_each_insn_all(file, func, insn) {
+ func_for_each_insn(file, func, insn) {
if (!last)
last = insn;
@@ -1117,7 +1163,7 @@ static int add_func_jump_tables(struct objtool_file *file,
struct instruction *insn;
int ret;
- func_for_each_insn_all(file, func, insn) {
+ func_for_each_insn(file, func, insn) {
if (!insn->jump_table)
continue;
@@ -1187,7 +1233,7 @@ static int read_unwind_hints(struct objtool_file *file)
for (i = 0; i < sec->len / sizeof(struct unwind_hint); i++) {
hint = (struct unwind_hint *)sec->data->d_buf + i;
- rela = find_rela_by_dest(sec, i * sizeof(*hint));
+ rela = find_rela_by_dest(file->elf, sec, i * sizeof(*hint));
if (!rela) {
WARN("can't find rela for unwind_hints[%d]", i);
return -1;
@@ -1935,6 +1981,41 @@ static int validate_sibling_call(struct instruction *insn, struct insn_state *st
return validate_call(insn, state);
}
+static int validate_return(struct symbol *func, struct instruction *insn, struct insn_state *state)
+{
+ if (state->uaccess && !func_uaccess_safe(func)) {
+ WARN_FUNC("return with UACCESS enabled",
+ insn->sec, insn->offset);
+ return 1;
+ }
+
+ if (!state->uaccess && func_uaccess_safe(func)) {
+ WARN_FUNC("return with UACCESS disabled from a UACCESS-safe function",
+ insn->sec, insn->offset);
+ return 1;
+ }
+
+ if (state->df) {
+ WARN_FUNC("return with DF set",
+ insn->sec, insn->offset);
+ return 1;
+ }
+
+ if (func && has_modified_stack_frame(state)) {
+ WARN_FUNC("return with modified stack frame",
+ insn->sec, insn->offset);
+ return 1;
+ }
+
+ if (state->bp_scratch) {
+ WARN("%s uses BP as a scratch register",
+ func->name);
+ return 1;
+ }
+
+ return 0;
+}
+
/*
* Follow the branch starting at the given instruction, and recursively follow
* any other branches (jumps). Meanwhile, track the frame pointer state at
@@ -1989,7 +2070,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func,
i = insn;
save_insn = NULL;
- func_for_each_insn_continue_reverse(file, func, i) {
+ sym_for_each_insn_continue_reverse(file, func, i) {
if (i->save) {
save_insn = i;
break;
@@ -2050,34 +2131,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func,
switch (insn->type) {
case INSN_RETURN:
- if (state.uaccess && !func_uaccess_safe(func)) {
- WARN_FUNC("return with UACCESS enabled", sec, insn->offset);
- return 1;
- }
-
- if (!state.uaccess && func_uaccess_safe(func)) {
- WARN_FUNC("return with UACCESS disabled from a UACCESS-safe function", sec, insn->offset);
- return 1;
- }
-
- if (state.df) {
- WARN_FUNC("return with DF set", sec, insn->offset);
- return 1;
- }
-
- if (func && has_modified_stack_frame(&state)) {
- WARN_FUNC("return with modified stack frame",
- sec, insn->offset);
- return 1;
- }
-
- if (state.bp_scratch) {
- WARN("%s uses BP as a scratch register",
- func->name);
- return 1;
- }
-
- return 0;
+ return validate_return(func, insn, &state);
case INSN_CALL:
case INSN_CALL_DYNAMIC:
@@ -2342,9 +2396,8 @@ static bool ignore_unreachable_insn(struct instruction *insn)
return false;
}
-static int validate_functions(struct objtool_file *file)
+static int validate_section(struct objtool_file *file, struct section *sec)
{
- struct section *sec;
struct symbol *func;
struct instruction *insn;
struct insn_state state;
@@ -2357,36 +2410,45 @@ static int validate_functions(struct objtool_file *file)
CFI_NUM_REGS * sizeof(struct cfi_reg));
state.stack_size = initial_func_cfi.cfa.offset;
- for_each_sec(file, sec) {
- list_for_each_entry(func, &sec->symbol_list, list) {
- if (func->type != STT_FUNC)
- continue;
+ list_for_each_entry(func, &sec->symbol_list, list) {
+ if (func->type != STT_FUNC)
+ continue;
- if (!func->len) {
- WARN("%s() is missing an ELF size annotation",
- func->name);
- warnings++;
- }
+ if (!func->len) {
+ WARN("%s() is missing an ELF size annotation",
+ func->name);
+ warnings++;
+ }
- if (func->pfunc != func || func->alias != func)
- continue;
+ if (func->pfunc != func || func->alias != func)
+ continue;
- insn = find_insn(file, sec, func->offset);
- if (!insn || insn->ignore || insn->visited)
- continue;
+ insn = find_insn(file, sec, func->offset);
+ if (!insn || insn->ignore || insn->visited)
+ continue;
- state.uaccess = func->uaccess_safe;
+ state.uaccess = func->uaccess_safe;
- ret = validate_branch(file, func, insn, state);
- if (ret && backtrace)
- BT_FUNC("<=== (func)", insn);
- warnings += ret;
- }
+ ret = validate_branch(file, func, insn, state);
+ if (ret && backtrace)
+ BT_FUNC("<=== (func)", insn);
+ warnings += ret;
}
return warnings;
}
+static int validate_functions(struct objtool_file *file)
+{
+ struct section *sec;
+ int warnings = 0;
+
+ for_each_sec(file, sec)
+ warnings += validate_section(file, sec);
+
+ return warnings;
+}
+
static int validate_reachable_instructions(struct objtool_file *file)
{
struct instruction *insn;
@@ -2405,23 +2467,6 @@ static int validate_reachable_instructions(struct objtool_file *file)
return 0;
}
-static void cleanup(struct objtool_file *file)
-{
- struct instruction *insn, *tmpinsn;
- struct alternative *alt, *tmpalt;
-
- list_for_each_entry_safe(insn, tmpinsn, &file->insn_list, list) {
- list_for_each_entry_safe(alt, tmpalt, &insn->alts, list) {
- list_del(&alt->list);
- free(alt);
- }
- list_del(&insn->list);
- hash_del(&insn->hash);
- free(insn);
- }
- elf_close(file->elf);
-}
-
static struct objtool_file file;
int check(const char *_objname, bool orc)
@@ -2489,10 +2534,14 @@ int check(const char *_objname, bool orc)
}
out:
- cleanup(&file);
+ if (ret < 0) {
+ /*
+ * Fatal error. The binary is corrupt or otherwise broken in
+ * some way, or objtool itself is broken. Fail the kernel
+ * build.
+ */
+ return ret;
+ }
- /* ignore warnings for now until we get all the code cleaned up */
- if (ret || warnings)
- return 0;
return 0;
}
diff --git a/tools/objtool/check.h b/tools/objtool/check.h
index 6d875ca6fce0..f0ce8ffe7135 100644
--- a/tools/objtool/check.h
+++ b/tools/objtool/check.h
@@ -50,7 +50,7 @@ struct instruction {
struct objtool_file {
struct elf *elf;
struct list_head insn_list;
- DECLARE_HASHTABLE(insn_hash, 16);
+ DECLARE_HASHTABLE(insn_hash, 20);
bool ignore_unreachables, c_file, hints, rodata;
};
diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c
index edba4745f25a..09ddc8f1def3 100644
--- a/tools/objtool/elf.c
+++ b/tools/objtool/elf.c
@@ -15,17 +15,107 @@
#include <string.h>
#include <unistd.h>
#include <errno.h>
+#include "builtin.h"
#include "elf.h"
#include "warn.h"
#define MAX_NAME_LEN 128
+static inline u32 str_hash(const char *str)
+{
+ return jhash(str, strlen(str), 0);
+}
+
+static void rb_add(struct rb_root *tree, struct rb_node *node,
+ int (*cmp)(struct rb_node *, const struct rb_node *))
+{
+ struct rb_node **link = &tree->rb_node;
+ struct rb_node *parent = NULL;
+
+ while (*link) {
+ parent = *link;
+ if (cmp(node, parent) < 0)
+ link = &parent->rb_left;
+ else
+ link = &parent->rb_right;
+ }
+
+ rb_link_node(node, parent, link);
+ rb_insert_color(node, tree);
+}
+
+static struct rb_node *rb_find_first(struct rb_root *tree, const void *key,
+ int (*cmp)(const void *key, const struct rb_node *))
+{
+ struct rb_node *node = tree->rb_node;
+ struct rb_node *match = NULL;
+
+ while (node) {
+ int c = cmp(key, node);
+ if (c <= 0) {
+ if (!c)
+ match = node;
+ node = node->rb_left;
+ } else if (c > 0) {
+ node = node->rb_right;
+ }
+ }
+
+ return match;
+}
+
+static struct rb_node *rb_next_match(struct rb_node *node, const void *key,
+ int (*cmp)(const void *key, const struct rb_node *))
+{
+ node = rb_next(node);
+ if (node && cmp(key, node))
+ node = NULL;
+ return node;
+}
+
+#define rb_for_each(tree, node, key, cmp) \
+ for ((node) = rb_find_first((tree), (key), (cmp)); \
+ (node); (node) = rb_next_match((node), (key), (cmp)))
+
+static int symbol_to_offset(struct rb_node *a, const struct rb_node *b)
+{
+ struct symbol *sa = rb_entry(a, struct symbol, node);
+ struct symbol *sb = rb_entry(b, struct symbol, node);
+
+ if (sa->offset < sb->offset)
+ return -1;
+ if (sa->offset > sb->offset)
+ return 1;
+
+ if (sa->len < sb->len)
+ return -1;
+ if (sa->len > sb->len)
+ return 1;
+
+ sa->alias = sb;
+
+ return 0;
+}
+
+static int symbol_by_offset(const void *key, const struct rb_node *node)
+{
+ const struct symbol *s = rb_entry(node, struct symbol, node);
+ const unsigned long *o = key;
+
+ if (*o < s->offset)
+ return -1;
+ if (*o > s->offset + s->len)
+ return 1;
+
+ return 0;
+}
+
struct section *find_section_by_name(struct elf *elf, const char *name)
{
struct section *sec;
- list_for_each_entry(sec, &elf->sections, list)
+ hash_for_each_possible(elf->section_name_hash, sec, name_hash, str_hash(name))
if (!strcmp(sec->name, name))
return sec;
@@ -37,7 +127,7 @@ static struct section *find_section_by_index(struct elf *elf,
{
struct section *sec;
- list_for_each_entry(sec, &elf->sections, list)
+ hash_for_each_possible(elf->section_hash, sec, hash, idx)
if (sec->idx == idx)
return sec;
@@ -46,88 +136,116 @@ static struct section *find_section_by_index(struct elf *elf,
static struct symbol *find_symbol_by_index(struct elf *elf, unsigned int idx)
{
- struct section *sec;
struct symbol *sym;
- list_for_each_entry(sec, &elf->sections, list)
- hash_for_each_possible(sec->symbol_hash, sym, hash, idx)
- if (sym->idx == idx)
- return sym;
+ hash_for_each_possible(elf->symbol_hash, sym, hash, idx)
+ if (sym->idx == idx)
+ return sym;
return NULL;
}
struct symbol *find_symbol_by_offset(struct section *sec, unsigned long offset)
{
- struct symbol *sym;
+ struct rb_node *node;
- list_for_each_entry(sym, &sec->symbol_list, list)
- if (sym->type != STT_SECTION &&
- sym->offset == offset)
- return sym;
+ rb_for_each(&sec->symbol_tree, node, &offset, symbol_by_offset) {
+ struct symbol *s = rb_entry(node, struct symbol, node);
+
+ if (s->offset == offset && s->type != STT_SECTION)
+ return s;
+ }
return NULL;
}
-struct symbol *find_symbol_by_name(struct elf *elf, const char *name)
+struct symbol *find_func_by_offset(struct section *sec, unsigned long offset)
{
- struct section *sec;
- struct symbol *sym;
+ struct rb_node *node;
- list_for_each_entry(sec, &elf->sections, list)
- list_for_each_entry(sym, &sec->symbol_list, list)
- if (!strcmp(sym->name, name))
- return sym;
+ rb_for_each(&sec->symbol_tree, node, &offset, symbol_by_offset) {
+ struct symbol *s = rb_entry(node, struct symbol, node);
+
+ if (s->offset == offset && s->type == STT_FUNC)
+ return s;
+ }
return NULL;
}
struct symbol *find_symbol_containing(struct section *sec, unsigned long offset)
{
- struct symbol *sym;
+ struct rb_node *node;
- list_for_each_entry(sym, &sec->symbol_list, list)
- if (sym->type != STT_SECTION &&
- offset >= sym->offset && offset < sym->offset + sym->len)
- return sym;
+ rb_for_each(&sec->symbol_tree, node, &offset, symbol_by_offset) {
+ struct symbol *s = rb_entry(node, struct symbol, node);
+
+ if (s->type != STT_SECTION)
+ return s;
+ }
return NULL;
}
-struct rela *find_rela_by_dest_range(struct section *sec, unsigned long offset,
- unsigned int len)
+struct symbol *find_func_containing(struct section *sec, unsigned long offset)
{
- struct rela *rela;
- unsigned long o;
+ struct rb_node *node;
- if (!sec->rela)
- return NULL;
+ rb_for_each(&sec->symbol_tree, node, &offset, symbol_by_offset) {
+ struct symbol *s = rb_entry(node, struct symbol, node);
- for (o = offset; o < offset + len; o++)
- hash_for_each_possible(sec->rela->rela_hash, rela, hash, o)
- if (rela->offset == o)
- return rela;
+ if (s->type == STT_FUNC)
+ return s;
+ }
return NULL;
}
-struct rela *find_rela_by_dest(struct section *sec, unsigned long offset)
+struct symbol *find_symbol_by_name(struct elf *elf, const char *name)
{
- return find_rela_by_dest_range(sec, offset, 1);
+ struct symbol *sym;
+
+ hash_for_each_possible(elf->symbol_name_hash, sym, name_hash, str_hash(name))
+ if (!strcmp(sym->name, name))
+ return sym;
+
+ return NULL;
}
-struct symbol *find_containing_func(struct section *sec, unsigned long offset)
+struct rela *find_rela_by_dest_range(struct elf *elf, struct section *sec,
+ unsigned long offset, unsigned int len)
{
- struct symbol *func;
+ struct rela *rela, *r = NULL;
+ unsigned long o;
+
+ if (!sec->rela)
+ return NULL;
- list_for_each_entry(func, &sec->symbol_list, list)
- if (func->type == STT_FUNC && offset >= func->offset &&
- offset < func->offset + func->len)
- return func;
+ sec = sec->rela;
+
+ for_offset_range(o, offset, offset + len) {
+ hash_for_each_possible(elf->rela_hash, rela, hash,
+ sec_offset_hash(sec, o)) {
+ if (rela->sec != sec)
+ continue;
+
+ if (rela->offset >= offset && rela->offset < offset + len) {
+ if (!r || rela->offset < r->offset)
+ r = rela;
+ }
+ }
+ if (r)
+ return r;
+ }
return NULL;
}
+struct rela *find_rela_by_dest(struct elf *elf, struct section *sec, unsigned long offset)
+{
+ return find_rela_by_dest_range(elf, sec, offset, 1);
+}
+
static int read_sections(struct elf *elf)
{
Elf_Scn *s = NULL;
@@ -155,10 +273,6 @@ static int read_sections(struct elf *elf)
INIT_LIST_HEAD(&sec->symbol_list);
INIT_LIST_HEAD(&sec->rela_list);
- hash_init(sec->rela_hash);
- hash_init(sec->symbol_hash);
-
- list_add_tail(&sec->list, &elf->sections);
s = elf_getscn(elf->elf, i);
if (!s) {
@@ -193,8 +307,15 @@ static int read_sections(struct elf *elf)
}
}
sec->len = sec->sh.sh_size;
+
+ list_add_tail(&sec->list, &elf->sections);
+ hash_add(elf->section_hash, &sec->hash, sec->idx);
+ hash_add(elf->section_name_hash, &sec->name_hash, str_hash(sec->name));
}
+ if (stats)
+ printf("nr_sections: %lu\n", (unsigned long)sections_nr);
+
/* sanity check, one more call to elf_nextscn() should return NULL */
if (elf_nextscn(elf->elf, s)) {
WARN("section entry mismatch");
@@ -207,8 +328,9 @@ static int read_sections(struct elf *elf)
static int read_symbols(struct elf *elf)
{
struct section *symtab, *sec;
- struct symbol *sym, *pfunc, *alias;
- struct list_head *entry, *tmp;
+ struct symbol *sym, *pfunc;
+ struct list_head *entry;
+ struct rb_node *pnode;
int symbols_nr, i;
char *coldstr;
@@ -227,7 +349,7 @@ static int read_symbols(struct elf *elf)
return -1;
}
memset(sym, 0, sizeof(*sym));
- alias = sym;
+ sym->alias = sym;
sym->idx = i;
@@ -265,33 +387,20 @@ static int read_symbols(struct elf *elf)
sym->offset = sym->sym.st_value;
sym->len = sym->sym.st_size;
- /* sorted insert into a per-section list */
- entry = &sym->sec->symbol_list;
- list_for_each_prev(tmp, &sym->sec->symbol_list) {
- struct symbol *s;
-
- s = list_entry(tmp, struct symbol, list);
-
- if (sym->offset > s->offset) {
- entry = tmp;
- break;
- }
-
- if (sym->offset == s->offset) {
- if (sym->len && sym->len == s->len && alias == sym)
- alias = s;
-
- if (sym->len >= s->len) {
- entry = tmp;
- break;
- }
- }
- }
- sym->alias = alias;
+ rb_add(&sym->sec->symbol_tree, &sym->node, symbol_to_offset);
+ pnode = rb_prev(&sym->node);
+ if (pnode)
+ entry = &rb_entry(pnode, struct symbol, node)->list;
+ else
+ entry = &sym->sec->symbol_list;
list_add(&sym->list, entry);
- hash_add(sym->sec->symbol_hash, &sym->hash, sym->idx);
+ hash_add(elf->symbol_hash, &sym->hash, sym->idx);
+ hash_add(elf->symbol_name_hash, &sym->name_hash, str_hash(sym->name));
}
+ if (stats)
+ printf("nr_symbols: %lu\n", (unsigned long)symbols_nr);
+
/* Create parent/child links for any cold subfunctions */
list_for_each_entry(sec, &elf->sections, list) {
list_for_each_entry(sym, &sec->symbol_list, list) {
@@ -353,6 +462,7 @@ static int read_relas(struct elf *elf)
struct rela *rela;
int i;
unsigned int symndx;
+ unsigned long nr_rela, max_rela = 0, tot_rela = 0;
list_for_each_entry(sec, &elf->sections, list) {
if (sec->sh.sh_type != SHT_RELA)
@@ -367,6 +477,7 @@ static int read_relas(struct elf *elf)
sec->base->rela = sec;
+ nr_rela = 0;
for (i = 0; i < sec->sh.sh_size / sec->sh.sh_entsize; i++) {
rela = malloc(sizeof(*rela));
if (!rela) {
@@ -393,9 +504,16 @@ static int read_relas(struct elf *elf)
}
list_add_tail(&rela->list, &sec->rela_list);
- hash_add(sec->rela_hash, &rela->hash, rela->offset);
-
+ hash_add(elf->rela_hash, &rela->hash, rela_hash(rela));
+ nr_rela++;
}
+ max_rela = max(max_rela, nr_rela);
+ tot_rela += nr_rela;
+ }
+
+ if (stats) {
+ printf("max_rela: %lu\n", max_rela);
+ printf("tot_rela: %lu\n", tot_rela);
}
return 0;
@@ -415,6 +533,11 @@ struct elf *elf_read(const char *name, int flags)
}
memset(elf, 0, sizeof(*elf));
+ hash_init(elf->symbol_hash);
+ hash_init(elf->symbol_name_hash);
+ hash_init(elf->section_hash);
+ hash_init(elf->section_name_hash);
+ hash_init(elf->rela_hash);
INIT_LIST_HEAD(&elf->sections);
elf->fd = open(name, flags);
@@ -475,10 +598,6 @@ struct section *elf_create_section(struct elf *elf, const char *name,
INIT_LIST_HEAD(&sec->symbol_list);
INIT_LIST_HEAD(&sec->rela_list);
- hash_init(sec->rela_hash);
- hash_init(sec->symbol_hash);
-
- list_add_tail(&sec->list, &elf->sections);
s = elf_newscn(elf->elf);
if (!s) {
@@ -556,6 +675,10 @@ struct section *elf_create_section(struct elf *elf, const char *name,
shstrtab->len += strlen(name) + 1;
shstrtab->changed = true;
+ list_add_tail(&sec->list, &elf->sections);
+ hash_add(elf->section_hash, &sec->hash, sec->idx);
+ hash_add(elf->section_name_hash, &sec->name_hash, str_hash(sec->name));
+
return sec;
}
diff --git a/tools/objtool/elf.h b/tools/objtool/elf.h
index 44150204db4d..ebbb10c61e24 100644
--- a/tools/objtool/elf.h
+++ b/tools/objtool/elf.h
@@ -10,6 +10,8 @@
#include <gelf.h>
#include <linux/list.h>
#include <linux/hashtable.h>
+#include <linux/rbtree.h>
+#include <linux/jhash.h>
#ifdef LIBELF_USE_DEPRECATED
# define elf_getshdrnum elf_getshnum
@@ -25,11 +27,12 @@
struct section {
struct list_head list;
+ struct hlist_node hash;
+ struct hlist_node name_hash;
GElf_Shdr sh;
+ struct rb_root symbol_tree;
struct list_head symbol_list;
- DECLARE_HASHTABLE(symbol_hash, 8);
struct list_head rela_list;
- DECLARE_HASHTABLE(rela_hash, 16);
struct section *base, *rela;
struct symbol *sym;
Elf_Data *data;
@@ -41,7 +44,9 @@ struct section {
struct symbol {
struct list_head list;
+ struct rb_node node;
struct hlist_node hash;
+ struct hlist_node name_hash;
GElf_Sym sym;
struct section *sec;
char *name;
@@ -71,19 +76,51 @@ struct elf {
int fd;
char *name;
struct list_head sections;
- DECLARE_HASHTABLE(rela_hash, 16);
+ DECLARE_HASHTABLE(symbol_hash, 20);
+ DECLARE_HASHTABLE(symbol_name_hash, 20);
+ DECLARE_HASHTABLE(section_hash, 16);
+ DECLARE_HASHTABLE(section_name_hash, 16);
+ DECLARE_HASHTABLE(rela_hash, 20);
};
+#define OFFSET_STRIDE_BITS 4
+#define OFFSET_STRIDE (1UL << OFFSET_STRIDE_BITS)
+#define OFFSET_STRIDE_MASK (~(OFFSET_STRIDE - 1))
+
+#define for_offset_range(_offset, _start, _end) \
+ for (_offset = ((_start) & OFFSET_STRIDE_MASK); \
+ _offset <= ((_end) & OFFSET_STRIDE_MASK); \
+ _offset += OFFSET_STRIDE)
+
+static inline u32 sec_offset_hash(struct section *sec, unsigned long offset)
+{
+ u32 ol, oh, idx = sec->idx;
+
+ offset &= OFFSET_STRIDE_MASK;
+
+ ol = offset;
+ oh = offset >> 32;
+
+ __jhash_mix(ol, oh, idx);
+
+ return ol;
+}
+
+static inline u32 rela_hash(struct rela *rela)
+{
+ return sec_offset_hash(rela->sec, rela->offset);
+}
struct elf *elf_read(const char *name, int flags);
struct section *find_section_by_name(struct elf *elf, const char *name);
+struct symbol *find_func_by_offset(struct section *sec, unsigned long offset);
struct symbol *find_symbol_by_offset(struct section *sec, unsigned long offset);
struct symbol *find_symbol_by_name(struct elf *elf, const char *name);
struct symbol *find_symbol_containing(struct section *sec, unsigned long offset);
-struct rela *find_rela_by_dest(struct section *sec, unsigned long offset);
-struct rela *find_rela_by_dest_range(struct section *sec, unsigned long offset,
- unsigned int len);
-struct symbol *find_containing_func(struct section *sec, unsigned long offset);
+struct rela *find_rela_by_dest(struct elf *elf, struct section *sec, unsigned long offset);
+struct rela *find_rela_by_dest_range(struct elf *elf, struct section *sec,
+ unsigned long offset, unsigned int len);
+struct symbol *find_func_containing(struct section *sec, unsigned long offset);
struct section *elf_create_section(struct elf *elf, const char *name, size_t
entsize, int nr);
struct section *elf_create_rela_section(struct elf *elf, struct section *base);
diff --git a/tools/objtool/orc_gen.c b/tools/objtool/orc_gen.c
index 27a4112848c2..41e4a2754da4 100644
--- a/tools/objtool/orc_gen.c
+++ b/tools/objtool/orc_gen.c
@@ -81,7 +81,7 @@ int create_orc(struct objtool_file *file)
return 0;
}
-static int create_orc_entry(struct section *u_sec, struct section *ip_relasec,
+static int create_orc_entry(struct elf *elf, struct section *u_sec, struct section *ip_relasec,
unsigned int idx, struct section *insn_sec,
unsigned long insn_off, struct orc_entry *o)
{
@@ -109,9 +109,10 @@ static int create_orc_entry(struct section *u_sec, struct section *ip_relasec,
rela->addend = insn_off;
rela->type = R_X86_64_PC32;
rela->offset = idx * sizeof(int);
+ rela->sec = ip_relasec;
list_add_tail(&rela->list, &ip_relasec->rela_list);
- hash_add(ip_relasec->rela_hash, &rela->hash, rela->offset);
+ hash_add(elf->rela_hash, &rela->hash, rela_hash(rela));
return 0;
}
@@ -182,7 +183,7 @@ int create_orc_sections(struct objtool_file *file)
if (!prev_insn || memcmp(&insn->orc, &prev_insn->orc,
sizeof(struct orc_entry))) {
- if (create_orc_entry(u_sec, ip_relasec, idx,
+ if (create_orc_entry(file->elf, u_sec, ip_relasec, idx,
insn->sec, insn->offset,
&insn->orc))
return -1;
@@ -194,7 +195,7 @@ int create_orc_sections(struct objtool_file *file)
/* section terminator */
if (prev_insn) {
- if (create_orc_entry(u_sec, ip_relasec, idx,
+ if (create_orc_entry(file->elf, u_sec, ip_relasec, idx,
prev_insn->sec,
prev_insn->offset + prev_insn->len,
&empty))
diff --git a/tools/objtool/special.c b/tools/objtool/special.c
index fdbaa611146d..e74e0189de22 100644
--- a/tools/objtool/special.c
+++ b/tools/objtool/special.c
@@ -118,7 +118,7 @@ static int get_alt_entry(struct elf *elf, struct special_entry *entry,
}
}
- orig_rela = find_rela_by_dest(sec, offset + entry->orig);
+ orig_rela = find_rela_by_dest(elf, sec, offset + entry->orig);
if (!orig_rela) {
WARN_FUNC("can't find orig rela", sec, offset + entry->orig);
return -1;
@@ -133,7 +133,7 @@ static int get_alt_entry(struct elf *elf, struct special_entry *entry,
alt->orig_off = orig_rela->addend;
if (!entry->group || alt->new_len) {
- new_rela = find_rela_by_dest(sec, offset + entry->new);
+ new_rela = find_rela_by_dest(elf, sec, offset + entry->new);
if (!new_rela) {
WARN_FUNC("can't find new rela",
sec, offset + entry->new);
diff --git a/tools/objtool/warn.h b/tools/objtool/warn.h
index cbb0a02b7480..7799f60de80a 100644
--- a/tools/objtool/warn.h
+++ b/tools/objtool/warn.h
@@ -21,7 +21,7 @@ static inline char *offstr(struct section *sec, unsigned long offset)
char *name, *str;
unsigned long name_off;
- func = find_containing_func(sec, offset);
+ func = find_func_containing(sec, offset);
if (func) {
name = func->name;
name_off = offset - func->offset;
diff --git a/tools/perf/Documentation/Makefile b/tools/perf/Documentation/Makefile
index adc5a7e44b98..31824d5269cc 100644
--- a/tools/perf/Documentation/Makefile
+++ b/tools/perf/Documentation/Makefile
@@ -295,7 +295,10 @@ $(OUTPUT)%.1 $(OUTPUT)%.5 $(OUTPUT)%.7 : $(OUTPUT)%.xml
$(OUTPUT)%.xml : %.txt
$(QUIET_ASCIIDOC)$(RM) $@+ $@ && \
$(ASCIIDOC) -b docbook -d manpage \
- $(ASCIIDOC_EXTRA) -aperf_version=$(PERF_VERSION) -o $@+ $< && \
+ $(ASCIIDOC_EXTRA) -aperf_version=$(PERF_VERSION) \
+ -aperf_date=$(shell git log -1 --pretty="format:%cd" \
+ --date=short $<) \
+ -o $@+ $< && \
mv $@+ $@
XSLT = docbook.xsl
diff --git a/tools/perf/Documentation/intel-pt.txt b/tools/perf/Documentation/intel-pt.txt
index 2cf2d9e9d0da..fd9241a1b987 100644
--- a/tools/perf/Documentation/intel-pt.txt
+++ b/tools/perf/Documentation/intel-pt.txt
@@ -1,991 +1 @@
-Intel Processor Trace
-=====================
-
-Overview
-========
-
-Intel Processor Trace (Intel PT) is an extension of Intel Architecture that
-collects information about software execution such as control flow, execution
-modes and timings and formats it into highly compressed binary packets.
-Technical details are documented in the Intel 64 and IA-32 Architectures
-Software Developer Manuals, Chapter 36 Intel Processor Trace.
-
-Intel PT is first supported in Intel Core M and 5th generation Intel Core
-processors that are based on the Intel micro-architecture code name Broadwell.
-
-Trace data is collected by 'perf record' and stored within the perf.data file.
-See below for options to 'perf record'.
-
-Trace data must be 'decoded' which involves walking the object code and matching
-the trace data packets. For example a TNT packet only tells whether a
-conditional branch was taken or not taken, so to make use of that packet the
-decoder must know precisely which instruction was being executed.
-
-Decoding is done on-the-fly. The decoder outputs samples in the same format as
-samples output by perf hardware events, for example as though the "instructions"
-or "branches" events had been recorded. Presently 3 tools support this:
-'perf script', 'perf report' and 'perf inject'. See below for more information
-on using those tools.
-
-The main distinguishing feature of Intel PT is that the decoder can determine
-the exact flow of software execution. Intel PT can be used to understand why
-and how did software get to a certain point, or behave a certain way. The
-software does not have to be recompiled, so Intel PT works with debug or release
-builds, however the executed images are needed - which makes use in JIT-compiled
-environments, or with self-modified code, a challenge. Also symbols need to be
-provided to make sense of addresses.
-
-A limitation of Intel PT is that it produces huge amounts of trace data
-(hundreds of megabytes per second per core) which takes a long time to decode,
-for example two or three orders of magnitude longer than it took to collect.
-Another limitation is the performance impact of tracing, something that will
-vary depending on the use-case and architecture.
-
-
-Quickstart
-==========
-
-It is important to start small. That is because it is easy to capture vastly
-more data than can possibly be processed.
-
-The simplest thing to do with Intel PT is userspace profiling of small programs.
-Data is captured with 'perf record' e.g. to trace 'ls' userspace-only:
-
- perf record -e intel_pt//u ls
-
-And profiled with 'perf report' e.g.
-
- perf report
-
-To also trace kernel space presents a problem, namely kernel self-modifying
-code. A fairly good kernel image is available in /proc/kcore but to get an
-accurate image a copy of /proc/kcore needs to be made under the same conditions
-as the data capture. A script perf-with-kcore can do that, but beware that the
-script makes use of 'sudo' to copy /proc/kcore. If you have perf installed
-locally from the source tree you can do:
-
- ~/libexec/perf-core/perf-with-kcore record pt_ls -e intel_pt// -- ls
-
-which will create a directory named 'pt_ls' and put the perf.data file and
-copies of /proc/kcore, /proc/kallsyms and /proc/modules into it. Then to use
-'perf report' becomes:
-
- ~/libexec/perf-core/perf-with-kcore report pt_ls
-
-Because samples are synthesized after-the-fact, the sampling period can be
-selected for reporting. e.g. sample every microsecond
-
- ~/libexec/perf-core/perf-with-kcore report pt_ls --itrace=i1usge
-
-See the sections below for more information about the --itrace option.
-
-Beware the smaller the period, the more samples that are produced, and the
-longer it takes to process them.
-
-Also note that the coarseness of Intel PT timing information will start to
-distort the statistical value of the sampling as the sampling period becomes
-smaller.
-
-To represent software control flow, "branches" samples are produced. By default
-a branch sample is synthesized for every single branch. To get an idea what
-data is available you can use the 'perf script' tool with all itrace sampling
-options, which will list all the samples.
-
- perf record -e intel_pt//u ls
- perf script --itrace=ibxwpe
-
-An interesting field that is not printed by default is 'flags' which can be
-displayed as follows:
-
- perf script --itrace=ibxwpe -F+flags
-
-The flags are "bcrosyiABEx" which stand for branch, call, return, conditional,
-system, asynchronous, interrupt, transaction abort, trace begin, trace end, and
-in transaction, respectively.
-
-Another interesting field that is not printed by default is 'ipc' which can be
-displayed as follows:
-
- perf script --itrace=be -F+ipc
-
-There are two ways that instructions-per-cycle (IPC) can be calculated depending
-on the recording.
-
-If the 'cyc' config term (see config terms section below) was used, then IPC is
-calculated using the cycle count from CYC packets, otherwise MTC packets are
-used - refer to the 'mtc' config term. When MTC is used, however, the values
-are less accurate because the timing is less accurate.
-
-Because Intel PT does not update the cycle count on every branch or instruction,
-the values will often be zero. When there are values, they will be the number
-of instructions and number of cycles since the last update, and thus represent
-the average IPC since the last IPC for that event type. Note IPC for "branches"
-events is calculated separately from IPC for "instructions" events.
-
-Also note that the IPC instruction count may or may not include the current
-instruction. If the cycle count is associated with an asynchronous branch
-(e.g. page fault or interrupt), then the instruction count does not include the
-current instruction, otherwise it does. That is consistent with whether or not
-that instruction has retired when the cycle count is updated.
-
-Another note, in the case of "branches" events, non-taken branches are not
-presently sampled, so IPC values for them do not appear e.g. a CYC packet with a
-TNT packet that starts with a non-taken branch. To see every possible IPC
-value, "instructions" events can be used e.g. --itrace=i0ns
-
-While it is possible to create scripts to analyze the data, an alternative
-approach is available to export the data to a sqlite or postgresql database.
-Refer to script export-to-sqlite.py or export-to-postgresql.py for more details,
-and to script exported-sql-viewer.py for an example of using the database.
-
-There is also script intel-pt-events.py which provides an example of how to
-unpack the raw data for power events and PTWRITE.
-
-As mentioned above, it is easy to capture too much data. One way to limit the
-data captured is to use 'snapshot' mode which is explained further below.
-Refer to 'new snapshot option' and 'Intel PT modes of operation' further below.
-
-Another problem that will be experienced is decoder errors. They can be caused
-by inability to access the executed image, self-modified or JIT-ed code, or the
-inability to match side-band information (such as context switches and mmaps)
-which results in the decoder not knowing what code was executed.
-
-There is also the problem of perf not being able to copy the data fast enough,
-resulting in data lost because the buffer was full. See 'Buffer handling' below
-for more details.
-
-
-perf record
-===========
-
-new event
----------
-
-The Intel PT kernel driver creates a new PMU for Intel PT. PMU events are
-selected by providing the PMU name followed by the "config" separated by slashes.
-An enhancement has been made to allow default "config" e.g. the option
-
- -e intel_pt//
-
-will use a default config value. Currently that is the same as
-
- -e intel_pt/tsc,noretcomp=0/
-
-which is the same as
-
- -e intel_pt/tsc=1,noretcomp=0/
-
-Note there are now new config terms - see section 'config terms' further below.
-
-The config terms are listed in /sys/devices/intel_pt/format. They are bit
-fields within the config member of the struct perf_event_attr which is
-passed to the kernel by the perf_event_open system call. They correspond to bit
-fields in the IA32_RTIT_CTL MSR. Here is a list of them and their definitions:
-
- $ grep -H . /sys/bus/event_source/devices/intel_pt/format/*
- /sys/bus/event_source/devices/intel_pt/format/cyc:config:1
- /sys/bus/event_source/devices/intel_pt/format/cyc_thresh:config:19-22
- /sys/bus/event_source/devices/intel_pt/format/mtc:config:9
- /sys/bus/event_source/devices/intel_pt/format/mtc_period:config:14-17
- /sys/bus/event_source/devices/intel_pt/format/noretcomp:config:11
- /sys/bus/event_source/devices/intel_pt/format/psb_period:config:24-27
- /sys/bus/event_source/devices/intel_pt/format/tsc:config:10
-
-Note that the default config must be overridden for each term i.e.
-
- -e intel_pt/noretcomp=0/
-
-is the same as:
-
- -e intel_pt/tsc=1,noretcomp=0/
-
-So, to disable TSC packets use:
-
- -e intel_pt/tsc=0/
-
-It is also possible to specify the config value explicitly:
-
- -e intel_pt/config=0x400/
-
-Note that, as with all events, the event is suffixed with event modifiers:
-
- u userspace
- k kernel
- h hypervisor
- G guest
- H host
- p precise ip
-
-'h', 'G' and 'H' are for virtualization which is not supported by Intel PT.
-'p' is also not relevant to Intel PT. So only options 'u' and 'k' are
-meaningful for Intel PT.
-
-perf_event_attr is displayed if the -vv option is used e.g.
-
- ------------------------------------------------------------
- perf_event_attr:
- type 6
- size 112
- config 0x400
- { sample_period, sample_freq } 1
- sample_type IP|TID|TIME|CPU|IDENTIFIER
- read_format ID
- disabled 1
- inherit 1
- exclude_kernel 1
- exclude_hv 1
- enable_on_exec 1
- sample_id_all 1
- ------------------------------------------------------------
- sys_perf_event_open: pid 31104 cpu 0 group_fd -1 flags 0x8
- sys_perf_event_open: pid 31104 cpu 1 group_fd -1 flags 0x8
- sys_perf_event_open: pid 31104 cpu 2 group_fd -1 flags 0x8
- sys_perf_event_open: pid 31104 cpu 3 group_fd -1 flags 0x8
- ------------------------------------------------------------
-
-
-config terms
-------------
-
-The June 2015 version of Intel 64 and IA-32 Architectures Software Developer
-Manuals, Chapter 36 Intel Processor Trace, defined new Intel PT features.
-Some of the features are reflect in new config terms. All the config terms are
-described below.
-
-tsc Always supported. Produces TSC timestamp packets to provide
- timing information. In some cases it is possible to decode
- without timing information, for example a per-thread context
- that does not overlap executable memory maps.
-
- The default config selects tsc (i.e. tsc=1).
-
-noretcomp Always supported. Disables "return compression" so a TIP packet
- is produced when a function returns. Causes more packets to be
- produced but might make decoding more reliable.
-
- The default config does not select noretcomp (i.e. noretcomp=0).
-
-psb_period Allows the frequency of PSB packets to be specified.
-
- The PSB packet is a synchronization packet that provides a
- starting point for decoding or recovery from errors.
-
- Support for psb_period is indicated by:
-
- /sys/bus/event_source/devices/intel_pt/caps/psb_cyc
-
- which contains "1" if the feature is supported and "0"
- otherwise.
-
- Valid values are given by:
-
- /sys/bus/event_source/devices/intel_pt/caps/psb_periods
-
- which contains a hexadecimal value, the bits of which represent
- valid values e.g. bit 2 set means value 2 is valid.
-
- The psb_period value is converted to the approximate number of
- trace bytes between PSB packets as:
-
- 2 ^ (value + 11)
-
- e.g. value 3 means 16KiB bytes between PSBs
-
- If an invalid value is entered, the error message
- will give a list of valid values e.g.
-
- $ perf record -e intel_pt/psb_period=15/u uname
- Invalid psb_period for intel_pt. Valid values are: 0-5
-
- If MTC packets are selected, the default config selects a value
- of 3 (i.e. psb_period=3) or the nearest lower value that is
- supported (0 is always supported). Otherwise the default is 0.
-
- If decoding is expected to be reliable and the buffer is large
- then a large PSB period can be used.
-
- Because a TSC packet is produced with PSB, the PSB period can
- also affect the granularity to timing information in the absence
- of MTC or CYC.
-
-mtc Produces MTC timing packets.
-
- MTC packets provide finer grain timestamp information than TSC
- packets. MTC packets record time using the hardware crystal
- clock (CTC) which is related to TSC packets using a TMA packet.
-
- Support for this feature is indicated by:
-
- /sys/bus/event_source/devices/intel_pt/caps/mtc
-
- which contains "1" if the feature is supported and
- "0" otherwise.
-
- The frequency of MTC packets can also be specified - see
- mtc_period below.
-
-mtc_period Specifies how frequently MTC packets are produced - see mtc
- above for how to determine if MTC packets are supported.
-
- Valid values are given by:
-
- /sys/bus/event_source/devices/intel_pt/caps/mtc_periods
-
- which contains a hexadecimal value, the bits of which represent
- valid values e.g. bit 2 set means value 2 is valid.
-
- The mtc_period value is converted to the MTC frequency as:
-
- CTC-frequency / (2 ^ value)
-
- e.g. value 3 means one eighth of CTC-frequency
-
- Where CTC is the hardware crystal clock, the frequency of which
- can be related to TSC via values provided in cpuid leaf 0x15.
-
- If an invalid value is entered, the error message
- will give a list of valid values e.g.
-
- $ perf record -e intel_pt/mtc_period=15/u uname
- Invalid mtc_period for intel_pt. Valid values are: 0,3,6,9
-
- The default value is 3 or the nearest lower value
- that is supported (0 is always supported).
-
-cyc Produces CYC timing packets.
-
- CYC packets provide even finer grain timestamp information than
- MTC and TSC packets. A CYC packet contains the number of CPU
- cycles since the last CYC packet. Unlike MTC and TSC packets,
- CYC packets are only sent when another packet is also sent.
-
- Support for this feature is indicated by:
-
- /sys/bus/event_source/devices/intel_pt/caps/psb_cyc
-
- which contains "1" if the feature is supported and
- "0" otherwise.
-
- The number of CYC packets produced can be reduced by specifying
- a threshold - see cyc_thresh below.
-
-cyc_thresh Specifies how frequently CYC packets are produced - see cyc
- above for how to determine if CYC packets are supported.
-
- Valid cyc_thresh values are given by:
-
- /sys/bus/event_source/devices/intel_pt/caps/cycle_thresholds
-
- which contains a hexadecimal value, the bits of which represent
- valid values e.g. bit 2 set means value 2 is valid.
-
- The cyc_thresh value represents the minimum number of CPU cycles
- that must have passed before a CYC packet can be sent. The
- number of CPU cycles is:
-
- 2 ^ (value - 1)
-
- e.g. value 4 means 8 CPU cycles must pass before a CYC packet
- can be sent. Note a CYC packet is still only sent when another
- packet is sent, not at, e.g. every 8 CPU cycles.
-
- If an invalid value is entered, the error message
- will give a list of valid values e.g.
-
- $ perf record -e intel_pt/cyc,cyc_thresh=15/u uname
- Invalid cyc_thresh for intel_pt. Valid values are: 0-12
-
- CYC packets are not requested by default.
-
-pt Specifies pass-through which enables the 'branch' config term.
-
- The default config selects 'pt' if it is available, so a user will
- never need to specify this term.
-
-branch Enable branch tracing. Branch tracing is enabled by default so to
- disable branch tracing use 'branch=0'.
-
- The default config selects 'branch' if it is available.
-
-ptw Enable PTWRITE packets which are produced when a ptwrite instruction
- is executed.
-
- Support for this feature is indicated by:
-
- /sys/bus/event_source/devices/intel_pt/caps/ptwrite
-
- which contains "1" if the feature is supported and
- "0" otherwise.
-
-fup_on_ptw Enable a FUP packet to follow the PTWRITE packet. The FUP packet
- provides the address of the ptwrite instruction. In the absence of
- fup_on_ptw, the decoder will use the address of the previous branch
- if branch tracing is enabled, otherwise the address will be zero.
- Note that fup_on_ptw will work even when branch tracing is disabled.
-
-pwr_evt Enable power events. The power events provide information about
- changes to the CPU C-state.
-
- Support for this feature is indicated by:
-
- /sys/bus/event_source/devices/intel_pt/caps/power_event_trace
-
- which contains "1" if the feature is supported and
- "0" otherwise.
-
-
-AUX area sampling option
-------------------------
-
-To select Intel PT "sampling" the AUX area sampling option can be used:
-
- --aux-sample
-
-Optionally it can be followed by the sample size in bytes e.g.
-
- --aux-sample=8192
-
-In addition, the Intel PT event to sample must be defined e.g.
-
- -e intel_pt//u
-
-Samples on other events will be created containing Intel PT data e.g. the
-following will create Intel PT samples on the branch-misses event, note the
-events must be grouped using {}:
-
- perf record --aux-sample -e '{intel_pt//u,branch-misses:u}'
-
-An alternative to '--aux-sample' is to add the config term 'aux-sample-size' to
-events. In this case, the grouping is implied e.g.
-
- perf record -e intel_pt//u -e branch-misses/aux-sample-size=8192/u
-
-is the same as:
-
- perf record -e '{intel_pt//u,branch-misses/aux-sample-size=8192/u}'
-
-but allows for also using an address filter e.g.:
-
- perf record -e intel_pt//u --filter 'filter * @/bin/ls' -e branch-misses/aux-sample-size=8192/u -- ls
-
-It is important to select a sample size that is big enough to contain at least
-one PSB packet. If not a warning will be displayed:
-
- Intel PT sample size (%zu) may be too small for PSB period (%zu)
-
-The calculation used for that is: if sample_size <= psb_period + 256 display the
-warning. When sampling is used, psb_period defaults to 0 (2KiB).
-
-The default sample size is 4KiB.
-
-The sample size is passed in aux_sample_size in struct perf_event_attr. The
-sample size is limited by the maximum event size which is 64KiB. It is
-difficult to know how big the event might be without the trace sample attached,
-but the tool validates that the sample size is not greater than 60KiB.
-
-
-new snapshot option
--------------------
-
-The difference between full trace and snapshot from the kernel's perspective is
-that in full trace we don't overwrite trace data that the user hasn't collected
-yet (and indicated that by advancing aux_tail), whereas in snapshot mode we let
-the trace run and overwrite older data in the buffer so that whenever something
-interesting happens, we can stop it and grab a snapshot of what was going on
-around that interesting moment.
-
-To select snapshot mode a new option has been added:
-
- -S
-
-Optionally it can be followed by the snapshot size e.g.
-
- -S0x100000
-
-The default snapshot size is the auxtrace mmap size. If neither auxtrace mmap size
-nor snapshot size is specified, then the default is 4MiB for privileged users
-(or if /proc/sys/kernel/perf_event_paranoid < 0), 128KiB for unprivileged users.
-If an unprivileged user does not specify mmap pages, the mmap pages will be
-reduced as described in the 'new auxtrace mmap size option' section below.
-
-The snapshot size is displayed if the option -vv is used e.g.
-
- Intel PT snapshot size: %zu
-
-
-new auxtrace mmap size option
----------------------------
-
-Intel PT buffer size is specified by an addition to the -m option e.g.
-
- -m,16
-
-selects a buffer size of 16 pages i.e. 64KiB.
-
-Note that the existing functionality of -m is unchanged. The auxtrace mmap size
-is specified by the optional addition of a comma and the value.
-
-The default auxtrace mmap size for Intel PT is 4MiB/page_size for privileged users
-(or if /proc/sys/kernel/perf_event_paranoid < 0), 128KiB for unprivileged users.
-If an unprivileged user does not specify mmap pages, the mmap pages will be
-reduced from the default 512KiB/page_size to 256KiB/page_size, otherwise the
-user is likely to get an error as they exceed their mlock limit (Max locked
-memory as shown in /proc/self/limits). Note that perf does not count the first
-512KiB (actually /proc/sys/kernel/perf_event_mlock_kb minus 1 page) per cpu
-against the mlock limit so an unprivileged user is allowed 512KiB per cpu plus
-their mlock limit (which defaults to 64KiB but is not multiplied by the number
-of cpus).
-
-In full-trace mode, powers of two are allowed for buffer size, with a minimum
-size of 2 pages. In snapshot mode or sampling mode, it is the same but the
-minimum size is 1 page.
-
-The mmap size and auxtrace mmap size are displayed if the -vv option is used e.g.
-
- mmap length 528384
- auxtrace mmap length 4198400
-
-
-Intel PT modes of operation
----------------------------
-
-Intel PT can be used in 2 modes:
- full-trace mode
- sample mode
- snapshot mode
-
-Full-trace mode traces continuously e.g.
-
- perf record -e intel_pt//u uname
-
-Sample mode attaches a Intel PT sample to other events e.g.
-
- perf record --aux-sample -e intel_pt//u -e branch-misses:u
-
-Snapshot mode captures the available data when a signal is sent e.g.
-
- perf record -v -e intel_pt//u -S ./loopy 1000000000 &
- [1] 11435
- kill -USR2 11435
- Recording AUX area tracing snapshot
-
-Note that the signal sent is SIGUSR2.
-Note that "Recording AUX area tracing snapshot" is displayed because the -v
-option is used.
-
-The 2 modes cannot be used together.
-
-
-Buffer handling
----------------
-
-There may be buffer limitations (i.e. single ToPa entry) which means that actual
-buffer sizes are limited to powers of 2 up to 4MiB (MAX_ORDER). In order to
-provide other sizes, and in particular an arbitrarily large size, multiple
-buffers are logically concatenated. However an interrupt must be used to switch
-between buffers. That has two potential problems:
- a) the interrupt may not be handled in time so that the current buffer
- becomes full and some trace data is lost.
- b) the interrupts may slow the system and affect the performance
- results.
-
-If trace data is lost, the driver sets 'truncated' in the PERF_RECORD_AUX event
-which the tools report as an error.
-
-In full-trace mode, the driver waits for data to be copied out before allowing
-the (logical) buffer to wrap-around. If data is not copied out quickly enough,
-again 'truncated' is set in the PERF_RECORD_AUX event. If the driver has to
-wait, the intel_pt event gets disabled. Because it is difficult to know when
-that happens, perf tools always re-enable the intel_pt event after copying out
-data.
-
-
-Intel PT and build ids
-----------------------
-
-By default "perf record" post-processes the event stream to find all build ids
-for executables for all addresses sampled. Deliberately, Intel PT is not
-decoded for that purpose (it would take too long). Instead the build ids for
-all executables encountered (due to mmap, comm or task events) are included
-in the perf.data file.
-
-To see buildids included in the perf.data file use the command:
-
- perf buildid-list
-
-If the perf.data file contains Intel PT data, that is the same as:
-
- perf buildid-list --with-hits
-
-
-Snapshot mode and event disabling
----------------------------------
-
-In order to make a snapshot, the intel_pt event is disabled using an IOCTL,
-namely PERF_EVENT_IOC_DISABLE. However doing that can also disable the
-collection of side-band information. In order to prevent that, a dummy
-software event has been introduced that permits tracking events (like mmaps) to
-continue to be recorded while intel_pt is disabled. That is important to ensure
-there is complete side-band information to allow the decoding of subsequent
-snapshots.
-
-A test has been created for that. To find the test:
-
- perf test list
- ...
- 23: Test using a dummy software event to keep tracking
-
-To run the test:
-
- perf test 23
- 23: Test using a dummy software event to keep tracking : Ok
-
-
-perf record modes (nothing new here)
-------------------------------------
-
-perf record essentially operates in one of three modes:
- per thread
- per cpu
- workload only
-
-"per thread" mode is selected by -t or by --per-thread (with -p or -u or just a
-workload).
-"per cpu" is selected by -C or -a.
-"workload only" mode is selected by not using the other options but providing a
-command to run (i.e. the workload).
-
-In per-thread mode an exact list of threads is traced. There is no inheritance.
-Each thread has its own event buffer.
-
-In per-cpu mode all processes (or processes from the selected cgroup i.e. -G
-option, or processes selected with -p or -u) are traced. Each cpu has its own
-buffer. Inheritance is allowed.
-
-In workload-only mode, the workload is traced but with per-cpu buffers.
-Inheritance is allowed. Note that you can now trace a workload in per-thread
-mode by using the --per-thread option.
-
-
-Privileged vs non-privileged users
-----------------------------------
-
-Unless /proc/sys/kernel/perf_event_paranoid is set to -1, unprivileged users
-have memory limits imposed upon them. That affects what buffer sizes they can
-have as outlined above.
-
-The v4.2 kernel introduced support for a context switch metadata event,
-PERF_RECORD_SWITCH, which allows unprivileged users to see when their processes
-are scheduled out and in, just not by whom, which is left for the
-PERF_RECORD_SWITCH_CPU_WIDE, that is only accessible in system wide context,
-which in turn requires CAP_SYS_ADMIN.
-
-Please see the 45ac1403f564 ("perf: Add PERF_RECORD_SWITCH to indicate context
-switches") commit, that introduces these metadata events for further info.
-
-When working with kernels < v4.2, the following considerations must be taken,
-as the sched:sched_switch tracepoints will be used to receive such information:
-
-Unless /proc/sys/kernel/perf_event_paranoid is set to -1, unprivileged users are
-not permitted to use tracepoints which means there is insufficient side-band
-information to decode Intel PT in per-cpu mode, and potentially workload-only
-mode too if the workload creates new processes.
-
-Note also, that to use tracepoints, read-access to debugfs is required. So if
-debugfs is not mounted or the user does not have read-access, it will again not
-be possible to decode Intel PT in per-cpu mode.
-
-
-sched_switch tracepoint
------------------------
-
-The sched_switch tracepoint is used to provide side-band data for Intel PT
-decoding in kernels where the PERF_RECORD_SWITCH metadata event isn't
-available.
-
-The sched_switch events are automatically added. e.g. the second event shown
-below:
-
- $ perf record -vv -e intel_pt//u uname
- ------------------------------------------------------------
- perf_event_attr:
- type 6
- size 112
- config 0x400
- { sample_period, sample_freq } 1
- sample_type IP|TID|TIME|CPU|IDENTIFIER
- read_format ID
- disabled 1
- inherit 1
- exclude_kernel 1
- exclude_hv 1
- enable_on_exec 1
- sample_id_all 1
- ------------------------------------------------------------
- sys_perf_event_open: pid 31104 cpu 0 group_fd -1 flags 0x8
- sys_perf_event_open: pid 31104 cpu 1 group_fd -1 flags 0x8
- sys_perf_event_open: pid 31104 cpu 2 group_fd -1 flags 0x8
- sys_perf_event_open: pid 31104 cpu 3 group_fd -1 flags 0x8
- ------------------------------------------------------------
- perf_event_attr:
- type 2
- size 112
- config 0x108
- { sample_period, sample_freq } 1
- sample_type IP|TID|TIME|CPU|PERIOD|RAW|IDENTIFIER
- read_format ID
- inherit 1
- sample_id_all 1
- exclude_guest 1
- ------------------------------------------------------------
- sys_perf_event_open: pid -1 cpu 0 group_fd -1 flags 0x8
- sys_perf_event_open: pid -1 cpu 1 group_fd -1 flags 0x8
- sys_perf_event_open: pid -1 cpu 2 group_fd -1 flags 0x8
- sys_perf_event_open: pid -1 cpu 3 group_fd -1 flags 0x8
- ------------------------------------------------------------
- perf_event_attr:
- type 1
- size 112
- config 0x9
- { sample_period, sample_freq } 1
- sample_type IP|TID|TIME|IDENTIFIER
- read_format ID
- disabled 1
- inherit 1
- exclude_kernel 1
- exclude_hv 1
- mmap 1
- comm 1
- enable_on_exec 1
- task 1
- sample_id_all 1
- mmap2 1
- comm_exec 1
- ------------------------------------------------------------
- sys_perf_event_open: pid 31104 cpu 0 group_fd -1 flags 0x8
- sys_perf_event_open: pid 31104 cpu 1 group_fd -1 flags 0x8
- sys_perf_event_open: pid 31104 cpu 2 group_fd -1 flags 0x8
- sys_perf_event_open: pid 31104 cpu 3 group_fd -1 flags 0x8
- mmap size 528384B
- AUX area mmap length 4194304
- perf event ring buffer mmapped per cpu
- Synthesizing auxtrace information
- Linux
- [ perf record: Woken up 1 times to write data ]
- [ perf record: Captured and wrote 0.042 MB perf.data ]
-
-Note, the sched_switch event is only added if the user is permitted to use it
-and only in per-cpu mode.
-
-Note also, the sched_switch event is only added if TSC packets are requested.
-That is because, in the absence of timing information, the sched_switch events
-cannot be matched against the Intel PT trace.
-
-
-perf script
-===========
-
-By default, perf script will decode trace data found in the perf.data file.
-This can be further controlled by new option --itrace.
-
-
-New --itrace option
--------------------
-
-Having no option is the same as
-
- --itrace
-
-which, in turn, is the same as
-
- --itrace=cepwx
-
-The letters are:
-
- i synthesize "instructions" events
- b synthesize "branches" events
- x synthesize "transactions" events
- w synthesize "ptwrite" events
- p synthesize "power" events
- c synthesize branches events (calls only)
- r synthesize branches events (returns only)
- e synthesize tracing error events
- d create a debug log
- g synthesize a call chain (use with i or x)
- l synthesize last branch entries (use with i or x)
- s skip initial number of events
-
-"Instructions" events look like they were recorded by "perf record -e
-instructions".
-
-"Branches" events look like they were recorded by "perf record -e branches". "c"
-and "r" can be combined to get calls and returns.
-
-"Transactions" events correspond to the start or end of transactions. The
-'flags' field can be used in perf script to determine whether the event is a
-tranasaction start, commit or abort.
-
-Note that "instructions", "branches" and "transactions" events depend on code
-flow packets which can be disabled by using the config term "branch=0". Refer
-to the config terms section above.
-
-"ptwrite" events record the payload of the ptwrite instruction and whether
-"fup_on_ptw" was used. "ptwrite" events depend on PTWRITE packets which are
-recorded only if the "ptw" config term was used. Refer to the config terms
-section above. perf script "synth" field displays "ptwrite" information like
-this: "ip: 0 payload: 0x123456789abcdef0" where "ip" is 1 if "fup_on_ptw" was
-used.
-
-"Power" events correspond to power event packets and CBR (core-to-bus ratio)
-packets. While CBR packets are always recorded when tracing is enabled, power
-event packets are recorded only if the "pwr_evt" config term was used. Refer to
-the config terms section above. The power events record information about
-C-state changes, whereas CBR is indicative of CPU frequency. perf script
-"event,synth" fields display information like this:
- cbr: cbr: 22 freq: 2189 MHz (200%)
- mwait: hints: 0x60 extensions: 0x1
- pwre: hw: 0 cstate: 2 sub-cstate: 0
- exstop: ip: 1
- pwrx: deepest cstate: 2 last cstate: 2 wake reason: 0x4
-Where:
- "cbr" includes the frequency and the percentage of maximum non-turbo
- "mwait" shows mwait hints and extensions
- "pwre" shows C-state transitions (to a C-state deeper than C0) and
- whether initiated by hardware
- "exstop" indicates execution stopped and whether the IP was recorded
- exactly,
- "pwrx" indicates return to C0
-For more details refer to the Intel 64 and IA-32 Architectures Software
-Developer Manuals.
-
-Error events show where the decoder lost the trace. Error events
-are quite important. Users must know if what they are seeing is a complete
-picture or not.
-
-The "d" option will cause the creation of a file "intel_pt.log" containing all
-decoded packets and instructions. Note that this option slows down the decoder
-and that the resulting file may be very large.
-
-In addition, the period of the "instructions" event can be specified. e.g.
-
- --itrace=i10us
-
-sets the period to 10us i.e. one instruction sample is synthesized for each 10
-microseconds of trace. Alternatives to "us" are "ms" (milliseconds),
-"ns" (nanoseconds), "t" (TSC ticks) or "i" (instructions).
-
-"ms", "us" and "ns" are converted to TSC ticks.
-
-The timing information included with Intel PT does not give the time of every
-instruction. Consequently, for the purpose of sampling, the decoder estimates
-the time since the last timing packet based on 1 tick per instruction. The time
-on the sample is *not* adjusted and reflects the last known value of TSC.
-
-For Intel PT, the default period is 100us.
-
-Setting it to a zero period means "as often as possible".
-
-In the case of Intel PT that is the same as a period of 1 and a unit of
-'instructions' (i.e. --itrace=i1i).
-
-Also the call chain size (default 16, max. 1024) for instructions or
-transactions events can be specified. e.g.
-
- --itrace=ig32
- --itrace=xg32
-
-Also the number of last branch entries (default 64, max. 1024) for instructions or
-transactions events can be specified. e.g.
-
- --itrace=il10
- --itrace=xl10
-
-Note that last branch entries are cleared for each sample, so there is no overlap
-from one sample to the next.
-
-To disable trace decoding entirely, use the option --no-itrace.
-
-It is also possible to skip events generated (instructions, branches, transactions)
-at the beginning. This is useful to ignore initialization code.
-
- --itrace=i0nss1000000
-
-skips the first million instructions.
-
-dump option
------------
-
-perf script has an option (-D) to "dump" the events i.e. display the binary
-data.
-
-When -D is used, Intel PT packets are displayed. The packet decoder does not
-pay attention to PSB packets, but just decodes the bytes - so the packets seen
-by the actual decoder may not be identical in places where the data is corrupt.
-One example of that would be when the buffer-switching interrupt has been too
-slow, and the buffer has been filled completely. In that case, the last packet
-in the buffer might be truncated and immediately followed by a PSB as the trace
-continues in the next buffer.
-
-To disable the display of Intel PT packets, combine the -D option with
---no-itrace.
-
-
-perf report
-===========
-
-By default, perf report will decode trace data found in the perf.data file.
-This can be further controlled by new option --itrace exactly the same as
-perf script, with the exception that the default is --itrace=igxe.
-
-
-perf inject
-===========
-
-perf inject also accepts the --itrace option in which case tracing data is
-removed and replaced with the synthesized events. e.g.
-
- perf inject --itrace -i perf.data -o perf.data.new
-
-Below is an example of using Intel PT with autofdo. It requires autofdo
-(https://github.com/google/autofdo) and gcc version 5. The bubble
-sort example is from the AutoFDO tutorial (https://gcc.gnu.org/wiki/AutoFDO/Tutorial)
-amended to take the number of elements as a parameter.
-
- $ gcc-5 -O3 sort.c -o sort_optimized
- $ ./sort_optimized 30000
- Bubble sorting array of 30000 elements
- 2254 ms
-
- $ cat ~/.perfconfig
- [intel-pt]
- mispred-all = on
-
- $ perf record -e intel_pt//u ./sort 3000
- Bubble sorting array of 3000 elements
- 58 ms
- [ perf record: Woken up 2 times to write data ]
- [ perf record: Captured and wrote 3.939 MB perf.data ]
- $ perf inject -i perf.data -o inj --itrace=i100usle --strip
- $ ./create_gcov --binary=./sort --profile=inj --gcov=sort.gcov -gcov_version=1
- $ gcc-5 -O3 -fauto-profile=sort.gcov sort.c -o sort_autofdo
- $ ./sort_autofdo 30000
- Bubble sorting array of 30000 elements
- 2155 ms
-
-Note there is currently no advantage to using Intel PT instead of LBR, but
-that may change in the future if greater use is made of the data.
-
-
-PEBS via Intel PT
-=================
-
-Some hardware has the feature to redirect PEBS records to the Intel PT trace.
-Recording is selected by using the aux-output config term e.g.
-
- perf record -c 10000 -e '{intel_pt/branch=0/,cycles/aux-output/ppp}' uname
-
-Note that currently, software only supports redirecting at most one PEBS event.
-
-To display PEBS events from the Intel PT trace, use the itrace 'o' option e.g.
-
- perf script --itrace=oe
+Documentation for support for Intel Processor Trace within perf tools' has moved to file perf-intel-pt.txt
diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt
index c4dd23c4b478..8ead55593984 100644
--- a/tools/perf/Documentation/perf-config.txt
+++ b/tools/perf/Documentation/perf-config.txt
@@ -239,7 +239,6 @@ buildid.*::
set buildid.dir to /dev/null. The default is $HOME/.debug
annotate.*::
- These options work only for TUI.
These are in control of addresses, jump function, source code
in lines of assembly code from a specific program.
@@ -269,6 +268,8 @@ annotate.*::
│ mov (%rdi),%rdx
│ return n;
+ This option works with tui, stdio2 browsers.
+
annotate.use_offset::
Basing on a first address of a loaded function, offset can be used.
Instead of using original addresses of assembly code,
@@ -287,6 +288,8 @@ annotate.*::
368:│ mov 0x8(%r14),%rdi
+ This option works with tui, stdio2 browsers.
+
annotate.jump_arrows::
There can be jump instruction among assembly code.
Depending on a boolean value of jump_arrows,
@@ -306,6 +309,8 @@ annotate.*::
│1330: mov %r15,%r10
│1333: cmp %r15,%r14
+ This option works with tui browser.
+
annotate.show_linenr::
When showing source code if this option is 'true',
line numbers are printed as below.
@@ -325,6 +330,8 @@ annotate.*::
│ array++;
│ }
+ This option works with tui, stdio2 browsers.
+
annotate.show_nr_jumps::
Let's see a part of assembly code.
@@ -335,6 +342,8 @@ annotate.*::
│1 1382: movb $0x1,-0x270(%rbp)
+ This option works with tui, stdio2 browsers.
+
annotate.show_total_period::
To compare two records on an instruction base, with this option
provided, display total number of samples that belong to a line
@@ -348,11 +357,30 @@ annotate.*::
99.93 │ mov %eax,%eax
+ This option works with tui, stdio2, stdio browsers.
+
+ annotate.show_nr_samples::
+ By default perf annotate shows percentage of samples. This option
+ can be used to print absolute number of samples. Ex, when set as
+ false:
+
+ Percent│
+ 74.03 │ mov %fs:0x28,%rax
+
+ When set as true:
+
+ Samples│
+ 6 │ mov %fs:0x28,%rax
+
+ This option works with tui, stdio2, stdio browsers.
+
annotate.offset_level::
Default is '1', meaning just jump targets will have offsets show right beside
the instruction. When set to '2' 'call' instructions will also have its offsets
shown, 3 or higher will show offsets for all instructions.
+ This option works with tui, stdio2 browsers.
+
hist.*::
hist.percentage::
This option control the way to calculate overhead of filtered entries -
@@ -490,6 +518,12 @@ top.*::
column by default.
The default is 'true'.
+ top.call-graph::
+ This is identical to 'call-graph.record-mode', except it is
+ applicable only for 'top' subcommand. This option ONLY setup
+ the unwind method. To enable 'perf top' to actually use it,
+ the command line option -g must be specified.
+
man.*::
man.viewer::
This option can assign a tool to view manual pages when 'help'
@@ -517,6 +551,16 @@ record.*::
But if this option is 'no-cache', it will not update the build-id cache.
'skip' skips post-processing and does not update the cache.
+ record.call-graph::
+ This is identical to 'call-graph.record-mode', except it is
+ applicable only for 'record' subcommand. This option ONLY setup
+ the unwind method. To enable 'perf record' to actually use it,
+ the command line option -g must be specified.
+
+ record.aio::
+ Use 'n' control blocks in asynchronous (Posix AIO) trace writing
+ mode ('n' default: 1, max: 4).
+
diff.*::
diff.order::
This option sets the number of columns to sort the result.
@@ -566,6 +610,11 @@ trace.*::
"libbeauty", the default, to use the same argument beautifiers used in the
strace-like sys_enter+sys_exit lines.
+ftrace.*::
+ ftrace.tracer::
+ Can be used to select the default tracer. Possible values are
+ 'function' and 'function_graph'.
+
llvm.*::
llvm.clang-path::
Path to clang. If omit, search it from $PATH.
@@ -610,6 +659,29 @@ scripts.*::
The script gets the same options passed as a full perf script,
in particular -i perfdata file, --cpu, --tid
+convert.*::
+
+ convert.queue-size::
+ Limit the size of ordered_events queue, so we could control
+ allocation size of perf data files without proper finished
+ round events.
+
+intel-pt.*::
+
+ intel-pt.cache-divisor::
+
+ intel-pt.mispred-all::
+ If set, Intel PT decoder will set the mispred flag on all
+ branches.
+
+auxtrace.*::
+
+ auxtrace.dumpdir::
+ s390 only. The directory to save the auxiliary trace buffer
+ can be changed using this option. Ex, auxtrace.dumpdir=/tmp.
+ If the directory does not exist or has the wrong file type,
+ the current directory is used.
+
SEE ALSO
--------
linkperf:perf[1]
diff --git a/tools/perf/Documentation/perf-inject.txt b/tools/perf/Documentation/perf-inject.txt
index a64d6588470e..70969ea73e01 100644
--- a/tools/perf/Documentation/perf-inject.txt
+++ b/tools/perf/Documentation/perf-inject.txt
@@ -66,4 +66,5 @@ include::itrace.txt[]
SEE ALSO
--------
-linkperf:perf-record[1], linkperf:perf-report[1], linkperf:perf-archive[1]
+linkperf:perf-record[1], linkperf:perf-report[1], linkperf:perf-archive[1],
+linkperf:perf-intel-pt[1]
diff --git a/tools/perf/Documentation/perf-intel-pt.txt b/tools/perf/Documentation/perf-intel-pt.txt
new file mode 100644
index 000000000000..456fdcbf26ac
--- /dev/null
+++ b/tools/perf/Documentation/perf-intel-pt.txt
@@ -0,0 +1,1007 @@
+perf-intel-pt(1)
+================
+
+NAME
+----
+perf-intel-pt - Support for Intel Processor Trace within perf tools
+
+SYNOPSIS
+--------
+[verse]
+'perf record' -e intel_pt//
+
+DESCRIPTION
+-----------
+
+Intel Processor Trace (Intel PT) is an extension of Intel Architecture that
+collects information about software execution such as control flow, execution
+modes and timings and formats it into highly compressed binary packets.
+Technical details are documented in the Intel 64 and IA-32 Architectures
+Software Developer Manuals, Chapter 36 Intel Processor Trace.
+
+Intel PT is first supported in Intel Core M and 5th generation Intel Core
+processors that are based on the Intel micro-architecture code name Broadwell.
+
+Trace data is collected by 'perf record' and stored within the perf.data file.
+See below for options to 'perf record'.
+
+Trace data must be 'decoded' which involves walking the object code and matching
+the trace data packets. For example a TNT packet only tells whether a
+conditional branch was taken or not taken, so to make use of that packet the
+decoder must know precisely which instruction was being executed.
+
+Decoding is done on-the-fly. The decoder outputs samples in the same format as
+samples output by perf hardware events, for example as though the "instructions"
+or "branches" events had been recorded. Presently 3 tools support this:
+'perf script', 'perf report' and 'perf inject'. See below for more information
+on using those tools.
+
+The main distinguishing feature of Intel PT is that the decoder can determine
+the exact flow of software execution. Intel PT can be used to understand why
+and how did software get to a certain point, or behave a certain way. The
+software does not have to be recompiled, so Intel PT works with debug or release
+builds, however the executed images are needed - which makes use in JIT-compiled
+environments, or with self-modified code, a challenge. Also symbols need to be
+provided to make sense of addresses.
+
+A limitation of Intel PT is that it produces huge amounts of trace data
+(hundreds of megabytes per second per core) which takes a long time to decode,
+for example two or three orders of magnitude longer than it took to collect.
+Another limitation is the performance impact of tracing, something that will
+vary depending on the use-case and architecture.
+
+
+Quickstart
+----------
+
+It is important to start small. That is because it is easy to capture vastly
+more data than can possibly be processed.
+
+The simplest thing to do with Intel PT is userspace profiling of small programs.
+Data is captured with 'perf record' e.g. to trace 'ls' userspace-only:
+
+ perf record -e intel_pt//u ls
+
+And profiled with 'perf report' e.g.
+
+ perf report
+
+To also trace kernel space presents a problem, namely kernel self-modifying
+code. A fairly good kernel image is available in /proc/kcore but to get an
+accurate image a copy of /proc/kcore needs to be made under the same conditions
+as the data capture. A script perf-with-kcore can do that, but beware that the
+script makes use of 'sudo' to copy /proc/kcore. If you have perf installed
+locally from the source tree you can do:
+
+ ~/libexec/perf-core/perf-with-kcore record pt_ls -e intel_pt// -- ls
+
+which will create a directory named 'pt_ls' and put the perf.data file and
+copies of /proc/kcore, /proc/kallsyms and /proc/modules into it. Then to use
+'perf report' becomes:
+
+ ~/libexec/perf-core/perf-with-kcore report pt_ls
+
+Because samples are synthesized after-the-fact, the sampling period can be
+selected for reporting. e.g. sample every microsecond
+
+ ~/libexec/perf-core/perf-with-kcore report pt_ls --itrace=i1usge
+
+See the sections below for more information about the --itrace option.
+
+Beware the smaller the period, the more samples that are produced, and the
+longer it takes to process them.
+
+Also note that the coarseness of Intel PT timing information will start to
+distort the statistical value of the sampling as the sampling period becomes
+smaller.
+
+To represent software control flow, "branches" samples are produced. By default
+a branch sample is synthesized for every single branch. To get an idea what
+data is available you can use the 'perf script' tool with all itrace sampling
+options, which will list all the samples.
+
+ perf record -e intel_pt//u ls
+ perf script --itrace=ibxwpe
+
+An interesting field that is not printed by default is 'flags' which can be
+displayed as follows:
+
+ perf script --itrace=ibxwpe -F+flags
+
+The flags are "bcrosyiABEx" which stand for branch, call, return, conditional,
+system, asynchronous, interrupt, transaction abort, trace begin, trace end, and
+in transaction, respectively.
+
+Another interesting field that is not printed by default is 'ipc' which can be
+displayed as follows:
+
+ perf script --itrace=be -F+ipc
+
+There are two ways that instructions-per-cycle (IPC) can be calculated depending
+on the recording.
+
+If the 'cyc' config term (see config terms section below) was used, then IPC is
+calculated using the cycle count from CYC packets, otherwise MTC packets are
+used - refer to the 'mtc' config term. When MTC is used, however, the values
+are less accurate because the timing is less accurate.
+
+Because Intel PT does not update the cycle count on every branch or instruction,
+the values will often be zero. When there are values, they will be the number
+of instructions and number of cycles since the last update, and thus represent
+the average IPC since the last IPC for that event type. Note IPC for "branches"
+events is calculated separately from IPC for "instructions" events.
+
+Also note that the IPC instruction count may or may not include the current
+instruction. If the cycle count is associated with an asynchronous branch
+(e.g. page fault or interrupt), then the instruction count does not include the
+current instruction, otherwise it does. That is consistent with whether or not
+that instruction has retired when the cycle count is updated.
+
+Another note, in the case of "branches" events, non-taken branches are not
+presently sampled, so IPC values for them do not appear e.g. a CYC packet with a
+TNT packet that starts with a non-taken branch. To see every possible IPC
+value, "instructions" events can be used e.g. --itrace=i0ns
+
+While it is possible to create scripts to analyze the data, an alternative
+approach is available to export the data to a sqlite or postgresql database.
+Refer to script export-to-sqlite.py or export-to-postgresql.py for more details,
+and to script exported-sql-viewer.py for an example of using the database.
+
+There is also script intel-pt-events.py which provides an example of how to
+unpack the raw data for power events and PTWRITE.
+
+As mentioned above, it is easy to capture too much data. One way to limit the
+data captured is to use 'snapshot' mode which is explained further below.
+Refer to 'new snapshot option' and 'Intel PT modes of operation' further below.
+
+Another problem that will be experienced is decoder errors. They can be caused
+by inability to access the executed image, self-modified or JIT-ed code, or the
+inability to match side-band information (such as context switches and mmaps)
+which results in the decoder not knowing what code was executed.
+
+There is also the problem of perf not being able to copy the data fast enough,
+resulting in data lost because the buffer was full. See 'Buffer handling' below
+for more details.
+
+
+perf record
+-----------
+
+new event
+~~~~~~~~~
+
+The Intel PT kernel driver creates a new PMU for Intel PT. PMU events are
+selected by providing the PMU name followed by the "config" separated by slashes.
+An enhancement has been made to allow default "config" e.g. the option
+
+ -e intel_pt//
+
+will use a default config value. Currently that is the same as
+
+ -e intel_pt/tsc,noretcomp=0/
+
+which is the same as
+
+ -e intel_pt/tsc=1,noretcomp=0/
+
+Note there are now new config terms - see section 'config terms' further below.
+
+The config terms are listed in /sys/devices/intel_pt/format. They are bit
+fields within the config member of the struct perf_event_attr which is
+passed to the kernel by the perf_event_open system call. They correspond to bit
+fields in the IA32_RTIT_CTL MSR. Here is a list of them and their definitions:
+
+ $ grep -H . /sys/bus/event_source/devices/intel_pt/format/*
+ /sys/bus/event_source/devices/intel_pt/format/cyc:config:1
+ /sys/bus/event_source/devices/intel_pt/format/cyc_thresh:config:19-22
+ /sys/bus/event_source/devices/intel_pt/format/mtc:config:9
+ /sys/bus/event_source/devices/intel_pt/format/mtc_period:config:14-17
+ /sys/bus/event_source/devices/intel_pt/format/noretcomp:config:11
+ /sys/bus/event_source/devices/intel_pt/format/psb_period:config:24-27
+ /sys/bus/event_source/devices/intel_pt/format/tsc:config:10
+
+Note that the default config must be overridden for each term i.e.
+
+ -e intel_pt/noretcomp=0/
+
+is the same as:
+
+ -e intel_pt/tsc=1,noretcomp=0/
+
+So, to disable TSC packets use:
+
+ -e intel_pt/tsc=0/
+
+It is also possible to specify the config value explicitly:
+
+ -e intel_pt/config=0x400/
+
+Note that, as with all events, the event is suffixed with event modifiers:
+
+ u userspace
+ k kernel
+ h hypervisor
+ G guest
+ H host
+ p precise ip
+
+'h', 'G' and 'H' are for virtualization which is not supported by Intel PT.
+'p' is also not relevant to Intel PT. So only options 'u' and 'k' are
+meaningful for Intel PT.
+
+perf_event_attr is displayed if the -vv option is used e.g.
+
+ ------------------------------------------------------------
+ perf_event_attr:
+ type 6
+ size 112
+ config 0x400
+ { sample_period, sample_freq } 1
+ sample_type IP|TID|TIME|CPU|IDENTIFIER
+ read_format ID
+ disabled 1
+ inherit 1
+ exclude_kernel 1
+ exclude_hv 1
+ enable_on_exec 1
+ sample_id_all 1
+ ------------------------------------------------------------
+ sys_perf_event_open: pid 31104 cpu 0 group_fd -1 flags 0x8
+ sys_perf_event_open: pid 31104 cpu 1 group_fd -1 flags 0x8
+ sys_perf_event_open: pid 31104 cpu 2 group_fd -1 flags 0x8
+ sys_perf_event_open: pid 31104 cpu 3 group_fd -1 flags 0x8
+ ------------------------------------------------------------
+
+
+config terms
+~~~~~~~~~~~~
+
+The June 2015 version of Intel 64 and IA-32 Architectures Software Developer
+Manuals, Chapter 36 Intel Processor Trace, defined new Intel PT features.
+Some of the features are reflect in new config terms. All the config terms are
+described below.
+
+tsc Always supported. Produces TSC timestamp packets to provide
+ timing information. In some cases it is possible to decode
+ without timing information, for example a per-thread context
+ that does not overlap executable memory maps.
+
+ The default config selects tsc (i.e. tsc=1).
+
+noretcomp Always supported. Disables "return compression" so a TIP packet
+ is produced when a function returns. Causes more packets to be
+ produced but might make decoding more reliable.
+
+ The default config does not select noretcomp (i.e. noretcomp=0).
+
+psb_period Allows the frequency of PSB packets to be specified.
+
+ The PSB packet is a synchronization packet that provides a
+ starting point for decoding or recovery from errors.
+
+ Support for psb_period is indicated by:
+
+ /sys/bus/event_source/devices/intel_pt/caps/psb_cyc
+
+ which contains "1" if the feature is supported and "0"
+ otherwise.
+
+ Valid values are given by:
+
+ /sys/bus/event_source/devices/intel_pt/caps/psb_periods
+
+ which contains a hexadecimal value, the bits of which represent
+ valid values e.g. bit 2 set means value 2 is valid.
+
+ The psb_period value is converted to the approximate number of
+ trace bytes between PSB packets as:
+
+ 2 ^ (value + 11)
+
+ e.g. value 3 means 16KiB bytes between PSBs
+
+ If an invalid value is entered, the error message
+ will give a list of valid values e.g.
+
+ $ perf record -e intel_pt/psb_period=15/u uname
+ Invalid psb_period for intel_pt. Valid values are: 0-5
+
+ If MTC packets are selected, the default config selects a value
+ of 3 (i.e. psb_period=3) or the nearest lower value that is
+ supported (0 is always supported). Otherwise the default is 0.
+
+ If decoding is expected to be reliable and the buffer is large
+ then a large PSB period can be used.
+
+ Because a TSC packet is produced with PSB, the PSB period can
+ also affect the granularity to timing information in the absence
+ of MTC or CYC.
+
+mtc Produces MTC timing packets.
+
+ MTC packets provide finer grain timestamp information than TSC
+ packets. MTC packets record time using the hardware crystal
+ clock (CTC) which is related to TSC packets using a TMA packet.
+
+ Support for this feature is indicated by:
+
+ /sys/bus/event_source/devices/intel_pt/caps/mtc
+
+ which contains "1" if the feature is supported and
+ "0" otherwise.
+
+ The frequency of MTC packets can also be specified - see
+ mtc_period below.
+
+mtc_period Specifies how frequently MTC packets are produced - see mtc
+ above for how to determine if MTC packets are supported.
+
+ Valid values are given by:
+
+ /sys/bus/event_source/devices/intel_pt/caps/mtc_periods
+
+ which contains a hexadecimal value, the bits of which represent
+ valid values e.g. bit 2 set means value 2 is valid.
+
+ The mtc_period value is converted to the MTC frequency as:
+
+ CTC-frequency / (2 ^ value)
+
+ e.g. value 3 means one eighth of CTC-frequency
+
+ Where CTC is the hardware crystal clock, the frequency of which
+ can be related to TSC via values provided in cpuid leaf 0x15.
+
+ If an invalid value is entered, the error message
+ will give a list of valid values e.g.
+
+ $ perf record -e intel_pt/mtc_period=15/u uname
+ Invalid mtc_period for intel_pt. Valid values are: 0,3,6,9
+
+ The default value is 3 or the nearest lower value
+ that is supported (0 is always supported).
+
+cyc Produces CYC timing packets.
+
+ CYC packets provide even finer grain timestamp information than
+ MTC and TSC packets. A CYC packet contains the number of CPU
+ cycles since the last CYC packet. Unlike MTC and TSC packets,
+ CYC packets are only sent when another packet is also sent.
+
+ Support for this feature is indicated by:
+
+ /sys/bus/event_source/devices/intel_pt/caps/psb_cyc
+
+ which contains "1" if the feature is supported and
+ "0" otherwise.
+
+ The number of CYC packets produced can be reduced by specifying
+ a threshold - see cyc_thresh below.
+
+cyc_thresh Specifies how frequently CYC packets are produced - see cyc
+ above for how to determine if CYC packets are supported.
+
+ Valid cyc_thresh values are given by:
+
+ /sys/bus/event_source/devices/intel_pt/caps/cycle_thresholds
+
+ which contains a hexadecimal value, the bits of which represent
+ valid values e.g. bit 2 set means value 2 is valid.
+
+ The cyc_thresh value represents the minimum number of CPU cycles
+ that must have passed before a CYC packet can be sent. The
+ number of CPU cycles is:
+
+ 2 ^ (value - 1)
+
+ e.g. value 4 means 8 CPU cycles must pass before a CYC packet
+ can be sent. Note a CYC packet is still only sent when another
+ packet is sent, not at, e.g. every 8 CPU cycles.
+
+ If an invalid value is entered, the error message
+ will give a list of valid values e.g.
+
+ $ perf record -e intel_pt/cyc,cyc_thresh=15/u uname
+ Invalid cyc_thresh for intel_pt. Valid values are: 0-12
+
+ CYC packets are not requested by default.
+
+pt Specifies pass-through which enables the 'branch' config term.
+
+ The default config selects 'pt' if it is available, so a user will
+ never need to specify this term.
+
+branch Enable branch tracing. Branch tracing is enabled by default so to
+ disable branch tracing use 'branch=0'.
+
+ The default config selects 'branch' if it is available.
+
+ptw Enable PTWRITE packets which are produced when a ptwrite instruction
+ is executed.
+
+ Support for this feature is indicated by:
+
+ /sys/bus/event_source/devices/intel_pt/caps/ptwrite
+
+ which contains "1" if the feature is supported and
+ "0" otherwise.
+
+fup_on_ptw Enable a FUP packet to follow the PTWRITE packet. The FUP packet
+ provides the address of the ptwrite instruction. In the absence of
+ fup_on_ptw, the decoder will use the address of the previous branch
+ if branch tracing is enabled, otherwise the address will be zero.
+ Note that fup_on_ptw will work even when branch tracing is disabled.
+
+pwr_evt Enable power events. The power events provide information about
+ changes to the CPU C-state.
+
+ Support for this feature is indicated by:
+
+ /sys/bus/event_source/devices/intel_pt/caps/power_event_trace
+
+ which contains "1" if the feature is supported and
+ "0" otherwise.
+
+
+AUX area sampling option
+~~~~~~~~~~~~~~~~~~~~~~~~
+
+To select Intel PT "sampling" the AUX area sampling option can be used:
+
+ --aux-sample
+
+Optionally it can be followed by the sample size in bytes e.g.
+
+ --aux-sample=8192
+
+In addition, the Intel PT event to sample must be defined e.g.
+
+ -e intel_pt//u
+
+Samples on other events will be created containing Intel PT data e.g. the
+following will create Intel PT samples on the branch-misses event, note the
+events must be grouped using {}:
+
+ perf record --aux-sample -e '{intel_pt//u,branch-misses:u}'
+
+An alternative to '--aux-sample' is to add the config term 'aux-sample-size' to
+events. In this case, the grouping is implied e.g.
+
+ perf record -e intel_pt//u -e branch-misses/aux-sample-size=8192/u
+
+is the same as:
+
+ perf record -e '{intel_pt//u,branch-misses/aux-sample-size=8192/u}'
+
+but allows for also using an address filter e.g.:
+
+ perf record -e intel_pt//u --filter 'filter * @/bin/ls' -e branch-misses/aux-sample-size=8192/u -- ls
+
+It is important to select a sample size that is big enough to contain at least
+one PSB packet. If not a warning will be displayed:
+
+ Intel PT sample size (%zu) may be too small for PSB period (%zu)
+
+The calculation used for that is: if sample_size <= psb_period + 256 display the
+warning. When sampling is used, psb_period defaults to 0 (2KiB).
+
+The default sample size is 4KiB.
+
+The sample size is passed in aux_sample_size in struct perf_event_attr. The
+sample size is limited by the maximum event size which is 64KiB. It is
+difficult to know how big the event might be without the trace sample attached,
+but the tool validates that the sample size is not greater than 60KiB.
+
+
+new snapshot option
+~~~~~~~~~~~~~~~~~~~
+
+The difference between full trace and snapshot from the kernel's perspective is
+that in full trace we don't overwrite trace data that the user hasn't collected
+yet (and indicated that by advancing aux_tail), whereas in snapshot mode we let
+the trace run and overwrite older data in the buffer so that whenever something
+interesting happens, we can stop it and grab a snapshot of what was going on
+around that interesting moment.
+
+To select snapshot mode a new option has been added:
+
+ -S
+
+Optionally it can be followed by the snapshot size e.g.
+
+ -S0x100000
+
+The default snapshot size is the auxtrace mmap size. If neither auxtrace mmap size
+nor snapshot size is specified, then the default is 4MiB for privileged users
+(or if /proc/sys/kernel/perf_event_paranoid < 0), 128KiB for unprivileged users.
+If an unprivileged user does not specify mmap pages, the mmap pages will be
+reduced as described in the 'new auxtrace mmap size option' section below.
+
+The snapshot size is displayed if the option -vv is used e.g.
+
+ Intel PT snapshot size: %zu
+
+
+new auxtrace mmap size option
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Intel PT buffer size is specified by an addition to the -m option e.g.
+
+ -m,16
+
+selects a buffer size of 16 pages i.e. 64KiB.
+
+Note that the existing functionality of -m is unchanged. The auxtrace mmap size
+is specified by the optional addition of a comma and the value.
+
+The default auxtrace mmap size for Intel PT is 4MiB/page_size for privileged users
+(or if /proc/sys/kernel/perf_event_paranoid < 0), 128KiB for unprivileged users.
+If an unprivileged user does not specify mmap pages, the mmap pages will be
+reduced from the default 512KiB/page_size to 256KiB/page_size, otherwise the
+user is likely to get an error as they exceed their mlock limit (Max locked
+memory as shown in /proc/self/limits). Note that perf does not count the first
+512KiB (actually /proc/sys/kernel/perf_event_mlock_kb minus 1 page) per cpu
+against the mlock limit so an unprivileged user is allowed 512KiB per cpu plus
+their mlock limit (which defaults to 64KiB but is not multiplied by the number
+of cpus).
+
+In full-trace mode, powers of two are allowed for buffer size, with a minimum
+size of 2 pages. In snapshot mode or sampling mode, it is the same but the
+minimum size is 1 page.
+
+The mmap size and auxtrace mmap size are displayed if the -vv option is used e.g.
+
+ mmap length 528384
+ auxtrace mmap length 4198400
+
+
+Intel PT modes of operation
+~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Intel PT can be used in 2 modes:
+ full-trace mode
+ sample mode
+ snapshot mode
+
+Full-trace mode traces continuously e.g.
+
+ perf record -e intel_pt//u uname
+
+Sample mode attaches a Intel PT sample to other events e.g.
+
+ perf record --aux-sample -e intel_pt//u -e branch-misses:u
+
+Snapshot mode captures the available data when a signal is sent e.g.
+
+ perf record -v -e intel_pt//u -S ./loopy 1000000000 &
+ [1] 11435
+ kill -USR2 11435
+ Recording AUX area tracing snapshot
+
+Note that the signal sent is SIGUSR2.
+Note that "Recording AUX area tracing snapshot" is displayed because the -v
+option is used.
+
+The 2 modes cannot be used together.
+
+
+Buffer handling
+~~~~~~~~~~~~~~~
+
+There may be buffer limitations (i.e. single ToPa entry) which means that actual
+buffer sizes are limited to powers of 2 up to 4MiB (MAX_ORDER). In order to
+provide other sizes, and in particular an arbitrarily large size, multiple
+buffers are logically concatenated. However an interrupt must be used to switch
+between buffers. That has two potential problems:
+ a) the interrupt may not be handled in time so that the current buffer
+ becomes full and some trace data is lost.
+ b) the interrupts may slow the system and affect the performance
+ results.
+
+If trace data is lost, the driver sets 'truncated' in the PERF_RECORD_AUX event
+which the tools report as an error.
+
+In full-trace mode, the driver waits for data to be copied out before allowing
+the (logical) buffer to wrap-around. If data is not copied out quickly enough,
+again 'truncated' is set in the PERF_RECORD_AUX event. If the driver has to
+wait, the intel_pt event gets disabled. Because it is difficult to know when
+that happens, perf tools always re-enable the intel_pt event after copying out
+data.
+
+
+Intel PT and build ids
+~~~~~~~~~~~~~~~~~~~~~~
+
+By default "perf record" post-processes the event stream to find all build ids
+for executables for all addresses sampled. Deliberately, Intel PT is not
+decoded for that purpose (it would take too long). Instead the build ids for
+all executables encountered (due to mmap, comm or task events) are included
+in the perf.data file.
+
+To see buildids included in the perf.data file use the command:
+
+ perf buildid-list
+
+If the perf.data file contains Intel PT data, that is the same as:
+
+ perf buildid-list --with-hits
+
+
+Snapshot mode and event disabling
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+In order to make a snapshot, the intel_pt event is disabled using an IOCTL,
+namely PERF_EVENT_IOC_DISABLE. However doing that can also disable the
+collection of side-band information. In order to prevent that, a dummy
+software event has been introduced that permits tracking events (like mmaps) to
+continue to be recorded while intel_pt is disabled. That is important to ensure
+there is complete side-band information to allow the decoding of subsequent
+snapshots.
+
+A test has been created for that. To find the test:
+
+ perf test list
+ ...
+ 23: Test using a dummy software event to keep tracking
+
+To run the test:
+
+ perf test 23
+ 23: Test using a dummy software event to keep tracking : Ok
+
+
+perf record modes (nothing new here)
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+perf record essentially operates in one of three modes:
+ per thread
+ per cpu
+ workload only
+
+"per thread" mode is selected by -t or by --per-thread (with -p or -u or just a
+workload).
+"per cpu" is selected by -C or -a.
+"workload only" mode is selected by not using the other options but providing a
+command to run (i.e. the workload).
+
+In per-thread mode an exact list of threads is traced. There is no inheritance.
+Each thread has its own event buffer.
+
+In per-cpu mode all processes (or processes from the selected cgroup i.e. -G
+option, or processes selected with -p or -u) are traced. Each cpu has its own
+buffer. Inheritance is allowed.
+
+In workload-only mode, the workload is traced but with per-cpu buffers.
+Inheritance is allowed. Note that you can now trace a workload in per-thread
+mode by using the --per-thread option.
+
+
+Privileged vs non-privileged users
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Unless /proc/sys/kernel/perf_event_paranoid is set to -1, unprivileged users
+have memory limits imposed upon them. That affects what buffer sizes they can
+have as outlined above.
+
+The v4.2 kernel introduced support for a context switch metadata event,
+PERF_RECORD_SWITCH, which allows unprivileged users to see when their processes
+are scheduled out and in, just not by whom, which is left for the
+PERF_RECORD_SWITCH_CPU_WIDE, that is only accessible in system wide context,
+which in turn requires CAP_SYS_ADMIN.
+
+Please see the 45ac1403f564 ("perf: Add PERF_RECORD_SWITCH to indicate context
+switches") commit, that introduces these metadata events for further info.
+
+When working with kernels < v4.2, the following considerations must be taken,
+as the sched:sched_switch tracepoints will be used to receive such information:
+
+Unless /proc/sys/kernel/perf_event_paranoid is set to -1, unprivileged users are
+not permitted to use tracepoints which means there is insufficient side-band
+information to decode Intel PT in per-cpu mode, and potentially workload-only
+mode too if the workload creates new processes.
+
+Note also, that to use tracepoints, read-access to debugfs is required. So if
+debugfs is not mounted or the user does not have read-access, it will again not
+be possible to decode Intel PT in per-cpu mode.
+
+
+sched_switch tracepoint
+~~~~~~~~~~~~~~~~~~~~~~~
+
+The sched_switch tracepoint is used to provide side-band data for Intel PT
+decoding in kernels where the PERF_RECORD_SWITCH metadata event isn't
+available.
+
+The sched_switch events are automatically added. e.g. the second event shown
+below:
+
+ $ perf record -vv -e intel_pt//u uname
+ ------------------------------------------------------------
+ perf_event_attr:
+ type 6
+ size 112
+ config 0x400
+ { sample_period, sample_freq } 1
+ sample_type IP|TID|TIME|CPU|IDENTIFIER
+ read_format ID
+ disabled 1
+ inherit 1
+ exclude_kernel 1
+ exclude_hv 1
+ enable_on_exec 1
+ sample_id_all 1
+ ------------------------------------------------------------
+ sys_perf_event_open: pid 31104 cpu 0 group_fd -1 flags 0x8
+ sys_perf_event_open: pid 31104 cpu 1 group_fd -1 flags 0x8
+ sys_perf_event_open: pid 31104 cpu 2 group_fd -1 flags 0x8
+ sys_perf_event_open: pid 31104 cpu 3 group_fd -1 flags 0x8
+ ------------------------------------------------------------
+ perf_event_attr:
+ type 2
+ size 112
+ config 0x108
+ { sample_period, sample_freq } 1
+ sample_type IP|TID|TIME|CPU|PERIOD|RAW|IDENTIFIER
+ read_format ID
+ inherit 1
+ sample_id_all 1
+ exclude_guest 1
+ ------------------------------------------------------------
+ sys_perf_event_open: pid -1 cpu 0 group_fd -1 flags 0x8
+ sys_perf_event_open: pid -1 cpu 1 group_fd -1 flags 0x8
+ sys_perf_event_open: pid -1 cpu 2 group_fd -1 flags 0x8
+ sys_perf_event_open: pid -1 cpu 3 group_fd -1 flags 0x8
+ ------------------------------------------------------------
+ perf_event_attr:
+ type 1
+ size 112
+ config 0x9
+ { sample_period, sample_freq } 1
+ sample_type IP|TID|TIME|IDENTIFIER
+ read_format ID
+ disabled 1
+ inherit 1
+ exclude_kernel 1
+ exclude_hv 1
+ mmap 1
+ comm 1
+ enable_on_exec 1
+ task 1
+ sample_id_all 1
+ mmap2 1
+ comm_exec 1
+ ------------------------------------------------------------
+ sys_perf_event_open: pid 31104 cpu 0 group_fd -1 flags 0x8
+ sys_perf_event_open: pid 31104 cpu 1 group_fd -1 flags 0x8
+ sys_perf_event_open: pid 31104 cpu 2 group_fd -1 flags 0x8
+ sys_perf_event_open: pid 31104 cpu 3 group_fd -1 flags 0x8
+ mmap size 528384B
+ AUX area mmap length 4194304
+ perf event ring buffer mmapped per cpu
+ Synthesizing auxtrace information
+ Linux
+ [ perf record: Woken up 1 times to write data ]
+ [ perf record: Captured and wrote 0.042 MB perf.data ]
+
+Note, the sched_switch event is only added if the user is permitted to use it
+and only in per-cpu mode.
+
+Note also, the sched_switch event is only added if TSC packets are requested.
+That is because, in the absence of timing information, the sched_switch events
+cannot be matched against the Intel PT trace.
+
+
+perf script
+-----------
+
+By default, perf script will decode trace data found in the perf.data file.
+This can be further controlled by new option --itrace.
+
+
+New --itrace option
+~~~~~~~~~~~~~~~~~~~
+
+Having no option is the same as
+
+ --itrace
+
+which, in turn, is the same as
+
+ --itrace=cepwx
+
+The letters are:
+
+ i synthesize "instructions" events
+ b synthesize "branches" events
+ x synthesize "transactions" events
+ w synthesize "ptwrite" events
+ p synthesize "power" events
+ c synthesize branches events (calls only)
+ r synthesize branches events (returns only)
+ e synthesize tracing error events
+ d create a debug log
+ g synthesize a call chain (use with i or x)
+ l synthesize last branch entries (use with i or x)
+ s skip initial number of events
+
+"Instructions" events look like they were recorded by "perf record -e
+instructions".
+
+"Branches" events look like they were recorded by "perf record -e branches". "c"
+and "r" can be combined to get calls and returns.
+
+"Transactions" events correspond to the start or end of transactions. The
+'flags' field can be used in perf script to determine whether the event is a
+tranasaction start, commit or abort.
+
+Note that "instructions", "branches" and "transactions" events depend on code
+flow packets which can be disabled by using the config term "branch=0". Refer
+to the config terms section above.
+
+"ptwrite" events record the payload of the ptwrite instruction and whether
+"fup_on_ptw" was used. "ptwrite" events depend on PTWRITE packets which are
+recorded only if the "ptw" config term was used. Refer to the config terms
+section above. perf script "synth" field displays "ptwrite" information like
+this: "ip: 0 payload: 0x123456789abcdef0" where "ip" is 1 if "fup_on_ptw" was
+used.
+
+"Power" events correspond to power event packets and CBR (core-to-bus ratio)
+packets. While CBR packets are always recorded when tracing is enabled, power
+event packets are recorded only if the "pwr_evt" config term was used. Refer to
+the config terms section above. The power events record information about
+C-state changes, whereas CBR is indicative of CPU frequency. perf script
+"event,synth" fields display information like this:
+ cbr: cbr: 22 freq: 2189 MHz (200%)
+ mwait: hints: 0x60 extensions: 0x1
+ pwre: hw: 0 cstate: 2 sub-cstate: 0
+ exstop: ip: 1
+ pwrx: deepest cstate: 2 last cstate: 2 wake reason: 0x4
+Where:
+ "cbr" includes the frequency and the percentage of maximum non-turbo
+ "mwait" shows mwait hints and extensions
+ "pwre" shows C-state transitions (to a C-state deeper than C0) and
+ whether initiated by hardware
+ "exstop" indicates execution stopped and whether the IP was recorded
+ exactly,
+ "pwrx" indicates return to C0
+For more details refer to the Intel 64 and IA-32 Architectures Software
+Developer Manuals.
+
+Error events show where the decoder lost the trace. Error events
+are quite important. Users must know if what they are seeing is a complete
+picture or not.
+
+The "d" option will cause the creation of a file "intel_pt.log" containing all
+decoded packets and instructions. Note that this option slows down the decoder
+and that the resulting file may be very large.
+
+In addition, the period of the "instructions" event can be specified. e.g.
+
+ --itrace=i10us
+
+sets the period to 10us i.e. one instruction sample is synthesized for each 10
+microseconds of trace. Alternatives to "us" are "ms" (milliseconds),
+"ns" (nanoseconds), "t" (TSC ticks) or "i" (instructions).
+
+"ms", "us" and "ns" are converted to TSC ticks.
+
+The timing information included with Intel PT does not give the time of every
+instruction. Consequently, for the purpose of sampling, the decoder estimates
+the time since the last timing packet based on 1 tick per instruction. The time
+on the sample is *not* adjusted and reflects the last known value of TSC.
+
+For Intel PT, the default period is 100us.
+
+Setting it to a zero period means "as often as possible".
+
+In the case of Intel PT that is the same as a period of 1 and a unit of
+'instructions' (i.e. --itrace=i1i).
+
+Also the call chain size (default 16, max. 1024) for instructions or
+transactions events can be specified. e.g.
+
+ --itrace=ig32
+ --itrace=xg32
+
+Also the number of last branch entries (default 64, max. 1024) for instructions or
+transactions events can be specified. e.g.
+
+ --itrace=il10
+ --itrace=xl10
+
+Note that last branch entries are cleared for each sample, so there is no overlap
+from one sample to the next.
+
+To disable trace decoding entirely, use the option --no-itrace.
+
+It is also possible to skip events generated (instructions, branches, transactions)
+at the beginning. This is useful to ignore initialization code.
+
+ --itrace=i0nss1000000
+
+skips the first million instructions.
+
+dump option
+~~~~~~~~~~~
+
+perf script has an option (-D) to "dump" the events i.e. display the binary
+data.
+
+When -D is used, Intel PT packets are displayed. The packet decoder does not
+pay attention to PSB packets, but just decodes the bytes - so the packets seen
+by the actual decoder may not be identical in places where the data is corrupt.
+One example of that would be when the buffer-switching interrupt has been too
+slow, and the buffer has been filled completely. In that case, the last packet
+in the buffer might be truncated and immediately followed by a PSB as the trace
+continues in the next buffer.
+
+To disable the display of Intel PT packets, combine the -D option with
+--no-itrace.
+
+
+perf report
+-----------
+
+By default, perf report will decode trace data found in the perf.data file.
+This can be further controlled by new option --itrace exactly the same as
+perf script, with the exception that the default is --itrace=igxe.
+
+
+perf inject
+-----------
+
+perf inject also accepts the --itrace option in which case tracing data is
+removed and replaced with the synthesized events. e.g.
+
+ perf inject --itrace -i perf.data -o perf.data.new
+
+Below is an example of using Intel PT with autofdo. It requires autofdo
+(https://github.com/google/autofdo) and gcc version 5. The bubble
+sort example is from the AutoFDO tutorial (https://gcc.gnu.org/wiki/AutoFDO/Tutorial)
+amended to take the number of elements as a parameter.
+
+ $ gcc-5 -O3 sort.c -o sort_optimized
+ $ ./sort_optimized 30000
+ Bubble sorting array of 30000 elements
+ 2254 ms
+
+ $ cat ~/.perfconfig
+ [intel-pt]
+ mispred-all = on
+
+ $ perf record -e intel_pt//u ./sort 3000
+ Bubble sorting array of 3000 elements
+ 58 ms
+ [ perf record: Woken up 2 times to write data ]
+ [ perf record: Captured and wrote 3.939 MB perf.data ]
+ $ perf inject -i perf.data -o inj --itrace=i100usle --strip
+ $ ./create_gcov --binary=./sort --profile=inj --gcov=sort.gcov -gcov_version=1
+ $ gcc-5 -O3 -fauto-profile=sort.gcov sort.c -o sort_autofdo
+ $ ./sort_autofdo 30000
+ Bubble sorting array of 30000 elements
+ 2155 ms
+
+Note there is currently no advantage to using Intel PT instead of LBR, but
+that may change in the future if greater use is made of the data.
+
+
+PEBS via Intel PT
+-----------------
+
+Some hardware has the feature to redirect PEBS records to the Intel PT trace.
+Recording is selected by using the aux-output config term e.g.
+
+ perf record -c 10000 -e '{intel_pt/branch=0/,cycles/aux-output/ppp}' uname
+
+Note that currently, software only supports redirecting at most one PEBS event.
+
+To display PEBS events from the Intel PT trace, use the itrace 'o' option e.g.
+
+ perf script --itrace=oe
+
+
+SEE ALSO
+--------
+
+linkperf:perf-record[1], linkperf:perf-script[1], linkperf:perf-report[1],
+linkperf:perf-inject[1]
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index b23a4012a606..7f4db7592467 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -589,4 +589,4 @@ appended unit character - B/K/M/G
SEE ALSO
--------
-linkperf:perf-stat[1], linkperf:perf-list[1]
+linkperf:perf-stat[1], linkperf:perf-list[1], linkperf:perf-intel-pt[1]
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index db61f16ffa56..bd0a029d4c08 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -546,4 +546,5 @@ include::callchain-overhead-calculation.txt[]
SEE ALSO
--------
-linkperf:perf-stat[1], linkperf:perf-annotate[1], linkperf:perf-record[1]
+linkperf:perf-stat[1], linkperf:perf-annotate[1], linkperf:perf-record[1],
+linkperf:perf-intel-pt[1]
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 2599b057e47b..db6a36aac47e 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -429,4 +429,4 @@ include::itrace.txt[]
SEE ALSO
--------
linkperf:perf-record[1], linkperf:perf-script-perl[1],
-linkperf:perf-script-python[1]
+linkperf:perf-script-python[1], linkperf:perf-intel-pt[1]
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 9431b8066fb4..4d56586b2fb9 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -334,6 +334,15 @@ Configure all used events to run in kernel space.
--all-user::
Configure all used events to run in user space.
+--percore-show-thread::
+The event modifier "percore" has supported to sum up the event counts
+for all hardware threads in a core and show the counts per core.
+
+This option with event modifier "percore" enabled also sums up the event
+counts for all hardware threads in a core but show the sum counts per
+hardware thread. This is essentially a replacement for the any bit and
+convenient for post processing.
+
EXAMPLES
--------
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 7902a5681fc8..b8fc7d972be9 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -35,7 +35,7 @@ endif
# Only pass canonical directory names as the output directory:
#
ifneq ($(O),)
- FULL_O := $(shell readlink -f $(O) || echo $(O))
+ FULL_O := $(shell cd $(PWD); readlink -f $(O) || echo $(O))
endif
#
diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c
index 2898cfdf8fe1..941f814820b8 100644
--- a/tools/perf/arch/arm/util/cs-etm.c
+++ b/tools/perf/arch/arm/util/cs-etm.c
@@ -858,21 +858,6 @@ static void cs_etm_recording_free(struct auxtrace_record *itr)
free(ptr);
}
-static int cs_etm_read_finish(struct auxtrace_record *itr, int idx)
-{
- struct cs_etm_recording *ptr =
- container_of(itr, struct cs_etm_recording, itr);
- struct evsel *evsel;
-
- evlist__for_each_entry(ptr->evlist, evsel) {
- if (evsel->core.attr.type == ptr->cs_etm_pmu->type)
- return perf_evlist__enable_event_idx(ptr->evlist,
- evsel, idx);
- }
-
- return -EINVAL;
-}
-
struct auxtrace_record *cs_etm_record_init(int *err)
{
struct perf_pmu *cs_etm_pmu;
@@ -892,6 +877,7 @@ struct auxtrace_record *cs_etm_record_init(int *err)
}
ptr->cs_etm_pmu = cs_etm_pmu;
+ ptr->itr.pmu = cs_etm_pmu;
ptr->itr.parse_snapshot_options = cs_etm_parse_snapshot_options;
ptr->itr.recording_options = cs_etm_recording_options;
ptr->itr.info_priv_size = cs_etm_info_priv_size;
@@ -901,7 +887,7 @@ struct auxtrace_record *cs_etm_record_init(int *err)
ptr->itr.snapshot_finish = cs_etm_snapshot_finish;
ptr->itr.reference = cs_etm_reference;
ptr->itr.free = cs_etm_recording_free;
- ptr->itr.read_finish = cs_etm_read_finish;
+ ptr->itr.read_finish = auxtrace_record__read_finish;
*err = 0;
return &ptr->itr;
diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c
index eba6541ec0f1..27653be24447 100644
--- a/tools/perf/arch/arm64/util/arm-spe.c
+++ b/tools/perf/arch/arm64/util/arm-spe.c
@@ -11,17 +11,17 @@
#include <linux/zalloc.h>
#include <time.h>
-#include "../../util/cpumap.h"
-#include "../../util/event.h"
-#include "../../util/evsel.h"
-#include "../../util/evlist.h"
-#include "../../util/session.h"
+#include "../../../util/cpumap.h"
+#include "../../../util/event.h"
+#include "../../../util/evsel.h"
+#include "../../../util/evlist.h"
+#include "../../../util/session.h"
#include <internal/lib.h> // page_size
-#include "../../util/pmu.h"
-#include "../../util/debug.h"
-#include "../../util/auxtrace.h"
-#include "../../util/record.h"
-#include "../../util/arm-spe.h"
+#include "../../../util/pmu.h"
+#include "../../../util/debug.h"
+#include "../../../util/auxtrace.h"
+#include "../../../util/record.h"
+#include "../../../util/arm-spe.h"
#define KiB(x) ((x) * 1024)
#define MiB(x) ((x) * 1024 * 1024)
@@ -158,20 +158,6 @@ static void arm_spe_recording_free(struct auxtrace_record *itr)
free(sper);
}
-static int arm_spe_read_finish(struct auxtrace_record *itr, int idx)
-{
- struct arm_spe_recording *sper =
- container_of(itr, struct arm_spe_recording, itr);
- struct evsel *evsel;
-
- evlist__for_each_entry(sper->evlist, evsel) {
- if (evsel->core.attr.type == sper->arm_spe_pmu->type)
- return perf_evlist__enable_event_idx(sper->evlist,
- evsel, idx);
- }
- return -EINVAL;
-}
-
struct auxtrace_record *arm_spe_recording_init(int *err,
struct perf_pmu *arm_spe_pmu)
{
@@ -189,12 +175,13 @@ struct auxtrace_record *arm_spe_recording_init(int *err,
}
sper->arm_spe_pmu = arm_spe_pmu;
+ sper->itr.pmu = arm_spe_pmu;
sper->itr.recording_options = arm_spe_recording_options;
sper->itr.info_priv_size = arm_spe_info_priv_size;
sper->itr.info_fill = arm_spe_info_fill;
sper->itr.free = arm_spe_recording_free;
sper->itr.reference = arm_spe_reference;
- sper->itr.read_finish = arm_spe_read_finish;
+ sper->itr.read_finish = auxtrace_record__read_finish;
sper->itr.alignment = 0;
*err = 0;
diff --git a/tools/perf/arch/arm64/util/header.c b/tools/perf/arch/arm64/util/header.c
index a32e4b72a98f..d730666ab95d 100644
--- a/tools/perf/arch/arm64/util/header.c
+++ b/tools/perf/arch/arm64/util/header.c
@@ -1,8 +1,10 @@
#include <stdio.h>
#include <stdlib.h>
#include <perf/cpumap.h>
+#include <util/cpumap.h>
#include <internal/cpumap.h>
#include <api/fs/fs.h>
+#include <errno.h>
#include "debug.h"
#include "header.h"
@@ -12,26 +14,21 @@
#define MIDR_VARIANT_SHIFT 20
#define MIDR_VARIANT_MASK (0xf << MIDR_VARIANT_SHIFT)
-char *get_cpuid_str(struct perf_pmu *pmu)
+static int _get_cpuid(char *buf, size_t sz, struct perf_cpu_map *cpus)
{
- char *buf = NULL;
- char path[PATH_MAX];
const char *sysfs = sysfs__mountpoint();
- int cpu;
u64 midr = 0;
- struct perf_cpu_map *cpus;
- FILE *file;
+ int cpu;
- if (!sysfs || !pmu || !pmu->cpus)
- return NULL;
+ if (!sysfs || sz < MIDR_SIZE)
+ return EINVAL;
- buf = malloc(MIDR_SIZE);
- if (!buf)
- return NULL;
+ cpus = perf_cpu_map__get(cpus);
- /* read midr from list of cpus mapped to this pmu */
- cpus = perf_cpu_map__get(pmu->cpus);
for (cpu = 0; cpu < perf_cpu_map__nr(cpus); cpu++) {
+ char path[PATH_MAX];
+ FILE *file;
+
scnprintf(path, PATH_MAX, "%s/devices/system/cpu/cpu%d"MIDR,
sysfs, cpus->map[cpu]);
@@ -57,12 +54,48 @@ char *get_cpuid_str(struct perf_pmu *pmu)
break;
}
- if (!midr) {
+ perf_cpu_map__put(cpus);
+
+ if (!midr)
+ return EINVAL;
+
+ return 0;
+}
+
+int get_cpuid(char *buf, size_t sz)
+{
+ struct perf_cpu_map *cpus = perf_cpu_map__new(NULL);
+ int ret;
+
+ if (!cpus)
+ return EINVAL;
+
+ ret = _get_cpuid(buf, sz, cpus);
+
+ perf_cpu_map__put(cpus);
+
+ return ret;
+}
+
+char *get_cpuid_str(struct perf_pmu *pmu)
+{
+ char *buf = NULL;
+ int res;
+
+ if (!pmu || !pmu->cpus)
+ return NULL;
+
+ buf = malloc(MIDR_SIZE);
+ if (!buf)
+ return NULL;
+
+ /* read midr from list of cpus mapped to this pmu */
+ res = _get_cpuid(buf, MIDR_SIZE, pmu->cpus);
+ if (res) {
pr_err("failed to get cpuid string for PMU %s\n", pmu->name);
free(buf);
buf = NULL;
}
- perf_cpu_map__put(cpus);
return buf;
}
diff --git a/tools/perf/arch/arm64/util/perf_regs.c b/tools/perf/arch/arm64/util/perf_regs.c
index 2864e2e3776d..2833e101a7c6 100644
--- a/tools/perf/arch/arm64/util/perf_regs.c
+++ b/tools/perf/arch/arm64/util/perf_regs.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
-#include "../../util/perf_regs.h"
+#include "../../../util/perf_regs.h"
const struct sample_reg sample_reg_masks[] = {
SMPL_REG_END
diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
index 43f736ed47f2..35b61bfc1b1a 100644
--- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
@@ -517,3 +517,5 @@
433 common fspick sys_fspick
434 common pidfd_open sys_pidfd_open
435 nospu clone3 ppc_clone3
+437 common openat2 sys_openat2
+438 common pidfd_getfd sys_pidfd_getfd
diff --git a/tools/perf/arch/powerpc/util/perf_regs.c b/tools/perf/arch/powerpc/util/perf_regs.c
index e9c436eeffc9..0a5242900248 100644
--- a/tools/perf/arch/powerpc/util/perf_regs.c
+++ b/tools/perf/arch/powerpc/util/perf_regs.c
@@ -4,8 +4,8 @@
#include <regex.h>
#include <linux/zalloc.h>
-#include "../../util/perf_regs.h"
-#include "../../util/debug.h"
+#include "../../../util/perf_regs.h"
+#include "../../../util/debug.h"
#include <linux/kernel.h>
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index c29976eca4a8..44d510bc9b78 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -357,6 +357,8 @@
433 common fspick __x64_sys_fspick
434 common pidfd_open __x64_sys_pidfd_open
435 common clone3 __x64_sys_clone3/ptregs
+437 common openat2 __x64_sys_openat2
+438 common pidfd_getfd __x64_sys_pidfd_getfd
#
# x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/tools/perf/arch/x86/tests/insn-x86-dat-32.c b/tools/perf/arch/x86/tests/insn-x86-dat-32.c
index e6461abc9e7b..9708ae892061 100644
--- a/tools/perf/arch/x86/tests/insn-x86-dat-32.c
+++ b/tools/perf/arch/x86/tests/insn-x86-dat-32.c
@@ -2085,6 +2085,118 @@
"67 f3 0f 38 f8 1c \tenqcmds (%si),%bx",},
{{0x67, 0xf3, 0x0f, 0x38, 0xf8, 0x8c, 0x34, 0x12, }, 8, 0, "", "",
"67 f3 0f 38 f8 8c 34 12 \tenqcmds 0x1234(%si),%cx",},
+{{0xf3, 0x0f, 0xae, 0xe8, }, 4, 0, "", "",
+"f3 0f ae e8 \tincsspd %eax",},
+{{0x0f, 0xae, 0x28, }, 3, 0, "", "",
+"0f ae 28 \txrstor (%eax)",},
+{{0x0f, 0xae, 0x2d, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f ae 2d 78 56 34 12 \txrstor 0x12345678",},
+{{0x0f, 0xae, 0xac, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
+"0f ae ac c8 78 56 34 12 \txrstor 0x12345678(%eax,%ecx,8)",},
+{{0x0f, 0xae, 0xe8, }, 3, 0, "", "",
+"0f ae e8 \tlfence ",},
+{{0xf3, 0x0f, 0x1e, 0xc8, }, 4, 0, "", "",
+"f3 0f 1e c8 \trdsspd %eax",},
+{{0xf3, 0x0f, 0x01, 0xea, }, 4, 0, "", "",
+"f3 0f 01 ea \tsaveprevssp ",},
+{{0xf3, 0x0f, 0x01, 0x28, }, 4, 0, "", "",
+"f3 0f 01 28 \trstorssp (%eax)",},
+{{0xf3, 0x0f, 0x01, 0x2d, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
+"f3 0f 01 2d 78 56 34 12 \trstorssp 0x12345678",},
+{{0xf3, 0x0f, 0x01, 0xac, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
+"f3 0f 01 ac c8 78 56 34 12 \trstorssp 0x12345678(%eax,%ecx,8)",},
+{{0x0f, 0x38, 0xf6, 0x08, }, 4, 0, "", "",
+"0f 38 f6 08 \twrssd %ecx,(%eax)",},
+{{0x0f, 0x38, 0xf6, 0x15, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
+"0f 38 f6 15 78 56 34 12 \twrssd %edx,0x12345678",},
+{{0x0f, 0x38, 0xf6, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
+"0f 38 f6 94 c8 78 56 34 12 \twrssd %edx,0x12345678(%eax,%ecx,8)",},
+{{0x66, 0x0f, 0x38, 0xf5, 0x08, }, 5, 0, "", "",
+"66 0f 38 f5 08 \twrussd %ecx,(%eax)",},
+{{0x66, 0x0f, 0x38, 0xf5, 0x15, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
+"66 0f 38 f5 15 78 56 34 12 \twrussd %edx,0x12345678",},
+{{0x66, 0x0f, 0x38, 0xf5, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "",
+"66 0f 38 f5 94 c8 78 56 34 12 \twrussd %edx,0x12345678(%eax,%ecx,8)",},
+{{0xf3, 0x0f, 0x01, 0xe8, }, 4, 0, "", "",
+"f3 0f 01 e8 \tsetssbsy ",},
+{{0x0f, 0x01, 0xee, }, 3, 0, "", "",
+"0f 01 ee \trdpkru ",},
+{{0x0f, 0x01, 0xef, }, 3, 0, "", "",
+"0f 01 ef \twrpkru ",},
+{{0xf3, 0x0f, 0xae, 0x30, }, 4, 0, "", "",
+"f3 0f ae 30 \tclrssbsy (%eax)",},
+{{0xf3, 0x0f, 0xae, 0x35, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
+"f3 0f ae 35 78 56 34 12 \tclrssbsy 0x12345678",},
+{{0xf3, 0x0f, 0xae, 0xb4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
+"f3 0f ae b4 c8 78 56 34 12 \tclrssbsy 0x12345678(%eax,%ecx,8)",},
+{{0xf3, 0x0f, 0x1e, 0xfb, }, 4, 0, "", "",
+"f3 0f 1e fb \tendbr32 ",},
+{{0xf3, 0x0f, 0x1e, 0xfa, }, 4, 0, "", "",
+"f3 0f 1e fa \tendbr64 ",},
+{{0xff, 0xd0, }, 2, 0, "call", "indirect",
+"ff d0 \tcall *%eax",},
+{{0xff, 0x10, }, 2, 0, "call", "indirect",
+"ff 10 \tcall *(%eax)",},
+{{0xff, 0x15, 0x78, 0x56, 0x34, 0x12, }, 6, 0, "call", "indirect",
+"ff 15 78 56 34 12 \tcall *0x12345678",},
+{{0xff, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "call", "indirect",
+"ff 94 c8 78 56 34 12 \tcall *0x12345678(%eax,%ecx,8)",},
+{{0xf2, 0xff, 0xd0, }, 3, 0, "call", "indirect",
+"f2 ff d0 \tbnd call *%eax",},
+{{0xf2, 0xff, 0x10, }, 3, 0, "call", "indirect",
+"f2 ff 10 \tbnd call *(%eax)",},
+{{0xf2, 0xff, 0x15, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "call", "indirect",
+"f2 ff 15 78 56 34 12 \tbnd call *0x12345678",},
+{{0xf2, 0xff, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "call", "indirect",
+"f2 ff 94 c8 78 56 34 12 \tbnd call *0x12345678(%eax,%ecx,8)",},
+{{0x3e, 0xff, 0xd0, }, 3, 0, "call", "indirect",
+"3e ff d0 \tnotrack call *%eax",},
+{{0x3e, 0xff, 0x10, }, 3, 0, "call", "indirect",
+"3e ff 10 \tnotrack call *(%eax)",},
+{{0x3e, 0xff, 0x15, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "call", "indirect",
+"3e ff 15 78 56 34 12 \tnotrack call *0x12345678",},
+{{0x3e, 0xff, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "call", "indirect",
+"3e ff 94 c8 78 56 34 12 \tnotrack call *0x12345678(%eax,%ecx,8)",},
+{{0x3e, 0xf2, 0xff, 0xd0, }, 4, 0, "call", "indirect",
+"3e f2 ff d0 \tnotrack bnd call *%eax",},
+{{0x3e, 0xf2, 0xff, 0x10, }, 4, 0, "call", "indirect",
+"3e f2 ff 10 \tnotrack bnd call *(%eax)",},
+{{0x3e, 0xf2, 0xff, 0x15, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "call", "indirect",
+"3e f2 ff 15 78 56 34 12 \tnotrack bnd call *0x12345678",},
+{{0x3e, 0xf2, 0xff, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "call", "indirect",
+"3e f2 ff 94 c8 78 56 34 12 \tnotrack bnd call *0x12345678(%eax,%ecx,8)",},
+{{0xff, 0xe0, }, 2, 0, "jmp", "indirect",
+"ff e0 \tjmp *%eax",},
+{{0xff, 0x20, }, 2, 0, "jmp", "indirect",
+"ff 20 \tjmp *(%eax)",},
+{{0xff, 0x25, 0x78, 0x56, 0x34, 0x12, }, 6, 0, "jmp", "indirect",
+"ff 25 78 56 34 12 \tjmp *0x12345678",},
+{{0xff, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "jmp", "indirect",
+"ff a4 c8 78 56 34 12 \tjmp *0x12345678(%eax,%ecx,8)",},
+{{0xf2, 0xff, 0xe0, }, 3, 0, "jmp", "indirect",
+"f2 ff e0 \tbnd jmp *%eax",},
+{{0xf2, 0xff, 0x20, }, 3, 0, "jmp", "indirect",
+"f2 ff 20 \tbnd jmp *(%eax)",},
+{{0xf2, 0xff, 0x25, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "jmp", "indirect",
+"f2 ff 25 78 56 34 12 \tbnd jmp *0x12345678",},
+{{0xf2, 0xff, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "jmp", "indirect",
+"f2 ff a4 c8 78 56 34 12 \tbnd jmp *0x12345678(%eax,%ecx,8)",},
+{{0x3e, 0xff, 0xe0, }, 3, 0, "jmp", "indirect",
+"3e ff e0 \tnotrack jmp *%eax",},
+{{0x3e, 0xff, 0x20, }, 3, 0, "jmp", "indirect",
+"3e ff 20 \tnotrack jmp *(%eax)",},
+{{0x3e, 0xff, 0x25, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "jmp", "indirect",
+"3e ff 25 78 56 34 12 \tnotrack jmp *0x12345678",},
+{{0x3e, 0xff, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "jmp", "indirect",
+"3e ff a4 c8 78 56 34 12 \tnotrack jmp *0x12345678(%eax,%ecx,8)",},
+{{0x3e, 0xf2, 0xff, 0xe0, }, 4, 0, "jmp", "indirect",
+"3e f2 ff e0 \tnotrack bnd jmp *%eax",},
+{{0x3e, 0xf2, 0xff, 0x20, }, 4, 0, "jmp", "indirect",
+"3e f2 ff 20 \tnotrack bnd jmp *(%eax)",},
+{{0x3e, 0xf2, 0xff, 0x25, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "jmp", "indirect",
+"3e f2 ff 25 78 56 34 12 \tnotrack bnd jmp *0x12345678",},
+{{0x3e, 0xf2, 0xff, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "jmp", "indirect",
+"3e f2 ff a4 c8 78 56 34 12 \tnotrack bnd jmp *0x12345678(%eax,%ecx,8)",},
{{0x0f, 0x01, 0xcf, }, 3, 0, "", "",
"0f 01 cf \tencls ",},
{{0x0f, 0x01, 0xd7, }, 3, 0, "", "",
diff --git a/tools/perf/arch/x86/tests/insn-x86-dat-64.c b/tools/perf/arch/x86/tests/insn-x86-dat-64.c
index 567ecccfad7c..5da17d41d302 100644
--- a/tools/perf/arch/x86/tests/insn-x86-dat-64.c
+++ b/tools/perf/arch/x86/tests/insn-x86-dat-64.c
@@ -2263,6 +2263,202 @@
"67 f3 0f 38 f8 18 \tenqcmds (%eax),%ebx",},
{{0x67, 0xf3, 0x0f, 0x38, 0xf8, 0x88, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "",
"67 f3 0f 38 f8 88 78 56 34 12 \tenqcmds 0x12345678(%eax),%ecx",},
+{{0xf3, 0x0f, 0xae, 0xe8, }, 4, 0, "", "",
+"f3 0f ae e8 \tincsspd %eax",},
+{{0xf3, 0x41, 0x0f, 0xae, 0xe8, }, 5, 0, "", "",
+"f3 41 0f ae e8 \tincsspd %r8d",},
+{{0xf3, 0x48, 0x0f, 0xae, 0xe8, }, 5, 0, "", "",
+"f3 48 0f ae e8 \tincsspq %rax",},
+{{0xf3, 0x49, 0x0f, 0xae, 0xe8, }, 5, 0, "", "",
+"f3 49 0f ae e8 \tincsspq %r8",},
+{{0x0f, 0xae, 0x28, }, 3, 0, "", "",
+"0f ae 28 \txrstor (%rax)",},
+{{0x41, 0x0f, 0xae, 0x28, }, 4, 0, "", "",
+"41 0f ae 28 \txrstor (%r8)",},
+{{0x0f, 0xae, 0x2c, 0x25, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
+"0f ae 2c 25 78 56 34 12 \txrstor 0x12345678",},
+{{0x0f, 0xae, 0xac, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
+"0f ae ac c8 78 56 34 12 \txrstor 0x12345678(%rax,%rcx,8)",},
+{{0x41, 0x0f, 0xae, 0xac, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
+"41 0f ae ac c8 78 56 34 12 \txrstor 0x12345678(%r8,%rcx,8)",},
+{{0x0f, 0xae, 0xe8, }, 3, 0, "", "",
+"0f ae e8 \tlfence ",},
+{{0xf3, 0x0f, 0x1e, 0xc8, }, 4, 0, "", "",
+"f3 0f 1e c8 \trdsspd %eax",},
+{{0xf3, 0x41, 0x0f, 0x1e, 0xc8, }, 5, 0, "", "",
+"f3 41 0f 1e c8 \trdsspd %r8d",},
+{{0xf3, 0x48, 0x0f, 0x1e, 0xc8, }, 5, 0, "", "",
+"f3 48 0f 1e c8 \trdsspq %rax",},
+{{0xf3, 0x49, 0x0f, 0x1e, 0xc8, }, 5, 0, "", "",
+"f3 49 0f 1e c8 \trdsspq %r8",},
+{{0xf3, 0x0f, 0x01, 0xea, }, 4, 0, "", "",
+"f3 0f 01 ea \tsaveprevssp ",},
+{{0xf3, 0x0f, 0x01, 0x28, }, 4, 0, "", "",
+"f3 0f 01 28 \trstorssp (%rax)",},
+{{0xf3, 0x41, 0x0f, 0x01, 0x28, }, 5, 0, "", "",
+"f3 41 0f 01 28 \trstorssp (%r8)",},
+{{0xf3, 0x0f, 0x01, 0x2c, 0x25, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
+"f3 0f 01 2c 25 78 56 34 12 \trstorssp 0x12345678",},
+{{0xf3, 0x0f, 0x01, 0xac, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
+"f3 0f 01 ac c8 78 56 34 12 \trstorssp 0x12345678(%rax,%rcx,8)",},
+{{0xf3, 0x41, 0x0f, 0x01, 0xac, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "",
+"f3 41 0f 01 ac c8 78 56 34 12 \trstorssp 0x12345678(%r8,%rcx,8)",},
+{{0x0f, 0x38, 0xf6, 0x08, }, 4, 0, "", "",
+"0f 38 f6 08 \twrssd %ecx,(%rax)",},
+{{0x41, 0x0f, 0x38, 0xf6, 0x10, }, 5, 0, "", "",
+"41 0f 38 f6 10 \twrssd %edx,(%r8)",},
+{{0x0f, 0x38, 0xf6, 0x14, 0x25, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
+"0f 38 f6 14 25 78 56 34 12 \twrssd %edx,0x12345678",},
+{{0x0f, 0x38, 0xf6, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
+"0f 38 f6 94 c8 78 56 34 12 \twrssd %edx,0x12345678(%rax,%rcx,8)",},
+{{0x41, 0x0f, 0x38, 0xf6, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "",
+"41 0f 38 f6 94 c8 78 56 34 12 \twrssd %edx,0x12345678(%r8,%rcx,8)",},
+{{0x48, 0x0f, 0x38, 0xf6, 0x08, }, 5, 0, "", "",
+"48 0f 38 f6 08 \twrssq %rcx,(%rax)",},
+{{0x49, 0x0f, 0x38, 0xf6, 0x10, }, 5, 0, "", "",
+"49 0f 38 f6 10 \twrssq %rdx,(%r8)",},
+{{0x48, 0x0f, 0x38, 0xf6, 0x14, 0x25, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "",
+"48 0f 38 f6 14 25 78 56 34 12 \twrssq %rdx,0x12345678",},
+{{0x48, 0x0f, 0x38, 0xf6, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "",
+"48 0f 38 f6 94 c8 78 56 34 12 \twrssq %rdx,0x12345678(%rax,%rcx,8)",},
+{{0x49, 0x0f, 0x38, 0xf6, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "",
+"49 0f 38 f6 94 c8 78 56 34 12 \twrssq %rdx,0x12345678(%r8,%rcx,8)",},
+{{0x66, 0x0f, 0x38, 0xf5, 0x08, }, 5, 0, "", "",
+"66 0f 38 f5 08 \twrussd %ecx,(%rax)",},
+{{0x66, 0x41, 0x0f, 0x38, 0xf5, 0x10, }, 6, 0, "", "",
+"66 41 0f 38 f5 10 \twrussd %edx,(%r8)",},
+{{0x66, 0x0f, 0x38, 0xf5, 0x14, 0x25, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "",
+"66 0f 38 f5 14 25 78 56 34 12 \twrussd %edx,0x12345678",},
+{{0x66, 0x0f, 0x38, 0xf5, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "",
+"66 0f 38 f5 94 c8 78 56 34 12 \twrussd %edx,0x12345678(%rax,%rcx,8)",},
+{{0x66, 0x41, 0x0f, 0x38, 0xf5, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"66 41 0f 38 f5 94 c8 78 56 34 12 \twrussd %edx,0x12345678(%r8,%rcx,8)",},
+{{0x66, 0x48, 0x0f, 0x38, 0xf5, 0x08, }, 6, 0, "", "",
+"66 48 0f 38 f5 08 \twrussq %rcx,(%rax)",},
+{{0x66, 0x49, 0x0f, 0x38, 0xf5, 0x10, }, 6, 0, "", "",
+"66 49 0f 38 f5 10 \twrussq %rdx,(%r8)",},
+{{0x66, 0x48, 0x0f, 0x38, 0xf5, 0x14, 0x25, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"66 48 0f 38 f5 14 25 78 56 34 12 \twrussq %rdx,0x12345678",},
+{{0x66, 0x48, 0x0f, 0x38, 0xf5, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"66 48 0f 38 f5 94 c8 78 56 34 12 \twrussq %rdx,0x12345678(%rax,%rcx,8)",},
+{{0x66, 0x49, 0x0f, 0x38, 0xf5, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"66 49 0f 38 f5 94 c8 78 56 34 12 \twrussq %rdx,0x12345678(%r8,%rcx,8)",},
+{{0xf3, 0x0f, 0x01, 0xe8, }, 4, 0, "", "",
+"f3 0f 01 e8 \tsetssbsy ",},
+{{0x0f, 0x01, 0xee, }, 3, 0, "", "",
+"0f 01 ee \trdpkru ",},
+{{0x0f, 0x01, 0xef, }, 3, 0, "", "",
+"0f 01 ef \twrpkru ",},
+{{0xf3, 0x0f, 0xae, 0x30, }, 4, 0, "", "",
+"f3 0f ae 30 \tclrssbsy (%rax)",},
+{{0xf3, 0x41, 0x0f, 0xae, 0x30, }, 5, 0, "", "",
+"f3 41 0f ae 30 \tclrssbsy (%r8)",},
+{{0xf3, 0x0f, 0xae, 0x34, 0x25, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
+"f3 0f ae 34 25 78 56 34 12 \tclrssbsy 0x12345678",},
+{{0xf3, 0x0f, 0xae, 0xb4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
+"f3 0f ae b4 c8 78 56 34 12 \tclrssbsy 0x12345678(%rax,%rcx,8)",},
+{{0xf3, 0x41, 0x0f, 0xae, 0xb4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "",
+"f3 41 0f ae b4 c8 78 56 34 12 \tclrssbsy 0x12345678(%r8,%rcx,8)",},
+{{0xf3, 0x0f, 0x1e, 0xfb, }, 4, 0, "", "",
+"f3 0f 1e fb \tendbr32 ",},
+{{0xf3, 0x0f, 0x1e, 0xfa, }, 4, 0, "", "",
+"f3 0f 1e fa \tendbr64 ",},
+{{0xff, 0xd0, }, 2, 0, "call", "indirect",
+"ff d0 \tcallq *%rax",},
+{{0xff, 0x10, }, 2, 0, "call", "indirect",
+"ff 10 \tcallq *(%rax)",},
+{{0x41, 0xff, 0x10, }, 3, 0, "call", "indirect",
+"41 ff 10 \tcallq *(%r8)",},
+{{0xff, 0x14, 0x25, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "call", "indirect",
+"ff 14 25 78 56 34 12 \tcallq *0x12345678",},
+{{0xff, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "call", "indirect",
+"ff 94 c8 78 56 34 12 \tcallq *0x12345678(%rax,%rcx,8)",},
+{{0x41, 0xff, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "call", "indirect",
+"41 ff 94 c8 78 56 34 12 \tcallq *0x12345678(%r8,%rcx,8)",},
+{{0xf2, 0xff, 0xd0, }, 3, 0, "call", "indirect",
+"f2 ff d0 \tbnd callq *%rax",},
+{{0xf2, 0xff, 0x10, }, 3, 0, "call", "indirect",
+"f2 ff 10 \tbnd callq *(%rax)",},
+{{0xf2, 0x41, 0xff, 0x10, }, 4, 0, "call", "indirect",
+"f2 41 ff 10 \tbnd callq *(%r8)",},
+{{0xf2, 0xff, 0x14, 0x25, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "call", "indirect",
+"f2 ff 14 25 78 56 34 12 \tbnd callq *0x12345678",},
+{{0xf2, 0xff, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "call", "indirect",
+"f2 ff 94 c8 78 56 34 12 \tbnd callq *0x12345678(%rax,%rcx,8)",},
+{{0xf2, 0x41, 0xff, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "call", "indirect",
+"f2 41 ff 94 c8 78 56 34 12 \tbnd callq *0x12345678(%r8,%rcx,8)",},
+{{0x3e, 0xff, 0xd0, }, 3, 0, "call", "indirect",
+"3e ff d0 \tnotrack callq *%rax",},
+{{0x3e, 0xff, 0x10, }, 3, 0, "call", "indirect",
+"3e ff 10 \tnotrack callq *(%rax)",},
+{{0x3e, 0x41, 0xff, 0x10, }, 4, 0, "call", "indirect",
+"3e 41 ff 10 \tnotrack callq *(%r8)",},
+{{0x3e, 0xff, 0x14, 0x25, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "call", "indirect",
+"3e ff 14 25 78 56 34 12 \tnotrack callq *0x12345678",},
+{{0x3e, 0xff, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "call", "indirect",
+"3e ff 94 c8 78 56 34 12 \tnotrack callq *0x12345678(%rax,%rcx,8)",},
+{{0x3e, 0x41, 0xff, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "call", "indirect",
+"3e 41 ff 94 c8 78 56 34 12 \tnotrack callq *0x12345678(%r8,%rcx,8)",},
+{{0x3e, 0xf2, 0xff, 0xd0, }, 4, 0, "call", "indirect",
+"3e f2 ff d0 \tnotrack bnd callq *%rax",},
+{{0x3e, 0xf2, 0xff, 0x10, }, 4, 0, "call", "indirect",
+"3e f2 ff 10 \tnotrack bnd callq *(%rax)",},
+{{0x3e, 0xf2, 0x41, 0xff, 0x10, }, 5, 0, "call", "indirect",
+"3e f2 41 ff 10 \tnotrack bnd callq *(%r8)",},
+{{0x3e, 0xf2, 0xff, 0x14, 0x25, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "call", "indirect",
+"3e f2 ff 14 25 78 56 34 12 \tnotrack bnd callq *0x12345678",},
+{{0x3e, 0xf2, 0xff, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "call", "indirect",
+"3e f2 ff 94 c8 78 56 34 12 \tnotrack bnd callq *0x12345678(%rax,%rcx,8)",},
+{{0x3e, 0xf2, 0x41, 0xff, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "call", "indirect",
+"3e f2 41 ff 94 c8 78 56 34 12 \tnotrack bnd callq *0x12345678(%r8,%rcx,8)",},
+{{0xff, 0xe0, }, 2, 0, "jmp", "indirect",
+"ff e0 \tjmpq *%rax",},
+{{0xff, 0x20, }, 2, 0, "jmp", "indirect",
+"ff 20 \tjmpq *(%rax)",},
+{{0x41, 0xff, 0x20, }, 3, 0, "jmp", "indirect",
+"41 ff 20 \tjmpq *(%r8)",},
+{{0xff, 0x24, 0x25, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "jmp", "indirect",
+"ff 24 25 78 56 34 12 \tjmpq *0x12345678",},
+{{0xff, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "jmp", "indirect",
+"ff a4 c8 78 56 34 12 \tjmpq *0x12345678(%rax,%rcx,8)",},
+{{0x41, 0xff, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "jmp", "indirect",
+"41 ff a4 c8 78 56 34 12 \tjmpq *0x12345678(%r8,%rcx,8)",},
+{{0xf2, 0xff, 0xe0, }, 3, 0, "jmp", "indirect",
+"f2 ff e0 \tbnd jmpq *%rax",},
+{{0xf2, 0xff, 0x20, }, 3, 0, "jmp", "indirect",
+"f2 ff 20 \tbnd jmpq *(%rax)",},
+{{0xf2, 0x41, 0xff, 0x20, }, 4, 0, "jmp", "indirect",
+"f2 41 ff 20 \tbnd jmpq *(%r8)",},
+{{0xf2, 0xff, 0x24, 0x25, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "jmp", "indirect",
+"f2 ff 24 25 78 56 34 12 \tbnd jmpq *0x12345678",},
+{{0xf2, 0xff, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "jmp", "indirect",
+"f2 ff a4 c8 78 56 34 12 \tbnd jmpq *0x12345678(%rax,%rcx,8)",},
+{{0xf2, 0x41, 0xff, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "jmp", "indirect",
+"f2 41 ff a4 c8 78 56 34 12 \tbnd jmpq *0x12345678(%r8,%rcx,8)",},
+{{0x3e, 0xff, 0xe0, }, 3, 0, "jmp", "indirect",
+"3e ff e0 \tnotrack jmpq *%rax",},
+{{0x3e, 0xff, 0x20, }, 3, 0, "jmp", "indirect",
+"3e ff 20 \tnotrack jmpq *(%rax)",},
+{{0x3e, 0x41, 0xff, 0x20, }, 4, 0, "jmp", "indirect",
+"3e 41 ff 20 \tnotrack jmpq *(%r8)",},
+{{0x3e, 0xff, 0x24, 0x25, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "jmp", "indirect",
+"3e ff 24 25 78 56 34 12 \tnotrack jmpq *0x12345678",},
+{{0x3e, 0xff, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "jmp", "indirect",
+"3e ff a4 c8 78 56 34 12 \tnotrack jmpq *0x12345678(%rax,%rcx,8)",},
+{{0x3e, 0x41, 0xff, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "jmp", "indirect",
+"3e 41 ff a4 c8 78 56 34 12 \tnotrack jmpq *0x12345678(%r8,%rcx,8)",},
+{{0x3e, 0xf2, 0xff, 0xe0, }, 4, 0, "jmp", "indirect",
+"3e f2 ff e0 \tnotrack bnd jmpq *%rax",},
+{{0x3e, 0xf2, 0xff, 0x20, }, 4, 0, "jmp", "indirect",
+"3e f2 ff 20 \tnotrack bnd jmpq *(%rax)",},
+{{0x3e, 0xf2, 0x41, 0xff, 0x20, }, 5, 0, "jmp", "indirect",
+"3e f2 41 ff 20 \tnotrack bnd jmpq *(%r8)",},
+{{0x3e, 0xf2, 0xff, 0x24, 0x25, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "jmp", "indirect",
+"3e f2 ff 24 25 78 56 34 12 \tnotrack bnd jmpq *0x12345678",},
+{{0x3e, 0xf2, 0xff, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "jmp", "indirect",
+"3e f2 ff a4 c8 78 56 34 12 \tnotrack bnd jmpq *0x12345678(%rax,%rcx,8)",},
+{{0x3e, 0xf2, 0x41, 0xff, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "jmp", "indirect",
+"3e f2 41 ff a4 c8 78 56 34 12 \tnotrack bnd jmpq *0x12345678(%r8,%rcx,8)",},
{{0x0f, 0x01, 0xcf, }, 3, 0, "", "",
"0f 01 cf \tencls ",},
{{0x0f, 0x01, 0xd7, }, 3, 0, "", "",
diff --git a/tools/perf/arch/x86/tests/insn-x86-dat-src.c b/tools/perf/arch/x86/tests/insn-x86-dat-src.c
index ddbf07c50bb8..c3808e94c46e 100644
--- a/tools/perf/arch/x86/tests/insn-x86-dat-src.c
+++ b/tools/perf/arch/x86/tests/insn-x86-dat-src.c
@@ -1771,6 +1771,145 @@ int main(void)
asm volatile("enqcmds (%eax),%ebx");
asm volatile("enqcmds 0x12345678(%eax),%ecx");
+ /* incsspd/q */
+
+ asm volatile("incsspd %eax");
+ asm volatile("incsspd %r8d");
+ asm volatile("incsspq %rax");
+ asm volatile("incsspq %r8");
+ /* Also check instructions in the same group encoding as incsspd/q */
+ asm volatile("xrstor (%rax)");
+ asm volatile("xrstor (%r8)");
+ asm volatile("xrstor (0x12345678)");
+ asm volatile("xrstor 0x12345678(%rax,%rcx,8)");
+ asm volatile("xrstor 0x12345678(%r8,%rcx,8)");
+ asm volatile("lfence");
+
+ /* rdsspd/q */
+
+ asm volatile("rdsspd %eax");
+ asm volatile("rdsspd %r8d");
+ asm volatile("rdsspq %rax");
+ asm volatile("rdsspq %r8");
+
+ /* saveprevssp */
+
+ asm volatile("saveprevssp");
+
+ /* rstorssp */
+
+ asm volatile("rstorssp (%rax)");
+ asm volatile("rstorssp (%r8)");
+ asm volatile("rstorssp (0x12345678)");
+ asm volatile("rstorssp 0x12345678(%rax,%rcx,8)");
+ asm volatile("rstorssp 0x12345678(%r8,%rcx,8)");
+
+ /* wrssd/q */
+
+ asm volatile("wrssd %ecx,(%rax)");
+ asm volatile("wrssd %edx,(%r8)");
+ asm volatile("wrssd %edx,(0x12345678)");
+ asm volatile("wrssd %edx,0x12345678(%rax,%rcx,8)");
+ asm volatile("wrssd %edx,0x12345678(%r8,%rcx,8)");
+ asm volatile("wrssq %rcx,(%rax)");
+ asm volatile("wrssq %rdx,(%r8)");
+ asm volatile("wrssq %rdx,(0x12345678)");
+ asm volatile("wrssq %rdx,0x12345678(%rax,%rcx,8)");
+ asm volatile("wrssq %rdx,0x12345678(%r8,%rcx,8)");
+
+ /* wrussd/q */
+
+ asm volatile("wrussd %ecx,(%rax)");
+ asm volatile("wrussd %edx,(%r8)");
+ asm volatile("wrussd %edx,(0x12345678)");
+ asm volatile("wrussd %edx,0x12345678(%rax,%rcx,8)");
+ asm volatile("wrussd %edx,0x12345678(%r8,%rcx,8)");
+ asm volatile("wrussq %rcx,(%rax)");
+ asm volatile("wrussq %rdx,(%r8)");
+ asm volatile("wrussq %rdx,(0x12345678)");
+ asm volatile("wrussq %rdx,0x12345678(%rax,%rcx,8)");
+ asm volatile("wrussq %rdx,0x12345678(%r8,%rcx,8)");
+
+ /* setssbsy */
+
+ asm volatile("setssbsy");
+ /* Also check instructions in the same group encoding as setssbsy */
+ asm volatile("rdpkru");
+ asm volatile("wrpkru");
+
+ /* clrssbsy */
+
+ asm volatile("clrssbsy (%rax)");
+ asm volatile("clrssbsy (%r8)");
+ asm volatile("clrssbsy (0x12345678)");
+ asm volatile("clrssbsy 0x12345678(%rax,%rcx,8)");
+ asm volatile("clrssbsy 0x12345678(%r8,%rcx,8)");
+
+ /* endbr32/64 */
+
+ asm volatile("endbr32");
+ asm volatile("endbr64");
+
+ /* call with/without notrack prefix */
+
+ asm volatile("callq *%rax"); /* Expecting: call indirect 0 */
+ asm volatile("callq *(%rax)"); /* Expecting: call indirect 0 */
+ asm volatile("callq *(%r8)"); /* Expecting: call indirect 0 */
+ asm volatile("callq *(0x12345678)"); /* Expecting: call indirect 0 */
+ asm volatile("callq *0x12345678(%rax,%rcx,8)"); /* Expecting: call indirect 0 */
+ asm volatile("callq *0x12345678(%r8,%rcx,8)"); /* Expecting: call indirect 0 */
+
+ asm volatile("bnd callq *%rax"); /* Expecting: call indirect 0 */
+ asm volatile("bnd callq *(%rax)"); /* Expecting: call indirect 0 */
+ asm volatile("bnd callq *(%r8)"); /* Expecting: call indirect 0 */
+ asm volatile("bnd callq *(0x12345678)"); /* Expecting: call indirect 0 */
+ asm volatile("bnd callq *0x12345678(%rax,%rcx,8)"); /* Expecting: call indirect 0 */
+ asm volatile("bnd callq *0x12345678(%r8,%rcx,8)"); /* Expecting: call indirect 0 */
+
+ asm volatile("notrack callq *%rax"); /* Expecting: call indirect 0 */
+ asm volatile("notrack callq *(%rax)"); /* Expecting: call indirect 0 */
+ asm volatile("notrack callq *(%r8)"); /* Expecting: call indirect 0 */
+ asm volatile("notrack callq *(0x12345678)"); /* Expecting: call indirect 0 */
+ asm volatile("notrack callq *0x12345678(%rax,%rcx,8)"); /* Expecting: call indirect 0 */
+ asm volatile("notrack callq *0x12345678(%r8,%rcx,8)"); /* Expecting: call indirect 0 */
+
+ asm volatile("notrack bnd callq *%rax"); /* Expecting: call indirect 0 */
+ asm volatile("notrack bnd callq *(%rax)"); /* Expecting: call indirect 0 */
+ asm volatile("notrack bnd callq *(%r8)"); /* Expecting: call indirect 0 */
+ asm volatile("notrack bnd callq *(0x12345678)"); /* Expecting: call indirect 0 */
+ asm volatile("notrack bnd callq *0x12345678(%rax,%rcx,8)"); /* Expecting: call indirect 0 */
+ asm volatile("notrack bnd callq *0x12345678(%r8,%rcx,8)"); /* Expecting: call indirect 0 */
+
+ /* jmp with/without notrack prefix */
+
+ asm volatile("jmpq *%rax"); /* Expecting: jmp indirect 0 */
+ asm volatile("jmpq *(%rax)"); /* Expecting: jmp indirect 0 */
+ asm volatile("jmpq *(%r8)"); /* Expecting: jmp indirect 0 */
+ asm volatile("jmpq *(0x12345678)"); /* Expecting: jmp indirect 0 */
+ asm volatile("jmpq *0x12345678(%rax,%rcx,8)"); /* Expecting: jmp indirect 0 */
+ asm volatile("jmpq *0x12345678(%r8,%rcx,8)"); /* Expecting: jmp indirect 0 */
+
+ asm volatile("bnd jmpq *%rax"); /* Expecting: jmp indirect 0 */
+ asm volatile("bnd jmpq *(%rax)"); /* Expecting: jmp indirect 0 */
+ asm volatile("bnd jmpq *(%r8)"); /* Expecting: jmp indirect 0 */
+ asm volatile("bnd jmpq *(0x12345678)"); /* Expecting: jmp indirect 0 */
+ asm volatile("bnd jmpq *0x12345678(%rax,%rcx,8)"); /* Expecting: jmp indirect 0 */
+ asm volatile("bnd jmpq *0x12345678(%r8,%rcx,8)"); /* Expecting: jmp indirect 0 */
+
+ asm volatile("notrack jmpq *%rax"); /* Expecting: jmp indirect 0 */
+ asm volatile("notrack jmpq *(%rax)"); /* Expecting: jmp indirect 0 */
+ asm volatile("notrack jmpq *(%r8)"); /* Expecting: jmp indirect 0 */
+ asm volatile("notrack jmpq *(0x12345678)"); /* Expecting: jmp indirect 0 */
+ asm volatile("notrack jmpq *0x12345678(%rax,%rcx,8)"); /* Expecting: jmp indirect 0 */
+ asm volatile("notrack jmpq *0x12345678(%r8,%rcx,8)"); /* Expecting: jmp indirect 0 */
+
+ asm volatile("notrack bnd jmpq *%rax"); /* Expecting: jmp indirect 0 */
+ asm volatile("notrack bnd jmpq *(%rax)"); /* Expecting: jmp indirect 0 */
+ asm volatile("notrack bnd jmpq *(%r8)"); /* Expecting: jmp indirect 0 */
+ asm volatile("notrack bnd jmpq *(0x12345678)"); /* Expecting: jmp indirect 0 */
+ asm volatile("notrack bnd jmpq *0x12345678(%rax,%rcx,8)"); /* Expecting: jmp indirect 0 */
+ asm volatile("notrack bnd jmpq *0x12345678(%r8,%rcx,8)"); /* Expecting: jmp indirect 0 */
+
#else /* #ifdef __x86_64__ */
/* bound r32, mem (same op code as EVEX prefix) */
@@ -3434,6 +3573,103 @@ int main(void)
asm volatile("enqcmds (%si),%bx");
asm volatile("enqcmds 0x1234(%si),%cx");
+ /* incsspd */
+
+ asm volatile("incsspd %eax");
+ /* Also check instructions in the same group encoding as incsspd */
+ asm volatile("xrstor (%eax)");
+ asm volatile("xrstor (0x12345678)");
+ asm volatile("xrstor 0x12345678(%eax,%ecx,8)");
+ asm volatile("lfence");
+
+ /* rdsspd */
+
+ asm volatile("rdsspd %eax");
+
+ /* saveprevssp */
+
+ asm volatile("saveprevssp");
+
+ /* rstorssp */
+
+ asm volatile("rstorssp (%eax)");
+ asm volatile("rstorssp (0x12345678)");
+ asm volatile("rstorssp 0x12345678(%eax,%ecx,8)");
+
+ /* wrssd */
+
+ asm volatile("wrssd %ecx,(%eax)");
+ asm volatile("wrssd %edx,(0x12345678)");
+ asm volatile("wrssd %edx,0x12345678(%eax,%ecx,8)");
+
+ /* wrussd */
+
+ asm volatile("wrussd %ecx,(%eax)");
+ asm volatile("wrussd %edx,(0x12345678)");
+ asm volatile("wrussd %edx,0x12345678(%eax,%ecx,8)");
+
+ /* setssbsy */
+
+ asm volatile("setssbsy");
+ /* Also check instructions in the same group encoding as setssbsy */
+ asm volatile("rdpkru");
+ asm volatile("wrpkru");
+
+ /* clrssbsy */
+
+ asm volatile("clrssbsy (%eax)");
+ asm volatile("clrssbsy (0x12345678)");
+ asm volatile("clrssbsy 0x12345678(%eax,%ecx,8)");
+
+ /* endbr32/64 */
+
+ asm volatile("endbr32");
+ asm volatile("endbr64");
+
+ /* call with/without notrack prefix */
+
+ asm volatile("call *%eax"); /* Expecting: call indirect 0 */
+ asm volatile("call *(%eax)"); /* Expecting: call indirect 0 */
+ asm volatile("call *(0x12345678)"); /* Expecting: call indirect 0 */
+ asm volatile("call *0x12345678(%eax,%ecx,8)"); /* Expecting: call indirect 0 */
+
+ asm volatile("bnd call *%eax"); /* Expecting: call indirect 0 */
+ asm volatile("bnd call *(%eax)"); /* Expecting: call indirect 0 */
+ asm volatile("bnd call *(0x12345678)"); /* Expecting: call indirect 0 */
+ asm volatile("bnd call *0x12345678(%eax,%ecx,8)"); /* Expecting: call indirect 0 */
+
+ asm volatile("notrack call *%eax"); /* Expecting: call indirect 0 */
+ asm volatile("notrack call *(%eax)"); /* Expecting: call indirect 0 */
+ asm volatile("notrack call *(0x12345678)"); /* Expecting: call indirect 0 */
+ asm volatile("notrack call *0x12345678(%eax,%ecx,8)"); /* Expecting: call indirect 0 */
+
+ asm volatile("notrack bnd call *%eax"); /* Expecting: call indirect 0 */
+ asm volatile("notrack bnd call *(%eax)"); /* Expecting: call indirect 0 */
+ asm volatile("notrack bnd call *(0x12345678)"); /* Expecting: call indirect 0 */
+ asm volatile("notrack bnd call *0x12345678(%eax,%ecx,8)"); /* Expecting: call indirect 0 */
+
+ /* jmp with/without notrack prefix */
+
+ asm volatile("jmp *%eax"); /* Expecting: jmp indirect 0 */
+ asm volatile("jmp *(%eax)"); /* Expecting: jmp indirect 0 */
+ asm volatile("jmp *(0x12345678)"); /* Expecting: jmp indirect 0 */
+ asm volatile("jmp *0x12345678(%eax,%ecx,8)"); /* Expecting: jmp indirect 0 */
+
+ asm volatile("bnd jmp *%eax"); /* Expecting: jmp indirect 0 */
+ asm volatile("bnd jmp *(%eax)"); /* Expecting: jmp indirect 0 */
+ asm volatile("bnd jmp *(0x12345678)"); /* Expecting: jmp indirect 0 */
+ asm volatile("bnd jmp *0x12345678(%eax,%ecx,8)"); /* Expecting: jmp indirect 0 */
+
+ asm volatile("notrack jmp *%eax"); /* Expecting: jmp indirect 0 */
+ asm volatile("notrack jmp *(%eax)"); /* Expecting: jmp indirect 0 */
+ asm volatile("notrack jmp *(0x12345678)"); /* Expecting: jmp indirect 0 */
+ asm volatile("notrack jmp *0x12345678(%eax,%ecx,8)"); /* Expecting: jmp indirect 0 */
+
+ asm volatile("notrack bnd jmp *%eax"); /* Expecting: jmp indirect 0 */
+ asm volatile("notrack bnd jmp *(%eax)"); /* Expecting: jmp indirect 0 */
+ asm volatile("notrack bnd jmp *(0x12345678)"); /* Expecting: jmp indirect 0 */
+ asm volatile("notrack bnd jmp *0x12345678(%eax,%ecx,8)"); /* Expecting: jmp indirect 0 */
+
#endif /* #ifndef __x86_64__ */
/* SGX */
diff --git a/tools/perf/arch/x86/util/auxtrace.c b/tools/perf/arch/x86/util/auxtrace.c
index 7abc9fd4cbec..3da506e13f49 100644
--- a/tools/perf/arch/x86/util/auxtrace.c
+++ b/tools/perf/arch/x86/util/auxtrace.c
@@ -7,13 +7,13 @@
#include <errno.h>
#include <stdbool.h>
-#include "../../util/header.h"
-#include "../../util/debug.h"
-#include "../../util/pmu.h"
-#include "../../util/auxtrace.h"
-#include "../../util/intel-pt.h"
-#include "../../util/intel-bts.h"
-#include "../../util/evlist.h"
+#include "../../../util/header.h"
+#include "../../../util/debug.h"
+#include "../../../util/pmu.h"
+#include "../../../util/auxtrace.h"
+#include "../../../util/intel-pt.h"
+#include "../../../util/intel-bts.h"
+#include "../../../util/evlist.h"
static
struct auxtrace_record *auxtrace_record__init_intel(struct evlist *evlist,
diff --git a/tools/perf/arch/x86/util/event.c b/tools/perf/arch/x86/util/event.c
index ac45015cc6ba..047dc00eafa6 100644
--- a/tools/perf/arch/x86/util/event.c
+++ b/tools/perf/arch/x86/util/event.c
@@ -3,12 +3,12 @@
#include <linux/string.h>
#include <linux/zalloc.h>
-#include "../../util/event.h"
-#include "../../util/synthetic-events.h"
-#include "../../util/machine.h"
-#include "../../util/tool.h"
-#include "../../util/map.h"
-#include "../../util/debug.h"
+#include "../../../util/event.h"
+#include "../../../util/synthetic-events.h"
+#include "../../../util/machine.h"
+#include "../../../util/tool.h"
+#include "../../../util/map.h"
+#include "../../../util/debug.h"
#if defined(__x86_64__)
diff --git a/tools/perf/arch/x86/util/header.c b/tools/perf/arch/x86/util/header.c
index aa6deb463bf3..578c8c568ffd 100644
--- a/tools/perf/arch/x86/util/header.c
+++ b/tools/perf/arch/x86/util/header.c
@@ -7,8 +7,8 @@
#include <string.h>
#include <regex.h>
-#include "../../util/debug.h"
-#include "../../util/header.h"
+#include "../../../util/debug.h"
+#include "../../../util/header.h"
static inline void
cpuid(unsigned int op, unsigned int *a, unsigned int *b, unsigned int *c,
diff --git a/tools/perf/arch/x86/util/intel-bts.c b/tools/perf/arch/x86/util/intel-bts.c
index 27d9e214d068..09f93800bffd 100644
--- a/tools/perf/arch/x86/util/intel-bts.c
+++ b/tools/perf/arch/x86/util/intel-bts.c
@@ -11,18 +11,18 @@
#include <linux/log2.h>
#include <linux/zalloc.h>
-#include "../../util/cpumap.h"
-#include "../../util/event.h"
-#include "../../util/evsel.h"
-#include "../../util/evlist.h"
-#include "../../util/mmap.h"
-#include "../../util/session.h"
-#include "../../util/pmu.h"
-#include "../../util/debug.h"
-#include "../../util/record.h"
-#include "../../util/tsc.h"
-#include "../../util/auxtrace.h"
-#include "../../util/intel-bts.h"
+#include "../../../util/cpumap.h"
+#include "../../../util/event.h"
+#include "../../../util/evsel.h"
+#include "../../../util/evlist.h"
+#include "../../../util/mmap.h"
+#include "../../../util/session.h"
+#include "../../../util/pmu.h"
+#include "../../../util/debug.h"
+#include "../../../util/record.h"
+#include "../../../util/tsc.h"
+#include "../../../util/auxtrace.h"
+#include "../../../util/intel-bts.h"
#include <internal/lib.h> // page_size
#define KiB(x) ((x) * 1024)
@@ -413,20 +413,6 @@ out_err:
return err;
}
-static int intel_bts_read_finish(struct auxtrace_record *itr, int idx)
-{
- struct intel_bts_recording *btsr =
- container_of(itr, struct intel_bts_recording, itr);
- struct evsel *evsel;
-
- evlist__for_each_entry(btsr->evlist, evsel) {
- if (evsel->core.attr.type == btsr->intel_bts_pmu->type)
- return perf_evlist__enable_event_idx(btsr->evlist,
- evsel, idx);
- }
- return -EINVAL;
-}
-
struct auxtrace_record *intel_bts_recording_init(int *err)
{
struct perf_pmu *intel_bts_pmu = perf_pmu__find(INTEL_BTS_PMU_NAME);
@@ -447,6 +433,7 @@ struct auxtrace_record *intel_bts_recording_init(int *err)
}
btsr->intel_bts_pmu = intel_bts_pmu;
+ btsr->itr.pmu = intel_bts_pmu;
btsr->itr.recording_options = intel_bts_recording_options;
btsr->itr.info_priv_size = intel_bts_info_priv_size;
btsr->itr.info_fill = intel_bts_info_fill;
@@ -456,7 +443,7 @@ struct auxtrace_record *intel_bts_recording_init(int *err)
btsr->itr.find_snapshot = intel_bts_find_snapshot;
btsr->itr.parse_snapshot_options = intel_bts_parse_snapshot_options;
btsr->itr.reference = intel_bts_reference;
- btsr->itr.read_finish = intel_bts_read_finish;
+ btsr->itr.read_finish = auxtrace_record__read_finish;
btsr->itr.alignment = sizeof(struct branch);
return &btsr->itr;
}
diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
index 20df442fdf36..1643aed8c4c8 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -13,23 +13,23 @@
#include <linux/zalloc.h>
#include <cpuid.h>
-#include "../../util/session.h"
-#include "../../util/event.h"
-#include "../../util/evlist.h"
-#include "../../util/evsel.h"
-#include "../../util/evsel_config.h"
-#include "../../util/cpumap.h"
-#include "../../util/mmap.h"
+#include "../../../util/session.h"
+#include "../../../util/event.h"
+#include "../../../util/evlist.h"
+#include "../../../util/evsel.h"
+#include "../../../util/evsel_config.h"
+#include "../../../util/cpumap.h"
+#include "../../../util/mmap.h"
#include <subcmd/parse-options.h>
-#include "../../util/parse-events.h"
-#include "../../util/pmu.h"
-#include "../../util/debug.h"
-#include "../../util/auxtrace.h"
-#include "../../util/record.h"
-#include "../../util/target.h"
-#include "../../util/tsc.h"
+#include "../../../util/parse-events.h"
+#include "../../../util/pmu.h"
+#include "../../../util/debug.h"
+#include "../../../util/auxtrace.h"
+#include "../../../util/record.h"
+#include "../../../util/target.h"
+#include "../../../util/tsc.h"
#include <internal/lib.h> // page_size
-#include "../../util/intel-pt.h"
+#include "../../../util/intel-pt.h"
#define KiB(x) ((x) * 1024)
#define MiB(x) ((x) * 1024 * 1024)
@@ -1166,20 +1166,6 @@ static u64 intel_pt_reference(struct auxtrace_record *itr __maybe_unused)
return rdtsc();
}
-static int intel_pt_read_finish(struct auxtrace_record *itr, int idx)
-{
- struct intel_pt_recording *ptr =
- container_of(itr, struct intel_pt_recording, itr);
- struct evsel *evsel;
-
- evlist__for_each_entry(ptr->evlist, evsel) {
- if (evsel->core.attr.type == ptr->intel_pt_pmu->type)
- return perf_evlist__enable_event_idx(ptr->evlist, evsel,
- idx);
- }
- return -EINVAL;
-}
-
struct auxtrace_record *intel_pt_recording_init(int *err)
{
struct perf_pmu *intel_pt_pmu = perf_pmu__find(INTEL_PT_PMU_NAME);
@@ -1200,6 +1186,7 @@ struct auxtrace_record *intel_pt_recording_init(int *err)
}
ptr->intel_pt_pmu = intel_pt_pmu;
+ ptr->itr.pmu = intel_pt_pmu;
ptr->itr.recording_options = intel_pt_recording_options;
ptr->itr.info_priv_size = intel_pt_info_priv_size;
ptr->itr.info_fill = intel_pt_info_fill;
@@ -1209,7 +1196,7 @@ struct auxtrace_record *intel_pt_recording_init(int *err)
ptr->itr.find_snapshot = intel_pt_find_snapshot;
ptr->itr.parse_snapshot_options = intel_pt_parse_snapshot_options;
ptr->itr.reference = intel_pt_reference;
- ptr->itr.read_finish = intel_pt_read_finish;
+ ptr->itr.read_finish = auxtrace_record__read_finish;
/*
* Decoding starts at a PSB packet. Minimum PSB period is 2K so 4K
* should give at least 1 PSB per sample.
diff --git a/tools/perf/arch/x86/util/machine.c b/tools/perf/arch/x86/util/machine.c
index e17e080e76f4..31679c35d493 100644
--- a/tools/perf/arch/x86/util/machine.c
+++ b/tools/perf/arch/x86/util/machine.c
@@ -5,9 +5,9 @@
#include <stdlib.h>
#include <internal/lib.h> // page_size
-#include "../../util/machine.h"
-#include "../../util/map.h"
-#include "../../util/symbol.h"
+#include "../../../util/machine.h"
+#include "../../../util/map.h"
+#include "../../../util/symbol.h"
#include <linux/ctype.h>
#include <symbol/kallsyms.h>
diff --git a/tools/perf/arch/x86/util/perf_regs.c b/tools/perf/arch/x86/util/perf_regs.c
index c218b83e063b..fca81b39b09f 100644
--- a/tools/perf/arch/x86/util/perf_regs.c
+++ b/tools/perf/arch/x86/util/perf_regs.c
@@ -5,10 +5,10 @@
#include <linux/kernel.h>
#include <linux/zalloc.h>
-#include "../../perf-sys.h"
-#include "../../util/perf_regs.h"
-#include "../../util/debug.h"
-#include "../../util/event.h"
+#include "../../../perf-sys.h"
+#include "../../../util/perf_regs.h"
+#include "../../../util/debug.h"
+#include "../../../util/event.h"
const struct sample_reg sample_reg_masks[] = {
SMPL_REG(AX, PERF_REG_X86_AX),
diff --git a/tools/perf/arch/x86/util/pmu.c b/tools/perf/arch/x86/util/pmu.c
index e33ef5bc31c5..d48d608517fd 100644
--- a/tools/perf/arch/x86/util/pmu.c
+++ b/tools/perf/arch/x86/util/pmu.c
@@ -4,9 +4,9 @@
#include <linux/stddef.h>
#include <linux/perf_event.h>
-#include "../../util/intel-pt.h"
-#include "../../util/intel-bts.h"
-#include "../../util/pmu.h"
+#include "../../../util/intel-pt.h"
+#include "../../../util/intel-bts.h"
+#include "../../../util/pmu.h"
struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused)
{
diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h
index fddb3ced9db6..4aa6de1aa67d 100644
--- a/tools/perf/bench/bench.h
+++ b/tools/perf/bench/bench.h
@@ -2,6 +2,10 @@
#ifndef BENCH_H
#define BENCH_H
+#include <sys/time.h>
+
+extern struct timeval bench__start, bench__end, bench__runtime;
+
/*
* The madvise transparent hugepage constants were added in glibc
* 2.13. For compatibility with older versions of glibc, define these
diff --git a/tools/perf/bench/epoll-ctl.c b/tools/perf/bench/epoll-ctl.c
index bb617e568841..cadc18d42aa4 100644
--- a/tools/perf/bench/epoll-ctl.c
+++ b/tools/perf/bench/epoll-ctl.c
@@ -35,7 +35,6 @@
static unsigned int nthreads = 0;
static unsigned int nsecs = 8;
-struct timeval start, end, runtime;
static bool done, __verbose, randomize;
/*
@@ -94,8 +93,8 @@ static void toggle_done(int sig __maybe_unused,
{
/* inform all threads that we're done for the day */
done = true;
- gettimeofday(&end, NULL);
- timersub(&end, &start, &runtime);
+ gettimeofday(&bench__end, NULL);
+ timersub(&bench__end, &bench__start, &bench__runtime);
}
static void nest_epollfd(void)
@@ -313,6 +312,7 @@ int bench_epoll_ctl(int argc, const char **argv)
exit(EXIT_FAILURE);
}
+ memset(&act, 0, sizeof(act));
sigfillset(&act.sa_mask);
act.sa_sigaction = toggle_done;
sigaction(SIGINT, &act, NULL);
@@ -361,7 +361,7 @@ int bench_epoll_ctl(int argc, const char **argv)
threads_starting = nthreads;
- gettimeofday(&start, NULL);
+ gettimeofday(&bench__start, NULL);
do_threads(worker, cpu);
diff --git a/tools/perf/bench/epoll-wait.c b/tools/perf/bench/epoll-wait.c
index 7af694437f4e..f938c585d512 100644
--- a/tools/perf/bench/epoll-wait.c
+++ b/tools/perf/bench/epoll-wait.c
@@ -90,7 +90,6 @@
static unsigned int nthreads = 0;
static unsigned int nsecs = 8;
-struct timeval start, end, runtime;
static bool wdone, done, __verbose, randomize, nonblocking;
/*
@@ -276,8 +275,8 @@ static void toggle_done(int sig __maybe_unused,
{
/* inform all threads that we're done for the day */
done = true;
- gettimeofday(&end, NULL);
- timersub(&end, &start, &runtime);
+ gettimeofday(&bench__end, NULL);
+ timersub(&bench__end, &bench__start, &bench__runtime);
}
static void print_summary(void)
@@ -287,7 +286,7 @@ static void print_summary(void)
printf("\nAveraged %ld operations/sec (+- %.2f%%), total secs = %d\n",
avg, rel_stddev_stats(stddev, avg),
- (int) runtime.tv_sec);
+ (int)bench__runtime.tv_sec);
}
static int do_threads(struct worker *worker, struct perf_cpu_map *cpu)
@@ -427,6 +426,7 @@ int bench_epoll_wait(int argc, const char **argv)
exit(EXIT_FAILURE);
}
+ memset(&act, 0, sizeof(act));
sigfillset(&act.sa_mask);
act.sa_sigaction = toggle_done;
sigaction(SIGINT, &act, NULL);
@@ -479,7 +479,7 @@ int bench_epoll_wait(int argc, const char **argv)
threads_starting = nthreads;
- gettimeofday(&start, NULL);
+ gettimeofday(&bench__start, NULL);
do_threads(worker, cpu);
@@ -519,7 +519,7 @@ int bench_epoll_wait(int argc, const char **argv)
qsort(worker, nthreads, sizeof(struct worker), cmpworker);
for (i = 0; i < nthreads; i++) {
- unsigned long t = worker[i].ops/runtime.tv_sec;
+ unsigned long t = worker[i].ops / bench__runtime.tv_sec;
update_stats(&throughput_stats, t);
diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c
index 8ba0c3330a9a..65eebe06c04d 100644
--- a/tools/perf/bench/futex-hash.c
+++ b/tools/perf/bench/futex-hash.c
@@ -37,7 +37,7 @@ static unsigned int nfutexes = 1024;
static bool fshared = false, done = false, silent = false;
static int futex_flag = 0;
-struct timeval start, end, runtime;
+struct timeval bench__start, bench__end, bench__runtime;
static pthread_mutex_t thread_lock;
static unsigned int threads_starting;
static struct stats throughput_stats;
@@ -103,8 +103,8 @@ static void toggle_done(int sig __maybe_unused,
{
/* inform all threads that we're done for the day */
done = true;
- gettimeofday(&end, NULL);
- timersub(&end, &start, &runtime);
+ gettimeofday(&bench__end, NULL);
+ timersub(&bench__end, &bench__start, &bench__runtime);
}
static void print_summary(void)
@@ -114,7 +114,7 @@ static void print_summary(void)
printf("%sAveraged %ld operations/sec (+- %.2f%%), total secs = %d\n",
!silent ? "\n" : "", avg, rel_stddev_stats(stddev, avg),
- (int) runtime.tv_sec);
+ (int)bench__runtime.tv_sec);
}
int bench_futex_hash(int argc, const char **argv)
@@ -137,6 +137,7 @@ int bench_futex_hash(int argc, const char **argv)
if (!cpu)
goto errmem;
+ memset(&act, 0, sizeof(act));
sigfillset(&act.sa_mask);
act.sa_sigaction = toggle_done;
sigaction(SIGINT, &act, NULL);
@@ -161,7 +162,7 @@ int bench_futex_hash(int argc, const char **argv)
threads_starting = nthreads;
pthread_attr_init(&thread_attr);
- gettimeofday(&start, NULL);
+ gettimeofday(&bench__start, NULL);
for (i = 0; i < nthreads; i++) {
worker[i].tid = i;
worker[i].futex = calloc(nfutexes, sizeof(*worker[i].futex));
@@ -204,7 +205,7 @@ int bench_futex_hash(int argc, const char **argv)
pthread_mutex_destroy(&thread_lock);
for (i = 0; i < nthreads; i++) {
- unsigned long t = worker[i].ops/runtime.tv_sec;
+ unsigned long t = worker[i].ops / bench__runtime.tv_sec;
update_stats(&throughput_stats, t);
if (!silent) {
if (nfutexes == 1)
diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c
index d0cae8125423..89fd8f325f38 100644
--- a/tools/perf/bench/futex-lock-pi.c
+++ b/tools/perf/bench/futex-lock-pi.c
@@ -37,7 +37,6 @@ static bool silent = false, multi = false;
static bool done = false, fshared = false;
static unsigned int nthreads = 0;
static int futex_flag = 0;
-struct timeval start, end, runtime;
static pthread_mutex_t thread_lock;
static unsigned int threads_starting;
static struct stats throughput_stats;
@@ -64,7 +63,7 @@ static void print_summary(void)
printf("%sAveraged %ld operations/sec (+- %.2f%%), total secs = %d\n",
!silent ? "\n" : "", avg, rel_stddev_stats(stddev, avg),
- (int) runtime.tv_sec);
+ (int)bench__runtime.tv_sec);
}
static void toggle_done(int sig __maybe_unused,
@@ -73,8 +72,8 @@ static void toggle_done(int sig __maybe_unused,
{
/* inform all threads that we're done for the day */
done = true;
- gettimeofday(&end, NULL);
- timersub(&end, &start, &runtime);
+ gettimeofday(&bench__end, NULL);
+ timersub(&bench__end, &bench__start, &bench__runtime);
}
static void *workerfn(void *arg)
@@ -161,6 +160,7 @@ int bench_futex_lock_pi(int argc, const char **argv)
if (!cpu)
err(EXIT_FAILURE, "calloc");
+ memset(&act, 0, sizeof(act));
sigfillset(&act.sa_mask);
act.sa_sigaction = toggle_done;
sigaction(SIGINT, &act, NULL);
@@ -185,7 +185,7 @@ int bench_futex_lock_pi(int argc, const char **argv)
threads_starting = nthreads;
pthread_attr_init(&thread_attr);
- gettimeofday(&start, NULL);
+ gettimeofday(&bench__start, NULL);
create_threads(worker, thread_attr, cpu);
pthread_attr_destroy(&thread_attr);
@@ -211,7 +211,7 @@ int bench_futex_lock_pi(int argc, const char **argv)
pthread_mutex_destroy(&thread_lock);
for (i = 0; i < nthreads; i++) {
- unsigned long t = worker[i].ops/runtime.tv_sec;
+ unsigned long t = worker[i].ops / bench__runtime.tv_sec;
update_stats(&throughput_stats, t);
if (!silent)
diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c
index a00a6891447a..7a15c2e61022 100644
--- a/tools/perf/bench/futex-requeue.c
+++ b/tools/perf/bench/futex-requeue.c
@@ -128,6 +128,7 @@ int bench_futex_requeue(int argc, const char **argv)
if (!cpu)
err(EXIT_FAILURE, "cpu_map__new");
+ memset(&act, 0, sizeof(act));
sigfillset(&act.sa_mask);
act.sa_sigaction = toggle_done;
sigaction(SIGINT, &act, NULL);
diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c
index a053cf2b7039..cd2b81a845ac 100644
--- a/tools/perf/bench/futex-wake-parallel.c
+++ b/tools/perf/bench/futex-wake-parallel.c
@@ -234,6 +234,7 @@ int bench_futex_wake_parallel(int argc, const char **argv)
exit(EXIT_FAILURE);
}
+ memset(&act, 0, sizeof(act));
sigfillset(&act.sa_mask);
act.sa_sigaction = toggle_done;
sigaction(SIGINT, &act, NULL);
diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c
index df810096abfe..2dfcef3e371e 100644
--- a/tools/perf/bench/futex-wake.c
+++ b/tools/perf/bench/futex-wake.c
@@ -43,7 +43,7 @@ static bool done = false, silent = false, fshared = false;
static pthread_mutex_t thread_lock;
static pthread_cond_t thread_parent, thread_worker;
static struct stats waketime_stats, wakeup_stats;
-static unsigned int ncpus, threads_starting, nthreads = 0;
+static unsigned int threads_starting, nthreads = 0;
static int futex_flag = 0;
static const struct option options[] = {
@@ -136,12 +136,13 @@ int bench_futex_wake(int argc, const char **argv)
if (!cpu)
err(EXIT_FAILURE, "calloc");
+ memset(&act, 0, sizeof(act));
sigfillset(&act.sa_mask);
act.sa_sigaction = toggle_done;
sigaction(SIGINT, &act, NULL);
if (!nthreads)
- nthreads = ncpus;
+ nthreads = cpu->nr;
worker = calloc(nthreads, sizeof(*worker));
if (!worker)
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index ff61795a4d13..6c0a0412502e 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -566,6 +566,8 @@ int cmd_annotate(int argc, const char **argv)
if (ret < 0)
return ret;
+ annotation_config__init(&annotate.opts);
+
argc = parse_options(argc, argv, options, annotate_usage, 0);
if (argc) {
/*
@@ -605,8 +607,6 @@ int cmd_annotate(int argc, const char **argv)
if (ret < 0)
goto out_delete;
- annotation_config__init();
-
symbol_conf.try_vmlinux_path = true;
ret = symbol__init(&annotate.session->header.env);
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index f8b6ae557d8b..5e697cd2224a 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -572,29 +572,12 @@ static void init_block_hist(struct block_hist *bh)
bh->valid = true;
}
-static int block_pair_cmp(struct hist_entry *a, struct hist_entry *b)
-{
- struct block_info *bi_a = a->block_info;
- struct block_info *bi_b = b->block_info;
- int cmp;
-
- if (!bi_a->sym || !bi_b->sym)
- return -1;
-
- cmp = strcmp(bi_a->sym->name, bi_b->sym->name);
-
- if ((!cmp) && (bi_a->start == bi_b->start) && (bi_a->end == bi_b->end))
- return 0;
-
- return -1;
-}
-
static struct hist_entry *get_block_pair(struct hist_entry *he,
struct hists *hists_pair)
{
struct rb_root_cached *root = hists_pair->entries_in;
struct rb_node *next = rb_first_cached(root);
- int cmp;
+ int64_t cmp;
while (next != NULL) {
struct hist_entry *he_pair = rb_entry(next, struct hist_entry,
@@ -602,7 +585,7 @@ static struct hist_entry *get_block_pair(struct hist_entry *he,
next = rb_next(&he_pair->rb_node_in);
- cmp = block_pair_cmp(he_pair, he);
+ cmp = __block_info__cmp(he_pair, he);
if (!cmp)
return he_pair;
}
@@ -1312,7 +1295,8 @@ static int cycles_printf(struct hist_entry *he, struct hist_entry *pair,
end_line = map__srcline(he->ms.map, bi->sym->start + bi->end,
he->ms.sym);
- if ((start_line != SRCLINE_UNKNOWN) && (end_line != SRCLINE_UNKNOWN)) {
+ if ((strncmp(start_line, SRCLINE_UNKNOWN, strlen(SRCLINE_UNKNOWN)) != 0) &&
+ (strncmp(end_line, SRCLINE_UNKNOWN, strlen(SRCLINE_UNKNOWN)) != 0)) {
scnprintf(buf, sizeof(buf), "[%s -> %s] %4ld",
start_line, end_line, block_he->diff.cycles);
} else {
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index 26bc5923e6b5..70548df2abb9 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -449,7 +449,8 @@ static int perf_del_probe_events(struct strfilter *filter)
ret = probe_file__del_strlist(kfd, klist);
if (ret < 0)
goto error;
- }
+ } else if (ret == -ENOMEM)
+ goto error;
ret2 = probe_file__get_events(ufd, filter, ulist);
if (ret2 == 0) {
@@ -459,7 +460,8 @@ static int perf_del_probe_events(struct strfilter *filter)
ret2 = probe_file__del_strlist(ufd, ulist);
if (ret2 < 0)
goto error;
- }
+ } else if (ret2 == -ENOMEM)
+ goto error;
if (ret == -ENOENT && ret2 == -ENOENT)
pr_warning("\"%s\" does not hit any event.\n", str);
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 9483b3f0cae3..5f4045df76f4 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -104,6 +104,7 @@ struct report {
bool symbol_ipc;
bool total_cycles_mode;
struct block_report *block_reports;
+ int nr_block_reports;
};
static int report__config(const char *var, const char *value, void *cb)
@@ -185,24 +186,23 @@ static int hist_iter__branch_callback(struct hist_entry_iter *iter,
{
struct hist_entry *he = iter->he;
struct report *rep = arg;
- struct branch_info *bi;
+ struct branch_info *bi = he->branch_info;
struct perf_sample *sample = iter->sample;
struct evsel *evsel = iter->evsel;
int err;
+ branch_type_count(&rep->brtype_stat, &bi->flags,
+ bi->from.addr, bi->to.addr);
+
if (!ui__has_annotation() && !rep->symbol_ipc)
return 0;
- bi = he->branch_info;
err = addr_map_symbol__inc_samples(&bi->from, sample, evsel);
if (err)
goto out;
err = addr_map_symbol__inc_samples(&bi->to, sample, evsel);
- branch_type_count(&rep->brtype_stat, &bi->flags,
- bi->from.addr, bi->to.addr);
-
out:
return err;
}
@@ -966,8 +966,19 @@ static int __cmd_report(struct report *rep)
report__output_resort(rep);
if (rep->total_cycles_mode) {
+ int block_hpps[6] = {
+ PERF_HPP_REPORT__BLOCK_TOTAL_CYCLES_PCT,
+ PERF_HPP_REPORT__BLOCK_LBR_CYCLES,
+ PERF_HPP_REPORT__BLOCK_CYCLES_PCT,
+ PERF_HPP_REPORT__BLOCK_AVG_CYCLES,
+ PERF_HPP_REPORT__BLOCK_RANGE,
+ PERF_HPP_REPORT__BLOCK_DSO,
+ };
+
rep->block_reports = block_info__create_report(session->evlist,
- rep->total_cycles);
+ rep->total_cycles,
+ block_hpps, 6,
+ &rep->nr_block_reports);
if (!rep->block_reports)
return -1;
}
@@ -1507,7 +1518,7 @@ repeat:
symbol_conf.priv_size += sizeof(u32);
symbol_conf.sort_by_name = true;
}
- annotation_config__init();
+ annotation_config__init(&report.annotation_opts);
}
if (symbol__init(&session->header.env) < 0)
@@ -1551,8 +1562,11 @@ error:
zfree(&report.ptime_range);
}
- if (report.block_reports)
- zfree(&report.block_reports);
+ if (report.block_reports) {
+ block_info__free_report(report.block_reports,
+ report.nr_block_reports);
+ report.block_reports = NULL;
+ }
zstd_fini(&(session->zstd_data));
perf_session__delete(session);
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index e2406b291c1c..656b347f6dd8 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -735,6 +735,7 @@ static int perf_sample__fprintf_brstack(struct perf_sample *sample,
struct perf_event_attr *attr, FILE *fp)
{
struct branch_stack *br = sample->branch_stack;
+ struct branch_entry *entries = perf_sample__branch_entries(sample);
struct addr_location alf, alt;
u64 i, from, to;
int printed = 0;
@@ -743,8 +744,8 @@ static int perf_sample__fprintf_brstack(struct perf_sample *sample,
return 0;
for (i = 0; i < br->nr; i++) {
- from = br->entries[i].from;
- to = br->entries[i].to;
+ from = entries[i].from;
+ to = entries[i].to;
if (PRINT_FIELD(DSO)) {
memset(&alf, 0, sizeof(alf));
@@ -768,10 +769,10 @@ static int perf_sample__fprintf_brstack(struct perf_sample *sample,
}
printed += fprintf(fp, "/%c/%c/%c/%d ",
- mispred_str( br->entries + i),
- br->entries[i].flags.in_tx? 'X' : '-',
- br->entries[i].flags.abort? 'A' : '-',
- br->entries[i].flags.cycles);
+ mispred_str(entries + i),
+ entries[i].flags.in_tx ? 'X' : '-',
+ entries[i].flags.abort ? 'A' : '-',
+ entries[i].flags.cycles);
}
return printed;
@@ -782,6 +783,7 @@ static int perf_sample__fprintf_brstacksym(struct perf_sample *sample,
struct perf_event_attr *attr, FILE *fp)
{
struct branch_stack *br = sample->branch_stack;
+ struct branch_entry *entries = perf_sample__branch_entries(sample);
struct addr_location alf, alt;
u64 i, from, to;
int printed = 0;
@@ -793,8 +795,8 @@ static int perf_sample__fprintf_brstacksym(struct perf_sample *sample,
memset(&alf, 0, sizeof(alf));
memset(&alt, 0, sizeof(alt));
- from = br->entries[i].from;
- to = br->entries[i].to;
+ from = entries[i].from;
+ to = entries[i].to;
thread__find_symbol_fb(thread, sample->cpumode, from, &alf);
thread__find_symbol_fb(thread, sample->cpumode, to, &alt);
@@ -813,10 +815,10 @@ static int perf_sample__fprintf_brstacksym(struct perf_sample *sample,
printed += fprintf(fp, ")");
}
printed += fprintf(fp, "/%c/%c/%c/%d ",
- mispred_str( br->entries + i),
- br->entries[i].flags.in_tx? 'X' : '-',
- br->entries[i].flags.abort? 'A' : '-',
- br->entries[i].flags.cycles);
+ mispred_str(entries + i),
+ entries[i].flags.in_tx ? 'X' : '-',
+ entries[i].flags.abort ? 'A' : '-',
+ entries[i].flags.cycles);
}
return printed;
@@ -827,6 +829,7 @@ static int perf_sample__fprintf_brstackoff(struct perf_sample *sample,
struct perf_event_attr *attr, FILE *fp)
{
struct branch_stack *br = sample->branch_stack;
+ struct branch_entry *entries = perf_sample__branch_entries(sample);
struct addr_location alf, alt;
u64 i, from, to;
int printed = 0;
@@ -838,8 +841,8 @@ static int perf_sample__fprintf_brstackoff(struct perf_sample *sample,
memset(&alf, 0, sizeof(alf));
memset(&alt, 0, sizeof(alt));
- from = br->entries[i].from;
- to = br->entries[i].to;
+ from = entries[i].from;
+ to = entries[i].to;
if (thread__find_map_fb(thread, sample->cpumode, from, &alf) &&
!alf.map->dso->adjust_symbols)
@@ -862,10 +865,10 @@ static int perf_sample__fprintf_brstackoff(struct perf_sample *sample,
printed += fprintf(fp, ")");
}
printed += fprintf(fp, "/%c/%c/%c/%d ",
- mispred_str(br->entries + i),
- br->entries[i].flags.in_tx ? 'X' : '-',
- br->entries[i].flags.abort ? 'A' : '-',
- br->entries[i].flags.cycles);
+ mispred_str(entries + i),
+ entries[i].flags.in_tx ? 'X' : '-',
+ entries[i].flags.abort ? 'A' : '-',
+ entries[i].flags.cycles);
}
return printed;
@@ -1053,6 +1056,7 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
struct machine *machine, FILE *fp)
{
struct branch_stack *br = sample->branch_stack;
+ struct branch_entry *entries = perf_sample__branch_entries(sample);
u64 start, end;
int i, insn, len, nr, ilen, printed = 0;
struct perf_insn x;
@@ -1073,31 +1077,31 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
printed += fprintf(fp, "%c", '\n');
/* Handle first from jump, of which we don't know the entry. */
- len = grab_bb(buffer, br->entries[nr-1].from,
- br->entries[nr-1].from,
+ len = grab_bb(buffer, entries[nr-1].from,
+ entries[nr-1].from,
machine, thread, &x.is64bit, &x.cpumode, false);
if (len > 0) {
- printed += ip__fprintf_sym(br->entries[nr - 1].from, thread,
+ printed += ip__fprintf_sym(entries[nr - 1].from, thread,
x.cpumode, x.cpu, &lastsym, attr, fp);
- printed += ip__fprintf_jump(br->entries[nr - 1].from, &br->entries[nr - 1],
+ printed += ip__fprintf_jump(entries[nr - 1].from, &entries[nr - 1],
&x, buffer, len, 0, fp, &total_cycles);
if (PRINT_FIELD(SRCCODE))
- printed += print_srccode(thread, x.cpumode, br->entries[nr - 1].from);
+ printed += print_srccode(thread, x.cpumode, entries[nr - 1].from);
}
/* Print all blocks */
for (i = nr - 2; i >= 0; i--) {
- if (br->entries[i].from || br->entries[i].to)
+ if (entries[i].from || entries[i].to)
pr_debug("%d: %" PRIx64 "-%" PRIx64 "\n", i,
- br->entries[i].from,
- br->entries[i].to);
- start = br->entries[i + 1].to;
- end = br->entries[i].from;
+ entries[i].from,
+ entries[i].to);
+ start = entries[i + 1].to;
+ end = entries[i].from;
len = grab_bb(buffer, start, end, machine, thread, &x.is64bit, &x.cpumode, false);
/* Patch up missing kernel transfers due to ring filters */
if (len == -ENXIO && i > 0) {
- end = br->entries[--i].from;
+ end = entries[--i].from;
pr_debug("\tpatching up to %" PRIx64 "-%" PRIx64 "\n", start, end);
len = grab_bb(buffer, start, end, machine, thread, &x.is64bit, &x.cpumode, false);
}
@@ -1110,7 +1114,7 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
printed += ip__fprintf_sym(ip, thread, x.cpumode, x.cpu, &lastsym, attr, fp);
if (ip == end) {
- printed += ip__fprintf_jump(ip, &br->entries[i], &x, buffer + off, len - off, ++insn, fp,
+ printed += ip__fprintf_jump(ip, &entries[i], &x, buffer + off, len - off, ++insn, fp,
&total_cycles);
if (PRINT_FIELD(SRCCODE))
printed += print_srccode(thread, x.cpumode, ip);
@@ -1134,9 +1138,9 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
* Hit the branch? In this case we are already done, and the target
* has not been executed yet.
*/
- if (br->entries[0].from == sample->ip)
+ if (entries[0].from == sample->ip)
goto out;
- if (br->entries[0].flags.abort)
+ if (entries[0].flags.abort)
goto out;
/*
@@ -1147,7 +1151,7 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
* between final branch and sample. When this happens just
* continue walking after the last TO until we hit a branch.
*/
- start = br->entries[0].to;
+ start = entries[0].to;
end = sample->ip;
if (end < start) {
/* Missing jump. Scan 128 bytes for the next branch */
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index a098c2ebf4ea..ec053dc1e35c 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -929,6 +929,10 @@ static struct option stat_options[] = {
OPT_BOOLEAN_FLAG(0, "all-user", &stat_config.all_user,
"Configure all used events to run in user space.",
PARSE_OPT_EXCLUSIVE),
+ OPT_BOOLEAN(0, "percore-show-thread", &stat_config.percore_show_thread,
+ "Use with 'percore' event qualifier to show the event "
+ "counts of one hardware thread by sum up total hardware "
+ "threads of same physical core"),
OPT_END()
};
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 8affcab75604..d2539b793f9d 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -143,7 +143,7 @@ static int perf_top__parse_source(struct perf_top *top, struct hist_entry *he)
return err;
}
- err = symbol__annotate(&he->ms, evsel, 0, &top->annotation_opts, NULL);
+ err = symbol__annotate(&he->ms, evsel, &top->annotation_opts, NULL);
if (err == 0) {
top->sym_filter_entry = he;
} else {
@@ -684,7 +684,9 @@ repeat:
delay_msecs = top->delay_secs * MSEC_PER_SEC;
set_term_quiet_input(&save);
/* trash return*/
- getc(stdin);
+ clearerr(stdin);
+ if (poll(&stdin_poll, 1, 0) > 0)
+ getc(stdin);
while (!done) {
perf_top__print_sym_table(top);
@@ -1683,7 +1685,7 @@ int cmd_top(int argc, const char **argv)
if (status < 0)
goto out_delete_evlist;
- annotation_config__init();
+ annotation_config__init(&top.annotation_opts);
symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL);
status = symbol__init(NULL);
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 46a72ecac427..01d542007c8b 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1065,7 +1065,9 @@ static struct syscall_fmt syscall_fmts[] = {
{ .name = "poll", .timeout = true, },
{ .name = "ppoll", .timeout = true, },
{ .name = "prctl",
- .arg = { [0] = { .scnprintf = SCA_PRCTL_OPTION, /* option */ },
+ .arg = { [0] = { .scnprintf = SCA_PRCTL_OPTION, /* option */
+ .strtoul = STUL_STRARRAY,
+ .parm = &strarray__prctl_options, },
[1] = { .scnprintf = SCA_PRCTL_ARG2, /* arg2 */ },
[2] = { .scnprintf = SCA_PRCTL_ARG3, /* arg3 */ }, }, },
{ .name = "pread", .alias = "pread64", },
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index 68039a96c1dc..bfb21d049e6c 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -13,6 +13,7 @@ include/uapi/linux/kcmp.h
include/uapi/linux/kvm.h
include/uapi/linux/in.h
include/uapi/linux/mount.h
+include/uapi/linux/openat2.h
include/uapi/linux/perf_event.h
include/uapi/linux/prctl.h
include/uapi/linux/sched.h
diff --git a/tools/perf/include/bpf/pid_filter.h b/tools/perf/include/bpf/pid_filter.h
index 607189a315b2..6e61c4bdf548 100644
--- a/tools/perf/include/bpf/pid_filter.h
+++ b/tools/perf/include/bpf/pid_filter.h
@@ -3,7 +3,7 @@
#ifndef _PERF_BPF_PID_FILTER_
#define _PERF_BPF_PID_FILTER_
-#include <bpf/bpf.h>
+#include <bpf.h>
#define pid_filter(name) pid_map(name, bool)
diff --git a/tools/perf/include/bpf/stdio.h b/tools/perf/include/bpf/stdio.h
index 7ca6fa5463ee..316af5b2ff35 100644
--- a/tools/perf/include/bpf/stdio.h
+++ b/tools/perf/include/bpf/stdio.h
@@ -1,6 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
-#include <bpf/bpf.h>
+#include <bpf.h>
struct bpf_map SEC("maps") __bpf_stdout__ = {
.type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
diff --git a/tools/perf/include/bpf/unistd.h b/tools/perf/include/bpf/unistd.h
index d1a35b6c649d..ca7877f9a976 100644
--- a/tools/perf/include/bpf/unistd.h
+++ b/tools/perf/include/bpf/unistd.h
@@ -1,6 +1,6 @@
// SPDX-License-Identifier: LGPL-2.1
-#include <bpf/bpf.h>
+#include <bpf.h>
static int (*bpf_get_current_pid_tgid)(void) = (void *)BPF_FUNC_get_current_pid_tgid;
diff --git a/tools/perf/pmu-events/arch/s390/cf_z15/crypto6.json b/tools/perf/pmu-events/arch/s390/cf_z15/crypto6.json
index 5e36bc2468d0..c998e4f1d1d2 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z15/crypto6.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z15/crypto6.json
@@ -4,27 +4,27 @@
"EventCode": "80",
"EventName": "ECC_FUNCTION_COUNT",
"BriefDescription": "ECC Function Count",
- "PublicDescription": "Long ECC function Count"
+ "PublicDescription": "This counter counts the total number of the elliptic-curve cryptography (ECC) functions issued by the CPU."
},
{
"Unit": "CPU-M-CF",
"EventCode": "81",
"EventName": "ECC_CYCLES_COUNT",
"BriefDescription": "ECC Cycles Count",
- "PublicDescription": "Long ECC Function cycles count"
+ "PublicDescription": "This counter counts the total number of CPU cycles when the ECC coprocessor is busy performing the elliptic-curve cryptography (ECC) functions issued by the CPU."
},
{
"Unit": "CPU-M-CF",
"EventCode": "82",
"EventName": "ECC_BLOCKED_FUNCTION_COUNT",
"BriefDescription": "Ecc Blocked Function Count",
- "PublicDescription": "Long ECC blocked function count"
+ "PublicDescription": "This counter counts the total number of the elliptic-curve cryptography (ECC) functions that are issued by the CPU and are blocked because the ECC coprocessor is busy performing a function issued by another CPU."
},
{
"Unit": "CPU-M-CF",
"EventCode": "83",
"EventName": "ECC_BLOCKED_CYCLES_COUNT",
"BriefDescription": "ECC Blocked Cycles Count",
- "PublicDescription": "Long ECC blocked cycles count"
+ "PublicDescription": "This counter counts the total number of CPU cycles blocked for the elliptic-curve cryptography (ECC) functions issued by the CPU because the ECC coprocessor is busy performing a function issued by another CPU."
},
]
diff --git a/tools/perf/pmu-events/arch/s390/cf_z15/extended.json b/tools/perf/pmu-events/arch/s390/cf_z15/extended.json
index 89e070727e1b..2df2e231e9ee 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z15/extended.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z15/extended.json
@@ -25,7 +25,7 @@
"EventCode": "131",
"EventName": "DTLB2_HPAGE_WRITES",
"BriefDescription": "DTLB2 One-Megabyte Page Writes",
- "PublicDescription": "A translation entry was written into the Combined Region and Segment Table Entry array in the Level-2 TLB for a one-megabyte page or a Last Host Translation was done"
+ "PublicDescription": "A translation entry was written into the Combined Region and Segment Table Entry array in the Level-2 TLB for a one-megabyte page"
},
{
"Unit": "CPU-M-CF",
@@ -358,6 +358,34 @@
},
{
"Unit": "CPU-M-CF",
+ "EventCode": "247",
+ "EventName": "DFLT_ACCESS",
+ "BriefDescription": "Cycles CPU spent obtaining access to Deflate unit",
+ "PublicDescription": "Cycles CPU spent obtaining access to Deflate unit"
+ },
+ {
+ "Unit": "CPU-M-CF",
+ "EventCode": "252",
+ "EventName": "DFLT_CYCLES",
+ "BriefDescription": "Cycles CPU is using Deflate unit",
+ "PublicDescription": "Cycles CPU is using Deflate unit"
+ },
+ {
+ "Unit": "CPU-M-CF",
+ "EventCode": "264",
+ "EventName": "DFLT_CC",
+ "BriefDescription": "Increments by one for every DEFLATE CONVERSION CALL instruction executed",
+ "PublicDescription": "Increments by one for every DEFLATE CONVERSION CALL instruction executed"
+ },
+ {
+ "Unit": "CPU-M-CF",
+ "EventCode": "265",
+ "EventName": "DFLT_CCERROR",
+ "BriefDescription": "Increments by one for every DEFLATE CONVERSION CALL instruction executed that ended in Condition Codes 0, 1 or 2",
+ "PublicDescription": "Increments by one for every DEFLATE CONVERSION CALL instruction executed that ended in Condition Codes 0, 1 or 2"
+ },
+ {
+ "Unit": "CPU-M-CF",
"EventCode": "448",
"EventName": "MT_DIAG_CYCLES_ONE_THR_ACTIVE",
"BriefDescription": "Cycle count with one thread active",
diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json
index f94653229dd4..a728c6e5119b 100644
--- a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json
@@ -215,7 +215,8 @@
"BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
"MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * cycles )",
"MetricGroup": "TLB",
- "MetricName": "Page_Walks_Utilization"
+ "MetricName": "Page_Walks_Utilization",
+ "MetricConstraint": "NO_NMI_WATCHDOG"
},
{
"BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
diff --git a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json
index e7feb60f9fa9..f97e8316ad2f 100644
--- a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json
@@ -215,7 +215,8 @@
"BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
"MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * cycles )",
"MetricGroup": "TLB",
- "MetricName": "Page_Walks_Utilization"
+ "MetricName": "Page_Walks_Utilization",
+ "MetricConstraint": "NO_NMI_WATCHDOG"
},
{
"BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json
index 21d7a0c2c2e8..35f5db1786f7 100644
--- a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json
@@ -215,7 +215,8 @@
"BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
"MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * cycles )",
"MetricGroup": "TLB",
- "MetricName": "Page_Walks_Utilization"
+ "MetricName": "Page_Walks_Utilization",
+ "MetricConstraint": "NO_NMI_WATCHDOG"
},
{
"BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c
index 079c77b6a2fd..3c4236a5bad8 100644
--- a/tools/perf/pmu-events/jevents.c
+++ b/tools/perf/pmu-events/jevents.c
@@ -323,7 +323,7 @@ static int print_events_table_entry(void *data, char *name, char *event,
char *pmu, char *unit, char *perpkg,
char *metric_expr,
char *metric_name, char *metric_group,
- char *deprecated)
+ char *deprecated, char *metric_constraint)
{
struct perf_entry_data *pd = data;
FILE *outfp = pd->outfp;
@@ -357,6 +357,8 @@ static int print_events_table_entry(void *data, char *name, char *event,
fprintf(outfp, "\t.metric_group = \"%s\",\n", metric_group);
if (deprecated)
fprintf(outfp, "\t.deprecated = \"%s\",\n", deprecated);
+ if (metric_constraint)
+ fprintf(outfp, "\t.metric_constraint = \"%s\",\n", metric_constraint);
fprintf(outfp, "},\n");
return 0;
@@ -375,6 +377,7 @@ struct event_struct {
char *metric_name;
char *metric_group;
char *deprecated;
+ char *metric_constraint;
};
#define ADD_EVENT_FIELD(field) do { if (field) { \
@@ -422,7 +425,7 @@ static int save_arch_std_events(void *data, char *name, char *event,
char *desc, char *long_desc, char *pmu,
char *unit, char *perpkg, char *metric_expr,
char *metric_name, char *metric_group,
- char *deprecated)
+ char *deprecated, char *metric_constraint)
{
struct event_struct *es;
@@ -486,7 +489,7 @@ try_fixup(const char *fn, char *arch_std, char **event, char **desc,
char **name, char **long_desc, char **pmu, char **filter,
char **perpkg, char **unit, char **metric_expr, char **metric_name,
char **metric_group, unsigned long long eventcode,
- char **deprecated)
+ char **deprecated, char **metric_constraint)
{
/* try to find matching event from arch standard values */
struct event_struct *es;
@@ -515,7 +518,7 @@ int json_events(const char *fn,
char *pmu, char *unit, char *perpkg,
char *metric_expr,
char *metric_name, char *metric_group,
- char *deprecated),
+ char *deprecated, char *metric_constraint),
void *data)
{
int err;
@@ -545,6 +548,7 @@ int json_events(const char *fn,
char *metric_name = NULL;
char *metric_group = NULL;
char *deprecated = NULL;
+ char *metric_constraint = NULL;
char *arch_std = NULL;
unsigned long long eventcode = 0;
struct msrmap *msr = NULL;
@@ -629,6 +633,8 @@ int json_events(const char *fn,
addfield(map, &metric_name, "", "", val);
} else if (json_streq(map, field, "MetricGroup")) {
addfield(map, &metric_group, "", "", val);
+ } else if (json_streq(map, field, "MetricConstraint")) {
+ addfield(map, &metric_constraint, "", "", val);
} else if (json_streq(map, field, "MetricExpr")) {
addfield(map, &metric_expr, "", "", val);
for (s = metric_expr; *s; s++)
@@ -670,13 +676,13 @@ int json_events(const char *fn,
&long_desc, &pmu, &filter, &perpkg,
&unit, &metric_expr, &metric_name,
&metric_group, eventcode,
- &deprecated);
+ &deprecated, &metric_constraint);
if (err)
goto free_strings;
}
err = func(data, name, real_event(name, event), desc, long_desc,
pmu, unit, perpkg, metric_expr, metric_name,
- metric_group, deprecated);
+ metric_group, deprecated, metric_constraint);
free_strings:
free(event);
free(desc);
@@ -691,6 +697,7 @@ free_strings:
free(metric_expr);
free(metric_name);
free(metric_group);
+ free(metric_constraint);
free(arch_std);
if (err)
@@ -1082,10 +1089,9 @@ static int process_one_file(const char *fpath, const struct stat *sb,
*/
int main(int argc, char *argv[])
{
- int rc;
+ int rc, ret = 0;
int maxfds;
char ldirname[PATH_MAX];
-
const char *arch;
const char *output_file;
const char *start_dirname;
@@ -1156,7 +1162,8 @@ int main(int argc, char *argv[])
/* Make build fail */
fclose(eventsfp);
free_arch_std_events();
- return 1;
+ ret = 1;
+ goto out_free_mapfile;
} else if (rc) {
goto empty_map;
}
@@ -1174,14 +1181,17 @@ int main(int argc, char *argv[])
/* Make build fail */
fclose(eventsfp);
free_arch_std_events();
- return 1;
+ ret = 1;
}
- return 0;
+
+ goto out_free_mapfile;
empty_map:
fclose(eventsfp);
create_empty_mapping(output_file);
free_arch_std_events();
- return 0;
+out_free_mapfile:
+ free(mapfile);
+ return ret;
}
diff --git a/tools/perf/pmu-events/jevents.h b/tools/perf/pmu-events/jevents.h
index 5cda49a42143..2afc8304529e 100644
--- a/tools/perf/pmu-events/jevents.h
+++ b/tools/perf/pmu-events/jevents.h
@@ -8,7 +8,7 @@ int json_events(const char *fn,
char *pmu,
char *unit, char *perpkg, char *metric_expr,
char *metric_name, char *metric_group,
- char *deprecated),
+ char *deprecated, char *metric_constraint),
void *data);
char *get_cpu_str(void);
diff --git a/tools/perf/pmu-events/pmu-events.h b/tools/perf/pmu-events/pmu-events.h
index caeb577d36c9..53e76d5d5b37 100644
--- a/tools/perf/pmu-events/pmu-events.h
+++ b/tools/perf/pmu-events/pmu-events.h
@@ -18,6 +18,7 @@ struct pmu_event {
const char *metric_name;
const char *metric_group;
const char *deprecated;
+ const char *metric_constraint;
};
/*
diff --git a/tools/perf/scripts/perl/check-perf-trace.pl b/tools/perf/scripts/perl/check-perf-trace.pl
index 4e7076c20616..d307ce8fd6ed 100644
--- a/tools/perf/scripts/perl/check-perf-trace.pl
+++ b/tools/perf/scripts/perl/check-perf-trace.pl
@@ -28,7 +28,7 @@ sub trace_end
sub irq::softirq_entry
{
my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
- $common_pid, $common_comm,
+ $common_pid, $common_comm, $common_callchain,
$vec) = @_;
print_header($event_name, $common_cpu, $common_secs, $common_nsecs,
@@ -43,7 +43,7 @@ sub irq::softirq_entry
sub kmem::kmalloc
{
my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
- $common_pid, $common_comm,
+ $common_pid, $common_comm, $common_callchain,
$call_site, $ptr, $bytes_req, $bytes_alloc,
$gfp_flags) = @_;
@@ -92,7 +92,7 @@ sub print_unhandled
sub trace_unhandled
{
my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
- $common_pid, $common_comm) = @_;
+ $common_pid, $common_comm, $common_callchain) = @_;
$unhandled{$event_name}++;
}
diff --git a/tools/perf/scripts/perl/failed-syscalls.pl b/tools/perf/scripts/perl/failed-syscalls.pl
index 55e7ae4c5c88..05954a8f363a 100644
--- a/tools/perf/scripts/perl/failed-syscalls.pl
+++ b/tools/perf/scripts/perl/failed-syscalls.pl
@@ -18,7 +18,7 @@ my %failed_syscalls;
sub raw_syscalls::sys_exit
{
my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
- $common_pid, $common_comm,
+ $common_pid, $common_comm, $common_callchain,
$id, $ret) = @_;
if ($ret < 0) {
diff --git a/tools/perf/scripts/perl/rw-by-file.pl b/tools/perf/scripts/perl/rw-by-file.pl
index 168fa5e94b44..92a750b8552b 100644
--- a/tools/perf/scripts/perl/rw-by-file.pl
+++ b/tools/perf/scripts/perl/rw-by-file.pl
@@ -28,7 +28,7 @@ my %writes;
sub syscalls::sys_enter_read
{
my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
- $common_pid, $common_comm, $nr, $fd, $buf, $count) = @_;
+ $common_pid, $common_comm, $common_callchain, $nr, $fd, $buf, $count) = @_;
if ($common_comm eq $for_comm) {
$reads{$fd}{bytes_requested} += $count;
@@ -39,7 +39,7 @@ sub syscalls::sys_enter_read
sub syscalls::sys_enter_write
{
my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
- $common_pid, $common_comm, $nr, $fd, $buf, $count) = @_;
+ $common_pid, $common_comm, $common_callchain, $nr, $fd, $buf, $count) = @_;
if ($common_comm eq $for_comm) {
$writes{$fd}{bytes_written} += $count;
@@ -98,7 +98,7 @@ sub print_unhandled
sub trace_unhandled
{
my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
- $common_pid, $common_comm) = @_;
+ $common_pid, $common_comm, $common_callchain) = @_;
$unhandled{$event_name}++;
}
diff --git a/tools/perf/scripts/perl/rw-by-pid.pl b/tools/perf/scripts/perl/rw-by-pid.pl
index 495698250b2f..d789fe39caab 100644
--- a/tools/perf/scripts/perl/rw-by-pid.pl
+++ b/tools/perf/scripts/perl/rw-by-pid.pl
@@ -24,7 +24,7 @@ my %writes;
sub syscalls::sys_exit_read
{
my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
- $common_pid, $common_comm,
+ $common_pid, $common_comm, $common_callchain,
$nr, $ret) = @_;
if ($ret > 0) {
@@ -40,7 +40,7 @@ sub syscalls::sys_exit_read
sub syscalls::sys_enter_read
{
my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
- $common_pid, $common_comm,
+ $common_pid, $common_comm, $common_callchain,
$nr, $fd, $buf, $count) = @_;
$reads{$common_pid}{bytes_requested} += $count;
@@ -51,7 +51,7 @@ sub syscalls::sys_enter_read
sub syscalls::sys_exit_write
{
my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
- $common_pid, $common_comm,
+ $common_pid, $common_comm, $common_callchain,
$nr, $ret) = @_;
if ($ret <= 0) {
@@ -62,7 +62,7 @@ sub syscalls::sys_exit_write
sub syscalls::sys_enter_write
{
my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
- $common_pid, $common_comm,
+ $common_pid, $common_comm, $common_callchain,
$nr, $fd, $buf, $count) = @_;
$writes{$common_pid}{bytes_written} += $count;
@@ -178,7 +178,7 @@ sub print_unhandled
sub trace_unhandled
{
my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
- $common_pid, $common_comm) = @_;
+ $common_pid, $common_comm, $common_callchain) = @_;
$unhandled{$event_name}++;
}
diff --git a/tools/perf/scripts/perl/rwtop.pl b/tools/perf/scripts/perl/rwtop.pl
index 6473442568a2..eba4df67af6b 100644
--- a/tools/perf/scripts/perl/rwtop.pl
+++ b/tools/perf/scripts/perl/rwtop.pl
@@ -35,7 +35,7 @@ if (!$interval) {
sub syscalls::sys_exit_read
{
my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
- $common_pid, $common_comm,
+ $common_pid, $common_comm, $common_callchain,
$nr, $ret) = @_;
print_check();
@@ -53,7 +53,7 @@ sub syscalls::sys_exit_read
sub syscalls::sys_enter_read
{
my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
- $common_pid, $common_comm,
+ $common_pid, $common_comm, $common_callchain,
$nr, $fd, $buf, $count) = @_;
print_check();
@@ -66,7 +66,7 @@ sub syscalls::sys_enter_read
sub syscalls::sys_exit_write
{
my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
- $common_pid, $common_comm,
+ $common_pid, $common_comm, $common_callchain,
$nr, $ret) = @_;
print_check();
@@ -79,7 +79,7 @@ sub syscalls::sys_exit_write
sub syscalls::sys_enter_write
{
my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
- $common_pid, $common_comm,
+ $common_pid, $common_comm, $common_callchain,
$nr, $fd, $buf, $count) = @_;
print_check();
@@ -197,7 +197,7 @@ sub print_unhandled
sub trace_unhandled
{
my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
- $common_pid, $common_comm) = @_;
+ $common_pid, $common_comm, $common_callchain) = @_;
$unhandled{$event_name}++;
}
diff --git a/tools/perf/scripts/perl/wakeup-latency.pl b/tools/perf/scripts/perl/wakeup-latency.pl
index efcfec5e347a..53444ff4ec7f 100644
--- a/tools/perf/scripts/perl/wakeup-latency.pl
+++ b/tools/perf/scripts/perl/wakeup-latency.pl
@@ -28,7 +28,7 @@ my $total_wakeups = 0;
sub sched::sched_switch
{
my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
- $common_pid, $common_comm,
+ $common_pid, $common_comm, $common_callchain,
$prev_comm, $prev_pid, $prev_prio, $prev_state, $next_comm, $next_pid,
$next_prio) = @_;
@@ -51,7 +51,7 @@ sub sched::sched_switch
sub sched::sched_wakeup
{
my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
- $common_pid, $common_comm,
+ $common_pid, $common_comm, $common_callchain,
$comm, $pid, $prio, $success, $target_cpu) = @_;
$last_wakeup{$target_cpu}{ts} = nsecs($common_secs, $common_nsecs);
@@ -101,7 +101,7 @@ sub print_unhandled
sub trace_unhandled
{
my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
- $common_pid, $common_comm) = @_;
+ $common_pid, $common_comm, $common_callchain) = @_;
$unhandled{$event_name}++;
}
diff --git a/tools/perf/tests/bp_account.c b/tools/perf/tests/bp_account.c
index d0b935356274..489b50604cf2 100644
--- a/tools/perf/tests/bp_account.c
+++ b/tools/perf/tests/bp_account.c
@@ -19,7 +19,7 @@
#include "../perf-sys.h"
#include "cloexec.h"
-volatile long the_var;
+static volatile long the_var;
static noinline int test_function(void)
{
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 5f05db75cdd8..54d9516c9839 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -543,8 +543,11 @@ static int run_shell_tests(int argc, const char *argv[], int i, int width)
return -1;
dir = opendir(st.dir);
- if (!dir)
+ if (!dir) {
+ pr_err("failed to open shell test directory: %s\n",
+ st.dir);
return -1;
+ }
for_each_shell_test(dir, st.dir, ent) {
int curr = i++;
diff --git a/tools/perf/tests/expr.c b/tools/perf/tests/expr.c
index 87843af4c118..28313e59d6f6 100644
--- a/tools/perf/tests/expr.c
+++ b/tools/perf/tests/expr.c
@@ -10,7 +10,7 @@ static int test(struct parse_ctx *ctx, const char *e, double val2)
{
double val;
- if (expr__parse(&val, ctx, &e))
+ if (expr__parse(&val, ctx, e))
TEST_ASSERT_VAL("parse test failed", 0);
TEST_ASSERT_VAL("unexpected value", val == val2);
return 0;
@@ -44,12 +44,12 @@ int test__expr(struct test *t __maybe_unused, int subtest __maybe_unused)
return ret;
p = "FOO/0";
- ret = expr__parse(&val, &ctx, &p);
- TEST_ASSERT_VAL("division by zero", ret == 1);
+ ret = expr__parse(&val, &ctx, p);
+ TEST_ASSERT_VAL("division by zero", ret == -1);
p = "BAR/";
- ret = expr__parse(&val, &ctx, &p);
- TEST_ASSERT_VAL("missing operand", ret == 1);
+ ret = expr__parse(&val, &ctx, p);
+ TEST_ASSERT_VAL("missing operand", ret == -1);
TEST_ASSERT_VAL("find other",
expr__find_other("FOO + BAR + BAZ + BOZO", "FOO", &other, &num_other) == 0);
diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c
index 2762e1155238..14239e472187 100644
--- a/tools/perf/tests/sample-parsing.c
+++ b/tools/perf/tests/sample-parsing.c
@@ -99,6 +99,7 @@ static bool samples_same(const struct perf_sample *s1,
if (type & PERF_SAMPLE_BRANCH_STACK) {
COMP(branch_stack->nr);
+ COMP(branch_stack->hw_idx);
for (i = 0; i < s1->branch_stack->nr; i++)
MCOMP(branch_stack->entries[i]);
}
@@ -186,7 +187,7 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format)
u64 data[64];
} branch_stack = {
/* 1 branch_entry */
- .data = {1, 211, 212, 213},
+ .data = {1, -1ULL, 211, 212, 213},
};
u64 regs[64];
const u64 raw_data[] = {0x123456780a0b0c0dULL, 0x1102030405060708ULL};
@@ -208,6 +209,7 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format)
.transaction = 112,
.raw_data = (void *)raw_data,
.callchain = &callchain.callchain,
+ .no_hw_idx = false,
.branch_stack = &branch_stack.branch_stack,
.user_regs = {
.abi = PERF_SAMPLE_REGS_ABI_64,
@@ -244,6 +246,9 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format)
if (sample_type & PERF_SAMPLE_REGS_INTR)
evsel.core.attr.sample_regs_intr = sample_regs;
+ if (sample_type & PERF_SAMPLE_BRANCH_STACK)
+ evsel.core.attr.branch_sample_type |= PERF_SAMPLE_BRANCH_HW_INDEX;
+
for (i = 0; i < sizeof(regs); i++)
*(i + (u8 *)regs) = i & 0xfe;
diff --git a/tools/perf/tests/shell/lib/probe_vfs_getname.sh b/tools/perf/tests/shell/lib/probe_vfs_getname.sh
index 7cb99b433888..c2cc42daf924 100644
--- a/tools/perf/tests/shell/lib/probe_vfs_getname.sh
+++ b/tools/perf/tests/shell/lib/probe_vfs_getname.sh
@@ -14,7 +14,7 @@ add_probe_vfs_getname() {
if [ $had_vfs_getname -eq 1 ] ; then
line=$(perf probe -L getname_flags 2>&1 | egrep 'result.*=.*filename;' | sed -r 's/[[:space:]]+([[:digit:]]+)[[:space:]]+result->uptr.*/\1/')
perf probe -q "vfs_getname=getname_flags:${line} pathname=result->name:string" || \
- perf probe $verbose "vfs_getname=getname_flags:${line} pathname=filename:string"
+ perf probe $verbose "vfs_getname=getname_flags:${line} pathname=filename:ustring"
fi
}
diff --git a/tools/perf/trace/beauty/beauty.h b/tools/perf/trace/beauty/beauty.h
index 5a61043c2ff7..d6dfe68a7612 100644
--- a/tools/perf/trace/beauty/beauty.h
+++ b/tools/perf/trace/beauty/beauty.h
@@ -213,6 +213,8 @@ size_t syscall_arg__scnprintf_x86_arch_prctl_code(char *bf, size_t size, struct
size_t syscall_arg__scnprintf_prctl_option(char *bf, size_t size, struct syscall_arg *arg);
#define SCA_PRCTL_OPTION syscall_arg__scnprintf_prctl_option
+extern struct strarray strarray__prctl_options;
+
size_t syscall_arg__scnprintf_prctl_arg2(char *bf, size_t size, struct syscall_arg *arg);
#define SCA_PRCTL_ARG2 syscall_arg__scnprintf_prctl_arg2
diff --git a/tools/perf/trace/beauty/prctl.c b/tools/perf/trace/beauty/prctl.c
index ba2179abed00..6fe5ad5f5d3a 100644
--- a/tools/perf/trace/beauty/prctl.c
+++ b/tools/perf/trace/beauty/prctl.c
@@ -11,9 +11,10 @@
#include "trace/beauty/generated/prctl_option_array.c"
+DEFINE_STRARRAY(prctl_options, "PR_");
+
static size_t prctl__scnprintf_option(int option, char *bf, size_t size, bool show_prefix)
{
- static DEFINE_STRARRAY(prctl_options, "PR_");
return strarray__scnprintf(&strarray__prctl_options, bf, size, "%d", show_prefix, option);
}
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index badbddbb30f8..9023267e5643 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -754,10 +754,9 @@ static int annotate_browser__run(struct annotate_browser *browser,
"? Search string backwards\n");
continue;
case 'r':
- {
- script_browse(NULL, NULL);
- continue;
- }
+ script_browse(NULL, NULL);
+ annotate_browser__show(&browser->b, title, help);
+ continue;
case 'k':
notes->options->show_linenr = !notes->options->show_linenr;
break;
@@ -834,13 +833,13 @@ show_sup_ins:
map_symbol__annotation_dump(ms, evsel, browser->opts);
continue;
case 't':
- if (notes->options->show_total_period) {
- notes->options->show_total_period = false;
- notes->options->show_nr_samples = true;
- } else if (notes->options->show_nr_samples)
- notes->options->show_nr_samples = false;
+ if (symbol_conf.show_total_period) {
+ symbol_conf.show_total_period = false;
+ symbol_conf.show_nr_samples = true;
+ } else if (symbol_conf.show_nr_samples)
+ symbol_conf.show_nr_samples = false;
else
- notes->options->show_total_period = true;
+ symbol_conf.show_total_period = true;
annotation__update_column_widths(notes);
continue;
case 'c':
diff --git a/tools/perf/ui/gtk/annotate.c b/tools/perf/ui/gtk/annotate.c
index 22cc240f7371..35f9641bf670 100644
--- a/tools/perf/ui/gtk/annotate.c
+++ b/tools/perf/ui/gtk/annotate.c
@@ -174,7 +174,7 @@ static int symbol__gtk_annotate(struct map_symbol *ms, struct evsel *evsel,
if (ms->map->dso->annotate_warned)
return -1;
- err = symbol__annotate(ms, evsel, 0, &annotation__default_options, NULL);
+ err = symbol__annotate(ms, evsel, &annotation__default_options, NULL);
if (err) {
char msg[BUFSIZ];
symbol__strerror_disassemble(ms, err, msg, sizeof(msg));
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 07da6c790b63..c0cf8dff694e 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -121,7 +121,9 @@ perf-y += mem-events.o
perf-y += vsprintf.o
perf-y += units.o
perf-y += time-utils.o
+perf-y += expr-flex.o
perf-y += expr-bison.o
+perf-y += expr.o
perf-y += branch.o
perf-y += mem2node.o
@@ -189,9 +191,13 @@ $(OUTPUT)util/parse-events-bison.c: util/parse-events.y
$(call rule_mkdir)
$(Q)$(call echo-cmd,bison)$(BISON) -v util/parse-events.y -d $(PARSER_DEBUG_BISON) -o $@ -p parse_events_
+$(OUTPUT)util/expr-flex.c: util/expr.l $(OUTPUT)util/expr-bison.c
+ $(call rule_mkdir)
+ $(Q)$(call echo-cmd,flex)$(FLEX) -o $@ --header-file=$(OUTPUT)util/expr-flex.h $(PARSER_DEBUG_FLEX) util/expr.l
+
$(OUTPUT)util/expr-bison.c: util/expr.y
$(call rule_mkdir)
- $(Q)$(call echo-cmd,bison)$(BISON) -v util/expr.y -d $(PARSER_DEBUG_BISON) -o $@ -p expr__
+ $(Q)$(call echo-cmd,bison)$(BISON) -v util/expr.y -d $(PARSER_DEBUG_BISON) -o $@ -p expr_
$(OUTPUT)util/pmu-flex.c: util/pmu.l $(OUTPUT)util/pmu-bison.c
$(call rule_mkdir)
@@ -203,12 +209,14 @@ $(OUTPUT)util/pmu-bison.c: util/pmu.y
CFLAGS_parse-events-flex.o += -w
CFLAGS_pmu-flex.o += -w
+CFLAGS_expr-flex.o += -w
CFLAGS_parse-events-bison.o += -DYYENABLE_NLS=0 -w
CFLAGS_pmu-bison.o += -DYYENABLE_NLS=0 -DYYLTYPE_IS_TRIVIAL=0 -w
CFLAGS_expr-bison.o += -DYYENABLE_NLS=0 -DYYLTYPE_IS_TRIVIAL=0 -w
$(OUTPUT)util/parse-events.o: $(OUTPUT)util/parse-events-flex.c $(OUTPUT)util/parse-events-bison.c
$(OUTPUT)util/pmu.o: $(OUTPUT)util/pmu-flex.c $(OUTPUT)util/pmu-bison.c
+$(OUTPUT)util/expr.o: $(OUTPUT)util/expr-flex.c $(OUTPUT)util/expr-bison.c
CFLAGS_bitmap.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
CFLAGS_find_bit.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
@@ -216,6 +224,7 @@ CFLAGS_rbtree.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ET
CFLAGS_libstring.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
CFLAGS_hweight.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
CFLAGS_parse-events.o += -Wno-redundant-decls
+CFLAGS_expr.o += -Wno-redundant-decls
CFLAGS_header.o += -include $(OUTPUT)PERF-VERSION-FILE
$(OUTPUT)util/kallsyms.o: ../lib/symbol/kallsyms.c FORCE
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index ca73fb74ad03..f1ea0d61eb5b 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -1143,93 +1143,70 @@ out:
}
struct annotate_args {
- size_t privsize;
- struct arch *arch;
- struct map_symbol ms;
- struct evsel *evsel;
+ struct arch *arch;
+ struct map_symbol ms;
+ struct evsel *evsel;
struct annotation_options *options;
- s64 offset;
- char *line;
- int line_nr;
+ s64 offset;
+ char *line;
+ int line_nr;
};
-static void annotation_line__delete(struct annotation_line *al)
+static void annotation_line__init(struct annotation_line *al,
+ struct annotate_args *args,
+ int nr)
{
- void *ptr = (void *) al - al->privsize;
+ al->offset = args->offset;
+ al->line = strdup(args->line);
+ al->line_nr = args->line_nr;
+ al->data_nr = nr;
+}
+static void annotation_line__exit(struct annotation_line *al)
+{
free_srcline(al->path);
zfree(&al->line);
- free(ptr);
}
-/*
- * Allocating the annotation line data with following
- * structure:
- *
- * --------------------------------------
- * private space | struct annotation_line
- * --------------------------------------
- *
- * Size of the private space is stored in 'struct annotation_line'.
- *
- */
-static struct annotation_line *
-annotation_line__new(struct annotate_args *args, size_t privsize)
+static size_t disasm_line_size(int nr)
{
struct annotation_line *al;
- struct evsel *evsel = args->evsel;
- size_t size = privsize + sizeof(*al);
- int nr = 1;
-
- if (perf_evsel__is_group_event(evsel))
- nr = evsel->core.nr_members;
- size += sizeof(al->data[0]) * nr;
-
- al = zalloc(size);
- if (al) {
- al = (void *) al + privsize;
- al->privsize = privsize;
- al->offset = args->offset;
- al->line = strdup(args->line);
- al->line_nr = args->line_nr;
- al->data_nr = nr;
- }
-
- return al;
+ return (sizeof(struct disasm_line) + (sizeof(al->data[0]) * nr));
}
/*
* Allocating the disasm annotation line data with
* following structure:
*
- * ------------------------------------------------------------
- * privsize space | struct disasm_line | struct annotation_line
- * ------------------------------------------------------------
+ * -------------------------------------------
+ * struct disasm_line | struct annotation_line
+ * -------------------------------------------
*
* We have 'struct annotation_line' member as last member
* of 'struct disasm_line' to have an easy access.
- *
*/
static struct disasm_line *disasm_line__new(struct annotate_args *args)
{
struct disasm_line *dl = NULL;
- struct annotation_line *al;
- size_t privsize = args->privsize + offsetof(struct disasm_line, al);
+ int nr = 1;
- al = annotation_line__new(args, privsize);
- if (al != NULL) {
- dl = disasm_line(al);
+ if (perf_evsel__is_group_event(args->evsel))
+ nr = args->evsel->core.nr_members;
- if (dl->al.line == NULL)
- goto out_delete;
+ dl = zalloc(disasm_line_size(nr));
+ if (!dl)
+ return NULL;
- if (args->offset != -1) {
- if (disasm_line__parse(dl->al.line, &dl->ins.name, &dl->ops.raw) < 0)
- goto out_free_line;
+ annotation_line__init(&dl->al, args, nr);
+ if (dl->al.line == NULL)
+ goto out_delete;
- disasm_line__init_ins(dl, args->arch, &args->ms);
- }
+ if (args->offset != -1) {
+ if (disasm_line__parse(dl->al.line, &dl->ins.name, &dl->ops.raw) < 0)
+ goto out_free_line;
+
+ disasm_line__init_ins(dl, args->arch, &args->ms);
}
return dl;
@@ -1248,7 +1225,8 @@ void disasm_line__free(struct disasm_line *dl)
else
ins__delete(&dl->ops);
zfree(&dl->ins.name);
- annotation_line__delete(&dl->al);
+ annotation_line__exit(&dl->al);
+ free(dl);
}
int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw, int max_ins_name)
@@ -2149,13 +2127,12 @@ void symbol__calc_percent(struct symbol *sym, struct evsel *evsel)
annotation__calc_percent(notes, evsel, symbol__size(sym));
}
-int symbol__annotate(struct map_symbol *ms, struct evsel *evsel, size_t privsize,
+int symbol__annotate(struct map_symbol *ms, struct evsel *evsel,
struct annotation_options *options, struct arch **parch)
{
struct symbol *sym = ms->sym;
struct annotation *notes = symbol__annotation(sym);
struct annotate_args args = {
- .privsize = privsize,
.evsel = evsel,
.options = options,
};
@@ -2634,8 +2611,6 @@ void annotation__mark_jump_targets(struct annotation *notes, struct symbol *sym)
if (++al->jump_sources > notes->max_jump_sources)
notes->max_jump_sources = al->jump_sources;
-
- ++notes->nr_jumps;
}
}
@@ -2644,6 +2619,8 @@ void annotation__set_offsets(struct annotation *notes, s64 size)
struct annotation_line *al;
notes->max_line_len = 0;
+ notes->nr_entries = 0;
+ notes->nr_asm_entries = 0;
list_for_each_entry(al, &notes->src->source, node) {
size_t line_len = strlen(al->line);
@@ -2790,7 +2767,7 @@ int symbol__tty_annotate(struct map_symbol *ms, struct evsel *evsel,
struct symbol *sym = ms->sym;
struct rb_root source_line = RB_ROOT;
- if (symbol__annotate(ms, evsel, 0, opts, NULL) < 0)
+ if (symbol__annotate(ms, evsel, opts, NULL) < 0)
return -1;
symbol__calc_percent(sym, evsel);
@@ -2915,9 +2892,9 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati
percent = annotation_data__percent(&al->data[i], percent_type);
obj__set_percent_color(obj, percent, current_entry);
- if (notes->options->show_total_period) {
+ if (symbol_conf.show_total_period) {
obj__printf(obj, "%11" PRIu64 " ", al->data[i].he.period);
- } else if (notes->options->show_nr_samples) {
+ } else if (symbol_conf.show_nr_samples) {
obj__printf(obj, "%6" PRIu64 " ",
al->data[i].he.nr_samples);
} else {
@@ -2931,8 +2908,8 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati
obj__printf(obj, "%-*s", pcnt_width, " ");
else {
obj__printf(obj, "%-*s", pcnt_width,
- notes->options->show_total_period ? "Period" :
- notes->options->show_nr_samples ? "Samples" : "Percent");
+ symbol_conf.show_total_period ? "Period" :
+ symbol_conf.show_nr_samples ? "Samples" : "Percent");
}
}
@@ -3070,7 +3047,7 @@ int symbol__annotate2(struct map_symbol *ms, struct evsel *evsel,
if (perf_evsel__is_group_event(evsel))
nr_pcnt = evsel->core.nr_members;
- err = symbol__annotate(ms, evsel, 0, options, parch);
+ err = symbol__annotate(ms, evsel, options, parch);
if (err)
goto out_free_offsets;
@@ -3094,69 +3071,46 @@ out_free_offsets:
return err;
}
-#define ANNOTATION__CFG(n) \
- { .name = #n, .value = &annotation__default_options.n, }
-
-/*
- * Keep the entries sorted, they are bsearch'ed
- */
-static struct annotation_config {
- const char *name;
- void *value;
-} annotation__configs[] = {
- ANNOTATION__CFG(hide_src_code),
- ANNOTATION__CFG(jump_arrows),
- ANNOTATION__CFG(offset_level),
- ANNOTATION__CFG(show_linenr),
- ANNOTATION__CFG(show_nr_jumps),
- ANNOTATION__CFG(show_nr_samples),
- ANNOTATION__CFG(show_total_period),
- ANNOTATION__CFG(use_offset),
-};
-
-#undef ANNOTATION__CFG
-
-static int annotation_config__cmp(const void *name, const void *cfgp)
+static int annotation__config(const char *var, const char *value, void *data)
{
- const struct annotation_config *cfg = cfgp;
-
- return strcmp(name, cfg->name);
-}
-
-static int annotation__config(const char *var, const char *value,
- void *data __maybe_unused)
-{
- struct annotation_config *cfg;
- const char *name;
+ struct annotation_options *opt = data;
if (!strstarts(var, "annotate."))
return 0;
- name = var + 9;
- cfg = bsearch(name, annotation__configs, ARRAY_SIZE(annotation__configs),
- sizeof(struct annotation_config), annotation_config__cmp);
-
- if (cfg == NULL)
- pr_debug("%s variable unknown, ignoring...", var);
- else if (strcmp(var, "annotate.offset_level") == 0) {
- perf_config_int(cfg->value, name, value);
-
- if (*(int *)cfg->value > ANNOTATION__MAX_OFFSET_LEVEL)
- *(int *)cfg->value = ANNOTATION__MAX_OFFSET_LEVEL;
- else if (*(int *)cfg->value < ANNOTATION__MIN_OFFSET_LEVEL)
- *(int *)cfg->value = ANNOTATION__MIN_OFFSET_LEVEL;
+ if (!strcmp(var, "annotate.offset_level")) {
+ perf_config_u8(&opt->offset_level, "offset_level", value);
+
+ if (opt->offset_level > ANNOTATION__MAX_OFFSET_LEVEL)
+ opt->offset_level = ANNOTATION__MAX_OFFSET_LEVEL;
+ else if (opt->offset_level < ANNOTATION__MIN_OFFSET_LEVEL)
+ opt->offset_level = ANNOTATION__MIN_OFFSET_LEVEL;
+ } else if (!strcmp(var, "annotate.hide_src_code")) {
+ opt->hide_src_code = perf_config_bool("hide_src_code", value);
+ } else if (!strcmp(var, "annotate.jump_arrows")) {
+ opt->jump_arrows = perf_config_bool("jump_arrows", value);
+ } else if (!strcmp(var, "annotate.show_linenr")) {
+ opt->show_linenr = perf_config_bool("show_linenr", value);
+ } else if (!strcmp(var, "annotate.show_nr_jumps")) {
+ opt->show_nr_jumps = perf_config_bool("show_nr_jumps", value);
+ } else if (!strcmp(var, "annotate.show_nr_samples")) {
+ symbol_conf.show_nr_samples = perf_config_bool("show_nr_samples",
+ value);
+ } else if (!strcmp(var, "annotate.show_total_period")) {
+ symbol_conf.show_total_period = perf_config_bool("show_total_period",
+ value);
+ } else if (!strcmp(var, "annotate.use_offset")) {
+ opt->use_offset = perf_config_bool("use_offset", value);
} else {
- *(bool *)cfg->value = perf_config_bool(name, value);
+ pr_debug("%s variable unknown, ignoring...", var);
}
+
return 0;
}
-void annotation_config__init(void)
+void annotation_config__init(struct annotation_options *opt)
{
- perf_config(annotation__config, NULL);
-
- annotation__default_options.show_total_period = symbol_conf.show_total_period;
- annotation__default_options.show_nr_samples = symbol_conf.show_nr_samples;
+ perf_config(annotation__config, opt);
}
static unsigned int parse_percent_type(char *str1, char *str2)
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 455403e8fede..07c775938d46 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -83,8 +83,6 @@ struct annotation_options {
full_path,
show_linenr,
show_nr_jumps,
- show_nr_samples,
- show_total_period,
show_minmax_cycle,
show_asm_raw,
annotate_src;
@@ -141,7 +139,6 @@ struct annotation_line {
u64 cycles;
u64 cycles_max;
u64 cycles_min;
- size_t privsize;
char *path;
u32 idx;
int idx_asm;
@@ -282,7 +279,6 @@ struct annotation {
struct annotation_options *options;
struct annotation_line **offsets;
int nr_events;
- int nr_jumps;
int max_jump_sources;
int nr_entries;
int nr_asm_entries;
@@ -309,7 +305,7 @@ static inline int annotation__cycles_width(struct annotation *notes)
static inline int annotation__pcnt_width(struct annotation *notes)
{
- return (notes->options->show_total_period ? 12 : 7) * notes->nr_events;
+ return (symbol_conf.show_total_period ? 12 : 7) * notes->nr_events;
}
static inline bool annotation_line__filter(struct annotation_line *al, struct annotation *notes)
@@ -352,7 +348,7 @@ struct annotated_source *symbol__hists(struct symbol *sym, int nr_hists);
void symbol__annotate_zero_histograms(struct symbol *sym);
int symbol__annotate(struct map_symbol *ms,
- struct evsel *evsel, size_t privsize,
+ struct evsel *evsel,
struct annotation_options *options,
struct arch **parch);
int symbol__annotate2(struct map_symbol *ms,
@@ -413,7 +409,7 @@ static inline int symbol__tui_annotate(struct map_symbol *ms __maybe_unused,
}
#endif
-void annotation_config__init(void);
+void annotation_config__init(struct annotation_options *opt);
int annotate_parse_percent_type(const struct option *opt, const char *_str,
int unset);
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index eb087e7df6f4..3571ce72ca28 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -629,8 +629,10 @@ int auxtrace_record__options(struct auxtrace_record *itr,
struct evlist *evlist,
struct record_opts *opts)
{
- if (itr)
+ if (itr) {
+ itr->evlist = evlist;
return itr->recording_options(itr, evlist, opts);
+ }
return 0;
}
@@ -664,6 +666,24 @@ int auxtrace_parse_snapshot_options(struct auxtrace_record *itr,
return -EINVAL;
}
+int auxtrace_record__read_finish(struct auxtrace_record *itr, int idx)
+{
+ struct evsel *evsel;
+
+ if (!itr->evlist || !itr->pmu)
+ return -EINVAL;
+
+ evlist__for_each_entry(itr->evlist, evsel) {
+ if (evsel->core.attr.type == itr->pmu->type) {
+ if (evsel->disabled)
+ return 0;
+ return perf_evlist__enable_event_idx(itr->evlist, evsel,
+ idx);
+ }
+ }
+ return -EINVAL;
+}
+
/*
* Event record size is 16-bit which results in a maximum size of about 64KiB.
* Allow about 4KiB for the rest of the sample record, to give a maximum
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index 749d72cd9c7b..e58ef160b599 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -29,6 +29,7 @@ struct record_opts;
struct perf_record_auxtrace_error;
struct perf_record_auxtrace_info;
struct events_stats;
+struct perf_pmu;
enum auxtrace_error_type {
PERF_AUXTRACE_ERROR_ITRACE = 1,
@@ -322,6 +323,8 @@ struct auxtrace_mmap_params {
* @read_finish: called after reading from an auxtrace mmap
* @alignment: alignment (if any) for AUX area data
* @default_aux_sample_size: default sample size for --aux sample option
+ * @pmu: associated pmu
+ * @evlist: selected events list
*/
struct auxtrace_record {
int (*recording_options)(struct auxtrace_record *itr,
@@ -346,6 +349,8 @@ struct auxtrace_record {
int (*read_finish)(struct auxtrace_record *itr, int idx);
unsigned int alignment;
unsigned int default_aux_sample_size;
+ struct perf_pmu *pmu;
+ struct evlist *evlist;
};
/**
@@ -537,6 +542,7 @@ int auxtrace_record__find_snapshot(struct auxtrace_record *itr, int idx,
struct auxtrace_mmap *mm,
unsigned char *data, u64 *head, u64 *old);
u64 auxtrace_record__reference(struct auxtrace_record *itr);
+int auxtrace_record__read_finish(struct auxtrace_record *itr, int idx);
int auxtrace_index__auxtrace_event(struct list_head *head, union perf_event *event,
off_t file_offset);
diff --git a/tools/perf/util/block-info.c b/tools/perf/util/block-info.c
index c4b030bf6ec2..423ec69bda6c 100644
--- a/tools/perf/util/block-info.c
+++ b/tools/perf/util/block-info.c
@@ -65,8 +65,7 @@ struct block_info *block_info__new(void)
return bi;
}
-int64_t block_info__cmp(struct perf_hpp_fmt *fmt __maybe_unused,
- struct hist_entry *left, struct hist_entry *right)
+int64_t __block_info__cmp(struct hist_entry *left, struct hist_entry *right)
{
struct block_info *bi_l = left->block_info;
struct block_info *bi_r = right->block_info;
@@ -74,30 +73,27 @@ int64_t block_info__cmp(struct perf_hpp_fmt *fmt __maybe_unused,
if (!bi_l->sym || !bi_r->sym) {
if (!bi_l->sym && !bi_r->sym)
- return 0;
+ return -1;
else if (!bi_l->sym)
return -1;
else
return 1;
}
- if (bi_l->sym == bi_r->sym) {
- if (bi_l->start == bi_r->start) {
- if (bi_l->end == bi_r->end)
- return 0;
- else
- return (int64_t)(bi_r->end - bi_l->end);
- } else
- return (int64_t)(bi_r->start - bi_l->start);
- } else {
- cmp = strcmp(bi_l->sym->name, bi_r->sym->name);
+ cmp = strcmp(bi_l->sym->name, bi_r->sym->name);
+ if (cmp)
return cmp;
- }
- if (bi_l->sym->start != bi_r->sym->start)
- return (int64_t)(bi_r->sym->start - bi_l->sym->start);
+ if (bi_l->start != bi_r->start)
+ return (int64_t)(bi_r->start - bi_l->start);
- return (int64_t)(bi_r->sym->end - bi_l->sym->end);
+ return (int64_t)(bi_r->end - bi_l->end);
+}
+
+int64_t block_info__cmp(struct perf_hpp_fmt *fmt __maybe_unused,
+ struct hist_entry *left, struct hist_entry *right)
+{
+ return __block_info__cmp(left, right);
}
static void init_block_info(struct block_info *bi, struct symbol *sym,
@@ -185,6 +181,17 @@ static int block_column_width(struct perf_hpp_fmt *fmt,
return block_fmt->width;
}
+static int color_pct(struct perf_hpp *hpp, int width, double pct)
+{
+#ifdef HAVE_SLANG_SUPPORT
+ if (use_browser) {
+ return __hpp__slsmg_color_printf(hpp, "%*.2f%%",
+ width - 1, pct);
+ }
+#endif
+ return hpp_color_scnprintf(hpp, "%*.2f%%", width - 1, pct);
+}
+
static int block_total_cycles_pct_entry(struct perf_hpp_fmt *fmt,
struct perf_hpp *hpp,
struct hist_entry *he)
@@ -192,14 +199,11 @@ static int block_total_cycles_pct_entry(struct perf_hpp_fmt *fmt,
struct block_fmt *block_fmt = container_of(fmt, struct block_fmt, fmt);
struct block_info *bi = he->block_info;
double ratio = 0.0;
- char buf[16];
if (block_fmt->total_cycles)
ratio = (double)bi->cycles / (double)block_fmt->total_cycles;
- sprintf(buf, "%.2f%%", 100.0 * ratio);
-
- return scnprintf(hpp->buf, hpp->size, "%*s", block_fmt->width, buf);
+ return color_pct(hpp, block_fmt->width, 100.0 * ratio);
}
static int64_t block_total_cycles_pct_sort(struct perf_hpp_fmt *fmt,
@@ -252,16 +256,13 @@ static int block_cycles_pct_entry(struct perf_hpp_fmt *fmt,
struct block_info *bi = he->block_info;
double ratio = 0.0;
u64 avg;
- char buf[16];
if (block_fmt->block_cycles && bi->num_aggr) {
avg = bi->cycles_aggr / bi->num_aggr;
ratio = (double)avg / (double)block_fmt->block_cycles;
}
- sprintf(buf, "%.2f%%", 100.0 * ratio);
-
- return scnprintf(hpp->buf, hpp->size, "%*s", block_fmt->width, buf);
+ return color_pct(hpp, block_fmt->width, 100.0 * ratio);
}
static int block_avg_cycles_entry(struct perf_hpp_fmt *fmt,
@@ -295,7 +296,8 @@ static int block_range_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
end_line = map__srcline(he->ms.map, bi->sym->start + bi->end,
he->ms.sym);
- if ((start_line != SRCLINE_UNKNOWN) && (end_line != SRCLINE_UNKNOWN)) {
+ if ((strncmp(start_line, SRCLINE_UNKNOWN, strlen(SRCLINE_UNKNOWN)) != 0) &&
+ (strncmp(end_line, SRCLINE_UNKNOWN, strlen(SRCLINE_UNKNOWN)) != 0)) {
scnprintf(buf, sizeof(buf), "[%s -> %s]",
start_line, end_line);
} else {
@@ -348,7 +350,7 @@ static void hpp_register(struct block_fmt *block_fmt, int idx,
switch (idx) {
case PERF_HPP_REPORT__BLOCK_TOTAL_CYCLES_PCT:
- fmt->entry = block_total_cycles_pct_entry;
+ fmt->color = block_total_cycles_pct_entry;
fmt->cmp = block_info__cmp;
fmt->sort = block_total_cycles_pct_sort;
break;
@@ -356,7 +358,7 @@ static void hpp_register(struct block_fmt *block_fmt, int idx,
fmt->entry = block_cycles_lbr_entry;
break;
case PERF_HPP_REPORT__BLOCK_CYCLES_PCT:
- fmt->entry = block_cycles_pct_entry;
+ fmt->color = block_cycles_pct_entry;
break;
case PERF_HPP_REPORT__BLOCK_AVG_CYCLES:
fmt->entry = block_avg_cycles_entry;
@@ -376,33 +378,41 @@ static void hpp_register(struct block_fmt *block_fmt, int idx,
}
static void register_block_columns(struct perf_hpp_list *hpp_list,
- struct block_fmt *block_fmts)
+ struct block_fmt *block_fmts,
+ int *block_hpps, int nr_hpps)
{
- for (int i = 0; i < PERF_HPP_REPORT__BLOCK_MAX_INDEX; i++)
- hpp_register(&block_fmts[i], i, hpp_list);
+ for (int i = 0; i < nr_hpps; i++)
+ hpp_register(&block_fmts[i], block_hpps[i], hpp_list);
}
-static void init_block_hist(struct block_hist *bh, struct block_fmt *block_fmts)
+static void init_block_hist(struct block_hist *bh, struct block_fmt *block_fmts,
+ int *block_hpps, int nr_hpps)
{
__hists__init(&bh->block_hists, &bh->block_list);
perf_hpp_list__init(&bh->block_list);
bh->block_list.nr_header_lines = 1;
- register_block_columns(&bh->block_list, block_fmts);
+ register_block_columns(&bh->block_list, block_fmts,
+ block_hpps, nr_hpps);
- perf_hpp_list__register_sort_field(&bh->block_list,
- &block_fmts[PERF_HPP_REPORT__BLOCK_TOTAL_CYCLES_PCT].fmt);
+ /* Sort by the first fmt */
+ perf_hpp_list__register_sort_field(&bh->block_list, &block_fmts[0].fmt);
}
-static void process_block_report(struct hists *hists,
- struct block_report *block_report,
- u64 total_cycles)
+static int process_block_report(struct hists *hists,
+ struct block_report *block_report,
+ u64 total_cycles, int *block_hpps,
+ int nr_hpps)
{
struct rb_node *next = rb_first_cached(&hists->entries);
struct block_hist *bh = &block_report->hist;
struct hist_entry *he;
- init_block_hist(bh, block_report->fmts);
+ if (nr_hpps > PERF_HPP_REPORT__BLOCK_MAX_INDEX)
+ return -1;
+
+ block_report->nr_fmts = nr_hpps;
+ init_block_hist(bh, block_report->fmts, block_hpps, nr_hpps);
while (next) {
he = rb_entry(next, struct hist_entry, rb_node);
@@ -411,16 +421,19 @@ static void process_block_report(struct hists *hists,
next = rb_next(&he->rb_node);
}
- for (int i = 0; i < PERF_HPP_REPORT__BLOCK_MAX_INDEX; i++) {
+ for (int i = 0; i < nr_hpps; i++) {
block_report->fmts[i].total_cycles = total_cycles;
block_report->fmts[i].block_cycles = block_report->cycles;
}
hists__output_resort(&bh->block_hists, NULL);
+ return 0;
}
struct block_report *block_info__create_report(struct evlist *evlist,
- u64 total_cycles)
+ u64 total_cycles,
+ int *block_hpps, int nr_hpps,
+ int *nr_reps)
{
struct block_report *block_reports;
int nr_hists = evlist->core.nr_entries, i = 0;
@@ -433,13 +446,23 @@ struct block_report *block_info__create_report(struct evlist *evlist,
evlist__for_each_entry(evlist, pos) {
struct hists *hists = evsel__hists(pos);
- process_block_report(hists, &block_reports[i], total_cycles);
+ process_block_report(hists, &block_reports[i], total_cycles,
+ block_hpps, nr_hpps);
i++;
}
+ *nr_reps = nr_hists;
return block_reports;
}
+void block_info__free_report(struct block_report *reps, int nr_reps)
+{
+ for (int i = 0; i < nr_reps; i++)
+ hists__delete_entries(&reps[i].hist.block_hists);
+
+ free(reps);
+}
+
int report__browse_block_hists(struct block_hist *bh, float min_percent,
struct evsel *evsel, struct perf_env *env,
struct annotation_options *annotation_opts)
@@ -451,13 +474,11 @@ int report__browse_block_hists(struct block_hist *bh, float min_percent,
symbol_conf.report_individual_block = true;
hists__fprintf(&bh->block_hists, true, 0, 0, min_percent,
stdout, true);
- hists__delete_entries(&bh->block_hists);
return 0;
case 1:
symbol_conf.report_individual_block = true;
ret = block_hists_tui_browse(bh, evsel, min_percent,
env, annotation_opts);
- hists__delete_entries(&bh->block_hists);
return ret;
default:
return -1;
diff --git a/tools/perf/util/block-info.h b/tools/perf/util/block-info.h
index bef0d75e9819..42e9dcc4cf0a 100644
--- a/tools/perf/util/block-info.h
+++ b/tools/perf/util/block-info.h
@@ -45,6 +45,7 @@ struct block_report {
struct block_hist hist;
u64 cycles;
struct block_fmt fmts[PERF_HPP_REPORT__BLOCK_MAX_INDEX];
+ int nr_fmts;
};
struct block_hist;
@@ -61,6 +62,8 @@ static inline void __block_info__zput(struct block_info **bi)
#define block_info__zput(bi) __block_info__zput(&bi)
+int64_t __block_info__cmp(struct hist_entry *left, struct hist_entry *right);
+
int64_t block_info__cmp(struct perf_hpp_fmt *fmt __maybe_unused,
struct hist_entry *left, struct hist_entry *right);
@@ -68,7 +71,11 @@ int block_info__process_sym(struct hist_entry *he, struct block_hist *bh,
u64 *block_cycles_aggr, u64 total_cycles);
struct block_report *block_info__create_report(struct evlist *evlist,
- u64 total_cycles);
+ u64 total_cycles,
+ int *block_hpps, int nr_hpps,
+ int *nr_reps);
+
+void block_info__free_report(struct block_report *reps, int nr_reps);
int report__browse_block_hists(struct block_hist *bh, float min_percent,
struct evsel *evsel, struct perf_env *env,
diff --git a/tools/perf/util/branch.h b/tools/perf/util/branch.h
index 88e00d268f6f..154a05cd03af 100644
--- a/tools/perf/util/branch.h
+++ b/tools/perf/util/branch.h
@@ -12,6 +12,7 @@
#include <linux/stddef.h>
#include <linux/perf_event.h>
#include <linux/types.h>
+#include "event.h"
struct branch_flags {
u64 mispred:1;
@@ -39,9 +40,30 @@ struct branch_entry {
struct branch_stack {
u64 nr;
+ u64 hw_idx;
struct branch_entry entries[0];
};
+/*
+ * The hw_idx is only available when PERF_SAMPLE_BRANCH_HW_INDEX is applied.
+ * Otherwise, the output format of a sample with branch stack is
+ * struct branch_stack {
+ * u64 nr;
+ * struct branch_entry entries[0];
+ * }
+ * Check whether the hw_idx is available,
+ * and return the corresponding pointer of entries[0].
+ */
+static inline struct branch_entry *perf_sample__branch_entries(struct perf_sample *sample)
+{
+ u64 *entry = (u64 *)sample->branch_stack;
+
+ entry++;
+ if (sample->no_hw_idx)
+ return (struct branch_entry *)entry;
+ return (struct branch_entry *)(++entry);
+}
+
struct branch_type_stat {
bool branch_to;
u64 counts[PERF_BR_MAX];
diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
index 4881d4af3381..5bc9d3b01bd9 100644
--- a/tools/perf/util/cgroup.c
+++ b/tools/perf/util/cgroup.c
@@ -3,75 +3,16 @@
#include "evsel.h"
#include "cgroup.h"
#include "evlist.h"
-#include <linux/stringify.h>
#include <linux/zalloc.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <fcntl.h>
#include <stdlib.h>
#include <string.h>
+#include <api/fs/fs.h>
int nr_cgroups;
-static int
-cgroupfs_find_mountpoint(char *buf, size_t maxlen)
-{
- FILE *fp;
- char mountpoint[PATH_MAX + 1], tokens[PATH_MAX + 1], type[PATH_MAX + 1];
- char path_v1[PATH_MAX + 1], path_v2[PATH_MAX + 2], *path;
- char *token, *saved_ptr = NULL;
-
- fp = fopen("/proc/mounts", "r");
- if (!fp)
- return -1;
-
- /*
- * in order to handle split hierarchy, we need to scan /proc/mounts
- * and inspect every cgroupfs mount point to find one that has
- * perf_event subsystem
- */
- path_v1[0] = '\0';
- path_v2[0] = '\0';
-
- while (fscanf(fp, "%*s %"__stringify(PATH_MAX)"s %"__stringify(PATH_MAX)"s %"
- __stringify(PATH_MAX)"s %*d %*d\n",
- mountpoint, type, tokens) == 3) {
-
- if (!path_v1[0] && !strcmp(type, "cgroup")) {
-
- token = strtok_r(tokens, ",", &saved_ptr);
-
- while (token != NULL) {
- if (!strcmp(token, "perf_event")) {
- strcpy(path_v1, mountpoint);
- break;
- }
- token = strtok_r(NULL, ",", &saved_ptr);
- }
- }
-
- if (!path_v2[0] && !strcmp(type, "cgroup2"))
- strcpy(path_v2, mountpoint);
-
- if (path_v1[0] && path_v2[0])
- break;
- }
- fclose(fp);
-
- if (path_v1[0])
- path = path_v1;
- else if (path_v2[0])
- path = path_v2;
- else
- return -1;
-
- if (strlen(path) < maxlen) {
- strcpy(buf, path);
- return 0;
- }
- return -1;
-}
-
static int open_cgroup(const char *name)
{
char path[PATH_MAX + 1];
@@ -79,7 +20,7 @@ static int open_cgroup(const char *name)
int fd;
- if (cgroupfs_find_mountpoint(mnt, PATH_MAX + 1))
+ if (cgroupfs_find_mountpoint(mnt, PATH_MAX + 1, "perf_event"))
return -1;
scnprintf(path, PATH_MAX, "%s/%s", mnt, name);
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index 0bc9c4d7fdc5..ef38eba56ed0 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -374,6 +374,18 @@ int perf_config_int(int *dest, const char *name, const char *value)
return 0;
}
+int perf_config_u8(u8 *dest, const char *name, const char *value)
+{
+ long ret = 0;
+
+ if (!perf_parse_long(value, &ret)) {
+ bad_config(name);
+ return -1;
+ }
+ *dest = ret;
+ return 0;
+}
+
static int perf_config_bool_or_int(const char *name, const char *value, int *is_bool)
{
int ret;
diff --git a/tools/perf/util/config.h b/tools/perf/util/config.h
index bd0a5897c76a..c10b66dde2f3 100644
--- a/tools/perf/util/config.h
+++ b/tools/perf/util/config.h
@@ -29,6 +29,7 @@ typedef int (*config_fn_t)(const char *, const char *, void *);
int perf_default_config(const char *, const char *, void *);
int perf_config(config_fn_t fn, void *);
int perf_config_int(int *dest, const char *, const char *);
+int perf_config_u8(u8 *dest, const char *name, const char *value);
int perf_config_u64(u64 *dest, const char *, const char *);
int perf_config_bool(const char *, const char *);
int config_error_nonbool(const char *);
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 5471045ebf5c..62d2f9b9ce1b 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -363,6 +363,23 @@ struct cs_etm_packet_queue
return NULL;
}
+static void cs_etm__packet_swap(struct cs_etm_auxtrace *etm,
+ struct cs_etm_traceid_queue *tidq)
+{
+ struct cs_etm_packet *tmp;
+
+ if (etm->sample_branches || etm->synth_opts.last_branch ||
+ etm->sample_instructions) {
+ /*
+ * Swap PACKET with PREV_PACKET: PACKET becomes PREV_PACKET for
+ * the next incoming packet.
+ */
+ tmp = tidq->packet;
+ tidq->packet = tidq->prev_packet;
+ tidq->prev_packet = tmp;
+ }
+}
+
static void cs_etm__packet_dump(const char *pkt_string)
{
const char *color = PERF_COLOR_BLUE;
@@ -945,7 +962,7 @@ static inline u64 cs_etm__instr_addr(struct cs_etm_queue *etmq,
if (packet->isa == CS_ETM_ISA_T32) {
u64 addr = packet->start_addr;
- while (offset > 0) {
+ while (offset) {
addr += cs_etm__t32_instr_size(etmq,
trace_chan_id, addr);
offset--;
@@ -1134,10 +1151,8 @@ static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq,
cs_etm__copy_insn(etmq, tidq->trace_chan_id, tidq->packet, &sample);
- if (etm->synth_opts.last_branch) {
- cs_etm__copy_last_branch_rb(etmq, tidq);
+ if (etm->synth_opts.last_branch)
sample.branch_stack = tidq->last_branch;
- }
if (etm->synth_opts.inject) {
ret = cs_etm__inject_event(event, &sample,
@@ -1153,9 +1168,6 @@ static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq,
"CS ETM Trace: failed to deliver instruction event, error %d\n",
ret);
- if (etm->synth_opts.last_branch)
- cs_etm__reset_last_branch_rb(tidq);
-
return ret;
}
@@ -1172,6 +1184,7 @@ static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq,
union perf_event *event = tidq->event_buf;
struct dummy_branch_stack {
u64 nr;
+ u64 hw_idx;
struct branch_entry entries;
} dummy_bs;
u64 ip;
@@ -1202,6 +1215,7 @@ static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq,
if (etm->synth_opts.last_branch) {
dummy_bs = (struct dummy_branch_stack){
.nr = 1,
+ .hw_idx = -1ULL,
.entries = {
.from = sample.ip,
.to = sample.addr,
@@ -1340,12 +1354,14 @@ static int cs_etm__sample(struct cs_etm_queue *etmq,
struct cs_etm_traceid_queue *tidq)
{
struct cs_etm_auxtrace *etm = etmq->etm;
- struct cs_etm_packet *tmp;
int ret;
u8 trace_chan_id = tidq->trace_chan_id;
- u64 instrs_executed = tidq->packet->instr_count;
+ u64 instrs_prev;
+
+ /* Get instructions remainder from previous packet */
+ instrs_prev = tidq->period_instructions;
- tidq->period_instructions += instrs_executed;
+ tidq->period_instructions += tidq->packet->instr_count;
/*
* Record a branch when the last instruction in
@@ -1363,26 +1379,80 @@ static int cs_etm__sample(struct cs_etm_queue *etmq,
* TODO: allow period to be defined in cycles and clock time
*/
- /* Get number of instructions executed after the sample point */
- u64 instrs_over = tidq->period_instructions -
- etm->instructions_sample_period;
+ /*
+ * Below diagram demonstrates the instruction samples
+ * generation flows:
+ *
+ * Instrs Instrs Instrs Instrs
+ * Sample(n) Sample(n+1) Sample(n+2) Sample(n+3)
+ * | | | |
+ * V V V V
+ * --------------------------------------------------
+ * ^ ^
+ * | |
+ * Period Period
+ * instructions(Pi) instructions(Pi')
+ *
+ * | |
+ * \---------------- -----------------/
+ * V
+ * tidq->packet->instr_count
+ *
+ * Instrs Sample(n...) are the synthesised samples occurring
+ * every etm->instructions_sample_period instructions - as
+ * defined on the perf command line. Sample(n) is being the
+ * last sample before the current etm packet, n+1 to n+3
+ * samples are generated from the current etm packet.
+ *
+ * tidq->packet->instr_count represents the number of
+ * instructions in the current etm packet.
+ *
+ * Period instructions (Pi) contains the the number of
+ * instructions executed after the sample point(n) from the
+ * previous etm packet. This will always be less than
+ * etm->instructions_sample_period.
+ *
+ * When generate new samples, it combines with two parts
+ * instructions, one is the tail of the old packet and another
+ * is the head of the new coming packet, to generate
+ * sample(n+1); sample(n+2) and sample(n+3) consume the
+ * instructions with sample period. After sample(n+3), the rest
+ * instructions will be used by later packet and it is assigned
+ * to tidq->period_instructions for next round calculation.
+ */
/*
- * Calculate the address of the sampled instruction (-1 as
- * sample is reported as though instruction has just been
- * executed, but PC has not advanced to next instruction)
+ * Get the initial offset into the current packet instructions;
+ * entry conditions ensure that instrs_prev is less than
+ * etm->instructions_sample_period.
*/
- u64 offset = (instrs_executed - instrs_over - 1);
- u64 addr = cs_etm__instr_addr(etmq, trace_chan_id,
- tidq->packet, offset);
+ u64 offset = etm->instructions_sample_period - instrs_prev;
+ u64 addr;
- ret = cs_etm__synth_instruction_sample(
- etmq, tidq, addr, etm->instructions_sample_period);
- if (ret)
- return ret;
+ /* Prepare last branches for instruction sample */
+ if (etm->synth_opts.last_branch)
+ cs_etm__copy_last_branch_rb(etmq, tidq);
- /* Carry remaining instructions into next sample period */
- tidq->period_instructions = instrs_over;
+ while (tidq->period_instructions >=
+ etm->instructions_sample_period) {
+ /*
+ * Calculate the address of the sampled instruction (-1
+ * as sample is reported as though instruction has just
+ * been executed, but PC has not advanced to next
+ * instruction)
+ */
+ addr = cs_etm__instr_addr(etmq, trace_chan_id,
+ tidq->packet, offset - 1);
+ ret = cs_etm__synth_instruction_sample(
+ etmq, tidq, addr,
+ etm->instructions_sample_period);
+ if (ret)
+ return ret;
+
+ offset += etm->instructions_sample_period;
+ tidq->period_instructions -=
+ etm->instructions_sample_period;
+ }
}
if (etm->sample_branches) {
@@ -1404,15 +1474,7 @@ static int cs_etm__sample(struct cs_etm_queue *etmq,
}
}
- if (etm->sample_branches || etm->synth_opts.last_branch) {
- /*
- * Swap PACKET with PREV_PACKET: PACKET becomes PREV_PACKET for
- * the next incoming packet.
- */
- tmp = tidq->packet;
- tidq->packet = tidq->prev_packet;
- tidq->prev_packet = tmp;
- }
+ cs_etm__packet_swap(etm, tidq);
return 0;
}
@@ -1441,7 +1503,6 @@ static int cs_etm__flush(struct cs_etm_queue *etmq,
{
int err = 0;
struct cs_etm_auxtrace *etm = etmq->etm;
- struct cs_etm_packet *tmp;
/* Handle start tracing packet */
if (tidq->prev_packet->sample_type == CS_ETM_EMPTY)
@@ -1449,6 +1510,11 @@ static int cs_etm__flush(struct cs_etm_queue *etmq,
if (etmq->etm->synth_opts.last_branch &&
tidq->prev_packet->sample_type == CS_ETM_RANGE) {
+ u64 addr;
+
+ /* Prepare last branches for instruction sample */
+ cs_etm__copy_last_branch_rb(etmq, tidq);
+
/*
* Generate a last branch event for the branches left in the
* circular buffer at the end of the trace.
@@ -1456,7 +1522,7 @@ static int cs_etm__flush(struct cs_etm_queue *etmq,
* Use the address of the end of the last reported execution
* range
*/
- u64 addr = cs_etm__last_executed_instr(tidq->prev_packet);
+ addr = cs_etm__last_executed_instr(tidq->prev_packet);
err = cs_etm__synth_instruction_sample(
etmq, tidq, addr,
@@ -1476,15 +1542,11 @@ static int cs_etm__flush(struct cs_etm_queue *etmq,
}
swap_packet:
- if (etm->sample_branches || etm->synth_opts.last_branch) {
- /*
- * Swap PACKET with PREV_PACKET: PACKET becomes PREV_PACKET for
- * the next incoming packet.
- */
- tmp = tidq->packet;
- tidq->packet = tidq->prev_packet;
- tidq->prev_packet = tmp;
- }
+ cs_etm__packet_swap(etm, tidq);
+
+ /* Reset last branches after flush the trace */
+ if (etm->synth_opts.last_branch)
+ cs_etm__reset_last_branch_rb(tidq);
return err;
}
@@ -1505,11 +1567,16 @@ static int cs_etm__end_block(struct cs_etm_queue *etmq,
*/
if (etmq->etm->synth_opts.last_branch &&
tidq->prev_packet->sample_type == CS_ETM_RANGE) {
+ u64 addr;
+
+ /* Prepare last branches for instruction sample */
+ cs_etm__copy_last_branch_rb(etmq, tidq);
+
/*
* Use the address of the end of the last reported execution
* range.
*/
- u64 addr = cs_etm__last_executed_instr(tidq->prev_packet);
+ addr = cs_etm__last_executed_instr(tidq->prev_packet);
err = cs_etm__synth_instruction_sample(
etmq, tidq, addr,
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index 6242a9215df7..4154f944f474 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -343,11 +343,11 @@ static const char *normalize_arch(char *arch)
const char *perf_env__arch(struct perf_env *env)
{
- struct utsname uts;
char *arch_name;
if (!env || !env->arch) { /* Assume local operation */
- if (uname(&uts) < 0)
+ static struct utsname uts = { .machine[0] = '\0', };
+ if (uts.machine[0] == '\0' && uname(&uts) < 0)
return NULL;
arch_name = uts.machine;
} else
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 85223159737c..3cda40a2fafc 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -139,6 +139,7 @@ struct perf_sample {
u16 insn_len;
u8 cpumode;
u16 misc;
+ bool no_hw_idx; /* No hw_idx collected in branch_stack */
char insn[MAX_INSN];
void *raw_data;
struct ip_callchain *callchain;
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index c8dc4450884c..816d930d774e 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -712,7 +712,8 @@ static void __perf_evsel__config_callchain(struct evsel *evsel,
attr->branch_sample_type = PERF_SAMPLE_BRANCH_USER |
PERF_SAMPLE_BRANCH_CALL_STACK |
PERF_SAMPLE_BRANCH_NO_CYCLES |
- PERF_SAMPLE_BRANCH_NO_FLAGS;
+ PERF_SAMPLE_BRANCH_NO_FLAGS |
+ PERF_SAMPLE_BRANCH_HW_INDEX;
}
} else
pr_warning("Cannot use LBR callstack with branch stack. "
@@ -763,7 +764,8 @@ perf_evsel__reset_callgraph(struct evsel *evsel,
if (param->record_mode == CALLCHAIN_LBR) {
perf_evsel__reset_sample_bit(evsel, BRANCH_STACK);
attr->branch_sample_type &= ~(PERF_SAMPLE_BRANCH_USER |
- PERF_SAMPLE_BRANCH_CALL_STACK);
+ PERF_SAMPLE_BRANCH_CALL_STACK |
+ PERF_SAMPLE_BRANCH_HW_INDEX);
}
if (param->record_mode == CALLCHAIN_DWARF) {
perf_evsel__reset_sample_bit(evsel, REGS_USER);
@@ -1673,6 +1675,8 @@ fallback_missing_features:
evsel->core.attr.ksymbol = 0;
if (perf_missing_features.bpf)
evsel->core.attr.bpf_event = 0;
+ if (perf_missing_features.branch_hw_idx)
+ evsel->core.attr.branch_sample_type &= ~PERF_SAMPLE_BRANCH_HW_INDEX;
retry_sample_id:
if (perf_missing_features.sample_id_all)
evsel->core.attr.sample_id_all = 0;
@@ -1784,7 +1788,12 @@ try_fallback:
* Must probe features in the order they were added to the
* perf_event_attr interface.
*/
- if (!perf_missing_features.aux_output && evsel->core.attr.aux_output) {
+ if (!perf_missing_features.branch_hw_idx &&
+ (evsel->core.attr.branch_sample_type & PERF_SAMPLE_BRANCH_HW_INDEX)) {
+ perf_missing_features.branch_hw_idx = true;
+ pr_debug2("switching off branch HW index support\n");
+ goto fallback_missing_features;
+ } else if (!perf_missing_features.aux_output && evsel->core.attr.aux_output) {
perf_missing_features.aux_output = true;
pr_debug2_peo("Kernel has no attr.aux_output support, bailing out\n");
goto out_close;
@@ -2169,7 +2178,12 @@ int perf_evsel__parse_sample(struct evsel *evsel, union perf_event *event,
if (data->branch_stack->nr > max_branch_nr)
return -EFAULT;
+
sz = data->branch_stack->nr * sizeof(struct branch_entry);
+ if (perf_evsel__has_branch_hw_idx(evsel))
+ sz += sizeof(u64);
+ else
+ data->no_hw_idx = true;
OVERFLOW_CHECK(array, sz, max_size);
array = (void *)array + sz;
}
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index dc14f4a823cd..33804740e2ca 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -119,6 +119,7 @@ struct perf_missing_features {
bool ksymbol;
bool bpf;
bool aux_output;
+ bool branch_hw_idx;
};
extern struct perf_missing_features perf_missing_features;
@@ -389,6 +390,11 @@ static inline bool perf_evsel__has_branch_callstack(const struct evsel *evsel)
return evsel->core.attr.branch_sample_type & PERF_SAMPLE_BRANCH_CALL_STACK;
}
+static inline bool perf_evsel__has_branch_hw_idx(const struct evsel *evsel)
+{
+ return evsel->core.attr.branch_sample_type & PERF_SAMPLE_BRANCH_HW_INDEX;
+}
+
static inline bool evsel__has_callchain(const struct evsel *evsel)
{
return (evsel->core.attr.sample_type & PERF_SAMPLE_CALLCHAIN) != 0;
diff --git a/tools/perf/util/expr.c b/tools/perf/util/expr.c
new file mode 100644
index 000000000000..fd192ddf93c1
--- /dev/null
+++ b/tools/perf/util/expr.c
@@ -0,0 +1,112 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stdbool.h>
+#include <assert.h>
+#include "expr.h"
+#include "expr-bison.h"
+#define YY_EXTRA_TYPE int
+#include "expr-flex.h"
+
+#ifdef PARSER_DEBUG
+extern int expr_debug;
+#endif
+
+/* Caller must make sure id is allocated */
+void expr__add_id(struct parse_ctx *ctx, const char *name, double val)
+{
+ int idx;
+
+ assert(ctx->num_ids < MAX_PARSE_ID);
+ idx = ctx->num_ids++;
+ ctx->ids[idx].name = name;
+ ctx->ids[idx].val = val;
+}
+
+void expr__ctx_init(struct parse_ctx *ctx)
+{
+ ctx->num_ids = 0;
+}
+
+static int
+__expr__parse(double *val, struct parse_ctx *ctx, const char *expr,
+ int start)
+{
+ YY_BUFFER_STATE buffer;
+ void *scanner;
+ int ret;
+
+ ret = expr_lex_init_extra(start, &scanner);
+ if (ret)
+ return ret;
+
+ buffer = expr__scan_string(expr, scanner);
+
+#ifdef PARSER_DEBUG
+ expr_debug = 1;
+#endif
+
+ ret = expr_parse(val, ctx, scanner);
+
+ expr__flush_buffer(buffer, scanner);
+ expr__delete_buffer(buffer, scanner);
+ expr_lex_destroy(scanner);
+ return ret;
+}
+
+int expr__parse(double *final_val, struct parse_ctx *ctx, const char *expr)
+{
+ return __expr__parse(final_val, ctx, expr, EXPR_PARSE) ? -1 : 0;
+}
+
+static bool
+already_seen(const char *val, const char *one, const char **other,
+ int num_other)
+{
+ int i;
+
+ if (one && !strcasecmp(one, val))
+ return true;
+ for (i = 0; i < num_other; i++)
+ if (!strcasecmp(other[i], val))
+ return true;
+ return false;
+}
+
+int expr__find_other(const char *expr, const char *one, const char ***other,
+ int *num_other)
+{
+ int err, i = 0, j = 0;
+ struct parse_ctx ctx;
+
+ expr__ctx_init(&ctx);
+ err = __expr__parse(NULL, &ctx, expr, EXPR_OTHER);
+ if (err)
+ return -1;
+
+ *other = malloc((ctx.num_ids + 1) * sizeof(char *));
+ if (!*other)
+ return -ENOMEM;
+
+ for (i = 0, j = 0; i < ctx.num_ids; i++) {
+ const char *str = ctx.ids[i].name;
+
+ if (already_seen(str, one, *other, j))
+ continue;
+
+ str = strdup(str);
+ if (!str)
+ goto out;
+ (*other)[j++] = str;
+ }
+ (*other)[j] = NULL;
+
+out:
+ if (i != ctx.num_ids) {
+ while (--j)
+ free((char *) (*other)[i]);
+ free(*other);
+ err = -1;
+ }
+
+ *num_other = j;
+ return err;
+}
diff --git a/tools/perf/util/expr.h b/tools/perf/util/expr.h
index 046160831f90..9377538f4097 100644
--- a/tools/perf/util/expr.h
+++ b/tools/perf/util/expr.h
@@ -2,7 +2,7 @@
#ifndef PARSE_CTX_H
#define PARSE_CTX_H 1
-#define EXPR_MAX_OTHER 15
+#define EXPR_MAX_OTHER 20
#define MAX_PARSE_ID EXPR_MAX_OTHER
struct parse_id {
@@ -17,10 +17,8 @@ struct parse_ctx {
void expr__ctx_init(struct parse_ctx *ctx);
void expr__add_id(struct parse_ctx *ctx, const char *id, double val);
-#ifndef IN_EXPR_Y
-int expr__parse(double *final_val, struct parse_ctx *ctx, const char **pp);
-#endif
-int expr__find_other(const char *p, const char *one, const char ***other,
+int expr__parse(double *final_val, struct parse_ctx *ctx, const char *expr);
+int expr__find_other(const char *expr, const char *one, const char ***other,
int *num_other);
#endif
diff --git a/tools/perf/util/expr.l b/tools/perf/util/expr.l
new file mode 100644
index 000000000000..eaad29243c23
--- /dev/null
+++ b/tools/perf/util/expr.l
@@ -0,0 +1,114 @@
+%option prefix="expr_"
+%option reentrant
+%option bison-bridge
+
+%{
+#include <linux/compiler.h>
+#include "expr.h"
+#include "expr-bison.h"
+
+char *expr_get_text(yyscan_t yyscanner);
+YYSTYPE *expr_get_lval(yyscan_t yyscanner);
+
+static int __value(YYSTYPE *yylval, char *str, int base, int token)
+{
+ u64 num;
+
+ errno = 0;
+ num = strtoull(str, NULL, base);
+ if (errno)
+ return EXPR_ERROR;
+
+ yylval->num = num;
+ return token;
+}
+
+static int value(yyscan_t scanner, int base)
+{
+ YYSTYPE *yylval = expr_get_lval(scanner);
+ char *text = expr_get_text(scanner);
+
+ return __value(yylval, text, base, NUMBER);
+}
+
+/*
+ * Allow @ instead of / to be able to specify pmu/event/ without
+ * conflicts with normal division.
+ */
+static char *normalize(char *str)
+{
+ char *ret = str;
+ char *dst = str;
+
+ while (*str) {
+ if (*str == '@')
+ *dst++ = '/';
+ else if (*str == '\\')
+ *dst++ = *++str;
+ else
+ *dst++ = *str;
+ str++;
+ }
+
+ *dst = 0x0;
+ return ret;
+}
+
+static int str(yyscan_t scanner, int token)
+{
+ YYSTYPE *yylval = expr_get_lval(scanner);
+ char *text = expr_get_text(scanner);
+
+ yylval->str = normalize(strdup(text));
+ if (!yylval->str)
+ return EXPR_ERROR;
+
+ yylval->str = normalize(yylval->str);
+ return token;
+}
+%}
+
+number [0-9]+
+
+sch [-,=]
+spec \\{sch}
+sym [0-9a-zA-Z_\.:@]+
+symbol {spec}*{sym}*{spec}*{sym}*
+
+%%
+ {
+ int start_token;
+
+ start_token = expr_get_extra(yyscanner);
+
+ if (start_token) {
+ expr_set_extra(NULL, yyscanner);
+ return start_token;
+ }
+ }
+
+max { return MAX; }
+min { return MIN; }
+if { return IF; }
+else { return ELSE; }
+#smt_on { return SMT_ON; }
+{number} { return value(yyscanner, 10); }
+{symbol} { return str(yyscanner, ID); }
+"|" { return '|'; }
+"^" { return '^'; }
+"&" { return '&'; }
+"-" { return '-'; }
+"+" { return '+'; }
+"*" { return '*'; }
+"/" { return '/'; }
+"%" { return '%'; }
+"(" { return '('; }
+")" { return ')'; }
+"," { return ','; }
+. { }
+%%
+
+int expr_wrap(void *scanner __maybe_unused)
+{
+ return 1;
+}
diff --git a/tools/perf/util/expr.y b/tools/perf/util/expr.y
index 7d226241f1d7..4720cbe79357 100644
--- a/tools/perf/util/expr.y
+++ b/tools/perf/util/expr.y
@@ -1,31 +1,32 @@
/* Simple expression parser */
%{
+#define YYDEBUG 1
+#include <stdio.h>
#include "util.h"
#include "util/debug.h"
#include <stdlib.h> // strtod()
#define IN_EXPR_Y 1
#include "expr.h"
#include "smt.h"
-#include <assert.h>
#include <string.h>
-#define MAXIDLEN 256
%}
%define api.pure full
%parse-param { double *final_val }
%parse-param { struct parse_ctx *ctx }
-%parse-param { const char **pp }
-%lex-param { const char **pp }
+%parse-param {void *scanner}
+%lex-param {void* scanner}
%union {
- double num;
- char id[MAXIDLEN+1];
+ double num;
+ char *str;
}
+%token EXPR_PARSE EXPR_OTHER EXPR_ERROR
%token <num> NUMBER
-%token <id> ID
+%token <str> ID
%token MIN MAX IF ELSE SMT_ON
%left MIN MAX IF
%left '|'
@@ -37,11 +38,9 @@
%type <num> expr if_expr
%{
-static int expr__lex(YYSTYPE *res, const char **pp);
-
-static void expr__error(double *final_val __maybe_unused,
+static void expr_error(double *final_val __maybe_unused,
struct parse_ctx *ctx __maybe_unused,
- const char **pp __maybe_unused,
+ void *scanner,
const char *s)
{
pr_debug("%s\n", s);
@@ -63,6 +62,27 @@ static int lookup_id(struct parse_ctx *ctx, char *id, double *val)
%}
%%
+start:
+EXPR_PARSE all_expr
+|
+EXPR_OTHER all_other
+
+all_other: all_other other
+|
+
+other: ID
+{
+ if (ctx->num_ids + 1 >= EXPR_MAX_OTHER) {
+ pr_err("failed: way too many variables");
+ YYABORT;
+ }
+
+ ctx->ids[ctx->num_ids++].name = $1;
+}
+|
+MIN | MAX | IF | ELSE | SMT_ON | NUMBER | '|' | '^' | '&' | '-' | '+' | '*' | '/' | '%' | '(' | ')'
+
+
all_expr: if_expr { *final_val = $1; }
;
@@ -93,146 +113,3 @@ expr: NUMBER
;
%%
-
-static int expr__symbol(YYSTYPE *res, const char *p, const char **pp)
-{
- char *dst = res->id;
- const char *s = p;
-
- if (*p == '#')
- *dst++ = *p++;
-
- while (isalnum(*p) || *p == '_' || *p == '.' || *p == ':' || *p == '@' || *p == '\\') {
- if (p - s >= MAXIDLEN)
- return -1;
- /*
- * Allow @ instead of / to be able to specify pmu/event/ without
- * conflicts with normal division.
- */
- if (*p == '@')
- *dst++ = '/';
- else if (*p == '\\')
- *dst++ = *++p;
- else
- *dst++ = *p;
- p++;
- }
- *dst = 0;
- *pp = p;
- dst = res->id;
- switch (dst[0]) {
- case 'm':
- if (!strcmp(dst, "min"))
- return MIN;
- if (!strcmp(dst, "max"))
- return MAX;
- break;
- case 'i':
- if (!strcmp(dst, "if"))
- return IF;
- break;
- case 'e':
- if (!strcmp(dst, "else"))
- return ELSE;
- break;
- case '#':
- if (!strcasecmp(dst, "#smt_on"))
- return SMT_ON;
- break;
- }
- return ID;
-}
-
-static int expr__lex(YYSTYPE *res, const char **pp)
-{
- int tok;
- const char *s;
- const char *p = *pp;
-
- while (isspace(*p))
- p++;
- s = p;
- switch (*p++) {
- case '#':
- case 'a' ... 'z':
- case 'A' ... 'Z':
- return expr__symbol(res, p - 1, pp);
- case '0' ... '9': case '.':
- res->num = strtod(s, (char **)&p);
- tok = NUMBER;
- break;
- default:
- tok = *s;
- break;
- }
- *pp = p;
- return tok;
-}
-
-/* Caller must make sure id is allocated */
-void expr__add_id(struct parse_ctx *ctx, const char *name, double val)
-{
- int idx;
- assert(ctx->num_ids < MAX_PARSE_ID);
- idx = ctx->num_ids++;
- ctx->ids[idx].name = name;
- ctx->ids[idx].val = val;
-}
-
-void expr__ctx_init(struct parse_ctx *ctx)
-{
- ctx->num_ids = 0;
-}
-
-static bool already_seen(const char *val, const char *one, const char **other,
- int num_other)
-{
- int i;
-
- if (one && !strcasecmp(one, val))
- return true;
- for (i = 0; i < num_other; i++)
- if (!strcasecmp(other[i], val))
- return true;
- return false;
-}
-
-int expr__find_other(const char *p, const char *one, const char ***other,
- int *num_otherp)
-{
- const char *orig = p;
- int err = -1;
- int num_other;
-
- *other = malloc((EXPR_MAX_OTHER + 1) * sizeof(char *));
- if (!*other)
- return -1;
-
- num_other = 0;
- for (;;) {
- YYSTYPE val;
- int tok = expr__lex(&val, &p);
- if (tok == 0) {
- err = 0;
- break;
- }
- if (tok == ID && !already_seen(val.id, one, *other, num_other)) {
- if (num_other >= EXPR_MAX_OTHER - 1) {
- pr_debug("Too many extra events in %s\n", orig);
- break;
- }
- (*other)[num_other] = strdup(val.id);
- if (!(*other)[num_other])
- return -1;
- num_other++;
- }
- }
- (*other)[num_other] = NULL;
- *num_otherp = num_other;
- if (err) {
- *num_otherp = 0;
- free(*other);
- *other = NULL;
- }
- return err;
-}
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 4246e7447e54..acbd046bf95c 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1590,6 +1590,40 @@ static void free_event_desc(struct evsel *events)
free(events);
}
+static bool perf_attr_check(struct perf_event_attr *attr)
+{
+ if (attr->__reserved_1 || attr->__reserved_2 || attr->__reserved_3) {
+ pr_warning("Reserved bits are set unexpectedly. "
+ "Please update perf tool.\n");
+ return false;
+ }
+
+ if (attr->sample_type & ~(PERF_SAMPLE_MAX-1)) {
+ pr_warning("Unknown sample type (0x%llx) is detected. "
+ "Please update perf tool.\n",
+ attr->sample_type);
+ return false;
+ }
+
+ if (attr->read_format & ~(PERF_FORMAT_MAX-1)) {
+ pr_warning("Unknown read format (0x%llx) is detected. "
+ "Please update perf tool.\n",
+ attr->read_format);
+ return false;
+ }
+
+ if ((attr->sample_type & PERF_SAMPLE_BRANCH_STACK) &&
+ (attr->branch_sample_type & ~(PERF_SAMPLE_BRANCH_MAX-1))) {
+ pr_warning("Unknown branch sample type (0x%llx) is detected. "
+ "Please update perf tool.\n",
+ attr->branch_sample_type);
+
+ return false;
+ }
+
+ return true;
+}
+
static struct evsel *read_event_desc(struct feat_fd *ff)
{
struct evsel *evsel, *events = NULL;
@@ -1634,6 +1668,9 @@ static struct evsel *read_event_desc(struct feat_fd *ff)
memcpy(&evsel->core.attr, buf, msz);
+ if (!perf_attr_check(&evsel->core.attr))
+ goto error;
+
if (do_read_u32(ff, &nr))
goto error;
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index ca5a8f4d007e..e74a5acf66d9 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -2584,9 +2584,10 @@ void hist__account_cycles(struct branch_stack *bs, struct addr_location *al,
u64 *total_cycles)
{
struct branch_info *bi;
+ struct branch_entry *entries = perf_sample__branch_entries(sample);
/* If we have branch cycles always annotate them. */
- if (bs && bs->nr && bs->entries[0].flags.cycles) {
+ if (bs && bs->nr && entries[0].flags.cycles) {
int i;
bi = sample__resolve_bstack(sample, al);
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 33cf8928cf05..23c8289c2472 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -1295,6 +1295,7 @@ static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq)
struct perf_sample sample = { .ip = 0, };
struct dummy_branch_stack {
u64 nr;
+ u64 hw_idx;
struct branch_entry entries;
} dummy_bs;
@@ -1316,6 +1317,7 @@ static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq)
if (pt->synth_opts.last_branch && sort__mode == SORT_MODE__BRANCH) {
dummy_bs = (struct dummy_branch_stack){
.nr = 1,
+ .hw_idx = -1ULL,
.entries = {
.from = sample.ip,
.to = sample.addr,
diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c
index eae47c2509eb..dbdffb6673fe 100644
--- a/tools/perf/util/llvm-utils.c
+++ b/tools/perf/util/llvm-utils.c
@@ -265,6 +265,8 @@ static int detect_kbuild_dir(char **kbuild_dir)
return -ENOMEM;
return 0;
}
+ pr_debug("%s: Couldn't find \"%s\", missing kernel-devel package?.\n",
+ __func__, autoconf_path);
free(autoconf_path);
return -ENOENT;
}
@@ -288,6 +290,7 @@ static const char *kinc_fetch_script =
"obj-y := dummy.o\n"
"\\$(obj)/%.o: \\$(src)/%.c\n"
"\t@echo -n \"\\$(NOSTDINC_FLAGS) \\$(LINUXINCLUDE) \\$(EXTRA_CFLAGS)\"\n"
+"\t\\$(CC) -c -o \\$@ \\$<\n"
"EOF\n"
"touch $TMPDIR/dummy.c\n"
"make -s -C $KBUILD_DIR M=$TMPDIR $KBUILD_OPTS dummy.o 2>/dev/null\n"
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index c8c5410315e8..fd14f1489802 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -686,6 +686,7 @@ static struct dso *machine__findnew_module_dso(struct machine *machine,
dso__set_module_info(dso, m, machine);
dso__set_long_name(dso, strdup(filename), true);
+ dso->kernel = DSO_TYPE_KERNEL;
}
dso__get(dso);
@@ -726,9 +727,17 @@ static int machine__process_ksymbol_register(struct machine *machine,
struct map *map = maps__find(&machine->kmaps, event->ksymbol.addr);
if (!map) {
- map = dso__new_map(event->ksymbol.name);
- if (!map)
+ struct dso *dso = dso__new(event->ksymbol.name);
+
+ if (dso) {
+ dso->kernel = DSO_TYPE_KERNEL;
+ map = map__new2(0, dso);
+ }
+
+ if (!dso || !map) {
+ dso__put(dso);
return -ENOMEM;
+ }
map->start = event->ksymbol.addr;
map->end = map->start + event->ksymbol.len;
@@ -972,7 +981,6 @@ int machine__create_extra_kernel_map(struct machine *machine,
kmap = map__kmap(map);
- kmap->kmaps = &machine->kmaps;
strlcpy(kmap->name, xm->name, KMAP_NAME_LEN);
maps__insert(&machine->kmaps, map);
@@ -1082,9 +1090,6 @@ int __weak machine__create_extra_kernel_maps(struct machine *machine __maybe_unu
static int
__machine__create_kernel_maps(struct machine *machine, struct dso *kernel)
{
- struct kmap *kmap;
- struct map *map;
-
/* In case of renewal the kernel map, destroy previous one */
machine__destroy_kernel_maps(machine);
@@ -1093,14 +1098,7 @@ __machine__create_kernel_maps(struct machine *machine, struct dso *kernel)
return -1;
machine->vmlinux_map->map_ip = machine->vmlinux_map->unmap_ip = identity__map_ip;
- map = machine__kernel_map(machine);
- kmap = map__kmap(map);
- if (!kmap)
- return -1;
-
- kmap->kmaps = &machine->kmaps;
- maps__insert(&machine->kmaps, map);
-
+ maps__insert(&machine->kmaps, machine->vmlinux_map);
return 0;
}
@@ -2083,15 +2081,16 @@ struct branch_info *sample__resolve_bstack(struct perf_sample *sample,
{
unsigned int i;
const struct branch_stack *bs = sample->branch_stack;
+ struct branch_entry *entries = perf_sample__branch_entries(sample);
struct branch_info *bi = calloc(bs->nr, sizeof(struct branch_info));
if (!bi)
return NULL;
for (i = 0; i < bs->nr; i++) {
- ip__resolve_ams(al->thread, &bi[i].to, bs->entries[i].to);
- ip__resolve_ams(al->thread, &bi[i].from, bs->entries[i].from);
- bi[i].flags = bs->entries[i].flags;
+ ip__resolve_ams(al->thread, &bi[i].to, entries[i].to);
+ ip__resolve_ams(al->thread, &bi[i].from, entries[i].from);
+ bi[i].flags = entries[i].flags;
}
return bi;
}
@@ -2187,6 +2186,7 @@ static int resolve_lbr_callchain_sample(struct thread *thread,
/* LBR only affects the user callchain */
if (i != chain_nr) {
struct branch_stack *lbr_stack = sample->branch_stack;
+ struct branch_entry *entries = perf_sample__branch_entries(sample);
int lbr_nr = lbr_stack->nr, j, k;
bool branch;
struct branch_flags *flags;
@@ -2212,31 +2212,29 @@ static int resolve_lbr_callchain_sample(struct thread *thread,
ip = chain->ips[j];
else if (j > i + 1) {
k = j - i - 2;
- ip = lbr_stack->entries[k].from;
+ ip = entries[k].from;
branch = true;
- flags = &lbr_stack->entries[k].flags;
+ flags = &entries[k].flags;
} else {
- ip = lbr_stack->entries[0].to;
+ ip = entries[0].to;
branch = true;
- flags = &lbr_stack->entries[0].flags;
- branch_from =
- lbr_stack->entries[0].from;
+ flags = &entries[0].flags;
+ branch_from = entries[0].from;
}
} else {
if (j < lbr_nr) {
k = lbr_nr - j - 1;
- ip = lbr_stack->entries[k].from;
+ ip = entries[k].from;
branch = true;
- flags = &lbr_stack->entries[k].flags;
+ flags = &entries[k].flags;
}
else if (j > lbr_nr)
ip = chain->ips[i + 1 - (j - lbr_nr)];
else {
- ip = lbr_stack->entries[0].to;
+ ip = entries[0].to;
branch = true;
- flags = &lbr_stack->entries[0].flags;
- branch_from =
- lbr_stack->entries[0].from;
+ flags = &entries[0].flags;
+ branch_from = entries[0].from;
}
}
@@ -2283,6 +2281,7 @@ static int thread__resolve_callchain_sample(struct thread *thread,
int max_stack)
{
struct branch_stack *branch = sample->branch_stack;
+ struct branch_entry *entries = perf_sample__branch_entries(sample);
struct ip_callchain *chain = sample->callchain;
int chain_nr = 0;
u8 cpumode = PERF_RECORD_MISC_USER;
@@ -2330,7 +2329,7 @@ static int thread__resolve_callchain_sample(struct thread *thread,
for (i = 0; i < nr; i++) {
if (callchain_param.order == ORDER_CALLEE) {
- be[i] = branch->entries[i];
+ be[i] = entries[i];
if (chain == NULL)
continue;
@@ -2349,7 +2348,7 @@ static int thread__resolve_callchain_sample(struct thread *thread,
be[i].from >= chain->ips[first_call] - 8)
first_call++;
} else
- be[i] = branch->entries[branch->nr - i - 1];
+ be[i] = entries[branch->nr - i - 1];
}
memset(iter, 0, sizeof(struct iterations) * nr);
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index f67960bedebb..53d96611e6a6 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -44,8 +44,8 @@ static inline int is_no_dso_memory(const char *filename)
static inline int is_android_lib(const char *filename)
{
- return !strncmp(filename, "/data/app-lib", 13) ||
- !strncmp(filename, "/system/lib", 11);
+ return strstarts(filename, "/data/app-lib/") ||
+ strstarts(filename, "/system/lib/");
}
static inline bool replace_android_lib(const char *filename, char *newfilename)
@@ -65,7 +65,7 @@ static inline bool replace_android_lib(const char *filename, char *newfilename)
app_abi_length = strlen(app_abi);
- if (!strncmp(filename, "/data/app-lib", 13)) {
+ if (strstarts(filename, "/data/app-lib/")) {
char *apk_path;
if (!app_abi_length)
@@ -89,7 +89,7 @@ static inline bool replace_android_lib(const char *filename, char *newfilename)
return true;
}
- if (!strncmp(filename, "/system/lib/", 11)) {
+ if (strstarts(filename, "/system/lib/")) {
char *ndk, *app;
const char *arch;
size_t ndk_length;
@@ -375,8 +375,13 @@ struct symbol *map__find_symbol_by_name(struct map *map, const char *name)
struct map *map__clone(struct map *from)
{
- struct map *map = memdup(from, sizeof(*map));
+ size_t size = sizeof(struct map);
+ struct map *map;
+
+ if (from->dso && from->dso->kernel)
+ size += sizeof(struct kmap);
+ map = memdup(from, size);
if (map != NULL) {
refcount_set(&map->refcnt, 1);
RB_CLEAR_NODE(&map->rb_node);
@@ -426,7 +431,7 @@ int map__fprintf_srcline(struct map *map, u64 addr, const char *prefix,
if (map && map->dso) {
char *srcline = map__srcline(map, addr, NULL);
- if (srcline != SRCLINE_UNKNOWN)
+ if (strncmp(srcline, SRCLINE_UNKNOWN, strlen(SRCLINE_UNKNOWN)) != 0)
ret = fprintf(fp, "%s%s", prefix, srcline);
free_srcline(srcline);
}
@@ -538,6 +543,16 @@ void maps__insert(struct maps *maps, struct map *map)
__maps__insert(maps, map);
++maps->nr_maps;
+ if (map->dso && map->dso->kernel) {
+ struct kmap *kmap = map__kmap(map);
+
+ if (kmap)
+ kmap->kmaps = maps;
+ else
+ pr_err("Internal error: kernel dso with non kernel map\n");
+ }
+
+
/*
* If we already performed some search by name, then we need to add the just
* inserted map and resort.
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index 02aee946b6c1..c3a8c701609a 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -22,6 +22,8 @@
#include <linux/string.h>
#include <linux/zalloc.h>
#include <subcmd/parse-options.h>
+#include <api/fs/fs.h>
+#include "util.h"
struct metric_event *metricgroup__lookup(struct rblist *metric_events,
struct evsel *evsel,
@@ -399,13 +401,85 @@ void metricgroup__print(bool metrics, bool metricgroups, char *filter,
strlist__delete(metriclist);
}
+static void metricgroup__add_metric_weak_group(struct strbuf *events,
+ const char **ids,
+ int idnum)
+{
+ bool no_group = false;
+ int i;
+
+ for (i = 0; i < idnum; i++) {
+ pr_debug("found event %s\n", ids[i]);
+ /*
+ * Duration time maps to a software event and can make
+ * groups not count. Always use it outside a
+ * group.
+ */
+ if (!strcmp(ids[i], "duration_time")) {
+ if (i > 0)
+ strbuf_addf(events, "}:W,");
+ strbuf_addf(events, "duration_time");
+ no_group = true;
+ continue;
+ }
+ strbuf_addf(events, "%s%s",
+ i == 0 || no_group ? "{" : ",",
+ ids[i]);
+ no_group = false;
+ }
+ if (!no_group)
+ strbuf_addf(events, "}:W");
+}
+
+static void metricgroup__add_metric_non_group(struct strbuf *events,
+ const char **ids,
+ int idnum)
+{
+ int i;
+
+ for (i = 0; i < idnum; i++)
+ strbuf_addf(events, ",%s", ids[i]);
+}
+
+static void metricgroup___watchdog_constraint_hint(const char *name, bool foot)
+{
+ static bool violate_nmi_constraint;
+
+ if (!foot) {
+ pr_warning("Splitting metric group %s into standalone metrics.\n", name);
+ violate_nmi_constraint = true;
+ return;
+ }
+
+ if (!violate_nmi_constraint)
+ return;
+
+ pr_warning("Try disabling the NMI watchdog to comply NO_NMI_WATCHDOG metric constraint:\n"
+ " echo 0 > /proc/sys/kernel/nmi_watchdog\n"
+ " perf stat ...\n"
+ " echo 1 > /proc/sys/kernel/nmi_watchdog\n");
+}
+
+static bool metricgroup__has_constraint(struct pmu_event *pe)
+{
+ if (!pe->metric_constraint)
+ return false;
+
+ if (!strcmp(pe->metric_constraint, "NO_NMI_WATCHDOG") &&
+ sysctl__nmi_watchdog_enabled()) {
+ metricgroup___watchdog_constraint_hint(pe->metric_name, false);
+ return true;
+ }
+
+ return false;
+}
+
static int metricgroup__add_metric(const char *metric, struct strbuf *events,
struct list_head *group_list)
{
struct pmu_events_map *map = perf_pmu__find_map(NULL);
struct pmu_event *pe;
- int ret = -EINVAL;
- int i, j;
+ int i, ret = -EINVAL;
if (!map)
return 0;
@@ -422,7 +496,6 @@ static int metricgroup__add_metric(const char *metric, struct strbuf *events,
const char **ids;
int idnum;
struct egroup *eg;
- bool no_group = false;
pr_debug("metric expr %s for %s\n", pe->metric_expr, pe->metric_name);
@@ -431,27 +504,11 @@ static int metricgroup__add_metric(const char *metric, struct strbuf *events,
continue;
if (events->len > 0)
strbuf_addf(events, ",");
- for (j = 0; j < idnum; j++) {
- pr_debug("found event %s\n", ids[j]);
- /*
- * Duration time maps to a software event and can make
- * groups not count. Always use it outside a
- * group.
- */
- if (!strcmp(ids[j], "duration_time")) {
- if (j > 0)
- strbuf_addf(events, "}:W,");
- strbuf_addf(events, "duration_time");
- no_group = true;
- continue;
- }
- strbuf_addf(events, "%s%s",
- j == 0 || no_group ? "{" : ",",
- ids[j]);
- no_group = false;
- }
- if (!no_group)
- strbuf_addf(events, "}:W");
+
+ if (metricgroup__has_constraint(pe))
+ metricgroup__add_metric_non_group(events, ids, idnum);
+ else
+ metricgroup__add_metric_weak_group(events, ids, idnum);
eg = malloc(sizeof(struct egroup));
if (!eg) {
@@ -493,6 +550,10 @@ static int metricgroup__add_metric_list(const char *list, struct strbuf *events,
}
}
free(nlist);
+
+ if (!ret)
+ metricgroup___watchdog_constraint_hint(NULL, true);
+
return ret;
}
diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index 3b664fa673a6..ab7108d22428 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -98,20 +98,29 @@ static int perf_mmap__aio_bind(struct mmap *map, int idx, int cpu, int affinity)
{
void *data;
size_t mmap_len;
- unsigned long node_mask;
+ unsigned long *node_mask;
+ unsigned long node_index;
+ int err = 0;
if (affinity != PERF_AFFINITY_SYS && cpu__max_node() > 1) {
data = map->aio.data[idx];
mmap_len = mmap__mmap_len(map);
- node_mask = 1UL << cpu__get_node(cpu);
- if (mbind(data, mmap_len, MPOL_BIND, &node_mask, 1, 0)) {
- pr_err("Failed to bind [%p-%p] AIO buffer to node %d: error %m\n",
- data, data + mmap_len, cpu__get_node(cpu));
+ node_index = cpu__get_node(cpu);
+ node_mask = bitmap_alloc(node_index + 1);
+ if (!node_mask) {
+ pr_err("Failed to allocate node mask for mbind: error %m\n");
return -1;
}
+ set_bit(node_index, node_mask);
+ if (mbind(data, mmap_len, MPOL_BIND, node_mask, node_index + 1 + 1, 0)) {
+ pr_err("Failed to bind [%p-%p] AIO buffer to node %lu: error %m\n",
+ data, data + mmap_len, node_index);
+ err = -1;
+ }
+ bitmap_free(node_mask);
}
- return 0;
+ return err;
}
#else /* !HAVE_LIBNUMA_SUPPORT */
static int perf_mmap__aio_alloc(struct mmap *map, int idx)
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index c01ba6f8fdad..a7dc0b096974 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -257,21 +257,15 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config)
path = zalloc(sizeof(*path));
if (!path)
return NULL;
- path->system = malloc(MAX_EVENT_LENGTH);
- if (!path->system) {
+ if (asprintf(&path->system, "%.*s", MAX_EVENT_LENGTH, sys_dirent->d_name) < 0) {
free(path);
return NULL;
}
- path->name = malloc(MAX_EVENT_LENGTH);
- if (!path->name) {
+ if (asprintf(&path->name, "%.*s", MAX_EVENT_LENGTH, evt_dirent->d_name) < 0) {
zfree(&path->system);
free(path);
return NULL;
}
- strncpy(path->system, sys_dirent->d_name,
- MAX_EVENT_LENGTH);
- strncpy(path->name, evt_dirent->d_name,
- MAX_EVENT_LENGTH);
return path;
}
}
@@ -1219,7 +1213,7 @@ static int config_attr(struct perf_event_attr *attr,
static int get_config_terms(struct list_head *head_config,
struct list_head *head_terms __maybe_unused)
{
-#define ADD_CONFIG_TERM(__type) \
+#define ADD_CONFIG_TERM(__type, __weak) \
struct perf_evsel_config_term *__t; \
\
__t = zalloc(sizeof(*__t)); \
@@ -1228,18 +1222,18 @@ static int get_config_terms(struct list_head *head_config,
\
INIT_LIST_HEAD(&__t->list); \
__t->type = PERF_EVSEL__CONFIG_TERM_ ## __type; \
- __t->weak = term->weak; \
+ __t->weak = __weak; \
list_add_tail(&__t->list, head_terms)
-#define ADD_CONFIG_TERM_VAL(__type, __name, __val) \
+#define ADD_CONFIG_TERM_VAL(__type, __name, __val, __weak) \
do { \
- ADD_CONFIG_TERM(__type); \
+ ADD_CONFIG_TERM(__type, __weak); \
__t->val.__name = __val; \
} while (0)
-#define ADD_CONFIG_TERM_STR(__type, __val) \
+#define ADD_CONFIG_TERM_STR(__type, __val, __weak) \
do { \
- ADD_CONFIG_TERM(__type); \
+ ADD_CONFIG_TERM(__type, __weak); \
__t->val.str = strdup(__val); \
if (!__t->val.str) { \
zfree(&__t); \
@@ -1253,62 +1247,62 @@ do { \
list_for_each_entry(term, head_config, list) {
switch (term->type_term) {
case PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD:
- ADD_CONFIG_TERM_VAL(PERIOD, period, term->val.num);
+ ADD_CONFIG_TERM_VAL(PERIOD, period, term->val.num, term->weak);
break;
case PARSE_EVENTS__TERM_TYPE_SAMPLE_FREQ:
- ADD_CONFIG_TERM_VAL(FREQ, freq, term->val.num);
+ ADD_CONFIG_TERM_VAL(FREQ, freq, term->val.num, term->weak);
break;
case PARSE_EVENTS__TERM_TYPE_TIME:
- ADD_CONFIG_TERM_VAL(TIME, time, term->val.num);
+ ADD_CONFIG_TERM_VAL(TIME, time, term->val.num, term->weak);
break;
case PARSE_EVENTS__TERM_TYPE_CALLGRAPH:
- ADD_CONFIG_TERM_STR(CALLGRAPH, term->val.str);
+ ADD_CONFIG_TERM_STR(CALLGRAPH, term->val.str, term->weak);
break;
case PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE:
- ADD_CONFIG_TERM_STR(BRANCH, term->val.str);
+ ADD_CONFIG_TERM_STR(BRANCH, term->val.str, term->weak);
break;
case PARSE_EVENTS__TERM_TYPE_STACKSIZE:
ADD_CONFIG_TERM_VAL(STACK_USER, stack_user,
- term->val.num);
+ term->val.num, term->weak);
break;
case PARSE_EVENTS__TERM_TYPE_INHERIT:
ADD_CONFIG_TERM_VAL(INHERIT, inherit,
- term->val.num ? 1 : 0);
+ term->val.num ? 1 : 0, term->weak);
break;
case PARSE_EVENTS__TERM_TYPE_NOINHERIT:
ADD_CONFIG_TERM_VAL(INHERIT, inherit,
- term->val.num ? 0 : 1);
+ term->val.num ? 0 : 1, term->weak);
break;
case PARSE_EVENTS__TERM_TYPE_MAX_STACK:
ADD_CONFIG_TERM_VAL(MAX_STACK, max_stack,
- term->val.num);
+ term->val.num, term->weak);
break;
case PARSE_EVENTS__TERM_TYPE_MAX_EVENTS:
ADD_CONFIG_TERM_VAL(MAX_EVENTS, max_events,
- term->val.num);
+ term->val.num, term->weak);
break;
case PARSE_EVENTS__TERM_TYPE_OVERWRITE:
ADD_CONFIG_TERM_VAL(OVERWRITE, overwrite,
- term->val.num ? 1 : 0);
+ term->val.num ? 1 : 0, term->weak);
break;
case PARSE_EVENTS__TERM_TYPE_NOOVERWRITE:
ADD_CONFIG_TERM_VAL(OVERWRITE, overwrite,
- term->val.num ? 0 : 1);
+ term->val.num ? 0 : 1, term->weak);
break;
case PARSE_EVENTS__TERM_TYPE_DRV_CFG:
- ADD_CONFIG_TERM_STR(DRV_CFG, term->val.str);
+ ADD_CONFIG_TERM_STR(DRV_CFG, term->val.str, term->weak);
break;
case PARSE_EVENTS__TERM_TYPE_PERCORE:
ADD_CONFIG_TERM_VAL(PERCORE, percore,
- term->val.num ? true : false);
+ term->val.num ? true : false, term->weak);
break;
case PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT:
ADD_CONFIG_TERM_VAL(AUX_OUTPUT, aux_output,
- term->val.num ? 1 : 0);
+ term->val.num ? 1 : 0, term->weak);
break;
case PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE:
ADD_CONFIG_TERM_VAL(AUX_SAMPLE_SIZE, aux_sample_size,
- term->val.num);
+ term->val.num, term->weak);
break;
default:
break;
@@ -1345,7 +1339,7 @@ static int get_config_chgs(struct perf_pmu *pmu, struct list_head *head_config,
}
if (bits)
- ADD_CONFIG_TERM_VAL(CFG_CHG, cfg_chg, bits);
+ ADD_CONFIG_TERM_VAL(CFG_CHG, cfg_chg, bits, false);
#undef ADD_CONFIG_TERM
return 0;
diff --git a/tools/perf/util/perf_event_attr_fprintf.c b/tools/perf/util/perf_event_attr_fprintf.c
index 651203126c71..355d3458d4e6 100644
--- a/tools/perf/util/perf_event_attr_fprintf.c
+++ b/tools/perf/util/perf_event_attr_fprintf.c
@@ -50,6 +50,7 @@ static void __p_branch_sample_type(char *buf, size_t size, u64 value)
bit_name(ABORT_TX), bit_name(IN_TX), bit_name(NO_TX),
bit_name(COND), bit_name(CALL_STACK), bit_name(IND_JUMP),
bit_name(CALL), bit_name(NO_FLAGS), bit_name(NO_CYCLES),
+ bit_name(HW_INDEX),
{ .name = NULL, }
};
#undef bit_name
diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
index 5003ba403345..8c852948513e 100644
--- a/tools/perf/util/probe-file.c
+++ b/tools/perf/util/probe-file.c
@@ -206,6 +206,9 @@ static struct strlist *__probe_file__get_namelist(int fd, bool include_group)
} else
ret = strlist__add(sl, tev.event);
clear_probe_trace_event(&tev);
+ /* Skip if there is same name multi-probe event in the list */
+ if (ret == -EEXIST)
+ ret = 0;
if (ret < 0)
break;
}
@@ -301,10 +304,15 @@ int probe_file__get_events(int fd, struct strfilter *filter,
p = strchr(ent->s, ':');
if ((p && strfilter__compare(filter, p + 1)) ||
strfilter__compare(filter, ent->s)) {
- strlist__add(plist, ent->s);
+ ret = strlist__add(plist, ent->s);
+ if (ret == -ENOMEM) {
+ pr_err("strlist__add failed with -ENOMEM\n");
+ goto out;
+ }
ret = 0;
}
}
+out:
strlist__delete(namelist);
return ret;
@@ -511,7 +519,11 @@ static int probe_cache__load(struct probe_cache *pcache)
ret = -EINVAL;
goto out;
}
- strlist__add(entry->tevlist, buf);
+ ret = strlist__add(entry->tevlist, buf);
+ if (ret == -ENOMEM) {
+ pr_err("strlist__add failed with -ENOMEM\n");
+ goto out;
+ }
}
}
out:
@@ -672,7 +684,12 @@ int probe_cache__add_entry(struct probe_cache *pcache,
command = synthesize_probe_trace_command(&tevs[i]);
if (!command)
goto out_err;
- strlist__add(entry->tevlist, command);
+ ret = strlist__add(entry->tevlist, command);
+ if (ret == -ENOMEM) {
+ pr_err("strlist__add failed with -ENOMEM\n");
+ goto out_err;
+ }
+
free(command);
}
list_add_tail(&entry->node, &pcache->entries);
@@ -853,9 +870,15 @@ int probe_cache__scan_sdt(struct probe_cache *pcache, const char *pathname)
break;
}
- strlist__add(entry->tevlist, buf);
+ ret = strlist__add(entry->tevlist, buf);
+
free(buf);
entry = NULL;
+
+ if (ret == -ENOMEM) {
+ pr_err("strlist__add failed with -ENOMEM\n");
+ break;
+ }
}
if (entry) {
list_del_init(&entry->node);
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 1c817add6ca4..e4cff49384f4 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -637,14 +637,19 @@ static int convert_to_trace_point(Dwarf_Die *sp_die, Dwfl_Module *mod,
return -EINVAL;
}
- /* Try to get actual symbol name from symtab */
- symbol = dwfl_module_addrsym(mod, paddr, &sym, NULL);
+ if (dwarf_entrypc(sp_die, &eaddr) == 0) {
+ /* If the DIE has entrypc, use it. */
+ symbol = dwarf_diename(sp_die);
+ } else {
+ /* Try to get actual symbol name and address from symtab */
+ symbol = dwfl_module_addrsym(mod, paddr, &sym, NULL);
+ eaddr = sym.st_value;
+ }
if (!symbol) {
pr_warning("Failed to find symbol at 0x%lx\n",
(unsigned long)paddr);
return -ENOENT;
}
- eaddr = sym.st_value;
tp->offset = (unsigned long)(paddr - eaddr);
tp->address = (unsigned long)paddr;
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 80ca5d0ab7fe..8c1b27cd8b99 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -464,6 +464,7 @@ static PyObject *python_process_brstack(struct perf_sample *sample,
struct thread *thread)
{
struct branch_stack *br = sample->branch_stack;
+ struct branch_entry *entries = perf_sample__branch_entries(sample);
PyObject *pylist;
u64 i;
@@ -484,28 +485,28 @@ static PyObject *python_process_brstack(struct perf_sample *sample,
Py_FatalError("couldn't create Python dictionary");
pydict_set_item_string_decref(pyelem, "from",
- PyLong_FromUnsignedLongLong(br->entries[i].from));
+ PyLong_FromUnsignedLongLong(entries[i].from));
pydict_set_item_string_decref(pyelem, "to",
- PyLong_FromUnsignedLongLong(br->entries[i].to));
+ PyLong_FromUnsignedLongLong(entries[i].to));
pydict_set_item_string_decref(pyelem, "mispred",
- PyBool_FromLong(br->entries[i].flags.mispred));
+ PyBool_FromLong(entries[i].flags.mispred));
pydict_set_item_string_decref(pyelem, "predicted",
- PyBool_FromLong(br->entries[i].flags.predicted));
+ PyBool_FromLong(entries[i].flags.predicted));
pydict_set_item_string_decref(pyelem, "in_tx",
- PyBool_FromLong(br->entries[i].flags.in_tx));
+ PyBool_FromLong(entries[i].flags.in_tx));
pydict_set_item_string_decref(pyelem, "abort",
- PyBool_FromLong(br->entries[i].flags.abort));
+ PyBool_FromLong(entries[i].flags.abort));
pydict_set_item_string_decref(pyelem, "cycles",
- PyLong_FromUnsignedLongLong(br->entries[i].flags.cycles));
+ PyLong_FromUnsignedLongLong(entries[i].flags.cycles));
thread__find_map_fb(thread, sample->cpumode,
- br->entries[i].from, &al);
+ entries[i].from, &al);
dsoname = get_dsoname(al.map);
pydict_set_item_string_decref(pyelem, "from_dsoname",
_PyUnicode_FromString(dsoname));
thread__find_map_fb(thread, sample->cpumode,
- br->entries[i].to, &al);
+ entries[i].to, &al);
dsoname = get_dsoname(al.map);
pydict_set_item_string_decref(pyelem, "to_dsoname",
_PyUnicode_FromString(dsoname));
@@ -561,6 +562,7 @@ static PyObject *python_process_brstacksym(struct perf_sample *sample,
struct thread *thread)
{
struct branch_stack *br = sample->branch_stack;
+ struct branch_entry *entries = perf_sample__branch_entries(sample);
PyObject *pylist;
u64 i;
char bf[512];
@@ -581,22 +583,22 @@ static PyObject *python_process_brstacksym(struct perf_sample *sample,
Py_FatalError("couldn't create Python dictionary");
thread__find_symbol_fb(thread, sample->cpumode,
- br->entries[i].from, &al);
+ entries[i].from, &al);
get_symoff(al.sym, &al, true, bf, sizeof(bf));
pydict_set_item_string_decref(pyelem, "from",
_PyUnicode_FromString(bf));
thread__find_symbol_fb(thread, sample->cpumode,
- br->entries[i].to, &al);
+ entries[i].to, &al);
get_symoff(al.sym, &al, true, bf, sizeof(bf));
pydict_set_item_string_decref(pyelem, "to",
_PyUnicode_FromString(bf));
- get_br_mspred(&br->entries[i].flags, bf, sizeof(bf));
+ get_br_mspred(&entries[i].flags, bf, sizeof(bf));
pydict_set_item_string_decref(pyelem, "pred",
_PyUnicode_FromString(bf));
- if (br->entries[i].flags.in_tx) {
+ if (entries[i].flags.in_tx) {
pydict_set_item_string_decref(pyelem, "in_tx",
_PyUnicode_FromString("X"));
} else {
@@ -604,7 +606,7 @@ static PyObject *python_process_brstacksym(struct perf_sample *sample,
_PyUnicode_FromString("-"));
}
- if (br->entries[i].flags.abort) {
+ if (entries[i].flags.abort) {
pydict_set_item_string_decref(pyelem, "abort",
_PyUnicode_FromString("A"));
} else {
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index d0d7d25b23e3..055b00abd56d 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1007,6 +1007,7 @@ static void callchain__lbr_callstack_printf(struct perf_sample *sample)
{
struct ip_callchain *callchain = sample->callchain;
struct branch_stack *lbr_stack = sample->branch_stack;
+ struct branch_entry *entries = perf_sample__branch_entries(sample);
u64 kernel_callchain_nr = callchain->nr;
unsigned int i;
@@ -1043,10 +1044,10 @@ static void callchain__lbr_callstack_printf(struct perf_sample *sample)
i, callchain->ips[i]);
printf("..... %2d: %016" PRIx64 "\n",
- (int)(kernel_callchain_nr), lbr_stack->entries[0].to);
+ (int)(kernel_callchain_nr), entries[0].to);
for (i = 0; i < lbr_stack->nr; i++)
printf("..... %2d: %016" PRIx64 "\n",
- (int)(i + kernel_callchain_nr + 1), lbr_stack->entries[i].from);
+ (int)(i + kernel_callchain_nr + 1), entries[i].from);
}
}
@@ -1068,6 +1069,7 @@ static void callchain__printf(struct evsel *evsel,
static void branch_stack__printf(struct perf_sample *sample, bool callstack)
{
+ struct branch_entry *entries = perf_sample__branch_entries(sample);
uint64_t i;
printf("%s: nr:%" PRIu64 "\n",
@@ -1075,7 +1077,7 @@ static void branch_stack__printf(struct perf_sample *sample, bool callstack)
sample->branch_stack->nr);
for (i = 0; i < sample->branch_stack->nr; i++) {
- struct branch_entry *e = &sample->branch_stack->entries[i];
+ struct branch_entry *e = &entries[i];
if (!callstack) {
printf("..... %2"PRIu64": %016" PRIx64 " -> %016" PRIx64 " %hu cycles %s%s%s%s %x\n",
diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index aa344a163eaf..8a065a6f9713 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -2,11 +2,13 @@ from os import getenv
from subprocess import Popen, PIPE
from re import sub
+cc = getenv("CC")
+cc_is_clang = b"clang version" in Popen([cc, "-v"], stderr=PIPE).stderr.readline()
+
def clang_has_option(option):
- return [o for o in Popen(['clang', option], stderr=PIPE).stderr.readlines() if b"unknown argument" in o] == [ ]
+ return [o for o in Popen([cc, option], stderr=PIPE).stderr.readlines() if b"unknown argument" in o] == [ ]
-cc = getenv("CC")
-if cc == "clang":
+if cc_is_clang:
from distutils.sysconfig import get_config_vars
vars = get_config_vars()
for var in ('CFLAGS', 'OPT'):
@@ -40,7 +42,7 @@ class install_lib(_install_lib):
cflags = getenv('CFLAGS', '').split()
# switch off several checks (need to be at the end of cflags list)
cflags += ['-fno-strict-aliasing', '-Wno-write-strings', '-Wno-unused-parameter', '-Wno-redundant-decls' ]
-if cc != "clang":
+if not cc_is_clang:
cflags += ['-Wno-cast-function-type' ]
src_perf = getenv('srctree') + '/tools/perf'
diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
index bc31fccc0057..76c6052b12e2 100644
--- a/tools/perf/util/stat-display.c
+++ b/tools/perf/util/stat-display.c
@@ -16,6 +16,7 @@
#include <linux/ctype.h>
#include "cgroup.h"
#include <api/fs/fs.h>
+#include "util.h"
#define CNTR_NOT_SUPPORTED "<not supported>"
#define CNTR_NOT_COUNTED "<not counted>"
@@ -110,7 +111,7 @@ static void aggr_printout(struct perf_stat_config *config,
config->csv_sep);
break;
case AGGR_NONE:
- if (evsel->percore) {
+ if (evsel->percore && !config->percore_show_thread) {
fprintf(config->output, "S%d-D%d-C%*d%s",
cpu_map__id_to_socket(id),
cpu_map__id_to_die(id),
@@ -628,7 +629,7 @@ static void aggr_cb(struct perf_stat_config *config,
static void print_counter_aggrdata(struct perf_stat_config *config,
struct evsel *counter, int s,
char *prefix, bool metric_only,
- bool *first)
+ bool *first, int cpu)
{
struct aggr_data ad;
FILE *output = config->output;
@@ -654,7 +655,7 @@ static void print_counter_aggrdata(struct perf_stat_config *config,
fprintf(output, "%s", prefix);
uval = val * counter->scale;
- printout(config, id, nr, counter, uval, prefix,
+ printout(config, cpu != -1 ? cpu : id, nr, counter, uval, prefix,
run, ena, 1.0, &rt_stat);
if (!metric_only)
fputc('\n', output);
@@ -687,7 +688,7 @@ static void print_aggr(struct perf_stat_config *config,
evlist__for_each_entry(evlist, counter) {
print_counter_aggrdata(config, counter, s,
prefix, metric_only,
- &first);
+ &first, -1);
}
if (metric_only)
fputc('\n', output);
@@ -1097,7 +1098,6 @@ static void print_footer(struct perf_stat_config *config)
{
double avg = avg_stats(config->walltime_nsecs_stats) / NSEC_PER_SEC;
FILE *output = config->output;
- int n;
if (!config->null_run)
fprintf(output, "\n");
@@ -1131,9 +1131,7 @@ static void print_footer(struct perf_stat_config *config)
}
fprintf(output, "\n\n");
- if (config->print_free_counters_hint &&
- sysctl__read_int("kernel/nmi_watchdog", &n) >= 0 &&
- n > 0)
+ if (config->print_free_counters_hint && sysctl__nmi_watchdog_enabled())
fprintf(output,
"Some events weren't counted. Try disabling the NMI watchdog:\n"
" echo 0 > /proc/sys/kernel/nmi_watchdog\n"
@@ -1146,6 +1144,26 @@ static void print_footer(struct perf_stat_config *config)
"the same PMU. Try reorganizing the group.\n");
}
+static void print_percore_thread(struct perf_stat_config *config,
+ struct evsel *counter, char *prefix)
+{
+ int s, s2, id;
+ bool first = true;
+
+ for (int i = 0; i < perf_evsel__nr_cpus(counter); i++) {
+ s2 = config->aggr_get_id(config, evsel__cpus(counter), i);
+ for (s = 0; s < config->aggr_map->nr; s++) {
+ id = config->aggr_map->map[s];
+ if (s2 == id)
+ break;
+ }
+
+ print_counter_aggrdata(config, counter, s,
+ prefix, false,
+ &first, i);
+ }
+}
+
static void print_percore(struct perf_stat_config *config,
struct evsel *counter, char *prefix)
{
@@ -1157,13 +1175,16 @@ static void print_percore(struct perf_stat_config *config,
if (!(config->aggr_map || config->aggr_get_id))
return;
+ if (config->percore_show_thread)
+ return print_percore_thread(config, counter, prefix);
+
for (s = 0; s < config->aggr_map->nr; s++) {
if (prefix && metric_only)
fprintf(output, "%s", prefix);
print_counter_aggrdata(config, counter, s,
prefix, metric_only,
- &first);
+ &first, -1);
}
if (metric_only)
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 2c41d47f6f83..0fd713d3674f 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -18,7 +18,6 @@
* AGGR_NONE: Use matching CPU
* AGGR_THREAD: Not supported?
*/
-static bool have_frontend_stalled;
struct runtime_stat rt_stat;
struct stats walltime_nsecs_stats;
@@ -144,7 +143,6 @@ void runtime_stat__exit(struct runtime_stat *st)
void perf_stat__init_shadow_stats(void)
{
- have_frontend_stalled = pmu_have_event("cpu", "stalled-cycles-frontend");
runtime_stat__init(&rt_stat);
}
@@ -779,9 +777,7 @@ static void generic_metric(struct perf_stat_config *config,
}
if (!metric_events[i]) {
- const char *p = metric_expr;
-
- if (expr__parse(&ratio, &pctx, &p) == 0) {
+ if (expr__parse(&ratio, &pctx, metric_expr) == 0) {
char *unit;
char metric_bf[64];
@@ -853,10 +849,6 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
print_metric(config, ctxp, NULL, "%7.2f ",
"stalled cycles per insn",
ratio);
- } else if (have_frontend_stalled) {
- out->new_line(config, ctxp);
- print_metric(config, ctxp, NULL, "%7.2f ",
- "stalled cycles per insn", 0);
}
} else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES)) {
if (runtime_stat_n(st, STAT_BRANCHES, ctx, cpu) != 0)
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index fb990efa54a8..b4fdfaa7f2c0 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -109,6 +109,7 @@ struct perf_stat_config {
bool walltime_run_table;
bool all_kernel;
bool all_user;
+ bool percore_show_thread;
FILE *output;
unsigned int interval;
unsigned int timeout;
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 3b379b1296f1..26bc6a0096ce 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -635,9 +635,12 @@ out:
static bool symbol__is_idle(const char *name)
{
const char * const idle_symbols[] = {
+ "acpi_idle_do_entry",
+ "acpi_processor_ffh_cstate_enter",
"arch_cpu_idle",
"cpu_idle",
"cpu_startup_entry",
+ "idle_cpu",
"intel_idle",
"default_idle",
"native_safe_halt",
@@ -651,13 +654,17 @@ static bool symbol__is_idle(const char *name)
NULL
};
int i;
+ static struct strlist *idle_symbols_list;
- for (i = 0; idle_symbols[i]; i++) {
- if (!strcmp(idle_symbols[i], name))
- return true;
- }
+ if (idle_symbols_list)
+ return strlist__has_entry(idle_symbols_list, name);
- return false;
+ idle_symbols_list = strlist__new(NULL, NULL);
+
+ for (i = 0; idle_symbols[i]; i++)
+ strlist__add(idle_symbols_list, idle_symbols[i]);
+
+ return strlist__has_entry(idle_symbols_list, name);
}
static int map__process_kallsym_symbol(void *arg, const char *name,
@@ -1615,7 +1622,12 @@ int dso__load(struct dso *dso, struct map *map)
goto out;
}
- if (dso->kernel) {
+ kmod = dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE ||
+ dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP ||
+ dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE ||
+ dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE_COMP;
+
+ if (dso->kernel && !kmod) {
if (dso->kernel == DSO_TYPE_KERNEL)
ret = dso__load_kernel_sym(dso, map);
else if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
@@ -1643,12 +1655,6 @@ int dso__load(struct dso *dso, struct map *map)
if (!name)
goto out;
- kmod = dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE ||
- dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP ||
- dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE ||
- dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE_COMP;
-
-
/*
* Read the build id if possible. This is required for
* DSO_BINARY_TYPE__BUILDID_DEBUGINFO to work
diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c
index c423298fe62d..3f28af39f9c6 100644
--- a/tools/perf/util/synthetic-events.c
+++ b/tools/perf/util/synthetic-events.c
@@ -345,6 +345,7 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
continue;
event->mmap2.ino = (u64)ino;
+ event->mmap2.ino_generation = 0;
/*
* Just like the kernel, see __perf_event_mmap in kernel/perf_event.c
@@ -1183,7 +1184,8 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
if (type & PERF_SAMPLE_BRANCH_STACK) {
sz = sample->branch_stack->nr * sizeof(struct branch_entry);
- sz += sizeof(u64);
+ /* nr, hw_idx */
+ sz += 2 * sizeof(u64);
result += sz;
}
@@ -1344,7 +1346,8 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_fo
if (type & PERF_SAMPLE_BRANCH_STACK) {
sz = sample->branch_stack->nr * sizeof(struct branch_entry);
- sz += sizeof(u64);
+ /* nr, hw_idx */
+ sz += 2 * sizeof(u64);
memcpy(array, sample->branch_stack, sz);
array = (void *)array + sz;
}
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 969ae560dad9..d707c9624dd9 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -55,6 +55,24 @@ int sysctl__max_stack(void)
return sysctl_perf_event_max_stack;
}
+bool sysctl__nmi_watchdog_enabled(void)
+{
+ static bool cached;
+ static bool nmi_watchdog;
+ int value;
+
+ if (cached)
+ return nmi_watchdog;
+
+ if (sysctl__read_int("kernel/nmi_watchdog", &value) < 0)
+ return false;
+
+ nmi_watchdog = (value > 0) ? true : false;
+ cached = true;
+
+ return nmi_watchdog;
+}
+
bool test_attr__enabled;
bool perf_host = true;
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 9969b8b46f7c..f486fdd3a538 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -29,6 +29,8 @@ size_t hex_width(u64 v);
int sysctl__max_stack(void);
+bool sysctl__nmi_watchdog_enabled(void);
+
int fetch_kernel_version(unsigned int *puint,
char *str, size_t str_sz);
#define KVER_VERSION(x) (((x) >> 16) & 0xff)
diff --git a/tools/power/cpupower/utils/idle_monitor/amd_fam14h_idle.c b/tools/power/cpupower/utils/idle_monitor/amd_fam14h_idle.c
index 33dc34db4f3c..20f46348271b 100644
--- a/tools/power/cpupower/utils/idle_monitor/amd_fam14h_idle.c
+++ b/tools/power/cpupower/utils/idle_monitor/amd_fam14h_idle.c
@@ -82,7 +82,7 @@ static struct pci_access *pci_acc;
static struct pci_dev *amd_fam14h_pci_dev;
static int nbp1_entered;
-struct timespec start_time;
+static struct timespec start_time;
static unsigned long long timediff;
#ifdef DEBUG
diff --git a/tools/power/cpupower/utils/idle_monitor/cpuidle_sysfs.c b/tools/power/cpupower/utils/idle_monitor/cpuidle_sysfs.c
index 3c4cee160b0e..a65f7d011513 100644
--- a/tools/power/cpupower/utils/idle_monitor/cpuidle_sysfs.c
+++ b/tools/power/cpupower/utils/idle_monitor/cpuidle_sysfs.c
@@ -19,7 +19,7 @@ struct cpuidle_monitor cpuidle_sysfs_monitor;
static unsigned long long **previous_count;
static unsigned long long **current_count;
-struct timespec start_time;
+static struct timespec start_time;
static unsigned long long timediff;
static int cpuidle_get_count_percent(unsigned int id, double *percent,
diff --git a/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.c b/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.c
index 6d44fec55ad5..7c77045fef52 100644
--- a/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.c
+++ b/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.c
@@ -27,6 +27,8 @@ struct cpuidle_monitor *all_monitors[] = {
0
};
+int cpu_count;
+
static struct cpuidle_monitor *monitors[MONITORS_MAX];
static unsigned int avail_monitors;
diff --git a/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.h b/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.h
index 5b5eb1da0cce..c559d3115330 100644
--- a/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.h
+++ b/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.h
@@ -25,7 +25,7 @@
#endif
#define CSTATE_DESC_LEN 60
-int cpu_count;
+extern int cpu_count;
/* Hard to define the right names ...: */
enum power_range_e {
diff --git a/tools/power/x86/intel-speed-select/isst-config.c b/tools/power/x86/intel-speed-select/isst-config.c
index 2b2b8167c65b..b73763489410 100644
--- a/tools/power/x86/intel-speed-select/isst-config.c
+++ b/tools/power/x86/intel-speed-select/isst-config.c
@@ -15,7 +15,7 @@ struct process_cmd_struct {
int arg;
};
-static const char *version_str = "v1.2";
+static const char *version_str = "v1.3";
static const int supported_api_ver = 1;
static struct isst_if_platform_info isst_platform_info;
static char *progname;
@@ -42,6 +42,7 @@ static int out_format_json;
static int cmd_help;
static int force_online_offline;
static int auto_mode;
+static int fact_enable_fail;
/* clos related */
static int current_clos = -1;
@@ -61,6 +62,18 @@ struct _cpu_map {
};
struct _cpu_map *cpu_map;
+struct cpu_topology {
+ short cpu;
+ short core_id;
+ short pkg_id;
+ short die_id;
+};
+
+FILE *get_output_file(void)
+{
+ return outf;
+}
+
void debug_printf(const char *format, ...)
{
va_list args;
@@ -82,6 +95,14 @@ int is_clx_n_platform(void)
return 0;
}
+int is_skx_based_platform(void)
+{
+ if (cpu_model == 0x55)
+ return 1;
+
+ return 0;
+}
+
static int update_cpu_model(void)
{
unsigned int ebx, ecx, edx;
@@ -175,25 +196,137 @@ int out_format_is_json(void)
return out_format_json;
}
+static int get_stored_topology_info(int cpu, int *core_id, int *pkg_id, int *die_id)
+{
+ const char *pathname = "/tmp/isst_cpu_topology.dat";
+ struct cpu_topology cpu_top;
+ FILE *fp;
+ int ret;
+
+ fp = fopen(pathname, "rb");
+ if (!fp)
+ return -1;
+
+ ret = fseek(fp, cpu * sizeof(cpu_top), SEEK_SET);
+ if (ret)
+ goto err_ret;
+
+ ret = fread(&cpu_top, sizeof(cpu_top), 1, fp);
+ if (ret != 1) {
+ ret = -1;
+ goto err_ret;
+ }
+
+ *pkg_id = cpu_top.pkg_id;
+ *core_id = cpu_top.core_id;
+ *die_id = cpu_top.die_id;
+ ret = 0;
+
+err_ret:
+ fclose(fp);
+
+ return ret;
+}
+
+static void store_cpu_topology(void)
+{
+ const char *pathname = "/tmp/isst_cpu_topology.dat";
+ FILE *fp;
+ int i;
+
+ fp = fopen(pathname, "rb");
+ if (fp) {
+ /* Mapping already exists */
+ fclose(fp);
+ return;
+ }
+
+ fp = fopen(pathname, "wb");
+ if (!fp) {
+ fprintf(stderr, "Can't create file:%s\n", pathname);
+ return;
+ }
+
+ for (i = 0; i < topo_max_cpus; ++i) {
+ struct cpu_topology cpu_top;
+
+ cpu_top.core_id = parse_int_file(0,
+ "/sys/devices/system/cpu/cpu%d/topology/core_id", i);
+ if (cpu_top.core_id < 0)
+ cpu_top.core_id = -1;
+
+ cpu_top.pkg_id = parse_int_file(0,
+ "/sys/devices/system/cpu/cpu%d/topology/physical_package_id", i);
+ if (cpu_top.pkg_id < 0)
+ cpu_top.pkg_id = -1;
+
+ cpu_top.die_id = parse_int_file(0,
+ "/sys/devices/system/cpu/cpu%d/topology/die_id", i);
+ if (cpu_top.die_id < 0)
+ cpu_top.die_id = -1;
+
+ cpu_top.cpu = i;
+
+ if (fwrite(&cpu_top, sizeof(cpu_top), 1, fp) != 1) {
+ fprintf(stderr, "Can't write to:%s\n", pathname);
+ break;
+ }
+ }
+
+ fclose(fp);
+}
+
int get_physical_package_id(int cpu)
{
- return parse_int_file(
- 0, "/sys/devices/system/cpu/cpu%d/topology/physical_package_id",
- cpu);
+ int ret;
+
+ ret = parse_int_file(0,
+ "/sys/devices/system/cpu/cpu%d/topology/physical_package_id",
+ cpu);
+ if (ret < 0) {
+ int core_id, pkg_id, die_id;
+
+ ret = get_stored_topology_info(cpu, &core_id, &pkg_id, &die_id);
+ if (!ret)
+ return pkg_id;
+ }
+
+ return ret;
}
int get_physical_core_id(int cpu)
{
- return parse_int_file(
- 0, "/sys/devices/system/cpu/cpu%d/topology/core_id", cpu);
+ int ret;
+
+ ret = parse_int_file(0,
+ "/sys/devices/system/cpu/cpu%d/topology/core_id",
+ cpu);
+ if (ret < 0) {
+ int core_id, pkg_id, die_id;
+
+ ret = get_stored_topology_info(cpu, &core_id, &pkg_id, &die_id);
+ if (!ret)
+ return core_id;
+ }
+
+ return ret;
}
int get_physical_die_id(int cpu)
{
int ret;
- ret = parse_int_file(0, "/sys/devices/system/cpu/cpu%d/topology/die_id",
- cpu);
+ ret = parse_int_file(0,
+ "/sys/devices/system/cpu/cpu%d/topology/die_id",
+ cpu);
+ if (ret < 0) {
+ int core_id, pkg_id, die_id;
+
+ ret = get_stored_topology_info(cpu, &core_id, &pkg_id, &die_id);
+ if (!ret)
+ return die_id;
+ }
+
if (ret < 0)
ret = 0;
@@ -219,8 +352,14 @@ static void set_cpu_online_offline(int cpu, int state)
"/sys/devices/system/cpu/cpu%d/online", cpu);
fd = open(buffer, O_WRONLY);
- if (fd < 0)
+ if (fd < 0) {
+ if (!cpu && state) {
+ fprintf(stderr, "This system is not configured for CPU 0 online/offline\n");
+ fprintf(stderr, "Ignoring online request for CPU 0 as this is already online\n");
+ return;
+ }
err(-1, "%s open failed", buffer);
+ }
if (state)
ret = write(fd, "1\n", 2);
@@ -259,7 +398,12 @@ static void for_each_online_package_in_set(void (*callback)(int, void *, void *,
die_id = get_physical_die_id(i);
if (die_id < 0)
die_id = 0;
- pkg_id = get_physical_package_id(i);
+
+ pkg_id = parse_int_file(0,
+ "/sys/devices/system/cpu/cpu%d/topology/physical_package_id", i);
+ if (pkg_id < 0)
+ continue;
+
/* Create an unique id for package, die combination to store */
pkg_id = (MAX_PACKAGE_COUNT * pkg_id + die_id);
@@ -281,7 +425,7 @@ static void for_each_online_target_cpu_in_set(
void (*callback)(int, void *, void *, void *, void *), void *arg1,
void *arg2, void *arg3, void *arg4)
{
- int i;
+ int i, found = 0;
for (i = 0; i < topo_max_cpus; ++i) {
int online;
@@ -295,9 +439,14 @@ static void for_each_online_target_cpu_in_set(
online =
1; /* online entry for CPU 0 needs some special configs */
- if (online && callback)
+ if (online && callback) {
callback(i, arg1, arg2, arg3, arg4);
+ found = 1;
+ }
}
+
+ if (!found)
+ fprintf(stderr, "No valid CPU in the list\n");
}
#define BITMASK_SIZE 32
@@ -305,14 +454,27 @@ static void set_max_cpu_num(void)
{
FILE *filep;
unsigned long dummy;
+ int i;
topo_max_cpus = 0;
- filep = fopen_or_exit(
- "/sys/devices/system/cpu/cpu0/topology/thread_siblings", "r");
+ for (i = 0; i < 256; ++i) {
+ char path[256];
+
+ snprintf(path, sizeof(path),
+ "/sys/devices/system/cpu/cpu%d/topology/thread_siblings", i);
+ filep = fopen(path, "r");
+ if (filep)
+ break;
+ }
+
+ if (!filep) {
+ fprintf(stderr, "Can't get max cpu number\n");
+ exit(0);
+ }
+
while (fscanf(filep, "%lx,", &dummy) == 1)
topo_max_cpus += BITMASK_SIZE;
fclose(filep);
- topo_max_cpus--; /* 0 based */
debug_printf("max cpus %d\n", topo_max_cpus);
}
@@ -362,6 +524,10 @@ static void set_cpu_present_cpu_mask(void)
die_id = 0;
pkg_id = get_physical_package_id(i);
+ if (pkg_id < 0) {
+ fprintf(stderr, "Failed to get package id, CPU %d may be offline\n", i);
+ continue;
+ }
if (pkg_id < MAX_PACKAGE_COUNT &&
die_id < MAX_DIE_PER_PACKAGE) {
int core_id = get_physical_core_id(i);
@@ -542,7 +708,11 @@ static int isst_send_mmio_command(unsigned int cpu, unsigned int reg, int write,
}
if (ioctl(fd, cmd, &io_regs) == -1) {
- perror("ISST_IF_IO_CMD");
+ if (errno == ENOTTY) {
+ perror("ISST_IF_IO_COMMAND\n");
+ fprintf(stderr, "Check presence of kernel modules: isst_if_mmio\n");
+ exit(0);
+ }
fprintf(outf, "Error: mmio_cmd cpu:%d reg:%x read_write:%x\n",
cpu, reg, write);
} else {
@@ -571,7 +741,8 @@ int isst_send_mbox_command(unsigned int cpu, unsigned char command,
"mbox_send: cpu:%d command:%x sub_command:%x parameter:%x req_data:%x\n",
cpu, command, sub_command, parameter, req_data);
- if (isst_platform_info.mmio_supported && command == CONFIG_CLOS) {
+ if (!is_skx_based_platform() && command == CONFIG_CLOS &&
+ sub_command != CLOS_PM_QOS_CONFIG) {
unsigned int value;
int write = 0;
int clos_id, core_id, ret = 0;
@@ -620,10 +791,14 @@ int isst_send_mbox_command(unsigned int cpu, unsigned char command,
err(-1, "%s open failed", pathname);
if (ioctl(fd, ISST_IF_MBOX_COMMAND, &mbox_cmds) == -1) {
- perror("ISST_IF_MBOX_COMMAND");
- fprintf(outf,
- "Error: mbox_cmd cpu:%d command:%x sub_command:%x parameter:%x req_data:%x\n",
- cpu, command, sub_command, parameter, req_data);
+ if (errno == ENOTTY) {
+ perror("ISST_IF_MBOX_COMMAND\n");
+ fprintf(stderr, "Check presence of kernel modules: isst_if_mbox_pci or isst_if_mbox_msr\n");
+ exit(0);
+ }
+ debug_printf(
+ "Error: mbox_cmd cpu:%d command:%x sub_command:%x parameter:%x req_data:%x errorno:%d\n",
+ cpu, command, sub_command, parameter, req_data, errno);
return -1;
} else {
*resp = mbox_cmds.mbox_cmd[0].resp_data;
@@ -656,7 +831,7 @@ int isst_send_msr_command(unsigned int cpu, unsigned int msr, int write,
msr_cmds.msr_cmd[0].data = *req_resp;
if (ioctl(fd, ISST_IF_MSR_COMMAND, &msr_cmds) == -1) {
- perror("ISST_IF_MSR_COMMAD");
+ perror("ISST_IF_MSR_COMMAND");
fprintf(outf, "Error: msr_cmd cpu:%d msr:%x read_write:%d\n",
cpu, msr, write);
} else {
@@ -697,12 +872,85 @@ static int isst_fill_platform_info(void)
return 0;
}
+static void isst_print_extended_platform_info(void)
+{
+ int cp_state, cp_cap, fact_support = 0, pbf_support = 0;
+ struct isst_pkg_ctdp_level_info ctdp_level;
+ struct isst_pkg_ctdp pkg_dev;
+ int ret, i, j;
+ FILE *filep;
+
+ for (i = 0; i < 256; ++i) {
+ char path[256];
+
+ snprintf(path, sizeof(path),
+ "/sys/devices/system/cpu/cpu%d/topology/thread_siblings", i);
+ filep = fopen(path, "r");
+ if (filep)
+ break;
+ }
+
+ if (!filep)
+ return;
+
+ fclose(filep);
+
+ ret = isst_get_ctdp_levels(i, &pkg_dev);
+ if (ret)
+ return;
+
+ if (pkg_dev.enabled) {
+ fprintf(outf, "Intel(R) SST-PP (feature perf-profile) is supported\n");
+ } else {
+ fprintf(outf, "Intel(R) SST-PP (feature perf-profile) is not supported\n");
+ fprintf(outf, "Only performance level 0 (base level) is present\n");
+ }
+
+ if (pkg_dev.locked)
+ fprintf(outf, "TDP level change control is locked\n");
+ else
+ fprintf(outf, "TDP level change control is unlocked, max level: %d \n", pkg_dev.levels);
+
+ for (j = 0; j <= pkg_dev.levels; ++j) {
+ ret = isst_get_ctdp_control(i, j, &ctdp_level);
+ if (ret)
+ continue;
+
+ if (!fact_support && ctdp_level.fact_support)
+ fact_support = 1;
+
+ if (!pbf_support && ctdp_level.pbf_support)
+ pbf_support = 1;
+ }
+
+ if (fact_support)
+ fprintf(outf, "Intel(R) SST-TF (feature turbo-freq) is supported\n");
+ else
+ fprintf(outf, "Intel(R) SST-TF (feature turbo-freq) is not supported\n");
+
+ if (pbf_support)
+ fprintf(outf, "Intel(R) SST-BF (feature base-freq) is supported\n");
+ else
+ fprintf(outf, "Intel(R) SST-BF (feature base-freq) is not supported\n");
+
+ ret = isst_read_pm_config(i, &cp_state, &cp_cap);
+ if (cp_cap)
+ fprintf(outf, "Intel(R) SST-CP (feature core-power) is supported\n");
+ else
+ fprintf(outf, "Intel(R) SST-CP (feature core-power) is not supported\n");
+}
+
static void isst_print_platform_information(void)
{
struct isst_if_platform_info platform_info;
const char *pathname = "/dev/isst_interface";
int fd;
+ if (is_clx_n_platform()) {
+ fprintf(stderr, "\nThis option in not supported on this platform\n");
+ exit(0);
+ }
+
fd = open(pathname, O_RDWR);
if (fd < 0)
err(-1, "%s open failed", pathname);
@@ -718,6 +966,7 @@ static void isst_print_platform_information(void)
platform_info.mbox_supported);
fprintf(outf, "Platform: mmio supported : %d\n",
platform_info.mmio_supported);
+ isst_print_extended_platform_info();
}
close(fd);
@@ -725,6 +974,7 @@ static void isst_print_platform_information(void)
exit(0);
}
+static char *local_str0, *local_str1;
static void exec_on_get_ctdp_cpu(int cpu, void *arg1, void *arg2, void *arg3,
void *arg4)
{
@@ -734,13 +984,14 @@ static void exec_on_get_ctdp_cpu(int cpu, void *arg1, void *arg2, void *arg3,
fn_ptr = arg1;
ret = fn_ptr(cpu, arg2);
if (ret)
- perror("get_tdp_*");
+ isst_display_error_info_message(1, "get_tdp_* failed", 0, 0);
else
isst_ctdp_display_core_info(cpu, outf, arg3,
- *(unsigned int *)arg4);
+ *(unsigned int *)arg4,
+ local_str0, local_str1);
}
-#define _get_tdp_level(desc, suffix, object, help) \
+#define _get_tdp_level(desc, suffix, object, help, str0, str1) \
static void get_tdp_##object(int arg) \
{ \
struct isst_pkg_ctdp ctdp; \
@@ -751,6 +1002,8 @@ static void exec_on_get_ctdp_cpu(int cpu, void *arg1, void *arg2, void *arg3,
help); \
exit(0); \
} \
+ local_str0 = str0; \
+ local_str1 = str1; \
isst_ctdp_display_information_start(outf); \
if (max_target_cpus) \
for_each_online_target_cpu_in_set( \
@@ -764,12 +1017,12 @@ static void exec_on_get_ctdp_cpu(int cpu, void *arg1, void *arg2, void *arg3,
isst_ctdp_display_information_end(outf); \
}
-_get_tdp_level("get-config-levels", levels, levels, "TDP levels");
-_get_tdp_level("get-config-version", levels, version, "TDP version");
-_get_tdp_level("get-config-enabled", levels, enabled, "TDP enable status");
+_get_tdp_level("get-config-levels", levels, levels, "Max TDP level", NULL, NULL);
+_get_tdp_level("get-config-version", levels, version, "TDP version", NULL, NULL);
+_get_tdp_level("get-config-enabled", levels, enabled, "perf-profile enable status", "disabled", "enabled");
_get_tdp_level("get-config-current_level", levels, current_level,
- "Current TDP Level");
-_get_tdp_level("get-lock-status", levels, locked, "TDP lock status");
+ "Current TDP Level", NULL, NULL);
+_get_tdp_level("get-lock-status", levels, locked, "TDP lock status", "unlocked", "locked");
struct isst_pkg_ctdp clx_n_pkg_dev;
@@ -902,9 +1155,14 @@ static void dump_clx_n_config_for_cpu(int cpu, void *arg1, void *arg2,
{
int ret;
+ if (tdp_level != 0xff && tdp_level != 0) {
+ isst_display_error_info_message(1, "Invalid level", 1, tdp_level);
+ exit(0);
+ }
+
ret = clx_n_config(cpu);
if (ret) {
- perror("isst_get_process_ctdp");
+ debug_printf("clx_n_config failed");
} else {
struct isst_pkg_ctdp_level_info *ctdp_level;
struct isst_pbf_info *pbf_info;
@@ -926,7 +1184,9 @@ static void dump_isst_config_for_cpu(int cpu, void *arg1, void *arg2,
memset(&pkg_dev, 0, sizeof(pkg_dev));
ret = isst_get_process_ctdp(cpu, tdp_level, &pkg_dev);
if (ret) {
- perror("isst_get_process_ctdp");
+ isst_display_error_info_message(1, "Failed to get perf-profile info on cpu", 1, cpu);
+ isst_ctdp_display_information_end(outf);
+ exit(1);
} else {
isst_ctdp_display_information(cpu, outf, tdp_level, &pkg_dev);
isst_get_process_ctdp_complete(cpu, &pkg_dev);
@@ -969,9 +1229,11 @@ static void set_tdp_level_for_cpu(int cpu, void *arg1, void *arg2, void *arg3,
int ret;
ret = isst_set_tdp_level(cpu, tdp_level);
- if (ret)
- perror("set_tdp_level_for_cpu");
- else {
+ if (ret) {
+ isst_display_error_info_message(1, "Set TDP level failed", 0, 0);
+ isst_ctdp_display_information_end(outf);
+ exit(1);
+ } else {
isst_display_result(cpu, outf, "perf-profile", "set_tdp_level",
ret);
if (force_online_offline) {
@@ -1009,11 +1271,13 @@ static void set_tdp_level(int arg)
"\t Arguments: -l|--level : Specify tdp level\n");
fprintf(stderr,
"\t Optional Arguments: -o | online : online/offline for the tdp level\n");
+ fprintf(stderr,
+ "\t online/offline operation has limitations, refer to Linux hotplug documentation\n");
exit(0);
}
if (tdp_level == 0xff) {
- fprintf(outf, "Invalid command: specify tdp_level\n");
+ isst_display_error_info_message(1, "Invalid command: specify tdp_level", 0, 0);
exit(1);
}
isst_ctdp_display_information_start(outf);
@@ -1033,7 +1297,7 @@ static void clx_n_dump_pbf_config_for_cpu(int cpu, void *arg1, void *arg2,
ret = clx_n_config(cpu);
if (ret) {
- perror("isst_get_process_ctdp");
+ isst_display_error_info_message(1, "clx_n_config failed", 0, 0);
} else {
struct isst_pkg_ctdp_level_info *ctdp_level;
struct isst_pbf_info *pbf_info;
@@ -1054,7 +1318,9 @@ static void dump_pbf_config_for_cpu(int cpu, void *arg1, void *arg2, void *arg3,
ret = isst_get_pbf_info(cpu, tdp_level, &pbf_info);
if (ret) {
- perror("isst_get_pbf_info");
+ isst_display_error_info_message(1, "Failed to get base-freq info at this level", 1, tdp_level);
+ isst_ctdp_display_information_end(outf);
+ exit(1);
} else {
isst_pbf_display_information(cpu, outf, tdp_level, &pbf_info);
isst_get_pbf_info_complete(&pbf_info);
@@ -1074,7 +1340,7 @@ static void dump_pbf_config(int arg)
}
if (tdp_level == 0xff) {
- fprintf(outf, "Invalid command: specify tdp_level\n");
+ isst_display_error_info_message(1, "Invalid command: specify tdp_level", 0, 0);
exit(1);
}
@@ -1100,7 +1366,7 @@ static int set_clos_param(int cpu, int clos, int epp, int wt, int min, int max)
ret = isst_pm_get_clos(cpu, clos, &clos_config);
if (ret) {
- perror("isst_pm_get_clos");
+ isst_display_error_info_message(1, "isst_pm_get_clos failed", 0, 0);
return ret;
}
clos_config.clos_min = min;
@@ -1109,7 +1375,7 @@ static int set_clos_param(int cpu, int clos, int epp, int wt, int min, int max)
clos_config.clos_prop_prio = wt;
ret = isst_set_clos(cpu, clos, &clos_config);
if (ret) {
- perror("isst_pm_set_clos");
+ isst_display_error_info_message(1, "isst_set_clos failed", 0, 0);
return ret;
}
@@ -1153,7 +1419,7 @@ static int set_clx_pbf_cpufreq_scaling_min_max(int cpu)
ret = clx_n_config(cpu);
if (ret) {
- perror("set_clx_pbf_cpufreq_scaling_min_max");
+ debug_printf("cpufreq_scaling_min_max failed for CLX");
return ret;
}
@@ -1316,7 +1582,7 @@ static int set_core_priority_and_min(int cpu, int mask_size,
debug_printf("Associate cpu: %d clos: %d\n", i, clos);
ret = isst_clos_associate(i, clos);
if (ret) {
- perror("isst_clos_associate");
+ isst_display_error_info_message(1, "isst_clos_associate failed", 0, 0);
return ret;
}
}
@@ -1332,14 +1598,14 @@ static int set_pbf_core_power(int cpu)
ret = isst_get_ctdp_levels(cpu, &pkg_dev);
if (ret) {
- perror("isst_get_ctdp_levels");
+ debug_printf("isst_get_ctdp_levels failed");
return ret;
}
debug_printf("Current_level: %d\n", pkg_dev.current_level);
ret = isst_get_pbf_info(cpu, pkg_dev.current_level, &pbf_info);
if (ret) {
- perror("isst_get_pbf_info");
+ debug_printf("isst_get_pbf_info failed");
return ret;
}
debug_printf("p1_high: %d p1_low: %d\n", pbf_info.p1_high,
@@ -1349,13 +1615,13 @@ static int set_pbf_core_power(int cpu)
pbf_info.core_cpumask,
pbf_info.p1_high, pbf_info.p1_low);
if (ret) {
- perror("set_core_priority_and_min");
+ debug_printf("set_core_priority_and_min failed");
return ret;
}
ret = isst_pm_qos_config(cpu, 1, 1);
if (ret) {
- perror("isst_pm_qos_config");
+ debug_printf("isst_pm_qos_config failed");
return ret;
}
@@ -1369,17 +1635,13 @@ static void set_pbf_for_cpu(int cpu, void *arg1, void *arg2, void *arg3,
int status = *(int *)arg4;
if (is_clx_n_platform()) {
+ ret = 0;
if (status) {
- ret = 0;
- if (auto_mode)
- set_clx_pbf_cpufreq_scaling_min_max(cpu);
+ set_clx_pbf_cpufreq_scaling_min_max(cpu);
} else {
- ret = -1;
- if (auto_mode) {
- set_scaling_max_to_cpuinfo_max(cpu);
- set_scaling_min_to_cpuinfo_min(cpu);
- }
+ set_scaling_max_to_cpuinfo_max(cpu);
+ set_scaling_min_to_cpuinfo_min(cpu);
}
goto disp_result;
}
@@ -1392,7 +1654,7 @@ static void set_pbf_for_cpu(int cpu, void *arg1, void *arg2, void *arg3,
ret = isst_set_pbf_fact_status(cpu, 1, status);
if (ret) {
- perror("isst_set_pbf");
+ debug_printf("isst_set_pbf_fact_status failed");
if (auto_mode)
isst_pm_qos_config(cpu, 0, 0);
} else {
@@ -1405,7 +1667,7 @@ static void set_pbf_for_cpu(int cpu, void *arg1, void *arg2, void *arg3,
}
if (auto_mode && !status)
- isst_pm_qos_config(cpu, 0, 0);
+ isst_pm_qos_config(cpu, 0, 1);
disp_result:
if (status)
@@ -1424,10 +1686,25 @@ static void set_pbf_enable(int arg)
if (enable) {
fprintf(stderr,
"Enable Intel Speed Select Technology base frequency feature\n");
+ if (is_clx_n_platform()) {
+ fprintf(stderr,
+ "\tOn this platform this command doesn't enable feature in the hardware.\n");
+ fprintf(stderr,
+ "\tIt updates the cpufreq scaling_min_freq to match cpufreq base_frequency.\n");
+ exit(0);
+
+ }
fprintf(stderr,
"\tOptional Arguments: -a|--auto : Use priority of cores to set core-power associations\n");
} else {
+ if (is_clx_n_platform()) {
+ fprintf(stderr,
+ "\tOn this platform this command doesn't disable feature in the hardware.\n");
+ fprintf(stderr,
+ "\tIt updates the cpufreq scaling_min_freq to match cpuinfo_min_freq\n");
+ exit(0);
+ }
fprintf(stderr,
"Disable Intel Speed Select Technology base frequency feature\n");
fprintf(stderr,
@@ -1452,12 +1729,15 @@ static void dump_fact_config_for_cpu(int cpu, void *arg1, void *arg2,
struct isst_fact_info fact_info;
int ret;
- ret = isst_get_fact_info(cpu, tdp_level, &fact_info);
- if (ret)
- perror("isst_get_fact_bucket_info");
- else
+ ret = isst_get_fact_info(cpu, tdp_level, fact_bucket, &fact_info);
+ if (ret) {
+ isst_display_error_info_message(1, "Failed to get turbo-freq info at this level", 1, tdp_level);
+ isst_ctdp_display_information_end(outf);
+ exit(1);
+ } else {
isst_fact_display_information(cpu, outf, tdp_level, fact_bucket,
fact_avx, &fact_info);
+ }
}
static void dump_fact_config(int arg)
@@ -1475,7 +1755,7 @@ static void dump_fact_config(int arg)
}
if (tdp_level == 0xff) {
- fprintf(outf, "Invalid command: specify tdp_level\n");
+ isst_display_error_info_message(1, "Invalid command: specify tdp_level\n", 0, 0);
exit(1);
}
@@ -1503,7 +1783,7 @@ static void set_fact_for_cpu(int cpu, void *arg1, void *arg2, void *arg3,
ret = isst_set_pbf_fact_status(cpu, 0, status);
if (ret) {
- perror("isst_set_fact");
+ debug_printf("isst_set_pbf_fact_status failed");
if (auto_mode)
isst_pm_qos_config(cpu, 0, 0);
@@ -1527,6 +1807,8 @@ static void set_fact_for_cpu(int cpu, void *arg1, void *arg2, void *arg3,
disp_results:
if (status) {
isst_display_result(cpu, outf, "turbo-freq", "enable", ret);
+ if (ret)
+ fact_enable_fail = ret;
} else {
/* Since we modified TRL during Fact enable, restore it */
isst_set_trl_from_current_tdp(cpu, fact_trl);
@@ -1568,7 +1850,7 @@ static void set_fact_enable(int arg)
NULL, &enable);
isst_ctdp_display_information_end(outf);
- if (enable && auto_mode) {
+ if (!fact_enable_fail && enable && auto_mode) {
/*
* When we adjust CLOS param, we have to set for siblings also.
* So for the each user specified CPU, also add the sibling
@@ -1652,9 +1934,12 @@ static void enable_clos_qos_config(int cpu, void *arg1, void *arg2, void *arg3,
int ret;
int status = *(int *)arg4;
+ if (is_skx_based_platform())
+ clos_priority_type = 1;
+
ret = isst_pm_qos_config(cpu, status, clos_priority_type);
if (ret)
- perror("isst_pm_qos_config");
+ isst_display_error_info_message(1, "isst_pm_qos_config failed", 0, 0);
if (status)
isst_display_result(cpu, outf, "core-power", "enable",
@@ -1672,9 +1957,11 @@ static void set_clos_enable(int arg)
if (enable) {
fprintf(stderr,
"Enable core-power for a package/die\n");
- fprintf(stderr,
- "\tClos Enable: Specify priority type with [--priority|-p]\n");
- fprintf(stderr, "\t\t 0: Proportional, 1: Ordered\n");
+ if (!is_skx_based_platform()) {
+ fprintf(stderr,
+ "\tClos Enable: Specify priority type with [--priority|-p]\n");
+ fprintf(stderr, "\t\t 0: Proportional, 1: Ordered\n");
+ }
} else {
fprintf(stderr,
"Disable core-power: [No command arguments are required]\n");
@@ -1705,7 +1992,7 @@ static void dump_clos_config_for_cpu(int cpu, void *arg1, void *arg2,
ret = isst_pm_get_clos(cpu, current_clos, &clos_config);
if (ret)
- perror("isst_pm_get_clos");
+ isst_display_error_info_message(1, "isst_pm_get_clos failed", 0, 0);
else
isst_clos_display_information(cpu, outf, current_clos,
&clos_config);
@@ -1721,7 +2008,8 @@ static void dump_clos_config(int arg)
exit(0);
}
if (current_clos < 0 || current_clos > 3) {
- fprintf(stderr, "Invalid clos id\n");
+ isst_display_error_info_message(1, "Invalid clos id\n", 0, 0);
+ isst_ctdp_display_information_end(outf);
exit(0);
}
@@ -1742,9 +2030,14 @@ static void get_clos_info_for_cpu(int cpu, void *arg1, void *arg2, void *arg3,
ret = isst_clos_get_clos_information(cpu, &enable, &prio_type);
if (ret)
- perror("isst_clos_get_info");
- else
- isst_clos_display_clos_information(cpu, outf, enable, prio_type);
+ isst_display_error_info_message(1, "isst_clos_get_info failed", 0, 0);
+ else {
+ int cp_state, cp_cap;
+
+ isst_read_pm_config(cpu, &cp_state, &cp_cap);
+ isst_clos_display_clos_information(cpu, outf, enable, prio_type,
+ cp_state, cp_cap);
+ }
}
static void dump_clos_info(int arg)
@@ -1752,19 +2045,17 @@ static void dump_clos_info(int arg)
if (cmd_help) {
fprintf(stderr,
"Print Intel Speed Select Technology core power information\n");
- fprintf(stderr, "\tSpecify targeted cpu id with [--cpu|-c]\n");
- exit(0);
- }
-
- if (!max_target_cpus) {
- fprintf(stderr,
- "Invalid target cpu. Specify with [-c|--cpu]\n");
+ fprintf(stderr, "\t Optionally specify targeted cpu id with [--cpu|-c]\n");
exit(0);
}
isst_ctdp_display_information_start(outf);
- for_each_online_target_cpu_in_set(get_clos_info_for_cpu, NULL,
- NULL, NULL, NULL);
+ if (max_target_cpus)
+ for_each_online_target_cpu_in_set(get_clos_info_for_cpu, NULL,
+ NULL, NULL, NULL);
+ else
+ for_each_online_package_in_set(get_clos_info_for_cpu, NULL,
+ NULL, NULL, NULL);
isst_ctdp_display_information_end(outf);
}
@@ -1785,7 +2076,7 @@ static void set_clos_config_for_cpu(int cpu, void *arg1, void *arg2, void *arg3,
clos_config.clos_desired = clos_desired;
ret = isst_set_clos(cpu, current_clos, &clos_config);
if (ret)
- perror("isst_set_clos");
+ isst_display_error_info_message(1, "isst_set_clos failed", 0, 0);
else
isst_display_result(cpu, outf, "core-power", "config", ret);
}
@@ -1797,26 +2088,27 @@ static void set_clos_config(int arg)
"Set core-power configuration for one of the four clos ids\n");
fprintf(stderr,
"\tSpecify targeted clos id with [--clos|-c]\n");
- fprintf(stderr, "\tSpecify clos EPP with [--epp|-e]\n");
- fprintf(stderr,
- "\tSpecify clos Proportional Priority [--weight|-w]\n");
+ if (!is_skx_based_platform()) {
+ fprintf(stderr, "\tSpecify clos EPP with [--epp|-e]\n");
+ fprintf(stderr,
+ "\tSpecify clos Proportional Priority [--weight|-w]\n");
+ }
fprintf(stderr, "\tSpecify clos min in MHz with [--min|-n]\n");
fprintf(stderr, "\tSpecify clos max in MHz with [--max|-m]\n");
- fprintf(stderr, "\tSpecify clos desired in MHz with [--desired|-d]\n");
exit(0);
}
if (current_clos < 0 || current_clos > 3) {
- fprintf(stderr, "Invalid clos id\n");
+ isst_display_error_info_message(1, "Invalid clos id\n", 0, 0);
exit(0);
}
- if (clos_epp < 0 || clos_epp > 0x0F) {
- fprintf(stderr, "clos epp is not specified, default: 0\n");
+ if (!is_skx_based_platform() && (clos_epp < 0 || clos_epp > 0x0F)) {
+ fprintf(stderr, "clos epp is not specified or invalid, default: 0\n");
clos_epp = 0;
}
- if (clos_prop_prio < 0 || clos_prop_prio > 0x0F) {
+ if (!is_skx_based_platform() && (clos_prop_prio < 0 || clos_prop_prio > 0x0F)) {
fprintf(stderr,
- "clos frequency weight is not specified, default: 0\n");
+ "clos frequency weight is not specified or invalid, default: 0\n");
clos_prop_prio = 0;
}
if (clos_min < 0) {
@@ -1824,11 +2116,11 @@ static void set_clos_config(int arg)
clos_min = 0;
}
if (clos_max < 0) {
- fprintf(stderr, "clos max is not specified, default: 25500 MHz\n");
+ fprintf(stderr, "clos max is not specified, default: Max frequency (ratio 0xff)\n");
clos_max = 0xff;
}
- if (clos_desired < 0) {
- fprintf(stderr, "clos desired is not specified, default: 0\n");
+ if (clos_desired) {
+ fprintf(stderr, "clos desired is not supported on this platform\n");
clos_desired = 0x00;
}
@@ -1849,7 +2141,7 @@ static void set_clos_assoc_for_cpu(int cpu, void *arg1, void *arg2, void *arg3,
ret = isst_clos_associate(cpu, current_clos);
if (ret)
- perror("isst_clos_associate");
+ debug_printf("isst_clos_associate failed");
else
isst_display_result(cpu, outf, "core-power", "assoc", ret);
}
@@ -1860,19 +2152,22 @@ static void set_clos_assoc(int arg)
fprintf(stderr, "Associate a clos id to a CPU\n");
fprintf(stderr,
"\tSpecify targeted clos id with [--clos|-c]\n");
+ fprintf(stderr,
+ "\tFor example to associate clos 1 to CPU 0: issue\n");
+ fprintf(stderr,
+ "\tintel-speed-select --cpu 0 core-power assoc --clos 1\n");
exit(0);
}
if (current_clos < 0 || current_clos > 3) {
- fprintf(stderr, "Invalid clos id\n");
+ isst_display_error_info_message(1, "Invalid clos id\n", 0, 0);
exit(0);
}
if (max_target_cpus)
for_each_online_target_cpu_in_set(set_clos_assoc_for_cpu, NULL,
NULL, NULL, NULL);
else {
- fprintf(stderr,
- "Invalid target cpu. Specify with [-c|--cpu]\n");
+ isst_display_error_info_message(1, "Invalid target cpu. Specify with [-c|--cpu]", 0, 0);
}
}
@@ -1883,7 +2178,7 @@ static void get_clos_assoc_for_cpu(int cpu, void *arg1, void *arg2, void *arg3,
ret = isst_clos_get_assoc_status(cpu, &clos);
if (ret)
- perror("isst_clos_get_assoc_status");
+ isst_display_error_info_message(1, "isst_clos_get_assoc_status failed", 0, 0);
else
isst_clos_display_assoc_information(cpu, outf, clos);
}
@@ -1897,8 +2192,7 @@ static void get_clos_assoc(int arg)
}
if (!max_target_cpus) {
- fprintf(stderr,
- "Invalid target cpu. Specify with [-c|--cpu]\n");
+ isst_display_error_info_message(1, "Invalid target cpu. Specify with [-c|--cpu]", 0, 0);
exit(0);
}
@@ -2035,7 +2329,7 @@ static void parse_cmd_args(int argc, int start, char **argv)
option_index = start;
optind = start + 1;
- while ((opt = getopt_long(argc, argv, "b:l:t:c:d:e:n:m:p:w:hoa",
+ while ((opt = getopt_long(argc, argv, "b:l:t:c:d:e:n:m:p:w:r:hoa",
long_options, &option_index)) != -1) {
switch (opt) {
case 'a':
@@ -2061,7 +2355,7 @@ static void parse_cmd_args(int argc, int start, char **argv)
fact_avx = 0x01;
} else if (!strncmp(optarg, "avx2", 4)) {
fact_avx = 0x02;
- } else if (!strncmp(optarg, "avx512", 4)) {
+ } else if (!strncmp(optarg, "avx512", 6)) {
fact_avx = 0x04;
} else {
fprintf(outf, "Invalid sse,avx options\n");
@@ -2078,6 +2372,10 @@ static void parse_cmd_args(int argc, int start, char **argv)
break;
case 'e':
clos_epp = atoi(optarg);
+ if (is_skx_based_platform()) {
+ isst_display_error_info_message(1, "epp can't be specified on this platform", 0, 0);
+ exit(0);
+ }
break;
case 'n':
clos_min = atoi(optarg);
@@ -2089,14 +2387,25 @@ static void parse_cmd_args(int argc, int start, char **argv)
break;
case 'p':
clos_priority_type = atoi(optarg);
+ if (is_skx_based_platform() && !clos_priority_type) {
+ isst_display_error_info_message(1, "Invalid clos priority type: proportional for this platform", 0, 0);
+ exit(0);
+ }
break;
case 'w':
clos_prop_prio = atoi(optarg);
+ if (is_skx_based_platform()) {
+ isst_display_error_info_message(1, "weight can't be specified on this platform", 0, 0);
+ exit(0);
+ }
break;
default:
- printf("no match\n");
+ printf("Unknown option: ignore\n");
}
}
+
+ if (argv[optind])
+ printf("Garbage at the end of command: ignore\n");
}
static void isst_help(void)
@@ -2214,11 +2523,18 @@ void process_command(int argc, char **argv,
static void usage(void)
{
- printf("Intel(R) Speed Select Technology\n");
+ if (is_clx_n_platform()) {
+ fprintf(stderr, "\nThere is limited support of Intel Speed Select features on this platform.\n");
+ fprintf(stderr, "Everything is pre-configured using BIOS options, this tool can't enable any feature in the hardware.\n\n");
+ }
+
printf("\nUsage:\n");
printf("intel-speed-select [OPTIONS] FEATURE COMMAND COMMAND_ARGUMENTS\n");
- printf("\nUse this tool to enumerate and control the Intel Speed Select Technology features,\n");
- printf("\nFEATURE : [perf-profile|base-freq|turbo-freq|core-power]\n");
+ printf("\nUse this tool to enumerate and control the Intel Speed Select Technology features:\n");
+ if (is_clx_n_platform())
+ printf("\nFEATURE : [perf-profile|base-freq]\n");
+ else
+ printf("\nFEATURE : [perf-profile|base-freq|turbo-freq|core-power]\n");
printf("\nFor help on each feature, use -h|--help\n");
printf("\tFor example: intel-speed-select perf-profile -h\n");
@@ -2231,17 +2547,29 @@ static void usage(void)
printf("\t\tDefault: Die scoped for all dies in the system with multiple dies/package\n");
printf("\t\t\t Or Package scoped for all Packages when each package contains one die\n");
printf("\t[-d|--debug] : Debug mode\n");
+ printf("\t[-f|--format] : output format [json|text]. Default: text\n");
printf("\t[-h|--help] : Print help\n");
printf("\t[-i|--info] : Print platform information\n");
printf("\t[-o|--out] : Output file\n");
printf("\t\t\tDefault : stderr\n");
- printf("\t[-f|--format] : output format [json|text]. Default: text\n");
printf("\t[-v|--version] : Print version\n");
printf("\nResult format\n");
printf("\tResult display uses a common format for each command:\n");
printf("\tResults are formatted in text/JSON with\n");
printf("\t\tPackage, Die, CPU, and command specific results.\n");
+
+ printf("\nExamples\n");
+ printf("\tTo get platform information:\n");
+ printf("\t\tintel-speed-select --info\n");
+ printf("\tTo get full perf-profile information dump:\n");
+ printf("\t\tintel-speed-select perf-profile info\n");
+ printf("\tTo get full base-freq information dump:\n");
+ printf("\t\tintel-speed-select base-freq info -l 0\n");
+ if (!is_clx_n_platform()) {
+ printf("\tTo get full turbo-freq information dump:\n");
+ printf("\t\tintel-speed-select turbo-freq info -l 0\n");
+ }
exit(1);
}
@@ -2254,6 +2582,8 @@ static void print_version(void)
static void cmdline(int argc, char **argv)
{
+ const char *pathname = "/dev/isst_interface";
+ FILE *fp;
int opt;
int option_index = 0;
int ret;
@@ -2269,6 +2599,28 @@ static void cmdline(int argc, char **argv)
{ 0, 0, 0, 0 }
};
+ if (geteuid() != 0) {
+ fprintf(stderr, "Must run as root\n");
+ exit(0);
+ }
+
+ ret = update_cpu_model();
+ if (ret)
+ err(-1, "Invalid CPU model (%d)\n", cpu_model);
+ printf("Intel(R) Speed Select Technology\n");
+ printf("Executing on CPU model:%d[0x%x]\n", cpu_model, cpu_model);
+
+ if (!is_clx_n_platform()) {
+ fp = fopen(pathname, "rb");
+ if (!fp) {
+ fprintf(stderr, "Intel speed select drivers are not loaded on this system.\n");
+ fprintf(stderr, "Verify that kernel config includes CONFIG_INTEL_SPEED_SELECT_INTERFACE.\n");
+ fprintf(stderr, "If the config is included then this is not a supported platform.\n");
+ exit(0);
+ }
+ fclose(fp);
+ }
+
progname = argv[0];
while ((opt = getopt_long_only(argc, argv, "+c:df:hio:v", long_options,
&option_index)) != -1) {
@@ -2303,21 +2655,12 @@ static void cmdline(int argc, char **argv)
}
}
- if (geteuid() != 0) {
- fprintf(stderr, "Must run as root\n");
- exit(0);
- }
-
if (optind > (argc - 2)) {
- fprintf(stderr, "Feature name and|or command not specified\n");
+ usage();
exit(0);
}
- ret = update_cpu_model();
- if (ret)
- err(-1, "Invalid CPU model (%d)\n", cpu_model);
- printf("Intel(R) Speed Select Technology\n");
- printf("Executing on CPU model:%d[0x%x]\n", cpu_model, cpu_model);
set_max_cpu_num();
+ store_cpu_topology();
set_cpu_present_cpu_mask();
set_cpu_target_cpu_mask();
diff --git a/tools/power/x86/intel-speed-select/isst-core.c b/tools/power/x86/intel-speed-select/isst-core.c
index 81a119f688a3..67c9b1139631 100644
--- a/tools/power/x86/intel-speed-select/isst-core.c
+++ b/tools/power/x86/intel-speed-select/isst-core.c
@@ -114,8 +114,10 @@ int isst_get_tdp_info(int cpu, int config_index,
ret = isst_send_mbox_command(cpu, CONFIG_TDP, CONFIG_TDP_GET_TDP_INFO,
0, config_index, &resp);
- if (ret)
+ if (ret) {
+ isst_display_error_info_message(1, "Invalid level, Can't get TDP information at level", 1, config_index);
return ret;
+ }
ctdp_level->pkg_tdp = resp & GENMASK(14, 0);
ctdp_level->tdp_ratio = (resp & GENMASK(23, 16)) >> 16;
@@ -352,7 +354,7 @@ int isst_set_tdp_level_msr(int cpu, int tdp_level)
debug_printf("cpu: tdp_level via MSR %d\n", cpu, tdp_level);
if (isst_get_config_tdp_lock_status(cpu)) {
- debug_printf("cpu: tdp_locked %d\n", cpu);
+ isst_display_error_info_message(1, "tdp_locked", 0, 0);
return -1;
}
@@ -373,19 +375,50 @@ int isst_set_tdp_level(int cpu, int tdp_level)
unsigned int resp;
int ret;
+
+ if (isst_get_config_tdp_lock_status(cpu)) {
+ isst_display_error_info_message(1, "TDP is locked", 0, 0);
+ return -1;
+
+ }
+
ret = isst_send_mbox_command(cpu, CONFIG_TDP, CONFIG_TDP_SET_LEVEL, 0,
tdp_level, &resp);
- if (ret)
- return isst_set_tdp_level_msr(cpu, tdp_level);
+ if (ret) {
+ isst_display_error_info_message(1, "Set TDP level failed for level", 1, tdp_level);
+ return ret;
+ }
return 0;
}
int isst_get_pbf_info(int cpu, int level, struct isst_pbf_info *pbf_info)
{
+ struct isst_pkg_ctdp_level_info ctdp_level;
+ struct isst_pkg_ctdp pkg_dev;
int i, ret, core_cnt, max;
unsigned int req, resp;
+ ret = isst_get_ctdp_levels(cpu, &pkg_dev);
+ if (ret) {
+ isst_display_error_info_message(1, "Failed to get number of levels", 0, 0);
+ return ret;
+ }
+
+ if (level > pkg_dev.levels) {
+ isst_display_error_info_message(1, "Invalid level", 1, level);
+ return -1;
+ }
+
+ ret = isst_get_ctdp_control(cpu, level, &ctdp_level);
+ if (ret)
+ return ret;
+
+ if (!ctdp_level.pbf_support) {
+ isst_display_error_info_message(1, "base-freq feature is not present at this level", 1, level);
+ return -1;
+ }
+
pbf_info->core_cpumask_size = alloc_cpu_set(&pbf_info->core_cpumask);
core_cnt = get_core_count(get_physical_package_id(cpu), get_physical_die_id(cpu));
@@ -481,6 +514,10 @@ int isst_set_pbf_fact_status(int cpu, int pbf, int enable)
else
req &= ~BIT(17);
} else {
+
+ if (enable && !ctdp_level.sst_cp_enabled)
+ isst_display_error_info_message(0, "Make sure to execute before: core-power enable", 0, 0);
+
if (ctdp_level.pbf_enabled)
req = BIT(17);
@@ -566,10 +603,32 @@ int isst_get_fact_bucket_info(int cpu, int level,
return 0;
}
-int isst_get_fact_info(int cpu, int level, struct isst_fact_info *fact_info)
+int isst_get_fact_info(int cpu, int level, int fact_bucket, struct isst_fact_info *fact_info)
{
+ struct isst_pkg_ctdp_level_info ctdp_level;
+ struct isst_pkg_ctdp pkg_dev;
unsigned int resp;
- int ret;
+ int j, ret, print;
+
+ ret = isst_get_ctdp_levels(cpu, &pkg_dev);
+ if (ret) {
+ isst_display_error_info_message(1, "Failed to get number of levels", 0, 0);
+ return ret;
+ }
+
+ if (level > pkg_dev.levels) {
+ isst_display_error_info_message(1, "Invalid level", 1, level);
+ return -1;
+ }
+
+ ret = isst_get_ctdp_control(cpu, level, &ctdp_level);
+ if (ret)
+ return ret;
+
+ if (!ctdp_level.fact_support) {
+ isst_display_error_info_message(1, "turbo-freq feature is not present at this level", 1, level);
+ return -1;
+ }
ret = isst_send_mbox_command(cpu, CONFIG_TDP,
CONFIG_TDP_GET_FACT_LP_CLIPPING_RATIO, 0,
@@ -585,8 +644,25 @@ int isst_get_fact_info(int cpu, int level, struct isst_fact_info *fact_info)
fact_info->lp_clipping_ratio_license_avx512 = (resp >> 16) & 0xff;
ret = isst_get_fact_bucket_info(cpu, level, fact_info->bucket_info);
+ if (ret)
+ return ret;
- return ret;
+ print = 0;
+ for (j = 0; j < ISST_FACT_MAX_BUCKETS; ++j) {
+ if (fact_bucket != 0xff && fact_bucket != j)
+ continue;
+
+ if (!fact_info->bucket_info[j].high_priority_cores_count)
+ break;
+
+ print = 1;
+ }
+ if (!print) {
+ isst_display_error_info_message(1, "Invalid bucket", 0, 0);
+ return -1;
+ }
+
+ return 0;
}
int isst_set_trl(int cpu, unsigned long long trl)
@@ -671,7 +747,7 @@ void isst_get_process_ctdp_complete(int cpu, struct isst_pkg_ctdp *pkg_dev)
int isst_get_process_ctdp(int cpu, int tdp_level, struct isst_pkg_ctdp *pkg_dev)
{
- int i, ret;
+ int i, ret, valid = 0;
if (pkg_dev->processed)
return 0;
@@ -684,6 +760,14 @@ int isst_get_process_ctdp(int cpu, int tdp_level, struct isst_pkg_ctdp *pkg_dev)
cpu, pkg_dev->enabled, pkg_dev->current_level,
pkg_dev->levels);
+ if (tdp_level != 0xff && tdp_level > pkg_dev->levels) {
+ isst_display_error_info_message(1, "Invalid level", 0, 0);
+ return -1;
+ }
+
+ if (!pkg_dev->enabled)
+ isst_display_error_info_message(0, "perf-profile feature is not supported, just base-config level 0 is valid", 0, 0);
+
for (i = 0; i <= pkg_dev->levels; ++i) {
struct isst_pkg_ctdp_level_info *ctdp_level;
@@ -703,6 +787,7 @@ int isst_get_process_ctdp(int cpu, int tdp_level, struct isst_pkg_ctdp *pkg_dev)
if (ret)
continue;
+ valid = 1;
pkg_dev->processed = 1;
ctdp_level->processed = 1;
@@ -713,7 +798,7 @@ int isst_get_process_ctdp(int cpu, int tdp_level, struct isst_pkg_ctdp *pkg_dev)
}
if (ctdp_level->fact_support) {
- ret = isst_get_fact_info(cpu, i,
+ ret = isst_get_fact_info(cpu, i, 0xff,
&ctdp_level->fact_info);
if (ret)
return ret;
@@ -775,6 +860,9 @@ int isst_get_process_ctdp(int cpu, int tdp_level, struct isst_pkg_ctdp *pkg_dev)
isst_get_uncore_mem_freq(cpu, i, ctdp_level);
}
+ if (!valid)
+ isst_display_error_info_message(0, "Invalid level, Can't get TDP control information at specified levels on cpu", 1, cpu);
+
return 0;
}
@@ -829,17 +917,19 @@ int isst_pm_qos_config(int cpu, int enable_clos, int priority_type)
}
ret = isst_write_pm_config(cpu, 0);
if (ret)
- perror("isst_write_pm_config\n");
+ isst_display_error_info_message(0, "WRITE_PM_CONFIG command failed, ignoring error\n", 0, 0);
} else {
ret = isst_write_pm_config(cpu, 1);
if (ret)
- perror("isst_write_pm_config\n");
+ isst_display_error_info_message(0, "WRITE_PM_CONFIG command failed, ignoring error\n", 0, 0);
}
ret = isst_send_mbox_command(cpu, CONFIG_CLOS, CLOS_PM_QOS_CONFIG, 0, 0,
&resp);
- if (ret)
+ if (ret) {
+ isst_display_error_info_message(1, "CLOS_PM_QOS_CONFIG command failed", 0, 0);
return ret;
+ }
debug_printf("cpu:%d CLOS_PM_QOS_CONFIG resp:%x\n", cpu, resp);
@@ -850,6 +940,9 @@ int isst_pm_qos_config(int cpu, int enable_clos, int priority_type)
else
req = req & ~BIT(1);
+ if (priority_type > 1)
+ isst_display_error_info_message(1, "Invalid priority type: Changing type to ordered", 0, 0);
+
if (priority_type)
req = req | BIT(2);
else
diff --git a/tools/power/x86/intel-speed-select/isst-display.c b/tools/power/x86/intel-speed-select/isst-display.c
index 4fb0c1d49d64..51dbaa5f02ec 100644
--- a/tools/power/x86/intel-speed-select/isst-display.c
+++ b/tools/power/x86/intel-speed-select/isst-display.c
@@ -158,10 +158,17 @@ static void format_and_print(FILE *outf, int level, char *header, char *value)
last_level = level;
}
-static void print_package_info(int cpu, FILE *outf)
+static int print_package_info(int cpu, FILE *outf)
{
char header[256];
+ if (out_format_is_json()) {
+ snprintf(header, sizeof(header), "package-%d:die-%d:cpu-%d",
+ get_physical_package_id(cpu), get_physical_die_id(cpu),
+ cpu);
+ format_and_print(outf, 1, header, NULL);
+ return 1;
+ }
snprintf(header, sizeof(header), "package-%d",
get_physical_package_id(cpu));
format_and_print(outf, 1, header, NULL);
@@ -169,6 +176,8 @@ static void print_package_info(int cpu, FILE *outf)
format_and_print(outf, 2, header, NULL);
snprintf(header, sizeof(header), "cpu-%d", cpu);
format_and_print(outf, 3, header, NULL);
+
+ return 3;
}
static void _isst_pbf_display_information(int cpu, FILE *outf, int level,
@@ -178,7 +187,7 @@ static void _isst_pbf_display_information(int cpu, FILE *outf, int level,
char header[256];
char value[256];
- snprintf(header, sizeof(header), "speed-select-base-freq");
+ snprintf(header, sizeof(header), "speed-select-base-freq-properties");
format_and_print(outf, disp_level, header, NULL);
snprintf(header, sizeof(header), "high-priority-base-frequency(MHz)");
@@ -222,9 +231,23 @@ static void _isst_fact_display_information(int cpu, FILE *outf, int level,
struct isst_fact_bucket_info *bucket_info = fact_info->bucket_info;
char header[256];
char value[256];
- int j;
+ int print = 0, j;
+
+ for (j = 0; j < ISST_FACT_MAX_BUCKETS; ++j) {
+ if (fact_bucket != 0xff && fact_bucket != j)
+ continue;
+
+ if (!bucket_info[j].high_priority_cores_count)
+ break;
- snprintf(header, sizeof(header), "speed-select-turbo-freq");
+ print = 1;
+ }
+ if (!print) {
+ fprintf(stderr, "Invalid bucket\n");
+ return;
+ }
+
+ snprintf(header, sizeof(header), "speed-select-turbo-freq-properties");
format_and_print(outf, base_level, header, NULL);
for (j = 0; j < ISST_FACT_MAX_BUCKETS; ++j) {
if (fact_bucket != 0xff && fact_bucket != j)
@@ -289,7 +312,7 @@ static void _isst_fact_display_information(int cpu, FILE *outf, int level,
}
void isst_ctdp_display_core_info(int cpu, FILE *outf, char *prefix,
- unsigned int val)
+ unsigned int val, char *str0, char *str1)
{
char header[256];
char value[256];
@@ -301,8 +324,12 @@ void isst_ctdp_display_core_info(int cpu, FILE *outf, char *prefix,
format_and_print(outf, 2, header, NULL);
snprintf(header, sizeof(header), "cpu-%d", cpu);
format_and_print(outf, 3, header, NULL);
-
- snprintf(value, sizeof(value), "%u", val);
+ if (str0 && !val)
+ snprintf(value, sizeof(value), "%s", str0);
+ else if (str1 && val)
+ snprintf(value, sizeof(value), "%s", str1);
+ else
+ snprintf(value, sizeof(value), "%u", val);
format_and_print(outf, 4, prefix, value);
format_and_print(outf, 1, NULL, NULL);
@@ -313,10 +340,11 @@ void isst_ctdp_display_information(int cpu, FILE *outf, int tdp_level,
{
char header[256];
char value[256];
- int i, base_level = 1;
+ static int level;
+ int i;
if (pkg_dev->processed)
- print_package_info(cpu, outf);
+ level = print_package_info(cpu, outf);
for (i = 0; i <= pkg_dev->levels; ++i) {
struct isst_pkg_ctdp_level_info *ctdp_level;
@@ -328,72 +356,80 @@ void isst_ctdp_display_information(int cpu, FILE *outf, int tdp_level,
snprintf(header, sizeof(header), "perf-profile-level-%d",
ctdp_level->level);
- format_and_print(outf, base_level + 3, header, NULL);
+ format_and_print(outf, level + 1, header, NULL);
snprintf(header, sizeof(header), "cpu-count");
j = get_cpu_count(get_physical_die_id(cpu),
get_physical_die_id(cpu));
snprintf(value, sizeof(value), "%d", j);
- format_and_print(outf, base_level + 4, header, value);
+ format_and_print(outf, level + 2, header, value);
+
+ j = CPU_COUNT_S(ctdp_level->core_cpumask_size,
+ ctdp_level->core_cpumask);
+ if (j) {
+ snprintf(header, sizeof(header), "enable-cpu-count");
+ snprintf(value, sizeof(value), "%d", j);
+ format_and_print(outf, level + 2, header, value);
+ }
if (ctdp_level->core_cpumask_size) {
snprintf(header, sizeof(header), "enable-cpu-mask");
printcpumask(sizeof(value), value,
ctdp_level->core_cpumask_size,
ctdp_level->core_cpumask);
- format_and_print(outf, base_level + 4, header, value);
+ format_and_print(outf, level + 2, header, value);
snprintf(header, sizeof(header), "enable-cpu-list");
printcpulist(sizeof(value), value,
ctdp_level->core_cpumask_size,
ctdp_level->core_cpumask);
- format_and_print(outf, base_level + 4, header, value);
+ format_and_print(outf, level + 2, header, value);
}
snprintf(header, sizeof(header), "thermal-design-power-ratio");
snprintf(value, sizeof(value), "%d", ctdp_level->tdp_ratio);
- format_and_print(outf, base_level + 4, header, value);
+ format_and_print(outf, level + 2, header, value);
snprintf(header, sizeof(header), "base-frequency(MHz)");
if (!ctdp_level->sse_p1)
ctdp_level->sse_p1 = ctdp_level->tdp_ratio;
snprintf(value, sizeof(value), "%d",
ctdp_level->sse_p1 * DISP_FREQ_MULTIPLIER);
- format_and_print(outf, base_level + 4, header, value);
+ format_and_print(outf, level + 2, header, value);
if (ctdp_level->avx2_p1) {
snprintf(header, sizeof(header), "base-frequency-avx2(MHz)");
snprintf(value, sizeof(value), "%d",
ctdp_level->avx2_p1 * DISP_FREQ_MULTIPLIER);
- format_and_print(outf, base_level + 4, header, value);
+ format_and_print(outf, level + 2, header, value);
}
if (ctdp_level->avx512_p1) {
snprintf(header, sizeof(header), "base-frequency-avx512(MHz)");
snprintf(value, sizeof(value), "%d",
ctdp_level->avx512_p1 * DISP_FREQ_MULTIPLIER);
- format_and_print(outf, base_level + 4, header, value);
+ format_and_print(outf, level + 2, header, value);
}
if (ctdp_level->uncore_p1) {
snprintf(header, sizeof(header), "uncore-frequency-min(MHz)");
snprintf(value, sizeof(value), "%d",
ctdp_level->uncore_p1 * DISP_FREQ_MULTIPLIER);
- format_and_print(outf, base_level + 4, header, value);
+ format_and_print(outf, level + 2, header, value);
}
if (ctdp_level->uncore_p0) {
snprintf(header, sizeof(header), "uncore-frequency-max(MHz)");
snprintf(value, sizeof(value), "%d",
ctdp_level->uncore_p0 * DISP_FREQ_MULTIPLIER);
- format_and_print(outf, base_level + 4, header, value);
+ format_and_print(outf, level + 2, header, value);
}
if (ctdp_level->mem_freq) {
snprintf(header, sizeof(header), "mem-frequency(MHz)");
snprintf(value, sizeof(value), "%d",
ctdp_level->mem_freq * DISP_FREQ_MULTIPLIER);
- format_and_print(outf, base_level + 4, header, value);
+ format_and_print(outf, level + 2, header, value);
}
snprintf(header, sizeof(header),
@@ -405,7 +441,7 @@ void isst_ctdp_display_information(int cpu, FILE *outf, int tdp_level,
snprintf(value, sizeof(value), "disabled");
} else
snprintf(value, sizeof(value), "unsupported");
- format_and_print(outf, base_level + 4, header, value);
+ format_and_print(outf, level + 2, header, value);
snprintf(header, sizeof(header),
"speed-select-base-freq");
@@ -416,7 +452,7 @@ void isst_ctdp_display_information(int cpu, FILE *outf, int tdp_level,
snprintf(value, sizeof(value), "disabled");
} else
snprintf(value, sizeof(value), "unsupported");
- format_and_print(outf, base_level + 4, header, value);
+ format_and_print(outf, level + 2, header, value);
snprintf(header, sizeof(header),
"speed-select-core-power");
@@ -427,110 +463,115 @@ void isst_ctdp_display_information(int cpu, FILE *outf, int tdp_level,
snprintf(value, sizeof(value), "disabled");
} else
snprintf(value, sizeof(value), "unsupported");
- format_and_print(outf, base_level + 4, header, value);
+ format_and_print(outf, level + 2, header, value);
if (is_clx_n_platform()) {
if (ctdp_level->pbf_support)
_isst_pbf_display_information(cpu, outf,
tdp_level,
&ctdp_level->pbf_info,
- base_level + 4);
+ level + 1);
continue;
}
if (ctdp_level->pkg_tdp) {
snprintf(header, sizeof(header), "thermal-design-power(W)");
snprintf(value, sizeof(value), "%d", ctdp_level->pkg_tdp);
- format_and_print(outf, base_level + 4, header, value);
+ format_and_print(outf, level + 2, header, value);
}
if (ctdp_level->t_proc_hot) {
snprintf(header, sizeof(header), "tjunction-max(C)");
snprintf(value, sizeof(value), "%d", ctdp_level->t_proc_hot);
- format_and_print(outf, base_level + 4, header, value);
+ format_and_print(outf, level + 2, header, value);
}
snprintf(header, sizeof(header), "turbo-ratio-limits-sse");
- format_and_print(outf, base_level + 4, header, NULL);
+ format_and_print(outf, level + 2, header, NULL);
for (j = 0; j < 8; ++j) {
snprintf(header, sizeof(header), "bucket-%d", j);
- format_and_print(outf, base_level + 5, header, NULL);
+ format_and_print(outf, level + 3, header, NULL);
snprintf(header, sizeof(header), "core-count");
snprintf(value, sizeof(value), "%llu", (ctdp_level->buckets_info >> (j * 8)) & 0xff);
- format_and_print(outf, base_level + 6, header, value);
+ format_and_print(outf, level + 4, header, value);
snprintf(header, sizeof(header),
"max-turbo-frequency(MHz)");
snprintf(value, sizeof(value), "%d",
ctdp_level->trl_sse_active_cores[j] *
DISP_FREQ_MULTIPLIER);
- format_and_print(outf, base_level + 6, header, value);
+ format_and_print(outf, level + 4, header, value);
}
if (ctdp_level->trl_avx_active_cores[0]) {
snprintf(header, sizeof(header), "turbo-ratio-limits-avx2");
- format_and_print(outf, base_level + 4, header, NULL);
+ format_and_print(outf, level + 2, header, NULL);
for (j = 0; j < 8; ++j) {
snprintf(header, sizeof(header), "bucket-%d", j);
- format_and_print(outf, base_level + 5, header, NULL);
+ format_and_print(outf, level + 3, header, NULL);
snprintf(header, sizeof(header), "core-count");
snprintf(value, sizeof(value), "%llu", (ctdp_level->buckets_info >> (j * 8)) & 0xff);
- format_and_print(outf, base_level + 6, header, value);
+ format_and_print(outf, level + 4, header, value);
snprintf(header, sizeof(header), "max-turbo-frequency(MHz)");
snprintf(value, sizeof(value), "%d", ctdp_level->trl_avx_active_cores[j] * DISP_FREQ_MULTIPLIER);
- format_and_print(outf, base_level + 6, header, value);
+ format_and_print(outf, level + 4, header, value);
}
}
if (ctdp_level->trl_avx_512_active_cores[0]) {
snprintf(header, sizeof(header), "turbo-ratio-limits-avx512");
- format_and_print(outf, base_level + 4, header, NULL);
+ format_and_print(outf, level + 2, header, NULL);
for (j = 0; j < 8; ++j) {
snprintf(header, sizeof(header), "bucket-%d", j);
- format_and_print(outf, base_level + 5, header, NULL);
+ format_and_print(outf, level + 3, header, NULL);
snprintf(header, sizeof(header), "core-count");
snprintf(value, sizeof(value), "%llu", (ctdp_level->buckets_info >> (j * 8)) & 0xff);
- format_and_print(outf, base_level + 6, header, value);
+ format_and_print(outf, level + 4, header, value);
snprintf(header, sizeof(header), "max-turbo-frequency(MHz)");
snprintf(value, sizeof(value), "%d", ctdp_level->trl_avx_512_active_cores[j] * DISP_FREQ_MULTIPLIER);
- format_and_print(outf, base_level + 6, header, value);
+ format_and_print(outf, level + 4, header, value);
}
}
if (ctdp_level->pbf_support)
_isst_pbf_display_information(cpu, outf, i,
&ctdp_level->pbf_info,
- base_level + 4);
+ level + 2);
if (ctdp_level->fact_support)
_isst_fact_display_information(cpu, outf, i, 0xff, 0xff,
&ctdp_level->fact_info,
- base_level + 4);
+ level + 2);
}
format_and_print(outf, 1, NULL, NULL);
}
+static int start;
void isst_ctdp_display_information_start(FILE *outf)
{
last_level = 0;
format_and_print(outf, 0, "start", NULL);
+ start = 1;
}
void isst_ctdp_display_information_end(FILE *outf)
{
format_and_print(outf, 0, NULL, NULL);
+ start = 0;
}
void isst_pbf_display_information(int cpu, FILE *outf, int level,
struct isst_pbf_info *pbf_info)
{
- print_package_info(cpu, outf);
- _isst_pbf_display_information(cpu, outf, level, pbf_info, 4);
+ int _level;
+
+ _level = print_package_info(cpu, outf);
+ _isst_pbf_display_information(cpu, outf, level, pbf_info, _level + 1);
format_and_print(outf, 1, NULL, NULL);
}
@@ -538,9 +579,11 @@ void isst_fact_display_information(int cpu, FILE *outf, int level,
int fact_bucket, int fact_avx,
struct isst_fact_info *fact_info)
{
- print_package_info(cpu, outf);
+ int _level;
+
+ _level = print_package_info(cpu, outf);
_isst_fact_display_information(cpu, outf, level, fact_bucket, fact_avx,
- fact_info, 4);
+ fact_info, _level + 1);
format_and_print(outf, 1, NULL, NULL);
}
@@ -549,94 +592,103 @@ void isst_clos_display_information(int cpu, FILE *outf, int clos,
{
char header[256];
char value[256];
+ int level;
- snprintf(header, sizeof(header), "package-%d",
- get_physical_package_id(cpu));
- format_and_print(outf, 1, header, NULL);
- snprintf(header, sizeof(header), "die-%d", get_physical_die_id(cpu));
- format_and_print(outf, 2, header, NULL);
- snprintf(header, sizeof(header), "cpu-%d", cpu);
- format_and_print(outf, 3, header, NULL);
+ level = print_package_info(cpu, outf);
snprintf(header, sizeof(header), "core-power");
- format_and_print(outf, 4, header, NULL);
+ format_and_print(outf, level + 1, header, NULL);
snprintf(header, sizeof(header), "clos");
snprintf(value, sizeof(value), "%d", clos);
- format_and_print(outf, 5, header, value);
+ format_and_print(outf, level + 2, header, value);
snprintf(header, sizeof(header), "epp");
snprintf(value, sizeof(value), "%d", clos_config->epp);
- format_and_print(outf, 5, header, value);
+ format_and_print(outf, level + 2, header, value);
snprintf(header, sizeof(header), "clos-proportional-priority");
snprintf(value, sizeof(value), "%d", clos_config->clos_prop_prio);
- format_and_print(outf, 5, header, value);
+ format_and_print(outf, level + 2, header, value);
snprintf(header, sizeof(header), "clos-min");
snprintf(value, sizeof(value), "%d MHz", clos_config->clos_min * DISP_FREQ_MULTIPLIER);
- format_and_print(outf, 5, header, value);
+ format_and_print(outf, level + 2, header, value);
snprintf(header, sizeof(header), "clos-max");
- snprintf(value, sizeof(value), "%d MHz", clos_config->clos_max * DISP_FREQ_MULTIPLIER);
- format_and_print(outf, 5, header, value);
+ if (clos_config->clos_max == 0xff)
+ snprintf(value, sizeof(value), "Max Turbo frequency");
+ else
+ snprintf(value, sizeof(value), "%d MHz", clos_config->clos_max * DISP_FREQ_MULTIPLIER);
+ format_and_print(outf, level + 2, header, value);
snprintf(header, sizeof(header), "clos-desired");
snprintf(value, sizeof(value), "%d MHz", clos_config->clos_desired * DISP_FREQ_MULTIPLIER);
- format_and_print(outf, 5, header, value);
+ format_and_print(outf, level + 2, header, value);
- format_and_print(outf, 1, NULL, NULL);
+ format_and_print(outf, level, NULL, NULL);
}
void isst_clos_display_clos_information(int cpu, FILE *outf,
- int clos_enable, int type)
+ int clos_enable, int type,
+ int state, int cap)
{
char header[256];
char value[256];
+ int level;
- snprintf(header, sizeof(header), "package-%d",
- get_physical_package_id(cpu));
- format_and_print(outf, 1, header, NULL);
- snprintf(header, sizeof(header), "die-%d", get_physical_die_id(cpu));
- format_and_print(outf, 2, header, NULL);
- snprintf(header, sizeof(header), "cpu-%d", cpu);
- format_and_print(outf, 3, header, NULL);
+ level = print_package_info(cpu, outf);
snprintf(header, sizeof(header), "core-power");
- format_and_print(outf, 4, header, NULL);
+ format_and_print(outf, level + 1, header, NULL);
+
+ snprintf(header, sizeof(header), "support-status");
+ if (cap)
+ snprintf(value, sizeof(value), "supported");
+ else
+ snprintf(value, sizeof(value), "unsupported");
+ format_and_print(outf, level + 2, header, value);
snprintf(header, sizeof(header), "enable-status");
- snprintf(value, sizeof(value), "%d", clos_enable);
- format_and_print(outf, 5, header, value);
+ if (state)
+ snprintf(value, sizeof(value), "enabled");
+ else
+ snprintf(value, sizeof(value), "disabled");
+ format_and_print(outf, level + 2, header, value);
+
+ snprintf(header, sizeof(header), "clos-enable-status");
+ if (clos_enable)
+ snprintf(value, sizeof(value), "enabled");
+ else
+ snprintf(value, sizeof(value), "disabled");
+ format_and_print(outf, level + 2, header, value);
snprintf(header, sizeof(header), "priority-type");
- snprintf(value, sizeof(value), "%d", type);
- format_and_print(outf, 5, header, value);
+ if (type)
+ snprintf(value, sizeof(value), "ordered");
+ else
+ snprintf(value, sizeof(value), "proportional");
+ format_and_print(outf, level + 2, header, value);
- format_and_print(outf, 1, NULL, NULL);
+ format_and_print(outf, level, NULL, NULL);
}
void isst_clos_display_assoc_information(int cpu, FILE *outf, int clos)
{
char header[256];
char value[256];
+ int level;
- snprintf(header, sizeof(header), "package-%d",
- get_physical_package_id(cpu));
- format_and_print(outf, 1, header, NULL);
- snprintf(header, sizeof(header), "die-%d", get_physical_die_id(cpu));
- format_and_print(outf, 2, header, NULL);
- snprintf(header, sizeof(header), "cpu-%d", cpu);
- format_and_print(outf, 3, header, NULL);
+ level = print_package_info(cpu, outf);
snprintf(header, sizeof(header), "get-assoc");
- format_and_print(outf, 4, header, NULL);
+ format_and_print(outf, level + 1, header, NULL);
snprintf(header, sizeof(header), "clos");
snprintf(value, sizeof(value), "%d", clos);
- format_and_print(outf, 5, header, value);
+ format_and_print(outf, level + 2, header, value);
- format_and_print(outf, 1, NULL, NULL);
+ format_and_print(outf, level, NULL, NULL);
}
void isst_display_result(int cpu, FILE *outf, char *feature, char *cmd,
@@ -644,24 +696,60 @@ void isst_display_result(int cpu, FILE *outf, char *feature, char *cmd,
{
char header[256];
char value[256];
+ int level = 3;
+
+ if (cpu >= 0)
+ level = print_package_info(cpu, outf);
- if (cpu >= 0) {
- snprintf(header, sizeof(header), "package-%d",
- get_physical_package_id(cpu));
- format_and_print(outf, 1, header, NULL);
- snprintf(header, sizeof(header), "die-%d", get_physical_die_id(cpu));
- format_and_print(outf, 2, header, NULL);
- snprintf(header, sizeof(header), "cpu-%d", cpu);
- format_and_print(outf, 3, header, NULL);
- }
snprintf(header, sizeof(header), "%s", feature);
- format_and_print(outf, 4, header, NULL);
+ format_and_print(outf, level + 1, header, NULL);
snprintf(header, sizeof(header), "%s", cmd);
if (!result)
snprintf(value, sizeof(value), "success");
else
snprintf(value, sizeof(value), "failed(error %d)", result);
- format_and_print(outf, 5, header, value);
+ format_and_print(outf, level + 2, header, value);
+
+ format_and_print(outf, level, NULL, NULL);
+}
+
+void isst_display_error_info_message(int error, char *msg, int arg_valid, int arg)
+{
+ FILE *outf = get_output_file();
+ static int error_index;
+ char header[256];
+ char value[256];
+
+ if (!out_format_is_json()) {
+ if (arg_valid)
+ snprintf(value, sizeof(value), "%s %d", msg, arg);
+ else
+ snprintf(value, sizeof(value), "%s", msg);
+
+ if (error)
+ fprintf(outf, "Error: %s\n", value);
+ else
+ fprintf(outf, "Information: %s\n", value);
+ return;
+ }
+
+ if (!start)
+ format_and_print(outf, 0, "start", NULL);
+
+ if (error)
+ snprintf(header, sizeof(header), "Error%d", error_index++);
+ else
+ snprintf(header, sizeof(header), "Information:%d", error_index++);
+ format_and_print(outf, 1, header, NULL);
+
+ snprintf(header, sizeof(header), "message");
+ if (arg_valid)
+ snprintf(value, sizeof(value), "%s %d", msg, arg);
+ else
+ snprintf(value, sizeof(value), "%s", msg);
+ format_and_print(outf, 2, header, value);
format_and_print(outf, 1, NULL, NULL);
+ if (!start)
+ format_and_print(outf, 0, NULL, NULL);
}
diff --git a/tools/power/x86/intel-speed-select/isst.h b/tools/power/x86/intel-speed-select/isst.h
index ad5aa6341d0f..2e1afd856a78 100644
--- a/tools/power/x86/intel-speed-select/isst.h
+++ b/tools/power/x86/intel-speed-select/isst.h
@@ -172,6 +172,7 @@ extern int get_cpu_count(int pkg_id, int die_id);
extern int get_core_count(int pkg_id, int die_id);
/* Common interfaces */
+FILE *get_output_file(void);
extern void debug_printf(const char *format, ...);
extern int out_format_is_json(void);
extern int get_physical_package_id(int cpu);
@@ -196,6 +197,8 @@ extern int isst_send_msr_command(unsigned int cpu, unsigned int command,
int write, unsigned long long *req_resp);
extern int isst_get_ctdp_levels(int cpu, struct isst_pkg_ctdp *pkg_dev);
+extern int isst_get_ctdp_control(int cpu, int config_index,
+ struct isst_pkg_ctdp_level_info *ctdp_level);
extern int isst_get_coremask_info(int cpu, int config_index,
struct isst_pkg_ctdp_level_info *ctdp_level);
extern int isst_get_process_ctdp(int cpu, int tdp_level,
@@ -205,7 +208,7 @@ extern void isst_get_process_ctdp_complete(int cpu,
extern void isst_ctdp_display_information(int cpu, FILE *outf, int tdp_level,
struct isst_pkg_ctdp *pkg_dev);
extern void isst_ctdp_display_core_info(int cpu, FILE *outf, char *prefix,
- unsigned int val);
+ unsigned int val, char *str0, char *str1);
extern void isst_ctdp_display_information_start(FILE *outf);
extern void isst_ctdp_display_information_end(FILE *outf);
extern void isst_pbf_display_information(int cpu, FILE *outf, int level,
@@ -216,7 +219,7 @@ extern int isst_set_pbf_fact_status(int cpu, int pbf, int enable);
extern int isst_get_pbf_info(int cpu, int level,
struct isst_pbf_info *pbf_info);
extern void isst_get_pbf_info_complete(struct isst_pbf_info *pbf_info);
-extern int isst_get_fact_info(int cpu, int level,
+extern int isst_get_fact_info(int cpu, int level, int fact_bucket,
struct isst_fact_info *fact_info);
extern int isst_get_fact_bucket_info(int cpu, int level,
struct isst_fact_bucket_info *bucket_info);
@@ -245,7 +248,10 @@ extern void isst_display_result(int cpu, FILE *outf, char *feature, char *cmd,
extern int isst_clos_get_clos_information(int cpu, int *enable, int *type);
extern void isst_clos_display_clos_information(int cpu, FILE *outf,
- int clos_enable, int type);
+ int clos_enable, int type,
+ int state, int cap);
extern int is_clx_n_platform(void);
extern int get_cpufreq_base_freq(int cpu);
+extern int isst_read_pm_config(int cpu, int *cp_state, int *cp_cap);
+extern void isst_display_error_info_message(int error, char *msg, int arg_valid, int arg);
#endif
diff --git a/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py b/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py
index 256199c7a182..3c47865bb247 100755
--- a/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py
+++ b/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py
@@ -235,7 +235,6 @@ def plot_duration_cpu():
output_png = 'all_cpu_durations.png'
g_plot = common_all_gnuplot_settings(output_png)
# autoscale this one, no set y range
- g_plot('set ytics 0, 500')
g_plot('set ylabel "Timer Duration (MilliSeconds)"')
g_plot('set title "{} : cpu durations : {:%F %H:%M}"'.format(testname, datetime.now()))
diff --git a/tools/power/x86/turbostat/Makefile b/tools/power/x86/turbostat/Makefile
index 13f1e8b9ac52..2b6551269e43 100644
--- a/tools/power/x86/turbostat/Makefile
+++ b/tools/power/x86/turbostat/Makefile
@@ -16,7 +16,7 @@ override CFLAGS += -D_FORTIFY_SOURCE=2
%: %.c
@mkdir -p $(BUILD_OUTPUT)
- $(CC) $(CFLAGS) $< -o $(BUILD_OUTPUT)/$@ $(LDFLAGS)
+ $(CC) $(CFLAGS) $< -o $(BUILD_OUTPUT)/$@ $(LDFLAGS) -lcap
.PHONY : clean
clean :
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 31c1ca0bb3ee..33b370865d16 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -30,7 +30,7 @@
#include <sched.h>
#include <time.h>
#include <cpuid.h>
-#include <linux/capability.h>
+#include <sys/capability.h>
#include <errno.h>
#include <math.h>
@@ -304,6 +304,10 @@ int *irqs_per_cpu; /* indexed by cpu_num */
void setup_all_buffers(void);
+char *sys_lpi_file;
+char *sys_lpi_file_sysfs = "/sys/devices/system/cpu/cpuidle/low_power_idle_system_residency_us";
+char *sys_lpi_file_debugfs = "/sys/kernel/debug/pmc_core/slp_s0_residency_usec";
+
int cpu_is_not_present(int cpu)
{
return !CPU_ISSET_S(cpu, cpu_present_setsize, cpu_present_set);
@@ -2916,8 +2920,6 @@ int snapshot_gfx_mhz(void)
*
* record snapshot of
* /sys/devices/system/cpu/cpuidle/low_power_idle_cpu_residency_us
- *
- * return 1 if config change requires a restart, else return 0
*/
int snapshot_cpu_lpi_us(void)
{
@@ -2941,17 +2943,14 @@ int snapshot_cpu_lpi_us(void)
/*
* snapshot_sys_lpi()
*
- * record snapshot of
- * /sys/devices/system/cpu/cpuidle/low_power_idle_system_residency_us
- *
- * return 1 if config change requires a restart, else return 0
+ * record snapshot of sys_lpi_file
*/
int snapshot_sys_lpi_us(void)
{
FILE *fp;
int retval;
- fp = fopen_or_die("/sys/devices/system/cpu/cpuidle/low_power_idle_system_residency_us", "r");
+ fp = fopen_or_die(sys_lpi_file, "r");
retval = fscanf(fp, "%lld", &cpuidle_cur_sys_lpi_us);
if (retval != 1) {
@@ -3151,28 +3150,42 @@ void check_dev_msr()
err(-5, "no /dev/cpu/0/msr, Try \"# modprobe msr\" ");
}
-void check_permissions()
+/*
+ * check for CAP_SYS_RAWIO
+ * return 0 on success
+ * return 1 on fail
+ */
+int check_for_cap_sys_rawio(void)
{
- struct __user_cap_header_struct cap_header_data;
- cap_user_header_t cap_header = &cap_header_data;
- struct __user_cap_data_struct cap_data_data;
- cap_user_data_t cap_data = &cap_data_data;
- extern int capget(cap_user_header_t hdrp, cap_user_data_t datap);
- int do_exit = 0;
- char pathname[32];
+ cap_t caps;
+ cap_flag_value_t cap_flag_value;
- /* check for CAP_SYS_RAWIO */
- cap_header->pid = getpid();
- cap_header->version = _LINUX_CAPABILITY_VERSION;
- if (capget(cap_header, cap_data) < 0)
- err(-6, "capget(2) failed");
+ caps = cap_get_proc();
+ if (caps == NULL)
+ err(-6, "cap_get_proc\n");
- if ((cap_data->effective & (1 << CAP_SYS_RAWIO)) == 0) {
- do_exit++;
+ if (cap_get_flag(caps, CAP_SYS_RAWIO, CAP_EFFECTIVE, &cap_flag_value))
+ err(-6, "cap_get\n");
+
+ if (cap_flag_value != CAP_SET) {
warnx("capget(CAP_SYS_RAWIO) failed,"
" try \"# setcap cap_sys_rawio=ep %s\"", progname);
+ return 1;
}
+ if (cap_free(caps) == -1)
+ err(-6, "cap_free\n");
+
+ return 0;
+}
+void check_permissions(void)
+{
+ int do_exit = 0;
+ char pathname[32];
+
+ /* check for CAP_SYS_RAWIO */
+ do_exit += check_for_cap_sys_rawio();
+
/* test file permissions */
sprintf(pathname, "/dev/cpu/%d/msr", base_cpu);
if (euidaccess(pathname, R_OK)) {
@@ -3265,6 +3278,7 @@ int probe_nhm_msrs(unsigned int family, unsigned int model)
case INTEL_FAM6_ATOM_GOLDMONT: /* BXT */
case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
case INTEL_FAM6_ATOM_GOLDMONT_D: /* DNV */
+ case INTEL_FAM6_ATOM_TREMONT: /* EHL */
pkg_cstate_limits = glm_pkg_cstate_limits;
break;
default:
@@ -3336,6 +3350,17 @@ int is_skx(unsigned int family, unsigned int model)
}
return 0;
}
+int is_ehl(unsigned int family, unsigned int model)
+{
+ if (!genuine_intel)
+ return 0;
+
+ switch (model) {
+ case INTEL_FAM6_ATOM_TREMONT:
+ return 1;
+ }
+ return 0;
+}
int has_turbo_ratio_limit(unsigned int family, unsigned int model)
{
@@ -3478,6 +3503,23 @@ dump_cstate_pstate_config_info(unsigned int family, unsigned int model)
dump_nhm_cst_cfg();
}
+static void dump_sysfs_file(char *path)
+{
+ FILE *input;
+ char cpuidle_buf[64];
+
+ input = fopen(path, "r");
+ if (input == NULL) {
+ if (debug)
+ fprintf(outf, "NSFOD %s\n", path);
+ return;
+ }
+ if (!fgets(cpuidle_buf, sizeof(cpuidle_buf), input))
+ err(1, "%s: failed to read file", path);
+ fclose(input);
+
+ fprintf(outf, "%s: %s", strrchr(path, '/') + 1, cpuidle_buf);
+}
static void
dump_sysfs_cstate_config(void)
{
@@ -3491,6 +3533,15 @@ dump_sysfs_cstate_config(void)
if (!DO_BIC(BIC_sysfs))
return;
+ if (access("/sys/devices/system/cpu/cpuidle", R_OK)) {
+ fprintf(outf, "cpuidle not loaded\n");
+ return;
+ }
+
+ dump_sysfs_file("/sys/devices/system/cpu/cpuidle/current_driver");
+ dump_sysfs_file("/sys/devices/system/cpu/cpuidle/current_governor");
+ dump_sysfs_file("/sys/devices/system/cpu/cpuidle/current_governor_ro");
+
for (state = 0; state < 10; ++state) {
sprintf(path, "/sys/devices/system/cpu/cpu%d/cpuidle/state%d/name",
@@ -3894,6 +3945,20 @@ void rapl_probe_intel(unsigned int family, unsigned int model)
else
BIC_PRESENT(BIC_PkgWatt);
break;
+ case INTEL_FAM6_ATOM_TREMONT: /* EHL */
+ do_rapl = RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_GFX | RAPL_PKG_POWER_INFO;
+ if (rapl_joules) {
+ BIC_PRESENT(BIC_Pkg_J);
+ BIC_PRESENT(BIC_Cor_J);
+ BIC_PRESENT(BIC_RAM_J);
+ BIC_PRESENT(BIC_GFX_J);
+ } else {
+ BIC_PRESENT(BIC_PkgWatt);
+ BIC_PRESENT(BIC_CorWatt);
+ BIC_PRESENT(BIC_RAMWatt);
+ BIC_PRESENT(BIC_GFXWatt);
+ }
+ break;
case INTEL_FAM6_SKYLAKE_L: /* SKL */
case INTEL_FAM6_CANNONLAKE_L: /* CNL */
do_rapl = RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_GFX | RAPL_PKG_POWER_INFO;
@@ -4295,6 +4360,7 @@ int has_snb_msrs(unsigned int family, unsigned int model)
case INTEL_FAM6_ATOM_GOLDMONT: /* BXT */
case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
case INTEL_FAM6_ATOM_GOLDMONT_D: /* DNV */
+ case INTEL_FAM6_ATOM_TREMONT: /* EHL */
return 1;
}
return 0;
@@ -4324,6 +4390,7 @@ int has_c8910_msrs(unsigned int family, unsigned int model)
case INTEL_FAM6_CANNONLAKE_L: /* CNL */
case INTEL_FAM6_ATOM_GOLDMONT: /* BXT */
case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
+ case INTEL_FAM6_ATOM_TREMONT: /* EHL */
return 1;
}
return 0;
@@ -4610,14 +4677,24 @@ unsigned int intel_model_duplicates(unsigned int model)
case INTEL_FAM6_SKYLAKE:
case INTEL_FAM6_KABYLAKE_L:
case INTEL_FAM6_KABYLAKE:
+ case INTEL_FAM6_COMETLAKE_L:
+ case INTEL_FAM6_COMETLAKE:
return INTEL_FAM6_SKYLAKE_L;
case INTEL_FAM6_ICELAKE_L:
case INTEL_FAM6_ICELAKE_NNPI:
+ case INTEL_FAM6_TIGERLAKE_L:
+ case INTEL_FAM6_TIGERLAKE:
return INTEL_FAM6_CANNONLAKE_L;
case INTEL_FAM6_ATOM_TREMONT_D:
return INTEL_FAM6_ATOM_GOLDMONT_D;
+
+ case INTEL_FAM6_ATOM_TREMONT_L:
+ return INTEL_FAM6_ATOM_TREMONT;
+
+ case INTEL_FAM6_ICELAKE_X:
+ return INTEL_FAM6_SKYLAKE_X;
}
return model;
}
@@ -4872,7 +4949,8 @@ void process_cpuid()
do_slm_cstates = is_slm(family, model);
do_knl_cstates = is_knl(family, model);
- if (do_slm_cstates || do_knl_cstates || is_cnl(family, model))
+ if (do_slm_cstates || do_knl_cstates || is_cnl(family, model) ||
+ is_ehl(family, model))
BIC_NOT_PRESENT(BIC_CPU_c3);
if (!quiet)
@@ -4907,10 +4985,16 @@ void process_cpuid()
else
BIC_NOT_PRESENT(BIC_CPU_LPI);
- if (!access("/sys/devices/system/cpu/cpuidle/low_power_idle_system_residency_us", R_OK))
+ if (!access(sys_lpi_file_sysfs, R_OK)) {
+ sys_lpi_file = sys_lpi_file_sysfs;
BIC_PRESENT(BIC_SYS_LPI);
- else
+ } else if (!access(sys_lpi_file_debugfs, R_OK)) {
+ sys_lpi_file = sys_lpi_file_debugfs;
+ BIC_PRESENT(BIC_SYS_LPI);
+ } else {
+ sys_lpi_file_sysfs = NULL;
BIC_NOT_PRESENT(BIC_SYS_LPI);
+ }
if (!quiet)
decode_misc_feature_control();
@@ -5306,7 +5390,7 @@ int get_and_dump_counters(void)
}
void print_version() {
- fprintf(outf, "turbostat version 19.08.31"
+ fprintf(outf, "turbostat version 20.03.20"
" - Len Brown <lenb@kernel.org>\n");
}
@@ -5323,9 +5407,9 @@ int add_counter(unsigned int msr_num, char *path, char *name,
}
msrp->msr_num = msr_num;
- strncpy(msrp->name, name, NAME_BYTES);
+ strncpy(msrp->name, name, NAME_BYTES - 1);
if (path)
- strncpy(msrp->path, path, PATH_BYTES);
+ strncpy(msrp->path, path, PATH_BYTES - 1);
msrp->width = width;
msrp->type = type;
msrp->format = format;
diff --git a/tools/scripts/Makefile.include b/tools/scripts/Makefile.include
index ded7a950dc40..a7974638561c 100644
--- a/tools/scripts/Makefile.include
+++ b/tools/scripts/Makefile.include
@@ -1,8 +1,8 @@
# SPDX-License-Identifier: GPL-2.0
ifneq ($(O),)
ifeq ($(origin O), command line)
- dummy := $(if $(shell test -d $(O) || echo $(O)),$(error O=$(O) does not exist),)
- ABSOLUTE_O := $(shell cd $(O) ; pwd)
+ dummy := $(if $(shell cd $(PWD); test -d $(O) || echo $(O)),$(error O=$(O) does not exist),)
+ ABSOLUTE_O := $(shell cd $(PWD); cd $(O) ; pwd)
OUTPUT := $(ABSOLUTE_O)/$(if $(subdir),$(subdir)/)
COMMAND_O := O=$(ABSOLUTE_O)
ifeq ($(objtree),)
@@ -106,6 +106,7 @@ ifneq ($(silent),1)
ifneq ($(V),1)
QUIET_CC = @echo ' CC '$@;
QUIET_CC_FPIC = @echo ' CC FPIC '$@;
+ QUIET_CLANG = @echo ' CLANG '$@;
QUIET_AR = @echo ' AR '$@;
QUIET_LINK = @echo ' LINK '$@;
QUIET_MKDIR = @echo ' MKDIR '$@;
diff --git a/tools/spi/Makefile b/tools/spi/Makefile
index 5c342e655e55..2249a1546cc1 100644
--- a/tools/spi/Makefile
+++ b/tools/spi/Makefile
@@ -51,7 +51,7 @@ $(OUTPUT)spidev_fdx: $(SPIDEV_FDX_IN)
clean:
rm -f $(ALL_PROGRAMS)
- rm -f $(OUTPUT)include/linux/spi/spidev.h
+ rm -rf $(OUTPUT)include/
find $(if $(OUTPUT),$(OUTPUT),.) -name '*.o' -delete -o -name '\.*.d' -delete
install: $(ALL_PROGRAMS)
diff --git a/tools/spi/spidev_test.c b/tools/spi/spidev_test.c
index 3559e7646256..27967dd90f8f 100644
--- a/tools/spi/spidev_test.c
+++ b/tools/spi/spidev_test.c
@@ -13,6 +13,7 @@
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
+#include <errno.h>
#include <getopt.h>
#include <fcntl.h>
#include <time.h>
@@ -26,7 +27,11 @@
static void pabort(const char *s)
{
- perror(s);
+ if (errno != 0)
+ perror(s);
+ else
+ printf("%s\n", s);
+
abort();
}
@@ -283,7 +288,6 @@ static void parse_opts(int argc, char *argv[])
break;
default:
print_usage(argv[0]);
- break;
}
}
if (mode & SPI_LOOP) {
@@ -405,6 +409,9 @@ int main(int argc, char *argv[])
parse_opts(argc, argv);
+ if (input_tx && input_file)
+ pabort("only one of -p and --input may be selected");
+
fd = open(device, O_RDWR);
if (fd < 0)
pabort("can't open device");
@@ -446,9 +453,6 @@ int main(int argc, char *argv[])
printf("bits per word: %d\n", bits);
printf("max speed: %d Hz (%d KHz)\n", speed, speed/1000);
- if (input_tx && input_file)
- pabort("only one of -p and --input may be selected");
-
if (input_tx)
transfer_escaped_string(fd, input_tx);
else if (input_file)
diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl
index 220d04f958a6..7570e36d636d 100755
--- a/tools/testing/ktest/ktest.pl
+++ b/tools/testing/ktest/ktest.pl
@@ -30,7 +30,7 @@ my %default = (
"EMAIL_WHEN_STARTED" => 0,
"NUM_TESTS" => 1,
"TEST_TYPE" => "build",
- "BUILD_TYPE" => "randconfig",
+ "BUILD_TYPE" => "oldconfig",
"MAKE_CMD" => "make",
"CLOSE_CONSOLE_SIGNAL" => "INT",
"TIMEOUT" => 120,
@@ -1030,7 +1030,7 @@ sub __read_config {
}
if (!$skip && $rest !~ /^\s*$/) {
- die "$name: $.: Gargbage found after $type\n$_";
+ die "$name: $.: Garbage found after $type\n$_";
}
if ($skip && $type eq "TEST_START") {
@@ -1063,7 +1063,7 @@ sub __read_config {
}
if ($rest !~ /^\s*$/) {
- die "$name: $.: Gargbage found after DEFAULTS\n$_";
+ die "$name: $.: Garbage found after DEFAULTS\n$_";
}
} elsif (/^\s*INCLUDE\s+(\S+)/) {
@@ -1154,7 +1154,7 @@ sub __read_config {
# on of these sections that have SKIP defined.
# The save variable can be
# defined multiple times and the new one simply overrides
- # the prevous one.
+ # the previous one.
set_variable($lvalue, $rvalue);
} else {
@@ -1234,7 +1234,7 @@ sub read_config {
foreach my $option (keys %not_used) {
print "$option\n";
}
- print "Set IGRNORE_UNUSED = 1 to have ktest ignore unused variables\n";
+ print "Set IGNORE_UNUSED = 1 to have ktest ignore unused variables\n";
if (!read_yn "Do you want to continue?") {
exit -1;
}
@@ -1345,7 +1345,7 @@ sub eval_option {
# Check for recursive evaluations.
# 100 deep should be more than enough.
if ($r++ > 100) {
- die "Over 100 evaluations accurred with $option\n" .
+ die "Over 100 evaluations occurred with $option\n" .
"Check for recursive variables\n";
}
$prev = $option;
@@ -1383,7 +1383,7 @@ sub reboot {
} else {
# Make sure everything has been written to disk
- run_ssh("sync");
+ run_ssh("sync", 10);
if (defined($time)) {
start_monitor;
@@ -1461,7 +1461,7 @@ sub get_test_name() {
sub dodie {
- # avoid recusion
+ # avoid recursion
return if ($in_die);
$in_die = 1;
diff --git a/tools/testing/ktest/sample.conf b/tools/testing/ktest/sample.conf
index c3bc933d437b..27666b8007ed 100644
--- a/tools/testing/ktest/sample.conf
+++ b/tools/testing/ktest/sample.conf
@@ -10,7 +10,7 @@
#
# Options set in the beginning of the file are considered to be
-# default options. These options can be overriden by test specific
+# default options. These options can be overridden by test specific
# options, with the following exceptions:
#
# LOG_FILE
@@ -204,7 +204,7 @@
#
# This config file can also contain "config variables".
# These are assigned with ":=" instead of the ktest option
-# assigment "=".
+# assignment "=".
#
# The difference between ktest options and config variables
# is that config variables can be used multiple times,
@@ -263,7 +263,7 @@
#### Using options in other options ####
#
# Options that are defined in the config file may also be used
-# by other options. All options are evaulated at time of
+# by other options. All options are evaluated at time of
# use (except that config variables are evaluated at config
# processing time).
#
@@ -505,7 +505,7 @@
#TEST = ssh user@machine /root/run_test
# The build type is any make config type or special command
-# (default randconfig)
+# (default oldconfig)
# nobuild - skip the clean and build step
# useconfig:/path/to/config - use the given config and run
# oldconfig on it.
@@ -707,7 +707,7 @@
# Line to define a successful boot up in console output.
# This is what the line contains, not the entire line. If you need
-# the entire line to match, then use regural expression syntax like:
+# the entire line to match, then use regular expression syntax like:
# (do not add any quotes around it)
#
# SUCCESS_LINE = ^MyBox Login:$
@@ -839,7 +839,7 @@
# (ignored if POWEROFF_ON_SUCCESS is set)
#REBOOT_ON_SUCCESS = 1
-# In case there are isses with rebooting, you can specify this
+# In case there are issues with rebooting, you can specify this
# to always powercycle after this amount of time after calling
# reboot.
# Note, POWERCYCLE_AFTER_REBOOT = 0 does NOT disable it. It just
@@ -848,7 +848,7 @@
# (default undefined)
#POWERCYCLE_AFTER_REBOOT = 5
-# In case there's isses with halting, you can specify this
+# In case there's issues with halting, you can specify this
# to always poweroff after this amount of time after calling
# halt.
# Note, POWEROFF_AFTER_HALT = 0 does NOT disable it. It just
@@ -972,7 +972,7 @@
#
# PATCHCHECK_START is required and is the first patch to
# test (the SHA1 of the commit). You may also specify anything
-# that git checkout allows (branch name, tage, HEAD~3).
+# that git checkout allows (branch name, tag, HEAD~3).
#
# PATCHCHECK_END is the last patch to check (default HEAD)
#
@@ -994,7 +994,7 @@
# IGNORE_WARNINGS is set for the given commit's sha1
#
# IGNORE_WARNINGS can be used to disable the failure of patchcheck
-# on a particuler commit (SHA1). You can add more than one commit
+# on a particular commit (SHA1). You can add more than one commit
# by adding a list of SHA1s that are space delimited.
#
# If BUILD_NOCLEAN is set, then make mrproper will not be run on
@@ -1093,7 +1093,7 @@
# whatever reason. (Can't reboot, want to inspect each iteration)
# Doing a BISECT_MANUAL will have the test wait for you to
# tell it if the test passed or failed after each iteration.
-# This is basicall the same as running git bisect yourself
+# This is basically the same as running git bisect yourself
# but ktest will rebuild and install the kernel for you.
#
# BISECT_CHECK = 1 (optional, default 0)
@@ -1239,7 +1239,7 @@
#
# CONFIG_BISECT_EXEC (optional)
# The config bisect is a separate program that comes with ktest.pl.
-# By befault, it will look for:
+# By default, it will look for:
# `pwd`/config-bisect.pl # the location ktest.pl was executed from.
# If it does not find it there, it will look for:
# `dirname <ktest.pl>`/config-bisect.pl # The directory that holds ktest.pl
diff --git a/tools/testing/kunit/kunit.py b/tools/testing/kunit/kunit.py
index e59eb9e7f923..180ad1e1b04f 100755
--- a/tools/testing/kunit/kunit.py
+++ b/tools/testing/kunit/kunit.py
@@ -24,6 +24,8 @@ KunitResult = namedtuple('KunitResult', ['status','result'])
KunitRequest = namedtuple('KunitRequest', ['raw_output','timeout', 'jobs', 'build_dir', 'defconfig'])
+KernelDirectoryPath = sys.argv[0].split('tools/testing/kunit/')[0]
+
class KunitStatus(Enum):
SUCCESS = auto()
CONFIG_FAILURE = auto()
@@ -35,6 +37,13 @@ def create_default_kunitconfig():
shutil.copyfile('arch/um/configs/kunit_defconfig',
kunit_kernel.kunitconfig_path)
+def get_kernel_root_path():
+ parts = sys.argv[0] if not __file__ else __file__
+ parts = os.path.realpath(parts).split('tools/testing/kunit')
+ if len(parts) != 2:
+ sys.exit(1)
+ return parts[0]
+
def run_tests(linux: kunit_kernel.LinuxSourceTree,
request: KunitRequest) -> KunitResult:
config_start = time.time()
@@ -114,6 +123,9 @@ def main(argv, linux=None):
cli_args = parser.parse_args(argv)
if cli_args.subcommand == 'run':
+ if get_kernel_root_path():
+ os.chdir(get_kernel_root_path())
+
if cli_args.build_dir:
if not os.path.exists(cli_args.build_dir):
os.mkdir(cli_args.build_dir)
diff --git a/tools/testing/kunit/kunit_kernel.py b/tools/testing/kunit/kunit_kernel.py
index cc5d844ecca1..d99ae75ef72f 100644
--- a/tools/testing/kunit/kunit_kernel.py
+++ b/tools/testing/kunit/kunit_kernel.py
@@ -93,6 +93,20 @@ class LinuxSourceTree(object):
return False
return True
+ def validate_config(self, build_dir):
+ kconfig_path = get_kconfig_path(build_dir)
+ validated_kconfig = kunit_config.Kconfig()
+ validated_kconfig.read_from_file(kconfig_path)
+ if not self._kconfig.is_subset_of(validated_kconfig):
+ invalid = self._kconfig.entries() - validated_kconfig.entries()
+ message = 'Provided Kconfig is not contained in validated .config. Following fields found in kunitconfig, ' \
+ 'but not in .config: %s' % (
+ ', '.join([str(e) for e in invalid])
+ )
+ logging.error(message)
+ return False
+ return True
+
def build_config(self, build_dir):
kconfig_path = get_kconfig_path(build_dir)
if build_dir and not os.path.exists(build_dir):
@@ -103,12 +117,7 @@ class LinuxSourceTree(object):
except ConfigError as e:
logging.error(e)
return False
- validated_kconfig = kunit_config.Kconfig()
- validated_kconfig.read_from_file(kconfig_path)
- if not self._kconfig.is_subset_of(validated_kconfig):
- logging.error('Provided Kconfig is not contained in validated .config!')
- return False
- return True
+ return self.validate_config(build_dir)
def build_reconfig(self, build_dir):
"""Creates a new .config if it is not a subset of the .kunitconfig."""
@@ -133,12 +142,7 @@ class LinuxSourceTree(object):
except (ConfigError, BuildError) as e:
logging.error(e)
return False
- used_kconfig = kunit_config.Kconfig()
- used_kconfig.read_from_file(get_kconfig_path(build_dir))
- if not self._kconfig.is_subset_of(used_kconfig):
- logging.error('Provided Kconfig is not contained in final config!')
- return False
- return True
+ return self.validate_config(build_dir)
def run_kernel(self, args=[], timeout=None, build_dir=''):
args.extend(['mem=256M'])
diff --git a/tools/testing/selftests/.gitignore b/tools/testing/selftests/.gitignore
index 61df01cdf0b2..304fdf1a21dc 100644
--- a/tools/testing/selftests/.gitignore
+++ b/tools/testing/selftests/.gitignore
@@ -3,4 +3,7 @@ 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 be22dbe94a4c..0635684cbf07 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -33,9 +33,9 @@ TARGETS += memory-hotplug
TARGETS += mount
TARGETS += mqueue
TARGETS += net
+TARGETS += net/forwarding
TARGETS += net/mptcp
TARGETS += netfilter
-TARGETS += networking/timestamping
TARGETS += nsfs
TARGETS += pidfd
TARGETS += powerpc
@@ -77,6 +77,12 @@ ifneq ($(SKIP_TARGETS),)
override TARGETS := $(TMP)
endif
+# User can set FORCE_TARGETS to 1 to require all targets to be successfully
+# built; make will fail if any of the targets cannot be built. If
+# FORCE_TARGETS is not set (the default), make will succeed if at least one
+# of the targets gets built.
+FORCE_TARGETS ?=
+
# Clear LDFLAGS and MAKEFLAGS if called from main
# Makefile to avoid test build failures when test
# Makefile doesn't have explicit build rules.
@@ -151,7 +157,8 @@ all: khdr
for TARGET in $(TARGETS); do \
BUILD_TARGET=$$BUILD/$$TARGET; \
mkdir $$BUILD_TARGET -p; \
- $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET; \
+ $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET \
+ $(if $(FORCE_TARGETS),|| exit); \
ret=$$((ret * $$?)); \
done; exit $$ret;
@@ -205,7 +212,8 @@ ifdef INSTALL_PATH
@ret=1; \
for TARGET in $(TARGETS); do \
BUILD_TARGET=$$BUILD/$$TARGET; \
- $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET INSTALL_PATH=$(INSTALL_PATH)/$$TARGET install; \
+ $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET INSTALL_PATH=$(INSTALL_PATH)/$$TARGET install \
+ $(if $(FORCE_TARGETS),|| exit); \
ret=$$((ret * $$?)); \
done; exit $$ret;
diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index ec464859c6b6..2198cd876675 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -31,6 +31,7 @@ test_tcp_check_syncookie_user
test_sysctl
test_hashmap
test_btf_dump
+test_current_pid_tgid_new_ns
xdping
test_cpp
*.skel.h
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 257a1aaaa37d..7729892e0b04 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -20,8 +20,9 @@ CLANG ?= clang
LLC ?= llc
LLVM_OBJCOPY ?= llvm-objcopy
BPF_GCC ?= $(shell command -v bpf-gcc;)
-CFLAGS += -g -Wall -O2 $(GENFLAGS) -I$(CURDIR) -I$(APIDIR) \
+CFLAGS += -g -rdynamic -Wall -O2 $(GENFLAGS) -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
@@ -32,7 +33,8 @@ TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test
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_progs-no_alu32 \
+ test_current_pid_tgid_new_ns
# Also test bpf-gcc, if present
ifneq ($(BPF_GCC),)
@@ -62,7 +64,8 @@ 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 \
@@ -128,10 +131,13 @@ $(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) \
@@ -171,6 +177,10 @@ $(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 +199,8 @@ 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 +219,7 @@ 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 +233,7 @@ 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
@@ -279,6 +289,7 @@ $(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), \
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..60e3ae5d4e48 100644
--- a/tools/testing/selftests/bpf/config
+++ b/tools/testing/selftests/bpf/config
@@ -35,3 +35,5 @@ CONFIG_MPLS_ROUTING=m
CONFIG_MPLS_IPTUNNEL=m
CONFIG_IPV6_SIT=m
CONFIG_BPF_JIT=y
+CONFIG_BPF_LSM=y
+CONFIG_SECURITY=y
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/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/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_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/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_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/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/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..542240e16564
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c
@@ -0,0 +1,88 @@
+// 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:
+ if (!link) {
+ bpf_link__destroy(link);
+ link = NULL;
+ }
+ 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/select_reuseport.c b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c
index 098bcae5f827..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;
@@ -506,9 +509,6 @@ static void test_syncookie(int type, sa_family_t family)
.pass_on_failure = 0,
};
- if (type != SOCK_STREAM)
- return;
-
/*
* +1 for TCP-SYN and
* +1 for the TCP-ACK (ack the syncookie)
@@ -726,12 +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)
@@ -758,7 +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)
{
@@ -766,12 +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),
};
@@ -779,7 +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);
@@ -814,16 +845,25 @@ 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;
saved_tcp_syncookie = read_int_sysctl(TCP_SYNCOOKIE_SYSCTL);
- if (saved_tcp_syncookie < 0 || saved_tcp_syncookie < 0)
+ if (saved_tcp_syncookie < 0)
goto out;
if (enable_fastopen())
@@ -831,8 +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/send_signal_sched_switch.c b/tools/testing/selftests/bpf/prog_tests/send_signal_sched_switch.c
new file mode 100644
index 000000000000..189a34a7addb
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/send_signal_sched_switch.c
@@ -0,0 +1,60 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <sys/mman.h>
+#include <pthread.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include "test_send_signal_kern.skel.h"
+
+static void sigusr1_handler(int signum)
+{
+}
+
+#define THREAD_COUNT 100
+
+static void *worker(void *p)
+{
+ int i;
+
+ for ( i = 0; i < 1000; i++)
+ usleep(1);
+
+ return NULL;
+}
+
+void test_send_signal_sched_switch(void)
+{
+ struct test_send_signal_kern *skel;
+ pthread_t threads[THREAD_COUNT];
+ u32 duration = 0;
+ int i, err;
+
+ signal(SIGUSR1, sigusr1_handler);
+
+ skel = test_send_signal_kern__open_and_load();
+ if (CHECK(!skel, "skel_open_and_load", "skeleton open_and_load failed\n"))
+ return;
+
+ skel->bss->pid = getpid();
+ skel->bss->sig = SIGUSR1;
+
+ err = test_send_signal_kern__attach(skel);
+ if (CHECK(err, "skel_attach", "skeleton attach failed\n"))
+ goto destroy_skel;
+
+ for (i = 0; i < THREAD_COUNT; i++) {
+ err = pthread_create(threads + i, NULL, worker, NULL);
+ if (CHECK(err, "pthread_create", "Error creating thread, %s\n",
+ strerror(errno)))
+ goto destroy_skel;
+ }
+
+ for (i = 0; i < THREAD_COUNT; i++)
+ pthread_join(threads[i], NULL);
+
+destroy_skel:
+ test_send_signal_kern__destroy(skel);
+}
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..d572e1a2c297
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/sk_assign.c
@@ -0,0 +1,309 @@
+// 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"
+
+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 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;
+ }
+
+ for (int i = 0; i < ARRAY_SIZE(tests) && !READ_ONCE(stop); i++) {
+ struct test_sk_cfg *test = &tests[i];
+ const struct sockaddr *addr;
+
+ 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 cleanup;
+
+ /* 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);
+cleanup:
+ 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..4538bd08203f 100644
--- a/tools/testing/selftests/bpf/prog_tests/skb_ctx.c
+++ b/tools/testing/selftests/bpf/prog_tests/skb_ctx.c
@@ -14,6 +14,7 @@ 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/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
index 07f5b462c2ef..aa43e0bd210c 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
@@ -3,6 +3,11 @@
#include "test_progs.h"
+#define TCP_REPAIR 19 /* TCP sock is under repair right now */
+
+#define TCP_REPAIR_ON 1
+#define TCP_REPAIR_OFF_NO_WP -1 /* Turn off without window probes */
+
static int connected_socket_v4(void)
{
struct sockaddr_in addr = {
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/tcp_rtt.c b/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c
index f4cd60d6fba2..e56b52ab41da 100644
--- a/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c
+++ b/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c
@@ -188,7 +188,7 @@ static int start_server(void)
};
int fd;
- fd = socket(AF_INET, SOCK_STREAM, 0);
+ fd = socket(AF_INET, SOCK_STREAM | SOCK_NONBLOCK, 0);
if (fd < 0) {
log_err("Failed to create server socket");
return -1;
@@ -205,6 +205,7 @@ static int start_server(void)
static pthread_mutex_t server_started_mtx = PTHREAD_MUTEX_INITIALIZER;
static pthread_cond_t server_started = PTHREAD_COND_INITIALIZER;
+static volatile bool server_done = false;
static void *server_thread(void *arg)
{
@@ -222,23 +223,24 @@ static void *server_thread(void *arg)
if (CHECK_FAIL(err < 0)) {
perror("Failed to listed on socket");
- return NULL;
+ return ERR_PTR(err);
}
- client_fd = accept(fd, (struct sockaddr *)&addr, &len);
+ while (true) {
+ client_fd = accept(fd, (struct sockaddr *)&addr, &len);
+ if (client_fd == -1 && errno == EAGAIN) {
+ usleep(50);
+ continue;
+ }
+ break;
+ }
if (CHECK_FAIL(client_fd < 0)) {
perror("Failed to accept client");
- return NULL;
+ return ERR_PTR(err);
}
- /* 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;
- }
+ while (!server_done)
+ usleep(50);
close(client_fd);
@@ -249,6 +251,7 @@ void test_tcp_rtt(void)
{
int server_fd, cgroup_fd;
pthread_t tid;
+ void *server_res;
cgroup_fd = test__join_cgroup("/tcp_rtt");
if (CHECK_FAIL(cgroup_fd < 0))
@@ -267,6 +270,11 @@ void test_tcp_rtt(void)
pthread_mutex_unlock(&server_started_mtx);
CHECK_FAIL(run_test(cgroup_fd, server_fd));
+
+ server_done = true;
+ CHECK_FAIL(pthread_join(tid, &server_res));
+ CHECK_FAIL(IS_ERR(server_res));
+
close_server_fd:
close(server_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..1e4c258de09d
--- /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};
+
+int heap_mprotect(void)
+{
+ void *buf;
+ long sz;
+ int ret;
+
+ sz = sysconf(_SC_PAGESIZE);
+ if (sz < 0)
+ return sz;
+
+ buf = memalign(sz, 2 * sz);
+ if (buf == NULL)
+ return -ENOMEM;
+
+ ret = mprotect(buf, sz, PROT_READ | PROT_WRITE | PROT_EXEC);
+ free(buf);
+ 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 = heap_mprotect();
+ if (CHECK(errno != EPERM, "heap_mprotect", "want errno=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/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_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_attach.c
new file mode 100644
index 000000000000..05b294d6b923
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_attach.c
@@ -0,0 +1,62 @@
+// 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)
+{
+ struct bpf_object *obj1, *obj2, *obj3;
+ const char *file = "./test_xdp.o";
+ int err, fd1, fd2, fd3;
+ __u32 duration = 0;
+ DECLARE_LIBBPF_OPTS(bpf_xdp_set_link_opts, opts,
+ .old_fd = -1);
+
+ err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj1, &fd1);
+ if (CHECK_FAIL(err))
+ return;
+ err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj2, &fd2);
+ if (CHECK_FAIL(err))
+ goto out_1;
+ 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_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_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;
+
+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..a0f688c37023 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c
@@ -4,17 +4,51 @@
#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 +61,21 @@ 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 +84,14 @@ 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 +102,15 @@ 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 +121,8 @@ 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/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/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/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/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..a4e3c223028d
--- /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_heap = 0;
+
+ is_heap = (vma->vm_start >= vma->vm_mm->start_brk &&
+ vma->vm_end <= vma->vm_mm->brk);
+
+ if (is_heap && 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/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_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_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_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_overhead.c b/tools/testing/selftests/bpf/progs/test_overhead.c
index bfe9fbcb9684..56a50b25cd33 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")
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_send_signal_kern.c b/tools/testing/selftests/bpf/progs/test_send_signal_kern.c
index 1acc91e87bfc..b4233d3efac2 100644
--- a/tools/testing/selftests/bpf/progs/test_send_signal_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_send_signal_kern.c
@@ -31,6 +31,12 @@ int send_signal_tp(void *ctx)
return bpf_send_signal_test(ctx);
}
+SEC("tracepoint/sched/sched_switch")
+int send_signal_tp_sched(void *ctx)
+{
+ return bpf_send_signal_test(ctx);
+}
+
SEC("perf_event")
int send_signal_perf(void *ctx)
{
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..8f530843b4da
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_sk_assign.c
@@ -0,0 +1,204 @@
+// 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>
+
+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;
+ size_t tuple_len;
+ 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;
+
+ if (ipv4) {
+ if (tuple->ipv4.dport != bpf_htons(4321))
+ return TC_ACT_OK;
+
+ ln.ipv4.daddr = bpf_htonl(0x7f000001);
+ ln.ipv4.dport = bpf_htons(1234);
+
+ sk = bpf_sk_lookup_udp(skb, &ln, sizeof(ln.ipv4),
+ BPF_F_CURRENT_NETNS, 0);
+ } else {
+ if (tuple->ipv6.dport != bpf_htons(4321))
+ return TC_ACT_OK;
+
+ /* Upper parts of daddr are already zero. */
+ ln.ipv6.daddr[3] = bpf_htonl(0x1);
+ ln.ipv6.dport = bpf_htons(1234);
+
+ sk = bpf_sk_lookup_udp(skb, &ln, sizeof(ln.ipv6),
+ BPF_F_CURRENT_NETNS, 0);
+ }
+
+ /* workaround: We can't do a single socket lookup here, because then
+ * the compiler will likely spill tuple_len to the stack. This makes it
+ * lose all bounds information in the verifier, which then rejects the
+ * call as unsafe.
+ */
+ 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;
+ size_t tuple_len;
+ 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);
+ }
+
+ if (ipv4) {
+ if (tuple->ipv4.dport != bpf_htons(4321))
+ return TC_ACT_OK;
+
+ ln.ipv4.daddr = bpf_htonl(0x7f000001);
+ ln.ipv4.dport = bpf_htons(1234);
+
+ sk = bpf_skc_lookup_tcp(skb, &ln, sizeof(ln.ipv4),
+ BPF_F_CURRENT_NETNS, 0);
+ } else {
+ if (tuple->ipv6.dport != bpf_htons(4321))
+ return TC_ACT_OK;
+
+ /* Upper parts of daddr are already zero. */
+ ln.ipv6.daddr[3] = bpf_htonl(0x1);
+ ln.ipv6.dport = bpf_htons(1234);
+
+ sk = bpf_skc_lookup_tcp(skb, &ln, sizeof(ln.ipv6),
+ BPF_F_CURRENT_NETNS, 0);
+ }
+
+ /* workaround: We can't do a single socket lookup here, because then
+ * the compiler will likely spill tuple_len to the stack. This makes it
+ * lose all bounds information in the verifier, which then rejects the
+ * call as unsafe.
+ */
+ 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_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_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_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_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/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 93040ca83e60..8da77cda5f4a 100644
--- a/tools/testing/selftests/bpf/test_btf.c
+++ b/tools/testing/selftests/bpf/test_btf.c
@@ -1062,6 +1062,48 @@ static struct btf_raw_test raw_tests[] = {
.err_str = "Member exceeds struct_size",
},
+/* Test member unexceeds the size of struct
+ *
+ * enum E {
+ * E0,
+ * E1,
+ * };
+ *
+ * struct A {
+ * char m;
+ * enum E __attribute__((packed)) n;
+ * };
+ */
+{
+ .descr = "size check test #5",
+ .raw_types = {
+ /* int */ /* [1] */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, sizeof(int)),
+ /* char */ /* [2] */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 8, 1),
+ /* enum E { */ /* [3] */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_ENUM, 0, 2), 1),
+ BTF_ENUM_ENC(NAME_TBD, 0),
+ BTF_ENUM_ENC(NAME_TBD, 1),
+ /* } */
+ /* struct A { */ /* [4] */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), 2),
+ BTF_MEMBER_ENC(NAME_TBD, 2, 0), /* char m; */
+ BTF_MEMBER_ENC(NAME_TBD, 3, 8),/* enum E __attribute__((packed)) n; */
+ /* } */
+ BTF_END_RAW,
+ },
+ .str_sec = "\0E\0E0\0E1\0A\0m\0n",
+ .str_sec_size = sizeof("\0E\0E0\0E1\0A\0m\0n"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "size_check5_map",
+ .key_size = sizeof(int),
+ .value_size = 2,
+ .key_type_id = 1,
+ .value_type_id = 4,
+ .max_entries = 4,
+},
+
/* typedef const void * const_void_ptr;
* struct A {
* const_void_ptr m;
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..c6766b2cff85 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;
diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index bab1e6f1d8f1..b521e0a512b6 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;
}
@@ -196,7 +245,7 @@ int bpf_find_map(const char *test, struct bpf_object *obj, const char *name)
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;
}
@@ -367,7 +416,7 @@ 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;
}
@@ -408,7 +457,7 @@ err:
int parse_num_list(const char *s, struct test_selector *sel)
{
- int i, set_len = 0, num, start = 0, end = -1;
+ int i, set_len = 0, new_len, num, start = 0, end = -1;
bool *set = NULL, *tmp, parsing_end = false;
char *next;
@@ -443,18 +492,19 @@ int parse_num_list(const char *s, struct test_selector *sel)
return -EINVAL;
if (end + 1 > set_len) {
- set_len = end + 1;
- tmp = realloc(set, 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++) {
+ for (i = start; i <= end; i++)
set[i] = true;
- }
-
}
if (!set)
@@ -613,10 +663,27 @@ 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 +691,14 @@ 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 +712,12 @@ 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++) {
@@ -669,12 +748,13 @@ 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);
diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h
index bcfa9ef23fda..f4aff6b8284b 100644
--- a/tools/testing/selftests/bpf/test_progs.h
+++ b/tools/testing/selftests/bpf/test_progs.h
@@ -71,6 +71,7 @@ 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 */
@@ -109,10 +110,10 @@ extern struct ipv6_packet pkt_v6;
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 +125,7 @@ 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; \
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/bounds.c b/tools/testing/selftests/bpf/verifier/bounds.c
index d55f476f2237..4d0d09574bf4 100644
--- a/tools/testing/selftests/bpf/verifier/bounds.c
+++ b/tools/testing/selftests/bpf/verifier/bounds.c
@@ -257,17 +257,15 @@
* [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",
+ .errstr = "value 72057594021150720 makes map_value pointer be out of bounds",
.result = REJECT
},
{
@@ -299,17 +297,15 @@
* [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",
+ .errstr = "value 72057594021150720 makes map_value pointer be out of bounds",
.result = REJECT
},
{
@@ -411,16 +407,14 @@
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 +500,42 @@
.errstr = "map_value pointer and 1000000000000",
.result = REJECT
},
+{
+ "bounds check mixed 32bit and 64bit arithmatic. 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 arithmatic. 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
+},
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/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/jmp32.c b/tools/testing/selftests/bpf/verifier/jmp32.c
index bf0322eb5346..bd5cae4a7f73 100644
--- a/tools/testing/selftests/bpf/verifier/jmp32.c
+++ b/tools/testing/selftests/bpf/verifier/jmp32.c
@@ -62,6 +62,21 @@
.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
+ "jset32: ignores upper bits",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_LD_IMM64(BPF_REG_7, 0x8000000000000000),
+ BPF_LD_IMM64(BPF_REG_8, 0x8000000000000000),
+ BPF_JMP_REG(BPF_JSET, BPF_REG_7, BPF_REG_8, 1),
+ BPF_EXIT_INSN(),
+ BPF_JMP32_REG(BPF_JSET, BPF_REG_7, BPF_REG_8, 1),
+ BPF_MOV64_IMM(BPF_REG_0, 2),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .retval = 2,
+},
+{
"jset32: min/max deduction",
.insns = {
BPF_RAND_UEXT_R7,
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 $h1 2001:db8:2::1
diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_acl_drops.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_acl_drops.sh
new file mode 100755
index 000000000000..26044e397157
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_acl_drops.sh
@@ -0,0 +1,151 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test devlink-trap ACL drops functionality over mlxsw.
+
+lib_dir=$(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 acl_drops $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 acl_drops $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_l2_drops.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l2_drops.sh
index 58cdbfb608e9..e7aecb065409 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
@@ -107,11 +107,11 @@ source_mac_is_multicast_test()
RET=0
- devlink_trap_drop_test $trap_name $group_name $swp2
+ devlink_trap_drop_test $trap_name $group_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()
@@ -132,7 +132,7 @@ __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 $group_name $swp2 101
# Add PVID and make sure packets are no longer dropped.
bridge vlan add vid 1 dev $swp1 pvid untagged master
@@ -148,7 +148,7 @@ __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()
@@ -193,7 +193,7 @@ 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 $group_name $swp2 101
# Add the VLAN on the bridge port and make sure packets are no longer
# dropped.
@@ -212,7 +212,7 @@ 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
@@ -237,7 +237,7 @@ __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 $group_name $swp2 101
# Change STP state to forwarding and make sure packets are no longer
# dropped.
@@ -254,7 +254,7 @@ __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
@@ -308,7 +308,7 @@ 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 $group_name $swp2 101
# Allow packets to be flooded to one port.
ip link set dev $swp2 type bridge_slave flood on
@@ -326,7 +326,7 @@ 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
}
@@ -354,7 +354,7 @@ 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 $group_name $swp2 101
# Allow packets to be flooded to one port.
ip link set dev $swp2 type bridge_slave mcast_flood on
@@ -372,7 +372,7 @@ 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
}
@@ -401,7 +401,7 @@ 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 $group_name $swp2 101
# Allow packets to be flooded.
ip link set dev $swp2 type bridge_slave flood on
@@ -419,7 +419,7 @@ 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 $swp2 ip 1 101
}
port_loopback_filter_test()
diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh
index d88d8e47d11b..616f47d86a61 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh
@@ -176,11 +176,11 @@ non_ip_test()
00:00 de:ad:be:ef" &
mz_pid=$!
- devlink_trap_drop_test $trap_name $group_name $rp2
+ devlink_trap_drop_test $trap_name $group_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()
@@ -206,11 +206,11 @@ __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 $group_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()
@@ -242,11 +242,11 @@ __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 $group_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()
@@ -277,11 +277,11 @@ __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 $group_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()
@@ -313,11 +313,11 @@ __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 $group_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()
@@ -345,11 +345,11 @@ 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 $group_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()
@@ -399,11 +399,11 @@ __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 $group_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()
@@ -446,11 +446,11 @@ __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 $group_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()
@@ -485,11 +485,11 @@ 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 $group_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()
@@ -511,11 +511,11 @@ 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 $group_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()
@@ -542,10 +542,10 @@ __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 $group_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 $subnet
}
@@ -641,13 +641,9 @@ erif_disabled_test()
mz_pid=$!
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 +655,6 @@ 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_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 $EXIT_STATUS
diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan.sh
index fd19161dd4ec..e11a416323cf 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan.sh
@@ -314,11 +314,11 @@ overlay_smac_is_mc_test()
-B 192.0.2.17 -t udp sp=12345,dp=$VXPORT,p=$payload -q &
mz_pid=$!
- devlink_trap_drop_test $trap_name $group_name $swp1
+ devlink_trap_drop_test $trap_name $group_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/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..58f3a05f08af
--- /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=3
+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 $EXIT_STATUS
diff --git a/tools/testing/selftests/drivers/net/mlxsw/tc_flower_restrictions.sh b/tools/testing/selftests/drivers/net/mlxsw/tc_flower_restrictions.sh
new file mode 100755
index 000000000000..68c80d0ec1ec
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/tc_flower_restrictions.sh
@@ -0,0 +1,186 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+
+ALL_TESTS="
+ shared_block_drop_test
+ egress_redirect_test
+ multi_mirror_test
+"
+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 $swp1 clsact
+
+ log_test "multi mirror"
+}
+
+setup_prepare()
+{
+ swp1=${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/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 $? "Offload more than expacted"
+ fi
}
tc_flower_test()
diff --git a/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh b/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh
index 4632f51af7ab..729a86cc4ede 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh
@@ -9,6 +9,7 @@ lib_dir=$(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..9f9741444549 100755
--- a/tools/testing/selftests/drivers/net/netdevsim/devlink.sh
+++ b/tools/testing/selftests/drivers/net/netdevsim/devlink.sh
@@ -141,6 +141,16 @@ 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 del $DL_HANDLE/dummy snapshot 25
+ check_err $? "Failed to delete snapshot with id 25"
+
+ check_region_snapshot_count dummy post-second-delete 2
+
log_test "regions test"
}
@@ -367,6 +377,11 @@ 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 $? "Failed to dummy reporter auto_recover option"
+
check_reporter_info dummy healthy 0 0 0 false
local BREAK_MSG="foo bar"
diff --git a/tools/testing/selftests/drivers/net/netdevsim/devlink_trap.sh b/tools/testing/selftests/drivers/net/netdevsim/devlink_trap.sh
index f101ab9441e2..dbd1e014ba17 100755
--- a/tools/testing/selftests/drivers/net/netdevsim/devlink_trap.sh
+++ b/tools/testing/selftests/drivers/net/netdevsim/devlink_trap.sh
@@ -16,6 +16,8 @@ ALL_TESTS="
trap_group_action_test
bad_trap_group_test
trap_group_stats_test
+ trap_policer_test
+ trap_policer_bind_test
port_del_test
dev_del_test
"
@@ -23,6 +25,7 @@ NETDEVSIM_PATH=/sys/bus/netdevsim/
DEV_ADDR=1337
DEV=netdevsim${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 +259,119 @@ trap_group_stats_test()
log_test "Trap group statistics"
}
+trap_policer_test()
+{
+ local packets_t0
+ local packets_t1
+
+ 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()
+{
+ 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 $? "Did not get an error for partially modified trap group"
+
+ log_test "Trap policer binding"
+}
+
port_del_test()
{
local group_name
diff --git a/tools/testing/selftests/firmware/Makefile b/tools/testing/selftests/firmware/Makefile
index 012b2cf69c11..40211cd8f0e6 100644
--- a/tools/testing/selftests/firmware/Makefile
+++ b/tools/testing/selftests/firmware/Makefile
@@ -1,13 +1,10 @@
# SPDX-License-Identifier: GPL-2.0-only
# Makefile for firmware loading selftests
-
-# No binaries, but make sure arg-less "make" doesn't trigger "run_tests"
-all:
+CFLAGS = -Wall \
+ -O2
TEST_PROGS := fw_run_tests.sh
TEST_FILES := fw_fallback.sh fw_filesystem.sh fw_lib.sh
+TEST_GEN_FILES := fw_namespace
include ../lib.mk
-
-# Nothing to clean up.
-clean:
diff --git a/tools/testing/selftests/firmware/fw_filesystem.sh b/tools/testing/selftests/firmware/fw_filesystem.sh
index 56894477c8bd..fcc281373b4d 100755
--- a/tools/testing/selftests/firmware/fw_filesystem.sh
+++ b/tools/testing/selftests/firmware/fw_filesystem.sh
@@ -86,6 +86,29 @@ else
fi
fi
+# Try platform (EFI embedded fw) loading too
+if [ ! -e "$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/Makefile b/tools/testing/selftests/ftrace/Makefile
index cd1f5b3a7774..d6e106fbce11 100644
--- a/tools/testing/selftests/ftrace/Makefile
+++ b/tools/testing/selftests/ftrace/Makefile
@@ -2,7 +2,7 @@
all:
TEST_PROGS := ftracetest
-TEST_FILES := test.d
+TEST_FILES := test.d settings
EXTRA_CLEAN := $(OUTPUT)/logs/*
include ../lib.mk
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 64cfcc75e3c1..f2ee1e889e13 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
@@ -1,6 +1,7 @@
#!/bin/sh
# SPDX-License-Identifier: GPL-2.0
# description: ftrace - function pid filters
+# flags: instance
# Make sure that function pid matching filter works.
# Also test it on an instance directory
@@ -96,13 +97,6 @@ do_test() {
}
do_test
-
-mkdir instances/foo
-cd instances/foo
-do_test
-cd ../../
-rmdir instances/foo
-
do_reset
exit 0
diff --git a/tools/testing/selftests/futex/functional/Makefile b/tools/testing/selftests/futex/functional/Makefile
index 30996306cabc..23207829ec75 100644
--- a/tools/testing/selftests/futex/functional/Makefile
+++ b/tools/testing/selftests/futex/functional/Makefile
@@ -1,7 +1,7 @@
# SPDX-License-Identifier: GPL-2.0
INCLUDES := -I../include -I../../
CFLAGS := $(CFLAGS) -g -O2 -Wall -D_GNU_SOURCE -pthread $(INCLUDES)
-LDFLAGS := $(LDFLAGS) -pthread -lrt
+LDLIBS := -lpthread -lrt
HEADERS := \
../include/futextest.h \
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 67abc1dd50ee..d91c53b726e6 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -8,7 +8,7 @@ KSFT_KHDR_INSTALL := 1
UNAME_M := $(shell uname -m)
LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/sparsebit.c
-LIBKVM_x86_64 = lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/ucall.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
@@ -26,6 +26,7 @@ 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 += clear_dirty_log_test
TEST_GEN_PROGS_x86_64 += dirty_log_test
TEST_GEN_PROGS_x86_64 += kvm_create_max_vcpus
diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h
index aa6451b3f740..7428513a4c68 100644
--- a/tools/testing/selftests/kvm/include/x86_64/processor.h
+++ b/tools/testing/selftests/kvm/include/x86_64/processor.h
@@ -36,24 +36,24 @@
#define X86_CR4_SMAP (1ul << 21)
#define X86_CR4_PKE (1ul << 22)
-/* The enum values match the intruction encoding of each register */
-enum x86_register {
- RAX = 0,
- RCX,
- RDX,
- RBX,
- RSP,
- RBP,
- RSI,
- RDI,
- R8,
- R9,
- R10,
- R11,
- R12,
- R13,
- R14,
- R15,
+/* General Registers in 64-Bit Mode */
+struct gpr64_regs {
+ u64 rax;
+ u64 rcx;
+ u64 rdx;
+ u64 rbx;
+ u64 rsp;
+ u64 rbp;
+ u64 rsi;
+ u64 rdi;
+ u64 r8;
+ u64 r9;
+ u64 r10;
+ u64 r11;
+ u64 r12;
+ u64 r13;
+ u64 r14;
+ u64 r15;
};
struct desc64 {
@@ -220,20 +220,20 @@ static inline void set_cr4(uint64_t val)
__asm__ __volatile__("mov %0, %%cr4" : : "r" (val) : "memory");
}
-static inline uint64_t get_gdt_base(void)
+static inline struct desc_ptr get_gdt(void)
{
struct desc_ptr gdt;
__asm__ __volatile__("sgdt %[gdt]"
: /* output */ [gdt]"=m"(gdt));
- return gdt.address;
+ return gdt;
}
-static inline uint64_t get_idt_base(void)
+static inline struct desc_ptr get_idt(void)
{
struct desc_ptr idt;
__asm__ __volatile__("sidt %[idt]"
: /* output */ [idt]"=m"(idt));
- return idt.address;
+ return idt;
}
#define SET_XMM(__var, __xmm) \
diff --git a/tools/testing/selftests/kvm/include/x86_64/svm.h b/tools/testing/selftests/kvm/include/x86_64/svm.h
new file mode 100644
index 000000000000..f4ea2355dbc2
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/x86_64/svm.h
@@ -0,0 +1,297 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * tools/testing/selftests/kvm/include/x86_64/svm.h
+ * This is a copy of arch/x86/include/asm/svm.h
+ *
+ */
+
+#ifndef SELFTEST_KVM_SVM_H
+#define SELFTEST_KVM_SVM_H
+
+enum {
+ INTERCEPT_INTR,
+ INTERCEPT_NMI,
+ INTERCEPT_SMI,
+ INTERCEPT_INIT,
+ INTERCEPT_VINTR,
+ INTERCEPT_SELECTIVE_CR0,
+ INTERCEPT_STORE_IDTR,
+ INTERCEPT_STORE_GDTR,
+ INTERCEPT_STORE_LDTR,
+ INTERCEPT_STORE_TR,
+ INTERCEPT_LOAD_IDTR,
+ INTERCEPT_LOAD_GDTR,
+ INTERCEPT_LOAD_LDTR,
+ INTERCEPT_LOAD_TR,
+ INTERCEPT_RDTSC,
+ INTERCEPT_RDPMC,
+ INTERCEPT_PUSHF,
+ INTERCEPT_POPF,
+ INTERCEPT_CPUID,
+ INTERCEPT_RSM,
+ INTERCEPT_IRET,
+ INTERCEPT_INTn,
+ INTERCEPT_INVD,
+ INTERCEPT_PAUSE,
+ INTERCEPT_HLT,
+ INTERCEPT_INVLPG,
+ INTERCEPT_INVLPGA,
+ INTERCEPT_IOIO_PROT,
+ INTERCEPT_MSR_PROT,
+ INTERCEPT_TASK_SWITCH,
+ INTERCEPT_FERR_FREEZE,
+ INTERCEPT_SHUTDOWN,
+ INTERCEPT_VMRUN,
+ INTERCEPT_VMMCALL,
+ INTERCEPT_VMLOAD,
+ INTERCEPT_VMSAVE,
+ INTERCEPT_STGI,
+ INTERCEPT_CLGI,
+ INTERCEPT_SKINIT,
+ INTERCEPT_RDTSCP,
+ INTERCEPT_ICEBP,
+ INTERCEPT_WBINVD,
+ INTERCEPT_MONITOR,
+ INTERCEPT_MWAIT,
+ INTERCEPT_MWAIT_COND,
+ INTERCEPT_XSETBV,
+ INTERCEPT_RDPRU,
+};
+
+
+struct __attribute__ ((__packed__)) vmcb_control_area {
+ u32 intercept_cr;
+ u32 intercept_dr;
+ u32 intercept_exceptions;
+ u64 intercept;
+ u8 reserved_1[40];
+ u16 pause_filter_thresh;
+ u16 pause_filter_count;
+ u64 iopm_base_pa;
+ u64 msrpm_base_pa;
+ u64 tsc_offset;
+ u32 asid;
+ u8 tlb_ctl;
+ u8 reserved_2[3];
+ u32 int_ctl;
+ u32 int_vector;
+ u32 int_state;
+ u8 reserved_3[4];
+ u32 exit_code;
+ u32 exit_code_hi;
+ u64 exit_info_1;
+ u64 exit_info_2;
+ u32 exit_int_info;
+ u32 exit_int_info_err;
+ u64 nested_ctl;
+ u64 avic_vapic_bar;
+ u8 reserved_4[8];
+ u32 event_inj;
+ u32 event_inj_err;
+ u64 nested_cr3;
+ u64 virt_ext;
+ u32 clean;
+ u32 reserved_5;
+ u64 next_rip;
+ u8 insn_len;
+ u8 insn_bytes[15];
+ u64 avic_backing_page; /* Offset 0xe0 */
+ u8 reserved_6[8]; /* Offset 0xe8 */
+ u64 avic_logical_id; /* Offset 0xf0 */
+ u64 avic_physical_id; /* Offset 0xf8 */
+ u8 reserved_7[768];
+};
+
+
+#define TLB_CONTROL_DO_NOTHING 0
+#define TLB_CONTROL_FLUSH_ALL_ASID 1
+#define TLB_CONTROL_FLUSH_ASID 3
+#define TLB_CONTROL_FLUSH_ASID_LOCAL 7
+
+#define V_TPR_MASK 0x0f
+
+#define V_IRQ_SHIFT 8
+#define V_IRQ_MASK (1 << V_IRQ_SHIFT)
+
+#define V_GIF_SHIFT 9
+#define V_GIF_MASK (1 << V_GIF_SHIFT)
+
+#define V_INTR_PRIO_SHIFT 16
+#define V_INTR_PRIO_MASK (0x0f << V_INTR_PRIO_SHIFT)
+
+#define V_IGN_TPR_SHIFT 20
+#define V_IGN_TPR_MASK (1 << V_IGN_TPR_SHIFT)
+
+#define V_INTR_MASKING_SHIFT 24
+#define V_INTR_MASKING_MASK (1 << V_INTR_MASKING_SHIFT)
+
+#define V_GIF_ENABLE_SHIFT 25
+#define V_GIF_ENABLE_MASK (1 << V_GIF_ENABLE_SHIFT)
+
+#define AVIC_ENABLE_SHIFT 31
+#define AVIC_ENABLE_MASK (1 << AVIC_ENABLE_SHIFT)
+
+#define LBR_CTL_ENABLE_MASK BIT_ULL(0)
+#define VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK BIT_ULL(1)
+
+#define SVM_INTERRUPT_SHADOW_MASK 1
+
+#define SVM_IOIO_STR_SHIFT 2
+#define SVM_IOIO_REP_SHIFT 3
+#define SVM_IOIO_SIZE_SHIFT 4
+#define SVM_IOIO_ASIZE_SHIFT 7
+
+#define SVM_IOIO_TYPE_MASK 1
+#define SVM_IOIO_STR_MASK (1 << SVM_IOIO_STR_SHIFT)
+#define SVM_IOIO_REP_MASK (1 << SVM_IOIO_REP_SHIFT)
+#define SVM_IOIO_SIZE_MASK (7 << SVM_IOIO_SIZE_SHIFT)
+#define SVM_IOIO_ASIZE_MASK (7 << SVM_IOIO_ASIZE_SHIFT)
+
+#define SVM_VM_CR_VALID_MASK 0x001fULL
+#define SVM_VM_CR_SVM_LOCK_MASK 0x0008ULL
+#define SVM_VM_CR_SVM_DIS_MASK 0x0010ULL
+
+#define SVM_NESTED_CTL_NP_ENABLE BIT(0)
+#define SVM_NESTED_CTL_SEV_ENABLE BIT(1)
+
+struct __attribute__ ((__packed__)) vmcb_seg {
+ u16 selector;
+ u16 attrib;
+ u32 limit;
+ u64 base;
+};
+
+struct __attribute__ ((__packed__)) vmcb_save_area {
+ struct vmcb_seg es;
+ struct vmcb_seg cs;
+ struct vmcb_seg ss;
+ struct vmcb_seg ds;
+ struct vmcb_seg fs;
+ struct vmcb_seg gs;
+ struct vmcb_seg gdtr;
+ struct vmcb_seg ldtr;
+ struct vmcb_seg idtr;
+ struct vmcb_seg tr;
+ u8 reserved_1[43];
+ u8 cpl;
+ u8 reserved_2[4];
+ u64 efer;
+ u8 reserved_3[112];
+ u64 cr4;
+ u64 cr3;
+ u64 cr0;
+ u64 dr7;
+ u64 dr6;
+ u64 rflags;
+ u64 rip;
+ u8 reserved_4[88];
+ u64 rsp;
+ u8 reserved_5[24];
+ u64 rax;
+ u64 star;
+ u64 lstar;
+ u64 cstar;
+ u64 sfmask;
+ u64 kernel_gs_base;
+ u64 sysenter_cs;
+ u64 sysenter_esp;
+ u64 sysenter_eip;
+ u64 cr2;
+ u8 reserved_6[32];
+ u64 g_pat;
+ u64 dbgctl;
+ u64 br_from;
+ u64 br_to;
+ u64 last_excp_from;
+ u64 last_excp_to;
+};
+
+struct __attribute__ ((__packed__)) vmcb {
+ struct vmcb_control_area control;
+ struct vmcb_save_area save;
+};
+
+#define SVM_CPUID_FUNC 0x8000000a
+
+#define SVM_VM_CR_SVM_DISABLE 4
+
+#define SVM_SELECTOR_S_SHIFT 4
+#define SVM_SELECTOR_DPL_SHIFT 5
+#define SVM_SELECTOR_P_SHIFT 7
+#define SVM_SELECTOR_AVL_SHIFT 8
+#define SVM_SELECTOR_L_SHIFT 9
+#define SVM_SELECTOR_DB_SHIFT 10
+#define SVM_SELECTOR_G_SHIFT 11
+
+#define SVM_SELECTOR_TYPE_MASK (0xf)
+#define SVM_SELECTOR_S_MASK (1 << SVM_SELECTOR_S_SHIFT)
+#define SVM_SELECTOR_DPL_MASK (3 << SVM_SELECTOR_DPL_SHIFT)
+#define SVM_SELECTOR_P_MASK (1 << SVM_SELECTOR_P_SHIFT)
+#define SVM_SELECTOR_AVL_MASK (1 << SVM_SELECTOR_AVL_SHIFT)
+#define SVM_SELECTOR_L_MASK (1 << SVM_SELECTOR_L_SHIFT)
+#define SVM_SELECTOR_DB_MASK (1 << SVM_SELECTOR_DB_SHIFT)
+#define SVM_SELECTOR_G_MASK (1 << SVM_SELECTOR_G_SHIFT)
+
+#define SVM_SELECTOR_WRITE_MASK (1 << 1)
+#define SVM_SELECTOR_READ_MASK SVM_SELECTOR_WRITE_MASK
+#define SVM_SELECTOR_CODE_MASK (1 << 3)
+
+#define INTERCEPT_CR0_READ 0
+#define INTERCEPT_CR3_READ 3
+#define INTERCEPT_CR4_READ 4
+#define INTERCEPT_CR8_READ 8
+#define INTERCEPT_CR0_WRITE (16 + 0)
+#define INTERCEPT_CR3_WRITE (16 + 3)
+#define INTERCEPT_CR4_WRITE (16 + 4)
+#define INTERCEPT_CR8_WRITE (16 + 8)
+
+#define INTERCEPT_DR0_READ 0
+#define INTERCEPT_DR1_READ 1
+#define INTERCEPT_DR2_READ 2
+#define INTERCEPT_DR3_READ 3
+#define INTERCEPT_DR4_READ 4
+#define INTERCEPT_DR5_READ 5
+#define INTERCEPT_DR6_READ 6
+#define INTERCEPT_DR7_READ 7
+#define INTERCEPT_DR0_WRITE (16 + 0)
+#define INTERCEPT_DR1_WRITE (16 + 1)
+#define INTERCEPT_DR2_WRITE (16 + 2)
+#define INTERCEPT_DR3_WRITE (16 + 3)
+#define INTERCEPT_DR4_WRITE (16 + 4)
+#define INTERCEPT_DR5_WRITE (16 + 5)
+#define INTERCEPT_DR6_WRITE (16 + 6)
+#define INTERCEPT_DR7_WRITE (16 + 7)
+
+#define SVM_EVTINJ_VEC_MASK 0xff
+
+#define SVM_EVTINJ_TYPE_SHIFT 8
+#define SVM_EVTINJ_TYPE_MASK (7 << SVM_EVTINJ_TYPE_SHIFT)
+
+#define SVM_EVTINJ_TYPE_INTR (0 << SVM_EVTINJ_TYPE_SHIFT)
+#define SVM_EVTINJ_TYPE_NMI (2 << SVM_EVTINJ_TYPE_SHIFT)
+#define SVM_EVTINJ_TYPE_EXEPT (3 << SVM_EVTINJ_TYPE_SHIFT)
+#define SVM_EVTINJ_TYPE_SOFT (4 << SVM_EVTINJ_TYPE_SHIFT)
+
+#define SVM_EVTINJ_VALID (1 << 31)
+#define SVM_EVTINJ_VALID_ERR (1 << 11)
+
+#define SVM_EXITINTINFO_VEC_MASK SVM_EVTINJ_VEC_MASK
+#define SVM_EXITINTINFO_TYPE_MASK SVM_EVTINJ_TYPE_MASK
+
+#define SVM_EXITINTINFO_TYPE_INTR SVM_EVTINJ_TYPE_INTR
+#define SVM_EXITINTINFO_TYPE_NMI SVM_EVTINJ_TYPE_NMI
+#define SVM_EXITINTINFO_TYPE_EXEPT SVM_EVTINJ_TYPE_EXEPT
+#define SVM_EXITINTINFO_TYPE_SOFT SVM_EVTINJ_TYPE_SOFT
+
+#define SVM_EXITINTINFO_VALID SVM_EVTINJ_VALID
+#define SVM_EXITINTINFO_VALID_ERR SVM_EVTINJ_VALID_ERR
+
+#define SVM_EXITINFOSHIFT_TS_REASON_IRET 36
+#define SVM_EXITINFOSHIFT_TS_REASON_JMP 38
+#define SVM_EXITINFOSHIFT_TS_HAS_ERROR_CODE 44
+
+#define SVM_EXITINFO_REG_MASK 0x0F
+
+#define SVM_CR0_SELECTIVE_MASK (X86_CR0_TS | X86_CR0_MP)
+
+#endif /* SELFTEST_KVM_SVM_H */
diff --git a/tools/testing/selftests/kvm/include/x86_64/svm_util.h b/tools/testing/selftests/kvm/include/x86_64/svm_util.h
new file mode 100644
index 000000000000..cd037917fece
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/x86_64/svm_util.h
@@ -0,0 +1,38 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * tools/testing/selftests/kvm/include/x86_64/svm_utils.h
+ * Header for nested SVM testing
+ *
+ * Copyright (C) 2020, Red Hat, Inc.
+ */
+
+#ifndef SELFTEST_KVM_SVM_UTILS_H
+#define SELFTEST_KVM_SVM_UTILS_H
+
+#include <stdint.h>
+#include "svm.h"
+#include "processor.h"
+
+#define CPUID_SVM_BIT 2
+#define CPUID_SVM BIT_ULL(CPUID_SVM_BIT)
+
+#define SVM_EXIT_VMMCALL 0x081
+
+struct svm_test_data {
+ /* VMCB */
+ struct vmcb *vmcb; /* gva */
+ void *vmcb_hva;
+ uint64_t vmcb_gpa;
+
+ /* host state-save area */
+ struct vmcb_save_area *save_area; /* gva */
+ void *save_area_hva;
+ uint64_t save_area_gpa;
+};
+
+struct svm_test_data *vcpu_alloc_svm(struct kvm_vm *vm, vm_vaddr_t *p_svm_gva);
+void generic_svm_setup(struct svm_test_data *svm, void *guest_rip, void *guest_rsp);
+void run_guest(struct vmcb *vmcb, uint64_t vmcb_gpa);
+void nested_svm_check_supported(void);
+
+#endif /* SELFTEST_KVM_SVM_UTILS_H */
diff --git a/tools/testing/selftests/kvm/lib/x86_64/svm.c b/tools/testing/selftests/kvm/lib/x86_64/svm.c
new file mode 100644
index 000000000000..6e05a8fc3fe0
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/x86_64/svm.c
@@ -0,0 +1,161 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * tools/testing/selftests/kvm/lib/x86_64/svm.c
+ * Helpers used for nested SVM testing
+ * Largely inspired from KVM unit test svm.c
+ *
+ * Copyright (C) 2020, Red Hat, Inc.
+ */
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "../kvm_util_internal.h"
+#include "processor.h"
+#include "svm_util.h"
+
+struct gpr64_regs guest_regs;
+u64 rflags;
+
+/* Allocate memory regions for nested SVM tests.
+ *
+ * Input Args:
+ * vm - The VM to allocate guest-virtual addresses in.
+ *
+ * Output Args:
+ * p_svm_gva - The guest virtual address for the struct svm_test_data.
+ *
+ * Return:
+ * Pointer to structure with the addresses of the SVM areas.
+ */
+struct svm_test_data *
+vcpu_alloc_svm(struct kvm_vm *vm, vm_vaddr_t *p_svm_gva)
+{
+ vm_vaddr_t svm_gva = vm_vaddr_alloc(vm, getpagesize(),
+ 0x10000, 0, 0);
+ struct svm_test_data *svm = addr_gva2hva(vm, svm_gva);
+
+ svm->vmcb = (void *)vm_vaddr_alloc(vm, getpagesize(),
+ 0x10000, 0, 0);
+ svm->vmcb_hva = addr_gva2hva(vm, (uintptr_t)svm->vmcb);
+ svm->vmcb_gpa = addr_gva2gpa(vm, (uintptr_t)svm->vmcb);
+
+ svm->save_area = (void *)vm_vaddr_alloc(vm, getpagesize(),
+ 0x10000, 0, 0);
+ svm->save_area_hva = addr_gva2hva(vm, (uintptr_t)svm->save_area);
+ svm->save_area_gpa = addr_gva2gpa(vm, (uintptr_t)svm->save_area);
+
+ *p_svm_gva = svm_gva;
+ return svm;
+}
+
+static void vmcb_set_seg(struct vmcb_seg *seg, u16 selector,
+ u64 base, u32 limit, u32 attr)
+{
+ seg->selector = selector;
+ seg->attrib = attr;
+ seg->limit = limit;
+ seg->base = base;
+}
+
+void generic_svm_setup(struct svm_test_data *svm, void *guest_rip, void *guest_rsp)
+{
+ struct vmcb *vmcb = svm->vmcb;
+ uint64_t vmcb_gpa = svm->vmcb_gpa;
+ struct vmcb_save_area *save = &vmcb->save;
+ struct vmcb_control_area *ctrl = &vmcb->control;
+ u32 data_seg_attr = 3 | SVM_SELECTOR_S_MASK | SVM_SELECTOR_P_MASK
+ | SVM_SELECTOR_DB_MASK | SVM_SELECTOR_G_MASK;
+ u32 code_seg_attr = 9 | SVM_SELECTOR_S_MASK | SVM_SELECTOR_P_MASK
+ | SVM_SELECTOR_L_MASK | SVM_SELECTOR_G_MASK;
+ uint64_t efer;
+
+ efer = rdmsr(MSR_EFER);
+ wrmsr(MSR_EFER, efer | EFER_SVME);
+ wrmsr(MSR_VM_HSAVE_PA, svm->save_area_gpa);
+
+ memset(vmcb, 0, sizeof(*vmcb));
+ asm volatile ("vmsave\n\t" : : "a" (vmcb_gpa) : "memory");
+ vmcb_set_seg(&save->es, get_es(), 0, -1U, data_seg_attr);
+ vmcb_set_seg(&save->cs, get_cs(), 0, -1U, code_seg_attr);
+ vmcb_set_seg(&save->ss, get_ss(), 0, -1U, data_seg_attr);
+ vmcb_set_seg(&save->ds, get_ds(), 0, -1U, data_seg_attr);
+ vmcb_set_seg(&save->gdtr, 0, get_gdt().address, get_gdt().size, 0);
+ vmcb_set_seg(&save->idtr, 0, get_idt().address, get_idt().size, 0);
+
+ ctrl->asid = 1;
+ save->cpl = 0;
+ save->efer = rdmsr(MSR_EFER);
+ asm volatile ("mov %%cr4, %0" : "=r"(save->cr4) : : "memory");
+ asm volatile ("mov %%cr3, %0" : "=r"(save->cr3) : : "memory");
+ asm volatile ("mov %%cr0, %0" : "=r"(save->cr0) : : "memory");
+ asm volatile ("mov %%dr7, %0" : "=r"(save->dr7) : : "memory");
+ asm volatile ("mov %%dr6, %0" : "=r"(save->dr6) : : "memory");
+ asm volatile ("mov %%cr2, %0" : "=r"(save->cr2) : : "memory");
+ save->g_pat = rdmsr(MSR_IA32_CR_PAT);
+ save->dbgctl = rdmsr(MSR_IA32_DEBUGCTLMSR);
+ ctrl->intercept = (1ULL << INTERCEPT_VMRUN) |
+ (1ULL << INTERCEPT_VMMCALL);
+
+ vmcb->save.rip = (u64)guest_rip;
+ vmcb->save.rsp = (u64)guest_rsp;
+ guest_regs.rdi = (u64)svm;
+}
+
+/*
+ * save/restore 64-bit general registers except rax, rip, rsp
+ * which are directly handed through the VMCB guest processor state
+ */
+#define SAVE_GPR_C \
+ "xchg %%rbx, guest_regs+0x20\n\t" \
+ "xchg %%rcx, guest_regs+0x10\n\t" \
+ "xchg %%rdx, guest_regs+0x18\n\t" \
+ "xchg %%rbp, guest_regs+0x30\n\t" \
+ "xchg %%rsi, guest_regs+0x38\n\t" \
+ "xchg %%rdi, guest_regs+0x40\n\t" \
+ "xchg %%r8, guest_regs+0x48\n\t" \
+ "xchg %%r9, guest_regs+0x50\n\t" \
+ "xchg %%r10, guest_regs+0x58\n\t" \
+ "xchg %%r11, guest_regs+0x60\n\t" \
+ "xchg %%r12, guest_regs+0x68\n\t" \
+ "xchg %%r13, guest_regs+0x70\n\t" \
+ "xchg %%r14, guest_regs+0x78\n\t" \
+ "xchg %%r15, guest_regs+0x80\n\t"
+
+#define LOAD_GPR_C SAVE_GPR_C
+
+/*
+ * selftests do not use interrupts so we dropped clgi/sti/cli/stgi
+ * for now. registers involved in LOAD/SAVE_GPR_C are eventually
+ * unmodified so they do not need to be in the clobber list.
+ */
+void run_guest(struct vmcb *vmcb, uint64_t vmcb_gpa)
+{
+ asm volatile (
+ "vmload\n\t"
+ "mov rflags, %%r15\n\t" // rflags
+ "mov %%r15, 0x170(%[vmcb])\n\t"
+ "mov guest_regs, %%r15\n\t" // rax
+ "mov %%r15, 0x1f8(%[vmcb])\n\t"
+ LOAD_GPR_C
+ "vmrun\n\t"
+ SAVE_GPR_C
+ "mov 0x170(%[vmcb]), %%r15\n\t" // rflags
+ "mov %%r15, rflags\n\t"
+ "mov 0x1f8(%[vmcb]), %%r15\n\t" // rax
+ "mov %%r15, guest_regs\n\t"
+ "vmsave\n\t"
+ : : [vmcb] "r" (vmcb), [vmcb_gpa] "a" (vmcb_gpa)
+ : "r15", "memory");
+}
+
+void nested_svm_check_supported(void)
+{
+ struct kvm_cpuid_entry2 *entry =
+ kvm_get_supported_cpuid_entry(0x80000001);
+
+ if (!(entry->ecx & CPUID_SVM)) {
+ fprintf(stderr, "nested SVM not enabled, skipping test\n");
+ 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 85064baf5e97..7aaa99ca4dbc 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/vmx.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/vmx.c
@@ -288,9 +288,9 @@ static inline void init_vmcs_host_state(void)
vmwrite(HOST_FS_BASE, rdmsr(MSR_FS_BASE));
vmwrite(HOST_GS_BASE, rdmsr(MSR_GS_BASE));
vmwrite(HOST_TR_BASE,
- get_desc64_base((struct desc64 *)(get_gdt_base() + get_tr())));
- vmwrite(HOST_GDTR_BASE, get_gdt_base());
- vmwrite(HOST_IDTR_BASE, get_idt_base());
+ get_desc64_base((struct desc64 *)(get_gdt().address + get_tr())));
+ vmwrite(HOST_GDTR_BASE, get_gdt().address);
+ vmwrite(HOST_IDTR_BASE, get_idt().address);
vmwrite(HOST_IA32_SYSENTER_ESP, rdmsr(MSR_IA32_SYSENTER_ESP));
vmwrite(HOST_IA32_SYSENTER_EIP, rdmsr(MSR_IA32_SYSENTER_EIP));
}
diff --git a/tools/testing/selftests/kvm/x86_64/svm_vmcall_test.c b/tools/testing/selftests/kvm/x86_64/svm_vmcall_test.c
new file mode 100644
index 000000000000..e280f68f6365
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/svm_vmcall_test.c
@@ -0,0 +1,79 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * svm_vmcall_test
+ *
+ * Copyright (C) 2020, Red Hat, Inc.
+ *
+ * Nested SVM testing: VMCALL
+ */
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+#include "svm_util.h"
+
+#define VCPU_ID 5
+
+static struct kvm_vm *vm;
+
+static void l2_guest_code(struct svm_test_data *svm)
+{
+ __asm__ __volatile__("vmcall");
+}
+
+static void l1_guest_code(struct svm_test_data *svm)
+{
+ #define L2_GUEST_STACK_SIZE 64
+ unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
+ struct vmcb *vmcb = svm->vmcb;
+
+ /* Prepare for L2 execution. */
+ generic_svm_setup(svm, l2_guest_code,
+ &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+
+ run_guest(vmcb, svm->vmcb_gpa);
+
+ GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_VMMCALL);
+ GUEST_DONE();
+}
+
+int main(int argc, char *argv[])
+{
+ vm_vaddr_t svm_gva;
+
+ nested_svm_check_supported();
+
+ vm = vm_create_default(VCPU_ID, 0, (void *) l1_guest_code);
+ vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
+
+ vcpu_alloc_svm(vm, &svm_gva);
+ vcpu_args_set(vm, VCPU_ID, 1, svm_gva);
+
+ for (;;) {
+ volatile struct kvm_run *run = vcpu_state(vm, VCPU_ID);
+ struct ucall uc;
+
+ vcpu_run(vm, VCPU_ID);
+ TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+ "Got exit_reason other than KVM_EXIT_IO: %u (%s)\n",
+ run->exit_reason,
+ exit_reason_str(run->exit_reason));
+
+ switch (get_ucall(vm, VCPU_ID, &uc)) {
+ case UCALL_ABORT:
+ TEST_ASSERT(false, "%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);
+ }
+ }
+done:
+ kvm_vm_free(vm);
+ return 0;
+}
diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk
index 70f03dff5479..b0556c752443 100644
--- a/tools/testing/selftests/lib.mk
+++ b/tools/testing/selftests/lib.mk
@@ -83,17 +83,20 @@ else
$(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_PROGS))
endif
+define INSTALL_SINGLE_RULE
+ $(if $(INSTALL_LIST),@mkdir -p $(INSTALL_PATH))
+ $(if $(INSTALL_LIST),@echo rsync -a $(INSTALL_LIST) $(INSTALL_PATH)/)
+ $(if $(INSTALL_LIST),@rsync -a $(INSTALL_LIST) $(INSTALL_PATH)/)
+endef
+
define INSTALL_RULE
- @if [ "X$(TEST_PROGS)$(TEST_PROGS_EXTENDED)$(TEST_FILES)" != "X" ]; then \
- mkdir -p ${INSTALL_PATH}; \
- echo "rsync -a $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(INSTALL_PATH)/"; \
- rsync -a $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(INSTALL_PATH)/; \
- fi
- @if [ "X$(TEST_GEN_PROGS)$(TEST_CUSTOM_PROGS)$(TEST_GEN_PROGS_EXTENDED)$(TEST_GEN_FILES)" != "X" ]; then \
- mkdir -p ${INSTALL_PATH}; \
- echo "rsync -a $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(INSTALL_PATH)/"; \
- rsync -a $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(INSTALL_PATH)/; \
- fi
+ $(eval INSTALL_LIST = $(TEST_PROGS)) $(INSTALL_SINGLE_RULE)
+ $(eval INSTALL_LIST = $(TEST_PROGS_EXTENDED)) $(INSTALL_SINGLE_RULE)
+ $(eval INSTALL_LIST = $(TEST_FILES)) $(INSTALL_SINGLE_RULE)
+ $(eval INSTALL_LIST = $(TEST_GEN_PROGS)) $(INSTALL_SINGLE_RULE)
+ $(eval INSTALL_LIST = $(TEST_CUSTOM_PROGS)) $(INSTALL_SINGLE_RULE)
+ $(eval INSTALL_LIST = $(TEST_GEN_PROGS_EXTENDED)) $(INSTALL_SINGLE_RULE)
+ $(eval INSTALL_LIST = $(TEST_GEN_FILES)) $(INSTALL_SINGLE_RULE)
endef
install: all
diff --git a/tools/testing/selftests/livepatch/Makefile b/tools/testing/selftests/livepatch/Makefile
index 3876d8d62494..1acc9e1fa3fb 100644
--- a/tools/testing/selftests/livepatch/Makefile
+++ b/tools/testing/selftests/livepatch/Makefile
@@ -8,4 +8,6 @@ TEST_PROGS := \
test-state.sh \
test-ftrace.sh
+TEST_FILES := settings
+
include ../lib.mk
diff --git a/tools/testing/selftests/lkdtm/.gitignore b/tools/testing/selftests/lkdtm/.gitignore
new file mode 100644
index 000000000000..f26212605b6b
--- /dev/null
+++ b/tools/testing/selftests/lkdtm/.gitignore
@@ -0,0 +1,2 @@
+*.sh
+!run.sh
diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore
index ecc52d4c034d..997c65dcad68 100644
--- a/tools/testing/selftests/net/.gitignore
+++ b/tools/testing/selftests/net/.gitignore
@@ -23,3 +23,8 @@ 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 b5694196430a..3f386eb9e7d7 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -11,7 +11,11 @@ TEST_PROGS += udpgso_bench.sh fib_rule_tests.sh msg_zerocopy.sh psock_snd.sh
TEST_PROGS += udpgro_bench.sh udpgro.sh test_vxlan_under_vrf.sh reuseport_addr_any.sh
TEST_PROGS += test_vxlan_fdb_changelink.sh so_txtime.sh ipv6_flowlabel.sh
TEST_PROGS += tcp_fastopen_backup_key.sh fcnal-test.sh l2tp.sh traceroute.sh
-TEST_PROGS += fin_ack_lat.sh
+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_EXTENDED := in_netns.sh
TEST_GEN_FILES = socket nettest
TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy reuseport_addr_any
@@ -20,6 +24,8 @@ 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
@@ -27,5 +33,5 @@ KSFT_KHDR_INSTALL := 1
include ../lib.mk
$(OUTPUT)/reuseport_bpf_numa: LDLIBS += -lnuma
-$(OUTPUT)/tcp_mmap: LDFLAGS += -lpthread
-$(OUTPUT)/tcp_inq: LDFLAGS += -lpthread
+$(OUTPUT)/tcp_mmap: LDLIBS += -lpthread
+$(OUTPUT)/tcp_inq: LDLIBS += -lpthread
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_tests.sh b/tools/testing/selftests/net/fib_tests.sh
index 6dd403103800..b7616704b55e 100755
--- a/tools/testing/selftests/net/fib_tests.sh
+++ b/tools/testing/selftests/net/fib_tests.sh
@@ -910,6 +910,12 @@ ipv6_rt_replace_mpath()
check_route6 "2001:db8:104::/64 via 2001:db8:101::3 dev veth1 metric 1024"
log_test $? 0 "Multipath with single path via multipath attribute"
+ # multipath with dev-only
+ add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2"
+ run_cmd "$IP -6 ro replace 2001:db8:104::/64 dev veth1"
+ check_route6 "2001:db8:104::/64 dev veth1 metric 1024"
+ log_test $? 0 "Multipath with dev-only"
+
# route replace fails - invalid nexthop 1
add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2"
run_cmd "$IP -6 ro replace 2001:db8:104::/64 nexthop via 2001:db8:111::3 nexthop via 2001:db8:103::3"
@@ -1035,6 +1041,27 @@ ipv6_addr_metric_test()
fi
log_test $rc 0 "Prefix route with metric on link up"
+ # verify peer metric added correctly
+ set -e
+ run_cmd "$IP -6 addr flush dev dummy2"
+ run_cmd "$IP -6 addr add dev dummy2 2001:db8:104::1 peer 2001:db8:104::2 metric 260"
+ set +e
+
+ check_route6 "2001:db8:104::1 dev dummy2 proto kernel metric 260"
+ log_test $? 0 "Set metric with peer route on local side"
+ log_test $? 0 "User specified metric on local address"
+ check_route6 "2001:db8:104::2 dev dummy2 proto kernel metric 260"
+ log_test $? 0 "Set metric with peer route on peer side"
+
+ set -e
+ run_cmd "$IP -6 addr change dev dummy2 2001:db8:104::1 peer 2001:db8:104::3 metric 261"
+ set +e
+
+ check_route6 "2001:db8:104::1 dev dummy2 proto kernel metric 261"
+ log_test $? 0 "Modify metric and peer address on local side"
+ check_route6 "2001:db8:104::3 dev dummy2 proto kernel metric 261"
+ log_test $? 0 "Modify metric and peer address on peer side"
+
$IP li del dummy1
$IP li del dummy2
cleanup
@@ -1451,13 +1478,20 @@ ipv4_addr_metric_test()
run_cmd "$IP addr flush dev dummy2"
run_cmd "$IP addr add dev dummy2 172.16.104.1/32 peer 172.16.104.2 metric 260"
- run_cmd "$IP addr change dev dummy2 172.16.104.1/32 peer 172.16.104.2 metric 261"
rc=$?
if [ $rc -eq 0 ]; then
- check_route "172.16.104.2 dev dummy2 proto kernel scope link src 172.16.104.1 metric 261"
+ check_route "172.16.104.2 dev dummy2 proto kernel scope link src 172.16.104.1 metric 260"
+ rc=$?
+ fi
+ log_test $rc 0 "Set metric of address with peer route"
+
+ run_cmd "$IP addr change dev dummy2 172.16.104.1/32 peer 172.16.104.3 metric 261"
+ rc=$?
+ if [ $rc -eq 0 ]; then
+ check_route "172.16.104.3 dev dummy2 proto kernel scope link src 172.16.104.1 metric 261"
rc=$?
fi
- log_test $rc 0 "Modify metric of address with peer route"
+ log_test $rc 0 "Modify metric and peer address for peer route"
$IP li del dummy1
$IP li del dummy2
diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile
new file mode 100644
index 000000000000..250fbb2d1625
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/Makefile
@@ -0,0 +1,76 @@
+# SPDX-License-Identifier: GPL-2.0+ OR MIT
+
+TEST_PROGS = bridge_igmp.sh \
+ bridge_port_isolation.sh \
+ bridge_sticky_fdb.sh \
+ bridge_vlan_aware.sh \
+ bridge_vlan_unaware.sh \
+ ethtool.sh \
+ gre_inner_v4_multipath.sh \
+ gre_inner_v6_multipath.sh \
+ gre_multipath.sh \
+ ip6gre_inner_v4_multipath.sh \
+ ip6gre_inner_v6_multipath.sh \
+ ipip_flat_gre_key.sh \
+ ipip_flat_gre_keys.sh \
+ ipip_flat_gre.sh \
+ ipip_hier_gre_key.sh \
+ ipip_hier_gre_keys.sh \
+ ipip_hier_gre.sh \
+ loopback.sh \
+ mirror_gre_bound.sh \
+ mirror_gre_bridge_1d.sh \
+ mirror_gre_bridge_1d_vlan.sh \
+ mirror_gre_bridge_1q_lag.sh \
+ mirror_gre_bridge_1q.sh \
+ mirror_gre_changes.sh \
+ mirror_gre_flower.sh \
+ mirror_gre_lag_lacp.sh \
+ mirror_gre_neigh.sh \
+ mirror_gre_nh.sh \
+ mirror_gre.sh \
+ mirror_gre_vlan_bridge_1q.sh \
+ mirror_gre_vlan.sh \
+ mirror_vlan.sh \
+ router_bridge.sh \
+ router_bridge_vlan.sh \
+ router_broadcast.sh \
+ router_mpath_nh.sh \
+ router_multicast.sh \
+ router_multipath.sh \
+ router.sh \
+ router_vid_1.sh \
+ sch_ets.sh \
+ sch_tbf_ets.sh \
+ sch_tbf_prio.sh \
+ sch_tbf_root.sh \
+ tc_actions.sh \
+ tc_chains.sh \
+ tc_flower_router.sh \
+ tc_flower.sh \
+ tc_shblocks.sh \
+ tc_vlan_modify.sh \
+ vxlan_asymmetric.sh \
+ vxlan_bridge_1d_port_8472.sh \
+ vxlan_bridge_1d.sh \
+ vxlan_bridge_1q_port_8472.sh \
+ vxlan_bridge_1q.sh \
+ vxlan_symmetric.sh
+
+TEST_PROGS_EXTENDED := devlink_lib.sh \
+ ethtool_lib.sh \
+ fib_offload_lib.sh \
+ forwarding.config.sample \
+ ipip_lib.sh \
+ lib.sh \
+ mirror_gre_lib.sh \
+ mirror_gre_topo_lib.sh \
+ mirror_lib.sh \
+ mirror_topo_lib.sh \
+ sch_ets_core.sh \
+ sch_ets_tests.sh \
+ sch_tbf_core.sh \
+ sch_tbf_etsprio.sh \
+ tc_common.sh
+
+include ../../lib.mk
diff --git a/tools/testing/selftests/net/forwarding/devlink_lib.sh b/tools/testing/selftests/net/forwarding/devlink_lib.sh
index 40b076983239..155d48bd4d9e 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
@@ -373,6 +379,7 @@ devlink_trap_drop_test()
local trap_name=$1; shift
local group_name=$1; shift
local dev=$1; shift
+ local handle=$1; shift
# 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
@@ -397,7 +404,7 @@ 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 +413,68 @@ 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 $handle flower
+}
+
+devlink_trap_policers_num_get()
+{
+ devlink -j -p trap policer show | jq '.[]["'$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/ethtool_lib.sh b/tools/testing/selftests/net/forwarding/ethtool_lib.sh
index 925d229a59d8..925d229a59d8 100755..100644
--- a/tools/testing/selftests/net/forwarding/ethtool_lib.sh
+++ b/tools/testing/selftests/net/forwarding/ethtool_lib.sh
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_gre.sh b/tools/testing/selftests/net/forwarding/mirror_gre.sh
index e6fd7a18c655..0266443601bc 100755
--- a/tools/testing/selftests/net/forwarding/mirror_gre.sh
+++ b/tools/testing/selftests/net/forwarding/mirror_gre.sh
@@ -63,22 +63,23 @@ test_span_gre_mac()
{
local tundev=$1; shift
local direction=$1; shift
- local prot=$1; shift
local what=$1; shift
- local swp3mac=$(mac_get $swp3)
- local h3mac=$(mac_get $h3)
+ case "$direction" in
+ ingress) local src_mac=$(mac_get $h1); local dst_mac=$(mac_get $h2)
+ ;;
+ egress) local src_mac=$(mac_get $h2); local dst_mac=$(mac_get $h1)
+ ;;
+ esac
RET=0
mirror_install $swp1 $direction $tundev "matchall $tcflags"
- tc filter add dev $h3 ingress pref 77 prot $prot \
- flower ip_proto 0x2f src_mac $swp3mac dst_mac $h3mac \
- action pass
+ icmp_capture_install h3-${tundev} "src_mac $src_mac dst_mac $dst_mac"
- mirror_test v$h1 192.0.2.1 192.0.2.2 $h3 77 10
+ mirror_test v$h1 192.0.2.1 192.0.2.2 h3-${tundev} 100 10
- tc filter del dev $h3 ingress pref 77
+ icmp_capture_uninstall h3-${tundev}
mirror_uninstall $swp1 $direction
log_test "$direction $what: envelope MAC ($tcflags)"
@@ -120,14 +121,14 @@ test_ip6gretap()
test_gretap_mac()
{
- test_span_gre_mac gt4 ingress ip "mirror to gretap"
- test_span_gre_mac gt4 egress ip "mirror to gretap"
+ test_span_gre_mac gt4 ingress "mirror to gretap"
+ test_span_gre_mac gt4 egress "mirror to gretap"
}
test_ip6gretap_mac()
{
- test_span_gre_mac gt6 ingress ipv6 "mirror to ip6gretap"
- test_span_gre_mac gt6 egress ipv6 "mirror to ip6gretap"
+ test_span_gre_mac gt6 ingress "mirror to ip6gretap"
+ test_span_gre_mac gt6 egress "mirror to ip6gretap"
}
test_all()
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..b50081855913
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/pedit_dsfield.sh
@@ -0,0 +1,238 @@
+#!/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
+ test_ip_dsfield
+ test_ip_dscp
+ test_ip_ecn
+ test_ip_dscp_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
+}
+
+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, 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"
+}
+
+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 $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/tc_common.sh b/tools/testing/selftests/net/forwarding/tc_common.sh
index 64f652633585..0e18e8be6e2a 100644
--- a/tools/testing/selftests/net/forwarding/tc_common.sh
+++ b/tools/testing/selftests/net/forwarding/tc_common.sh
@@ -6,39 +6,14 @@ CHECK_TC="yes"
# Can be overridden by the configuration file. See lib.sh
TC_HIT_TIMEOUT=${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/net/forwarding/vxlan_bridge_1d.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
index bb10e33690b2..ce6bea9675c0 100755
--- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
+++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
@@ -516,9 +516,9 @@ test_tos()
RET=0
tc filter add dev v1 egress pref 77 prot ip \
- flower ip_tos 0x40 action pass
- vxlan_ping_test $h1 192.0.2.3 "-Q 0x40" v1 egress 77 10
- vxlan_ping_test $h1 192.0.2.3 "-Q 0x30" v1 egress 77 0
+ flower ip_tos 0x14 action pass
+ vxlan_ping_test $h1 192.0.2.3 "-Q 0x14" v1 egress 77 10
+ vxlan_ping_test $h1 192.0.2.3 "-Q 0x18" v1 egress 77 0
tc filter del dev v1 egress pref 77 prot ip
log_test "VXLAN: envelope TOS inheritance"
diff --git a/tools/testing/selftests/networking/timestamping/hwtstamp_config.c b/tools/testing/selftests/net/hwtstamp_config.c
index e1fdee841021..e1fdee841021 100644
--- a/tools/testing/selftests/networking/timestamping/hwtstamp_config.c
+++ b/tools/testing/selftests/net/hwtstamp_config.c
diff --git a/tools/testing/selftests/net/mptcp/.gitignore b/tools/testing/selftests/net/mptcp/.gitignore
index d72f07642738..ea13b255a99d 100644
--- a/tools/testing/selftests/net/mptcp/.gitignore
+++ b/tools/testing/selftests/net/mptcp/.gitignore
@@ -1,2 +1,3 @@
mptcp_connect
+pm_nl_ctl
*.pcap
diff --git a/tools/testing/selftests/net/mptcp/Makefile b/tools/testing/selftests/net/mptcp/Makefile
index 93de52016dde..f50976ee7d44 100644
--- a/tools/testing/selftests/net/mptcp/Makefile
+++ b/tools/testing/selftests/net/mptcp/Makefile
@@ -1,12 +1,15 @@
# SPDX-License-Identifier: GPL-2.0
top_srcdir = ../../../../..
+KSFT_KHDR_INSTALL := 1
-CFLAGS = -Wall -Wl,--no-as-needed -O2 -g
+CFLAGS = -Wall -Wl,--no-as-needed -O2 -g -I$(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
EXTRA_CLEAN := *.pcap
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..9172746b6cf0
--- /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 $out
+ 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/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/net/reuseport_addr_any.c b/tools/testing/selftests/net/reuseport_addr_any.c
index c6233935fed1..b8475cb29be7 100644
--- a/tools/testing/selftests/net/reuseport_addr_any.c
+++ b/tools/testing/selftests/net/reuseport_addr_any.c
@@ -21,6 +21,10 @@
#include <sys/socket.h>
#include <unistd.h>
+#ifndef SOL_DCCP
+#define SOL_DCCP 269
+#endif
+
static const char *IP4_ADDR = "127.0.0.1";
static const char *IP6_ADDR = "::1";
static const char *IP4_MAPPED6 = "::ffff:127.0.0.1";
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/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/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/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile
index 08194aa44006..9c0f758310fe 100644
--- a/tools/testing/selftests/netfilter/Makefile
+++ b/tools/testing/selftests/netfilter/Makefile
@@ -3,6 +3,10 @@
TEST_PROGS := nft_trans_stress.sh nft_nat.sh bridge_brouter.sh \
conntrack_icmp_related.sh nft_flowtable.sh ipvs.sh \
- nft_concat_range.sh
+ nft_concat_range.sh \
+ nft_queue.sh
+
+LDLIBS = -lmnl
+TEST_GEN_FILES = nf-queue
include ../lib.mk
diff --git a/tools/testing/selftests/netfilter/config b/tools/testing/selftests/netfilter/config
index 59caa8f71cd8..4faf2ce021d9 100644
--- a/tools/testing/selftests/netfilter/config
+++ b/tools/testing/selftests/netfilter/config
@@ -1,2 +1,8 @@
CONFIG_NET_NS=y
CONFIG_NF_TABLES_INET=y
+CONFIG_NFT_QUEUE=m
+CONFIG_NFT_NAT=m
+CONFIG_NFT_REDIR=m
+CONFIG_NFT_MASQ=m
+CONFIG_NFT_FLOW_OFFLOAD=m
+CONFIG_NF_CT_NETLINK=m
diff --git a/tools/testing/selftests/netfilter/nf-queue.c b/tools/testing/selftests/netfilter/nf-queue.c
new file mode 100644
index 000000000000..29c73bce38fa
--- /dev/null
+++ b/tools/testing/selftests/netfilter/nf-queue.c
@@ -0,0 +1,352 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <errno.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdint.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <string.h>
+#include <time.h>
+#include <arpa/inet.h>
+
+#include <libmnl/libmnl.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nfnetlink.h>
+#include <linux/netfilter/nfnetlink_queue.h>
+
+struct options {
+ bool count_packets;
+ int verbose;
+ unsigned int queue_num;
+ unsigned int timeout;
+};
+
+static unsigned int queue_stats[5];
+static struct options opts;
+
+static void help(const char *p)
+{
+ printf("Usage: %s [-c|-v [-vv] ] [-t timeout] [-q queue_num]\n", p);
+}
+
+static int parse_attr_cb(const struct nlattr *attr, void *data)
+{
+ const struct nlattr **tb = data;
+ int type = mnl_attr_get_type(attr);
+
+ /* skip unsupported attribute in user-space */
+ if (mnl_attr_type_valid(attr, NFQA_MAX) < 0)
+ return MNL_CB_OK;
+
+ switch (type) {
+ case NFQA_MARK:
+ case NFQA_IFINDEX_INDEV:
+ case NFQA_IFINDEX_OUTDEV:
+ case NFQA_IFINDEX_PHYSINDEV:
+ case NFQA_IFINDEX_PHYSOUTDEV:
+ if (mnl_attr_validate(attr, MNL_TYPE_U32) < 0) {
+ perror("mnl_attr_validate");
+ return MNL_CB_ERROR;
+ }
+ break;
+ case NFQA_TIMESTAMP:
+ if (mnl_attr_validate2(attr, MNL_TYPE_UNSPEC,
+ sizeof(struct nfqnl_msg_packet_timestamp)) < 0) {
+ perror("mnl_attr_validate2");
+ return MNL_CB_ERROR;
+ }
+ break;
+ case NFQA_HWADDR:
+ if (mnl_attr_validate2(attr, MNL_TYPE_UNSPEC,
+ sizeof(struct nfqnl_msg_packet_hw)) < 0) {
+ perror("mnl_attr_validate2");
+ return MNL_CB_ERROR;
+ }
+ break;
+ case NFQA_PAYLOAD:
+ break;
+ }
+ tb[type] = attr;
+ return MNL_CB_OK;
+}
+
+static int queue_cb(const struct nlmsghdr *nlh, void *data)
+{
+ struct nlattr *tb[NFQA_MAX+1] = { 0 };
+ struct nfqnl_msg_packet_hdr *ph = NULL;
+ uint32_t id = 0;
+
+ (void)data;
+
+ mnl_attr_parse(nlh, sizeof(struct nfgenmsg), parse_attr_cb, tb);
+ if (tb[NFQA_PACKET_HDR]) {
+ ph = mnl_attr_get_payload(tb[NFQA_PACKET_HDR]);
+ id = ntohl(ph->packet_id);
+
+ if (opts.verbose > 0)
+ printf("packet hook=%u, hwproto 0x%x",
+ ntohs(ph->hw_protocol), ph->hook);
+
+ if (ph->hook >= 5) {
+ fprintf(stderr, "Unknown hook %d\n", ph->hook);
+ return MNL_CB_ERROR;
+ }
+
+ if (opts.verbose > 0) {
+ uint32_t skbinfo = 0;
+
+ if (tb[NFQA_SKB_INFO])
+ skbinfo = ntohl(mnl_attr_get_u32(tb[NFQA_SKB_INFO]));
+ if (skbinfo & NFQA_SKB_CSUMNOTREADY)
+ printf(" csumnotready");
+ if (skbinfo & NFQA_SKB_GSO)
+ printf(" gso");
+ if (skbinfo & NFQA_SKB_CSUM_NOTVERIFIED)
+ printf(" csumnotverified");
+ puts("");
+ }
+
+ if (opts.count_packets)
+ queue_stats[ph->hook]++;
+ }
+
+ return MNL_CB_OK + id;
+}
+
+static struct nlmsghdr *
+nfq_build_cfg_request(char *buf, uint8_t command, int queue_num)
+{
+ struct nlmsghdr *nlh = mnl_nlmsg_put_header(buf);
+ struct nfqnl_msg_config_cmd cmd = {
+ .command = command,
+ .pf = htons(AF_INET),
+ };
+ struct nfgenmsg *nfg;
+
+ nlh->nlmsg_type = (NFNL_SUBSYS_QUEUE << 8) | NFQNL_MSG_CONFIG;
+ nlh->nlmsg_flags = NLM_F_REQUEST;
+
+ nfg = mnl_nlmsg_put_extra_header(nlh, sizeof(*nfg));
+
+ nfg->nfgen_family = AF_UNSPEC;
+ nfg->version = NFNETLINK_V0;
+ nfg->res_id = htons(queue_num);
+
+ mnl_attr_put(nlh, NFQA_CFG_CMD, sizeof(cmd), &cmd);
+
+ return nlh;
+}
+
+static struct nlmsghdr *
+nfq_build_cfg_params(char *buf, uint8_t mode, int range, int queue_num)
+{
+ struct nlmsghdr *nlh = mnl_nlmsg_put_header(buf);
+ struct nfqnl_msg_config_params params = {
+ .copy_range = htonl(range),
+ .copy_mode = mode,
+ };
+ struct nfgenmsg *nfg;
+
+ nlh->nlmsg_type = (NFNL_SUBSYS_QUEUE << 8) | NFQNL_MSG_CONFIG;
+ nlh->nlmsg_flags = NLM_F_REQUEST;
+
+ nfg = mnl_nlmsg_put_extra_header(nlh, sizeof(*nfg));
+ nfg->nfgen_family = AF_UNSPEC;
+ nfg->version = NFNETLINK_V0;
+ nfg->res_id = htons(queue_num);
+
+ mnl_attr_put(nlh, NFQA_CFG_PARAMS, sizeof(params), &params);
+
+ return nlh;
+}
+
+static struct nlmsghdr *
+nfq_build_verdict(char *buf, int id, int queue_num, int verd)
+{
+ struct nfqnl_msg_verdict_hdr vh = {
+ .verdict = htonl(verd),
+ .id = htonl(id),
+ };
+ struct nlmsghdr *nlh;
+ struct nfgenmsg *nfg;
+
+ nlh = mnl_nlmsg_put_header(buf);
+ nlh->nlmsg_type = (NFNL_SUBSYS_QUEUE << 8) | NFQNL_MSG_VERDICT;
+ nlh->nlmsg_flags = NLM_F_REQUEST;
+ nfg = mnl_nlmsg_put_extra_header(nlh, sizeof(*nfg));
+ nfg->nfgen_family = AF_UNSPEC;
+ nfg->version = NFNETLINK_V0;
+ nfg->res_id = htons(queue_num);
+
+ mnl_attr_put(nlh, NFQA_VERDICT_HDR, sizeof(vh), &vh);
+
+ return nlh;
+}
+
+static void print_stats(void)
+{
+ unsigned int last, total;
+ int i;
+
+ if (!opts.count_packets)
+ return;
+
+ total = 0;
+ last = queue_stats[0];
+
+ for (i = 0; i < 5; i++) {
+ printf("hook %d packets %08u\n", i, queue_stats[i]);
+ last = queue_stats[i];
+ total += last;
+ }
+
+ printf("%u packets total\n", total);
+}
+
+struct mnl_socket *open_queue(void)
+{
+ char buf[MNL_SOCKET_BUFFER_SIZE];
+ unsigned int queue_num;
+ struct mnl_socket *nl;
+ struct nlmsghdr *nlh;
+ struct timeval tv;
+ uint32_t flags;
+
+ nl = mnl_socket_open(NETLINK_NETFILTER);
+ if (nl == NULL) {
+ perror("mnl_socket_open");
+ exit(EXIT_FAILURE);
+ }
+
+ if (mnl_socket_bind(nl, 0, MNL_SOCKET_AUTOPID) < 0) {
+ perror("mnl_socket_bind");
+ exit(EXIT_FAILURE);
+ }
+
+ queue_num = opts.queue_num;
+ nlh = nfq_build_cfg_request(buf, NFQNL_CFG_CMD_BIND, queue_num);
+
+ if (mnl_socket_sendto(nl, nlh, nlh->nlmsg_len) < 0) {
+ perror("mnl_socket_sendto");
+ exit(EXIT_FAILURE);
+ }
+
+ nlh = nfq_build_cfg_params(buf, NFQNL_COPY_PACKET, 0xFFFF, queue_num);
+
+ flags = NFQA_CFG_F_GSO | NFQA_CFG_F_UID_GID;
+ mnl_attr_put_u32(nlh, NFQA_CFG_FLAGS, htonl(flags));
+ mnl_attr_put_u32(nlh, NFQA_CFG_MASK, htonl(flags));
+
+ if (mnl_socket_sendto(nl, nlh, nlh->nlmsg_len) < 0) {
+ perror("mnl_socket_sendto");
+ exit(EXIT_FAILURE);
+ }
+
+ memset(&tv, 0, sizeof(tv));
+ tv.tv_sec = opts.timeout;
+ if (opts.timeout && setsockopt(mnl_socket_get_fd(nl),
+ SOL_SOCKET, SO_RCVTIMEO,
+ &tv, sizeof(tv))) {
+ perror("setsockopt(SO_RCVTIMEO)");
+ exit(EXIT_FAILURE);
+ }
+
+ return nl;
+}
+
+static int mainloop(void)
+{
+ unsigned int buflen = 64 * 1024 + MNL_SOCKET_BUFFER_SIZE;
+ struct mnl_socket *nl;
+ struct nlmsghdr *nlh;
+ unsigned int portid;
+ char *buf;
+ int ret;
+
+ buf = malloc(buflen);
+ if (!buf) {
+ perror("malloc");
+ exit(EXIT_FAILURE);
+ }
+
+ nl = open_queue();
+ portid = mnl_socket_get_portid(nl);
+
+ for (;;) {
+ uint32_t id;
+
+ ret = mnl_socket_recvfrom(nl, buf, buflen);
+ if (ret == -1) {
+ if (errno == ENOBUFS)
+ continue;
+
+ if (errno == EAGAIN) {
+ errno = 0;
+ ret = 0;
+ break;
+ }
+
+ perror("mnl_socket_recvfrom");
+ exit(EXIT_FAILURE);
+ }
+
+ ret = mnl_cb_run(buf, ret, 0, portid, queue_cb, NULL);
+ if (ret < 0) {
+ perror("mnl_cb_run");
+ exit(EXIT_FAILURE);
+ }
+
+ id = ret - MNL_CB_OK;
+ nlh = nfq_build_verdict(buf, id, opts.queue_num, NF_ACCEPT);
+ if (mnl_socket_sendto(nl, nlh, nlh->nlmsg_len) < 0) {
+ perror("mnl_socket_sendto");
+ exit(EXIT_FAILURE);
+ }
+ }
+
+ mnl_socket_close(nl);
+
+ return ret;
+}
+
+static void parse_opts(int argc, char **argv)
+{
+ int c;
+
+ while ((c = getopt(argc, argv, "chvt:q:")) != -1) {
+ switch (c) {
+ case 'c':
+ opts.count_packets = true;
+ break;
+ case 'h':
+ help(argv[0]);
+ exit(0);
+ break;
+ case 'q':
+ opts.queue_num = atoi(optarg);
+ if (opts.queue_num > 0xffff)
+ opts.queue_num = 0;
+ break;
+ case 't':
+ opts.timeout = atoi(optarg);
+ break;
+ case 'v':
+ opts.verbose++;
+ break;
+ }
+ }
+}
+
+int main(int argc, char *argv[])
+{
+ int ret;
+
+ parse_opts(argc, argv);
+
+ ret = mainloop();
+ if (opts.count_packets)
+ print_stats();
+
+ return ret;
+}
diff --git a/tools/testing/selftests/netfilter/nft_concat_range.sh b/tools/testing/selftests/netfilter/nft_concat_range.sh
index aca21dde102a..5a4938d6dcf2 100755
--- a/tools/testing/selftests/netfilter/nft_concat_range.sh
+++ b/tools/testing/selftests/netfilter/nft_concat_range.sh
@@ -13,11 +13,12 @@
KSELFTEST_SKIP=4
# Available test groups:
+# - reported_issues: check for issues that were reported in the past
# - correctness: check that packets match given entries, and only those
# - concurrency: attempt races between insertion, deletion and lookup
# - timeout: check that packets match entries until they expire
# - performance: estimate matching rate, compare with rbtree and hash baselines
-TESTS="correctness concurrency timeout"
+TESTS="reported_issues correctness concurrency timeout"
[ "${quicktest}" != "1" ] && TESTS="${TESTS} performance"
# Set types, defined by TYPE_ variables below
@@ -25,6 +26,9 @@ TYPES="net_port port_net net6_port port_proto net6_port_mac net6_port_mac_proto
net_port_net net_mac net_mac_icmp net6_mac_icmp net6_port_net6_port
net_port_mac_proto_net"
+# Reported bugs, also described by TYPE_ variables below
+BUGS="flush_remove_add"
+
# List of possible paths to pktgen script from kernel tree for performance tests
PKTGEN_SCRIPT_PATHS="
../../../samples/pktgen/pktgen_bench_xmit_mode_netif_receive.sh
@@ -327,6 +331,12 @@ flood_spec ip daddr . tcp dport . meta l4proto . ip saddr
perf_duration 0
"
+# Definition of tests for bugs reported in the past:
+# display display text for test report
+TYPE_flush_remove_add="
+display Add two elements, flush, re-add
+"
+
# Set template for all tests, types and rules are filled in depending on test
set_template='
flush ruleset
@@ -440,6 +450,8 @@ setup_set() {
# Check that at least one of the needed tools is available
check_tools() {
+ [ -z "${tools}" ] && return 0
+
__tools=
for tool in ${tools}; do
if [ "${tool}" = "nc" ] && [ "${proto}" = "udp6" ] && \
@@ -1025,7 +1037,7 @@ format_noconcat() {
add() {
if ! nft add element inet filter test "${1}"; then
err "Failed to add ${1} given ruleset:"
- err "$(nft list ruleset -a)"
+ err "$(nft -a list ruleset)"
return 1
fi
}
@@ -1045,7 +1057,7 @@ add_perf() {
add_perf_norange() {
if ! nft add element netdev perf norange "${1}"; then
err "Failed to add ${1} given ruleset:"
- err "$(nft list ruleset -a)"
+ err "$(nft -a list ruleset)"
return 1
fi
}
@@ -1054,7 +1066,7 @@ add_perf_norange() {
add_perf_noconcat() {
if ! nft add element netdev perf noconcat "${1}"; then
err "Failed to add ${1} given ruleset:"
- err "$(nft list ruleset -a)"
+ err "$(nft -a list ruleset)"
return 1
fi
}
@@ -1063,7 +1075,7 @@ add_perf_noconcat() {
del() {
if ! nft delete element inet filter test "${1}"; then
err "Failed to delete ${1} given ruleset:"
- err "$(nft list ruleset -a)"
+ err "$(nft -a list ruleset)"
return 1
fi
}
@@ -1134,7 +1146,7 @@ send_match() {
err " $(for f in ${src}; do
eval format_\$f "${2}"; printf ' '; done)"
err "should have matched ruleset:"
- err "$(nft list ruleset -a)"
+ err "$(nft -a list ruleset)"
return 1
fi
nft reset counter inet filter test >/dev/null
@@ -1160,7 +1172,7 @@ send_nomatch() {
err " $(for f in ${src}; do
eval format_\$f "${2}"; printf ' '; done)"
err "should not have matched ruleset:"
- err "$(nft list ruleset -a)"
+ err "$(nft -a list ruleset)"
return 1
fi
}
@@ -1430,6 +1442,23 @@ test_performance() {
kill "${perf_pid}"
}
+test_bug_flush_remove_add() {
+ set_cmd='{ set s { type ipv4_addr . inet_service; flags interval; }; }'
+ elem1='{ 10.0.0.1 . 22-25, 10.0.0.1 . 10-20 }'
+ elem2='{ 10.0.0.1 . 10-20, 10.0.0.1 . 22-25 }'
+ for i in `seq 1 100`; do
+ nft add table t ${set_cmd} || return ${KSELFTEST_SKIP}
+ nft add element t s ${elem1} 2>/dev/null || return 1
+ nft flush set t s 2>/dev/null || return 1
+ nft add element t s ${elem2} 2>/dev/null || return 1
+ done
+ nft flush ruleset
+}
+
+test_reported_issues() {
+ eval test_bug_"${subtest}"
+}
+
# Run everything in a separate network namespace
[ "${1}" != "run" ] && { unshare -n "${0}" run; exit $?; }
tmp="$(mktemp)"
@@ -1438,9 +1467,15 @@ trap cleanup EXIT
# Entry point for test runs
passed=0
for name in ${TESTS}; do
- printf "TEST: %s\n" "${name}"
- for type in ${TYPES}; do
- eval desc=\$TYPE_"${type}"
+ printf "TEST: %s\n" "$(echo ${name} | tr '_' ' ')"
+ if [ "${name}" = "reported_issues" ]; then
+ SUBTESTS="${BUGS}"
+ else
+ SUBTESTS="${TYPES}"
+ fi
+
+ for subtest in ${SUBTESTS}; do
+ eval desc=\$TYPE_"${subtest}"
IFS='
'
for __line in ${desc}; do
diff --git a/tools/testing/selftests/netfilter/nft_queue.sh b/tools/testing/selftests/netfilter/nft_queue.sh
new file mode 100755
index 000000000000..6898448b4266
--- /dev/null
+++ b/tools/testing/selftests/netfilter/nft_queue.sh
@@ -0,0 +1,332 @@
+#!/bin/bash
+#
+# This tests nf_queue:
+# 1. can process packets from all hooks
+# 2. support running nfqueue from more than one base chain
+#
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+ret=0
+
+sfx=$(mktemp -u "XXXXXXXX")
+ns1="ns1-$sfx"
+ns2="ns2-$sfx"
+nsrouter="nsrouter-$sfx"
+
+cleanup()
+{
+ ip netns del ${ns1}
+ ip netns del ${ns2}
+ ip netns del ${nsrouter}
+ rm -f "$TMPFILE0"
+ rm -f "$TMPFILE1"
+}
+
+nft --version > /dev/null 2>&1
+if [ $? -ne 0 ];then
+ echo "SKIP: Could not run test without nft tool"
+ exit $ksft_skip
+fi
+
+ip -Version > /dev/null 2>&1
+if [ $? -ne 0 ];then
+ echo "SKIP: Could not run test without ip tool"
+ exit $ksft_skip
+fi
+
+ip netns add ${nsrouter}
+if [ $? -ne 0 ];then
+ echo "SKIP: Could not create net namespace"
+ exit $ksft_skip
+fi
+
+TMPFILE0=$(mktemp)
+TMPFILE1=$(mktemp)
+trap cleanup EXIT
+
+ip netns add ${ns1}
+ip netns add ${ns2}
+
+ip link add veth0 netns ${nsrouter} type veth peer name eth0 netns ${ns1} > /dev/null 2>&1
+if [ $? -ne 0 ];then
+ echo "SKIP: No virtual ethernet pair device support in kernel"
+ exit $ksft_skip
+fi
+ip link add veth1 netns ${nsrouter} type veth peer name eth0 netns ${ns2}
+
+ip -net ${nsrouter} link set lo up
+ip -net ${nsrouter} link set veth0 up
+ip -net ${nsrouter} addr add 10.0.1.1/24 dev veth0
+ip -net ${nsrouter} addr add dead:1::1/64 dev veth0
+
+ip -net ${nsrouter} link set veth1 up
+ip -net ${nsrouter} addr add 10.0.2.1/24 dev veth1
+ip -net ${nsrouter} addr add dead:2::1/64 dev veth1
+
+ip -net ${ns1} link set lo up
+ip -net ${ns1} link set eth0 up
+
+ip -net ${ns2} link set lo up
+ip -net ${ns2} link set eth0 up
+
+ip -net ${ns1} addr add 10.0.1.99/24 dev eth0
+ip -net ${ns1} addr add dead:1::99/64 dev eth0
+ip -net ${ns1} route add default via 10.0.1.1
+ip -net ${ns1} route add default via dead:1::1
+
+ip -net ${ns2} addr add 10.0.2.99/24 dev eth0
+ip -net ${ns2} addr add dead:2::99/64 dev eth0
+ip -net ${ns2} route add default via 10.0.2.1
+ip -net ${ns2} route add default via dead:2::1
+
+load_ruleset() {
+ local name=$1
+ local prio=$2
+
+ip netns exec ${nsrouter} nft -f - <<EOF
+table inet $name {
+ chain nfq {
+ ip protocol icmp queue bypass
+ icmpv6 type { "echo-request", "echo-reply" } queue num 1 bypass
+ }
+ chain pre {
+ type filter hook prerouting priority $prio; policy accept;
+ jump nfq
+ }
+ chain input {
+ type filter hook input priority $prio; policy accept;
+ jump nfq
+ }
+ chain forward {
+ type filter hook forward priority $prio; policy accept;
+ tcp dport 12345 queue num 2
+ jump nfq
+ }
+ chain output {
+ type filter hook output priority $prio; policy accept;
+ tcp dport 12345 queue num 3
+ jump nfq
+ }
+ chain post {
+ type filter hook postrouting priority $prio; policy accept;
+ jump nfq
+ }
+}
+EOF
+}
+
+load_counter_ruleset() {
+ local prio=$1
+
+ip netns exec ${nsrouter} nft -f - <<EOF
+table inet countrules {
+ chain pre {
+ type filter hook prerouting priority $prio; policy accept;
+ counter
+ }
+ chain input {
+ type filter hook input priority $prio; policy accept;
+ counter
+ }
+ chain forward {
+ type filter hook forward priority $prio; policy accept;
+ counter
+ }
+ chain output {
+ type filter hook output priority $prio; policy accept;
+ counter
+ }
+ chain post {
+ type filter hook postrouting priority $prio; policy accept;
+ counter
+ }
+}
+EOF
+}
+
+test_ping() {
+ ip netns exec ${ns1} ping -c 1 -q 10.0.2.99 > /dev/null
+ if [ $? -ne 0 ];then
+ return 1
+ fi
+
+ ip netns exec ${ns1} ping -c 1 -q dead:2::99 > /dev/null
+ if [ $? -ne 0 ];then
+ return 1
+ fi
+
+ return 0
+}
+
+test_ping_router() {
+ ip netns exec ${ns1} ping -c 1 -q 10.0.2.1 > /dev/null
+ if [ $? -ne 0 ];then
+ return 1
+ fi
+
+ ip netns exec ${ns1} ping -c 1 -q dead:2::1 > /dev/null
+ if [ $? -ne 0 ];then
+ return 1
+ fi
+
+ return 0
+}
+
+test_queue_blackhole() {
+ local proto=$1
+
+ip netns exec ${nsrouter} nft -f - <<EOF
+table $proto blackh {
+ chain forward {
+ type filter hook forward priority 0; policy accept;
+ queue num 600
+ }
+}
+EOF
+ if [ $proto = "ip" ] ;then
+ ip netns exec ${ns1} ping -c 1 -q 10.0.2.99 > /dev/null
+ lret=$?
+ elif [ $proto = "ip6" ]; then
+ ip netns exec ${ns1} ping -c 1 -q dead:2::99 > /dev/null
+ lret=$?
+ else
+ lret=111
+ fi
+
+ # queue without bypass keyword should drop traffic if no listener exists.
+ if [ $lret -eq 0 ];then
+ echo "FAIL: $proto expected failure, got $lret" 1>&2
+ exit 1
+ fi
+
+ ip netns exec ${nsrouter} nft delete table $proto blackh
+ if [ $? -ne 0 ] ;then
+ echo "FAIL: $proto: Could not delete blackh table"
+ exit 1
+ fi
+
+ echo "PASS: $proto: statement with no listener results in packet drop"
+}
+
+test_queue()
+{
+ local expected=$1
+ local last=""
+
+ # spawn nf-queue listeners
+ ip netns exec ${nsrouter} ./nf-queue -c -q 0 -t 3 > "$TMPFILE0" &
+ ip netns exec ${nsrouter} ./nf-queue -c -q 1 -t 3 > "$TMPFILE1" &
+ sleep 1
+ test_ping
+ ret=$?
+ if [ $ret -ne 0 ];then
+ echo "FAIL: netns routing/connectivity with active listener on queue $queue: $ret" 1>&2
+ exit $ret
+ fi
+
+ test_ping_router
+ ret=$?
+ if [ $ret -ne 0 ];then
+ echo "FAIL: netns router unreachable listener on queue $queue: $ret" 1>&2
+ exit $ret
+ fi
+
+ wait
+ ret=$?
+
+ for file in $TMPFILE0 $TMPFILE1; do
+ last=$(tail -n1 "$file")
+ if [ x"$last" != x"$expected packets total" ]; then
+ echo "FAIL: Expected $expected packets total, but got $last" 1>&2
+ cat "$file" 1>&2
+
+ ip netns exec ${nsrouter} nft list ruleset
+ exit 1
+ fi
+ done
+
+ echo "PASS: Expected and received $last"
+}
+
+test_tcp_forward()
+{
+ ip netns exec ${nsrouter} ./nf-queue -q 2 -t 10 &
+ local nfqpid=$!
+
+ tmpfile=$(mktemp) || exit 1
+ dd conv=sparse status=none if=/dev/zero bs=1M count=100 of=$tmpfile
+ ip netns exec ${ns2} nc -w 5 -l -p 12345 <"$tmpfile" >/dev/null &
+ local rpid=$!
+
+ sleep 1
+ ip netns exec ${ns1} nc -w 5 10.0.2.99 12345 <"$tmpfile" >/dev/null &
+
+ rm -f "$tmpfile"
+
+ wait $rpid
+ wait $lpid
+ [ $? -eq 0 ] && echo "PASS: tcp and nfqueue in forward chain"
+}
+
+test_tcp_localhost()
+{
+ tc -net "${nsrouter}" qdisc add dev lo root netem loss random 1%
+
+ tmpfile=$(mktemp) || exit 1
+
+ dd conv=sparse status=none if=/dev/zero bs=1M count=900 of=$tmpfile
+ ip netns exec ${nsrouter} nc -w 5 -l -p 12345 <"$tmpfile" >/dev/null &
+ local rpid=$!
+
+ ip netns exec ${nsrouter} ./nf-queue -q 3 -t 30 &
+ local nfqpid=$!
+
+ sleep 1
+ ip netns exec ${nsrouter} nc -w 5 127.0.0.1 12345 <"$tmpfile" > /dev/null
+ rm -f "$tmpfile"
+
+ wait $rpid
+ [ $? -eq 0 ] && echo "PASS: tcp via loopback"
+}
+
+ip netns exec ${nsrouter} sysctl net.ipv6.conf.all.forwarding=1 > /dev/null
+ip netns exec ${nsrouter} sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null
+ip netns exec ${nsrouter} sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null
+
+load_ruleset "filter" 0
+
+sleep 3
+
+test_ping
+ret=$?
+if [ $ret -eq 0 ];then
+ # queue bypass works (rules were skipped, no listener)
+ echo "PASS: ${ns1} can reach ${ns2}"
+else
+ echo "FAIL: ${ns1} cannot reach ${ns2}: $ret" 1>&2
+ exit $ret
+fi
+
+test_queue_blackhole ip
+test_queue_blackhole ip6
+
+# dummy ruleset to add base chains between the
+# queueing rules. We don't want the second reinject
+# to re-execute the old hooks.
+load_counter_ruleset 10
+
+# we are hooking all: prerouting/input/forward/output/postrouting.
+# we ping ${ns2} from ${ns1} via ${nsrouter} using ipv4 and ipv6, so:
+# 1x icmp prerouting,forward,postrouting -> 3 queue events (6 incl. reply).
+# 1x icmp prerouting,input,output postrouting -> 4 queue events incl. reply.
+# so we expect that userspace program receives 10 packets.
+test_queue 10
+
+# same. We queue to a second program as well.
+load_ruleset "filter2" 20
+test_queue 20
+
+test_tcp_forward
+test_tcp_localhost
+
+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/openat2/helpers.c b/tools/testing/selftests/openat2/helpers.c
index e9a6557ab16f..5074681ffdc9 100644
--- a/tools/testing/selftests/openat2/helpers.c
+++ b/tools/testing/selftests/openat2/helpers.c
@@ -46,7 +46,7 @@ int sys_renameat2(int olddirfd, const char *oldpath,
int touchat(int dfd, const char *path)
{
- int fd = openat(dfd, path, O_CREAT);
+ int fd = openat(dfd, path, O_CREAT, 0700);
if (fd >= 0)
close(fd);
return fd;
diff --git a/tools/testing/selftests/openat2/resolve_test.c b/tools/testing/selftests/openat2/resolve_test.c
index 7a94b1da8e7b..bbafad440893 100644
--- a/tools/testing/selftests/openat2/resolve_test.c
+++ b/tools/testing/selftests/openat2/resolve_test.c
@@ -230,7 +230,7 @@ void test_openat2_opath_tests(void)
{ .name = "[in_root] garbage link to /root",
.path = "cheeky/garbageself", .how.resolve = RESOLVE_IN_ROOT,
.out.path = "root", .pass = true },
- { .name = "[in_root] chainged garbage links to /root",
+ { .name = "[in_root] chained garbage links to /root",
.path = "abscheeky/garbageself", .how.resolve = RESOLVE_IN_ROOT,
.out.path = "root", .pass = true },
{ .name = "[in_root] relative path to 'root'",
diff --git a/tools/testing/selftests/pidfd/.gitignore b/tools/testing/selftests/pidfd/.gitignore
index 3a779c084d96..39559d723c41 100644
--- a/tools/testing/selftests/pidfd/.gitignore
+++ b/tools/testing/selftests/pidfd/.gitignore
@@ -2,4 +2,5 @@ pidfd_open_test
pidfd_poll_test
pidfd_test
pidfd_wait
+pidfd_fdinfo_test
pidfd_getfd_test
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 $# arg mustmatch cannotmatch
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh b/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh
index 1871d00bccd7..6f50722f251f 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh
@@ -20,7 +20,9 @@
rundir="${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.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
index e5edd5198725..0326f4a5ff9c 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 "$@"
@@ -68,4 +71,16 @@ do
fi
done
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.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh
index 78d18ab8e954..2315e2ec12d6 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm.sh
@@ -39,7 +39,7 @@ 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 () {
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/TREE10 b/tools/testing/selftests/rcutorture/configs/rcu/TREE10
new file mode 100644
index 000000000000..2debe7891aeb
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE10
@@ -0,0 +1,18 @@
+CONFIG_SMP=y
+CONFIG_NR_CPUS=100
+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/rseq/Makefile b/tools/testing/selftests/rseq/Makefile
index d6469535630a..2af9d39a9716 100644
--- a/tools/testing/selftests/rseq/Makefile
+++ b/tools/testing/selftests/rseq/Makefile
@@ -4,7 +4,7 @@ ifneq ($(shell $(CC) --version 2>&1 | head -n 1 | grep clang),)
CLANG_FLAGS += -no-integrated-as
endif
-CFLAGS += -O2 -Wall -g -I./ -I../../../../usr/include/ -L./ -Wl,-rpath=./ \
+CFLAGS += -O2 -Wall -g -I./ -I../../../../usr/include/ -L$(OUTPUT) -Wl,-rpath=./ \
$(CLANG_FLAGS)
LDLIBS += -lpthread
@@ -19,6 +19,8 @@ TEST_GEN_PROGS_EXTENDED = librseq.so
TEST_PROGS = run_param_test.sh
+TEST_FILES := settings
+
include ../lib.mk
$(OUTPUT)/librseq.so: rseq.c rseq.h rseq-*.h
diff --git a/tools/testing/selftests/rtc/Makefile b/tools/testing/selftests/rtc/Makefile
index de9c8566672a..55198ecc04db 100644
--- a/tools/testing/selftests/rtc/Makefile
+++ b/tools/testing/selftests/rtc/Makefile
@@ -1,9 +1,11 @@
# SPDX-License-Identifier: GPL-2.0
CFLAGS += -O3 -Wl,-no-as-needed -Wall
-LDFLAGS += -lrt -lpthread -lm
+LDLIBS += -lrt -lpthread -lm
TEST_GEN_PROGS = rtctest
TEST_GEN_PROGS_EXTENDED = setdate
+TEST_FILES := settings
+
include ../lib.mk
diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c
index 7bf82fb07f67..89fb3e0b552e 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)
{
@@ -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 };
@@ -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;
@@ -3196,6 +3250,24 @@ 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/tc-testing/config b/tools/testing/selftests/tc-testing/config
index 477bc61b374a..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
@@ -57,3 +58,9 @@ CONFIG_NET_IFE_SKBMARK=m
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/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/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/timens/Makefile b/tools/testing/selftests/timens/Makefile
index e9fb30bd8aeb..b4fd9a934654 100644
--- a/tools/testing/selftests/timens/Makefile
+++ b/tools/testing/selftests/timens/Makefile
@@ -2,6 +2,6 @@ TEST_GEN_PROGS := timens timerfd timer clock_nanosleep procfs exec
TEST_GEN_PROGS_EXTENDED := gettime_perf
CFLAGS := -Wall -Werror -pthread
-LDFLAGS := -lrt -ldl
+LDLIBS := -lrt -ldl
include ../lib.mk
diff --git a/tools/testing/selftests/tpm2/test_smoke.sh b/tools/testing/selftests/tpm2/test_smoke.sh
index 8155c2ea7ccb..b630c7b5950a 100755
--- a/tools/testing/selftests/tpm2/test_smoke.sh
+++ b/tools/testing/selftests/tpm2/test_smoke.sh
@@ -1,8 +1,17 @@
#!/bin/bash
# SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause)
+self.flags = flags
-python -m unittest -v tpm2_tests.SmokeTest
-python -m unittest -v tpm2_tests.AsyncTest
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+
+if [ -f /dev/tpm0 ] ; then
+ python -m unittest -v tpm2_tests.SmokeTest
+ python -m unittest -v tpm2_tests.AsyncTest
+else
+ exit $ksft_skip
+fi
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 a6f5e346635e..180b469c53b4 100755
--- a/tools/testing/selftests/tpm2/test_space.sh
+++ b/tools/testing/selftests/tpm2/test_space.sh
@@ -1,4 +1,11 @@
#!/bin/bash
# SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause)
-python -m unittest -v tpm2_tests.SpaceTest
+# 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
diff --git a/tools/testing/selftests/vm/run_vmtests b/tools/testing/selftests/vm/run_vmtests
index a692ea828317..f33714843198 100755
--- a/tools/testing/selftests/vm/run_vmtests
+++ b/tools/testing/selftests/vm/run_vmtests
@@ -112,6 +112,17 @@ echo "NOTE: The above hugetlb tests provide minimal coverage. Use"
echo " https://github.com/libhugetlbfs/libhugetlbfs.git for"
echo " hugetlb regression testing."
+echo "---------------------------"
+echo "running map_fixed_noreplace"
+echo "---------------------------"
+./map_fixed_noreplace
+if [ $? -ne 0 ]; then
+ echo "[FAIL]"
+ exitcode=1
+else
+ echo "[PASS]"
+fi
+
echo "-------------------"
echo "running userfaultfd"
echo "-------------------"
@@ -186,6 +197,17 @@ else
echo "[PASS]"
fi
+echo "-------------------------"
+echo "running mlock-random-test"
+echo "-------------------------"
+./mlock-random-test
+if [ $? -ne 0 ]; then
+ echo "[FAIL]"
+ exitcode=1
+else
+ echo "[PASS]"
+fi
+
echo "--------------------"
echo "running mlock2-tests"
echo "--------------------"
@@ -197,6 +219,17 @@ else
echo "[PASS]"
fi
+echo "-----------------"
+echo "running thuge-gen"
+echo "-----------------"
+./thuge-gen
+if [ $? -ne 0 ]; then
+ echo "[FAIL]"
+ exitcode=1
+else
+ echo "[PASS]"
+fi
+
if [ $VADDR64 -ne 0 ]; then
echo "-----------------------------"
echo "running virtual_address_range"
diff --git a/tools/testing/selftests/wireguard/netns.sh b/tools/testing/selftests/wireguard/netns.sh
index f5ab1cda8bb5..936e1ca9410e 100755
--- a/tools/testing/selftests/wireguard/netns.sh
+++ b/tools/testing/selftests/wireguard/netns.sh
@@ -24,6 +24,7 @@
set -e
exec 3>&1
+export LANG=C
export WG_HIDE_KEYS=never
netns0="wg-test-$$-0"
netns1="wg-test-$$-1"
@@ -297,7 +298,17 @@ ip1 -4 rule add table main suppress_prefixlength 0
n1 ping -W 1 -c 100 -f 192.168.99.7
n1 ping -W 1 -c 100 -f abab::1111
+# Have ns2 NAT into wg0 packets from ns0, but return an icmp error along the right route.
+n2 iptables -t nat -A POSTROUTING -s 10.0.0.0/24 -d 192.168.241.0/24 -j SNAT --to 192.168.241.2
+n0 iptables -t filter -A INPUT \! -s 10.0.0.0/24 -i vethrs -j DROP # Manual rpfilter just to be explicit.
+n2 bash -c 'printf 1 > /proc/sys/net/ipv4/ip_forward'
+ip0 -4 route add 192.168.241.1 via 10.0.0.100
+n2 wg set wg0 peer "$pub1" remove
+[[ $(! n0 ping -W 1 -c 1 192.168.241.1 || false) == *"From 10.0.0.100 icmp_seq=1 Destination Host Unreachable"* ]]
+
n0 iptables -t nat -F
+n0 iptables -t filter -F
+n2 iptables -t nat -F
ip0 link del vethrc
ip0 link del vethrs
ip1 link del wg0
@@ -516,11 +527,16 @@ n0 wg set wg0 peer "$pub2" allowed-ips 0.0.0.0/0
n0 wg set wg0 peer "$pub2" allowed-ips ::/0,1700::/111,5000::/4,e000::/37,9000::/75
n0 wg set wg0 peer "$pub2" allowed-ips ::/0
n0 wg set wg0 peer "$pub2" remove
-low_order_points=( AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA= AQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA= 4Ot6fDtBuK4WVuP68Z/EatoJjeucMrH9hmIFFl9JuAA= X5yVvKNQjCSx0LFVnIPvWwREXMRYHI6G2CJO3dCfEVc= 7P///////////////////////////////////////38= 7f///////////////////////////////////////38= 7v///////////////////////////////////////38= )
-n0 wg set wg0 private-key /dev/null ${low_order_points[@]/#/peer }
-[[ -z $(n0 wg show wg0 peers) ]]
-n0 wg set wg0 private-key <(echo "$key1") ${low_order_points[@]/#/peer }
-[[ -z $(n0 wg show wg0 peers) ]]
+for low_order_point in AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA= AQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA= 4Ot6fDtBuK4WVuP68Z/EatoJjeucMrH9hmIFFl9JuAA= X5yVvKNQjCSx0LFVnIPvWwREXMRYHI6G2CJO3dCfEVc= 7P///////////////////////////////////////38= 7f///////////////////////////////////////38= 7v///////////////////////////////////////38=; do
+ n0 wg set wg0 peer "$low_order_point" persistent-keepalive 1 endpoint 127.0.0.1:1111
+done
+[[ -n $(n0 wg show wg0 peers) ]]
+exec 4< <(n0 ncat -l -u -p 1111)
+ncat_pid=$!
+waitncatudp $netns0 $ncat_pid
+ip0 link set wg0 up
+! read -r -n 1 -t 2 <&4 || false
+kill $ncat_pid
ip0 link del wg0
declare -A objects
diff --git a/tools/testing/selftests/wireguard/qemu/Makefile b/tools/testing/selftests/wireguard/qemu/Makefile
index f10aa3590adc..90598a425c18 100644
--- a/tools/testing/selftests/wireguard/qemu/Makefile
+++ b/tools/testing/selftests/wireguard/qemu/Makefile
@@ -38,19 +38,17 @@ endef
define file_download =
$(DISTFILES_PATH)/$(1):
mkdir -p $(DISTFILES_PATH)
- flock -x $$@.lock -c '[ -f $$@ ] && exit 0; wget -O $$@.tmp $(MIRROR)$(1) || wget -O $$@.tmp $(2)$(1) || rm -f $$@.tmp'
- if echo "$(3) $$@.tmp" | sha256sum -c -; then mv $$@.tmp $$@; else rm -f $$@.tmp; exit 71; fi
+ flock -x $$@.lock -c '[ -f $$@ ] && exit 0; wget -O $$@.tmp $(MIRROR)$(1) || wget -O $$@.tmp $(2)$(1) || rm -f $$@.tmp; [ -f $$@.tmp ] || exit 1; if echo "$(3) $$@.tmp" | sha256sum -c -; then mv $$@.tmp $$@; else rm -f $$@.tmp; exit 71; fi'
endef
-$(eval $(call tar_download,MUSL,musl,1.1.24,.tar.gz,https://www.musl-libc.org/releases/,1370c9a812b2cf2a7d92802510cca0058cc37e66a7bedd70051f0a34015022a3))
-$(eval $(call tar_download,LIBMNL,libmnl,1.0.4,.tar.bz2,https://www.netfilter.org/projects/libmnl/files/,171f89699f286a5854b72b91d06e8f8e3683064c5901fb09d954a9ab6f551f81))
+$(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,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 $(call tar_download,IPUTILS,iputils,s20190709,.tar.gz,https://github.com/iputils/iputils/archive/s20190709.tar.gz/#,a15720dd741d7538dd2645f9f516d193636ae4300ff7dbc8bfca757bf166490a))
-$(eval $(call tar_download,WIREGUARD_TOOLS,wireguard-tools,1.0.20191226,.tar.xz,https://git.zx2c4.com/wireguard-tools/snapshot/,aa8af0fdc9872d369d8c890a84dbc2a2466b55795dccd5b47721b2d97644b04f))
+$(eval $(call tar_download,WIREGUARD_TOOLS,wireguard-tools,1.0.20200206,.tar.xz,https://git.zx2c4.com/wireguard-tools/snapshot/,f5207248c6a3c3e3bfc9ab30b91c1897b00802ed861e1f9faaed873366078c64))
KERNEL_BUILD_PATH := $(BUILD_PATH)/kernel$(if $(findstring yes,$(DEBUG_KERNEL)),-debug)
rwildcard=$(foreach d,$(wildcard $1*),$(call rwildcard,$d/,$2) $(filter $(subst *,%,$2),$d))
@@ -295,21 +293,13 @@ $(IPERF_PATH)/src/iperf3: | $(IPERF_PATH)/.installed $(USERSPACE_DEPS)
$(MAKE) -C $(IPERF_PATH)
$(STRIP) -s $@
-$(LIBMNL_PATH)/.installed: $(LIBMNL_TAR)
- flock -s $<.lock tar -C $(BUILD_PATH) -xf $<
- touch $@
-
-$(LIBMNL_PATH)/src/.libs/libmnl.a: | $(LIBMNL_PATH)/.installed $(USERSPACE_DEPS)
- cd $(LIBMNL_PATH) && ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared
- $(MAKE) -C $(LIBMNL_PATH)
- sed -i 's:prefix=.*:prefix=$(LIBMNL_PATH):' $(LIBMNL_PATH)/libmnl.pc
-
$(WIREGUARD_TOOLS_PATH)/.installed: $(WIREGUARD_TOOLS_TAR)
+ mkdir -p $(BUILD_PATH)
flock -s $<.lock tar -C $(BUILD_PATH) -xf $<
touch $@
-$(WIREGUARD_TOOLS_PATH)/src/wg: | $(WIREGUARD_TOOLS_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS)
- LDFLAGS="$(LDFLAGS) -L$(LIBMNL_PATH)/src/.libs" $(MAKE) -C $(WIREGUARD_TOOLS_PATH)/src LIBMNL_CFLAGS="-I$(LIBMNL_PATH)/include" LIBMNL_LDLIBS="-lmnl" wg
+$(WIREGUARD_TOOLS_PATH)/src/wg: | $(WIREGUARD_TOOLS_PATH)/.installed $(USERSPACE_DEPS)
+ $(MAKE) -C $(WIREGUARD_TOOLS_PATH)/src wg
$(STRIP) -s $@
$(BUILD_PATH)/init: init.c | $(USERSPACE_DEPS)
@@ -340,17 +330,17 @@ $(BASH_PATH)/bash: | $(BASH_PATH)/.installed $(USERSPACE_DEPS)
$(IPROUTE2_PATH)/.installed: $(IPROUTE2_TAR)
mkdir -p $(BUILD_PATH)
flock -s $<.lock tar -C $(BUILD_PATH) -xf $<
- printf 'CC:=$(CC)\nPKG_CONFIG:=pkg-config\nTC_CONFIG_XT:=n\nTC_CONFIG_ATM:=n\nTC_CONFIG_IPSET:=n\nIP_CONFIG_SETNS:=y\nHAVE_ELF:=n\nHAVE_MNL:=y\nHAVE_BERKELEY_DB:=n\nHAVE_LATEX:=n\nHAVE_PDFLATEX:=n\nCFLAGS+=-DHAVE_SETNS -DHAVE_LIBMNL -I$(LIBMNL_PATH)/include\nLDLIBS+=-lmnl' > $(IPROUTE2_PATH)/config.mk
+ printf 'CC:=$(CC)\nPKG_CONFIG:=pkg-config\nTC_CONFIG_XT:=n\nTC_CONFIG_ATM:=n\nTC_CONFIG_IPSET:=n\nIP_CONFIG_SETNS:=y\nHAVE_ELF:=n\nHAVE_MNL:=n\nHAVE_BERKELEY_DB:=n\nHAVE_LATEX:=n\nHAVE_PDFLATEX:=n\nCFLAGS+=-DHAVE_SETNS\n' > $(IPROUTE2_PATH)/config.mk
printf 'lib: snapshot\n\t$$(MAKE) -C lib\nip/ip: lib\n\t$$(MAKE) -C ip ip\nmisc/ss: lib\n\t$$(MAKE) -C misc ss\n' >> $(IPROUTE2_PATH)/Makefile
touch $@
-$(IPROUTE2_PATH)/ip/ip: | $(IPROUTE2_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS)
- LDFLAGS="$(LDFLAGS) -L$(LIBMNL_PATH)/src/.libs" PKG_CONFIG_LIBDIR="$(LIBMNL_PATH)" $(MAKE) -C $(IPROUTE2_PATH) PREFIX=/ ip/ip
- $(STRIP) -s $(IPROUTE2_PATH)/ip/ip
+$(IPROUTE2_PATH)/ip/ip: | $(IPROUTE2_PATH)/.installed $(USERSPACE_DEPS)
+ $(MAKE) -C $(IPROUTE2_PATH) PREFIX=/ ip/ip
+ $(STRIP) -s $@
-$(IPROUTE2_PATH)/misc/ss: | $(IPROUTE2_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS)
- LDFLAGS="$(LDFLAGS) -L$(LIBMNL_PATH)/src/.libs" PKG_CONFIG_LIBDIR="$(LIBMNL_PATH)" $(MAKE) -C $(IPROUTE2_PATH) PREFIX=/ misc/ss
- $(STRIP) -s $(IPROUTE2_PATH)/misc/ss
+$(IPROUTE2_PATH)/misc/ss: | $(IPROUTE2_PATH)/.installed $(USERSPACE_DEPS)
+ $(MAKE) -C $(IPROUTE2_PATH) PREFIX=/ misc/ss
+ $(STRIP) -s $@
$(IPTABLES_PATH)/.installed: $(IPTABLES_TAR)
mkdir -p $(BUILD_PATH)
@@ -358,8 +348,8 @@ $(IPTABLES_PATH)/.installed: $(IPTABLES_TAR)
sed -i -e "/nfnetlink=[01]/s:=[01]:=0:" -e "/nfconntrack=[01]/s:=[01]:=0:" $(IPTABLES_PATH)/configure
touch $@
-$(IPTABLES_PATH)/iptables/xtables-legacy-multi: | $(IPTABLES_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS)
- cd $(IPTABLES_PATH) && PKG_CONFIG_LIBDIR="$(LIBMNL_PATH)" ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared --disable-nftables --disable-bpf-compiler --disable-nfsynproxy --disable-libipq --with-kernel=$(BUILD_PATH)/include
+$(IPTABLES_PATH)/iptables/xtables-legacy-multi: | $(IPTABLES_PATH)/.installed $(USERSPACE_DEPS)
+ cd $(IPTABLES_PATH) && ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared --disable-nftables --disable-bpf-compiler --disable-nfsynproxy --disable-libipq --disable-connlabel --with-kernel=$(BUILD_PATH)/include
$(MAKE) -C $(IPTABLES_PATH)
$(STRIP) -s $@
diff --git a/tools/testing/selftests/wireguard/qemu/init.c b/tools/testing/selftests/wireguard/qemu/init.c
index 90bc9813cadc..c9698120ac9d 100644
--- a/tools/testing/selftests/wireguard/qemu/init.c
+++ b/tools/testing/selftests/wireguard/qemu/init.c
@@ -13,7 +13,6 @@
#include <fcntl.h>
#include <sys/wait.h>
#include <sys/mount.h>
-#include <sys/types.h>
#include <sys/stat.h>
#include <sys/types.h>
#include <sys/io.h>
diff --git a/tools/testing/selftests/wireguard/qemu/kernel.config b/tools/testing/selftests/wireguard/qemu/kernel.config
index af9323a0b6e0..d531de13c95b 100644
--- a/tools/testing/selftests/wireguard/qemu/kernel.config
+++ b/tools/testing/selftests/wireguard/qemu/kernel.config
@@ -56,7 +56,6 @@ CONFIG_NO_HZ_IDLE=y
CONFIG_NO_HZ_FULL=n
CONFIG_HZ_PERIODIC=n
CONFIG_HIGH_RES_TIMERS=y
-CONFIG_COMPAT_32BIT_TIME=y
CONFIG_ARCH_RANDOM=y
CONFIG_FILE_LOCKING=y
CONFIG_POSIX_TIMERS=y
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)
diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c
index 1d8b93f1af31..5a4fb80fa832 100644
--- a/tools/testing/vsock/vsock_test.c
+++ b/tools/testing/vsock/vsock_test.c
@@ -55,6 +55,78 @@ static void test_stream_connection_reset(const struct test_opts *opts)
close(fd);
}
+static void test_stream_bind_only_client(const struct test_opts *opts)
+{
+ union {
+ struct sockaddr sa;
+ struct sockaddr_vm svm;
+ } addr = {
+ .svm = {
+ .svm_family = AF_VSOCK,
+ .svm_port = 1234,
+ .svm_cid = opts->peer_cid,
+ },
+ };
+ int ret;
+ int fd;
+
+ /* Wait for the server to be ready */
+ control_expectln("BIND");
+
+ fd = socket(AF_VSOCK, SOCK_STREAM, 0);
+
+ timeout_begin(TIMEOUT);
+ do {
+ ret = connect(fd, &addr.sa, sizeof(addr.svm));
+ timeout_check("connect");
+ } while (ret < 0 && errno == EINTR);
+ timeout_end();
+
+ if (ret != -1) {
+ fprintf(stderr, "expected connect(2) failure, got %d\n", ret);
+ exit(EXIT_FAILURE);
+ }
+ if (errno != ECONNRESET) {
+ fprintf(stderr, "unexpected connect(2) errno %d\n", errno);
+ exit(EXIT_FAILURE);
+ }
+
+ /* Notify the server that the client has finished */
+ control_writeln("DONE");
+
+ close(fd);
+}
+
+static void test_stream_bind_only_server(const struct test_opts *opts)
+{
+ union {
+ struct sockaddr sa;
+ struct sockaddr_vm svm;
+ } addr = {
+ .svm = {
+ .svm_family = AF_VSOCK,
+ .svm_port = 1234,
+ .svm_cid = VMADDR_CID_ANY,
+ },
+ };
+ int fd;
+
+ fd = socket(AF_VSOCK, SOCK_STREAM, 0);
+
+ if (bind(fd, &addr.sa, sizeof(addr.svm)) < 0) {
+ perror("bind");
+ exit(EXIT_FAILURE);
+ }
+
+ /* Notify the client that the server is ready */
+ control_writeln("BIND");
+
+ /* Wait for the client to finish */
+ control_expectln("DONE");
+
+ close(fd);
+}
+
static void test_stream_client_close_client(const struct test_opts *opts)
{
int fd;
@@ -213,6 +285,11 @@ static struct test_case test_cases[] = {
.run_client = test_stream_connection_reset,
},
{
+ .name = "SOCK_STREAM bind only",
+ .run_client = test_stream_bind_only_client,
+ .run_server = test_stream_bind_only_server,
+ },
+ {
.name = "SOCK_STREAM client close",
.run_client = test_stream_client_close_client,
.run_server = test_stream_client_close_server,