aboutsummaryrefslogtreecommitdiff
path: root/tools
diff options
context:
space:
mode:
Diffstat (limited to 'tools')
-rw-r--r--tools/accounting/getdelays.c8
-rw-r--r--tools/arch/arm64/include/uapi/asm/kvm.h5
-rw-r--r--tools/arch/x86/include/asm/cpufeatures.h5
-rw-r--r--tools/arch/x86/include/asm/insn.h2
-rw-r--r--tools/arch/x86/include/asm/msr-index.h18
-rw-r--r--tools/arch/x86/include/asm/required-features.h4
-rw-r--r--tools/arch/x86/include/uapi/asm/kvm.h19
-rw-r--r--tools/arch/x86/include/uapi/asm/prctl.h26
-rw-r--r--tools/arch/x86/lib/memcpy_64.S22
-rw-r--r--tools/arch/x86/lib/memset_64.S12
-rw-r--r--tools/arch/x86/lib/x86-opcode-map.txt111
-rw-r--r--tools/bpf/bpftool/skeleton/pid_iter.bpf.c4
-rw-r--r--tools/bpf/resolve_btfids/Makefile6
-rw-r--r--tools/bpf/runqslower/runqslower.bpf.c2
-rw-r--r--tools/bpf/runqslower/runqslower.c2
-rw-r--r--tools/bpf/runqslower/runqslower.h2
-rw-r--r--tools/build/Build.include2
-rw-r--r--tools/cgroup/memcg_slabinfo.py30
-rw-r--r--tools/iio/iio_event_monitor.c1
-rw-r--r--tools/include/asm-generic/bitops.h1
-rw-r--r--tools/include/linux/bitmap.h7
-rw-r--r--tools/include/linux/find.h (renamed from tools/include/asm-generic/bitops/find.h)81
-rw-r--r--tools/include/linux/hash.h5
-rw-r--r--tools/include/nolibc/nolibc.h86
-rw-r--r--tools/include/uapi/asm-generic/unistd.h5
-rw-r--r--tools/include/uapi/drm/drm.h18
-rw-r--r--tools/include/uapi/linux/kvm.h18
-rw-r--r--tools/include/uapi/linux/lirc.h229
-rw-r--r--tools/include/uapi/linux/perf_event.h9
-rw-r--r--tools/include/uapi/linux/prctl.h3
-rw-r--r--tools/include/uapi/sound/asound.h11
-rw-r--r--tools/lib/find_bit.c20
-rw-r--r--tools/lib/perf/Documentation/libperf.txt11
-rw-r--r--tools/lib/perf/cpumap.c113
-rw-r--r--tools/lib/perf/evlist.c19
-rw-r--r--tools/lib/perf/evsel.c115
-rw-r--r--tools/lib/perf/include/internal/cpumap.h14
-rw-r--r--tools/lib/perf/include/internal/evlist.h5
-rw-r--r--tools/lib/perf/include/internal/evsel.h4
-rw-r--r--tools/lib/perf/include/internal/mmap.h5
-rw-r--r--tools/lib/perf/include/perf/cpumap.h11
-rw-r--r--tools/lib/perf/include/perf/evsel.h14
-rw-r--r--tools/lib/perf/libperf.map3
-rw-r--r--tools/lib/perf/mmap.c102
-rw-r--r--tools/lib/perf/tests/test-cpumap.c11
-rw-r--r--tools/lib/perf/tests/test-evlist.c163
-rw-r--r--tools/lib/perf/tests/test-evsel.c5
-rw-r--r--tools/lib/subcmd/subcmd-util.h11
-rw-r--r--tools/lib/traceevent/event-parse.c59
-rw-r--r--tools/lib/traceevent/event-parse.h5
-rw-r--r--tools/lib/traceevent/parse-filter.c5
-rw-r--r--tools/memory-model/Documentation/explanation.txt95
-rw-r--r--tools/memory-model/README12
-rw-r--r--tools/memory-model/linux-kernel.cat6
-rw-r--r--tools/memory-model/litmus-tests/LB+unlocklockonceonce+poacquireonce.litmus35
-rw-r--r--tools/memory-model/litmus-tests/MP+unlocklockonceonce+fencermbonceonce.litmus33
-rw-r--r--tools/memory-model/litmus-tests/README8
-rw-r--r--tools/objtool/arch/x86/decode.c24
-rw-r--r--tools/objtool/builtin-check.c3
-rw-r--r--tools/objtool/check.c73
-rw-r--r--tools/objtool/include/objtool/arch.h1
-rw-r--r--tools/objtool/include/objtool/builtin.h2
-rw-r--r--tools/objtool/include/objtool/elf.h2
-rw-r--r--tools/perf/Documentation/perf-buildid-cache.txt5
-rw-r--r--tools/perf/Documentation/perf-config.txt9
-rw-r--r--tools/perf/Documentation/perf-list.txt48
-rw-r--r--tools/perf/Documentation/perf-record.txt15
-rw-r--r--tools/perf/Documentation/perf-stat.txt10
-rw-r--r--tools/perf/Documentation/perf-top.txt7
-rw-r--r--tools/perf/Makefile.config10
-rw-r--r--tools/perf/Makefile.perf4
-rw-r--r--tools/perf/arch/arm/include/perf_regs.h42
-rw-r--r--tools/perf/arch/arm/util/cs-etm.c54
-rw-r--r--tools/perf/arch/arm64/include/perf_regs.h78
-rw-r--r--tools/perf/arch/arm64/util/machine.c7
-rw-r--r--tools/perf/arch/arm64/util/pmu.c2
-rw-r--r--tools/perf/arch/csky/include/perf_regs.h82
-rw-r--r--tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl1
-rw-r--r--tools/perf/arch/mips/include/perf_regs.h69
-rw-r--r--tools/perf/arch/powerpc/entry/syscalls/syscall.tbl1
-rw-r--r--tools/perf/arch/powerpc/include/perf_regs.h66
-rw-r--r--tools/perf/arch/powerpc/util/event.c8
-rw-r--r--tools/perf/arch/riscv/include/perf_regs.h74
-rw-r--r--tools/perf/arch/s390/entry/syscalls/syscall.tbl1
-rw-r--r--tools/perf/arch/s390/include/perf_regs.h78
-rw-r--r--tools/perf/arch/x86/entry/syscalls/syscall_64.tbl1
-rw-r--r--tools/perf/arch/x86/include/perf_regs.h82
-rw-r--r--tools/perf/arch/x86/tests/insn-x86-dat-32.c918
-rw-r--r--tools/perf/arch/x86/tests/insn-x86-dat-64.c1426
-rw-r--r--tools/perf/arch/x86/tests/insn-x86-dat-src.c1189
-rw-r--r--tools/perf/arch/x86/util/evlist.c17
-rw-r--r--tools/perf/bench/epoll-ctl.c6
-rw-r--r--tools/perf/bench/epoll-wait.c4
-rw-r--r--tools/perf/bench/evlist-open-close.c4
-rw-r--r--tools/perf/bench/futex-hash.c4
-rw-r--r--tools/perf/bench/futex-lock-pi.c4
-rw-r--r--tools/perf/bench/futex-requeue.c4
-rw-r--r--tools/perf/bench/futex-wake-parallel.c4
-rw-r--r--tools/perf/bench/futex-wake.c4
-rw-r--r--tools/perf/builtin-bench.c5
-rw-r--r--tools/perf/builtin-buildid-cache.c25
-rw-r--r--tools/perf/builtin-c2c.c15
-rw-r--r--tools/perf/builtin-ftrace.c448
-rw-r--r--tools/perf/builtin-inject.c5
-rw-r--r--tools/perf/builtin-kmem.c2
-rw-r--r--tools/perf/builtin-record.c23
-rw-r--r--tools/perf/builtin-report.c4
-rw-r--r--tools/perf/builtin-sched.c71
-rw-r--r--tools/perf/builtin-script.c45
-rw-r--r--tools/perf/builtin-stat.c557
-rw-r--r--tools/perf/builtin-trace.c28
-rw-r--r--tools/perf/dlfilters/dlfilter-test-api-v0.c2
-rw-r--r--tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/branch.json8
-rw-r--r--tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/bus.json20
-rw-r--r--tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/cache.json155
-rw-r--r--tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/exception.json47
-rw-r--r--tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/instruction.json143
-rw-r--r--tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/memory.json38
-rw-r--r--tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/other.json5
-rw-r--r--tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/pipeline.json23
-rw-r--r--tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/spe.json14
-rw-r--r--tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/trace.json29
-rw-r--r--tools/perf/pmu-events/arch/arm64/common-and-microarch.json (renamed from tools/perf/pmu-events/arch/arm64/armv8-common-and-microarch.json)198
-rw-r--r--tools/perf/pmu-events/arch/arm64/mapfile.csv1
-rw-r--r--tools/perf/pmu-events/arch/arm64/recommended.json (renamed from tools/perf/pmu-events/arch/arm64/armv8-recommended.json)202
-rw-r--r--tools/perf/pmu-events/arch/test/test_soc/cpu/uncore.json16
-rw-r--r--tools/perf/pmu-events/jevents.c2
-rw-r--r--tools/perf/tests/Build1
-rw-r--r--tools/perf/tests/attr.c6
-rw-r--r--tools/perf/tests/attr/README2
-rw-r--r--tools/perf/tests/attr/test-record-graph-default2
-rw-r--r--tools/perf/tests/attr/test-record-graph-default-aarch649
-rw-r--r--tools/perf/tests/attr/test-record-graph-fp2
-rw-r--r--tools/perf/tests/attr/test-record-graph-fp-aarch649
-rw-r--r--tools/perf/tests/bitmap.c4
-rw-r--r--tools/perf/tests/builtin-test.c16
-rw-r--r--tools/perf/tests/cpumap.c6
-rw-r--r--tools/perf/tests/event_update.c8
-rw-r--r--tools/perf/tests/mem2node.c9
-rw-r--r--tools/perf/tests/mmap-basic.c5
-rw-r--r--tools/perf/tests/openat-syscall-all-cpus.c39
-rw-r--r--tools/perf/tests/parse-events.c49
-rw-r--r--tools/perf/tests/pmu-events.c32
-rwxr-xr-xtools/perf/tests/shell/stat_all_metricgroups.sh2
-rw-r--r--tools/perf/tests/sigtrap.c164
-rw-r--r--tools/perf/tests/stat.c3
-rw-r--r--tools/perf/tests/tests.h1
-rw-r--r--tools/perf/tests/topology.c58
-rwxr-xr-xtools/perf/trace/beauty/prctl_option.sh2
-rw-r--r--tools/perf/ui/browsers/annotate.c23
-rw-r--r--tools/perf/util/Build2
-rw-r--r--tools/perf/util/affinity.c10
-rw-r--r--tools/perf/util/annotate.c1
-rw-r--r--tools/perf/util/arm-spe-decoder/arm-spe-decoder.c2
-rw-r--r--tools/perf/util/arm-spe-decoder/arm-spe-decoder.h1
-rw-r--r--tools/perf/util/arm-spe.c67
-rw-r--r--tools/perf/util/arm64-frame-pointer-unwind-support.c63
-rw-r--r--tools/perf/util/arm64-frame-pointer-unwind-support.h10
-rw-r--r--tools/perf/util/auxtrace.c14
-rw-r--r--tools/perf/util/auxtrace.h5
-rw-r--r--tools/perf/util/bpf-loader.c18
-rw-r--r--tools/perf/util/bpf_counter.c29
-rw-r--r--tools/perf/util/bpf_counter.h4
-rw-r--r--tools/perf/util/bpf_counter_cgroup.c12
-rw-r--r--tools/perf/util/bpf_ftrace.c152
-rw-r--r--tools/perf/util/bpf_skel/func_latency.bpf.c114
-rw-r--r--tools/perf/util/branch.c4
-rw-r--r--tools/perf/util/callchain.c14
-rw-r--r--tools/perf/util/callchain.h4
-rw-r--r--tools/perf/util/counts.c8
-rw-r--r--tools/perf/util/counts.h14
-rw-r--r--tools/perf/util/cpumap.c253
-rw-r--r--tools/perf/util/cpumap.h125
-rw-r--r--tools/perf/util/cputopo.c11
-rw-r--r--tools/perf/util/cs-etm.c16
-rw-r--r--tools/perf/util/data-convert-bt.c2
-rw-r--r--tools/perf/util/data.c7
-rw-r--r--tools/perf/util/debug.c2
-rw-r--r--tools/perf/util/env.c29
-rw-r--r--tools/perf/util/env.h3
-rw-r--r--tools/perf/util/evlist-hybrid.c15
-rw-r--r--tools/perf/util/evlist.c180
-rw-r--r--tools/perf/util/evlist.h52
-rw-r--r--tools/perf/util/evsel.c205
-rw-r--r--tools/perf/util/evsel.h33
-rw-r--r--tools/perf/util/expr.c37
-rw-r--r--tools/perf/util/ftrace.h81
-rw-r--r--tools/perf/util/header.c6
-rw-r--r--tools/perf/util/hist.c4
-rw-r--r--tools/perf/util/hist.h3
-rw-r--r--tools/perf/util/include/linux/linkage.h52
-rw-r--r--tools/perf/util/libunwind/arm64.c2
-rw-r--r--tools/perf/util/machine.c55
-rw-r--r--tools/perf/util/machine.h1
-rw-r--r--tools/perf/util/map_symbol.h1
-rw-r--r--tools/perf/util/mem-events.c29
-rw-r--r--tools/perf/util/metricgroup.c46
-rw-r--r--tools/perf/util/mmap.c19
-rw-r--r--tools/perf/util/mmap.h3
-rw-r--r--tools/perf/util/namespaces.c76
-rw-r--r--tools/perf/util/namespaces.h2
-rw-r--r--tools/perf/util/parse-events-hybrid.c9
-rw-r--r--tools/perf/util/parse-events.c83
-rw-r--r--tools/perf/util/parse-events.h1
-rw-r--r--tools/perf/util/parse-events.l2
-rw-r--r--tools/perf/util/parse-events.y17
-rw-r--r--tools/perf/util/perf_api_probe.c19
-rw-r--r--tools/perf/util/perf_event_attr_fprintf.c2
-rw-r--r--tools/perf/util/perf_regs.c666
-rw-r--r--tools/perf/util/perf_regs.h17
-rw-r--r--tools/perf/util/probe-event.c3
-rw-r--r--tools/perf/util/python.c12
-rw-r--r--tools/perf/util/record.c13
-rw-r--r--tools/perf/util/scripting-engines/trace-event-perl.c2
-rw-r--r--tools/perf/util/scripting-engines/trace-event-python.c22
-rw-r--r--tools/perf/util/session.c38
-rw-r--r--tools/perf/util/smt.c73
-rw-r--r--tools/perf/util/sort.c40
-rw-r--r--tools/perf/util/sort.h3
-rw-r--r--tools/perf/util/stat-display.c157
-rw-r--r--tools/perf/util/stat-shadow.c308
-rw-r--r--tools/perf/util/stat.c47
-rw-r--r--tools/perf/util/stat.h9
-rw-r--r--tools/perf/util/svghelper.c10
-rw-r--r--tools/perf/util/symbol.c2
-rw-r--r--tools/perf/util/synthetic-events.c43
-rw-r--r--tools/perf/util/synthetic-events.h3
-rw-r--r--tools/perf/util/top.c6
-rw-r--r--tools/perf/util/util.c15
-rw-r--r--tools/perf/util/util.h11
-rw-r--r--tools/power/acpi/.gitignore1
-rw-r--r--tools/power/acpi/Makefile16
-rw-r--r--tools/power/acpi/Makefile.rules2
-rw-r--r--tools/power/acpi/man/pfrut.8137
-rw-r--r--tools/power/acpi/tools/pfrut/Makefile23
-rw-r--r--tools/power/acpi/tools/pfrut/pfrut.c424
-rw-r--r--tools/power/cpupower/Makefile6
-rw-r--r--tools/power/cpupower/TODO (renamed from tools/power/cpupower/ToDo)0
-rw-r--r--tools/power/cpupower/lib/acpi_cppc.c59
-rw-r--r--tools/power/cpupower/lib/acpi_cppc.h21
-rw-r--r--tools/power/cpupower/lib/cpufreq.c23
-rw-r--r--tools/power/cpupower/lib/cpufreq.h12
-rw-r--r--tools/power/cpupower/man/cpupower-frequency-info.13
-rw-r--r--tools/power/cpupower/man/cpupower-idle-set.12
-rw-r--r--tools/power/cpupower/utils/cpufreq-info.c87
-rw-r--r--tools/power/cpupower/utils/helpers/amd.c77
-rw-r--r--tools/power/cpupower/utils/helpers/cpuid.c13
-rw-r--r--tools/power/cpupower/utils/helpers/helpers.h22
-rw-r--r--tools/power/cpupower/utils/helpers/misc.c60
-rwxr-xr-xtools/power/x86/amd_pstate_tracer/amd_pstate_trace.py354
-rw-r--r--tools/power/x86/intel-speed-select/Build2
-rw-r--r--tools/power/x86/intel-speed-select/Makefile10
-rw-r--r--tools/power/x86/intel-speed-select/hfi-events.c309
-rw-r--r--tools/power/x86/intel-speed-select/isst-config.c56
-rw-r--r--tools/power/x86/intel-speed-select/isst-daemon.c244
-rw-r--r--tools/power/x86/intel-speed-select/isst.h13
-rwxr-xr-xtools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py260
-rw-r--r--tools/power/x86/turbostat/turbostat.c2
-rw-r--r--tools/scripts/Makefile.include2
-rw-r--r--tools/testing/cxl/Kbuild3
-rw-r--r--tools/testing/cxl/test/cxl.c68
-rw-r--r--tools/testing/cxl/test/mem.c99
-rw-r--r--tools/testing/cxl/test/mock.c30
-rw-r--r--tools/testing/cxl/test/mock.h6
-rw-r--r--tools/testing/kunit/kunit_kernel.py1
-rwxr-xr-xtools/testing/kunit/run_checks.py2
-rw-r--r--tools/testing/nvdimm/Kbuild8
-rw-r--r--tools/testing/nvdimm/dax_pmem_compat_test.c8
-rw-r--r--tools/testing/nvdimm/dax_pmem_core_test.c8
-rw-r--r--tools/testing/nvdimm/test/iomap.c43
-rw-r--r--tools/testing/nvdimm/test/ndtest.c4
-rw-r--r--tools/testing/nvdimm/test/nfit.c4
-rw-r--r--tools/testing/scatterlist/linux/mm.h3
-rw-r--r--tools/testing/selftests/Makefile3
-rw-r--r--tools/testing/selftests/alsa/.gitignore1
-rw-r--r--tools/testing/selftests/alsa/Makefile9
-rw-r--r--tools/testing/selftests/alsa/mixer-test.c705
-rw-r--r--tools/testing/selftests/arm64/abi/syscall-abi.c1
-rw-r--r--tools/testing/selftests/arm64/fp/sve-ptrace.c15
-rw-r--r--tools/testing/selftests/arm64/mte/check_gcr_el1_cswitch.c11
-rw-r--r--tools/testing/selftests/arm64/mte/check_user_mem.c193
-rw-r--r--tools/testing/selftests/arm64/signal/test_signals.h1
-rw-r--r--tools/testing/selftests/arm64/signal/test_signals_utils.c34
-rw-r--r--tools/testing/selftests/arm64/signal/test_signals_utils.h2
-rw-r--r--tools/testing/selftests/bpf/prog_tests/d_path.c14
-rw-r--r--tools/testing/selftests/bpf/prog_tests/timer_crash.c32
-rw-r--r--tools/testing/selftests/bpf/prog_tests/xdp_link.c61
-rw-r--r--tools/testing/selftests/bpf/progs/test_d_path_check_types.c32
-rw-r--r--tools/testing/selftests/bpf/progs/test_sockmap_kern.h26
-rw-r--r--tools/testing/selftests/bpf/progs/test_stacktrace_map.c6
-rw-r--r--tools/testing/selftests/bpf/progs/test_tracepoint.c6
-rw-r--r--tools/testing/selftests/bpf/progs/test_xdp_link.c6
-rw-r--r--tools/testing/selftests/bpf/progs/timer_crash.c54
-rw-r--r--tools/testing/selftests/bpf/test_lirc_mode2_user.c1
-rw-r--r--tools/testing/selftests/bpf/verifier/ringbuf.c95
-rw-r--r--tools/testing/selftests/bpf/verifier/spill_fill.c2
-rw-r--r--tools/testing/selftests/cgroup/cgroup_util.c15
-rw-r--r--tools/testing/selftests/cgroup/cgroup_util.h1
-rw-r--r--tools/testing/selftests/cgroup/test_memcontrol.c78
-rw-r--r--tools/testing/selftests/clone3/clone3.c2
-rwxr-xr-xtools/testing/selftests/cpufreq/main.sh2
-rw-r--r--tools/testing/selftests/damon/Makefile1
-rw-r--r--tools/testing/selftests/damon/sysfs.sh306
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh2
-rw-r--r--tools/testing/selftests/drivers/net/mlxsw/tc_police_scale.sh3
-rw-r--r--tools/testing/selftests/exec/Makefile7
-rw-r--r--tools/testing/selftests/exec/null-argv.c78
-rw-r--r--tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc2
-rw-r--r--tools/testing/selftests/futex/Makefile4
-rw-r--r--tools/testing/selftests/gpio/.gitignore2
-rw-r--r--tools/testing/selftests/gpio/Makefile4
-rw-r--r--tools/testing/selftests/gpio/config1
-rw-r--r--tools/testing/selftests/gpio/gpio-chip-info.c57
-rw-r--r--tools/testing/selftests/gpio/gpio-line-name.c55
-rwxr-xr-xtools/testing/selftests/gpio/gpio-sim.sh396
-rw-r--r--tools/testing/selftests/ir/ir_loopback.c10
-rw-r--r--tools/testing/selftests/kexec/Makefile2
-rwxr-xr-xtools/testing/selftests/kexec/kexec_common_lib.sh51
-rwxr-xr-xtools/testing/selftests/kexec/test_kexec_file_load.sh13
-rw-r--r--tools/testing/selftests/kselftest_harness.h4
-rw-r--r--tools/testing/selftests/kvm/.gitignore6
-rw-r--r--tools/testing/selftests/kvm/Makefile24
-rw-r--r--tools/testing/selftests/kvm/aarch64/arch_timer.c7
-rw-r--r--tools/testing/selftests/kvm/aarch64/get-reg-list.c50
-rw-r--r--tools/testing/selftests/kvm/aarch64/vgic_irq.c857
-rw-r--r--tools/testing/selftests/kvm/include/aarch64/gic.h26
-rw-r--r--tools/testing/selftests/kvm/include/aarch64/gic_v3.h (renamed from tools/testing/selftests/kvm/lib/aarch64/gic_v3.h)12
-rw-r--r--tools/testing/selftests/kvm/include/aarch64/processor.h3
-rw-r--r--tools/testing/selftests/kvm/include/aarch64/vgic.h18
-rw-r--r--tools/testing/selftests/kvm/include/kvm_util.h409
-rw-r--r--tools/testing/selftests/kvm/include/kvm_util_base.h398
-rw-r--r--tools/testing/selftests/kvm/include/riscv/processor.h135
-rw-r--r--tools/testing/selftests/kvm/include/ucall_common.h59
-rw-r--r--tools/testing/selftests/kvm/include/x86_64/processor.h52
-rw-r--r--tools/testing/selftests/kvm/lib/aarch64/gic.c66
-rw-r--r--tools/testing/selftests/kvm/lib/aarch64/gic_private.h11
-rw-r--r--tools/testing/selftests/kvm/lib/aarch64/gic_v3.c206
-rw-r--r--tools/testing/selftests/kvm/lib/aarch64/processor.c82
-rw-r--r--tools/testing/selftests/kvm/lib/aarch64/vgic.c107
-rw-r--r--tools/testing/selftests/kvm/lib/guest_modes.c59
-rw-r--r--tools/testing/selftests/kvm/lib/kvm_util.c129
-rw-r--r--tools/testing/selftests/kvm/lib/riscv/processor.c362
-rw-r--r--tools/testing/selftests/kvm/lib/riscv/ucall.c87
-rw-r--r--tools/testing/selftests/kvm/lib/x86_64/processor.c244
-rw-r--r--tools/testing/selftests/kvm/x86_64/amx_test.c450
-rw-r--r--tools/testing/selftests/kvm/x86_64/cpuid_test.c (renamed from tools/testing/selftests/kvm/x86_64/get_cpuid_test.c)30
-rw-r--r--tools/testing/selftests/kvm/x86_64/evmcs_test.c2
-rw-r--r--tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c434
-rw-r--r--tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c59
-rw-r--r--tools/testing/selftests/kvm/x86_64/smm_test.c3
-rw-r--r--tools/testing/selftests/kvm/x86_64/state_test.c2
-rw-r--r--tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c4
-rw-r--r--tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c4
-rw-r--r--tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c139
-rw-r--r--tools/testing/selftests/kvm/x86_64/vmx_preemption_timer_test.c2
-rw-r--r--tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c218
-rwxr-xr-xtools/testing/selftests/lkdtm/stack-entropy.sh16
-rw-r--r--tools/testing/selftests/memfd/memfd_test.c1
-rw-r--r--tools/testing/selftests/mincore/mincore_selftest.c20
-rw-r--r--tools/testing/selftests/mount_setattr/mount_setattr_test.c4
-rwxr-xr-xtools/testing/selftests/net/fcnal-test.sh3
-rw-r--r--tools/testing/selftests/net/ioam6_parser.c5
-rwxr-xr-xtools/testing/selftests/net/mptcp/diag.sh44
-rwxr-xr-xtools/testing/selftests/net/mptcp/mptcp_connect.sh4
-rwxr-xr-xtools/testing/selftests/net/mptcp/mptcp_join.sh38
-rwxr-xr-xtools/testing/selftests/net/pmtu.sh21
-rw-r--r--tools/testing/selftests/net/settings2
-rw-r--r--tools/testing/selftests/netfilter/.gitignore1
-rw-r--r--tools/testing/selftests/netfilter/Makefile4
-rw-r--r--tools/testing/selftests/netfilter/connect_close.c136
-rwxr-xr-xtools/testing/selftests/netfilter/nft_concat_range.sh74
-rwxr-xr-xtools/testing/selftests/netfilter/nft_fib.sh1
-rwxr-xr-xtools/testing/selftests/netfilter/nft_nat.sh157
-rwxr-xr-xtools/testing/selftests/netfilter/nft_queue.sh19
-rwxr-xr-xtools/testing/selftests/netfilter/nft_synproxy.sh117
-rwxr-xr-xtools/testing/selftests/netfilter/nft_zones_many.sh12
-rw-r--r--tools/testing/selftests/openat2/Makefile2
-rw-r--r--tools/testing/selftests/openat2/helpers.h12
-rw-r--r--tools/testing/selftests/openat2/openat2_test.c12
-rw-r--r--tools/testing/selftests/perf_events/sigtrap_threads.c17
-rw-r--r--tools/testing/selftests/pidfd/pidfd.h13
-rw-r--r--tools/testing/selftests/pidfd/pidfd_fdinfo_test.c22
-rw-r--r--tools/testing/selftests/pidfd/pidfd_test.c6
-rw-r--r--tools/testing/selftests/pidfd/pidfd_wait.c5
-rwxr-xr-xtools/testing/selftests/powerpc/security/mitigation-patching.sh5
-rw-r--r--tools/testing/selftests/powerpc/security/spectre_v2.c2
-rw-r--r--tools/testing/selftests/powerpc/signal/.gitignore2
-rw-r--r--tools/testing/selftests/powerpc/signal/Makefile2
-rw-r--r--tools/testing/selftests/powerpc/signal/sigreturn_kernel.c132
-rw-r--r--tools/testing/selftests/powerpc/signal/sigreturn_unaligned.c43
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/console-badness.sh2
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm-again.sh4
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm-check-branches.sh4
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm-end-run-stats.sh4
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm-find-errors.sh10
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh2
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm-remote.sh42
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm.sh25
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/parse-build.sh3
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/parse-console.sh10
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/torture.sh38
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/RUDE012
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/SRCU-N.boot1
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/SRCU-P.boot2
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/SRCU-T1
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/SRCU-U1
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/TASKS01.boot1
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/TINY011
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/TINY021
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/TRACE012
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/TRACE01.boot1
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/TRACE02.boot1
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/TREE011
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/TREE021
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/TREE02.boot1
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/TREE041
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/TREE051
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/TREE061
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/TREE071
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/TREE081
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/TREE101
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/TREE10.boot1
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcuscale/TINY2
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcuscale/TRACE011
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcuscale/TREE1
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcuscale/TREE541
-rw-r--r--tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT1
-rw-r--r--tools/testing/selftests/rcutorture/configs/refscale/PREEMPT1
-rw-r--r--tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt1
-rw-r--r--tools/testing/selftests/rseq/Makefile2
-rw-r--r--tools/testing/selftests/rseq/basic_percpu_ops_test.c2
-rw-r--r--tools/testing/selftests/rseq/compiler.h30
-rw-r--r--tools/testing/selftests/rseq/param_test.c8
-rw-r--r--tools/testing/selftests/rseq/rseq-abi.h151
-rw-r--r--tools/testing/selftests/rseq/rseq-arm.h110
-rw-r--r--tools/testing/selftests/rseq/rseq-arm64.h79
-rw-r--r--tools/testing/selftests/rseq/rseq-generic-thread-pointer.h25
-rw-r--r--tools/testing/selftests/rseq/rseq-mips.h71
-rw-r--r--tools/testing/selftests/rseq/rseq-ppc-thread-pointer.h30
-rw-r--r--tools/testing/selftests/rseq/rseq-ppc.h128
-rw-r--r--tools/testing/selftests/rseq/rseq-s390.h55
-rw-r--r--tools/testing/selftests/rseq/rseq-skip.h2
-rw-r--r--tools/testing/selftests/rseq/rseq-thread-pointer.h19
-rw-r--r--tools/testing/selftests/rseq/rseq-x86-thread-pointer.h40
-rw-r--r--tools/testing/selftests/rseq/rseq-x86.h200
-rw-r--r--tools/testing/selftests/rseq/rseq.c164
-rw-r--r--tools/testing/selftests/rseq/rseq.h30
-rw-r--r--tools/testing/selftests/rtc/settings2
-rw-r--r--tools/testing/selftests/seccomp/Makefile2
-rw-r--r--tools/testing/selftests/sgx/Makefile2
-rw-r--r--tools/testing/selftests/sgx/load.c9
-rw-r--r--tools/testing/selftests/sgx/main.c9
-rw-r--r--tools/testing/selftests/tpm2/tpm2.py31
-rw-r--r--tools/testing/selftests/tpm2/tpm2_tests.py45
-rw-r--r--tools/testing/selftests/vDSO/vdso_test_abi.c135
-rw-r--r--tools/testing/selftests/vm/.gitignore1
-rw-r--r--tools/testing/selftests/vm/Makefile13
-rw-r--r--tools/testing/selftests/vm/charge_reserved_hugetlb.sh34
-rw-r--r--tools/testing/selftests/vm/hmm-tests.c42
-rw-r--r--tools/testing/selftests/vm/hugepage-mremap.c60
-rw-r--r--tools/testing/selftests/vm/hugepage-vmemmap.c144
-rw-r--r--tools/testing/selftests/vm/hugetlb_reparenting_test.sh21
-rw-r--r--tools/testing/selftests/vm/map_fixed_noreplace.c49
-rwxr-xr-xtools/testing/selftests/vm/run_vmtests.sh14
-rw-r--r--tools/testing/selftests/vm/transhuge-stress.c35
-rw-r--r--tools/testing/selftests/vm/userfaultfd.c25
-rw-r--r--tools/testing/selftests/vm/write_hugetlb_memory.sh2
-rw-r--r--tools/testing/selftests/x86/Makefile6
-rwxr-xr-xtools/testing/selftests/x86/check_cc.sh2
-rwxr-xr-xtools/testing/selftests/zram/zram.sh15
-rwxr-xr-xtools/testing/selftests/zram/zram01.sh33
-rwxr-xr-xtools/testing/selftests/zram/zram02.sh1
-rwxr-xr-xtools/testing/selftests/zram/zram_lib.sh134
-rw-r--r--tools/tracing/Makefile18
-rw-r--r--tools/tracing/rtla/Makefile104
-rw-r--r--tools/tracing/rtla/README.txt36
-rw-r--r--tools/tracing/rtla/src/osnoise.c878
-rw-r--r--tools/tracing/rtla/src/osnoise.h91
-rw-r--r--tools/tracing/rtla/src/osnoise_hist.c800
-rw-r--r--tools/tracing/rtla/src/osnoise_top.c579
-rw-r--r--tools/tracing/rtla/src/rtla.c87
-rw-r--r--tools/tracing/rtla/src/timerlat.c72
-rw-r--r--tools/tracing/rtla/src/timerlat.h4
-rw-r--r--tools/tracing/rtla/src/timerlat_hist.c821
-rw-r--r--tools/tracing/rtla/src/timerlat_top.c617
-rw-r--r--tools/tracing/rtla/src/trace.c192
-rw-r--r--tools/tracing/rtla/src/trace.h27
-rw-r--r--tools/tracing/rtla/src/utils.c433
-rw-r--r--tools/tracing/rtla/src/utils.h56
-rw-r--r--tools/virtio/linux/mm_types.h3
-rw-r--r--tools/virtio/virtio_test.c1
491 files changed, 25263 insertions, 4582 deletions
diff --git a/tools/accounting/getdelays.c b/tools/accounting/getdelays.c
index 5ef1c15e88ad..11e86739456d 100644
--- a/tools/accounting/getdelays.c
+++ b/tools/accounting/getdelays.c
@@ -205,6 +205,8 @@ static void print_delayacct(struct taskstats *t)
"RECLAIM %12s%15s%15s\n"
" %15llu%15llu%15llums\n"
"THRASHING%12s%15s%15s\n"
+ " %15llu%15llu%15llums\n"
+ "COMPACT %12s%15s%15s\n"
" %15llu%15llu%15llums\n",
"count", "real total", "virtual total",
"delay total", "delay average",
@@ -228,7 +230,11 @@ static void print_delayacct(struct taskstats *t)
"count", "delay total", "delay average",
(unsigned long long)t->thrashing_count,
(unsigned long long)t->thrashing_delay_total,
- average_ms(t->thrashing_delay_total, t->thrashing_count));
+ average_ms(t->thrashing_delay_total, t->thrashing_count),
+ "count", "delay total", "delay average",
+ (unsigned long long)t->compact_count,
+ (unsigned long long)t->compact_delay_total,
+ average_ms(t->compact_delay_total, t->compact_count));
}
static void task_context_switch_counts(struct taskstats *t)
diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h
index b3edde68bc3e..323e251ed37b 100644
--- a/tools/arch/arm64/include/uapi/asm/kvm.h
+++ b/tools/arch/arm64/include/uapi/asm/kvm.h
@@ -281,6 +281,11 @@ struct kvm_arm_copy_mte_tags {
#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED 3
#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED (1U << 4)
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3 KVM_REG_ARM_FW_REG(3)
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_AVAIL 0
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_AVAIL 1
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_REQUIRED 2
+
/* SVE registers */
#define KVM_REG_ARM64_SVE (0x15 << KVM_REG_ARM_COPROC_SHIFT)
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index d5b5f2ab87a0..65d147974f8d 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -204,7 +204,7 @@
/* FREE! ( 7*32+10) */
#define X86_FEATURE_PTI ( 7*32+11) /* Kernel Page Table Isolation enabled */
#define X86_FEATURE_RETPOLINE ( 7*32+12) /* "" Generic Retpoline mitigation for Spectre variant 2 */
-#define X86_FEATURE_RETPOLINE_AMD ( 7*32+13) /* "" AMD Retpoline mitigation for Spectre variant 2 */
+#define X86_FEATURE_RETPOLINE_LFENCE ( 7*32+13) /* "" Use LFENCE for Spectre variant 2 */
#define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */
#define X86_FEATURE_CDP_L2 ( 7*32+15) /* Code and Data Prioritization L2 */
#define X86_FEATURE_MSR_SPEC_CTRL ( 7*32+16) /* "" MSR SPEC_CTRL is implemented */
@@ -299,7 +299,9 @@
/* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
#define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI instructions */
#define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */
+#define X86_FEATURE_AMX_BF16 (18*32+22) /* AMX bf16 Support */
#define X86_FEATURE_AMX_TILE (18*32+24) /* AMX tile Support */
+#define X86_FEATURE_AMX_INT8 (18*32+25) /* AMX int8 Support */
/* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */
#define X86_FEATURE_CLZERO (13*32+ 0) /* CLZERO instruction */
@@ -315,6 +317,7 @@
#define X86_FEATURE_AMD_SSBD (13*32+24) /* "" Speculative Store Bypass Disable */
#define X86_FEATURE_VIRT_SSBD (13*32+25) /* Virtualized Speculative Store Bypass Disable */
#define X86_FEATURE_AMD_SSB_NO (13*32+26) /* "" Speculative Store Bypass is fixed in hardware. */
+#define X86_FEATURE_CPPC (13*32+27) /* Collaborative Processor Performance Control */
/* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */
#define X86_FEATURE_DTHERM (14*32+ 0) /* Digital Thermal Sensor */
diff --git a/tools/arch/x86/include/asm/insn.h b/tools/arch/x86/include/asm/insn.h
index dc632b41f135..65c0d9ce1e29 100644
--- a/tools/arch/x86/include/asm/insn.h
+++ b/tools/arch/x86/include/asm/insn.h
@@ -124,7 +124,7 @@ struct insn {
#define X86_VEX_B(vex) ((vex) & 0x20) /* VEX3 Byte1 */
#define X86_VEX_L(vex) ((vex) & 0x04) /* VEX3 Byte2, VEX2 Byte1 */
/* VEX bit fields */
-#define X86_EVEX_M(vex) ((vex) & 0x03) /* EVEX Byte1 */
+#define X86_EVEX_M(vex) ((vex) & 0x07) /* EVEX Byte1 */
#define X86_VEX3_M(vex) ((vex) & 0x1f) /* VEX3 Byte1 */
#define X86_VEX2_M 1 /* VEX2.M always 1 */
#define X86_VEX_V(vex) (((vex) & 0x78) >> 3) /* VEX3 Byte2, VEX2 Byte1 */
diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index 01e2650b9585..a4a39c3e0f19 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -476,6 +476,7 @@
#define MSR_AMD64_ICIBSEXTDCTL 0xc001103c
#define MSR_AMD64_IBSOPDATA4 0xc001103d
#define MSR_AMD64_IBS_REG_COUNT_MAX 8 /* includes MSR_AMD64_IBSBRTARGET */
+#define MSR_AMD64_SVM_AVIC_DOORBELL 0xc001011b
#define MSR_AMD64_VM_PAGE_FLUSH 0xc001011e
#define MSR_AMD64_SEV_ES_GHCB 0xc0010130
#define MSR_AMD64_SEV 0xc0010131
@@ -486,6 +487,23 @@
#define MSR_AMD64_VIRT_SPEC_CTRL 0xc001011f
+/* AMD Collaborative Processor Performance Control MSRs */
+#define MSR_AMD_CPPC_CAP1 0xc00102b0
+#define MSR_AMD_CPPC_ENABLE 0xc00102b1
+#define MSR_AMD_CPPC_CAP2 0xc00102b2
+#define MSR_AMD_CPPC_REQ 0xc00102b3
+#define MSR_AMD_CPPC_STATUS 0xc00102b4
+
+#define AMD_CPPC_LOWEST_PERF(x) (((x) >> 0) & 0xff)
+#define AMD_CPPC_LOWNONLIN_PERF(x) (((x) >> 8) & 0xff)
+#define AMD_CPPC_NOMINAL_PERF(x) (((x) >> 16) & 0xff)
+#define AMD_CPPC_HIGHEST_PERF(x) (((x) >> 24) & 0xff)
+
+#define AMD_CPPC_MAX_PERF(x) (((x) & 0xff) << 0)
+#define AMD_CPPC_MIN_PERF(x) (((x) & 0xff) << 8)
+#define AMD_CPPC_DES_PERF(x) (((x) & 0xff) << 16)
+#define AMD_CPPC_ENERGY_PERF_PREF(x) (((x) & 0xff) << 24)
+
/* Fam 17h MSRs */
#define MSR_F17H_IRPERF 0xc00000e9
diff --git a/tools/arch/x86/include/asm/required-features.h b/tools/arch/x86/include/asm/required-features.h
index b2d504f11937..aff774775c67 100644
--- a/tools/arch/x86/include/asm/required-features.h
+++ b/tools/arch/x86/include/asm/required-features.h
@@ -35,11 +35,7 @@
# define NEED_CMOV 0
#endif
-#ifdef CONFIG_X86_USE_3DNOW
-# define NEED_3DNOW (1<<(X86_FEATURE_3DNOW & 31))
-#else
# define NEED_3DNOW 0
-#endif
#if defined(CONFIG_X86_P6_NOP) || defined(CONFIG_X86_64)
# define NEED_NOPL (1<<(X86_FEATURE_NOPL & 31))
diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index 5a776a08f78c..bf6e96011dfe 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -373,9 +373,23 @@ struct kvm_debugregs {
__u64 reserved[9];
};
-/* for KVM_CAP_XSAVE */
+/* for KVM_CAP_XSAVE and KVM_CAP_XSAVE2 */
struct kvm_xsave {
+ /*
+ * KVM_GET_XSAVE2 and KVM_SET_XSAVE write and read as many bytes
+ * as are returned by KVM_CHECK_EXTENSION(KVM_CAP_XSAVE2)
+ * respectively, when invoked on the vm file descriptor.
+ *
+ * The size value returned by KVM_CHECK_EXTENSION(KVM_CAP_XSAVE2)
+ * will always be at least 4096. Currently, it is only greater
+ * than 4096 if a dynamic feature has been enabled with
+ * ``arch_prctl()``, but this may change in the future.
+ *
+ * The offsets of the state save areas in struct kvm_xsave follow
+ * the contents of CPUID leaf 0xD on the host.
+ */
__u32 region[1024];
+ __u32 extra[0];
};
#define KVM_MAX_XCRS 16
@@ -438,6 +452,9 @@ struct kvm_sync_regs {
#define KVM_STATE_VMX_PREEMPTION_TIMER_DEADLINE 0x00000001
+/* attributes for system fd (group 0) */
+#define KVM_X86_XCOMP_GUEST_SUPP 0
+
struct kvm_vmx_nested_state_data {
__u8 vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE];
__u8 shadow_vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE];
diff --git a/tools/arch/x86/include/uapi/asm/prctl.h b/tools/arch/x86/include/uapi/asm/prctl.h
index 754a07856817..500b96e71f18 100644
--- a/tools/arch/x86/include/uapi/asm/prctl.h
+++ b/tools/arch/x86/include/uapi/asm/prctl.h
@@ -2,20 +2,22 @@
#ifndef _ASM_X86_PRCTL_H
#define _ASM_X86_PRCTL_H
-#define ARCH_SET_GS 0x1001
-#define ARCH_SET_FS 0x1002
-#define ARCH_GET_FS 0x1003
-#define ARCH_GET_GS 0x1004
+#define ARCH_SET_GS 0x1001
+#define ARCH_SET_FS 0x1002
+#define ARCH_GET_FS 0x1003
+#define ARCH_GET_GS 0x1004
-#define ARCH_GET_CPUID 0x1011
-#define ARCH_SET_CPUID 0x1012
+#define ARCH_GET_CPUID 0x1011
+#define ARCH_SET_CPUID 0x1012
-#define ARCH_GET_XCOMP_SUPP 0x1021
-#define ARCH_GET_XCOMP_PERM 0x1022
-#define ARCH_REQ_XCOMP_PERM 0x1023
+#define ARCH_GET_XCOMP_SUPP 0x1021
+#define ARCH_GET_XCOMP_PERM 0x1022
+#define ARCH_REQ_XCOMP_PERM 0x1023
+#define ARCH_GET_XCOMP_GUEST_PERM 0x1024
+#define ARCH_REQ_XCOMP_GUEST_PERM 0x1025
-#define ARCH_MAP_VDSO_X32 0x2001
-#define ARCH_MAP_VDSO_32 0x2002
-#define ARCH_MAP_VDSO_64 0x2003
+#define ARCH_MAP_VDSO_X32 0x2001
+#define ARCH_MAP_VDSO_32 0x2002
+#define ARCH_MAP_VDSO_64 0x2003
#endif /* _ASM_X86_PRCTL_H */
diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S
index 1cc9da6e29c7..d0d7b9bc6cad 100644
--- a/tools/arch/x86/lib/memcpy_64.S
+++ b/tools/arch/x86/lib/memcpy_64.S
@@ -27,8 +27,7 @@
* Output:
* rax original destination
*/
-SYM_FUNC_START_ALIAS(__memcpy)
-SYM_FUNC_START_WEAK(memcpy)
+SYM_FUNC_START(__memcpy)
ALTERNATIVE_2 "jmp memcpy_orig", "", X86_FEATURE_REP_GOOD, \
"jmp memcpy_erms", X86_FEATURE_ERMS
@@ -39,12 +38,13 @@ SYM_FUNC_START_WEAK(memcpy)
rep movsq
movl %edx, %ecx
rep movsb
- ret
-SYM_FUNC_END(memcpy)
-SYM_FUNC_END_ALIAS(__memcpy)
-EXPORT_SYMBOL(memcpy)
+ RET
+SYM_FUNC_END(__memcpy)
EXPORT_SYMBOL(__memcpy)
+SYM_FUNC_ALIAS_WEAK(memcpy, __memcpy)
+EXPORT_SYMBOL(memcpy)
+
/*
* memcpy_erms() - enhanced fast string memcpy. This is faster and
* simpler than memcpy. Use memcpy_erms when possible.
@@ -53,7 +53,7 @@ SYM_FUNC_START_LOCAL(memcpy_erms)
movq %rdi, %rax
movq %rdx, %rcx
rep movsb
- ret
+ RET
SYM_FUNC_END(memcpy_erms)
SYM_FUNC_START_LOCAL(memcpy_orig)
@@ -137,7 +137,7 @@ SYM_FUNC_START_LOCAL(memcpy_orig)
movq %r9, 1*8(%rdi)
movq %r10, -2*8(%rdi, %rdx)
movq %r11, -1*8(%rdi, %rdx)
- retq
+ RET
.p2align 4
.Lless_16bytes:
cmpl $8, %edx
@@ -149,7 +149,7 @@ SYM_FUNC_START_LOCAL(memcpy_orig)
movq -1*8(%rsi, %rdx), %r9
movq %r8, 0*8(%rdi)
movq %r9, -1*8(%rdi, %rdx)
- retq
+ RET
.p2align 4
.Lless_8bytes:
cmpl $4, %edx
@@ -162,7 +162,7 @@ SYM_FUNC_START_LOCAL(memcpy_orig)
movl -4(%rsi, %rdx), %r8d
movl %ecx, (%rdi)
movl %r8d, -4(%rdi, %rdx)
- retq
+ RET
.p2align 4
.Lless_3bytes:
subl $1, %edx
@@ -180,7 +180,7 @@ SYM_FUNC_START_LOCAL(memcpy_orig)
movb %cl, (%rdi)
.Lend:
- retq
+ RET
SYM_FUNC_END(memcpy_orig)
.popsection
diff --git a/tools/arch/x86/lib/memset_64.S b/tools/arch/x86/lib/memset_64.S
index 9827ae267f96..fc9ffd3ff3b2 100644
--- a/tools/arch/x86/lib/memset_64.S
+++ b/tools/arch/x86/lib/memset_64.S
@@ -17,7 +17,6 @@
*
* rax original destination
*/
-SYM_FUNC_START_WEAK(memset)
SYM_FUNC_START(__memset)
/*
* Some CPUs support enhanced REP MOVSB/STOSB feature. It is recommended
@@ -40,12 +39,13 @@ SYM_FUNC_START(__memset)
movl %edx,%ecx
rep stosb
movq %r9,%rax
- ret
+ RET
SYM_FUNC_END(__memset)
-SYM_FUNC_END_ALIAS(memset)
-EXPORT_SYMBOL(memset)
EXPORT_SYMBOL(__memset)
+SYM_FUNC_ALIAS_WEAK(memset, __memset)
+EXPORT_SYMBOL(memset)
+
/*
* ISO C memset - set a memory block to a byte value. This function uses
* enhanced rep stosb to override the fast string function.
@@ -63,7 +63,7 @@ SYM_FUNC_START_LOCAL(memset_erms)
movq %rdx,%rcx
rep stosb
movq %r9,%rax
- ret
+ RET
SYM_FUNC_END(memset_erms)
SYM_FUNC_START_LOCAL(memset_orig)
@@ -125,7 +125,7 @@ SYM_FUNC_START_LOCAL(memset_orig)
.Lende:
movq %r10,%rax
- ret
+ RET
.Lbad_alignment:
cmpq $7,%rdx
diff --git a/tools/arch/x86/lib/x86-opcode-map.txt b/tools/arch/x86/lib/x86-opcode-map.txt
index ec31f5b60323..d12d1358f96d 100644
--- a/tools/arch/x86/lib/x86-opcode-map.txt
+++ b/tools/arch/x86/lib/x86-opcode-map.txt
@@ -690,7 +690,10 @@ AVXcode: 2
45: vpsrlvd/q Vx,Hx,Wx (66),(v)
46: vpsravd Vx,Hx,Wx (66),(v) | vpsravd/q Vx,Hx,Wx (66),(evo)
47: vpsllvd/q Vx,Hx,Wx (66),(v)
-# Skip 0x48-0x4b
+# Skip 0x48
+49: TILERELEASE (v1),(000),(11B) | LDTILECFG Mtc (v1)(000) | STTILECFG Mtc (66),(v1),(000) | TILEZERO Vt (F2),(v1),(11B)
+# Skip 0x4a
+4b: TILELOADD Vt,Wsm (F2),(v1) | TILELOADDT1 Vt,Wsm (66),(v1) | TILESTORED Wsm,Vt (F3),(v)
4c: vrcp14ps/d Vpd,Wpd (66),(ev)
4d: vrcp14ss/d Vsd,Hpd,Wsd (66),(ev)
4e: vrsqrt14ps/d Vpd,Wpd (66),(ev)
@@ -705,7 +708,10 @@ AVXcode: 2
59: vpbroadcastq Vx,Wx (66),(v) | vbroadcasti32x2 Vx,Wx (66),(evo)
5a: vbroadcasti128 Vqq,Mdq (66),(v) | vbroadcasti32x4/64x2 Vx,Wx (66),(evo)
5b: vbroadcasti32x8/64x4 Vqq,Mdq (66),(ev)
-# Skip 0x5c-0x61
+5c: TDPBF16PS Vt,Wt,Ht (F3),(v1)
+# Skip 0x5d
+5e: TDPBSSD Vt,Wt,Ht (F2),(v1) | TDPBSUD Vt,Wt,Ht (F3),(v1) | TDPBUSD Vt,Wt,Ht (66),(v1) | TDPBUUD Vt,Wt,Ht (v1)
+# Skip 0x5f-0x61
62: vpexpandb/w Vx,Wx (66),(ev)
63: vpcompressb/w Wx,Vx (66),(ev)
64: vpblendmd/q Vx,Hx,Wx (66),(ev)
@@ -822,9 +828,9 @@ AVXcode: 3
05: vpermilpd Vx,Wx,Ib (66),(v)
06: vperm2f128 Vqq,Hqq,Wqq,Ib (66),(v)
07:
-08: vroundps Vx,Wx,Ib (66) | vrndscaleps Vx,Wx,Ib (66),(evo)
+08: vroundps Vx,Wx,Ib (66) | vrndscaleps Vx,Wx,Ib (66),(evo) | vrndscaleph Vx,Wx,Ib (evo)
09: vroundpd Vx,Wx,Ib (66) | vrndscalepd Vx,Wx,Ib (66),(evo)
-0a: vroundss Vss,Wss,Ib (66),(v1) | vrndscaless Vx,Hx,Wx,Ib (66),(evo)
+0a: vroundss Vss,Wss,Ib (66),(v1) | vrndscaless Vx,Hx,Wx,Ib (66),(evo) | vrndscalesh Vx,Hx,Wx,Ib (evo)
0b: vroundsd Vsd,Wsd,Ib (66),(v1) | vrndscalesd Vx,Hx,Wx,Ib (66),(evo)
0c: vblendps Vx,Hx,Wx,Ib (66)
0d: vblendpd Vx,Hx,Wx,Ib (66)
@@ -846,8 +852,8 @@ AVXcode: 3
22: vpinsrd/q Vdq,Hdq,Ey,Ib (66),(v1)
23: vshuff32x4/64x2 Vx,Hx,Wx,Ib (66),(ev)
25: vpternlogd/q Vx,Hx,Wx,Ib (66),(ev)
-26: vgetmantps/d Vx,Wx,Ib (66),(ev)
-27: vgetmantss/d Vx,Hx,Wx,Ib (66),(ev)
+26: vgetmantps/d Vx,Wx,Ib (66),(ev) | vgetmantph Vx,Wx,Ib (ev)
+27: vgetmantss/d Vx,Hx,Wx,Ib (66),(ev) | vgetmantsh Vx,Hx,Wx,Ib (ev)
30: kshiftrb/w Vk,Uk,Ib (66),(v)
31: kshiftrd/q Vk,Uk,Ib (66),(v)
32: kshiftlb/w Vk,Uk,Ib (66),(v)
@@ -871,23 +877,102 @@ AVXcode: 3
51: vrangess/d Vx,Hx,Wx,Ib (66),(ev)
54: vfixupimmps/d Vx,Hx,Wx,Ib (66),(ev)
55: vfixupimmss/d Vx,Hx,Wx,Ib (66),(ev)
-56: vreduceps/d Vx,Wx,Ib (66),(ev)
-57: vreducess/d Vx,Hx,Wx,Ib (66),(ev)
+56: vreduceps/d Vx,Wx,Ib (66),(ev) | vreduceph Vx,Wx,Ib (ev)
+57: vreducess/d Vx,Hx,Wx,Ib (66),(ev) | vreducesh Vx,Hx,Wx,Ib (ev)
60: vpcmpestrm Vdq,Wdq,Ib (66),(v1)
61: vpcmpestri Vdq,Wdq,Ib (66),(v1)
62: vpcmpistrm Vdq,Wdq,Ib (66),(v1)
63: vpcmpistri Vdq,Wdq,Ib (66),(v1)
-66: vfpclassps/d Vk,Wx,Ib (66),(ev)
-67: vfpclassss/d Vk,Wx,Ib (66),(ev)
+66: vfpclassps/d Vk,Wx,Ib (66),(ev) | vfpclassph Vx,Wx,Ib (ev)
+67: vfpclassss/d Vk,Wx,Ib (66),(ev) | vfpclasssh Vx,Wx,Ib (ev)
70: vpshldw Vx,Hx,Wx,Ib (66),(ev)
71: vpshldd/q Vx,Hx,Wx,Ib (66),(ev)
72: vpshrdw Vx,Hx,Wx,Ib (66),(ev)
73: vpshrdd/q Vx,Hx,Wx,Ib (66),(ev)
+c2: vcmpph Vx,Hx,Wx,Ib (ev) | vcmpsh Vx,Hx,Wx,Ib (F3),(ev)
cc: sha1rnds4 Vdq,Wdq,Ib
ce: vgf2p8affineqb Vx,Wx,Ib (66)
cf: vgf2p8affineinvqb Vx,Wx,Ib (66)
df: VAESKEYGEN Vdq,Wdq,Ib (66),(v1)
-f0: RORX Gy,Ey,Ib (F2),(v)
+f0: RORX Gy,Ey,Ib (F2),(v) | HRESET Gv,Ib (F3),(000),(11B)
+EndTable
+
+Table: EVEX map 5
+Referrer:
+AVXcode: 5
+10: vmovsh Vx,Hx,Wx (F3),(ev) | vmovsh Vx,Wx (F3),(ev)
+11: vmovsh Wx,Hx,Vx (F3),(ev) | vmovsh Wx,Vx (F3),(ev)
+1d: vcvtps2phx Vx,Wx (66),(ev) | vcvtss2sh Vx,Hx,Wx (ev)
+2a: vcvtsi2sh Vx,Hx,Wx (F3),(ev)
+2c: vcvttsh2si Vx,Wx (F3),(ev)
+2d: vcvtsh2si Vx,Wx (F3),(ev)
+2e: vucomish Vx,Wx (ev)
+2f: vcomish Vx,Wx (ev)
+51: vsqrtph Vx,Wx (ev) | vsqrtsh Vx,Hx,Wx (F3),(ev)
+58: vaddph Vx,Hx,Wx (ev) | vaddsh Vx,Hx,Wx (F3),(ev)
+59: vmulph Vx,Hx,Wx (ev) | vmulsh Vx,Hx,Wx (F3),(ev)
+5a: vcvtpd2ph Vx,Wx (66),(ev) | vcvtph2pd Vx,Wx (ev) | vcvtsd2sh Vx,Hx,Wx (F2),(ev) | vcvtsh2sd Vx,Hx,Wx (F3),(ev)
+5b: vcvtdq2ph Vx,Wx (ev) | vcvtph2dq Vx,Wx (66),(ev) | vcvtqq2ph Vx,Wx (ev) | vcvttph2dq Vx,Wx (F3),(ev)
+5c: vsubph Vx,Hx,Wx (ev) | vsubsh Vx,Hx,Wx (F3),(ev)
+5d: vminph Vx,Hx,Wx (ev) | vminsh Vx,Hx,Wx (F3),(ev)
+5e: vdivph Vx,Hx,Wx (ev) | vdivsh Vx,Hx,Wx (F3),(ev)
+5f: vmaxph Vx,Hx,Wx (ev) | vmaxsh Vx,Hx,Wx (F3),(ev)
+6e: vmovw Vx,Wx (66),(ev)
+78: vcvttph2udq Vx,Wx (ev) | vcvttph2uqq Vx,Wx (66),(ev) | vcvttsh2usi Vx,Wx (F3),(ev)
+79: vcvtph2udq Vx,Wx (ev) | vcvtph2uqq Vx,Wx (66),(ev) | vcvtsh2usi Vx,Wx (F3),(ev)
+7a: vcvttph2qq Vx,Wx (66),(ev) | vcvtudq2ph Vx,Wx (F2),(ev) | vcvtuqq2ph Vx,Wx (F2),(ev)
+7b: vcvtph2qq Vx,Wx (66),(ev) | vcvtusi2sh Vx,Hx,Wx (F3),(ev)
+7c: vcvttph2uw Vx,Wx (ev) | vcvttph2w Vx,Wx (66),(ev)
+7d: vcvtph2uw Vx,Wx (ev) | vcvtph2w Vx,Wx (66),(ev) | vcvtuw2ph Vx,Wx (F2),(ev) | vcvtw2ph Vx,Wx (F3),(ev)
+7e: vmovw Wx,Vx (66),(ev)
+EndTable
+
+Table: EVEX map 6
+Referrer:
+AVXcode: 6
+13: vcvtph2psx Vx,Wx (66),(ev) | vcvtsh2ss Vx,Hx,Wx (ev)
+2c: vscalefph Vx,Hx,Wx (66),(ev)
+2d: vscalefsh Vx,Hx,Wx (66),(ev)
+42: vgetexpph Vx,Wx (66),(ev)
+43: vgetexpsh Vx,Hx,Wx (66),(ev)
+4c: vrcpph Vx,Wx (66),(ev)
+4d: vrcpsh Vx,Hx,Wx (66),(ev)
+4e: vrsqrtph Vx,Wx (66),(ev)
+4f: vrsqrtsh Vx,Hx,Wx (66),(ev)
+56: vfcmaddcph Vx,Hx,Wx (F2),(ev) | vfmaddcph Vx,Hx,Wx (F3),(ev)
+57: vfcmaddcsh Vx,Hx,Wx (F2),(ev) | vfmaddcsh Vx,Hx,Wx (F3),(ev)
+96: vfmaddsub132ph Vx,Hx,Wx (66),(ev)
+97: vfmsubadd132ph Vx,Hx,Wx (66),(ev)
+98: vfmadd132ph Vx,Hx,Wx (66),(ev)
+99: vfmadd132sh Vx,Hx,Wx (66),(ev)
+9a: vfmsub132ph Vx,Hx,Wx (66),(ev)
+9b: vfmsub132sh Vx,Hx,Wx (66),(ev)
+9c: vfnmadd132ph Vx,Hx,Wx (66),(ev)
+9d: vfnmadd132sh Vx,Hx,Wx (66),(ev)
+9e: vfnmsub132ph Vx,Hx,Wx (66),(ev)
+9f: vfnmsub132sh Vx,Hx,Wx (66),(ev)
+a6: vfmaddsub213ph Vx,Hx,Wx (66),(ev)
+a7: vfmsubadd213ph Vx,Hx,Wx (66),(ev)
+a8: vfmadd213ph Vx,Hx,Wx (66),(ev)
+a9: vfmadd213sh Vx,Hx,Wx (66),(ev)
+aa: vfmsub213ph Vx,Hx,Wx (66),(ev)
+ab: vfmsub213sh Vx,Hx,Wx (66),(ev)
+ac: vfnmadd213ph Vx,Hx,Wx (66),(ev)
+ad: vfnmadd213sh Vx,Hx,Wx (66),(ev)
+ae: vfnmsub213ph Vx,Hx,Wx (66),(ev)
+af: vfnmsub213sh Vx,Hx,Wx (66),(ev)
+b6: vfmaddsub231ph Vx,Hx,Wx (66),(ev)
+b7: vfmsubadd231ph Vx,Hx,Wx (66),(ev)
+b8: vfmadd231ph Vx,Hx,Wx (66),(ev)
+b9: vfmadd231sh Vx,Hx,Wx (66),(ev)
+ba: vfmsub231ph Vx,Hx,Wx (66),(ev)
+bb: vfmsub231sh Vx,Hx,Wx (66),(ev)
+bc: vfnmadd231ph Vx,Hx,Wx (66),(ev)
+bd: vfnmadd231sh Vx,Hx,Wx (66),(ev)
+be: vfnmsub231ph Vx,Hx,Wx (66),(ev)
+bf: vfnmsub231sh Vx,Hx,Wx (66),(ev)
+d6: vfcmulcph Vx,Hx,Wx (F2),(ev) | vfmulcph Vx,Hx,Wx (F3),(ev)
+d7: vfcmulcsh Vx,Hx,Wx (F2),(ev) | vfmulcsh Vx,Hx,Wx (F3),(ev)
EndTable
GrpTable: Grp1
@@ -970,7 +1055,7 @@ 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) | SAVEPREVSSP (F3),(010),(11B) | RSTORSSP Mq (F3) | SETSSBSY (F3),(000),(11B)
+5: rdpkru (110),(11B) | wrpkru (111),(11B) | SAVEPREVSSP (F3),(010),(11B) | RSTORSSP Mq (F3) | SETSSBSY (F3),(000),(11B) | CLUI (F3),(110),(11B) | SERIALIZE (000),(11B) | STUI (F3),(111),(11B) | TESTUI (F3)(101)(11B) | UIRET (F3),(100),(11B) | XRESLDTRK (F2),(000),(11B) | XSUSLDTRK (F2),(001),(11B)
6: LMSW Ew
7: INVLPG Mb | SWAPGS (o64),(000),(11B) | RDTSCP (001),(11B)
EndTable
@@ -987,7 +1072,7 @@ GrpTable: Grp9
3: xrstors
4: xsavec
5: xsaves
-6: VMPTRLD Mq | VMCLEAR Mq (66) | VMXON Mq (F3) | RDRAND Rv (11B)
+6: VMPTRLD Mq | VMCLEAR Mq (66) | VMXON Mq (F3) | RDRAND Rv (11B) | SENDUIPI Gq (F3)
7: VMPTRST Mq | VMPTRST Mq (F3) | RDSEED Rv (11B)
EndTable
diff --git a/tools/bpf/bpftool/skeleton/pid_iter.bpf.c b/tools/bpf/bpftool/skeleton/pid_iter.bpf.c
index d9b420972934..f70702fcb224 100644
--- a/tools/bpf/bpftool/skeleton/pid_iter.bpf.c
+++ b/tools/bpf/bpftool/skeleton/pid_iter.bpf.c
@@ -71,8 +71,8 @@ int iter(struct bpf_iter__task_file *ctx)
e.pid = task->tgid;
e.id = get_obj_id(file->private_data, obj_type);
- bpf_probe_read_kernel(&e.comm, sizeof(e.comm),
- task->group_leader->comm);
+ bpf_probe_read_kernel_str(&e.comm, sizeof(e.comm),
+ task->group_leader->comm);
bpf_seq_write(ctx->meta->seq, &e, sizeof(e));
return 0;
diff --git a/tools/bpf/resolve_btfids/Makefile b/tools/bpf/resolve_btfids/Makefile
index 9ddeca947635..320a88ac28c9 100644
--- a/tools/bpf/resolve_btfids/Makefile
+++ b/tools/bpf/resolve_btfids/Makefile
@@ -9,7 +9,11 @@ ifeq ($(V),1)
msg =
else
Q = @
- msg = @printf ' %-8s %s%s\n' "$(1)" "$(notdir $(2))" "$(if $(3), $(3))";
+ ifeq ($(silent),1)
+ msg =
+ else
+ msg = @printf ' %-8s %s%s\n' "$(1)" "$(notdir $(2))" "$(if $(3), $(3))";
+ endif
MAKEFLAGS=--no-print-directory
endif
diff --git a/tools/bpf/runqslower/runqslower.bpf.c b/tools/bpf/runqslower/runqslower.bpf.c
index ab9353f2fd46..9a5c1f008fe6 100644
--- a/tools/bpf/runqslower/runqslower.bpf.c
+++ b/tools/bpf/runqslower/runqslower.bpf.c
@@ -68,7 +68,7 @@ int handle__sched_switch(u64 *ctx)
*/
struct task_struct *prev = (struct task_struct *)ctx[1];
struct task_struct *next = (struct task_struct *)ctx[2];
- struct event event = {};
+ struct runq_event event = {};
u64 *tsp, delta_us;
long state;
u32 pid;
diff --git a/tools/bpf/runqslower/runqslower.c b/tools/bpf/runqslower/runqslower.c
index 2414cc764461..d78f4148597f 100644
--- a/tools/bpf/runqslower/runqslower.c
+++ b/tools/bpf/runqslower/runqslower.c
@@ -100,7 +100,7 @@ static int bump_memlock_rlimit(void)
void handle_event(void *ctx, int cpu, void *data, __u32 data_sz)
{
- const struct event *e = data;
+ const struct runq_event *e = data;
struct tm *tm;
char ts[32];
time_t t;
diff --git a/tools/bpf/runqslower/runqslower.h b/tools/bpf/runqslower/runqslower.h
index 9db225425e5f..4f70f07200c2 100644
--- a/tools/bpf/runqslower/runqslower.h
+++ b/tools/bpf/runqslower/runqslower.h
@@ -4,7 +4,7 @@
#define TASK_COMM_LEN 16
-struct event {
+struct runq_event {
char task[TASK_COMM_LEN];
__u64 delta_us;
pid_t pid;
diff --git a/tools/build/Build.include b/tools/build/Build.include
index 2cf3b1bde86e..c2a95ab47379 100644
--- a/tools/build/Build.include
+++ b/tools/build/Build.include
@@ -99,7 +99,7 @@ cxx_flags = -Wp,-MD,$(depfile) -Wp,-MT,$@ $(CXXFLAGS) -D"BUILD_STR(s)=\#s" $(CXX
###
## HOSTCC C flags
-host_c_flags = -Wp,-MD,$(depfile) -Wp,-MT,$@ $(KBUILD_HOSTCFLAGS) -D"BUILD_STR(s)=\#s" $(HOSTCFLAGS_$(basetarget).o) $(HOSTCFLAGS_$(obj))
+host_c_flags = -Wp,-MD,$(depfile) -Wp,-MT,$@ $(HOSTCFLAGS) -D"BUILD_STR(s)=\#s" $(HOSTCFLAGS_$(basetarget).o) $(HOSTCFLAGS_$(obj))
# output directory for tests below
TMPOUT = .tmp_$$$$
diff --git a/tools/cgroup/memcg_slabinfo.py b/tools/cgroup/memcg_slabinfo.py
index 1600b17dbb8a..1d3a90d93fe2 100644
--- a/tools/cgroup/memcg_slabinfo.py
+++ b/tools/cgroup/memcg_slabinfo.py
@@ -11,7 +11,7 @@ from drgn.helpers.linux import list_for_each_entry, list_empty
from drgn.helpers.linux import for_each_page
from drgn.helpers.linux.cpumask import for_each_online_cpu
from drgn.helpers.linux.percpu import per_cpu_ptr
-from drgn import container_of, FaultError, Object
+from drgn import container_of, FaultError, Object, cast
DESC = """
@@ -69,15 +69,15 @@ def oo_objects(s):
def count_partial(n, fn):
- nr_pages = 0
- for page in list_for_each_entry('struct page', n.partial.address_of_(),
- 'lru'):
- nr_pages += fn(page)
- return nr_pages
+ nr_objs = 0
+ for slab in list_for_each_entry('struct slab', n.partial.address_of_(),
+ 'slab_list'):
+ nr_objs += fn(slab)
+ return nr_objs
-def count_free(page):
- return page.objects - page.inuse
+def count_free(slab):
+ return slab.objects - slab.inuse
def slub_get_slabinfo(s, cfg):
@@ -145,14 +145,14 @@ def detect_kernel_config():
return cfg
-def for_each_slab_page(prog):
+def for_each_slab(prog):
PGSlab = 1 << prog.constant('PG_slab')
PGHead = 1 << prog.constant('PG_head')
for page in for_each_page(prog):
try:
if page.flags.value_() & PGSlab:
- yield page
+ yield cast('struct slab *', page)
except FaultError:
pass
@@ -190,13 +190,13 @@ def main():
'list'):
obj_cgroups.add(ptr.value_())
- # look over all slab pages, belonging to non-root memcgs
- # and look for objects belonging to the given memory cgroup
- for page in for_each_slab_page(prog):
- objcg_vec_raw = page.memcg_data.value_()
+ # look over all slab folios and look for objects belonging
+ # to the given memory cgroup
+ for slab in for_each_slab(prog):
+ objcg_vec_raw = slab.memcg_data.value_()
if objcg_vec_raw == 0:
continue
- cache = page.slab_cache
+ cache = slab.slab_cache
if not cache:
continue
addr = cache.value_()
diff --git a/tools/iio/iio_event_monitor.c b/tools/iio/iio_event_monitor.c
index 0076437f6e3f..b94a16ba5c6c 100644
--- a/tools/iio/iio_event_monitor.c
+++ b/tools/iio/iio_event_monitor.c
@@ -279,6 +279,7 @@ static void print_event(struct iio_event_data *event)
printf(", direction: %s", iio_ev_dir_text[dir]);
printf("\n");
+ fflush(stdout);
}
/* Enable or disable events in sysfs if the knob is available */
diff --git a/tools/include/asm-generic/bitops.h b/tools/include/asm-generic/bitops.h
index 5d2ab38965cc..9ab313e93555 100644
--- a/tools/include/asm-generic/bitops.h
+++ b/tools/include/asm-generic/bitops.h
@@ -18,7 +18,6 @@
#include <asm-generic/bitops/fls.h>
#include <asm-generic/bitops/__fls.h>
#include <asm-generic/bitops/fls64.h>
-#include <asm-generic/bitops/find.h>
#ifndef _TOOLS_LINUX_BITOPS_H_
#error only <linux/bitops.h> can be included directly
diff --git a/tools/include/linux/bitmap.h b/tools/include/linux/bitmap.h
index 95611df1d26e..ea97804d04d4 100644
--- a/tools/include/linux/bitmap.h
+++ b/tools/include/linux/bitmap.h
@@ -1,9 +1,10 @@
/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _PERF_BITOPS_H
-#define _PERF_BITOPS_H
+#ifndef _TOOLS_LINUX_BITMAP_H
+#define _TOOLS_LINUX_BITMAP_H
#include <string.h>
#include <linux/bitops.h>
+#include <linux/find.h>
#include <stdlib.h>
#include <linux/kernel.h>
@@ -181,4 +182,4 @@ static inline int bitmap_intersects(const unsigned long *src1,
return __bitmap_intersects(src1, src2, nbits);
}
-#endif /* _PERF_BITOPS_H */
+#endif /* _TOOLS_LINUX_BITMAP_H */
diff --git a/tools/include/asm-generic/bitops/find.h b/tools/include/linux/find.h
index 6481fd11012a..47e2bd6c5174 100644
--- a/tools/include/asm-generic/bitops/find.h
+++ b/tools/include/linux/find.h
@@ -1,11 +1,19 @@
/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _TOOLS_LINUX_ASM_GENERIC_BITOPS_FIND_H_
-#define _TOOLS_LINUX_ASM_GENERIC_BITOPS_FIND_H_
+#ifndef _TOOLS_LINUX_FIND_H_
+#define _TOOLS_LINUX_FIND_H_
+
+#ifndef _TOOLS_LINUX_BITMAP_H
+#error tools: only <linux/bitmap.h> can be included directly
+#endif
+
+#include <linux/bitops.h>
extern unsigned long _find_next_bit(const unsigned long *addr1,
const unsigned long *addr2, unsigned long nbits,
unsigned long start, unsigned long invert, unsigned long le);
extern unsigned long _find_first_bit(const unsigned long *addr, unsigned long size);
+extern unsigned long _find_first_and_bit(const unsigned long *addr1,
+ const unsigned long *addr2, unsigned long size);
extern unsigned long _find_first_zero_bit(const unsigned long *addr, unsigned long size);
extern unsigned long _find_last_bit(const unsigned long *addr, unsigned long size);
@@ -96,7 +104,6 @@ unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size,
#endif
#ifndef find_first_bit
-
/**
* find_first_bit - find the first set bit in a memory region
* @addr: The address to start the search at
@@ -116,11 +123,34 @@ unsigned long find_first_bit(const unsigned long *addr, unsigned long size)
return _find_first_bit(addr, size);
}
+#endif
+
+#ifndef find_first_and_bit
+/**
+ * find_first_and_bit - find the first set bit in both memory regions
+ * @addr1: The first address to base the search on
+ * @addr2: The second address to base the search on
+ * @size: The bitmap size in bits
+ *
+ * Returns the bit number for the next set bit
+ * If no bits are set, returns @size.
+ */
+static inline
+unsigned long find_first_and_bit(const unsigned long *addr1,
+ const unsigned long *addr2,
+ unsigned long size)
+{
+ if (small_const_nbits(size)) {
+ unsigned long val = *addr1 & *addr2 & GENMASK(size - 1, 0);
-#endif /* find_first_bit */
+ return val ? __ffs(val) : size;
+ }
-#ifndef find_first_zero_bit
+ return _find_first_and_bit(addr1, addr2, size);
+}
+#endif
+#ifndef find_first_zero_bit
/**
* find_first_zero_bit - find the first cleared bit in a memory region
* @addr: The address to start the search at
@@ -142,4 +172,43 @@ unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size)
}
#endif
-#endif /*_TOOLS_LINUX_ASM_GENERIC_BITOPS_FIND_H_ */
+#ifndef find_last_bit
+/**
+ * find_last_bit - find the last set bit in a memory region
+ * @addr: The address to start the search at
+ * @size: The number of bits to search
+ *
+ * Returns the bit number of the last set bit, or size.
+ */
+static inline
+unsigned long find_last_bit(const unsigned long *addr, unsigned long size)
+{
+ if (small_const_nbits(size)) {
+ unsigned long val = *addr & GENMASK(size - 1, 0);
+
+ return val ? __fls(val) : size;
+ }
+
+ return _find_last_bit(addr, size);
+}
+#endif
+
+/**
+ * find_next_clump8 - find next 8-bit clump with set bits in a memory region
+ * @clump: location to store copy of found clump
+ * @addr: address to base the search on
+ * @size: bitmap size in number of bits
+ * @offset: bit offset at which to start searching
+ *
+ * Returns the bit offset for the next set clump; the found clump value is
+ * copied to the location pointed by @clump. If no bits are set, returns @size.
+ */
+extern unsigned long find_next_clump8(unsigned long *clump,
+ const unsigned long *addr,
+ unsigned long size, unsigned long offset);
+
+#define find_first_clump8(clump, bits, size) \
+ find_next_clump8((clump), (bits), (size), 0)
+
+
+#endif /*__LINUX_FIND_H_ */
diff --git a/tools/include/linux/hash.h b/tools/include/linux/hash.h
index ad6fa21d977b..38edaa08f862 100644
--- a/tools/include/linux/hash.h
+++ b/tools/include/linux/hash.h
@@ -62,10 +62,7 @@ static inline u32 __hash_32_generic(u32 val)
return val * GOLDEN_RATIO_32;
}
-#ifndef HAVE_ARCH_HASH_32
-#define hash_32 hash_32_generic
-#endif
-static inline u32 hash_32_generic(u32 val, unsigned int bits)
+static inline u32 hash_32(u32 val, unsigned int bits)
{
/* High bits are more random, so use them. */
return __hash_32(val) >> (32 - bits);
diff --git a/tools/include/nolibc/nolibc.h b/tools/include/nolibc/nolibc.h
index 3430667b0d24..c1c285fe494a 100644
--- a/tools/include/nolibc/nolibc.h
+++ b/tools/include/nolibc/nolibc.h
@@ -265,12 +265,17 @@ struct stat {
* - arguments are in rdi, rsi, rdx, r10, r8, r9 respectively
* - the system call is performed by calling the syscall instruction
* - syscall return comes in rax
- * - rcx and r8..r11 may be clobbered, others are preserved.
+ * - rcx and r11 are clobbered, others are preserved.
* - the arguments are cast to long and assigned into the target registers
* which are then simply passed as registers to the asm code, so that we
* don't have to experience issues with register constraints.
* - the syscall number is always specified last in order to allow to force
* some registers before (gcc refuses a %-register at the last position).
+ * - see also x86-64 ABI section A.2 AMD64 Linux Kernel Conventions, A.2.1
+ * Calling Conventions.
+ *
+ * Link x86-64 ABI: https://gitlab.com/x86-psABIs/x86-64-ABI/-/wikis/x86-64-psABI
+ *
*/
#define my_syscall0(num) \
@@ -280,9 +285,9 @@ struct stat {
\
asm volatile ( \
"syscall\n" \
- : "=a" (_ret) \
+ : "=a"(_ret) \
: "0"(_num) \
- : "rcx", "r8", "r9", "r10", "r11", "memory", "cc" \
+ : "rcx", "r11", "memory", "cc" \
); \
_ret; \
})
@@ -295,10 +300,10 @@ struct stat {
\
asm volatile ( \
"syscall\n" \
- : "=a" (_ret) \
+ : "=a"(_ret) \
: "r"(_arg1), \
"0"(_num) \
- : "rcx", "r8", "r9", "r10", "r11", "memory", "cc" \
+ : "rcx", "r11", "memory", "cc" \
); \
_ret; \
})
@@ -312,10 +317,10 @@ struct stat {
\
asm volatile ( \
"syscall\n" \
- : "=a" (_ret) \
+ : "=a"(_ret) \
: "r"(_arg1), "r"(_arg2), \
"0"(_num) \
- : "rcx", "r8", "r9", "r10", "r11", "memory", "cc" \
+ : "rcx", "r11", "memory", "cc" \
); \
_ret; \
})
@@ -330,10 +335,10 @@ struct stat {
\
asm volatile ( \
"syscall\n" \
- : "=a" (_ret) \
+ : "=a"(_ret) \
: "r"(_arg1), "r"(_arg2), "r"(_arg3), \
"0"(_num) \
- : "rcx", "r8", "r9", "r10", "r11", "memory", "cc" \
+ : "rcx", "r11", "memory", "cc" \
); \
_ret; \
})
@@ -349,10 +354,10 @@ struct stat {
\
asm volatile ( \
"syscall\n" \
- : "=a" (_ret), "=r"(_arg4) \
+ : "=a"(_ret) \
: "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), \
"0"(_num) \
- : "rcx", "r8", "r9", "r11", "memory", "cc" \
+ : "rcx", "r11", "memory", "cc" \
); \
_ret; \
})
@@ -369,10 +374,10 @@ struct stat {
\
asm volatile ( \
"syscall\n" \
- : "=a" (_ret), "=r"(_arg4), "=r"(_arg5) \
+ : "=a"(_ret) \
: "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \
"0"(_num) \
- : "rcx", "r9", "r11", "memory", "cc" \
+ : "rcx", "r11", "memory", "cc" \
); \
_ret; \
})
@@ -390,7 +395,7 @@ struct stat {
\
asm volatile ( \
"syscall\n" \
- : "=a" (_ret), "=r"(_arg4), "=r"(_arg5) \
+ : "=a"(_ret) \
: "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \
"r"(_arg6), "0"(_num) \
: "rcx", "r11", "memory", "cc" \
@@ -399,17 +404,23 @@ struct stat {
})
/* startup code */
+/*
+ * x86-64 System V ABI mandates:
+ * 1) %rsp must be 16-byte aligned right before the function call.
+ * 2) The deepest stack frame should be zero (the %rbp).
+ *
+ */
asm(".section .text\n"
".global _start\n"
"_start:\n"
"pop %rdi\n" // argc (first arg, %rdi)
"mov %rsp, %rsi\n" // argv[] (second arg, %rsi)
"lea 8(%rsi,%rdi,8),%rdx\n" // then a NULL then envp (third arg, %rdx)
- "and $-16, %rsp\n" // x86 ABI : esp must be 16-byte aligned when
- "sub $8, %rsp\n" // entering the callee
+ "xor %ebp, %ebp\n" // zero the stack frame
+ "and $-16, %rsp\n" // x86 ABI : esp must be 16-byte aligned before call
"call main\n" // main() returns the status code, we'll exit with it.
- "movzb %al, %rdi\n" // retrieve exit code from 8 lower bits
- "mov $60, %rax\n" // NR_exit == 60
+ "mov %eax, %edi\n" // retrieve exit code (32 bit)
+ "mov $60, %eax\n" // NR_exit == 60
"syscall\n" // really exit
"hlt\n" // ensure it does not return
"");
@@ -577,20 +588,28 @@ struct sys_stat_struct {
})
/* startup code */
+/*
+ * i386 System V ABI mandates:
+ * 1) last pushed argument must be 16-byte aligned.
+ * 2) The deepest stack frame should be set to zero
+ *
+ */
asm(".section .text\n"
".global _start\n"
"_start:\n"
"pop %eax\n" // argc (first arg, %eax)
"mov %esp, %ebx\n" // argv[] (second arg, %ebx)
"lea 4(%ebx,%eax,4),%ecx\n" // then a NULL then envp (third arg, %ecx)
- "and $-16, %esp\n" // x86 ABI : esp must be 16-byte aligned when
+ "xor %ebp, %ebp\n" // zero the stack frame
+ "and $-16, %esp\n" // x86 ABI : esp must be 16-byte aligned before
+ "sub $4, %esp\n" // the call instruction (args are aligned)
"push %ecx\n" // push all registers on the stack so that we
"push %ebx\n" // support both regparm and plain stack modes
"push %eax\n"
"call main\n" // main() returns the status code in %eax
- "movzbl %al, %ebx\n" // retrieve exit code from lower 8 bits
- "movl $1, %eax\n" // NR_exit == 1
- "int $0x80\n" // exit now
+ "mov %eax, %ebx\n" // retrieve exit code (32-bit int)
+ "movl $1, %eax\n" // NR_exit == 1
+ "int $0x80\n" // exit now
"hlt\n" // ensure it does not
"");
@@ -774,7 +793,6 @@ asm(".section .text\n"
"and %r3, %r1, $-8\n" // AAPCS : sp must be 8-byte aligned in the
"mov %sp, %r3\n" // callee, an bl doesn't push (lr=pc)
"bl main\n" // main() returns the status code, we'll exit with it.
- "and %r0, %r0, $0xff\n" // limit exit code to 8 bits
"movs r7, $1\n" // NR_exit == 1
"svc $0x00\n"
"");
@@ -971,7 +989,6 @@ asm(".section .text\n"
"add x2, x2, x1\n" // + argv
"and sp, x1, -16\n" // sp must be 16-byte aligned in the callee
"bl main\n" // main() returns the status code, we'll exit with it.
- "and x0, x0, 0xff\n" // limit exit code to 8 bits
"mov x8, 93\n" // NR_exit == 93
"svc #0\n"
"");
@@ -1176,7 +1193,7 @@ asm(".section .text\n"
"addiu $sp,$sp,-16\n" // the callee expects to save a0..a3 there!
"jal main\n" // main() returns the status code, we'll exit with it.
"nop\n" // delayed slot
- "and $a0, $v0, 0xff\n" // limit exit code to 8 bits
+ "move $a0, $v0\n" // retrieve 32-bit exit code from v0
"li $v0, 4001\n" // NR_exit == 4001
"syscall\n"
".end __start\n"
@@ -1374,7 +1391,6 @@ asm(".section .text\n"
"add a2,a2,a1\n" // + argv
"andi sp,a1,-16\n" // sp must be 16-byte aligned
"call main\n" // main() returns the status code, we'll exit with it.
- "andi a0, a0, 0xff\n" // limit exit code to 8 bits
"li a7, 93\n" // NR_exit == 93
"ecall\n"
"");
@@ -1556,6 +1572,12 @@ pid_t sys_getpid(void)
}
static __attribute__((unused))
+pid_t sys_gettid(void)
+{
+ return my_syscall0(__NR_gettid);
+}
+
+static __attribute__((unused))
int sys_gettimeofday(struct timeval *tv, struct timezone *tz)
{
return my_syscall2(__NR_gettimeofday, tv, tz);
@@ -2014,6 +2036,18 @@ pid_t getpid(void)
}
static __attribute__((unused))
+pid_t gettid(void)
+{
+ pid_t ret = sys_gettid();
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+static __attribute__((unused))
int gettimeofday(struct timeval *tv, struct timezone *tz)
{
int ret = sys_gettimeofday(tv, tz);
diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
index 4557a8b6086f..1c48b0ae3ba3 100644
--- a/tools/include/uapi/asm-generic/unistd.h
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -883,8 +883,11 @@ __SYSCALL(__NR_process_mrelease, sys_process_mrelease)
#define __NR_futex_waitv 449
__SYSCALL(__NR_futex_waitv, sys_futex_waitv)
+#define __NR_set_mempolicy_home_node 450
+__SYSCALL(__NR_set_mempolicy_home_node, sys_set_mempolicy_home_node)
+
#undef __NR_syscalls
-#define __NR_syscalls 450
+#define __NR_syscalls 451
/*
* 32 bit systems traditionally used different
diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h
index 3b810b53ba8b..642808520d92 100644
--- a/tools/include/uapi/drm/drm.h
+++ b/tools/include/uapi/drm/drm.h
@@ -1096,6 +1096,24 @@ extern "C" {
#define DRM_IOCTL_SYNCOBJ_TRANSFER DRM_IOWR(0xCC, struct drm_syncobj_transfer)
#define DRM_IOCTL_SYNCOBJ_TIMELINE_SIGNAL DRM_IOWR(0xCD, struct drm_syncobj_timeline_array)
+/**
+ * DRM_IOCTL_MODE_GETFB2 - Get framebuffer metadata.
+ *
+ * This queries metadata about a framebuffer. User-space fills
+ * &drm_mode_fb_cmd2.fb_id as the input, and the kernels fills the rest of the
+ * struct as the output.
+ *
+ * If the client is DRM master or has &CAP_SYS_ADMIN, &drm_mode_fb_cmd2.handles
+ * will be filled with GEM buffer handles. Planes are valid until one has a
+ * zero handle -- this can be used to compute the number of planes.
+ *
+ * Otherwise, &drm_mode_fb_cmd2.handles will be zeroed and planes are valid
+ * until one has a zero &drm_mode_fb_cmd2.pitches.
+ *
+ * If the framebuffer has a format modifier, &DRM_MODE_FB_MODIFIERS will be set
+ * in &drm_mode_fb_cmd2.flags and &drm_mode_fb_cmd2.modifier will contain the
+ * modifier. Otherwise, user-space must ignore &drm_mode_fb_cmd2.modifier.
+ */
#define DRM_IOCTL_MODE_GETFB2 DRM_IOWR(0xCE, struct drm_mode_fb_cmd2)
/*
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 1daa45268de2..507ee1f2aa96 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -1131,6 +1131,10 @@ struct kvm_ppc_resize_hpt {
#define KVM_CAP_EXIT_ON_EMULATION_FAILURE 204
#define KVM_CAP_ARM_MTE 205
#define KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM 206
+#define KVM_CAP_VM_GPA_BITS 207
+#define KVM_CAP_XSAVE2 208
+#define KVM_CAP_SYS_ATTRIBUTES 209
+#define KVM_CAP_PPC_AIL_MODE_3 210
#ifdef KVM_CAP_IRQ_ROUTING
@@ -1162,11 +1166,20 @@ struct kvm_irq_routing_hv_sint {
__u32 sint;
};
+struct kvm_irq_routing_xen_evtchn {
+ __u32 port;
+ __u32 vcpu;
+ __u32 priority;
+};
+
+#define KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL ((__u32)(-1))
+
/* gsi routing entry types */
#define KVM_IRQ_ROUTING_IRQCHIP 1
#define KVM_IRQ_ROUTING_MSI 2
#define KVM_IRQ_ROUTING_S390_ADAPTER 3
#define KVM_IRQ_ROUTING_HV_SINT 4
+#define KVM_IRQ_ROUTING_XEN_EVTCHN 5
struct kvm_irq_routing_entry {
__u32 gsi;
@@ -1178,6 +1191,7 @@ struct kvm_irq_routing_entry {
struct kvm_irq_routing_msi msi;
struct kvm_irq_routing_s390_adapter adapter;
struct kvm_irq_routing_hv_sint hv_sint;
+ struct kvm_irq_routing_xen_evtchn xen_evtchn;
__u32 pad[8];
} u;
};
@@ -1208,6 +1222,7 @@ struct kvm_x86_mce {
#define KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL (1 << 1)
#define KVM_XEN_HVM_CONFIG_SHARED_INFO (1 << 2)
#define KVM_XEN_HVM_CONFIG_RUNSTATE (1 << 3)
+#define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL (1 << 4)
struct kvm_xen_hvm_config {
__u32 flags;
@@ -2031,4 +2046,7 @@ struct kvm_stats_desc {
#define KVM_GET_STATS_FD _IO(KVMIO, 0xce)
+/* Available with KVM_CAP_XSAVE2 */
+#define KVM_GET_XSAVE2 _IOR(KVMIO, 0xcf, struct kvm_xsave)
+
#endif /* __LINUX_KVM_H */
diff --git a/tools/include/uapi/linux/lirc.h b/tools/include/uapi/linux/lirc.h
deleted file mode 100644
index 45fcbf99d72e..000000000000
--- a/tools/include/uapi/linux/lirc.h
+++ /dev/null
@@ -1,229 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-/*
- * lirc.h - linux infrared remote control header file
- * last modified 2010/07/13 by Jarod Wilson
- */
-
-#ifndef _LINUX_LIRC_H
-#define _LINUX_LIRC_H
-
-#include <linux/types.h>
-#include <linux/ioctl.h>
-
-#define PULSE_BIT 0x01000000
-#define PULSE_MASK 0x00FFFFFF
-
-#define LIRC_MODE2_SPACE 0x00000000
-#define LIRC_MODE2_PULSE 0x01000000
-#define LIRC_MODE2_FREQUENCY 0x02000000
-#define LIRC_MODE2_TIMEOUT 0x03000000
-
-#define LIRC_VALUE_MASK 0x00FFFFFF
-#define LIRC_MODE2_MASK 0xFF000000
-
-#define LIRC_SPACE(val) (((val)&LIRC_VALUE_MASK) | LIRC_MODE2_SPACE)
-#define LIRC_PULSE(val) (((val)&LIRC_VALUE_MASK) | LIRC_MODE2_PULSE)
-#define LIRC_FREQUENCY(val) (((val)&LIRC_VALUE_MASK) | LIRC_MODE2_FREQUENCY)
-#define LIRC_TIMEOUT(val) (((val)&LIRC_VALUE_MASK) | LIRC_MODE2_TIMEOUT)
-
-#define LIRC_VALUE(val) ((val)&LIRC_VALUE_MASK)
-#define LIRC_MODE2(val) ((val)&LIRC_MODE2_MASK)
-
-#define LIRC_IS_SPACE(val) (LIRC_MODE2(val) == LIRC_MODE2_SPACE)
-#define LIRC_IS_PULSE(val) (LIRC_MODE2(val) == LIRC_MODE2_PULSE)
-#define LIRC_IS_FREQUENCY(val) (LIRC_MODE2(val) == LIRC_MODE2_FREQUENCY)
-#define LIRC_IS_TIMEOUT(val) (LIRC_MODE2(val) == LIRC_MODE2_TIMEOUT)
-
-/* used heavily by lirc userspace */
-#define lirc_t int
-
-/*** lirc compatible hardware features ***/
-
-#define LIRC_MODE2SEND(x) (x)
-#define LIRC_SEND2MODE(x) (x)
-#define LIRC_MODE2REC(x) ((x) << 16)
-#define LIRC_REC2MODE(x) ((x) >> 16)
-
-#define LIRC_MODE_RAW 0x00000001
-#define LIRC_MODE_PULSE 0x00000002
-#define LIRC_MODE_MODE2 0x00000004
-#define LIRC_MODE_SCANCODE 0x00000008
-#define LIRC_MODE_LIRCCODE 0x00000010
-
-
-#define LIRC_CAN_SEND_RAW LIRC_MODE2SEND(LIRC_MODE_RAW)
-#define LIRC_CAN_SEND_PULSE LIRC_MODE2SEND(LIRC_MODE_PULSE)
-#define LIRC_CAN_SEND_MODE2 LIRC_MODE2SEND(LIRC_MODE_MODE2)
-#define LIRC_CAN_SEND_LIRCCODE LIRC_MODE2SEND(LIRC_MODE_LIRCCODE)
-
-#define LIRC_CAN_SEND_MASK 0x0000003f
-
-#define LIRC_CAN_SET_SEND_CARRIER 0x00000100
-#define LIRC_CAN_SET_SEND_DUTY_CYCLE 0x00000200
-#define LIRC_CAN_SET_TRANSMITTER_MASK 0x00000400
-
-#define LIRC_CAN_REC_RAW LIRC_MODE2REC(LIRC_MODE_RAW)
-#define LIRC_CAN_REC_PULSE LIRC_MODE2REC(LIRC_MODE_PULSE)
-#define LIRC_CAN_REC_MODE2 LIRC_MODE2REC(LIRC_MODE_MODE2)
-#define LIRC_CAN_REC_SCANCODE LIRC_MODE2REC(LIRC_MODE_SCANCODE)
-#define LIRC_CAN_REC_LIRCCODE LIRC_MODE2REC(LIRC_MODE_LIRCCODE)
-
-#define LIRC_CAN_REC_MASK LIRC_MODE2REC(LIRC_CAN_SEND_MASK)
-
-#define LIRC_CAN_SET_REC_CARRIER (LIRC_CAN_SET_SEND_CARRIER << 16)
-#define LIRC_CAN_SET_REC_DUTY_CYCLE (LIRC_CAN_SET_SEND_DUTY_CYCLE << 16)
-
-#define LIRC_CAN_SET_REC_DUTY_CYCLE_RANGE 0x40000000
-#define LIRC_CAN_SET_REC_CARRIER_RANGE 0x80000000
-#define LIRC_CAN_GET_REC_RESOLUTION 0x20000000
-#define LIRC_CAN_SET_REC_TIMEOUT 0x10000000
-#define LIRC_CAN_SET_REC_FILTER 0x08000000
-
-#define LIRC_CAN_MEASURE_CARRIER 0x02000000
-#define LIRC_CAN_USE_WIDEBAND_RECEIVER 0x04000000
-
-#define LIRC_CAN_SEND(x) ((x)&LIRC_CAN_SEND_MASK)
-#define LIRC_CAN_REC(x) ((x)&LIRC_CAN_REC_MASK)
-
-#define LIRC_CAN_NOTIFY_DECODE 0x01000000
-
-/*** IOCTL commands for lirc driver ***/
-
-#define LIRC_GET_FEATURES _IOR('i', 0x00000000, __u32)
-
-#define LIRC_GET_SEND_MODE _IOR('i', 0x00000001, __u32)
-#define LIRC_GET_REC_MODE _IOR('i', 0x00000002, __u32)
-#define LIRC_GET_REC_RESOLUTION _IOR('i', 0x00000007, __u32)
-
-#define LIRC_GET_MIN_TIMEOUT _IOR('i', 0x00000008, __u32)
-#define LIRC_GET_MAX_TIMEOUT _IOR('i', 0x00000009, __u32)
-
-/* code length in bits, currently only for LIRC_MODE_LIRCCODE */
-#define LIRC_GET_LENGTH _IOR('i', 0x0000000f, __u32)
-
-#define LIRC_SET_SEND_MODE _IOW('i', 0x00000011, __u32)
-#define LIRC_SET_REC_MODE _IOW('i', 0x00000012, __u32)
-/* Note: these can reset the according pulse_width */
-#define LIRC_SET_SEND_CARRIER _IOW('i', 0x00000013, __u32)
-#define LIRC_SET_REC_CARRIER _IOW('i', 0x00000014, __u32)
-#define LIRC_SET_SEND_DUTY_CYCLE _IOW('i', 0x00000015, __u32)
-#define LIRC_SET_TRANSMITTER_MASK _IOW('i', 0x00000017, __u32)
-
-/*
- * when a timeout != 0 is set the driver will send a
- * LIRC_MODE2_TIMEOUT data packet, otherwise LIRC_MODE2_TIMEOUT is
- * never sent, timeout is disabled by default
- */
-#define LIRC_SET_REC_TIMEOUT _IOW('i', 0x00000018, __u32)
-
-/* 1 enables, 0 disables timeout reports in MODE2 */
-#define LIRC_SET_REC_TIMEOUT_REPORTS _IOW('i', 0x00000019, __u32)
-
-/*
- * if enabled from the next key press on the driver will send
- * LIRC_MODE2_FREQUENCY packets
- */
-#define LIRC_SET_MEASURE_CARRIER_MODE _IOW('i', 0x0000001d, __u32)
-
-/*
- * to set a range use LIRC_SET_REC_CARRIER_RANGE with the
- * lower bound first and later LIRC_SET_REC_CARRIER with the upper bound
- */
-#define LIRC_SET_REC_CARRIER_RANGE _IOW('i', 0x0000001f, __u32)
-
-#define LIRC_SET_WIDEBAND_RECEIVER _IOW('i', 0x00000023, __u32)
-
-/*
- * Return the recording timeout, which is either set by
- * the ioctl LIRC_SET_REC_TIMEOUT or by the kernel after setting the protocols.
- */
-#define LIRC_GET_REC_TIMEOUT _IOR('i', 0x00000024, __u32)
-
-/*
- * struct lirc_scancode - decoded scancode with protocol for use with
- * LIRC_MODE_SCANCODE
- *
- * @timestamp: Timestamp in nanoseconds using CLOCK_MONOTONIC when IR
- * was decoded.
- * @flags: should be 0 for transmit. When receiving scancodes,
- * LIRC_SCANCODE_FLAG_TOGGLE or LIRC_SCANCODE_FLAG_REPEAT can be set
- * depending on the protocol
- * @rc_proto: see enum rc_proto
- * @keycode: the translated keycode. Set to 0 for transmit.
- * @scancode: the scancode received or to be sent
- */
-struct lirc_scancode {
- __u64 timestamp;
- __u16 flags;
- __u16 rc_proto;
- __u32 keycode;
- __u64 scancode;
-};
-
-/* Set if the toggle bit of rc-5 or rc-6 is enabled */
-#define LIRC_SCANCODE_FLAG_TOGGLE 1
-/* Set if this is a nec or sanyo repeat */
-#define LIRC_SCANCODE_FLAG_REPEAT 2
-
-/**
- * enum rc_proto - the Remote Controller protocol
- *
- * @RC_PROTO_UNKNOWN: Protocol not known
- * @RC_PROTO_OTHER: Protocol known but proprietary
- * @RC_PROTO_RC5: Philips RC5 protocol
- * @RC_PROTO_RC5X_20: Philips RC5x 20 bit protocol
- * @RC_PROTO_RC5_SZ: StreamZap variant of RC5
- * @RC_PROTO_JVC: JVC protocol
- * @RC_PROTO_SONY12: Sony 12 bit protocol
- * @RC_PROTO_SONY15: Sony 15 bit protocol
- * @RC_PROTO_SONY20: Sony 20 bit protocol
- * @RC_PROTO_NEC: NEC protocol
- * @RC_PROTO_NECX: Extended NEC protocol
- * @RC_PROTO_NEC32: NEC 32 bit protocol
- * @RC_PROTO_SANYO: Sanyo protocol
- * @RC_PROTO_MCIR2_KBD: RC6-ish MCE keyboard
- * @RC_PROTO_MCIR2_MSE: RC6-ish MCE mouse
- * @RC_PROTO_RC6_0: Philips RC6-0-16 protocol
- * @RC_PROTO_RC6_6A_20: Philips RC6-6A-20 protocol
- * @RC_PROTO_RC6_6A_24: Philips RC6-6A-24 protocol
- * @RC_PROTO_RC6_6A_32: Philips RC6-6A-32 protocol
- * @RC_PROTO_RC6_MCE: MCE (Philips RC6-6A-32 subtype) protocol
- * @RC_PROTO_SHARP: Sharp protocol
- * @RC_PROTO_XMP: XMP protocol
- * @RC_PROTO_CEC: CEC protocol
- * @RC_PROTO_IMON: iMon Pad protocol
- * @RC_PROTO_RCMM12: RC-MM protocol 12 bits
- * @RC_PROTO_RCMM24: RC-MM protocol 24 bits
- * @RC_PROTO_RCMM32: RC-MM protocol 32 bits
- */
-enum rc_proto {
- RC_PROTO_UNKNOWN = 0,
- RC_PROTO_OTHER = 1,
- RC_PROTO_RC5 = 2,
- RC_PROTO_RC5X_20 = 3,
- RC_PROTO_RC5_SZ = 4,
- RC_PROTO_JVC = 5,
- RC_PROTO_SONY12 = 6,
- RC_PROTO_SONY15 = 7,
- RC_PROTO_SONY20 = 8,
- RC_PROTO_NEC = 9,
- RC_PROTO_NECX = 10,
- RC_PROTO_NEC32 = 11,
- RC_PROTO_SANYO = 12,
- RC_PROTO_MCIR2_KBD = 13,
- RC_PROTO_MCIR2_MSE = 14,
- RC_PROTO_RC6_0 = 15,
- RC_PROTO_RC6_6A_20 = 16,
- RC_PROTO_RC6_6A_24 = 17,
- RC_PROTO_RC6_6A_32 = 18,
- RC_PROTO_RC6_MCE = 19,
- RC_PROTO_SHARP = 20,
- RC_PROTO_XMP = 21,
- RC_PROTO_CEC = 22,
- RC_PROTO_IMON = 23,
- RC_PROTO_RCMM12 = 24,
- RC_PROTO_RCMM24 = 25,
- RC_PROTO_RCMM32 = 26,
-};
-
-#endif
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index bd8860eeb291..d37629dbad72 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -251,6 +251,8 @@ enum {
PERF_BR_SYSRET = 8, /* syscall return */
PERF_BR_COND_CALL = 9, /* conditional function call */
PERF_BR_COND_RET = 10, /* conditional function return */
+ PERF_BR_ERET = 11, /* exception return */
+ PERF_BR_IRQ = 12, /* irq */
PERF_BR_MAX,
};
@@ -465,6 +467,8 @@ struct perf_event_attr {
/*
* User provided data if sigtrap=1, passed back to user via
* siginfo_t::si_perf_data, e.g. to permit user to identify the event.
+ * Note, siginfo_t::si_perf_data is long-sized, and sig_data will be
+ * truncated accordingly on 32 bit architectures.
*/
__u64 sig_data;
};
@@ -1332,7 +1336,10 @@ union perf_mem_data_src {
/* hop level */
#define PERF_MEM_HOPS_0 0x01 /* remote core, same node */
-/* 2-7 available */
+#define PERF_MEM_HOPS_1 0x02 /* remote node, same socket */
+#define PERF_MEM_HOPS_2 0x03 /* remote socket, same board */
+#define PERF_MEM_HOPS_3 0x04 /* remote board */
+/* 5-7 available */
#define PERF_MEM_HOPS_SHIFT 43
#define PERF_MEM_S(a, s) \
diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h
index bb73e9a0b24f..e998764f0262 100644
--- a/tools/include/uapi/linux/prctl.h
+++ b/tools/include/uapi/linux/prctl.h
@@ -272,4 +272,7 @@ struct prctl_mm_map {
# define PR_SCHED_CORE_SCOPE_THREAD_GROUP 1
# define PR_SCHED_CORE_SCOPE_PROCESS_GROUP 2
+#define PR_SET_VMA 0x53564d41
+# define PR_SET_VMA_ANON_NAME 0
+
#endif /* _LINUX_PRCTL_H */
diff --git a/tools/include/uapi/sound/asound.h b/tools/include/uapi/sound/asound.h
index 5fbb79e30819..2d3e5df39a59 100644
--- a/tools/include/uapi/sound/asound.h
+++ b/tools/include/uapi/sound/asound.h
@@ -56,8 +56,10 @@
* *
****************************************************************************/
+#define AES_IEC958_STATUS_SIZE 24
+
struct snd_aes_iec958 {
- unsigned char status[24]; /* AES/IEC958 channel status bits */
+ unsigned char status[AES_IEC958_STATUS_SIZE]; /* AES/IEC958 channel status bits */
unsigned char subcode[147]; /* AES/IEC958 subcode bits */
unsigned char pad; /* nothing */
unsigned char dig_subframe[4]; /* AES/IEC958 subframe bits */
@@ -202,6 +204,11 @@ typedef int __bitwise snd_pcm_format_t;
#define SNDRV_PCM_FORMAT_S24_BE ((__force snd_pcm_format_t) 7) /* low three bytes */
#define SNDRV_PCM_FORMAT_U24_LE ((__force snd_pcm_format_t) 8) /* low three bytes */
#define SNDRV_PCM_FORMAT_U24_BE ((__force snd_pcm_format_t) 9) /* low three bytes */
+/*
+ * For S32/U32 formats, 'msbits' hardware parameter is often used to deliver information about the
+ * available bit count in most significant bit. It's for the case of so-called 'left-justified' or
+ * `right-padding` sample which has less width than 32 bit.
+ */
#define SNDRV_PCM_FORMAT_S32_LE ((__force snd_pcm_format_t) 10)
#define SNDRV_PCM_FORMAT_S32_BE ((__force snd_pcm_format_t) 11)
#define SNDRV_PCM_FORMAT_U32_LE ((__force snd_pcm_format_t) 12)
@@ -300,7 +307,7 @@ typedef int __bitwise snd_pcm_subformat_t;
#define SNDRV_PCM_INFO_HAS_LINK_ESTIMATED_ATIME 0x04000000 /* report estimated link audio time */
#define SNDRV_PCM_INFO_HAS_LINK_SYNCHRONIZED_ATIME 0x08000000 /* report synchronized audio/system time */
#define SNDRV_PCM_INFO_EXPLICIT_SYNC 0x10000000 /* needs explicit sync of pointers and data */
-
+#define SNDRV_PCM_INFO_NO_REWINDS 0x20000000 /* hardware can only support monotonic changes of appl_ptr */
#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 */
diff --git a/tools/lib/find_bit.c b/tools/lib/find_bit.c
index 109aa7ffcf97..ba4b8d94e004 100644
--- a/tools/lib/find_bit.c
+++ b/tools/lib/find_bit.c
@@ -96,6 +96,26 @@ unsigned long _find_first_bit(const unsigned long *addr, unsigned long size)
}
#endif
+#ifndef find_first_and_bit
+/*
+ * Find the first set bit in two memory regions.
+ */
+unsigned long _find_first_and_bit(const unsigned long *addr1,
+ const unsigned long *addr2,
+ unsigned long size)
+{
+ unsigned long idx, val;
+
+ for (idx = 0; idx * BITS_PER_LONG < size; idx++) {
+ val = addr1[idx] & addr2[idx];
+ if (val)
+ return min(idx * BITS_PER_LONG + __ffs(val), size);
+ }
+
+ return size;
+}
+#endif
+
#ifndef find_first_zero_bit
/*
* Find the first cleared bit in a memory region.
diff --git a/tools/lib/perf/Documentation/libperf.txt b/tools/lib/perf/Documentation/libperf.txt
index 63ae5e0195ce..32c5051c24eb 100644
--- a/tools/lib/perf/Documentation/libperf.txt
+++ b/tools/lib/perf/Documentation/libperf.txt
@@ -48,6 +48,7 @@ SYNOPSIS
int perf_cpu_map__nr(const struct perf_cpu_map *cpus);
bool perf_cpu_map__empty(const struct perf_cpu_map *map);
int perf_cpu_map__max(struct perf_cpu_map *map);
+ bool perf_cpu_map__has(const struct perf_cpu_map *map, int cpu);
#define perf_cpu_map__for_each_cpu(cpu, idx, cpus)
--
@@ -135,16 +136,16 @@ SYNOPSIS
int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus,
struct perf_thread_map *threads);
void perf_evsel__close(struct perf_evsel *evsel);
- void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu);
+ void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu_map_idx);
int perf_evsel__mmap(struct perf_evsel *evsel, int pages);
void perf_evsel__munmap(struct perf_evsel *evsel);
- void *perf_evsel__mmap_base(struct perf_evsel *evsel, int cpu, int thread);
- int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread,
+ void *perf_evsel__mmap_base(struct perf_evsel *evsel, int cpu_map_idx, int thread);
+ int perf_evsel__read(struct perf_evsel *evsel, int cpu_map_idx, int thread,
struct perf_counts_values *count);
int perf_evsel__enable(struct perf_evsel *evsel);
- int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu);
+ int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu_map_idx);
int perf_evsel__disable(struct perf_evsel *evsel);
- int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu);
+ int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu_map_idx);
struct perf_cpu_map *perf_evsel__cpus(struct perf_evsel *evsel);
struct perf_thread_map *perf_evsel__threads(struct perf_evsel *evsel);
struct perf_event_attr *perf_evsel__attr(struct perf_evsel *evsel);
diff --git a/tools/lib/perf/cpumap.c b/tools/lib/perf/cpumap.c
index adaad3dddf6e..ee66760f1e63 100644
--- a/tools/lib/perf/cpumap.c
+++ b/tools/lib/perf/cpumap.c
@@ -10,15 +10,24 @@
#include <ctype.h>
#include <limits.h>
-struct perf_cpu_map *perf_cpu_map__dummy_new(void)
+static struct perf_cpu_map *perf_cpu_map__alloc(int nr_cpus)
{
- struct perf_cpu_map *cpus = malloc(sizeof(*cpus) + sizeof(int));
+ struct perf_cpu_map *cpus = malloc(sizeof(*cpus) + sizeof(struct perf_cpu) * nr_cpus);
if (cpus != NULL) {
- cpus->nr = 1;
- cpus->map[0] = -1;
+ cpus->nr = nr_cpus;
refcount_set(&cpus->refcnt, 1);
+
}
+ return cpus;
+}
+
+struct perf_cpu_map *perf_cpu_map__dummy_new(void)
+{
+ struct perf_cpu_map *cpus = perf_cpu_map__alloc(1);
+
+ if (cpus)
+ cpus->map[0].cpu = -1;
return cpus;
}
@@ -54,15 +63,12 @@ static struct perf_cpu_map *cpu_map__default_new(void)
if (nr_cpus < 0)
return NULL;
- cpus = malloc(sizeof(*cpus) + nr_cpus * sizeof(int));
+ cpus = perf_cpu_map__alloc(nr_cpus);
if (cpus != NULL) {
int i;
for (i = 0; i < nr_cpus; ++i)
- cpus->map[i] = i;
-
- cpus->nr = nr_cpus;
- refcount_set(&cpus->refcnt, 1);
+ cpus->map[i].cpu = i;
}
return cpus;
@@ -73,31 +79,32 @@ struct perf_cpu_map *perf_cpu_map__default_new(void)
return cpu_map__default_new();
}
-static int cmp_int(const void *a, const void *b)
+
+static int cmp_cpu(const void *a, const void *b)
{
- return *(const int *)a - *(const int*)b;
+ const struct perf_cpu *cpu_a = a, *cpu_b = b;
+
+ return cpu_a->cpu - cpu_b->cpu;
}
-static struct perf_cpu_map *cpu_map__trim_new(int nr_cpus, int *tmp_cpus)
+static struct perf_cpu_map *cpu_map__trim_new(int nr_cpus, const struct perf_cpu *tmp_cpus)
{
- size_t payload_size = nr_cpus * sizeof(int);
- struct perf_cpu_map *cpus = malloc(sizeof(*cpus) + payload_size);
+ size_t payload_size = nr_cpus * sizeof(struct perf_cpu);
+ struct perf_cpu_map *cpus = perf_cpu_map__alloc(nr_cpus);
int i, j;
if (cpus != NULL) {
memcpy(cpus->map, tmp_cpus, payload_size);
- qsort(cpus->map, nr_cpus, sizeof(int), cmp_int);
+ qsort(cpus->map, nr_cpus, sizeof(struct perf_cpu), cmp_cpu);
/* Remove dups */
j = 0;
for (i = 0; i < nr_cpus; i++) {
- if (i == 0 || cpus->map[i] != cpus->map[i - 1])
- cpus->map[j++] = cpus->map[i];
+ if (i == 0 || cpus->map[i].cpu != cpus->map[i - 1].cpu)
+ cpus->map[j++].cpu = cpus->map[i].cpu;
}
cpus->nr = j;
assert(j <= nr_cpus);
- refcount_set(&cpus->refcnt, 1);
}
-
return cpus;
}
@@ -105,7 +112,7 @@ struct perf_cpu_map *perf_cpu_map__read(FILE *file)
{
struct perf_cpu_map *cpus = NULL;
int nr_cpus = 0;
- int *tmp_cpus = NULL, *tmp;
+ struct perf_cpu *tmp_cpus = NULL, *tmp;
int max_entries = 0;
int n, cpu, prev;
char sep;
@@ -124,24 +131,24 @@ struct perf_cpu_map *perf_cpu_map__read(FILE *file)
if (new_max >= max_entries) {
max_entries = new_max + MAX_NR_CPUS / 2;
- tmp = realloc(tmp_cpus, max_entries * sizeof(int));
+ tmp = realloc(tmp_cpus, max_entries * sizeof(struct perf_cpu));
if (tmp == NULL)
goto out_free_tmp;
tmp_cpus = tmp;
}
while (++prev < cpu)
- tmp_cpus[nr_cpus++] = prev;
+ tmp_cpus[nr_cpus++].cpu = prev;
}
if (nr_cpus == max_entries) {
max_entries += MAX_NR_CPUS;
- tmp = realloc(tmp_cpus, max_entries * sizeof(int));
+ tmp = realloc(tmp_cpus, max_entries * sizeof(struct perf_cpu));
if (tmp == NULL)
goto out_free_tmp;
tmp_cpus = tmp;
}
- tmp_cpus[nr_cpus++] = cpu;
+ tmp_cpus[nr_cpus++].cpu = cpu;
if (n == 2 && sep == '-')
prev = cpu;
else
@@ -179,7 +186,7 @@ struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list)
unsigned long start_cpu, end_cpu = 0;
char *p = NULL;
int i, nr_cpus = 0;
- int *tmp_cpus = NULL, *tmp;
+ struct perf_cpu *tmp_cpus = NULL, *tmp;
int max_entries = 0;
if (!cpu_list)
@@ -220,17 +227,17 @@ struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list)
for (; start_cpu <= end_cpu; start_cpu++) {
/* check for duplicates */
for (i = 0; i < nr_cpus; i++)
- if (tmp_cpus[i] == (int)start_cpu)
+ if (tmp_cpus[i].cpu == (int)start_cpu)
goto invalid;
if (nr_cpus == max_entries) {
max_entries += MAX_NR_CPUS;
- tmp = realloc(tmp_cpus, max_entries * sizeof(int));
+ tmp = realloc(tmp_cpus, max_entries * sizeof(struct perf_cpu));
if (tmp == NULL)
goto invalid;
tmp_cpus = tmp;
}
- tmp_cpus[nr_cpus++] = (int)start_cpu;
+ tmp_cpus[nr_cpus++].cpu = (int)start_cpu;
}
if (*p)
++p;
@@ -250,12 +257,16 @@ out:
return cpus;
}
-int perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx)
+struct perf_cpu perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx)
{
+ struct perf_cpu result = {
+ .cpu = -1
+ };
+
if (cpus && idx < cpus->nr)
return cpus->map[idx];
- return -1;
+ return result;
}
int perf_cpu_map__nr(const struct perf_cpu_map *cpus)
@@ -265,21 +276,26 @@ int perf_cpu_map__nr(const struct perf_cpu_map *cpus)
bool perf_cpu_map__empty(const struct perf_cpu_map *map)
{
- return map ? map->map[0] == -1 : true;
+ return map ? map->map[0].cpu == -1 : true;
}
-int perf_cpu_map__idx(struct perf_cpu_map *cpus, int cpu)
+int perf_cpu_map__idx(const struct perf_cpu_map *cpus, struct perf_cpu cpu)
{
- int low = 0, high = cpus->nr;
+ int low, high;
+ if (!cpus)
+ return -1;
+
+ low = 0;
+ high = cpus->nr;
while (low < high) {
- int idx = (low + high) / 2,
- cpu_at_idx = cpus->map[idx];
+ int idx = (low + high) / 2;
+ struct perf_cpu cpu_at_idx = cpus->map[idx];
- if (cpu_at_idx == cpu)
+ if (cpu_at_idx.cpu == cpu.cpu)
return idx;
- if (cpu_at_idx > cpu)
+ if (cpu_at_idx.cpu > cpu.cpu)
high = idx;
else
low = idx + 1;
@@ -288,10 +304,19 @@ int perf_cpu_map__idx(struct perf_cpu_map *cpus, int cpu)
return -1;
}
-int perf_cpu_map__max(struct perf_cpu_map *map)
+bool perf_cpu_map__has(const struct perf_cpu_map *cpus, struct perf_cpu cpu)
{
+ return perf_cpu_map__idx(cpus, cpu) != -1;
+}
+
+struct perf_cpu perf_cpu_map__max(struct perf_cpu_map *map)
+{
+ struct perf_cpu result = {
+ .cpu = -1
+ };
+
// cpu_map__trim_new() qsort()s it, cpu_map__default_new() sorts it as well.
- return map->nr > 0 ? map->map[map->nr - 1] : -1;
+ return map->nr > 0 ? map->map[map->nr - 1] : result;
}
/*
@@ -305,7 +330,7 @@ int perf_cpu_map__max(struct perf_cpu_map *map)
struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig,
struct perf_cpu_map *other)
{
- int *tmp_cpus;
+ struct perf_cpu *tmp_cpus;
int tmp_len;
int i, j, k;
struct perf_cpu_map *merged;
@@ -319,19 +344,19 @@ struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig,
if (!other)
return orig;
if (orig->nr == other->nr &&
- !memcmp(orig->map, other->map, orig->nr * sizeof(int)))
+ !memcmp(orig->map, other->map, orig->nr * sizeof(struct perf_cpu)))
return orig;
tmp_len = orig->nr + other->nr;
- tmp_cpus = malloc(tmp_len * sizeof(int));
+ tmp_cpus = malloc(tmp_len * sizeof(struct perf_cpu));
if (!tmp_cpus)
return NULL;
/* Standard merge algorithm from wikipedia */
i = j = k = 0;
while (i < orig->nr && j < other->nr) {
- if (orig->map[i] <= other->map[j]) {
- if (orig->map[i] == other->map[j])
+ if (orig->map[i].cpu <= other->map[j].cpu) {
+ if (orig->map[i].cpu == other->map[j].cpu)
j++;
tmp_cpus[k++] = orig->map[i++];
} else
diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c
index e37dfad31383..9a770bfdc804 100644
--- a/tools/lib/perf/evlist.c
+++ b/tools/lib/perf/evlist.c
@@ -407,7 +407,7 @@ perf_evlist__mmap_cb_get(struct perf_evlist *evlist, bool overwrite, int idx)
static int
perf_evlist__mmap_cb_mmap(struct perf_mmap *map, struct perf_mmap_param *mp,
- int output, int cpu)
+ int output, struct perf_cpu cpu)
{
return perf_mmap__mmap(map, mp, output, cpu);
}
@@ -426,7 +426,7 @@ mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,
int idx, struct perf_mmap_param *mp, int cpu_idx,
int thread, int *_output, int *_output_overwrite)
{
- int evlist_cpu = perf_cpu_map__cpu(evlist->cpus, cpu_idx);
+ struct perf_cpu evlist_cpu = perf_cpu_map__cpu(evlist->cpus, cpu_idx);
struct perf_evsel *evsel;
int revent;
@@ -643,14 +643,14 @@ perf_evlist__next_mmap(struct perf_evlist *evlist, struct perf_mmap *map,
return overwrite ? evlist->mmap_ovw_first : evlist->mmap_first;
}
-void __perf_evlist__set_leader(struct list_head *list)
+void __perf_evlist__set_leader(struct list_head *list, struct perf_evsel *leader)
{
- struct perf_evsel *evsel, *leader;
+ struct perf_evsel *first, *last, *evsel;
- leader = list_entry(list->next, struct perf_evsel, node);
- evsel = list_entry(list->prev, struct perf_evsel, node);
+ first = list_first_entry(list, struct perf_evsel, node);
+ last = list_last_entry(list, struct perf_evsel, node);
- leader->nr_members = evsel->idx - leader->idx + 1;
+ leader->nr_members = last->idx - first->idx + 1;
__perf_evlist__for_each_entry(list, evsel)
evsel->leader = leader;
@@ -659,7 +659,10 @@ void __perf_evlist__set_leader(struct list_head *list)
void perf_evlist__set_leader(struct perf_evlist *evlist)
{
if (evlist->nr_entries) {
+ struct perf_evsel *first = list_entry(evlist->entries.next,
+ struct perf_evsel, node);
+
evlist->nr_groups = evlist->nr_entries > 1 ? 1 : 0;
- __perf_evlist__set_leader(&evlist->entries);
+ __perf_evlist__set_leader(&evlist->entries, first);
}
}
diff --git a/tools/lib/perf/evsel.c b/tools/lib/perf/evsel.c
index 8441e3e1aaac..210ea7c06ce8 100644
--- a/tools/lib/perf/evsel.c
+++ b/tools/lib/perf/evsel.c
@@ -43,18 +43,22 @@ void perf_evsel__delete(struct perf_evsel *evsel)
free(evsel);
}
-#define FD(e, x, y) ((int *) xyarray__entry(e->fd, x, y))
-#define MMAP(e, x, y) (e->mmap ? ((struct perf_mmap *) xyarray__entry(e->mmap, x, y)) : NULL)
+#define FD(_evsel, _cpu_map_idx, _thread) \
+ ((int *)xyarray__entry(_evsel->fd, _cpu_map_idx, _thread))
+#define MMAP(_evsel, _cpu_map_idx, _thread) \
+ (_evsel->mmap ? ((struct perf_mmap *) xyarray__entry(_evsel->mmap, _cpu_map_idx, _thread)) \
+ : NULL)
int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
{
evsel->fd = xyarray__new(ncpus, nthreads, sizeof(int));
if (evsel->fd) {
- int cpu, thread;
- for (cpu = 0; cpu < ncpus; cpu++) {
+ int idx, thread;
+
+ for (idx = 0; idx < ncpus; idx++) {
for (thread = 0; thread < nthreads; thread++) {
- int *fd = FD(evsel, cpu, thread);
+ int *fd = FD(evsel, idx, thread);
if (fd)
*fd = -1;
@@ -74,13 +78,13 @@ static int perf_evsel__alloc_mmap(struct perf_evsel *evsel, int ncpus, int nthre
static int
sys_perf_event_open(struct perf_event_attr *attr,
- pid_t pid, int cpu, int group_fd,
+ pid_t pid, struct perf_cpu cpu, int group_fd,
unsigned long flags)
{
- return syscall(__NR_perf_event_open, attr, pid, cpu, group_fd, flags);
+ return syscall(__NR_perf_event_open, attr, pid, cpu.cpu, group_fd, flags);
}
-static int get_group_fd(struct perf_evsel *evsel, int cpu, int thread, int *group_fd)
+static int get_group_fd(struct perf_evsel *evsel, int cpu_map_idx, int thread, int *group_fd)
{
struct perf_evsel *leader = evsel->leader;
int *fd;
@@ -97,7 +101,7 @@ static int get_group_fd(struct perf_evsel *evsel, int cpu, int thread, int *grou
if (!leader->fd)
return -ENOTCONN;
- fd = FD(leader, cpu, thread);
+ fd = FD(leader, cpu_map_idx, thread);
if (fd == NULL || *fd == -1)
return -EBADF;
@@ -109,7 +113,8 @@ static int get_group_fd(struct perf_evsel *evsel, int cpu, int thread, int *grou
int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus,
struct perf_thread_map *threads)
{
- int cpu, thread, err = 0;
+ struct perf_cpu cpu;
+ int idx, thread, err = 0;
if (cpus == NULL) {
static struct perf_cpu_map *empty_cpu_map;
@@ -136,24 +141,24 @@ int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus,
}
if (evsel->fd == NULL &&
- perf_evsel__alloc_fd(evsel, cpus->nr, threads->nr) < 0)
+ perf_evsel__alloc_fd(evsel, perf_cpu_map__nr(cpus), threads->nr) < 0)
return -ENOMEM;
- for (cpu = 0; cpu < cpus->nr; cpu++) {
+ perf_cpu_map__for_each_cpu(cpu, idx, cpus) {
for (thread = 0; thread < threads->nr; thread++) {
int fd, group_fd, *evsel_fd;
- evsel_fd = FD(evsel, cpu, thread);
+ evsel_fd = FD(evsel, idx, thread);
if (evsel_fd == NULL)
return -EINVAL;
- err = get_group_fd(evsel, cpu, thread, &group_fd);
+ err = get_group_fd(evsel, idx, thread, &group_fd);
if (err < 0)
return err;
fd = sys_perf_event_open(&evsel->attr,
threads->map[thread].pid,
- cpus->map[cpu], group_fd, 0);
+ cpu, group_fd, 0);
if (fd < 0)
return -errno;
@@ -165,12 +170,12 @@ int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus,
return err;
}
-static void perf_evsel__close_fd_cpu(struct perf_evsel *evsel, int cpu)
+static void perf_evsel__close_fd_cpu(struct perf_evsel *evsel, int cpu_map_idx)
{
int thread;
for (thread = 0; thread < xyarray__max_y(evsel->fd); ++thread) {
- int *fd = FD(evsel, cpu, thread);
+ int *fd = FD(evsel, cpu_map_idx, thread);
if (fd && *fd >= 0) {
close(*fd);
@@ -181,10 +186,8 @@ static void perf_evsel__close_fd_cpu(struct perf_evsel *evsel, int cpu)
void perf_evsel__close_fd(struct perf_evsel *evsel)
{
- int cpu;
-
- for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++)
- perf_evsel__close_fd_cpu(evsel, cpu);
+ for (int idx = 0; idx < xyarray__max_x(evsel->fd); idx++)
+ perf_evsel__close_fd_cpu(evsel, idx);
}
void perf_evsel__free_fd(struct perf_evsel *evsel)
@@ -202,29 +205,29 @@ void perf_evsel__close(struct perf_evsel *evsel)
perf_evsel__free_fd(evsel);
}
-void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu)
+void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu_map_idx)
{
if (evsel->fd == NULL)
return;
- perf_evsel__close_fd_cpu(evsel, cpu);
+ perf_evsel__close_fd_cpu(evsel, cpu_map_idx);
}
void perf_evsel__munmap(struct perf_evsel *evsel)
{
- int cpu, thread;
+ int idx, thread;
if (evsel->fd == NULL || evsel->mmap == NULL)
return;
- for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) {
+ for (idx = 0; idx < xyarray__max_x(evsel->fd); idx++) {
for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) {
- int *fd = FD(evsel, cpu, thread);
+ int *fd = FD(evsel, idx, thread);
if (fd == NULL || *fd < 0)
continue;
- perf_mmap__munmap(MMAP(evsel, cpu, thread));
+ perf_mmap__munmap(MMAP(evsel, idx, thread));
}
}
@@ -234,7 +237,7 @@ void perf_evsel__munmap(struct perf_evsel *evsel)
int perf_evsel__mmap(struct perf_evsel *evsel, int pages)
{
- int ret, cpu, thread;
+ int ret, idx, thread;
struct perf_mmap_param mp = {
.prot = PROT_READ | PROT_WRITE,
.mask = (pages * page_size) - 1,
@@ -246,15 +249,16 @@ int perf_evsel__mmap(struct perf_evsel *evsel, int pages)
if (perf_evsel__alloc_mmap(evsel, xyarray__max_x(evsel->fd), xyarray__max_y(evsel->fd)) < 0)
return -ENOMEM;
- for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) {
+ for (idx = 0; idx < xyarray__max_x(evsel->fd); idx++) {
for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) {
- int *fd = FD(evsel, cpu, thread);
+ int *fd = FD(evsel, idx, thread);
struct perf_mmap *map;
+ struct perf_cpu cpu = perf_cpu_map__cpu(evsel->cpus, idx);
if (fd == NULL || *fd < 0)
continue;
- map = MMAP(evsel, cpu, thread);
+ map = MMAP(evsel, idx, thread);
perf_mmap__init(map, NULL, false, NULL);
ret = perf_mmap__mmap(map, &mp, *fd, cpu);
@@ -268,14 +272,14 @@ int perf_evsel__mmap(struct perf_evsel *evsel, int pages)
return 0;
}
-void *perf_evsel__mmap_base(struct perf_evsel *evsel, int cpu, int thread)
+void *perf_evsel__mmap_base(struct perf_evsel *evsel, int cpu_map_idx, int thread)
{
- int *fd = FD(evsel, cpu, thread);
+ int *fd = FD(evsel, cpu_map_idx, thread);
- if (fd == NULL || *fd < 0 || MMAP(evsel, cpu, thread) == NULL)
+ if (fd == NULL || *fd < 0 || MMAP(evsel, cpu_map_idx, thread) == NULL)
return NULL;
- return MMAP(evsel, cpu, thread)->base;
+ return MMAP(evsel, cpu_map_idx, thread)->base;
}
int perf_evsel__read_size(struct perf_evsel *evsel)
@@ -303,19 +307,19 @@ int perf_evsel__read_size(struct perf_evsel *evsel)
return size;
}
-int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread,
+int perf_evsel__read(struct perf_evsel *evsel, int cpu_map_idx, int thread,
struct perf_counts_values *count)
{
size_t size = perf_evsel__read_size(evsel);
- int *fd = FD(evsel, cpu, thread);
+ int *fd = FD(evsel, cpu_map_idx, thread);
memset(count, 0, sizeof(*count));
if (fd == NULL || *fd < 0)
return -EINVAL;
- if (MMAP(evsel, cpu, thread) &&
- !perf_mmap__read_self(MMAP(evsel, cpu, thread), count))
+ if (MMAP(evsel, cpu_map_idx, thread) &&
+ !perf_mmap__read_self(MMAP(evsel, cpu_map_idx, thread), count))
return 0;
if (readn(*fd, count->values, size) <= 0)
@@ -326,13 +330,13 @@ int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread,
static int perf_evsel__run_ioctl(struct perf_evsel *evsel,
int ioc, void *arg,
- int cpu)
+ int cpu_map_idx)
{
int thread;
for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) {
int err;
- int *fd = FD(evsel, cpu, thread);
+ int *fd = FD(evsel, cpu_map_idx, thread);
if (fd == NULL || *fd < 0)
return -1;
@@ -346,9 +350,9 @@ static int perf_evsel__run_ioctl(struct perf_evsel *evsel,
return 0;
}
-int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu)
+int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu_map_idx)
{
- return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_ENABLE, NULL, cpu);
+ return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_ENABLE, NULL, cpu_map_idx);
}
int perf_evsel__enable(struct perf_evsel *evsel)
@@ -361,9 +365,9 @@ int perf_evsel__enable(struct perf_evsel *evsel)
return err;
}
-int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu)
+int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu_map_idx)
{
- return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_DISABLE, NULL, cpu);
+ return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_DISABLE, NULL, cpu_map_idx);
}
int perf_evsel__disable(struct perf_evsel *evsel)
@@ -380,7 +384,7 @@ int perf_evsel__apply_filter(struct perf_evsel *evsel, const char *filter)
{
int err = 0, i;
- for (i = 0; i < evsel->cpus->nr && !err; i++)
+ for (i = 0; i < perf_cpu_map__nr(evsel->cpus) && !err; i++)
err = perf_evsel__run_ioctl(evsel,
PERF_EVENT_IOC_SET_FILTER,
(void *)filter, i);
@@ -431,3 +435,22 @@ void perf_evsel__free_id(struct perf_evsel *evsel)
zfree(&evsel->id);
evsel->ids = 0;
}
+
+void perf_counts_values__scale(struct perf_counts_values *count,
+ bool scale, __s8 *pscaled)
+{
+ s8 scaled = 0;
+
+ if (scale) {
+ if (count->run == 0) {
+ scaled = -1;
+ count->val = 0;
+ } else if (count->run < count->ena) {
+ scaled = 1;
+ count->val = (u64)((double)count->val * count->ena / count->run);
+ }
+ }
+
+ if (pscaled)
+ *pscaled = scaled;
+}
diff --git a/tools/lib/perf/include/internal/cpumap.h b/tools/lib/perf/include/internal/cpumap.h
index 840d4032587b..1973a18c096b 100644
--- a/tools/lib/perf/include/internal/cpumap.h
+++ b/tools/lib/perf/include/internal/cpumap.h
@@ -3,17 +3,27 @@
#define __LIBPERF_INTERNAL_CPUMAP_H
#include <linux/refcount.h>
+#include <perf/cpumap.h>
+/**
+ * A sized, reference counted, sorted array of integers representing CPU
+ * numbers. This is commonly used to capture which CPUs a PMU is associated
+ * with. The indices into the cpumap are frequently used as they avoid having
+ * gaps if CPU numbers were used. For events associated with a pid, rather than
+ * a CPU, a single dummy map with an entry of -1 is used.
+ */
struct perf_cpu_map {
refcount_t refcnt;
+ /** Length of the map array. */
int nr;
- int map[];
+ /** The CPU values. */
+ struct perf_cpu map[];
};
#ifndef MAX_NR_CPUS
#define MAX_NR_CPUS 2048
#endif
-int perf_cpu_map__idx(struct perf_cpu_map *cpus, int cpu);
+int perf_cpu_map__idx(const struct perf_cpu_map *cpus, struct perf_cpu cpu);
#endif /* __LIBPERF_INTERNAL_CPUMAP_H */
diff --git a/tools/lib/perf/include/internal/evlist.h b/tools/lib/perf/include/internal/evlist.h
index f366dbad6a88..4cefade540bd 100644
--- a/tools/lib/perf/include/internal/evlist.h
+++ b/tools/lib/perf/include/internal/evlist.h
@@ -4,6 +4,7 @@
#include <linux/list.h>
#include <api/fd/array.h>
+#include <internal/cpumap.h>
#include <internal/evsel.h>
#define PERF_EVLIST__HLIST_BITS 8
@@ -36,7 +37,7 @@ typedef void
typedef struct perf_mmap*
(*perf_evlist_mmap__cb_get_t)(struct perf_evlist*, bool, int);
typedef int
-(*perf_evlist_mmap__cb_mmap_t)(struct perf_mmap*, struct perf_mmap_param*, int, int);
+(*perf_evlist_mmap__cb_mmap_t)(struct perf_mmap*, struct perf_mmap_param*, int, struct perf_cpu);
struct perf_evlist_mmap_ops {
perf_evlist_mmap__cb_idx_t idx;
@@ -127,5 +128,5 @@ int perf_evlist__id_add_fd(struct perf_evlist *evlist,
void perf_evlist__reset_id_hash(struct perf_evlist *evlist);
-void __perf_evlist__set_leader(struct list_head *list);
+void __perf_evlist__set_leader(struct list_head *list, struct perf_evsel *leader);
#endif /* __LIBPERF_INTERNAL_EVLIST_H */
diff --git a/tools/lib/perf/include/internal/evsel.h b/tools/lib/perf/include/internal/evsel.h
index 1f3eacbad2e8..cfc9ebd7968e 100644
--- a/tools/lib/perf/include/internal/evsel.h
+++ b/tools/lib/perf/include/internal/evsel.h
@@ -6,8 +6,8 @@
#include <linux/perf_event.h>
#include <stdbool.h>
#include <sys/types.h>
+#include <internal/cpumap.h>
-struct perf_cpu_map;
struct perf_thread_map;
struct xyarray;
@@ -27,7 +27,7 @@ struct perf_sample_id {
* queue number.
*/
int idx;
- int cpu;
+ struct perf_cpu cpu;
pid_t tid;
/* Holds total ID period value for PERF_SAMPLE_READ processing. */
diff --git a/tools/lib/perf/include/internal/mmap.h b/tools/lib/perf/include/internal/mmap.h
index 5e3422f40ed5..5a062af8e9d8 100644
--- a/tools/lib/perf/include/internal/mmap.h
+++ b/tools/lib/perf/include/internal/mmap.h
@@ -6,6 +6,7 @@
#include <linux/refcount.h>
#include <linux/types.h>
#include <stdbool.h>
+#include <internal/cpumap.h>
/* perf sample has 16 bits size limit */
#define PERF_SAMPLE_MAX_SIZE (1 << 16)
@@ -24,7 +25,7 @@ struct perf_mmap {
void *base;
int mask;
int fd;
- int cpu;
+ struct perf_cpu cpu;
refcount_t refcnt;
u64 prev;
u64 start;
@@ -46,7 +47,7 @@ size_t perf_mmap__mmap_len(struct perf_mmap *map);
void perf_mmap__init(struct perf_mmap *map, struct perf_mmap *prev,
bool overwrite, libperf_unmap_cb_t unmap_cb);
int perf_mmap__mmap(struct perf_mmap *map, struct perf_mmap_param *mp,
- int fd, int cpu);
+ int fd, struct perf_cpu cpu);
void perf_mmap__munmap(struct perf_mmap *map);
void perf_mmap__get(struct perf_mmap *map);
void perf_mmap__put(struct perf_mmap *map);
diff --git a/tools/lib/perf/include/perf/cpumap.h b/tools/lib/perf/include/perf/cpumap.h
index 7c27766ea0bf..4a2edbdb5e2b 100644
--- a/tools/lib/perf/include/perf/cpumap.h
+++ b/tools/lib/perf/include/perf/cpumap.h
@@ -3,10 +3,14 @@
#define __LIBPERF_CPUMAP_H
#include <perf/core.h>
+#include <perf/cpumap.h>
#include <stdio.h>
#include <stdbool.h>
-struct perf_cpu_map;
+/** A wrapper around a CPU to avoid confusion with the perf_cpu_map's map's indices. */
+struct perf_cpu {
+ int cpu;
+};
LIBPERF_API struct perf_cpu_map *perf_cpu_map__dummy_new(void);
LIBPERF_API struct perf_cpu_map *perf_cpu_map__default_new(void);
@@ -16,10 +20,11 @@ LIBPERF_API struct perf_cpu_map *perf_cpu_map__get(struct perf_cpu_map *map);
LIBPERF_API struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig,
struct perf_cpu_map *other);
LIBPERF_API void perf_cpu_map__put(struct perf_cpu_map *map);
-LIBPERF_API int perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx);
+LIBPERF_API struct perf_cpu perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx);
LIBPERF_API int perf_cpu_map__nr(const struct perf_cpu_map *cpus);
LIBPERF_API bool perf_cpu_map__empty(const struct perf_cpu_map *map);
-LIBPERF_API int perf_cpu_map__max(struct perf_cpu_map *map);
+LIBPERF_API struct perf_cpu perf_cpu_map__max(struct perf_cpu_map *map);
+LIBPERF_API bool perf_cpu_map__has(const struct perf_cpu_map *map, struct perf_cpu cpu);
#define perf_cpu_map__for_each_cpu(cpu, idx, cpus) \
for ((idx) = 0, (cpu) = perf_cpu_map__cpu(cpus, idx); \
diff --git a/tools/lib/perf/include/perf/evsel.h b/tools/lib/perf/include/perf/evsel.h
index 60eae25076d3..2a9516b42d15 100644
--- a/tools/lib/perf/include/perf/evsel.h
+++ b/tools/lib/perf/include/perf/evsel.h
@@ -4,6 +4,8 @@
#include <stdint.h>
#include <perf/core.h>
+#include <stdbool.h>
+#include <linux/types.h>
struct perf_evsel;
struct perf_event_attr;
@@ -26,18 +28,20 @@ LIBPERF_API void perf_evsel__delete(struct perf_evsel *evsel);
LIBPERF_API int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus,
struct perf_thread_map *threads);
LIBPERF_API void perf_evsel__close(struct perf_evsel *evsel);
-LIBPERF_API void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu);
+LIBPERF_API void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu_map_idx);
LIBPERF_API int perf_evsel__mmap(struct perf_evsel *evsel, int pages);
LIBPERF_API void perf_evsel__munmap(struct perf_evsel *evsel);
-LIBPERF_API void *perf_evsel__mmap_base(struct perf_evsel *evsel, int cpu, int thread);
-LIBPERF_API int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread,
+LIBPERF_API void *perf_evsel__mmap_base(struct perf_evsel *evsel, int cpu_map_idx, int thread);
+LIBPERF_API int perf_evsel__read(struct perf_evsel *evsel, int cpu_map_idx, int thread,
struct perf_counts_values *count);
LIBPERF_API int perf_evsel__enable(struct perf_evsel *evsel);
-LIBPERF_API int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu);
+LIBPERF_API int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu_map_idx);
LIBPERF_API int perf_evsel__disable(struct perf_evsel *evsel);
-LIBPERF_API int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu);
+LIBPERF_API int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu_map_idx);
LIBPERF_API struct perf_cpu_map *perf_evsel__cpus(struct perf_evsel *evsel);
LIBPERF_API struct perf_thread_map *perf_evsel__threads(struct perf_evsel *evsel);
LIBPERF_API struct perf_event_attr *perf_evsel__attr(struct perf_evsel *evsel);
+LIBPERF_API void perf_counts_values__scale(struct perf_counts_values *count,
+ bool scale, __s8 *pscaled);
#endif /* __LIBPERF_EVSEL_H */
diff --git a/tools/lib/perf/libperf.map b/tools/lib/perf/libperf.map
index 71468606e8a7..6fa0d651576b 100644
--- a/tools/lib/perf/libperf.map
+++ b/tools/lib/perf/libperf.map
@@ -2,6 +2,7 @@ LIBPERF_0.0.1 {
global:
libperf_init;
perf_cpu_map__dummy_new;
+ perf_cpu_map__default_new;
perf_cpu_map__get;
perf_cpu_map__put;
perf_cpu_map__new;
@@ -10,6 +11,7 @@ LIBPERF_0.0.1 {
perf_cpu_map__cpu;
perf_cpu_map__empty;
perf_cpu_map__max;
+ perf_cpu_map__has;
perf_thread_map__new_dummy;
perf_thread_map__set_pid;
perf_thread_map__comm;
@@ -50,6 +52,7 @@ LIBPERF_0.0.1 {
perf_mmap__read_init;
perf_mmap__read_done;
perf_mmap__read_event;
+ perf_counts_values__scale;
local:
*;
};
diff --git a/tools/lib/perf/mmap.c b/tools/lib/perf/mmap.c
index c89dfa5f67b3..0d1634cedf44 100644
--- a/tools/lib/perf/mmap.c
+++ b/tools/lib/perf/mmap.c
@@ -13,6 +13,7 @@
#include <internal/lib.h>
#include <linux/kernel.h>
#include <linux/math64.h>
+#include <linux/stringify.h>
#include "internal.h"
void perf_mmap__init(struct perf_mmap *map, struct perf_mmap *prev,
@@ -32,7 +33,7 @@ size_t perf_mmap__mmap_len(struct perf_mmap *map)
}
int perf_mmap__mmap(struct perf_mmap *map, struct perf_mmap_param *mp,
- int fd, int cpu)
+ int fd, struct perf_cpu cpu)
{
map->prev = 0;
map->mask = mp->mask;
@@ -294,6 +295,103 @@ static u64 read_timestamp(void)
return low | ((u64)high) << 32;
}
+#elif defined(__aarch64__)
+#define read_sysreg(r) ({ \
+ u64 __val; \
+ asm volatile("mrs %0, " __stringify(r) : "=r" (__val)); \
+ __val; \
+})
+
+static u64 read_pmccntr(void)
+{
+ return read_sysreg(pmccntr_el0);
+}
+
+#define PMEVCNTR_READ(idx) \
+ static u64 read_pmevcntr_##idx(void) { \
+ return read_sysreg(pmevcntr##idx##_el0); \
+ }
+
+PMEVCNTR_READ(0);
+PMEVCNTR_READ(1);
+PMEVCNTR_READ(2);
+PMEVCNTR_READ(3);
+PMEVCNTR_READ(4);
+PMEVCNTR_READ(5);
+PMEVCNTR_READ(6);
+PMEVCNTR_READ(7);
+PMEVCNTR_READ(8);
+PMEVCNTR_READ(9);
+PMEVCNTR_READ(10);
+PMEVCNTR_READ(11);
+PMEVCNTR_READ(12);
+PMEVCNTR_READ(13);
+PMEVCNTR_READ(14);
+PMEVCNTR_READ(15);
+PMEVCNTR_READ(16);
+PMEVCNTR_READ(17);
+PMEVCNTR_READ(18);
+PMEVCNTR_READ(19);
+PMEVCNTR_READ(20);
+PMEVCNTR_READ(21);
+PMEVCNTR_READ(22);
+PMEVCNTR_READ(23);
+PMEVCNTR_READ(24);
+PMEVCNTR_READ(25);
+PMEVCNTR_READ(26);
+PMEVCNTR_READ(27);
+PMEVCNTR_READ(28);
+PMEVCNTR_READ(29);
+PMEVCNTR_READ(30);
+
+/*
+ * Read a value direct from PMEVCNTR<idx>
+ */
+static u64 read_perf_counter(unsigned int counter)
+{
+ static u64 (* const read_f[])(void) = {
+ read_pmevcntr_0,
+ read_pmevcntr_1,
+ read_pmevcntr_2,
+ read_pmevcntr_3,
+ read_pmevcntr_4,
+ read_pmevcntr_5,
+ read_pmevcntr_6,
+ read_pmevcntr_7,
+ read_pmevcntr_8,
+ read_pmevcntr_9,
+ read_pmevcntr_10,
+ read_pmevcntr_11,
+ read_pmevcntr_13,
+ read_pmevcntr_12,
+ read_pmevcntr_14,
+ read_pmevcntr_15,
+ read_pmevcntr_16,
+ read_pmevcntr_17,
+ read_pmevcntr_18,
+ read_pmevcntr_19,
+ read_pmevcntr_20,
+ read_pmevcntr_21,
+ read_pmevcntr_22,
+ read_pmevcntr_23,
+ read_pmevcntr_24,
+ read_pmevcntr_25,
+ read_pmevcntr_26,
+ read_pmevcntr_27,
+ read_pmevcntr_28,
+ read_pmevcntr_29,
+ read_pmevcntr_30,
+ read_pmccntr
+ };
+
+ if (counter < ARRAY_SIZE(read_f))
+ return (read_f[counter])();
+
+ return 0;
+}
+
+static u64 read_timestamp(void) { return read_sysreg(cntvct_el0); }
+
#else
static u64 read_perf_counter(unsigned int counter __maybe_unused) { return 0; }
static u64 read_timestamp(void) { return 0; }
@@ -353,8 +451,6 @@ int perf_mmap__read_self(struct perf_mmap *map, struct perf_counts_values *count
count->ena += delta;
if (idx)
count->run += delta;
-
- cnt = mul_u64_u64_div64(cnt, count->ena, count->run);
}
count->val = cnt;
diff --git a/tools/lib/perf/tests/test-cpumap.c b/tools/lib/perf/tests/test-cpumap.c
index d39378eaf897..87b0510a556f 100644
--- a/tools/lib/perf/tests/test-cpumap.c
+++ b/tools/lib/perf/tests/test-cpumap.c
@@ -14,6 +14,8 @@ static int libperf_print(enum libperf_print_level level,
int test_cpumap(int argc, char **argv)
{
struct perf_cpu_map *cpus;
+ struct perf_cpu cpu;
+ int idx;
__T_START;
@@ -27,6 +29,15 @@ int test_cpumap(int argc, char **argv)
perf_cpu_map__put(cpus);
perf_cpu_map__put(cpus);
+ cpus = perf_cpu_map__default_new();
+ if (!cpus)
+ return -1;
+
+ perf_cpu_map__for_each_cpu(cpu, idx, cpus)
+ __T("wrong cpu number", cpu.cpu != -1);
+
+ perf_cpu_map__put(cpus);
+
__T_END;
return tests_failed == 0 ? 0 : -1;
}
diff --git a/tools/lib/perf/tests/test-evlist.c b/tools/lib/perf/tests/test-evlist.c
index ce91a582f0e4..fa854c83b7e7 100644
--- a/tools/lib/perf/tests/test-evlist.c
+++ b/tools/lib/perf/tests/test-evlist.c
@@ -1,5 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
#define _GNU_SOURCE // needed for sched.h to get sched_[gs]etaffinity and CPU_(ZERO,SET)
+#include <inttypes.h>
#include <sched.h>
#include <stdio.h>
#include <stdarg.h>
@@ -21,6 +22,9 @@
#include "tests.h"
#include <internal/evsel.h>
+#define EVENT_NUM 15
+#define WAIT_COUNT 100000000UL
+
static int libperf_print(enum libperf_print_level level,
const char *fmt, va_list ap)
{
@@ -331,7 +335,8 @@ static int test_mmap_cpus(void)
};
cpu_set_t saved_mask;
char path[PATH_MAX];
- int id, err, cpu, tmp;
+ int id, err, tmp;
+ struct perf_cpu cpu;
union perf_event *event;
int count = 0;
@@ -374,7 +379,7 @@ static int test_mmap_cpus(void)
cpu_set_t mask;
CPU_ZERO(&mask);
- CPU_SET(cpu, &mask);
+ CPU_SET(cpu.cpu, &mask);
err = sched_setaffinity(0, sizeof(mask), &mask);
__T("sched_setaffinity failed", err == 0);
@@ -413,6 +418,159 @@ static int test_mmap_cpus(void)
return 0;
}
+static double display_error(long long average,
+ long long high,
+ long long low,
+ long long expected)
+{
+ double error;
+
+ error = (((double)average - expected) / expected) * 100.0;
+
+ __T_VERBOSE(" Expected: %lld\n", expected);
+ __T_VERBOSE(" High: %lld Low: %lld Average: %lld\n",
+ high, low, average);
+
+ __T_VERBOSE(" Average Error = %.2f%%\n", error);
+
+ return error;
+}
+
+static int test_stat_multiplexing(void)
+{
+ struct perf_counts_values expected_counts = { .val = 0 };
+ struct perf_counts_values counts[EVENT_NUM] = {{ .val = 0 },};
+ struct perf_thread_map *threads;
+ struct perf_evlist *evlist;
+ struct perf_evsel *evsel;
+ struct perf_event_attr attr = {
+ .type = PERF_TYPE_HARDWARE,
+ .config = PERF_COUNT_HW_INSTRUCTIONS,
+ .read_format = PERF_FORMAT_TOTAL_TIME_ENABLED |
+ PERF_FORMAT_TOTAL_TIME_RUNNING,
+ .disabled = 1,
+ };
+ int err, i, nonzero = 0;
+ unsigned long count;
+ long long max = 0, min = 0, avg = 0;
+ double error = 0.0;
+ s8 scaled = 0;
+
+ /* read for non-multiplexing event count */
+ threads = perf_thread_map__new_dummy();
+ __T("failed to create threads", threads);
+
+ perf_thread_map__set_pid(threads, 0, 0);
+
+ evsel = perf_evsel__new(&attr);
+ __T("failed to create evsel", evsel);
+
+ err = perf_evsel__open(evsel, NULL, threads);
+ __T("failed to open evsel", err == 0);
+
+ err = perf_evsel__enable(evsel);
+ __T("failed to enable evsel", err == 0);
+
+ /* wait loop */
+ count = WAIT_COUNT;
+ while (count--)
+ ;
+
+ perf_evsel__read(evsel, 0, 0, &expected_counts);
+ __T("failed to read value for evsel", expected_counts.val != 0);
+ __T("failed to read non-multiplexing event count",
+ expected_counts.ena == expected_counts.run);
+
+ err = perf_evsel__disable(evsel);
+ __T("failed to enable evsel", err == 0);
+
+ perf_evsel__close(evsel);
+ perf_evsel__delete(evsel);
+
+ perf_thread_map__put(threads);
+
+ /* read for multiplexing event count */
+ threads = perf_thread_map__new_dummy();
+ __T("failed to create threads", threads);
+
+ perf_thread_map__set_pid(threads, 0, 0);
+
+ evlist = perf_evlist__new();
+ __T("failed to create evlist", evlist);
+
+ for (i = 0; i < EVENT_NUM; i++) {
+ evsel = perf_evsel__new(&attr);
+ __T("failed to create evsel", evsel);
+
+ perf_evlist__add(evlist, evsel);
+ }
+ perf_evlist__set_maps(evlist, NULL, threads);
+
+ err = perf_evlist__open(evlist);
+ __T("failed to open evsel", err == 0);
+
+ perf_evlist__enable(evlist);
+
+ /* wait loop */
+ count = WAIT_COUNT;
+ while (count--)
+ ;
+
+ i = 0;
+ perf_evlist__for_each_evsel(evlist, evsel) {
+ perf_evsel__read(evsel, 0, 0, &counts[i]);
+ __T("failed to read value for evsel", counts[i].val != 0);
+ i++;
+ }
+
+ perf_evlist__disable(evlist);
+
+ min = counts[0].val;
+ for (i = 0; i < EVENT_NUM; i++) {
+ __T_VERBOSE("Event %2d -- Raw count = %" PRIu64 ", run = %" PRIu64 ", enable = %" PRIu64 "\n",
+ i, counts[i].val, counts[i].run, counts[i].ena);
+
+ perf_counts_values__scale(&counts[i], true, &scaled);
+ if (scaled == 1) {
+ __T_VERBOSE("\t Scaled count = %" PRIu64 " (%.2lf%%, %" PRIu64 "/%" PRIu64 ")\n",
+ counts[i].val,
+ (double)counts[i].run / (double)counts[i].ena * 100.0,
+ counts[i].run, counts[i].ena);
+ } else if (scaled == -1) {
+ __T_VERBOSE("\t Not Running\n");
+ } else {
+ __T_VERBOSE("\t Not Scaling\n");
+ }
+
+ if (counts[i].val > max)
+ max = counts[i].val;
+
+ if (counts[i].val < min)
+ min = counts[i].val;
+
+ avg += counts[i].val;
+
+ if (counts[i].val != 0)
+ nonzero++;
+ }
+
+ if (nonzero != 0)
+ avg = avg / nonzero;
+ else
+ avg = 0;
+
+ error = display_error(avg, max, min, expected_counts.val);
+
+ __T("Error out of range!", ((error <= 1.0) && (error >= -1.0)));
+
+ perf_evlist__close(evlist);
+ perf_evlist__delete(evlist);
+
+ perf_thread_map__put(threads);
+
+ return 0;
+}
+
int test_evlist(int argc, char **argv)
{
__T_START;
@@ -424,6 +582,7 @@ int test_evlist(int argc, char **argv)
test_stat_thread_enable();
test_mmap_thread();
test_mmap_cpus();
+ test_stat_multiplexing();
__T_END;
return tests_failed == 0 ? 0 : -1;
diff --git a/tools/lib/perf/tests/test-evsel.c b/tools/lib/perf/tests/test-evsel.c
index 33ae9334861a..89be89afb24d 100644
--- a/tools/lib/perf/tests/test-evsel.c
+++ b/tools/lib/perf/tests/test-evsel.c
@@ -130,6 +130,9 @@ static int test_stat_user_read(int event)
struct perf_event_attr attr = {
.type = PERF_TYPE_HARDWARE,
.config = event,
+#ifdef __aarch64__
+ .config1 = 0x2, /* Request user access */
+#endif
};
int err, i;
@@ -150,7 +153,7 @@ static int test_stat_user_read(int event)
pc = perf_evsel__mmap_base(evsel, 0, 0);
__T("failed to get mmapped address", pc);
-#if defined(__i386__) || defined(__x86_64__)
+#if defined(__i386__) || defined(__x86_64__) || defined(__aarch64__)
__T("userspace counter access not supported", pc->cap_user_rdpmc);
__T("userspace counter access not enabled", pc->index);
__T("userspace counter width not set", pc->pmc_width >= 32);
diff --git a/tools/lib/subcmd/subcmd-util.h b/tools/lib/subcmd/subcmd-util.h
index 794a375dad36..b2aec04fce8f 100644
--- a/tools/lib/subcmd/subcmd-util.h
+++ b/tools/lib/subcmd/subcmd-util.h
@@ -50,15 +50,8 @@ static NORETURN inline void die(const char *err, ...)
static inline void *xrealloc(void *ptr, size_t size)
{
void *ret = realloc(ptr, size);
- if (!ret && !size)
- ret = realloc(ptr, 1);
- if (!ret) {
- ret = realloc(ptr, size);
- if (!ret && !size)
- ret = realloc(ptr, 1);
- if (!ret)
- die("Out of memory, realloc failed");
- }
+ if (!ret)
+ die("Out of memory, realloc failed");
return ret;
}
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index fe58843d047c..8e24c4c78c7f 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -1367,6 +1367,14 @@ static int field_is_dynamic(struct tep_format_field *field)
return 0;
}
+static int field_is_relative_dynamic(struct tep_format_field *field)
+{
+ if (strncmp(field->type, "__rel_loc", 9) == 0)
+ return 1;
+
+ return 0;
+}
+
static int field_is_long(struct tep_format_field *field)
{
/* includes long long */
@@ -1622,6 +1630,8 @@ static int event_read_fields(struct tep_event *event, struct tep_format_field **
field->flags |= TEP_FIELD_IS_STRING;
if (field_is_dynamic(field))
field->flags |= TEP_FIELD_IS_DYNAMIC;
+ if (field_is_relative_dynamic(field))
+ field->flags |= TEP_FIELD_IS_DYNAMIC | TEP_FIELD_IS_RELATIVE;
if (field_is_long(field))
field->flags |= TEP_FIELD_IS_LONG;
@@ -2928,7 +2938,7 @@ process_str(struct tep_event *event __maybe_unused, struct tep_print_arg *arg,
arg->type = TEP_PRINT_STRING;
arg->string.string = token;
- arg->string.offset = -1;
+ arg->string.field = NULL;
if (read_expected(TEP_EVENT_DELIM, ")") < 0)
goto out_err;
@@ -2957,7 +2967,7 @@ process_bitmask(struct tep_event *event __maybe_unused, struct tep_print_arg *ar
arg->type = TEP_PRINT_BITMASK;
arg->bitmask.bitmask = token;
- arg->bitmask.offset = -1;
+ arg->bitmask.field = NULL;
if (read_expected(TEP_EVENT_DELIM, ")") < 0)
goto out_err;
@@ -3123,19 +3133,23 @@ process_function(struct tep_event *event, struct tep_print_arg *arg,
free_token(token);
return process_int_array(event, arg, tok);
}
- if (strcmp(token, "__get_str") == 0) {
+ if (strcmp(token, "__get_str") == 0 ||
+ strcmp(token, "__get_rel_str") == 0) {
free_token(token);
return process_str(event, arg, tok);
}
- if (strcmp(token, "__get_bitmask") == 0) {
+ if (strcmp(token, "__get_bitmask") == 0 ||
+ strcmp(token, "__get_rel_bitmask") == 0) {
free_token(token);
return process_bitmask(event, arg, tok);
}
- if (strcmp(token, "__get_dynamic_array") == 0) {
+ if (strcmp(token, "__get_dynamic_array") == 0 ||
+ strcmp(token, "__get_rel_dynamic_array") == 0) {
free_token(token);
return process_dynamic_array(event, arg, tok);
}
- if (strcmp(token, "__get_dynamic_array_len") == 0) {
+ if (strcmp(token, "__get_dynamic_array_len") == 0 ||
+ strcmp(token, "__get_rel_dynamic_array_len") == 0) {
free_token(token);
return process_dynamic_array_len(event, arg, tok);
}
@@ -4163,14 +4177,16 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
case TEP_PRINT_STRING: {
int str_offset;
- if (arg->string.offset == -1) {
- struct tep_format_field *f;
+ if (!arg->string.field)
+ arg->string.field = tep_find_any_field(event, arg->string.string);
+ if (!arg->string.field)
+ break;
- f = tep_find_any_field(event, arg->string.string);
- arg->string.offset = f->offset;
- }
- str_offset = data2host4(tep, *(unsigned int *)(data + arg->string.offset));
+ str_offset = data2host4(tep,
+ *(unsigned int *)(data + arg->string.field->offset));
str_offset &= 0xffff;
+ if (arg->string.field->flags & TEP_FIELD_IS_RELATIVE)
+ str_offset += arg->string.field->offset + arg->string.field->size;
print_str_to_seq(s, format, len_arg, ((char *)data) + str_offset);
break;
}
@@ -4181,15 +4197,16 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
int bitmask_offset;
int bitmask_size;
- if (arg->bitmask.offset == -1) {
- struct tep_format_field *f;
-
- f = tep_find_any_field(event, arg->bitmask.bitmask);
- arg->bitmask.offset = f->offset;
- }
- bitmask_offset = data2host4(tep, *(unsigned int *)(data + arg->bitmask.offset));
+ if (!arg->bitmask.field)
+ arg->bitmask.field = tep_find_any_field(event, arg->bitmask.bitmask);
+ if (!arg->bitmask.field)
+ break;
+ bitmask_offset = data2host4(tep,
+ *(unsigned int *)(data + arg->bitmask.field->offset));
bitmask_size = bitmask_offset >> 16;
bitmask_offset &= 0xffff;
+ if (arg->bitmask.field->flags & TEP_FIELD_IS_RELATIVE)
+ bitmask_offset += arg->bitmask.field->offset + arg->bitmask.field->size;
print_bitmask_to_seq(tep, s, format, len_arg,
data + bitmask_offset, bitmask_size);
break;
@@ -5109,6 +5126,8 @@ void tep_print_field(struct trace_seq *s, void *data,
offset = val;
len = offset >> 16;
offset &= 0xffff;
+ if (field->flags & TEP_FIELD_IS_RELATIVE)
+ offset += field->offset + field->size;
}
if (field->flags & TEP_FIELD_IS_STRING &&
is_printable_array(data + offset, len)) {
@@ -6987,6 +7006,8 @@ void *tep_get_field_raw(struct trace_seq *s, struct tep_event *event,
data + offset, field->size);
*len = offset >> 16;
offset &= 0xffff;
+ if (field->flags & TEP_FIELD_IS_RELATIVE)
+ offset += field->offset + field->size;
} else
*len = field->size;
diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index a67ad9a5b835..41d4f9f6a843 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -125,6 +125,7 @@ enum tep_format_flags {
TEP_FIELD_IS_LONG = 32,
TEP_FIELD_IS_FLAG = 64,
TEP_FIELD_IS_SYMBOLIC = 128,
+ TEP_FIELD_IS_RELATIVE = 256,
};
struct tep_format_field {
@@ -153,12 +154,12 @@ struct tep_print_arg_atom {
struct tep_print_arg_string {
char *string;
- int offset;
+ struct tep_format_field *field;
};
struct tep_print_arg_bitmask {
char *bitmask;
- int offset;
+ struct tep_format_field *field;
};
struct tep_print_arg_field {
diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c
index 368826bb5a57..5df177070d53 100644
--- a/tools/lib/traceevent/parse-filter.c
+++ b/tools/lib/traceevent/parse-filter.c
@@ -1712,8 +1712,11 @@ static const char *get_field_str(struct tep_filter_arg *arg, struct tep_record *
if (arg->str.field->flags & TEP_FIELD_IS_DYNAMIC) {
addr = *(unsigned int *)val;
- val = record->data + (addr & 0xffff);
size = addr >> 16;
+ addr &= 0xffff;
+ if (arg->str.field->flags & TEP_FIELD_IS_RELATIVE)
+ addr += arg->str.field->offset + arg->str.field->size;
+ val = record->data + addr;
}
/*
diff --git a/tools/memory-model/Documentation/explanation.txt b/tools/memory-model/Documentation/explanation.txt
index 5d72f3112e56..ee819a402b69 100644
--- a/tools/memory-model/Documentation/explanation.txt
+++ b/tools/memory-model/Documentation/explanation.txt
@@ -485,6 +485,57 @@ have R ->po X. It wouldn't make sense for a computation to depend
somehow on a value that doesn't get loaded from shared memory until
later in the code!
+Here's a trick question: When is a dependency not a dependency? Answer:
+When it is purely syntactic rather than semantic. We say a dependency
+between two accesses is purely syntactic if the second access doesn't
+actually depend on the result of the first. Here is a trivial example:
+
+ r1 = READ_ONCE(x);
+ WRITE_ONCE(y, r1 * 0);
+
+There appears to be a data dependency from the load of x to the store
+of y, since the value to be stored is computed from the value that was
+loaded. But in fact, the value stored does not really depend on
+anything since it will always be 0. Thus the data dependency is only
+syntactic (it appears to exist in the code) but not semantic (the
+second access will always be the same, regardless of the value of the
+first access). Given code like this, a compiler could simply discard
+the value returned by the load from x, which would certainly destroy
+any dependency. (The compiler is not permitted to eliminate entirely
+the load generated for a READ_ONCE() -- that's one of the nice
+properties of READ_ONCE() -- but it is allowed to ignore the load's
+value.)
+
+It's natural to object that no one in their right mind would write
+code like the above. However, macro expansions can easily give rise
+to this sort of thing, in ways that often are not apparent to the
+programmer.
+
+Another mechanism that can lead to purely syntactic dependencies is
+related to the notion of "undefined behavior". Certain program
+behaviors are called "undefined" in the C language specification,
+which means that when they occur there are no guarantees at all about
+the outcome. Consider the following example:
+
+ int a[1];
+ int i;
+
+ r1 = READ_ONCE(i);
+ r2 = READ_ONCE(a[r1]);
+
+Access beyond the end or before the beginning of an array is one kind
+of undefined behavior. Therefore the compiler doesn't have to worry
+about what will happen if r1 is nonzero, and it can assume that r1
+will always be zero regardless of the value actually loaded from i.
+(If the assumption turns out to be wrong the resulting behavior will
+be undefined anyway, so the compiler doesn't care!) Thus the value
+from the load can be discarded, breaking the address dependency.
+
+The LKMM is unaware that purely syntactic dependencies are different
+from semantic dependencies and therefore mistakenly predicts that the
+accesses in the two examples above will be ordered. This is another
+example of how the compiler can undermine the memory model. Be warned.
+
THE READS-FROM RELATION: rf, rfi, and rfe
-----------------------------------------
@@ -1813,15 +1864,16 @@ spin_trylock() -- we can call these things lock-releases and
lock-acquires -- have two properties beyond those of ordinary releases
and acquires.
-First, when a lock-acquire reads from a lock-release, the LKMM
-requires that every instruction po-before the lock-release must
-execute before any instruction po-after the lock-acquire. This would
-naturally hold if the release and acquire operations were on different
-CPUs, but the LKMM says it holds even when they are on the same CPU.
-For example:
+First, when a lock-acquire reads from or is po-after a lock-release,
+the LKMM requires that every instruction po-before the lock-release
+must execute before any instruction po-after the lock-acquire. This
+would naturally hold if the release and acquire operations were on
+different CPUs and accessed the same lock variable, but the LKMM says
+it also holds when they are on the same CPU, even if they access
+different lock variables. For example:
int x, y;
- spinlock_t s;
+ spinlock_t s, t;
P0()
{
@@ -1830,9 +1882,9 @@ For example:
spin_lock(&s);
r1 = READ_ONCE(x);
spin_unlock(&s);
- spin_lock(&s);
+ spin_lock(&t);
r2 = READ_ONCE(y);
- spin_unlock(&s);
+ spin_unlock(&t);
}
P1()
@@ -1842,10 +1894,10 @@ For example:
WRITE_ONCE(x, 1);
}
-Here the second spin_lock() reads from the first spin_unlock(), and
-therefore the load of x must execute before the load of y. Thus we
-cannot have r1 = 1 and r2 = 0 at the end (this is an instance of the
-MP pattern).
+Here the second spin_lock() is po-after the first spin_unlock(), and
+therefore the load of x must execute before the load of y, even though
+the two locking operations use different locks. Thus we cannot have
+r1 = 1 and r2 = 0 at the end (this is an instance of the MP pattern).
This requirement does not apply to ordinary release and acquire
fences, only to lock-related operations. For instance, suppose P0()
@@ -1872,13 +1924,13 @@ instructions in the following order:
and thus it could load y before x, obtaining r2 = 0 and r1 = 1.
-Second, when a lock-acquire reads from a lock-release, and some other
-stores W and W' occur po-before the lock-release and po-after the
-lock-acquire respectively, the LKMM requires that W must propagate to
-each CPU before W' does. For example, consider:
+Second, when a lock-acquire reads from or is po-after a lock-release,
+and some other stores W and W' occur po-before the lock-release and
+po-after the lock-acquire respectively, the LKMM requires that W must
+propagate to each CPU before W' does. For example, consider:
int x, y;
- spinlock_t x;
+ spinlock_t s;
P0()
{
@@ -1908,7 +1960,12 @@ each CPU before W' does. For example, consider:
If r1 = 1 at the end then the spin_lock() in P1 must have read from
the spin_unlock() in P0. Hence the store to x must propagate to P2
-before the store to y does, so we cannot have r2 = 1 and r3 = 0.
+before the store to y does, so we cannot have r2 = 1 and r3 = 0. But
+if P1 had used a lock variable different from s, the writes could have
+propagated in either order. (On the other hand, if the code in P0 and
+P1 had all executed on a single CPU, as in the example before this
+one, then the writes would have propagated in order even if the two
+critical sections used different lock variables.)
These two special requirements for lock-release and lock-acquire do
not arise from the operational model. Nevertheless, kernel developers
diff --git a/tools/memory-model/README b/tools/memory-model/README
index 9a84c45504ab..9edd402704c4 100644
--- a/tools/memory-model/README
+++ b/tools/memory-model/README
@@ -195,6 +195,18 @@ litmus-tests
are listed in litmus-tests/README. A great deal more litmus
tests are available at https://github.com/paulmckrcu/litmus.
+ By "representative", it means the one in the litmus-tests
+ directory is:
+
+ 1) simple, the number of threads should be relatively
+ small and each thread function should be relatively
+ simple.
+ 2) orthogonal, there should be no two litmus tests
+ describing the same aspect of the memory model.
+ 3) textbook, developers can easily copy-paste-modify
+ the litmus tests to use the patterns on their own
+ code.
+
lock.cat
Provides a front-end analysis of lock acquisition and release,
for example, associating a lock acquisition with the preceding
diff --git a/tools/memory-model/linux-kernel.cat b/tools/memory-model/linux-kernel.cat
index 2a9b4fe4a84e..d70315fddef6 100644
--- a/tools/memory-model/linux-kernel.cat
+++ b/tools/memory-model/linux-kernel.cat
@@ -27,7 +27,7 @@ include "lock.cat"
(* Release Acquire *)
let acq-po = [Acquire] ; po ; [M]
let po-rel = [M] ; po ; [Release]
-let po-unlock-rf-lock-po = po ; [UL] ; rf ; [LKR] ; po
+let po-unlock-lock-po = po ; [UL] ; (po|rf) ; [LKR] ; po
(* Fences *)
let R4rmb = R \ Noreturn (* Reads for which rmb works *)
@@ -70,12 +70,12 @@ let rwdep = (dep | ctrl) ; [W]
let overwrite = co | fr
let to-w = rwdep | (overwrite & int) | (addr ; [Plain] ; wmb)
let to-r = addr | (dep ; [Marked] ; rfi)
-let ppo = to-r | to-w | fence | (po-unlock-rf-lock-po & int)
+let ppo = to-r | to-w | fence | (po-unlock-lock-po & int)
(* Propagation: Ordering from release operations and strong fences. *)
let A-cumul(r) = (rfe ; [Marked])? ; r
let cumul-fence = [Marked] ; (A-cumul(strong-fence | po-rel) | wmb |
- po-unlock-rf-lock-po) ; [Marked]
+ po-unlock-lock-po) ; [Marked]
let prop = [Marked] ; (overwrite & ext)? ; cumul-fence* ;
[Marked] ; rfe? ; [Marked]
diff --git a/tools/memory-model/litmus-tests/LB+unlocklockonceonce+poacquireonce.litmus b/tools/memory-model/litmus-tests/LB+unlocklockonceonce+poacquireonce.litmus
new file mode 100644
index 000000000000..eb34123a6ffe
--- /dev/null
+++ b/tools/memory-model/litmus-tests/LB+unlocklockonceonce+poacquireonce.litmus
@@ -0,0 +1,35 @@
+C LB+unlocklockonceonce+poacquireonce
+
+(*
+ * Result: Never
+ *
+ * If two locked critical sections execute on the same CPU, all accesses
+ * in the first must execute before any accesses in the second, even if the
+ * critical sections are protected by different locks. Note: Even when a
+ * write executes before a read, their memory effects can be reordered from
+ * the viewpoint of another CPU (the kind of reordering allowed by TSO).
+ *)
+
+{}
+
+P0(spinlock_t *s, spinlock_t *t, int *x, int *y)
+{
+ int r1;
+
+ spin_lock(s);
+ r1 = READ_ONCE(*x);
+ spin_unlock(s);
+ spin_lock(t);
+ WRITE_ONCE(*y, 1);
+ spin_unlock(t);
+}
+
+P1(int *x, int *y)
+{
+ int r2;
+
+ r2 = smp_load_acquire(y);
+ WRITE_ONCE(*x, 1);
+}
+
+exists (0:r1=1 /\ 1:r2=1)
diff --git a/tools/memory-model/litmus-tests/MP+unlocklockonceonce+fencermbonceonce.litmus b/tools/memory-model/litmus-tests/MP+unlocklockonceonce+fencermbonceonce.litmus
new file mode 100644
index 000000000000..2feb1398be71
--- /dev/null
+++ b/tools/memory-model/litmus-tests/MP+unlocklockonceonce+fencermbonceonce.litmus
@@ -0,0 +1,33 @@
+C MP+unlocklockonceonce+fencermbonceonce
+
+(*
+ * Result: Never
+ *
+ * If two locked critical sections execute on the same CPU, stores in the
+ * first must propagate to each CPU before stores in the second do, even if
+ * the critical sections are protected by different locks.
+ *)
+
+{}
+
+P0(spinlock_t *s, spinlock_t *t, int *x, int *y)
+{
+ spin_lock(s);
+ WRITE_ONCE(*x, 1);
+ spin_unlock(s);
+ spin_lock(t);
+ WRITE_ONCE(*y, 1);
+ spin_unlock(t);
+}
+
+P1(int *x, int *y)
+{
+ int r1;
+ int r2;
+
+ r1 = READ_ONCE(*y);
+ smp_rmb();
+ r2 = READ_ONCE(*x);
+}
+
+exists (1:r1=1 /\ 1:r2=0)
diff --git a/tools/memory-model/litmus-tests/README b/tools/memory-model/litmus-tests/README
index 681f9067fa9e..d311a0ff1ae6 100644
--- a/tools/memory-model/litmus-tests/README
+++ b/tools/memory-model/litmus-tests/README
@@ -63,6 +63,10 @@ LB+poonceonces.litmus
As above, but with store-release replaced with WRITE_ONCE()
and load-acquire replaced with READ_ONCE().
+LB+unlocklockonceonce+poacquireonce.litmus
+ Does a unlock+lock pair provides ordering guarantee between a
+ load and a store?
+
MP+onceassign+derefonce.litmus
As below, but with rcu_assign_pointer() and an rcu_dereference().
@@ -90,6 +94,10 @@ MP+porevlocks.litmus
As below, but with the first access of the writer process
and the second access of reader process protected by a lock.
+MP+unlocklockonceonce+fencermbonceonce.litmus
+ Does a unlock+lock pair provides ordering guarantee between a
+ store and another store?
+
MP+fencewmbonceonce+fencermbonceonce.litmus
Does a smp_wmb() (between the stores) and an smp_rmb() (between
the loads) suffice for the message-passing litmus test, where one
diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c
index 4d6d7fc13255..479e769ca324 100644
--- a/tools/objtool/arch/x86/decode.c
+++ b/tools/objtool/arch/x86/decode.c
@@ -112,7 +112,7 @@ int arch_decode_instruction(struct objtool_file *file, const struct section *sec
const struct elf *elf = file->elf;
struct insn insn;
int x86_64, ret;
- unsigned char op1, op2,
+ unsigned char op1, op2, op3,
rex = 0, rex_b = 0, rex_r = 0, rex_w = 0, rex_x = 0,
modrm = 0, modrm_mod = 0, modrm_rm = 0, modrm_reg = 0,
sib = 0, /* sib_scale = 0, */ sib_index = 0, sib_base = 0;
@@ -139,6 +139,7 @@ int arch_decode_instruction(struct objtool_file *file, const struct section *sec
op1 = insn.opcode.bytes[0];
op2 = insn.opcode.bytes[1];
+ op3 = insn.opcode.bytes[2];
if (insn.rex_prefix.nbytes) {
rex = insn.rex_prefix.bytes[0];
@@ -491,6 +492,14 @@ int arch_decode_instruction(struct objtool_file *file, const struct section *sec
/* nopl/nopw */
*type = INSN_NOP;
+ } else if (op2 == 0x38 && op3 == 0xf8) {
+ if (insn.prefixes.nbytes == 1 &&
+ insn.prefixes.bytes[0] == 0xf2) {
+ /* ENQCMD cannot be used in the kernel. */
+ WARN("ENQCMD instruction at %s:%lx", sec->name,
+ offset);
+ }
+
} else if (op2 == 0xa0 || op2 == 0xa8) {
/* push fs/gs */
@@ -531,6 +540,11 @@ int arch_decode_instruction(struct objtool_file *file, const struct section *sec
}
break;
+ case 0xcc:
+ /* int3 */
+ *type = INSN_TRAP;
+ break;
+
case 0xe3:
/* jecxz/jrcxz */
*type = INSN_JUMP_CONDITIONAL;
@@ -697,10 +711,10 @@ const char *arch_ret_insn(int len)
{
static const char ret[5][5] = {
{ BYTE_RET },
- { BYTE_RET, BYTES_NOP1 },
- { BYTE_RET, BYTES_NOP2 },
- { BYTE_RET, BYTES_NOP3 },
- { BYTE_RET, BYTES_NOP4 },
+ { BYTE_RET, 0xcc },
+ { BYTE_RET, 0xcc, BYTES_NOP1 },
+ { BYTE_RET, 0xcc, BYTES_NOP2 },
+ { BYTE_RET, 0xcc, BYTES_NOP3 },
};
if (len < 1 || len > 5) {
diff --git a/tools/objtool/builtin-check.c b/tools/objtool/builtin-check.c
index 8b38b5d6fec7..38070f26105b 100644
--- a/tools/objtool/builtin-check.c
+++ b/tools/objtool/builtin-check.c
@@ -20,7 +20,7 @@
#include <objtool/objtool.h>
bool no_fp, no_unreachable, retpoline, module, backtrace, uaccess, stats,
- validate_dup, vmlinux, mcount, noinstr, backup;
+ validate_dup, vmlinux, mcount, noinstr, backup, sls;
static const char * const check_usage[] = {
"objtool check [<options>] file.o",
@@ -45,6 +45,7 @@ const struct option check_options[] = {
OPT_BOOLEAN('l', "vmlinux", &vmlinux, "vmlinux.o validation"),
OPT_BOOLEAN('M', "mcount", &mcount, "generate __mcount_loc"),
OPT_BOOLEAN('B', "backup", &backup, "create .orig files before modification"),
+ OPT_BOOLEAN('S', "sls", &sls, "validate straight-line-speculation"),
OPT_END(),
};
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 21735829b860..7c33ec67c4a9 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -168,14 +168,16 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func,
"panic",
"do_exit",
"do_task_dead",
- "__module_put_and_exit",
- "complete_and_exit",
+ "kthread_exit",
+ "make_task_dead",
+ "__module_put_and_kthread_exit",
+ "kthread_complete_and_exit",
"__reiserfs_panic",
"lbug_with_loc",
"fortify_panic",
"usercopy_abort",
"machine_real_restart",
- "rewind_stack_do_exit",
+ "rewind_stack_and_make_dead",
"kunit_try_catch_throw",
"xen_start_kernel",
"cpu_bringup_and_idle",
@@ -849,6 +851,10 @@ static const char *uaccess_safe_builtin[] = {
"__asan_report_store16_noabort",
/* KCSAN */
"__kcsan_check_access",
+ "__kcsan_mb",
+ "__kcsan_wmb",
+ "__kcsan_rmb",
+ "__kcsan_release",
"kcsan_found_watchpoint",
"kcsan_setup_watchpoint",
"kcsan_check_scoped_accesses",
@@ -1068,11 +1074,11 @@ static void annotate_call_site(struct objtool_file *file,
}
/*
- * Many compilers cannot disable KCOV with a function attribute
- * so they need a little help, NOP out any KCOV calls from noinstr
- * text.
+ * Many compilers cannot disable KCOV or sanitizer calls with a function
+ * attribute so they need a little help, NOP out any such calls from
+ * noinstr text.
*/
- if (insn->sec->noinstr && sym->kcov) {
+ if (insn->sec->noinstr && sym->profiling_func) {
if (reloc) {
reloc->type = R_NONE;
elf_write_reloc(file->elf, reloc);
@@ -1987,6 +1993,31 @@ static int read_intra_function_calls(struct objtool_file *file)
return 0;
}
+/*
+ * Return true if name matches an instrumentation function, where calls to that
+ * function from noinstr code can safely be removed, but compilers won't do so.
+ */
+static bool is_profiling_func(const char *name)
+{
+ /*
+ * Many compilers cannot disable KCOV with a function attribute.
+ */
+ if (!strncmp(name, "__sanitizer_cov_", 16))
+ return true;
+
+ /*
+ * Some compilers currently do not remove __tsan_func_entry/exit nor
+ * __tsan_atomic_signal_fence (used for barrier instrumentation) with
+ * the __no_sanitize_thread attribute, remove them. Once the kernel's
+ * minimum Clang version is 14.0, this can be removed.
+ */
+ if (!strncmp(name, "__tsan_func_", 12) ||
+ !strcmp(name, "__tsan_atomic_signal_fence"))
+ return true;
+
+ return false;
+}
+
static int classify_symbols(struct objtool_file *file)
{
struct section *sec;
@@ -2007,8 +2038,8 @@ static int classify_symbols(struct objtool_file *file)
if (!strcmp(func->name, "__fentry__"))
func->fentry = true;
- if (!strncmp(func->name, "__sanitizer_cov_", 16))
- func->kcov = true;
+ if (is_profiling_func(func->name))
+ func->profiling_func = true;
}
}
@@ -2823,7 +2854,7 @@ static inline bool func_uaccess_safe(struct symbol *func)
static inline const char *call_dest_name(struct instruction *insn)
{
- static char pvname[16];
+ static char pvname[19];
struct reloc *rel;
int idx;
@@ -3084,6 +3115,12 @@ static int validate_branch(struct objtool_file *file, struct symbol *func,
switch (insn->type) {
case INSN_RETURN:
+ if (next_insn && next_insn->type == INSN_TRAP) {
+ next_insn->ignore = true;
+ } else if (sls && !insn->retpoline_safe) {
+ WARN_FUNC("missing int3 after ret",
+ insn->sec, insn->offset);
+ }
return validate_return(func, insn, &state);
case INSN_CALL:
@@ -3127,6 +3164,14 @@ static int validate_branch(struct objtool_file *file, struct symbol *func,
break;
case INSN_JUMP_DYNAMIC:
+ if (next_insn && next_insn->type == INSN_TRAP) {
+ next_insn->ignore = true;
+ } else if (sls && !insn->retpoline_safe) {
+ WARN_FUNC("missing int3 after indirect jump",
+ insn->sec, insn->offset);
+ }
+
+ /* fallthrough */
case INSN_JUMP_DYNAMIC_CONDITIONAL:
if (is_sibling_call(insn)) {
ret = validate_sibling_call(file, insn, &state);
@@ -3296,14 +3341,10 @@ static bool ignore_unreachable_insn(struct objtool_file *file, struct instructio
return true;
/*
- * Ignore any unused exceptions. This can happen when a whitelisted
- * function has an exception table entry.
- *
- * Also ignore alternative replacement instructions. This can happen
+ * Ignore alternative replacement instructions. This can happen
* when a whitelisted function uses one of the ALTERNATIVE macros.
*/
- if (!strcmp(insn->sec->name, ".fixup") ||
- !strcmp(insn->sec->name, ".altinstr_replacement") ||
+ if (!strcmp(insn->sec->name, ".altinstr_replacement") ||
!strcmp(insn->sec->name, ".altinstr_aux"))
return true;
diff --git a/tools/objtool/include/objtool/arch.h b/tools/objtool/include/objtool/arch.h
index 589ff58426ab..76bae3078286 100644
--- a/tools/objtool/include/objtool/arch.h
+++ b/tools/objtool/include/objtool/arch.h
@@ -26,6 +26,7 @@ enum insn_type {
INSN_CLAC,
INSN_STD,
INSN_CLD,
+ INSN_TRAP,
INSN_OTHER,
};
diff --git a/tools/objtool/include/objtool/builtin.h b/tools/objtool/include/objtool/builtin.h
index 15ac0b7d3d6a..89ba869ed08f 100644
--- a/tools/objtool/include/objtool/builtin.h
+++ b/tools/objtool/include/objtool/builtin.h
@@ -9,7 +9,7 @@
extern const struct option check_options[];
extern bool no_fp, no_unreachable, retpoline, module, backtrace, uaccess, stats,
- validate_dup, vmlinux, mcount, noinstr, backup;
+ validate_dup, vmlinux, mcount, noinstr, backup, sls;
extern int cmd_parse_options(int argc, const char **argv, const char * const usage[]);
diff --git a/tools/objtool/include/objtool/elf.h b/tools/objtool/include/objtool/elf.h
index cdc739fa9a6f..d22336781401 100644
--- a/tools/objtool/include/objtool/elf.h
+++ b/tools/objtool/include/objtool/elf.h
@@ -58,7 +58,7 @@ struct symbol {
u8 static_call_tramp : 1;
u8 retpoline_thunk : 1;
u8 fentry : 1;
- u8 kcov : 1;
+ u8 profiling_func : 1;
struct list_head pv_target;
};
diff --git a/tools/perf/Documentation/perf-buildid-cache.txt b/tools/perf/Documentation/perf-buildid-cache.txt
index cd8ce6e8ec12..7e44b419d301 100644
--- a/tools/perf/Documentation/perf-buildid-cache.txt
+++ b/tools/perf/Documentation/perf-buildid-cache.txt
@@ -74,12 +74,15 @@ OPTIONS
used when creating a uprobe for a process that resides in a
different mount namespace from the perf(1) utility.
---debuginfod=URLs::
+--debuginfod[=URLs]::
Specify debuginfod URL to be used when retrieving perf.data binaries,
it follows the same syntax as the DEBUGINFOD_URLS variable, like:
buildid-cache.debuginfod=http://192.168.122.174:8002
+ If the URLs is not specified, the value of DEBUGINFOD_URLS
+ system environment variable is used.
+
SEE ALSO
--------
linkperf:perf-record[1], linkperf:perf-report[1], linkperf:perf-buildid-list[1]
diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt
index 3bb75c1f25e8..0420e71698ee 100644
--- a/tools/perf/Documentation/perf-config.txt
+++ b/tools/perf/Documentation/perf-config.txt
@@ -587,6 +587,15 @@ record.*::
Use 'n' control blocks in asynchronous (Posix AIO) trace writing
mode ('n' default: 1, max: 4).
+ record.debuginfod::
+ Specify debuginfod URL to be used when cacheing perf.data binaries,
+ it follows the same syntax as the DEBUGINFOD_URLS variable, like:
+
+ http://192.168.122.174:8002
+
+ If the URLs is 'system', the value of DEBUGINFOD_URLS system environment
+ variable is used.
+
diff.*::
diff.order::
This option sets the number of columns to sort the result.
diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt
index 4dc8d0af19df..57384a97c04f 100644
--- a/tools/perf/Documentation/perf-list.txt
+++ b/tools/perf/Documentation/perf-list.txt
@@ -81,7 +81,11 @@ On AMD systems it is implemented using IBS (up to precise-level 2).
The precise modifier works with event types 0x76 (cpu-cycles, CPU
clocks not halted) and 0xC1 (micro-ops retired). Both events map to
IBS execution sampling (IBS op) with the IBS Op Counter Control bit
-(IbsOpCntCtl) set respectively (see AMD64 Architecture Programmer’s
+(IbsOpCntCtl) set respectively (see the
+Core Complex (CCX) -> Processor x86 Core -> Instruction Based Sampling (IBS)
+section of the [AMD Processor Programming Reference (PPR)] relevant to the
+family, model and stepping of the processor being used).
+
Manual Volume 2: System Programming, 13.3 Instruction-Based
Sampling). Examples to use IBS:
@@ -94,10 +98,12 @@ RAW HARDWARE EVENT DESCRIPTOR
Even when an event is not available in a symbolic form within perf right now,
it can be encoded in a per processor specific way.
-For instance For x86 CPUs NNN represents the raw register encoding with the
+For instance on x86 CPUs, N is a hexadecimal value that represents the raw register encoding with the
layout of IA32_PERFEVTSELx MSRs (see [Intel® 64 and IA-32 Architectures Software Developer's Manual Volume 3B: System Programming Guide] Figure 30-1 Layout
-of IA32_PERFEVTSELx MSRs) or AMD's PerfEvtSeln (see [AMD64 Architecture Programmer’s Manual Volume 2: System Programming], Page 344,
-Figure 13-7 Performance Event-Select Register (PerfEvtSeln)).
+of IA32_PERFEVTSELx MSRs) or AMD's PERF_CTL MSRs (see the
+Core Complex (CCX) -> Processor x86 Core -> MSR Registers section of the
+[AMD Processor Programming Reference (PPR)] relevant to the family, model
+and stepping of the processor being used).
Note: Only the following bit fields can be set in x86 counter
registers: event, umask, edge, inv, cmask. Esp. guest/host only and
@@ -126,6 +132,38 @@ It's also possible to use pmu syntax:
perf record -e cpu/r1a8/ ...
perf record -e cpu/r0x1a8/ ...
+Some processors, like those from AMD, support event codes and unit masks
+larger than a byte. In such cases, the bits corresponding to the event
+configuration parameters can be seen with:
+
+ cat /sys/bus/event_source/devices/<pmu>/format/<config>
+
+Example:
+
+If the AMD docs for an EPYC 7713 processor describe an event as:
+
+ Event Umask Event Mask
+ Num. Value Mnemonic Description
+
+ 28FH 03H op_cache_hit_miss.op_cache_hit Counts Op Cache micro-tag
+ hit events.
+
+raw encoding of 0x0328F cannot be used since the upper nibble of the
+EventSelect bits have to be specified via bits 32-35 as can be seen with:
+
+ cat /sys/bus/event_source/devices/cpu/format/event
+
+raw encoding of 0x20000038F should be used instead:
+
+ perf stat -e r20000038f -a sleep 1
+ perf record -e r20000038f ...
+
+It's also possible to use pmu syntax:
+
+ perf record -e r20000038f -a sleep 1
+ perf record -e cpu/r20000038f/ ...
+ perf record -e cpu/r0x20000038f/ ...
+
You should refer to the processor specific documentation for getting these
details. Some of them are referenced in the SEE ALSO section below.
@@ -316,4 +354,4 @@ SEE ALSO
linkperf:perf-stat[1], linkperf:perf-top[1],
linkperf:perf-record[1],
http://www.intel.com/sdm/[Intel® 64 and IA-32 Architectures Software Developer's Manual Volume 3B: System Programming Guide],
-http://support.amd.com/us/Processor_TechDocs/24593_APM_v2.pdf[AMD64 Architecture Programmer’s Manual Volume 2: System Programming]
+https://bugzilla.kernel.org/show_bug.cgi?id=206537[AMD Processor Programming Reference (PPR)]
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 3cf7bac67239..9ccc75935bc5 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -30,8 +30,10 @@ OPTIONS
- a symbolic event name (use 'perf list' to list all events)
- - a raw PMU event (eventsel+umask) in the form of rNNN where NNN is a
- hexadecimal event descriptor.
+ - a raw PMU event in the form of rN where N is a hexadecimal value
+ that represents the raw register encoding with the layout of the
+ event control registers as described by entries in
+ /sys/bus/event_sources/devices/cpu/format/*.
- a symbolic or raw PMU event followed by an optional colon
and a list of event modifiers, e.g., cpu-cycles:p. See the
@@ -713,6 +715,15 @@ measurements:
include::intel-hybrid.txt[]
+--debuginfod[=URLs]::
+ Specify debuginfod URL to be used when cacheing perf.data binaries,
+ it follows the same syntax as the DEBUGINFOD_URLS variable, like:
+
+ http://192.168.122.174:8002
+
+ If the URLs is not specified, the value of DEBUGINFOD_URLS
+ system environment variable is used.
+
SEE ALSO
--------
linkperf:perf-stat[1], linkperf:perf-list[1], linkperf:perf-intel-pt[1]
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 7e6fb7cbc0f4..c06c341e72b9 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -36,8 +36,10 @@ report::
- a symbolic event name (use 'perf list' to list all events)
- - a raw PMU event (eventsel+umask) in the form of rNNN where NNN is a
- hexadecimal event descriptor.
+ - a raw PMU event in the form of rN where N is a hexadecimal value
+ that represents the raw register encoding with the layout of the
+ event control registers as described by entries in
+ /sys/bus/event_sources/devices/cpu/format/*.
- a symbolic or raw PMU event followed by an optional colon
and a list of event modifiers, e.g., cpu-cycles:p. See the
@@ -493,6 +495,10 @@ This option can be enabled in perf config by setting the variable
$ perf config stat.no-csv-summary=true
+--cputype::
+Only enable events on applying cpu with this type for hybrid platform
+(e.g. core or atom)"
+
EXAMPLES
--------
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index 9898a32b8d9c..cac3dfbee7d8 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -38,9 +38,10 @@ Default is to monitor all CPUS.
-e <event>::
--event=<event>::
Select the PMU event. Selection can be a symbolic event name
- (use 'perf list' to list all events) or a raw PMU
- event (eventsel+umask) in the form of rNNN where NNN is a
- hexadecimal event descriptor.
+ (use 'perf list' to list all events) or a raw PMU event in the form
+ of rN where N is a hexadecimal value that represents the raw register
+ encoding with the layout of the event control registers as described
+ by entries in /sys/bus/event_sources/devices/cpu/format/*.
-E <entries>::
--entries=<entries>::
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 3df74cf5651a..96ad944ca6a8 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -17,6 +17,7 @@ detected = $(shell echo "$(1)=y" >> $(OUTPUT).config-detected)
detected_var = $(shell echo "$(1)=$($(1))" >> $(OUTPUT).config-detected)
CFLAGS := $(EXTRA_CFLAGS) $(filter-out -Wnested-externs,$(EXTRA_WARNINGS))
+HOSTCFLAGS := $(filter-out -Wnested-externs,$(EXTRA_WARNINGS))
include $(srctree)/tools/scripts/Makefile.arch
@@ -143,7 +144,10 @@ FEATURE_CHECK_LDFLAGS-libcrypto = -lcrypto
ifdef CSINCLUDES
LIBOPENCSD_CFLAGS := -I$(CSINCLUDES)
endif
-OPENCSDLIBS := -lopencsd_c_api -lopencsd -lstdc++
+OPENCSDLIBS := -lopencsd_c_api
+ifeq ($(findstring -static,${LDFLAGS}),-static)
+ OPENCSDLIBS += -lopencsd -lstdc++
+endif
ifdef CSLIBS
LIBOPENCSD_LDFLAGS := -L$(CSLIBS)
endif
@@ -211,6 +215,7 @@ endif
ifneq ($(WERROR),0)
CORE_CFLAGS += -Werror
CXXFLAGS += -Werror
+ HOSTCFLAGS += -Werror
endif
ifndef DEBUG
@@ -290,6 +295,9 @@ CXXFLAGS += -ggdb3
CXXFLAGS += -funwind-tables
CXXFLAGS += -Wno-strict-aliasing
+HOSTCFLAGS += -Wall
+HOSTCFLAGS += -Wextra
+
# Enforce a non-executable stack, as we may regress (again) in the future by
# adding assembler files missing the .GNU-stack linker note.
LDFLAGS += -Wl,-z,noexecstack
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 80522bcfafe0..ac861e42c8f7 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -226,7 +226,7 @@ else
endif
export srctree OUTPUT RM CC CXX LD AR CFLAGS CXXFLAGS V BISON FLEX AWK
-export HOSTCC HOSTLD HOSTAR
+export HOSTCC HOSTLD HOSTAR HOSTCFLAGS
include $(srctree)/tools/build/Makefile.include
@@ -1041,7 +1041,7 @@ SKEL_OUT := $(abspath $(OUTPUT)util/bpf_skel)
SKEL_TMP_OUT := $(abspath $(SKEL_OUT)/.tmp)
SKELETONS := $(SKEL_OUT)/bpf_prog_profiler.skel.h
SKELETONS += $(SKEL_OUT)/bperf_leader.skel.h $(SKEL_OUT)/bperf_follower.skel.h
-SKELETONS += $(SKEL_OUT)/bperf_cgroup.skel.h
+SKELETONS += $(SKEL_OUT)/bperf_cgroup.skel.h $(SKEL_OUT)/func_latency.skel.h
$(SKEL_TMP_OUT) $(LIBBPF_OUTPUT):
$(Q)$(MKDIR) -p $@
diff --git a/tools/perf/arch/arm/include/perf_regs.h b/tools/perf/arch/arm/include/perf_regs.h
index 4085419283d0..99a06550e25d 100644
--- a/tools/perf/arch/arm/include/perf_regs.h
+++ b/tools/perf/arch/arm/include/perf_regs.h
@@ -15,46 +15,4 @@ void perf_regs_load(u64 *regs);
#define PERF_REG_IP PERF_REG_ARM_PC
#define PERF_REG_SP PERF_REG_ARM_SP
-static inline const char *__perf_reg_name(int id)
-{
- switch (id) {
- case PERF_REG_ARM_R0:
- return "r0";
- case PERF_REG_ARM_R1:
- return "r1";
- case PERF_REG_ARM_R2:
- return "r2";
- case PERF_REG_ARM_R3:
- return "r3";
- case PERF_REG_ARM_R4:
- return "r4";
- case PERF_REG_ARM_R5:
- return "r5";
- case PERF_REG_ARM_R6:
- return "r6";
- case PERF_REG_ARM_R7:
- return "r7";
- case PERF_REG_ARM_R8:
- return "r8";
- case PERF_REG_ARM_R9:
- return "r9";
- case PERF_REG_ARM_R10:
- return "r10";
- case PERF_REG_ARM_FP:
- return "fp";
- case PERF_REG_ARM_IP:
- return "ip";
- case PERF_REG_ARM_SP:
- return "sp";
- case PERF_REG_ARM_LR:
- return "lr";
- case PERF_REG_ARM_PC:
- return "pc";
- default:
- return NULL;
- }
-
- return NULL;
-}
-
#endif /* ARCH_PERF_REGS_H */
diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c
index 293a23bf8be3..2e8b2c4365a0 100644
--- a/tools/perf/arch/arm/util/cs-etm.c
+++ b/tools/perf/arch/arm/util/cs-etm.c
@@ -203,9 +203,11 @@ static int cs_etm_set_option(struct auxtrace_record *itr,
struct perf_cpu_map *online_cpus = perf_cpu_map__new(NULL);
/* Set option of each CPU we have */
- for (i = 0; i < cpu__max_cpu(); i++) {
- if (!cpu_map__has(event_cpus, i) ||
- !cpu_map__has(online_cpus, i))
+ for (i = 0; i < cpu__max_cpu().cpu; i++) {
+ struct perf_cpu cpu = { .cpu = i, };
+
+ if (!perf_cpu_map__has(event_cpus, cpu) ||
+ !perf_cpu_map__has(online_cpus, cpu))
continue;
if (option & BIT(ETM_OPT_CTXTID)) {
@@ -407,25 +409,6 @@ static int cs_etm_recording_options(struct auxtrace_record *itr,
}
- /* Validate auxtrace_mmap_pages provided by user */
- if (opts->auxtrace_mmap_pages) {
- unsigned int max_page = (KiB(128) / page_size);
- size_t sz = opts->auxtrace_mmap_pages * (size_t)page_size;
-
- if (!privileged &&
- opts->auxtrace_mmap_pages > max_page) {
- opts->auxtrace_mmap_pages = max_page;
- pr_err("auxtrace too big, truncating to %d\n",
- max_page);
- }
-
- if (!is_power_of_2(sz)) {
- pr_err("Invalid mmap size for %s: must be a power of 2\n",
- CORESIGHT_ETM_PMU_NAME);
- return -EINVAL;
- }
- }
-
if (opts->auxtrace_snapshot_mode)
pr_debug2("%s snapshot size: %zu\n", CORESIGHT_ETM_PMU_NAME,
opts->auxtrace_snapshot_size);
@@ -541,9 +524,11 @@ cs_etm_info_priv_size(struct auxtrace_record *itr __maybe_unused,
/* cpu map is not empty, we have specific CPUs to work with */
if (!perf_cpu_map__empty(event_cpus)) {
- for (i = 0; i < cpu__max_cpu(); i++) {
- if (!cpu_map__has(event_cpus, i) ||
- !cpu_map__has(online_cpus, i))
+ for (i = 0; i < cpu__max_cpu().cpu; i++) {
+ struct perf_cpu cpu = { .cpu = i, };
+
+ if (!perf_cpu_map__has(event_cpus, cpu) ||
+ !perf_cpu_map__has(online_cpus, cpu))
continue;
if (cs_etm_is_ete(itr, i))
@@ -555,8 +540,10 @@ cs_etm_info_priv_size(struct auxtrace_record *itr __maybe_unused,
}
} else {
/* get configuration for all CPUs in the system */
- for (i = 0; i < cpu__max_cpu(); i++) {
- if (!cpu_map__has(online_cpus, i))
+ for (i = 0; i < cpu__max_cpu().cpu; i++) {
+ struct perf_cpu cpu = { .cpu = i, };
+
+ if (!perf_cpu_map__has(online_cpus, cpu))
continue;
if (cs_etm_is_ete(itr, i))
@@ -741,8 +728,10 @@ static int cs_etm_info_fill(struct auxtrace_record *itr,
} else {
/* Make sure all specified CPUs are online */
for (i = 0; i < perf_cpu_map__nr(event_cpus); i++) {
- if (cpu_map__has(event_cpus, i) &&
- !cpu_map__has(online_cpus, i))
+ struct perf_cpu cpu = { .cpu = i, };
+
+ if (perf_cpu_map__has(event_cpus, cpu) &&
+ !perf_cpu_map__has(online_cpus, cpu))
return -EINVAL;
}
@@ -762,9 +751,12 @@ static int cs_etm_info_fill(struct auxtrace_record *itr,
offset = CS_ETM_SNAPSHOT + 1;
- for (i = 0; i < cpu__max_cpu() && offset < priv_size; i++)
- if (cpu_map__has(cpu_map, i))
+ for (i = 0; i < cpu__max_cpu().cpu && offset < priv_size; i++) {
+ struct perf_cpu cpu = { .cpu = i, };
+
+ if (perf_cpu_map__has(cpu_map, cpu))
cs_etm_get_metadata(i, &offset, itr, info);
+ }
perf_cpu_map__put(online_cpus);
diff --git a/tools/perf/arch/arm64/include/perf_regs.h b/tools/perf/arch/arm64/include/perf_regs.h
index fa3e07459f76..35a3cc775b39 100644
--- a/tools/perf/arch/arm64/include/perf_regs.h
+++ b/tools/perf/arch/arm64/include/perf_regs.h
@@ -4,7 +4,9 @@
#include <stdlib.h>
#include <linux/types.h>
+#define perf_event_arm_regs perf_event_arm64_regs
#include <asm/perf_regs.h>
+#undef perf_event_arm_regs
void perf_regs_load(u64 *regs);
@@ -15,80 +17,4 @@ void perf_regs_load(u64 *regs);
#define PERF_REG_IP PERF_REG_ARM64_PC
#define PERF_REG_SP PERF_REG_ARM64_SP
-static inline const char *__perf_reg_name(int id)
-{
- switch (id) {
- case PERF_REG_ARM64_X0:
- return "x0";
- case PERF_REG_ARM64_X1:
- return "x1";
- case PERF_REG_ARM64_X2:
- return "x2";
- case PERF_REG_ARM64_X3:
- return "x3";
- case PERF_REG_ARM64_X4:
- return "x4";
- case PERF_REG_ARM64_X5:
- return "x5";
- case PERF_REG_ARM64_X6:
- return "x6";
- case PERF_REG_ARM64_X7:
- return "x7";
- case PERF_REG_ARM64_X8:
- return "x8";
- case PERF_REG_ARM64_X9:
- return "x9";
- case PERF_REG_ARM64_X10:
- return "x10";
- case PERF_REG_ARM64_X11:
- return "x11";
- case PERF_REG_ARM64_X12:
- return "x12";
- case PERF_REG_ARM64_X13:
- return "x13";
- case PERF_REG_ARM64_X14:
- return "x14";
- case PERF_REG_ARM64_X15:
- return "x15";
- case PERF_REG_ARM64_X16:
- return "x16";
- case PERF_REG_ARM64_X17:
- return "x17";
- case PERF_REG_ARM64_X18:
- return "x18";
- case PERF_REG_ARM64_X19:
- return "x19";
- case PERF_REG_ARM64_X20:
- return "x20";
- case PERF_REG_ARM64_X21:
- return "x21";
- case PERF_REG_ARM64_X22:
- return "x22";
- case PERF_REG_ARM64_X23:
- return "x23";
- case PERF_REG_ARM64_X24:
- return "x24";
- case PERF_REG_ARM64_X25:
- return "x25";
- case PERF_REG_ARM64_X26:
- return "x26";
- case PERF_REG_ARM64_X27:
- return "x27";
- case PERF_REG_ARM64_X28:
- return "x28";
- case PERF_REG_ARM64_X29:
- return "x29";
- case PERF_REG_ARM64_SP:
- return "sp";
- case PERF_REG_ARM64_LR:
- return "lr";
- case PERF_REG_ARM64_PC:
- return "pc";
- default:
- return NULL;
- }
-
- return NULL;
-}
-
#endif /* ARCH_PERF_REGS_H */
diff --git a/tools/perf/arch/arm64/util/machine.c b/tools/perf/arch/arm64/util/machine.c
index 7e7714290a87..d2ce31e28cd7 100644
--- a/tools/perf/arch/arm64/util/machine.c
+++ b/tools/perf/arch/arm64/util/machine.c
@@ -5,6 +5,8 @@
#include <string.h>
#include "debug.h"
#include "symbol.h"
+#include "callchain.h"
+#include "record.h"
/* On arm64, kernel text segment starts at high memory address,
* for example 0xffff 0000 8xxx xxxx. Modules start at a low memory
@@ -26,3 +28,8 @@ void arch__symbols__fixup_end(struct symbol *p, struct symbol *c)
p->end = c->start;
pr_debug4("%s sym:%s end:%#" PRIx64 "\n", __func__, p->name, p->end);
}
+
+void arch__add_leaf_frame_record_opts(struct record_opts *opts)
+{
+ opts->sample_user_regs |= sample_reg_masks[PERF_REG_ARM64_LR].mask;
+}
diff --git a/tools/perf/arch/arm64/util/pmu.c b/tools/perf/arch/arm64/util/pmu.c
index d3a18f9c85f6..79124bba713e 100644
--- a/tools/perf/arch/arm64/util/pmu.c
+++ b/tools/perf/arch/arm64/util/pmu.c
@@ -15,7 +15,7 @@ const struct pmu_events_map *pmu_events_map__find(void)
* The cpumap should cover all CPUs. Otherwise, some CPUs may
* not support some events or have different event IDs.
*/
- if (pmu->cpus->nr != cpu__max_cpu())
+ if (pmu->cpus->nr != cpu__max_cpu().cpu)
return NULL;
return perf_pmu__find_map(pmu);
diff --git a/tools/perf/arch/csky/include/perf_regs.h b/tools/perf/arch/csky/include/perf_regs.h
index 25ac3bdcb9d1..1afcc0e916c2 100644
--- a/tools/perf/arch/csky/include/perf_regs.h
+++ b/tools/perf/arch/csky/include/perf_regs.h
@@ -15,86 +15,4 @@
#define PERF_REG_IP PERF_REG_CSKY_PC
#define PERF_REG_SP PERF_REG_CSKY_SP
-static inline const char *__perf_reg_name(int id)
-{
- switch (id) {
- case PERF_REG_CSKY_A0:
- return "a0";
- case PERF_REG_CSKY_A1:
- return "a1";
- case PERF_REG_CSKY_A2:
- return "a2";
- case PERF_REG_CSKY_A3:
- return "a3";
- case PERF_REG_CSKY_REGS0:
- return "regs0";
- case PERF_REG_CSKY_REGS1:
- return "regs1";
- case PERF_REG_CSKY_REGS2:
- return "regs2";
- case PERF_REG_CSKY_REGS3:
- return "regs3";
- case PERF_REG_CSKY_REGS4:
- return "regs4";
- case PERF_REG_CSKY_REGS5:
- return "regs5";
- case PERF_REG_CSKY_REGS6:
- return "regs6";
- case PERF_REG_CSKY_REGS7:
- return "regs7";
- case PERF_REG_CSKY_REGS8:
- return "regs8";
- case PERF_REG_CSKY_REGS9:
- return "regs9";
- case PERF_REG_CSKY_SP:
- return "sp";
- case PERF_REG_CSKY_LR:
- return "lr";
- case PERF_REG_CSKY_PC:
- return "pc";
-#if defined(__CSKYABIV2__)
- case PERF_REG_CSKY_EXREGS0:
- return "exregs0";
- case PERF_REG_CSKY_EXREGS1:
- return "exregs1";
- case PERF_REG_CSKY_EXREGS2:
- return "exregs2";
- case PERF_REG_CSKY_EXREGS3:
- return "exregs3";
- case PERF_REG_CSKY_EXREGS4:
- return "exregs4";
- case PERF_REG_CSKY_EXREGS5:
- return "exregs5";
- case PERF_REG_CSKY_EXREGS6:
- return "exregs6";
- case PERF_REG_CSKY_EXREGS7:
- return "exregs7";
- case PERF_REG_CSKY_EXREGS8:
- return "exregs8";
- case PERF_REG_CSKY_EXREGS9:
- return "exregs9";
- case PERF_REG_CSKY_EXREGS10:
- return "exregs10";
- case PERF_REG_CSKY_EXREGS11:
- return "exregs11";
- case PERF_REG_CSKY_EXREGS12:
- return "exregs12";
- case PERF_REG_CSKY_EXREGS13:
- return "exregs13";
- case PERF_REG_CSKY_EXREGS14:
- return "exregs14";
- case PERF_REG_CSKY_TLS:
- return "tls";
- case PERF_REG_CSKY_HI:
- return "hi";
- case PERF_REG_CSKY_LO:
- return "lo";
-#endif
- default:
- return NULL;
- }
-
- return NULL;
-}
-
#endif /* ARCH_PERF_REGS_H */
diff --git a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
index e2c481fcede6..3f1886ad9d80 100644
--- a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
+++ b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
@@ -364,3 +364,4 @@
# 447 reserved for memfd_secret
448 n64 process_mrelease sys_process_mrelease
449 n64 futex_waitv sys_futex_waitv
+450 common set_mempolicy_home_node sys_set_mempolicy_home_node
diff --git a/tools/perf/arch/mips/include/perf_regs.h b/tools/perf/arch/mips/include/perf_regs.h
index ee73b36a14d1..b8cd8bbb37ba 100644
--- a/tools/perf/arch/mips/include/perf_regs.h
+++ b/tools/perf/arch/mips/include/perf_regs.h
@@ -12,73 +12,4 @@
#define PERF_REGS_MASK ((1ULL << PERF_REG_MIPS_MAX) - 1)
-static inline const char *__perf_reg_name(int id)
-{
- switch (id) {
- case PERF_REG_MIPS_PC:
- return "PC";
- case PERF_REG_MIPS_R1:
- return "$1";
- case PERF_REG_MIPS_R2:
- return "$2";
- case PERF_REG_MIPS_R3:
- return "$3";
- case PERF_REG_MIPS_R4:
- return "$4";
- case PERF_REG_MIPS_R5:
- return "$5";
- case PERF_REG_MIPS_R6:
- return "$6";
- case PERF_REG_MIPS_R7:
- return "$7";
- case PERF_REG_MIPS_R8:
- return "$8";
- case PERF_REG_MIPS_R9:
- return "$9";
- case PERF_REG_MIPS_R10:
- return "$10";
- case PERF_REG_MIPS_R11:
- return "$11";
- case PERF_REG_MIPS_R12:
- return "$12";
- case PERF_REG_MIPS_R13:
- return "$13";
- case PERF_REG_MIPS_R14:
- return "$14";
- case PERF_REG_MIPS_R15:
- return "$15";
- case PERF_REG_MIPS_R16:
- return "$16";
- case PERF_REG_MIPS_R17:
- return "$17";
- case PERF_REG_MIPS_R18:
- return "$18";
- case PERF_REG_MIPS_R19:
- return "$19";
- case PERF_REG_MIPS_R20:
- return "$20";
- case PERF_REG_MIPS_R21:
- return "$21";
- case PERF_REG_MIPS_R22:
- return "$22";
- case PERF_REG_MIPS_R23:
- return "$23";
- case PERF_REG_MIPS_R24:
- return "$24";
- case PERF_REG_MIPS_R25:
- return "$25";
- case PERF_REG_MIPS_R28:
- return "$28";
- case PERF_REG_MIPS_R29:
- return "$29";
- case PERF_REG_MIPS_R30:
- return "$30";
- case PERF_REG_MIPS_R31:
- return "$31";
- default:
- break;
- }
- return NULL;
-}
-
#endif /* ARCH_PERF_REGS_H */
diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
index 15109af9d075..2600b4237292 100644
--- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
@@ -529,3 +529,4 @@
# 447 reserved for memfd_secret
448 common process_mrelease sys_process_mrelease
449 common futex_waitv sys_futex_waitv
+450 nospu set_mempolicy_home_node sys_set_mempolicy_home_node
diff --git a/tools/perf/arch/powerpc/include/perf_regs.h b/tools/perf/arch/powerpc/include/perf_regs.h
index 93339d17acc4..9bb17c3f370b 100644
--- a/tools/perf/arch/powerpc/include/perf_regs.h
+++ b/tools/perf/arch/powerpc/include/perf_regs.h
@@ -19,70 +19,4 @@ void perf_regs_load(u64 *regs);
#define PERF_REG_IP PERF_REG_POWERPC_NIP
#define PERF_REG_SP PERF_REG_POWERPC_R1
-static const char *reg_names[] = {
- [PERF_REG_POWERPC_R0] = "r0",
- [PERF_REG_POWERPC_R1] = "r1",
- [PERF_REG_POWERPC_R2] = "r2",
- [PERF_REG_POWERPC_R3] = "r3",
- [PERF_REG_POWERPC_R4] = "r4",
- [PERF_REG_POWERPC_R5] = "r5",
- [PERF_REG_POWERPC_R6] = "r6",
- [PERF_REG_POWERPC_R7] = "r7",
- [PERF_REG_POWERPC_R8] = "r8",
- [PERF_REG_POWERPC_R9] = "r9",
- [PERF_REG_POWERPC_R10] = "r10",
- [PERF_REG_POWERPC_R11] = "r11",
- [PERF_REG_POWERPC_R12] = "r12",
- [PERF_REG_POWERPC_R13] = "r13",
- [PERF_REG_POWERPC_R14] = "r14",
- [PERF_REG_POWERPC_R15] = "r15",
- [PERF_REG_POWERPC_R16] = "r16",
- [PERF_REG_POWERPC_R17] = "r17",
- [PERF_REG_POWERPC_R18] = "r18",
- [PERF_REG_POWERPC_R19] = "r19",
- [PERF_REG_POWERPC_R20] = "r20",
- [PERF_REG_POWERPC_R21] = "r21",
- [PERF_REG_POWERPC_R22] = "r22",
- [PERF_REG_POWERPC_R23] = "r23",
- [PERF_REG_POWERPC_R24] = "r24",
- [PERF_REG_POWERPC_R25] = "r25",
- [PERF_REG_POWERPC_R26] = "r26",
- [PERF_REG_POWERPC_R27] = "r27",
- [PERF_REG_POWERPC_R28] = "r28",
- [PERF_REG_POWERPC_R29] = "r29",
- [PERF_REG_POWERPC_R30] = "r30",
- [PERF_REG_POWERPC_R31] = "r31",
- [PERF_REG_POWERPC_NIP] = "nip",
- [PERF_REG_POWERPC_MSR] = "msr",
- [PERF_REG_POWERPC_ORIG_R3] = "orig_r3",
- [PERF_REG_POWERPC_CTR] = "ctr",
- [PERF_REG_POWERPC_LINK] = "link",
- [PERF_REG_POWERPC_XER] = "xer",
- [PERF_REG_POWERPC_CCR] = "ccr",
- [PERF_REG_POWERPC_SOFTE] = "softe",
- [PERF_REG_POWERPC_TRAP] = "trap",
- [PERF_REG_POWERPC_DAR] = "dar",
- [PERF_REG_POWERPC_DSISR] = "dsisr",
- [PERF_REG_POWERPC_SIER] = "sier",
- [PERF_REG_POWERPC_MMCRA] = "mmcra",
- [PERF_REG_POWERPC_MMCR0] = "mmcr0",
- [PERF_REG_POWERPC_MMCR1] = "mmcr1",
- [PERF_REG_POWERPC_MMCR2] = "mmcr2",
- [PERF_REG_POWERPC_MMCR3] = "mmcr3",
- [PERF_REG_POWERPC_SIER2] = "sier2",
- [PERF_REG_POWERPC_SIER3] = "sier3",
- [PERF_REG_POWERPC_PMC1] = "pmc1",
- [PERF_REG_POWERPC_PMC2] = "pmc2",
- [PERF_REG_POWERPC_PMC3] = "pmc3",
- [PERF_REG_POWERPC_PMC4] = "pmc4",
- [PERF_REG_POWERPC_PMC5] = "pmc5",
- [PERF_REG_POWERPC_PMC6] = "pmc6",
- [PERF_REG_POWERPC_SDAR] = "sdar",
- [PERF_REG_POWERPC_SIAR] = "siar",
-};
-
-static inline const char *__perf_reg_name(int id)
-{
- return reg_names[id];
-}
#endif /* ARCH_PERF_REGS_H */
diff --git a/tools/perf/arch/powerpc/util/event.c b/tools/perf/arch/powerpc/util/event.c
index 3bf441257466..cf430a4c55b9 100644
--- a/tools/perf/arch/powerpc/util/event.c
+++ b/tools/perf/arch/powerpc/util/event.c
@@ -40,8 +40,12 @@ const char *arch_perf_header_entry(const char *se_header)
{
if (!strcmp(se_header, "Local INSTR Latency"))
return "Finish Cyc";
- else if (!strcmp(se_header, "Pipeline Stage Cycle"))
+ else if (!strcmp(se_header, "INSTR Latency"))
+ return "Global Finish_cyc";
+ else if (!strcmp(se_header, "Local Pipeline Stage Cycle"))
return "Dispatch Cyc";
+ else if (!strcmp(se_header, "Pipeline Stage Cycle"))
+ return "Global Dispatch_cyc";
return se_header;
}
@@ -49,5 +53,7 @@ int arch_support_sort_key(const char *sort_key)
{
if (!strcmp(sort_key, "p_stage_cyc"))
return 1;
+ if (!strcmp(sort_key, "local_p_stage_cyc"))
+ return 1;
return 0;
}
diff --git a/tools/perf/arch/riscv/include/perf_regs.h b/tools/perf/arch/riscv/include/perf_regs.h
index 6b02a767c918..6944bf0de53e 100644
--- a/tools/perf/arch/riscv/include/perf_regs.h
+++ b/tools/perf/arch/riscv/include/perf_regs.h
@@ -19,78 +19,4 @@
#define PERF_REG_IP PERF_REG_RISCV_PC
#define PERF_REG_SP PERF_REG_RISCV_SP
-static inline const char *__perf_reg_name(int id)
-{
- switch (id) {
- case PERF_REG_RISCV_PC:
- return "pc";
- case PERF_REG_RISCV_RA:
- return "ra";
- case PERF_REG_RISCV_SP:
- return "sp";
- case PERF_REG_RISCV_GP:
- return "gp";
- case PERF_REG_RISCV_TP:
- return "tp";
- case PERF_REG_RISCV_T0:
- return "t0";
- case PERF_REG_RISCV_T1:
- return "t1";
- case PERF_REG_RISCV_T2:
- return "t2";
- case PERF_REG_RISCV_S0:
- return "s0";
- case PERF_REG_RISCV_S1:
- return "s1";
- case PERF_REG_RISCV_A0:
- return "a0";
- case PERF_REG_RISCV_A1:
- return "a1";
- case PERF_REG_RISCV_A2:
- return "a2";
- case PERF_REG_RISCV_A3:
- return "a3";
- case PERF_REG_RISCV_A4:
- return "a4";
- case PERF_REG_RISCV_A5:
- return "a5";
- case PERF_REG_RISCV_A6:
- return "a6";
- case PERF_REG_RISCV_A7:
- return "a7";
- case PERF_REG_RISCV_S2:
- return "s2";
- case PERF_REG_RISCV_S3:
- return "s3";
- case PERF_REG_RISCV_S4:
- return "s4";
- case PERF_REG_RISCV_S5:
- return "s5";
- case PERF_REG_RISCV_S6:
- return "s6";
- case PERF_REG_RISCV_S7:
- return "s7";
- case PERF_REG_RISCV_S8:
- return "s8";
- case PERF_REG_RISCV_S9:
- return "s9";
- case PERF_REG_RISCV_S10:
- return "s10";
- case PERF_REG_RISCV_S11:
- return "s11";
- case PERF_REG_RISCV_T3:
- return "t3";
- case PERF_REG_RISCV_T4:
- return "t4";
- case PERF_REG_RISCV_T5:
- return "t5";
- case PERF_REG_RISCV_T6:
- return "t6";
- default:
- return NULL;
- }
-
- return NULL;
-}
-
#endif /* ARCH_PERF_REGS_H */
diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
index ed9c5c2eafad..799147658dee 100644
--- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
@@ -452,3 +452,4 @@
# 447 reserved for memfd_secret
448 common process_mrelease sys_process_mrelease sys_process_mrelease
449 common futex_waitv sys_futex_waitv sys_futex_waitv
+450 common set_mempolicy_home_node sys_set_mempolicy_home_node sys_set_mempolicy_home_node
diff --git a/tools/perf/arch/s390/include/perf_regs.h b/tools/perf/arch/s390/include/perf_regs.h
index ce3031526623..52fcc0891da6 100644
--- a/tools/perf/arch/s390/include/perf_regs.h
+++ b/tools/perf/arch/s390/include/perf_regs.h
@@ -14,82 +14,4 @@ void perf_regs_load(u64 *regs);
#define PERF_REG_IP PERF_REG_S390_PC
#define PERF_REG_SP PERF_REG_S390_R15
-static inline const char *__perf_reg_name(int id)
-{
- switch (id) {
- case PERF_REG_S390_R0:
- return "R0";
- case PERF_REG_S390_R1:
- return "R1";
- case PERF_REG_S390_R2:
- return "R2";
- case PERF_REG_S390_R3:
- return "R3";
- case PERF_REG_S390_R4:
- return "R4";
- case PERF_REG_S390_R5:
- return "R5";
- case PERF_REG_S390_R6:
- return "R6";
- case PERF_REG_S390_R7:
- return "R7";
- case PERF_REG_S390_R8:
- return "R8";
- case PERF_REG_S390_R9:
- return "R9";
- case PERF_REG_S390_R10:
- return "R10";
- case PERF_REG_S390_R11:
- return "R11";
- case PERF_REG_S390_R12:
- return "R12";
- case PERF_REG_S390_R13:
- return "R13";
- case PERF_REG_S390_R14:
- return "R14";
- case PERF_REG_S390_R15:
- return "R15";
- case PERF_REG_S390_FP0:
- return "FP0";
- case PERF_REG_S390_FP1:
- return "FP1";
- case PERF_REG_S390_FP2:
- return "FP2";
- case PERF_REG_S390_FP3:
- return "FP3";
- case PERF_REG_S390_FP4:
- return "FP4";
- case PERF_REG_S390_FP5:
- return "FP5";
- case PERF_REG_S390_FP6:
- return "FP6";
- case PERF_REG_S390_FP7:
- return "FP7";
- case PERF_REG_S390_FP8:
- return "FP8";
- case PERF_REG_S390_FP9:
- return "FP9";
- case PERF_REG_S390_FP10:
- return "FP10";
- case PERF_REG_S390_FP11:
- return "FP11";
- case PERF_REG_S390_FP12:
- return "FP12";
- case PERF_REG_S390_FP13:
- return "FP13";
- case PERF_REG_S390_FP14:
- return "FP14";
- case PERF_REG_S390_FP15:
- return "FP15";
- case PERF_REG_S390_MASK:
- return "MASK";
- case PERF_REG_S390_PC:
- return "PC";
- default:
- return NULL;
- }
-
- return NULL;
-}
-
#endif /* ARCH_PERF_REGS_H */
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index fe8f8dd157b4..c84d12608cd2 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -371,6 +371,7 @@
447 common memfd_secret sys_memfd_secret
448 common process_mrelease sys_process_mrelease
449 common futex_waitv sys_futex_waitv
+450 common set_mempolicy_home_node sys_set_mempolicy_home_node
#
# Due to a historical design error, certain syscalls are numbered differently
diff --git a/tools/perf/arch/x86/include/perf_regs.h b/tools/perf/arch/x86/include/perf_regs.h
index cddc4cdc0d9b..16e23b722042 100644
--- a/tools/perf/arch/x86/include/perf_regs.h
+++ b/tools/perf/arch/x86/include/perf_regs.h
@@ -23,86 +23,4 @@ void perf_regs_load(u64 *regs);
#define PERF_REG_IP PERF_REG_X86_IP
#define PERF_REG_SP PERF_REG_X86_SP
-static inline const char *__perf_reg_name(int id)
-{
- switch (id) {
- case PERF_REG_X86_AX:
- return "AX";
- case PERF_REG_X86_BX:
- return "BX";
- case PERF_REG_X86_CX:
- return "CX";
- case PERF_REG_X86_DX:
- return "DX";
- case PERF_REG_X86_SI:
- return "SI";
- case PERF_REG_X86_DI:
- return "DI";
- case PERF_REG_X86_BP:
- return "BP";
- case PERF_REG_X86_SP:
- return "SP";
- case PERF_REG_X86_IP:
- return "IP";
- case PERF_REG_X86_FLAGS:
- return "FLAGS";
- case PERF_REG_X86_CS:
- return "CS";
- case PERF_REG_X86_SS:
- return "SS";
- case PERF_REG_X86_DS:
- return "DS";
- case PERF_REG_X86_ES:
- return "ES";
- case PERF_REG_X86_FS:
- return "FS";
- case PERF_REG_X86_GS:
- return "GS";
-#ifdef HAVE_ARCH_X86_64_SUPPORT
- case PERF_REG_X86_R8:
- return "R8";
- case PERF_REG_X86_R9:
- return "R9";
- case PERF_REG_X86_R10:
- return "R10";
- case PERF_REG_X86_R11:
- return "R11";
- case PERF_REG_X86_R12:
- return "R12";
- case PERF_REG_X86_R13:
- return "R13";
- case PERF_REG_X86_R14:
- return "R14";
- case PERF_REG_X86_R15:
- return "R15";
-#endif /* HAVE_ARCH_X86_64_SUPPORT */
-
-#define XMM(x) \
- case PERF_REG_X86_XMM ## x: \
- case PERF_REG_X86_XMM ## x + 1: \
- return "XMM" #x;
- XMM(0)
- XMM(1)
- XMM(2)
- XMM(3)
- XMM(4)
- XMM(5)
- XMM(6)
- XMM(7)
- XMM(8)
- XMM(9)
- XMM(10)
- XMM(11)
- XMM(12)
- XMM(13)
- XMM(14)
- XMM(15)
-#undef XMM
- default:
- return NULL;
- }
-
- return NULL;
-}
-
#endif /* ARCH_PERF_REGS_H */
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 9708ae892061..ba429cadb18f 100644
--- a/tools/perf/arch/x86/tests/insn-x86-dat-32.c
+++ b/tools/perf/arch/x86/tests/insn-x86-dat-32.c
@@ -2197,6 +2197,924 @@
"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)",},
+{{0x62, 0xf5, 0x6c, 0x48, 0x58, 0xcb, }, 6, 0, "", "",
+"62 f5 6c 48 58 cb \tvaddph %zmm3,%zmm2,%zmm1",},
+{{0x62, 0xf5, 0x6c, 0x48, 0x58, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6c 48 58 8c c8 78 56 34 12 \tvaddph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",},
+{{0x62, 0xf5, 0x6c, 0x08, 0x58, 0xcb, }, 6, 0, "", "",
+"62 f5 6c 08 58 cb \tvaddph %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x6c, 0x08, 0x58, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6c 08 58 8c c8 78 56 34 12 \tvaddph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x6c, 0x28, 0x58, 0xcb, }, 6, 0, "", "",
+"62 f5 6c 28 58 cb \tvaddph %ymm3,%ymm2,%ymm1",},
+{{0x62, 0xf5, 0x6c, 0x28, 0x58, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6c 28 58 8c c8 78 56 34 12 \tvaddph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",},
+{{0x62, 0xf5, 0x6e, 0x08, 0x58, 0xcb, }, 6, 0, "", "",
+"62 f5 6e 08 58 cb \tvaddsh %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x6e, 0x08, 0x58, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6e 08 58 8c c8 78 56 34 12 \tvaddsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf3, 0x6c, 0x48, 0xc2, 0xeb, 0x12, }, 7, 0, "", "",
+"62 f3 6c 48 c2 eb 12 \tvcmple_oqph %zmm3,%zmm2,%k5",},
+{{0x62, 0xf3, 0x6c, 0x48, 0xc2, 0xac, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "",
+"62 f3 6c 48 c2 ac c8 78 56 34 12 12 \tvcmple_oqph 0x12345678(%eax,%ecx,8),%zmm2,%k5",},
+{{0x62, 0xf3, 0x6c, 0x08, 0xc2, 0xeb, 0x12, }, 7, 0, "", "",
+"62 f3 6c 08 c2 eb 12 \tvcmple_oqph %xmm3,%xmm2,%k5",},
+{{0x62, 0xf3, 0x6c, 0x08, 0xc2, 0xac, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "",
+"62 f3 6c 08 c2 ac c8 78 56 34 12 12 \tvcmple_oqph 0x12345678(%eax,%ecx,8),%xmm2,%k5",},
+{{0x62, 0xf3, 0x6c, 0x28, 0xc2, 0xeb, 0x12, }, 7, 0, "", "",
+"62 f3 6c 28 c2 eb 12 \tvcmple_oqph %ymm3,%ymm2,%k5",},
+{{0x62, 0xf3, 0x6c, 0x28, 0xc2, 0xac, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "",
+"62 f3 6c 28 c2 ac c8 78 56 34 12 12 \tvcmple_oqph 0x12345678(%eax,%ecx,8),%ymm2,%k5",},
+{{0x62, 0xf3, 0x6e, 0x08, 0xc2, 0xeb, 0x12, }, 7, 0, "", "",
+"62 f3 6e 08 c2 eb 12 \tvcmple_oqsh %xmm3,%xmm2,%k5",},
+{{0x62, 0xf3, 0x6e, 0x08, 0xc2, 0xac, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "",
+"62 f3 6e 08 c2 ac c8 78 56 34 12 12 \tvcmple_oqsh 0x12345678(%eax,%ecx,8),%xmm2,%k5",},
+{{0x62, 0xf5, 0x7c, 0x08, 0x2f, 0xca, }, 6, 0, "", "",
+"62 f5 7c 08 2f ca \tvcomish %xmm2,%xmm1",},
+{{0x62, 0xf5, 0x7c, 0x08, 0x2f, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7c 08 2f 8c c8 78 56 34 12 \tvcomish 0x12345678(%eax,%ecx,8),%xmm1",},
+{{0x62, 0xf5, 0x7c, 0x48, 0x5b, 0xca, }, 6, 0, "", "",
+"62 f5 7c 48 5b ca \tvcvtdq2ph %zmm2,%ymm1",},
+{{0x62, 0xf5, 0x7c, 0x48, 0x5b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7c 48 5b 8c c8 78 56 34 12 \tvcvtdq2ph 0x12345678(%eax,%ecx,8),%ymm1",},
+{{0x62, 0xf5, 0x7c, 0x08, 0x5b, 0xca, }, 6, 0, "", "",
+"62 f5 7c 08 5b ca \tvcvtdq2ph %xmm2,%xmm1",},
+{{0x62, 0xf5, 0x7c, 0x28, 0x5b, 0xca, }, 6, 0, "", "",
+"62 f5 7c 28 5b ca \tvcvtdq2ph %ymm2,%xmm1",},
+{{0x62, 0xf5, 0xfd, 0x48, 0x5a, 0xca, }, 6, 0, "", "",
+"62 f5 fd 48 5a ca \tvcvtpd2ph %zmm2,%xmm1",},
+{{0x62, 0xf5, 0xfd, 0x08, 0x5a, 0xca, }, 6, 0, "", "",
+"62 f5 fd 08 5a ca \tvcvtpd2ph %xmm2,%xmm1",},
+{{0x62, 0xf5, 0xfd, 0x28, 0x5a, 0xca, }, 6, 0, "", "",
+"62 f5 fd 28 5a ca \tvcvtpd2ph %ymm2,%xmm1",},
+{{0x62, 0xf5, 0x7d, 0x48, 0x5b, 0xca, }, 6, 0, "", "",
+"62 f5 7d 48 5b ca \tvcvtph2dq %ymm2,%zmm1",},
+{{0x62, 0xf5, 0x7d, 0x48, 0x5b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7d 48 5b 8c c8 78 56 34 12 \tvcvtph2dq 0x12345678(%eax,%ecx,8),%zmm1",},
+{{0x62, 0xf5, 0x7d, 0x08, 0x5b, 0xca, }, 6, 0, "", "",
+"62 f5 7d 08 5b ca \tvcvtph2dq %xmm2,%xmm1",},
+{{0x62, 0xf5, 0x7d, 0x08, 0x5b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7d 08 5b 8c c8 78 56 34 12 \tvcvtph2dq 0x12345678(%eax,%ecx,8),%xmm1",},
+{{0x62, 0xf5, 0x7d, 0x28, 0x5b, 0xca, }, 6, 0, "", "",
+"62 f5 7d 28 5b ca \tvcvtph2dq %xmm2,%ymm1",},
+{{0x62, 0xf5, 0x7d, 0x28, 0x5b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7d 28 5b 8c c8 78 56 34 12 \tvcvtph2dq 0x12345678(%eax,%ecx,8),%ymm1",},
+{{0x62, 0xf5, 0x7c, 0x48, 0x5a, 0xca, }, 6, 0, "", "",
+"62 f5 7c 48 5a ca \tvcvtph2pd %xmm2,%zmm1",},
+{{0x62, 0xf5, 0x7c, 0x48, 0x5a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7c 48 5a 8c c8 78 56 34 12 \tvcvtph2pd 0x12345678(%eax,%ecx,8),%zmm1",},
+{{0x62, 0xf5, 0x7c, 0x08, 0x5a, 0xca, }, 6, 0, "", "",
+"62 f5 7c 08 5a ca \tvcvtph2pd %xmm2,%xmm1",},
+{{0x62, 0xf5, 0x7c, 0x08, 0x5a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7c 08 5a 8c c8 78 56 34 12 \tvcvtph2pd 0x12345678(%eax,%ecx,8),%xmm1",},
+{{0x62, 0xf5, 0x7c, 0x28, 0x5a, 0xca, }, 6, 0, "", "",
+"62 f5 7c 28 5a ca \tvcvtph2pd %xmm2,%ymm1",},
+{{0x62, 0xf5, 0x7c, 0x28, 0x5a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7c 28 5a 8c c8 78 56 34 12 \tvcvtph2pd 0x12345678(%eax,%ecx,8),%ymm1",},
+{{0x62, 0xf2, 0x7d, 0x48, 0x13, 0xca, }, 6, 0, "", "",
+"62 f2 7d 48 13 ca \tvcvtph2ps %ymm2,%zmm1",},
+{{0x62, 0xf2, 0x7d, 0x48, 0x13, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f2 7d 48 13 8c c8 78 56 34 12 \tvcvtph2ps 0x12345678(%eax,%ecx,8),%zmm1",},
+{{0xc4, 0xe2, 0x79, 0x13, 0xca, }, 5, 0, "", "",
+"c4 e2 79 13 ca \tvcvtph2ps %xmm2,%xmm1",},
+{{0xc4, 0xe2, 0x79, 0x13, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "",
+"c4 e2 79 13 8c c8 78 56 34 12 \tvcvtph2ps 0x12345678(%eax,%ecx,8),%xmm1",},
+{{0xc4, 0xe2, 0x7d, 0x13, 0xca, }, 5, 0, "", "",
+"c4 e2 7d 13 ca \tvcvtph2ps %xmm2,%ymm1",},
+{{0xc4, 0xe2, 0x7d, 0x13, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "",
+"c4 e2 7d 13 8c c8 78 56 34 12 \tvcvtph2ps 0x12345678(%eax,%ecx,8),%ymm1",},
+{{0xc4, 0xe2, 0x79, 0x13, 0xca, }, 5, 0, "", "",
+"c4 e2 79 13 ca \tvcvtph2ps %xmm2,%xmm1",},
+{{0xc4, 0xe2, 0x79, 0x13, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "",
+"c4 e2 79 13 8c c8 78 56 34 12 \tvcvtph2ps 0x12345678(%eax,%ecx,8),%xmm1",},
+{{0xc4, 0xe2, 0x7d, 0x13, 0xca, }, 5, 0, "", "",
+"c4 e2 7d 13 ca \tvcvtph2ps %xmm2,%ymm1",},
+{{0xc4, 0xe2, 0x7d, 0x13, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "",
+"c4 e2 7d 13 8c c8 78 56 34 12 \tvcvtph2ps 0x12345678(%eax,%ecx,8),%ymm1",},
+{{0x62, 0xf6, 0x7d, 0x48, 0x13, 0xca, }, 6, 0, "", "",
+"62 f6 7d 48 13 ca \tvcvtph2psx %ymm2,%zmm1",},
+{{0x62, 0xf6, 0x7d, 0x48, 0x13, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 7d 48 13 8c c8 78 56 34 12 \tvcvtph2psx 0x12345678(%eax,%ecx,8),%zmm1",},
+{{0x62, 0xf6, 0x7d, 0x08, 0x13, 0xca, }, 6, 0, "", "",
+"62 f6 7d 08 13 ca \tvcvtph2psx %xmm2,%xmm1",},
+{{0x62, 0xf6, 0x7d, 0x08, 0x13, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 7d 08 13 8c c8 78 56 34 12 \tvcvtph2psx 0x12345678(%eax,%ecx,8),%xmm1",},
+{{0x62, 0xf6, 0x7d, 0x28, 0x13, 0xca, }, 6, 0, "", "",
+"62 f6 7d 28 13 ca \tvcvtph2psx %xmm2,%ymm1",},
+{{0x62, 0xf6, 0x7d, 0x28, 0x13, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 7d 28 13 8c c8 78 56 34 12 \tvcvtph2psx 0x12345678(%eax,%ecx,8),%ymm1",},
+{{0x62, 0xf5, 0x7d, 0x48, 0x7b, 0xca, }, 6, 0, "", "",
+"62 f5 7d 48 7b ca \tvcvtph2qq %xmm2,%zmm1",},
+{{0x62, 0xf5, 0x7d, 0x48, 0x7b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7d 48 7b 8c c8 78 56 34 12 \tvcvtph2qq 0x12345678(%eax,%ecx,8),%zmm1",},
+{{0x62, 0xf5, 0x7d, 0x08, 0x7b, 0xca, }, 6, 0, "", "",
+"62 f5 7d 08 7b ca \tvcvtph2qq %xmm2,%xmm1",},
+{{0x62, 0xf5, 0x7d, 0x08, 0x7b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7d 08 7b 8c c8 78 56 34 12 \tvcvtph2qq 0x12345678(%eax,%ecx,8),%xmm1",},
+{{0x62, 0xf5, 0x7d, 0x28, 0x7b, 0xca, }, 6, 0, "", "",
+"62 f5 7d 28 7b ca \tvcvtph2qq %xmm2,%ymm1",},
+{{0x62, 0xf5, 0x7d, 0x28, 0x7b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7d 28 7b 8c c8 78 56 34 12 \tvcvtph2qq 0x12345678(%eax,%ecx,8),%ymm1",},
+{{0x62, 0xf5, 0x7c, 0x48, 0x79, 0xca, }, 6, 0, "", "",
+"62 f5 7c 48 79 ca \tvcvtph2udq %ymm2,%zmm1",},
+{{0x62, 0xf5, 0x7c, 0x48, 0x79, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7c 48 79 8c c8 78 56 34 12 \tvcvtph2udq 0x12345678(%eax,%ecx,8),%zmm1",},
+{{0x62, 0xf5, 0x7c, 0x08, 0x79, 0xca, }, 6, 0, "", "",
+"62 f5 7c 08 79 ca \tvcvtph2udq %xmm2,%xmm1",},
+{{0x62, 0xf5, 0x7c, 0x08, 0x79, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7c 08 79 8c c8 78 56 34 12 \tvcvtph2udq 0x12345678(%eax,%ecx,8),%xmm1",},
+{{0x62, 0xf5, 0x7c, 0x28, 0x79, 0xca, }, 6, 0, "", "",
+"62 f5 7c 28 79 ca \tvcvtph2udq %xmm2,%ymm1",},
+{{0x62, 0xf5, 0x7c, 0x28, 0x79, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7c 28 79 8c c8 78 56 34 12 \tvcvtph2udq 0x12345678(%eax,%ecx,8),%ymm1",},
+{{0x62, 0xf5, 0x7d, 0x48, 0x79, 0xca, }, 6, 0, "", "",
+"62 f5 7d 48 79 ca \tvcvtph2uqq %xmm2,%zmm1",},
+{{0x62, 0xf5, 0x7d, 0x48, 0x79, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7d 48 79 8c c8 78 56 34 12 \tvcvtph2uqq 0x12345678(%eax,%ecx,8),%zmm1",},
+{{0x62, 0xf5, 0x7d, 0x08, 0x79, 0xca, }, 6, 0, "", "",
+"62 f5 7d 08 79 ca \tvcvtph2uqq %xmm2,%xmm1",},
+{{0x62, 0xf5, 0x7d, 0x08, 0x79, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7d 08 79 8c c8 78 56 34 12 \tvcvtph2uqq 0x12345678(%eax,%ecx,8),%xmm1",},
+{{0x62, 0xf5, 0x7d, 0x28, 0x79, 0xca, }, 6, 0, "", "",
+"62 f5 7d 28 79 ca \tvcvtph2uqq %xmm2,%ymm1",},
+{{0x62, 0xf5, 0x7d, 0x28, 0x79, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7d 28 79 8c c8 78 56 34 12 \tvcvtph2uqq 0x12345678(%eax,%ecx,8),%ymm1",},
+{{0x62, 0xf5, 0x7c, 0x48, 0x7d, 0xca, }, 6, 0, "", "",
+"62 f5 7c 48 7d ca \tvcvtph2uw %zmm2,%zmm1",},
+{{0x62, 0xf5, 0x7c, 0x48, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7c 48 7d 8c c8 78 56 34 12 \tvcvtph2uw 0x12345678(%eax,%ecx,8),%zmm1",},
+{{0x62, 0xf5, 0x7c, 0x08, 0x7d, 0xca, }, 6, 0, "", "",
+"62 f5 7c 08 7d ca \tvcvtph2uw %xmm2,%xmm1",},
+{{0x62, 0xf5, 0x7c, 0x08, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7c 08 7d 8c c8 78 56 34 12 \tvcvtph2uw 0x12345678(%eax,%ecx,8),%xmm1",},
+{{0x62, 0xf5, 0x7c, 0x28, 0x7d, 0xca, }, 6, 0, "", "",
+"62 f5 7c 28 7d ca \tvcvtph2uw %ymm2,%ymm1",},
+{{0x62, 0xf5, 0x7c, 0x28, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7c 28 7d 8c c8 78 56 34 12 \tvcvtph2uw 0x12345678(%eax,%ecx,8),%ymm1",},
+{{0x62, 0xf5, 0x7d, 0x48, 0x7d, 0xca, }, 6, 0, "", "",
+"62 f5 7d 48 7d ca \tvcvtph2w %zmm2,%zmm1",},
+{{0x62, 0xf5, 0x7d, 0x48, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7d 48 7d 8c c8 78 56 34 12 \tvcvtph2w 0x12345678(%eax,%ecx,8),%zmm1",},
+{{0x62, 0xf5, 0x7d, 0x08, 0x7d, 0xca, }, 6, 0, "", "",
+"62 f5 7d 08 7d ca \tvcvtph2w %xmm2,%xmm1",},
+{{0x62, 0xf5, 0x7d, 0x08, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7d 08 7d 8c c8 78 56 34 12 \tvcvtph2w 0x12345678(%eax,%ecx,8),%xmm1",},
+{{0x62, 0xf5, 0x7d, 0x28, 0x7d, 0xca, }, 6, 0, "", "",
+"62 f5 7d 28 7d ca \tvcvtph2w %ymm2,%ymm1",},
+{{0x62, 0xf5, 0x7d, 0x28, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7d 28 7d 8c c8 78 56 34 12 \tvcvtph2w 0x12345678(%eax,%ecx,8),%ymm1",},
+{{0x62, 0xf3, 0x7d, 0x48, 0x1d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "",
+"62 f3 7d 48 1d 8c c8 78 56 34 12 12 \tvcvtps2ph $0x12,%zmm1,0x12345678(%eax,%ecx,8)",},
+{{0x62, 0xf3, 0x7d, 0x48, 0x1d, 0xd1, 0x12, }, 7, 0, "", "",
+"62 f3 7d 48 1d d1 12 \tvcvtps2ph $0x12,%zmm2,%ymm1",},
+{{0xc4, 0xe3, 0x7d, 0x1d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 11, 0, "", "",
+"c4 e3 7d 1d 8c c8 78 56 34 12 12 \tvcvtps2ph $0x12,%ymm1,0x12345678(%eax,%ecx,8)",},
+{{0xc4, 0xe3, 0x79, 0x1d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 11, 0, "", "",
+"c4 e3 79 1d 8c c8 78 56 34 12 12 \tvcvtps2ph $0x12,%xmm1,0x12345678(%eax,%ecx,8)",},
+{{0xc4, 0xe3, 0x79, 0x1d, 0xd1, 0x12, }, 6, 0, "", "",
+"c4 e3 79 1d d1 12 \tvcvtps2ph $0x12,%xmm2,%xmm1",},
+{{0xc4, 0xe3, 0x7d, 0x1d, 0xd1, 0x12, }, 6, 0, "", "",
+"c4 e3 7d 1d d1 12 \tvcvtps2ph $0x12,%ymm2,%xmm1",},
+{{0xc4, 0xe3, 0x7d, 0x1d, 0xd1, 0x12, }, 6, 0, "", "",
+"c4 e3 7d 1d d1 12 \tvcvtps2ph $0x12,%ymm2,%xmm1",},
+{{0xc4, 0xe3, 0x7d, 0x1d, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 11, 0, "", "",
+"c4 e3 7d 1d 94 c8 78 56 34 12 12 \tvcvtps2ph $0x12,%ymm2,0x12345678(%eax,%ecx,8)",},
+{{0xc4, 0xe3, 0x79, 0x1d, 0xd1, 0x12, }, 6, 0, "", "",
+"c4 e3 79 1d d1 12 \tvcvtps2ph $0x12,%xmm2,%xmm1",},
+{{0xc4, 0xe3, 0x79, 0x1d, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 11, 0, "", "",
+"c4 e3 79 1d 94 c8 78 56 34 12 12 \tvcvtps2ph $0x12,%xmm2,0x12345678(%eax,%ecx,8)",},
+{{0x62, 0xf5, 0x7d, 0x48, 0x1d, 0xca, }, 6, 0, "", "",
+"62 f5 7d 48 1d ca \tvcvtps2phx %zmm2,%ymm1",},
+{{0x62, 0xf5, 0x7d, 0x48, 0x1d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7d 48 1d 8c c8 78 56 34 12 \tvcvtps2phx 0x12345678(%eax,%ecx,8),%ymm1",},
+{{0x62, 0xf5, 0x7d, 0x08, 0x1d, 0xca, }, 6, 0, "", "",
+"62 f5 7d 08 1d ca \tvcvtps2phx %xmm2,%xmm1",},
+{{0x62, 0xf5, 0x7d, 0x28, 0x1d, 0xca, }, 6, 0, "", "",
+"62 f5 7d 28 1d ca \tvcvtps2phx %ymm2,%xmm1",},
+{{0x62, 0xf5, 0xfc, 0x48, 0x5b, 0xca, }, 6, 0, "", "",
+"62 f5 fc 48 5b ca \tvcvtqq2ph %zmm2,%xmm1",},
+{{0x62, 0xf5, 0xfc, 0x08, 0x5b, 0xca, }, 6, 0, "", "",
+"62 f5 fc 08 5b ca \tvcvtqq2ph %xmm2,%xmm1",},
+{{0x62, 0xf5, 0xfc, 0x28, 0x5b, 0xca, }, 6, 0, "", "",
+"62 f5 fc 28 5b ca \tvcvtqq2ph %ymm2,%xmm1",},
+{{0x62, 0xf5, 0xef, 0x08, 0x5a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 ef 08 5a 8c c8 78 56 34 12 \tvcvtsd2sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x6e, 0x08, 0x5a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6e 08 5a 8c c8 78 56 34 12 \tvcvtsh2sd 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x7e, 0x08, 0x2d, 0x84, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7e 08 2d 84 c8 78 56 34 12 \tvcvtsh2si 0x12345678(%eax,%ecx,8),%eax",},
+{{0x62, 0xf6, 0x6c, 0x08, 0x13, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6c 08 13 8c c8 78 56 34 12 \tvcvtsh2ss 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x7e, 0x08, 0x79, 0xc1, }, 6, 0, "", "",
+"62 f5 7e 08 79 c1 \tvcvtsh2usi %xmm1,%eax",},
+{{0x62, 0xf5, 0x7e, 0x08, 0x79, 0x84, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7e 08 79 84 c8 78 56 34 12 \tvcvtsh2usi 0x12345678(%eax,%ecx,8),%eax",},
+{{0x62, 0xf5, 0x6e, 0x08, 0x2a, 0xc8, }, 6, 0, "", "",
+"62 f5 6e 08 2a c8 \tvcvtsi2sh %eax,%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x6e, 0x08, 0x2a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6e 08 2a 8c c8 78 56 34 12 \tvcvtsi2sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x6e, 0x08, 0x2a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6e 08 2a 8c c8 78 56 34 12 \tvcvtsi2sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x6c, 0x08, 0x1d, 0xcb, }, 6, 0, "", "",
+"62 f5 6c 08 1d cb \tvcvtss2sh %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x6c, 0x08, 0x1d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6c 08 1d 8c c8 78 56 34 12 \tvcvtss2sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x7e, 0x48, 0x5b, 0xca, }, 6, 0, "", "",
+"62 f5 7e 48 5b ca \tvcvttph2dq %ymm2,%zmm1",},
+{{0x62, 0xf5, 0x7e, 0x48, 0x5b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7e 48 5b 8c c8 78 56 34 12 \tvcvttph2dq 0x12345678(%eax,%ecx,8),%zmm1",},
+{{0x62, 0xf5, 0x7e, 0x08, 0x5b, 0xca, }, 6, 0, "", "",
+"62 f5 7e 08 5b ca \tvcvttph2dq %xmm2,%xmm1",},
+{{0x62, 0xf5, 0x7e, 0x08, 0x5b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7e 08 5b 8c c8 78 56 34 12 \tvcvttph2dq 0x12345678(%eax,%ecx,8),%xmm1",},
+{{0x62, 0xf5, 0x7e, 0x28, 0x5b, 0xca, }, 6, 0, "", "",
+"62 f5 7e 28 5b ca \tvcvttph2dq %xmm2,%ymm1",},
+{{0x62, 0xf5, 0x7e, 0x28, 0x5b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7e 28 5b 8c c8 78 56 34 12 \tvcvttph2dq 0x12345678(%eax,%ecx,8),%ymm1",},
+{{0x62, 0xf5, 0x7d, 0x48, 0x7a, 0xca, }, 6, 0, "", "",
+"62 f5 7d 48 7a ca \tvcvttph2qq %xmm2,%zmm1",},
+{{0x62, 0xf5, 0x7d, 0x48, 0x7a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7d 48 7a 8c c8 78 56 34 12 \tvcvttph2qq 0x12345678(%eax,%ecx,8),%zmm1",},
+{{0x62, 0xf5, 0x7d, 0x08, 0x7a, 0xca, }, 6, 0, "", "",
+"62 f5 7d 08 7a ca \tvcvttph2qq %xmm2,%xmm1",},
+{{0x62, 0xf5, 0x7d, 0x08, 0x7a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7d 08 7a 8c c8 78 56 34 12 \tvcvttph2qq 0x12345678(%eax,%ecx,8),%xmm1",},
+{{0x62, 0xf5, 0x7d, 0x28, 0x7a, 0xca, }, 6, 0, "", "",
+"62 f5 7d 28 7a ca \tvcvttph2qq %xmm2,%ymm1",},
+{{0x62, 0xf5, 0x7d, 0x28, 0x7a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7d 28 7a 8c c8 78 56 34 12 \tvcvttph2qq 0x12345678(%eax,%ecx,8),%ymm1",},
+{{0x62, 0xf5, 0x7c, 0x48, 0x78, 0xca, }, 6, 0, "", "",
+"62 f5 7c 48 78 ca \tvcvttph2udq %ymm2,%zmm1",},
+{{0x62, 0xf5, 0x7c, 0x48, 0x78, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7c 48 78 8c c8 78 56 34 12 \tvcvttph2udq 0x12345678(%eax,%ecx,8),%zmm1",},
+{{0x62, 0xf5, 0x7c, 0x08, 0x78, 0xca, }, 6, 0, "", "",
+"62 f5 7c 08 78 ca \tvcvttph2udq %xmm2,%xmm1",},
+{{0x62, 0xf5, 0x7c, 0x08, 0x78, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7c 08 78 8c c8 78 56 34 12 \tvcvttph2udq 0x12345678(%eax,%ecx,8),%xmm1",},
+{{0x62, 0xf5, 0x7c, 0x28, 0x78, 0xca, }, 6, 0, "", "",
+"62 f5 7c 28 78 ca \tvcvttph2udq %xmm2,%ymm1",},
+{{0x62, 0xf5, 0x7c, 0x28, 0x78, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7c 28 78 8c c8 78 56 34 12 \tvcvttph2udq 0x12345678(%eax,%ecx,8),%ymm1",},
+{{0x62, 0xf5, 0x7d, 0x48, 0x78, 0xca, }, 6, 0, "", "",
+"62 f5 7d 48 78 ca \tvcvttph2uqq %xmm2,%zmm1",},
+{{0x62, 0xf5, 0x7d, 0x48, 0x78, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7d 48 78 8c c8 78 56 34 12 \tvcvttph2uqq 0x12345678(%eax,%ecx,8),%zmm1",},
+{{0x62, 0xf5, 0x7d, 0x08, 0x78, 0xca, }, 6, 0, "", "",
+"62 f5 7d 08 78 ca \tvcvttph2uqq %xmm2,%xmm1",},
+{{0x62, 0xf5, 0x7d, 0x08, 0x78, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7d 08 78 8c c8 78 56 34 12 \tvcvttph2uqq 0x12345678(%eax,%ecx,8),%xmm1",},
+{{0x62, 0xf5, 0x7d, 0x28, 0x78, 0xca, }, 6, 0, "", "",
+"62 f5 7d 28 78 ca \tvcvttph2uqq %xmm2,%ymm1",},
+{{0x62, 0xf5, 0x7d, 0x28, 0x78, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7d 28 78 8c c8 78 56 34 12 \tvcvttph2uqq 0x12345678(%eax,%ecx,8),%ymm1",},
+{{0x62, 0xf5, 0x7c, 0x48, 0x7c, 0xca, }, 6, 0, "", "",
+"62 f5 7c 48 7c ca \tvcvttph2uw %zmm2,%zmm1",},
+{{0x62, 0xf5, 0x7c, 0x48, 0x7c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7c 48 7c 8c c8 78 56 34 12 \tvcvttph2uw 0x12345678(%eax,%ecx,8),%zmm1",},
+{{0x62, 0xf5, 0x7c, 0x08, 0x7c, 0xca, }, 6, 0, "", "",
+"62 f5 7c 08 7c ca \tvcvttph2uw %xmm2,%xmm1",},
+{{0x62, 0xf5, 0x7c, 0x08, 0x7c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7c 08 7c 8c c8 78 56 34 12 \tvcvttph2uw 0x12345678(%eax,%ecx,8),%xmm1",},
+{{0x62, 0xf5, 0x7c, 0x28, 0x7c, 0xca, }, 6, 0, "", "",
+"62 f5 7c 28 7c ca \tvcvttph2uw %ymm2,%ymm1",},
+{{0x62, 0xf5, 0x7c, 0x28, 0x7c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7c 28 7c 8c c8 78 56 34 12 \tvcvttph2uw 0x12345678(%eax,%ecx,8),%ymm1",},
+{{0x62, 0xf5, 0x7d, 0x48, 0x7c, 0xca, }, 6, 0, "", "",
+"62 f5 7d 48 7c ca \tvcvttph2w %zmm2,%zmm1",},
+{{0x62, 0xf5, 0x7d, 0x48, 0x7c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7d 48 7c 8c c8 78 56 34 12 \tvcvttph2w 0x12345678(%eax,%ecx,8),%zmm1",},
+{{0x62, 0xf5, 0x7d, 0x08, 0x7c, 0xca, }, 6, 0, "", "",
+"62 f5 7d 08 7c ca \tvcvttph2w %xmm2,%xmm1",},
+{{0x62, 0xf5, 0x7d, 0x08, 0x7c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7d 08 7c 8c c8 78 56 34 12 \tvcvttph2w 0x12345678(%eax,%ecx,8),%xmm1",},
+{{0x62, 0xf5, 0x7d, 0x28, 0x7c, 0xca, }, 6, 0, "", "",
+"62 f5 7d 28 7c ca \tvcvttph2w %ymm2,%ymm1",},
+{{0x62, 0xf5, 0x7d, 0x28, 0x7c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7d 28 7c 8c c8 78 56 34 12 \tvcvttph2w 0x12345678(%eax,%ecx,8),%ymm1",},
+{{0x62, 0xf5, 0x7e, 0x08, 0x2c, 0xc1, }, 6, 0, "", "",
+"62 f5 7e 08 2c c1 \tvcvttsh2si %xmm1,%eax",},
+{{0x62, 0xf5, 0x7e, 0x08, 0x2c, 0x84, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7e 08 2c 84 c8 78 56 34 12 \tvcvttsh2si 0x12345678(%eax,%ecx,8),%eax",},
+{{0x62, 0xf5, 0x7e, 0x08, 0x78, 0xc1, }, 6, 0, "", "",
+"62 f5 7e 08 78 c1 \tvcvttsh2usi %xmm1,%eax",},
+{{0x62, 0xf5, 0x7e, 0x08, 0x78, 0x84, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7e 08 78 84 c8 78 56 34 12 \tvcvttsh2usi 0x12345678(%eax,%ecx,8),%eax",},
+{{0x62, 0xf5, 0x7f, 0x48, 0x7a, 0xca, }, 6, 0, "", "",
+"62 f5 7f 48 7a ca \tvcvtudq2ph %zmm2,%ymm1",},
+{{0x62, 0xf5, 0x7f, 0x48, 0x7a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7f 48 7a 8c c8 78 56 34 12 \tvcvtudq2ph 0x12345678(%eax,%ecx,8),%ymm1",},
+{{0x62, 0xf5, 0x7f, 0x08, 0x7a, 0xca, }, 6, 0, "", "",
+"62 f5 7f 08 7a ca \tvcvtudq2ph %xmm2,%xmm1",},
+{{0x62, 0xf5, 0x7f, 0x28, 0x7a, 0xca, }, 6, 0, "", "",
+"62 f5 7f 28 7a ca \tvcvtudq2ph %ymm2,%xmm1",},
+{{0x62, 0xf5, 0xff, 0x48, 0x7a, 0xca, }, 6, 0, "", "",
+"62 f5 ff 48 7a ca \tvcvtuqq2ph %zmm2,%xmm1",},
+{{0x62, 0xf5, 0xff, 0x08, 0x7a, 0xca, }, 6, 0, "", "",
+"62 f5 ff 08 7a ca \tvcvtuqq2ph %xmm2,%xmm1",},
+{{0x62, 0xf5, 0xff, 0x28, 0x7a, 0xca, }, 6, 0, "", "",
+"62 f5 ff 28 7a ca \tvcvtuqq2ph %ymm2,%xmm1",},
+{{0x62, 0xf5, 0x6e, 0x08, 0x7b, 0xc8, }, 6, 0, "", "",
+"62 f5 6e 08 7b c8 \tvcvtusi2sh %eax,%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x6e, 0x08, 0x7b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6e 08 7b 8c c8 78 56 34 12 \tvcvtusi2sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x6e, 0x08, 0x7b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6e 08 7b 8c c8 78 56 34 12 \tvcvtusi2sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x7f, 0x48, 0x7d, 0xca, }, 6, 0, "", "",
+"62 f5 7f 48 7d ca \tvcvtuw2ph %zmm2,%zmm1",},
+{{0x62, 0xf5, 0x7f, 0x48, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7f 48 7d 8c c8 78 56 34 12 \tvcvtuw2ph 0x12345678(%eax,%ecx,8),%zmm1",},
+{{0x62, 0xf5, 0x7f, 0x08, 0x7d, 0xca, }, 6, 0, "", "",
+"62 f5 7f 08 7d ca \tvcvtuw2ph %xmm2,%xmm1",},
+{{0x62, 0xf5, 0x7f, 0x08, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7f 08 7d 8c c8 78 56 34 12 \tvcvtuw2ph 0x12345678(%eax,%ecx,8),%xmm1",},
+{{0x62, 0xf5, 0x7f, 0x28, 0x7d, 0xca, }, 6, 0, "", "",
+"62 f5 7f 28 7d ca \tvcvtuw2ph %ymm2,%ymm1",},
+{{0x62, 0xf5, 0x7f, 0x28, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7f 28 7d 8c c8 78 56 34 12 \tvcvtuw2ph 0x12345678(%eax,%ecx,8),%ymm1",},
+{{0x62, 0xf5, 0x7e, 0x48, 0x7d, 0xca, }, 6, 0, "", "",
+"62 f5 7e 48 7d ca \tvcvtw2ph %zmm2,%zmm1",},
+{{0x62, 0xf5, 0x7e, 0x48, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7e 48 7d 8c c8 78 56 34 12 \tvcvtw2ph 0x12345678(%eax,%ecx,8),%zmm1",},
+{{0x62, 0xf5, 0x7e, 0x08, 0x7d, 0xca, }, 6, 0, "", "",
+"62 f5 7e 08 7d ca \tvcvtw2ph %xmm2,%xmm1",},
+{{0x62, 0xf5, 0x7e, 0x08, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7e 08 7d 8c c8 78 56 34 12 \tvcvtw2ph 0x12345678(%eax,%ecx,8),%xmm1",},
+{{0x62, 0xf5, 0x7e, 0x28, 0x7d, 0xca, }, 6, 0, "", "",
+"62 f5 7e 28 7d ca \tvcvtw2ph %ymm2,%ymm1",},
+{{0x62, 0xf5, 0x7e, 0x28, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7e 28 7d 8c c8 78 56 34 12 \tvcvtw2ph 0x12345678(%eax,%ecx,8),%ymm1",},
+{{0x62, 0xf5, 0x6c, 0x48, 0x5e, 0xcb, }, 6, 0, "", "",
+"62 f5 6c 48 5e cb \tvdivph %zmm3,%zmm2,%zmm1",},
+{{0x62, 0xf5, 0x6c, 0x48, 0x5e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6c 48 5e 8c c8 78 56 34 12 \tvdivph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",},
+{{0x62, 0xf5, 0x6c, 0x08, 0x5e, 0xcb, }, 6, 0, "", "",
+"62 f5 6c 08 5e cb \tvdivph %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x6c, 0x08, 0x5e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6c 08 5e 8c c8 78 56 34 12 \tvdivph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x6c, 0x28, 0x5e, 0xcb, }, 6, 0, "", "",
+"62 f5 6c 28 5e cb \tvdivph %ymm3,%ymm2,%ymm1",},
+{{0x62, 0xf5, 0x6c, 0x28, 0x5e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6c 28 5e 8c c8 78 56 34 12 \tvdivph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",},
+{{0x62, 0xf5, 0x6e, 0x08, 0x5e, 0xcb, }, 6, 0, "", "",
+"62 f5 6e 08 5e cb \tvdivsh %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x6e, 0x08, 0x5e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6e 08 5e 8c c8 78 56 34 12 \tvdivsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6f, 0x48, 0x56, 0xcb, }, 6, 0, "", "",
+"62 f6 6f 48 56 cb \tvfcmaddcph %zmm3,%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6f, 0x48, 0x56, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6f 48 56 8c c8 78 56 34 12 \tvfcmaddcph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6f, 0x08, 0x56, 0xcb, }, 6, 0, "", "",
+"62 f6 6f 08 56 cb \tvfcmaddcph %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6f, 0x08, 0x56, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6f 08 56 8c c8 78 56 34 12 \tvfcmaddcph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6f, 0x28, 0x56, 0xcb, }, 6, 0, "", "",
+"62 f6 6f 28 56 cb \tvfcmaddcph %ymm3,%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6f, 0x28, 0x56, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6f 28 56 8c c8 78 56 34 12 \tvfcmaddcph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6f, 0x08, 0x57, 0xcb, }, 6, 0, "", "",
+"62 f6 6f 08 57 cb \tvfcmaddcsh %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6f, 0x08, 0x57, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6f 08 57 8c c8 78 56 34 12 \tvfcmaddcsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6f, 0x48, 0xd6, 0xcb, }, 6, 0, "", "",
+"62 f6 6f 48 d6 cb \tvfcmulcph %zmm3,%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6f, 0x48, 0xd6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6f 48 d6 8c c8 78 56 34 12 \tvfcmulcph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6f, 0x08, 0xd6, 0xcb, }, 6, 0, "", "",
+"62 f6 6f 08 d6 cb \tvfcmulcph %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6f, 0x08, 0xd6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6f 08 d6 8c c8 78 56 34 12 \tvfcmulcph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6f, 0x28, 0xd6, 0xcb, }, 6, 0, "", "",
+"62 f6 6f 28 d6 cb \tvfcmulcph %ymm3,%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6f, 0x28, 0xd6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6f 28 d6 8c c8 78 56 34 12 \tvfcmulcph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6f, 0x08, 0xd7, 0xcb, }, 6, 0, "", "",
+"62 f6 6f 08 d7 cb \tvfcmulcsh %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6f, 0x08, 0xd7, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6f 08 d7 8c c8 78 56 34 12 \tvfcmulcsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0x98, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 48 98 cb \tvfmadd132ph %zmm3,%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0x98, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 48 98 8c c8 78 56 34 12 \tvfmadd132ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x98, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 98 cb \tvfmadd132ph %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x98, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 98 8c c8 78 56 34 12 \tvfmadd132ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0x98, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 28 98 cb \tvfmadd132ph %ymm3,%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0x98, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 28 98 8c c8 78 56 34 12 \tvfmadd132ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x99, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 99 cb \tvfmadd132sh %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x99, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 99 8c c8 78 56 34 12 \tvfmadd132sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0xa8, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 48 a8 cb \tvfmadd213ph %zmm3,%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0xa8, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 48 a8 8c c8 78 56 34 12 \tvfmadd213ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xa8, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 a8 cb \tvfmadd213ph %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xa8, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 a8 8c c8 78 56 34 12 \tvfmadd213ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0xa8, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 28 a8 cb \tvfmadd213ph %ymm3,%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0xa8, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 28 a8 8c c8 78 56 34 12 \tvfmadd213ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xa9, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 a9 cb \tvfmadd213sh %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xa9, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 a9 8c c8 78 56 34 12 \tvfmadd213sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0xb8, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 48 b8 cb \tvfmadd231ph %zmm3,%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0xb8, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 48 b8 8c c8 78 56 34 12 \tvfmadd231ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xb8, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 b8 cb \tvfmadd231ph %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xb8, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 b8 8c c8 78 56 34 12 \tvfmadd231ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0xb8, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 28 b8 cb \tvfmadd231ph %ymm3,%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0xb8, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 28 b8 8c c8 78 56 34 12 \tvfmadd231ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xb9, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 b9 cb \tvfmadd231sh %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xb9, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 b9 8c c8 78 56 34 12 \tvfmadd231sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6e, 0x48, 0x56, 0xcb, }, 6, 0, "", "",
+"62 f6 6e 48 56 cb \tvfmaddcph %zmm3,%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6e, 0x48, 0x56, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6e 48 56 8c c8 78 56 34 12 \tvfmaddcph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6e, 0x08, 0x56, 0xcb, }, 6, 0, "", "",
+"62 f6 6e 08 56 cb \tvfmaddcph %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6e, 0x08, 0x56, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6e 08 56 8c c8 78 56 34 12 \tvfmaddcph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6e, 0x28, 0x56, 0xcb, }, 6, 0, "", "",
+"62 f6 6e 28 56 cb \tvfmaddcph %ymm3,%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6e, 0x28, 0x56, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6e 28 56 8c c8 78 56 34 12 \tvfmaddcph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6e, 0x08, 0x57, 0xcb, }, 6, 0, "", "",
+"62 f6 6e 08 57 cb \tvfmaddcsh %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6e, 0x08, 0x57, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6e 08 57 8c c8 78 56 34 12 \tvfmaddcsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0x96, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 48 96 cb \tvfmaddsub132ph %zmm3,%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0x96, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 48 96 8c c8 78 56 34 12 \tvfmaddsub132ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x96, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 96 cb \tvfmaddsub132ph %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x96, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 96 8c c8 78 56 34 12 \tvfmaddsub132ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0x96, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 28 96 cb \tvfmaddsub132ph %ymm3,%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0x96, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 28 96 8c c8 78 56 34 12 \tvfmaddsub132ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0xa6, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 48 a6 cb \tvfmaddsub213ph %zmm3,%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0xa6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 48 a6 8c c8 78 56 34 12 \tvfmaddsub213ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xa6, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 a6 cb \tvfmaddsub213ph %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xa6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 a6 8c c8 78 56 34 12 \tvfmaddsub213ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0xa6, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 28 a6 cb \tvfmaddsub213ph %ymm3,%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0xa6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 28 a6 8c c8 78 56 34 12 \tvfmaddsub213ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0xb6, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 48 b6 cb \tvfmaddsub231ph %zmm3,%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0xb6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 48 b6 8c c8 78 56 34 12 \tvfmaddsub231ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xb6, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 b6 cb \tvfmaddsub231ph %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xb6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 b6 8c c8 78 56 34 12 \tvfmaddsub231ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0xb6, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 28 b6 cb \tvfmaddsub231ph %ymm3,%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0xb6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 28 b6 8c c8 78 56 34 12 \tvfmaddsub231ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0x9a, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 48 9a cb \tvfmsub132ph %zmm3,%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0x9a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 48 9a 8c c8 78 56 34 12 \tvfmsub132ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x9a, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 9a cb \tvfmsub132ph %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x9a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 9a 8c c8 78 56 34 12 \tvfmsub132ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0x9a, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 28 9a cb \tvfmsub132ph %ymm3,%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0x9a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 28 9a 8c c8 78 56 34 12 \tvfmsub132ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x9b, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 9b cb \tvfmsub132sh %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x9b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 9b 8c c8 78 56 34 12 \tvfmsub132sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0xaa, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 48 aa cb \tvfmsub213ph %zmm3,%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0xaa, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 48 aa 8c c8 78 56 34 12 \tvfmsub213ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xaa, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 aa cb \tvfmsub213ph %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xaa, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 aa 8c c8 78 56 34 12 \tvfmsub213ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0xaa, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 28 aa cb \tvfmsub213ph %ymm3,%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0xaa, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 28 aa 8c c8 78 56 34 12 \tvfmsub213ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xab, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 ab cb \tvfmsub213sh %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xab, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 ab 8c c8 78 56 34 12 \tvfmsub213sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0xba, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 48 ba cb \tvfmsub231ph %zmm3,%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0xba, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 48 ba 8c c8 78 56 34 12 \tvfmsub231ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xba, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 ba cb \tvfmsub231ph %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xba, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 ba 8c c8 78 56 34 12 \tvfmsub231ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0xba, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 28 ba cb \tvfmsub231ph %ymm3,%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0xba, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 28 ba 8c c8 78 56 34 12 \tvfmsub231ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xbb, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 bb cb \tvfmsub231sh %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xbb, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 bb 8c c8 78 56 34 12 \tvfmsub231sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0x97, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 48 97 cb \tvfmsubadd132ph %zmm3,%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0x97, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 48 97 8c c8 78 56 34 12 \tvfmsubadd132ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x97, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 97 cb \tvfmsubadd132ph %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x97, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 97 8c c8 78 56 34 12 \tvfmsubadd132ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0x97, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 28 97 cb \tvfmsubadd132ph %ymm3,%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0x97, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 28 97 8c c8 78 56 34 12 \tvfmsubadd132ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0xa7, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 48 a7 cb \tvfmsubadd213ph %zmm3,%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0xa7, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 48 a7 8c c8 78 56 34 12 \tvfmsubadd213ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xa7, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 a7 cb \tvfmsubadd213ph %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xa7, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 a7 8c c8 78 56 34 12 \tvfmsubadd213ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0xa7, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 28 a7 cb \tvfmsubadd213ph %ymm3,%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0xa7, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 28 a7 8c c8 78 56 34 12 \tvfmsubadd213ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0xb7, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 48 b7 cb \tvfmsubadd231ph %zmm3,%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0xb7, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 48 b7 8c c8 78 56 34 12 \tvfmsubadd231ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xb7, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 b7 cb \tvfmsubadd231ph %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xb7, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 b7 8c c8 78 56 34 12 \tvfmsubadd231ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0xb7, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 28 b7 cb \tvfmsubadd231ph %ymm3,%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0xb7, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 28 b7 8c c8 78 56 34 12 \tvfmsubadd231ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6e, 0x48, 0xd6, 0xcb, }, 6, 0, "", "",
+"62 f6 6e 48 d6 cb \tvfmulcph %zmm3,%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6e, 0x48, 0xd6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6e 48 d6 8c c8 78 56 34 12 \tvfmulcph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6e, 0x08, 0xd6, 0xcb, }, 6, 0, "", "",
+"62 f6 6e 08 d6 cb \tvfmulcph %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6e, 0x08, 0xd6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6e 08 d6 8c c8 78 56 34 12 \tvfmulcph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6e, 0x28, 0xd6, 0xcb, }, 6, 0, "", "",
+"62 f6 6e 28 d6 cb \tvfmulcph %ymm3,%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6e, 0x28, 0xd6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6e 28 d6 8c c8 78 56 34 12 \tvfmulcph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6e, 0x08, 0xd7, 0xcb, }, 6, 0, "", "",
+"62 f6 6e 08 d7 cb \tvfmulcsh %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6e, 0x08, 0xd7, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6e 08 d7 8c c8 78 56 34 12 \tvfmulcsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0x9c, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 48 9c cb \tvfnmadd132ph %zmm3,%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0x9c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 48 9c 8c c8 78 56 34 12 \tvfnmadd132ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x9c, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 9c cb \tvfnmadd132ph %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x9c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 9c 8c c8 78 56 34 12 \tvfnmadd132ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0x9c, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 28 9c cb \tvfnmadd132ph %ymm3,%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0x9c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 28 9c 8c c8 78 56 34 12 \tvfnmadd132ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x9d, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 9d cb \tvfnmadd132sh %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x9d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 9d 8c c8 78 56 34 12 \tvfnmadd132sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0xac, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 48 ac cb \tvfnmadd213ph %zmm3,%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0xac, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 48 ac 8c c8 78 56 34 12 \tvfnmadd213ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xac, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 ac cb \tvfnmadd213ph %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xac, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 ac 8c c8 78 56 34 12 \tvfnmadd213ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0xac, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 28 ac cb \tvfnmadd213ph %ymm3,%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0xac, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 28 ac 8c c8 78 56 34 12 \tvfnmadd213ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xad, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 ad cb \tvfnmadd213sh %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xad, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 ad 8c c8 78 56 34 12 \tvfnmadd213sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0xbc, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 48 bc cb \tvfnmadd231ph %zmm3,%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0xbc, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 48 bc 8c c8 78 56 34 12 \tvfnmadd231ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xbc, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 bc cb \tvfnmadd231ph %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xbc, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 bc 8c c8 78 56 34 12 \tvfnmadd231ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0xbc, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 28 bc cb \tvfnmadd231ph %ymm3,%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0xbc, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 28 bc 8c c8 78 56 34 12 \tvfnmadd231ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xbd, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 bd cb \tvfnmadd231sh %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xbd, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 bd 8c c8 78 56 34 12 \tvfnmadd231sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0x9e, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 48 9e cb \tvfnmsub132ph %zmm3,%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0x9e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 48 9e 8c c8 78 56 34 12 \tvfnmsub132ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x9e, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 9e cb \tvfnmsub132ph %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x9e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 9e 8c c8 78 56 34 12 \tvfnmsub132ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0x9e, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 28 9e cb \tvfnmsub132ph %ymm3,%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0x9e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 28 9e 8c c8 78 56 34 12 \tvfnmsub132ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x9f, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 9f cb \tvfnmsub132sh %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x9f, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 9f 8c c8 78 56 34 12 \tvfnmsub132sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0xae, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 48 ae cb \tvfnmsub213ph %zmm3,%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0xae, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 48 ae 8c c8 78 56 34 12 \tvfnmsub213ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xae, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 ae cb \tvfnmsub213ph %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xae, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 ae 8c c8 78 56 34 12 \tvfnmsub213ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0xae, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 28 ae cb \tvfnmsub213ph %ymm3,%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0xae, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 28 ae 8c c8 78 56 34 12 \tvfnmsub213ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xaf, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 af cb \tvfnmsub213sh %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xaf, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 af 8c c8 78 56 34 12 \tvfnmsub213sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0xbe, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 48 be cb \tvfnmsub231ph %zmm3,%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0xbe, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 48 be 8c c8 78 56 34 12 \tvfnmsub231ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xbe, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 be cb \tvfnmsub231ph %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xbe, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 be 8c c8 78 56 34 12 \tvfnmsub231ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0xbe, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 28 be cb \tvfnmsub231ph %ymm3,%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0xbe, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 28 be 8c c8 78 56 34 12 \tvfnmsub231ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xbf, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 bf cb \tvfnmsub231sh %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xbf, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 bf 8c c8 78 56 34 12 \tvfnmsub231sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf3, 0x7c, 0x48, 0x66, 0xe9, 0x12, }, 7, 0, "", "",
+"62 f3 7c 48 66 e9 12 \tvfpclassph $0x12,%zmm1,%k5",},
+{{0x62, 0xf3, 0x7c, 0x08, 0x66, 0xe9, 0x12, }, 7, 0, "", "",
+"62 f3 7c 08 66 e9 12 \tvfpclassph $0x12,%xmm1,%k5",},
+{{0x62, 0xf3, 0x7c, 0x28, 0x66, 0xe9, 0x12, }, 7, 0, "", "",
+"62 f3 7c 28 66 e9 12 \tvfpclassph $0x12,%ymm1,%k5",},
+{{0x62, 0xf3, 0x7c, 0x08, 0x67, 0xe9, 0x12, }, 7, 0, "", "",
+"62 f3 7c 08 67 e9 12 \tvfpclasssh $0x12,%xmm1,%k5",},
+{{0x62, 0xf3, 0x7c, 0x08, 0x67, 0xac, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "",
+"62 f3 7c 08 67 ac c8 78 56 34 12 12 \tvfpclasssh $0x12,0x12345678(%eax,%ecx,8),%k5",},
+{{0x62, 0xf6, 0x7d, 0x48, 0x42, 0xca, }, 6, 0, "", "",
+"62 f6 7d 48 42 ca \tvgetexpph %zmm2,%zmm1",},
+{{0x62, 0xf6, 0x7d, 0x48, 0x42, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 7d 48 42 8c c8 78 56 34 12 \tvgetexpph 0x12345678(%eax,%ecx,8),%zmm1",},
+{{0x62, 0xf6, 0x7d, 0x08, 0x42, 0xca, }, 6, 0, "", "",
+"62 f6 7d 08 42 ca \tvgetexpph %xmm2,%xmm1",},
+{{0x62, 0xf6, 0x7d, 0x08, 0x42, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 7d 08 42 8c c8 78 56 34 12 \tvgetexpph 0x12345678(%eax,%ecx,8),%xmm1",},
+{{0x62, 0xf6, 0x7d, 0x28, 0x42, 0xca, }, 6, 0, "", "",
+"62 f6 7d 28 42 ca \tvgetexpph %ymm2,%ymm1",},
+{{0x62, 0xf6, 0x7d, 0x28, 0x42, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 7d 28 42 8c c8 78 56 34 12 \tvgetexpph 0x12345678(%eax,%ecx,8),%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x43, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 43 cb \tvgetexpsh %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x43, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 43 8c c8 78 56 34 12 \tvgetexpsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf3, 0x7c, 0x48, 0x26, 0xca, 0x12, }, 7, 0, "", "",
+"62 f3 7c 48 26 ca 12 \tvgetmantph $0x12,%zmm2,%zmm1",},
+{{0x62, 0xf3, 0x7c, 0x48, 0x26, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "",
+"62 f3 7c 48 26 8c c8 78 56 34 12 12 \tvgetmantph $0x12,0x12345678(%eax,%ecx,8),%zmm1",},
+{{0x62, 0xf3, 0x7c, 0x08, 0x26, 0xca, 0x12, }, 7, 0, "", "",
+"62 f3 7c 08 26 ca 12 \tvgetmantph $0x12,%xmm2,%xmm1",},
+{{0x62, 0xf3, 0x7c, 0x08, 0x26, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "",
+"62 f3 7c 08 26 8c c8 78 56 34 12 12 \tvgetmantph $0x12,0x12345678(%eax,%ecx,8),%xmm1",},
+{{0x62, 0xf3, 0x7c, 0x28, 0x26, 0xca, 0x12, }, 7, 0, "", "",
+"62 f3 7c 28 26 ca 12 \tvgetmantph $0x12,%ymm2,%ymm1",},
+{{0x62, 0xf3, 0x7c, 0x28, 0x26, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "",
+"62 f3 7c 28 26 8c c8 78 56 34 12 12 \tvgetmantph $0x12,0x12345678(%eax,%ecx,8),%ymm1",},
+{{0x62, 0xf3, 0x6c, 0x08, 0x27, 0xcb, 0x12, }, 7, 0, "", "",
+"62 f3 6c 08 27 cb 12 \tvgetmantsh $0x12,%xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf3, 0x6c, 0x08, 0x27, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "",
+"62 f3 6c 08 27 8c c8 78 56 34 12 12 \tvgetmantsh $0x12,0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x6c, 0x48, 0x5f, 0xcb, }, 6, 0, "", "",
+"62 f5 6c 48 5f cb \tvmaxph %zmm3,%zmm2,%zmm1",},
+{{0x62, 0xf5, 0x6c, 0x48, 0x5f, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6c 48 5f 8c c8 78 56 34 12 \tvmaxph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",},
+{{0x62, 0xf5, 0x6c, 0x08, 0x5f, 0xcb, }, 6, 0, "", "",
+"62 f5 6c 08 5f cb \tvmaxph %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x6c, 0x08, 0x5f, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6c 08 5f 8c c8 78 56 34 12 \tvmaxph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x6c, 0x28, 0x5f, 0xcb, }, 6, 0, "", "",
+"62 f5 6c 28 5f cb \tvmaxph %ymm3,%ymm2,%ymm1",},
+{{0x62, 0xf5, 0x6c, 0x28, 0x5f, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6c 28 5f 8c c8 78 56 34 12 \tvmaxph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",},
+{{0x62, 0xf5, 0x6e, 0x08, 0x5f, 0xcb, }, 6, 0, "", "",
+"62 f5 6e 08 5f cb \tvmaxsh %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x6e, 0x08, 0x5f, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6e 08 5f 8c c8 78 56 34 12 \tvmaxsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x6c, 0x48, 0x5d, 0xcb, }, 6, 0, "", "",
+"62 f5 6c 48 5d cb \tvminph %zmm3,%zmm2,%zmm1",},
+{{0x62, 0xf5, 0x6c, 0x48, 0x5d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6c 48 5d 8c c8 78 56 34 12 \tvminph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",},
+{{0x62, 0xf5, 0x6c, 0x08, 0x5d, 0xcb, }, 6, 0, "", "",
+"62 f5 6c 08 5d cb \tvminph %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x6c, 0x08, 0x5d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6c 08 5d 8c c8 78 56 34 12 \tvminph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x6c, 0x28, 0x5d, 0xcb, }, 6, 0, "", "",
+"62 f5 6c 28 5d cb \tvminph %ymm3,%ymm2,%ymm1",},
+{{0x62, 0xf5, 0x6c, 0x28, 0x5d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6c 28 5d 8c c8 78 56 34 12 \tvminph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",},
+{{0x62, 0xf5, 0x6e, 0x08, 0x5d, 0xcb, }, 6, 0, "", "",
+"62 f5 6e 08 5d cb \tvminsh %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x6e, 0x08, 0x5d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6e 08 5d 8c c8 78 56 34 12 \tvminsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x7e, 0x08, 0x11, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7e 08 11 8c c8 78 56 34 12 \tvmovsh %xmm1,0x12345678(%eax,%ecx,8)",},
+{{0x62, 0xf5, 0x7e, 0x08, 0x10, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7e 08 10 8c c8 78 56 34 12 \tvmovsh 0x12345678(%eax,%ecx,8),%xmm1",},
+{{0x62, 0xf5, 0x6e, 0x08, 0x10, 0xcb, }, 6, 0, "", "",
+"62 f5 6e 08 10 cb \tvmovsh %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x7d, 0x08, 0x7e, 0xc8, }, 6, 0, "", "",
+"62 f5 7d 08 7e c8 \tvmovw %xmm1,%eax",},
+{{0x62, 0xf5, 0x7d, 0x08, 0x7e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7d 08 7e 8c c8 78 56 34 12 \tvmovw %xmm1,0x12345678(%eax,%ecx,8)",},
+{{0x62, 0xf5, 0x7d, 0x08, 0x6e, 0xc8, }, 6, 0, "", "",
+"62 f5 7d 08 6e c8 \tvmovw %eax,%xmm1",},
+{{0x62, 0xf5, 0x7d, 0x08, 0x6e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7d 08 6e 8c c8 78 56 34 12 \tvmovw 0x12345678(%eax,%ecx,8),%xmm1",},
+{{0x62, 0xf5, 0x6c, 0x48, 0x59, 0xcb, }, 6, 0, "", "",
+"62 f5 6c 48 59 cb \tvmulph %zmm3,%zmm2,%zmm1",},
+{{0x62, 0xf5, 0x6c, 0x48, 0x59, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6c 48 59 8c c8 78 56 34 12 \tvmulph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",},
+{{0x62, 0xf5, 0x6c, 0x08, 0x59, 0xcb, }, 6, 0, "", "",
+"62 f5 6c 08 59 cb \tvmulph %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x6c, 0x08, 0x59, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6c 08 59 8c c8 78 56 34 12 \tvmulph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x6c, 0x28, 0x59, 0xcb, }, 6, 0, "", "",
+"62 f5 6c 28 59 cb \tvmulph %ymm3,%ymm2,%ymm1",},
+{{0x62, 0xf5, 0x6c, 0x28, 0x59, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6c 28 59 8c c8 78 56 34 12 \tvmulph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",},
+{{0x62, 0xf5, 0x6e, 0x08, 0x59, 0xcb, }, 6, 0, "", "",
+"62 f5 6e 08 59 cb \tvmulsh %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x6e, 0x08, 0x59, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6e 08 59 8c c8 78 56 34 12 \tvmulsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x7d, 0x48, 0x4c, 0xca, }, 6, 0, "", "",
+"62 f6 7d 48 4c ca \tvrcpph %zmm2,%zmm1",},
+{{0x62, 0xf6, 0x7d, 0x48, 0x4c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 7d 48 4c 8c c8 78 56 34 12 \tvrcpph 0x12345678(%eax,%ecx,8),%zmm1",},
+{{0x62, 0xf6, 0x7d, 0x08, 0x4c, 0xca, }, 6, 0, "", "",
+"62 f6 7d 08 4c ca \tvrcpph %xmm2,%xmm1",},
+{{0x62, 0xf6, 0x7d, 0x08, 0x4c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 7d 08 4c 8c c8 78 56 34 12 \tvrcpph 0x12345678(%eax,%ecx,8),%xmm1",},
+{{0x62, 0xf6, 0x7d, 0x28, 0x4c, 0xca, }, 6, 0, "", "",
+"62 f6 7d 28 4c ca \tvrcpph %ymm2,%ymm1",},
+{{0x62, 0xf6, 0x7d, 0x28, 0x4c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 7d 28 4c 8c c8 78 56 34 12 \tvrcpph 0x12345678(%eax,%ecx,8),%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x4d, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 4d cb \tvrcpsh %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x4d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 4d 8c c8 78 56 34 12 \tvrcpsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf3, 0x7c, 0x48, 0x56, 0xca, 0x12, }, 7, 0, "", "",
+"62 f3 7c 48 56 ca 12 \tvreduceph $0x12,%zmm2,%zmm1",},
+{{0x62, 0xf3, 0x7c, 0x48, 0x56, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "",
+"62 f3 7c 48 56 8c c8 78 56 34 12 12 \tvreduceph $0x12,0x12345678(%eax,%ecx,8),%zmm1",},
+{{0x62, 0xf3, 0x7c, 0x08, 0x56, 0xca, 0x12, }, 7, 0, "", "",
+"62 f3 7c 08 56 ca 12 \tvreduceph $0x12,%xmm2,%xmm1",},
+{{0x62, 0xf3, 0x7c, 0x08, 0x56, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "",
+"62 f3 7c 08 56 8c c8 78 56 34 12 12 \tvreduceph $0x12,0x12345678(%eax,%ecx,8),%xmm1",},
+{{0x62, 0xf3, 0x7c, 0x28, 0x56, 0xca, 0x12, }, 7, 0, "", "",
+"62 f3 7c 28 56 ca 12 \tvreduceph $0x12,%ymm2,%ymm1",},
+{{0x62, 0xf3, 0x7c, 0x28, 0x56, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "",
+"62 f3 7c 28 56 8c c8 78 56 34 12 12 \tvreduceph $0x12,0x12345678(%eax,%ecx,8),%ymm1",},
+{{0x62, 0xf3, 0x6c, 0x08, 0x57, 0xcb, 0x12, }, 7, 0, "", "",
+"62 f3 6c 08 57 cb 12 \tvreducesh $0x12,%xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf3, 0x6c, 0x08, 0x57, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "",
+"62 f3 6c 08 57 8c c8 78 56 34 12 12 \tvreducesh $0x12,0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf3, 0x7c, 0x48, 0x08, 0xca, 0x12, }, 7, 0, "", "",
+"62 f3 7c 48 08 ca 12 \tvrndscaleph $0x12,%zmm2,%zmm1",},
+{{0x62, 0xf3, 0x7c, 0x48, 0x08, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "",
+"62 f3 7c 48 08 8c c8 78 56 34 12 12 \tvrndscaleph $0x12,0x12345678(%eax,%ecx,8),%zmm1",},
+{{0x62, 0xf3, 0x7c, 0x08, 0x08, 0xca, 0x12, }, 7, 0, "", "",
+"62 f3 7c 08 08 ca 12 \tvrndscaleph $0x12,%xmm2,%xmm1",},
+{{0x62, 0xf3, 0x7c, 0x08, 0x08, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "",
+"62 f3 7c 08 08 8c c8 78 56 34 12 12 \tvrndscaleph $0x12,0x12345678(%eax,%ecx,8),%xmm1",},
+{{0x62, 0xf3, 0x7c, 0x28, 0x08, 0xca, 0x12, }, 7, 0, "", "",
+"62 f3 7c 28 08 ca 12 \tvrndscaleph $0x12,%ymm2,%ymm1",},
+{{0x62, 0xf3, 0x7c, 0x28, 0x08, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "",
+"62 f3 7c 28 08 8c c8 78 56 34 12 12 \tvrndscaleph $0x12,0x12345678(%eax,%ecx,8),%ymm1",},
+{{0x62, 0xf3, 0x6c, 0x08, 0x0a, 0xcb, 0x12, }, 7, 0, "", "",
+"62 f3 6c 08 0a cb 12 \tvrndscalesh $0x12,%xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf3, 0x6c, 0x08, 0x0a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "",
+"62 f3 6c 08 0a 8c c8 78 56 34 12 12 \tvrndscalesh $0x12,0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x7d, 0x48, 0x4e, 0xca, }, 6, 0, "", "",
+"62 f6 7d 48 4e ca \tvrsqrtph %zmm2,%zmm1",},
+{{0x62, 0xf6, 0x7d, 0x48, 0x4e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 7d 48 4e 8c c8 78 56 34 12 \tvrsqrtph 0x12345678(%eax,%ecx,8),%zmm1",},
+{{0x62, 0xf6, 0x7d, 0x08, 0x4e, 0xca, }, 6, 0, "", "",
+"62 f6 7d 08 4e ca \tvrsqrtph %xmm2,%xmm1",},
+{{0x62, 0xf6, 0x7d, 0x08, 0x4e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 7d 08 4e 8c c8 78 56 34 12 \tvrsqrtph 0x12345678(%eax,%ecx,8),%xmm1",},
+{{0x62, 0xf6, 0x7d, 0x28, 0x4e, 0xca, }, 6, 0, "", "",
+"62 f6 7d 28 4e ca \tvrsqrtph %ymm2,%ymm1",},
+{{0x62, 0xf6, 0x7d, 0x28, 0x4e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 7d 28 4e 8c c8 78 56 34 12 \tvrsqrtph 0x12345678(%eax,%ecx,8),%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x4f, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 4f cb \tvrsqrtsh %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x4f, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 4f 8c c8 78 56 34 12 \tvrsqrtsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0x2c, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 48 2c cb \tvscalefph %zmm3,%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0x2c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 48 2c 8c c8 78 56 34 12 \tvscalefph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x2c, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 2c cb \tvscalefph %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x2c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 2c 8c c8 78 56 34 12 \tvscalefph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0x2c, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 28 2c cb \tvscalefph %ymm3,%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0x2c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 28 2c 8c c8 78 56 34 12 \tvscalefph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x2d, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 2d cb \tvscalefsh %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x2d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 2d 8c c8 78 56 34 12 \tvscalefsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x7c, 0x48, 0x51, 0xca, }, 6, 0, "", "",
+"62 f5 7c 48 51 ca \tvsqrtph %zmm2,%zmm1",},
+{{0x62, 0xf5, 0x7c, 0x48, 0x51, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7c 48 51 8c c8 78 56 34 12 \tvsqrtph 0x12345678(%eax,%ecx,8),%zmm1",},
+{{0x62, 0xf5, 0x7c, 0x08, 0x51, 0xca, }, 6, 0, "", "",
+"62 f5 7c 08 51 ca \tvsqrtph %xmm2,%xmm1",},
+{{0x62, 0xf5, 0x7c, 0x08, 0x51, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7c 08 51 8c c8 78 56 34 12 \tvsqrtph 0x12345678(%eax,%ecx,8),%xmm1",},
+{{0x62, 0xf5, 0x7c, 0x28, 0x51, 0xca, }, 6, 0, "", "",
+"62 f5 7c 28 51 ca \tvsqrtph %ymm2,%ymm1",},
+{{0x62, 0xf5, 0x7c, 0x28, 0x51, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7c 28 51 8c c8 78 56 34 12 \tvsqrtph 0x12345678(%eax,%ecx,8),%ymm1",},
+{{0x62, 0xf5, 0x6e, 0x08, 0x51, 0xcb, }, 6, 0, "", "",
+"62 f5 6e 08 51 cb \tvsqrtsh %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x6e, 0x08, 0x51, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6e 08 51 8c c8 78 56 34 12 \tvsqrtsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x6c, 0x48, 0x5c, 0xcb, }, 6, 0, "", "",
+"62 f5 6c 48 5c cb \tvsubph %zmm3,%zmm2,%zmm1",},
+{{0x62, 0xf5, 0x6c, 0x48, 0x5c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6c 48 5c 8c c8 78 56 34 12 \tvsubph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",},
+{{0x62, 0xf5, 0x6c, 0x08, 0x5c, 0xcb, }, 6, 0, "", "",
+"62 f5 6c 08 5c cb \tvsubph %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x6c, 0x08, 0x5c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6c 08 5c 8c c8 78 56 34 12 \tvsubph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x6c, 0x28, 0x5c, 0xcb, }, 6, 0, "", "",
+"62 f5 6c 28 5c cb \tvsubph %ymm3,%ymm2,%ymm1",},
+{{0x62, 0xf5, 0x6c, 0x28, 0x5c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6c 28 5c 8c c8 78 56 34 12 \tvsubph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",},
+{{0x62, 0xf5, 0x6e, 0x08, 0x5c, 0xcb, }, 6, 0, "", "",
+"62 f5 6e 08 5c cb \tvsubsh %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x6e, 0x08, 0x5c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6e 08 5c 8c c8 78 56 34 12 \tvsubsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x7c, 0x08, 0x2e, 0xca, }, 6, 0, "", "",
+"62 f5 7c 08 2e ca \tvucomish %xmm2,%xmm1",},
+{{0x62, 0xf5, 0x7c, 0x08, 0x2e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7c 08 2e 8c c8 78 56 34 12 \tvucomish 0x12345678(%eax,%ecx,8),%xmm1",},
+{{0xf3, 0x0f, 0x3a, 0xf0, 0xc0, 0x00, }, 6, 0, "", "",
+"f3 0f 3a f0 c0 00 \threset $0x0",},
+{{0x0f, 0x01, 0xe8, }, 3, 0, "", "",
+"0f 01 e8 \tserialize ",},
+{{0xf2, 0x0f, 0x01, 0xe9, }, 4, 0, "", "",
+"f2 0f 01 e9 \txresldtrk ",},
+{{0xf2, 0x0f, 0x01, 0xe8, }, 4, 0, "", "",
+"f2 0f 01 e8 \txsusldtrk ",},
{{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 5da17d41d302..3a47e98fec33 100644
--- a/tools/perf/arch/x86/tests/insn-x86-dat-64.c
+++ b/tools/perf/arch/x86/tests/insn-x86-dat-64.c
@@ -2459,6 +2459,1432 @@
"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)",},
+{{0xc4, 0xe2, 0x78, 0x49, 0x04, 0xc8, }, 6, 0, "", "",
+"c4 e2 78 49 04 c8 \tldtilecfg (%rax,%rcx,8)",},
+{{0xc4, 0xc2, 0x78, 0x49, 0x04, 0xc8, }, 6, 0, "", "",
+"c4 c2 78 49 04 c8 \tldtilecfg (%r8,%rcx,8)",},
+{{0xc4, 0xe2, 0x79, 0x49, 0x04, 0xc8, }, 6, 0, "", "",
+"c4 e2 79 49 04 c8 \tsttilecfg (%rax,%rcx,8)",},
+{{0xc4, 0xc2, 0x79, 0x49, 0x04, 0xc8, }, 6, 0, "", "",
+"c4 c2 79 49 04 c8 \tsttilecfg (%r8,%rcx,8)",},
+{{0xc4, 0xe2, 0x7a, 0x5c, 0xd1, }, 5, 0, "", "",
+"c4 e2 7a 5c d1 \ttdpbf16ps %tmm0,%tmm1,%tmm2",},
+{{0xc4, 0xe2, 0x7b, 0x5e, 0xd1, }, 5, 0, "", "",
+"c4 e2 7b 5e d1 \ttdpbssd %tmm0,%tmm1,%tmm2",},
+{{0xc4, 0xe2, 0x7a, 0x5e, 0xd1, }, 5, 0, "", "",
+"c4 e2 7a 5e d1 \ttdpbsud %tmm0,%tmm1,%tmm2",},
+{{0xc4, 0xe2, 0x79, 0x5e, 0xd1, }, 5, 0, "", "",
+"c4 e2 79 5e d1 \ttdpbusd %tmm0,%tmm1,%tmm2",},
+{{0xc4, 0xe2, 0x78, 0x5e, 0xd1, }, 5, 0, "", "",
+"c4 e2 78 5e d1 \ttdpbuud %tmm0,%tmm1,%tmm2",},
+{{0xc4, 0xe2, 0x7b, 0x4b, 0x0c, 0xc8, }, 6, 0, "", "",
+"c4 e2 7b 4b 0c c8 \ttileloadd (%rax,%rcx,8),%tmm1",},
+{{0xc4, 0xc2, 0x7b, 0x4b, 0x14, 0xc8, }, 6, 0, "", "",
+"c4 c2 7b 4b 14 c8 \ttileloadd (%r8,%rcx,8),%tmm2",},
+{{0xc4, 0xe2, 0x79, 0x4b, 0x0c, 0xc8, }, 6, 0, "", "",
+"c4 e2 79 4b 0c c8 \ttileloaddt1 (%rax,%rcx,8),%tmm1",},
+{{0xc4, 0xc2, 0x79, 0x4b, 0x14, 0xc8, }, 6, 0, "", "",
+"c4 c2 79 4b 14 c8 \ttileloaddt1 (%r8,%rcx,8),%tmm2",},
+{{0xc4, 0xe2, 0x78, 0x49, 0xc0, }, 5, 0, "", "",
+"c4 e2 78 49 c0 \ttilerelease ",},
+{{0xc4, 0xe2, 0x7a, 0x4b, 0x0c, 0xc8, }, 6, 0, "", "",
+"c4 e2 7a 4b 0c c8 \ttilestored %tmm1,(%rax,%rcx,8)",},
+{{0xc4, 0xc2, 0x7a, 0x4b, 0x14, 0xc8, }, 6, 0, "", "",
+"c4 c2 7a 4b 14 c8 \ttilestored %tmm2,(%r8,%rcx,8)",},
+{{0xc4, 0xe2, 0x7b, 0x49, 0xc0, }, 5, 0, "", "",
+"c4 e2 7b 49 c0 \ttilezero %tmm0",},
+{{0xc4, 0xe2, 0x7b, 0x49, 0xf8, }, 5, 0, "", "",
+"c4 e2 7b 49 f8 \ttilezero %tmm7",},
+{{0xf3, 0x0f, 0x01, 0xee, }, 4, 0, "", "",
+"f3 0f 01 ee \tclui ",},
+{{0xf3, 0x0f, 0xc7, 0xf0, }, 4, 0, "", "",
+"f3 0f c7 f0 \tsenduipi %rax",},
+{{0xf3, 0x41, 0x0f, 0xc7, 0xf0, }, 5, 0, "", "",
+"f3 41 0f c7 f0 \tsenduipi %r8",},
+{{0xf3, 0x0f, 0x01, 0xef, }, 4, 0, "", "",
+"f3 0f 01 ef \tstui ",},
+{{0xf3, 0x0f, 0x01, 0xed, }, 4, 0, "", "",
+"f3 0f 01 ed \ttestui ",},
+{{0xf3, 0x0f, 0x01, 0xec, }, 4, 0, "", "",
+"f3 0f 01 ec \tuiret ",},
+{{0x62, 0xf5, 0x6c, 0x48, 0x58, 0xcb, }, 6, 0, "", "",
+"62 f5 6c 48 58 cb \tvaddph %zmm3,%zmm2,%zmm1",},
+{{0x62, 0xf5, 0x6c, 0x48, 0x58, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6c 48 58 8c c8 78 56 34 12 \tvaddph 0x12345678(%rax,%rcx,8),%zmm2,%zmm1",},
+{{0x67, 0x62, 0xf5, 0x6c, 0x48, 0x58, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 6c 48 58 8c c8 78 56 34 12 \tvaddph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",},
+{{0x62, 0xf5, 0x6c, 0x08, 0x58, 0xcb, }, 6, 0, "", "",
+"62 f5 6c 08 58 cb \tvaddph %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x6c, 0x08, 0x58, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6c 08 58 8c c8 78 56 34 12 \tvaddph 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf5, 0x6c, 0x08, 0x58, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 6c 08 58 8c c8 78 56 34 12 \tvaddph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x6c, 0x28, 0x58, 0xcb, }, 6, 0, "", "",
+"62 f5 6c 28 58 cb \tvaddph %ymm3,%ymm2,%ymm1",},
+{{0x62, 0xf5, 0x6c, 0x28, 0x58, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6c 28 58 8c c8 78 56 34 12 \tvaddph 0x12345678(%rax,%rcx,8),%ymm2,%ymm1",},
+{{0x67, 0x62, 0xf5, 0x6c, 0x28, 0x58, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 6c 28 58 8c c8 78 56 34 12 \tvaddph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",},
+{{0x62, 0xf5, 0x6e, 0x08, 0x58, 0xcb, }, 6, 0, "", "",
+"62 f5 6e 08 58 cb \tvaddsh %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x6e, 0x08, 0x58, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6e 08 58 8c c8 78 56 34 12 \tvaddsh 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf5, 0x6e, 0x08, 0x58, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 6e 08 58 8c c8 78 56 34 12 \tvaddsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf3, 0x6c, 0x48, 0xc2, 0xeb, 0x12, }, 7, 0, "", "",
+"62 f3 6c 48 c2 eb 12 \tvcmple_oqph %zmm3,%zmm2,%k5",},
+{{0x62, 0xf3, 0x6c, 0x48, 0xc2, 0xac, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "",
+"62 f3 6c 48 c2 ac c8 78 56 34 12 12 \tvcmple_oqph 0x12345678(%rax,%rcx,8),%zmm2,%k5",},
+{{0x67, 0x62, 0xf3, 0x6c, 0x48, 0xc2, 0xac, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 13, 0, "", "",
+"67 62 f3 6c 48 c2 ac c8 78 56 34 12 12 \tvcmple_oqph 0x12345678(%eax,%ecx,8),%zmm2,%k5",},
+{{0x62, 0xf3, 0x6c, 0x08, 0xc2, 0xeb, 0x12, }, 7, 0, "", "",
+"62 f3 6c 08 c2 eb 12 \tvcmple_oqph %xmm3,%xmm2,%k5",},
+{{0x62, 0xf3, 0x6c, 0x08, 0xc2, 0xac, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "",
+"62 f3 6c 08 c2 ac c8 78 56 34 12 12 \tvcmple_oqph 0x12345678(%rax,%rcx,8),%xmm2,%k5",},
+{{0x67, 0x62, 0xf3, 0x6c, 0x08, 0xc2, 0xac, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 13, 0, "", "",
+"67 62 f3 6c 08 c2 ac c8 78 56 34 12 12 \tvcmple_oqph 0x12345678(%eax,%ecx,8),%xmm2,%k5",},
+{{0x62, 0xf3, 0x6c, 0x28, 0xc2, 0xeb, 0x12, }, 7, 0, "", "",
+"62 f3 6c 28 c2 eb 12 \tvcmple_oqph %ymm3,%ymm2,%k5",},
+{{0x62, 0xf3, 0x6c, 0x28, 0xc2, 0xac, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "",
+"62 f3 6c 28 c2 ac c8 78 56 34 12 12 \tvcmple_oqph 0x12345678(%rax,%rcx,8),%ymm2,%k5",},
+{{0x67, 0x62, 0xf3, 0x6c, 0x28, 0xc2, 0xac, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 13, 0, "", "",
+"67 62 f3 6c 28 c2 ac c8 78 56 34 12 12 \tvcmple_oqph 0x12345678(%eax,%ecx,8),%ymm2,%k5",},
+{{0x62, 0xf3, 0x6e, 0x08, 0xc2, 0xeb, 0x12, }, 7, 0, "", "",
+"62 f3 6e 08 c2 eb 12 \tvcmple_oqsh %xmm3,%xmm2,%k5",},
+{{0x62, 0xf3, 0x6e, 0x08, 0xc2, 0xac, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "",
+"62 f3 6e 08 c2 ac c8 78 56 34 12 12 \tvcmple_oqsh 0x12345678(%rax,%rcx,8),%xmm2,%k5",},
+{{0x67, 0x62, 0xf3, 0x6e, 0x08, 0xc2, 0xac, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 13, 0, "", "",
+"67 62 f3 6e 08 c2 ac c8 78 56 34 12 12 \tvcmple_oqsh 0x12345678(%eax,%ecx,8),%xmm2,%k5",},
+{{0x62, 0xf5, 0x7c, 0x08, 0x2f, 0xca, }, 6, 0, "", "",
+"62 f5 7c 08 2f ca \tvcomish %xmm2,%xmm1",},
+{{0x62, 0xf5, 0x7c, 0x08, 0x2f, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7c 08 2f 8c c8 78 56 34 12 \tvcomish 0x12345678(%rax,%rcx,8),%xmm1",},
+{{0x67, 0x62, 0xf5, 0x7c, 0x08, 0x2f, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7c 08 2f 8c c8 78 56 34 12 \tvcomish 0x12345678(%eax,%ecx,8),%xmm1",},
+{{0x62, 0xf5, 0x7c, 0x48, 0x5b, 0xca, }, 6, 0, "", "",
+"62 f5 7c 48 5b ca \tvcvtdq2ph %zmm2,%ymm1",},
+{{0x62, 0xf5, 0x7c, 0x48, 0x5b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7c 48 5b 8c c8 78 56 34 12 \tvcvtdq2ph 0x12345678(%rax,%rcx,8),%ymm1",},
+{{0x67, 0x62, 0xf5, 0x7c, 0x48, 0x5b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7c 48 5b 8c c8 78 56 34 12 \tvcvtdq2ph 0x12345678(%eax,%ecx,8),%ymm1",},
+{{0x62, 0xf5, 0x7c, 0x08, 0x5b, 0xca, }, 6, 0, "", "",
+"62 f5 7c 08 5b ca \tvcvtdq2ph %xmm2,%xmm1",},
+{{0x62, 0xf5, 0x7c, 0x28, 0x5b, 0xca, }, 6, 0, "", "",
+"62 f5 7c 28 5b ca \tvcvtdq2ph %ymm2,%xmm1",},
+{{0x62, 0xf5, 0xfd, 0x48, 0x5a, 0xca, }, 6, 0, "", "",
+"62 f5 fd 48 5a ca \tvcvtpd2ph %zmm2,%xmm1",},
+{{0x62, 0xf5, 0xfd, 0x08, 0x5a, 0xca, }, 6, 0, "", "",
+"62 f5 fd 08 5a ca \tvcvtpd2ph %xmm2,%xmm1",},
+{{0x62, 0xf5, 0xfd, 0x28, 0x5a, 0xca, }, 6, 0, "", "",
+"62 f5 fd 28 5a ca \tvcvtpd2ph %ymm2,%xmm1",},
+{{0x62, 0xf5, 0x7d, 0x48, 0x5b, 0xca, }, 6, 0, "", "",
+"62 f5 7d 48 5b ca \tvcvtph2dq %ymm2,%zmm1",},
+{{0x62, 0xf5, 0x7d, 0x48, 0x5b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7d 48 5b 8c c8 78 56 34 12 \tvcvtph2dq 0x12345678(%rax,%rcx,8),%zmm1",},
+{{0x67, 0x62, 0xf5, 0x7d, 0x48, 0x5b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7d 48 5b 8c c8 78 56 34 12 \tvcvtph2dq 0x12345678(%eax,%ecx,8),%zmm1",},
+{{0x62, 0xf5, 0x7d, 0x08, 0x5b, 0xca, }, 6, 0, "", "",
+"62 f5 7d 08 5b ca \tvcvtph2dq %xmm2,%xmm1",},
+{{0x62, 0xf5, 0x7d, 0x08, 0x5b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7d 08 5b 8c c8 78 56 34 12 \tvcvtph2dq 0x12345678(%rax,%rcx,8),%xmm1",},
+{{0x67, 0x62, 0xf5, 0x7d, 0x08, 0x5b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7d 08 5b 8c c8 78 56 34 12 \tvcvtph2dq 0x12345678(%eax,%ecx,8),%xmm1",},
+{{0x62, 0xf5, 0x7d, 0x28, 0x5b, 0xca, }, 6, 0, "", "",
+"62 f5 7d 28 5b ca \tvcvtph2dq %xmm2,%ymm1",},
+{{0x62, 0xf5, 0x7d, 0x28, 0x5b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7d 28 5b 8c c8 78 56 34 12 \tvcvtph2dq 0x12345678(%rax,%rcx,8),%ymm1",},
+{{0x67, 0x62, 0xf5, 0x7d, 0x28, 0x5b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7d 28 5b 8c c8 78 56 34 12 \tvcvtph2dq 0x12345678(%eax,%ecx,8),%ymm1",},
+{{0x62, 0xf5, 0x7c, 0x48, 0x5a, 0xca, }, 6, 0, "", "",
+"62 f5 7c 48 5a ca \tvcvtph2pd %xmm2,%zmm1",},
+{{0x62, 0xf5, 0x7c, 0x48, 0x5a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7c 48 5a 8c c8 78 56 34 12 \tvcvtph2pd 0x12345678(%rax,%rcx,8),%zmm1",},
+{{0x67, 0x62, 0xf5, 0x7c, 0x48, 0x5a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7c 48 5a 8c c8 78 56 34 12 \tvcvtph2pd 0x12345678(%eax,%ecx,8),%zmm1",},
+{{0x62, 0xf5, 0x7c, 0x08, 0x5a, 0xca, }, 6, 0, "", "",
+"62 f5 7c 08 5a ca \tvcvtph2pd %xmm2,%xmm1",},
+{{0x62, 0xf5, 0x7c, 0x08, 0x5a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7c 08 5a 8c c8 78 56 34 12 \tvcvtph2pd 0x12345678(%rax,%rcx,8),%xmm1",},
+{{0x67, 0x62, 0xf5, 0x7c, 0x08, 0x5a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7c 08 5a 8c c8 78 56 34 12 \tvcvtph2pd 0x12345678(%eax,%ecx,8),%xmm1",},
+{{0x62, 0xf5, 0x7c, 0x28, 0x5a, 0xca, }, 6, 0, "", "",
+"62 f5 7c 28 5a ca \tvcvtph2pd %xmm2,%ymm1",},
+{{0x62, 0xf5, 0x7c, 0x28, 0x5a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7c 28 5a 8c c8 78 56 34 12 \tvcvtph2pd 0x12345678(%rax,%rcx,8),%ymm1",},
+{{0x67, 0x62, 0xf5, 0x7c, 0x28, 0x5a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7c 28 5a 8c c8 78 56 34 12 \tvcvtph2pd 0x12345678(%eax,%ecx,8),%ymm1",},
+{{0x62, 0xf2, 0x7d, 0x48, 0x13, 0xca, }, 6, 0, "", "",
+"62 f2 7d 48 13 ca \tvcvtph2ps %ymm2,%zmm1",},
+{{0x62, 0xf2, 0x7d, 0x48, 0x13, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f2 7d 48 13 8c c8 78 56 34 12 \tvcvtph2ps 0x12345678(%rax,%rcx,8),%zmm1",},
+{{0x67, 0x62, 0xf2, 0x7d, 0x48, 0x13, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f2 7d 48 13 8c c8 78 56 34 12 \tvcvtph2ps 0x12345678(%eax,%ecx,8),%zmm1",},
+{{0xc4, 0xe2, 0x79, 0x13, 0xca, }, 5, 0, "", "",
+"c4 e2 79 13 ca \tvcvtph2ps %xmm2,%xmm1",},
+{{0xc4, 0xe2, 0x79, 0x13, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "",
+"c4 e2 79 13 8c c8 78 56 34 12 \tvcvtph2ps 0x12345678(%rax,%rcx,8),%xmm1",},
+{{0x67, 0xc4, 0xe2, 0x79, 0x13, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"67 c4 e2 79 13 8c c8 78 56 34 12 \tvcvtph2ps 0x12345678(%eax,%ecx,8),%xmm1",},
+{{0xc4, 0xe2, 0x7d, 0x13, 0xca, }, 5, 0, "", "",
+"c4 e2 7d 13 ca \tvcvtph2ps %xmm2,%ymm1",},
+{{0xc4, 0xe2, 0x7d, 0x13, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "",
+"c4 e2 7d 13 8c c8 78 56 34 12 \tvcvtph2ps 0x12345678(%rax,%rcx,8),%ymm1",},
+{{0x67, 0xc4, 0xe2, 0x7d, 0x13, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"67 c4 e2 7d 13 8c c8 78 56 34 12 \tvcvtph2ps 0x12345678(%eax,%ecx,8),%ymm1",},
+{{0xc4, 0xe2, 0x79, 0x13, 0xca, }, 5, 0, "", "",
+"c4 e2 79 13 ca \tvcvtph2ps %xmm2,%xmm1",},
+{{0xc4, 0xe2, 0x79, 0x13, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "",
+"c4 e2 79 13 8c c8 78 56 34 12 \tvcvtph2ps 0x12345678(%rax,%rcx,8),%xmm1",},
+{{0x67, 0xc4, 0xe2, 0x79, 0x13, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"67 c4 e2 79 13 8c c8 78 56 34 12 \tvcvtph2ps 0x12345678(%eax,%ecx,8),%xmm1",},
+{{0xc4, 0xe2, 0x7d, 0x13, 0xca, }, 5, 0, "", "",
+"c4 e2 7d 13 ca \tvcvtph2ps %xmm2,%ymm1",},
+{{0xc4, 0xe2, 0x7d, 0x13, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "",
+"c4 e2 7d 13 8c c8 78 56 34 12 \tvcvtph2ps 0x12345678(%rax,%rcx,8),%ymm1",},
+{{0x67, 0xc4, 0xe2, 0x7d, 0x13, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"67 c4 e2 7d 13 8c c8 78 56 34 12 \tvcvtph2ps 0x12345678(%eax,%ecx,8),%ymm1",},
+{{0x62, 0xf6, 0x7d, 0x48, 0x13, 0xca, }, 6, 0, "", "",
+"62 f6 7d 48 13 ca \tvcvtph2psx %ymm2,%zmm1",},
+{{0x62, 0xf6, 0x7d, 0x48, 0x13, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 7d 48 13 8c c8 78 56 34 12 \tvcvtph2psx 0x12345678(%rax,%rcx,8),%zmm1",},
+{{0x67, 0x62, 0xf6, 0x7d, 0x48, 0x13, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 7d 48 13 8c c8 78 56 34 12 \tvcvtph2psx 0x12345678(%eax,%ecx,8),%zmm1",},
+{{0x62, 0xf6, 0x7d, 0x08, 0x13, 0xca, }, 6, 0, "", "",
+"62 f6 7d 08 13 ca \tvcvtph2psx %xmm2,%xmm1",},
+{{0x62, 0xf6, 0x7d, 0x08, 0x13, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 7d 08 13 8c c8 78 56 34 12 \tvcvtph2psx 0x12345678(%rax,%rcx,8),%xmm1",},
+{{0x67, 0x62, 0xf6, 0x7d, 0x08, 0x13, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 7d 08 13 8c c8 78 56 34 12 \tvcvtph2psx 0x12345678(%eax,%ecx,8),%xmm1",},
+{{0x62, 0xf6, 0x7d, 0x28, 0x13, 0xca, }, 6, 0, "", "",
+"62 f6 7d 28 13 ca \tvcvtph2psx %xmm2,%ymm1",},
+{{0x62, 0xf6, 0x7d, 0x28, 0x13, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 7d 28 13 8c c8 78 56 34 12 \tvcvtph2psx 0x12345678(%rax,%rcx,8),%ymm1",},
+{{0x67, 0x62, 0xf6, 0x7d, 0x28, 0x13, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 7d 28 13 8c c8 78 56 34 12 \tvcvtph2psx 0x12345678(%eax,%ecx,8),%ymm1",},
+{{0x62, 0xf5, 0x7d, 0x48, 0x7b, 0xca, }, 6, 0, "", "",
+"62 f5 7d 48 7b ca \tvcvtph2qq %xmm2,%zmm1",},
+{{0x62, 0xf5, 0x7d, 0x48, 0x7b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7d 48 7b 8c c8 78 56 34 12 \tvcvtph2qq 0x12345678(%rax,%rcx,8),%zmm1",},
+{{0x67, 0x62, 0xf5, 0x7d, 0x48, 0x7b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7d 48 7b 8c c8 78 56 34 12 \tvcvtph2qq 0x12345678(%eax,%ecx,8),%zmm1",},
+{{0x62, 0xf5, 0x7d, 0x08, 0x7b, 0xca, }, 6, 0, "", "",
+"62 f5 7d 08 7b ca \tvcvtph2qq %xmm2,%xmm1",},
+{{0x62, 0xf5, 0x7d, 0x08, 0x7b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7d 08 7b 8c c8 78 56 34 12 \tvcvtph2qq 0x12345678(%rax,%rcx,8),%xmm1",},
+{{0x67, 0x62, 0xf5, 0x7d, 0x08, 0x7b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7d 08 7b 8c c8 78 56 34 12 \tvcvtph2qq 0x12345678(%eax,%ecx,8),%xmm1",},
+{{0x62, 0xf5, 0x7d, 0x28, 0x7b, 0xca, }, 6, 0, "", "",
+"62 f5 7d 28 7b ca \tvcvtph2qq %xmm2,%ymm1",},
+{{0x62, 0xf5, 0x7d, 0x28, 0x7b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7d 28 7b 8c c8 78 56 34 12 \tvcvtph2qq 0x12345678(%rax,%rcx,8),%ymm1",},
+{{0x67, 0x62, 0xf5, 0x7d, 0x28, 0x7b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7d 28 7b 8c c8 78 56 34 12 \tvcvtph2qq 0x12345678(%eax,%ecx,8),%ymm1",},
+{{0x62, 0xf5, 0x7c, 0x48, 0x79, 0xca, }, 6, 0, "", "",
+"62 f5 7c 48 79 ca \tvcvtph2udq %ymm2,%zmm1",},
+{{0x62, 0xf5, 0x7c, 0x48, 0x79, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7c 48 79 8c c8 78 56 34 12 \tvcvtph2udq 0x12345678(%rax,%rcx,8),%zmm1",},
+{{0x67, 0x62, 0xf5, 0x7c, 0x48, 0x79, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7c 48 79 8c c8 78 56 34 12 \tvcvtph2udq 0x12345678(%eax,%ecx,8),%zmm1",},
+{{0x62, 0xf5, 0x7c, 0x08, 0x79, 0xca, }, 6, 0, "", "",
+"62 f5 7c 08 79 ca \tvcvtph2udq %xmm2,%xmm1",},
+{{0x62, 0xf5, 0x7c, 0x08, 0x79, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7c 08 79 8c c8 78 56 34 12 \tvcvtph2udq 0x12345678(%rax,%rcx,8),%xmm1",},
+{{0x67, 0x62, 0xf5, 0x7c, 0x08, 0x79, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7c 08 79 8c c8 78 56 34 12 \tvcvtph2udq 0x12345678(%eax,%ecx,8),%xmm1",},
+{{0x62, 0xf5, 0x7c, 0x28, 0x79, 0xca, }, 6, 0, "", "",
+"62 f5 7c 28 79 ca \tvcvtph2udq %xmm2,%ymm1",},
+{{0x62, 0xf5, 0x7c, 0x28, 0x79, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7c 28 79 8c c8 78 56 34 12 \tvcvtph2udq 0x12345678(%rax,%rcx,8),%ymm1",},
+{{0x67, 0x62, 0xf5, 0x7c, 0x28, 0x79, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7c 28 79 8c c8 78 56 34 12 \tvcvtph2udq 0x12345678(%eax,%ecx,8),%ymm1",},
+{{0x62, 0xf5, 0x7d, 0x48, 0x79, 0xca, }, 6, 0, "", "",
+"62 f5 7d 48 79 ca \tvcvtph2uqq %xmm2,%zmm1",},
+{{0x62, 0xf5, 0x7d, 0x48, 0x79, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7d 48 79 8c c8 78 56 34 12 \tvcvtph2uqq 0x12345678(%rax,%rcx,8),%zmm1",},
+{{0x67, 0x62, 0xf5, 0x7d, 0x48, 0x79, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7d 48 79 8c c8 78 56 34 12 \tvcvtph2uqq 0x12345678(%eax,%ecx,8),%zmm1",},
+{{0x62, 0xf5, 0x7d, 0x08, 0x79, 0xca, }, 6, 0, "", "",
+"62 f5 7d 08 79 ca \tvcvtph2uqq %xmm2,%xmm1",},
+{{0x62, 0xf5, 0x7d, 0x08, 0x79, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7d 08 79 8c c8 78 56 34 12 \tvcvtph2uqq 0x12345678(%rax,%rcx,8),%xmm1",},
+{{0x67, 0x62, 0xf5, 0x7d, 0x08, 0x79, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7d 08 79 8c c8 78 56 34 12 \tvcvtph2uqq 0x12345678(%eax,%ecx,8),%xmm1",},
+{{0x62, 0xf5, 0x7d, 0x28, 0x79, 0xca, }, 6, 0, "", "",
+"62 f5 7d 28 79 ca \tvcvtph2uqq %xmm2,%ymm1",},
+{{0x62, 0xf5, 0x7d, 0x28, 0x79, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7d 28 79 8c c8 78 56 34 12 \tvcvtph2uqq 0x12345678(%rax,%rcx,8),%ymm1",},
+{{0x67, 0x62, 0xf5, 0x7d, 0x28, 0x79, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7d 28 79 8c c8 78 56 34 12 \tvcvtph2uqq 0x12345678(%eax,%ecx,8),%ymm1",},
+{{0x62, 0xf5, 0x7c, 0x48, 0x7d, 0xca, }, 6, 0, "", "",
+"62 f5 7c 48 7d ca \tvcvtph2uw %zmm2,%zmm1",},
+{{0x62, 0xf5, 0x7c, 0x48, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7c 48 7d 8c c8 78 56 34 12 \tvcvtph2uw 0x12345678(%rax,%rcx,8),%zmm1",},
+{{0x67, 0x62, 0xf5, 0x7c, 0x48, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7c 48 7d 8c c8 78 56 34 12 \tvcvtph2uw 0x12345678(%eax,%ecx,8),%zmm1",},
+{{0x62, 0xf5, 0x7c, 0x08, 0x7d, 0xca, }, 6, 0, "", "",
+"62 f5 7c 08 7d ca \tvcvtph2uw %xmm2,%xmm1",},
+{{0x62, 0xf5, 0x7c, 0x08, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7c 08 7d 8c c8 78 56 34 12 \tvcvtph2uw 0x12345678(%rax,%rcx,8),%xmm1",},
+{{0x67, 0x62, 0xf5, 0x7c, 0x08, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7c 08 7d 8c c8 78 56 34 12 \tvcvtph2uw 0x12345678(%eax,%ecx,8),%xmm1",},
+{{0x62, 0xf5, 0x7c, 0x28, 0x7d, 0xca, }, 6, 0, "", "",
+"62 f5 7c 28 7d ca \tvcvtph2uw %ymm2,%ymm1",},
+{{0x62, 0xf5, 0x7c, 0x28, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7c 28 7d 8c c8 78 56 34 12 \tvcvtph2uw 0x12345678(%rax,%rcx,8),%ymm1",},
+{{0x67, 0x62, 0xf5, 0x7c, 0x28, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7c 28 7d 8c c8 78 56 34 12 \tvcvtph2uw 0x12345678(%eax,%ecx,8),%ymm1",},
+{{0x62, 0xf5, 0x7d, 0x48, 0x7d, 0xca, }, 6, 0, "", "",
+"62 f5 7d 48 7d ca \tvcvtph2w %zmm2,%zmm1",},
+{{0x62, 0xf5, 0x7d, 0x48, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7d 48 7d 8c c8 78 56 34 12 \tvcvtph2w 0x12345678(%rax,%rcx,8),%zmm1",},
+{{0x67, 0x62, 0xf5, 0x7d, 0x48, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7d 48 7d 8c c8 78 56 34 12 \tvcvtph2w 0x12345678(%eax,%ecx,8),%zmm1",},
+{{0x62, 0xf5, 0x7d, 0x08, 0x7d, 0xca, }, 6, 0, "", "",
+"62 f5 7d 08 7d ca \tvcvtph2w %xmm2,%xmm1",},
+{{0x62, 0xf5, 0x7d, 0x08, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7d 08 7d 8c c8 78 56 34 12 \tvcvtph2w 0x12345678(%rax,%rcx,8),%xmm1",},
+{{0x67, 0x62, 0xf5, 0x7d, 0x08, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7d 08 7d 8c c8 78 56 34 12 \tvcvtph2w 0x12345678(%eax,%ecx,8),%xmm1",},
+{{0x62, 0xf5, 0x7d, 0x28, 0x7d, 0xca, }, 6, 0, "", "",
+"62 f5 7d 28 7d ca \tvcvtph2w %ymm2,%ymm1",},
+{{0x62, 0xf5, 0x7d, 0x28, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7d 28 7d 8c c8 78 56 34 12 \tvcvtph2w 0x12345678(%rax,%rcx,8),%ymm1",},
+{{0x67, 0x62, 0xf5, 0x7d, 0x28, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7d 28 7d 8c c8 78 56 34 12 \tvcvtph2w 0x12345678(%eax,%ecx,8),%ymm1",},
+{{0x62, 0xf3, 0x7d, 0x48, 0x1d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "",
+"62 f3 7d 48 1d 8c c8 78 56 34 12 12 \tvcvtps2ph $0x12,%zmm1,0x12345678(%rax,%rcx,8)",},
+{{0x67, 0x62, 0xf3, 0x7d, 0x48, 0x1d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 13, 0, "", "",
+"67 62 f3 7d 48 1d 8c c8 78 56 34 12 12 \tvcvtps2ph $0x12,%zmm1,0x12345678(%eax,%ecx,8)",},
+{{0x62, 0xf3, 0x7d, 0x48, 0x1d, 0xd1, 0x12, }, 7, 0, "", "",
+"62 f3 7d 48 1d d1 12 \tvcvtps2ph $0x12,%zmm2,%ymm1",},
+{{0xc4, 0xe3, 0x7d, 0x1d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 11, 0, "", "",
+"c4 e3 7d 1d 8c c8 78 56 34 12 12 \tvcvtps2ph $0x12,%ymm1,0x12345678(%rax,%rcx,8)",},
+{{0x67, 0xc4, 0xe3, 0x7d, 0x1d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "",
+"67 c4 e3 7d 1d 8c c8 78 56 34 12 12 \tvcvtps2ph $0x12,%ymm1,0x12345678(%eax,%ecx,8)",},
+{{0xc4, 0xe3, 0x79, 0x1d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 11, 0, "", "",
+"c4 e3 79 1d 8c c8 78 56 34 12 12 \tvcvtps2ph $0x12,%xmm1,0x12345678(%rax,%rcx,8)",},
+{{0x67, 0xc4, 0xe3, 0x79, 0x1d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "",
+"67 c4 e3 79 1d 8c c8 78 56 34 12 12 \tvcvtps2ph $0x12,%xmm1,0x12345678(%eax,%ecx,8)",},
+{{0xc4, 0xe3, 0x79, 0x1d, 0xd1, 0x12, }, 6, 0, "", "",
+"c4 e3 79 1d d1 12 \tvcvtps2ph $0x12,%xmm2,%xmm1",},
+{{0xc4, 0xe3, 0x7d, 0x1d, 0xd1, 0x12, }, 6, 0, "", "",
+"c4 e3 7d 1d d1 12 \tvcvtps2ph $0x12,%ymm2,%xmm1",},
+{{0xc4, 0xe3, 0x7d, 0x1d, 0xd1, 0x12, }, 6, 0, "", "",
+"c4 e3 7d 1d d1 12 \tvcvtps2ph $0x12,%ymm2,%xmm1",},
+{{0xc4, 0xe3, 0x7d, 0x1d, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 11, 0, "", "",
+"c4 e3 7d 1d 94 c8 78 56 34 12 12 \tvcvtps2ph $0x12,%ymm2,0x12345678(%rax,%rcx,8)",},
+{{0x67, 0xc4, 0xe3, 0x7d, 0x1d, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "",
+"67 c4 e3 7d 1d 94 c8 78 56 34 12 12 \tvcvtps2ph $0x12,%ymm2,0x12345678(%eax,%ecx,8)",},
+{{0xc4, 0xe3, 0x79, 0x1d, 0xd1, 0x12, }, 6, 0, "", "",
+"c4 e3 79 1d d1 12 \tvcvtps2ph $0x12,%xmm2,%xmm1",},
+{{0xc4, 0xe3, 0x79, 0x1d, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 11, 0, "", "",
+"c4 e3 79 1d 94 c8 78 56 34 12 12 \tvcvtps2ph $0x12,%xmm2,0x12345678(%rax,%rcx,8)",},
+{{0x67, 0xc4, 0xe3, 0x79, 0x1d, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "",
+"67 c4 e3 79 1d 94 c8 78 56 34 12 12 \tvcvtps2ph $0x12,%xmm2,0x12345678(%eax,%ecx,8)",},
+{{0x62, 0xf5, 0x7d, 0x48, 0x1d, 0xca, }, 6, 0, "", "",
+"62 f5 7d 48 1d ca \tvcvtps2phx %zmm2,%ymm1",},
+{{0x62, 0xf5, 0x7d, 0x48, 0x1d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7d 48 1d 8c c8 78 56 34 12 \tvcvtps2phx 0x12345678(%rax,%rcx,8),%ymm1",},
+{{0x67, 0x62, 0xf5, 0x7d, 0x48, 0x1d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7d 48 1d 8c c8 78 56 34 12 \tvcvtps2phx 0x12345678(%eax,%ecx,8),%ymm1",},
+{{0x62, 0xf5, 0x7d, 0x08, 0x1d, 0xca, }, 6, 0, "", "",
+"62 f5 7d 08 1d ca \tvcvtps2phx %xmm2,%xmm1",},
+{{0x62, 0xf5, 0x7d, 0x28, 0x1d, 0xca, }, 6, 0, "", "",
+"62 f5 7d 28 1d ca \tvcvtps2phx %ymm2,%xmm1",},
+{{0x62, 0xf5, 0xfc, 0x48, 0x5b, 0xca, }, 6, 0, "", "",
+"62 f5 fc 48 5b ca \tvcvtqq2ph %zmm2,%xmm1",},
+{{0x62, 0xf5, 0xfc, 0x08, 0x5b, 0xca, }, 6, 0, "", "",
+"62 f5 fc 08 5b ca \tvcvtqq2ph %xmm2,%xmm1",},
+{{0x62, 0xf5, 0xfc, 0x28, 0x5b, 0xca, }, 6, 0, "", "",
+"62 f5 fc 28 5b ca \tvcvtqq2ph %ymm2,%xmm1",},
+{{0x67, 0x62, 0xf5, 0xef, 0x08, 0x5a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 ef 08 5a 8c c8 78 56 34 12 \tvcvtsd2sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf5, 0x6e, 0x08, 0x5a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 6e 08 5a 8c c8 78 56 34 12 \tvcvtsh2sd 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf5, 0x7e, 0x08, 0x2d, 0x84, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7e 08 2d 84 c8 78 56 34 12 \tvcvtsh2si 0x12345678(%eax,%ecx,8),%eax",},
+{{0x67, 0x62, 0xf5, 0xfe, 0x08, 0x2d, 0x84, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 fe 08 2d 84 c8 78 56 34 12 \tvcvtsh2si 0x12345678(%eax,%ecx,8),%rax",},
+{{0x67, 0x62, 0xf6, 0x6c, 0x08, 0x13, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6c 08 13 8c c8 78 56 34 12 \tvcvtsh2ss 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x7e, 0x08, 0x79, 0xc1, }, 6, 0, "", "",
+"62 f5 7e 08 79 c1 \tvcvtsh2usi %xmm1,%eax",},
+{{0x62, 0xf5, 0x7e, 0x08, 0x79, 0x84, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7e 08 79 84 c8 78 56 34 12 \tvcvtsh2usi 0x12345678(%rax,%rcx,8),%eax",},
+{{0x67, 0x62, 0xf5, 0x7e, 0x08, 0x79, 0x84, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7e 08 79 84 c8 78 56 34 12 \tvcvtsh2usi 0x12345678(%eax,%ecx,8),%eax",},
+{{0x62, 0xf5, 0xfe, 0x08, 0x79, 0xc1, }, 6, 0, "", "",
+"62 f5 fe 08 79 c1 \tvcvtsh2usi %xmm1,%rax",},
+{{0x62, 0xf5, 0xfe, 0x08, 0x79, 0x84, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 fe 08 79 84 c8 78 56 34 12 \tvcvtsh2usi 0x12345678(%rax,%rcx,8),%rax",},
+{{0x67, 0x62, 0xf5, 0xfe, 0x08, 0x79, 0x84, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 fe 08 79 84 c8 78 56 34 12 \tvcvtsh2usi 0x12345678(%eax,%ecx,8),%rax",},
+{{0x62, 0xf5, 0x6e, 0x08, 0x2a, 0xc8, }, 6, 0, "", "",
+"62 f5 6e 08 2a c8 \tvcvtsi2sh %eax,%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x6e, 0x08, 0x2a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6e 08 2a 8c c8 78 56 34 12 \tvcvtsi2shl 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf5, 0x6e, 0x08, 0x2a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 6e 08 2a 8c c8 78 56 34 12 \tvcvtsi2shl 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf5, 0xee, 0x08, 0x2a, 0xc8, }, 6, 0, "", "",
+"62 f5 ee 08 2a c8 \tvcvtsi2sh %rax,%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x6e, 0x08, 0x2a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6e 08 2a 8c c8 78 56 34 12 \tvcvtsi2shl 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf5, 0x6e, 0x08, 0x2a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 6e 08 2a 8c c8 78 56 34 12 \tvcvtsi2shl 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x6c, 0x08, 0x1d, 0xcb, }, 6, 0, "", "",
+"62 f5 6c 08 1d cb \tvcvtss2sh %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x6c, 0x08, 0x1d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6c 08 1d 8c c8 78 56 34 12 \tvcvtss2sh 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf5, 0x6c, 0x08, 0x1d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 6c 08 1d 8c c8 78 56 34 12 \tvcvtss2sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x7e, 0x48, 0x5b, 0xca, }, 6, 0, "", "",
+"62 f5 7e 48 5b ca \tvcvttph2dq %ymm2,%zmm1",},
+{{0x62, 0xf5, 0x7e, 0x48, 0x5b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7e 48 5b 8c c8 78 56 34 12 \tvcvttph2dq 0x12345678(%rax,%rcx,8),%zmm1",},
+{{0x67, 0x62, 0xf5, 0x7e, 0x48, 0x5b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7e 48 5b 8c c8 78 56 34 12 \tvcvttph2dq 0x12345678(%eax,%ecx,8),%zmm1",},
+{{0x62, 0xf5, 0x7e, 0x08, 0x5b, 0xca, }, 6, 0, "", "",
+"62 f5 7e 08 5b ca \tvcvttph2dq %xmm2,%xmm1",},
+{{0x62, 0xf5, 0x7e, 0x08, 0x5b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7e 08 5b 8c c8 78 56 34 12 \tvcvttph2dq 0x12345678(%rax,%rcx,8),%xmm1",},
+{{0x67, 0x62, 0xf5, 0x7e, 0x08, 0x5b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7e 08 5b 8c c8 78 56 34 12 \tvcvttph2dq 0x12345678(%eax,%ecx,8),%xmm1",},
+{{0x62, 0xf5, 0x7e, 0x28, 0x5b, 0xca, }, 6, 0, "", "",
+"62 f5 7e 28 5b ca \tvcvttph2dq %xmm2,%ymm1",},
+{{0x62, 0xf5, 0x7e, 0x28, 0x5b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7e 28 5b 8c c8 78 56 34 12 \tvcvttph2dq 0x12345678(%rax,%rcx,8),%ymm1",},
+{{0x67, 0x62, 0xf5, 0x7e, 0x28, 0x5b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7e 28 5b 8c c8 78 56 34 12 \tvcvttph2dq 0x12345678(%eax,%ecx,8),%ymm1",},
+{{0x62, 0xf5, 0x7d, 0x48, 0x7a, 0xca, }, 6, 0, "", "",
+"62 f5 7d 48 7a ca \tvcvttph2qq %xmm2,%zmm1",},
+{{0x62, 0xf5, 0x7d, 0x48, 0x7a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7d 48 7a 8c c8 78 56 34 12 \tvcvttph2qq 0x12345678(%rax,%rcx,8),%zmm1",},
+{{0x67, 0x62, 0xf5, 0x7d, 0x48, 0x7a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7d 48 7a 8c c8 78 56 34 12 \tvcvttph2qq 0x12345678(%eax,%ecx,8),%zmm1",},
+{{0x62, 0xf5, 0x7d, 0x08, 0x7a, 0xca, }, 6, 0, "", "",
+"62 f5 7d 08 7a ca \tvcvttph2qq %xmm2,%xmm1",},
+{{0x62, 0xf5, 0x7d, 0x08, 0x7a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7d 08 7a 8c c8 78 56 34 12 \tvcvttph2qq 0x12345678(%rax,%rcx,8),%xmm1",},
+{{0x67, 0x62, 0xf5, 0x7d, 0x08, 0x7a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7d 08 7a 8c c8 78 56 34 12 \tvcvttph2qq 0x12345678(%eax,%ecx,8),%xmm1",},
+{{0x62, 0xf5, 0x7d, 0x28, 0x7a, 0xca, }, 6, 0, "", "",
+"62 f5 7d 28 7a ca \tvcvttph2qq %xmm2,%ymm1",},
+{{0x62, 0xf5, 0x7d, 0x28, 0x7a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7d 28 7a 8c c8 78 56 34 12 \tvcvttph2qq 0x12345678(%rax,%rcx,8),%ymm1",},
+{{0x67, 0x62, 0xf5, 0x7d, 0x28, 0x7a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7d 28 7a 8c c8 78 56 34 12 \tvcvttph2qq 0x12345678(%eax,%ecx,8),%ymm1",},
+{{0x62, 0xf5, 0x7c, 0x48, 0x78, 0xca, }, 6, 0, "", "",
+"62 f5 7c 48 78 ca \tvcvttph2udq %ymm2,%zmm1",},
+{{0x62, 0xf5, 0x7c, 0x48, 0x78, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7c 48 78 8c c8 78 56 34 12 \tvcvttph2udq 0x12345678(%rax,%rcx,8),%zmm1",},
+{{0x67, 0x62, 0xf5, 0x7c, 0x48, 0x78, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7c 48 78 8c c8 78 56 34 12 \tvcvttph2udq 0x12345678(%eax,%ecx,8),%zmm1",},
+{{0x62, 0xf5, 0x7c, 0x08, 0x78, 0xca, }, 6, 0, "", "",
+"62 f5 7c 08 78 ca \tvcvttph2udq %xmm2,%xmm1",},
+{{0x62, 0xf5, 0x7c, 0x08, 0x78, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7c 08 78 8c c8 78 56 34 12 \tvcvttph2udq 0x12345678(%rax,%rcx,8),%xmm1",},
+{{0x67, 0x62, 0xf5, 0x7c, 0x08, 0x78, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7c 08 78 8c c8 78 56 34 12 \tvcvttph2udq 0x12345678(%eax,%ecx,8),%xmm1",},
+{{0x62, 0xf5, 0x7c, 0x28, 0x78, 0xca, }, 6, 0, "", "",
+"62 f5 7c 28 78 ca \tvcvttph2udq %xmm2,%ymm1",},
+{{0x62, 0xf5, 0x7c, 0x28, 0x78, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7c 28 78 8c c8 78 56 34 12 \tvcvttph2udq 0x12345678(%rax,%rcx,8),%ymm1",},
+{{0x67, 0x62, 0xf5, 0x7c, 0x28, 0x78, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7c 28 78 8c c8 78 56 34 12 \tvcvttph2udq 0x12345678(%eax,%ecx,8),%ymm1",},
+{{0x62, 0xf5, 0x7d, 0x48, 0x78, 0xca, }, 6, 0, "", "",
+"62 f5 7d 48 78 ca \tvcvttph2uqq %xmm2,%zmm1",},
+{{0x62, 0xf5, 0x7d, 0x48, 0x78, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7d 48 78 8c c8 78 56 34 12 \tvcvttph2uqq 0x12345678(%rax,%rcx,8),%zmm1",},
+{{0x67, 0x62, 0xf5, 0x7d, 0x48, 0x78, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7d 48 78 8c c8 78 56 34 12 \tvcvttph2uqq 0x12345678(%eax,%ecx,8),%zmm1",},
+{{0x62, 0xf5, 0x7d, 0x08, 0x78, 0xca, }, 6, 0, "", "",
+"62 f5 7d 08 78 ca \tvcvttph2uqq %xmm2,%xmm1",},
+{{0x62, 0xf5, 0x7d, 0x08, 0x78, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7d 08 78 8c c8 78 56 34 12 \tvcvttph2uqq 0x12345678(%rax,%rcx,8),%xmm1",},
+{{0x67, 0x62, 0xf5, 0x7d, 0x08, 0x78, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7d 08 78 8c c8 78 56 34 12 \tvcvttph2uqq 0x12345678(%eax,%ecx,8),%xmm1",},
+{{0x62, 0xf5, 0x7d, 0x28, 0x78, 0xca, }, 6, 0, "", "",
+"62 f5 7d 28 78 ca \tvcvttph2uqq %xmm2,%ymm1",},
+{{0x62, 0xf5, 0x7d, 0x28, 0x78, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7d 28 78 8c c8 78 56 34 12 \tvcvttph2uqq 0x12345678(%rax,%rcx,8),%ymm1",},
+{{0x67, 0x62, 0xf5, 0x7d, 0x28, 0x78, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7d 28 78 8c c8 78 56 34 12 \tvcvttph2uqq 0x12345678(%eax,%ecx,8),%ymm1",},
+{{0x62, 0xf5, 0x7c, 0x48, 0x7c, 0xca, }, 6, 0, "", "",
+"62 f5 7c 48 7c ca \tvcvttph2uw %zmm2,%zmm1",},
+{{0x62, 0xf5, 0x7c, 0x48, 0x7c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7c 48 7c 8c c8 78 56 34 12 \tvcvttph2uw 0x12345678(%rax,%rcx,8),%zmm1",},
+{{0x67, 0x62, 0xf5, 0x7c, 0x48, 0x7c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7c 48 7c 8c c8 78 56 34 12 \tvcvttph2uw 0x12345678(%eax,%ecx,8),%zmm1",},
+{{0x62, 0xf5, 0x7c, 0x08, 0x7c, 0xca, }, 6, 0, "", "",
+"62 f5 7c 08 7c ca \tvcvttph2uw %xmm2,%xmm1",},
+{{0x62, 0xf5, 0x7c, 0x08, 0x7c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7c 08 7c 8c c8 78 56 34 12 \tvcvttph2uw 0x12345678(%rax,%rcx,8),%xmm1",},
+{{0x67, 0x62, 0xf5, 0x7c, 0x08, 0x7c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7c 08 7c 8c c8 78 56 34 12 \tvcvttph2uw 0x12345678(%eax,%ecx,8),%xmm1",},
+{{0x62, 0xf5, 0x7c, 0x28, 0x7c, 0xca, }, 6, 0, "", "",
+"62 f5 7c 28 7c ca \tvcvttph2uw %ymm2,%ymm1",},
+{{0x62, 0xf5, 0x7c, 0x28, 0x7c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7c 28 7c 8c c8 78 56 34 12 \tvcvttph2uw 0x12345678(%rax,%rcx,8),%ymm1",},
+{{0x67, 0x62, 0xf5, 0x7c, 0x28, 0x7c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7c 28 7c 8c c8 78 56 34 12 \tvcvttph2uw 0x12345678(%eax,%ecx,8),%ymm1",},
+{{0x62, 0xf5, 0x7d, 0x48, 0x7c, 0xca, }, 6, 0, "", "",
+"62 f5 7d 48 7c ca \tvcvttph2w %zmm2,%zmm1",},
+{{0x62, 0xf5, 0x7d, 0x48, 0x7c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7d 48 7c 8c c8 78 56 34 12 \tvcvttph2w 0x12345678(%rax,%rcx,8),%zmm1",},
+{{0x67, 0x62, 0xf5, 0x7d, 0x48, 0x7c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7d 48 7c 8c c8 78 56 34 12 \tvcvttph2w 0x12345678(%eax,%ecx,8),%zmm1",},
+{{0x62, 0xf5, 0x7d, 0x08, 0x7c, 0xca, }, 6, 0, "", "",
+"62 f5 7d 08 7c ca \tvcvttph2w %xmm2,%xmm1",},
+{{0x62, 0xf5, 0x7d, 0x08, 0x7c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7d 08 7c 8c c8 78 56 34 12 \tvcvttph2w 0x12345678(%rax,%rcx,8),%xmm1",},
+{{0x67, 0x62, 0xf5, 0x7d, 0x08, 0x7c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7d 08 7c 8c c8 78 56 34 12 \tvcvttph2w 0x12345678(%eax,%ecx,8),%xmm1",},
+{{0x62, 0xf5, 0x7d, 0x28, 0x7c, 0xca, }, 6, 0, "", "",
+"62 f5 7d 28 7c ca \tvcvttph2w %ymm2,%ymm1",},
+{{0x62, 0xf5, 0x7d, 0x28, 0x7c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7d 28 7c 8c c8 78 56 34 12 \tvcvttph2w 0x12345678(%rax,%rcx,8),%ymm1",},
+{{0x67, 0x62, 0xf5, 0x7d, 0x28, 0x7c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7d 28 7c 8c c8 78 56 34 12 \tvcvttph2w 0x12345678(%eax,%ecx,8),%ymm1",},
+{{0x62, 0xf5, 0x7e, 0x08, 0x2c, 0xc1, }, 6, 0, "", "",
+"62 f5 7e 08 2c c1 \tvcvttsh2si %xmm1,%eax",},
+{{0x62, 0xf5, 0x7e, 0x08, 0x2c, 0x84, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7e 08 2c 84 c8 78 56 34 12 \tvcvttsh2si 0x12345678(%rax,%rcx,8),%eax",},
+{{0x67, 0x62, 0xf5, 0x7e, 0x08, 0x2c, 0x84, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7e 08 2c 84 c8 78 56 34 12 \tvcvttsh2si 0x12345678(%eax,%ecx,8),%eax",},
+{{0x62, 0xf5, 0xfe, 0x08, 0x2c, 0xc1, }, 6, 0, "", "",
+"62 f5 fe 08 2c c1 \tvcvttsh2si %xmm1,%rax",},
+{{0x62, 0xf5, 0xfe, 0x08, 0x2c, 0x84, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 fe 08 2c 84 c8 78 56 34 12 \tvcvttsh2si 0x12345678(%rax,%rcx,8),%rax",},
+{{0x67, 0x62, 0xf5, 0xfe, 0x08, 0x2c, 0x84, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 fe 08 2c 84 c8 78 56 34 12 \tvcvttsh2si 0x12345678(%eax,%ecx,8),%rax",},
+{{0x62, 0xf5, 0x7e, 0x08, 0x78, 0xc1, }, 6, 0, "", "",
+"62 f5 7e 08 78 c1 \tvcvttsh2usi %xmm1,%eax",},
+{{0x62, 0xf5, 0x7e, 0x08, 0x78, 0x84, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7e 08 78 84 c8 78 56 34 12 \tvcvttsh2usi 0x12345678(%rax,%rcx,8),%eax",},
+{{0x67, 0x62, 0xf5, 0x7e, 0x08, 0x78, 0x84, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7e 08 78 84 c8 78 56 34 12 \tvcvttsh2usi 0x12345678(%eax,%ecx,8),%eax",},
+{{0x62, 0xf5, 0xfe, 0x08, 0x78, 0xc1, }, 6, 0, "", "",
+"62 f5 fe 08 78 c1 \tvcvttsh2usi %xmm1,%rax",},
+{{0x62, 0xf5, 0xfe, 0x08, 0x78, 0x84, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 fe 08 78 84 c8 78 56 34 12 \tvcvttsh2usi 0x12345678(%rax,%rcx,8),%rax",},
+{{0x67, 0x62, 0xf5, 0xfe, 0x08, 0x78, 0x84, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 fe 08 78 84 c8 78 56 34 12 \tvcvttsh2usi 0x12345678(%eax,%ecx,8),%rax",},
+{{0x62, 0xf5, 0x7f, 0x48, 0x7a, 0xca, }, 6, 0, "", "",
+"62 f5 7f 48 7a ca \tvcvtudq2ph %zmm2,%ymm1",},
+{{0x62, 0xf5, 0x7f, 0x48, 0x7a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7f 48 7a 8c c8 78 56 34 12 \tvcvtudq2ph 0x12345678(%rax,%rcx,8),%ymm1",},
+{{0x67, 0x62, 0xf5, 0x7f, 0x48, 0x7a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7f 48 7a 8c c8 78 56 34 12 \tvcvtudq2ph 0x12345678(%eax,%ecx,8),%ymm1",},
+{{0x62, 0xf5, 0x7f, 0x08, 0x7a, 0xca, }, 6, 0, "", "",
+"62 f5 7f 08 7a ca \tvcvtudq2ph %xmm2,%xmm1",},
+{{0x62, 0xf5, 0x7f, 0x28, 0x7a, 0xca, }, 6, 0, "", "",
+"62 f5 7f 28 7a ca \tvcvtudq2ph %ymm2,%xmm1",},
+{{0x62, 0xf5, 0xff, 0x48, 0x7a, 0xca, }, 6, 0, "", "",
+"62 f5 ff 48 7a ca \tvcvtuqq2ph %zmm2,%xmm1",},
+{{0x62, 0xf5, 0xff, 0x08, 0x7a, 0xca, }, 6, 0, "", "",
+"62 f5 ff 08 7a ca \tvcvtuqq2ph %xmm2,%xmm1",},
+{{0x62, 0xf5, 0xff, 0x28, 0x7a, 0xca, }, 6, 0, "", "",
+"62 f5 ff 28 7a ca \tvcvtuqq2ph %ymm2,%xmm1",},
+{{0x62, 0xf5, 0x6e, 0x08, 0x7b, 0xc8, }, 6, 0, "", "",
+"62 f5 6e 08 7b c8 \tvcvtusi2sh %eax,%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x6e, 0x08, 0x7b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6e 08 7b 8c c8 78 56 34 12 \tvcvtusi2shl 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf5, 0x6e, 0x08, 0x7b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 6e 08 7b 8c c8 78 56 34 12 \tvcvtusi2shl 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf5, 0xee, 0x08, 0x7b, 0xc8, }, 6, 0, "", "",
+"62 f5 ee 08 7b c8 \tvcvtusi2sh %rax,%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x6e, 0x08, 0x7b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6e 08 7b 8c c8 78 56 34 12 \tvcvtusi2shl 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf5, 0x6e, 0x08, 0x7b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 6e 08 7b 8c c8 78 56 34 12 \tvcvtusi2shl 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x7f, 0x48, 0x7d, 0xca, }, 6, 0, "", "",
+"62 f5 7f 48 7d ca \tvcvtuw2ph %zmm2,%zmm1",},
+{{0x62, 0xf5, 0x7f, 0x48, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7f 48 7d 8c c8 78 56 34 12 \tvcvtuw2ph 0x12345678(%rax,%rcx,8),%zmm1",},
+{{0x67, 0x62, 0xf5, 0x7f, 0x48, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7f 48 7d 8c c8 78 56 34 12 \tvcvtuw2ph 0x12345678(%eax,%ecx,8),%zmm1",},
+{{0x62, 0xf5, 0x7f, 0x08, 0x7d, 0xca, }, 6, 0, "", "",
+"62 f5 7f 08 7d ca \tvcvtuw2ph %xmm2,%xmm1",},
+{{0x62, 0xf5, 0x7f, 0x08, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7f 08 7d 8c c8 78 56 34 12 \tvcvtuw2ph 0x12345678(%rax,%rcx,8),%xmm1",},
+{{0x67, 0x62, 0xf5, 0x7f, 0x08, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7f 08 7d 8c c8 78 56 34 12 \tvcvtuw2ph 0x12345678(%eax,%ecx,8),%xmm1",},
+{{0x62, 0xf5, 0x7f, 0x28, 0x7d, 0xca, }, 6, 0, "", "",
+"62 f5 7f 28 7d ca \tvcvtuw2ph %ymm2,%ymm1",},
+{{0x62, 0xf5, 0x7f, 0x28, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7f 28 7d 8c c8 78 56 34 12 \tvcvtuw2ph 0x12345678(%rax,%rcx,8),%ymm1",},
+{{0x67, 0x62, 0xf5, 0x7f, 0x28, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7f 28 7d 8c c8 78 56 34 12 \tvcvtuw2ph 0x12345678(%eax,%ecx,8),%ymm1",},
+{{0x62, 0xf5, 0x7e, 0x48, 0x7d, 0xca, }, 6, 0, "", "",
+"62 f5 7e 48 7d ca \tvcvtw2ph %zmm2,%zmm1",},
+{{0x62, 0xf5, 0x7e, 0x48, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7e 48 7d 8c c8 78 56 34 12 \tvcvtw2ph 0x12345678(%rax,%rcx,8),%zmm1",},
+{{0x67, 0x62, 0xf5, 0x7e, 0x48, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7e 48 7d 8c c8 78 56 34 12 \tvcvtw2ph 0x12345678(%eax,%ecx,8),%zmm1",},
+{{0x62, 0xf5, 0x7e, 0x08, 0x7d, 0xca, }, 6, 0, "", "",
+"62 f5 7e 08 7d ca \tvcvtw2ph %xmm2,%xmm1",},
+{{0x62, 0xf5, 0x7e, 0x08, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7e 08 7d 8c c8 78 56 34 12 \tvcvtw2ph 0x12345678(%rax,%rcx,8),%xmm1",},
+{{0x67, 0x62, 0xf5, 0x7e, 0x08, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7e 08 7d 8c c8 78 56 34 12 \tvcvtw2ph 0x12345678(%eax,%ecx,8),%xmm1",},
+{{0x62, 0xf5, 0x7e, 0x28, 0x7d, 0xca, }, 6, 0, "", "",
+"62 f5 7e 28 7d ca \tvcvtw2ph %ymm2,%ymm1",},
+{{0x62, 0xf5, 0x7e, 0x28, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7e 28 7d 8c c8 78 56 34 12 \tvcvtw2ph 0x12345678(%rax,%rcx,8),%ymm1",},
+{{0x67, 0x62, 0xf5, 0x7e, 0x28, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7e 28 7d 8c c8 78 56 34 12 \tvcvtw2ph 0x12345678(%eax,%ecx,8),%ymm1",},
+{{0x62, 0xf5, 0x6c, 0x48, 0x5e, 0xcb, }, 6, 0, "", "",
+"62 f5 6c 48 5e cb \tvdivph %zmm3,%zmm2,%zmm1",},
+{{0x62, 0xf5, 0x6c, 0x48, 0x5e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6c 48 5e 8c c8 78 56 34 12 \tvdivph 0x12345678(%rax,%rcx,8),%zmm2,%zmm1",},
+{{0x67, 0x62, 0xf5, 0x6c, 0x48, 0x5e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 6c 48 5e 8c c8 78 56 34 12 \tvdivph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",},
+{{0x62, 0xf5, 0x6c, 0x08, 0x5e, 0xcb, }, 6, 0, "", "",
+"62 f5 6c 08 5e cb \tvdivph %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x6c, 0x08, 0x5e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6c 08 5e 8c c8 78 56 34 12 \tvdivph 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf5, 0x6c, 0x08, 0x5e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 6c 08 5e 8c c8 78 56 34 12 \tvdivph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x6c, 0x28, 0x5e, 0xcb, }, 6, 0, "", "",
+"62 f5 6c 28 5e cb \tvdivph %ymm3,%ymm2,%ymm1",},
+{{0x62, 0xf5, 0x6c, 0x28, 0x5e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6c 28 5e 8c c8 78 56 34 12 \tvdivph 0x12345678(%rax,%rcx,8),%ymm2,%ymm1",},
+{{0x67, 0x62, 0xf5, 0x6c, 0x28, 0x5e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 6c 28 5e 8c c8 78 56 34 12 \tvdivph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",},
+{{0x62, 0xf5, 0x6e, 0x08, 0x5e, 0xcb, }, 6, 0, "", "",
+"62 f5 6e 08 5e cb \tvdivsh %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x6e, 0x08, 0x5e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6e 08 5e 8c c8 78 56 34 12 \tvdivsh 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf5, 0x6e, 0x08, 0x5e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 6e 08 5e 8c c8 78 56 34 12 \tvdivsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6f, 0x48, 0x56, 0xcb, }, 6, 0, "", "",
+"62 f6 6f 48 56 cb \tvfcmaddcph %zmm3,%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6f, 0x48, 0x56, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6f 48 56 8c c8 78 56 34 12 \tvfcmaddcph 0x12345678(%rax,%rcx,8),%zmm2,%zmm1",},
+{{0x67, 0x62, 0xf6, 0x6f, 0x48, 0x56, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6f 48 56 8c c8 78 56 34 12 \tvfcmaddcph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6f, 0x08, 0x56, 0xcb, }, 6, 0, "", "",
+"62 f6 6f 08 56 cb \tvfcmaddcph %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6f, 0x08, 0x56, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6f 08 56 8c c8 78 56 34 12 \tvfcmaddcph 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf6, 0x6f, 0x08, 0x56, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6f 08 56 8c c8 78 56 34 12 \tvfcmaddcph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6f, 0x28, 0x56, 0xcb, }, 6, 0, "", "",
+"62 f6 6f 28 56 cb \tvfcmaddcph %ymm3,%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6f, 0x28, 0x56, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6f 28 56 8c c8 78 56 34 12 \tvfcmaddcph 0x12345678(%rax,%rcx,8),%ymm2,%ymm1",},
+{{0x67, 0x62, 0xf6, 0x6f, 0x28, 0x56, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6f 28 56 8c c8 78 56 34 12 \tvfcmaddcph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6f, 0x08, 0x57, 0xcb, }, 6, 0, "", "",
+"62 f6 6f 08 57 cb \tvfcmaddcsh %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6f, 0x08, 0x57, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6f 08 57 8c c8 78 56 34 12 \tvfcmaddcsh 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf6, 0x6f, 0x08, 0x57, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6f 08 57 8c c8 78 56 34 12 \tvfcmaddcsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6f, 0x48, 0xd6, 0xcb, }, 6, 0, "", "",
+"62 f6 6f 48 d6 cb \tvfcmulcph %zmm3,%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6f, 0x48, 0xd6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6f 48 d6 8c c8 78 56 34 12 \tvfcmulcph 0x12345678(%rax,%rcx,8),%zmm2,%zmm1",},
+{{0x67, 0x62, 0xf6, 0x6f, 0x48, 0xd6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6f 48 d6 8c c8 78 56 34 12 \tvfcmulcph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6f, 0x08, 0xd6, 0xcb, }, 6, 0, "", "",
+"62 f6 6f 08 d6 cb \tvfcmulcph %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6f, 0x08, 0xd6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6f 08 d6 8c c8 78 56 34 12 \tvfcmulcph 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf6, 0x6f, 0x08, 0xd6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6f 08 d6 8c c8 78 56 34 12 \tvfcmulcph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6f, 0x28, 0xd6, 0xcb, }, 6, 0, "", "",
+"62 f6 6f 28 d6 cb \tvfcmulcph %ymm3,%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6f, 0x28, 0xd6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6f 28 d6 8c c8 78 56 34 12 \tvfcmulcph 0x12345678(%rax,%rcx,8),%ymm2,%ymm1",},
+{{0x67, 0x62, 0xf6, 0x6f, 0x28, 0xd6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6f 28 d6 8c c8 78 56 34 12 \tvfcmulcph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6f, 0x08, 0xd7, 0xcb, }, 6, 0, "", "",
+"62 f6 6f 08 d7 cb \tvfcmulcsh %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6f, 0x08, 0xd7, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6f 08 d7 8c c8 78 56 34 12 \tvfcmulcsh 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf6, 0x6f, 0x08, 0xd7, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6f 08 d7 8c c8 78 56 34 12 \tvfcmulcsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0x98, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 48 98 cb \tvfmadd132ph %zmm3,%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0x98, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 48 98 8c c8 78 56 34 12 \tvfmadd132ph 0x12345678(%rax,%rcx,8),%zmm2,%zmm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x48, 0x98, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 48 98 8c c8 78 56 34 12 \tvfmadd132ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x98, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 98 cb \tvfmadd132ph %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x98, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 98 8c c8 78 56 34 12 \tvfmadd132ph 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0x98, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 08 98 8c c8 78 56 34 12 \tvfmadd132ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0x98, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 28 98 cb \tvfmadd132ph %ymm3,%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0x98, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 28 98 8c c8 78 56 34 12 \tvfmadd132ph 0x12345678(%rax,%rcx,8),%ymm2,%ymm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x28, 0x98, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 28 98 8c c8 78 56 34 12 \tvfmadd132ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x99, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 99 cb \tvfmadd132sh %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x99, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 99 8c c8 78 56 34 12 \tvfmadd132sh 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0x99, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 08 99 8c c8 78 56 34 12 \tvfmadd132sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0xa8, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 48 a8 cb \tvfmadd213ph %zmm3,%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0xa8, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 48 a8 8c c8 78 56 34 12 \tvfmadd213ph 0x12345678(%rax,%rcx,8),%zmm2,%zmm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x48, 0xa8, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 48 a8 8c c8 78 56 34 12 \tvfmadd213ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xa8, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 a8 cb \tvfmadd213ph %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xa8, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 a8 8c c8 78 56 34 12 \tvfmadd213ph 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0xa8, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 08 a8 8c c8 78 56 34 12 \tvfmadd213ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0xa8, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 28 a8 cb \tvfmadd213ph %ymm3,%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0xa8, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 28 a8 8c c8 78 56 34 12 \tvfmadd213ph 0x12345678(%rax,%rcx,8),%ymm2,%ymm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x28, 0xa8, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 28 a8 8c c8 78 56 34 12 \tvfmadd213ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xa9, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 a9 cb \tvfmadd213sh %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xa9, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 a9 8c c8 78 56 34 12 \tvfmadd213sh 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0xa9, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 08 a9 8c c8 78 56 34 12 \tvfmadd213sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0xb8, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 48 b8 cb \tvfmadd231ph %zmm3,%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0xb8, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 48 b8 8c c8 78 56 34 12 \tvfmadd231ph 0x12345678(%rax,%rcx,8),%zmm2,%zmm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x48, 0xb8, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 48 b8 8c c8 78 56 34 12 \tvfmadd231ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xb8, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 b8 cb \tvfmadd231ph %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xb8, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 b8 8c c8 78 56 34 12 \tvfmadd231ph 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0xb8, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 08 b8 8c c8 78 56 34 12 \tvfmadd231ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0xb8, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 28 b8 cb \tvfmadd231ph %ymm3,%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0xb8, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 28 b8 8c c8 78 56 34 12 \tvfmadd231ph 0x12345678(%rax,%rcx,8),%ymm2,%ymm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x28, 0xb8, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 28 b8 8c c8 78 56 34 12 \tvfmadd231ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xb9, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 b9 cb \tvfmadd231sh %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xb9, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 b9 8c c8 78 56 34 12 \tvfmadd231sh 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0xb9, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 08 b9 8c c8 78 56 34 12 \tvfmadd231sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6e, 0x48, 0x56, 0xcb, }, 6, 0, "", "",
+"62 f6 6e 48 56 cb \tvfmaddcph %zmm3,%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6e, 0x48, 0x56, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6e 48 56 8c c8 78 56 34 12 \tvfmaddcph 0x12345678(%rax,%rcx,8),%zmm2,%zmm1",},
+{{0x67, 0x62, 0xf6, 0x6e, 0x48, 0x56, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6e 48 56 8c c8 78 56 34 12 \tvfmaddcph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6e, 0x08, 0x56, 0xcb, }, 6, 0, "", "",
+"62 f6 6e 08 56 cb \tvfmaddcph %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6e, 0x08, 0x56, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6e 08 56 8c c8 78 56 34 12 \tvfmaddcph 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf6, 0x6e, 0x08, 0x56, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6e 08 56 8c c8 78 56 34 12 \tvfmaddcph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6e, 0x28, 0x56, 0xcb, }, 6, 0, "", "",
+"62 f6 6e 28 56 cb \tvfmaddcph %ymm3,%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6e, 0x28, 0x56, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6e 28 56 8c c8 78 56 34 12 \tvfmaddcph 0x12345678(%rax,%rcx,8),%ymm2,%ymm1",},
+{{0x67, 0x62, 0xf6, 0x6e, 0x28, 0x56, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6e 28 56 8c c8 78 56 34 12 \tvfmaddcph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6e, 0x08, 0x57, 0xcb, }, 6, 0, "", "",
+"62 f6 6e 08 57 cb \tvfmaddcsh %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6e, 0x08, 0x57, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6e 08 57 8c c8 78 56 34 12 \tvfmaddcsh 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf6, 0x6e, 0x08, 0x57, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6e 08 57 8c c8 78 56 34 12 \tvfmaddcsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0x96, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 48 96 cb \tvfmaddsub132ph %zmm3,%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0x96, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 48 96 8c c8 78 56 34 12 \tvfmaddsub132ph 0x12345678(%rax,%rcx,8),%zmm2,%zmm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x48, 0x96, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 48 96 8c c8 78 56 34 12 \tvfmaddsub132ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x96, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 96 cb \tvfmaddsub132ph %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x96, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 96 8c c8 78 56 34 12 \tvfmaddsub132ph 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0x96, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 08 96 8c c8 78 56 34 12 \tvfmaddsub132ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0x96, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 28 96 cb \tvfmaddsub132ph %ymm3,%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0x96, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 28 96 8c c8 78 56 34 12 \tvfmaddsub132ph 0x12345678(%rax,%rcx,8),%ymm2,%ymm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x28, 0x96, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 28 96 8c c8 78 56 34 12 \tvfmaddsub132ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0xa6, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 48 a6 cb \tvfmaddsub213ph %zmm3,%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0xa6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 48 a6 8c c8 78 56 34 12 \tvfmaddsub213ph 0x12345678(%rax,%rcx,8),%zmm2,%zmm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x48, 0xa6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 48 a6 8c c8 78 56 34 12 \tvfmaddsub213ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xa6, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 a6 cb \tvfmaddsub213ph %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xa6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 a6 8c c8 78 56 34 12 \tvfmaddsub213ph 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0xa6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 08 a6 8c c8 78 56 34 12 \tvfmaddsub213ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0xa6, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 28 a6 cb \tvfmaddsub213ph %ymm3,%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0xa6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 28 a6 8c c8 78 56 34 12 \tvfmaddsub213ph 0x12345678(%rax,%rcx,8),%ymm2,%ymm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x28, 0xa6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 28 a6 8c c8 78 56 34 12 \tvfmaddsub213ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0xb6, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 48 b6 cb \tvfmaddsub231ph %zmm3,%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0xb6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 48 b6 8c c8 78 56 34 12 \tvfmaddsub231ph 0x12345678(%rax,%rcx,8),%zmm2,%zmm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x48, 0xb6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 48 b6 8c c8 78 56 34 12 \tvfmaddsub231ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xb6, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 b6 cb \tvfmaddsub231ph %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xb6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 b6 8c c8 78 56 34 12 \tvfmaddsub231ph 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0xb6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 08 b6 8c c8 78 56 34 12 \tvfmaddsub231ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0xb6, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 28 b6 cb \tvfmaddsub231ph %ymm3,%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0xb6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 28 b6 8c c8 78 56 34 12 \tvfmaddsub231ph 0x12345678(%rax,%rcx,8),%ymm2,%ymm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x28, 0xb6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 28 b6 8c c8 78 56 34 12 \tvfmaddsub231ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0x9a, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 48 9a cb \tvfmsub132ph %zmm3,%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0x9a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 48 9a 8c c8 78 56 34 12 \tvfmsub132ph 0x12345678(%rax,%rcx,8),%zmm2,%zmm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x48, 0x9a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 48 9a 8c c8 78 56 34 12 \tvfmsub132ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x9a, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 9a cb \tvfmsub132ph %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x9a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 9a 8c c8 78 56 34 12 \tvfmsub132ph 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0x9a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 08 9a 8c c8 78 56 34 12 \tvfmsub132ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0x9a, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 28 9a cb \tvfmsub132ph %ymm3,%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0x9a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 28 9a 8c c8 78 56 34 12 \tvfmsub132ph 0x12345678(%rax,%rcx,8),%ymm2,%ymm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x28, 0x9a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 28 9a 8c c8 78 56 34 12 \tvfmsub132ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x9b, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 9b cb \tvfmsub132sh %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x9b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 9b 8c c8 78 56 34 12 \tvfmsub132sh 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0x9b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 08 9b 8c c8 78 56 34 12 \tvfmsub132sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0xaa, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 48 aa cb \tvfmsub213ph %zmm3,%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0xaa, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 48 aa 8c c8 78 56 34 12 \tvfmsub213ph 0x12345678(%rax,%rcx,8),%zmm2,%zmm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x48, 0xaa, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 48 aa 8c c8 78 56 34 12 \tvfmsub213ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xaa, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 aa cb \tvfmsub213ph %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xaa, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 aa 8c c8 78 56 34 12 \tvfmsub213ph 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0xaa, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 08 aa 8c c8 78 56 34 12 \tvfmsub213ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0xaa, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 28 aa cb \tvfmsub213ph %ymm3,%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0xaa, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 28 aa 8c c8 78 56 34 12 \tvfmsub213ph 0x12345678(%rax,%rcx,8),%ymm2,%ymm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x28, 0xaa, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 28 aa 8c c8 78 56 34 12 \tvfmsub213ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xab, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 ab cb \tvfmsub213sh %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xab, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 ab 8c c8 78 56 34 12 \tvfmsub213sh 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0xab, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 08 ab 8c c8 78 56 34 12 \tvfmsub213sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0xba, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 48 ba cb \tvfmsub231ph %zmm3,%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0xba, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 48 ba 8c c8 78 56 34 12 \tvfmsub231ph 0x12345678(%rax,%rcx,8),%zmm2,%zmm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x48, 0xba, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 48 ba 8c c8 78 56 34 12 \tvfmsub231ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xba, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 ba cb \tvfmsub231ph %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xba, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 ba 8c c8 78 56 34 12 \tvfmsub231ph 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0xba, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 08 ba 8c c8 78 56 34 12 \tvfmsub231ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0xba, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 28 ba cb \tvfmsub231ph %ymm3,%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0xba, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 28 ba 8c c8 78 56 34 12 \tvfmsub231ph 0x12345678(%rax,%rcx,8),%ymm2,%ymm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x28, 0xba, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 28 ba 8c c8 78 56 34 12 \tvfmsub231ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xbb, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 bb cb \tvfmsub231sh %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xbb, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 bb 8c c8 78 56 34 12 \tvfmsub231sh 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0xbb, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 08 bb 8c c8 78 56 34 12 \tvfmsub231sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0x97, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 48 97 cb \tvfmsubadd132ph %zmm3,%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0x97, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 48 97 8c c8 78 56 34 12 \tvfmsubadd132ph 0x12345678(%rax,%rcx,8),%zmm2,%zmm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x48, 0x97, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 48 97 8c c8 78 56 34 12 \tvfmsubadd132ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x97, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 97 cb \tvfmsubadd132ph %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x97, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 97 8c c8 78 56 34 12 \tvfmsubadd132ph 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0x97, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 08 97 8c c8 78 56 34 12 \tvfmsubadd132ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0x97, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 28 97 cb \tvfmsubadd132ph %ymm3,%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0x97, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 28 97 8c c8 78 56 34 12 \tvfmsubadd132ph 0x12345678(%rax,%rcx,8),%ymm2,%ymm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x28, 0x97, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 28 97 8c c8 78 56 34 12 \tvfmsubadd132ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0xa7, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 48 a7 cb \tvfmsubadd213ph %zmm3,%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0xa7, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 48 a7 8c c8 78 56 34 12 \tvfmsubadd213ph 0x12345678(%rax,%rcx,8),%zmm2,%zmm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x48, 0xa7, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 48 a7 8c c8 78 56 34 12 \tvfmsubadd213ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xa7, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 a7 cb \tvfmsubadd213ph %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xa7, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 a7 8c c8 78 56 34 12 \tvfmsubadd213ph 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0xa7, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 08 a7 8c c8 78 56 34 12 \tvfmsubadd213ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0xa7, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 28 a7 cb \tvfmsubadd213ph %ymm3,%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0xa7, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 28 a7 8c c8 78 56 34 12 \tvfmsubadd213ph 0x12345678(%rax,%rcx,8),%ymm2,%ymm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x28, 0xa7, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 28 a7 8c c8 78 56 34 12 \tvfmsubadd213ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0xb7, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 48 b7 cb \tvfmsubadd231ph %zmm3,%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0xb7, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 48 b7 8c c8 78 56 34 12 \tvfmsubadd231ph 0x12345678(%rax,%rcx,8),%zmm2,%zmm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x48, 0xb7, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 48 b7 8c c8 78 56 34 12 \tvfmsubadd231ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xb7, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 b7 cb \tvfmsubadd231ph %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xb7, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 b7 8c c8 78 56 34 12 \tvfmsubadd231ph 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0xb7, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 08 b7 8c c8 78 56 34 12 \tvfmsubadd231ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0xb7, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 28 b7 cb \tvfmsubadd231ph %ymm3,%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0xb7, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 28 b7 8c c8 78 56 34 12 \tvfmsubadd231ph 0x12345678(%rax,%rcx,8),%ymm2,%ymm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x28, 0xb7, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 28 b7 8c c8 78 56 34 12 \tvfmsubadd231ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6e, 0x48, 0xd6, 0xcb, }, 6, 0, "", "",
+"62 f6 6e 48 d6 cb \tvfmulcph %zmm3,%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6e, 0x48, 0xd6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6e 48 d6 8c c8 78 56 34 12 \tvfmulcph 0x12345678(%rax,%rcx,8),%zmm2,%zmm1",},
+{{0x67, 0x62, 0xf6, 0x6e, 0x48, 0xd6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6e 48 d6 8c c8 78 56 34 12 \tvfmulcph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6e, 0x08, 0xd6, 0xcb, }, 6, 0, "", "",
+"62 f6 6e 08 d6 cb \tvfmulcph %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6e, 0x08, 0xd6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6e 08 d6 8c c8 78 56 34 12 \tvfmulcph 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf6, 0x6e, 0x08, 0xd6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6e 08 d6 8c c8 78 56 34 12 \tvfmulcph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6e, 0x28, 0xd6, 0xcb, }, 6, 0, "", "",
+"62 f6 6e 28 d6 cb \tvfmulcph %ymm3,%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6e, 0x28, 0xd6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6e 28 d6 8c c8 78 56 34 12 \tvfmulcph 0x12345678(%rax,%rcx,8),%ymm2,%ymm1",},
+{{0x67, 0x62, 0xf6, 0x6e, 0x28, 0xd6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6e 28 d6 8c c8 78 56 34 12 \tvfmulcph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6e, 0x08, 0xd7, 0xcb, }, 6, 0, "", "",
+"62 f6 6e 08 d7 cb \tvfmulcsh %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6e, 0x08, 0xd7, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6e 08 d7 8c c8 78 56 34 12 \tvfmulcsh 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf6, 0x6e, 0x08, 0xd7, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6e 08 d7 8c c8 78 56 34 12 \tvfmulcsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0x9c, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 48 9c cb \tvfnmadd132ph %zmm3,%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0x9c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 48 9c 8c c8 78 56 34 12 \tvfnmadd132ph 0x12345678(%rax,%rcx,8),%zmm2,%zmm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x48, 0x9c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 48 9c 8c c8 78 56 34 12 \tvfnmadd132ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x9c, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 9c cb \tvfnmadd132ph %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x9c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 9c 8c c8 78 56 34 12 \tvfnmadd132ph 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0x9c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 08 9c 8c c8 78 56 34 12 \tvfnmadd132ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0x9c, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 28 9c cb \tvfnmadd132ph %ymm3,%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0x9c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 28 9c 8c c8 78 56 34 12 \tvfnmadd132ph 0x12345678(%rax,%rcx,8),%ymm2,%ymm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x28, 0x9c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 28 9c 8c c8 78 56 34 12 \tvfnmadd132ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x9d, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 9d cb \tvfnmadd132sh %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x9d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 9d 8c c8 78 56 34 12 \tvfnmadd132sh 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0x9d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 08 9d 8c c8 78 56 34 12 \tvfnmadd132sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0xac, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 48 ac cb \tvfnmadd213ph %zmm3,%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0xac, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 48 ac 8c c8 78 56 34 12 \tvfnmadd213ph 0x12345678(%rax,%rcx,8),%zmm2,%zmm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x48, 0xac, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 48 ac 8c c8 78 56 34 12 \tvfnmadd213ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xac, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 ac cb \tvfnmadd213ph %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xac, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 ac 8c c8 78 56 34 12 \tvfnmadd213ph 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0xac, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 08 ac 8c c8 78 56 34 12 \tvfnmadd213ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0xac, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 28 ac cb \tvfnmadd213ph %ymm3,%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0xac, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 28 ac 8c c8 78 56 34 12 \tvfnmadd213ph 0x12345678(%rax,%rcx,8),%ymm2,%ymm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x28, 0xac, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 28 ac 8c c8 78 56 34 12 \tvfnmadd213ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xad, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 ad cb \tvfnmadd213sh %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xad, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 ad 8c c8 78 56 34 12 \tvfnmadd213sh 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0xad, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 08 ad 8c c8 78 56 34 12 \tvfnmadd213sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0xbc, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 48 bc cb \tvfnmadd231ph %zmm3,%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0xbc, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 48 bc 8c c8 78 56 34 12 \tvfnmadd231ph 0x12345678(%rax,%rcx,8),%zmm2,%zmm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x48, 0xbc, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 48 bc 8c c8 78 56 34 12 \tvfnmadd231ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xbc, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 bc cb \tvfnmadd231ph %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xbc, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 bc 8c c8 78 56 34 12 \tvfnmadd231ph 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0xbc, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 08 bc 8c c8 78 56 34 12 \tvfnmadd231ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0xbc, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 28 bc cb \tvfnmadd231ph %ymm3,%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0xbc, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 28 bc 8c c8 78 56 34 12 \tvfnmadd231ph 0x12345678(%rax,%rcx,8),%ymm2,%ymm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x28, 0xbc, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 28 bc 8c c8 78 56 34 12 \tvfnmadd231ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xbd, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 bd cb \tvfnmadd231sh %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xbd, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 bd 8c c8 78 56 34 12 \tvfnmadd231sh 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0xbd, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 08 bd 8c c8 78 56 34 12 \tvfnmadd231sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0x9e, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 48 9e cb \tvfnmsub132ph %zmm3,%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0x9e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 48 9e 8c c8 78 56 34 12 \tvfnmsub132ph 0x12345678(%rax,%rcx,8),%zmm2,%zmm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x48, 0x9e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 48 9e 8c c8 78 56 34 12 \tvfnmsub132ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x9e, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 9e cb \tvfnmsub132ph %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x9e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 9e 8c c8 78 56 34 12 \tvfnmsub132ph 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0x9e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 08 9e 8c c8 78 56 34 12 \tvfnmsub132ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0x9e, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 28 9e cb \tvfnmsub132ph %ymm3,%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0x9e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 28 9e 8c c8 78 56 34 12 \tvfnmsub132ph 0x12345678(%rax,%rcx,8),%ymm2,%ymm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x28, 0x9e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 28 9e 8c c8 78 56 34 12 \tvfnmsub132ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x9f, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 9f cb \tvfnmsub132sh %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x9f, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 9f 8c c8 78 56 34 12 \tvfnmsub132sh 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0x9f, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 08 9f 8c c8 78 56 34 12 \tvfnmsub132sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0xae, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 48 ae cb \tvfnmsub213ph %zmm3,%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0xae, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 48 ae 8c c8 78 56 34 12 \tvfnmsub213ph 0x12345678(%rax,%rcx,8),%zmm2,%zmm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x48, 0xae, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 48 ae 8c c8 78 56 34 12 \tvfnmsub213ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xae, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 ae cb \tvfnmsub213ph %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xae, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 ae 8c c8 78 56 34 12 \tvfnmsub213ph 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0xae, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 08 ae 8c c8 78 56 34 12 \tvfnmsub213ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0xae, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 28 ae cb \tvfnmsub213ph %ymm3,%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0xae, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 28 ae 8c c8 78 56 34 12 \tvfnmsub213ph 0x12345678(%rax,%rcx,8),%ymm2,%ymm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x28, 0xae, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 28 ae 8c c8 78 56 34 12 \tvfnmsub213ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xaf, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 af cb \tvfnmsub213sh %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xaf, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 af 8c c8 78 56 34 12 \tvfnmsub213sh 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0xaf, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 08 af 8c c8 78 56 34 12 \tvfnmsub213sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0xbe, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 48 be cb \tvfnmsub231ph %zmm3,%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0xbe, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 48 be 8c c8 78 56 34 12 \tvfnmsub231ph 0x12345678(%rax,%rcx,8),%zmm2,%zmm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x48, 0xbe, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 48 be 8c c8 78 56 34 12 \tvfnmsub231ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xbe, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 be cb \tvfnmsub231ph %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xbe, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 be 8c c8 78 56 34 12 \tvfnmsub231ph 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0xbe, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 08 be 8c c8 78 56 34 12 \tvfnmsub231ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0xbe, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 28 be cb \tvfnmsub231ph %ymm3,%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0xbe, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 28 be 8c c8 78 56 34 12 \tvfnmsub231ph 0x12345678(%rax,%rcx,8),%ymm2,%ymm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x28, 0xbe, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 28 be 8c c8 78 56 34 12 \tvfnmsub231ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xbf, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 bf cb \tvfnmsub231sh %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0xbf, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 bf 8c c8 78 56 34 12 \tvfnmsub231sh 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0xbf, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 08 bf 8c c8 78 56 34 12 \tvfnmsub231sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf3, 0x7c, 0x48, 0x66, 0xe9, 0x12, }, 7, 0, "", "",
+"62 f3 7c 48 66 e9 12 \tvfpclassph $0x12,%zmm1,%k5",},
+{{0x62, 0xf3, 0x7c, 0x08, 0x66, 0xe9, 0x12, }, 7, 0, "", "",
+"62 f3 7c 08 66 e9 12 \tvfpclassph $0x12,%xmm1,%k5",},
+{{0x62, 0xf3, 0x7c, 0x28, 0x66, 0xe9, 0x12, }, 7, 0, "", "",
+"62 f3 7c 28 66 e9 12 \tvfpclassph $0x12,%ymm1,%k5",},
+{{0x62, 0xf3, 0x7c, 0x08, 0x67, 0xe9, 0x12, }, 7, 0, "", "",
+"62 f3 7c 08 67 e9 12 \tvfpclasssh $0x12,%xmm1,%k5",},
+{{0x62, 0xf3, 0x7c, 0x08, 0x67, 0xac, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "",
+"62 f3 7c 08 67 ac c8 78 56 34 12 12 \tvfpclasssh $0x12,0x12345678(%rax,%rcx,8),%k5",},
+{{0x67, 0x62, 0xf3, 0x7c, 0x08, 0x67, 0xac, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 13, 0, "", "",
+"67 62 f3 7c 08 67 ac c8 78 56 34 12 12 \tvfpclasssh $0x12,0x12345678(%eax,%ecx,8),%k5",},
+{{0x62, 0xf6, 0x7d, 0x48, 0x42, 0xca, }, 6, 0, "", "",
+"62 f6 7d 48 42 ca \tvgetexpph %zmm2,%zmm1",},
+{{0x62, 0xf6, 0x7d, 0x48, 0x42, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 7d 48 42 8c c8 78 56 34 12 \tvgetexpph 0x12345678(%rax,%rcx,8),%zmm1",},
+{{0x67, 0x62, 0xf6, 0x7d, 0x48, 0x42, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 7d 48 42 8c c8 78 56 34 12 \tvgetexpph 0x12345678(%eax,%ecx,8),%zmm1",},
+{{0x62, 0xf6, 0x7d, 0x08, 0x42, 0xca, }, 6, 0, "", "",
+"62 f6 7d 08 42 ca \tvgetexpph %xmm2,%xmm1",},
+{{0x62, 0xf6, 0x7d, 0x08, 0x42, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 7d 08 42 8c c8 78 56 34 12 \tvgetexpph 0x12345678(%rax,%rcx,8),%xmm1",},
+{{0x67, 0x62, 0xf6, 0x7d, 0x08, 0x42, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 7d 08 42 8c c8 78 56 34 12 \tvgetexpph 0x12345678(%eax,%ecx,8),%xmm1",},
+{{0x62, 0xf6, 0x7d, 0x28, 0x42, 0xca, }, 6, 0, "", "",
+"62 f6 7d 28 42 ca \tvgetexpph %ymm2,%ymm1",},
+{{0x62, 0xf6, 0x7d, 0x28, 0x42, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 7d 28 42 8c c8 78 56 34 12 \tvgetexpph 0x12345678(%rax,%rcx,8),%ymm1",},
+{{0x67, 0x62, 0xf6, 0x7d, 0x28, 0x42, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 7d 28 42 8c c8 78 56 34 12 \tvgetexpph 0x12345678(%eax,%ecx,8),%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x43, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 43 cb \tvgetexpsh %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x43, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 43 8c c8 78 56 34 12 \tvgetexpsh 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0x43, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 08 43 8c c8 78 56 34 12 \tvgetexpsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf3, 0x7c, 0x48, 0x26, 0xca, 0x12, }, 7, 0, "", "",
+"62 f3 7c 48 26 ca 12 \tvgetmantph $0x12,%zmm2,%zmm1",},
+{{0x62, 0xf3, 0x7c, 0x48, 0x26, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "",
+"62 f3 7c 48 26 8c c8 78 56 34 12 12 \tvgetmantph $0x12,0x12345678(%rax,%rcx,8),%zmm1",},
+{{0x67, 0x62, 0xf3, 0x7c, 0x48, 0x26, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 13, 0, "", "",
+"67 62 f3 7c 48 26 8c c8 78 56 34 12 12 \tvgetmantph $0x12,0x12345678(%eax,%ecx,8),%zmm1",},
+{{0x62, 0xf3, 0x7c, 0x08, 0x26, 0xca, 0x12, }, 7, 0, "", "",
+"62 f3 7c 08 26 ca 12 \tvgetmantph $0x12,%xmm2,%xmm1",},
+{{0x62, 0xf3, 0x7c, 0x08, 0x26, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "",
+"62 f3 7c 08 26 8c c8 78 56 34 12 12 \tvgetmantph $0x12,0x12345678(%rax,%rcx,8),%xmm1",},
+{{0x67, 0x62, 0xf3, 0x7c, 0x08, 0x26, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 13, 0, "", "",
+"67 62 f3 7c 08 26 8c c8 78 56 34 12 12 \tvgetmantph $0x12,0x12345678(%eax,%ecx,8),%xmm1",},
+{{0x62, 0xf3, 0x7c, 0x28, 0x26, 0xca, 0x12, }, 7, 0, "", "",
+"62 f3 7c 28 26 ca 12 \tvgetmantph $0x12,%ymm2,%ymm1",},
+{{0x62, 0xf3, 0x7c, 0x28, 0x26, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "",
+"62 f3 7c 28 26 8c c8 78 56 34 12 12 \tvgetmantph $0x12,0x12345678(%rax,%rcx,8),%ymm1",},
+{{0x67, 0x62, 0xf3, 0x7c, 0x28, 0x26, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 13, 0, "", "",
+"67 62 f3 7c 28 26 8c c8 78 56 34 12 12 \tvgetmantph $0x12,0x12345678(%eax,%ecx,8),%ymm1",},
+{{0x62, 0xf3, 0x6c, 0x08, 0x27, 0xcb, 0x12, }, 7, 0, "", "",
+"62 f3 6c 08 27 cb 12 \tvgetmantsh $0x12,%xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf3, 0x6c, 0x08, 0x27, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "",
+"62 f3 6c 08 27 8c c8 78 56 34 12 12 \tvgetmantsh $0x12,0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf3, 0x6c, 0x08, 0x27, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 13, 0, "", "",
+"67 62 f3 6c 08 27 8c c8 78 56 34 12 12 \tvgetmantsh $0x12,0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x6c, 0x48, 0x5f, 0xcb, }, 6, 0, "", "",
+"62 f5 6c 48 5f cb \tvmaxph %zmm3,%zmm2,%zmm1",},
+{{0x62, 0xf5, 0x6c, 0x48, 0x5f, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6c 48 5f 8c c8 78 56 34 12 \tvmaxph 0x12345678(%rax,%rcx,8),%zmm2,%zmm1",},
+{{0x67, 0x62, 0xf5, 0x6c, 0x48, 0x5f, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 6c 48 5f 8c c8 78 56 34 12 \tvmaxph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",},
+{{0x62, 0xf5, 0x6c, 0x08, 0x5f, 0xcb, }, 6, 0, "", "",
+"62 f5 6c 08 5f cb \tvmaxph %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x6c, 0x08, 0x5f, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6c 08 5f 8c c8 78 56 34 12 \tvmaxph 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf5, 0x6c, 0x08, 0x5f, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 6c 08 5f 8c c8 78 56 34 12 \tvmaxph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x6c, 0x28, 0x5f, 0xcb, }, 6, 0, "", "",
+"62 f5 6c 28 5f cb \tvmaxph %ymm3,%ymm2,%ymm1",},
+{{0x62, 0xf5, 0x6c, 0x28, 0x5f, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6c 28 5f 8c c8 78 56 34 12 \tvmaxph 0x12345678(%rax,%rcx,8),%ymm2,%ymm1",},
+{{0x67, 0x62, 0xf5, 0x6c, 0x28, 0x5f, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 6c 28 5f 8c c8 78 56 34 12 \tvmaxph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",},
+{{0x62, 0xf5, 0x6e, 0x08, 0x5f, 0xcb, }, 6, 0, "", "",
+"62 f5 6e 08 5f cb \tvmaxsh %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x6e, 0x08, 0x5f, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6e 08 5f 8c c8 78 56 34 12 \tvmaxsh 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf5, 0x6e, 0x08, 0x5f, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 6e 08 5f 8c c8 78 56 34 12 \tvmaxsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x6c, 0x48, 0x5d, 0xcb, }, 6, 0, "", "",
+"62 f5 6c 48 5d cb \tvminph %zmm3,%zmm2,%zmm1",},
+{{0x62, 0xf5, 0x6c, 0x48, 0x5d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6c 48 5d 8c c8 78 56 34 12 \tvminph 0x12345678(%rax,%rcx,8),%zmm2,%zmm1",},
+{{0x67, 0x62, 0xf5, 0x6c, 0x48, 0x5d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 6c 48 5d 8c c8 78 56 34 12 \tvminph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",},
+{{0x62, 0xf5, 0x6c, 0x08, 0x5d, 0xcb, }, 6, 0, "", "",
+"62 f5 6c 08 5d cb \tvminph %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x6c, 0x08, 0x5d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6c 08 5d 8c c8 78 56 34 12 \tvminph 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf5, 0x6c, 0x08, 0x5d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 6c 08 5d 8c c8 78 56 34 12 \tvminph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x6c, 0x28, 0x5d, 0xcb, }, 6, 0, "", "",
+"62 f5 6c 28 5d cb \tvminph %ymm3,%ymm2,%ymm1",},
+{{0x62, 0xf5, 0x6c, 0x28, 0x5d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6c 28 5d 8c c8 78 56 34 12 \tvminph 0x12345678(%rax,%rcx,8),%ymm2,%ymm1",},
+{{0x67, 0x62, 0xf5, 0x6c, 0x28, 0x5d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 6c 28 5d 8c c8 78 56 34 12 \tvminph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",},
+{{0x62, 0xf5, 0x6e, 0x08, 0x5d, 0xcb, }, 6, 0, "", "",
+"62 f5 6e 08 5d cb \tvminsh %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x6e, 0x08, 0x5d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6e 08 5d 8c c8 78 56 34 12 \tvminsh 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf5, 0x6e, 0x08, 0x5d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 6e 08 5d 8c c8 78 56 34 12 \tvminsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x7e, 0x08, 0x11, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7e 08 11 8c c8 78 56 34 12 \tvmovsh %xmm1,0x12345678(%rax,%rcx,8)",},
+{{0x67, 0x62, 0xf5, 0x7e, 0x08, 0x11, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7e 08 11 8c c8 78 56 34 12 \tvmovsh %xmm1,0x12345678(%eax,%ecx,8)",},
+{{0x62, 0xf5, 0x7e, 0x08, 0x10, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7e 08 10 8c c8 78 56 34 12 \tvmovsh 0x12345678(%rax,%rcx,8),%xmm1",},
+{{0x67, 0x62, 0xf5, 0x7e, 0x08, 0x10, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7e 08 10 8c c8 78 56 34 12 \tvmovsh 0x12345678(%eax,%ecx,8),%xmm1",},
+{{0x62, 0xf5, 0x6e, 0x08, 0x10, 0xcb, }, 6, 0, "", "",
+"62 f5 6e 08 10 cb \tvmovsh %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x7d, 0x08, 0x7e, 0xc8, }, 6, 0, "", "",
+"62 f5 7d 08 7e c8 \tvmovw %xmm1,%eax",},
+{{0x62, 0xf5, 0x7d, 0x08, 0x7e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7d 08 7e 8c c8 78 56 34 12 \tvmovw %xmm1,0x12345678(%rax,%rcx,8)",},
+{{0x67, 0x62, 0xf5, 0x7d, 0x08, 0x7e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7d 08 7e 8c c8 78 56 34 12 \tvmovw %xmm1,0x12345678(%eax,%ecx,8)",},
+{{0x62, 0xf5, 0x7d, 0x08, 0x6e, 0xc8, }, 6, 0, "", "",
+"62 f5 7d 08 6e c8 \tvmovw %eax,%xmm1",},
+{{0x62, 0xf5, 0x7d, 0x08, 0x6e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7d 08 6e 8c c8 78 56 34 12 \tvmovw 0x12345678(%rax,%rcx,8),%xmm1",},
+{{0x67, 0x62, 0xf5, 0x7d, 0x08, 0x6e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7d 08 6e 8c c8 78 56 34 12 \tvmovw 0x12345678(%eax,%ecx,8),%xmm1",},
+{{0x62, 0xf5, 0x6c, 0x48, 0x59, 0xcb, }, 6, 0, "", "",
+"62 f5 6c 48 59 cb \tvmulph %zmm3,%zmm2,%zmm1",},
+{{0x62, 0xf5, 0x6c, 0x48, 0x59, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6c 48 59 8c c8 78 56 34 12 \tvmulph 0x12345678(%rax,%rcx,8),%zmm2,%zmm1",},
+{{0x67, 0x62, 0xf5, 0x6c, 0x48, 0x59, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 6c 48 59 8c c8 78 56 34 12 \tvmulph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",},
+{{0x62, 0xf5, 0x6c, 0x08, 0x59, 0xcb, }, 6, 0, "", "",
+"62 f5 6c 08 59 cb \tvmulph %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x6c, 0x08, 0x59, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6c 08 59 8c c8 78 56 34 12 \tvmulph 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf5, 0x6c, 0x08, 0x59, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 6c 08 59 8c c8 78 56 34 12 \tvmulph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x6c, 0x28, 0x59, 0xcb, }, 6, 0, "", "",
+"62 f5 6c 28 59 cb \tvmulph %ymm3,%ymm2,%ymm1",},
+{{0x62, 0xf5, 0x6c, 0x28, 0x59, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6c 28 59 8c c8 78 56 34 12 \tvmulph 0x12345678(%rax,%rcx,8),%ymm2,%ymm1",},
+{{0x67, 0x62, 0xf5, 0x6c, 0x28, 0x59, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 6c 28 59 8c c8 78 56 34 12 \tvmulph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",},
+{{0x62, 0xf5, 0x6e, 0x08, 0x59, 0xcb, }, 6, 0, "", "",
+"62 f5 6e 08 59 cb \tvmulsh %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x6e, 0x08, 0x59, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6e 08 59 8c c8 78 56 34 12 \tvmulsh 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf5, 0x6e, 0x08, 0x59, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 6e 08 59 8c c8 78 56 34 12 \tvmulsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x7d, 0x48, 0x4c, 0xca, }, 6, 0, "", "",
+"62 f6 7d 48 4c ca \tvrcpph %zmm2,%zmm1",},
+{{0x62, 0xf6, 0x7d, 0x48, 0x4c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 7d 48 4c 8c c8 78 56 34 12 \tvrcpph 0x12345678(%rax,%rcx,8),%zmm1",},
+{{0x67, 0x62, 0xf6, 0x7d, 0x48, 0x4c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 7d 48 4c 8c c8 78 56 34 12 \tvrcpph 0x12345678(%eax,%ecx,8),%zmm1",},
+{{0x62, 0xf6, 0x7d, 0x08, 0x4c, 0xca, }, 6, 0, "", "",
+"62 f6 7d 08 4c ca \tvrcpph %xmm2,%xmm1",},
+{{0x62, 0xf6, 0x7d, 0x08, 0x4c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 7d 08 4c 8c c8 78 56 34 12 \tvrcpph 0x12345678(%rax,%rcx,8),%xmm1",},
+{{0x67, 0x62, 0xf6, 0x7d, 0x08, 0x4c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 7d 08 4c 8c c8 78 56 34 12 \tvrcpph 0x12345678(%eax,%ecx,8),%xmm1",},
+{{0x62, 0xf6, 0x7d, 0x28, 0x4c, 0xca, }, 6, 0, "", "",
+"62 f6 7d 28 4c ca \tvrcpph %ymm2,%ymm1",},
+{{0x62, 0xf6, 0x7d, 0x28, 0x4c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 7d 28 4c 8c c8 78 56 34 12 \tvrcpph 0x12345678(%rax,%rcx,8),%ymm1",},
+{{0x67, 0x62, 0xf6, 0x7d, 0x28, 0x4c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 7d 28 4c 8c c8 78 56 34 12 \tvrcpph 0x12345678(%eax,%ecx,8),%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x4d, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 4d cb \tvrcpsh %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x4d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 4d 8c c8 78 56 34 12 \tvrcpsh 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0x4d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 08 4d 8c c8 78 56 34 12 \tvrcpsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf3, 0x7c, 0x48, 0x56, 0xca, 0x12, }, 7, 0, "", "",
+"62 f3 7c 48 56 ca 12 \tvreduceph $0x12,%zmm2,%zmm1",},
+{{0x62, 0xf3, 0x7c, 0x48, 0x56, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "",
+"62 f3 7c 48 56 8c c8 78 56 34 12 12 \tvreduceph $0x12,0x12345678(%rax,%rcx,8),%zmm1",},
+{{0x67, 0x62, 0xf3, 0x7c, 0x48, 0x56, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 13, 0, "", "",
+"67 62 f3 7c 48 56 8c c8 78 56 34 12 12 \tvreduceph $0x12,0x12345678(%eax,%ecx,8),%zmm1",},
+{{0x62, 0xf3, 0x7c, 0x08, 0x56, 0xca, 0x12, }, 7, 0, "", "",
+"62 f3 7c 08 56 ca 12 \tvreduceph $0x12,%xmm2,%xmm1",},
+{{0x62, 0xf3, 0x7c, 0x08, 0x56, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "",
+"62 f3 7c 08 56 8c c8 78 56 34 12 12 \tvreduceph $0x12,0x12345678(%rax,%rcx,8),%xmm1",},
+{{0x67, 0x62, 0xf3, 0x7c, 0x08, 0x56, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 13, 0, "", "",
+"67 62 f3 7c 08 56 8c c8 78 56 34 12 12 \tvreduceph $0x12,0x12345678(%eax,%ecx,8),%xmm1",},
+{{0x62, 0xf3, 0x7c, 0x28, 0x56, 0xca, 0x12, }, 7, 0, "", "",
+"62 f3 7c 28 56 ca 12 \tvreduceph $0x12,%ymm2,%ymm1",},
+{{0x62, 0xf3, 0x7c, 0x28, 0x56, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "",
+"62 f3 7c 28 56 8c c8 78 56 34 12 12 \tvreduceph $0x12,0x12345678(%rax,%rcx,8),%ymm1",},
+{{0x67, 0x62, 0xf3, 0x7c, 0x28, 0x56, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 13, 0, "", "",
+"67 62 f3 7c 28 56 8c c8 78 56 34 12 12 \tvreduceph $0x12,0x12345678(%eax,%ecx,8),%ymm1",},
+{{0x62, 0xf3, 0x6c, 0x08, 0x57, 0xcb, 0x12, }, 7, 0, "", "",
+"62 f3 6c 08 57 cb 12 \tvreducesh $0x12,%xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf3, 0x6c, 0x08, 0x57, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "",
+"62 f3 6c 08 57 8c c8 78 56 34 12 12 \tvreducesh $0x12,0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf3, 0x6c, 0x08, 0x57, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 13, 0, "", "",
+"67 62 f3 6c 08 57 8c c8 78 56 34 12 12 \tvreducesh $0x12,0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf3, 0x7c, 0x48, 0x08, 0xca, 0x12, }, 7, 0, "", "",
+"62 f3 7c 48 08 ca 12 \tvrndscaleph $0x12,%zmm2,%zmm1",},
+{{0x62, 0xf3, 0x7c, 0x48, 0x08, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "",
+"62 f3 7c 48 08 8c c8 78 56 34 12 12 \tvrndscaleph $0x12,0x12345678(%rax,%rcx,8),%zmm1",},
+{{0x67, 0x62, 0xf3, 0x7c, 0x48, 0x08, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 13, 0, "", "",
+"67 62 f3 7c 48 08 8c c8 78 56 34 12 12 \tvrndscaleph $0x12,0x12345678(%eax,%ecx,8),%zmm1",},
+{{0x62, 0xf3, 0x7c, 0x08, 0x08, 0xca, 0x12, }, 7, 0, "", "",
+"62 f3 7c 08 08 ca 12 \tvrndscaleph $0x12,%xmm2,%xmm1",},
+{{0x62, 0xf3, 0x7c, 0x08, 0x08, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "",
+"62 f3 7c 08 08 8c c8 78 56 34 12 12 \tvrndscaleph $0x12,0x12345678(%rax,%rcx,8),%xmm1",},
+{{0x67, 0x62, 0xf3, 0x7c, 0x08, 0x08, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 13, 0, "", "",
+"67 62 f3 7c 08 08 8c c8 78 56 34 12 12 \tvrndscaleph $0x12,0x12345678(%eax,%ecx,8),%xmm1",},
+{{0x62, 0xf3, 0x7c, 0x28, 0x08, 0xca, 0x12, }, 7, 0, "", "",
+"62 f3 7c 28 08 ca 12 \tvrndscaleph $0x12,%ymm2,%ymm1",},
+{{0x62, 0xf3, 0x7c, 0x28, 0x08, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "",
+"62 f3 7c 28 08 8c c8 78 56 34 12 12 \tvrndscaleph $0x12,0x12345678(%rax,%rcx,8),%ymm1",},
+{{0x67, 0x62, 0xf3, 0x7c, 0x28, 0x08, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 13, 0, "", "",
+"67 62 f3 7c 28 08 8c c8 78 56 34 12 12 \tvrndscaleph $0x12,0x12345678(%eax,%ecx,8),%ymm1",},
+{{0x62, 0xf3, 0x6c, 0x08, 0x0a, 0xcb, 0x12, }, 7, 0, "", "",
+"62 f3 6c 08 0a cb 12 \tvrndscalesh $0x12,%xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf3, 0x6c, 0x08, 0x0a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "",
+"62 f3 6c 08 0a 8c c8 78 56 34 12 12 \tvrndscalesh $0x12,0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf3, 0x6c, 0x08, 0x0a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 13, 0, "", "",
+"67 62 f3 6c 08 0a 8c c8 78 56 34 12 12 \tvrndscalesh $0x12,0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x7d, 0x48, 0x4e, 0xca, }, 6, 0, "", "",
+"62 f6 7d 48 4e ca \tvrsqrtph %zmm2,%zmm1",},
+{{0x62, 0xf6, 0x7d, 0x48, 0x4e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 7d 48 4e 8c c8 78 56 34 12 \tvrsqrtph 0x12345678(%rax,%rcx,8),%zmm1",},
+{{0x67, 0x62, 0xf6, 0x7d, 0x48, 0x4e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 7d 48 4e 8c c8 78 56 34 12 \tvrsqrtph 0x12345678(%eax,%ecx,8),%zmm1",},
+{{0x62, 0xf6, 0x7d, 0x08, 0x4e, 0xca, }, 6, 0, "", "",
+"62 f6 7d 08 4e ca \tvrsqrtph %xmm2,%xmm1",},
+{{0x62, 0xf6, 0x7d, 0x08, 0x4e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 7d 08 4e 8c c8 78 56 34 12 \tvrsqrtph 0x12345678(%rax,%rcx,8),%xmm1",},
+{{0x67, 0x62, 0xf6, 0x7d, 0x08, 0x4e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 7d 08 4e 8c c8 78 56 34 12 \tvrsqrtph 0x12345678(%eax,%ecx,8),%xmm1",},
+{{0x62, 0xf6, 0x7d, 0x28, 0x4e, 0xca, }, 6, 0, "", "",
+"62 f6 7d 28 4e ca \tvrsqrtph %ymm2,%ymm1",},
+{{0x62, 0xf6, 0x7d, 0x28, 0x4e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 7d 28 4e 8c c8 78 56 34 12 \tvrsqrtph 0x12345678(%rax,%rcx,8),%ymm1",},
+{{0x67, 0x62, 0xf6, 0x7d, 0x28, 0x4e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 7d 28 4e 8c c8 78 56 34 12 \tvrsqrtph 0x12345678(%eax,%ecx,8),%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x4f, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 4f cb \tvrsqrtsh %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x4f, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 4f 8c c8 78 56 34 12 \tvrsqrtsh 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0x4f, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 08 4f 8c c8 78 56 34 12 \tvrsqrtsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0x2c, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 48 2c cb \tvscalefph %zmm3,%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x48, 0x2c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 48 2c 8c c8 78 56 34 12 \tvscalefph 0x12345678(%rax,%rcx,8),%zmm2,%zmm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x48, 0x2c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 48 2c 8c c8 78 56 34 12 \tvscalefph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x2c, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 2c cb \tvscalefph %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x2c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 2c 8c c8 78 56 34 12 \tvscalefph 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0x2c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 08 2c 8c c8 78 56 34 12 \tvscalefph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0x2c, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 28 2c cb \tvscalefph %ymm3,%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x28, 0x2c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 28 2c 8c c8 78 56 34 12 \tvscalefph 0x12345678(%rax,%rcx,8),%ymm2,%ymm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x28, 0x2c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 28 2c 8c c8 78 56 34 12 \tvscalefph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x2d, 0xcb, }, 6, 0, "", "",
+"62 f6 6d 08 2d cb \tvscalefsh %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf6, 0x6d, 0x08, 0x2d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f6 6d 08 2d 8c c8 78 56 34 12 \tvscalefsh 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0x2d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f6 6d 08 2d 8c c8 78 56 34 12 \tvscalefsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x7c, 0x48, 0x51, 0xca, }, 6, 0, "", "",
+"62 f5 7c 48 51 ca \tvsqrtph %zmm2,%zmm1",},
+{{0x62, 0xf5, 0x7c, 0x48, 0x51, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7c 48 51 8c c8 78 56 34 12 \tvsqrtph 0x12345678(%rax,%rcx,8),%zmm1",},
+{{0x67, 0x62, 0xf5, 0x7c, 0x48, 0x51, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7c 48 51 8c c8 78 56 34 12 \tvsqrtph 0x12345678(%eax,%ecx,8),%zmm1",},
+{{0x62, 0xf5, 0x7c, 0x08, 0x51, 0xca, }, 6, 0, "", "",
+"62 f5 7c 08 51 ca \tvsqrtph %xmm2,%xmm1",},
+{{0x62, 0xf5, 0x7c, 0x08, 0x51, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7c 08 51 8c c8 78 56 34 12 \tvsqrtph 0x12345678(%rax,%rcx,8),%xmm1",},
+{{0x67, 0x62, 0xf5, 0x7c, 0x08, 0x51, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7c 08 51 8c c8 78 56 34 12 \tvsqrtph 0x12345678(%eax,%ecx,8),%xmm1",},
+{{0x62, 0xf5, 0x7c, 0x28, 0x51, 0xca, }, 6, 0, "", "",
+"62 f5 7c 28 51 ca \tvsqrtph %ymm2,%ymm1",},
+{{0x62, 0xf5, 0x7c, 0x28, 0x51, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7c 28 51 8c c8 78 56 34 12 \tvsqrtph 0x12345678(%rax,%rcx,8),%ymm1",},
+{{0x67, 0x62, 0xf5, 0x7c, 0x28, 0x51, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7c 28 51 8c c8 78 56 34 12 \tvsqrtph 0x12345678(%eax,%ecx,8),%ymm1",},
+{{0x62, 0xf5, 0x6e, 0x08, 0x51, 0xcb, }, 6, 0, "", "",
+"62 f5 6e 08 51 cb \tvsqrtsh %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x6e, 0x08, 0x51, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6e 08 51 8c c8 78 56 34 12 \tvsqrtsh 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf5, 0x6e, 0x08, 0x51, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 6e 08 51 8c c8 78 56 34 12 \tvsqrtsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x6c, 0x48, 0x5c, 0xcb, }, 6, 0, "", "",
+"62 f5 6c 48 5c cb \tvsubph %zmm3,%zmm2,%zmm1",},
+{{0x62, 0xf5, 0x6c, 0x48, 0x5c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6c 48 5c 8c c8 78 56 34 12 \tvsubph 0x12345678(%rax,%rcx,8),%zmm2,%zmm1",},
+{{0x67, 0x62, 0xf5, 0x6c, 0x48, 0x5c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 6c 48 5c 8c c8 78 56 34 12 \tvsubph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",},
+{{0x62, 0xf5, 0x6c, 0x08, 0x5c, 0xcb, }, 6, 0, "", "",
+"62 f5 6c 08 5c cb \tvsubph %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x6c, 0x08, 0x5c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6c 08 5c 8c c8 78 56 34 12 \tvsubph 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf5, 0x6c, 0x08, 0x5c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 6c 08 5c 8c c8 78 56 34 12 \tvsubph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x6c, 0x28, 0x5c, 0xcb, }, 6, 0, "", "",
+"62 f5 6c 28 5c cb \tvsubph %ymm3,%ymm2,%ymm1",},
+{{0x62, 0xf5, 0x6c, 0x28, 0x5c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6c 28 5c 8c c8 78 56 34 12 \tvsubph 0x12345678(%rax,%rcx,8),%ymm2,%ymm1",},
+{{0x67, 0x62, 0xf5, 0x6c, 0x28, 0x5c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 6c 28 5c 8c c8 78 56 34 12 \tvsubph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",},
+{{0x62, 0xf5, 0x6e, 0x08, 0x5c, 0xcb, }, 6, 0, "", "",
+"62 f5 6e 08 5c cb \tvsubsh %xmm3,%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x6e, 0x08, 0x5c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 6e 08 5c 8c c8 78 56 34 12 \tvsubsh 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",},
+{{0x67, 0x62, 0xf5, 0x6e, 0x08, 0x5c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 6e 08 5c 8c c8 78 56 34 12 \tvsubsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",},
+{{0x62, 0xf5, 0x7c, 0x08, 0x2e, 0xca, }, 6, 0, "", "",
+"62 f5 7c 08 2e ca \tvucomish %xmm2,%xmm1",},
+{{0x62, 0xf5, 0x7c, 0x08, 0x2e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "",
+"62 f5 7c 08 2e 8c c8 78 56 34 12 \tvucomish 0x12345678(%rax,%rcx,8),%xmm1",},
+{{0x67, 0x62, 0xf5, 0x7c, 0x08, 0x2e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "",
+"67 62 f5 7c 08 2e 8c c8 78 56 34 12 \tvucomish 0x12345678(%eax,%ecx,8),%xmm1",},
+{{0xf3, 0x0f, 0x3a, 0xf0, 0xc0, 0x00, }, 6, 0, "", "",
+"f3 0f 3a f0 c0 00 \threset $0x0",},
+{{0x0f, 0x01, 0xe8, }, 3, 0, "", "",
+"0f 01 e8 \tserialize ",},
+{{0xf2, 0x0f, 0x01, 0xe9, }, 4, 0, "", "",
+"f2 0f 01 e9 \txresldtrk ",},
+{{0xf2, 0x0f, 0x01, 0xe8, }, 4, 0, "", "",
+"f2 0f 01 e8 \txsusldtrk ",},
{{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 c3808e94c46e..a391464c8dee 100644
--- a/tools/perf/arch/x86/tests/insn-x86-dat-src.c
+++ b/tools/perf/arch/x86/tests/insn-x86-dat-src.c
@@ -1910,6 +1910,724 @@ int main(void)
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 */
+ /* AMX */
+
+ asm volatile("ldtilecfg (%rax,%rcx,8)");
+ asm volatile("ldtilecfg (%r8,%rcx,8)");
+ asm volatile("sttilecfg (%rax,%rcx,8)");
+ asm volatile("sttilecfg (%r8,%rcx,8)");
+ asm volatile("tdpbf16ps %tmm0, %tmm1, %tmm2");
+ asm volatile("tdpbssd %tmm0, %tmm1, %tmm2");
+ asm volatile("tdpbsud %tmm0, %tmm1, %tmm2");
+ asm volatile("tdpbusd %tmm0, %tmm1, %tmm2");
+ asm volatile("tdpbuud %tmm0, %tmm1, %tmm2");
+ asm volatile("tileloadd (%rax,%rcx,8), %tmm1");
+ asm volatile("tileloadd (%r8,%rcx,8), %tmm2");
+ asm volatile("tileloaddt1 (%rax,%rcx,8), %tmm1");
+ asm volatile("tileloaddt1 (%r8,%rcx,8), %tmm2");
+ asm volatile("tilerelease");
+ asm volatile("tilestored %tmm1, (%rax,%rcx,8)");
+ asm volatile("tilestored %tmm2, (%r8,%rcx,8)");
+ asm volatile("tilezero %tmm0");
+ asm volatile("tilezero %tmm7");
+
+ /* User Interrupt */
+
+ asm volatile("clui");
+ asm volatile("senduipi %rax");
+ asm volatile("senduipi %r8");
+ asm volatile("stui");
+ asm volatile("testui");
+ asm volatile("uiret");
+
+ /* AVX512-FP16 */
+
+ asm volatile("vaddph %zmm3, %zmm2, %zmm1");
+ asm volatile("vaddph 0x12345678(%rax,%rcx,8), %zmm2, %zmm1");
+ asm volatile("vaddph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1");
+ asm volatile("vaddph %xmm3, %xmm2, %xmm1");
+ asm volatile("vaddph 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vaddph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vaddph %ymm3, %ymm2, %ymm1");
+ asm volatile("vaddph 0x12345678(%rax,%rcx,8), %ymm2, %ymm1");
+ asm volatile("vaddph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1");
+ asm volatile("vaddsh %xmm3, %xmm2, %xmm1");
+ asm volatile("vaddsh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vaddsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vcmpph $0x12, %zmm3, %zmm2, %k5");
+ asm volatile("vcmpph $0x12, 0x12345678(%rax,%rcx,8), %zmm2, %k5");
+ asm volatile("vcmpph $0x12, 0x12345678(%eax,%ecx,8), %zmm2, %k5");
+ asm volatile("vcmpph $0x12, %xmm3, %xmm2, %k5");
+ asm volatile("vcmpph $0x12, 0x12345678(%rax,%rcx,8), %xmm2, %k5");
+ asm volatile("vcmpph $0x12, 0x12345678(%eax,%ecx,8), %xmm2, %k5");
+ asm volatile("vcmpph $0x12, %ymm3, %ymm2, %k5");
+ asm volatile("vcmpph $0x12, 0x12345678(%rax,%rcx,8), %ymm2, %k5");
+ asm volatile("vcmpph $0x12, 0x12345678(%eax,%ecx,8), %ymm2, %k5");
+ asm volatile("vcmpsh $0x12, %xmm3, %xmm2, %k5");
+ asm volatile("vcmpsh $0x12, 0x12345678(%rax,%rcx,8), %xmm2, %k5");
+ asm volatile("vcmpsh $0x12, 0x12345678(%eax,%ecx,8), %xmm2, %k5");
+ asm volatile("vcomish %xmm2, %xmm1");
+ asm volatile("vcomish 0x12345678(%rax,%rcx,8), %xmm1");
+ asm volatile("vcomish 0x12345678(%eax,%ecx,8), %xmm1");
+ asm volatile("vcvtdq2ph %zmm2, %ymm1");
+ asm volatile("vcvtdq2ph 0x12345678(%rax,%rcx,8), %ymm1");
+ asm volatile("vcvtdq2ph 0x12345678(%eax,%ecx,8), %ymm1");
+ asm volatile("vcvtdq2ph %xmm2, %xmm1");
+ asm volatile("vcvtdq2ph %ymm2, %xmm1");
+ asm volatile("vcvtpd2ph %zmm2, %xmm1");
+ asm volatile("vcvtpd2ph %xmm2, %xmm1");
+ asm volatile("vcvtpd2ph %ymm2, %xmm1");
+ asm volatile("vcvtph2dq %ymm2, %zmm1");
+ asm volatile("vcvtph2dq 0x12345678(%rax,%rcx,8), %zmm1");
+ asm volatile("vcvtph2dq 0x12345678(%eax,%ecx,8), %zmm1");
+ asm volatile("vcvtph2dq %xmm2, %xmm1");
+ asm volatile("vcvtph2dq 0x12345678(%rax,%rcx,8), %xmm1");
+ asm volatile("vcvtph2dq 0x12345678(%eax,%ecx,8), %xmm1");
+ asm volatile("vcvtph2dq %xmm2, %ymm1");
+ asm volatile("vcvtph2dq 0x12345678(%rax,%rcx,8), %ymm1");
+ asm volatile("vcvtph2dq 0x12345678(%eax,%ecx,8), %ymm1");
+ asm volatile("vcvtph2pd %xmm2, %zmm1");
+ asm volatile("vcvtph2pd 0x12345678(%rax,%rcx,8), %zmm1");
+ asm volatile("vcvtph2pd 0x12345678(%eax,%ecx,8), %zmm1");
+ asm volatile("vcvtph2pd %xmm2, %xmm1");
+ asm volatile("vcvtph2pd 0x12345678(%rax,%rcx,8), %xmm1");
+ asm volatile("vcvtph2pd 0x12345678(%eax,%ecx,8), %xmm1");
+ asm volatile("vcvtph2pd %xmm2, %ymm1");
+ asm volatile("vcvtph2pd 0x12345678(%rax,%rcx,8), %ymm1");
+ asm volatile("vcvtph2pd 0x12345678(%eax,%ecx,8), %ymm1");
+ asm volatile("vcvtph2ps %ymm2, %zmm1");
+ asm volatile("vcvtph2ps 0x12345678(%rax,%rcx,8), %zmm1");
+ asm volatile("vcvtph2ps 0x12345678(%eax,%ecx,8), %zmm1");
+ asm volatile("vcvtph2ps %xmm2, %xmm1");
+ asm volatile("vcvtph2ps 0x12345678(%rax,%rcx,8), %xmm1");
+ asm volatile("vcvtph2ps 0x12345678(%eax,%ecx,8), %xmm1");
+ asm volatile("vcvtph2ps %xmm2, %ymm1");
+ asm volatile("vcvtph2ps 0x12345678(%rax,%rcx,8), %ymm1");
+ asm volatile("vcvtph2ps 0x12345678(%eax,%ecx,8), %ymm1");
+ asm volatile("vcvtph2ps %xmm2, %xmm1");
+ asm volatile("vcvtph2ps 0x12345678(%rax,%rcx,8), %xmm1");
+ asm volatile("vcvtph2ps 0x12345678(%eax,%ecx,8), %xmm1");
+ asm volatile("vcvtph2ps %xmm2, %ymm1");
+ asm volatile("vcvtph2ps 0x12345678(%rax,%rcx,8), %ymm1");
+ asm volatile("vcvtph2ps 0x12345678(%eax,%ecx,8), %ymm1");
+ asm volatile("vcvtph2psx %ymm2, %zmm1");
+ asm volatile("vcvtph2psx 0x12345678(%rax,%rcx,8), %zmm1");
+ asm volatile("vcvtph2psx 0x12345678(%eax,%ecx,8), %zmm1");
+ asm volatile("vcvtph2psx %xmm2, %xmm1");
+ asm volatile("vcvtph2psx 0x12345678(%rax,%rcx,8), %xmm1");
+ asm volatile("vcvtph2psx 0x12345678(%eax,%ecx,8), %xmm1");
+ asm volatile("vcvtph2psx %xmm2, %ymm1");
+ asm volatile("vcvtph2psx 0x12345678(%rax,%rcx,8), %ymm1");
+ asm volatile("vcvtph2psx 0x12345678(%eax,%ecx,8), %ymm1");
+ asm volatile("vcvtph2qq %xmm2, %zmm1");
+ asm volatile("vcvtph2qq 0x12345678(%rax,%rcx,8), %zmm1");
+ asm volatile("vcvtph2qq 0x12345678(%eax,%ecx,8), %zmm1");
+ asm volatile("vcvtph2qq %xmm2, %xmm1");
+ asm volatile("vcvtph2qq 0x12345678(%rax,%rcx,8), %xmm1");
+ asm volatile("vcvtph2qq 0x12345678(%eax,%ecx,8), %xmm1");
+ asm volatile("vcvtph2qq %xmm2, %ymm1");
+ asm volatile("vcvtph2qq 0x12345678(%rax,%rcx,8), %ymm1");
+ asm volatile("vcvtph2qq 0x12345678(%eax,%ecx,8), %ymm1");
+ asm volatile("vcvtph2udq %ymm2, %zmm1");
+ asm volatile("vcvtph2udq 0x12345678(%rax,%rcx,8), %zmm1");
+ asm volatile("vcvtph2udq 0x12345678(%eax,%ecx,8), %zmm1");
+ asm volatile("vcvtph2udq %xmm2, %xmm1");
+ asm volatile("vcvtph2udq 0x12345678(%rax,%rcx,8), %xmm1");
+ asm volatile("vcvtph2udq 0x12345678(%eax,%ecx,8), %xmm1");
+ asm volatile("vcvtph2udq %xmm2, %ymm1");
+ asm volatile("vcvtph2udq 0x12345678(%rax,%rcx,8), %ymm1");
+ asm volatile("vcvtph2udq 0x12345678(%eax,%ecx,8), %ymm1");
+ asm volatile("vcvtph2uqq %xmm2, %zmm1");
+ asm volatile("vcvtph2uqq 0x12345678(%rax,%rcx,8), %zmm1");
+ asm volatile("vcvtph2uqq 0x12345678(%eax,%ecx,8), %zmm1");
+ asm volatile("vcvtph2uqq %xmm2, %xmm1");
+ asm volatile("vcvtph2uqq 0x12345678(%rax,%rcx,8), %xmm1");
+ asm volatile("vcvtph2uqq 0x12345678(%eax,%ecx,8), %xmm1");
+ asm volatile("vcvtph2uqq %xmm2, %ymm1");
+ asm volatile("vcvtph2uqq 0x12345678(%rax,%rcx,8), %ymm1");
+ asm volatile("vcvtph2uqq 0x12345678(%eax,%ecx,8), %ymm1");
+ asm volatile("vcvtph2uw %zmm2, %zmm1");
+ asm volatile("vcvtph2uw 0x12345678(%rax,%rcx,8), %zmm1");
+ asm volatile("vcvtph2uw 0x12345678(%eax,%ecx,8), %zmm1");
+ asm volatile("vcvtph2uw %xmm2, %xmm1");
+ asm volatile("vcvtph2uw 0x12345678(%rax,%rcx,8), %xmm1");
+ asm volatile("vcvtph2uw 0x12345678(%eax,%ecx,8), %xmm1");
+ asm volatile("vcvtph2uw %ymm2, %ymm1");
+ asm volatile("vcvtph2uw 0x12345678(%rax,%rcx,8), %ymm1");
+ asm volatile("vcvtph2uw 0x12345678(%eax,%ecx,8), %ymm1");
+ asm volatile("vcvtph2w %zmm2, %zmm1");
+ asm volatile("vcvtph2w 0x12345678(%rax,%rcx,8), %zmm1");
+ asm volatile("vcvtph2w 0x12345678(%eax,%ecx,8), %zmm1");
+ asm volatile("vcvtph2w %xmm2, %xmm1");
+ asm volatile("vcvtph2w 0x12345678(%rax,%rcx,8), %xmm1");
+ asm volatile("vcvtph2w 0x12345678(%eax,%ecx,8), %xmm1");
+ asm volatile("vcvtph2w %ymm2, %ymm1");
+ asm volatile("vcvtph2w 0x12345678(%rax,%rcx,8), %ymm1");
+ asm volatile("vcvtph2w 0x12345678(%eax,%ecx,8), %ymm1");
+ asm volatile("vcvtps2ph $0x12, %zmm1, 0x12345678(%rax,%rcx,8)");
+ asm volatile("vcvtps2ph $0x12, %zmm1, 0x12345678(%eax,%ecx,8)");
+ asm volatile("vcvtps2ph $0x12, %zmm2, %ymm1");
+ asm volatile("vcvtps2ph $0x12, %ymm1, 0x12345678(%rax,%rcx,8)");
+ asm volatile("vcvtps2ph $0x12, %ymm1, 0x12345678(%eax,%ecx,8)");
+ asm volatile("vcvtps2ph $0x12, %xmm1, 0x12345678(%rax,%rcx,8)");
+ asm volatile("vcvtps2ph $0x12, %xmm1, 0x12345678(%eax,%ecx,8)");
+ asm volatile("vcvtps2ph $0x12, %xmm2, %xmm1");
+ asm volatile("vcvtps2ph $0x12, %ymm2, %xmm1");
+ asm volatile("vcvtps2ph $0x12, %ymm2, %xmm1");
+ asm volatile("vcvtps2ph $0x12, %ymm2, 0x12345678(%rax,%rcx,8)");
+ asm volatile("vcvtps2ph $0x12, %ymm2, 0x12345678(%eax,%ecx,8)");
+ asm volatile("vcvtps2ph $0x12, %xmm2, %xmm1");
+ asm volatile("vcvtps2ph $0x12, %xmm2, 0x12345678(%rax,%rcx,8)");
+ asm volatile("vcvtps2ph $0x12, %xmm2, 0x12345678(%eax,%ecx,8)");
+ asm volatile("vcvtps2phx %zmm2, %ymm1");
+ asm volatile("vcvtps2phx 0x12345678(%rax,%rcx,8), %ymm1");
+ asm volatile("vcvtps2phx 0x12345678(%eax,%ecx,8), %ymm1");
+ asm volatile("vcvtps2phx %xmm2, %xmm1");
+ asm volatile("vcvtps2phx %ymm2, %xmm1");
+ asm volatile("vcvtqq2ph %zmm2, %xmm1");
+ asm volatile("vcvtqq2ph %xmm2, %xmm1");
+ asm volatile("vcvtqq2ph %ymm2, %xmm1");
+ asm volatile("vcvtsd2sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vcvtsh2sd 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vcvtsh2si 0x12345678(%eax,%ecx,8), %eax");
+ asm volatile("vcvtsh2si 0x12345678(%eax,%ecx,8), %rax");
+ asm volatile("vcvtsh2ss 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vcvtsh2usi %xmm1, %eax");
+ asm volatile("vcvtsh2usi 0x12345678(%rax,%rcx,8), %eax");
+ asm volatile("vcvtsh2usi 0x12345678(%eax,%ecx,8), %eax");
+ asm volatile("vcvtsh2usi %xmm1, %rax");
+ asm volatile("vcvtsh2usi 0x12345678(%rax,%rcx,8), %rax");
+ asm volatile("vcvtsh2usi 0x12345678(%eax,%ecx,8), %rax");
+ asm volatile("vcvtsi2sh %eax, %xmm2, %xmm1");
+ asm volatile("vcvtsi2sh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vcvtsi2sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vcvtsi2sh %rax, %xmm2, %xmm1");
+ asm volatile("vcvtsi2sh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vcvtsi2sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vcvtss2sh %xmm3, %xmm2, %xmm1");
+ asm volatile("vcvtss2sh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vcvtss2sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vcvttph2dq %ymm2, %zmm1");
+ asm volatile("vcvttph2dq 0x12345678(%rax,%rcx,8), %zmm1");
+ asm volatile("vcvttph2dq 0x12345678(%eax,%ecx,8), %zmm1");
+ asm volatile("vcvttph2dq %xmm2, %xmm1");
+ asm volatile("vcvttph2dq 0x12345678(%rax,%rcx,8), %xmm1");
+ asm volatile("vcvttph2dq 0x12345678(%eax,%ecx,8), %xmm1");
+ asm volatile("vcvttph2dq %xmm2, %ymm1");
+ asm volatile("vcvttph2dq 0x12345678(%rax,%rcx,8), %ymm1");
+ asm volatile("vcvttph2dq 0x12345678(%eax,%ecx,8), %ymm1");
+ asm volatile("vcvttph2qq %xmm2, %zmm1");
+ asm volatile("vcvttph2qq 0x12345678(%rax,%rcx,8), %zmm1");
+ asm volatile("vcvttph2qq 0x12345678(%eax,%ecx,8), %zmm1");
+ asm volatile("vcvttph2qq %xmm2, %xmm1");
+ asm volatile("vcvttph2qq 0x12345678(%rax,%rcx,8), %xmm1");
+ asm volatile("vcvttph2qq 0x12345678(%eax,%ecx,8), %xmm1");
+ asm volatile("vcvttph2qq %xmm2, %ymm1");
+ asm volatile("vcvttph2qq 0x12345678(%rax,%rcx,8), %ymm1");
+ asm volatile("vcvttph2qq 0x12345678(%eax,%ecx,8), %ymm1");
+ asm volatile("vcvttph2udq %ymm2, %zmm1");
+ asm volatile("vcvttph2udq 0x12345678(%rax,%rcx,8), %zmm1");
+ asm volatile("vcvttph2udq 0x12345678(%eax,%ecx,8), %zmm1");
+ asm volatile("vcvttph2udq %xmm2, %xmm1");
+ asm volatile("vcvttph2udq 0x12345678(%rax,%rcx,8), %xmm1");
+ asm volatile("vcvttph2udq 0x12345678(%eax,%ecx,8), %xmm1");
+ asm volatile("vcvttph2udq %xmm2, %ymm1");
+ asm volatile("vcvttph2udq 0x12345678(%rax,%rcx,8), %ymm1");
+ asm volatile("vcvttph2udq 0x12345678(%eax,%ecx,8), %ymm1");
+ asm volatile("vcvttph2uqq %xmm2, %zmm1");
+ asm volatile("vcvttph2uqq 0x12345678(%rax,%rcx,8), %zmm1");
+ asm volatile("vcvttph2uqq 0x12345678(%eax,%ecx,8), %zmm1");
+ asm volatile("vcvttph2uqq %xmm2, %xmm1");
+ asm volatile("vcvttph2uqq 0x12345678(%rax,%rcx,8), %xmm1");
+ asm volatile("vcvttph2uqq 0x12345678(%eax,%ecx,8), %xmm1");
+ asm volatile("vcvttph2uqq %xmm2, %ymm1");
+ asm volatile("vcvttph2uqq 0x12345678(%rax,%rcx,8), %ymm1");
+ asm volatile("vcvttph2uqq 0x12345678(%eax,%ecx,8), %ymm1");
+ asm volatile("vcvttph2uw %zmm2, %zmm1");
+ asm volatile("vcvttph2uw 0x12345678(%rax,%rcx,8), %zmm1");
+ asm volatile("vcvttph2uw 0x12345678(%eax,%ecx,8), %zmm1");
+ asm volatile("vcvttph2uw %xmm2, %xmm1");
+ asm volatile("vcvttph2uw 0x12345678(%rax,%rcx,8), %xmm1");
+ asm volatile("vcvttph2uw 0x12345678(%eax,%ecx,8), %xmm1");
+ asm volatile("vcvttph2uw %ymm2, %ymm1");
+ asm volatile("vcvttph2uw 0x12345678(%rax,%rcx,8), %ymm1");
+ asm volatile("vcvttph2uw 0x12345678(%eax,%ecx,8), %ymm1");
+ asm volatile("vcvttph2w %zmm2, %zmm1");
+ asm volatile("vcvttph2w 0x12345678(%rax,%rcx,8), %zmm1");
+ asm volatile("vcvttph2w 0x12345678(%eax,%ecx,8), %zmm1");
+ asm volatile("vcvttph2w %xmm2, %xmm1");
+ asm volatile("vcvttph2w 0x12345678(%rax,%rcx,8), %xmm1");
+ asm volatile("vcvttph2w 0x12345678(%eax,%ecx,8), %xmm1");
+ asm volatile("vcvttph2w %ymm2, %ymm1");
+ asm volatile("vcvttph2w 0x12345678(%rax,%rcx,8), %ymm1");
+ asm volatile("vcvttph2w 0x12345678(%eax,%ecx,8), %ymm1");
+ asm volatile("vcvttsh2si %xmm1, %eax");
+ asm volatile("vcvttsh2si 0x12345678(%rax,%rcx,8), %eax");
+ asm volatile("vcvttsh2si 0x12345678(%eax,%ecx,8), %eax");
+ asm volatile("vcvttsh2si %xmm1, %rax");
+ asm volatile("vcvttsh2si 0x12345678(%rax,%rcx,8), %rax");
+ asm volatile("vcvttsh2si 0x12345678(%eax,%ecx,8), %rax");
+ asm volatile("vcvttsh2usi %xmm1, %eax");
+ asm volatile("vcvttsh2usi 0x12345678(%rax,%rcx,8), %eax");
+ asm volatile("vcvttsh2usi 0x12345678(%eax,%ecx,8), %eax");
+ asm volatile("vcvttsh2usi %xmm1, %rax");
+ asm volatile("vcvttsh2usi 0x12345678(%rax,%rcx,8), %rax");
+ asm volatile("vcvttsh2usi 0x12345678(%eax,%ecx,8), %rax");
+ asm volatile("vcvtudq2ph %zmm2, %ymm1");
+ asm volatile("vcvtudq2ph 0x12345678(%rax,%rcx,8), %ymm1");
+ asm volatile("vcvtudq2ph 0x12345678(%eax,%ecx,8), %ymm1");
+ asm volatile("vcvtudq2ph %xmm2, %xmm1");
+ asm volatile("vcvtudq2ph %ymm2, %xmm1");
+ asm volatile("vcvtuqq2ph %zmm2, %xmm1");
+ asm volatile("vcvtuqq2ph %xmm2, %xmm1");
+ asm volatile("vcvtuqq2ph %ymm2, %xmm1");
+ asm volatile("vcvtusi2sh %eax, %xmm2, %xmm1");
+ asm volatile("vcvtusi2sh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vcvtusi2sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vcvtusi2sh %rax, %xmm2, %xmm1");
+ asm volatile("vcvtusi2sh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vcvtusi2sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vcvtuw2ph %zmm2, %zmm1");
+ asm volatile("vcvtuw2ph 0x12345678(%rax,%rcx,8), %zmm1");
+ asm volatile("vcvtuw2ph 0x12345678(%eax,%ecx,8), %zmm1");
+ asm volatile("vcvtuw2ph %xmm2, %xmm1");
+ asm volatile("vcvtuw2ph 0x12345678(%rax,%rcx,8), %xmm1");
+ asm volatile("vcvtuw2ph 0x12345678(%eax,%ecx,8), %xmm1");
+ asm volatile("vcvtuw2ph %ymm2, %ymm1");
+ asm volatile("vcvtuw2ph 0x12345678(%rax,%rcx,8), %ymm1");
+ asm volatile("vcvtuw2ph 0x12345678(%eax,%ecx,8), %ymm1");
+ asm volatile("vcvtw2ph %zmm2, %zmm1");
+ asm volatile("vcvtw2ph 0x12345678(%rax,%rcx,8), %zmm1");
+ asm volatile("vcvtw2ph 0x12345678(%eax,%ecx,8), %zmm1");
+ asm volatile("vcvtw2ph %xmm2, %xmm1");
+ asm volatile("vcvtw2ph 0x12345678(%rax,%rcx,8), %xmm1");
+ asm volatile("vcvtw2ph 0x12345678(%eax,%ecx,8), %xmm1");
+ asm volatile("vcvtw2ph %ymm2, %ymm1");
+ asm volatile("vcvtw2ph 0x12345678(%rax,%rcx,8), %ymm1");
+ asm volatile("vcvtw2ph 0x12345678(%eax,%ecx,8), %ymm1");
+ asm volatile("vdivph %zmm3, %zmm2, %zmm1");
+ asm volatile("vdivph 0x12345678(%rax,%rcx,8), %zmm2, %zmm1");
+ asm volatile("vdivph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1");
+ asm volatile("vdivph %xmm3, %xmm2, %xmm1");
+ asm volatile("vdivph 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vdivph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vdivph %ymm3, %ymm2, %ymm1");
+ asm volatile("vdivph 0x12345678(%rax,%rcx,8), %ymm2, %ymm1");
+ asm volatile("vdivph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1");
+ asm volatile("vdivsh %xmm3, %xmm2, %xmm1");
+ asm volatile("vdivsh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vdivsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfcmaddcph %zmm3, %zmm2, %zmm1");
+ asm volatile("vfcmaddcph 0x12345678(%rax,%rcx,8), %zmm2, %zmm1");
+ asm volatile("vfcmaddcph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1");
+ asm volatile("vfcmaddcph %xmm3, %xmm2, %xmm1");
+ asm volatile("vfcmaddcph 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vfcmaddcph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfcmaddcph %ymm3, %ymm2, %ymm1");
+ asm volatile("vfcmaddcph 0x12345678(%rax,%rcx,8), %ymm2, %ymm1");
+ asm volatile("vfcmaddcph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1");
+ asm volatile("vfcmaddcsh %xmm3, %xmm2, %xmm1");
+ asm volatile("vfcmaddcsh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vfcmaddcsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfcmulcph %zmm3, %zmm2, %zmm1");
+ asm volatile("vfcmulcph 0x12345678(%rax,%rcx,8), %zmm2, %zmm1");
+ asm volatile("vfcmulcph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1");
+ asm volatile("vfcmulcph %xmm3, %xmm2, %xmm1");
+ asm volatile("vfcmulcph 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vfcmulcph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfcmulcph %ymm3, %ymm2, %ymm1");
+ asm volatile("vfcmulcph 0x12345678(%rax,%rcx,8), %ymm2, %ymm1");
+ asm volatile("vfcmulcph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1");
+ asm volatile("vfcmulcsh %xmm3, %xmm2, %xmm1");
+ asm volatile("vfcmulcsh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vfcmulcsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfmadd132ph %zmm3, %zmm2, %zmm1");
+ asm volatile("vfmadd132ph 0x12345678(%rax,%rcx,8), %zmm2, %zmm1");
+ asm volatile("vfmadd132ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1");
+ asm volatile("vfmadd132ph %xmm3, %xmm2, %xmm1");
+ asm volatile("vfmadd132ph 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vfmadd132ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfmadd132ph %ymm3, %ymm2, %ymm1");
+ asm volatile("vfmadd132ph 0x12345678(%rax,%rcx,8), %ymm2, %ymm1");
+ asm volatile("vfmadd132ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1");
+ asm volatile("vfmadd132sh %xmm3, %xmm2, %xmm1");
+ asm volatile("vfmadd132sh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vfmadd132sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfmadd213ph %zmm3, %zmm2, %zmm1");
+ asm volatile("vfmadd213ph 0x12345678(%rax,%rcx,8), %zmm2, %zmm1");
+ asm volatile("vfmadd213ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1");
+ asm volatile("vfmadd213ph %xmm3, %xmm2, %xmm1");
+ asm volatile("vfmadd213ph 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vfmadd213ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfmadd213ph %ymm3, %ymm2, %ymm1");
+ asm volatile("vfmadd213ph 0x12345678(%rax,%rcx,8), %ymm2, %ymm1");
+ asm volatile("vfmadd213ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1");
+ asm volatile("vfmadd213sh %xmm3, %xmm2, %xmm1");
+ asm volatile("vfmadd213sh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vfmadd213sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfmadd231ph %zmm3, %zmm2, %zmm1");
+ asm volatile("vfmadd231ph 0x12345678(%rax,%rcx,8), %zmm2, %zmm1");
+ asm volatile("vfmadd231ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1");
+ asm volatile("vfmadd231ph %xmm3, %xmm2, %xmm1");
+ asm volatile("vfmadd231ph 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vfmadd231ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfmadd231ph %ymm3, %ymm2, %ymm1");
+ asm volatile("vfmadd231ph 0x12345678(%rax,%rcx,8), %ymm2, %ymm1");
+ asm volatile("vfmadd231ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1");
+ asm volatile("vfmadd231sh %xmm3, %xmm2, %xmm1");
+ asm volatile("vfmadd231sh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vfmadd231sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfmaddcph %zmm3, %zmm2, %zmm1");
+ asm volatile("vfmaddcph 0x12345678(%rax,%rcx,8), %zmm2, %zmm1");
+ asm volatile("vfmaddcph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1");
+ asm volatile("vfmaddcph %xmm3, %xmm2, %xmm1");
+ asm volatile("vfmaddcph 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vfmaddcph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfmaddcph %ymm3, %ymm2, %ymm1");
+ asm volatile("vfmaddcph 0x12345678(%rax,%rcx,8), %ymm2, %ymm1");
+ asm volatile("vfmaddcph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1");
+ asm volatile("vfmaddcsh %xmm3, %xmm2, %xmm1");
+ asm volatile("vfmaddcsh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vfmaddcsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfmaddsub132ph %zmm3, %zmm2, %zmm1");
+ asm volatile("vfmaddsub132ph 0x12345678(%rax,%rcx,8), %zmm2, %zmm1");
+ asm volatile("vfmaddsub132ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1");
+ asm volatile("vfmaddsub132ph %xmm3, %xmm2, %xmm1");
+ asm volatile("vfmaddsub132ph 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vfmaddsub132ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfmaddsub132ph %ymm3, %ymm2, %ymm1");
+ asm volatile("vfmaddsub132ph 0x12345678(%rax,%rcx,8), %ymm2, %ymm1");
+ asm volatile("vfmaddsub132ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1");
+ asm volatile("vfmaddsub213ph %zmm3, %zmm2, %zmm1");
+ asm volatile("vfmaddsub213ph 0x12345678(%rax,%rcx,8), %zmm2, %zmm1");
+ asm volatile("vfmaddsub213ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1");
+ asm volatile("vfmaddsub213ph %xmm3, %xmm2, %xmm1");
+ asm volatile("vfmaddsub213ph 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vfmaddsub213ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfmaddsub213ph %ymm3, %ymm2, %ymm1");
+ asm volatile("vfmaddsub213ph 0x12345678(%rax,%rcx,8), %ymm2, %ymm1");
+ asm volatile("vfmaddsub213ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1");
+ asm volatile("vfmaddsub231ph %zmm3, %zmm2, %zmm1");
+ asm volatile("vfmaddsub231ph 0x12345678(%rax,%rcx,8), %zmm2, %zmm1");
+ asm volatile("vfmaddsub231ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1");
+ asm volatile("vfmaddsub231ph %xmm3, %xmm2, %xmm1");
+ asm volatile("vfmaddsub231ph 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vfmaddsub231ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfmaddsub231ph %ymm3, %ymm2, %ymm1");
+ asm volatile("vfmaddsub231ph 0x12345678(%rax,%rcx,8), %ymm2, %ymm1");
+ asm volatile("vfmaddsub231ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1");
+ asm volatile("vfmsub132ph %zmm3, %zmm2, %zmm1");
+ asm volatile("vfmsub132ph 0x12345678(%rax,%rcx,8), %zmm2, %zmm1");
+ asm volatile("vfmsub132ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1");
+ asm volatile("vfmsub132ph %xmm3, %xmm2, %xmm1");
+ asm volatile("vfmsub132ph 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vfmsub132ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfmsub132ph %ymm3, %ymm2, %ymm1");
+ asm volatile("vfmsub132ph 0x12345678(%rax,%rcx,8), %ymm2, %ymm1");
+ asm volatile("vfmsub132ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1");
+ asm volatile("vfmsub132sh %xmm3, %xmm2, %xmm1");
+ asm volatile("vfmsub132sh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vfmsub132sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfmsub213ph %zmm3, %zmm2, %zmm1");
+ asm volatile("vfmsub213ph 0x12345678(%rax,%rcx,8), %zmm2, %zmm1");
+ asm volatile("vfmsub213ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1");
+ asm volatile("vfmsub213ph %xmm3, %xmm2, %xmm1");
+ asm volatile("vfmsub213ph 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vfmsub213ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfmsub213ph %ymm3, %ymm2, %ymm1");
+ asm volatile("vfmsub213ph 0x12345678(%rax,%rcx,8), %ymm2, %ymm1");
+ asm volatile("vfmsub213ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1");
+ asm volatile("vfmsub213sh %xmm3, %xmm2, %xmm1");
+ asm volatile("vfmsub213sh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vfmsub213sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfmsub231ph %zmm3, %zmm2, %zmm1");
+ asm volatile("vfmsub231ph 0x12345678(%rax,%rcx,8), %zmm2, %zmm1");
+ asm volatile("vfmsub231ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1");
+ asm volatile("vfmsub231ph %xmm3, %xmm2, %xmm1");
+ asm volatile("vfmsub231ph 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vfmsub231ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfmsub231ph %ymm3, %ymm2, %ymm1");
+ asm volatile("vfmsub231ph 0x12345678(%rax,%rcx,8), %ymm2, %ymm1");
+ asm volatile("vfmsub231ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1");
+ asm volatile("vfmsub231sh %xmm3, %xmm2, %xmm1");
+ asm volatile("vfmsub231sh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vfmsub231sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfmsubadd132ph %zmm3, %zmm2, %zmm1");
+ asm volatile("vfmsubadd132ph 0x12345678(%rax,%rcx,8), %zmm2, %zmm1");
+ asm volatile("vfmsubadd132ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1");
+ asm volatile("vfmsubadd132ph %xmm3, %xmm2, %xmm1");
+ asm volatile("vfmsubadd132ph 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vfmsubadd132ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfmsubadd132ph %ymm3, %ymm2, %ymm1");
+ asm volatile("vfmsubadd132ph 0x12345678(%rax,%rcx,8), %ymm2, %ymm1");
+ asm volatile("vfmsubadd132ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1");
+ asm volatile("vfmsubadd213ph %zmm3, %zmm2, %zmm1");
+ asm volatile("vfmsubadd213ph 0x12345678(%rax,%rcx,8), %zmm2, %zmm1");
+ asm volatile("vfmsubadd213ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1");
+ asm volatile("vfmsubadd213ph %xmm3, %xmm2, %xmm1");
+ asm volatile("vfmsubadd213ph 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vfmsubadd213ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfmsubadd213ph %ymm3, %ymm2, %ymm1");
+ asm volatile("vfmsubadd213ph 0x12345678(%rax,%rcx,8), %ymm2, %ymm1");
+ asm volatile("vfmsubadd213ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1");
+ asm volatile("vfmsubadd231ph %zmm3, %zmm2, %zmm1");
+ asm volatile("vfmsubadd231ph 0x12345678(%rax,%rcx,8), %zmm2, %zmm1");
+ asm volatile("vfmsubadd231ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1");
+ asm volatile("vfmsubadd231ph %xmm3, %xmm2, %xmm1");
+ asm volatile("vfmsubadd231ph 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vfmsubadd231ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfmsubadd231ph %ymm3, %ymm2, %ymm1");
+ asm volatile("vfmsubadd231ph 0x12345678(%rax,%rcx,8), %ymm2, %ymm1");
+ asm volatile("vfmsubadd231ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1");
+ asm volatile("vfmulcph %zmm3, %zmm2, %zmm1");
+ asm volatile("vfmulcph 0x12345678(%rax,%rcx,8), %zmm2, %zmm1");
+ asm volatile("vfmulcph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1");
+ asm volatile("vfmulcph %xmm3, %xmm2, %xmm1");
+ asm volatile("vfmulcph 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vfmulcph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfmulcph %ymm3, %ymm2, %ymm1");
+ asm volatile("vfmulcph 0x12345678(%rax,%rcx,8), %ymm2, %ymm1");
+ asm volatile("vfmulcph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1");
+ asm volatile("vfmulcsh %xmm3, %xmm2, %xmm1");
+ asm volatile("vfmulcsh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vfmulcsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfnmadd132ph %zmm3, %zmm2, %zmm1");
+ asm volatile("vfnmadd132ph 0x12345678(%rax,%rcx,8), %zmm2, %zmm1");
+ asm volatile("vfnmadd132ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1");
+ asm volatile("vfnmadd132ph %xmm3, %xmm2, %xmm1");
+ asm volatile("vfnmadd132ph 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vfnmadd132ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfnmadd132ph %ymm3, %ymm2, %ymm1");
+ asm volatile("vfnmadd132ph 0x12345678(%rax,%rcx,8), %ymm2, %ymm1");
+ asm volatile("vfnmadd132ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1");
+ asm volatile("vfnmadd132sh %xmm3, %xmm2, %xmm1");
+ asm volatile("vfnmadd132sh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vfnmadd132sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfnmadd213ph %zmm3, %zmm2, %zmm1");
+ asm volatile("vfnmadd213ph 0x12345678(%rax,%rcx,8), %zmm2, %zmm1");
+ asm volatile("vfnmadd213ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1");
+ asm volatile("vfnmadd213ph %xmm3, %xmm2, %xmm1");
+ asm volatile("vfnmadd213ph 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vfnmadd213ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfnmadd213ph %ymm3, %ymm2, %ymm1");
+ asm volatile("vfnmadd213ph 0x12345678(%rax,%rcx,8), %ymm2, %ymm1");
+ asm volatile("vfnmadd213ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1");
+ asm volatile("vfnmadd213sh %xmm3, %xmm2, %xmm1");
+ asm volatile("vfnmadd213sh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vfnmadd213sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfnmadd231ph %zmm3, %zmm2, %zmm1");
+ asm volatile("vfnmadd231ph 0x12345678(%rax,%rcx,8), %zmm2, %zmm1");
+ asm volatile("vfnmadd231ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1");
+ asm volatile("vfnmadd231ph %xmm3, %xmm2, %xmm1");
+ asm volatile("vfnmadd231ph 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vfnmadd231ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfnmadd231ph %ymm3, %ymm2, %ymm1");
+ asm volatile("vfnmadd231ph 0x12345678(%rax,%rcx,8), %ymm2, %ymm1");
+ asm volatile("vfnmadd231ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1");
+ asm volatile("vfnmadd231sh %xmm3, %xmm2, %xmm1");
+ asm volatile("vfnmadd231sh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vfnmadd231sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfnmsub132ph %zmm3, %zmm2, %zmm1");
+ asm volatile("vfnmsub132ph 0x12345678(%rax,%rcx,8), %zmm2, %zmm1");
+ asm volatile("vfnmsub132ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1");
+ asm volatile("vfnmsub132ph %xmm3, %xmm2, %xmm1");
+ asm volatile("vfnmsub132ph 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vfnmsub132ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfnmsub132ph %ymm3, %ymm2, %ymm1");
+ asm volatile("vfnmsub132ph 0x12345678(%rax,%rcx,8), %ymm2, %ymm1");
+ asm volatile("vfnmsub132ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1");
+ asm volatile("vfnmsub132sh %xmm3, %xmm2, %xmm1");
+ asm volatile("vfnmsub132sh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vfnmsub132sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfnmsub213ph %zmm3, %zmm2, %zmm1");
+ asm volatile("vfnmsub213ph 0x12345678(%rax,%rcx,8), %zmm2, %zmm1");
+ asm volatile("vfnmsub213ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1");
+ asm volatile("vfnmsub213ph %xmm3, %xmm2, %xmm1");
+ asm volatile("vfnmsub213ph 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vfnmsub213ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfnmsub213ph %ymm3, %ymm2, %ymm1");
+ asm volatile("vfnmsub213ph 0x12345678(%rax,%rcx,8), %ymm2, %ymm1");
+ asm volatile("vfnmsub213ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1");
+ asm volatile("vfnmsub213sh %xmm3, %xmm2, %xmm1");
+ asm volatile("vfnmsub213sh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vfnmsub213sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfnmsub231ph %zmm3, %zmm2, %zmm1");
+ asm volatile("vfnmsub231ph 0x12345678(%rax,%rcx,8), %zmm2, %zmm1");
+ asm volatile("vfnmsub231ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1");
+ asm volatile("vfnmsub231ph %xmm3, %xmm2, %xmm1");
+ asm volatile("vfnmsub231ph 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vfnmsub231ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfnmsub231ph %ymm3, %ymm2, %ymm1");
+ asm volatile("vfnmsub231ph 0x12345678(%rax,%rcx,8), %ymm2, %ymm1");
+ asm volatile("vfnmsub231ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1");
+ asm volatile("vfnmsub231sh %xmm3, %xmm2, %xmm1");
+ asm volatile("vfnmsub231sh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vfnmsub231sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfpclassph $0x12, %zmm1, %k5");
+ asm volatile("vfpclassph $0x12, %xmm1, %k5");
+ asm volatile("vfpclassph $0x12, %ymm1, %k5");
+ asm volatile("vfpclasssh $0x12, %xmm1, %k5");
+ asm volatile("vfpclasssh $0x12, 0x12345678(%rax,%rcx,8), %k5");
+ asm volatile("vfpclasssh $0x12, 0x12345678(%eax,%ecx,8), %k5");
+ asm volatile("vgetexpph %zmm2, %zmm1");
+ asm volatile("vgetexpph 0x12345678(%rax,%rcx,8), %zmm1");
+ asm volatile("vgetexpph 0x12345678(%eax,%ecx,8), %zmm1");
+ asm volatile("vgetexpph %xmm2, %xmm1");
+ asm volatile("vgetexpph 0x12345678(%rax,%rcx,8), %xmm1");
+ asm volatile("vgetexpph 0x12345678(%eax,%ecx,8), %xmm1");
+ asm volatile("vgetexpph %ymm2, %ymm1");
+ asm volatile("vgetexpph 0x12345678(%rax,%rcx,8), %ymm1");
+ asm volatile("vgetexpph 0x12345678(%eax,%ecx,8), %ymm1");
+ asm volatile("vgetexpsh %xmm3, %xmm2, %xmm1");
+ asm volatile("vgetexpsh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vgetexpsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vgetmantph $0x12, %zmm2, %zmm1");
+ asm volatile("vgetmantph $0x12, 0x12345678(%rax,%rcx,8), %zmm1");
+ asm volatile("vgetmantph $0x12, 0x12345678(%eax,%ecx,8), %zmm1");
+ asm volatile("vgetmantph $0x12, %xmm2, %xmm1");
+ asm volatile("vgetmantph $0x12, 0x12345678(%rax,%rcx,8), %xmm1");
+ asm volatile("vgetmantph $0x12, 0x12345678(%eax,%ecx,8), %xmm1");
+ asm volatile("vgetmantph $0x12, %ymm2, %ymm1");
+ asm volatile("vgetmantph $0x12, 0x12345678(%rax,%rcx,8), %ymm1");
+ asm volatile("vgetmantph $0x12, 0x12345678(%eax,%ecx,8), %ymm1");
+ asm volatile("vgetmantsh $0x12, %xmm3, %xmm2, %xmm1");
+ asm volatile("vgetmantsh $0x12, 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vgetmantsh $0x12, 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vmaxph %zmm3, %zmm2, %zmm1");
+ asm volatile("vmaxph 0x12345678(%rax,%rcx,8), %zmm2, %zmm1");
+ asm volatile("vmaxph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1");
+ asm volatile("vmaxph %xmm3, %xmm2, %xmm1");
+ asm volatile("vmaxph 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vmaxph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vmaxph %ymm3, %ymm2, %ymm1");
+ asm volatile("vmaxph 0x12345678(%rax,%rcx,8), %ymm2, %ymm1");
+ asm volatile("vmaxph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1");
+ asm volatile("vmaxsh %xmm3, %xmm2, %xmm1");
+ asm volatile("vmaxsh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vmaxsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vminph %zmm3, %zmm2, %zmm1");
+ asm volatile("vminph 0x12345678(%rax,%rcx,8), %zmm2, %zmm1");
+ asm volatile("vminph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1");
+ asm volatile("vminph %xmm3, %xmm2, %xmm1");
+ asm volatile("vminph 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vminph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vminph %ymm3, %ymm2, %ymm1");
+ asm volatile("vminph 0x12345678(%rax,%rcx,8), %ymm2, %ymm1");
+ asm volatile("vminph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1");
+ asm volatile("vminsh %xmm3, %xmm2, %xmm1");
+ asm volatile("vminsh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vminsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vmovsh %xmm1, 0x12345678(%rax,%rcx,8)");
+ asm volatile("vmovsh %xmm1, 0x12345678(%eax,%ecx,8)");
+ asm volatile("vmovsh 0x12345678(%rax,%rcx,8), %xmm1");
+ asm volatile("vmovsh 0x12345678(%eax,%ecx,8), %xmm1");
+ asm volatile("vmovsh %xmm3, %xmm2, %xmm1");
+ asm volatile("vmovw %xmm1, %eax");
+ asm volatile("vmovw %xmm1, 0x12345678(%rax,%rcx,8)");
+ asm volatile("vmovw %xmm1, 0x12345678(%eax,%ecx,8)");
+ asm volatile("vmovw %eax, %xmm1");
+ asm volatile("vmovw 0x12345678(%rax,%rcx,8), %xmm1");
+ asm volatile("vmovw 0x12345678(%eax,%ecx,8), %xmm1");
+ asm volatile("vmulph %zmm3, %zmm2, %zmm1");
+ asm volatile("vmulph 0x12345678(%rax,%rcx,8), %zmm2, %zmm1");
+ asm volatile("vmulph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1");
+ asm volatile("vmulph %xmm3, %xmm2, %xmm1");
+ asm volatile("vmulph 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vmulph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vmulph %ymm3, %ymm2, %ymm1");
+ asm volatile("vmulph 0x12345678(%rax,%rcx,8), %ymm2, %ymm1");
+ asm volatile("vmulph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1");
+ asm volatile("vmulsh %xmm3, %xmm2, %xmm1");
+ asm volatile("vmulsh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vmulsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vrcpph %zmm2, %zmm1");
+ asm volatile("vrcpph 0x12345678(%rax,%rcx,8), %zmm1");
+ asm volatile("vrcpph 0x12345678(%eax,%ecx,8), %zmm1");
+ asm volatile("vrcpph %xmm2, %xmm1");
+ asm volatile("vrcpph 0x12345678(%rax,%rcx,8), %xmm1");
+ asm volatile("vrcpph 0x12345678(%eax,%ecx,8), %xmm1");
+ asm volatile("vrcpph %ymm2, %ymm1");
+ asm volatile("vrcpph 0x12345678(%rax,%rcx,8), %ymm1");
+ asm volatile("vrcpph 0x12345678(%eax,%ecx,8), %ymm1");
+ asm volatile("vrcpsh %xmm3, %xmm2, %xmm1");
+ asm volatile("vrcpsh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vrcpsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vreduceph $0x12, %zmm2, %zmm1");
+ asm volatile("vreduceph $0x12, 0x12345678(%rax,%rcx,8), %zmm1");
+ asm volatile("vreduceph $0x12, 0x12345678(%eax,%ecx,8), %zmm1");
+ asm volatile("vreduceph $0x12, %xmm2, %xmm1");
+ asm volatile("vreduceph $0x12, 0x12345678(%rax,%rcx,8), %xmm1");
+ asm volatile("vreduceph $0x12, 0x12345678(%eax,%ecx,8), %xmm1");
+ asm volatile("vreduceph $0x12, %ymm2, %ymm1");
+ asm volatile("vreduceph $0x12, 0x12345678(%rax,%rcx,8), %ymm1");
+ asm volatile("vreduceph $0x12, 0x12345678(%eax,%ecx,8), %ymm1");
+ asm volatile("vreducesh $0x12, %xmm3, %xmm2, %xmm1");
+ asm volatile("vreducesh $0x12, 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vreducesh $0x12, 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vrndscaleph $0x12, %zmm2, %zmm1");
+ asm volatile("vrndscaleph $0x12, 0x12345678(%rax,%rcx,8), %zmm1");
+ asm volatile("vrndscaleph $0x12, 0x12345678(%eax,%ecx,8), %zmm1");
+ asm volatile("vrndscaleph $0x12, %xmm2, %xmm1");
+ asm volatile("vrndscaleph $0x12, 0x12345678(%rax,%rcx,8), %xmm1");
+ asm volatile("vrndscaleph $0x12, 0x12345678(%eax,%ecx,8), %xmm1");
+ asm volatile("vrndscaleph $0x12, %ymm2, %ymm1");
+ asm volatile("vrndscaleph $0x12, 0x12345678(%rax,%rcx,8), %ymm1");
+ asm volatile("vrndscaleph $0x12, 0x12345678(%eax,%ecx,8), %ymm1");
+ asm volatile("vrndscalesh $0x12, %xmm3, %xmm2, %xmm1");
+ asm volatile("vrndscalesh $0x12, 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vrndscalesh $0x12, 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vrsqrtph %zmm2, %zmm1");
+ asm volatile("vrsqrtph 0x12345678(%rax,%rcx,8), %zmm1");
+ asm volatile("vrsqrtph 0x12345678(%eax,%ecx,8), %zmm1");
+ asm volatile("vrsqrtph %xmm2, %xmm1");
+ asm volatile("vrsqrtph 0x12345678(%rax,%rcx,8), %xmm1");
+ asm volatile("vrsqrtph 0x12345678(%eax,%ecx,8), %xmm1");
+ asm volatile("vrsqrtph %ymm2, %ymm1");
+ asm volatile("vrsqrtph 0x12345678(%rax,%rcx,8), %ymm1");
+ asm volatile("vrsqrtph 0x12345678(%eax,%ecx,8), %ymm1");
+ asm volatile("vrsqrtsh %xmm3, %xmm2, %xmm1");
+ asm volatile("vrsqrtsh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vrsqrtsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vscalefph %zmm3, %zmm2, %zmm1");
+ asm volatile("vscalefph 0x12345678(%rax,%rcx,8), %zmm2, %zmm1");
+ asm volatile("vscalefph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1");
+ asm volatile("vscalefph %xmm3, %xmm2, %xmm1");
+ asm volatile("vscalefph 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vscalefph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vscalefph %ymm3, %ymm2, %ymm1");
+ asm volatile("vscalefph 0x12345678(%rax,%rcx,8), %ymm2, %ymm1");
+ asm volatile("vscalefph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1");
+ asm volatile("vscalefsh %xmm3, %xmm2, %xmm1");
+ asm volatile("vscalefsh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vscalefsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vsqrtph %zmm2, %zmm1");
+ asm volatile("vsqrtph 0x12345678(%rax,%rcx,8), %zmm1");
+ asm volatile("vsqrtph 0x12345678(%eax,%ecx,8), %zmm1");
+ asm volatile("vsqrtph %xmm2, %xmm1");
+ asm volatile("vsqrtph 0x12345678(%rax,%rcx,8), %xmm1");
+ asm volatile("vsqrtph 0x12345678(%eax,%ecx,8), %xmm1");
+ asm volatile("vsqrtph %ymm2, %ymm1");
+ asm volatile("vsqrtph 0x12345678(%rax,%rcx,8), %ymm1");
+ asm volatile("vsqrtph 0x12345678(%eax,%ecx,8), %ymm1");
+ asm volatile("vsqrtsh %xmm3, %xmm2, %xmm1");
+ asm volatile("vsqrtsh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vsqrtsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vsubph %zmm3, %zmm2, %zmm1");
+ asm volatile("vsubph 0x12345678(%rax,%rcx,8), %zmm2, %zmm1");
+ asm volatile("vsubph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1");
+ asm volatile("vsubph %xmm3, %xmm2, %xmm1");
+ asm volatile("vsubph 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vsubph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vsubph %ymm3, %ymm2, %ymm1");
+ asm volatile("vsubph 0x12345678(%rax,%rcx,8), %ymm2, %ymm1");
+ asm volatile("vsubph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1");
+ asm volatile("vsubsh %xmm3, %xmm2, %xmm1");
+ asm volatile("vsubsh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1");
+ asm volatile("vsubsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vucomish %xmm2, %xmm1");
+ asm volatile("vucomish 0x12345678(%rax,%rcx,8), %xmm1");
+ asm volatile("vucomish 0x12345678(%eax,%ecx,8), %xmm1");
+
#else /* #ifdef __x86_64__ */
/* bound r32, mem (same op code as EVEX prefix) */
@@ -3670,8 +4388,479 @@ int main(void)
asm volatile("notrack bnd jmp *(0x12345678)"); /* Expecting: jmp indirect 0 */
asm volatile("notrack bnd jmp *0x12345678(%eax,%ecx,8)"); /* Expecting: jmp indirect 0 */
+ /* AVX512-FP16 */
+
+ asm volatile("vaddph %zmm3, %zmm2, %zmm1");
+ asm volatile("vaddph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1");
+ asm volatile("vaddph %xmm3, %xmm2, %xmm1");
+ asm volatile("vaddph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vaddph %ymm3, %ymm2, %ymm1");
+ asm volatile("vaddph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1");
+ asm volatile("vaddsh %xmm3, %xmm2, %xmm1");
+ asm volatile("vaddsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vcmpph $0x12, %zmm3, %zmm2, %k5");
+ asm volatile("vcmpph $0x12, 0x12345678(%eax,%ecx,8), %zmm2, %k5");
+ asm volatile("vcmpph $0x12, %xmm3, %xmm2, %k5");
+ asm volatile("vcmpph $0x12, 0x12345678(%eax,%ecx,8), %xmm2, %k5");
+ asm volatile("vcmpph $0x12, %ymm3, %ymm2, %k5");
+ asm volatile("vcmpph $0x12, 0x12345678(%eax,%ecx,8), %ymm2, %k5");
+ asm volatile("vcmpsh $0x12, %xmm3, %xmm2, %k5");
+ asm volatile("vcmpsh $0x12, 0x12345678(%eax,%ecx,8), %xmm2, %k5");
+ asm volatile("vcomish %xmm2, %xmm1");
+ asm volatile("vcomish 0x12345678(%eax,%ecx,8), %xmm1");
+ asm volatile("vcvtdq2ph %zmm2, %ymm1");
+ asm volatile("vcvtdq2ph 0x12345678(%eax,%ecx,8), %ymm1");
+ asm volatile("vcvtdq2ph %xmm2, %xmm1");
+ asm volatile("vcvtdq2ph %ymm2, %xmm1");
+ asm volatile("vcvtpd2ph %zmm2, %xmm1");
+ asm volatile("vcvtpd2ph %xmm2, %xmm1");
+ asm volatile("vcvtpd2ph %ymm2, %xmm1");
+ asm volatile("vcvtph2dq %ymm2, %zmm1");
+ asm volatile("vcvtph2dq 0x12345678(%eax,%ecx,8), %zmm1");
+ asm volatile("vcvtph2dq %xmm2, %xmm1");
+ asm volatile("vcvtph2dq 0x12345678(%eax,%ecx,8), %xmm1");
+ asm volatile("vcvtph2dq %xmm2, %ymm1");
+ asm volatile("vcvtph2dq 0x12345678(%eax,%ecx,8), %ymm1");
+ asm volatile("vcvtph2pd %xmm2, %zmm1");
+ asm volatile("vcvtph2pd 0x12345678(%eax,%ecx,8), %zmm1");
+ asm volatile("vcvtph2pd %xmm2, %xmm1");
+ asm volatile("vcvtph2pd 0x12345678(%eax,%ecx,8), %xmm1");
+ asm volatile("vcvtph2pd %xmm2, %ymm1");
+ asm volatile("vcvtph2pd 0x12345678(%eax,%ecx,8), %ymm1");
+ asm volatile("vcvtph2ps %ymm2, %zmm1");
+ asm volatile("vcvtph2ps 0x12345678(%eax,%ecx,8), %zmm1");
+ asm volatile("vcvtph2ps %xmm2, %xmm1");
+ asm volatile("vcvtph2ps 0x12345678(%eax,%ecx,8), %xmm1");
+ asm volatile("vcvtph2ps %xmm2, %ymm1");
+ asm volatile("vcvtph2ps 0x12345678(%eax,%ecx,8), %ymm1");
+ asm volatile("vcvtph2ps %xmm2, %xmm1");
+ asm volatile("vcvtph2ps 0x12345678(%eax,%ecx,8), %xmm1");
+ asm volatile("vcvtph2ps %xmm2, %ymm1");
+ asm volatile("vcvtph2ps 0x12345678(%eax,%ecx,8), %ymm1");
+ asm volatile("vcvtph2psx %ymm2, %zmm1");
+ asm volatile("vcvtph2psx 0x12345678(%eax,%ecx,8), %zmm1");
+ asm volatile("vcvtph2psx %xmm2, %xmm1");
+ asm volatile("vcvtph2psx 0x12345678(%eax,%ecx,8), %xmm1");
+ asm volatile("vcvtph2psx %xmm2, %ymm1");
+ asm volatile("vcvtph2psx 0x12345678(%eax,%ecx,8), %ymm1");
+ asm volatile("vcvtph2qq %xmm2, %zmm1");
+ asm volatile("vcvtph2qq 0x12345678(%eax,%ecx,8), %zmm1");
+ asm volatile("vcvtph2qq %xmm2, %xmm1");
+ asm volatile("vcvtph2qq 0x12345678(%eax,%ecx,8), %xmm1");
+ asm volatile("vcvtph2qq %xmm2, %ymm1");
+ asm volatile("vcvtph2qq 0x12345678(%eax,%ecx,8), %ymm1");
+ asm volatile("vcvtph2udq %ymm2, %zmm1");
+ asm volatile("vcvtph2udq 0x12345678(%eax,%ecx,8), %zmm1");
+ asm volatile("vcvtph2udq %xmm2, %xmm1");
+ asm volatile("vcvtph2udq 0x12345678(%eax,%ecx,8), %xmm1");
+ asm volatile("vcvtph2udq %xmm2, %ymm1");
+ asm volatile("vcvtph2udq 0x12345678(%eax,%ecx,8), %ymm1");
+ asm volatile("vcvtph2uqq %xmm2, %zmm1");
+ asm volatile("vcvtph2uqq 0x12345678(%eax,%ecx,8), %zmm1");
+ asm volatile("vcvtph2uqq %xmm2, %xmm1");
+ asm volatile("vcvtph2uqq 0x12345678(%eax,%ecx,8), %xmm1");
+ asm volatile("vcvtph2uqq %xmm2, %ymm1");
+ asm volatile("vcvtph2uqq 0x12345678(%eax,%ecx,8), %ymm1");
+ asm volatile("vcvtph2uw %zmm2, %zmm1");
+ asm volatile("vcvtph2uw 0x12345678(%eax,%ecx,8), %zmm1");
+ asm volatile("vcvtph2uw %xmm2, %xmm1");
+ asm volatile("vcvtph2uw 0x12345678(%eax,%ecx,8), %xmm1");
+ asm volatile("vcvtph2uw %ymm2, %ymm1");
+ asm volatile("vcvtph2uw 0x12345678(%eax,%ecx,8), %ymm1");
+ asm volatile("vcvtph2w %zmm2, %zmm1");
+ asm volatile("vcvtph2w 0x12345678(%eax,%ecx,8), %zmm1");
+ asm volatile("vcvtph2w %xmm2, %xmm1");
+ asm volatile("vcvtph2w 0x12345678(%eax,%ecx,8), %xmm1");
+ asm volatile("vcvtph2w %ymm2, %ymm1");
+ asm volatile("vcvtph2w 0x12345678(%eax,%ecx,8), %ymm1");
+ asm volatile("vcvtps2ph $0x12, %zmm1, 0x12345678(%eax,%ecx,8)");
+ asm volatile("vcvtps2ph $0x12, %zmm2, %ymm1");
+ asm volatile("vcvtps2ph $0x12, %ymm1, 0x12345678(%eax,%ecx,8)");
+ asm volatile("vcvtps2ph $0x12, %xmm1, 0x12345678(%eax,%ecx,8)");
+ asm volatile("vcvtps2ph $0x12, %xmm2, %xmm1");
+ asm volatile("vcvtps2ph $0x12, %ymm2, %xmm1");
+ asm volatile("vcvtps2ph $0x12, %ymm2, %xmm1");
+ asm volatile("vcvtps2ph $0x12, %ymm2, 0x12345678(%eax,%ecx,8)");
+ asm volatile("vcvtps2ph $0x12, %xmm2, %xmm1");
+ asm volatile("vcvtps2ph $0x12, %xmm2, 0x12345678(%eax,%ecx,8)");
+ asm volatile("vcvtps2phx %zmm2, %ymm1");
+ asm volatile("vcvtps2phx 0x12345678(%eax,%ecx,8), %ymm1");
+ asm volatile("vcvtps2phx %xmm2, %xmm1");
+ asm volatile("vcvtps2phx %ymm2, %xmm1");
+ asm volatile("vcvtqq2ph %zmm2, %xmm1");
+ asm volatile("vcvtqq2ph %xmm2, %xmm1");
+ asm volatile("vcvtqq2ph %ymm2, %xmm1");
+ asm volatile("vcvtsd2sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vcvtsh2sd 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vcvtsh2si 0x12345678(%eax,%ecx,8), %eax");
+ asm volatile("vcvtsh2ss 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vcvtsh2usi %xmm1, %eax");
+ asm volatile("vcvtsh2usi 0x12345678(%eax,%ecx,8), %eax");
+ asm volatile("vcvtsi2sh %eax, %xmm2, %xmm1");
+ asm volatile("vcvtsi2sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vcvtsi2sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vcvtss2sh %xmm3, %xmm2, %xmm1");
+ asm volatile("vcvtss2sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vcvttph2dq %ymm2, %zmm1");
+ asm volatile("vcvttph2dq 0x12345678(%eax,%ecx,8), %zmm1");
+ asm volatile("vcvttph2dq %xmm2, %xmm1");
+ asm volatile("vcvttph2dq 0x12345678(%eax,%ecx,8), %xmm1");
+ asm volatile("vcvttph2dq %xmm2, %ymm1");
+ asm volatile("vcvttph2dq 0x12345678(%eax,%ecx,8), %ymm1");
+ asm volatile("vcvttph2qq %xmm2, %zmm1");
+ asm volatile("vcvttph2qq 0x12345678(%eax,%ecx,8), %zmm1");
+ asm volatile("vcvttph2qq %xmm2, %xmm1");
+ asm volatile("vcvttph2qq 0x12345678(%eax,%ecx,8), %xmm1");
+ asm volatile("vcvttph2qq %xmm2, %ymm1");
+ asm volatile("vcvttph2qq 0x12345678(%eax,%ecx,8), %ymm1");
+ asm volatile("vcvttph2udq %ymm2, %zmm1");
+ asm volatile("vcvttph2udq 0x12345678(%eax,%ecx,8), %zmm1");
+ asm volatile("vcvttph2udq %xmm2, %xmm1");
+ asm volatile("vcvttph2udq 0x12345678(%eax,%ecx,8), %xmm1");
+ asm volatile("vcvttph2udq %xmm2, %ymm1");
+ asm volatile("vcvttph2udq 0x12345678(%eax,%ecx,8), %ymm1");
+ asm volatile("vcvttph2uqq %xmm2, %zmm1");
+ asm volatile("vcvttph2uqq 0x12345678(%eax,%ecx,8), %zmm1");
+ asm volatile("vcvttph2uqq %xmm2, %xmm1");
+ asm volatile("vcvttph2uqq 0x12345678(%eax,%ecx,8), %xmm1");
+ asm volatile("vcvttph2uqq %xmm2, %ymm1");
+ asm volatile("vcvttph2uqq 0x12345678(%eax,%ecx,8), %ymm1");
+ asm volatile("vcvttph2uw %zmm2, %zmm1");
+ asm volatile("vcvttph2uw 0x12345678(%eax,%ecx,8), %zmm1");
+ asm volatile("vcvttph2uw %xmm2, %xmm1");
+ asm volatile("vcvttph2uw 0x12345678(%eax,%ecx,8), %xmm1");
+ asm volatile("vcvttph2uw %ymm2, %ymm1");
+ asm volatile("vcvttph2uw 0x12345678(%eax,%ecx,8), %ymm1");
+ asm volatile("vcvttph2w %zmm2, %zmm1");
+ asm volatile("vcvttph2w 0x12345678(%eax,%ecx,8), %zmm1");
+ asm volatile("vcvttph2w %xmm2, %xmm1");
+ asm volatile("vcvttph2w 0x12345678(%eax,%ecx,8), %xmm1");
+ asm volatile("vcvttph2w %ymm2, %ymm1");
+ asm volatile("vcvttph2w 0x12345678(%eax,%ecx,8), %ymm1");
+ asm volatile("vcvttsh2si %xmm1, %eax");
+ asm volatile("vcvttsh2si 0x12345678(%eax,%ecx,8), %eax");
+ asm volatile("vcvttsh2usi %xmm1, %eax");
+ asm volatile("vcvttsh2usi 0x12345678(%eax,%ecx,8), %eax");
+ asm volatile("vcvtudq2ph %zmm2, %ymm1");
+ asm volatile("vcvtudq2ph 0x12345678(%eax,%ecx,8), %ymm1");
+ asm volatile("vcvtudq2ph %xmm2, %xmm1");
+ asm volatile("vcvtudq2ph %ymm2, %xmm1");
+ asm volatile("vcvtuqq2ph %zmm2, %xmm1");
+ asm volatile("vcvtuqq2ph %xmm2, %xmm1");
+ asm volatile("vcvtuqq2ph %ymm2, %xmm1");
+ asm volatile("vcvtusi2sh %eax, %xmm2, %xmm1");
+ asm volatile("vcvtusi2sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vcvtusi2sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vcvtuw2ph %zmm2, %zmm1");
+ asm volatile("vcvtuw2ph 0x12345678(%eax,%ecx,8), %zmm1");
+ asm volatile("vcvtuw2ph %xmm2, %xmm1");
+ asm volatile("vcvtuw2ph 0x12345678(%eax,%ecx,8), %xmm1");
+ asm volatile("vcvtuw2ph %ymm2, %ymm1");
+ asm volatile("vcvtuw2ph 0x12345678(%eax,%ecx,8), %ymm1");
+ asm volatile("vcvtw2ph %zmm2, %zmm1");
+ asm volatile("vcvtw2ph 0x12345678(%eax,%ecx,8), %zmm1");
+ asm volatile("vcvtw2ph %xmm2, %xmm1");
+ asm volatile("vcvtw2ph 0x12345678(%eax,%ecx,8), %xmm1");
+ asm volatile("vcvtw2ph %ymm2, %ymm1");
+ asm volatile("vcvtw2ph 0x12345678(%eax,%ecx,8), %ymm1");
+ asm volatile("vdivph %zmm3, %zmm2, %zmm1");
+ asm volatile("vdivph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1");
+ asm volatile("vdivph %xmm3, %xmm2, %xmm1");
+ asm volatile("vdivph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vdivph %ymm3, %ymm2, %ymm1");
+ asm volatile("vdivph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1");
+ asm volatile("vdivsh %xmm3, %xmm2, %xmm1");
+ asm volatile("vdivsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfcmaddcph %zmm3, %zmm2, %zmm1");
+ asm volatile("vfcmaddcph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1");
+ asm volatile("vfcmaddcph %xmm3, %xmm2, %xmm1");
+ asm volatile("vfcmaddcph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfcmaddcph %ymm3, %ymm2, %ymm1");
+ asm volatile("vfcmaddcph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1");
+ asm volatile("vfcmaddcsh %xmm3, %xmm2, %xmm1");
+ asm volatile("vfcmaddcsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfcmulcph %zmm3, %zmm2, %zmm1");
+ asm volatile("vfcmulcph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1");
+ asm volatile("vfcmulcph %xmm3, %xmm2, %xmm1");
+ asm volatile("vfcmulcph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfcmulcph %ymm3, %ymm2, %ymm1");
+ asm volatile("vfcmulcph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1");
+ asm volatile("vfcmulcsh %xmm3, %xmm2, %xmm1");
+ asm volatile("vfcmulcsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfmadd132ph %zmm3, %zmm2, %zmm1");
+ asm volatile("vfmadd132ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1");
+ asm volatile("vfmadd132ph %xmm3, %xmm2, %xmm1");
+ asm volatile("vfmadd132ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfmadd132ph %ymm3, %ymm2, %ymm1");
+ asm volatile("vfmadd132ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1");
+ asm volatile("vfmadd132sh %xmm3, %xmm2, %xmm1");
+ asm volatile("vfmadd132sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfmadd213ph %zmm3, %zmm2, %zmm1");
+ asm volatile("vfmadd213ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1");
+ asm volatile("vfmadd213ph %xmm3, %xmm2, %xmm1");
+ asm volatile("vfmadd213ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfmadd213ph %ymm3, %ymm2, %ymm1");
+ asm volatile("vfmadd213ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1");
+ asm volatile("vfmadd213sh %xmm3, %xmm2, %xmm1");
+ asm volatile("vfmadd213sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfmadd231ph %zmm3, %zmm2, %zmm1");
+ asm volatile("vfmadd231ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1");
+ asm volatile("vfmadd231ph %xmm3, %xmm2, %xmm1");
+ asm volatile("vfmadd231ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfmadd231ph %ymm3, %ymm2, %ymm1");
+ asm volatile("vfmadd231ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1");
+ asm volatile("vfmadd231sh %xmm3, %xmm2, %xmm1");
+ asm volatile("vfmadd231sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfmaddcph %zmm3, %zmm2, %zmm1");
+ asm volatile("vfmaddcph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1");
+ asm volatile("vfmaddcph %xmm3, %xmm2, %xmm1");
+ asm volatile("vfmaddcph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfmaddcph %ymm3, %ymm2, %ymm1");
+ asm volatile("vfmaddcph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1");
+ asm volatile("vfmaddcsh %xmm3, %xmm2, %xmm1");
+ asm volatile("vfmaddcsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfmaddsub132ph %zmm3, %zmm2, %zmm1");
+ asm volatile("vfmaddsub132ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1");
+ asm volatile("vfmaddsub132ph %xmm3, %xmm2, %xmm1");
+ asm volatile("vfmaddsub132ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfmaddsub132ph %ymm3, %ymm2, %ymm1");
+ asm volatile("vfmaddsub132ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1");
+ asm volatile("vfmaddsub213ph %zmm3, %zmm2, %zmm1");
+ asm volatile("vfmaddsub213ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1");
+ asm volatile("vfmaddsub213ph %xmm3, %xmm2, %xmm1");
+ asm volatile("vfmaddsub213ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfmaddsub213ph %ymm3, %ymm2, %ymm1");
+ asm volatile("vfmaddsub213ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1");
+ asm volatile("vfmaddsub231ph %zmm3, %zmm2, %zmm1");
+ asm volatile("vfmaddsub231ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1");
+ asm volatile("vfmaddsub231ph %xmm3, %xmm2, %xmm1");
+ asm volatile("vfmaddsub231ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfmaddsub231ph %ymm3, %ymm2, %ymm1");
+ asm volatile("vfmaddsub231ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1");
+ asm volatile("vfmsub132ph %zmm3, %zmm2, %zmm1");
+ asm volatile("vfmsub132ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1");
+ asm volatile("vfmsub132ph %xmm3, %xmm2, %xmm1");
+ asm volatile("vfmsub132ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfmsub132ph %ymm3, %ymm2, %ymm1");
+ asm volatile("vfmsub132ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1");
+ asm volatile("vfmsub132sh %xmm3, %xmm2, %xmm1");
+ asm volatile("vfmsub132sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfmsub213ph %zmm3, %zmm2, %zmm1");
+ asm volatile("vfmsub213ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1");
+ asm volatile("vfmsub213ph %xmm3, %xmm2, %xmm1");
+ asm volatile("vfmsub213ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfmsub213ph %ymm3, %ymm2, %ymm1");
+ asm volatile("vfmsub213ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1");
+ asm volatile("vfmsub213sh %xmm3, %xmm2, %xmm1");
+ asm volatile("vfmsub213sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfmsub231ph %zmm3, %zmm2, %zmm1");
+ asm volatile("vfmsub231ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1");
+ asm volatile("vfmsub231ph %xmm3, %xmm2, %xmm1");
+ asm volatile("vfmsub231ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfmsub231ph %ymm3, %ymm2, %ymm1");
+ asm volatile("vfmsub231ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1");
+ asm volatile("vfmsub231sh %xmm3, %xmm2, %xmm1");
+ asm volatile("vfmsub231sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfmsubadd132ph %zmm3, %zmm2, %zmm1");
+ asm volatile("vfmsubadd132ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1");
+ asm volatile("vfmsubadd132ph %xmm3, %xmm2, %xmm1");
+ asm volatile("vfmsubadd132ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfmsubadd132ph %ymm3, %ymm2, %ymm1");
+ asm volatile("vfmsubadd132ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1");
+ asm volatile("vfmsubadd213ph %zmm3, %zmm2, %zmm1");
+ asm volatile("vfmsubadd213ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1");
+ asm volatile("vfmsubadd213ph %xmm3, %xmm2, %xmm1");
+ asm volatile("vfmsubadd213ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfmsubadd213ph %ymm3, %ymm2, %ymm1");
+ asm volatile("vfmsubadd213ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1");
+ asm volatile("vfmsubadd231ph %zmm3, %zmm2, %zmm1");
+ asm volatile("vfmsubadd231ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1");
+ asm volatile("vfmsubadd231ph %xmm3, %xmm2, %xmm1");
+ asm volatile("vfmsubadd231ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfmsubadd231ph %ymm3, %ymm2, %ymm1");
+ asm volatile("vfmsubadd231ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1");
+ asm volatile("vfmulcph %zmm3, %zmm2, %zmm1");
+ asm volatile("vfmulcph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1");
+ asm volatile("vfmulcph %xmm3, %xmm2, %xmm1");
+ asm volatile("vfmulcph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfmulcph %ymm3, %ymm2, %ymm1");
+ asm volatile("vfmulcph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1");
+ asm volatile("vfmulcsh %xmm3, %xmm2, %xmm1");
+ asm volatile("vfmulcsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfnmadd132ph %zmm3, %zmm2, %zmm1");
+ asm volatile("vfnmadd132ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1");
+ asm volatile("vfnmadd132ph %xmm3, %xmm2, %xmm1");
+ asm volatile("vfnmadd132ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfnmadd132ph %ymm3, %ymm2, %ymm1");
+ asm volatile("vfnmadd132ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1");
+ asm volatile("vfnmadd132sh %xmm3, %xmm2, %xmm1");
+ asm volatile("vfnmadd132sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfnmadd213ph %zmm3, %zmm2, %zmm1");
+ asm volatile("vfnmadd213ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1");
+ asm volatile("vfnmadd213ph %xmm3, %xmm2, %xmm1");
+ asm volatile("vfnmadd213ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfnmadd213ph %ymm3, %ymm2, %ymm1");
+ asm volatile("vfnmadd213ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1");
+ asm volatile("vfnmadd213sh %xmm3, %xmm2, %xmm1");
+ asm volatile("vfnmadd213sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfnmadd231ph %zmm3, %zmm2, %zmm1");
+ asm volatile("vfnmadd231ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1");
+ asm volatile("vfnmadd231ph %xmm3, %xmm2, %xmm1");
+ asm volatile("vfnmadd231ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfnmadd231ph %ymm3, %ymm2, %ymm1");
+ asm volatile("vfnmadd231ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1");
+ asm volatile("vfnmadd231sh %xmm3, %xmm2, %xmm1");
+ asm volatile("vfnmadd231sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfnmsub132ph %zmm3, %zmm2, %zmm1");
+ asm volatile("vfnmsub132ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1");
+ asm volatile("vfnmsub132ph %xmm3, %xmm2, %xmm1");
+ asm volatile("vfnmsub132ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfnmsub132ph %ymm3, %ymm2, %ymm1");
+ asm volatile("vfnmsub132ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1");
+ asm volatile("vfnmsub132sh %xmm3, %xmm2, %xmm1");
+ asm volatile("vfnmsub132sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfnmsub213ph %zmm3, %zmm2, %zmm1");
+ asm volatile("vfnmsub213ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1");
+ asm volatile("vfnmsub213ph %xmm3, %xmm2, %xmm1");
+ asm volatile("vfnmsub213ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfnmsub213ph %ymm3, %ymm2, %ymm1");
+ asm volatile("vfnmsub213ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1");
+ asm volatile("vfnmsub213sh %xmm3, %xmm2, %xmm1");
+ asm volatile("vfnmsub213sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfnmsub231ph %zmm3, %zmm2, %zmm1");
+ asm volatile("vfnmsub231ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1");
+ asm volatile("vfnmsub231ph %xmm3, %xmm2, %xmm1");
+ asm volatile("vfnmsub231ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfnmsub231ph %ymm3, %ymm2, %ymm1");
+ asm volatile("vfnmsub231ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1");
+ asm volatile("vfnmsub231sh %xmm3, %xmm2, %xmm1");
+ asm volatile("vfnmsub231sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vfpclassph $0x12, %zmm1, %k5");
+ asm volatile("vfpclassph $0x12, %xmm1, %k5");
+ asm volatile("vfpclassph $0x12, %ymm1, %k5");
+ asm volatile("vfpclasssh $0x12, %xmm1, %k5");
+ asm volatile("vfpclasssh $0x12, 0x12345678(%eax,%ecx,8), %k5");
+ asm volatile("vgetexpph %zmm2, %zmm1");
+ asm volatile("vgetexpph 0x12345678(%eax,%ecx,8), %zmm1");
+ asm volatile("vgetexpph %xmm2, %xmm1");
+ asm volatile("vgetexpph 0x12345678(%eax,%ecx,8), %xmm1");
+ asm volatile("vgetexpph %ymm2, %ymm1");
+ asm volatile("vgetexpph 0x12345678(%eax,%ecx,8), %ymm1");
+ asm volatile("vgetexpsh %xmm3, %xmm2, %xmm1");
+ asm volatile("vgetexpsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vgetmantph $0x12, %zmm2, %zmm1");
+ asm volatile("vgetmantph $0x12, 0x12345678(%eax,%ecx,8), %zmm1");
+ asm volatile("vgetmantph $0x12, %xmm2, %xmm1");
+ asm volatile("vgetmantph $0x12, 0x12345678(%eax,%ecx,8), %xmm1");
+ asm volatile("vgetmantph $0x12, %ymm2, %ymm1");
+ asm volatile("vgetmantph $0x12, 0x12345678(%eax,%ecx,8), %ymm1");
+ asm volatile("vgetmantsh $0x12, %xmm3, %xmm2, %xmm1");
+ asm volatile("vgetmantsh $0x12, 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vmaxph %zmm3, %zmm2, %zmm1");
+ asm volatile("vmaxph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1");
+ asm volatile("vmaxph %xmm3, %xmm2, %xmm1");
+ asm volatile("vmaxph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vmaxph %ymm3, %ymm2, %ymm1");
+ asm volatile("vmaxph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1");
+ asm volatile("vmaxsh %xmm3, %xmm2, %xmm1");
+ asm volatile("vmaxsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vminph %zmm3, %zmm2, %zmm1");
+ asm volatile("vminph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1");
+ asm volatile("vminph %xmm3, %xmm2, %xmm1");
+ asm volatile("vminph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vminph %ymm3, %ymm2, %ymm1");
+ asm volatile("vminph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1");
+ asm volatile("vminsh %xmm3, %xmm2, %xmm1");
+ asm volatile("vminsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vmovsh %xmm1, 0x12345678(%eax,%ecx,8)");
+ asm volatile("vmovsh 0x12345678(%eax,%ecx,8), %xmm1");
+ asm volatile("vmovsh %xmm3, %xmm2, %xmm1");
+ asm volatile("vmovw %xmm1, %eax");
+ asm volatile("vmovw %xmm1, 0x12345678(%eax,%ecx,8)");
+ asm volatile("vmovw %eax, %xmm1");
+ asm volatile("vmovw 0x12345678(%eax,%ecx,8), %xmm1");
+ asm volatile("vmulph %zmm3, %zmm2, %zmm1");
+ asm volatile("vmulph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1");
+ asm volatile("vmulph %xmm3, %xmm2, %xmm1");
+ asm volatile("vmulph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vmulph %ymm3, %ymm2, %ymm1");
+ asm volatile("vmulph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1");
+ asm volatile("vmulsh %xmm3, %xmm2, %xmm1");
+ asm volatile("vmulsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vrcpph %zmm2, %zmm1");
+ asm volatile("vrcpph 0x12345678(%eax,%ecx,8), %zmm1");
+ asm volatile("vrcpph %xmm2, %xmm1");
+ asm volatile("vrcpph 0x12345678(%eax,%ecx,8), %xmm1");
+ asm volatile("vrcpph %ymm2, %ymm1");
+ asm volatile("vrcpph 0x12345678(%eax,%ecx,8), %ymm1");
+ asm volatile("vrcpsh %xmm3, %xmm2, %xmm1");
+ asm volatile("vrcpsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vreduceph $0x12, %zmm2, %zmm1");
+ asm volatile("vreduceph $0x12, 0x12345678(%eax,%ecx,8), %zmm1");
+ asm volatile("vreduceph $0x12, %xmm2, %xmm1");
+ asm volatile("vreduceph $0x12, 0x12345678(%eax,%ecx,8), %xmm1");
+ asm volatile("vreduceph $0x12, %ymm2, %ymm1");
+ asm volatile("vreduceph $0x12, 0x12345678(%eax,%ecx,8), %ymm1");
+ asm volatile("vreducesh $0x12, %xmm3, %xmm2, %xmm1");
+ asm volatile("vreducesh $0x12, 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vrndscaleph $0x12, %zmm2, %zmm1");
+ asm volatile("vrndscaleph $0x12, 0x12345678(%eax,%ecx,8), %zmm1");
+ asm volatile("vrndscaleph $0x12, %xmm2, %xmm1");
+ asm volatile("vrndscaleph $0x12, 0x12345678(%eax,%ecx,8), %xmm1");
+ asm volatile("vrndscaleph $0x12, %ymm2, %ymm1");
+ asm volatile("vrndscaleph $0x12, 0x12345678(%eax,%ecx,8), %ymm1");
+ asm volatile("vrndscalesh $0x12, %xmm3, %xmm2, %xmm1");
+ asm volatile("vrndscalesh $0x12, 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vrsqrtph %zmm2, %zmm1");
+ asm volatile("vrsqrtph 0x12345678(%eax,%ecx,8), %zmm1");
+ asm volatile("vrsqrtph %xmm2, %xmm1");
+ asm volatile("vrsqrtph 0x12345678(%eax,%ecx,8), %xmm1");
+ asm volatile("vrsqrtph %ymm2, %ymm1");
+ asm volatile("vrsqrtph 0x12345678(%eax,%ecx,8), %ymm1");
+ asm volatile("vrsqrtsh %xmm3, %xmm2, %xmm1");
+ asm volatile("vrsqrtsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vscalefph %zmm3, %zmm2, %zmm1");
+ asm volatile("vscalefph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1");
+ asm volatile("vscalefph %xmm3, %xmm2, %xmm1");
+ asm volatile("vscalefph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vscalefph %ymm3, %ymm2, %ymm1");
+ asm volatile("vscalefph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1");
+ asm volatile("vscalefsh %xmm3, %xmm2, %xmm1");
+ asm volatile("vscalefsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vsqrtph %zmm2, %zmm1");
+ asm volatile("vsqrtph 0x12345678(%eax,%ecx,8), %zmm1");
+ asm volatile("vsqrtph %xmm2, %xmm1");
+ asm volatile("vsqrtph 0x12345678(%eax,%ecx,8), %xmm1");
+ asm volatile("vsqrtph %ymm2, %ymm1");
+ asm volatile("vsqrtph 0x12345678(%eax,%ecx,8), %ymm1");
+ asm volatile("vsqrtsh %xmm3, %xmm2, %xmm1");
+ asm volatile("vsqrtsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vsubph %zmm3, %zmm2, %zmm1");
+ asm volatile("vsubph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1");
+ asm volatile("vsubph %xmm3, %xmm2, %xmm1");
+ asm volatile("vsubph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vsubph %ymm3, %ymm2, %ymm1");
+ asm volatile("vsubph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1");
+ asm volatile("vsubsh %xmm3, %xmm2, %xmm1");
+ asm volatile("vsubsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1");
+ asm volatile("vucomish %xmm2, %xmm1");
+ asm volatile("vucomish 0x12345678(%eax,%ecx,8), %xmm1");
+
#endif /* #ifndef __x86_64__ */
+ /* Prediction history reset */
+
+ asm volatile("hreset $0");
+
+ /* Serialize instruction execution */
+
+ asm volatile("serialize");
+
+ /* TSX suspend load address tracking */
+
+ asm volatile("xresldtrk");
+ asm volatile("xsusldtrk");
+
/* SGX */
asm volatile("encls");
diff --git a/tools/perf/arch/x86/util/evlist.c b/tools/perf/arch/x86/util/evlist.c
index 0b0951030a2f..8d9b55959256 100644
--- a/tools/perf/arch/x86/util/evlist.c
+++ b/tools/perf/arch/x86/util/evlist.c
@@ -17,3 +17,20 @@ int arch_evlist__add_default_attrs(struct evlist *evlist)
else
return parse_events(evlist, TOPDOWN_L1_EVENTS, NULL);
}
+
+struct evsel *arch_evlist__leader(struct list_head *list)
+{
+ struct evsel *evsel, *first;
+
+ first = list_first_entry(list, struct evsel, core.node);
+
+ if (!pmu_have_event("cpu", "slots"))
+ return first;
+
+ __evlist__for_each_entry(list, evsel) {
+ if (evsel->pmu_name && !strcmp(evsel->pmu_name, "cpu") &&
+ evsel->name && strcasestr(evsel->name, "slots"))
+ return evsel;
+ }
+ return first;
+}
diff --git a/tools/perf/bench/epoll-ctl.c b/tools/perf/bench/epoll-ctl.c
index ddaca75c3bc0..134612bde0cb 100644
--- a/tools/perf/bench/epoll-ctl.c
+++ b/tools/perf/bench/epoll-ctl.c
@@ -106,7 +106,7 @@ static void nest_epollfd(void)
printinfo("Nesting level(s): %d\n", nested);
epollfdp = calloc(nested, sizeof(int));
- if (!epollfd)
+ if (!epollfdp)
err(EXIT_FAILURE, "calloc");
for (i = 0; i < nested; i++) {
@@ -253,7 +253,7 @@ static int do_threads(struct worker *worker, struct perf_cpu_map *cpu)
if (!noaffinity) {
CPU_ZERO(&cpuset);
- CPU_SET(cpu->map[i % cpu->nr], &cpuset);
+ CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset);
ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset);
if (ret)
@@ -333,7 +333,7 @@ int bench_epoll_ctl(int argc, const char **argv)
/* default to the number of CPUs */
if (!nthreads)
- nthreads = cpu->nr;
+ nthreads = perf_cpu_map__nr(cpu);
worker = calloc(nthreads, sizeof(*worker));
if (!worker)
diff --git a/tools/perf/bench/epoll-wait.c b/tools/perf/bench/epoll-wait.c
index 79d13dbc0a47..37de970c9743 100644
--- a/tools/perf/bench/epoll-wait.c
+++ b/tools/perf/bench/epoll-wait.c
@@ -342,7 +342,7 @@ static int do_threads(struct worker *worker, struct perf_cpu_map *cpu)
if (!noaffinity) {
CPU_ZERO(&cpuset);
- CPU_SET(cpu->map[i % cpu->nr], &cpuset);
+ CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset);
ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset);
if (ret)
@@ -452,7 +452,7 @@ int bench_epoll_wait(int argc, const char **argv)
/* default to the number of CPUs and leave one for the writer pthread */
if (!nthreads)
- nthreads = cpu->nr - 1;
+ nthreads = perf_cpu_map__nr(cpu) - 1;
worker = calloc(nthreads, sizeof(*worker));
if (!worker) {
diff --git a/tools/perf/bench/evlist-open-close.c b/tools/perf/bench/evlist-open-close.c
index 482738e9bdad..de56601f69ee 100644
--- a/tools/perf/bench/evlist-open-close.c
+++ b/tools/perf/bench/evlist-open-close.c
@@ -71,7 +71,7 @@ static int evlist__count_evsel_fds(struct evlist *evlist)
int cnt = 0;
evlist__for_each_entry(evlist, evsel)
- cnt += evsel->core.threads->nr * evsel->core.cpus->nr;
+ cnt += evsel->core.threads->nr * perf_cpu_map__nr(evsel->core.cpus);
return cnt;
}
@@ -151,7 +151,7 @@ static int bench_evlist_open_close__run(char *evstr)
init_stats(&time_stats);
- printf(" Number of cpus:\t%d\n", evlist->core.cpus->nr);
+ printf(" Number of cpus:\t%d\n", perf_cpu_map__nr(evlist->core.cpus));
printf(" Number of threads:\t%d\n", evlist->core.threads->nr);
printf(" Number of events:\t%d (%d fds)\n",
evlist->core.nr_entries, evlist__count_evsel_fds(evlist));
diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c
index fcdea3e44937..dbcecec4eeda 100644
--- a/tools/perf/bench/futex-hash.c
+++ b/tools/perf/bench/futex-hash.c
@@ -150,7 +150,7 @@ int bench_futex_hash(int argc, const char **argv)
}
if (!params.nthreads) /* default to the number of CPUs */
- params.nthreads = cpu->nr;
+ params.nthreads = perf_cpu_map__nr(cpu);
worker = calloc(params.nthreads, sizeof(*worker));
if (!worker)
@@ -177,7 +177,7 @@ int bench_futex_hash(int argc, const char **argv)
goto errmem;
CPU_ZERO(&cpuset);
- CPU_SET(cpu->map[i % cpu->nr], &cpuset);
+ CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset);
ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset);
if (ret)
diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c
index 137890f78e17..6fc9a3d55c1f 100644
--- a/tools/perf/bench/futex-lock-pi.c
+++ b/tools/perf/bench/futex-lock-pi.c
@@ -136,7 +136,7 @@ static void create_threads(struct worker *w, pthread_attr_t thread_attr,
worker[i].futex = &global_futex;
CPU_ZERO(&cpuset);
- CPU_SET(cpu->map[i % cpu->nr], &cpuset);
+ CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset);
if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset))
err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
@@ -173,7 +173,7 @@ int bench_futex_lock_pi(int argc, const char **argv)
}
if (!params.nthreads)
- params.nthreads = cpu->nr;
+ params.nthreads = perf_cpu_map__nr(cpu);
worker = calloc(params.nthreads, sizeof(*worker));
if (!worker)
diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c
index f7a5ffebb940..2f59d5d1c509 100644
--- a/tools/perf/bench/futex-requeue.c
+++ b/tools/perf/bench/futex-requeue.c
@@ -131,7 +131,7 @@ static void block_threads(pthread_t *w,
/* create and block all threads */
for (i = 0; i < params.nthreads; i++) {
CPU_ZERO(&cpuset);
- CPU_SET(cpu->map[i % cpu->nr], &cpuset);
+ CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset);
if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset))
err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
@@ -175,7 +175,7 @@ int bench_futex_requeue(int argc, const char **argv)
}
if (!params.nthreads)
- params.nthreads = cpu->nr;
+ params.nthreads = perf_cpu_map__nr(cpu);
worker = calloc(params.nthreads, sizeof(*worker));
if (!worker)
diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c
index 0983f40b4b40..861deb934745 100644
--- a/tools/perf/bench/futex-wake-parallel.c
+++ b/tools/perf/bench/futex-wake-parallel.c
@@ -152,7 +152,7 @@ static void block_threads(pthread_t *w, pthread_attr_t thread_attr,
/* create and block all threads */
for (i = 0; i < params.nthreads; i++) {
CPU_ZERO(&cpuset);
- CPU_SET(cpu->map[i % cpu->nr], &cpuset);
+ CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset);
if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset))
err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
@@ -252,7 +252,7 @@ int bench_futex_wake_parallel(int argc, const char **argv)
err(EXIT_FAILURE, "calloc");
if (!params.nthreads)
- params.nthreads = cpu->nr;
+ params.nthreads = perf_cpu_map__nr(cpu);
/* some sanity checks */
if (params.nwakes > params.nthreads ||
diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c
index 2226a475e782..cfda48bef1d7 100644
--- a/tools/perf/bench/futex-wake.c
+++ b/tools/perf/bench/futex-wake.c
@@ -105,7 +105,7 @@ static void block_threads(pthread_t *w,
/* create and block all threads */
for (i = 0; i < params.nthreads; i++) {
CPU_ZERO(&cpuset);
- CPU_SET(cpu->map[i % cpu->nr], &cpuset);
+ CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset);
if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset))
err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
@@ -151,7 +151,7 @@ int bench_futex_wake(int argc, const char **argv)
}
if (!params.nthreads)
- params.nthreads = cpu->nr;
+ params.nthreads = perf_cpu_map__nr(cpu);
worker = calloc(params.nthreads, sizeof(*worker));
if (!worker)
diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c
index d0895162c2ba..d291f3a8af5f 100644
--- a/tools/perf/builtin-bench.c
+++ b/tools/perf/builtin-bench.c
@@ -226,7 +226,6 @@ static void run_collection(struct collection *coll)
if (!bench->fn)
break;
printf("# Running %s/%s benchmark...\n", coll->name, bench->name);
- fflush(stdout);
argv[1] = bench->name;
run_bench(coll->name, bench->name, bench->fn, 1, argv);
@@ -247,6 +246,9 @@ int cmd_bench(int argc, const char **argv)
struct collection *coll;
int ret = 0;
+ /* Unbuffered output */
+ setvbuf(stdout, NULL, _IONBF, 0);
+
if (argc < 2) {
/* No collection specified. */
print_usage();
@@ -300,7 +302,6 @@ int cmd_bench(int argc, const char **argv)
if (bench_format == BENCH_FORMAT_DEFAULT)
printf("# Running '%s/%s' benchmark:\n", coll->name, bench->name);
- fflush(stdout);
ret = run_bench(coll->name, bench->name, bench->fn, argc-1, argv+1);
goto end;
}
diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c
index 0db3cfc04c47..cd381693658b 100644
--- a/tools/perf/builtin-buildid-cache.c
+++ b/tools/perf/builtin-buildid-cache.c
@@ -351,10 +351,14 @@ static int build_id_cache__show_all(void)
static int perf_buildid_cache_config(const char *var, const char *value, void *cb)
{
- const char **debuginfod = cb;
+ struct perf_debuginfod *di = cb;
- if (!strcmp(var, "buildid-cache.debuginfod"))
- *debuginfod = strdup(value);
+ if (!strcmp(var, "buildid-cache.debuginfod")) {
+ di->urls = strdup(value);
+ if (!di->urls)
+ return -ENOMEM;
+ di->set = true;
+ }
return 0;
}
@@ -373,8 +377,8 @@ int cmd_buildid_cache(int argc, const char **argv)
*purge_name_list_str = NULL,
*missing_filename = NULL,
*update_name_list_str = NULL,
- *kcore_filename = NULL,
- *debuginfod = NULL;
+ *kcore_filename = NULL;
+ struct perf_debuginfod debuginfod = { };
char sbuf[STRERR_BUFSIZE];
struct perf_data data = {
@@ -399,8 +403,10 @@ int cmd_buildid_cache(int argc, const char **argv)
OPT_BOOLEAN('f', "force", &force, "don't complain, do it"),
OPT_STRING('u', "update", &update_name_list_str, "file list",
"file(s) to update"),
- OPT_STRING(0, "debuginfod", &debuginfod, "debuginfod url",
- "set debuginfod url"),
+ OPT_STRING_OPTARG_SET(0, "debuginfod", &debuginfod.urls,
+ &debuginfod.set, "debuginfod urls",
+ "Enable debuginfod data retrieval from DEBUGINFOD_URLS or specified urls",
+ "system"),
OPT_INCR('v', "verbose", &verbose, "be more verbose"),
OPT_INTEGER(0, "target-ns", &ns_id, "target pid for namespace context"),
OPT_END()
@@ -425,10 +431,7 @@ int cmd_buildid_cache(int argc, const char **argv)
if (argc || !(list_files || opts_flag))
usage_with_options(buildid_cache_usage, buildid_cache_options);
- if (debuginfod) {
- pr_debug("DEBUGINFOD_URLS=%s\n", debuginfod);
- setenv("DEBUGINFOD_URLS", debuginfod, 1);
- }
+ perf_debuginfod_setup(&debuginfod);
/* -l is exclusive. It can not be used with other options. */
if (list_files && opts_flag) {
diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index b5c67ef73862..77dd4afacca4 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -2015,7 +2015,8 @@ static int setup_nodes(struct perf_session *session)
{
struct numa_node *n;
unsigned long **nodes;
- int node, cpu;
+ int node, idx;
+ struct perf_cpu cpu;
int *cpu2node;
if (c2c.node_info > 2)
@@ -2038,8 +2039,8 @@ static int setup_nodes(struct perf_session *session)
if (!cpu2node)
return -ENOMEM;
- for (cpu = 0; cpu < c2c.cpus_cnt; cpu++)
- cpu2node[cpu] = -1;
+ for (idx = 0; idx < c2c.cpus_cnt; idx++)
+ cpu2node[idx] = -1;
c2c.cpu2node = cpu2node;
@@ -2057,13 +2058,13 @@ static int setup_nodes(struct perf_session *session)
if (perf_cpu_map__empty(map))
continue;
- for (cpu = 0; cpu < map->nr; cpu++) {
- set_bit(map->map[cpu], set);
+ perf_cpu_map__for_each_cpu(cpu, idx, map) {
+ set_bit(cpu.cpu, set);
- if (WARN_ONCE(cpu2node[map->map[cpu]] != -1, "node/cpu topology bug"))
+ if (WARN_ONCE(cpu2node[cpu.cpu] != -1, "node/cpu topology bug"))
return -EINVAL;
- cpu2node[map->map[cpu]] = node;
+ cpu2node[cpu.cpu] = node;
}
}
diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c
index 87cb11a7a3ee..a8785dec5ca6 100644
--- a/tools/perf/builtin-ftrace.c
+++ b/tools/perf/builtin-ftrace.c
@@ -13,7 +13,9 @@
#include <signal.h>
#include <stdlib.h>
#include <fcntl.h>
+#include <math.h>
#include <poll.h>
+#include <ctype.h>
#include <linux/capability.h>
#include <linux/string.h>
@@ -28,36 +30,12 @@
#include "strfilter.h"
#include "util/cap.h"
#include "util/config.h"
+#include "util/ftrace.h"
#include "util/units.h"
#include "util/parse-sublevel-options.h"
#define DEFAULT_TRACER "function_graph"
-struct perf_ftrace {
- struct evlist *evlist;
- struct target target;
- const char *tracer;
- struct list_head filters;
- struct list_head notrace;
- struct list_head graph_funcs;
- struct list_head nograph_funcs;
- int graph_depth;
- unsigned long percpu_buffer_size;
- bool inherit;
- int func_stack_trace;
- int func_irq_info;
- int graph_nosleep_time;
- int graph_noirqs;
- int graph_verbose;
- int graph_thresh;
- unsigned int initial_delay;
-};
-
-struct filter_entry {
- struct list_head list;
- char name[];
-};
-
static volatile int workload_exec_errno;
static bool done;
@@ -303,7 +281,7 @@ static int set_tracing_cpumask(struct perf_cpu_map *cpumap)
int ret;
int last_cpu;
- last_cpu = cpu_map__cpu(cpumap, cpumap->nr - 1);
+ last_cpu = perf_cpu_map__cpu(cpumap, perf_cpu_map__nr(cpumap) - 1).cpu;
mask_size = last_cpu / 4 + 2; /* one more byte for EOS */
mask_size += last_cpu / 32; /* ',' is needed for every 32th cpus */
@@ -565,7 +543,24 @@ static int set_tracing_options(struct perf_ftrace *ftrace)
return 0;
}
-static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv)
+static void select_tracer(struct perf_ftrace *ftrace)
+{
+ bool graph = !list_empty(&ftrace->graph_funcs) ||
+ !list_empty(&ftrace->nograph_funcs);
+ bool func = !list_empty(&ftrace->filters) ||
+ !list_empty(&ftrace->notrace);
+
+ /* The function_graph has priority over function tracer. */
+ if (graph)
+ ftrace->tracer = "function_graph";
+ else if (func)
+ ftrace->tracer = "function";
+ /* Otherwise, the default tracer is used. */
+
+ pr_debug("%s tracer is used\n", ftrace->tracer);
+}
+
+static int __cmd_ftrace(struct perf_ftrace *ftrace)
{
char *trace_file;
int trace_fd;
@@ -586,10 +581,7 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv)
return -1;
}
- signal(SIGINT, sig_handler);
- signal(SIGUSR1, sig_handler);
- signal(SIGCHLD, sig_handler);
- signal(SIGPIPE, sig_handler);
+ select_tracer(ftrace);
if (reset_tracing_files(ftrace) < 0) {
pr_err("failed to reset ftrace\n");
@@ -600,11 +592,6 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv)
if (write_tracing_file("trace", "0") < 0)
goto out;
- if (argc && evlist__prepare_workload(ftrace->evlist, &ftrace->target, argv, false,
- ftrace__workload_exec_failed_signal) < 0) {
- goto out;
- }
-
if (set_tracing_options(ftrace) < 0)
goto out_reset;
@@ -693,6 +680,270 @@ out:
return (done && !workload_exec_errno) ? 0 : -1;
}
+static void make_histogram(int buckets[], char *buf, size_t len, char *linebuf)
+{
+ char *p, *q;
+ char *unit;
+ double num;
+ int i;
+
+ /* ensure NUL termination */
+ buf[len] = '\0';
+
+ /* handle data line by line */
+ for (p = buf; (q = strchr(p, '\n')) != NULL; p = q + 1) {
+ *q = '\0';
+ /* move it to the line buffer */
+ strcat(linebuf, p);
+
+ /*
+ * parse trace output to get function duration like in
+ *
+ * # tracer: function_graph
+ * #
+ * # CPU DURATION FUNCTION CALLS
+ * # | | | | | | |
+ * 1) + 10.291 us | do_filp_open();
+ * 1) 4.889 us | do_filp_open();
+ * 1) 6.086 us | do_filp_open();
+ *
+ */
+ if (linebuf[0] == '#')
+ goto next;
+
+ /* ignore CPU */
+ p = strchr(linebuf, ')');
+ if (p == NULL)
+ p = linebuf;
+
+ while (*p && !isdigit(*p) && (*p != '|'))
+ p++;
+
+ /* no duration */
+ if (*p == '\0' || *p == '|')
+ goto next;
+
+ num = strtod(p, &unit);
+ if (!unit || strncmp(unit, " us", 3))
+ goto next;
+
+ i = log2(num);
+ if (i < 0)
+ i = 0;
+ if (i >= NUM_BUCKET)
+ i = NUM_BUCKET - 1;
+
+ buckets[i]++;
+
+next:
+ /* empty the line buffer for the next output */
+ linebuf[0] = '\0';
+ }
+
+ /* preserve any remaining output (before newline) */
+ strcat(linebuf, p);
+}
+
+static void display_histogram(int buckets[])
+{
+ int i;
+ int total = 0;
+ int bar_total = 46; /* to fit in 80 column */
+ char bar[] = "###############################################";
+ int bar_len;
+
+ for (i = 0; i < NUM_BUCKET; i++)
+ total += buckets[i];
+
+ if (total == 0) {
+ printf("No data found\n");
+ return;
+ }
+
+ printf("# %14s | %10s | %-*s |\n",
+ " DURATION ", "COUNT", bar_total, "GRAPH");
+
+ bar_len = buckets[0] * bar_total / total;
+ printf(" %4d - %-4d %s | %10d | %.*s%*s |\n",
+ 0, 1, "us", buckets[0], bar_len, bar, bar_total - bar_len, "");
+
+ for (i = 1; i < NUM_BUCKET - 1; i++) {
+ int start = (1 << (i - 1));
+ int stop = 1 << i;
+ const char *unit = "us";
+
+ if (start >= 1024) {
+ start >>= 10;
+ stop >>= 10;
+ unit = "ms";
+ }
+ bar_len = buckets[i] * bar_total / total;
+ printf(" %4d - %-4d %s | %10d | %.*s%*s |\n",
+ start, stop, unit, buckets[i], bar_len, bar,
+ bar_total - bar_len, "");
+ }
+
+ bar_len = buckets[NUM_BUCKET - 1] * bar_total / total;
+ printf(" %4d - %-4s %s | %10d | %.*s%*s |\n",
+ 1, "...", " s", buckets[NUM_BUCKET - 1], bar_len, bar,
+ bar_total - bar_len, "");
+
+}
+
+static int prepare_func_latency(struct perf_ftrace *ftrace)
+{
+ char *trace_file;
+ int fd;
+
+ if (ftrace->target.use_bpf)
+ return perf_ftrace__latency_prepare_bpf(ftrace);
+
+ if (reset_tracing_files(ftrace) < 0) {
+ pr_err("failed to reset ftrace\n");
+ return -1;
+ }
+
+ /* reset ftrace buffer */
+ if (write_tracing_file("trace", "0") < 0)
+ return -1;
+
+ if (set_tracing_options(ftrace) < 0)
+ return -1;
+
+ /* force to use the function_graph tracer to track duration */
+ if (write_tracing_file("current_tracer", "function_graph") < 0) {
+ pr_err("failed to set current_tracer to function_graph\n");
+ return -1;
+ }
+
+ trace_file = get_tracing_file("trace_pipe");
+ if (!trace_file) {
+ pr_err("failed to open trace_pipe\n");
+ return -1;
+ }
+
+ fd = open(trace_file, O_RDONLY);
+ if (fd < 0)
+ pr_err("failed to open trace_pipe\n");
+
+ put_tracing_file(trace_file);
+ return fd;
+}
+
+static int start_func_latency(struct perf_ftrace *ftrace)
+{
+ if (ftrace->target.use_bpf)
+ return perf_ftrace__latency_start_bpf(ftrace);
+
+ if (write_tracing_file("tracing_on", "1") < 0) {
+ pr_err("can't enable tracing\n");
+ return -1;
+ }
+
+ return 0;
+}
+
+static int stop_func_latency(struct perf_ftrace *ftrace)
+{
+ if (ftrace->target.use_bpf)
+ return perf_ftrace__latency_stop_bpf(ftrace);
+
+ write_tracing_file("tracing_on", "0");
+ return 0;
+}
+
+static int read_func_latency(struct perf_ftrace *ftrace, int buckets[])
+{
+ if (ftrace->target.use_bpf)
+ return perf_ftrace__latency_read_bpf(ftrace, buckets);
+
+ return 0;
+}
+
+static int cleanup_func_latency(struct perf_ftrace *ftrace)
+{
+ if (ftrace->target.use_bpf)
+ return perf_ftrace__latency_cleanup_bpf(ftrace);
+
+ reset_tracing_files(ftrace);
+ return 0;
+}
+
+static int __cmd_latency(struct perf_ftrace *ftrace)
+{
+ int trace_fd;
+ char buf[4096];
+ char line[256];
+ struct pollfd pollfd = {
+ .events = POLLIN,
+ };
+ int buckets[NUM_BUCKET] = { };
+
+ if (!(perf_cap__capable(CAP_PERFMON) ||
+ perf_cap__capable(CAP_SYS_ADMIN))) {
+ pr_err("ftrace only works for %s!\n",
+#ifdef HAVE_LIBCAP_SUPPORT
+ "users with the CAP_PERFMON or CAP_SYS_ADMIN capability"
+#else
+ "root"
+#endif
+ );
+ return -1;
+ }
+
+ trace_fd = prepare_func_latency(ftrace);
+ if (trace_fd < 0)
+ goto out;
+
+ fcntl(trace_fd, F_SETFL, O_NONBLOCK);
+ pollfd.fd = trace_fd;
+
+ if (start_func_latency(ftrace) < 0)
+ goto out;
+
+ evlist__start_workload(ftrace->evlist);
+
+ line[0] = '\0';
+ while (!done) {
+ if (poll(&pollfd, 1, -1) < 0)
+ break;
+
+ if (pollfd.revents & POLLIN) {
+ int n = read(trace_fd, buf, sizeof(buf) - 1);
+ if (n < 0)
+ break;
+
+ make_histogram(buckets, buf, n, line);
+ }
+ }
+
+ stop_func_latency(ftrace);
+
+ if (workload_exec_errno) {
+ const char *emsg = str_error_r(workload_exec_errno, buf, sizeof(buf));
+ pr_err("workload failed: %s\n", emsg);
+ goto out;
+ }
+
+ /* read remaining buffer contents */
+ while (!ftrace->target.use_bpf) {
+ int n = read(trace_fd, buf, sizeof(buf) - 1);
+ if (n <= 0)
+ break;
+ make_histogram(buckets, buf, n, line);
+ }
+
+ read_func_latency(ftrace, buckets);
+
+ display_histogram(buckets);
+
+out:
+ close(trace_fd);
+ cleanup_func_latency(ftrace);
+
+ return (done && !workload_exec_errno) ? 0 : -1;
+}
+
static int perf_ftrace_config(const char *var, const char *value, void *cb)
{
struct perf_ftrace *ftrace = cb;
@@ -855,41 +1106,21 @@ static int parse_graph_tracer_opts(const struct option *opt,
return 0;
}
-static void select_tracer(struct perf_ftrace *ftrace)
-{
- bool graph = !list_empty(&ftrace->graph_funcs) ||
- !list_empty(&ftrace->nograph_funcs);
- bool func = !list_empty(&ftrace->filters) ||
- !list_empty(&ftrace->notrace);
-
- /* The function_graph has priority over function tracer. */
- if (graph)
- ftrace->tracer = "function_graph";
- else if (func)
- ftrace->tracer = "function";
- /* Otherwise, the default tracer is used. */
-
- pr_debug("%s tracer is used\n", ftrace->tracer);
-}
+enum perf_ftrace_subcommand {
+ PERF_FTRACE_NONE,
+ PERF_FTRACE_TRACE,
+ PERF_FTRACE_LATENCY,
+};
int cmd_ftrace(int argc, const char **argv)
{
int ret;
+ int (*cmd_func)(struct perf_ftrace *) = NULL;
struct perf_ftrace ftrace = {
.tracer = DEFAULT_TRACER,
.target = { .uid = UINT_MAX, },
};
- const char * const ftrace_usage[] = {
- "perf ftrace [<options>] [<command>]",
- "perf ftrace [<options>] -- <command> [<options>]",
- NULL
- };
- const struct option ftrace_options[] = {
- OPT_STRING('t', "tracer", &ftrace.tracer, "tracer",
- "Tracer to use: function_graph(default) or function"),
- OPT_CALLBACK_DEFAULT('F', "funcs", NULL, "[FILTER]",
- "Show available functions to filter",
- opt_list_avail_functions, "*"),
+ const struct option common_options[] = {
OPT_STRING('p', "pid", &ftrace.target.pid, "pid",
"Trace on existing process id"),
/* TODO: Add short option -t after -t/--tracer can be removed. */
@@ -901,6 +1132,14 @@ int cmd_ftrace(int argc, const char **argv)
"System-wide collection from all CPUs"),
OPT_STRING('C', "cpu", &ftrace.target.cpu_list, "cpu",
"List of cpus to monitor"),
+ OPT_END()
+ };
+ const struct option ftrace_options[] = {
+ OPT_STRING('t', "tracer", &ftrace.tracer, "tracer",
+ "Tracer to use: function_graph(default) or function"),
+ OPT_CALLBACK_DEFAULT('F', "funcs", NULL, "[FILTER]",
+ "Show available functions to filter",
+ opt_list_avail_functions, "*"),
OPT_CALLBACK('T', "trace-funcs", &ftrace.filters, "func",
"Trace given functions using function tracer",
parse_filter_func),
@@ -923,24 +1162,87 @@ int cmd_ftrace(int argc, const char **argv)
"Trace children processes"),
OPT_UINTEGER('D', "delay", &ftrace.initial_delay,
"Number of milliseconds to wait before starting tracing after program start"),
- OPT_END()
+ OPT_PARENT(common_options),
+ };
+ const struct option latency_options[] = {
+ OPT_CALLBACK('T', "trace-funcs", &ftrace.filters, "func",
+ "Show latency of given function", parse_filter_func),
+#ifdef HAVE_BPF_SKEL
+ OPT_BOOLEAN('b', "use-bpf", &ftrace.target.use_bpf,
+ "Use BPF to measure function latency"),
+#endif
+ OPT_PARENT(common_options),
+ };
+ const struct option *options = ftrace_options;
+
+ const char * const ftrace_usage[] = {
+ "perf ftrace [<options>] [<command>]",
+ "perf ftrace [<options>] -- [<command>] [<options>]",
+ "perf ftrace {trace|latency} [<options>] [<command>]",
+ "perf ftrace {trace|latency} [<options>] -- [<command>] [<options>]",
+ NULL
};
+ enum perf_ftrace_subcommand subcmd = PERF_FTRACE_NONE;
INIT_LIST_HEAD(&ftrace.filters);
INIT_LIST_HEAD(&ftrace.notrace);
INIT_LIST_HEAD(&ftrace.graph_funcs);
INIT_LIST_HEAD(&ftrace.nograph_funcs);
+ signal(SIGINT, sig_handler);
+ signal(SIGUSR1, sig_handler);
+ signal(SIGCHLD, sig_handler);
+ signal(SIGPIPE, sig_handler);
+
ret = perf_config(perf_ftrace_config, &ftrace);
if (ret < 0)
return -1;
- argc = parse_options(argc, argv, ftrace_options, ftrace_usage,
+ if (argc > 1) {
+ if (!strcmp(argv[1], "trace")) {
+ subcmd = PERF_FTRACE_TRACE;
+ } else if (!strcmp(argv[1], "latency")) {
+ subcmd = PERF_FTRACE_LATENCY;
+ options = latency_options;
+ }
+
+ if (subcmd != PERF_FTRACE_NONE) {
+ argc--;
+ argv++;
+ }
+ }
+ /* for backward compatibility */
+ if (subcmd == PERF_FTRACE_NONE)
+ subcmd = PERF_FTRACE_TRACE;
+
+ argc = parse_options(argc, argv, options, ftrace_usage,
PARSE_OPT_STOP_AT_NON_OPTION);
- if (!argc && target__none(&ftrace.target))
- ftrace.target.system_wide = true;
+ if (argc < 0) {
+ ret = -EINVAL;
+ goto out_delete_filters;
+ }
- select_tracer(&ftrace);
+ switch (subcmd) {
+ case PERF_FTRACE_TRACE:
+ if (!argc && target__none(&ftrace.target))
+ ftrace.target.system_wide = true;
+ cmd_func = __cmd_ftrace;
+ break;
+ case PERF_FTRACE_LATENCY:
+ if (list_empty(&ftrace.filters)) {
+ pr_err("Should provide a function to measure\n");
+ parse_options_usage(ftrace_usage, options, "T", 1);
+ ret = -EINVAL;
+ goto out_delete_filters;
+ }
+ cmd_func = __cmd_latency;
+ break;
+ case PERF_FTRACE_NONE:
+ default:
+ pr_err("Invalid subcommand\n");
+ ret = -EINVAL;
+ goto out_delete_filters;
+ }
ret = target__validate(&ftrace.target);
if (ret) {
@@ -961,7 +1263,15 @@ int cmd_ftrace(int argc, const char **argv)
if (ret < 0)
goto out_delete_evlist;
- ret = __cmd_ftrace(&ftrace, argc, argv);
+ if (argc) {
+ ret = evlist__prepare_workload(ftrace.evlist, &ftrace.target,
+ argv, false,
+ ftrace__workload_exec_failed_signal);
+ if (ret < 0)
+ goto out_delete_evlist;
+ }
+
+ ret = cmd_func(&ftrace);
out_delete_evlist:
evlist__delete(ftrace.evlist);
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 409b721666cb..fbf43a454cba 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -535,12 +535,9 @@ static int perf_event__repipe_exit(struct perf_tool *tool,
static int perf_event__repipe_tracing_data(struct perf_session *session,
union perf_event *event)
{
- int err;
-
perf_event__repipe_synth(session->tool, event);
- err = perf_event__process_tracing_data(session, event);
- return err;
+ return perf_event__process_tracing_data(session, event);
}
static int dso__read_build_id(struct dso *dso)
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index da03a341c63c..99d7ff9a8eff 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -192,7 +192,7 @@ static int evsel__process_alloc_node_event(struct evsel *evsel, struct perf_samp
int ret = evsel__process_alloc_event(evsel, sample);
if (!ret) {
- int node1 = cpu__get_node(sample->cpu),
+ int node1 = cpu__get_node((struct perf_cpu){.cpu = sample->cpu}),
node2 = evsel__intval(evsel, sample, "node");
if (node1 != node2)
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 0338b813585a..bb716c953d02 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -111,6 +111,7 @@ struct record {
unsigned long long samples;
struct mmap_cpu_mask affinity_mask;
unsigned long output_max_size; /* = 0: unlimited */
+ struct perf_debuginfod debuginfod;
};
static volatile int done;
@@ -2177,6 +2178,12 @@ static int perf_record_config(const char *var, const char *value, void *cb)
rec->opts.nr_cblocks = nr_cblocks_default;
}
#endif
+ if (!strcmp(var, "record.debuginfod")) {
+ rec->debuginfod.urls = strdup(value);
+ if (!rec->debuginfod.urls)
+ return -ENOMEM;
+ rec->debuginfod.set = true;
+ }
return 0;
}
@@ -2267,6 +2274,10 @@ out_free:
return ret;
}
+void __weak arch__add_leaf_frame_record_opts(struct record_opts *opts __maybe_unused)
+{
+}
+
static int parse_control_option(const struct option *opt,
const char *str,
int unset __maybe_unused)
@@ -2663,6 +2674,10 @@ static struct option __record_options[] = {
parse_control_option),
OPT_CALLBACK(0, "synth", &record.opts, "no|all|task|mmap|cgroup",
"Fine-tune event synthesis: default=all", parse_record_synth_option),
+ OPT_STRING_OPTARG_SET(0, "debuginfod", &record.debuginfod.urls,
+ &record.debuginfod.set, "debuginfod urls",
+ "Enable debuginfod data retrieval from DEBUGINFOD_URLS or specified urls",
+ "system"),
OPT_END()
};
@@ -2716,6 +2731,8 @@ int cmd_record(int argc, const char **argv)
if (err)
return err;
+ perf_debuginfod_setup(&record.debuginfod);
+
/* Make system wide (-a) the default target. */
if (!argc && target__none(&rec->opts.target))
rec->opts.target.system_wide = true;
@@ -2792,7 +2809,7 @@ int cmd_record(int argc, const char **argv)
symbol__init(NULL);
if (rec->opts.affinity != PERF_AFFINITY_SYS) {
- rec->affinity_mask.nbits = cpu__max_cpu();
+ rec->affinity_mask.nbits = cpu__max_cpu().cpu;
rec->affinity_mask.bits = bitmap_zalloc(rec->affinity_mask.nbits);
if (!rec->affinity_mask.bits) {
pr_err("Failed to allocate thread mask for %zd cpus\n", rec->affinity_mask.nbits);
@@ -2898,6 +2915,10 @@ int cmd_record(int argc, const char **argv)
}
rec->opts.target.hybrid = perf_pmu__has_hybrid();
+
+ if (callchain_param.enabled && callchain_param.record_mode == CALLCHAIN_FP)
+ arch__add_leaf_frame_record_opts(&rec->opts);
+
err = -ENOMEM;
if (evlist__create_maps(rec->evlist, &rec->opts.target) < 0)
usage_with_options(record_usage, record_options);
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 8ae400429870..1dd92d8c9279 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -410,7 +410,7 @@ static int report__setup_sample_type(struct report *rep)
}
}
- callchain_param_setup(sample_type);
+ callchain_param_setup(sample_type, perf_env__arch(&rep->session->header.env));
if (rep->stitch_lbr && (callchain_param.record_mode != CALLCHAIN_LBR)) {
ui__warning("Can't find LBR callchain. Switch off --stitch-lbr.\n"
@@ -1127,7 +1127,7 @@ static int process_attr(struct perf_tool *tool __maybe_unused,
* on events sample_type.
*/
sample_type = evlist__combined_sample_type(*pevlist);
- callchain_param_setup(sample_type);
+ callchain_param_setup(sample_type, perf_env__arch((*pevlist)->env));
return 0;
}
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 4527f632ebe4..72d446de9c60 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -167,7 +167,7 @@ struct trace_sched_handler {
struct perf_sched_map {
DECLARE_BITMAP(comp_cpus_mask, MAX_CPUS);
- int *comp_cpus;
+ struct perf_cpu *comp_cpus;
bool comp;
struct perf_thread_map *color_pids;
const char *color_pids_str;
@@ -191,7 +191,7 @@ struct perf_sched {
* Track the current task - that way we can know whether there's any
* weird events, such as a task being switched away that is not current.
*/
- int max_cpu;
+ struct perf_cpu max_cpu;
u32 curr_pid[MAX_CPUS];
struct thread *curr_thread[MAX_CPUS];
char next_shortname1;
@@ -1535,28 +1535,31 @@ static int map_switch_event(struct perf_sched *sched, struct evsel *evsel,
int new_shortname;
u64 timestamp0, timestamp = sample->time;
s64 delta;
- int i, this_cpu = sample->cpu;
+ int i;
+ struct perf_cpu this_cpu = {
+ .cpu = sample->cpu,
+ };
int cpus_nr;
bool new_cpu = false;
const char *color = PERF_COLOR_NORMAL;
char stimestamp[32];
- BUG_ON(this_cpu >= MAX_CPUS || this_cpu < 0);
+ BUG_ON(this_cpu.cpu >= MAX_CPUS || this_cpu.cpu < 0);
- if (this_cpu > sched->max_cpu)
+ if (this_cpu.cpu > sched->max_cpu.cpu)
sched->max_cpu = this_cpu;
if (sched->map.comp) {
cpus_nr = bitmap_weight(sched->map.comp_cpus_mask, MAX_CPUS);
- if (!test_and_set_bit(this_cpu, sched->map.comp_cpus_mask)) {
+ if (!test_and_set_bit(this_cpu.cpu, sched->map.comp_cpus_mask)) {
sched->map.comp_cpus[cpus_nr++] = this_cpu;
new_cpu = true;
}
} else
- cpus_nr = sched->max_cpu;
+ cpus_nr = sched->max_cpu.cpu;
- timestamp0 = sched->cpu_last_switched[this_cpu];
- sched->cpu_last_switched[this_cpu] = timestamp;
+ timestamp0 = sched->cpu_last_switched[this_cpu.cpu];
+ sched->cpu_last_switched[this_cpu.cpu] = timestamp;
if (timestamp0)
delta = timestamp - timestamp0;
else
@@ -1577,7 +1580,7 @@ static int map_switch_event(struct perf_sched *sched, struct evsel *evsel,
return -1;
}
- sched->curr_thread[this_cpu] = thread__get(sched_in);
+ sched->curr_thread[this_cpu.cpu] = thread__get(sched_in);
printf(" ");
@@ -1608,8 +1611,10 @@ static int map_switch_event(struct perf_sched *sched, struct evsel *evsel,
}
for (i = 0; i < cpus_nr; i++) {
- int cpu = sched->map.comp ? sched->map.comp_cpus[i] : i;
- struct thread *curr_thread = sched->curr_thread[cpu];
+ struct perf_cpu cpu = {
+ .cpu = sched->map.comp ? sched->map.comp_cpus[i].cpu : i,
+ };
+ struct thread *curr_thread = sched->curr_thread[cpu.cpu];
struct thread_runtime *curr_tr;
const char *pid_color = color;
const char *cpu_color = color;
@@ -1617,19 +1622,19 @@ static int map_switch_event(struct perf_sched *sched, struct evsel *evsel,
if (curr_thread && thread__has_color(curr_thread))
pid_color = COLOR_PIDS;
- if (sched->map.cpus && !cpu_map__has(sched->map.cpus, cpu))
+ if (sched->map.cpus && !perf_cpu_map__has(sched->map.cpus, cpu))
continue;
- if (sched->map.color_cpus && cpu_map__has(sched->map.color_cpus, cpu))
+ if (sched->map.color_cpus && perf_cpu_map__has(sched->map.color_cpus, cpu))
cpu_color = COLOR_CPUS;
- if (cpu != this_cpu)
+ if (cpu.cpu != this_cpu.cpu)
color_fprintf(stdout, color, " ");
else
color_fprintf(stdout, cpu_color, "*");
- if (sched->curr_thread[cpu]) {
- curr_tr = thread__get_runtime(sched->curr_thread[cpu]);
+ if (sched->curr_thread[cpu.cpu]) {
+ curr_tr = thread__get_runtime(sched->curr_thread[cpu.cpu]);
if (curr_tr == NULL) {
thread__put(sched_in);
return -1;
@@ -1639,7 +1644,7 @@ static int map_switch_event(struct perf_sched *sched, struct evsel *evsel,
color_fprintf(stdout, color, " ");
}
- if (sched->map.cpus && !cpu_map__has(sched->map.cpus, this_cpu))
+ if (sched->map.cpus && !perf_cpu_map__has(sched->map.cpus, this_cpu))
goto out;
timestamp__scnprintf_usec(timestamp, stimestamp, sizeof(stimestamp));
@@ -1929,7 +1934,7 @@ static char *timehist_get_commstr(struct thread *thread)
static void timehist_header(struct perf_sched *sched)
{
- u32 ncpus = sched->max_cpu + 1;
+ u32 ncpus = sched->max_cpu.cpu + 1;
u32 i, j;
printf("%15s %6s ", "time", "cpu");
@@ -2008,7 +2013,7 @@ static void timehist_print_sample(struct perf_sched *sched,
struct thread_runtime *tr = thread__priv(thread);
const char *next_comm = evsel__strval(evsel, sample, "next_comm");
const u32 next_pid = evsel__intval(evsel, sample, "next_pid");
- u32 max_cpus = sched->max_cpu + 1;
+ u32 max_cpus = sched->max_cpu.cpu + 1;
char tstr[64];
char nstr[30];
u64 wait_time;
@@ -2389,7 +2394,7 @@ static void timehist_print_wakeup_event(struct perf_sched *sched,
timestamp__scnprintf_usec(sample->time, tstr, sizeof(tstr));
printf("%15s [%04d] ", tstr, sample->cpu);
if (sched->show_cpu_visual)
- printf(" %*s ", sched->max_cpu + 1, "");
+ printf(" %*s ", sched->max_cpu.cpu + 1, "");
printf(" %-*s ", comm_width, timehist_get_commstr(thread));
@@ -2449,13 +2454,13 @@ static void timehist_print_migration_event(struct perf_sched *sched,
{
struct thread *thread;
char tstr[64];
- u32 max_cpus = sched->max_cpu + 1;
+ u32 max_cpus;
u32 ocpu, dcpu;
if (sched->summary_only)
return;
- max_cpus = sched->max_cpu + 1;
+ max_cpus = sched->max_cpu.cpu + 1;
ocpu = evsel__intval(evsel, sample, "orig_cpu");
dcpu = evsel__intval(evsel, sample, "dest_cpu");
@@ -2918,7 +2923,7 @@ static void timehist_print_summary(struct perf_sched *sched,
printf(" Total scheduling time (msec): ");
print_sched_time(hist_time, 2);
- printf(" (x %d)\n", sched->max_cpu);
+ printf(" (x %d)\n", sched->max_cpu.cpu);
}
typedef int (*sched_handler)(struct perf_tool *tool,
@@ -2935,9 +2940,11 @@ static int perf_timehist__process_sample(struct perf_tool *tool,
{
struct perf_sched *sched = container_of(tool, struct perf_sched, tool);
int err = 0;
- int this_cpu = sample->cpu;
+ struct perf_cpu this_cpu = {
+ .cpu = sample->cpu,
+ };
- if (this_cpu > sched->max_cpu)
+ if (this_cpu.cpu > sched->max_cpu.cpu)
sched->max_cpu = this_cpu;
if (evsel->handler != NULL) {
@@ -3054,10 +3061,10 @@ static int perf_sched__timehist(struct perf_sched *sched)
goto out;
/* pre-allocate struct for per-CPU idle stats */
- sched->max_cpu = session->header.env.nr_cpus_online;
- if (sched->max_cpu == 0)
- sched->max_cpu = 4;
- if (init_idle_threads(sched->max_cpu))
+ sched->max_cpu.cpu = session->header.env.nr_cpus_online;
+ if (sched->max_cpu.cpu == 0)
+ sched->max_cpu.cpu = 4;
+ if (init_idle_threads(sched->max_cpu.cpu))
goto out;
/* summary_only implies summary option, but don't overwrite summary if set */
@@ -3209,10 +3216,10 @@ static int setup_map_cpus(struct perf_sched *sched)
{
struct perf_cpu_map *map;
- sched->max_cpu = sysconf(_SC_NPROCESSORS_CONF);
+ sched->max_cpu.cpu = sysconf(_SC_NPROCESSORS_CONF);
if (sched->map.comp) {
- sched->map.comp_cpus = zalloc(sched->max_cpu * sizeof(int));
+ sched->map.comp_cpus = zalloc(sched->max_cpu.cpu * sizeof(int));
if (!sched->map.comp_cpus)
return -1;
}
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index c82b033e8942..fa478ddcd18a 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -15,6 +15,7 @@
#include "util/symbol.h"
#include "util/thread.h"
#include "util/trace-event.h"
+#include "util/env.h"
#include "util/evlist.h"
#include "util/evsel.h"
#include "util/evsel_fprintf.h"
@@ -462,7 +463,7 @@ static int evsel__check_attr(struct evsel *evsel, struct perf_session *session)
return -EINVAL;
if (PRINT_FIELD(WEIGHT) &&
- evsel__check_stype(evsel, PERF_SAMPLE_WEIGHT_TYPE, "WEIGHT", PERF_OUTPUT_WEIGHT))
+ evsel__do_check_stype(evsel, PERF_SAMPLE_WEIGHT_TYPE, "WEIGHT", PERF_OUTPUT_WEIGHT, allow_user_set))
return -EINVAL;
if (PRINT_FIELD(SYM) &&
@@ -514,7 +515,7 @@ static int evsel__check_attr(struct evsel *evsel, struct perf_session *session)
return -EINVAL;
if (PRINT_FIELD(PHYS_ADDR) &&
- evsel__check_stype(evsel, PERF_SAMPLE_PHYS_ADDR, "PHYS_ADDR", PERF_OUTPUT_PHYS_ADDR))
+ evsel__do_check_stype(evsel, PERF_SAMPLE_PHYS_ADDR, "PHYS_ADDR", PERF_OUTPUT_PHYS_ADDR, allow_user_set))
return -EINVAL;
if (PRINT_FIELD(DATA_PAGE_SIZE) &&
@@ -648,7 +649,7 @@ out:
return 0;
}
-static int perf_sample__fprintf_regs(struct regs_dump *regs, uint64_t mask,
+static int perf_sample__fprintf_regs(struct regs_dump *regs, uint64_t mask, const char *arch,
FILE *fp)
{
unsigned i = 0, r;
@@ -661,7 +662,7 @@ static int perf_sample__fprintf_regs(struct regs_dump *regs, uint64_t mask,
for_each_set_bit(r, (unsigned long *) &mask, sizeof(mask) * 8) {
u64 val = regs->regs[i++];
- printed += fprintf(fp, "%5s:0x%"PRIx64" ", perf_reg_name(r), val);
+ printed += fprintf(fp, "%5s:0x%"PRIx64" ", perf_reg_name(r, arch), val);
}
return printed;
@@ -718,17 +719,17 @@ tod_scnprintf(struct perf_script *script, char *buf, int buflen,
}
static int perf_sample__fprintf_iregs(struct perf_sample *sample,
- struct perf_event_attr *attr, FILE *fp)
+ struct perf_event_attr *attr, const char *arch, FILE *fp)
{
return perf_sample__fprintf_regs(&sample->intr_regs,
- attr->sample_regs_intr, fp);
+ attr->sample_regs_intr, arch, fp);
}
static int perf_sample__fprintf_uregs(struct perf_sample *sample,
- struct perf_event_attr *attr, FILE *fp)
+ struct perf_event_attr *attr, const char *arch, FILE *fp)
{
return perf_sample__fprintf_regs(&sample->user_regs,
- attr->sample_regs_user, fp);
+ attr->sample_regs_user, arch, fp);
}
static int perf_sample__fprintf_start(struct perf_script *script,
@@ -2000,6 +2001,7 @@ static void process_event(struct perf_script *script,
struct evsel_script *es = evsel->priv;
FILE *fp = es->fp;
char str[PAGE_SIZE_NAME_LEN];
+ const char *arch = perf_env__arch(machine->env);
if (output[type].fields == 0)
return;
@@ -2066,10 +2068,10 @@ static void process_event(struct perf_script *script,
}
if (PRINT_FIELD(IREGS))
- perf_sample__fprintf_iregs(sample, attr, fp);
+ perf_sample__fprintf_iregs(sample, attr, arch, fp);
if (PRINT_FIELD(UREGS))
- perf_sample__fprintf_uregs(sample, attr, fp);
+ perf_sample__fprintf_uregs(sample, attr, arch, fp);
if (PRINT_FIELD(BRSTACK))
perf_sample__fprintf_brstack(sample, thread, attr, fp);
@@ -2113,8 +2115,8 @@ static struct scripting_ops *scripting_ops;
static void __process_stat(struct evsel *counter, u64 tstamp)
{
int nthreads = perf_thread_map__nr(counter->core.threads);
- int ncpus = evsel__nr_cpus(counter);
- int cpu, thread;
+ int idx, thread;
+ struct perf_cpu cpu;
static int header_printed;
if (counter->core.system_wide)
@@ -2127,13 +2129,13 @@ static void __process_stat(struct evsel *counter, u64 tstamp)
}
for (thread = 0; thread < nthreads; thread++) {
- for (cpu = 0; cpu < ncpus; cpu++) {
+ perf_cpu_map__for_each_cpu(cpu, idx, evsel__cpus(counter)) {
struct perf_counts_values *counts;
- counts = perf_counts(counter->counts, cpu, thread);
+ counts = perf_counts(counter->counts, idx, thread);
printf("%3d %8d %15" PRIu64 " %15" PRIu64 " %15" PRIu64 " %15" PRIu64 " %s\n",
- counter->core.cpus->map[cpu],
+ cpu.cpu,
perf_thread_map__pid(counter->core.threads, thread),
counts->val,
counts->ena,
@@ -2316,7 +2318,7 @@ static int process_attr(struct perf_tool *tool, union perf_event *event,
* on events sample_type.
*/
sample_type = evlist__combined_sample_type(evlist);
- callchain_param_setup(sample_type);
+ callchain_param_setup(sample_type, perf_env__arch((*pevlist)->env));
/* Enable fields for callchain entries */
if (symbol_conf.use_callchain &&
@@ -3466,16 +3468,7 @@ static void script__setup_sample_type(struct perf_script *script)
struct perf_session *session = script->session;
u64 sample_type = evlist__combined_sample_type(session->evlist);
- if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain) {
- if ((sample_type & PERF_SAMPLE_REGS_USER) &&
- (sample_type & PERF_SAMPLE_STACK_USER)) {
- callchain_param.record_mode = CALLCHAIN_DWARF;
- dwarf_callchain_users = true;
- } else if (sample_type & PERF_SAMPLE_BRANCH_STACK)
- callchain_param.record_mode = CALLCHAIN_LBR;
- else
- callchain_param.record_mode = CALLCHAIN_FP;
- }
+ callchain_param_setup(sample_type, perf_env__arch(session->machines.host.env));
if (script->stitch_lbr && (callchain_param.record_mode != CALLCHAIN_LBR)) {
pr_warning("Can't find LBR callchain. Switch off --stitch-lbr.\n"
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 7974933dbc77..3f98689dd687 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -230,11 +230,12 @@ static bool cpus_map_matched(struct evsel *a, struct evsel *b)
if (!a->core.cpus || !b->core.cpus)
return false;
- if (a->core.cpus->nr != b->core.cpus->nr)
+ if (perf_cpu_map__nr(a->core.cpus) != perf_cpu_map__nr(b->core.cpus))
return false;
- for (int i = 0; i < a->core.cpus->nr; i++) {
- if (a->core.cpus->map[i] != b->core.cpus->map[i])
+ for (int i = 0; i < perf_cpu_map__nr(a->core.cpus); i++) {
+ if (perf_cpu_map__cpu(a->core.cpus, i).cpu !=
+ perf_cpu_map__cpu(b->core.cpus, i).cpu)
return false;
}
@@ -327,34 +328,35 @@ static int write_stat_round_event(u64 tm, u64 type)
#define SID(e, x, y) xyarray__entry(e->core.sample_id, x, y)
-static int evsel__write_stat_event(struct evsel *counter, u32 cpu, u32 thread,
+static int evsel__write_stat_event(struct evsel *counter, int cpu_map_idx, u32 thread,
struct perf_counts_values *count)
{
- struct perf_sample_id *sid = SID(counter, cpu, thread);
+ struct perf_sample_id *sid = SID(counter, cpu_map_idx, thread);
+ struct perf_cpu cpu = perf_cpu_map__cpu(evsel__cpus(counter), cpu_map_idx);
return perf_event__synthesize_stat(NULL, cpu, thread, sid->id, count,
process_synthesized_event, NULL);
}
-static int read_single_counter(struct evsel *counter, int cpu,
+static int read_single_counter(struct evsel *counter, int cpu_map_idx,
int thread, struct timespec *rs)
{
if (counter->tool_event == PERF_TOOL_DURATION_TIME) {
u64 val = rs->tv_nsec + rs->tv_sec*1000000000ULL;
struct perf_counts_values *count =
- perf_counts(counter->counts, cpu, thread);
+ perf_counts(counter->counts, cpu_map_idx, thread);
count->ena = count->run = val;
count->val = val;
return 0;
}
- return evsel__read_counter(counter, cpu, thread);
+ return evsel__read_counter(counter, cpu_map_idx, thread);
}
/*
* Read out the results of a single counter:
* do not aggregate counts across CPUs in system-wide mode
*/
-static int read_counter_cpu(struct evsel *counter, struct timespec *rs, int cpu)
+static int read_counter_cpu(struct evsel *counter, struct timespec *rs, int cpu_map_idx)
{
int nthreads = perf_thread_map__nr(evsel_list->core.threads);
int thread;
@@ -368,24 +370,24 @@ static int read_counter_cpu(struct evsel *counter, struct timespec *rs, int cpu)
for (thread = 0; thread < nthreads; thread++) {
struct perf_counts_values *count;
- count = perf_counts(counter->counts, cpu, thread);
+ count = perf_counts(counter->counts, cpu_map_idx, thread);
/*
* The leader's group read loads data into its group members
* (via evsel__read_counter()) and sets their count->loaded.
*/
- if (!perf_counts__is_loaded(counter->counts, cpu, thread) &&
- read_single_counter(counter, cpu, thread, rs)) {
+ if (!perf_counts__is_loaded(counter->counts, cpu_map_idx, thread) &&
+ read_single_counter(counter, cpu_map_idx, thread, rs)) {
counter->counts->scaled = -1;
- perf_counts(counter->counts, cpu, thread)->ena = 0;
- perf_counts(counter->counts, cpu, thread)->run = 0;
+ perf_counts(counter->counts, cpu_map_idx, thread)->ena = 0;
+ perf_counts(counter->counts, cpu_map_idx, thread)->run = 0;
return -1;
}
- perf_counts__set_loaded(counter->counts, cpu, thread, false);
+ perf_counts__set_loaded(counter->counts, cpu_map_idx, thread, false);
if (STAT_RECORD) {
- if (evsel__write_stat_event(counter, cpu, thread, count)) {
+ if (evsel__write_stat_event(counter, cpu_map_idx, thread, count)) {
pr_err("failed to write stat event\n");
return -1;
}
@@ -395,7 +397,8 @@ static int read_counter_cpu(struct evsel *counter, struct timespec *rs, int cpu)
fprintf(stat_config.output,
"%s: %d: %" PRIu64 " %" PRIu64 " %" PRIu64 "\n",
evsel__name(counter),
- cpu,
+ perf_cpu_map__cpu(evsel__cpus(counter),
+ cpu_map_idx).cpu,
count->val, count->ena, count->run);
}
}
@@ -405,36 +408,33 @@ static int read_counter_cpu(struct evsel *counter, struct timespec *rs, int cpu)
static int read_affinity_counters(struct timespec *rs)
{
- struct evsel *counter;
- struct affinity affinity;
- int i, ncpus, cpu;
+ struct evlist_cpu_iterator evlist_cpu_itr;
+ struct affinity saved_affinity, *affinity;
if (all_counters_use_bpf)
return 0;
- if (affinity__setup(&affinity) < 0)
+ if (!target__has_cpu(&target) || target__has_per_thread(&target))
+ affinity = NULL;
+ else if (affinity__setup(&saved_affinity) < 0)
return -1;
+ else
+ affinity = &saved_affinity;
- ncpus = perf_cpu_map__nr(evsel_list->core.all_cpus);
- if (!target__has_cpu(&target) || target__has_per_thread(&target))
- ncpus = 1;
- evlist__for_each_cpu(evsel_list, i, cpu) {
- if (i >= ncpus)
- break;
- affinity__set(&affinity, cpu);
+ evlist__for_each_cpu(evlist_cpu_itr, evsel_list, affinity) {
+ struct evsel *counter = evlist_cpu_itr.evsel;
- evlist__for_each_entry(evsel_list, counter) {
- if (evsel__cpu_iter_skip(counter, cpu))
- continue;
- if (evsel__is_bpf(counter))
- continue;
- if (!counter->err) {
- counter->err = read_counter_cpu(counter, rs,
- counter->cpu_iter - 1);
- }
+ if (evsel__is_bpf(counter))
+ continue;
+
+ if (!counter->err) {
+ counter->err = read_counter_cpu(counter, rs,
+ evlist_cpu_itr.cpu_map_idx);
}
}
- affinity__cleanup(&affinity);
+ if (affinity)
+ affinity__cleanup(&saved_affinity);
+
return 0;
}
@@ -788,8 +788,9 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
int status = 0;
const bool forks = (argc > 0);
bool is_pipe = STAT_RECORD ? perf_stat.data.is_pipe : false;
- struct affinity affinity;
- int i, cpu, err;
+ struct evlist_cpu_iterator evlist_cpu_itr;
+ struct affinity saved_affinity, *affinity = NULL;
+ int err;
bool second_pass = false;
if (forks) {
@@ -803,8 +804,11 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
if (group)
evlist__set_leader(evsel_list);
- if (affinity__setup(&affinity) < 0)
- return -1;
+ if (!cpu_map__is_dummy(evsel_list->core.cpus)) {
+ if (affinity__setup(&saved_affinity) < 0)
+ return -1;
+ affinity = &saved_affinity;
+ }
evlist__for_each_entry(evsel_list, counter) {
if (bpf_counter__load(counter, &target))
@@ -813,103 +817,98 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
all_counters_use_bpf = false;
}
- evlist__for_each_cpu (evsel_list, i, cpu) {
+ evlist__for_each_cpu(evlist_cpu_itr, evsel_list, affinity) {
+ counter = evlist_cpu_itr.evsel;
+
/*
* bperf calls evsel__open_per_cpu() in bperf__load(), so
* no need to call it again here.
*/
if (target.use_bpf)
break;
- affinity__set(&affinity, cpu);
- evlist__for_each_entry(evsel_list, counter) {
- if (evsel__cpu_iter_skip(counter, cpu))
+ if (counter->reset_group || counter->errored)
+ continue;
+ if (evsel__is_bpf(counter))
+ continue;
+try_again:
+ if (create_perf_stat_counter(counter, &stat_config, &target,
+ evlist_cpu_itr.cpu_map_idx) < 0) {
+
+ /*
+ * Weak group failed. We cannot just undo this here
+ * because earlier CPUs might be in group mode, and the kernel
+ * doesn't support mixing group and non group reads. Defer
+ * it to later.
+ * Don't close here because we're in the wrong affinity.
+ */
+ if ((errno == EINVAL || errno == EBADF) &&
+ evsel__leader(counter) != counter &&
+ counter->weak_group) {
+ evlist__reset_weak_group(evsel_list, counter, false);
+ assert(counter->reset_group);
+ second_pass = true;
continue;
- if (counter->reset_group || counter->errored)
+ }
+
+ switch (stat_handle_error(counter)) {
+ case COUNTER_FATAL:
+ return -1;
+ case COUNTER_RETRY:
+ goto try_again;
+ case COUNTER_SKIP:
continue;
- if (evsel__is_bpf(counter))
+ default:
+ break;
+ }
+
+ }
+ counter->supported = true;
+ }
+
+ if (second_pass) {
+ /*
+ * Now redo all the weak group after closing them,
+ * and also close errored counters.
+ */
+
+ /* First close errored or weak retry */
+ evlist__for_each_cpu(evlist_cpu_itr, evsel_list, affinity) {
+ counter = evlist_cpu_itr.evsel;
+
+ if (!counter->reset_group && !counter->errored)
continue;
-try_again:
+
+ perf_evsel__close_cpu(&counter->core, evlist_cpu_itr.cpu_map_idx);
+ }
+ /* Now reopen weak */
+ evlist__for_each_cpu(evlist_cpu_itr, evsel_list, affinity) {
+ counter = evlist_cpu_itr.evsel;
+
+ if (!counter->reset_group && !counter->errored)
+ continue;
+ if (!counter->reset_group)
+ continue;
+try_again_reset:
+ pr_debug2("reopening weak %s\n", evsel__name(counter));
if (create_perf_stat_counter(counter, &stat_config, &target,
- counter->cpu_iter - 1) < 0) {
-
- /*
- * Weak group failed. We cannot just undo this here
- * because earlier CPUs might be in group mode, and the kernel
- * doesn't support mixing group and non group reads. Defer
- * it to later.
- * Don't close here because we're in the wrong affinity.
- */
- if ((errno == EINVAL || errno == EBADF) &&
- evsel__leader(counter) != counter &&
- counter->weak_group) {
- evlist__reset_weak_group(evsel_list, counter, false);
- assert(counter->reset_group);
- second_pass = true;
- continue;
- }
+ evlist_cpu_itr.cpu_map_idx) < 0) {
switch (stat_handle_error(counter)) {
case COUNTER_FATAL:
return -1;
case COUNTER_RETRY:
- goto try_again;
+ goto try_again_reset;
case COUNTER_SKIP:
continue;
default:
break;
}
-
}
counter->supported = true;
}
}
-
- if (second_pass) {
- /*
- * Now redo all the weak group after closing them,
- * and also close errored counters.
- */
-
- evlist__for_each_cpu(evsel_list, i, cpu) {
- affinity__set(&affinity, cpu);
- /* First close errored or weak retry */
- evlist__for_each_entry(evsel_list, counter) {
- if (!counter->reset_group && !counter->errored)
- continue;
- if (evsel__cpu_iter_skip_no_inc(counter, cpu))
- continue;
- perf_evsel__close_cpu(&counter->core, counter->cpu_iter);
- }
- /* Now reopen weak */
- evlist__for_each_entry(evsel_list, counter) {
- if (!counter->reset_group && !counter->errored)
- continue;
- if (evsel__cpu_iter_skip(counter, cpu))
- continue;
- if (!counter->reset_group)
- continue;
-try_again_reset:
- pr_debug2("reopening weak %s\n", evsel__name(counter));
- if (create_perf_stat_counter(counter, &stat_config, &target,
- counter->cpu_iter - 1) < 0) {
-
- switch (stat_handle_error(counter)) {
- case COUNTER_FATAL:
- return -1;
- case COUNTER_RETRY:
- goto try_again_reset;
- case COUNTER_SKIP:
- continue;
- default:
- break;
- }
- }
- counter->supported = true;
- }
- }
- }
- affinity__cleanup(&affinity);
+ affinity__cleanup(affinity);
evlist__for_each_entry(evsel_list, counter) {
if (!counter->supported) {
@@ -1168,6 +1167,26 @@ static int parse_stat_cgroups(const struct option *opt,
return parse_cgroups(opt, str, unset);
}
+static int parse_hybrid_type(const struct option *opt,
+ const char *str,
+ int unset __maybe_unused)
+{
+ struct evlist *evlist = *(struct evlist **)opt->value;
+
+ if (!list_empty(&evlist->core.entries)) {
+ fprintf(stderr, "Must define cputype before events/metrics\n");
+ return -1;
+ }
+
+ evlist->hybrid_pmu_name = perf_pmu__hybrid_type_to_pmu(str);
+ if (!evlist->hybrid_pmu_name) {
+ fprintf(stderr, "--cputype %s is not supported!\n", str);
+ return -1;
+ }
+
+ return 0;
+}
+
static struct option stat_options[] = {
OPT_BOOLEAN('T', "transaction", &transaction_run,
"hardware transaction statistics"),
@@ -1282,6 +1301,10 @@ static struct option stat_options[] = {
"don't print 'summary' for CSV summary output"),
OPT_BOOLEAN(0, "quiet", &stat_config.quiet,
"don't print output (useful with record)"),
+ OPT_CALLBACK(0, "cputype", &evsel_list, "hybrid cpu type",
+ "Only enable events on applying cpu with this type "
+ "for hybrid platform (e.g. core or atom)",
+ parse_hybrid_type),
#ifdef HAVE_LIBPFM
OPT_CALLBACK(0, "pfm-events", &evsel_list, "event",
"libpfm4 event selector. use 'perf list' to list available events",
@@ -1298,70 +1321,75 @@ static struct option stat_options[] = {
OPT_END()
};
+static const char *const aggr_mode__string[] = {
+ [AGGR_CORE] = "core",
+ [AGGR_DIE] = "die",
+ [AGGR_GLOBAL] = "global",
+ [AGGR_NODE] = "node",
+ [AGGR_NONE] = "none",
+ [AGGR_SOCKET] = "socket",
+ [AGGR_THREAD] = "thread",
+ [AGGR_UNSET] = "unset",
+};
+
static struct aggr_cpu_id perf_stat__get_socket(struct perf_stat_config *config __maybe_unused,
- struct perf_cpu_map *map, int cpu)
+ struct perf_cpu cpu)
{
- return cpu_map__get_socket(map, cpu, NULL);
+ return aggr_cpu_id__socket(cpu, /*data=*/NULL);
}
static struct aggr_cpu_id perf_stat__get_die(struct perf_stat_config *config __maybe_unused,
- struct perf_cpu_map *map, int cpu)
+ struct perf_cpu cpu)
{
- return cpu_map__get_die(map, cpu, NULL);
+ return aggr_cpu_id__die(cpu, /*data=*/NULL);
}
static struct aggr_cpu_id perf_stat__get_core(struct perf_stat_config *config __maybe_unused,
- struct perf_cpu_map *map, int cpu)
+ struct perf_cpu cpu)
{
- return cpu_map__get_core(map, cpu, NULL);
+ return aggr_cpu_id__core(cpu, /*data=*/NULL);
}
static struct aggr_cpu_id perf_stat__get_node(struct perf_stat_config *config __maybe_unused,
- struct perf_cpu_map *map, int cpu)
+ struct perf_cpu cpu)
{
- return cpu_map__get_node(map, cpu, NULL);
+ return aggr_cpu_id__node(cpu, /*data=*/NULL);
}
static struct aggr_cpu_id perf_stat__get_aggr(struct perf_stat_config *config,
- aggr_get_id_t get_id, struct perf_cpu_map *map, int idx)
+ aggr_get_id_t get_id, struct perf_cpu cpu)
{
- int cpu;
- struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id();
+ struct aggr_cpu_id id = aggr_cpu_id__empty();
- if (idx >= map->nr)
- return id;
+ if (aggr_cpu_id__is_empty(&config->cpus_aggr_map->map[cpu.cpu]))
+ config->cpus_aggr_map->map[cpu.cpu] = get_id(config, cpu);
- cpu = map->map[idx];
-
- if (cpu_map__aggr_cpu_id_is_empty(config->cpus_aggr_map->map[cpu]))
- config->cpus_aggr_map->map[cpu] = get_id(config, map, idx);
-
- id = config->cpus_aggr_map->map[cpu];
+ id = config->cpus_aggr_map->map[cpu.cpu];
return id;
}
static struct aggr_cpu_id perf_stat__get_socket_cached(struct perf_stat_config *config,
- struct perf_cpu_map *map, int idx)
+ struct perf_cpu cpu)
{
- return perf_stat__get_aggr(config, perf_stat__get_socket, map, idx);
+ return perf_stat__get_aggr(config, perf_stat__get_socket, cpu);
}
static struct aggr_cpu_id perf_stat__get_die_cached(struct perf_stat_config *config,
- struct perf_cpu_map *map, int idx)
+ struct perf_cpu cpu)
{
- return perf_stat__get_aggr(config, perf_stat__get_die, map, idx);
+ return perf_stat__get_aggr(config, perf_stat__get_die, cpu);
}
static struct aggr_cpu_id perf_stat__get_core_cached(struct perf_stat_config *config,
- struct perf_cpu_map *map, int idx)
+ struct perf_cpu cpu)
{
- return perf_stat__get_aggr(config, perf_stat__get_core, map, idx);
+ return perf_stat__get_aggr(config, perf_stat__get_core, cpu);
}
static struct aggr_cpu_id perf_stat__get_node_cached(struct perf_stat_config *config,
- struct perf_cpu_map *map, int idx)
+ struct perf_cpu cpu)
{
- return perf_stat__get_aggr(config, perf_stat__get_node, map, idx);
+ return perf_stat__get_aggr(config, perf_stat__get_node, cpu);
}
static bool term_percore_set(void)
@@ -1376,54 +1404,67 @@ static bool term_percore_set(void)
return false;
}
-static int perf_stat_init_aggr_mode(void)
+static aggr_cpu_id_get_t aggr_mode__get_aggr(enum aggr_mode aggr_mode)
{
- int nr;
+ switch (aggr_mode) {
+ case AGGR_SOCKET:
+ return aggr_cpu_id__socket;
+ case AGGR_DIE:
+ return aggr_cpu_id__die;
+ case AGGR_CORE:
+ return aggr_cpu_id__core;
+ case AGGR_NODE:
+ return aggr_cpu_id__node;
+ case AGGR_NONE:
+ if (term_percore_set())
+ return aggr_cpu_id__core;
+
+ return NULL;
+ case AGGR_GLOBAL:
+ case AGGR_THREAD:
+ case AGGR_UNSET:
+ default:
+ return NULL;
+ }
+}
- switch (stat_config.aggr_mode) {
+static aggr_get_id_t aggr_mode__get_id(enum aggr_mode aggr_mode)
+{
+ switch (aggr_mode) {
case AGGR_SOCKET:
- if (cpu_map__build_socket_map(evsel_list->core.cpus, &stat_config.aggr_map)) {
- perror("cannot build socket map");
- return -1;
- }
- stat_config.aggr_get_id = perf_stat__get_socket_cached;
- break;
+ return perf_stat__get_socket_cached;
case AGGR_DIE:
- if (cpu_map__build_die_map(evsel_list->core.cpus, &stat_config.aggr_map)) {
- perror("cannot build die map");
- return -1;
- }
- stat_config.aggr_get_id = perf_stat__get_die_cached;
- break;
+ return perf_stat__get_die_cached;
case AGGR_CORE:
- if (cpu_map__build_core_map(evsel_list->core.cpus, &stat_config.aggr_map)) {
- perror("cannot build core map");
- return -1;
- }
- stat_config.aggr_get_id = perf_stat__get_core_cached;
- break;
+ return perf_stat__get_core_cached;
case AGGR_NODE:
- if (cpu_map__build_node_map(evsel_list->core.cpus, &stat_config.aggr_map)) {
- perror("cannot build core map");
- return -1;
- }
- stat_config.aggr_get_id = perf_stat__get_node_cached;
- break;
+ return perf_stat__get_node_cached;
case AGGR_NONE:
if (term_percore_set()) {
- if (cpu_map__build_core_map(evsel_list->core.cpus,
- &stat_config.aggr_map)) {
- perror("cannot build core map");
- return -1;
- }
- stat_config.aggr_get_id = perf_stat__get_core_cached;
+ return perf_stat__get_core_cached;
}
- break;
+ return NULL;
case AGGR_GLOBAL:
case AGGR_THREAD:
case AGGR_UNSET:
default:
- break;
+ return NULL;
+ }
+}
+
+static int perf_stat_init_aggr_mode(void)
+{
+ int nr;
+ aggr_cpu_id_get_t get_id = aggr_mode__get_aggr(stat_config.aggr_mode);
+
+ if (get_id) {
+ stat_config.aggr_map = cpu_aggr_map__new(evsel_list->core.cpus,
+ get_id, /*data=*/NULL);
+ if (!stat_config.aggr_map) {
+ pr_err("cannot build %s map", aggr_mode__string[stat_config.aggr_mode]);
+ return -1;
+ }
+ stat_config.aggr_get_id = aggr_mode__get_id(stat_config.aggr_mode);
}
/*
@@ -1431,7 +1472,7 @@ static int perf_stat_init_aggr_mode(void)
* taking the highest cpu number to be the size of
* the aggregation translate cpumap.
*/
- nr = perf_cpu_map__max(evsel_list->core.cpus);
+ nr = perf_cpu_map__max(evsel_list->core.cpus).cpu;
stat_config.cpus_aggr_map = cpu_aggr_map__empty_new(nr + 1);
return stat_config.cpus_aggr_map ? 0 : -ENOMEM;
}
@@ -1459,169 +1500,139 @@ static void perf_stat__exit_aggr_mode(void)
stat_config.cpus_aggr_map = NULL;
}
-static inline int perf_env__get_cpu(struct perf_env *env, struct perf_cpu_map *map, int idx)
-{
- int cpu;
-
- if (idx > map->nr)
- return -1;
-
- cpu = map->map[idx];
-
- if (cpu >= env->nr_cpus_avail)
- return -1;
-
- return cpu;
-}
-
-static struct aggr_cpu_id perf_env__get_socket(struct perf_cpu_map *map, int idx, void *data)
+static struct aggr_cpu_id perf_env__get_socket_aggr_by_cpu(struct perf_cpu cpu, void *data)
{
struct perf_env *env = data;
- int cpu = perf_env__get_cpu(env, map, idx);
- struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id();
+ struct aggr_cpu_id id = aggr_cpu_id__empty();
- if (cpu != -1)
- id.socket = env->cpu[cpu].socket_id;
+ if (cpu.cpu != -1)
+ id.socket = env->cpu[cpu.cpu].socket_id;
return id;
}
-static struct aggr_cpu_id perf_env__get_die(struct perf_cpu_map *map, int idx, void *data)
+static struct aggr_cpu_id perf_env__get_die_aggr_by_cpu(struct perf_cpu cpu, void *data)
{
struct perf_env *env = data;
- struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id();
- int cpu = perf_env__get_cpu(env, map, idx);
+ struct aggr_cpu_id id = aggr_cpu_id__empty();
- if (cpu != -1) {
+ if (cpu.cpu != -1) {
/*
* die_id is relative to socket, so start
* with the socket ID and then add die to
* make a unique ID.
*/
- id.socket = env->cpu[cpu].socket_id;
- id.die = env->cpu[cpu].die_id;
+ id.socket = env->cpu[cpu.cpu].socket_id;
+ id.die = env->cpu[cpu.cpu].die_id;
}
return id;
}
-static struct aggr_cpu_id perf_env__get_core(struct perf_cpu_map *map, int idx, void *data)
+static struct aggr_cpu_id perf_env__get_core_aggr_by_cpu(struct perf_cpu cpu, void *data)
{
struct perf_env *env = data;
- struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id();
- int cpu = perf_env__get_cpu(env, map, idx);
+ struct aggr_cpu_id id = aggr_cpu_id__empty();
- if (cpu != -1) {
+ if (cpu.cpu != -1) {
/*
* core_id is relative to socket and die,
* we need a global id. So we set
* socket, die id and core id
*/
- id.socket = env->cpu[cpu].socket_id;
- id.die = env->cpu[cpu].die_id;
- id.core = env->cpu[cpu].core_id;
+ id.socket = env->cpu[cpu.cpu].socket_id;
+ id.die = env->cpu[cpu.cpu].die_id;
+ id.core = env->cpu[cpu.cpu].core_id;
}
return id;
}
-static struct aggr_cpu_id perf_env__get_node(struct perf_cpu_map *map, int idx, void *data)
+static struct aggr_cpu_id perf_env__get_node_aggr_by_cpu(struct perf_cpu cpu, void *data)
{
- int cpu = perf_env__get_cpu(data, map, idx);
- struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id();
+ struct aggr_cpu_id id = aggr_cpu_id__empty();
id.node = perf_env__numa_node(data, cpu);
return id;
}
-static int perf_env__build_socket_map(struct perf_env *env, struct perf_cpu_map *cpus,
- struct cpu_aggr_map **sockp)
-{
- return cpu_map__build_map(cpus, sockp, perf_env__get_socket, env);
-}
-
-static int perf_env__build_die_map(struct perf_env *env, struct perf_cpu_map *cpus,
- struct cpu_aggr_map **diep)
-{
- return cpu_map__build_map(cpus, diep, perf_env__get_die, env);
-}
-
-static int perf_env__build_core_map(struct perf_env *env, struct perf_cpu_map *cpus,
- struct cpu_aggr_map **corep)
-{
- return cpu_map__build_map(cpus, corep, perf_env__get_core, env);
-}
-
-static int perf_env__build_node_map(struct perf_env *env, struct perf_cpu_map *cpus,
- struct cpu_aggr_map **nodep)
-{
- return cpu_map__build_map(cpus, nodep, perf_env__get_node, env);
-}
-
static struct aggr_cpu_id perf_stat__get_socket_file(struct perf_stat_config *config __maybe_unused,
- struct perf_cpu_map *map, int idx)
+ struct perf_cpu cpu)
{
- return perf_env__get_socket(map, idx, &perf_stat.session->header.env);
+ return perf_env__get_socket_aggr_by_cpu(cpu, &perf_stat.session->header.env);
}
static struct aggr_cpu_id perf_stat__get_die_file(struct perf_stat_config *config __maybe_unused,
- struct perf_cpu_map *map, int idx)
+ struct perf_cpu cpu)
{
- return perf_env__get_die(map, idx, &perf_stat.session->header.env);
+ return perf_env__get_die_aggr_by_cpu(cpu, &perf_stat.session->header.env);
}
static struct aggr_cpu_id perf_stat__get_core_file(struct perf_stat_config *config __maybe_unused,
- struct perf_cpu_map *map, int idx)
+ struct perf_cpu cpu)
{
- return perf_env__get_core(map, idx, &perf_stat.session->header.env);
+ return perf_env__get_core_aggr_by_cpu(cpu, &perf_stat.session->header.env);
}
static struct aggr_cpu_id perf_stat__get_node_file(struct perf_stat_config *config __maybe_unused,
- struct perf_cpu_map *map, int idx)
+ struct perf_cpu cpu)
{
- return perf_env__get_node(map, idx, &perf_stat.session->header.env);
+ return perf_env__get_node_aggr_by_cpu(cpu, &perf_stat.session->header.env);
}
-static int perf_stat_init_aggr_mode_file(struct perf_stat *st)
+static aggr_cpu_id_get_t aggr_mode__get_aggr_file(enum aggr_mode aggr_mode)
{
- struct perf_env *env = &st->session->header.env;
+ switch (aggr_mode) {
+ case AGGR_SOCKET:
+ return perf_env__get_socket_aggr_by_cpu;
+ case AGGR_DIE:
+ return perf_env__get_die_aggr_by_cpu;
+ case AGGR_CORE:
+ return perf_env__get_core_aggr_by_cpu;
+ case AGGR_NODE:
+ return perf_env__get_node_aggr_by_cpu;
+ case AGGR_NONE:
+ case AGGR_GLOBAL:
+ case AGGR_THREAD:
+ case AGGR_UNSET:
+ default:
+ return NULL;
+ }
+}
- switch (stat_config.aggr_mode) {
+static aggr_get_id_t aggr_mode__get_id_file(enum aggr_mode aggr_mode)
+{
+ switch (aggr_mode) {
case AGGR_SOCKET:
- if (perf_env__build_socket_map(env, evsel_list->core.cpus, &stat_config.aggr_map)) {
- perror("cannot build socket map");
- return -1;
- }
- stat_config.aggr_get_id = perf_stat__get_socket_file;
- break;
+ return perf_stat__get_socket_file;
case AGGR_DIE:
- if (perf_env__build_die_map(env, evsel_list->core.cpus, &stat_config.aggr_map)) {
- perror("cannot build die map");
- return -1;
- }
- stat_config.aggr_get_id = perf_stat__get_die_file;
- break;
+ return perf_stat__get_die_file;
case AGGR_CORE:
- if (perf_env__build_core_map(env, evsel_list->core.cpus, &stat_config.aggr_map)) {
- perror("cannot build core map");
- return -1;
- }
- stat_config.aggr_get_id = perf_stat__get_core_file;
- break;
+ return perf_stat__get_core_file;
case AGGR_NODE:
- if (perf_env__build_node_map(env, evsel_list->core.cpus, &stat_config.aggr_map)) {
- perror("cannot build core map");
- return -1;
- }
- stat_config.aggr_get_id = perf_stat__get_node_file;
- break;
+ return perf_stat__get_node_file;
case AGGR_NONE:
case AGGR_GLOBAL:
case AGGR_THREAD:
case AGGR_UNSET:
default:
- break;
+ return NULL;
}
+}
+
+static int perf_stat_init_aggr_mode_file(struct perf_stat *st)
+{
+ struct perf_env *env = &st->session->header.env;
+ aggr_cpu_id_get_t get_id = aggr_mode__get_aggr_file(stat_config.aggr_mode);
+
+ if (!get_id)
+ return 0;
+ stat_config.aggr_map = cpu_aggr_map__new(evsel_list->core.cpus, get_id, env);
+ if (!stat_config.aggr_map) {
+ pr_err("cannot build %s map", aggr_mode__string[stat_config.aggr_mode]);
+ return -1;
+ }
+ stat_config.aggr_get_id = aggr_mode__get_id_file(stat_config.aggr_mode);
return 0;
}
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index df9fc00b4cd6..52b137a184a6 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1536,13 +1536,20 @@ static size_t trace__fprintf_tstamp(struct trace *trace, u64 tstamp, FILE *fp)
return fprintf(fp, " ? ");
}
+static pid_t workload_pid = -1;
static bool done = false;
static bool interrupted = false;
-static void sig_handler(int sig)
+static void sighandler_interrupt(int sig __maybe_unused)
{
- done = true;
- interrupted = sig == SIGINT;
+ done = interrupted = true;
+}
+
+static void sighandler_chld(int sig __maybe_unused, siginfo_t *info,
+ void *context __maybe_unused)
+{
+ if (info->si_pid == workload_pid)
+ done = true;
}
static size_t trace__fprintf_comm_tid(struct trace *trace, struct thread *thread, FILE *fp)
@@ -2726,6 +2733,8 @@ static size_t trace__fprintf_tp_fields(struct trace *trace, struct evsel *evsel,
offset = format_field__intval(field, sample, evsel->needs_swap);
syscall_arg.len = offset >> 16;
offset &= 0xffff;
+ if (field->flags & TEP_FIELD_IS_RELATIVE)
+ offset += field->offset + field->size;
}
val = (uintptr_t)(sample->raw_data + offset);
@@ -3936,7 +3945,6 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
bool draining = false;
trace->live = true;
- signal(SIGCHLD, sig_handler);
if (!trace->raw_augmented_syscalls) {
if (trace->trace_syscalls && trace__add_syscall_newtp(trace))
@@ -3962,6 +3970,9 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
evlist__add(evlist, pgfault_min);
}
+ /* Enable ignoring missing threads when -u/-p option is defined. */
+ trace->opts.ignore_missing_thread = trace->opts.target.uid != UINT_MAX || trace->opts.target.pid;
+
if (trace->sched &&
evlist__add_newtp(evlist, "sched", "sched_stat_runtime", trace__sched_stat_runtime))
goto out_error_sched_stat_runtime;
@@ -4013,6 +4024,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
fprintf(trace->output, "Couldn't run the workload!\n");
goto out_delete_evlist;
}
+ workload_pid = evlist->workload.pid;
}
err = evlist__open(evlist);
@@ -4882,10 +4894,16 @@ int cmd_trace(int argc, const char **argv)
const char * const trace_subcommands[] = { "record", NULL };
int err = -1;
char bf[BUFSIZ];
+ struct sigaction sigchld_act;
signal(SIGSEGV, sighandler_dump_stack);
signal(SIGFPE, sighandler_dump_stack);
- signal(SIGINT, sig_handler);
+ signal(SIGINT, sighandler_interrupt);
+
+ memset(&sigchld_act, 0, sizeof(sigchld_act));
+ sigchld_act.sa_flags = SA_SIGINFO;
+ sigchld_act.sa_sigaction = sighandler_chld;
+ sigaction(SIGCHLD, &sigchld_act, NULL);
trace.evlist = evlist__new();
trace.sctbl = syscalltbl__new();
diff --git a/tools/perf/dlfilters/dlfilter-test-api-v0.c b/tools/perf/dlfilters/dlfilter-test-api-v0.c
index 7565a1852c74..b17eb52a0694 100644
--- a/tools/perf/dlfilters/dlfilter-test-api-v0.c
+++ b/tools/perf/dlfilters/dlfilter-test-api-v0.c
@@ -308,8 +308,6 @@ int filter_event_early(void *data, const struct perf_dlfilter_sample *sample, vo
int filter_event(void *data, const struct perf_dlfilter_sample *sample, void *ctx)
{
- struct filter_data *d = data;
-
pr_debug("%s API\n", __func__);
return do_checks(data, sample, ctx, false);
diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/branch.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/branch.json
new file mode 100644
index 000000000000..79f2016c53b0
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/branch.json
@@ -0,0 +1,8 @@
+[
+ {
+ "ArchStdEvent": "BR_MIS_PRED"
+ },
+ {
+ "ArchStdEvent": "BR_PRED"
+ }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/bus.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/bus.json
new file mode 100644
index 000000000000..579c1c993d17
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/bus.json
@@ -0,0 +1,20 @@
+[
+ {
+ "ArchStdEvent": "CPU_CYCLES"
+ },
+ {
+ "ArchStdEvent": "BUS_ACCESS"
+ },
+ {
+ "ArchStdEvent": "BUS_CYCLES"
+ },
+ {
+ "ArchStdEvent": "BUS_ACCESS_RD"
+ },
+ {
+ "ArchStdEvent": "BUS_ACCESS_WR"
+ },
+ {
+ "ArchStdEvent": "CNT_CYCLES"
+ }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/cache.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/cache.json
new file mode 100644
index 000000000000..0141f749bff3
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/cache.json
@@ -0,0 +1,155 @@
+[
+ {
+ "ArchStdEvent": "L1I_CACHE_REFILL"
+ },
+ {
+ "ArchStdEvent": "L1I_TLB_REFILL"
+ },
+ {
+ "ArchStdEvent": "L1D_CACHE_REFILL"
+ },
+ {
+ "ArchStdEvent": "L1D_CACHE"
+ },
+ {
+ "ArchStdEvent": "L1D_TLB_REFILL"
+ },
+ {
+ "ArchStdEvent": "L1I_CACHE"
+ },
+ {
+ "ArchStdEvent": "L1D_CACHE_WB"
+ },
+ {
+ "ArchStdEvent": "L2D_CACHE"
+ },
+ {
+ "ArchStdEvent": "L2D_CACHE_REFILL"
+ },
+ {
+ "ArchStdEvent": "L2D_CACHE_WB"
+ },
+ {
+ "ArchStdEvent": "L2D_CACHE_ALLOCATE"
+ },
+ {
+ "ArchStdEvent": "L1D_TLB"
+ },
+ {
+ "ArchStdEvent": "L1I_TLB"
+ },
+ {
+ "ArchStdEvent": "L3D_CACHE_ALLOCATE"
+ },
+ {
+ "ArchStdEvent": "L3D_CACHE_REFILL"
+ },
+ {
+ "ArchStdEvent": "L3D_CACHE"
+ },
+ {
+ "ArchStdEvent": "L2D_TLB_REFILL"
+ },
+ {
+ "ArchStdEvent": "L2D_TLB"
+ },
+ {
+ "ArchStdEvent": "DTLB_WALK"
+ },
+ {
+ "ArchStdEvent": "ITLB_WALK"
+ },
+ {
+ "ArchStdEvent": "LL_CACHE_RD"
+ },
+ {
+ "ArchStdEvent": "LL_CACHE_MISS_RD"
+ },
+ {
+ "ArchStdEvent": "L1D_CACHE_LMISS_RD"
+ },
+ {
+ "ArchStdEvent": "L1D_CACHE_RD"
+ },
+ {
+ "ArchStdEvent": "L1D_CACHE_WR"
+ },
+ {
+ "ArchStdEvent": "L1D_CACHE_REFILL_RD"
+ },
+ {
+ "ArchStdEvent": "L1D_CACHE_REFILL_WR"
+ },
+ {
+ "ArchStdEvent": "L1D_CACHE_REFILL_INNER"
+ },
+ {
+ "ArchStdEvent": "L1D_CACHE_REFILL_OUTER"
+ },
+ {
+ "ArchStdEvent": "L1D_CACHE_WB_VICTIM"
+ },
+ {
+ "ArchStdEvent": "L1D_CACHE_WB_CLEAN"
+ },
+ {
+ "ArchStdEvent": "L1D_CACHE_INVAL"
+ },
+ {
+ "ArchStdEvent": "L1D_TLB_REFILL_RD"
+ },
+ {
+ "ArchStdEvent": "L1D_TLB_REFILL_WR"
+ },
+ {
+ "ArchStdEvent": "L1D_TLB_RD"
+ },
+ {
+ "ArchStdEvent": "L1D_TLB_WR"
+ },
+ {
+ "ArchStdEvent": "L2D_CACHE_RD"
+ },
+ {
+ "ArchStdEvent": "L2D_CACHE_WR"
+ },
+ {
+ "ArchStdEvent": "L2D_CACHE_REFILL_RD"
+ },
+ {
+ "ArchStdEvent": "L2D_CACHE_REFILL_WR"
+ },
+ {
+ "ArchStdEvent": "L2D_CACHE_WB_VICTIM"
+ },
+ {
+ "ArchStdEvent": "L2D_CACHE_WB_CLEAN"
+ },
+ {
+ "ArchStdEvent": "L2D_CACHE_INVAL"
+ },
+ {
+ "ArchStdEvent": "L2D_TLB_REFILL_RD"
+ },
+ {
+ "ArchStdEvent": "L2D_TLB_REFILL_WR"
+ },
+ {
+ "ArchStdEvent": "L2D_TLB_RD"
+ },
+ {
+ "ArchStdEvent": "L2D_TLB_WR"
+ },
+ {
+ "ArchStdEvent": "L3D_CACHE_RD"
+ },
+ {
+ "ArchStdEvent": "L1I_CACHE_LMISS"
+ },
+ {
+ "ArchStdEvent": "L2D_CACHE_LMISS_RD"
+ },
+ {
+ "ArchStdEvent": "L3D_CACHE_LMISS_RD"
+ }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/exception.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/exception.json
new file mode 100644
index 000000000000..344a2d552ad5
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/exception.json
@@ -0,0 +1,47 @@
+[
+ {
+ "ArchStdEvent": "EXC_TAKEN"
+ },
+ {
+ "ArchStdEvent": "MEMORY_ERROR"
+ },
+ {
+ "ArchStdEvent": "EXC_UNDEF"
+ },
+ {
+ "ArchStdEvent": "EXC_SVC"
+ },
+ {
+ "ArchStdEvent": "EXC_PABORT"
+ },
+ {
+ "ArchStdEvent": "EXC_DABORT"
+ },
+ {
+ "ArchStdEvent": "EXC_IRQ"
+ },
+ {
+ "ArchStdEvent": "EXC_FIQ"
+ },
+ {
+ "ArchStdEvent": "EXC_SMC"
+ },
+ {
+ "ArchStdEvent": "EXC_HVC"
+ },
+ {
+ "ArchStdEvent": "EXC_TRAP_PABORT"
+ },
+ {
+ "ArchStdEvent": "EXC_TRAP_DABORT"
+ },
+ {
+ "ArchStdEvent": "EXC_TRAP_OTHER"
+ },
+ {
+ "ArchStdEvent": "EXC_TRAP_IRQ"
+ },
+ {
+ "ArchStdEvent": "EXC_TRAP_FIQ"
+ }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/instruction.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/instruction.json
new file mode 100644
index 000000000000..e57cd55937c6
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/instruction.json
@@ -0,0 +1,143 @@
+[
+ {
+ "ArchStdEvent": "SW_INCR"
+ },
+ {
+ "ArchStdEvent": "INST_RETIRED"
+ },
+ {
+ "ArchStdEvent": "EXC_RETURN"
+ },
+ {
+ "ArchStdEvent": "CID_WRITE_RETIRED"
+ },
+ {
+ "ArchStdEvent": "INST_SPEC"
+ },
+ {
+ "ArchStdEvent": "TTBR_WRITE_RETIRED"
+ },
+ {
+ "ArchStdEvent": "BR_RETIRED"
+ },
+ {
+ "ArchStdEvent": "BR_MIS_PRED_RETIRED"
+ },
+ {
+ "ArchStdEvent": "OP_RETIRED"
+ },
+ {
+ "ArchStdEvent": "OP_SPEC"
+ },
+ {
+ "ArchStdEvent": "LDREX_SPEC"
+ },
+ {
+ "ArchStdEvent": "STREX_PASS_SPEC"
+ },
+ {
+ "ArchStdEvent": "STREX_FAIL_SPEC"
+ },
+ {
+ "ArchStdEvent": "STREX_SPEC"
+ },
+ {
+ "ArchStdEvent": "LD_SPEC"
+ },
+ {
+ "ArchStdEvent": "ST_SPEC"
+ },
+ {
+ "ArchStdEvent": "DP_SPEC"
+ },
+ {
+ "ArchStdEvent": "ASE_SPEC"
+ },
+ {
+ "ArchStdEvent": "VFP_SPEC"
+ },
+ {
+ "ArchStdEvent": "PC_WRITE_SPEC"
+ },
+ {
+ "ArchStdEvent": "CRYPTO_SPEC"
+ },
+ {
+ "ArchStdEvent": "BR_IMMED_SPEC"
+ },
+ {
+ "ArchStdEvent": "BR_RETURN_SPEC"
+ },
+ {
+ "ArchStdEvent": "BR_INDIRECT_SPEC"
+ },
+ {
+ "ArchStdEvent": "ISB_SPEC"
+ },
+ {
+ "ArchStdEvent": "DSB_SPEC"
+ },
+ {
+ "ArchStdEvent": "DMB_SPEC"
+ },
+ {
+ "ArchStdEvent": "RC_LD_SPEC"
+ },
+ {
+ "ArchStdEvent": "RC_ST_SPEC"
+ },
+ {
+ "ArchStdEvent": "ASE_INST_SPEC"
+ },
+ {
+ "ArchStdEvent": "SVE_INST_SPEC"
+ },
+ {
+ "ArchStdEvent": "FP_HP_SPEC"
+ },
+ {
+ "ArchStdEvent": "FP_SP_SPEC"
+ },
+ {
+ "ArchStdEvent": "FP_DP_SPEC"
+ },
+ {
+ "ArchStdEvent": "SVE_PRED_SPEC"
+ },
+ {
+ "ArchStdEvent": "SVE_PRED_EMPTY_SPEC"
+ },
+ {
+ "ArchStdEvent": "SVE_PRED_FULL_SPEC"
+ },
+ {
+ "ArchStdEvent": "SVE_PRED_PARTIAL_SPEC"
+ },
+ {
+ "ArchStdEvent": "SVE_PRED_NOT_FULL_SPEC"
+ },
+ {
+ "ArchStdEvent": "SVE_LDFF_SPEC"
+ },
+ {
+ "ArchStdEvent": "SVE_LDFF_FAULT_SPEC"
+ },
+ {
+ "ArchStdEvent": "FP_SCALE_OPS_SPEC"
+ },
+ {
+ "ArchStdEvent": "FP_FIXED_OPS_SPEC"
+ },
+ {
+ "ArchStdEvent": "ASE_SVE_INT8_SPEC"
+ },
+ {
+ "ArchStdEvent": "ASE_SVE_INT16_SPEC"
+ },
+ {
+ "ArchStdEvent": "ASE_SVE_INT32_SPEC"
+ },
+ {
+ "ArchStdEvent": "ASE_SVE_INT64_SPEC"
+ }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/memory.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/memory.json
new file mode 100644
index 000000000000..e522113aeb96
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/memory.json
@@ -0,0 +1,38 @@
+[
+ {
+ "ArchStdEvent": "MEM_ACCESS"
+ },
+ {
+ "ArchStdEvent": "MEM_ACCESS_RD"
+ },
+ {
+ "ArchStdEvent": "MEM_ACCESS_WR"
+ },
+ {
+ "ArchStdEvent": "UNALIGNED_LD_SPEC"
+ },
+ {
+ "ArchStdEvent": "UNALIGNED_ST_SPEC"
+ },
+ {
+ "ArchStdEvent": "UNALIGNED_LDST_SPEC"
+ },
+ {
+ "ArchStdEvent": "LDST_ALIGN_LAT"
+ },
+ {
+ "ArchStdEvent": "LD_ALIGN_LAT"
+ },
+ {
+ "ArchStdEvent": "ST_ALIGN_LAT"
+ },
+ {
+ "ArchStdEvent": "MEM_ACCESS_CHECKED"
+ },
+ {
+ "ArchStdEvent": "MEM_ACCESS_CHECKED_RD"
+ },
+ {
+ "ArchStdEvent": "MEM_ACCESS_CHECKED_WR"
+ }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/other.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/other.json
new file mode 100644
index 000000000000..20d8365756c5
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/other.json
@@ -0,0 +1,5 @@
+[
+ {
+ "ArchStdEvent": "REMOTE_ACCESS"
+ }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/pipeline.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/pipeline.json
new file mode 100644
index 000000000000..f9fae15f7555
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/pipeline.json
@@ -0,0 +1,23 @@
+[
+ {
+ "ArchStdEvent": "STALL_FRONTEND"
+ },
+ {
+ "ArchStdEvent": "STALL_BACKEND"
+ },
+ {
+ "ArchStdEvent": "STALL"
+ },
+ {
+ "ArchStdEvent": "STALL_SLOT_BACKEND"
+ },
+ {
+ "ArchStdEvent": "STALL_SLOT_FRONTEND"
+ },
+ {
+ "ArchStdEvent": "STALL_SLOT"
+ },
+ {
+ "ArchStdEvent": "STALL_BACKEND_MEM"
+ }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/spe.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/spe.json
new file mode 100644
index 000000000000..20f2165c85fe
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/spe.json
@@ -0,0 +1,14 @@
+[
+ {
+ "ArchStdEvent": "SAMPLE_POP"
+ },
+ {
+ "ArchStdEvent": "SAMPLE_FEED"
+ },
+ {
+ "ArchStdEvent": "SAMPLE_FILTRATE"
+ },
+ {
+ "ArchStdEvent": "SAMPLE_COLLISION"
+ }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/trace.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/trace.json
new file mode 100644
index 000000000000..3116135c59e2
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/trace.json
@@ -0,0 +1,29 @@
+[
+ {
+ "ArchStdEvent": "TRB_WRAP"
+ },
+ {
+ "ArchStdEvent": "TRCEXTOUT0"
+ },
+ {
+ "ArchStdEvent": "TRCEXTOUT1"
+ },
+ {
+ "ArchStdEvent": "TRCEXTOUT2"
+ },
+ {
+ "ArchStdEvent": "TRCEXTOUT3"
+ },
+ {
+ "ArchStdEvent": "CTI_TRIGOUT4"
+ },
+ {
+ "ArchStdEvent": "CTI_TRIGOUT5"
+ },
+ {
+ "ArchStdEvent": "CTI_TRIGOUT6"
+ },
+ {
+ "ArchStdEvent": "CTI_TRIGOUT7"
+ }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/armv8-common-and-microarch.json b/tools/perf/pmu-events/arch/arm64/common-and-microarch.json
index 423767510aff..80d7a70829a0 100644
--- a/tools/perf/pmu-events/arch/arm64/armv8-common-and-microarch.json
+++ b/tools/perf/pmu-events/arch/arm64/common-and-microarch.json
@@ -300,6 +300,30 @@
"BriefDescription": "No operation sent for execution on a slot"
},
{
+ "PublicDescription": "Sample Population",
+ "EventCode": "0x4000",
+ "EventName": "SAMPLE_POP",
+ "BriefDescription": "Sample Population"
+ },
+ {
+ "PublicDescription": "Sample Taken",
+ "EventCode": "0x4001",
+ "EventName": "SAMPLE_FEED",
+ "BriefDescription": "Sample Taken"
+ },
+ {
+ "PublicDescription": "Sample Taken and not removed by filtering",
+ "EventCode": "0x4002",
+ "EventName": "SAMPLE_FILTRATE",
+ "BriefDescription": "Sample Taken and not removed by filtering"
+ },
+ {
+ "PublicDescription": "Sample collided with previous sample",
+ "EventCode": "0x4003",
+ "EventName": "SAMPLE_COLLISION",
+ "BriefDescription": "Sample collided with previous sample"
+ },
+ {
"PublicDescription": "Constant frequency cycles. The counter increments at a constant frequency equal to the rate of increment of the system counter, CNTPCT_EL0.",
"EventCode": "0x4004",
"EventName": "CNT_CYCLES",
@@ -330,6 +354,96 @@
"BriefDescription": "Level 3 data cache long-latency read miss"
},
{
+ "PublicDescription": "Trace buffer current write pointer wrapped",
+ "EventCode": "0x400C",
+ "EventName": "TRB_WRAP",
+ "BriefDescription": "Trace buffer current write pointer wrapped"
+ },
+ {
+ "PublicDescription": "PE Trace Unit external output 0",
+ "EventCode": "0x4010",
+ "EventName": "TRCEXTOUT0",
+ "BriefDescription": "PE Trace Unit external output 0"
+ },
+ {
+ "PublicDescription": "PE Trace Unit external output 1",
+ "EventCode": "0x4011",
+ "EventName": "TRCEXTOUT1",
+ "BriefDescription": "PE Trace Unit external output 1"
+ },
+ {
+ "PublicDescription": "PE Trace Unit external output 2",
+ "EventCode": "0x4012",
+ "EventName": "TRCEXTOUT2",
+ "BriefDescription": "PE Trace Unit external output 2"
+ },
+ {
+ "PublicDescription": "PE Trace Unit external output 3",
+ "EventCode": "0x4013",
+ "EventName": "TRCEXTOUT3",
+ "BriefDescription": "PE Trace Unit external output 3"
+ },
+ {
+ "PublicDescription": "Cross-trigger Interface output trigger 4",
+ "EventCode": "0x4018",
+ "EventName": "CTI_TRIGOUT4",
+ "BriefDescription": "Cross-trigger Interface output trigger 4"
+ },
+ {
+ "PublicDescription": "Cross-trigger Interface output trigger 5 ",
+ "EventCode": "0x4019",
+ "EventName": "CTI_TRIGOUT5",
+ "BriefDescription": "Cross-trigger Interface output trigger 5 "
+ },
+ {
+ "PublicDescription": "Cross-trigger Interface output trigger 6",
+ "EventCode": "0x401A",
+ "EventName": "CTI_TRIGOUT6",
+ "BriefDescription": "Cross-trigger Interface output trigger 6"
+ },
+ {
+ "PublicDescription": "Cross-trigger Interface output trigger 7",
+ "EventCode": "0x401B",
+ "EventName": "CTI_TRIGOUT7",
+ "BriefDescription": "Cross-trigger Interface output trigger 7"
+ },
+ {
+ "PublicDescription": "Access with additional latency from alignment",
+ "EventCode": "0x4020",
+ "EventName": "LDST_ALIGN_LAT",
+ "BriefDescription": "Access with additional latency from alignment"
+ },
+ {
+ "PublicDescription": "Load with additional latency from alignment",
+ "EventCode": "0x4021",
+ "EventName": "LD_ALIGN_LAT",
+ "BriefDescription": "Load with additional latency from alignment"
+ },
+ {
+ "PublicDescription": "Store with additional latency from alignment",
+ "EventCode": "0x4022",
+ "EventName": "ST_ALIGN_LAT",
+ "BriefDescription": "Store with additional latency from alignment"
+ },
+ {
+ "PublicDescription": "Checked data memory access",
+ "EventCode": "0x4024",
+ "EventName": "MEM_ACCESS_CHECKED",
+ "BriefDescription": "Checked data memory access"
+ },
+ {
+ "PublicDescription": "Checked data memory access, read",
+ "EventCode": "0x4025",
+ "EventName": "MEM_ACCESS_CHECKED_RD",
+ "BriefDescription": "Checked data memory access, read"
+ },
+ {
+ "PublicDescription": "Checked data memory access, write",
+ "EventCode": "0x4026",
+ "EventName": "MEM_ACCESS_CHECKED_WR",
+ "BriefDescription": "Checked data memory access, write"
+ },
+ {
"PublicDescription": "SIMD Instruction architecturally executed.",
"EventCode": "0x8000",
"EventName": "SIMD_INST_RETIRED",
@@ -342,6 +456,18 @@
"BriefDescription": "Instruction architecturally executed, SVE."
},
{
+ "PublicDescription": "ASE operations speculatively executed",
+ "EventCode": "0x8005",
+ "EventName": "ASE_INST_SPEC",
+ "BriefDescription": "ASE operations speculatively executed"
+ },
+ {
+ "PublicDescription": "SVE operations speculatively executed",
+ "EventCode": "0x8006",
+ "EventName": "SVE_INST_SPEC",
+ "BriefDescription": "SVE operations speculatively executed"
+ },
+ {
"PublicDescription": "Microarchitectural operation, Operations speculatively executed.",
"EventCode": "0x8008",
"EventName": "UOP_SPEC",
@@ -360,6 +486,24 @@
"BriefDescription": "Floating-point Operations speculatively executed."
},
{
+ "PublicDescription": "Floating-point half-precision operations speculatively executed",
+ "EventCode": "0x8014",
+ "EventName": "FP_HP_SPEC",
+ "BriefDescription": "Floating-point half-precision operations speculatively executed"
+ },
+ {
+ "PublicDescription": "Floating-point single-precision operations speculatively executed",
+ "EventCode": "0x8018",
+ "EventName": "FP_SP_SPEC",
+ "BriefDescription": "Floating-point single-precision operations speculatively executed"
+ },
+ {
+ "PublicDescription": "Floating-point double-precision operations speculatively executed",
+ "EventCode": "0x801C",
+ "EventName": "FP_DP_SPEC",
+ "BriefDescription": "Floating-point double-precision operations speculatively executed"
+ },
+ {
"PublicDescription": "Floating-point FMA Operations speculatively executed.",
"EventCode": "0x8028",
"EventName": "FP_FMA_SPEC",
@@ -390,6 +534,30 @@
"BriefDescription": "SVE predicated Operations speculatively executed."
},
{
+ "PublicDescription": "SVE predicated operations with no active predicates speculatively executed",
+ "EventCode": "0x8075",
+ "EventName": "SVE_PRED_EMPTY_SPEC",
+ "BriefDescription": "SVE predicated operations with no active predicates speculatively executed"
+ },
+ {
+ "PublicDescription": "SVE predicated operations speculatively executed with all active predicates",
+ "EventCode": "0x8076",
+ "EventName": "SVE_PRED_FULL_SPEC",
+ "BriefDescription": "SVE predicated operations speculatively executed with all active predicates"
+ },
+ {
+ "PublicDescription": "SVE predicated operations speculatively executed with partially active predicates",
+ "EventCode": "0x8077",
+ "EventName": "SVE_PRED_PARTIAL_SPEC",
+ "BriefDescription": "SVE predicated operations speculatively executed with partially active predicates"
+ },
+ {
+ "PublicDescription": "SVE predicated operations with empty or partially active predicates",
+ "EventCode": "0x8079",
+ "EventName": "SVE_PRED_NOT_FULL_SPEC",
+ "BriefDescription": "SVE predicated operations with empty or partially active predicates"
+ },
+ {
"PublicDescription": "SVE MOVPRFX Operations speculatively executed.",
"EventCode": "0x807C",
"EventName": "SVE_MOVPRFX_SPEC",
@@ -498,6 +666,12 @@
"BriefDescription": "SVE First-fault load Operations speculatively executed."
},
{
+ "PublicDescription": "SVE first-fault load operations speculatively executed which set FFR bit to 0",
+ "EventCode": "0x80BD",
+ "EventName": "SVE_LDFF_FAULT_SPEC",
+ "BriefDescription": "SVE first-fault load operations speculatively executed which set FFR bit to 0"
+ },
+ {
"PublicDescription": "Scalable floating-point element Operations speculatively executed.",
"EventCode": "0x80C0",
"EventName": "FP_SCALE_OPS_SPEC",
@@ -544,5 +718,29 @@
"EventCode": "0x80C7",
"EventName": "FP_DP_FIXED_OPS_SPEC",
"BriefDescription": "Non-scalable double-precision floating-point element Operations speculatively executed."
+ },
+ {
+ "PublicDescription": "Advanced SIMD and SVE 8-bit integer operations speculatively executed",
+ "EventCode": "0x80E3",
+ "EventName": "ASE_SVE_INT8_SPEC",
+ "BriefDescription": "Advanced SIMD and SVE 8-bit integer operations speculatively executed"
+ },
+ {
+ "PublicDescription": "Advanced SIMD and SVE 16-bit integer operations speculatively executed",
+ "EventCode": "0x80E7",
+ "EventName": "ASE_SVE_INT16_SPEC",
+ "BriefDescription": "Advanced SIMD and SVE 16-bit integer operations speculatively executed"
+ },
+ {
+ "PublicDescription": "Advanced SIMD and SVE 32-bit integer operations speculatively executed",
+ "EventCode": "0x80EB",
+ "EventName": "ASE_SVE_INT32_SPEC",
+ "BriefDescription": "Advanced SIMD and SVE 32-bit integer operations speculatively executed"
+ },
+ {
+ "PublicDescription": "Advanced SIMD and SVE 64-bit integer operations speculatively executed",
+ "EventCode": "0x80EF",
+ "EventName": "ASE_SVE_INT64_SPEC",
+ "BriefDescription": "Advanced SIMD and SVE 64-bit integer operations speculatively executed"
}
]
diff --git a/tools/perf/pmu-events/arch/arm64/mapfile.csv b/tools/perf/pmu-events/arch/arm64/mapfile.csv
index 31d8b57ca9bb..b899db48c12a 100644
--- a/tools/perf/pmu-events/arch/arm64/mapfile.csv
+++ b/tools/perf/pmu-events/arch/arm64/mapfile.csv
@@ -19,6 +19,7 @@
0x00000000410fd0b0,v1,arm/cortex-a76-n1,core
0x00000000410fd0c0,v1,arm/cortex-a76-n1,core
0x00000000410fd400,v1,arm/neoverse-v1,core
+0x00000000410fd490,v1,arm/neoverse-n2,core
0x00000000420f5160,v1,cavium/thunderx2,core
0x00000000430f0af0,v1,cavium/thunderx2,core
0x00000000460f0010,v1,fujitsu/a64fx,core
diff --git a/tools/perf/pmu-events/arch/arm64/armv8-recommended.json b/tools/perf/pmu-events/arch/arm64/recommended.json
index d0a19866563d..210afa856091 100644
--- a/tools/perf/pmu-events/arch/arm64/armv8-recommended.json
+++ b/tools/perf/pmu-events/arch/arm64/recommended.json
@@ -148,305 +148,305 @@
"EventCode": "0x60",
"EventName": "BUS_ACCESS_RD",
"BriefDescription": "Bus access read"
- },
- {
+ },
+ {
"PublicDescription": "Bus access write",
"EventCode": "0x61",
"EventName": "BUS_ACCESS_WR",
"BriefDescription": "Bus access write"
- },
- {
+ },
+ {
"PublicDescription": "Bus access, Normal, Cacheable, Shareable",
"EventCode": "0x62",
"EventName": "BUS_ACCESS_SHARED",
"BriefDescription": "Bus access, Normal, Cacheable, Shareable"
- },
- {
+ },
+ {
"PublicDescription": "Bus access, not Normal, Cacheable, Shareable",
"EventCode": "0x63",
"EventName": "BUS_ACCESS_NOT_SHARED",
"BriefDescription": "Bus access, not Normal, Cacheable, Shareable"
- },
- {
+ },
+ {
"PublicDescription": "Bus access, Normal",
"EventCode": "0x64",
"EventName": "BUS_ACCESS_NORMAL",
"BriefDescription": "Bus access, Normal"
- },
- {
+ },
+ {
"PublicDescription": "Bus access, peripheral",
"EventCode": "0x65",
"EventName": "BUS_ACCESS_PERIPH",
"BriefDescription": "Bus access, peripheral"
- },
- {
+ },
+ {
"PublicDescription": "Data memory access, read",
"EventCode": "0x66",
"EventName": "MEM_ACCESS_RD",
"BriefDescription": "Data memory access, read"
- },
- {
+ },
+ {
"PublicDescription": "Data memory access, write",
"EventCode": "0x67",
"EventName": "MEM_ACCESS_WR",
"BriefDescription": "Data memory access, write"
- },
- {
+ },
+ {
"PublicDescription": "Unaligned access, read",
"EventCode": "0x68",
"EventName": "UNALIGNED_LD_SPEC",
"BriefDescription": "Unaligned access, read"
- },
- {
+ },
+ {
"PublicDescription": "Unaligned access, write",
"EventCode": "0x69",
"EventName": "UNALIGNED_ST_SPEC",
"BriefDescription": "Unaligned access, write"
- },
- {
+ },
+ {
"PublicDescription": "Unaligned access",
"EventCode": "0x6a",
"EventName": "UNALIGNED_LDST_SPEC",
"BriefDescription": "Unaligned access"
- },
- {
+ },
+ {
"PublicDescription": "Exclusive operation speculatively executed, LDREX or LDX",
"EventCode": "0x6c",
"EventName": "LDREX_SPEC",
"BriefDescription": "Exclusive operation speculatively executed, LDREX or LDX"
- },
- {
+ },
+ {
"PublicDescription": "Exclusive operation speculatively executed, STREX or STX pass",
"EventCode": "0x6d",
"EventName": "STREX_PASS_SPEC",
"BriefDescription": "Exclusive operation speculatively executed, STREX or STX pass"
- },
- {
+ },
+ {
"PublicDescription": "Exclusive operation speculatively executed, STREX or STX fail",
"EventCode": "0x6e",
"EventName": "STREX_FAIL_SPEC",
"BriefDescription": "Exclusive operation speculatively executed, STREX or STX fail"
- },
- {
+ },
+ {
"PublicDescription": "Exclusive operation speculatively executed, STREX or STX",
"EventCode": "0x6f",
"EventName": "STREX_SPEC",
"BriefDescription": "Exclusive operation speculatively executed, STREX or STX"
- },
- {
+ },
+ {
"PublicDescription": "Operation speculatively executed, load",
"EventCode": "0x70",
"EventName": "LD_SPEC",
"BriefDescription": "Operation speculatively executed, load"
- },
- {
+ },
+ {
"PublicDescription": "Operation speculatively executed, store",
"EventCode": "0x71",
"EventName": "ST_SPEC",
"BriefDescription": "Operation speculatively executed, store"
- },
- {
+ },
+ {
"PublicDescription": "Operation speculatively executed, load or store",
"EventCode": "0x72",
"EventName": "LDST_SPEC",
"BriefDescription": "Operation speculatively executed, load or store"
- },
- {
+ },
+ {
"PublicDescription": "Operation speculatively executed, integer data processing",
"EventCode": "0x73",
"EventName": "DP_SPEC",
"BriefDescription": "Operation speculatively executed, integer data processing"
- },
- {
+ },
+ {
"PublicDescription": "Operation speculatively executed, Advanced SIMD instruction",
"EventCode": "0x74",
"EventName": "ASE_SPEC",
"BriefDescription": "Operation speculatively executed, Advanced SIMD instruction"
- },
- {
+ },
+ {
"PublicDescription": "Operation speculatively executed, floating-point instruction",
"EventCode": "0x75",
"EventName": "VFP_SPEC",
"BriefDescription": "Operation speculatively executed, floating-point instruction"
- },
- {
+ },
+ {
"PublicDescription": "Operation speculatively executed, software change of the PC",
"EventCode": "0x76",
"EventName": "PC_WRITE_SPEC",
"BriefDescription": "Operation speculatively executed, software change of the PC"
- },
- {
+ },
+ {
"PublicDescription": "Operation speculatively executed, Cryptographic instruction",
"EventCode": "0x77",
"EventName": "CRYPTO_SPEC",
"BriefDescription": "Operation speculatively executed, Cryptographic instruction"
- },
- {
+ },
+ {
"PublicDescription": "Branch speculatively executed, immediate branch",
"EventCode": "0x78",
"EventName": "BR_IMMED_SPEC",
"BriefDescription": "Branch speculatively executed, immediate branch"
- },
- {
+ },
+ {
"PublicDescription": "Branch speculatively executed, procedure return",
"EventCode": "0x79",
"EventName": "BR_RETURN_SPEC",
"BriefDescription": "Branch speculatively executed, procedure return"
- },
- {
+ },
+ {
"PublicDescription": "Branch speculatively executed, indirect branch",
"EventCode": "0x7a",
"EventName": "BR_INDIRECT_SPEC",
"BriefDescription": "Branch speculatively executed, indirect branch"
- },
- {
+ },
+ {
"PublicDescription": "Barrier speculatively executed, ISB",
"EventCode": "0x7c",
"EventName": "ISB_SPEC",
"BriefDescription": "Barrier speculatively executed, ISB"
- },
- {
+ },
+ {
"PublicDescription": "Barrier speculatively executed, DSB",
"EventCode": "0x7d",
"EventName": "DSB_SPEC",
"BriefDescription": "Barrier speculatively executed, DSB"
- },
- {
+ },
+ {
"PublicDescription": "Barrier speculatively executed, DMB",
"EventCode": "0x7e",
"EventName": "DMB_SPEC",
"BriefDescription": "Barrier speculatively executed, DMB"
- },
- {
+ },
+ {
"PublicDescription": "Exception taken, Other synchronous",
"EventCode": "0x81",
"EventName": "EXC_UNDEF",
"BriefDescription": "Exception taken, Other synchronous"
- },
- {
+ },
+ {
"PublicDescription": "Exception taken, Supervisor Call",
"EventCode": "0x82",
"EventName": "EXC_SVC",
"BriefDescription": "Exception taken, Supervisor Call"
- },
- {
+ },
+ {
"PublicDescription": "Exception taken, Instruction Abort",
"EventCode": "0x83",
"EventName": "EXC_PABORT",
"BriefDescription": "Exception taken, Instruction Abort"
- },
- {
+ },
+ {
"PublicDescription": "Exception taken, Data Abort and SError",
"EventCode": "0x84",
"EventName": "EXC_DABORT",
"BriefDescription": "Exception taken, Data Abort and SError"
- },
- {
+ },
+ {
"PublicDescription": "Exception taken, IRQ",
"EventCode": "0x86",
"EventName": "EXC_IRQ",
"BriefDescription": "Exception taken, IRQ"
- },
- {
+ },
+ {
"PublicDescription": "Exception taken, FIQ",
"EventCode": "0x87",
"EventName": "EXC_FIQ",
"BriefDescription": "Exception taken, FIQ"
- },
- {
+ },
+ {
"PublicDescription": "Exception taken, Secure Monitor Call",
"EventCode": "0x88",
"EventName": "EXC_SMC",
"BriefDescription": "Exception taken, Secure Monitor Call"
- },
- {
+ },
+ {
"PublicDescription": "Exception taken, Hypervisor Call",
"EventCode": "0x8a",
"EventName": "EXC_HVC",
"BriefDescription": "Exception taken, Hypervisor Call"
- },
- {
+ },
+ {
"PublicDescription": "Exception taken, Instruction Abort not taken locally",
"EventCode": "0x8b",
"EventName": "EXC_TRAP_PABORT",
"BriefDescription": "Exception taken, Instruction Abort not taken locally"
- },
- {
+ },
+ {
"PublicDescription": "Exception taken, Data Abort or SError not taken locally",
"EventCode": "0x8c",
"EventName": "EXC_TRAP_DABORT",
"BriefDescription": "Exception taken, Data Abort or SError not taken locally"
- },
- {
+ },
+ {
"PublicDescription": "Exception taken, Other traps not taken locally",
"EventCode": "0x8d",
"EventName": "EXC_TRAP_OTHER",
"BriefDescription": "Exception taken, Other traps not taken locally"
- },
- {
+ },
+ {
"PublicDescription": "Exception taken, IRQ not taken locally",
"EventCode": "0x8e",
"EventName": "EXC_TRAP_IRQ",
"BriefDescription": "Exception taken, IRQ not taken locally"
- },
- {
+ },
+ {
"PublicDescription": "Exception taken, FIQ not taken locally",
"EventCode": "0x8f",
"EventName": "EXC_TRAP_FIQ",
"BriefDescription": "Exception taken, FIQ not taken locally"
- },
- {
+ },
+ {
"PublicDescription": "Release consistency operation speculatively executed, Load-Acquire",
"EventCode": "0x90",
"EventName": "RC_LD_SPEC",
"BriefDescription": "Release consistency operation speculatively executed, Load-Acquire"
- },
- {
+ },
+ {
"PublicDescription": "Release consistency operation speculatively executed, Store-Release",
"EventCode": "0x91",
"EventName": "RC_ST_SPEC",
"BriefDescription": "Release consistency operation speculatively executed, Store-Release"
- },
- {
+ },
+ {
"PublicDescription": "Attributable Level 3 data or unified cache access, read",
"EventCode": "0xa0",
"EventName": "L3D_CACHE_RD",
"BriefDescription": "Attributable Level 3 data or unified cache access, read"
- },
- {
+ },
+ {
"PublicDescription": "Attributable Level 3 data or unified cache access, write",
"EventCode": "0xa1",
"EventName": "L3D_CACHE_WR",
"BriefDescription": "Attributable Level 3 data or unified cache access, write"
- },
- {
+ },
+ {
"PublicDescription": "Attributable Level 3 data or unified cache refill, read",
"EventCode": "0xa2",
"EventName": "L3D_CACHE_REFILL_RD",
"BriefDescription": "Attributable Level 3 data or unified cache refill, read"
- },
- {
+ },
+ {
"PublicDescription": "Attributable Level 3 data or unified cache refill, write",
"EventCode": "0xa3",
"EventName": "L3D_CACHE_REFILL_WR",
"BriefDescription": "Attributable Level 3 data or unified cache refill, write"
- },
- {
+ },
+ {
"PublicDescription": "Attributable Level 3 data or unified cache Write-Back, victim",
"EventCode": "0xa6",
"EventName": "L3D_CACHE_WB_VICTIM",
"BriefDescription": "Attributable Level 3 data or unified cache Write-Back, victim"
- },
- {
+ },
+ {
"PublicDescription": "Attributable Level 3 data or unified cache Write-Back, cache clean",
"EventCode": "0xa7",
"EventName": "L3D_CACHE_WB_CLEAN",
"BriefDescription": "Attributable Level 3 data or unified cache Write-Back, cache clean"
- },
- {
+ },
+ {
"PublicDescription": "Attributable Level 3 data or unified cache access, invalidate",
"EventCode": "0xa8",
"EventName": "L3D_CACHE_INVAL",
"BriefDescription": "Attributable Level 3 data or unified cache access, invalidate"
- }
+ }
]
diff --git a/tools/perf/pmu-events/arch/test/test_soc/cpu/uncore.json b/tools/perf/pmu-events/arch/test/test_soc/cpu/uncore.json
index 73089c682f80..41bac1c6a008 100644
--- a/tools/perf/pmu-events/arch/test/test_soc/cpu/uncore.json
+++ b/tools/perf/pmu-events/arch/test/test_soc/cpu/uncore.json
@@ -19,6 +19,22 @@
"EdgeDetect": "0"
},
{
+ "Unit": "CBO",
+ "EventCode": "0xE0",
+ "UMask": "0x00",
+ "EventName": "event-hyphen",
+ "BriefDescription": "UNC_CBO_HYPHEN",
+ "PublicDescription": "UNC_CBO_HYPHEN"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0xC0",
+ "UMask": "0x00",
+ "EventName": "event-two-hyph",
+ "BriefDescription": "UNC_CBO_TWO_HYPH",
+ "PublicDescription": "UNC_CBO_TWO_HYPH"
+ },
+ {
"EventCode": "0x7",
"EventName": "uncore_hisi_l3c.rd_hit_cpipe",
"BriefDescription": "Total read hits",
diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c
index 2e7c4153875b..1a57c3f81dd4 100644
--- a/tools/perf/pmu-events/jevents.c
+++ b/tools/perf/pmu-events/jevents.c
@@ -672,8 +672,6 @@ static int json_events(const char *fn,
addfield(map, &je.metric_constraint, "", "", val);
} else if (json_streq(map, field, "MetricExpr")) {
addfield(map, &je.metric_expr, "", "", val);
- for (s = je.metric_expr; *s; s++)
- *s = tolower(*s);
} else if (json_streq(map, field, "ArchStdEvent")) {
addfield(map, &arch_std, "", "", val);
for (s = arch_std; *s; s++)
diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build
index 803ca426f8e6..af2b37ef7c70 100644
--- a/tools/perf/tests/Build
+++ b/tools/perf/tests/Build
@@ -65,6 +65,7 @@ perf-y += pe-file-parsing.o
perf-y += expand-cgroup.o
perf-y += perf-time-to-tsc.o
perf-y += dlfilter-test.o
+perf-y += sigtrap.o
$(OUTPUT)tests/llvm-src-base.c: tests/bpf-script-example.c tests/Build
$(call rule_mkdir)
diff --git a/tools/perf/tests/attr.c b/tools/perf/tests/attr.c
index 0f73e300f207..56fba08a3037 100644
--- a/tools/perf/tests/attr.c
+++ b/tools/perf/tests/attr.c
@@ -65,7 +65,7 @@ do { \
#define WRITE_ASS(field, fmt) __WRITE_ASS(field, fmt, attr->field)
-static int store_event(struct perf_event_attr *attr, pid_t pid, int cpu,
+static int store_event(struct perf_event_attr *attr, pid_t pid, struct perf_cpu cpu,
int fd, int group_fd, unsigned long flags)
{
FILE *file;
@@ -93,7 +93,7 @@ static int store_event(struct perf_event_attr *attr, pid_t pid, int cpu,
/* syscall arguments */
__WRITE_ASS(fd, "d", fd);
__WRITE_ASS(group_fd, "d", group_fd);
- __WRITE_ASS(cpu, "d", cpu);
+ __WRITE_ASS(cpu, "d", cpu.cpu);
__WRITE_ASS(pid, "d", pid);
__WRITE_ASS(flags, "lu", flags);
@@ -144,7 +144,7 @@ static int store_event(struct perf_event_attr *attr, pid_t pid, int cpu,
return 0;
}
-void test_attr__open(struct perf_event_attr *attr, pid_t pid, int cpu,
+void test_attr__open(struct perf_event_attr *attr, pid_t pid, struct perf_cpu cpu,
int fd, int group_fd, unsigned long flags)
{
int errno_saved = errno;
diff --git a/tools/perf/tests/attr/README b/tools/perf/tests/attr/README
index a36f49fb4dbe..1116fc6bf2ac 100644
--- a/tools/perf/tests/attr/README
+++ b/tools/perf/tests/attr/README
@@ -45,8 +45,10 @@ Following tests are defined (with perf commands):
perf record -d kill (test-record-data)
perf record -F 100 kill (test-record-freq)
perf record -g kill (test-record-graph-default)
+ perf record -g kill (test-record-graph-default-aarch64)
perf record --call-graph dwarf kill (test-record-graph-dwarf)
perf record --call-graph fp kill (test-record-graph-fp)
+ perf record --call-graph fp kill (test-record-graph-fp-aarch64)
perf record --group -e cycles,instructions kill (test-record-group)
perf record -e '{cycles,instructions}' kill (test-record-group1)
perf record -e '{cycles/period=1/,instructions/period=2/}:S' kill (test-record-group2)
diff --git a/tools/perf/tests/attr/test-record-graph-default b/tools/perf/tests/attr/test-record-graph-default
index 5d8234d50845..f0a18b4ea4f5 100644
--- a/tools/perf/tests/attr/test-record-graph-default
+++ b/tools/perf/tests/attr/test-record-graph-default
@@ -2,6 +2,8 @@
command = record
args = --no-bpf-event -g kill >/dev/null 2>&1
ret = 1
+# arm64 enables registers in the default mode (fp)
+arch = !aarch64
[event:base-record]
sample_type=295
diff --git a/tools/perf/tests/attr/test-record-graph-default-aarch64 b/tools/perf/tests/attr/test-record-graph-default-aarch64
new file mode 100644
index 000000000000..e98d62efb6f7
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-graph-default-aarch64
@@ -0,0 +1,9 @@
+[config]
+command = record
+args = --no-bpf-event -g kill >/dev/null 2>&1
+ret = 1
+arch = aarch64
+
+[event:base-record]
+sample_type=4391
+sample_regs_user=1073741824
diff --git a/tools/perf/tests/attr/test-record-graph-fp b/tools/perf/tests/attr/test-record-graph-fp
index 5630521c0b0f..a6e60e839205 100644
--- a/tools/perf/tests/attr/test-record-graph-fp
+++ b/tools/perf/tests/attr/test-record-graph-fp
@@ -2,6 +2,8 @@
command = record
args = --no-bpf-event --call-graph fp kill >/dev/null 2>&1
ret = 1
+# arm64 enables registers in fp mode
+arch = !aarch64
[event:base-record]
sample_type=295
diff --git a/tools/perf/tests/attr/test-record-graph-fp-aarch64 b/tools/perf/tests/attr/test-record-graph-fp-aarch64
new file mode 100644
index 000000000000..cbeea9971285
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-graph-fp-aarch64
@@ -0,0 +1,9 @@
+[config]
+command = record
+args = --no-bpf-event --call-graph fp kill >/dev/null 2>&1
+ret = 1
+arch = aarch64
+
+[event:base-record]
+sample_type=4391
+sample_regs_user=1073741824
diff --git a/tools/perf/tests/bitmap.c b/tools/perf/tests/bitmap.c
index 384856347236..4965dd666956 100644
--- a/tools/perf/tests/bitmap.c
+++ b/tools/perf/tests/bitmap.c
@@ -17,8 +17,8 @@ static unsigned long *get_bitmap(const char *str, int nbits)
bm = bitmap_zalloc(nbits);
if (map && bm) {
- for (i = 0; i < map->nr; i++)
- set_bit(map->map[i], bm);
+ for (i = 0; i < perf_cpu_map__nr(map); i++)
+ set_bit(perf_cpu_map__cpu(map, i).cpu, bm);
}
if (map)
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 8cb5a1c3489e..fac3717d9ba1 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -107,6 +107,7 @@ static struct test_suite *generic_tests[] = {
&suite__expand_cgroup_events,
&suite__perf_time_to_tsc,
&suite__dlfilter,
+ &suite__sigtrap,
NULL,
};
@@ -420,7 +421,7 @@ static int run_shell_tests(int argc, const char *argv[], int i, int width,
continue;
st.file = ent->d_name;
- pr_info("%2d: %-*s:", i, width, test_suite.desc);
+ pr_info("%3d: %-*s:", i, width, test_suite.desc);
if (intlist__find(skiplist, i)) {
color_fprintf(stderr, PERF_COLOR_YELLOW, " Skip (user override)\n");
@@ -470,7 +471,7 @@ static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist)
continue;
}
- pr_info("%2d: %-*s:", i, width, test_description(t, -1));
+ pr_info("%3d: %-*s:", i, width, test_description(t, -1));
if (intlist__find(skiplist, i)) {
color_fprintf(stderr, PERF_COLOR_YELLOW, " Skip (user override)\n");
@@ -510,7 +511,7 @@ static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist)
curr, argc, argv))
continue;
- pr_info("%2d.%1d: %-*s:", i, subi + 1, subw,
+ pr_info("%3d.%1d: %-*s:", i, subi + 1, subw,
test_description(t, subi));
test_and_print(t, subi);
}
@@ -545,7 +546,7 @@ static int perf_test__list_shell(int argc, const char **argv, int i)
if (!perf_test__matches(t.desc, curr, argc, argv))
continue;
- pr_info("%2d: %s\n", i, t.desc);
+ pr_info("%3d: %s\n", i, t.desc);
}
@@ -567,14 +568,14 @@ static int perf_test__list(int argc, const char **argv)
if (!perf_test__matches(test_description(t, -1), curr, argc, argv))
continue;
- pr_info("%2d: %s\n", i, test_description(t, -1));
+ pr_info("%3d: %s\n", i, test_description(t, -1));
if (has_subtests(t)) {
int subn = num_subtests(t);
int subi;
for (subi = 0; subi < subn; subi++)
- pr_info("%2d:%1d: %s\n", i, subi + 1,
+ pr_info("%3d:%1d: %s\n", i, subi + 1,
test_description(t, subi));
}
}
@@ -606,6 +607,9 @@ int cmd_test(int argc, const char **argv)
if (ret < 0)
return ret;
+ /* Unbuffered output */
+ setvbuf(stdout, NULL, _IONBF, 0);
+
argc = parse_options_subcommand(argc, argv, test_options, test_subcommands, test_usage, 0);
if (argc >= 1 && !strcmp(argv[0], "list"))
return perf_test__list(argc - 1, argv + 1);
diff --git a/tools/perf/tests/cpumap.c b/tools/perf/tests/cpumap.c
index 89a155092f85..84e87e31f119 100644
--- a/tools/perf/tests/cpumap.c
+++ b/tools/perf/tests/cpumap.c
@@ -38,7 +38,7 @@ static int process_event_mask(struct perf_tool *tool __maybe_unused,
TEST_ASSERT_VAL("wrong nr", map->nr == 20);
for (i = 0; i < 20; i++) {
- TEST_ASSERT_VAL("wrong cpu", map->map[i] == i);
+ TEST_ASSERT_VAL("wrong cpu", map->map[i].cpu == i);
}
perf_cpu_map__put(map);
@@ -67,8 +67,8 @@ static int process_event_cpus(struct perf_tool *tool __maybe_unused,
map = cpu_map__new_data(data);
TEST_ASSERT_VAL("wrong nr", map->nr == 2);
- TEST_ASSERT_VAL("wrong cpu", map->map[0] == 1);
- TEST_ASSERT_VAL("wrong cpu", map->map[1] == 256);
+ TEST_ASSERT_VAL("wrong cpu", map->map[0].cpu == 1);
+ TEST_ASSERT_VAL("wrong cpu", map->map[1].cpu == 256);
TEST_ASSERT_VAL("wrong refcnt", refcount_read(&map->refcnt) == 1);
perf_cpu_map__put(map);
return 0;
diff --git a/tools/perf/tests/event_update.c b/tools/perf/tests/event_update.c
index d01532d40acb..78db4d704e76 100644
--- a/tools/perf/tests/event_update.c
+++ b/tools/perf/tests/event_update.c
@@ -75,10 +75,10 @@ static int process_event_cpus(struct perf_tool *tool __maybe_unused,
TEST_ASSERT_VAL("wrong id", ev->id == 123);
TEST_ASSERT_VAL("wrong type", ev->type == PERF_EVENT_UPDATE__CPUS);
- TEST_ASSERT_VAL("wrong cpus", map->nr == 3);
- TEST_ASSERT_VAL("wrong cpus", map->map[0] == 1);
- TEST_ASSERT_VAL("wrong cpus", map->map[1] == 2);
- TEST_ASSERT_VAL("wrong cpus", map->map[2] == 3);
+ TEST_ASSERT_VAL("wrong cpus", perf_cpu_map__nr(map) == 3);
+ TEST_ASSERT_VAL("wrong cpus", perf_cpu_map__cpu(map, 0).cpu == 1);
+ TEST_ASSERT_VAL("wrong cpus", perf_cpu_map__cpu(map, 1).cpu == 2);
+ TEST_ASSERT_VAL("wrong cpus", perf_cpu_map__cpu(map, 2).cpu == 3);
perf_cpu_map__put(map);
return 0;
}
diff --git a/tools/perf/tests/mem2node.c b/tools/perf/tests/mem2node.c
index b17b86391383..4c96829510c9 100644
--- a/tools/perf/tests/mem2node.c
+++ b/tools/perf/tests/mem2node.c
@@ -25,14 +25,15 @@ static unsigned long *get_bitmap(const char *str, int nbits)
{
struct perf_cpu_map *map = perf_cpu_map__new(str);
unsigned long *bm = NULL;
- int i;
bm = bitmap_zalloc(nbits);
if (map && bm) {
- for (i = 0; i < map->nr; i++) {
- set_bit(map->map[i], bm);
- }
+ struct perf_cpu cpu;
+ int i;
+
+ perf_cpu_map__for_each_cpu(cpu, i, map)
+ set_bit(cpu.cpu, bm);
}
if (map)
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index 90b2feda31ac..c3c17600f29c 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -59,11 +59,12 @@ static int test__basic_mmap(struct test_suite *test __maybe_unused, int subtest
}
CPU_ZERO(&cpu_set);
- CPU_SET(cpus->map[0], &cpu_set);
+ CPU_SET(perf_cpu_map__cpu(cpus, 0).cpu, &cpu_set);
sched_setaffinity(0, sizeof(cpu_set), &cpu_set);
if (sched_setaffinity(0, sizeof(cpu_set), &cpu_set) < 0) {
pr_debug("sched_setaffinity() failed on CPU %d: %s ",
- cpus->map[0], str_error_r(errno, sbuf, sizeof(sbuf)));
+ perf_cpu_map__cpu(cpus, 0).cpu,
+ str_error_r(errno, sbuf, sizeof(sbuf)));
goto out_free_cpus;
}
diff --git a/tools/perf/tests/openat-syscall-all-cpus.c b/tools/perf/tests/openat-syscall-all-cpus.c
index cd3dd463783f..1ab362323d25 100644
--- a/tools/perf/tests/openat-syscall-all-cpus.c
+++ b/tools/perf/tests/openat-syscall-all-cpus.c
@@ -22,7 +22,8 @@
static int test__openat_syscall_event_on_all_cpus(struct test_suite *test __maybe_unused,
int subtest __maybe_unused)
{
- int err = -1, fd, cpu;
+ int err = -1, fd, idx;
+ struct perf_cpu cpu;
struct perf_cpu_map *cpus;
struct evsel *evsel;
unsigned int nr_openat_calls = 111, i;
@@ -58,23 +59,23 @@ static int test__openat_syscall_event_on_all_cpus(struct test_suite *test __mayb
goto out_evsel_delete;
}
- for (cpu = 0; cpu < cpus->nr; ++cpu) {
- unsigned int ncalls = nr_openat_calls + cpu;
+ perf_cpu_map__for_each_cpu(cpu, idx, cpus) {
+ unsigned int ncalls = nr_openat_calls + idx;
/*
* XXX eventually lift this restriction in a way that
* keeps perf building on older glibc installations
* without CPU_ALLOC. 1024 cpus in 2010 still seems
* a reasonable upper limit tho :-)
*/
- if (cpus->map[cpu] >= CPU_SETSIZE) {
- pr_debug("Ignoring CPU %d\n", cpus->map[cpu]);
+ if (cpu.cpu >= CPU_SETSIZE) {
+ pr_debug("Ignoring CPU %d\n", cpu.cpu);
continue;
}
- CPU_SET(cpus->map[cpu], &cpu_set);
+ CPU_SET(cpu.cpu, &cpu_set);
if (sched_setaffinity(0, sizeof(cpu_set), &cpu_set) < 0) {
pr_debug("sched_setaffinity() failed on CPU %d: %s ",
- cpus->map[cpu],
+ cpu.cpu,
str_error_r(errno, sbuf, sizeof(sbuf)));
goto out_close_fd;
}
@@ -82,37 +83,29 @@ static int test__openat_syscall_event_on_all_cpus(struct test_suite *test __mayb
fd = openat(0, "/etc/passwd", O_RDONLY);
close(fd);
}
- CPU_CLR(cpus->map[cpu], &cpu_set);
+ CPU_CLR(cpu.cpu, &cpu_set);
}
- /*
- * Here we need to explicitly preallocate the counts, as if
- * we use the auto allocation it will allocate just for 1 cpu,
- * as we start by cpu 0.
- */
- if (evsel__alloc_counts(evsel, cpus->nr, 1) < 0) {
- pr_debug("evsel__alloc_counts(ncpus=%d)\n", cpus->nr);
- goto out_close_fd;
- }
+ evsel->core.cpus = perf_cpu_map__get(cpus);
err = 0;
- for (cpu = 0; cpu < cpus->nr; ++cpu) {
+ perf_cpu_map__for_each_cpu(cpu, idx, cpus) {
unsigned int expected;
- if (cpus->map[cpu] >= CPU_SETSIZE)
+ if (cpu.cpu >= CPU_SETSIZE)
continue;
- if (evsel__read_on_cpu(evsel, cpu, 0) < 0) {
+ if (evsel__read_on_cpu(evsel, idx, 0) < 0) {
pr_debug("evsel__read_on_cpu\n");
err = -1;
break;
}
- expected = nr_openat_calls + cpu;
- if (perf_counts(evsel->counts, cpu, 0)->val != expected) {
+ expected = nr_openat_calls + idx;
+ if (perf_counts(evsel->counts, idx, 0)->val != expected) {
pr_debug("evsel__read_on_cpu: expected to intercept %d calls on cpu %d, got %" PRIu64 "\n",
- expected, cpus->map[cpu], perf_counts(evsel->counts, cpu, 0)->val);
+ expected, cpu.cpu, perf_counts(evsel->counts, idx, 0)->val);
err = -1;
}
}
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index a508f1dbcb2a..e71efadb24f5 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -2069,6 +2069,31 @@ static int test_event(struct evlist_test *e)
return ret;
}
+static int test_event_fake_pmu(const char *str)
+{
+ struct parse_events_error err;
+ struct evlist *evlist;
+ int ret;
+
+ evlist = evlist__new();
+ if (!evlist)
+ return -ENOMEM;
+
+ parse_events_error__init(&err);
+ perf_pmu__test_parse_init();
+ ret = __parse_events(evlist, str, &err, &perf_pmu__fake);
+ if (ret) {
+ pr_debug("failed to parse event '%s', err %d, str '%s'\n",
+ str, ret, err.str);
+ parse_events_error__print(&err, str);
+ }
+
+ parse_events_error__exit(&err);
+ evlist__delete(evlist);
+
+ return ret;
+}
+
static int test_events(struct evlist_test *events, unsigned cnt)
{
int ret1, ret2 = 0;
@@ -2276,6 +2301,26 @@ static int test_pmu_events_alias(char *event, char *alias)
return test_event(&e);
}
+static int test_pmu_events_alias2(void)
+{
+ static const char events[][30] = {
+ "event-hyphen",
+ "event-two-hyph",
+ };
+ unsigned long i;
+ int ret = 0;
+
+ for (i = 0; i < ARRAY_SIZE(events); i++) {
+ ret = test_event_fake_pmu(&events[i][0]);
+ if (ret) {
+ pr_err("check_parse_fake %s failed\n", &events[i][0]);
+ break;
+ }
+ }
+
+ return ret;
+}
+
static int test__parse_events(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
{
int ret1, ret2 = 0;
@@ -2313,6 +2358,10 @@ do { \
return ret;
}
+ ret1 = test_pmu_events_alias2();
+ if (!ret2)
+ ret2 = ret1;
+
ret1 = test_terms(test__terms, ARRAY_SIZE(test__terms));
if (!ret2)
ret2 = ret1;
diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c
index df1c9a3cc05b..1c695fb5a79c 100644
--- a/tools/perf/tests/pmu-events.c
+++ b/tools/perf/tests/pmu-events.c
@@ -143,6 +143,34 @@ static const struct perf_pmu_test_event unc_cbo_xsnp_response_miss_eviction = {
.matching_pmu = "uncore_cbox_0",
};
+static const struct perf_pmu_test_event uncore_hyphen = {
+ .event = {
+ .name = "event-hyphen",
+ .event = "umask=0x00,event=0xe0",
+ .desc = "Unit: uncore_cbox UNC_CBO_HYPHEN",
+ .topic = "uncore",
+ .long_desc = "UNC_CBO_HYPHEN",
+ .pmu = "uncore_cbox",
+ },
+ .alias_str = "umask=0,event=0xe0",
+ .alias_long_desc = "UNC_CBO_HYPHEN",
+ .matching_pmu = "uncore_cbox_0",
+};
+
+static const struct perf_pmu_test_event uncore_two_hyph = {
+ .event = {
+ .name = "event-two-hyph",
+ .event = "umask=0x00,event=0xc0",
+ .desc = "Unit: uncore_cbox UNC_CBO_TWO_HYPH",
+ .topic = "uncore",
+ .long_desc = "UNC_CBO_TWO_HYPH",
+ .pmu = "uncore_cbox",
+ },
+ .alias_str = "umask=0,event=0xc0",
+ .alias_long_desc = "UNC_CBO_TWO_HYPH",
+ .matching_pmu = "uncore_cbox_0",
+};
+
static const struct perf_pmu_test_event uncore_hisi_l3c_rd_hit_cpipe = {
.event = {
.name = "uncore_hisi_l3c.rd_hit_cpipe",
@@ -188,6 +216,8 @@ static const struct perf_pmu_test_event uncore_imc_cache_hits = {
static const struct perf_pmu_test_event *uncore_events[] = {
&uncore_hisi_ddrc_flux_wcmd,
&unc_cbo_xsnp_response_miss_eviction,
+ &uncore_hyphen,
+ &uncore_two_hyph,
&uncore_hisi_l3c_rd_hit_cpipe,
&uncore_imc_free_running_cache_miss,
&uncore_imc_cache_hits,
@@ -654,6 +684,8 @@ static struct perf_pmu_test_pmu test_pmus[] = {
},
.aliases = {
&unc_cbo_xsnp_response_miss_eviction,
+ &uncore_hyphen,
+ &uncore_two_hyph,
},
},
{
diff --git a/tools/perf/tests/shell/stat_all_metricgroups.sh b/tools/perf/tests/shell/stat_all_metricgroups.sh
index de24d374ce24..cb35e488809a 100755
--- a/tools/perf/tests/shell/stat_all_metricgroups.sh
+++ b/tools/perf/tests/shell/stat_all_metricgroups.sh
@@ -6,7 +6,7 @@ set -e
for m in $(perf list --raw-dump metricgroups); do
echo "Testing $m"
- perf stat -M "$m" true
+ perf stat -M "$m" -a true
done
exit 0
diff --git a/tools/perf/tests/sigtrap.c b/tools/perf/tests/sigtrap.c
new file mode 100644
index 000000000000..e32ece90e164
--- /dev/null
+++ b/tools/perf/tests/sigtrap.c
@@ -0,0 +1,164 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Basic test for sigtrap support.
+ *
+ * Copyright (C) 2021, Google LLC.
+ */
+
+#include <errno.h>
+#include <stdint.h>
+#include <stdlib.h>
+#include <linux/hw_breakpoint.h>
+#include <linux/string.h>
+#include <pthread.h>
+#include <signal.h>
+#include <sys/ioctl.h>
+#include <sys/syscall.h>
+#include <unistd.h>
+
+#include "cloexec.h"
+#include "debug.h"
+#include "event.h"
+#include "tests.h"
+#include "../perf-sys.h"
+
+#define NUM_THREADS 5
+
+static struct {
+ int tids_want_signal; /* Which threads still want a signal. */
+ int signal_count; /* Sanity check number of signals received. */
+ volatile int iterate_on; /* Variable to set breakpoint on. */
+ siginfo_t first_siginfo; /* First observed siginfo_t. */
+} ctx;
+
+#define TEST_SIG_DATA (~(unsigned long)(&ctx.iterate_on))
+
+static struct perf_event_attr make_event_attr(void)
+{
+ struct perf_event_attr attr = {
+ .type = PERF_TYPE_BREAKPOINT,
+ .size = sizeof(attr),
+ .sample_period = 1,
+ .disabled = 1,
+ .bp_addr = (unsigned long)&ctx.iterate_on,
+ .bp_type = HW_BREAKPOINT_RW,
+ .bp_len = HW_BREAKPOINT_LEN_1,
+ .inherit = 1, /* Children inherit events ... */
+ .inherit_thread = 1, /* ... but only cloned with CLONE_THREAD. */
+ .remove_on_exec = 1, /* Required by sigtrap. */
+ .sigtrap = 1, /* Request synchronous SIGTRAP on event. */
+ .sig_data = TEST_SIG_DATA,
+ .exclude_kernel = 1, /* To allow */
+ .exclude_hv = 1, /* running as !root */
+ };
+ return attr;
+}
+
+static void
+sigtrap_handler(int signum __maybe_unused, siginfo_t *info, void *ucontext __maybe_unused)
+{
+ if (!__atomic_fetch_add(&ctx.signal_count, 1, __ATOMIC_RELAXED))
+ ctx.first_siginfo = *info;
+ __atomic_fetch_sub(&ctx.tids_want_signal, syscall(SYS_gettid), __ATOMIC_RELAXED);
+}
+
+static void *test_thread(void *arg)
+{
+ pthread_barrier_t *barrier = (pthread_barrier_t *)arg;
+ pid_t tid = syscall(SYS_gettid);
+ int i;
+
+ pthread_barrier_wait(barrier);
+
+ __atomic_fetch_add(&ctx.tids_want_signal, tid, __ATOMIC_RELAXED);
+ for (i = 0; i < ctx.iterate_on - 1; i++)
+ __atomic_fetch_add(&ctx.tids_want_signal, tid, __ATOMIC_RELAXED);
+
+ return NULL;
+}
+
+static int run_test_threads(pthread_t *threads, pthread_barrier_t *barrier)
+{
+ int i;
+
+ pthread_barrier_wait(barrier);
+ for (i = 0; i < NUM_THREADS; i++)
+ TEST_ASSERT_EQUAL("pthread_join() failed", pthread_join(threads[i], NULL), 0);
+
+ return TEST_OK;
+}
+
+static int run_stress_test(int fd, pthread_t *threads, pthread_barrier_t *barrier)
+{
+ int ret;
+
+ ctx.iterate_on = 3000;
+
+ TEST_ASSERT_EQUAL("misfired signal?", ctx.signal_count, 0);
+ TEST_ASSERT_EQUAL("enable failed", ioctl(fd, PERF_EVENT_IOC_ENABLE, 0), 0);
+ ret = run_test_threads(threads, barrier);
+ TEST_ASSERT_EQUAL("disable failed", ioctl(fd, PERF_EVENT_IOC_DISABLE, 0), 0);
+
+ TEST_ASSERT_EQUAL("unexpected sigtraps", ctx.signal_count, NUM_THREADS * ctx.iterate_on);
+ TEST_ASSERT_EQUAL("missing signals or incorrectly delivered", ctx.tids_want_signal, 0);
+ TEST_ASSERT_VAL("unexpected si_addr", ctx.first_siginfo.si_addr == &ctx.iterate_on);
+#if 0 /* FIXME: enable when libc's signal.h has si_perf_{type,data} */
+ TEST_ASSERT_EQUAL("unexpected si_perf_type", ctx.first_siginfo.si_perf_type,
+ PERF_TYPE_BREAKPOINT);
+ TEST_ASSERT_EQUAL("unexpected si_perf_data", ctx.first_siginfo.si_perf_data,
+ TEST_SIG_DATA);
+#endif
+
+ return ret;
+}
+
+static int test__sigtrap(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
+{
+ struct perf_event_attr attr = make_event_attr();
+ struct sigaction action = {};
+ struct sigaction oldact;
+ pthread_t threads[NUM_THREADS];
+ pthread_barrier_t barrier;
+ char sbuf[STRERR_BUFSIZE];
+ int i, fd, ret = TEST_FAIL;
+
+ if (!BP_SIGNAL_IS_SUPPORTED) {
+ pr_debug("Test not supported on this architecture");
+ return TEST_SKIP;
+ }
+
+ pthread_barrier_init(&barrier, NULL, NUM_THREADS + 1);
+
+ action.sa_flags = SA_SIGINFO | SA_NODEFER;
+ action.sa_sigaction = sigtrap_handler;
+ sigemptyset(&action.sa_mask);
+ if (sigaction(SIGTRAP, &action, &oldact)) {
+ pr_debug("FAILED sigaction(): %s\n", str_error_r(errno, sbuf, sizeof(sbuf)));
+ goto out;
+ }
+
+ fd = sys_perf_event_open(&attr, 0, -1, -1, perf_event_open_cloexec_flag());
+ if (fd < 0) {
+ pr_debug("FAILED sys_perf_event_open(): %s\n", str_error_r(errno, sbuf, sizeof(sbuf)));
+ goto out_restore_sigaction;
+ }
+
+ for (i = 0; i < NUM_THREADS; i++) {
+ if (pthread_create(&threads[i], NULL, test_thread, &barrier)) {
+ pr_debug("FAILED pthread_create(): %s\n", str_error_r(errno, sbuf, sizeof(sbuf)));
+ goto out_close_perf_event;
+ }
+ }
+
+ ret = run_stress_test(fd, threads, &barrier);
+
+out_close_perf_event:
+ close(fd);
+out_restore_sigaction:
+ sigaction(SIGTRAP, &oldact, NULL);
+out:
+ pthread_barrier_destroy(&barrier);
+ return ret;
+}
+
+DEFINE_SUITE("Sigtrap", sigtrap);
diff --git a/tools/perf/tests/stat.c b/tools/perf/tests/stat.c
index 2eb096b5e6da..500974040fe3 100644
--- a/tools/perf/tests/stat.c
+++ b/tools/perf/tests/stat.c
@@ -87,7 +87,8 @@ static int test__synthesize_stat(struct test_suite *test __maybe_unused, int sub
count.run = 300;
TEST_ASSERT_VAL("failed to synthesize stat_config",
- !perf_event__synthesize_stat(NULL, 1, 2, 3, &count, process_stat_event, NULL));
+ !perf_event__synthesize_stat(NULL, (struct perf_cpu){.cpu = 1}, 2, 3,
+ &count, process_stat_event, NULL));
return 0;
}
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index 8f65098110fc..5bbb8f6a48fc 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -146,6 +146,7 @@ DECLARE_SUITE(pe_file_parsing);
DECLARE_SUITE(expand_cgroup_events);
DECLARE_SUITE(perf_time_to_tsc);
DECLARE_SUITE(dlfilter);
+DECLARE_SUITE(sigtrap);
/*
* PowerPC and S390 do not support creation of instruction breakpoints using the
diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c
index 869986139146..ee1e3dcbc0bd 100644
--- a/tools/perf/tests/topology.c
+++ b/tools/perf/tests/topology.c
@@ -112,62 +112,88 @@ static int check_cpu_topology(char *path, struct perf_cpu_map *map)
TEST_ASSERT_VAL("Session header CPU map not set", session->header.env.cpu);
for (i = 0; i < session->header.env.nr_cpus_avail; i++) {
- if (!cpu_map__has(map, i))
+ struct perf_cpu cpu = { .cpu = i };
+
+ if (!perf_cpu_map__has(map, cpu))
continue;
pr_debug("CPU %d, core %d, socket %d\n", i,
session->header.env.cpu[i].core_id,
session->header.env.cpu[i].socket_id);
}
+ // Test that CPU ID contains socket, die, core and CPU
+ for (i = 0; i < perf_cpu_map__nr(map); i++) {
+ id = aggr_cpu_id__cpu(perf_cpu_map__cpu(map, i), NULL);
+ TEST_ASSERT_VAL("Cpu map - CPU ID doesn't match",
+ perf_cpu_map__cpu(map, i).cpu == id.cpu.cpu);
+
+ TEST_ASSERT_VAL("Cpu map - Core ID doesn't match",
+ session->header.env.cpu[perf_cpu_map__cpu(map, i).cpu].core_id == id.core);
+ TEST_ASSERT_VAL("Cpu map - Socket ID doesn't match",
+ session->header.env.cpu[perf_cpu_map__cpu(map, i).cpu].socket_id ==
+ id.socket);
+
+ TEST_ASSERT_VAL("Cpu map - Die ID doesn't match",
+ session->header.env.cpu[perf_cpu_map__cpu(map, i).cpu].die_id == id.die);
+ TEST_ASSERT_VAL("Cpu map - Node ID is set", id.node == -1);
+ TEST_ASSERT_VAL("Cpu map - Thread is set", id.thread == -1);
+ }
+
// Test that core ID contains socket, die and core
- for (i = 0; i < map->nr; i++) {
- id = cpu_map__get_core(map, i, NULL);
+ for (i = 0; i < perf_cpu_map__nr(map); i++) {
+ id = aggr_cpu_id__core(perf_cpu_map__cpu(map, i), NULL);
TEST_ASSERT_VAL("Core map - Core ID doesn't match",
- session->header.env.cpu[map->map[i]].core_id == id.core);
+ session->header.env.cpu[perf_cpu_map__cpu(map, i).cpu].core_id == id.core);
TEST_ASSERT_VAL("Core map - Socket ID doesn't match",
- session->header.env.cpu[map->map[i]].socket_id == id.socket);
+ session->header.env.cpu[perf_cpu_map__cpu(map, i).cpu].socket_id ==
+ id.socket);
TEST_ASSERT_VAL("Core map - Die ID doesn't match",
- session->header.env.cpu[map->map[i]].die_id == id.die);
+ session->header.env.cpu[perf_cpu_map__cpu(map, i).cpu].die_id == id.die);
TEST_ASSERT_VAL("Core map - Node ID is set", id.node == -1);
TEST_ASSERT_VAL("Core map - Thread is set", id.thread == -1);
}
// Test that die ID contains socket and die
- for (i = 0; i < map->nr; i++) {
- id = cpu_map__get_die(map, i, NULL);
+ for (i = 0; i < perf_cpu_map__nr(map); i++) {
+ id = aggr_cpu_id__die(perf_cpu_map__cpu(map, i), NULL);
TEST_ASSERT_VAL("Die map - Socket ID doesn't match",
- session->header.env.cpu[map->map[i]].socket_id == id.socket);
+ session->header.env.cpu[perf_cpu_map__cpu(map, i).cpu].socket_id ==
+ id.socket);
TEST_ASSERT_VAL("Die map - Die ID doesn't match",
- session->header.env.cpu[map->map[i]].die_id == id.die);
+ session->header.env.cpu[perf_cpu_map__cpu(map, i).cpu].die_id == id.die);
TEST_ASSERT_VAL("Die map - Node ID is set", id.node == -1);
TEST_ASSERT_VAL("Die map - Core is set", id.core == -1);
+ TEST_ASSERT_VAL("Die map - CPU is set", id.cpu.cpu == -1);
TEST_ASSERT_VAL("Die map - Thread is set", id.thread == -1);
}
// Test that socket ID contains only socket
- for (i = 0; i < map->nr; i++) {
- id = cpu_map__get_socket(map, i, NULL);
+ for (i = 0; i < perf_cpu_map__nr(map); i++) {
+ id = aggr_cpu_id__socket(perf_cpu_map__cpu(map, i), NULL);
TEST_ASSERT_VAL("Socket map - Socket ID doesn't match",
- session->header.env.cpu[map->map[i]].socket_id == id.socket);
+ session->header.env.cpu[perf_cpu_map__cpu(map, i).cpu].socket_id ==
+ id.socket);
TEST_ASSERT_VAL("Socket map - Node ID is set", id.node == -1);
TEST_ASSERT_VAL("Socket map - Die ID is set", id.die == -1);
TEST_ASSERT_VAL("Socket map - Core is set", id.core == -1);
+ TEST_ASSERT_VAL("Socket map - CPU is set", id.cpu.cpu == -1);
TEST_ASSERT_VAL("Socket map - Thread is set", id.thread == -1);
}
// Test that node ID contains only node
- for (i = 0; i < map->nr; i++) {
- id = cpu_map__get_node(map, i, NULL);
+ for (i = 0; i < perf_cpu_map__nr(map); i++) {
+ id = aggr_cpu_id__node(perf_cpu_map__cpu(map, i), NULL);
TEST_ASSERT_VAL("Node map - Node ID doesn't match",
- cpu__get_node(map->map[i]) == id.node);
+ cpu__get_node(perf_cpu_map__cpu(map, i)) == id.node);
TEST_ASSERT_VAL("Node map - Socket is set", id.socket == -1);
TEST_ASSERT_VAL("Node map - Die ID is set", id.die == -1);
TEST_ASSERT_VAL("Node map - Core is set", id.core == -1);
+ TEST_ASSERT_VAL("Node map - CPU is set", id.cpu.cpu == -1);
TEST_ASSERT_VAL("Node map - Thread is set", id.thread == -1);
}
perf_session__delete(session);
diff --git a/tools/perf/trace/beauty/prctl_option.sh b/tools/perf/trace/beauty/prctl_option.sh
index 3109d7b05e11..3d278785fe57 100755
--- a/tools/perf/trace/beauty/prctl_option.sh
+++ b/tools/perf/trace/beauty/prctl_option.sh
@@ -4,7 +4,7 @@
[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
printf "static const char *prctl_options[] = {\n"
-regex='^#define[[:space:]]+PR_(\w+)[[:space:]]*([[:xdigit:]]+).*'
+regex='^#define[[:space:]]{1}PR_(\w+)[[:space:]]*([[:xdigit:]]+)([[:space:]]*\/.*)?$'
egrep $regex ${header_dir}/prctl.h | grep -v PR_SET_PTRACER | \
sed -r "s/$regex/\2 \1/g" | \
sort -n | xargs printf "\t[%s] = \"%s\",\n"
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index e81c2493efdf..44ba900828f6 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -966,6 +966,7 @@ int symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel,
.opts = opts,
};
int ret = -1, err;
+ int not_annotated = list_empty(&notes->src->source);
if (sym == NULL)
return -1;
@@ -973,13 +974,15 @@ int symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel,
if (ms->map->dso->annotate_warned)
return -1;
- err = symbol__annotate2(ms, evsel, opts, &browser.arch);
- if (err) {
- char msg[BUFSIZ];
- ms->map->dso->annotate_warned = true;
- symbol__strerror_disassemble(ms, err, msg, sizeof(msg));
- ui__error("Couldn't annotate %s:\n%s", sym->name, msg);
- goto out_free_offsets;
+ if (not_annotated) {
+ err = symbol__annotate2(ms, evsel, opts, &browser.arch);
+ if (err) {
+ char msg[BUFSIZ];
+ ms->map->dso->annotate_warned = true;
+ symbol__strerror_disassemble(ms, err, msg, sizeof(msg));
+ ui__error("Couldn't annotate %s:\n%s", sym->name, msg);
+ goto out_free_offsets;
+ }
}
ui_helpline__push("Press ESC to exit");
@@ -994,9 +997,11 @@ int symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel,
ret = annotate_browser__run(&browser, evsel, hbt);
- annotated_source__purge(notes->src);
+ if(not_annotated)
+ annotated_source__purge(notes->src);
out_free_offsets:
- zfree(&notes->offsets);
+ if(not_annotated)
+ zfree(&notes->offsets);
return ret;
}
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 2e5bfbb69960..2a403cefcaf2 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -1,3 +1,4 @@
+perf-y += arm64-frame-pointer-unwind-support.o
perf-y += annotate.o
perf-y += block-info.o
perf-y += block-range.o
@@ -144,6 +145,7 @@ perf-$(CONFIG_LIBBPF) += bpf-loader.o
perf-$(CONFIG_LIBBPF) += bpf_map.o
perf-$(CONFIG_PERF_BPF_SKEL) += bpf_counter.o
perf-$(CONFIG_PERF_BPF_SKEL) += bpf_counter_cgroup.o
+perf-$(CONFIG_PERF_BPF_SKEL) += bpf_ftrace.o
perf-$(CONFIG_BPF_PROLOGUE) += bpf-prologue.o
perf-$(CONFIG_LIBELF) += symbol-elf.o
perf-$(CONFIG_LIBELF) += probe-file.o
diff --git a/tools/perf/util/affinity.c b/tools/perf/util/affinity.c
index 7b12bd7a3080..4d216c0dc425 100644
--- a/tools/perf/util/affinity.c
+++ b/tools/perf/util/affinity.c
@@ -11,7 +11,7 @@
static int get_cpu_set_size(void)
{
- int sz = cpu__max_cpu() + 8 - 1;
+ int sz = cpu__max_cpu().cpu + 8 - 1;
/*
* sched_getaffinity doesn't like masks smaller than the kernel.
* Hopefully that's big enough.
@@ -62,7 +62,7 @@ void affinity__set(struct affinity *a, int cpu)
clear_bit(cpu, a->sched_cpus);
}
-void affinity__cleanup(struct affinity *a)
+static void __affinity__cleanup(struct affinity *a)
{
int cpu_set_size = get_cpu_set_size();
@@ -71,3 +71,9 @@ void affinity__cleanup(struct affinity *a)
zfree(&a->sched_cpus);
zfree(&a->orig_cpus);
}
+
+void affinity__cleanup(struct affinity *a)
+{
+ if (a != NULL)
+ __affinity__cleanup(a);
+}
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 01900689dc00..8190a124b99d 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -2036,6 +2036,7 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
memset(&objdump_process, 0, sizeof(objdump_process));
objdump_process.argv = objdump_argv;
objdump_process.out = -1;
+ objdump_process.err = -1;
if (start_command(&objdump_process)) {
pr_err("Failure starting to run %s\n", command);
err = -1;
diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c
index 3fc528c9270c..5e390a1a79ab 100644
--- a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c
+++ b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c
@@ -179,6 +179,8 @@ static int arm_spe_read_record(struct arm_spe_decoder *decoder)
decoder->record.phys_addr = ip;
break;
case ARM_SPE_COUNTER:
+ if (idx == SPE_CNT_PKT_HDR_INDEX_TOTAL_LAT)
+ decoder->record.latency = payload;
break;
case ARM_SPE_CONTEXT:
decoder->record.context_id = payload;
diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h
index 46a8556a9e95..69b31084d6be 100644
--- a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h
+++ b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h
@@ -33,6 +33,7 @@ struct arm_spe_record {
enum arm_spe_sample_type type;
int err;
u32 op;
+ u32 latency;
u64 from_ip;
u64 to_ip;
u64 timestamp;
diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
index fccac06b573a..d2b64e3f588b 100644
--- a/tools/perf/util/arm-spe.c
+++ b/tools/perf/util/arm-spe.c
@@ -58,6 +58,8 @@ struct arm_spe {
u8 sample_branch;
u8 sample_remote_access;
u8 sample_memory;
+ u8 sample_instructions;
+ u64 instructions_sample_period;
u64 l1d_miss_id;
u64 l1d_access_id;
@@ -68,6 +70,7 @@ struct arm_spe {
u64 branch_miss_id;
u64 remote_access_id;
u64 memory_id;
+ u64 instructions_id;
u64 kernel_start;
@@ -90,6 +93,7 @@ struct arm_spe_queue {
u64 time;
u64 timestamp;
struct thread *thread;
+ u64 period_instructions;
};
static void arm_spe_dump(struct arm_spe *spe __maybe_unused,
@@ -202,6 +206,7 @@ static struct arm_spe_queue *arm_spe__alloc_queue(struct arm_spe *spe,
speq->pid = -1;
speq->tid = -1;
speq->cpu = -1;
+ speq->period_instructions = 0;
/* params set */
params.get_trace = arm_spe_get_trace;
@@ -330,6 +335,7 @@ static int arm_spe__synth_mem_sample(struct arm_spe_queue *speq,
sample.addr = record->virt_addr;
sample.phys_addr = record->phys_addr;
sample.data_src = data_src;
+ sample.weight = record->latency;
return arm_spe_deliver_synth_event(spe, speq, event, &sample);
}
@@ -347,6 +353,36 @@ static int arm_spe__synth_branch_sample(struct arm_spe_queue *speq,
sample.id = spe_events_id;
sample.stream_id = spe_events_id;
sample.addr = record->to_ip;
+ sample.weight = record->latency;
+
+ return arm_spe_deliver_synth_event(spe, speq, event, &sample);
+}
+
+static int arm_spe__synth_instruction_sample(struct arm_spe_queue *speq,
+ u64 spe_events_id, u64 data_src)
+{
+ struct arm_spe *spe = speq->spe;
+ struct arm_spe_record *record = &speq->decoder->record;
+ union perf_event *event = speq->event_buf;
+ struct perf_sample sample = { .ip = 0, };
+
+ /*
+ * Handles perf instruction sampling period.
+ */
+ speq->period_instructions++;
+ if (speq->period_instructions < spe->instructions_sample_period)
+ return 0;
+ speq->period_instructions = 0;
+
+ arm_spe_prep_sample(spe, speq, event, &sample);
+
+ sample.id = spe_events_id;
+ sample.stream_id = spe_events_id;
+ sample.addr = record->virt_addr;
+ sample.phys_addr = record->phys_addr;
+ sample.data_src = data_src;
+ sample.period = spe->instructions_sample_period;
+ sample.weight = record->latency;
return arm_spe_deliver_synth_event(spe, speq, event, &sample);
}
@@ -480,6 +516,12 @@ static int arm_spe_sample(struct arm_spe_queue *speq)
return err;
}
+ if (spe->sample_instructions) {
+ err = arm_spe__synth_instruction_sample(speq, spe->instructions_id, data_src);
+ if (err)
+ return err;
+ }
+
return 0;
}
@@ -993,7 +1035,8 @@ arm_spe_synth_events(struct arm_spe *spe, struct perf_session *session)
attr.type = PERF_TYPE_HARDWARE;
attr.sample_type = evsel->core.attr.sample_type & PERF_SAMPLE_MASK;
attr.sample_type |= PERF_SAMPLE_IP | PERF_SAMPLE_TID |
- PERF_SAMPLE_PERIOD | PERF_SAMPLE_DATA_SRC;
+ PERF_SAMPLE_PERIOD | PERF_SAMPLE_DATA_SRC |
+ PERF_SAMPLE_WEIGHT;
if (spe->timeless_decoding)
attr.sample_type &= ~(u64)PERF_SAMPLE_TIME;
else
@@ -1107,7 +1150,29 @@ arm_spe_synth_events(struct arm_spe *spe, struct perf_session *session)
return err;
spe->memory_id = id;
arm_spe_set_event_name(evlist, id, "memory");
+ id += 1;
+ }
+
+ if (spe->synth_opts.instructions) {
+ if (spe->synth_opts.period_type != PERF_ITRACE_PERIOD_INSTRUCTIONS) {
+ pr_warning("Only instruction-based sampling period is currently supported by Arm SPE.\n");
+ goto synth_instructions_out;
+ }
+ if (spe->synth_opts.period > 1)
+ pr_warning("Arm SPE has a hardware-based sample period.\n"
+ "Additional instruction events will be discarded by --itrace\n");
+
+ spe->sample_instructions = true;
+ attr.config = PERF_COUNT_HW_INSTRUCTIONS;
+ attr.sample_period = spe->synth_opts.period;
+ spe->instructions_sample_period = attr.sample_period;
+ err = arm_spe_synth_event(session, &attr, id);
+ if (err)
+ return err;
+ spe->instructions_id = id;
+ arm_spe_set_event_name(evlist, id, "instructions");
}
+synth_instructions_out:
return 0;
}
diff --git a/tools/perf/util/arm64-frame-pointer-unwind-support.c b/tools/perf/util/arm64-frame-pointer-unwind-support.c
new file mode 100644
index 000000000000..2242a885fbd7
--- /dev/null
+++ b/tools/perf/util/arm64-frame-pointer-unwind-support.c
@@ -0,0 +1,63 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "arm64-frame-pointer-unwind-support.h"
+#include "callchain.h"
+#include "event.h"
+#include "perf_regs.h" // SMPL_REG_MASK
+#include "unwind.h"
+
+#define perf_event_arm_regs perf_event_arm64_regs
+#include "../../arch/arm64/include/uapi/asm/perf_regs.h"
+#undef perf_event_arm_regs
+
+struct entries {
+ u64 stack[2];
+ size_t length;
+};
+
+static bool get_leaf_frame_caller_enabled(struct perf_sample *sample)
+{
+ return callchain_param.record_mode == CALLCHAIN_FP && sample->user_regs.regs
+ && sample->user_regs.mask & SMPL_REG_MASK(PERF_REG_ARM64_LR);
+}
+
+static int add_entry(struct unwind_entry *entry, void *arg)
+{
+ struct entries *entries = arg;
+
+ entries->stack[entries->length++] = entry->ip;
+ return 0;
+}
+
+u64 get_leaf_frame_caller_aarch64(struct perf_sample *sample, struct thread *thread, int usr_idx)
+{
+ int ret;
+ struct entries entries = {};
+ struct regs_dump old_regs = sample->user_regs;
+
+ if (!get_leaf_frame_caller_enabled(sample))
+ return 0;
+
+ /*
+ * If PC and SP are not recorded, get the value of PC from the stack
+ * and set its mask. SP is not used when doing the unwinding but it
+ * still needs to be set to prevent failures.
+ */
+
+ if (!(sample->user_regs.mask & SMPL_REG_MASK(PERF_REG_ARM64_PC))) {
+ sample->user_regs.cache_mask |= SMPL_REG_MASK(PERF_REG_ARM64_PC);
+ sample->user_regs.cache_regs[PERF_REG_ARM64_PC] = sample->callchain->ips[usr_idx+1];
+ }
+
+ if (!(sample->user_regs.mask & SMPL_REG_MASK(PERF_REG_ARM64_SP))) {
+ sample->user_regs.cache_mask |= SMPL_REG_MASK(PERF_REG_ARM64_SP);
+ sample->user_regs.cache_regs[PERF_REG_ARM64_SP] = 0;
+ }
+
+ ret = unwind__get_entries(add_entry, &entries, thread, sample, 2);
+ sample->user_regs = old_regs;
+
+ if (ret || entries.length != 2)
+ return ret;
+
+ return callchain_param.order == ORDER_CALLER ? entries.stack[0] : entries.stack[1];
+}
diff --git a/tools/perf/util/arm64-frame-pointer-unwind-support.h b/tools/perf/util/arm64-frame-pointer-unwind-support.h
new file mode 100644
index 000000000000..32af9ce94398
--- /dev/null
+++ b/tools/perf/util/arm64-frame-pointer-unwind-support.h
@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __PERF_ARM_FRAME_POINTER_UNWIND_SUPPORT_H
+#define __PERF_ARM_FRAME_POINTER_UNWIND_SUPPORT_H
+
+#include "event.h"
+#include "thread.h"
+
+u64 get_leaf_frame_caller_aarch64(struct perf_sample *sample, struct thread *thread, int user_idx);
+
+#endif /* __PERF_ARM_FRAME_POINTER_UNWIND_SUPPORT_H */
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index c679394b898d..825336304a37 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -123,7 +123,7 @@ int auxtrace_mmap__mmap(struct auxtrace_mmap *mm,
mm->prev = 0;
mm->idx = mp->idx;
mm->tid = mp->tid;
- mm->cpu = mp->cpu;
+ mm->cpu = mp->cpu.cpu;
if (!mp->len) {
mm->base = NULL;
@@ -174,13 +174,13 @@ void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp,
mp->idx = idx;
if (per_cpu) {
- mp->cpu = evlist->core.cpus->map[idx];
+ mp->cpu = perf_cpu_map__cpu(evlist->core.cpus, idx);
if (evlist->core.threads)
mp->tid = perf_thread_map__pid(evlist->core.threads, 0);
else
mp->tid = -1;
} else {
- mp->cpu = -1;
+ mp->cpu.cpu = -1;
mp->tid = perf_thread_map__pid(evlist->core.threads, idx);
}
}
@@ -292,7 +292,7 @@ static int auxtrace_queues__queue_buffer(struct auxtrace_queues *queues,
if (!queue->set) {
queue->set = true;
queue->tid = buffer->tid;
- queue->cpu = buffer->cpu;
+ queue->cpu = buffer->cpu.cpu;
}
buffer->buffer_nr = queues->next_buffer_nr++;
@@ -339,11 +339,11 @@ static int auxtrace_queues__split_buffer(struct auxtrace_queues *queues,
return 0;
}
-static bool filter_cpu(struct perf_session *session, int cpu)
+static bool filter_cpu(struct perf_session *session, struct perf_cpu cpu)
{
unsigned long *cpu_bitmap = session->itrace_synth_opts->cpu_bitmap;
- return cpu_bitmap && cpu != -1 && !test_bit(cpu, cpu_bitmap);
+ return cpu_bitmap && cpu.cpu != -1 && !test_bit(cpu.cpu, cpu_bitmap);
}
static int auxtrace_queues__add_buffer(struct auxtrace_queues *queues,
@@ -399,7 +399,7 @@ int auxtrace_queues__add_event(struct auxtrace_queues *queues,
struct auxtrace_buffer buffer = {
.pid = -1,
.tid = event->auxtrace.tid,
- .cpu = event->auxtrace.cpu,
+ .cpu = { event->auxtrace.cpu },
.data_offset = data_offset,
.offset = event->auxtrace.offset,
.reference = event->auxtrace.reference,
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index bbf0d78c6401..19910b9011f3 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -15,6 +15,7 @@
#include <linux/list.h>
#include <linux/perf_event.h>
#include <linux/types.h>
+#include <internal/cpumap.h>
#include <asm/bitsperlong.h>
#include <asm/barrier.h>
@@ -240,7 +241,7 @@ struct auxtrace_buffer {
size_t size;
pid_t pid;
pid_t tid;
- int cpu;
+ struct perf_cpu cpu;
void *data;
off_t data_offset;
void *mmap_addr;
@@ -350,7 +351,7 @@ struct auxtrace_mmap_params {
int prot;
int idx;
pid_t tid;
- int cpu;
+ struct perf_cpu cpu;
};
/**
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index 528aeb0ab79d..16ec605a9fe4 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -424,7 +424,7 @@ preproc_gen_prologue(struct bpf_program *prog, int n,
size_t prologue_cnt = 0;
int i, err;
- if (IS_ERR(priv) || !priv || priv->is_tp)
+ if (IS_ERR_OR_NULL(priv) || priv->is_tp)
goto errout;
pev = &priv->pev;
@@ -573,7 +573,7 @@ static int hook_load_preprocessor(struct bpf_program *prog)
bool need_prologue = false;
int err, i;
- if (IS_ERR(priv) || !priv) {
+ if (IS_ERR_OR_NULL(priv)) {
pr_debug("Internal error when hook preprocessor\n");
return -BPF_LOADER_ERRNO__INTERNAL;
}
@@ -645,8 +645,11 @@ int bpf__probe(struct bpf_object *obj)
goto out;
priv = bpf_program__priv(prog);
- if (IS_ERR(priv) || !priv) {
- err = PTR_ERR(priv);
+ if (IS_ERR_OR_NULL(priv)) {
+ if (!priv)
+ err = -BPF_LOADER_ERRNO__INTERNAL;
+ else
+ err = PTR_ERR(priv);
goto out;
}
@@ -696,7 +699,7 @@ int bpf__unprobe(struct bpf_object *obj)
struct bpf_prog_priv *priv = bpf_program__priv(prog);
int i;
- if (IS_ERR(priv) || !priv || priv->is_tp)
+ if (IS_ERR_OR_NULL(priv) || priv->is_tp)
continue;
for (i = 0; i < priv->pev.ntevs; i++) {
@@ -754,7 +757,7 @@ int bpf__foreach_event(struct bpf_object *obj,
struct perf_probe_event *pev;
int i, fd;
- if (IS_ERR(priv) || !priv) {
+ if (IS_ERR_OR_NULL(priv)) {
pr_debug("bpf: failed to get private field\n");
return -BPF_LOADER_ERRNO__INTERNAL;
}
@@ -1217,9 +1220,10 @@ bpf__obj_config_map(struct bpf_object *obj,
pr_debug("ERROR: Invalid map config option '%s'\n", map_opt);
err = -BPF_LOADER_ERRNO__OBJCONF_MAP_OPT;
out:
- free(map_name);
if (!err)
*key_scan_pos += strlen(map_opt);
+
+ free(map_name);
return err;
}
diff --git a/tools/perf/util/bpf_counter.c b/tools/perf/util/bpf_counter.c
index 5a97fd7d0a71..3ce8d03cb7ec 100644
--- a/tools/perf/util/bpf_counter.c
+++ b/tools/perf/util/bpf_counter.c
@@ -265,7 +265,7 @@ static int bpf_program_profiler__read(struct evsel *evsel)
return 0;
}
-static int bpf_program_profiler__install_pe(struct evsel *evsel, int cpu,
+static int bpf_program_profiler__install_pe(struct evsel *evsel, int cpu_map_idx,
int fd)
{
struct bpf_prog_profiler_bpf *skel;
@@ -277,7 +277,7 @@ static int bpf_program_profiler__install_pe(struct evsel *evsel, int cpu,
assert(skel != NULL);
ret = bpf_map_update_elem(bpf_map__fd(skel->maps.events),
- &cpu, &fd, BPF_ANY);
+ &cpu_map_idx, &fd, BPF_ANY);
if (ret)
return ret;
}
@@ -554,7 +554,7 @@ static int bperf__load(struct evsel *evsel, struct target *target)
filter_type == BPERF_FILTER_TGID)
key = evsel->core.threads->map[i].pid;
else if (filter_type == BPERF_FILTER_CPU)
- key = evsel->core.cpus->map[i];
+ key = evsel->core.cpus->map[i].cpu;
else
break;
@@ -580,12 +580,12 @@ out:
return err;
}
-static int bperf__install_pe(struct evsel *evsel, int cpu, int fd)
+static int bperf__install_pe(struct evsel *evsel, int cpu_map_idx, int fd)
{
struct bperf_leader_bpf *skel = evsel->leader_skel;
return bpf_map_update_elem(bpf_map__fd(skel->maps.events),
- &cpu, &fd, BPF_ANY);
+ &cpu_map_idx, &fd, BPF_ANY);
}
/*
@@ -598,7 +598,7 @@ static int bperf_sync_counters(struct evsel *evsel)
num_cpu = all_cpu_map->nr;
for (i = 0; i < num_cpu; i++) {
- cpu = all_cpu_map->map[i];
+ cpu = all_cpu_map->map[i].cpu;
bperf_trigger_reading(evsel->bperf_leader_prog_fd, cpu);
}
return 0;
@@ -619,15 +619,17 @@ static int bperf__disable(struct evsel *evsel)
static int bperf__read(struct evsel *evsel)
{
struct bperf_follower_bpf *skel = evsel->follower_skel;
- __u32 num_cpu_bpf = cpu__max_cpu();
+ __u32 num_cpu_bpf = cpu__max_cpu().cpu;
struct bpf_perf_event_value values[num_cpu_bpf];
int reading_map_fd, err = 0;
- __u32 i, j, num_cpu;
+ __u32 i;
+ int j;
bperf_sync_counters(evsel);
reading_map_fd = bpf_map__fd(skel->maps.accum_readings);
for (i = 0; i < bpf_map__max_entries(skel->maps.accum_readings); i++) {
+ struct perf_cpu entry;
__u32 cpu;
err = bpf_map_lookup_elem(reading_map_fd, &i, values);
@@ -637,16 +639,15 @@ static int bperf__read(struct evsel *evsel)
case BPERF_FILTER_GLOBAL:
assert(i == 0);
- num_cpu = all_cpu_map->nr;
- for (j = 0; j < num_cpu; j++) {
- cpu = all_cpu_map->map[j];
+ perf_cpu_map__for_each_cpu(entry, j, all_cpu_map) {
+ cpu = entry.cpu;
perf_counts(evsel->counts, cpu, 0)->val = values[cpu].counter;
perf_counts(evsel->counts, cpu, 0)->ena = values[cpu].enabled;
perf_counts(evsel->counts, cpu, 0)->run = values[cpu].running;
}
break;
case BPERF_FILTER_CPU:
- cpu = evsel->core.cpus->map[i];
+ cpu = evsel->core.cpus->map[i].cpu;
perf_counts(evsel->counts, i, 0)->val = values[cpu].counter;
perf_counts(evsel->counts, i, 0)->ena = values[cpu].enabled;
perf_counts(evsel->counts, i, 0)->run = values[cpu].running;
@@ -771,11 +772,11 @@ static inline bool bpf_counter_skip(struct evsel *evsel)
evsel->follower_skel == NULL;
}
-int bpf_counter__install_pe(struct evsel *evsel, int cpu, int fd)
+int bpf_counter__install_pe(struct evsel *evsel, int cpu_map_idx, int fd)
{
if (bpf_counter_skip(evsel))
return 0;
- return evsel->bpf_counter_ops->install_pe(evsel, cpu, fd);
+ return evsel->bpf_counter_ops->install_pe(evsel, cpu_map_idx, fd);
}
int bpf_counter__load(struct evsel *evsel, struct target *target)
diff --git a/tools/perf/util/bpf_counter.h b/tools/perf/util/bpf_counter.h
index 65ebaa6694fb..4dbf26408b69 100644
--- a/tools/perf/util/bpf_counter.h
+++ b/tools/perf/util/bpf_counter.h
@@ -16,7 +16,7 @@ typedef int (*bpf_counter_evsel_op)(struct evsel *evsel);
typedef int (*bpf_counter_evsel_target_op)(struct evsel *evsel,
struct target *target);
typedef int (*bpf_counter_evsel_install_pe_op)(struct evsel *evsel,
- int cpu,
+ int cpu_map_idx,
int fd);
struct bpf_counter_ops {
@@ -40,7 +40,7 @@ int bpf_counter__enable(struct evsel *evsel);
int bpf_counter__disable(struct evsel *evsel);
int bpf_counter__read(struct evsel *evsel);
void bpf_counter__destroy(struct evsel *evsel);
-int bpf_counter__install_pe(struct evsel *evsel, int cpu, int fd);
+int bpf_counter__install_pe(struct evsel *evsel, int cpu_map_idx, int fd);
#else /* HAVE_BPF_SKEL */
diff --git a/tools/perf/util/bpf_counter_cgroup.c b/tools/perf/util/bpf_counter_cgroup.c
index cbc6c2bca488..ac60c08e8e2a 100644
--- a/tools/perf/util/bpf_counter_cgroup.c
+++ b/tools/perf/util/bpf_counter_cgroup.c
@@ -48,7 +48,7 @@ static int bperf_load_program(struct evlist *evlist)
struct cgroup *cgrp, *leader_cgrp;
__u32 i, cpu;
__u32 nr_cpus = evlist->core.all_cpus->nr;
- int total_cpus = cpu__max_cpu();
+ int total_cpus = cpu__max_cpu().cpu;
int map_size, map_fd;
int prog_fd, err;
@@ -125,7 +125,7 @@ static int bperf_load_program(struct evlist *evlist)
for (cpu = 0; cpu < nr_cpus; cpu++) {
int fd = FD(evsel, cpu);
__u32 idx = evsel->core.idx * total_cpus +
- evlist->core.all_cpus->map[cpu];
+ evlist->core.all_cpus->map[cpu].cpu;
err = bpf_map_update_elem(map_fd, &idx, &fd,
BPF_ANY);
@@ -212,7 +212,7 @@ static int bperf_cgrp__sync_counters(struct evlist *evlist)
int prog_fd = bpf_program__fd(skel->progs.trigger_read);
for (i = 0; i < nr_cpus; i++) {
- cpu = evlist->core.all_cpus->map[i];
+ cpu = evlist->core.all_cpus->map[i].cpu;
bperf_trigger_reading(prog_fd, cpu);
}
@@ -245,7 +245,7 @@ static int bperf_cgrp__read(struct evsel *evsel)
{
struct evlist *evlist = evsel->evlist;
int i, cpu, nr_cpus = evlist->core.all_cpus->nr;
- int total_cpus = cpu__max_cpu();
+ int total_cpus = cpu__max_cpu().cpu;
struct perf_counts_values *counts;
struct bpf_perf_event_value *values;
int reading_map_fd, err = 0;
@@ -266,13 +266,13 @@ static int bperf_cgrp__read(struct evsel *evsel)
idx = evsel->core.idx;
err = bpf_map_lookup_elem(reading_map_fd, &idx, values);
if (err) {
- pr_err("bpf map lookup falied: idx=%u, event=%s, cgrp=%s\n",
+ pr_err("bpf map lookup failed: idx=%u, event=%s, cgrp=%s\n",
idx, evsel__name(evsel), evsel->cgrp->name);
goto out;
}
for (i = 0; i < nr_cpus; i++) {
- cpu = evlist->core.all_cpus->map[i];
+ cpu = evlist->core.all_cpus->map[i].cpu;
counts = perf_counts(evsel->counts, i, 0);
counts->val = values[cpu].counter;
diff --git a/tools/perf/util/bpf_ftrace.c b/tools/perf/util/bpf_ftrace.c
new file mode 100644
index 000000000000..d756cc66eef3
--- /dev/null
+++ b/tools/perf/util/bpf_ftrace.c
@@ -0,0 +1,152 @@
+#include <stdio.h>
+#include <fcntl.h>
+#include <stdint.h>
+#include <stdlib.h>
+
+#include <linux/err.h>
+
+#include "util/ftrace.h"
+#include "util/cpumap.h"
+#include "util/thread_map.h"
+#include "util/debug.h"
+#include "util/evlist.h"
+#include "util/bpf_counter.h"
+
+#include "util/bpf_skel/func_latency.skel.h"
+
+static struct func_latency_bpf *skel;
+
+int perf_ftrace__latency_prepare_bpf(struct perf_ftrace *ftrace)
+{
+ int fd, err;
+ int i, ncpus = 1, ntasks = 1;
+ struct filter_entry *func;
+
+ if (!list_is_singular(&ftrace->filters)) {
+ pr_err("ERROR: %s target function(s).\n",
+ list_empty(&ftrace->filters) ? "No" : "Too many");
+ return -1;
+ }
+
+ func = list_first_entry(&ftrace->filters, struct filter_entry, list);
+
+ skel = func_latency_bpf__open();
+ if (!skel) {
+ pr_err("Failed to open func latency skeleton\n");
+ return -1;
+ }
+
+ /* don't need to set cpu filter for system-wide mode */
+ if (ftrace->target.cpu_list) {
+ ncpus = perf_cpu_map__nr(ftrace->evlist->core.cpus);
+ bpf_map__set_max_entries(skel->maps.cpu_filter, ncpus);
+ }
+
+ if (target__has_task(&ftrace->target) || target__none(&ftrace->target)) {
+ ntasks = perf_thread_map__nr(ftrace->evlist->core.threads);
+ bpf_map__set_max_entries(skel->maps.task_filter, ntasks);
+ }
+
+ set_max_rlimit();
+
+ err = func_latency_bpf__load(skel);
+ if (err) {
+ pr_err("Failed to load func latency skeleton\n");
+ goto out;
+ }
+
+ if (ftrace->target.cpu_list) {
+ u32 cpu;
+ u8 val = 1;
+
+ skel->bss->has_cpu = 1;
+ fd = bpf_map__fd(skel->maps.cpu_filter);
+
+ for (i = 0; i < ncpus; i++) {
+ cpu = perf_cpu_map__cpu(ftrace->evlist->core.cpus, i).cpu;
+ bpf_map_update_elem(fd, &cpu, &val, BPF_ANY);
+ }
+ }
+
+ if (target__has_task(&ftrace->target) || target__none(&ftrace->target)) {
+ u32 pid;
+ u8 val = 1;
+
+ skel->bss->has_task = 1;
+ fd = bpf_map__fd(skel->maps.task_filter);
+
+ for (i = 0; i < ntasks; i++) {
+ pid = perf_thread_map__pid(ftrace->evlist->core.threads, i);
+ bpf_map_update_elem(fd, &pid, &val, BPF_ANY);
+ }
+ }
+
+ skel->links.func_begin = bpf_program__attach_kprobe(skel->progs.func_begin,
+ false, func->name);
+ if (IS_ERR(skel->links.func_begin)) {
+ pr_err("Failed to attach fentry program\n");
+ err = PTR_ERR(skel->links.func_begin);
+ goto out;
+ }
+
+ skel->links.func_end = bpf_program__attach_kprobe(skel->progs.func_end,
+ true, func->name);
+ if (IS_ERR(skel->links.func_end)) {
+ pr_err("Failed to attach fexit program\n");
+ err = PTR_ERR(skel->links.func_end);
+ goto out;
+ }
+
+ /* XXX: we don't actually use this fd - just for poll() */
+ return open("/dev/null", O_RDONLY);
+
+out:
+ return err;
+}
+
+int perf_ftrace__latency_start_bpf(struct perf_ftrace *ftrace __maybe_unused)
+{
+ skel->bss->enabled = 1;
+ return 0;
+}
+
+int perf_ftrace__latency_stop_bpf(struct perf_ftrace *ftrace __maybe_unused)
+{
+ skel->bss->enabled = 0;
+ return 0;
+}
+
+int perf_ftrace__latency_read_bpf(struct perf_ftrace *ftrace __maybe_unused,
+ int buckets[])
+{
+ int i, fd, err;
+ u32 idx;
+ u64 *hist;
+ int ncpus = cpu__max_cpu().cpu;
+
+ fd = bpf_map__fd(skel->maps.latency);
+
+ hist = calloc(ncpus, sizeof(*hist));
+ if (hist == NULL)
+ return -ENOMEM;
+
+ for (idx = 0; idx < NUM_BUCKET; idx++) {
+ err = bpf_map_lookup_elem(fd, &idx, hist);
+ if (err) {
+ buckets[idx] = 0;
+ continue;
+ }
+
+ for (i = 0; i < ncpus; i++)
+ buckets[idx] += hist[i];
+ }
+
+ free(hist);
+ return 0;
+}
+
+int perf_ftrace__latency_cleanup_bpf(struct perf_ftrace *ftrace __maybe_unused)
+{
+ func_latency_bpf__destroy(skel);
+ return 0;
+}
diff --git a/tools/perf/util/bpf_skel/func_latency.bpf.c b/tools/perf/util/bpf_skel/func_latency.bpf.c
new file mode 100644
index 000000000000..ea94187fe443
--- /dev/null
+++ b/tools/perf/util/bpf_skel/func_latency.bpf.c
@@ -0,0 +1,114 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+// Copyright (c) 2021 Google
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+// This should be in sync with "util/ftrace.h"
+#define NUM_BUCKET 22
+
+struct {
+ __uint(type, BPF_MAP_TYPE_HASH);
+ __uint(key_size, sizeof(__u64));
+ __uint(value_size, sizeof(__u64));
+ __uint(max_entries, 10000);
+} functime SEC(".maps");
+
+struct {
+ __uint(type, BPF_MAP_TYPE_HASH);
+ __uint(key_size, sizeof(__u32));
+ __uint(value_size, sizeof(__u8));
+ __uint(max_entries, 1);
+} cpu_filter SEC(".maps");
+
+struct {
+ __uint(type, BPF_MAP_TYPE_HASH);
+ __uint(key_size, sizeof(__u32));
+ __uint(value_size, sizeof(__u8));
+ __uint(max_entries, 1);
+} task_filter SEC(".maps");
+
+struct {
+ __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+ __uint(key_size, sizeof(__u32));
+ __uint(value_size, sizeof(__u64));
+ __uint(max_entries, NUM_BUCKET);
+} latency SEC(".maps");
+
+
+int enabled = 0;
+int has_cpu = 0;
+int has_task = 0;
+
+SEC("kprobe/func")
+int BPF_PROG(func_begin)
+{
+ __u64 key, now;
+
+ if (!enabled)
+ return 0;
+
+ key = bpf_get_current_pid_tgid();
+
+ if (has_cpu) {
+ __u32 cpu = bpf_get_smp_processor_id();
+ __u8 *ok;
+
+ ok = bpf_map_lookup_elem(&cpu_filter, &cpu);
+ if (!ok)
+ return 0;
+ }
+
+ if (has_task) {
+ __u32 pid = key & 0xffffffff;
+ __u8 *ok;
+
+ ok = bpf_map_lookup_elem(&task_filter, &pid);
+ if (!ok)
+ return 0;
+ }
+
+ now = bpf_ktime_get_ns();
+
+ // overwrite timestamp for nested functions
+ bpf_map_update_elem(&functime, &key, &now, BPF_ANY);
+ return 0;
+}
+
+SEC("kretprobe/func")
+int BPF_PROG(func_end)
+{
+ __u64 tid;
+ __u64 *start;
+
+ if (!enabled)
+ return 0;
+
+ tid = bpf_get_current_pid_tgid();
+
+ start = bpf_map_lookup_elem(&functime, &tid);
+ if (start) {
+ __s64 delta = bpf_ktime_get_ns() - *start;
+ __u32 key;
+ __u64 *hist;
+
+ bpf_map_delete_elem(&functime, &tid);
+
+ if (delta < 0)
+ return 0;
+
+ // calculate index using delta in usec
+ for (key = 0; key < (NUM_BUCKET - 1); key++) {
+ if (delta < ((1000UL) << key))
+ break;
+ }
+
+ hist = bpf_map_lookup_elem(&latency, &key);
+ if (!hist)
+ return 0;
+
+ *hist += 1;
+ }
+
+ return 0;
+}
diff --git a/tools/perf/util/branch.c b/tools/perf/util/branch.c
index 2285b1eb3128..a9a909db8cc7 100644
--- a/tools/perf/util/branch.c
+++ b/tools/perf/util/branch.c
@@ -49,7 +49,9 @@ const char *branch_type_name(int type)
"SYSCALL",
"SYSRET",
"COND_CALL",
- "COND_RET"
+ "COND_RET",
+ "ERET",
+ "IRQ"
};
if (type >= 0 && type < PERF_BR_MAX)
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 8e2777133bd9..131207b91d15 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -1600,7 +1600,7 @@ void callchain_cursor_reset(struct callchain_cursor *cursor)
map__zput(node->ms.map);
}
-void callchain_param_setup(u64 sample_type)
+void callchain_param_setup(u64 sample_type, const char *arch)
{
if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain) {
if ((sample_type & PERF_SAMPLE_REGS_USER) &&
@@ -1612,6 +1612,18 @@ void callchain_param_setup(u64 sample_type)
else
callchain_param.record_mode = CALLCHAIN_FP;
}
+
+ /*
+ * It's necessary to use libunwind to reliably determine the caller of
+ * a leaf function on aarch64, as otherwise we cannot know whether to
+ * start from the LR or FP.
+ *
+ * Always starting from the LR can result in duplicate or entirely
+ * erroneous entries. Always skipping the LR and starting from the FP
+ * can result in missing entries.
+ */
+ if (callchain_param.record_mode == CALLCHAIN_FP && !strcmp(arch, "arm64"))
+ dwarf_callchain_users = true;
}
static bool chain_match(struct callchain_list *base_chain,
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 5824134f983b..d95615daed73 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -280,6 +280,8 @@ static inline int arch_skip_callchain_idx(struct thread *thread __maybe_unused,
}
#endif
+void arch__add_leaf_frame_record_opts(struct record_opts *opts);
+
char *callchain_list__sym_name(struct callchain_list *cl,
char *bf, size_t bfsize, bool show_dso);
char *callchain_node__scnprintf_value(struct callchain_node *node,
@@ -298,7 +300,7 @@ int callchain_branch_counts(struct callchain_root *root,
u64 *branch_count, u64 *predicted_count,
u64 *abort_count, u64 *cycles_count);
-void callchain_param_setup(u64 sample_type);
+void callchain_param_setup(u64 sample_type, const char *arch);
bool callchain_cnode_matched(struct callchain_node *base_cnode,
struct callchain_node *pair_cnode);
diff --git a/tools/perf/util/counts.c b/tools/perf/util/counts.c
index 582f3aeaf5e4..7a447d918458 100644
--- a/tools/perf/util/counts.c
+++ b/tools/perf/util/counts.c
@@ -4,6 +4,7 @@
#include <string.h>
#include "evsel.h"
#include "counts.h"
+#include <perf/threadmap.h>
#include <linux/zalloc.h>
struct perf_counts *perf_counts__new(int ncpus, int nthreads)
@@ -55,9 +56,12 @@ void evsel__reset_counts(struct evsel *evsel)
perf_counts__reset(evsel->counts);
}
-int evsel__alloc_counts(struct evsel *evsel, int ncpus, int nthreads)
+int evsel__alloc_counts(struct evsel *evsel)
{
- evsel->counts = perf_counts__new(ncpus, nthreads);
+ struct perf_cpu_map *cpus = evsel__cpus(evsel);
+ int nthreads = perf_thread_map__nr(evsel->core.threads);
+
+ evsel->counts = perf_counts__new(perf_cpu_map__nr(cpus), nthreads);
return evsel->counts != NULL ? 0 : -ENOMEM;
}
diff --git a/tools/perf/util/counts.h b/tools/perf/util/counts.h
index 7ff36bf6d644..5de275194f2b 100644
--- a/tools/perf/util/counts.h
+++ b/tools/perf/util/counts.h
@@ -18,21 +18,21 @@ struct perf_counts {
static inline struct perf_counts_values*
-perf_counts(struct perf_counts *counts, int cpu, int thread)
+perf_counts(struct perf_counts *counts, int cpu_map_idx, int thread)
{
- return xyarray__entry(counts->values, cpu, thread);
+ return xyarray__entry(counts->values, cpu_map_idx, thread);
}
static inline bool
-perf_counts__is_loaded(struct perf_counts *counts, int cpu, int thread)
+perf_counts__is_loaded(struct perf_counts *counts, int cpu_map_idx, int thread)
{
- return *((bool *) xyarray__entry(counts->loaded, cpu, thread));
+ return *((bool *) xyarray__entry(counts->loaded, cpu_map_idx, thread));
}
static inline void
-perf_counts__set_loaded(struct perf_counts *counts, int cpu, int thread, bool loaded)
+perf_counts__set_loaded(struct perf_counts *counts, int cpu_map_idx, int thread, bool loaded)
{
- *((bool *) xyarray__entry(counts->loaded, cpu, thread)) = loaded;
+ *((bool *) xyarray__entry(counts->loaded, cpu_map_idx, thread)) = loaded;
}
struct perf_counts *perf_counts__new(int ncpus, int nthreads);
@@ -40,7 +40,7 @@ void perf_counts__delete(struct perf_counts *counts);
void perf_counts__reset(struct perf_counts *counts);
void evsel__reset_counts(struct evsel *evsel);
-int evsel__alloc_counts(struct evsel *evsel, int ncpus, int nthreads);
+int evsel__alloc_counts(struct evsel *evsel);
void evsel__free_counts(struct evsel *evsel);
#endif /* __PERF_COUNTS_H */
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index 87d3eca9b872..12b2243222b0 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -13,9 +13,13 @@
#include <linux/ctype.h>
#include <linux/zalloc.h>
-static int max_cpu_num;
-static int max_present_cpu_num;
+static struct perf_cpu max_cpu_num;
+static struct perf_cpu max_present_cpu_num;
static int max_node_num;
+/**
+ * The numa node X as read from /sys/devices/system/node/nodeX indexed by the
+ * CPU number.
+ */
static int *cpunode_map;
static struct perf_cpu_map *cpu_map__from_entries(struct cpu_map_entries *cpus)
@@ -33,9 +37,9 @@ static struct perf_cpu_map *cpu_map__from_entries(struct cpu_map_entries *cpus)
* otherwise it would become 65535.
*/
if (cpus->cpu[i] == (u16) -1)
- map->map[i] = -1;
+ map->map[i].cpu = -1;
else
- map->map[i] = (int) cpus->cpu[i];
+ map->map[i].cpu = (int) cpus->cpu[i];
}
}
@@ -54,7 +58,7 @@ static struct perf_cpu_map *cpu_map__from_mask(struct perf_record_record_cpu_map
int cpu, i = 0;
for_each_set_bit(cpu, mask->mask, nbits)
- map->map[i++] = cpu;
+ map->map[i++].cpu = cpu;
}
return map;
@@ -87,7 +91,7 @@ struct perf_cpu_map *perf_cpu_map__empty_new(int nr)
cpus->nr = nr;
for (i = 0; i < nr; i++)
- cpus->map[i] = -1;
+ cpus->map[i].cpu = -1;
refcount_set(&cpus->refcnt, 1);
}
@@ -104,7 +108,7 @@ struct cpu_aggr_map *cpu_aggr_map__empty_new(int nr)
cpus->nr = nr;
for (i = 0; i < nr; i++)
- cpus->map[i] = cpu_map__empty_aggr_cpu_id();
+ cpus->map[i] = aggr_cpu_id__empty();
refcount_set(&cpus->refcnt, 1);
}
@@ -122,28 +126,21 @@ static int cpu__get_topology_int(int cpu, const char *name, int *value)
return sysfs__read_int(path, value);
}
-int cpu_map__get_socket_id(int cpu)
+int cpu__get_socket_id(struct perf_cpu cpu)
{
- int value, ret = cpu__get_topology_int(cpu, "physical_package_id", &value);
+ int value, ret = cpu__get_topology_int(cpu.cpu, "physical_package_id", &value);
return ret ?: value;
}
-struct aggr_cpu_id cpu_map__get_socket(struct perf_cpu_map *map, int idx,
- void *data __maybe_unused)
+struct aggr_cpu_id aggr_cpu_id__socket(struct perf_cpu cpu, void *data __maybe_unused)
{
- int cpu;
- struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id();
+ struct aggr_cpu_id id = aggr_cpu_id__empty();
- if (idx > map->nr)
- return id;
-
- cpu = map->map[idx];
-
- id.socket = cpu_map__get_socket_id(cpu);
+ id.socket = cpu__get_socket_id(cpu);
return id;
}
-static int cmp_aggr_cpu_id(const void *a_pointer, const void *b_pointer)
+static int aggr_cpu_id__cmp(const void *a_pointer, const void *b_pointer)
{
struct aggr_cpu_id *a = (struct aggr_cpu_id *)a_pointer;
struct aggr_cpu_id *b = (struct aggr_cpu_id *)b_pointer;
@@ -160,57 +157,64 @@ static int cmp_aggr_cpu_id(const void *a_pointer, const void *b_pointer)
return a->thread - b->thread;
}
-int cpu_map__build_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **res,
- struct aggr_cpu_id (*f)(struct perf_cpu_map *map, int cpu, void *data),
- void *data)
+struct cpu_aggr_map *cpu_aggr_map__new(const struct perf_cpu_map *cpus,
+ aggr_cpu_id_get_t get_id,
+ void *data)
{
- int nr = cpus->nr;
- struct cpu_aggr_map *c = cpu_aggr_map__empty_new(nr);
- int cpu, s2;
- struct aggr_cpu_id s1;
+ int idx;
+ struct perf_cpu cpu;
+ struct cpu_aggr_map *c = cpu_aggr_map__empty_new(cpus->nr);
if (!c)
- return -1;
+ return NULL;
/* Reset size as it may only be partially filled */
c->nr = 0;
- for (cpu = 0; cpu < nr; cpu++) {
- s1 = f(cpus, cpu, data);
- for (s2 = 0; s2 < c->nr; s2++) {
- if (cpu_map__compare_aggr_cpu_id(s1, c->map[s2]))
+ perf_cpu_map__for_each_cpu(cpu, idx, cpus) {
+ bool duplicate = false;
+ struct aggr_cpu_id cpu_id = get_id(cpu, data);
+
+ for (int j = 0; j < c->nr; j++) {
+ if (aggr_cpu_id__equal(&cpu_id, &c->map[j])) {
+ duplicate = true;
break;
+ }
}
- if (s2 == c->nr) {
- c->map[c->nr] = s1;
+ if (!duplicate) {
+ c->map[c->nr] = cpu_id;
c->nr++;
}
}
+ /* Trim. */
+ if (c->nr != cpus->nr) {
+ struct cpu_aggr_map *trimmed_c =
+ realloc(c,
+ sizeof(struct cpu_aggr_map) + sizeof(struct aggr_cpu_id) * c->nr);
+
+ if (trimmed_c)
+ c = trimmed_c;
+ }
/* ensure we process id in increasing order */
- qsort(c->map, c->nr, sizeof(struct aggr_cpu_id), cmp_aggr_cpu_id);
+ qsort(c->map, c->nr, sizeof(struct aggr_cpu_id), aggr_cpu_id__cmp);
+
+ return c;
- *res = c;
- return 0;
}
-int cpu_map__get_die_id(int cpu)
+int cpu__get_die_id(struct perf_cpu cpu)
{
- int value, ret = cpu__get_topology_int(cpu, "die_id", &value);
+ int value, ret = cpu__get_topology_int(cpu.cpu, "die_id", &value);
return ret ?: value;
}
-struct aggr_cpu_id cpu_map__get_die(struct perf_cpu_map *map, int idx, void *data)
+struct aggr_cpu_id aggr_cpu_id__die(struct perf_cpu cpu, void *data)
{
- int cpu, die;
- struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id();
+ struct aggr_cpu_id id;
+ int die;
- if (idx > map->nr)
- return id;
-
- cpu = map->map[idx];
-
- die = cpu_map__get_die_id(cpu);
+ die = cpu__get_die_id(cpu);
/* There is no die_id on legacy system. */
if (die == -1)
die = 0;
@@ -220,79 +224,59 @@ struct aggr_cpu_id cpu_map__get_die(struct perf_cpu_map *map, int idx, void *dat
* with the socket ID and then add die to
* make a unique ID.
*/
- id = cpu_map__get_socket(map, idx, data);
- if (cpu_map__aggr_cpu_id_is_empty(id))
+ id = aggr_cpu_id__socket(cpu, data);
+ if (aggr_cpu_id__is_empty(&id))
return id;
id.die = die;
return id;
}
-int cpu_map__get_core_id(int cpu)
+int cpu__get_core_id(struct perf_cpu cpu)
{
- int value, ret = cpu__get_topology_int(cpu, "core_id", &value);
+ int value, ret = cpu__get_topology_int(cpu.cpu, "core_id", &value);
return ret ?: value;
}
-int cpu_map__get_node_id(int cpu)
-{
- return cpu__get_node(cpu);
-}
-
-struct aggr_cpu_id cpu_map__get_core(struct perf_cpu_map *map, int idx, void *data)
+struct aggr_cpu_id aggr_cpu_id__core(struct perf_cpu cpu, void *data)
{
- int cpu;
- struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id();
-
- if (idx > map->nr)
- return id;
+ struct aggr_cpu_id id;
+ int core = cpu__get_core_id(cpu);
- cpu = map->map[idx];
-
- cpu = cpu_map__get_core_id(cpu);
-
- /* cpu_map__get_die returns a struct with socket and die set*/
- id = cpu_map__get_die(map, idx, data);
- if (cpu_map__aggr_cpu_id_is_empty(id))
+ /* aggr_cpu_id__die returns a struct with socket and die set. */
+ id = aggr_cpu_id__die(cpu, data);
+ if (aggr_cpu_id__is_empty(&id))
return id;
/*
* core_id is relative to socket and die, we need a global id.
* So we combine the result from cpu_map__get_die with the core id
*/
- id.core = cpu;
+ id.core = core;
return id;
+
}
-struct aggr_cpu_id cpu_map__get_node(struct perf_cpu_map *map, int idx, void *data __maybe_unused)
+struct aggr_cpu_id aggr_cpu_id__cpu(struct perf_cpu cpu, void *data)
{
- struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id();
+ struct aggr_cpu_id id;
- if (idx < 0 || idx >= map->nr)
+ /* aggr_cpu_id__core returns a struct with socket, die and core set. */
+ id = aggr_cpu_id__core(cpu, data);
+ if (aggr_cpu_id__is_empty(&id))
return id;
- id.node = cpu_map__get_node_id(map->map[idx]);
+ id.cpu = cpu;
return id;
-}
-int cpu_map__build_socket_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **sockp)
-{
- return cpu_map__build_map(cpus, sockp, cpu_map__get_socket, NULL);
}
-int cpu_map__build_die_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **diep)
+struct aggr_cpu_id aggr_cpu_id__node(struct perf_cpu cpu, void *data __maybe_unused)
{
- return cpu_map__build_map(cpus, diep, cpu_map__get_die, NULL);
-}
-
-int cpu_map__build_core_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **corep)
-{
- return cpu_map__build_map(cpus, corep, cpu_map__get_core, NULL);
-}
+ struct aggr_cpu_id id = aggr_cpu_id__empty();
-int cpu_map__build_node_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **numap)
-{
- return cpu_map__build_map(cpus, numap, cpu_map__get_node, NULL);
+ id.node = cpu__get_node(cpu);
+ return id;
}
/* setup simple routines to easily access node numbers given a cpu number */
@@ -335,8 +319,8 @@ static void set_max_cpu_num(void)
int ret = -1;
/* set up default */
- max_cpu_num = 4096;
- max_present_cpu_num = 4096;
+ max_cpu_num.cpu = 4096;
+ max_present_cpu_num.cpu = 4096;
mnt = sysfs__mountpoint();
if (!mnt)
@@ -349,7 +333,7 @@ static void set_max_cpu_num(void)
goto out;
}
- ret = get_max_num(path, &max_cpu_num);
+ ret = get_max_num(path, &max_cpu_num.cpu);
if (ret)
goto out;
@@ -360,11 +344,11 @@ static void set_max_cpu_num(void)
goto out;
}
- ret = get_max_num(path, &max_present_cpu_num);
+ ret = get_max_num(path, &max_present_cpu_num.cpu);
out:
if (ret)
- pr_err("Failed to read max cpus, using default of %d\n", max_cpu_num);
+ pr_err("Failed to read max cpus, using default of %d\n", max_cpu_num.cpu);
}
/* Determine highest possible node in the system for sparse allocation */
@@ -403,31 +387,31 @@ int cpu__max_node(void)
return max_node_num;
}
-int cpu__max_cpu(void)
+struct perf_cpu cpu__max_cpu(void)
{
- if (unlikely(!max_cpu_num))
+ if (unlikely(!max_cpu_num.cpu))
set_max_cpu_num();
return max_cpu_num;
}
-int cpu__max_present_cpu(void)
+struct perf_cpu cpu__max_present_cpu(void)
{
- if (unlikely(!max_present_cpu_num))
+ if (unlikely(!max_present_cpu_num.cpu))
set_max_cpu_num();
return max_present_cpu_num;
}
-int cpu__get_node(int cpu)
+int cpu__get_node(struct perf_cpu cpu)
{
if (unlikely(cpunode_map == NULL)) {
pr_debug("cpu_map not initialized\n");
return -1;
}
- return cpunode_map[cpu];
+ return cpunode_map[cpu.cpu];
}
static int init_cpunode_map(void)
@@ -437,13 +421,13 @@ static int init_cpunode_map(void)
set_max_cpu_num();
set_max_node_num();
- cpunode_map = calloc(max_cpu_num, sizeof(int));
+ cpunode_map = calloc(max_cpu_num.cpu, sizeof(int));
if (!cpunode_map) {
pr_err("%s: calloc failed\n", __func__);
return -1;
}
- for (i = 0; i < max_cpu_num; i++)
+ for (i = 0; i < max_cpu_num.cpu; i++)
cpunode_map[i] = -1;
return 0;
@@ -502,47 +486,39 @@ int cpu__setup_cpunode_map(void)
return 0;
}
-bool cpu_map__has(struct perf_cpu_map *cpus, int cpu)
-{
- return perf_cpu_map__idx(cpus, cpu) != -1;
-}
-
-int cpu_map__cpu(struct perf_cpu_map *cpus, int idx)
-{
- return cpus->map[idx];
-}
-
size_t cpu_map__snprint(struct perf_cpu_map *map, char *buf, size_t size)
{
- int i, cpu, start = -1;
+ int i, start = -1;
bool first = true;
size_t ret = 0;
#define COMMA first ? "" : ","
for (i = 0; i < map->nr + 1; i++) {
+ struct perf_cpu cpu = { .cpu = INT_MAX };
bool last = i == map->nr;
- cpu = last ? INT_MAX : map->map[i];
+ if (!last)
+ cpu = map->map[i];
if (start == -1) {
start = i;
if (last) {
ret += snprintf(buf + ret, size - ret,
"%s%d", COMMA,
- map->map[i]);
+ map->map[i].cpu);
}
- } else if (((i - start) != (cpu - map->map[start])) || last) {
+ } else if (((i - start) != (cpu.cpu - map->map[start].cpu)) || last) {
int end = i - 1;
if (start == end) {
ret += snprintf(buf + ret, size - ret,
"%s%d", COMMA,
- map->map[start]);
+ map->map[start].cpu);
} else {
ret += snprintf(buf + ret, size - ret,
"%s%d-%d", COMMA,
- map->map[start], map->map[end]);
+ map->map[start].cpu, map->map[end].cpu);
}
first = false;
start = i;
@@ -569,23 +545,23 @@ size_t cpu_map__snprint_mask(struct perf_cpu_map *map, char *buf, size_t size)
int i, cpu;
char *ptr = buf;
unsigned char *bitmap;
- int last_cpu = cpu_map__cpu(map, map->nr - 1);
+ struct perf_cpu last_cpu = perf_cpu_map__cpu(map, map->nr - 1);
if (buf == NULL)
return 0;
- bitmap = zalloc(last_cpu / 8 + 1);
+ bitmap = zalloc(last_cpu.cpu / 8 + 1);
if (bitmap == NULL) {
buf[0] = '\0';
return 0;
}
for (i = 0; i < map->nr; i++) {
- cpu = cpu_map__cpu(map, i);
+ cpu = perf_cpu_map__cpu(map, i).cpu;
bitmap[cpu / 8] |= 1 << (cpu % 8);
}
- for (cpu = last_cpu / 4 * 4; cpu >= 0; cpu -= 4) {
+ for (cpu = last_cpu.cpu / 4 * 4; cpu >= 0; cpu -= 4) {
unsigned char bits = bitmap[cpu / 8];
if (cpu % 8)
@@ -614,32 +590,35 @@ const struct perf_cpu_map *cpu_map__online(void) /* thread unsafe */
return online;
}
-bool cpu_map__compare_aggr_cpu_id(struct aggr_cpu_id a, struct aggr_cpu_id b)
+bool aggr_cpu_id__equal(const struct aggr_cpu_id *a, const struct aggr_cpu_id *b)
{
- return a.thread == b.thread &&
- a.node == b.node &&
- a.socket == b.socket &&
- a.die == b.die &&
- a.core == b.core;
+ return a->thread == b->thread &&
+ a->node == b->node &&
+ a->socket == b->socket &&
+ a->die == b->die &&
+ a->core == b->core &&
+ a->cpu.cpu == b->cpu.cpu;
}
-bool cpu_map__aggr_cpu_id_is_empty(struct aggr_cpu_id a)
+bool aggr_cpu_id__is_empty(const struct aggr_cpu_id *a)
{
- return a.thread == -1 &&
- a.node == -1 &&
- a.socket == -1 &&
- a.die == -1 &&
- a.core == -1;
+ return a->thread == -1 &&
+ a->node == -1 &&
+ a->socket == -1 &&
+ a->die == -1 &&
+ a->core == -1 &&
+ a->cpu.cpu == -1;
}
-struct aggr_cpu_id cpu_map__empty_aggr_cpu_id(void)
+struct aggr_cpu_id aggr_cpu_id__empty(void)
{
struct aggr_cpu_id ret = {
.thread = -1,
.node = -1,
.socket = -1,
.die = -1,
- .core = -1
+ .core = -1,
+ .cpu = (struct perf_cpu){ .cpu = -1 },
};
return ret;
}
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
index a27eeaf086e8..703ae6d3386e 100644
--- a/tools/perf/util/cpumap.h
+++ b/tools/perf/util/cpumap.h
@@ -2,71 +2,134 @@
#ifndef __PERF_CPUMAP_H
#define __PERF_CPUMAP_H
-#include <stdio.h>
#include <stdbool.h>
+#include <stdio.h>
#include <internal/cpumap.h>
#include <perf/cpumap.h>
+/** Identify where counts are aggregated, -1 implies not to aggregate. */
struct aggr_cpu_id {
+ /** A value in the range 0 to number of threads. */
int thread;
+ /** The numa node X as read from /sys/devices/system/node/nodeX. */
int node;
+ /**
+ * The socket number as read from
+ * /sys/devices/system/cpu/cpuX/topology/physical_package_id.
+ */
int socket;
+ /** The die id as read from /sys/devices/system/cpu/cpuX/topology/die_id. */
int die;
+ /** The core id as read from /sys/devices/system/cpu/cpuX/topology/core_id. */
int core;
+ /** CPU aggregation, note there is one CPU for each SMT thread. */
+ struct perf_cpu cpu;
};
+/** A collection of aggr_cpu_id values, the "built" version is sorted and uniqued. */
struct cpu_aggr_map {
refcount_t refcnt;
+ /** Number of valid entries. */
int nr;
+ /** The entries. */
struct aggr_cpu_id map[];
};
struct perf_record_cpu_map_data;
struct perf_cpu_map *perf_cpu_map__empty_new(int nr);
-struct cpu_aggr_map *cpu_aggr_map__empty_new(int nr);
struct perf_cpu_map *cpu_map__new_data(struct perf_record_cpu_map_data *data);
size_t cpu_map__snprint(struct perf_cpu_map *map, char *buf, size_t size);
size_t cpu_map__snprint_mask(struct perf_cpu_map *map, char *buf, size_t size);
size_t cpu_map__fprintf(struct perf_cpu_map *map, FILE *fp);
-int cpu_map__get_socket_id(int cpu);
-struct aggr_cpu_id cpu_map__get_socket(struct perf_cpu_map *map, int idx, void *data);
-int cpu_map__get_die_id(int cpu);
-struct aggr_cpu_id cpu_map__get_die(struct perf_cpu_map *map, int idx, void *data);
-int cpu_map__get_core_id(int cpu);
-struct aggr_cpu_id cpu_map__get_core(struct perf_cpu_map *map, int idx, void *data);
-int cpu_map__get_node_id(int cpu);
-struct aggr_cpu_id cpu_map__get_node(struct perf_cpu_map *map, int idx, void *data);
-int cpu_map__build_socket_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **sockp);
-int cpu_map__build_die_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **diep);
-int cpu_map__build_core_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **corep);
-int cpu_map__build_node_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **nodep);
const struct perf_cpu_map *cpu_map__online(void); /* thread unsafe */
-static inline int cpu_map__socket(struct perf_cpu_map *sock, int s)
+int cpu__setup_cpunode_map(void);
+
+int cpu__max_node(void);
+struct perf_cpu cpu__max_cpu(void);
+struct perf_cpu cpu__max_present_cpu(void);
+
+/**
+ * cpu_map__is_dummy - Events associated with a pid, rather than a CPU, use a single dummy map with an entry of -1.
+ */
+static inline bool cpu_map__is_dummy(struct perf_cpu_map *cpus)
{
- if (!sock || s > sock->nr || s < 0)
- return 0;
- return sock->map[s];
+ return perf_cpu_map__nr(cpus) == 1 && perf_cpu_map__cpu(cpus, 0).cpu == -1;
}
-int cpu__setup_cpunode_map(void);
+/**
+ * cpu__get_node - Returns the numa node X as read from
+ * /sys/devices/system/node/nodeX for the given CPU.
+ */
+int cpu__get_node(struct perf_cpu cpu);
+/**
+ * cpu__get_socket_id - Returns the socket number as read from
+ * /sys/devices/system/cpu/cpuX/topology/physical_package_id for the given CPU.
+ */
+int cpu__get_socket_id(struct perf_cpu cpu);
+/**
+ * cpu__get_die_id - Returns the die id as read from
+ * /sys/devices/system/cpu/cpuX/topology/die_id for the given CPU.
+ */
+int cpu__get_die_id(struct perf_cpu cpu);
+/**
+ * cpu__get_core_id - Returns the core id as read from
+ * /sys/devices/system/cpu/cpuX/topology/core_id for the given CPU.
+ */
+int cpu__get_core_id(struct perf_cpu cpu);
-int cpu__max_node(void);
-int cpu__max_cpu(void);
-int cpu__max_present_cpu(void);
-int cpu__get_node(int cpu);
+/**
+ * cpu_aggr_map__empty_new - Create a cpu_aggr_map of size nr with every entry
+ * being empty.
+ */
+struct cpu_aggr_map *cpu_aggr_map__empty_new(int nr);
+
+typedef struct aggr_cpu_id (*aggr_cpu_id_get_t)(struct perf_cpu cpu, void *data);
+
+/**
+ * cpu_aggr_map__new - Create a cpu_aggr_map with an aggr_cpu_id for each cpu in
+ * cpus. The aggr_cpu_id is created with 'get_id' that may have a data value
+ * passed to it. The cpu_aggr_map is sorted with duplicate values removed.
+ */
+struct cpu_aggr_map *cpu_aggr_map__new(const struct perf_cpu_map *cpus,
+ aggr_cpu_id_get_t get_id,
+ void *data);
-int cpu_map__build_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **res,
- struct aggr_cpu_id (*f)(struct perf_cpu_map *map, int cpu, void *data),
- void *data);
+bool aggr_cpu_id__equal(const struct aggr_cpu_id *a, const struct aggr_cpu_id *b);
+bool aggr_cpu_id__is_empty(const struct aggr_cpu_id *a);
+struct aggr_cpu_id aggr_cpu_id__empty(void);
-int cpu_map__cpu(struct perf_cpu_map *cpus, int idx);
-bool cpu_map__has(struct perf_cpu_map *cpus, int cpu);
-bool cpu_map__compare_aggr_cpu_id(struct aggr_cpu_id a, struct aggr_cpu_id b);
-bool cpu_map__aggr_cpu_id_is_empty(struct aggr_cpu_id a);
-struct aggr_cpu_id cpu_map__empty_aggr_cpu_id(void);
+/**
+ * aggr_cpu_id__socket - Create an aggr_cpu_id with the socket populated with
+ * the socket for cpu. The function signature is compatible with
+ * aggr_cpu_id_get_t.
+ */
+struct aggr_cpu_id aggr_cpu_id__socket(struct perf_cpu cpu, void *data);
+/**
+ * aggr_cpu_id__die - Create an aggr_cpu_id with the die and socket populated
+ * with the die and socket for cpu. The function signature is compatible with
+ * aggr_cpu_id_get_t.
+ */
+struct aggr_cpu_id aggr_cpu_id__die(struct perf_cpu cpu, void *data);
+/**
+ * aggr_cpu_id__core - Create an aggr_cpu_id with the core, die and socket
+ * populated with the core, die and socket for cpu. The function signature is
+ * compatible with aggr_cpu_id_get_t.
+ */
+struct aggr_cpu_id aggr_cpu_id__core(struct perf_cpu cpu, void *data);
+/**
+ * aggr_cpu_id__core - Create an aggr_cpu_id with the cpu, core, die and socket
+ * populated with the cpu, core, die and socket for cpu. The function signature
+ * is compatible with aggr_cpu_id_get_t.
+ */
+struct aggr_cpu_id aggr_cpu_id__cpu(struct perf_cpu cpu, void *data);
+/**
+ * aggr_cpu_id__node - Create an aggr_cpu_id with the numa node populated for
+ * cpu. The function signature is compatible with aggr_cpu_id_get_t.
+ */
+struct aggr_cpu_id aggr_cpu_id__node(struct perf_cpu cpu, void *data);
#endif /* __PERF_CPUMAP_H */
diff --git a/tools/perf/util/cputopo.c b/tools/perf/util/cputopo.c
index 51b429c86f98..d275d843c155 100644
--- a/tools/perf/util/cputopo.c
+++ b/tools/perf/util/cputopo.c
@@ -165,7 +165,8 @@ static bool has_die_topology(void)
if (uname(&uts) < 0)
return false;
- if (strncmp(uts.machine, "x86_64", 6))
+ if (strncmp(uts.machine, "x86_64", 6) &&
+ strncmp(uts.machine, "s390x", 5))
return false;
scnprintf(filename, MAXPATHLEN, DIE_CPUS_FMT,
@@ -187,7 +188,7 @@ struct cpu_topology *cpu_topology__new(void)
struct perf_cpu_map *map;
bool has_die = has_die_topology();
- ncpus = cpu__max_present_cpu();
+ ncpus = cpu__max_present_cpu().cpu;
/* build online CPU map */
map = perf_cpu_map__new(NULL);
@@ -218,7 +219,7 @@ struct cpu_topology *cpu_topology__new(void)
tp->core_cpus_list = addr;
for (i = 0; i < nr; i++) {
- if (!cpu_map__has(map, i))
+ if (!perf_cpu_map__has(map, (struct perf_cpu){ .cpu = i }))
continue;
ret = build_cpu_topology(tp, i);
@@ -324,7 +325,7 @@ struct numa_topology *numa_topology__new(void)
if (!node_map)
goto out;
- nr = (u32) node_map->nr;
+ nr = (u32) perf_cpu_map__nr(node_map);
tp = zalloc(sizeof(*tp) + sizeof(tp->nodes[0])*nr);
if (!tp)
@@ -333,7 +334,7 @@ struct numa_topology *numa_topology__new(void)
tp->nr = nr;
for (i = 0; i < nr; i++) {
- if (load_numa_node(&tp->nodes[i], node_map->map[i])) {
+ if (load_numa_node(&tp->nodes[i], perf_cpu_map__cpu(node_map, i).cpu)) {
numa_topology__delete(tp);
tp = NULL;
break;
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 4f672f7d008c..8b95fb3c4d7b 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -50,8 +50,6 @@ struct cs_etm_auxtrace {
u8 timeless_decoding;
u8 snapshot_mode;
u8 data_queued;
- u8 sample_branches;
- u8 sample_instructions;
int num_cpu;
u64 latest_kernel_timestamp;
@@ -410,8 +408,8 @@ static void cs_etm__packet_swap(struct cs_etm_auxtrace *etm,
{
struct cs_etm_packet *tmp;
- if (etm->sample_branches || etm->synth_opts.last_branch ||
- etm->sample_instructions) {
+ if (etm->synth_opts.branches || etm->synth_opts.last_branch ||
+ etm->synth_opts.instructions) {
/*
* Swap PACKET with PREV_PACKET: PACKET becomes PREV_PACKET for
* the next incoming packet.
@@ -1365,7 +1363,6 @@ static int cs_etm__synth_events(struct cs_etm_auxtrace *etm,
err = cs_etm__synth_event(session, &attr, id);
if (err)
return err;
- etm->sample_branches = true;
etm->branches_sample_type = attr.sample_type;
etm->branches_id = id;
id += 1;
@@ -1389,7 +1386,6 @@ static int cs_etm__synth_events(struct cs_etm_auxtrace *etm,
err = cs_etm__synth_event(session, &attr, id);
if (err)
return err;
- etm->sample_instructions = true;
etm->instructions_sample_type = attr.sample_type;
etm->instructions_id = id;
id += 1;
@@ -1420,7 +1416,7 @@ static int cs_etm__sample(struct cs_etm_queue *etmq,
tidq->prev_packet->last_instr_taken_branch)
cs_etm__update_last_branch_rb(etmq, tidq);
- if (etm->sample_instructions &&
+ if (etm->synth_opts.instructions &&
tidq->period_instructions >= etm->instructions_sample_period) {
/*
* Emit instruction sample periodically
@@ -1503,7 +1499,7 @@ static int cs_etm__sample(struct cs_etm_queue *etmq,
}
}
- if (etm->sample_branches) {
+ if (etm->synth_opts.branches) {
bool generate_sample = false;
/* Generate sample for tracing on packet */
@@ -1557,6 +1553,7 @@ static int cs_etm__flush(struct cs_etm_queue *etmq,
goto swap_packet;
if (etmq->etm->synth_opts.last_branch &&
+ etmq->etm->synth_opts.instructions &&
tidq->prev_packet->sample_type == CS_ETM_RANGE) {
u64 addr;
@@ -1582,7 +1579,7 @@ static int cs_etm__flush(struct cs_etm_queue *etmq,
}
- if (etm->sample_branches &&
+ if (etm->synth_opts.branches &&
tidq->prev_packet->sample_type == CS_ETM_RANGE) {
err = cs_etm__synth_branch_sample(etmq, tidq);
if (err)
@@ -1614,6 +1611,7 @@ static int cs_etm__end_block(struct cs_etm_queue *etmq,
* the trace.
*/
if (etmq->etm->synth_opts.last_branch &&
+ etmq->etm->synth_opts.instructions &&
tidq->prev_packet->sample_type == CS_ETM_RANGE) {
u64 addr;
diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c
index 8f7705bbc2da..9e0aee276df8 100644
--- a/tools/perf/util/data-convert-bt.c
+++ b/tools/perf/util/data-convert-bt.c
@@ -318,6 +318,8 @@ static int add_tracepoint_field_value(struct ctf_writer *cw,
offset = tmp_val;
len = offset >> 16;
offset &= 0xffff;
+ if (flags & TEP_FIELD_IS_RELATIVE)
+ offset += fmtf->offset + fmtf->size;
}
if (flags & TEP_FIELD_IS_ARRAY) {
diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c
index f5d260b1df4d..15a4547d608e 100644
--- a/tools/perf/util/data.c
+++ b/tools/perf/util/data.c
@@ -44,10 +44,6 @@ int perf_data__create_dir(struct perf_data *data, int nr)
if (!files)
return -ENOMEM;
- data->dir.version = PERF_DIR_VERSION;
- data->dir.files = files;
- data->dir.nr = nr;
-
for (i = 0; i < nr; i++) {
struct perf_data_file *file = &files[i];
@@ -62,6 +58,9 @@ int perf_data__create_dir(struct perf_data *data, int nr)
file->fd = ret;
}
+ data->dir.version = PERF_DIR_VERSION;
+ data->dir.files = files;
+ data->dir.nr = nr;
return 0;
out_err:
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index 2c06abf6dcd2..65e6c22f38e4 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -179,7 +179,7 @@ static int trace_event_printer(enum binary_printer_ops op,
break;
case BINARY_PRINT_CHAR_DATA:
printed += color_fprintf(fp, color, "%c",
- isprint(ch) ? ch : '.');
+ isprint(ch) && isascii(ch) ? ch : '.');
break;
case BINARY_PRINT_CHAR_PAD:
printed += color_fprintf(fp, color, " ");
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index b9904896eb97..579e44c59914 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -285,13 +285,13 @@ out_enomem:
int perf_env__read_cpu_topology_map(struct perf_env *env)
{
- int cpu, nr_cpus;
+ int idx, nr_cpus;
if (env->cpu != NULL)
return 0;
if (env->nr_cpus_avail == 0)
- env->nr_cpus_avail = cpu__max_present_cpu();
+ env->nr_cpus_avail = cpu__max_present_cpu().cpu;
nr_cpus = env->nr_cpus_avail;
if (nr_cpus == -1)
@@ -301,10 +301,12 @@ int perf_env__read_cpu_topology_map(struct perf_env *env)
if (env->cpu == NULL)
return -ENOMEM;
- for (cpu = 0; cpu < nr_cpus; ++cpu) {
- env->cpu[cpu].core_id = cpu_map__get_core_id(cpu);
- env->cpu[cpu].socket_id = cpu_map__get_socket_id(cpu);
- env->cpu[cpu].die_id = cpu_map__get_die_id(cpu);
+ for (idx = 0; idx < nr_cpus; ++idx) {
+ struct perf_cpu cpu = { .cpu = idx };
+
+ env->cpu[idx].core_id = cpu__get_core_id(cpu);
+ env->cpu[idx].socket_id = cpu__get_socket_id(cpu);
+ env->cpu[idx].die_id = cpu__get_die_id(cpu);
}
env->nr_cpus_avail = nr_cpus;
@@ -381,7 +383,7 @@ static int perf_env__read_arch(struct perf_env *env)
static int perf_env__read_nr_cpus_avail(struct perf_env *env)
{
if (env->nr_cpus_avail == 0)
- env->nr_cpus_avail = cpu__max_present_cpu();
+ env->nr_cpus_avail = cpu__max_present_cpu().cpu;
return env->nr_cpus_avail ? 0 : -ENOENT;
}
@@ -487,7 +489,7 @@ const char *perf_env__pmu_mappings(struct perf_env *env)
return env->pmu_mappings;
}
-int perf_env__numa_node(struct perf_env *env, int cpu)
+int perf_env__numa_node(struct perf_env *env, struct perf_cpu cpu)
{
if (!env->nr_numa_map) {
struct numa_node *nn;
@@ -495,7 +497,7 @@ int perf_env__numa_node(struct perf_env *env, int cpu)
for (i = 0; i < env->nr_numa_nodes; i++) {
nn = &env->numa_nodes[i];
- nr = max(nr, perf_cpu_map__max(nn->map));
+ nr = max(nr, perf_cpu_map__max(nn->map).cpu);
}
nr++;
@@ -514,13 +516,14 @@ int perf_env__numa_node(struct perf_env *env, int cpu)
env->nr_numa_map = nr;
for (i = 0; i < env->nr_numa_nodes; i++) {
- int tmp, j;
+ struct perf_cpu tmp;
+ int j;
nn = &env->numa_nodes[i];
- perf_cpu_map__for_each_cpu(j, tmp, nn->map)
- env->numa_map[j] = i;
+ perf_cpu_map__for_each_cpu(tmp, j, nn->map)
+ env->numa_map[tmp.cpu] = i;
}
}
- return cpu >= 0 && cpu < env->nr_numa_map ? env->numa_map[cpu] : -1;
+ return cpu.cpu >= 0 && cpu.cpu < env->nr_numa_map ? env->numa_map[cpu.cpu] : -1;
}
diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h
index 163e5ec503a2..a3541f98e1fc 100644
--- a/tools/perf/util/env.h
+++ b/tools/perf/util/env.h
@@ -4,6 +4,7 @@
#include <linux/types.h>
#include <linux/rbtree.h>
+#include "cpumap.h"
#include "rwsem.h"
struct perf_cpu_map;
@@ -170,5 +171,5 @@ struct bpf_prog_info_node *perf_env__find_bpf_prog_info(struct perf_env *env,
bool perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node);
struct btf_node *perf_env__find_btf(struct perf_env *env, __u32 btf_id);
-int perf_env__numa_node(struct perf_env *env, int cpu);
+int perf_env__numa_node(struct perf_env *env, struct perf_cpu cpu);
#endif /* __PERF_ENV_H */
diff --git a/tools/perf/util/evlist-hybrid.c b/tools/perf/util/evlist-hybrid.c
index 7c554234b43d..57f02beef023 100644
--- a/tools/perf/util/evlist-hybrid.c
+++ b/tools/perf/util/evlist-hybrid.c
@@ -124,22 +124,23 @@ int evlist__fix_hybrid_cpus(struct evlist *evlist, const char *cpu_list)
events_nr++;
- if (matched_cpus->nr > 0 && (unmatched_cpus->nr > 0 ||
- matched_cpus->nr < cpus->nr ||
- matched_cpus->nr < pmu->cpus->nr)) {
+ if (perf_cpu_map__nr(matched_cpus) > 0 &&
+ (perf_cpu_map__nr(unmatched_cpus) > 0 ||
+ perf_cpu_map__nr(matched_cpus) < perf_cpu_map__nr(cpus) ||
+ perf_cpu_map__nr(matched_cpus) < perf_cpu_map__nr(pmu->cpus))) {
perf_cpu_map__put(evsel->core.cpus);
perf_cpu_map__put(evsel->core.own_cpus);
evsel->core.cpus = perf_cpu_map__get(matched_cpus);
evsel->core.own_cpus = perf_cpu_map__get(matched_cpus);
- if (unmatched_cpus->nr > 0) {
+ if (perf_cpu_map__nr(unmatched_cpus) > 0) {
cpu_map__snprint(matched_cpus, buf1, sizeof(buf1));
pr_warning("WARNING: use %s in '%s' for '%s', skip other cpus in list.\n",
buf1, pmu->name, evsel->name);
}
}
- if (matched_cpus->nr == 0) {
+ if (perf_cpu_map__nr(matched_cpus) == 0) {
evlist__remove(evlist, evsel);
evsel__delete(evsel);
@@ -153,8 +154,8 @@ int evlist__fix_hybrid_cpus(struct evlist *evlist, const char *cpu_list)
perf_cpu_map__put(matched_cpus);
perf_cpu_map__put(unmatched_cpus);
}
-
- ret = (unmatched_count == events_nr) ? -1 : 0;
+ if (events_nr)
+ ret = (unmatched_count == events_nr) ? -1 : 0;
out:
perf_cpu_map__put(cpus);
return ret;
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 5f92319ce258..41a66a48cbdf 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -342,36 +342,71 @@ static int evlist__nr_threads(struct evlist *evlist, struct evsel *evsel)
return perf_thread_map__nr(evlist->core.threads);
}
-void evlist__cpu_iter_start(struct evlist *evlist)
-{
- struct evsel *pos;
-
- /*
- * Reset the per evsel cpu_iter. This is needed because
- * each evsel's cpumap may have a different index space,
- * and some operations need the index to modify
- * the FD xyarray (e.g. open, close)
- */
- evlist__for_each_entry(evlist, pos)
- pos->cpu_iter = 0;
-}
+struct evlist_cpu_iterator evlist__cpu_begin(struct evlist *evlist, struct affinity *affinity)
+{
+ struct evlist_cpu_iterator itr = {
+ .container = evlist,
+ .evsel = NULL,
+ .cpu_map_idx = 0,
+ .evlist_cpu_map_idx = 0,
+ .evlist_cpu_map_nr = perf_cpu_map__nr(evlist->core.all_cpus),
+ .cpu = (struct perf_cpu){ .cpu = -1},
+ .affinity = affinity,
+ };
-bool evsel__cpu_iter_skip_no_inc(struct evsel *ev, int cpu)
-{
- if (ev->cpu_iter >= ev->core.cpus->nr)
- return true;
- if (cpu >= 0 && ev->core.cpus->map[ev->cpu_iter] != cpu)
- return true;
- return false;
+ if (evlist__empty(evlist)) {
+ /* Ensure the empty list doesn't iterate. */
+ itr.evlist_cpu_map_idx = itr.evlist_cpu_map_nr;
+ } else {
+ itr.evsel = evlist__first(evlist);
+ if (itr.affinity) {
+ itr.cpu = perf_cpu_map__cpu(evlist->core.all_cpus, 0);
+ affinity__set(itr.affinity, itr.cpu.cpu);
+ itr.cpu_map_idx = perf_cpu_map__idx(itr.evsel->core.cpus, itr.cpu);
+ /*
+ * If this CPU isn't in the evsel's cpu map then advance
+ * through the list.
+ */
+ if (itr.cpu_map_idx == -1)
+ evlist_cpu_iterator__next(&itr);
+ }
+ }
+ return itr;
+}
+
+void evlist_cpu_iterator__next(struct evlist_cpu_iterator *evlist_cpu_itr)
+{
+ while (evlist_cpu_itr->evsel != evlist__last(evlist_cpu_itr->container)) {
+ evlist_cpu_itr->evsel = evsel__next(evlist_cpu_itr->evsel);
+ evlist_cpu_itr->cpu_map_idx =
+ perf_cpu_map__idx(evlist_cpu_itr->evsel->core.cpus,
+ evlist_cpu_itr->cpu);
+ if (evlist_cpu_itr->cpu_map_idx != -1)
+ return;
+ }
+ evlist_cpu_itr->evlist_cpu_map_idx++;
+ if (evlist_cpu_itr->evlist_cpu_map_idx < evlist_cpu_itr->evlist_cpu_map_nr) {
+ evlist_cpu_itr->evsel = evlist__first(evlist_cpu_itr->container);
+ evlist_cpu_itr->cpu =
+ perf_cpu_map__cpu(evlist_cpu_itr->container->core.all_cpus,
+ evlist_cpu_itr->evlist_cpu_map_idx);
+ if (evlist_cpu_itr->affinity)
+ affinity__set(evlist_cpu_itr->affinity, evlist_cpu_itr->cpu.cpu);
+ evlist_cpu_itr->cpu_map_idx =
+ perf_cpu_map__idx(evlist_cpu_itr->evsel->core.cpus,
+ evlist_cpu_itr->cpu);
+ /*
+ * If this CPU isn't in the evsel's cpu map then advance through
+ * the list.
+ */
+ if (evlist_cpu_itr->cpu_map_idx == -1)
+ evlist_cpu_iterator__next(evlist_cpu_itr);
+ }
}
-bool evsel__cpu_iter_skip(struct evsel *ev, int cpu)
+bool evlist_cpu_iterator__end(const struct evlist_cpu_iterator *evlist_cpu_itr)
{
- if (!evsel__cpu_iter_skip_no_inc(ev, cpu)) {
- ev->cpu_iter++;
- return false;
- }
- return true;
+ return evlist_cpu_itr->evlist_cpu_map_idx >= evlist_cpu_itr->evlist_cpu_map_nr;
}
static int evsel__strcmp(struct evsel *pos, char *evsel_name)
@@ -400,37 +435,36 @@ static int evlist__is_enabled(struct evlist *evlist)
static void __evlist__disable(struct evlist *evlist, char *evsel_name)
{
struct evsel *pos;
- struct affinity affinity;
- int cpu, i, imm = 0;
+ struct evlist_cpu_iterator evlist_cpu_itr;
+ struct affinity saved_affinity, *affinity = NULL;
bool has_imm = false;
- if (affinity__setup(&affinity) < 0)
- return;
+ // See explanation in evlist__close()
+ if (!cpu_map__is_dummy(evlist->core.cpus)) {
+ if (affinity__setup(&saved_affinity) < 0)
+ return;
+ affinity = &saved_affinity;
+ }
/* Disable 'immediate' events last */
- for (imm = 0; imm <= 1; imm++) {
- evlist__for_each_cpu(evlist, i, cpu) {
- affinity__set(&affinity, cpu);
-
- evlist__for_each_entry(evlist, pos) {
- if (evsel__strcmp(pos, evsel_name))
- continue;
- if (evsel__cpu_iter_skip(pos, cpu))
- continue;
- if (pos->disabled || !evsel__is_group_leader(pos) || !pos->core.fd)
- continue;
- if (pos->immediate)
- has_imm = true;
- if (pos->immediate != imm)
- continue;
- evsel__disable_cpu(pos, pos->cpu_iter - 1);
- }
+ for (int imm = 0; imm <= 1; imm++) {
+ evlist__for_each_cpu(evlist_cpu_itr, evlist, affinity) {
+ pos = evlist_cpu_itr.evsel;
+ if (evsel__strcmp(pos, evsel_name))
+ continue;
+ if (pos->disabled || !evsel__is_group_leader(pos) || !pos->core.fd)
+ continue;
+ if (pos->immediate)
+ has_imm = true;
+ if (pos->immediate != imm)
+ continue;
+ evsel__disable_cpu(pos, evlist_cpu_itr.cpu_map_idx);
}
if (!has_imm)
break;
}
- affinity__cleanup(&affinity);
+ affinity__cleanup(affinity);
evlist__for_each_entry(evlist, pos) {
if (evsel__strcmp(pos, evsel_name))
continue;
@@ -462,26 +496,25 @@ void evlist__disable_evsel(struct evlist *evlist, char *evsel_name)
static void __evlist__enable(struct evlist *evlist, char *evsel_name)
{
struct evsel *pos;
- struct affinity affinity;
- int cpu, i;
-
- if (affinity__setup(&affinity) < 0)
- return;
+ struct evlist_cpu_iterator evlist_cpu_itr;
+ struct affinity saved_affinity, *affinity = NULL;
- evlist__for_each_cpu(evlist, i, cpu) {
- affinity__set(&affinity, cpu);
+ // See explanation in evlist__close()
+ if (!cpu_map__is_dummy(evlist->core.cpus)) {
+ if (affinity__setup(&saved_affinity) < 0)
+ return;
+ affinity = &saved_affinity;
+ }
- evlist__for_each_entry(evlist, pos) {
- if (evsel__strcmp(pos, evsel_name))
- continue;
- if (evsel__cpu_iter_skip(pos, cpu))
- continue;
- if (!evsel__is_group_leader(pos) || !pos->core.fd)
- continue;
- evsel__enable_cpu(pos, pos->cpu_iter - 1);
- }
+ evlist__for_each_cpu(evlist_cpu_itr, evlist, affinity) {
+ pos = evlist_cpu_itr.evsel;
+ if (evsel__strcmp(pos, evsel_name))
+ continue;
+ if (!evsel__is_group_leader(pos) || !pos->core.fd)
+ continue;
+ evsel__enable_cpu(pos, evlist_cpu_itr.cpu_map_idx);
}
- affinity__cleanup(&affinity);
+ affinity__cleanup(affinity);
evlist__for_each_entry(evlist, pos) {
if (evsel__strcmp(pos, evsel_name))
continue;
@@ -800,7 +833,7 @@ perf_evlist__mmap_cb_get(struct perf_evlist *_evlist, bool overwrite, int idx)
static int
perf_evlist__mmap_cb_mmap(struct perf_mmap *_map, struct perf_mmap_param *_mp,
- int output, int cpu)
+ int output, struct perf_cpu cpu)
{
struct mmap *map = container_of(_map, struct mmap, core);
struct mmap_params *mp = container_of(_mp, struct mmap_params, core);
@@ -1264,14 +1297,14 @@ void evlist__set_selected(struct evlist *evlist, struct evsel *evsel)
void evlist__close(struct evlist *evlist)
{
struct evsel *evsel;
+ struct evlist_cpu_iterator evlist_cpu_itr;
struct affinity affinity;
- int cpu, i;
/*
* With perf record core.cpus is usually NULL.
* Use the old method to handle this for now.
*/
- if (!evlist->core.cpus) {
+ if (!evlist->core.cpus || cpu_map__is_dummy(evlist->core.cpus)) {
evlist__for_each_entry_reverse(evlist, evsel)
evsel__close(evsel);
return;
@@ -1279,15 +1312,12 @@ void evlist__close(struct evlist *evlist)
if (affinity__setup(&affinity) < 0)
return;
- evlist__for_each_cpu(evlist, i, cpu) {
- affinity__set(&affinity, cpu);
- evlist__for_each_entry_reverse(evlist, evsel) {
- if (evsel__cpu_iter_skip(evsel, cpu))
- continue;
- perf_evsel__close_cpu(&evsel->core, evsel->cpu_iter - 1);
- }
+ evlist__for_each_cpu(evlist_cpu_itr, evlist, &affinity) {
+ perf_evsel__close_cpu(&evlist_cpu_itr.evsel->core,
+ evlist_cpu_itr.cpu_map_idx);
}
+
affinity__cleanup(&affinity);
evlist__for_each_entry_reverse(evlist, evsel) {
perf_evsel__free_fd(&evsel->core);
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 97bfb8d0be4f..64cba56fbc74 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -64,6 +64,7 @@ struct evlist {
struct evsel *selected;
struct events_stats stats;
struct perf_env *env;
+ const char *hybrid_pmu_name;
void (*trace_event_sample_raw)(struct evlist *evlist,
union perf_event *event,
struct perf_sample *sample);
@@ -110,6 +111,7 @@ int __evlist__add_default_attrs(struct evlist *evlist,
__evlist__add_default_attrs(evlist, array, ARRAY_SIZE(array))
int arch_evlist__add_default_attrs(struct evlist *evlist);
+struct evsel *arch_evlist__leader(struct list_head *list);
int evlist__add_dummy(struct evlist *evlist);
@@ -325,17 +327,53 @@ void evlist__to_front(struct evlist *evlist, struct evsel *move_evsel);
#define evlist__for_each_entry_safe(evlist, tmp, evsel) \
__evlist__for_each_entry_safe(&(evlist)->core.entries, tmp, evsel)
-#define evlist__for_each_cpu(evlist, index, cpu) \
- evlist__cpu_iter_start(evlist); \
- perf_cpu_map__for_each_cpu (cpu, index, (evlist)->core.all_cpus)
+/** Iterator state for evlist__for_each_cpu */
+struct evlist_cpu_iterator {
+ /** The list being iterated through. */
+ struct evlist *container;
+ /** The current evsel of the iterator. */
+ struct evsel *evsel;
+ /** The CPU map index corresponding to the evsel->core.cpus for the current CPU. */
+ int cpu_map_idx;
+ /**
+ * The CPU map index corresponding to evlist->core.all_cpus for the
+ * current CPU. Distinct from cpu_map_idx as the evsel's cpu map may
+ * contain fewer entries.
+ */
+ int evlist_cpu_map_idx;
+ /** The number of CPU map entries in evlist->core.all_cpus. */
+ int evlist_cpu_map_nr;
+ /** The current CPU of the iterator. */
+ struct perf_cpu cpu;
+ /** If present, used to set the affinity when switching between CPUs. */
+ struct affinity *affinity;
+};
+
+/**
+ * evlist__for_each_cpu - without affinity, iterate over the evlist. With
+ * affinity, iterate over all CPUs and then the evlist
+ * for each evsel on that CPU. When switching between
+ * CPUs the affinity is set to the CPU to avoid IPIs
+ * during syscalls.
+ * @evlist_cpu_itr: the iterator instance.
+ * @evlist: evlist instance to iterate.
+ * @affinity: NULL or used to set the affinity to the current CPU.
+ */
+#define evlist__for_each_cpu(evlist_cpu_itr, evlist, affinity) \
+ for ((evlist_cpu_itr) = evlist__cpu_begin(evlist, affinity); \
+ !evlist_cpu_iterator__end(&evlist_cpu_itr); \
+ evlist_cpu_iterator__next(&evlist_cpu_itr))
+
+/** Returns an iterator set to the first CPU/evsel of evlist. */
+struct evlist_cpu_iterator evlist__cpu_begin(struct evlist *evlist, struct affinity *affinity);
+/** Move to next element in iterator, updating CPU, evsel and the affinity. */
+void evlist_cpu_iterator__next(struct evlist_cpu_iterator *evlist_cpu_itr);
+/** Returns true when iterator is at the end of the CPUs and evlist. */
+bool evlist_cpu_iterator__end(const struct evlist_cpu_iterator *evlist_cpu_itr);
struct evsel *evlist__get_tracking_event(struct evlist *evlist);
void evlist__set_tracking_event(struct evlist *evlist, struct evsel *tracking_evsel);
-void evlist__cpu_iter_start(struct evlist *evlist);
-bool evsel__cpu_iter_skip(struct evsel *ev, int cpu);
-bool evsel__cpu_iter_skip_no_inc(struct evsel *ev, int cpu);
-
struct evsel *evlist__find_evsel_by_str(struct evlist *evlist, const char *str);
struct evsel *evlist__event2evsel(struct evlist *evlist, union perf_event *event);
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index ac0127be0459..22d3267ce294 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1064,6 +1064,17 @@ void __weak arch_evsel__fixup_new_cycles(struct perf_event_attr *attr __maybe_un
{
}
+static void evsel__set_default_freq_period(struct record_opts *opts,
+ struct perf_event_attr *attr)
+{
+ if (opts->freq) {
+ attr->freq = 1;
+ attr->sample_freq = opts->freq;
+ } else {
+ attr->sample_period = opts->default_interval;
+ }
+}
+
/*
* The enable_on_exec/disabled value strategy:
*
@@ -1130,14 +1141,12 @@ void evsel__config(struct evsel *evsel, struct record_opts *opts,
* We default some events to have a default interval. But keep
* it a weak assumption overridable by the user.
*/
- if (!attr->sample_period) {
- if (opts->freq) {
- attr->freq = 1;
- attr->sample_freq = opts->freq;
- } else {
- attr->sample_period = opts->default_interval;
- }
- }
+ if ((evsel->is_libpfm_event && !attr->sample_period) ||
+ (!evsel->is_libpfm_event && (!attr->sample_period ||
+ opts->user_freq != UINT_MAX ||
+ opts->user_interval != ULLONG_MAX)))
+ evsel__set_default_freq_period(opts, attr);
+
/*
* If attr->freq was set (here or earlier), ask for period
* to be sampled.
@@ -1372,9 +1381,9 @@ int evsel__append_addr_filter(struct evsel *evsel, const char *filter)
}
/* Caller has to clear disabled after going through all CPUs. */
-int evsel__enable_cpu(struct evsel *evsel, int cpu)
+int evsel__enable_cpu(struct evsel *evsel, int cpu_map_idx)
{
- return perf_evsel__enable_cpu(&evsel->core, cpu);
+ return perf_evsel__enable_cpu(&evsel->core, cpu_map_idx);
}
int evsel__enable(struct evsel *evsel)
@@ -1387,9 +1396,9 @@ int evsel__enable(struct evsel *evsel)
}
/* Caller has to set disabled after going through all CPUs. */
-int evsel__disable_cpu(struct evsel *evsel, int cpu)
+int evsel__disable_cpu(struct evsel *evsel, int cpu_map_idx)
{
- return perf_evsel__disable_cpu(&evsel->core, cpu);
+ return perf_evsel__disable_cpu(&evsel->core, cpu_map_idx);
}
int evsel__disable(struct evsel *evsel)
@@ -1455,7 +1464,7 @@ void evsel__delete(struct evsel *evsel)
free(evsel);
}
-void evsel__compute_deltas(struct evsel *evsel, int cpu, int thread,
+void evsel__compute_deltas(struct evsel *evsel, int cpu_map_idx, int thread,
struct perf_counts_values *count)
{
struct perf_counts_values tmp;
@@ -1463,12 +1472,12 @@ void evsel__compute_deltas(struct evsel *evsel, int cpu, int thread,
if (!evsel->prev_raw_counts)
return;
- if (cpu == -1) {
+ if (cpu_map_idx == -1) {
tmp = evsel->prev_raw_counts->aggr;
evsel->prev_raw_counts->aggr = *count;
} else {
- tmp = *perf_counts(evsel->prev_raw_counts, cpu, thread);
- *perf_counts(evsel->prev_raw_counts, cpu, thread) = *count;
+ tmp = *perf_counts(evsel->prev_raw_counts, cpu_map_idx, thread);
+ *perf_counts(evsel->prev_raw_counts, cpu_map_idx, thread) = *count;
}
count->val = count->val - tmp.val;
@@ -1476,46 +1485,28 @@ void evsel__compute_deltas(struct evsel *evsel, int cpu, int thread,
count->run = count->run - tmp.run;
}
-void perf_counts_values__scale(struct perf_counts_values *count,
- bool scale, s8 *pscaled)
+static int evsel__read_one(struct evsel *evsel, int cpu_map_idx, int thread)
{
- s8 scaled = 0;
+ struct perf_counts_values *count = perf_counts(evsel->counts, cpu_map_idx, thread);
- if (scale) {
- if (count->run == 0) {
- scaled = -1;
- count->val = 0;
- } else if (count->run < count->ena) {
- scaled = 1;
- count->val = (u64)((double) count->val * count->ena / count->run);
- }
- }
-
- if (pscaled)
- *pscaled = scaled;
-}
-
-static int evsel__read_one(struct evsel *evsel, int cpu, int thread)
-{
- struct perf_counts_values *count = perf_counts(evsel->counts, cpu, thread);
-
- return perf_evsel__read(&evsel->core, cpu, thread, count);
+ return perf_evsel__read(&evsel->core, cpu_map_idx, thread, count);
}
-static void evsel__set_count(struct evsel *counter, int cpu, int thread, u64 val, u64 ena, u64 run)
+static void evsel__set_count(struct evsel *counter, int cpu_map_idx, int thread,
+ u64 val, u64 ena, u64 run)
{
struct perf_counts_values *count;
- count = perf_counts(counter->counts, cpu, thread);
+ count = perf_counts(counter->counts, cpu_map_idx, thread);
count->val = val;
count->ena = ena;
count->run = run;
- perf_counts__set_loaded(counter->counts, cpu, thread, true);
+ perf_counts__set_loaded(counter->counts, cpu_map_idx, thread, true);
}
-static int evsel__process_group_data(struct evsel *leader, int cpu, int thread, u64 *data)
+static int evsel__process_group_data(struct evsel *leader, int cpu_map_idx, int thread, u64 *data)
{
u64 read_format = leader->core.attr.read_format;
struct sample_read_value *v;
@@ -1534,7 +1525,7 @@ static int evsel__process_group_data(struct evsel *leader, int cpu, int thread,
v = (struct sample_read_value *) data;
- evsel__set_count(leader, cpu, thread, v[0].value, ena, run);
+ evsel__set_count(leader, cpu_map_idx, thread, v[0].value, ena, run);
for (i = 1; i < nr; i++) {
struct evsel *counter;
@@ -1543,13 +1534,13 @@ static int evsel__process_group_data(struct evsel *leader, int cpu, int thread,
if (!counter)
return -EINVAL;
- evsel__set_count(counter, cpu, thread, v[i].value, ena, run);
+ evsel__set_count(counter, cpu_map_idx, thread, v[i].value, ena, run);
}
return 0;
}
-static int evsel__read_group(struct evsel *leader, int cpu, int thread)
+static int evsel__read_group(struct evsel *leader, int cpu_map_idx, int thread)
{
struct perf_stat_evsel *ps = leader->stats;
u64 read_format = leader->core.attr.read_format;
@@ -1570,67 +1561,67 @@ static int evsel__read_group(struct evsel *leader, int cpu, int thread)
ps->group_data = data;
}
- if (FD(leader, cpu, thread) < 0)
+ if (FD(leader, cpu_map_idx, thread) < 0)
return -EINVAL;
- if (readn(FD(leader, cpu, thread), data, size) <= 0)
+ if (readn(FD(leader, cpu_map_idx, thread), data, size) <= 0)
return -errno;
- return evsel__process_group_data(leader, cpu, thread, data);
+ return evsel__process_group_data(leader, cpu_map_idx, thread, data);
}
-int evsel__read_counter(struct evsel *evsel, int cpu, int thread)
+int evsel__read_counter(struct evsel *evsel, int cpu_map_idx, int thread)
{
u64 read_format = evsel->core.attr.read_format;
if (read_format & PERF_FORMAT_GROUP)
- return evsel__read_group(evsel, cpu, thread);
+ return evsel__read_group(evsel, cpu_map_idx, thread);
- return evsel__read_one(evsel, cpu, thread);
+ return evsel__read_one(evsel, cpu_map_idx, thread);
}
-int __evsel__read_on_cpu(struct evsel *evsel, int cpu, int thread, bool scale)
+int __evsel__read_on_cpu(struct evsel *evsel, int cpu_map_idx, int thread, bool scale)
{
struct perf_counts_values count;
size_t nv = scale ? 3 : 1;
- if (FD(evsel, cpu, thread) < 0)
+ if (FD(evsel, cpu_map_idx, thread) < 0)
return -EINVAL;
- if (evsel->counts == NULL && evsel__alloc_counts(evsel, cpu + 1, thread + 1) < 0)
+ if (evsel->counts == NULL && evsel__alloc_counts(evsel) < 0)
return -ENOMEM;
- if (readn(FD(evsel, cpu, thread), &count, nv * sizeof(u64)) <= 0)
+ if (readn(FD(evsel, cpu_map_idx, thread), &count, nv * sizeof(u64)) <= 0)
return -errno;
- evsel__compute_deltas(evsel, cpu, thread, &count);
+ evsel__compute_deltas(evsel, cpu_map_idx, thread, &count);
perf_counts_values__scale(&count, scale, NULL);
- *perf_counts(evsel->counts, cpu, thread) = count;
+ *perf_counts(evsel->counts, cpu_map_idx, thread) = count;
return 0;
}
static int evsel__match_other_cpu(struct evsel *evsel, struct evsel *other,
- int cpu)
+ int cpu_map_idx)
{
- int cpuid;
+ struct perf_cpu cpu;
- cpuid = perf_cpu_map__cpu(evsel->core.cpus, cpu);
- return perf_cpu_map__idx(other->core.cpus, cpuid);
+ cpu = perf_cpu_map__cpu(evsel->core.cpus, cpu_map_idx);
+ return perf_cpu_map__idx(other->core.cpus, cpu);
}
-static int evsel__hybrid_group_cpu(struct evsel *evsel, int cpu)
+static int evsel__hybrid_group_cpu_map_idx(struct evsel *evsel, int cpu_map_idx)
{
struct evsel *leader = evsel__leader(evsel);
if ((evsel__is_hybrid(evsel) && !evsel__is_hybrid(leader)) ||
(!evsel__is_hybrid(evsel) && evsel__is_hybrid(leader))) {
- return evsel__match_other_cpu(evsel, leader, cpu);
+ return evsel__match_other_cpu(evsel, leader, cpu_map_idx);
}
- return cpu;
+ return cpu_map_idx;
}
-static int get_group_fd(struct evsel *evsel, int cpu, int thread)
+static int get_group_fd(struct evsel *evsel, int cpu_map_idx, int thread)
{
struct evsel *leader = evsel__leader(evsel);
int fd;
@@ -1644,11 +1635,11 @@ static int get_group_fd(struct evsel *evsel, int cpu, int thread)
*/
BUG_ON(!leader->core.fd);
- cpu = evsel__hybrid_group_cpu(evsel, cpu);
- if (cpu == -1)
+ cpu_map_idx = evsel__hybrid_group_cpu_map_idx(evsel, cpu_map_idx);
+ if (cpu_map_idx == -1)
return -1;
- fd = FD(leader, cpu, thread);
+ fd = FD(leader, cpu_map_idx, thread);
BUG_ON(fd == -1);
return fd;
@@ -1662,16 +1653,16 @@ static void evsel__remove_fd(struct evsel *pos, int nr_cpus, int nr_threads, int
}
static int update_fds(struct evsel *evsel,
- int nr_cpus, int cpu_idx,
+ int nr_cpus, int cpu_map_idx,
int nr_threads, int thread_idx)
{
struct evsel *pos;
- if (cpu_idx >= nr_cpus || thread_idx >= nr_threads)
+ if (cpu_map_idx >= nr_cpus || thread_idx >= nr_threads)
return -EINVAL;
evlist__for_each_entry(evsel->evlist, pos) {
- nr_cpus = pos != evsel ? nr_cpus : cpu_idx;
+ nr_cpus = pos != evsel ? nr_cpus : cpu_map_idx;
evsel__remove_fd(pos, nr_cpus, nr_threads, thread_idx);
@@ -1685,10 +1676,10 @@ static int update_fds(struct evsel *evsel,
return 0;
}
-bool evsel__ignore_missing_thread(struct evsel *evsel,
- int nr_cpus, int cpu,
- struct perf_thread_map *threads,
- int thread, int err)
+static bool evsel__ignore_missing_thread(struct evsel *evsel,
+ int nr_cpus, int cpu_map_idx,
+ struct perf_thread_map *threads,
+ int thread, int err)
{
pid_t ignore_pid = perf_thread_map__pid(threads, thread);
@@ -1711,7 +1702,7 @@ bool evsel__ignore_missing_thread(struct evsel *evsel,
* We should remove fd for missing_thread first
* because thread_map__remove() will decrease threads->nr.
*/
- if (update_fds(evsel, nr_cpus, cpu, threads->nr, thread))
+ if (update_fds(evsel, nr_cpus, cpu_map_idx, threads->nr, thread))
return false;
if (thread_map__remove(threads, thread))
@@ -1800,7 +1791,7 @@ static int __evsel__prepare_open(struct evsel *evsel, struct perf_cpu_map *cpus,
nthreads = threads->nr;
if (evsel->core.fd == NULL &&
- perf_evsel__alloc_fd(&evsel->core, cpus->nr, nthreads) < 0)
+ perf_evsel__alloc_fd(&evsel->core, perf_cpu_map__nr(cpus), nthreads) < 0)
return -ENOMEM;
evsel->open_flags = PERF_FLAG_FD_CLOEXEC;
@@ -1993,9 +1984,9 @@ bool evsel__increase_rlimit(enum rlimit_action *set_rlimit)
static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,
struct perf_thread_map *threads,
- int start_cpu, int end_cpu)
+ int start_cpu_map_idx, int end_cpu_map_idx)
{
- int cpu, thread, nthreads;
+ int idx, thread, nthreads;
int pid = -1, err, old_errno;
enum rlimit_action set_rlimit = NO_CHANGE;
@@ -2022,7 +2013,7 @@ fallback_missing_features:
display_attr(&evsel->core.attr);
- for (cpu = start_cpu; cpu < end_cpu; cpu++) {
+ for (idx = start_cpu_map_idx; idx < end_cpu_map_idx; idx++) {
for (thread = 0; thread < nthreads; thread++) {
int fd, group_fd;
@@ -2033,17 +2024,18 @@ retry_open:
if (!evsel->cgrp && !evsel->core.system_wide)
pid = perf_thread_map__pid(threads, thread);
- group_fd = get_group_fd(evsel, cpu, thread);
+ group_fd = get_group_fd(evsel, idx, thread);
test_attr__ready();
pr_debug2_peo("sys_perf_event_open: pid %d cpu %d group_fd %d flags %#lx",
- pid, cpus->map[cpu], group_fd, evsel->open_flags);
+ pid, perf_cpu_map__cpu(cpus, idx).cpu, group_fd, evsel->open_flags);
- fd = sys_perf_event_open(&evsel->core.attr, pid, cpus->map[cpu],
+ fd = sys_perf_event_open(&evsel->core.attr, pid,
+ perf_cpu_map__cpu(cpus, idx).cpu,
group_fd, evsel->open_flags);
- FD(evsel, cpu, thread) = fd;
+ FD(evsel, idx, thread) = fd;
if (fd < 0) {
err = -errno;
@@ -2053,10 +2045,11 @@ retry_open:
goto try_fallback;
}
- bpf_counter__install_pe(evsel, cpu, fd);
+ bpf_counter__install_pe(evsel, idx, fd);
if (unlikely(test_attr__enabled)) {
- test_attr__open(&evsel->core.attr, pid, cpus->map[cpu],
+ test_attr__open(&evsel->core.attr, pid,
+ perf_cpu_map__cpu(cpus, idx),
fd, group_fd, evsel->open_flags);
}
@@ -2097,7 +2090,8 @@ try_fallback:
if (evsel__precise_ip_fallback(evsel))
goto retry_open;
- if (evsel__ignore_missing_thread(evsel, cpus->nr, cpu, threads, thread, err)) {
+ if (evsel__ignore_missing_thread(evsel, perf_cpu_map__nr(cpus),
+ idx, threads, thread, err)) {
/* We just removed 1 thread, so lower the upper nthreads limit. */
nthreads--;
@@ -2112,7 +2106,7 @@ try_fallback:
if (err == -EMFILE && evsel__increase_rlimit(&set_rlimit))
goto retry_open;
- if (err != -EINVAL || cpu > 0 || thread > 0)
+ if (err != -EINVAL || idx > 0 || thread > 0)
goto out_close;
if (evsel__detect_missing_features(evsel))
@@ -2124,12 +2118,12 @@ out_close:
old_errno = errno;
do {
while (--thread >= 0) {
- if (FD(evsel, cpu, thread) >= 0)
- close(FD(evsel, cpu, thread));
- FD(evsel, cpu, thread) = -1;
+ if (FD(evsel, idx, thread) >= 0)
+ close(FD(evsel, idx, thread));
+ FD(evsel, idx, thread) = -1;
}
thread = nthreads;
- } while (--cpu >= 0);
+ } while (--idx >= 0);
errno = old_errno;
return err;
}
@@ -2137,7 +2131,7 @@ out_close:
int evsel__open(struct evsel *evsel, struct perf_cpu_map *cpus,
struct perf_thread_map *threads)
{
- return evsel__open_cpu(evsel, cpus, threads, 0, cpus ? cpus->nr : 1);
+ return evsel__open_cpu(evsel, cpus, threads, 0, perf_cpu_map__nr(cpus));
}
void evsel__close(struct evsel *evsel)
@@ -2146,13 +2140,12 @@ void evsel__close(struct evsel *evsel)
perf_evsel__free_id(&evsel->core);
}
-int evsel__open_per_cpu(struct evsel *evsel, struct perf_cpu_map *cpus, int cpu)
+int evsel__open_per_cpu(struct evsel *evsel, struct perf_cpu_map *cpus, int cpu_map_idx)
{
- if (cpu == -1)
- return evsel__open_cpu(evsel, cpus, NULL, 0,
- cpus ? cpus->nr : 1);
+ if (cpu_map_idx == -1)
+ return evsel__open_cpu(evsel, cpus, NULL, 0, perf_cpu_map__nr(cpus));
- return evsel__open_cpu(evsel, cpus, NULL, cpu, cpu + 1);
+ return evsel__open_cpu(evsel, cpus, NULL, cpu_map_idx, cpu_map_idx + 1);
}
int evsel__open_per_thread(struct evsel *evsel, struct perf_thread_map *threads)
@@ -2706,6 +2699,8 @@ void *evsel__rawptr(struct evsel *evsel, struct perf_sample *sample, const char
if (field->flags & TEP_FIELD_IS_DYNAMIC) {
offset = *(int *)(sample->raw_data + field->offset);
offset &= 0xffff;
+ if (field->flags & TEP_FIELD_IS_RELATIVE)
+ offset += field->offset + field->size;
}
return sample->raw_data + offset;
@@ -2950,6 +2945,10 @@ int evsel__open_strerror(struct evsel *evsel, struct target *target,
return scnprintf(msg, size, "wrong clockid (%d).", clockid);
if (perf_missing_features.aux_output)
return scnprintf(msg, size, "The 'aux_output' feature is not supported, update the kernel.");
+ if (!target__has_cpu(target))
+ return scnprintf(msg, size,
+ "Invalid event (%s) in per-thread mode, enable system wide with '-a'.",
+ evsel__name(evsel));
break;
case ENODATA:
return scnprintf(msg, size, "Cannot collect data source with the load latency event alone. "
@@ -2973,15 +2972,15 @@ struct perf_env *evsel__env(struct evsel *evsel)
static int store_evsel_ids(struct evsel *evsel, struct evlist *evlist)
{
- int cpu, thread;
+ int cpu_map_idx, thread;
- for (cpu = 0; cpu < xyarray__max_x(evsel->core.fd); cpu++) {
+ for (cpu_map_idx = 0; cpu_map_idx < xyarray__max_x(evsel->core.fd); cpu_map_idx++) {
for (thread = 0; thread < xyarray__max_y(evsel->core.fd);
thread++) {
- int fd = FD(evsel, cpu, thread);
+ int fd = FD(evsel, cpu_map_idx, thread);
if (perf_evlist__id_add_fd(&evlist->core, &evsel->core,
- cpu, thread, fd) < 0)
+ cpu_map_idx, thread, fd) < 0)
return -1;
}
}
@@ -2994,7 +2993,7 @@ int evsel__store_ids(struct evsel *evsel, struct evlist *evlist)
struct perf_cpu_map *cpus = evsel->core.cpus;
struct perf_thread_map *threads = evsel->core.threads;
- if (perf_evsel__alloc_id(&evsel->core, cpus->nr, threads->nr))
+ if (perf_evsel__alloc_id(&evsel->core, perf_cpu_map__nr(cpus), threads->nr))
return -ENOMEM;
return store_evsel_ids(evsel, evlist);
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 29d49a8c1e92..041b42d33bf5 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -11,6 +11,7 @@
#include <perf/evsel.h>
#include "symbol_conf.h"
#include <internal/cpumap.h>
+#include <perf/cpumap.h>
struct bpf_object;
struct cgroup;
@@ -121,7 +122,6 @@ struct evsel {
bool errored;
struct hashmap *per_pkg_mask;
int err;
- int cpu_iter;
struct {
evsel__sb_cb_t *cb;
void *data;
@@ -192,12 +192,9 @@ static inline struct perf_cpu_map *evsel__cpus(struct evsel *evsel)
static inline int evsel__nr_cpus(struct evsel *evsel)
{
- return evsel__cpus(evsel)->nr;
+ return perf_cpu_map__nr(evsel__cpus(evsel));
}
-void perf_counts_values__scale(struct perf_counts_values *count,
- bool scale, s8 *pscaled);
-
void evsel__compute_deltas(struct evsel *evsel, int cpu, int thread,
struct perf_counts_values *count);
@@ -288,12 +285,12 @@ void arch_evsel__fixup_new_cycles(struct perf_event_attr *attr);
int evsel__set_filter(struct evsel *evsel, const char *filter);
int evsel__append_tp_filter(struct evsel *evsel, const char *filter);
int evsel__append_addr_filter(struct evsel *evsel, const char *filter);
-int evsel__enable_cpu(struct evsel *evsel, int cpu);
+int evsel__enable_cpu(struct evsel *evsel, int cpu_map_idx);
int evsel__enable(struct evsel *evsel);
int evsel__disable(struct evsel *evsel);
-int evsel__disable_cpu(struct evsel *evsel, int cpu);
+int evsel__disable_cpu(struct evsel *evsel, int cpu_map_idx);
-int evsel__open_per_cpu(struct evsel *evsel, struct perf_cpu_map *cpus, int cpu);
+int evsel__open_per_cpu(struct evsel *evsel, struct perf_cpu_map *cpus, int cpu_map_idx);
int evsel__open_per_thread(struct evsel *evsel, struct perf_thread_map *threads);
int evsel__open(struct evsel *evsel, struct perf_cpu_map *cpus,
struct perf_thread_map *threads);
@@ -305,10 +302,6 @@ bool evsel__detect_missing_features(struct evsel *evsel);
enum rlimit_action { NO_CHANGE, SET_TO_MAX, INCREASED_MAX };
bool evsel__increase_rlimit(enum rlimit_action *set_rlimit);
-bool evsel__ignore_missing_thread(struct evsel *evsel,
- int nr_cpus, int cpu,
- struct perf_thread_map *threads,
- int thread, int err);
bool evsel__precise_ip_fallback(struct evsel *evsel);
struct perf_sample;
@@ -337,32 +330,32 @@ static inline bool evsel__match2(struct evsel *e1, struct evsel *e2)
(e1->core.attr.config == e2->core.attr.config);
}
-int evsel__read_counter(struct evsel *evsel, int cpu, int thread);
+int evsel__read_counter(struct evsel *evsel, int cpu_map_idx, int thread);
-int __evsel__read_on_cpu(struct evsel *evsel, int cpu, int thread, bool scale);
+int __evsel__read_on_cpu(struct evsel *evsel, int cpu_map_idx, int thread, bool scale);
/**
* evsel__read_on_cpu - Read out the results on a CPU and thread
*
* @evsel - event selector to read value
- * @cpu - CPU of interest
+ * @cpu_map_idx - CPU of interest
* @thread - thread of interest
*/
-static inline int evsel__read_on_cpu(struct evsel *evsel, int cpu, int thread)
+static inline int evsel__read_on_cpu(struct evsel *evsel, int cpu_map_idx, int thread)
{
- return __evsel__read_on_cpu(evsel, cpu, thread, false);
+ return __evsel__read_on_cpu(evsel, cpu_map_idx, thread, false);
}
/**
* evsel__read_on_cpu_scaled - Read out the results on a CPU and thread, scaled
*
* @evsel - event selector to read value
- * @cpu - CPU of interest
+ * @cpu_map_idx - CPU of interest
* @thread - thread of interest
*/
-static inline int evsel__read_on_cpu_scaled(struct evsel *evsel, int cpu, int thread)
+static inline int evsel__read_on_cpu_scaled(struct evsel *evsel, int cpu_map_idx, int thread)
{
- return __evsel__read_on_cpu(evsel, cpu, thread, true);
+ return __evsel__read_on_cpu(evsel, cpu_map_idx, thread, true);
}
int evsel__parse_sample(struct evsel *evsel, union perf_event *event,
diff --git a/tools/perf/util/expr.c b/tools/perf/util/expr.c
index 666b59baeb70..675f318ce7c1 100644
--- a/tools/perf/util/expr.c
+++ b/tools/perf/util/expr.c
@@ -405,12 +405,17 @@ double expr_id_data__source_count(const struct expr_id_data *data)
double expr__get_literal(const char *literal)
{
static struct cpu_topology *topology;
+ double result = NAN;
- if (!strcmp("#smt_on", literal))
- return smt_on() > 0 ? 1.0 : 0.0;
+ if (!strcasecmp("#smt_on", literal)) {
+ result = smt_on() > 0 ? 1.0 : 0.0;
+ goto out;
+ }
- if (!strcmp("#num_cpus", literal))
- return cpu__max_present_cpu();
+ if (!strcmp("#num_cpus", literal)) {
+ result = cpu__max_present_cpu().cpu;
+ goto out;
+ }
/*
* Assume that topology strings are consistent, such as CPUs "0-1"
@@ -422,16 +427,24 @@ double expr__get_literal(const char *literal)
topology = cpu_topology__new();
if (!topology) {
pr_err("Error creating CPU topology");
- return NAN;
+ goto out;
}
}
- if (!strcmp("#num_packages", literal))
- return topology->package_cpus_lists;
- if (!strcmp("#num_dies", literal))
- return topology->die_cpus_lists;
- if (!strcmp("#num_cores", literal))
- return topology->core_cpus_lists;
+ if (!strcmp("#num_packages", literal)) {
+ result = topology->package_cpus_lists;
+ goto out;
+ }
+ if (!strcmp("#num_dies", literal)) {
+ result = topology->die_cpus_lists;
+ goto out;
+ }
+ if (!strcmp("#num_cores", literal)) {
+ result = topology->core_cpus_lists;
+ goto out;
+ }
pr_err("Unrecognized literal '%s'", literal);
- return NAN;
+out:
+ pr_debug2("literal: %s = %f\n", literal, result);
+ return result;
}
diff --git a/tools/perf/util/ftrace.h b/tools/perf/util/ftrace.h
new file mode 100644
index 000000000000..887f68a185f7
--- /dev/null
+++ b/tools/perf/util/ftrace.h
@@ -0,0 +1,81 @@
+#ifndef __PERF_FTRACE_H__
+#define __PERF_FTRACE_H__
+
+#include <linux/list.h>
+
+#include "target.h"
+
+struct evlist;
+
+struct perf_ftrace {
+ struct evlist *evlist;
+ struct target target;
+ const char *tracer;
+ struct list_head filters;
+ struct list_head notrace;
+ struct list_head graph_funcs;
+ struct list_head nograph_funcs;
+ unsigned long percpu_buffer_size;
+ bool inherit;
+ int graph_depth;
+ int func_stack_trace;
+ int func_irq_info;
+ int graph_nosleep_time;
+ int graph_noirqs;
+ int graph_verbose;
+ int graph_thresh;
+ unsigned int initial_delay;
+};
+
+struct filter_entry {
+ struct list_head list;
+ char name[];
+};
+
+#define NUM_BUCKET 22 /* 20 + 2 (for outliers in both direction) */
+
+#ifdef HAVE_BPF_SKEL
+
+int perf_ftrace__latency_prepare_bpf(struct perf_ftrace *ftrace);
+int perf_ftrace__latency_start_bpf(struct perf_ftrace *ftrace);
+int perf_ftrace__latency_stop_bpf(struct perf_ftrace *ftrace);
+int perf_ftrace__latency_read_bpf(struct perf_ftrace *ftrace,
+ int buckets[]);
+int perf_ftrace__latency_cleanup_bpf(struct perf_ftrace *ftrace);
+
+#else /* !HAVE_BPF_SKEL */
+
+static inline int
+perf_ftrace__latency_prepare_bpf(struct perf_ftrace *ftrace __maybe_unused)
+{
+ return -1;
+}
+
+static inline int
+perf_ftrace__latency_start_bpf(struct perf_ftrace *ftrace __maybe_unused)
+{
+ return -1;
+}
+
+static inline int
+perf_ftrace__latency_stop_bpf(struct perf_ftrace *ftrace __maybe_unused)
+{
+ return -1;
+}
+
+static inline int
+perf_ftrace__latency_read_bpf(struct perf_ftrace *ftrace __maybe_unused,
+ int buckets[] __maybe_unused)
+{
+ return -1;
+}
+
+static inline int
+perf_ftrace__latency_cleanup_bpf(struct perf_ftrace *ftrace __maybe_unused)
+{
+ return -1;
+}
+
+#endif /* HAVE_BPF_SKEL */
+
+#endif /* __PERF_FTRACE_H__ */
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index e3c1a532d059..6da12e522edc 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -472,7 +472,7 @@ static int write_nrcpus(struct feat_fd *ff,
u32 nrc, nra;
int ret;
- nrc = cpu__max_present_cpu();
+ nrc = cpu__max_present_cpu().cpu;
nr = sysconf(_SC_NPROCESSORS_ONLN);
if (nr < 0)
@@ -1163,7 +1163,7 @@ static int build_caches(struct cpu_cache_level caches[], u32 *cntp)
u32 nr, cpu;
u16 level;
- nr = cpu__max_cpu();
+ nr = cpu__max_cpu().cpu;
for (cpu = 0; cpu < nr; cpu++) {
for (level = 0; level < MAX_CACHE_LVL; level++) {
@@ -1195,7 +1195,7 @@ static int build_caches(struct cpu_cache_level caches[], u32 *cntp)
static int write_cache(struct feat_fd *ff,
struct evlist *evlist __maybe_unused)
{
- u32 max_caches = cpu__max_cpu() * MAX_CACHE_LVL;
+ u32 max_caches = cpu__max_cpu().cpu * MAX_CACHE_LVL;
struct cpu_cache_level caches[max_caches];
u32 cnt = 0, i, version = 1;
int ret;
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index b776465e04ef..0a8033b09e28 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -211,7 +211,9 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
hists__new_col_len(hists, HISTC_MEM_BLOCKED, 10);
hists__new_col_len(hists, HISTC_LOCAL_INS_LAT, 13);
hists__new_col_len(hists, HISTC_GLOBAL_INS_LAT, 13);
- hists__new_col_len(hists, HISTC_P_STAGE_CYC, 13);
+ hists__new_col_len(hists, HISTC_LOCAL_P_STAGE_CYC, 13);
+ hists__new_col_len(hists, HISTC_GLOBAL_P_STAGE_CYC, 13);
+
if (symbol_conf.nanosecs)
hists__new_col_len(hists, HISTC_TIME, 16);
else
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 621f35ae1efa..2a15e22fb89c 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -75,7 +75,8 @@ enum hist_column {
HISTC_MEM_BLOCKED,
HISTC_LOCAL_INS_LAT,
HISTC_GLOBAL_INS_LAT,
- HISTC_P_STAGE_CYC,
+ HISTC_LOCAL_P_STAGE_CYC,
+ HISTC_GLOBAL_P_STAGE_CYC,
HISTC_NR_COLS, /* Last entry */
};
diff --git a/tools/perf/util/include/linux/linkage.h b/tools/perf/util/include/linux/linkage.h
index 5acf053fca7d..aa0c5179836d 100644
--- a/tools/perf/util/include/linux/linkage.h
+++ b/tools/perf/util/include/linux/linkage.h
@@ -50,41 +50,32 @@
#ifndef SYM_END
#define SYM_END(name, sym_type) \
.type name sym_type ASM_NL \
+ .set .L__sym_size_##name, .-name ASM_NL \
.size name, .-name
#endif
-/*
- * SYM_FUNC_START_ALIAS -- use where there are two global names for one
- * function
- */
-#ifndef SYM_FUNC_START_ALIAS
-#define SYM_FUNC_START_ALIAS(name) \
- SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN)
+/* SYM_ALIAS -- use only if you have to */
+#ifndef SYM_ALIAS
+#define SYM_ALIAS(alias, name, sym_type, linkage) \
+ linkage(alias) ASM_NL \
+ .set alias, name ASM_NL \
+ .type alias sym_type ASM_NL \
+ .set .L__sym_size_##alias, .L__sym_size_##name ASM_NL \
+ .size alias, .L__sym_size_##alias
#endif
/* SYM_FUNC_START -- use for global functions */
#ifndef SYM_FUNC_START
-/*
- * The same as SYM_FUNC_START_ALIAS, but we will need to distinguish these two
- * later.
- */
#define SYM_FUNC_START(name) \
SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN)
#endif
/* SYM_FUNC_START_LOCAL -- use for local functions */
#ifndef SYM_FUNC_START_LOCAL
-/* the same as SYM_FUNC_START_LOCAL_ALIAS, see comment near SYM_FUNC_START */
#define SYM_FUNC_START_LOCAL(name) \
SYM_START(name, SYM_L_LOCAL, SYM_A_ALIGN)
#endif
-/* SYM_FUNC_END_ALIAS -- the end of LOCAL_ALIASed or ALIASed function */
-#ifndef SYM_FUNC_END_ALIAS
-#define SYM_FUNC_END_ALIAS(name) \
- SYM_END(name, SYM_T_FUNC)
-#endif
-
/* SYM_FUNC_START_WEAK -- use for weak functions */
#ifndef SYM_FUNC_START_WEAK
#define SYM_FUNC_START_WEAK(name) \
@@ -96,9 +87,32 @@
* SYM_FUNC_START_WEAK, ...
*/
#ifndef SYM_FUNC_END
-/* the same as SYM_FUNC_END_ALIAS, see comment near SYM_FUNC_START */
#define SYM_FUNC_END(name) \
SYM_END(name, SYM_T_FUNC)
#endif
+/*
+ * SYM_FUNC_ALIAS -- define a global alias for an existing function
+ */
+#ifndef SYM_FUNC_ALIAS
+#define SYM_FUNC_ALIAS(alias, name) \
+ SYM_ALIAS(alias, name, SYM_T_FUNC, SYM_L_GLOBAL)
+#endif
+
+/*
+ * SYM_FUNC_ALIAS_LOCAL -- define a local alias for an existing function
+ */
+#ifndef SYM_FUNC_ALIAS_LOCAL
+#define SYM_FUNC_ALIAS_LOCAL(alias, name) \
+ SYM_ALIAS(alias, name, SYM_T_FUNC, SYM_L_LOCAL)
+#endif
+
+/*
+ * SYM_FUNC_ALIAS_WEAK -- define a weak global alias for an existing function
+ */
+#ifndef SYM_FUNC_ALIAS_WEAK
+#define SYM_FUNC_ALIAS_WEAK(alias, name) \
+ SYM_ALIAS(alias, name, SYM_T_FUNC, SYM_L_WEAK)
+#endif
+
#endif /* PERF_LINUX_LINKAGE_H_ */
diff --git a/tools/perf/util/libunwind/arm64.c b/tools/perf/util/libunwind/arm64.c
index c397be0c2e32..15f60fd09424 100644
--- a/tools/perf/util/libunwind/arm64.c
+++ b/tools/perf/util/libunwind/arm64.c
@@ -23,7 +23,9 @@
#include "unwind.h"
#include "libunwind-aarch64.h"
+#define perf_event_arm_regs perf_event_arm64_regs
#include <../../../../arch/arm64/include/uapi/asm/perf_regs.h>
+#undef perf_event_arm_regs
#include "../../arch/arm64/util/unwind-libunwind.c"
/* NO_LIBUNWIND_DEBUG_FRAME is a feature flag for local libunwind,
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index fb8496df8432..394550003693 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -16,6 +16,7 @@
#include "map_symbol.h"
#include "branch.h"
#include "mem-events.h"
+#include "path.h"
#include "srcline.h"
#include "symbol.h"
#include "sort.h"
@@ -34,6 +35,7 @@
#include "bpf-event.h"
#include <internal/lib.h> // page_size
#include "cgroup.h"
+#include "arm64-frame-pointer-unwind-support.h"
#include <linux/ctype.h>
#include <symbol/kallsyms.h>
@@ -1415,7 +1417,7 @@ static int maps__set_modules_path_dir(struct maps *maps, const char *dir_name, i
struct stat st;
/*sshfs might return bad dent->d_type, so we have to stat*/
- snprintf(path, sizeof(path), "%s/%s", dir_name, dent->d_name);
+ path__join(path, sizeof(path), dir_name, dent->d_name);
if (stat(path, &st))
continue;
@@ -2071,6 +2073,7 @@ static void ip__resolve_ams(struct thread *thread,
ams->addr = ip;
ams->al_addr = al.addr;
+ ams->al_level = al.level;
ams->ms.maps = al.maps;
ams->ms.sym = al.sym;
ams->ms.map = al.map;
@@ -2090,6 +2093,7 @@ static void ip__resolve_data(struct thread *thread,
ams->addr = addr;
ams->al_addr = al.addr;
+ ams->al_level = al.level;
ams->ms.maps = al.maps;
ams->ms.sym = al.sym;
ams->ms.map = al.map;
@@ -2710,6 +2714,15 @@ static int find_prev_cpumode(struct ip_callchain *chain, struct thread *thread,
return err;
}
+static u64 get_leaf_frame_caller(struct perf_sample *sample,
+ struct thread *thread, int usr_idx)
+{
+ if (machine__normalized_is(thread->maps->machine, "arm64"))
+ return get_leaf_frame_caller_aarch64(sample, thread, usr_idx);
+ else
+ return 0;
+}
+
static int thread__resolve_callchain_sample(struct thread *thread,
struct callchain_cursor *cursor,
struct evsel *evsel,
@@ -2723,9 +2736,10 @@ static int thread__resolve_callchain_sample(struct thread *thread,
struct ip_callchain *chain = sample->callchain;
int chain_nr = 0;
u8 cpumode = PERF_RECORD_MISC_USER;
- int i, j, err, nr_entries;
+ int i, j, err, nr_entries, usr_idx;
int skip_idx = -1;
int first_call = 0;
+ u64 leaf_frame_caller;
if (chain)
chain_nr = chain->nr;
@@ -2850,6 +2864,34 @@ check_calls:
continue;
}
+ /*
+ * PERF_CONTEXT_USER allows us to locate where the user stack ends.
+ * Depending on callchain_param.order and the position of PERF_CONTEXT_USER,
+ * the index will be different in order to add the missing frame
+ * at the right place.
+ */
+
+ usr_idx = callchain_param.order == ORDER_CALLEE ? j-2 : j-1;
+
+ if (usr_idx >= 0 && chain->ips[usr_idx] == PERF_CONTEXT_USER) {
+
+ leaf_frame_caller = get_leaf_frame_caller(sample, thread, usr_idx);
+
+ /*
+ * check if leaf_frame_Caller != ip to not add the same
+ * value twice.
+ */
+
+ if (leaf_frame_caller && leaf_frame_caller != ip) {
+
+ err = add_callchain_ip(thread, cursor, parent,
+ root_al, &cpumode, leaf_frame_caller,
+ false, NULL, NULL, 0);
+ if (err)
+ return (err < 0) ? err : 0;
+ }
+ }
+
err = add_callchain_ip(thread, cursor, parent,
root_al, &cpumode, ip,
false, NULL, NULL, 0);
@@ -3079,14 +3121,19 @@ int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid,
}
/*
- * Compares the raw arch string. N.B. see instead perf_env__arch() if a
- * normalized arch is needed.
+ * Compares the raw arch string. N.B. see instead perf_env__arch() or
+ * machine__normalized_is() if a normalized arch is needed.
*/
bool machine__is(struct machine *machine, const char *arch)
{
return machine && !strcmp(perf_env__raw_arch(machine->env), arch);
}
+bool machine__normalized_is(struct machine *machine, const char *arch)
+{
+ return machine && !strcmp(perf_env__arch(machine->env), arch);
+}
+
int machine__nr_cpus_avail(struct machine *machine)
{
return machine ? perf_env__nr_cpus_avail(machine->env) : 0;
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index a143087eeb47..c5a45dc8df4c 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -208,6 +208,7 @@ static inline bool machine__is_host(struct machine *machine)
}
bool machine__is(struct machine *machine, const char *arch);
+bool machine__normalized_is(struct machine *machine, const char *arch);
int machine__nr_cpus_avail(struct machine *machine);
struct thread *__machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid);
diff --git a/tools/perf/util/map_symbol.h b/tools/perf/util/map_symbol.h
index 7d22ade082c8..e08817b0c30f 100644
--- a/tools/perf/util/map_symbol.h
+++ b/tools/perf/util/map_symbol.h
@@ -18,6 +18,7 @@ struct addr_map_symbol {
struct map_symbol ms;
u64 addr;
u64 al_addr;
+ char al_level;
u64 phys_addr;
u64 data_page_size;
};
diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
index 3167b4628b6d..ed0ab838bcc5 100644
--- a/tools/perf/util/mem-events.c
+++ b/tools/perf/util/mem-events.c
@@ -309,6 +309,9 @@ static const char * const mem_hops[] = {
* to be set with mem_hops field.
*/
"core, same node",
+ "node, same socket",
+ "socket, same board",
+ "board",
};
int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
@@ -316,7 +319,7 @@ int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
size_t i, l = 0;
u64 m = PERF_MEM_LVL_NA;
u64 hit, miss;
- int printed;
+ int printed = 0;
if (mem_info)
m = mem_info->data_src.mem_lvl;
@@ -335,18 +338,22 @@ int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
l += 7;
}
- if (mem_info && mem_info->data_src.mem_hops)
+ /*
+ * Incase mem_hops field is set, we can skip printing data source via
+ * PERF_MEM_LVL namespace.
+ */
+ if (mem_info && mem_info->data_src.mem_hops) {
l += scnprintf(out + l, sz - l, "%s ", mem_hops[mem_info->data_src.mem_hops]);
-
- printed = 0;
- for (i = 0; m && i < ARRAY_SIZE(mem_lvl); i++, m >>= 1) {
- if (!(m & 0x1))
- continue;
- if (printed++) {
- strcat(out, " or ");
- l += 4;
+ } else {
+ for (i = 0; m && i < ARRAY_SIZE(mem_lvl); i++, m >>= 1) {
+ if (!(m & 0x1))
+ continue;
+ if (printed++) {
+ strcat(out, " or ");
+ l += 4;
+ }
+ l += scnprintf(out + l, sz - l, mem_lvl[i]);
}
- l += scnprintf(out + l, sz - l, mem_lvl[i]);
}
if (mem_info && mem_info->data_src.mem_lvl_num) {
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index fffe02aae3ed..d8492e339521 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -209,8 +209,8 @@ static struct metric *metric__new(const struct pmu_event *pe,
m->metric_name = pe->metric_name;
m->modifier = modifier ? strdup(modifier) : NULL;
if (modifier && !m->modifier) {
- free(m);
expr__ctx_free(m->pctx);
+ free(m);
return NULL;
}
m->metric_expr = pe->metric_expr;
@@ -314,7 +314,7 @@ static int setup_metric_events(struct hashmap *ids,
*/
metric_id = evsel__metric_id(ev);
evlist__for_each_entry_continue(metric_evlist, ev) {
- if (!strcmp(evsel__metric_id(metric_events[i]), metric_id))
+ if (!strcmp(evsel__metric_id(ev), metric_id))
ev->metric_leader = metric_events[i];
}
}
@@ -1115,13 +1115,27 @@ out:
return ret;
}
+/**
+ * metric_list_cmp - list_sort comparator that sorts metrics with more events to
+ * the front. duration_time is excluded from the count.
+ */
static int metric_list_cmp(void *priv __maybe_unused, const struct list_head *l,
const struct list_head *r)
{
const struct metric *left = container_of(l, struct metric, nd);
const struct metric *right = container_of(r, struct metric, nd);
+ struct expr_id_data *data;
+ int left_count, right_count;
+
+ left_count = hashmap__size(left->pctx->ids);
+ if (!expr__get_id(left->pctx, "duration_time", &data))
+ left_count--;
+
+ right_count = hashmap__size(right->pctx->ids);
+ if (!expr__get_id(right->pctx, "duration_time", &data))
+ right_count--;
- return hashmap__size(right->pctx->ids) - hashmap__size(left->pctx->ids);
+ return right_count - left_count;
}
/**
@@ -1299,14 +1313,16 @@ err_out:
/**
* parse_ids - Build the event string for the ids and parse them creating an
* evlist. The encoded metric_ids are decoded.
+ * @metric_no_merge: is metric sharing explicitly disabled.
* @fake_pmu: used when testing metrics not supported by the current CPU.
* @ids: the event identifiers parsed from a metric.
* @modifier: any modifiers added to the events.
* @has_constraint: false if events should be placed in a weak group.
* @out_evlist: the created list of events.
*/
-static int parse_ids(struct perf_pmu *fake_pmu, struct expr_parse_ctx *ids,
- const char *modifier, bool has_constraint, struct evlist **out_evlist)
+static int parse_ids(bool metric_no_merge, struct perf_pmu *fake_pmu,
+ struct expr_parse_ctx *ids, const char *modifier,
+ bool has_constraint, struct evlist **out_evlist)
{
struct parse_events_error parse_error;
struct evlist *parsed_evlist;
@@ -1314,12 +1330,19 @@ static int parse_ids(struct perf_pmu *fake_pmu, struct expr_parse_ctx *ids,
int ret;
*out_evlist = NULL;
- if (hashmap__size(ids->ids) == 0) {
+ if (!metric_no_merge || hashmap__size(ids->ids) == 0) {
char *tmp;
/*
- * No ids/events in the expression parsing context. Events may
- * have been removed because of constant evaluation, e.g.:
- * event1 if #smt_on else 0
+ * We may fail to share events between metrics because
+ * duration_time isn't present in one metric. For example, a
+ * ratio of cache misses doesn't need duration_time but the same
+ * events may be used for a misses per second. Events without
+ * sharing implies multiplexing, that is best avoided, so place
+ * duration_time in every group.
+ *
+ * Also, there may be no ids/events in the expression parsing
+ * context because of constant evaluation, e.g.:
+ * event1 if #smt_on else 0
* Add a duration_time event to avoid a parse error on an empty
* string.
*/
@@ -1387,7 +1410,8 @@ static int parse_groups(struct evlist *perf_evlist, const char *str,
ret = build_combined_expr_ctx(&metric_list, &combined);
if (!ret && combined && hashmap__size(combined->ids)) {
- ret = parse_ids(fake_pmu, combined, /*modifier=*/NULL,
+ ret = parse_ids(metric_no_merge, fake_pmu, combined,
+ /*modifier=*/NULL,
/*has_constraint=*/true,
&combined_evlist);
}
@@ -1435,7 +1459,7 @@ static int parse_groups(struct evlist *perf_evlist, const char *str,
}
}
if (!metric_evlist) {
- ret = parse_ids(fake_pmu, m->pctx, m->modifier,
+ ret = parse_ids(metric_no_merge, fake_pmu, m->pctx, m->modifier,
m->has_constraint, &m->evlist);
if (ret)
goto out;
diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index 23ecdba9e670..0e8ff8d1e206 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -94,7 +94,7 @@ static void perf_mmap__aio_free(struct mmap *map, int idx)
}
}
-static int perf_mmap__aio_bind(struct mmap *map, int idx, int cpu, int affinity)
+static int perf_mmap__aio_bind(struct mmap *map, int idx, struct perf_cpu cpu, int affinity)
{
void *data;
size_t mmap_len;
@@ -138,7 +138,7 @@ static void perf_mmap__aio_free(struct mmap *map, int idx)
}
static int perf_mmap__aio_bind(struct mmap *map __maybe_unused, int idx __maybe_unused,
- int cpu __maybe_unused, int affinity __maybe_unused)
+ struct perf_cpu cpu __maybe_unused, int affinity __maybe_unused)
{
return 0;
}
@@ -240,7 +240,8 @@ void mmap__munmap(struct mmap *map)
static void build_node_mask(int node, struct mmap_cpu_mask *mask)
{
- int c, cpu, nr_cpus;
+ int idx, nr_cpus;
+ struct perf_cpu cpu;
const struct perf_cpu_map *cpu_map = NULL;
cpu_map = cpu_map__online();
@@ -248,16 +249,16 @@ static void build_node_mask(int node, struct mmap_cpu_mask *mask)
return;
nr_cpus = perf_cpu_map__nr(cpu_map);
- for (c = 0; c < nr_cpus; c++) {
- cpu = cpu_map->map[c]; /* map c index to online cpu index */
+ for (idx = 0; idx < nr_cpus; idx++) {
+ cpu = perf_cpu_map__cpu(cpu_map, idx); /* map c index to online cpu index */
if (cpu__get_node(cpu) == node)
- set_bit(cpu, mask->bits);
+ set_bit(cpu.cpu, mask->bits);
}
}
static int perf_mmap__setup_affinity_mask(struct mmap *map, struct mmap_params *mp)
{
- map->affinity_mask.nbits = cpu__max_cpu();
+ map->affinity_mask.nbits = cpu__max_cpu().cpu;
map->affinity_mask.bits = bitmap_zalloc(map->affinity_mask.nbits);
if (!map->affinity_mask.bits)
return -1;
@@ -265,12 +266,12 @@ static int perf_mmap__setup_affinity_mask(struct mmap *map, struct mmap_params *
if (mp->affinity == PERF_AFFINITY_NODE && cpu__max_node() > 1)
build_node_mask(cpu__get_node(map->core.cpu), &map->affinity_mask);
else if (mp->affinity == PERF_AFFINITY_CPU)
- set_bit(map->core.cpu, map->affinity_mask.bits);
+ set_bit(map->core.cpu.cpu, map->affinity_mask.bits);
return 0;
}
-int mmap__mmap(struct mmap *map, struct mmap_params *mp, int fd, int cpu)
+int mmap__mmap(struct mmap *map, struct mmap_params *mp, int fd, struct perf_cpu cpu)
{
if (perf_mmap__mmap(&map->core, &mp->core, fd, cpu)) {
pr_debug2("failed to mmap perf event ring buffer, error %d\n",
diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h
index 8e259b9610f8..83f6bd4d4082 100644
--- a/tools/perf/util/mmap.h
+++ b/tools/perf/util/mmap.h
@@ -7,6 +7,7 @@
#include <linux/types.h>
#include <linux/ring_buffer.h>
#include <linux/bitops.h>
+#include <perf/cpumap.h>
#include <stdbool.h>
#include <pthread.h> // for cpu_set_t
#ifdef HAVE_AIO_SUPPORT
@@ -52,7 +53,7 @@ struct mmap_params {
struct auxtrace_mmap_params auxtrace_mp;
};
-int mmap__mmap(struct mmap *map, struct mmap_params *mp, int fd, int cpu);
+int mmap__mmap(struct mmap *map, struct mmap_params *mp, int fd, struct perf_cpu cpu);
void mmap__munmap(struct mmap *map);
union perf_event *perf_mmap__read_forward(struct mmap *map);
diff --git a/tools/perf/util/namespaces.c b/tools/perf/util/namespaces.c
index 608b20c72a5c..48aa3217300b 100644
--- a/tools/perf/util/namespaces.c
+++ b/tools/perf/util/namespaces.c
@@ -60,17 +60,49 @@ void namespaces__free(struct namespaces *namespaces)
free(namespaces);
}
+static int nsinfo__get_nspid(struct nsinfo *nsi, const char *path)
+{
+ FILE *f = NULL;
+ char *statln = NULL;
+ size_t linesz = 0;
+ char *nspid;
+
+ f = fopen(path, "r");
+ if (f == NULL)
+ return -1;
+
+ while (getline(&statln, &linesz, f) != -1) {
+ /* Use tgid if CONFIG_PID_NS is not defined. */
+ if (strstr(statln, "Tgid:") != NULL) {
+ nsi->tgid = (pid_t)strtol(strrchr(statln, '\t'),
+ NULL, 10);
+ nsi->nstgid = nsi->tgid;
+ }
+
+ if (strstr(statln, "NStgid:") != NULL) {
+ nspid = strrchr(statln, '\t');
+ nsi->nstgid = (pid_t)strtol(nspid, NULL, 10);
+ /*
+ * If innermost tgid is not the first, process is in a different
+ * PID namespace.
+ */
+ nsi->in_pidns = (statln + sizeof("NStgid:") - 1) != nspid;
+ break;
+ }
+ }
+
+ fclose(f);
+ free(statln);
+ return 0;
+}
+
int nsinfo__init(struct nsinfo *nsi)
{
char oldns[PATH_MAX];
char spath[PATH_MAX];
char *newns = NULL;
- char *statln = NULL;
- char *nspid;
struct stat old_stat;
struct stat new_stat;
- FILE *f = NULL;
- size_t linesz = 0;
int rv = -1;
if (snprintf(oldns, PATH_MAX, "/proc/self/ns/mnt") >= PATH_MAX)
@@ -100,34 +132,9 @@ int nsinfo__init(struct nsinfo *nsi)
if (snprintf(spath, PATH_MAX, "/proc/%d/status", nsi->pid) >= PATH_MAX)
goto out;
- f = fopen(spath, "r");
- if (f == NULL)
- goto out;
-
- while (getline(&statln, &linesz, f) != -1) {
- /* Use tgid if CONFIG_PID_NS is not defined. */
- if (strstr(statln, "Tgid:") != NULL) {
- nsi->tgid = (pid_t)strtol(strrchr(statln, '\t'),
- NULL, 10);
- nsi->nstgid = nsi->tgid;
- }
-
- if (strstr(statln, "NStgid:") != NULL) {
- nspid = strrchr(statln, '\t');
- nsi->nstgid = (pid_t)strtol(nspid, NULL, 10);
- /* If innermost tgid is not the first, process is in a different
- * PID namespace.
- */
- nsi->in_pidns = (statln + sizeof("NStgid:") - 1) != nspid;
- break;
- }
- }
- rv = 0;
+ rv = nsinfo__get_nspid(nsi, spath);
out:
- if (f != NULL)
- (void) fclose(f);
- free(statln);
free(newns);
return rv;
}
@@ -299,3 +306,12 @@ int nsinfo__stat(const char *filename, struct stat *st, struct nsinfo *nsi)
return ret;
}
+
+bool nsinfo__is_in_root_namespace(void)
+{
+ struct nsinfo nsi;
+
+ memset(&nsi, 0x0, sizeof(nsi));
+ nsinfo__get_nspid(&nsi, "/proc/self/status");
+ return !nsi.in_pidns;
+}
diff --git a/tools/perf/util/namespaces.h b/tools/perf/util/namespaces.h
index ad9775db7b9c..9ceea9643507 100644
--- a/tools/perf/util/namespaces.h
+++ b/tools/perf/util/namespaces.h
@@ -59,6 +59,8 @@ void nsinfo__mountns_exit(struct nscookie *nc);
char *nsinfo__realpath(const char *path, struct nsinfo *nsi);
int nsinfo__stat(const char *filename, struct stat *st, struct nsinfo *nsi);
+bool nsinfo__is_in_root_namespace(void);
+
static inline void __nsinfo__zput(struct nsinfo **nsip)
{
if (nsip) {
diff --git a/tools/perf/util/parse-events-hybrid.c b/tools/perf/util/parse-events-hybrid.c
index 9fc86971027b..284f8eabd3b9 100644
--- a/tools/perf/util/parse-events-hybrid.c
+++ b/tools/perf/util/parse-events-hybrid.c
@@ -63,10 +63,13 @@ static int create_event_hybrid(__u32 config_type, int *idx,
static int pmu_cmp(struct parse_events_state *parse_state,
struct perf_pmu *pmu)
{
- if (!parse_state->hybrid_pmu_name)
- return 0;
+ if (parse_state->evlist && parse_state->evlist->hybrid_pmu_name)
+ return strcmp(parse_state->evlist->hybrid_pmu_name, pmu->name);
+
+ if (parse_state->hybrid_pmu_name)
+ return strcmp(parse_state->hybrid_pmu_name, pmu->name);
- return strcmp(parse_state->hybrid_pmu_name, pmu->name);
+ return 0;
}
static int add_hw_hybrid(struct parse_events_state *parse_state,
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index ba74fdf74af9..24997925ae00 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -1648,6 +1648,7 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
{
struct parse_events_term *term;
struct list_head *list = NULL;
+ struct list_head *orig_head = NULL;
struct perf_pmu *pmu = NULL;
int ok = 0;
char *config;
@@ -1674,7 +1675,6 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
}
list_add_tail(&term->list, head);
-
/* Add it for all PMUs that support the alias */
list = malloc(sizeof(struct list_head));
if (!list)
@@ -1687,16 +1687,27 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
list_for_each_entry(alias, &pmu->aliases, list) {
if (!strcasecmp(alias->name, str)) {
+ parse_events_copy_term_list(head, &orig_head);
if (!parse_events_add_pmu(parse_state, list,
- pmu->name, head,
+ pmu->name, orig_head,
true, true)) {
pr_debug("%s -> %s/%s/\n", str,
pmu->name, alias->str);
ok++;
}
+ parse_events_terms__delete(orig_head);
}
}
}
+
+ if (parse_state->fake_pmu) {
+ if (!parse_events_add_pmu(parse_state, list, str, head,
+ true, true)) {
+ pr_debug("%s -> %s/%s/\n", str, "fake_pmu", str);
+ ok++;
+ }
+ }
+
out_err:
if (ok)
*listp = list;
@@ -1824,6 +1835,11 @@ out:
return ret;
}
+__weak struct evsel *arch_evlist__leader(struct list_head *list)
+{
+ return list_first_entry(list, struct evsel, core.node);
+}
+
void parse_events__set_leader(char *name, struct list_head *list,
struct parse_events_state *parse_state)
{
@@ -1837,9 +1853,10 @@ void parse_events__set_leader(char *name, struct list_head *list,
if (parse_events__set_leader_for_uncore_aliase(name, list, parse_state))
return;
- __perf_evlist__set_leader(list);
- leader = list_entry(list->next, struct evsel, core.node);
+ leader = arch_evlist__leader(list);
+ __perf_evlist__set_leader(list, &leader->core);
leader->group_name = name ? strdup(name) : NULL;
+ list_move(&leader->core.node, list);
}
/* list_event is assumed to point to malloc'ed memory */
@@ -2092,8 +2109,17 @@ static void perf_pmu__parse_init(void)
pmu = NULL;
while ((pmu = perf_pmu__scan(pmu)) != NULL) {
list_for_each_entry(alias, &pmu->aliases, list) {
- if (strchr(alias->name, '-'))
+ char *tmp = strchr(alias->name, '-');
+
+ if (tmp) {
+ char *tmp2 = NULL;
+
+ tmp2 = strchr(tmp + 1, '-');
len++;
+ if (tmp2)
+ len++;
+ }
+
len++;
}
}
@@ -2113,8 +2139,20 @@ static void perf_pmu__parse_init(void)
list_for_each_entry(alias, &pmu->aliases, list) {
struct perf_pmu_event_symbol *p = perf_pmu_events_list + len;
char *tmp = strchr(alias->name, '-');
+ char *tmp2 = NULL;
- if (tmp != NULL) {
+ if (tmp)
+ tmp2 = strchr(tmp + 1, '-');
+ if (tmp2) {
+ SET_SYMBOL(strndup(alias->name, tmp - alias->name),
+ PMU_EVENT_SYMBOL_PREFIX);
+ p++;
+ tmp++;
+ SET_SYMBOL(strndup(tmp, tmp2 - tmp), PMU_EVENT_SYMBOL_SUFFIX);
+ p++;
+ SET_SYMBOL(strdup(++tmp2), PMU_EVENT_SYMBOL_SUFFIX2);
+ len += 3;
+ } else if (tmp) {
SET_SYMBOL(strndup(alias->name, tmp - alias->name),
PMU_EVENT_SYMBOL_PREFIX);
p++;
@@ -2141,23 +2179,38 @@ err:
*/
int perf_pmu__test_parse_init(void)
{
- struct perf_pmu_event_symbol *list;
+ struct perf_pmu_event_symbol *list, *tmp, symbols[] = {
+ {(char *)"read", PMU_EVENT_SYMBOL},
+ {(char *)"event", PMU_EVENT_SYMBOL_PREFIX},
+ {(char *)"two", PMU_EVENT_SYMBOL_SUFFIX},
+ {(char *)"hyphen", PMU_EVENT_SYMBOL_SUFFIX},
+ {(char *)"hyph", PMU_EVENT_SYMBOL_SUFFIX2},
+ };
+ unsigned long i, j;
- list = malloc(sizeof(*list) * 1);
+ tmp = list = malloc(sizeof(*list) * ARRAY_SIZE(symbols));
if (!list)
return -ENOMEM;
- list->type = PMU_EVENT_SYMBOL;
- list->symbol = strdup("read");
-
- if (!list->symbol) {
- free(list);
- return -ENOMEM;
+ for (i = 0; i < ARRAY_SIZE(symbols); i++, tmp++) {
+ tmp->type = symbols[i].type;
+ tmp->symbol = strdup(symbols[i].symbol);
+ if (!tmp->symbol)
+ goto err_free;
}
perf_pmu_events_list = list;
- perf_pmu_events_list_num = 1;
+ perf_pmu_events_list_num = ARRAY_SIZE(symbols);
+
+ qsort(perf_pmu_events_list, ARRAY_SIZE(symbols),
+ sizeof(struct perf_pmu_event_symbol), comp_pmu);
return 0;
+
+err_free:
+ for (j = 0, tmp = list; j < i; j++, tmp++)
+ free(tmp->symbol);
+ free(list);
+ return -ENOMEM;
}
enum perf_pmu_event_symbol_type
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index c7fc93f54577..a38b8b160e80 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -53,6 +53,7 @@ enum perf_pmu_event_symbol_type {
PMU_EVENT_SYMBOL, /* normal style PMU event */
PMU_EVENT_SYMBOL_PREFIX, /* prefix of pre-suf style event */
PMU_EVENT_SYMBOL_SUFFIX, /* suffix of pre-suf style event */
+ PMU_EVENT_SYMBOL_SUFFIX2, /* suffix of pre-suf2 style event */
};
struct perf_pmu_event_symbol {
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 4efe9872c667..5b6e4b5249cf 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -149,6 +149,8 @@ static int pmu_str_check(yyscan_t scanner, struct parse_events_state *parse_stat
return PE_PMU_EVENT_PRE;
case PMU_EVENT_SYMBOL_SUFFIX:
return PE_PMU_EVENT_SUF;
+ case PMU_EVENT_SYMBOL_SUFFIX2:
+ return PE_PMU_EVENT_SUF2;
case PMU_EVENT_SYMBOL:
return parse_state->fake_pmu
? PE_PMU_EVENT_FAKE : PE_KERNEL_PMU_EVENT;
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 174158982fae..be8c51770051 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -69,7 +69,7 @@ static void inc_group_count(struct list_head *list,
%token PE_NAME_CACHE_TYPE PE_NAME_CACHE_OP_RESULT
%token PE_PREFIX_MEM PE_PREFIX_RAW PE_PREFIX_GROUP
%token PE_ERROR
-%token PE_PMU_EVENT_PRE PE_PMU_EVENT_SUF PE_KERNEL_PMU_EVENT PE_PMU_EVENT_FAKE
+%token PE_PMU_EVENT_PRE PE_PMU_EVENT_SUF PE_PMU_EVENT_SUF2 PE_KERNEL_PMU_EVENT PE_PMU_EVENT_FAKE
%token PE_ARRAY_ALL PE_ARRAY_RANGE
%token PE_DRV_CFG_TERM
%type <num> PE_VALUE
@@ -87,7 +87,7 @@ static void inc_group_count(struct list_head *list,
%type <str> PE_MODIFIER_EVENT
%type <str> PE_MODIFIER_BP
%type <str> PE_EVENT_NAME
-%type <str> PE_PMU_EVENT_PRE PE_PMU_EVENT_SUF PE_KERNEL_PMU_EVENT PE_PMU_EVENT_FAKE
+%type <str> PE_PMU_EVENT_PRE PE_PMU_EVENT_SUF PE_PMU_EVENT_SUF2 PE_KERNEL_PMU_EVENT PE_PMU_EVENT_FAKE
%type <str> PE_DRV_CFG_TERM
%type <str> event_pmu_name
%destructor { free ($$); } <str>
@@ -372,6 +372,19 @@ PE_KERNEL_PMU_EVENT opt_pmu_config
$$ = list;
}
|
+PE_PMU_EVENT_PRE '-' PE_PMU_EVENT_SUF '-' PE_PMU_EVENT_SUF2 sep_dc
+{
+ struct list_head *list;
+ char pmu_name[128];
+ snprintf(pmu_name, sizeof(pmu_name), "%s-%s-%s", $1, $3, $5);
+ free($1);
+ free($3);
+ free($5);
+ if (parse_events_multi_pmu_add(_parse_state, pmu_name, NULL, &list) < 0)
+ YYABORT;
+ $$ = list;
+}
+|
PE_PMU_EVENT_PRE '-' PE_PMU_EVENT_SUF sep_dc
{
struct list_head *list;
diff --git a/tools/perf/util/perf_api_probe.c b/tools/perf/util/perf_api_probe.c
index 020411682a3c..c28dd50bd571 100644
--- a/tools/perf/util/perf_api_probe.c
+++ b/tools/perf/util/perf_api_probe.c
@@ -11,7 +11,7 @@
typedef void (*setup_probe_fn_t)(struct evsel *evsel);
-static int perf_do_probe_api(setup_probe_fn_t fn, int cpu, const char *str)
+static int perf_do_probe_api(setup_probe_fn_t fn, struct perf_cpu cpu, const char *str)
{
struct evlist *evlist;
struct evsel *evsel;
@@ -29,7 +29,7 @@ static int perf_do_probe_api(setup_probe_fn_t fn, int cpu, const char *str)
evsel = evlist__first(evlist);
while (1) {
- fd = sys_perf_event_open(&evsel->core.attr, pid, cpu, -1, flags);
+ fd = sys_perf_event_open(&evsel->core.attr, pid, cpu.cpu, -1, flags);
if (fd < 0) {
if (pid == -1 && errno == EACCES) {
pid = 0;
@@ -43,7 +43,7 @@ static int perf_do_probe_api(setup_probe_fn_t fn, int cpu, const char *str)
fn(evsel);
- fd = sys_perf_event_open(&evsel->core.attr, pid, cpu, -1, flags);
+ fd = sys_perf_event_open(&evsel->core.attr, pid, cpu.cpu, -1, flags);
if (fd < 0) {
if (errno == EINVAL)
err = -EINVAL;
@@ -61,12 +61,13 @@ static bool perf_probe_api(setup_probe_fn_t fn)
{
const char *try[] = {"cycles:u", "instructions:u", "cpu-clock:u", NULL};
struct perf_cpu_map *cpus;
- int cpu, ret, i = 0;
+ struct perf_cpu cpu;
+ int ret, i = 0;
cpus = perf_cpu_map__new(NULL);
if (!cpus)
return false;
- cpu = cpus->map[0];
+ cpu = perf_cpu_map__cpu(cpus, 0);
perf_cpu_map__put(cpus);
do {
@@ -136,15 +137,17 @@ bool perf_can_record_cpu_wide(void)
.exclude_kernel = 1,
};
struct perf_cpu_map *cpus;
- int cpu, fd;
+ struct perf_cpu cpu;
+ int fd;
cpus = perf_cpu_map__new(NULL);
if (!cpus)
return false;
- cpu = cpus->map[0];
+
+ cpu = perf_cpu_map__cpu(cpus, 0);
perf_cpu_map__put(cpus);
- fd = sys_perf_event_open(&attr, -1, cpu, -1, 0);
+ fd = sys_perf_event_open(&attr, -1, cpu.cpu, -1, 0);
if (fd < 0)
return false;
close(fd);
diff --git a/tools/perf/util/perf_event_attr_fprintf.c b/tools/perf/util/perf_event_attr_fprintf.c
index 47b7531f51da..98af3fa4ea35 100644
--- a/tools/perf/util/perf_event_attr_fprintf.c
+++ b/tools/perf/util/perf_event_attr_fprintf.c
@@ -52,7 +52,7 @@ 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),
+ bit_name(TYPE_SAVE), bit_name(HW_INDEX),
{ .name = NULL, }
};
#undef bit_name
diff --git a/tools/perf/util/perf_regs.c b/tools/perf/util/perf_regs.c
index 06a7461ba864..a982e40ee5a9 100644
--- a/tools/perf/util/perf_regs.c
+++ b/tools/perf/util/perf_regs.c
@@ -1,5 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
#include <errno.h>
+#include <string.h>
#include "perf_regs.h"
#include "event.h"
@@ -20,6 +21,671 @@ uint64_t __weak arch__user_reg_mask(void)
}
#ifdef HAVE_PERF_REGS_SUPPORT
+
+#define perf_event_arm_regs perf_event_arm64_regs
+#include "../../arch/arm64/include/uapi/asm/perf_regs.h"
+#undef perf_event_arm_regs
+
+#include "../../arch/arm/include/uapi/asm/perf_regs.h"
+#include "../../arch/csky/include/uapi/asm/perf_regs.h"
+#include "../../arch/mips/include/uapi/asm/perf_regs.h"
+#include "../../arch/powerpc/include/uapi/asm/perf_regs.h"
+#include "../../arch/riscv/include/uapi/asm/perf_regs.h"
+#include "../../arch/s390/include/uapi/asm/perf_regs.h"
+#include "../../arch/x86/include/uapi/asm/perf_regs.h"
+
+static const char *__perf_reg_name_arm64(int id)
+{
+ switch (id) {
+ case PERF_REG_ARM64_X0:
+ return "x0";
+ case PERF_REG_ARM64_X1:
+ return "x1";
+ case PERF_REG_ARM64_X2:
+ return "x2";
+ case PERF_REG_ARM64_X3:
+ return "x3";
+ case PERF_REG_ARM64_X4:
+ return "x4";
+ case PERF_REG_ARM64_X5:
+ return "x5";
+ case PERF_REG_ARM64_X6:
+ return "x6";
+ case PERF_REG_ARM64_X7:
+ return "x7";
+ case PERF_REG_ARM64_X8:
+ return "x8";
+ case PERF_REG_ARM64_X9:
+ return "x9";
+ case PERF_REG_ARM64_X10:
+ return "x10";
+ case PERF_REG_ARM64_X11:
+ return "x11";
+ case PERF_REG_ARM64_X12:
+ return "x12";
+ case PERF_REG_ARM64_X13:
+ return "x13";
+ case PERF_REG_ARM64_X14:
+ return "x14";
+ case PERF_REG_ARM64_X15:
+ return "x15";
+ case PERF_REG_ARM64_X16:
+ return "x16";
+ case PERF_REG_ARM64_X17:
+ return "x17";
+ case PERF_REG_ARM64_X18:
+ return "x18";
+ case PERF_REG_ARM64_X19:
+ return "x19";
+ case PERF_REG_ARM64_X20:
+ return "x20";
+ case PERF_REG_ARM64_X21:
+ return "x21";
+ case PERF_REG_ARM64_X22:
+ return "x22";
+ case PERF_REG_ARM64_X23:
+ return "x23";
+ case PERF_REG_ARM64_X24:
+ return "x24";
+ case PERF_REG_ARM64_X25:
+ return "x25";
+ case PERF_REG_ARM64_X26:
+ return "x26";
+ case PERF_REG_ARM64_X27:
+ return "x27";
+ case PERF_REG_ARM64_X28:
+ return "x28";
+ case PERF_REG_ARM64_X29:
+ return "x29";
+ case PERF_REG_ARM64_SP:
+ return "sp";
+ case PERF_REG_ARM64_LR:
+ return "lr";
+ case PERF_REG_ARM64_PC:
+ return "pc";
+ default:
+ return NULL;
+ }
+
+ return NULL;
+}
+
+static const char *__perf_reg_name_arm(int id)
+{
+ switch (id) {
+ case PERF_REG_ARM_R0:
+ return "r0";
+ case PERF_REG_ARM_R1:
+ return "r1";
+ case PERF_REG_ARM_R2:
+ return "r2";
+ case PERF_REG_ARM_R3:
+ return "r3";
+ case PERF_REG_ARM_R4:
+ return "r4";
+ case PERF_REG_ARM_R5:
+ return "r5";
+ case PERF_REG_ARM_R6:
+ return "r6";
+ case PERF_REG_ARM_R7:
+ return "r7";
+ case PERF_REG_ARM_R8:
+ return "r8";
+ case PERF_REG_ARM_R9:
+ return "r9";
+ case PERF_REG_ARM_R10:
+ return "r10";
+ case PERF_REG_ARM_FP:
+ return "fp";
+ case PERF_REG_ARM_IP:
+ return "ip";
+ case PERF_REG_ARM_SP:
+ return "sp";
+ case PERF_REG_ARM_LR:
+ return "lr";
+ case PERF_REG_ARM_PC:
+ return "pc";
+ default:
+ return NULL;
+ }
+
+ return NULL;
+}
+
+static const char *__perf_reg_name_csky(int id)
+{
+ switch (id) {
+ case PERF_REG_CSKY_A0:
+ return "a0";
+ case PERF_REG_CSKY_A1:
+ return "a1";
+ case PERF_REG_CSKY_A2:
+ return "a2";
+ case PERF_REG_CSKY_A3:
+ return "a3";
+ case PERF_REG_CSKY_REGS0:
+ return "regs0";
+ case PERF_REG_CSKY_REGS1:
+ return "regs1";
+ case PERF_REG_CSKY_REGS2:
+ return "regs2";
+ case PERF_REG_CSKY_REGS3:
+ return "regs3";
+ case PERF_REG_CSKY_REGS4:
+ return "regs4";
+ case PERF_REG_CSKY_REGS5:
+ return "regs5";
+ case PERF_REG_CSKY_REGS6:
+ return "regs6";
+ case PERF_REG_CSKY_REGS7:
+ return "regs7";
+ case PERF_REG_CSKY_REGS8:
+ return "regs8";
+ case PERF_REG_CSKY_REGS9:
+ return "regs9";
+ case PERF_REG_CSKY_SP:
+ return "sp";
+ case PERF_REG_CSKY_LR:
+ return "lr";
+ case PERF_REG_CSKY_PC:
+ return "pc";
+#if defined(__CSKYABIV2__)
+ case PERF_REG_CSKY_EXREGS0:
+ return "exregs0";
+ case PERF_REG_CSKY_EXREGS1:
+ return "exregs1";
+ case PERF_REG_CSKY_EXREGS2:
+ return "exregs2";
+ case PERF_REG_CSKY_EXREGS3:
+ return "exregs3";
+ case PERF_REG_CSKY_EXREGS4:
+ return "exregs4";
+ case PERF_REG_CSKY_EXREGS5:
+ return "exregs5";
+ case PERF_REG_CSKY_EXREGS6:
+ return "exregs6";
+ case PERF_REG_CSKY_EXREGS7:
+ return "exregs7";
+ case PERF_REG_CSKY_EXREGS8:
+ return "exregs8";
+ case PERF_REG_CSKY_EXREGS9:
+ return "exregs9";
+ case PERF_REG_CSKY_EXREGS10:
+ return "exregs10";
+ case PERF_REG_CSKY_EXREGS11:
+ return "exregs11";
+ case PERF_REG_CSKY_EXREGS12:
+ return "exregs12";
+ case PERF_REG_CSKY_EXREGS13:
+ return "exregs13";
+ case PERF_REG_CSKY_EXREGS14:
+ return "exregs14";
+ case PERF_REG_CSKY_TLS:
+ return "tls";
+ case PERF_REG_CSKY_HI:
+ return "hi";
+ case PERF_REG_CSKY_LO:
+ return "lo";
+#endif
+ default:
+ return NULL;
+ }
+
+ return NULL;
+}
+
+static const char *__perf_reg_name_mips(int id)
+{
+ switch (id) {
+ case PERF_REG_MIPS_PC:
+ return "PC";
+ case PERF_REG_MIPS_R1:
+ return "$1";
+ case PERF_REG_MIPS_R2:
+ return "$2";
+ case PERF_REG_MIPS_R3:
+ return "$3";
+ case PERF_REG_MIPS_R4:
+ return "$4";
+ case PERF_REG_MIPS_R5:
+ return "$5";
+ case PERF_REG_MIPS_R6:
+ return "$6";
+ case PERF_REG_MIPS_R7:
+ return "$7";
+ case PERF_REG_MIPS_R8:
+ return "$8";
+ case PERF_REG_MIPS_R9:
+ return "$9";
+ case PERF_REG_MIPS_R10:
+ return "$10";
+ case PERF_REG_MIPS_R11:
+ return "$11";
+ case PERF_REG_MIPS_R12:
+ return "$12";
+ case PERF_REG_MIPS_R13:
+ return "$13";
+ case PERF_REG_MIPS_R14:
+ return "$14";
+ case PERF_REG_MIPS_R15:
+ return "$15";
+ case PERF_REG_MIPS_R16:
+ return "$16";
+ case PERF_REG_MIPS_R17:
+ return "$17";
+ case PERF_REG_MIPS_R18:
+ return "$18";
+ case PERF_REG_MIPS_R19:
+ return "$19";
+ case PERF_REG_MIPS_R20:
+ return "$20";
+ case PERF_REG_MIPS_R21:
+ return "$21";
+ case PERF_REG_MIPS_R22:
+ return "$22";
+ case PERF_REG_MIPS_R23:
+ return "$23";
+ case PERF_REG_MIPS_R24:
+ return "$24";
+ case PERF_REG_MIPS_R25:
+ return "$25";
+ case PERF_REG_MIPS_R28:
+ return "$28";
+ case PERF_REG_MIPS_R29:
+ return "$29";
+ case PERF_REG_MIPS_R30:
+ return "$30";
+ case PERF_REG_MIPS_R31:
+ return "$31";
+ default:
+ break;
+ }
+ return NULL;
+}
+
+static const char *__perf_reg_name_powerpc(int id)
+{
+ switch (id) {
+ case PERF_REG_POWERPC_R0:
+ return "r0";
+ case PERF_REG_POWERPC_R1:
+ return "r1";
+ case PERF_REG_POWERPC_R2:
+ return "r2";
+ case PERF_REG_POWERPC_R3:
+ return "r3";
+ case PERF_REG_POWERPC_R4:
+ return "r4";
+ case PERF_REG_POWERPC_R5:
+ return "r5";
+ case PERF_REG_POWERPC_R6:
+ return "r6";
+ case PERF_REG_POWERPC_R7:
+ return "r7";
+ case PERF_REG_POWERPC_R8:
+ return "r8";
+ case PERF_REG_POWERPC_R9:
+ return "r9";
+ case PERF_REG_POWERPC_R10:
+ return "r10";
+ case PERF_REG_POWERPC_R11:
+ return "r11";
+ case PERF_REG_POWERPC_R12:
+ return "r12";
+ case PERF_REG_POWERPC_R13:
+ return "r13";
+ case PERF_REG_POWERPC_R14:
+ return "r14";
+ case PERF_REG_POWERPC_R15:
+ return "r15";
+ case PERF_REG_POWERPC_R16:
+ return "r16";
+ case PERF_REG_POWERPC_R17:
+ return "r17";
+ case PERF_REG_POWERPC_R18:
+ return "r18";
+ case PERF_REG_POWERPC_R19:
+ return "r19";
+ case PERF_REG_POWERPC_R20:
+ return "r20";
+ case PERF_REG_POWERPC_R21:
+ return "r21";
+ case PERF_REG_POWERPC_R22:
+ return "r22";
+ case PERF_REG_POWERPC_R23:
+ return "r23";
+ case PERF_REG_POWERPC_R24:
+ return "r24";
+ case PERF_REG_POWERPC_R25:
+ return "r25";
+ case PERF_REG_POWERPC_R26:
+ return "r26";
+ case PERF_REG_POWERPC_R27:
+ return "r27";
+ case PERF_REG_POWERPC_R28:
+ return "r28";
+ case PERF_REG_POWERPC_R29:
+ return "r29";
+ case PERF_REG_POWERPC_R30:
+ return "r30";
+ case PERF_REG_POWERPC_R31:
+ return "r31";
+ case PERF_REG_POWERPC_NIP:
+ return "nip";
+ case PERF_REG_POWERPC_MSR:
+ return "msr";
+ case PERF_REG_POWERPC_ORIG_R3:
+ return "orig_r3";
+ case PERF_REG_POWERPC_CTR:
+ return "ctr";
+ case PERF_REG_POWERPC_LINK:
+ return "link";
+ case PERF_REG_POWERPC_XER:
+ return "xer";
+ case PERF_REG_POWERPC_CCR:
+ return "ccr";
+ case PERF_REG_POWERPC_SOFTE:
+ return "softe";
+ case PERF_REG_POWERPC_TRAP:
+ return "trap";
+ case PERF_REG_POWERPC_DAR:
+ return "dar";
+ case PERF_REG_POWERPC_DSISR:
+ return "dsisr";
+ case PERF_REG_POWERPC_SIER:
+ return "sier";
+ case PERF_REG_POWERPC_MMCRA:
+ return "mmcra";
+ case PERF_REG_POWERPC_MMCR0:
+ return "mmcr0";
+ case PERF_REG_POWERPC_MMCR1:
+ return "mmcr1";
+ case PERF_REG_POWERPC_MMCR2:
+ return "mmcr2";
+ case PERF_REG_POWERPC_MMCR3:
+ return "mmcr3";
+ case PERF_REG_POWERPC_SIER2:
+ return "sier2";
+ case PERF_REG_POWERPC_SIER3:
+ return "sier3";
+ case PERF_REG_POWERPC_PMC1:
+ return "pmc1";
+ case PERF_REG_POWERPC_PMC2:
+ return "pmc2";
+ case PERF_REG_POWERPC_PMC3:
+ return "pmc3";
+ case PERF_REG_POWERPC_PMC4:
+ return "pmc4";
+ case PERF_REG_POWERPC_PMC5:
+ return "pmc5";
+ case PERF_REG_POWERPC_PMC6:
+ return "pmc6";
+ case PERF_REG_POWERPC_SDAR:
+ return "sdar";
+ case PERF_REG_POWERPC_SIAR:
+ return "siar";
+ default:
+ break;
+ }
+ return NULL;
+}
+
+static const char *__perf_reg_name_riscv(int id)
+{
+ switch (id) {
+ case PERF_REG_RISCV_PC:
+ return "pc";
+ case PERF_REG_RISCV_RA:
+ return "ra";
+ case PERF_REG_RISCV_SP:
+ return "sp";
+ case PERF_REG_RISCV_GP:
+ return "gp";
+ case PERF_REG_RISCV_TP:
+ return "tp";
+ case PERF_REG_RISCV_T0:
+ return "t0";
+ case PERF_REG_RISCV_T1:
+ return "t1";
+ case PERF_REG_RISCV_T2:
+ return "t2";
+ case PERF_REG_RISCV_S0:
+ return "s0";
+ case PERF_REG_RISCV_S1:
+ return "s1";
+ case PERF_REG_RISCV_A0:
+ return "a0";
+ case PERF_REG_RISCV_A1:
+ return "a1";
+ case PERF_REG_RISCV_A2:
+ return "a2";
+ case PERF_REG_RISCV_A3:
+ return "a3";
+ case PERF_REG_RISCV_A4:
+ return "a4";
+ case PERF_REG_RISCV_A5:
+ return "a5";
+ case PERF_REG_RISCV_A6:
+ return "a6";
+ case PERF_REG_RISCV_A7:
+ return "a7";
+ case PERF_REG_RISCV_S2:
+ return "s2";
+ case PERF_REG_RISCV_S3:
+ return "s3";
+ case PERF_REG_RISCV_S4:
+ return "s4";
+ case PERF_REG_RISCV_S5:
+ return "s5";
+ case PERF_REG_RISCV_S6:
+ return "s6";
+ case PERF_REG_RISCV_S7:
+ return "s7";
+ case PERF_REG_RISCV_S8:
+ return "s8";
+ case PERF_REG_RISCV_S9:
+ return "s9";
+ case PERF_REG_RISCV_S10:
+ return "s10";
+ case PERF_REG_RISCV_S11:
+ return "s11";
+ case PERF_REG_RISCV_T3:
+ return "t3";
+ case PERF_REG_RISCV_T4:
+ return "t4";
+ case PERF_REG_RISCV_T5:
+ return "t5";
+ case PERF_REG_RISCV_T6:
+ return "t6";
+ default:
+ return NULL;
+ }
+
+ return NULL;
+}
+
+static const char *__perf_reg_name_s390(int id)
+{
+ switch (id) {
+ case PERF_REG_S390_R0:
+ return "R0";
+ case PERF_REG_S390_R1:
+ return "R1";
+ case PERF_REG_S390_R2:
+ return "R2";
+ case PERF_REG_S390_R3:
+ return "R3";
+ case PERF_REG_S390_R4:
+ return "R4";
+ case PERF_REG_S390_R5:
+ return "R5";
+ case PERF_REG_S390_R6:
+ return "R6";
+ case PERF_REG_S390_R7:
+ return "R7";
+ case PERF_REG_S390_R8:
+ return "R8";
+ case PERF_REG_S390_R9:
+ return "R9";
+ case PERF_REG_S390_R10:
+ return "R10";
+ case PERF_REG_S390_R11:
+ return "R11";
+ case PERF_REG_S390_R12:
+ return "R12";
+ case PERF_REG_S390_R13:
+ return "R13";
+ case PERF_REG_S390_R14:
+ return "R14";
+ case PERF_REG_S390_R15:
+ return "R15";
+ case PERF_REG_S390_FP0:
+ return "FP0";
+ case PERF_REG_S390_FP1:
+ return "FP1";
+ case PERF_REG_S390_FP2:
+ return "FP2";
+ case PERF_REG_S390_FP3:
+ return "FP3";
+ case PERF_REG_S390_FP4:
+ return "FP4";
+ case PERF_REG_S390_FP5:
+ return "FP5";
+ case PERF_REG_S390_FP6:
+ return "FP6";
+ case PERF_REG_S390_FP7:
+ return "FP7";
+ case PERF_REG_S390_FP8:
+ return "FP8";
+ case PERF_REG_S390_FP9:
+ return "FP9";
+ case PERF_REG_S390_FP10:
+ return "FP10";
+ case PERF_REG_S390_FP11:
+ return "FP11";
+ case PERF_REG_S390_FP12:
+ return "FP12";
+ case PERF_REG_S390_FP13:
+ return "FP13";
+ case PERF_REG_S390_FP14:
+ return "FP14";
+ case PERF_REG_S390_FP15:
+ return "FP15";
+ case PERF_REG_S390_MASK:
+ return "MASK";
+ case PERF_REG_S390_PC:
+ return "PC";
+ default:
+ return NULL;
+ }
+
+ return NULL;
+}
+
+static const char *__perf_reg_name_x86(int id)
+{
+ switch (id) {
+ case PERF_REG_X86_AX:
+ return "AX";
+ case PERF_REG_X86_BX:
+ return "BX";
+ case PERF_REG_X86_CX:
+ return "CX";
+ case PERF_REG_X86_DX:
+ return "DX";
+ case PERF_REG_X86_SI:
+ return "SI";
+ case PERF_REG_X86_DI:
+ return "DI";
+ case PERF_REG_X86_BP:
+ return "BP";
+ case PERF_REG_X86_SP:
+ return "SP";
+ case PERF_REG_X86_IP:
+ return "IP";
+ case PERF_REG_X86_FLAGS:
+ return "FLAGS";
+ case PERF_REG_X86_CS:
+ return "CS";
+ case PERF_REG_X86_SS:
+ return "SS";
+ case PERF_REG_X86_DS:
+ return "DS";
+ case PERF_REG_X86_ES:
+ return "ES";
+ case PERF_REG_X86_FS:
+ return "FS";
+ case PERF_REG_X86_GS:
+ return "GS";
+ case PERF_REG_X86_R8:
+ return "R8";
+ case PERF_REG_X86_R9:
+ return "R9";
+ case PERF_REG_X86_R10:
+ return "R10";
+ case PERF_REG_X86_R11:
+ return "R11";
+ case PERF_REG_X86_R12:
+ return "R12";
+ case PERF_REG_X86_R13:
+ return "R13";
+ case PERF_REG_X86_R14:
+ return "R14";
+ case PERF_REG_X86_R15:
+ return "R15";
+
+#define XMM(x) \
+ case PERF_REG_X86_XMM ## x: \
+ case PERF_REG_X86_XMM ## x + 1: \
+ return "XMM" #x;
+ XMM(0)
+ XMM(1)
+ XMM(2)
+ XMM(3)
+ XMM(4)
+ XMM(5)
+ XMM(6)
+ XMM(7)
+ XMM(8)
+ XMM(9)
+ XMM(10)
+ XMM(11)
+ XMM(12)
+ XMM(13)
+ XMM(14)
+ XMM(15)
+#undef XMM
+ default:
+ return NULL;
+ }
+
+ return NULL;
+}
+
+const char *perf_reg_name(int id, const char *arch)
+{
+ const char *reg_name = NULL;
+
+ if (!strcmp(arch, "csky"))
+ reg_name = __perf_reg_name_csky(id);
+ else if (!strcmp(arch, "mips"))
+ reg_name = __perf_reg_name_mips(id);
+ else if (!strcmp(arch, "powerpc"))
+ reg_name = __perf_reg_name_powerpc(id);
+ else if (!strcmp(arch, "riscv"))
+ reg_name = __perf_reg_name_riscv(id);
+ else if (!strcmp(arch, "s390"))
+ reg_name = __perf_reg_name_s390(id);
+ else if (!strcmp(arch, "x86"))
+ reg_name = __perf_reg_name_x86(id);
+ else if (!strcmp(arch, "arm"))
+ reg_name = __perf_reg_name_arm(id);
+ else if (!strcmp(arch, "arm64"))
+ reg_name = __perf_reg_name_arm64(id);
+
+ return reg_name ?: "unknown";
+}
+
int perf_reg_value(u64 *valp, struct regs_dump *regs, int id)
{
int i, idx = 0;
diff --git a/tools/perf/util/perf_regs.h b/tools/perf/util/perf_regs.h
index eeac181ebccf..ce1127af05e4 100644
--- a/tools/perf/util/perf_regs.h
+++ b/tools/perf/util/perf_regs.h
@@ -11,8 +11,11 @@ struct sample_reg {
const char *name;
uint64_t mask;
};
-#define SMPL_REG(n, b) { .name = #n, .mask = 1ULL << (b) }
-#define SMPL_REG2(n, b) { .name = #n, .mask = 3ULL << (b) }
+
+#define SMPL_REG_MASK(b) (1ULL << (b))
+#define SMPL_REG(n, b) { .name = #n, .mask = SMPL_REG_MASK(b) }
+#define SMPL_REG2_MASK(b) (3ULL << (b))
+#define SMPL_REG2(n, b) { .name = #n, .mask = SMPL_REG2_MASK(b) }
#define SMPL_REG_END { .name = NULL }
enum {
@@ -31,22 +34,16 @@ extern const struct sample_reg sample_reg_masks[];
#define DWARF_MINIMAL_REGS ((1ULL << PERF_REG_IP) | (1ULL << PERF_REG_SP))
+const char *perf_reg_name(int id, const char *arch);
int perf_reg_value(u64 *valp, struct regs_dump *regs, int id);
-static inline const char *perf_reg_name(int id)
-{
- const char *reg_name = __perf_reg_name(id);
-
- return reg_name ?: "unknown";
-}
-
#else
#define PERF_REGS_MASK 0
#define PERF_REGS_MAX 0
#define DWARF_MINIMAL_REGS PERF_REGS_MASK
-static inline const char *perf_reg_name(int id __maybe_unused)
+static inline const char *perf_reg_name(int id __maybe_unused, const char *arch __maybe_unused)
{
return "unknown";
}
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index b2a02c9ab8ea..a834918a0a0d 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -3083,6 +3083,9 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev,
for (j = 0; j < num_matched_functions; j++) {
sym = syms[j];
+ if (sym->type != STT_FUNC)
+ continue;
+
/* There can be duplicated symbols in the map */
for (i = 0; i < j; i++)
if (sym->start == syms[i]->start) {
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 7f782a31bda3..52d8995cfd73 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -428,6 +428,8 @@ tracepoint_field(struct pyrf_event *pe, struct tep_format_field *field)
offset = val;
len = offset >> 16;
offset &= 0xffff;
+ if (field->flags & TEP_FIELD_IS_RELATIVE)
+ offset += field->offset + field->size;
}
if (field->flags & TEP_FIELD_IS_STRING &&
is_printable_array(data + offset, len)) {
@@ -636,17 +638,17 @@ static Py_ssize_t pyrf_cpu_map__length(PyObject *obj)
{
struct pyrf_cpu_map *pcpus = (void *)obj;
- return pcpus->cpus->nr;
+ return perf_cpu_map__nr(pcpus->cpus);
}
static PyObject *pyrf_cpu_map__item(PyObject *obj, Py_ssize_t i)
{
struct pyrf_cpu_map *pcpus = (void *)obj;
- if (i >= pcpus->cpus->nr)
+ if (i >= perf_cpu_map__nr(pcpus->cpus))
return NULL;
- return Py_BuildValue("i", pcpus->cpus->map[i]);
+ return Py_BuildValue("i", perf_cpu_map__cpu(pcpus->cpus, i).cpu);
}
static PySequenceMethods pyrf_cpu_map__sequence_methods = {
@@ -1057,7 +1059,7 @@ static struct mmap *get_md(struct evlist *evlist, int cpu)
for (i = 0; i < evlist->core.nr_mmaps; i++) {
struct mmap *md = &evlist->mmap[i];
- if (md->core.cpu == cpu)
+ if (md->core.cpu.cpu == cpu)
return md;
}
@@ -1443,7 +1445,7 @@ error:
* Dummy, to avoid dragging all the test_attr infrastructure in the python
* binding.
*/
-void test_attr__open(struct perf_event_attr *attr, pid_t pid, int cpu,
+void test_attr__open(struct perf_event_attr *attr, pid_t pid, struct perf_cpu cpu,
int fd, int group_fd, unsigned long flags)
{
}
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index bff669b615ee..007a64681416 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -106,7 +106,7 @@ void evlist__config(struct evlist *evlist, struct record_opts *opts, struct call
if (opts->group)
evlist__set_leader(evlist);
- if (evlist->core.cpus->map[0] < 0)
+ if (perf_cpu_map__cpu(evlist->core.cpus, 0).cpu < 0)
opts->no_inherit = true;
use_comm_exec = perf_can_comm_exec();
@@ -229,7 +229,8 @@ bool evlist__can_select_event(struct evlist *evlist, const char *str)
{
struct evlist *temp_evlist;
struct evsel *evsel;
- int err, fd, cpu;
+ int err, fd;
+ struct perf_cpu cpu = { .cpu = 0 };
bool ret = false;
pid_t pid = -1;
@@ -246,14 +247,16 @@ bool evlist__can_select_event(struct evlist *evlist, const char *str)
if (!evlist || perf_cpu_map__empty(evlist->core.cpus)) {
struct perf_cpu_map *cpus = perf_cpu_map__new(NULL);
- cpu = cpus ? cpus->map[0] : 0;
+ if (cpus)
+ cpu = perf_cpu_map__cpu(cpus, 0);
+
perf_cpu_map__put(cpus);
} else {
- cpu = evlist->core.cpus->map[0];
+ cpu = perf_cpu_map__cpu(evlist->core.cpus, 0);
}
while (1) {
- fd = sys_perf_event_open(&evsel->core.attr, pid, cpu, -1,
+ fd = sys_perf_event_open(&evsel->core.attr, pid, cpu.cpu, -1,
perf_event_open_cloexec_flag());
if (fd < 0) {
if (pid == -1 && errno == EACCES) {
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index 32a721b3e9a5..a5d945415bbc 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -392,6 +392,8 @@ static void perl_process_tracepoint(struct perf_sample *sample,
if (field->flags & TEP_FIELD_IS_DYNAMIC) {
offset = *(int *)(data + field->offset);
offset &= 0xffff;
+ if (field->flags & TEP_FIELD_IS_RELATIVE)
+ offset += field->offset + field->size;
} else
offset = field->offset;
XPUSHs(sv_2mortal(newSVpv((char *)data + offset, 0)));
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index c0c010350bc2..e752e1f4a5f0 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -36,6 +36,7 @@
#include "../debug.h"
#include "../dso.h"
#include "../callchain.h"
+#include "../env.h"
#include "../evsel.h"
#include "../event.h"
#include "../thread.h"
@@ -687,7 +688,7 @@ static void set_sample_datasrc_in_dict(PyObject *dict,
_PyUnicode_FromString(decode));
}
-static void regs_map(struct regs_dump *regs, uint64_t mask, char *bf, int size)
+static void regs_map(struct regs_dump *regs, uint64_t mask, const char *arch, char *bf, int size)
{
unsigned int i = 0, r;
int printed = 0;
@@ -702,7 +703,7 @@ static void regs_map(struct regs_dump *regs, uint64_t mask, char *bf, int size)
printed += scnprintf(bf + printed, size - printed,
"%5s:0x%" PRIx64 " ",
- perf_reg_name(r), val);
+ perf_reg_name(r, arch), val);
}
}
@@ -711,6 +712,7 @@ static void set_regs_in_dict(PyObject *dict,
struct evsel *evsel)
{
struct perf_event_attr *attr = &evsel->core.attr;
+ const char *arch = perf_env__arch(evsel__env(evsel));
/*
* Here value 28 is a constant size which can be used to print
@@ -722,12 +724,12 @@ static void set_regs_in_dict(PyObject *dict,
int size = __sw_hweight64(attr->sample_regs_intr) * 28;
char bf[size];
- regs_map(&sample->intr_regs, attr->sample_regs_intr, bf, sizeof(bf));
+ regs_map(&sample->intr_regs, attr->sample_regs_intr, arch, bf, sizeof(bf));
pydict_set_item_string_decref(dict, "iregs",
_PyUnicode_FromString(bf));
- regs_map(&sample->user_regs, attr->sample_regs_user, bf, sizeof(bf));
+ regs_map(&sample->user_regs, attr->sample_regs_user, arch, bf, sizeof(bf));
pydict_set_item_string_decref(dict, "uregs",
_PyUnicode_FromString(bf));
@@ -942,6 +944,8 @@ static void python_process_tracepoint(struct perf_sample *sample,
offset = val;
len = offset >> 16;
offset &= 0xffff;
+ if (field->flags & TEP_FIELD_IS_RELATIVE)
+ offset += field->offset + field->size;
}
if (field->flags & TEP_FIELD_IS_STRING &&
is_printable_array(data + offset, len)) {
@@ -1553,7 +1557,7 @@ static void get_handler_name(char *str, size_t size,
}
static void
-process_stat(struct evsel *counter, int cpu, int thread, u64 tstamp,
+process_stat(struct evsel *counter, struct perf_cpu cpu, int thread, u64 tstamp,
struct perf_counts_values *count)
{
PyObject *handler, *t;
@@ -1573,7 +1577,7 @@ process_stat(struct evsel *counter, int cpu, int thread, u64 tstamp,
return;
}
- PyTuple_SetItem(t, n++, _PyLong_FromLong(cpu));
+ PyTuple_SetItem(t, n++, _PyLong_FromLong(cpu.cpu));
PyTuple_SetItem(t, n++, _PyLong_FromLong(thread));
tuple_set_u64(t, n++, tstamp);
@@ -1597,14 +1601,14 @@ static void python_process_stat(struct perf_stat_config *config,
int cpu, thread;
if (config->aggr_mode == AGGR_GLOBAL) {
- process_stat(counter, -1, -1, tstamp,
+ process_stat(counter, (struct perf_cpu){ .cpu = -1 }, -1, tstamp,
&counter->counts->aggr);
return;
}
for (thread = 0; thread < threads->nr; thread++) {
- for (cpu = 0; cpu < cpus->nr; cpu++) {
- process_stat(counter, cpus->map[cpu],
+ for (cpu = 0; cpu < perf_cpu_map__nr(cpus); cpu++) {
+ process_stat(counter, perf_cpu_map__cpu(cpus, cpu),
perf_thread_map__pid(threads, thread), tstamp,
perf_counts(counter->counts, cpu, thread));
}
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index d8857d1b6d7c..498b05708db5 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -15,6 +15,7 @@
#include "map_symbol.h"
#include "branch.h"
#include "debug.h"
+#include "env.h"
#include "evlist.h"
#include "evsel.h"
#include "memswap.h"
@@ -1168,7 +1169,7 @@ static void branch_stack__printf(struct perf_sample *sample, bool callstack)
}
}
-static void regs_dump__printf(u64 mask, u64 *regs)
+static void regs_dump__printf(u64 mask, u64 *regs, const char *arch)
{
unsigned rid, i = 0;
@@ -1176,7 +1177,7 @@ static void regs_dump__printf(u64 mask, u64 *regs)
u64 val = regs[i++];
printf(".... %-5s 0x%016" PRIx64 "\n",
- perf_reg_name(rid), val);
+ perf_reg_name(rid, arch), val);
}
}
@@ -1194,7 +1195,7 @@ static inline const char *regs_dump_abi(struct regs_dump *d)
return regs_abi[d->abi];
}
-static void regs__printf(const char *type, struct regs_dump *regs)
+static void regs__printf(const char *type, struct regs_dump *regs, const char *arch)
{
u64 mask = regs->mask;
@@ -1203,23 +1204,23 @@ static void regs__printf(const char *type, struct regs_dump *regs)
mask,
regs_dump_abi(regs));
- regs_dump__printf(mask, regs->regs);
+ regs_dump__printf(mask, regs->regs, arch);
}
-static void regs_user__printf(struct perf_sample *sample)
+static void regs_user__printf(struct perf_sample *sample, const char *arch)
{
struct regs_dump *user_regs = &sample->user_regs;
if (user_regs->regs)
- regs__printf("user", user_regs);
+ regs__printf("user", user_regs, arch);
}
-static void regs_intr__printf(struct perf_sample *sample)
+static void regs_intr__printf(struct perf_sample *sample, const char *arch)
{
struct regs_dump *intr_regs = &sample->intr_regs;
if (intr_regs->regs)
- regs__printf("intr", intr_regs);
+ regs__printf("intr", intr_regs, arch);
}
static void stack_user__printf(struct stack_dump *dump)
@@ -1304,7 +1305,7 @@ char *get_page_size_name(u64 size, char *str)
}
static void dump_sample(struct evsel *evsel, union perf_event *event,
- struct perf_sample *sample)
+ struct perf_sample *sample, const char *arch)
{
u64 sample_type;
char str[PAGE_SIZE_NAME_LEN];
@@ -1325,10 +1326,10 @@ static void dump_sample(struct evsel *evsel, union perf_event *event,
branch_stack__printf(sample, evsel__has_branch_callstack(evsel));
if (sample_type & PERF_SAMPLE_REGS_USER)
- regs_user__printf(sample);
+ regs_user__printf(sample, arch);
if (sample_type & PERF_SAMPLE_REGS_INTR)
- regs_intr__printf(sample);
+ regs_intr__printf(sample, arch);
if (sample_type & PERF_SAMPLE_STACK_USER)
stack_user__printf(&sample->user_stack);
@@ -1502,11 +1503,12 @@ static int machines__deliver_event(struct machines *machines,
++evlist->stats.nr_unknown_id;
return 0;
}
- dump_sample(evsel, event, sample);
if (machine == NULL) {
++evlist->stats.nr_unprocessable_samples;
+ dump_sample(evsel, event, sample, perf_env__arch(NULL));
return 0;
}
+ dump_sample(evsel, event, sample, perf_env__arch(machine->env));
return evlist__deliver_sample(evlist, tool, event, sample, evsel, machine);
case PERF_RECORD_MMAP:
return tool->mmap(tool, event, sample, machine);
@@ -2536,16 +2538,16 @@ int perf_session__cpu_bitmap(struct perf_session *session,
return -1;
}
- for (i = 0; i < map->nr; i++) {
- int cpu = map->map[i];
+ for (i = 0; i < perf_cpu_map__nr(map); i++) {
+ struct perf_cpu cpu = perf_cpu_map__cpu(map, i);
- if (cpu >= nr_cpus) {
+ if (cpu.cpu >= nr_cpus) {
pr_err("Requested CPU %d too large. "
- "Consider raising MAX_NR_CPUS\n", cpu);
+ "Consider raising MAX_NR_CPUS\n", cpu.cpu);
goto out_delete_map;
}
- set_bit(cpu, cpu_bitmap);
+ set_bit(cpu.cpu, cpu_bitmap);
}
err = 0;
@@ -2597,7 +2599,7 @@ int perf_event__process_id_index(struct perf_session *session,
if (!sid)
return -ENOENT;
sid->idx = e->idx;
- sid->cpu = e->cpu;
+ sid->cpu.cpu = e->cpu;
sid->tid = e->tid;
}
return 0;
diff --git a/tools/perf/util/smt.c b/tools/perf/util/smt.c
index 34f1b1b1176c..2b0a36ebf27a 100644
--- a/tools/perf/util/smt.c
+++ b/tools/perf/util/smt.c
@@ -5,6 +5,56 @@
#include "api/fs/fs.h"
#include "smt.h"
+/**
+ * hweight_str - Returns the number of bits set in str. Stops at first non-hex
+ * or ',' character.
+ */
+static int hweight_str(char *str)
+{
+ int result = 0;
+
+ while (*str) {
+ switch (*str++) {
+ case '0':
+ case ',':
+ break;
+ case '1':
+ case '2':
+ case '4':
+ case '8':
+ result++;
+ break;
+ case '3':
+ case '5':
+ case '6':
+ case '9':
+ case 'a':
+ case 'A':
+ case 'c':
+ case 'C':
+ result += 2;
+ break;
+ case '7':
+ case 'b':
+ case 'B':
+ case 'd':
+ case 'D':
+ case 'e':
+ case 'E':
+ result += 3;
+ break;
+ case 'f':
+ case 'F':
+ result += 4;
+ break;
+ default:
+ goto done;
+ }
+ }
+done:
+ return result;
+}
+
int smt_on(void)
{
static bool cached;
@@ -15,9 +65,12 @@ int smt_on(void)
if (cached)
return cached_result;
- if (sysfs__read_int("devices/system/cpu/smt/active", &cached_result) >= 0)
- goto done;
+ if (sysfs__read_int("devices/system/cpu/smt/active", &cached_result) >= 0) {
+ cached = true;
+ return cached_result;
+ }
+ cached_result = 0;
ncpu = sysconf(_SC_NPROCESSORS_CONF);
for (cpu = 0; cpu < ncpu; cpu++) {
unsigned long long siblings;
@@ -26,27 +79,21 @@ int smt_on(void)
char fn[256];
snprintf(fn, sizeof fn,
- "devices/system/cpu/cpu%d/topology/core_cpus", cpu);
+ "devices/system/cpu/cpu%d/topology/thread_siblings", cpu);
if (sysfs__read_str(fn, &str, &strlen) < 0) {
snprintf(fn, sizeof fn,
- "devices/system/cpu/cpu%d/topology/thread_siblings",
- cpu);
+ "devices/system/cpu/cpu%d/topology/core_cpus", cpu);
if (sysfs__read_str(fn, &str, &strlen) < 0)
continue;
}
/* Entry is hex, but does not have 0x, so need custom parser */
- siblings = strtoull(str, NULL, 16);
+ siblings = hweight_str(str);
free(str);
- if (hweight64(siblings) > 1) {
+ if (siblings > 1) {
cached_result = 1;
- cached = true;
break;
}
}
- if (!cached) {
- cached_result = 0;
-done:
- cached = true;
- }
+ cached = true;
return cached_result;
}
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index a111065b484e..2da081ef532b 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -37,7 +37,7 @@ const char default_parent_pattern[] = "^sys_|^do_page_fault";
const char *parent_pattern = default_parent_pattern;
const char *default_sort_order = "comm,dso,symbol";
const char default_branch_sort_order[] = "comm,dso_from,symbol_from,symbol_to,cycles";
-const char default_mem_sort_order[] = "local_weight,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked,blocked,local_ins_lat,p_stage_cyc";
+const char default_mem_sort_order[] = "local_weight,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked,blocked,local_ins_lat,local_p_stage_cyc";
const char default_top_sort_order[] = "dso,symbol";
const char default_diff_sort_order[] = "dso,symbol";
const char default_tracepoint_sort_order[] = "trace";
@@ -46,8 +46,8 @@ const char *field_order;
regex_t ignore_callees_regex;
int have_ignore_callees = 0;
enum sort_mode sort__mode = SORT_MODE__NORMAL;
-const char *dynamic_headers[] = {"local_ins_lat", "p_stage_cyc"};
-const char *arch_specific_sort_keys[] = {"p_stage_cyc"};
+static const char *const dynamic_headers[] = {"local_ins_lat", "ins_lat", "local_p_stage_cyc", "p_stage_cyc"};
+static const char *const arch_specific_sort_keys[] = {"local_p_stage_cyc", "p_stage_cyc"};
/*
* Replaces all occurrences of a char used with the:
@@ -915,7 +915,7 @@ static int hist_entry__sym_from_snprintf(struct hist_entry *he, char *bf,
struct addr_map_symbol *from = &he->branch_info->from;
return _hist_entry__sym_snprintf(&from->ms, from->al_addr,
- he->level, bf, size, width);
+ from->al_level, bf, size, width);
}
return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A");
@@ -928,7 +928,7 @@ static int hist_entry__sym_to_snprintf(struct hist_entry *he, char *bf,
struct addr_map_symbol *to = &he->branch_info->to;
return _hist_entry__sym_snprintf(&to->ms, to->al_addr,
- he->level, bf, size, width);
+ to->al_level, bf, size, width);
}
return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A");
@@ -1392,22 +1392,37 @@ struct sort_entry sort_global_ins_lat = {
};
static int64_t
-sort__global_p_stage_cyc_cmp(struct hist_entry *left, struct hist_entry *right)
+sort__p_stage_cyc_cmp(struct hist_entry *left, struct hist_entry *right)
{
return left->p_stage_cyc - right->p_stage_cyc;
}
+static int hist_entry__global_p_stage_cyc_snprintf(struct hist_entry *he, char *bf,
+ size_t size, unsigned int width)
+{
+ return repsep_snprintf(bf, size, "%-*u", width,
+ he->p_stage_cyc * he->stat.nr_events);
+}
+
+
static int hist_entry__p_stage_cyc_snprintf(struct hist_entry *he, char *bf,
size_t size, unsigned int width)
{
return repsep_snprintf(bf, size, "%-*u", width, he->p_stage_cyc);
}
-struct sort_entry sort_p_stage_cyc = {
- .se_header = "Pipeline Stage Cycle",
- .se_cmp = sort__global_p_stage_cyc_cmp,
+struct sort_entry sort_local_p_stage_cyc = {
+ .se_header = "Local Pipeline Stage Cycle",
+ .se_cmp = sort__p_stage_cyc_cmp,
.se_snprintf = hist_entry__p_stage_cyc_snprintf,
- .se_width_idx = HISTC_P_STAGE_CYC,
+ .se_width_idx = HISTC_LOCAL_P_STAGE_CYC,
+};
+
+struct sort_entry sort_global_p_stage_cyc = {
+ .se_header = "Pipeline Stage Cycle",
+ .se_cmp = sort__p_stage_cyc_cmp,
+ .se_snprintf = hist_entry__global_p_stage_cyc_snprintf,
+ .se_width_idx = HISTC_GLOBAL_P_STAGE_CYC,
};
struct sort_entry sort_mem_daddr_sym = {
@@ -1858,7 +1873,8 @@ static struct sort_dimension common_sort_dimensions[] = {
DIM(SORT_CODE_PAGE_SIZE, "code_page_size", sort_code_page_size),
DIM(SORT_LOCAL_INS_LAT, "local_ins_lat", sort_local_ins_lat),
DIM(SORT_GLOBAL_INS_LAT, "ins_lat", sort_global_ins_lat),
- DIM(SORT_PIPELINE_STAGE_CYC, "p_stage_cyc", sort_p_stage_cyc),
+ DIM(SORT_LOCAL_PIPELINE_STAGE_CYC, "local_p_stage_cyc", sort_local_p_stage_cyc),
+ DIM(SORT_GLOBAL_PIPELINE_STAGE_CYC, "p_stage_cyc", sort_global_p_stage_cyc),
};
#undef DIM
@@ -2365,6 +2381,8 @@ static int64_t __sort__hde_cmp(struct perf_hpp_fmt *fmt,
tep_read_number_field(field, a->raw_data, &dyn);
offset = dyn & 0xffff;
size = (dyn >> 16) & 0xffff;
+ if (field->flags & TEP_FIELD_IS_RELATIVE)
+ offset += field->offset + field->size;
/* record max width for output */
if (size > hde->dynamic_len)
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 7b7145501933..f994261888e1 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -235,7 +235,8 @@ enum sort_type {
SORT_CODE_PAGE_SIZE,
SORT_LOCAL_INS_LAT,
SORT_GLOBAL_INS_LAT,
- SORT_PIPELINE_STAGE_CYC,
+ SORT_LOCAL_PIPELINE_STAGE_CYC,
+ SORT_GLOBAL_PIPELINE_STAGE_CYC,
/* branch stack specific sort keys */
__SORT_BRANCH_STACK,
diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
index 588601000f3f..9cbe351b141f 100644
--- a/tools/perf/util/stat-display.c
+++ b/tools/perf/util/stat-display.c
@@ -4,6 +4,7 @@
#include <linux/string.h>
#include <linux/time64.h>
#include <math.h>
+#include <perf/cpumap.h>
#include "color.h"
#include "counts.h"
#include "evlist.h"
@@ -120,11 +121,10 @@ static void aggr_printout(struct perf_stat_config *config,
id.die,
config->csv_output ? 0 : -3,
id.core, config->csv_sep);
- } else if (id.core > -1) {
+ } else if (id.cpu.cpu > -1) {
fprintf(config->output, "CPU%*d%s",
config->csv_output ? 0 : -7,
- evsel__cpus(evsel)->map[id.core],
- config->csv_sep);
+ id.cpu.cpu, config->csv_sep);
}
break;
case AGGR_THREAD:
@@ -327,26 +327,24 @@ static void print_metric_header(struct perf_stat_config *config,
fprintf(os->fh, "%*s ", config->metric_only_len, unit);
}
-static int first_shadow_cpu(struct perf_stat_config *config,
- struct evsel *evsel, struct aggr_cpu_id id)
+static int first_shadow_cpu_map_idx(struct perf_stat_config *config,
+ struct evsel *evsel, const struct aggr_cpu_id *id)
{
- struct evlist *evlist = evsel->evlist;
- int i;
+ struct perf_cpu_map *cpus = evsel__cpus(evsel);
+ struct perf_cpu cpu;
+ int idx;
if (config->aggr_mode == AGGR_NONE)
- return id.core;
+ return perf_cpu_map__idx(cpus, id->cpu);
if (!config->aggr_get_id)
return 0;
- for (i = 0; i < evsel__nr_cpus(evsel); i++) {
- int cpu2 = evsel__cpus(evsel)->map[i];
+ perf_cpu_map__for_each_cpu(cpu, idx, cpus) {
+ struct aggr_cpu_id cpu_id = config->aggr_get_id(config, cpu);
- if (cpu_map__compare_aggr_cpu_id(
- config->aggr_get_id(config, evlist->core.cpus, cpu2),
- id)) {
- return cpu2;
- }
+ if (aggr_cpu_id__equal(&cpu_id, id))
+ return idx;
}
return 0;
}
@@ -505,7 +503,7 @@ static void printout(struct perf_stat_config *config, struct aggr_cpu_id id, int
}
perf_stat__print_shadow_stats(config, counter, uval,
- first_shadow_cpu(config, counter, id),
+ first_shadow_cpu_map_idx(config, counter, &id),
&out, &config->metric_events, st);
if (!config->csv_output && !config->metric_only) {
print_noise(config, counter, noise);
@@ -516,23 +514,26 @@ static void printout(struct perf_stat_config *config, struct aggr_cpu_id id, int
static void aggr_update_shadow(struct perf_stat_config *config,
struct evlist *evlist)
{
- int cpu, s;
+ int idx, s;
+ struct perf_cpu cpu;
struct aggr_cpu_id s2, id;
u64 val;
struct evsel *counter;
+ struct perf_cpu_map *cpus;
for (s = 0; s < config->aggr_map->nr; s++) {
id = config->aggr_map->map[s];
evlist__for_each_entry(evlist, counter) {
+ cpus = evsel__cpus(counter);
val = 0;
- for (cpu = 0; cpu < evsel__nr_cpus(counter); cpu++) {
- s2 = config->aggr_get_id(config, evlist->core.cpus, cpu);
- if (!cpu_map__compare_aggr_cpu_id(s2, id))
+ perf_cpu_map__for_each_cpu(cpu, idx, cpus) {
+ s2 = config->aggr_get_id(config, cpu);
+ if (!aggr_cpu_id__equal(&s2, &id))
continue;
- val += perf_counts(counter->counts, cpu, 0)->val;
+ val += perf_counts(counter->counts, idx, 0)->val;
}
perf_stat__update_shadow_stats(counter, val,
- first_shadow_cpu(config, counter, id),
+ first_shadow_cpu_map_idx(config, counter, &id),
&rt_stat);
}
}
@@ -584,15 +585,16 @@ static void collect_all_aliases(struct perf_stat_config *config, struct evsel *c
alias = list_prepare_entry(counter, &(evlist->core.entries), core.node);
list_for_each_entry_continue (alias, &evlist->core.entries, core.node) {
- if (strcmp(evsel__name(alias), evsel__name(counter)) ||
- alias->scale != counter->scale ||
- alias->cgrp != counter->cgrp ||
- strcmp(alias->unit, counter->unit) ||
- evsel__is_clock(alias) != evsel__is_clock(counter) ||
- !strcmp(alias->pmu_name, counter->pmu_name))
- break;
- alias->merged_stat = true;
- cb(config, alias, data, false);
+ /* Merge events with the same name, etc. but on different PMUs. */
+ if (!strcmp(evsel__name(alias), evsel__name(counter)) &&
+ alias->scale == counter->scale &&
+ alias->cgrp == counter->cgrp &&
+ !strcmp(alias->unit, counter->unit) &&
+ evsel__is_clock(alias) == evsel__is_clock(counter) &&
+ strcmp(alias->pmu_name, counter->pmu_name)) {
+ alias->merged_stat = true;
+ cb(config, alias, data, false);
+ }
}
}
@@ -627,25 +629,28 @@ struct aggr_data {
u64 ena, run, val;
struct aggr_cpu_id id;
int nr;
- int cpu;
+ int cpu_map_idx;
};
static void aggr_cb(struct perf_stat_config *config,
struct evsel *counter, void *data, bool first)
{
struct aggr_data *ad = data;
- int cpu;
+ int idx;
+ struct perf_cpu cpu;
+ struct perf_cpu_map *cpus;
struct aggr_cpu_id s2;
- for (cpu = 0; cpu < evsel__nr_cpus(counter); cpu++) {
+ cpus = evsel__cpus(counter);
+ perf_cpu_map__for_each_cpu(cpu, idx, cpus) {
struct perf_counts_values *counts;
- s2 = config->aggr_get_id(config, evsel__cpus(counter), cpu);
- if (!cpu_map__compare_aggr_cpu_id(s2, ad->id))
+ s2 = config->aggr_get_id(config, cpu);
+ if (!aggr_cpu_id__equal(&s2, &ad->id))
continue;
if (first)
ad->nr++;
- counts = perf_counts(counter->counts, cpu, 0);
+ counts = perf_counts(counter->counts, idx, 0);
/*
* When any result is bad, make them all to give
* consistent output in interval mode.
@@ -665,7 +670,7 @@ 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, int cpu)
+ bool *first, struct perf_cpu cpu)
{
struct aggr_data ad;
FILE *output = config->output;
@@ -695,10 +700,9 @@ static void print_counter_aggrdata(struct perf_stat_config *config,
fprintf(output, "%s", prefix);
uval = val * counter->scale;
- if (cpu != -1) {
- id = cpu_map__empty_aggr_cpu_id();
- id.core = cpu;
- }
+ if (cpu.cpu != -1)
+ id = aggr_cpu_id__cpu(cpu, /*data=*/NULL);
+
printout(config, id, nr, counter, uval,
prefix, run, ena, 1.0, &rt_stat);
if (!metric_only)
@@ -731,8 +735,8 @@ static void print_aggr(struct perf_stat_config *config,
first = true;
evlist__for_each_entry(evlist, counter) {
print_counter_aggrdata(config, counter, s,
- prefix, metric_only,
- &first, -1);
+ prefix, metric_only,
+ &first, (struct perf_cpu){ .cpu = -1 });
}
if (metric_only)
fputc('\n', output);
@@ -778,7 +782,7 @@ static struct perf_aggr_thread_value *sort_aggr_thread(
continue;
buf[i].counter = counter;
- buf[i].id = cpu_map__empty_aggr_cpu_id();
+ buf[i].id = aggr_cpu_id__empty();
buf[i].id.thread = thread;
buf[i].uval = uval;
buf[i].val = val;
@@ -866,7 +870,7 @@ static void print_counter_aggr(struct perf_stat_config *config,
fprintf(output, "%s", prefix);
uval = cd.avg * counter->scale;
- printout(config, cpu_map__empty_aggr_cpu_id(), 0, counter, uval, prefix, cd.avg_running,
+ printout(config, aggr_cpu_id__empty(), 0, counter, uval, prefix, cd.avg_running,
cd.avg_enabled, cd.avg, &rt_stat);
if (!metric_only)
fprintf(output, "\n");
@@ -878,9 +882,9 @@ static void counter_cb(struct perf_stat_config *config __maybe_unused,
{
struct aggr_data *ad = data;
- ad->val += perf_counts(counter->counts, ad->cpu, 0)->val;
- ad->ena += perf_counts(counter->counts, ad->cpu, 0)->ena;
- ad->run += perf_counts(counter->counts, ad->cpu, 0)->run;
+ ad->val += perf_counts(counter->counts, ad->cpu_map_idx, 0)->val;
+ ad->ena += perf_counts(counter->counts, ad->cpu_map_idx, 0)->ena;
+ ad->run += perf_counts(counter->counts, ad->cpu_map_idx, 0)->run;
}
/*
@@ -893,11 +897,12 @@ static void print_counter(struct perf_stat_config *config,
FILE *output = config->output;
u64 ena, run, val;
double uval;
- int cpu;
+ int idx;
+ struct perf_cpu cpu;
struct aggr_cpu_id id;
- for (cpu = 0; cpu < evsel__nr_cpus(counter); cpu++) {
- struct aggr_data ad = { .cpu = cpu };
+ perf_cpu_map__for_each_cpu(cpu, idx, evsel__cpus(counter)) {
+ struct aggr_data ad = { .cpu_map_idx = idx };
if (!collect_data(config, counter, counter_cb, &ad))
return;
@@ -909,8 +914,7 @@ static void print_counter(struct perf_stat_config *config,
fprintf(output, "%s", prefix);
uval = val * counter->scale;
- id = cpu_map__empty_aggr_cpu_id();
- id.core = cpu;
+ id = aggr_cpu_id__cpu(cpu, /*data=*/NULL);
printout(config, id, 0, counter, uval, prefix,
run, ena, 1.0, &rt_stat);
@@ -922,29 +926,32 @@ static void print_no_aggr_metric(struct perf_stat_config *config,
struct evlist *evlist,
char *prefix)
{
- int cpu;
- int nrcpus = 0;
- struct evsel *counter;
- u64 ena, run, val;
- double uval;
- struct aggr_cpu_id id;
+ int all_idx;
+ struct perf_cpu cpu;
- nrcpus = evlist->core.cpus->nr;
- for (cpu = 0; cpu < nrcpus; cpu++) {
+ perf_cpu_map__for_each_cpu(cpu, all_idx, evlist->core.cpus) {
+ struct evsel *counter;
bool first = true;
if (prefix)
fputs(prefix, config->output);
evlist__for_each_entry(evlist, counter) {
- id = cpu_map__empty_aggr_cpu_id();
- id.core = cpu;
+ u64 ena, run, val;
+ double uval;
+ struct aggr_cpu_id id;
+ int counter_idx = perf_cpu_map__idx(evsel__cpus(counter), cpu);
+
+ if (counter_idx < 0)
+ continue;
+
+ id = aggr_cpu_id__cpu(cpu, /*data=*/NULL);
if (first) {
aggr_printout(config, counter, id, 0);
first = false;
}
- val = perf_counts(counter->counts, cpu, 0)->val;
- ena = perf_counts(counter->counts, cpu, 0)->ena;
- run = perf_counts(counter->counts, cpu, 0)->run;
+ val = perf_counts(counter->counts, counter_idx, 0)->val;
+ ena = perf_counts(counter->counts, counter_idx, 0)->ena;
+ run = perf_counts(counter->counts, counter_idx, 0)->run;
uval = val * counter->scale;
printout(config, id, 0, counter, uval, prefix,
@@ -1208,19 +1215,23 @@ static void print_percore_thread(struct perf_stat_config *config,
{
int s;
struct aggr_cpu_id s2, id;
+ struct perf_cpu_map *cpus;
bool first = true;
+ int idx;
+ struct perf_cpu cpu;
- for (int i = 0; i < evsel__nr_cpus(counter); i++) {
- s2 = config->aggr_get_id(config, evsel__cpus(counter), i);
+ cpus = evsel__cpus(counter);
+ perf_cpu_map__for_each_cpu(cpu, idx, cpus) {
+ s2 = config->aggr_get_id(config, cpu);
for (s = 0; s < config->aggr_map->nr; s++) {
id = config->aggr_map->map[s];
- if (cpu_map__compare_aggr_cpu_id(s2, id))
+ if (aggr_cpu_id__equal(&s2, &id))
break;
}
print_counter_aggrdata(config, counter, s,
prefix, false,
- &first, i);
+ &first, cpu);
}
}
@@ -1243,8 +1254,8 @@ static void print_percore(struct perf_stat_config *config,
fprintf(output, "%s", prefix);
print_counter_aggrdata(config, counter, s,
- prefix, metric_only,
- &first, -1);
+ prefix, metric_only,
+ &first, (struct perf_cpu){ .cpu = -1 });
}
if (metric_only)
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 5c7308efa768..10af7804e482 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -32,7 +32,7 @@ struct saved_value {
struct evsel *evsel;
enum stat_type type;
int ctx;
- int cpu;
+ int cpu_map_idx;
struct cgroup *cgrp;
struct runtime_stat *stat;
struct stats stats;
@@ -47,8 +47,8 @@ static int saved_value_cmp(struct rb_node *rb_node, const void *entry)
rb_node);
const struct saved_value *b = entry;
- if (a->cpu != b->cpu)
- return a->cpu - b->cpu;
+ if (a->cpu_map_idx != b->cpu_map_idx)
+ return a->cpu_map_idx - b->cpu_map_idx;
/*
* Previously the rbtree was used to link generic metrics.
@@ -105,7 +105,7 @@ static void saved_value_delete(struct rblist *rblist __maybe_unused,
}
static struct saved_value *saved_value_lookup(struct evsel *evsel,
- int cpu,
+ int cpu_map_idx,
bool create,
enum stat_type type,
int ctx,
@@ -115,7 +115,7 @@ static struct saved_value *saved_value_lookup(struct evsel *evsel,
struct rblist *rblist;
struct rb_node *nd;
struct saved_value dm = {
- .cpu = cpu,
+ .cpu_map_idx = cpu_map_idx,
.evsel = evsel,
.type = type,
.ctx = ctx,
@@ -213,10 +213,10 @@ struct runtime_stat_data {
static void update_runtime_stat(struct runtime_stat *st,
enum stat_type type,
- int cpu, u64 count,
+ int cpu_map_idx, u64 count,
struct runtime_stat_data *rsd)
{
- struct saved_value *v = saved_value_lookup(NULL, cpu, true, type,
+ struct saved_value *v = saved_value_lookup(NULL, cpu_map_idx, true, type,
rsd->ctx, st, rsd->cgrp);
if (v)
@@ -229,7 +229,7 @@ static void update_runtime_stat(struct runtime_stat *st,
* instruction rates, etc:
*/
void perf_stat__update_shadow_stats(struct evsel *counter, u64 count,
- int cpu, struct runtime_stat *st)
+ int cpu_map_idx, struct runtime_stat *st)
{
u64 count_ns = count;
struct saved_value *v;
@@ -241,88 +241,88 @@ void perf_stat__update_shadow_stats(struct evsel *counter, u64 count,
count *= counter->scale;
if (evsel__is_clock(counter))
- update_runtime_stat(st, STAT_NSECS, cpu, count_ns, &rsd);
+ update_runtime_stat(st, STAT_NSECS, cpu_map_idx, count_ns, &rsd);
else if (evsel__match(counter, HARDWARE, HW_CPU_CYCLES))
- update_runtime_stat(st, STAT_CYCLES, cpu, count, &rsd);
+ update_runtime_stat(st, STAT_CYCLES, cpu_map_idx, count, &rsd);
else if (perf_stat_evsel__is(counter, CYCLES_IN_TX))
- update_runtime_stat(st, STAT_CYCLES_IN_TX, cpu, count, &rsd);
+ update_runtime_stat(st, STAT_CYCLES_IN_TX, cpu_map_idx, count, &rsd);
else if (perf_stat_evsel__is(counter, TRANSACTION_START))
- update_runtime_stat(st, STAT_TRANSACTION, cpu, count, &rsd);
+ update_runtime_stat(st, STAT_TRANSACTION, cpu_map_idx, count, &rsd);
else if (perf_stat_evsel__is(counter, ELISION_START))
- update_runtime_stat(st, STAT_ELISION, cpu, count, &rsd);
+ update_runtime_stat(st, STAT_ELISION, cpu_map_idx, count, &rsd);
else if (perf_stat_evsel__is(counter, TOPDOWN_TOTAL_SLOTS))
update_runtime_stat(st, STAT_TOPDOWN_TOTAL_SLOTS,
- cpu, count, &rsd);
+ cpu_map_idx, count, &rsd);
else if (perf_stat_evsel__is(counter, TOPDOWN_SLOTS_ISSUED))
update_runtime_stat(st, STAT_TOPDOWN_SLOTS_ISSUED,
- cpu, count, &rsd);
+ cpu_map_idx, count, &rsd);
else if (perf_stat_evsel__is(counter, TOPDOWN_SLOTS_RETIRED))
update_runtime_stat(st, STAT_TOPDOWN_SLOTS_RETIRED,
- cpu, count, &rsd);
+ cpu_map_idx, count, &rsd);
else if (perf_stat_evsel__is(counter, TOPDOWN_FETCH_BUBBLES))
update_runtime_stat(st, STAT_TOPDOWN_FETCH_BUBBLES,
- cpu, count, &rsd);
+ cpu_map_idx, count, &rsd);
else if (perf_stat_evsel__is(counter, TOPDOWN_RECOVERY_BUBBLES))
update_runtime_stat(st, STAT_TOPDOWN_RECOVERY_BUBBLES,
- cpu, count, &rsd);
+ cpu_map_idx, count, &rsd);
else if (perf_stat_evsel__is(counter, TOPDOWN_RETIRING))
update_runtime_stat(st, STAT_TOPDOWN_RETIRING,
- cpu, count, &rsd);
+ cpu_map_idx, count, &rsd);
else if (perf_stat_evsel__is(counter, TOPDOWN_BAD_SPEC))
update_runtime_stat(st, STAT_TOPDOWN_BAD_SPEC,
- cpu, count, &rsd);
+ cpu_map_idx, count, &rsd);
else if (perf_stat_evsel__is(counter, TOPDOWN_FE_BOUND))
update_runtime_stat(st, STAT_TOPDOWN_FE_BOUND,
- cpu, count, &rsd);
+ cpu_map_idx, count, &rsd);
else if (perf_stat_evsel__is(counter, TOPDOWN_BE_BOUND))
update_runtime_stat(st, STAT_TOPDOWN_BE_BOUND,
- cpu, count, &rsd);
+ cpu_map_idx, count, &rsd);
else if (perf_stat_evsel__is(counter, TOPDOWN_HEAVY_OPS))
update_runtime_stat(st, STAT_TOPDOWN_HEAVY_OPS,
- cpu, count, &rsd);
+ cpu_map_idx, count, &rsd);
else if (perf_stat_evsel__is(counter, TOPDOWN_BR_MISPREDICT))
update_runtime_stat(st, STAT_TOPDOWN_BR_MISPREDICT,
- cpu, count, &rsd);
+ cpu_map_idx, count, &rsd);
else if (perf_stat_evsel__is(counter, TOPDOWN_FETCH_LAT))
update_runtime_stat(st, STAT_TOPDOWN_FETCH_LAT,
- cpu, count, &rsd);
+ cpu_map_idx, count, &rsd);
else if (perf_stat_evsel__is(counter, TOPDOWN_MEM_BOUND))
update_runtime_stat(st, STAT_TOPDOWN_MEM_BOUND,
- cpu, count, &rsd);
+ cpu_map_idx, count, &rsd);
else if (evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND))
update_runtime_stat(st, STAT_STALLED_CYCLES_FRONT,
- cpu, count, &rsd);
+ cpu_map_idx, count, &rsd);
else if (evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_BACKEND))
update_runtime_stat(st, STAT_STALLED_CYCLES_BACK,
- cpu, count, &rsd);
+ cpu_map_idx, count, &rsd);
else if (evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS))
- update_runtime_stat(st, STAT_BRANCHES, cpu, count, &rsd);
+ update_runtime_stat(st, STAT_BRANCHES, cpu_map_idx, count, &rsd);
else if (evsel__match(counter, HARDWARE, HW_CACHE_REFERENCES))
- update_runtime_stat(st, STAT_CACHEREFS, cpu, count, &rsd);
+ update_runtime_stat(st, STAT_CACHEREFS, cpu_map_idx, count, &rsd);
else if (evsel__match(counter, HW_CACHE, HW_CACHE_L1D))
- update_runtime_stat(st, STAT_L1_DCACHE, cpu, count, &rsd);
+ update_runtime_stat(st, STAT_L1_DCACHE, cpu_map_idx, count, &rsd);
else if (evsel__match(counter, HW_CACHE, HW_CACHE_L1I))
- update_runtime_stat(st, STAT_L1_ICACHE, cpu, count, &rsd);
+ update_runtime_stat(st, STAT_L1_ICACHE, cpu_map_idx, count, &rsd);
else if (evsel__match(counter, HW_CACHE, HW_CACHE_LL))
- update_runtime_stat(st, STAT_LL_CACHE, cpu, count, &rsd);
+ update_runtime_stat(st, STAT_LL_CACHE, cpu_map_idx, count, &rsd);
else if (evsel__match(counter, HW_CACHE, HW_CACHE_DTLB))
- update_runtime_stat(st, STAT_DTLB_CACHE, cpu, count, &rsd);
+ update_runtime_stat(st, STAT_DTLB_CACHE, cpu_map_idx, count, &rsd);
else if (evsel__match(counter, HW_CACHE, HW_CACHE_ITLB))
- update_runtime_stat(st, STAT_ITLB_CACHE, cpu, count, &rsd);
+ update_runtime_stat(st, STAT_ITLB_CACHE, cpu_map_idx, count, &rsd);
else if (perf_stat_evsel__is(counter, SMI_NUM))
- update_runtime_stat(st, STAT_SMI_NUM, cpu, count, &rsd);
+ update_runtime_stat(st, STAT_SMI_NUM, cpu_map_idx, count, &rsd);
else if (perf_stat_evsel__is(counter, APERF))
- update_runtime_stat(st, STAT_APERF, cpu, count, &rsd);
+ update_runtime_stat(st, STAT_APERF, cpu_map_idx, count, &rsd);
if (counter->collect_stat) {
- v = saved_value_lookup(counter, cpu, true, STAT_NONE, 0, st,
+ v = saved_value_lookup(counter, cpu_map_idx, true, STAT_NONE, 0, st,
rsd.cgrp);
update_stats(&v->stats, count);
if (counter->metric_leader)
v->metric_total += count;
} else if (counter->metric_leader) {
v = saved_value_lookup(counter->metric_leader,
- cpu, true, STAT_NONE, 0, st, rsd.cgrp);
+ cpu_map_idx, true, STAT_NONE, 0, st, rsd.cgrp);
v->metric_total += count;
v->metric_other++;
}
@@ -464,12 +464,12 @@ void perf_stat__collect_metric_expr(struct evlist *evsel_list)
}
static double runtime_stat_avg(struct runtime_stat *st,
- enum stat_type type, int cpu,
+ enum stat_type type, int cpu_map_idx,
struct runtime_stat_data *rsd)
{
struct saved_value *v;
- v = saved_value_lookup(NULL, cpu, false, type, rsd->ctx, st, rsd->cgrp);
+ v = saved_value_lookup(NULL, cpu_map_idx, false, type, rsd->ctx, st, rsd->cgrp);
if (!v)
return 0.0;
@@ -477,12 +477,12 @@ static double runtime_stat_avg(struct runtime_stat *st,
}
static double runtime_stat_n(struct runtime_stat *st,
- enum stat_type type, int cpu,
+ enum stat_type type, int cpu_map_idx,
struct runtime_stat_data *rsd)
{
struct saved_value *v;
- v = saved_value_lookup(NULL, cpu, false, type, rsd->ctx, st, rsd->cgrp);
+ v = saved_value_lookup(NULL, cpu_map_idx, false, type, rsd->ctx, st, rsd->cgrp);
if (!v)
return 0.0;
@@ -490,7 +490,7 @@ static double runtime_stat_n(struct runtime_stat *st,
}
static void print_stalled_cycles_frontend(struct perf_stat_config *config,
- int cpu, double avg,
+ int cpu_map_idx, double avg,
struct perf_stat_output_ctx *out,
struct runtime_stat *st,
struct runtime_stat_data *rsd)
@@ -498,7 +498,7 @@ static void print_stalled_cycles_frontend(struct perf_stat_config *config,
double total, ratio = 0.0;
const char *color;
- total = runtime_stat_avg(st, STAT_CYCLES, cpu, rsd);
+ total = runtime_stat_avg(st, STAT_CYCLES, cpu_map_idx, rsd);
if (total)
ratio = avg / total * 100.0;
@@ -513,7 +513,7 @@ static void print_stalled_cycles_frontend(struct perf_stat_config *config,
}
static void print_stalled_cycles_backend(struct perf_stat_config *config,
- int cpu, double avg,
+ int cpu_map_idx, double avg,
struct perf_stat_output_ctx *out,
struct runtime_stat *st,
struct runtime_stat_data *rsd)
@@ -521,7 +521,7 @@ static void print_stalled_cycles_backend(struct perf_stat_config *config,
double total, ratio = 0.0;
const char *color;
- total = runtime_stat_avg(st, STAT_CYCLES, cpu, rsd);
+ total = runtime_stat_avg(st, STAT_CYCLES, cpu_map_idx, rsd);
if (total)
ratio = avg / total * 100.0;
@@ -532,7 +532,7 @@ static void print_stalled_cycles_backend(struct perf_stat_config *config,
}
static void print_branch_misses(struct perf_stat_config *config,
- int cpu, double avg,
+ int cpu_map_idx, double avg,
struct perf_stat_output_ctx *out,
struct runtime_stat *st,
struct runtime_stat_data *rsd)
@@ -540,7 +540,7 @@ static void print_branch_misses(struct perf_stat_config *config,
double total, ratio = 0.0;
const char *color;
- total = runtime_stat_avg(st, STAT_BRANCHES, cpu, rsd);
+ total = runtime_stat_avg(st, STAT_BRANCHES, cpu_map_idx, rsd);
if (total)
ratio = avg / total * 100.0;
@@ -551,7 +551,7 @@ static void print_branch_misses(struct perf_stat_config *config,
}
static void print_l1_dcache_misses(struct perf_stat_config *config,
- int cpu, double avg,
+ int cpu_map_idx, double avg,
struct perf_stat_output_ctx *out,
struct runtime_stat *st,
struct runtime_stat_data *rsd)
@@ -559,7 +559,7 @@ static void print_l1_dcache_misses(struct perf_stat_config *config,
double total, ratio = 0.0;
const char *color;
- total = runtime_stat_avg(st, STAT_L1_DCACHE, cpu, rsd);
+ total = runtime_stat_avg(st, STAT_L1_DCACHE, cpu_map_idx, rsd);
if (total)
ratio = avg / total * 100.0;
@@ -570,7 +570,7 @@ static void print_l1_dcache_misses(struct perf_stat_config *config,
}
static void print_l1_icache_misses(struct perf_stat_config *config,
- int cpu, double avg,
+ int cpu_map_idx, double avg,
struct perf_stat_output_ctx *out,
struct runtime_stat *st,
struct runtime_stat_data *rsd)
@@ -578,7 +578,7 @@ static void print_l1_icache_misses(struct perf_stat_config *config,
double total, ratio = 0.0;
const char *color;
- total = runtime_stat_avg(st, STAT_L1_ICACHE, cpu, rsd);
+ total = runtime_stat_avg(st, STAT_L1_ICACHE, cpu_map_idx, rsd);
if (total)
ratio = avg / total * 100.0;
@@ -588,7 +588,7 @@ static void print_l1_icache_misses(struct perf_stat_config *config,
}
static void print_dtlb_cache_misses(struct perf_stat_config *config,
- int cpu, double avg,
+ int cpu_map_idx, double avg,
struct perf_stat_output_ctx *out,
struct runtime_stat *st,
struct runtime_stat_data *rsd)
@@ -596,7 +596,7 @@ static void print_dtlb_cache_misses(struct perf_stat_config *config,
double total, ratio = 0.0;
const char *color;
- total = runtime_stat_avg(st, STAT_DTLB_CACHE, cpu, rsd);
+ total = runtime_stat_avg(st, STAT_DTLB_CACHE, cpu_map_idx, rsd);
if (total)
ratio = avg / total * 100.0;
@@ -606,7 +606,7 @@ static void print_dtlb_cache_misses(struct perf_stat_config *config,
}
static void print_itlb_cache_misses(struct perf_stat_config *config,
- int cpu, double avg,
+ int cpu_map_idx, double avg,
struct perf_stat_output_ctx *out,
struct runtime_stat *st,
struct runtime_stat_data *rsd)
@@ -614,7 +614,7 @@ static void print_itlb_cache_misses(struct perf_stat_config *config,
double total, ratio = 0.0;
const char *color;
- total = runtime_stat_avg(st, STAT_ITLB_CACHE, cpu, rsd);
+ total = runtime_stat_avg(st, STAT_ITLB_CACHE, cpu_map_idx, rsd);
if (total)
ratio = avg / total * 100.0;
@@ -624,7 +624,7 @@ static void print_itlb_cache_misses(struct perf_stat_config *config,
}
static void print_ll_cache_misses(struct perf_stat_config *config,
- int cpu, double avg,
+ int cpu_map_idx, double avg,
struct perf_stat_output_ctx *out,
struct runtime_stat *st,
struct runtime_stat_data *rsd)
@@ -632,7 +632,7 @@ static void print_ll_cache_misses(struct perf_stat_config *config,
double total, ratio = 0.0;
const char *color;
- total = runtime_stat_avg(st, STAT_LL_CACHE, cpu, rsd);
+ total = runtime_stat_avg(st, STAT_LL_CACHE, cpu_map_idx, rsd);
if (total)
ratio = avg / total * 100.0;
@@ -690,61 +690,61 @@ static double sanitize_val(double x)
return x;
}
-static double td_total_slots(int cpu, struct runtime_stat *st,
+static double td_total_slots(int cpu_map_idx, struct runtime_stat *st,
struct runtime_stat_data *rsd)
{
- return runtime_stat_avg(st, STAT_TOPDOWN_TOTAL_SLOTS, cpu, rsd);
+ return runtime_stat_avg(st, STAT_TOPDOWN_TOTAL_SLOTS, cpu_map_idx, rsd);
}
-static double td_bad_spec(int cpu, struct runtime_stat *st,
+static double td_bad_spec(int cpu_map_idx, struct runtime_stat *st,
struct runtime_stat_data *rsd)
{
double bad_spec = 0;
double total_slots;
double total;
- total = runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_ISSUED, cpu, rsd) -
- runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_RETIRED, cpu, rsd) +
- runtime_stat_avg(st, STAT_TOPDOWN_RECOVERY_BUBBLES, cpu, rsd);
+ total = runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_ISSUED, cpu_map_idx, rsd) -
+ runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_RETIRED, cpu_map_idx, rsd) +
+ runtime_stat_avg(st, STAT_TOPDOWN_RECOVERY_BUBBLES, cpu_map_idx, rsd);
- total_slots = td_total_slots(cpu, st, rsd);
+ total_slots = td_total_slots(cpu_map_idx, st, rsd);
if (total_slots)
bad_spec = total / total_slots;
return sanitize_val(bad_spec);
}
-static double td_retiring(int cpu, struct runtime_stat *st,
+static double td_retiring(int cpu_map_idx, struct runtime_stat *st,
struct runtime_stat_data *rsd)
{
double retiring = 0;
- double total_slots = td_total_slots(cpu, st, rsd);
+ double total_slots = td_total_slots(cpu_map_idx, st, rsd);
double ret_slots = runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_RETIRED,
- cpu, rsd);
+ cpu_map_idx, rsd);
if (total_slots)
retiring = ret_slots / total_slots;
return retiring;
}
-static double td_fe_bound(int cpu, struct runtime_stat *st,
+static double td_fe_bound(int cpu_map_idx, struct runtime_stat *st,
struct runtime_stat_data *rsd)
{
double fe_bound = 0;
- double total_slots = td_total_slots(cpu, st, rsd);
+ double total_slots = td_total_slots(cpu_map_idx, st, rsd);
double fetch_bub = runtime_stat_avg(st, STAT_TOPDOWN_FETCH_BUBBLES,
- cpu, rsd);
+ cpu_map_idx, rsd);
if (total_slots)
fe_bound = fetch_bub / total_slots;
return fe_bound;
}
-static double td_be_bound(int cpu, struct runtime_stat *st,
+static double td_be_bound(int cpu_map_idx, struct runtime_stat *st,
struct runtime_stat_data *rsd)
{
- double sum = (td_fe_bound(cpu, st, rsd) +
- td_bad_spec(cpu, st, rsd) +
- td_retiring(cpu, st, rsd));
+ double sum = (td_fe_bound(cpu_map_idx, st, rsd) +
+ td_bad_spec(cpu_map_idx, st, rsd) +
+ td_retiring(cpu_map_idx, st, rsd));
if (sum == 0)
return 0;
return sanitize_val(1.0 - sum);
@@ -755,15 +755,15 @@ static double td_be_bound(int cpu, struct runtime_stat *st,
* the ratios we need to recreate the sum.
*/
-static double td_metric_ratio(int cpu, enum stat_type type,
+static double td_metric_ratio(int cpu_map_idx, enum stat_type type,
struct runtime_stat *stat,
struct runtime_stat_data *rsd)
{
- double sum = runtime_stat_avg(stat, STAT_TOPDOWN_RETIRING, cpu, rsd) +
- runtime_stat_avg(stat, STAT_TOPDOWN_FE_BOUND, cpu, rsd) +
- runtime_stat_avg(stat, STAT_TOPDOWN_BE_BOUND, cpu, rsd) +
- runtime_stat_avg(stat, STAT_TOPDOWN_BAD_SPEC, cpu, rsd);
- double d = runtime_stat_avg(stat, type, cpu, rsd);
+ double sum = runtime_stat_avg(stat, STAT_TOPDOWN_RETIRING, cpu_map_idx, rsd) +
+ runtime_stat_avg(stat, STAT_TOPDOWN_FE_BOUND, cpu_map_idx, rsd) +
+ runtime_stat_avg(stat, STAT_TOPDOWN_BE_BOUND, cpu_map_idx, rsd) +
+ runtime_stat_avg(stat, STAT_TOPDOWN_BAD_SPEC, cpu_map_idx, rsd);
+ double d = runtime_stat_avg(stat, type, cpu_map_idx, rsd);
if (sum)
return d / sum;
@@ -775,23 +775,23 @@ static double td_metric_ratio(int cpu, enum stat_type type,
* We allow two missing.
*/
-static bool full_td(int cpu, struct runtime_stat *stat,
+static bool full_td(int cpu_map_idx, struct runtime_stat *stat,
struct runtime_stat_data *rsd)
{
int c = 0;
- if (runtime_stat_avg(stat, STAT_TOPDOWN_RETIRING, cpu, rsd) > 0)
+ if (runtime_stat_avg(stat, STAT_TOPDOWN_RETIRING, cpu_map_idx, rsd) > 0)
c++;
- if (runtime_stat_avg(stat, STAT_TOPDOWN_BE_BOUND, cpu, rsd) > 0)
+ if (runtime_stat_avg(stat, STAT_TOPDOWN_BE_BOUND, cpu_map_idx, rsd) > 0)
c++;
- if (runtime_stat_avg(stat, STAT_TOPDOWN_FE_BOUND, cpu, rsd) > 0)
+ if (runtime_stat_avg(stat, STAT_TOPDOWN_FE_BOUND, cpu_map_idx, rsd) > 0)
c++;
- if (runtime_stat_avg(stat, STAT_TOPDOWN_BAD_SPEC, cpu, rsd) > 0)
+ if (runtime_stat_avg(stat, STAT_TOPDOWN_BAD_SPEC, cpu_map_idx, rsd) > 0)
c++;
return c >= 2;
}
-static void print_smi_cost(struct perf_stat_config *config, int cpu,
+static void print_smi_cost(struct perf_stat_config *config, int cpu_map_idx,
struct perf_stat_output_ctx *out,
struct runtime_stat *st,
struct runtime_stat_data *rsd)
@@ -799,9 +799,9 @@ static void print_smi_cost(struct perf_stat_config *config, int cpu,
double smi_num, aperf, cycles, cost = 0.0;
const char *color = NULL;
- smi_num = runtime_stat_avg(st, STAT_SMI_NUM, cpu, rsd);
- aperf = runtime_stat_avg(st, STAT_APERF, cpu, rsd);
- cycles = runtime_stat_avg(st, STAT_CYCLES, cpu, rsd);
+ smi_num = runtime_stat_avg(st, STAT_SMI_NUM, cpu_map_idx, rsd);
+ aperf = runtime_stat_avg(st, STAT_APERF, cpu_map_idx, rsd);
+ cycles = runtime_stat_avg(st, STAT_CYCLES, cpu_map_idx, rsd);
if ((cycles == 0) || (aperf == 0))
return;
@@ -818,7 +818,7 @@ static void print_smi_cost(struct perf_stat_config *config, int cpu,
static int prepare_metric(struct evsel **metric_events,
struct metric_ref *metric_refs,
struct expr_parse_ctx *pctx,
- int cpu,
+ int cpu_map_idx,
struct runtime_stat *st)
{
double scale;
@@ -836,7 +836,7 @@ static int prepare_metric(struct evsel **metric_events,
scale = 1e-9;
source_count = 1;
} else {
- v = saved_value_lookup(metric_events[i], cpu, false,
+ v = saved_value_lookup(metric_events[i], cpu_map_idx, false,
STAT_NONE, 0, st,
metric_events[i]->cgrp);
if (!v)
@@ -874,7 +874,7 @@ static void generic_metric(struct perf_stat_config *config,
const char *metric_name,
const char *metric_unit,
int runtime,
- int cpu,
+ int cpu_map_idx,
struct perf_stat_output_ctx *out,
struct runtime_stat *st)
{
@@ -889,7 +889,7 @@ static void generic_metric(struct perf_stat_config *config,
return;
pctx->runtime = runtime;
- i = prepare_metric(metric_events, metric_refs, pctx, cpu, st);
+ i = prepare_metric(metric_events, metric_refs, pctx, cpu_map_idx, st);
if (i < 0) {
expr__ctx_free(pctx);
return;
@@ -934,7 +934,7 @@ static void generic_metric(struct perf_stat_config *config,
expr__ctx_free(pctx);
}
-double test_generic_metric(struct metric_expr *mexp, int cpu, struct runtime_stat *st)
+double test_generic_metric(struct metric_expr *mexp, int cpu_map_idx, struct runtime_stat *st)
{
struct expr_parse_ctx *pctx;
double ratio = 0.0;
@@ -943,7 +943,7 @@ double test_generic_metric(struct metric_expr *mexp, int cpu, struct runtime_sta
if (!pctx)
return NAN;
- if (prepare_metric(mexp->metric_events, mexp->metric_refs, pctx, cpu, st) < 0)
+ if (prepare_metric(mexp->metric_events, mexp->metric_refs, pctx, cpu_map_idx, st) < 0)
goto out;
if (expr__parse(&ratio, pctx, mexp->metric_expr))
@@ -956,7 +956,7 @@ out:
void perf_stat__print_shadow_stats(struct perf_stat_config *config,
struct evsel *evsel,
- double avg, int cpu,
+ double avg, int cpu_map_idx,
struct perf_stat_output_ctx *out,
struct rblist *metric_events,
struct runtime_stat *st)
@@ -975,7 +975,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
if (config->iostat_run) {
iostat_print_metric(config, evsel, out);
} else if (evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) {
- total = runtime_stat_avg(st, STAT_CYCLES, cpu, &rsd);
+ total = runtime_stat_avg(st, STAT_CYCLES, cpu_map_idx, &rsd);
if (total) {
ratio = avg / total;
@@ -985,11 +985,11 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
print_metric(config, ctxp, NULL, NULL, "insn per cycle", 0);
}
- total = runtime_stat_avg(st, STAT_STALLED_CYCLES_FRONT, cpu, &rsd);
+ total = runtime_stat_avg(st, STAT_STALLED_CYCLES_FRONT, cpu_map_idx, &rsd);
total = max(total, runtime_stat_avg(st,
STAT_STALLED_CYCLES_BACK,
- cpu, &rsd));
+ cpu_map_idx, &rsd));
if (total && avg) {
out->new_line(config, ctxp);
@@ -999,8 +999,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
ratio);
}
} else if (evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES)) {
- if (runtime_stat_n(st, STAT_BRANCHES, cpu, &rsd) != 0)
- print_branch_misses(config, cpu, avg, out, st, &rsd);
+ if (runtime_stat_n(st, STAT_BRANCHES, cpu_map_idx, &rsd) != 0)
+ print_branch_misses(config, cpu_map_idx, avg, out, st, &rsd);
else
print_metric(config, ctxp, NULL, NULL, "of all branches", 0);
} else if (
@@ -1009,8 +1009,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
- if (runtime_stat_n(st, STAT_L1_DCACHE, cpu, &rsd) != 0)
- print_l1_dcache_misses(config, cpu, avg, out, st, &rsd);
+ if (runtime_stat_n(st, STAT_L1_DCACHE, cpu_map_idx, &rsd) != 0)
+ print_l1_dcache_misses(config, cpu_map_idx, avg, out, st, &rsd);
else
print_metric(config, ctxp, NULL, NULL, "of all L1-dcache accesses", 0);
} else if (
@@ -1019,8 +1019,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
- if (runtime_stat_n(st, STAT_L1_ICACHE, cpu, &rsd) != 0)
- print_l1_icache_misses(config, cpu, avg, out, st, &rsd);
+ if (runtime_stat_n(st, STAT_L1_ICACHE, cpu_map_idx, &rsd) != 0)
+ print_l1_icache_misses(config, cpu_map_idx, avg, out, st, &rsd);
else
print_metric(config, ctxp, NULL, NULL, "of all L1-icache accesses", 0);
} else if (
@@ -1029,8 +1029,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
- if (runtime_stat_n(st, STAT_DTLB_CACHE, cpu, &rsd) != 0)
- print_dtlb_cache_misses(config, cpu, avg, out, st, &rsd);
+ if (runtime_stat_n(st, STAT_DTLB_CACHE, cpu_map_idx, &rsd) != 0)
+ print_dtlb_cache_misses(config, cpu_map_idx, avg, out, st, &rsd);
else
print_metric(config, ctxp, NULL, NULL, "of all dTLB cache accesses", 0);
} else if (
@@ -1039,8 +1039,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
- if (runtime_stat_n(st, STAT_ITLB_CACHE, cpu, &rsd) != 0)
- print_itlb_cache_misses(config, cpu, avg, out, st, &rsd);
+ if (runtime_stat_n(st, STAT_ITLB_CACHE, cpu_map_idx, &rsd) != 0)
+ print_itlb_cache_misses(config, cpu_map_idx, avg, out, st, &rsd);
else
print_metric(config, ctxp, NULL, NULL, "of all iTLB cache accesses", 0);
} else if (
@@ -1049,27 +1049,27 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
- if (runtime_stat_n(st, STAT_LL_CACHE, cpu, &rsd) != 0)
- print_ll_cache_misses(config, cpu, avg, out, st, &rsd);
+ if (runtime_stat_n(st, STAT_LL_CACHE, cpu_map_idx, &rsd) != 0)
+ print_ll_cache_misses(config, cpu_map_idx, avg, out, st, &rsd);
else
print_metric(config, ctxp, NULL, NULL, "of all LL-cache accesses", 0);
} else if (evsel__match(evsel, HARDWARE, HW_CACHE_MISSES)) {
- total = runtime_stat_avg(st, STAT_CACHEREFS, cpu, &rsd);
+ total = runtime_stat_avg(st, STAT_CACHEREFS, cpu_map_idx, &rsd);
if (total)
ratio = avg * 100 / total;
- if (runtime_stat_n(st, STAT_CACHEREFS, cpu, &rsd) != 0)
+ if (runtime_stat_n(st, STAT_CACHEREFS, cpu_map_idx, &rsd) != 0)
print_metric(config, ctxp, NULL, "%8.3f %%",
"of all cache refs", ratio);
else
print_metric(config, ctxp, NULL, NULL, "of all cache refs", 0);
} else if (evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) {
- print_stalled_cycles_frontend(config, cpu, avg, out, st, &rsd);
+ print_stalled_cycles_frontend(config, cpu_map_idx, avg, out, st, &rsd);
} else if (evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) {
- print_stalled_cycles_backend(config, cpu, avg, out, st, &rsd);
+ print_stalled_cycles_backend(config, cpu_map_idx, avg, out, st, &rsd);
} else if (evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) {
- total = runtime_stat_avg(st, STAT_NSECS, cpu, &rsd);
+ total = runtime_stat_avg(st, STAT_NSECS, cpu_map_idx, &rsd);
if (total) {
ratio = avg / total;
@@ -1078,7 +1078,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
print_metric(config, ctxp, NULL, NULL, "Ghz", 0);
}
} else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX)) {
- total = runtime_stat_avg(st, STAT_CYCLES, cpu, &rsd);
+ total = runtime_stat_avg(st, STAT_CYCLES, cpu_map_idx, &rsd);
if (total)
print_metric(config, ctxp, NULL,
@@ -1088,8 +1088,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
print_metric(config, ctxp, NULL, NULL, "transactional cycles",
0);
} else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX_CP)) {
- total = runtime_stat_avg(st, STAT_CYCLES, cpu, &rsd);
- total2 = runtime_stat_avg(st, STAT_CYCLES_IN_TX, cpu, &rsd);
+ total = runtime_stat_avg(st, STAT_CYCLES, cpu_map_idx, &rsd);
+ total2 = runtime_stat_avg(st, STAT_CYCLES_IN_TX, cpu_map_idx, &rsd);
if (total2 < avg)
total2 = avg;
@@ -1099,19 +1099,19 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
else
print_metric(config, ctxp, NULL, NULL, "aborted cycles", 0);
} else if (perf_stat_evsel__is(evsel, TRANSACTION_START)) {
- total = runtime_stat_avg(st, STAT_CYCLES_IN_TX, cpu, &rsd);
+ total = runtime_stat_avg(st, STAT_CYCLES_IN_TX, cpu_map_idx, &rsd);
if (avg)
ratio = total / avg;
- if (runtime_stat_n(st, STAT_CYCLES_IN_TX, cpu, &rsd) != 0)
+ if (runtime_stat_n(st, STAT_CYCLES_IN_TX, cpu_map_idx, &rsd) != 0)
print_metric(config, ctxp, NULL, "%8.0f",
"cycles / transaction", ratio);
else
print_metric(config, ctxp, NULL, NULL, "cycles / transaction",
0);
} else if (perf_stat_evsel__is(evsel, ELISION_START)) {
- total = runtime_stat_avg(st, STAT_CYCLES_IN_TX, cpu, &rsd);
+ total = runtime_stat_avg(st, STAT_CYCLES_IN_TX, cpu_map_idx, &rsd);
if (avg)
ratio = total / avg;
@@ -1124,28 +1124,28 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
else
print_metric(config, ctxp, NULL, NULL, "CPUs utilized", 0);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_FETCH_BUBBLES)) {
- double fe_bound = td_fe_bound(cpu, st, &rsd);
+ double fe_bound = td_fe_bound(cpu_map_idx, st, &rsd);
if (fe_bound > 0.2)
color = PERF_COLOR_RED;
print_metric(config, ctxp, color, "%8.1f%%", "frontend bound",
fe_bound * 100.);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_SLOTS_RETIRED)) {
- double retiring = td_retiring(cpu, st, &rsd);
+ double retiring = td_retiring(cpu_map_idx, st, &rsd);
if (retiring > 0.7)
color = PERF_COLOR_GREEN;
print_metric(config, ctxp, color, "%8.1f%%", "retiring",
retiring * 100.);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_RECOVERY_BUBBLES)) {
- double bad_spec = td_bad_spec(cpu, st, &rsd);
+ double bad_spec = td_bad_spec(cpu_map_idx, st, &rsd);
if (bad_spec > 0.1)
color = PERF_COLOR_RED;
print_metric(config, ctxp, color, "%8.1f%%", "bad speculation",
bad_spec * 100.);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_SLOTS_ISSUED)) {
- double be_bound = td_be_bound(cpu, st, &rsd);
+ double be_bound = td_be_bound(cpu_map_idx, st, &rsd);
const char *name = "backend bound";
static int have_recovery_bubbles = -1;
@@ -1158,14 +1158,14 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
if (be_bound > 0.2)
color = PERF_COLOR_RED;
- if (td_total_slots(cpu, st, &rsd) > 0)
+ if (td_total_slots(cpu_map_idx, st, &rsd) > 0)
print_metric(config, ctxp, color, "%8.1f%%", name,
be_bound * 100.);
else
print_metric(config, ctxp, NULL, NULL, name, 0);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_RETIRING) &&
- full_td(cpu, st, &rsd)) {
- double retiring = td_metric_ratio(cpu,
+ full_td(cpu_map_idx, st, &rsd)) {
+ double retiring = td_metric_ratio(cpu_map_idx,
STAT_TOPDOWN_RETIRING, st,
&rsd);
if (retiring > 0.7)
@@ -1173,8 +1173,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
print_metric(config, ctxp, color, "%8.1f%%", "retiring",
retiring * 100.);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_FE_BOUND) &&
- full_td(cpu, st, &rsd)) {
- double fe_bound = td_metric_ratio(cpu,
+ full_td(cpu_map_idx, st, &rsd)) {
+ double fe_bound = td_metric_ratio(cpu_map_idx,
STAT_TOPDOWN_FE_BOUND, st,
&rsd);
if (fe_bound > 0.2)
@@ -1182,8 +1182,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
print_metric(config, ctxp, color, "%8.1f%%", "frontend bound",
fe_bound * 100.);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_BE_BOUND) &&
- full_td(cpu, st, &rsd)) {
- double be_bound = td_metric_ratio(cpu,
+ full_td(cpu_map_idx, st, &rsd)) {
+ double be_bound = td_metric_ratio(cpu_map_idx,
STAT_TOPDOWN_BE_BOUND, st,
&rsd);
if (be_bound > 0.2)
@@ -1191,8 +1191,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
print_metric(config, ctxp, color, "%8.1f%%", "backend bound",
be_bound * 100.);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_BAD_SPEC) &&
- full_td(cpu, st, &rsd)) {
- double bad_spec = td_metric_ratio(cpu,
+ full_td(cpu_map_idx, st, &rsd)) {
+ double bad_spec = td_metric_ratio(cpu_map_idx,
STAT_TOPDOWN_BAD_SPEC, st,
&rsd);
if (bad_spec > 0.1)
@@ -1200,11 +1200,11 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
print_metric(config, ctxp, color, "%8.1f%%", "bad speculation",
bad_spec * 100.);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_HEAVY_OPS) &&
- full_td(cpu, st, &rsd) && (config->topdown_level > 1)) {
- double retiring = td_metric_ratio(cpu,
+ full_td(cpu_map_idx, st, &rsd) && (config->topdown_level > 1)) {
+ double retiring = td_metric_ratio(cpu_map_idx,
STAT_TOPDOWN_RETIRING, st,
&rsd);
- double heavy_ops = td_metric_ratio(cpu,
+ double heavy_ops = td_metric_ratio(cpu_map_idx,
STAT_TOPDOWN_HEAVY_OPS, st,
&rsd);
double light_ops = retiring - heavy_ops;
@@ -1220,11 +1220,11 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
print_metric(config, ctxp, color, "%8.1f%%", "light operations",
light_ops * 100.);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_BR_MISPREDICT) &&
- full_td(cpu, st, &rsd) && (config->topdown_level > 1)) {
- double bad_spec = td_metric_ratio(cpu,
+ full_td(cpu_map_idx, st, &rsd) && (config->topdown_level > 1)) {
+ double bad_spec = td_metric_ratio(cpu_map_idx,
STAT_TOPDOWN_BAD_SPEC, st,
&rsd);
- double br_mis = td_metric_ratio(cpu,
+ double br_mis = td_metric_ratio(cpu_map_idx,
STAT_TOPDOWN_BR_MISPREDICT, st,
&rsd);
double m_clears = bad_spec - br_mis;
@@ -1240,11 +1240,11 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
print_metric(config, ctxp, color, "%8.1f%%", "machine clears",
m_clears * 100.);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_FETCH_LAT) &&
- full_td(cpu, st, &rsd) && (config->topdown_level > 1)) {
- double fe_bound = td_metric_ratio(cpu,
+ full_td(cpu_map_idx, st, &rsd) && (config->topdown_level > 1)) {
+ double fe_bound = td_metric_ratio(cpu_map_idx,
STAT_TOPDOWN_FE_BOUND, st,
&rsd);
- double fetch_lat = td_metric_ratio(cpu,
+ double fetch_lat = td_metric_ratio(cpu_map_idx,
STAT_TOPDOWN_FETCH_LAT, st,
&rsd);
double fetch_bw = fe_bound - fetch_lat;
@@ -1260,11 +1260,11 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
print_metric(config, ctxp, color, "%8.1f%%", "fetch bandwidth",
fetch_bw * 100.);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_MEM_BOUND) &&
- full_td(cpu, st, &rsd) && (config->topdown_level > 1)) {
- double be_bound = td_metric_ratio(cpu,
+ full_td(cpu_map_idx, st, &rsd) && (config->topdown_level > 1)) {
+ double be_bound = td_metric_ratio(cpu_map_idx,
STAT_TOPDOWN_BE_BOUND, st,
&rsd);
- double mem_bound = td_metric_ratio(cpu,
+ double mem_bound = td_metric_ratio(cpu_map_idx,
STAT_TOPDOWN_MEM_BOUND, st,
&rsd);
double core_bound = be_bound - mem_bound;
@@ -1281,12 +1281,12 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
core_bound * 100.);
} else if (evsel->metric_expr) {
generic_metric(config, evsel->metric_expr, evsel->metric_events, NULL,
- evsel->name, evsel->metric_name, NULL, 1, cpu, out, st);
- } else if (runtime_stat_n(st, STAT_NSECS, cpu, &rsd) != 0) {
+ evsel->name, evsel->metric_name, NULL, 1, cpu_map_idx, out, st);
+ } else if (runtime_stat_n(st, STAT_NSECS, cpu_map_idx, &rsd) != 0) {
char unit = ' ';
char unit_buf[10] = "/sec";
- total = runtime_stat_avg(st, STAT_NSECS, cpu, &rsd);
+ total = runtime_stat_avg(st, STAT_NSECS, cpu_map_idx, &rsd);
if (total)
ratio = convert_unit_double(1000000000.0 * avg / total, &unit);
@@ -1294,7 +1294,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
snprintf(unit_buf, sizeof(unit_buf), "%c/sec", unit);
print_metric(config, ctxp, NULL, "%8.3f", unit_buf, ratio);
} else if (perf_stat_evsel__is(evsel, SMI_NUM)) {
- print_smi_cost(config, cpu, out, st, &rsd);
+ print_smi_cost(config, cpu_map_idx, out, st, &rsd);
} else {
num = 0;
}
@@ -1307,7 +1307,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
out->new_line(config, ctxp);
generic_metric(config, mexp->metric_expr, mexp->metric_events,
mexp->metric_refs, evsel->name, mexp->metric_name,
- mexp->metric_unit, mexp->runtime, cpu, out, st);
+ mexp->metric_unit, mexp->runtime, cpu_map_idx, out, st);
}
}
if (num == 0)
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 09ea334586f2..ee6f03481215 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -152,11 +152,13 @@ static void evsel__free_stat_priv(struct evsel *evsel)
zfree(&evsel->stats);
}
-static int evsel__alloc_prev_raw_counts(struct evsel *evsel, int ncpus, int nthreads)
+static int evsel__alloc_prev_raw_counts(struct evsel *evsel)
{
+ int cpu_map_nr = evsel__nr_cpus(evsel);
+ int nthreads = perf_thread_map__nr(evsel->core.threads);
struct perf_counts *counts;
- counts = perf_counts__new(ncpus, nthreads);
+ counts = perf_counts__new(cpu_map_nr, nthreads);
if (counts)
evsel->prev_raw_counts = counts;
@@ -177,12 +179,9 @@ static void evsel__reset_prev_raw_counts(struct evsel *evsel)
static int evsel__alloc_stats(struct evsel *evsel, bool alloc_raw)
{
- int ncpus = evsel__nr_cpus(evsel);
- int nthreads = perf_thread_map__nr(evsel->core.threads);
-
if (evsel__alloc_stat_priv(evsel) < 0 ||
- evsel__alloc_counts(evsel, ncpus, nthreads) < 0 ||
- (alloc_raw && evsel__alloc_prev_raw_counts(evsel, ncpus, nthreads) < 0))
+ evsel__alloc_counts(evsel) < 0 ||
+ (alloc_raw && evsel__alloc_prev_raw_counts(evsel) < 0))
return -ENOMEM;
return 0;
@@ -293,11 +292,12 @@ static bool pkg_id_equal(const void *__key1, const void *__key2,
return *key1 == *key2;
}
-static int check_per_pkg(struct evsel *counter,
- struct perf_counts_values *vals, int cpu, bool *skip)
+static int check_per_pkg(struct evsel *counter, struct perf_counts_values *vals,
+ int cpu_map_idx, bool *skip)
{
struct hashmap *mask = counter->per_pkg_mask;
struct perf_cpu_map *cpus = evsel__cpus(counter);
+ struct perf_cpu cpu = perf_cpu_map__cpu(cpus, cpu_map_idx);
int s, d, ret = 0;
uint64_t *key;
@@ -328,7 +328,7 @@ static int check_per_pkg(struct evsel *counter,
if (!(vals->run && vals->ena))
return 0;
- s = cpu_map__get_socket(cpus, cpu, NULL).socket;
+ s = cpu__get_socket_id(cpu);
if (s < 0)
return -1;
@@ -336,7 +336,7 @@ static int check_per_pkg(struct evsel *counter,
* On multi-die system, die_id > 0. On no-die system, die_id = 0.
* We use hashmap(socket, die) to check the used socket+die pair.
*/
- d = cpu_map__get_die(cpus, cpu, NULL).die;
+ d = cpu__get_die_id(cpu);
if (d < 0)
return -1;
@@ -345,9 +345,10 @@ static int check_per_pkg(struct evsel *counter,
return -ENOMEM;
*key = (uint64_t)d << 32 | s;
- if (hashmap__find(mask, (void *)key, NULL))
+ if (hashmap__find(mask, (void *)key, NULL)) {
*skip = true;
- else
+ free(key);
+ } else
ret = hashmap__add(mask, (void *)key, (void *)1);
return ret;
@@ -355,14 +356,14 @@ static int check_per_pkg(struct evsel *counter,
static int
process_counter_values(struct perf_stat_config *config, struct evsel *evsel,
- int cpu, int thread,
+ int cpu_map_idx, int thread,
struct perf_counts_values *count)
{
struct perf_counts_values *aggr = &evsel->counts->aggr;
static struct perf_counts_values zero;
bool skip = false;
- if (check_per_pkg(evsel, count, cpu, &skip)) {
+ if (check_per_pkg(evsel, count, cpu_map_idx, &skip)) {
pr_err("failed to read per-pkg counter\n");
return -1;
}
@@ -378,11 +379,11 @@ process_counter_values(struct perf_stat_config *config, struct evsel *evsel,
case AGGR_NODE:
case AGGR_NONE:
if (!evsel->snapshot)
- evsel__compute_deltas(evsel, cpu, thread, count);
+ evsel__compute_deltas(evsel, cpu_map_idx, thread, count);
perf_counts_values__scale(count, config->scale, NULL);
if ((config->aggr_mode == AGGR_NONE) && (!evsel->percore)) {
perf_stat__update_shadow_stats(evsel, count->val,
- cpu, &rt_stat);
+ cpu_map_idx, &rt_stat);
}
if (config->aggr_mode == AGGR_THREAD) {
@@ -411,15 +412,15 @@ static int process_counter_maps(struct perf_stat_config *config,
{
int nthreads = perf_thread_map__nr(counter->core.threads);
int ncpus = evsel__nr_cpus(counter);
- int cpu, thread;
+ int idx, thread;
if (counter->core.system_wide)
nthreads = 1;
for (thread = 0; thread < nthreads; thread++) {
- for (cpu = 0; cpu < ncpus; cpu++) {
- if (process_counter_values(config, counter, cpu, thread,
- perf_counts(counter->counts, cpu, thread)))
+ for (idx = 0; idx < ncpus; idx++) {
+ if (process_counter_values(config, counter, idx, thread,
+ perf_counts(counter->counts, idx, thread)))
return -1;
}
}
@@ -531,7 +532,7 @@ size_t perf_event__fprintf_stat_config(union perf_event *event, FILE *fp)
int create_perf_stat_counter(struct evsel *evsel,
struct perf_stat_config *config,
struct target *target,
- int cpu)
+ int cpu_map_idx)
{
struct perf_event_attr *attr = &evsel->core.attr;
struct evsel *leader = evsel__leader(evsel);
@@ -585,7 +586,7 @@ int create_perf_stat_counter(struct evsel *evsel,
}
if (target__has_cpu(target) && !target__has_per_thread(target))
- return evsel__open_per_cpu(evsel, evsel__cpus(evsel), cpu);
+ return evsel__open_per_cpu(evsel, evsel__cpus(evsel), cpu_map_idx);
return evsel__open_per_thread(evsel, evsel->core.threads);
}
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 32c8527de347..335d19cc3063 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -108,8 +108,7 @@ struct runtime_stat {
struct rblist value_list;
};
-typedef struct aggr_cpu_id (*aggr_get_id_t)(struct perf_stat_config *config,
- struct perf_cpu_map *m, int cpu);
+typedef struct aggr_cpu_id (*aggr_get_id_t)(struct perf_stat_config *config, struct perf_cpu cpu);
struct perf_stat_config {
enum aggr_mode aggr_mode;
@@ -209,7 +208,7 @@ void perf_stat__init_shadow_stats(void);
void perf_stat__reset_shadow_stats(void);
void perf_stat__reset_shadow_per_stat(struct runtime_stat *st);
void perf_stat__update_shadow_stats(struct evsel *counter, u64 count,
- int cpu, struct runtime_stat *st);
+ int cpu_map_idx, struct runtime_stat *st);
struct perf_stat_output_ctx {
void *ctx;
print_metric_t print_metric;
@@ -249,10 +248,10 @@ size_t perf_event__fprintf_stat_config(union perf_event *event, FILE *fp);
int create_perf_stat_counter(struct evsel *evsel,
struct perf_stat_config *config,
struct target *target,
- int cpu);
+ int cpu_map_idx);
void evlist__print_counters(struct evlist *evlist, struct perf_stat_config *config,
struct target *_target, struct timespec *ts, int argc, const char **argv);
struct metric_expr;
-double test_generic_metric(struct metric_expr *mexp, int cpu, struct runtime_stat *st);
+double test_generic_metric(struct metric_expr *mexp, int cpu_map_idx, struct runtime_stat *st);
#endif
diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c
index 96f941e01681..1e0c731fc539 100644
--- a/tools/perf/util/svghelper.c
+++ b/tools/perf/util/svghelper.c
@@ -728,20 +728,20 @@ static int str_to_bitmap(char *s, cpumask_t *b, int nr_cpus)
int i;
int ret = 0;
struct perf_cpu_map *m;
- int c;
+ struct perf_cpu c;
m = perf_cpu_map__new(s);
if (!m)
return -1;
- for (i = 0; i < m->nr; i++) {
- c = m->map[i];
- if (c >= nr_cpus) {
+ for (i = 0; i < perf_cpu_map__nr(m); i++) {
+ c = perf_cpu_map__cpu(m, i);
+ if (c.cpu >= nr_cpus) {
ret = -1;
break;
}
- set_bit(c, cpumask_bits(b));
+ set_bit(c.cpu, cpumask_bits(b));
}
perf_cpu_map__put(m);
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index b2ed3140a1fa..dfde9eada224 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -231,7 +231,7 @@ void symbols__fixup_end(struct rb_root_cached *symbols)
prev = curr;
curr = rb_entry(nd, struct symbol, rb_node);
- if (prev->end == prev->start && prev->end != curr->start)
+ if (prev->end == prev->start || prev->end != curr->start)
arch__symbols__fixup_end(prev, curr);
}
diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c
index 198982109f0f..b654de0841f8 100644
--- a/tools/perf/util/synthetic-events.c
+++ b/tools/perf/util/synthetic-events.c
@@ -1186,12 +1186,12 @@ int perf_event__synthesize_thread_map2(struct perf_tool *tool,
static void synthesize_cpus(struct cpu_map_entries *cpus,
struct perf_cpu_map *map)
{
- int i;
+ int i, map_nr = perf_cpu_map__nr(map);
- cpus->nr = map->nr;
+ cpus->nr = map_nr;
- for (i = 0; i < map->nr; i++)
- cpus->cpu[i] = map->map[i];
+ for (i = 0; i < map_nr; i++)
+ cpus->cpu[i] = perf_cpu_map__cpu(map, i).cpu;
}
static void synthesize_mask(struct perf_record_record_cpu_map *mask,
@@ -1202,13 +1202,13 @@ static void synthesize_mask(struct perf_record_record_cpu_map *mask,
mask->nr = BITS_TO_LONGS(max);
mask->long_size = sizeof(long);
- for (i = 0; i < map->nr; i++)
- set_bit(map->map[i], mask->mask);
+ for (i = 0; i < perf_cpu_map__nr(map); i++)
+ set_bit(perf_cpu_map__cpu(map, i).cpu, mask->mask);
}
static size_t cpus_size(struct perf_cpu_map *map)
{
- return sizeof(struct cpu_map_entries) + map->nr * sizeof(u16);
+ return sizeof(struct cpu_map_entries) + perf_cpu_map__nr(map) * sizeof(u16);
}
static size_t mask_size(struct perf_cpu_map *map, int *max)
@@ -1217,9 +1217,9 @@ static size_t mask_size(struct perf_cpu_map *map, int *max)
*max = 0;
- for (i = 0; i < map->nr; i++) {
+ for (i = 0; i < perf_cpu_map__nr(map); i++) {
/* bit position of the cpu is + 1 */
- int bit = map->map[i] + 1;
+ int bit = perf_cpu_map__cpu(map, i).cpu + 1;
if (bit > *max)
*max = bit;
@@ -1354,7 +1354,7 @@ int perf_event__synthesize_stat_config(struct perf_tool *tool,
}
int perf_event__synthesize_stat(struct perf_tool *tool,
- u32 cpu, u32 thread, u64 id,
+ struct perf_cpu cpu, u32 thread, u64 id,
struct perf_counts_values *count,
perf_event__handler_t process,
struct machine *machine)
@@ -1366,7 +1366,7 @@ int perf_event__synthesize_stat(struct perf_tool *tool,
event.header.misc = 0;
event.id = id;
- event.cpu = cpu;
+ event.cpu = cpu.cpu;
event.thread = thread;
event.val = count->val;
event.ena = count->ena;
@@ -1763,7 +1763,7 @@ int perf_event__synthesize_id_index(struct perf_tool *tool, perf_event__handler_
}
e->idx = sid->idx;
- e->cpu = sid->cpu;
+ e->cpu = sid->cpu.cpu;
e->tid = sid->tid;
}
}
@@ -1784,6 +1784,25 @@ int __machine__synthesize_threads(struct machine *machine, struct perf_tool *too
perf_event__handler_t process, bool needs_mmap,
bool data_mmap, unsigned int nr_threads_synthesize)
{
+ /*
+ * When perf runs in non-root PID namespace, and the namespace's proc FS
+ * is not mounted, nsinfo__is_in_root_namespace() returns false.
+ * In this case, the proc FS is coming for the parent namespace, thus
+ * perf tool will wrongly gather process info from its parent PID
+ * namespace.
+ *
+ * To avoid the confusion that the perf tool runs in a child PID
+ * namespace but it synthesizes thread info from its parent PID
+ * namespace, returns failure with warning.
+ */
+ if (!nsinfo__is_in_root_namespace()) {
+ pr_err("Perf runs in non-root PID namespace but it tries to ");
+ pr_err("gather process info from its parent PID namespace.\n");
+ pr_err("Please mount the proc file system properly, e.g. ");
+ pr_err("add the option '--mount-proc' for unshare command.\n");
+ return -EPERM;
+ }
+
if (target__has_task(target))
return perf_event__synthesize_thread_map(tool, threads, process, machine,
needs_mmap, data_mmap);
diff --git a/tools/perf/util/synthetic-events.h b/tools/perf/util/synthetic-events.h
index c931433bacbf..78a0450db164 100644
--- a/tools/perf/util/synthetic-events.h
+++ b/tools/perf/util/synthetic-events.h
@@ -6,6 +6,7 @@
#include <sys/types.h> // pid_t
#include <linux/compiler.h>
#include <linux/types.h>
+#include <perf/cpumap.h>
struct auxtrace_record;
struct dso;
@@ -63,7 +64,7 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_fo
int perf_event__synthesize_stat_config(struct perf_tool *tool, struct perf_stat_config *config, perf_event__handler_t process, struct machine *machine);
int perf_event__synthesize_stat_events(struct perf_stat_config *config, struct perf_tool *tool, struct evlist *evlist, perf_event__handler_t process, bool attrs);
int perf_event__synthesize_stat_round(struct perf_tool *tool, u64 time, u64 type, perf_event__handler_t process, struct machine *machine);
-int perf_event__synthesize_stat(struct perf_tool *tool, u32 cpu, u32 thread, u64 id, struct perf_counts_values *count, perf_event__handler_t process, struct machine *machine);
+int perf_event__synthesize_stat(struct perf_tool *tool, struct perf_cpu cpu, u32 thread, u64 id, struct perf_counts_values *count, perf_event__handler_t process, struct machine *machine);
int perf_event__synthesize_thread_map2(struct perf_tool *tool, struct perf_thread_map *threads, perf_event__handler_t process, struct machine *machine);
int perf_event__synthesize_thread_map(struct perf_tool *tool, struct perf_thread_map *threads, perf_event__handler_t process, struct machine *machine, bool needs_mmap, bool mmap_data);
int perf_event__synthesize_threads(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine, bool needs_mmap, bool mmap_data, unsigned int nr_threads_synthesize);
diff --git a/tools/perf/util/top.c b/tools/perf/util/top.c
index 27945eeb0cb5..c1ebfc5d2e0c 100644
--- a/tools/perf/util/top.c
+++ b/tools/perf/util/top.c
@@ -95,15 +95,15 @@ size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size)
if (target->cpu_list)
ret += SNPRINTF(bf + ret, size - ret, ", CPU%s: %s)",
- top->evlist->core.cpus->nr > 1 ? "s" : "",
+ perf_cpu_map__nr(top->evlist->core.cpus) > 1 ? "s" : "",
target->cpu_list);
else {
if (target->tid)
ret += SNPRINTF(bf + ret, size - ret, ")");
else
ret += SNPRINTF(bf + ret, size - ret, ", %d CPU%s)",
- top->evlist->core.cpus->nr,
- top->evlist->core.cpus->nr > 1 ? "s" : "");
+ perf_cpu_map__nr(top->evlist->core.cpus),
+ perf_cpu_map__nr(top->evlist->core.cpus) > 1 ? "s" : "");
}
perf_top__reset_sample_counters(top);
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index df3c4671be72..fb4f6616b5fa 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -416,3 +416,18 @@ char *perf_exe(char *buf, int len)
}
return strcpy(buf, "perf");
}
+
+void perf_debuginfod_setup(struct perf_debuginfod *di)
+{
+ /*
+ * By default '!di->set' we clear DEBUGINFOD_URLS, so debuginfod
+ * processing is not triggered, otherwise we set it to 'di->urls'
+ * value. If 'di->urls' is "system" we keep DEBUGINFOD_URLS value.
+ */
+ if (!di->set)
+ setenv("DEBUGINFOD_URLS", "", 1);
+ else if (di->urls && strcmp(di->urls, "system"))
+ setenv("DEBUGINFOD_URLS", di->urls, 1);
+
+ pr_debug("DEBUGINFOD_URLS=%s\n", getenv("DEBUGINFOD_URLS"));
+}
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 9f0d36ba77f2..7b625cbd2dd8 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -11,6 +11,9 @@
#include <stddef.h>
#include <linux/compiler.h>
#include <sys/types.h>
+#ifndef __cplusplus
+#include <internal/cpumap.h>
+#endif
/* General helper functions */
void usage(const char *err) __noreturn;
@@ -66,6 +69,12 @@ extern bool test_attr__enabled;
void test_attr__ready(void);
void test_attr__init(void);
struct perf_event_attr;
-void test_attr__open(struct perf_event_attr *attr, pid_t pid, int cpu,
+void test_attr__open(struct perf_event_attr *attr, pid_t pid, struct perf_cpu cpu,
int fd, int group_fd, unsigned long flags);
+
+struct perf_debuginfod {
+ const char *urls;
+ bool set;
+};
+void perf_debuginfod_setup(struct perf_debuginfod *di);
#endif /* GIT_COMPAT_UTIL_H */
diff --git a/tools/power/acpi/.gitignore b/tools/power/acpi/.gitignore
index 0b319fc8bb17..eada0297ef88 100644
--- a/tools/power/acpi/.gitignore
+++ b/tools/power/acpi/.gitignore
@@ -2,4 +2,5 @@
/acpidbg
/acpidump
/ec
+/pfrut
/include/
diff --git a/tools/power/acpi/Makefile b/tools/power/acpi/Makefile
index a249c50ebf55..5ff1d9c864d0 100644
--- a/tools/power/acpi/Makefile
+++ b/tools/power/acpi/Makefile
@@ -9,18 +9,18 @@ include ../../scripts/Makefile.include
.NOTPARALLEL:
-all: acpidbg acpidump ec
-clean: acpidbg_clean acpidump_clean ec_clean
-install: acpidbg_install acpidump_install ec_install
-uninstall: acpidbg_uninstall acpidump_uninstall ec_uninstall
+all: acpidbg acpidump ec pfrut
+clean: acpidbg_clean acpidump_clean ec_clean pfrut_clean
+install: acpidbg_install acpidump_install ec_install pfrut_install
+uninstall: acpidbg_uninstall acpidump_uninstall ec_uninstall pfrut_uninstall
-acpidbg acpidump ec: FORCE
+acpidbg acpidump ec pfrut: FORCE
$(call descend,tools/$@,all)
-acpidbg_clean acpidump_clean ec_clean:
+acpidbg_clean acpidump_clean ec_clean pfrut_clean:
$(call descend,tools/$(@:_clean=),clean)
-acpidbg_install acpidump_install ec_install:
+acpidbg_install acpidump_install ec_install pfrut_install:
$(call descend,tools/$(@:_install=),install)
-acpidbg_uninstall acpidump_uninstall ec_uninstall:
+acpidbg_uninstall acpidump_uninstall ec_uninstall pfrut_uninstall:
$(call descend,tools/$(@:_uninstall=),uninstall)
.PHONY: FORCE
diff --git a/tools/power/acpi/Makefile.rules b/tools/power/acpi/Makefile.rules
index 1d7616f5d0ae..b71aada77688 100644
--- a/tools/power/acpi/Makefile.rules
+++ b/tools/power/acpi/Makefile.rules
@@ -9,7 +9,7 @@ objdir := $(OUTPUT)tools/$(TOOL)/
toolobjs := $(addprefix $(objdir),$(TOOL_OBJS))
$(OUTPUT)$(TOOL): $(toolobjs) FORCE
$(ECHO) " LD " $(subst $(OUTPUT),,$@)
- $(QUIET) $(LD) $(CFLAGS) $(LDFLAGS) $(toolobjs) -L$(OUTPUT) -o $@
+ $(QUIET) $(LD) $(CFLAGS) $(toolobjs) $(LDFLAGS) -L$(OUTPUT) -o $@
$(ECHO) " STRIP " $(subst $(OUTPUT),,$@)
$(QUIET) $(STRIPCMD) $@
diff --git a/tools/power/acpi/man/pfrut.8 b/tools/power/acpi/man/pfrut.8
new file mode 100644
index 000000000000..3db574770e8d
--- /dev/null
+++ b/tools/power/acpi/man/pfrut.8
@@ -0,0 +1,137 @@
+.TH "PFRUT" "8" "October 2021" "pfrut 1.0" ""
+.hy
+.SH Name
+.PP
+pfrut \- Platform Firmware Runtime Update and Telemetry tool
+.SH SYNOPSIS
+.PP
+\f[B]pfrut\f[R] [\f[I]Options\f[R]]
+.SH DESCRIPTION
+.PP
+The PFRUT(Platform Firmware Runtime Update and Telemetry) kernel interface is designed
+to
+.PD 0
+.P
+.PD
+interact with the platform firmware interface defined in the
+.PD 0
+.P
+.PD
+Management Mode Firmware Runtime
+Update (https://uefi.org/sites/default/files/resources/Intel_MM_OS_Interface_Spec_Rev100.pdf)
+.PD 0
+.P
+.PD
+\f[B]pfrut\f[R] is the tool to interact with the kernel interface.
+.PD 0
+.P
+.PD
+.SH OPTIONS
+.TP
+.B \f[B]\-h\f[R], \f[B]\-\-help\f[R]
+Display helper information.
+.TP
+.B \f[B]\-l\f[R], \f[B]\-\-load\f[R]
+Load the capsule file into the system.
+To be more specific, the capsule file will be copied to the
+communication buffer.
+.TP
+.B \f[B]\-s\f[R], \f[B]\-\-stage\f[R]
+Stage the capsule image from communication buffer into Management Mode
+and perform authentication.
+.TP
+.B \f[B]\-a\f[R], \f[B]\-\-activate\f[R]
+Activate a previous staged capsule image.
+.TP
+.B \f[B]\-u\f[R], \f[B]\-\-update\f[R]
+Perform both stage and activation actions.
+.TP
+.B \f[B]\-q\f[R], \f[B]\-\-query\f[R]
+Query the update capability.
+.TP
+.B \f[B]\-d\f[R], \f[B]\-\-setrev\f[R]
+Set the revision ID of code injection/driver update.
+.TP
+.B \f[B]\-D\f[R], \f[B]\-\-setrevlog\f[R]
+Set the revision ID of telemetry.
+.TP
+.B \f[B]\-G\f[R], \f[B]\-\-getloginfo\f[R]
+Get telemetry log information and print it out.
+.TP
+.B \f[B]\-T\f[R], \f[B]\-\-type\f[R]
+Set the telemetry log data type.
+.TP
+.B \f[B]\-L\f[R], \f[B]\-\-level\f[R]
+Set the telemetry log level.
+.TP
+.B \f[B]\-R\f[R], \f[B]\-\-read\f[R]
+Read all the telemetry data and print it out.
+.SH EXAMPLES
+.PP
+\f[B]pfrut \-G\f[R]
+.PP
+log_level:4
+.PD 0
+.P
+.PD
+log_type:0
+.PD 0
+.P
+.PD
+log_revid:2
+.PD 0
+.P
+.PD
+max_data_size:65536
+.PD 0
+.P
+.PD
+chunk1_size:0
+.PD 0
+.P
+.PD
+chunk2_size:1401
+.PD 0
+.P
+.PD
+rollover_cnt:0
+.PD 0
+.P
+.PD
+reset_cnt:4
+.PP
+\f[B]pfru \-q\f[R]
+.PP
+code injection image type:794bf8b2\-6e7b\-454e\-885f\-3fb9bb185402
+.PD 0
+.P
+.PD
+fw_version:0
+.PD 0
+.P
+.PD
+code_rt_version:1
+.PD 0
+.P
+.PD
+driver update image type:0e5f0b14\-f849\-7945\-ad81\-bc7b6d2bb245
+.PD 0
+.P
+.PD
+drv_rt_version:0
+.PD 0
+.P
+.PD
+drv_svn:0
+.PD 0
+.P
+.PD
+platform id:39214663\-b1a8\-4eaa\-9024\-f2bb53ea4723
+.PD 0
+.P
+.PD
+oem id:a36db54f\-ea2a\-e14e\-b7c4\-b5780e51ba3d
+.PP
+\f[B]pfrut \-l yours.cap \-u \-T 1 \-L 4\f[R]
+.SH AUTHORS
+Chen Yu.
diff --git a/tools/power/acpi/tools/pfrut/Makefile b/tools/power/acpi/tools/pfrut/Makefile
new file mode 100644
index 000000000000..61c1a96fd433
--- /dev/null
+++ b/tools/power/acpi/tools/pfrut/Makefile
@@ -0,0 +1,23 @@
+# SPDX-License-Identifier: GPL-2.0+
+
+include ../../Makefile.config
+
+TOOL = pfrut
+EXTRA_INSTALL = install-man
+EXTRA_UNINSTALL = uninstall-man
+
+CFLAGS += -Wall -O2
+CFLAGS += -DPFRUT_HEADER='"../../../../../include/uapi/linux/pfrut.h"'
+LDFLAGS += -luuid
+
+TOOL_OBJS = \
+ pfrut.o
+
+include ../../Makefile.rules
+
+install-man: $(srctree)/man/pfrut.8
+ $(ECHO) " INST " pfrut.8
+ $(QUIET) $(INSTALL_DATA) -D $< $(DESTDIR)$(mandir)/man8/pfrut.8
+uninstall-man:
+ $(ECHO) " UNINST " pfrut.8
+ $(QUIET) rm -f $(DESTDIR)$(mandir)/man8/pfrut.8
diff --git a/tools/power/acpi/tools/pfrut/pfrut.c b/tools/power/acpi/tools/pfrut/pfrut.c
new file mode 100644
index 000000000000..d79c335594b2
--- /dev/null
+++ b/tools/power/acpi/tools/pfrut/pfrut.c
@@ -0,0 +1,424 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Platform Firmware Runtime Update tool to do Management
+ * Mode code injection/driver update and telemetry retrieval.
+ *
+ * This tool uses the interfaces provided by pfr_update and
+ * pfr_telemetry drivers. These interfaces are exposed via
+ * /dev/pfr_update and /dev/pfr_telemetry. Write operation
+ * on the /dev/pfr_update is to load the EFI capsule into
+ * kernel space. Mmap/read operations on /dev/pfr_telemetry
+ * could be used to read the telemetry data to user space.
+ */
+#define _GNU_SOURCE
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <unistd.h>
+#include <getopt.h>
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+#include <uuid/uuid.h>
+#include PFRUT_HEADER
+
+char *capsule_name;
+int action, query_cap, log_type, log_level, log_read, log_getinfo,
+ revid, log_revid;
+int set_log_level, set_log_type,
+ set_revid, set_log_revid;
+
+char *progname;
+
+#define LOG_ERR 0
+#define LOG_WARN 1
+#define LOG_INFO 2
+#define LOG_VERB 4
+#define LOG_EXEC_IDX 0
+#define LOG_HISTORY_IDX 1
+#define REVID_1 1
+#define REVID_2 2
+
+static int valid_log_level(int level)
+{
+ return level == LOG_ERR || level == LOG_WARN ||
+ level == LOG_INFO || level == LOG_VERB;
+}
+
+static int valid_log_type(int type)
+{
+ return type == LOG_EXEC_IDX || type == LOG_HISTORY_IDX;
+}
+
+static inline int valid_log_revid(int id)
+{
+ return id == REVID_1 || id == REVID_2;
+}
+
+static void help(void)
+{
+ fprintf(stderr,
+ "usage: %s [OPTIONS]\n"
+ " code injection:\n"
+ " -l, --load\n"
+ " -s, --stage\n"
+ " -a, --activate\n"
+ " -u, --update [stage and activate]\n"
+ " -q, --query\n"
+ " -d, --revid update\n"
+ " telemetry:\n"
+ " -G, --getloginfo\n"
+ " -T, --type(0:execution, 1:history)\n"
+ " -L, --level(0, 1, 2, 4)\n"
+ " -R, --read\n"
+ " -D, --revid log\n",
+ progname);
+}
+
+char *option_string = "l:sauqd:GT:L:RD:h";
+static struct option long_options[] = {
+ {"load", required_argument, 0, 'l'},
+ {"stage", no_argument, 0, 's'},
+ {"activate", no_argument, 0, 'a'},
+ {"update", no_argument, 0, 'u'},
+ {"query", no_argument, 0, 'q'},
+ {"getloginfo", no_argument, 0, 'G'},
+ {"type", required_argument, 0, 'T'},
+ {"level", required_argument, 0, 'L'},
+ {"read", no_argument, 0, 'R'},
+ {"setrev", required_argument, 0, 'd'},
+ {"setrevlog", required_argument, 0, 'D'},
+ {"help", no_argument, 0, 'h'},
+ {}
+};
+
+static void parse_options(int argc, char **argv)
+{
+ int option_index = 0;
+ char *pathname;
+ int opt;
+
+ pathname = strdup(argv[0]);
+ progname = basename(pathname);
+
+ while ((opt = getopt_long_only(argc, argv, option_string,
+ long_options, &option_index)) != -1) {
+ switch (opt) {
+ case 'l':
+ capsule_name = optarg;
+ break;
+ case 's':
+ action = 1;
+ break;
+ case 'a':
+ action = 2;
+ break;
+ case 'u':
+ action = 3;
+ break;
+ case 'q':
+ query_cap = 1;
+ break;
+ case 'G':
+ log_getinfo = 1;
+ break;
+ case 'T':
+ log_type = atoi(optarg);
+ set_log_type = 1;
+ break;
+ case 'L':
+ log_level = atoi(optarg);
+ set_log_level = 1;
+ break;
+ case 'R':
+ log_read = 1;
+ break;
+ case 'd':
+ revid = atoi(optarg);
+ set_revid = 1;
+ break;
+ case 'D':
+ log_revid = atoi(optarg);
+ set_log_revid = 1;
+ break;
+ case 'h':
+ help();
+ exit(0);
+ default:
+ break;
+ }
+ }
+}
+
+void print_cap(struct pfru_update_cap_info *cap)
+{
+ char *uuid;
+
+ uuid = malloc(37);
+ if (!uuid) {
+ perror("Can not allocate uuid buffer\n");
+ exit(1);
+ }
+
+ uuid_unparse(cap->code_type, uuid);
+ printf("code injection image type:%s\n", uuid);
+ printf("fw_version:%d\n", cap->fw_version);
+ printf("code_rt_version:%d\n", cap->code_rt_version);
+
+ uuid_unparse(cap->drv_type, uuid);
+ printf("driver update image type:%s\n", uuid);
+ printf("drv_rt_version:%d\n", cap->drv_rt_version);
+ printf("drv_svn:%d\n", cap->drv_svn);
+
+ uuid_unparse(cap->platform_id, uuid);
+ printf("platform id:%s\n", uuid);
+ uuid_unparse(cap->oem_id, uuid);
+ printf("oem id:%s\n", uuid);
+ printf("oem information length:%d\n", cap->oem_info_len);
+
+ free(uuid);
+}
+
+int main(int argc, char *argv[])
+{
+ int fd_update, fd_update_log, fd_capsule;
+ struct pfrt_log_data_info data_info;
+ struct pfrt_log_info info;
+ struct pfru_update_cap_info cap;
+ void *addr_map_capsule;
+ struct stat st;
+ char *log_buf;
+ int ret = 0;
+
+ if (getuid() != 0) {
+ printf("Please run the tool as root - Exiting.\n");
+ return 1;
+ }
+
+ parse_options(argc, argv);
+
+ fd_update = open("/dev/acpi_pfr_update0", O_RDWR);
+ if (fd_update < 0) {
+ printf("PFRU device not supported - Quit...\n");
+ return 1;
+ }
+
+ fd_update_log = open("/dev/acpi_pfr_telemetry0", O_RDWR);
+ if (fd_update_log < 0) {
+ printf("PFRT device not supported - Quit...\n");
+ return 1;
+ }
+
+ if (query_cap) {
+ ret = ioctl(fd_update, PFRU_IOC_QUERY_CAP, &cap);
+ if (ret)
+ perror("Query Update Capability info failed.");
+ else
+ print_cap(&cap);
+
+ close(fd_update);
+ close(fd_update_log);
+
+ return ret;
+ }
+
+ if (log_getinfo) {
+ ret = ioctl(fd_update_log, PFRT_LOG_IOC_GET_DATA_INFO, &data_info);
+ if (ret) {
+ perror("Get telemetry data info failed.");
+ close(fd_update);
+ close(fd_update_log);
+
+ return 1;
+ }
+
+ ret = ioctl(fd_update_log, PFRT_LOG_IOC_GET_INFO, &info);
+ if (ret) {
+ perror("Get telemetry info failed.");
+ close(fd_update);
+ close(fd_update_log);
+
+ return 1;
+ }
+
+ printf("log_level:%d\n", info.log_level);
+ printf("log_type:%d\n", info.log_type);
+ printf("log_revid:%d\n", info.log_revid);
+ printf("max_data_size:%d\n", data_info.max_data_size);
+ printf("chunk1_size:%d\n", data_info.chunk1_size);
+ printf("chunk2_size:%d\n", data_info.chunk2_size);
+ printf("rollover_cnt:%d\n", data_info.rollover_cnt);
+ printf("reset_cnt:%d\n", data_info.reset_cnt);
+
+ return 0;
+ }
+
+ info.log_level = -1;
+ info.log_type = -1;
+ info.log_revid = -1;
+
+ if (set_log_level) {
+ if (!valid_log_level(log_level)) {
+ printf("Invalid log level %d\n",
+ log_level);
+ } else {
+ info.log_level = log_level;
+ }
+ }
+
+ if (set_log_type) {
+ if (!valid_log_type(log_type)) {
+ printf("Invalid log type %d\n",
+ log_type);
+ } else {
+ info.log_type = log_type;
+ }
+ }
+
+ if (set_log_revid) {
+ if (!valid_log_revid(log_revid)) {
+ printf("Invalid log revid %d, unchanged.\n",
+ log_revid);
+ } else {
+ info.log_revid = log_revid;
+ }
+ }
+
+ ret = ioctl(fd_update_log, PFRT_LOG_IOC_SET_INFO, &info);
+ if (ret) {
+ perror("Log information set failed.(log_level, log_type, log_revid)");
+ close(fd_update);
+ close(fd_update_log);
+
+ return 1;
+ }
+
+ if (set_revid) {
+ ret = ioctl(fd_update, PFRU_IOC_SET_REV, &revid);
+ if (ret) {
+ perror("pfru update revid set failed");
+ close(fd_update);
+ close(fd_update_log);
+
+ return 1;
+ }
+
+ printf("pfru update revid set to %d\n", revid);
+ }
+
+ if (capsule_name) {
+ fd_capsule = open(capsule_name, O_RDONLY);
+ if (fd_capsule < 0) {
+ perror("Can not open capsule file...");
+ close(fd_update);
+ close(fd_update_log);
+
+ return 1;
+ }
+
+ if (fstat(fd_capsule, &st) < 0) {
+ perror("Can not fstat capsule file...");
+ close(fd_capsule);
+ close(fd_update);
+ close(fd_update_log);
+
+ return 1;
+ }
+
+ addr_map_capsule = mmap(NULL, st.st_size, PROT_READ, MAP_SHARED,
+ fd_capsule, 0);
+ if (addr_map_capsule == MAP_FAILED) {
+ perror("Failed to mmap capsule file.");
+ close(fd_capsule);
+ close(fd_update);
+ close(fd_update_log);
+
+ return 1;
+ }
+
+ ret = write(fd_update, (char *)addr_map_capsule, st.st_size);
+ printf("Load %d bytes of capsule file into the system\n",
+ ret);
+
+ if (ret == -1) {
+ perror("Failed to load capsule file");
+ close(fd_capsule);
+ close(fd_update);
+ close(fd_update_log);
+
+ return 1;
+ }
+
+ munmap(addr_map_capsule, st.st_size);
+ close(fd_capsule);
+ printf("Load done.\n");
+ }
+
+ if (action) {
+ if (action == 1) {
+ ret = ioctl(fd_update, PFRU_IOC_STAGE, NULL);
+ } else if (action == 2) {
+ ret = ioctl(fd_update, PFRU_IOC_ACTIVATE, NULL);
+ } else if (action == 3) {
+ ret = ioctl(fd_update, PFRU_IOC_STAGE_ACTIVATE, NULL);
+ } else {
+ close(fd_update);
+ close(fd_update_log);
+
+ return 1;
+ }
+ printf("Update finished, return %d\n", ret);
+ }
+
+ close(fd_update);
+
+ if (log_read) {
+ void *p_mmap;
+ int max_data_sz;
+
+ ret = ioctl(fd_update_log, PFRT_LOG_IOC_GET_DATA_INFO, &data_info);
+ if (ret) {
+ perror("Get telemetry data info failed.");
+ close(fd_update_log);
+
+ return 1;
+ }
+
+ max_data_sz = data_info.max_data_size;
+ if (!max_data_sz) {
+ printf("No telemetry data available.\n");
+ close(fd_update_log);
+
+ return 1;
+ }
+
+ log_buf = malloc(max_data_sz + 1);
+ if (!log_buf) {
+ perror("log_buf allocate failed.");
+ close(fd_update_log);
+
+ return 1;
+ }
+
+ p_mmap = mmap(NULL, max_data_sz, PROT_READ, MAP_SHARED, fd_update_log, 0);
+ if (p_mmap == MAP_FAILED) {
+ perror("mmap error.");
+ close(fd_update_log);
+
+ return 1;
+ }
+
+ memcpy(log_buf, p_mmap, max_data_sz);
+ log_buf[max_data_sz] = '\0';
+ printf("%s\n", log_buf);
+ free(log_buf);
+
+ munmap(p_mmap, max_data_sz);
+ }
+
+ close(fd_update_log);
+
+ return 0;
+}
diff --git a/tools/power/cpupower/Makefile b/tools/power/cpupower/Makefile
index 3b1594447f29..e9b6de314654 100644
--- a/tools/power/cpupower/Makefile
+++ b/tools/power/cpupower/Makefile
@@ -143,9 +143,9 @@ UTIL_HEADERS = utils/helpers/helpers.h utils/idle_monitor/cpupower-monitor.h \
utils/helpers/bitmask.h \
utils/idle_monitor/idle_monitors.h utils/idle_monitor/idle_monitors.def
-LIB_HEADERS = lib/cpufreq.h lib/cpupower.h lib/cpuidle.h
-LIB_SRC = lib/cpufreq.c lib/cpupower.c lib/cpuidle.c
-LIB_OBJS = lib/cpufreq.o lib/cpupower.o lib/cpuidle.o
+LIB_HEADERS = lib/cpufreq.h lib/cpupower.h lib/cpuidle.h lib/acpi_cppc.h
+LIB_SRC = lib/cpufreq.c lib/cpupower.c lib/cpuidle.c lib/acpi_cppc.c
+LIB_OBJS = lib/cpufreq.o lib/cpupower.o lib/cpuidle.o lib/acpi_cppc.o
LIB_OBJS := $(addprefix $(OUTPUT),$(LIB_OBJS))
override CFLAGS += -pipe
diff --git a/tools/power/cpupower/ToDo b/tools/power/cpupower/TODO
index b196a139a3e4..b196a139a3e4 100644
--- a/tools/power/cpupower/ToDo
+++ b/tools/power/cpupower/TODO
diff --git a/tools/power/cpupower/lib/acpi_cppc.c b/tools/power/cpupower/lib/acpi_cppc.c
new file mode 100644
index 000000000000..c401ac331e9f
--- /dev/null
+++ b/tools/power/cpupower/lib/acpi_cppc.c
@@ -0,0 +1,59 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <stdio.h>
+#include <errno.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <unistd.h>
+
+#include "cpupower_intern.h"
+#include "acpi_cppc.h"
+
+/* ACPI CPPC sysfs access ***********************************************/
+
+static int acpi_cppc_read_file(unsigned int cpu, const char *fname,
+ char *buf, size_t buflen)
+{
+ char path[SYSFS_PATH_MAX];
+
+ snprintf(path, sizeof(path), PATH_TO_CPU "cpu%u/acpi_cppc/%s",
+ cpu, fname);
+ return cpupower_read_sysfs(path, buf, buflen);
+}
+
+static const char * const acpi_cppc_value_files[] = {
+ [HIGHEST_PERF] = "highest_perf",
+ [LOWEST_PERF] = "lowest_perf",
+ [NOMINAL_PERF] = "nominal_perf",
+ [LOWEST_NONLINEAR_PERF] = "lowest_nonlinear_perf",
+ [LOWEST_FREQ] = "lowest_freq",
+ [NOMINAL_FREQ] = "nominal_freq",
+ [REFERENCE_PERF] = "reference_perf",
+ [WRAPAROUND_TIME] = "wraparound_time"
+};
+
+unsigned long acpi_cppc_get_data(unsigned int cpu, enum acpi_cppc_value which)
+{
+ unsigned long long value;
+ unsigned int len;
+ char linebuf[MAX_LINE_LEN];
+ char *endp;
+
+ if (which >= MAX_CPPC_VALUE_FILES)
+ return 0;
+
+ len = acpi_cppc_read_file(cpu, acpi_cppc_value_files[which],
+ linebuf, sizeof(linebuf));
+ if (len == 0)
+ return 0;
+
+ value = strtoull(linebuf, &endp, 0);
+
+ if (endp == linebuf || errno == ERANGE)
+ return 0;
+
+ return value;
+}
diff --git a/tools/power/cpupower/lib/acpi_cppc.h b/tools/power/cpupower/lib/acpi_cppc.h
new file mode 100644
index 000000000000..85ca83080316
--- /dev/null
+++ b/tools/power/cpupower/lib/acpi_cppc.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef __ACPI_CPPC_H__
+#define __ACPI_CPPC_H__
+
+enum acpi_cppc_value {
+ HIGHEST_PERF,
+ LOWEST_PERF,
+ NOMINAL_PERF,
+ LOWEST_NONLINEAR_PERF,
+ LOWEST_FREQ,
+ NOMINAL_FREQ,
+ REFERENCE_PERF,
+ WRAPAROUND_TIME,
+ MAX_CPPC_VALUE_FILES
+};
+
+unsigned long acpi_cppc_get_data(unsigned int cpu,
+ enum acpi_cppc_value which);
+
+#endif /* _ACPI_CPPC_H */
diff --git a/tools/power/cpupower/lib/cpufreq.c b/tools/power/cpupower/lib/cpufreq.c
index c3b56db8b921..1516d23c17c9 100644
--- a/tools/power/cpupower/lib/cpufreq.c
+++ b/tools/power/cpupower/lib/cpufreq.c
@@ -83,20 +83,21 @@ static const char *cpufreq_value_files[MAX_CPUFREQ_VALUE_READ_FILES] = {
[STATS_NUM_TRANSITIONS] = "stats/total_trans"
};
-
-static unsigned long sysfs_cpufreq_get_one_value(unsigned int cpu,
- enum cpufreq_value which)
+unsigned long cpufreq_get_sysfs_value_from_table(unsigned int cpu,
+ const char **table,
+ unsigned int index,
+ unsigned int size)
{
unsigned long value;
unsigned int len;
char linebuf[MAX_LINE_LEN];
char *endp;
- if (which >= MAX_CPUFREQ_VALUE_READ_FILES)
+ if (!table || index >= size || !table[index])
return 0;
- len = sysfs_cpufreq_read_file(cpu, cpufreq_value_files[which],
- linebuf, sizeof(linebuf));
+ len = sysfs_cpufreq_read_file(cpu, table[index], linebuf,
+ sizeof(linebuf));
if (len == 0)
return 0;
@@ -109,6 +110,14 @@ static unsigned long sysfs_cpufreq_get_one_value(unsigned int cpu,
return value;
}
+static unsigned long sysfs_cpufreq_get_one_value(unsigned int cpu,
+ enum cpufreq_value which)
+{
+ return cpufreq_get_sysfs_value_from_table(cpu, cpufreq_value_files,
+ which,
+ MAX_CPUFREQ_VALUE_READ_FILES);
+}
+
/* read access to files which contain one string */
enum cpufreq_string {
@@ -124,7 +133,7 @@ static const char *cpufreq_string_files[MAX_CPUFREQ_STRING_FILES] = {
static char *sysfs_cpufreq_get_one_string(unsigned int cpu,
- enum cpufreq_string which)
+ enum cpufreq_string which)
{
char linebuf[MAX_LINE_LEN];
char *result;
diff --git a/tools/power/cpupower/lib/cpufreq.h b/tools/power/cpupower/lib/cpufreq.h
index 95f4fd9e2656..2f3c84035806 100644
--- a/tools/power/cpupower/lib/cpufreq.h
+++ b/tools/power/cpupower/lib/cpufreq.h
@@ -203,6 +203,18 @@ int cpufreq_modify_policy_governor(unsigned int cpu, char *governor);
int cpufreq_set_frequency(unsigned int cpu,
unsigned long target_frequency);
+/*
+ * get the sysfs value from specific table
+ *
+ * Read the value with the sysfs file name from specific table. Does
+ * only work if the cpufreq driver has the specific sysfs interfaces.
+ */
+
+unsigned long cpufreq_get_sysfs_value_from_table(unsigned int cpu,
+ const char **table,
+ unsigned int index,
+ unsigned int size);
+
#ifdef __cplusplus
}
#endif
diff --git a/tools/power/cpupower/man/cpupower-frequency-info.1 b/tools/power/cpupower/man/cpupower-frequency-info.1
index 6aa8d239dff9..dd545b499480 100644
--- a/tools/power/cpupower/man/cpupower-frequency-info.1
+++ b/tools/power/cpupower/man/cpupower-frequency-info.1
@@ -53,6 +53,9 @@ human\-readable output for the \-f, \-w, \-s and \-y parameters.
\fB\-n\fR \fB\-\-no-rounding\fR
Output frequencies and latencies without rounding off values.
.TP
+\fB\-c\fR \fB\-\-perf\fR
+Get performances and frequencies capabilities of CPPC, by reading it from hardware (only available on the hardware with CPPC).
+.TP
.SH "REMARKS"
.LP
By default only values of core zero are displayed. How to display settings of
diff --git a/tools/power/cpupower/man/cpupower-idle-set.1 b/tools/power/cpupower/man/cpupower-idle-set.1
index 21916cff7516..8cef3c71e19e 100644
--- a/tools/power/cpupower/man/cpupower-idle-set.1
+++ b/tools/power/cpupower/man/cpupower-idle-set.1
@@ -4,7 +4,7 @@
cpupower\-idle\-set \- Utility to set cpu idle state specific kernel options
.SH "SYNTAX"
.LP
-cpupower [ \-c cpulist ] idle\-info [\fIoptions\fP]
+cpupower [ \-c cpulist ] idle\-set [\fIoptions\fP]
.SH "DESCRIPTION"
.LP
The cpupower idle\-set subcommand allows to set cpu idle, also called cpu
diff --git a/tools/power/cpupower/utils/cpufreq-info.c b/tools/power/cpupower/utils/cpufreq-info.c
index f9895e31ff5a..0646f615fe2d 100644
--- a/tools/power/cpupower/utils/cpufreq-info.c
+++ b/tools/power/cpupower/utils/cpufreq-info.c
@@ -84,43 +84,6 @@ static void proc_cpufreq_output(void)
}
static int no_rounding;
-static void print_speed(unsigned long speed)
-{
- unsigned long tmp;
-
- if (no_rounding) {
- if (speed > 1000000)
- printf("%u.%06u GHz", ((unsigned int) speed/1000000),
- ((unsigned int) speed%1000000));
- else if (speed > 1000)
- printf("%u.%03u MHz", ((unsigned int) speed/1000),
- (unsigned int) (speed%1000));
- else
- printf("%lu kHz", speed);
- } else {
- if (speed > 1000000) {
- tmp = speed%10000;
- if (tmp >= 5000)
- speed += 10000;
- printf("%u.%02u GHz", ((unsigned int) speed/1000000),
- ((unsigned int) (speed%1000000)/10000));
- } else if (speed > 100000) {
- tmp = speed%1000;
- if (tmp >= 500)
- speed += 1000;
- printf("%u MHz", ((unsigned int) speed/1000));
- } else if (speed > 1000) {
- tmp = speed%100;
- if (tmp >= 50)
- speed += 100;
- printf("%u.%01u MHz", ((unsigned int) speed/1000),
- ((unsigned int) (speed%1000)/100));
- }
- }
-
- return;
-}
-
static void print_duration(unsigned long duration)
{
unsigned long tmp;
@@ -183,9 +146,12 @@ static int get_boost_mode_x86(unsigned int cpu)
printf(_(" Supported: %s\n"), support ? _("yes") : _("no"));
printf(_(" Active: %s\n"), active ? _("yes") : _("no"));
- if ((cpupower_cpu_info.vendor == X86_VENDOR_AMD &&
- cpupower_cpu_info.family >= 0x10) ||
- cpupower_cpu_info.vendor == X86_VENDOR_HYGON) {
+ if (cpupower_cpu_info.vendor == X86_VENDOR_AMD &&
+ cpupower_cpu_info.caps & CPUPOWER_CAP_AMD_PSTATE) {
+ return 0;
+ } else if ((cpupower_cpu_info.vendor == X86_VENDOR_AMD &&
+ cpupower_cpu_info.family >= 0x10) ||
+ cpupower_cpu_info.vendor == X86_VENDOR_HYGON) {
ret = decode_pstates(cpu, b_states, pstates, &pstate_no);
if (ret)
return ret;
@@ -254,11 +220,11 @@ static int get_boost_mode(unsigned int cpu)
if (freqs) {
printf(_(" boost frequency steps: "));
while (freqs->next) {
- print_speed(freqs->frequency);
+ print_speed(freqs->frequency, no_rounding);
printf(", ");
freqs = freqs->next;
}
- print_speed(freqs->frequency);
+ print_speed(freqs->frequency, no_rounding);
printf("\n");
cpufreq_put_available_frequencies(freqs);
}
@@ -277,7 +243,7 @@ static int get_freq_kernel(unsigned int cpu, unsigned int human)
return -EINVAL;
}
if (human) {
- print_speed(freq);
+ print_speed(freq, no_rounding);
} else
printf("%lu", freq);
printf(_(" (asserted by call to kernel)\n"));
@@ -296,7 +262,7 @@ static int get_freq_hardware(unsigned int cpu, unsigned int human)
return -EINVAL;
}
if (human) {
- print_speed(freq);
+ print_speed(freq, no_rounding);
} else
printf("%lu", freq);
printf(_(" (asserted by call to hardware)\n"));
@@ -316,9 +282,9 @@ static int get_hardware_limits(unsigned int cpu, unsigned int human)
if (human) {
printf(_(" hardware limits: "));
- print_speed(min);
+ print_speed(min, no_rounding);
printf(" - ");
- print_speed(max);
+ print_speed(max, no_rounding);
printf("\n");
} else {
printf("%lu %lu\n", min, max);
@@ -350,9 +316,9 @@ static int get_policy(unsigned int cpu)
return -EINVAL;
}
printf(_(" current policy: frequency should be within "));
- print_speed(policy->min);
+ print_speed(policy->min, no_rounding);
printf(_(" and "));
- print_speed(policy->max);
+ print_speed(policy->max, no_rounding);
printf(".\n ");
printf(_("The governor \"%s\" may decide which speed to use\n"
@@ -436,7 +402,7 @@ static int get_freq_stats(unsigned int cpu, unsigned int human)
struct cpufreq_stats *stats = cpufreq_get_stats(cpu, &total_time);
while (stats) {
if (human) {
- print_speed(stats->frequency);
+ print_speed(stats->frequency, no_rounding);
printf(":%.2f%%",
(100.0 * stats->time_in_state) / total_time);
} else
@@ -472,6 +438,17 @@ static int get_latency(unsigned int cpu, unsigned int human)
return 0;
}
+/* --performance / -c */
+
+static int get_perf_cap(unsigned int cpu)
+{
+ if (cpupower_cpu_info.vendor == X86_VENDOR_AMD &&
+ cpupower_cpu_info.caps & CPUPOWER_CAP_AMD_PSTATE)
+ amd_pstate_show_perf_and_freq(cpu, no_rounding);
+
+ return 0;
+}
+
static void debug_output_one(unsigned int cpu)
{
struct cpufreq_available_frequencies *freqs;
@@ -486,11 +463,11 @@ static void debug_output_one(unsigned int cpu)
if (freqs) {
printf(_(" available frequency steps: "));
while (freqs->next) {
- print_speed(freqs->frequency);
+ print_speed(freqs->frequency, no_rounding);
printf(", ");
freqs = freqs->next;
}
- print_speed(freqs->frequency);
+ print_speed(freqs->frequency, no_rounding);
printf("\n");
cpufreq_put_available_frequencies(freqs);
}
@@ -500,6 +477,7 @@ static void debug_output_one(unsigned int cpu)
if (get_freq_hardware(cpu, 1) < 0)
get_freq_kernel(cpu, 1);
get_boost_mode(cpu);
+ get_perf_cap(cpu);
}
static struct option info_opts[] = {
@@ -518,6 +496,7 @@ static struct option info_opts[] = {
{"proc", no_argument, NULL, 'o'},
{"human", no_argument, NULL, 'm'},
{"no-rounding", no_argument, NULL, 'n'},
+ {"performance", no_argument, NULL, 'c'},
{ },
};
@@ -531,7 +510,7 @@ int cmd_freq_info(int argc, char **argv)
int output_param = 0;
do {
- ret = getopt_long(argc, argv, "oefwldpgrasmybn", info_opts,
+ ret = getopt_long(argc, argv, "oefwldpgrasmybnc", info_opts,
NULL);
switch (ret) {
case '?':
@@ -554,6 +533,7 @@ int cmd_freq_info(int argc, char **argv)
case 'e':
case 's':
case 'y':
+ case 'c':
if (output_param) {
output_param = -1;
cont = 0;
@@ -660,6 +640,9 @@ int cmd_freq_info(int argc, char **argv)
case 'y':
ret = get_latency(cpu, human);
break;
+ case 'c':
+ ret = get_perf_cap(cpu);
+ break;
}
if (ret)
return ret;
diff --git a/tools/power/cpupower/utils/helpers/amd.c b/tools/power/cpupower/utils/helpers/amd.c
index 97f2c857048e..c519cc89c97f 100644
--- a/tools/power/cpupower/utils/helpers/amd.c
+++ b/tools/power/cpupower/utils/helpers/amd.c
@@ -8,7 +8,10 @@
#include <pci/pci.h>
#include "helpers/helpers.h"
+#include "cpufreq.h"
+#include "acpi_cppc.h"
+/* ACPI P-States Helper Functions for AMD Processors ***************/
#define MSR_AMD_PSTATE_STATUS 0xc0010063
#define MSR_AMD_PSTATE 0xc0010064
#define MSR_AMD_PSTATE_LIMIT 0xc0010061
@@ -146,4 +149,78 @@ int amd_pci_get_num_boost_states(int *active, int *states)
pci_cleanup(pci_acc);
return 0;
}
+
+/* ACPI P-States Helper Functions for AMD Processors ***************/
+
+/* AMD P-State Helper Functions ************************************/
+enum amd_pstate_value {
+ AMD_PSTATE_HIGHEST_PERF,
+ AMD_PSTATE_MAX_FREQ,
+ AMD_PSTATE_LOWEST_NONLINEAR_FREQ,
+ MAX_AMD_PSTATE_VALUE_READ_FILES,
+};
+
+static const char *amd_pstate_value_files[MAX_AMD_PSTATE_VALUE_READ_FILES] = {
+ [AMD_PSTATE_HIGHEST_PERF] = "amd_pstate_highest_perf",
+ [AMD_PSTATE_MAX_FREQ] = "amd_pstate_max_freq",
+ [AMD_PSTATE_LOWEST_NONLINEAR_FREQ] = "amd_pstate_lowest_nonlinear_freq",
+};
+
+static unsigned long amd_pstate_get_data(unsigned int cpu,
+ enum amd_pstate_value value)
+{
+ return cpufreq_get_sysfs_value_from_table(cpu,
+ amd_pstate_value_files,
+ value,
+ MAX_AMD_PSTATE_VALUE_READ_FILES);
+}
+
+void amd_pstate_boost_init(unsigned int cpu, int *support, int *active)
+{
+ unsigned long highest_perf, nominal_perf, cpuinfo_min,
+ cpuinfo_max, amd_pstate_max;
+
+ highest_perf = amd_pstate_get_data(cpu, AMD_PSTATE_HIGHEST_PERF);
+ nominal_perf = acpi_cppc_get_data(cpu, NOMINAL_PERF);
+
+ *support = highest_perf > nominal_perf ? 1 : 0;
+ if (!(*support))
+ return;
+
+ cpufreq_get_hardware_limits(cpu, &cpuinfo_min, &cpuinfo_max);
+ amd_pstate_max = amd_pstate_get_data(cpu, AMD_PSTATE_MAX_FREQ);
+
+ *active = cpuinfo_max == amd_pstate_max ? 1 : 0;
+}
+
+void amd_pstate_show_perf_and_freq(unsigned int cpu, int no_rounding)
+{
+ printf(_(" AMD PSTATE Highest Performance: %lu. Maximum Frequency: "),
+ amd_pstate_get_data(cpu, AMD_PSTATE_HIGHEST_PERF));
+ /*
+ * If boost isn't active, the cpuinfo_max doesn't indicate real max
+ * frequency. So we read it back from amd-pstate sysfs entry.
+ */
+ print_speed(amd_pstate_get_data(cpu, AMD_PSTATE_MAX_FREQ), no_rounding);
+ printf(".\n");
+
+ printf(_(" AMD PSTATE Nominal Performance: %lu. Nominal Frequency: "),
+ acpi_cppc_get_data(cpu, NOMINAL_PERF));
+ print_speed(acpi_cppc_get_data(cpu, NOMINAL_FREQ) * 1000,
+ no_rounding);
+ printf(".\n");
+
+ printf(_(" AMD PSTATE Lowest Non-linear Performance: %lu. Lowest Non-linear Frequency: "),
+ acpi_cppc_get_data(cpu, LOWEST_NONLINEAR_PERF));
+ print_speed(amd_pstate_get_data(cpu, AMD_PSTATE_LOWEST_NONLINEAR_FREQ),
+ no_rounding);
+ printf(".\n");
+
+ printf(_(" AMD PSTATE Lowest Performance: %lu. Lowest Frequency: "),
+ acpi_cppc_get_data(cpu, LOWEST_PERF));
+ print_speed(acpi_cppc_get_data(cpu, LOWEST_FREQ) * 1000, no_rounding);
+ printf(".\n");
+}
+
+/* AMD P-State Helper Functions ************************************/
#endif /* defined(__i386__) || defined(__x86_64__) */
diff --git a/tools/power/cpupower/utils/helpers/cpuid.c b/tools/power/cpupower/utils/helpers/cpuid.c
index 72eb43593180..eae91f11d187 100644
--- a/tools/power/cpupower/utils/helpers/cpuid.c
+++ b/tools/power/cpupower/utils/helpers/cpuid.c
@@ -149,6 +149,19 @@ out:
if (ext_cpuid_level >= 0x80000008 &&
cpuid_ebx(0x80000008) & (1 << 4))
cpu_info->caps |= CPUPOWER_CAP_AMD_RDPRU;
+
+ if (cpupower_amd_pstate_enabled()) {
+ cpu_info->caps |= CPUPOWER_CAP_AMD_PSTATE;
+
+ /*
+ * If AMD P-State is enabled, the firmware will treat
+ * AMD P-State function as high priority.
+ */
+ cpu_info->caps &= ~CPUPOWER_CAP_AMD_CPB;
+ cpu_info->caps &= ~CPUPOWER_CAP_AMD_CPB_MSR;
+ cpu_info->caps &= ~CPUPOWER_CAP_AMD_HW_PSTATE;
+ cpu_info->caps &= ~CPUPOWER_CAP_AMD_PSTATEDEF;
+ }
}
if (cpu_info->vendor == X86_VENDOR_INTEL) {
diff --git a/tools/power/cpupower/utils/helpers/helpers.h b/tools/power/cpupower/utils/helpers/helpers.h
index 33ffacee7fcb..96e4bede078b 100644
--- a/tools/power/cpupower/utils/helpers/helpers.h
+++ b/tools/power/cpupower/utils/helpers/helpers.h
@@ -11,6 +11,7 @@
#include <libintl.h>
#include <locale.h>
+#include <stdbool.h>
#include "helpers/bitmask.h"
#include <cpupower.h>
@@ -73,6 +74,7 @@ enum cpupower_cpu_vendor {X86_VENDOR_UNKNOWN = 0, X86_VENDOR_INTEL,
#define CPUPOWER_CAP_AMD_HW_PSTATE 0x00000100
#define CPUPOWER_CAP_AMD_PSTATEDEF 0x00000200
#define CPUPOWER_CAP_AMD_CPB_MSR 0x00000400
+#define CPUPOWER_CAP_AMD_PSTATE 0x00000800
#define CPUPOWER_AMD_CPBDIS 0x02000000
@@ -135,6 +137,16 @@ extern int decode_pstates(unsigned int cpu, int boost_states,
extern int cpufreq_has_boost_support(unsigned int cpu, int *support,
int *active, int * states);
+
+/* AMD P-State stuff **************************/
+bool cpupower_amd_pstate_enabled(void);
+void amd_pstate_boost_init(unsigned int cpu,
+ int *support, int *active);
+void amd_pstate_show_perf_and_freq(unsigned int cpu,
+ int no_rounding);
+
+/* AMD P-State stuff **************************/
+
/*
* CPUID functions returning a single datum
*/
@@ -167,6 +179,15 @@ static inline int cpufreq_has_boost_support(unsigned int cpu, int *support,
int *active, int * states)
{ return -1; }
+static inline bool cpupower_amd_pstate_enabled(void)
+{ return false; }
+static inline void amd_pstate_boost_init(unsigned int cpu, int *support,
+ int *active)
+{}
+static inline void amd_pstate_show_perf_and_freq(unsigned int cpu,
+ int no_rounding)
+{}
+
/* cpuid and cpuinfo helpers **************************/
static inline unsigned int cpuid_eax(unsigned int op) { return 0; };
@@ -184,5 +205,6 @@ extern struct bitmask *offline_cpus;
void get_cpustate(void);
void print_online_cpus(void);
void print_offline_cpus(void);
+void print_speed(unsigned long speed, int no_rounding);
#endif /* __CPUPOWERUTILS_HELPERS__ */
diff --git a/tools/power/cpupower/utils/helpers/misc.c b/tools/power/cpupower/utils/helpers/misc.c
index fc6e34511721..9547b29254a7 100644
--- a/tools/power/cpupower/utils/helpers/misc.c
+++ b/tools/power/cpupower/utils/helpers/misc.c
@@ -3,9 +3,11 @@
#include <stdio.h>
#include <errno.h>
#include <stdlib.h>
+#include <string.h>
#include "helpers/helpers.h"
#include "helpers/sysfs.h"
+#include "cpufreq.h"
#if defined(__i386__) || defined(__x86_64__)
@@ -39,6 +41,8 @@ int cpufreq_has_boost_support(unsigned int cpu, int *support, int *active,
if (ret)
return ret;
}
+ } else if (cpupower_cpu_info.caps & CPUPOWER_CAP_AMD_PSTATE) {
+ amd_pstate_boost_init(cpu, support, active);
} else if (cpupower_cpu_info.caps & CPUPOWER_CAP_INTEL_IDA)
*support = *active = 1;
return 0;
@@ -83,6 +87,22 @@ int cpupower_intel_set_perf_bias(unsigned int cpu, unsigned int val)
return 0;
}
+bool cpupower_amd_pstate_enabled(void)
+{
+ char *driver = cpufreq_get_driver(0);
+ bool ret = false;
+
+ if (!driver)
+ return ret;
+
+ if (!strcmp(driver, "amd-pstate"))
+ ret = true;
+
+ cpufreq_put_driver(driver);
+
+ return ret;
+}
+
#endif /* #if defined(__i386__) || defined(__x86_64__) */
/* get_cpustate
@@ -144,3 +164,43 @@ void print_offline_cpus(void)
printf(_("cpupower set operation was not performed on them\n"));
}
}
+
+/*
+ * print_speed
+ *
+ * Print the exact CPU frequency with appropriate unit
+ */
+void print_speed(unsigned long speed, int no_rounding)
+{
+ unsigned long tmp;
+
+ if (no_rounding) {
+ if (speed > 1000000)
+ printf("%u.%06u GHz", ((unsigned int)speed / 1000000),
+ ((unsigned int)speed % 1000000));
+ else if (speed > 1000)
+ printf("%u.%03u MHz", ((unsigned int)speed / 1000),
+ (unsigned int)(speed % 1000));
+ else
+ printf("%lu kHz", speed);
+ } else {
+ if (speed > 1000000) {
+ tmp = speed % 10000;
+ if (tmp >= 5000)
+ speed += 10000;
+ printf("%u.%02u GHz", ((unsigned int)speed / 1000000),
+ ((unsigned int)(speed % 1000000) / 10000));
+ } else if (speed > 100000) {
+ tmp = speed % 1000;
+ if (tmp >= 500)
+ speed += 1000;
+ printf("%u MHz", ((unsigned int)speed / 1000));
+ } else if (speed > 1000) {
+ tmp = speed % 100;
+ if (tmp >= 50)
+ speed += 100;
+ printf("%u.%01u MHz", ((unsigned int)speed / 1000),
+ ((unsigned int)(speed % 1000) / 100));
+ }
+ }
+}
diff --git a/tools/power/x86/amd_pstate_tracer/amd_pstate_trace.py b/tools/power/x86/amd_pstate_tracer/amd_pstate_trace.py
new file mode 100755
index 000000000000..2dea4032ac56
--- /dev/null
+++ b/tools/power/x86/amd_pstate_tracer/amd_pstate_trace.py
@@ -0,0 +1,354 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0-only
+# -*- coding: utf-8 -*-
+#
+""" This utility can be used to debug and tune the performance of the
+AMD P-State driver. It imports intel_pstate_tracer to analyze AMD P-State
+trace event.
+
+Prerequisites:
+ Python version 2.7.x or higher
+ gnuplot 5.0 or higher
+ gnuplot-py 1.8 or higher
+ (Most of the distributions have these required packages. They may be called
+ gnuplot-py, phython-gnuplot or phython3-gnuplot, gnuplot-nox, ... )
+
+ Kernel config for Linux trace is enabled
+
+ see print_help(): for Usage and Output details
+
+"""
+from __future__ import print_function
+from datetime import datetime
+import subprocess
+import os
+import time
+import re
+import signal
+import sys
+import getopt
+import Gnuplot
+from numpy import *
+from decimal import *
+sys.path.append('../intel_pstate_tracer')
+#import intel_pstate_tracer
+import intel_pstate_tracer as ipt
+
+__license__ = "GPL version 2"
+
+MAX_CPUS = 256
+# Define the csv file columns
+C_COMM = 15
+C_ELAPSED = 14
+C_SAMPLE = 13
+C_DURATION = 12
+C_LOAD = 11
+C_TSC = 10
+C_APERF = 9
+C_MPERF = 8
+C_FREQ = 7
+C_MAX_PERF = 6
+C_DES_PERF = 5
+C_MIN_PERF = 4
+C_USEC = 3
+C_SEC = 2
+C_CPU = 1
+
+global sample_num, last_sec_cpu, last_usec_cpu, start_time, test_name, trace_file
+
+getcontext().prec = 11
+
+sample_num =0
+last_sec_cpu = [0] * MAX_CPUS
+last_usec_cpu = [0] * MAX_CPUS
+
+def plot_per_cpu_freq(cpu_index):
+ """ Plot per cpu frequency """
+
+ file_name = 'cpu{:0>3}.csv'.format(cpu_index)
+ if os.path.exists(file_name):
+ output_png = "cpu%03d_frequency.png" % cpu_index
+ g_plot = ipt.common_gnuplot_settings()
+ g_plot('set output "' + output_png + '"')
+ g_plot('set yrange [0:7]')
+ g_plot('set ytics 0, 1')
+ g_plot('set ylabel "CPU Frequency (GHz)"')
+ g_plot('set title "{} : frequency : CPU {:0>3} : {:%F %H:%M}"'.format(test_name, cpu_index, datetime.now()))
+ g_plot('set ylabel "CPU frequency"')
+ g_plot('set key off')
+ ipt.set_4_plot_linestyles(g_plot)
+ g_plot('plot "' + file_name + '" using {:d}:{:d} with linespoints linestyle 1 axis x1y1'.format(C_ELAPSED, C_FREQ))
+
+def plot_per_cpu_des_perf(cpu_index):
+ """ Plot per cpu desired perf """
+
+ file_name = 'cpu{:0>3}.csv'.format(cpu_index)
+ if os.path.exists(file_name):
+ output_png = "cpu%03d_des_perf.png" % cpu_index
+ g_plot = ipt.common_gnuplot_settings()
+ g_plot('set output "' + output_png + '"')
+ g_plot('set yrange [0:255]')
+ g_plot('set ylabel "des perf"')
+ g_plot('set title "{} : cpu des perf : CPU {:0>3} : {:%F %H:%M}"'.format(test_name, cpu_index, datetime.now()))
+ g_plot('set key off')
+ ipt.set_4_plot_linestyles(g_plot)
+ g_plot('plot "' + file_name + '" using {:d}:{:d} with linespoints linestyle 1 axis x1y1'.format(C_ELAPSED, C_DES_PERF))
+
+def plot_per_cpu_load(cpu_index):
+ """ Plot per cpu load """
+
+ file_name = 'cpu{:0>3}.csv'.format(cpu_index)
+ if os.path.exists(file_name):
+ output_png = "cpu%03d_load.png" % cpu_index
+ g_plot = ipt.common_gnuplot_settings()
+ g_plot('set output "' + output_png + '"')
+ g_plot('set yrange [0:100]')
+ g_plot('set ytics 0, 10')
+ g_plot('set ylabel "CPU load (percent)"')
+ g_plot('set title "{} : cpu load : CPU {:0>3} : {:%F %H:%M}"'.format(test_name, cpu_index, datetime.now()))
+ g_plot('set key off')
+ ipt.set_4_plot_linestyles(g_plot)
+ g_plot('plot "' + file_name + '" using {:d}:{:d} with linespoints linestyle 1 axis x1y1'.format(C_ELAPSED, C_LOAD))
+
+def plot_all_cpu_frequency():
+ """ Plot all cpu frequencies """
+
+ output_png = 'all_cpu_frequencies.png'
+ g_plot = ipt.common_gnuplot_settings()
+ g_plot('set output "' + output_png + '"')
+ g_plot('set ylabel "CPU Frequency (GHz)"')
+ g_plot('set title "{} : cpu frequencies : {:%F %H:%M}"'.format(test_name, datetime.now()))
+
+ title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).decode('utf-8').replace('\n', ' ')
+ plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_ELAPSED, C_FREQ)
+ g_plot('title_list = "{}"'.format(title_list))
+ g_plot(plot_str)
+
+def plot_all_cpu_des_perf():
+ """ Plot all cpu desired perf """
+
+ output_png = 'all_cpu_des_perf.png'
+ g_plot = ipt.common_gnuplot_settings()
+ g_plot('set output "' + output_png + '"')
+ g_plot('set ylabel "des perf"')
+ g_plot('set title "{} : cpu des perf : {:%F %H:%M}"'.format(test_name, datetime.now()))
+
+ title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).decode('utf-8').replace('\n', ' ')
+ plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 255 ps 1 title i".format(C_ELAPSED, C_DES_PERF)
+ g_plot('title_list = "{}"'.format(title_list))
+ g_plot(plot_str)
+
+def plot_all_cpu_load():
+ """ Plot all cpu load """
+
+ output_png = 'all_cpu_load.png'
+ g_plot = ipt.common_gnuplot_settings()
+ g_plot('set output "' + output_png + '"')
+ g_plot('set yrange [0:100]')
+ g_plot('set ylabel "CPU load (percent)"')
+ g_plot('set title "{} : cpu load : {:%F %H:%M}"'.format(test_name, datetime.now()))
+
+ title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).decode('utf-8').replace('\n', ' ')
+ plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 255 ps 1 title i".format(C_ELAPSED, C_LOAD)
+ g_plot('title_list = "{}"'.format(title_list))
+ g_plot(plot_str)
+
+def store_csv(cpu_int, time_pre_dec, time_post_dec, min_perf, des_perf, max_perf, freq_ghz, mperf, aperf, tsc, common_comm, load, duration_ms, sample_num, elapsed_time, cpu_mask):
+ """ Store master csv file information """
+
+ global graph_data_present
+
+ if cpu_mask[cpu_int] == 0:
+ return
+
+ try:
+ f_handle = open('cpu.csv', 'a')
+ string_buffer = "CPU_%03u, %05u, %06u, %u, %u, %u, %.4f, %u, %u, %u, %.2f, %.3f, %u, %.3f, %s\n" % (cpu_int, int(time_pre_dec), int(time_post_dec), int(min_perf), int(des_perf), int(max_perf), freq_ghz, int(mperf), int(aperf), int(tsc), load, duration_ms, sample_num, elapsed_time, common_comm)
+ f_handle.write(string_buffer)
+ f_handle.close()
+ except:
+ print('IO error cpu.csv')
+ return
+
+ graph_data_present = True;
+
+
+def cleanup_data_files():
+ """ clean up existing data files """
+
+ if os.path.exists('cpu.csv'):
+ os.remove('cpu.csv')
+ f_handle = open('cpu.csv', 'a')
+ f_handle.write('common_cpu, common_secs, common_usecs, min_perf, des_perf, max_perf, freq, mperf, aperf, tsc, load, duration_ms, sample_num, elapsed_time, common_comm')
+ f_handle.write('\n')
+ f_handle.close()
+
+def read_trace_data(file_name, cpu_mask):
+ """ Read and parse trace data """
+
+ global current_max_cpu
+ global sample_num, last_sec_cpu, last_usec_cpu, start_time
+
+ try:
+ data = open(file_name, 'r').read()
+ except:
+ print('Error opening ', file_name)
+ sys.exit(2)
+
+ for line in data.splitlines():
+ search_obj = \
+ re.search(r'(^(.*?)\[)((\d+)[^\]])(.*?)(\d+)([.])(\d+)(.*?amd_min_perf=)(\d+)(.*?amd_des_perf=)(\d+)(.*?amd_max_perf=)(\d+)(.*?freq=)(\d+)(.*?mperf=)(\d+)(.*?aperf=)(\d+)(.*?tsc=)(\d+)'
+ , line)
+
+ if search_obj:
+ cpu = search_obj.group(3)
+ cpu_int = int(cpu)
+ cpu = str(cpu_int)
+
+ time_pre_dec = search_obj.group(6)
+ time_post_dec = search_obj.group(8)
+ min_perf = search_obj.group(10)
+ des_perf = search_obj.group(12)
+ max_perf = search_obj.group(14)
+ freq = search_obj.group(16)
+ mperf = search_obj.group(18)
+ aperf = search_obj.group(20)
+ tsc = search_obj.group(22)
+
+ common_comm = search_obj.group(2).replace(' ', '')
+
+ if sample_num == 0 :
+ start_time = Decimal(time_pre_dec) + Decimal(time_post_dec) / Decimal(1000000)
+ sample_num += 1
+
+ if last_sec_cpu[cpu_int] == 0 :
+ last_sec_cpu[cpu_int] = time_pre_dec
+ last_usec_cpu[cpu_int] = time_post_dec
+ else :
+ duration_us = (int(time_pre_dec) - int(last_sec_cpu[cpu_int])) * 1000000 + (int(time_post_dec) - int(last_usec_cpu[cpu_int]))
+ duration_ms = Decimal(duration_us) / Decimal(1000)
+ last_sec_cpu[cpu_int] = time_pre_dec
+ last_usec_cpu[cpu_int] = time_post_dec
+ elapsed_time = Decimal(time_pre_dec) + Decimal(time_post_dec) / Decimal(1000000) - start_time
+ load = Decimal(int(mperf)*100)/ Decimal(tsc)
+ freq_ghz = Decimal(freq)/Decimal(1000000)
+ store_csv(cpu_int, time_pre_dec, time_post_dec, min_perf, des_perf, max_perf, freq_ghz, mperf, aperf, tsc, common_comm, load, duration_ms, sample_num, elapsed_time, cpu_mask)
+
+ if cpu_int > current_max_cpu:
+ current_max_cpu = cpu_int
+# Now separate the main overall csv file into per CPU csv files.
+ ipt.split_csv(current_max_cpu, cpu_mask)
+
+
+def signal_handler(signal, frame):
+ print(' SIGINT: Forcing cleanup before exit.')
+ if interval:
+ ipt.disable_trace(trace_file)
+ ipt.clear_trace_file()
+ ipt.free_trace_buffer()
+ sys.exit(0)
+
+trace_file = "/sys/kernel/debug/tracing/events/amd_cpu/enable"
+signal.signal(signal.SIGINT, signal_handler)
+
+interval = ""
+file_name = ""
+cpu_list = ""
+test_name = ""
+memory = "10240"
+graph_data_present = False;
+
+valid1 = False
+valid2 = False
+
+cpu_mask = zeros((MAX_CPUS,), dtype=int)
+
+
+try:
+ opts, args = getopt.getopt(sys.argv[1:],"ht:i:c:n:m:",["help","trace_file=","interval=","cpu=","name=","memory="])
+except getopt.GetoptError:
+ ipt.print_help('amd_pstate')
+ sys.exit(2)
+for opt, arg in opts:
+ if opt == '-h':
+ print()
+ sys.exit()
+ elif opt in ("-t", "--trace_file"):
+ valid1 = True
+ location = os.path.realpath(os.path.join(os.getcwd(), os.path.dirname(__file__)))
+ file_name = os.path.join(location, arg)
+ elif opt in ("-i", "--interval"):
+ valid1 = True
+ interval = arg
+ elif opt in ("-c", "--cpu"):
+ cpu_list = arg
+ elif opt in ("-n", "--name"):
+ valid2 = True
+ test_name = arg
+ elif opt in ("-m", "--memory"):
+ memory = arg
+
+if not (valid1 and valid2):
+ ipt.print_help('amd_pstate')
+ sys.exit()
+
+if cpu_list:
+ for p in re.split("[,]", cpu_list):
+ if int(p) < MAX_CPUS :
+ cpu_mask[int(p)] = 1
+else:
+ for i in range (0, MAX_CPUS):
+ cpu_mask[i] = 1
+
+if not os.path.exists('results'):
+ os.mkdir('results')
+ ipt.fix_ownership('results')
+
+os.chdir('results')
+if os.path.exists(test_name):
+ print('The test name directory already exists. Please provide a unique test name. Test re-run not supported, yet.')
+ sys.exit()
+os.mkdir(test_name)
+ipt.fix_ownership(test_name)
+os.chdir(test_name)
+
+cur_version = sys.version_info
+print('python version (should be >= 2.7):')
+print(cur_version)
+
+cleanup_data_files()
+
+if interval:
+ file_name = "/sys/kernel/debug/tracing/trace"
+ ipt.clear_trace_file()
+ ipt.set_trace_buffer_size(memory)
+ ipt.enable_trace(trace_file)
+ time.sleep(int(interval))
+ ipt.disable_trace(trace_file)
+
+current_max_cpu = 0
+
+read_trace_data(file_name, cpu_mask)
+
+if interval:
+ ipt.clear_trace_file()
+ ipt.free_trace_buffer()
+
+if graph_data_present == False:
+ print('No valid data to plot')
+ sys.exit(2)
+
+for cpu_no in range(0, current_max_cpu + 1):
+ plot_per_cpu_freq(cpu_no)
+ plot_per_cpu_des_perf(cpu_no)
+ plot_per_cpu_load(cpu_no)
+
+plot_all_cpu_des_perf()
+plot_all_cpu_frequency()
+plot_all_cpu_load()
+
+for root, dirs, files in os.walk('.'):
+ for f in files:
+ ipt.fix_ownership(f)
+
+os.chdir('../../')
diff --git a/tools/power/x86/intel-speed-select/Build b/tools/power/x86/intel-speed-select/Build
index b61456d75190..81e36bd578b1 100644
--- a/tools/power/x86/intel-speed-select/Build
+++ b/tools/power/x86/intel-speed-select/Build
@@ -1 +1 @@
-intel-speed-select-y += isst-config.o isst-core.o isst-display.o
+intel-speed-select-y += isst-config.o isst-core.o isst-display.o isst-daemon.o hfi-events.o
diff --git a/tools/power/x86/intel-speed-select/Makefile b/tools/power/x86/intel-speed-select/Makefile
index 12c6939dca2a..d2fba1297d96 100644
--- a/tools/power/x86/intel-speed-select/Makefile
+++ b/tools/power/x86/intel-speed-select/Makefile
@@ -13,8 +13,8 @@ endif
# Do not use make's built-in rules
# (this improves performance and avoids hard-to-debug behaviour);
MAKEFLAGS += -r
-
-override CFLAGS += -O2 -Wall -g -D_GNU_SOURCE -I$(OUTPUT)include
+override CFLAGS += -O2 -Wall -g -D_GNU_SOURCE -I$(OUTPUT)include -I/usr/include/libnl3
+override LDFLAGS += -lnl-genl-3 -lnl-3
ALL_TARGETS := intel-speed-select
ALL_PROGRAMS := $(patsubst %,$(OUTPUT)%,$(ALL_TARGETS))
@@ -31,7 +31,11 @@ $(OUTPUT)include/linux/isst_if.h: ../../../../include/uapi/linux/isst_if.h
mkdir -p $(OUTPUT)include/linux 2>&1 || true
ln -sf $(CURDIR)/../../../../include/uapi/linux/isst_if.h $@
-prepare: $(OUTPUT)include/linux/isst_if.h
+$(OUTPUT)include/linux/thermal.h: ../../../../include/uapi/linux/thermal.h
+ mkdir -p $(OUTPUT)include/linux 2>&1 || true
+ ln -sf $(CURDIR)/../../../../include/uapi/linux/thermal.h $@
+
+prepare: $(OUTPUT)include/linux/isst_if.h $(OUTPUT)include/linux/thermal.h
ISST_IN := $(OUTPUT)intel-speed-select-in.o
diff --git a/tools/power/x86/intel-speed-select/hfi-events.c b/tools/power/x86/intel-speed-select/hfi-events.c
new file mode 100644
index 000000000000..e85676711372
--- /dev/null
+++ b/tools/power/x86/intel-speed-select/hfi-events.c
@@ -0,0 +1,309 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Intel Speed Select -- Read HFI events for OOB
+ * Copyright (c) 2022 Intel Corporation.
+ */
+
+/*
+ * This file incorporates work covered by the following copyright and
+ * permission notice:
+
+ * WPA Supplicant - driver interaction with Linux nl80211/cfg80211
+ * Copyright (c) 2003-2008, Jouni Malinen <[email protected]>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Alternatively, this software may be distributed under the terms of
+ * BSD license.
+ *
+ * Requires
+ * libnl-genl-3-dev
+ *
+ * For Fedora/CenOS
+ * dnf install libnl3-devel
+ * For Ubuntu
+ * apt install libnl-3-dev libnl-genl-3-dev
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdarg.h>
+#include <string.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <sys/file.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <errno.h>
+#include <getopt.h>
+#include <signal.h>
+#include <netlink/genl/genl.h>
+#include <netlink/genl/family.h>
+#include <netlink/genl/ctrl.h>
+
+#include <linux/thermal.h>
+#include "isst.h"
+
+struct hfi_event_data {
+ struct nl_sock *nl_handle;
+ struct nl_cb *nl_cb;
+};
+
+struct hfi_event_data drv;
+
+static int ack_handler(struct nl_msg *msg, void *arg)
+{
+ int *err = arg;
+ *err = 0;
+ return NL_STOP;
+}
+
+static int finish_handler(struct nl_msg *msg, void *arg)
+{
+ int *ret = arg;
+ *ret = 0;
+ return NL_SKIP;
+}
+
+static int error_handler(struct sockaddr_nl *nla, struct nlmsgerr *err,
+ void *arg)
+{
+ int *ret = arg;
+ *ret = err->error;
+ return NL_SKIP;
+}
+
+static int seq_check_handler(struct nl_msg *msg, void *arg)
+{
+ return NL_OK;
+}
+
+static int send_and_recv_msgs(struct hfi_event_data *drv,
+ struct nl_msg *msg,
+ int (*valid_handler)(struct nl_msg *, void *),
+ void *valid_data)
+{
+ struct nl_cb *cb;
+ int err = -ENOMEM;
+
+ cb = nl_cb_clone(drv->nl_cb);
+ if (!cb)
+ goto out;
+
+ err = nl_send_auto_complete(drv->nl_handle, msg);
+ if (err < 0)
+ goto out;
+
+ err = 1;
+
+ nl_cb_err(cb, NL_CB_CUSTOM, error_handler, &err);
+ nl_cb_set(cb, NL_CB_FINISH, NL_CB_CUSTOM, finish_handler, &err);
+ nl_cb_set(cb, NL_CB_ACK, NL_CB_CUSTOM, ack_handler, &err);
+
+ if (valid_handler)
+ nl_cb_set(cb, NL_CB_VALID, NL_CB_CUSTOM,
+ valid_handler, valid_data);
+
+ while (err > 0)
+ nl_recvmsgs(drv->nl_handle, cb);
+ out:
+ nl_cb_put(cb);
+ nlmsg_free(msg);
+ return err;
+}
+
+struct family_data {
+ const char *group;
+ int id;
+};
+
+static int family_handler(struct nl_msg *msg, void *arg)
+{
+ struct family_data *res = arg;
+ struct nlattr *tb[CTRL_ATTR_MAX + 1];
+ struct genlmsghdr *gnlh = nlmsg_data(nlmsg_hdr(msg));
+ struct nlattr *mcgrp;
+ int i;
+
+ nla_parse(tb, CTRL_ATTR_MAX, genlmsg_attrdata(gnlh, 0),
+ genlmsg_attrlen(gnlh, 0), NULL);
+ if (!tb[CTRL_ATTR_MCAST_GROUPS])
+ return NL_SKIP;
+
+ nla_for_each_nested(mcgrp, tb[CTRL_ATTR_MCAST_GROUPS], i) {
+ struct nlattr *tb2[CTRL_ATTR_MCAST_GRP_MAX + 1];
+ nla_parse(tb2, CTRL_ATTR_MCAST_GRP_MAX, nla_data(mcgrp),
+ nla_len(mcgrp), NULL);
+ if (!tb2[CTRL_ATTR_MCAST_GRP_NAME] ||
+ !tb2[CTRL_ATTR_MCAST_GRP_ID] ||
+ strncmp(nla_data(tb2[CTRL_ATTR_MCAST_GRP_NAME]),
+ res->group,
+ nla_len(tb2[CTRL_ATTR_MCAST_GRP_NAME])) != 0)
+ continue;
+ res->id = nla_get_u32(tb2[CTRL_ATTR_MCAST_GRP_ID]);
+ break;
+ };
+
+ return 0;
+}
+
+static int nl_get_multicast_id(struct hfi_event_data *drv,
+ const char *family, const char *group)
+{
+ struct nl_msg *msg;
+ int ret = -1;
+ struct family_data res = { group, -ENOENT };
+
+ msg = nlmsg_alloc();
+ if (!msg)
+ return -ENOMEM;
+ genlmsg_put(msg, 0, 0, genl_ctrl_resolve(drv->nl_handle, "nlctrl"),
+ 0, 0, CTRL_CMD_GETFAMILY, 0);
+ NLA_PUT_STRING(msg, CTRL_ATTR_FAMILY_NAME, family);
+
+ ret = send_and_recv_msgs(drv, msg, family_handler, &res);
+ msg = NULL;
+ if (ret == 0)
+ ret = res.id;
+
+nla_put_failure:
+ nlmsg_free(msg);
+ return ret;
+}
+
+struct perf_cap {
+ int cpu;
+ int perf;
+ int eff;
+};
+
+static void process_hfi_event(struct perf_cap *perf_cap)
+{
+ process_level_change(perf_cap->cpu);
+}
+
+static int handle_event(struct nl_msg *n, void *arg)
+{
+ struct nlmsghdr *nlh = nlmsg_hdr(n);
+ struct genlmsghdr *genlhdr = genlmsg_hdr(nlh);
+ struct nlattr *attrs[THERMAL_GENL_ATTR_MAX + 1];
+ int ret;
+ struct perf_cap perf_cap;
+
+ ret = genlmsg_parse(nlh, 0, attrs, THERMAL_GENL_ATTR_MAX, NULL);
+
+ debug_printf("Received event %d parse_rer:%d\n", genlhdr->cmd, ret);
+ if (genlhdr->cmd == THERMAL_GENL_EVENT_CPU_CAPABILITY_CHANGE) {
+ struct nlattr *cap;
+ int j, index = 0;
+
+ debug_printf("THERMAL_GENL_EVENT_CPU_CAPABILITY_CHANGE\n");
+ nla_for_each_nested(cap, attrs[THERMAL_GENL_ATTR_CPU_CAPABILITY], j) {
+ switch (index) {
+ case 0:
+ perf_cap.cpu = nla_get_u32(cap);
+ break;
+ case 1:
+ perf_cap.perf = nla_get_u32(cap);
+ break;
+ case 2:
+ perf_cap.eff = nla_get_u32(cap);
+ break;
+ default:
+ break;
+ }
+ ++index;
+ if (index == 3) {
+ index = 0;
+ process_hfi_event(&perf_cap);
+ }
+ }
+ }
+
+ return 0;
+}
+
+static int _hfi_exit;
+
+static int check_hf_suport(void)
+{
+ unsigned int eax = 0, ebx = 0, ecx = 0, edx = 0;
+
+ __cpuid(6, eax, ebx, ecx, edx);
+ if (eax & BIT(19))
+ return 1;
+
+ return 0;
+}
+
+int hfi_main(void)
+{
+ struct nl_sock *sock;
+ struct nl_cb *cb;
+ int err = 0;
+ int mcast_id;
+ int no_block = 0;
+
+ if (!check_hf_suport()) {
+ fprintf(stderr, "CPU Doesn't support HFI\n");
+ return -1;
+ }
+
+ sock = nl_socket_alloc();
+ if (!sock) {
+ fprintf(stderr, "nl_socket_alloc failed\n");
+ return -1;
+ }
+
+ if (genl_connect(sock)) {
+ fprintf(stderr, "genl_connect(sk_event) failed\n");
+ goto free_sock;
+ }
+
+ drv.nl_handle = sock;
+ drv.nl_cb = cb = nl_cb_alloc(NL_CB_DEFAULT);
+ if (drv.nl_cb == NULL) {
+ printf("Failed to allocate netlink callbacks");
+ goto free_sock;
+ }
+
+ mcast_id = nl_get_multicast_id(&drv, THERMAL_GENL_FAMILY_NAME,
+ THERMAL_GENL_EVENT_GROUP_NAME);
+ if (mcast_id < 0) {
+ fprintf(stderr, "nl_get_multicast_id failed\n");
+ goto free_sock;
+ }
+
+ if (nl_socket_add_membership(sock, mcast_id)) {
+ fprintf(stderr, "nl_socket_add_membership failed");
+ goto free_sock;
+ }
+
+ nl_cb_set(cb, NL_CB_SEQ_CHECK, NL_CB_CUSTOM, seq_check_handler, 0);
+ nl_cb_set(cb, NL_CB_VALID, NL_CB_CUSTOM, handle_event, NULL);
+
+ if (no_block)
+ nl_socket_set_nonblocking(sock);
+
+ debug_printf("hfi is initialized\n");
+
+ while (!_hfi_exit && !err) {
+ err = nl_recvmsgs(sock, cb);
+ debug_printf("nl_recv_message err:%d\n", err);
+ }
+
+ return 0;
+
+ /* Netlink library doesn't have calls to dealloc cb or disconnect */
+free_sock:
+ nl_socket_free(sock);
+
+ return -1;
+}
+
+void hfi_exit(void)
+{
+ _hfi_exit = 1;
+}
diff --git a/tools/power/x86/intel-speed-select/isst-config.c b/tools/power/x86/intel-speed-select/isst-config.c
index bf9fd3549a1d..060390e88e37 100644
--- a/tools/power/x86/intel-speed-select/isst-config.c
+++ b/tools/power/x86/intel-speed-select/isst-config.c
@@ -15,7 +15,8 @@ struct process_cmd_struct {
int arg;
};
-static const char *version_str = "v1.10";
+static const char *version_str = "v1.12";
+
static const int supported_api_ver = 1;
static struct isst_if_platform_info isst_platform_info;
static char *progname;
@@ -368,7 +369,7 @@ int get_topo_max_cpus(void)
return topo_max_cpus;
}
-static void set_cpu_online_offline(int cpu, int state)
+void set_cpu_online_offline(int cpu, int state)
{
char buffer[128];
int fd, ret;
@@ -409,12 +410,10 @@ static void force_all_cpus_online(void)
unlink("/var/run/isst_cpu_topology.dat");
}
-#define MAX_PACKAGE_COUNT 8
-#define MAX_DIE_PER_PACKAGE 2
-static void for_each_online_package_in_set(void (*callback)(int, void *, void *,
- void *, void *),
- void *arg1, void *arg2, void *arg3,
- void *arg4)
+void for_each_online_package_in_set(void (*callback)(int, void *, void *,
+ void *, void *),
+ void *arg1, void *arg2, void *arg3,
+ void *arg4)
{
int max_packages[MAX_PACKAGE_COUNT * MAX_PACKAGE_COUNT];
int pkg_index = 0, i;
@@ -1599,6 +1598,7 @@ static void set_scaling_min_to_cpuinfo_max(int cpu)
die_id != get_physical_die_id(i))
continue;
+ adjust_scaling_max_from_base_freq(i);
set_cpufreq_scaling_min_max_from_cpuinfo(i, 1, 0);
adjust_scaling_min_from_base_freq(i);
}
@@ -1615,6 +1615,7 @@ static void set_scaling_min_to_cpuinfo_min(int cpu)
die_id != get_physical_die_id(i))
continue;
+ adjust_scaling_max_from_base_freq(i);
set_cpufreq_scaling_min_max_from_cpuinfo(i, 0, 0);
}
}
@@ -2801,7 +2802,9 @@ static void usage(void)
printf("\t[-p|--pause] : Delay between two mail box commands in milliseconds\n");
printf("\t[-r|--retry] : Retry count for mail box commands on failure, default 3\n");
printf("\t[-v|--version] : Print version\n");
-
+ printf("\t[-b|--oob : Start a daemon to process HFI events for perf profile change from Out of Band agent.\n");
+ printf("\t[-n|--no-daemon : Don't run as daemon. By default --oob will turn on daemon mode\n");
+ printf("\t[-w|--delay : Delay for reading config level state change in OOB poll mode.\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");
@@ -2835,6 +2838,9 @@ static void cmdline(int argc, char **argv)
int opt, force_cpus_online = 0;
int option_index = 0;
int ret;
+ int oob_mode = 0;
+ int poll_interval = -1;
+ int no_daemon = 0;
static struct option long_options[] = {
{ "all-cpus-online", no_argument, 0, 'a' },
@@ -2847,6 +2853,9 @@ static void cmdline(int argc, char **argv)
{ "out", required_argument, 0, 'o' },
{ "retry", required_argument, 0, 'r' },
{ "version", no_argument, 0, 'v' },
+ { "oob", no_argument, 0, 'b' },
+ { "no-daemon", no_argument, 0, 'n' },
+ { "poll-interval", required_argument, 0, 'w' },
{ 0, 0, 0, 0 }
};
@@ -2873,7 +2882,7 @@ static void cmdline(int argc, char **argv)
}
progname = argv[0];
- while ((opt = getopt_long_only(argc, argv, "+c:df:hio:va", long_options,
+ while ((opt = getopt_long_only(argc, argv, "+c:df:hio:vabw:n", long_options,
&option_index)) != -1) {
switch (opt) {
case 'a':
@@ -2918,12 +2927,26 @@ static void cmdline(int argc, char **argv)
case 'v':
print_version();
break;
+ case 'b':
+ oob_mode = 1;
+ break;
+ case 'n':
+ no_daemon = 1;
+ break;
+ case 'w':
+ ret = strtol(optarg, &ptr, 10);
+ if (!ret) {
+ fprintf(stderr, "Invalid poll interval count\n");
+ exit(0);
+ }
+ poll_interval = ret;
+ break;
default:
usage();
}
}
- if (optind > (argc - 2)) {
+ if (optind > (argc - 2) && !oob_mode) {
usage();
exit(0);
}
@@ -2934,6 +2957,17 @@ static void cmdline(int argc, char **argv)
set_cpu_present_cpu_mask();
set_cpu_target_cpu_mask();
+ if (oob_mode) {
+ create_cpu_map();
+ if (debug_flag)
+ fprintf(stderr, "OOB mode is enabled in debug mode\n");
+
+ ret = isst_daemon(debug_flag, poll_interval, no_daemon);
+ if (ret)
+ fprintf(stderr, "OOB mode enable failed\n");
+ goto out;
+ }
+
if (!is_clx_n_platform()) {
ret = isst_fill_platform_info();
if (ret)
diff --git a/tools/power/x86/intel-speed-select/isst-daemon.c b/tools/power/x86/intel-speed-select/isst-daemon.c
new file mode 100644
index 000000000000..dd372924bc82
--- /dev/null
+++ b/tools/power/x86/intel-speed-select/isst-daemon.c
@@ -0,0 +1,244 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Intel Speed Select -- Allow speed select to daemonize
+ * Copyright (c) 2022 Intel Corporation.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdarg.h>
+#include <string.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <sys/file.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <errno.h>
+#include <getopt.h>
+#include <signal.h>
+#include <time.h>
+
+#include "isst.h"
+
+static int per_package_levels_info[MAX_PACKAGE_COUNT][MAX_DIE_PER_PACKAGE];
+static time_t per_package_levels_tm[MAX_PACKAGE_COUNT][MAX_DIE_PER_PACKAGE];
+
+static void init_levels(void)
+{
+ int i, j;
+
+ for (i = 0; i < MAX_PACKAGE_COUNT; ++i)
+ for (j = 0; j < MAX_DIE_PER_PACKAGE; ++j)
+ per_package_levels_info[i][j] = -1;
+}
+
+void process_level_change(int cpu)
+{
+ struct isst_pkg_ctdp_level_info ctdp_level;
+ int pkg_id = get_physical_package_id(cpu);
+ int die_id = get_physical_die_id(cpu);
+ struct isst_pkg_ctdp pkg_dev;
+ time_t tm;
+ int ret;
+
+ if (pkg_id >= MAX_PACKAGE_COUNT || die_id > MAX_DIE_PER_PACKAGE) {
+ debug_printf("Invalid package/die info for cpu:%d\n", cpu);
+ return;
+ }
+
+ tm = time(NULL);
+ if (tm - per_package_levels_tm[pkg_id][die_id] < 2 )
+ return;
+
+ per_package_levels_tm[pkg_id][die_id] = tm;
+
+ ret = isst_get_ctdp_levels(cpu, &pkg_dev);
+ if (ret) {
+ debug_printf("Can't get tdp levels for cpu:%d\n", cpu);
+ return;
+ }
+
+ debug_printf("Get Config level %d pkg:%d die:%d current_level:%d \n", cpu,
+ pkg_id, die_id, pkg_dev.current_level);
+
+ if (pkg_dev.locked) {
+ debug_printf("config TDP s locked \n");
+ return;
+ }
+
+ if (per_package_levels_info[pkg_id][die_id] == pkg_dev.current_level)
+ return;
+
+ debug_printf("**Config level change for cpu:%d pkg:%d die:%d from %d to %d\n",
+ cpu, pkg_id, die_id, per_package_levels_info[pkg_id][die_id],
+ pkg_dev.current_level);
+
+ per_package_levels_info[pkg_id][die_id] = pkg_dev.current_level;
+
+ ctdp_level.core_cpumask_size =
+ alloc_cpu_set(&ctdp_level.core_cpumask);
+ ret = isst_get_coremask_info(cpu, pkg_dev.current_level, &ctdp_level);
+ if (ret) {
+ free_cpu_set(ctdp_level.core_cpumask);
+ debug_printf("Can't get core_mask:%d\n", cpu);
+ return;
+ }
+
+ if (ctdp_level.cpu_count) {
+ int i, max_cpus = get_topo_max_cpus();
+ for (i = 0; i < max_cpus; ++i) {
+ if (pkg_id != get_physical_package_id(i) || die_id != get_physical_die_id(i))
+ continue;
+ if (CPU_ISSET_S(i, ctdp_level.core_cpumask_size, ctdp_level.core_cpumask)) {
+ fprintf(stderr, "online cpu %d\n", i);
+ set_cpu_online_offline(i, 1);
+ } else {
+ fprintf(stderr, "offline cpu %d\n", i);
+ set_cpu_online_offline(i, 0);
+ }
+ }
+ }
+
+ free_cpu_set(ctdp_level.core_cpumask);
+}
+
+static void _poll_for_config_change(int cpu, void *arg1, void *arg2,
+ void *arg3, void *arg4)
+{
+ process_level_change(cpu);
+}
+
+static void poll_for_config_change(void)
+{
+ for_each_online_package_in_set(_poll_for_config_change, NULL, NULL,
+ NULL, NULL);
+}
+
+static int done = 0;
+static int pid_file_handle;
+
+static void signal_handler(int sig)
+{
+ switch (sig) {
+ case SIGINT:
+ case SIGTERM:
+ done = 1;
+ hfi_exit();
+ exit(0);
+ break;
+ default:
+ break;
+ }
+}
+
+static void daemonize(char *rundir, char *pidfile)
+{
+ int pid, sid, i;
+ char str[10];
+ struct sigaction sig_actions;
+ sigset_t sig_set;
+ int ret;
+
+ if (getppid() == 1)
+ return;
+
+ sigemptyset(&sig_set);
+ sigaddset(&sig_set, SIGCHLD);
+ sigaddset(&sig_set, SIGTSTP);
+ sigaddset(&sig_set, SIGTTOU);
+ sigaddset(&sig_set, SIGTTIN);
+ sigprocmask(SIG_BLOCK, &sig_set, NULL);
+
+ sig_actions.sa_handler = signal_handler;
+ sigemptyset(&sig_actions.sa_mask);
+ sig_actions.sa_flags = 0;
+
+ sigaction(SIGHUP, &sig_actions, NULL);
+ sigaction(SIGTERM, &sig_actions, NULL);
+ sigaction(SIGINT, &sig_actions, NULL);
+
+ pid = fork();
+ if (pid < 0) {
+ /* Could not fork */
+ exit(EXIT_FAILURE);
+ }
+ if (pid > 0)
+ exit(EXIT_SUCCESS);
+
+ umask(027);
+
+ sid = setsid();
+ if (sid < 0)
+ exit(EXIT_FAILURE);
+
+ /* close all descriptors */
+ for (i = getdtablesize(); i >= 0; --i)
+ close(i);
+
+ i = open("/dev/null", O_RDWR);
+ ret = dup(i);
+ if (ret == -1)
+ exit(EXIT_FAILURE);
+
+ ret = dup(i);
+ if (ret == -1)
+ exit(EXIT_FAILURE);
+
+ ret = chdir(rundir);
+ if (ret == -1)
+ exit(EXIT_FAILURE);
+
+ pid_file_handle = open(pidfile, O_RDWR | O_CREAT, 0600);
+ if (pid_file_handle == -1) {
+ /* Couldn't open lock file */
+ exit(1);
+ }
+ /* Try to lock file */
+#ifdef LOCKF_SUPPORT
+ if (lockf(pid_file_handle, F_TLOCK, 0) == -1) {
+#else
+ if (flock(pid_file_handle, LOCK_EX|LOCK_NB) < 0) {
+#endif
+ /* Couldn't get lock on lock file */
+ fprintf(stderr, "Couldn't get lock file %d\n", getpid());
+ exit(1);
+ }
+ snprintf(str, sizeof(str), "%d\n", getpid());
+ ret = write(pid_file_handle, str, strlen(str));
+ if (ret == -1)
+ exit(EXIT_FAILURE);
+
+ close(i);
+}
+
+int isst_daemon(int debug_mode, int poll_interval, int no_daemon)
+{
+ int ret;
+
+ if (!no_daemon && poll_interval < 0 && !debug_mode) {
+ fprintf(stderr, "OOB mode is enabled and will run as daemon\n");
+ daemonize((char *) "/tmp/",
+ (char *)"/tmp/hfi-events.pid");
+ } else {
+ signal(SIGINT, signal_handler);
+ }
+
+ init_levels();
+
+ if (poll_interval < 0) {
+ ret = hfi_main();
+ if (ret) {
+ fprintf(stderr, "HFI initialization failed\n");
+ }
+ fprintf(stderr, "Must specify poll-interval\n");
+ return ret;
+ }
+
+ debug_printf("Starting loop\n");
+ while (!done) {
+ sleep(poll_interval);
+ poll_for_config_change();
+ }
+
+ return 0;
+}
diff --git a/tools/power/x86/intel-speed-select/isst.h b/tools/power/x86/intel-speed-select/isst.h
index 1aa15d5ea57c..0796d8c6a882 100644
--- a/tools/power/x86/intel-speed-select/isst.h
+++ b/tools/power/x86/intel-speed-select/isst.h
@@ -76,6 +76,9 @@
#define DISP_FREQ_MULTIPLIER 100
+#define MAX_PACKAGE_COUNT 8
+#define MAX_DIE_PER_PACKAGE 2
+
struct isst_clos_config {
int pkg_id;
int die_id;
@@ -260,4 +263,14 @@ extern int is_skx_based_platform(void);
extern int is_spr_platform(void);
extern int is_icx_platform(void);
extern void isst_trl_display_information(int cpu, FILE *outf, unsigned long long trl);
+
+extern void set_cpu_online_offline(int cpu, int state);
+extern void for_each_online_package_in_set(void (*callback)(int, void *, void *,
+ void *, void *),
+ void *arg1, void *arg2, void *arg3,
+ void *arg4);
+extern int isst_daemon(int debug_mode, int poll_interval, int no_daemon);
+extern void process_level_change(int cpu);
+extern int hfi_main(void);
+extern void hfi_exit(void);
#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 e15e20696d17..b46e9eb8f5aa 100755
--- a/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py
+++ b/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py
@@ -63,7 +63,7 @@ C_USEC = 3
C_SEC = 2
C_CPU = 1
-global sample_num, last_sec_cpu, last_usec_cpu, start_time, testname
+global sample_num, last_sec_cpu, last_usec_cpu, start_time, testname, trace_file
# 11 digits covers uptime to 115 days
getcontext().prec = 11
@@ -72,17 +72,17 @@ sample_num =0
last_sec_cpu = [0] * MAX_CPUS
last_usec_cpu = [0] * MAX_CPUS
-def print_help():
- print('intel_pstate_tracer.py:')
+def print_help(driver_name):
+ print('%s_tracer.py:'%driver_name)
print(' Usage:')
print(' If the trace file is available, then to simply parse and plot, use (sudo not required):')
- print(' ./intel_pstate_tracer.py [-c cpus] -t <trace_file> -n <test_name>')
+ print(' ./%s_tracer.py [-c cpus] -t <trace_file> -n <test_name>'%driver_name)
print(' Or')
- print(' ./intel_pstate_tracer.py [--cpu cpus] ---trace_file <trace_file> --name <test_name>')
+ print(' ./%s_tracer.py [--cpu cpus] ---trace_file <trace_file> --name <test_name>'%driver_name)
print(' To generate trace file, parse and plot, use (sudo required):')
- print(' sudo ./intel_pstate_tracer.py [-c cpus] -i <interval> -n <test_name> -m <kbytes>')
+ print(' sudo ./%s_tracer.py [-c cpus] -i <interval> -n <test_name> -m <kbytes>'%driver_name)
print(' Or')
- print(' sudo ./intel_pstate_tracer.py [--cpu cpus] --interval <interval> --name <test_name> --memory <kbytes>')
+ print(' sudo ./%s_tracer.py [--cpu cpus] --interval <interval> --name <test_name> --memory <kbytes>'%driver_name)
print(' Optional argument:')
print(' cpus: comma separated list of CPUs')
print(' kbytes: Kilo bytes of memory per CPU to allocate to the trace buffer. Default: 10240')
@@ -323,7 +323,7 @@ def set_4_plot_linestyles(g_plot):
g_plot('set style line 3 linetype 1 linecolor rgb "purple" pointtype -1')
g_plot('set style line 4 linetype 1 linecolor rgb "blue" pointtype -1')
-def store_csv(cpu_int, time_pre_dec, time_post_dec, core_busy, scaled, _from, _to, mperf, aperf, tsc, freq_ghz, io_boost, common_comm, load, duration_ms, sample_num, elapsed_time, tsc_ghz):
+def store_csv(cpu_int, time_pre_dec, time_post_dec, core_busy, scaled, _from, _to, mperf, aperf, tsc, freq_ghz, io_boost, common_comm, load, duration_ms, sample_num, elapsed_time, tsc_ghz, cpu_mask):
""" Store master csv file information """
global graph_data_present
@@ -342,11 +342,9 @@ def store_csv(cpu_int, time_pre_dec, time_post_dec, core_busy, scaled, _from, _t
graph_data_present = True;
-def split_csv():
+def split_csv(current_max_cpu, cpu_mask):
""" seperate the all csv file into per CPU csv files. """
- global current_max_cpu
-
if os.path.exists('cpu.csv'):
for index in range(0, current_max_cpu + 1):
if cpu_mask[int(index)] != 0:
@@ -381,27 +379,25 @@ def clear_trace_file():
print('IO error clearing trace file ')
sys.exit(2)
-def enable_trace():
+def enable_trace(trace_file):
""" Enable trace """
try:
- open('/sys/kernel/debug/tracing/events/power/pstate_sample/enable'
- , 'w').write("1")
+ open(trace_file,'w').write("1")
except:
print('IO error enabling trace ')
sys.exit(2)
-def disable_trace():
+def disable_trace(trace_file):
""" Disable trace """
try:
- open('/sys/kernel/debug/tracing/events/power/pstate_sample/enable'
- , 'w').write("0")
+ open(trace_file, 'w').write("0")
except:
print('IO error disabling trace ')
sys.exit(2)
-def set_trace_buffer_size():
+def set_trace_buffer_size(memory):
""" Set trace buffer size """
try:
@@ -421,7 +417,7 @@ def free_trace_buffer():
print('IO error freeing trace buffer ')
sys.exit(2)
-def read_trace_data(filename):
+def read_trace_data(filename, cpu_mask):
""" Read and parse trace data """
global current_max_cpu
@@ -481,135 +477,137 @@ def read_trace_data(filename):
tsc_ghz = Decimal(0)
if duration_ms != Decimal(0) :
tsc_ghz = Decimal(tsc)/duration_ms/Decimal(1000000)
- store_csv(cpu_int, time_pre_dec, time_post_dec, core_busy, scaled, _from, _to, mperf, aperf, tsc, freq_ghz, io_boost, common_comm, load, duration_ms, sample_num, elapsed_time, tsc_ghz)
+ store_csv(cpu_int, time_pre_dec, time_post_dec, core_busy, scaled, _from, _to, mperf, aperf, tsc, freq_ghz, io_boost, common_comm, load, duration_ms, sample_num, elapsed_time, tsc_ghz, cpu_mask)
if cpu_int > current_max_cpu:
current_max_cpu = cpu_int
# End of for each trace line loop
# Now seperate the main overall csv file into per CPU csv files.
- split_csv()
+ split_csv(current_max_cpu, cpu_mask)
def signal_handler(signal, frame):
print(' SIGINT: Forcing cleanup before exit.')
if interval:
- disable_trace()
+ disable_trace(trace_file)
clear_trace_file()
# Free the memory
free_trace_buffer()
sys.exit(0)
-signal.signal(signal.SIGINT, signal_handler)
+if __name__ == "__main__":
+ trace_file = "/sys/kernel/debug/tracing/events/power/pstate_sample/enable"
+ signal.signal(signal.SIGINT, signal_handler)
-interval = ""
-filename = ""
-cpu_list = ""
-testname = ""
-memory = "10240"
-graph_data_present = False;
+ interval = ""
+ filename = ""
+ cpu_list = ""
+ testname = ""
+ memory = "10240"
+ graph_data_present = False;
-valid1 = False
-valid2 = False
+ valid1 = False
+ valid2 = False
-cpu_mask = zeros((MAX_CPUS,), dtype=int)
+ cpu_mask = zeros((MAX_CPUS,), dtype=int)
-try:
- opts, args = getopt.getopt(sys.argv[1:],"ht:i:c:n:m:",["help","trace_file=","interval=","cpu=","name=","memory="])
-except getopt.GetoptError:
- print_help()
- sys.exit(2)
-for opt, arg in opts:
- if opt == '-h':
- print()
+ try:
+ opts, args = getopt.getopt(sys.argv[1:],"ht:i:c:n:m:",["help","trace_file=","interval=","cpu=","name=","memory="])
+ except getopt.GetoptError:
+ print_help('intel_pstate')
+ sys.exit(2)
+ for opt, arg in opts:
+ if opt == '-h':
+ print_help('intel_pstate')
+ sys.exit()
+ elif opt in ("-t", "--trace_file"):
+ valid1 = True
+ location = os.path.realpath(os.path.join(os.getcwd(), os.path.dirname(__file__)))
+ filename = os.path.join(location, arg)
+ elif opt in ("-i", "--interval"):
+ valid1 = True
+ interval = arg
+ elif opt in ("-c", "--cpu"):
+ cpu_list = arg
+ elif opt in ("-n", "--name"):
+ valid2 = True
+ testname = arg
+ elif opt in ("-m", "--memory"):
+ memory = arg
+
+ if not (valid1 and valid2):
+ print_help('intel_pstate')
sys.exit()
- elif opt in ("-t", "--trace_file"):
- valid1 = True
- location = os.path.realpath(os.path.join(os.getcwd(), os.path.dirname(__file__)))
- filename = os.path.join(location, arg)
- elif opt in ("-i", "--interval"):
- valid1 = True
- interval = arg
- elif opt in ("-c", "--cpu"):
- cpu_list = arg
- elif opt in ("-n", "--name"):
- valid2 = True
- testname = arg
- elif opt in ("-m", "--memory"):
- memory = arg
-
-if not (valid1 and valid2):
- print_help()
- sys.exit()
-
-if cpu_list:
- for p in re.split("[,]", cpu_list):
- if int(p) < MAX_CPUS :
- cpu_mask[int(p)] = 1
-else:
- for i in range (0, MAX_CPUS):
- cpu_mask[i] = 1
-
-if not os.path.exists('results'):
- os.mkdir('results')
+
+ if cpu_list:
+ for p in re.split("[,]", cpu_list):
+ if int(p) < MAX_CPUS :
+ cpu_mask[int(p)] = 1
+ else:
+ for i in range (0, MAX_CPUS):
+ cpu_mask[i] = 1
+
+ if not os.path.exists('results'):
+ os.mkdir('results')
+ # The regular user needs to own the directory, not root.
+ fix_ownership('results')
+
+ os.chdir('results')
+ if os.path.exists(testname):
+ print('The test name directory already exists. Please provide a unique test name. Test re-run not supported, yet.')
+ sys.exit()
+ os.mkdir(testname)
# The regular user needs to own the directory, not root.
- fix_ownership('results')
-
-os.chdir('results')
-if os.path.exists(testname):
- print('The test name directory already exists. Please provide a unique test name. Test re-run not supported, yet.')
- sys.exit()
-os.mkdir(testname)
-# The regular user needs to own the directory, not root.
-fix_ownership(testname)
-os.chdir(testname)
-
-# Temporary (or perhaps not)
-cur_version = sys.version_info
-print('python version (should be >= 2.7):')
-print(cur_version)
-
-# Left as "cleanup" for potential future re-run ability.
-cleanup_data_files()
-
-if interval:
- filename = "/sys/kernel/debug/tracing/trace"
- clear_trace_file()
- set_trace_buffer_size()
- enable_trace()
- print('Sleeping for ', interval, 'seconds')
- time.sleep(int(interval))
- disable_trace()
-
-current_max_cpu = 0
-
-read_trace_data(filename)
-
-if interval:
- clear_trace_file()
- # Free the memory
- free_trace_buffer()
-
-if graph_data_present == False:
- print('No valid data to plot')
- sys.exit(2)
-
-for cpu_no in range(0, current_max_cpu + 1):
- plot_perf_busy_with_sample(cpu_no)
- plot_perf_busy(cpu_no)
- plot_durations(cpu_no)
- plot_loads(cpu_no)
-
-plot_pstate_cpu_with_sample()
-plot_pstate_cpu()
-plot_load_cpu()
-plot_frequency_cpu()
-plot_duration_cpu()
-plot_scaled_cpu()
-plot_boost_cpu()
-plot_ghz_cpu()
-
-# It is preferrable, but not necessary, that the regular user owns the files, not root.
-for root, dirs, files in os.walk('.'):
- for f in files:
- fix_ownership(f)
-
-os.chdir('../../')
+ fix_ownership(testname)
+ os.chdir(testname)
+
+ # Temporary (or perhaps not)
+ cur_version = sys.version_info
+ print('python version (should be >= 2.7):')
+ print(cur_version)
+
+ # Left as "cleanup" for potential future re-run ability.
+ cleanup_data_files()
+
+ if interval:
+ filename = "/sys/kernel/debug/tracing/trace"
+ clear_trace_file()
+ set_trace_buffer_size(memory)
+ enable_trace(trace_file)
+ print('Sleeping for ', interval, 'seconds')
+ time.sleep(int(interval))
+ disable_trace(trace_file)
+
+ current_max_cpu = 0
+
+ read_trace_data(filename, cpu_mask)
+
+ if interval:
+ clear_trace_file()
+ # Free the memory
+ free_trace_buffer()
+
+ if graph_data_present == False:
+ print('No valid data to plot')
+ sys.exit(2)
+
+ for cpu_no in range(0, current_max_cpu + 1):
+ plot_perf_busy_with_sample(cpu_no)
+ plot_perf_busy(cpu_no)
+ plot_durations(cpu_no)
+ plot_loads(cpu_no)
+
+ plot_pstate_cpu_with_sample()
+ plot_pstate_cpu()
+ plot_load_cpu()
+ plot_frequency_cpu()
+ plot_duration_cpu()
+ plot_scaled_cpu()
+ plot_boost_cpu()
+ plot_ghz_cpu()
+
+ # It is preferrable, but not necessary, that the regular user owns the files, not root.
+ for root, dirs, files in os.walk('.'):
+ for f in files:
+ fix_ownership(f)
+
+ os.chdir('../../')
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 47d3ba895d6d..bc5ae0872fed 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -2323,7 +2323,7 @@ int skx_pkg_cstate_limits[16] =
};
int icx_pkg_cstate_limits[16] =
- { PCL__0, PCL__2, PCL__6, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV,
+ { PCL__0, PCL__2, PCL__6, PCL__6, PCLRSV, PCLRSV, PCLRSV, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV,
PCLRSV, PCLRSV
};
diff --git a/tools/scripts/Makefile.include b/tools/scripts/Makefile.include
index b0be5f40a3f1..79d102304470 100644
--- a/tools/scripts/Makefile.include
+++ b/tools/scripts/Makefile.include
@@ -90,7 +90,7 @@ EXTRA_WARNINGS += -Wstrict-aliasing=3
else ifneq ($(CROSS_COMPILE),)
CLANG_CROSS_FLAGS := --target=$(notdir $(CROSS_COMPILE:%-=%))
-GCC_TOOLCHAIN_DIR := $(dir $(shell which $(CROSS_COMPILE)gcc))
+GCC_TOOLCHAIN_DIR := $(dir $(shell which $(CROSS_COMPILE)gcc 2>/dev/null))
ifneq ($(GCC_TOOLCHAIN_DIR),)
CLANG_CROSS_FLAGS += --prefix=$(GCC_TOOLCHAIN_DIR)$(notdir $(CROSS_COMPILE))
CLANG_CROSS_FLAGS += --sysroot=$(shell $(CROSS_COMPILE)gcc -print-sysroot)
diff --git a/tools/testing/cxl/Kbuild b/tools/testing/cxl/Kbuild
index 86deba8308a1..1acdf2fc31c5 100644
--- a/tools/testing/cxl/Kbuild
+++ b/tools/testing/cxl/Kbuild
@@ -1,7 +1,6 @@
# SPDX-License-Identifier: GPL-2.0
+ldflags-y += --wrap=acpi_table_parse_cedt
ldflags-y += --wrap=is_acpi_device_node
-ldflags-y += --wrap=acpi_get_table
-ldflags-y += --wrap=acpi_put_table
ldflags-y += --wrap=acpi_evaluate_integer
ldflags-y += --wrap=acpi_pci_find_root
ldflags-y += --wrap=pci_walk_bus
diff --git a/tools/testing/cxl/test/cxl.c b/tools/testing/cxl/test/cxl.c
index cb32f9e27d5d..736d99006fb7 100644
--- a/tools/testing/cxl/test/cxl.c
+++ b/tools/testing/cxl/test/cxl.c
@@ -182,6 +182,13 @@ static struct {
},
};
+struct acpi_cedt_cfmws *mock_cfmws[4] = {
+ [0] = &mock_cedt.cfmws0.cfmws,
+ [1] = &mock_cedt.cfmws1.cfmws,
+ [2] = &mock_cedt.cfmws2.cfmws,
+ [3] = &mock_cedt.cfmws3.cfmws,
+};
+
struct cxl_mock_res {
struct list_head list;
struct range range;
@@ -232,12 +239,6 @@ static struct cxl_mock_res *alloc_mock_res(resource_size_t size)
static int populate_cedt(void)
{
- struct acpi_cedt_cfmws *cfmws[4] = {
- [0] = &mock_cedt.cfmws0.cfmws,
- [1] = &mock_cedt.cfmws1.cfmws,
- [2] = &mock_cedt.cfmws2.cfmws,
- [3] = &mock_cedt.cfmws3.cfmws,
- };
struct cxl_mock_res *res;
int i;
@@ -257,8 +258,8 @@ static int populate_cedt(void)
chbs->length = size;
}
- for (i = 0; i < ARRAY_SIZE(cfmws); i++) {
- struct acpi_cedt_cfmws *window = cfmws[i];
+ for (i = 0; i < ARRAY_SIZE(mock_cfmws); i++) {
+ struct acpi_cedt_cfmws *window = mock_cfmws[i];
res = alloc_mock_res(window->window_size);
if (!res)
@@ -269,21 +270,44 @@ static int populate_cedt(void)
return 0;
}
-static acpi_status mock_acpi_get_table(char *signature, u32 instance,
- struct acpi_table_header **out_table)
+/*
+ * WARNING, this hack assumes the format of 'struct
+ * cxl_cfmws_context' and 'struct cxl_chbs_context' share the property that
+ * the first struct member is the device being probed by the cxl_acpi
+ * driver.
+ */
+struct cxl_cedt_context {
+ struct device *dev;
+};
+
+static int mock_acpi_table_parse_cedt(enum acpi_cedt_type id,
+ acpi_tbl_entry_handler_arg handler_arg,
+ void *arg)
{
- if (instance < U32_MAX || strcmp(signature, ACPI_SIG_CEDT) != 0)
- return acpi_get_table(signature, instance, out_table);
+ struct cxl_cedt_context *ctx = arg;
+ struct device *dev = ctx->dev;
+ union acpi_subtable_headers *h;
+ unsigned long end;
+ int i;
- *out_table = (struct acpi_table_header *) &mock_cedt;
- return AE_OK;
-}
+ if (dev != &cxl_acpi->dev)
+ return acpi_table_parse_cedt(id, handler_arg, arg);
-static void mock_acpi_put_table(struct acpi_table_header *table)
-{
- if (table == (struct acpi_table_header *) &mock_cedt)
- return;
- acpi_put_table(table);
+ if (id == ACPI_CEDT_TYPE_CHBS)
+ for (i = 0; i < ARRAY_SIZE(mock_cedt.chbs); i++) {
+ h = (union acpi_subtable_headers *)&mock_cedt.chbs[i];
+ end = (unsigned long)&mock_cedt.chbs[i + 1];
+ handler_arg(h, arg, end);
+ }
+
+ if (id == ACPI_CEDT_TYPE_CFMWS)
+ for (i = 0; i < ARRAY_SIZE(mock_cfmws); i++) {
+ h = (union acpi_subtable_headers *) mock_cfmws[i];
+ end = (unsigned long) h + mock_cfmws[i]->header.length;
+ handler_arg(h, arg, end);
+ }
+
+ return 0;
}
static bool is_mock_bridge(struct device *dev)
@@ -388,8 +412,7 @@ static struct cxl_mock_ops cxl_mock_ops = {
.is_mock_port = is_mock_port,
.is_mock_dev = is_mock_dev,
.mock_port = mock_cxl_root_port,
- .acpi_get_table = mock_acpi_get_table,
- .acpi_put_table = mock_acpi_put_table,
+ .acpi_table_parse_cedt = mock_acpi_table_parse_cedt,
.acpi_evaluate_integer = mock_acpi_evaluate_integer,
.acpi_pci_find_root = mock_acpi_pci_find_root,
.list = LIST_HEAD_INIT(cxl_mock_ops.list),
@@ -574,3 +597,4 @@ static __exit void cxl_test_exit(void)
module_init(cxl_test_init);
module_exit(cxl_test_exit);
MODULE_LICENSE("GPL v2");
+MODULE_IMPORT_NS(ACPI);
diff --git a/tools/testing/cxl/test/mem.c b/tools/testing/cxl/test/mem.c
index 12a8437a9ca0..8c2086c4caef 100644
--- a/tools/testing/cxl/test/mem.c
+++ b/tools/testing/cxl/test/mem.c
@@ -28,8 +28,24 @@ static struct cxl_cel_entry mock_cel[] = {
.opcode = cpu_to_le16(CXL_MBOX_OP_SET_LSA),
.effect = cpu_to_le16(EFFECT(1) | EFFECT(2)),
},
+ {
+ .opcode = cpu_to_le16(CXL_MBOX_OP_GET_HEALTH_INFO),
+ .effect = cpu_to_le16(0),
+ },
};
+/* See CXL 2.0 Table 181 Get Health Info Output Payload */
+struct cxl_mbox_health_info {
+ u8 health_status;
+ u8 media_status;
+ u8 ext_status;
+ u8 life_used;
+ __le16 temperature;
+ __le32 dirty_shutdowns;
+ __le32 volatile_errors;
+ __le32 pmem_errors;
+} __packed;
+
static struct {
struct cxl_mbox_get_supported_logs gsl;
struct cxl_gsl_entry entry;
@@ -54,7 +70,7 @@ static int mock_gsl(struct cxl_mbox_cmd *cmd)
return 0;
}
-static int mock_get_log(struct cxl_mem *cxlm, struct cxl_mbox_cmd *cmd)
+static int mock_get_log(struct cxl_dev_state *cxlds, struct cxl_mbox_cmd *cmd)
{
struct cxl_mbox_get_log *gl = cmd->payload_in;
u32 offset = le32_to_cpu(gl->offset);
@@ -64,7 +80,7 @@ static int mock_get_log(struct cxl_mem *cxlm, struct cxl_mbox_cmd *cmd)
if (cmd->size_in < sizeof(*gl))
return -EINVAL;
- if (length > cxlm->payload_size)
+ if (length > cxlds->payload_size)
return -EINVAL;
if (offset + length > sizeof(mock_cel))
return -EINVAL;
@@ -78,9 +94,9 @@ static int mock_get_log(struct cxl_mem *cxlm, struct cxl_mbox_cmd *cmd)
return 0;
}
-static int mock_id(struct cxl_mem *cxlm, struct cxl_mbox_cmd *cmd)
+static int mock_id(struct cxl_dev_state *cxlds, struct cxl_mbox_cmd *cmd)
{
- struct platform_device *pdev = to_platform_device(cxlm->dev);
+ struct platform_device *pdev = to_platform_device(cxlds->dev);
struct cxl_mbox_identify id = {
.fw_revision = { "mock fw v1 " },
.lsa_size = cpu_to_le32(LSA_SIZE),
@@ -120,10 +136,10 @@ static int mock_id(struct cxl_mem *cxlm, struct cxl_mbox_cmd *cmd)
return 0;
}
-static int mock_get_lsa(struct cxl_mem *cxlm, struct cxl_mbox_cmd *cmd)
+static int mock_get_lsa(struct cxl_dev_state *cxlds, struct cxl_mbox_cmd *cmd)
{
struct cxl_mbox_get_lsa *get_lsa = cmd->payload_in;
- void *lsa = dev_get_drvdata(cxlm->dev);
+ void *lsa = dev_get_drvdata(cxlds->dev);
u32 offset, length;
if (sizeof(*get_lsa) > cmd->size_in)
@@ -139,10 +155,10 @@ static int mock_get_lsa(struct cxl_mem *cxlm, struct cxl_mbox_cmd *cmd)
return 0;
}
-static int mock_set_lsa(struct cxl_mem *cxlm, struct cxl_mbox_cmd *cmd)
+static int mock_set_lsa(struct cxl_dev_state *cxlds, struct cxl_mbox_cmd *cmd)
{
struct cxl_mbox_set_lsa *set_lsa = cmd->payload_in;
- void *lsa = dev_get_drvdata(cxlm->dev);
+ void *lsa = dev_get_drvdata(cxlds->dev);
u32 offset, length;
if (sizeof(*set_lsa) > cmd->size_in)
@@ -156,9 +172,39 @@ static int mock_set_lsa(struct cxl_mem *cxlm, struct cxl_mbox_cmd *cmd)
return 0;
}
-static int cxl_mock_mbox_send(struct cxl_mem *cxlm, struct cxl_mbox_cmd *cmd)
+static int mock_health_info(struct cxl_dev_state *cxlds,
+ struct cxl_mbox_cmd *cmd)
{
- struct device *dev = cxlm->dev;
+ struct cxl_mbox_health_info health_info = {
+ /* set flags for maint needed, perf degraded, hw replacement */
+ .health_status = 0x7,
+ /* set media status to "All Data Lost" */
+ .media_status = 0x3,
+ /*
+ * set ext_status flags for:
+ * ext_life_used: normal,
+ * ext_temperature: critical,
+ * ext_corrected_volatile: warning,
+ * ext_corrected_persistent: normal,
+ */
+ .ext_status = 0x18,
+ .life_used = 15,
+ .temperature = cpu_to_le16(25),
+ .dirty_shutdowns = cpu_to_le32(10),
+ .volatile_errors = cpu_to_le32(20),
+ .pmem_errors = cpu_to_le32(30),
+ };
+
+ if (cmd->size_out < sizeof(health_info))
+ return -EINVAL;
+
+ memcpy(cmd->payload_out, &health_info, sizeof(health_info));
+ return 0;
+}
+
+static int cxl_mock_mbox_send(struct cxl_dev_state *cxlds, struct cxl_mbox_cmd *cmd)
+{
+ struct device *dev = cxlds->dev;
int rc = -EIO;
switch (cmd->opcode) {
@@ -166,16 +212,19 @@ static int cxl_mock_mbox_send(struct cxl_mem *cxlm, struct cxl_mbox_cmd *cmd)
rc = mock_gsl(cmd);
break;
case CXL_MBOX_OP_GET_LOG:
- rc = mock_get_log(cxlm, cmd);
+ rc = mock_get_log(cxlds, cmd);
break;
case CXL_MBOX_OP_IDENTIFY:
- rc = mock_id(cxlm, cmd);
+ rc = mock_id(cxlds, cmd);
break;
case CXL_MBOX_OP_GET_LSA:
- rc = mock_get_lsa(cxlm, cmd);
+ rc = mock_get_lsa(cxlds, cmd);
break;
case CXL_MBOX_OP_SET_LSA:
- rc = mock_set_lsa(cxlm, cmd);
+ rc = mock_set_lsa(cxlds, cmd);
+ break;
+ case CXL_MBOX_OP_GET_HEALTH_INFO:
+ rc = mock_health_info(cxlds, cmd);
break;
default:
break;
@@ -196,7 +245,7 @@ static int cxl_mock_mem_probe(struct platform_device *pdev)
{
struct device *dev = &pdev->dev;
struct cxl_memdev *cxlmd;
- struct cxl_mem *cxlm;
+ struct cxl_dev_state *cxlds;
void *lsa;
int rc;
@@ -208,30 +257,30 @@ static int cxl_mock_mem_probe(struct platform_device *pdev)
return rc;
dev_set_drvdata(dev, lsa);
- cxlm = cxl_mem_create(dev);
- if (IS_ERR(cxlm))
- return PTR_ERR(cxlm);
+ cxlds = cxl_dev_state_create(dev);
+ if (IS_ERR(cxlds))
+ return PTR_ERR(cxlds);
- cxlm->mbox_send = cxl_mock_mbox_send;
- cxlm->payload_size = SZ_4K;
+ cxlds->mbox_send = cxl_mock_mbox_send;
+ cxlds->payload_size = SZ_4K;
- rc = cxl_mem_enumerate_cmds(cxlm);
+ rc = cxl_enumerate_cmds(cxlds);
if (rc)
return rc;
- rc = cxl_mem_identify(cxlm);
+ rc = cxl_dev_state_identify(cxlds);
if (rc)
return rc;
- rc = cxl_mem_create_range_info(cxlm);
+ rc = cxl_mem_create_range_info(cxlds);
if (rc)
return rc;
- cxlmd = devm_cxl_add_memdev(cxlm);
+ cxlmd = devm_cxl_add_memdev(cxlds);
if (IS_ERR(cxlmd))
return PTR_ERR(cxlmd);
- if (range_len(&cxlm->pmem_range) && IS_ENABLED(CONFIG_CXL_PMEM))
+ if (range_len(&cxlds->pmem_range) && IS_ENABLED(CONFIG_CXL_PMEM))
rc = devm_cxl_add_nvdimm(dev, cxlmd);
return 0;
diff --git a/tools/testing/cxl/test/mock.c b/tools/testing/cxl/test/mock.c
index b8c108abcf07..17408f892df4 100644
--- a/tools/testing/cxl/test/mock.c
+++ b/tools/testing/cxl/test/mock.c
@@ -58,36 +58,23 @@ bool __wrap_is_acpi_device_node(const struct fwnode_handle *fwnode)
}
EXPORT_SYMBOL(__wrap_is_acpi_device_node);
-acpi_status __wrap_acpi_get_table(char *signature, u32 instance,
- struct acpi_table_header **out_table)
+int __wrap_acpi_table_parse_cedt(enum acpi_cedt_type id,
+ acpi_tbl_entry_handler_arg handler_arg,
+ void *arg)
{
- int index;
+ int index, rc;
struct cxl_mock_ops *ops = get_cxl_mock_ops(&index);
- acpi_status status;
if (ops)
- status = ops->acpi_get_table(signature, instance, out_table);
+ rc = ops->acpi_table_parse_cedt(id, handler_arg, arg);
else
- status = acpi_get_table(signature, instance, out_table);
+ rc = acpi_table_parse_cedt(id, handler_arg, arg);
put_cxl_mock_ops(index);
- return status;
-}
-EXPORT_SYMBOL(__wrap_acpi_get_table);
-
-void __wrap_acpi_put_table(struct acpi_table_header *table)
-{
- int index;
- struct cxl_mock_ops *ops = get_cxl_mock_ops(&index);
-
- if (ops)
- ops->acpi_put_table(table);
- else
- acpi_put_table(table);
- put_cxl_mock_ops(index);
+ return rc;
}
-EXPORT_SYMBOL(__wrap_acpi_put_table);
+EXPORT_SYMBOL_NS_GPL(__wrap_acpi_table_parse_cedt, ACPI);
acpi_status __wrap_acpi_evaluate_integer(acpi_handle handle,
acpi_string pathname,
@@ -169,3 +156,4 @@ __wrap_nvdimm_bus_register(struct device *dev,
EXPORT_SYMBOL_GPL(__wrap_nvdimm_bus_register);
MODULE_LICENSE("GPL v2");
+MODULE_IMPORT_NS(ACPI);
diff --git a/tools/testing/cxl/test/mock.h b/tools/testing/cxl/test/mock.h
index 805a94cb3fbe..15ed0fd877e4 100644
--- a/tools/testing/cxl/test/mock.h
+++ b/tools/testing/cxl/test/mock.h
@@ -6,9 +6,9 @@
struct cxl_mock_ops {
struct list_head list;
bool (*is_mock_adev)(struct acpi_device *dev);
- acpi_status (*acpi_get_table)(char *signature, u32 instance,
- struct acpi_table_header **out_table);
- void (*acpi_put_table)(struct acpi_table_header *table);
+ int (*acpi_table_parse_cedt)(enum acpi_cedt_type id,
+ acpi_tbl_entry_handler_arg handler_arg,
+ void *arg);
bool (*is_mock_bridge)(struct device *dev);
acpi_status (*acpi_evaluate_integer)(acpi_handle handle,
acpi_string pathname,
diff --git a/tools/testing/kunit/kunit_kernel.py b/tools/testing/kunit/kunit_kernel.py
index 44bbe54f25f1..3c4196cef3ed 100644
--- a/tools/testing/kunit/kunit_kernel.py
+++ b/tools/testing/kunit/kunit_kernel.py
@@ -6,6 +6,7 @@
# Author: Felix Guo <[email protected]>
# Author: Brendan Higgins <[email protected]>
+import importlib.abc
import importlib.util
import logging
import subprocess
diff --git a/tools/testing/kunit/run_checks.py b/tools/testing/kunit/run_checks.py
index 4f32133ed77c..13d854afca9d 100755
--- a/tools/testing/kunit/run_checks.py
+++ b/tools/testing/kunit/run_checks.py
@@ -61,7 +61,7 @@ def main(argv: Sequence[str]) -> None:
elif isinstance(ex, subprocess.CalledProcessError):
print(f'{name}: FAILED')
else:
- print('{name}: unexpected exception: {ex}')
+ print(f'{name}: unexpected exception: {ex}')
continue
output = ex.output
diff --git a/tools/testing/nvdimm/Kbuild b/tools/testing/nvdimm/Kbuild
index 47f9cc9dcd94..c57d9e9d4480 100644
--- a/tools/testing/nvdimm/Kbuild
+++ b/tools/testing/nvdimm/Kbuild
@@ -35,8 +35,6 @@ obj-$(CONFIG_DAX) += dax.o
endif
obj-$(CONFIG_DEV_DAX) += device_dax.o
obj-$(CONFIG_DEV_DAX_PMEM) += dax_pmem.o
-obj-$(CONFIG_DEV_DAX_PMEM) += dax_pmem_core.o
-obj-$(CONFIG_DEV_DAX_PMEM_COMPAT) += dax_pmem_compat.o
nfit-y := $(ACPI_SRC)/core.o
nfit-y += $(ACPI_SRC)/intel.o
@@ -67,12 +65,8 @@ device_dax-y += dax-dev.o
device_dax-y += device_dax_test.o
device_dax-y += config_check.o
-dax_pmem-y := $(DAX_SRC)/pmem/pmem.o
+dax_pmem-y := $(DAX_SRC)/pmem.o
dax_pmem-y += dax_pmem_test.o
-dax_pmem_core-y := $(DAX_SRC)/pmem/core.o
-dax_pmem_core-y += dax_pmem_core_test.o
-dax_pmem_compat-y := $(DAX_SRC)/pmem/compat.o
-dax_pmem_compat-y += dax_pmem_compat_test.o
dax_pmem-y += config_check.o
libnvdimm-y := $(NVDIMM_SRC)/core.o
diff --git a/tools/testing/nvdimm/dax_pmem_compat_test.c b/tools/testing/nvdimm/dax_pmem_compat_test.c
deleted file mode 100644
index 7cd1877f3765..000000000000
--- a/tools/testing/nvdimm/dax_pmem_compat_test.c
+++ /dev/null
@@ -1,8 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-// Copyright(c) 2019 Intel Corporation. All rights reserved.
-
-#include <linux/module.h>
-#include <linux/printk.h>
-#include "watermark.h"
-
-nfit_test_watermark(dax_pmem_compat);
diff --git a/tools/testing/nvdimm/dax_pmem_core_test.c b/tools/testing/nvdimm/dax_pmem_core_test.c
deleted file mode 100644
index a4249cdbeec1..000000000000
--- a/tools/testing/nvdimm/dax_pmem_core_test.c
+++ /dev/null
@@ -1,8 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-// Copyright(c) 2019 Intel Corporation. All rights reserved.
-
-#include <linux/module.h>
-#include <linux/printk.h>
-#include "watermark.h"
-
-nfit_test_watermark(dax_pmem_core);
diff --git a/tools/testing/nvdimm/test/iomap.c b/tools/testing/nvdimm/test/iomap.c
index ed563bdd88f3..b752ce47ead3 100644
--- a/tools/testing/nvdimm/test/iomap.c
+++ b/tools/testing/nvdimm/test/iomap.c
@@ -100,25 +100,17 @@ static void nfit_test_kill(void *_pgmap)
{
struct dev_pagemap *pgmap = _pgmap;
- WARN_ON(!pgmap || !pgmap->ref);
-
- if (pgmap->ops && pgmap->ops->kill)
- pgmap->ops->kill(pgmap);
- else
- percpu_ref_kill(pgmap->ref);
-
- if (pgmap->ops && pgmap->ops->cleanup) {
- pgmap->ops->cleanup(pgmap);
- } else {
- wait_for_completion(&pgmap->done);
- percpu_ref_exit(pgmap->ref);
- }
+ WARN_ON(!pgmap);
+
+ percpu_ref_kill(&pgmap->ref);
+
+ wait_for_completion(&pgmap->done);
+ percpu_ref_exit(&pgmap->ref);
}
static void dev_pagemap_percpu_release(struct percpu_ref *ref)
{
- struct dev_pagemap *pgmap =
- container_of(ref, struct dev_pagemap, internal_ref);
+ struct dev_pagemap *pgmap = container_of(ref, struct dev_pagemap, ref);
complete(&pgmap->done);
}
@@ -132,22 +124,11 @@ void *__wrap_devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
if (!nfit_res)
return devm_memremap_pages(dev, pgmap);
- if (!pgmap->ref) {
- if (pgmap->ops && (pgmap->ops->kill || pgmap->ops->cleanup))
- return ERR_PTR(-EINVAL);
-
- init_completion(&pgmap->done);
- error = percpu_ref_init(&pgmap->internal_ref,
- dev_pagemap_percpu_release, 0, GFP_KERNEL);
- if (error)
- return ERR_PTR(error);
- pgmap->ref = &pgmap->internal_ref;
- } else {
- if (!pgmap->ops || !pgmap->ops->kill || !pgmap->ops->cleanup) {
- WARN(1, "Missing reference count teardown definition\n");
- return ERR_PTR(-EINVAL);
- }
- }
+ init_completion(&pgmap->done);
+ error = percpu_ref_init(&pgmap->ref, dev_pagemap_percpu_release, 0,
+ GFP_KERNEL);
+ if (error)
+ return ERR_PTR(error);
error = devm_add_action_or_reset(dev, nfit_test_kill, pgmap);
if (error)
diff --git a/tools/testing/nvdimm/test/ndtest.c b/tools/testing/nvdimm/test/ndtest.c
index 6862915f1fb0..3ca7c32e9362 100644
--- a/tools/testing/nvdimm/test/ndtest.c
+++ b/tools/testing/nvdimm/test/ndtest.c
@@ -1054,10 +1054,6 @@ static __init int ndtest_init(void)
libnvdimm_test();
device_dax_test();
dax_pmem_test();
- dax_pmem_core_test();
-#ifdef CONFIG_DEV_DAX_PMEM_COMPAT
- dax_pmem_compat_test();
-#endif
nfit_test_setup(ndtest_resource_lookup, NULL);
diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c
index b1bff5fb0f65..0bc91ffee257 100644
--- a/tools/testing/nvdimm/test/nfit.c
+++ b/tools/testing/nvdimm/test/nfit.c
@@ -3300,10 +3300,6 @@ static __init int nfit_test_init(void)
acpi_nfit_test();
device_dax_test();
dax_pmem_test();
- dax_pmem_core_test();
-#ifdef CONFIG_DEV_DAX_PMEM_COMPAT
- dax_pmem_compat_test();
-#endif
nfit_test_setup(nfit_test_lookup, nfit_test_evaluate_dsm);
diff --git a/tools/testing/scatterlist/linux/mm.h b/tools/testing/scatterlist/linux/mm.h
index 16ec895bbe5f..5bd9e6e80625 100644
--- a/tools/testing/scatterlist/linux/mm.h
+++ b/tools/testing/scatterlist/linux/mm.h
@@ -74,7 +74,7 @@ static inline unsigned long page_to_phys(struct page *page)
__UNIQUE_ID(min1_), __UNIQUE_ID(min2_), \
x, y)
-#define preemptible() (1)
+#define pagefault_disabled() (0)
static inline void *kmap(struct page *page)
{
@@ -127,6 +127,7 @@ kmalloc_array(unsigned int n, unsigned int size, unsigned int flags)
#define kmemleak_free(a)
#define PageSlab(p) (0)
+#define flush_dcache_page(p)
#define MAX_ERRNO 4095
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index c852eb40c4f7..d08fe4cfe811 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -1,5 +1,6 @@
# SPDX-License-Identifier: GPL-2.0
-TARGETS = arm64
+TARGETS += alsa
+TARGETS += arm64
TARGETS += bpf
TARGETS += breakpoints
TARGETS += capabilities
diff --git a/tools/testing/selftests/alsa/.gitignore b/tools/testing/selftests/alsa/.gitignore
new file mode 100644
index 000000000000..3bb7c41266a8
--- /dev/null
+++ b/tools/testing/selftests/alsa/.gitignore
@@ -0,0 +1 @@
+mixer-test
diff --git a/tools/testing/selftests/alsa/Makefile b/tools/testing/selftests/alsa/Makefile
new file mode 100644
index 000000000000..f64d9090426d
--- /dev/null
+++ b/tools/testing/selftests/alsa/Makefile
@@ -0,0 +1,9 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+
+CFLAGS += $(shell pkg-config --cflags alsa)
+LDLIBS += $(shell pkg-config --libs alsa)
+
+TEST_GEN_PROGS := mixer-test
+
+include ../lib.mk
diff --git a/tools/testing/selftests/alsa/mixer-test.c b/tools/testing/selftests/alsa/mixer-test.c
new file mode 100644
index 000000000000..17f158d7a767
--- /dev/null
+++ b/tools/testing/selftests/alsa/mixer-test.c
@@ -0,0 +1,705 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// kselftest for the ALSA mixer API
+//
+// Original author: Mark Brown <[email protected]>
+// Copyright (c) 2021 Arm Limited
+
+// This test will iterate over all cards detected in the system, exercising
+// every mixer control it can find. This may conflict with other system
+// software if there is audio activity so is best run on a system with a
+// minimal active userspace.
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdbool.h>
+#include <string.h>
+#include <getopt.h>
+#include <stdarg.h>
+#include <ctype.h>
+#include <math.h>
+#include <errno.h>
+#include <assert.h>
+#include <alsa/asoundlib.h>
+#include <poll.h>
+#include <stdint.h>
+
+#include "../kselftest.h"
+
+#define TESTS_PER_CONTROL 3
+
+struct card_data {
+ snd_ctl_t *handle;
+ int card;
+ int num_ctls;
+ snd_ctl_elem_list_t *ctls;
+ struct card_data *next;
+};
+
+struct ctl_data {
+ const char *name;
+ snd_ctl_elem_id_t *id;
+ snd_ctl_elem_info_t *info;
+ snd_ctl_elem_value_t *def_val;
+ int elem;
+ struct card_data *card;
+ struct ctl_data *next;
+};
+
+static const char *alsa_config =
+"ctl.hw {\n"
+" @args [ CARD ]\n"
+" @args.CARD.type string\n"
+" type hw\n"
+" card $CARD\n"
+"}\n"
+;
+
+int num_cards = 0;
+int num_controls = 0;
+struct card_data *card_list = NULL;
+struct ctl_data *ctl_list = NULL;
+
+#ifdef SND_LIB_VER
+#if SND_LIB_VERSION >= SND_LIB_VER(1, 2, 6)
+#define LIB_HAS_LOAD_STRING
+#endif
+#endif
+
+#ifndef LIB_HAS_LOAD_STRING
+int snd_config_load_string(snd_config_t **config, const char *s, size_t size)
+{
+ snd_input_t *input;
+ snd_config_t *dst;
+ int err;
+
+ assert(config && s);
+ if (size == 0)
+ size = strlen(s);
+ err = snd_input_buffer_open(&input, s, size);
+ if (err < 0)
+ return err;
+ err = snd_config_top(&dst);
+ if (err < 0) {
+ snd_input_close(input);
+ return err;
+ }
+ err = snd_config_load(dst, input);
+ snd_input_close(input);
+ if (err < 0) {
+ snd_config_delete(dst);
+ return err;
+ }
+ *config = dst;
+ return 0;
+}
+#endif
+
+void find_controls(void)
+{
+ char name[32];
+ int card, ctl, err;
+ struct card_data *card_data;
+ struct ctl_data *ctl_data;
+ snd_config_t *config;
+
+ card = -1;
+ if (snd_card_next(&card) < 0 || card < 0)
+ return;
+
+ err = snd_config_load_string(&config, alsa_config, strlen(alsa_config));
+ if (err < 0) {
+ ksft_print_msg("Unable to parse custom alsa-lib configuration: %s\n",
+ snd_strerror(err));
+ ksft_exit_fail();
+ }
+
+ while (card >= 0) {
+ sprintf(name, "hw:%d", card);
+
+ card_data = malloc(sizeof(*card_data));
+ if (!card_data)
+ ksft_exit_fail_msg("Out of memory\n");
+
+ err = snd_ctl_open_lconf(&card_data->handle, name, 0, config);
+ if (err < 0) {
+ ksft_print_msg("Failed to get hctl for card %d: %s\n",
+ card, snd_strerror(err));
+ goto next_card;
+ }
+
+ /* Count controls */
+ snd_ctl_elem_list_malloc(&card_data->ctls);
+ snd_ctl_elem_list(card_data->handle, card_data->ctls);
+ card_data->num_ctls = snd_ctl_elem_list_get_count(card_data->ctls);
+
+ /* Enumerate control information */
+ snd_ctl_elem_list_alloc_space(card_data->ctls, card_data->num_ctls);
+ snd_ctl_elem_list(card_data->handle, card_data->ctls);
+
+ card_data->card = num_cards++;
+ card_data->next = card_list;
+ card_list = card_data;
+
+ num_controls += card_data->num_ctls;
+
+ for (ctl = 0; ctl < card_data->num_ctls; ctl++) {
+ ctl_data = malloc(sizeof(*ctl_data));
+ if (!ctl_data)
+ ksft_exit_fail_msg("Out of memory\n");
+
+ ctl_data->card = card_data;
+ ctl_data->elem = ctl;
+ ctl_data->name = snd_ctl_elem_list_get_name(card_data->ctls,
+ ctl);
+
+ err = snd_ctl_elem_id_malloc(&ctl_data->id);
+ if (err < 0)
+ ksft_exit_fail_msg("Out of memory\n");
+
+ err = snd_ctl_elem_info_malloc(&ctl_data->info);
+ if (err < 0)
+ ksft_exit_fail_msg("Out of memory\n");
+
+ err = snd_ctl_elem_value_malloc(&ctl_data->def_val);
+ if (err < 0)
+ ksft_exit_fail_msg("Out of memory\n");
+
+ snd_ctl_elem_list_get_id(card_data->ctls, ctl,
+ ctl_data->id);
+ snd_ctl_elem_info_set_id(ctl_data->info, ctl_data->id);
+ err = snd_ctl_elem_info(card_data->handle,
+ ctl_data->info);
+ if (err < 0) {
+ ksft_print_msg("%s getting info for %d\n",
+ snd_strerror(err),
+ ctl_data->name);
+ }
+
+ snd_ctl_elem_value_set_id(ctl_data->def_val,
+ ctl_data->id);
+
+ ctl_data->next = ctl_list;
+ ctl_list = ctl_data;
+ }
+
+ next_card:
+ if (snd_card_next(&card) < 0) {
+ ksft_print_msg("snd_card_next");
+ break;
+ }
+ }
+
+ snd_config_delete(config);
+}
+
+bool ctl_value_index_valid(struct ctl_data *ctl, snd_ctl_elem_value_t *val,
+ int index)
+{
+ long int_val;
+ long long int64_val;
+
+ switch (snd_ctl_elem_info_get_type(ctl->info)) {
+ case SND_CTL_ELEM_TYPE_NONE:
+ ksft_print_msg("%s.%d Invalid control type NONE\n",
+ ctl->name, index);
+ return false;
+
+ case SND_CTL_ELEM_TYPE_BOOLEAN:
+ int_val = snd_ctl_elem_value_get_boolean(val, index);
+ switch (int_val) {
+ case 0:
+ case 1:
+ break;
+ default:
+ ksft_print_msg("%s.%d Invalid boolean value %ld\n",
+ ctl->name, index, int_val);
+ return false;
+ }
+ break;
+
+ case SND_CTL_ELEM_TYPE_INTEGER:
+ int_val = snd_ctl_elem_value_get_integer(val, index);
+
+ if (int_val < snd_ctl_elem_info_get_min(ctl->info)) {
+ ksft_print_msg("%s.%d value %ld less than minimum %ld\n",
+ ctl->name, index, int_val,
+ snd_ctl_elem_info_get_min(ctl->info));
+ return false;
+ }
+
+ if (int_val > snd_ctl_elem_info_get_max(ctl->info)) {
+ ksft_print_msg("%s.%d value %ld more than maximum %ld\n",
+ ctl->name, index, int_val,
+ snd_ctl_elem_info_get_max(ctl->info));
+ return false;
+ }
+
+ /* Only check step size if there is one and we're in bounds */
+ if (snd_ctl_elem_info_get_step(ctl->info) &&
+ (int_val - snd_ctl_elem_info_get_min(ctl->info) %
+ snd_ctl_elem_info_get_step(ctl->info))) {
+ ksft_print_msg("%s.%d value %ld invalid for step %ld minimum %ld\n",
+ ctl->name, index, int_val,
+ snd_ctl_elem_info_get_step(ctl->info),
+ snd_ctl_elem_info_get_min(ctl->info));
+ return false;
+ }
+ break;
+
+ case SND_CTL_ELEM_TYPE_INTEGER64:
+ int64_val = snd_ctl_elem_value_get_integer64(val, index);
+
+ if (int64_val < snd_ctl_elem_info_get_min64(ctl->info)) {
+ ksft_print_msg("%s.%d value %lld less than minimum %lld\n",
+ ctl->name, index, int64_val,
+ snd_ctl_elem_info_get_min64(ctl->info));
+ return false;
+ }
+
+ if (int64_val > snd_ctl_elem_info_get_max64(ctl->info)) {
+ ksft_print_msg("%s.%d value %lld more than maximum %lld\n",
+ ctl->name, index, int64_val,
+ snd_ctl_elem_info_get_max(ctl->info));
+ return false;
+ }
+
+ /* Only check step size if there is one and we're in bounds */
+ if (snd_ctl_elem_info_get_step64(ctl->info) &&
+ (int64_val - snd_ctl_elem_info_get_min64(ctl->info)) %
+ snd_ctl_elem_info_get_step64(ctl->info)) {
+ ksft_print_msg("%s.%d value %lld invalid for step %lld minimum %lld\n",
+ ctl->name, index, int64_val,
+ snd_ctl_elem_info_get_step64(ctl->info),
+ snd_ctl_elem_info_get_min64(ctl->info));
+ return false;
+ }
+ break;
+
+ case SND_CTL_ELEM_TYPE_ENUMERATED:
+ int_val = snd_ctl_elem_value_get_enumerated(val, index);
+
+ if (int_val < 0) {
+ ksft_print_msg("%s.%d negative value %ld for enumeration\n",
+ ctl->name, index, int_val);
+ return false;
+ }
+
+ if (int_val >= snd_ctl_elem_info_get_items(ctl->info)) {
+ ksft_print_msg("%s.%d value %ld more than item count %ld\n",
+ ctl->name, index, int_val,
+ snd_ctl_elem_info_get_items(ctl->info));
+ return false;
+ }
+ break;
+
+ default:
+ /* No tests for other types */
+ break;
+ }
+
+ return true;
+}
+
+/*
+ * Check that the provided value meets the constraints for the
+ * provided control.
+ */
+bool ctl_value_valid(struct ctl_data *ctl, snd_ctl_elem_value_t *val)
+{
+ int i;
+ bool valid = true;
+
+ for (i = 0; i < snd_ctl_elem_info_get_count(ctl->info); i++)
+ if (!ctl_value_index_valid(ctl, val, i))
+ valid = false;
+
+ return valid;
+}
+
+/*
+ * Check that we can read the default value and it is valid. Write
+ * tests use the read value to restore the default.
+ */
+void test_ctl_get_value(struct ctl_data *ctl)
+{
+ int err;
+
+ /* If the control is turned off let's be polite */
+ if (snd_ctl_elem_info_is_inactive(ctl->info)) {
+ ksft_print_msg("%s is inactive\n", ctl->name);
+ ksft_test_result_skip("get_value.%d.%d\n",
+ ctl->card->card, ctl->elem);
+ return;
+ }
+
+ /* Can't test reading on an unreadable control */
+ if (!snd_ctl_elem_info_is_readable(ctl->info)) {
+ ksft_print_msg("%s is not readable\n", ctl->name);
+ ksft_test_result_skip("get_value.%d.%d\n",
+ ctl->card->card, ctl->elem);
+ return;
+ }
+
+ err = snd_ctl_elem_read(ctl->card->handle, ctl->def_val);
+ if (err < 0) {
+ ksft_print_msg("snd_ctl_elem_read() failed: %s\n",
+ snd_strerror(err));
+ goto out;
+ }
+
+ if (!ctl_value_valid(ctl, ctl->def_val))
+ err = -EINVAL;
+
+out:
+ ksft_test_result(err >= 0, "get_value.%d.%d\n",
+ ctl->card->card, ctl->elem);
+}
+
+bool show_mismatch(struct ctl_data *ctl, int index,
+ snd_ctl_elem_value_t *read_val,
+ snd_ctl_elem_value_t *expected_val)
+{
+ long long expected_int, read_int;
+
+ /*
+ * We factor out the code to compare values representable as
+ * integers, ensure that check doesn't log otherwise.
+ */
+ expected_int = 0;
+ read_int = 0;
+
+ switch (snd_ctl_elem_info_get_type(ctl->info)) {
+ case SND_CTL_ELEM_TYPE_BOOLEAN:
+ expected_int = snd_ctl_elem_value_get_boolean(expected_val,
+ index);
+ read_int = snd_ctl_elem_value_get_boolean(read_val, index);
+ break;
+
+ case SND_CTL_ELEM_TYPE_INTEGER:
+ expected_int = snd_ctl_elem_value_get_integer(expected_val,
+ index);
+ read_int = snd_ctl_elem_value_get_integer(read_val, index);
+ break;
+
+ case SND_CTL_ELEM_TYPE_INTEGER64:
+ expected_int = snd_ctl_elem_value_get_integer64(expected_val,
+ index);
+ read_int = snd_ctl_elem_value_get_integer64(read_val,
+ index);
+ break;
+
+ case SND_CTL_ELEM_TYPE_ENUMERATED:
+ expected_int = snd_ctl_elem_value_get_enumerated(expected_val,
+ index);
+ read_int = snd_ctl_elem_value_get_enumerated(read_val,
+ index);
+ break;
+
+ default:
+ break;
+ }
+
+ if (expected_int != read_int) {
+ /*
+ * NOTE: The volatile attribute means that the hardware
+ * can voluntarily change the state of control element
+ * independent of any operation by software.
+ */
+ bool is_volatile = snd_ctl_elem_info_is_volatile(ctl->info);
+ ksft_print_msg("%s.%d expected %lld but read %lld, is_volatile %d\n",
+ ctl->name, index, expected_int, read_int, is_volatile);
+ return !is_volatile;
+ } else {
+ return false;
+ }
+}
+
+/*
+ * Write a value then if possible verify that we get the expected
+ * result. An optional expected value can be provided if we expect
+ * the write to fail, for verifying that invalid writes don't corrupt
+ * anything.
+ */
+int write_and_verify(struct ctl_data *ctl,
+ snd_ctl_elem_value_t *write_val,
+ snd_ctl_elem_value_t *expected_val)
+{
+ int err, i;
+ bool error_expected, mismatch_shown;
+ snd_ctl_elem_value_t *read_val, *w_val;
+ snd_ctl_elem_value_alloca(&read_val);
+ snd_ctl_elem_value_alloca(&w_val);
+
+ /*
+ * We need to copy the write value since writing can modify
+ * the value which causes surprises, and allocate an expected
+ * value if we expect to read back what we wrote.
+ */
+ snd_ctl_elem_value_copy(w_val, write_val);
+ if (expected_val) {
+ error_expected = true;
+ } else {
+ error_expected = false;
+ snd_ctl_elem_value_alloca(&expected_val);
+ snd_ctl_elem_value_copy(expected_val, write_val);
+ }
+
+ /*
+ * Do the write, if we have an expected value ignore the error
+ * and carry on to validate the expected value.
+ */
+ err = snd_ctl_elem_write(ctl->card->handle, w_val);
+ if (err < 0 && !error_expected) {
+ ksft_print_msg("snd_ctl_elem_write() failed: %s\n",
+ snd_strerror(err));
+ return err;
+ }
+
+ /* Can we do the verification part? */
+ if (!snd_ctl_elem_info_is_readable(ctl->info))
+ return err;
+
+ snd_ctl_elem_value_set_id(read_val, ctl->id);
+
+ err = snd_ctl_elem_read(ctl->card->handle, read_val);
+ if (err < 0) {
+ ksft_print_msg("snd_ctl_elem_read() failed: %s\n",
+ snd_strerror(err));
+ return err;
+ }
+
+ /*
+ * Use the libray to compare values, if there's a mismatch
+ * carry on and try to provide a more useful diagnostic than
+ * just "mismatch".
+ */
+ if (!snd_ctl_elem_value_compare(expected_val, read_val))
+ return 0;
+
+ mismatch_shown = false;
+ for (i = 0; i < snd_ctl_elem_info_get_count(ctl->info); i++)
+ if (show_mismatch(ctl, i, read_val, expected_val))
+ mismatch_shown = true;
+
+ if (!mismatch_shown)
+ ksft_print_msg("%s read and written values differ\n",
+ ctl->name);
+
+ return -1;
+}
+
+/*
+ * Make sure we can write the default value back to the control, this
+ * should validate that at least some write works.
+ */
+void test_ctl_write_default(struct ctl_data *ctl)
+{
+ int err;
+
+ /* If the control is turned off let's be polite */
+ if (snd_ctl_elem_info_is_inactive(ctl->info)) {
+ ksft_print_msg("%s is inactive\n", ctl->name);
+ ksft_test_result_skip("write_default.%d.%d\n",
+ ctl->card->card, ctl->elem);
+ return;
+ }
+
+ if (!snd_ctl_elem_info_is_writable(ctl->info)) {
+ ksft_print_msg("%s is not writeable\n", ctl->name);
+ ksft_test_result_skip("write_default.%d.%d\n",
+ ctl->card->card, ctl->elem);
+ return;
+ }
+
+ /* No idea what the default was for unreadable controls */
+ if (!snd_ctl_elem_info_is_readable(ctl->info)) {
+ ksft_print_msg("%s couldn't read default\n", ctl->name);
+ ksft_test_result_skip("write_default.%d.%d\n",
+ ctl->card->card, ctl->elem);
+ return;
+ }
+
+ err = write_and_verify(ctl, ctl->def_val, NULL);
+
+ ksft_test_result(err >= 0, "write_default.%d.%d\n",
+ ctl->card->card, ctl->elem);
+}
+
+bool test_ctl_write_valid_boolean(struct ctl_data *ctl)
+{
+ int err, i, j;
+ bool fail = false;
+ snd_ctl_elem_value_t *val;
+ snd_ctl_elem_value_alloca(&val);
+
+ snd_ctl_elem_value_set_id(val, ctl->id);
+
+ for (i = 0; i < snd_ctl_elem_info_get_count(ctl->info); i++) {
+ for (j = 0; j < 2; j++) {
+ snd_ctl_elem_value_set_boolean(val, i, j);
+ err = write_and_verify(ctl, val, NULL);
+ if (err != 0)
+ fail = true;
+ }
+ }
+
+ return !fail;
+}
+
+bool test_ctl_write_valid_integer(struct ctl_data *ctl)
+{
+ int err;
+ int i;
+ long j, step;
+ bool fail = false;
+ snd_ctl_elem_value_t *val;
+ snd_ctl_elem_value_alloca(&val);
+
+ snd_ctl_elem_value_set_id(val, ctl->id);
+
+ step = snd_ctl_elem_info_get_step(ctl->info);
+ if (!step)
+ step = 1;
+
+ for (i = 0; i < snd_ctl_elem_info_get_count(ctl->info); i++) {
+ for (j = snd_ctl_elem_info_get_min(ctl->info);
+ j <= snd_ctl_elem_info_get_max(ctl->info); j += step) {
+
+ snd_ctl_elem_value_set_integer(val, i, j);
+ err = write_and_verify(ctl, val, NULL);
+ if (err != 0)
+ fail = true;
+ }
+ }
+
+
+ return !fail;
+}
+
+bool test_ctl_write_valid_integer64(struct ctl_data *ctl)
+{
+ int err, i;
+ long long j, step;
+ bool fail = false;
+ snd_ctl_elem_value_t *val;
+ snd_ctl_elem_value_alloca(&val);
+
+ snd_ctl_elem_value_set_id(val, ctl->id);
+
+ step = snd_ctl_elem_info_get_step64(ctl->info);
+ if (!step)
+ step = 1;
+
+ for (i = 0; i < snd_ctl_elem_info_get_count(ctl->info); i++) {
+ for (j = snd_ctl_elem_info_get_min64(ctl->info);
+ j <= snd_ctl_elem_info_get_max64(ctl->info); j += step) {
+
+ snd_ctl_elem_value_set_integer64(val, i, j);
+ err = write_and_verify(ctl, val, NULL);
+ if (err != 0)
+ fail = true;
+ }
+ }
+
+ return !fail;
+}
+
+bool test_ctl_write_valid_enumerated(struct ctl_data *ctl)
+{
+ int err, i, j;
+ bool fail = false;
+ snd_ctl_elem_value_t *val;
+ snd_ctl_elem_value_alloca(&val);
+
+ snd_ctl_elem_value_set_id(val, ctl->id);
+
+ for (i = 0; i < snd_ctl_elem_info_get_count(ctl->info); i++) {
+ for (j = 0; j < snd_ctl_elem_info_get_items(ctl->info); j++) {
+ snd_ctl_elem_value_set_enumerated(val, i, j);
+ err = write_and_verify(ctl, val, NULL);
+ if (err != 0)
+ fail = true;
+ }
+ }
+
+ return !fail;
+}
+
+void test_ctl_write_valid(struct ctl_data *ctl)
+{
+ bool pass;
+ int err;
+
+ /* If the control is turned off let's be polite */
+ if (snd_ctl_elem_info_is_inactive(ctl->info)) {
+ ksft_print_msg("%s is inactive\n", ctl->name);
+ ksft_test_result_skip("write_valid.%d.%d\n",
+ ctl->card->card, ctl->elem);
+ return;
+ }
+
+ if (!snd_ctl_elem_info_is_writable(ctl->info)) {
+ ksft_print_msg("%s is not writeable\n", ctl->name);
+ ksft_test_result_skip("write_valid.%d.%d\n",
+ ctl->card->card, ctl->elem);
+ return;
+ }
+
+ switch (snd_ctl_elem_info_get_type(ctl->info)) {
+ case SND_CTL_ELEM_TYPE_BOOLEAN:
+ pass = test_ctl_write_valid_boolean(ctl);
+ break;
+
+ case SND_CTL_ELEM_TYPE_INTEGER:
+ pass = test_ctl_write_valid_integer(ctl);
+ break;
+
+ case SND_CTL_ELEM_TYPE_INTEGER64:
+ pass = test_ctl_write_valid_integer64(ctl);
+ break;
+
+ case SND_CTL_ELEM_TYPE_ENUMERATED:
+ pass = test_ctl_write_valid_enumerated(ctl);
+ break;
+
+ default:
+ /* No tests for this yet */
+ ksft_test_result_skip("write_valid.%d.%d\n",
+ ctl->card->card, ctl->elem);
+ return;
+ }
+
+ /* Restore the default value to minimise disruption */
+ err = write_and_verify(ctl, ctl->def_val, NULL);
+ if (err < 0)
+ pass = false;
+
+ ksft_test_result(pass, "write_valid.%d.%d\n",
+ ctl->card->card, ctl->elem);
+}
+
+int main(void)
+{
+ struct ctl_data *ctl;
+
+ ksft_print_header();
+
+ find_controls();
+
+ ksft_set_plan(num_controls * TESTS_PER_CONTROL);
+
+ for (ctl = ctl_list; ctl != NULL; ctl = ctl->next) {
+ /*
+ * Must test get_value() before we write anything, the
+ * test stores the default value for later cleanup.
+ */
+ test_ctl_get_value(ctl);
+ test_ctl_write_default(ctl);
+ test_ctl_write_valid(ctl);
+ }
+
+ ksft_exit_pass();
+
+ return 0;
+}
diff --git a/tools/testing/selftests/arm64/abi/syscall-abi.c b/tools/testing/selftests/arm64/abi/syscall-abi.c
index d8eeeafb50dc..1e13b7523918 100644
--- a/tools/testing/selftests/arm64/abi/syscall-abi.c
+++ b/tools/testing/selftests/arm64/abi/syscall-abi.c
@@ -18,7 +18,6 @@
#include "../../kselftest.h"
-#define ARRAY_SIZE(a) (sizeof(a) / sizeof(a[0]))
#define NUM_VL ((SVE_VQ_MAX - SVE_VQ_MIN) + 1)
extern void do_syscall(int sve_vl);
diff --git a/tools/testing/selftests/arm64/fp/sve-ptrace.c b/tools/testing/selftests/arm64/fp/sve-ptrace.c
index af798b9d232c..4c418b2021e0 100644
--- a/tools/testing/selftests/arm64/fp/sve-ptrace.c
+++ b/tools/testing/selftests/arm64/fp/sve-ptrace.c
@@ -21,8 +21,6 @@
#include "../../kselftest.h"
-#define ARRAY_SIZE(a) (sizeof(a) / sizeof(a[0]))
-
/* <linux/elf.h> and <sys/auxv.h> don't like each other, so: */
#ifndef NT_ARM_SVE
#define NT_ARM_SVE 0x405
@@ -261,7 +259,7 @@ static void ptrace_sve_fpsimd(pid_t child, const struct vec_type *type)
}
ksft_test_result((sve->flags & SVE_PT_REGS_MASK) == SVE_PT_REGS_FPSIMD,
- "Set FPSIMD registers via %s\n", type->name);
+ "Got FPSIMD registers via %s\n", type->name);
if ((sve->flags & SVE_PT_REGS_MASK) != SVE_PT_REGS_FPSIMD)
goto out;
@@ -489,6 +487,8 @@ static int do_parent(pid_t child)
unsigned int vq, vl;
bool vl_supported;
+ ksft_print_msg("Parent is %d, child is %d\n", getpid(), child);
+
/* Attach to the child */
while (1) {
int sig;
@@ -557,7 +557,14 @@ static int do_parent(pid_t child)
}
/* prctl() flags */
- ptrace_set_get_inherit(child, &vec_types[i]);
+ if (getauxval(vec_types[i].hwcap_type) & vec_types[i].hwcap) {
+ ptrace_set_get_inherit(child, &vec_types[i]);
+ } else {
+ ksft_test_result_skip("%s SVE_PT_VL_INHERIT set\n",
+ vec_types[i].name);
+ ksft_test_result_skip("%s SVE_PT_VL_INHERIT cleared\n",
+ vec_types[i].name);
+ }
/* Step through every possible VQ */
for (vq = SVE_VQ_MIN; vq <= SVE_VQ_MAX; vq++) {
diff --git a/tools/testing/selftests/arm64/mte/check_gcr_el1_cswitch.c b/tools/testing/selftests/arm64/mte/check_gcr_el1_cswitch.c
index a876db1f096a..325bca0de0f6 100644
--- a/tools/testing/selftests/arm64/mte/check_gcr_el1_cswitch.c
+++ b/tools/testing/selftests/arm64/mte/check_gcr_el1_cswitch.c
@@ -19,17 +19,6 @@
#include "kselftest.h"
#include "mte_common_util.h"
-#define PR_SET_TAGGED_ADDR_CTRL 55
-#define PR_GET_TAGGED_ADDR_CTRL 56
-# define PR_TAGGED_ADDR_ENABLE (1UL << 0)
-# define PR_MTE_TCF_SHIFT 1
-# define PR_MTE_TCF_NONE (0UL << PR_MTE_TCF_SHIFT)
-# define PR_MTE_TCF_SYNC (1UL << PR_MTE_TCF_SHIFT)
-# define PR_MTE_TCF_ASYNC (2UL << PR_MTE_TCF_SHIFT)
-# define PR_MTE_TCF_MASK (3UL << PR_MTE_TCF_SHIFT)
-# define PR_MTE_TAG_SHIFT 3
-# define PR_MTE_TAG_MASK (0xffffUL << PR_MTE_TAG_SHIFT)
-
#include "mte_def.h"
#define NUM_ITERATIONS 1024
diff --git a/tools/testing/selftests/arm64/mte/check_user_mem.c b/tools/testing/selftests/arm64/mte/check_user_mem.c
index 1de7a0abd0ae..f4ae5f87a3b7 100644
--- a/tools/testing/selftests/arm64/mte/check_user_mem.c
+++ b/tools/testing/selftests/arm64/mte/check_user_mem.c
@@ -3,6 +3,7 @@
#define _GNU_SOURCE
+#include <assert.h>
#include <errno.h>
#include <fcntl.h>
#include <signal.h>
@@ -11,6 +12,7 @@
#include <string.h>
#include <ucontext.h>
#include <unistd.h>
+#include <sys/uio.h>
#include <sys/mman.h>
#include "kselftest.h"
@@ -19,14 +21,28 @@
static size_t page_sz;
-static int check_usermem_access_fault(int mem_type, int mode, int mapping)
+#define TEST_NAME_MAX 100
+
+enum test_type {
+ READ_TEST,
+ WRITE_TEST,
+ READV_TEST,
+ WRITEV_TEST,
+ LAST_TEST,
+};
+
+static int check_usermem_access_fault(int mem_type, int mode, int mapping,
+ int tag_offset, int tag_len,
+ enum test_type test_type)
{
int fd, i, err;
char val = 'A';
- size_t len, read_len;
+ ssize_t len, syscall_len;
void *ptr, *ptr_next;
+ int fileoff, ptroff, size;
+ int sizes[] = {1, 2, 3, 8, 16, 32, 4096, page_sz};
- err = KSFT_FAIL;
+ err = KSFT_PASS;
len = 2 * page_sz;
mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG);
fd = create_temp_file();
@@ -43,9 +59,9 @@ static int check_usermem_access_fault(int mem_type, int mode, int mapping)
}
mte_initialize_current_context(mode, (uintptr_t)ptr, len);
/* Copy from file into buffer with valid tag */
- read_len = read(fd, ptr, len);
+ syscall_len = read(fd, ptr, len);
mte_wait_after_trig();
- if (cur_mte_cxt.fault_valid || read_len < len)
+ if (cur_mte_cxt.fault_valid || syscall_len < len)
goto usermem_acc_err;
/* Verify same pattern is read */
for (i = 0; i < len; i++)
@@ -54,36 +70,136 @@ static int check_usermem_access_fault(int mem_type, int mode, int mapping)
if (i < len)
goto usermem_acc_err;
- /* Tag the next half of memory with different value */
- ptr_next = (void *)((unsigned long)ptr + page_sz);
+ if (!tag_len)
+ tag_len = len - tag_offset;
+ /* Tag a part of memory with different value */
+ ptr_next = (void *)((unsigned long)ptr + tag_offset);
ptr_next = mte_insert_new_tag(ptr_next);
- mte_set_tag_address_range(ptr_next, page_sz);
+ mte_set_tag_address_range(ptr_next, tag_len);
- lseek(fd, 0, 0);
- /* Copy from file into buffer with invalid tag */
- read_len = read(fd, ptr, len);
- mte_wait_after_trig();
- /*
- * Accessing user memory in kernel with invalid tag should fail in sync
- * mode without fault but may not fail in async mode as per the
- * implemented MTE userspace support in Arm64 kernel.
- */
- if (mode == MTE_SYNC_ERR &&
- !cur_mte_cxt.fault_valid && read_len < len) {
- err = KSFT_PASS;
- } else if (mode == MTE_ASYNC_ERR &&
- !cur_mte_cxt.fault_valid && read_len == len) {
- err = KSFT_PASS;
+ for (fileoff = 0; fileoff < 16; fileoff++) {
+ for (ptroff = 0; ptroff < 16; ptroff++) {
+ for (i = 0; i < ARRAY_SIZE(sizes); i++) {
+ size = sizes[i];
+ lseek(fd, 0, 0);
+
+ /* perform file operation on buffer with invalid tag */
+ switch (test_type) {
+ case READ_TEST:
+ syscall_len = read(fd, ptr + ptroff, size);
+ break;
+ case WRITE_TEST:
+ syscall_len = write(fd, ptr + ptroff, size);
+ break;
+ case READV_TEST: {
+ struct iovec iov[1];
+ iov[0].iov_base = ptr + ptroff;
+ iov[0].iov_len = size;
+ syscall_len = readv(fd, iov, 1);
+ break;
+ }
+ case WRITEV_TEST: {
+ struct iovec iov[1];
+ iov[0].iov_base = ptr + ptroff;
+ iov[0].iov_len = size;
+ syscall_len = writev(fd, iov, 1);
+ break;
+ }
+ case LAST_TEST:
+ goto usermem_acc_err;
+ }
+
+ mte_wait_after_trig();
+ /*
+ * Accessing user memory in kernel with invalid tag should fail in sync
+ * mode without fault but may not fail in async mode as per the
+ * implemented MTE userspace support in Arm64 kernel.
+ */
+ if (cur_mte_cxt.fault_valid) {
+ goto usermem_acc_err;
+ }
+ if (mode == MTE_SYNC_ERR && syscall_len < len) {
+ /* test passed */
+ } else if (mode == MTE_ASYNC_ERR && syscall_len == size) {
+ /* test passed */
+ } else {
+ goto usermem_acc_err;
+ }
+ }
+ }
}
+
+ goto exit;
+
usermem_acc_err:
+ err = KSFT_FAIL;
+exit:
mte_free_memory((void *)ptr, len, mem_type, true);
close(fd);
return err;
}
+void format_test_name(char* name, int name_len, int type, int sync, int map, int len, int offset) {
+ const char* test_type;
+ const char* mte_type;
+ const char* map_type;
+
+ switch (type) {
+ case READ_TEST:
+ test_type = "read";
+ break;
+ case WRITE_TEST:
+ test_type = "write";
+ break;
+ case READV_TEST:
+ test_type = "readv";
+ break;
+ case WRITEV_TEST:
+ test_type = "writev";
+ break;
+ default:
+ assert(0);
+ break;
+ }
+
+ switch (sync) {
+ case MTE_SYNC_ERR:
+ mte_type = "MTE_SYNC_ERR";
+ break;
+ case MTE_ASYNC_ERR:
+ mte_type = "MTE_ASYNC_ERR";
+ break;
+ default:
+ assert(0);
+ break;
+ }
+
+ switch (map) {
+ case MAP_SHARED:
+ map_type = "MAP_SHARED";
+ break;
+ case MAP_PRIVATE:
+ map_type = "MAP_PRIVATE";
+ break;
+ default:
+ assert(0);
+ break;
+ }
+
+ snprintf(name, name_len,
+ "test type: %s, %s, %s, tag len: %d, tag offset: %d\n",
+ test_type, mte_type, map_type, len, offset);
+}
+
int main(int argc, char *argv[])
{
int err;
+ int t, s, m, l, o;
+ int mte_sync[] = {MTE_SYNC_ERR, MTE_ASYNC_ERR};
+ int maps[] = {MAP_SHARED, MAP_PRIVATE};
+ int tag_lens[] = {0, MT_GRANULE_SIZE};
+ int tag_offsets[] = {page_sz, MT_GRANULE_SIZE};
+ char test_name[TEST_NAME_MAX];
page_sz = getpagesize();
if (!page_sz) {
@@ -98,17 +214,28 @@ int main(int argc, char *argv[])
mte_register_signal(SIGSEGV, mte_default_handler);
/* Set test plan */
- ksft_set_plan(4);
+ ksft_set_plan(64);
- evaluate_test(check_usermem_access_fault(USE_MMAP, MTE_SYNC_ERR, MAP_PRIVATE),
- "Check memory access from kernel in sync mode, private mapping and mmap memory\n");
- evaluate_test(check_usermem_access_fault(USE_MMAP, MTE_SYNC_ERR, MAP_SHARED),
- "Check memory access from kernel in sync mode, shared mapping and mmap memory\n");
-
- evaluate_test(check_usermem_access_fault(USE_MMAP, MTE_ASYNC_ERR, MAP_PRIVATE),
- "Check memory access from kernel in async mode, private mapping and mmap memory\n");
- evaluate_test(check_usermem_access_fault(USE_MMAP, MTE_ASYNC_ERR, MAP_SHARED),
- "Check memory access from kernel in async mode, shared mapping and mmap memory\n");
+ for (t = 0; t < LAST_TEST; t++) {
+ for (s = 0; s < ARRAY_SIZE(mte_sync); s++) {
+ for (m = 0; m < ARRAY_SIZE(maps); m++) {
+ for (l = 0; l < ARRAY_SIZE(tag_lens); l++) {
+ for (o = 0; o < ARRAY_SIZE(tag_offsets); o++) {
+ int sync = mte_sync[s];
+ int map = maps[m];
+ int offset = tag_offsets[o];
+ int tag_len = tag_lens[l];
+ int res = check_usermem_access_fault(USE_MMAP, sync,
+ map, offset,
+ tag_len, t);
+ format_test_name(test_name, TEST_NAME_MAX,
+ t, sync, map, tag_len, offset);
+ evaluate_test(res, test_name);
+ }
+ }
+ }
+ }
+ }
mte_restore_setup();
ksft_print_cnts();
diff --git a/tools/testing/selftests/arm64/signal/test_signals.h b/tools/testing/selftests/arm64/signal/test_signals.h
index ebe8694dbef0..f909b70d9e98 100644
--- a/tools/testing/selftests/arm64/signal/test_signals.h
+++ b/tools/testing/selftests/arm64/signal/test_signals.h
@@ -53,6 +53,7 @@ struct tdescr {
char *name;
char *descr;
unsigned long feats_required;
+ unsigned long feats_incompatible;
/* bitmask of effectively supported feats: populated at run-time */
unsigned long feats_supported;
bool initialized;
diff --git a/tools/testing/selftests/arm64/signal/test_signals_utils.c b/tools/testing/selftests/arm64/signal/test_signals_utils.c
index 2f8c23af3b5e..5743897984b0 100644
--- a/tools/testing/selftests/arm64/signal/test_signals_utils.c
+++ b/tools/testing/selftests/arm64/signal/test_signals_utils.c
@@ -36,6 +36,8 @@ static inline char *feats_to_string(unsigned long feats)
{
size_t flen = MAX_FEATS_SZ - 1;
+ feats_string[0] = '\0';
+
for (int i = 0; i < FMAX_END; i++) {
if (feats & (1UL << i)) {
size_t tlen = strlen(feats_names[i]);
@@ -256,7 +258,7 @@ int test_init(struct tdescr *td)
td->minsigstksz = MINSIGSTKSZ;
fprintf(stderr, "Detected MINSTKSIGSZ:%d\n", td->minsigstksz);
- if (td->feats_required) {
+ if (td->feats_required || td->feats_incompatible) {
td->feats_supported = 0;
/*
* Checking for CPU required features using both the
@@ -267,15 +269,29 @@ int test_init(struct tdescr *td)
if (getauxval(AT_HWCAP) & HWCAP_SVE)
td->feats_supported |= FEAT_SVE;
if (feats_ok(td)) {
- fprintf(stderr,
- "Required Features: [%s] supported\n",
- feats_to_string(td->feats_required &
- td->feats_supported));
+ if (td->feats_required & td->feats_supported)
+ fprintf(stderr,
+ "Required Features: [%s] supported\n",
+ feats_to_string(td->feats_required &
+ td->feats_supported));
+ if (!(td->feats_incompatible & td->feats_supported))
+ fprintf(stderr,
+ "Incompatible Features: [%s] absent\n",
+ feats_to_string(td->feats_incompatible));
} else {
- fprintf(stderr,
- "Required Features: [%s] NOT supported\n",
- feats_to_string(td->feats_required &
- ~td->feats_supported));
+ if ((td->feats_required & td->feats_supported) !=
+ td->feats_supported)
+ fprintf(stderr,
+ "Required Features: [%s] NOT supported\n",
+ feats_to_string(td->feats_required &
+ ~td->feats_supported));
+ if (td->feats_incompatible & td->feats_supported)
+ fprintf(stderr,
+ "Incompatible Features: [%s] supported\n",
+ feats_to_string(td->feats_incompatible &
+ ~td->feats_supported));
+
+
td->result = KSFT_SKIP;
return 0;
}
diff --git a/tools/testing/selftests/arm64/signal/test_signals_utils.h b/tools/testing/selftests/arm64/signal/test_signals_utils.h
index 6772b5c8d274..f3aa99ba67bb 100644
--- a/tools/testing/selftests/arm64/signal/test_signals_utils.h
+++ b/tools/testing/selftests/arm64/signal/test_signals_utils.h
@@ -18,6 +18,8 @@ void test_result(struct tdescr *td);
static inline bool feats_ok(struct tdescr *td)
{
+ if (td->feats_incompatible & td->feats_supported)
+ return false;
return (td->feats_required & td->feats_supported) == td->feats_required;
}
diff --git a/tools/testing/selftests/bpf/prog_tests/d_path.c b/tools/testing/selftests/bpf/prog_tests/d_path.c
index 32fc5b3b5cf6..911345c526e6 100644
--- a/tools/testing/selftests/bpf/prog_tests/d_path.c
+++ b/tools/testing/selftests/bpf/prog_tests/d_path.c
@@ -10,6 +10,7 @@
#include "test_d_path.skel.h"
#include "test_d_path_check_rdonly_mem.skel.h"
+#include "test_d_path_check_types.skel.h"
static int duration;
@@ -167,6 +168,16 @@ static void test_d_path_check_rdonly_mem(void)
test_d_path_check_rdonly_mem__destroy(skel);
}
+static void test_d_path_check_types(void)
+{
+ struct test_d_path_check_types *skel;
+
+ skel = test_d_path_check_types__open_and_load();
+ ASSERT_ERR_PTR(skel, "unexpected_load_passing_wrong_type");
+
+ test_d_path_check_types__destroy(skel);
+}
+
void test_d_path(void)
{
if (test__start_subtest("basic"))
@@ -174,4 +185,7 @@ void test_d_path(void)
if (test__start_subtest("check_rdonly_mem"))
test_d_path_check_rdonly_mem();
+
+ if (test__start_subtest("check_alloc_mem"))
+ test_d_path_check_types();
}
diff --git a/tools/testing/selftests/bpf/prog_tests/timer_crash.c b/tools/testing/selftests/bpf/prog_tests/timer_crash.c
new file mode 100644
index 000000000000..f74b82305da8
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/timer_crash.c
@@ -0,0 +1,32 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+#include "timer_crash.skel.h"
+
+enum {
+ MODE_ARRAY,
+ MODE_HASH,
+};
+
+static void test_timer_crash_mode(int mode)
+{
+ struct timer_crash *skel;
+
+ skel = timer_crash__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "timer_crash__open_and_load"))
+ return;
+ skel->bss->pid = getpid();
+ skel->bss->crash_map = mode;
+ if (!ASSERT_OK(timer_crash__attach(skel), "timer_crash__attach"))
+ goto end;
+ usleep(1);
+end:
+ timer_crash__destroy(skel);
+}
+
+void test_timer_crash(void)
+{
+ if (test__start_subtest("array"))
+ test_timer_crash_mode(MODE_ARRAY);
+ if (test__start_subtest("hash"))
+ test_timer_crash_mode(MODE_HASH);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_link.c b/tools/testing/selftests/bpf/prog_tests/xdp_link.c
index 983ab0b47d30..b2b357f8c74c 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_link.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_link.c
@@ -8,46 +8,47 @@
void serial_test_xdp_link(void)
{
- __u32 duration = 0, id1, id2, id0 = 0, prog_fd1, prog_fd2, err;
DECLARE_LIBBPF_OPTS(bpf_xdp_set_link_opts, opts, .old_fd = -1);
struct test_xdp_link *skel1 = NULL, *skel2 = NULL;
+ __u32 id1, id2, id0 = 0, prog_fd1, prog_fd2;
struct bpf_link_info link_info;
struct bpf_prog_info prog_info;
struct bpf_link *link;
+ int err;
__u32 link_info_len = sizeof(link_info);
__u32 prog_info_len = sizeof(prog_info);
skel1 = test_xdp_link__open_and_load();
- if (CHECK(!skel1, "skel_load", "skeleton open and load failed\n"))
+ if (!ASSERT_OK_PTR(skel1, "skel_load"))
goto cleanup;
prog_fd1 = bpf_program__fd(skel1->progs.xdp_handler);
skel2 = test_xdp_link__open_and_load();
- if (CHECK(!skel2, "skel_load", "skeleton open and load failed\n"))
+ if (!ASSERT_OK_PTR(skel2, "skel_load"))
goto cleanup;
prog_fd2 = bpf_program__fd(skel2->progs.xdp_handler);
memset(&prog_info, 0, sizeof(prog_info));
err = bpf_obj_get_info_by_fd(prog_fd1, &prog_info, &prog_info_len);
- if (CHECK(err, "fd_info1", "failed %d\n", -errno))
+ if (!ASSERT_OK(err, "fd_info1"))
goto cleanup;
id1 = prog_info.id;
memset(&prog_info, 0, sizeof(prog_info));
err = bpf_obj_get_info_by_fd(prog_fd2, &prog_info, &prog_info_len);
- if (CHECK(err, "fd_info2", "failed %d\n", -errno))
+ if (!ASSERT_OK(err, "fd_info2"))
goto cleanup;
id2 = prog_info.id;
/* set initial prog attachment */
err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, prog_fd1, XDP_FLAGS_REPLACE, &opts);
- if (CHECK(err, "fd_attach", "initial prog attach failed: %d\n", err))
+ if (!ASSERT_OK(err, "fd_attach"))
goto cleanup;
/* validate prog ID */
err = bpf_get_link_xdp_id(IFINDEX_LO, &id0, 0);
- CHECK(err || id0 != id1, "id1_check",
- "loaded prog id %u != id1 %u, err %d", id0, id1, err);
+ if (!ASSERT_OK(err, "id1_check_err") || !ASSERT_EQ(id0, id1, "id1_check_val"))
+ goto cleanup;
/* BPF link is not allowed to replace prog attachment */
link = bpf_program__attach_xdp(skel1->progs.xdp_handler, IFINDEX_LO);
@@ -62,7 +63,7 @@ void serial_test_xdp_link(void)
/* detach BPF program */
opts.old_fd = prog_fd1;
err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, -1, XDP_FLAGS_REPLACE, &opts);
- if (CHECK(err, "prog_detach", "failed %d\n", err))
+ if (!ASSERT_OK(err, "prog_detach"))
goto cleanup;
/* now BPF link should attach successfully */
@@ -73,24 +74,23 @@ void serial_test_xdp_link(void)
/* validate prog ID */
err = bpf_get_link_xdp_id(IFINDEX_LO, &id0, 0);
- if (CHECK(err || id0 != id1, "id1_check",
- "loaded prog id %u != id1 %u, err %d", id0, id1, err))
+ if (!ASSERT_OK(err, "id1_check_err") || !ASSERT_EQ(id0, id1, "id1_check_val"))
goto cleanup;
/* BPF prog attach is not allowed to replace BPF link */
opts.old_fd = prog_fd1;
err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, prog_fd2, XDP_FLAGS_REPLACE, &opts);
- if (CHECK(!err, "prog_attach_fail", "unexpected success\n"))
+ if (!ASSERT_ERR(err, "prog_attach_fail"))
goto cleanup;
/* Can't force-update when BPF link is active */
err = bpf_set_link_xdp_fd(IFINDEX_LO, prog_fd2, 0);
- if (CHECK(!err, "prog_update_fail", "unexpected success\n"))
+ if (!ASSERT_ERR(err, "prog_update_fail"))
goto cleanup;
/* Can't force-detach when BPF link is active */
err = bpf_set_link_xdp_fd(IFINDEX_LO, -1, 0);
- if (CHECK(!err, "prog_detach_fail", "unexpected success\n"))
+ if (!ASSERT_ERR(err, "prog_detach_fail"))
goto cleanup;
/* BPF link is not allowed to replace another BPF link */
@@ -110,40 +110,39 @@ void serial_test_xdp_link(void)
skel2->links.xdp_handler = link;
err = bpf_get_link_xdp_id(IFINDEX_LO, &id0, 0);
- if (CHECK(err || id0 != id2, "id2_check",
- "loaded prog id %u != id2 %u, err %d", id0, id1, err))
+ if (!ASSERT_OK(err, "id2_check_err") || !ASSERT_EQ(id0, id2, "id2_check_val"))
goto cleanup;
/* updating program under active BPF link works as expected */
err = bpf_link__update_program(link, skel1->progs.xdp_handler);
- if (CHECK(err, "link_upd", "failed: %d\n", err))
+ if (!ASSERT_OK(err, "link_upd"))
goto cleanup;
memset(&link_info, 0, sizeof(link_info));
err = bpf_obj_get_info_by_fd(bpf_link__fd(link), &link_info, &link_info_len);
- if (CHECK(err, "link_info", "failed: %d\n", err))
+ if (!ASSERT_OK(err, "link_info"))
goto cleanup;
- CHECK(link_info.type != BPF_LINK_TYPE_XDP, "link_type",
- "got %u != exp %u\n", link_info.type, BPF_LINK_TYPE_XDP);
- CHECK(link_info.prog_id != id1, "link_prog_id",
- "got %u != exp %u\n", link_info.prog_id, id1);
- CHECK(link_info.xdp.ifindex != IFINDEX_LO, "link_ifindex",
- "got %u != exp %u\n", link_info.xdp.ifindex, IFINDEX_LO);
+ ASSERT_EQ(link_info.type, BPF_LINK_TYPE_XDP, "link_type");
+ ASSERT_EQ(link_info.prog_id, id1, "link_prog_id");
+ ASSERT_EQ(link_info.xdp.ifindex, IFINDEX_LO, "link_ifindex");
+
+ /* updating program under active BPF link with different type fails */
+ err = bpf_link__update_program(link, skel1->progs.tc_handler);
+ if (!ASSERT_ERR(err, "link_upd_invalid"))
+ goto cleanup;
err = bpf_link__detach(link);
- if (CHECK(err, "link_detach", "failed %d\n", err))
+ if (!ASSERT_OK(err, "link_detach"))
goto cleanup;
memset(&link_info, 0, sizeof(link_info));
err = bpf_obj_get_info_by_fd(bpf_link__fd(link), &link_info, &link_info_len);
- if (CHECK(err, "link_info", "failed: %d\n", err))
- goto cleanup;
- CHECK(link_info.prog_id != id1, "link_prog_id",
- "got %u != exp %u\n", link_info.prog_id, id1);
+
+ ASSERT_OK(err, "link_info");
+ ASSERT_EQ(link_info.prog_id, id1, "link_prog_id");
/* ifindex should be zeroed out */
- CHECK(link_info.xdp.ifindex != 0, "link_ifindex",
- "got %u != exp %u\n", link_info.xdp.ifindex, 0);
+ ASSERT_EQ(link_info.xdp.ifindex, 0, "link_ifindex");
cleanup:
test_xdp_link__destroy(skel1);
diff --git a/tools/testing/selftests/bpf/progs/test_d_path_check_types.c b/tools/testing/selftests/bpf/progs/test_d_path_check_types.c
new file mode 100644
index 000000000000..7e02b7361307
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_d_path_check_types.c
@@ -0,0 +1,32 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+extern const int bpf_prog_active __ksym;
+
+struct {
+ __uint(type, BPF_MAP_TYPE_RINGBUF);
+ __uint(max_entries, 1 << 12);
+} ringbuf SEC(".maps");
+
+SEC("fentry/security_inode_getattr")
+int BPF_PROG(d_path_check_rdonly_mem, struct path *path, struct kstat *stat,
+ __u32 request_mask, unsigned int query_flags)
+{
+ void *active;
+ u32 cpu;
+
+ cpu = bpf_get_smp_processor_id();
+ active = (void *)bpf_per_cpu_ptr(&bpf_prog_active, cpu);
+ if (active) {
+ /* FAIL here! 'active' points to 'regular' memory. It
+ * cannot be submitted to ring buffer.
+ */
+ bpf_ringbuf_submit(active, 0);
+ }
+ return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_kern.h b/tools/testing/selftests/bpf/progs/test_sockmap_kern.h
index 2966564b8497..6c85b00f27b2 100644
--- a/tools/testing/selftests/bpf/progs/test_sockmap_kern.h
+++ b/tools/testing/selftests/bpf/progs/test_sockmap_kern.h
@@ -235,7 +235,7 @@ SEC("sk_msg1")
int bpf_prog4(struct sk_msg_md *msg)
{
int *bytes, zero = 0, one = 1, two = 2, three = 3, four = 4, five = 5;
- int *start, *end, *start_push, *end_push, *start_pop, *pop;
+ int *start, *end, *start_push, *end_push, *start_pop, *pop, err = 0;
bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
if (bytes)
@@ -249,8 +249,11 @@ int bpf_prog4(struct sk_msg_md *msg)
bpf_msg_pull_data(msg, *start, *end, 0);
start_push = bpf_map_lookup_elem(&sock_bytes, &two);
end_push = bpf_map_lookup_elem(&sock_bytes, &three);
- if (start_push && end_push)
- bpf_msg_push_data(msg, *start_push, *end_push, 0);
+ if (start_push && end_push) {
+ err = bpf_msg_push_data(msg, *start_push, *end_push, 0);
+ if (err)
+ return SK_DROP;
+ }
start_pop = bpf_map_lookup_elem(&sock_bytes, &four);
pop = bpf_map_lookup_elem(&sock_bytes, &five);
if (start_pop && pop)
@@ -263,6 +266,7 @@ int bpf_prog6(struct sk_msg_md *msg)
{
int zero = 0, one = 1, two = 2, three = 3, four = 4, five = 5, key = 0;
int *bytes, *start, *end, *start_push, *end_push, *start_pop, *pop, *f;
+ int err = 0;
__u64 flags = 0;
bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
@@ -279,8 +283,11 @@ int bpf_prog6(struct sk_msg_md *msg)
start_push = bpf_map_lookup_elem(&sock_bytes, &two);
end_push = bpf_map_lookup_elem(&sock_bytes, &three);
- if (start_push && end_push)
- bpf_msg_push_data(msg, *start_push, *end_push, 0);
+ if (start_push && end_push) {
+ err = bpf_msg_push_data(msg, *start_push, *end_push, 0);
+ if (err)
+ return SK_DROP;
+ }
start_pop = bpf_map_lookup_elem(&sock_bytes, &four);
pop = bpf_map_lookup_elem(&sock_bytes, &five);
@@ -338,7 +345,7 @@ SEC("sk_msg5")
int bpf_prog10(struct sk_msg_md *msg)
{
int *bytes, *start, *end, *start_push, *end_push, *start_pop, *pop;
- int zero = 0, one = 1, two = 2, three = 3, four = 4, five = 5;
+ int zero = 0, one = 1, two = 2, three = 3, four = 4, five = 5, err = 0;
bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
if (bytes)
@@ -352,8 +359,11 @@ int bpf_prog10(struct sk_msg_md *msg)
bpf_msg_pull_data(msg, *start, *end, 0);
start_push = bpf_map_lookup_elem(&sock_bytes, &two);
end_push = bpf_map_lookup_elem(&sock_bytes, &three);
- if (start_push && end_push)
- bpf_msg_push_data(msg, *start_push, *end_push, 0);
+ if (start_push && end_push) {
+ err = bpf_msg_push_data(msg, *start_push, *end_push, 0);
+ if (err)
+ return SK_PASS;
+ }
start_pop = bpf_map_lookup_elem(&sock_bytes, &four);
pop = bpf_map_lookup_elem(&sock_bytes, &five);
if (start_pop && pop)
diff --git a/tools/testing/selftests/bpf/progs/test_stacktrace_map.c b/tools/testing/selftests/bpf/progs/test_stacktrace_map.c
index a8233e7f173b..728dbd39eff0 100644
--- a/tools/testing/selftests/bpf/progs/test_stacktrace_map.c
+++ b/tools/testing/selftests/bpf/progs/test_stacktrace_map.c
@@ -1,7 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
// Copyright (c) 2018 Facebook
-#include <linux/bpf.h>
+#include <vmlinux.h>
#include <bpf/bpf_helpers.h>
#ifndef PERF_MAX_STACK_DEPTH
@@ -41,11 +41,11 @@ struct {
/* taken from /sys/kernel/debug/tracing/events/sched/sched_switch/format */
struct sched_switch_args {
unsigned long long pad;
- char prev_comm[16];
+ char prev_comm[TASK_COMM_LEN];
int prev_pid;
int prev_prio;
long long prev_state;
- char next_comm[16];
+ char next_comm[TASK_COMM_LEN];
int next_pid;
int next_prio;
};
diff --git a/tools/testing/selftests/bpf/progs/test_tracepoint.c b/tools/testing/selftests/bpf/progs/test_tracepoint.c
index ce6974016f53..43bd7a20cc50 100644
--- a/tools/testing/selftests/bpf/progs/test_tracepoint.c
+++ b/tools/testing/selftests/bpf/progs/test_tracepoint.c
@@ -1,17 +1,17 @@
// SPDX-License-Identifier: GPL-2.0
// Copyright (c) 2017 Facebook
-#include <linux/bpf.h>
+#include <vmlinux.h>
#include <bpf/bpf_helpers.h>
/* taken from /sys/kernel/debug/tracing/events/sched/sched_switch/format */
struct sched_switch_args {
unsigned long long pad;
- char prev_comm[16];
+ char prev_comm[TASK_COMM_LEN];
int prev_pid;
int prev_prio;
long long prev_state;
- char next_comm[16];
+ char next_comm[TASK_COMM_LEN];
int next_pid;
int next_prio;
};
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_link.c b/tools/testing/selftests/bpf/progs/test_xdp_link.c
index ee7d6ac0f615..64ff32eaae92 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp_link.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_link.c
@@ -10,3 +10,9 @@ int xdp_handler(struct xdp_md *xdp)
{
return 0;
}
+
+SEC("tc")
+int tc_handler(struct __sk_buff *skb)
+{
+ return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/timer_crash.c b/tools/testing/selftests/bpf/progs/timer_crash.c
new file mode 100644
index 000000000000..f8f7944e70da
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/timer_crash.c
@@ -0,0 +1,54 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+
+struct map_elem {
+ struct bpf_timer timer;
+ struct bpf_spin_lock lock;
+};
+
+struct {
+ __uint(type, BPF_MAP_TYPE_ARRAY);
+ __uint(max_entries, 1);
+ __type(key, int);
+ __type(value, struct map_elem);
+} amap SEC(".maps");
+
+struct {
+ __uint(type, BPF_MAP_TYPE_HASH);
+ __uint(max_entries, 1);
+ __type(key, int);
+ __type(value, struct map_elem);
+} hmap SEC(".maps");
+
+int pid = 0;
+int crash_map = 0; /* 0 for amap, 1 for hmap */
+
+SEC("fentry/do_nanosleep")
+int sys_enter(void *ctx)
+{
+ struct map_elem *e, value = {};
+ void *map = crash_map ? (void *)&hmap : (void *)&amap;
+
+ if (bpf_get_current_task_btf()->tgid != pid)
+ return 0;
+
+ *(void **)&value = (void *)0xdeadcaf3;
+
+ bpf_map_update_elem(map, &(int){0}, &value, 0);
+ /* For array map, doing bpf_map_update_elem will do a
+ * check_and_free_timer_in_array, which will trigger the crash if timer
+ * pointer was overwritten, for hmap we need to use bpf_timer_cancel.
+ */
+ if (crash_map == 1) {
+ e = bpf_map_lookup_elem(map, &(int){0});
+ if (!e)
+ return 0;
+ bpf_timer_cancel(&e->timer);
+ }
+ return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_lirc_mode2_user.c b/tools/testing/selftests/bpf/test_lirc_mode2_user.c
index ebf68dce5504..2893e9f2f1e0 100644
--- a/tools/testing/selftests/bpf/test_lirc_mode2_user.c
+++ b/tools/testing/selftests/bpf/test_lirc_mode2_user.c
@@ -28,7 +28,6 @@
// 5. We can read keycode from same /dev/lirc device
#include <linux/bpf.h>
-#include <linux/lirc.h>
#include <linux/input.h>
#include <errno.h>
#include <stdio.h>
diff --git a/tools/testing/selftests/bpf/verifier/ringbuf.c b/tools/testing/selftests/bpf/verifier/ringbuf.c
new file mode 100644
index 000000000000..b64d33e4833c
--- /dev/null
+++ b/tools/testing/selftests/bpf/verifier/ringbuf.c
@@ -0,0 +1,95 @@
+{
+ "ringbuf: invalid reservation offset 1",
+ .insns = {
+ /* reserve 8 byte ringbuf memory */
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_MOV64_IMM(BPF_REG_2, 8),
+ BPF_MOV64_IMM(BPF_REG_3, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ringbuf_reserve),
+ /* store a pointer to the reserved memory in R6 */
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+ /* check whether the reservation was successful */
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
+ /* spill R6(mem) into the stack */
+ BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_6, -8),
+ /* fill it back in R7 */
+ BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_10, -8),
+ /* should be able to access *(R7) = 0 */
+ BPF_ST_MEM(BPF_DW, BPF_REG_7, 0, 0),
+ /* submit the reserved ringbuf memory */
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
+ /* add invalid offset to reserved ringbuf memory */
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0xcafe),
+ BPF_MOV64_IMM(BPF_REG_2, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ringbuf_submit),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_ringbuf = { 1 },
+ .result = REJECT,
+ .errstr = "dereference of modified alloc_mem ptr R1",
+},
+{
+ "ringbuf: invalid reservation offset 2",
+ .insns = {
+ /* reserve 8 byte ringbuf memory */
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_MOV64_IMM(BPF_REG_2, 8),
+ BPF_MOV64_IMM(BPF_REG_3, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ringbuf_reserve),
+ /* store a pointer to the reserved memory in R6 */
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+ /* check whether the reservation was successful */
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
+ /* spill R6(mem) into the stack */
+ BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_6, -8),
+ /* fill it back in R7 */
+ BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_10, -8),
+ /* add invalid offset to reserved ringbuf memory */
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, 0xcafe),
+ /* should be able to access *(R7) = 0 */
+ BPF_ST_MEM(BPF_DW, BPF_REG_7, 0, 0),
+ /* submit the reserved ringbuf memory */
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
+ BPF_MOV64_IMM(BPF_REG_2, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ringbuf_submit),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_ringbuf = { 1 },
+ .result = REJECT,
+ .errstr = "R7 min value is outside of the allowed memory range",
+},
+{
+ "ringbuf: check passing rb mem to helpers",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ /* reserve 8 byte ringbuf memory */
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_MOV64_IMM(BPF_REG_2, 8),
+ BPF_MOV64_IMM(BPF_REG_3, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ringbuf_reserve),
+ BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
+ /* check whether the reservation was successful */
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+ BPF_EXIT_INSN(),
+ /* pass allocated ring buffer memory to fib lookup */
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+ BPF_MOV64_IMM(BPF_REG_3, 8),
+ BPF_MOV64_IMM(BPF_REG_4, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_fib_lookup),
+ /* submit the ringbuf memory */
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
+ BPF_MOV64_IMM(BPF_REG_2, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ringbuf_submit),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_ringbuf = { 2 },
+ .prog_type = BPF_PROG_TYPE_XDP,
+ .result = ACCEPT,
+},
diff --git a/tools/testing/selftests/bpf/verifier/spill_fill.c b/tools/testing/selftests/bpf/verifier/spill_fill.c
index 1a8eb9672bd1..8cfc5349d2a8 100644
--- a/tools/testing/selftests/bpf/verifier/spill_fill.c
+++ b/tools/testing/selftests/bpf/verifier/spill_fill.c
@@ -84,7 +84,7 @@
},
.fixup_map_ringbuf = { 1 },
.result = REJECT,
- .errstr = "R0 pointer arithmetic on mem_or_null prohibited",
+ .errstr = "R0 pointer arithmetic on alloc_mem_or_null prohibited",
},
{
"check corrupted spill/fill",
diff --git a/tools/testing/selftests/cgroup/cgroup_util.c b/tools/testing/selftests/cgroup/cgroup_util.c
index 0cf7e90c0052..dbaa7aabbb4a 100644
--- a/tools/testing/selftests/cgroup/cgroup_util.c
+++ b/tools/testing/selftests/cgroup/cgroup_util.c
@@ -583,7 +583,7 @@ int clone_into_cgroup_run_wait(const char *cgroup)
return 0;
}
-int cg_prepare_for_wait(const char *cgroup)
+static int __prepare_for_wait(const char *cgroup, const char *filename)
{
int fd, ret = -1;
@@ -591,8 +591,7 @@ int cg_prepare_for_wait(const char *cgroup)
if (fd == -1)
return fd;
- ret = inotify_add_watch(fd, cg_control(cgroup, "cgroup.events"),
- IN_MODIFY);
+ ret = inotify_add_watch(fd, cg_control(cgroup, filename), IN_MODIFY);
if (ret == -1) {
close(fd);
fd = -1;
@@ -601,6 +600,16 @@ int cg_prepare_for_wait(const char *cgroup)
return fd;
}
+int cg_prepare_for_wait(const char *cgroup)
+{
+ return __prepare_for_wait(cgroup, "cgroup.events");
+}
+
+int memcg_prepare_for_wait(const char *cgroup)
+{
+ return __prepare_for_wait(cgroup, "memory.events");
+}
+
int cg_wait_for(int fd)
{
int ret = -1;
diff --git a/tools/testing/selftests/cgroup/cgroup_util.h b/tools/testing/selftests/cgroup/cgroup_util.h
index 4f66d10626d2..628738532ac9 100644
--- a/tools/testing/selftests/cgroup/cgroup_util.h
+++ b/tools/testing/selftests/cgroup/cgroup_util.h
@@ -55,4 +55,5 @@ extern int clone_reap(pid_t pid, int options);
extern int clone_into_cgroup_run_wait(const char *cgroup);
extern int dirfd_open_opath(const char *dir);
extern int cg_prepare_for_wait(const char *cgroup);
+extern int memcg_prepare_for_wait(const char *cgroup);
extern int cg_wait_for(int fd);
diff --git a/tools/testing/selftests/cgroup/test_memcontrol.c b/tools/testing/selftests/cgroup/test_memcontrol.c
index c19a97dd02d4..36ccf2322e21 100644
--- a/tools/testing/selftests/cgroup/test_memcontrol.c
+++ b/tools/testing/selftests/cgroup/test_memcontrol.c
@@ -16,6 +16,7 @@
#include <netinet/in.h>
#include <netdb.h>
#include <errno.h>
+#include <sys/mman.h>
#include "../kselftest.h"
#include "cgroup_util.h"
@@ -628,6 +629,82 @@ cleanup:
return ret;
}
+static int alloc_anon_mlock(const char *cgroup, void *arg)
+{
+ size_t size = (size_t)arg;
+ void *buf;
+
+ buf = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANON,
+ 0, 0);
+ if (buf == MAP_FAILED)
+ return -1;
+
+ mlock(buf, size);
+ munmap(buf, size);
+ return 0;
+}
+
+/*
+ * This test checks that memory.high is able to throttle big single shot
+ * allocation i.e. large allocation within one kernel entry.
+ */
+static int test_memcg_high_sync(const char *root)
+{
+ int ret = KSFT_FAIL, pid, fd = -1;
+ char *memcg;
+ long pre_high, pre_max;
+ long post_high, post_max;
+
+ memcg = cg_name(root, "memcg_test");
+ if (!memcg)
+ goto cleanup;
+
+ if (cg_create(memcg))
+ goto cleanup;
+
+ pre_high = cg_read_key_long(memcg, "memory.events", "high ");
+ pre_max = cg_read_key_long(memcg, "memory.events", "max ");
+ if (pre_high < 0 || pre_max < 0)
+ goto cleanup;
+
+ if (cg_write(memcg, "memory.swap.max", "0"))
+ goto cleanup;
+
+ if (cg_write(memcg, "memory.high", "30M"))
+ goto cleanup;
+
+ if (cg_write(memcg, "memory.max", "140M"))
+ goto cleanup;
+
+ fd = memcg_prepare_for_wait(memcg);
+ if (fd < 0)
+ goto cleanup;
+
+ pid = cg_run_nowait(memcg, alloc_anon_mlock, (void *)MB(200));
+ if (pid < 0)
+ goto cleanup;
+
+ cg_wait_for(fd);
+
+ post_high = cg_read_key_long(memcg, "memory.events", "high ");
+ post_max = cg_read_key_long(memcg, "memory.events", "max ");
+ if (post_high < 0 || post_max < 0)
+ goto cleanup;
+
+ if (pre_high == post_high || pre_max != post_max)
+ goto cleanup;
+
+ ret = KSFT_PASS;
+
+cleanup:
+ if (fd >= 0)
+ close(fd);
+ cg_destroy(memcg);
+ free(memcg);
+
+ return ret;
+}
+
/*
* This test checks that memory.max limits the amount of
* memory which can be consumed by either anonymous memory
@@ -1180,6 +1257,7 @@ struct memcg_test {
T(test_memcg_min),
T(test_memcg_low),
T(test_memcg_high),
+ T(test_memcg_high_sync),
T(test_memcg_max),
T(test_memcg_oom_events),
T(test_memcg_swap_max),
diff --git a/tools/testing/selftests/clone3/clone3.c b/tools/testing/selftests/clone3/clone3.c
index 076cf4325f78..cd4582129c7d 100644
--- a/tools/testing/selftests/clone3/clone3.c
+++ b/tools/testing/selftests/clone3/clone3.c
@@ -126,8 +126,6 @@ static void test_clone3(uint64_t flags, size_t size, int expected,
int main(int argc, char *argv[])
{
- pid_t pid;
-
uid_t uid = getuid();
ksft_print_header();
diff --git a/tools/testing/selftests/cpufreq/main.sh b/tools/testing/selftests/cpufreq/main.sh
index 31f8c9a76c5f..60ce18ed0666 100755
--- a/tools/testing/selftests/cpufreq/main.sh
+++ b/tools/testing/selftests/cpufreq/main.sh
@@ -194,5 +194,5 @@ prerequisite
# Run requested functions
clear_dumps $OUTFILE
-do_test >> $OUTFILE.txt
+do_test | tee -a $OUTFILE.txt
dmesg_dumps $OUTFILE
diff --git a/tools/testing/selftests/damon/Makefile b/tools/testing/selftests/damon/Makefile
index 937d36ae9a69..0470c5f3e690 100644
--- a/tools/testing/selftests/damon/Makefile
+++ b/tools/testing/selftests/damon/Makefile
@@ -6,5 +6,6 @@ TEST_GEN_FILES += huge_count_read_write
TEST_FILES = _chk_dependency.sh _debugfs_common.sh
TEST_PROGS = debugfs_attrs.sh debugfs_schemes.sh debugfs_target_ids.sh
TEST_PROGS += debugfs_empty_targets.sh debugfs_huge_count_read_write.sh
+TEST_PROGS += sysfs.sh
include ../lib.mk
diff --git a/tools/testing/selftests/damon/sysfs.sh b/tools/testing/selftests/damon/sysfs.sh
new file mode 100644
index 000000000000..2e3ae77cb6db
--- /dev/null
+++ b/tools/testing/selftests/damon/sysfs.sh
@@ -0,0 +1,306 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Kselftest frmework requirement - SKIP code is 4.
+ksft_skip=4
+
+ensure_write_succ()
+{
+ file=$1
+ content=$2
+ reason=$3
+
+ if ! echo "$content" > "$file"
+ then
+ echo "writing $content to $file failed"
+ echo "expected success because $reason"
+ exit 1
+ fi
+}
+
+ensure_write_fail()
+{
+ file=$1
+ content=$2
+ reason=$3
+
+ if echo "$content" > "$file"
+ then
+ echo "writing $content to $file succeed ($fail_reason)"
+ echo "expected failure because $reason"
+ exit 1
+ fi
+}
+
+ensure_dir()
+{
+ dir=$1
+ to_ensure=$2
+ if [ "$to_ensure" = "exist" ] && [ ! -d "$dir" ]
+ then
+ echo "$dir dir is expected but not found"
+ exit 1
+ elif [ "$to_ensure" = "not_exist" ] && [ -d "$dir" ]
+ then
+ echo "$dir dir is not expected but found"
+ exit 1
+ fi
+}
+
+ensure_file()
+{
+ file=$1
+ to_ensure=$2
+ permission=$3
+ if [ "$to_ensure" = "exist" ]
+ then
+ if [ ! -f "$file" ]
+ then
+ echo "$file is expected but not found"
+ exit 1
+ fi
+ perm=$(stat -c "%a" "$file")
+ if [ ! "$perm" = "$permission" ]
+ then
+ echo "$file permission: expected $permission but $perm"
+ exit 1
+ fi
+ elif [ "$to_ensure" = "not_exist" ] && [ -f "$dir" ]
+ then
+ echo "$file is not expected but found"
+ exit 1
+ fi
+}
+
+test_range()
+{
+ range_dir=$1
+ ensure_dir "$range_dir" "exist"
+ ensure_file "$range_dir/min" "exist" 600
+ ensure_file "$range_dir/max" "exist" 600
+}
+
+test_stats()
+{
+ stats_dir=$1
+ ensure_dir "$stats_dir" "exist"
+ for f in nr_tried sz_tried nr_applied sz_applied qt_exceeds
+ do
+ ensure_file "$stats_dir/$f" "exist" "400"
+ done
+}
+
+test_watermarks()
+{
+ watermarks_dir=$1
+ ensure_dir "$watermarks_dir" "exist"
+ ensure_file "$watermarks_dir/metric" "exist" "600"
+ ensure_file "$watermarks_dir/interval_us" "exist" "600"
+ ensure_file "$watermarks_dir/high" "exist" "600"
+ ensure_file "$watermarks_dir/mid" "exist" "600"
+ ensure_file "$watermarks_dir/low" "exist" "600"
+}
+
+test_weights()
+{
+ weights_dir=$1
+ ensure_dir "$weights_dir" "exist"
+ ensure_file "$weights_dir/sz_permil" "exist" "600"
+ ensure_file "$weights_dir/nr_accesses_permil" "exist" "600"
+ ensure_file "$weights_dir/age_permil" "exist" "600"
+}
+
+test_quotas()
+{
+ quotas_dir=$1
+ ensure_dir "$quotas_dir" "exist"
+ ensure_file "$quotas_dir/ms" "exist" 600
+ ensure_file "$quotas_dir/bytes" "exist" 600
+ ensure_file "$quotas_dir/reset_interval_ms" "exist" 600
+ test_weights "$quotas_dir/weights"
+}
+
+test_access_pattern()
+{
+ access_pattern_dir=$1
+ ensure_dir "$access_pattern_dir" "exist"
+ test_range "$access_pattern_dir/age"
+ test_range "$access_pattern_dir/nr_accesses"
+ test_range "$access_pattern_dir/sz"
+}
+
+test_scheme()
+{
+ scheme_dir=$1
+ ensure_dir "$scheme_dir" "exist"
+ ensure_file "$scheme_dir/action" "exist" "600"
+ test_access_pattern "$scheme_dir/access_pattern"
+ test_quotas "$scheme_dir/quotas"
+ test_watermarks "$scheme_dir/watermarks"
+ test_stats "$scheme_dir/stats"
+}
+
+test_schemes()
+{
+ schemes_dir=$1
+ ensure_dir "$schemes_dir" "exist"
+ ensure_file "$schemes_dir/nr_schemes" "exist" 600
+
+ ensure_write_succ "$schemes_dir/nr_schemes" "1" "valid input"
+ test_scheme "$schemes_dir/0"
+
+ ensure_write_succ "$schemes_dir/nr_schemes" "2" "valid input"
+ test_scheme "$schemes_dir/0"
+ test_scheme "$schemes_dir/1"
+
+ ensure_write_succ "$schemes_dir/nr_schemes" "0" "valid input"
+ ensure_dir "$schemes_dir/0" "not_exist"
+ ensure_dir "$schemes_dir/1" "not_exist"
+}
+
+test_region()
+{
+ region_dir=$1
+ ensure_dir "$region_dir" "exist"
+ ensure_file "$region_dir/start" "exist" 600
+ ensure_file "$region_dir/end" "exist" 600
+}
+
+test_regions()
+{
+ regions_dir=$1
+ ensure_dir "$regions_dir" "exist"
+ ensure_file "$regions_dir/nr_regions" "exist" 600
+
+ ensure_write_succ "$regions_dir/nr_regions" "1" "valid input"
+ test_region "$regions_dir/0"
+
+ ensure_write_succ "$regions_dir/nr_regions" "2" "valid input"
+ test_region "$regions_dir/0"
+ test_region "$regions_dir/1"
+
+ ensure_write_succ "$regions_dir/nr_regions" "0" "valid input"
+ ensure_dir "$regions_dir/0" "not_exist"
+ ensure_dir "$regions_dir/1" "not_exist"
+}
+
+test_target()
+{
+ target_dir=$1
+ ensure_dir "$target_dir" "exist"
+ ensure_file "$target_dir/pid_target" "exist" "600"
+ test_regions "$target_dir/regions"
+}
+
+test_targets()
+{
+ targets_dir=$1
+ ensure_dir "$targets_dir" "exist"
+ ensure_file "$targets_dir/nr_targets" "exist" 600
+
+ ensure_write_succ "$targets_dir/nr_targets" "1" "valid input"
+ test_target "$targets_dir/0"
+
+ ensure_write_succ "$targets_dir/nr_targets" "2" "valid input"
+ test_target "$targets_dir/0"
+ test_target "$targets_dir/1"
+
+ ensure_write_succ "$targets_dir/nr_targets" "0" "valid input"
+ ensure_dir "$targets_dir/0" "not_exist"
+ ensure_dir "$targets_dir/1" "not_exist"
+}
+
+test_intervals()
+{
+ intervals_dir=$1
+ ensure_dir "$intervals_dir" "exist"
+ ensure_file "$intervals_dir/aggr_us" "exist" "600"
+ ensure_file "$intervals_dir/sample_us" "exist" "600"
+ ensure_file "$intervals_dir/update_us" "exist" "600"
+}
+
+test_monitoring_attrs()
+{
+ monitoring_attrs_dir=$1
+ ensure_dir "$monitoring_attrs_dir" "exist"
+ test_intervals "$monitoring_attrs_dir/intervals"
+ test_range "$monitoring_attrs_dir/nr_regions"
+}
+
+test_context()
+{
+ context_dir=$1
+ ensure_dir "$context_dir" "exist"
+ ensure_file "$context_dir/operations" "exist" 600
+ test_monitoring_attrs "$context_dir/monitoring_attrs"
+ test_targets "$context_dir/targets"
+ test_schemes "$context_dir/schemes"
+}
+
+test_contexts()
+{
+ contexts_dir=$1
+ ensure_dir "$contexts_dir" "exist"
+ ensure_file "$contexts_dir/nr_contexts" "exist" 600
+
+ ensure_write_succ "$contexts_dir/nr_contexts" "1" "valid input"
+ test_context "$contexts_dir/0"
+
+ ensure_write_fail "$contexts_dir/nr_contexts" "2" "only 0/1 are supported"
+ test_context "$contexts_dir/0"
+
+ ensure_write_succ "$contexts_dir/nr_contexts" "0" "valid input"
+ ensure_dir "$contexts_dir/0" "not_exist"
+}
+
+test_kdamond()
+{
+ kdamond_dir=$1
+ ensure_dir "$kdamond_dir" "exist"
+ ensure_file "$kdamond_dir/state" "exist" "600"
+ ensure_file "$kdamond_dir/pid" "exist" 400
+ test_contexts "$kdamond_dir/contexts"
+}
+
+test_kdamonds()
+{
+ kdamonds_dir=$1
+ ensure_dir "$kdamonds_dir" "exist"
+
+ ensure_file "$kdamonds_dir/nr_kdamonds" "exist" "600"
+
+ ensure_write_succ "$kdamonds_dir/nr_kdamonds" "1" "valid input"
+ test_kdamond "$kdamonds_dir/0"
+
+ ensure_write_succ "$kdamonds_dir/nr_kdamonds" "2" "valid input"
+ test_kdamond "$kdamonds_dir/0"
+ test_kdamond "$kdamonds_dir/1"
+
+ ensure_write_succ "$kdamonds_dir/nr_kdamonds" "0" "valid input"
+ ensure_dir "$kdamonds_dir/0" "not_exist"
+ ensure_dir "$kdamonds_dir/1" "not_exist"
+}
+
+test_damon_sysfs()
+{
+ damon_sysfs=$1
+ if [ ! -d "$damon_sysfs" ]
+ then
+ echo "$damon_sysfs not found"
+ exit $ksft_skip
+ fi
+
+ test_kdamonds "$damon_sysfs/kdamonds"
+}
+
+check_dependencies()
+{
+ if [ $EUID -ne 0 ]
+ then
+ echo "Run as root"
+ exit $ksft_skip
+ fi
+}
+
+check_dependencies
+test_damon_sysfs "/sys/kernel/mm/damon/admin"
diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh
index bcb110e830ce..dea33dc93790 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh
@@ -50,8 +50,8 @@ for current_test in ${TESTS:-$ALL_TESTS}; do
else
log_test "'$current_test' [$profile] overflow $target"
fi
+ RET_FIN=$(( RET_FIN || RET ))
done
- RET_FIN=$(( RET_FIN || RET ))
done
done
current_test=""
diff --git a/tools/testing/selftests/drivers/net/mlxsw/tc_police_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/tc_police_scale.sh
index 3e3e06ea5703..86e787895f78 100644
--- a/tools/testing/selftests/drivers/net/mlxsw/tc_police_scale.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/tc_police_scale.sh
@@ -60,7 +60,8 @@ __tc_police_test()
tc_police_rules_create $count $should_fail
- offload_count=$(tc filter show dev $swp1 ingress | grep in_hw | wc -l)
+ offload_count=$(tc -j filter show dev $swp1 ingress |
+ jq "[.[] | select(.options.in_hw == true)] | length")
((offload_count == count))
check_err_fail $should_fail $? "tc police offload count"
}
diff --git a/tools/testing/selftests/exec/Makefile b/tools/testing/selftests/exec/Makefile
index dd61118df66e..a89ba6de7987 100644
--- a/tools/testing/selftests/exec/Makefile
+++ b/tools/testing/selftests/exec/Makefile
@@ -3,13 +3,14 @@ CFLAGS = -Wall
CFLAGS += -Wno-nonnull
CFLAGS += -D_GNU_SOURCE
-TEST_PROGS := binfmt_script non-regular
-TEST_GEN_PROGS := execveat load_address_4096 load_address_2097152 load_address_16777216
-TEST_GEN_FILES := execveat.symlink execveat.denatured script subdir pipe
+TEST_PROGS := binfmt_script
+TEST_GEN_PROGS := execveat load_address_4096 load_address_2097152 load_address_16777216 non-regular
+TEST_GEN_FILES := execveat.symlink execveat.denatured script subdir
# Makefile is a run-time dependency, since it's accessed by the execveat test
TEST_FILES := Makefile
TEST_GEN_PROGS += recursion-depth
+TEST_GEN_PROGS += null-argv
EXTRA_CLEAN := $(OUTPUT)/subdir.moved $(OUTPUT)/execveat.moved $(OUTPUT)/xxxxx* \
$(OUTPUT)/S_I*.test
diff --git a/tools/testing/selftests/exec/null-argv.c b/tools/testing/selftests/exec/null-argv.c
new file mode 100644
index 000000000000..c19726e710d1
--- /dev/null
+++ b/tools/testing/selftests/exec/null-argv.c
@@ -0,0 +1,78 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Test that empty argvs are swapped out for a single empty string. */
+#include <stdio.h>
+#include <unistd.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+
+#include "../kselftest.h"
+
+#define FORK(exec) \
+do { \
+ pid = fork(); \
+ if (pid == 0) { \
+ /* Child */ \
+ exec; /* Some kind of exec */ \
+ perror("# " #exec); \
+ return 1; \
+ } \
+ check_result(pid, #exec); \
+} while (0)
+
+void check_result(pid_t pid, const char *msg)
+{
+ int wstatus;
+
+ if (pid == (pid_t)-1) {
+ perror("# fork");
+ ksft_test_result_fail("fork failed: %s\n", msg);
+ return;
+ }
+ if (waitpid(pid, &wstatus, 0) < 0) {
+ perror("# waitpid");
+ ksft_test_result_fail("waitpid failed: %s\n", msg);
+ return;
+ }
+ if (!WIFEXITED(wstatus)) {
+ ksft_test_result_fail("child did not exit: %s\n", msg);
+ return;
+ }
+ if (WEXITSTATUS(wstatus) != 0) {
+ ksft_test_result_fail("non-zero exit: %s\n", msg);
+ return;
+ }
+ ksft_test_result_pass("%s\n", msg);
+}
+
+int main(int argc, char *argv[], char *envp[])
+{
+ pid_t pid;
+ static char * const args[] = { NULL };
+ static char * const str[] = { "", NULL };
+
+ /* argc counting checks */
+ if (argc < 1) {
+ fprintf(stderr, "# FAIL: saw argc == 0 (old kernel?)\n");
+ return 1;
+ }
+ if (argc != 1) {
+ fprintf(stderr, "# FAIL: unknown argc (%d)\n", argc);
+ return 1;
+ }
+ if (argv[0][0] == '\0') {
+ /* Good, we found a NULL terminated string at argv[0]! */
+ return 0;
+ }
+
+ /* Test runner. */
+ ksft_print_header();
+ ksft_set_plan(5);
+
+ FORK(execve(argv[0], str, NULL));
+ FORK(execve(argv[0], NULL, NULL));
+ FORK(execve(argv[0], NULL, envp));
+ FORK(execve(argv[0], args, NULL));
+ FORK(execve(argv[0], args, envp));
+
+ ksft_exit(ksft_cnt.ksft_pass == ksft_plan);
+}
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc
index e96e279e0533..25432b8cd5bd 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc
@@ -19,7 +19,7 @@ fail() { # mesg
FILTER=set_ftrace_filter
FUNC1="schedule"
-FUNC2="do_softirq"
+FUNC2="scheduler_tick"
ALL_FUNCS="#### all functions enabled ####"
diff --git a/tools/testing/selftests/futex/Makefile b/tools/testing/selftests/futex/Makefile
index 12631f0076a1..11e157d7533b 100644
--- a/tools/testing/selftests/futex/Makefile
+++ b/tools/testing/selftests/futex/Makefile
@@ -11,7 +11,7 @@ all:
@for DIR in $(SUBDIRS); do \
BUILD_TARGET=$(OUTPUT)/$$DIR; \
mkdir $$BUILD_TARGET -p; \
- make OUTPUT=$$BUILD_TARGET -C $$DIR $@;\
+ $(MAKE) OUTPUT=$$BUILD_TARGET -C $$DIR $@;\
if [ -e $$DIR/$(TEST_PROGS) ]; then \
rsync -a $$DIR/$(TEST_PROGS) $$BUILD_TARGET/; \
fi \
@@ -32,6 +32,6 @@ override define CLEAN
@for DIR in $(SUBDIRS); do \
BUILD_TARGET=$(OUTPUT)/$$DIR; \
mkdir $$BUILD_TARGET -p; \
- make OUTPUT=$$BUILD_TARGET -C $$DIR $@;\
+ $(MAKE) OUTPUT=$$BUILD_TARGET -C $$DIR $@;\
done
endef
diff --git a/tools/testing/selftests/gpio/.gitignore b/tools/testing/selftests/gpio/.gitignore
index a4969f7ee020..ededb077a3a6 100644
--- a/tools/testing/selftests/gpio/.gitignore
+++ b/tools/testing/selftests/gpio/.gitignore
@@ -1,2 +1,4 @@
# SPDX-License-Identifier: GPL-2.0-only
gpio-mockup-cdev
+gpio-chip-info
+gpio-line-name
diff --git a/tools/testing/selftests/gpio/Makefile b/tools/testing/selftests/gpio/Makefile
index d7b312b44a62..71b306602368 100644
--- a/tools/testing/selftests/gpio/Makefile
+++ b/tools/testing/selftests/gpio/Makefile
@@ -1,8 +1,8 @@
# SPDX-License-Identifier: GPL-2.0
-TEST_PROGS := gpio-mockup.sh
+TEST_PROGS := gpio-mockup.sh gpio-sim.sh
TEST_FILES := gpio-mockup-sysfs.sh
-TEST_GEN_PROGS_EXTENDED := gpio-mockup-cdev
+TEST_GEN_PROGS_EXTENDED := gpio-mockup-cdev gpio-chip-info gpio-line-name
CFLAGS += -O2 -g -Wall -I../../../../usr/include/
include ../lib.mk
diff --git a/tools/testing/selftests/gpio/config b/tools/testing/selftests/gpio/config
index ce100342c20b..409a8532facc 100644
--- a/tools/testing/selftests/gpio/config
+++ b/tools/testing/selftests/gpio/config
@@ -1,3 +1,4 @@
CONFIG_GPIOLIB=y
CONFIG_GPIO_CDEV=y
CONFIG_GPIO_MOCKUP=m
+CONFIG_GPIO_SIM=m
diff --git a/tools/testing/selftests/gpio/gpio-chip-info.c b/tools/testing/selftests/gpio/gpio-chip-info.c
new file mode 100644
index 000000000000..fdc07e742fba
--- /dev/null
+++ b/tools/testing/selftests/gpio/gpio-chip-info.c
@@ -0,0 +1,57 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * GPIO character device helper for reading chip information.
+ *
+ * Copyright (C) 2021 Bartosz Golaszewski <[email protected]>
+ */
+
+#include <fcntl.h>
+#include <linux/gpio.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <sys/types.h>
+
+static void print_usage(void)
+{
+ printf("usage:\n");
+ printf(" gpio-chip-info <chip path> [name|label|num-lines]\n");
+}
+
+int main(int argc, char **argv)
+{
+ struct gpiochip_info info;
+ int fd, ret;
+
+ if (argc != 3) {
+ print_usage();
+ return EXIT_FAILURE;
+ }
+
+ fd = open(argv[1], O_RDWR);
+ if (fd < 0) {
+ perror("unable to open the GPIO chip");
+ return EXIT_FAILURE;
+ }
+
+ memset(&info, 0, sizeof(info));
+ ret = ioctl(fd, GPIO_GET_CHIPINFO_IOCTL, &info);
+ if (ret) {
+ perror("chip info ioctl failed");
+ return EXIT_FAILURE;
+ }
+
+ if (strcmp(argv[2], "name") == 0) {
+ printf("%s\n", info.name);
+ } else if (strcmp(argv[2], "label") == 0) {
+ printf("%s\n", info.label);
+ } else if (strcmp(argv[2], "num-lines") == 0) {
+ printf("%u\n", info.lines);
+ } else {
+ fprintf(stderr, "unknown command: %s\n", argv[2]);
+ return EXIT_FAILURE;
+ }
+
+ return EXIT_SUCCESS;
+}
diff --git a/tools/testing/selftests/gpio/gpio-line-name.c b/tools/testing/selftests/gpio/gpio-line-name.c
new file mode 100644
index 000000000000..e635cfadbded
--- /dev/null
+++ b/tools/testing/selftests/gpio/gpio-line-name.c
@@ -0,0 +1,55 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * GPIO character device helper for reading line names.
+ *
+ * Copyright (C) 2021 Bartosz Golaszewski <[email protected]>
+ */
+
+#include <fcntl.h>
+#include <linux/gpio.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <sys/types.h>
+
+static void print_usage(void)
+{
+ printf("usage:\n");
+ printf(" gpio-line-name <chip path> <line offset>\n");
+}
+
+int main(int argc, char **argv)
+{
+ struct gpio_v2_line_info info;
+ int fd, ret;
+ char *endp;
+
+ if (argc != 3) {
+ print_usage();
+ return EXIT_FAILURE;
+ }
+
+ fd = open(argv[1], O_RDWR);
+ if (fd < 0) {
+ perror("unable to open the GPIO chip");
+ return EXIT_FAILURE;
+ }
+
+ memset(&info, 0, sizeof(info));
+ info.offset = strtoul(argv[2], &endp, 10);
+ if (*endp != '\0') {
+ print_usage();
+ return EXIT_FAILURE;
+ }
+
+ ret = ioctl(fd, GPIO_V2_GET_LINEINFO_IOCTL, &info);
+ if (ret) {
+ perror("line info ioctl failed");
+ return EXIT_FAILURE;
+ }
+
+ printf("%s\n", info.name);
+
+ return EXIT_SUCCESS;
+}
diff --git a/tools/testing/selftests/gpio/gpio-sim.sh b/tools/testing/selftests/gpio/gpio-sim.sh
new file mode 100755
index 000000000000..341e3de00896
--- /dev/null
+++ b/tools/testing/selftests/gpio/gpio-sim.sh
@@ -0,0 +1,396 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (C) 2021 Bartosz Golaszewski <[email protected]>
+
+BASE_DIR=`dirname $0`
+CONFIGFS_DIR="/sys/kernel/config/gpio-sim"
+MODULE="gpio-sim"
+
+fail() {
+ echo "$*" >&2
+ echo "GPIO $MODULE test FAIL"
+ exit 1
+}
+
+skip() {
+ echo "$*" >&2
+ echo "GPIO $MODULE test SKIP"
+ exit 4
+}
+
+remove_chip() {
+ local CHIP=$1
+
+ for FILE in $CONFIGFS_DIR/$CHIP/*; do
+ BANK=`basename $FILE`
+ if [ "$BANK" = "live" -o "$BANK" = "dev_name" ]; then
+ continue
+ fi
+
+ LINES=`ls $CONFIGFS_DIR/$CHIP/$BANK/ | egrep ^line`
+ if [ "$?" = 0 ]; then
+ for LINE in $LINES; do
+ if [ -e $CONFIGFS_DIR/$CHIP/$BANK/$LINE/hog ]; then
+ rmdir $CONFIGFS_DIR/$CHIP/$BANK/$LINE/hog || \
+ fail "Unable to remove the hog"
+ fi
+
+ rmdir $CONFIGFS_DIR/$CHIP/$BANK/$LINE || \
+ fail "Unable to remove the line"
+ done
+ fi
+
+ rmdir $CONFIGFS_DIR/$CHIP/$BANK
+ done
+
+ rmdir $CONFIGFS_DIR/$CHIP || fail "Unable to remove the chip"
+}
+
+configfs_cleanup() {
+ for CHIP in `ls $CONFIGFS_DIR/`; do
+ remove_chip $CHIP
+ done
+}
+
+create_chip() {
+ local CHIP=$1
+
+ mkdir $CONFIGFS_DIR/$CHIP
+}
+
+create_bank() {
+ local CHIP=$1
+ local BANK=$2
+
+ mkdir $CONFIGFS_DIR/$CHIP/$BANK
+}
+
+set_label() {
+ local CHIP=$1
+ local BANK=$2
+ local LABEL=$3
+
+ echo $LABEL > $CONFIGFS_DIR/$CHIP/$BANK/label || fail "Unable to set the chip label"
+}
+
+set_num_lines() {
+ local CHIP=$1
+ local BANK=$2
+ local NUM_LINES=$3
+
+ echo $NUM_LINES > $CONFIGFS_DIR/$CHIP/$BANK/num_lines || \
+ fail "Unable to set the number of lines"
+}
+
+set_line_name() {
+ local CHIP=$1
+ local BANK=$2
+ local OFFSET=$3
+ local NAME=$4
+ local LINE_DIR=$CONFIGFS_DIR/$CHIP/$BANK/line$OFFSET
+
+ test -d $LINE_DIR || mkdir $LINE_DIR
+ echo $NAME > $LINE_DIR/name || fail "Unable to set the line name"
+}
+
+enable_chip() {
+ local CHIP=$1
+
+ echo 1 > $CONFIGFS_DIR/$CHIP/live || fail "Unable to enable the chip"
+}
+
+disable_chip() {
+ local CHIP=$1
+
+ echo 0 > $CONFIGFS_DIR/$CHIP/live || fail "Unable to disable the chip"
+}
+
+configfs_chip_name() {
+ local CHIP=$1
+ local BANK=$2
+
+ cat $CONFIGFS_DIR/$CHIP/$BANK/chip_name 2> /dev/null || \
+ fail "unable to read the chip name from configfs"
+}
+
+configfs_dev_name() {
+ local CHIP=$1
+
+ cat $CONFIGFS_DIR/$CHIP/dev_name 2> /dev/null || \
+ fail "unable to read the device name from configfs"
+}
+
+get_chip_num_lines() {
+ local CHIP=$1
+ local BANK=$2
+
+ $BASE_DIR/gpio-chip-info /dev/`configfs_chip_name $CHIP $BANK` num-lines || \
+ fail "unable to read the number of lines from the character device"
+}
+
+get_chip_label() {
+ local CHIP=$1
+ local BANK=$2
+
+ $BASE_DIR/gpio-chip-info /dev/`configfs_chip_name $CHIP $BANK` label || \
+ fail "unable to read the chip label from the character device"
+}
+
+get_line_name() {
+ local CHIP=$1
+ local BANK=$2
+ local OFFSET=$3
+
+ $BASE_DIR/gpio-line-name /dev/`configfs_chip_name $CHIP $BANK` $OFFSET || \
+ fail "unable to read the line name from the character device"
+}
+
+sysfs_set_pull() {
+ local DEV=$1
+ local BANK=$2
+ local OFFSET=$3
+ local PULL=$4
+ local DEVNAME=`configfs_dev_name $DEV`
+ local CHIPNAME=`configfs_chip_name $DEV $BANK`
+ local SYSFSPATH="/sys/devices/platform/$DEVNAME/$CHIPNAME/sim_gpio$OFFSET/pull"
+
+ echo $PULL > $SYSFSPATH || fail "Unable to set line pull in sysfs"
+}
+
+# Load the gpio-sim module. This will pull in configfs if needed too.
+modprobe gpio-sim || skip "unable to load the gpio-sim module"
+# Make sure configfs is mounted at /sys/kernel/config. Wait a bit if needed.
+for IDX in `seq 5`; do
+ if [ "$IDX" -eq "5" ]; then
+ skip "configfs not mounted at /sys/kernel/config"
+ fi
+
+ mountpoint -q /sys/kernel/config && break
+ sleep 0.1
+done
+# If the module was already loaded: remove all previous chips
+configfs_cleanup
+
+trap "exit 1" SIGTERM SIGINT
+trap configfs_cleanup EXIT
+
+echo "1. chip_name and dev_name attributes"
+
+echo "1.1. Chip name is communicated to user"
+create_chip chip
+create_bank chip bank
+enable_chip chip
+test -n `cat $CONFIGFS_DIR/chip/bank/chip_name` || fail "chip_name doesn't work"
+remove_chip chip
+
+echo "1.2. chip_name returns 'none' if the chip is still pending"
+create_chip chip
+create_bank chip bank
+test "`cat $CONFIGFS_DIR/chip/bank/chip_name`" = "none" || \
+ fail "chip_name doesn't return 'none' for a pending chip"
+remove_chip chip
+
+echo "1.3. Device name is communicated to user"
+create_chip chip
+create_bank chip bank
+enable_chip chip
+test -n `cat $CONFIGFS_DIR/chip/dev_name` || fail "dev_name doesn't work"
+remove_chip chip
+
+echo "2. Creating and configuring simulated chips"
+
+echo "2.1. Default number of lines is 1"
+create_chip chip
+create_bank chip bank
+enable_chip chip
+test "`get_chip_num_lines chip bank`" = "1" || fail "default number of lines is not 1"
+remove_chip chip
+
+echo "2.2. Number of lines can be specified"
+create_chip chip
+create_bank chip bank
+set_num_lines chip bank 16
+enable_chip chip
+test "`get_chip_num_lines chip bank`" = "16" || fail "number of lines is not 16"
+remove_chip chip
+
+echo "2.3. Label can be set"
+create_chip chip
+create_bank chip bank
+set_label chip bank foobar
+enable_chip chip
+test "`get_chip_label chip bank`" = "foobar" || fail "label is incorrect"
+remove_chip chip
+
+echo "2.4. Label can be left empty"
+create_chip chip
+create_bank chip bank
+enable_chip chip
+test -z "`cat $CONFIGFS_DIR/chip/bank/label`" || fail "label is not empty"
+remove_chip chip
+
+echo "2.5. Line names can be configured"
+create_chip chip
+create_bank chip bank
+set_num_lines chip bank 16
+set_line_name chip bank 0 foo
+set_line_name chip bank 2 bar
+enable_chip chip
+test "`get_line_name chip bank 0`" = "foo" || fail "line name is incorrect"
+test "`get_line_name chip bank 2`" = "bar" || fail "line name is incorrect"
+remove_chip chip
+
+echo "2.6. Line config can remain unused if offset is greater than number of lines"
+create_chip chip
+create_bank chip bank
+set_num_lines chip bank 2
+set_line_name chip bank 5 foobar
+enable_chip chip
+test "`get_line_name chip bank 0`" = "" || fail "line name is incorrect"
+test "`get_line_name chip bank 1`" = "" || fail "line name is incorrect"
+remove_chip chip
+
+echo "2.7. Line configfs directory names are sanitized"
+create_chip chip
+create_bank chip bank
+mkdir $CONFIGFS_DIR/chip/bank/line12foobar 2> /dev/null && \
+ fail "invalid configfs line name accepted"
+mkdir $CONFIGFS_DIR/chip/bank/line_no_offset 2> /dev/null && \
+ fail "invalid configfs line name accepted"
+remove_chip chip
+
+echo "2.8. Multiple chips can be created"
+CHIPS="chip0 chip1 chip2"
+for CHIP in $CHIPS; do
+ create_chip $CHIP
+ create_bank $CHIP bank
+ enable_chip $CHIP
+done
+for CHIP in $CHIPS; do
+ remove_chip $CHIP
+done
+
+echo "2.9. Can't modify settings when chip is live"
+create_chip chip
+create_bank chip bank
+enable_chip chip
+echo foobar > $CONFIGFS_DIR/chip/bank/label 2> /dev/null && \
+ fail "Setting label of a live chip should fail"
+echo 8 > $CONFIGFS_DIR/chip/bank/num_lines 2> /dev/null && \
+ fail "Setting number of lines of a live chip should fail"
+remove_chip chip
+
+echo "2.10. Can't create line items when chip is live"
+create_chip chip
+create_bank chip bank
+enable_chip chip
+mkdir $CONFIGFS_DIR/chip/bank/line0 2> /dev/null && fail "Creating line item should fail"
+remove_chip chip
+
+echo "2.11. Probe errors are propagated to user-space"
+create_chip chip
+create_bank chip bank
+set_num_lines chip bank 99999
+echo 1 > $CONFIGFS_DIR/chip/live 2> /dev/null && fail "Probe error was not propagated"
+remove_chip chip
+
+echo "2.12. Cannot enable a chip without any GPIO banks"
+create_chip chip
+echo 1 > $CONFIGFS_DIR/chip/live 2> /dev/null && fail "Chip enabled without any GPIO banks"
+remove_chip chip
+
+echo "2.13. Duplicate chip labels are not allowed"
+create_chip chip
+create_bank chip bank0
+set_label chip bank0 foobar
+create_bank chip bank1
+set_label chip bank1 foobar
+echo 1 > $CONFIGFS_DIR/chip/live 2> /dev/null && fail "Duplicate chip labels were not rejected"
+remove_chip chip
+
+echo "2.14. Lines can be hogged"
+create_chip chip
+create_bank chip bank
+set_num_lines chip bank 8
+mkdir -p $CONFIGFS_DIR/chip/bank/line4/hog
+enable_chip chip
+$BASE_DIR/gpio-mockup-cdev -s 1 /dev/`configfs_chip_name chip bank` 4 2> /dev/null && \
+ fail "Setting the value of a hogged line shouldn't succeed"
+remove_chip chip
+
+echo "3. Controlling simulated chips"
+
+echo "3.1. Pull can be set over sysfs"
+create_chip chip
+create_bank chip bank
+set_num_lines chip bank 8
+enable_chip chip
+sysfs_set_pull chip bank 0 pull-up
+$BASE_DIR/gpio-mockup-cdev /dev/`configfs_chip_name chip bank` 0
+test "$?" = "1" || fail "pull set incorrectly"
+sysfs_set_pull chip bank 0 pull-down
+$BASE_DIR/gpio-mockup-cdev /dev/`configfs_chip_name chip bank` 1
+test "$?" = "0" || fail "pull set incorrectly"
+remove_chip chip
+
+echo "3.2. Pull can be read from sysfs"
+create_chip chip
+create_bank chip bank
+set_num_lines chip bank 8
+enable_chip chip
+DEVNAME=`configfs_dev_name chip`
+CHIPNAME=`configfs_chip_name chip bank`
+SYSFS_PATH=/sys/devices/platform/$DEVNAME/$CHIPNAME/sim_gpio0/pull
+test `cat $SYSFS_PATH` = "pull-down" || fail "reading the pull failed"
+sysfs_set_pull chip bank 0 pull-up
+test `cat $SYSFS_PATH` = "pull-up" || fail "reading the pull failed"
+remove_chip chip
+
+echo "3.3. Incorrect input in sysfs is rejected"
+create_chip chip
+create_bank chip bank
+set_num_lines chip bank 8
+enable_chip chip
+DEVNAME=`configfs_dev_name chip`
+CHIPNAME=`configfs_chip_name chip bank`
+SYSFS_PATH="/sys/devices/platform/$DEVNAME/$CHIPNAME/sim_gpio0/pull"
+echo foobar > $SYSFS_PATH 2> /dev/null && fail "invalid input not detected"
+remove_chip chip
+
+echo "3.4. Can't write to value"
+create_chip chip
+create_bank chip bank
+enable_chip chip
+DEVNAME=`configfs_dev_name chip`
+CHIPNAME=`configfs_chip_name chip bank`
+SYSFS_PATH="/sys/devices/platform/$DEVNAME/$CHIPNAME/sim_gpio0/value"
+echo 1 > $SYSFS_PATH 2> /dev/null && fail "writing to 'value' succeeded unexpectedly"
+remove_chip chip
+
+echo "4. Simulated GPIO chips are functional"
+
+echo "4.1. Values can be read from sysfs"
+create_chip chip
+create_bank chip bank
+set_num_lines chip bank 8
+enable_chip chip
+DEVNAME=`configfs_dev_name chip`
+CHIPNAME=`configfs_chip_name chip bank`
+SYSFS_PATH="/sys/devices/platform/$DEVNAME/$CHIPNAME/sim_gpio0/value"
+test `cat $SYSFS_PATH` = "0" || fail "incorrect value read from sysfs"
+$BASE_DIR/gpio-mockup-cdev -s 1 /dev/`configfs_chip_name chip bank` 0 &
+sleep 0.1 # FIXME Any better way?
+test `cat $SYSFS_PATH` = "1" || fail "incorrect value read from sysfs"
+kill $!
+remove_chip chip
+
+echo "4.2. Bias settings work correctly"
+create_chip chip
+create_bank chip bank
+set_num_lines chip bank 8
+enable_chip chip
+$BASE_DIR/gpio-mockup-cdev -b pull-up /dev/`configfs_chip_name chip bank` 0
+test `cat $SYSFS_PATH` = "1" || fail "bias setting does not work"
+remove_chip chip
+
+echo "GPIO $MODULE test PASS"
diff --git a/tools/testing/selftests/ir/ir_loopback.c b/tools/testing/selftests/ir/ir_loopback.c
index 06256c96df12..f4a15cbdd5ea 100644
--- a/tools/testing/selftests/ir/ir_loopback.c
+++ b/tools/testing/selftests/ir/ir_loopback.c
@@ -29,6 +29,16 @@
#define SYSFS_PATH_MAX 256
#define DNAME_PATH_MAX 256
+/*
+ * Support ancient lirc.h which does not have these values. Can be removed
+ * once RHEL 8 is no longer a relevant testing platform.
+ */
+#if RC_PROTO_MAX < 26
+#define RC_PROTO_RCMM12 24
+#define RC_PROTO_RCMM24 25
+#define RC_PROTO_RCMM32 26
+#endif
+
static const struct {
enum rc_proto proto;
const char *name;
diff --git a/tools/testing/selftests/kexec/Makefile b/tools/testing/selftests/kexec/Makefile
index aa91d2063249..806a150648c3 100644
--- a/tools/testing/selftests/kexec/Makefile
+++ b/tools/testing/selftests/kexec/Makefile
@@ -4,7 +4,7 @@
uname_M := $(shell uname -m 2>/dev/null || echo not)
ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/x86/ -e s/x86_64/x86/)
-ifeq ($(ARCH),x86)
+ifeq ($(ARCH),$(filter $(ARCH),x86 ppc64le))
TEST_PROGS := test_kexec_load.sh test_kexec_file_load.sh
TEST_FILES := kexec_common_lib.sh
diff --git a/tools/testing/selftests/kexec/kexec_common_lib.sh b/tools/testing/selftests/kexec/kexec_common_lib.sh
index 43017cfe88f7..0e114b34d5d7 100755
--- a/tools/testing/selftests/kexec/kexec_common_lib.sh
+++ b/tools/testing/selftests/kexec/kexec_common_lib.sh
@@ -91,6 +91,27 @@ get_efi_var_secureboot_mode()
return 0;
}
+# On powerpc platform, check device-tree property
+# /proc/device-tree/ibm,secureboot/os-secureboot-enforcing
+# to detect secureboot state.
+get_ppc64_secureboot_mode()
+{
+ local secure_boot_file="/proc/device-tree/ibm,secureboot/os-secureboot-enforcing"
+ # Check for secure boot file existence
+ if [ -f $secure_boot_file ]; then
+ log_info "Secureboot is enabled (Device tree)"
+ return 1;
+ fi
+ log_info "Secureboot is not enabled (Device tree)"
+ return 0;
+}
+
+# Return the architecture of the system
+get_arch()
+{
+ echo $(arch)
+}
+
# Check efivar SecureBoot-$(the UUID) and SetupMode-$(the UUID).
# The secure boot mode can be accessed either as the last integer
# of "od -An -t u1 /sys/firmware/efi/efivars/SecureBoot-*" or from
@@ -100,14 +121,19 @@ get_efi_var_secureboot_mode()
get_secureboot_mode()
{
local secureboot_mode=0
+ local system_arch=$(get_arch)
- get_efivarfs_secureboot_mode
- secureboot_mode=$?
-
- # fallback to using the efi_var files
- if [ $secureboot_mode -eq 0 ]; then
- get_efi_var_secureboot_mode
+ if [ "$system_arch" == "ppc64le" ]; then
+ get_ppc64_secureboot_mode
+ secureboot_mode=$?
+ else
+ get_efivarfs_secureboot_mode
secureboot_mode=$?
+ # fallback to using the efi_var files
+ if [ $secureboot_mode -eq 0 ]; then
+ get_efi_var_secureboot_mode
+ secureboot_mode=$?
+ fi
fi
if [ $secureboot_mode -eq 0 ]; then
@@ -138,15 +164,20 @@ kconfig_enabled()
return 0
}
-# Attempt to get the kernel config first via proc, and then by
-# extracting it from the kernel image or the configs.ko using
-# scripts/extract-ikconfig.
+# Attempt to get the kernel config first by checking the modules directory
+# then via proc, and finally by extracting it from the kernel image or the
+# configs.ko using scripts/extract-ikconfig.
# Return 1 for found.
get_kconfig()
{
local proc_config="/proc/config.gz"
local module_dir="/lib/modules/`uname -r`"
- local configs_module="$module_dir/kernel/kernel/configs.ko"
+ local configs_module="$module_dir/kernel/kernel/configs.ko*"
+
+ if [ -f $module_dir/config ]; then
+ IKCONFIG=$module_dir/config
+ return 1
+ fi
if [ ! -f $proc_config ]; then
modprobe configs > /dev/null 2>&1
diff --git a/tools/testing/selftests/kexec/test_kexec_file_load.sh b/tools/testing/selftests/kexec/test_kexec_file_load.sh
index 2ff600388c30..c9ccb3c93d72 100755
--- a/tools/testing/selftests/kexec/test_kexec_file_load.sh
+++ b/tools/testing/selftests/kexec/test_kexec_file_load.sh
@@ -97,10 +97,11 @@ check_for_imasig()
check_for_modsig()
{
local module_sig_string="~Module signature appended~"
- local sig="$(tail --bytes $((${#module_sig_string} + 1)) $KERNEL_IMAGE)"
local ret=0
- if [ "$sig" == "$module_sig_string" ]; then
+ tail --bytes $((${#module_sig_string} + 1)) $KERNEL_IMAGE | \
+ grep -q "$module_sig_string"
+ if [ $? -eq 0 ]; then
ret=1
log_info "kexec kernel image modsig signed"
else
@@ -225,8 +226,12 @@ get_secureboot_mode
secureboot=$?
# Are there pe and ima signatures
-check_for_pesig
-pe_signed=$?
+if [ "$(get_arch)" == 'ppc64le' ]; then
+ pe_signed=0
+else
+ check_for_pesig
+ pe_signed=$?
+fi
check_for_imasig
ima_signed=$?
diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h
index 471eaa7b3a3f..11779405dc80 100644
--- a/tools/testing/selftests/kselftest_harness.h
+++ b/tools/testing/selftests/kselftest_harness.h
@@ -877,7 +877,8 @@ static void __timeout_handler(int sig, siginfo_t *info, void *ucontext)
}
t->timed_out = true;
- kill(t->pid, SIGKILL);
+ // signal process group
+ kill(-(t->pid), SIGKILL);
}
void __wait_for_test(struct __test_metadata *t)
@@ -987,6 +988,7 @@ void __run_test(struct __fixture_metadata *f,
ksft_print_msg("ERROR SPAWNING TEST CHILD\n");
t->passed = 0;
} else if (t->pid == 0) {
+ setpgrp();
t->fn(t, variant);
if (t->skip)
_exit(255);
diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index 3cb5ac5da087..dce7de7755e6 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -4,14 +4,16 @@
/aarch64/get-reg-list
/aarch64/psci_cpu_on_test
/aarch64/vgic_init
+/aarch64/vgic_irq
/s390x/memop
/s390x/resets
/s390x/sync_regs_test
+/x86_64/amx_test
+/x86_64/cpuid_test
/x86_64/cr4_cpuid_sync_test
/x86_64/debug_regs
/x86_64/evmcs_test
/x86_64/emulator_error_test
-/x86_64/get_cpuid_test
/x86_64/get_msr_index_features
/x86_64/kvm_clock_test
/x86_64/kvm_pv_test
@@ -21,6 +23,7 @@
/x86_64/mmio_warning_test
/x86_64/mmu_role_test
/x86_64/platform_info_test
+/x86_64/pmu_event_filter_test
/x86_64/set_boot_cpu_id
/x86_64/set_sregs_test
/x86_64/sev_migrate_tests
@@ -35,6 +38,7 @@
/x86_64/vmx_apic_access_test
/x86_64/vmx_close_while_nested_test
/x86_64/vmx_dirty_log_test
+/x86_64/vmx_exception_with_invalid_guest_state
/x86_64/vmx_invalid_nested_guest_state
/x86_64/vmx_preemption_timer_test
/x86_64/vmx_set_nested_state_test
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 17342b575e85..17c3f0749f05 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -32,17 +32,22 @@ endif
ifeq ($(ARCH),s390)
UNAME_M := s390x
endif
+# Set UNAME_M riscv compile/install to work
+ifeq ($(ARCH),riscv)
+ UNAME_M := riscv
+endif
LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/rbtree.c lib/sparsebit.c lib/test_util.c lib/guest_modes.c lib/perf_test_util.c
LIBKVM_x86_64 = lib/x86_64/apic.c lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/svm.c lib/x86_64/ucall.c lib/x86_64/handlers.S
LIBKVM_aarch64 = lib/aarch64/processor.c lib/aarch64/ucall.c lib/aarch64/handlers.S lib/aarch64/spinlock.c lib/aarch64/gic.c lib/aarch64/gic_v3.c lib/aarch64/vgic.c
LIBKVM_s390x = lib/s390x/processor.c lib/s390x/ucall.c lib/s390x/diag318_test_handler.c
+LIBKVM_riscv = lib/riscv/processor.c lib/riscv/ucall.c
-TEST_GEN_PROGS_x86_64 = x86_64/cr4_cpuid_sync_test
+TEST_GEN_PROGS_x86_64 = x86_64/cpuid_test
+TEST_GEN_PROGS_x86_64 += x86_64/cr4_cpuid_sync_test
TEST_GEN_PROGS_x86_64 += x86_64/get_msr_index_features
TEST_GEN_PROGS_x86_64 += x86_64/evmcs_test
TEST_GEN_PROGS_x86_64 += x86_64/emulator_error_test
-TEST_GEN_PROGS_x86_64 += x86_64/get_cpuid_test
TEST_GEN_PROGS_x86_64 += x86_64/hyperv_clock
TEST_GEN_PROGS_x86_64 += x86_64/hyperv_cpuid
TEST_GEN_PROGS_x86_64 += x86_64/hyperv_features
@@ -51,6 +56,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/kvm_pv_test
TEST_GEN_PROGS_x86_64 += x86_64/mmio_warning_test
TEST_GEN_PROGS_x86_64 += x86_64/mmu_role_test
TEST_GEN_PROGS_x86_64 += x86_64/platform_info_test
+TEST_GEN_PROGS_x86_64 += x86_64/pmu_event_filter_test
TEST_GEN_PROGS_x86_64 += x86_64/set_boot_cpu_id
TEST_GEN_PROGS_x86_64 += x86_64/set_sregs_test
TEST_GEN_PROGS_x86_64 += x86_64/smm_test
@@ -64,6 +70,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/userspace_msr_exit_test
TEST_GEN_PROGS_x86_64 += x86_64/vmx_apic_access_test
TEST_GEN_PROGS_x86_64 += x86_64/vmx_close_while_nested_test
TEST_GEN_PROGS_x86_64 += x86_64/vmx_dirty_log_test
+TEST_GEN_PROGS_x86_64 += x86_64/vmx_exception_with_invalid_guest_state
TEST_GEN_PROGS_x86_64 += x86_64/vmx_invalid_nested_guest_state
TEST_GEN_PROGS_x86_64 += x86_64/vmx_set_nested_state_test
TEST_GEN_PROGS_x86_64 += x86_64/vmx_tsc_adjust_test
@@ -75,8 +82,9 @@ TEST_GEN_PROGS_x86_64 += x86_64/tsc_msrs_test
TEST_GEN_PROGS_x86_64 += x86_64/vmx_pmu_msrs_test
TEST_GEN_PROGS_x86_64 += x86_64/xen_shinfo_test
TEST_GEN_PROGS_x86_64 += x86_64/xen_vmcall_test
-TEST_GEN_PROGS_x86_64 += x86_64/vmx_pi_mmio_test
TEST_GEN_PROGS_x86_64 += x86_64/sev_migrate_tests
+TEST_GEN_PROGS_x86_64 += x86_64/amx_test
+TEST_GEN_PROGS_x86_64 += access_tracking_perf_test
TEST_GEN_PROGS_x86_64 += demand_paging_test
TEST_GEN_PROGS_x86_64 += dirty_log_test
TEST_GEN_PROGS_x86_64 += dirty_log_perf_test
@@ -96,6 +104,7 @@ TEST_GEN_PROGS_aarch64 += aarch64/debug-exceptions
TEST_GEN_PROGS_aarch64 += aarch64/get-reg-list
TEST_GEN_PROGS_aarch64 += aarch64/psci_cpu_on_test
TEST_GEN_PROGS_aarch64 += aarch64/vgic_init
+TEST_GEN_PROGS_aarch64 += aarch64/vgic_irq
TEST_GEN_PROGS_aarch64 += demand_paging_test
TEST_GEN_PROGS_aarch64 += dirty_log_test
TEST_GEN_PROGS_aarch64 += dirty_log_perf_test
@@ -119,6 +128,13 @@ TEST_GEN_PROGS_s390x += rseq_test
TEST_GEN_PROGS_s390x += set_memory_region_test
TEST_GEN_PROGS_s390x += kvm_binary_stats_test
+TEST_GEN_PROGS_riscv += demand_paging_test
+TEST_GEN_PROGS_riscv += dirty_log_test
+TEST_GEN_PROGS_riscv += kvm_create_max_vcpus
+TEST_GEN_PROGS_riscv += kvm_page_table_test
+TEST_GEN_PROGS_riscv += set_memory_region_test
+TEST_GEN_PROGS_riscv += kvm_binary_stats_test
+
TEST_GEN_PROGS += $(TEST_GEN_PROGS_$(UNAME_M))
LIBKVM += $(LIBKVM_$(UNAME_M))
@@ -133,7 +149,7 @@ endif
CFLAGS += -Wall -Wstrict-prototypes -Wuninitialized -O2 -g -std=gnu99 \
-fno-stack-protector -fno-PIE -I$(LINUX_TOOL_INCLUDE) \
-I$(LINUX_TOOL_ARCH_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude \
- -I$(<D) -Iinclude/$(UNAME_M) -I..
+ -I$(<D) -Iinclude/$(UNAME_M) -I.. $(EXTRA_CFLAGS)
no-pie-option := $(call try-run, echo 'int main() { return 0; }' | \
$(CC) -Werror -no-pie -x c - -o "$$TMP", -no-pie)
diff --git a/tools/testing/selftests/kvm/aarch64/arch_timer.c b/tools/testing/selftests/kvm/aarch64/arch_timer.c
index bf6a45b0b8dc..b08d30bf71c5 100644
--- a/tools/testing/selftests/kvm/aarch64/arch_timer.c
+++ b/tools/testing/selftests/kvm/aarch64/arch_timer.c
@@ -366,6 +366,7 @@ static struct kvm_vm *test_vm_create(void)
{
struct kvm_vm *vm;
unsigned int i;
+ int ret;
int nr_vcpus = test_args.nr_vcpus;
vm = vm_create_default_with_vcpus(nr_vcpus, 0, 0, guest_code, NULL);
@@ -382,7 +383,11 @@ static struct kvm_vm *test_vm_create(void)
ucall_init(vm, NULL);
test_init_timer_irq(vm);
- vgic_v3_setup(vm, nr_vcpus, GICD_BASE_GPA, GICR_BASE_GPA);
+ ret = vgic_v3_setup(vm, nr_vcpus, 64, GICD_BASE_GPA, GICR_BASE_GPA);
+ if (ret < 0) {
+ print_skip("Failed to create vgic-v3");
+ exit(KSFT_SKIP);
+ }
/* Make all the test's cmdline args visible to the guest */
sync_global_to_guest(vm, test_args);
diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list.c b/tools/testing/selftests/kvm/aarch64/get-reg-list.c
index cc898181faab..f769fc6cd927 100644
--- a/tools/testing/selftests/kvm/aarch64/get-reg-list.c
+++ b/tools/testing/selftests/kvm/aarch64/get-reg-list.c
@@ -1014,6 +1014,22 @@ static __u64 sve_rejects_set[] = {
KVM_REG_ARM64_SVE_VLS,
};
+static __u64 pauth_addr_regs[] = {
+ ARM64_SYS_REG(3, 0, 2, 1, 0), /* APIAKEYLO_EL1 */
+ ARM64_SYS_REG(3, 0, 2, 1, 1), /* APIAKEYHI_EL1 */
+ ARM64_SYS_REG(3, 0, 2, 1, 2), /* APIBKEYLO_EL1 */
+ ARM64_SYS_REG(3, 0, 2, 1, 3), /* APIBKEYHI_EL1 */
+ ARM64_SYS_REG(3, 0, 2, 2, 0), /* APDAKEYLO_EL1 */
+ ARM64_SYS_REG(3, 0, 2, 2, 1), /* APDAKEYHI_EL1 */
+ ARM64_SYS_REG(3, 0, 2, 2, 2), /* APDBKEYLO_EL1 */
+ ARM64_SYS_REG(3, 0, 2, 2, 3) /* APDBKEYHI_EL1 */
+};
+
+static __u64 pauth_generic_regs[] = {
+ ARM64_SYS_REG(3, 0, 2, 3, 0), /* APGAKEYLO_EL1 */
+ ARM64_SYS_REG(3, 0, 2, 3, 1), /* APGAKEYHI_EL1 */
+};
+
#define BASE_SUBLIST \
{ "base", .regs = base_regs, .regs_n = ARRAY_SIZE(base_regs), }
#define VREGS_SUBLIST \
@@ -1025,6 +1041,21 @@ static __u64 sve_rejects_set[] = {
{ "sve", .capability = KVM_CAP_ARM_SVE, .feature = KVM_ARM_VCPU_SVE, .finalize = true, \
.regs = sve_regs, .regs_n = ARRAY_SIZE(sve_regs), \
.rejects_set = sve_rejects_set, .rejects_set_n = ARRAY_SIZE(sve_rejects_set), }
+#define PAUTH_SUBLIST \
+ { \
+ .name = "pauth_address", \
+ .capability = KVM_CAP_ARM_PTRAUTH_ADDRESS, \
+ .feature = KVM_ARM_VCPU_PTRAUTH_ADDRESS, \
+ .regs = pauth_addr_regs, \
+ .regs_n = ARRAY_SIZE(pauth_addr_regs), \
+ }, \
+ { \
+ .name = "pauth_generic", \
+ .capability = KVM_CAP_ARM_PTRAUTH_GENERIC, \
+ .feature = KVM_ARM_VCPU_PTRAUTH_GENERIC, \
+ .regs = pauth_generic_regs, \
+ .regs_n = ARRAY_SIZE(pauth_generic_regs), \
+ }
static struct vcpu_config vregs_config = {
.sublists = {
@@ -1056,11 +1087,30 @@ static struct vcpu_config sve_pmu_config = {
{0},
},
};
+static struct vcpu_config pauth_config = {
+ .sublists = {
+ BASE_SUBLIST,
+ VREGS_SUBLIST,
+ PAUTH_SUBLIST,
+ {0},
+ },
+};
+static struct vcpu_config pauth_pmu_config = {
+ .sublists = {
+ BASE_SUBLIST,
+ VREGS_SUBLIST,
+ PAUTH_SUBLIST,
+ PMU_SUBLIST,
+ {0},
+ },
+};
static struct vcpu_config *vcpu_configs[] = {
&vregs_config,
&vregs_pmu_config,
&sve_config,
&sve_pmu_config,
+ &pauth_config,
+ &pauth_pmu_config,
};
static int vcpu_configs_n = ARRAY_SIZE(vcpu_configs);
diff --git a/tools/testing/selftests/kvm/aarch64/vgic_irq.c b/tools/testing/selftests/kvm/aarch64/vgic_irq.c
new file mode 100644
index 000000000000..7eca97799917
--- /dev/null
+++ b/tools/testing/selftests/kvm/aarch64/vgic_irq.c
@@ -0,0 +1,857 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * vgic_irq.c - Test userspace injection of IRQs
+ *
+ * This test validates the injection of IRQs from userspace using various
+ * methods (e.g., KVM_IRQ_LINE) and modes (e.g., EOI). The guest "asks" the
+ * host to inject a specific intid via a GUEST_SYNC call, and then checks that
+ * it received it.
+ */
+
+#include <asm/kvm.h>
+#include <asm/kvm_para.h>
+#include <sys/eventfd.h>
+#include <linux/sizes.h>
+
+#include "processor.h"
+#include "test_util.h"
+#include "kvm_util.h"
+#include "gic.h"
+#include "gic_v3.h"
+#include "vgic.h"
+
+#define GICD_BASE_GPA 0x08000000ULL
+#define GICR_BASE_GPA 0x080A0000ULL
+#define VCPU_ID 0
+
+/*
+ * Stores the user specified args; it's passed to the guest and to every test
+ * function.
+ */
+struct test_args {
+ uint32_t nr_irqs; /* number of KVM supported IRQs. */
+ bool eoi_split; /* 1 is eoir+dir, 0 is eoir only */
+ bool level_sensitive; /* 1 is level, 0 is edge */
+ int kvm_max_routes; /* output of KVM_CAP_IRQ_ROUTING */
+ bool kvm_supports_irqfd; /* output of KVM_CAP_IRQFD */
+};
+
+/*
+ * KVM implements 32 priority levels:
+ * 0x00 (highest priority) - 0xF8 (lowest priority), in steps of 8
+ *
+ * Note that these macros will still be correct in the case that KVM implements
+ * more priority levels. Also note that 32 is the minimum for GICv3 and GICv2.
+ */
+#define KVM_NUM_PRIOS 32
+#define KVM_PRIO_SHIFT 3 /* steps of 8 = 1 << 3 */
+#define KVM_PRIO_STEPS (1 << KVM_PRIO_SHIFT) /* 8 */
+#define LOWEST_PRIO (KVM_NUM_PRIOS - 1)
+#define CPU_PRIO_MASK (LOWEST_PRIO << KVM_PRIO_SHIFT) /* 0xf8 */
+#define IRQ_DEFAULT_PRIO (LOWEST_PRIO - 1)
+#define IRQ_DEFAULT_PRIO_REG (IRQ_DEFAULT_PRIO << KVM_PRIO_SHIFT) /* 0xf0 */
+
+static void *dist = (void *)GICD_BASE_GPA;
+static void *redist = (void *)GICR_BASE_GPA;
+
+/*
+ * The kvm_inject_* utilities are used by the guest to ask the host to inject
+ * interrupts (e.g., using the KVM_IRQ_LINE ioctl).
+ */
+
+typedef enum {
+ KVM_INJECT_EDGE_IRQ_LINE = 1,
+ KVM_SET_IRQ_LINE,
+ KVM_SET_IRQ_LINE_HIGH,
+ KVM_SET_LEVEL_INFO_HIGH,
+ KVM_INJECT_IRQFD,
+ KVM_WRITE_ISPENDR,
+ KVM_WRITE_ISACTIVER,
+} kvm_inject_cmd;
+
+struct kvm_inject_args {
+ kvm_inject_cmd cmd;
+ uint32_t first_intid;
+ uint32_t num;
+ int level;
+ bool expect_failure;
+};
+
+/* Used on the guest side to perform the hypercall. */
+static void kvm_inject_call(kvm_inject_cmd cmd, uint32_t first_intid,
+ uint32_t num, int level, bool expect_failure);
+
+/* Used on the host side to get the hypercall info. */
+static void kvm_inject_get_call(struct kvm_vm *vm, struct ucall *uc,
+ struct kvm_inject_args *args);
+
+#define _KVM_INJECT_MULTI(cmd, intid, num, expect_failure) \
+ kvm_inject_call(cmd, intid, num, -1 /* not used */, expect_failure)
+
+#define KVM_INJECT_MULTI(cmd, intid, num) \
+ _KVM_INJECT_MULTI(cmd, intid, num, false)
+
+#define _KVM_INJECT(cmd, intid, expect_failure) \
+ _KVM_INJECT_MULTI(cmd, intid, 1, expect_failure)
+
+#define KVM_INJECT(cmd, intid) \
+ _KVM_INJECT_MULTI(cmd, intid, 1, false)
+
+#define KVM_ACTIVATE(cmd, intid) \
+ kvm_inject_call(cmd, intid, 1, 1, false);
+
+struct kvm_inject_desc {
+ kvm_inject_cmd cmd;
+ /* can inject PPIs, PPIs, and/or SPIs. */
+ bool sgi, ppi, spi;
+};
+
+static struct kvm_inject_desc inject_edge_fns[] = {
+ /* sgi ppi spi */
+ { KVM_INJECT_EDGE_IRQ_LINE, false, false, true },
+ { KVM_INJECT_IRQFD, false, false, true },
+ { KVM_WRITE_ISPENDR, true, false, true },
+ { 0, },
+};
+
+static struct kvm_inject_desc inject_level_fns[] = {
+ /* sgi ppi spi */
+ { KVM_SET_IRQ_LINE_HIGH, false, true, true },
+ { KVM_SET_LEVEL_INFO_HIGH, false, true, true },
+ { KVM_INJECT_IRQFD, false, false, true },
+ { KVM_WRITE_ISPENDR, false, true, true },
+ { 0, },
+};
+
+static struct kvm_inject_desc set_active_fns[] = {
+ /* sgi ppi spi */
+ { KVM_WRITE_ISACTIVER, true, true, true },
+ { 0, },
+};
+
+#define for_each_inject_fn(t, f) \
+ for ((f) = (t); (f)->cmd; (f)++)
+
+#define for_each_supported_inject_fn(args, t, f) \
+ for_each_inject_fn(t, f) \
+ if ((args)->kvm_supports_irqfd || (f)->cmd != KVM_INJECT_IRQFD)
+
+#define for_each_supported_activate_fn(args, t, f) \
+ for_each_supported_inject_fn((args), (t), (f))
+
+/* Shared between the guest main thread and the IRQ handlers. */
+volatile uint64_t irq_handled;
+volatile uint32_t irqnr_received[MAX_SPI + 1];
+
+static void reset_stats(void)
+{
+ int i;
+
+ irq_handled = 0;
+ for (i = 0; i <= MAX_SPI; i++)
+ irqnr_received[i] = 0;
+}
+
+static uint64_t gic_read_ap1r0(void)
+{
+ uint64_t reg = read_sysreg_s(SYS_ICV_AP1R0_EL1);
+
+ dsb(sy);
+ return reg;
+}
+
+static void gic_write_ap1r0(uint64_t val)
+{
+ write_sysreg_s(val, SYS_ICV_AP1R0_EL1);
+ isb();
+}
+
+static void guest_set_irq_line(uint32_t intid, uint32_t level);
+
+static void guest_irq_generic_handler(bool eoi_split, bool level_sensitive)
+{
+ uint32_t intid = gic_get_and_ack_irq();
+
+ if (intid == IAR_SPURIOUS)
+ return;
+
+ GUEST_ASSERT(gic_irq_get_active(intid));
+
+ if (!level_sensitive)
+ GUEST_ASSERT(!gic_irq_get_pending(intid));
+
+ if (level_sensitive)
+ guest_set_irq_line(intid, 0);
+
+ GUEST_ASSERT(intid < MAX_SPI);
+ irqnr_received[intid] += 1;
+ irq_handled += 1;
+
+ gic_set_eoi(intid);
+ GUEST_ASSERT_EQ(gic_read_ap1r0(), 0);
+ if (eoi_split)
+ gic_set_dir(intid);
+
+ GUEST_ASSERT(!gic_irq_get_active(intid));
+ GUEST_ASSERT(!gic_irq_get_pending(intid));
+}
+
+static void kvm_inject_call(kvm_inject_cmd cmd, uint32_t first_intid,
+ uint32_t num, int level, bool expect_failure)
+{
+ struct kvm_inject_args args = {
+ .cmd = cmd,
+ .first_intid = first_intid,
+ .num = num,
+ .level = level,
+ .expect_failure = expect_failure,
+ };
+ GUEST_SYNC(&args);
+}
+
+#define GUEST_ASSERT_IAR_EMPTY() \
+do { \
+ uint32_t _intid; \
+ _intid = gic_get_and_ack_irq(); \
+ GUEST_ASSERT(_intid == 0 || _intid == IAR_SPURIOUS); \
+} while (0)
+
+#define CAT_HELPER(a, b) a ## b
+#define CAT(a, b) CAT_HELPER(a, b)
+#define PREFIX guest_irq_handler_
+#define GUEST_IRQ_HANDLER_NAME(split, lev) CAT(PREFIX, CAT(split, lev))
+#define GENERATE_GUEST_IRQ_HANDLER(split, lev) \
+static void CAT(PREFIX, CAT(split, lev))(struct ex_regs *regs) \
+{ \
+ guest_irq_generic_handler(split, lev); \
+}
+
+GENERATE_GUEST_IRQ_HANDLER(0, 0);
+GENERATE_GUEST_IRQ_HANDLER(0, 1);
+GENERATE_GUEST_IRQ_HANDLER(1, 0);
+GENERATE_GUEST_IRQ_HANDLER(1, 1);
+
+static void (*guest_irq_handlers[2][2])(struct ex_regs *) = {
+ {GUEST_IRQ_HANDLER_NAME(0, 0), GUEST_IRQ_HANDLER_NAME(0, 1),},
+ {GUEST_IRQ_HANDLER_NAME(1, 0), GUEST_IRQ_HANDLER_NAME(1, 1),},
+};
+
+static void reset_priorities(struct test_args *args)
+{
+ int i;
+
+ for (i = 0; i < args->nr_irqs; i++)
+ gic_set_priority(i, IRQ_DEFAULT_PRIO_REG);
+}
+
+static void guest_set_irq_line(uint32_t intid, uint32_t level)
+{
+ kvm_inject_call(KVM_SET_IRQ_LINE, intid, 1, level, false);
+}
+
+static void test_inject_fail(struct test_args *args,
+ uint32_t intid, kvm_inject_cmd cmd)
+{
+ reset_stats();
+
+ _KVM_INJECT(cmd, intid, true);
+ /* no IRQ to handle on entry */
+
+ GUEST_ASSERT_EQ(irq_handled, 0);
+ GUEST_ASSERT_IAR_EMPTY();
+}
+
+static void guest_inject(struct test_args *args,
+ uint32_t first_intid, uint32_t num,
+ kvm_inject_cmd cmd)
+{
+ uint32_t i;
+
+ reset_stats();
+
+ /* Cycle over all priorities to make things more interesting. */
+ for (i = first_intid; i < num + first_intid; i++)
+ gic_set_priority(i, (i % (KVM_NUM_PRIOS - 1)) << 3);
+
+ asm volatile("msr daifset, #2" : : : "memory");
+ KVM_INJECT_MULTI(cmd, first_intid, num);
+
+ while (irq_handled < num) {
+ asm volatile("wfi\n"
+ "msr daifclr, #2\n"
+ /* handle IRQ */
+ "msr daifset, #2\n"
+ : : : "memory");
+ }
+ asm volatile("msr daifclr, #2" : : : "memory");
+
+ GUEST_ASSERT_EQ(irq_handled, num);
+ for (i = first_intid; i < num + first_intid; i++)
+ GUEST_ASSERT_EQ(irqnr_received[i], 1);
+ GUEST_ASSERT_IAR_EMPTY();
+
+ reset_priorities(args);
+}
+
+/*
+ * Restore the active state of multiple concurrent IRQs (given by
+ * concurrent_irqs). This does what a live-migration would do on the
+ * destination side assuming there are some active IRQs that were not
+ * deactivated yet.
+ */
+static void guest_restore_active(struct test_args *args,
+ uint32_t first_intid, uint32_t num,
+ kvm_inject_cmd cmd)
+{
+ uint32_t prio, intid, ap1r;
+ int i;
+
+ /* Set the priorities of the first (KVM_NUM_PRIOS - 1) IRQs
+ * in descending order, so intid+1 can preempt intid.
+ */
+ for (i = 0, prio = (num - 1) * 8; i < num; i++, prio -= 8) {
+ GUEST_ASSERT(prio >= 0);
+ intid = i + first_intid;
+ gic_set_priority(intid, prio);
+ }
+
+ /* In a real migration, KVM would restore all GIC state before running
+ * guest code.
+ */
+ for (i = 0; i < num; i++) {
+ intid = i + first_intid;
+ KVM_ACTIVATE(cmd, intid);
+ ap1r = gic_read_ap1r0();
+ ap1r |= 1U << i;
+ gic_write_ap1r0(ap1r);
+ }
+
+ /* This is where the "migration" would occur. */
+
+ /* finish handling the IRQs starting with the highest priority one. */
+ for (i = 0; i < num; i++) {
+ intid = num - i - 1 + first_intid;
+ gic_set_eoi(intid);
+ if (args->eoi_split)
+ gic_set_dir(intid);
+ }
+
+ for (i = 0; i < num; i++)
+ GUEST_ASSERT(!gic_irq_get_active(i + first_intid));
+ GUEST_ASSERT_EQ(gic_read_ap1r0(), 0);
+ GUEST_ASSERT_IAR_EMPTY();
+}
+
+/*
+ * Polls the IAR until it's not a spurious interrupt.
+ *
+ * This function should only be used in test_inject_preemption (with IRQs
+ * masked).
+ */
+static uint32_t wait_for_and_activate_irq(void)
+{
+ uint32_t intid;
+
+ do {
+ asm volatile("wfi" : : : "memory");
+ intid = gic_get_and_ack_irq();
+ } while (intid == IAR_SPURIOUS);
+
+ return intid;
+}
+
+/*
+ * Inject multiple concurrent IRQs (num IRQs starting at first_intid) and
+ * handle them without handling the actual exceptions. This is done by masking
+ * interrupts for the whole test.
+ */
+static void test_inject_preemption(struct test_args *args,
+ uint32_t first_intid, int num,
+ kvm_inject_cmd cmd)
+{
+ uint32_t intid, prio, step = KVM_PRIO_STEPS;
+ int i;
+
+ /* Set the priorities of the first (KVM_NUM_PRIOS - 1) IRQs
+ * in descending order, so intid+1 can preempt intid.
+ */
+ for (i = 0, prio = (num - 1) * step; i < num; i++, prio -= step) {
+ GUEST_ASSERT(prio >= 0);
+ intid = i + first_intid;
+ gic_set_priority(intid, prio);
+ }
+
+ local_irq_disable();
+
+ for (i = 0; i < num; i++) {
+ uint32_t tmp;
+ intid = i + first_intid;
+ KVM_INJECT(cmd, intid);
+ /* Each successive IRQ will preempt the previous one. */
+ tmp = wait_for_and_activate_irq();
+ GUEST_ASSERT_EQ(tmp, intid);
+ if (args->level_sensitive)
+ guest_set_irq_line(intid, 0);
+ }
+
+ /* finish handling the IRQs starting with the highest priority one. */
+ for (i = 0; i < num; i++) {
+ intid = num - i - 1 + first_intid;
+ gic_set_eoi(intid);
+ if (args->eoi_split)
+ gic_set_dir(intid);
+ }
+
+ local_irq_enable();
+
+ for (i = 0; i < num; i++)
+ GUEST_ASSERT(!gic_irq_get_active(i + first_intid));
+ GUEST_ASSERT_EQ(gic_read_ap1r0(), 0);
+ GUEST_ASSERT_IAR_EMPTY();
+
+ reset_priorities(args);
+}
+
+static void test_injection(struct test_args *args, struct kvm_inject_desc *f)
+{
+ uint32_t nr_irqs = args->nr_irqs;
+
+ if (f->sgi) {
+ guest_inject(args, MIN_SGI, 1, f->cmd);
+ guest_inject(args, 0, 16, f->cmd);
+ }
+
+ if (f->ppi)
+ guest_inject(args, MIN_PPI, 1, f->cmd);
+
+ if (f->spi) {
+ guest_inject(args, MIN_SPI, 1, f->cmd);
+ guest_inject(args, nr_irqs - 1, 1, f->cmd);
+ guest_inject(args, MIN_SPI, nr_irqs - MIN_SPI, f->cmd);
+ }
+}
+
+static void test_injection_failure(struct test_args *args,
+ struct kvm_inject_desc *f)
+{
+ uint32_t bad_intid[] = { args->nr_irqs, 1020, 1024, 1120, 5120, ~0U, };
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(bad_intid); i++)
+ test_inject_fail(args, bad_intid[i], f->cmd);
+}
+
+static void test_preemption(struct test_args *args, struct kvm_inject_desc *f)
+{
+ /*
+ * Test up to 4 levels of preemption. The reason is that KVM doesn't
+ * currently implement the ability to have more than the number-of-LRs
+ * number of concurrently active IRQs. The number of LRs implemented is
+ * IMPLEMENTATION DEFINED, however, it seems that most implement 4.
+ */
+ if (f->sgi)
+ test_inject_preemption(args, MIN_SGI, 4, f->cmd);
+
+ if (f->ppi)
+ test_inject_preemption(args, MIN_PPI, 4, f->cmd);
+
+ if (f->spi)
+ test_inject_preemption(args, MIN_SPI, 4, f->cmd);
+}
+
+static void test_restore_active(struct test_args *args, struct kvm_inject_desc *f)
+{
+ /* Test up to 4 active IRQs. Same reason as in test_preemption. */
+ if (f->sgi)
+ guest_restore_active(args, MIN_SGI, 4, f->cmd);
+
+ if (f->ppi)
+ guest_restore_active(args, MIN_PPI, 4, f->cmd);
+
+ if (f->spi)
+ guest_restore_active(args, MIN_SPI, 4, f->cmd);
+}
+
+static void guest_code(struct test_args args)
+{
+ uint32_t i, nr_irqs = args.nr_irqs;
+ bool level_sensitive = args.level_sensitive;
+ struct kvm_inject_desc *f, *inject_fns;
+
+ gic_init(GIC_V3, 1, dist, redist);
+
+ for (i = 0; i < nr_irqs; i++)
+ gic_irq_enable(i);
+
+ for (i = MIN_SPI; i < nr_irqs; i++)
+ gic_irq_set_config(i, !args.level_sensitive);
+
+ gic_set_eoi_split(args.eoi_split);
+
+ reset_priorities(&args);
+ gic_set_priority_mask(CPU_PRIO_MASK);
+
+ inject_fns = level_sensitive ? inject_level_fns
+ : inject_edge_fns;
+
+ local_irq_enable();
+
+ /* Start the tests. */
+ for_each_supported_inject_fn(&args, inject_fns, f) {
+ test_injection(&args, f);
+ test_preemption(&args, f);
+ test_injection_failure(&args, f);
+ }
+
+ /* Restore the active state of IRQs. This would happen when live
+ * migrating IRQs in the middle of being handled.
+ */
+ for_each_supported_activate_fn(&args, set_active_fns, f)
+ test_restore_active(&args, f);
+
+ GUEST_DONE();
+}
+
+static void kvm_irq_line_check(struct kvm_vm *vm, uint32_t intid, int level,
+ struct test_args *test_args, bool expect_failure)
+{
+ int ret;
+
+ if (!expect_failure) {
+ kvm_arm_irq_line(vm, intid, level);
+ } else {
+ /* The interface doesn't allow larger intid's. */
+ if (intid > KVM_ARM_IRQ_NUM_MASK)
+ return;
+
+ ret = _kvm_arm_irq_line(vm, intid, level);
+ TEST_ASSERT(ret != 0 && errno == EINVAL,
+ "Bad intid %i did not cause KVM_IRQ_LINE "
+ "error: rc: %i errno: %i", intid, ret, errno);
+ }
+}
+
+void kvm_irq_set_level_info_check(int gic_fd, uint32_t intid, int level,
+ bool expect_failure)
+{
+ if (!expect_failure) {
+ kvm_irq_set_level_info(gic_fd, intid, level);
+ } else {
+ int ret = _kvm_irq_set_level_info(gic_fd, intid, level);
+ /*
+ * The kernel silently fails for invalid SPIs and SGIs (which
+ * are not level-sensitive). It only checks for intid to not
+ * spill over 1U << 10 (the max reserved SPI). Also, callers
+ * are supposed to mask the intid with 0x3ff (1023).
+ */
+ if (intid > VGIC_MAX_RESERVED)
+ TEST_ASSERT(ret != 0 && errno == EINVAL,
+ "Bad intid %i did not cause VGIC_GRP_LEVEL_INFO "
+ "error: rc: %i errno: %i", intid, ret, errno);
+ else
+ TEST_ASSERT(!ret, "KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO "
+ "for intid %i failed, rc: %i errno: %i",
+ intid, ret, errno);
+ }
+}
+
+static void kvm_set_gsi_routing_irqchip_check(struct kvm_vm *vm,
+ uint32_t intid, uint32_t num, uint32_t kvm_max_routes,
+ bool expect_failure)
+{
+ struct kvm_irq_routing *routing;
+ int ret;
+ uint64_t i;
+
+ assert(num <= kvm_max_routes && kvm_max_routes <= KVM_MAX_IRQ_ROUTES);
+
+ routing = kvm_gsi_routing_create();
+ for (i = intid; i < (uint64_t)intid + num; i++)
+ kvm_gsi_routing_irqchip_add(routing, i - MIN_SPI, i - MIN_SPI);
+
+ if (!expect_failure) {
+ kvm_gsi_routing_write(vm, routing);
+ } else {
+ ret = _kvm_gsi_routing_write(vm, routing);
+ /* The kernel only checks for KVM_IRQCHIP_NUM_PINS. */
+ if (intid >= KVM_IRQCHIP_NUM_PINS)
+ TEST_ASSERT(ret != 0 && errno == EINVAL,
+ "Bad intid %u did not cause KVM_SET_GSI_ROUTING "
+ "error: rc: %i errno: %i", intid, ret, errno);
+ else
+ TEST_ASSERT(ret == 0, "KVM_SET_GSI_ROUTING "
+ "for intid %i failed, rc: %i errno: %i",
+ intid, ret, errno);
+ }
+}
+
+static void kvm_irq_write_ispendr_check(int gic_fd, uint32_t intid,
+ uint32_t vcpu, bool expect_failure)
+{
+ /*
+ * Ignore this when expecting failure as invalid intids will lead to
+ * either trying to inject SGIs when we configured the test to be
+ * level_sensitive (or the reverse), or inject large intids which
+ * will lead to writing above the ISPENDR register space (and we
+ * don't want to do that either).
+ */
+ if (!expect_failure)
+ kvm_irq_write_ispendr(gic_fd, intid, vcpu);
+}
+
+static void kvm_routing_and_irqfd_check(struct kvm_vm *vm,
+ uint32_t intid, uint32_t num, uint32_t kvm_max_routes,
+ bool expect_failure)
+{
+ int fd[MAX_SPI];
+ uint64_t val;
+ int ret, f;
+ uint64_t i;
+
+ /*
+ * There is no way to try injecting an SGI or PPI as the interface
+ * starts counting from the first SPI (above the private ones), so just
+ * exit.
+ */
+ if (INTID_IS_SGI(intid) || INTID_IS_PPI(intid))
+ return;
+
+ kvm_set_gsi_routing_irqchip_check(vm, intid, num,
+ kvm_max_routes, expect_failure);
+
+ /*
+ * If expect_failure, then just to inject anyway. These
+ * will silently fail. And in any case, the guest will check
+ * that no actual interrupt was injected for those cases.
+ */
+
+ for (f = 0, i = intid; i < (uint64_t)intid + num; i++, f++) {
+ fd[f] = eventfd(0, 0);
+ TEST_ASSERT(fd[f] != -1,
+ "eventfd failed, errno: %i\n", errno);
+ }
+
+ for (f = 0, i = intid; i < (uint64_t)intid + num; i++, f++) {
+ struct kvm_irqfd irqfd = {
+ .fd = fd[f],
+ .gsi = i - MIN_SPI,
+ };
+ assert(i <= (uint64_t)UINT_MAX);
+ vm_ioctl(vm, KVM_IRQFD, &irqfd);
+ }
+
+ for (f = 0, i = intid; i < (uint64_t)intid + num; i++, f++) {
+ val = 1;
+ ret = write(fd[f], &val, sizeof(uint64_t));
+ TEST_ASSERT(ret == sizeof(uint64_t),
+ "Write to KVM_IRQFD failed with ret: %d\n", ret);
+ }
+
+ for (f = 0, i = intid; i < (uint64_t)intid + num; i++, f++)
+ close(fd[f]);
+}
+
+/* handles the valid case: intid=0xffffffff num=1 */
+#define for_each_intid(first, num, tmp, i) \
+ for ((tmp) = (i) = (first); \
+ (tmp) < (uint64_t)(first) + (uint64_t)(num); \
+ (tmp)++, (i)++)
+
+static void run_guest_cmd(struct kvm_vm *vm, int gic_fd,
+ struct kvm_inject_args *inject_args,
+ struct test_args *test_args)
+{
+ kvm_inject_cmd cmd = inject_args->cmd;
+ uint32_t intid = inject_args->first_intid;
+ uint32_t num = inject_args->num;
+ int level = inject_args->level;
+ bool expect_failure = inject_args->expect_failure;
+ uint64_t tmp;
+ uint32_t i;
+
+ /* handles the valid case: intid=0xffffffff num=1 */
+ assert(intid < UINT_MAX - num || num == 1);
+
+ switch (cmd) {
+ case KVM_INJECT_EDGE_IRQ_LINE:
+ for_each_intid(intid, num, tmp, i)
+ kvm_irq_line_check(vm, i, 1, test_args,
+ expect_failure);
+ for_each_intid(intid, num, tmp, i)
+ kvm_irq_line_check(vm, i, 0, test_args,
+ expect_failure);
+ break;
+ case KVM_SET_IRQ_LINE:
+ for_each_intid(intid, num, tmp, i)
+ kvm_irq_line_check(vm, i, level, test_args,
+ expect_failure);
+ break;
+ case KVM_SET_IRQ_LINE_HIGH:
+ for_each_intid(intid, num, tmp, i)
+ kvm_irq_line_check(vm, i, 1, test_args,
+ expect_failure);
+ break;
+ case KVM_SET_LEVEL_INFO_HIGH:
+ for_each_intid(intid, num, tmp, i)
+ kvm_irq_set_level_info_check(gic_fd, i, 1,
+ expect_failure);
+ break;
+ case KVM_INJECT_IRQFD:
+ kvm_routing_and_irqfd_check(vm, intid, num,
+ test_args->kvm_max_routes,
+ expect_failure);
+ break;
+ case KVM_WRITE_ISPENDR:
+ for (i = intid; i < intid + num; i++)
+ kvm_irq_write_ispendr_check(gic_fd, i,
+ VCPU_ID, expect_failure);
+ break;
+ case KVM_WRITE_ISACTIVER:
+ for (i = intid; i < intid + num; i++)
+ kvm_irq_write_isactiver(gic_fd, i, VCPU_ID);
+ break;
+ default:
+ break;
+ }
+}
+
+static void kvm_inject_get_call(struct kvm_vm *vm, struct ucall *uc,
+ struct kvm_inject_args *args)
+{
+ struct kvm_inject_args *kvm_args_hva;
+ vm_vaddr_t kvm_args_gva;
+
+ kvm_args_gva = uc->args[1];
+ kvm_args_hva = (struct kvm_inject_args *)addr_gva2hva(vm, kvm_args_gva);
+ memcpy(args, kvm_args_hva, sizeof(struct kvm_inject_args));
+}
+
+static void print_args(struct test_args *args)
+{
+ printf("nr-irqs=%d level-sensitive=%d eoi-split=%d\n",
+ args->nr_irqs, args->level_sensitive,
+ args->eoi_split);
+}
+
+static void test_vgic(uint32_t nr_irqs, bool level_sensitive, bool eoi_split)
+{
+ struct ucall uc;
+ int gic_fd;
+ struct kvm_vm *vm;
+ struct kvm_inject_args inject_args;
+
+ struct test_args args = {
+ .nr_irqs = nr_irqs,
+ .level_sensitive = level_sensitive,
+ .eoi_split = eoi_split,
+ .kvm_max_routes = kvm_check_cap(KVM_CAP_IRQ_ROUTING),
+ .kvm_supports_irqfd = kvm_check_cap(KVM_CAP_IRQFD),
+ };
+
+ print_args(&args);
+
+ vm = vm_create_default(VCPU_ID, 0, guest_code);
+ ucall_init(vm, NULL);
+
+ vm_init_descriptor_tables(vm);
+ vcpu_init_descriptor_tables(vm, VCPU_ID);
+
+ /* Setup the guest args page (so it gets the args). */
+ vcpu_args_set(vm, 0, 1, args);
+
+ gic_fd = vgic_v3_setup(vm, 1, nr_irqs,
+ GICD_BASE_GPA, GICR_BASE_GPA);
+ if (gic_fd < 0) {
+ print_skip("Failed to create vgic-v3, skipping");
+ exit(KSFT_SKIP);
+ }
+
+ vm_install_exception_handler(vm, VECTOR_IRQ_CURRENT,
+ guest_irq_handlers[args.eoi_split][args.level_sensitive]);
+
+ while (1) {
+ vcpu_run(vm, VCPU_ID);
+
+ switch (get_ucall(vm, VCPU_ID, &uc)) {
+ case UCALL_SYNC:
+ kvm_inject_get_call(vm, &uc, &inject_args);
+ run_guest_cmd(vm, gic_fd, &inject_args, &args);
+ break;
+ case UCALL_ABORT:
+ TEST_FAIL("%s at %s:%ld\n\tvalues: %#lx, %#lx",
+ (const char *)uc.args[0],
+ __FILE__, uc.args[1], uc.args[2], uc.args[3]);
+ break;
+ case UCALL_DONE:
+ goto done;
+ default:
+ TEST_FAIL("Unknown ucall %lu", uc.cmd);
+ }
+ }
+
+done:
+ close(gic_fd);
+ kvm_vm_free(vm);
+}
+
+static void help(const char *name)
+{
+ printf(
+ "\n"
+ "usage: %s [-n num_irqs] [-e eoi_split] [-l level_sensitive]\n", name);
+ printf(" -n: specify number of IRQs to setup the vgic with. "
+ "It has to be a multiple of 32 and between 64 and 1024.\n");
+ printf(" -e: if 1 then EOI is split into a write to DIR on top "
+ "of writing EOI.\n");
+ printf(" -l: specify whether the IRQs are level-sensitive (1) or not (0).");
+ puts("");
+ exit(1);
+}
+
+int main(int argc, char **argv)
+{
+ uint32_t nr_irqs = 64;
+ bool default_args = true;
+ bool level_sensitive = false;
+ int opt;
+ bool eoi_split = false;
+
+ /* Tell stdout not to buffer its content */
+ setbuf(stdout, NULL);
+
+ while ((opt = getopt(argc, argv, "hn:e:l:")) != -1) {
+ switch (opt) {
+ case 'n':
+ nr_irqs = atoi(optarg);
+ if (nr_irqs > 1024 || nr_irqs % 32)
+ help(argv[0]);
+ break;
+ case 'e':
+ eoi_split = (bool)atoi(optarg);
+ default_args = false;
+ break;
+ case 'l':
+ level_sensitive = (bool)atoi(optarg);
+ default_args = false;
+ break;
+ case 'h':
+ default:
+ help(argv[0]);
+ break;
+ }
+ }
+
+ /* If the user just specified nr_irqs and/or gic_version, then run all
+ * combinations.
+ */
+ if (default_args) {
+ test_vgic(nr_irqs, false /* level */, false /* eoi_split */);
+ test_vgic(nr_irqs, false /* level */, true /* eoi_split */);
+ test_vgic(nr_irqs, true /* level */, false /* eoi_split */);
+ test_vgic(nr_irqs, true /* level */, true /* eoi_split */);
+ } else {
+ test_vgic(nr_irqs, level_sensitive, eoi_split);
+ }
+
+ return 0;
+}
diff --git a/tools/testing/selftests/kvm/include/aarch64/gic.h b/tools/testing/selftests/kvm/include/aarch64/gic.h
index 85dd1e53048e..b217ea17cac5 100644
--- a/tools/testing/selftests/kvm/include/aarch64/gic.h
+++ b/tools/testing/selftests/kvm/include/aarch64/gic.h
@@ -11,11 +11,37 @@ enum gic_type {
GIC_TYPE_MAX,
};
+#define MIN_SGI 0
+#define MIN_PPI 16
+#define MIN_SPI 32
+#define MAX_SPI 1019
+#define IAR_SPURIOUS 1023
+
+#define INTID_IS_SGI(intid) (0 <= (intid) && (intid) < MIN_PPI)
+#define INTID_IS_PPI(intid) (MIN_PPI <= (intid) && (intid) < MIN_SPI)
+#define INTID_IS_SPI(intid) (MIN_SPI <= (intid) && (intid) <= MAX_SPI)
+
void gic_init(enum gic_type type, unsigned int nr_cpus,
void *dist_base, void *redist_base);
void gic_irq_enable(unsigned int intid);
void gic_irq_disable(unsigned int intid);
unsigned int gic_get_and_ack_irq(void);
void gic_set_eoi(unsigned int intid);
+void gic_set_dir(unsigned int intid);
+
+/*
+ * Sets the EOI mode. When split is false, EOI just drops the priority. When
+ * split is true, EOI drops the priority and deactivates the interrupt.
+ */
+void gic_set_eoi_split(bool split);
+void gic_set_priority_mask(uint64_t mask);
+void gic_set_priority(uint32_t intid, uint32_t prio);
+void gic_irq_set_active(unsigned int intid);
+void gic_irq_clear_active(unsigned int intid);
+bool gic_irq_get_active(unsigned int intid);
+void gic_irq_set_pending(unsigned int intid);
+void gic_irq_clear_pending(unsigned int intid);
+bool gic_irq_get_pending(unsigned int intid);
+void gic_irq_set_config(unsigned int intid, bool is_edge);
#endif /* SELFTEST_KVM_GIC_H */
diff --git a/tools/testing/selftests/kvm/lib/aarch64/gic_v3.h b/tools/testing/selftests/kvm/include/aarch64/gic_v3.h
index b51536d469a6..ba0886e8a2bb 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/gic_v3.h
+++ b/tools/testing/selftests/kvm/include/aarch64/gic_v3.h
@@ -16,8 +16,12 @@
#define GICD_IGROUPR 0x0080
#define GICD_ISENABLER 0x0100
#define GICD_ICENABLER 0x0180
+#define GICD_ISPENDR 0x0200
+#define GICD_ICPENDR 0x0280
#define GICD_ICACTIVER 0x0380
+#define GICD_ISACTIVER 0x0300
#define GICD_IPRIORITYR 0x0400
+#define GICD_ICFGR 0x0C00
/*
* The assumption is that the guest runs in a non-secure mode.
@@ -49,16 +53,24 @@
#define GICR_IGROUPR0 GICD_IGROUPR
#define GICR_ISENABLER0 GICD_ISENABLER
#define GICR_ICENABLER0 GICD_ICENABLER
+#define GICR_ISPENDR0 GICD_ISPENDR
+#define GICR_ISACTIVER0 GICD_ISACTIVER
#define GICR_ICACTIVER0 GICD_ICACTIVER
+#define GICR_ICENABLER GICD_ICENABLER
+#define GICR_ICACTIVER GICD_ICACTIVER
#define GICR_IPRIORITYR0 GICD_IPRIORITYR
/* CPU interface registers */
#define SYS_ICC_PMR_EL1 sys_reg(3, 0, 4, 6, 0)
#define SYS_ICC_IAR1_EL1 sys_reg(3, 0, 12, 12, 0)
#define SYS_ICC_EOIR1_EL1 sys_reg(3, 0, 12, 12, 1)
+#define SYS_ICC_DIR_EL1 sys_reg(3, 0, 12, 11, 1)
+#define SYS_ICC_CTLR_EL1 sys_reg(3, 0, 12, 12, 4)
#define SYS_ICC_SRE_EL1 sys_reg(3, 0, 12, 12, 5)
#define SYS_ICC_GRPEN1_EL1 sys_reg(3, 0, 12, 12, 7)
+#define SYS_ICV_AP1R0_EL1 sys_reg(3, 0, 12, 9, 0)
+
#define ICC_PMR_DEF_PRIO 0xf0
#define ICC_SRE_EL1_SRE (1U << 0)
diff --git a/tools/testing/selftests/kvm/include/aarch64/processor.h b/tools/testing/selftests/kvm/include/aarch64/processor.h
index 27d8e1bb5b36..8f9f46979a00 100644
--- a/tools/testing/selftests/kvm/include/aarch64/processor.h
+++ b/tools/testing/selftests/kvm/include/aarch64/processor.h
@@ -113,6 +113,9 @@ enum {
#define ESR_EC_WP_CURRENT 0x35
#define ESR_EC_BRK_INS 0x3c
+void aarch64_get_supported_page_sizes(uint32_t ipa,
+ bool *ps4k, bool *ps16k, bool *ps64k);
+
void vm_init_descriptor_tables(struct kvm_vm *vm);
void vcpu_init_descriptor_tables(struct kvm_vm *vm, uint32_t vcpuid);
diff --git a/tools/testing/selftests/kvm/include/aarch64/vgic.h b/tools/testing/selftests/kvm/include/aarch64/vgic.h
index 0ecfb253893c..4442081221a0 100644
--- a/tools/testing/selftests/kvm/include/aarch64/vgic.h
+++ b/tools/testing/selftests/kvm/include/aarch64/vgic.h
@@ -14,7 +14,21 @@
((uint64_t)(flags) << 12) | \
index)
-int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus,
+int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, uint32_t nr_irqs,
uint64_t gicd_base_gpa, uint64_t gicr_base_gpa);
-#endif /* SELFTEST_KVM_VGIC_H */
+#define VGIC_MAX_RESERVED 1023
+
+void kvm_irq_set_level_info(int gic_fd, uint32_t intid, int level);
+int _kvm_irq_set_level_info(int gic_fd, uint32_t intid, int level);
+
+void kvm_arm_irq_line(struct kvm_vm *vm, uint32_t intid, int level);
+int _kvm_arm_irq_line(struct kvm_vm *vm, uint32_t intid, int level);
+
+/* The vcpu arg only applies to private interrupts. */
+void kvm_irq_write_ispendr(int gic_fd, uint32_t intid, uint32_t vcpu);
+void kvm_irq_write_isactiver(int gic_fd, uint32_t intid, uint32_t vcpu);
+
+#define KVM_IRQCHIP_NUM_PINS (1020 - 32)
+
+#endif // SELFTEST_KVM_VGIC_H
diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index 2d62edc49d67..c9286811a4cb 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -7,412 +7,7 @@
#ifndef SELFTEST_KVM_UTIL_H
#define SELFTEST_KVM_UTIL_H
-#include "test_util.h"
-
-#include "asm/kvm.h"
-#include "linux/list.h"
-#include "linux/kvm.h"
-#include <sys/ioctl.h>
-
-#include "sparsebit.h"
-
-#define KVM_DEV_PATH "/dev/kvm"
-#define KVM_MAX_VCPUS 512
-
-#define NSEC_PER_SEC 1000000000L
-
-/*
- * Callers of kvm_util only have an incomplete/opaque description of the
- * structure kvm_util is using to maintain the state of a VM.
- */
-struct kvm_vm;
-
-typedef uint64_t vm_paddr_t; /* Virtual Machine (Guest) physical address */
-typedef uint64_t vm_vaddr_t; /* Virtual Machine (Guest) virtual address */
-
-/* Minimum allocated guest virtual and physical addresses */
-#define KVM_UTIL_MIN_VADDR 0x2000
-#define KVM_GUEST_PAGE_TABLE_MIN_PADDR 0x180000
-
-#define DEFAULT_GUEST_PHY_PAGES 512
-#define DEFAULT_GUEST_STACK_VADDR_MIN 0xab6000
-#define DEFAULT_STACK_PGS 5
-
-enum vm_guest_mode {
- VM_MODE_P52V48_4K,
- VM_MODE_P52V48_64K,
- VM_MODE_P48V48_4K,
- VM_MODE_P48V48_64K,
- VM_MODE_P40V48_4K,
- VM_MODE_P40V48_64K,
- VM_MODE_PXXV48_4K, /* For 48bits VA but ANY bits PA */
- VM_MODE_P47V64_4K,
- VM_MODE_P44V64_4K,
- NUM_VM_MODES,
-};
-
-#if defined(__aarch64__)
-
-#define VM_MODE_DEFAULT VM_MODE_P40V48_4K
-#define MIN_PAGE_SHIFT 12U
-#define ptes_per_page(page_size) ((page_size) / 8)
-
-#elif defined(__x86_64__)
-
-#define VM_MODE_DEFAULT VM_MODE_PXXV48_4K
-#define MIN_PAGE_SHIFT 12U
-#define ptes_per_page(page_size) ((page_size) / 8)
-
-#elif defined(__s390x__)
-
-#define VM_MODE_DEFAULT VM_MODE_P44V64_4K
-#define MIN_PAGE_SHIFT 12U
-#define ptes_per_page(page_size) ((page_size) / 16)
-
-#endif
-
-#define MIN_PAGE_SIZE (1U << MIN_PAGE_SHIFT)
-#define PTES_PER_MIN_PAGE ptes_per_page(MIN_PAGE_SIZE)
-
-struct vm_guest_mode_params {
- unsigned int pa_bits;
- unsigned int va_bits;
- unsigned int page_size;
- unsigned int page_shift;
-};
-extern const struct vm_guest_mode_params vm_guest_mode_params[];
-
-int open_path_or_exit(const char *path, int flags);
-int open_kvm_dev_path_or_exit(void);
-int kvm_check_cap(long cap);
-int vm_enable_cap(struct kvm_vm *vm, struct kvm_enable_cap *cap);
-int vcpu_enable_cap(struct kvm_vm *vm, uint32_t vcpu_id,
- struct kvm_enable_cap *cap);
-void vm_enable_dirty_ring(struct kvm_vm *vm, uint32_t ring_size);
-const char *vm_guest_mode_string(uint32_t i);
-
-struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm);
-void kvm_vm_free(struct kvm_vm *vmp);
-void kvm_vm_restart(struct kvm_vm *vmp, int perm);
-void kvm_vm_release(struct kvm_vm *vmp);
-void kvm_vm_get_dirty_log(struct kvm_vm *vm, int slot, void *log);
-void kvm_vm_clear_dirty_log(struct kvm_vm *vm, int slot, void *log,
- uint64_t first_page, uint32_t num_pages);
-uint32_t kvm_vm_reset_dirty_ring(struct kvm_vm *vm);
-
-int kvm_memcmp_hva_gva(void *hva, struct kvm_vm *vm, const vm_vaddr_t gva,
- size_t len);
-
-void kvm_vm_elf_load(struct kvm_vm *vm, const char *filename);
-
-void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent);
-
-/*
- * VM VCPU Dump
- *
- * Input Args:
- * stream - Output FILE stream
- * vm - Virtual Machine
- * vcpuid - VCPU ID
- * indent - Left margin indent amount
- *
- * Output Args: None
- *
- * Return: None
- *
- * Dumps the current state of the VCPU specified by @vcpuid, within the VM
- * given by @vm, to the FILE stream given by @stream.
- */
-void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid,
- uint8_t indent);
-
-void vm_create_irqchip(struct kvm_vm *vm);
-
-void vm_userspace_mem_region_add(struct kvm_vm *vm,
- enum vm_mem_backing_src_type src_type,
- uint64_t guest_paddr, uint32_t slot, uint64_t npages,
- uint32_t flags);
-
-void vcpu_ioctl(struct kvm_vm *vm, uint32_t vcpuid, unsigned long ioctl,
- void *arg);
-int _vcpu_ioctl(struct kvm_vm *vm, uint32_t vcpuid, unsigned long ioctl,
- void *arg);
-void vm_ioctl(struct kvm_vm *vm, unsigned long ioctl, void *arg);
-int _vm_ioctl(struct kvm_vm *vm, unsigned long cmd, void *arg);
-void kvm_ioctl(struct kvm_vm *vm, unsigned long ioctl, void *arg);
-int _kvm_ioctl(struct kvm_vm *vm, unsigned long ioctl, void *arg);
-void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags);
-void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa);
-void vm_mem_region_delete(struct kvm_vm *vm, uint32_t slot);
-void vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpuid);
-vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min);
-vm_vaddr_t vm_vaddr_alloc_pages(struct kvm_vm *vm, int nr_pages);
-vm_vaddr_t vm_vaddr_alloc_page(struct kvm_vm *vm);
-
-void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
- unsigned int npages);
-void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa);
-void *addr_gva2hva(struct kvm_vm *vm, vm_vaddr_t gva);
-vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva);
-void *addr_gpa2alias(struct kvm_vm *vm, vm_paddr_t gpa);
-
-/*
- * Address Guest Virtual to Guest Physical
- *
- * Input Args:
- * vm - Virtual Machine
- * gva - VM virtual address
- *
- * Output Args: None
- *
- * Return:
- * Equivalent VM physical address
- *
- * Returns the VM physical address of the translated VM virtual
- * address given by @gva.
- */
-vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva);
-
-struct kvm_run *vcpu_state(struct kvm_vm *vm, uint32_t vcpuid);
-void vcpu_run(struct kvm_vm *vm, uint32_t vcpuid);
-int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid);
-int vcpu_get_fd(struct kvm_vm *vm, uint32_t vcpuid);
-void vcpu_run_complete_io(struct kvm_vm *vm, uint32_t vcpuid);
-void vcpu_set_guest_debug(struct kvm_vm *vm, uint32_t vcpuid,
- struct kvm_guest_debug *debug);
-void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid,
- struct kvm_mp_state *mp_state);
-struct kvm_reg_list *vcpu_get_reg_list(struct kvm_vm *vm, uint32_t vcpuid);
-void vcpu_regs_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs);
-void vcpu_regs_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs);
-
-/*
- * VM VCPU Args Set
- *
- * Input Args:
- * vm - Virtual Machine
- * vcpuid - VCPU ID
- * num - number of arguments
- * ... - arguments, each of type uint64_t
- *
- * Output Args: None
- *
- * Return: None
- *
- * Sets the first @num function input registers of the VCPU with @vcpuid,
- * per the C calling convention of the architecture, to the values given
- * as variable args. Each of the variable args is expected to be of type
- * uint64_t. The maximum @num can be is specific to the architecture.
- */
-void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...);
-
-void vcpu_sregs_get(struct kvm_vm *vm, uint32_t vcpuid,
- struct kvm_sregs *sregs);
-void vcpu_sregs_set(struct kvm_vm *vm, uint32_t vcpuid,
- struct kvm_sregs *sregs);
-int _vcpu_sregs_set(struct kvm_vm *vm, uint32_t vcpuid,
- struct kvm_sregs *sregs);
-void vcpu_fpu_get(struct kvm_vm *vm, uint32_t vcpuid,
- struct kvm_fpu *fpu);
-void vcpu_fpu_set(struct kvm_vm *vm, uint32_t vcpuid,
- struct kvm_fpu *fpu);
-void vcpu_get_reg(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_one_reg *reg);
-void vcpu_set_reg(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_one_reg *reg);
-#ifdef __KVM_HAVE_VCPU_EVENTS
-void vcpu_events_get(struct kvm_vm *vm, uint32_t vcpuid,
- struct kvm_vcpu_events *events);
-void vcpu_events_set(struct kvm_vm *vm, uint32_t vcpuid,
- struct kvm_vcpu_events *events);
-#endif
-#ifdef __x86_64__
-void vcpu_nested_state_get(struct kvm_vm *vm, uint32_t vcpuid,
- struct kvm_nested_state *state);
-int vcpu_nested_state_set(struct kvm_vm *vm, uint32_t vcpuid,
- struct kvm_nested_state *state, bool ignore_error);
-#endif
-void *vcpu_map_dirty_ring(struct kvm_vm *vm, uint32_t vcpuid);
-
-int _kvm_device_check_attr(int dev_fd, uint32_t group, uint64_t attr);
-int kvm_device_check_attr(int dev_fd, uint32_t group, uint64_t attr);
-int _kvm_create_device(struct kvm_vm *vm, uint64_t type, bool test, int *fd);
-int kvm_create_device(struct kvm_vm *vm, uint64_t type, bool test);
-int _kvm_device_access(int dev_fd, uint32_t group, uint64_t attr,
- void *val, bool write);
-int kvm_device_access(int dev_fd, uint32_t group, uint64_t attr,
- void *val, bool write);
-
-int _vcpu_has_device_attr(struct kvm_vm *vm, uint32_t vcpuid, uint32_t group,
- uint64_t attr);
-int vcpu_has_device_attr(struct kvm_vm *vm, uint32_t vcpuid, uint32_t group,
- uint64_t attr);
-int _vcpu_access_device_attr(struct kvm_vm *vm, uint32_t vcpuid, uint32_t group,
- uint64_t attr, void *val, bool write);
-int vcpu_access_device_attr(struct kvm_vm *vm, uint32_t vcpuid, uint32_t group,
- uint64_t attr, void *val, bool write);
-
-const char *exit_reason_str(unsigned int exit_reason);
-
-void virt_pgd_alloc(struct kvm_vm *vm);
-
-/*
- * VM Virtual Page Map
- *
- * Input Args:
- * vm - Virtual Machine
- * vaddr - VM Virtual Address
- * paddr - VM Physical Address
- * memslot - Memory region slot for new virtual translation tables
- *
- * Output Args: None
- *
- * Return: None
- *
- * Within @vm, creates a virtual translation for the page starting
- * at @vaddr to the page starting at @paddr.
- */
-void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr);
-
-vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm, vm_paddr_t paddr_min,
- uint32_t memslot);
-vm_paddr_t vm_phy_pages_alloc(struct kvm_vm *vm, size_t num,
- vm_paddr_t paddr_min, uint32_t memslot);
-vm_paddr_t vm_alloc_page_table(struct kvm_vm *vm);
-
-/*
- * Create a VM with reasonable defaults
- *
- * Input Args:
- * vcpuid - The id of the single VCPU to add to the VM.
- * extra_mem_pages - The number of extra pages to add (this will
- * decide how much extra space we will need to
- * setup the page tables using memslot 0)
- * guest_code - The vCPU's entry point
- *
- * Output Args: None
- *
- * Return:
- * Pointer to opaque structure that describes the created VM.
- */
-struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages,
- void *guest_code);
-
-/* Same as vm_create_default, but can be used for more than one vcpu */
-struct kvm_vm *vm_create_default_with_vcpus(uint32_t nr_vcpus, uint64_t extra_mem_pages,
- uint32_t num_percpu_pages, void *guest_code,
- uint32_t vcpuids[]);
-
-/* Like vm_create_default_with_vcpus, but accepts mode and slot0 memory as a parameter */
-struct kvm_vm *vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus,
- uint64_t slot0_mem_pages, uint64_t extra_mem_pages,
- uint32_t num_percpu_pages, void *guest_code,
- uint32_t vcpuids[]);
-
-/*
- * Adds a vCPU with reasonable defaults (e.g. a stack)
- *
- * Input Args:
- * vm - Virtual Machine
- * vcpuid - The id of the VCPU to add to the VM.
- * guest_code - The vCPU's entry point
- */
-void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code);
-
-bool vm_is_unrestricted_guest(struct kvm_vm *vm);
-
-unsigned int vm_get_page_size(struct kvm_vm *vm);
-unsigned int vm_get_page_shift(struct kvm_vm *vm);
-unsigned long vm_compute_max_gfn(struct kvm_vm *vm);
-uint64_t vm_get_max_gfn(struct kvm_vm *vm);
-int vm_get_fd(struct kvm_vm *vm);
-
-unsigned int vm_calc_num_guest_pages(enum vm_guest_mode mode, size_t size);
-unsigned int vm_num_host_pages(enum vm_guest_mode mode, unsigned int num_guest_pages);
-unsigned int vm_num_guest_pages(enum vm_guest_mode mode, unsigned int num_host_pages);
-static inline unsigned int
-vm_adjust_num_guest_pages(enum vm_guest_mode mode, unsigned int num_guest_pages)
-{
- unsigned int n;
- n = vm_num_guest_pages(mode, vm_num_host_pages(mode, num_guest_pages));
-#ifdef __s390x__
- /* s390 requires 1M aligned guest sizes */
- n = (n + 255) & ~255;
-#endif
- return n;
-}
-
-struct kvm_userspace_memory_region *
-kvm_userspace_memory_region_find(struct kvm_vm *vm, uint64_t start,
- uint64_t end);
-
-struct kvm_dirty_log *
-allocate_kvm_dirty_log(struct kvm_userspace_memory_region *region);
-
-int vm_create_device(struct kvm_vm *vm, struct kvm_create_device *cd);
-
-#define sync_global_to_guest(vm, g) ({ \
- typeof(g) *_p = addr_gva2hva(vm, (vm_vaddr_t)&(g)); \
- memcpy(_p, &(g), sizeof(g)); \
-})
-
-#define sync_global_from_guest(vm, g) ({ \
- typeof(g) *_p = addr_gva2hva(vm, (vm_vaddr_t)&(g)); \
- memcpy(&(g), _p, sizeof(g)); \
-})
-
-void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid);
-
-/* Common ucalls */
-enum {
- UCALL_NONE,
- UCALL_SYNC,
- UCALL_ABORT,
- UCALL_DONE,
- UCALL_UNHANDLED,
-};
-
-#define UCALL_MAX_ARGS 6
-
-struct ucall {
- uint64_t cmd;
- uint64_t args[UCALL_MAX_ARGS];
-};
-
-void ucall_init(struct kvm_vm *vm, void *arg);
-void ucall_uninit(struct kvm_vm *vm);
-void ucall(uint64_t cmd, int nargs, ...);
-uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc);
-
-#define GUEST_SYNC_ARGS(stage, arg1, arg2, arg3, arg4) \
- ucall(UCALL_SYNC, 6, "hello", stage, arg1, arg2, arg3, arg4)
-#define GUEST_SYNC(stage) ucall(UCALL_SYNC, 2, "hello", stage)
-#define GUEST_DONE() ucall(UCALL_DONE, 0)
-#define __GUEST_ASSERT(_condition, _condstr, _nargs, _args...) do { \
- if (!(_condition)) \
- ucall(UCALL_ABORT, 2 + _nargs, \
- "Failed guest assert: " \
- _condstr, __LINE__, _args); \
-} while (0)
-
-#define GUEST_ASSERT(_condition) \
- __GUEST_ASSERT(_condition, #_condition, 0, 0)
-
-#define GUEST_ASSERT_1(_condition, arg1) \
- __GUEST_ASSERT(_condition, #_condition, 1, (arg1))
-
-#define GUEST_ASSERT_2(_condition, arg1, arg2) \
- __GUEST_ASSERT(_condition, #_condition, 2, (arg1), (arg2))
-
-#define GUEST_ASSERT_3(_condition, arg1, arg2, arg3) \
- __GUEST_ASSERT(_condition, #_condition, 3, (arg1), (arg2), (arg3))
-
-#define GUEST_ASSERT_4(_condition, arg1, arg2, arg3, arg4) \
- __GUEST_ASSERT(_condition, #_condition, 4, (arg1), (arg2), (arg3), (arg4))
-
-#define GUEST_ASSERT_EQ(a, b) __GUEST_ASSERT((a) == (b), #a " == " #b, 2, a, b)
-
-int vm_get_stats_fd(struct kvm_vm *vm);
-int vcpu_get_stats_fd(struct kvm_vm *vm, uint32_t vcpuid);
-
-uint32_t guest_get_vcpuid(void);
+#include "kvm_util_base.h"
+#include "ucall_common.h"
#endif /* SELFTEST_KVM_UTIL_H */
diff --git a/tools/testing/selftests/kvm/include/kvm_util_base.h b/tools/testing/selftests/kvm/include/kvm_util_base.h
new file mode 100644
index 000000000000..4ed6aa049a91
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/kvm_util_base.h
@@ -0,0 +1,398 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * tools/testing/selftests/kvm/include/kvm_util_base.h
+ *
+ * Copyright (C) 2018, Google LLC.
+ */
+#ifndef SELFTEST_KVM_UTIL_BASE_H
+#define SELFTEST_KVM_UTIL_BASE_H
+
+#include "test_util.h"
+
+#include "asm/kvm.h"
+#include "linux/list.h"
+#include "linux/kvm.h"
+#include <sys/ioctl.h>
+
+#include "sparsebit.h"
+
+#define KVM_DEV_PATH "/dev/kvm"
+#define KVM_MAX_VCPUS 512
+
+#define NSEC_PER_SEC 1000000000L
+
+/*
+ * Callers of kvm_util only have an incomplete/opaque description of the
+ * structure kvm_util is using to maintain the state of a VM.
+ */
+struct kvm_vm;
+
+typedef uint64_t vm_paddr_t; /* Virtual Machine (Guest) physical address */
+typedef uint64_t vm_vaddr_t; /* Virtual Machine (Guest) virtual address */
+
+/* Minimum allocated guest virtual and physical addresses */
+#define KVM_UTIL_MIN_VADDR 0x2000
+#define KVM_GUEST_PAGE_TABLE_MIN_PADDR 0x180000
+
+#define DEFAULT_GUEST_PHY_PAGES 512
+#define DEFAULT_GUEST_STACK_VADDR_MIN 0xab6000
+#define DEFAULT_STACK_PGS 5
+
+enum vm_guest_mode {
+ VM_MODE_P52V48_4K,
+ VM_MODE_P52V48_64K,
+ VM_MODE_P48V48_4K,
+ VM_MODE_P48V48_16K,
+ VM_MODE_P48V48_64K,
+ VM_MODE_P40V48_4K,
+ VM_MODE_P40V48_16K,
+ VM_MODE_P40V48_64K,
+ VM_MODE_PXXV48_4K, /* For 48bits VA but ANY bits PA */
+ VM_MODE_P47V64_4K,
+ VM_MODE_P44V64_4K,
+ VM_MODE_P36V48_4K,
+ VM_MODE_P36V48_16K,
+ VM_MODE_P36V48_64K,
+ VM_MODE_P36V47_16K,
+ NUM_VM_MODES,
+};
+
+#if defined(__aarch64__)
+
+extern enum vm_guest_mode vm_mode_default;
+
+#define VM_MODE_DEFAULT vm_mode_default
+#define MIN_PAGE_SHIFT 12U
+#define ptes_per_page(page_size) ((page_size) / 8)
+
+#elif defined(__x86_64__)
+
+#define VM_MODE_DEFAULT VM_MODE_PXXV48_4K
+#define MIN_PAGE_SHIFT 12U
+#define ptes_per_page(page_size) ((page_size) / 8)
+
+#elif defined(__s390x__)
+
+#define VM_MODE_DEFAULT VM_MODE_P44V64_4K
+#define MIN_PAGE_SHIFT 12U
+#define ptes_per_page(page_size) ((page_size) / 16)
+
+#elif defined(__riscv)
+
+#if __riscv_xlen == 32
+#error "RISC-V 32-bit kvm selftests not supported"
+#endif
+
+#define VM_MODE_DEFAULT VM_MODE_P40V48_4K
+#define MIN_PAGE_SHIFT 12U
+#define ptes_per_page(page_size) ((page_size) / 8)
+
+#endif
+
+#define MIN_PAGE_SIZE (1U << MIN_PAGE_SHIFT)
+#define PTES_PER_MIN_PAGE ptes_per_page(MIN_PAGE_SIZE)
+
+struct vm_guest_mode_params {
+ unsigned int pa_bits;
+ unsigned int va_bits;
+ unsigned int page_size;
+ unsigned int page_shift;
+};
+extern const struct vm_guest_mode_params vm_guest_mode_params[];
+
+int open_path_or_exit(const char *path, int flags);
+int open_kvm_dev_path_or_exit(void);
+int kvm_check_cap(long cap);
+int vm_check_cap(struct kvm_vm *vm, long cap);
+int vm_enable_cap(struct kvm_vm *vm, struct kvm_enable_cap *cap);
+int vcpu_enable_cap(struct kvm_vm *vm, uint32_t vcpu_id,
+ struct kvm_enable_cap *cap);
+void vm_enable_dirty_ring(struct kvm_vm *vm, uint32_t ring_size);
+const char *vm_guest_mode_string(uint32_t i);
+
+struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm);
+void kvm_vm_free(struct kvm_vm *vmp);
+void kvm_vm_restart(struct kvm_vm *vmp, int perm);
+void kvm_vm_release(struct kvm_vm *vmp);
+void kvm_vm_get_dirty_log(struct kvm_vm *vm, int slot, void *log);
+void kvm_vm_clear_dirty_log(struct kvm_vm *vm, int slot, void *log,
+ uint64_t first_page, uint32_t num_pages);
+uint32_t kvm_vm_reset_dirty_ring(struct kvm_vm *vm);
+
+int kvm_memcmp_hva_gva(void *hva, struct kvm_vm *vm, const vm_vaddr_t gva,
+ size_t len);
+
+void kvm_vm_elf_load(struct kvm_vm *vm, const char *filename);
+
+void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent);
+
+/*
+ * VM VCPU Dump
+ *
+ * Input Args:
+ * stream - Output FILE stream
+ * vm - Virtual Machine
+ * vcpuid - VCPU ID
+ * indent - Left margin indent amount
+ *
+ * Output Args: None
+ *
+ * Return: None
+ *
+ * Dumps the current state of the VCPU specified by @vcpuid, within the VM
+ * given by @vm, to the FILE stream given by @stream.
+ */
+void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid,
+ uint8_t indent);
+
+void vm_create_irqchip(struct kvm_vm *vm);
+
+void vm_userspace_mem_region_add(struct kvm_vm *vm,
+ enum vm_mem_backing_src_type src_type,
+ uint64_t guest_paddr, uint32_t slot, uint64_t npages,
+ uint32_t flags);
+
+void vcpu_ioctl(struct kvm_vm *vm, uint32_t vcpuid, unsigned long ioctl,
+ void *arg);
+int _vcpu_ioctl(struct kvm_vm *vm, uint32_t vcpuid, unsigned long ioctl,
+ void *arg);
+void vm_ioctl(struct kvm_vm *vm, unsigned long ioctl, void *arg);
+int _vm_ioctl(struct kvm_vm *vm, unsigned long cmd, void *arg);
+void kvm_ioctl(struct kvm_vm *vm, unsigned long ioctl, void *arg);
+int _kvm_ioctl(struct kvm_vm *vm, unsigned long ioctl, void *arg);
+void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags);
+void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa);
+void vm_mem_region_delete(struct kvm_vm *vm, uint32_t slot);
+void vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpuid);
+vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min);
+vm_vaddr_t vm_vaddr_alloc_pages(struct kvm_vm *vm, int nr_pages);
+vm_vaddr_t vm_vaddr_alloc_page(struct kvm_vm *vm);
+
+void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
+ unsigned int npages);
+void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa);
+void *addr_gva2hva(struct kvm_vm *vm, vm_vaddr_t gva);
+vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva);
+void *addr_gpa2alias(struct kvm_vm *vm, vm_paddr_t gpa);
+
+/*
+ * Address Guest Virtual to Guest Physical
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * gva - VM virtual address
+ *
+ * Output Args: None
+ *
+ * Return:
+ * Equivalent VM physical address
+ *
+ * Returns the VM physical address of the translated VM virtual
+ * address given by @gva.
+ */
+vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva);
+
+struct kvm_run *vcpu_state(struct kvm_vm *vm, uint32_t vcpuid);
+void vcpu_run(struct kvm_vm *vm, uint32_t vcpuid);
+int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid);
+int vcpu_get_fd(struct kvm_vm *vm, uint32_t vcpuid);
+void vcpu_run_complete_io(struct kvm_vm *vm, uint32_t vcpuid);
+void vcpu_set_guest_debug(struct kvm_vm *vm, uint32_t vcpuid,
+ struct kvm_guest_debug *debug);
+void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid,
+ struct kvm_mp_state *mp_state);
+struct kvm_reg_list *vcpu_get_reg_list(struct kvm_vm *vm, uint32_t vcpuid);
+void vcpu_regs_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs);
+void vcpu_regs_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs);
+
+/*
+ * VM VCPU Args Set
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * vcpuid - VCPU ID
+ * num - number of arguments
+ * ... - arguments, each of type uint64_t
+ *
+ * Output Args: None
+ *
+ * Return: None
+ *
+ * Sets the first @num function input registers of the VCPU with @vcpuid,
+ * per the C calling convention of the architecture, to the values given
+ * as variable args. Each of the variable args is expected to be of type
+ * uint64_t. The maximum @num can be is specific to the architecture.
+ */
+void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...);
+
+void vcpu_sregs_get(struct kvm_vm *vm, uint32_t vcpuid,
+ struct kvm_sregs *sregs);
+void vcpu_sregs_set(struct kvm_vm *vm, uint32_t vcpuid,
+ struct kvm_sregs *sregs);
+int _vcpu_sregs_set(struct kvm_vm *vm, uint32_t vcpuid,
+ struct kvm_sregs *sregs);
+void vcpu_fpu_get(struct kvm_vm *vm, uint32_t vcpuid,
+ struct kvm_fpu *fpu);
+void vcpu_fpu_set(struct kvm_vm *vm, uint32_t vcpuid,
+ struct kvm_fpu *fpu);
+void vcpu_get_reg(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_one_reg *reg);
+void vcpu_set_reg(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_one_reg *reg);
+#ifdef __KVM_HAVE_VCPU_EVENTS
+void vcpu_events_get(struct kvm_vm *vm, uint32_t vcpuid,
+ struct kvm_vcpu_events *events);
+void vcpu_events_set(struct kvm_vm *vm, uint32_t vcpuid,
+ struct kvm_vcpu_events *events);
+#endif
+#ifdef __x86_64__
+void vcpu_nested_state_get(struct kvm_vm *vm, uint32_t vcpuid,
+ struct kvm_nested_state *state);
+int vcpu_nested_state_set(struct kvm_vm *vm, uint32_t vcpuid,
+ struct kvm_nested_state *state, bool ignore_error);
+#endif
+void *vcpu_map_dirty_ring(struct kvm_vm *vm, uint32_t vcpuid);
+
+int _kvm_device_check_attr(int dev_fd, uint32_t group, uint64_t attr);
+int kvm_device_check_attr(int dev_fd, uint32_t group, uint64_t attr);
+int _kvm_create_device(struct kvm_vm *vm, uint64_t type, bool test, int *fd);
+int kvm_create_device(struct kvm_vm *vm, uint64_t type, bool test);
+int _kvm_device_access(int dev_fd, uint32_t group, uint64_t attr,
+ void *val, bool write);
+int kvm_device_access(int dev_fd, uint32_t group, uint64_t attr,
+ void *val, bool write);
+void kvm_irq_line(struct kvm_vm *vm, uint32_t irq, int level);
+int _kvm_irq_line(struct kvm_vm *vm, uint32_t irq, int level);
+
+int _vcpu_has_device_attr(struct kvm_vm *vm, uint32_t vcpuid, uint32_t group,
+ uint64_t attr);
+int vcpu_has_device_attr(struct kvm_vm *vm, uint32_t vcpuid, uint32_t group,
+ uint64_t attr);
+int _vcpu_access_device_attr(struct kvm_vm *vm, uint32_t vcpuid, uint32_t group,
+ uint64_t attr, void *val, bool write);
+int vcpu_access_device_attr(struct kvm_vm *vm, uint32_t vcpuid, uint32_t group,
+ uint64_t attr, void *val, bool write);
+
+#define KVM_MAX_IRQ_ROUTES 4096
+
+struct kvm_irq_routing *kvm_gsi_routing_create(void);
+void kvm_gsi_routing_irqchip_add(struct kvm_irq_routing *routing,
+ uint32_t gsi, uint32_t pin);
+int _kvm_gsi_routing_write(struct kvm_vm *vm, struct kvm_irq_routing *routing);
+void kvm_gsi_routing_write(struct kvm_vm *vm, struct kvm_irq_routing *routing);
+
+const char *exit_reason_str(unsigned int exit_reason);
+
+void virt_pgd_alloc(struct kvm_vm *vm);
+
+/*
+ * VM Virtual Page Map
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * vaddr - VM Virtual Address
+ * paddr - VM Physical Address
+ * memslot - Memory region slot for new virtual translation tables
+ *
+ * Output Args: None
+ *
+ * Return: None
+ *
+ * Within @vm, creates a virtual translation for the page starting
+ * at @vaddr to the page starting at @paddr.
+ */
+void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr);
+
+vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm, vm_paddr_t paddr_min,
+ uint32_t memslot);
+vm_paddr_t vm_phy_pages_alloc(struct kvm_vm *vm, size_t num,
+ vm_paddr_t paddr_min, uint32_t memslot);
+vm_paddr_t vm_alloc_page_table(struct kvm_vm *vm);
+
+/*
+ * Create a VM with reasonable defaults
+ *
+ * Input Args:
+ * vcpuid - The id of the single VCPU to add to the VM.
+ * extra_mem_pages - The number of extra pages to add (this will
+ * decide how much extra space we will need to
+ * setup the page tables using memslot 0)
+ * guest_code - The vCPU's entry point
+ *
+ * Output Args: None
+ *
+ * Return:
+ * Pointer to opaque structure that describes the created VM.
+ */
+struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages,
+ void *guest_code);
+
+/* Same as vm_create_default, but can be used for more than one vcpu */
+struct kvm_vm *vm_create_default_with_vcpus(uint32_t nr_vcpus, uint64_t extra_mem_pages,
+ uint32_t num_percpu_pages, void *guest_code,
+ uint32_t vcpuids[]);
+
+/* Like vm_create_default_with_vcpus, but accepts mode and slot0 memory as a parameter */
+struct kvm_vm *vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus,
+ uint64_t slot0_mem_pages, uint64_t extra_mem_pages,
+ uint32_t num_percpu_pages, void *guest_code,
+ uint32_t vcpuids[]);
+
+/*
+ * Adds a vCPU with reasonable defaults (e.g. a stack)
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * vcpuid - The id of the VCPU to add to the VM.
+ * guest_code - The vCPU's entry point
+ */
+void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code);
+
+bool vm_is_unrestricted_guest(struct kvm_vm *vm);
+
+unsigned int vm_get_page_size(struct kvm_vm *vm);
+unsigned int vm_get_page_shift(struct kvm_vm *vm);
+unsigned long vm_compute_max_gfn(struct kvm_vm *vm);
+uint64_t vm_get_max_gfn(struct kvm_vm *vm);
+int vm_get_fd(struct kvm_vm *vm);
+
+unsigned int vm_calc_num_guest_pages(enum vm_guest_mode mode, size_t size);
+unsigned int vm_num_host_pages(enum vm_guest_mode mode, unsigned int num_guest_pages);
+unsigned int vm_num_guest_pages(enum vm_guest_mode mode, unsigned int num_host_pages);
+static inline unsigned int
+vm_adjust_num_guest_pages(enum vm_guest_mode mode, unsigned int num_guest_pages)
+{
+ unsigned int n;
+ n = vm_num_guest_pages(mode, vm_num_host_pages(mode, num_guest_pages));
+#ifdef __s390x__
+ /* s390 requires 1M aligned guest sizes */
+ n = (n + 255) & ~255;
+#endif
+ return n;
+}
+
+struct kvm_userspace_memory_region *
+kvm_userspace_memory_region_find(struct kvm_vm *vm, uint64_t start,
+ uint64_t end);
+
+struct kvm_dirty_log *
+allocate_kvm_dirty_log(struct kvm_userspace_memory_region *region);
+
+int vm_create_device(struct kvm_vm *vm, struct kvm_create_device *cd);
+
+#define sync_global_to_guest(vm, g) ({ \
+ typeof(g) *_p = addr_gva2hva(vm, (vm_vaddr_t)&(g)); \
+ memcpy(_p, &(g), sizeof(g)); \
+})
+
+#define sync_global_from_guest(vm, g) ({ \
+ typeof(g) *_p = addr_gva2hva(vm, (vm_vaddr_t)&(g)); \
+ memcpy(&(g), _p, sizeof(g)); \
+})
+
+void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid);
+
+int vm_get_stats_fd(struct kvm_vm *vm);
+int vcpu_get_stats_fd(struct kvm_vm *vm, uint32_t vcpuid);
+
+uint32_t guest_get_vcpuid(void);
+
+#endif /* SELFTEST_KVM_UTIL_BASE_H */
diff --git a/tools/testing/selftests/kvm/include/riscv/processor.h b/tools/testing/selftests/kvm/include/riscv/processor.h
new file mode 100644
index 000000000000..dc284c6bdbc3
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/riscv/processor.h
@@ -0,0 +1,135 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * RISC-V processor specific defines
+ *
+ * Copyright (C) 2021 Western Digital Corporation or its affiliates.
+ */
+#ifndef SELFTEST_KVM_PROCESSOR_H
+#define SELFTEST_KVM_PROCESSOR_H
+
+#include "kvm_util.h"
+#include <linux/stringify.h>
+
+static inline uint64_t __kvm_reg_id(uint64_t type, uint64_t idx,
+ uint64_t size)
+{
+ return KVM_REG_RISCV | type | idx | size;
+}
+
+#if __riscv_xlen == 64
+#define KVM_REG_SIZE_ULONG KVM_REG_SIZE_U64
+#else
+#define KVM_REG_SIZE_ULONG KVM_REG_SIZE_U32
+#endif
+
+#define RISCV_CONFIG_REG(name) __kvm_reg_id(KVM_REG_RISCV_CONFIG, \
+ KVM_REG_RISCV_CONFIG_REG(name), \
+ KVM_REG_SIZE_ULONG)
+
+#define RISCV_CORE_REG(name) __kvm_reg_id(KVM_REG_RISCV_CORE, \
+ KVM_REG_RISCV_CORE_REG(name), \
+ KVM_REG_SIZE_ULONG)
+
+#define RISCV_CSR_REG(name) __kvm_reg_id(KVM_REG_RISCV_CSR, \
+ KVM_REG_RISCV_CSR_REG(name), \
+ KVM_REG_SIZE_ULONG)
+
+#define RISCV_TIMER_REG(name) __kvm_reg_id(KVM_REG_RISCV_TIMER, \
+ KVM_REG_RISCV_TIMER_REG(name), \
+ KVM_REG_SIZE_U64)
+
+static inline void get_reg(struct kvm_vm *vm, uint32_t vcpuid, uint64_t id,
+ unsigned long *addr)
+{
+ struct kvm_one_reg reg;
+
+ reg.id = id;
+ reg.addr = (unsigned long)addr;
+ vcpu_get_reg(vm, vcpuid, &reg);
+}
+
+static inline void set_reg(struct kvm_vm *vm, uint32_t vcpuid, uint64_t id,
+ unsigned long val)
+{
+ struct kvm_one_reg reg;
+
+ reg.id = id;
+ reg.addr = (unsigned long)&val;
+ vcpu_set_reg(vm, vcpuid, &reg);
+}
+
+/* L3 index Bit[47:39] */
+#define PGTBL_L3_INDEX_MASK 0x0000FF8000000000ULL
+#define PGTBL_L3_INDEX_SHIFT 39
+#define PGTBL_L3_BLOCK_SHIFT 39
+#define PGTBL_L3_BLOCK_SIZE 0x0000008000000000ULL
+#define PGTBL_L3_MAP_MASK (~(PGTBL_L3_BLOCK_SIZE - 1))
+/* L2 index Bit[38:30] */
+#define PGTBL_L2_INDEX_MASK 0x0000007FC0000000ULL
+#define PGTBL_L2_INDEX_SHIFT 30
+#define PGTBL_L2_BLOCK_SHIFT 30
+#define PGTBL_L2_BLOCK_SIZE 0x0000000040000000ULL
+#define PGTBL_L2_MAP_MASK (~(PGTBL_L2_BLOCK_SIZE - 1))
+/* L1 index Bit[29:21] */
+#define PGTBL_L1_INDEX_MASK 0x000000003FE00000ULL
+#define PGTBL_L1_INDEX_SHIFT 21
+#define PGTBL_L1_BLOCK_SHIFT 21
+#define PGTBL_L1_BLOCK_SIZE 0x0000000000200000ULL
+#define PGTBL_L1_MAP_MASK (~(PGTBL_L1_BLOCK_SIZE - 1))
+/* L0 index Bit[20:12] */
+#define PGTBL_L0_INDEX_MASK 0x00000000001FF000ULL
+#define PGTBL_L0_INDEX_SHIFT 12
+#define PGTBL_L0_BLOCK_SHIFT 12
+#define PGTBL_L0_BLOCK_SIZE 0x0000000000001000ULL
+#define PGTBL_L0_MAP_MASK (~(PGTBL_L0_BLOCK_SIZE - 1))
+
+#define PGTBL_PTE_ADDR_MASK 0x003FFFFFFFFFFC00ULL
+#define PGTBL_PTE_ADDR_SHIFT 10
+#define PGTBL_PTE_RSW_MASK 0x0000000000000300ULL
+#define PGTBL_PTE_RSW_SHIFT 8
+#define PGTBL_PTE_DIRTY_MASK 0x0000000000000080ULL
+#define PGTBL_PTE_DIRTY_SHIFT 7
+#define PGTBL_PTE_ACCESSED_MASK 0x0000000000000040ULL
+#define PGTBL_PTE_ACCESSED_SHIFT 6
+#define PGTBL_PTE_GLOBAL_MASK 0x0000000000000020ULL
+#define PGTBL_PTE_GLOBAL_SHIFT 5
+#define PGTBL_PTE_USER_MASK 0x0000000000000010ULL
+#define PGTBL_PTE_USER_SHIFT 4
+#define PGTBL_PTE_EXECUTE_MASK 0x0000000000000008ULL
+#define PGTBL_PTE_EXECUTE_SHIFT 3
+#define PGTBL_PTE_WRITE_MASK 0x0000000000000004ULL
+#define PGTBL_PTE_WRITE_SHIFT 2
+#define PGTBL_PTE_READ_MASK 0x0000000000000002ULL
+#define PGTBL_PTE_READ_SHIFT 1
+#define PGTBL_PTE_PERM_MASK (PGTBL_PTE_EXECUTE_MASK | \
+ PGTBL_PTE_WRITE_MASK | \
+ PGTBL_PTE_READ_MASK)
+#define PGTBL_PTE_VALID_MASK 0x0000000000000001ULL
+#define PGTBL_PTE_VALID_SHIFT 0
+
+#define PGTBL_PAGE_SIZE PGTBL_L0_BLOCK_SIZE
+#define PGTBL_PAGE_SIZE_SHIFT PGTBL_L0_BLOCK_SHIFT
+
+#define SATP_PPN _AC(0x00000FFFFFFFFFFF, UL)
+#define SATP_MODE_39 _AC(0x8000000000000000, UL)
+#define SATP_MODE_48 _AC(0x9000000000000000, UL)
+#define SATP_ASID_BITS 16
+#define SATP_ASID_SHIFT 44
+#define SATP_ASID_MASK _AC(0xFFFF, UL)
+
+#define SBI_EXT_EXPERIMENTAL_START 0x08000000
+#define SBI_EXT_EXPERIMENTAL_END 0x08FFFFFF
+
+#define KVM_RISCV_SELFTESTS_SBI_EXT SBI_EXT_EXPERIMENTAL_END
+
+struct sbiret {
+ long error;
+ long value;
+};
+
+struct sbiret sbi_ecall(int ext, int fid, unsigned long arg0,
+ unsigned long arg1, unsigned long arg2,
+ unsigned long arg3, unsigned long arg4,
+ unsigned long arg5);
+
+#endif /* SELFTEST_KVM_PROCESSOR_H */
diff --git a/tools/testing/selftests/kvm/include/ucall_common.h b/tools/testing/selftests/kvm/include/ucall_common.h
new file mode 100644
index 000000000000..9eecc9d40b79
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/ucall_common.h
@@ -0,0 +1,59 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * tools/testing/selftests/kvm/include/kvm_util.h
+ *
+ * Copyright (C) 2018, Google LLC.
+ */
+#ifndef SELFTEST_KVM_UCALL_COMMON_H
+#define SELFTEST_KVM_UCALL_COMMON_H
+
+/* Common ucalls */
+enum {
+ UCALL_NONE,
+ UCALL_SYNC,
+ UCALL_ABORT,
+ UCALL_DONE,
+ UCALL_UNHANDLED,
+};
+
+#define UCALL_MAX_ARGS 6
+
+struct ucall {
+ uint64_t cmd;
+ uint64_t args[UCALL_MAX_ARGS];
+};
+
+void ucall_init(struct kvm_vm *vm, void *arg);
+void ucall_uninit(struct kvm_vm *vm);
+void ucall(uint64_t cmd, int nargs, ...);
+uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc);
+
+#define GUEST_SYNC_ARGS(stage, arg1, arg2, arg3, arg4) \
+ ucall(UCALL_SYNC, 6, "hello", stage, arg1, arg2, arg3, arg4)
+#define GUEST_SYNC(stage) ucall(UCALL_SYNC, 2, "hello", stage)
+#define GUEST_DONE() ucall(UCALL_DONE, 0)
+#define __GUEST_ASSERT(_condition, _condstr, _nargs, _args...) do { \
+ if (!(_condition)) \
+ ucall(UCALL_ABORT, 2 + _nargs, \
+ "Failed guest assert: " \
+ _condstr, __LINE__, _args); \
+} while (0)
+
+#define GUEST_ASSERT(_condition) \
+ __GUEST_ASSERT(_condition, #_condition, 0, 0)
+
+#define GUEST_ASSERT_1(_condition, arg1) \
+ __GUEST_ASSERT(_condition, #_condition, 1, (arg1))
+
+#define GUEST_ASSERT_2(_condition, arg1, arg2) \
+ __GUEST_ASSERT(_condition, #_condition, 2, (arg1), (arg2))
+
+#define GUEST_ASSERT_3(_condition, arg1, arg2, arg3) \
+ __GUEST_ASSERT(_condition, #_condition, 3, (arg1), (arg2), (arg3))
+
+#define GUEST_ASSERT_4(_condition, arg1, arg2, arg3, arg4) \
+ __GUEST_ASSERT(_condition, #_condition, 4, (arg1), (arg2), (arg3), (arg4))
+
+#define GUEST_ASSERT_EQ(a, b) __GUEST_ASSERT((a) == (b), #a " == " #b, 2, a, b)
+
+#endif /* SELFTEST_KVM_UCALL_COMMON_H */
diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h
index 05e65ca1c30c..8a470da7b71a 100644
--- a/tools/testing/selftests/kvm/include/x86_64/processor.h
+++ b/tools/testing/selftests/kvm/include/x86_64/processor.h
@@ -10,8 +10,10 @@
#include <assert.h>
#include <stdint.h>
+#include <syscall.h>
#include <asm/msr-index.h>
+#include <asm/prctl.h>
#include "../kvm_util.h"
@@ -92,6 +94,21 @@ struct desc_ptr {
uint64_t address;
} __attribute__((packed));
+struct kvm_x86_state {
+ struct kvm_xsave *xsave;
+ struct kvm_vcpu_events events;
+ struct kvm_mp_state mp_state;
+ struct kvm_regs regs;
+ struct kvm_xcrs xcrs;
+ struct kvm_sregs sregs;
+ struct kvm_debugregs debugregs;
+ union {
+ struct kvm_nested_state nested;
+ char nested_[16384];
+ };
+ struct kvm_msrs msrs;
+};
+
static inline uint64_t get_desc64_base(const struct desc64 *desc)
{
return ((uint64_t)desc->base3 << 32) |
@@ -347,17 +364,37 @@ static inline unsigned long get_xmm(int n)
}
bool is_intel_cpu(void);
+bool is_amd_cpu(void);
+
+static inline unsigned int x86_family(unsigned int eax)
+{
+ unsigned int x86;
+
+ x86 = (eax >> 8) & 0xf;
+
+ if (x86 == 0xf)
+ x86 += (eax >> 20) & 0xff;
+
+ return x86;
+}
+
+static inline unsigned int x86_model(unsigned int eax)
+{
+ return ((eax >> 12) & 0xf0) | ((eax >> 4) & 0x0f);
+}
-struct kvm_x86_state;
struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid);
void vcpu_load_state(struct kvm_vm *vm, uint32_t vcpuid,
struct kvm_x86_state *state);
+void kvm_x86_state_cleanup(struct kvm_x86_state *state);
struct kvm_msr_list *kvm_get_msr_index_list(void);
uint64_t kvm_get_feature_msr(uint64_t msr_index);
struct kvm_cpuid2 *kvm_get_supported_cpuid(void);
struct kvm_cpuid2 *vcpu_get_cpuid(struct kvm_vm *vm, uint32_t vcpuid);
+int __vcpu_set_cpuid(struct kvm_vm *vm, uint32_t vcpuid,
+ struct kvm_cpuid2 *cpuid);
void vcpu_set_cpuid(struct kvm_vm *vm, uint32_t vcpuid,
struct kvm_cpuid2 *cpuid);
@@ -402,6 +439,11 @@ void vm_set_page_table_entry(struct kvm_vm *vm, int vcpuid, uint64_t vaddr,
uint64_t pte);
/*
+ * get_cpuid() - find matching CPUID entry and return pointer to it.
+ */
+struct kvm_cpuid_entry2 *get_cpuid(struct kvm_cpuid2 *cpuid, uint32_t function,
+ uint32_t index);
+/*
* set_cpuid() - overwrites a matching cpuid entry with the provided value.
* matches based on ent->function && ent->index. returns true
* if a match was found and successfully overwritten.
@@ -416,6 +458,7 @@ uint64_t kvm_hypercall(uint64_t nr, uint64_t a0, uint64_t a1, uint64_t a2,
struct kvm_cpuid2 *kvm_get_supported_hv_cpuid(void);
void vcpu_set_hv_cpuid(struct kvm_vm *vm, uint32_t vcpuid);
struct kvm_cpuid2 *vcpu_get_supported_hv_cpuid(struct kvm_vm *vm, uint32_t vcpuid);
+void vm_xsave_req_perm(int bit);
enum x86_page_size {
X86_PAGE_SIZE_4K = 0,
@@ -443,4 +486,11 @@ void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
/* VMX_EPT_VPID_CAP bits */
#define VMX_EPT_VPID_CAP_AD_BITS (1ULL << 21)
+#define XSTATE_XTILE_CFG_BIT 17
+#define XSTATE_XTILE_DATA_BIT 18
+
+#define XSTATE_XTILE_CFG_MASK (1ULL << XSTATE_XTILE_CFG_BIT)
+#define XSTATE_XTILE_DATA_MASK (1ULL << XSTATE_XTILE_DATA_BIT)
+#define XFEATURE_XTILE_MASK (XSTATE_XTILE_CFG_MASK | \
+ XSTATE_XTILE_DATA_MASK)
#endif /* SELFTEST_KVM_PROCESSOR_H */
diff --git a/tools/testing/selftests/kvm/lib/aarch64/gic.c b/tools/testing/selftests/kvm/lib/aarch64/gic.c
index fff4fc27504d..55668631d546 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/gic.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/gic.c
@@ -93,3 +93,69 @@ void gic_set_eoi(unsigned int intid)
GUEST_ASSERT(gic_common_ops);
gic_common_ops->gic_write_eoir(intid);
}
+
+void gic_set_dir(unsigned int intid)
+{
+ GUEST_ASSERT(gic_common_ops);
+ gic_common_ops->gic_write_dir(intid);
+}
+
+void gic_set_eoi_split(bool split)
+{
+ GUEST_ASSERT(gic_common_ops);
+ gic_common_ops->gic_set_eoi_split(split);
+}
+
+void gic_set_priority_mask(uint64_t pmr)
+{
+ GUEST_ASSERT(gic_common_ops);
+ gic_common_ops->gic_set_priority_mask(pmr);
+}
+
+void gic_set_priority(unsigned int intid, unsigned int prio)
+{
+ GUEST_ASSERT(gic_common_ops);
+ gic_common_ops->gic_set_priority(intid, prio);
+}
+
+void gic_irq_set_active(unsigned int intid)
+{
+ GUEST_ASSERT(gic_common_ops);
+ gic_common_ops->gic_irq_set_active(intid);
+}
+
+void gic_irq_clear_active(unsigned int intid)
+{
+ GUEST_ASSERT(gic_common_ops);
+ gic_common_ops->gic_irq_clear_active(intid);
+}
+
+bool gic_irq_get_active(unsigned int intid)
+{
+ GUEST_ASSERT(gic_common_ops);
+ return gic_common_ops->gic_irq_get_active(intid);
+}
+
+void gic_irq_set_pending(unsigned int intid)
+{
+ GUEST_ASSERT(gic_common_ops);
+ gic_common_ops->gic_irq_set_pending(intid);
+}
+
+void gic_irq_clear_pending(unsigned int intid)
+{
+ GUEST_ASSERT(gic_common_ops);
+ gic_common_ops->gic_irq_clear_pending(intid);
+}
+
+bool gic_irq_get_pending(unsigned int intid)
+{
+ GUEST_ASSERT(gic_common_ops);
+ return gic_common_ops->gic_irq_get_pending(intid);
+}
+
+void gic_irq_set_config(unsigned int intid, bool is_edge)
+{
+ GUEST_ASSERT(gic_common_ops);
+ gic_common_ops->gic_irq_set_config(intid, is_edge);
+}
diff --git a/tools/testing/selftests/kvm/lib/aarch64/gic_private.h b/tools/testing/selftests/kvm/lib/aarch64/gic_private.h
index d81d739433dc..75d07313c893 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/gic_private.h
+++ b/tools/testing/selftests/kvm/lib/aarch64/gic_private.h
@@ -14,6 +14,17 @@ struct gic_common_ops {
void (*gic_irq_disable)(unsigned int intid);
uint64_t (*gic_read_iar)(void);
void (*gic_write_eoir)(uint32_t irq);
+ void (*gic_write_dir)(uint32_t irq);
+ void (*gic_set_eoi_split)(bool split);
+ void (*gic_set_priority_mask)(uint64_t mask);
+ void (*gic_set_priority)(uint32_t intid, uint32_t prio);
+ void (*gic_irq_set_active)(uint32_t intid);
+ void (*gic_irq_clear_active)(uint32_t intid);
+ bool (*gic_irq_get_active)(uint32_t intid);
+ void (*gic_irq_set_pending)(uint32_t intid);
+ void (*gic_irq_clear_pending)(uint32_t intid);
+ bool (*gic_irq_get_pending)(uint32_t intid);
+ void (*gic_irq_set_config)(uint32_t intid, bool is_edge);
};
extern const struct gic_common_ops gicv3_ops;
diff --git a/tools/testing/selftests/kvm/lib/aarch64/gic_v3.c b/tools/testing/selftests/kvm/lib/aarch64/gic_v3.c
index 2dbf3339b62e..00f613c0583c 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/gic_v3.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/gic_v3.c
@@ -19,7 +19,8 @@ struct gicv3_data {
unsigned int nr_spis;
};
-#define sgi_base_from_redist(redist_base) (redist_base + SZ_64K)
+#define sgi_base_from_redist(redist_base) (redist_base + SZ_64K)
+#define DIST_BIT (1U << 31)
enum gicv3_intid_range {
SGI_RANGE,
@@ -50,6 +51,14 @@ static void gicv3_gicr_wait_for_rwp(void *redist_base)
}
}
+static void gicv3_wait_for_rwp(uint32_t cpu_or_dist)
+{
+ if (cpu_or_dist & DIST_BIT)
+ gicv3_gicd_wait_for_rwp();
+ else
+ gicv3_gicr_wait_for_rwp(gicv3_data.redist_base[cpu_or_dist]);
+}
+
static enum gicv3_intid_range get_intid_range(unsigned int intid)
{
switch (intid) {
@@ -81,39 +90,175 @@ static void gicv3_write_eoir(uint32_t irq)
isb();
}
-static void
-gicv3_config_irq(unsigned int intid, unsigned int offset)
+static void gicv3_write_dir(uint32_t irq)
+{
+ write_sysreg_s(irq, SYS_ICC_DIR_EL1);
+ isb();
+}
+
+static void gicv3_set_priority_mask(uint64_t mask)
+{
+ write_sysreg_s(mask, SYS_ICC_PMR_EL1);
+}
+
+static void gicv3_set_eoi_split(bool split)
+{
+ uint32_t val;
+
+ /* All other fields are read-only, so no need to read CTLR first. In
+ * fact, the kernel does the same.
+ */
+ val = split ? (1U << 1) : 0;
+ write_sysreg_s(val, SYS_ICC_CTLR_EL1);
+ isb();
+}
+
+uint32_t gicv3_reg_readl(uint32_t cpu_or_dist, uint64_t offset)
+{
+ void *base = cpu_or_dist & DIST_BIT ? gicv3_data.dist_base
+ : sgi_base_from_redist(gicv3_data.redist_base[cpu_or_dist]);
+ return readl(base + offset);
+}
+
+void gicv3_reg_writel(uint32_t cpu_or_dist, uint64_t offset, uint32_t reg_val)
+{
+ void *base = cpu_or_dist & DIST_BIT ? gicv3_data.dist_base
+ : sgi_base_from_redist(gicv3_data.redist_base[cpu_or_dist]);
+ writel(reg_val, base + offset);
+}
+
+uint32_t gicv3_getl_fields(uint32_t cpu_or_dist, uint64_t offset, uint32_t mask)
+{
+ return gicv3_reg_readl(cpu_or_dist, offset) & mask;
+}
+
+void gicv3_setl_fields(uint32_t cpu_or_dist, uint64_t offset,
+ uint32_t mask, uint32_t reg_val)
+{
+ uint32_t tmp = gicv3_reg_readl(cpu_or_dist, offset) & ~mask;
+
+ tmp |= (reg_val & mask);
+ gicv3_reg_writel(cpu_or_dist, offset, tmp);
+}
+
+/*
+ * We use a single offset for the distributor and redistributor maps as they
+ * have the same value in both. The only exceptions are registers that only
+ * exist in one and not the other, like GICR_WAKER that doesn't exist in the
+ * distributor map. Such registers are conveniently marked as reserved in the
+ * map that doesn't implement it; like GICR_WAKER's offset of 0x0014 being
+ * marked as "Reserved" in the Distributor map.
+ */
+static void gicv3_access_reg(uint32_t intid, uint64_t offset,
+ uint32_t reg_bits, uint32_t bits_per_field,
+ bool write, uint32_t *val)
{
uint32_t cpu = guest_get_vcpuid();
- uint32_t mask = 1 << (intid % 32);
enum gicv3_intid_range intid_range = get_intid_range(intid);
- void *reg;
-
- /* We care about 'cpu' only for SGIs or PPIs */
- if (intid_range == SGI_RANGE || intid_range == PPI_RANGE) {
- GUEST_ASSERT(cpu < gicv3_data.nr_cpus);
-
- reg = sgi_base_from_redist(gicv3_data.redist_base[cpu]) +
- offset;
- writel(mask, reg);
- gicv3_gicr_wait_for_rwp(gicv3_data.redist_base[cpu]);
- } else if (intid_range == SPI_RANGE) {
- reg = gicv3_data.dist_base + offset + (intid / 32) * 4;
- writel(mask, reg);
- gicv3_gicd_wait_for_rwp();
- } else {
- GUEST_ASSERT(0);
- }
+ uint32_t fields_per_reg, index, mask, shift;
+ uint32_t cpu_or_dist;
+
+ GUEST_ASSERT(bits_per_field <= reg_bits);
+ GUEST_ASSERT(*val < (1U << bits_per_field));
+ /* Some registers like IROUTER are 64 bit long. Those are currently not
+ * supported by readl nor writel, so just asserting here until then.
+ */
+ GUEST_ASSERT(reg_bits == 32);
+
+ fields_per_reg = reg_bits / bits_per_field;
+ index = intid % fields_per_reg;
+ shift = index * bits_per_field;
+ mask = ((1U << bits_per_field) - 1) << shift;
+
+ /* Set offset to the actual register holding intid's config. */
+ offset += (intid / fields_per_reg) * (reg_bits / 8);
+
+ cpu_or_dist = (intid_range == SPI_RANGE) ? DIST_BIT : cpu;
+
+ if (write)
+ gicv3_setl_fields(cpu_or_dist, offset, mask, *val << shift);
+ *val = gicv3_getl_fields(cpu_or_dist, offset, mask) >> shift;
+}
+
+static void gicv3_write_reg(uint32_t intid, uint64_t offset,
+ uint32_t reg_bits, uint32_t bits_per_field, uint32_t val)
+{
+ gicv3_access_reg(intid, offset, reg_bits,
+ bits_per_field, true, &val);
+}
+
+static uint32_t gicv3_read_reg(uint32_t intid, uint64_t offset,
+ uint32_t reg_bits, uint32_t bits_per_field)
+{
+ uint32_t val;
+
+ gicv3_access_reg(intid, offset, reg_bits,
+ bits_per_field, false, &val);
+ return val;
+}
+
+static void gicv3_set_priority(uint32_t intid, uint32_t prio)
+{
+ gicv3_write_reg(intid, GICD_IPRIORITYR, 32, 8, prio);
+}
+
+/* Sets the intid to be level-sensitive or edge-triggered. */
+static void gicv3_irq_set_config(uint32_t intid, bool is_edge)
+{
+ uint32_t val;
+
+ /* N/A for private interrupts. */
+ GUEST_ASSERT(get_intid_range(intid) == SPI_RANGE);
+ val = is_edge ? 2 : 0;
+ gicv3_write_reg(intid, GICD_ICFGR, 32, 2, val);
+}
+
+static void gicv3_irq_enable(uint32_t intid)
+{
+ bool is_spi = get_intid_range(intid) == SPI_RANGE;
+ uint32_t cpu = guest_get_vcpuid();
+
+ gicv3_write_reg(intid, GICD_ISENABLER, 32, 1, 1);
+ gicv3_wait_for_rwp(is_spi ? DIST_BIT : cpu);
+}
+
+static void gicv3_irq_disable(uint32_t intid)
+{
+ bool is_spi = get_intid_range(intid) == SPI_RANGE;
+ uint32_t cpu = guest_get_vcpuid();
+
+ gicv3_write_reg(intid, GICD_ICENABLER, 32, 1, 1);
+ gicv3_wait_for_rwp(is_spi ? DIST_BIT : cpu);
+}
+
+static void gicv3_irq_set_active(uint32_t intid)
+{
+ gicv3_write_reg(intid, GICD_ISACTIVER, 32, 1, 1);
+}
+
+static void gicv3_irq_clear_active(uint32_t intid)
+{
+ gicv3_write_reg(intid, GICD_ICACTIVER, 32, 1, 1);
+}
+
+static bool gicv3_irq_get_active(uint32_t intid)
+{
+ return gicv3_read_reg(intid, GICD_ISACTIVER, 32, 1);
+}
+
+static void gicv3_irq_set_pending(uint32_t intid)
+{
+ gicv3_write_reg(intid, GICD_ISPENDR, 32, 1, 1);
}
-static void gicv3_irq_enable(unsigned int intid)
+static void gicv3_irq_clear_pending(uint32_t intid)
{
- gicv3_config_irq(intid, GICD_ISENABLER);
+ gicv3_write_reg(intid, GICD_ICPENDR, 32, 1, 1);
}
-static void gicv3_irq_disable(unsigned int intid)
+static bool gicv3_irq_get_pending(uint32_t intid)
{
- gicv3_config_irq(intid, GICD_ICENABLER);
+ return gicv3_read_reg(intid, GICD_ISPENDR, 32, 1);
}
static void gicv3_enable_redist(void *redist_base)
@@ -237,4 +382,15 @@ const struct gic_common_ops gicv3_ops = {
.gic_irq_disable = gicv3_irq_disable,
.gic_read_iar = gicv3_read_iar,
.gic_write_eoir = gicv3_write_eoir,
+ .gic_write_dir = gicv3_write_dir,
+ .gic_set_priority_mask = gicv3_set_priority_mask,
+ .gic_set_eoi_split = gicv3_set_eoi_split,
+ .gic_set_priority = gicv3_set_priority,
+ .gic_irq_set_active = gicv3_irq_set_active,
+ .gic_irq_clear_active = gicv3_irq_clear_active,
+ .gic_irq_get_active = gicv3_irq_get_active,
+ .gic_irq_set_pending = gicv3_irq_set_pending,
+ .gic_irq_clear_pending = gicv3_irq_clear_pending,
+ .gic_irq_get_pending = gicv3_irq_get_pending,
+ .gic_irq_set_config = gicv3_irq_set_config,
};
diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c
index b4eeeafd2a70..9343d82519b4 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/processor.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c
@@ -8,6 +8,7 @@
#include <linux/compiler.h>
#include <assert.h>
+#include "guest_modes.h"
#include "kvm_util.h"
#include "../kvm_util_internal.h"
#include "processor.h"
@@ -237,6 +238,7 @@ void aarch64_vcpu_setup(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_vcpu_init
get_reg(vm, vcpuid, KVM_ARM64_SYS_REG(SYS_SCTLR_EL1), &sctlr_el1);
get_reg(vm, vcpuid, KVM_ARM64_SYS_REG(SYS_TCR_EL1), &tcr_el1);
+ /* Configure base granule size */
switch (vm->mode) {
case VM_MODE_P52V48_4K:
TEST_FAIL("AArch64 does not support 4K sized pages "
@@ -245,25 +247,47 @@ void aarch64_vcpu_setup(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_vcpu_init
TEST_FAIL("AArch64 does not support 4K sized pages "
"with ANY-bit physical address ranges");
case VM_MODE_P52V48_64K:
+ case VM_MODE_P48V48_64K:
+ case VM_MODE_P40V48_64K:
+ case VM_MODE_P36V48_64K:
tcr_el1 |= 1ul << 14; /* TG0 = 64KB */
- tcr_el1 |= 6ul << 32; /* IPS = 52 bits */
+ break;
+ case VM_MODE_P48V48_16K:
+ case VM_MODE_P40V48_16K:
+ case VM_MODE_P36V48_16K:
+ case VM_MODE_P36V47_16K:
+ tcr_el1 |= 2ul << 14; /* TG0 = 16KB */
break;
case VM_MODE_P48V48_4K:
+ case VM_MODE_P40V48_4K:
+ case VM_MODE_P36V48_4K:
tcr_el1 |= 0ul << 14; /* TG0 = 4KB */
- tcr_el1 |= 5ul << 32; /* IPS = 48 bits */
break;
+ default:
+ TEST_FAIL("Unknown guest mode, mode: 0x%x", vm->mode);
+ }
+
+ /* Configure output size */
+ switch (vm->mode) {
+ case VM_MODE_P52V48_64K:
+ tcr_el1 |= 6ul << 32; /* IPS = 52 bits */
+ break;
+ case VM_MODE_P48V48_4K:
+ case VM_MODE_P48V48_16K:
case VM_MODE_P48V48_64K:
- tcr_el1 |= 1ul << 14; /* TG0 = 64KB */
tcr_el1 |= 5ul << 32; /* IPS = 48 bits */
break;
case VM_MODE_P40V48_4K:
- tcr_el1 |= 0ul << 14; /* TG0 = 4KB */
- tcr_el1 |= 2ul << 32; /* IPS = 40 bits */
- break;
+ case VM_MODE_P40V48_16K:
case VM_MODE_P40V48_64K:
- tcr_el1 |= 1ul << 14; /* TG0 = 64KB */
tcr_el1 |= 2ul << 32; /* IPS = 40 bits */
break;
+ case VM_MODE_P36V48_4K:
+ case VM_MODE_P36V48_16K:
+ case VM_MODE_P36V48_64K:
+ case VM_MODE_P36V47_16K:
+ tcr_el1 |= 1ul << 32; /* IPS = 36 bits */
+ break;
default:
TEST_FAIL("Unknown guest mode, mode: 0x%x", vm->mode);
}
@@ -432,3 +456,47 @@ uint32_t guest_get_vcpuid(void)
{
return read_sysreg(tpidr_el1);
}
+
+void aarch64_get_supported_page_sizes(uint32_t ipa,
+ bool *ps4k, bool *ps16k, bool *ps64k)
+{
+ struct kvm_vcpu_init preferred_init;
+ int kvm_fd, vm_fd, vcpu_fd, err;
+ uint64_t val;
+ struct kvm_one_reg reg = {
+ .id = KVM_ARM64_SYS_REG(SYS_ID_AA64MMFR0_EL1),
+ .addr = (uint64_t)&val,
+ };
+
+ kvm_fd = open_kvm_dev_path_or_exit();
+ vm_fd = ioctl(kvm_fd, KVM_CREATE_VM, ipa);
+ TEST_ASSERT(vm_fd >= 0, "Can't create VM");
+
+ vcpu_fd = ioctl(vm_fd, KVM_CREATE_VCPU, 0);
+ TEST_ASSERT(vcpu_fd >= 0, "Can't create vcpu");
+
+ err = ioctl(vm_fd, KVM_ARM_PREFERRED_TARGET, &preferred_init);
+ TEST_ASSERT(err == 0, "Can't get target");
+ err = ioctl(vcpu_fd, KVM_ARM_VCPU_INIT, &preferred_init);
+ TEST_ASSERT(err == 0, "Can't get init vcpu");
+
+ err = ioctl(vcpu_fd, KVM_GET_ONE_REG, &reg);
+ TEST_ASSERT(err == 0, "Can't get MMFR0");
+
+ *ps4k = ((val >> 28) & 0xf) != 0xf;
+ *ps64k = ((val >> 24) & 0xf) == 0;
+ *ps16k = ((val >> 20) & 0xf) != 0;
+
+ close(vcpu_fd);
+ close(vm_fd);
+ close(kvm_fd);
+}
+
+/*
+ * arm64 doesn't have a true default mode, so start by computing the
+ * available IPA space and page sizes early.
+ */
+void __attribute__((constructor)) init_guest_modes(void)
+{
+ guest_modes_append_default();
+}
diff --git a/tools/testing/selftests/kvm/lib/aarch64/vgic.c b/tools/testing/selftests/kvm/lib/aarch64/vgic.c
index b9b271ff520d..f5cd0c536d85 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/vgic.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/vgic.c
@@ -5,11 +5,14 @@
#include <linux/kvm.h>
#include <linux/sizes.h>
+#include <asm/kvm_para.h>
#include <asm/kvm.h>
#include "kvm_util.h"
#include "../kvm_util_internal.h"
#include "vgic.h"
+#include "gic.h"
+#include "gic_v3.h"
/*
* vGIC-v3 default host setup
@@ -28,7 +31,7 @@
* redistributor regions of the guest. Since it depends on the number of
* vCPUs for the VM, it must be called after all the vCPUs have been created.
*/
-int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus,
+int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, uint32_t nr_irqs,
uint64_t gicd_base_gpa, uint64_t gicr_base_gpa)
{
int gic_fd;
@@ -49,7 +52,16 @@ int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus,
nr_vcpus, nr_vcpus_created);
/* Distributor setup */
- gic_fd = kvm_create_device(vm, KVM_DEV_TYPE_ARM_VGIC_V3, false);
+ if (_kvm_create_device(vm, KVM_DEV_TYPE_ARM_VGIC_V3,
+ false, &gic_fd) != 0)
+ return -1;
+
+ kvm_device_access(gic_fd, KVM_DEV_ARM_VGIC_GRP_NR_IRQS,
+ 0, &nr_irqs, true);
+
+ kvm_device_access(gic_fd, KVM_DEV_ARM_VGIC_GRP_CTRL,
+ KVM_DEV_ARM_VGIC_CTRL_INIT, NULL, true);
+
kvm_device_access(gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
KVM_VGIC_V3_ADDR_TYPE_DIST, &gicd_base_gpa, true);
nr_gic_pages = vm_calc_num_guest_pages(vm->mode, KVM_VGIC_V3_DIST_SIZE);
@@ -68,3 +80,94 @@ int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus,
return gic_fd;
}
+
+/* should only work for level sensitive interrupts */
+int _kvm_irq_set_level_info(int gic_fd, uint32_t intid, int level)
+{
+ uint64_t attr = 32 * (intid / 32);
+ uint64_t index = intid % 32;
+ uint64_t val;
+ int ret;
+
+ ret = _kvm_device_access(gic_fd, KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO,
+ attr, &val, false);
+ if (ret != 0)
+ return ret;
+
+ val |= 1U << index;
+ ret = _kvm_device_access(gic_fd, KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO,
+ attr, &val, true);
+ return ret;
+}
+
+void kvm_irq_set_level_info(int gic_fd, uint32_t intid, int level)
+{
+ int ret = _kvm_irq_set_level_info(gic_fd, intid, level);
+
+ TEST_ASSERT(ret == 0, "KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO failed, "
+ "rc: %i errno: %i", ret, errno);
+}
+
+int _kvm_arm_irq_line(struct kvm_vm *vm, uint32_t intid, int level)
+{
+ uint32_t irq = intid & KVM_ARM_IRQ_NUM_MASK;
+
+ TEST_ASSERT(!INTID_IS_SGI(intid), "KVM_IRQ_LINE's interface itself "
+ "doesn't allow injecting SGIs. There's no mask for it.");
+
+ if (INTID_IS_PPI(intid))
+ irq |= KVM_ARM_IRQ_TYPE_PPI << KVM_ARM_IRQ_TYPE_SHIFT;
+ else
+ irq |= KVM_ARM_IRQ_TYPE_SPI << KVM_ARM_IRQ_TYPE_SHIFT;
+
+ return _kvm_irq_line(vm, irq, level);
+}
+
+void kvm_arm_irq_line(struct kvm_vm *vm, uint32_t intid, int level)
+{
+ int ret = _kvm_arm_irq_line(vm, intid, level);
+
+ TEST_ASSERT(ret == 0, "KVM_IRQ_LINE failed, rc: %i errno: %i",
+ ret, errno);
+}
+
+static void vgic_poke_irq(int gic_fd, uint32_t intid,
+ uint32_t vcpu, uint64_t reg_off)
+{
+ uint64_t reg = intid / 32;
+ uint64_t index = intid % 32;
+ uint64_t attr = reg_off + reg * 4;
+ uint64_t val;
+ bool intid_is_private = INTID_IS_SGI(intid) || INTID_IS_PPI(intid);
+
+ /* Check that the addr part of the attr is within 32 bits. */
+ assert(attr <= KVM_DEV_ARM_VGIC_OFFSET_MASK);
+
+ uint32_t group = intid_is_private ? KVM_DEV_ARM_VGIC_GRP_REDIST_REGS
+ : KVM_DEV_ARM_VGIC_GRP_DIST_REGS;
+
+ if (intid_is_private) {
+ /* TODO: only vcpu 0 implemented for now. */
+ assert(vcpu == 0);
+ attr += SZ_64K;
+ }
+
+ /* All calls will succeed, even with invalid intid's, as long as the
+ * addr part of the attr is within 32 bits (checked above). An invalid
+ * intid will just make the read/writes point to above the intended
+ * register space (i.e., ICPENDR after ISPENDR).
+ */
+ kvm_device_access(gic_fd, group, attr, &val, false);
+ val |= 1ULL << index;
+ kvm_device_access(gic_fd, group, attr, &val, true);
+}
+
+void kvm_irq_write_ispendr(int gic_fd, uint32_t intid, uint32_t vcpu)
+{
+ vgic_poke_irq(gic_fd, intid, vcpu, GICD_ISPENDR);
+}
+
+void kvm_irq_write_isactiver(int gic_fd, uint32_t intid, uint32_t vcpu)
+{
+ vgic_poke_irq(gic_fd, intid, vcpu, GICD_ISACTIVER);
+}
diff --git a/tools/testing/selftests/kvm/lib/guest_modes.c b/tools/testing/selftests/kvm/lib/guest_modes.c
index c330f414ef96..8784013b747c 100644
--- a/tools/testing/selftests/kvm/lib/guest_modes.c
+++ b/tools/testing/selftests/kvm/lib/guest_modes.c
@@ -4,22 +4,59 @@
*/
#include "guest_modes.h"
+#ifdef __aarch64__
+#include "processor.h"
+enum vm_guest_mode vm_mode_default;
+#endif
+
struct guest_mode guest_modes[NUM_VM_MODES];
void guest_modes_append_default(void)
{
+#ifndef __aarch64__
guest_mode_append(VM_MODE_DEFAULT, true, true);
-
-#ifdef __aarch64__
- guest_mode_append(VM_MODE_P40V48_64K, true, true);
+#else
{
unsigned int limit = kvm_check_cap(KVM_CAP_ARM_VM_IPA_SIZE);
+ bool ps4k, ps16k, ps64k;
+ int i;
+
+ aarch64_get_supported_page_sizes(limit, &ps4k, &ps16k, &ps64k);
+
+ vm_mode_default = NUM_VM_MODES;
+
if (limit >= 52)
- guest_mode_append(VM_MODE_P52V48_64K, true, true);
+ guest_mode_append(VM_MODE_P52V48_64K, ps64k, ps64k);
if (limit >= 48) {
- guest_mode_append(VM_MODE_P48V48_4K, true, true);
- guest_mode_append(VM_MODE_P48V48_64K, true, true);
+ guest_mode_append(VM_MODE_P48V48_4K, ps4k, ps4k);
+ guest_mode_append(VM_MODE_P48V48_16K, ps16k, ps16k);
+ guest_mode_append(VM_MODE_P48V48_64K, ps64k, ps64k);
+ }
+ if (limit >= 40) {
+ guest_mode_append(VM_MODE_P40V48_4K, ps4k, ps4k);
+ guest_mode_append(VM_MODE_P40V48_16K, ps16k, ps16k);
+ guest_mode_append(VM_MODE_P40V48_64K, ps64k, ps64k);
+ if (ps4k)
+ vm_mode_default = VM_MODE_P40V48_4K;
}
+ if (limit >= 36) {
+ guest_mode_append(VM_MODE_P36V48_4K, ps4k, ps4k);
+ guest_mode_append(VM_MODE_P36V48_16K, ps16k, ps16k);
+ guest_mode_append(VM_MODE_P36V48_64K, ps64k, ps64k);
+ guest_mode_append(VM_MODE_P36V47_16K, ps16k, ps16k);
+ }
+
+ /*
+ * Pick the first supported IPA size if the default
+ * isn't available.
+ */
+ for (i = 0; vm_mode_default == NUM_VM_MODES && i < NUM_VM_MODES; i++) {
+ if (guest_modes[i].supported && guest_modes[i].enabled)
+ vm_mode_default = i;
+ }
+
+ TEST_ASSERT(vm_mode_default != NUM_VM_MODES,
+ "No supported mode!");
}
#endif
#ifdef __s390x__
@@ -38,6 +75,16 @@ void guest_modes_append_default(void)
guest_mode_append(VM_MODE_P47V64_4K, true, true);
}
#endif
+#ifdef __riscv
+ {
+ unsigned int sz = kvm_check_cap(KVM_CAP_VM_GPA_BITS);
+
+ if (sz >= 52)
+ guest_mode_append(VM_MODE_P52V48_4K, true, true);
+ if (sz >= 48)
+ guest_mode_append(VM_MODE_P48V48_4K, true, true);
+ }
+#endif
}
void for_each_guest_mode(void (*func)(enum vm_guest_mode, void *), void *arg)
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 53d2b5d04b82..d8cf851ab119 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -85,6 +85,33 @@ int kvm_check_cap(long cap)
return ret;
}
+/* VM Check Capability
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * cap - Capability
+ *
+ * Output Args: None
+ *
+ * Return:
+ * On success, the Value corresponding to the capability (KVM_CAP_*)
+ * specified by the value of cap. On failure a TEST_ASSERT failure
+ * is produced.
+ *
+ * Looks up and returns the value corresponding to the capability
+ * (KVM_CAP_*) given by cap.
+ */
+int vm_check_cap(struct kvm_vm *vm, long cap)
+{
+ int ret;
+
+ ret = ioctl(vm->fd, KVM_CHECK_EXTENSION, cap);
+ TEST_ASSERT(ret >= 0, "KVM_CHECK_EXTENSION VM IOCTL failed,\n"
+ " rc: %i errno: %i", ret, errno);
+
+ return ret;
+}
+
/* VM Enable Capability
*
* Input Args:
@@ -166,12 +193,18 @@ const char *vm_guest_mode_string(uint32_t i)
[VM_MODE_P52V48_4K] = "PA-bits:52, VA-bits:48, 4K pages",
[VM_MODE_P52V48_64K] = "PA-bits:52, VA-bits:48, 64K pages",
[VM_MODE_P48V48_4K] = "PA-bits:48, VA-bits:48, 4K pages",
+ [VM_MODE_P48V48_16K] = "PA-bits:48, VA-bits:48, 16K pages",
[VM_MODE_P48V48_64K] = "PA-bits:48, VA-bits:48, 64K pages",
[VM_MODE_P40V48_4K] = "PA-bits:40, VA-bits:48, 4K pages",
+ [VM_MODE_P40V48_16K] = "PA-bits:40, VA-bits:48, 16K pages",
[VM_MODE_P40V48_64K] = "PA-bits:40, VA-bits:48, 64K pages",
[VM_MODE_PXXV48_4K] = "PA-bits:ANY, VA-bits:48, 4K pages",
[VM_MODE_P47V64_4K] = "PA-bits:47, VA-bits:64, 4K pages",
[VM_MODE_P44V64_4K] = "PA-bits:44, VA-bits:64, 4K pages",
+ [VM_MODE_P36V48_4K] = "PA-bits:36, VA-bits:48, 4K pages",
+ [VM_MODE_P36V48_16K] = "PA-bits:36, VA-bits:48, 16K pages",
+ [VM_MODE_P36V48_64K] = "PA-bits:36, VA-bits:48, 64K pages",
+ [VM_MODE_P36V47_16K] = "PA-bits:36, VA-bits:47, 16K pages",
};
_Static_assert(sizeof(strings)/sizeof(char *) == NUM_VM_MODES,
"Missing new mode strings?");
@@ -185,12 +218,18 @@ const struct vm_guest_mode_params vm_guest_mode_params[] = {
[VM_MODE_P52V48_4K] = { 52, 48, 0x1000, 12 },
[VM_MODE_P52V48_64K] = { 52, 48, 0x10000, 16 },
[VM_MODE_P48V48_4K] = { 48, 48, 0x1000, 12 },
+ [VM_MODE_P48V48_16K] = { 48, 48, 0x4000, 14 },
[VM_MODE_P48V48_64K] = { 48, 48, 0x10000, 16 },
[VM_MODE_P40V48_4K] = { 40, 48, 0x1000, 12 },
+ [VM_MODE_P40V48_16K] = { 40, 48, 0x4000, 14 },
[VM_MODE_P40V48_64K] = { 40, 48, 0x10000, 16 },
[VM_MODE_PXXV48_4K] = { 0, 0, 0x1000, 12 },
[VM_MODE_P47V64_4K] = { 47, 64, 0x1000, 12 },
[VM_MODE_P44V64_4K] = { 44, 64, 0x1000, 12 },
+ [VM_MODE_P36V48_4K] = { 36, 48, 0x1000, 12 },
+ [VM_MODE_P36V48_16K] = { 36, 48, 0x4000, 14 },
+ [VM_MODE_P36V48_64K] = { 36, 48, 0x10000, 16 },
+ [VM_MODE_P36V47_16K] = { 36, 47, 0x4000, 14 },
};
_Static_assert(sizeof(vm_guest_mode_params)/sizeof(struct vm_guest_mode_params) == NUM_VM_MODES,
"Missing new mode params?");
@@ -252,9 +291,19 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
vm->pgtable_levels = 3;
break;
case VM_MODE_P40V48_4K:
+ case VM_MODE_P36V48_4K:
vm->pgtable_levels = 4;
break;
case VM_MODE_P40V48_64K:
+ case VM_MODE_P36V48_64K:
+ vm->pgtable_levels = 3;
+ break;
+ case VM_MODE_P48V48_16K:
+ case VM_MODE_P40V48_16K:
+ case VM_MODE_P36V48_16K:
+ vm->pgtable_levels = 4;
+ break;
+ case VM_MODE_P36V47_16K:
vm->pgtable_levels = 3;
break;
case VM_MODE_PXXV48_4K:
@@ -443,9 +492,11 @@ void kvm_vm_get_dirty_log(struct kvm_vm *vm, int slot, void *log)
void kvm_vm_clear_dirty_log(struct kvm_vm *vm, int slot, void *log,
uint64_t first_page, uint32_t num_pages)
{
- struct kvm_clear_dirty_log args = { .dirty_bitmap = log, .slot = slot,
- .first_page = first_page,
- .num_pages = num_pages };
+ struct kvm_clear_dirty_log args = {
+ .dirty_bitmap = log, .slot = slot,
+ .first_page = first_page,
+ .num_pages = num_pages
+ };
int ret;
ret = ioctl(vm->fd, KVM_CLEAR_DIRTY_LOG, &args);
@@ -2087,6 +2138,78 @@ int vcpu_access_device_attr(struct kvm_vm *vm, uint32_t vcpuid, uint32_t group,
}
/*
+ * IRQ related functions.
+ */
+
+int _kvm_irq_line(struct kvm_vm *vm, uint32_t irq, int level)
+{
+ struct kvm_irq_level irq_level = {
+ .irq = irq,
+ .level = level,
+ };
+
+ return _vm_ioctl(vm, KVM_IRQ_LINE, &irq_level);
+}
+
+void kvm_irq_line(struct kvm_vm *vm, uint32_t irq, int level)
+{
+ int ret = _kvm_irq_line(vm, irq, level);
+
+ TEST_ASSERT(ret >= 0, "KVM_IRQ_LINE failed, rc: %i errno: %i", ret, errno);
+}
+
+struct kvm_irq_routing *kvm_gsi_routing_create(void)
+{
+ struct kvm_irq_routing *routing;
+ size_t size;
+
+ size = sizeof(struct kvm_irq_routing);
+ /* Allocate space for the max number of entries: this wastes 196 KBs. */
+ size += KVM_MAX_IRQ_ROUTES * sizeof(struct kvm_irq_routing_entry);
+ routing = calloc(1, size);
+ assert(routing);
+
+ return routing;
+}
+
+void kvm_gsi_routing_irqchip_add(struct kvm_irq_routing *routing,
+ uint32_t gsi, uint32_t pin)
+{
+ int i;
+
+ assert(routing);
+ assert(routing->nr < KVM_MAX_IRQ_ROUTES);
+
+ i = routing->nr;
+ routing->entries[i].gsi = gsi;
+ routing->entries[i].type = KVM_IRQ_ROUTING_IRQCHIP;
+ routing->entries[i].flags = 0;
+ routing->entries[i].u.irqchip.irqchip = 0;
+ routing->entries[i].u.irqchip.pin = pin;
+ routing->nr++;
+}
+
+int _kvm_gsi_routing_write(struct kvm_vm *vm, struct kvm_irq_routing *routing)
+{
+ int ret;
+
+ assert(routing);
+ ret = ioctl(vm_get_fd(vm), KVM_SET_GSI_ROUTING, routing);
+ free(routing);
+
+ return ret;
+}
+
+void kvm_gsi_routing_write(struct kvm_vm *vm, struct kvm_irq_routing *routing)
+{
+ int ret;
+
+ ret = _kvm_gsi_routing_write(vm, routing);
+ TEST_ASSERT(ret == 0, "KVM_SET_GSI_ROUTING failed, rc: %i errno: %i",
+ ret, errno);
+}
+
+/*
* VM Dump
*
* Input Args:
diff --git a/tools/testing/selftests/kvm/lib/riscv/processor.c b/tools/testing/selftests/kvm/lib/riscv/processor.c
new file mode 100644
index 000000000000..d377f2603d98
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/riscv/processor.c
@@ -0,0 +1,362 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * RISC-V code
+ *
+ * Copyright (C) 2021 Western Digital Corporation or its affiliates.
+ */
+
+#include <linux/compiler.h>
+#include <assert.h>
+
+#include "kvm_util.h"
+#include "../kvm_util_internal.h"
+#include "processor.h"
+
+#define DEFAULT_RISCV_GUEST_STACK_VADDR_MIN 0xac0000
+
+static uint64_t page_align(struct kvm_vm *vm, uint64_t v)
+{
+ return (v + vm->page_size) & ~(vm->page_size - 1);
+}
+
+static uint64_t pte_addr(struct kvm_vm *vm, uint64_t entry)
+{
+ return ((entry & PGTBL_PTE_ADDR_MASK) >> PGTBL_PTE_ADDR_SHIFT) <<
+ PGTBL_PAGE_SIZE_SHIFT;
+}
+
+static uint64_t ptrs_per_pte(struct kvm_vm *vm)
+{
+ return PGTBL_PAGE_SIZE / sizeof(uint64_t);
+}
+
+static uint64_t pte_index_mask[] = {
+ PGTBL_L0_INDEX_MASK,
+ PGTBL_L1_INDEX_MASK,
+ PGTBL_L2_INDEX_MASK,
+ PGTBL_L3_INDEX_MASK,
+};
+
+static uint32_t pte_index_shift[] = {
+ PGTBL_L0_INDEX_SHIFT,
+ PGTBL_L1_INDEX_SHIFT,
+ PGTBL_L2_INDEX_SHIFT,
+ PGTBL_L3_INDEX_SHIFT,
+};
+
+static uint64_t pte_index(struct kvm_vm *vm, vm_vaddr_t gva, int level)
+{
+ TEST_ASSERT(level > -1,
+ "Negative page table level (%d) not possible", level);
+ TEST_ASSERT(level < vm->pgtable_levels,
+ "Invalid page table level (%d)", level);
+
+ return (gva & pte_index_mask[level]) >> pte_index_shift[level];
+}
+
+void virt_pgd_alloc(struct kvm_vm *vm)
+{
+ if (!vm->pgd_created) {
+ vm_paddr_t paddr = vm_phy_pages_alloc(vm,
+ page_align(vm, ptrs_per_pte(vm) * 8) / vm->page_size,
+ KVM_GUEST_PAGE_TABLE_MIN_PADDR, 0);
+ vm->pgd = paddr;
+ vm->pgd_created = true;
+ }
+}
+
+void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr)
+{
+ uint64_t *ptep, next_ppn;
+ int level = vm->pgtable_levels - 1;
+
+ TEST_ASSERT((vaddr % vm->page_size) == 0,
+ "Virtual address not on page boundary,\n"
+ " vaddr: 0x%lx vm->page_size: 0x%x", vaddr, vm->page_size);
+ TEST_ASSERT(sparsebit_is_set(vm->vpages_valid,
+ (vaddr >> vm->page_shift)),
+ "Invalid virtual address, vaddr: 0x%lx", vaddr);
+ TEST_ASSERT((paddr % vm->page_size) == 0,
+ "Physical address not on page boundary,\n"
+ " paddr: 0x%lx vm->page_size: 0x%x", paddr, vm->page_size);
+ TEST_ASSERT((paddr >> vm->page_shift) <= vm->max_gfn,
+ "Physical address beyond maximum supported,\n"
+ " paddr: 0x%lx vm->max_gfn: 0x%lx vm->page_size: 0x%x",
+ paddr, vm->max_gfn, vm->page_size);
+
+ ptep = addr_gpa2hva(vm, vm->pgd) + pte_index(vm, vaddr, level) * 8;
+ if (!*ptep) {
+ next_ppn = vm_alloc_page_table(vm) >> PGTBL_PAGE_SIZE_SHIFT;
+ *ptep = (next_ppn << PGTBL_PTE_ADDR_SHIFT) |
+ PGTBL_PTE_VALID_MASK;
+ }
+ level--;
+
+ while (level > -1) {
+ ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) +
+ pte_index(vm, vaddr, level) * 8;
+ if (!*ptep && level > 0) {
+ next_ppn = vm_alloc_page_table(vm) >>
+ PGTBL_PAGE_SIZE_SHIFT;
+ *ptep = (next_ppn << PGTBL_PTE_ADDR_SHIFT) |
+ PGTBL_PTE_VALID_MASK;
+ }
+ level--;
+ }
+
+ paddr = paddr >> PGTBL_PAGE_SIZE_SHIFT;
+ *ptep = (paddr << PGTBL_PTE_ADDR_SHIFT) |
+ PGTBL_PTE_PERM_MASK | PGTBL_PTE_VALID_MASK;
+}
+
+vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva)
+{
+ uint64_t *ptep;
+ int level = vm->pgtable_levels - 1;
+
+ if (!vm->pgd_created)
+ goto unmapped_gva;
+
+ ptep = addr_gpa2hva(vm, vm->pgd) + pte_index(vm, gva, level) * 8;
+ if (!ptep)
+ goto unmapped_gva;
+ level--;
+
+ while (level > -1) {
+ ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) +
+ pte_index(vm, gva, level) * 8;
+ if (!ptep)
+ goto unmapped_gva;
+ level--;
+ }
+
+ return pte_addr(vm, *ptep) + (gva & (vm->page_size - 1));
+
+unmapped_gva:
+ TEST_FAIL("No mapping for vm virtual address gva: 0x%lx level: %d",
+ gva, level);
+ exit(1);
+}
+
+static void pte_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent,
+ uint64_t page, int level)
+{
+#ifdef DEBUG
+ static const char *const type[] = { "pte", "pmd", "pud", "p4d"};
+ uint64_t pte, *ptep;
+
+ if (level < 0)
+ return;
+
+ for (pte = page; pte < page + ptrs_per_pte(vm) * 8; pte += 8) {
+ ptep = addr_gpa2hva(vm, pte);
+ if (!*ptep)
+ continue;
+ fprintf(stream, "%*s%s: %lx: %lx at %p\n", indent, "",
+ type[level], pte, *ptep, ptep);
+ pte_dump(stream, vm, indent + 1,
+ pte_addr(vm, *ptep), level - 1);
+ }
+#endif
+}
+
+void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
+{
+ int level = vm->pgtable_levels - 1;
+ uint64_t pgd, *ptep;
+
+ if (!vm->pgd_created)
+ return;
+
+ for (pgd = vm->pgd; pgd < vm->pgd + ptrs_per_pte(vm) * 8; pgd += 8) {
+ ptep = addr_gpa2hva(vm, pgd);
+ if (!*ptep)
+ continue;
+ fprintf(stream, "%*spgd: %lx: %lx at %p\n", indent, "",
+ pgd, *ptep, ptep);
+ pte_dump(stream, vm, indent + 1,
+ pte_addr(vm, *ptep), level - 1);
+ }
+}
+
+void riscv_vcpu_mmu_setup(struct kvm_vm *vm, int vcpuid)
+{
+ unsigned long satp;
+
+ /*
+ * The RISC-V Sv48 MMU mode supports 56-bit physical address
+ * for 48-bit virtual address with 4KB last level page size.
+ */
+ switch (vm->mode) {
+ case VM_MODE_P52V48_4K:
+ case VM_MODE_P48V48_4K:
+ case VM_MODE_P40V48_4K:
+ break;
+ default:
+ TEST_FAIL("Unknown guest mode, mode: 0x%x", vm->mode);
+ }
+
+ satp = (vm->pgd >> PGTBL_PAGE_SIZE_SHIFT) & SATP_PPN;
+ satp |= SATP_MODE_48;
+
+ set_reg(vm, vcpuid, RISCV_CSR_REG(satp), satp);
+}
+
+void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid, uint8_t indent)
+{
+ struct kvm_riscv_core core;
+
+ get_reg(vm, vcpuid, RISCV_CORE_REG(mode), &core.mode);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.pc), &core.regs.pc);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.ra), &core.regs.ra);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.sp), &core.regs.sp);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.gp), &core.regs.gp);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.tp), &core.regs.tp);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.t0), &core.regs.t0);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.t1), &core.regs.t1);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.t2), &core.regs.t2);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s0), &core.regs.s0);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s1), &core.regs.s1);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.a0), &core.regs.a0);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.a1), &core.regs.a1);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.a2), &core.regs.a2);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.a3), &core.regs.a3);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.a4), &core.regs.a4);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.a5), &core.regs.a5);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.a6), &core.regs.a6);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.a7), &core.regs.a7);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s2), &core.regs.s2);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s3), &core.regs.s3);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s4), &core.regs.s4);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s5), &core.regs.s5);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s6), &core.regs.s6);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s7), &core.regs.s7);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s8), &core.regs.s8);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s9), &core.regs.s9);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s10), &core.regs.s10);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s11), &core.regs.s11);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.t3), &core.regs.t3);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.t4), &core.regs.t4);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.t5), &core.regs.t5);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.t6), &core.regs.t6);
+
+ fprintf(stream,
+ " MODE: 0x%lx\n", core.mode);
+ fprintf(stream,
+ " PC: 0x%016lx RA: 0x%016lx SP: 0x%016lx GP: 0x%016lx\n",
+ core.regs.pc, core.regs.ra, core.regs.sp, core.regs.gp);
+ fprintf(stream,
+ " TP: 0x%016lx T0: 0x%016lx T1: 0x%016lx T2: 0x%016lx\n",
+ core.regs.tp, core.regs.t0, core.regs.t1, core.regs.t2);
+ fprintf(stream,
+ " S0: 0x%016lx S1: 0x%016lx A0: 0x%016lx A1: 0x%016lx\n",
+ core.regs.s0, core.regs.s1, core.regs.a0, core.regs.a1);
+ fprintf(stream,
+ " A2: 0x%016lx A3: 0x%016lx A4: 0x%016lx A5: 0x%016lx\n",
+ core.regs.a2, core.regs.a3, core.regs.a4, core.regs.a5);
+ fprintf(stream,
+ " A6: 0x%016lx A7: 0x%016lx S2: 0x%016lx S3: 0x%016lx\n",
+ core.regs.a6, core.regs.a7, core.regs.s2, core.regs.s3);
+ fprintf(stream,
+ " S4: 0x%016lx S5: 0x%016lx S6: 0x%016lx S7: 0x%016lx\n",
+ core.regs.s4, core.regs.s5, core.regs.s6, core.regs.s7);
+ fprintf(stream,
+ " S8: 0x%016lx S9: 0x%016lx S10: 0x%016lx S11: 0x%016lx\n",
+ core.regs.s8, core.regs.s9, core.regs.s10, core.regs.s11);
+ fprintf(stream,
+ " T3: 0x%016lx T4: 0x%016lx T5: 0x%016lx T6: 0x%016lx\n",
+ core.regs.t3, core.regs.t4, core.regs.t5, core.regs.t6);
+}
+
+static void guest_hang(void)
+{
+ while (1)
+ ;
+}
+
+void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code)
+{
+ int r;
+ size_t stack_size = vm->page_size == 4096 ?
+ DEFAULT_STACK_PGS * vm->page_size :
+ vm->page_size;
+ unsigned long stack_vaddr = vm_vaddr_alloc(vm, stack_size,
+ DEFAULT_RISCV_GUEST_STACK_VADDR_MIN);
+ unsigned long current_gp = 0;
+ struct kvm_mp_state mps;
+
+ vm_vcpu_add(vm, vcpuid);
+ riscv_vcpu_mmu_setup(vm, vcpuid);
+
+ /*
+ * With SBI HSM support in KVM RISC-V, all secondary VCPUs are
+ * powered-off by default so we ensure that all secondary VCPUs
+ * are powered-on using KVM_SET_MP_STATE ioctl().
+ */
+ mps.mp_state = KVM_MP_STATE_RUNNABLE;
+ r = _vcpu_ioctl(vm, vcpuid, KVM_SET_MP_STATE, &mps);
+ TEST_ASSERT(!r, "IOCTL KVM_SET_MP_STATE failed (error %d)", r);
+
+ /* Setup global pointer of guest to be same as the host */
+ asm volatile (
+ "add %0, gp, zero" : "=r" (current_gp) : : "memory");
+ set_reg(vm, vcpuid, RISCV_CORE_REG(regs.gp), current_gp);
+
+ /* Setup stack pointer and program counter of guest */
+ set_reg(vm, vcpuid, RISCV_CORE_REG(regs.sp),
+ stack_vaddr + stack_size);
+ set_reg(vm, vcpuid, RISCV_CORE_REG(regs.pc),
+ (unsigned long)guest_code);
+
+ /* Setup default exception vector of guest */
+ set_reg(vm, vcpuid, RISCV_CSR_REG(stvec),
+ (unsigned long)guest_hang);
+}
+
+void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...)
+{
+ va_list ap;
+ uint64_t id = RISCV_CORE_REG(regs.a0);
+ int i;
+
+ TEST_ASSERT(num >= 1 && num <= 8, "Unsupported number of args,\n"
+ " num: %u\n", num);
+
+ va_start(ap, num);
+
+ for (i = 0; i < num; i++) {
+ switch (i) {
+ case 0:
+ id = RISCV_CORE_REG(regs.a0);
+ break;
+ case 1:
+ id = RISCV_CORE_REG(regs.a1);
+ break;
+ case 2:
+ id = RISCV_CORE_REG(regs.a2);
+ break;
+ case 3:
+ id = RISCV_CORE_REG(regs.a3);
+ break;
+ case 4:
+ id = RISCV_CORE_REG(regs.a4);
+ break;
+ case 5:
+ id = RISCV_CORE_REG(regs.a5);
+ break;
+ case 6:
+ id = RISCV_CORE_REG(regs.a6);
+ break;
+ case 7:
+ id = RISCV_CORE_REG(regs.a7);
+ break;
+ };
+ set_reg(vm, vcpuid, id, va_arg(ap, uint64_t));
+ }
+
+ va_end(ap);
+}
+
+void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid)
+{
+}
diff --git a/tools/testing/selftests/kvm/lib/riscv/ucall.c b/tools/testing/selftests/kvm/lib/riscv/ucall.c
new file mode 100644
index 000000000000..9e42d8248fa6
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/riscv/ucall.c
@@ -0,0 +1,87 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ucall support. A ucall is a "hypercall to userspace".
+ *
+ * Copyright (C) 2021 Western Digital Corporation or its affiliates.
+ */
+
+#include <linux/kvm.h>
+
+#include "kvm_util.h"
+#include "../kvm_util_internal.h"
+#include "processor.h"
+
+void ucall_init(struct kvm_vm *vm, void *arg)
+{
+}
+
+void ucall_uninit(struct kvm_vm *vm)
+{
+}
+
+struct sbiret sbi_ecall(int ext, int fid, unsigned long arg0,
+ unsigned long arg1, unsigned long arg2,
+ unsigned long arg3, unsigned long arg4,
+ unsigned long arg5)
+{
+ register uintptr_t a0 asm ("a0") = (uintptr_t)(arg0);
+ register uintptr_t a1 asm ("a1") = (uintptr_t)(arg1);
+ register uintptr_t a2 asm ("a2") = (uintptr_t)(arg2);
+ register uintptr_t a3 asm ("a3") = (uintptr_t)(arg3);
+ register uintptr_t a4 asm ("a4") = (uintptr_t)(arg4);
+ register uintptr_t a5 asm ("a5") = (uintptr_t)(arg5);
+ register uintptr_t a6 asm ("a6") = (uintptr_t)(fid);
+ register uintptr_t a7 asm ("a7") = (uintptr_t)(ext);
+ struct sbiret ret;
+
+ asm volatile (
+ "ecall"
+ : "+r" (a0), "+r" (a1)
+ : "r" (a2), "r" (a3), "r" (a4), "r" (a5), "r" (a6), "r" (a7)
+ : "memory");
+ ret.error = a0;
+ ret.value = a1;
+
+ return ret;
+}
+
+void ucall(uint64_t cmd, int nargs, ...)
+{
+ struct ucall uc = {
+ .cmd = cmd,
+ };
+ va_list va;
+ int i;
+
+ nargs = nargs <= UCALL_MAX_ARGS ? nargs : UCALL_MAX_ARGS;
+
+ va_start(va, nargs);
+ for (i = 0; i < nargs; ++i)
+ uc.args[i] = va_arg(va, uint64_t);
+ va_end(va);
+
+ sbi_ecall(KVM_RISCV_SELFTESTS_SBI_EXT, 0, (vm_vaddr_t)&uc,
+ 0, 0, 0, 0, 0);
+}
+
+uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc)
+{
+ struct kvm_run *run = vcpu_state(vm, vcpu_id);
+ struct ucall ucall = {};
+
+ if (uc)
+ memset(uc, 0, sizeof(*uc));
+
+ if (run->exit_reason == KVM_EXIT_RISCV_SBI &&
+ run->riscv_sbi.extension_id == KVM_RISCV_SELFTESTS_SBI_EXT &&
+ run->riscv_sbi.function_id == 0) {
+ memcpy(&ucall, addr_gva2hva(vm, run->riscv_sbi.args[0]),
+ sizeof(ucall));
+
+ vcpu_run_complete_io(vm, vcpu_id);
+ if (uc)
+ memcpy(uc, &ucall, sizeof(ucall));
+ }
+
+ return ucall.cmd;
+}
diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c
index eef7b34756d5..9f000dfb5594 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c
@@ -650,6 +650,60 @@ static void vcpu_setup(struct kvm_vm *vm, int vcpuid)
vcpu_sregs_set(vm, vcpuid, &sregs);
}
+#define CPUID_XFD_BIT (1 << 4)
+static bool is_xfd_supported(void)
+{
+ int eax, ebx, ecx, edx;
+ const int leaf = 0xd, subleaf = 0x1;
+
+ __asm__ __volatile__(
+ "cpuid"
+ : /* output */ "=a"(eax), "=b"(ebx),
+ "=c"(ecx), "=d"(edx)
+ : /* input */ "0"(leaf), "2"(subleaf));
+
+ return !!(eax & CPUID_XFD_BIT);
+}
+
+void vm_xsave_req_perm(int bit)
+{
+ int kvm_fd;
+ u64 bitmask;
+ long rc;
+ struct kvm_device_attr attr = {
+ .group = 0,
+ .attr = KVM_X86_XCOMP_GUEST_SUPP,
+ .addr = (unsigned long) &bitmask
+ };
+
+ kvm_fd = open_kvm_dev_path_or_exit();
+ rc = ioctl(kvm_fd, KVM_GET_DEVICE_ATTR, &attr);
+ close(kvm_fd);
+ if (rc == -1 && (errno == ENXIO || errno == EINVAL))
+ exit(KSFT_SKIP);
+ TEST_ASSERT(rc == 0, "KVM_GET_DEVICE_ATTR(0, KVM_X86_XCOMP_GUEST_SUPP) error: %ld", rc);
+ if (!(bitmask & (1ULL << bit)))
+ exit(KSFT_SKIP);
+
+ if (!is_xfd_supported())
+ exit(KSFT_SKIP);
+
+ rc = syscall(SYS_arch_prctl, ARCH_REQ_XCOMP_GUEST_PERM, bit);
+
+ /*
+ * The older kernel version(<5.15) can't support
+ * ARCH_REQ_XCOMP_GUEST_PERM and directly return.
+ */
+ if (rc)
+ return;
+
+ rc = syscall(SYS_arch_prctl, ARCH_GET_XCOMP_GUEST_PERM, &bitmask);
+ TEST_ASSERT(rc == 0, "prctl(ARCH_GET_XCOMP_GUEST_PERM) error: %ld", rc);
+ TEST_ASSERT(bitmask & (1ULL << bit),
+ "prctl(ARCH_REQ_XCOMP_GUEST_PERM) failure bitmask=0x%lx",
+ bitmask);
+}
+
void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code)
{
struct kvm_mp_state mp_state;
@@ -847,6 +901,17 @@ kvm_get_supported_cpuid_index(uint32_t function, uint32_t index)
return entry;
}
+
+int __vcpu_set_cpuid(struct kvm_vm *vm, uint32_t vcpuid,
+ struct kvm_cpuid2 *cpuid)
+{
+ struct vcpu *vcpu = vcpu_find(vm, vcpuid);
+
+ TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
+
+ return ioctl(vcpu->fd, KVM_SET_CPUID2, cpuid);
+}
+
/*
* VM VCPU CPUID Set
*
@@ -864,12 +929,9 @@ kvm_get_supported_cpuid_index(uint32_t function, uint32_t index)
void vcpu_set_cpuid(struct kvm_vm *vm,
uint32_t vcpuid, struct kvm_cpuid2 *cpuid)
{
- struct vcpu *vcpu = vcpu_find(vm, vcpuid);
int rc;
- TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
-
- rc = ioctl(vcpu->fd, KVM_SET_CPUID2, cpuid);
+ rc = __vcpu_set_cpuid(vm, vcpuid, cpuid);
TEST_ASSERT(rc == 0, "KVM_SET_CPUID2 failed, rc: %i errno: %i",
rc, errno);
@@ -1017,21 +1079,6 @@ void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid, uint8_t indent)
sregs_dump(stream, &sregs, indent + 4);
}
-struct kvm_x86_state {
- struct kvm_vcpu_events events;
- struct kvm_mp_state mp_state;
- struct kvm_regs regs;
- struct kvm_xsave xsave;
- struct kvm_xcrs xcrs;
- struct kvm_sregs sregs;
- struct kvm_debugregs debugregs;
- union {
- struct kvm_nested_state nested;
- char nested_[16384];
- };
- struct kvm_msrs msrs;
-};
-
static int kvm_get_num_msrs_fd(int kvm_fd)
{
struct kvm_msr_list nmsrs;
@@ -1069,6 +1116,22 @@ struct kvm_msr_list *kvm_get_msr_index_list(void)
return list;
}
+static int vcpu_save_xsave_state(struct kvm_vm *vm, struct vcpu *vcpu,
+ struct kvm_x86_state *state)
+{
+ int size;
+
+ size = vm_check_cap(vm, KVM_CAP_XSAVE2);
+ if (!size)
+ size = sizeof(struct kvm_xsave);
+
+ state->xsave = malloc(size);
+ if (size == sizeof(struct kvm_xsave))
+ return ioctl(vcpu->fd, KVM_GET_XSAVE, state->xsave);
+ else
+ return ioctl(vcpu->fd, KVM_GET_XSAVE2, state->xsave);
+}
+
struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid)
{
struct vcpu *vcpu = vcpu_find(vm, vcpuid);
@@ -1096,25 +1159,25 @@ struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid)
list = malloc(sizeof(*list) + nmsrs * sizeof(list->indices[0]));
list->nmsrs = nmsrs;
r = ioctl(vm->kvm_fd, KVM_GET_MSR_INDEX_LIST, list);
- TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_MSR_INDEX_LIST, r: %i",
- r);
+ TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_MSR_INDEX_LIST, r: %i",
+ r);
state = malloc(sizeof(*state) + nmsrs * sizeof(state->msrs.entries[0]));
r = ioctl(vcpu->fd, KVM_GET_VCPU_EVENTS, &state->events);
- TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_VCPU_EVENTS, r: %i",
- r);
+ TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_VCPU_EVENTS, r: %i",
+ r);
r = ioctl(vcpu->fd, KVM_GET_MP_STATE, &state->mp_state);
- TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_MP_STATE, r: %i",
- r);
+ TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_MP_STATE, r: %i",
+ r);
r = ioctl(vcpu->fd, KVM_GET_REGS, &state->regs);
- TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_REGS, r: %i",
- r);
+ TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_REGS, r: %i",
+ r);
- r = ioctl(vcpu->fd, KVM_GET_XSAVE, &state->xsave);
- TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_XSAVE, r: %i",
- r);
+ r = vcpu_save_xsave_state(vm, vcpu, state);
+ TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_XSAVE, r: %i",
+ r);
if (kvm_check_cap(KVM_CAP_XCRS)) {
r = ioctl(vcpu->fd, KVM_GET_XCRS, &state->xcrs);
@@ -1123,17 +1186,17 @@ struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid)
}
r = ioctl(vcpu->fd, KVM_GET_SREGS, &state->sregs);
- TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_SREGS, r: %i",
- r);
+ TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_SREGS, r: %i",
+ r);
if (nested_size) {
state->nested.size = sizeof(state->nested_);
r = ioctl(vcpu->fd, KVM_GET_NESTED_STATE, &state->nested);
TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_NESTED_STATE, r: %i",
- r);
+ r);
TEST_ASSERT(state->nested.size <= nested_size,
- "Nested state size too big, %i (KVM_CHECK_CAP gave %i)",
- state->nested.size, nested_size);
+ "Nested state size too big, %i (KVM_CHECK_CAP gave %i)",
+ state->nested.size, nested_size);
} else
state->nested.size = 0;
@@ -1141,12 +1204,12 @@ struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid)
for (i = 0; i < nmsrs; i++)
state->msrs.entries[i].index = list->indices[i];
r = ioctl(vcpu->fd, KVM_GET_MSRS, &state->msrs);
- TEST_ASSERT(r == nmsrs, "Unexpected result from KVM_GET_MSRS, r: %i (failed MSR was 0x%x)",
- r, r == nmsrs ? -1 : list->indices[r]);
+ TEST_ASSERT(r == nmsrs, "Unexpected result from KVM_GET_MSRS, r: %i (failed MSR was 0x%x)",
+ r, r == nmsrs ? -1 : list->indices[r]);
r = ioctl(vcpu->fd, KVM_GET_DEBUGREGS, &state->debugregs);
- TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_DEBUGREGS, r: %i",
- r);
+ TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_DEBUGREGS, r: %i",
+ r);
free(list);
return state;
@@ -1157,9 +1220,14 @@ void vcpu_load_state(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_x86_state *s
struct vcpu *vcpu = vcpu_find(vm, vcpuid);
int r;
- r = ioctl(vcpu->fd, KVM_SET_XSAVE, &state->xsave);
- TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_XSAVE, r: %i",
- r);
+ r = ioctl(vcpu->fd, KVM_SET_SREGS, &state->sregs);
+ TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_SREGS, r: %i",
+ r);
+
+ r = ioctl(vcpu->fd, KVM_SET_MSRS, &state->msrs);
+ TEST_ASSERT(r == state->msrs.nmsrs,
+ "Unexpected result from KVM_SET_MSRS, r: %i (failed at %x)",
+ r, r == state->msrs.nmsrs ? -1 : state->msrs.entries[r].index);
if (kvm_check_cap(KVM_CAP_XCRS)) {
r = ioctl(vcpu->fd, KVM_SET_XCRS, &state->xcrs);
@@ -1167,41 +1235,43 @@ void vcpu_load_state(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_x86_state *s
r);
}
- r = ioctl(vcpu->fd, KVM_SET_SREGS, &state->sregs);
- TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_SREGS, r: %i",
- r);
-
- r = ioctl(vcpu->fd, KVM_SET_MSRS, &state->msrs);
- TEST_ASSERT(r == state->msrs.nmsrs, "Unexpected result from KVM_SET_MSRS, r: %i (failed at %x)",
- r, r == state->msrs.nmsrs ? -1 : state->msrs.entries[r].index);
+ r = ioctl(vcpu->fd, KVM_SET_XSAVE, state->xsave);
+ TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_XSAVE, r: %i",
+ r);
r = ioctl(vcpu->fd, KVM_SET_VCPU_EVENTS, &state->events);
- TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_VCPU_EVENTS, r: %i",
- r);
+ TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_VCPU_EVENTS, r: %i",
+ r);
r = ioctl(vcpu->fd, KVM_SET_MP_STATE, &state->mp_state);
- TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_MP_STATE, r: %i",
- r);
+ TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_MP_STATE, r: %i",
+ r);
r = ioctl(vcpu->fd, KVM_SET_DEBUGREGS, &state->debugregs);
- TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_DEBUGREGS, r: %i",
- r);
+ TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_DEBUGREGS, r: %i",
+ r);
r = ioctl(vcpu->fd, KVM_SET_REGS, &state->regs);
- TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_REGS, r: %i",
- r);
+ TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_REGS, r: %i",
+ r);
if (state->nested.size) {
r = ioctl(vcpu->fd, KVM_SET_NESTED_STATE, &state->nested);
TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_NESTED_STATE, r: %i",
- r);
+ r);
}
}
-bool is_intel_cpu(void)
+void kvm_x86_state_cleanup(struct kvm_x86_state *state)
+{
+ free(state->xsave);
+ free(state);
+}
+
+static bool cpu_vendor_string_is(const char *vendor)
{
+ const uint32_t *chunk = (const uint32_t *)vendor;
int eax, ebx, ecx, edx;
- const uint32_t *chunk;
const int leaf = 0;
__asm__ __volatile__(
@@ -1210,10 +1280,22 @@ bool is_intel_cpu(void)
"=c"(ecx), "=d"(edx)
: /* input */ "0"(leaf), "2"(0));
- chunk = (const uint32_t *)("GenuineIntel");
return (ebx == chunk[0] && edx == chunk[1] && ecx == chunk[2]);
}
+bool is_intel_cpu(void)
+{
+ return cpu_vendor_string_is("GenuineIntel");
+}
+
+/*
+ * Exclude early K5 samples with a vendor string of "AMDisbetter!"
+ */
+bool is_amd_cpu(void)
+{
+ return cpu_vendor_string_is("AuthenticAMD");
+}
+
uint32_t kvm_get_cpuid_max_basic(void)
{
return kvm_get_supported_cpuid_entry(0)->eax;
@@ -1337,6 +1419,23 @@ void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid)
}
}
+struct kvm_cpuid_entry2 *get_cpuid(struct kvm_cpuid2 *cpuid, uint32_t function,
+ uint32_t index)
+{
+ int i;
+
+ for (i = 0; i < cpuid->nent; i++) {
+ struct kvm_cpuid_entry2 *cur = &cpuid->entries[i];
+
+ if (cur->function == function && cur->index == index)
+ return cur;
+ }
+
+ TEST_FAIL("CPUID function 0x%x index 0x%x not found ", function, index);
+
+ return NULL;
+}
+
bool set_cpuid(struct kvm_cpuid2 *cpuid,
struct kvm_cpuid_entry2 *ent)
{
@@ -1432,22 +1531,6 @@ struct kvm_cpuid2 *vcpu_get_supported_hv_cpuid(struct kvm_vm *vm, uint32_t vcpui
return cpuid;
}
-#define X86EMUL_CPUID_VENDOR_AuthenticAMD_ebx 0x68747541
-#define X86EMUL_CPUID_VENDOR_AuthenticAMD_ecx 0x444d4163
-#define X86EMUL_CPUID_VENDOR_AuthenticAMD_edx 0x69746e65
-
-static inline unsigned x86_family(unsigned int eax)
-{
- unsigned int x86;
-
- x86 = (eax >> 8) & 0xf;
-
- if (x86 == 0xf)
- x86 += (eax >> 20) & 0xff;
-
- return x86;
-}
-
unsigned long vm_compute_max_gfn(struct kvm_vm *vm)
{
const unsigned long num_ht_pages = 12 << (30 - vm->page_shift); /* 12 GiB */
@@ -1457,11 +1540,7 @@ unsigned long vm_compute_max_gfn(struct kvm_vm *vm)
max_gfn = (1ULL << (vm->pa_bits - vm->page_shift)) - 1;
/* Avoid reserved HyperTransport region on AMD processors. */
- eax = ecx = 0;
- cpuid(&eax, &ebx, &ecx, &edx);
- if (ebx != X86EMUL_CPUID_VENDOR_AuthenticAMD_ebx ||
- ecx != X86EMUL_CPUID_VENDOR_AuthenticAMD_ecx ||
- edx != X86EMUL_CPUID_VENDOR_AuthenticAMD_edx)
+ if (!is_amd_cpu())
return max_gfn;
/* On parts with <40 physical address bits, the area is fully hidden */
@@ -1471,6 +1550,7 @@ unsigned long vm_compute_max_gfn(struct kvm_vm *vm)
/* Before family 17h, the HyperTransport area is just below 1T. */
ht_gfn = (1 << 28) - num_ht_pages;
eax = 1;
+ ecx = 0;
cpuid(&eax, &ebx, &ecx, &edx);
if (x86_family(eax) < 0x17)
goto done;
diff --git a/tools/testing/selftests/kvm/x86_64/amx_test.c b/tools/testing/selftests/kvm/x86_64/amx_test.c
new file mode 100644
index 000000000000..52a3ef6629e8
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/amx_test.c
@@ -0,0 +1,450 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * amx tests
+ *
+ * Copyright (C) 2021, Intel, Inc.
+ *
+ * Tests for amx #NM exception and save/restore.
+ */
+
+#define _GNU_SOURCE /* for program_invocation_short_name */
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <sys/syscall.h>
+
+#include "test_util.h"
+
+#include "kvm_util.h"
+#include "processor.h"
+#include "vmx.h"
+
+#ifndef __x86_64__
+# error This test is 64-bit only
+#endif
+
+#define VCPU_ID 0
+#define X86_FEATURE_XSAVE (1 << 26)
+#define X86_FEATURE_OSXSAVE (1 << 27)
+
+#define PAGE_SIZE (1 << 12)
+#define NUM_TILES 8
+#define TILE_SIZE 1024
+#define XSAVE_SIZE ((NUM_TILES * TILE_SIZE) + PAGE_SIZE)
+
+/* Tile configuration associated: */
+#define MAX_TILES 16
+#define RESERVED_BYTES 14
+
+#define XFEATURE_XTILECFG 17
+#define XFEATURE_XTILEDATA 18
+#define XFEATURE_MASK_XTILECFG (1 << XFEATURE_XTILECFG)
+#define XFEATURE_MASK_XTILEDATA (1 << XFEATURE_XTILEDATA)
+#define XFEATURE_MASK_XTILE (XFEATURE_MASK_XTILECFG | XFEATURE_MASK_XTILEDATA)
+
+#define TILE_CPUID 0x1d
+#define XSTATE_CPUID 0xd
+#define TILE_PALETTE_CPUID_SUBLEAVE 0x1
+#define XSTATE_USER_STATE_SUBLEAVE 0x0
+
+#define XSAVE_HDR_OFFSET 512
+
+struct xsave_data {
+ u8 area[XSAVE_SIZE];
+} __aligned(64);
+
+struct tile_config {
+ u8 palette_id;
+ u8 start_row;
+ u8 reserved[RESERVED_BYTES];
+ u16 colsb[MAX_TILES];
+ u8 rows[MAX_TILES];
+};
+
+struct tile_data {
+ u8 data[NUM_TILES * TILE_SIZE];
+};
+
+struct xtile_info {
+ u16 bytes_per_tile;
+ u16 bytes_per_row;
+ u16 max_names;
+ u16 max_rows;
+ u32 xsave_offset;
+ u32 xsave_size;
+};
+
+static struct xtile_info xtile;
+
+static inline u64 __xgetbv(u32 index)
+{
+ u32 eax, edx;
+
+ asm volatile("xgetbv;"
+ : "=a" (eax), "=d" (edx)
+ : "c" (index));
+ return eax + ((u64)edx << 32);
+}
+
+static inline void __xsetbv(u32 index, u64 value)
+{
+ u32 eax = value;
+ u32 edx = value >> 32;
+
+ asm volatile("xsetbv" :: "a" (eax), "d" (edx), "c" (index));
+}
+
+static inline void __ldtilecfg(void *cfg)
+{
+ asm volatile(".byte 0xc4,0xe2,0x78,0x49,0x00"
+ : : "a"(cfg));
+}
+
+static inline void __tileloadd(void *tile)
+{
+ asm volatile(".byte 0xc4,0xe2,0x7b,0x4b,0x04,0x10"
+ : : "a"(tile), "d"(0));
+}
+
+static inline void __tilerelease(void)
+{
+ asm volatile(".byte 0xc4, 0xe2, 0x78, 0x49, 0xc0" ::);
+}
+
+static inline void __xsavec(struct xsave_data *data, uint64_t rfbm)
+{
+ uint32_t rfbm_lo = rfbm;
+ uint32_t rfbm_hi = rfbm >> 32;
+
+ asm volatile("xsavec (%%rdi)"
+ : : "D" (data), "a" (rfbm_lo), "d" (rfbm_hi)
+ : "memory");
+}
+
+static inline void check_cpuid_xsave(void)
+{
+ uint32_t eax, ebx, ecx, edx;
+
+ eax = 1;
+ ecx = 0;
+ cpuid(&eax, &ebx, &ecx, &edx);
+ if (!(ecx & X86_FEATURE_XSAVE))
+ GUEST_ASSERT(!"cpuid: no CPU xsave support!");
+ if (!(ecx & X86_FEATURE_OSXSAVE))
+ GUEST_ASSERT(!"cpuid: no OS xsave support!");
+}
+
+static bool check_xsave_supports_xtile(void)
+{
+ return __xgetbv(0) & XFEATURE_MASK_XTILE;
+}
+
+static bool enum_xtile_config(void)
+{
+ u32 eax, ebx, ecx, edx;
+
+ eax = TILE_CPUID;
+ ecx = TILE_PALETTE_CPUID_SUBLEAVE;
+
+ cpuid(&eax, &ebx, &ecx, &edx);
+ if (!eax || !ebx || !ecx)
+ return false;
+
+ xtile.max_names = ebx >> 16;
+ if (xtile.max_names < NUM_TILES)
+ return false;
+
+ xtile.bytes_per_tile = eax >> 16;
+ if (xtile.bytes_per_tile < TILE_SIZE)
+ return false;
+
+ xtile.bytes_per_row = ebx;
+ xtile.max_rows = ecx;
+
+ return true;
+}
+
+static bool enum_xsave_tile(void)
+{
+ u32 eax, ebx, ecx, edx;
+
+ eax = XSTATE_CPUID;
+ ecx = XFEATURE_XTILEDATA;
+
+ cpuid(&eax, &ebx, &ecx, &edx);
+ if (!eax || !ebx)
+ return false;
+
+ xtile.xsave_offset = ebx;
+ xtile.xsave_size = eax;
+
+ return true;
+}
+
+static bool check_xsave_size(void)
+{
+ u32 eax, ebx, ecx, edx;
+ bool valid = false;
+
+ eax = XSTATE_CPUID;
+ ecx = XSTATE_USER_STATE_SUBLEAVE;
+
+ cpuid(&eax, &ebx, &ecx, &edx);
+ if (ebx && ebx <= XSAVE_SIZE)
+ valid = true;
+
+ return valid;
+}
+
+static bool check_xtile_info(void)
+{
+ bool ret = false;
+
+ if (!check_xsave_size())
+ return ret;
+
+ if (!enum_xsave_tile())
+ return ret;
+
+ if (!enum_xtile_config())
+ return ret;
+
+ if (sizeof(struct tile_data) >= xtile.xsave_size)
+ ret = true;
+
+ return ret;
+}
+
+static void set_tilecfg(struct tile_config *cfg)
+{
+ int i;
+
+ /* Only palette id 1 */
+ cfg->palette_id = 1;
+ for (i = 0; i < xtile.max_names; i++) {
+ cfg->colsb[i] = xtile.bytes_per_row;
+ cfg->rows[i] = xtile.max_rows;
+ }
+}
+
+static void set_xstatebv(void *data, uint64_t bv)
+{
+ *(uint64_t *)(data + XSAVE_HDR_OFFSET) = bv;
+}
+
+static u64 get_xstatebv(void *data)
+{
+ return *(u64 *)(data + XSAVE_HDR_OFFSET);
+}
+
+static void init_regs(void)
+{
+ uint64_t cr4, xcr0;
+
+ /* turn on CR4.OSXSAVE */
+ cr4 = get_cr4();
+ cr4 |= X86_CR4_OSXSAVE;
+ set_cr4(cr4);
+
+ xcr0 = __xgetbv(0);
+ xcr0 |= XFEATURE_MASK_XTILE;
+ __xsetbv(0x0, xcr0);
+}
+
+static void __attribute__((__flatten__)) guest_code(struct tile_config *amx_cfg,
+ struct tile_data *tiledata,
+ struct xsave_data *xsave_data)
+{
+ init_regs();
+ check_cpuid_xsave();
+ GUEST_ASSERT(check_xsave_supports_xtile());
+ GUEST_ASSERT(check_xtile_info());
+
+ /* check xtile configs */
+ GUEST_ASSERT(xtile.xsave_offset == 2816);
+ GUEST_ASSERT(xtile.xsave_size == 8192);
+ GUEST_ASSERT(xtile.max_names == 8);
+ GUEST_ASSERT(xtile.bytes_per_tile == 1024);
+ GUEST_ASSERT(xtile.bytes_per_row == 64);
+ GUEST_ASSERT(xtile.max_rows == 16);
+ GUEST_SYNC(1);
+
+ /* xfd=0, enable amx */
+ wrmsr(MSR_IA32_XFD, 0);
+ GUEST_SYNC(2);
+ GUEST_ASSERT(rdmsr(MSR_IA32_XFD) == 0);
+ set_tilecfg(amx_cfg);
+ __ldtilecfg(amx_cfg);
+ GUEST_SYNC(3);
+ /* Check save/restore when trap to userspace */
+ __tileloadd(tiledata);
+ GUEST_SYNC(4);
+ __tilerelease();
+ GUEST_SYNC(5);
+ /* bit 18 not in the XCOMP_BV after xsavec() */
+ set_xstatebv(xsave_data, XFEATURE_MASK_XTILEDATA);
+ __xsavec(xsave_data, XFEATURE_MASK_XTILEDATA);
+ GUEST_ASSERT((get_xstatebv(xsave_data) & XFEATURE_MASK_XTILEDATA) == 0);
+
+ /* xfd=0x40000, disable amx tiledata */
+ wrmsr(MSR_IA32_XFD, XFEATURE_MASK_XTILEDATA);
+ GUEST_SYNC(6);
+ GUEST_ASSERT(rdmsr(MSR_IA32_XFD) == XFEATURE_MASK_XTILEDATA);
+ set_tilecfg(amx_cfg);
+ __ldtilecfg(amx_cfg);
+ /* Trigger #NM exception */
+ __tileloadd(tiledata);
+ GUEST_SYNC(10);
+
+ GUEST_DONE();
+}
+
+void guest_nm_handler(struct ex_regs *regs)
+{
+ /* Check if #NM is triggered by XFEATURE_MASK_XTILEDATA */
+ GUEST_SYNC(7);
+ GUEST_ASSERT(rdmsr(MSR_IA32_XFD_ERR) == XFEATURE_MASK_XTILEDATA);
+ GUEST_SYNC(8);
+ GUEST_ASSERT(rdmsr(MSR_IA32_XFD_ERR) == XFEATURE_MASK_XTILEDATA);
+ /* Clear xfd_err */
+ wrmsr(MSR_IA32_XFD_ERR, 0);
+ /* xfd=0, enable amx */
+ wrmsr(MSR_IA32_XFD, 0);
+ GUEST_SYNC(9);
+}
+
+int main(int argc, char *argv[])
+{
+ struct kvm_cpuid_entry2 *entry;
+ struct kvm_regs regs1, regs2;
+ bool amx_supported = false;
+ struct kvm_vm *vm;
+ struct kvm_run *run;
+ struct kvm_x86_state *state;
+ int xsave_restore_size = 0;
+ vm_vaddr_t amx_cfg, tiledata, xsavedata;
+ struct ucall uc;
+ u32 amx_offset;
+ int stage, ret;
+
+ vm_xsave_req_perm(XSTATE_XTILE_DATA_BIT);
+
+ /* Create VM */
+ vm = vm_create_default(VCPU_ID, 0, guest_code);
+
+ entry = kvm_get_supported_cpuid_entry(1);
+ if (!(entry->ecx & X86_FEATURE_XSAVE)) {
+ print_skip("XSAVE feature not supported");
+ exit(KSFT_SKIP);
+ }
+
+ if (kvm_get_cpuid_max_basic() >= 0xd) {
+ entry = kvm_get_supported_cpuid_index(0xd, 0);
+ amx_supported = entry && !!(entry->eax & XFEATURE_MASK_XTILE);
+ if (!amx_supported) {
+ print_skip("AMX is not supported by the vCPU (eax=0x%x)", entry->eax);
+ exit(KSFT_SKIP);
+ }
+ /* Get xsave/restore max size */
+ xsave_restore_size = entry->ecx;
+ }
+
+ run = vcpu_state(vm, VCPU_ID);
+ vcpu_regs_get(vm, VCPU_ID, &regs1);
+
+ /* Register #NM handler */
+ vm_init_descriptor_tables(vm);
+ vcpu_init_descriptor_tables(vm, VCPU_ID);
+ vm_install_exception_handler(vm, NM_VECTOR, guest_nm_handler);
+
+ /* amx cfg for guest_code */
+ amx_cfg = vm_vaddr_alloc_page(vm);
+ memset(addr_gva2hva(vm, amx_cfg), 0x0, getpagesize());
+
+ /* amx tiledata for guest_code */
+ tiledata = vm_vaddr_alloc_pages(vm, 2);
+ memset(addr_gva2hva(vm, tiledata), rand() | 1, 2 * getpagesize());
+
+ /* xsave data for guest_code */
+ xsavedata = vm_vaddr_alloc_pages(vm, 3);
+ memset(addr_gva2hva(vm, xsavedata), 0, 3 * getpagesize());
+ vcpu_args_set(vm, VCPU_ID, 3, amx_cfg, tiledata, xsavedata);
+
+ for (stage = 1; ; stage++) {
+ _vcpu_run(vm, VCPU_ID);
+ TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+ "Stage %d: unexpected exit reason: %u (%s),\n",
+ stage, run->exit_reason,
+ exit_reason_str(run->exit_reason));
+
+ switch (get_ucall(vm, VCPU_ID, &uc)) {
+ case UCALL_ABORT:
+ TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0],
+ __FILE__, uc.args[1]);
+ /* NOT REACHED */
+ case UCALL_SYNC:
+ switch (uc.args[1]) {
+ case 1:
+ case 2:
+ case 3:
+ case 5:
+ case 6:
+ case 7:
+ case 8:
+ fprintf(stderr, "GUEST_SYNC(%ld)\n", uc.args[1]);
+ break;
+ case 4:
+ case 10:
+ fprintf(stderr,
+ "GUEST_SYNC(%ld), check save/restore status\n", uc.args[1]);
+
+ /* Compacted mode, get amx offset by xsave area
+ * size subtract 8K amx size.
+ */
+ amx_offset = xsave_restore_size - NUM_TILES*TILE_SIZE;
+ state = vcpu_save_state(vm, VCPU_ID);
+ void *amx_start = (void *)state->xsave + amx_offset;
+ void *tiles_data = (void *)addr_gva2hva(vm, tiledata);
+ /* Only check TMM0 register, 1 tile */
+ ret = memcmp(amx_start, tiles_data, TILE_SIZE);
+ TEST_ASSERT(ret == 0, "memcmp failed, ret=%d\n", ret);
+ kvm_x86_state_cleanup(state);
+ break;
+ case 9:
+ fprintf(stderr,
+ "GUEST_SYNC(%ld), #NM exception and enable amx\n", uc.args[1]);
+ break;
+ }
+ break;
+ case UCALL_DONE:
+ fprintf(stderr, "UCALL_DONE\n");
+ goto done;
+ default:
+ TEST_FAIL("Unknown ucall %lu", uc.cmd);
+ }
+
+ state = vcpu_save_state(vm, VCPU_ID);
+ memset(&regs1, 0, sizeof(regs1));
+ vcpu_regs_get(vm, VCPU_ID, &regs1);
+
+ kvm_vm_release(vm);
+
+ /* Restore state in a new VM. */
+ kvm_vm_restart(vm, O_RDWR);
+ vm_vcpu_add(vm, VCPU_ID);
+ vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
+ vcpu_load_state(vm, VCPU_ID, state);
+ run = vcpu_state(vm, VCPU_ID);
+ kvm_x86_state_cleanup(state);
+
+ memset(&regs2, 0, sizeof(regs2));
+ vcpu_regs_get(vm, VCPU_ID, &regs2);
+ TEST_ASSERT(!memcmp(&regs1, &regs2, sizeof(regs2)),
+ "Unexpected register values after vcpu_load_state; rdi: %lx rsi: %lx",
+ (ulong) regs2.rdi, (ulong) regs2.rsi);
+ }
+done:
+ kvm_vm_free(vm);
+}
diff --git a/tools/testing/selftests/kvm/x86_64/get_cpuid_test.c b/tools/testing/selftests/kvm/x86_64/cpuid_test.c
index a711f83749ea..16d2465c5634 100644
--- a/tools/testing/selftests/kvm/x86_64/get_cpuid_test.c
+++ b/tools/testing/selftests/kvm/x86_64/cpuid_test.c
@@ -154,6 +154,34 @@ struct kvm_cpuid2 *vcpu_alloc_cpuid(struct kvm_vm *vm, vm_vaddr_t *p_gva, struct
return guest_cpuids;
}
+static void set_cpuid_after_run(struct kvm_vm *vm, struct kvm_cpuid2 *cpuid)
+{
+ struct kvm_cpuid_entry2 *ent;
+ int rc;
+ u32 eax, ebx, x;
+
+ /* Setting unmodified CPUID is allowed */
+ rc = __vcpu_set_cpuid(vm, VCPU_ID, cpuid);
+ TEST_ASSERT(!rc, "Setting unmodified CPUID after KVM_RUN failed: %d", rc);
+
+ /* Changing CPU features is forbidden */
+ ent = get_cpuid(cpuid, 0x7, 0);
+ ebx = ent->ebx;
+ ent->ebx--;
+ rc = __vcpu_set_cpuid(vm, VCPU_ID, cpuid);
+ TEST_ASSERT(rc, "Changing CPU features should fail");
+ ent->ebx = ebx;
+
+ /* Changing MAXPHYADDR is forbidden */
+ ent = get_cpuid(cpuid, 0x80000008, 0);
+ eax = ent->eax;
+ x = eax & 0xff;
+ ent->eax = (eax & ~0xffu) | (x - 1);
+ rc = __vcpu_set_cpuid(vm, VCPU_ID, cpuid);
+ TEST_ASSERT(rc, "Changing MAXPHYADDR should fail");
+ ent->eax = eax;
+}
+
int main(void)
{
struct kvm_cpuid2 *supp_cpuid, *cpuid2;
@@ -175,5 +203,7 @@ int main(void)
for (stage = 0; stage < 3; stage++)
run_vcpu(vm, VCPU_ID, stage);
+ set_cpuid_after_run(vm, cpuid2);
+
kvm_vm_free(vm);
}
diff --git a/tools/testing/selftests/kvm/x86_64/evmcs_test.c b/tools/testing/selftests/kvm/x86_64/evmcs_test.c
index 2b46dcca86a8..4c7841dfd481 100644
--- a/tools/testing/selftests/kvm/x86_64/evmcs_test.c
+++ b/tools/testing/selftests/kvm/x86_64/evmcs_test.c
@@ -129,7 +129,7 @@ static void save_restore_vm(struct kvm_vm *vm)
vcpu_set_hv_cpuid(vm, VCPU_ID);
vcpu_enable_evmcs(vm, VCPU_ID);
vcpu_load_state(vm, VCPU_ID, state);
- free(state);
+ kvm_x86_state_cleanup(state);
memset(&regs2, 0, sizeof(regs2));
vcpu_regs_get(vm, VCPU_ID, &regs2);
diff --git a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c
new file mode 100644
index 000000000000..c715adcbd487
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c
@@ -0,0 +1,434 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Test for x86 KVM_SET_PMU_EVENT_FILTER.
+ *
+ * Copyright (C) 2022, Google LLC.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ *
+ * Verifies the expected behavior of allow lists and deny lists for
+ * virtual PMU events.
+ */
+
+#define _GNU_SOURCE /* for program_invocation_short_name */
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+
+/*
+ * In lieu of copying perf_event.h into tools...
+ */
+#define ARCH_PERFMON_EVENTSEL_OS (1ULL << 17)
+#define ARCH_PERFMON_EVENTSEL_ENABLE (1ULL << 22)
+
+union cpuid10_eax {
+ struct {
+ unsigned int version_id:8;
+ unsigned int num_counters:8;
+ unsigned int bit_width:8;
+ unsigned int mask_length:8;
+ } split;
+ unsigned int full;
+};
+
+union cpuid10_ebx {
+ struct {
+ unsigned int no_unhalted_core_cycles:1;
+ unsigned int no_instructions_retired:1;
+ unsigned int no_unhalted_reference_cycles:1;
+ unsigned int no_llc_reference:1;
+ unsigned int no_llc_misses:1;
+ unsigned int no_branch_instruction_retired:1;
+ unsigned int no_branch_misses_retired:1;
+ } split;
+ unsigned int full;
+};
+
+/* End of stuff taken from perf_event.h. */
+
+/* Oddly, this isn't in perf_event.h. */
+#define ARCH_PERFMON_BRANCHES_RETIRED 5
+
+#define VCPU_ID 0
+#define NUM_BRANCHES 42
+
+/*
+ * This is how the event selector and unit mask are stored in an AMD
+ * core performance event-select register. Intel's format is similar,
+ * but the event selector is only 8 bits.
+ */
+#define EVENT(select, umask) ((select & 0xf00UL) << 24 | (select & 0xff) | \
+ (umask & 0xff) << 8)
+
+/*
+ * "Branch instructions retired", from the Intel SDM, volume 3,
+ * "Pre-defined Architectural Performance Events."
+ */
+
+#define INTEL_BR_RETIRED EVENT(0xc4, 0)
+
+/*
+ * "Retired branch instructions", from Processor Programming Reference
+ * (PPR) for AMD Family 17h Model 01h, Revision B1 Processors,
+ * Preliminary Processor Programming Reference (PPR) for AMD Family
+ * 17h Model 31h, Revision B0 Processors, and Preliminary Processor
+ * Programming Reference (PPR) for AMD Family 19h Model 01h, Revision
+ * B1 Processors Volume 1 of 2.
+ */
+
+#define AMD_ZEN_BR_RETIRED EVENT(0xc2, 0)
+
+/*
+ * This event list comprises Intel's eight architectural events plus
+ * AMD's "retired branch instructions" for Zen[123] (and possibly
+ * other AMD CPUs).
+ */
+static const uint64_t event_list[] = {
+ EVENT(0x3c, 0),
+ EVENT(0xc0, 0),
+ EVENT(0x3c, 1),
+ EVENT(0x2e, 0x4f),
+ EVENT(0x2e, 0x41),
+ EVENT(0xc4, 0),
+ EVENT(0xc5, 0),
+ EVENT(0xa4, 1),
+ AMD_ZEN_BR_RETIRED,
+};
+
+/*
+ * If we encounter a #GP during the guest PMU sanity check, then the guest
+ * PMU is not functional. Inform the hypervisor via GUEST_SYNC(0).
+ */
+static void guest_gp_handler(struct ex_regs *regs)
+{
+ GUEST_SYNC(0);
+}
+
+/*
+ * Check that we can write a new value to the given MSR and read it back.
+ * The caller should provide a non-empty set of bits that are safe to flip.
+ *
+ * Return on success. GUEST_SYNC(0) on error.
+ */
+static void check_msr(uint32_t msr, uint64_t bits_to_flip)
+{
+ uint64_t v = rdmsr(msr) ^ bits_to_flip;
+
+ wrmsr(msr, v);
+ if (rdmsr(msr) != v)
+ GUEST_SYNC(0);
+
+ v ^= bits_to_flip;
+ wrmsr(msr, v);
+ if (rdmsr(msr) != v)
+ GUEST_SYNC(0);
+}
+
+static void intel_guest_code(void)
+{
+ check_msr(MSR_CORE_PERF_GLOBAL_CTRL, 1);
+ check_msr(MSR_P6_EVNTSEL0, 0xffff);
+ check_msr(MSR_IA32_PMC0, 0xffff);
+ GUEST_SYNC(1);
+
+ for (;;) {
+ uint64_t br0, br1;
+
+ wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, 0);
+ wrmsr(MSR_P6_EVNTSEL0, ARCH_PERFMON_EVENTSEL_ENABLE |
+ ARCH_PERFMON_EVENTSEL_OS | INTEL_BR_RETIRED);
+ wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, 1);
+ br0 = rdmsr(MSR_IA32_PMC0);
+ __asm__ __volatile__("loop ." : "+c"((int){NUM_BRANCHES}));
+ br1 = rdmsr(MSR_IA32_PMC0);
+ GUEST_SYNC(br1 - br0);
+ }
+}
+
+/*
+ * To avoid needing a check for CPUID.80000001:ECX.PerfCtrExtCore[bit 23],
+ * this code uses the always-available, legacy K7 PMU MSRs, which alias to
+ * the first four of the six extended core PMU MSRs.
+ */
+static void amd_guest_code(void)
+{
+ check_msr(MSR_K7_EVNTSEL0, 0xffff);
+ check_msr(MSR_K7_PERFCTR0, 0xffff);
+ GUEST_SYNC(1);
+
+ for (;;) {
+ uint64_t br0, br1;
+
+ wrmsr(MSR_K7_EVNTSEL0, 0);
+ wrmsr(MSR_K7_EVNTSEL0, ARCH_PERFMON_EVENTSEL_ENABLE |
+ ARCH_PERFMON_EVENTSEL_OS | AMD_ZEN_BR_RETIRED);
+ br0 = rdmsr(MSR_K7_PERFCTR0);
+ __asm__ __volatile__("loop ." : "+c"((int){NUM_BRANCHES}));
+ br1 = rdmsr(MSR_K7_PERFCTR0);
+ GUEST_SYNC(br1 - br0);
+ }
+}
+
+/*
+ * Run the VM to the next GUEST_SYNC(value), and return the value passed
+ * to the sync. Any other exit from the guest is fatal.
+ */
+static uint64_t run_vm_to_sync(struct kvm_vm *vm)
+{
+ 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,
+ "Exit_reason other than KVM_EXIT_IO: %u (%s)\n",
+ run->exit_reason,
+ exit_reason_str(run->exit_reason));
+ get_ucall(vm, VCPU_ID, &uc);
+ TEST_ASSERT(uc.cmd == UCALL_SYNC,
+ "Received ucall other than UCALL_SYNC: %lu", uc.cmd);
+ return uc.args[1];
+}
+
+/*
+ * In a nested environment or if the vPMU is disabled, the guest PMU
+ * might not work as architected (accessing the PMU MSRs may raise
+ * #GP, or writes could simply be discarded). In those situations,
+ * there is no point in running these tests. The guest code will perform
+ * a sanity check and then GUEST_SYNC(success). In the case of failure,
+ * the behavior of the guest on resumption is undefined.
+ */
+static bool sanity_check_pmu(struct kvm_vm *vm)
+{
+ bool success;
+
+ vm_install_exception_handler(vm, GP_VECTOR, guest_gp_handler);
+ success = run_vm_to_sync(vm);
+ vm_install_exception_handler(vm, GP_VECTOR, NULL);
+
+ return success;
+}
+
+static struct kvm_pmu_event_filter *make_pmu_event_filter(uint32_t nevents)
+{
+ struct kvm_pmu_event_filter *f;
+ int size = sizeof(*f) + nevents * sizeof(f->events[0]);
+
+ f = malloc(size);
+ TEST_ASSERT(f, "Out of memory");
+ memset(f, 0, size);
+ f->nevents = nevents;
+ return f;
+}
+
+static struct kvm_pmu_event_filter *event_filter(uint32_t action)
+{
+ struct kvm_pmu_event_filter *f;
+ int i;
+
+ f = make_pmu_event_filter(ARRAY_SIZE(event_list));
+ f->action = action;
+ for (i = 0; i < ARRAY_SIZE(event_list); i++)
+ f->events[i] = event_list[i];
+
+ return f;
+}
+
+/*
+ * Remove the first occurrence of 'event' (if any) from the filter's
+ * event list.
+ */
+static struct kvm_pmu_event_filter *remove_event(struct kvm_pmu_event_filter *f,
+ uint64_t event)
+{
+ bool found = false;
+ int i;
+
+ for (i = 0; i < f->nevents; i++) {
+ if (found)
+ f->events[i - 1] = f->events[i];
+ else
+ found = f->events[i] == event;
+ }
+ if (found)
+ f->nevents--;
+ return f;
+}
+
+static void test_without_filter(struct kvm_vm *vm)
+{
+ uint64_t count = run_vm_to_sync(vm);
+
+ if (count != NUM_BRANCHES)
+ pr_info("%s: Branch instructions retired = %lu (expected %u)\n",
+ __func__, count, NUM_BRANCHES);
+ TEST_ASSERT(count, "Allowed PMU event is not counting");
+}
+
+static uint64_t test_with_filter(struct kvm_vm *vm,
+ struct kvm_pmu_event_filter *f)
+{
+ vm_ioctl(vm, KVM_SET_PMU_EVENT_FILTER, (void *)f);
+ return run_vm_to_sync(vm);
+}
+
+static void test_member_deny_list(struct kvm_vm *vm)
+{
+ struct kvm_pmu_event_filter *f = event_filter(KVM_PMU_EVENT_DENY);
+ uint64_t count = test_with_filter(vm, f);
+
+ free(f);
+ if (count)
+ pr_info("%s: Branch instructions retired = %lu (expected 0)\n",
+ __func__, count);
+ TEST_ASSERT(!count, "Disallowed PMU Event is counting");
+}
+
+static void test_member_allow_list(struct kvm_vm *vm)
+{
+ struct kvm_pmu_event_filter *f = event_filter(KVM_PMU_EVENT_ALLOW);
+ uint64_t count = test_with_filter(vm, f);
+
+ free(f);
+ if (count != NUM_BRANCHES)
+ pr_info("%s: Branch instructions retired = %lu (expected %u)\n",
+ __func__, count, NUM_BRANCHES);
+ TEST_ASSERT(count, "Allowed PMU event is not counting");
+}
+
+static void test_not_member_deny_list(struct kvm_vm *vm)
+{
+ struct kvm_pmu_event_filter *f = event_filter(KVM_PMU_EVENT_DENY);
+ uint64_t count;
+
+ remove_event(f, INTEL_BR_RETIRED);
+ remove_event(f, AMD_ZEN_BR_RETIRED);
+ count = test_with_filter(vm, f);
+ free(f);
+ if (count != NUM_BRANCHES)
+ pr_info("%s: Branch instructions retired = %lu (expected %u)\n",
+ __func__, count, NUM_BRANCHES);
+ TEST_ASSERT(count, "Allowed PMU event is not counting");
+}
+
+static void test_not_member_allow_list(struct kvm_vm *vm)
+{
+ struct kvm_pmu_event_filter *f = event_filter(KVM_PMU_EVENT_ALLOW);
+ uint64_t count;
+
+ remove_event(f, INTEL_BR_RETIRED);
+ remove_event(f, AMD_ZEN_BR_RETIRED);
+ count = test_with_filter(vm, f);
+ free(f);
+ if (count)
+ pr_info("%s: Branch instructions retired = %lu (expected 0)\n",
+ __func__, count);
+ TEST_ASSERT(!count, "Disallowed PMU Event is counting");
+}
+
+/*
+ * Check for a non-zero PMU version, at least one general-purpose
+ * counter per logical processor, an EBX bit vector of length greater
+ * than 5, and EBX[5] clear.
+ */
+static bool check_intel_pmu_leaf(struct kvm_cpuid_entry2 *entry)
+{
+ union cpuid10_eax eax = { .full = entry->eax };
+ union cpuid10_ebx ebx = { .full = entry->ebx };
+
+ return eax.split.version_id && eax.split.num_counters > 0 &&
+ eax.split.mask_length > ARCH_PERFMON_BRANCHES_RETIRED &&
+ !ebx.split.no_branch_instruction_retired;
+}
+
+/*
+ * Note that CPUID leaf 0xa is Intel-specific. This leaf should be
+ * clear on AMD hardware.
+ */
+static bool use_intel_pmu(void)
+{
+ struct kvm_cpuid_entry2 *entry;
+
+ entry = kvm_get_supported_cpuid_index(0xa, 0);
+ return is_intel_cpu() && entry && check_intel_pmu_leaf(entry);
+}
+
+static bool is_zen1(uint32_t eax)
+{
+ return x86_family(eax) == 0x17 && x86_model(eax) <= 0x0f;
+}
+
+static bool is_zen2(uint32_t eax)
+{
+ return x86_family(eax) == 0x17 &&
+ x86_model(eax) >= 0x30 && x86_model(eax) <= 0x3f;
+}
+
+static bool is_zen3(uint32_t eax)
+{
+ return x86_family(eax) == 0x19 && x86_model(eax) <= 0x0f;
+}
+
+/*
+ * Determining AMD support for a PMU event requires consulting the AMD
+ * PPR for the CPU or reference material derived therefrom. The AMD
+ * test code herein has been verified to work on Zen1, Zen2, and Zen3.
+ *
+ * Feel free to add more AMD CPUs that are documented to support event
+ * select 0xc2 umask 0 as "retired branch instructions."
+ */
+static bool use_amd_pmu(void)
+{
+ struct kvm_cpuid_entry2 *entry;
+
+ entry = kvm_get_supported_cpuid_index(1, 0);
+ return is_amd_cpu() && entry &&
+ (is_zen1(entry->eax) ||
+ is_zen2(entry->eax) ||
+ is_zen3(entry->eax));
+}
+
+int main(int argc, char *argv[])
+{
+ void (*guest_code)(void) = NULL;
+ struct kvm_vm *vm;
+ int r;
+
+ /* Tell stdout not to buffer its content */
+ setbuf(stdout, NULL);
+
+ r = kvm_check_cap(KVM_CAP_PMU_EVENT_FILTER);
+ if (!r) {
+ print_skip("KVM_CAP_PMU_EVENT_FILTER not supported");
+ exit(KSFT_SKIP);
+ }
+
+ if (use_intel_pmu())
+ guest_code = intel_guest_code;
+ else if (use_amd_pmu())
+ guest_code = amd_guest_code;
+
+ if (!guest_code) {
+ print_skip("Don't know how to test this guest PMU");
+ exit(KSFT_SKIP);
+ }
+
+ vm = vm_create_default(VCPU_ID, 0, guest_code);
+
+ vm_init_descriptor_tables(vm);
+ vcpu_init_descriptor_tables(vm, VCPU_ID);
+
+ if (!sanity_check_pmu(vm)) {
+ print_skip("Guest PMU is not functional");
+ exit(KSFT_SKIP);
+ }
+
+ test_without_filter(vm);
+ test_member_deny_list(vm);
+ test_member_allow_list(vm);
+ test_not_member_deny_list(vm);
+ test_not_member_allow_list(vm);
+
+ kvm_vm_free(vm);
+
+ return 0;
+}
diff --git a/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c b/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c
index 29b18d565cf4..80056bbbb003 100644
--- a/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c
+++ b/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c
@@ -21,7 +21,7 @@
#define NR_LOCK_TESTING_THREADS 3
#define NR_LOCK_TESTING_ITERATIONS 10000
-static void sev_ioctl(int vm_fd, int cmd_id, void *data)
+static int __sev_ioctl(int vm_fd, int cmd_id, void *data, __u32 *fw_error)
{
struct kvm_sev_cmd cmd = {
.id = cmd_id,
@@ -31,9 +31,19 @@ static void sev_ioctl(int vm_fd, int cmd_id, void *data)
int ret;
ret = ioctl(vm_fd, KVM_MEMORY_ENCRYPT_OP, &cmd);
- TEST_ASSERT((ret == 0 || cmd.error == SEV_RET_SUCCESS),
+ *fw_error = cmd.error;
+ return ret;
+}
+
+static void sev_ioctl(int vm_fd, int cmd_id, void *data)
+{
+ int ret;
+ __u32 fw_error;
+
+ ret = __sev_ioctl(vm_fd, cmd_id, data, &fw_error);
+ TEST_ASSERT(ret == 0 && fw_error == SEV_RET_SUCCESS,
"%d failed: return code: %d, errno: %d, fw error: %d",
- cmd_id, ret, errno, cmd.error);
+ cmd_id, ret, errno, fw_error);
}
static struct kvm_vm *sev_vm_create(bool es)
@@ -225,12 +235,45 @@ static void sev_mirror_create(int dst_fd, int src_fd)
TEST_ASSERT(!ret, "Copying context failed, ret: %d, errno: %d\n", ret, errno);
}
+static void verify_mirror_allowed_cmds(int vm_fd)
+{
+ struct kvm_sev_guest_status status;
+
+ for (int cmd_id = KVM_SEV_INIT; cmd_id < KVM_SEV_NR_MAX; ++cmd_id) {
+ int ret;
+ __u32 fw_error;
+
+ /*
+ * These commands are allowed for mirror VMs, all others are
+ * not.
+ */
+ switch (cmd_id) {
+ case KVM_SEV_LAUNCH_UPDATE_VMSA:
+ case KVM_SEV_GUEST_STATUS:
+ case KVM_SEV_DBG_DECRYPT:
+ case KVM_SEV_DBG_ENCRYPT:
+ continue;
+ default:
+ break;
+ }
+
+ /*
+ * These commands should be disallowed before the data
+ * parameter is examined so NULL is OK here.
+ */
+ ret = __sev_ioctl(vm_fd, cmd_id, NULL, &fw_error);
+ TEST_ASSERT(
+ ret == -1 && errno == EINVAL,
+ "Should not be able call command: %d. ret: %d, errno: %d\n",
+ cmd_id, ret, errno);
+ }
+
+ sev_ioctl(vm_fd, KVM_SEV_GUEST_STATUS, &status);
+}
+
static void test_sev_mirror(bool es)
{
struct kvm_vm *src_vm, *dst_vm;
- struct kvm_sev_launch_start start = {
- .policy = es ? SEV_POLICY_ES : 0
- };
int i;
src_vm = sev_vm_create(es);
@@ -241,10 +284,12 @@ static void test_sev_mirror(bool es)
/* Check that we can complete creation of the mirror VM. */
for (i = 0; i < NR_MIGRATE_TEST_VCPUS; ++i)
vm_vcpu_add(dst_vm, i);
- sev_ioctl(dst_vm->fd, KVM_SEV_LAUNCH_START, &start);
+
if (es)
sev_ioctl(dst_vm->fd, KVM_SEV_LAUNCH_UPDATE_VMSA, NULL);
+ verify_mirror_allowed_cmds(dst_vm->fd);
+
kvm_vm_free(src_vm);
kvm_vm_free(dst_vm);
}
diff --git a/tools/testing/selftests/kvm/x86_64/smm_test.c b/tools/testing/selftests/kvm/x86_64/smm_test.c
index d0fe2fdce58c..a626d40fdb48 100644
--- a/tools/testing/selftests/kvm/x86_64/smm_test.c
+++ b/tools/testing/selftests/kvm/x86_64/smm_test.c
@@ -105,7 +105,6 @@ static void guest_code(void *arg)
if (cpu_has_svm()) {
run_guest(svm->vmcb, svm->vmcb_gpa);
- svm->vmcb->save.rip += 3;
run_guest(svm->vmcb, svm->vmcb_gpa);
} else {
vmlaunch();
@@ -212,7 +211,7 @@ int main(int argc, char *argv[])
vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
vcpu_load_state(vm, VCPU_ID, state);
run = vcpu_state(vm, VCPU_ID);
- free(state);
+ kvm_x86_state_cleanup(state);
}
done:
diff --git a/tools/testing/selftests/kvm/x86_64/state_test.c b/tools/testing/selftests/kvm/x86_64/state_test.c
index 32854c1462ad..2e0a92da8ff5 100644
--- a/tools/testing/selftests/kvm/x86_64/state_test.c
+++ b/tools/testing/selftests/kvm/x86_64/state_test.c
@@ -218,7 +218,7 @@ int main(int argc, char *argv[])
vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
vcpu_load_state(vm, VCPU_ID, state);
run = vcpu_state(vm, VCPU_ID);
- free(state);
+ kvm_x86_state_cleanup(state);
memset(&regs2, 0, sizeof(regs2));
vcpu_regs_get(vm, VCPU_ID, &regs2);
diff --git a/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c b/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c
index 5a6a662f2e59..a426078b16a3 100644
--- a/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c
+++ b/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c
@@ -77,8 +77,8 @@ static void run_vcpu(struct kvm_vm *vm, uint32_t vcpuid, int stage)
switch (get_ucall(vm, vcpuid, &uc)) {
case UCALL_SYNC:
TEST_ASSERT(!strcmp((const char *)uc.args[0], "hello") &&
- uc.args[1] == stage + 1, "Stage %d: Unexpected register values vmexit, got %lx",
- stage + 1, (ulong)uc.args[1]);
+ uc.args[1] == stage + 1, "Stage %d: Unexpected register values vmexit, got %lx",
+ stage + 1, (ulong)uc.args[1]);
return;
case UCALL_DONE:
return;
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c b/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c
index 2835a17f1b7a..edac8839e717 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c
@@ -30,8 +30,8 @@ static struct kvm_vm *vm;
static void l2_guest_code(void)
{
/* Exit to L0 */
- asm volatile("inb %%dx, %%al"
- : : [port] "d" (PORT_L0_EXIT) : "rax");
+ asm volatile("inb %%dx, %%al"
+ : : [port] "d" (PORT_L0_EXIT) : "rax");
}
static void l1_guest_code(struct vmx_pages *vmx_pages)
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c b/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c
new file mode 100644
index 000000000000..27a850f3d7ce
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c
@@ -0,0 +1,139 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+
+#include <signal.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <sys/time.h>
+
+#include "kselftest.h"
+
+#define VCPU_ID 0
+
+static struct kvm_vm *vm;
+
+static void guest_ud_handler(struct ex_regs *regs)
+{
+ /* Loop on the ud2 until guest state is made invalid. */
+}
+
+static void guest_code(void)
+{
+ asm volatile("ud2");
+}
+
+static void __run_vcpu_with_invalid_state(void)
+{
+ struct kvm_run *run = vcpu_state(vm, VCPU_ID);
+
+ vcpu_run(vm, VCPU_ID);
+
+ TEST_ASSERT(run->exit_reason == KVM_EXIT_INTERNAL_ERROR,
+ "Expected KVM_EXIT_INTERNAL_ERROR, got %d (%s)\n",
+ run->exit_reason, exit_reason_str(run->exit_reason));
+ TEST_ASSERT(run->emulation_failure.suberror == KVM_INTERNAL_ERROR_EMULATION,
+ "Expected emulation failure, got %d\n",
+ run->emulation_failure.suberror);
+}
+
+static void run_vcpu_with_invalid_state(void)
+{
+ /*
+ * Always run twice to verify KVM handles the case where _KVM_ queues
+ * an exception with invalid state and then exits to userspace, i.e.
+ * that KVM doesn't explode if userspace ignores the initial error.
+ */
+ __run_vcpu_with_invalid_state();
+ __run_vcpu_with_invalid_state();
+}
+
+static void set_timer(void)
+{
+ struct itimerval timer;
+
+ timer.it_value.tv_sec = 0;
+ timer.it_value.tv_usec = 200;
+ timer.it_interval = timer.it_value;
+ ASSERT_EQ(setitimer(ITIMER_REAL, &timer, NULL), 0);
+}
+
+static void set_or_clear_invalid_guest_state(bool set)
+{
+ static struct kvm_sregs sregs;
+
+ if (!sregs.cr0)
+ vcpu_sregs_get(vm, VCPU_ID, &sregs);
+ sregs.tr.unusable = !!set;
+ vcpu_sregs_set(vm, VCPU_ID, &sregs);
+}
+
+static void set_invalid_guest_state(void)
+{
+ set_or_clear_invalid_guest_state(true);
+}
+
+static void clear_invalid_guest_state(void)
+{
+ set_or_clear_invalid_guest_state(false);
+}
+
+static void sigalrm_handler(int sig)
+{
+ struct kvm_vcpu_events events;
+
+ TEST_ASSERT(sig == SIGALRM, "Unexpected signal = %d", sig);
+
+ vcpu_events_get(vm, VCPU_ID, &events);
+
+ /*
+ * If an exception is pending, attempt KVM_RUN with invalid guest,
+ * otherwise rearm the timer and keep doing so until the timer fires
+ * between KVM queueing an exception and re-entering the guest.
+ */
+ if (events.exception.pending) {
+ set_invalid_guest_state();
+ run_vcpu_with_invalid_state();
+ } else {
+ set_timer();
+ }
+}
+
+int main(int argc, char *argv[])
+{
+ if (!is_intel_cpu() || vm_is_unrestricted_guest(NULL)) {
+ print_skip("Must be run with kvm_intel.unrestricted_guest=0");
+ exit(KSFT_SKIP);
+ }
+
+ vm = vm_create_default(VCPU_ID, 0, (void *)guest_code);
+
+ vm_init_descriptor_tables(vm);
+ vcpu_init_descriptor_tables(vm, VCPU_ID);
+
+ vm_install_exception_handler(vm, UD_VECTOR, guest_ud_handler);
+
+ /*
+ * Stuff invalid guest state for L2 by making TR unusuable. The next
+ * KVM_RUN should induce a TRIPLE_FAULT in L2 as KVM doesn't support
+ * emulating invalid guest state for L2.
+ */
+ set_invalid_guest_state();
+ run_vcpu_with_invalid_state();
+
+ /*
+ * Verify KVM also handles the case where userspace gains control while
+ * an exception is pending and stuffs invalid state. Run with valid
+ * guest state and a timer firing every 200us, and attempt to enter the
+ * guest with invalid state when the handler interrupts KVM with an
+ * exception pending.
+ */
+ clear_invalid_guest_state();
+ TEST_ASSERT(signal(SIGALRM, sigalrm_handler) != SIG_ERR,
+ "Failed to register SIGALRM handler, errno = %d (%s)",
+ errno, strerror(errno));
+
+ set_timer();
+ run_vcpu_with_invalid_state();
+}
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_preemption_timer_test.c b/tools/testing/selftests/kvm/x86_64/vmx_preemption_timer_test.c
index a07480aed397..ff92e25b6f1e 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_preemption_timer_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_preemption_timer_test.c
@@ -244,7 +244,7 @@ int main(int argc, char *argv[])
vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
vcpu_load_state(vm, VCPU_ID, state);
run = vcpu_state(vm, VCPU_ID);
- free(state);
+ kvm_x86_state_cleanup(state);
memset(&regs2, 0, sizeof(regs2));
vcpu_regs_get(vm, VCPU_ID, &regs2);
diff --git a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
index a0699f00b3d6..865e17146815 100644
--- a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
+++ b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
@@ -14,6 +14,9 @@
#include <stdint.h>
#include <time.h>
#include <sched.h>
+#include <signal.h>
+
+#include <sys/eventfd.h>
#define VCPU_ID 5
@@ -22,10 +25,15 @@
#define SHINFO_REGION_SLOT 10
#define PAGE_SIZE 4096
+#define DUMMY_REGION_GPA (SHINFO_REGION_GPA + (2 * PAGE_SIZE))
+#define DUMMY_REGION_SLOT 11
+
+#define SHINFO_ADDR (SHINFO_REGION_GPA)
#define PVTIME_ADDR (SHINFO_REGION_GPA + PAGE_SIZE)
#define RUNSTATE_ADDR (SHINFO_REGION_GPA + PAGE_SIZE + 0x20)
#define VCPU_INFO_ADDR (SHINFO_REGION_GPA + 0x40)
+#define SHINFO_VADDR (SHINFO_REGION_GVA)
#define RUNSTATE_VADDR (SHINFO_REGION_GVA + PAGE_SIZE + 0x20)
#define VCPU_INFO_VADDR (SHINFO_REGION_GVA + 0x40)
@@ -38,20 +46,20 @@ static struct kvm_vm *vm;
#define MIN_STEAL_TIME 50000
struct pvclock_vcpu_time_info {
- u32 version;
- u32 pad0;
- u64 tsc_timestamp;
- u64 system_time;
- u32 tsc_to_system_mul;
- s8 tsc_shift;
- u8 flags;
- u8 pad[2];
+ u32 version;
+ u32 pad0;
+ u64 tsc_timestamp;
+ u64 system_time;
+ u32 tsc_to_system_mul;
+ s8 tsc_shift;
+ u8 flags;
+ u8 pad[2];
} __attribute__((__packed__)); /* 32 bytes */
struct pvclock_wall_clock {
- u32 version;
- u32 sec;
- u32 nsec;
+ u32 version;
+ u32 sec;
+ u32 nsec;
} __attribute__((__packed__));
struct vcpu_runstate_info {
@@ -66,22 +74,44 @@ struct arch_vcpu_info {
};
struct vcpu_info {
- uint8_t evtchn_upcall_pending;
- uint8_t evtchn_upcall_mask;
- unsigned long evtchn_pending_sel;
- struct arch_vcpu_info arch;
- struct pvclock_vcpu_time_info time;
+ uint8_t evtchn_upcall_pending;
+ uint8_t evtchn_upcall_mask;
+ unsigned long evtchn_pending_sel;
+ struct arch_vcpu_info arch;
+ struct pvclock_vcpu_time_info time;
}; /* 64 bytes (x86) */
+struct shared_info {
+ struct vcpu_info vcpu_info[32];
+ unsigned long evtchn_pending[64];
+ unsigned long evtchn_mask[64];
+ struct pvclock_wall_clock wc;
+ uint32_t wc_sec_hi;
+ /* arch_shared_info here */
+};
+
#define RUNSTATE_running 0
#define RUNSTATE_runnable 1
#define RUNSTATE_blocked 2
#define RUNSTATE_offline 3
+static const char *runstate_names[] = {
+ "running",
+ "runnable",
+ "blocked",
+ "offline"
+};
+
+struct {
+ struct kvm_irq_routing info;
+ struct kvm_irq_routing_entry entries[2];
+} irq_routes;
+
static void evtchn_handler(struct ex_regs *regs)
{
struct vcpu_info *vi = (void *)VCPU_INFO_VADDR;
vi->evtchn_upcall_pending = 0;
+ vi->evtchn_pending_sel = 0;
GUEST_SYNC(0x20);
}
@@ -127,7 +157,25 @@ static void guest_code(void)
GUEST_SYNC(6);
GUEST_ASSERT(rs->time[RUNSTATE_runnable] >= MIN_STEAL_TIME);
- GUEST_DONE();
+ /* Attempt to deliver a *masked* interrupt */
+ GUEST_SYNC(7);
+
+ /* Wait until we see the bit set */
+ struct shared_info *si = (void *)SHINFO_VADDR;
+ while (!si->evtchn_pending[0])
+ __asm__ __volatile__ ("rep nop" : : : "memory");
+
+ /* Now deliver an *unmasked* interrupt */
+ GUEST_SYNC(8);
+
+ while (!si->evtchn_pending[1])
+ __asm__ __volatile__ ("rep nop" : : : "memory");
+
+ /* Change memslots and deliver an interrupt */
+ GUEST_SYNC(9);
+
+ for (;;)
+ __asm__ __volatile__ ("rep nop" : : : "memory");
}
static int cmp_timespec(struct timespec *a, struct timespec *b)
@@ -144,9 +192,18 @@ static int cmp_timespec(struct timespec *a, struct timespec *b)
return 0;
}
+static void handle_alrm(int sig)
+{
+ TEST_FAIL("IRQ delivery timed out");
+}
+
int main(int argc, char *argv[])
{
struct timespec min_ts, max_ts, vm_ts;
+ bool verbose;
+
+ verbose = argc > 1 && (!strncmp(argv[1], "-v", 3) ||
+ !strncmp(argv[1], "--verbose", 10));
int xen_caps = kvm_check_cap(KVM_CAP_XEN_HVM);
if (!(xen_caps & KVM_XEN_HVM_CONFIG_SHARED_INFO) ) {
@@ -155,6 +212,7 @@ int main(int argc, char *argv[])
}
bool do_runstate_tests = !!(xen_caps & KVM_XEN_HVM_CONFIG_RUNSTATE);
+ bool do_eventfd_tests = !!(xen_caps & KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL);
clock_gettime(CLOCK_REALTIME, &min_ts);
@@ -166,6 +224,11 @@ int main(int argc, char *argv[])
SHINFO_REGION_GPA, SHINFO_REGION_SLOT, 2, 0);
virt_map(vm, SHINFO_REGION_GVA, SHINFO_REGION_GPA, 2);
+ struct shared_info *shinfo = addr_gpa2hva(vm, SHINFO_VADDR);
+
+ int zero_fd = open("/dev/zero", O_RDONLY);
+ TEST_ASSERT(zero_fd != -1, "Failed to open /dev/zero");
+
struct kvm_xen_hvm_config hvmc = {
.flags = KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL,
.msr = XEN_HYPERCALL_MSR,
@@ -184,6 +247,16 @@ int main(int argc, char *argv[])
};
vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &ha);
+ /*
+ * Test what happens when the HVA of the shinfo page is remapped after
+ * the kernel has a reference to it. But make sure we copy the clock
+ * info over since that's only set at setup time, and we test it later.
+ */
+ struct pvclock_wall_clock wc_copy = shinfo->wc;
+ void *m = mmap(shinfo, PAGE_SIZE, PROT_READ|PROT_WRITE, MAP_FIXED|MAP_PRIVATE, zero_fd, 0);
+ TEST_ASSERT(m == shinfo, "Failed to map /dev/zero over shared info");
+ shinfo->wc = wc_copy;
+
struct kvm_xen_vcpu_attr vi = {
.type = KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO,
.u.gpa = VCPU_INFO_ADDR,
@@ -214,6 +287,49 @@ int main(int argc, char *argv[])
vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &st);
}
+ int irq_fd[2] = { -1, -1 };
+
+ if (do_eventfd_tests) {
+ irq_fd[0] = eventfd(0, 0);
+ irq_fd[1] = eventfd(0, 0);
+
+ /* Unexpected, but not a KVM failure */
+ if (irq_fd[0] == -1 || irq_fd[1] == -1)
+ do_eventfd_tests = false;
+ }
+
+ if (do_eventfd_tests) {
+ irq_routes.info.nr = 2;
+
+ irq_routes.entries[0].gsi = 32;
+ irq_routes.entries[0].type = KVM_IRQ_ROUTING_XEN_EVTCHN;
+ irq_routes.entries[0].u.xen_evtchn.port = 15;
+ irq_routes.entries[0].u.xen_evtchn.vcpu = VCPU_ID;
+ irq_routes.entries[0].u.xen_evtchn.priority = KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL;
+
+ irq_routes.entries[1].gsi = 33;
+ irq_routes.entries[1].type = KVM_IRQ_ROUTING_XEN_EVTCHN;
+ irq_routes.entries[1].u.xen_evtchn.port = 66;
+ irq_routes.entries[1].u.xen_evtchn.vcpu = VCPU_ID;
+ irq_routes.entries[1].u.xen_evtchn.priority = KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL;
+
+ vm_ioctl(vm, KVM_SET_GSI_ROUTING, &irq_routes);
+
+ struct kvm_irqfd ifd = { };
+
+ ifd.fd = irq_fd[0];
+ ifd.gsi = 32;
+ vm_ioctl(vm, KVM_IRQFD, &ifd);
+
+ ifd.fd = irq_fd[1];
+ ifd.gsi = 33;
+ vm_ioctl(vm, KVM_IRQFD, &ifd);
+
+ struct sigaction sa = { };
+ sa.sa_handler = handle_alrm;
+ sigaction(SIGALRM, &sa, NULL);
+ }
+
struct vcpu_info *vinfo = addr_gpa2hva(vm, VCPU_INFO_VADDR);
vinfo->evtchn_upcall_pending = 0;
@@ -248,6 +364,8 @@ int main(int argc, char *argv[])
switch (uc.args[1]) {
case 0:
+ if (verbose)
+ printf("Delivering evtchn upcall\n");
evtchn_irq_expected = true;
vinfo->evtchn_upcall_pending = 1;
break;
@@ -256,11 +374,16 @@ int main(int argc, char *argv[])
TEST_ASSERT(!evtchn_irq_expected, "Event channel IRQ not seen");
if (!do_runstate_tests)
goto done;
+ if (verbose)
+ printf("Testing runstate %s\n", runstate_names[uc.args[1]]);
rst.type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT;
rst.u.runstate.state = uc.args[1];
vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &rst);
break;
+
case 4:
+ if (verbose)
+ printf("Testing RUNSTATE_ADJUST\n");
rst.type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST;
memset(&rst.u, 0, sizeof(rst.u));
rst.u.runstate.state = (uint64_t)-1;
@@ -274,6 +397,8 @@ int main(int argc, char *argv[])
break;
case 5:
+ if (verbose)
+ printf("Testing RUNSTATE_DATA\n");
rst.type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA;
memset(&rst.u, 0, sizeof(rst.u));
rst.u.runstate.state = RUNSTATE_running;
@@ -282,16 +407,54 @@ int main(int argc, char *argv[])
rst.u.runstate.time_offline = 0x5a;
vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &rst);
break;
+
case 6:
+ if (verbose)
+ printf("Testing steal time\n");
/* Yield until scheduler delay exceeds target */
rundelay = get_run_delay() + MIN_STEAL_TIME;
do {
sched_yield();
} while (get_run_delay() < rundelay);
break;
+
+ case 7:
+ if (!do_eventfd_tests)
+ goto done;
+ if (verbose)
+ printf("Testing masked event channel\n");
+ shinfo->evtchn_mask[0] = 0x8000;
+ eventfd_write(irq_fd[0], 1UL);
+ alarm(1);
+ break;
+
+ case 8:
+ if (verbose)
+ printf("Testing unmasked event channel\n");
+ /* Unmask that, but deliver the other one */
+ shinfo->evtchn_pending[0] = 0;
+ shinfo->evtchn_mask[0] = 0;
+ eventfd_write(irq_fd[1], 1UL);
+ evtchn_irq_expected = true;
+ alarm(1);
+ break;
+
+ case 9:
+ if (verbose)
+ printf("Testing event channel after memslot change\n");
+ vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
+ DUMMY_REGION_GPA, DUMMY_REGION_SLOT, 1, 0);
+ eventfd_write(irq_fd[0], 1UL);
+ evtchn_irq_expected = true;
+ alarm(1);
+ break;
+
case 0x20:
TEST_ASSERT(evtchn_irq_expected, "Unexpected event channel IRQ");
evtchn_irq_expected = false;
+ if (shinfo->evtchn_pending[1] &&
+ shinfo->evtchn_pending[0])
+ goto done;
break;
}
break;
@@ -318,9 +481,19 @@ int main(int argc, char *argv[])
ti = addr_gpa2hva(vm, SHINFO_REGION_GPA + 0x40 + 0x20);
ti2 = addr_gpa2hva(vm, PVTIME_ADDR);
+ if (verbose) {
+ printf("Wall clock (v %d) %d.%09d\n", wc->version, wc->sec, wc->nsec);
+ printf("Time info 1: v %u tsc %" PRIu64 " time %" PRIu64 " mul %u shift %u flags %x\n",
+ ti->version, ti->tsc_timestamp, ti->system_time, ti->tsc_to_system_mul,
+ ti->tsc_shift, ti->flags);
+ printf("Time info 2: v %u tsc %" PRIu64 " time %" PRIu64 " mul %u shift %u flags %x\n",
+ ti2->version, ti2->tsc_timestamp, ti2->system_time, ti2->tsc_to_system_mul,
+ ti2->tsc_shift, ti2->flags);
+ }
+
vm_ts.tv_sec = wc->sec;
vm_ts.tv_nsec = wc->nsec;
- TEST_ASSERT(wc->version && !(wc->version & 1),
+ TEST_ASSERT(wc->version && !(wc->version & 1),
"Bad wallclock version %x", wc->version);
TEST_ASSERT(cmp_timespec(&min_ts, &vm_ts) <= 0, "VM time too old");
TEST_ASSERT(cmp_timespec(&max_ts, &vm_ts) >= 0, "VM time too new");
@@ -341,6 +514,15 @@ int main(int argc, char *argv[])
};
vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_GET_ATTR, &rst);
+ if (verbose) {
+ printf("Runstate: %s(%d), entry %" PRIu64 " ns\n",
+ rs->state <= RUNSTATE_offline ? runstate_names[rs->state] : "unknown",
+ rs->state, rs->state_entry_time);
+ for (int i = RUNSTATE_running; i <= RUNSTATE_offline; i++) {
+ printf("State %s: %" PRIu64 " ns\n",
+ runstate_names[i], rs->time[i]);
+ }
+ }
TEST_ASSERT(rs->state == rst.u.runstate.state, "Runstate mismatch");
TEST_ASSERT(rs->state_entry_time == rst.u.runstate.state_entry_time,
"State entry time mismatch");
diff --git a/tools/testing/selftests/lkdtm/stack-entropy.sh b/tools/testing/selftests/lkdtm/stack-entropy.sh
index 1b4d95d575f8..14fedeef762e 100755
--- a/tools/testing/selftests/lkdtm/stack-entropy.sh
+++ b/tools/testing/selftests/lkdtm/stack-entropy.sh
@@ -4,13 +4,27 @@
# Measure kernel stack entropy by sampling via LKDTM's REPORT_STACK test.
set -e
samples="${1:-1000}"
+TRIGGER=/sys/kernel/debug/provoke-crash/DIRECT
+KSELFTEST_SKIP_TEST=4
+
+# Verify we have LKDTM available in the kernel.
+if [ ! -r $TRIGGER ] ; then
+ /sbin/modprobe -q lkdtm || true
+ if [ ! -r $TRIGGER ] ; then
+ echo "Cannot find $TRIGGER (missing CONFIG_LKDTM?)"
+ else
+ echo "Cannot write $TRIGGER (need to run as root?)"
+ fi
+ # Skip this test
+ exit $KSELFTEST_SKIP_TEST
+fi
# Capture dmesg continuously since it may fill up depending on sample size.
log=$(mktemp -t stack-entropy-XXXXXX)
dmesg --follow >"$log" & pid=$!
report=-1
for i in $(seq 1 $samples); do
- echo "REPORT_STACK" >/sys/kernel/debug/provoke-crash/DIRECT
+ echo "REPORT_STACK" > $TRIGGER
if [ -t 1 ]; then
percent=$(( 100 * $i / $samples ))
if [ "$percent" -ne "$report" ]; then
diff --git a/tools/testing/selftests/memfd/memfd_test.c b/tools/testing/selftests/memfd/memfd_test.c
index 192a2899bae8..94df2692e6e4 100644
--- a/tools/testing/selftests/memfd/memfd_test.c
+++ b/tools/testing/selftests/memfd/memfd_test.c
@@ -455,6 +455,7 @@ static void mfd_fail_write(int fd)
printf("mmap()+mprotect() didn't fail as expected\n");
abort();
}
+ munmap(p, mfd_def_size);
}
/* verify PUNCH_HOLE fails */
diff --git a/tools/testing/selftests/mincore/mincore_selftest.c b/tools/testing/selftests/mincore/mincore_selftest.c
index e54106643337..4c88238fc8f0 100644
--- a/tools/testing/selftests/mincore/mincore_selftest.c
+++ b/tools/testing/selftests/mincore/mincore_selftest.c
@@ -207,15 +207,21 @@ TEST(check_file_mmap)
errno = 0;
fd = open(".", O_TMPFILE | O_RDWR, 0600);
- ASSERT_NE(-1, fd) {
- TH_LOG("Can't create temporary file: %s",
- strerror(errno));
+ if (fd < 0) {
+ ASSERT_EQ(errno, EOPNOTSUPP) {
+ TH_LOG("Can't create temporary file: %s",
+ strerror(errno));
+ }
+ SKIP(goto out_free, "O_TMPFILE not supported by filesystem.");
}
errno = 0;
retval = fallocate(fd, 0, 0, FILE_SIZE);
- ASSERT_EQ(0, retval) {
- TH_LOG("Error allocating space for the temporary file: %s",
- strerror(errno));
+ if (retval) {
+ ASSERT_EQ(errno, EOPNOTSUPP) {
+ TH_LOG("Error allocating space for the temporary file: %s",
+ strerror(errno));
+ }
+ SKIP(goto out_close, "fallocate not supported by filesystem.");
}
/*
@@ -271,7 +277,9 @@ TEST(check_file_mmap)
}
munmap(addr, FILE_SIZE);
+out_close:
close(fd);
+out_free:
free(vec);
}
diff --git a/tools/testing/selftests/mount_setattr/mount_setattr_test.c b/tools/testing/selftests/mount_setattr/mount_setattr_test.c
index f31205f04ee0..8c5fea68ae67 100644
--- a/tools/testing/selftests/mount_setattr/mount_setattr_test.c
+++ b/tools/testing/selftests/mount_setattr/mount_setattr_test.c
@@ -1236,7 +1236,7 @@ static int get_userns_fd(unsigned long nsid, unsigned long hostid, unsigned long
}
/**
- * Validate that an attached mount in our mount namespace can be idmapped.
+ * Validate that an attached mount in our mount namespace cannot be idmapped.
* (The kernel enforces that the mount's mount namespace and the caller's mount
* namespace match.)
*/
@@ -1259,7 +1259,7 @@ TEST_F(mount_setattr_idmapped, attached_mount_inside_current_mount_namespace)
attr.userns_fd = get_userns_fd(0, 10000, 10000);
ASSERT_GE(attr.userns_fd, 0);
- ASSERT_EQ(sys_mount_setattr(open_tree_fd, "", AT_EMPTY_PATH, &attr, sizeof(attr)), 0);
+ ASSERT_NE(sys_mount_setattr(open_tree_fd, "", AT_EMPTY_PATH, &attr, sizeof(attr)), 0);
ASSERT_EQ(close(attr.userns_fd), 0);
ASSERT_EQ(close(open_tree_fd), 0);
}
diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh
index 412d85205546..3f4c8cfe7aca 100755
--- a/tools/testing/selftests/net/fcnal-test.sh
+++ b/tools/testing/selftests/net/fcnal-test.sh
@@ -4059,6 +4059,9 @@ usage: ${0##*/} OPTS
-p Pause on fail
-P Pause after each test
-v Be verbose
+
+Tests:
+ $TESTS_IPV4 $TESTS_IPV6 $TESTS_OTHER
EOF
}
diff --git a/tools/testing/selftests/net/ioam6_parser.c b/tools/testing/selftests/net/ioam6_parser.c
index 8f6997d35816..d9d1d4190126 100644
--- a/tools/testing/selftests/net/ioam6_parser.c
+++ b/tools/testing/selftests/net/ioam6_parser.c
@@ -240,11 +240,8 @@ static int check_ioam6_data(__u8 **p, struct ioam6_trace_hdr *ioam6h,
*p += sizeof(__u32);
}
- if (ioam6h->type.bit6) {
- if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff)
- return 1;
+ if (ioam6h->type.bit6)
*p += sizeof(__u32);
- }
if (ioam6h->type.bit7) {
if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff)
diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh
index 2674ba20d524..ff821025d309 100755
--- a/tools/testing/selftests/net/mptcp/diag.sh
+++ b/tools/testing/selftests/net/mptcp/diag.sh
@@ -71,6 +71,36 @@ chk_msk_remote_key_nr()
__chk_nr "grep -c remote_key" $*
}
+# $1: ns, $2: port
+wait_local_port_listen()
+{
+ local listener_ns="${1}"
+ local port="${2}"
+
+ local port_hex i
+
+ port_hex="$(printf "%04X" "${port}")"
+ for i in $(seq 10); do
+ ip netns exec "${listener_ns}" cat /proc/net/tcp | \
+ awk "BEGIN {rc=1} {if (\$2 ~ /:${port_hex}\$/ && \$4 ~ /0A/) {rc=0; exit}} END {exit rc}" &&
+ break
+ sleep 0.1
+ done
+}
+
+wait_connected()
+{
+ local listener_ns="${1}"
+ local port="${2}"
+
+ local port_hex i
+
+ port_hex="$(printf "%04X" "${port}")"
+ for i in $(seq 10); do
+ ip netns exec ${listener_ns} grep -q " 0100007F:${port_hex} " /proc/net/tcp && break
+ sleep 0.1
+ done
+}
trap cleanup EXIT
ip netns add $ns
@@ -81,15 +111,15 @@ echo "a" | \
ip netns exec $ns \
./mptcp_connect -p 10000 -l -t ${timeout_poll} \
0.0.0.0 >/dev/null &
-sleep 0.1
+wait_local_port_listen $ns 10000
chk_msk_nr 0 "no msk on netns creation"
echo "b" | \
timeout ${timeout_test} \
ip netns exec $ns \
- ./mptcp_connect -p 10000 -j -t ${timeout_poll} \
+ ./mptcp_connect -p 10000 -r 0 -t ${timeout_poll} \
127.0.0.1 >/dev/null &
-sleep 0.1
+wait_connected $ns 10000
chk_msk_nr 2 "after MPC handshake "
chk_msk_remote_key_nr 2 "....chk remote_key"
chk_msk_fallback_nr 0 "....chk no fallback"
@@ -101,13 +131,13 @@ echo "a" | \
ip netns exec $ns \
./mptcp_connect -p 10001 -l -s TCP -t ${timeout_poll} \
0.0.0.0 >/dev/null &
-sleep 0.1
+wait_local_port_listen $ns 10001
echo "b" | \
timeout ${timeout_test} \
ip netns exec $ns \
- ./mptcp_connect -p 10001 -j -t ${timeout_poll} \
+ ./mptcp_connect -p 10001 -r 0 -t ${timeout_poll} \
127.0.0.1 >/dev/null &
-sleep 0.1
+wait_connected $ns 10001
chk_msk_fallback_nr 1 "check fallback"
flush_pids
@@ -119,7 +149,7 @@ for I in `seq 1 $NR_CLIENTS`; do
./mptcp_connect -p $((I+10001)) -l -w 10 \
-t ${timeout_poll} 0.0.0.0 >/dev/null &
done
-sleep 0.1
+wait_local_port_listen $ns $((NR_CLIENTS + 10001))
for I in `seq 1 $NR_CLIENTS`; do
echo "b" | \
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
index cb5809b89081..f0f4ab96b8f3 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
@@ -763,8 +763,8 @@ run_tests_disconnect()
run_tests_lo "$ns1" "$ns1" dead:beef:1::1 1 "-I 3 -i $old_cin"
# restore previous status
- cout=$old_cout
- cout_disconnect="$cout".disconnect
+ sin=$old_sin
+ sin_disconnect="$cout".disconnect
cin=$old_cin
cin_disconnect="$cin".disconnect
connect_per_transfer=1
diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 27d0eb9afdca..0c8a2a20b96c 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -75,6 +75,7 @@ init()
# 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$i
+ ip -net "$ns2" route add default via dead:beef:$i::1 dev ns2eth$i metric 10$i
done
}
@@ -659,6 +660,7 @@ chk_join_nr()
local ack_nr=$4
local count
local dump_stats
+ local with_cookie
printf "%02u %-36s %s" "$TEST_COUNT" "$msg" "syn"
count=`ip netns exec $ns1 nstat -as | grep MPTcpExtMPJoinSynRx | awk '{print $2}'`
@@ -672,12 +674,20 @@ chk_join_nr()
fi
echo -n " - synack"
+ with_cookie=`ip netns exec $ns2 sysctl -n net.ipv4.tcp_syncookies`
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 $syn_ack_nr"
- ret=1
- dump_stats=1
+ # simult connections exceeding the limit with cookie enabled could go up to
+ # synack validation as the conn limit can be enforced reliably only after
+ # the subflow creation
+ if [ "$with_cookie" = 2 ] && [ "$count" -gt "$syn_ack_nr" ] && [ "$count" -le "$syn_nr" ]; then
+ echo -n "[ ok ]"
+ else
+ echo "[fail] got $count JOIN[s] synack expected $syn_ack_nr"
+ ret=1
+ dump_stats=1
+ fi
else
echo -n "[ ok ]"
fi
@@ -751,11 +761,17 @@ chk_add_nr()
local mis_ack_nr=${8:-0}
local count
local dump_stats
+ local timeout
+
+ timeout=`ip netns exec $ns1 sysctl -n net.mptcp.add_addr_timeout`
printf "%-39s %s" " " "add"
- count=`ip netns exec $ns2 nstat -as | grep MPTcpExtAddAddr | awk '{print $2}'`
+ count=`ip netns exec $ns2 nstat -as MPTcpExtAddAddr | grep MPTcpExtAddAddr | awk '{print $2}'`
[ -z "$count" ] && count=0
- if [ "$count" != "$add_nr" ]; then
+
+ # if the test configured a short timeout tolerate greater then expected
+ # add addrs options, due to retransmissions
+ if [ "$count" != "$add_nr" ] && [ "$timeout" -gt 1 -o "$count" -lt "$add_nr" ]; then
echo "[fail] got $count ADD_ADDR[s] expected $add_nr"
ret=1
dump_stats=1
@@ -960,7 +976,7 @@ wait_for_tw()
local ns=$1
while [ $time -lt $timeout_ms ]; do
- local cnt=$(ip netns exec $ns ss -t state time-wait |wc -l)
+ local cnt=$(ip netns exec $ns nstat -as TcpAttemptFails | grep TcpAttemptFails | awk '{print $2}')
[ "$cnt" = 1 ] && return 1
time=$((time + 100))
@@ -1157,7 +1173,11 @@ signal_address_tests()
ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags signal
ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags signal
ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags signal
- run_tests $ns1 $ns2 10.0.1.1
+
+ # the peer could possibly miss some addr notification, allow retransmission
+ ip netns exec $ns1 sysctl -q net.mptcp.add_addr_timeout=1
+ run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow
+ chk_join_nr "signal addresses race test" 3 3 3
# the server will not signal the address terminating
# the MPC subflow
@@ -1476,7 +1496,7 @@ ipv6_tests()
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 dead:beef:3::2 flags subflow
+ ip netns exec $ns2 ./pm_nl_ctl add dead:beef:3::2 dev ns2eth3 flags subflow
run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow
chk_join_nr "single subflow IPv6" 1 1 1
@@ -1511,7 +1531,7 @@ ipv6_tests()
ip netns exec $ns1 ./pm_nl_ctl limits 0 2
ip netns exec $ns1 ./pm_nl_ctl add dead:beef:2::1 flags signal
ip netns exec $ns2 ./pm_nl_ctl limits 1 2
- ip netns exec $ns2 ./pm_nl_ctl add dead:beef:3::2 flags subflow
+ ip netns exec $ns2 ./pm_nl_ctl add dead:beef:3::2 dev ns2eth3 flags subflow
run_tests $ns1 $ns2 dead:beef:1::1 0 -1 -1 slow
chk_join_nr "remove subflow and signal IPv6" 2 2 2
chk_add_nr 1 1
diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index 543ad7513a8e..694732e4b344 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -374,6 +374,16 @@ run_cmd() {
return $rc
}
+run_cmd_bg() {
+ cmd="$*"
+
+ if [ "$VERBOSE" = "1" ]; then
+ printf " COMMAND: %s &\n" "${cmd}"
+ fi
+
+ $cmd 2>&1 &
+}
+
# Find the auto-generated name for this namespace
nsname() {
eval echo \$NS_$1
@@ -670,10 +680,10 @@ setup_nettest_xfrm() {
[ ${1} -eq 6 ] && proto="-6" || proto=""
port=${2}
- run_cmd ${ns_a} nettest ${proto} -q -D -s -x -p ${port} -t 5 &
+ run_cmd_bg "${ns_a}" nettest "${proto}" -q -D -s -x -p "${port}" -t 5
nettest_pids="${nettest_pids} $!"
- run_cmd ${ns_b} nettest ${proto} -q -D -s -x -p ${port} -t 5 &
+ run_cmd_bg "${ns_b}" nettest "${proto}" -q -D -s -x -p "${port}" -t 5
nettest_pids="${nettest_pids} $!"
}
@@ -865,7 +875,6 @@ setup_ovs_bridge() {
setup() {
[ "$(id -u)" -ne 0 ] && echo " need to run as root" && return $ksft_skip
- cleanup
for arg do
eval setup_${arg} || { echo " ${arg} not supported"; return 1; }
done
@@ -876,7 +885,7 @@ trace() {
for arg do
[ "${ns_cmd}" = "" ] && ns_cmd="${arg}" && continue
- ${ns_cmd} tcpdump -s 0 -i "${arg}" -w "${name}_${arg}.pcap" 2> /dev/null &
+ ${ns_cmd} tcpdump --immediate-mode -s 0 -i "${arg}" -w "${name}_${arg}.pcap" 2> /dev/null &
tcpdump_pids="${tcpdump_pids} $!"
ns_cmd=
done
@@ -1836,6 +1845,10 @@ run_test() {
unset IFS
+ # Since cleanup() relies on variables modified by this subshell, it
+ # has to run in this context.
+ trap cleanup EXIT
+
if [ "$VERBOSE" = "1" ]; then
printf "\n##########################################################################\n\n"
fi
diff --git a/tools/testing/selftests/net/settings b/tools/testing/selftests/net/settings
index 694d70710ff0..dfc27cdc6c05 100644
--- a/tools/testing/selftests/net/settings
+++ b/tools/testing/selftests/net/settings
@@ -1 +1 @@
-timeout=300
+timeout=1500
diff --git a/tools/testing/selftests/netfilter/.gitignore b/tools/testing/selftests/netfilter/.gitignore
index 8448f74adfec..4cb887b57413 100644
--- a/tools/testing/selftests/netfilter/.gitignore
+++ b/tools/testing/selftests/netfilter/.gitignore
@@ -1,2 +1,3 @@
# SPDX-License-Identifier: GPL-2.0-only
nf-queue
+connect_close
diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile
index ffca314897c4..7e81c9a7fff9 100644
--- a/tools/testing/selftests/netfilter/Makefile
+++ b/tools/testing/selftests/netfilter/Makefile
@@ -6,9 +6,9 @@ TEST_PROGS := nft_trans_stress.sh nft_fib.sh nft_nat.sh bridge_brouter.sh \
nft_concat_range.sh nft_conntrack_helper.sh \
nft_queue.sh nft_meta.sh nf_nat_edemux.sh \
ipip-conntrack-mtu.sh conntrack_tcp_unreplied.sh \
- conntrack_vrf.sh
+ conntrack_vrf.sh nft_synproxy.sh
LDLIBS = -lmnl
-TEST_GEN_FILES = nf-queue
+TEST_GEN_FILES = nf-queue connect_close
include ../lib.mk
diff --git a/tools/testing/selftests/netfilter/connect_close.c b/tools/testing/selftests/netfilter/connect_close.c
new file mode 100644
index 000000000000..1c3b0add54c4
--- /dev/null
+++ b/tools/testing/selftests/netfilter/connect_close.c
@@ -0,0 +1,136 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <fcntl.h>
+#include <string.h>
+#include <unistd.h>
+#include <signal.h>
+
+#include <arpa/inet.h>
+#include <sys/socket.h>
+
+#define PORT 12345
+#define RUNTIME 10
+
+static struct {
+ unsigned int timeout;
+ unsigned int port;
+} opts = {
+ .timeout = RUNTIME,
+ .port = PORT,
+};
+
+static void handler(int sig)
+{
+ _exit(sig == SIGALRM ? 0 : 1);
+}
+
+static void set_timeout(void)
+{
+ struct sigaction action = {
+ .sa_handler = handler,
+ };
+
+ sigaction(SIGALRM, &action, NULL);
+
+ alarm(opts.timeout);
+}
+
+static void do_connect(const struct sockaddr_in *dst)
+{
+ int s = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP);
+
+ if (s >= 0)
+ fcntl(s, F_SETFL, O_NONBLOCK);
+
+ connect(s, (struct sockaddr *)dst, sizeof(*dst));
+ close(s);
+}
+
+static void do_accept(const struct sockaddr_in *src)
+{
+ int c, one = 1, s = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP);
+
+ if (s < 0)
+ return;
+
+ setsockopt(s, SOL_SOCKET, SO_REUSEADDR, &one, sizeof(one));
+ setsockopt(s, SOL_SOCKET, SO_REUSEPORT, &one, sizeof(one));
+
+ bind(s, (struct sockaddr *)src, sizeof(*src));
+
+ listen(s, 16);
+
+ c = accept(s, NULL, NULL);
+ if (c >= 0)
+ close(c);
+
+ close(s);
+}
+
+static int accept_loop(void)
+{
+ struct sockaddr_in src = {
+ .sin_family = AF_INET,
+ .sin_port = htons(opts.port),
+ };
+
+ inet_pton(AF_INET, "127.0.0.1", &src.sin_addr);
+
+ set_timeout();
+
+ for (;;)
+ do_accept(&src);
+
+ return 1;
+}
+
+static int connect_loop(void)
+{
+ struct sockaddr_in dst = {
+ .sin_family = AF_INET,
+ .sin_port = htons(opts.port),
+ };
+
+ inet_pton(AF_INET, "127.0.0.1", &dst.sin_addr);
+
+ set_timeout();
+
+ for (;;)
+ do_connect(&dst);
+
+ return 1;
+}
+
+static void parse_opts(int argc, char **argv)
+{
+ int c;
+
+ while ((c = getopt(argc, argv, "t:p:")) != -1) {
+ switch (c) {
+ case 't':
+ opts.timeout = atoi(optarg);
+ break;
+ case 'p':
+ opts.port = atoi(optarg);
+ break;
+ }
+ }
+}
+
+int main(int argc, char *argv[])
+{
+ pid_t p;
+
+ parse_opts(argc, argv);
+
+ p = fork();
+ if (p < 0)
+ return 111;
+
+ if (p > 0)
+ return accept_loop();
+
+ return connect_loop();
+}
diff --git a/tools/testing/selftests/netfilter/nft_concat_range.sh b/tools/testing/selftests/netfilter/nft_concat_range.sh
index ed61f6cab60f..b35010cc7f6a 100755
--- a/tools/testing/selftests/netfilter/nft_concat_range.sh
+++ b/tools/testing/selftests/netfilter/nft_concat_range.sh
@@ -27,7 +27,7 @@ TYPES="net_port port_net net6_port port_proto net6_port_mac net6_port_mac_proto
net6_port_net6_port net_port_mac_proto_net"
# Reported bugs, also described by TYPE_ variables below
-BUGS="flush_remove_add"
+BUGS="flush_remove_add reload"
# List of possible paths to pktgen script from kernel tree for performance tests
PKTGEN_SCRIPT_PATHS="
@@ -354,6 +354,23 @@ TYPE_flush_remove_add="
display Add two elements, flush, re-add
"
+TYPE_reload="
+display net,mac with reload
+type_spec ipv4_addr . ether_addr
+chain_spec ip daddr . ether saddr
+dst addr4
+src mac
+start 1
+count 1
+src_delta 2000
+tools sendip nc bash
+proto udp
+
+race_repeat 0
+
+perf_duration 0
+"
+
# Set template for all tests, types and rules are filled in depending on test
set_template='
flush ruleset
@@ -1473,6 +1490,59 @@ test_bug_flush_remove_add() {
nft flush ruleset
}
+# - add ranged element, check that packets match it
+# - reload the set, check packets still match
+test_bug_reload() {
+ setup veth send_"${proto}" set || return ${KSELFTEST_SKIP}
+ rstart=${start}
+
+ range_size=1
+ for i in $(seq "${start}" $((start + count))); do
+ end=$((start + range_size))
+
+ # Avoid negative or zero-sized port ranges
+ if [ $((end / 65534)) -gt $((start / 65534)) ]; then
+ start=${end}
+ end=$((end + 1))
+ fi
+ srcstart=$((start + src_delta))
+ srcend=$((end + src_delta))
+
+ add "$(format)" || return 1
+ range_size=$((range_size + 1))
+ start=$((end + range_size))
+ done
+
+ # check kernel does allocate pcpu sctrach map
+ # for reload with no elemet add/delete
+ ( echo flush set inet filter test ;
+ nft list set inet filter test ) | nft -f -
+
+ start=${rstart}
+ range_size=1
+
+ for i in $(seq "${start}" $((start + count))); do
+ end=$((start + range_size))
+
+ # Avoid negative or zero-sized port ranges
+ if [ $((end / 65534)) -gt $((start / 65534)) ]; then
+ start=${end}
+ end=$((end + 1))
+ fi
+ srcstart=$((start + src_delta))
+ srcend=$((end + src_delta))
+
+ for j in $(seq ${start} $((range_size / 2 + 1)) ${end}); do
+ send_match "${j}" $((j + src_delta)) || return 1
+ done
+
+ range_size=$((range_size + 1))
+ start=$((end + range_size))
+ done
+
+ nft flush ruleset
+}
+
test_reported_issues() {
eval test_bug_"${subtest}"
}
@@ -1531,4 +1601,4 @@ for name in ${TESTS}; do
done
done
-[ ${passed} -eq 0 ] && exit ${KSELFTEST_SKIP}
+[ ${passed} -eq 0 ] && exit ${KSELFTEST_SKIP} || exit 0
diff --git a/tools/testing/selftests/netfilter/nft_fib.sh b/tools/testing/selftests/netfilter/nft_fib.sh
index 6caf6ac8c285..695a1958723f 100755
--- a/tools/testing/selftests/netfilter/nft_fib.sh
+++ b/tools/testing/selftests/netfilter/nft_fib.sh
@@ -174,6 +174,7 @@ test_ping() {
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
+ip netns exec ${nsrouter} sysctl net.ipv4.conf.veth0.rp_filter=0 > /dev/null
sleep 3
diff --git a/tools/testing/selftests/netfilter/nft_nat.sh b/tools/testing/selftests/netfilter/nft_nat.sh
index 349a319a9e51..eb8543b9a5c4 100755
--- a/tools/testing/selftests/netfilter/nft_nat.sh
+++ b/tools/testing/selftests/netfilter/nft_nat.sh
@@ -880,9 +880,8 @@ EOF
return $ksft_skip
fi
- # test default behaviour. Packet from ns1 to ns0 is not redirected
- # due to automatic port translation.
- test_port_shadow "default" "ROUTER"
+ # test default behaviour. Packet from ns1 to ns0 is redirected to ns2.
+ test_port_shadow "default" "CLIENT"
# test packet filter based mitigation: prevent forwarding of
# packets claiming to come from the service port.
@@ -899,6 +898,144 @@ EOF
ip netns exec "$ns0" nft delete table $family nat
}
+test_stateless_nat_ip()
+{
+ local lret=0
+
+ ip netns exec "$ns0" sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null
+ ip netns exec "$ns0" sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null
+
+ ip netns exec "$ns2" ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1
+ if [ $? -ne 0 ] ; then
+ echo "ERROR: cannot ping $ns1 from $ns2 before loading stateless rules"
+ return 1
+ fi
+
+ip netns exec "$ns0" nft -f /dev/stdin <<EOF
+table ip stateless {
+ map xlate_in {
+ typeof meta iifname . ip saddr . ip daddr : ip daddr
+ elements = {
+ "veth1" . 10.0.2.99 . 10.0.1.99 : 10.0.2.2,
+ }
+ }
+ map xlate_out {
+ typeof meta iifname . ip saddr . ip daddr : ip daddr
+ elements = {
+ "veth0" . 10.0.1.99 . 10.0.2.2 : 10.0.2.99
+ }
+ }
+
+ chain prerouting {
+ type filter hook prerouting priority -400; policy accept;
+ ip saddr set meta iifname . ip saddr . ip daddr map @xlate_in
+ ip daddr set meta iifname . ip saddr . ip daddr map @xlate_out
+ }
+}
+EOF
+ if [ $? -ne 0 ]; then
+ echo "SKIP: Could not add ip statless rules"
+ return $ksft_skip
+ fi
+
+ reset_counters
+
+ ip netns exec "$ns2" ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1
+ if [ $? -ne 0 ] ; then
+ echo "ERROR: cannot ping $ns1 from $ns2 with stateless rules"
+ lret=1
+ fi
+
+ # ns1 should have seen packets from .2.2, due to stateless rewrite.
+ expect="packets 1 bytes 84"
+ cnt=$(ip netns exec "$ns1" nft list counter inet filter ns0insl | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter "$ns1" ns0insl "$expect" "test_stateless 1"
+ lret=1
+ fi
+
+ for dir in "in" "out" ; do
+ cnt=$(ip netns exec "$ns2" nft list counter inet filter ns1${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter "$ns2" ns1$dir "$expect" "test_stateless 2"
+ lret=1
+ fi
+ done
+
+ # ns1 should not have seen packets from ns2, due to masquerade
+ expect="packets 0 bytes 0"
+ for dir in "in" "out" ; do
+ cnt=$(ip netns exec "$ns1" nft list counter inet filter ns2${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter "$ns1" ns0$dir "$expect" "test_stateless 3"
+ lret=1
+ fi
+
+ cnt=$(ip netns exec "$ns0" nft list counter inet filter ns1${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter "$ns0" ns1$dir "$expect" "test_stateless 4"
+ lret=1
+ fi
+ done
+
+ reset_counters
+
+ socat -h > /dev/null 2>&1
+ if [ $? -ne 0 ];then
+ echo "SKIP: Could not run stateless nat frag test without socat tool"
+ if [ $lret -eq 0 ]; then
+ return $ksft_skip
+ fi
+
+ ip netns exec "$ns0" nft delete table ip stateless
+ return $lret
+ fi
+
+ local tmpfile=$(mktemp)
+ dd if=/dev/urandom of=$tmpfile bs=4096 count=1 2>/dev/null
+
+ local outfile=$(mktemp)
+ ip netns exec "$ns1" timeout 3 socat -u UDP4-RECV:4233 OPEN:$outfile < /dev/null &
+ sc_r=$!
+
+ sleep 1
+ # re-do with large ping -> ip fragmentation
+ ip netns exec "$ns2" timeout 3 socat - UDP4-SENDTO:"10.0.1.99:4233" < "$tmpfile" > /dev/null
+ if [ $? -ne 0 ] ; then
+ echo "ERROR: failed to test udp $ns1 to $ns2 with stateless ip nat" 1>&2
+ lret=1
+ fi
+
+ wait
+
+ cmp "$tmpfile" "$outfile"
+ if [ $? -ne 0 ]; then
+ ls -l "$tmpfile" "$outfile"
+ echo "ERROR: in and output file mismatch when checking udp with stateless nat" 1>&2
+ lret=1
+ fi
+
+ rm -f "$tmpfile" "$outfile"
+
+ # ns1 should have seen packets from 2.2, due to stateless rewrite.
+ expect="packets 3 bytes 4164"
+ cnt=$(ip netns exec "$ns1" nft list counter inet filter ns0insl | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter "$ns1" ns0insl "$expect" "test_stateless 5"
+ lret=1
+ fi
+
+ ip netns exec "$ns0" nft delete table ip stateless
+ if [ $? -ne 0 ]; then
+ echo "ERROR: Could not delete table ip stateless" 1>&2
+ lret=1
+ fi
+
+ test $lret -eq 0 && echo "PASS: IP statless for $ns2"
+
+ return $lret
+}
+
# ip netns exec "$ns0" ping -c 1 -q 10.0.$i.99
for i in 0 1 2; do
ip netns exec ns$i-$sfx nft -f /dev/stdin <<EOF
@@ -965,6 +1102,19 @@ table inet filter {
EOF
done
+# special case for stateless nat check, counter needs to
+# be done before (input) ip defragmentation
+ip netns exec ns1-$sfx nft -f /dev/stdin <<EOF
+table inet filter {
+ counter ns0insl {}
+
+ chain pre {
+ type filter hook prerouting priority -400; policy accept;
+ ip saddr 10.0.2.2 counter name "ns0insl"
+ }
+}
+EOF
+
sleep 3
# test basic connectivity
for i in 1 2; do
@@ -1019,6 +1169,7 @@ $test_inet_nat && test_redirect inet
$test_inet_nat && test_redirect6 inet
test_port_shadowing
+test_stateless_nat_ip
if [ $ret -ne 0 ];then
echo -n "FAIL: "
diff --git a/tools/testing/selftests/netfilter/nft_queue.sh b/tools/testing/selftests/netfilter/nft_queue.sh
index 7d27f1f3bc01..e12729753351 100755
--- a/tools/testing/selftests/netfilter/nft_queue.sh
+++ b/tools/testing/selftests/netfilter/nft_queue.sh
@@ -113,6 +113,7 @@ table inet $name {
chain output {
type filter hook output priority $prio; policy accept;
tcp dport 12345 queue num 3
+ tcp sport 23456 queue num 3
jump nfq
}
chain post {
@@ -296,6 +297,23 @@ test_tcp_localhost()
wait 2>/dev/null
}
+test_tcp_localhost_connectclose()
+{
+ tmpfile=$(mktemp) || exit 1
+
+ ip netns exec ${nsrouter} ./connect_close -p 23456 -t $timeout &
+
+ ip netns exec ${nsrouter} ./nf-queue -q 3 -t $timeout &
+ local nfqpid=$!
+
+ sleep 1
+ rm -f "$tmpfile"
+
+ wait $rpid
+ [ $? -eq 0 ] && echo "PASS: tcp via loopback with connect/close"
+ wait 2>/dev/null
+}
+
test_tcp_localhost_requeue()
{
ip netns exec ${nsrouter} nft -f /dev/stdin <<EOF
@@ -424,6 +442,7 @@ test_queue 20
test_tcp_forward
test_tcp_localhost
+test_tcp_localhost_connectclose
test_tcp_localhost_requeue
test_icmp_vrf
diff --git a/tools/testing/selftests/netfilter/nft_synproxy.sh b/tools/testing/selftests/netfilter/nft_synproxy.sh
new file mode 100755
index 000000000000..b62933b680d6
--- /dev/null
+++ b/tools/testing/selftests/netfilter/nft_synproxy.sh
@@ -0,0 +1,117 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+ret=0
+
+rnd=$(mktemp -u XXXXXXXX)
+nsr="nsr-$rnd" # synproxy machine
+ns1="ns1-$rnd" # iperf client
+ns2="ns2-$rnd" # iperf server
+
+checktool (){
+ if ! $1 > /dev/null 2>&1; then
+ echo "SKIP: Could not $2"
+ exit $ksft_skip
+ fi
+}
+
+checktool "nft --version" "run test without nft tool"
+checktool "ip -Version" "run test without ip tool"
+checktool "iperf3 --version" "run test without iperf3"
+checktool "ip netns add $nsr" "create net namespace"
+
+modprobe -q nf_conntrack
+
+ip netns add $ns1
+ip netns add $ns2
+
+cleanup() {
+ ip netns pids $ns1 | xargs kill 2>/dev/null
+ ip netns pids $ns2 | xargs kill 2>/dev/null
+ ip netns del $ns1
+ ip netns del $ns2
+
+ ip netns del $nsr
+}
+
+trap cleanup EXIT
+
+ip link add veth0 netns $nsr type veth peer name eth0 netns $ns1
+ip link add veth1 netns $nsr type veth peer name eth0 netns $ns2
+
+for dev in lo veth0 veth1; do
+ip -net $nsr link set $dev up
+done
+
+ip -net $nsr addr add 10.0.1.1/24 dev veth0
+ip -net $nsr addr add 10.0.2.1/24 dev veth1
+
+ip netns exec $nsr sysctl -q net.ipv4.conf.veth0.forwarding=1
+ip netns exec $nsr sysctl -q net.ipv4.conf.veth1.forwarding=1
+ip netns exec $nsr sysctl -q net.netfilter.nf_conntrack_tcp_loose=0
+
+for n in $ns1 $ns2; do
+ ip -net $n link set lo up
+ ip -net $n link set eth0 up
+done
+ip -net $ns1 addr add 10.0.1.99/24 dev eth0
+ip -net $ns2 addr add 10.0.2.99/24 dev eth0
+ip -net $ns1 route add default via 10.0.1.1
+ip -net $ns2 route add default via 10.0.2.1
+
+# test basic connectivity
+if ! ip netns exec $ns1 ping -c 1 -q 10.0.2.99 > /dev/null; then
+ echo "ERROR: $ns1 cannot reach $ns2" 1>&2
+ exit 1
+fi
+
+if ! ip netns exec $ns2 ping -c 1 -q 10.0.1.99 > /dev/null; then
+ echo "ERROR: $ns2 cannot reach $ns1" 1>&2
+ exit 1
+fi
+
+ip netns exec $ns2 iperf3 -s > /dev/null 2>&1 &
+# ip netns exec $nsr tcpdump -vvv -n -i veth1 tcp | head -n 10 &
+
+sleep 1
+
+ip netns exec $nsr nft -f - <<EOF
+table inet filter {
+ chain prerouting {
+ type filter hook prerouting priority -300; policy accept;
+ meta iif veth0 tcp flags syn counter notrack
+ }
+
+ chain forward {
+ type filter hook forward priority 0; policy accept;
+
+ ct state new,established counter accept
+
+ meta iif veth0 meta l4proto tcp ct state untracked,invalid synproxy mss 1460 sack-perm timestamp
+
+ ct state invalid counter drop
+
+ # make ns2 unreachable w.o. tcp synproxy
+ tcp flags syn counter drop
+ }
+}
+EOF
+if [ $? -ne 0 ]; then
+ echo "SKIP: Cannot add nft synproxy"
+ exit $ksft_skip
+fi
+
+ip netns exec $ns1 timeout 5 iperf3 -c 10.0.2.99 -n $((1 * 1024 * 1024)) > /dev/null
+
+if [ $? -ne 0 ]; then
+ echo "FAIL: iperf3 returned an error" 1>&2
+ ret=$?
+ ip netns exec $nsr nft list ruleset
+else
+ echo "PASS: synproxy connection successful"
+fi
+
+exit $ret
diff --git a/tools/testing/selftests/netfilter/nft_zones_many.sh b/tools/testing/selftests/netfilter/nft_zones_many.sh
index 04633119b29a..5a8db0b48928 100755
--- a/tools/testing/selftests/netfilter/nft_zones_many.sh
+++ b/tools/testing/selftests/netfilter/nft_zones_many.sh
@@ -9,7 +9,7 @@ ns="ns-$sfx"
# Kselftest framework requirement - SKIP code is 4.
ksft_skip=4
-zones=20000
+zones=2000
have_ct_tool=0
ret=0
@@ -75,10 +75,10 @@ EOF
while [ $i -lt $max_zones ]; do
local start=$(date +%s%3N)
- i=$((i + 10000))
+ i=$((i + 1000))
j=$((j + 1))
# nft rule in output places each packet in a different zone.
- dd if=/dev/zero of=/dev/stdout bs=8k count=10000 2>/dev/null | ip netns exec "$ns" socat STDIN UDP:127.0.0.1:12345,sourceport=12345
+ dd if=/dev/zero of=/dev/stdout bs=8k count=1000 2>/dev/null | ip netns exec "$ns" socat STDIN UDP:127.0.0.1:12345,sourceport=12345
if [ $? -ne 0 ] ;then
ret=1
break
@@ -86,7 +86,7 @@ EOF
stop=$(date +%s%3N)
local duration=$((stop-start))
- echo "PASS: added 10000 entries in $duration ms (now $i total, loop $j)"
+ echo "PASS: added 1000 entries in $duration ms (now $i total, loop $j)"
done
if [ $have_ct_tool -eq 1 ]; then
@@ -128,11 +128,11 @@ test_conntrack_tool() {
break
fi
- if [ $((i%10000)) -eq 0 ];then
+ if [ $((i%1000)) -eq 0 ];then
stop=$(date +%s%3N)
local duration=$((stop-start))
- echo "PASS: added 10000 entries in $duration ms (now $i total)"
+ echo "PASS: added 1000 entries in $duration ms (now $i total)"
start=$stop
fi
done
diff --git a/tools/testing/selftests/openat2/Makefile b/tools/testing/selftests/openat2/Makefile
index 4b93b1417b86..843ba56d8e49 100644
--- a/tools/testing/selftests/openat2/Makefile
+++ b/tools/testing/selftests/openat2/Makefile
@@ -5,4 +5,4 @@ TEST_GEN_PROGS := openat2_test resolve_test rename_attack_test
include ../lib.mk
-$(TEST_GEN_PROGS): helpers.c
+$(TEST_GEN_PROGS): helpers.c helpers.h
diff --git a/tools/testing/selftests/openat2/helpers.h b/tools/testing/selftests/openat2/helpers.h
index a6ea27344db2..7056340b9339 100644
--- a/tools/testing/selftests/openat2/helpers.h
+++ b/tools/testing/selftests/openat2/helpers.h
@@ -9,6 +9,7 @@
#define _GNU_SOURCE
#include <stdint.h>
+#include <stdbool.h>
#include <errno.h>
#include <linux/types.h>
#include "../kselftest.h"
@@ -62,11 +63,12 @@ bool needs_openat2(const struct open_how *how);
(similar to chroot(2)). */
#endif /* RESOLVE_IN_ROOT */
-#define E_func(func, ...) \
- do { \
- if (func(__VA_ARGS__) < 0) \
- ksft_exit_fail_msg("%s:%d %s failed\n", \
- __FILE__, __LINE__, #func);\
+#define E_func(func, ...) \
+ do { \
+ errno = 0; \
+ if (func(__VA_ARGS__) < 0) \
+ ksft_exit_fail_msg("%s:%d %s failed - errno:%d\n", \
+ __FILE__, __LINE__, #func, errno); \
} while (0)
#define E_asprintf(...) E_func(asprintf, __VA_ARGS__)
diff --git a/tools/testing/selftests/openat2/openat2_test.c b/tools/testing/selftests/openat2/openat2_test.c
index 1bddbe934204..7fb902099de4 100644
--- a/tools/testing/selftests/openat2/openat2_test.c
+++ b/tools/testing/selftests/openat2/openat2_test.c
@@ -259,6 +259,16 @@ void test_openat2_flags(void)
unlink(path);
fd = sys_openat2(AT_FDCWD, path, &test->how);
+ if (fd < 0 && fd == -EOPNOTSUPP) {
+ /*
+ * Skip the testcase if it failed because not supported
+ * by FS. (e.g. a valid O_TMPFILE combination on NFS)
+ */
+ ksft_test_result_skip("openat2 with %s fails with %d (%s)\n",
+ test->name, fd, strerror(-fd));
+ goto next;
+ }
+
if (test->err >= 0)
failed = (fd < 0);
else
@@ -303,7 +313,7 @@ skip:
else
resultfn("openat2 with %s fails with %d (%s)\n",
test->name, test->err, strerror(-test->err));
-
+next:
free(fdpath);
fflush(stdout);
}
diff --git a/tools/testing/selftests/perf_events/sigtrap_threads.c b/tools/testing/selftests/perf_events/sigtrap_threads.c
index 8e83cf91513a..6d849dc2bee0 100644
--- a/tools/testing/selftests/perf_events/sigtrap_threads.c
+++ b/tools/testing/selftests/perf_events/sigtrap_threads.c
@@ -44,9 +44,10 @@ static struct {
} ctx;
/* Unique value to check si_perf_data is correctly set from perf_event_attr::sig_data. */
-#define TEST_SIG_DATA(addr) (~(unsigned long)(addr))
+#define TEST_SIG_DATA(addr, id) (~(unsigned long)(addr) + id)
-static struct perf_event_attr make_event_attr(bool enabled, volatile void *addr)
+static struct perf_event_attr make_event_attr(bool enabled, volatile void *addr,
+ unsigned long id)
{
struct perf_event_attr attr = {
.type = PERF_TYPE_BREAKPOINT,
@@ -60,7 +61,7 @@ static struct perf_event_attr make_event_attr(bool enabled, volatile void *addr)
.inherit_thread = 1, /* ... but only cloned with CLONE_THREAD. */
.remove_on_exec = 1, /* Required by sigtrap. */
.sigtrap = 1, /* Request synchronous SIGTRAP on event. */
- .sig_data = TEST_SIG_DATA(addr),
+ .sig_data = TEST_SIG_DATA(addr, id),
};
return attr;
}
@@ -110,7 +111,7 @@ FIXTURE(sigtrap_threads)
FIXTURE_SETUP(sigtrap_threads)
{
- struct perf_event_attr attr = make_event_attr(false, &ctx.iterate_on);
+ struct perf_event_attr attr = make_event_attr(false, &ctx.iterate_on, 0);
struct sigaction action = {};
int i;
@@ -165,7 +166,7 @@ TEST_F(sigtrap_threads, enable_event)
EXPECT_EQ(ctx.tids_want_signal, 0);
EXPECT_EQ(ctx.first_siginfo.si_addr, &ctx.iterate_on);
EXPECT_EQ(ctx.first_siginfo.si_perf_type, PERF_TYPE_BREAKPOINT);
- EXPECT_EQ(ctx.first_siginfo.si_perf_data, TEST_SIG_DATA(&ctx.iterate_on));
+ EXPECT_EQ(ctx.first_siginfo.si_perf_data, TEST_SIG_DATA(&ctx.iterate_on, 0));
/* Check enabled for parent. */
ctx.iterate_on = 0;
@@ -175,7 +176,7 @@ TEST_F(sigtrap_threads, enable_event)
/* Test that modification propagates to all inherited events. */
TEST_F(sigtrap_threads, modify_and_enable_event)
{
- struct perf_event_attr new_attr = make_event_attr(true, &ctx.iterate_on);
+ struct perf_event_attr new_attr = make_event_attr(true, &ctx.iterate_on, 42);
EXPECT_EQ(ioctl(self->fd, PERF_EVENT_IOC_MODIFY_ATTRIBUTES, &new_attr), 0);
run_test_threads(_metadata, self);
@@ -184,7 +185,7 @@ TEST_F(sigtrap_threads, modify_and_enable_event)
EXPECT_EQ(ctx.tids_want_signal, 0);
EXPECT_EQ(ctx.first_siginfo.si_addr, &ctx.iterate_on);
EXPECT_EQ(ctx.first_siginfo.si_perf_type, PERF_TYPE_BREAKPOINT);
- EXPECT_EQ(ctx.first_siginfo.si_perf_data, TEST_SIG_DATA(&ctx.iterate_on));
+ EXPECT_EQ(ctx.first_siginfo.si_perf_data, TEST_SIG_DATA(&ctx.iterate_on, 42));
/* Check enabled for parent. */
ctx.iterate_on = 0;
@@ -204,7 +205,7 @@ TEST_F(sigtrap_threads, signal_stress)
EXPECT_EQ(ctx.tids_want_signal, 0);
EXPECT_EQ(ctx.first_siginfo.si_addr, &ctx.iterate_on);
EXPECT_EQ(ctx.first_siginfo.si_perf_type, PERF_TYPE_BREAKPOINT);
- EXPECT_EQ(ctx.first_siginfo.si_perf_data, TEST_SIG_DATA(&ctx.iterate_on));
+ EXPECT_EQ(ctx.first_siginfo.si_perf_data, TEST_SIG_DATA(&ctx.iterate_on, 0));
}
TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/pidfd/pidfd.h b/tools/testing/selftests/pidfd/pidfd.h
index 01f8d3c0cf2c..6922d6417e1c 100644
--- a/tools/testing/selftests/pidfd/pidfd.h
+++ b/tools/testing/selftests/pidfd/pidfd.h
@@ -68,7 +68,7 @@
#define PIDFD_SKIP 3
#define PIDFD_XFAIL 4
-int wait_for_pid(pid_t pid)
+static inline int wait_for_pid(pid_t pid)
{
int status, ret;
@@ -78,13 +78,20 @@ again:
if (errno == EINTR)
goto again;
+ ksft_print_msg("waitpid returned -1, errno=%d\n", errno);
return -1;
}
- if (!WIFEXITED(status))
+ if (!WIFEXITED(status)) {
+ ksft_print_msg(
+ "waitpid !WIFEXITED, WIFSIGNALED=%d, WTERMSIG=%d\n",
+ WIFSIGNALED(status), WTERMSIG(status));
return -1;
+ }
- return WEXITSTATUS(status);
+ ret = WEXITSTATUS(status);
+ ksft_print_msg("waitpid WEXITSTATUS=%d\n", ret);
+ return ret;
}
static inline int sys_pidfd_open(pid_t pid, unsigned int flags)
diff --git a/tools/testing/selftests/pidfd/pidfd_fdinfo_test.c b/tools/testing/selftests/pidfd/pidfd_fdinfo_test.c
index 22558524f71c..3fd8e903118f 100644
--- a/tools/testing/selftests/pidfd/pidfd_fdinfo_test.c
+++ b/tools/testing/selftests/pidfd/pidfd_fdinfo_test.c
@@ -12,6 +12,7 @@
#include <string.h>
#include <syscall.h>
#include <sys/wait.h>
+#include <sys/mman.h>
#include "pidfd.h"
#include "../kselftest.h"
@@ -80,7 +81,10 @@ static inline int error_check(struct error *err, const char *test_name)
return err->code;
}
+#define CHILD_STACK_SIZE 8192
+
struct child {
+ char *stack;
pid_t pid;
int fd;
};
@@ -89,17 +93,22 @@ static struct child clone_newns(int (*fn)(void *), void *args,
struct error *err)
{
static int flags = CLONE_PIDFD | CLONE_NEWPID | CLONE_NEWNS | SIGCHLD;
- size_t stack_size = 1024;
- char *stack[1024] = { 0 };
struct child ret;
if (!(flags & CLONE_NEWUSER) && geteuid() != 0)
flags |= CLONE_NEWUSER;
+ ret.stack = mmap(NULL, CHILD_STACK_SIZE, PROT_READ | PROT_WRITE,
+ MAP_PRIVATE | MAP_ANONYMOUS | MAP_STACK, -1, 0);
+ if (ret.stack == MAP_FAILED) {
+ error_set(err, -1, "mmap of stack failed (errno %d)", errno);
+ return ret;
+ }
+
#ifdef __ia64__
- ret.pid = __clone2(fn, stack, stack_size, flags, args, &ret.fd);
+ ret.pid = __clone2(fn, ret.stack, CHILD_STACK_SIZE, flags, args, &ret.fd);
#else
- ret.pid = clone(fn, stack + stack_size, flags, args, &ret.fd);
+ ret.pid = clone(fn, ret.stack + CHILD_STACK_SIZE, flags, args, &ret.fd);
#endif
if (ret.pid < 0) {
@@ -129,6 +138,11 @@ static inline int child_join(struct child *child, struct error *err)
else if (r > 0)
error_set(err, r, "child %d reported: %d", child->pid, r);
+ if (munmap(child->stack, CHILD_STACK_SIZE)) {
+ error_set(err, -1, "munmap of child stack failed (errno %d)", errno);
+ r = -1;
+ }
+
return r;
}
diff --git a/tools/testing/selftests/pidfd/pidfd_test.c b/tools/testing/selftests/pidfd/pidfd_test.c
index 529eb700ac26..9a2d64901d59 100644
--- a/tools/testing/selftests/pidfd/pidfd_test.c
+++ b/tools/testing/selftests/pidfd/pidfd_test.c
@@ -441,7 +441,6 @@ static void test_pidfd_poll_exec(int use_waitpid)
{
int pid, pidfd = 0;
int status, ret;
- pthread_t t1;
time_t prog_start = time(NULL);
const char *test_name = "pidfd_poll check for premature notification on child thread exec";
@@ -500,13 +499,14 @@ static int child_poll_leader_exit_test(void *args)
*/
*child_exit_secs = time(NULL);
syscall(SYS_exit, 0);
+ /* Never reached, but appeases compiler thinking we should return. */
+ exit(0);
}
static void test_pidfd_poll_leader_exit(int use_waitpid)
{
int pid, pidfd = 0;
- int status, ret;
- time_t prog_start = time(NULL);
+ int status, ret = 0;
const char *test_name = "pidfd_poll check for premature notification on non-empty"
"group leader exit";
diff --git a/tools/testing/selftests/pidfd/pidfd_wait.c b/tools/testing/selftests/pidfd/pidfd_wait.c
index be2943f072f6..17999e082aa7 100644
--- a/tools/testing/selftests/pidfd/pidfd_wait.c
+++ b/tools/testing/selftests/pidfd/pidfd_wait.c
@@ -39,7 +39,7 @@ static int sys_waitid(int which, pid_t pid, siginfo_t *info, int options,
TEST(wait_simple)
{
- int pidfd = -1, status = 0;
+ int pidfd = -1;
pid_t parent_tid = -1;
struct clone_args args = {
.parent_tid = ptr_to_u64(&parent_tid),
@@ -47,7 +47,6 @@ TEST(wait_simple)
.flags = CLONE_PIDFD | CLONE_PARENT_SETTID,
.exit_signal = SIGCHLD,
};
- int ret;
pid_t pid;
siginfo_t info = {
.si_signo = 0,
@@ -88,7 +87,7 @@ TEST(wait_simple)
TEST(wait_states)
{
- int pidfd = -1, status = 0;
+ int pidfd = -1;
pid_t parent_tid = -1;
struct clone_args args = {
.parent_tid = ptr_to_u64(&parent_tid),
diff --git a/tools/testing/selftests/powerpc/security/mitigation-patching.sh b/tools/testing/selftests/powerpc/security/mitigation-patching.sh
index b0b20e0b4e30..f43aa4b77fba 100755
--- a/tools/testing/selftests/powerpc/security/mitigation-patching.sh
+++ b/tools/testing/selftests/powerpc/security/mitigation-patching.sh
@@ -44,7 +44,10 @@ mitigations="barrier_nospec stf_barrier count_cache_flush rfi_flush entry_flush
for m in $mitigations
do
- do_one "$m" &
+ if [[ -f /sys/kernel/debug/powerpc/$m ]]
+ then
+ do_one "$m" &
+ fi
done
echo "Spawned threads enabling/disabling mitigations ..."
diff --git a/tools/testing/selftests/powerpc/security/spectre_v2.c b/tools/testing/selftests/powerpc/security/spectre_v2.c
index adc2b7294e5f..83647b8277e7 100644
--- a/tools/testing/selftests/powerpc/security/spectre_v2.c
+++ b/tools/testing/selftests/powerpc/security/spectre_v2.c
@@ -193,7 +193,7 @@ int spectre_v2_test(void)
* We are not vulnerable and reporting otherwise, so
* missing such a mismatch is safe.
*/
- if (state == VULNERABLE)
+ if (miss_percent > 95)
return 4;
return 1;
diff --git a/tools/testing/selftests/powerpc/signal/.gitignore b/tools/testing/selftests/powerpc/signal/.gitignore
index ce3375cd8e73..9d0915777fed 100644
--- a/tools/testing/selftests/powerpc/signal/.gitignore
+++ b/tools/testing/selftests/powerpc/signal/.gitignore
@@ -4,3 +4,5 @@ signal_tm
sigfuz
sigreturn_vdso
sig_sc_double_restart
+sigreturn_kernel
+sigreturn_unaligned
diff --git a/tools/testing/selftests/powerpc/signal/Makefile b/tools/testing/selftests/powerpc/signal/Makefile
index d6ae54663aed..f679d260afc8 100644
--- a/tools/testing/selftests/powerpc/signal/Makefile
+++ b/tools/testing/selftests/powerpc/signal/Makefile
@@ -1,5 +1,7 @@
# SPDX-License-Identifier: GPL-2.0
TEST_GEN_PROGS := signal signal_tm sigfuz sigreturn_vdso sig_sc_double_restart
+TEST_GEN_PROGS += sigreturn_kernel
+TEST_GEN_PROGS += sigreturn_unaligned
CFLAGS += -maltivec
$(OUTPUT)/signal_tm: CFLAGS += -mhtm
diff --git a/tools/testing/selftests/powerpc/signal/sigreturn_kernel.c b/tools/testing/selftests/powerpc/signal/sigreturn_kernel.c
new file mode 100644
index 000000000000..0a1b6e591eee
--- /dev/null
+++ b/tools/testing/selftests/powerpc/signal/sigreturn_kernel.c
@@ -0,0 +1,132 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Test that we can't sigreturn to kernel addresses, or to kernel mode.
+ */
+
+#define _GNU_SOURCE
+
+#include <stdio.h>
+#include <signal.h>
+#include <stdlib.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+#include "utils.h"
+
+#define MSR_PR (1ul << 14)
+
+static volatile unsigned long long sigreturn_addr;
+static volatile unsigned long long sigreturn_msr_mask;
+
+static void sigusr1_handler(int signo, siginfo_t *si, void *uc_ptr)
+{
+ ucontext_t *uc = (ucontext_t *)uc_ptr;
+
+ if (sigreturn_addr)
+ UCONTEXT_NIA(uc) = sigreturn_addr;
+
+ if (sigreturn_msr_mask)
+ UCONTEXT_MSR(uc) &= sigreturn_msr_mask;
+}
+
+static pid_t fork_child(void)
+{
+ pid_t pid;
+
+ pid = fork();
+ if (pid == 0) {
+ raise(SIGUSR1);
+ exit(0);
+ }
+
+ return pid;
+}
+
+static int expect_segv(pid_t pid)
+{
+ int child_ret;
+
+ waitpid(pid, &child_ret, 0);
+ FAIL_IF(WIFEXITED(child_ret));
+ FAIL_IF(!WIFSIGNALED(child_ret));
+ FAIL_IF(WTERMSIG(child_ret) != 11);
+
+ return 0;
+}
+
+int test_sigreturn_kernel(void)
+{
+ struct sigaction act;
+ int child_ret, i;
+ pid_t pid;
+
+ act.sa_sigaction = sigusr1_handler;
+ act.sa_flags = SA_SIGINFO;
+ sigemptyset(&act.sa_mask);
+
+ FAIL_IF(sigaction(SIGUSR1, &act, NULL));
+
+ for (i = 0; i < 2; i++) {
+ // Return to kernel
+ sigreturn_addr = 0xcull << 60;
+ pid = fork_child();
+ expect_segv(pid);
+
+ // Return to kernel virtual
+ sigreturn_addr = 0xc008ull << 48;
+ pid = fork_child();
+ expect_segv(pid);
+
+ // Return out of range
+ sigreturn_addr = 0xc010ull << 48;
+ pid = fork_child();
+ expect_segv(pid);
+
+ // Return to no-man's land, just below PAGE_OFFSET
+ sigreturn_addr = (0xcull << 60) - (64 * 1024);
+ pid = fork_child();
+ expect_segv(pid);
+
+ // Return to no-man's land, above TASK_SIZE_4PB
+ sigreturn_addr = 0x1ull << 52;
+ pid = fork_child();
+ expect_segv(pid);
+
+ // Return to 0xd space
+ sigreturn_addr = 0xdull << 60;
+ pid = fork_child();
+ expect_segv(pid);
+
+ // Return to 0xe space
+ sigreturn_addr = 0xeull << 60;
+ pid = fork_child();
+ expect_segv(pid);
+
+ // Return to 0xf space
+ sigreturn_addr = 0xfull << 60;
+ pid = fork_child();
+ expect_segv(pid);
+
+ // Attempt to set PR=0 for 2nd loop (should be blocked by kernel)
+ sigreturn_msr_mask = ~MSR_PR;
+ }
+
+ printf("All children killed as expected\n");
+
+ // Don't change address, just MSR, should return to user as normal
+ sigreturn_addr = 0;
+ sigreturn_msr_mask = ~MSR_PR;
+ pid = fork_child();
+ waitpid(pid, &child_ret, 0);
+ FAIL_IF(!WIFEXITED(child_ret));
+ FAIL_IF(WIFSIGNALED(child_ret));
+ FAIL_IF(WEXITSTATUS(child_ret) != 0);
+
+ return 0;
+}
+
+int main(void)
+{
+ return test_harness(test_sigreturn_kernel, "sigreturn_kernel");
+}
diff --git a/tools/testing/selftests/powerpc/signal/sigreturn_unaligned.c b/tools/testing/selftests/powerpc/signal/sigreturn_unaligned.c
new file mode 100644
index 000000000000..6e58ee4f0fdf
--- /dev/null
+++ b/tools/testing/selftests/powerpc/signal/sigreturn_unaligned.c
@@ -0,0 +1,43 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Test sigreturn to an unaligned address, ie. low 2 bits set.
+ * Nothing bad should happen.
+ * This was able to trigger warnings with CONFIG_PPC_RFI_SRR_DEBUG=y.
+ */
+
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <ucontext.h>
+#include <unistd.h>
+
+#include "utils.h"
+
+
+static void sigusr1_handler(int signo, siginfo_t *info, void *ptr)
+{
+ ucontext_t *uc = ptr;
+
+ UCONTEXT_NIA(uc) |= 3;
+}
+
+static int test_sigreturn_unaligned(void)
+{
+ struct sigaction action;
+
+ memset(&action, 0, sizeof(action));
+ action.sa_sigaction = sigusr1_handler;
+ action.sa_flags = SA_SIGINFO;
+
+ FAIL_IF(sigaction(SIGUSR1, &action, NULL) == -1);
+
+ raise(SIGUSR1);
+
+ return 0;
+}
+
+int main(void)
+{
+ return test_harness(test_sigreturn_unaligned, "sigreturn_unaligned");
+}
diff --git a/tools/testing/selftests/rcutorture/bin/console-badness.sh b/tools/testing/selftests/rcutorture/bin/console-badness.sh
index e6a132df6172..69f8a5958cef 100755
--- a/tools/testing/selftests/rcutorture/bin/console-badness.sh
+++ b/tools/testing/selftests/rcutorture/bin/console-badness.sh
@@ -10,7 +10,7 @@
#
# Authors: Paul E. McKenney <[email protected]>
-egrep 'Badness|WARNING:|Warn|BUG|===========|Call Trace:|Oops:|detected stalls on CPUs/tasks:|self-detected stall on CPU|Stall ended before state dump start|\?\?\? Writer stall state|rcu_.*kthread starved for|!!!' |
+egrep 'Badness|WARNING:|Warn|BUG|===========|BUG: KCSAN:|Call Trace:|Oops:|detected stalls on CPUs/tasks:|self-detected stall on CPU|Stall ended before state dump start|\?\?\? Writer stall state|rcu_.*kthread starved for|!!!' |
grep -v 'ODEBUG: ' |
grep -v 'This means that this is a DEBUG kernel and it is' |
grep -v 'Warning: unable to open an initial console' |
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-again.sh b/tools/testing/selftests/rcutorture/bin/kvm-again.sh
index 5a0023d183da..0941f1ddab65 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-again.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-again.sh
@@ -47,8 +47,8 @@ else
exit 1
fi
-KVM="`pwd`/tools/testing/selftests/rcutorture"; export KVM
-PATH=${KVM}/bin:$PATH; export PATH
+RCUTORTURE="`pwd`/tools/testing/selftests/rcutorture"; export RCUTORTURE
+PATH=${RCUTORTURE}/bin:$PATH; export PATH
. functions.sh
dryrun=
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-check-branches.sh b/tools/testing/selftests/rcutorture/bin/kvm-check-branches.sh
index 370406bbfeed..f17000a2ccf1 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-check-branches.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-check-branches.sh
@@ -49,8 +49,8 @@ fi
mkdir $resdir/$ds
echo Results directory: $resdir/$ds
-KVM="`pwd`/tools/testing/selftests/rcutorture"; export KVM
-PATH=${KVM}/bin:$PATH; export PATH
+RCUTORTURE="`pwd`/tools/testing/selftests/rcutorture"; export RCUTORTURE
+PATH=${RCUTORTURE}/bin:$PATH; export PATH
. functions.sh
echo Using all `identify_qemu_vcpus` CPUs.
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-end-run-stats.sh b/tools/testing/selftests/rcutorture/bin/kvm-end-run-stats.sh
index e4a00779b8c6..ee886b40a5d2 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-end-run-stats.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-end-run-stats.sh
@@ -22,8 +22,8 @@ T=${TMPDIR-/tmp}/kvm-end-run-stats.sh.$$
trap 'rm -rf $T' 0
mkdir $T
-KVM="`pwd`/tools/testing/selftests/rcutorture"; export KVM
-PATH=${KVM}/bin:$PATH; export PATH
+RCUTORTURE="`pwd`/tools/testing/selftests/rcutorture"; export RCUTORTURE
+PATH=${RCUTORTURE}/bin:$PATH; export PATH
. functions.sh
default_starttime="`get_starttime`"
starttime="${2-default_starttime}"
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh b/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh
index daf64b507038..5f682fc892dd 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh
@@ -30,9 +30,15 @@ editor=${EDITOR-vi}
files=
for i in ${rundir}/*/Make.out
do
- if egrep -q "error:|warning:" < $i
+ scenariodir="`dirname $i`"
+ scenariobasedir="`echo ${scenariodir} | sed -e 's/\.[0-9]*$//'`"
+ if egrep -q "error:|warning:|^ld: .*undefined reference to" < $i
then
- egrep "error:|warning:" < $i > $i.diags
+ egrep "error:|warning:|^ld: .*undefined reference to" < $i > $i.diags
+ files="$files $i.diags $i"
+ elif ! test -f ${scenariobasedir}/vmlinux
+ then
+ echo No ${scenariobasedir}/vmlinux file > $i.diags
files="$files $i.diags $i"
fi
done
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh
index fbdf162b6acd..43e1387234d1 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh
@@ -25,7 +25,7 @@ stopstate="`grep 'End-test grace-period state: g' $i/console.log 2> /dev/null |
tail -1 | sed -e 's/^\[[ 0-9.]*] //' |
awk '{ print \"[\" $1 \" \" $5 \" \" $6 \" \" $7 \"]\"; }' |
tr -d '\012\015'`"
-fwdprog="`grep 'rcu_torture_fwd_prog_cr Duration' $i/console.log 2> /dev/null | sed -e 's/^\[[^]]*] //' | sort -k15nr | head -1 | awk '{ print $14 " " $15 }'`"
+fwdprog="`grep 'rcu_torture_fwd_prog n_max_cbs: ' $i/console.log 2> /dev/null | sed -e 's/^\[[^]]*] //' | sort -k3nr | head -1 | awk '{ print $2 " " $3 }' | tr -d '\015'`"
if test -z "$ngps"
then
echo "$configfile ------- " $stopstate
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-remote.sh b/tools/testing/selftests/rcutorture/bin/kvm-remote.sh
index c7d42ef80c53..8c4c1e4792d0 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-remote.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-remote.sh
@@ -19,8 +19,8 @@ then
exit 1
fi
-KVM="`pwd`/tools/testing/selftests/rcutorture"; export KVM
-PATH=${KVM}/bin:$PATH; export PATH
+RCUTORTURE="`pwd`/tools/testing/selftests/rcutorture"; export RCUTORTURE
+PATH=${RCUTORTURE}/bin:$PATH; export PATH
. functions.sh
starttime="`get_starttime`"
@@ -108,8 +108,8 @@ else
cat $T/kvm-again.sh.out | tee -a "$oldrun/remote-log"
exit 2
fi
- cp -a "$rundir" "$KVM/res/"
- oldrun="$KVM/res/$ds"
+ cp -a "$rundir" "$RCUTORTURE/res/"
+ oldrun="$RCUTORTURE/res/$ds"
fi
echo | tee -a "$oldrun/remote-log"
echo " ----" kvm-again.sh output: "(`date`)" | tee -a "$oldrun/remote-log"
@@ -144,7 +144,7 @@ do
if test "$ret" -ne 0
then
echo System $i unreachable, giving up. | tee -a "$oldrun/remote-log"
- exit 4 | tee -a "$oldrun/remote-log"
+ exit 4
fi
done
@@ -155,11 +155,23 @@ do
echo Downloading tarball to $i `date` | tee -a "$oldrun/remote-log"
cat $T/binres.tgz | ssh $i "cd /tmp; tar -xzf -"
ret=$?
- if test "$ret" -ne 0
- then
- echo Unable to download $T/binres.tgz to system $i, giving up. | tee -a "$oldrun/remote-log"
- exit 10 | tee -a "$oldrun/remote-log"
- fi
+ tries=0
+ while test "$ret" -ne 0
+ do
+ echo Unable to download $T/binres.tgz to system $i, waiting and then retrying. $tries prior retries. | tee -a "$oldrun/remote-log"
+ sleep 60
+ cat $T/binres.tgz | ssh $i "cd /tmp; tar -xzf -"
+ ret=$?
+ if test "$ret" -ne 0
+ then
+ if test "$tries" > 5
+ then
+ echo Unable to download $T/binres.tgz to system $i, giving up. | tee -a "$oldrun/remote-log"
+ exit 10
+ fi
+ fi
+ tries=$((tries+1))
+ done
done
# Function to check for presence of a file on the specified system.
@@ -177,16 +189,16 @@ checkremotefile () {
ret=$?
if test "$ret" -eq 255
then
- echo " ---" ssh failure to $1 checking for file $2, retry after $sleeptime seconds. `date`
+ echo " ---" ssh failure to $1 checking for file $2, retry after $sleeptime seconds. `date` | tee -a "$oldrun/remote-log"
elif test "$ret" -eq 0
then
return 0
elif test "$ret" -eq 1
then
- echo " ---" File \"$2\" not found: ssh $1 test -f \"$2\"
+ echo " ---" File \"$2\" not found: ssh $1 test -f \"$2\" | tee -a "$oldrun/remote-log"
return 1
else
- echo " ---" Exit code $ret: ssh $1 test -f \"$2\", retry after $sleeptime seconds. `date`
+ echo " ---" Exit code $ret: ssh $1 test -f \"$2\", retry after $sleeptime seconds. `date` | tee -a "$oldrun/remote-log"
return $ret
fi
sleep $sleeptime
@@ -245,7 +257,7 @@ do
sleep 30
fi
done
-echo All batches started. `date`
+echo All batches started. `date` | tee -a "$oldrun/remote-log"
# Wait for all remaining scenarios to complete and collect results.
for i in $systems
@@ -254,7 +266,7 @@ do
do
sleep 30
done
- echo " ---" Collecting results from $i `date`
+ echo " ---" Collecting results from $i `date` | tee -a "$oldrun/remote-log"
( cd "$oldrun"; ssh $i "cd $rundir; tar -czf - kvm-remote-*.sh.out */console.log */kvm-test-1-run*.sh.out */qemu[_-]pid */qemu-retval */qemu-affinity; rm -rf $T > /dev/null 2>&1" | tar -xzf - )
done
diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh
index 6cf9ec6a3d1c..55b2c1533282 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm.sh
@@ -25,15 +25,15 @@ LANG=en_US.UTF-8; export LANG
dur=$((30*60))
dryrun=""
-KVM="`pwd`/tools/testing/selftests/rcutorture"; export KVM
-PATH=${KVM}/bin:$PATH; export PATH
+RCUTORTURE="`pwd`/tools/testing/selftests/rcutorture"; export RCUTORTURE
+PATH=${RCUTORTURE}/bin:$PATH; export PATH
. functions.sh
TORTURE_ALLOTED_CPUS="`identify_qemu_vcpus`"
TORTURE_DEFCONFIG=defconfig
TORTURE_BOOT_IMAGE=""
TORTURE_BUILDONLY=
-TORTURE_INITRD="$KVM/initrd"; export TORTURE_INITRD
+TORTURE_INITRD="$RCUTORTURE/initrd"; export TORTURE_INITRD
TORTURE_KCONFIG_ARG=""
TORTURE_KCONFIG_GDB_ARG=""
TORTURE_BOOT_GDB_ARG=""
@@ -74,7 +74,9 @@ usage () {
echo " --help"
echo " --interactive"
echo " --jitter N [ maxsleep (us) [ maxspin (us) ] ]"
+ echo " --kasan"
echo " --kconfig Kconfig-options"
+ echo " --kcsan"
echo " --kmake-arg kernel-make-arguments"
echo " --mac nn:nn:nn:nn:nn:nn"
echo " --memory megabytes|nnnG"
@@ -83,6 +85,7 @@ usage () {
echo " --qemu-cmd qemu-system-..."
echo " --remote"
echo " --results absolute-pathname"
+ echo " --shutdown-grace seconds"
echo " --torture lock|rcu|rcuscale|refscale|scf"
echo " --trust-make"
exit 1
@@ -175,14 +178,14 @@ do
jitter="$2"
shift
;;
+ --kasan)
+ TORTURE_KCONFIG_KASAN_ARG="CONFIG_DEBUG_INFO=y CONFIG_KASAN=y"; export TORTURE_KCONFIG_KASAN_ARG
+ ;;
--kconfig|--kconfigs)
checkarg --kconfig "(Kconfig options)" $# "$2" '^CONFIG_[A-Z0-9_]\+=\([ynm]\|[0-9]\+\)\( CONFIG_[A-Z0-9_]\+=\([ynm]\|[0-9]\+\)\)*$' '^error$'
TORTURE_KCONFIG_ARG="`echo "$TORTURE_KCONFIG_ARG $2" | sed -e 's/^ *//' -e 's/ *$//'`"
shift
;;
- --kasan)
- TORTURE_KCONFIG_KASAN_ARG="CONFIG_DEBUG_INFO=y CONFIG_KASAN=y"; export TORTURE_KCONFIG_KASAN_ARG
- ;;
--kcsan)
TORTURE_KCONFIG_KCSAN_ARG="CONFIG_DEBUG_INFO=y CONFIG_KCSAN=y CONFIG_KCSAN_STRICT=y CONFIG_KCSAN_REPORT_ONCE_IN_MS=100000 CONFIG_KCSAN_VERBOSE=y CONFIG_DEBUG_LOCK_ALLOC=y CONFIG_PROVE_LOCKING=y"; export TORTURE_KCONFIG_KCSAN_ARG
;;
@@ -259,7 +262,7 @@ else
exit 1
fi
-CONFIGFRAG=${KVM}/configs/${TORTURE_SUITE}; export CONFIGFRAG
+CONFIGFRAG=${RCUTORTURE}/configs/${TORTURE_SUITE}; export CONFIGFRAG
defaultconfigs="`tr '\012' ' ' < $CONFIGFRAG/CFLIST`"
if test -z "$configs"
@@ -269,7 +272,7 @@ fi
if test -z "$resdir"
then
- resdir=$KVM/res
+ resdir=$RCUTORTURE/res
fi
# Create a file of test-name/#cpus pairs, sorted by decreasing #cpus.
@@ -277,7 +280,7 @@ configs_derep=
for CF in $configs
do
case $CF in
- [0-9]\**|[0-9][0-9]\**|[0-9][0-9][0-9]\**)
+ [0-9]\**|[0-9][0-9]\**|[0-9][0-9][0-9]\**|[0-9][0-9][0-9][0-9]\**)
config_reps=`echo $CF | sed -e 's/\*.*$//'`
CF1=`echo $CF | sed -e 's/^[^*]*\*//'`
;;
@@ -383,7 +386,7 @@ END {
# Generate a script to execute the tests in appropriate batches.
cat << ___EOF___ > $T/script
CONFIGFRAG="$CONFIGFRAG"; export CONFIGFRAG
-KVM="$KVM"; export KVM
+RCUTORTURE="$RCUTORTURE"; export RCUTORTURE
PATH="$PATH"; export PATH
TORTURE_ALLOTED_CPUS="$TORTURE_ALLOTED_CPUS"; export TORTURE_ALLOTED_CPUS
TORTURE_BOOT_IMAGE="$TORTURE_BOOT_IMAGE"; export TORTURE_BOOT_IMAGE
@@ -566,7 +569,7 @@ ___EOF___
awk < $T/cfgcpu.pack \
-v TORTURE_BUILDONLY="$TORTURE_BUILDONLY" \
-v CONFIGDIR="$CONFIGFRAG/" \
- -v KVM="$KVM" \
+ -v RCUTORTURE="$RCUTORTURE" \
-v ncpus=$cpus \
-v jitter="$jitter" \
-v rd=$resdir/$ds/ \
diff --git a/tools/testing/selftests/rcutorture/bin/parse-build.sh b/tools/testing/selftests/rcutorture/bin/parse-build.sh
index 9313e5065ae9..2dbfca3589b1 100755
--- a/tools/testing/selftests/rcutorture/bin/parse-build.sh
+++ b/tools/testing/selftests/rcutorture/bin/parse-build.sh
@@ -39,7 +39,8 @@ fi
grep warning: < $F > $T/warnings
grep "include/linux/*rcu*\.h:" $T/warnings > $T/hwarnings
grep "kernel/rcu/[^/]*:" $T/warnings > $T/cwarnings
-cat $T/hwarnings $T/cwarnings > $T/rcuwarnings
+grep "^ld: .*undefined reference to" $T/warnings | head -1 > $T/ldwarnings
+cat $T/hwarnings $T/cwarnings $T/ldwarnings > $T/rcuwarnings
if test -s $T/rcuwarnings
then
print_warning $title build errors:
diff --git a/tools/testing/selftests/rcutorture/bin/parse-console.sh b/tools/testing/selftests/rcutorture/bin/parse-console.sh
index 9f624bd53c27..822eb037a057 100755
--- a/tools/testing/selftests/rcutorture/bin/parse-console.sh
+++ b/tools/testing/selftests/rcutorture/bin/parse-console.sh
@@ -138,6 +138,16 @@ then
then
summary="$summary Bugs: $n_bugs"
fi
+ n_kcsan=`egrep -c 'BUG: KCSAN: ' $file`
+ if test "$n_kcsan" -ne 0
+ then
+ if test "$n_bugs" = "$n_kcsan"
+ then
+ summary="$summary (all bugs kcsan)"
+ else
+ summary="$summary KCSAN: $n_kcsan"
+ fi
+ fi
n_calltrace=`grep -c 'Call Trace:' $file`
if test "$n_calltrace" -ne 0
then
diff --git a/tools/testing/selftests/rcutorture/bin/torture.sh b/tools/testing/selftests/rcutorture/bin/torture.sh
index eae88aacca2a..bfe09e2829c8 100755
--- a/tools/testing/selftests/rcutorture/bin/torture.sh
+++ b/tools/testing/selftests/rcutorture/bin/torture.sh
@@ -13,8 +13,8 @@
scriptname=$0
args="$*"
-KVM="`pwd`/tools/testing/selftests/rcutorture"; export KVM
-PATH=${KVM}/bin:$PATH; export PATH
+RCUTORTURE="`pwd`/tools/testing/selftests/rcutorture"; export RCUTORTURE
+PATH=${RCUTORTURE}/bin:$PATH; export PATH
. functions.sh
TORTURE_ALLOTED_CPUS="`identify_qemu_vcpus`"
@@ -37,7 +37,7 @@ configs_scftorture=
kcsan_kmake_args=
# Default compression, duration, and apportionment.
-compress_kasan_vmlinux="`identify_qemu_vcpus`"
+compress_concurrency="`identify_qemu_vcpus`"
duration_base=10
duration_rcutorture_frac=7
duration_locktorture_frac=1
@@ -67,12 +67,12 @@ function doyesno () {
usage () {
echo "Usage: $scriptname optional arguments:"
- echo " --compress-kasan-vmlinux concurrency"
+ echo " --compress-concurrency concurrency"
echo " --configs-rcutorture \"config-file list w/ repeat factor (3*TINY01)\""
echo " --configs-locktorture \"config-file list w/ repeat factor (10*LOCK01)\""
echo " --configs-scftorture \"config-file list w/ repeat factor (2*CFLIST)\""
- echo " --doall"
- echo " --doallmodconfig / --do-no-allmodconfig"
+ echo " --do-all"
+ echo " --do-allmodconfig / --do-no-allmodconfig"
echo " --do-clocksourcewd / --do-no-clocksourcewd"
echo " --do-kasan / --do-no-kasan"
echo " --do-kcsan / --do-no-kcsan"
@@ -91,9 +91,9 @@ usage () {
while test $# -gt 0
do
case "$1" in
- --compress-kasan-vmlinux)
- checkarg --compress-kasan-vmlinux "(concurrency level)" $# "$2" '^[0-9][0-9]*$' '^error'
- compress_kasan_vmlinux=$2
+ --compress-concurrency)
+ checkarg --compress-concurrency "(concurrency level)" $# "$2" '^[0-9][0-9]*$' '^error'
+ compress_concurrency=$2
shift
;;
--config-rcutorture|--configs-rcutorture)
@@ -414,8 +414,14 @@ nfailures=0
echo FAILURES: | tee -a $T/log
if test -s "$T/failures"
then
- cat "$T/failures" | tee -a $T/log
+ awk < "$T/failures" -v sq="'" '{ print "echo " sq $0 sq; print "sed -e " sq "1,/^ --- .* Test summary:$/d" sq " " $2 "/log | grep Summary: | sed -e " sq "s/^[^S]*/ /" sq; }' | sh | tee -a $T/log | tee "$T/failuresum"
nfailures="`wc -l "$T/failures" | awk '{ print $1 }'`"
+ grep "^ Summary: " "$T/failuresum" |
+ grep -v '^ Summary: Bugs: [0-9]* (all bugs kcsan)$' > "$T/nonkcsan"
+ if test -s "$T/nonkcsan"
+ then
+ nonkcsanbug="yes"
+ fi
ret=2
fi
if test "$do_kcsan" = "yes"
@@ -424,12 +430,16 @@ then
fi
echo Started at $startdate, ended at `date`, duration `get_starttime_duration $starttime`. | tee -a $T/log
echo Summary: Successes: $nsuccesses Failures: $nfailures. | tee -a $T/log
+if test -z "$nonkcsanbug" && test -s "$T/failuresum"
+then
+ echo " All bugs were KCSAN failures."
+fi
tdir="`cat $T/successes $T/failures | head -1 | awk '{ print $NF }' | sed -e 's,/[^/]\+/*$,,'`"
-if test -n "$tdir" && test $compress_kasan_vmlinux -gt 0
+if test -n "$tdir" && test $compress_concurrency -gt 0
then
# KASAN vmlinux files can approach 1GB in size, so compress them.
- echo Looking for KASAN files to compress: `date` > "$tdir/log-xz" 2>&1
- find "$tdir" -type d -name '*-kasan' -print > $T/xz-todo
+ echo Looking for K[AC]SAN files to compress: `date` > "$tdir/log-xz" 2>&1
+ find "$tdir" -type d -name '*-k[ac]san' -print > $T/xz-todo
ncompresses=0
batchno=1
if test -s $T/xz-todo
@@ -447,7 +457,7 @@ then
do
xz "$j" >> "$tdir/log-xz" 2>&1 &
ncompresses=$((ncompresses+1))
- if test $ncompresses -ge $compress_kasan_vmlinux
+ if test $ncompresses -ge $compress_concurrency
then
echo Waiting for batch $batchno of $ncompresses compressions `date` | tee -a "$tdir/log-xz" | tee -a $T/log
wait
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/RUDE01 b/tools/testing/selftests/rcutorture/configs/rcu/RUDE01
index 3ca112444ce7..7093422050f6 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/RUDE01
+++ b/tools/testing/selftests/rcutorture/configs/rcu/RUDE01
@@ -1,5 +1,5 @@
CONFIG_SMP=y
-CONFIG_NR_CPUS=4
+CONFIG_NR_CPUS=3
CONFIG_HOTPLUG_CPU=y
CONFIG_PREEMPT_NONE=n
CONFIG_PREEMPT_VOLUNTARY=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N.boot b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N.boot
index 238bfe3bd0cc..ce0694fd9b92 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N.boot
+++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N.boot
@@ -1 +1,2 @@
rcutorture.torture_type=srcu
+rcutorture.fwd_progress=3
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-P.boot b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-P.boot
index ce48c7b82673..2db39f298d18 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-P.boot
+++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-P.boot
@@ -1,2 +1,4 @@
rcutorture.torture_type=srcud
rcupdate.rcu_self_test=1
+rcutorture.fwd_progress=3
+srcutree.big_cpu_lim=5
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-T b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-T
index d6557c38dfe4..c70cf0405f24 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-T
+++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-T
@@ -2,6 +2,7 @@ CONFIG_SMP=n
CONFIG_PREEMPT_NONE=y
CONFIG_PREEMPT_VOLUNTARY=n
CONFIG_PREEMPT=n
+CONFIG_PREEMPT_DYNAMIC=n
#CHECK#CONFIG_TINY_SRCU=y
CONFIG_RCU_TRACE=n
CONFIG_DEBUG_LOCK_ALLOC=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-U b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-U
index 6bc24e99862f..bc9eeabaa1b1 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-U
+++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-U
@@ -2,6 +2,7 @@ CONFIG_SMP=n
CONFIG_PREEMPT_NONE=y
CONFIG_PREEMPT_VOLUNTARY=n
CONFIG_PREEMPT=n
+CONFIG_PREEMPT_DYNAMIC=n
#CHECK#CONFIG_TINY_SRCU=y
CONFIG_RCU_TRACE=n
CONFIG_DEBUG_LOCK_ALLOC=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TASKS01.boot b/tools/testing/selftests/rcutorture/configs/rcu/TASKS01.boot
index 22cdeced98ea..30ca5b493c4b 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TASKS01.boot
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TASKS01.boot
@@ -1,2 +1,3 @@
rcutorture.torture_type=tasks
rcutree.use_softirq=0
+rcupdate.rcu_task_enqueue_lim=4
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TINY01 b/tools/testing/selftests/rcutorture/configs/rcu/TINY01
index 6db705e55487..0953c52fcfd7 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TINY01
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TINY01
@@ -2,6 +2,7 @@ CONFIG_SMP=n
CONFIG_PREEMPT_NONE=y
CONFIG_PREEMPT_VOLUNTARY=n
CONFIG_PREEMPT=n
+CONFIG_PREEMPT_DYNAMIC=n
#CHECK#CONFIG_TINY_RCU=y
CONFIG_HZ_PERIODIC=n
CONFIG_NO_HZ_IDLE=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TINY02 b/tools/testing/selftests/rcutorture/configs/rcu/TINY02
index d8674264318d..30439f6fc20e 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TINY02
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TINY02
@@ -2,6 +2,7 @@ CONFIG_SMP=n
CONFIG_PREEMPT_NONE=y
CONFIG_PREEMPT_VOLUNTARY=n
CONFIG_PREEMPT=n
+CONFIG_PREEMPT_DYNAMIC=n
#CHECK#CONFIG_TINY_RCU=y
CONFIG_HZ_PERIODIC=y
CONFIG_NO_HZ_IDLE=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TRACE01 b/tools/testing/selftests/rcutorture/configs/rcu/TRACE01
index 34c8ff5a12f2..e4d74e5fc1d0 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TRACE01
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TRACE01
@@ -1,5 +1,5 @@
CONFIG_SMP=y
-CONFIG_NR_CPUS=4
+CONFIG_NR_CPUS=5
CONFIG_HOTPLUG_CPU=y
CONFIG_PREEMPT_NONE=y
CONFIG_PREEMPT_VOLUNTARY=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TRACE01.boot b/tools/testing/selftests/rcutorture/configs/rcu/TRACE01.boot
index 9675ad632dcc..ba6d636a4856 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TRACE01.boot
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TRACE01.boot
@@ -1 +1,2 @@
rcutorture.torture_type=tasks-tracing
+rcupdate.rcu_task_enqueue_lim=2
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TRACE02.boot b/tools/testing/selftests/rcutorture/configs/rcu/TRACE02.boot
index 9675ad632dcc..c70b5db6c2ae 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TRACE02.boot
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TRACE02.boot
@@ -1 +1,2 @@
rcutorture.torture_type=tasks-tracing
+rcutorture.fwd_progress=2
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE01 b/tools/testing/selftests/rcutorture/configs/rcu/TREE01
index b5b53973c01e..8ae41d5f81a3 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE01
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE01
@@ -6,7 +6,6 @@ CONFIG_PREEMPT=y
CONFIG_HZ_PERIODIC=n
CONFIG_NO_HZ_IDLE=y
CONFIG_NO_HZ_FULL=n
-CONFIG_RCU_FAST_NO_HZ=y
CONFIG_RCU_TRACE=y
CONFIG_HOTPLUG_CPU=y
CONFIG_MAXSMP=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE02 b/tools/testing/selftests/rcutorture/configs/rcu/TREE02
index 65daee4fbf5a..2871ee599891 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE02
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE02
@@ -7,7 +7,6 @@ CONFIG_PREEMPT=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_FANOUT=3
CONFIG_RCU_FANOUT_LEAF=3
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE02.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE02.boot
new file mode 100644
index 000000000000..dd914fa8f690
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE02.boot
@@ -0,0 +1 @@
+rcutorture.fwd_progress=2
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE04 b/tools/testing/selftests/rcutorture/configs/rcu/TREE04
index f6d6a40c0576..22ad0261728d 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE04
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE04
@@ -7,7 +7,6 @@ CONFIG_PREEMPT=n
CONFIG_HZ_PERIODIC=n
CONFIG_NO_HZ_IDLE=n
CONFIG_NO_HZ_FULL=y
-CONFIG_RCU_FAST_NO_HZ=y
CONFIG_RCU_TRACE=y
CONFIG_RCU_FANOUT=4
CONFIG_RCU_FANOUT_LEAF=3
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE05 b/tools/testing/selftests/rcutorture/configs/rcu/TREE05
index 4f95f8544f3f..9f48c73709ec 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE05
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE05
@@ -7,7 +7,6 @@ CONFIG_PREEMPT=n
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_HOTPLUG_CPU=y
CONFIG_RCU_FANOUT=6
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE06 b/tools/testing/selftests/rcutorture/configs/rcu/TREE06
index bf4980d606b5..db27651de04b 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE06
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE06
@@ -7,7 +7,6 @@ CONFIG_PREEMPT=n
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_FANOUT=6
CONFIG_RCU_FANOUT_LEAF=6
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE07 b/tools/testing/selftests/rcutorture/configs/rcu/TREE07
index d7afb271a586..2789b47e4ecd 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE07
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE07
@@ -7,7 +7,6 @@ CONFIG_PREEMPT=n
CONFIG_HZ_PERIODIC=n
CONFIG_NO_HZ_IDLE=n
CONFIG_NO_HZ_FULL=y
-CONFIG_RCU_FAST_NO_HZ=n
CONFIG_RCU_TRACE=y
CONFIG_HOTPLUG_CPU=y
CONFIG_RCU_FANOUT=2
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE08 b/tools/testing/selftests/rcutorture/configs/rcu/TREE08
index c810c5276a89..8b561355b9ef 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE08
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE08
@@ -7,7 +7,6 @@ CONFIG_PREEMPT=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_FANOUT=3
CONFIG_RCU_FANOUT_LEAF=2
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE10 b/tools/testing/selftests/rcutorture/configs/rcu/TREE10
index 7311f84a5876..4a00539bfdd7 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE10
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE10
@@ -7,7 +7,6 @@ CONFIG_PREEMPT=n
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
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE10.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE10.boot
new file mode 100644
index 000000000000..dd914fa8f690
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE10.boot
@@ -0,0 +1 @@
+rcutorture.fwd_progress=2
diff --git a/tools/testing/selftests/rcutorture/configs/rcuscale/TINY b/tools/testing/selftests/rcutorture/configs/rcuscale/TINY
index fb05ef5279b4..0fa2dc086e10 100644
--- a/tools/testing/selftests/rcutorture/configs/rcuscale/TINY
+++ b/tools/testing/selftests/rcutorture/configs/rcuscale/TINY
@@ -2,11 +2,11 @@ CONFIG_SMP=n
CONFIG_PREEMPT_NONE=y
CONFIG_PREEMPT_VOLUNTARY=n
CONFIG_PREEMPT=n
+CONFIG_PREEMPT_DYNAMIC=n
#CHECK#CONFIG_TINY_RCU=y
CONFIG_HZ_PERIODIC=n
CONFIG_NO_HZ_IDLE=y
CONFIG_NO_HZ_FULL=n
-CONFIG_RCU_FAST_NO_HZ=n
CONFIG_RCU_NOCB_CPU=n
CONFIG_DEBUG_LOCK_ALLOC=n
CONFIG_PROVE_LOCKING=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcuscale/TRACE01 b/tools/testing/selftests/rcutorture/configs/rcuscale/TRACE01
index e6baa2fbaeb3..227aba7783af 100644
--- a/tools/testing/selftests/rcutorture/configs/rcuscale/TRACE01
+++ b/tools/testing/selftests/rcutorture/configs/rcuscale/TRACE01
@@ -5,7 +5,6 @@ CONFIG_PREEMPT=n
CONFIG_HZ_PERIODIC=n
CONFIG_NO_HZ_IDLE=y
CONFIG_NO_HZ_FULL=n
-CONFIG_RCU_FAST_NO_HZ=n
CONFIG_RCU_NOCB_CPU=n
CONFIG_DEBUG_LOCK_ALLOC=n
CONFIG_PROVE_LOCKING=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcuscale/TREE b/tools/testing/selftests/rcutorture/configs/rcuscale/TREE
index 4cc1cc581321..f110d9ffbe4c 100644
--- a/tools/testing/selftests/rcutorture/configs/rcuscale/TREE
+++ b/tools/testing/selftests/rcutorture/configs/rcuscale/TREE
@@ -6,7 +6,6 @@ CONFIG_PREEMPT=y
CONFIG_HZ_PERIODIC=n
CONFIG_NO_HZ_IDLE=y
CONFIG_NO_HZ_FULL=n
-CONFIG_RCU_FAST_NO_HZ=n
CONFIG_HOTPLUG_CPU=y
CONFIG_SUSPEND=n
CONFIG_HIBERNATION=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcuscale/TREE54 b/tools/testing/selftests/rcutorture/configs/rcuscale/TREE54
index f5952061fde7..9f83e5372796 100644
--- a/tools/testing/selftests/rcutorture/configs/rcuscale/TREE54
+++ b/tools/testing/selftests/rcutorture/configs/rcuscale/TREE54
@@ -7,7 +7,6 @@ CONFIG_PREEMPT=y
CONFIG_HZ_PERIODIC=n
CONFIG_NO_HZ_IDLE=y
CONFIG_NO_HZ_FULL=n
-CONFIG_RCU_FAST_NO_HZ=n
CONFIG_HOTPLUG_CPU=y
CONFIG_SUSPEND=n
CONFIG_HIBERNATION=n
diff --git a/tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT b/tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT
index ad505a887bec..7f06838a91e6 100644
--- a/tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT
+++ b/tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT
@@ -6,7 +6,6 @@ CONFIG_PREEMPT=n
CONFIG_HZ_PERIODIC=n
CONFIG_NO_HZ_IDLE=y
CONFIG_NO_HZ_FULL=n
-CONFIG_RCU_FAST_NO_HZ=n
CONFIG_HOTPLUG_CPU=y
CONFIG_SUSPEND=n
CONFIG_HIBERNATION=n
diff --git a/tools/testing/selftests/rcutorture/configs/refscale/PREEMPT b/tools/testing/selftests/rcutorture/configs/refscale/PREEMPT
index 4f08e641bb6b..52e3ef674056 100644
--- a/tools/testing/selftests/rcutorture/configs/refscale/PREEMPT
+++ b/tools/testing/selftests/rcutorture/configs/refscale/PREEMPT
@@ -6,7 +6,6 @@ CONFIG_PREEMPT=y
CONFIG_HZ_PERIODIC=n
CONFIG_NO_HZ_IDLE=y
CONFIG_NO_HZ_FULL=n
-CONFIG_RCU_FAST_NO_HZ=n
CONFIG_HOTPLUG_CPU=y
CONFIG_SUSPEND=n
CONFIG_HIBERNATION=n
diff --git a/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt b/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt
index 1b96d68473b8..42acb1a64ce1 100644
--- a/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt
+++ b/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt
@@ -15,7 +15,6 @@ CONFIG_PROVE_RCU -- Hardwired to CONFIG_PROVE_LOCKING.
CONFIG_RCU_BOOST -- one of PREEMPT_RCU.
CONFIG_RCU_FANOUT -- Cover hierarchy, but overlap with others.
CONFIG_RCU_FANOUT_LEAF -- Do one non-default.
-CONFIG_RCU_FAST_NO_HZ -- Do one, but not with all nohz_full CPUs.
CONFIG_RCU_NOCB_CPU -- Do three, one with no rcu_nocbs CPUs, one with
rcu_nocbs=0, and one with all rcu_nocbs CPUs.
CONFIG_RCU_TRACE -- Do half.
diff --git a/tools/testing/selftests/rseq/Makefile b/tools/testing/selftests/rseq/Makefile
index 2af9d39a9716..215e1067f037 100644
--- a/tools/testing/selftests/rseq/Makefile
+++ b/tools/testing/selftests/rseq/Makefile
@@ -6,7 +6,7 @@ endif
CFLAGS += -O2 -Wall -g -I./ -I../../../../usr/include/ -L$(OUTPUT) -Wl,-rpath=./ \
$(CLANG_FLAGS)
-LDLIBS += -lpthread
+LDLIBS += -lpthread -ldl
# Own dependencies because we only want to build against 1st prerequisite, but
# still track changes to header files and depend on shared object.
diff --git a/tools/testing/selftests/rseq/basic_percpu_ops_test.c b/tools/testing/selftests/rseq/basic_percpu_ops_test.c
index b953a52ff706..517756afc2a4 100644
--- a/tools/testing/selftests/rseq/basic_percpu_ops_test.c
+++ b/tools/testing/selftests/rseq/basic_percpu_ops_test.c
@@ -167,7 +167,7 @@ struct percpu_list_node *this_cpu_list_pop(struct percpu_list *list,
for (;;) {
struct percpu_list_node *head;
intptr_t *targetptr, expectnot, *load;
- off_t offset;
+ long offset;
int ret, cpu;
cpu = rseq_cpu_start();
diff --git a/tools/testing/selftests/rseq/compiler.h b/tools/testing/selftests/rseq/compiler.h
new file mode 100644
index 000000000000..876eb6a7f75b
--- /dev/null
+++ b/tools/testing/selftests/rseq/compiler.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: LGPL-2.1-only OR MIT */
+/*
+ * rseq/compiler.h
+ *
+ * Work-around asm goto compiler bugs.
+ *
+ * (C) Copyright 2021 - Mathieu Desnoyers <[email protected]>
+ */
+
+#ifndef RSEQ_COMPILER_H
+#define RSEQ_COMPILER_H
+
+/*
+ * gcc prior to 4.8.2 miscompiles asm goto.
+ * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58670
+ *
+ * gcc prior to 8.1.0 miscompiles asm goto at O1.
+ * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=103908
+ *
+ * clang prior to version 13.0.1 miscompiles asm goto at O2.
+ * https://github.com/llvm/llvm-project/issues/52735
+ *
+ * Work around these issues by adding a volatile inline asm with
+ * memory clobber in the fallthrough after the asm goto and at each
+ * label target. Emit this for all compilers in case other similar
+ * issues are found in the future.
+ */
+#define rseq_after_asm_goto() asm volatile ("" : : : "memory")
+
+#endif /* RSEQ_COMPILER_H_ */
diff --git a/tools/testing/selftests/rseq/param_test.c b/tools/testing/selftests/rseq/param_test.c
index 699ad5f93c34..da23c22d5882 100644
--- a/tools/testing/selftests/rseq/param_test.c
+++ b/tools/testing/selftests/rseq/param_test.c
@@ -161,7 +161,7 @@ unsigned int yield_mod_cnt, nr_abort;
" cbnz " INJECT_ASM_REG ", 222b\n" \
"333:\n"
-#elif __PPC__
+#elif defined(__PPC__)
#define RSEQ_INJECT_INPUT \
, [loop_cnt_1]"m"(loop_cnt[1]) \
@@ -368,9 +368,7 @@ void *test_percpu_spinlock_thread(void *arg)
abort();
reps = thread_data->reps;
for (i = 0; i < reps; i++) {
- int cpu = rseq_cpu_start();
-
- cpu = rseq_this_cpu_lock(&data->lock);
+ int cpu = rseq_this_cpu_lock(&data->lock);
data->c[cpu].count++;
rseq_percpu_unlock(&data->lock, cpu);
#ifndef BENCHMARK
@@ -551,7 +549,7 @@ struct percpu_list_node *this_cpu_list_pop(struct percpu_list *list,
for (;;) {
struct percpu_list_node *head;
intptr_t *targetptr, expectnot, *load;
- off_t offset;
+ long offset;
int ret;
cpu = rseq_cpu_start();
diff --git a/tools/testing/selftests/rseq/rseq-abi.h b/tools/testing/selftests/rseq/rseq-abi.h
new file mode 100644
index 000000000000..a8c44d9af71f
--- /dev/null
+++ b/tools/testing/selftests/rseq/rseq-abi.h
@@ -0,0 +1,151 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+#ifndef _RSEQ_ABI_H
+#define _RSEQ_ABI_H
+
+/*
+ * rseq-abi.h
+ *
+ * Restartable sequences system call API
+ *
+ * Copyright (c) 2015-2022 Mathieu Desnoyers <[email protected]>
+ */
+
+#include <linux/types.h>
+#include <asm/byteorder.h>
+
+enum rseq_abi_cpu_id_state {
+ RSEQ_ABI_CPU_ID_UNINITIALIZED = -1,
+ RSEQ_ABI_CPU_ID_REGISTRATION_FAILED = -2,
+};
+
+enum rseq_abi_flags {
+ RSEQ_ABI_FLAG_UNREGISTER = (1 << 0),
+};
+
+enum rseq_abi_cs_flags_bit {
+ RSEQ_ABI_CS_FLAG_NO_RESTART_ON_PREEMPT_BIT = 0,
+ RSEQ_ABI_CS_FLAG_NO_RESTART_ON_SIGNAL_BIT = 1,
+ RSEQ_ABI_CS_FLAG_NO_RESTART_ON_MIGRATE_BIT = 2,
+};
+
+enum rseq_abi_cs_flags {
+ RSEQ_ABI_CS_FLAG_NO_RESTART_ON_PREEMPT =
+ (1U << RSEQ_ABI_CS_FLAG_NO_RESTART_ON_PREEMPT_BIT),
+ RSEQ_ABI_CS_FLAG_NO_RESTART_ON_SIGNAL =
+ (1U << RSEQ_ABI_CS_FLAG_NO_RESTART_ON_SIGNAL_BIT),
+ RSEQ_ABI_CS_FLAG_NO_RESTART_ON_MIGRATE =
+ (1U << RSEQ_ABI_CS_FLAG_NO_RESTART_ON_MIGRATE_BIT),
+};
+
+/*
+ * struct rseq_abi_cs is aligned on 4 * 8 bytes to ensure it is always
+ * contained within a single cache-line. It is usually declared as
+ * link-time constant data.
+ */
+struct rseq_abi_cs {
+ /* Version of this structure. */
+ __u32 version;
+ /* enum rseq_abi_cs_flags */
+ __u32 flags;
+ __u64 start_ip;
+ /* Offset from start_ip. */
+ __u64 post_commit_offset;
+ __u64 abort_ip;
+} __attribute__((aligned(4 * sizeof(__u64))));
+
+/*
+ * struct rseq_abi is aligned on 4 * 8 bytes to ensure it is always
+ * contained within a single cache-line.
+ *
+ * A single struct rseq_abi per thread is allowed.
+ */
+struct rseq_abi {
+ /*
+ * Restartable sequences cpu_id_start field. Updated by the
+ * kernel. Read by user-space with single-copy atomicity
+ * semantics. This field should only be read by the thread which
+ * registered this data structure. Aligned on 32-bit. Always
+ * contains a value in the range of possible CPUs, although the
+ * value may not be the actual current CPU (e.g. if rseq is not
+ * initialized). This CPU number value should always be compared
+ * against the value of the cpu_id field before performing a rseq
+ * commit or returning a value read from a data structure indexed
+ * using the cpu_id_start value.
+ */
+ __u32 cpu_id_start;
+ /*
+ * Restartable sequences cpu_id field. Updated by the kernel.
+ * Read by user-space with single-copy atomicity semantics. This
+ * field should only be read by the thread which registered this
+ * data structure. Aligned on 32-bit. Values
+ * RSEQ_CPU_ID_UNINITIALIZED and RSEQ_CPU_ID_REGISTRATION_FAILED
+ * have a special semantic: the former means "rseq uninitialized",
+ * and latter means "rseq initialization failed". This value is
+ * meant to be read within rseq critical sections and compared
+ * with the cpu_id_start value previously read, before performing
+ * the commit instruction, or read and compared with the
+ * cpu_id_start value before returning a value loaded from a data
+ * structure indexed using the cpu_id_start value.
+ */
+ __u32 cpu_id;
+ /*
+ * Restartable sequences rseq_cs field.
+ *
+ * Contains NULL when no critical section is active for the current
+ * thread, or holds a pointer to the currently active struct rseq_cs.
+ *
+ * Updated by user-space, which sets the address of the currently
+ * active rseq_cs at the beginning of assembly instruction sequence
+ * block, and set to NULL by the kernel when it restarts an assembly
+ * instruction sequence block, as well as when the kernel detects that
+ * it is preempting or delivering a signal outside of the range
+ * targeted by the rseq_cs. Also needs to be set to NULL by user-space
+ * before reclaiming memory that contains the targeted struct rseq_cs.
+ *
+ * Read and set by the kernel. Set by user-space with single-copy
+ * atomicity semantics. This field should only be updated by the
+ * thread which registered this data structure. Aligned on 64-bit.
+ */
+ union {
+ __u64 ptr64;
+
+ /*
+ * The "arch" field provides architecture accessor for
+ * the ptr field based on architecture pointer size and
+ * endianness.
+ */
+ struct {
+#ifdef __LP64__
+ __u64 ptr;
+#elif defined(__BYTE_ORDER) ? (__BYTE_ORDER == __BIG_ENDIAN) : defined(__BIG_ENDIAN)
+ __u32 padding; /* Initialized to zero. */
+ __u32 ptr;
+#else
+ __u32 ptr;
+ __u32 padding; /* Initialized to zero. */
+#endif
+ } arch;
+ } rseq_cs;
+
+ /*
+ * Restartable sequences flags field.
+ *
+ * This field should only be updated by the thread which
+ * registered this data structure. Read by the kernel.
+ * Mainly used for single-stepping through rseq critical sections
+ * with debuggers.
+ *
+ * - RSEQ_ABI_CS_FLAG_NO_RESTART_ON_PREEMPT
+ * Inhibit instruction sequence block restart on preemption
+ * for this thread.
+ * - RSEQ_ABI_CS_FLAG_NO_RESTART_ON_SIGNAL
+ * Inhibit instruction sequence block restart on signal
+ * delivery for this thread.
+ * - RSEQ_ABI_CS_FLAG_NO_RESTART_ON_MIGRATE
+ * Inhibit instruction sequence block restart on migration for
+ * this thread.
+ */
+ __u32 flags;
+} __attribute__((aligned(4 * sizeof(__u64))));
+
+#endif /* _RSEQ_ABI_H */
diff --git a/tools/testing/selftests/rseq/rseq-arm.h b/tools/testing/selftests/rseq/rseq-arm.h
index 5943c816c07c..893a11eca9d5 100644
--- a/tools/testing/selftests/rseq/rseq-arm.h
+++ b/tools/testing/selftests/rseq/rseq-arm.h
@@ -147,14 +147,11 @@ do { \
teardown \
"b %l[" __rseq_str(cmpfail_label) "]\n\t"
-#define rseq_workaround_gcc_asm_size_guess() __asm__ __volatile__("")
-
static inline __attribute__((always_inline))
int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
{
RSEQ_INJECT_C(9)
- rseq_workaround_gcc_asm_size_guess();
__asm__ __volatile__ goto (
RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
@@ -185,8 +182,8 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
"5:\n\t"
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
[v] "m" (*v),
[expect] "r" (expect),
[newv] "r" (newv)
@@ -198,30 +195,31 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
, error1, error2
#endif
);
- rseq_workaround_gcc_asm_size_guess();
+ rseq_after_asm_goto();
return 0;
abort:
- rseq_workaround_gcc_asm_size_guess();
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
- rseq_workaround_gcc_asm_size_guess();
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
static inline __attribute__((always_inline))
int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
- off_t voffp, intptr_t *load, int cpu)
+ long voffp, intptr_t *load, int cpu)
{
RSEQ_INJECT_C(9)
- rseq_workaround_gcc_asm_size_guess();
__asm__ __volatile__ goto (
RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
@@ -255,8 +253,8 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
"5:\n\t"
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
/* final store input */
[v] "m" (*v),
[expectnot] "r" (expectnot),
@@ -270,19 +268,21 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
, error1, error2
#endif
);
- rseq_workaround_gcc_asm_size_guess();
+ rseq_after_asm_goto();
return 0;
abort:
- rseq_workaround_gcc_asm_size_guess();
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
- rseq_workaround_gcc_asm_size_guess();
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
@@ -292,7 +292,6 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
{
RSEQ_INJECT_C(9)
- rseq_workaround_gcc_asm_size_guess();
__asm__ __volatile__ goto (
RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
#ifdef RSEQ_COMPARE_TWICE
@@ -316,8 +315,8 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
"5:\n\t"
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
[v] "m" (*v),
[count] "Ir" (count)
RSEQ_INJECT_INPUT
@@ -328,14 +327,15 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
, error1
#endif
);
- rseq_workaround_gcc_asm_size_guess();
+ rseq_after_asm_goto();
return 0;
abort:
- rseq_workaround_gcc_asm_size_guess();
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
#endif
}
@@ -347,7 +347,6 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
{
RSEQ_INJECT_C(9)
- rseq_workaround_gcc_asm_size_guess();
__asm__ __volatile__ goto (
RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
@@ -381,8 +380,8 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
"5:\n\t"
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
/* try store input */
[v2] "m" (*v2),
[newv2] "r" (newv2),
@@ -398,19 +397,21 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
, error1, error2
#endif
);
- rseq_workaround_gcc_asm_size_guess();
+ rseq_after_asm_goto();
return 0;
abort:
- rseq_workaround_gcc_asm_size_guess();
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
- rseq_workaround_gcc_asm_size_guess();
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
@@ -422,7 +423,6 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
{
RSEQ_INJECT_C(9)
- rseq_workaround_gcc_asm_size_guess();
__asm__ __volatile__ goto (
RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
@@ -457,8 +457,8 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
"5:\n\t"
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
/* try store input */
[v2] "m" (*v2),
[newv2] "r" (newv2),
@@ -474,19 +474,21 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
, error1, error2
#endif
);
- rseq_workaround_gcc_asm_size_guess();
+ rseq_after_asm_goto();
return 0;
abort:
- rseq_workaround_gcc_asm_size_guess();
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
- rseq_workaround_gcc_asm_size_guess();
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
@@ -498,7 +500,6 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
{
RSEQ_INJECT_C(9)
- rseq_workaround_gcc_asm_size_guess();
__asm__ __volatile__ goto (
RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
@@ -537,8 +538,8 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
"5:\n\t"
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
/* cmp2 input */
[v2] "m" (*v2),
[expect2] "r" (expect2),
@@ -554,21 +555,24 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
, error1, error2, error3
#endif
);
- rseq_workaround_gcc_asm_size_guess();
+ rseq_after_asm_goto();
return 0;
abort:
- rseq_workaround_gcc_asm_size_guess();
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
- rseq_workaround_gcc_asm_size_guess();
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("1st expected value comparison failed");
error3:
+ rseq_after_asm_goto();
rseq_bug("2nd expected value comparison failed");
#endif
}
@@ -582,7 +586,6 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
RSEQ_INJECT_C(9)
- rseq_workaround_gcc_asm_size_guess();
__asm__ __volatile__ goto (
RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
@@ -657,8 +660,8 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
"8:\n\t"
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
/* final store input */
[v] "m" (*v),
[expect] "r" (expect),
@@ -678,21 +681,21 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
, error1, error2
#endif
);
- rseq_workaround_gcc_asm_size_guess();
+ rseq_after_asm_goto();
return 0;
abort:
- rseq_workaround_gcc_asm_size_guess();
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
- rseq_workaround_gcc_asm_size_guess();
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
- rseq_workaround_gcc_asm_size_guess();
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
- rseq_workaround_gcc_asm_size_guess();
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
@@ -706,7 +709,6 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
RSEQ_INJECT_C(9)
- rseq_workaround_gcc_asm_size_guess();
__asm__ __volatile__ goto (
RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
@@ -782,8 +784,8 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
"8:\n\t"
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
/* final store input */
[v] "m" (*v),
[expect] "r" (expect),
@@ -803,21 +805,21 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
, error1, error2
#endif
);
- rseq_workaround_gcc_asm_size_guess();
+ rseq_after_asm_goto();
return 0;
abort:
- rseq_workaround_gcc_asm_size_guess();
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
- rseq_workaround_gcc_asm_size_guess();
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
- rseq_workaround_gcc_asm_size_guess();
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
- rseq_workaround_gcc_asm_size_guess();
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
diff --git a/tools/testing/selftests/rseq/rseq-arm64.h b/tools/testing/selftests/rseq/rseq-arm64.h
index 200dae9e4208..cbe190a4d005 100644
--- a/tools/testing/selftests/rseq/rseq-arm64.h
+++ b/tools/testing/selftests/rseq/rseq-arm64.h
@@ -230,8 +230,8 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
RSEQ_ASM_DEFINE_ABORT(4, abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "Qo" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "Qo" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
[v] "Qo" (*v),
[expect] "r" (expect),
[newv] "r" (newv)
@@ -242,24 +242,28 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
, error1, error2
#endif
);
-
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
static inline __attribute__((always_inline))
int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
- off_t voffp, intptr_t *load, int cpu)
+ long voffp, intptr_t *load, int cpu)
{
RSEQ_INJECT_C(9)
@@ -287,8 +291,8 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
RSEQ_ASM_DEFINE_ABORT(4, abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "Qo" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "Qo" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
[v] "Qo" (*v),
[expectnot] "r" (expectnot),
[load] "Qo" (*load),
@@ -300,16 +304,21 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
, error1, error2
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
@@ -337,8 +346,8 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
RSEQ_ASM_DEFINE_ABORT(4, abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "Qo" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "Qo" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
[v] "Qo" (*v),
[count] "r" (count)
RSEQ_INJECT_INPUT
@@ -348,12 +357,15 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
, error1
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
#endif
}
@@ -388,8 +400,8 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
RSEQ_ASM_DEFINE_ABORT(4, abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "Qo" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "Qo" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
[expect] "r" (expect),
[v] "Qo" (*v),
[newv] "r" (newv),
@@ -402,17 +414,21 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
, error1, error2
#endif
);
-
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
@@ -447,8 +463,8 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
RSEQ_ASM_DEFINE_ABORT(4, abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "Qo" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "Qo" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
[expect] "r" (expect),
[v] "Qo" (*v),
[newv] "r" (newv),
@@ -461,17 +477,21 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
, error1, error2
#endif
);
-
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
@@ -508,8 +528,8 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
RSEQ_ASM_DEFINE_ABORT(4, abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "Qo" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "Qo" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
[v] "Qo" (*v),
[expect] "r" (expect),
[v2] "Qo" (*v2),
@@ -522,19 +542,24 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
, error1, error2, error3
#endif
);
-
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
error3:
+ rseq_after_asm_goto();
rseq_bug("2nd expected value comparison failed");
#endif
}
@@ -569,8 +594,8 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
RSEQ_ASM_DEFINE_ABORT(4, abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "Qo" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "Qo" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
[expect] "r" (expect),
[v] "Qo" (*v),
[newv] "r" (newv),
@@ -584,17 +609,21 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
, error1, error2
#endif
);
-
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
@@ -629,8 +658,8 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
RSEQ_ASM_DEFINE_ABORT(4, abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "Qo" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "Qo" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
[expect] "r" (expect),
[v] "Qo" (*v),
[newv] "r" (newv),
@@ -644,17 +673,21 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
, error1, error2
#endif
);
-
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
diff --git a/tools/testing/selftests/rseq/rseq-generic-thread-pointer.h b/tools/testing/selftests/rseq/rseq-generic-thread-pointer.h
new file mode 100644
index 000000000000..38c584661571
--- /dev/null
+++ b/tools/testing/selftests/rseq/rseq-generic-thread-pointer.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: LGPL-2.1-only OR MIT */
+/*
+ * rseq-generic-thread-pointer.h
+ *
+ * (C) Copyright 2021 - Mathieu Desnoyers <[email protected]>
+ */
+
+#ifndef _RSEQ_GENERIC_THREAD_POINTER
+#define _RSEQ_GENERIC_THREAD_POINTER
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/* Use gcc builtin thread pointer. */
+static inline void *rseq_thread_pointer(void)
+{
+ return __builtin_thread_pointer();
+}
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif
diff --git a/tools/testing/selftests/rseq/rseq-mips.h b/tools/testing/selftests/rseq/rseq-mips.h
index e989e7c14b09..878739fae2fd 100644
--- a/tools/testing/selftests/rseq/rseq-mips.h
+++ b/tools/testing/selftests/rseq/rseq-mips.h
@@ -154,14 +154,11 @@ do { \
teardown \
"b %l[" __rseq_str(cmpfail_label) "]\n\t"
-#define rseq_workaround_gcc_asm_size_guess() __asm__ __volatile__("")
-
static inline __attribute__((always_inline))
int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
{
RSEQ_INJECT_C(9)
- rseq_workaround_gcc_asm_size_guess();
__asm__ __volatile__ goto (
RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
@@ -190,8 +187,8 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
"5:\n\t"
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
[v] "m" (*v),
[expect] "r" (expect),
[newv] "r" (newv)
@@ -203,14 +200,11 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
, error1, error2
#endif
);
- rseq_workaround_gcc_asm_size_guess();
return 0;
abort:
- rseq_workaround_gcc_asm_size_guess();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
- rseq_workaround_gcc_asm_size_guess();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
@@ -222,11 +216,10 @@ error2:
static inline __attribute__((always_inline))
int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
- off_t voffp, intptr_t *load, int cpu)
+ long voffp, intptr_t *load, int cpu)
{
RSEQ_INJECT_C(9)
- rseq_workaround_gcc_asm_size_guess();
__asm__ __volatile__ goto (
RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
@@ -258,8 +251,8 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
"5:\n\t"
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
/* final store input */
[v] "m" (*v),
[expectnot] "r" (expectnot),
@@ -273,14 +266,11 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
, error1, error2
#endif
);
- rseq_workaround_gcc_asm_size_guess();
return 0;
abort:
- rseq_workaround_gcc_asm_size_guess();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
- rseq_workaround_gcc_asm_size_guess();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
@@ -295,7 +285,6 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
{
RSEQ_INJECT_C(9)
- rseq_workaround_gcc_asm_size_guess();
__asm__ __volatile__ goto (
RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
#ifdef RSEQ_COMPARE_TWICE
@@ -319,8 +308,8 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
"5:\n\t"
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
[v] "m" (*v),
[count] "Ir" (count)
RSEQ_INJECT_INPUT
@@ -331,10 +320,8 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
, error1
#endif
);
- rseq_workaround_gcc_asm_size_guess();
return 0;
abort:
- rseq_workaround_gcc_asm_size_guess();
RSEQ_INJECT_FAILED
return -1;
#ifdef RSEQ_COMPARE_TWICE
@@ -350,7 +337,6 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
{
RSEQ_INJECT_C(9)
- rseq_workaround_gcc_asm_size_guess();
__asm__ __volatile__ goto (
RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
@@ -382,8 +368,8 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
"5:\n\t"
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
/* try store input */
[v2] "m" (*v2),
[newv2] "r" (newv2),
@@ -399,14 +385,11 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
, error1, error2
#endif
);
- rseq_workaround_gcc_asm_size_guess();
return 0;
abort:
- rseq_workaround_gcc_asm_size_guess();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
- rseq_workaround_gcc_asm_size_guess();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
@@ -423,7 +406,6 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
{
RSEQ_INJECT_C(9)
- rseq_workaround_gcc_asm_size_guess();
__asm__ __volatile__ goto (
RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
@@ -456,8 +438,8 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
"5:\n\t"
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
/* try store input */
[v2] "m" (*v2),
[newv2] "r" (newv2),
@@ -473,14 +455,11 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
, error1, error2
#endif
);
- rseq_workaround_gcc_asm_size_guess();
return 0;
abort:
- rseq_workaround_gcc_asm_size_guess();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
- rseq_workaround_gcc_asm_size_guess();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
@@ -497,7 +476,6 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
{
RSEQ_INJECT_C(9)
- rseq_workaround_gcc_asm_size_guess();
__asm__ __volatile__ goto (
RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
@@ -532,8 +510,8 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
"5:\n\t"
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
/* cmp2 input */
[v2] "m" (*v2),
[expect2] "r" (expect2),
@@ -549,14 +527,11 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
, error1, error2, error3
#endif
);
- rseq_workaround_gcc_asm_size_guess();
return 0;
abort:
- rseq_workaround_gcc_asm_size_guess();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
- rseq_workaround_gcc_asm_size_guess();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
@@ -577,7 +552,6 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
RSEQ_INJECT_C(9)
- rseq_workaround_gcc_asm_size_guess();
__asm__ __volatile__ goto (
RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
@@ -649,8 +623,8 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
"8:\n\t"
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
/* final store input */
[v] "m" (*v),
[expect] "r" (expect),
@@ -670,21 +644,16 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
, error1, error2
#endif
);
- rseq_workaround_gcc_asm_size_guess();
return 0;
abort:
- rseq_workaround_gcc_asm_size_guess();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
- rseq_workaround_gcc_asm_size_guess();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
- rseq_workaround_gcc_asm_size_guess();
rseq_bug("cpu_id comparison failed");
error2:
- rseq_workaround_gcc_asm_size_guess();
rseq_bug("expected value comparison failed");
#endif
}
@@ -698,7 +667,6 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
RSEQ_INJECT_C(9)
- rseq_workaround_gcc_asm_size_guess();
__asm__ __volatile__ goto (
RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
@@ -771,8 +739,8 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
"8:\n\t"
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
/* final store input */
[v] "m" (*v),
[expect] "r" (expect),
@@ -792,21 +760,16 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
, error1, error2
#endif
);
- rseq_workaround_gcc_asm_size_guess();
return 0;
abort:
- rseq_workaround_gcc_asm_size_guess();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
- rseq_workaround_gcc_asm_size_guess();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
- rseq_workaround_gcc_asm_size_guess();
rseq_bug("cpu_id comparison failed");
error2:
- rseq_workaround_gcc_asm_size_guess();
rseq_bug("expected value comparison failed");
#endif
}
diff --git a/tools/testing/selftests/rseq/rseq-ppc-thread-pointer.h b/tools/testing/selftests/rseq/rseq-ppc-thread-pointer.h
new file mode 100644
index 000000000000..263eee84fb76
--- /dev/null
+++ b/tools/testing/selftests/rseq/rseq-ppc-thread-pointer.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: LGPL-2.1-only OR MIT */
+/*
+ * rseq-ppc-thread-pointer.h
+ *
+ * (C) Copyright 2021 - Mathieu Desnoyers <[email protected]>
+ */
+
+#ifndef _RSEQ_PPC_THREAD_POINTER
+#define _RSEQ_PPC_THREAD_POINTER
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+static inline void *rseq_thread_pointer(void)
+{
+#ifdef __powerpc64__
+ register void *__result asm ("r13");
+#else
+ register void *__result asm ("r2");
+#endif
+ asm ("" : "=r" (__result));
+ return __result;
+}
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif
diff --git a/tools/testing/selftests/rseq/rseq-ppc.h b/tools/testing/selftests/rseq/rseq-ppc.h
index 76be90196fe4..bab8e0b9fb11 100644
--- a/tools/testing/selftests/rseq/rseq-ppc.h
+++ b/tools/testing/selftests/rseq/rseq-ppc.h
@@ -47,10 +47,13 @@ do { \
#ifdef __PPC64__
-#define STORE_WORD "std "
-#define LOAD_WORD "ld "
-#define LOADX_WORD "ldx "
-#define CMP_WORD "cmpd "
+#define RSEQ_STORE_LONG(arg) "std%U[" __rseq_str(arg) "]%X[" __rseq_str(arg) "] " /* To memory ("m" constraint) */
+#define RSEQ_STORE_INT(arg) "stw%U[" __rseq_str(arg) "]%X[" __rseq_str(arg) "] " /* To memory ("m" constraint) */
+#define RSEQ_LOAD_LONG(arg) "ld%U[" __rseq_str(arg) "]%X[" __rseq_str(arg) "] " /* From memory ("m" constraint) */
+#define RSEQ_LOAD_INT(arg) "lwz%U[" __rseq_str(arg) "]%X[" __rseq_str(arg) "] " /* From memory ("m" constraint) */
+#define RSEQ_LOADX_LONG "ldx " /* From base register ("b" constraint) */
+#define RSEQ_CMP_LONG "cmpd "
+#define RSEQ_CMP_LONG_INT "cmpdi "
#define __RSEQ_ASM_DEFINE_TABLE(label, version, flags, \
start_ip, post_commit_offset, abort_ip) \
@@ -89,10 +92,13 @@ do { \
#else /* #ifdef __PPC64__ */
-#define STORE_WORD "stw "
-#define LOAD_WORD "lwz "
-#define LOADX_WORD "lwzx "
-#define CMP_WORD "cmpw "
+#define RSEQ_STORE_LONG(arg) "stw%U[" __rseq_str(arg) "]%X[" __rseq_str(arg) "] " /* To memory ("m" constraint) */
+#define RSEQ_STORE_INT(arg) RSEQ_STORE_LONG(arg) /* To memory ("m" constraint) */
+#define RSEQ_LOAD_LONG(arg) "lwz%U[" __rseq_str(arg) "]%X[" __rseq_str(arg) "] " /* From memory ("m" constraint) */
+#define RSEQ_LOAD_INT(arg) RSEQ_LOAD_LONG(arg) /* From memory ("m" constraint) */
+#define RSEQ_LOADX_LONG "lwzx " /* From base register ("b" constraint) */
+#define RSEQ_CMP_LONG "cmpw "
+#define RSEQ_CMP_LONG_INT "cmpwi "
#define __RSEQ_ASM_DEFINE_TABLE(label, version, flags, \
start_ip, post_commit_offset, abort_ip) \
@@ -125,7 +131,7 @@ do { \
RSEQ_INJECT_ASM(1) \
"lis %%r17, (" __rseq_str(cs_label) ")@ha\n\t" \
"addi %%r17, %%r17, (" __rseq_str(cs_label) ")@l\n\t" \
- "stw %%r17, %[" __rseq_str(rseq_cs) "]\n\t" \
+ RSEQ_STORE_INT(rseq_cs) "%%r17, %[" __rseq_str(rseq_cs) "]\n\t" \
__rseq_str(label) ":\n\t"
#endif /* #ifdef __PPC64__ */
@@ -136,7 +142,7 @@ do { \
#define RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, label) \
RSEQ_INJECT_ASM(2) \
- "lwz %%r17, %[" __rseq_str(current_cpu_id) "]\n\t" \
+ RSEQ_LOAD_INT(current_cpu_id) "%%r17, %[" __rseq_str(current_cpu_id) "]\n\t" \
"cmpw cr7, %[" __rseq_str(cpu_id) "], %%r17\n\t" \
"bne- cr7, " __rseq_str(label) "\n\t"
@@ -153,25 +159,25 @@ do { \
* RSEQ_ASM_OP_* (else): doesn't have hard-code registers(unless cr7)
*/
#define RSEQ_ASM_OP_CMPEQ(var, expect, label) \
- LOAD_WORD "%%r17, %[" __rseq_str(var) "]\n\t" \
- CMP_WORD "cr7, %%r17, %[" __rseq_str(expect) "]\n\t" \
+ RSEQ_LOAD_LONG(var) "%%r17, %[" __rseq_str(var) "]\n\t" \
+ RSEQ_CMP_LONG "cr7, %%r17, %[" __rseq_str(expect) "]\n\t" \
"bne- cr7, " __rseq_str(label) "\n\t"
#define RSEQ_ASM_OP_CMPNE(var, expectnot, label) \
- LOAD_WORD "%%r17, %[" __rseq_str(var) "]\n\t" \
- CMP_WORD "cr7, %%r17, %[" __rseq_str(expectnot) "]\n\t" \
+ RSEQ_LOAD_LONG(var) "%%r17, %[" __rseq_str(var) "]\n\t" \
+ RSEQ_CMP_LONG "cr7, %%r17, %[" __rseq_str(expectnot) "]\n\t" \
"beq- cr7, " __rseq_str(label) "\n\t"
#define RSEQ_ASM_OP_STORE(value, var) \
- STORE_WORD "%[" __rseq_str(value) "], %[" __rseq_str(var) "]\n\t"
+ RSEQ_STORE_LONG(var) "%[" __rseq_str(value) "], %[" __rseq_str(var) "]\n\t"
/* Load @var to r17 */
#define RSEQ_ASM_OP_R_LOAD(var) \
- LOAD_WORD "%%r17, %[" __rseq_str(var) "]\n\t"
+ RSEQ_LOAD_LONG(var) "%%r17, %[" __rseq_str(var) "]\n\t"
/* Store r17 to @var */
#define RSEQ_ASM_OP_R_STORE(var) \
- STORE_WORD "%%r17, %[" __rseq_str(var) "]\n\t"
+ RSEQ_STORE_LONG(var) "%%r17, %[" __rseq_str(var) "]\n\t"
/* Add @count to r17 */
#define RSEQ_ASM_OP_R_ADD(count) \
@@ -179,11 +185,11 @@ do { \
/* Load (r17 + voffp) to r17 */
#define RSEQ_ASM_OP_R_LOADX(voffp) \
- LOADX_WORD "%%r17, %[" __rseq_str(voffp) "], %%r17\n\t"
+ RSEQ_LOADX_LONG "%%r17, %[" __rseq_str(voffp) "], %%r17\n\t"
/* TODO: implement a faster memcpy. */
#define RSEQ_ASM_OP_R_MEMCPY() \
- "cmpdi %%r19, 0\n\t" \
+ RSEQ_CMP_LONG_INT "%%r19, 0\n\t" \
"beq 333f\n\t" \
"addi %%r20, %%r20, -1\n\t" \
"addi %%r21, %%r21, -1\n\t" \
@@ -191,16 +197,16 @@ do { \
"lbzu %%r18, 1(%%r20)\n\t" \
"stbu %%r18, 1(%%r21)\n\t" \
"addi %%r19, %%r19, -1\n\t" \
- "cmpdi %%r19, 0\n\t" \
+ RSEQ_CMP_LONG_INT "%%r19, 0\n\t" \
"bne 222b\n\t" \
"333:\n\t" \
#define RSEQ_ASM_OP_R_FINAL_STORE(var, post_commit_label) \
- STORE_WORD "%%r17, %[" __rseq_str(var) "]\n\t" \
+ RSEQ_STORE_LONG(var) "%%r17, %[" __rseq_str(var) "]\n\t" \
__rseq_str(post_commit_label) ":\n\t"
#define RSEQ_ASM_OP_FINAL_STORE(value, var, post_commit_label) \
- STORE_WORD "%[" __rseq_str(value) "], %[" __rseq_str(var) "]\n\t" \
+ RSEQ_STORE_LONG(var) "%[" __rseq_str(value) "], %[" __rseq_str(var) "]\n\t" \
__rseq_str(post_commit_label) ":\n\t"
static inline __attribute__((always_inline))
@@ -235,8 +241,8 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
RSEQ_ASM_DEFINE_ABORT(4, abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
[v] "m" (*v),
[expect] "r" (expect),
[newv] "r" (newv)
@@ -248,23 +254,28 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
, error1, error2
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
static inline __attribute__((always_inline))
int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
- off_t voffp, intptr_t *load, int cpu)
+ long voffp, intptr_t *load, int cpu)
{
RSEQ_INJECT_C(9)
@@ -301,8 +312,8 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
RSEQ_ASM_DEFINE_ABORT(4, abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
/* final store input */
[v] "m" (*v),
[expectnot] "r" (expectnot),
@@ -316,16 +327,21 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
, error1, error2
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
@@ -359,8 +375,8 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
RSEQ_ASM_DEFINE_ABORT(4, abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
/* final store input */
[v] "m" (*v),
[count] "r" (count)
@@ -372,12 +388,15 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
, error1
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
#endif
}
@@ -419,8 +438,8 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
RSEQ_ASM_DEFINE_ABORT(4, abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
/* try store input */
[v2] "m" (*v2),
[newv2] "r" (newv2),
@@ -436,16 +455,21 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
, error1, error2
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
@@ -489,8 +513,8 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
RSEQ_ASM_DEFINE_ABORT(4, abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
/* try store input */
[v2] "m" (*v2),
[newv2] "r" (newv2),
@@ -506,16 +530,21 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
, error1, error2
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
@@ -560,8 +589,8 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
RSEQ_ASM_DEFINE_ABORT(4, abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
/* cmp2 input */
[v2] "m" (*v2),
[expect2] "r" (expect2),
@@ -577,18 +606,24 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
, error1, error2, error3
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("1st expected value comparison failed");
error3:
+ rseq_after_asm_goto();
rseq_bug("2nd expected value comparison failed");
#endif
}
@@ -635,8 +670,8 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
RSEQ_ASM_DEFINE_ABORT(4, abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
/* final store input */
[v] "m" (*v),
[expect] "r" (expect),
@@ -653,16 +688,21 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
, error1, error2
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
@@ -711,8 +751,8 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
RSEQ_ASM_DEFINE_ABORT(4, abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
/* final store input */
[v] "m" (*v),
[expect] "r" (expect),
@@ -729,23 +769,23 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
, error1, error2
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
-#undef STORE_WORD
-#undef LOAD_WORD
-#undef LOADX_WORD
-#undef CMP_WORD
-
#endif /* !RSEQ_SKIP_FASTPATH */
diff --git a/tools/testing/selftests/rseq/rseq-s390.h b/tools/testing/selftests/rseq/rseq-s390.h
index 8ef94ad1cbb4..4e6dc5f0cb42 100644
--- a/tools/testing/selftests/rseq/rseq-s390.h
+++ b/tools/testing/selftests/rseq/rseq-s390.h
@@ -165,8 +165,8 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
RSEQ_ASM_DEFINE_ABORT(4, "", abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
[v] "m" (*v),
[expect] "r" (expect),
[newv] "r" (newv)
@@ -178,16 +178,21 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
, error1, error2
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
@@ -198,7 +203,7 @@ error2:
*/
static inline __attribute__((always_inline))
int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
- off_t voffp, intptr_t *load, int cpu)
+ long voffp, intptr_t *load, int cpu)
{
RSEQ_INJECT_C(9)
@@ -233,8 +238,8 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
RSEQ_ASM_DEFINE_ABORT(4, "", abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
/* final store input */
[v] "m" (*v),
[expectnot] "r" (expectnot),
@@ -248,16 +253,21 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
, error1, error2
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
@@ -288,8 +298,8 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
RSEQ_ASM_DEFINE_ABORT(4, "", abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
/* final store input */
[v] "m" (*v),
[count] "r" (count)
@@ -301,12 +311,15 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
, error1
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
#endif
}
@@ -347,8 +360,8 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
RSEQ_ASM_DEFINE_ABORT(4, "", abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
/* try store input */
[v2] "m" (*v2),
[newv2] "r" (newv2),
@@ -364,16 +377,21 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
, error1, error2
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
@@ -426,8 +444,8 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
RSEQ_ASM_DEFINE_ABORT(4, "", abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
/* cmp2 input */
[v2] "m" (*v2),
[expect2] "r" (expect2),
@@ -443,18 +461,24 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
, error1, error2, error3
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("1st expected value comparison failed");
error3:
+ rseq_after_asm_goto();
rseq_bug("2nd expected value comparison failed");
#endif
}
@@ -534,8 +558,8 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
#endif
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
/* final store input */
[v] "m" (*v),
[expect] "r" (expect),
@@ -555,16 +579,21 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
, error1, error2
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
diff --git a/tools/testing/selftests/rseq/rseq-skip.h b/tools/testing/selftests/rseq/rseq-skip.h
index 72750b5905a9..7b53dac1fcdd 100644
--- a/tools/testing/selftests/rseq/rseq-skip.h
+++ b/tools/testing/selftests/rseq/rseq-skip.h
@@ -13,7 +13,7 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
static inline __attribute__((always_inline))
int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
- off_t voffp, intptr_t *load, int cpu)
+ long voffp, intptr_t *load, int cpu)
{
return -1;
}
diff --git a/tools/testing/selftests/rseq/rseq-thread-pointer.h b/tools/testing/selftests/rseq/rseq-thread-pointer.h
new file mode 100644
index 000000000000..977c25d758b2
--- /dev/null
+++ b/tools/testing/selftests/rseq/rseq-thread-pointer.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: LGPL-2.1-only OR MIT */
+/*
+ * rseq-thread-pointer.h
+ *
+ * (C) Copyright 2021 - Mathieu Desnoyers <[email protected]>
+ */
+
+#ifndef _RSEQ_THREAD_POINTER
+#define _RSEQ_THREAD_POINTER
+
+#if defined(__x86_64__) || defined(__i386__)
+#include "rseq-x86-thread-pointer.h"
+#elif defined(__PPC__)
+#include "rseq-ppc-thread-pointer.h"
+#else
+#include "rseq-generic-thread-pointer.h"
+#endif
+
+#endif
diff --git a/tools/testing/selftests/rseq/rseq-x86-thread-pointer.h b/tools/testing/selftests/rseq/rseq-x86-thread-pointer.h
new file mode 100644
index 000000000000..d3133587d996
--- /dev/null
+++ b/tools/testing/selftests/rseq/rseq-x86-thread-pointer.h
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: LGPL-2.1-only OR MIT */
+/*
+ * rseq-x86-thread-pointer.h
+ *
+ * (C) Copyright 2021 - Mathieu Desnoyers <[email protected]>
+ */
+
+#ifndef _RSEQ_X86_THREAD_POINTER
+#define _RSEQ_X86_THREAD_POINTER
+
+#include <features.h>
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#if __GNUC_PREREQ (11, 1)
+static inline void *rseq_thread_pointer(void)
+{
+ return __builtin_thread_pointer();
+}
+#else
+static inline void *rseq_thread_pointer(void)
+{
+ void *__result;
+
+# ifdef __x86_64__
+ __asm__ ("mov %%fs:0, %0" : "=r" (__result));
+# else
+ __asm__ ("mov %%gs:0, %0" : "=r" (__result));
+# endif
+ return __result;
+}
+#endif /* !GCC 11 */
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif
diff --git a/tools/testing/selftests/rseq/rseq-x86.h b/tools/testing/selftests/rseq/rseq-x86.h
index 640411518e46..bd01dc41ca13 100644
--- a/tools/testing/selftests/rseq/rseq-x86.h
+++ b/tools/testing/selftests/rseq/rseq-x86.h
@@ -28,6 +28,8 @@
#ifdef __x86_64__
+#define RSEQ_ASM_TP_SEGMENT %%fs
+
#define rseq_smp_mb() \
__asm__ __volatile__ ("lock; addl $0,-128(%%rsp)" ::: "memory", "cc")
#define rseq_smp_rmb() rseq_barrier()
@@ -123,14 +125,14 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
#endif
/* Start rseq by storing table entry pointer into rseq_cs. */
- RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+ RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
RSEQ_INJECT_ASM(3)
"cmpq %[v], %[expect]\n\t"
"jnz %l[cmpfail]\n\t"
RSEQ_INJECT_ASM(4)
#ifdef RSEQ_COMPARE_TWICE
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1])
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
"cmpq %[v], %[expect]\n\t"
"jnz %l[error2]\n\t"
#endif
@@ -141,7 +143,7 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
RSEQ_ASM_DEFINE_ABORT(4, "", abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [rseq_abi] "r" (&__rseq_abi),
+ [rseq_offset] "r" (rseq_offset),
[v] "m" (*v),
[expect] "r" (expect),
[newv] "r" (newv)
@@ -152,16 +154,21 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
, error1, error2
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
@@ -172,7 +179,7 @@ error2:
*/
static inline __attribute__((always_inline))
int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
- off_t voffp, intptr_t *load, int cpu)
+ long voffp, intptr_t *load, int cpu)
{
RSEQ_INJECT_C(9)
@@ -184,15 +191,15 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
#endif
/* Start rseq by storing table entry pointer into rseq_cs. */
- RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+ RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
RSEQ_INJECT_ASM(3)
"movq %[v], %%rbx\n\t"
"cmpq %%rbx, %[expectnot]\n\t"
"je %l[cmpfail]\n\t"
RSEQ_INJECT_ASM(4)
#ifdef RSEQ_COMPARE_TWICE
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1])
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
"movq %[v], %%rbx\n\t"
"cmpq %%rbx, %[expectnot]\n\t"
"je %l[error2]\n\t"
@@ -207,7 +214,7 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
RSEQ_ASM_DEFINE_ABORT(4, "", abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [rseq_abi] "r" (&__rseq_abi),
+ [rseq_offset] "r" (rseq_offset),
/* final store input */
[v] "m" (*v),
[expectnot] "r" (expectnot),
@@ -220,16 +227,21 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
, error1, error2
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
@@ -245,11 +257,11 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1])
#endif
/* Start rseq by storing table entry pointer into rseq_cs. */
- RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+ RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
RSEQ_INJECT_ASM(3)
#ifdef RSEQ_COMPARE_TWICE
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1])
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
#endif
/* final store */
"addq %[count], %[v]\n\t"
@@ -258,7 +270,7 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
RSEQ_ASM_DEFINE_ABORT(4, "", abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [rseq_abi] "r" (&__rseq_abi),
+ [rseq_offset] "r" (rseq_offset),
/* final store input */
[v] "m" (*v),
[count] "er" (count)
@@ -269,12 +281,15 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
, error1
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
#endif
}
@@ -286,7 +301,7 @@ error1:
* *pval += inc;
*/
static inline __attribute__((always_inline))
-int rseq_offset_deref_addv(intptr_t *ptr, off_t off, intptr_t inc, int cpu)
+int rseq_offset_deref_addv(intptr_t *ptr, long off, intptr_t inc, int cpu)
{
RSEQ_INJECT_C(9)
@@ -296,11 +311,11 @@ int rseq_offset_deref_addv(intptr_t *ptr, off_t off, intptr_t inc, int cpu)
RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1])
#endif
/* Start rseq by storing table entry pointer into rseq_cs. */
- RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+ RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
RSEQ_INJECT_ASM(3)
#ifdef RSEQ_COMPARE_TWICE
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1])
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
#endif
/* get p+v */
"movq %[ptr], %%rbx\n\t"
@@ -314,7 +329,7 @@ int rseq_offset_deref_addv(intptr_t *ptr, off_t off, intptr_t inc, int cpu)
RSEQ_ASM_DEFINE_ABORT(4, "", abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [rseq_abi] "r" (&__rseq_abi),
+ [rseq_offset] "r" (rseq_offset),
/* final store input */
[ptr] "m" (*ptr),
[off] "er" (off),
@@ -351,14 +366,14 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
#endif
/* Start rseq by storing table entry pointer into rseq_cs. */
- RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+ RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
RSEQ_INJECT_ASM(3)
"cmpq %[v], %[expect]\n\t"
"jnz %l[cmpfail]\n\t"
RSEQ_INJECT_ASM(4)
#ifdef RSEQ_COMPARE_TWICE
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1])
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
"cmpq %[v], %[expect]\n\t"
"jnz %l[error2]\n\t"
#endif
@@ -372,7 +387,7 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
RSEQ_ASM_DEFINE_ABORT(4, "", abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [rseq_abi] "r" (&__rseq_abi),
+ [rseq_offset] "r" (rseq_offset),
/* try store input */
[v2] "m" (*v2),
[newv2] "r" (newv2),
@@ -387,16 +402,21 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
, error1, error2
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
@@ -426,8 +446,8 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error3])
#endif
/* Start rseq by storing table entry pointer into rseq_cs. */
- RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+ RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
RSEQ_INJECT_ASM(3)
"cmpq %[v], %[expect]\n\t"
"jnz %l[cmpfail]\n\t"
@@ -436,7 +456,7 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
"jnz %l[cmpfail]\n\t"
RSEQ_INJECT_ASM(5)
#ifdef RSEQ_COMPARE_TWICE
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1])
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
"cmpq %[v], %[expect]\n\t"
"jnz %l[error2]\n\t"
"cmpq %[v2], %[expect2]\n\t"
@@ -449,7 +469,7 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
RSEQ_ASM_DEFINE_ABORT(4, "", abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [rseq_abi] "r" (&__rseq_abi),
+ [rseq_offset] "r" (rseq_offset),
/* cmp2 input */
[v2] "m" (*v2),
[expect2] "r" (expect2),
@@ -464,18 +484,24 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
, error1, error2, error3
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("1st expected value comparison failed");
error3:
+ rseq_after_asm_goto();
rseq_bug("2nd expected value comparison failed");
#endif
}
@@ -500,14 +526,14 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
"movq %[dst], %[rseq_scratch1]\n\t"
"movq %[len], %[rseq_scratch2]\n\t"
/* Start rseq by storing table entry pointer into rseq_cs. */
- RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+ RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
RSEQ_INJECT_ASM(3)
"cmpq %[v], %[expect]\n\t"
"jnz 5f\n\t"
RSEQ_INJECT_ASM(4)
#ifdef RSEQ_COMPARE_TWICE
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 6f)
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 6f)
"cmpq %[v], %[expect]\n\t"
"jnz 7f\n\t"
#endif
@@ -555,7 +581,7 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
#endif
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [rseq_abi] "r" (&__rseq_abi),
+ [rseq_offset] "r" (rseq_offset),
/* final store input */
[v] "m" (*v),
[expect] "r" (expect),
@@ -574,16 +600,21 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
, error1, error2
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
@@ -600,7 +631,9 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
#endif /* !RSEQ_SKIP_FASTPATH */
-#elif __i386__
+#elif defined(__i386__)
+
+#define RSEQ_ASM_TP_SEGMENT %%gs
#define rseq_smp_mb() \
__asm__ __volatile__ ("lock; addl $0,-128(%%esp)" ::: "memory", "cc")
@@ -701,14 +734,14 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
#endif
/* Start rseq by storing table entry pointer into rseq_cs. */
- RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+ RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
RSEQ_INJECT_ASM(3)
"cmpl %[v], %[expect]\n\t"
"jnz %l[cmpfail]\n\t"
RSEQ_INJECT_ASM(4)
#ifdef RSEQ_COMPARE_TWICE
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1])
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
"cmpl %[v], %[expect]\n\t"
"jnz %l[error2]\n\t"
#endif
@@ -719,7 +752,7 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
RSEQ_ASM_DEFINE_ABORT(4, "", abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [rseq_abi] "r" (&__rseq_abi),
+ [rseq_offset] "r" (rseq_offset),
[v] "m" (*v),
[expect] "r" (expect),
[newv] "r" (newv)
@@ -730,16 +763,21 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
, error1, error2
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
@@ -750,7 +788,7 @@ error2:
*/
static inline __attribute__((always_inline))
int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
- off_t voffp, intptr_t *load, int cpu)
+ long voffp, intptr_t *load, int cpu)
{
RSEQ_INJECT_C(9)
@@ -762,15 +800,15 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
#endif
/* Start rseq by storing table entry pointer into rseq_cs. */
- RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+ RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
RSEQ_INJECT_ASM(3)
"movl %[v], %%ebx\n\t"
"cmpl %%ebx, %[expectnot]\n\t"
"je %l[cmpfail]\n\t"
RSEQ_INJECT_ASM(4)
#ifdef RSEQ_COMPARE_TWICE
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1])
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
"movl %[v], %%ebx\n\t"
"cmpl %%ebx, %[expectnot]\n\t"
"je %l[error2]\n\t"
@@ -785,7 +823,7 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
RSEQ_ASM_DEFINE_ABORT(4, "", abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [rseq_abi] "r" (&__rseq_abi),
+ [rseq_offset] "r" (rseq_offset),
/* final store input */
[v] "m" (*v),
[expectnot] "r" (expectnot),
@@ -798,16 +836,21 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
, error1, error2
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
@@ -823,11 +866,11 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1])
#endif
/* Start rseq by storing table entry pointer into rseq_cs. */
- RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+ RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
RSEQ_INJECT_ASM(3)
#ifdef RSEQ_COMPARE_TWICE
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1])
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
#endif
/* final store */
"addl %[count], %[v]\n\t"
@@ -836,7 +879,7 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
RSEQ_ASM_DEFINE_ABORT(4, "", abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [rseq_abi] "r" (&__rseq_abi),
+ [rseq_offset] "r" (rseq_offset),
/* final store input */
[v] "m" (*v),
[count] "ir" (count)
@@ -847,12 +890,15 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
, error1
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
#endif
}
@@ -872,14 +918,14 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
#endif
/* Start rseq by storing table entry pointer into rseq_cs. */
- RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+ RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
RSEQ_INJECT_ASM(3)
"cmpl %[v], %[expect]\n\t"
"jnz %l[cmpfail]\n\t"
RSEQ_INJECT_ASM(4)
#ifdef RSEQ_COMPARE_TWICE
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1])
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
"cmpl %[v], %[expect]\n\t"
"jnz %l[error2]\n\t"
#endif
@@ -894,7 +940,7 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
RSEQ_ASM_DEFINE_ABORT(4, "", abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [rseq_abi] "r" (&__rseq_abi),
+ [rseq_offset] "r" (rseq_offset),
/* try store input */
[v2] "m" (*v2),
[newv2] "m" (newv2),
@@ -909,16 +955,21 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
, error1, error2
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
@@ -938,15 +989,15 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
#endif
/* Start rseq by storing table entry pointer into rseq_cs. */
- RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+ RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
RSEQ_INJECT_ASM(3)
"movl %[expect], %%eax\n\t"
"cmpl %[v], %%eax\n\t"
"jnz %l[cmpfail]\n\t"
RSEQ_INJECT_ASM(4)
#ifdef RSEQ_COMPARE_TWICE
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1])
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
"movl %[expect], %%eax\n\t"
"cmpl %[v], %%eax\n\t"
"jnz %l[error2]\n\t"
@@ -962,7 +1013,7 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
RSEQ_ASM_DEFINE_ABORT(4, "", abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [rseq_abi] "r" (&__rseq_abi),
+ [rseq_offset] "r" (rseq_offset),
/* try store input */
[v2] "m" (*v2),
[newv2] "r" (newv2),
@@ -977,16 +1028,21 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
, error1, error2
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
@@ -1008,8 +1064,8 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error3])
#endif
/* Start rseq by storing table entry pointer into rseq_cs. */
- RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+ RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
RSEQ_INJECT_ASM(3)
"cmpl %[v], %[expect]\n\t"
"jnz %l[cmpfail]\n\t"
@@ -1018,7 +1074,7 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
"jnz %l[cmpfail]\n\t"
RSEQ_INJECT_ASM(5)
#ifdef RSEQ_COMPARE_TWICE
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1])
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
"cmpl %[v], %[expect]\n\t"
"jnz %l[error2]\n\t"
"cmpl %[expect2], %[v2]\n\t"
@@ -1032,7 +1088,7 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
RSEQ_ASM_DEFINE_ABORT(4, "", abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [rseq_abi] "r" (&__rseq_abi),
+ [rseq_offset] "r" (rseq_offset),
/* cmp2 input */
[v2] "m" (*v2),
[expect2] "r" (expect2),
@@ -1047,18 +1103,24 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
, error1, error2, error3
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("1st expected value comparison failed");
error3:
+ rseq_after_asm_goto();
rseq_bug("2nd expected value comparison failed");
#endif
}
@@ -1084,15 +1146,15 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
"movl %[dst], %[rseq_scratch1]\n\t"
"movl %[len], %[rseq_scratch2]\n\t"
/* Start rseq by storing table entry pointer into rseq_cs. */
- RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+ RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
RSEQ_INJECT_ASM(3)
"movl %[expect], %%eax\n\t"
"cmpl %%eax, %[v]\n\t"
"jnz 5f\n\t"
RSEQ_INJECT_ASM(4)
#ifdef RSEQ_COMPARE_TWICE
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 6f)
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 6f)
"movl %[expect], %%eax\n\t"
"cmpl %%eax, %[v]\n\t"
"jnz 7f\n\t"
@@ -1142,7 +1204,7 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
#endif
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [rseq_abi] "r" (&__rseq_abi),
+ [rseq_offset] "r" (rseq_offset),
/* final store input */
[v] "m" (*v),
[expect] "m" (expect),
@@ -1161,16 +1223,21 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
, error1, error2
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
@@ -1196,15 +1263,15 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
"movl %[dst], %[rseq_scratch1]\n\t"
"movl %[len], %[rseq_scratch2]\n\t"
/* Start rseq by storing table entry pointer into rseq_cs. */
- RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+ RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
RSEQ_INJECT_ASM(3)
"movl %[expect], %%eax\n\t"
"cmpl %%eax, %[v]\n\t"
"jnz 5f\n\t"
RSEQ_INJECT_ASM(4)
#ifdef RSEQ_COMPARE_TWICE
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 6f)
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 6f)
"movl %[expect], %%eax\n\t"
"cmpl %%eax, %[v]\n\t"
"jnz 7f\n\t"
@@ -1255,7 +1322,7 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
#endif
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [rseq_abi] "r" (&__rseq_abi),
+ [rseq_offset] "r" (rseq_offset),
/* final store input */
[v] "m" (*v),
[expect] "m" (expect),
@@ -1274,16 +1341,21 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
, error1, error2
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
diff --git a/tools/testing/selftests/rseq/rseq.c b/tools/testing/selftests/rseq/rseq.c
index fb440dfca158..986b9458efb2 100644
--- a/tools/testing/selftests/rseq/rseq.c
+++ b/tools/testing/selftests/rseq/rseq.c
@@ -26,130 +26,124 @@
#include <assert.h>
#include <signal.h>
#include <limits.h>
+#include <dlfcn.h>
+#include <stddef.h>
#include "../kselftest.h"
#include "rseq.h"
-__thread volatile struct rseq __rseq_abi = {
- .cpu_id = RSEQ_CPU_ID_UNINITIALIZED,
-};
-
-/*
- * Shared with other libraries. This library may take rseq ownership if it is
- * still 0 when executing the library constructor. Set to 1 by library
- * constructor when handling rseq. Set to 0 in destructor if handling rseq.
- */
-int __rseq_handled;
-
-/* Whether this library have ownership of rseq registration. */
-static int rseq_ownership;
+static const ptrdiff_t *libc_rseq_offset_p;
+static const unsigned int *libc_rseq_size_p;
+static const unsigned int *libc_rseq_flags_p;
-static __thread volatile uint32_t __rseq_refcount;
+/* Offset from the thread pointer to the rseq area. */
+ptrdiff_t rseq_offset;
-static void signal_off_save(sigset_t *oldset)
-{
- sigset_t set;
- int ret;
+/* Size of the registered rseq area. 0 if the registration was
+ unsuccessful. */
+unsigned int rseq_size = -1U;
- sigfillset(&set);
- ret = pthread_sigmask(SIG_BLOCK, &set, oldset);
- if (ret)
- abort();
-}
+/* Flags used during rseq registration. */
+unsigned int rseq_flags;
-static void signal_restore(sigset_t oldset)
-{
- int ret;
+static int rseq_ownership;
- ret = pthread_sigmask(SIG_SETMASK, &oldset, NULL);
- if (ret)
- abort();
-}
+static
+__thread struct rseq_abi __rseq_abi __attribute__((tls_model("initial-exec"))) = {
+ .cpu_id = RSEQ_ABI_CPU_ID_UNINITIALIZED,
+};
-static int sys_rseq(volatile struct rseq *rseq_abi, uint32_t rseq_len,
+static int sys_rseq(struct rseq_abi *rseq_abi, uint32_t rseq_len,
int flags, uint32_t sig)
{
return syscall(__NR_rseq, rseq_abi, rseq_len, flags, sig);
}
-int rseq_register_current_thread(void)
+int rseq_available(void)
{
- int rc, ret = 0;
- sigset_t oldset;
+ int rc;
- if (!rseq_ownership)
+ rc = sys_rseq(NULL, 0, 0, 0);
+ if (rc != -1)
+ abort();
+ switch (errno) {
+ case ENOSYS:
return 0;
- signal_off_save(&oldset);
- if (__rseq_refcount == UINT_MAX) {
- ret = -1;
- goto end;
- }
- if (__rseq_refcount++)
- goto end;
- rc = sys_rseq(&__rseq_abi, sizeof(struct rseq), 0, RSEQ_SIG);
- if (!rc) {
- assert(rseq_current_cpu_raw() >= 0);
- goto end;
+ case EINVAL:
+ return 1;
+ default:
+ abort();
}
- if (errno != EBUSY)
- __rseq_abi.cpu_id = RSEQ_CPU_ID_REGISTRATION_FAILED;
- ret = -1;
- __rseq_refcount--;
-end:
- signal_restore(oldset);
- return ret;
}
-int rseq_unregister_current_thread(void)
+int rseq_register_current_thread(void)
{
- int rc, ret = 0;
- sigset_t oldset;
+ int rc;
- if (!rseq_ownership)
+ if (!rseq_ownership) {
+ /* Treat libc's ownership as a successful registration. */
return 0;
- signal_off_save(&oldset);
- if (!__rseq_refcount) {
- ret = -1;
- goto end;
}
- if (--__rseq_refcount)
- goto end;
- rc = sys_rseq(&__rseq_abi, sizeof(struct rseq),
- RSEQ_FLAG_UNREGISTER, RSEQ_SIG);
- if (!rc)
- goto end;
- __rseq_refcount = 1;
- ret = -1;
-end:
- signal_restore(oldset);
- return ret;
+ rc = sys_rseq(&__rseq_abi, sizeof(struct rseq_abi), 0, RSEQ_SIG);
+ if (rc)
+ return -1;
+ assert(rseq_current_cpu_raw() >= 0);
+ return 0;
}
-int32_t rseq_fallback_current_cpu(void)
+int rseq_unregister_current_thread(void)
{
- int32_t cpu;
+ int rc;
- cpu = sched_getcpu();
- if (cpu < 0) {
- perror("sched_getcpu()");
- abort();
+ if (!rseq_ownership) {
+ /* Treat libc's ownership as a successful unregistration. */
+ return 0;
}
- return cpu;
+ rc = sys_rseq(&__rseq_abi, sizeof(struct rseq_abi), RSEQ_ABI_FLAG_UNREGISTER, RSEQ_SIG);
+ if (rc)
+ return -1;
+ return 0;
}
-void __attribute__((constructor)) rseq_init(void)
+static __attribute__((constructor))
+void rseq_init(void)
{
- /* Check whether rseq is handled by another library. */
- if (__rseq_handled)
+ libc_rseq_offset_p = dlsym(RTLD_NEXT, "__rseq_offset");
+ libc_rseq_size_p = dlsym(RTLD_NEXT, "__rseq_size");
+ libc_rseq_flags_p = dlsym(RTLD_NEXT, "__rseq_flags");
+ if (libc_rseq_size_p && libc_rseq_offset_p && libc_rseq_flags_p) {
+ /* rseq registration owned by glibc */
+ rseq_offset = *libc_rseq_offset_p;
+ rseq_size = *libc_rseq_size_p;
+ rseq_flags = *libc_rseq_flags_p;
+ return;
+ }
+ if (!rseq_available())
return;
- __rseq_handled = 1;
rseq_ownership = 1;
+ rseq_offset = (void *)&__rseq_abi - rseq_thread_pointer();
+ rseq_size = sizeof(struct rseq_abi);
+ rseq_flags = 0;
}
-void __attribute__((destructor)) rseq_fini(void)
+static __attribute__((destructor))
+void rseq_exit(void)
{
if (!rseq_ownership)
return;
- __rseq_handled = 0;
+ rseq_offset = 0;
+ rseq_size = -1U;
rseq_ownership = 0;
}
+
+int32_t rseq_fallback_current_cpu(void)
+{
+ int32_t cpu;
+
+ cpu = sched_getcpu();
+ if (cpu < 0) {
+ perror("sched_getcpu()");
+ abort();
+ }
+ return cpu;
+}
diff --git a/tools/testing/selftests/rseq/rseq.h b/tools/testing/selftests/rseq/rseq.h
index 3f63eb362b92..9d850b290c2e 100644
--- a/tools/testing/selftests/rseq/rseq.h
+++ b/tools/testing/selftests/rseq/rseq.h
@@ -16,7 +16,9 @@
#include <errno.h>
#include <stdio.h>
#include <stdlib.h>
-#include <linux/rseq.h>
+#include <stddef.h>
+#include "rseq-abi.h"
+#include "compiler.h"
/*
* Empty code injection macros, override when testing.
@@ -43,8 +45,20 @@
#define RSEQ_INJECT_FAILED
#endif
-extern __thread volatile struct rseq __rseq_abi;
-extern int __rseq_handled;
+#include "rseq-thread-pointer.h"
+
+/* Offset from the thread pointer to the rseq area. */
+extern ptrdiff_t rseq_offset;
+/* Size of the registered rseq area. 0 if the registration was
+ unsuccessful. */
+extern unsigned int rseq_size;
+/* Flags used during rseq registration. */
+extern unsigned int rseq_flags;
+
+static inline struct rseq_abi *rseq_get_abi(void)
+{
+ return (struct rseq_abi *) ((uintptr_t) rseq_thread_pointer() + rseq_offset);
+}
#define rseq_likely(x) __builtin_expect(!!(x), 1)
#define rseq_unlikely(x) __builtin_expect(!!(x), 0)
@@ -108,7 +122,7 @@ int32_t rseq_fallback_current_cpu(void);
*/
static inline int32_t rseq_current_cpu_raw(void)
{
- return RSEQ_ACCESS_ONCE(__rseq_abi.cpu_id);
+ return RSEQ_ACCESS_ONCE(rseq_get_abi()->cpu_id);
}
/*
@@ -124,7 +138,7 @@ static inline int32_t rseq_current_cpu_raw(void)
*/
static inline uint32_t rseq_cpu_start(void)
{
- return RSEQ_ACCESS_ONCE(__rseq_abi.cpu_id_start);
+ return RSEQ_ACCESS_ONCE(rseq_get_abi()->cpu_id_start);
}
static inline uint32_t rseq_current_cpu(void)
@@ -139,11 +153,7 @@ static inline uint32_t rseq_current_cpu(void)
static inline void rseq_clear_rseq_cs(void)
{
-#ifdef __LP64__
- __rseq_abi.rseq_cs.ptr = 0;
-#else
- __rseq_abi.rseq_cs.ptr.ptr32 = 0;
-#endif
+ RSEQ_WRITE_ONCE(rseq_get_abi()->rseq_cs.arch.ptr, 0);
}
/*
diff --git a/tools/testing/selftests/rtc/settings b/tools/testing/selftests/rtc/settings
index ba4d85f74cd6..a953c96aa16e 100644
--- a/tools/testing/selftests/rtc/settings
+++ b/tools/testing/selftests/rtc/settings
@@ -1 +1 @@
-timeout=90
+timeout=180
diff --git a/tools/testing/selftests/seccomp/Makefile b/tools/testing/selftests/seccomp/Makefile
index 0ebfe8b0e147..585f7a0c10cb 100644
--- a/tools/testing/selftests/seccomp/Makefile
+++ b/tools/testing/selftests/seccomp/Makefile
@@ -1,5 +1,5 @@
# SPDX-License-Identifier: GPL-2.0
-CFLAGS += -Wl,-no-as-needed -Wall
+CFLAGS += -Wl,-no-as-needed -Wall -isystem ../../../../usr/include/
LDFLAGS += -lpthread
TEST_GEN_PROGS := seccomp_bpf seccomp_benchmark
diff --git a/tools/testing/selftests/sgx/Makefile b/tools/testing/selftests/sgx/Makefile
index 2956584e1e37..75af864e07b6 100644
--- a/tools/testing/selftests/sgx/Makefile
+++ b/tools/testing/selftests/sgx/Makefile
@@ -4,7 +4,7 @@ include ../lib.mk
.PHONY: all clean
-CAN_BUILD_X86_64 := $(shell ../x86/check_cc.sh $(CC) \
+CAN_BUILD_X86_64 := $(shell ../x86/check_cc.sh "$(CC)" \
../x86/trivial_64bit_program.c)
ifndef OBJCOPY
diff --git a/tools/testing/selftests/sgx/load.c b/tools/testing/selftests/sgx/load.c
index 9d4322c946e2..006b464c8fc9 100644
--- a/tools/testing/selftests/sgx/load.c
+++ b/tools/testing/selftests/sgx/load.c
@@ -21,7 +21,7 @@
void encl_delete(struct encl *encl)
{
- struct encl_segment *heap_seg = &encl->segment_tbl[encl->nr_segments - 1];
+ struct encl_segment *heap_seg;
if (encl->encl_base)
munmap((void *)encl->encl_base, encl->encl_size);
@@ -32,10 +32,11 @@ void encl_delete(struct encl *encl)
if (encl->fd)
close(encl->fd);
- munmap(heap_seg->src, heap_seg->size);
-
- if (encl->segment_tbl)
+ if (encl->segment_tbl) {
+ heap_seg = &encl->segment_tbl[encl->nr_segments - 1];
+ munmap(heap_seg->src, heap_seg->size);
free(encl->segment_tbl);
+ }
memset(encl, 0, sizeof(*encl));
}
diff --git a/tools/testing/selftests/sgx/main.c b/tools/testing/selftests/sgx/main.c
index 370c4995f7c4..dd74fa42302e 100644
--- a/tools/testing/selftests/sgx/main.c
+++ b/tools/testing/selftests/sgx/main.c
@@ -146,7 +146,8 @@ static bool setup_test_encl(unsigned long heap_size, struct encl *encl,
if (!encl_load("test_encl.elf", encl, heap_size)) {
encl_delete(encl);
- TH_LOG("Failed to load the test enclave.\n");
+ TH_LOG("Failed to load the test enclave.");
+ return false;
}
if (!encl_measure(encl))
@@ -185,8 +186,6 @@ static bool setup_test_encl(unsigned long heap_size, struct encl *encl,
return true;
err:
- encl_delete(encl);
-
for (i = 0; i < encl->nr_segments; i++) {
seg = &encl->segment_tbl[i];
@@ -205,7 +204,9 @@ err:
fclose(maps_file);
}
- TH_LOG("Failed to initialize the test enclave.\n");
+ TH_LOG("Failed to initialize the test enclave.");
+
+ encl_delete(encl);
return false;
}
diff --git a/tools/testing/selftests/tpm2/tpm2.py b/tools/testing/selftests/tpm2/tpm2.py
index f34486cd7342..057a4f49c79d 100644
--- a/tools/testing/selftests/tpm2/tpm2.py
+++ b/tools/testing/selftests/tpm2/tpm2.py
@@ -56,6 +56,7 @@ TSS2_RESMGR_TPM_RC_LAYER = (11 << TSS2_RC_LAYER_SHIFT)
TPM2_CAP_HANDLES = 0x00000001
TPM2_CAP_COMMANDS = 0x00000002
+TPM2_CAP_PCRS = 0x00000005
TPM2_CAP_TPM_PROPERTIES = 0x00000006
TPM2_PT_FIXED = 0x100
@@ -712,3 +713,33 @@ class Client:
pt += 1
return handles
+
+ def get_cap_pcrs(self):
+ pcr_banks = {}
+
+ fmt = '>HII III'
+
+ cmd = struct.pack(fmt,
+ TPM2_ST_NO_SESSIONS,
+ struct.calcsize(fmt),
+ TPM2_CC_GET_CAPABILITY,
+ TPM2_CAP_PCRS, 0, 1)
+ rsp = self.send_cmd(cmd)[10:]
+ _, _, cnt = struct.unpack('>BII', rsp[:9])
+ rsp = rsp[9:]
+
+ # items are TPMS_PCR_SELECTION's
+ for i in range(0, cnt):
+ hash, sizeOfSelect = struct.unpack('>HB', rsp[:3])
+ rsp = rsp[3:]
+
+ pcrSelect = 0
+ if sizeOfSelect > 0:
+ pcrSelect, = struct.unpack('%ds' % sizeOfSelect,
+ rsp[:sizeOfSelect])
+ rsp = rsp[sizeOfSelect:]
+ pcrSelect = int.from_bytes(pcrSelect, byteorder='big')
+
+ pcr_banks[hash] = pcrSelect
+
+ return pcr_banks
diff --git a/tools/testing/selftests/tpm2/tpm2_tests.py b/tools/testing/selftests/tpm2/tpm2_tests.py
index 9d764306887b..ffe98b5c8d22 100644
--- a/tools/testing/selftests/tpm2/tpm2_tests.py
+++ b/tools/testing/selftests/tpm2/tpm2_tests.py
@@ -27,7 +27,17 @@ class SmokeTest(unittest.TestCase):
result = self.client.unseal(self.root_key, blob, auth, None)
self.assertEqual(data, result)
+ def determine_bank_alg(self, mask):
+ pcr_banks = self.client.get_cap_pcrs()
+ for bank_alg, pcrSelection in pcr_banks.items():
+ if pcrSelection & mask == mask:
+ return bank_alg
+ return None
+
def test_seal_with_policy(self):
+ bank_alg = self.determine_bank_alg(1 << 16)
+ self.assertIsNotNone(bank_alg)
+
handle = self.client.start_auth_session(tpm2.TPM2_SE_TRIAL)
data = ('X' * 64).encode()
@@ -35,7 +45,7 @@ class SmokeTest(unittest.TestCase):
pcrs = [16]
try:
- self.client.policy_pcr(handle, pcrs)
+ self.client.policy_pcr(handle, pcrs, bank_alg=bank_alg)
self.client.policy_password(handle)
policy_dig = self.client.get_policy_digest(handle)
@@ -47,7 +57,7 @@ class SmokeTest(unittest.TestCase):
handle = self.client.start_auth_session(tpm2.TPM2_SE_POLICY)
try:
- self.client.policy_pcr(handle, pcrs)
+ self.client.policy_pcr(handle, pcrs, bank_alg=bank_alg)
self.client.policy_password(handle)
result = self.client.unseal(self.root_key, blob, auth, handle)
@@ -72,6 +82,9 @@ class SmokeTest(unittest.TestCase):
self.assertEqual(rc, tpm2.TPM2_RC_AUTH_FAIL)
def test_unseal_with_wrong_policy(self):
+ bank_alg = self.determine_bank_alg(1 << 16 | 1 << 1)
+ self.assertIsNotNone(bank_alg)
+
handle = self.client.start_auth_session(tpm2.TPM2_SE_TRIAL)
data = ('X' * 64).encode()
@@ -79,7 +92,7 @@ class SmokeTest(unittest.TestCase):
pcrs = [16]
try:
- self.client.policy_pcr(handle, pcrs)
+ self.client.policy_pcr(handle, pcrs, bank_alg=bank_alg)
self.client.policy_password(handle)
policy_dig = self.client.get_policy_digest(handle)
@@ -91,13 +104,13 @@ class SmokeTest(unittest.TestCase):
# Extend first a PCR that is not part of the policy and try to unseal.
# This should succeed.
- ds = tpm2.get_digest_size(tpm2.TPM2_ALG_SHA1)
- self.client.extend_pcr(1, ('X' * ds).encode())
+ ds = tpm2.get_digest_size(bank_alg)
+ self.client.extend_pcr(1, ('X' * ds).encode(), bank_alg=bank_alg)
handle = self.client.start_auth_session(tpm2.TPM2_SE_POLICY)
try:
- self.client.policy_pcr(handle, pcrs)
+ self.client.policy_pcr(handle, pcrs, bank_alg=bank_alg)
self.client.policy_password(handle)
result = self.client.unseal(self.root_key, blob, auth, handle)
@@ -109,14 +122,14 @@ class SmokeTest(unittest.TestCase):
# Then, extend a PCR that is part of the policy and try to unseal.
# This should fail.
- self.client.extend_pcr(16, ('X' * ds).encode())
+ self.client.extend_pcr(16, ('X' * ds).encode(), bank_alg=bank_alg)
handle = self.client.start_auth_session(tpm2.TPM2_SE_POLICY)
rc = 0
try:
- self.client.policy_pcr(handle, pcrs)
+ self.client.policy_pcr(handle, pcrs, bank_alg=bank_alg)
self.client.policy_password(handle)
result = self.client.unseal(self.root_key, blob, auth, handle)
@@ -302,3 +315,19 @@ class AsyncTest(unittest.TestCase):
log.debug("Calling get_cap in a NON_BLOCKING mode")
async_client.get_cap(tpm2.TPM2_CAP_HANDLES, tpm2.HR_LOADED_SESSION)
async_client.close()
+
+ def test_flush_invalid_context(self):
+ log = logging.getLogger(__name__)
+ log.debug(sys._getframe().f_code.co_name)
+
+ async_client = tpm2.Client(tpm2.Client.FLAG_SPACE | tpm2.Client.FLAG_NONBLOCK)
+ log.debug("Calling flush_context passing in an invalid handle ")
+ handle = 0x80123456
+ rc = 0
+ try:
+ async_client.flush_context(handle)
+ except OSError as e:
+ rc = e.errno
+
+ self.assertEqual(rc, 22)
+ async_client.close()
diff --git a/tools/testing/selftests/vDSO/vdso_test_abi.c b/tools/testing/selftests/vDSO/vdso_test_abi.c
index 3d603f1394af..883ca85424bc 100644
--- a/tools/testing/selftests/vDSO/vdso_test_abi.c
+++ b/tools/testing/selftests/vDSO/vdso_test_abi.c
@@ -33,110 +33,114 @@ typedef long (*vdso_clock_gettime_t)(clockid_t clk_id, struct timespec *ts);
typedef long (*vdso_clock_getres_t)(clockid_t clk_id, struct timespec *ts);
typedef time_t (*vdso_time_t)(time_t *t);
-static int vdso_test_gettimeofday(void)
+#define VDSO_TEST_PASS_MSG() "\n%s(): PASS\n", __func__
+#define VDSO_TEST_FAIL_MSG(x) "\n%s(): %s FAIL\n", __func__, x
+#define VDSO_TEST_SKIP_MSG(x) "\n%s(): SKIP: Could not find %s\n", __func__, x
+
+static void vdso_test_gettimeofday(void)
{
/* Find gettimeofday. */
vdso_gettimeofday_t vdso_gettimeofday =
(vdso_gettimeofday_t)vdso_sym(version, name[0]);
if (!vdso_gettimeofday) {
- printf("Could not find %s\n", name[0]);
- return KSFT_SKIP;
+ ksft_test_result_skip(VDSO_TEST_SKIP_MSG(name[0]));
+ return;
}
struct timeval tv;
long ret = vdso_gettimeofday(&tv, 0);
if (ret == 0) {
- printf("The time is %lld.%06lld\n",
- (long long)tv.tv_sec, (long long)tv.tv_usec);
+ ksft_print_msg("The time is %lld.%06lld\n",
+ (long long)tv.tv_sec, (long long)tv.tv_usec);
+ ksft_test_result_pass(VDSO_TEST_PASS_MSG());
} else {
- printf("%s failed\n", name[0]);
- return KSFT_FAIL;
+ ksft_test_result_fail(VDSO_TEST_FAIL_MSG(name[0]));
}
-
- return KSFT_PASS;
}
-static int vdso_test_clock_gettime(clockid_t clk_id)
+static void vdso_test_clock_gettime(clockid_t clk_id)
{
/* Find clock_gettime. */
vdso_clock_gettime_t vdso_clock_gettime =
(vdso_clock_gettime_t)vdso_sym(version, name[1]);
if (!vdso_clock_gettime) {
- printf("Could not find %s\n", name[1]);
- return KSFT_SKIP;
+ ksft_test_result_skip(VDSO_TEST_SKIP_MSG(name[1]));
+ return;
}
struct timespec ts;
long ret = vdso_clock_gettime(clk_id, &ts);
if (ret == 0) {
- printf("The time is %lld.%06lld\n",
- (long long)ts.tv_sec, (long long)ts.tv_nsec);
+ ksft_print_msg("The time is %lld.%06lld\n",
+ (long long)ts.tv_sec, (long long)ts.tv_nsec);
+ ksft_test_result_pass(VDSO_TEST_PASS_MSG());
} else {
- printf("%s failed\n", name[1]);
- return KSFT_FAIL;
+ ksft_test_result_fail(VDSO_TEST_FAIL_MSG(name[1]));
}
-
- return KSFT_PASS;
}
-static int vdso_test_time(void)
+static void vdso_test_time(void)
{
/* Find time. */
vdso_time_t vdso_time =
(vdso_time_t)vdso_sym(version, name[2]);
if (!vdso_time) {
- printf("Could not find %s\n", name[2]);
- return KSFT_SKIP;
+ ksft_test_result_skip(VDSO_TEST_SKIP_MSG(name[2]));
+ return;
}
long ret = vdso_time(NULL);
if (ret > 0) {
- printf("The time in hours since January 1, 1970 is %lld\n",
+ ksft_print_msg("The time in hours since January 1, 1970 is %lld\n",
(long long)(ret / 3600));
+ ksft_test_result_pass(VDSO_TEST_PASS_MSG());
} else {
- printf("%s failed\n", name[2]);
- return KSFT_FAIL;
+ ksft_test_result_fail(VDSO_TEST_FAIL_MSG(name[2]));
}
-
- return KSFT_PASS;
}
-static int vdso_test_clock_getres(clockid_t clk_id)
+static void vdso_test_clock_getres(clockid_t clk_id)
{
+ int clock_getres_fail = 0;
+
/* Find clock_getres. */
vdso_clock_getres_t vdso_clock_getres =
(vdso_clock_getres_t)vdso_sym(version, name[3]);
if (!vdso_clock_getres) {
- printf("Could not find %s\n", name[3]);
- return KSFT_SKIP;
+ ksft_test_result_skip(VDSO_TEST_SKIP_MSG(name[3]));
+ return;
}
struct timespec ts, sys_ts;
long ret = vdso_clock_getres(clk_id, &ts);
if (ret == 0) {
- printf("The resolution is %lld %lld\n",
- (long long)ts.tv_sec, (long long)ts.tv_nsec);
+ ksft_print_msg("The vdso resolution is %lld %lld\n",
+ (long long)ts.tv_sec, (long long)ts.tv_nsec);
} else {
- printf("%s failed\n", name[3]);
- return KSFT_FAIL;
+ clock_getres_fail++;
}
ret = syscall(SYS_clock_getres, clk_id, &sys_ts);
- if ((sys_ts.tv_sec != ts.tv_sec) || (sys_ts.tv_nsec != ts.tv_nsec)) {
- printf("%s failed\n", name[3]);
- return KSFT_FAIL;
- }
+ ksft_print_msg("The syscall resolution is %lld %lld\n",
+ (long long)sys_ts.tv_sec, (long long)sys_ts.tv_nsec);
- return KSFT_PASS;
+ if ((sys_ts.tv_sec != ts.tv_sec) || (sys_ts.tv_nsec != ts.tv_nsec))
+ clock_getres_fail++;
+
+ if (clock_getres_fail > 0) {
+ ksft_test_result_fail(VDSO_TEST_FAIL_MSG(name[3]));
+ } else {
+ ksft_test_result_pass(VDSO_TEST_PASS_MSG());
+ }
}
const char *vdso_clock_name[12] = {
@@ -158,36 +162,23 @@ const char *vdso_clock_name[12] = {
* This function calls vdso_test_clock_gettime and vdso_test_clock_getres
* with different values for clock_id.
*/
-static inline int vdso_test_clock(clockid_t clock_id)
+static inline void vdso_test_clock(clockid_t clock_id)
{
- int ret0, ret1;
-
- ret0 = vdso_test_clock_gettime(clock_id);
- /* A skipped test is considered passed */
- if (ret0 == KSFT_SKIP)
- ret0 = KSFT_PASS;
-
- ret1 = vdso_test_clock_getres(clock_id);
- /* A skipped test is considered passed */
- if (ret1 == KSFT_SKIP)
- ret1 = KSFT_PASS;
+ ksft_print_msg("\nclock_id: %s\n", vdso_clock_name[clock_id]);
- ret0 += ret1;
+ vdso_test_clock_gettime(clock_id);
- printf("clock_id: %s", vdso_clock_name[clock_id]);
-
- if (ret0 > 0)
- printf(" [FAIL]\n");
- else
- printf(" [PASS]\n");
-
- return ret0;
+ vdso_test_clock_getres(clock_id);
}
+#define VDSO_TEST_PLAN 16
+
int main(int argc, char **argv)
{
unsigned long sysinfo_ehdr = getauxval(AT_SYSINFO_EHDR);
- int ret;
+
+ ksft_print_header();
+ ksft_set_plan(VDSO_TEST_PLAN);
if (!sysinfo_ehdr) {
printf("AT_SYSINFO_EHDR is not present!\n");
@@ -201,44 +192,42 @@ int main(int argc, char **argv)
vdso_init_from_sysinfo_ehdr(getauxval(AT_SYSINFO_EHDR));
- ret = vdso_test_gettimeofday();
+ vdso_test_gettimeofday();
#if _POSIX_TIMERS > 0
#ifdef CLOCK_REALTIME
- ret += vdso_test_clock(CLOCK_REALTIME);
+ vdso_test_clock(CLOCK_REALTIME);
#endif
#ifdef CLOCK_BOOTTIME
- ret += vdso_test_clock(CLOCK_BOOTTIME);
+ vdso_test_clock(CLOCK_BOOTTIME);
#endif
#ifdef CLOCK_TAI
- ret += vdso_test_clock(CLOCK_TAI);
+ vdso_test_clock(CLOCK_TAI);
#endif
#ifdef CLOCK_REALTIME_COARSE
- ret += vdso_test_clock(CLOCK_REALTIME_COARSE);
+ vdso_test_clock(CLOCK_REALTIME_COARSE);
#endif
#ifdef CLOCK_MONOTONIC
- ret += vdso_test_clock(CLOCK_MONOTONIC);
+ vdso_test_clock(CLOCK_MONOTONIC);
#endif
#ifdef CLOCK_MONOTONIC_RAW
- ret += vdso_test_clock(CLOCK_MONOTONIC_RAW);
+ vdso_test_clock(CLOCK_MONOTONIC_RAW);
#endif
#ifdef CLOCK_MONOTONIC_COARSE
- ret += vdso_test_clock(CLOCK_MONOTONIC_COARSE);
+ vdso_test_clock(CLOCK_MONOTONIC_COARSE);
#endif
#endif
- ret += vdso_test_time();
-
- if (ret > 0)
- return KSFT_FAIL;
+ vdso_test_time();
- return KSFT_PASS;
+ ksft_print_cnts();
+ return ksft_get_fail_cnt() == 0 ? KSFT_PASS : KSFT_FAIL;
}
diff --git a/tools/testing/selftests/vm/.gitignore b/tools/testing/selftests/vm/.gitignore
index 2e7e86e85282..3b5faec3c04f 100644
--- a/tools/testing/selftests/vm/.gitignore
+++ b/tools/testing/selftests/vm/.gitignore
@@ -2,6 +2,7 @@
hugepage-mmap
hugepage-mremap
hugepage-shm
+hugepage-vmemmap
khugepaged
map_hugetlb
map_populate
diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile
index 1607322a112c..81040f01711f 100644
--- a/tools/testing/selftests/vm/Makefile
+++ b/tools/testing/selftests/vm/Makefile
@@ -1,6 +1,8 @@
# SPDX-License-Identifier: GPL-2.0
# Makefile for vm selftests
+LOCAL_HDRS += $(selfdir)/vm/local_config.h $(top_srcdir)/mm/gup_test.h
+
include local_config.mk
uname_M := $(shell uname -m 2>/dev/null || echo not)
@@ -31,6 +33,7 @@ TEST_GEN_FILES += hmm-tests
TEST_GEN_FILES += hugepage-mmap
TEST_GEN_FILES += hugepage-mremap
TEST_GEN_FILES += hugepage-shm
+TEST_GEN_FILES += hugepage-vmemmap
TEST_GEN_FILES += khugepaged
TEST_GEN_FILES += madv_populate
TEST_GEN_FILES += map_fixed_noreplace
@@ -49,9 +52,9 @@ TEST_GEN_FILES += split_huge_page_test
TEST_GEN_FILES += ksm_tests
ifeq ($(MACHINE),x86_64)
-CAN_BUILD_I386 := $(shell ./../x86/check_cc.sh $(CC) ../x86/trivial_32bit_program.c -m32)
-CAN_BUILD_X86_64 := $(shell ./../x86/check_cc.sh $(CC) ../x86/trivial_64bit_program.c)
-CAN_BUILD_WITH_NOPIE := $(shell ./../x86/check_cc.sh $(CC) ../x86/trivial_program.c -no-pie)
+CAN_BUILD_I386 := $(shell ./../x86/check_cc.sh "$(CC)" ../x86/trivial_32bit_program.c -m32)
+CAN_BUILD_X86_64 := $(shell ./../x86/check_cc.sh "$(CC)" ../x86/trivial_64bit_program.c)
+CAN_BUILD_WITH_NOPIE := $(shell ./../x86/check_cc.sh "$(CC)" ../x86/trivial_program.c -no-pie)
TARGETS := protection_keys
BINARIES_32 := $(TARGETS:%=%_32)
@@ -140,10 +143,6 @@ endif
$(OUTPUT)/mlock-random-test $(OUTPUT)/memfd_secret: LDLIBS += -lcap
-$(OUTPUT)/gup_test: ../../../../mm/gup_test.h
-
-$(OUTPUT)/hmm-tests: local_config.h
-
# HMM_EXTRA_LIBS may get set in local_config.mk, or it may be left empty.
$(OUTPUT)/hmm-tests: LDLIBS += $(HMM_EXTRA_LIBS)
diff --git a/tools/testing/selftests/vm/charge_reserved_hugetlb.sh b/tools/testing/selftests/vm/charge_reserved_hugetlb.sh
index fe8fcfb334e0..a5cb4b09a46c 100644
--- a/tools/testing/selftests/vm/charge_reserved_hugetlb.sh
+++ b/tools/testing/selftests/vm/charge_reserved_hugetlb.sh
@@ -24,19 +24,23 @@ if [[ "$1" == "-cgroup-v2" ]]; then
reservation_usage_file=rsvd.current
fi
-cgroup_path=/dev/cgroup/memory
-if [[ ! -e $cgroup_path ]]; then
- mkdir -p $cgroup_path
- if [[ $cgroup2 ]]; then
+if [[ $cgroup2 ]]; then
+ cgroup_path=$(mount -t cgroup2 | head -1 | awk -e '{print $3}')
+ if [[ -z "$cgroup_path" ]]; then
+ cgroup_path=/dev/cgroup/memory
mount -t cgroup2 none $cgroup_path
- else
+ do_umount=1
+ fi
+ echo "+hugetlb" >$cgroup_path/cgroup.subtree_control
+else
+ cgroup_path=$(mount -t cgroup | grep ",hugetlb" | awk -e '{print $3}')
+ if [[ -z "$cgroup_path" ]]; then
+ cgroup_path=/dev/cgroup/memory
mount -t cgroup memory,hugetlb $cgroup_path
+ do_umount=1
fi
fi
-
-if [[ $cgroup2 ]]; then
- echo "+hugetlb" >/dev/cgroup/memory/cgroup.subtree_control
-fi
+export cgroup_path
function cleanup() {
if [[ $cgroup2 ]]; then
@@ -108,7 +112,7 @@ function setup_cgroup() {
function wait_for_hugetlb_memory_to_get_depleted() {
local cgroup="$1"
- local path="/dev/cgroup/memory/$cgroup/hugetlb.${MB}MB.$reservation_usage_file"
+ local path="$cgroup_path/$cgroup/hugetlb.${MB}MB.$reservation_usage_file"
# Wait for hugetlbfs memory to get depleted.
while [ $(cat $path) != 0 ]; do
echo Waiting for hugetlb memory to get depleted.
@@ -121,7 +125,7 @@ function wait_for_hugetlb_memory_to_get_reserved() {
local cgroup="$1"
local size="$2"
- local path="/dev/cgroup/memory/$cgroup/hugetlb.${MB}MB.$reservation_usage_file"
+ local path="$cgroup_path/$cgroup/hugetlb.${MB}MB.$reservation_usage_file"
# Wait for hugetlbfs memory to get written.
while [ $(cat $path) != $size ]; do
echo Waiting for hugetlb memory reservation to reach size $size.
@@ -134,7 +138,7 @@ function wait_for_hugetlb_memory_to_get_written() {
local cgroup="$1"
local size="$2"
- local path="/dev/cgroup/memory/$cgroup/hugetlb.${MB}MB.$fault_usage_file"
+ local path="$cgroup_path/$cgroup/hugetlb.${MB}MB.$fault_usage_file"
# Wait for hugetlbfs memory to get written.
while [ $(cat $path) != $size ]; do
echo Waiting for hugetlb memory to reach size $size.
@@ -574,5 +578,7 @@ for populate in "" "-o"; do
done # populate
done # method
-umount $cgroup_path
-rmdir $cgroup_path
+if [[ $do_umount ]]; then
+ umount $cgroup_path
+ rmdir $cgroup_path
+fi
diff --git a/tools/testing/selftests/vm/hmm-tests.c b/tools/testing/selftests/vm/hmm-tests.c
index 864f126ffd78..203323967b50 100644
--- a/tools/testing/selftests/vm/hmm-tests.c
+++ b/tools/testing/selftests/vm/hmm-tests.c
@@ -1251,6 +1251,48 @@ TEST_F(hmm, anon_teardown)
/*
* Test memory snapshot without faulting in pages accessed by the device.
*/
+TEST_F(hmm, mixedmap)
+{
+ struct hmm_buffer *buffer;
+ unsigned long npages;
+ unsigned long size;
+ unsigned char *m;
+ int ret;
+
+ npages = 1;
+ size = npages << self->page_shift;
+
+ buffer = malloc(sizeof(*buffer));
+ ASSERT_NE(buffer, NULL);
+
+ buffer->fd = -1;
+ buffer->size = size;
+ buffer->mirror = malloc(npages);
+ ASSERT_NE(buffer->mirror, NULL);
+
+
+ /* Reserve a range of addresses. */
+ buffer->ptr = mmap(NULL, size,
+ PROT_READ | PROT_WRITE,
+ MAP_PRIVATE,
+ self->fd, 0);
+ ASSERT_NE(buffer->ptr, MAP_FAILED);
+
+ /* Simulate a device snapshotting CPU pagetables. */
+ ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_SNAPSHOT, buffer, npages);
+ ASSERT_EQ(ret, 0);
+ ASSERT_EQ(buffer->cpages, npages);
+
+ /* Check what the device saw. */
+ m = buffer->mirror;
+ ASSERT_EQ(m[0], HMM_DMIRROR_PROT_READ);
+
+ hmm_buffer_free(buffer);
+}
+
+/*
+ * Test memory snapshot without faulting in pages accessed by the device.
+ */
TEST_F(hmm2, snapshot)
{
struct hmm_buffer *buffer;
diff --git a/tools/testing/selftests/vm/hugepage-mremap.c b/tools/testing/selftests/vm/hugepage-mremap.c
index 257df94697a5..1d689084a54b 100644
--- a/tools/testing/selftests/vm/hugepage-mremap.c
+++ b/tools/testing/selftests/vm/hugepage-mremap.c
@@ -3,8 +3,13 @@
* hugepage-mremap:
*
* Example of remapping huge page memory in a user application using the
- * mremap system call. Code assumes a hugetlbfs filesystem is mounted
- * at './huge'. The code will use 10MB worth of huge pages.
+ * mremap system call. The path to a file in a hugetlbfs filesystem must
+ * be passed as the last argument to this test. The amount of memory used
+ * by this test in MBs can optionally be passed as an argument. If no memory
+ * amount is passed, the default amount is 10MB.
+ *
+ * To make sure the test triggers pmd sharing and goes through the 'unshare'
+ * path in the mremap code use 1GB (1024) or more.
*/
#define _GNU_SOURCE
@@ -18,7 +23,8 @@
#include <linux/userfaultfd.h>
#include <sys/ioctl.h>
-#define LENGTH (1UL * 1024 * 1024 * 1024)
+#define DEFAULT_LENGTH_MB 10UL
+#define MB_TO_BYTES(x) (x * 1024 * 1024)
#define PROTECTION (PROT_READ | PROT_WRITE | PROT_EXEC)
#define FLAGS (MAP_SHARED | MAP_ANONYMOUS)
@@ -28,20 +34,20 @@ static void check_bytes(char *addr)
printf("First hex is %x\n", *((unsigned int *)addr));
}
-static void write_bytes(char *addr)
+static void write_bytes(char *addr, size_t len)
{
unsigned long i;
- for (i = 0; i < LENGTH; i++)
+ for (i = 0; i < len; i++)
*(addr + i) = (char)i;
}
-static int read_bytes(char *addr)
+static int read_bytes(char *addr, size_t len)
{
unsigned long i;
check_bytes(addr);
- for (i = 0; i < LENGTH; i++)
+ for (i = 0; i < len; i++)
if (*(addr + i) != (char)i) {
printf("Mismatch at %lu\n", i);
return 1;
@@ -99,11 +105,28 @@ static void register_region_with_uffd(char *addr, size_t len)
}
}
-int main(void)
+int main(int argc, char *argv[])
{
+ size_t length;
+
+ if (argc != 2 && argc != 3) {
+ printf("Usage: %s [length_in_MB] <hugetlb_file>\n", argv[0]);
+ exit(1);
+ }
+
+ /* Read memory length as the first arg if valid, otherwise fallback to
+ * the default length.
+ */
+ if (argc == 3)
+ length = argc > 2 ? (size_t)atoi(argv[1]) : 0UL;
+
+ length = length > 0 ? length : DEFAULT_LENGTH_MB;
+ length = MB_TO_BYTES(length);
+
int ret = 0;
- int fd = open("/huge/test", O_CREAT | O_RDWR, 0755);
+ /* last arg is the hugetlb file name */
+ int fd = open(argv[argc-1], O_CREAT | O_RDWR, 0755);
if (fd < 0) {
perror("Open failed");
@@ -112,7 +135,7 @@ int main(void)
/* mmap to a PUD aligned address to hopefully trigger pmd sharing. */
unsigned long suggested_addr = 0x7eaa40000000;
- void *haddr = mmap((void *)suggested_addr, LENGTH, PROTECTION,
+ void *haddr = mmap((void *)suggested_addr, length, PROTECTION,
MAP_HUGETLB | MAP_SHARED | MAP_POPULATE, fd, 0);
printf("Map haddr: Returned address is %p\n", haddr);
if (haddr == MAP_FAILED) {
@@ -122,7 +145,7 @@ int main(void)
/* mmap again to a dummy address to hopefully trigger pmd sharing. */
suggested_addr = 0x7daa40000000;
- void *daddr = mmap((void *)suggested_addr, LENGTH, PROTECTION,
+ void *daddr = mmap((void *)suggested_addr, length, PROTECTION,
MAP_HUGETLB | MAP_SHARED | MAP_POPULATE, fd, 0);
printf("Map daddr: Returned address is %p\n", daddr);
if (daddr == MAP_FAILED) {
@@ -132,16 +155,16 @@ int main(void)
suggested_addr = 0x7faa40000000;
void *vaddr =
- mmap((void *)suggested_addr, LENGTH, PROTECTION, FLAGS, -1, 0);
+ mmap((void *)suggested_addr, length, PROTECTION, FLAGS, -1, 0);
printf("Map vaddr: Returned address is %p\n", vaddr);
if (vaddr == MAP_FAILED) {
perror("mmap2");
exit(1);
}
- register_region_with_uffd(haddr, LENGTH);
+ register_region_with_uffd(haddr, length);
- void *addr = mremap(haddr, LENGTH, LENGTH,
+ void *addr = mremap(haddr, length, length,
MREMAP_MAYMOVE | MREMAP_FIXED, vaddr);
if (addr == MAP_FAILED) {
perror("mremap");
@@ -150,10 +173,13 @@ int main(void)
printf("Mremap: Returned address is %p\n", addr);
check_bytes(addr);
- write_bytes(addr);
- ret = read_bytes(addr);
+ write_bytes(addr, length);
+ ret = read_bytes(addr, length);
+
+ munmap(addr, length);
- munmap(addr, LENGTH);
+ close(fd);
+ unlink(argv[argc-1]);
return ret;
}
diff --git a/tools/testing/selftests/vm/hugepage-vmemmap.c b/tools/testing/selftests/vm/hugepage-vmemmap.c
new file mode 100644
index 000000000000..557bdbd4f87e
--- /dev/null
+++ b/tools/testing/selftests/vm/hugepage-vmemmap.c
@@ -0,0 +1,144 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * A test case of using hugepage memory in a user application using the
+ * mmap system call with MAP_HUGETLB flag. Before running this program
+ * make sure the administrator has allocated enough default sized huge
+ * pages to cover the 2 MB allocation.
+ */
+#include <stdlib.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <sys/mman.h>
+#include <fcntl.h>
+
+#define MAP_LENGTH (2UL * 1024 * 1024)
+
+#ifndef MAP_HUGETLB
+#define MAP_HUGETLB 0x40000 /* arch specific */
+#endif
+
+#define PAGE_SIZE 4096
+
+#define PAGE_COMPOUND_HEAD (1UL << 15)
+#define PAGE_COMPOUND_TAIL (1UL << 16)
+#define PAGE_HUGE (1UL << 17)
+
+#define HEAD_PAGE_FLAGS (PAGE_COMPOUND_HEAD | PAGE_HUGE)
+#define TAIL_PAGE_FLAGS (PAGE_COMPOUND_TAIL | PAGE_HUGE)
+
+#define PM_PFRAME_BITS 55
+#define PM_PFRAME_MASK ~((1UL << PM_PFRAME_BITS) - 1)
+
+/*
+ * For ia64 architecture, Linux kernel reserves Region number 4 for hugepages.
+ * That means the addresses starting with 0x800000... will need to be
+ * specified. Specifying a fixed address is not required on ppc64, i386
+ * or x86_64.
+ */
+#ifdef __ia64__
+#define MAP_ADDR (void *)(0x8000000000000000UL)
+#define MAP_FLAGS (MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB | MAP_FIXED)
+#else
+#define MAP_ADDR NULL
+#define MAP_FLAGS (MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB)
+#endif
+
+static void write_bytes(char *addr, size_t length)
+{
+ unsigned long i;
+
+ for (i = 0; i < length; i++)
+ *(addr + i) = (char)i;
+}
+
+static unsigned long virt_to_pfn(void *addr)
+{
+ int fd;
+ unsigned long pagemap;
+
+ fd = open("/proc/self/pagemap", O_RDONLY);
+ if (fd < 0)
+ return -1UL;
+
+ lseek(fd, (unsigned long)addr / PAGE_SIZE * sizeof(pagemap), SEEK_SET);
+ read(fd, &pagemap, sizeof(pagemap));
+ close(fd);
+
+ return pagemap & ~PM_PFRAME_MASK;
+}
+
+static int check_page_flags(unsigned long pfn)
+{
+ int fd, i;
+ unsigned long pageflags;
+
+ fd = open("/proc/kpageflags", O_RDONLY);
+ if (fd < 0)
+ return -1;
+
+ lseek(fd, pfn * sizeof(pageflags), SEEK_SET);
+
+ read(fd, &pageflags, sizeof(pageflags));
+ if ((pageflags & HEAD_PAGE_FLAGS) != HEAD_PAGE_FLAGS) {
+ close(fd);
+ printf("Head page flags (%lx) is invalid\n", pageflags);
+ return -1;
+ }
+
+ /*
+ * pages other than the first page must be tail and shouldn't be head;
+ * this also verifies kernel has correctly set the fake page_head to tail
+ * while hugetlb_free_vmemmap is enabled.
+ */
+ for (i = 1; i < MAP_LENGTH / PAGE_SIZE; i++) {
+ read(fd, &pageflags, sizeof(pageflags));
+ if ((pageflags & TAIL_PAGE_FLAGS) != TAIL_PAGE_FLAGS ||
+ (pageflags & HEAD_PAGE_FLAGS) == HEAD_PAGE_FLAGS) {
+ close(fd);
+ printf("Tail page flags (%lx) is invalid\n", pageflags);
+ return -1;
+ }
+ }
+
+ close(fd);
+
+ return 0;
+}
+
+int main(int argc, char **argv)
+{
+ void *addr;
+ unsigned long pfn;
+
+ addr = mmap(MAP_ADDR, MAP_LENGTH, PROT_READ | PROT_WRITE, MAP_FLAGS, -1, 0);
+ if (addr == MAP_FAILED) {
+ perror("mmap");
+ exit(1);
+ }
+
+ /* Trigger allocation of HugeTLB page. */
+ write_bytes(addr, MAP_LENGTH);
+
+ pfn = virt_to_pfn(addr);
+ if (pfn == -1UL) {
+ munmap(addr, MAP_LENGTH);
+ perror("virt_to_pfn");
+ exit(1);
+ }
+
+ printf("Returned address is %p whose pfn is %lx\n", addr, pfn);
+
+ if (check_page_flags(pfn) < 0) {
+ munmap(addr, MAP_LENGTH);
+ perror("check_page_flags");
+ exit(1);
+ }
+
+ /* munmap() length of MAP_HUGETLB memory must be hugepage aligned */
+ if (munmap(addr, MAP_LENGTH)) {
+ perror("munmap");
+ exit(1);
+ }
+
+ return 0;
+}
diff --git a/tools/testing/selftests/vm/hugetlb_reparenting_test.sh b/tools/testing/selftests/vm/hugetlb_reparenting_test.sh
index 4a9a3afe9fd4..bf2d2a684edf 100644
--- a/tools/testing/selftests/vm/hugetlb_reparenting_test.sh
+++ b/tools/testing/selftests/vm/hugetlb_reparenting_test.sh
@@ -18,19 +18,24 @@ if [[ "$1" == "-cgroup-v2" ]]; then
usage_file=current
fi
-CGROUP_ROOT='/dev/cgroup/memory'
-MNT='/mnt/huge/'
-if [[ ! -e $CGROUP_ROOT ]]; then
- mkdir -p $CGROUP_ROOT
- if [[ $cgroup2 ]]; then
+if [[ $cgroup2 ]]; then
+ CGROUP_ROOT=$(mount -t cgroup2 | head -1 | awk -e '{print $3}')
+ if [[ -z "$CGROUP_ROOT" ]]; then
+ CGROUP_ROOT=/dev/cgroup/memory
mount -t cgroup2 none $CGROUP_ROOT
- sleep 1
- echo "+hugetlb +memory" >$CGROUP_ROOT/cgroup.subtree_control
- else
+ do_umount=1
+ fi
+ echo "+hugetlb +memory" >$CGROUP_ROOT/cgroup.subtree_control
+else
+ CGROUP_ROOT=$(mount -t cgroup | grep ",hugetlb" | awk -e '{print $3}')
+ if [[ -z "$CGROUP_ROOT" ]]; then
+ CGROUP_ROOT=/dev/cgroup/memory
mount -t cgroup memory,hugetlb $CGROUP_ROOT
+ do_umount=1
fi
fi
+MNT='/mnt/huge/'
function get_machine_hugepage_size() {
hpz=$(grep -i hugepagesize /proc/meminfo)
diff --git a/tools/testing/selftests/vm/map_fixed_noreplace.c b/tools/testing/selftests/vm/map_fixed_noreplace.c
index d91bde511268..eed44322d1a6 100644
--- a/tools/testing/selftests/vm/map_fixed_noreplace.c
+++ b/tools/testing/selftests/vm/map_fixed_noreplace.c
@@ -17,9 +17,6 @@
#define MAP_FIXED_NOREPLACE 0x100000
#endif
-#define BASE_ADDRESS (256ul * 1024 * 1024)
-
-
static void dump_maps(void)
{
char cmd[32];
@@ -28,18 +25,46 @@ static void dump_maps(void)
system(cmd);
}
+static unsigned long find_base_addr(unsigned long size)
+{
+ void *addr;
+ unsigned long flags;
+
+ flags = MAP_PRIVATE | MAP_ANONYMOUS;
+ addr = mmap(NULL, size, PROT_NONE, flags, -1, 0);
+ if (addr == MAP_FAILED) {
+ printf("Error: couldn't map the space we need for the test\n");
+ return 0;
+ }
+
+ if (munmap(addr, size) != 0) {
+ printf("Error: couldn't map the space we need for the test\n");
+ return 0;
+ }
+ return (unsigned long)addr;
+}
+
int main(void)
{
+ unsigned long base_addr;
unsigned long flags, addr, size, page_size;
char *p;
page_size = sysconf(_SC_PAGE_SIZE);
+ //let's find a base addr that is free before we start the tests
+ size = 5 * page_size;
+ base_addr = find_base_addr(size);
+ if (!base_addr) {
+ printf("Error: couldn't map the space we need for the test\n");
+ return 1;
+ }
+
flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_FIXED_NOREPLACE;
// Check we can map all the areas we need below
errno = 0;
- addr = BASE_ADDRESS;
+ addr = base_addr;
size = 5 * page_size;
p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0);
@@ -60,7 +85,7 @@ int main(void)
printf("unmap() successful\n");
errno = 0;
- addr = BASE_ADDRESS + page_size;
+ addr = base_addr + page_size;
size = 3 * page_size;
p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0);
printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p);
@@ -80,7 +105,7 @@ int main(void)
* +4 | free | new
*/
errno = 0;
- addr = BASE_ADDRESS;
+ addr = base_addr;
size = 5 * page_size;
p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0);
printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p);
@@ -101,7 +126,7 @@ int main(void)
* +4 | free |
*/
errno = 0;
- addr = BASE_ADDRESS + (2 * page_size);
+ addr = base_addr + (2 * page_size);
size = page_size;
p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0);
printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p);
@@ -121,7 +146,7 @@ int main(void)
* +4 | free | new
*/
errno = 0;
- addr = BASE_ADDRESS + (3 * page_size);
+ addr = base_addr + (3 * page_size);
size = 2 * page_size;
p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0);
printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p);
@@ -141,7 +166,7 @@ int main(void)
* +4 | free |
*/
errno = 0;
- addr = BASE_ADDRESS;
+ addr = base_addr;
size = 2 * page_size;
p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0);
printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p);
@@ -161,7 +186,7 @@ int main(void)
* +4 | free |
*/
errno = 0;
- addr = BASE_ADDRESS;
+ addr = base_addr;
size = page_size;
p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0);
printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p);
@@ -181,7 +206,7 @@ int main(void)
* +4 | free | new
*/
errno = 0;
- addr = BASE_ADDRESS + (4 * page_size);
+ addr = base_addr + (4 * page_size);
size = page_size;
p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0);
printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p);
@@ -192,7 +217,7 @@ int main(void)
return 1;
}
- addr = BASE_ADDRESS;
+ addr = base_addr;
size = 5 * page_size;
if (munmap((void *)addr, size) != 0) {
dump_maps();
diff --git a/tools/testing/selftests/vm/run_vmtests.sh b/tools/testing/selftests/vm/run_vmtests.sh
index a24d30af3094..e10d50e0b8e8 100755
--- a/tools/testing/selftests/vm/run_vmtests.sh
+++ b/tools/testing/selftests/vm/run_vmtests.sh
@@ -111,7 +111,19 @@ fi
echo "-----------------------"
echo "running hugepage-mremap"
echo "-----------------------"
-./hugepage-mremap
+./hugepage-mremap $mnt/huge_mremap
+if [ $? -ne 0 ]; then
+ echo "[FAIL]"
+ exitcode=1
+else
+ echo "[PASS]"
+fi
+rm -f $mnt/huge_mremap
+
+echo "------------------------"
+echo "running hugepage-vmemmap"
+echo "------------------------"
+./hugepage-vmemmap
if [ $? -ne 0 ]; then
echo "[FAIL]"
exitcode=1
diff --git a/tools/testing/selftests/vm/transhuge-stress.c b/tools/testing/selftests/vm/transhuge-stress.c
index 5e4c036f6ad3..a03cb3fce1f6 100644
--- a/tools/testing/selftests/vm/transhuge-stress.c
+++ b/tools/testing/selftests/vm/transhuge-stress.c
@@ -26,15 +26,17 @@
#define PAGEMAP_PFN(ent) ((ent) & ((1ull << 55) - 1))
int pagemap_fd;
+int backing_fd = -1;
+int mmap_flags = MAP_ANONYMOUS | MAP_NORESERVE | MAP_PRIVATE;
+#define PROT_RW (PROT_READ | PROT_WRITE)
int64_t allocate_transhuge(void *ptr)
{
uint64_t ent[2];
/* drop pmd */
- if (mmap(ptr, HPAGE_SIZE, PROT_READ | PROT_WRITE,
- MAP_FIXED | MAP_ANONYMOUS |
- MAP_NORESERVE | MAP_PRIVATE, -1, 0) != ptr)
+ if (mmap(ptr, HPAGE_SIZE, PROT_RW, MAP_FIXED | mmap_flags,
+ backing_fd, 0) != ptr)
errx(2, "mmap transhuge");
if (madvise(ptr, HPAGE_SIZE, MADV_HUGEPAGE))
@@ -60,6 +62,8 @@ int main(int argc, char **argv)
size_t ram, len;
void *ptr, *p;
struct timespec a, b;
+ int i = 0;
+ char *name = NULL;
double s;
uint8_t *map;
size_t map_len;
@@ -69,13 +73,23 @@ int main(int argc, char **argv)
ram = SIZE_MAX / 4;
else
ram *= sysconf(_SC_PAGESIZE);
+ len = ram;
+
+ while (++i < argc) {
+ if (!strcmp(argv[i], "-h"))
+ errx(1, "usage: %s [size in MiB]", argv[0]);
+ else if (!strcmp(argv[i], "-f"))
+ name = argv[++i];
+ else
+ len = atoll(argv[i]) << 20;
+ }
- if (argc == 1)
- len = ram;
- else if (!strcmp(argv[1], "-h"))
- errx(1, "usage: %s [size in MiB]", argv[0]);
- else
- len = atoll(argv[1]) << 20;
+ if (name) {
+ backing_fd = open(name, O_RDWR);
+ if (backing_fd == -1)
+ errx(2, "open %s", name);
+ mmap_flags = MAP_SHARED;
+ }
warnx("allocate %zd transhuge pages, using %zd MiB virtual memory"
" and %zd MiB of ram", len >> HPAGE_SHIFT, len >> 20,
@@ -86,8 +100,7 @@ int main(int argc, char **argv)
err(2, "open pagemap");
len -= len % HPAGE_SIZE;
- ptr = mmap(NULL, len + HPAGE_SIZE, PROT_READ | PROT_WRITE,
- MAP_ANONYMOUS | MAP_NORESERVE | MAP_PRIVATE, -1, 0);
+ ptr = mmap(NULL, len + HPAGE_SIZE, PROT_RW, mmap_flags, backing_fd, 0);
if (ptr == MAP_FAILED)
err(2, "initial mmap");
ptr += HPAGE_SIZE - (uintptr_t)ptr % HPAGE_SIZE;
diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c
index 9354a5e0321c..29cc6f247a9e 100644
--- a/tools/testing/selftests/vm/userfaultfd.c
+++ b/tools/testing/selftests/vm/userfaultfd.c
@@ -46,6 +46,7 @@
#include <signal.h>
#include <poll.h>
#include <string.h>
+#include <linux/mman.h>
#include <sys/mman.h>
#include <sys/syscall.h>
#include <sys/ioctl.h>
@@ -87,7 +88,7 @@ static bool test_uffdio_minor = false;
static bool map_shared;
static int shm_fd;
-static int huge_fd = -1; /* only used for hugetlb_shared test */
+static int huge_fd;
static char *huge_fd_off0;
static unsigned long long *count_verify;
static int uffd = -1;
@@ -223,9 +224,6 @@ static void noop_alias_mapping(__u64 *start, size_t len, unsigned long offset)
static void hugetlb_release_pages(char *rel_area)
{
- if (huge_fd == -1)
- return;
-
if (fallocate(huge_fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
rel_area == huge_fd_off0 ? 0 : nr_pages * page_size,
nr_pages * page_size))
@@ -238,17 +236,17 @@ static void hugetlb_allocate_area(void **alloc_area)
char **alloc_area_alias;
*alloc_area = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE,
- map_shared ? MAP_SHARED :
- MAP_PRIVATE | MAP_HUGETLB |
+ (map_shared ? MAP_SHARED : MAP_PRIVATE) |
+ MAP_HUGETLB |
(*alloc_area == area_src ? 0 : MAP_NORESERVE),
- huge_fd,
- *alloc_area == area_src ? 0 : nr_pages * page_size);
+ huge_fd, *alloc_area == area_src ? 0 :
+ nr_pages * page_size);
if (*alloc_area == MAP_FAILED)
err("mmap of hugetlbfs file failed");
if (map_shared) {
area_alias = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE,
- MAP_SHARED,
+ MAP_SHARED | MAP_HUGETLB,
huge_fd, *alloc_area == area_src ? 0 :
nr_pages * page_size);
if (area_alias == MAP_FAILED)
@@ -542,7 +540,7 @@ static void continue_range(int ufd, __u64 start, __u64 len)
static void *locking_thread(void *arg)
{
unsigned long cpu = (unsigned long) arg;
- unsigned long page_nr = *(&(page_nr)); /* uninitialized warning */
+ unsigned long page_nr;
unsigned long long count;
if (!(bounces & BOUNCE_RANDOM)) {
@@ -648,7 +646,7 @@ static int uffd_read_msg(int ufd, struct uffd_msg *msg)
if (ret != sizeof(*msg)) {
if (ret < 0) {
- if (errno == EAGAIN)
+ if (errno == EAGAIN || errno == EINTR)
return 1;
err("blocking read error");
} else {
@@ -724,8 +722,11 @@ static void *uffd_poll_thread(void *arg)
for (;;) {
ret = poll(pollfd, 2, -1);
- if (ret <= 0)
+ if (ret <= 0) {
+ if (errno == EINTR || errno == EAGAIN)
+ continue;
err("poll error: %d", ret);
+ }
if (pollfd[1].revents & POLLIN) {
if (read(pollfd[1].fd, &tmp_chr, 1) != 1)
err("read pipefd error");
diff --git a/tools/testing/selftests/vm/write_hugetlb_memory.sh b/tools/testing/selftests/vm/write_hugetlb_memory.sh
index d3d0d108924d..70a02301f4c2 100644
--- a/tools/testing/selftests/vm/write_hugetlb_memory.sh
+++ b/tools/testing/selftests/vm/write_hugetlb_memory.sh
@@ -14,7 +14,7 @@ want_sleep=$8
reserve=$9
echo "Putting task in cgroup '$cgroup'"
-echo $$ > /dev/cgroup/memory/"$cgroup"/cgroup.procs
+echo $$ > ${cgroup_path:-/dev/cgroup/memory}/"$cgroup"/cgroup.procs
echo "Method is $method"
diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile
index 8a1f62ab3c8e..53df7d3893d3 100644
--- a/tools/testing/selftests/x86/Makefile
+++ b/tools/testing/selftests/x86/Makefile
@@ -6,9 +6,9 @@ include ../lib.mk
.PHONY: all all_32 all_64 warn_32bit_failure clean
UNAME_M := $(shell uname -m)
-CAN_BUILD_I386 := $(shell ./check_cc.sh $(CC) trivial_32bit_program.c -m32)
-CAN_BUILD_X86_64 := $(shell ./check_cc.sh $(CC) trivial_64bit_program.c)
-CAN_BUILD_WITH_NOPIE := $(shell ./check_cc.sh $(CC) trivial_program.c -no-pie)
+CAN_BUILD_I386 := $(shell ./check_cc.sh "$(CC)" trivial_32bit_program.c -m32)
+CAN_BUILD_X86_64 := $(shell ./check_cc.sh "$(CC)" trivial_64bit_program.c)
+CAN_BUILD_WITH_NOPIE := $(shell ./check_cc.sh "$(CC)" trivial_program.c -no-pie)
TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt test_mremap_vdso \
check_initial_reg_state sigreturn iopl ioperm \
diff --git a/tools/testing/selftests/x86/check_cc.sh b/tools/testing/selftests/x86/check_cc.sh
index 3e2089c8cf54..8c669c0d662e 100755
--- a/tools/testing/selftests/x86/check_cc.sh
+++ b/tools/testing/selftests/x86/check_cc.sh
@@ -7,7 +7,7 @@ CC="$1"
TESTPROG="$2"
shift 2
-if "$CC" -o /dev/null "$TESTPROG" -O0 "$@" 2>/dev/null; then
+if [ -n "$CC" ] && $CC -o /dev/null "$TESTPROG" -O0 "$@" 2>/dev/null; then
echo 1
else
echo 0
diff --git a/tools/testing/selftests/zram/zram.sh b/tools/testing/selftests/zram/zram.sh
index 232e958ec454..b0b91d9b0dc2 100755
--- a/tools/testing/selftests/zram/zram.sh
+++ b/tools/testing/selftests/zram/zram.sh
@@ -2,9 +2,6 @@
# SPDX-License-Identifier: GPL-2.0
TCID="zram.sh"
-# Kselftest framework requirement - SKIP code is 4.
-ksft_skip=4
-
. ./zram_lib.sh
run_zram () {
@@ -18,14 +15,4 @@ echo ""
check_prereqs
-# check zram module exists
-MODULE_PATH=/lib/modules/`uname -r`/kernel/drivers/block/zram/zram.ko
-if [ -f $MODULE_PATH ]; then
- run_zram
-elif [ -b /dev/zram0 ]; then
- run_zram
-else
- echo "$TCID : No zram.ko module or /dev/zram0 device file not found"
- echo "$TCID : CONFIG_ZRAM is not set"
- exit $ksft_skip
-fi
+run_zram
diff --git a/tools/testing/selftests/zram/zram01.sh b/tools/testing/selftests/zram/zram01.sh
index 114863d9fb87..8f4affe34f3e 100755
--- a/tools/testing/selftests/zram/zram01.sh
+++ b/tools/testing/selftests/zram/zram01.sh
@@ -33,9 +33,7 @@ zram_algs="lzo"
zram_fill_fs()
{
- local mem_free0=$(free -m | awk 'NR==2 {print $4}')
-
- for i in $(seq 0 $(($dev_num - 1))); do
+ for i in $(seq $dev_start $dev_end); do
echo "fill zram$i..."
local b=0
while [ true ]; do
@@ -45,29 +43,17 @@ zram_fill_fs()
b=$(($b + 1))
done
echo "zram$i can be filled with '$b' KB"
- done
- local mem_free1=$(free -m | awk 'NR==2 {print $4}')
- local used_mem=$(($mem_free0 - $mem_free1))
+ local mem_used_total=`awk '{print $3}' "/sys/block/zram$i/mm_stat"`
+ local v=$((100 * 1024 * $b / $mem_used_total))
+ if [ "$v" -lt 100 ]; then
+ echo "FAIL compression ratio: 0.$v:1"
+ ERR_CODE=-1
+ return
+ fi
- local total_size=0
- for sm in $zram_sizes; do
- local s=$(echo $sm | sed 's/M//')
- total_size=$(($total_size + $s))
+ echo "zram compression ratio: $(echo "scale=2; $v / 100 " | bc):1: OK"
done
-
- echo "zram used ${used_mem}M, zram disk sizes ${total_size}M"
-
- local v=$((100 * $total_size / $used_mem))
-
- if [ "$v" -lt 100 ]; then
- echo "FAIL compression ratio: 0.$v:1"
- ERR_CODE=-1
- zram_cleanup
- return
- fi
-
- echo "zram compression ratio: $(echo "scale=2; $v / 100 " | bc):1: OK"
}
check_prereqs
@@ -81,7 +67,6 @@ zram_mount
zram_fill_fs
zram_cleanup
-zram_unload
if [ $ERR_CODE -ne 0 ]; then
echo "$TCID : [FAIL]"
diff --git a/tools/testing/selftests/zram/zram02.sh b/tools/testing/selftests/zram/zram02.sh
index e83b404807c0..2418b0c4ed13 100755
--- a/tools/testing/selftests/zram/zram02.sh
+++ b/tools/testing/selftests/zram/zram02.sh
@@ -36,7 +36,6 @@ zram_set_memlimit
zram_makeswap
zram_swapoff
zram_cleanup
-zram_unload
if [ $ERR_CODE -ne 0 ]; then
echo "$TCID : [FAIL]"
diff --git a/tools/testing/selftests/zram/zram_lib.sh b/tools/testing/selftests/zram/zram_lib.sh
index 6f872f266fd1..21ec1966de76 100755
--- a/tools/testing/selftests/zram/zram_lib.sh
+++ b/tools/testing/selftests/zram/zram_lib.sh
@@ -5,12 +5,17 @@
# Author: Alexey Kodanev <[email protected]>
# Modified: Naresh Kamboju <[email protected]>
-MODULE=0
dev_makeswap=-1
dev_mounted=-1
-
+dev_start=0
+dev_end=-1
+module_load=-1
+sys_control=-1
# Kselftest framework requirement - SKIP code is 4.
ksft_skip=4
+kernel_version=`uname -r | cut -d'.' -f1,2`
+kernel_major=${kernel_version%.*}
+kernel_minor=${kernel_version#*.}
trap INT
@@ -25,68 +30,104 @@ check_prereqs()
fi
}
+kernel_gte()
+{
+ major=${1%.*}
+ minor=${1#*.}
+
+ if [ $kernel_major -gt $major ]; then
+ return 0
+ elif [[ $kernel_major -eq $major && $kernel_minor -ge $minor ]]; then
+ return 0
+ fi
+
+ return 1
+}
+
zram_cleanup()
{
echo "zram cleanup"
local i=
- for i in $(seq 0 $dev_makeswap); do
+ for i in $(seq $dev_start $dev_makeswap); do
swapoff /dev/zram$i
done
- for i in $(seq 0 $dev_mounted); do
+ for i in $(seq $dev_start $dev_mounted); do
umount /dev/zram$i
done
- for i in $(seq 0 $(($dev_num - 1))); do
+ for i in $(seq $dev_start $dev_end); do
echo 1 > /sys/block/zram${i}/reset
rm -rf zram$i
done
-}
+ if [ $sys_control -eq 1 ]; then
+ for i in $(seq $dev_start $dev_end); do
+ echo $i > /sys/class/zram-control/hot_remove
+ done
+ fi
-zram_unload()
-{
- if [ $MODULE -ne 0 ] ; then
- echo "zram rmmod zram"
+ if [ $module_load -eq 1 ]; then
rmmod zram > /dev/null 2>&1
fi
}
zram_load()
{
- # check zram module exists
- MODULE_PATH=/lib/modules/`uname -r`/kernel/drivers/block/zram/zram.ko
- if [ -f $MODULE_PATH ]; then
- MODULE=1
- echo "create '$dev_num' zram device(s)"
- modprobe zram num_devices=$dev_num
- if [ $? -ne 0 ]; then
- echo "failed to insert zram module"
- exit 1
- fi
-
- dev_num_created=$(ls /dev/zram* | wc -w)
+ echo "create '$dev_num' zram device(s)"
+
+ # zram module loaded, new kernel
+ if [ -d "/sys/class/zram-control" ]; then
+ echo "zram modules already loaded, kernel supports" \
+ "zram-control interface"
+ dev_start=$(ls /dev/zram* | wc -w)
+ dev_end=$(($dev_start + $dev_num - 1))
+ sys_control=1
+
+ for i in $(seq $dev_start $dev_end); do
+ cat /sys/class/zram-control/hot_add > /dev/null
+ done
+
+ echo "all zram devices (/dev/zram$dev_start~$dev_end" \
+ "successfully created"
+ return 0
+ fi
- if [ "$dev_num_created" -ne "$dev_num" ]; then
- echo "unexpected num of devices: $dev_num_created"
- ERR_CODE=-1
+ # detect old kernel or built-in
+ modprobe zram num_devices=$dev_num
+ if [ ! -d "/sys/class/zram-control" ]; then
+ if grep -q '^zram' /proc/modules; then
+ rmmod zram > /dev/null 2>&1
+ if [ $? -ne 0 ]; then
+ echo "zram module is being used on old kernel" \
+ "without zram-control interface"
+ exit $ksft_skip
+ fi
else
- echo "zram load module successful"
+ echo "test needs CONFIG_ZRAM=m on old kernel without" \
+ "zram-control interface"
+ exit $ksft_skip
fi
- elif [ -b /dev/zram0 ]; then
- echo "/dev/zram0 device file found: OK"
- else
- echo "ERROR: No zram.ko module or no /dev/zram0 device found"
- echo "$TCID : CONFIG_ZRAM is not set"
- exit 1
+ modprobe zram num_devices=$dev_num
fi
+
+ module_load=1
+ dev_end=$(($dev_num - 1))
+ echo "all zram devices (/dev/zram0~$dev_end) successfully created"
}
zram_max_streams()
{
echo "set max_comp_streams to zram device(s)"
- local i=0
+ kernel_gte 4.7
+ if [ $? -eq 0 ]; then
+ echo "The device attribute max_comp_streams was"\
+ "deprecated in 4.7"
+ return 0
+ fi
+
+ local i=$dev_start
for max_s in $zram_max_streams; do
local sys_path="/sys/block/zram${i}/max_comp_streams"
echo $max_s > $sys_path || \
@@ -98,7 +139,7 @@ zram_max_streams()
echo "FAIL can't set max_streams '$max_s', get $max_stream"
i=$(($i + 1))
- echo "$sys_path = '$max_streams' ($i/$dev_num)"
+ echo "$sys_path = '$max_streams'"
done
echo "zram max streams: OK"
@@ -108,15 +149,16 @@ zram_compress_alg()
{
echo "test that we can set compression algorithm"
- local algs=$(cat /sys/block/zram0/comp_algorithm)
+ local i=$dev_start
+ local algs=$(cat /sys/block/zram${i}/comp_algorithm)
echo "supported algs: $algs"
- local i=0
+
for alg in $zram_algs; do
local sys_path="/sys/block/zram${i}/comp_algorithm"
echo "$alg" > $sys_path || \
echo "FAIL can't set '$alg' to $sys_path"
i=$(($i + 1))
- echo "$sys_path = '$alg' ($i/$dev_num)"
+ echo "$sys_path = '$alg'"
done
echo "zram set compression algorithm: OK"
@@ -125,14 +167,14 @@ zram_compress_alg()
zram_set_disksizes()
{
echo "set disk size to zram device(s)"
- local i=0
+ local i=$dev_start
for ds in $zram_sizes; do
local sys_path="/sys/block/zram${i}/disksize"
echo "$ds" > $sys_path || \
echo "FAIL can't set '$ds' to $sys_path"
i=$(($i + 1))
- echo "$sys_path = '$ds' ($i/$dev_num)"
+ echo "$sys_path = '$ds'"
done
echo "zram set disksizes: OK"
@@ -142,14 +184,14 @@ zram_set_memlimit()
{
echo "set memory limit to zram device(s)"
- local i=0
+ local i=$dev_start
for ds in $zram_mem_limits; do
local sys_path="/sys/block/zram${i}/mem_limit"
echo "$ds" > $sys_path || \
echo "FAIL can't set '$ds' to $sys_path"
i=$(($i + 1))
- echo "$sys_path = '$ds' ($i/$dev_num)"
+ echo "$sys_path = '$ds'"
done
echo "zram set memory limit: OK"
@@ -158,8 +200,8 @@ zram_set_memlimit()
zram_makeswap()
{
echo "make swap with zram device(s)"
- local i=0
- for i in $(seq 0 $(($dev_num - 1))); do
+ local i=$dev_start
+ for i in $(seq $dev_start $dev_end); do
mkswap /dev/zram$i > err.log 2>&1
if [ $? -ne 0 ]; then
cat err.log
@@ -182,7 +224,7 @@ zram_makeswap()
zram_swapoff()
{
local i=
- for i in $(seq 0 $dev_makeswap); do
+ for i in $(seq $dev_start $dev_end); do
swapoff /dev/zram$i > err.log 2>&1
if [ $? -ne 0 ]; then
cat err.log
@@ -196,7 +238,7 @@ zram_swapoff()
zram_makefs()
{
- local i=0
+ local i=$dev_start
for fs in $zram_filesystems; do
# if requested fs not supported default it to ext2
which mkfs.$fs > /dev/null 2>&1 || fs=ext2
@@ -215,7 +257,7 @@ zram_makefs()
zram_mount()
{
local i=0
- for i in $(seq 0 $(($dev_num - 1))); do
+ for i in $(seq $dev_start $dev_end); do
echo "mount /dev/zram$i"
mkdir zram$i
mount /dev/zram$i zram$i > /dev/null || \
diff --git a/tools/tracing/Makefile b/tools/tracing/Makefile
index 87e0ec48e2e7..95e485f12d97 100644
--- a/tools/tracing/Makefile
+++ b/tools/tracing/Makefile
@@ -1,11 +1,11 @@
# SPDX-License-Identifier: GPL-2.0
include ../scripts/Makefile.include
-all: latency
+all: latency rtla
-clean: latency_clean
+clean: latency_clean rtla_clean
-install: latency_install
+install: latency_install rtla_install
latency:
$(call descend,latency)
@@ -16,4 +16,14 @@ latency_install:
latency_clean:
$(call descend,latency,clean)
-.PHONY: all install clean latency latency_install latency_clean
+rtla:
+ $(call descend,rtla)
+
+rtla_install:
+ $(call descend,rtla,install)
+
+rtla_clean:
+ $(call descend,rtla,clean)
+
+.PHONY: all install clean latency latency_install latency_clean \
+ rtla rtla_install rtla_clean
diff --git a/tools/tracing/rtla/Makefile b/tools/tracing/rtla/Makefile
new file mode 100644
index 000000000000..5a1eda617992
--- /dev/null
+++ b/tools/tracing/rtla/Makefile
@@ -0,0 +1,104 @@
+NAME := rtla
+# Follow the kernel version
+VERSION := $(shell cat VERSION 2> /dev/null || make -sC ../../.. kernelversion)
+
+# From libtracefs:
+# Makefiles suck: This macro sets a default value of $(2) for the
+# variable named by $(1), unless the variable has been set by
+# environment or command line. This is necessary for CC and AR
+# because make sets default values, so the simpler ?= approach
+# won't work as expected.
+define allow-override
+ $(if $(or $(findstring environment,$(origin $(1))),\
+ $(findstring command line,$(origin $(1)))),,\
+ $(eval $(1) = $(2)))
+endef
+
+# Allow setting CC and AR, or setting CROSS_COMPILE as a prefix.
+$(call allow-override,CC,$(CROSS_COMPILE)gcc)
+$(call allow-override,AR,$(CROSS_COMPILE)ar)
+$(call allow-override,STRIP,$(CROSS_COMPILE)strip)
+$(call allow-override,PKG_CONFIG,pkg-config)
+$(call allow-override,LD_SO_CONF_PATH,/etc/ld.so.conf.d/)
+$(call allow-override,LDCONFIG,ldconfig)
+
+INSTALL = install
+FOPTS := -flto=auto -ffat-lto-objects -fexceptions -fstack-protector-strong \
+ -fasynchronous-unwind-tables -fstack-clash-protection
+WOPTS := -Wall -Werror=format-security -Wp,-D_FORTIFY_SOURCE=2 -Wp,-D_GLIBCXX_ASSERTIONS -Wno-maybe-uninitialized
+
+TRACEFS_HEADERS := $$($(PKG_CONFIG) --cflags libtracefs)
+
+CFLAGS := -O -g -DVERSION=\"$(VERSION)\" $(FOPTS) $(MOPTS) $(WOPTS) $(TRACEFS_HEADERS)
+LDFLAGS := -ggdb
+LIBS := $$($(PKG_CONFIG) --libs libtracefs) -lprocps
+
+SRC := $(wildcard src/*.c)
+HDR := $(wildcard src/*.h)
+OBJ := $(SRC:.c=.o)
+DIRS := src
+FILES := Makefile README.txt
+CEXT := bz2
+TARBALL := $(NAME)-$(VERSION).tar.$(CEXT)
+TAROPTS := -cvjf $(TARBALL)
+BINDIR := /usr/bin
+DATADIR := /usr/share
+DOCDIR := $(DATADIR)/doc
+MANDIR := $(DATADIR)/man
+LICDIR := $(DATADIR)/licenses
+SRCTREE := $(if $(BUILD_SRC),$(BUILD_SRC),$(CURDIR))
+
+# If running from the tarball, man pages are stored in the Documentation
+# dir. If running from the kernel source, man pages are stored in
+# Documentation/tools/rtla/.
+ifneq ($(wildcard Documentation/.*),)
+DOCSRC = Documentation/
+else
+DOCSRC = $(SRCTREE)/../../../Documentation/tools/rtla/
+endif
+
+.PHONY: all
+all: rtla
+
+rtla: $(OBJ)
+ $(CC) -o rtla $(LDFLAGS) $(OBJ) $(LIBS)
+
+static: $(OBJ)
+ $(CC) -o rtla-static $(LDFLAGS) --static $(OBJ) $(LIBS) -lpthread -ldl
+
+.PHONY: install
+install: doc_install
+ $(INSTALL) -d -m 755 $(DESTDIR)$(BINDIR)
+ $(INSTALL) rtla -m 755 $(DESTDIR)$(BINDIR)
+ $(STRIP) $(DESTDIR)$(BINDIR)/rtla
+ @test ! -f $(DESTDIR)$(BINDIR)/osnoise || rm $(DESTDIR)$(BINDIR)/osnoise
+ ln -s $(DESTDIR)$(BINDIR)/rtla $(DESTDIR)$(BINDIR)/osnoise
+ @test ! -f $(DESTDIR)$(BINDIR)/timerlat || rm $(DESTDIR)$(BINDIR)/timerlat
+ ln -s $(DESTDIR)$(BINDIR)/rtla $(DESTDIR)$(BINDIR)/timerlat
+
+.PHONY: clean tarball
+clean: doc_clean
+ @test ! -f rtla || rm rtla
+ @test ! -f rtla-static || rm rtla-static
+ @test ! -f src/rtla.o || rm src/rtla.o
+ @test ! -f $(TARBALL) || rm -f $(TARBALL)
+ @rm -rf *~ $(OBJ) *.tar.$(CEXT)
+
+tarball: clean
+ rm -rf $(NAME)-$(VERSION) && mkdir $(NAME)-$(VERSION)
+ echo $(VERSION) > $(NAME)-$(VERSION)/VERSION
+ cp -r $(DIRS) $(FILES) $(NAME)-$(VERSION)
+ mkdir $(NAME)-$(VERSION)/Documentation/
+ cp -rp $(SRCTREE)/../../../Documentation/tools/rtla/* $(NAME)-$(VERSION)/Documentation/
+ tar $(TAROPTS) --exclude='*~' $(NAME)-$(VERSION)
+ rm -rf $(NAME)-$(VERSION)
+
+.PHONY: doc doc_clean doc_install
+doc:
+ $(MAKE) -C $(DOCSRC)
+
+doc_clean:
+ $(MAKE) -C $(DOCSRC) clean
+
+doc_install:
+ $(MAKE) -C $(DOCSRC) install
diff --git a/tools/tracing/rtla/README.txt b/tools/tracing/rtla/README.txt
new file mode 100644
index 000000000000..6c88446f7e74
--- /dev/null
+++ b/tools/tracing/rtla/README.txt
@@ -0,0 +1,36 @@
+RTLA: Real-Time Linux Analysis tools
+
+The rtla is a meta-tool that includes a set of commands that
+aims to analyze the real-time properties of Linux. But, instead of
+testing Linux as a black box, rtla leverages kernel tracing
+capabilities to provide precise information about the properties
+and root causes of unexpected results.
+
+Installing RTLA
+
+RTLA depends on some libraries and tools. More precisely, it depends on the
+following libraries:
+
+ - libtracefs
+ - libtraceevent
+ - procps
+
+It also depends on python3-docutils to compile man pages.
+
+For development, we suggest the following steps for compiling rtla:
+
+ $ git clone git://git.kernel.org/pub/scm/libs/libtrace/libtraceevent.git
+ $ cd libtraceevent/
+ $ make
+ $ sudo make install
+ $ cd ..
+ $ git clone git://git.kernel.org/pub/scm/libs/libtrace/libtracefs.git
+ $ cd libtracefs/
+ $ make
+ $ sudo make install
+ $ cd ..
+ $ cd $rtla_src
+ $ make
+ $ sudo make install
+
+For further information, please refer to the rtla man page.
diff --git a/tools/tracing/rtla/src/osnoise.c b/tools/tracing/rtla/src/osnoise.c
new file mode 100644
index 000000000000..e60f1862bad0
--- /dev/null
+++ b/tools/tracing/rtla/src/osnoise.c
@@ -0,0 +1,878 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2021 Red Hat Inc, Daniel Bristot de Oliveira <[email protected]>
+ */
+
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <pthread.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <stdio.h>
+
+#include "osnoise.h"
+#include "utils.h"
+
+/*
+ * osnoise_get_cpus - return the original "osnoise/cpus" content
+ *
+ * It also saves the value to be restored.
+ */
+char *osnoise_get_cpus(struct osnoise_context *context)
+{
+ if (context->curr_cpus)
+ return context->curr_cpus;
+
+ if (context->orig_cpus)
+ return context->orig_cpus;
+
+ context->orig_cpus = tracefs_instance_file_read(NULL, "osnoise/cpus", NULL);
+
+ /*
+ * The error value (NULL) is the same for tracefs_instance_file_read()
+ * and this functions, so:
+ */
+ return context->orig_cpus;
+}
+
+/*
+ * osnoise_set_cpus - configure osnoise to run on *cpus
+ *
+ * "osnoise/cpus" file is used to set the cpus in which osnoise/timerlat
+ * will run. This function opens this file, saves the current value,
+ * and set the cpus passed as argument.
+ */
+int osnoise_set_cpus(struct osnoise_context *context, char *cpus)
+{
+ char *orig_cpus = osnoise_get_cpus(context);
+ char buffer[1024];
+ int retval;
+
+ if (!orig_cpus)
+ return -1;
+
+ context->curr_cpus = strdup(cpus);
+ if (!context->curr_cpus)
+ return -1;
+
+ snprintf(buffer, 1024, "%s\n", cpus);
+
+ debug_msg("setting cpus to %s from %s", cpus, context->orig_cpus);
+
+ retval = tracefs_instance_file_write(NULL, "osnoise/cpus", buffer);
+ if (retval < 0) {
+ free(context->curr_cpus);
+ context->curr_cpus = NULL;
+ return -1;
+ }
+
+ return 0;
+}
+
+/*
+ * osnoise_restore_cpus - restore the original "osnoise/cpus"
+ *
+ * osnoise_set_cpus() saves the original data for the "osnoise/cpus"
+ * file. This function restore the original config it was previously
+ * modified.
+ */
+void osnoise_restore_cpus(struct osnoise_context *context)
+{
+ int retval;
+
+ if (!context->orig_cpus)
+ return;
+
+ if (!context->curr_cpus)
+ return;
+
+ /* nothing to do? */
+ if (!strcmp(context->orig_cpus, context->curr_cpus))
+ goto out_done;
+
+ debug_msg("restoring cpus to %s", context->orig_cpus);
+
+ retval = tracefs_instance_file_write(NULL, "osnoise/cpus", context->orig_cpus);
+ if (retval < 0)
+ err_msg("could not restore original osnoise cpus\n");
+
+out_done:
+ free(context->curr_cpus);
+ context->curr_cpus = NULL;
+}
+
+/*
+ * osnoise_put_cpus - restore cpus config and cleanup data
+ */
+void osnoise_put_cpus(struct osnoise_context *context)
+{
+ osnoise_restore_cpus(context);
+
+ if (!context->orig_cpus)
+ return;
+
+ free(context->orig_cpus);
+ context->orig_cpus = NULL;
+}
+
+/*
+ * osnoise_read_ll_config - read a long long value from a config
+ *
+ * returns -1 on error.
+ */
+static long long osnoise_read_ll_config(char *rel_path)
+{
+ long long retval;
+ char *buffer;
+
+ buffer = tracefs_instance_file_read(NULL, rel_path, NULL);
+ if (!buffer)
+ return -1;
+
+ /* get_llong_from_str returns -1 on error */
+ retval = get_llong_from_str(buffer);
+
+ debug_msg("reading %s returned %lld\n", rel_path, retval);
+
+ free(buffer);
+
+ return retval;
+}
+
+/*
+ * osnoise_write_ll_config - write a long long value to a config in rel_path
+ *
+ * returns -1 on error.
+ */
+static long long osnoise_write_ll_config(char *rel_path, long long value)
+{
+ char buffer[BUFF_U64_STR_SIZE];
+ long long retval;
+
+ snprintf(buffer, sizeof(buffer), "%lld\n", value);
+
+ debug_msg("setting %s to %lld\n", rel_path, value);
+
+ retval = tracefs_instance_file_write(NULL, rel_path, buffer);
+ return retval;
+}
+
+/*
+ * osnoise_get_runtime - return the original "osnoise/runtime_us" value
+ *
+ * It also saves the value to be restored.
+ */
+unsigned long long osnoise_get_runtime(struct osnoise_context *context)
+{
+ long long runtime_us;
+
+ if (context->runtime_us != OSNOISE_TIME_INIT_VAL)
+ return context->runtime_us;
+
+ if (context->orig_runtime_us != OSNOISE_TIME_INIT_VAL)
+ return context->orig_runtime_us;
+
+ runtime_us = osnoise_read_ll_config("osnoise/runtime_us");
+ if (runtime_us < 0)
+ goto out_err;
+
+ context->orig_runtime_us = runtime_us;
+ return runtime_us;
+
+out_err:
+ return OSNOISE_TIME_INIT_VAL;
+}
+
+/*
+ * osnoise_get_period - return the original "osnoise/period_us" value
+ *
+ * It also saves the value to be restored.
+ */
+unsigned long long osnoise_get_period(struct osnoise_context *context)
+{
+ long long period_us;
+
+ if (context->period_us != OSNOISE_TIME_INIT_VAL)
+ return context->period_us;
+
+ if (context->orig_period_us != OSNOISE_TIME_INIT_VAL)
+ return context->orig_period_us;
+
+ period_us = osnoise_read_ll_config("osnoise/period_us");
+ if (period_us < 0)
+ goto out_err;
+
+ context->orig_period_us = period_us;
+ return period_us;
+
+out_err:
+ return OSNOISE_TIME_INIT_VAL;
+}
+
+static int __osnoise_write_runtime(struct osnoise_context *context,
+ unsigned long long runtime)
+{
+ int retval;
+
+ if (context->orig_runtime_us == OSNOISE_TIME_INIT_VAL)
+ return -1;
+
+ retval = osnoise_write_ll_config("osnoise/runtime_us", runtime);
+ if (retval < 0)
+ return -1;
+
+ context->runtime_us = runtime;
+ return 0;
+}
+
+static int __osnoise_write_period(struct osnoise_context *context,
+ unsigned long long period)
+{
+ int retval;
+
+ if (context->orig_period_us == OSNOISE_TIME_INIT_VAL)
+ return -1;
+
+ retval = osnoise_write_ll_config("osnoise/period_us", period);
+ if (retval < 0)
+ return -1;
+
+ context->period_us = period;
+ return 0;
+}
+
+/*
+ * osnoise_set_runtime_period - set osnoise runtime and period
+ *
+ * Osnoise's runtime and period are related as runtime <= period.
+ * Thus, this function saves the original values, and then tries
+ * to set the runtime and period if they are != 0.
+ */
+int osnoise_set_runtime_period(struct osnoise_context *context,
+ unsigned long long runtime,
+ unsigned long long period)
+{
+ unsigned long long curr_runtime_us;
+ unsigned long long curr_period_us;
+ int retval;
+
+ if (!period && !runtime)
+ return 0;
+
+ curr_runtime_us = osnoise_get_runtime(context);
+ curr_period_us = osnoise_get_period(context);
+
+ /* error getting any value? */
+ if (curr_period_us == OSNOISE_TIME_INIT_VAL || curr_runtime_us == OSNOISE_TIME_INIT_VAL)
+ return -1;
+
+ if (!period) {
+ if (runtime > curr_period_us)
+ return -1;
+ return __osnoise_write_runtime(context, runtime);
+ } else if (!runtime) {
+ if (period < curr_runtime_us)
+ return -1;
+ return __osnoise_write_period(context, period);
+ }
+
+ if (runtime > curr_period_us) {
+ retval = __osnoise_write_period(context, period);
+ if (retval)
+ return -1;
+ retval = __osnoise_write_runtime(context, runtime);
+ if (retval)
+ return -1;
+ } else {
+ retval = __osnoise_write_runtime(context, runtime);
+ if (retval)
+ return -1;
+ retval = __osnoise_write_period(context, period);
+ if (retval)
+ return -1;
+ }
+
+ return 0;
+}
+
+/*
+ * osnoise_restore_runtime_period - restore the original runtime and period
+ */
+void osnoise_restore_runtime_period(struct osnoise_context *context)
+{
+ unsigned long long orig_runtime = context->orig_runtime_us;
+ unsigned long long orig_period = context->orig_period_us;
+ unsigned long long curr_runtime = context->runtime_us;
+ unsigned long long curr_period = context->period_us;
+ int retval;
+
+ if ((orig_runtime == OSNOISE_TIME_INIT_VAL) && (orig_period == OSNOISE_TIME_INIT_VAL))
+ return;
+
+ if ((orig_period == curr_period) && (orig_runtime == curr_runtime))
+ goto out_done;
+
+ retval = osnoise_set_runtime_period(context, orig_runtime, orig_period);
+ if (retval)
+ err_msg("Could not restore original osnoise runtime/period\n");
+
+out_done:
+ context->runtime_us = OSNOISE_TIME_INIT_VAL;
+ context->period_us = OSNOISE_TIME_INIT_VAL;
+}
+
+/*
+ * osnoise_put_runtime_period - restore original values and cleanup data
+ */
+void osnoise_put_runtime_period(struct osnoise_context *context)
+{
+ osnoise_restore_runtime_period(context);
+
+ if (context->orig_runtime_us != OSNOISE_TIME_INIT_VAL)
+ context->orig_runtime_us = OSNOISE_TIME_INIT_VAL;
+
+ if (context->orig_period_us != OSNOISE_TIME_INIT_VAL)
+ context->orig_period_us = OSNOISE_TIME_INIT_VAL;
+}
+
+/*
+ * osnoise_get_timerlat_period_us - read and save the original "timerlat_period_us"
+ */
+static long long
+osnoise_get_timerlat_period_us(struct osnoise_context *context)
+{
+ long long timerlat_period_us;
+
+ if (context->timerlat_period_us != OSNOISE_TIME_INIT_VAL)
+ return context->timerlat_period_us;
+
+ if (context->orig_timerlat_period_us != OSNOISE_TIME_INIT_VAL)
+ return context->orig_timerlat_period_us;
+
+ timerlat_period_us = osnoise_read_ll_config("osnoise/timerlat_period_us");
+ if (timerlat_period_us < 0)
+ goto out_err;
+
+ context->orig_timerlat_period_us = timerlat_period_us;
+ return timerlat_period_us;
+
+out_err:
+ return OSNOISE_TIME_INIT_VAL;
+}
+
+/*
+ * osnoise_set_timerlat_period_us - set "timerlat_period_us"
+ */
+int osnoise_set_timerlat_period_us(struct osnoise_context *context, long long timerlat_period_us)
+{
+ long long curr_timerlat_period_us = osnoise_get_timerlat_period_us(context);
+ int retval;
+
+ if (curr_timerlat_period_us == OSNOISE_TIME_INIT_VAL)
+ return -1;
+
+ retval = osnoise_write_ll_config("osnoise/timerlat_period_us", timerlat_period_us);
+ if (retval < 0)
+ return -1;
+
+ context->timerlat_period_us = timerlat_period_us;
+
+ return 0;
+}
+
+/*
+ * osnoise_restore_timerlat_period_us - restore "timerlat_period_us"
+ */
+void osnoise_restore_timerlat_period_us(struct osnoise_context *context)
+{
+ int retval;
+
+ if (context->orig_timerlat_period_us == OSNOISE_TIME_INIT_VAL)
+ return;
+
+ if (context->orig_timerlat_period_us == context->timerlat_period_us)
+ goto out_done;
+
+ retval = osnoise_write_ll_config("osnoise/timerlat_period_us", context->orig_timerlat_period_us);
+ if (retval < 0)
+ err_msg("Could not restore original osnoise timerlat_period_us\n");
+
+out_done:
+ context->timerlat_period_us = OSNOISE_TIME_INIT_VAL;
+}
+
+/*
+ * osnoise_put_timerlat_period_us - restore original values and cleanup data
+ */
+void osnoise_put_timerlat_period_us(struct osnoise_context *context)
+{
+ osnoise_restore_timerlat_period_us(context);
+
+ if (context->orig_timerlat_period_us == OSNOISE_TIME_INIT_VAL)
+ return;
+
+ context->orig_timerlat_period_us = OSNOISE_TIME_INIT_VAL;
+}
+
+/*
+ * osnoise_get_stop_us - read and save the original "stop_tracing_us"
+ */
+static long long
+osnoise_get_stop_us(struct osnoise_context *context)
+{
+ long long stop_us;
+
+ if (context->stop_us != OSNOISE_OPTION_INIT_VAL)
+ return context->stop_us;
+
+ if (context->orig_stop_us != OSNOISE_OPTION_INIT_VAL)
+ return context->orig_stop_us;
+
+ stop_us = osnoise_read_ll_config("osnoise/stop_tracing_us");
+ if (stop_us < 0)
+ goto out_err;
+
+ context->orig_stop_us = stop_us;
+ return stop_us;
+
+out_err:
+ return OSNOISE_OPTION_INIT_VAL;
+}
+
+/*
+ * osnoise_set_stop_us - set "stop_tracing_us"
+ */
+int osnoise_set_stop_us(struct osnoise_context *context, long long stop_us)
+{
+ long long curr_stop_us = osnoise_get_stop_us(context);
+ int retval;
+
+ if (curr_stop_us == OSNOISE_OPTION_INIT_VAL)
+ return -1;
+
+ retval = osnoise_write_ll_config("osnoise/stop_tracing_us", stop_us);
+ if (retval < 0)
+ return -1;
+
+ context->stop_us = stop_us;
+
+ return 0;
+}
+
+/*
+ * osnoise_restore_stop_us - restore the original "stop_tracing_us"
+ */
+void osnoise_restore_stop_us(struct osnoise_context *context)
+{
+ int retval;
+
+ if (context->orig_stop_us == OSNOISE_OPTION_INIT_VAL)
+ return;
+
+ if (context->orig_stop_us == context->stop_us)
+ goto out_done;
+
+ retval = osnoise_write_ll_config("osnoise/stop_tracing_us", context->orig_stop_us);
+ if (retval < 0)
+ err_msg("Could not restore original osnoise stop_us\n");
+
+out_done:
+ context->stop_us = OSNOISE_OPTION_INIT_VAL;
+}
+
+/*
+ * osnoise_put_stop_us - restore original values and cleanup data
+ */
+void osnoise_put_stop_us(struct osnoise_context *context)
+{
+ osnoise_restore_stop_us(context);
+
+ if (context->orig_stop_us == OSNOISE_OPTION_INIT_VAL)
+ return;
+
+ context->orig_stop_us = OSNOISE_OPTION_INIT_VAL;
+}
+
+/*
+ * osnoise_get_stop_total_us - read and save the original "stop_tracing_total_us"
+ */
+static long long
+osnoise_get_stop_total_us(struct osnoise_context *context)
+{
+ long long stop_total_us;
+
+ if (context->stop_total_us != OSNOISE_OPTION_INIT_VAL)
+ return context->stop_total_us;
+
+ if (context->orig_stop_total_us != OSNOISE_OPTION_INIT_VAL)
+ return context->orig_stop_total_us;
+
+ stop_total_us = osnoise_read_ll_config("osnoise/stop_tracing_total_us");
+ if (stop_total_us < 0)
+ goto out_err;
+
+ context->orig_stop_total_us = stop_total_us;
+ return stop_total_us;
+
+out_err:
+ return OSNOISE_OPTION_INIT_VAL;
+}
+
+/*
+ * osnoise_set_stop_total_us - set "stop_tracing_total_us"
+ */
+int osnoise_set_stop_total_us(struct osnoise_context *context, long long stop_total_us)
+{
+ long long curr_stop_total_us = osnoise_get_stop_total_us(context);
+ int retval;
+
+ if (curr_stop_total_us == OSNOISE_OPTION_INIT_VAL)
+ return -1;
+
+ retval = osnoise_write_ll_config("osnoise/stop_tracing_total_us", stop_total_us);
+ if (retval < 0)
+ return -1;
+
+ context->stop_total_us = stop_total_us;
+
+ return 0;
+}
+
+/*
+ * osnoise_restore_stop_total_us - restore the original "stop_tracing_total_us"
+ */
+void osnoise_restore_stop_total_us(struct osnoise_context *context)
+{
+ int retval;
+
+ if (context->orig_stop_total_us == OSNOISE_OPTION_INIT_VAL)
+ return;
+
+ if (context->orig_stop_total_us == context->stop_total_us)
+ goto out_done;
+
+ retval = osnoise_write_ll_config("osnoise/stop_tracing_total_us",
+ context->orig_stop_total_us);
+ if (retval < 0)
+ err_msg("Could not restore original osnoise stop_total_us\n");
+
+out_done:
+ context->stop_total_us = OSNOISE_OPTION_INIT_VAL;
+}
+
+/*
+ * osnoise_put_stop_total_us - restore original values and cleanup data
+ */
+void osnoise_put_stop_total_us(struct osnoise_context *context)
+{
+ osnoise_restore_stop_total_us(context);
+
+ if (context->orig_stop_total_us == OSNOISE_OPTION_INIT_VAL)
+ return;
+
+ context->orig_stop_total_us = OSNOISE_OPTION_INIT_VAL;
+}
+
+/*
+ * osnoise_get_print_stack - read and save the original "print_stack"
+ */
+static long long
+osnoise_get_print_stack(struct osnoise_context *context)
+{
+ long long print_stack;
+
+ if (context->print_stack != OSNOISE_OPTION_INIT_VAL)
+ return context->print_stack;
+
+ if (context->orig_print_stack != OSNOISE_OPTION_INIT_VAL)
+ return context->orig_print_stack;
+
+ print_stack = osnoise_read_ll_config("osnoise/print_stack");
+ if (print_stack < 0)
+ goto out_err;
+
+ context->orig_print_stack = print_stack;
+ return print_stack;
+
+out_err:
+ return OSNOISE_OPTION_INIT_VAL;
+}
+
+/*
+ * osnoise_set_print_stack - set "print_stack"
+ */
+int osnoise_set_print_stack(struct osnoise_context *context, long long print_stack)
+{
+ long long curr_print_stack = osnoise_get_print_stack(context);
+ int retval;
+
+ if (curr_print_stack == OSNOISE_OPTION_INIT_VAL)
+ return -1;
+
+ retval = osnoise_write_ll_config("osnoise/print_stack", print_stack);
+ if (retval < 0)
+ return -1;
+
+ context->print_stack = print_stack;
+
+ return 0;
+}
+
+/*
+ * osnoise_restore_print_stack - restore the original "print_stack"
+ */
+void osnoise_restore_print_stack(struct osnoise_context *context)
+{
+ int retval;
+
+ if (context->orig_print_stack == OSNOISE_OPTION_INIT_VAL)
+ return;
+
+ if (context->orig_print_stack == context->print_stack)
+ goto out_done;
+
+ retval = osnoise_write_ll_config("osnoise/print_stack", context->orig_print_stack);
+ if (retval < 0)
+ err_msg("Could not restore original osnoise print_stack\n");
+
+out_done:
+ context->print_stack = OSNOISE_OPTION_INIT_VAL;
+}
+
+/*
+ * osnoise_put_print_stack - restore original values and cleanup data
+ */
+void osnoise_put_print_stack(struct osnoise_context *context)
+{
+ osnoise_restore_print_stack(context);
+
+ if (context->orig_print_stack == OSNOISE_OPTION_INIT_VAL)
+ return;
+
+ context->orig_print_stack = OSNOISE_OPTION_INIT_VAL;
+}
+
+/*
+ * enable_osnoise - enable osnoise tracer in the trace_instance
+ */
+int enable_osnoise(struct trace_instance *trace)
+{
+ return enable_tracer_by_name(trace->inst, "osnoise");
+}
+
+/*
+ * enable_timerlat - enable timerlat tracer in the trace_instance
+ */
+int enable_timerlat(struct trace_instance *trace)
+{
+ return enable_tracer_by_name(trace->inst, "timerlat");
+}
+
+enum {
+ FLAG_CONTEXT_NEWLY_CREATED = (1 << 0),
+ FLAG_CONTEXT_DELETED = (1 << 1),
+};
+
+/*
+ * osnoise_get_context - increase the usage of a context and return it
+ */
+int osnoise_get_context(struct osnoise_context *context)
+{
+ int ret;
+
+ if (context->flags & FLAG_CONTEXT_DELETED) {
+ ret = -1;
+ } else {
+ context->ref++;
+ ret = 0;
+ }
+
+ return ret;
+}
+
+/*
+ * osnoise_context_alloc - alloc an osnoise_context
+ *
+ * The osnoise context contains the information of the "osnoise/" configs.
+ * It is used to set and restore the config.
+ */
+struct osnoise_context *osnoise_context_alloc(void)
+{
+ struct osnoise_context *context;
+
+ context = calloc(1, sizeof(*context));
+ if (!context)
+ return NULL;
+
+ context->orig_stop_us = OSNOISE_OPTION_INIT_VAL;
+ context->stop_us = OSNOISE_OPTION_INIT_VAL;
+
+ context->orig_stop_total_us = OSNOISE_OPTION_INIT_VAL;
+ context->stop_total_us = OSNOISE_OPTION_INIT_VAL;
+
+ context->orig_print_stack = OSNOISE_OPTION_INIT_VAL;
+ context->print_stack = OSNOISE_OPTION_INIT_VAL;
+
+ osnoise_get_context(context);
+
+ return context;
+}
+
+/*
+ * osnoise_put_context - put the osnoise_put_context
+ *
+ * If there is no other user for the context, the original data
+ * is restored.
+ */
+void osnoise_put_context(struct osnoise_context *context)
+{
+ if (--context->ref < 1)
+ context->flags |= FLAG_CONTEXT_DELETED;
+
+ if (!(context->flags & FLAG_CONTEXT_DELETED))
+ return;
+
+ osnoise_put_cpus(context);
+ osnoise_put_runtime_period(context);
+ osnoise_put_stop_us(context);
+ osnoise_put_stop_total_us(context);
+ osnoise_put_timerlat_period_us(context);
+ osnoise_put_print_stack(context);
+
+ free(context);
+}
+
+/*
+ * osnoise_destroy_tool - disable trace, restore configs and free data
+ */
+void osnoise_destroy_tool(struct osnoise_tool *top)
+{
+ if (!top)
+ return;
+
+ trace_instance_destroy(&top->trace);
+
+ if (top->context)
+ osnoise_put_context(top->context);
+
+ free(top);
+}
+
+/*
+ * osnoise_init_tool - init an osnoise tool
+ *
+ * It allocs data, create a context to store data and
+ * creates a new trace instance for the tool.
+ */
+struct osnoise_tool *osnoise_init_tool(char *tool_name)
+{
+ struct osnoise_tool *top;
+ int retval;
+
+ top = calloc(1, sizeof(*top));
+ if (!top)
+ return NULL;
+
+ top->context = osnoise_context_alloc();
+ if (!top->context)
+ goto out_err;
+
+ retval = trace_instance_init(&top->trace, tool_name);
+ if (retval)
+ goto out_err;
+
+ return top;
+out_err:
+ osnoise_destroy_tool(top);
+ return NULL;
+}
+
+/*
+ * osnoise_init_trace_tool - init a tracer instance to trace osnoise events
+ */
+struct osnoise_tool *osnoise_init_trace_tool(char *tracer)
+{
+ struct osnoise_tool *trace;
+ int retval;
+
+ trace = osnoise_init_tool("osnoise_trace");
+ if (!trace)
+ return NULL;
+
+ retval = tracefs_event_enable(trace->trace.inst, "osnoise", NULL);
+ if (retval < 0 && !errno) {
+ err_msg("Could not find osnoise events\n");
+ goto out_err;
+ }
+
+ retval = enable_tracer_by_name(trace->trace.inst, tracer);
+ if (retval) {
+ err_msg("Could not enable %s tracer for tracing\n", tracer);
+ goto out_err;
+ }
+
+ return trace;
+out_err:
+ osnoise_destroy_tool(trace);
+ return NULL;
+}
+
+static void osnoise_usage(void)
+{
+ int i;
+
+ static const char *msg[] = {
+ "",
+ "osnoise version " VERSION,
+ "",
+ " usage: [rtla] osnoise [MODE] ...",
+ "",
+ " modes:",
+ " top - prints the summary from osnoise tracer",
+ " hist - prints a histogram of osnoise samples",
+ "",
+ "if no MODE is given, the top mode is called, passing the arguments",
+ NULL,
+ };
+
+ for (i = 0; msg[i]; i++)
+ fprintf(stderr, "%s\n", msg[i]);
+ exit(1);
+}
+
+int osnoise_main(int argc, char *argv[])
+{
+ if (argc == 0)
+ goto usage;
+
+ /*
+ * if osnoise was called without any argument, run the
+ * default cmdline.
+ */
+ if (argc == 1) {
+ osnoise_top_main(argc, argv);
+ exit(0);
+ }
+
+ if ((strcmp(argv[1], "-h") == 0) || (strcmp(argv[1], "--help") == 0)) {
+ osnoise_usage();
+ exit(0);
+ } else if (strncmp(argv[1], "-", 1) == 0) {
+ /* the user skipped the tool, call the default one */
+ osnoise_top_main(argc, argv);
+ exit(0);
+ } else if (strcmp(argv[1], "top") == 0) {
+ osnoise_top_main(argc-1, &argv[1]);
+ exit(0);
+ } else if (strcmp(argv[1], "hist") == 0) {
+ osnoise_hist_main(argc-1, &argv[1]);
+ exit(0);
+ }
+
+usage:
+ osnoise_usage();
+ exit(1);
+}
diff --git a/tools/tracing/rtla/src/osnoise.h b/tools/tracing/rtla/src/osnoise.h
new file mode 100644
index 000000000000..9e4b2e2a4559
--- /dev/null
+++ b/tools/tracing/rtla/src/osnoise.h
@@ -0,0 +1,91 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "trace.h"
+
+/*
+ * osnoise_context - read, store, write, restore osnoise configs.
+ */
+struct osnoise_context {
+ int flags;
+ int ref;
+
+ char *curr_cpus;
+ char *orig_cpus;
+
+ /* 0 as init value */
+ unsigned long long orig_runtime_us;
+ unsigned long long runtime_us;
+
+ /* 0 as init value */
+ unsigned long long orig_period_us;
+ unsigned long long period_us;
+
+ /* 0 as init value */
+ long long orig_timerlat_period_us;
+ long long timerlat_period_us;
+
+ /* -1 as init value because 0 is disabled */
+ long long orig_stop_us;
+ long long stop_us;
+
+ /* -1 as init value because 0 is disabled */
+ long long orig_stop_total_us;
+ long long stop_total_us;
+
+ /* -1 as init value because 0 is disabled */
+ long long orig_print_stack;
+ long long print_stack;
+};
+
+/*
+ * *_INIT_VALs are also invalid values, they are used to
+ * communicate errors.
+ */
+#define OSNOISE_OPTION_INIT_VAL (-1)
+#define OSNOISE_TIME_INIT_VAL (0)
+
+struct osnoise_context *osnoise_context_alloc(void);
+int osnoise_get_context(struct osnoise_context *context);
+void osnoise_put_context(struct osnoise_context *context);
+
+int osnoise_set_cpus(struct osnoise_context *context, char *cpus);
+void osnoise_restore_cpus(struct osnoise_context *context);
+
+int osnoise_set_runtime_period(struct osnoise_context *context,
+ unsigned long long runtime,
+ unsigned long long period);
+void osnoise_restore_runtime_period(struct osnoise_context *context);
+
+int osnoise_set_stop_us(struct osnoise_context *context,
+ long long stop_us);
+void osnoise_restore_stop_us(struct osnoise_context *context);
+
+int osnoise_set_stop_total_us(struct osnoise_context *context,
+ long long stop_total_us);
+void osnoise_restore_stop_total_us(struct osnoise_context *context);
+
+int osnoise_set_timerlat_period_us(struct osnoise_context *context,
+ long long timerlat_period_us);
+void osnoise_restore_timerlat_period_us(struct osnoise_context *context);
+
+void osnoise_restore_print_stack(struct osnoise_context *context);
+int osnoise_set_print_stack(struct osnoise_context *context,
+ long long print_stack);
+
+/*
+ * osnoise_tool - osnoise based tool definition.
+ */
+struct osnoise_tool {
+ struct trace_instance trace;
+ struct osnoise_context *context;
+ void *data;
+ void *params;
+ time_t start_time;
+};
+
+void osnoise_destroy_tool(struct osnoise_tool *top);
+struct osnoise_tool *osnoise_init_tool(char *tool_name);
+struct osnoise_tool *osnoise_init_trace_tool(char *tracer);
+
+int osnoise_hist_main(int argc, char *argv[]);
+int osnoise_top_main(int argc, char **argv);
+int osnoise_main(int argc, char **argv);
diff --git a/tools/tracing/rtla/src/osnoise_hist.c b/tools/tracing/rtla/src/osnoise_hist.c
new file mode 100644
index 000000000000..52c053cc1789
--- /dev/null
+++ b/tools/tracing/rtla/src/osnoise_hist.c
@@ -0,0 +1,800 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2021 Red Hat Inc, Daniel Bristot de Oliveira <[email protected]>
+ */
+
+#include <getopt.h>
+#include <stdlib.h>
+#include <string.h>
+#include <signal.h>
+#include <unistd.h>
+#include <errno.h>
+#include <stdio.h>
+#include <time.h>
+
+#include "utils.h"
+#include "osnoise.h"
+
+struct osnoise_hist_params {
+ char *cpus;
+ char *monitored_cpus;
+ char *trace_output;
+ unsigned long long runtime;
+ unsigned long long period;
+ long long stop_us;
+ long long stop_total_us;
+ int sleep_time;
+ int duration;
+ int set_sched;
+ int output_divisor;
+ struct sched_attr sched_param;
+
+ char no_header;
+ char no_summary;
+ char no_index;
+ char with_zeros;
+ int bucket_size;
+ int entries;
+};
+
+struct osnoise_hist_cpu {
+ int *samples;
+ int count;
+
+ unsigned long long min_sample;
+ unsigned long long sum_sample;
+ unsigned long long max_sample;
+
+};
+
+struct osnoise_hist_data {
+ struct tracefs_hist *trace_hist;
+ struct osnoise_hist_cpu *hist;
+ int entries;
+ int bucket_size;
+ int nr_cpus;
+};
+
+/*
+ * osnoise_free_histogram - free runtime data
+ */
+static void
+osnoise_free_histogram(struct osnoise_hist_data *data)
+{
+ int cpu;
+
+ /* one histogram for IRQ and one for thread, per CPU */
+ for (cpu = 0; cpu < data->nr_cpus; cpu++) {
+ if (data->hist[cpu].samples)
+ free(data->hist[cpu].samples);
+ }
+
+ /* one set of histograms per CPU */
+ if (data->hist)
+ free(data->hist);
+
+ free(data);
+}
+
+/*
+ * osnoise_alloc_histogram - alloc runtime data
+ */
+static struct osnoise_hist_data
+*osnoise_alloc_histogram(int nr_cpus, int entries, int bucket_size)
+{
+ struct osnoise_hist_data *data;
+ int cpu;
+
+ data = calloc(1, sizeof(*data));
+ if (!data)
+ return NULL;
+
+ data->entries = entries;
+ data->bucket_size = bucket_size;
+ data->nr_cpus = nr_cpus;
+
+ data->hist = calloc(1, sizeof(*data->hist) * nr_cpus);
+ if (!data->hist)
+ goto cleanup;
+
+ for (cpu = 0; cpu < nr_cpus; cpu++) {
+ data->hist[cpu].samples = calloc(1, sizeof(*data->hist->samples) * (entries + 1));
+ if (!data->hist[cpu].samples)
+ goto cleanup;
+ }
+
+ /* set the min to max */
+ for (cpu = 0; cpu < nr_cpus; cpu++)
+ data->hist[cpu].min_sample = ~0;
+
+ return data;
+
+cleanup:
+ osnoise_free_histogram(data);
+ return NULL;
+}
+
+static void osnoise_hist_update_multiple(struct osnoise_tool *tool, int cpu,
+ unsigned long long duration, int count)
+{
+ struct osnoise_hist_params *params = tool->params;
+ struct osnoise_hist_data *data = tool->data;
+ int entries = data->entries;
+ int bucket;
+ int *hist;
+
+ if (params->output_divisor)
+ duration = duration / params->output_divisor;
+
+ if (data->bucket_size)
+ bucket = duration / data->bucket_size;
+
+ hist = data->hist[cpu].samples;
+ data->hist[cpu].count += count;
+ update_min(&data->hist[cpu].min_sample, &duration);
+ update_sum(&data->hist[cpu].sum_sample, &duration);
+ update_max(&data->hist[cpu].max_sample, &duration);
+
+ if (bucket < entries)
+ hist[bucket] += count;
+ else
+ hist[entries] += count;
+}
+
+/*
+ * osnoise_destroy_trace_hist - disable events used to collect histogram
+ */
+static void osnoise_destroy_trace_hist(struct osnoise_tool *tool)
+{
+ struct osnoise_hist_data *data = tool->data;
+
+ tracefs_hist_pause(tool->trace.inst, data->trace_hist);
+ tracefs_hist_destroy(tool->trace.inst, data->trace_hist);
+}
+
+/*
+ * osnoise_init_trace_hist - enable events used to collect histogram
+ */
+static int osnoise_init_trace_hist(struct osnoise_tool *tool)
+{
+ struct osnoise_hist_params *params = tool->params;
+ struct osnoise_hist_data *data = tool->data;
+ int bucket_size;
+ char buff[128];
+ int retval = 0;
+
+ /*
+ * Set the size of the bucket.
+ */
+ bucket_size = params->output_divisor * params->bucket_size;
+ snprintf(buff, sizeof(buff), "duration.buckets=%d", bucket_size);
+
+ data->trace_hist = tracefs_hist_alloc(tool->trace.tep, "osnoise", "sample_threshold",
+ buff, TRACEFS_HIST_KEY_NORMAL);
+ if (!data->trace_hist)
+ return 1;
+
+ retval = tracefs_hist_add_key(data->trace_hist, "cpu", 0);
+ if (retval)
+ goto out_err;
+
+ retval = tracefs_hist_start(tool->trace.inst, data->trace_hist);
+ if (retval)
+ goto out_err;
+
+ return 0;
+
+out_err:
+ osnoise_destroy_trace_hist(tool);
+ return 1;
+}
+
+/*
+ * osnoise_read_trace_hist - parse histogram file and file osnoise histogram
+ */
+static void osnoise_read_trace_hist(struct osnoise_tool *tool)
+{
+ struct osnoise_hist_data *data = tool->data;
+ long long cpu, counter, duration;
+ char *content, *position;
+
+ tracefs_hist_pause(tool->trace.inst, data->trace_hist);
+
+ content = tracefs_event_file_read(tool->trace.inst, "osnoise",
+ "sample_threshold",
+ "hist", NULL);
+ if (!content)
+ return;
+
+ position = content;
+ while (true) {
+ position = strstr(position, "duration: ~");
+ if (!position)
+ break;
+ position += strlen("duration: ~");
+ duration = get_llong_from_str(position);
+ if (duration == -1)
+ err_msg("error reading duration from histogram\n");
+
+ position = strstr(position, "cpu:");
+ if (!position)
+ break;
+ position += strlen("cpu: ");
+ cpu = get_llong_from_str(position);
+ if (cpu == -1)
+ err_msg("error reading cpu from histogram\n");
+
+ position = strstr(position, "hitcount:");
+ if (!position)
+ break;
+ position += strlen("hitcount: ");
+ counter = get_llong_from_str(position);
+ if (counter == -1)
+ err_msg("error reading counter from histogram\n");
+
+ osnoise_hist_update_multiple(tool, cpu, duration, counter);
+ }
+ free(content);
+}
+
+/*
+ * osnoise_hist_header - print the header of the tracer to the output
+ */
+static void osnoise_hist_header(struct osnoise_tool *tool)
+{
+ struct osnoise_hist_params *params = tool->params;
+ struct osnoise_hist_data *data = tool->data;
+ struct trace_seq *s = tool->trace.seq;
+ char duration[26];
+ int cpu;
+
+ if (params->no_header)
+ return;
+
+ get_duration(tool->start_time, duration, sizeof(duration));
+ trace_seq_printf(s, "# RTLA osnoise histogram\n");
+ trace_seq_printf(s, "# Time unit is %s (%s)\n",
+ params->output_divisor == 1 ? "nanoseconds" : "microseconds",
+ params->output_divisor == 1 ? "ns" : "us");
+
+ trace_seq_printf(s, "# Duration: %s\n", duration);
+
+ if (!params->no_index)
+ trace_seq_printf(s, "Index");
+
+ for (cpu = 0; cpu < data->nr_cpus; cpu++) {
+ if (params->cpus && !params->monitored_cpus[cpu])
+ continue;
+
+ if (!data->hist[cpu].count)
+ continue;
+
+ trace_seq_printf(s, " CPU-%03d", cpu);
+ }
+ trace_seq_printf(s, "\n");
+
+ trace_seq_do_printf(s);
+ trace_seq_reset(s);
+}
+
+/*
+ * osnoise_print_summary - print the summary of the hist data to the output
+ */
+static void
+osnoise_print_summary(struct osnoise_hist_params *params,
+ struct trace_instance *trace,
+ struct osnoise_hist_data *data)
+{
+ int cpu;
+
+ if (params->no_summary)
+ return;
+
+ if (!params->no_index)
+ trace_seq_printf(trace->seq, "count:");
+
+ for (cpu = 0; cpu < data->nr_cpus; cpu++) {
+ if (params->cpus && !params->monitored_cpus[cpu])
+ continue;
+
+ if (!data->hist[cpu].count)
+ continue;
+
+ trace_seq_printf(trace->seq, "%9d ", data->hist[cpu].count);
+ }
+ trace_seq_printf(trace->seq, "\n");
+
+ if (!params->no_index)
+ trace_seq_printf(trace->seq, "min: ");
+
+ for (cpu = 0; cpu < data->nr_cpus; cpu++) {
+ if (params->cpus && !params->monitored_cpus[cpu])
+ continue;
+
+ if (!data->hist[cpu].count)
+ continue;
+
+ trace_seq_printf(trace->seq, "%9llu ", data->hist[cpu].min_sample);
+
+ }
+ trace_seq_printf(trace->seq, "\n");
+
+ if (!params->no_index)
+ trace_seq_printf(trace->seq, "avg: ");
+
+ for (cpu = 0; cpu < data->nr_cpus; cpu++) {
+ if (params->cpus && !params->monitored_cpus[cpu])
+ continue;
+
+ if (!data->hist[cpu].count)
+ continue;
+
+ if (data->hist[cpu].count)
+ trace_seq_printf(trace->seq, "%9llu ",
+ data->hist[cpu].sum_sample / data->hist[cpu].count);
+ else
+ trace_seq_printf(trace->seq, " - ");
+ }
+ trace_seq_printf(trace->seq, "\n");
+
+ if (!params->no_index)
+ trace_seq_printf(trace->seq, "max: ");
+
+ for (cpu = 0; cpu < data->nr_cpus; cpu++) {
+ if (params->cpus && !params->monitored_cpus[cpu])
+ continue;
+
+ if (!data->hist[cpu].count)
+ continue;
+
+ trace_seq_printf(trace->seq, "%9llu ", data->hist[cpu].max_sample);
+
+ }
+ trace_seq_printf(trace->seq, "\n");
+ trace_seq_do_printf(trace->seq);
+ trace_seq_reset(trace->seq);
+}
+
+/*
+ * osnoise_print_stats - print data for all CPUs
+ */
+static void
+osnoise_print_stats(struct osnoise_hist_params *params, struct osnoise_tool *tool)
+{
+ struct osnoise_hist_data *data = tool->data;
+ struct trace_instance *trace = &tool->trace;
+ int bucket, cpu;
+ int total;
+
+ osnoise_hist_header(tool);
+
+ for (bucket = 0; bucket < data->entries; bucket++) {
+ total = 0;
+
+ if (!params->no_index)
+ trace_seq_printf(trace->seq, "%-6d",
+ bucket * data->bucket_size);
+
+ for (cpu = 0; cpu < data->nr_cpus; cpu++) {
+ if (params->cpus && !params->monitored_cpus[cpu])
+ continue;
+
+ if (!data->hist[cpu].count)
+ continue;
+
+ total += data->hist[cpu].samples[bucket];
+ trace_seq_printf(trace->seq, "%9d ", data->hist[cpu].samples[bucket]);
+ }
+
+ if (total == 0 && !params->with_zeros) {
+ trace_seq_reset(trace->seq);
+ continue;
+ }
+
+ trace_seq_printf(trace->seq, "\n");
+ trace_seq_do_printf(trace->seq);
+ trace_seq_reset(trace->seq);
+ }
+
+ if (!params->no_index)
+ trace_seq_printf(trace->seq, "over: ");
+
+ for (cpu = 0; cpu < data->nr_cpus; cpu++) {
+ if (params->cpus && !params->monitored_cpus[cpu])
+ continue;
+
+ if (!data->hist[cpu].count)
+ continue;
+
+ trace_seq_printf(trace->seq, "%9d ",
+ data->hist[cpu].samples[data->entries]);
+ }
+ trace_seq_printf(trace->seq, "\n");
+ trace_seq_do_printf(trace->seq);
+ trace_seq_reset(trace->seq);
+
+ osnoise_print_summary(params, trace, data);
+}
+
+/*
+ * osnoise_hist_usage - prints osnoise hist usage message
+ */
+static void osnoise_hist_usage(char *usage)
+{
+ int i;
+
+ static const char * const msg[] = {
+ "",
+ " usage: rtla osnoise hist [-h] [-D] [-d s] [-p us] [-r us] [-s us] [-S us] [-t[=file]] \\",
+ " [-c cpu-list] [-P priority] [-b N] [-E N] [--no-header] [--no-summary] \\",
+ " [--no-index] [--with-zeros]",
+ "",
+ " -h/--help: print this menu",
+ " -p/--period us: osnoise period in us",
+ " -r/--runtime us: osnoise runtime in us",
+ " -s/--stop us: stop trace if a single sample is higher than the argument in us",
+ " -S/--stop-total us: stop trace if the total sample is higher than the argument in us",
+ " -c/--cpus cpu-list: list of cpus to run osnoise threads",
+ " -d/--duration time[s|m|h|d]: duration of the session",
+ " -D/--debug: print debug info",
+ " -t/--trace[=file]: save the stopped trace to [file|osnoise_trace.txt]",
+ " -b/--bucket-size N: set the histogram bucket size (default 1)",
+ " -E/--entries N: set the number of entries of the histogram (default 256)",
+ " --no-header: do not print header",
+ " --no-summary: do not print summary",
+ " --no-index: do not print index",
+ " --with-zeros: print zero only entries",
+ " -P/--priority o:prio|r:prio|f:prio|d:runtime:period: set scheduling parameters",
+ " o:prio - use SCHED_OTHER with prio",
+ " r:prio - use SCHED_RR with prio",
+ " f:prio - use SCHED_FIFO with prio",
+ " d:runtime[us|ms|s]:period[us|ms|s] - use SCHED_DEADLINE with runtime and period",
+ " in nanoseconds",
+ NULL,
+ };
+
+ if (usage)
+ fprintf(stderr, "%s\n", usage);
+
+ fprintf(stderr, "rtla osnoise hist: a per-cpu histogram of the OS noise (version %s)\n",
+ VERSION);
+
+ for (i = 0; msg[i]; i++)
+ fprintf(stderr, "%s\n", msg[i]);
+ exit(1);
+}
+
+/*
+ * osnoise_hist_parse_args - allocs, parse and fill the cmd line parameters
+ */
+static struct osnoise_hist_params
+*osnoise_hist_parse_args(int argc, char *argv[])
+{
+ struct osnoise_hist_params *params;
+ int retval;
+ int c;
+
+ params = calloc(1, sizeof(*params));
+ if (!params)
+ exit(1);
+
+ /* display data in microseconds */
+ params->output_divisor = 1000;
+ params->bucket_size = 1;
+ params->entries = 256;
+
+ while (1) {
+ static struct option long_options[] = {
+ {"bucket-size", required_argument, 0, 'b'},
+ {"entries", required_argument, 0, 'E'},
+ {"cpus", required_argument, 0, 'c'},
+ {"debug", no_argument, 0, 'D'},
+ {"duration", required_argument, 0, 'd'},
+ {"help", no_argument, 0, 'h'},
+ {"period", required_argument, 0, 'p'},
+ {"priority", required_argument, 0, 'P'},
+ {"runtime", required_argument, 0, 'r'},
+ {"stop", required_argument, 0, 's'},
+ {"stop-total", required_argument, 0, 'S'},
+ {"trace", optional_argument, 0, 't'},
+ {"no-header", no_argument, 0, '0'},
+ {"no-summary", no_argument, 0, '1'},
+ {"no-index", no_argument, 0, '2'},
+ {"with-zeros", no_argument, 0, '3'},
+ {0, 0, 0, 0}
+ };
+
+ /* getopt_long stores the option index here. */
+ int option_index = 0;
+
+ c = getopt_long(argc, argv, "c:b:d:E:Dhp:P:r:s:S:t::0123",
+ long_options, &option_index);
+
+ /* detect the end of the options. */
+ if (c == -1)
+ break;
+
+ switch (c) {
+ case 'b':
+ params->bucket_size = get_llong_from_str(optarg);
+ if ((params->bucket_size == 0) || (params->bucket_size >= 1000000))
+ osnoise_hist_usage("Bucket size needs to be > 0 and <= 1000000\n");
+ break;
+ case 'c':
+ retval = parse_cpu_list(optarg, &params->monitored_cpus);
+ if (retval)
+ osnoise_hist_usage("\nInvalid -c cpu list\n");
+ params->cpus = optarg;
+ break;
+ case 'D':
+ config_debug = 1;
+ break;
+ case 'd':
+ params->duration = parse_seconds_duration(optarg);
+ if (!params->duration)
+ osnoise_hist_usage("Invalid -D duration\n");
+ break;
+ case 'E':
+ params->entries = get_llong_from_str(optarg);
+ if ((params->entries < 10) || (params->entries > 9999999))
+ osnoise_hist_usage("Entries must be > 10 and < 9999999\n");
+ break;
+ case 'h':
+ case '?':
+ osnoise_hist_usage(NULL);
+ break;
+ case 'p':
+ params->period = get_llong_from_str(optarg);
+ if (params->period > 10000000)
+ osnoise_hist_usage("Period longer than 10 s\n");
+ break;
+ case 'P':
+ retval = parse_prio(optarg, &params->sched_param);
+ if (retval == -1)
+ osnoise_hist_usage("Invalid -P priority");
+ params->set_sched = 1;
+ break;
+ case 'r':
+ params->runtime = get_llong_from_str(optarg);
+ if (params->runtime < 100)
+ osnoise_hist_usage("Runtime shorter than 100 us\n");
+ break;
+ case 's':
+ params->stop_us = get_llong_from_str(optarg);
+ break;
+ case 'S':
+ params->stop_total_us = get_llong_from_str(optarg);
+ break;
+ case 't':
+ if (optarg)
+ /* skip = */
+ params->trace_output = &optarg[1];
+ else
+ params->trace_output = "osnoise_trace.txt";
+ break;
+ case '0': /* no header */
+ params->no_header = 1;
+ break;
+ case '1': /* no summary */
+ params->no_summary = 1;
+ break;
+ case '2': /* no index */
+ params->no_index = 1;
+ break;
+ case '3': /* with zeros */
+ params->with_zeros = 1;
+ break;
+ default:
+ osnoise_hist_usage("Invalid option");
+ }
+ }
+
+ if (geteuid()) {
+ err_msg("rtla needs root permission\n");
+ exit(EXIT_FAILURE);
+ }
+
+ if (params->no_index && !params->with_zeros)
+ osnoise_hist_usage("no-index set and with-zeros not set - it does not make sense");
+
+ return params;
+}
+
+/*
+ * osnoise_hist_apply_config - apply the hist configs to the initialized tool
+ */
+static int
+osnoise_hist_apply_config(struct osnoise_tool *tool, struct osnoise_hist_params *params)
+{
+ int retval;
+
+ if (!params->sleep_time)
+ params->sleep_time = 1;
+
+ if (params->cpus) {
+ retval = osnoise_set_cpus(tool->context, params->cpus);
+ if (retval) {
+ err_msg("Failed to apply CPUs config\n");
+ goto out_err;
+ }
+ }
+
+ if (params->runtime || params->period) {
+ retval = osnoise_set_runtime_period(tool->context,
+ params->runtime,
+ params->period);
+ if (retval) {
+ err_msg("Failed to set runtime and/or period\n");
+ goto out_err;
+ }
+ }
+
+ if (params->stop_us) {
+ retval = osnoise_set_stop_us(tool->context, params->stop_us);
+ if (retval) {
+ err_msg("Failed to set stop us\n");
+ goto out_err;
+ }
+ }
+
+ if (params->stop_total_us) {
+ retval = osnoise_set_stop_total_us(tool->context, params->stop_total_us);
+ if (retval) {
+ err_msg("Failed to set stop total us\n");
+ goto out_err;
+ }
+ }
+
+ return 0;
+
+out_err:
+ return -1;
+}
+
+/*
+ * osnoise_init_hist - initialize a osnoise hist tool with parameters
+ */
+static struct osnoise_tool
+*osnoise_init_hist(struct osnoise_hist_params *params)
+{
+ struct osnoise_tool *tool;
+ int nr_cpus;
+
+ nr_cpus = sysconf(_SC_NPROCESSORS_CONF);
+
+ tool = osnoise_init_tool("osnoise_hist");
+ if (!tool)
+ return NULL;
+
+ tool->data = osnoise_alloc_histogram(nr_cpus, params->entries, params->bucket_size);
+ if (!tool->data)
+ goto out_err;
+
+ tool->params = params;
+
+ return tool;
+
+out_err:
+ osnoise_destroy_tool(tool);
+ return NULL;
+}
+
+static int stop_tracing;
+static void stop_hist(int sig)
+{
+ stop_tracing = 1;
+}
+
+/*
+ * osnoise_hist_set_signals - handles the signal to stop the tool
+ */
+static void
+osnoise_hist_set_signals(struct osnoise_hist_params *params)
+{
+ signal(SIGINT, stop_hist);
+ if (params->duration) {
+ signal(SIGALRM, stop_hist);
+ alarm(params->duration);
+ }
+}
+
+int osnoise_hist_main(int argc, char *argv[])
+{
+ struct osnoise_hist_params *params;
+ struct osnoise_tool *record = NULL;
+ struct osnoise_tool *tool = NULL;
+ struct trace_instance *trace;
+ int return_value = 1;
+ int retval;
+
+ params = osnoise_hist_parse_args(argc, argv);
+ if (!params)
+ exit(1);
+
+ tool = osnoise_init_hist(params);
+ if (!tool) {
+ err_msg("Could not init osnoise hist\n");
+ goto out_exit;
+ }
+
+ retval = osnoise_hist_apply_config(tool, params);
+ if (retval) {
+ err_msg("Could not apply config\n");
+ goto out_destroy;
+ }
+
+ trace = &tool->trace;
+
+ retval = enable_osnoise(trace);
+ if (retval) {
+ err_msg("Failed to enable osnoise tracer\n");
+ goto out_destroy;
+ }
+
+ retval = osnoise_init_trace_hist(tool);
+ if (retval)
+ goto out_destroy;
+
+ if (params->set_sched) {
+ retval = set_comm_sched_attr("osnoise/", &params->sched_param);
+ if (retval) {
+ err_msg("Failed to set sched parameters\n");
+ goto out_hist;
+ }
+ }
+
+ trace_instance_start(trace);
+
+ if (params->trace_output) {
+ record = osnoise_init_trace_tool("osnoise");
+ if (!record) {
+ err_msg("Failed to enable the trace instance\n");
+ goto out_hist;
+ }
+ trace_instance_start(&record->trace);
+ }
+
+ tool->start_time = time(NULL);
+ osnoise_hist_set_signals(params);
+
+ while (!stop_tracing) {
+ sleep(params->sleep_time);
+
+ retval = tracefs_iterate_raw_events(trace->tep,
+ trace->inst,
+ NULL,
+ 0,
+ collect_registered_events,
+ trace);
+ if (retval < 0) {
+ err_msg("Error iterating on events\n");
+ goto out_hist;
+ }
+
+ if (!tracefs_trace_is_on(trace->inst))
+ break;
+ };
+
+ osnoise_read_trace_hist(tool);
+
+ osnoise_print_stats(params, tool);
+
+ return_value = 0;
+
+ if (!tracefs_trace_is_on(trace->inst)) {
+ printf("rtla timelat hit stop tracing\n");
+ if (params->trace_output) {
+ printf(" Saving trace to %s\n", params->trace_output);
+ save_trace_to_file(record->trace.inst, params->trace_output);
+ }
+ }
+
+out_hist:
+ osnoise_free_histogram(tool->data);
+out_destroy:
+ osnoise_destroy_tool(record);
+ osnoise_destroy_tool(tool);
+ free(params);
+out_exit:
+ exit(return_value);
+}
diff --git a/tools/tracing/rtla/src/osnoise_top.c b/tools/tracing/rtla/src/osnoise_top.c
new file mode 100644
index 000000000000..7af769b9c0de
--- /dev/null
+++ b/tools/tracing/rtla/src/osnoise_top.c
@@ -0,0 +1,579 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2021 Red Hat Inc, Daniel Bristot de Oliveira <[email protected]>
+ */
+
+#include <getopt.h>
+#include <stdlib.h>
+#include <string.h>
+#include <signal.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <time.h>
+
+#include "osnoise.h"
+#include "utils.h"
+
+/*
+ * osnoise top parameters
+ */
+struct osnoise_top_params {
+ char *cpus;
+ char *monitored_cpus;
+ char *trace_output;
+ unsigned long long runtime;
+ unsigned long long period;
+ long long stop_us;
+ long long stop_total_us;
+ int sleep_time;
+ int duration;
+ int quiet;
+ int set_sched;
+ struct sched_attr sched_param;
+};
+
+struct osnoise_top_cpu {
+ unsigned long long sum_runtime;
+ unsigned long long sum_noise;
+ unsigned long long max_noise;
+ unsigned long long max_sample;
+
+ unsigned long long hw_count;
+ unsigned long long nmi_count;
+ unsigned long long irq_count;
+ unsigned long long softirq_count;
+ unsigned long long thread_count;
+
+ int sum_cycles;
+};
+
+struct osnoise_top_data {
+ struct osnoise_top_cpu *cpu_data;
+ int nr_cpus;
+};
+
+/*
+ * osnoise_free_top - free runtime data
+ */
+static void
+osnoise_free_top(struct osnoise_top_data *data)
+{
+ free(data->cpu_data);
+ free(data);
+}
+
+/*
+ * osnoise_alloc_histogram - alloc runtime data
+ */
+static struct osnoise_top_data *osnoise_alloc_top(int nr_cpus)
+{
+ struct osnoise_top_data *data;
+
+ data = calloc(1, sizeof(*data));
+ if (!data)
+ return NULL;
+
+ data->nr_cpus = nr_cpus;
+
+ /* one set of histograms per CPU */
+ data->cpu_data = calloc(1, sizeof(*data->cpu_data) * nr_cpus);
+ if (!data->cpu_data)
+ goto cleanup;
+
+ return data;
+
+cleanup:
+ osnoise_free_top(data);
+ return NULL;
+}
+
+/*
+ * osnoise_top_handler - this is the handler for osnoise tracer events
+ */
+static int
+osnoise_top_handler(struct trace_seq *s, struct tep_record *record,
+ struct tep_event *event, void *context)
+{
+ struct trace_instance *trace = context;
+ struct osnoise_tool *tool;
+ unsigned long long val;
+ struct osnoise_top_cpu *cpu_data;
+ struct osnoise_top_data *data;
+ int cpu = record->cpu;
+
+ tool = container_of(trace, struct osnoise_tool, trace);
+
+ data = tool->data;
+ cpu_data = &data->cpu_data[cpu];
+
+ cpu_data->sum_cycles++;
+
+ tep_get_field_val(s, event, "runtime", record, &val, 1);
+ update_sum(&cpu_data->sum_runtime, &val);
+
+ tep_get_field_val(s, event, "noise", record, &val, 1);
+ update_max(&cpu_data->max_noise, &val);
+ update_sum(&cpu_data->sum_noise, &val);
+
+ tep_get_field_val(s, event, "max_sample", record, &val, 1);
+ update_max(&cpu_data->max_sample, &val);
+
+ tep_get_field_val(s, event, "hw_count", record, &val, 1);
+ update_sum(&cpu_data->hw_count, &val);
+
+ tep_get_field_val(s, event, "nmi_count", record, &val, 1);
+ update_sum(&cpu_data->nmi_count, &val);
+
+ tep_get_field_val(s, event, "irq_count", record, &val, 1);
+ update_sum(&cpu_data->irq_count, &val);
+
+ tep_get_field_val(s, event, "softirq_count", record, &val, 1);
+ update_sum(&cpu_data->softirq_count, &val);
+
+ tep_get_field_val(s, event, "thread_count", record, &val, 1);
+ update_sum(&cpu_data->thread_count, &val);
+
+ return 0;
+}
+
+/*
+ * osnoise_top_header - print the header of the tool output
+ */
+static void osnoise_top_header(struct osnoise_tool *top)
+{
+ struct trace_seq *s = top->trace.seq;
+ char duration[26];
+
+ get_duration(top->start_time, duration, sizeof(duration));
+
+ trace_seq_printf(s, "\033[2;37;40m");
+ trace_seq_printf(s, " Operating System Noise");
+ trace_seq_printf(s, " ");
+ trace_seq_printf(s, " ");
+ trace_seq_printf(s, "\033[0;0;0m");
+ trace_seq_printf(s, "\n");
+
+ trace_seq_printf(s, "duration: %9s | time is in us\n", duration);
+
+ trace_seq_printf(s, "\033[2;30;47m");
+ trace_seq_printf(s, "CPU Period Runtime ");
+ trace_seq_printf(s, " Noise ");
+ trace_seq_printf(s, " %% CPU Aval ");
+ trace_seq_printf(s, " Max Noise Max Single ");
+ trace_seq_printf(s, " HW NMI IRQ Softirq Thread");
+ trace_seq_printf(s, "\033[0;0;0m");
+ trace_seq_printf(s, "\n");
+}
+
+/*
+ * clear_terminal - clears the output terminal
+ */
+static void clear_terminal(struct trace_seq *seq)
+{
+ if (!config_debug)
+ trace_seq_printf(seq, "\033c");
+}
+
+/*
+ * osnoise_top_print - prints the output of a given CPU
+ */
+static void osnoise_top_print(struct osnoise_tool *tool, int cpu)
+{
+ struct trace_seq *s = tool->trace.seq;
+ struct osnoise_top_cpu *cpu_data;
+ struct osnoise_top_data *data;
+ int percentage;
+ int decimal;
+
+ data = tool->data;
+ cpu_data = &data->cpu_data[cpu];
+
+ if (!cpu_data->sum_runtime)
+ return;
+
+ percentage = ((cpu_data->sum_runtime - cpu_data->sum_noise) * 10000000)
+ / cpu_data->sum_runtime;
+ decimal = percentage % 100000;
+ percentage = percentage / 100000;
+
+ trace_seq_printf(s, "%3d #%-6d %12llu ", cpu, cpu_data->sum_cycles, cpu_data->sum_runtime);
+ trace_seq_printf(s, "%12llu ", cpu_data->sum_noise);
+ trace_seq_printf(s, " %3d.%05d", percentage, decimal);
+ trace_seq_printf(s, "%12llu %12llu", cpu_data->max_noise, cpu_data->max_sample);
+
+ trace_seq_printf(s, "%12llu ", cpu_data->hw_count);
+ trace_seq_printf(s, "%12llu ", cpu_data->nmi_count);
+ trace_seq_printf(s, "%12llu ", cpu_data->irq_count);
+ trace_seq_printf(s, "%12llu ", cpu_data->softirq_count);
+ trace_seq_printf(s, "%12llu\n", cpu_data->thread_count);
+}
+
+/*
+ * osnoise_print_stats - print data for all cpus
+ */
+static void
+osnoise_print_stats(struct osnoise_top_params *params, struct osnoise_tool *top)
+{
+ struct trace_instance *trace = &top->trace;
+ static int nr_cpus = -1;
+ int i;
+
+ if (nr_cpus == -1)
+ nr_cpus = sysconf(_SC_NPROCESSORS_CONF);
+
+ if (!params->quiet)
+ clear_terminal(trace->seq);
+
+ osnoise_top_header(top);
+
+ for (i = 0; i < nr_cpus; i++) {
+ if (params->cpus && !params->monitored_cpus[i])
+ continue;
+ osnoise_top_print(top, i);
+ }
+
+ trace_seq_do_printf(trace->seq);
+ trace_seq_reset(trace->seq);
+}
+
+/*
+ * osnoise_top_usage - prints osnoise top usage message
+ */
+void osnoise_top_usage(char *usage)
+{
+ int i;
+
+ static const char * const msg[] = {
+ " usage: rtla osnoise [top] [-h] [-q] [-D] [-d s] [-p us] [-r us] [-s us] [-S us] [-t[=file]] \\",
+ " [-c cpu-list] [-P priority]",
+ "",
+ " -h/--help: print this menu",
+ " -p/--period us: osnoise period in us",
+ " -r/--runtime us: osnoise runtime in us",
+ " -s/--stop us: stop trace if a single sample is higher than the argument in us",
+ " -S/--stop-total us: stop trace if the total sample is higher than the argument in us",
+ " -c/--cpus cpu-list: list of cpus to run osnoise threads",
+ " -d/--duration time[s|m|h|d]: duration of the session",
+ " -D/--debug: print debug info",
+ " -t/--trace[=file]: save the stopped trace to [file|osnoise_trace.txt]",
+ " -q/--quiet print only a summary at the end",
+ " -P/--priority o:prio|r:prio|f:prio|d:runtime:period : set scheduling parameters",
+ " o:prio - use SCHED_OTHER with prio",
+ " r:prio - use SCHED_RR with prio",
+ " f:prio - use SCHED_FIFO with prio",
+ " d:runtime[us|ms|s]:period[us|ms|s] - use SCHED_DEADLINE with runtime and period",
+ " in nanoseconds",
+ NULL,
+ };
+
+ if (usage)
+ fprintf(stderr, "%s\n", usage);
+
+ fprintf(stderr, "rtla osnoise top: a per-cpu summary of the OS noise (version %s)\n",
+ VERSION);
+
+ for (i = 0; msg[i]; i++)
+ fprintf(stderr, "%s\n", msg[i]);
+ exit(1);
+}
+
+/*
+ * osnoise_top_parse_args - allocs, parse and fill the cmd line parameters
+ */
+struct osnoise_top_params *osnoise_top_parse_args(int argc, char **argv)
+{
+ struct osnoise_top_params *params;
+ int retval;
+ int c;
+
+ params = calloc(1, sizeof(*params));
+ if (!params)
+ exit(1);
+
+ while (1) {
+ static struct option long_options[] = {
+ {"cpus", required_argument, 0, 'c'},
+ {"debug", no_argument, 0, 'D'},
+ {"duration", required_argument, 0, 'd'},
+ {"help", no_argument, 0, 'h'},
+ {"period", required_argument, 0, 'p'},
+ {"priority", required_argument, 0, 'P'},
+ {"quiet", no_argument, 0, 'q'},
+ {"runtime", required_argument, 0, 'r'},
+ {"stop", required_argument, 0, 's'},
+ {"stop-total", required_argument, 0, 'S'},
+ {"trace", optional_argument, 0, 't'},
+ {0, 0, 0, 0}
+ };
+
+ /* getopt_long stores the option index here. */
+ int option_index = 0;
+
+ c = getopt_long(argc, argv, "c:d:Dhp:P:qr:s:S:t::",
+ long_options, &option_index);
+
+ /* Detect the end of the options. */
+ if (c == -1)
+ break;
+
+ switch (c) {
+ case 'c':
+ retval = parse_cpu_list(optarg, &params->monitored_cpus);
+ if (retval)
+ osnoise_top_usage("\nInvalid -c cpu list\n");
+ params->cpus = optarg;
+ break;
+ case 'D':
+ config_debug = 1;
+ break;
+ case 'd':
+ params->duration = parse_seconds_duration(optarg);
+ if (!params->duration)
+ osnoise_top_usage("Invalid -D duration\n");
+ break;
+ case 'h':
+ case '?':
+ osnoise_top_usage(NULL);
+ break;
+ case 'p':
+ params->period = get_llong_from_str(optarg);
+ if (params->period > 10000000)
+ osnoise_top_usage("Period longer than 10 s\n");
+ break;
+ case 'P':
+ retval = parse_prio(optarg, &params->sched_param);
+ if (retval == -1)
+ osnoise_top_usage("Invalid -P priority");
+ params->set_sched = 1;
+ break;
+ case 'q':
+ params->quiet = 1;
+ break;
+ case 'r':
+ params->runtime = get_llong_from_str(optarg);
+ if (params->runtime < 100)
+ osnoise_top_usage("Runtime shorter than 100 us\n");
+ break;
+ case 's':
+ params->stop_us = get_llong_from_str(optarg);
+ break;
+ case 'S':
+ params->stop_total_us = get_llong_from_str(optarg);
+ break;
+ case 't':
+ if (optarg)
+ /* skip = */
+ params->trace_output = &optarg[1];
+ else
+ params->trace_output = "osnoise_trace.txt";
+ break;
+ default:
+ osnoise_top_usage("Invalid option");
+ }
+ }
+
+ if (geteuid()) {
+ err_msg("osnoise needs root permission\n");
+ exit(EXIT_FAILURE);
+ }
+
+ return params;
+}
+
+/*
+ * osnoise_top_apply_config - apply the top configs to the initialized tool
+ */
+static int
+osnoise_top_apply_config(struct osnoise_tool *tool, struct osnoise_top_params *params)
+{
+ int retval;
+
+ if (!params->sleep_time)
+ params->sleep_time = 1;
+
+ if (params->cpus) {
+ retval = osnoise_set_cpus(tool->context, params->cpus);
+ if (retval) {
+ err_msg("Failed to apply CPUs config\n");
+ goto out_err;
+ }
+ }
+
+ if (params->runtime || params->period) {
+ retval = osnoise_set_runtime_period(tool->context,
+ params->runtime,
+ params->period);
+ if (retval) {
+ err_msg("Failed to set runtime and/or period\n");
+ goto out_err;
+ }
+ }
+
+ if (params->stop_us) {
+ retval = osnoise_set_stop_us(tool->context, params->stop_us);
+ if (retval) {
+ err_msg("Failed to set stop us\n");
+ goto out_err;
+ }
+ }
+
+ if (params->stop_total_us) {
+ retval = osnoise_set_stop_total_us(tool->context, params->stop_total_us);
+ if (retval) {
+ err_msg("Failed to set stop total us\n");
+ goto out_err;
+ }
+ }
+
+ return 0;
+
+out_err:
+ return -1;
+}
+
+/*
+ * osnoise_init_top - initialize a osnoise top tool with parameters
+ */
+struct osnoise_tool *osnoise_init_top(struct osnoise_top_params *params)
+{
+ struct osnoise_tool *tool;
+ int nr_cpus;
+
+ nr_cpus = sysconf(_SC_NPROCESSORS_CONF);
+
+ tool = osnoise_init_tool("osnoise_top");
+ if (!tool)
+ return NULL;
+
+ tool->data = osnoise_alloc_top(nr_cpus);
+ if (!tool->data)
+ goto out_err;
+
+ tool->params = params;
+
+ tep_register_event_handler(tool->trace.tep, -1, "ftrace", "osnoise",
+ osnoise_top_handler, NULL);
+
+ return tool;
+
+out_err:
+ osnoise_free_top(tool->data);
+ osnoise_destroy_tool(tool);
+ return NULL;
+}
+
+static int stop_tracing;
+static void stop_top(int sig)
+{
+ stop_tracing = 1;
+}
+
+/*
+ * osnoise_top_set_signals - handles the signal to stop the tool
+ */
+static void osnoise_top_set_signals(struct osnoise_top_params *params)
+{
+ signal(SIGINT, stop_top);
+ if (params->duration) {
+ signal(SIGALRM, stop_top);
+ alarm(params->duration);
+ }
+}
+
+int osnoise_top_main(int argc, char **argv)
+{
+ struct osnoise_top_params *params;
+ struct osnoise_tool *record = NULL;
+ struct osnoise_tool *tool = NULL;
+ struct trace_instance *trace;
+ int return_value = 1;
+ int retval;
+
+ params = osnoise_top_parse_args(argc, argv);
+ if (!params)
+ exit(1);
+
+ tool = osnoise_init_top(params);
+ if (!tool) {
+ err_msg("Could not init osnoise top\n");
+ goto out_exit;
+ }
+
+ retval = osnoise_top_apply_config(tool, params);
+ if (retval) {
+ err_msg("Could not apply config\n");
+ goto out_top;
+ }
+
+ trace = &tool->trace;
+
+ retval = enable_osnoise(trace);
+ if (retval) {
+ err_msg("Failed to enable osnoise tracer\n");
+ goto out_top;
+ }
+
+ if (params->set_sched) {
+ retval = set_comm_sched_attr("osnoise/", &params->sched_param);
+ if (retval) {
+ err_msg("Failed to set sched parameters\n");
+ goto out_top;
+ }
+ }
+
+ trace_instance_start(trace);
+
+ if (params->trace_output) {
+ record = osnoise_init_trace_tool("osnoise");
+ if (!record) {
+ err_msg("Failed to enable the trace instance\n");
+ goto out_top;
+ }
+ trace_instance_start(&record->trace);
+ }
+
+ tool->start_time = time(NULL);
+ osnoise_top_set_signals(params);
+
+ do {
+ sleep(params->sleep_time);
+
+ retval = tracefs_iterate_raw_events(trace->tep,
+ trace->inst,
+ NULL,
+ 0,
+ collect_registered_events,
+ trace);
+ if (retval < 0) {
+ err_msg("Error iterating on events\n");
+ goto out_top;
+ }
+
+ if (!params->quiet)
+ osnoise_print_stats(params, tool);
+
+ if (!tracefs_trace_is_on(trace->inst))
+ break;
+
+ } while (!stop_tracing);
+
+ osnoise_print_stats(params, tool);
+
+ return_value = 0;
+
+ if (!tracefs_trace_is_on(trace->inst)) {
+ printf("osnoise hit stop tracing\n");
+ if (params->trace_output) {
+ printf(" Saving trace to %s\n", params->trace_output);
+ save_trace_to_file(record->trace.inst, params->trace_output);
+ }
+ }
+
+out_top:
+ osnoise_free_top(tool->data);
+ osnoise_destroy_tool(record);
+ osnoise_destroy_tool(tool);
+ free(params);
+out_exit:
+ exit(return_value);
+}
diff --git a/tools/tracing/rtla/src/rtla.c b/tools/tracing/rtla/src/rtla.c
new file mode 100644
index 000000000000..09bd21b8af81
--- /dev/null
+++ b/tools/tracing/rtla/src/rtla.c
@@ -0,0 +1,87 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2021 Red Hat Inc, Daniel Bristot de Oliveira <[email protected]>
+ */
+
+#include <getopt.h>
+#include <stdlib.h>
+#include <string.h>
+#include <stdio.h>
+
+#include "osnoise.h"
+#include "timerlat.h"
+
+/*
+ * rtla_usage - print rtla usage
+ */
+static void rtla_usage(void)
+{
+ int i;
+
+ static const char *msg[] = {
+ "",
+ "rtla version " VERSION,
+ "",
+ " usage: rtla COMMAND ...",
+ "",
+ " commands:",
+ " osnoise - gives information about the operating system noise (osnoise)",
+ " timerlat - measures the timer irq and thread latency",
+ "",
+ NULL,
+ };
+
+ for (i = 0; msg[i]; i++)
+ fprintf(stderr, "%s\n", msg[i]);
+ exit(1);
+}
+
+/*
+ * run_command - try to run a rtla tool command
+ *
+ * It returns 0 if it fails. The tool's main will generally not
+ * return as they should call exit().
+ */
+int run_command(int argc, char **argv, int start_position)
+{
+ if (strcmp(argv[start_position], "osnoise") == 0) {
+ osnoise_main(argc-start_position, &argv[start_position]);
+ goto ran;
+ } else if (strcmp(argv[start_position], "timerlat") == 0) {
+ timerlat_main(argc-start_position, &argv[start_position]);
+ goto ran;
+ }
+
+ return 0;
+ran:
+ return 1;
+}
+
+int main(int argc, char *argv[])
+{
+ int retval;
+
+ /* is it an alias? */
+ retval = run_command(argc, argv, 0);
+ if (retval)
+ exit(0);
+
+ if (argc < 2)
+ goto usage;
+
+ if (strcmp(argv[1], "-h") == 0) {
+ rtla_usage();
+ exit(0);
+ } else if (strcmp(argv[1], "--help") == 0) {
+ rtla_usage();
+ exit(0);
+ }
+
+ retval = run_command(argc, argv, 1);
+ if (retval)
+ exit(0);
+
+usage:
+ rtla_usage();
+ exit(1);
+}
diff --git a/tools/tracing/rtla/src/timerlat.c b/tools/tracing/rtla/src/timerlat.c
new file mode 100644
index 000000000000..97abbf494fee
--- /dev/null
+++ b/tools/tracing/rtla/src/timerlat.c
@@ -0,0 +1,72 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2021 Red Hat Inc, Daniel Bristot de Oliveira <[email protected]>
+ */
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <pthread.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <stdio.h>
+
+#include "timerlat.h"
+
+static void timerlat_usage(void)
+{
+ int i;
+
+ static const char * const msg[] = {
+ "",
+ "timerlat version " VERSION,
+ "",
+ " usage: [rtla] timerlat [MODE] ...",
+ "",
+ " modes:",
+ " top - prints the summary from timerlat tracer",
+ " hist - prints a histogram of timer latencies",
+ "",
+ "if no MODE is given, the top mode is called, passing the arguments",
+ NULL,
+ };
+
+ for (i = 0; msg[i]; i++)
+ fprintf(stderr, "%s\n", msg[i]);
+ exit(1);
+}
+
+int timerlat_main(int argc, char *argv[])
+{
+ if (argc == 0)
+ goto usage;
+
+ /*
+ * if timerlat was called without any argument, run the
+ * default cmdline.
+ */
+ if (argc == 1) {
+ timerlat_top_main(argc, argv);
+ exit(0);
+ }
+
+ if ((strcmp(argv[1], "-h") == 0) || (strcmp(argv[1], "--help") == 0)) {
+ timerlat_usage();
+ exit(0);
+ } else if (strncmp(argv[1], "-", 1) == 0) {
+ /* the user skipped the tool, call the default one */
+ timerlat_top_main(argc, argv);
+ exit(0);
+ } else if (strcmp(argv[1], "top") == 0) {
+ timerlat_top_main(argc-1, &argv[1]);
+ exit(0);
+ } else if (strcmp(argv[1], "hist") == 0) {
+ timerlat_hist_main(argc-1, &argv[1]);
+ exit(0);
+ }
+
+usage:
+ timerlat_usage();
+ exit(1);
+}
diff --git a/tools/tracing/rtla/src/timerlat.h b/tools/tracing/rtla/src/timerlat.h
new file mode 100644
index 000000000000..88561bfd14f3
--- /dev/null
+++ b/tools/tracing/rtla/src/timerlat.h
@@ -0,0 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
+int timerlat_hist_main(int argc, char *argv[]);
+int timerlat_top_main(int argc, char *argv[]);
+int timerlat_main(int argc, char *argv[]);
diff --git a/tools/tracing/rtla/src/timerlat_hist.c b/tools/tracing/rtla/src/timerlat_hist.c
new file mode 100644
index 000000000000..237e1735afa7
--- /dev/null
+++ b/tools/tracing/rtla/src/timerlat_hist.c
@@ -0,0 +1,821 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2021 Red Hat Inc, Daniel Bristot de Oliveira <[email protected]>
+ */
+
+#include <getopt.h>
+#include <stdlib.h>
+#include <string.h>
+#include <signal.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <time.h>
+
+#include "utils.h"
+#include "osnoise.h"
+#include "timerlat.h"
+
+struct timerlat_hist_params {
+ char *cpus;
+ char *monitored_cpus;
+ char *trace_output;
+ unsigned long long runtime;
+ long long stop_us;
+ long long stop_total_us;
+ long long timerlat_period_us;
+ long long print_stack;
+ int sleep_time;
+ int output_divisor;
+ int duration;
+ int set_sched;
+ struct sched_attr sched_param;
+
+ char no_irq;
+ char no_thread;
+ char no_header;
+ char no_summary;
+ char no_index;
+ char with_zeros;
+ int bucket_size;
+ int entries;
+};
+
+struct timerlat_hist_cpu {
+ int *irq;
+ int *thread;
+
+ int irq_count;
+ int thread_count;
+
+ unsigned long long min_irq;
+ unsigned long long sum_irq;
+ unsigned long long max_irq;
+
+ unsigned long long min_thread;
+ unsigned long long sum_thread;
+ unsigned long long max_thread;
+};
+
+struct timerlat_hist_data {
+ struct timerlat_hist_cpu *hist;
+ int entries;
+ int bucket_size;
+ int nr_cpus;
+};
+
+/*
+ * timerlat_free_histogram - free runtime data
+ */
+static void
+timerlat_free_histogram(struct timerlat_hist_data *data)
+{
+ int cpu;
+
+ /* one histogram for IRQ and one for thread, per CPU */
+ for (cpu = 0; cpu < data->nr_cpus; cpu++) {
+ if (data->hist[cpu].irq)
+ free(data->hist[cpu].irq);
+
+ if (data->hist[cpu].thread)
+ free(data->hist[cpu].thread);
+ }
+
+ /* one set of histograms per CPU */
+ if (data->hist)
+ free(data->hist);
+
+ free(data);
+}
+
+/*
+ * timerlat_alloc_histogram - alloc runtime data
+ */
+static struct timerlat_hist_data
+*timerlat_alloc_histogram(int nr_cpus, int entries, int bucket_size)
+{
+ struct timerlat_hist_data *data;
+ int cpu;
+
+ data = calloc(1, sizeof(*data));
+ if (!data)
+ return NULL;
+
+ data->entries = entries;
+ data->bucket_size = bucket_size;
+ data->nr_cpus = nr_cpus;
+
+ /* one set of histograms per CPU */
+ data->hist = calloc(1, sizeof(*data->hist) * nr_cpus);
+ if (!data->hist)
+ goto cleanup;
+
+ /* one histogram for IRQ and one for thread, per cpu */
+ for (cpu = 0; cpu < nr_cpus; cpu++) {
+ data->hist[cpu].irq = calloc(1, sizeof(*data->hist->irq) * (entries + 1));
+ if (!data->hist[cpu].irq)
+ goto cleanup;
+ data->hist[cpu].thread = calloc(1, sizeof(*data->hist->thread) * (entries + 1));
+ if (!data->hist[cpu].thread)
+ goto cleanup;
+ }
+
+ /* set the min to max */
+ for (cpu = 0; cpu < nr_cpus; cpu++) {
+ data->hist[cpu].min_irq = ~0;
+ data->hist[cpu].min_thread = ~0;
+ }
+
+ return data;
+
+cleanup:
+ timerlat_free_histogram(data);
+ return NULL;
+}
+
+/*
+ * timerlat_hist_update - record a new timerlat occurent on cpu, updating data
+ */
+static void
+timerlat_hist_update(struct osnoise_tool *tool, int cpu,
+ unsigned long long thread,
+ unsigned long long latency)
+{
+ struct timerlat_hist_params *params = tool->params;
+ struct timerlat_hist_data *data = tool->data;
+ int entries = data->entries;
+ int bucket;
+ int *hist;
+
+ if (params->output_divisor)
+ latency = latency / params->output_divisor;
+
+ if (data->bucket_size)
+ bucket = latency / data->bucket_size;
+
+ if (!thread) {
+ hist = data->hist[cpu].irq;
+ data->hist[cpu].irq_count++;
+ update_min(&data->hist[cpu].min_irq, &latency);
+ update_sum(&data->hist[cpu].sum_irq, &latency);
+ update_max(&data->hist[cpu].max_irq, &latency);
+ } else {
+ hist = data->hist[cpu].thread;
+ data->hist[cpu].thread_count++;
+ update_min(&data->hist[cpu].min_thread, &latency);
+ update_sum(&data->hist[cpu].sum_thread, &latency);
+ update_max(&data->hist[cpu].max_thread, &latency);
+ }
+
+ if (bucket < entries)
+ hist[bucket]++;
+ else
+ hist[entries]++;
+}
+
+/*
+ * timerlat_hist_handler - this is the handler for timerlat tracer events
+ */
+static int
+timerlat_hist_handler(struct trace_seq *s, struct tep_record *record,
+ struct tep_event *event, void *data)
+{
+ struct trace_instance *trace = data;
+ unsigned long long thread, latency;
+ struct osnoise_tool *tool;
+ int cpu = record->cpu;
+
+ tool = container_of(trace, struct osnoise_tool, trace);
+
+ tep_get_field_val(s, event, "context", record, &thread, 1);
+ tep_get_field_val(s, event, "timer_latency", record, &latency, 1);
+
+ timerlat_hist_update(tool, cpu, thread, latency);
+
+ return 0;
+}
+
+/*
+ * timerlat_hist_header - print the header of the tracer to the output
+ */
+static void timerlat_hist_header(struct osnoise_tool *tool)
+{
+ struct timerlat_hist_params *params = tool->params;
+ struct timerlat_hist_data *data = tool->data;
+ struct trace_seq *s = tool->trace.seq;
+ char duration[26];
+ int cpu;
+
+ if (params->no_header)
+ return;
+
+ get_duration(tool->start_time, duration, sizeof(duration));
+ trace_seq_printf(s, "# RTLA timerlat histogram\n");
+ trace_seq_printf(s, "# Time unit is %s (%s)\n",
+ params->output_divisor == 1 ? "nanoseconds" : "microseconds",
+ params->output_divisor == 1 ? "ns" : "us");
+
+ trace_seq_printf(s, "# Duration: %s\n", duration);
+
+ if (!params->no_index)
+ trace_seq_printf(s, "Index");
+
+ for (cpu = 0; cpu < data->nr_cpus; cpu++) {
+ if (params->cpus && !params->monitored_cpus[cpu])
+ continue;
+
+ if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count)
+ continue;
+
+ if (!params->no_irq)
+ trace_seq_printf(s, " IRQ-%03d", cpu);
+
+ if (!params->no_thread)
+ trace_seq_printf(s, " Thr-%03d", cpu);
+ }
+ trace_seq_printf(s, "\n");
+
+
+ trace_seq_do_printf(s);
+ trace_seq_reset(s);
+}
+
+/*
+ * timerlat_print_summary - print the summary of the hist data to the output
+ */
+static void
+timerlat_print_summary(struct timerlat_hist_params *params,
+ struct trace_instance *trace,
+ struct timerlat_hist_data *data)
+{
+ int cpu;
+
+ if (params->no_summary)
+ return;
+
+ if (!params->no_index)
+ trace_seq_printf(trace->seq, "count:");
+
+ for (cpu = 0; cpu < data->nr_cpus; cpu++) {
+ if (params->cpus && !params->monitored_cpus[cpu])
+ continue;
+
+ if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count)
+ continue;
+
+ if (!params->no_irq)
+ trace_seq_printf(trace->seq, "%9d ",
+ data->hist[cpu].irq_count);
+
+ if (!params->no_thread)
+ trace_seq_printf(trace->seq, "%9d ",
+ data->hist[cpu].thread_count);
+ }
+ trace_seq_printf(trace->seq, "\n");
+
+ if (!params->no_index)
+ trace_seq_printf(trace->seq, "min: ");
+
+ for (cpu = 0; cpu < data->nr_cpus; cpu++) {
+ if (params->cpus && !params->monitored_cpus[cpu])
+ continue;
+
+ if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count)
+ continue;
+
+ if (!params->no_irq)
+ trace_seq_printf(trace->seq, "%9llu ",
+ data->hist[cpu].min_irq);
+
+ if (!params->no_thread)
+ trace_seq_printf(trace->seq, "%9llu ",
+ data->hist[cpu].min_thread);
+ }
+ trace_seq_printf(trace->seq, "\n");
+
+ if (!params->no_index)
+ trace_seq_printf(trace->seq, "avg: ");
+
+ for (cpu = 0; cpu < data->nr_cpus; cpu++) {
+ if (params->cpus && !params->monitored_cpus[cpu])
+ continue;
+
+ if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count)
+ continue;
+
+ if (!params->no_irq) {
+ if (data->hist[cpu].irq_count)
+ trace_seq_printf(trace->seq, "%9llu ",
+ data->hist[cpu].sum_irq / data->hist[cpu].irq_count);
+ else
+ trace_seq_printf(trace->seq, " - ");
+ }
+
+ if (!params->no_thread) {
+ if (data->hist[cpu].thread_count)
+ trace_seq_printf(trace->seq, "%9llu ",
+ data->hist[cpu].sum_thread / data->hist[cpu].thread_count);
+ else
+ trace_seq_printf(trace->seq, " - ");
+ }
+ }
+ trace_seq_printf(trace->seq, "\n");
+
+ if (!params->no_index)
+ trace_seq_printf(trace->seq, "max: ");
+
+ for (cpu = 0; cpu < data->nr_cpus; cpu++) {
+ if (params->cpus && !params->monitored_cpus[cpu])
+ continue;
+
+ if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count)
+ continue;
+
+ if (!params->no_irq)
+ trace_seq_printf(trace->seq, "%9llu ",
+ data->hist[cpu].max_irq);
+
+ if (!params->no_thread)
+ trace_seq_printf(trace->seq, "%9llu ",
+ data->hist[cpu].max_thread);
+ }
+ trace_seq_printf(trace->seq, "\n");
+ trace_seq_do_printf(trace->seq);
+ trace_seq_reset(trace->seq);
+}
+
+/*
+ * timerlat_print_stats - print data for all CPUs
+ */
+static void
+timerlat_print_stats(struct timerlat_hist_params *params, struct osnoise_tool *tool)
+{
+ struct timerlat_hist_data *data = tool->data;
+ struct trace_instance *trace = &tool->trace;
+ int bucket, cpu;
+ int total;
+
+ timerlat_hist_header(tool);
+
+ for (bucket = 0; bucket < data->entries; bucket++) {
+ total = 0;
+
+ if (!params->no_index)
+ trace_seq_printf(trace->seq, "%-6d",
+ bucket * data->bucket_size);
+
+ for (cpu = 0; cpu < data->nr_cpus; cpu++) {
+ if (params->cpus && !params->monitored_cpus[cpu])
+ continue;
+
+ if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count)
+ continue;
+
+ if (!params->no_irq) {
+ total += data->hist[cpu].irq[bucket];
+ trace_seq_printf(trace->seq, "%9d ",
+ data->hist[cpu].irq[bucket]);
+ }
+
+ if (!params->no_thread) {
+ total += data->hist[cpu].thread[bucket];
+ trace_seq_printf(trace->seq, "%9d ",
+ data->hist[cpu].thread[bucket]);
+ }
+
+ }
+
+ if (total == 0 && !params->with_zeros) {
+ trace_seq_reset(trace->seq);
+ continue;
+ }
+
+ trace_seq_printf(trace->seq, "\n");
+ trace_seq_do_printf(trace->seq);
+ trace_seq_reset(trace->seq);
+ }
+
+ if (!params->no_index)
+ trace_seq_printf(trace->seq, "over: ");
+
+ for (cpu = 0; cpu < data->nr_cpus; cpu++) {
+ if (params->cpus && !params->monitored_cpus[cpu])
+ continue;
+
+ if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count)
+ continue;
+
+ if (!params->no_irq)
+ trace_seq_printf(trace->seq, "%9d ",
+ data->hist[cpu].irq[data->entries]);
+
+ if (!params->no_thread)
+ trace_seq_printf(trace->seq, "%9d ",
+ data->hist[cpu].thread[data->entries]);
+ }
+ trace_seq_printf(trace->seq, "\n");
+ trace_seq_do_printf(trace->seq);
+ trace_seq_reset(trace->seq);
+
+ timerlat_print_summary(params, trace, data);
+}
+
+/*
+ * timerlat_hist_usage - prints timerlat top usage message
+ */
+static void timerlat_hist_usage(char *usage)
+{
+ int i;
+
+ char *msg[] = {
+ "",
+ " usage: [rtla] timerlat hist [-h] [-q] [-d s] [-D] [-n] [-p us] [-i us] [-T us] [-s us] [-t[=file]] \\",
+ " [-c cpu-list] [-P priority] [-E N] [-b N] [--no-irq] [--no-thread] [--no-header] [--no-summary] \\",
+ " [--no-index] [--with-zeros]",
+ "",
+ " -h/--help: print this menu",
+ " -p/--period us: timerlat period in us",
+ " -i/--irq us: stop trace if the irq latency is higher than the argument in us",
+ " -T/--thread us: stop trace if the thread latency is higher than the argument in us",
+ " -s/--stack us: save the stack trace at the IRQ if a thread latency is higher than the argument in us",
+ " -c/--cpus cpus: run the tracer only on the given cpus",
+ " -d/--duration time[m|h|d]: duration of the session in seconds",
+ " -D/--debug: print debug info",
+ " -T/--trace[=file]: save the stopped trace to [file|timerlat_trace.txt]",
+ " -n/--nano: display data in nanoseconds",
+ " -b/--bucket-size N: set the histogram bucket size (default 1)",
+ " -E/--entries N: set the number of entries of the histogram (default 256)",
+ " --no-irq: ignore IRQ latencies",
+ " --no-thread: ignore thread latencies",
+ " --no-header: do not print header",
+ " --no-summary: do not print summary",
+ " --no-index: do not print index",
+ " --with-zeros: print zero only entries",
+ " -P/--priority o:prio|r:prio|f:prio|d:runtime:period : set scheduling parameters",
+ " o:prio - use SCHED_OTHER with prio",
+ " r:prio - use SCHED_RR with prio",
+ " f:prio - use SCHED_FIFO with prio",
+ " d:runtime[us|ms|s]:period[us|ms|s] - use SCHED_DEADLINE with runtime and period",
+ " in nanoseconds",
+ NULL,
+ };
+
+ if (usage)
+ fprintf(stderr, "%s\n", usage);
+
+ fprintf(stderr, "rtla timerlat hist: a per-cpu histogram of the timer latency (version %s)\n",
+ VERSION);
+
+ for (i = 0; msg[i]; i++)
+ fprintf(stderr, "%s\n", msg[i]);
+ exit(1);
+}
+
+/*
+ * timerlat_hist_parse_args - allocs, parse and fill the cmd line parameters
+ */
+static struct timerlat_hist_params
+*timerlat_hist_parse_args(int argc, char *argv[])
+{
+ struct timerlat_hist_params *params;
+ int retval;
+ int c;
+
+ params = calloc(1, sizeof(*params));
+ if (!params)
+ exit(1);
+
+ /* display data in microseconds */
+ params->output_divisor = 1000;
+ params->bucket_size = 1;
+ params->entries = 256;
+
+ while (1) {
+ static struct option long_options[] = {
+ {"cpus", required_argument, 0, 'c'},
+ {"bucket-size", required_argument, 0, 'b'},
+ {"debug", no_argument, 0, 'D'},
+ {"entries", required_argument, 0, 'E'},
+ {"duration", required_argument, 0, 'd'},
+ {"help", no_argument, 0, 'h'},
+ {"irq", required_argument, 0, 'i'},
+ {"nano", no_argument, 0, 'n'},
+ {"period", required_argument, 0, 'p'},
+ {"priority", required_argument, 0, 'P'},
+ {"stack", required_argument, 0, 's'},
+ {"thread", required_argument, 0, 'T'},
+ {"trace", optional_argument, 0, 't'},
+ {"no-irq", no_argument, 0, '0'},
+ {"no-thread", no_argument, 0, '1'},
+ {"no-header", no_argument, 0, '2'},
+ {"no-summary", no_argument, 0, '3'},
+ {"no-index", no_argument, 0, '4'},
+ {"with-zeros", no_argument, 0, '5'},
+ {0, 0, 0, 0}
+ };
+
+ /* getopt_long stores the option index here. */
+ int option_index = 0;
+
+ c = getopt_long(argc, argv, "c:b:d:E:Dhi:np:P:s:t::T:012345",
+ long_options, &option_index);
+
+ /* detect the end of the options. */
+ if (c == -1)
+ break;
+
+ switch (c) {
+ case 'c':
+ retval = parse_cpu_list(optarg, &params->monitored_cpus);
+ if (retval)
+ timerlat_hist_usage("\nInvalid -c cpu list\n");
+ params->cpus = optarg;
+ break;
+ case 'b':
+ params->bucket_size = get_llong_from_str(optarg);
+ if ((params->bucket_size == 0) || (params->bucket_size >= 1000000))
+ timerlat_hist_usage("Bucket size needs to be > 0 and <= 1000000\n");
+ break;
+ case 'D':
+ config_debug = 1;
+ break;
+ case 'd':
+ params->duration = parse_seconds_duration(optarg);
+ if (!params->duration)
+ timerlat_hist_usage("Invalid -D duration\n");
+ break;
+ case 'E':
+ params->entries = get_llong_from_str(optarg);
+ if ((params->entries < 10) || (params->entries > 9999999))
+ timerlat_hist_usage("Entries must be > 10 and < 9999999\n");
+ break;
+ case 'h':
+ case '?':
+ timerlat_hist_usage(NULL);
+ break;
+ case 'i':
+ params->stop_us = get_llong_from_str(optarg);
+ break;
+ case 'n':
+ params->output_divisor = 1;
+ break;
+ case 'p':
+ params->timerlat_period_us = get_llong_from_str(optarg);
+ if (params->timerlat_period_us > 1000000)
+ timerlat_hist_usage("Period longer than 1 s\n");
+ break;
+ case 'P':
+ retval = parse_prio(optarg, &params->sched_param);
+ if (retval == -1)
+ timerlat_hist_usage("Invalid -P priority");
+ params->set_sched = 1;
+ break;
+ case 's':
+ params->print_stack = get_llong_from_str(optarg);
+ break;
+ case 'T':
+ params->stop_total_us = get_llong_from_str(optarg);
+ break;
+ case 't':
+ if (optarg)
+ /* skip = */
+ params->trace_output = &optarg[1];
+ else
+ params->trace_output = "timerlat_trace.txt";
+ break;
+ case '0': /* no irq */
+ params->no_irq = 1;
+ break;
+ case '1': /* no thread */
+ params->no_thread = 1;
+ break;
+ case '2': /* no header */
+ params->no_header = 1;
+ break;
+ case '3': /* no summary */
+ params->no_summary = 1;
+ break;
+ case '4': /* no index */
+ params->no_index = 1;
+ break;
+ case '5': /* with zeros */
+ params->with_zeros = 1;
+ break;
+ default:
+ timerlat_hist_usage("Invalid option");
+ }
+ }
+
+ if (geteuid()) {
+ err_msg("rtla needs root permission\n");
+ exit(EXIT_FAILURE);
+ }
+
+ if (params->no_irq && params->no_thread)
+ timerlat_hist_usage("no-irq and no-thread set, there is nothing to do here");
+
+ if (params->no_index && !params->with_zeros)
+ timerlat_hist_usage("no-index set with with-zeros is not set - it does not make sense");
+
+ return params;
+}
+
+/*
+ * timerlat_hist_apply_config - apply the hist configs to the initialized tool
+ */
+static int
+timerlat_hist_apply_config(struct osnoise_tool *tool, struct timerlat_hist_params *params)
+{
+ int retval;
+
+ if (!params->sleep_time)
+ params->sleep_time = 1;
+
+ if (params->cpus) {
+ retval = osnoise_set_cpus(tool->context, params->cpus);
+ if (retval) {
+ err_msg("Failed to apply CPUs config\n");
+ goto out_err;
+ }
+ }
+
+ if (params->stop_us) {
+ retval = osnoise_set_stop_us(tool->context, params->stop_us);
+ if (retval) {
+ err_msg("Failed to set stop us\n");
+ goto out_err;
+ }
+ }
+
+ if (params->stop_total_us) {
+ retval = osnoise_set_stop_total_us(tool->context, params->stop_total_us);
+ if (retval) {
+ err_msg("Failed to set stop total us\n");
+ goto out_err;
+ }
+ }
+
+ if (params->timerlat_period_us) {
+ retval = osnoise_set_timerlat_period_us(tool->context, params->timerlat_period_us);
+ if (retval) {
+ err_msg("Failed to set timerlat period\n");
+ goto out_err;
+ }
+ }
+
+ if (params->print_stack) {
+ retval = osnoise_set_print_stack(tool->context, params->print_stack);
+ if (retval) {
+ err_msg("Failed to set print stack\n");
+ goto out_err;
+ }
+ }
+
+ return 0;
+
+out_err:
+ return -1;
+}
+
+/*
+ * timerlat_init_hist - initialize a timerlat hist tool with parameters
+ */
+static struct osnoise_tool
+*timerlat_init_hist(struct timerlat_hist_params *params)
+{
+ struct osnoise_tool *tool;
+ int nr_cpus;
+
+ nr_cpus = sysconf(_SC_NPROCESSORS_CONF);
+
+ tool = osnoise_init_tool("timerlat_hist");
+ if (!tool)
+ return NULL;
+
+ tool->data = timerlat_alloc_histogram(nr_cpus, params->entries, params->bucket_size);
+ if (!tool->data)
+ goto out_err;
+
+ tool->params = params;
+
+ tep_register_event_handler(tool->trace.tep, -1, "ftrace", "timerlat",
+ timerlat_hist_handler, tool);
+
+ return tool;
+
+out_err:
+ osnoise_destroy_tool(tool);
+ return NULL;
+}
+
+static int stop_tracing;
+static void stop_hist(int sig)
+{
+ stop_tracing = 1;
+}
+
+/*
+ * timerlat_hist_set_signals - handles the signal to stop the tool
+ */
+static void
+timerlat_hist_set_signals(struct timerlat_hist_params *params)
+{
+ signal(SIGINT, stop_hist);
+ if (params->duration) {
+ signal(SIGALRM, stop_hist);
+ alarm(params->duration);
+ }
+}
+
+int timerlat_hist_main(int argc, char *argv[])
+{
+ struct timerlat_hist_params *params;
+ struct osnoise_tool *record = NULL;
+ struct osnoise_tool *tool = NULL;
+ struct trace_instance *trace;
+ int return_value = 1;
+ int retval;
+
+ params = timerlat_hist_parse_args(argc, argv);
+ if (!params)
+ exit(1);
+
+ tool = timerlat_init_hist(params);
+ if (!tool) {
+ err_msg("Could not init osnoise hist\n");
+ goto out_exit;
+ }
+
+ retval = timerlat_hist_apply_config(tool, params);
+ if (retval) {
+ err_msg("Could not apply config\n");
+ goto out_hist;
+ }
+
+ trace = &tool->trace;
+
+ retval = enable_timerlat(trace);
+ if (retval) {
+ err_msg("Failed to enable timerlat tracer\n");
+ goto out_hist;
+ }
+
+ if (params->set_sched) {
+ retval = set_comm_sched_attr("timerlat/", &params->sched_param);
+ if (retval) {
+ err_msg("Failed to set sched parameters\n");
+ goto out_hist;
+ }
+ }
+
+ trace_instance_start(trace);
+
+ if (params->trace_output) {
+ record = osnoise_init_trace_tool("timerlat");
+ if (!record) {
+ err_msg("Failed to enable the trace instance\n");
+ goto out_hist;
+ }
+ trace_instance_start(&record->trace);
+ }
+
+ tool->start_time = time(NULL);
+ timerlat_hist_set_signals(params);
+
+ while (!stop_tracing) {
+ sleep(params->sleep_time);
+
+ retval = tracefs_iterate_raw_events(trace->tep,
+ trace->inst,
+ NULL,
+ 0,
+ collect_registered_events,
+ trace);
+ if (retval < 0) {
+ err_msg("Error iterating on events\n");
+ goto out_hist;
+ }
+
+ if (!tracefs_trace_is_on(trace->inst))
+ break;
+ };
+
+ timerlat_print_stats(params, tool);
+
+ return_value = 0;
+
+ if (!tracefs_trace_is_on(trace->inst)) {
+ printf("rtla timelat hit stop tracing\n");
+ if (params->trace_output) {
+ printf(" Saving trace to %s\n", params->trace_output);
+ save_trace_to_file(record->trace.inst, params->trace_output);
+ }
+ }
+
+out_hist:
+ timerlat_free_histogram(tool->data);
+ osnoise_destroy_tool(record);
+ osnoise_destroy_tool(tool);
+ free(params);
+out_exit:
+ exit(return_value);
+}
diff --git a/tools/tracing/rtla/src/timerlat_top.c b/tools/tracing/rtla/src/timerlat_top.c
new file mode 100644
index 000000000000..d4187f6534ed
--- /dev/null
+++ b/tools/tracing/rtla/src/timerlat_top.c
@@ -0,0 +1,617 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2021 Red Hat Inc, Daniel Bristot de Oliveira <[email protected]>
+ */
+
+#include <getopt.h>
+#include <stdlib.h>
+#include <string.h>
+#include <signal.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <time.h>
+
+#include "utils.h"
+#include "osnoise.h"
+#include "timerlat.h"
+
+struct timerlat_top_params {
+ char *cpus;
+ char *monitored_cpus;
+ char *trace_output;
+ unsigned long long runtime;
+ long long stop_us;
+ long long stop_total_us;
+ long long timerlat_period_us;
+ long long print_stack;
+ int sleep_time;
+ int output_divisor;
+ int duration;
+ int quiet;
+ int set_sched;
+ struct sched_attr sched_param;
+};
+
+struct timerlat_top_cpu {
+ int irq_count;
+ int thread_count;
+
+ unsigned long long cur_irq;
+ unsigned long long min_irq;
+ unsigned long long sum_irq;
+ unsigned long long max_irq;
+
+ unsigned long long cur_thread;
+ unsigned long long min_thread;
+ unsigned long long sum_thread;
+ unsigned long long max_thread;
+};
+
+struct timerlat_top_data {
+ struct timerlat_top_cpu *cpu_data;
+ int nr_cpus;
+};
+
+/*
+ * timerlat_free_top - free runtime data
+ */
+static void
+timerlat_free_top(struct timerlat_top_data *data)
+{
+ free(data->cpu_data);
+ free(data);
+}
+
+/*
+ * timerlat_alloc_histogram - alloc runtime data
+ */
+static struct timerlat_top_data *timerlat_alloc_top(int nr_cpus)
+{
+ struct timerlat_top_data *data;
+ int cpu;
+
+ data = calloc(1, sizeof(*data));
+ if (!data)
+ return NULL;
+
+ data->nr_cpus = nr_cpus;
+
+ /* one set of histograms per CPU */
+ data->cpu_data = calloc(1, sizeof(*data->cpu_data) * nr_cpus);
+ if (!data->cpu_data)
+ goto cleanup;
+
+ /* set the min to max */
+ for (cpu = 0; cpu < nr_cpus; cpu++) {
+ data->cpu_data[cpu].min_irq = ~0;
+ data->cpu_data[cpu].min_thread = ~0;
+ }
+
+ return data;
+
+cleanup:
+ timerlat_free_top(data);
+ return NULL;
+}
+
+/*
+ * timerlat_hist_update - record a new timerlat occurent on cpu, updating data
+ */
+static void
+timerlat_top_update(struct osnoise_tool *tool, int cpu,
+ unsigned long long thread,
+ unsigned long long latency)
+{
+ struct timerlat_top_data *data = tool->data;
+ struct timerlat_top_cpu *cpu_data = &data->cpu_data[cpu];
+
+ if (!thread) {
+ cpu_data->irq_count++;
+ cpu_data->cur_irq = latency;
+ update_min(&cpu_data->min_irq, &latency);
+ update_sum(&cpu_data->sum_irq, &latency);
+ update_max(&cpu_data->max_irq, &latency);
+ } else {
+ cpu_data->thread_count++;
+ cpu_data->cur_thread = latency;
+ update_min(&cpu_data->min_thread, &latency);
+ update_sum(&cpu_data->sum_thread, &latency);
+ update_max(&cpu_data->max_thread, &latency);
+ }
+}
+
+/*
+ * timerlat_top_handler - this is the handler for timerlat tracer events
+ */
+static int
+timerlat_top_handler(struct trace_seq *s, struct tep_record *record,
+ struct tep_event *event, void *context)
+{
+ struct trace_instance *trace = context;
+ unsigned long long latency, thread;
+ struct osnoise_tool *top;
+ int cpu = record->cpu;
+
+ top = container_of(trace, struct osnoise_tool, trace);
+
+ tep_get_field_val(s, event, "context", record, &thread, 1);
+ tep_get_field_val(s, event, "timer_latency", record, &latency, 1);
+
+ timerlat_top_update(top, cpu, thread, latency);
+
+ return 0;
+}
+
+/*
+ * timerlat_top_header - print the header of the tool output
+ */
+static void timerlat_top_header(struct osnoise_tool *top)
+{
+ struct timerlat_top_params *params = top->params;
+ struct trace_seq *s = top->trace.seq;
+ char duration[26];
+
+ get_duration(top->start_time, duration, sizeof(duration));
+
+ trace_seq_printf(s, "\033[2;37;40m");
+ trace_seq_printf(s, " Timer Latency ");
+ trace_seq_printf(s, "\033[0;0;0m");
+ trace_seq_printf(s, "\n");
+
+ trace_seq_printf(s, "%-6s | IRQ Timer Latency (%s) | Thread Timer Latency (%s)\n", duration,
+ params->output_divisor == 1 ? "ns" : "us",
+ params->output_divisor == 1 ? "ns" : "us");
+
+ trace_seq_printf(s, "\033[2;30;47m");
+ trace_seq_printf(s, "CPU COUNT | cur min avg max | cur min avg max");
+ trace_seq_printf(s, "\033[0;0;0m");
+ trace_seq_printf(s, "\n");
+}
+
+/*
+ * timerlat_top_print - prints the output of a given CPU
+ */
+static void timerlat_top_print(struct osnoise_tool *top, int cpu)
+{
+
+ struct timerlat_top_params *params = top->params;
+ struct timerlat_top_data *data = top->data;
+ struct timerlat_top_cpu *cpu_data = &data->cpu_data[cpu];
+ int divisor = params->output_divisor;
+ struct trace_seq *s = top->trace.seq;
+
+ if (divisor == 0)
+ return;
+
+ /*
+ * Skip if no data is available: is this cpu offline?
+ */
+ if (!cpu_data->irq_count && !cpu_data->thread_count)
+ return;
+
+ /*
+ * Unless trace is being lost, IRQ counter is always the max.
+ */
+ trace_seq_printf(s, "%3d #%-9d |", cpu, cpu_data->irq_count);
+
+ if (!cpu_data->irq_count) {
+ trace_seq_printf(s, " - ");
+ trace_seq_printf(s, " - ");
+ trace_seq_printf(s, " - ");
+ trace_seq_printf(s, " - |");
+ } else {
+ trace_seq_printf(s, "%9llu ", cpu_data->cur_irq / params->output_divisor);
+ trace_seq_printf(s, "%9llu ", cpu_data->min_irq / params->output_divisor);
+ trace_seq_printf(s, "%9llu ", (cpu_data->sum_irq / cpu_data->irq_count) / divisor);
+ trace_seq_printf(s, "%9llu |", cpu_data->max_irq / divisor);
+ }
+
+ if (!cpu_data->thread_count) {
+ trace_seq_printf(s, " - ");
+ trace_seq_printf(s, " - ");
+ trace_seq_printf(s, " - ");
+ trace_seq_printf(s, " -\n");
+ } else {
+ trace_seq_printf(s, "%9llu ", cpu_data->cur_thread / divisor);
+ trace_seq_printf(s, "%9llu ", cpu_data->min_thread / divisor);
+ trace_seq_printf(s, "%9llu ",
+ (cpu_data->sum_thread / cpu_data->thread_count) / divisor);
+ trace_seq_printf(s, "%9llu\n", cpu_data->max_thread / divisor);
+ }
+}
+
+/*
+ * clear_terminal - clears the output terminal
+ */
+static void clear_terminal(struct trace_seq *seq)
+{
+ if (!config_debug)
+ trace_seq_printf(seq, "\033c");
+}
+
+/*
+ * timerlat_print_stats - print data for all cpus
+ */
+static void
+timerlat_print_stats(struct timerlat_top_params *params, struct osnoise_tool *top)
+{
+ struct trace_instance *trace = &top->trace;
+ static int nr_cpus = -1;
+ int i;
+
+ if (nr_cpus == -1)
+ nr_cpus = sysconf(_SC_NPROCESSORS_CONF);
+
+ if (!params->quiet)
+ clear_terminal(trace->seq);
+
+ timerlat_top_header(top);
+
+ for (i = 0; i < nr_cpus; i++) {
+ if (params->cpus && !params->monitored_cpus[i])
+ continue;
+ timerlat_top_print(top, i);
+ }
+
+ trace_seq_do_printf(trace->seq);
+ trace_seq_reset(trace->seq);
+}
+
+/*
+ * timerlat_top_usage - prints timerlat top usage message
+ */
+static void timerlat_top_usage(char *usage)
+{
+ int i;
+
+ static const char *const msg[] = {
+ "",
+ " usage: rtla timerlat [top] [-h] [-q] [-d s] [-D] [-n] [-p us] [-i us] [-T us] [-s us] [-t[=file]] \\",
+ " [-c cpu-list] [-P priority]",
+ "",
+ " -h/--help: print this menu",
+ " -p/--period us: timerlat period in us",
+ " -i/--irq us: stop trace if the irq latency is higher than the argument in us",
+ " -T/--thread us: stop trace if the thread latency is higher than the argument in us",
+ " -s/--stack us: save the stack trace at the IRQ if a thread latency is higher than the argument in us",
+ " -c/--cpus cpus: run the tracer only on the given cpus",
+ " -d/--duration time[m|h|d]: duration of the session in seconds",
+ " -D/--debug: print debug info",
+ " -t/--trace[=file]: save the stopped trace to [file|timerlat_trace.txt]",
+ " -n/--nano: display data in nanoseconds",
+ " -q/--quiet print only a summary at the end",
+ " -P/--priority o:prio|r:prio|f:prio|d:runtime:period : set scheduling parameters",
+ " o:prio - use SCHED_OTHER with prio",
+ " r:prio - use SCHED_RR with prio",
+ " f:prio - use SCHED_FIFO with prio",
+ " d:runtime[us|ms|s]:period[us|ms|s] - use SCHED_DEADLINE with runtime and period",
+ " in nanoseconds",
+ NULL,
+ };
+
+ if (usage)
+ fprintf(stderr, "%s\n", usage);
+
+ fprintf(stderr, "rtla timerlat top: a per-cpu summary of the timer latency (version %s)\n",
+ VERSION);
+
+ for (i = 0; msg[i]; i++)
+ fprintf(stderr, "%s\n", msg[i]);
+ exit(1);
+}
+
+/*
+ * timerlat_top_parse_args - allocs, parse and fill the cmd line parameters
+ */
+static struct timerlat_top_params
+*timerlat_top_parse_args(int argc, char **argv)
+{
+ struct timerlat_top_params *params;
+ int retval;
+ int c;
+
+ params = calloc(1, sizeof(*params));
+ if (!params)
+ exit(1);
+
+ /* display data in microseconds */
+ params->output_divisor = 1000;
+
+ while (1) {
+ static struct option long_options[] = {
+ {"cpus", required_argument, 0, 'c'},
+ {"debug", no_argument, 0, 'D'},
+ {"duration", required_argument, 0, 'd'},
+ {"help", no_argument, 0, 'h'},
+ {"irq", required_argument, 0, 'i'},
+ {"nano", no_argument, 0, 'n'},
+ {"period", required_argument, 0, 'p'},
+ {"priority", required_argument, 0, 'P'},
+ {"quiet", no_argument, 0, 'q'},
+ {"stack", required_argument, 0, 's'},
+ {"thread", required_argument, 0, 'T'},
+ {"trace", optional_argument, 0, 't'},
+ {0, 0, 0, 0}
+ };
+
+ /* getopt_long stores the option index here. */
+ int option_index = 0;
+
+ c = getopt_long(argc, argv, "c:d:Dhi:np:P:qs:t::T:",
+ long_options, &option_index);
+
+ /* detect the end of the options. */
+ if (c == -1)
+ break;
+
+ switch (c) {
+ case 'c':
+ retval = parse_cpu_list(optarg, &params->monitored_cpus);
+ if (retval)
+ timerlat_top_usage("\nInvalid -c cpu list\n");
+ params->cpus = optarg;
+ break;
+ case 'D':
+ config_debug = 1;
+ break;
+ case 'd':
+ params->duration = parse_seconds_duration(optarg);
+ if (!params->duration)
+ timerlat_top_usage("Invalid -D duration\n");
+ break;
+ case 'h':
+ case '?':
+ timerlat_top_usage(NULL);
+ break;
+ case 'i':
+ params->stop_us = get_llong_from_str(optarg);
+ break;
+ case 'n':
+ params->output_divisor = 1;
+ break;
+ case 'p':
+ params->timerlat_period_us = get_llong_from_str(optarg);
+ if (params->timerlat_period_us > 1000000)
+ timerlat_top_usage("Period longer than 1 s\n");
+ break;
+ case 'P':
+ retval = parse_prio(optarg, &params->sched_param);
+ if (retval == -1)
+ timerlat_top_usage("Invalid -P priority");
+ params->set_sched = 1;
+ break;
+ case 'q':
+ params->quiet = 1;
+ break;
+ case 's':
+ params->print_stack = get_llong_from_str(optarg);
+ break;
+ case 'T':
+ params->stop_total_us = get_llong_from_str(optarg);
+ break;
+ case 't':
+ if (optarg)
+ /* skip = */
+ params->trace_output = &optarg[1];
+ else
+ params->trace_output = "timerlat_trace.txt";
+ break;
+ default:
+ timerlat_top_usage("Invalid option");
+ }
+ }
+
+ if (geteuid()) {
+ err_msg("rtla needs root permission\n");
+ exit(EXIT_FAILURE);
+ }
+
+ return params;
+}
+
+/*
+ * timerlat_top_apply_config - apply the top configs to the initialized tool
+ */
+static int
+timerlat_top_apply_config(struct osnoise_tool *top, struct timerlat_top_params *params)
+{
+ int retval;
+
+ if (!params->sleep_time)
+ params->sleep_time = 1;
+
+ if (params->cpus) {
+ retval = osnoise_set_cpus(top->context, params->cpus);
+ if (retval) {
+ err_msg("Failed to apply CPUs config\n");
+ goto out_err;
+ }
+ }
+
+ if (params->stop_us) {
+ retval = osnoise_set_stop_us(top->context, params->stop_us);
+ if (retval) {
+ err_msg("Failed to set stop us\n");
+ goto out_err;
+ }
+ }
+
+ if (params->stop_total_us) {
+ retval = osnoise_set_stop_total_us(top->context, params->stop_total_us);
+ if (retval) {
+ err_msg("Failed to set stop total us\n");
+ goto out_err;
+ }
+ }
+
+
+ if (params->timerlat_period_us) {
+ retval = osnoise_set_timerlat_period_us(top->context, params->timerlat_period_us);
+ if (retval) {
+ err_msg("Failed to set timerlat period\n");
+ goto out_err;
+ }
+ }
+
+
+ if (params->print_stack) {
+ retval = osnoise_set_print_stack(top->context, params->print_stack);
+ if (retval) {
+ err_msg("Failed to set print stack\n");
+ goto out_err;
+ }
+ }
+
+ return 0;
+
+out_err:
+ return -1;
+}
+
+/*
+ * timerlat_init_top - initialize a timerlat top tool with parameters
+ */
+static struct osnoise_tool
+*timerlat_init_top(struct timerlat_top_params *params)
+{
+ struct osnoise_tool *top;
+ int nr_cpus;
+
+ nr_cpus = sysconf(_SC_NPROCESSORS_CONF);
+
+ top = osnoise_init_tool("timerlat_top");
+ if (!top)
+ return NULL;
+
+ top->data = timerlat_alloc_top(nr_cpus);
+ if (!top->data)
+ goto out_err;
+
+ top->params = params;
+
+ tep_register_event_handler(top->trace.tep, -1, "ftrace", "timerlat",
+ timerlat_top_handler, top);
+
+ return top;
+
+out_err:
+ osnoise_destroy_tool(top);
+ return NULL;
+}
+
+static int stop_tracing;
+static void stop_top(int sig)
+{
+ stop_tracing = 1;
+}
+
+/*
+ * timerlat_top_set_signals - handles the signal to stop the tool
+ */
+static void
+timerlat_top_set_signals(struct timerlat_top_params *params)
+{
+ signal(SIGINT, stop_top);
+ if (params->duration) {
+ signal(SIGALRM, stop_top);
+ alarm(params->duration);
+ }
+}
+
+int timerlat_top_main(int argc, char *argv[])
+{
+ struct timerlat_top_params *params;
+ struct osnoise_tool *record = NULL;
+ struct osnoise_tool *top = NULL;
+ struct trace_instance *trace;
+ int return_value = 1;
+ int retval;
+
+ params = timerlat_top_parse_args(argc, argv);
+ if (!params)
+ exit(1);
+
+ top = timerlat_init_top(params);
+ if (!top) {
+ err_msg("Could not init osnoise top\n");
+ goto out_exit;
+ }
+
+ retval = timerlat_top_apply_config(top, params);
+ if (retval) {
+ err_msg("Could not apply config\n");
+ goto out_top;
+ }
+
+ trace = &top->trace;
+
+ retval = enable_timerlat(trace);
+ if (retval) {
+ err_msg("Failed to enable timerlat tracer\n");
+ goto out_top;
+ }
+
+ if (params->set_sched) {
+ retval = set_comm_sched_attr("timerlat/", &params->sched_param);
+ if (retval) {
+ err_msg("Failed to set sched parameters\n");
+ goto out_top;
+ }
+ }
+
+ trace_instance_start(trace);
+
+ if (params->trace_output) {
+ record = osnoise_init_trace_tool("timerlat");
+ if (!record) {
+ err_msg("Failed to enable the trace instance\n");
+ goto out_top;
+ }
+ trace_instance_start(&record->trace);
+ }
+
+ top->start_time = time(NULL);
+ timerlat_top_set_signals(params);
+
+ while (!stop_tracing) {
+ sleep(params->sleep_time);
+
+ retval = tracefs_iterate_raw_events(trace->tep,
+ trace->inst,
+ NULL,
+ 0,
+ collect_registered_events,
+ trace);
+ if (retval < 0) {
+ err_msg("Error iterating on events\n");
+ goto out_top;
+ }
+
+ if (!params->quiet)
+ timerlat_print_stats(params, top);
+
+ if (!tracefs_trace_is_on(trace->inst))
+ break;
+
+ };
+
+ timerlat_print_stats(params, top);
+
+ return_value = 0;
+
+ if (!tracefs_trace_is_on(trace->inst)) {
+ printf("rtla timelat hit stop tracing\n");
+ if (params->trace_output) {
+ printf(" Saving trace to %s\n", params->trace_output);
+ save_trace_to_file(record->trace.inst, params->trace_output);
+ }
+ }
+
+out_top:
+ timerlat_free_top(top->data);
+ osnoise_destroy_tool(record);
+ osnoise_destroy_tool(top);
+ free(params);
+out_exit:
+ exit(return_value);
+}
diff --git a/tools/tracing/rtla/src/trace.c b/tools/tracing/rtla/src/trace.c
new file mode 100644
index 000000000000..83de259abcc1
--- /dev/null
+++ b/tools/tracing/rtla/src/trace.c
@@ -0,0 +1,192 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <sys/sendfile.h>
+#include <tracefs.h>
+#include <signal.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <errno.h>
+
+#include "trace.h"
+#include "utils.h"
+
+/*
+ * enable_tracer_by_name - enable a tracer on the given instance
+ */
+int enable_tracer_by_name(struct tracefs_instance *inst, const char *tracer_name)
+{
+ enum tracefs_tracers tracer;
+ int retval;
+
+ tracer = TRACEFS_TRACER_CUSTOM;
+
+ debug_msg("Enabling %s tracer\n", tracer_name);
+
+ retval = tracefs_tracer_set(inst, tracer, tracer_name);
+ if (retval < 0) {
+ if (errno == ENODEV)
+ err_msg("Tracer %s not found!\n", tracer_name);
+
+ err_msg("Failed to enable the %s tracer\n", tracer_name);
+ return -1;
+ }
+
+ return 0;
+}
+
+/*
+ * disable_tracer - set nop tracer to the insta
+ */
+void disable_tracer(struct tracefs_instance *inst)
+{
+ enum tracefs_tracers t = TRACEFS_TRACER_NOP;
+ int retval;
+
+ retval = tracefs_tracer_set(inst, t);
+ if (retval < 0)
+ err_msg("Oops, error disabling tracer\n");
+}
+
+/*
+ * create_instance - create a trace instance with *instance_name
+ */
+struct tracefs_instance *create_instance(char *instance_name)
+{
+ return tracefs_instance_create(instance_name);
+}
+
+/*
+ * destroy_instance - remove a trace instance and free the data
+ */
+void destroy_instance(struct tracefs_instance *inst)
+{
+ tracefs_instance_destroy(inst);
+ tracefs_instance_free(inst);
+}
+
+/*
+ * save_trace_to_file - save the trace output of the instance to the file
+ */
+int save_trace_to_file(struct tracefs_instance *inst, const char *filename)
+{
+ const char *file = "trace";
+ mode_t mode = 0644;
+ char buffer[4096];
+ int out_fd, in_fd;
+ int retval = -1;
+
+ in_fd = tracefs_instance_file_open(inst, file, O_RDONLY);
+ if (in_fd < 0) {
+ err_msg("Failed to open trace file\n");
+ return -1;
+ }
+
+ out_fd = creat(filename, mode);
+ if (out_fd < 0) {
+ err_msg("Failed to create output file %s\n", filename);
+ goto out_close_in;
+ }
+
+ do {
+ retval = read(in_fd, buffer, sizeof(buffer));
+ if (retval <= 0)
+ goto out_close;
+
+ retval = write(out_fd, buffer, retval);
+ if (retval < 0)
+ goto out_close;
+ } while (retval > 0);
+
+ retval = 0;
+out_close:
+ close(out_fd);
+out_close_in:
+ close(in_fd);
+ return retval;
+}
+
+/*
+ * collect_registered_events - call the existing callback function for the event
+ *
+ * If an event has a registered callback function, call it.
+ * Otherwise, ignore the event.
+ */
+int
+collect_registered_events(struct tep_event *event, struct tep_record *record,
+ int cpu, void *context)
+{
+ struct trace_instance *trace = context;
+ struct trace_seq *s = trace->seq;
+
+ if (!event->handler)
+ return 0;
+
+ event->handler(s, record, event, context);
+
+ return 0;
+}
+
+/*
+ * trace_instance_destroy - destroy and free a rtla trace instance
+ */
+void trace_instance_destroy(struct trace_instance *trace)
+{
+ if (trace->inst) {
+ disable_tracer(trace->inst);
+ destroy_instance(trace->inst);
+ }
+
+ if (trace->seq)
+ free(trace->seq);
+
+ if (trace->tep)
+ tep_free(trace->tep);
+}
+
+/*
+ * trace_instance_init - create an rtla trace instance
+ *
+ * It is more than the tracefs instance, as it contains other
+ * things required for the tracing, such as the local events and
+ * a seq file.
+ *
+ * Note that the trace instance is returned disabled. This allows
+ * the tool to apply some other configs, like setting priority
+ * to the kernel threads, before starting generating trace entries.
+ */
+int trace_instance_init(struct trace_instance *trace, char *tool_name)
+{
+ trace->seq = calloc(1, sizeof(*trace->seq));
+ if (!trace->seq)
+ goto out_err;
+
+ trace_seq_init(trace->seq);
+
+ trace->inst = create_instance(tool_name);
+ if (!trace->inst)
+ goto out_err;
+
+ trace->tep = tracefs_local_events(NULL);
+ if (!trace->tep)
+ goto out_err;
+
+ /*
+ * Let the main enable the record after setting some other
+ * things such as the priority of the tracer's threads.
+ */
+ tracefs_trace_off(trace->inst);
+
+ return 0;
+
+out_err:
+ trace_instance_destroy(trace);
+ return 1;
+}
+
+/*
+ * trace_instance_start - start tracing a given rtla instance
+ */
+int trace_instance_start(struct trace_instance *trace)
+{
+ return tracefs_trace_on(trace->inst);
+}
diff --git a/tools/tracing/rtla/src/trace.h b/tools/tracing/rtla/src/trace.h
new file mode 100644
index 000000000000..0ea1df0ad9a7
--- /dev/null
+++ b/tools/tracing/rtla/src/trace.h
@@ -0,0 +1,27 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <tracefs.h>
+#include <stddef.h>
+
+struct trace_instance {
+ struct tracefs_instance *inst;
+ struct tep_handle *tep;
+ struct trace_seq *seq;
+};
+
+int trace_instance_init(struct trace_instance *trace, char *tool_name);
+int trace_instance_start(struct trace_instance *trace);
+void trace_instance_destroy(struct trace_instance *trace);
+
+struct trace_seq *get_trace_seq(void);
+int enable_tracer_by_name(struct tracefs_instance *inst, const char *tracer_name);
+void disable_tracer(struct tracefs_instance *inst);
+
+int enable_osnoise(struct trace_instance *trace);
+int enable_timerlat(struct trace_instance *trace);
+
+struct tracefs_instance *create_instance(char *instance_name);
+void destroy_instance(struct tracefs_instance *inst);
+
+int save_trace_to_file(struct tracefs_instance *inst, const char *filename);
+int collect_registered_events(struct tep_event *tep, struct tep_record *record,
+ int cpu, void *context);
diff --git a/tools/tracing/rtla/src/utils.c b/tools/tracing/rtla/src/utils.c
new file mode 100644
index 000000000000..ffaf8ec84001
--- /dev/null
+++ b/tools/tracing/rtla/src/utils.c
@@ -0,0 +1,433 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2021 Red Hat Inc, Daniel Bristot de Oliveira <[email protected]>
+ */
+
+#include <proc/readproc.h>
+#include <stdarg.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <ctype.h>
+#include <errno.h>
+#include <sched.h>
+#include <stdio.h>
+
+#include "utils.h"
+
+#define MAX_MSG_LENGTH 1024
+int config_debug;
+
+/*
+ * err_msg - print an error message to the stderr
+ */
+void err_msg(const char *fmt, ...)
+{
+ char message[MAX_MSG_LENGTH];
+ va_list ap;
+
+ va_start(ap, fmt);
+ vsnprintf(message, sizeof(message), fmt, ap);
+ va_end(ap);
+
+ fprintf(stderr, "%s", message);
+}
+
+/*
+ * debug_msg - print a debug message to stderr if debug is set
+ */
+void debug_msg(const char *fmt, ...)
+{
+ char message[MAX_MSG_LENGTH];
+ va_list ap;
+
+ if (!config_debug)
+ return;
+
+ va_start(ap, fmt);
+ vsnprintf(message, sizeof(message), fmt, ap);
+ va_end(ap);
+
+ fprintf(stderr, "%s", message);
+}
+
+/*
+ * get_llong_from_str - get a long long int from a string
+ */
+long long get_llong_from_str(char *start)
+{
+ long long value;
+ char *end;
+
+ errno = 0;
+ value = strtoll(start, &end, 10);
+ if (errno || start == end)
+ return -1;
+
+ return value;
+}
+
+/*
+ * get_duration - fill output with a human readable duration since start_time
+ */
+void get_duration(time_t start_time, char *output, int output_size)
+{
+ time_t now = time(NULL);
+ struct tm *tm_info;
+ time_t duration;
+
+ duration = difftime(now, start_time);
+ tm_info = gmtime(&duration);
+
+ snprintf(output, output_size, "%3d %02d:%02d:%02d",
+ tm_info->tm_yday,
+ tm_info->tm_hour,
+ tm_info->tm_min,
+ tm_info->tm_sec);
+}
+
+/*
+ * parse_cpu_list - parse a cpu_list filling a char vector with cpus set
+ *
+ * Receives a cpu list, like 1-3,5 (cpus 1, 2, 3, 5), and then set the char
+ * in the monitored_cpus.
+ *
+ * XXX: convert to a bitmask.
+ */
+int parse_cpu_list(char *cpu_list, char **monitored_cpus)
+{
+ char *mon_cpus;
+ const char *p;
+ int end_cpu;
+ int nr_cpus;
+ int cpu;
+ int i;
+
+ nr_cpus = sysconf(_SC_NPROCESSORS_CONF);
+
+ mon_cpus = malloc(nr_cpus * sizeof(char));
+ memset(mon_cpus, 0, (nr_cpus * sizeof(char)));
+
+ for (p = cpu_list; *p; ) {
+ cpu = atoi(p);
+ if (cpu < 0 || (!cpu && *p != '0') || cpu >= nr_cpus)
+ goto err;
+
+ while (isdigit(*p))
+ p++;
+ if (*p == '-') {
+ p++;
+ end_cpu = atoi(p);
+ if (end_cpu < cpu || (!end_cpu && *p != '0') || end_cpu >= nr_cpus)
+ goto err;
+ while (isdigit(*p))
+ p++;
+ } else
+ end_cpu = cpu;
+
+ if (cpu == end_cpu) {
+ debug_msg("cpu_list: adding cpu %d\n", cpu);
+ mon_cpus[cpu] = 1;
+ } else {
+ for (i = cpu; i <= end_cpu; i++) {
+ debug_msg("cpu_list: adding cpu %d\n", i);
+ mon_cpus[i] = 1;
+ }
+ }
+
+ if (*p == ',')
+ p++;
+ }
+
+ *monitored_cpus = mon_cpus;
+
+ return 0;
+
+err:
+ debug_msg("Error parsing the cpu list %s", cpu_list);
+ return 1;
+}
+
+/*
+ * parse_duration - parse duration with s/m/h/d suffix converting it to seconds
+ */
+long parse_seconds_duration(char *val)
+{
+ char *end;
+ long t;
+
+ t = strtol(val, &end, 10);
+
+ if (end) {
+ switch (*end) {
+ case 's':
+ case 'S':
+ break;
+ case 'm':
+ case 'M':
+ t *= 60;
+ break;
+ case 'h':
+ case 'H':
+ t *= 60 * 60;
+ break;
+
+ case 'd':
+ case 'D':
+ t *= 24 * 60 * 60;
+ break;
+ }
+ }
+
+ return t;
+}
+
+/*
+ * parse_ns_duration - parse duration with ns/us/ms/s converting it to nanoseconds
+ */
+long parse_ns_duration(char *val)
+{
+ char *end;
+ long t;
+
+ t = strtol(val, &end, 10);
+
+ if (end) {
+ if (!strncmp(end, "ns", 2)) {
+ return t;
+ } else if (!strncmp(end, "us", 2)) {
+ t *= 1000;
+ return t;
+ } else if (!strncmp(end, "ms", 2)) {
+ t *= 1000 * 1000;
+ return t;
+ } else if (!strncmp(end, "s", 1)) {
+ t *= 1000 * 1000 * 1000;
+ return t;
+ }
+ return -1;
+ }
+
+ return t;
+}
+
+/*
+ * This is a set of helper functions to use SCHED_DEADLINE.
+ */
+#ifdef __x86_64__
+# define __NR_sched_setattr 314
+# define __NR_sched_getattr 315
+#elif __i386__
+# define __NR_sched_setattr 351
+# define __NR_sched_getattr 352
+#elif __arm__
+# define __NR_sched_setattr 380
+# define __NR_sched_getattr 381
+#elif __aarch64__
+# define __NR_sched_setattr 274
+# define __NR_sched_getattr 275
+#elif __powerpc__
+# define __NR_sched_setattr 355
+# define __NR_sched_getattr 356
+#elif __s390x__
+# define __NR_sched_setattr 345
+# define __NR_sched_getattr 346
+#endif
+
+#define SCHED_DEADLINE 6
+
+static inline int sched_setattr(pid_t pid, const struct sched_attr *attr,
+ unsigned int flags) {
+ return syscall(__NR_sched_setattr, pid, attr, flags);
+}
+
+static inline int sched_getattr(pid_t pid, struct sched_attr *attr,
+ unsigned int size, unsigned int flags)
+{
+ return syscall(__NR_sched_getattr, pid, attr, size, flags);
+}
+
+int __set_sched_attr(int pid, struct sched_attr *attr)
+{
+ int flags = 0;
+ int retval;
+
+ retval = sched_setattr(pid, attr, flags);
+ if (retval < 0) {
+ err_msg("boost_with_deadline failed to boost pid %d: %s\n",
+ pid, strerror(errno));
+ return 1;
+ }
+
+ return 0;
+}
+/*
+ * set_comm_sched_attr - set sched params to threads starting with char *comm
+ *
+ * This function uses procps to list the currently running threads and then
+ * set the sched_attr *attr to the threads that start with char *comm. It is
+ * mainly used to set the priority to the kernel threads created by the
+ * tracers.
+ */
+int set_comm_sched_attr(const char *comm, struct sched_attr *attr)
+{
+ int flags = PROC_FILLCOM | PROC_FILLSTAT;
+ PROCTAB *ptp;
+ proc_t task;
+ int retval;
+
+ ptp = openproc(flags);
+ if (!ptp) {
+ err_msg("error openproc()\n");
+ return -ENOENT;
+ }
+
+ memset(&task, 0, sizeof(task));
+
+ while (readproc(ptp, &task)) {
+ retval = strncmp(comm, task.cmd, strlen(comm));
+ if (retval)
+ continue;
+ retval = __set_sched_attr(task.tid, attr);
+ if (retval)
+ goto out_err;
+ }
+
+ closeproc(ptp);
+ return 0;
+
+out_err:
+ closeproc(ptp);
+ return 1;
+}
+
+#define INVALID_VAL (~0L)
+static long get_long_ns_after_colon(char *start)
+{
+ long val = INVALID_VAL;
+
+ /* find the ":" */
+ start = strstr(start, ":");
+ if (!start)
+ return -1;
+
+ /* skip ":" */
+ start++;
+ val = parse_ns_duration(start);
+
+ return val;
+}
+
+static long get_long_after_colon(char *start)
+{
+ long val = INVALID_VAL;
+
+ /* find the ":" */
+ start = strstr(start, ":");
+ if (!start)
+ return -1;
+
+ /* skip ":" */
+ start++;
+ val = get_llong_from_str(start);
+
+ return val;
+}
+
+/*
+ * parse priority in the format:
+ * SCHED_OTHER:
+ * o:<prio>
+ * O:<prio>
+ * SCHED_RR:
+ * r:<prio>
+ * R:<prio>
+ * SCHED_FIFO:
+ * f:<prio>
+ * F:<prio>
+ * SCHED_DEADLINE:
+ * d:runtime:period
+ * D:runtime:period
+ */
+int parse_prio(char *arg, struct sched_attr *sched_param)
+{
+ long prio;
+ long runtime;
+ long period;
+
+ memset(sched_param, 0, sizeof(*sched_param));
+ sched_param->size = sizeof(*sched_param);
+
+ switch (arg[0]) {
+ case 'd':
+ case 'D':
+ /* d:runtime:period */
+ if (strlen(arg) < 4)
+ return -1;
+
+ runtime = get_long_ns_after_colon(arg);
+ if (runtime == INVALID_VAL)
+ return -1;
+
+ period = get_long_ns_after_colon(&arg[2]);
+ if (period == INVALID_VAL)
+ return -1;
+
+ if (runtime > period)
+ return -1;
+
+ sched_param->sched_policy = SCHED_DEADLINE;
+ sched_param->sched_runtime = runtime;
+ sched_param->sched_deadline = period;
+ sched_param->sched_period = period;
+ break;
+ case 'f':
+ case 'F':
+ /* f:prio */
+ prio = get_long_after_colon(arg);
+ if (prio == INVALID_VAL)
+ return -1;
+
+ if (prio < sched_get_priority_min(SCHED_FIFO))
+ return -1;
+ if (prio > sched_get_priority_max(SCHED_FIFO))
+ return -1;
+
+ sched_param->sched_policy = SCHED_FIFO;
+ sched_param->sched_priority = prio;
+ break;
+ case 'r':
+ case 'R':
+ /* r:prio */
+ prio = get_long_after_colon(arg);
+ if (prio == INVALID_VAL)
+ return -1;
+
+ if (prio < sched_get_priority_min(SCHED_RR))
+ return -1;
+ if (prio > sched_get_priority_max(SCHED_RR))
+ return -1;
+
+ sched_param->sched_policy = SCHED_RR;
+ sched_param->sched_priority = prio;
+ break;
+ case 'o':
+ case 'O':
+ /* o:prio */
+ prio = get_long_after_colon(arg);
+ if (prio == INVALID_VAL)
+ return -1;
+
+ if (prio < sched_get_priority_min(SCHED_OTHER))
+ return -1;
+ if (prio > sched_get_priority_max(SCHED_OTHER))
+ return -1;
+
+ sched_param->sched_policy = SCHED_OTHER;
+ sched_param->sched_priority = prio;
+ break;
+ default:
+ return -1;
+ }
+ return 0;
+}
diff --git a/tools/tracing/rtla/src/utils.h b/tools/tracing/rtla/src/utils.h
new file mode 100644
index 000000000000..9aa962319ca2
--- /dev/null
+++ b/tools/tracing/rtla/src/utils.h
@@ -0,0 +1,56 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stdint.h>
+#include <time.h>
+
+/*
+ * '18446744073709551615\0'
+ */
+#define BUFF_U64_STR_SIZE 24
+
+#define container_of(ptr, type, member)({ \
+ const typeof(((type *)0)->member) *__mptr = (ptr); \
+ (type *)((char *)__mptr - offsetof(type, member)) ; })
+
+extern int config_debug;
+void debug_msg(const char *fmt, ...);
+void err_msg(const char *fmt, ...);
+
+long parse_seconds_duration(char *val);
+void get_duration(time_t start_time, char *output, int output_size);
+
+int parse_cpu_list(char *cpu_list, char **monitored_cpus);
+long long get_llong_from_str(char *start);
+
+static inline void
+update_min(unsigned long long *a, unsigned long long *b)
+{
+ if (*a > *b)
+ *a = *b;
+}
+
+static inline void
+update_max(unsigned long long *a, unsigned long long *b)
+{
+ if (*a < *b)
+ *a = *b;
+}
+
+static inline void
+update_sum(unsigned long long *a, unsigned long long *b)
+{
+ *a += *b;
+}
+
+struct sched_attr {
+ uint32_t size;
+ uint32_t sched_policy;
+ uint64_t sched_flags;
+ int32_t sched_nice;
+ uint32_t sched_priority;
+ uint64_t sched_runtime;
+ uint64_t sched_deadline;
+ uint64_t sched_period;
+};
+
+int parse_prio(char *arg, struct sched_attr *sched_param);
+int set_comm_sched_attr(const char *comm, struct sched_attr *attr);
diff --git a/tools/virtio/linux/mm_types.h b/tools/virtio/linux/mm_types.h
new file mode 100644
index 000000000000..356ba4d496f6
--- /dev/null
+++ b/tools/virtio/linux/mm_types.h
@@ -0,0 +1,3 @@
+struct folio {
+ struct page page;
+};
diff --git a/tools/virtio/virtio_test.c b/tools/virtio/virtio_test.c
index cb3f29c09aff..23f142af544a 100644
--- a/tools/virtio/virtio_test.c
+++ b/tools/virtio/virtio_test.c
@@ -130,6 +130,7 @@ static void vdev_info_init(struct vdev_info* dev, unsigned long long features)
memset(dev, 0, sizeof *dev);
dev->vdev.features = features;
INIT_LIST_HEAD(&dev->vdev.vqs);
+ spin_lock_init(&dev->vdev.vqs_list_lock);
dev->buf_size = 1024;
dev->buf = malloc(dev->buf_size);
assert(dev->buf);