From b530551891768b5ef537558d41befc4e42c3cc6c Mon Sep 17 00:00:00 2001 From: "Raziel K. Crowe" <84860158+CWDSYSTEMS@users.noreply.github.com> Date: Sat, 2 Apr 2022 17:08:35 +0500 Subject: [PATCH] phase 2 --- tools/accounting/getdelays.c | 8 +- tools/bootconfig/Makefile | 4 +- tools/bootconfig/include/linux/bootconfig.h | 45 +- tools/bootconfig/main.c | 32 +- tools/bpf/bpftool/.gitignore | 2 +- tools/bpf/bpftool/Documentation/Makefile | 4 +- .../bpf/bpftool/Documentation/bpftool-btf.rst | 7 +- .../bpftool/Documentation/bpftool-cgroup.rst | 17 +- .../bpftool/Documentation/bpftool-feature.rst | 6 +- .../bpf/bpftool/Documentation/bpftool-gen.rst | 7 +- .../bpftool/Documentation/bpftool-iter.rst | 6 +- .../bpftool/Documentation/bpftool-link.rst | 7 +- .../bpf/bpftool/Documentation/bpftool-map.rst | 9 +- .../bpf/bpftool/Documentation/bpftool-net.rst | 68 +- .../bpftool/Documentation/bpftool-perf.rst | 6 +- .../bpftool/Documentation/bpftool-prog.rst | 6 +- .../Documentation/bpftool-struct_ops.rst | 6 +- tools/bpf/bpftool/Documentation/bpftool.rst | 7 +- .../bpftool/Documentation/common_options.rst | 11 + tools/bpf/bpftool/Makefile | 100 +- tools/bpf/bpftool/bash-completion/bpftool | 5 +- tools/bpf/bpftool/btf.c | 169 +- tools/bpf/bpftool/btf_dumper.c | 42 +- tools/bpf/bpftool/common.c | 51 +- tools/bpf/bpftool/feature.c | 112 +- tools/bpf/bpftool/gen.c | 218 +- tools/bpf/bpftool/iter.c | 9 +- tools/bpf/bpftool/link.c | 45 +- tools/bpf/bpftool/main.c | 42 +- tools/bpf/bpftool/main.h | 57 +- tools/bpf/bpftool/map.c | 81 +- tools/bpf/bpftool/map_perf_ring.c | 10 +- tools/bpf/bpftool/pids.c | 90 +- tools/bpf/bpftool/prog.c | 293 +- tools/bpf/bpftool/skeleton/pid_iter.bpf.c | 4 +- tools/bpf/bpftool/struct_ops.c | 31 +- tools/bpf/resolve_btfids/Makefile | 20 +- tools/bpf/resolve_btfids/main.c | 42 +- tools/bpf/runqslower/Makefile | 23 +- tools/bpf/runqslower/runqslower.bpf.c | 2 +- tools/bpf/runqslower/runqslower.c | 8 +- tools/bpf/runqslower/runqslower.h | 2 +- tools/build/Build.include | 2 +- tools/build/Makefile.feature | 1 + tools/build/feature/Makefile | 12 +- tools/build/feature/test-bpf.c | 6 + tools/cgroup/memcg_slabinfo.py | 30 +- tools/iio/iio_event_monitor.c | 1 + tools/include/asm-generic/bitops.h | 1 - tools/include/linux/bitmap.h | 7 +- tools/include/linux/hash.h | 5 +- tools/include/linux/kernel.h | 24 +- tools/include/linux/objtool.h | 12 + tools/include/linux/spinlock.h | 2 - tools/include/nolibc/nolibc.h | 53 +- tools/include/uapi/asm-generic/unistd.h | 8 +- tools/include/uapi/drm/drm.h | 18 + tools/include/uapi/drm/i915_drm.h | 242 +- tools/include/uapi/linux/bpf.h | 241 +- tools/include/uapi/linux/btf.h | 56 +- tools/include/uapi/linux/if_link.h | 295 +- tools/include/uapi/linux/kvm.h | 48 +- tools/include/uapi/linux/perf_event.h | 39 +- tools/include/uapi/linux/prctl.h | 8 +- tools/include/uapi/sound/asound.h | 9 +- tools/lib/bpf/.gitignore | 1 - tools/lib/bpf/Makefile | 66 +- tools/lib/bpf/bpf.c | 502 ++- tools/lib/bpf/bpf.h | 246 +- tools/lib/bpf/bpf_gen_internal.h | 43 +- tools/lib/bpf/bpf_helpers.h | 51 +- tools/lib/bpf/bpf_tracing.h | 411 +- tools/lib/bpf/btf.c | 502 ++- tools/lib/bpf/btf.h | 204 +- tools/lib/bpf/btf_dump.c | 105 +- tools/lib/bpf/gen_loader.c | 591 ++- tools/lib/bpf/libbpf.c | 3312 +++++++++++------ tools/lib/bpf/libbpf.h | 488 ++- tools/lib/bpf/libbpf.map | 46 + tools/lib/bpf/libbpf_common.h | 43 +- tools/lib/bpf/libbpf_internal.h | 167 +- tools/lib/bpf/libbpf_legacy.h | 29 + tools/lib/bpf/libbpf_probes.c | 273 +- tools/lib/bpf/linker.c | 49 +- tools/lib/bpf/relo_core.c | 253 +- tools/lib/bpf/relo_core.h | 103 +- tools/lib/bpf/skel_internal.h | 13 +- tools/lib/bpf/xsk.c | 71 +- tools/lib/bpf/xsk.h | 90 +- tools/lib/find_bit.c | 20 + tools/lib/perf/Documentation/libperf.txt | 11 +- tools/lib/perf/cpumap.c | 119 +- tools/lib/perf/evlist.c | 19 +- tools/lib/perf/evsel.c | 115 +- tools/lib/perf/include/internal/cpumap.h | 14 +- tools/lib/perf/include/internal/evlist.h | 5 +- tools/lib/perf/include/internal/evsel.h | 4 +- tools/lib/perf/include/internal/mmap.h | 5 +- tools/lib/perf/include/perf/cpumap.h | 11 +- tools/lib/perf/include/perf/event.h | 6 + tools/lib/perf/include/perf/evsel.h | 14 +- tools/lib/perf/libperf.map | 3 + tools/lib/perf/mmap.c | 102 +- tools/lib/perf/tests/test-cpumap.c | 11 + tools/lib/perf/tests/test-evlist.c | 163 +- tools/lib/perf/tests/test-evsel.c | 5 +- tools/lib/traceevent/event-parse.c | 59 +- tools/lib/traceevent/event-parse.h | 5 +- tools/lib/traceevent/parse-filter.c | 5 +- .../Documentation/explanation.txt | 44 +- tools/memory-model/README | 12 + tools/memory-model/linux-kernel.cat | 6 +- tools/memory-model/litmus-tests/README | 8 + tools/objtool/arch/x86/decode.c | 187 +- tools/objtool/builtin-check.c | 3 +- tools/objtool/check.c | 583 ++- tools/objtool/elf.c | 85 +- tools/objtool/include/objtool/arch.h | 5 +- tools/objtool/include/objtool/builtin.h | 2 +- tools/objtool/include/objtool/cfi.h | 2 + tools/objtool/include/objtool/check.h | 3 +- tools/objtool/include/objtool/elf.h | 9 +- tools/objtool/include/objtool/objtool.h | 9 + tools/objtool/objtool.c | 26 + tools/objtool/orc_gen.c | 15 +- tools/objtool/special.c | 8 - tools/perf/Documentation/itrace.txt | 2 + .../perf/Documentation/perf-buildid-cache.txt | 5 +- tools/perf/Documentation/perf-config.txt | 9 + tools/perf/Documentation/perf-inject.txt | 7 + tools/perf/Documentation/perf-intel-pt.txt | 35 +- tools/perf/Documentation/perf-kmem.txt | 13 +- tools/perf/Documentation/perf-list.txt | 52 +- tools/perf/Documentation/perf-record.txt | 33 +- tools/perf/Documentation/perf-script.txt | 2 +- tools/perf/Documentation/perf-stat.txt | 10 +- tools/perf/Documentation/perf-top.txt | 7 +- .../Documentation/perf.data-file-format.txt | 2 +- tools/perf/bench/epoll-ctl.c | 6 +- tools/perf/bench/epoll-wait.c | 4 +- tools/perf/bench/evlist-open-close.c | 19 +- tools/perf/bench/futex-hash.c | 4 +- tools/perf/bench/futex-lock-pi.c | 4 +- tools/perf/bench/futex-requeue.c | 4 +- tools/perf/bench/futex-wake-parallel.c | 4 +- tools/perf/bench/futex-wake.c | 4 +- tools/perf/bench/futex.h | 43 +- tools/perf/bench/synthesize.c | 4 +- tools/perf/dlfilters/dlfilter-test-api-v0.c | 2 - .../arch/arm64/ampere/emag/bus.json | 2 +- .../arch/arm64/ampere/emag/cache.json | 20 +- .../arch/arm64/ampere/emag/clock.json | 2 +- .../arch/arm64/ampere/emag/exception.json | 4 +- .../arch/arm64/ampere/emag/instruction.json | 10 +- .../arch/arm64/ampere/emag/memory.json | 4 +- .../arch/arm64/arm/cortex-a76-n1/branch.json | 4 +- .../arch/arm64/arm/cortex-a76-n1/bus.json | 12 +- .../arch/arm64/arm/cortex-a76-n1/cache.json | 34 +- .../arm64/arm/cortex-a76-n1/exception.json | 4 +- .../arm64/arm/cortex-a76-n1/instruction.json | 18 +- .../arch/arm64/arm/cortex-a76-n1/memory.json | 2 +- .../arch/arm64/arm/cortex-a76-n1/other.json | 2 +- .../arm64/arm/cortex-a76-n1/pipeline.json | 4 +- .../arch/arm64/hisilicon/hip08/metrics.json | 2 +- .../arm64/hisilicon/hip08/uncore-ddrc.json | 32 +- .../arm64/hisilicon/hip08/uncore-hha.json | 120 +- .../arm64/hisilicon/hip08/uncore-l3c.json | 52 +- tools/perf/pmu-events/arch/arm64/mapfile.csv | 2 + .../pmu-events/arch/nds32/n13/atcpmu.json | 2 +- .../pmu-events/arch/s390/cf_z10/basic.json | 2 +- .../pmu-events/arch/s390/cf_z10/crypto.json | 2 +- .../pmu-events/arch/s390/cf_z10/extended.json | 2 +- .../pmu-events/arch/s390/cf_z13/basic.json | 2 +- .../pmu-events/arch/s390/cf_z13/crypto.json | 2 +- .../pmu-events/arch/s390/cf_z13/extended.json | 2 +- .../pmu-events/arch/s390/cf_z14/basic.json | 2 +- .../pmu-events/arch/s390/cf_z14/crypto.json | 2 +- .../pmu-events/arch/s390/cf_z14/extended.json | 2 +- .../pmu-events/arch/s390/cf_z15/basic.json | 2 +- .../pmu-events/arch/s390/cf_z15/crypto.json | 2 +- .../pmu-events/arch/s390/cf_z15/crypto6.json | 2 +- .../pmu-events/arch/s390/cf_z15/extended.json | 2 +- .../pmu-events/arch/s390/cf_z196/basic.json | 2 +- .../pmu-events/arch/s390/cf_z196/crypto.json | 2 +- .../arch/s390/cf_z196/extended.json | 2 +- .../pmu-events/arch/s390/cf_zec12/basic.json | 2 +- .../pmu-events/arch/s390/cf_zec12/crypto.json | 2 +- .../arch/s390/cf_zec12/extended.json | 2 +- .../arch/test/test_soc/cpu/uncore.json | 18 +- .../arch/test/test_soc/sys/uncore.json | 7 + .../arch/x86/icelakex/icx-metrics.json | 2 +- tools/perf/pmu-events/jevents.c | 34 +- tools/perf/pmu-events/jsmn.c | 43 +- tools/perf/pmu-events/pmu-events.h | 8 +- tools/perf/tests/Build | 1 + tools/perf/tests/api-io.c | 6 +- tools/perf/tests/attr.c | 10 +- tools/perf/tests/attr/README | 2 + .../perf/tests/attr/test-record-graph-default | 2 + tools/perf/tests/attr/test-record-graph-fp | 2 + tools/perf/tests/backward-ring-buffer.c | 7 +- tools/perf/tests/bitmap.c | 8 +- tools/perf/tests/bp_account.c | 36 +- tools/perf/tests/bp_signal.c | 34 +- tools/perf/tests/bp_signal_overflow.c | 9 +- tools/perf/tests/bpf.c | 92 +- tools/perf/tests/builtin-test.c | 588 +-- tools/perf/tests/clang.c | 54 +- tools/perf/tests/code-reading.c | 7 +- tools/perf/tests/cpumap.c | 16 +- tools/perf/tests/demangle-java-test.c | 4 +- tools/perf/tests/demangle-ocaml-test.c | 4 +- tools/perf/tests/dlfilter-test.c | 4 +- tools/perf/tests/dso-data.c | 10 +- tools/perf/tests/dwarf-unwind.c | 5 +- tools/perf/tests/event-times.c | 4 +- tools/perf/tests/event_update.c | 17 +- tools/perf/tests/evsel-roundtrip-name.c | 5 +- tools/perf/tests/evsel-tp-sched.c | 5 +- tools/perf/tests/expand-cgroup.c | 12 +- tools/perf/tests/expr.c | 197 +- tools/perf/tests/fdarray.c | 7 +- tools/perf/tests/genelf.c | 6 +- tools/perf/tests/hists_cumulate.c | 4 +- tools/perf/tests/hists_filter.c | 4 +- tools/perf/tests/hists_link.c | 4 +- tools/perf/tests/hists_output.c | 4 +- tools/perf/tests/is_printable_array.c | 4 +- tools/perf/tests/keep-tracking.c | 4 +- tools/perf/tests/kmod-path.c | 4 +- tools/perf/tests/llvm.c | 80 +- tools/perf/tests/maps.c | 4 +- tools/perf/tests/mem.c | 4 +- tools/perf/tests/mem2node.c | 13 +- tools/perf/tests/mmap-basic.c | 9 +- tools/perf/tests/mmap-thread-lookup.c | 8 +- tools/perf/tests/openat-syscall-all-cpus.c | 44 +- tools/perf/tests/openat-syscall-tp-fields.c | 5 +- tools/perf/tests/openat-syscall.c | 5 +- tools/perf/tests/parse-events.c | 65 +- tools/perf/tests/parse-metric.c | 7 +- tools/perf/tests/parse-no-sample-id-all.c | 5 +- tools/perf/tests/pe-file-parsing.c | 6 +- tools/perf/tests/perf-hooks.c | 4 +- tools/perf/tests/perf-record.c | 4 +- tools/perf/tests/perf-time-to-tsc.c | 30 +- tools/perf/tests/pfm.c | 69 +- tools/perf/tests/pmu-events.c | 311 +- tools/perf/tests/pmu.c | 4 +- tools/perf/tests/python-use.c | 4 +- tools/perf/tests/sample-parsing.c | 47 +- tools/perf/tests/sdt.c | 6 +- tools/perf/tests/shell/stat_bpf_counters.sh | 2 +- tools/perf/tests/shell/test_arm_coresight.sh | 11 +- tools/perf/tests/stat.c | 14 +- tools/perf/tests/sw-clock.c | 4 +- tools/perf/tests/switch-tracking.c | 4 +- tools/perf/tests/task-exit.c | 4 +- tools/perf/tests/tests.h | 239 +- tools/perf/tests/thread-map.c | 10 +- tools/perf/tests/thread-maps-share.c | 4 +- tools/perf/tests/time-utils-test.c | 4 +- tools/perf/tests/topology.c | 64 +- tools/perf/tests/unit_number__scnprintf.c | 4 +- tools/perf/tests/vmlinux-kallsyms.c | 107 +- tools/perf/tests/wp.c | 124 +- tools/perf/trace/beauty/beauty.h | 5 + .../perf/trace/beauty/include/linux/socket.h | 2 + tools/perf/trace/beauty/prctl_option.sh | 2 +- tools/perf/trace/beauty/sockaddr.c | 2 +- tools/perf/trace/beauty/socket.c | 21 +- tools/perf/trace/beauty/socket.sh | 38 +- tools/perf/ui/tui/setup.c | 8 +- tools/perf/util/Build | 8 + tools/perf/util/annotate.c | 23 +- tools/perf/util/annotate.h | 3 + .../util/arm-spe-decoder/arm-spe-decoder.c | 4 + .../util/arm-spe-decoder/arm-spe-decoder.h | 2 + .../arm-spe-decoder/arm-spe-pkt-decoder.c | 2 +- tools/perf/util/arm-spe.c | 189 +- tools/perf/util/auxtrace.c | 17 +- tools/perf/util/bpf-event.h | 2 +- tools/perf/util/bpf_counter.c | 61 +- tools/perf/util/bpf_skel/bperf_follower.bpf.c | 3 +- tools/perf/util/bpf_skel/bperf_leader.bpf.c | 3 +- .../util/bpf_skel/bpf_prog_profiler.bpf.c | 2 +- tools/perf/util/c++/clang-c.h | 8 +- tools/perf/util/c++/clang-test.cpp | 6 +- tools/perf/util/c++/clang.cpp | 23 +- tools/perf/util/callchain.c | 14 +- tools/perf/util/counts.c | 8 +- tools/perf/util/cpumap.h | 127 +- tools/perf/util/cs-etm.c | 18 +- tools/perf/util/env.c | 30 +- tools/perf/util/event.c | 18 + tools/perf/util/event.h | 10 +- tools/perf/util/evlist-hybrid.c | 11 +- tools/perf/util/evlist.h | 52 +- tools/perf/util/evsel.c | 343 +- tools/perf/util/evsel_fprintf.c | 12 +- tools/perf/util/expr.h | 38 +- tools/perf/util/header.c | 62 +- tools/perf/util/hist.c | 4 +- tools/perf/util/hist.h | 3 +- .../util/intel-pt-decoder/intel-pt-decoder.c | 1 + .../util/intel-pt-decoder/intel-pt-decoder.h | 1 + .../intel-pt-decoder/intel-pt-insn-decoder.c | 2 +- .../perf/util/intel-pt-decoder/intel-pt-log.c | 8 +- .../intel-pt-decoder/intel-pt-pkt-decoder.c | 2 +- tools/perf/util/intel-pt.c | 106 +- tools/perf/util/libunwind/arm64.c | 2 + tools/perf/util/mmap.c | 30 +- tools/perf/util/namespaces.c | 76 +- tools/perf/util/namespaces.h | 2 + tools/perf/util/parse-events-hybrid.h | 6 +- tools/perf/util/parse-events.y | 44 +- tools/perf/util/perf_api_probe.c | 19 +- tools/perf/util/perf_regs.c | 669 ++++ tools/perf/util/perf_regs.h | 17 +- tools/perf/util/pmu.c | 68 +- tools/perf/util/record.c | 13 +- .../util/scripting-engines/trace-event-perl.c | 2 + .../scripting-engines/trace-event-python.c | 22 +- tools/perf/util/session.c | 246 +- tools/perf/util/session.h | 10 +- tools/perf/util/smt.c | 73 +- tools/perf/util/sort.c | 40 +- tools/perf/util/stat-display.c | 138 +- tools/perf/util/stat-shadow.c | 383 +- tools/perf/util/stat.c | 47 +- tools/perf/util/svghelper.c | 10 +- tools/perf/util/symbol.c | 37 +- tools/perf/util/synthetic-events.c | 116 +- tools/perf/util/synthetic-events.h | 23 +- tools/perf/util/tool.h | 1 + tools/power/acpi/.gitignore | 1 + tools/power/acpi/Makefile | 16 +- tools/power/acpi/Makefile.config | 1 + tools/power/acpi/Makefile.rules | 3 +- .../x86/intel-speed-select/isst-config.c | 4 +- tools/scripts/Makefile.arch | 3 +- tools/scripts/Makefile.include | 13 +- tools/testing/kunit/kunit.py | 292 +- tools/testing/kunit/kunit_config.py | 53 +- tools/testing/kunit/kunit_json.py | 54 +- tools/testing/kunit/kunit_kernel.py | 183 +- tools/testing/kunit/kunit_parser.py | 1050 ++++-- tools/testing/kunit/kunit_tool_test.py | 362 +- tools/testing/nvdimm/Kbuild | 8 +- tools/testing/nvdimm/test/iomap.c | 39 +- tools/testing/nvdimm/test/ndtest.c | 4 - tools/testing/nvdimm/test/nfit.c | 4 - tools/testing/radix-tree/linux/lockdep.h | 3 + tools/testing/scatterlist/linux/mm.h | 3 +- tools/testing/selftests/Makefile | 3 +- tools/testing/selftests/arm64/Makefile | 2 +- tools/testing/selftests/arm64/fp/.gitignore | 1 + tools/testing/selftests/arm64/fp/Makefile | 10 +- tools/testing/selftests/arm64/fp/TODO | 9 +- tools/testing/selftests/arm64/fp/assembler.h | 11 + .../testing/selftests/arm64/fp/fpsimd-test.S | 164 - tools/testing/selftests/arm64/fp/sve-ptrace.c | 589 ++- tools/testing/selftests/arm64/fp/sve-test.S | 163 - tools/testing/selftests/arm64/fp/vec-syscfg.c | 97 +- .../arm64/signal/test_signals_utils.c | 12 +- tools/testing/selftests/bpf/.gitignore | 5 +- tools/testing/selftests/bpf/Makefile | 139 +- tools/testing/selftests/bpf/README.rst | 28 + tools/testing/selftests/bpf/bench.c | 129 +- tools/testing/selftests/bpf/bench.h | 14 +- .../selftests/bpf/benchs/bench_count.c | 2 +- .../selftests/bpf/benchs/bench_rename.c | 16 +- .../selftests/bpf/benchs/bench_ringbufs.c | 22 +- .../selftests/bpf/benchs/bench_trigger.c | 162 +- .../bpf/benchs/run_bench_ringbufs.sh | 30 +- .../bpf/bpf_testmod/bpf_testmod-events.h | 15 + .../selftests/bpf/bpf_testmod/bpf_testmod.c | 72 +- .../selftests/bpf/bpf_testmod/bpf_testmod.h | 5 + tools/testing/selftests/bpf/btf_helpers.c | 17 +- tools/testing/selftests/bpf/cgroup_helpers.c | 5 +- tools/testing/selftests/bpf/cgroup_helpers.h | 2 +- tools/testing/selftests/bpf/config | 2 + .../selftests/bpf/flow_dissector_load.c | 18 +- .../selftests/bpf/flow_dissector_load.h | 13 +- .../selftests/bpf/get_cgroup_id_user.c | 5 +- .../bpf/map_tests/array_map_batch_ops.c | 13 +- .../bpf/map_tests/htab_map_batch_ops.c | 13 +- .../bpf/map_tests/lpm_trie_map_batch_ops.c | 15 +- .../selftests/bpf/map_tests/sk_storage_map.c | 52 +- .../testing/selftests/bpf/prog_tests/align.c | 202 +- .../selftests/bpf/prog_tests/atomics.c | 39 +- .../selftests/bpf/prog_tests/attach_probe.c | 33 +- .../selftests/bpf/prog_tests/bpf_iter.c | 22 +- .../bpf/prog_tests/bpf_iter_setsockopt.c | 2 +- .../selftests/bpf/prog_tests/bpf_obj_id.c | 8 +- .../selftests/bpf/prog_tests/bpf_tcp_ca.c | 7 +- .../bpf/prog_tests/bpf_verif_scale.c | 263 +- tools/testing/selftests/bpf/prog_tests/btf.c | 833 ++++- .../bpf/prog_tests/btf_dedup_split.c | 119 +- .../selftests/bpf/prog_tests/btf_dump.c | 84 +- .../selftests/bpf/prog_tests/btf_endian.c | 18 +- .../selftests/bpf/prog_tests/btf_split.c | 6 +- .../selftests/bpf/prog_tests/btf_write.c | 175 +- .../bpf/prog_tests/cg_storage_multi.c | 2 +- .../bpf/prog_tests/cgroup_attach_autodetach.c | 4 +- .../bpf/prog_tests/cgroup_attach_multi.c | 16 +- .../bpf/prog_tests/cgroup_attach_override.c | 4 +- .../selftests/bpf/prog_tests/cgroup_link.c | 2 +- .../selftests/bpf/prog_tests/check_mtu.c | 2 +- .../bpf/prog_tests/connect_force_port.c | 35 +- .../selftests/bpf/prog_tests/core_autosize.c | 4 +- .../selftests/bpf/prog_tests/core_reloc.c | 101 +- .../testing/selftests/bpf/prog_tests/d_path.c | 36 +- .../selftests/bpf/prog_tests/fentry_fexit.c | 16 +- .../selftests/bpf/prog_tests/fentry_test.c | 14 +- .../selftests/bpf/prog_tests/fexit_bpf2bpf.c | 71 +- .../selftests/bpf/prog_tests/fexit_sleep.c | 12 +- .../selftests/bpf/prog_tests/fexit_stress.c | 33 +- .../selftests/bpf/prog_tests/fexit_test.c | 14 +- .../selftests/bpf/prog_tests/flow_dissector.c | 4 +- .../prog_tests/flow_dissector_load_bytes.c | 4 +- .../bpf/prog_tests/flow_dissector_reattach.c | 6 +- .../bpf/prog_tests/get_stack_raw_tp.c | 27 +- .../selftests/bpf/prog_tests/global_data.c | 13 +- .../bpf/prog_tests/global_data_init.c | 2 +- .../bpf/prog_tests/global_func_args.c | 2 +- .../selftests/bpf/prog_tests/kfree_skb.c | 69 +- .../selftests/bpf/prog_tests/kfunc_call.c | 30 +- .../selftests/bpf/prog_tests/ksyms_btf.c | 49 +- .../selftests/bpf/prog_tests/ksyms_module.c | 57 +- .../selftests/bpf/prog_tests/l4lb_all.c | 2 +- .../bpf/prog_tests/load_bytes_relative.c | 2 +- .../selftests/bpf/prog_tests/map_lock.c | 4 +- .../selftests/bpf/prog_tests/map_ptr.c | 16 +- .../bpf/prog_tests/migrate_reuseport.c | 2 +- .../selftests/bpf/prog_tests/modify_return.c | 3 +- .../selftests/bpf/prog_tests/module_attach.c | 46 +- .../testing/selftests/bpf/prog_tests/netcnt.c | 2 +- .../bpf/prog_tests/ns_current_pid_tgid.c | 3 +- .../selftests/bpf/prog_tests/perf_buffer.c | 26 +- .../selftests/bpf/prog_tests/perf_link.c | 3 +- .../selftests/bpf/prog_tests/pinning.c | 4 +- .../selftests/bpf/prog_tests/pkt_access.c | 2 +- .../selftests/bpf/prog_tests/pkt_md_access.c | 2 +- .../selftests/bpf/prog_tests/probe_user.c | 7 +- .../bpf/prog_tests/queue_stack_map.c | 14 +- .../raw_tp_writable_reject_nbd_invalid.c | 14 +- .../bpf/prog_tests/raw_tp_writable_test_run.c | 32 +- .../selftests/bpf/prog_tests/rdonly_maps.c | 2 +- .../selftests/bpf/prog_tests/recursion.c | 10 +- .../bpf/prog_tests/reference_tracking.c | 52 +- .../selftests/bpf/prog_tests/resolve_btfids.c | 14 +- .../selftests/bpf/prog_tests/ringbuf.c | 12 +- .../selftests/bpf/prog_tests/ringbuf_multi.c | 4 +- .../bpf/prog_tests/select_reuseport.c | 26 +- .../bpf/prog_tests/send_signal_sched_switch.c | 3 +- .../selftests/bpf/prog_tests/signal_pending.c | 4 +- .../selftests/bpf/prog_tests/sk_assign.c | 2 +- .../selftests/bpf/prog_tests/sk_lookup.c | 32 +- .../bpf/prog_tests/sk_storage_tracing.c | 2 +- .../selftests/bpf/prog_tests/skb_ctx.c | 8 +- .../selftests/bpf/prog_tests/skb_helpers.c | 2 +- .../selftests/bpf/prog_tests/skeleton.c | 35 + .../selftests/bpf/prog_tests/snprintf.c | 4 +- .../selftests/bpf/prog_tests/snprintf_btf.c | 2 +- .../selftests/bpf/prog_tests/sock_fields.c | 3 +- .../selftests/bpf/prog_tests/sockmap_basic.c | 4 +- .../selftests/bpf/prog_tests/sockmap_ktls.c | 2 +- .../selftests/bpf/prog_tests/sockmap_listen.c | 6 +- .../selftests/bpf/prog_tests/sockopt.c | 19 +- .../bpf/prog_tests/sockopt_inherit.c | 27 +- .../selftests/bpf/prog_tests/sockopt_multi.c | 42 +- .../selftests/bpf/prog_tests/spinlock.c | 4 +- .../selftests/bpf/prog_tests/stacktrace_map.c | 6 +- .../bpf/prog_tests/stacktrace_map_raw_tp.c | 6 +- .../selftests/bpf/prog_tests/tailcalls.c | 99 +- .../bpf/prog_tests/task_fd_query_rawtp.c | 2 +- .../bpf/prog_tests/task_fd_query_tp.c | 4 +- .../selftests/bpf/prog_tests/tc_redirect.c | 18 +- .../selftests/bpf/prog_tests/tcp_estats.c | 2 +- .../selftests/bpf/prog_tests/tcp_rtt.c | 21 +- .../selftests/bpf/prog_tests/test_bpffs.c | 89 +- .../bpf/prog_tests/test_global_funcs.c | 28 +- .../bpf/prog_tests/test_local_storage.c | 20 +- .../selftests/bpf/prog_tests/test_overhead.c | 20 +- .../testing/selftests/bpf/prog_tests/timer.c | 3 +- .../selftests/bpf/prog_tests/timer_mim.c | 2 +- .../bpf/prog_tests/tp_attach_query.c | 4 +- .../selftests/bpf/prog_tests/trace_printk.c | 40 +- .../bpf/prog_tests/trampoline_count.c | 9 +- tools/testing/selftests/bpf/prog_tests/xdp.c | 13 +- .../bpf/prog_tests/xdp_adjust_tail.c | 12 +- .../selftests/bpf/prog_tests/xdp_attach.c | 8 +- .../selftests/bpf/prog_tests/xdp_bonding.c | 38 +- .../selftests/bpf/prog_tests/xdp_bpf2bpf.c | 13 +- .../bpf/prog_tests/xdp_cpumap_attach.c | 2 +- .../bpf/prog_tests/xdp_devmap_attach.c | 6 +- .../selftests/bpf/prog_tests/xdp_info.c | 4 +- .../selftests/bpf/prog_tests/xdp_link.c | 63 +- .../selftests/bpf/prog_tests/xdp_perf.c | 2 +- tools/testing/selftests/bpf/progs/atomics.c | 16 + tools/testing/selftests/bpf/progs/bpf_cubic.c | 12 +- tools/testing/selftests/bpf/progs/bpf_flow.c | 3 +- .../selftests/bpf/progs/bpf_iter_unix.c | 2 +- .../selftests/bpf/progs/bpf_tracing_net.h | 2 - .../bpf/progs/btf_dump_test_case_bitfields.c | 10 +- .../bpf/progs/btf_dump_test_case_packing.c | 4 +- .../bpf/progs/btf_dump_test_case_padding.c | 2 +- .../bpf/progs/btf_dump_test_case_syntax.c | 2 +- .../bpf/progs/cg_storage_multi_isolated.c | 4 +- .../bpf/progs/cg_storage_multi_shared.c | 4 +- .../bpf/progs/cgroup_skb_sk_lookup_kern.c | 1 - .../selftests/bpf/progs/connect4_prog.c | 2 - .../selftests/bpf/progs/connect6_prog.c | 2 - .../selftests/bpf/progs/connect_force_port4.c | 1 - .../selftests/bpf/progs/connect_force_port6.c | 1 - .../testing/selftests/bpf/progs/dev_cgroup.c | 1 - .../selftests/bpf/progs/fexit_bpf2bpf.c | 2 +- .../testing/selftests/bpf/progs/fexit_sleep.c | 4 +- .../bpf/progs/for_each_array_map_elem.c | 14 +- .../bpf/progs/for_each_hash_map_elem.c | 2 +- .../selftests/bpf/progs/get_cgroup_id_kern.c | 1 - tools/testing/selftests/bpf/progs/kfree_skb.c | 4 +- .../selftests/bpf/progs/kfunc_call_test.c | 4 +- .../bpf/progs/kfunc_call_test_subprog.c | 2 +- .../selftests/bpf/progs/local_storage.c | 24 +- .../selftests/bpf/progs/map_ptr_kern.c | 17 +- .../testing/selftests/bpf/progs/netcnt_prog.c | 1 - .../selftests/bpf/progs/perf_event_stackmap.c | 4 +- tools/testing/selftests/bpf/progs/pyperf.h | 71 +- tools/testing/selftests/bpf/progs/recursion.c | 9 +- .../selftests/bpf/progs/sendmsg4_prog.c | 2 - .../selftests/bpf/progs/sendmsg6_prog.c | 2 - .../testing/selftests/bpf/progs/skb_pkt_end.c | 2 +- .../selftests/bpf/progs/sockmap_parse_prog.c | 2 - .../bpf/progs/sockmap_tcp_msg_prog.c | 2 - .../bpf/progs/sockmap_verdict_prog.c | 14 +- .../selftests/bpf/progs/sockopt_inherit.c | 1 - .../selftests/bpf/progs/sockopt_multi.c | 5 +- .../testing/selftests/bpf/progs/strobemeta.h | 75 +- tools/testing/selftests/bpf/progs/tailcall1.c | 7 +- tools/testing/selftests/bpf/progs/tailcall2.c | 23 +- tools/testing/selftests/bpf/progs/tailcall3.c | 7 +- tools/testing/selftests/bpf/progs/tailcall4.c | 7 +- tools/testing/selftests/bpf/progs/tailcall5.c | 7 +- .../selftests/bpf/progs/tailcall_bpf2bpf1.c | 7 +- .../selftests/bpf/progs/tailcall_bpf2bpf2.c | 7 +- .../selftests/bpf/progs/tailcall_bpf2bpf3.c | 11 +- .../selftests/bpf/progs/tailcall_bpf2bpf4.c | 15 +- tools/testing/selftests/bpf/progs/tcp_rtt.c | 1 - .../selftests/bpf/progs/test_btf_haskv.c | 2 - .../selftests/bpf/progs/test_btf_map_in_map.c | 14 +- .../selftests/bpf/progs/test_btf_newkv.c | 2 - .../selftests/bpf/progs/test_btf_nokv.c | 2 - .../bpf/progs/test_btf_skc_cls_ingress.c | 2 +- .../selftests/bpf/progs/test_cgroup_link.c | 4 +- .../selftests/bpf/progs/test_check_mtu.c | 12 +- .../selftests/bpf/progs/test_cls_redirect.c | 2 +- .../bpf/progs/test_core_reloc_mods.c | 9 + .../selftests/bpf/progs/test_enable_stats.c | 2 +- .../selftests/bpf/progs/test_global_data.c | 2 +- .../selftests/bpf/progs/test_global_func1.c | 2 +- .../selftests/bpf/progs/test_global_func3.c | 2 +- .../selftests/bpf/progs/test_global_func5.c | 2 +- .../selftests/bpf/progs/test_global_func6.c | 2 +- .../selftests/bpf/progs/test_global_func7.c | 2 +- .../selftests/bpf/progs/test_ksyms_module.c | 46 +- tools/testing/selftests/bpf/progs/test_l4lb.c | 4 +- .../selftests/bpf/progs/test_l4lb_noinline.c | 2 +- .../selftests/bpf/progs/test_map_in_map.c | 13 +- .../bpf/progs/test_map_in_map_invalid.c | 2 +- .../selftests/bpf/progs/test_map_lock.c | 2 +- .../bpf/progs/test_misc_tcp_hdr_options.c | 2 +- .../selftests/bpf/progs/test_module_attach.c | 26 + .../bpf/progs/test_pe_preserve_elems.c | 8 +- .../selftests/bpf/progs/test_perf_buffer.c | 22 +- .../selftests/bpf/progs/test_pinning.c | 2 - .../bpf/progs/test_pinning_invalid.c | 2 - .../selftests/bpf/progs/test_pkt_access.c | 3 +- .../selftests/bpf/progs/test_pkt_md_access.c | 4 +- .../selftests/bpf/progs/test_probe_user.c | 28 +- .../bpf/progs/test_queue_stack_map.h | 4 +- .../bpf/progs/test_select_reuseport_kern.c | 6 +- .../selftests/bpf/progs/test_sk_assign.c | 3 +- .../selftests/bpf/progs/test_sk_lookup.c | 53 +- .../selftests/bpf/progs/test_sk_lookup_kern.c | 37 +- .../bpf/progs/test_sk_storage_tracing.c | 2 +- .../bpf/progs/test_skb_cgroup_id_kern.c | 2 - .../selftests/bpf/progs/test_skb_ctx.c | 9 +- .../selftests/bpf/progs/test_skb_helpers.c | 2 +- .../selftests/bpf/progs/test_skeleton.c | 18 + .../selftests/bpf/progs/test_sockmap_kern.h | 1 - .../selftests/bpf/progs/test_sockmap_listen.c | 3 +- .../progs/test_sockmap_skb_verdict_attach.c | 2 +- .../selftests/bpf/progs/test_sockmap_update.c | 2 +- .../selftests/bpf/progs/test_spin_lock.c | 2 +- .../bpf/progs/test_stacktrace_build_id.c | 5 +- .../selftests/bpf/progs/test_stacktrace_map.c | 10 +- .../testing/selftests/bpf/progs/test_tc_bpf.c | 2 +- .../selftests/bpf/progs/test_tc_neigh.c | 6 +- .../selftests/bpf/progs/test_tc_neigh_fib.c | 6 +- .../selftests/bpf/progs/test_tc_peer.c | 10 +- .../bpf/progs/test_tcp_check_syncookie_kern.c | 4 +- .../selftests/bpf/progs/test_tcp_estats.c | 3 +- .../bpf/progs/test_tcp_hdr_options.c | 2 +- .../selftests/bpf/progs/test_tcpbpf_kern.c | 1 - .../selftests/bpf/progs/test_tcpnotify_kern.c | 6 +- .../selftests/bpf/progs/test_tracepoint.c | 7 +- .../selftests/bpf/progs/test_tunnel_kern.c | 2 - .../selftests/bpf/progs/test_verif_scale2.c | 4 +- tools/testing/selftests/bpf/progs/test_xdp.c | 4 +- .../bpf/progs/test_xdp_adjust_tail_grow.c | 2 +- .../bpf/progs/test_xdp_adjust_tail_shrink.c | 4 +- .../selftests/bpf/progs/test_xdp_bpf2bpf.c | 4 +- .../bpf/progs/test_xdp_devmap_helpers.c | 2 +- .../selftests/bpf/progs/test_xdp_link.c | 8 +- .../selftests/bpf/progs/test_xdp_loop.c | 4 +- .../selftests/bpf/progs/test_xdp_noinline.c | 4 +- .../selftests/bpf/progs/test_xdp_redirect.c | 2 - .../bpf/progs/test_xdp_with_cpumap_helpers.c | 4 +- .../bpf/progs/test_xdp_with_devmap_helpers.c | 4 +- .../selftests/bpf/progs/trigger_bench.c | 7 + tools/testing/selftests/bpf/progs/xdp_dummy.c | 2 +- .../bpf/progs/xdp_redirect_multi_kern.c | 4 +- .../testing/selftests/bpf/progs/xdping_kern.c | 4 +- tools/testing/selftests/bpf/test_bpftool.py | 22 +- .../selftests/bpf/test_bpftool_build.sh | 4 + .../selftests/bpf/test_bpftool_synctypes.py | 94 +- tools/testing/selftests/bpf/test_btf.h | 6 + .../selftests/bpf/test_cgroup_storage.c | 11 +- tools/testing/selftests/bpf/test_cpp.cpp | 9 +- tools/testing/selftests/bpf/test_dev_cgroup.c | 3 +- .../selftests/bpf/test_flow_dissector.sh | 10 +- .../selftests/bpf/test_lirc_mode2_user.c | 7 +- tools/testing/selftests/bpf/test_lpm_map.c | 27 +- tools/testing/selftests/bpf/test_lru_map.c | 25 +- tools/testing/selftests/bpf/test_maps.c | 118 +- tools/testing/selftests/bpf/test_progs.c | 712 +++- tools/testing/selftests/bpf/test_progs.h | 40 +- tools/testing/selftests/bpf/test_sock.c | 389 +- tools/testing/selftests/bpf/test_sock_addr.c | 50 +- tools/testing/selftests/bpf/test_sockmap.c | 35 +- tools/testing/selftests/bpf/test_sysctl.c | 27 +- tools/testing/selftests/bpf/test_tag.c | 8 +- .../selftests/bpf/test_tcp_check_syncookie.sh | 4 +- .../selftests/bpf/test_tcpnotify_user.c | 7 +- tools/testing/selftests/bpf/test_tunnel.sh | 5 +- tools/testing/selftests/bpf/test_verifier.c | 152 +- tools/testing/selftests/bpf/test_xdp_meta.sh | 5 +- .../selftests/bpf/test_xdp_redirect.sh | 4 +- .../selftests/bpf/test_xdp_redirect_multi.sh | 2 +- tools/testing/selftests/bpf/test_xdp_veth.sh | 4 +- tools/testing/selftests/bpf/test_xdp_vlan.sh | 7 +- tools/testing/selftests/bpf/testing_helpers.c | 62 + tools/testing/selftests/bpf/testing_helpers.h | 6 + tools/testing/selftests/bpf/trace_helpers.c | 1 + .../selftests/bpf/verifier/atomic_cmpxchg.c | 42 +- tools/testing/selftests/bpf/verifier/calls.c | 23 + .../selftests/bpf/verifier/ctx_sk_lookup.c | 32 + .../testing/selftests/bpf/verifier/ctx_skb.c | 74 +- tools/testing/selftests/bpf/verifier/jit.c | 69 +- tools/testing/selftests/bpf/verifier/lwt.c | 2 +- .../selftests/bpf/verifier/map_in_map.c | 34 + .../bpf/verifier/perf_event_sample_period.c | 6 +- .../selftests/bpf/verifier/search_pruning.c | 71 + .../selftests/bpf/verifier/spill_fill.c | 238 ++ .../selftests/bpf/verifier/value_ptr_arith.c | 2 +- tools/testing/selftests/bpf/vmtest.sh | 50 +- .../selftests/bpf/xdp_redirect_multi.c | 15 +- tools/testing/selftests/bpf/xdping.c | 10 +- tools/testing/selftests/bpf/xdpxceiver.c | 981 +++-- tools/testing/selftests/bpf/xdpxceiver.h | 75 +- tools/testing/selftests/cgroup/Makefile | 12 +- tools/testing/selftests/cgroup/cgroup_util.h | 4 +- tools/testing/selftests/cgroup/test_core.c | 165 + .../testing/selftests/core/close_range_test.c | 4 - tools/testing/selftests/cpufreq/main.sh | 2 +- tools/testing/selftests/damon/Makefile | 5 +- .../testing/selftests/damon/debugfs_attrs.sh | 78 +- .../drivers/net/mlxsw/devlink_trap_control.sh | 7 +- .../drivers/net/mlxsw/devlink_trap_policer.sh | 32 +- .../net/mlxsw/devlink_trap_tunnel_ipip.sh | 50 +- .../net/mlxsw/devlink_trap_tunnel_vxlan.sh | 7 +- .../selftests/drivers/net/mlxsw/mlxsw_lib.sh | 50 + .../selftests/drivers/net/mlxsw/rtnetlink.sh | 112 +- .../drivers/net/mlxsw/sch_red_core.sh | 129 +- .../drivers/net/mlxsw/sch_red_ets.sh | 66 +- .../drivers/net/mlxsw/sch_red_root.sh | 8 + .../net/mlxsw/spectrum-2/resource_scale.sh | 9 +- .../mlxsw/spectrum/devlink_lib_spectrum.sh | 6 +- .../net/mlxsw/spectrum/resource_scale.sh | 2 +- .../drivers/net/mlxsw/tc_restrictions.sh | 3 +- .../selftests/drivers/net/mlxsw/tc_sample.sh | 13 +- .../selftests/drivers/net/mlxsw/vxlan.sh | 242 +- .../drivers/net/mlxsw/vxlan_fdb_veto.sh | 39 +- .../drivers/net/netdevsim/ethtool-common.sh | 2 +- .../drivers/net/ocelot/tc_flower_chains.sh | 50 +- tools/testing/selftests/ftrace/ftracetest | 2 +- .../testing/selftests/ftrace/test.d/functions | 12 + .../test.d/kprobe/kprobe_args_string.tc | 3 + .../test.d/kprobe/kprobe_args_syntax.tc | 4 + .../selftests/futex/functional/.gitignore | 1 + .../selftests/futex/functional/Makefile | 3 +- .../futex/functional/futex_wait_timeout.c | 21 +- .../futex/functional/futex_wait_wouldblock.c | 41 +- .../testing/selftests/futex/functional/run.sh | 3 + tools/testing/selftests/gpio/.gitignore | 2 + tools/testing/selftests/gpio/Makefile | 6 +- tools/testing/selftests/gpio/config | 1 + .../testing/selftests/gpio/gpio-mockup-cdev.c | 2 +- tools/testing/selftests/ir/ir_loopback.c | 11 +- tools/testing/selftests/kexec/Makefile | 2 +- .../selftests/kexec/kexec_common_lib.sh | 51 +- .../selftests/kexec/test_kexec_file_load.sh | 13 +- tools/testing/selftests/kselftest.h | 4 + tools/testing/selftests/kselftest/runner.sh | 28 +- tools/testing/selftests/kselftest_harness.h | 2 + tools/testing/selftests/kvm/.gitignore | 12 +- tools/testing/selftests/kvm/Makefile | 32 +- .../selftests/kvm/aarch64/arch_timer.c | 7 +- .../selftests/kvm/aarch64/debug-exceptions.c | 30 +- .../selftests/kvm/aarch64/get-reg-list.c | 50 + .../selftests/kvm/aarch64/psci_cpu_on_test.c | 2 +- .../testing/selftests/kvm/aarch64/vgic_init.c | 369 +- .../testing/selftests/kvm/aarch64/vgic_irq.c | 4 + .../selftests/kvm/access_tracking_perf_test.c | 54 +- .../selftests/kvm/demand_paging_test.c | 56 +- .../selftests/kvm/dirty_log_perf_test.c | 29 +- tools/testing/selftests/kvm/dirty_log_test.c | 6 +- .../selftests/kvm/include/aarch64/processor.h | 93 +- .../testing/selftests/kvm/include/kvm_util.h | 395 +- .../selftests/kvm/include/perf_test_util.h | 23 +- .../testing/selftests/kvm/include/test_util.h | 26 + .../selftests/kvm/include/x86_64/processor.h | 52 +- .../selftests/kvm/include/x86_64/svm_util.h | 2 + .../selftests/kvm/kvm_create_max_vcpus.c | 2 +- .../selftests/kvm/kvm_page_table_test.c | 2 +- .../selftests/kvm/lib/aarch64/processor.c | 108 +- .../testing/selftests/kvm/lib/aarch64/vgic.c | 4 +- tools/testing/selftests/kvm/lib/elf.c | 3 +- tools/testing/selftests/kvm/lib/guest_modes.c | 59 +- tools/testing/selftests/kvm/lib/kvm_util.c | 237 +- .../selftests/kvm/lib/perf_test_util.c | 186 +- tools/testing/selftests/kvm/lib/sparsebit.c | 2 +- tools/testing/selftests/kvm/lib/test_util.c | 5 + .../selftests/kvm/lib/x86_64/processor.c | 248 +- tools/testing/selftests/kvm/lib/x86_64/svm.c | 13 + .../kvm/memslot_modification_stress_test.c | 38 +- .../testing/selftests/kvm/memslot_perf_test.c | 56 +- .../kvm/x86_64/cr4_cpuid_sync_test.c | 3 +- .../testing/selftests/kvm/x86_64/evmcs_test.c | 2 +- .../selftests/kvm/x86_64/hyperv_features.c | 140 +- tools/testing/selftests/kvm/x86_64/smm_test.c | 2 +- .../testing/selftests/kvm/x86_64/state_test.c | 2 +- .../selftests/kvm/x86_64/svm_int_ctl_test.c | 2 +- .../selftests/kvm/x86_64/tsc_msrs_test.c | 4 +- .../kvm/x86_64/vmx_close_while_nested_test.c | 4 +- .../selftests/kvm/x86_64/vmx_pmu_msrs_test.c | 17 - .../kvm/x86_64/vmx_preemption_timer_test.c | 2 +- .../selftests/kvm/x86_64/xen_shinfo_test.c | 283 +- tools/testing/selftests/landlock/common.h | 4 - tools/testing/selftests/lkdtm/config | 1 + tools/testing/selftests/lkdtm/run.sh | 10 +- .../testing/selftests/lkdtm/stack-entropy.sh | 16 +- tools/testing/selftests/lkdtm/tests.txt | 1 + tools/testing/selftests/memory-hotplug/config | 1 - .../mount/unprivileged-remount-test.c | 4 +- .../move_mount_set_group_test.c | 10 +- tools/testing/selftests/net/.gitignore | 5 + tools/testing/selftests/net/Makefile | 4 + tools/testing/selftests/net/config | 1 + tools/testing/selftests/net/fcnal-test.sh | 53 +- tools/testing/selftests/net/fib_nexthops.sh | 63 + tools/testing/selftests/net/forwarding/config | 1 + .../selftests/net/forwarding/devlink_lib.sh | 6 - .../net/forwarding/forwarding.config.sample | 4 + tools/testing/selftests/net/forwarding/lib.sh | 26 +- .../forwarding/mirror_gre_bridge_1d_vlan.sh | 2 +- .../net/forwarding/mirror_gre_changes.sh | 2 +- .../forwarding/mirror_gre_vlan_bridge_1q.sh | 13 +- .../selftests/net/forwarding/mirror_lib.sh | 3 +- .../selftests/net/forwarding/mirror_vlan.sh | 4 +- .../net/forwarding/sch_tbf_etsprio.sh | 28 + .../selftests/net/forwarding/tc_actions.sh | 47 +- .../selftests/net/forwarding/tc_common.sh | 10 + .../net/forwarding/vxlan_bridge_1q.sh | 20 - tools/testing/selftests/net/gro.c | 41 +- tools/testing/selftests/net/ioam6.sh | 208 +- tools/testing/selftests/net/ioam6_parser.c | 5 +- tools/testing/selftests/net/ipsec.c | 1 - tools/testing/selftests/net/mptcp/.gitignore | 2 + tools/testing/selftests/net/mptcp/Makefile | 2 +- tools/testing/selftests/net/mptcp/config | 10 +- .../selftests/net/mptcp/mptcp_connect.c | 418 ++- .../selftests/net/mptcp/mptcp_connect.sh | 139 +- .../testing/selftests/net/mptcp/mptcp_join.sh | 224 +- .../selftests/net/mptcp/mptcp_sockopt.sh | 75 +- .../selftests/net/mptcp/simult_flows.sh | 36 +- tools/testing/selftests/net/nettest.c | 33 +- tools/testing/selftests/net/reuseport_bpf.c | 4 +- .../selftests/net/reuseport_bpf_numa.c | 4 + tools/testing/selftests/net/rxtimestamp.c | 2 +- tools/testing/selftests/net/settings | 2 +- tools/testing/selftests/net/socket.c | 3 +- .../selftests/net/tcp_fastopen_backup_key.c | 6 +- .../selftests/net/test_vxlan_under_vrf.sh | 2 + tools/testing/selftests/net/tls.c | 604 ++- tools/testing/selftests/netfilter/.gitignore | 1 + tools/testing/selftests/netfilter/Makefile | 4 +- .../selftests/netfilter/connect_close.c | 136 + .../selftests/netfilter/ipip-conntrack-mtu.sh | 9 +- .../selftests/netfilter/nf_nat_edemux.sh | 10 +- .../selftests/netfilter/nft_concat_range.sh | 24 +- tools/testing/selftests/netfilter/nft_nat.sh | 35 +- .../testing/selftests/netfilter/nft_queue.sh | 73 + .../selftests/netfilter/nft_zones_many.sh | 29 +- .../selftests/perf_events/sigtrap_threads.c | 17 +- .../powerpc/security/mitigation-patching.sh | 9 +- .../selftests/powerpc/signal/.gitignore | 1 + .../testing/selftests/powerpc/signal/Makefile | 1 + tools/testing/selftests/proc/.gitignore | 1 + tools/testing/selftests/proc/Makefile | 2 + .../rcutorture/bin/kvm-find-errors.sh | 4 +- .../rcutorture/bin/kvm-recheck-rcu.sh | 2 +- .../selftests/rcutorture/bin/kvm-remote.sh | 24 +- tools/testing/selftests/rcutorture/bin/kvm.sh | 11 +- .../selftests/rcutorture/bin/parse-build.sh | 3 +- .../selftests/rcutorture/bin/torture.sh | 11 +- .../selftests/rcutorture/configs/rcu/SRCU-t | 1 + .../selftests/rcutorture/configs/rcu/SRCU-u | 1 + .../rcutorture/configs/rcu/TASKS01.boot | 1 + .../selftests/rcutorture/configs/rcu/TINY01 | 1 + .../selftests/rcutorture/configs/rcu/TINY02 | 1 + .../rcutorture/configs/rcu/TRACE01.boot | 1 + .../rcutorture/configs/rcu/TRACE02.boot | 1 + .../selftests/rcutorture/configs/rcu/TREE01 | 1 - .../selftests/rcutorture/configs/rcu/TREE02 | 1 - .../selftests/rcutorture/configs/rcu/TREE04 | 1 - .../selftests/rcutorture/configs/rcu/TREE05 | 1 - .../selftests/rcutorture/configs/rcu/TREE06 | 1 - .../selftests/rcutorture/configs/rcu/TREE07 | 1 - .../selftests/rcutorture/configs/rcu/TREE08 | 1 - .../selftests/rcutorture/configs/rcu/TREE10 | 1 - .../rcutorture/configs/rcuscale/TINY | 2 +- .../rcutorture/configs/rcuscale/TRACE01 | 1 - .../rcutorture/configs/rcuscale/TREE | 1 - .../rcutorture/configs/rcuscale/TREE54 | 1 - .../rcutorture/configs/refscale/NOPREEMPT | 1 - .../rcutorture/configs/refscale/PREEMPT | 1 - .../rcutorture/doc/TREE_RCU-kconfig.txt | 1 - .../selftests/rseq/basic_percpu_ops_test.c | 3 +- tools/testing/selftests/rseq/rseq.c | 3 +- .../selftests/seccomp/seccomp_benchmark.c | 2 +- tools/testing/selftests/seccomp/seccomp_bpf.c | 64 +- tools/testing/selftests/sgx/Makefile | 2 +- tools/testing/selftests/sgx/defines.h | 33 +- tools/testing/selftests/sgx/load.c | 40 +- tools/testing/selftests/sgx/main.c | 358 +- tools/testing/selftests/sgx/main.h | 6 +- tools/testing/selftests/sgx/sigstruct.c | 12 +- tools/testing/selftests/sgx/test_encl.c | 60 +- .../selftests/sgx/test_encl_bootstrap.S | 21 +- .../selftests/sparc64/drivers/adi-test.c | 4 - tools/testing/selftests/tc-testing/config | 2 + .../tc-testing/tc-tests/actions/bpf.json | 2 +- .../tc-testing/tc-tests/actions/police.json | 24 + .../tc-testing/tc-tests/filters/matchall.json | 72 + .../tc-testing/tc-tests/qdiscs/mq.json | 12 +- tools/testing/selftests/tc-testing/tdc.py | 8 +- tools/testing/selftests/tc-testing/tdc.sh | 1 + tools/testing/selftests/timens/procfs.c | 2 - tools/testing/selftests/timens/timens.c | 2 - .../selftests/timers/alarmtimer-suspend.c | 2 +- .../selftests/timers/inconsistency-check.c | 2 +- tools/testing/selftests/vm/.gitignore | 1 + tools/testing/selftests/vm/Makefile | 7 +- tools/testing/selftests/vm/hugepage-mremap.c | 26 +- tools/testing/selftests/vm/ksm_tests.c | 154 +- tools/testing/selftests/vm/madv_populate.c | 15 +- tools/testing/selftests/vm/mremap_test.c | 1 - tools/testing/selftests/vm/pkey-helpers.h | 3 +- tools/testing/selftests/vm/run_vmtests.sh | 12 + tools/testing/selftests/vm/userfaultfd.c | 179 +- tools/testing/selftests/vm/va_128TBswitch.c | 2 +- tools/testing/selftests/x86/Makefile | 2 +- tools/thermal/tmon/pid.c | 3 +- tools/tracing/Makefile | 18 +- tools/virtio/linux/mm_types.h | 3 + tools/virtio/virtio_test.c | 1 + usr/Makefile | 7 +- usr/gen_init_cpio.c | 20 +- usr/include/Makefile | 6 +- virt/kvm/Kconfig | 6 + virt/kvm/async_pf.c | 2 +- virt/kvm/dirty_ring.c | 11 +- virt/kvm/eventfd.c | 15 +- virt/kvm/kvm_main.c | 1438 +++---- 897 files changed, 27571 insertions(+), 12462 deletions(-) create mode 100644 tools/testing/selftests/netfilter/connect_close.c create mode 100644 tools/virtio/linux/mm_types.h diff --git a/tools/accounting/getdelays.c b/tools/accounting/getdelays.c index 5ef1c15e88..11e8673945 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/bootconfig/Makefile b/tools/bootconfig/Makefile index da59757753..566c3e0ee5 100644 --- a/tools/bootconfig/Makefile +++ b/tools/bootconfig/Makefile @@ -15,9 +15,9 @@ CFLAGS = -Wall -g -I$(CURDIR)/include ALL_TARGETS := bootconfig ALL_PROGRAMS := $(patsubst %,$(OUTPUT)%,$(ALL_TARGETS)) -all: $(ALL_PROGRAMS) +all: $(ALL_PROGRAMS) test -$(OUTPUT)bootconfig: main.c $(LIBSRC) +$(OUTPUT)bootconfig: main.c include/linux/bootconfig.h $(LIBSRC) $(CC) $(filter %.c,$^) $(CFLAGS) -o $@ test: $(ALL_PROGRAMS) test-bootconfig.sh diff --git a/tools/bootconfig/include/linux/bootconfig.h b/tools/bootconfig/include/linux/bootconfig.h index de7f30f99a..6784296a06 100644 --- a/tools/bootconfig/include/linux/bootconfig.h +++ b/tools/bootconfig/include/linux/bootconfig.h @@ -2,10 +2,53 @@ #ifndef _BOOTCONFIG_LINUX_BOOTCONFIG_H #define _BOOTCONFIG_LINUX_BOOTCONFIG_H -#include "../../../../include/linux/bootconfig.h" +#include +#include +#include +#include +#include +#include +#include + #ifndef fallthrough # define fallthrough #endif +#define WARN_ON(cond) \ + ((cond) ? printf("Internal warning(%s:%d, %s): %s\n", \ + __FILE__, __LINE__, __func__, #cond) : 0) + +#define unlikely(cond) (cond) + +/* Copied from lib/string.c */ +static inline char *skip_spaces(const char *str) +{ + while (isspace(*str)) + ++str; + return (char *)str; +} + +static inline char *strim(char *s) +{ + size_t size; + char *end; + + size = strlen(s); + if (!size) + return s; + + end = s + size - 1; + while (end >= s && isspace(*end)) + end--; + *(end + 1) = '\0'; + + return skip_spaces(s); +} + +#define __init +#define __initdata + +#include "../../../../include/linux/bootconfig.h" + #endif diff --git a/tools/bootconfig/main.c b/tools/bootconfig/main.c index fd67496a94..156b62a163 100644 --- a/tools/bootconfig/main.c +++ b/tools/bootconfig/main.c @@ -12,9 +12,10 @@ #include #include -#include #include +#define pr_err(fmt, ...) fprintf(stderr, fmt, ##__VA_ARGS__) + static int xbc_show_value(struct xbc_node *node, bool semicolon) { const char *val, *eol; @@ -176,7 +177,7 @@ static int load_xbc_from_initrd(int fd, char **buf) { struct stat stat; int ret; - u32 size = 0, csum = 0, rcsum; + uint32_t size = 0, csum = 0, rcsum; char magic[BOOTCONFIG_MAGIC_LEN]; const char *msg; @@ -200,11 +201,11 @@ static int load_xbc_from_initrd(int fd, char **buf) if (lseek(fd, -(8 + BOOTCONFIG_MAGIC_LEN), SEEK_END) < 0) return pr_errno("Failed to lseek for size", -errno); - if (read(fd, &size, sizeof(u32)) < 0) + if (read(fd, &size, sizeof(uint32_t)) < 0) return pr_errno("Failed to read size", -errno); size = le32toh(size); - if (read(fd, &csum, sizeof(u32)) < 0) + if (read(fd, &csum, sizeof(uint32_t)) < 0) return pr_errno("Failed to read checksum", -errno); csum = le32toh(csum); @@ -229,7 +230,7 @@ static int load_xbc_from_initrd(int fd, char **buf) return -EINVAL; } - ret = xbc_init(*buf, &msg, NULL); + ret = xbc_init(*buf, size, &msg, NULL); /* Wrong data */ if (ret < 0) { pr_err("parse error: %s.\n", msg); @@ -269,7 +270,7 @@ static int init_xbc_with_error(char *buf, int len) if (!copy) return -ENOMEM; - ret = xbc_init(buf, &msg, &pos); + ret = xbc_init(buf, len, &msg, &pos); if (ret < 0) show_xbc_error(copy, msg, pos); free(copy); @@ -362,7 +363,7 @@ static int apply_xbc(const char *path, const char *xbc_path) size_t total_size; struct stat stat; const char *msg; - u32 size, csum; + uint32_t size, csum; int pos, pad; int ret, fd; @@ -376,13 +377,13 @@ static int apply_xbc(const char *path, const char *xbc_path) /* Backup the bootconfig data */ data = calloc(size + BOOTCONFIG_ALIGN + - sizeof(u32) + sizeof(u32) + BOOTCONFIG_MAGIC_LEN, 1); + sizeof(uint32_t) + sizeof(uint32_t) + BOOTCONFIG_MAGIC_LEN, 1); if (!data) return -ENOMEM; memcpy(data, buf, size); /* Check the data format */ - ret = xbc_init(buf, &msg, &pos); + ret = xbc_init(buf, size, &msg, &pos); if (ret < 0) { show_xbc_error(data, msg, pos); free(data); @@ -391,12 +392,13 @@ static int apply_xbc(const char *path, const char *xbc_path) return ret; } printf("Apply %s to %s\n", xbc_path, path); + xbc_get_info(&ret, NULL); printf("\tNumber of nodes: %d\n", ret); printf("\tSize: %u bytes\n", (unsigned int)size); printf("\tChecksum: %d\n", (unsigned int)csum); /* TODO: Check the options by schema */ - xbc_destroy_all(); + xbc_exit(); free(buf); /* Remove old boot config if exists */ @@ -423,17 +425,17 @@ static int apply_xbc(const char *path, const char *xbc_path) } /* To align up the total size to BOOTCONFIG_ALIGN, get padding size */ - total_size = stat.st_size + size + sizeof(u32) * 2 + BOOTCONFIG_MAGIC_LEN; + total_size = stat.st_size + size + sizeof(uint32_t) * 2 + BOOTCONFIG_MAGIC_LEN; pad = ((total_size + BOOTCONFIG_ALIGN - 1) & (~BOOTCONFIG_ALIGN_MASK)) - total_size; size += pad; /* Add a footer */ p = data + size; - *(u32 *)p = htole32(size); - p += sizeof(u32); + *(uint32_t *)p = htole32(size); + p += sizeof(uint32_t); - *(u32 *)p = htole32(csum); - p += sizeof(u32); + *(uint32_t *)p = htole32(csum); + p += sizeof(uint32_t); memcpy(p, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN); p += BOOTCONFIG_MAGIC_LEN; diff --git a/tools/bpf/bpftool/.gitignore b/tools/bpf/bpftool/.gitignore index 05ce4446b7..a736f64dc5 100644 --- a/tools/bpf/bpftool/.gitignore +++ b/tools/bpf/bpftool/.gitignore @@ -1,4 +1,4 @@ -# SPDX-License-Identifier: GPL-2.0-only +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) *.d /bootstrap/ /bpftool diff --git a/tools/bpf/bpftool/Documentation/Makefile b/tools/bpf/bpftool/Documentation/Makefile index f89929c703..ac8487dcff 100644 --- a/tools/bpf/bpftool/Documentation/Makefile +++ b/tools/bpf/bpftool/Documentation/Makefile @@ -1,4 +1,4 @@ -# SPDX-License-Identifier: GPL-2.0-only +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) include ../../../scripts/Makefile.include INSTALL ?= install @@ -24,7 +24,7 @@ man: man8 man8: $(DOC_MAN8) RST2MAN_DEP := $(shell command -v rst2man 2>/dev/null) -RST2MAN_OPTS += --verbose +RST2MAN_OPTS += --verbose --strip-comments list_pages = $(sort $(basename $(filter-out $(1),$(MAN8_RST)))) see_also = $(subst " ",, \ diff --git a/tools/bpf/bpftool/Documentation/bpftool-btf.rst b/tools/bpf/bpftool/Documentation/bpftool-btf.rst index 4425d942dd..342716f74e 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-btf.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-btf.rst @@ -1,3 +1,5 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + ================ bpftool-btf ================ @@ -7,13 +9,14 @@ tool for inspection of BTF data :Manual section: 8 +.. include:: substitutions.rst + SYNOPSIS ======== **bpftool** [*OPTIONS*] **btf** *COMMAND* - *OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] | {**-d** | **--debug** } | - { **-B** | **--base-btf** } } + *OPTIONS* := { |COMMON_OPTIONS| | { **-B** | **--base-btf** } } *COMMANDS* := { **dump** | **help** } diff --git a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst index 13a217a250..a17e9aa314 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst @@ -1,3 +1,5 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + ================ bpftool-cgroup ================ @@ -7,13 +9,14 @@ tool for inspection and simple manipulation of eBPF progs :Manual section: 8 +.. include:: substitutions.rst + SYNOPSIS ======== **bpftool** [*OPTIONS*] **cgroup** *COMMAND* - *OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-d** | **--debug** } | - { **-f** | **--bpffs** } } + *OPTIONS* := { |COMMON_OPTIONS| | { **-f** | **--bpffs** } } *COMMANDS* := { **show** | **list** | **tree** | **attach** | **detach** | **help** } @@ -30,9 +33,9 @@ CGROUP COMMANDS | *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* } | *ATTACH_TYPE* := { **ingress** | **egress** | **sock_create** | **sock_ops** | **device** | | **bind4** | **bind6** | **post_bind4** | **post_bind6** | **connect4** | **connect6** | -| **getpeername4** | **getpeername6** | **getsockname4** | **getsockname6** | **sendmsg4** | -| **sendmsg6** | **recvmsg4** | **recvmsg6** | **sysctl** | **getsockopt** | **setsockopt** | -| **sock_release** } +| **getpeername4** | **getpeername6** | **getsockname4** | **getsockname6** | **sendmsg4** | +| **sendmsg6** | **recvmsg4** | **recvmsg6** | **sysctl** | **getsockopt** | **setsockopt** | +| **sock_release** } | *ATTACH_FLAGS* := { **multi** | **override** } DESCRIPTION @@ -98,9 +101,9 @@ DESCRIPTION **sendmsg6** call to sendto(2), sendmsg(2), sendmmsg(2) for an unconnected udp6 socket (since 4.18); **recvmsg4** call to recvfrom(2), recvmsg(2), recvmmsg(2) for - an unconnected udp4 socket (since 5.2); + an unconnected udp4 socket (since 5.2); **recvmsg6** call to recvfrom(2), recvmsg(2), recvmmsg(2) for - an unconnected udp6 socket (since 5.2); + an unconnected udp6 socket (since 5.2); **sysctl** sysctl access (since 5.2); **getsockopt** call to getsockopt (since 5.3); **setsockopt** call to setsockopt (since 5.3); diff --git a/tools/bpf/bpftool/Documentation/bpftool-feature.rst b/tools/bpf/bpftool/Documentation/bpftool-feature.rst index ab9f57ee4c..4ce9a77bc1 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-feature.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-feature.rst @@ -1,3 +1,5 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + =============== bpftool-feature =============== @@ -7,12 +9,14 @@ tool for inspection of eBPF-related parameters for Linux kernel or net device :Manual section: 8 +.. include:: substitutions.rst + SYNOPSIS ======== **bpftool** [*OPTIONS*] **feature** *COMMAND* - *OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-d** | **--debug** } } + *OPTIONS* := { |COMMON_OPTIONS| } *COMMANDS* := { **probe** | **help** } diff --git a/tools/bpf/bpftool/Documentation/bpftool-gen.rst b/tools/bpf/bpftool/Documentation/bpftool-gen.rst index 2a137f8a4c..bc276388f4 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-gen.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-gen.rst @@ -1,3 +1,5 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + ================ bpftool-gen ================ @@ -7,13 +9,14 @@ tool for BPF code-generation :Manual section: 8 +.. include:: substitutions.rst + SYNOPSIS ======== **bpftool** [*OPTIONS*] **gen** *COMMAND* - *OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-d** | **--debug** } | - { **-L** | **--use-loader** } } + *OPTIONS* := { |COMMON_OPTIONS| | { **-L** | **--use-loader** } } *COMMAND* := { **object** | **skeleton** | **help** } diff --git a/tools/bpf/bpftool/Documentation/bpftool-iter.rst b/tools/bpf/bpftool/Documentation/bpftool-iter.rst index 471f363a72..84839d4886 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-iter.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-iter.rst @@ -1,3 +1,5 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + ============ bpftool-iter ============ @@ -7,12 +9,14 @@ tool to create BPF iterators :Manual section: 8 +.. include:: substitutions.rst + SYNOPSIS ======== **bpftool** [*OPTIONS*] **iter** *COMMAND* - *OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-d** | **--debug** } } + *OPTIONS* := { |COMMON_OPTIONS| } *COMMANDS* := { **pin** | **help** } diff --git a/tools/bpf/bpftool/Documentation/bpftool-link.rst b/tools/bpf/bpftool/Documentation/bpftool-link.rst index 9434349636..52a4eee4af 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-link.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-link.rst @@ -1,3 +1,5 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + ================ bpftool-link ================ @@ -7,13 +9,14 @@ tool for inspection and simple manipulation of eBPF links :Manual section: 8 +.. include:: substitutions.rst + SYNOPSIS ======== **bpftool** [*OPTIONS*] **link** *COMMAND* - *OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-d** | **--debug** } | - { **-f** | **--bpffs** } | { **-n** | **--nomount** } } + *OPTIONS* := { |COMMON_OPTIONS| | { **-f** | **--bpffs** } | { **-n** | **--nomount** } } *COMMANDS* := { **show** | **list** | **pin** | **help** } diff --git a/tools/bpf/bpftool/Documentation/bpftool-map.rst b/tools/bpf/bpftool/Documentation/bpftool-map.rst index 1445cadc15..7c188a5984 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-map.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst @@ -1,3 +1,5 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + ================ bpftool-map ================ @@ -7,13 +9,14 @@ tool for inspection and simple manipulation of eBPF maps :Manual section: 8 +.. include:: substitutions.rst + SYNOPSIS ======== **bpftool** [*OPTIONS*] **map** *COMMAND* - *OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-d** | **--debug** } | - { **-f** | **--bpffs** } | { **-n** | **--nomount** } } + *OPTIONS* := { |COMMON_OPTIONS| | { **-f** | **--bpffs** } | { **-n** | **--nomount** } } *COMMANDS* := { **show** | **list** | **create** | **dump** | **update** | **lookup** | **getnext** | @@ -52,7 +55,7 @@ MAP COMMANDS | | **devmap** | **devmap_hash** | **sockmap** | **cpumap** | **xskmap** | **sockhash** | | **cgroup_storage** | **reuseport_sockarray** | **percpu_cgroup_storage** | | **queue** | **stack** | **sk_storage** | **struct_ops** | **ringbuf** | **inode_storage** - | **task_storage** } +| | **task_storage** | **bloom_filter** } DESCRIPTION =========== diff --git a/tools/bpf/bpftool/Documentation/bpftool-net.rst b/tools/bpf/bpftool/Documentation/bpftool-net.rst index 1ae0375e8f..f4e0a51633 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-net.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-net.rst @@ -1,3 +1,5 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + ================ bpftool-net ================ @@ -7,12 +9,14 @@ tool for inspection of netdev/tc related bpf prog attachments :Manual section: 8 +.. include:: substitutions.rst + SYNOPSIS ======== **bpftool** [*OPTIONS*] **net** *COMMAND* - *OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-d** | **--debug** } } + *OPTIONS* := { |COMMON_OPTIONS| } *COMMANDS* := { **show** | **list** | **attach** | **detach** | **help** } @@ -31,44 +35,44 @@ NET COMMANDS DESCRIPTION =========== **bpftool net { show | list }** [ **dev** *NAME* ] - List bpf program attachments in the kernel networking subsystem. + List bpf program attachments in the kernel networking subsystem. - Currently, only device driver xdp attachments and tc filter - classification/action attachments are implemented, i.e., for - program types **BPF_PROG_TYPE_SCHED_CLS**, - **BPF_PROG_TYPE_SCHED_ACT** and **BPF_PROG_TYPE_XDP**. - For programs attached to a particular cgroup, e.g., - **BPF_PROG_TYPE_CGROUP_SKB**, **BPF_PROG_TYPE_CGROUP_SOCK**, - **BPF_PROG_TYPE_SOCK_OPS** and **BPF_PROG_TYPE_CGROUP_SOCK_ADDR**, - users can use **bpftool cgroup** to dump cgroup attachments. - For sk_{filter, skb, msg, reuseport} and lwt/seg6 - bpf programs, users should consult other tools, e.g., iproute2. + Currently, only device driver xdp attachments and tc filter + classification/action attachments are implemented, i.e., for + program types **BPF_PROG_TYPE_SCHED_CLS**, + **BPF_PROG_TYPE_SCHED_ACT** and **BPF_PROG_TYPE_XDP**. + For programs attached to a particular cgroup, e.g., + **BPF_PROG_TYPE_CGROUP_SKB**, **BPF_PROG_TYPE_CGROUP_SOCK**, + **BPF_PROG_TYPE_SOCK_OPS** and **BPF_PROG_TYPE_CGROUP_SOCK_ADDR**, + users can use **bpftool cgroup** to dump cgroup attachments. + For sk_{filter, skb, msg, reuseport} and lwt/seg6 + bpf programs, users should consult other tools, e.g., iproute2. - The current output will start with all xdp program attachments, followed by - all tc class/qdisc bpf program attachments. Both xdp programs and - tc programs are ordered based on ifindex number. If multiple bpf - programs attached to the same networking device through **tc filter**, - the order will be first all bpf programs attached to tc classes, then - all bpf programs attached to non clsact qdiscs, and finally all - bpf programs attached to root and clsact qdisc. + The current output will start with all xdp program attachments, followed by + all tc class/qdisc bpf program attachments. Both xdp programs and + tc programs are ordered based on ifindex number. If multiple bpf + programs attached to the same networking device through **tc filter**, + the order will be first all bpf programs attached to tc classes, then + all bpf programs attached to non clsact qdiscs, and finally all + bpf programs attached to root and clsact qdisc. **bpftool** **net attach** *ATTACH_TYPE* *PROG* **dev** *NAME* [ **overwrite** ] - Attach bpf program *PROG* to network interface *NAME* with - type specified by *ATTACH_TYPE*. Previously attached bpf program - can be replaced by the command used with **overwrite** option. - Currently, only XDP-related modes are supported for *ATTACH_TYPE*. + Attach bpf program *PROG* to network interface *NAME* with + type specified by *ATTACH_TYPE*. Previously attached bpf program + can be replaced by the command used with **overwrite** option. + Currently, only XDP-related modes are supported for *ATTACH_TYPE*. - *ATTACH_TYPE* can be of: - **xdp** - try native XDP and fallback to generic XDP if NIC driver does not support it; - **xdpgeneric** - Generic XDP. runs at generic XDP hook when packet already enters receive path as skb; - **xdpdrv** - Native XDP. runs earliest point in driver's receive path; - **xdpoffload** - Offload XDP. runs directly on NIC on each packet reception; + *ATTACH_TYPE* can be of: + **xdp** - try native XDP and fallback to generic XDP if NIC driver does not support it; + **xdpgeneric** - Generic XDP. runs at generic XDP hook when packet already enters receive path as skb; + **xdpdrv** - Native XDP. runs earliest point in driver's receive path; + **xdpoffload** - Offload XDP. runs directly on NIC on each packet reception; **bpftool** **net detach** *ATTACH_TYPE* **dev** *NAME* - Detach bpf program attached to network interface *NAME* with - type specified by *ATTACH_TYPE*. To detach bpf program, same - *ATTACH_TYPE* previously used for attach must be specified. - Currently, only XDP-related modes are supported for *ATTACH_TYPE*. + Detach bpf program attached to network interface *NAME* with + type specified by *ATTACH_TYPE*. To detach bpf program, same + *ATTACH_TYPE* previously used for attach must be specified. + Currently, only XDP-related modes are supported for *ATTACH_TYPE*. **bpftool net help** Print short help message. diff --git a/tools/bpf/bpftool/Documentation/bpftool-perf.rst b/tools/bpf/bpftool/Documentation/bpftool-perf.rst index ce52798a91..5fea633a82 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-perf.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-perf.rst @@ -1,3 +1,5 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + ================ bpftool-perf ================ @@ -7,12 +9,14 @@ tool for inspection of perf related bpf prog attachments :Manual section: 8 +.. include:: substitutions.rst + SYNOPSIS ======== **bpftool** [*OPTIONS*] **perf** *COMMAND* - *OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-d** | **--debug** } } + *OPTIONS* := { |COMMON_OPTIONS| } *COMMANDS* := { **show** | **list** | **help** } diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst index f27265bd58..a2e9359e55 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst @@ -1,3 +1,5 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + ================ bpftool-prog ================ @@ -7,12 +9,14 @@ tool for inspection and simple manipulation of eBPF progs :Manual section: 8 +.. include:: substitutions.rst + SYNOPSIS ======== **bpftool** [*OPTIONS*] **prog** *COMMAND* - *OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-d** | **--debug** } | + *OPTIONS* := { |COMMON_OPTIONS| | { **-f** | **--bpffs** } | { **-m** | **--mapcompat** } | { **-n** | **--nomount** } | { **-L** | **--use-loader** } } diff --git a/tools/bpf/bpftool/Documentation/bpftool-struct_ops.rst b/tools/bpf/bpftool/Documentation/bpftool-struct_ops.rst index 02afc0fc14..ee53a122c0 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-struct_ops.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-struct_ops.rst @@ -1,3 +1,5 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + ================== bpftool-struct_ops ================== @@ -7,12 +9,14 @@ tool to register/unregister/introspect BPF struct_ops :Manual section: 8 +.. include:: substitutions.rst + SYNOPSIS ======== **bpftool** [*OPTIONS*] **struct_ops** *COMMAND* - *OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-d** | **--debug** } } + *OPTIONS* := { |COMMON_OPTIONS| } *COMMANDS* := { **show** | **list** | **dump** | **register** | **unregister** | **help** } diff --git a/tools/bpf/bpftool/Documentation/bpftool.rst b/tools/bpf/bpftool/Documentation/bpftool.rst index 8ac86565c5..7084dd9fa2 100644 --- a/tools/bpf/bpftool/Documentation/bpftool.rst +++ b/tools/bpf/bpftool/Documentation/bpftool.rst @@ -1,3 +1,5 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + ================ BPFTOOL ================ @@ -7,6 +9,8 @@ tool for inspection and simple manipulation of eBPF programs and maps :Manual section: 8 +.. include:: substitutions.rst + SYNOPSIS ======== @@ -18,8 +22,7 @@ SYNOPSIS *OBJECT* := { **map** | **program** | **cgroup** | **perf** | **net** | **feature** } - *OPTIONS* := { { **-V** | **--version** } | - { **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-d** | **--debug** } } + *OPTIONS* := { { **-V** | **--version** } | |COMMON_OPTIONS| } *MAP-COMMANDS* := { **show** | **list** | **create** | **dump** | **update** | **lookup** | **getnext** | diff --git a/tools/bpf/bpftool/Documentation/common_options.rst b/tools/bpf/bpftool/Documentation/common_options.rst index 05d06c74dc..908487b9c2 100644 --- a/tools/bpf/bpftool/Documentation/common_options.rst +++ b/tools/bpf/bpftool/Documentation/common_options.rst @@ -1,3 +1,5 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + -h, --help Print short help message (similar to **bpftool help**). @@ -20,3 +22,12 @@ Print all logs available, even debug-level information. This includes logs from libbpf as well as from the verifier, when attempting to load programs. + +-l, --legacy + Use legacy libbpf mode which has more relaxed BPF program + requirements. By default, bpftool has more strict requirements + about section names, changes pinning logic and doesn't support + some of the older non-BTF map declarations. + + See https://github.com/libbpf/libbpf/wiki/Libbpf:-the-road-to-v1.0 + for details. diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile index cce52df3be..83369f55df 100644 --- a/tools/bpf/bpftool/Makefile +++ b/tools/bpf/bpftool/Makefile @@ -1,4 +1,4 @@ -# SPDX-License-Identifier: GPL-2.0-only +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) include ../../scripts/Makefile.include ifeq ($(srctree),) @@ -13,35 +13,55 @@ else Q = @ endif -BPF_DIR = $(srctree)/tools/lib/bpf/ +BPF_DIR = $(srctree)/tools/lib/bpf ifneq ($(OUTPUT),) - LIBBPF_OUTPUT = $(OUTPUT)/libbpf/ - LIBBPF_PATH = $(LIBBPF_OUTPUT) - BOOTSTRAP_OUTPUT = $(OUTPUT)/bootstrap/ + _OUTPUT := $(OUTPUT) else - LIBBPF_OUTPUT = - LIBBPF_PATH = $(BPF_DIR) - BOOTSTRAP_OUTPUT = $(CURDIR)/bootstrap/ + _OUTPUT := $(CURDIR) endif +BOOTSTRAP_OUTPUT := $(_OUTPUT)/bootstrap/ -LIBBPF = $(LIBBPF_PATH)libbpf.a -LIBBPF_BOOTSTRAP_OUTPUT = $(BOOTSTRAP_OUTPUT)libbpf/ -LIBBPF_BOOTSTRAP = $(LIBBPF_BOOTSTRAP_OUTPUT)libbpf.a +LIBBPF_OUTPUT := $(_OUTPUT)/libbpf/ +LIBBPF_DESTDIR := $(LIBBPF_OUTPUT) +LIBBPF_INCLUDE := $(LIBBPF_DESTDIR)/include +LIBBPF_HDRS_DIR := $(LIBBPF_INCLUDE)/bpf +LIBBPF := $(LIBBPF_OUTPUT)libbpf.a + +LIBBPF_BOOTSTRAP_OUTPUT := $(BOOTSTRAP_OUTPUT)libbpf/ +LIBBPF_BOOTSTRAP_DESTDIR := $(LIBBPF_BOOTSTRAP_OUTPUT) +LIBBPF_BOOTSTRAP_INCLUDE := $(LIBBPF_BOOTSTRAP_DESTDIR)/include +LIBBPF_BOOTSTRAP_HDRS_DIR := $(LIBBPF_BOOTSTRAP_INCLUDE)/bpf +LIBBPF_BOOTSTRAP := $(LIBBPF_BOOTSTRAP_OUTPUT)libbpf.a + +# We need to copy hashmap.h and nlattr.h which is not otherwise exported by +# libbpf, but still required by bpftool. +LIBBPF_INTERNAL_HDRS := $(addprefix $(LIBBPF_HDRS_DIR)/,hashmap.h nlattr.h) +LIBBPF_BOOTSTRAP_INTERNAL_HDRS := $(addprefix $(LIBBPF_BOOTSTRAP_HDRS_DIR)/,hashmap.h) ifeq ($(BPFTOOL_VERSION),) BPFTOOL_VERSION := $(shell make -rR --no-print-directory -sC ../../.. kernelversion) endif -$(LIBBPF_OUTPUT) $(BOOTSTRAP_OUTPUT) $(LIBBPF_BOOTSTRAP_OUTPUT): +$(LIBBPF_OUTPUT) $(BOOTSTRAP_OUTPUT) $(LIBBPF_BOOTSTRAP_OUTPUT) $(LIBBPF_HDRS_DIR) $(LIBBPF_BOOTSTRAP_HDRS_DIR): $(QUIET_MKDIR)mkdir -p $@ -$(LIBBPF): FORCE | $(LIBBPF_OUTPUT) - $(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(LIBBPF_OUTPUT) $(LIBBPF_OUTPUT)libbpf.a +$(LIBBPF): $(wildcard $(BPF_DIR)/*.[ch] $(BPF_DIR)/Makefile) | $(LIBBPF_OUTPUT) + $(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(LIBBPF_OUTPUT) \ + DESTDIR=$(LIBBPF_DESTDIR) prefix= $(LIBBPF) install_headers -$(LIBBPF_BOOTSTRAP): FORCE | $(LIBBPF_BOOTSTRAP_OUTPUT) +$(LIBBPF_INTERNAL_HDRS): $(LIBBPF_HDRS_DIR)/%.h: $(BPF_DIR)/%.h | $(LIBBPF_HDRS_DIR) + $(call QUIET_INSTALL, $@) + $(Q)install -m 644 -t $(LIBBPF_HDRS_DIR) $< + +$(LIBBPF_BOOTSTRAP): $(wildcard $(BPF_DIR)/*.[ch] $(BPF_DIR)/Makefile) | $(LIBBPF_BOOTSTRAP_OUTPUT) $(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(LIBBPF_BOOTSTRAP_OUTPUT) \ - ARCH= CC=$(HOSTCC) LD=$(HOSTLD) $@ + DESTDIR=$(LIBBPF_BOOTSTRAP_DESTDIR) prefix= \ + ARCH= CROSS_COMPILE= CC=$(HOSTCC) LD=$(HOSTLD) $@ install_headers + +$(LIBBPF_BOOTSTRAP_INTERNAL_HDRS): $(LIBBPF_BOOTSTRAP_HDRS_DIR)/%.h: $(BPF_DIR)/%.h | $(LIBBPF_BOOTSTRAP_HDRS_DIR) + $(call QUIET_INSTALL, $@) + $(Q)install -m 644 -t $(LIBBPF_BOOTSTRAP_HDRS_DIR) $< $(LIBBPF)-clean: FORCE | $(LIBBPF_OUTPUT) $(call QUIET_CLEAN, libbpf) @@ -59,11 +79,10 @@ CFLAGS += -W -Wall -Wextra -Wno-unused-parameter -Wno-missing-field-initializers CFLAGS += $(filter-out -Wswitch-enum -Wnested-externs,$(EXTRA_WARNINGS)) CFLAGS += -DPACKAGE='"bpftool"' -D__EXPORTED_HEADERS__ \ -I$(if $(OUTPUT),$(OUTPUT),.) \ + -I$(LIBBPF_INCLUDE) \ -I$(srctree)/kernel/bpf/ \ -I$(srctree)/tools/include \ - -I$(srctree)/tools/include/uapi \ - -I$(srctree)/tools/lib \ - -I$(srctree)/tools/perf + -I$(srctree)/tools/include/uapi CFLAGS += -DBPFTOOL_VERSION='"$(BPFTOOL_VERSION)"' ifneq ($(EXTRA_CFLAGS),) CFLAGS += $(EXTRA_CFLAGS) @@ -133,10 +152,16 @@ CFLAGS += -DHAVE_LIBBFD_SUPPORT SRCS += $(BFD_SRCS) endif +HOST_CFLAGS = $(subst -I$(LIBBPF_INCLUDE),-I$(LIBBPF_BOOTSTRAP_INCLUDE),\ + $(subst $(CLANG_CROSS_FLAGS),,$(CFLAGS))) + BPFTOOL_BOOTSTRAP := $(BOOTSTRAP_OUTPUT)bpftool BOOTSTRAP_OBJS = $(addprefix $(BOOTSTRAP_OUTPUT),main.o common.o json_writer.o gen.o btf.o xlated_dumper.o btf_dumper.o disasm.o) +$(BOOTSTRAP_OBJS): $(LIBBPF_BOOTSTRAP) + OBJS = $(patsubst %.c,$(OUTPUT)%.o,$(SRCS)) $(OUTPUT)disasm.o +$(OBJS): $(LIBBPF) $(LIBBPF_INTERNAL_HDRS) VMLINUX_BTF_PATHS ?= $(if $(O),$(O)/vmlinux) \ $(if $(KBUILD_OUTPUT),$(KBUILD_OUTPUT)/vmlinux) \ @@ -159,13 +184,13 @@ else $(Q)cp "$(VMLINUX_H)" $@ endif -$(OUTPUT)%.bpf.o: skeleton/%.bpf.c $(OUTPUT)vmlinux.h $(LIBBPF) +$(OUTPUT)%.bpf.o: skeleton/%.bpf.c $(OUTPUT)vmlinux.h $(LIBBPF_BOOTSTRAP) $(QUIET_CLANG)$(CLANG) \ -I$(if $(OUTPUT),$(OUTPUT),.) \ -I$(srctree)/tools/include/uapi/ \ - -I$(LIBBPF_PATH) \ - -I$(srctree)/tools/lib \ - -g -O2 -Wall -target bpf -c $< -o $@ && $(LLVM_STRIP) -g $@ + -I$(LIBBPF_BOOTSTRAP_INCLUDE) \ + -g -O2 -Wall -target bpf -c $< -o $@ + $(Q)$(LLVM_STRIP) -g $@ $(OUTPUT)%.skel.h: $(OUTPUT)%.bpf.o $(BPFTOOL_BOOTSTRAP) $(QUIET_GEN)$(BPFTOOL_BOOTSTRAP) gen skeleton $< > $@ @@ -180,25 +205,27 @@ endif CFLAGS += $(if $(BUILD_BPF_SKELS),,-DBPFTOOL_WITHOUT_SKELETONS) $(BOOTSTRAP_OUTPUT)disasm.o: $(srctree)/kernel/bpf/disasm.c - $(QUIET_CC)$(HOSTCC) $(CFLAGS) -c -MMD -o $@ $< + $(QUIET_CC)$(HOSTCC) $(HOST_CFLAGS) -c -MMD $< -o $@ $(OUTPUT)disasm.o: $(srctree)/kernel/bpf/disasm.c - $(QUIET_CC)$(CC) $(CFLAGS) -c -MMD -o $@ $< + $(QUIET_CC)$(CC) $(CFLAGS) -c -MMD $< -o $@ -$(OUTPUT)feature.o: | zdep +$(OUTPUT)feature.o: +ifneq ($(feature-zlib), 1) + $(error "No zlib found") +endif $(BPFTOOL_BOOTSTRAP): $(BOOTSTRAP_OBJS) $(LIBBPF_BOOTSTRAP) - $(QUIET_LINK)$(HOSTCC) $(CFLAGS) $(LDFLAGS) -o $@ $(BOOTSTRAP_OBJS) \ - $(LIBS_BOOTSTRAP) + $(QUIET_LINK)$(HOSTCC) $(HOST_CFLAGS) $(LDFLAGS) $(BOOTSTRAP_OBJS) $(LIBS_BOOTSTRAP) -o $@ $(OUTPUT)bpftool: $(OBJS) $(LIBBPF) - $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) -o $@ $(OBJS) $(LIBS) + $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $(OBJS) $(LIBS) -o $@ -$(BOOTSTRAP_OUTPUT)%.o: %.c | $(BOOTSTRAP_OUTPUT) - $(QUIET_CC)$(HOSTCC) $(CFLAGS) -c -MMD -o $@ $< +$(BOOTSTRAP_OUTPUT)%.o: %.c $(LIBBPF_BOOTSTRAP_INTERNAL_HDRS) | $(BOOTSTRAP_OUTPUT) + $(QUIET_CC)$(HOSTCC) $(HOST_CFLAGS) -c -MMD $< -o $@ $(OUTPUT)%.o: %.c - $(QUIET_CC)$(CC) $(CFLAGS) -c -MMD -o $@ $< + $(QUIET_CC)$(CC) $(CFLAGS) -c -MMD $< -o $@ feature-detect-clean: $(call QUIET_CLEAN, feature-detect) @@ -213,10 +240,12 @@ clean: $(LIBBPF)-clean $(LIBBPF_BOOTSTRAP)-clean feature-detect-clean $(Q)$(RM) -- $(OUTPUT)FEATURE-DUMP.bpftool $(Q)$(RM) -r -- $(OUTPUT)feature/ -install: $(OUTPUT)bpftool +install-bin: $(OUTPUT)bpftool $(call QUIET_INSTALL, bpftool) $(Q)$(INSTALL) -m 0755 -d $(DESTDIR)$(prefix)/sbin $(Q)$(INSTALL) $(OUTPUT)bpftool $(DESTDIR)$(prefix)/sbin/bpftool + +install: install-bin $(Q)$(INSTALL) -m 0755 -d $(DESTDIR)$(bash_compdir) $(Q)$(INSTALL) -m 0644 bash-completion/bpftool $(DESTDIR)$(bash_compdir) @@ -239,10 +268,7 @@ doc-uninstall: FORCE: -zdep: - @if [ "$(feature-zlib)" != "1" ]; then echo "No zlib found"; exit 1 ; fi - .SECONDARY: -.PHONY: all FORCE clean install uninstall zdep +.PHONY: all FORCE bootstrap clean install-bin install uninstall .PHONY: doc doc-clean doc-install doc-uninstall .DEFAULT_GOAL := all diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool index 88e2bcf16c..493753a496 100644 --- a/tools/bpf/bpftool/bash-completion/bpftool +++ b/tools/bpf/bpftool/bash-completion/bpftool @@ -261,7 +261,7 @@ _bpftool() # Deal with options if [[ ${words[cword]} == -* ]]; then local c='--version --json --pretty --bpffs --mapcompat --debug \ - --use-loader --base-btf' + --use-loader --base-btf --legacy' COMPREPLY=( $( compgen -W "$c" -- "$cur" ) ) return 0 fi @@ -710,7 +710,8 @@ _bpftool() hash_of_maps devmap devmap_hash sockmap cpumap \ xskmap sockhash cgroup_storage reuseport_sockarray \ percpu_cgroup_storage queue stack sk_storage \ - struct_ops inode_storage task_storage ringbuf' + struct_ops ringbuf inode_storage task_storage \ + bloom_filter' COMPREPLY=( $( compgen -W "$BPFTOOL_MAP_CREATE_TYPES" -- "$cur" ) ) return 0 ;; diff --git a/tools/bpf/bpftool/btf.c b/tools/bpf/bpftool/btf.c index f7e5ff3586..59833125ac 100644 --- a/tools/bpf/bpftool/btf.c +++ b/tools/bpf/bpftool/btf.c @@ -8,14 +8,15 @@ #include #include #include -#include -#include -#include #include -#include #include #include +#include +#include +#include +#include + #include "json_writer.h" #include "main.h" @@ -37,16 +38,13 @@ static const char * const btf_kind_str[NR_BTF_KINDS] = { [BTF_KIND_VAR] = "VAR", [BTF_KIND_DATASEC] = "DATASEC", [BTF_KIND_FLOAT] = "FLOAT", -}; - -struct btf_attach_table { - DECLARE_HASHTABLE(table, 16); + [BTF_KIND_DECL_TAG] = "DECL_TAG", + [BTF_KIND_TYPE_TAG] = "TYPE_TAG", }; struct btf_attach_point { __u32 obj_id; __u32 btf_id; - struct hlist_node hash; }; static const char *btf_int_enc_str(__u8 encoding) @@ -145,6 +143,7 @@ static int dump_btf_type(const struct btf *btf, __u32 id, case BTF_KIND_VOLATILE: case BTF_KIND_RESTRICT: case BTF_KIND_TYPEDEF: + case BTF_KIND_TYPE_TAG: if (json_output) jsonw_uint_field(w, "type_id", t->type); else @@ -328,7 +327,7 @@ static int dump_btf_type(const struct btf *btf, __u32 id, printf("\n\ttype_id=%u offset=%u size=%u", v->type, v->offset, v->size); - if (v->type <= btf__get_nr_types(btf)) { + if (v->type < btf__type_cnt(btf)) { vt = btf__type_by_id(btf, v->type); printf(" (%s '%s')", btf_kind_str[btf_kind_safe(btf_kind(vt))], @@ -347,6 +346,17 @@ static int dump_btf_type(const struct btf *btf, __u32 id, printf(" size=%u", t->size); break; } + case BTF_KIND_DECL_TAG: { + const struct btf_decl_tag *tag = (const void *)(t + 1); + + if (json_output) { + jsonw_uint_field(w, "type_id", t->type); + jsonw_int_field(w, "component_idx", tag->component_idx); + } else { + printf(" type_id=%u component_idx=%d", t->type, tag->component_idx); + } + break; + } default: break; } @@ -378,14 +388,14 @@ static int dump_btf_raw(const struct btf *btf, } } else { const struct btf *base; - int cnt = btf__get_nr_types(btf); + int cnt = btf__type_cnt(btf); int start_id = 1; base = btf__base_btf(btf); if (base) - start_id = btf__get_nr_types(base) + 1; + start_id = btf__type_cnt(base); - for (i = start_id; i <= cnt; i++) { + for (i = start_id; i < cnt; i++) { t = btf__type_by_id(btf, i); dump_btf_type(btf, i, t); } @@ -410,9 +420,10 @@ static int dump_btf_c(const struct btf *btf, struct btf_dump *d; int err = 0, i; - d = btf_dump__new(btf, NULL, NULL, btf_dump_printf); - if (IS_ERR(d)) - return PTR_ERR(d); + d = btf_dump__new(btf, btf_dump_printf, NULL, NULL); + err = libbpf_get_error(d); + if (err) + return err; printf("#ifndef __VMLINUX_H__\n"); printf("#define __VMLINUX_H__\n"); @@ -428,9 +439,9 @@ static int dump_btf_c(const struct btf *btf, goto done; } } else { - int cnt = btf__get_nr_types(btf); + int cnt = btf__type_cnt(btf); - for (i = 1; i <= cnt; i++) { + for (i = 1; i < cnt; i++) { err = btf_dump__dump_type(d, i); if (err) goto done; @@ -539,8 +550,8 @@ static int do_dump(int argc, char **argv) } btf = btf__parse_split(*argv, base ?: base_btf); - if (IS_ERR(btf)) { - err = -PTR_ERR(btf); + err = libbpf_get_error(btf); + if (err) { btf = NULL; p_err("failed to load BTF from %s: %s", *argv, strerror(err)); @@ -633,21 +644,8 @@ static int btf_parse_fd(int *argc, char ***argv) return fd; } -static void delete_btf_table(struct btf_attach_table *tab) -{ - struct btf_attach_point *obj; - struct hlist_node *tmp; - - unsigned int bkt; - - hash_for_each_safe(tab->table, bkt, tmp, obj, hash) { - hash_del(&obj->hash); - free(obj); - } -} - static int -build_btf_type_table(struct btf_attach_table *tab, enum bpf_obj_type type, +build_btf_type_table(struct hashmap *tab, enum bpf_obj_type type, void *info, __u32 *len) { static const char * const names[] = { @@ -655,7 +653,6 @@ build_btf_type_table(struct btf_attach_table *tab, enum bpf_obj_type type, [BPF_OBJ_PROG] = "prog", [BPF_OBJ_MAP] = "map", }; - struct btf_attach_point *obj_node; __u32 btf_id, id = 0; int err; int fd; @@ -729,28 +726,25 @@ build_btf_type_table(struct btf_attach_table *tab, enum bpf_obj_type type, if (!btf_id) continue; - obj_node = calloc(1, sizeof(*obj_node)); - if (!obj_node) { - p_err("failed to allocate memory: %s", strerror(errno)); - err = -ENOMEM; + err = hashmap__append(tab, u32_as_hash_field(btf_id), + u32_as_hash_field(id)); + if (err) { + p_err("failed to append entry to hashmap for BTF ID %u, object ID %u: %s", + btf_id, id, strerror(errno)); goto err_free; } - - obj_node->obj_id = id; - obj_node->btf_id = btf_id; - hash_add(tab->table, &obj_node->hash, obj_node->btf_id); } return 0; err_free: - delete_btf_table(tab); + hashmap__free(tab); return err; } static int -build_btf_tables(struct btf_attach_table *btf_prog_table, - struct btf_attach_table *btf_map_table) +build_btf_tables(struct hashmap *btf_prog_table, + struct hashmap *btf_map_table) { struct bpf_prog_info prog_info; __u32 prog_len = sizeof(prog_info); @@ -766,7 +760,7 @@ build_btf_tables(struct btf_attach_table *btf_prog_table, err = build_btf_type_table(btf_map_table, BPF_OBJ_MAP, &map_info, &map_len); if (err) { - delete_btf_table(btf_prog_table); + hashmap__free(btf_prog_table); return err; } @@ -775,10 +769,10 @@ build_btf_tables(struct btf_attach_table *btf_prog_table, static void show_btf_plain(struct bpf_btf_info *info, int fd, - struct btf_attach_table *btf_prog_table, - struct btf_attach_table *btf_map_table) + struct hashmap *btf_prog_table, + struct hashmap *btf_map_table) { - struct btf_attach_point *obj; + struct hashmap_entry *entry; const char *name = u64_to_ptr(info->name); int n; @@ -792,29 +786,30 @@ show_btf_plain(struct bpf_btf_info *info, int fd, printf("size %uB", info->btf_size); n = 0; - hash_for_each_possible(btf_prog_table->table, obj, hash, info->id) { - if (obj->btf_id == info->id) - printf("%s%u", n++ == 0 ? " prog_ids " : ",", - obj->obj_id); + hashmap__for_each_key_entry(btf_prog_table, entry, + u32_as_hash_field(info->id)) { + printf("%s%u", n++ == 0 ? " prog_ids " : ",", + hash_field_as_u32(entry->value)); } n = 0; - hash_for_each_possible(btf_map_table->table, obj, hash, info->id) { - if (obj->btf_id == info->id) - printf("%s%u", n++ == 0 ? " map_ids " : ",", - obj->obj_id); + hashmap__for_each_key_entry(btf_map_table, entry, + u32_as_hash_field(info->id)) { + printf("%s%u", n++ == 0 ? " map_ids " : ",", + hash_field_as_u32(entry->value)); } - emit_obj_refs_plain(&refs_table, info->id, "\n\tpids "); + + emit_obj_refs_plain(refs_table, info->id, "\n\tpids "); printf("\n"); } static void show_btf_json(struct bpf_btf_info *info, int fd, - struct btf_attach_table *btf_prog_table, - struct btf_attach_table *btf_map_table) + struct hashmap *btf_prog_table, + struct hashmap *btf_map_table) { - struct btf_attach_point *obj; + struct hashmap_entry *entry; const char *name = u64_to_ptr(info->name); jsonw_start_object(json_wtr); /* btf object */ @@ -823,23 +818,21 @@ show_btf_json(struct bpf_btf_info *info, int fd, jsonw_name(json_wtr, "prog_ids"); jsonw_start_array(json_wtr); /* prog_ids */ - hash_for_each_possible(btf_prog_table->table, obj, hash, - info->id) { - if (obj->btf_id == info->id) - jsonw_uint(json_wtr, obj->obj_id); + hashmap__for_each_key_entry(btf_prog_table, entry, + u32_as_hash_field(info->id)) { + jsonw_uint(json_wtr, hash_field_as_u32(entry->value)); } jsonw_end_array(json_wtr); /* prog_ids */ jsonw_name(json_wtr, "map_ids"); jsonw_start_array(json_wtr); /* map_ids */ - hash_for_each_possible(btf_map_table->table, obj, hash, - info->id) { - if (obj->btf_id == info->id) - jsonw_uint(json_wtr, obj->obj_id); + hashmap__for_each_key_entry(btf_map_table, entry, + u32_as_hash_field(info->id)) { + jsonw_uint(json_wtr, hash_field_as_u32(entry->value)); } jsonw_end_array(json_wtr); /* map_ids */ - emit_obj_refs_json(&refs_table, info->id, json_wtr); /* pids */ + emit_obj_refs_json(refs_table, info->id, json_wtr); /* pids */ jsonw_bool_field(json_wtr, "kernel", info->kernel_btf); @@ -850,8 +843,8 @@ show_btf_json(struct bpf_btf_info *info, int fd, } static int -show_btf(int fd, struct btf_attach_table *btf_prog_table, - struct btf_attach_table *btf_map_table) +show_btf(int fd, struct hashmap *btf_prog_table, + struct hashmap *btf_map_table) { struct bpf_btf_info info; __u32 len = sizeof(info); @@ -888,8 +881,8 @@ show_btf(int fd, struct btf_attach_table *btf_prog_table, static int do_show(int argc, char **argv) { - struct btf_attach_table btf_prog_table; - struct btf_attach_table btf_map_table; + struct hashmap *btf_prog_table; + struct hashmap *btf_map_table; int err, fd = -1; __u32 id = 0; @@ -905,9 +898,19 @@ static int do_show(int argc, char **argv) return BAD_ARG(); } - hash_init(btf_prog_table.table); - hash_init(btf_map_table.table); - err = build_btf_tables(&btf_prog_table, &btf_map_table); + btf_prog_table = hashmap__new(hash_fn_for_key_as_id, + equal_fn_for_key_as_id, NULL); + btf_map_table = hashmap__new(hash_fn_for_key_as_id, + equal_fn_for_key_as_id, NULL); + if (!btf_prog_table || !btf_map_table) { + hashmap__free(btf_prog_table); + hashmap__free(btf_map_table); + if (fd >= 0) + close(fd); + p_err("failed to create hashmap for object references"); + return -1; + } + err = build_btf_tables(btf_prog_table, btf_map_table); if (err) { if (fd >= 0) close(fd); @@ -916,7 +919,7 @@ static int do_show(int argc, char **argv) build_obj_refs_table(&refs_table, BPF_OBJ_BTF); if (fd >= 0) { - err = show_btf(fd, &btf_prog_table, &btf_map_table); + err = show_btf(fd, btf_prog_table, btf_map_table); close(fd); goto exit_free; } @@ -948,7 +951,7 @@ static int do_show(int argc, char **argv) break; } - err = show_btf(fd, &btf_prog_table, &btf_map_table); + err = show_btf(fd, btf_prog_table, btf_map_table); close(fd); if (err) break; @@ -958,9 +961,9 @@ static int do_show(int argc, char **argv) jsonw_end_array(json_wtr); /* root array */ exit_free: - delete_btf_table(&btf_prog_table); - delete_btf_table(&btf_map_table); - delete_obj_refs_table(&refs_table); + hashmap__free(btf_prog_table); + hashmap__free(btf_map_table); + delete_obj_refs_table(refs_table); return err; } diff --git a/tools/bpf/bpftool/btf_dumper.c b/tools/bpf/bpftool/btf_dumper.c index 9c25286a5c..f5dddf8ef4 100644 --- a/tools/bpf/bpftool/btf_dumper.c +++ b/tools/bpf/bpftool/btf_dumper.c @@ -32,14 +32,16 @@ static int dump_prog_id_as_func_ptr(const struct btf_dumper *d, const struct btf_type *func_proto, __u32 prog_id) { - struct bpf_prog_info_linear *prog_info = NULL; const struct btf_type *func_type; + int prog_fd = -1, func_sig_len; + struct bpf_prog_info info = {}; + __u32 info_len = sizeof(info); const char *prog_name = NULL; - struct bpf_func_info *finfo; struct btf *prog_btf = NULL; - struct bpf_prog_info *info; - int prog_fd, func_sig_len; + struct bpf_func_info finfo; + __u32 finfo_rec_size; char prog_str[1024]; + int err; /* Get the ptr's func_proto */ func_sig_len = btf_dump_func(d->btf, prog_str, func_proto, NULL, 0, @@ -52,25 +54,30 @@ static int dump_prog_id_as_func_ptr(const struct btf_dumper *d, /* Get the bpf_prog's name. Obtain from func_info. */ prog_fd = bpf_prog_get_fd_by_id(prog_id); - if (prog_fd == -1) + if (prog_fd < 0) goto print; - prog_info = bpf_program__get_prog_info_linear(prog_fd, - 1UL << BPF_PROG_INFO_FUNC_INFO); - close(prog_fd); - if (IS_ERR(prog_info)) { - prog_info = NULL; + err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); + if (err) goto print; - } - info = &prog_info->info; - if (!info->btf_id || !info->nr_func_info) + if (!info.btf_id || !info.nr_func_info) goto print; - prog_btf = btf__load_from_kernel_by_id(info->btf_id); + + finfo_rec_size = info.func_info_rec_size; + memset(&info, 0, sizeof(info)); + info.nr_func_info = 1; + info.func_info_rec_size = finfo_rec_size; + info.func_info = ptr_to_u64(&finfo); + + err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); + if (err) + goto print; + + prog_btf = btf__load_from_kernel_by_id(info.btf_id); if (libbpf_get_error(prog_btf)) goto print; - finfo = u64_to_ptr(info->func_info); - func_type = btf__type_by_id(prog_btf, finfo->type_id); + func_type = btf__type_by_id(prog_btf, finfo.type_id); if (!func_type || !btf_is_func(func_type)) goto print; @@ -92,7 +99,8 @@ static int dump_prog_id_as_func_ptr(const struct btf_dumper *d, prog_str[sizeof(prog_str) - 1] = '\0'; jsonw_string(d->jw, prog_str); btf__free(prog_btf); - free(prog_info); + if (prog_fd >= 0) + close(prog_fd); return 0; } diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c index d42d930a3e..fa8eb81343 100644 --- a/tools/bpf/bpftool/common.c +++ b/tools/bpf/bpftool/common.c @@ -22,6 +22,7 @@ #include #include +#include #include /* libbpf_num_possible_cpus */ #include "main.h" @@ -73,6 +74,7 @@ const char * const attach_type_name[__MAX_BPF_ATTACH_TYPE] = { [BPF_XDP] = "xdp", [BPF_SK_REUSEPORT_SELECT] = "sk_skb_reuseport_select", [BPF_SK_REUSEPORT_SELECT_OR_MIGRATE] = "sk_skb_reuseport_select_or_migrate", + [BPF_PERF_EVENT] = "perf_event", }; void p_err(const char *fmt, ...) @@ -393,7 +395,7 @@ void print_hex_data_json(uint8_t *data, size_t len) } /* extra params for nftw cb */ -static struct pinned_obj_table *build_fn_table; +static struct hashmap *build_fn_table; static enum bpf_obj_type build_fn_type; static int do_build_table_cb(const char *fpath, const struct stat *sb, @@ -401,9 +403,9 @@ static int do_build_table_cb(const char *fpath, const struct stat *sb, { struct bpf_prog_info pinned_info; __u32 len = sizeof(pinned_info); - struct pinned_obj *obj_node; enum bpf_obj_type objtype; int fd, err = 0; + char *path; if (typeflag != FTW_F) goto out_ret; @@ -420,28 +422,26 @@ static int do_build_table_cb(const char *fpath, const struct stat *sb, if (bpf_obj_get_info_by_fd(fd, &pinned_info, &len)) goto out_close; - obj_node = calloc(1, sizeof(*obj_node)); - if (!obj_node) { + path = strdup(fpath); + if (!path) { err = -1; goto out_close; } - obj_node->id = pinned_info.id; - obj_node->path = strdup(fpath); - if (!obj_node->path) { - err = -1; - free(obj_node); + err = hashmap__append(build_fn_table, u32_as_hash_field(pinned_info.id), path); + if (err) { + p_err("failed to append entry to hashmap for ID %u, path '%s': %s", + pinned_info.id, path, strerror(errno)); goto out_close; } - hash_add(build_fn_table->table, &obj_node->hash, obj_node->id); out_close: close(fd); out_ret: return err; } -int build_pinned_obj_table(struct pinned_obj_table *tab, +int build_pinned_obj_table(struct hashmap *tab, enum bpf_obj_type type) { struct mntent *mntent = NULL; @@ -470,17 +470,18 @@ int build_pinned_obj_table(struct pinned_obj_table *tab, return err; } -void delete_pinned_obj_table(struct pinned_obj_table *tab) +void delete_pinned_obj_table(struct hashmap *map) { - struct pinned_obj *obj; - struct hlist_node *tmp; - unsigned int bkt; + struct hashmap_entry *entry; + size_t bkt; - hash_for_each_safe(tab->table, bkt, tmp, obj, hash) { - hash_del(&obj->hash); - free(obj->path); - free(obj); - } + if (!map) + return; + + hashmap__for_each_entry(map, entry, bkt) + free(entry->value); + + hashmap__free(map); } unsigned int get_page_size(void) @@ -962,3 +963,13 @@ int map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len) return fd; } + +size_t hash_fn_for_key_as_id(const void *key, void *ctx) +{ + return (size_t)key; +} + +bool equal_fn_for_key_as_id(const void *k1, const void *k2, void *ctx) +{ + return k1 == k2; +} diff --git a/tools/bpf/bpftool/feature.c b/tools/bpf/bpftool/feature.c index 7f36385aa9..e999159fa2 100644 --- a/tools/bpf/bpftool/feature.c +++ b/tools/bpf/bpftool/feature.c @@ -467,7 +467,7 @@ static bool probe_bpf_syscall(const char *define_prefix) { bool res; - bpf_load_program(BPF_PROG_TYPE_UNSPEC, NULL, 0, NULL, 0, NULL, 0); + bpf_prog_load(BPF_PROG_TYPE_UNSPEC, NULL, NULL, NULL, 0, NULL); res = (errno != ENOSYS); print_bool_feature("have_bpf_syscall", @@ -624,6 +624,7 @@ probe_helpers_for_progtype(enum bpf_prog_type prog_type, bool supported_type, */ switch (id) { case BPF_FUNC_trace_printk: + case BPF_FUNC_trace_vprintk: case BPF_FUNC_probe_write_user: if (!full_mode) continue; @@ -642,15 +643,111 @@ probe_helpers_for_progtype(enum bpf_prog_type prog_type, bool supported_type, } static void -probe_large_insn_limit(const char *define_prefix, __u32 ifindex) +probe_misc_feature(struct bpf_insn *insns, size_t len, + const char *define_prefix, __u32 ifindex, + const char *feat_name, const char *plain_name, + const char *define_name) { + LIBBPF_OPTS(bpf_prog_load_opts, opts, + .prog_ifindex = ifindex, + ); bool res; + int fd; - res = bpf_probe_large_insn_limit(ifindex); - print_bool_feature("have_large_insn_limit", + errno = 0; + fd = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", + insns, len, &opts); + res = fd >= 0 || !errno; + + if (fd >= 0) + close(fd); + + print_bool_feature(feat_name, plain_name, define_name, res, + define_prefix); +} + +/* + * Probe for availability of kernel commit (5.3): + * + * c04c0d2b968a ("bpf: increase complexity limit and maximum program size") + */ +static void probe_large_insn_limit(const char *define_prefix, __u32 ifindex) +{ + struct bpf_insn insns[BPF_MAXINSNS + 1]; + int i; + + for (i = 0; i < BPF_MAXINSNS; i++) + insns[i] = BPF_MOV64_IMM(BPF_REG_0, 1); + insns[BPF_MAXINSNS] = BPF_EXIT_INSN(); + + probe_misc_feature(insns, ARRAY_SIZE(insns), + define_prefix, ifindex, + "have_large_insn_limit", "Large program size limit", - "LARGE_INSN_LIMIT", - res, define_prefix); + "LARGE_INSN_LIMIT"); +} + +/* + * Probe for bounded loop support introduced in commit 2589726d12a1 + * ("bpf: introduce bounded loops"). + */ +static void +probe_bounded_loops(const char *define_prefix, __u32 ifindex) +{ + struct bpf_insn insns[4] = { + BPF_MOV64_IMM(BPF_REG_0, 10), + BPF_ALU64_IMM(BPF_SUB, BPF_REG_0, 1), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, -2), + BPF_EXIT_INSN() + }; + + probe_misc_feature(insns, ARRAY_SIZE(insns), + define_prefix, ifindex, + "have_bounded_loops", + "Bounded loop support", + "BOUNDED_LOOPS"); +} + +/* + * Probe for the v2 instruction set extension introduced in commit 92b31a9af73b + * ("bpf: add BPF_J{LT,LE,SLT,SLE} instructions"). + */ +static void +probe_v2_isa_extension(const char *define_prefix, __u32 ifindex) +{ + struct bpf_insn insns[4] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JLT, BPF_REG_0, 0, 1), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN() + }; + + probe_misc_feature(insns, ARRAY_SIZE(insns), + define_prefix, ifindex, + "have_v2_isa_extension", + "ISA extension v2", + "V2_ISA_EXTENSION"); +} + +/* + * Probe for the v3 instruction set extension introduced in commit 092ed0968bb6 + * ("bpf: verifier support JMP32"). + */ +static void +probe_v3_isa_extension(const char *define_prefix, __u32 ifindex) +{ + struct bpf_insn insns[4] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_JMP32_IMM(BPF_JLT, BPF_REG_0, 0, 1), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN() + }; + + probe_misc_feature(insns, ARRAY_SIZE(insns), + define_prefix, ifindex, + "have_v3_isa_extension", + "ISA extension v3", + "V3_ISA_EXTENSION"); } static void @@ -767,6 +864,9 @@ static void section_misc(const char *define_prefix, __u32 ifindex) "/*** eBPF misc features ***/", define_prefix); probe_large_insn_limit(define_prefix, ifindex); + probe_bounded_loops(define_prefix, ifindex); + probe_v2_isa_extension(define_prefix, ifindex); + probe_v3_isa_extension(define_prefix, ifindex); print_end_section(); } diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c index d40d92bbf0..b4695df2ea 100644 --- a/tools/bpf/bpftool/gen.c +++ b/tools/bpf/bpftool/gen.c @@ -18,7 +18,6 @@ #include #include #include -#include #include "json_writer.h" #include "main.h" @@ -34,6 +33,11 @@ static void sanitize_identifier(char *name) name[i] = '_'; } +static bool str_has_prefix(const char *str, const char *prefix) +{ + return strncmp(str, prefix, strlen(prefix)) == 0; +} + static bool str_has_suffix(const char *str, const char *suffix) { size_t i, n1 = strlen(str), n2 = strlen(suffix); @@ -68,23 +72,47 @@ static void get_header_guard(char *guard, const char *obj_name) guard[i] = toupper(guard[i]); } -static const char *get_map_ident(const struct bpf_map *map) +static bool get_map_ident(const struct bpf_map *map, char *buf, size_t buf_sz) { + static const char *sfxs[] = { ".data", ".rodata", ".bss", ".kconfig" }; const char *name = bpf_map__name(map); + int i, n; - if (!bpf_map__is_internal(map)) - return name; + if (!bpf_map__is_internal(map)) { + snprintf(buf, buf_sz, "%s", name); + return true; + } - if (str_has_suffix(name, ".data")) - return "data"; - else if (str_has_suffix(name, ".rodata")) - return "rodata"; - else if (str_has_suffix(name, ".bss")) - return "bss"; - else if (str_has_suffix(name, ".kconfig")) - return "kconfig"; - else - return NULL; + for (i = 0, n = ARRAY_SIZE(sfxs); i < n; i++) { + const char *sfx = sfxs[i], *p; + + p = strstr(name, sfx); + if (p) { + snprintf(buf, buf_sz, "%s", p + 1); + sanitize_identifier(buf); + return true; + } + } + + return false; +} + +static bool get_datasec_ident(const char *sec_name, char *buf, size_t buf_sz) +{ + static const char *pfxs[] = { ".data", ".rodata", ".bss", ".kconfig" }; + int i, n; + + for (i = 0, n = ARRAY_SIZE(pfxs); i < n; i++) { + const char *pfx = pfxs[i]; + + if (str_has_prefix(sec_name, pfx)) { + snprintf(buf, buf_sz, "%s", sec_name + 1); + sanitize_identifier(buf); + return true; + } + } + + return false; } static void codegen_btf_dump_printf(void *ctx, const char *fmt, va_list args) @@ -101,24 +129,14 @@ static int codegen_datasec_def(struct bpf_object *obj, const char *sec_name = btf__name_by_offset(btf, sec->name_off); const struct btf_var_secinfo *sec_var = btf_var_secinfos(sec); int i, err, off = 0, pad_cnt = 0, vlen = btf_vlen(sec); - const char *sec_ident; - char var_ident[256]; + char var_ident[256], sec_ident[256]; bool strip_mods = false; - if (strcmp(sec_name, ".data") == 0) { - sec_ident = "data"; - strip_mods = true; - } else if (strcmp(sec_name, ".bss") == 0) { - sec_ident = "bss"; - strip_mods = true; - } else if (strcmp(sec_name, ".rodata") == 0) { - sec_ident = "rodata"; - strip_mods = true; - } else if (strcmp(sec_name, ".kconfig") == 0) { - sec_ident = "kconfig"; - } else { + if (!get_datasec_ident(sec_name, sec_ident, sizeof(sec_ident))) return 0; - } + + if (strcmp(sec_name, ".kconfig") != 0) + strip_mods = true; printf(" struct %s__%s {\n", obj_name, sec_ident); for (i = 0; i < vlen; i++, sec_var++) { @@ -193,24 +211,64 @@ static int codegen_datasec_def(struct bpf_object *obj, static int codegen_datasecs(struct bpf_object *obj, const char *obj_name) { struct btf *btf = bpf_object__btf(obj); - int n = btf__get_nr_types(btf); + int n = btf__type_cnt(btf); struct btf_dump *d; + struct bpf_map *map; + const struct btf_type *sec; + char sec_ident[256], map_ident[256]; int i, err = 0; - d = btf_dump__new(btf, NULL, NULL, codegen_btf_dump_printf); - if (IS_ERR(d)) - return PTR_ERR(d); + d = btf_dump__new(btf, codegen_btf_dump_printf, NULL, NULL); + err = libbpf_get_error(d); + if (err) + return err; - for (i = 1; i <= n; i++) { - const struct btf_type *t = btf__type_by_id(btf, i); - - if (!btf_is_datasec(t)) + bpf_object__for_each_map(map, obj) { + /* only generate definitions for memory-mapped internal maps */ + if (!bpf_map__is_internal(map)) + continue; + if (!(bpf_map__def(map)->map_flags & BPF_F_MMAPABLE)) continue; - err = codegen_datasec_def(obj, btf, d, t, obj_name); - if (err) - goto out; + if (!get_map_ident(map, map_ident, sizeof(map_ident))) + continue; + + sec = NULL; + for (i = 1; i < n; i++) { + const struct btf_type *t = btf__type_by_id(btf, i); + const char *name; + + if (!btf_is_datasec(t)) + continue; + + name = btf__str_by_offset(btf, t->name_off); + if (!get_datasec_ident(name, sec_ident, sizeof(sec_ident))) + continue; + + if (strcmp(sec_ident, map_ident) == 0) { + sec = t; + break; + } + } + + /* In some cases (e.g., sections like .rodata.cst16 containing + * compiler allocated string constants only) there will be + * special internal maps with no corresponding DATASEC BTF + * type. In such case, generate empty structs for each such + * map. It will still be memory-mapped and its contents + * accessible from user-space through BPF skeleton. + */ + if (!sec) { + printf(" struct %s__%s {\n", obj_name, map_ident); + printf(" } *%s;\n", map_ident); + } else { + err = codegen_datasec_def(obj, btf, d, sec, obj_name); + if (err) + goto out; + } } + + out: btf_dump__free(d); return err; @@ -238,8 +296,8 @@ static void codegen(const char *template, ...) } else if (c == '\n') { break; } else { - p_err("unrecognized character at pos %td in template '%s'", - src - template - 1, template); + p_err("unrecognized character at pos %td in template '%s': '%c'", + src - template - 1, template, c); free(s); exit(-1); } @@ -386,6 +444,7 @@ static void codegen_destroy(struct bpf_object *obj, const char *obj_name) { struct bpf_program *prog; struct bpf_map *map; + char ident[256]; codegen("\ \n\ @@ -406,10 +465,7 @@ static void codegen_destroy(struct bpf_object *obj, const char *obj_name) } bpf_object__for_each_map(map, obj) { - const char * ident; - - ident = get_map_ident(map); - if (!ident) + if (!get_map_ident(map, ident, sizeof(ident))) continue; if (bpf_map__is_internal(map) && (bpf_map__def(map)->map_flags & BPF_F_MMAPABLE)) @@ -430,21 +486,16 @@ static void codegen_destroy(struct bpf_object *obj, const char *obj_name) static int gen_trace(struct bpf_object *obj, const char *obj_name, const char *header_guard) { - struct bpf_object_load_attr load_attr = {}; DECLARE_LIBBPF_OPTS(gen_loader_opts, opts); struct bpf_map *map; + char ident[256]; int err = 0; err = bpf_object__gen_loader(obj, &opts); if (err) return err; - load_attr.obj = obj; - if (verifier_logs) - /* log_level1 + log_level2 + stats, but not stable UAPI */ - load_attr.log_level = 1 + 2 + 4; - - err = bpf_object__load_xattr(&load_attr); + err = bpf_object__load(obj); if (err) { p_err("failed to load object file"); goto out; @@ -478,12 +529,10 @@ static int gen_trace(struct bpf_object *obj, const char *obj_name, const char *h ", obj_name, opts.data_sz); bpf_object__for_each_map(map, obj) { - const char *ident; const void *mmap_data = NULL; size_t mmap_size = 0; - ident = get_map_ident(map); - if (!ident) + if (!get_map_ident(map, ident, sizeof(ident))) continue; if (!bpf_map__is_internal(map) || @@ -545,15 +594,15 @@ static int gen_trace(struct bpf_object *obj, const char *obj_name, const char *h return err; \n\ ", obj_name); bpf_object__for_each_map(map, obj) { - const char *ident, *mmap_flags; + const char *mmap_flags; - ident = get_map_ident(map); - if (!ident) + if (!get_map_ident(map, ident, sizeof(ident))) continue; if (!bpf_map__is_internal(map) || !(bpf_map__def(map)->map_flags & BPF_F_MMAPABLE)) continue; + if (bpf_map__def(map)->map_flags & BPF_F_RDONLY_PROG) mmap_flags = "PROT_READ"; else @@ -603,7 +652,8 @@ static int do_skeleton(int argc, char **argv) DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts); char obj_name[MAX_OBJ_NAME_LEN] = "", *obj_data; struct bpf_object *obj = NULL; - const char *file, *ident; + const char *file; + char ident[256]; struct bpf_program *prog; int fd, err = -1; struct bpf_map *map; @@ -663,19 +713,22 @@ static int do_skeleton(int argc, char **argv) if (obj_name[0] == '\0') get_obj_name(obj_name, file); opts.object_name = obj_name; + if (verifier_logs) + /* log_level1 + log_level2 + stats, but not stable UAPI */ + opts.kernel_log_level = 1 + 2 + 4; obj = bpf_object__open_mem(obj_data, file_sz, &opts); - if (IS_ERR(obj)) { + err = libbpf_get_error(obj); + if (err) { char err_buf[256]; - libbpf_strerror(PTR_ERR(obj), err_buf, sizeof(err_buf)); + libbpf_strerror(err, err_buf, sizeof(err_buf)); p_err("failed to open BPF object file: %s", err_buf); obj = NULL; goto out; } bpf_object__for_each_map(map, obj) { - ident = get_map_ident(map); - if (!ident) { + if (!get_map_ident(map, ident, sizeof(ident))) { p_err("ignoring unrecognized internal map '%s'...", bpf_map__name(map)); continue; @@ -728,8 +781,7 @@ static int do_skeleton(int argc, char **argv) if (map_cnt) { printf("\tstruct {\n"); bpf_object__for_each_map(map, obj) { - ident = get_map_ident(map); - if (!ident) + if (!get_map_ident(map, ident, sizeof(ident))) continue; if (use_loader) printf("\t\tstruct bpf_map_desc %s;\n", ident); @@ -803,7 +855,10 @@ static int do_skeleton(int argc, char **argv) } \n\ \n\ err = %1$s__create_skeleton(obj); \n\ - err = err ?: bpf_object__open_skeleton(obj->skeleton, opts);\n\ + if (err) \n\ + goto err_out; \n\ + \n\ + err = bpf_object__open_skeleton(obj->skeleton, opts);\n\ if (err) \n\ goto err_out; \n\ \n\ @@ -862,6 +917,8 @@ static int do_skeleton(int argc, char **argv) codegen("\ \n\ \n\ + static inline const void *%1$s__elf_bytes(size_t *sz); \n\ + \n\ static inline int \n\ %1$s__create_skeleton(struct %1$s *obj) \n\ { \n\ @@ -893,9 +950,7 @@ static int do_skeleton(int argc, char **argv) ); i = 0; bpf_object__for_each_map(map, obj) { - ident = get_map_ident(map); - - if (!ident) + if (!get_map_ident(map, ident, sizeof(ident))) continue; codegen("\ @@ -943,10 +998,20 @@ static int do_skeleton(int argc, char **argv) codegen("\ \n\ \n\ - s->data_sz = %d; \n\ - s->data = (void *)\"\\ \n\ - ", - file_sz); + s->data = (void *)%2$s__elf_bytes(&s->data_sz); \n\ + \n\ + return 0; \n\ + err: \n\ + bpf_object__destroy_skeleton(s); \n\ + return -ENOMEM; \n\ + } \n\ + \n\ + static inline const void *%2$s__elf_bytes(size_t *sz) \n\ + { \n\ + *sz = %1$d; \n\ + return (const void *)\"\\ \n\ + " + , file_sz, obj_name); /* embed contents of BPF object file */ print_hex(obj_data, file_sz); @@ -954,11 +1019,6 @@ static int do_skeleton(int argc, char **argv) codegen("\ \n\ \"; \n\ - \n\ - return 0; \n\ - err: \n\ - bpf_object__destroy_skeleton(s); \n\ - return -ENOMEM; \n\ } \n\ \n\ #endif /* %s */ \n\ diff --git a/tools/bpf/bpftool/iter.c b/tools/bpf/bpftool/iter.c index 84a9b01d95..f88fdc820d 100644 --- a/tools/bpf/bpftool/iter.c +++ b/tools/bpf/bpftool/iter.c @@ -46,7 +46,8 @@ static int do_pin(int argc, char **argv) } obj = bpf_object__open(objfile); - if (IS_ERR(obj)) { + err = libbpf_get_error(obj); + if (err) { p_err("can't open objfile %s", objfile); goto close_map_fd; } @@ -57,15 +58,15 @@ static int do_pin(int argc, char **argv) goto close_obj; } - prog = bpf_program__next(NULL, obj); + prog = bpf_object__next_program(obj, NULL); if (!prog) { p_err("can't find bpf program in objfile %s", objfile); goto close_obj; } link = bpf_program__attach_iter(prog, &iter_opts); - if (IS_ERR(link)) { - err = PTR_ERR(link); + err = libbpf_get_error(link); + if (err) { p_err("attach_iter failed for program %s", bpf_program__name(prog)); goto close_obj; diff --git a/tools/bpf/bpftool/link.c b/tools/bpf/bpftool/link.c index 8cc3e36f8c..2c258db0d3 100644 --- a/tools/bpf/bpftool/link.c +++ b/tools/bpf/bpftool/link.c @@ -7,6 +7,7 @@ #include #include +#include #include "json_writer.h" #include "main.h" @@ -20,6 +21,8 @@ static const char * const link_type_name[] = { [BPF_LINK_TYPE_NETNS] = "netns", }; +static struct hashmap *link_table; + static int link_parse_fd(int *argc, char ***argv) { int fd; @@ -156,19 +159,18 @@ static int show_link_close_json(int fd, struct bpf_link_info *info) break; } - if (!hash_empty(link_table.table)) { - struct pinned_obj *obj; + if (!hashmap__empty(link_table)) { + struct hashmap_entry *entry; jsonw_name(json_wtr, "pinned"); jsonw_start_array(json_wtr); - hash_for_each_possible(link_table.table, obj, hash, info->id) { - if (obj->id == info->id) - jsonw_string(json_wtr, obj->path); - } + hashmap__for_each_key_entry(link_table, entry, + u32_as_hash_field(info->id)) + jsonw_string(json_wtr, entry->value); jsonw_end_array(json_wtr); } - emit_obj_refs_json(&refs_table, info->id, json_wtr); + emit_obj_refs_json(refs_table, info->id, json_wtr); jsonw_end_object(json_wtr); @@ -244,15 +246,14 @@ static int show_link_close_plain(int fd, struct bpf_link_info *info) break; } - if (!hash_empty(link_table.table)) { - struct pinned_obj *obj; + if (!hashmap__empty(link_table)) { + struct hashmap_entry *entry; - hash_for_each_possible(link_table.table, obj, hash, info->id) { - if (obj->id == info->id) - printf("\n\tpinned %s", obj->path); - } + hashmap__for_each_key_entry(link_table, entry, + u32_as_hash_field(info->id)) + printf("\n\tpinned %s", (char *)entry->value); } - emit_obj_refs_plain(&refs_table, info->id, "\n\tpids "); + emit_obj_refs_plain(refs_table, info->id, "\n\tpids "); printf("\n"); @@ -302,8 +303,15 @@ static int do_show(int argc, char **argv) __u32 id = 0; int err, fd; - if (show_pinned) - build_pinned_obj_table(&link_table, BPF_OBJ_LINK); + if (show_pinned) { + link_table = hashmap__new(hash_fn_for_key_as_id, + equal_fn_for_key_as_id, NULL); + if (!link_table) { + p_err("failed to create hashmap for pinned paths"); + return -1; + } + build_pinned_obj_table(link_table, BPF_OBJ_LINK); + } build_obj_refs_table(&refs_table, BPF_OBJ_LINK); if (argc == 2) { @@ -344,7 +352,10 @@ static int do_show(int argc, char **argv) if (json_output) jsonw_end_array(json_wtr); - delete_obj_refs_table(&refs_table); + delete_obj_refs_table(refs_table); + + if (show_pinned) + delete_pinned_obj_table(link_table); return errno == ENOENT ? 0 : -1; } diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c index d27ec4f852..020e91a542 100644 --- a/tools/bpf/bpftool/main.c +++ b/tools/bpf/bpftool/main.c @@ -10,8 +10,9 @@ #include #include -#include #include +#include +#include #include "main.h" @@ -30,11 +31,9 @@ bool block_mount; bool verifier_logs; bool relaxed_maps; bool use_loader; +bool legacy_libbpf; struct btf *base_btf; -struct pinned_obj_table prog_table; -struct pinned_obj_table map_table; -struct pinned_obj_table link_table; -struct obj_refs_table refs_table; +struct hashmap *refs_table; static void __noreturn clean_and_exit(int i) { @@ -94,6 +93,7 @@ static int do_version(int argc, char **argv) jsonw_name(json_wtr, "features"); jsonw_start_object(json_wtr); /* features */ jsonw_bool_field(json_wtr, "libbfd", has_libbfd); + jsonw_bool_field(json_wtr, "libbpf_strict", !legacy_libbpf); jsonw_bool_field(json_wtr, "skeletons", has_skeletons); jsonw_end_object(json_wtr); /* features */ @@ -107,6 +107,10 @@ static int do_version(int argc, char **argv) printf(" libbfd"); nb_features++; } + if (!legacy_libbpf) { + printf("%s libbpf_strict", nb_features++ ? "," : ""); + nb_features++; + } if (has_skeletons) printf("%s skeletons", nb_features++ ? "," : ""); printf("\n"); @@ -398,8 +402,10 @@ int main(int argc, char **argv) { "debug", no_argument, NULL, 'd' }, { "use-loader", no_argument, NULL, 'L' }, { "base-btf", required_argument, NULL, 'B' }, + { "legacy", no_argument, NULL, 'l' }, { 0 } }; + bool version_requested = false; int opt, ret; setlinebuf(stdout); @@ -411,16 +417,13 @@ int main(int argc, char **argv) block_mount = false; bin_name = argv[0]; - hash_init(prog_table.table); - hash_init(map_table.table); - hash_init(link_table.table); - opterr = 0; - while ((opt = getopt_long(argc, argv, "VhpjfLmndB:", + while ((opt = getopt_long(argc, argv, "VhpjfLmndB:l", options, NULL)) >= 0) { switch (opt) { case 'V': - return do_version(argc, argv); + version_requested = true; + break; case 'h': return do_help(argc, argv); case 'p': @@ -462,6 +465,9 @@ int main(int argc, char **argv) case 'L': use_loader = true; break; + case 'l': + legacy_libbpf = true; + break; default: p_err("unrecognized option '%s'", argv[optind - 1]); if (json_output) @@ -471,21 +477,25 @@ int main(int argc, char **argv) } } + if (!legacy_libbpf) { + ret = libbpf_set_strict_mode(LIBBPF_STRICT_ALL); + if (ret) + p_err("failed to enable libbpf strict mode: %d", ret); + } + argc -= optind; argv += optind; if (argc < 0) usage(); + if (version_requested) + return do_version(argc, argv); + ret = cmd_select(cmds, argc, argv, do_help); if (json_output) jsonw_destroy(&json_wtr); - if (show_pinned) { - delete_pinned_obj_table(&prog_table); - delete_pinned_obj_table(&map_table); - delete_pinned_obj_table(&link_table); - } btf__free(base_btf); return ret; diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h index 90caa42aac..8d76d937a6 100644 --- a/tools/bpf/bpftool/main.h +++ b/tools/bpf/bpftool/main.h @@ -11,9 +11,9 @@ #include #include #include -#include #include +#include #include #include "json_writer.h" @@ -57,7 +57,7 @@ static inline void *u64_to_ptr(__u64 ptr) #define HELP_SPEC_PROGRAM \ "PROG := { id PROG_ID | pinned FILE | tag PROG_TAG | name PROG_NAME }" #define HELP_SPEC_OPTIONS \ - "OPTIONS := { {-j|--json} [{-p|--pretty}] | {-d|--debug}" + "OPTIONS := { {-j|--json} [{-p|--pretty}] | {-d|--debug} | {-l|--legacy}" #define HELP_SPEC_MAP \ "MAP := { id MAP_ID | pinned FILE | name MAP_NAME }" #define HELP_SPEC_LINK \ @@ -90,11 +90,9 @@ extern bool block_mount; extern bool verifier_logs; extern bool relaxed_maps; extern bool use_loader; +extern bool legacy_libbpf; extern struct btf *base_btf; -extern struct pinned_obj_table prog_table; -extern struct pinned_obj_table map_table; -extern struct pinned_obj_table link_table; -extern struct obj_refs_table refs_table; +extern struct hashmap *refs_table; void __printf(1, 2) p_err(const char *fmt, ...); void __printf(1, 2) p_info(const char *fmt, ...); @@ -108,28 +106,12 @@ void set_max_rlimit(void); int mount_tracefs(const char *target); -struct pinned_obj_table { - DECLARE_HASHTABLE(table, 16); -}; - -struct pinned_obj { - __u32 id; - char *path; - struct hlist_node hash; -}; - -struct obj_refs_table { - DECLARE_HASHTABLE(table, 16); -}; - struct obj_ref { int pid; char comm[16]; }; struct obj_refs { - struct hlist_node node; - __u32 id; int ref_cnt; struct obj_ref *refs; }; @@ -137,15 +119,15 @@ struct obj_refs { struct btf; struct bpf_line_info; -int build_pinned_obj_table(struct pinned_obj_table *table, +int build_pinned_obj_table(struct hashmap *table, enum bpf_obj_type type); -void delete_pinned_obj_table(struct pinned_obj_table *tab); -__weak int build_obj_refs_table(struct obj_refs_table *table, +void delete_pinned_obj_table(struct hashmap *table); +__weak int build_obj_refs_table(struct hashmap **table, enum bpf_obj_type type); -__weak void delete_obj_refs_table(struct obj_refs_table *table); -__weak void emit_obj_refs_json(struct obj_refs_table *table, __u32 id, +__weak void delete_obj_refs_table(struct hashmap *table); +__weak void emit_obj_refs_json(struct hashmap *table, __u32 id, json_writer_t *json_wtr); -__weak void emit_obj_refs_plain(struct obj_refs_table *table, __u32 id, +__weak void emit_obj_refs_plain(struct hashmap *table, __u32 id, const char *prefix); void print_dev_plain(__u32 ifindex, __u64 ns_dev, __u64 ns_inode); void print_dev_json(__u32 ifindex, __u64 ns_dev, __u64 ns_inode); @@ -259,4 +241,23 @@ int do_filter_dump(struct tcmsg *ifinfo, struct nlattr **tb, const char *kind, int print_all_levels(__maybe_unused enum libbpf_print_level level, const char *format, va_list args); + +size_t hash_fn_for_key_as_id(const void *key, void *ctx); +bool equal_fn_for_key_as_id(const void *k1, const void *k2, void *ctx); + +static inline void *u32_as_hash_field(__u32 x) +{ + return (void *)(uintptr_t)x; +} + +static inline __u32 hash_field_as_u32(const void *x) +{ + return (__u32)(uintptr_t)x; +} + +static inline bool hashmap__empty(struct hashmap *map) +{ + return map ? hashmap__size(map) == 0 : true; +} + #endif diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c index 407071d54a..cc530a2298 100644 --- a/tools/bpf/bpftool/map.c +++ b/tools/bpf/bpftool/map.c @@ -17,6 +17,7 @@ #include #include +#include #include "json_writer.h" #include "main.h" @@ -52,10 +53,13 @@ const char * const map_type_name[] = { [BPF_MAP_TYPE_RINGBUF] = "ringbuf", [BPF_MAP_TYPE_INODE_STORAGE] = "inode_storage", [BPF_MAP_TYPE_TASK_STORAGE] = "task_storage", + [BPF_MAP_TYPE_BLOOM_FILTER] = "bloom_filter", }; const size_t map_type_name_size = ARRAY_SIZE(map_type_name); +static struct hashmap *map_table; + static bool map_is_per_cpu(__u32 type) { return type == BPF_MAP_TYPE_PERCPU_HASH || @@ -535,19 +539,18 @@ static int show_map_close_json(int fd, struct bpf_map_info *info) if (info->btf_id) jsonw_int_field(json_wtr, "btf_id", info->btf_id); - if (!hash_empty(map_table.table)) { - struct pinned_obj *obj; + if (!hashmap__empty(map_table)) { + struct hashmap_entry *entry; jsonw_name(json_wtr, "pinned"); jsonw_start_array(json_wtr); - hash_for_each_possible(map_table.table, obj, hash, info->id) { - if (obj->id == info->id) - jsonw_string(json_wtr, obj->path); - } + hashmap__for_each_key_entry(map_table, entry, + u32_as_hash_field(info->id)) + jsonw_string(json_wtr, entry->value); jsonw_end_array(json_wtr); } - emit_obj_refs_json(&refs_table, info->id, json_wtr); + emit_obj_refs_json(refs_table, info->id, json_wtr); jsonw_end_object(json_wtr); @@ -610,13 +613,12 @@ static int show_map_close_plain(int fd, struct bpf_map_info *info) } close(fd); - if (!hash_empty(map_table.table)) { - struct pinned_obj *obj; + if (!hashmap__empty(map_table)) { + struct hashmap_entry *entry; - hash_for_each_possible(map_table.table, obj, hash, info->id) { - if (obj->id == info->id) - printf("\n\tpinned %s", obj->path); - } + hashmap__for_each_key_entry(map_table, entry, + u32_as_hash_field(info->id)) + printf("\n\tpinned %s", (char *)entry->value); } printf("\n"); @@ -636,7 +638,7 @@ static int show_map_close_plain(int fd, struct bpf_map_info *info) if (frozen) printf("%sfrozen", info->btf_id ? " " : ""); - emit_obj_refs_plain(&refs_table, info->id, "\n\tpids "); + emit_obj_refs_plain(refs_table, info->id, "\n\tpids "); printf("\n"); return 0; @@ -694,8 +696,15 @@ static int do_show(int argc, char **argv) int err; int fd; - if (show_pinned) - build_pinned_obj_table(&map_table, BPF_OBJ_MAP); + if (show_pinned) { + map_table = hashmap__new(hash_fn_for_key_as_id, + equal_fn_for_key_as_id, NULL); + if (!map_table) { + p_err("failed to create hashmap for pinned paths"); + return -1; + } + build_pinned_obj_table(map_table, BPF_OBJ_MAP); + } build_obj_refs_table(&refs_table, BPF_OBJ_MAP); if (argc == 2) @@ -740,7 +749,10 @@ static int do_show(int argc, char **argv) if (json_output) jsonw_end_array(json_wtr); - delete_obj_refs_table(&refs_table); + delete_obj_refs_table(refs_table); + + if (show_pinned) + delete_pinned_obj_table(map_table); return errno == ENOENT ? 0 : -1; } @@ -800,7 +812,7 @@ static struct btf *get_map_kv_btf(const struct bpf_map_info *info) if (info->btf_vmlinux_value_type_id) { if (!btf_vmlinux) { btf_vmlinux = libbpf_find_kernel_btf(); - if (IS_ERR(btf_vmlinux)) + if (libbpf_get_error(btf_vmlinux)) p_err("failed to get kernel btf"); } return btf_vmlinux; @@ -820,13 +832,13 @@ static struct btf *get_map_kv_btf(const struct bpf_map_info *info) static void free_map_kv_btf(struct btf *btf) { - if (!IS_ERR(btf) && btf != btf_vmlinux) + if (!libbpf_get_error(btf) && btf != btf_vmlinux) btf__free(btf); } static void free_btf_vmlinux(void) { - if (!IS_ERR(btf_vmlinux)) + if (!libbpf_get_error(btf_vmlinux)) btf__free(btf_vmlinux); } @@ -851,8 +863,8 @@ map_dump(int fd, struct bpf_map_info *info, json_writer_t *wtr, if (wtr) { btf = get_map_kv_btf(info); - if (IS_ERR(btf)) { - err = PTR_ERR(btf); + err = libbpf_get_error(btf); + if (err) { goto exit_free; } @@ -1249,7 +1261,10 @@ static int do_pin(int argc, char **argv) static int do_create(int argc, char **argv) { - struct bpf_create_map_attr attr = { NULL, }; + LIBBPF_OPTS(bpf_map_create_opts, attr); + enum bpf_map_type map_type = BPF_MAP_TYPE_UNSPEC; + __u32 key_size = 0, value_size = 0, max_entries = 0; + const char *map_name = NULL; const char *pinfile; int err = -1, fd; @@ -1264,30 +1279,30 @@ static int do_create(int argc, char **argv) if (is_prefix(*argv, "type")) { NEXT_ARG(); - if (attr.map_type) { + if (map_type) { p_err("map type already specified"); goto exit; } - attr.map_type = map_type_from_str(*argv); - if ((int)attr.map_type < 0) { + map_type = map_type_from_str(*argv); + if ((int)map_type < 0) { p_err("unrecognized map type: %s", *argv); goto exit; } NEXT_ARG(); } else if (is_prefix(*argv, "name")) { NEXT_ARG(); - attr.name = GET_ARG(); + map_name = GET_ARG(); } else if (is_prefix(*argv, "key")) { - if (parse_u32_arg(&argc, &argv, &attr.key_size, + if (parse_u32_arg(&argc, &argv, &key_size, "key size")) goto exit; } else if (is_prefix(*argv, "value")) { - if (parse_u32_arg(&argc, &argv, &attr.value_size, + if (parse_u32_arg(&argc, &argv, &value_size, "value size")) goto exit; } else if (is_prefix(*argv, "entries")) { - if (parse_u32_arg(&argc, &argv, &attr.max_entries, + if (parse_u32_arg(&argc, &argv, &max_entries, "max entries")) goto exit; } else if (is_prefix(*argv, "flags")) { @@ -1328,14 +1343,14 @@ static int do_create(int argc, char **argv) } } - if (!attr.name) { + if (!map_name) { p_err("map name not specified"); goto exit; } set_max_rlimit(); - fd = bpf_create_map_xattr(&attr); + fd = bpf_map_create(map_type, map_name, key_size, value_size, max_entries, &attr); if (fd < 0) { p_err("map create failed: %s", strerror(errno)); goto exit; @@ -1466,7 +1481,7 @@ static int do_help(int argc, char **argv) " devmap | devmap_hash | sockmap | cpumap | xskmap | sockhash |\n" " cgroup_storage | reuseport_sockarray | percpu_cgroup_storage |\n" " queue | stack | sk_storage | struct_ops | ringbuf | inode_storage |\n" - " task_storage }\n" + " task_storage | bloom_filter }\n" " " HELP_SPEC_OPTIONS " |\n" " {-f|--bpffs} | {-n|--nomount} }\n" "", diff --git a/tools/bpf/bpftool/map_perf_ring.c b/tools/bpf/bpftool/map_perf_ring.c index 825f29f93a..6b0c410152 100644 --- a/tools/bpf/bpftool/map_perf_ring.c +++ b/tools/bpf/bpftool/map_perf_ring.c @@ -22,7 +22,6 @@ #include #include -#include #include "main.h" @@ -125,7 +124,7 @@ int do_event_pipe(int argc, char **argv) .wakeup_events = 1, }; struct bpf_map_info map_info = {}; - struct perf_buffer_raw_opts opts = {}; + LIBBPF_OPTS(perf_buffer_raw_opts, opts); struct event_pipe_ctx ctx = { .all_cpus = true, .cpu = -1, @@ -191,14 +190,11 @@ int do_event_pipe(int argc, char **argv) ctx.idx = 0; } - opts.attr = &perf_attr; - opts.event_cb = print_bpf_output; - opts.ctx = &ctx; opts.cpu_cnt = ctx.all_cpus ? 0 : 1; opts.cpus = &ctx.cpu; opts.map_keys = &ctx.idx; - - pb = perf_buffer__new_raw(map_fd, MMAP_PAGE_CNT, &opts); + pb = perf_buffer__new_raw(map_fd, MMAP_PAGE_CNT, &perf_attr, + print_bpf_output, &ctx, &opts); err = libbpf_get_error(pb); if (err) { p_err("failed to create perf buffer: %s (%d)", diff --git a/tools/bpf/bpftool/pids.c b/tools/bpf/bpftool/pids.c index 477e55d59c..56b598eee0 100644 --- a/tools/bpf/bpftool/pids.c +++ b/tools/bpf/bpftool/pids.c @@ -6,35 +6,37 @@ #include #include #include + #include +#include #include "main.h" #include "skeleton/pid_iter.h" #ifdef BPFTOOL_WITHOUT_SKELETONS -int build_obj_refs_table(struct obj_refs_table *table, enum bpf_obj_type type) +int build_obj_refs_table(struct hashmap **map, enum bpf_obj_type type) { return -ENOTSUP; } -void delete_obj_refs_table(struct obj_refs_table *table) {} -void emit_obj_refs_plain(struct obj_refs_table *table, __u32 id, const char *prefix) {} -void emit_obj_refs_json(struct obj_refs_table *table, __u32 id, json_writer_t *json_writer) {} +void delete_obj_refs_table(struct hashmap *map) {} +void emit_obj_refs_plain(struct hashmap *map, __u32 id, const char *prefix) {} +void emit_obj_refs_json(struct hashmap *map, __u32 id, json_writer_t *json_writer) {} #else /* BPFTOOL_WITHOUT_SKELETONS */ #include "pid_iter.skel.h" -static void add_ref(struct obj_refs_table *table, struct pid_iter_entry *e) +static void add_ref(struct hashmap *map, struct pid_iter_entry *e) { + struct hashmap_entry *entry; struct obj_refs *refs; struct obj_ref *ref; + int err, i; void *tmp; - int i; - hash_for_each_possible(table->table, refs, node, e->id) { - if (refs->id != e->id) - continue; + hashmap__for_each_key_entry(map, entry, u32_as_hash_field(e->id)) { + refs = entry->value; for (i = 0; i < refs->ref_cnt; i++) { if (refs->refs[i].pid == e->pid) @@ -64,7 +66,6 @@ static void add_ref(struct obj_refs_table *table, struct pid_iter_entry *e) return; } - refs->id = e->id; refs->refs = malloc(sizeof(*refs->refs)); if (!refs->refs) { free(refs); @@ -76,7 +77,11 @@ static void add_ref(struct obj_refs_table *table, struct pid_iter_entry *e) ref->pid = e->pid; memcpy(ref->comm, e->comm, sizeof(ref->comm)); refs->ref_cnt = 1; - hash_add(table->table, &refs->node, e->id); + + err = hashmap__append(map, u32_as_hash_field(e->id), refs); + if (err) + p_err("failed to append entry to hashmap for ID %u: %s", + e->id, strerror(errno)); } static int __printf(2, 0) @@ -87,7 +92,7 @@ libbpf_print_none(__maybe_unused enum libbpf_print_level level, return 0; } -int build_obj_refs_table(struct obj_refs_table *table, enum bpf_obj_type type) +int build_obj_refs_table(struct hashmap **map, enum bpf_obj_type type) { struct pid_iter_entry *e; char buf[4096 / sizeof(*e) * sizeof(*e)]; @@ -95,7 +100,11 @@ int build_obj_refs_table(struct obj_refs_table *table, enum bpf_obj_type type) int err, ret, fd = -1, i; libbpf_print_fn_t default_print; - hash_init(table->table); + *map = hashmap__new(hash_fn_for_key_as_id, equal_fn_for_key_as_id, NULL); + if (!*map) { + p_err("failed to create hashmap for PID references"); + return -1; + } set_max_rlimit(); skel = pid_iter_bpf__open(); @@ -151,7 +160,7 @@ int build_obj_refs_table(struct obj_refs_table *table, enum bpf_obj_type type) e = (void *)buf; for (i = 0; i < ret; i++, e++) { - add_ref(table, e); + add_ref(*map, e); } } err = 0; @@ -162,39 +171,44 @@ int build_obj_refs_table(struct obj_refs_table *table, enum bpf_obj_type type) return err; } -void delete_obj_refs_table(struct obj_refs_table *table) +void delete_obj_refs_table(struct hashmap *map) { - struct obj_refs *refs; - struct hlist_node *tmp; - unsigned int bkt; + struct hashmap_entry *entry; + size_t bkt; + + if (!map) + return; + + hashmap__for_each_entry(map, entry, bkt) { + struct obj_refs *refs = entry->value; - hash_for_each_safe(table->table, bkt, tmp, refs, node) { - hash_del(&refs->node); free(refs->refs); free(refs); } + + hashmap__free(map); } -void emit_obj_refs_json(struct obj_refs_table *table, __u32 id, +void emit_obj_refs_json(struct hashmap *map, __u32 id, json_writer_t *json_writer) { - struct obj_refs *refs; - struct obj_ref *ref; - int i; + struct hashmap_entry *entry; - if (hash_empty(table->table)) + if (hashmap__empty(map)) return; - hash_for_each_possible(table->table, refs, node, id) { - if (refs->id != id) - continue; + hashmap__for_each_key_entry(map, entry, u32_as_hash_field(id)) { + struct obj_refs *refs = entry->value; + int i; + if (refs->ref_cnt == 0) break; jsonw_name(json_writer, "pids"); jsonw_start_array(json_writer); for (i = 0; i < refs->ref_cnt; i++) { - ref = &refs->refs[i]; + struct obj_ref *ref = &refs->refs[i]; + jsonw_start_object(json_writer); jsonw_int_field(json_writer, "pid", ref->pid); jsonw_string_field(json_writer, "comm", ref->comm); @@ -205,24 +219,24 @@ void emit_obj_refs_json(struct obj_refs_table *table, __u32 id, } } -void emit_obj_refs_plain(struct obj_refs_table *table, __u32 id, const char *prefix) +void emit_obj_refs_plain(struct hashmap *map, __u32 id, const char *prefix) { - struct obj_refs *refs; - struct obj_ref *ref; - int i; + struct hashmap_entry *entry; - if (hash_empty(table->table)) + if (hashmap__empty(map)) return; - hash_for_each_possible(table->table, refs, node, id) { - if (refs->id != id) - continue; + hashmap__for_each_key_entry(map, entry, u32_as_hash_field(id)) { + struct obj_refs *refs = entry->value; + int i; + if (refs->ref_cnt == 0) break; printf("%s", prefix); for (i = 0; i < refs->ref_cnt; i++) { - ref = &refs->refs[i]; + struct obj_ref *ref = &refs->refs[i]; + printf("%s%s(%d)", i == 0 ? "" : ", ", ref->comm, ref->pid); } break; diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index f8755beb3d..2a21d50516 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -24,8 +24,8 @@ #include #include +#include #include -#include #include #include "cfg.h" @@ -85,6 +85,8 @@ static const char * const attach_type_strings[] = { [__MAX_BPF_ATTACH_TYPE] = NULL, }; +static struct hashmap *prog_table; + static enum bpf_attach_type parse_attach_type(const char *str) { enum bpf_attach_type type; @@ -98,6 +100,76 @@ static enum bpf_attach_type parse_attach_type(const char *str) return __MAX_BPF_ATTACH_TYPE; } +static int prep_prog_info(struct bpf_prog_info *const info, enum dump_mode mode, + void **info_data, size_t *const info_data_sz) +{ + struct bpf_prog_info holder = {}; + size_t needed = 0; + void *ptr; + + if (mode == DUMP_JITED) { + holder.jited_prog_len = info->jited_prog_len; + needed += info->jited_prog_len; + } else { + holder.xlated_prog_len = info->xlated_prog_len; + needed += info->xlated_prog_len; + } + + holder.nr_jited_ksyms = info->nr_jited_ksyms; + needed += info->nr_jited_ksyms * sizeof(__u64); + + holder.nr_jited_func_lens = info->nr_jited_func_lens; + needed += info->nr_jited_func_lens * sizeof(__u32); + + holder.nr_func_info = info->nr_func_info; + holder.func_info_rec_size = info->func_info_rec_size; + needed += info->nr_func_info * info->func_info_rec_size; + + holder.nr_line_info = info->nr_line_info; + holder.line_info_rec_size = info->line_info_rec_size; + needed += info->nr_line_info * info->line_info_rec_size; + + holder.nr_jited_line_info = info->nr_jited_line_info; + holder.jited_line_info_rec_size = info->jited_line_info_rec_size; + needed += info->nr_jited_line_info * info->jited_line_info_rec_size; + + if (needed > *info_data_sz) { + ptr = realloc(*info_data, needed); + if (!ptr) + return -1; + + *info_data = ptr; + *info_data_sz = needed; + } + ptr = *info_data; + + if (mode == DUMP_JITED) { + holder.jited_prog_insns = ptr_to_u64(ptr); + ptr += holder.jited_prog_len; + } else { + holder.xlated_prog_insns = ptr_to_u64(ptr); + ptr += holder.xlated_prog_len; + } + + holder.jited_ksyms = ptr_to_u64(ptr); + ptr += holder.nr_jited_ksyms * sizeof(__u64); + + holder.jited_func_lens = ptr_to_u64(ptr); + ptr += holder.nr_jited_func_lens * sizeof(__u32); + + holder.func_info = ptr_to_u64(ptr); + ptr += holder.nr_func_info * holder.func_info_rec_size; + + holder.line_info = ptr_to_u64(ptr); + ptr += holder.nr_line_info * holder.line_info_rec_size; + + holder.jited_line_info = ptr_to_u64(ptr); + ptr += holder.nr_jited_line_info * holder.jited_line_info_rec_size; + + *info = holder; + return 0; +} + static void print_boot_time(__u64 nsecs, char *buf, unsigned int size) { struct timespec real_time_ts, boot_time_ts; @@ -417,19 +489,18 @@ static void print_prog_json(struct bpf_prog_info *info, int fd) if (info->btf_id) jsonw_int_field(json_wtr, "btf_id", info->btf_id); - if (!hash_empty(prog_table.table)) { - struct pinned_obj *obj; + if (!hashmap__empty(prog_table)) { + struct hashmap_entry *entry; jsonw_name(json_wtr, "pinned"); jsonw_start_array(json_wtr); - hash_for_each_possible(prog_table.table, obj, hash, info->id) { - if (obj->id == info->id) - jsonw_string(json_wtr, obj->path); - } + hashmap__for_each_key_entry(prog_table, entry, + u32_as_hash_field(info->id)) + jsonw_string(json_wtr, entry->value); jsonw_end_array(json_wtr); } - emit_obj_refs_json(&refs_table, info->id, json_wtr); + emit_obj_refs_json(refs_table, info->id, json_wtr); show_prog_metadata(fd, info->nr_map_ids); @@ -489,19 +560,18 @@ static void print_prog_plain(struct bpf_prog_info *info, int fd) if (info->nr_map_ids) show_prog_maps(fd, info->nr_map_ids); - if (!hash_empty(prog_table.table)) { - struct pinned_obj *obj; + if (!hashmap__empty(prog_table)) { + struct hashmap_entry *entry; - hash_for_each_possible(prog_table.table, obj, hash, info->id) { - if (obj->id == info->id) - printf("\n\tpinned %s", obj->path); - } + hashmap__for_each_key_entry(prog_table, entry, + u32_as_hash_field(info->id)) + printf("\n\tpinned %s", (char *)entry->value); } if (info->btf_id) printf("\n\tbtf_id %d", info->btf_id); - emit_obj_refs_plain(&refs_table, info->id, "\n\tpids "); + emit_obj_refs_plain(refs_table, info->id, "\n\tpids "); printf("\n"); @@ -568,8 +638,15 @@ static int do_show(int argc, char **argv) int err; int fd; - if (show_pinned) - build_pinned_obj_table(&prog_table, BPF_OBJ_PROG); + if (show_pinned) { + prog_table = hashmap__new(hash_fn_for_key_as_id, + equal_fn_for_key_as_id, NULL); + if (!prog_table) { + p_err("failed to create hashmap for pinned paths"); + return -1; + } + build_pinned_obj_table(prog_table, BPF_OBJ_PROG); + } build_obj_refs_table(&refs_table, BPF_OBJ_PROG); if (argc == 2) @@ -612,7 +689,10 @@ static int do_show(int argc, char **argv) if (json_output) jsonw_end_array(json_wtr); - delete_obj_refs_table(&refs_table); + delete_obj_refs_table(refs_table); + + if (show_pinned) + delete_pinned_obj_table(prog_table); return err; } @@ -796,16 +876,18 @@ prog_dump(struct bpf_prog_info *info, enum dump_mode mode, static int do_dump(int argc, char **argv) { - struct bpf_prog_info_linear *info_linear; + struct bpf_prog_info info; + __u32 info_len = sizeof(info); + size_t info_data_sz = 0; + void *info_data = NULL; char *filepath = NULL; bool opcodes = false; bool visual = false; enum dump_mode mode; bool linum = false; - int *fds = NULL; int nb_fds, i = 0; + int *fds = NULL; int err = -1; - __u64 arrays; if (is_prefix(*argv, "jited")) { if (disasm_init()) @@ -865,43 +947,44 @@ static int do_dump(int argc, char **argv) goto exit_close; } - if (mode == DUMP_JITED) - arrays = 1UL << BPF_PROG_INFO_JITED_INSNS; - else - arrays = 1UL << BPF_PROG_INFO_XLATED_INSNS; - - arrays |= 1UL << BPF_PROG_INFO_JITED_KSYMS; - arrays |= 1UL << BPF_PROG_INFO_JITED_FUNC_LENS; - arrays |= 1UL << BPF_PROG_INFO_FUNC_INFO; - arrays |= 1UL << BPF_PROG_INFO_LINE_INFO; - arrays |= 1UL << BPF_PROG_INFO_JITED_LINE_INFO; - if (json_output && nb_fds > 1) jsonw_start_array(json_wtr); /* root array */ for (i = 0; i < nb_fds; i++) { - info_linear = bpf_program__get_prog_info_linear(fds[i], arrays); - if (IS_ERR_OR_NULL(info_linear)) { + memset(&info, 0, sizeof(info)); + + err = bpf_obj_get_info_by_fd(fds[i], &info, &info_len); + if (err) { + p_err("can't get prog info: %s", strerror(errno)); + break; + } + + err = prep_prog_info(&info, mode, &info_data, &info_data_sz); + if (err) { + p_err("can't grow prog info_data"); + break; + } + + err = bpf_obj_get_info_by_fd(fds[i], &info, &info_len); + if (err) { p_err("can't get prog info: %s", strerror(errno)); break; } if (json_output && nb_fds > 1) { jsonw_start_object(json_wtr); /* prog object */ - print_prog_header_json(&info_linear->info); + print_prog_header_json(&info); jsonw_name(json_wtr, "insns"); } else if (nb_fds > 1) { - print_prog_header_plain(&info_linear->info); + print_prog_header_plain(&info); } - err = prog_dump(&info_linear->info, mode, filepath, opcodes, - visual, linum); + err = prog_dump(&info, mode, filepath, opcodes, visual, linum); if (json_output && nb_fds > 1) jsonw_end_object(json_wtr); /* prog object */ else if (i != nb_fds - 1 && nb_fds > 1) printf("\n"); - free(info_linear); if (err) break; close(fds[i]); @@ -913,6 +996,7 @@ static int do_dump(int argc, char **argv) for (; i < nb_fds; i++) close(fds[i]); exit_free: + free(info_data); free(fds); return err; } @@ -1380,7 +1464,6 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) DECLARE_LIBBPF_OPTS(bpf_object_open_opts, open_opts, .relaxed_maps = relaxed_maps, ); - struct bpf_object_load_attr load_attr = { 0 }; enum bpf_attach_type expected_attach_type; struct map_replace *map_replace = NULL; struct bpf_program *prog = NULL, *pos; @@ -1402,8 +1485,6 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) while (argc) { if (is_prefix(*argv, "type")) { - char *type; - NEXT_ARG(); if (common_prog_type != BPF_PROG_TYPE_UNSPEC) { @@ -1413,21 +1494,26 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) if (!REQ_ARGS(1)) goto err_free_reuse_maps; - /* Put a '/' at the end of type to appease libbpf */ - type = malloc(strlen(*argv) + 2); - if (!type) { - p_err("mem alloc failed"); - goto err_free_reuse_maps; - } - *type = 0; - strcat(type, *argv); - strcat(type, "/"); + err = libbpf_prog_type_by_name(*argv, &common_prog_type, + &expected_attach_type); + if (err < 0) { + /* Put a '/' at the end of type to appease libbpf */ + char *type = malloc(strlen(*argv) + 2); - err = get_prog_type_by_name(type, &common_prog_type, - &expected_attach_type); - free(type); - if (err < 0) - goto err_free_reuse_maps; + if (!type) { + p_err("mem alloc failed"); + goto err_free_reuse_maps; + } + *type = 0; + strcat(type, *argv); + strcat(type, "/"); + + err = get_prog_type_by_name(type, &common_prog_type, + &expected_attach_type); + free(type); + if (err < 0) + goto err_free_reuse_maps; + } NEXT_ARG(); } else if (is_prefix(*argv, "map")) { @@ -1511,6 +1597,10 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) set_max_rlimit(); + if (verifier_logs) + /* log_level1 + log_level2 + stats, but not stable UAPI */ + open_opts.kernel_log_level = 1 + 2 + 4; + obj = bpf_object__open_file(file, &open_opts); if (libbpf_get_error(obj)) { p_err("failed to open object file"); @@ -1565,7 +1655,7 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) j = 0; idx = 0; bpf_object__for_each_map(map, obj) { - if (!bpf_map__is_offload_neutral(map)) + if (bpf_map__type(map) != BPF_MAP_TYPE_PERF_EVENT_ARRAY) bpf_map__set_ifindex(map, ifindex); if (j < old_map_fds && idx == map_replace[j].idx) { @@ -1590,12 +1680,7 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) goto err_close_obj; } - load_attr.obj = obj; - if (verifier_logs) - /* log_level1 + log_level2 + stats, but not stable UAPI */ - load_attr.log_level = 1 + 2 + 4; - - err = bpf_object__load_xattr(&load_attr); + err = bpf_object__load(obj); if (err) { p_err("failed to load object file"); goto err_close_obj; @@ -1606,7 +1691,7 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) goto err_close_obj; if (first_prog_only) { - prog = bpf_program__next(NULL, obj); + prog = bpf_object__next_program(obj, NULL); if (!prog) { p_err("object file doesn't contain any bpf program"); goto err_close_obj; @@ -1650,6 +1735,11 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) else bpf_object__unpin_programs(obj, pinfile); err_close_obj: + if (!legacy_libbpf) { + p_info("Warning: bpftool is now running in libbpf strict mode and has more stringent requirements about BPF programs.\n" + "If it used to work for this object file but now doesn't, see --legacy option for more details.\n"); + } + bpf_object__close(obj); err_free_reuse_maps: for (i = 0; i < old_map_fds; i++) @@ -1682,17 +1772,19 @@ static int try_loader(struct gen_loader_opts *gen) sizeof(struct bpf_prog_desc)); int log_buf_sz = (1u << 24) - 1; int err, fds_before, fd_delta; - char *log_buf; + char *log_buf = NULL; ctx = alloca(ctx_sz); memset(ctx, 0, ctx_sz); ctx->sz = ctx_sz; - ctx->log_level = 1; - ctx->log_size = log_buf_sz; - log_buf = malloc(log_buf_sz); - if (!log_buf) - return -ENOMEM; - ctx->log_buf = (long) log_buf; + if (verifier_logs) { + ctx->log_level = 1 + 2 + 4; + ctx->log_size = log_buf_sz; + log_buf = malloc(log_buf_sz); + if (!log_buf) + return -ENOMEM; + ctx->log_buf = (long) log_buf; + } opts.ctx = ctx; opts.data = gen->data; opts.data_sz = gen->data_sz; @@ -1701,9 +1793,9 @@ static int try_loader(struct gen_loader_opts *gen) fds_before = count_open_fds(); err = bpf_load_and_run(&opts); fd_delta = count_open_fds() - fds_before; - if (err < 0) { + if (err < 0 || verifier_logs) { fprintf(stderr, "err %d\n%s\n%s", err, opts.errstr, log_buf); - if (fd_delta) + if (fd_delta && err < 0) fprintf(stderr, "loader prog leaked %d FDs\n", fd_delta); } @@ -1715,7 +1807,6 @@ static int do_loader(int argc, char **argv) { DECLARE_LIBBPF_OPTS(bpf_object_open_opts, open_opts); DECLARE_LIBBPF_OPTS(gen_loader_opts, gen); - struct bpf_object_load_attr load_attr = {}; struct bpf_object *obj; const char *file; int err = 0; @@ -1724,6 +1815,10 @@ static int do_loader(int argc, char **argv) return -1; file = GET_ARG(); + if (verifier_logs) + /* log_level1 + log_level2 + stats, but not stable UAPI */ + open_opts.kernel_log_level = 1 + 2 + 4; + obj = bpf_object__open_file(file, &open_opts); if (libbpf_get_error(obj)) { p_err("failed to open object file"); @@ -1734,12 +1829,7 @@ static int do_loader(int argc, char **argv) if (err) goto err_close_obj; - load_attr.obj = obj; - if (verifier_logs) - /* log_level1 + log_level2 + stats, but not stable UAPI */ - load_attr.log_level = 1 + 2 + 4; - - err = bpf_object__load_xattr(&load_attr); + err = bpf_object__load(obj); if (err) { p_err("failed to load object file"); goto err_close_obj; @@ -2009,41 +2099,58 @@ static void profile_print_readings(void) static char *profile_target_name(int tgt_fd) { - struct bpf_prog_info_linear *info_linear; - struct bpf_func_info *func_info; + struct bpf_func_info func_info; + struct bpf_prog_info info = {}; + __u32 info_len = sizeof(info); const struct btf_type *t; + __u32 func_info_rec_size; struct btf *btf = NULL; char *name = NULL; + int err; - info_linear = bpf_program__get_prog_info_linear( - tgt_fd, 1UL << BPF_PROG_INFO_FUNC_INFO); - if (IS_ERR_OR_NULL(info_linear)) { - p_err("failed to get info_linear for prog FD %d", tgt_fd); - return NULL; + err = bpf_obj_get_info_by_fd(tgt_fd, &info, &info_len); + if (err) { + p_err("failed to bpf_obj_get_info_by_fd for prog FD %d", tgt_fd); + goto out; } - if (info_linear->info.btf_id == 0) { + if (info.btf_id == 0) { p_err("prog FD %d doesn't have valid btf", tgt_fd); goto out; } - btf = btf__load_from_kernel_by_id(info_linear->info.btf_id); + func_info_rec_size = info.func_info_rec_size; + if (info.nr_func_info == 0) { + p_err("bpf_obj_get_info_by_fd for prog FD %d found 0 func_info", tgt_fd); + goto out; + } + + memset(&info, 0, sizeof(info)); + info.nr_func_info = 1; + info.func_info_rec_size = func_info_rec_size; + info.func_info = ptr_to_u64(&func_info); + + err = bpf_obj_get_info_by_fd(tgt_fd, &info, &info_len); + if (err) { + p_err("failed to get func_info for prog FD %d", tgt_fd); + goto out; + } + + btf = btf__load_from_kernel_by_id(info.btf_id); if (libbpf_get_error(btf)) { p_err("failed to load btf for prog FD %d", tgt_fd); goto out; } - func_info = u64_to_ptr(info_linear->info.func_info); - t = btf__type_by_id(btf, func_info[0].type_id); + t = btf__type_by_id(btf, func_info.type_id); if (!t) { p_err("btf %d doesn't have type %d", - info_linear->info.btf_id, func_info[0].type_id); + info.btf_id, func_info.type_id); goto out; } name = strdup(btf__name_by_offset(btf, t->name_off)); out: btf__free(btf); - free(info_linear); return name; } diff --git a/tools/bpf/bpftool/skeleton/pid_iter.bpf.c b/tools/bpf/bpftool/skeleton/pid_iter.bpf.c index d9b4209729..f70702fcb2 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/bpftool/struct_ops.c b/tools/bpf/bpftool/struct_ops.c index ab2d229056..2f693b082b 100644 --- a/tools/bpf/bpftool/struct_ops.c +++ b/tools/bpf/bpftool/struct_ops.c @@ -32,7 +32,7 @@ static const struct btf *get_btf_vmlinux(void) return btf_vmlinux; btf_vmlinux = libbpf_find_kernel_btf(); - if (IS_ERR(btf_vmlinux)) + if (libbpf_get_error(btf_vmlinux)) p_err("struct_ops requires kernel CONFIG_DEBUG_INFO_BTF=y"); return btf_vmlinux; @@ -45,7 +45,7 @@ static const char *get_kern_struct_ops_name(const struct bpf_map_info *info) const char *st_ops_name; kern_btf = get_btf_vmlinux(); - if (IS_ERR(kern_btf)) + if (libbpf_get_error(kern_btf)) return ""; t = btf__type_by_id(kern_btf, info->btf_vmlinux_value_type_id); @@ -63,7 +63,7 @@ static __s32 get_map_info_type_id(void) return map_info_type_id; kern_btf = get_btf_vmlinux(); - if (IS_ERR(kern_btf)) { + if (libbpf_get_error(kern_btf)) { map_info_type_id = PTR_ERR(kern_btf); return map_info_type_id; } @@ -252,7 +252,7 @@ static struct res do_one_id(const char *id_str, work_func func, void *data, } fd = bpf_map_get_fd_by_id(id); - if (fd == -1) { + if (fd < 0) { p_err("can't get map by id (%lu): %s", id, strerror(errno)); res.nr_errs++; return res; @@ -415,7 +415,7 @@ static int do_dump(int argc, char **argv) } kern_btf = get_btf_vmlinux(); - if (IS_ERR(kern_btf)) + if (libbpf_get_error(kern_btf)) return -1; if (!json_output) { @@ -479,7 +479,7 @@ static int do_unregister(int argc, char **argv) static int do_register(int argc, char **argv) { - struct bpf_object_load_attr load_attr = {}; + LIBBPF_OPTS(bpf_object_open_opts, open_opts); const struct bpf_map_def *def; struct bpf_map_info info = {}; __u32 info_len = sizeof(info); @@ -494,18 +494,17 @@ static int do_register(int argc, char **argv) file = GET_ARG(); - obj = bpf_object__open(file); - if (IS_ERR_OR_NULL(obj)) + if (verifier_logs) + /* log_level1 + log_level2 + stats, but not stable UAPI */ + open_opts.kernel_log_level = 1 + 2 + 4; + + obj = bpf_object__open_file(file, &open_opts); + if (libbpf_get_error(obj)) return -1; set_max_rlimit(); - load_attr.obj = obj; - if (verifier_logs) - /* log_level1 + log_level2 + stats, but not stable UAPI */ - load_attr.log_level = 1 + 2 + 4; - - if (bpf_object__load_xattr(&load_attr)) { + if (bpf_object__load(obj)) { bpf_object__close(obj); return -1; } @@ -516,7 +515,7 @@ static int do_register(int argc, char **argv) continue; link = bpf_map__attach_struct_ops(map); - if (IS_ERR(link)) { + if (libbpf_get_error(link)) { p_err("can't register struct_ops %s: %s", bpf_map__name(map), strerror(-PTR_ERR(link))); @@ -596,7 +595,7 @@ int do_struct_ops(int argc, char **argv) err = cmd_select(cmds, argc, argv, do_help); - if (!IS_ERR(btf_vmlinux)) + if (!libbpf_get_error(btf_vmlinux)) btf__free(btf_vmlinux); return err; diff --git a/tools/bpf/resolve_btfids/Makefile b/tools/bpf/resolve_btfids/Makefile index af9f9d3534..320a88ac28 100644 --- a/tools/bpf/resolve_btfids/Makefile +++ b/tools/bpf/resolve_btfids/Makefile @@ -23,6 +23,7 @@ CC = $(HOSTCC) LD = $(HOSTLD) ARCH = $(HOSTARCH) RM ?= rm +CROSS_COMPILE = OUTPUT ?= $(srctree)/tools/bpf/resolve_btfids/ @@ -30,27 +31,33 @@ LIBBPF_SRC := $(srctree)/tools/lib/bpf/ SUBCMD_SRC := $(srctree)/tools/lib/subcmd/ BPFOBJ := $(OUTPUT)/libbpf/libbpf.a +LIBBPF_OUT := $(abspath $(dir $(BPFOBJ)))/ SUBCMDOBJ := $(OUTPUT)/libsubcmd/libsubcmd.a +LIBBPF_DESTDIR := $(LIBBPF_OUT) +LIBBPF_INCLUDE := $(LIBBPF_DESTDIR)include + BINARY := $(OUTPUT)/resolve_btfids BINARY_IN := $(BINARY)-in.o all: $(BINARY) -$(OUTPUT) $(OUTPUT)/libbpf $(OUTPUT)/libsubcmd: +$(OUTPUT) $(OUTPUT)/libsubcmd $(LIBBPF_OUT): $(call msg,MKDIR,,$@) $(Q)mkdir -p $(@) $(SUBCMDOBJ): fixdep FORCE | $(OUTPUT)/libsubcmd $(Q)$(MAKE) -C $(SUBCMD_SRC) OUTPUT=$(abspath $(dir $@))/ $(abspath $@) -$(BPFOBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(OUTPUT)/libbpf - $(Q)$(MAKE) $(submake_extras) -C $(LIBBPF_SRC) OUTPUT=$(abspath $(dir $@))/ $(abspath $@) +$(BPFOBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(LIBBPF_OUT) + $(Q)$(MAKE) $(submake_extras) -C $(LIBBPF_SRC) OUTPUT=$(LIBBPF_OUT) \ + DESTDIR=$(LIBBPF_DESTDIR) prefix= \ + $(abspath $@) install_headers CFLAGS := -g \ -I$(srctree)/tools/include \ -I$(srctree)/tools/include/uapi \ - -I$(LIBBPF_SRC) \ + -I$(LIBBPF_INCLUDE) \ -I$(SUBCMD_SRC) LIBS = -lelf -lz @@ -58,7 +65,7 @@ LIBS = -lelf -lz export srctree OUTPUT CFLAGS Q include $(srctree)/tools/build/Makefile.include -$(BINARY_IN): fixdep FORCE | $(OUTPUT) +$(BINARY_IN): $(BPFOBJ) fixdep FORCE | $(OUTPUT) $(Q)$(MAKE) $(build)=resolve_btfids $(BINARY): $(BPFOBJ) $(SUBCMDOBJ) $(BINARY_IN) @@ -68,7 +75,8 @@ $(BINARY): $(BPFOBJ) $(SUBCMDOBJ) $(BINARY_IN) clean_objects := $(wildcard $(OUTPUT)/*.o \ $(OUTPUT)/.*.o.cmd \ $(OUTPUT)/.*.o.d \ - $(OUTPUT)/libbpf \ + $(LIBBPF_OUT) \ + $(LIBBPF_DESTDIR) \ $(OUTPUT)/libsubcmd \ $(OUTPUT)/resolve_btfids) diff --git a/tools/bpf/resolve_btfids/main.c b/tools/bpf/resolve_btfids/main.c index 45e0d64061..5d26f3c6f9 100644 --- a/tools/bpf/resolve_btfids/main.c +++ b/tools/bpf/resolve_btfids/main.c @@ -60,8 +60,8 @@ #include #include #include -#include -#include +#include +#include #include #define BTF_IDS_SECTION ".BTF_ids" @@ -83,12 +83,14 @@ struct btf_id { int cnt; }; int addr_cnt; + bool is_set; Elf64_Addr addr[ADDR_CNT]; }; struct object { const char *path; const char *btf; + const char *base_btf_path; struct { int fd; @@ -450,8 +452,10 @@ static int symbols_collect(struct object *obj) * in symbol's size, together with 'cnt' field hence * that - 1. */ - if (id) + if (id) { id->cnt = sym.st_size / sizeof(int) - 1; + id->is_set = true; + } } else { pr_err("FAILED unsupported prefix %s\n", prefix); return -1; @@ -477,25 +481,36 @@ static int symbols_resolve(struct object *obj) int nr_structs = obj->nr_structs; int nr_unions = obj->nr_unions; int nr_funcs = obj->nr_funcs; + struct btf *base_btf = NULL; int err, type_id; struct btf *btf; __u32 nr_types; - btf = btf__parse(obj->btf ?: obj->path, NULL); + if (obj->base_btf_path) { + base_btf = btf__parse(obj->base_btf_path, NULL); + err = libbpf_get_error(base_btf); + if (err) { + pr_err("FAILED: load base BTF from %s: %s\n", + obj->base_btf_path, strerror(-err)); + return -1; + } + } + + btf = btf__parse_split(obj->btf ?: obj->path, base_btf); err = libbpf_get_error(btf); if (err) { pr_err("FAILED: load BTF from %s: %s\n", obj->btf ?: obj->path, strerror(-err)); - return -1; + goto out; } err = -1; - nr_types = btf__get_nr_types(btf); + nr_types = btf__type_cnt(btf); /* * Iterate all the BTF types and search for collected symbol IDs. */ - for (type_id = 1; type_id <= nr_types; type_id++) { + for (type_id = 1; type_id < nr_types; type_id++) { const struct btf_type *type; struct rb_root *root; struct btf_id *id; @@ -545,6 +560,7 @@ static int symbols_resolve(struct object *obj) err = 0; out: + btf__free(base_btf); btf__free(btf); return err; } @@ -555,9 +571,8 @@ static int id_patch(struct object *obj, struct btf_id *id) int *ptr = data->d_buf; int i; - if (!id->id) { + if (!id->id && !id->is_set) pr_err("WARN: resolve_btfids: unresolved symbol %s\n", id->name); - } for (i = 0; i < id->addr_cnt; i++) { unsigned long addr = id->addr[i]; @@ -678,7 +693,6 @@ static const char * const resolve_btfids_usage[] = { int main(int argc, const char **argv) { - bool no_fail = false; struct object obj = { .efile = { .idlist_shndx = -1, @@ -695,8 +709,8 @@ int main(int argc, const char **argv) "be more verbose (show errors, etc)"), OPT_STRING(0, "btf", &obj.btf, "BTF data", "BTF data"), - OPT_BOOLEAN(0, "no-fail", &no_fail, - "do not fail if " BTF_IDS_SECTION " section is not found"), + OPT_STRING('b', "btf_base", &obj.base_btf_path, "file", + "path of file providing base BTF"), OPT_END() }; int err = -1; @@ -717,9 +731,7 @@ int main(int argc, const char **argv) */ if (obj.efile.idlist_shndx == -1 || obj.efile.symbols_shndx == -1) { - if (no_fail) - return 0; - pr_err("FAILED to find needed sections\n"); + pr_debug("Cannot find .BTF_ids or symbols sections, nothing to do\n"); err = 0; goto out; } diff --git a/tools/bpf/runqslower/Makefile b/tools/bpf/runqslower/Makefile index 3818ec511f..da6de16a3d 100644 --- a/tools/bpf/runqslower/Makefile +++ b/tools/bpf/runqslower/Makefile @@ -9,10 +9,10 @@ BPFTOOL ?= $(DEFAULT_BPFTOOL) LIBBPF_SRC := $(abspath ../../lib/bpf) BPFOBJ_OUTPUT := $(OUTPUT)libbpf/ BPFOBJ := $(BPFOBJ_OUTPUT)libbpf.a -BPF_INCLUDE := $(BPFOBJ_OUTPUT) -INCLUDES := -I$(OUTPUT) -I$(BPF_INCLUDE) -I$(abspath ../../lib) \ - -I$(abspath ../../include/uapi) -CFLAGS := -g -Wall +BPF_DESTDIR := $(BPFOBJ_OUTPUT) +BPF_INCLUDE := $(BPF_DESTDIR)/include +INCLUDES := -I$(OUTPUT) -I$(BPF_INCLUDE) -I$(abspath ../../include/uapi) +CFLAGS := -g -Wall $(CLANG_CROSS_FLAGS) # Try to detect best kernel BTF source KERNEL_REL := $(shell uname -r) @@ -33,7 +33,7 @@ endif .DELETE_ON_ERROR: -.PHONY: all clean runqslower +.PHONY: all clean runqslower libbpf_hdrs all: runqslower runqslower: $(OUTPUT)/runqslower @@ -46,13 +46,15 @@ clean: $(Q)$(RM) $(OUTPUT)runqslower $(Q)$(RM) -r .output +libbpf_hdrs: $(BPFOBJ) + $(OUTPUT)/runqslower: $(OUTPUT)/runqslower.o $(BPFOBJ) $(QUIET_LINK)$(CC) $(CFLAGS) $^ -lelf -lz -o $@ $(OUTPUT)/runqslower.o: runqslower.h $(OUTPUT)/runqslower.skel.h \ - $(OUTPUT)/runqslower.bpf.o + $(OUTPUT)/runqslower.bpf.o | libbpf_hdrs -$(OUTPUT)/runqslower.bpf.o: $(OUTPUT)/vmlinux.h runqslower.h +$(OUTPUT)/runqslower.bpf.o: $(OUTPUT)/vmlinux.h runqslower.h | libbpf_hdrs $(OUTPUT)/%.skel.h: $(OUTPUT)/%.bpf.o | $(BPFTOOL) $(QUIET_GEN)$(BPFTOOL) gen skeleton $< > $@ @@ -81,8 +83,9 @@ else endif $(BPFOBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(BPFOBJ_OUTPUT) - $(Q)$(MAKE) $(submake_extras) -C $(LIBBPF_SRC) OUTPUT=$(BPFOBJ_OUTPUT) $@ + $(Q)$(MAKE) $(submake_extras) -C $(LIBBPF_SRC) OUTPUT=$(BPFOBJ_OUTPUT) \ + DESTDIR=$(BPFOBJ_OUTPUT) prefix= $(abspath $@) install_headers -$(DEFAULT_BPFTOOL): | $(BPFTOOL_OUTPUT) +$(DEFAULT_BPFTOOL): $(BPFOBJ) | $(BPFTOOL_OUTPUT) $(Q)$(MAKE) $(submake_extras) -C ../bpftool OUTPUT=$(BPFTOOL_OUTPUT) \ - CC=$(HOSTCC) LD=$(HOSTLD) + ARCH= CROSS_COMPILE= CC=$(HOSTCC) LD=$(HOSTLD) diff --git a/tools/bpf/runqslower/runqslower.bpf.c b/tools/bpf/runqslower/runqslower.bpf.c index ab9353f2fd..9a5c1f008f 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 d897158449..d78f414859 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; @@ -123,7 +123,6 @@ int main(int argc, char **argv) .parser = parse_arg, .doc = argp_program_doc, }; - struct perf_buffer_opts pb_opts; struct perf_buffer *pb = NULL; struct runqslower_bpf *obj; int err; @@ -165,9 +164,8 @@ int main(int argc, char **argv) printf("Tracing run queue latency higher than %llu us\n", env.min_us); printf("%-8s %-16s %-6s %14s\n", "TIME", "COMM", "PID", "LAT(us)"); - pb_opts.sample_cb = handle_event; - pb_opts.lost_cb = handle_lost_events; - pb = perf_buffer__new(bpf_map__fd(obj->maps.events), 64, &pb_opts); + pb = perf_buffer__new(bpf_map__fd(obj->maps.events), 64, + handle_event, handle_lost_events, NULL, NULL); err = libbpf_get_error(pb); if (err) { pb = NULL; diff --git a/tools/bpf/runqslower/runqslower.h b/tools/bpf/runqslower/runqslower.h index 9db225425e..4f70f07200 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 2cf3b1bde8..c2a95ab473 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/build/Makefile.feature b/tools/build/Makefile.feature index 88dd7db55d..ae61f46404 100644 --- a/tools/build/Makefile.feature +++ b/tools/build/Makefile.feature @@ -51,6 +51,7 @@ FEATURE_TESTS_BASIC := \ libslang \ libslang-include-subdir \ libtraceevent \ + libtracefs \ libcrypto \ libunwind \ pthread-attr-setaffinity-np \ diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile index e1e670014b..1480910c79 100644 --- a/tools/build/feature/Makefile +++ b/tools/build/feature/Makefile @@ -35,6 +35,7 @@ FILES= \ test-libslang.bin \ test-libslang-include-subdir.bin \ test-libtraceevent.bin \ + test-libtracefs.bin \ test-libcrypto.bin \ test-libunwind.bin \ test-libunwind-debug-frame.bin \ @@ -89,7 +90,7 @@ __BUILDXX = $(CXX) $(CXXFLAGS) -MD -Wall -Werror -o $@ $(patsubst %.bin,%.cpp,$( ############################### $(OUTPUT)test-all.bin: - $(BUILD) -fstack-protector-all -O2 -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lelf -I/usr/include/slang -lslang $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl -lz -llzma -lzstd -lcap + $(BUILD) -fstack-protector-all -O2 -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lelf -lslang $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl -lz -llzma -lzstd -lcap $(OUTPUT)test-hello.bin: $(BUILD) @@ -198,6 +199,9 @@ $(OUTPUT)test-libslang-include-subdir.bin: $(OUTPUT)test-libtraceevent.bin: $(BUILD) -ltraceevent +$(OUTPUT)test-libtracefs.bin: + $(BUILD) -ltracefs + $(OUTPUT)test-libcrypto.bin: $(BUILD) -lcrypto @@ -292,7 +296,7 @@ $(OUTPUT)test-jvmti-cmlr.bin: $(BUILD) $(OUTPUT)test-llvm.bin: - $(BUILDXX) -std=gnu++11 \ + $(BUILDXX) -std=gnu++14 \ -I$(shell $(LLVM_CONFIG) --includedir) \ -L$(shell $(LLVM_CONFIG) --libdir) \ $(shell $(LLVM_CONFIG) --libs Core BPF) \ @@ -300,12 +304,12 @@ $(OUTPUT)test-llvm.bin: > $(@:.bin=.make.output) 2>&1 $(OUTPUT)test-llvm-version.bin: - $(BUILDXX) -std=gnu++11 \ + $(BUILDXX) -std=gnu++14 \ -I$(shell $(LLVM_CONFIG) --includedir) \ > $(@:.bin=.make.output) 2>&1 $(OUTPUT)test-clang.bin: - $(BUILDXX) -std=gnu++11 \ + $(BUILDXX) -std=gnu++14 \ -I$(shell $(LLVM_CONFIG) --includedir) \ -L$(shell $(LLVM_CONFIG) --libdir) \ -Wl,--start-group -lclangBasic -lclangDriver \ diff --git a/tools/build/feature/test-bpf.c b/tools/build/feature/test-bpf.c index 82070eadfc..727d22e34a 100644 --- a/tools/build/feature/test-bpf.c +++ b/tools/build/feature/test-bpf.c @@ -14,6 +14,12 @@ # define __NR_bpf 349 # elif defined(__s390__) # define __NR_bpf 351 +# elif defined(__mips__) && defined(_ABIO32) +# define __NR_bpf 4355 +# elif defined(__mips__) && defined(_ABIN32) +# define __NR_bpf 6319 +# elif defined(__mips__) && defined(_ABI64) +# define __NR_bpf 5315 # else # error __NR_bpf not defined. libbpf does not support your arch. # endif diff --git a/tools/cgroup/memcg_slabinfo.py b/tools/cgroup/memcg_slabinfo.py index 1600b17dbb..1d3a90d93f 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 0076437f6e..b94a16ba5c 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 5d2ab38965..9ab313e935 100644 --- a/tools/include/asm-generic/bitops.h +++ b/tools/include/asm-generic/bitops.h @@ -18,7 +18,6 @@ #include #include #include -#include #ifndef _TOOLS_LINUX_BITOPS_H_ #error only can be included directly diff --git a/tools/include/linux/bitmap.h b/tools/include/linux/bitmap.h index 95611df1d2..ea97804d04 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 #include +#include #include #include @@ -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/linux/hash.h b/tools/include/linux/hash.h index ad6fa21d97..38edaa08f8 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/linux/kernel.h b/tools/include/linux/kernel.h index a7e54a08fb..9701e8307d 100644 --- a/tools/include/linux/kernel.h +++ b/tools/include/linux/kernel.h @@ -7,6 +7,7 @@ #include #include #include +#include #include #include @@ -14,8 +15,6 @@ #define UINT_MAX (~0U) #endif -#define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d)) - #define PERF_ALIGN(x, a) __PERF_ALIGN_MASK(x, (typeof(x))(a)-1) #define __PERF_ALIGN_MASK(x, mask) (((x)+(mask))&~(mask)) @@ -52,15 +51,6 @@ _min1 < _min2 ? _min1 : _min2; }) #endif -#ifndef roundup -#define roundup(x, y) ( \ -{ \ - const typeof(y) __y = y; \ - (((x) + (__y - 1)) / __y) * __y; \ -} \ -) -#endif - #ifndef BUG_ON #ifdef NDEBUG #define BUG_ON(cond) do { if (cond) {} } while (0) @@ -102,17 +92,9 @@ int vscnprintf(char *buf, size_t size, const char *fmt, va_list args); int scnprintf(char * buf, size_t size, const char * fmt, ...); int scnprintf_pad(char * buf, size_t size, const char * fmt, ...); +#ifndef ARRAY_SIZE #define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]) + __must_be_array(arr)) - -/* - * This looks more complex than it should be. But we need to - * get the type for the ~ right in round_down (it needs to be - * as wide as the result!), and we want to evaluate the macro - * arguments just once each. - */ -#define __round_mask(x, y) ((__typeof__(x))((y)-1)) -#define round_up(x, y) ((((x)-1) | __round_mask(x, y))+1) -#define round_down(x, y) ((x) & ~__round_mask(x, y)) +#endif #define current_gfp_context(k) 0 #define synchronize_rcu() diff --git a/tools/include/linux/objtool.h b/tools/include/linux/objtool.h index 7e72d975cb..aca52db2f3 100644 --- a/tools/include/linux/objtool.h +++ b/tools/include/linux/objtool.h @@ -66,6 +66,17 @@ struct unwind_hint { static void __used __section(".discard.func_stack_frame_non_standard") \ *__func_stack_frame_non_standard_##func = func +/* + * STACK_FRAME_NON_STANDARD_FP() is a frame-pointer-specific function ignore + * for the case where a function is intentionally missing frame pointer setup, + * but otherwise needs objtool/ORC coverage when frame pointers are disabled. + */ +#ifdef CONFIG_FRAME_POINTER +#define STACK_FRAME_NON_STANDARD_FP(func) STACK_FRAME_NON_STANDARD(func) +#else +#define STACK_FRAME_NON_STANDARD_FP(func) +#endif + #else /* __ASSEMBLY__ */ /* @@ -127,6 +138,7 @@ struct unwind_hint { #define UNWIND_HINT(sp_reg, sp_offset, type, end) \ "\n\t" #define STACK_FRAME_NON_STANDARD(func) +#define STACK_FRAME_NON_STANDARD_FP(func) #else #define ANNOTATE_INTRA_FUNCTION_CALL .macro UNWIND_HINT sp_reg:req sp_offset=0 type:req end=0 diff --git a/tools/include/linux/spinlock.h b/tools/include/linux/spinlock.h index c934572d93..622266b197 100644 --- a/tools/include/linux/spinlock.h +++ b/tools/include/linux/spinlock.h @@ -37,6 +37,4 @@ static inline bool arch_spin_is_locked(arch_spinlock_t *mutex) return true; } -#include - #endif diff --git a/tools/include/nolibc/nolibc.h b/tools/include/nolibc/nolibc.h index 3e2c6f2ed5..c1c285fe49 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" \ @@ -415,7 +420,7 @@ asm(".section .text\n" "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. "mov %eax, %edi\n" // retrieve exit code (32 bit) - "mov $60, %rax\n" // NR_exit == 60 + "mov $60, %eax\n" // NR_exit == 60 "syscall\n" // really exit "hlt\n" // ensure it does not return ""); @@ -1566,6 +1571,12 @@ pid_t sys_getpid(void) return my_syscall0(__NR_getpid); } +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) { @@ -2024,6 +2035,18 @@ pid_t getpid(void) return ret; } +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) { diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h index 1c5fb86d45..1c48b0ae3b 100644 --- a/tools/include/uapi/asm-generic/unistd.h +++ b/tools/include/uapi/asm-generic/unistd.h @@ -880,8 +880,14 @@ __SYSCALL(__NR_memfd_secret, sys_memfd_secret) #define __NR_process_mrelease 448 __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 449 +#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 3b810b53ba..642808520d 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/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h index bde5860b36..914ebd9290 100644 --- a/tools/include/uapi/drm/i915_drm.h +++ b/tools/include/uapi/drm/i915_drm.h @@ -1522,6 +1522,12 @@ struct drm_i915_gem_caching { #define I915_TILING_NONE 0 #define I915_TILING_X 1 #define I915_TILING_Y 2 +/* + * Do not add new tiling types here. The I915_TILING_* values are for + * de-tiling fence registers that no longer exist on modern platforms. Although + * the hardware may support new types of tiling in general (e.g., Tile4), we + * do not need to add them to the uapi that is specific to now-defunct ioctls. + */ #define I915_TILING_LAST I915_TILING_Y #define I915_BIT_6_SWIZZLE_NONE 0 @@ -1824,6 +1830,7 @@ struct drm_i915_gem_context_param { * Extensions: * i915_context_engines_load_balance (I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE) * i915_context_engines_bond (I915_CONTEXT_ENGINES_EXT_BOND) + * i915_context_engines_parallel_submit (I915_CONTEXT_ENGINES_EXT_PARALLEL_SUBMIT) */ #define I915_CONTEXT_PARAM_ENGINES 0xa @@ -1846,6 +1853,55 @@ struct drm_i915_gem_context_param { * attempted to use it, never re-use this context param number. */ #define I915_CONTEXT_PARAM_RINGSIZE 0xc + +/* + * I915_CONTEXT_PARAM_PROTECTED_CONTENT: + * + * Mark that the context makes use of protected content, which will result + * in the context being invalidated when the protected content session is. + * Given that the protected content session is killed on suspend, the device + * is kept awake for the lifetime of a protected context, so the user should + * make sure to dispose of them once done. + * This flag can only be set at context creation time and, when set to true, + * must be preceded by an explicit setting of I915_CONTEXT_PARAM_RECOVERABLE + * to false. This flag can't be set to true in conjunction with setting the + * I915_CONTEXT_PARAM_BANNABLE flag to false. Creation example: + * + * .. code-block:: C + * + * struct drm_i915_gem_context_create_ext_setparam p_protected = { + * .base = { + * .name = I915_CONTEXT_CREATE_EXT_SETPARAM, + * }, + * .param = { + * .param = I915_CONTEXT_PARAM_PROTECTED_CONTENT, + * .value = 1, + * } + * }; + * struct drm_i915_gem_context_create_ext_setparam p_norecover = { + * .base = { + * .name = I915_CONTEXT_CREATE_EXT_SETPARAM, + * .next_extension = to_user_pointer(&p_protected), + * }, + * .param = { + * .param = I915_CONTEXT_PARAM_RECOVERABLE, + * .value = 0, + * } + * }; + * struct drm_i915_gem_context_create_ext create = { + * .flags = I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS, + * .extensions = to_user_pointer(&p_norecover); + * }; + * + * ctx_id = gem_context_create_ext(drm_fd, &create); + * + * In addition to the normal failure cases, setting this flag during context + * creation can result in the following errors: + * + * -ENODEV: feature not available + * -EPERM: trying to mark a recoverable or not bannable context as protected + */ +#define I915_CONTEXT_PARAM_PROTECTED_CONTENT 0xd /* Must be kept compact -- no holes and well documented */ __u64 value; @@ -2049,6 +2105,135 @@ struct i915_context_engines_bond { struct i915_engine_class_instance engines[N__]; \ } __attribute__((packed)) name__ +/** + * struct i915_context_engines_parallel_submit - Configure engine for + * parallel submission. + * + * Setup a slot in the context engine map to allow multiple BBs to be submitted + * in a single execbuf IOCTL. Those BBs will then be scheduled to run on the GPU + * in parallel. Multiple hardware contexts are created internally in the i915 to + * run these BBs. Once a slot is configured for N BBs only N BBs can be + * submitted in each execbuf IOCTL and this is implicit behavior e.g. The user + * doesn't tell the execbuf IOCTL there are N BBs, the execbuf IOCTL knows how + * many BBs there are based on the slot's configuration. The N BBs are the last + * N buffer objects or first N if I915_EXEC_BATCH_FIRST is set. + * + * The default placement behavior is to create implicit bonds between each + * context if each context maps to more than 1 physical engine (e.g. context is + * a virtual engine). Also we only allow contexts of same engine class and these + * contexts must be in logically contiguous order. Examples of the placement + * behavior are described below. Lastly, the default is to not allow BBs to be + * preempted mid-batch. Rather insert coordinated preemption points on all + * hardware contexts between each set of BBs. Flags could be added in the future + * to change both of these default behaviors. + * + * Returns -EINVAL if hardware context placement configuration is invalid or if + * the placement configuration isn't supported on the platform / submission + * interface. + * Returns -ENODEV if extension isn't supported on the platform / submission + * interface. + * + * .. code-block:: none + * + * Examples syntax: + * CS[X] = generic engine of same class, logical instance X + * INVALID = I915_ENGINE_CLASS_INVALID, I915_ENGINE_CLASS_INVALID_NONE + * + * Example 1 pseudo code: + * set_engines(INVALID) + * set_parallel(engine_index=0, width=2, num_siblings=1, + * engines=CS[0],CS[1]) + * + * Results in the following valid placement: + * CS[0], CS[1] + * + * Example 2 pseudo code: + * set_engines(INVALID) + * set_parallel(engine_index=0, width=2, num_siblings=2, + * engines=CS[0],CS[2],CS[1],CS[3]) + * + * Results in the following valid placements: + * CS[0], CS[1] + * CS[2], CS[3] + * + * This can be thought of as two virtual engines, each containing two + * engines thereby making a 2D array. However, there are bonds tying the + * entries together and placing restrictions on how they can be scheduled. + * Specifically, the scheduler can choose only vertical columns from the 2D + * array. That is, CS[0] is bonded to CS[1] and CS[2] to CS[3]. So if the + * scheduler wants to submit to CS[0], it must also choose CS[1] and vice + * versa. Same for CS[2] requires also using CS[3]. + * VE[0] = CS[0], CS[2] + * VE[1] = CS[1], CS[3] + * + * Example 3 pseudo code: + * set_engines(INVALID) + * set_parallel(engine_index=0, width=2, num_siblings=2, + * engines=CS[0],CS[1],CS[1],CS[3]) + * + * Results in the following valid and invalid placements: + * CS[0], CS[1] + * CS[1], CS[3] - Not logically contiguous, return -EINVAL + */ +struct i915_context_engines_parallel_submit { + /** + * @base: base user extension. + */ + struct i915_user_extension base; + + /** + * @engine_index: slot for parallel engine + */ + __u16 engine_index; + + /** + * @width: number of contexts per parallel engine or in other words the + * number of batches in each submission + */ + __u16 width; + + /** + * @num_siblings: number of siblings per context or in other words the + * number of possible placements for each submission + */ + __u16 num_siblings; + + /** + * @mbz16: reserved for future use; must be zero + */ + __u16 mbz16; + + /** + * @flags: all undefined flags must be zero, currently not defined flags + */ + __u64 flags; + + /** + * @mbz64: reserved for future use; must be zero + */ + __u64 mbz64[3]; + + /** + * @engines: 2-d array of engine instances to configure parallel engine + * + * length = width (i) * num_siblings (j) + * index = j + i * num_siblings + */ + struct i915_engine_class_instance engines[0]; + +} __packed; + +#define I915_DEFINE_CONTEXT_ENGINES_PARALLEL_SUBMIT(name__, N__) struct { \ + struct i915_user_extension base; \ + __u16 engine_index; \ + __u16 width; \ + __u16 num_siblings; \ + __u16 mbz16; \ + __u64 flags; \ + __u64 mbz64[3]; \ + struct i915_engine_class_instance engines[N__]; \ +} __attribute__((packed)) name__ + /** * DOC: Context Engine Map uAPI * @@ -2108,6 +2293,7 @@ struct i915_context_param_engines { __u64 extensions; /* linked chain of extension blocks, 0 terminates */ #define I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE 0 /* see i915_context_engines_load_balance */ #define I915_CONTEXT_ENGINES_EXT_BOND 1 /* see i915_context_engines_bond */ +#define I915_CONTEXT_ENGINES_EXT_PARALLEL_SUBMIT 2 /* see i915_context_engines_parallel_submit */ struct i915_engine_class_instance engines[0]; } __attribute__((packed)); @@ -2726,14 +2912,20 @@ struct drm_i915_engine_info { /** @flags: Engine flags. */ __u64 flags; +#define I915_ENGINE_INFO_HAS_LOGICAL_INSTANCE (1 << 0) /** @capabilities: Capabilities of this engine. */ __u64 capabilities; #define I915_VIDEO_CLASS_CAPABILITY_HEVC (1 << 0) #define I915_VIDEO_AND_ENHANCE_CLASS_CAPABILITY_SFC (1 << 1) + /** @logical_instance: Logical instance of engine */ + __u16 logical_instance; + /** @rsvd1: Reserved fields. */ - __u64 rsvd1[4]; + __u16 rsvd1[3]; + /** @rsvd2: Reserved fields. */ + __u64 rsvd2[3]; }; /** @@ -2979,8 +3171,12 @@ struct drm_i915_gem_create_ext { * * For I915_GEM_CREATE_EXT_MEMORY_REGIONS usage see * struct drm_i915_gem_create_ext_memory_regions. + * + * For I915_GEM_CREATE_EXT_PROTECTED_CONTENT usage see + * struct drm_i915_gem_create_ext_protected_content. */ #define I915_GEM_CREATE_EXT_MEMORY_REGIONS 0 +#define I915_GEM_CREATE_EXT_PROTECTED_CONTENT 1 __u64 extensions; }; @@ -3038,6 +3234,50 @@ struct drm_i915_gem_create_ext_memory_regions { __u64 regions; }; +/** + * struct drm_i915_gem_create_ext_protected_content - The + * I915_OBJECT_PARAM_PROTECTED_CONTENT extension. + * + * If this extension is provided, buffer contents are expected to be protected + * by PXP encryption and require decryption for scan out and processing. This + * is only possible on platforms that have PXP enabled, on all other scenarios + * using this extension will cause the ioctl to fail and return -ENODEV. The + * flags parameter is reserved for future expansion and must currently be set + * to zero. + * + * The buffer contents are considered invalid after a PXP session teardown. + * + * The encryption is guaranteed to be processed correctly only if the object + * is submitted with a context created using the + * I915_CONTEXT_PARAM_PROTECTED_CONTENT flag. This will also enable extra checks + * at submission time on the validity of the objects involved. + * + * Below is an example on how to create a protected object: + * + * .. code-block:: C + * + * struct drm_i915_gem_create_ext_protected_content protected_ext = { + * .base = { .name = I915_GEM_CREATE_EXT_PROTECTED_CONTENT }, + * .flags = 0, + * }; + * struct drm_i915_gem_create_ext create_ext = { + * .size = PAGE_SIZE, + * .extensions = (uintptr_t)&protected_ext, + * }; + * + * int err = ioctl(fd, DRM_IOCTL_I915_GEM_CREATE_EXT, &create_ext); + * if (err) ... + */ +struct drm_i915_gem_create_ext_protected_content { + /** @base: Extension link. See struct i915_user_extension. */ + struct i915_user_extension base; + /** @flags: reserved for future usage, currently MBZ */ + __u32 flags; +}; + +/* ID of the protected content session managed by i915 when PXP is active */ +#define I915_PROTECTED_CONTENT_DEFAULT_SESSION 0xf + #if defined(__cplusplus) } #endif diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 791f31dd0a..b0383d371b 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -906,6 +906,7 @@ enum bpf_map_type { BPF_MAP_TYPE_RINGBUF, BPF_MAP_TYPE_INODE_STORAGE, BPF_MAP_TYPE_TASK_STORAGE, + BPF_MAP_TYPE_BLOOM_FILTER, }; /* Note that tracing related programs such as @@ -1274,6 +1275,13 @@ union bpf_attr { * struct stored as the * map value */ + /* Any per-map-type extra fields + * + * BPF_MAP_TYPE_BLOOM_FILTER - the lowest 4 bits indicate the + * number of hash functions (if 0, the bloom filter will default + * to using 5 hash functions). + */ + __u64 map_extra; }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ @@ -1334,8 +1342,10 @@ union bpf_attr { /* or valid module BTF object fd or 0 to attach to vmlinux */ __u32 attach_btf_obj_fd; }; - __u32 :32; /* pad */ + __u32 core_relo_cnt; /* number of bpf_core_relo */ __aligned_u64 fd_array; /* array of FDs */ + __aligned_u64 core_relos; + __u32 core_relo_rec_size; /* sizeof(struct bpf_core_relo) */ }; struct { /* anonymous struct used by BPF_OBJ_* commands */ @@ -1629,7 +1639,7 @@ union bpf_attr { * u32 bpf_get_smp_processor_id(void) * Description * Get the SMP (symmetric multiprocessing) processor id. Note that - * all programs run with preemption disabled, which means that the + * all programs run with migration disabled, which means that the * SMP processor id is stable during all the execution of the * program. * Return @@ -1736,7 +1746,7 @@ union bpf_attr { * if the maximum number of tail calls has been reached for this * chain of programs. This limit is defined in the kernel by the * macro **MAX_TAIL_CALL_CNT** (not accessible to user space), - * which is currently set to 32. + * which is currently set to 33. * Return * 0 on success, or a negative error in case of failure. * @@ -4046,7 +4056,7 @@ union bpf_attr { * arguments. The *data* are a **u64** array and corresponding format string * values are stored in the array. For strings and pointers where pointees * are accessed, only the pointer values are stored in the *data* array. - * The *data_len* is the size of *data* in bytes. + * The *data_len* is the size of *data* in bytes - must be a multiple of 8. * * Formats **%s**, **%p{i,I}{4,6}** requires to read kernel memory. * Reading kernel memory may fail due to either invalid address or @@ -4751,7 +4761,8 @@ union bpf_attr { * Each format specifier in **fmt** corresponds to one u64 element * in the **data** array. For strings and pointers where pointees * are accessed, only the pointer values are stored in the *data* - * array. The *data_len* is the size of *data* in bytes. + * array. The *data_len* is the size of *data* in bytes - must be + * a multiple of 8. * * Formats **%s** and **%p{i,I}{4,6}** require to read kernel * memory. Reading kernel memory may fail due to either invalid @@ -4877,6 +4888,136 @@ union bpf_attr { * Get the struct pt_regs associated with **task**. * Return * A pointer to struct pt_regs. + * + * long bpf_get_branch_snapshot(void *entries, u32 size, u64 flags) + * Description + * Get branch trace from hardware engines like Intel LBR. The + * hardware engine is stopped shortly after the helper is + * called. Therefore, the user need to filter branch entries + * based on the actual use case. To capture branch trace + * before the trigger point of the BPF program, the helper + * should be called at the beginning of the BPF program. + * + * The data is stored as struct perf_branch_entry into output + * buffer *entries*. *size* is the size of *entries* in bytes. + * *flags* is reserved for now and must be zero. + * + * Return + * On success, number of bytes written to *buf*. On error, a + * negative value. + * + * **-EINVAL** if *flags* is not zero. + * + * **-ENOENT** if architecture does not support branch records. + * + * long bpf_trace_vprintk(const char *fmt, u32 fmt_size, const void *data, u32 data_len) + * Description + * Behaves like **bpf_trace_printk**\ () helper, but takes an array of u64 + * to format and can handle more format args as a result. + * + * Arguments are to be used as in **bpf_seq_printf**\ () helper. + * Return + * The number of bytes written to the buffer, or a negative error + * in case of failure. + * + * struct unix_sock *bpf_skc_to_unix_sock(void *sk) + * Description + * Dynamically cast a *sk* pointer to a *unix_sock* pointer. + * Return + * *sk* if casting is valid, or **NULL** otherwise. + * + * long bpf_kallsyms_lookup_name(const char *name, int name_sz, int flags, u64 *res) + * Description + * Get the address of a kernel symbol, returned in *res*. *res* is + * set to 0 if the symbol is not found. + * Return + * On success, zero. On error, a negative value. + * + * **-EINVAL** if *flags* is not zero. + * + * **-EINVAL** if string *name* is not the same size as *name_sz*. + * + * **-ENOENT** if symbol is not found. + * + * **-EPERM** if caller does not have permission to obtain kernel address. + * + * long bpf_find_vma(struct task_struct *task, u64 addr, void *callback_fn, void *callback_ctx, u64 flags) + * Description + * Find vma of *task* that contains *addr*, call *callback_fn* + * function with *task*, *vma*, and *callback_ctx*. + * The *callback_fn* should be a static function and + * the *callback_ctx* should be a pointer to the stack. + * The *flags* is used to control certain aspects of the helper. + * Currently, the *flags* must be 0. + * + * The expected callback signature is + * + * long (\*callback_fn)(struct task_struct \*task, struct vm_area_struct \*vma, void \*callback_ctx); + * + * Return + * 0 on success. + * **-ENOENT** if *task->mm* is NULL, or no vma contains *addr*. + * **-EBUSY** if failed to try lock mmap_lock. + * **-EINVAL** for invalid **flags**. + * + * long bpf_loop(u32 nr_loops, void *callback_fn, void *callback_ctx, u64 flags) + * Description + * For **nr_loops**, call **callback_fn** function + * with **callback_ctx** as the context parameter. + * The **callback_fn** should be a static function and + * the **callback_ctx** should be a pointer to the stack. + * The **flags** is used to control certain aspects of the helper. + * Currently, the **flags** must be 0. Currently, nr_loops is + * limited to 1 << 23 (~8 million) loops. + * + * long (\*callback_fn)(u32 index, void \*ctx); + * + * where **index** is the current index in the loop. The index + * is zero-indexed. + * + * If **callback_fn** returns 0, the helper will continue to the next + * loop. If return value is 1, the helper will skip the rest of + * the loops and return. Other return values are not used now, + * and will be rejected by the verifier. + * + * Return + * The number of loops performed, **-EINVAL** for invalid **flags**, + * **-E2BIG** if **nr_loops** exceeds the maximum number of loops. + * + * long bpf_strncmp(const char *s1, u32 s1_sz, const char *s2) + * Description + * Do strncmp() between **s1** and **s2**. **s1** doesn't need + * to be null-terminated and **s1_sz** is the maximum storage + * size of **s1**. **s2** must be a read-only string. + * Return + * An integer less than, equal to, or greater than zero + * if the first **s1_sz** bytes of **s1** is found to be + * less than, to match, or be greater than **s2**. + * + * long bpf_get_func_arg(void *ctx, u32 n, u64 *value) + * Description + * Get **n**-th argument (zero based) of the traced function (for tracing programs) + * returned in **value**. + * + * Return + * 0 on success. + * **-EINVAL** if n >= arguments count of traced function. + * + * long bpf_get_func_ret(void *ctx, u64 *value) + * Description + * Get return value of the traced function (for tracing programs) + * in **value**. + * + * Return + * 0 on success. + * **-EOPNOTSUPP** for tracing programs other than BPF_TRACE_FEXIT or BPF_MODIFY_RETURN. + * + * long bpf_get_func_arg_cnt(void *ctx) + * Description + * Get number of arguments of the traced function (for tracing programs). + * + * Return + * The number of arguments of the traced function. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5055,6 +5196,16 @@ union bpf_attr { FN(get_func_ip), \ FN(get_attach_cookie), \ FN(task_pt_regs), \ + FN(get_branch_snapshot), \ + FN(trace_vprintk), \ + FN(skc_to_unix_sock), \ + FN(kallsyms_lookup_name), \ + FN(find_vma), \ + FN(loop), \ + FN(strncmp), \ + FN(get_func_arg), \ + FN(get_func_ret), \ + FN(get_func_arg_cnt), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper @@ -5284,6 +5435,8 @@ struct __sk_buff { __u32 gso_segs; __bpf_md_ptr(struct bpf_sock *, sk); __u32 gso_size; + __u32 :32; /* Padding, future use. */ + __u64 hwtstamp; }; struct bpf_tunnel_key { @@ -5577,6 +5730,7 @@ struct bpf_prog_info { __u64 run_time_ns; __u64 run_cnt; __u64 recursion_misses; + __u32 verified_insns; } __attribute__((aligned(8))); struct bpf_map_info { @@ -5594,6 +5748,8 @@ struct bpf_map_info { __u32 btf_id; __u32 btf_key_type_id; __u32 btf_value_type_id; + __u32 :32; /* alignment pad */ + __u64 map_extra; } __attribute__((aligned(8))); struct bpf_btf_info { @@ -6226,6 +6382,7 @@ struct bpf_sk_lookup { __u32 local_ip4; /* Network byte order */ __u32 local_ip6[4]; /* Network byte order */ __u32 local_port; /* Host byte order */ + __u32 ingress_ifindex; /* The arriving interface. Determined by inet_iif. */ }; /* @@ -6258,4 +6415,78 @@ enum { BTF_F_ZERO = (1ULL << 3), }; +/* bpf_core_relo_kind encodes which aspect of captured field/type/enum value + * has to be adjusted by relocations. It is emitted by llvm and passed to + * libbpf and later to the kernel. + */ +enum bpf_core_relo_kind { + BPF_CORE_FIELD_BYTE_OFFSET = 0, /* field byte offset */ + BPF_CORE_FIELD_BYTE_SIZE = 1, /* field size in bytes */ + BPF_CORE_FIELD_EXISTS = 2, /* field existence in target kernel */ + BPF_CORE_FIELD_SIGNED = 3, /* field signedness (0 - unsigned, 1 - signed) */ + BPF_CORE_FIELD_LSHIFT_U64 = 4, /* bitfield-specific left bitshift */ + BPF_CORE_FIELD_RSHIFT_U64 = 5, /* bitfield-specific right bitshift */ + BPF_CORE_TYPE_ID_LOCAL = 6, /* type ID in local BPF object */ + BPF_CORE_TYPE_ID_TARGET = 7, /* type ID in target kernel */ + BPF_CORE_TYPE_EXISTS = 8, /* type existence in target kernel */ + BPF_CORE_TYPE_SIZE = 9, /* type size in bytes */ + BPF_CORE_ENUMVAL_EXISTS = 10, /* enum value existence in target kernel */ + BPF_CORE_ENUMVAL_VALUE = 11, /* enum value integer value */ +}; + +/* + * "struct bpf_core_relo" is used to pass relocation data form LLVM to libbpf + * and from libbpf to the kernel. + * + * CO-RE relocation captures the following data: + * - insn_off - instruction offset (in bytes) within a BPF program that needs + * its insn->imm field to be relocated with actual field info; + * - type_id - BTF type ID of the "root" (containing) entity of a relocatable + * type or field; + * - access_str_off - offset into corresponding .BTF string section. String + * interpretation depends on specific relocation kind: + * - for field-based relocations, string encodes an accessed field using + * a sequence of field and array indices, separated by colon (:). It's + * conceptually very close to LLVM's getelementptr ([0]) instruction's + * arguments for identifying offset to a field. + * - for type-based relocations, strings is expected to be just "0"; + * - for enum value-based relocations, string contains an index of enum + * value within its enum type; + * - kind - one of enum bpf_core_relo_kind; + * + * Example: + * struct sample { + * int a; + * struct { + * int b[10]; + * }; + * }; + * + * struct sample *s = ...; + * int *x = &s->a; // encoded as "0:0" (a is field #0) + * int *y = &s->b[5]; // encoded as "0:1:0:5" (anon struct is field #1, + * // b is field #0 inside anon struct, accessing elem #5) + * int *z = &s[10]->b; // encoded as "10:1" (ptr is used as an array) + * + * type_id for all relocs in this example will capture BTF type id of + * `struct sample`. + * + * Such relocation is emitted when using __builtin_preserve_access_index() + * Clang built-in, passing expression that captures field address, e.g.: + * + * bpf_probe_read(&dst, sizeof(dst), + * __builtin_preserve_access_index(&src->a.b.c)); + * + * In this case Clang will emit field relocation recording necessary data to + * be able to find offset of embedded `a.b.c` field within `src` struct. + * + * [0] https://llvm.org/docs/LangRef.html#getelementptr-instruction + */ +struct bpf_core_relo { + __u32 insn_off; + __u32 type_id; + __u32 access_str_off; + enum bpf_core_relo_kind kind; +}; + #endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/tools/include/uapi/linux/btf.h b/tools/include/uapi/linux/btf.h index d27b1708ef..b0d8fea195 100644 --- a/tools/include/uapi/linux/btf.h +++ b/tools/include/uapi/linux/btf.h @@ -43,7 +43,7 @@ struct btf_type { * "size" tells the size of the type it is describing. * * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT, - * FUNC, FUNC_PROTO and VAR. + * FUNC, FUNC_PROTO, VAR, DECL_TAG and TYPE_TAG. * "type" is a type_id referring to another type. */ union { @@ -56,25 +56,30 @@ struct btf_type { #define BTF_INFO_VLEN(info) ((info) & 0xffff) #define BTF_INFO_KFLAG(info) ((info) >> 31) -#define BTF_KIND_UNKN 0 /* Unknown */ -#define BTF_KIND_INT 1 /* Integer */ -#define BTF_KIND_PTR 2 /* Pointer */ -#define BTF_KIND_ARRAY 3 /* Array */ -#define BTF_KIND_STRUCT 4 /* Struct */ -#define BTF_KIND_UNION 5 /* Union */ -#define BTF_KIND_ENUM 6 /* Enumeration */ -#define BTF_KIND_FWD 7 /* Forward */ -#define BTF_KIND_TYPEDEF 8 /* Typedef */ -#define BTF_KIND_VOLATILE 9 /* Volatile */ -#define BTF_KIND_CONST 10 /* Const */ -#define BTF_KIND_RESTRICT 11 /* Restrict */ -#define BTF_KIND_FUNC 12 /* Function */ -#define BTF_KIND_FUNC_PROTO 13 /* Function Proto */ -#define BTF_KIND_VAR 14 /* Variable */ -#define BTF_KIND_DATASEC 15 /* Section */ -#define BTF_KIND_FLOAT 16 /* Floating point */ -#define BTF_KIND_MAX BTF_KIND_FLOAT -#define NR_BTF_KINDS (BTF_KIND_MAX + 1) +enum { + BTF_KIND_UNKN = 0, /* Unknown */ + BTF_KIND_INT = 1, /* Integer */ + BTF_KIND_PTR = 2, /* Pointer */ + BTF_KIND_ARRAY = 3, /* Array */ + BTF_KIND_STRUCT = 4, /* Struct */ + BTF_KIND_UNION = 5, /* Union */ + BTF_KIND_ENUM = 6, /* Enumeration */ + BTF_KIND_FWD = 7, /* Forward */ + BTF_KIND_TYPEDEF = 8, /* Typedef */ + BTF_KIND_VOLATILE = 9, /* Volatile */ + BTF_KIND_CONST = 10, /* Const */ + BTF_KIND_RESTRICT = 11, /* Restrict */ + BTF_KIND_FUNC = 12, /* Function */ + BTF_KIND_FUNC_PROTO = 13, /* Function Proto */ + BTF_KIND_VAR = 14, /* Variable */ + BTF_KIND_DATASEC = 15, /* Section */ + BTF_KIND_FLOAT = 16, /* Floating point */ + BTF_KIND_DECL_TAG = 17, /* Decl Tag */ + BTF_KIND_TYPE_TAG = 18, /* Type Tag */ + + NR_BTF_KINDS, + BTF_KIND_MAX = NR_BTF_KINDS - 1, +}; /* For some specific BTF_KIND, "struct btf_type" is immediately * followed by extra data. @@ -170,4 +175,15 @@ struct btf_var_secinfo { __u32 size; }; +/* BTF_KIND_DECL_TAG is followed by a single "struct btf_decl_tag" to describe + * additional information related to the tag applied location. + * If component_idx == -1, the tag is applied to a struct, union, + * variable or function. Otherwise, it is applied to a struct/union + * member or a func argument, and component_idx indicates which member + * or argument (0 ... vlen-1). + */ +struct btf_decl_tag { + __s32 component_idx; +}; + #endif /* _UAPI__LINUX_BTF_H__ */ diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h index b3610fdd1f..6218f93f5c 100644 --- a/tools/include/uapi/linux/if_link.h +++ b/tools/include/uapi/linux/if_link.h @@ -7,24 +7,23 @@ /* This struct should be in sync with struct rtnl_link_stats64 */ struct rtnl_link_stats { - __u32 rx_packets; /* total packets received */ - __u32 tx_packets; /* total packets transmitted */ - __u32 rx_bytes; /* total bytes received */ - __u32 tx_bytes; /* total bytes transmitted */ - __u32 rx_errors; /* bad packets received */ - __u32 tx_errors; /* packet transmit problems */ - __u32 rx_dropped; /* no space in linux buffers */ - __u32 tx_dropped; /* no space available in linux */ - __u32 multicast; /* multicast packets received */ + __u32 rx_packets; + __u32 tx_packets; + __u32 rx_bytes; + __u32 tx_bytes; + __u32 rx_errors; + __u32 tx_errors; + __u32 rx_dropped; + __u32 tx_dropped; + __u32 multicast; __u32 collisions; - /* detailed rx_errors: */ __u32 rx_length_errors; - __u32 rx_over_errors; /* receiver ring buff overflow */ - __u32 rx_crc_errors; /* recved pkt with crc error */ - __u32 rx_frame_errors; /* recv'd frame alignment error */ - __u32 rx_fifo_errors; /* recv'r fifo overrun */ - __u32 rx_missed_errors; /* receiver missed packet */ + __u32 rx_over_errors; + __u32 rx_crc_errors; + __u32 rx_frame_errors; + __u32 rx_fifo_errors; + __u32 rx_missed_errors; /* detailed tx_errors */ __u32 tx_aborted_errors; @@ -37,29 +36,201 @@ struct rtnl_link_stats { __u32 rx_compressed; __u32 tx_compressed; - __u32 rx_nohandler; /* dropped, no handler found */ + __u32 rx_nohandler; }; -/* The main device statistics structure */ +/** + * struct rtnl_link_stats64 - The main device statistics structure. + * + * @rx_packets: Number of good packets received by the interface. + * For hardware interfaces counts all good packets received from the device + * by the host, including packets which host had to drop at various stages + * of processing (even in the driver). + * + * @tx_packets: Number of packets successfully transmitted. + * For hardware interfaces counts packets which host was able to successfully + * hand over to the device, which does not necessarily mean that packets + * had been successfully transmitted out of the device, only that device + * acknowledged it copied them out of host memory. + * + * @rx_bytes: Number of good received bytes, corresponding to @rx_packets. + * + * For IEEE 802.3 devices should count the length of Ethernet Frames + * excluding the FCS. + * + * @tx_bytes: Number of good transmitted bytes, corresponding to @tx_packets. + * + * For IEEE 802.3 devices should count the length of Ethernet Frames + * excluding the FCS. + * + * @rx_errors: Total number of bad packets received on this network device. + * This counter must include events counted by @rx_length_errors, + * @rx_crc_errors, @rx_frame_errors and other errors not otherwise + * counted. + * + * @tx_errors: Total number of transmit problems. + * This counter must include events counter by @tx_aborted_errors, + * @tx_carrier_errors, @tx_fifo_errors, @tx_heartbeat_errors, + * @tx_window_errors and other errors not otherwise counted. + * + * @rx_dropped: Number of packets received but not processed, + * e.g. due to lack of resources or unsupported protocol. + * For hardware interfaces this counter may include packets discarded + * due to L2 address filtering but should not include packets dropped + * by the device due to buffer exhaustion which are counted separately in + * @rx_missed_errors (since procfs folds those two counters together). + * + * @tx_dropped: Number of packets dropped on their way to transmission, + * e.g. due to lack of resources. + * + * @multicast: Multicast packets received. + * For hardware interfaces this statistic is commonly calculated + * at the device level (unlike @rx_packets) and therefore may include + * packets which did not reach the host. + * + * For IEEE 802.3 devices this counter may be equivalent to: + * + * - 30.3.1.1.21 aMulticastFramesReceivedOK + * + * @collisions: Number of collisions during packet transmissions. + * + * @rx_length_errors: Number of packets dropped due to invalid length. + * Part of aggregate "frame" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices this counter should be equivalent to a sum + * of the following attributes: + * + * - 30.3.1.1.23 aInRangeLengthErrors + * - 30.3.1.1.24 aOutOfRangeLengthField + * - 30.3.1.1.25 aFrameTooLongErrors + * + * @rx_over_errors: Receiver FIFO overflow event counter. + * + * Historically the count of overflow events. Such events may be + * reported in the receive descriptors or via interrupts, and may + * not correspond one-to-one with dropped packets. + * + * The recommended interpretation for high speed interfaces is - + * number of packets dropped because they did not fit into buffers + * provided by the host, e.g. packets larger than MTU or next buffer + * in the ring was not available for a scatter transfer. + * + * Part of aggregate "frame" errors in `/proc/net/dev`. + * + * This statistics was historically used interchangeably with + * @rx_fifo_errors. + * + * This statistic corresponds to hardware events and is not commonly used + * on software devices. + * + * @rx_crc_errors: Number of packets received with a CRC error. + * Part of aggregate "frame" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices this counter must be equivalent to: + * + * - 30.3.1.1.6 aFrameCheckSequenceErrors + * + * @rx_frame_errors: Receiver frame alignment errors. + * Part of aggregate "frame" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices this counter should be equivalent to: + * + * - 30.3.1.1.7 aAlignmentErrors + * + * @rx_fifo_errors: Receiver FIFO error counter. + * + * Historically the count of overflow events. Those events may be + * reported in the receive descriptors or via interrupts, and may + * not correspond one-to-one with dropped packets. + * + * This statistics was used interchangeably with @rx_over_errors. + * Not recommended for use in drivers for high speed interfaces. + * + * This statistic is used on software devices, e.g. to count software + * packet queue overflow (can) or sequencing errors (GRE). + * + * @rx_missed_errors: Count of packets missed by the host. + * Folded into the "drop" counter in `/proc/net/dev`. + * + * Counts number of packets dropped by the device due to lack + * of buffer space. This usually indicates that the host interface + * is slower than the network interface, or host is not keeping up + * with the receive packet rate. + * + * This statistic corresponds to hardware events and is not used + * on software devices. + * + * @tx_aborted_errors: + * Part of aggregate "carrier" errors in `/proc/net/dev`. + * For IEEE 802.3 devices capable of half-duplex operation this counter + * must be equivalent to: + * + * - 30.3.1.1.11 aFramesAbortedDueToXSColls + * + * High speed interfaces may use this counter as a general device + * discard counter. + * + * @tx_carrier_errors: Number of frame transmission errors due to loss + * of carrier during transmission. + * Part of aggregate "carrier" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices this counter must be equivalent to: + * + * - 30.3.1.1.13 aCarrierSenseErrors + * + * @tx_fifo_errors: Number of frame transmission errors due to device + * FIFO underrun / underflow. This condition occurs when the device + * begins transmission of a frame but is unable to deliver the + * entire frame to the transmitter in time for transmission. + * Part of aggregate "carrier" errors in `/proc/net/dev`. + * + * @tx_heartbeat_errors: Number of Heartbeat / SQE Test errors for + * old half-duplex Ethernet. + * Part of aggregate "carrier" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices possibly equivalent to: + * + * - 30.3.2.1.4 aSQETestErrors + * + * @tx_window_errors: Number of frame transmission errors due + * to late collisions (for Ethernet - after the first 64B of transmission). + * Part of aggregate "carrier" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices this counter must be equivalent to: + * + * - 30.3.1.1.10 aLateCollisions + * + * @rx_compressed: Number of correctly received compressed packets. + * This counters is only meaningful for interfaces which support + * packet compression (e.g. CSLIP, PPP). + * + * @tx_compressed: Number of transmitted compressed packets. + * This counters is only meaningful for interfaces which support + * packet compression (e.g. CSLIP, PPP). + * + * @rx_nohandler: Number of packets received on the interface + * but dropped by the networking stack because the device is + * not designated to receive packets (e.g. backup link in a bond). + */ struct rtnl_link_stats64 { - __u64 rx_packets; /* total packets received */ - __u64 tx_packets; /* total packets transmitted */ - __u64 rx_bytes; /* total bytes received */ - __u64 tx_bytes; /* total bytes transmitted */ - __u64 rx_errors; /* bad packets received */ - __u64 tx_errors; /* packet transmit problems */ - __u64 rx_dropped; /* no space in linux buffers */ - __u64 tx_dropped; /* no space available in linux */ - __u64 multicast; /* multicast packets received */ + __u64 rx_packets; + __u64 tx_packets; + __u64 rx_bytes; + __u64 tx_bytes; + __u64 rx_errors; + __u64 tx_errors; + __u64 rx_dropped; + __u64 tx_dropped; + __u64 multicast; __u64 collisions; /* detailed rx_errors: */ __u64 rx_length_errors; - __u64 rx_over_errors; /* receiver ring buff overflow */ - __u64 rx_crc_errors; /* recved pkt with crc error */ - __u64 rx_frame_errors; /* recv'd frame alignment error */ - __u64 rx_fifo_errors; /* recv'r fifo overrun */ - __u64 rx_missed_errors; /* receiver missed packet */ + __u64 rx_over_errors; + __u64 rx_crc_errors; + __u64 rx_frame_errors; + __u64 rx_fifo_errors; + __u64 rx_missed_errors; /* detailed tx_errors */ __u64 tx_aborted_errors; @@ -71,8 +242,7 @@ struct rtnl_link_stats64 { /* for cslip etc */ __u64 rx_compressed; __u64 tx_compressed; - - __u64 rx_nohandler; /* dropped, no handler found */ + __u64 rx_nohandler; }; /* The struct should be in sync with struct ifmap */ @@ -170,12 +340,30 @@ enum { IFLA_PROP_LIST, IFLA_ALT_IFNAME, /* Alternative ifname */ IFLA_PERM_ADDRESS, + IFLA_PROTO_DOWN_REASON, + + /* device (sysfs) name as parent, used instead + * of IFLA_LINK where there's no parent netdev + */ + IFLA_PARENT_DEV_NAME, + IFLA_PARENT_DEV_BUS_NAME, + IFLA_GRO_MAX_SIZE, + __IFLA_MAX }; #define IFLA_MAX (__IFLA_MAX - 1) +enum { + IFLA_PROTO_DOWN_REASON_UNSPEC, + IFLA_PROTO_DOWN_REASON_MASK, /* u32, mask for reason bits */ + IFLA_PROTO_DOWN_REASON_VALUE, /* u32, reason bit value */ + + __IFLA_PROTO_DOWN_REASON_CNT, + IFLA_PROTO_DOWN_REASON_MAX = __IFLA_PROTO_DOWN_REASON_CNT - 1 +}; + /* backwards compatibility for userspace */ #ifndef __KERNEL__ #define IFLA_RTA(r) ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct ifinfomsg)))) @@ -293,6 +481,7 @@ enum { IFLA_BR_MCAST_MLD_VERSION, IFLA_BR_VLAN_STATS_PER_PORT, IFLA_BR_MULTI_BOOLOPT, + IFLA_BR_MCAST_QUERIER_STATE, __IFLA_BR_MAX, }; @@ -346,6 +535,8 @@ enum { IFLA_BRPORT_BACKUP_PORT, IFLA_BRPORT_MRP_RING_OPEN, IFLA_BRPORT_MRP_IN_OPEN, + IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT, + IFLA_BRPORT_MCAST_EHT_HOSTS_CNT, __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) @@ -433,6 +624,7 @@ enum macvlan_macaddr_mode { }; #define MACVLAN_FLAG_NOPROMISC 1 +#define MACVLAN_FLAG_NODST 2 /* skip dst macvlan if matching src macvlan */ /* VRF section */ enum { @@ -597,6 +789,18 @@ enum ifla_geneve_df { GENEVE_DF_MAX = __GENEVE_DF_END - 1, }; +/* Bareudp section */ +enum { + IFLA_BAREUDP_UNSPEC, + IFLA_BAREUDP_PORT, + IFLA_BAREUDP_ETHERTYPE, + IFLA_BAREUDP_SRCPORT_MIN, + IFLA_BAREUDP_MULTIPROTO_MODE, + __IFLA_BAREUDP_MAX +}; + +#define IFLA_BAREUDP_MAX (__IFLA_BAREUDP_MAX - 1) + /* PPP section */ enum { IFLA_PPP_UNSPEC, @@ -655,6 +859,7 @@ enum { IFLA_BOND_TLB_DYNAMIC_LB, IFLA_BOND_PEER_NOTIF_DELAY, IFLA_BOND_AD_LACP_ACTIVE, + IFLA_BOND_MISSED_MAX, __IFLA_BOND_MAX, }; @@ -899,7 +1104,14 @@ enum { #define IFLA_IPOIB_MAX (__IFLA_IPOIB_MAX - 1) -/* HSR section */ +/* HSR/PRP section, both uses same interface */ + +/* Different redundancy protocols for hsr device */ +enum { + HSR_PROTOCOL_HSR, + HSR_PROTOCOL_PRP, + HSR_PROTOCOL_MAX, +}; enum { IFLA_HSR_UNSPEC, @@ -909,6 +1121,9 @@ enum { IFLA_HSR_SUPERVISION_ADDR, /* Supervision frame multicast addr */ IFLA_HSR_SEQ_NR, IFLA_HSR_VERSION, /* HSR version */ + IFLA_HSR_PROTOCOL, /* Indicate different protocol than + * HSR. For example PRP. + */ __IFLA_HSR_MAX, }; @@ -1033,6 +1248,8 @@ enum { #define RMNET_FLAGS_INGRESS_MAP_COMMANDS (1U << 1) #define RMNET_FLAGS_INGRESS_MAP_CKSUMV4 (1U << 2) #define RMNET_FLAGS_EGRESS_MAP_CKSUMV4 (1U << 3) +#define RMNET_FLAGS_INGRESS_MAP_CKSUMV5 (1U << 4) +#define RMNET_FLAGS_EGRESS_MAP_CKSUMV5 (1U << 5) enum { IFLA_RMNET_UNSPEC, @@ -1048,4 +1265,14 @@ struct ifla_rmnet_flags { __u32 mask; }; +/* MCTP section */ + +enum { + IFLA_MCTP_UNSPEC, + IFLA_MCTP_NET, + __IFLA_MCTP_MAX, +}; + +#define IFLA_MCTP_MAX (__IFLA_MCTP_MAX - 1) + #endif /* _UAPI_LINUX_IF_LINK_H */ diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index a067410ebe..507ee1f2aa 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -269,6 +269,7 @@ struct kvm_xen_exit { #define KVM_EXIT_AP_RESET_HOLD 32 #define KVM_EXIT_X86_BUS_LOCK 33 #define KVM_EXIT_XEN 34 +#define KVM_EXIT_RISCV_SBI 35 /* For KVM_EXIT_INTERNAL_ERROR */ /* Emulate instruction failed. */ @@ -397,13 +398,23 @@ struct kvm_run { * "ndata" is correct, that new fields are enumerated in "flags", * and that each flag enumerates fields that are 64-bit aligned * and sized (so that ndata+internal.data[] is valid/accurate). + * + * Space beyond the defined fields may be used to store arbitrary + * debug information relating to the emulation failure. It is + * accounted for in "ndata" but the format is unspecified and is + * not represented in "flags". Any such information is *not* ABI! */ struct { __u32 suberror; __u32 ndata; __u64 flags; - __u8 insn_size; - __u8 insn_bytes[15]; + union { + struct { + __u8 insn_size; + __u8 insn_bytes[15]; + }; + }; + /* Arbitrary debug data may follow. */ } emulation_failure; /* KVM_EXIT_OSI */ struct { @@ -469,6 +480,13 @@ struct kvm_run { } msr; /* KVM_EXIT_XEN */ struct kvm_xen_exit xen; + /* KVM_EXIT_RISCV_SBI */ + struct { + unsigned long extension_id; + unsigned long function_id; + unsigned long args[6]; + unsigned long ret[2]; + } riscv_sbi; /* Fix the size of the union. */ char padding[256]; }; @@ -1112,6 +1130,11 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_BINARY_STATS_FD 203 #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 @@ -1143,11 +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; @@ -1159,6 +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; }; @@ -1189,6 +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; @@ -1223,11 +1257,16 @@ struct kvm_irqfd { /* Do not use 1, KVM_CHECK_EXTENSION returned it before we had flags. */ #define KVM_CLOCK_TSC_STABLE 2 +#define KVM_CLOCK_REALTIME (1 << 2) +#define KVM_CLOCK_HOST_TSC (1 << 3) struct kvm_clock_data { __u64 clock; __u32 flags; - __u32 pad[9]; + __u32 pad0; + __u64 realtime; + __u64 host_tsc; + __u32 pad[4]; }; /* For KVM_CAP_SW_TLB */ @@ -2007,4 +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/perf_event.h b/tools/include/uapi/linux/perf_event.h index f92880a156..82858b697c 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -465,6 +465,8 @@ 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; }; @@ -1141,6 +1143,21 @@ enum perf_event_type { */ PERF_RECORD_TEXT_POKE = 20, + /* + * Data written to the AUX area by hardware due to aux_output, may need + * to be matched to the event by an architecture-specific hardware ID. + * This records the hardware ID, but requires sample_id to provide the + * event ID. e.g. Intel PT uses this record to disambiguate PEBS-via-PT + * records from multiple events. + * + * struct { + * struct perf_event_header header; + * u64 hw_id; + * struct sample_id sample_id; + * }; + */ + PERF_RECORD_AUX_OUTPUT_HW_ID = 21, + PERF_RECORD_MAX, /* non-ABI */ }; @@ -1210,14 +1227,16 @@ union perf_mem_data_src { mem_remote:1, /* remote */ mem_snoopx:2, /* snoop mode, ext */ mem_blk:3, /* access blocked */ - mem_rsvd:21; + mem_hops:3, /* hop level */ + mem_rsvd:18; }; }; #elif defined(__BIG_ENDIAN_BITFIELD) union perf_mem_data_src { __u64 val; struct { - __u64 mem_rsvd:21, + __u64 mem_rsvd:18, + mem_hops:3, /* hop level */ mem_blk:3, /* access blocked */ mem_snoopx:2, /* snoop mode, ext */ mem_remote:1, /* remote */ @@ -1241,7 +1260,13 @@ union perf_mem_data_src { #define PERF_MEM_OP_EXEC 0x10 /* code (execution) */ #define PERF_MEM_OP_SHIFT 0 -/* memory hierarchy (memory level, hit or miss) */ +/* + * PERF_MEM_LVL_* namespace being depricated to some extent in the + * favour of newer composite PERF_MEM_{LVLNUM_,REMOTE_,SNOOPX_} fields. + * Supporting this namespace inorder to not break defined ABIs. + * + * memory hierarchy (memory level, hit or miss) + */ #define PERF_MEM_LVL_NA 0x01 /* not available */ #define PERF_MEM_LVL_HIT 0x02 /* hit level */ #define PERF_MEM_LVL_MISS 0x04 /* miss level */ @@ -1307,6 +1332,14 @@ union perf_mem_data_src { #define PERF_MEM_BLK_ADDR 0x04 /* address conflict */ #define PERF_MEM_BLK_SHIFT 40 +/* hop level */ +#define PERF_MEM_HOPS_0 0x01 /* remote core, same node */ +#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) \ (((__u64)PERF_MEM_##a##_##s) << PERF_MEM_##a##_SHIFT) diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h index 43bd7f713c..e998764f02 100644 --- a/tools/include/uapi/linux/prctl.h +++ b/tools/include/uapi/linux/prctl.h @@ -235,7 +235,7 @@ struct prctl_mm_map { #define PR_GET_TAGGED_ADDR_CTRL 56 # define PR_TAGGED_ADDR_ENABLE (1UL << 0) /* MTE tag check fault modes */ -# define PR_MTE_TCF_NONE 0 +# define PR_MTE_TCF_NONE 0UL # define PR_MTE_TCF_SYNC (1UL << 1) # define PR_MTE_TCF_ASYNC (1UL << 2) # define PR_MTE_TCF_MASK (PR_MTE_TCF_SYNC | PR_MTE_TCF_ASYNC) @@ -268,5 +268,11 @@ struct prctl_mm_map { # define PR_SCHED_CORE_SHARE_TO 2 /* push core_sched cookie to pid */ # define PR_SCHED_CORE_SHARE_FROM 3 /* pull core_sched cookie to pid */ # define PR_SCHED_CORE_MAX 4 +# define PR_SCHED_CORE_SCOPE_THREAD 0 +# 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 93e40f91bd..2d3e5df39a 100644 --- a/tools/include/uapi/sound/asound.h +++ b/tools/include/uapi/sound/asound.h @@ -204,6 +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) @@ -302,7 +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 */ @@ -1004,7 +1009,7 @@ typedef int __bitwise snd_ctl_elem_iface_t; #define SNDRV_CTL_ELEM_ACCESS_WRITE (1<<1) #define SNDRV_CTL_ELEM_ACCESS_READWRITE (SNDRV_CTL_ELEM_ACCESS_READ|SNDRV_CTL_ELEM_ACCESS_WRITE) #define SNDRV_CTL_ELEM_ACCESS_VOLATILE (1<<2) /* control value may be changed without a notification */ -// (1 << 3) is unused. +/* (1 << 3) is unused. */ #define SNDRV_CTL_ELEM_ACCESS_TLV_READ (1<<4) /* TLV read is possible */ #define SNDRV_CTL_ELEM_ACCESS_TLV_WRITE (1<<5) /* TLV write is possible */ #define SNDRV_CTL_ELEM_ACCESS_TLV_READWRITE (SNDRV_CTL_ELEM_ACCESS_TLV_READ|SNDRV_CTL_ELEM_ACCESS_TLV_WRITE) diff --git a/tools/lib/bpf/.gitignore b/tools/lib/bpf/.gitignore index 5d4cfac671..0da84cb9e6 100644 --- a/tools/lib/bpf/.gitignore +++ b/tools/lib/bpf/.gitignore @@ -1,5 +1,4 @@ # SPDX-License-Identifier: GPL-2.0-only -libbpf_version.h libbpf.pc libbpf.so.* TAGS diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile index 74c3b73a5f..f947b61b21 100644 --- a/tools/lib/bpf/Makefile +++ b/tools/lib/bpf/Makefile @@ -8,7 +8,8 @@ VERSION_SCRIPT := libbpf.map LIBBPF_VERSION := $(shell \ grep -oE '^LIBBPF_([0-9.]+)' $(VERSION_SCRIPT) | \ sort -rV | head -n1 | cut -d'_' -f2) -LIBBPF_MAJOR_VERSION := $(firstword $(subst ., ,$(LIBBPF_VERSION))) +LIBBPF_MAJOR_VERSION := $(word 1,$(subst ., ,$(LIBBPF_VERSION))) +LIBBPF_MINOR_VERSION := $(word 2,$(subst ., ,$(LIBBPF_VERSION))) MAKEFLAGS += --no-print-directory @@ -59,7 +60,8 @@ ifndef VERBOSE VERBOSE = 0 endif -INCLUDES = -I. -I$(srctree)/tools/include -I$(srctree)/tools/include/uapi +INCLUDES = -I$(if $(OUTPUT),$(OUTPUT),.) \ + -I$(srctree)/tools/include -I$(srctree)/tools/include/uapi export prefix libdir src obj @@ -82,11 +84,13 @@ else endif # Append required CFLAGS +override CFLAGS += -std=gnu89 override CFLAGS += $(EXTRA_WARNINGS) -Wno-switch-enum override CFLAGS += -Werror -Wall override CFLAGS += $(INCLUDES) override CFLAGS += -fvisibility=hidden override CFLAGS += -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 +override CFLAGS += $(CLANG_CROSS_FLAGS) # flags specific for shared library SHLIB_FLAGS := -DSHARED -fPIC @@ -112,6 +116,7 @@ STATIC_OBJDIR := $(OUTPUT)staticobjs/ BPF_IN_SHARED := $(SHARED_OBJDIR)libbpf-in.o BPF_IN_STATIC := $(STATIC_OBJDIR)libbpf-in.o BPF_HELPER_DEFS := $(OUTPUT)bpf_helper_defs.h +BPF_GENERATED := $(BPF_HELPER_DEFS) LIB_TARGET := $(addprefix $(OUTPUT),$(LIB_TARGET)) LIB_FILE := $(addprefix $(OUTPUT),$(LIB_FILE)) @@ -136,25 +141,19 @@ all: fixdep all_cmd: $(CMD_TARGETS) check -$(BPF_IN_SHARED): force $(BPF_HELPER_DEFS) +$(BPF_IN_SHARED): force $(BPF_GENERATED) @(test -f ../../include/uapi/linux/bpf.h -a -f ../../../include/uapi/linux/bpf.h && ( \ (diff -B ../../include/uapi/linux/bpf.h ../../../include/uapi/linux/bpf.h >/dev/null) || \ echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/bpf.h' differs from latest version at 'include/uapi/linux/bpf.h'" >&2 )) || true @(test -f ../../include/uapi/linux/bpf_common.h -a -f ../../../include/uapi/linux/bpf_common.h && ( \ (diff -B ../../include/uapi/linux/bpf_common.h ../../../include/uapi/linux/bpf_common.h >/dev/null) || \ echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/bpf_common.h' differs from latest version at 'include/uapi/linux/bpf_common.h'" >&2 )) || true - @(test -f ../../include/uapi/linux/netlink.h -a -f ../../../include/uapi/linux/netlink.h && ( \ - (diff -B ../../include/uapi/linux/netlink.h ../../../include/uapi/linux/netlink.h >/dev/null) || \ - echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/netlink.h' differs from latest version at 'include/uapi/linux/netlink.h'" >&2 )) || true - @(test -f ../../include/uapi/linux/if_link.h -a -f ../../../include/uapi/linux/if_link.h && ( \ - (diff -B ../../include/uapi/linux/if_link.h ../../../include/uapi/linux/if_link.h >/dev/null) || \ - echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/if_link.h' differs from latest version at 'include/uapi/linux/if_link.h'" >&2 )) || true @(test -f ../../include/uapi/linux/if_xdp.h -a -f ../../../include/uapi/linux/if_xdp.h && ( \ (diff -B ../../include/uapi/linux/if_xdp.h ../../../include/uapi/linux/if_xdp.h >/dev/null) || \ echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/if_xdp.h' differs from latest version at 'include/uapi/linux/if_xdp.h'" >&2 )) || true $(Q)$(MAKE) $(build)=libbpf OUTPUT=$(SHARED_OBJDIR) CFLAGS="$(CFLAGS) $(SHLIB_FLAGS)" -$(BPF_IN_STATIC): force $(BPF_HELPER_DEFS) +$(BPF_IN_STATIC): force $(BPF_GENERATED) $(Q)$(MAKE) $(build)=libbpf OUTPUT=$(STATIC_OBJDIR) $(BPF_HELPER_DEFS): $(srctree)/tools/include/uapi/linux/bpf.h @@ -164,7 +163,7 @@ $(BPF_HELPER_DEFS): $(srctree)/tools/include/uapi/linux/bpf.h $(OUTPUT)libbpf.so: $(OUTPUT)libbpf.so.$(LIBBPF_VERSION) $(OUTPUT)libbpf.so.$(LIBBPF_VERSION): $(BPF_IN_SHARED) $(VERSION_SCRIPT) - $(QUIET_LINK)$(CC) $(LDFLAGS) \ + $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) \ --shared -Wl,-soname,libbpf.so.$(LIBBPF_MAJOR_VERSION) \ -Wl,--version-script=$(VERSION_SCRIPT) $< -lelf -lz -o $@ @ln -sf $(@F) $(OUTPUT)libbpf.so @@ -179,7 +178,7 @@ $(OUTPUT)libbpf.pc: -e "s|@VERSION@|$(LIBBPF_VERSION)|" \ < libbpf.pc.template > $@ -check: check_abi +check: check_abi check_version check_abi: $(OUTPUT)libbpf.so $(VERSION_SCRIPT) @if [ "$(GLOBAL_SYM_COUNT)" != "$(VERSIONED_SYM_COUNT)" ]; then \ @@ -205,6 +204,21 @@ check_abi: $(OUTPUT)libbpf.so $(VERSION_SCRIPT) exit 1; \ fi +HDR_MAJ_VERSION := $(shell grep -oE '^$(pound)define LIBBPF_MAJOR_VERSION ([0-9]+)$$' libbpf_version.h | cut -d' ' -f3) +HDR_MIN_VERSION := $(shell grep -oE '^$(pound)define LIBBPF_MINOR_VERSION ([0-9]+)$$' libbpf_version.h | cut -d' ' -f3) + +check_version: $(VERSION_SCRIPT) libbpf_version.h + @if [ "$(HDR_MAJ_VERSION)" != "$(LIBBPF_MAJOR_VERSION)" ]; then \ + echo "Error: libbpf major version mismatch detected: " \ + "'$(HDR_MAJ_VERSION)' != '$(LIBBPF_MAJOR_VERSION)'" >&2; \ + exit 1; \ + fi + @if [ "$(HDR_MIN_VERSION)" != "$(LIBBPF_MINOR_VERSION)" ]; then \ + echo "Error: libbpf minor version mismatch detected: " \ + "'$(HDR_MIN_VERSION)' != '$(LIBBPF_MINOR_VERSION)'" >&2; \ + exit 1; \ + fi + define do_install_mkdir if [ ! -d '$(DESTDIR_SQ)$1' ]; then \ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$1'; \ @@ -223,14 +237,24 @@ install_lib: all_cmd $(call do_install_mkdir,$(libdir_SQ)); \ cp -fpR $(LIB_FILE) $(DESTDIR)$(libdir_SQ) -INSTALL_HEADERS = bpf.h libbpf.h btf.h libbpf_common.h libbpf_legacy.h xsk.h \ - bpf_helpers.h $(BPF_HELPER_DEFS) bpf_tracing.h \ - bpf_endian.h bpf_core_read.h skel_internal.h +SRC_HDRS := bpf.h libbpf.h btf.h libbpf_common.h libbpf_legacy.h xsk.h \ + bpf_helpers.h bpf_tracing.h bpf_endian.h bpf_core_read.h \ + skel_internal.h libbpf_version.h +GEN_HDRS := $(BPF_GENERATED) -install_headers: $(BPF_HELPER_DEFS) - $(call QUIET_INSTALL, headers) \ - $(foreach hdr,$(INSTALL_HEADERS), \ - $(call do_install,$(hdr),$(prefix)/include/bpf,644);) +INSTALL_PFX := $(DESTDIR)$(prefix)/include/bpf +INSTALL_SRC_HDRS := $(addprefix $(INSTALL_PFX)/, $(SRC_HDRS)) +INSTALL_GEN_HDRS := $(addprefix $(INSTALL_PFX)/, $(notdir $(GEN_HDRS))) + +$(INSTALL_SRC_HDRS): $(INSTALL_PFX)/%.h: %.h + $(call QUIET_INSTALL, $@) \ + $(call do_install,$<,$(prefix)/include/bpf,644) + +$(INSTALL_GEN_HDRS): $(INSTALL_PFX)/%.h: $(OUTPUT)%.h + $(call QUIET_INSTALL, $@) \ + $(call do_install,$<,$(prefix)/include/bpf,644) + +install_headers: $(BPF_GENERATED) $(INSTALL_SRC_HDRS) $(INSTALL_GEN_HDRS) install_pkgconfig: $(PC_FILE) $(call QUIET_INSTALL, $(PC_FILE)) \ @@ -240,12 +264,12 @@ install: install_lib install_pkgconfig install_headers clean: $(call QUIET_CLEAN, libbpf) $(RM) -rf $(CMD_TARGETS) \ - *~ .*.d .*.cmd LIBBPF-CFLAGS $(BPF_HELPER_DEFS) \ + *~ .*.d .*.cmd LIBBPF-CFLAGS $(BPF_GENERATED) \ $(SHARED_OBJDIR) $(STATIC_OBJDIR) \ $(addprefix $(OUTPUT), \ *.o *.a *.so *.so.$(LIBBPF_MAJOR_VERSION) *.pc) -PHONY += force cscope tags +PHONY += force cscope tags check check_abi check_version force: cscope: diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index bfd1ce9fe2..550b4cbb6c 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -28,6 +28,9 @@ #include #include #include +#include +#include +#include #include "bpf.h" #include "libbpf.h" #include "libbpf_internal.h" @@ -49,6 +52,12 @@ # define __NR_bpf 351 # elif defined(__arc__) # define __NR_bpf 280 +# elif defined(__mips__) && defined(_ABIO32) +# define __NR_bpf 4355 +# elif defined(__mips__) && defined(_ABIN32) +# define __NR_bpf 6319 +# elif defined(__mips__) && defined(_ABI64) +# define __NR_bpf 5315 # else # error __NR_bpf not defined. libbpf does not support your arch. # endif @@ -65,133 +74,217 @@ static inline int sys_bpf(enum bpf_cmd cmd, union bpf_attr *attr, return syscall(__NR_bpf, cmd, attr, size); } -static inline int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size) +static inline int sys_bpf_fd(enum bpf_cmd cmd, union bpf_attr *attr, + unsigned int size) +{ + int fd; + + fd = sys_bpf(cmd, attr, size); + return ensure_good_fd(fd); +} + +#define PROG_LOAD_ATTEMPTS 5 + +static inline int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size, int attempts) { - int retries = 5; int fd; do { - fd = sys_bpf(BPF_PROG_LOAD, attr, size); - } while (fd < 0 && errno == EAGAIN && retries-- > 0); + fd = sys_bpf_fd(BPF_PROG_LOAD, attr, size); + } while (fd < 0 && errno == EAGAIN && --attempts > 0); return fd; } -int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr) +/* Probe whether kernel switched from memlock-based (RLIMIT_MEMLOCK) to + * memcg-based memory accounting for BPF maps and progs. This was done in [0]. + * We use the support for bpf_ktime_get_coarse_ns() helper, which was added in + * the same 5.11 Linux release ([1]), to detect memcg-based accounting for BPF. + * + * [0] https://lore.kernel.org/bpf/20201201215900.3569844-1-guro@fb.com/ + * [1] d05512618056 ("bpf: Add bpf_ktime_get_coarse_ns helper") + */ +int probe_memcg_account(void) { + const size_t prog_load_attr_sz = offsetofend(union bpf_attr, attach_btf_obj_fd); + struct bpf_insn insns[] = { + BPF_EMIT_CALL(BPF_FUNC_ktime_get_coarse_ns), + BPF_EXIT_INSN(), + }; + size_t insn_cnt = sizeof(insns) / sizeof(insns[0]); + union bpf_attr attr; + int prog_fd; + + /* attempt loading freplace trying to use custom BTF */ + memset(&attr, 0, prog_load_attr_sz); + attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER; + attr.insns = ptr_to_u64(insns); + attr.insn_cnt = insn_cnt; + attr.license = ptr_to_u64("GPL"); + + prog_fd = sys_bpf_fd(BPF_PROG_LOAD, &attr, prog_load_attr_sz); + if (prog_fd >= 0) { + close(prog_fd); + return 1; + } + return 0; +} + +static bool memlock_bumped; +static rlim_t memlock_rlim = RLIM_INFINITY; + +int libbpf_set_memlock_rlim(size_t memlock_bytes) +{ + if (memlock_bumped) + return libbpf_err(-EBUSY); + + memlock_rlim = memlock_bytes; + return 0; +} + +int bump_rlimit_memlock(void) +{ + struct rlimit rlim; + + /* this the default in libbpf 1.0, but for now user has to opt-in explicitly */ + if (!(libbpf_mode & LIBBPF_STRICT_AUTO_RLIMIT_MEMLOCK)) + return 0; + + /* if kernel supports memcg-based accounting, skip bumping RLIMIT_MEMLOCK */ + if (memlock_bumped || kernel_supports(NULL, FEAT_MEMCG_ACCOUNT)) + return 0; + + memlock_bumped = true; + + /* zero memlock_rlim_max disables auto-bumping RLIMIT_MEMLOCK */ + if (memlock_rlim == 0) + return 0; + + rlim.rlim_cur = rlim.rlim_max = memlock_rlim; + if (setrlimit(RLIMIT_MEMLOCK, &rlim)) + return -errno; + + return 0; +} + +int bpf_map_create(enum bpf_map_type map_type, + const char *map_name, + __u32 key_size, + __u32 value_size, + __u32 max_entries, + const struct bpf_map_create_opts *opts) +{ + const size_t attr_sz = offsetofend(union bpf_attr, map_extra); union bpf_attr attr; int fd; - memset(&attr, '\0', sizeof(attr)); + bump_rlimit_memlock(); - attr.map_type = create_attr->map_type; - attr.key_size = create_attr->key_size; - attr.value_size = create_attr->value_size; - attr.max_entries = create_attr->max_entries; - attr.map_flags = create_attr->map_flags; - if (create_attr->name) - memcpy(attr.map_name, create_attr->name, - min(strlen(create_attr->name), BPF_OBJ_NAME_LEN - 1)); - attr.numa_node = create_attr->numa_node; - attr.btf_fd = create_attr->btf_fd; - attr.btf_key_type_id = create_attr->btf_key_type_id; - attr.btf_value_type_id = create_attr->btf_value_type_id; - attr.map_ifindex = create_attr->map_ifindex; - if (attr.map_type == BPF_MAP_TYPE_STRUCT_OPS) - attr.btf_vmlinux_value_type_id = - create_attr->btf_vmlinux_value_type_id; - else - attr.inner_map_fd = create_attr->inner_map_fd; + memset(&attr, 0, attr_sz); - fd = sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr)); + if (!OPTS_VALID(opts, bpf_map_create_opts)) + return libbpf_err(-EINVAL); + + attr.map_type = map_type; + if (map_name) + libbpf_strlcpy(attr.map_name, map_name, sizeof(attr.map_name)); + attr.key_size = key_size; + attr.value_size = value_size; + attr.max_entries = max_entries; + + attr.btf_fd = OPTS_GET(opts, btf_fd, 0); + attr.btf_key_type_id = OPTS_GET(opts, btf_key_type_id, 0); + attr.btf_value_type_id = OPTS_GET(opts, btf_value_type_id, 0); + attr.btf_vmlinux_value_type_id = OPTS_GET(opts, btf_vmlinux_value_type_id, 0); + + attr.inner_map_fd = OPTS_GET(opts, inner_map_fd, 0); + attr.map_flags = OPTS_GET(opts, map_flags, 0); + attr.map_extra = OPTS_GET(opts, map_extra, 0); + attr.numa_node = OPTS_GET(opts, numa_node, 0); + attr.map_ifindex = OPTS_GET(opts, map_ifindex, 0); + + fd = sys_bpf_fd(BPF_MAP_CREATE, &attr, attr_sz); return libbpf_err_errno(fd); } +int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr) +{ + LIBBPF_OPTS(bpf_map_create_opts, p); + + p.map_flags = create_attr->map_flags; + p.numa_node = create_attr->numa_node; + p.btf_fd = create_attr->btf_fd; + p.btf_key_type_id = create_attr->btf_key_type_id; + p.btf_value_type_id = create_attr->btf_value_type_id; + p.map_ifindex = create_attr->map_ifindex; + if (create_attr->map_type == BPF_MAP_TYPE_STRUCT_OPS) + p.btf_vmlinux_value_type_id = create_attr->btf_vmlinux_value_type_id; + else + p.inner_map_fd = create_attr->inner_map_fd; + + return bpf_map_create(create_attr->map_type, create_attr->name, + create_attr->key_size, create_attr->value_size, + create_attr->max_entries, &p); +} + int bpf_create_map_node(enum bpf_map_type map_type, const char *name, int key_size, int value_size, int max_entries, __u32 map_flags, int node) { - struct bpf_create_map_attr map_attr = {}; + LIBBPF_OPTS(bpf_map_create_opts, opts); - map_attr.name = name; - map_attr.map_type = map_type; - map_attr.map_flags = map_flags; - map_attr.key_size = key_size; - map_attr.value_size = value_size; - map_attr.max_entries = max_entries; + opts.map_flags = map_flags; if (node >= 0) { - map_attr.numa_node = node; - map_attr.map_flags |= BPF_F_NUMA_NODE; + opts.numa_node = node; + opts.map_flags |= BPF_F_NUMA_NODE; } - return bpf_create_map_xattr(&map_attr); + return bpf_map_create(map_type, name, key_size, value_size, max_entries, &opts); } int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size, int max_entries, __u32 map_flags) { - struct bpf_create_map_attr map_attr = {}; + LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = map_flags); - map_attr.map_type = map_type; - map_attr.map_flags = map_flags; - map_attr.key_size = key_size; - map_attr.value_size = value_size; - map_attr.max_entries = max_entries; - - return bpf_create_map_xattr(&map_attr); + return bpf_map_create(map_type, NULL, key_size, value_size, max_entries, &opts); } int bpf_create_map_name(enum bpf_map_type map_type, const char *name, int key_size, int value_size, int max_entries, __u32 map_flags) { - struct bpf_create_map_attr map_attr = {}; + LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = map_flags); - map_attr.name = name; - map_attr.map_type = map_type; - map_attr.map_flags = map_flags; - map_attr.key_size = key_size; - map_attr.value_size = value_size; - map_attr.max_entries = max_entries; - - return bpf_create_map_xattr(&map_attr); + return bpf_map_create(map_type, name, key_size, value_size, max_entries, &opts); } int bpf_create_map_in_map_node(enum bpf_map_type map_type, const char *name, int key_size, int inner_map_fd, int max_entries, __u32 map_flags, int node) { - union bpf_attr attr; - int fd; - - memset(&attr, '\0', sizeof(attr)); - - attr.map_type = map_type; - attr.key_size = key_size; - attr.value_size = 4; - attr.inner_map_fd = inner_map_fd; - attr.max_entries = max_entries; - attr.map_flags = map_flags; - if (name) - memcpy(attr.map_name, name, - min(strlen(name), BPF_OBJ_NAME_LEN - 1)); + LIBBPF_OPTS(bpf_map_create_opts, opts); + opts.inner_map_fd = inner_map_fd; + opts.map_flags = map_flags; if (node >= 0) { - attr.map_flags |= BPF_F_NUMA_NODE; - attr.numa_node = node; + opts.map_flags |= BPF_F_NUMA_NODE; + opts.numa_node = node; } - fd = sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr)); - return libbpf_err_errno(fd); + return bpf_map_create(map_type, name, key_size, 4, max_entries, &opts); } int bpf_create_map_in_map(enum bpf_map_type map_type, const char *name, int key_size, int inner_map_fd, int max_entries, __u32 map_flags) { - return bpf_create_map_in_map_node(map_type, name, key_size, - inner_map_fd, max_entries, map_flags, - -1); + LIBBPF_OPTS(bpf_map_create_opts, opts, + .inner_map_fd = inner_map_fd, + .map_flags = map_flags, + ); + + return bpf_map_create(map_type, name, key_size, 4, max_entries, &opts); } static void * @@ -219,57 +312,95 @@ alloc_zero_tailing_info(const void *orecord, __u32 cnt, return info; } -int libbpf__bpf_prog_load(const struct bpf_prog_load_params *load_attr) +DEFAULT_VERSION(bpf_prog_load_v0_6_0, bpf_prog_load, LIBBPF_0.6.0) +int bpf_prog_load_v0_6_0(enum bpf_prog_type prog_type, + const char *prog_name, const char *license, + const struct bpf_insn *insns, size_t insn_cnt, + const struct bpf_prog_load_opts *opts) { void *finfo = NULL, *linfo = NULL; + const char *func_info, *line_info; + __u32 log_size, log_level, attach_prog_fd, attach_btf_obj_fd; + __u32 func_info_rec_size, line_info_rec_size; + int fd, attempts; union bpf_attr attr; - int fd; + char *log_buf; - if (!load_attr->log_buf != !load_attr->log_buf_sz) + bump_rlimit_memlock(); + + if (!OPTS_VALID(opts, bpf_prog_load_opts)) return libbpf_err(-EINVAL); - if (load_attr->log_level > (4 | 2 | 1) || (load_attr->log_level && !load_attr->log_buf)) + attempts = OPTS_GET(opts, attempts, 0); + if (attempts < 0) return libbpf_err(-EINVAL); + if (attempts == 0) + attempts = PROG_LOAD_ATTEMPTS; memset(&attr, 0, sizeof(attr)); - attr.prog_type = load_attr->prog_type; - attr.expected_attach_type = load_attr->expected_attach_type; - if (load_attr->attach_prog_fd) - attr.attach_prog_fd = load_attr->attach_prog_fd; + attr.prog_type = prog_type; + attr.expected_attach_type = OPTS_GET(opts, expected_attach_type, 0); + + attr.prog_btf_fd = OPTS_GET(opts, prog_btf_fd, 0); + attr.prog_flags = OPTS_GET(opts, prog_flags, 0); + attr.prog_ifindex = OPTS_GET(opts, prog_ifindex, 0); + attr.kern_version = OPTS_GET(opts, kern_version, 0); + + if (prog_name) + libbpf_strlcpy(attr.prog_name, prog_name, sizeof(attr.prog_name)); + attr.license = ptr_to_u64(license); + + if (insn_cnt > UINT_MAX) + return libbpf_err(-E2BIG); + + attr.insns = ptr_to_u64(insns); + attr.insn_cnt = (__u32)insn_cnt; + + attach_prog_fd = OPTS_GET(opts, attach_prog_fd, 0); + attach_btf_obj_fd = OPTS_GET(opts, attach_btf_obj_fd, 0); + + if (attach_prog_fd && attach_btf_obj_fd) + return libbpf_err(-EINVAL); + + attr.attach_btf_id = OPTS_GET(opts, attach_btf_id, 0); + if (attach_prog_fd) + attr.attach_prog_fd = attach_prog_fd; else - attr.attach_btf_obj_fd = load_attr->attach_btf_obj_fd; - attr.attach_btf_id = load_attr->attach_btf_id; + attr.attach_btf_obj_fd = attach_btf_obj_fd; - attr.prog_ifindex = load_attr->prog_ifindex; - attr.kern_version = load_attr->kern_version; + log_buf = OPTS_GET(opts, log_buf, NULL); + log_size = OPTS_GET(opts, log_size, 0); + log_level = OPTS_GET(opts, log_level, 0); - attr.insn_cnt = (__u32)load_attr->insn_cnt; - attr.insns = ptr_to_u64(load_attr->insns); - attr.license = ptr_to_u64(load_attr->license); + if (!!log_buf != !!log_size) + return libbpf_err(-EINVAL); + if (log_level > (4 | 2 | 1)) + return libbpf_err(-EINVAL); + if (log_level && !log_buf) + return libbpf_err(-EINVAL); - attr.log_level = load_attr->log_level; - if (attr.log_level) { - attr.log_buf = ptr_to_u64(load_attr->log_buf); - attr.log_size = load_attr->log_buf_sz; + func_info_rec_size = OPTS_GET(opts, func_info_rec_size, 0); + func_info = OPTS_GET(opts, func_info, NULL); + attr.func_info_rec_size = func_info_rec_size; + attr.func_info = ptr_to_u64(func_info); + attr.func_info_cnt = OPTS_GET(opts, func_info_cnt, 0); + + line_info_rec_size = OPTS_GET(opts, line_info_rec_size, 0); + line_info = OPTS_GET(opts, line_info, NULL); + attr.line_info_rec_size = line_info_rec_size; + attr.line_info = ptr_to_u64(line_info); + attr.line_info_cnt = OPTS_GET(opts, line_info_cnt, 0); + + attr.fd_array = ptr_to_u64(OPTS_GET(opts, fd_array, NULL)); + + if (log_level) { + attr.log_buf = ptr_to_u64(log_buf); + attr.log_size = log_size; + attr.log_level = log_level; } - attr.prog_btf_fd = load_attr->prog_btf_fd; - attr.prog_flags = load_attr->prog_flags; - - attr.func_info_rec_size = load_attr->func_info_rec_size; - attr.func_info_cnt = load_attr->func_info_cnt; - attr.func_info = ptr_to_u64(load_attr->func_info); - - attr.line_info_rec_size = load_attr->line_info_rec_size; - attr.line_info_cnt = load_attr->line_info_cnt; - attr.line_info = ptr_to_u64(load_attr->line_info); - - if (load_attr->name) - memcpy(attr.prog_name, load_attr->name, - min(strlen(load_attr->name), (size_t)BPF_OBJ_NAME_LEN - 1)); - - fd = sys_bpf_prog_load(&attr, sizeof(attr)); + fd = sys_bpf_prog_load(&attr, sizeof(attr), attempts); if (fd >= 0) return fd; @@ -279,11 +410,11 @@ int libbpf__bpf_prog_load(const struct bpf_prog_load_params *load_attr) */ while (errno == E2BIG && (!finfo || !linfo)) { if (!finfo && attr.func_info_cnt && - attr.func_info_rec_size < load_attr->func_info_rec_size) { + attr.func_info_rec_size < func_info_rec_size) { /* try with corrected func info records */ - finfo = alloc_zero_tailing_info(load_attr->func_info, - load_attr->func_info_cnt, - load_attr->func_info_rec_size, + finfo = alloc_zero_tailing_info(func_info, + attr.func_info_cnt, + func_info_rec_size, attr.func_info_rec_size); if (!finfo) { errno = E2BIG; @@ -291,13 +422,12 @@ int libbpf__bpf_prog_load(const struct bpf_prog_load_params *load_attr) } attr.func_info = ptr_to_u64(finfo); - attr.func_info_rec_size = load_attr->func_info_rec_size; + attr.func_info_rec_size = func_info_rec_size; } else if (!linfo && attr.line_info_cnt && - attr.line_info_rec_size < - load_attr->line_info_rec_size) { - linfo = alloc_zero_tailing_info(load_attr->line_info, - load_attr->line_info_cnt, - load_attr->line_info_rec_size, + attr.line_info_rec_size < line_info_rec_size) { + linfo = alloc_zero_tailing_info(line_info, + attr.line_info_cnt, + line_info_rec_size, attr.line_info_rec_size); if (!linfo) { errno = E2BIG; @@ -305,26 +435,27 @@ int libbpf__bpf_prog_load(const struct bpf_prog_load_params *load_attr) } attr.line_info = ptr_to_u64(linfo); - attr.line_info_rec_size = load_attr->line_info_rec_size; + attr.line_info_rec_size = line_info_rec_size; } else { break; } - fd = sys_bpf_prog_load(&attr, sizeof(attr)); + fd = sys_bpf_prog_load(&attr, sizeof(attr), attempts); if (fd >= 0) goto done; } - if (load_attr->log_level || !load_attr->log_buf) - goto done; + if (log_level == 0 && log_buf) { + /* log_level == 0 with non-NULL log_buf requires retrying on error + * with log_level == 1 and log_buf/log_buf_size set, to get details of + * failure + */ + attr.log_buf = ptr_to_u64(log_buf); + attr.log_size = log_size; + attr.log_level = 1; - /* Try again with log */ - attr.log_buf = ptr_to_u64(load_attr->log_buf); - attr.log_size = load_attr->log_buf_sz; - attr.log_level = 1; - load_attr->log_buf[0] = 0; - - fd = sys_bpf_prog_load(&attr, sizeof(attr)); + fd = sys_bpf_prog_load(&attr, sizeof(attr), attempts); + } done: /* free() doesn't affect errno, so we don't need to restore it */ free(finfo); @@ -332,17 +463,20 @@ int libbpf__bpf_prog_load(const struct bpf_prog_load_params *load_attr) return libbpf_err_errno(fd); } +__attribute__((alias("bpf_load_program_xattr2"))) int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr, - char *log_buf, size_t log_buf_sz) + char *log_buf, size_t log_buf_sz); + +static int bpf_load_program_xattr2(const struct bpf_load_program_attr *load_attr, + char *log_buf, size_t log_buf_sz) { - struct bpf_prog_load_params p = {}; + LIBBPF_OPTS(bpf_prog_load_opts, p); if (!load_attr || !log_buf != !log_buf_sz) return libbpf_err(-EINVAL); - p.prog_type = load_attr->prog_type; p.expected_attach_type = load_attr->expected_attach_type; - switch (p.prog_type) { + switch (load_attr->prog_type) { case BPF_PROG_TYPE_STRUCT_OPS: case BPF_PROG_TYPE_LSM: p.attach_btf_id = load_attr->attach_btf_id; @@ -356,12 +490,9 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr, p.prog_ifindex = load_attr->prog_ifindex; p.kern_version = load_attr->kern_version; } - p.insn_cnt = load_attr->insns_cnt; - p.insns = load_attr->insns; - p.license = load_attr->license; p.log_level = load_attr->log_level; p.log_buf = log_buf; - p.log_buf_sz = log_buf_sz; + p.log_size = log_buf_sz; p.prog_btf_fd = load_attr->prog_btf_fd; p.func_info_rec_size = load_attr->func_info_rec_size; p.func_info_cnt = load_attr->func_info_cnt; @@ -369,10 +500,10 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr, p.line_info_rec_size = load_attr->line_info_rec_size; p.line_info_cnt = load_attr->line_info_cnt; p.line_info = load_attr->line_info; - p.name = load_attr->name; p.prog_flags = load_attr->prog_flags; - return libbpf__bpf_prog_load(&p); + return bpf_prog_load(load_attr->prog_type, load_attr->name, load_attr->license, + load_attr->insns, load_attr->insns_cnt, &p); } int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns, @@ -391,7 +522,7 @@ int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns, load_attr.license = license; load_attr.kern_version = kern_version; - return bpf_load_program_xattr(&load_attr, log_buf, log_buf_sz); + return bpf_load_program_xattr2(&load_attr, log_buf, log_buf_sz); } int bpf_verify_program(enum bpf_prog_type type, const struct bpf_insn *insns, @@ -402,6 +533,8 @@ int bpf_verify_program(enum bpf_prog_type type, const struct bpf_insn *insns, union bpf_attr attr; int fd; + bump_rlimit_memlock(); + memset(&attr, 0, sizeof(attr)); attr.prog_type = type; attr.insn_cnt = (__u32)insns_cnt; @@ -414,7 +547,7 @@ int bpf_verify_program(enum bpf_prog_type type, const struct bpf_insn *insns, attr.kern_version = kern_version; attr.prog_flags = prog_flags; - fd = sys_bpf_prog_load(&attr, sizeof(attr)); + fd = sys_bpf_prog_load(&attr, sizeof(attr), PROG_LOAD_ATTEMPTS); return libbpf_err_errno(fd); } @@ -558,11 +691,11 @@ static int bpf_map_batch_common(int cmd, int fd, void *in_batch, return libbpf_err_errno(ret); } -int bpf_map_delete_batch(int fd, void *keys, __u32 *count, +int bpf_map_delete_batch(int fd, const void *keys, __u32 *count, const struct bpf_map_batch_opts *opts) { return bpf_map_batch_common(BPF_MAP_DELETE_BATCH, fd, NULL, - NULL, keys, NULL, count, opts); + NULL, (void *)keys, NULL, count, opts); } int bpf_map_lookup_batch(int fd, void *in_batch, void *out_batch, void *keys, @@ -582,11 +715,11 @@ int bpf_map_lookup_and_delete_batch(int fd, void *in_batch, void *out_batch, count, opts); } -int bpf_map_update_batch(int fd, void *keys, void *values, __u32 *count, +int bpf_map_update_batch(int fd, const void *keys, const void *values, __u32 *count, const struct bpf_map_batch_opts *opts) { return bpf_map_batch_common(BPF_MAP_UPDATE_BATCH, fd, NULL, NULL, - keys, values, count, opts); + (void *)keys, (void *)values, count, opts); } int bpf_obj_pin(int fd, const char *pathname) @@ -610,7 +743,7 @@ int bpf_obj_get(const char *pathname) memset(&attr, 0, sizeof(attr)); attr.pathname = ptr_to_u64((void *)pathname); - fd = sys_bpf(BPF_OBJ_GET, &attr, sizeof(attr)); + fd = sys_bpf_fd(BPF_OBJ_GET, &attr, sizeof(attr)); return libbpf_err_errno(fd); } @@ -721,7 +854,7 @@ int bpf_link_create(int prog_fd, int target_fd, break; } proceed: - fd = sys_bpf(BPF_LINK_CREATE, &attr, sizeof(attr)); + fd = sys_bpf_fd(BPF_LINK_CREATE, &attr, sizeof(attr)); return libbpf_err_errno(fd); } @@ -764,7 +897,7 @@ int bpf_iter_create(int link_fd) memset(&attr, 0, sizeof(attr)); attr.iter_create.link_fd = link_fd; - fd = sys_bpf(BPF_ITER_CREATE, &attr, sizeof(attr)); + fd = sys_bpf_fd(BPF_ITER_CREATE, &attr, sizeof(attr)); return libbpf_err_errno(fd); } @@ -922,7 +1055,7 @@ int bpf_prog_get_fd_by_id(__u32 id) memset(&attr, 0, sizeof(attr)); attr.prog_id = id; - fd = sys_bpf(BPF_PROG_GET_FD_BY_ID, &attr, sizeof(attr)); + fd = sys_bpf_fd(BPF_PROG_GET_FD_BY_ID, &attr, sizeof(attr)); return libbpf_err_errno(fd); } @@ -934,7 +1067,7 @@ int bpf_map_get_fd_by_id(__u32 id) memset(&attr, 0, sizeof(attr)); attr.map_id = id; - fd = sys_bpf(BPF_MAP_GET_FD_BY_ID, &attr, sizeof(attr)); + fd = sys_bpf_fd(BPF_MAP_GET_FD_BY_ID, &attr, sizeof(attr)); return libbpf_err_errno(fd); } @@ -946,7 +1079,7 @@ int bpf_btf_get_fd_by_id(__u32 id) memset(&attr, 0, sizeof(attr)); attr.btf_id = id; - fd = sys_bpf(BPF_BTF_GET_FD_BY_ID, &attr, sizeof(attr)); + fd = sys_bpf_fd(BPF_BTF_GET_FD_BY_ID, &attr, sizeof(attr)); return libbpf_err_errno(fd); } @@ -958,7 +1091,7 @@ int bpf_link_get_fd_by_id(__u32 id) memset(&attr, 0, sizeof(attr)); attr.link_id = id; - fd = sys_bpf(BPF_LINK_GET_FD_BY_ID, &attr, sizeof(attr)); + fd = sys_bpf_fd(BPF_LINK_GET_FD_BY_ID, &attr, sizeof(attr)); return libbpf_err_errno(fd); } @@ -989,28 +1122,71 @@ int bpf_raw_tracepoint_open(const char *name, int prog_fd) attr.raw_tracepoint.name = ptr_to_u64(name); attr.raw_tracepoint.prog_fd = prog_fd; - fd = sys_bpf(BPF_RAW_TRACEPOINT_OPEN, &attr, sizeof(attr)); + fd = sys_bpf_fd(BPF_RAW_TRACEPOINT_OPEN, &attr, sizeof(attr)); return libbpf_err_errno(fd); } -int bpf_load_btf(const void *btf, __u32 btf_size, char *log_buf, __u32 log_buf_size, - bool do_log) +int bpf_btf_load(const void *btf_data, size_t btf_size, const struct bpf_btf_load_opts *opts) { - union bpf_attr attr = {}; + const size_t attr_sz = offsetofend(union bpf_attr, btf_log_level); + union bpf_attr attr; + char *log_buf; + size_t log_size; + __u32 log_level; int fd; - attr.btf = ptr_to_u64(btf); + bump_rlimit_memlock(); + + memset(&attr, 0, attr_sz); + + if (!OPTS_VALID(opts, bpf_btf_load_opts)) + return libbpf_err(-EINVAL); + + log_buf = OPTS_GET(opts, log_buf, NULL); + log_size = OPTS_GET(opts, log_size, 0); + log_level = OPTS_GET(opts, log_level, 0); + + if (log_size > UINT_MAX) + return libbpf_err(-EINVAL); + if (log_size && !log_buf) + return libbpf_err(-EINVAL); + + attr.btf = ptr_to_u64(btf_data); attr.btf_size = btf_size; + /* log_level == 0 and log_buf != NULL means "try loading without + * log_buf, but retry with log_buf and log_level=1 on error", which is + * consistent across low-level and high-level BTF and program loading + * APIs within libbpf and provides a sensible behavior in practice + */ + if (log_level) { + attr.btf_log_buf = ptr_to_u64(log_buf); + attr.btf_log_size = (__u32)log_size; + attr.btf_log_level = log_level; + } + + fd = sys_bpf_fd(BPF_BTF_LOAD, &attr, attr_sz); + if (fd < 0 && log_buf && log_level == 0) { + attr.btf_log_buf = ptr_to_u64(log_buf); + attr.btf_log_size = (__u32)log_size; + attr.btf_log_level = 1; + fd = sys_bpf_fd(BPF_BTF_LOAD, &attr, attr_sz); + } + return libbpf_err_errno(fd); +} + +int bpf_load_btf(const void *btf, __u32 btf_size, char *log_buf, __u32 log_buf_size, bool do_log) +{ + LIBBPF_OPTS(bpf_btf_load_opts, opts); + int fd; retry: if (do_log && log_buf && log_buf_size) { - attr.btf_log_level = 1; - attr.btf_log_size = log_buf_size; - attr.btf_log_buf = ptr_to_u64(log_buf); + opts.log_buf = log_buf; + opts.log_size = log_buf_size; + opts.log_level = 1; } - fd = sys_bpf(BPF_BTF_LOAD, &attr, sizeof(attr)); - + fd = bpf_btf_load(btf, btf_size, &opts); if (fd < 0 && !do_log && log_buf && log_buf_size) { do_log = true; goto retry; @@ -1051,7 +1227,7 @@ int bpf_enable_stats(enum bpf_stats_type type) memset(&attr, 0, sizeof(attr)); attr.enable_stats.type = type; - fd = sys_bpf(BPF_ENABLE_STATS, &attr, sizeof(attr)); + fd = sys_bpf_fd(BPF_ENABLE_STATS, &attr, sizeof(attr)); return libbpf_err_errno(fd); } diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index 6fffb3cdf3..14e0d97ad2 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -29,11 +29,38 @@ #include #include "libbpf_common.h" +#include "libbpf_legacy.h" #ifdef __cplusplus extern "C" { #endif +int libbpf_set_memlock_rlim(size_t memlock_bytes); + +struct bpf_map_create_opts { + size_t sz; /* size of this struct for forward/backward compatibility */ + + __u32 btf_fd; + __u32 btf_key_type_id; + __u32 btf_value_type_id; + __u32 btf_vmlinux_value_type_id; + + __u32 inner_map_fd; + __u32 map_flags; + __u64 map_extra; + + __u32 numa_node; + __u32 map_ifindex; +}; +#define bpf_map_create_opts__last_field map_ifindex + +LIBBPF_API int bpf_map_create(enum bpf_map_type map_type, + const char *map_name, + __u32 key_size, + __u32 value_size, + __u32 max_entries, + const struct bpf_map_create_opts *opts); + struct bpf_create_map_attr { const char *name; enum bpf_map_type map_type; @@ -52,25 +79,95 @@ struct bpf_create_map_attr { }; }; -LIBBPF_API int -bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr); +LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_map_create() instead") +LIBBPF_API int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr); +LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_map_create() instead") LIBBPF_API int bpf_create_map_node(enum bpf_map_type map_type, const char *name, int key_size, int value_size, int max_entries, __u32 map_flags, int node); +LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_map_create() instead") LIBBPF_API int bpf_create_map_name(enum bpf_map_type map_type, const char *name, int key_size, int value_size, int max_entries, __u32 map_flags); +LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_map_create() instead") LIBBPF_API int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size, int max_entries, __u32 map_flags); +LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_map_create() instead") LIBBPF_API int bpf_create_map_in_map_node(enum bpf_map_type map_type, const char *name, int key_size, int inner_map_fd, int max_entries, __u32 map_flags, int node); +LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_map_create() instead") LIBBPF_API int bpf_create_map_in_map(enum bpf_map_type map_type, const char *name, int key_size, int inner_map_fd, int max_entries, __u32 map_flags); +struct bpf_prog_load_opts { + size_t sz; /* size of this struct for forward/backward compatibility */ + + /* libbpf can retry BPF_PROG_LOAD command if bpf() syscall returns + * -EAGAIN. This field determines how many attempts libbpf has to + * make. If not specified, libbpf will use default value of 5. + */ + int attempts; + + enum bpf_attach_type expected_attach_type; + __u32 prog_btf_fd; + __u32 prog_flags; + __u32 prog_ifindex; + __u32 kern_version; + + __u32 attach_btf_id; + __u32 attach_prog_fd; + __u32 attach_btf_obj_fd; + + const int *fd_array; + + /* .BTF.ext func info data */ + const void *func_info; + __u32 func_info_cnt; + __u32 func_info_rec_size; + + /* .BTF.ext line info data */ + const void *line_info; + __u32 line_info_cnt; + __u32 line_info_rec_size; + + /* verifier log options */ + __u32 log_level; + __u32 log_size; + char *log_buf; +}; +#define bpf_prog_load_opts__last_field log_buf + +LIBBPF_API int bpf_prog_load(enum bpf_prog_type prog_type, + const char *prog_name, const char *license, + const struct bpf_insn *insns, size_t insn_cnt, + const struct bpf_prog_load_opts *opts); +/* this "specialization" should go away in libbpf 1.0 */ +LIBBPF_API int bpf_prog_load_v0_6_0(enum bpf_prog_type prog_type, + const char *prog_name, const char *license, + const struct bpf_insn *insns, size_t insn_cnt, + const struct bpf_prog_load_opts *opts); + +/* This is an elaborate way to not conflict with deprecated bpf_prog_load() + * API, defined in libbpf.h. Once we hit libbpf 1.0, all this will be gone. + * With this approach, if someone is calling bpf_prog_load() with + * 4 arguments, they will use the deprecated API, which keeps backwards + * compatibility (both source code and binary). If bpf_prog_load() is called + * with 6 arguments, though, it gets redirected to __bpf_prog_load. + * So looking forward to libbpf 1.0 when this hack will be gone and + * __bpf_prog_load() will be called just bpf_prog_load(). + */ +#ifndef bpf_prog_load +#define bpf_prog_load(...) ___libbpf_overload(___bpf_prog_load, __VA_ARGS__) +#define ___bpf_prog_load4(file, type, pobj, prog_fd) \ + bpf_prog_load_deprecated(file, type, pobj, prog_fd) +#define ___bpf_prog_load6(prog_type, prog_name, license, insns, insn_cnt, opts) \ + bpf_prog_load(prog_type, prog_name, license, insns, insn_cnt, opts) +#endif /* bpf_prog_load */ + struct bpf_load_program_attr { enum bpf_prog_type prog_type; enum bpf_attach_type expected_attach_type; @@ -100,15 +197,18 @@ struct bpf_load_program_attr { /* Flags to direct loading requirements */ #define MAPS_RELAX_COMPAT 0x01 -/* Recommend log buffer size */ +/* Recommended log buffer size */ #define BPF_LOG_BUF_SIZE (UINT32_MAX >> 8) /* verifier maximum in kernels <= 5.1 */ -LIBBPF_API int -bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr, - char *log_buf, size_t log_buf_sz); + +LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_prog_load() instead") +LIBBPF_API int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr, + char *log_buf, size_t log_buf_sz); +LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_prog_load() instead") LIBBPF_API int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns, size_t insns_cnt, const char *license, __u32 kern_version, char *log_buf, size_t log_buf_sz); +LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_prog_load() instead") LIBBPF_API int bpf_verify_program(enum bpf_prog_type type, const struct bpf_insn *insns, size_t insns_cnt, __u32 prog_flags, @@ -116,6 +216,23 @@ LIBBPF_API int bpf_verify_program(enum bpf_prog_type type, char *log_buf, size_t log_buf_sz, int log_level); +struct bpf_btf_load_opts { + size_t sz; /* size of this struct for forward/backward compatibility */ + + /* kernel log options */ + char *log_buf; + __u32 log_level; + __u32 log_size; +}; +#define bpf_btf_load_opts__last_field log_size + +LIBBPF_API int bpf_btf_load(const void *btf_data, size_t btf_size, + const struct bpf_btf_load_opts *opts); + +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_btf_load() instead") +LIBBPF_API int bpf_load_btf(const void *btf, __u32 btf_size, char *log_buf, + __u32 log_buf_size, bool do_log); + LIBBPF_API int bpf_map_update_elem(int fd, const void *key, const void *value, __u64 flags); @@ -137,17 +254,128 @@ struct bpf_map_batch_opts { }; #define bpf_map_batch_opts__last_field flags -LIBBPF_API int bpf_map_delete_batch(int fd, void *keys, + +/** + * @brief **bpf_map_delete_batch()** allows for batch deletion of multiple + * elements in a BPF map. + * + * @param fd BPF map file descriptor + * @param keys pointer to an array of *count* keys + * @param count input and output parameter; on input **count** represents the + * number of elements in the map to delete in batch; + * on output if a non-EFAULT error is returned, **count** represents the number of deleted + * elements if the output **count** value is not equal to the input **count** value + * If EFAULT is returned, **count** should not be trusted to be correct. + * @param opts options for configuring the way the batch deletion works + * @return 0, on success; negative error code, otherwise (errno is also set to + * the error code) + */ +LIBBPF_API int bpf_map_delete_batch(int fd, const void *keys, __u32 *count, const struct bpf_map_batch_opts *opts); + +/** + * @brief **bpf_map_lookup_batch()** allows for batch lookup of BPF map elements. + * + * The parameter *in_batch* is the address of the first element in the batch to read. + * *out_batch* is an output parameter that should be passed as *in_batch* to subsequent + * calls to **bpf_map_lookup_batch()**. NULL can be passed for *in_batch* to indicate + * that the batched lookup starts from the beginning of the map. + * + * The *keys* and *values* are output parameters which must point to memory large enough to + * hold *count* items based on the key and value size of the map *map_fd*. The *keys* + * buffer must be of *key_size* * *count*. The *values* buffer must be of + * *value_size* * *count*. + * + * @param fd BPF map file descriptor + * @param in_batch address of the first element in batch to read, can pass NULL to + * indicate that the batched lookup starts from the beginning of the map. + * @param out_batch output parameter that should be passed to next call as *in_batch* + * @param keys pointer to an array large enough for *count* keys + * @param values pointer to an array large enough for *count* values + * @param count input and output parameter; on input it's the number of elements + * in the map to read in batch; on output it's the number of elements that were + * successfully read. + * If a non-EFAULT error is returned, count will be set as the number of elements + * that were read before the error occurred. + * If EFAULT is returned, **count** should not be trusted to be correct. + * @param opts options for configuring the way the batch lookup works + * @return 0, on success; negative error code, otherwise (errno is also set to + * the error code) + */ LIBBPF_API int bpf_map_lookup_batch(int fd, void *in_batch, void *out_batch, void *keys, void *values, __u32 *count, const struct bpf_map_batch_opts *opts); + +/** + * @brief **bpf_map_lookup_and_delete_batch()** allows for batch lookup and deletion + * of BPF map elements where each element is deleted after being retrieved. + * + * @param fd BPF map file descriptor + * @param in_batch address of the first element in batch to read, can pass NULL to + * get address of the first element in *out_batch* + * @param out_batch output parameter that should be passed to next call as *in_batch* + * @param keys pointer to an array of *count* keys + * @param values pointer to an array large enough for *count* values + * @param count input and output parameter; on input it's the number of elements + * in the map to read and delete in batch; on output it represents the number of + * elements that were successfully read and deleted + * If a non-**EFAULT** error code is returned and if the output **count** value + * is not equal to the input **count** value, up to **count** elements may + * have been deleted. + * if **EFAULT** is returned up to *count* elements may have been deleted without + * being returned via the *keys* and *values* output parameters. + * @param opts options for configuring the way the batch lookup and delete works + * @return 0, on success; negative error code, otherwise (errno is also set to + * the error code) + */ LIBBPF_API int bpf_map_lookup_and_delete_batch(int fd, void *in_batch, void *out_batch, void *keys, void *values, __u32 *count, const struct bpf_map_batch_opts *opts); -LIBBPF_API int bpf_map_update_batch(int fd, void *keys, void *values, + +/** + * @brief **bpf_map_update_batch()** updates multiple elements in a map + * by specifying keys and their corresponding values. + * + * The *keys* and *values* parameters must point to memory large enough + * to hold *count* items based on the key and value size of the map. + * + * The *opts* parameter can be used to control how *bpf_map_update_batch()* + * should handle keys that either do or do not already exist in the map. + * In particular the *flags* parameter of *bpf_map_batch_opts* can be + * one of the following: + * + * Note that *count* is an input and output parameter, where on output it + * represents how many elements were successfully updated. Also note that if + * **EFAULT** then *count* should not be trusted to be correct. + * + * **BPF_ANY** + * Create new elements or update existing. + * + * **BPF_NOEXIST** + * Create new elements only if they do not exist. + * + * **BPF_EXIST** + * Update existing elements. + * + * **BPF_F_LOCK** + * Update spin_lock-ed map elements. This must be + * specified if the map value contains a spinlock. + * + * @param fd BPF map file descriptor + * @param keys pointer to an array of *count* keys + * @param values pointer to an array of *count* values + * @param count input and output parameter; on input it's the number of elements + * in the map to update in batch; on output if a non-EFAULT error is returned, + * **count** represents the number of updated elements if the output **count** + * value is not equal to the input **count** value. + * If EFAULT is returned, **count** should not be trusted to be correct. + * @param opts options for configuring the way the batch update works + * @return 0, on success; negative error code, otherwise (errno is also set to + * the error code) + */ +LIBBPF_API int bpf_map_update_batch(int fd, const void *keys, const void *values, __u32 *count, const struct bpf_map_batch_opts *opts); @@ -243,8 +471,6 @@ LIBBPF_API int bpf_prog_query(int target_fd, enum bpf_attach_type type, __u32 query_flags, __u32 *attach_flags, __u32 *prog_ids, __u32 *prog_cnt); LIBBPF_API int bpf_raw_tracepoint_open(const char *name, int prog_fd); -LIBBPF_API int bpf_load_btf(const void *btf, __u32 btf_size, char *log_buf, - __u32 log_buf_size, bool do_log); LIBBPF_API int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf, __u32 *buf_len, __u32 *prog_id, __u32 *fd_type, __u64 *probe_offset, __u64 *probe_addr); diff --git a/tools/lib/bpf/bpf_gen_internal.h b/tools/lib/bpf/bpf_gen_internal.h index 615400391e..223308931d 100644 --- a/tools/lib/bpf/bpf_gen_internal.h +++ b/tools/lib/bpf/bpf_gen_internal.h @@ -3,10 +3,27 @@ #ifndef __BPF_GEN_INTERNAL_H #define __BPF_GEN_INTERNAL_H +#include "bpf.h" + struct ksym_relo_desc { const char *name; int kind; int insn_idx; + bool is_weak; + bool is_typeless; +}; + +struct ksym_desc { + const char *name; + int ref; + int kind; + union { + /* used for kfunc */ + int off; + /* used for typeless ksym */ + bool typeless; + }; + int insn; }; struct bpf_gen { @@ -22,20 +39,34 @@ struct bpf_gen { int error; struct ksym_relo_desc *relos; int relo_cnt; + struct bpf_core_relo *core_relos; + int core_relo_cnt; char attach_target[128]; int attach_kind; + struct ksym_desc *ksyms; + __u32 nr_ksyms; + int fd_array; + int nr_fd_array; }; -void bpf_gen__init(struct bpf_gen *gen, int log_level); -int bpf_gen__finish(struct bpf_gen *gen); +void bpf_gen__init(struct bpf_gen *gen, int log_level, int nr_progs, int nr_maps); +int bpf_gen__finish(struct bpf_gen *gen, int nr_progs, int nr_maps); void bpf_gen__free(struct bpf_gen *gen); void bpf_gen__load_btf(struct bpf_gen *gen, const void *raw_data, __u32 raw_size); -void bpf_gen__map_create(struct bpf_gen *gen, struct bpf_create_map_attr *map_attr, int map_idx); -struct bpf_prog_load_params; -void bpf_gen__prog_load(struct bpf_gen *gen, struct bpf_prog_load_params *load_attr, int prog_idx); +void bpf_gen__map_create(struct bpf_gen *gen, + enum bpf_map_type map_type, const char *map_name, + __u32 key_size, __u32 value_size, __u32 max_entries, + struct bpf_map_create_opts *map_attr, int map_idx); +void bpf_gen__prog_load(struct bpf_gen *gen, + enum bpf_prog_type prog_type, const char *prog_name, + const char *license, struct bpf_insn *insns, size_t insn_cnt, + struct bpf_prog_load_opts *load_attr, int prog_idx); void bpf_gen__map_update_elem(struct bpf_gen *gen, int map_idx, void *value, __u32 value_size); void bpf_gen__map_freeze(struct bpf_gen *gen, int map_idx); void bpf_gen__record_attach_target(struct bpf_gen *gen, const char *name, enum bpf_attach_type type); -void bpf_gen__record_extern(struct bpf_gen *gen, const char *name, int kind, int insn_idx); +void bpf_gen__record_extern(struct bpf_gen *gen, const char *name, bool is_weak, + bool is_typeless, int kind, int insn_idx); +void bpf_gen__record_relo_core(struct bpf_gen *gen, const struct bpf_core_relo *core_relo); +void bpf_gen__populate_outer_map(struct bpf_gen *gen, int outer_map_idx, int key, int inner_map_idx); #endif diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h index b9987c3efa..963b1060d9 100644 --- a/tools/lib/bpf/bpf_helpers.h +++ b/tools/lib/bpf/bpf_helpers.h @@ -14,14 +14,6 @@ #define __type(name, val) typeof(val) *name #define __array(name, val) typeof(val) *name[] -/* Helper macro to print out debug messages */ -#define bpf_printk(fmt, ...) \ -({ \ - char ____fmt[] = fmt; \ - bpf_trace_printk(____fmt, sizeof(____fmt), \ - ##__VA_ARGS__); \ -}) - /* * Helper macro to place programs, maps, license in * different sections in elf_bpf file. Section names @@ -224,4 +216,47 @@ enum libbpf_tristate { ___param, sizeof(___param)); \ }) +#ifdef BPF_NO_GLOBAL_DATA +#define BPF_PRINTK_FMT_MOD +#else +#define BPF_PRINTK_FMT_MOD static const +#endif + +#define __bpf_printk(fmt, ...) \ +({ \ + BPF_PRINTK_FMT_MOD char ____fmt[] = fmt; \ + bpf_trace_printk(____fmt, sizeof(____fmt), \ + ##__VA_ARGS__); \ +}) + +/* + * __bpf_vprintk wraps the bpf_trace_vprintk helper with variadic arguments + * instead of an array of u64. + */ +#define __bpf_vprintk(fmt, args...) \ +({ \ + static const char ___fmt[] = fmt; \ + unsigned long long ___param[___bpf_narg(args)]; \ + \ + _Pragma("GCC diagnostic push") \ + _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \ + ___bpf_fill(___param, args); \ + _Pragma("GCC diagnostic pop") \ + \ + bpf_trace_vprintk(___fmt, sizeof(___fmt), \ + ___param, sizeof(___param)); \ +}) + +/* Use __bpf_printk when bpf_printk call has 3 or fewer fmt args + * Otherwise use __bpf_vprintk + */ +#define ___bpf_pick_printk(...) \ + ___bpf_nth(_, ##__VA_ARGS__, __bpf_vprintk, __bpf_vprintk, __bpf_vprintk, \ + __bpf_vprintk, __bpf_vprintk, __bpf_vprintk, __bpf_vprintk, \ + __bpf_vprintk, __bpf_vprintk, __bpf_printk /*3*/, __bpf_printk /*2*/,\ + __bpf_printk /*1*/, __bpf_printk /*0*/) + +/* Helper macro to print out debug messages */ +#define bpf_printk(fmt, args...) ___bpf_pick_printk(args)(fmt, ##args) + #endif diff --git a/tools/lib/bpf/bpf_tracing.h b/tools/lib/bpf/bpf_tracing.h index d6bfbe0092..90f56b0f58 100644 --- a/tools/lib/bpf/bpf_tracing.h +++ b/tools/lib/bpf/bpf_tracing.h @@ -24,6 +24,9 @@ #elif defined(__TARGET_ARCH_sparc) #define bpf_target_sparc #define bpf_target_defined +#elif defined(__TARGET_ARCH_riscv) + #define bpf_target_riscv + #define bpf_target_defined #else /* Fall back to what the compiler says */ @@ -48,6 +51,9 @@ #elif defined(__sparc__) #define bpf_target_sparc #define bpf_target_defined +#elif defined(__riscv) && __riscv_xlen == 64 + #define bpf_target_riscv + #define bpf_target_defined #endif /* no compiler target */ #endif @@ -60,251 +66,204 @@ #if defined(__KERNEL__) || defined(__VMLINUX_H__) -#define PT_REGS_PARM1(x) ((x)->di) -#define PT_REGS_PARM2(x) ((x)->si) -#define PT_REGS_PARM3(x) ((x)->dx) -#define PT_REGS_PARM4(x) ((x)->cx) -#define PT_REGS_PARM5(x) ((x)->r8) -#define PT_REGS_RET(x) ((x)->sp) -#define PT_REGS_FP(x) ((x)->bp) -#define PT_REGS_RC(x) ((x)->ax) -#define PT_REGS_SP(x) ((x)->sp) -#define PT_REGS_IP(x) ((x)->ip) - -#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), di) -#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), si) -#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), dx) -#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), cx) -#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), r8) -#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), sp) -#define PT_REGS_FP_CORE(x) BPF_CORE_READ((x), bp) -#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), ax) -#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), sp) -#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), ip) +#define __PT_PARM1_REG di +#define __PT_PARM2_REG si +#define __PT_PARM3_REG dx +#define __PT_PARM4_REG cx +#define __PT_PARM5_REG r8 +#define __PT_RET_REG sp +#define __PT_FP_REG bp +#define __PT_RC_REG ax +#define __PT_SP_REG sp +#define __PT_IP_REG ip #else #ifdef __i386__ + +#define __PT_PARM1_REG eax +#define __PT_PARM2_REG edx +#define __PT_PARM3_REG ecx /* i386 kernel is built with -mregparm=3 */ -#define PT_REGS_PARM1(x) ((x)->eax) -#define PT_REGS_PARM2(x) ((x)->edx) -#define PT_REGS_PARM3(x) ((x)->ecx) -#define PT_REGS_PARM4(x) 0 -#define PT_REGS_PARM5(x) 0 -#define PT_REGS_RET(x) ((x)->esp) -#define PT_REGS_FP(x) ((x)->ebp) -#define PT_REGS_RC(x) ((x)->eax) -#define PT_REGS_SP(x) ((x)->esp) -#define PT_REGS_IP(x) ((x)->eip) +#define __PT_PARM4_REG __unsupported__ +#define __PT_PARM5_REG __unsupported__ +#define __PT_RET_REG esp +#define __PT_FP_REG ebp +#define __PT_RC_REG eax +#define __PT_SP_REG esp +#define __PT_IP_REG eip -#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), eax) -#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), edx) -#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), ecx) -#define PT_REGS_PARM4_CORE(x) 0 -#define PT_REGS_PARM5_CORE(x) 0 -#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), esp) -#define PT_REGS_FP_CORE(x) BPF_CORE_READ((x), ebp) -#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), eax) -#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), esp) -#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), eip) +#else /* __i386__ */ -#else +#define __PT_PARM1_REG rdi +#define __PT_PARM2_REG rsi +#define __PT_PARM3_REG rdx +#define __PT_PARM4_REG rcx +#define __PT_PARM5_REG r8 +#define __PT_RET_REG rsp +#define __PT_FP_REG rbp +#define __PT_RC_REG rax +#define __PT_SP_REG rsp +#define __PT_IP_REG rip -#define PT_REGS_PARM1(x) ((x)->rdi) -#define PT_REGS_PARM2(x) ((x)->rsi) -#define PT_REGS_PARM3(x) ((x)->rdx) -#define PT_REGS_PARM4(x) ((x)->rcx) -#define PT_REGS_PARM5(x) ((x)->r8) -#define PT_REGS_RET(x) ((x)->rsp) -#define PT_REGS_FP(x) ((x)->rbp) -#define PT_REGS_RC(x) ((x)->rax) -#define PT_REGS_SP(x) ((x)->rsp) -#define PT_REGS_IP(x) ((x)->rip) +#endif /* __i386__ */ -#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), rdi) -#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), rsi) -#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), rdx) -#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), rcx) -#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), r8) -#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), rsp) -#define PT_REGS_FP_CORE(x) BPF_CORE_READ((x), rbp) -#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), rax) -#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), rsp) -#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), rip) - -#endif -#endif +#endif /* __KERNEL__ || __VMLINUX_H__ */ #elif defined(bpf_target_s390) /* s390 provides user_pt_regs instead of struct pt_regs to userspace */ -struct pt_regs; -#define PT_REGS_S390 const volatile user_pt_regs -#define PT_REGS_PARM1(x) (((PT_REGS_S390 *)(x))->gprs[2]) -#define PT_REGS_PARM2(x) (((PT_REGS_S390 *)(x))->gprs[3]) -#define PT_REGS_PARM3(x) (((PT_REGS_S390 *)(x))->gprs[4]) -#define PT_REGS_PARM4(x) (((PT_REGS_S390 *)(x))->gprs[5]) -#define PT_REGS_PARM5(x) (((PT_REGS_S390 *)(x))->gprs[6]) -#define PT_REGS_RET(x) (((PT_REGS_S390 *)(x))->gprs[14]) -/* Works only with CONFIG_FRAME_POINTER */ -#define PT_REGS_FP(x) (((PT_REGS_S390 *)(x))->gprs[11]) -#define PT_REGS_RC(x) (((PT_REGS_S390 *)(x))->gprs[2]) -#define PT_REGS_SP(x) (((PT_REGS_S390 *)(x))->gprs[15]) -#define PT_REGS_IP(x) (((PT_REGS_S390 *)(x))->psw.addr) - -#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[2]) -#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[3]) -#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[4]) -#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[5]) -#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[6]) -#define PT_REGS_RET_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[14]) -#define PT_REGS_FP_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[11]) -#define PT_REGS_RC_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[2]) -#define PT_REGS_SP_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[15]) -#define PT_REGS_IP_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), psw.addr) +#define __PT_REGS_CAST(x) ((const user_pt_regs *)(x)) +#define __PT_PARM1_REG gprs[2] +#define __PT_PARM2_REG gprs[3] +#define __PT_PARM3_REG gprs[4] +#define __PT_PARM4_REG gprs[5] +#define __PT_PARM5_REG gprs[6] +#define __PT_RET_REG grps[14] +#define __PT_FP_REG gprs[11] /* Works only with CONFIG_FRAME_POINTER */ +#define __PT_RC_REG gprs[2] +#define __PT_SP_REG gprs[15] +#define __PT_IP_REG psw.addr #elif defined(bpf_target_arm) -#define PT_REGS_PARM1(x) ((x)->uregs[0]) -#define PT_REGS_PARM2(x) ((x)->uregs[1]) -#define PT_REGS_PARM3(x) ((x)->uregs[2]) -#define PT_REGS_PARM4(x) ((x)->uregs[3]) -#define PT_REGS_PARM5(x) ((x)->uregs[4]) -#define PT_REGS_RET(x) ((x)->uregs[14]) -#define PT_REGS_FP(x) ((x)->uregs[11]) /* Works only with CONFIG_FRAME_POINTER */ -#define PT_REGS_RC(x) ((x)->uregs[0]) -#define PT_REGS_SP(x) ((x)->uregs[13]) -#define PT_REGS_IP(x) ((x)->uregs[12]) - -#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), uregs[0]) -#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), uregs[1]) -#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), uregs[2]) -#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), uregs[3]) -#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), uregs[4]) -#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), uregs[14]) -#define PT_REGS_FP_CORE(x) BPF_CORE_READ((x), uregs[11]) -#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), uregs[0]) -#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), uregs[13]) -#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), uregs[12]) +#define __PT_PARM1_REG uregs[0] +#define __PT_PARM2_REG uregs[1] +#define __PT_PARM3_REG uregs[2] +#define __PT_PARM4_REG uregs[3] +#define __PT_PARM5_REG uregs[4] +#define __PT_RET_REG uregs[14] +#define __PT_FP_REG uregs[11] /* Works only with CONFIG_FRAME_POINTER */ +#define __PT_RC_REG uregs[0] +#define __PT_SP_REG uregs[13] +#define __PT_IP_REG uregs[12] #elif defined(bpf_target_arm64) /* arm64 provides struct user_pt_regs instead of struct pt_regs to userspace */ -struct pt_regs; -#define PT_REGS_ARM64 const volatile struct user_pt_regs -#define PT_REGS_PARM1(x) (((PT_REGS_ARM64 *)(x))->regs[0]) -#define PT_REGS_PARM2(x) (((PT_REGS_ARM64 *)(x))->regs[1]) -#define PT_REGS_PARM3(x) (((PT_REGS_ARM64 *)(x))->regs[2]) -#define PT_REGS_PARM4(x) (((PT_REGS_ARM64 *)(x))->regs[3]) -#define PT_REGS_PARM5(x) (((PT_REGS_ARM64 *)(x))->regs[4]) -#define PT_REGS_RET(x) (((PT_REGS_ARM64 *)(x))->regs[30]) -/* Works only with CONFIG_FRAME_POINTER */ -#define PT_REGS_FP(x) (((PT_REGS_ARM64 *)(x))->regs[29]) -#define PT_REGS_RC(x) (((PT_REGS_ARM64 *)(x))->regs[0]) -#define PT_REGS_SP(x) (((PT_REGS_ARM64 *)(x))->sp) -#define PT_REGS_IP(x) (((PT_REGS_ARM64 *)(x))->pc) - -#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[0]) -#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[1]) -#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[2]) -#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[3]) -#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[4]) -#define PT_REGS_RET_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[30]) -#define PT_REGS_FP_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[29]) -#define PT_REGS_RC_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[0]) -#define PT_REGS_SP_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), sp) -#define PT_REGS_IP_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), pc) +#define __PT_REGS_CAST(x) ((const struct user_pt_regs *)(x)) +#define __PT_PARM1_REG regs[0] +#define __PT_PARM2_REG regs[1] +#define __PT_PARM3_REG regs[2] +#define __PT_PARM4_REG regs[3] +#define __PT_PARM5_REG regs[4] +#define __PT_RET_REG regs[30] +#define __PT_FP_REG regs[29] /* Works only with CONFIG_FRAME_POINTER */ +#define __PT_RC_REG regs[0] +#define __PT_SP_REG sp +#define __PT_IP_REG pc #elif defined(bpf_target_mips) -#define PT_REGS_PARM1(x) ((x)->regs[4]) -#define PT_REGS_PARM2(x) ((x)->regs[5]) -#define PT_REGS_PARM3(x) ((x)->regs[6]) -#define PT_REGS_PARM4(x) ((x)->regs[7]) -#define PT_REGS_PARM5(x) ((x)->regs[8]) -#define PT_REGS_RET(x) ((x)->regs[31]) -#define PT_REGS_FP(x) ((x)->regs[30]) /* Works only with CONFIG_FRAME_POINTER */ -#define PT_REGS_RC(x) ((x)->regs[2]) -#define PT_REGS_SP(x) ((x)->regs[29]) -#define PT_REGS_IP(x) ((x)->cp0_epc) - -#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), regs[4]) -#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), regs[5]) -#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), regs[6]) -#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), regs[7]) -#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), regs[8]) -#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), regs[31]) -#define PT_REGS_FP_CORE(x) BPF_CORE_READ((x), regs[30]) -#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), regs[2]) -#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), regs[29]) -#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), cp0_epc) +#define __PT_PARM1_REG regs[4] +#define __PT_PARM2_REG regs[5] +#define __PT_PARM3_REG regs[6] +#define __PT_PARM4_REG regs[7] +#define __PT_PARM5_REG regs[8] +#define __PT_RET_REG regs[31] +#define __PT_FP_REG regs[30] /* Works only with CONFIG_FRAME_POINTER */ +#define __PT_RC_REG regs[2] +#define __PT_SP_REG regs[29] +#define __PT_IP_REG cp0_epc #elif defined(bpf_target_powerpc) -#define PT_REGS_PARM1(x) ((x)->gpr[3]) -#define PT_REGS_PARM2(x) ((x)->gpr[4]) -#define PT_REGS_PARM3(x) ((x)->gpr[5]) -#define PT_REGS_PARM4(x) ((x)->gpr[6]) -#define PT_REGS_PARM5(x) ((x)->gpr[7]) -#define PT_REGS_RC(x) ((x)->gpr[3]) -#define PT_REGS_SP(x) ((x)->sp) -#define PT_REGS_IP(x) ((x)->nip) - -#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), gpr[3]) -#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), gpr[4]) -#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), gpr[5]) -#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), gpr[6]) -#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), gpr[7]) -#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), gpr[3]) -#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), sp) -#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), nip) +#define __PT_PARM1_REG gpr[3] +#define __PT_PARM2_REG gpr[4] +#define __PT_PARM3_REG gpr[5] +#define __PT_PARM4_REG gpr[6] +#define __PT_PARM5_REG gpr[7] +#define __PT_RET_REG regs[31] +#define __PT_FP_REG __unsupported__ +#define __PT_RC_REG gpr[3] +#define __PT_SP_REG sp +#define __PT_IP_REG nip #elif defined(bpf_target_sparc) -#define PT_REGS_PARM1(x) ((x)->u_regs[UREG_I0]) -#define PT_REGS_PARM2(x) ((x)->u_regs[UREG_I1]) -#define PT_REGS_PARM3(x) ((x)->u_regs[UREG_I2]) -#define PT_REGS_PARM4(x) ((x)->u_regs[UREG_I3]) -#define PT_REGS_PARM5(x) ((x)->u_regs[UREG_I4]) -#define PT_REGS_RET(x) ((x)->u_regs[UREG_I7]) -#define PT_REGS_RC(x) ((x)->u_regs[UREG_I0]) -#define PT_REGS_SP(x) ((x)->u_regs[UREG_FP]) - -#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I0]) -#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I1]) -#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I2]) -#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I3]) -#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I4]) -#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I7]) -#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I0]) -#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), u_regs[UREG_FP]) - +#define __PT_PARM1_REG u_regs[UREG_I0] +#define __PT_PARM2_REG u_regs[UREG_I1] +#define __PT_PARM3_REG u_regs[UREG_I2] +#define __PT_PARM4_REG u_regs[UREG_I3] +#define __PT_PARM5_REG u_regs[UREG_I4] +#define __PT_RET_REG u_regs[UREG_I7] +#define __PT_FP_REG __unsupported__ +#define __PT_RC_REG u_regs[UREG_I0] +#define __PT_SP_REG u_regs[UREG_FP] /* Should this also be a bpf_target check for the sparc case? */ #if defined(__arch64__) -#define PT_REGS_IP(x) ((x)->tpc) -#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), tpc) +#define __PT_IP_REG tpc #else -#define PT_REGS_IP(x) ((x)->pc) -#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), pc) +#define __PT_IP_REG pc #endif +#elif defined(bpf_target_riscv) + +#define __PT_REGS_CAST(x) ((const struct user_regs_struct *)(x)) +#define __PT_PARM1_REG a0 +#define __PT_PARM2_REG a1 +#define __PT_PARM3_REG a2 +#define __PT_PARM4_REG a3 +#define __PT_PARM5_REG a4 +#define __PT_RET_REG ra +#define __PT_FP_REG fp +#define __PT_RC_REG a5 +#define __PT_SP_REG sp +#define __PT_IP_REG epc + #endif +#if defined(bpf_target_defined) + +struct pt_regs; + +/* allow some architecutres to override `struct pt_regs` */ +#ifndef __PT_REGS_CAST +#define __PT_REGS_CAST(x) (x) +#endif + +#define PT_REGS_PARM1(x) (__PT_REGS_CAST(x)->__PT_PARM1_REG) +#define PT_REGS_PARM2(x) (__PT_REGS_CAST(x)->__PT_PARM2_REG) +#define PT_REGS_PARM3(x) (__PT_REGS_CAST(x)->__PT_PARM3_REG) +#define PT_REGS_PARM4(x) (__PT_REGS_CAST(x)->__PT_PARM4_REG) +#define PT_REGS_PARM5(x) (__PT_REGS_CAST(x)->__PT_PARM5_REG) +#define PT_REGS_RET(x) (__PT_REGS_CAST(x)->__PT_RET_REG) +#define PT_REGS_FP(x) (__PT_REGS_CAST(x)->__PT_FP_REG) +#define PT_REGS_RC(x) (__PT_REGS_CAST(x)->__PT_RC_REG) +#define PT_REGS_SP(x) (__PT_REGS_CAST(x)->__PT_SP_REG) +#define PT_REGS_IP(x) (__PT_REGS_CAST(x)->__PT_IP_REG) + +#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM1_REG) +#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM2_REG) +#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM3_REG) +#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM4_REG) +#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM5_REG) +#define PT_REGS_RET_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_RET_REG) +#define PT_REGS_FP_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_FP_REG) +#define PT_REGS_RC_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_RC_REG) +#define PT_REGS_SP_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_SP_REG) +#define PT_REGS_IP_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_IP_REG) + #if defined(bpf_target_powerpc) + #define BPF_KPROBE_READ_RET_IP(ip, ctx) ({ (ip) = (ctx)->link; }) #define BPF_KRETPROBE_READ_RET_IP BPF_KPROBE_READ_RET_IP + #elif defined(bpf_target_sparc) + #define BPF_KPROBE_READ_RET_IP(ip, ctx) ({ (ip) = PT_REGS_RET(ctx); }) #define BPF_KRETPROBE_READ_RET_IP BPF_KPROBE_READ_RET_IP -#elif defined(bpf_target_defined) + +#else + #define BPF_KPROBE_READ_RET_IP(ip, ctx) \ ({ bpf_probe_read_kernel(&(ip), sizeof(ip), (void *)PT_REGS_RET(ctx)); }) #define BPF_KRETPROBE_READ_RET_IP(ip, ctx) \ - ({ bpf_probe_read_kernel(&(ip), sizeof(ip), \ - (void *)(PT_REGS_FP(ctx) + sizeof(ip))); }) + ({ bpf_probe_read_kernel(&(ip), sizeof(ip), (void *)(PT_REGS_FP(ctx) + sizeof(ip))); }) + #endif -#if !defined(bpf_target_defined) +#else /* defined(bpf_target_defined) */ #define PT_REGS_PARM1(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) #define PT_REGS_PARM2(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) @@ -331,7 +290,7 @@ struct pt_regs; #define BPF_KPROBE_READ_RET_IP(ip, ctx) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) #define BPF_KRETPROBE_READ_RET_IP(ip, ctx) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) -#endif /* !defined(bpf_target_defined) */ +#endif /* defined(bpf_target_defined) */ #ifndef ___bpf_concat #define ___bpf_concat(a, b) a ## b @@ -343,25 +302,23 @@ struct pt_regs; #define ___bpf_nth(_, _1, _2, _3, _4, _5, _6, _7, _8, _9, _a, _b, _c, N, ...) N #endif #ifndef ___bpf_narg -#define ___bpf_narg(...) \ - ___bpf_nth(_, ##__VA_ARGS__, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0) +#define ___bpf_narg(...) ___bpf_nth(_, ##__VA_ARGS__, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0) #endif -#define ___bpf_ctx_cast0() ctx -#define ___bpf_ctx_cast1(x) ___bpf_ctx_cast0(), (void *)ctx[0] -#define ___bpf_ctx_cast2(x, args...) ___bpf_ctx_cast1(args), (void *)ctx[1] -#define ___bpf_ctx_cast3(x, args...) ___bpf_ctx_cast2(args), (void *)ctx[2] -#define ___bpf_ctx_cast4(x, args...) ___bpf_ctx_cast3(args), (void *)ctx[3] -#define ___bpf_ctx_cast5(x, args...) ___bpf_ctx_cast4(args), (void *)ctx[4] -#define ___bpf_ctx_cast6(x, args...) ___bpf_ctx_cast5(args), (void *)ctx[5] -#define ___bpf_ctx_cast7(x, args...) ___bpf_ctx_cast6(args), (void *)ctx[6] -#define ___bpf_ctx_cast8(x, args...) ___bpf_ctx_cast7(args), (void *)ctx[7] -#define ___bpf_ctx_cast9(x, args...) ___bpf_ctx_cast8(args), (void *)ctx[8] +#define ___bpf_ctx_cast0() ctx +#define ___bpf_ctx_cast1(x) ___bpf_ctx_cast0(), (void *)ctx[0] +#define ___bpf_ctx_cast2(x, args...) ___bpf_ctx_cast1(args), (void *)ctx[1] +#define ___bpf_ctx_cast3(x, args...) ___bpf_ctx_cast2(args), (void *)ctx[2] +#define ___bpf_ctx_cast4(x, args...) ___bpf_ctx_cast3(args), (void *)ctx[3] +#define ___bpf_ctx_cast5(x, args...) ___bpf_ctx_cast4(args), (void *)ctx[4] +#define ___bpf_ctx_cast6(x, args...) ___bpf_ctx_cast5(args), (void *)ctx[5] +#define ___bpf_ctx_cast7(x, args...) ___bpf_ctx_cast6(args), (void *)ctx[6] +#define ___bpf_ctx_cast8(x, args...) ___bpf_ctx_cast7(args), (void *)ctx[7] +#define ___bpf_ctx_cast9(x, args...) ___bpf_ctx_cast8(args), (void *)ctx[8] #define ___bpf_ctx_cast10(x, args...) ___bpf_ctx_cast9(args), (void *)ctx[9] #define ___bpf_ctx_cast11(x, args...) ___bpf_ctx_cast10(args), (void *)ctx[10] #define ___bpf_ctx_cast12(x, args...) ___bpf_ctx_cast11(args), (void *)ctx[11] -#define ___bpf_ctx_cast(args...) \ - ___bpf_apply(___bpf_ctx_cast, ___bpf_narg(args))(args) +#define ___bpf_ctx_cast(args...) ___bpf_apply(___bpf_ctx_cast, ___bpf_narg(args))(args) /* * BPF_PROG is a convenience wrapper for generic tp_btf/fentry/fexit and @@ -394,19 +351,13 @@ ____##name(unsigned long long *ctx, ##args) struct pt_regs; -#define ___bpf_kprobe_args0() ctx -#define ___bpf_kprobe_args1(x) \ - ___bpf_kprobe_args0(), (void *)PT_REGS_PARM1(ctx) -#define ___bpf_kprobe_args2(x, args...) \ - ___bpf_kprobe_args1(args), (void *)PT_REGS_PARM2(ctx) -#define ___bpf_kprobe_args3(x, args...) \ - ___bpf_kprobe_args2(args), (void *)PT_REGS_PARM3(ctx) -#define ___bpf_kprobe_args4(x, args...) \ - ___bpf_kprobe_args3(args), (void *)PT_REGS_PARM4(ctx) -#define ___bpf_kprobe_args5(x, args...) \ - ___bpf_kprobe_args4(args), (void *)PT_REGS_PARM5(ctx) -#define ___bpf_kprobe_args(args...) \ - ___bpf_apply(___bpf_kprobe_args, ___bpf_narg(args))(args) +#define ___bpf_kprobe_args0() ctx +#define ___bpf_kprobe_args1(x) ___bpf_kprobe_args0(), (void *)PT_REGS_PARM1(ctx) +#define ___bpf_kprobe_args2(x, args...) ___bpf_kprobe_args1(args), (void *)PT_REGS_PARM2(ctx) +#define ___bpf_kprobe_args3(x, args...) ___bpf_kprobe_args2(args), (void *)PT_REGS_PARM3(ctx) +#define ___bpf_kprobe_args4(x, args...) ___bpf_kprobe_args3(args), (void *)PT_REGS_PARM4(ctx) +#define ___bpf_kprobe_args5(x, args...) ___bpf_kprobe_args4(args), (void *)PT_REGS_PARM5(ctx) +#define ___bpf_kprobe_args(args...) ___bpf_apply(___bpf_kprobe_args, ___bpf_narg(args))(args) /* * BPF_KPROBE serves the same purpose for kprobes as BPF_PROG for @@ -432,11 +383,9 @@ typeof(name(0)) name(struct pt_regs *ctx) \ static __attribute__((always_inline)) typeof(name(0)) \ ____##name(struct pt_regs *ctx, ##args) -#define ___bpf_kretprobe_args0() ctx -#define ___bpf_kretprobe_args1(x) \ - ___bpf_kretprobe_args0(), (void *)PT_REGS_RC(ctx) -#define ___bpf_kretprobe_args(args...) \ - ___bpf_apply(___bpf_kretprobe_args, ___bpf_narg(args))(args) +#define ___bpf_kretprobe_args0() ctx +#define ___bpf_kretprobe_args1(x) ___bpf_kretprobe_args0(), (void *)PT_REGS_RC(ctx) +#define ___bpf_kretprobe_args(args...) ___bpf_apply(___bpf_kretprobe_args, ___bpf_narg(args))(args) /* * BPF_KRETPROBE is similar to BPF_KPROBE, except, it only provides optional diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 5f3d20ae66..9aa19c89f7 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -57,7 +57,7 @@ struct btf { * representation is broken up into three independently allocated * memory regions to be able to modify them independently. * raw_data is nulled out at that point, but can be later allocated - * and cached again if user calls btf__get_raw_data(), at which point + * and cached again if user calls btf__raw_data(), at which point * raw_data will contain a contiguous copy of header, types, and * strings: * @@ -189,12 +189,17 @@ int libbpf_ensure_mem(void **data, size_t *cap_cnt, size_t elem_sz, size_t need_ return 0; } +static void *btf_add_type_offs_mem(struct btf *btf, size_t add_cnt) +{ + return libbpf_add_mem((void **)&btf->type_offs, &btf->type_offs_cap, sizeof(__u32), + btf->nr_types, BTF_MAX_NR_TYPES, add_cnt); +} + static int btf_add_type_idx_entry(struct btf *btf, __u32 type_off) { __u32 *p; - p = libbpf_add_mem((void **)&btf->type_offs, &btf->type_offs_cap, sizeof(__u32), - btf->nr_types, BTF_MAX_NR_TYPES, 1); + p = btf_add_type_offs_mem(btf, 1); if (!p) return -ENOMEM; @@ -294,6 +299,7 @@ static int btf_type_size(const struct btf_type *t) case BTF_KIND_TYPEDEF: case BTF_KIND_FUNC: case BTF_KIND_FLOAT: + case BTF_KIND_TYPE_TAG: return base_size; case BTF_KIND_INT: return base_size + sizeof(__u32); @@ -310,6 +316,8 @@ static int btf_type_size(const struct btf_type *t) return base_size + sizeof(struct btf_var); case BTF_KIND_DATASEC: return base_size + vlen * sizeof(struct btf_var_secinfo); + case BTF_KIND_DECL_TAG: + return base_size + sizeof(struct btf_decl_tag); default: pr_debug("Unsupported BTF_KIND:%u\n", btf_kind(t)); return -EINVAL; @@ -342,6 +350,7 @@ static int btf_bswap_type_rest(struct btf_type *t) case BTF_KIND_TYPEDEF: case BTF_KIND_FUNC: case BTF_KIND_FLOAT: + case BTF_KIND_TYPE_TAG: return 0; case BTF_KIND_INT: *(__u32 *)(t + 1) = bswap_32(*(__u32 *)(t + 1)); @@ -382,6 +391,9 @@ static int btf_bswap_type_rest(struct btf_type *t) v->size = bswap_32(v->size); } return 0; + case BTF_KIND_DECL_TAG: + btf_decl_tag(t)->component_idx = bswap_32(btf_decl_tag(t)->component_idx); + return 0; default: pr_debug("Unsupported BTF_KIND:%u\n", btf_kind(t)); return -EINVAL; @@ -431,13 +443,18 @@ __u32 btf__get_nr_types(const struct btf *btf) return btf->start_id + btf->nr_types - 1; } +__u32 btf__type_cnt(const struct btf *btf) +{ + return btf->start_id + btf->nr_types; +} + const struct btf *btf__base_btf(const struct btf *btf) { return btf->base_btf; } /* internal helper returning non-const pointer to a type */ -struct btf_type *btf_type_by_id(struct btf *btf, __u32 type_id) +struct btf_type *btf_type_by_id(const struct btf *btf, __u32 type_id) { if (type_id == 0) return &btf_void; @@ -462,8 +479,8 @@ static int determine_ptr_size(const struct btf *btf) if (btf->base_btf && btf->base_btf->ptr_sz > 0) return btf->base_btf->ptr_sz; - n = btf__get_nr_types(btf); - for (i = 1; i <= n; i++) { + n = btf__type_cnt(btf); + for (i = 1; i < n; i++) { t = btf__type_by_id(btf, i); if (!btf_is_int(t)) continue; @@ -523,9 +540,9 @@ int btf__set_pointer_size(struct btf *btf, size_t ptr_sz) static bool is_host_big_endian(void) { -#if __BYTE_ORDER == __LITTLE_ENDIAN +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ return false; -#elif __BYTE_ORDER == __BIG_ENDIAN +#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ return true; #else # error "Unrecognized __BYTE_ORDER__" @@ -592,6 +609,8 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id) case BTF_KIND_CONST: case BTF_KIND_RESTRICT: case BTF_KIND_VAR: + case BTF_KIND_DECL_TAG: + case BTF_KIND_TYPE_TAG: type_id = t->type; break; case BTF_KIND_ARRAY: @@ -633,6 +652,7 @@ int btf__align_of(const struct btf *btf, __u32 id) case BTF_KIND_VOLATILE: case BTF_KIND_CONST: case BTF_KIND_RESTRICT: + case BTF_KIND_TYPE_TAG: return btf__align_of(btf, t->type); case BTF_KIND_ARRAY: return btf__align_of(btf, btf_array(t)->type); @@ -679,12 +699,12 @@ int btf__resolve_type(const struct btf *btf, __u32 type_id) __s32 btf__find_by_name(const struct btf *btf, const char *type_name) { - __u32 i, nr_types = btf__get_nr_types(btf); + __u32 i, nr_types = btf__type_cnt(btf); if (!strcmp(type_name, "void")) return 0; - for (i = 1; i <= nr_types; i++) { + for (i = 1; i < nr_types; i++) { const struct btf_type *t = btf__type_by_id(btf, i); const char *name = btf__name_by_offset(btf, t->name_off); @@ -695,15 +715,15 @@ __s32 btf__find_by_name(const struct btf *btf, const char *type_name) return libbpf_err(-ENOENT); } -__s32 btf__find_by_name_kind(const struct btf *btf, const char *type_name, - __u32 kind) +static __s32 btf_find_by_name_kind(const struct btf *btf, int start_id, + const char *type_name, __u32 kind) { - __u32 i, nr_types = btf__get_nr_types(btf); + __u32 i, nr_types = btf__type_cnt(btf); if (kind == BTF_KIND_UNKN || !strcmp(type_name, "void")) return 0; - for (i = 1; i <= nr_types; i++) { + for (i = start_id; i < nr_types; i++) { const struct btf_type *t = btf__type_by_id(btf, i); const char *name; @@ -717,6 +737,18 @@ __s32 btf__find_by_name_kind(const struct btf *btf, const char *type_name, return libbpf_err(-ENOENT); } +__s32 btf__find_by_name_kind_own(const struct btf *btf, const char *type_name, + __u32 kind) +{ + return btf_find_by_name_kind(btf, btf->start_id, type_name, kind); +} + +__s32 btf__find_by_name_kind(const struct btf *btf, const char *type_name, + __u32 kind) +{ + return btf_find_by_name_kind(btf, 1, type_name, kind); +} + static bool btf_is_modifiable(const struct btf *btf) { return (void *)btf->hdr != btf->raw_data; @@ -764,7 +796,7 @@ static struct btf *btf_new_empty(struct btf *base_btf) if (base_btf) { btf->base_btf = base_btf; - btf->start_id = btf__get_nr_types(base_btf) + 1; + btf->start_id = btf__type_cnt(base_btf); btf->start_str_off = base_btf->hdr->str_len; } @@ -814,7 +846,7 @@ static struct btf *btf_new(const void *data, __u32 size, struct btf *base_btf) if (base_btf) { btf->base_btf = base_btf; - btf->start_id = btf__get_nr_types(base_btf) + 1; + btf->start_id = btf__type_cnt(base_btf); btf->start_str_off = base_btf->hdr->str_len; } @@ -869,7 +901,7 @@ static struct btf *btf_parse_elf(const char *path, struct btf *base_btf, return ERR_PTR(-LIBBPF_ERRNO__LIBELF); } - fd = open(path, O_RDONLY); + fd = open(path, O_RDONLY | O_CLOEXEC); if (fd < 0) { err = -errno; pr_warn("failed to open %s: %s\n", path, strerror(errno)); @@ -1090,149 +1122,88 @@ struct btf *btf__parse_split(const char *path, struct btf *base_btf) return libbpf_ptr(btf_parse(path, base_btf, NULL)); } -static int compare_vsi_off(const void *_a, const void *_b) -{ - const struct btf_var_secinfo *a = _a; - const struct btf_var_secinfo *b = _b; - - return a->offset - b->offset; -} - -static int btf_fixup_datasec(struct bpf_object *obj, struct btf *btf, - struct btf_type *t) -{ - __u32 size = 0, off = 0, i, vars = btf_vlen(t); - const char *name = btf__name_by_offset(btf, t->name_off); - const struct btf_type *t_var; - struct btf_var_secinfo *vsi; - const struct btf_var *var; - int ret; - - if (!name) { - pr_debug("No name found in string section for DATASEC kind.\n"); - return -ENOENT; - } - - /* .extern datasec size and var offsets were set correctly during - * extern collection step, so just skip straight to sorting variables - */ - if (t->size) - goto sort_vars; - - ret = bpf_object__section_size(obj, name, &size); - if (ret || !size || (t->size && t->size != size)) { - pr_debug("Invalid size for section %s: %u bytes\n", name, size); - return -ENOENT; - } - - t->size = size; - - for (i = 0, vsi = btf_var_secinfos(t); i < vars; i++, vsi++) { - t_var = btf__type_by_id(btf, vsi->type); - var = btf_var(t_var); - - if (!btf_is_var(t_var)) { - pr_debug("Non-VAR type seen in section %s\n", name); - return -EINVAL; - } - - if (var->linkage == BTF_VAR_STATIC) - continue; - - name = btf__name_by_offset(btf, t_var->name_off); - if (!name) { - pr_debug("No name found in string section for VAR kind\n"); - return -ENOENT; - } - - ret = bpf_object__variable_offset(obj, name, &off); - if (ret) { - pr_debug("No offset found in symbol table for VAR %s\n", - name); - return -ENOENT; - } - - vsi->offset = off; - } - -sort_vars: - qsort(btf_var_secinfos(t), vars, sizeof(*vsi), compare_vsi_off); - return 0; -} - -int btf__finalize_data(struct bpf_object *obj, struct btf *btf) -{ - int err = 0; - __u32 i; - - for (i = 1; i <= btf->nr_types; i++) { - struct btf_type *t = btf_type_by_id(btf, i); - - /* Loader needs to fix up some of the things compiler - * couldn't get its hands on while emitting BTF. This - * is section size and global variable offset. We use - * the info from the ELF itself for this purpose. - */ - if (btf_is_datasec(t)) { - err = btf_fixup_datasec(obj, btf, t); - if (err) - break; - } - } - - return libbpf_err(err); -} - static void *btf_get_raw_data(const struct btf *btf, __u32 *size, bool swap_endian); -int btf__load_into_kernel(struct btf *btf) +int btf_load_into_kernel(struct btf *btf, char *log_buf, size_t log_sz, __u32 log_level) { - __u32 log_buf_size = 0, raw_size; - char *log_buf = NULL; + LIBBPF_OPTS(bpf_btf_load_opts, opts); + __u32 buf_sz = 0, raw_size; + char *buf = NULL, *tmp; void *raw_data; int err = 0; if (btf->fd >= 0) return libbpf_err(-EEXIST); + if (log_sz && !log_buf) + return libbpf_err(-EINVAL); -retry_load: - if (log_buf_size) { - log_buf = malloc(log_buf_size); - if (!log_buf) - return libbpf_err(-ENOMEM); - - *log_buf = 0; - } - + /* cache native raw data representation */ raw_data = btf_get_raw_data(btf, &raw_size, false); if (!raw_data) { err = -ENOMEM; goto done; } - /* cache native raw data representation */ btf->raw_size = raw_size; btf->raw_data = raw_data; - btf->fd = bpf_load_btf(raw_data, raw_size, log_buf, log_buf_size, false); - if (btf->fd < 0) { - if (!log_buf || errno == ENOSPC) { - log_buf_size = max((__u32)BPF_LOG_BUF_SIZE, - log_buf_size << 1); - free(log_buf); - goto retry_load; +retry_load: + /* if log_level is 0, we won't provide log_buf/log_size to the kernel, + * initially. Only if BTF loading fails, we bump log_level to 1 and + * retry, using either auto-allocated or custom log_buf. This way + * non-NULL custom log_buf provides a buffer just in case, but hopes + * for successful load and no need for log_buf. + */ + if (log_level) { + /* if caller didn't provide custom log_buf, we'll keep + * allocating our own progressively bigger buffers for BTF + * verification log + */ + if (!log_buf) { + buf_sz = max((__u32)BPF_LOG_BUF_SIZE, buf_sz * 2); + tmp = realloc(buf, buf_sz); + if (!tmp) { + err = -ENOMEM; + goto done; + } + buf = tmp; + buf[0] = '\0'; } + opts.log_buf = log_buf ? log_buf : buf; + opts.log_size = log_buf ? log_sz : buf_sz; + opts.log_level = log_level; + } + + btf->fd = bpf_btf_load(raw_data, raw_size, &opts); + if (btf->fd < 0) { + /* time to turn on verbose mode and try again */ + if (log_level == 0) { + log_level = 1; + goto retry_load; + } + /* only retry if caller didn't provide custom log_buf, but + * make sure we can never overflow buf_sz + */ + if (!log_buf && errno == ENOSPC && buf_sz <= UINT_MAX / 2) + goto retry_load; + err = -errno; - pr_warn("Error loading BTF: %s(%d)\n", strerror(errno), errno); - if (*log_buf) - pr_warn("%s\n", log_buf); - goto done; + pr_warn("BTF loading error: %d\n", err); + /* don't print out contents of custom log_buf */ + if (!log_buf && buf[0]) + pr_warn("-- BEGIN BTF LOAD LOG ---\n%s\n-- END BTF LOAD LOG --\n", buf); } done: - free(log_buf); + free(buf); return libbpf_err(err); } + +int btf__load_into_kernel(struct btf *btf) +{ + return btf_load_into_kernel(btf, NULL, 0, 0); +} + int btf__load(struct btf *) __attribute__((alias("btf__load_into_kernel"))); int btf__fd(const struct btf *btf) @@ -1300,7 +1271,7 @@ static void *btf_get_raw_data(const struct btf *btf, __u32 *size, bool swap_endi return NULL; } -const void *btf__get_raw_data(const struct btf *btf_ro, __u32 *size) +const void *btf__raw_data(const struct btf *btf_ro, __u32 *size) { struct btf *btf = (struct btf *)btf_ro; __u32 data_sz; @@ -1308,7 +1279,7 @@ const void *btf__get_raw_data(const struct btf *btf_ro, __u32 *size) data = btf_get_raw_data(btf, &data_sz, btf->swapped_endian); if (!data) - return errno = -ENOMEM, NULL; + return errno = ENOMEM, NULL; btf->raw_size = data_sz; if (btf->swapped_endian) @@ -1319,6 +1290,9 @@ const void *btf__get_raw_data(const struct btf *btf_ro, __u32 *size) return data; } +__attribute__((alias("btf__raw_data"))) +const void *btf__get_raw_data(const struct btf *btf, __u32 *size); + const char *btf__str_by_offset(const struct btf *btf, __u32 offset) { if (offset < btf->start_str_off) @@ -1691,6 +1665,111 @@ int btf__add_type(struct btf *btf, const struct btf *src_btf, const struct btf_t return btf_commit_type(btf, sz); } +static int btf_rewrite_type_ids(__u32 *type_id, void *ctx) +{ + struct btf *btf = ctx; + + if (!*type_id) /* nothing to do for VOID references */ + return 0; + + /* we haven't updated btf's type count yet, so + * btf->start_id + btf->nr_types - 1 is the type ID offset we should + * add to all newly added BTF types + */ + *type_id += btf->start_id + btf->nr_types - 1; + return 0; +} + +int btf__add_btf(struct btf *btf, const struct btf *src_btf) +{ + struct btf_pipe p = { .src = src_btf, .dst = btf }; + int data_sz, sz, cnt, i, err, old_strs_len; + __u32 *off; + void *t; + + /* appending split BTF isn't supported yet */ + if (src_btf->base_btf) + return libbpf_err(-ENOTSUP); + + /* deconstruct BTF, if necessary, and invalidate raw_data */ + if (btf_ensure_modifiable(btf)) + return libbpf_err(-ENOMEM); + + /* remember original strings section size if we have to roll back + * partial strings section changes + */ + old_strs_len = btf->hdr->str_len; + + data_sz = src_btf->hdr->type_len; + cnt = btf__type_cnt(src_btf) - 1; + + /* pre-allocate enough memory for new types */ + t = btf_add_type_mem(btf, data_sz); + if (!t) + return libbpf_err(-ENOMEM); + + /* pre-allocate enough memory for type offset index for new types */ + off = btf_add_type_offs_mem(btf, cnt); + if (!off) + return libbpf_err(-ENOMEM); + + /* bulk copy types data for all types from src_btf */ + memcpy(t, src_btf->types_data, data_sz); + + for (i = 0; i < cnt; i++) { + sz = btf_type_size(t); + if (sz < 0) { + /* unlikely, has to be corrupted src_btf */ + err = sz; + goto err_out; + } + + /* fill out type ID to type offset mapping for lookups by type ID */ + *off = t - btf->types_data; + + /* add, dedup, and remap strings referenced by this BTF type */ + err = btf_type_visit_str_offs(t, btf_rewrite_str, &p); + if (err) + goto err_out; + + /* remap all type IDs referenced from this BTF type */ + err = btf_type_visit_type_ids(t, btf_rewrite_type_ids, btf); + if (err) + goto err_out; + + /* go to next type data and type offset index entry */ + t += sz; + off++; + } + + /* Up until now any of the copied type data was effectively invisible, + * so if we exited early before this point due to error, BTF would be + * effectively unmodified. There would be extra internal memory + * pre-allocated, but it would not be available for querying. But now + * that we've copied and rewritten all the data successfully, we can + * update type count and various internal offsets and sizes to + * "commit" the changes and made them visible to the outside world. + */ + btf->hdr->type_len += data_sz; + btf->hdr->str_off += data_sz; + btf->nr_types += cnt; + + /* return type ID of the first added BTF type */ + return btf->start_id + btf->nr_types - cnt; +err_out: + /* zero out preallocated memory as if it was just allocated with + * libbpf_add_mem() + */ + memset(btf->types_data + btf->hdr->type_len, 0, data_sz); + memset(btf->strs_data + old_strs_len, 0, btf->hdr->str_len - old_strs_len); + + /* and now restore original strings section size; types data size + * wasn't modified, so doesn't need restoring, see big comment above */ + btf->hdr->str_len = old_strs_len; + + return libbpf_err(err); +} + /* * Append new BTF_KIND_INT type with: * - *name* - non-empty, non-NULL type name; @@ -1939,7 +2018,7 @@ int btf__add_union(struct btf *btf, const char *name, __u32 byte_sz) static struct btf_type *btf_last_type(struct btf *btf) { - return btf_type_by_id(btf, btf__get_nr_types(btf)); + return btf_type_by_id(btf, btf__type_cnt(btf) - 1); } /* @@ -2192,6 +2271,22 @@ int btf__add_restrict(struct btf *btf, int ref_type_id) return btf_add_ref_kind(btf, BTF_KIND_RESTRICT, NULL, ref_type_id); } +/* + * Append new BTF_KIND_TYPE_TAG type with: + * - *value*, non-empty/non-NULL tag value; + * - *ref_type_id* - referenced type ID, it might not exist yet; + * Returns: + * - >0, type ID of newly added BTF type; + * - <0, on error. + */ +int btf__add_type_tag(struct btf *btf, const char *value, int ref_type_id) +{ + if (!value|| !value[0]) + return libbpf_err(-EINVAL); + + return btf_add_ref_kind(btf, BTF_KIND_TYPE_TAG, value, ref_type_id); +} + /* * Append new BTF_KIND_FUNC type with: * - *name*, non-empty/non-NULL name; @@ -2446,6 +2541,48 @@ int btf__add_datasec_var_info(struct btf *btf, int var_type_id, __u32 offset, __ return 0; } +/* + * Append new BTF_KIND_DECL_TAG type with: + * - *value* - non-empty/non-NULL string; + * - *ref_type_id* - referenced type ID, it might not exist yet; + * - *component_idx* - -1 for tagging reference type, otherwise struct/union + * member or function argument index; + * Returns: + * - >0, type ID of newly added BTF type; + * - <0, on error. + */ +int btf__add_decl_tag(struct btf *btf, const char *value, int ref_type_id, + int component_idx) +{ + struct btf_type *t; + int sz, value_off; + + if (!value || !value[0] || component_idx < -1) + return libbpf_err(-EINVAL); + + if (validate_type_id(ref_type_id)) + return libbpf_err(-EINVAL); + + if (btf_ensure_modifiable(btf)) + return libbpf_err(-ENOMEM); + + sz = sizeof(struct btf_type) + sizeof(struct btf_decl_tag); + t = btf_add_type_mem(btf, sz); + if (!t) + return libbpf_err(-ENOMEM); + + value_off = btf__add_str(btf, value); + if (value_off < 0) + return value_off; + + t->name_off = value_off; + t->info = btf_type_info(BTF_KIND_DECL_TAG, 0, false); + t->type = ref_type_id; + btf_decl_tag(t)->component_idx = component_idx; + + return btf_commit_type(btf, sz); +} + struct btf_ext_sec_setup_param { __u32 off; __u32 len; @@ -2761,8 +2898,7 @@ __u32 btf_ext__line_info_rec_size(const struct btf_ext *btf_ext) struct btf_dedup; -static struct btf_dedup *btf_dedup_new(struct btf *btf, struct btf_ext *btf_ext, - const struct btf_dedup_opts *opts); +static struct btf_dedup *btf_dedup_new(struct btf *btf, const struct btf_dedup_opts *opts); static void btf_dedup_free(struct btf_dedup *d); static int btf_dedup_prep(struct btf_dedup *d); static int btf_dedup_strings(struct btf_dedup *d); @@ -2909,12 +3045,17 @@ static int btf_dedup_remap_types(struct btf_dedup *d); * deduplicating structs/unions is described in greater details in comments for * `btf_dedup_is_equiv` function. */ -int btf__dedup(struct btf *btf, struct btf_ext *btf_ext, - const struct btf_dedup_opts *opts) + +DEFAULT_VERSION(btf__dedup_v0_6_0, btf__dedup, LIBBPF_0.6.0) +int btf__dedup_v0_6_0(struct btf *btf, const struct btf_dedup_opts *opts) { - struct btf_dedup *d = btf_dedup_new(btf, btf_ext, opts); + struct btf_dedup *d; int err; + if (!OPTS_VALID(opts, btf_dedup_opts)) + return libbpf_err(-EINVAL); + + d = btf_dedup_new(btf, opts); if (IS_ERR(d)) { pr_debug("btf_dedup_new failed: %ld", PTR_ERR(d)); return libbpf_err(-EINVAL); @@ -2966,6 +3107,19 @@ int btf__dedup(struct btf *btf, struct btf_ext *btf_ext, return libbpf_err(err); } +COMPAT_VERSION(btf__dedup_deprecated, btf__dedup, LIBBPF_0.0.2) +int btf__dedup_deprecated(struct btf *btf, struct btf_ext *btf_ext, const void *unused_opts) +{ + LIBBPF_OPTS(btf_dedup_opts, opts, .btf_ext = btf_ext); + + if (unused_opts) { + pr_warn("please use new version of btf__dedup() that supports options\n"); + return libbpf_err(-ENOTSUP); + } + + return btf__dedup(btf, &opts); +} + #define BTF_UNPROCESSED_ID ((__u32)-1) #define BTF_IN_PROGRESS_ID ((__u32)-2) @@ -3078,8 +3232,7 @@ static bool btf_dedup_equal_fn(const void *k1, const void *k2, void *ctx) return k1 == k2; } -static struct btf_dedup *btf_dedup_new(struct btf *btf, struct btf_ext *btf_ext, - const struct btf_dedup_opts *opts) +static struct btf_dedup *btf_dedup_new(struct btf *btf, const struct btf_dedup_opts *opts) { struct btf_dedup *d = calloc(1, sizeof(struct btf_dedup)); hashmap_hash_fn hash_fn = btf_dedup_identity_hash_fn; @@ -3088,13 +3241,11 @@ static struct btf_dedup *btf_dedup_new(struct btf *btf, struct btf_ext *btf_ext, if (!d) return ERR_PTR(-ENOMEM); - d->opts.dont_resolve_fwds = opts && opts->dont_resolve_fwds; - /* dedup_table_size is now used only to force collisions in tests */ - if (opts && opts->dedup_table_size == 1) + if (OPTS_GET(opts, force_collisions, false)) hash_fn = btf_dedup_collision_hash_fn; d->btf = btf; - d->btf_ext = btf_ext; + d->btf_ext = OPTS_GET(opts, btf_ext, NULL); d->dedup_table = hashmap__new(hash_fn, btf_dedup_equal_fn, NULL); if (IS_ERR(d->dedup_table)) { @@ -3103,7 +3254,7 @@ static struct btf_dedup *btf_dedup_new(struct btf *btf, struct btf_ext *btf_ext, goto done; } - type_cnt = btf__get_nr_types(btf) + 1; + type_cnt = btf__type_cnt(btf); d->map = malloc(sizeof(__u32) * type_cnt); if (!d->map) { err = -ENOMEM; @@ -3264,8 +3415,8 @@ static bool btf_equal_common(struct btf_type *t1, struct btf_type *t2) t1->size == t2->size; } -/* Calculate type signature hash of INT. */ -static long btf_hash_int(struct btf_type *t) +/* Calculate type signature hash of INT or TAG. */ +static long btf_hash_int_decl_tag(struct btf_type *t) { __u32 info = *(__u32 *)(t + 1); long h; @@ -3275,8 +3426,8 @@ static long btf_hash_int(struct btf_type *t) return h; } -/* Check structural equality of two INTs. */ -static bool btf_equal_int(struct btf_type *t1, struct btf_type *t2) +/* Check structural equality of two INTs or TAGs. */ +static bool btf_equal_int_tag(struct btf_type *t1, struct btf_type *t2) { __u32 info1, info2; @@ -3540,10 +3691,12 @@ static int btf_dedup_prep(struct btf_dedup *d) case BTF_KIND_TYPEDEF: case BTF_KIND_FUNC: case BTF_KIND_FLOAT: + case BTF_KIND_TYPE_TAG: h = btf_hash_common(t); break; case BTF_KIND_INT: - h = btf_hash_int(t); + case BTF_KIND_DECL_TAG: + h = btf_hash_int_decl_tag(t); break; case BTF_KIND_ENUM: h = btf_hash_enum(t); @@ -3598,14 +3751,16 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id) case BTF_KIND_FUNC_PROTO: case BTF_KIND_VAR: case BTF_KIND_DATASEC: + case BTF_KIND_DECL_TAG: + case BTF_KIND_TYPE_TAG: return 0; case BTF_KIND_INT: - h = btf_hash_int(t); + h = btf_hash_int_decl_tag(t); for_each_dedup_cand(d, hash_entry, h) { cand_id = (__u32)(long)hash_entry->value; cand = btf_type_by_id(d->btf, cand_id); - if (btf_equal_int(t, cand)) { + if (btf_equal_int_tag(t, cand)) { new_id = cand_id; break; } @@ -3621,8 +3776,6 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id) new_id = cand_id; break; } - if (d->opts.dont_resolve_fwds) - continue; if (btf_compat_enum(t, cand)) { if (btf_is_enum_fwd(t)) { /* resolve fwd to full enum */ @@ -3902,8 +4055,7 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id, return 0; /* FWD <--> STRUCT/UNION equivalence check, if enabled */ - if (!d->opts.dont_resolve_fwds - && (cand_kind == BTF_KIND_FWD || canon_kind == BTF_KIND_FWD) + if ((cand_kind == BTF_KIND_FWD || canon_kind == BTF_KIND_FWD) && cand_kind != canon_kind) { __u16 real_kind; __u16 fwd_kind; @@ -3926,13 +4078,10 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id, switch (cand_kind) { case BTF_KIND_INT: - return btf_equal_int(cand_type, canon_type); + return btf_equal_int_tag(cand_type, canon_type); case BTF_KIND_ENUM: - if (d->opts.dont_resolve_fwds) - return btf_equal_enum(cand_type, canon_type); - else - return btf_compat_enum(cand_type, canon_type); + return btf_compat_enum(cand_type, canon_type); case BTF_KIND_FWD: case BTF_KIND_FLOAT: @@ -3944,6 +4093,7 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id, case BTF_KIND_PTR: case BTF_KIND_TYPEDEF: case BTF_KIND_FUNC: + case BTF_KIND_TYPE_TAG: if (cand_type->info != canon_type->info) return 0; return btf_dedup_is_equiv(d, cand_type->type, canon_type->type); @@ -4239,6 +4389,7 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id) case BTF_KIND_PTR: case BTF_KIND_TYPEDEF: case BTF_KIND_FUNC: + case BTF_KIND_TYPE_TAG: ref_type_id = btf_dedup_ref_type(d, t->type); if (ref_type_id < 0) return ref_type_id; @@ -4255,6 +4406,23 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id) } break; + case BTF_KIND_DECL_TAG: + ref_type_id = btf_dedup_ref_type(d, t->type); + if (ref_type_id < 0) + return ref_type_id; + t->type = ref_type_id; + + h = btf_hash_int_decl_tag(t); + for_each_dedup_cand(d, hash_entry, h) { + cand_id = (__u32)(long)hash_entry->value; + cand = btf_type_by_id(d->btf, cand_id); + if (btf_equal_int_tag(t, cand)) { + new_id = cand_id; + break; + } + } + break; + case BTF_KIND_ARRAY: { struct btf_array *info = btf_array(t); @@ -4527,6 +4695,8 @@ int btf_type_visit_type_ids(struct btf_type *t, type_id_visit_fn visit, void *ct case BTF_KIND_TYPEDEF: case BTF_KIND_FUNC: case BTF_KIND_VAR: + case BTF_KIND_DECL_TAG: + case BTF_KIND_TYPE_TAG: return visit(&t->type, ctx); case BTF_KIND_ARRAY: { diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h index b0ee338a0c..061839f045 100644 --- a/tools/lib/bpf/btf.h +++ b/tools/lib/bpf/btf.h @@ -1,5 +1,6 @@ /* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ /* Copyright (c) 2018 Facebook */ +/*! \file */ #ifndef __LIBBPF_BTF_H #define __LIBBPF_BTF_H @@ -30,11 +31,80 @@ enum btf_endianness { BTF_BIG_ENDIAN = 1, }; +/** + * @brief **btf__free()** frees all data of a BTF object + * @param btf BTF object to free + */ LIBBPF_API void btf__free(struct btf *btf); +/** + * @brief **btf__new()** creates a new instance of a BTF object from the raw + * bytes of an ELF's BTF section + * @param data raw bytes + * @param size number of bytes passed in `data` + * @return new BTF object instance which has to be eventually freed with + * **btf__free()** + * + * On error, error-code-encoded-as-pointer is returned, not a NULL. To extract + * error code from such a pointer `libbpf_get_error()` should be used. If + * `libbpf_set_strict_mode(LIBBPF_STRICT_CLEAN_PTRS)` is enabled, NULL is + * returned on error instead. In both cases thread-local `errno` variable is + * always set to error code as well. + */ LIBBPF_API struct btf *btf__new(const void *data, __u32 size); + +/** + * @brief **btf__new_split()** create a new instance of a BTF object from the + * provided raw data bytes. It takes another BTF instance, **base_btf**, which + * serves as a base BTF, which is extended by types in a newly created BTF + * instance + * @param data raw bytes + * @param size length of raw bytes + * @param base_btf the base BTF object + * @return new BTF object instance which has to be eventually freed with + * **btf__free()** + * + * If *base_btf* is NULL, `btf__new_split()` is equivalent to `btf__new()` and + * creates non-split BTF. + * + * On error, error-code-encoded-as-pointer is returned, not a NULL. To extract + * error code from such a pointer `libbpf_get_error()` should be used. If + * `libbpf_set_strict_mode(LIBBPF_STRICT_CLEAN_PTRS)` is enabled, NULL is + * returned on error instead. In both cases thread-local `errno` variable is + * always set to error code as well. + */ LIBBPF_API struct btf *btf__new_split(const void *data, __u32 size, struct btf *base_btf); + +/** + * @brief **btf__new_empty()** creates an empty BTF object. Use + * `btf__add_*()` to populate such BTF object. + * @return new BTF object instance which has to be eventually freed with + * **btf__free()** + * + * On error, error-code-encoded-as-pointer is returned, not a NULL. To extract + * error code from such a pointer `libbpf_get_error()` should be used. If + * `libbpf_set_strict_mode(LIBBPF_STRICT_CLEAN_PTRS)` is enabled, NULL is + * returned on error instead. In both cases thread-local `errno` variable is + * always set to error code as well. + */ LIBBPF_API struct btf *btf__new_empty(void); + +/** + * @brief **btf__new_empty_split()** creates an unpopulated BTF object from an + * ELF BTF section except with a base BTF on top of which split BTF should be + * based + * @return new BTF object instance which has to be eventually freed with + * **btf__free()** + * + * If *base_btf* is NULL, `btf__new_empty_split()` is equivalent to + * `btf__new_empty()` and creates non-split BTF. + * + * On error, error-code-encoded-as-pointer is returned, not a NULL. To extract + * error code from such a pointer `libbpf_get_error()` should be used. If + * `libbpf_set_strict_mode(LIBBPF_STRICT_CLEAN_PTRS)` is enabled, NULL is + * returned on error instead. In both cases thread-local `errno` variable is + * always set to error code as well. + */ LIBBPF_API struct btf *btf__new_empty_split(struct btf *base_btf); LIBBPF_API struct btf *btf__parse(const char *path, struct btf_ext **btf_ext); @@ -50,16 +120,21 @@ LIBBPF_API struct btf *libbpf_find_kernel_btf(void); LIBBPF_API struct btf *btf__load_from_kernel_by_id(__u32 id); LIBBPF_API struct btf *btf__load_from_kernel_by_id_split(__u32 id, struct btf *base_btf); +LIBBPF_DEPRECATED_SINCE(0, 6, "use btf__load_from_kernel_by_id instead") LIBBPF_API int btf__get_from_id(__u32 id, struct btf **btf); +LIBBPF_DEPRECATED_SINCE(0, 6, "intended for internal libbpf use only") LIBBPF_API int btf__finalize_data(struct bpf_object *obj, struct btf *btf); +LIBBPF_DEPRECATED_SINCE(0, 6, "use btf__load_into_kernel instead") LIBBPF_API int btf__load(struct btf *btf); LIBBPF_API int btf__load_into_kernel(struct btf *btf); LIBBPF_API __s32 btf__find_by_name(const struct btf *btf, const char *type_name); LIBBPF_API __s32 btf__find_by_name_kind(const struct btf *btf, const char *type_name, __u32 kind); +LIBBPF_DEPRECATED_SINCE(0, 7, "use btf__type_cnt() instead; note that btf__get_nr_types() == btf__type_cnt() - 1") LIBBPF_API __u32 btf__get_nr_types(const struct btf *btf); +LIBBPF_API __u32 btf__type_cnt(const struct btf *btf); LIBBPF_API const struct btf *btf__base_btf(const struct btf *btf); LIBBPF_API const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 id); @@ -72,7 +147,9 @@ LIBBPF_API int btf__resolve_type(const struct btf *btf, __u32 type_id); LIBBPF_API int btf__align_of(const struct btf *btf, __u32 id); LIBBPF_API int btf__fd(const struct btf *btf); LIBBPF_API void btf__set_fd(struct btf *btf, int fd); +LIBBPF_DEPRECATED_SINCE(0, 7, "use btf__raw_data() instead") LIBBPF_API const void *btf__get_raw_data(const struct btf *btf, __u32 *size); +LIBBPF_API const void *btf__raw_data(const struct btf *btf, __u32 *size); LIBBPF_API const char *btf__name_by_offset(const struct btf *btf, __u32 offset); LIBBPF_API const char *btf__str_by_offset(const struct btf *btf, __u32 offset); LIBBPF_API int btf__get_map_kv_tids(const struct btf *btf, const char *map_name, @@ -101,6 +178,28 @@ LIBBPF_API int btf__find_str(struct btf *btf, const char *s); LIBBPF_API int btf__add_str(struct btf *btf, const char *s); LIBBPF_API int btf__add_type(struct btf *btf, const struct btf *src_btf, const struct btf_type *src_type); +/** + * @brief **btf__add_btf()** appends all the BTF types from *src_btf* into *btf* + * @param btf BTF object which all the BTF types and strings are added to + * @param src_btf BTF object which all BTF types and referenced strings are copied from + * @return BTF type ID of the first appended BTF type, or negative error code + * + * **btf__add_btf()** can be used to simply and efficiently append the entire + * contents of one BTF object to another one. All the BTF type data is copied + * over, all referenced type IDs are adjusted by adding a necessary ID offset. + * Only strings referenced from BTF types are copied over and deduplicated, so + * if there were some unused strings in *src_btf*, those won't be copied over, + * which is consistent with the general string deduplication semantics of BTF + * writing APIs. + * + * If any error is encountered during this process, the contents of *btf* is + * left intact, which means that **btf__add_btf()** follows the transactional + * semantics and the operation as a whole is all-or-nothing. + * + * *src_btf* has to be non-split BTF, as of now copying types from split BTF + * is not supported and will result in -ENOTSUP error code returned. + */ +LIBBPF_API int btf__add_btf(struct btf *btf, const struct btf *src_btf); LIBBPF_API int btf__add_int(struct btf *btf, const char *name, size_t byte_sz, int encoding); LIBBPF_API int btf__add_float(struct btf *btf, const char *name, size_t byte_sz); @@ -128,6 +227,7 @@ LIBBPF_API int btf__add_typedef(struct btf *btf, const char *name, int ref_type_ LIBBPF_API int btf__add_volatile(struct btf *btf, int ref_type_id); LIBBPF_API int btf__add_const(struct btf *btf, int ref_type_id); LIBBPF_API int btf__add_restrict(struct btf *btf, int ref_type_id); +LIBBPF_API int btf__add_type_tag(struct btf *btf, const char *value, int ref_type_id); /* func and func_proto construction APIs */ LIBBPF_API int btf__add_func(struct btf *btf, const char *name, @@ -141,26 +241,91 @@ LIBBPF_API int btf__add_datasec(struct btf *btf, const char *name, __u32 byte_sz LIBBPF_API int btf__add_datasec_var_info(struct btf *btf, int var_type_id, __u32 offset, __u32 byte_sz); -struct btf_dedup_opts { - unsigned int dedup_table_size; - bool dont_resolve_fwds; -}; +/* tag construction API */ +LIBBPF_API int btf__add_decl_tag(struct btf *btf, const char *value, int ref_type_id, + int component_idx); -LIBBPF_API int btf__dedup(struct btf *btf, struct btf_ext *btf_ext, - const struct btf_dedup_opts *opts); +struct btf_dedup_opts { + size_t sz; + /* optional .BTF.ext info to dedup along the main BTF info */ + struct btf_ext *btf_ext; + /* force hash collisions (used for testing) */ + bool force_collisions; + size_t :0; +}; +#define btf_dedup_opts__last_field force_collisions + +LIBBPF_API int btf__dedup(struct btf *btf, const struct btf_dedup_opts *opts); + +LIBBPF_API int btf__dedup_v0_6_0(struct btf *btf, const struct btf_dedup_opts *opts); + +LIBBPF_DEPRECATED_SINCE(0, 7, "use btf__dedup() instead") +LIBBPF_API int btf__dedup_deprecated(struct btf *btf, struct btf_ext *btf_ext, const void *opts); +#define btf__dedup(...) ___libbpf_overload(___btf_dedup, __VA_ARGS__) +#define ___btf_dedup3(btf, btf_ext, opts) btf__dedup_deprecated(btf, btf_ext, opts) +#define ___btf_dedup2(btf, opts) btf__dedup(btf, opts) struct btf_dump; struct btf_dump_opts { - void *ctx; + union { + size_t sz; + void *ctx; /* DEPRECATED: will be gone in v1.0 */ + }; }; typedef void (*btf_dump_printf_fn_t)(void *ctx, const char *fmt, va_list args); LIBBPF_API struct btf_dump *btf_dump__new(const struct btf *btf, - const struct btf_ext *btf_ext, - const struct btf_dump_opts *opts, - btf_dump_printf_fn_t printf_fn); + btf_dump_printf_fn_t printf_fn, + void *ctx, + const struct btf_dump_opts *opts); + +LIBBPF_API struct btf_dump *btf_dump__new_v0_6_0(const struct btf *btf, + btf_dump_printf_fn_t printf_fn, + void *ctx, + const struct btf_dump_opts *opts); + +LIBBPF_API struct btf_dump *btf_dump__new_deprecated(const struct btf *btf, + const struct btf_ext *btf_ext, + const struct btf_dump_opts *opts, + btf_dump_printf_fn_t printf_fn); + +/* Choose either btf_dump__new() or btf_dump__new_deprecated() based on the + * type of 4th argument. If it's btf_dump's print callback, use deprecated + * API; otherwise, choose the new btf_dump__new(). ___libbpf_override() + * doesn't work here because both variants have 4 input arguments. + * + * (void *) casts are necessary to avoid compilation warnings about type + * mismatches, because even though __builtin_choose_expr() only ever evaluates + * one side the other side still has to satisfy type constraints (this is + * compiler implementation limitation which might be lifted eventually, + * according to the documentation). So passing struct btf_ext in place of + * btf_dump_printf_fn_t would be generating compilation warning. Casting to + * void * avoids this issue. + * + * Also, two type compatibility checks for a function and function pointer are + * required because passing function reference into btf_dump__new() as + * btf_dump__new(..., my_callback, ...) and as btf_dump__new(..., + * &my_callback, ...) (not explicit ampersand in the latter case) actually + * differs as far as __builtin_types_compatible_p() is concerned. Thus two + * checks are combined to detect callback argument. + * + * The rest works just like in case of ___libbpf_override() usage with symbol + * versioning. + * + * C++ compilers don't support __builtin_types_compatible_p(), so at least + * don't screw up compilation for them and let C++ users pick btf_dump__new + * vs btf_dump__new_deprecated explicitly. + */ +#ifndef __cplusplus +#define btf_dump__new(a1, a2, a3, a4) __builtin_choose_expr( \ + __builtin_types_compatible_p(typeof(a4), btf_dump_printf_fn_t) || \ + __builtin_types_compatible_p(typeof(a4), void(void *, const char *, va_list)), \ + btf_dump__new_deprecated((void *)a1, (void *)a2, (void *)a3, (void *)a4), \ + btf_dump__new((void *)a1, (void *)a2, (void *)a3, (void *)a4)) +#endif + LIBBPF_API void btf_dump__free(struct btf_dump *d); LIBBPF_API int btf_dump__dump_type(struct btf_dump *d, __u32 id); @@ -300,7 +465,8 @@ static inline bool btf_is_mod(const struct btf_type *t) return kind == BTF_KIND_VOLATILE || kind == BTF_KIND_CONST || - kind == BTF_KIND_RESTRICT; + kind == BTF_KIND_RESTRICT || + kind == BTF_KIND_TYPE_TAG; } static inline bool btf_is_func(const struct btf_type *t) @@ -328,6 +494,16 @@ static inline bool btf_is_float(const struct btf_type *t) return btf_kind(t) == BTF_KIND_FLOAT; } +static inline bool btf_is_decl_tag(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_DECL_TAG; +} + +static inline bool btf_is_type_tag(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_TYPE_TAG; +} + static inline __u8 btf_int_encoding(const struct btf_type *t) { return BTF_INT_ENCODING(*(__u32 *)(t + 1)); @@ -396,6 +572,12 @@ btf_var_secinfos(const struct btf_type *t) return (struct btf_var_secinfo *)(t + 1); } +struct btf_decl_tag; +static inline struct btf_decl_tag *btf_decl_tag(const struct btf_type *t) +{ + return (struct btf_decl_tag *)(t + 1); +} + #ifdef __cplusplus } /* extern "C" */ #endif diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c index 8c93258027..b9a3260c83 100644 --- a/tools/lib/bpf/btf_dump.c +++ b/tools/lib/bpf/btf_dump.c @@ -77,9 +77,8 @@ struct btf_dump_data { struct btf_dump { const struct btf *btf; - const struct btf_ext *btf_ext; btf_dump_printf_fn_t printf_fn; - struct btf_dump_opts opts; + void *cb_ctx; int ptr_sz; bool strip_mods; bool skip_anon_defs; @@ -138,29 +137,32 @@ static void btf_dump_printf(const struct btf_dump *d, const char *fmt, ...) va_list args; va_start(args, fmt); - d->printf_fn(d->opts.ctx, fmt, args); + d->printf_fn(d->cb_ctx, fmt, args); va_end(args); } static int btf_dump_mark_referenced(struct btf_dump *d); static int btf_dump_resize(struct btf_dump *d); -struct btf_dump *btf_dump__new(const struct btf *btf, - const struct btf_ext *btf_ext, - const struct btf_dump_opts *opts, - btf_dump_printf_fn_t printf_fn) +DEFAULT_VERSION(btf_dump__new_v0_6_0, btf_dump__new, LIBBPF_0.6.0) +struct btf_dump *btf_dump__new_v0_6_0(const struct btf *btf, + btf_dump_printf_fn_t printf_fn, + void *ctx, + const struct btf_dump_opts *opts) { struct btf_dump *d; int err; + if (!printf_fn) + return libbpf_err_ptr(-EINVAL); + d = calloc(1, sizeof(struct btf_dump)); if (!d) return libbpf_err_ptr(-ENOMEM); d->btf = btf; - d->btf_ext = btf_ext; d->printf_fn = printf_fn; - d->opts.ctx = opts ? opts->ctx : NULL; + d->cb_ctx = ctx; d->ptr_sz = btf__pointer_size(btf) ? : sizeof(void *); d->type_names = hashmap__new(str_hash_fn, str_equal_fn, NULL); @@ -186,9 +188,20 @@ struct btf_dump *btf_dump__new(const struct btf *btf, return libbpf_err_ptr(err); } +COMPAT_VERSION(btf_dump__new_deprecated, btf_dump__new, LIBBPF_0.0.4) +struct btf_dump *btf_dump__new_deprecated(const struct btf *btf, + const struct btf_ext *btf_ext, + const struct btf_dump_opts *opts, + btf_dump_printf_fn_t printf_fn) +{ + if (!printf_fn) + return libbpf_err_ptr(-EINVAL); + return btf_dump__new_v0_6_0(btf, printf_fn, opts ? opts->ctx : NULL, opts); +} + static int btf_dump_resize(struct btf_dump *d) { - int err, last_id = btf__get_nr_types(d->btf); + int err, last_id = btf__type_cnt(d->btf) - 1; if (last_id <= d->last_id) return 0; @@ -262,7 +275,7 @@ int btf_dump__dump_type(struct btf_dump *d, __u32 id) { int err, i; - if (id > btf__get_nr_types(d->btf)) + if (id >= btf__type_cnt(d->btf)) return libbpf_err(-EINVAL); err = btf_dump_resize(d); @@ -294,11 +307,11 @@ int btf_dump__dump_type(struct btf_dump *d, __u32 id) */ static int btf_dump_mark_referenced(struct btf_dump *d) { - int i, j, n = btf__get_nr_types(d->btf); + int i, j, n = btf__type_cnt(d->btf); const struct btf_type *t; __u16 vlen; - for (i = d->last_id + 1; i <= n; i++) { + for (i = d->last_id + 1; i < n; i++) { t = btf__type_by_id(d->btf, i); vlen = btf_vlen(t); @@ -316,6 +329,8 @@ static int btf_dump_mark_referenced(struct btf_dump *d) case BTF_KIND_TYPEDEF: case BTF_KIND_FUNC: case BTF_KIND_VAR: + case BTF_KIND_DECL_TAG: + case BTF_KIND_TYPE_TAG: d->type_states[t->type].referenced = 1; break; @@ -559,6 +574,7 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr) case BTF_KIND_VOLATILE: case BTF_KIND_CONST: case BTF_KIND_RESTRICT: + case BTF_KIND_TYPE_TAG: return btf_dump_order_type(d, t->type, through_ptr); case BTF_KIND_FUNC_PROTO: { @@ -583,6 +599,7 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr) case BTF_KIND_FUNC: case BTF_KIND_VAR: case BTF_KIND_DATASEC: + case BTF_KIND_DECL_TAG: d->type_states[id].order_state = ORDERED; return 0; @@ -732,6 +749,7 @@ static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id) case BTF_KIND_VOLATILE: case BTF_KIND_CONST: case BTF_KIND_RESTRICT: + case BTF_KIND_TYPE_TAG: btf_dump_emit_type(d, t->type, cont_id); break; case BTF_KIND_ARRAY: @@ -1152,6 +1170,7 @@ static void btf_dump_emit_type_decl(struct btf_dump *d, __u32 id, case BTF_KIND_CONST: case BTF_KIND_RESTRICT: case BTF_KIND_FUNC_PROTO: + case BTF_KIND_TYPE_TAG: id = t->type; break; case BTF_KIND_ARRAY: @@ -1320,6 +1339,11 @@ static void btf_dump_emit_type_chain(struct btf_dump *d, case BTF_KIND_RESTRICT: btf_dump_printf(d, " restrict"); break; + case BTF_KIND_TYPE_TAG: + btf_dump_emit_mods(d, decls); + name = btf_name_of(d, t->name_off); + btf_dump_printf(d, " __attribute__((btf_type_tag(\"%s\")))", name); + break; case BTF_KIND_ARRAY: { const struct btf_array *a = btf_array(t); const struct btf_type *next_t; @@ -1560,29 +1584,28 @@ static int btf_dump_get_bitfield_value(struct btf_dump *d, __u64 *value) { __u16 left_shift_bits, right_shift_bits; - __u8 nr_copy_bits, nr_copy_bytes; const __u8 *bytes = data; - int sz = t->size; + __u8 nr_copy_bits; __u64 num = 0; int i; /* Maximum supported bitfield size is 64 bits */ - if (sz > 8) { - pr_warn("unexpected bitfield size %d\n", sz); + if (t->size > 8) { + pr_warn("unexpected bitfield size %d\n", t->size); return -EINVAL; } /* Bitfield value retrieval is done in two steps; first relevant bytes are * stored in num, then we left/right shift num to eliminate irrelevant bits. */ +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ + for (i = t->size - 1; i >= 0; i--) + num = num * 256 + bytes[i]; nr_copy_bits = bit_sz + bits_offset; - nr_copy_bytes = t->size; -#if __BYTE_ORDER == __LITTLE_ENDIAN - for (i = nr_copy_bytes - 1; i >= 0; i--) - num = num * 256 + bytes[i]; -#elif __BYTE_ORDER == __BIG_ENDIAN - for (i = 0; i < nr_copy_bytes; i++) +#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ + for (i = 0; i < t->size; i++) num = num * 256 + bytes[i]; + nr_copy_bits = t->size * 8 - bits_offset; #else # error "Unrecognized __BYTE_ORDER__" #endif @@ -1656,9 +1679,15 @@ static int btf_dump_base_type_check_zero(struct btf_dump *d, return 0; } -static bool ptr_is_aligned(const void *data, int data_sz) +static bool ptr_is_aligned(const struct btf *btf, __u32 type_id, + const void *data) { - return ((uintptr_t)data) % data_sz == 0; + int alignment = btf__align_of(btf, type_id); + + if (alignment == 0) + return false; + + return ((uintptr_t)data) % alignment == 0; } static int btf_dump_int_data(struct btf_dump *d, @@ -1669,9 +1698,10 @@ static int btf_dump_int_data(struct btf_dump *d, { __u8 encoding = btf_int_encoding(t); bool sign = encoding & BTF_INT_SIGNED; + char buf[16] __attribute__((aligned(16))); int sz = t->size; - if (sz == 0) { + if (sz == 0 || sz > sizeof(buf)) { pr_warn("unexpected size %d for id [%u]\n", sz, type_id); return -EINVAL; } @@ -1679,8 +1709,10 @@ static int btf_dump_int_data(struct btf_dump *d, /* handle packed int data - accesses of integers not aligned on * int boundaries can cause problems on some platforms. */ - if (!ptr_is_aligned(data, sz)) - return btf_dump_bitfield_data(d, t, data, 0, 0); + if (!ptr_is_aligned(d->btf, type_id, data)) { + memcpy(buf, data, sz); + data = buf; + } switch (sz) { case 16: { @@ -1690,10 +1722,10 @@ static int btf_dump_int_data(struct btf_dump *d, /* avoid use of __int128 as some 32-bit platforms do not * support it. */ -#if __BYTE_ORDER == __LITTLE_ENDIAN +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ lsi = ints[0]; msi = ints[1]; -#elif __BYTE_ORDER == __BIG_ENDIAN +#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ lsi = ints[1]; msi = ints[0]; #else @@ -1766,7 +1798,7 @@ static int btf_dump_float_data(struct btf_dump *d, int sz = t->size; /* handle unaligned data; copy to local union */ - if (!ptr_is_aligned(data, sz)) { + if (!ptr_is_aligned(d->btf, type_id, data)) { memcpy(&fl, data, sz); flp = &fl; } @@ -1929,7 +1961,7 @@ static int btf_dump_ptr_data(struct btf_dump *d, __u32 id, const void *data) { - if (ptr_is_aligned(data, d->ptr_sz) && d->ptr_sz == sizeof(void *)) { + if (ptr_is_aligned(d->btf, id, data) && d->ptr_sz == sizeof(void *)) { btf_dump_type_values(d, "%p", *(void **)data); } else { union ptr_data pt; @@ -1949,10 +1981,8 @@ static int btf_dump_get_enum_value(struct btf_dump *d, __u32 id, __s64 *value) { - int sz = t->size; - /* handle unaligned enum value */ - if (!ptr_is_aligned(data, sz)) { + if (!ptr_is_aligned(d->btf, id, data)) { __u64 val; int err; @@ -2215,6 +2245,7 @@ static int btf_dump_dump_type_data(struct btf_dump *d, case BTF_KIND_FWD: case BTF_KIND_FUNC: case BTF_KIND_FUNC_PROTO: + case BTF_KIND_DECL_TAG: err = btf_dump_unsupported_data(d, t, id); break; case BTF_KIND_INT: @@ -2290,8 +2321,8 @@ int btf_dump__dump_type_data(struct btf_dump *d, __u32 id, if (!opts->indent_str) d->typed_dump->indent_str[0] = '\t'; else - strncat(d->typed_dump->indent_str, opts->indent_str, - sizeof(d->typed_dump->indent_str) - 1); + libbpf_strlcpy(d->typed_dump->indent_str, opts->indent_str, + sizeof(d->typed_dump->indent_str)); d->typed_dump->compact = OPTS_GET(opts, compact, false); d->typed_dump->skip_names = OPTS_GET(opts, skip_names, false); diff --git a/tools/lib/bpf/gen_loader.c b/tools/lib/bpf/gen_loader.c index 33c19590ee..8ecef1088b 100644 --- a/tools/lib/bpf/gen_loader.c +++ b/tools/lib/bpf/gen_loader.c @@ -5,6 +5,7 @@ #include #include #include +#include #include "btf.h" #include "bpf.h" #include "libbpf.h" @@ -12,9 +13,12 @@ #include "hashmap.h" #include "bpf_gen_internal.h" #include "skel_internal.h" +#include -#define MAX_USED_MAPS 64 -#define MAX_USED_PROGS 32 +#define MAX_USED_MAPS 64 +#define MAX_USED_PROGS 32 +#define MAX_KFUNC_DESCS 256 +#define MAX_FD_ARRAY_SZ (MAX_USED_MAPS + MAX_KFUNC_DESCS) /* The following structure describes the stack layout of the loader program. * In addition R6 contains the pointer to context. @@ -29,9 +33,8 @@ */ struct loader_stack { __u32 btf_fd; - __u32 map_fd[MAX_USED_MAPS]; - __u32 prog_fd[MAX_USED_PROGS]; __u32 inner_map_fd; + __u32 prog_fd[MAX_USED_PROGS]; }; #define stack_off(field) \ @@ -39,6 +42,11 @@ struct loader_stack { #define attr_field(attr, field) (attr + offsetof(union bpf_attr, field)) +static int blob_fd_array_off(struct bpf_gen *gen, int index) +{ + return gen->fd_array + index * sizeof(int); +} + static int realloc_insn_buf(struct bpf_gen *gen, __u32 size) { size_t off = gen->insn_cur - gen->insn_start; @@ -99,11 +107,15 @@ static void emit2(struct bpf_gen *gen, struct bpf_insn insn1, struct bpf_insn in emit(gen, insn2); } -void bpf_gen__init(struct bpf_gen *gen, int log_level) +static int add_data(struct bpf_gen *gen, const void *data, __u32 size); +static void emit_sys_close_blob(struct bpf_gen *gen, int blob_off); + +void bpf_gen__init(struct bpf_gen *gen, int log_level, int nr_progs, int nr_maps) { - size_t stack_sz = sizeof(struct loader_stack); + size_t stack_sz = sizeof(struct loader_stack), nr_progs_sz; int i; + gen->fd_array = add_data(gen, NULL, MAX_FD_ARRAY_SZ * sizeof(int)); gen->log_level = log_level; /* save ctx pointer into R6 */ emit(gen, BPF_MOV64_REG(BPF_REG_6, BPF_REG_1)); @@ -115,19 +127,27 @@ void bpf_gen__init(struct bpf_gen *gen, int log_level) emit(gen, BPF_MOV64_IMM(BPF_REG_3, 0)); emit(gen, BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel)); + /* amount of stack actually used, only used to calculate iterations, not stack offset */ + nr_progs_sz = offsetof(struct loader_stack, prog_fd[nr_progs]); /* jump over cleanup code */ emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, - /* size of cleanup code below */ - (stack_sz / 4) * 3 + 2)); + /* size of cleanup code below (including map fd cleanup) */ + (nr_progs_sz / 4) * 3 + 2 + + /* 6 insns for emit_sys_close_blob, + * 6 insns for debug_regs in emit_sys_close_blob + */ + nr_maps * (6 + (gen->log_level ? 6 : 0)))); /* remember the label where all error branches will jump to */ gen->cleanup_label = gen->insn_cur - gen->insn_start; /* emit cleanup code: close all temp FDs */ - for (i = 0; i < stack_sz; i += 4) { + for (i = 0; i < nr_progs_sz; i += 4) { emit(gen, BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_10, -stack_sz + i)); emit(gen, BPF_JMP_IMM(BPF_JSLE, BPF_REG_1, 0, 1)); emit(gen, BPF_EMIT_CALL(BPF_FUNC_sys_close)); } + for (i = 0; i < nr_maps; i++) + emit_sys_close_blob(gen, blob_fd_array_off(gen, i)); /* R7 contains the error code from sys_bpf. Copy it into R0 and exit. */ emit(gen, BPF_MOV64_REG(BPF_REG_0, BPF_REG_7)); emit(gen, BPF_EXIT_INSN()); @@ -135,16 +155,47 @@ void bpf_gen__init(struct bpf_gen *gen, int log_level) static int add_data(struct bpf_gen *gen, const void *data, __u32 size) { + __u32 size8 = roundup(size, 8); + __u64 zero = 0; void *prev; - if (realloc_data_buf(gen, size)) + if (realloc_data_buf(gen, size8)) return 0; prev = gen->data_cur; - memcpy(gen->data_cur, data, size); - gen->data_cur += size; + if (data) { + memcpy(gen->data_cur, data, size); + memcpy(gen->data_cur + size, &zero, size8 - size); + } else { + memset(gen->data_cur, 0, size8); + } + gen->data_cur += size8; return prev - gen->data_start; } +/* Get index for map_fd/btf_fd slot in reserved fd_array, or in data relative + * to start of fd_array. Caller can decide if it is usable or not. + */ +static int add_map_fd(struct bpf_gen *gen) +{ + if (gen->nr_maps == MAX_USED_MAPS) { + pr_warn("Total maps exceeds %d\n", MAX_USED_MAPS); + gen->error = -E2BIG; + return 0; + } + return gen->nr_maps++; +} + +static int add_kfunc_btf_fd(struct bpf_gen *gen) +{ + int cur; + + if (gen->nr_fd_array == MAX_KFUNC_DESCS) { + cur = add_data(gen, NULL, sizeof(int)); + return (cur - gen->fd_array) / sizeof(int); + } + return MAX_USED_MAPS + gen->nr_fd_array++; +} + static int insn_bytes_to_bpf_size(__u32 sz) { switch (sz) { @@ -166,14 +217,22 @@ static void emit_rel_store(struct bpf_gen *gen, int off, int data) emit(gen, BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0)); } -/* *(u64 *)(blob + off) = (u64)(void *)(%sp + stack_off) */ -static void emit_rel_store_sp(struct bpf_gen *gen, int off, int stack_off) +static void move_blob2blob(struct bpf_gen *gen, int off, int size, int blob_off) { - emit(gen, BPF_MOV64_REG(BPF_REG_0, BPF_REG_10)); - emit(gen, BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, stack_off)); + emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_2, BPF_PSEUDO_MAP_IDX_VALUE, + 0, 0, 0, blob_off)); + emit(gen, BPF_LDX_MEM(insn_bytes_to_bpf_size(size), BPF_REG_0, BPF_REG_2, 0)); emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE, 0, 0, 0, off)); - emit(gen, BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0)); + emit(gen, BPF_STX_MEM(insn_bytes_to_bpf_size(size), BPF_REG_1, BPF_REG_0, 0)); +} + +static void move_blob2ctx(struct bpf_gen *gen, int ctx_off, int size, int blob_off) +{ + emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE, + 0, 0, 0, blob_off)); + emit(gen, BPF_LDX_MEM(insn_bytes_to_bpf_size(size), BPF_REG_0, BPF_REG_1, 0)); + emit(gen, BPF_STX_MEM(insn_bytes_to_bpf_size(size), BPF_REG_6, BPF_REG_0, ctx_off)); } static void move_ctx2blob(struct bpf_gen *gen, int off, int size, int ctx_off, @@ -308,10 +367,16 @@ static void emit_sys_close_blob(struct bpf_gen *gen, int blob_off) __emit_sys_close(gen); } -int bpf_gen__finish(struct bpf_gen *gen) +int bpf_gen__finish(struct bpf_gen *gen, int nr_progs, int nr_maps) { int i; + if (nr_progs < gen->nr_progs || nr_maps != gen->nr_maps) { + pr_warn("nr_progs %d/%d nr_maps %d/%d mismatch\n", + nr_progs, gen->nr_progs, nr_maps, gen->nr_maps); + gen->error = -EFAULT; + return gen->error; + } emit_sys_close_stack(gen, stack_off(btf_fd)); for (i = 0; i < gen->nr_progs; i++) move_stack2ctx(gen, @@ -321,11 +386,11 @@ int bpf_gen__finish(struct bpf_gen *gen) offsetof(struct bpf_prog_desc, prog_fd), 4, stack_off(prog_fd[i])); for (i = 0; i < gen->nr_maps; i++) - move_stack2ctx(gen, - sizeof(struct bpf_loader_ctx) + - sizeof(struct bpf_map_desc) * i + - offsetof(struct bpf_map_desc, map_fd), 4, - stack_off(map_fd[i])); + move_blob2ctx(gen, + sizeof(struct bpf_loader_ctx) + + sizeof(struct bpf_map_desc) * i + + offsetof(struct bpf_map_desc, map_fd), 4, + blob_fd_array_off(gen, i)); emit(gen, BPF_MOV64_IMM(BPF_REG_0, 0)); emit(gen, BPF_EXIT_INSN()); pr_debug("gen: finish %d\n", gen->error); @@ -381,46 +446,32 @@ void bpf_gen__load_btf(struct bpf_gen *gen, const void *btf_raw_data, } void bpf_gen__map_create(struct bpf_gen *gen, - struct bpf_create_map_attr *map_attr, int map_idx) + enum bpf_map_type map_type, + const char *map_name, + __u32 key_size, __u32 value_size, __u32 max_entries, + struct bpf_map_create_opts *map_attr, int map_idx) { - int attr_size = offsetofend(union bpf_attr, btf_vmlinux_value_type_id); + int attr_size = offsetofend(union bpf_attr, map_extra); bool close_inner_map_fd = false; - int map_create_attr; + int map_create_attr, idx; union bpf_attr attr; memset(&attr, 0, attr_size); - attr.map_type = map_attr->map_type; - attr.key_size = map_attr->key_size; - attr.value_size = map_attr->value_size; + attr.map_type = map_type; + attr.key_size = key_size; + attr.value_size = value_size; attr.map_flags = map_attr->map_flags; - memcpy(attr.map_name, map_attr->name, - min((unsigned)strlen(map_attr->name), BPF_OBJ_NAME_LEN - 1)); + attr.map_extra = map_attr->map_extra; + if (map_name) + libbpf_strlcpy(attr.map_name, map_name, sizeof(attr.map_name)); attr.numa_node = map_attr->numa_node; attr.map_ifindex = map_attr->map_ifindex; - attr.max_entries = map_attr->max_entries; - switch (attr.map_type) { - case BPF_MAP_TYPE_PERF_EVENT_ARRAY: - case BPF_MAP_TYPE_CGROUP_ARRAY: - case BPF_MAP_TYPE_STACK_TRACE: - case BPF_MAP_TYPE_ARRAY_OF_MAPS: - case BPF_MAP_TYPE_HASH_OF_MAPS: - case BPF_MAP_TYPE_DEVMAP: - case BPF_MAP_TYPE_DEVMAP_HASH: - case BPF_MAP_TYPE_CPUMAP: - case BPF_MAP_TYPE_XSKMAP: - case BPF_MAP_TYPE_SOCKMAP: - case BPF_MAP_TYPE_SOCKHASH: - case BPF_MAP_TYPE_QUEUE: - case BPF_MAP_TYPE_STACK: - case BPF_MAP_TYPE_RINGBUF: - break; - default: - attr.btf_key_type_id = map_attr->btf_key_type_id; - attr.btf_value_type_id = map_attr->btf_value_type_id; - } + attr.max_entries = max_entries; + attr.btf_key_type_id = map_attr->btf_key_type_id; + attr.btf_value_type_id = map_attr->btf_value_type_id; pr_debug("gen: map_create: %s idx %d type %d value_type_id %d\n", - attr.map_name, map_idx, map_attr->map_type, attr.btf_value_type_id); + attr.map_name, map_idx, map_type, attr.btf_value_type_id); map_create_attr = add_data(gen, &attr, attr_size); if (attr.btf_value_type_id) @@ -447,7 +498,7 @@ void bpf_gen__map_create(struct bpf_gen *gen, /* emit MAP_CREATE command */ emit_sys_bpf(gen, BPF_MAP_CREATE, map_create_attr, attr_size); debug_ret(gen, "map_create %s idx %d type %d value_size %d value_btf_id %d", - attr.map_name, map_idx, map_attr->map_type, attr.value_size, + attr.map_name, map_idx, map_type, value_size, attr.btf_value_type_id); emit_check_err(gen); /* remember map_fd in the stack, if successful */ @@ -462,9 +513,11 @@ void bpf_gen__map_create(struct bpf_gen *gen, gen->error = -EDOM; /* internal bug */ return; } else { - emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_7, - stack_off(map_fd[map_idx]))); - gen->nr_maps++; + /* add_map_fd does gen->nr_maps++ */ + idx = add_map_fd(gen); + emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE, + 0, 0, 0, blob_fd_array_off(gen, idx))); + emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_7, 0)); } if (close_inner_map_fd) emit_sys_close_stack(gen, stack_off(inner_map_fd)); @@ -506,8 +559,8 @@ static void emit_find_attach_target(struct bpf_gen *gen) */ } -void bpf_gen__record_extern(struct bpf_gen *gen, const char *name, int kind, - int insn_idx) +void bpf_gen__record_extern(struct bpf_gen *gen, const char *name, bool is_weak, + bool is_typeless, int kind, int insn_idx) { struct ksym_relo_desc *relo; @@ -519,38 +572,313 @@ void bpf_gen__record_extern(struct bpf_gen *gen, const char *name, int kind, gen->relos = relo; relo += gen->relo_cnt; relo->name = name; + relo->is_weak = is_weak; + relo->is_typeless = is_typeless; relo->kind = kind; relo->insn_idx = insn_idx; gen->relo_cnt++; } -static void emit_relo(struct bpf_gen *gen, struct ksym_relo_desc *relo, int insns) +/* returns existing ksym_desc with ref incremented, or inserts a new one */ +static struct ksym_desc *get_ksym_desc(struct bpf_gen *gen, struct ksym_relo_desc *relo) { - int name, insn, len = strlen(relo->name) + 1; + struct ksym_desc *kdesc; + int i; - pr_debug("gen: emit_relo: %s at %d\n", relo->name, relo->insn_idx); - name = add_data(gen, relo->name, len); + for (i = 0; i < gen->nr_ksyms; i++) { + if (!strcmp(gen->ksyms[i].name, relo->name)) { + gen->ksyms[i].ref++; + return &gen->ksyms[i]; + } + } + kdesc = libbpf_reallocarray(gen->ksyms, gen->nr_ksyms + 1, sizeof(*kdesc)); + if (!kdesc) { + gen->error = -ENOMEM; + return NULL; + } + gen->ksyms = kdesc; + kdesc = &gen->ksyms[gen->nr_ksyms++]; + kdesc->name = relo->name; + kdesc->kind = relo->kind; + kdesc->ref = 1; + kdesc->off = 0; + kdesc->insn = 0; + return kdesc; +} +/* Overwrites BPF_REG_{0, 1, 2, 3, 4, 7} + * Returns result in BPF_REG_7 + */ +static void emit_bpf_find_by_name_kind(struct bpf_gen *gen, struct ksym_relo_desc *relo) +{ + int name_off, len = strlen(relo->name) + 1; + + name_off = add_data(gen, relo->name, len); emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE, - 0, 0, 0, name)); + 0, 0, 0, name_off)); emit(gen, BPF_MOV64_IMM(BPF_REG_2, len)); emit(gen, BPF_MOV64_IMM(BPF_REG_3, relo->kind)); emit(gen, BPF_MOV64_IMM(BPF_REG_4, 0)); emit(gen, BPF_EMIT_CALL(BPF_FUNC_btf_find_by_name_kind)); emit(gen, BPF_MOV64_REG(BPF_REG_7, BPF_REG_0)); debug_ret(gen, "find_by_name_kind(%s,%d)", relo->name, relo->kind); - emit_check_err(gen); +} + +/* Overwrites BPF_REG_{0, 1, 2, 3, 4, 7} + * Returns result in BPF_REG_7 + * Returns u64 symbol addr in BPF_REG_9 + */ +static void emit_bpf_kallsyms_lookup_name(struct bpf_gen *gen, struct ksym_relo_desc *relo) +{ + int name_off, len = strlen(relo->name) + 1, res_off; + + name_off = add_data(gen, relo->name, len); + res_off = add_data(gen, NULL, 8); /* res is u64 */ + emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE, + 0, 0, 0, name_off)); + emit(gen, BPF_MOV64_IMM(BPF_REG_2, len)); + emit(gen, BPF_MOV64_IMM(BPF_REG_3, 0)); + emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_4, BPF_PSEUDO_MAP_IDX_VALUE, + 0, 0, 0, res_off)); + emit(gen, BPF_MOV64_REG(BPF_REG_7, BPF_REG_4)); + emit(gen, BPF_EMIT_CALL(BPF_FUNC_kallsyms_lookup_name)); + emit(gen, BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 0)); + emit(gen, BPF_MOV64_REG(BPF_REG_7, BPF_REG_0)); + debug_ret(gen, "kallsyms_lookup_name(%s,%d)", relo->name, relo->kind); +} + +/* Expects: + * BPF_REG_8 - pointer to instruction + * + * We need to reuse BTF fd for same symbol otherwise each relocation takes a new + * index, while kernel limits total kfunc BTFs to 256. For duplicate symbols, + * this would mean a new BTF fd index for each entry. By pairing symbol name + * with index, we get the insn->imm, insn->off pairing that kernel uses for + * kfunc_tab, which becomes the effective limit even though all of them may + * share same index in fd_array (such that kfunc_btf_tab has 1 element). + */ +static void emit_relo_kfunc_btf(struct bpf_gen *gen, struct ksym_relo_desc *relo, int insn) +{ + struct ksym_desc *kdesc; + int btf_fd_idx; + + kdesc = get_ksym_desc(gen, relo); + if (!kdesc) + return; + /* try to copy from existing bpf_insn */ + if (kdesc->ref > 1) { + move_blob2blob(gen, insn + offsetof(struct bpf_insn, imm), 4, + kdesc->insn + offsetof(struct bpf_insn, imm)); + move_blob2blob(gen, insn + offsetof(struct bpf_insn, off), 2, + kdesc->insn + offsetof(struct bpf_insn, off)); + goto log; + } + /* remember insn offset, so we can copy BTF ID and FD later */ + kdesc->insn = insn; + emit_bpf_find_by_name_kind(gen, relo); + if (!relo->is_weak) + emit_check_err(gen); + /* get index in fd_array to store BTF FD at */ + btf_fd_idx = add_kfunc_btf_fd(gen); + if (btf_fd_idx > INT16_MAX) { + pr_warn("BTF fd off %d for kfunc %s exceeds INT16_MAX, cannot process relocation\n", + btf_fd_idx, relo->name); + gen->error = -E2BIG; + return; + } + kdesc->off = btf_fd_idx; + /* jump to success case */ + emit(gen, BPF_JMP_IMM(BPF_JSGE, BPF_REG_7, 0, 3)); + /* set value for imm, off as 0 */ + emit(gen, BPF_ST_MEM(BPF_W, BPF_REG_8, offsetof(struct bpf_insn, imm), 0)); + emit(gen, BPF_ST_MEM(BPF_H, BPF_REG_8, offsetof(struct bpf_insn, off), 0)); + /* skip success case for ret < 0 */ + emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, 10)); /* store btf_id into insn[insn_idx].imm */ - insn = insns + sizeof(struct bpf_insn) * relo->insn_idx + - offsetof(struct bpf_insn, imm); + emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_8, BPF_REG_7, offsetof(struct bpf_insn, imm))); + /* obtain fd in BPF_REG_9 */ + emit(gen, BPF_MOV64_REG(BPF_REG_9, BPF_REG_7)); + emit(gen, BPF_ALU64_IMM(BPF_RSH, BPF_REG_9, 32)); + /* jump to fd_array store if fd denotes module BTF */ + emit(gen, BPF_JMP_IMM(BPF_JNE, BPF_REG_9, 0, 2)); + /* set the default value for off */ + emit(gen, BPF_ST_MEM(BPF_H, BPF_REG_8, offsetof(struct bpf_insn, off), 0)); + /* skip BTF fd store for vmlinux BTF */ + emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, 4)); + /* load fd_array slot pointer */ emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_0, BPF_PSEUDO_MAP_IDX_VALUE, - 0, 0, 0, insn)); - emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_7, 0)); - if (relo->kind == BTF_KIND_VAR) { - /* store btf_obj_fd into insn[insn_idx + 1].imm */ - emit(gen, BPF_ALU64_IMM(BPF_RSH, BPF_REG_7, 32)); - emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_7, - sizeof(struct bpf_insn))); + 0, 0, 0, blob_fd_array_off(gen, btf_fd_idx))); + /* store BTF fd in slot */ + emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_9, 0)); + /* store index into insn[insn_idx].off */ + emit(gen, BPF_ST_MEM(BPF_H, BPF_REG_8, offsetof(struct bpf_insn, off), btf_fd_idx)); +log: + if (!gen->log_level) + return; + emit(gen, BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_8, + offsetof(struct bpf_insn, imm))); + emit(gen, BPF_LDX_MEM(BPF_H, BPF_REG_9, BPF_REG_8, + offsetof(struct bpf_insn, off))); + debug_regs(gen, BPF_REG_7, BPF_REG_9, " func (%s:count=%d): imm: %%d, off: %%d", + relo->name, kdesc->ref); + emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_0, BPF_PSEUDO_MAP_IDX_VALUE, + 0, 0, 0, blob_fd_array_off(gen, kdesc->off))); + emit(gen, BPF_LDX_MEM(BPF_W, BPF_REG_9, BPF_REG_0, 0)); + debug_regs(gen, BPF_REG_9, -1, " func (%s:count=%d): btf_fd", + relo->name, kdesc->ref); +} + +static void emit_ksym_relo_log(struct bpf_gen *gen, struct ksym_relo_desc *relo, + int ref) +{ + if (!gen->log_level) + return; + emit(gen, BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_8, + offsetof(struct bpf_insn, imm))); + emit(gen, BPF_LDX_MEM(BPF_H, BPF_REG_9, BPF_REG_8, sizeof(struct bpf_insn) + + offsetof(struct bpf_insn, imm))); + debug_regs(gen, BPF_REG_7, BPF_REG_9, " var t=%d w=%d (%s:count=%d): imm[0]: %%d, imm[1]: %%d", + relo->is_typeless, relo->is_weak, relo->name, ref); + emit(gen, BPF_LDX_MEM(BPF_B, BPF_REG_9, BPF_REG_8, offsetofend(struct bpf_insn, code))); + debug_regs(gen, BPF_REG_9, -1, " var t=%d w=%d (%s:count=%d): insn.reg", + relo->is_typeless, relo->is_weak, relo->name, ref); +} + +/* Expects: + * BPF_REG_8 - pointer to instruction + */ +static void emit_relo_ksym_typeless(struct bpf_gen *gen, + struct ksym_relo_desc *relo, int insn) +{ + struct ksym_desc *kdesc; + + kdesc = get_ksym_desc(gen, relo); + if (!kdesc) + return; + /* try to copy from existing ldimm64 insn */ + if (kdesc->ref > 1) { + move_blob2blob(gen, insn + offsetof(struct bpf_insn, imm), 4, + kdesc->insn + offsetof(struct bpf_insn, imm)); + move_blob2blob(gen, insn + sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm), 4, + kdesc->insn + sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm)); + goto log; + } + /* remember insn offset, so we can copy ksym addr later */ + kdesc->insn = insn; + /* skip typeless ksym_desc in fd closing loop in cleanup_relos */ + kdesc->typeless = true; + emit_bpf_kallsyms_lookup_name(gen, relo); + emit(gen, BPF_JMP_IMM(BPF_JEQ, BPF_REG_7, -ENOENT, 1)); + emit_check_err(gen); + /* store lower half of addr into insn[insn_idx].imm */ + emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_8, BPF_REG_9, offsetof(struct bpf_insn, imm))); + /* store upper half of addr into insn[insn_idx + 1].imm */ + emit(gen, BPF_ALU64_IMM(BPF_RSH, BPF_REG_9, 32)); + emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_8, BPF_REG_9, + sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm))); +log: + emit_ksym_relo_log(gen, relo, kdesc->ref); +} + +static __u32 src_reg_mask(void) +{ +#if defined(__LITTLE_ENDIAN_BITFIELD) + return 0x0f; /* src_reg,dst_reg,... */ +#elif defined(__BIG_ENDIAN_BITFIELD) + return 0xf0; /* dst_reg,src_reg,... */ +#else +#error "Unsupported bit endianness, cannot proceed" +#endif +} + +/* Expects: + * BPF_REG_8 - pointer to instruction + */ +static void emit_relo_ksym_btf(struct bpf_gen *gen, struct ksym_relo_desc *relo, int insn) +{ + struct ksym_desc *kdesc; + __u32 reg_mask; + + kdesc = get_ksym_desc(gen, relo); + if (!kdesc) + return; + /* try to copy from existing ldimm64 insn */ + if (kdesc->ref > 1) { + move_blob2blob(gen, insn + offsetof(struct bpf_insn, imm), 4, + kdesc->insn + offsetof(struct bpf_insn, imm)); + move_blob2blob(gen, insn + sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm), 4, + kdesc->insn + sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm)); + /* jump over src_reg adjustment if imm is not 0, reuse BPF_REG_0 from move_blob2blob */ + emit(gen, BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 3)); + goto clear_src_reg; + } + /* remember insn offset, so we can copy BTF ID and FD later */ + kdesc->insn = insn; + emit_bpf_find_by_name_kind(gen, relo); + if (!relo->is_weak) + emit_check_err(gen); + /* jump to success case */ + emit(gen, BPF_JMP_IMM(BPF_JSGE, BPF_REG_7, 0, 3)); + /* set values for insn[insn_idx].imm, insn[insn_idx + 1].imm as 0 */ + emit(gen, BPF_ST_MEM(BPF_W, BPF_REG_8, offsetof(struct bpf_insn, imm), 0)); + emit(gen, BPF_ST_MEM(BPF_W, BPF_REG_8, sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm), 0)); + /* skip success case for ret < 0 */ + emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, 4)); + /* store btf_id into insn[insn_idx].imm */ + emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_8, BPF_REG_7, offsetof(struct bpf_insn, imm))); + /* store btf_obj_fd into insn[insn_idx + 1].imm */ + emit(gen, BPF_ALU64_IMM(BPF_RSH, BPF_REG_7, 32)); + emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_8, BPF_REG_7, + sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm))); + /* skip src_reg adjustment */ + emit(gen, BPF_JMP_IMM(BPF_JSGE, BPF_REG_7, 0, 3)); +clear_src_reg: + /* clear bpf_object__relocate_data's src_reg assignment, otherwise we get a verifier failure */ + reg_mask = src_reg_mask(); + emit(gen, BPF_LDX_MEM(BPF_B, BPF_REG_9, BPF_REG_8, offsetofend(struct bpf_insn, code))); + emit(gen, BPF_ALU32_IMM(BPF_AND, BPF_REG_9, reg_mask)); + emit(gen, BPF_STX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, offsetofend(struct bpf_insn, code))); + + emit_ksym_relo_log(gen, relo, kdesc->ref); +} + +void bpf_gen__record_relo_core(struct bpf_gen *gen, + const struct bpf_core_relo *core_relo) +{ + struct bpf_core_relo *relos; + + relos = libbpf_reallocarray(gen->core_relos, gen->core_relo_cnt + 1, sizeof(*relos)); + if (!relos) { + gen->error = -ENOMEM; + return; + } + gen->core_relos = relos; + relos += gen->core_relo_cnt; + memcpy(relos, core_relo, sizeof(*relos)); + gen->core_relo_cnt++; +} + +static void emit_relo(struct bpf_gen *gen, struct ksym_relo_desc *relo, int insns) +{ + int insn; + + pr_debug("gen: emit_relo (%d): %s at %d\n", relo->kind, relo->name, relo->insn_idx); + insn = insns + sizeof(struct bpf_insn) * relo->insn_idx; + emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_8, BPF_PSEUDO_MAP_IDX_VALUE, 0, 0, 0, insn)); + switch (relo->kind) { + case BTF_KIND_VAR: + if (relo->is_typeless) + emit_relo_ksym_typeless(gen, relo, insn); + else + emit_relo_ksym_btf(gen, relo, insn); + break; + case BTF_KIND_FUNC: + emit_relo_kfunc_btf(gen, relo, insn); + break; + default: + pr_warn("Unknown relocation kind '%d'\n", relo->kind); + gen->error = -EDOM; + return; } } @@ -562,48 +890,68 @@ static void emit_relos(struct bpf_gen *gen, int insns) emit_relo(gen, gen->relos + i, insns); } +static void cleanup_core_relo(struct bpf_gen *gen) +{ + if (!gen->core_relo_cnt) + return; + free(gen->core_relos); + gen->core_relo_cnt = 0; + gen->core_relos = NULL; +} + static void cleanup_relos(struct bpf_gen *gen, int insns) { int i, insn; - for (i = 0; i < gen->relo_cnt; i++) { - if (gen->relos[i].kind != BTF_KIND_VAR) - continue; - /* close fd recorded in insn[insn_idx + 1].imm */ - insn = insns + - sizeof(struct bpf_insn) * (gen->relos[i].insn_idx + 1) + - offsetof(struct bpf_insn, imm); - emit_sys_close_blob(gen, insn); + for (i = 0; i < gen->nr_ksyms; i++) { + /* only close fds for typed ksyms and kfuncs */ + if (gen->ksyms[i].kind == BTF_KIND_VAR && !gen->ksyms[i].typeless) { + /* close fd recorded in insn[insn_idx + 1].imm */ + insn = gen->ksyms[i].insn; + insn += sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm); + emit_sys_close_blob(gen, insn); + } else if (gen->ksyms[i].kind == BTF_KIND_FUNC) { + emit_sys_close_blob(gen, blob_fd_array_off(gen, gen->ksyms[i].off)); + if (gen->ksyms[i].off < MAX_FD_ARRAY_SZ) + gen->nr_fd_array--; + } + } + if (gen->nr_ksyms) { + free(gen->ksyms); + gen->nr_ksyms = 0; + gen->ksyms = NULL; } if (gen->relo_cnt) { free(gen->relos); gen->relo_cnt = 0; gen->relos = NULL; } + cleanup_core_relo(gen); } void bpf_gen__prog_load(struct bpf_gen *gen, - struct bpf_prog_load_params *load_attr, int prog_idx) + enum bpf_prog_type prog_type, const char *prog_name, + const char *license, struct bpf_insn *insns, size_t insn_cnt, + struct bpf_prog_load_opts *load_attr, int prog_idx) { - int attr_size = offsetofend(union bpf_attr, fd_array); - int prog_load_attr, license, insns, func_info, line_info; + int prog_load_attr, license_off, insns_off, func_info, line_info, core_relos; + int attr_size = offsetofend(union bpf_attr, core_relo_rec_size); union bpf_attr attr; memset(&attr, 0, attr_size); - pr_debug("gen: prog_load: type %d insns_cnt %zd\n", - load_attr->prog_type, load_attr->insn_cnt); + pr_debug("gen: prog_load: type %d insns_cnt %zd progi_idx %d\n", + prog_type, insn_cnt, prog_idx); /* add license string to blob of bytes */ - license = add_data(gen, load_attr->license, strlen(load_attr->license) + 1); + license_off = add_data(gen, license, strlen(license) + 1); /* add insns to blob of bytes */ - insns = add_data(gen, load_attr->insns, - load_attr->insn_cnt * sizeof(struct bpf_insn)); + insns_off = add_data(gen, insns, insn_cnt * sizeof(struct bpf_insn)); - attr.prog_type = load_attr->prog_type; + attr.prog_type = prog_type; attr.expected_attach_type = load_attr->expected_attach_type; attr.attach_btf_id = load_attr->attach_btf_id; attr.prog_ifindex = load_attr->prog_ifindex; attr.kern_version = 0; - attr.insn_cnt = (__u32)load_attr->insn_cnt; + attr.insn_cnt = (__u32)insn_cnt; attr.prog_flags = load_attr->prog_flags; attr.func_info_rec_size = load_attr->func_info_rec_size; @@ -616,15 +964,19 @@ void bpf_gen__prog_load(struct bpf_gen *gen, line_info = add_data(gen, load_attr->line_info, attr.line_info_cnt * attr.line_info_rec_size); - memcpy(attr.prog_name, load_attr->name, - min((unsigned)strlen(load_attr->name), BPF_OBJ_NAME_LEN - 1)); + attr.core_relo_rec_size = sizeof(struct bpf_core_relo); + attr.core_relo_cnt = gen->core_relo_cnt; + core_relos = add_data(gen, gen->core_relos, + attr.core_relo_cnt * attr.core_relo_rec_size); + + libbpf_strlcpy(attr.prog_name, prog_name, sizeof(attr.prog_name)); prog_load_attr = add_data(gen, &attr, attr_size); /* populate union bpf_attr with a pointer to license */ - emit_rel_store(gen, attr_field(prog_load_attr, license), license); + emit_rel_store(gen, attr_field(prog_load_attr, license), license_off); /* populate union bpf_attr with a pointer to instructions */ - emit_rel_store(gen, attr_field(prog_load_attr, insns), insns); + emit_rel_store(gen, attr_field(prog_load_attr, insns), insns_off); /* populate union bpf_attr with a pointer to func_info */ emit_rel_store(gen, attr_field(prog_load_attr, func_info), func_info); @@ -632,9 +984,11 @@ void bpf_gen__prog_load(struct bpf_gen *gen, /* populate union bpf_attr with a pointer to line_info */ emit_rel_store(gen, attr_field(prog_load_attr, line_info), line_info); - /* populate union bpf_attr fd_array with a pointer to stack where map_fds are saved */ - emit_rel_store_sp(gen, attr_field(prog_load_attr, fd_array), - stack_off(map_fd[0])); + /* populate union bpf_attr with a pointer to core_relos */ + emit_rel_store(gen, attr_field(prog_load_attr, core_relos), core_relos); + + /* populate union bpf_attr fd_array with a pointer to data where map_fds are saved */ + emit_rel_store(gen, attr_field(prog_load_attr, fd_array), gen->fd_array); /* populate union bpf_attr with user provided log details */ move_ctx2blob(gen, attr_field(prog_load_attr, log_level), 4, @@ -657,12 +1011,12 @@ void bpf_gen__prog_load(struct bpf_gen *gen, emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_7, offsetof(union bpf_attr, attach_btf_obj_fd))); } - emit_relos(gen, insns); + emit_relos(gen, insns_off); /* emit PROG_LOAD command */ emit_sys_bpf(gen, BPF_PROG_LOAD, prog_load_attr, attr_size); debug_ret(gen, "prog_load %s insn_cnt %d", attr.prog_name, attr.insn_cnt); /* successful or not, close btf module FDs used in extern ksyms and attach_btf_obj_fd */ - cleanup_relos(gen, insns); + cleanup_relos(gen, insns_off); if (gen->attach_kind) { emit_sys_close_blob(gen, attr_field(prog_load_attr, attach_btf_obj_fd)); @@ -703,8 +1057,8 @@ void bpf_gen__map_update_elem(struct bpf_gen *gen, int map_idx, void *pvalue, emit(gen, BPF_EMIT_CALL(BPF_FUNC_copy_from_user)); map_update_attr = add_data(gen, &attr, attr_size); - move_stack2blob(gen, attr_field(map_update_attr, map_fd), 4, - stack_off(map_fd[map_idx])); + move_blob2blob(gen, attr_field(map_update_attr, map_fd), 4, + blob_fd_array_off(gen, map_idx)); emit_rel_store(gen, attr_field(map_update_attr, key), key); emit_rel_store(gen, attr_field(map_update_attr, value), value); /* emit MAP_UPDATE_ELEM command */ @@ -713,6 +1067,33 @@ void bpf_gen__map_update_elem(struct bpf_gen *gen, int map_idx, void *pvalue, emit_check_err(gen); } +void bpf_gen__populate_outer_map(struct bpf_gen *gen, int outer_map_idx, int slot, + int inner_map_idx) +{ + int attr_size = offsetofend(union bpf_attr, flags); + int map_update_attr, key; + union bpf_attr attr; + + memset(&attr, 0, attr_size); + pr_debug("gen: populate_outer_map: outer %d key %d inner %d\n", + outer_map_idx, slot, inner_map_idx); + + key = add_data(gen, &slot, sizeof(slot)); + + map_update_attr = add_data(gen, &attr, attr_size); + move_blob2blob(gen, attr_field(map_update_attr, map_fd), 4, + blob_fd_array_off(gen, outer_map_idx)); + emit_rel_store(gen, attr_field(map_update_attr, key), key); + emit_rel_store(gen, attr_field(map_update_attr, value), + blob_fd_array_off(gen, inner_map_idx)); + + /* emit MAP_UPDATE_ELEM command */ + emit_sys_bpf(gen, BPF_MAP_UPDATE_ELEM, map_update_attr, attr_size); + debug_ret(gen, "populate_outer_map outer %d key %d inner %d", + outer_map_idx, slot, inner_map_idx); + emit_check_err(gen); +} + void bpf_gen__map_freeze(struct bpf_gen *gen, int map_idx) { int attr_size = offsetofend(union bpf_attr, map_fd); @@ -722,8 +1103,8 @@ void bpf_gen__map_freeze(struct bpf_gen *gen, int map_idx) memset(&attr, 0, attr_size); pr_debug("gen: map_freeze: idx %d\n", map_idx); map_freeze_attr = add_data(gen, &attr, attr_size); - move_stack2blob(gen, attr_field(map_freeze_attr, map_fd), 4, - stack_off(map_fd[map_idx])); + move_blob2blob(gen, attr_field(map_freeze_attr, map_fd), 4, + blob_fd_array_off(gen, map_idx)); /* emit MAP_FREEZE command */ emit_sys_bpf(gen, BPF_MAP_FREEZE, map_freeze_attr, attr_size); debug_ret(gen, "map_freeze"); diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 0ad29203cb..7f10dd501a 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -168,37 +168,24 @@ int libbpf_set_strict_mode(enum libbpf_strict_mode mode) return 0; } -enum kern_feature_id { - /* v4.14: kernel support for program & map names. */ - FEAT_PROG_NAME, - /* v5.2: kernel support for global data sections. */ - FEAT_GLOBAL_DATA, - /* BTF support */ - FEAT_BTF, - /* BTF_KIND_FUNC and BTF_KIND_FUNC_PROTO support */ - FEAT_BTF_FUNC, - /* BTF_KIND_VAR and BTF_KIND_DATASEC support */ - FEAT_BTF_DATASEC, - /* BTF_FUNC_GLOBAL is supported */ - FEAT_BTF_GLOBAL_FUNC, - /* BPF_F_MMAPABLE is supported for arrays */ - FEAT_ARRAY_MMAP, - /* kernel support for expected_attach_type in BPF_PROG_LOAD */ - FEAT_EXP_ATTACH_TYPE, - /* bpf_probe_read_{kernel,user}[_str] helpers */ - FEAT_PROBE_READ_KERN, - /* BPF_PROG_BIND_MAP is supported */ - FEAT_PROG_BIND_MAP, - /* Kernel support for module BTFs */ - FEAT_MODULE_BTF, - /* BTF_KIND_FLOAT support */ - FEAT_BTF_FLOAT, - /* BPF perf link support */ - FEAT_PERF_LINK, - __FEAT_CNT, -}; +__u32 libbpf_major_version(void) +{ + return LIBBPF_MAJOR_VERSION; +} -static bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id); +__u32 libbpf_minor_version(void) +{ + return LIBBPF_MINOR_VERSION; +} + +const char *libbpf_version_string(void) +{ +#define __S(X) #X +#define _S(X) __S(X) + return "v" _S(LIBBPF_MAJOR_VERSION) "." _S(LIBBPF_MINOR_VERSION); +#undef _S +#undef __S +} enum reloc_type { RELO_LD64, @@ -207,29 +194,57 @@ enum reloc_type { RELO_EXTERN_VAR, RELO_EXTERN_FUNC, RELO_SUBPROG_ADDR, + RELO_CORE, }; struct reloc_desc { enum reloc_type type; int insn_idx; - int map_idx; - int sym_off; + union { + const struct bpf_core_relo *core_relo; /* used when type == RELO_CORE */ + struct { + int map_idx; + int sym_off; + }; + }; }; struct bpf_sec_def; -typedef struct bpf_link *(*attach_fn_t)(const struct bpf_sec_def *sec, - struct bpf_program *prog); +typedef int (*init_fn_t)(struct bpf_program *prog, long cookie); +typedef int (*preload_fn_t)(struct bpf_program *prog, struct bpf_prog_load_opts *opts, long cookie); +typedef struct bpf_link *(*attach_fn_t)(const struct bpf_program *prog, long cookie); + +/* stored as sec_def->cookie for all libbpf-supported SEC()s */ +enum sec_def_flags { + SEC_NONE = 0, + /* expected_attach_type is optional, if kernel doesn't support that */ + SEC_EXP_ATTACH_OPT = 1, + /* legacy, only used by libbpf_get_type_names() and + * libbpf_attach_type_by_name(), not used by libbpf itself at all. + * This used to be associated with cgroup (and few other) BPF programs + * that were attachable through BPF_PROG_ATTACH command. Pretty + * meaningless nowadays, though. + */ + SEC_ATTACHABLE = 2, + SEC_ATTACHABLE_OPT = SEC_ATTACHABLE | SEC_EXP_ATTACH_OPT, + /* attachment target is specified through BTF ID in either kernel or + * other BPF program's BTF object */ + SEC_ATTACH_BTF = 4, + /* BPF program type allows sleeping/blocking in kernel */ + SEC_SLEEPABLE = 8, + /* allow non-strict prefix matching */ + SEC_SLOPPY_PFX = 16, +}; struct bpf_sec_def { const char *sec; - size_t len; enum bpf_prog_type prog_type; enum bpf_attach_type expected_attach_type; - bool is_exp_attach_type_optional; - bool is_attachable; - bool is_attach_btf; - bool is_sleepable; + long cookie; + + init_fn_t init_fn; + preload_fn_t preload_fn; attach_fn_t attach_fn; }; @@ -261,7 +276,7 @@ struct bpf_program { size_t sub_insn_off; char *name; - /* sec_name with / replaced by _; makes recursive pinning + /* name with / replaced by _; makes recursive pinning * in bpf_object__pin_programs easier */ char *pin_name; @@ -280,7 +295,11 @@ struct bpf_program { struct reloc_desc *reloc_desc; int nr_reloc; - int log_level; + + /* BPF verifier log settings */ + char *log_buf; + size_t log_size; + __u32 log_level; struct { int nr; @@ -346,15 +365,14 @@ enum libbpf_map_type { LIBBPF_MAP_KCONFIG, }; -static const char * const libbpf_type_to_btf_name[] = { - [LIBBPF_MAP_DATA] = DATA_SEC, - [LIBBPF_MAP_BSS] = BSS_SEC, - [LIBBPF_MAP_RODATA] = RODATA_SEC, - [LIBBPF_MAP_KCONFIG] = KCONFIG_SEC, -}; - struct bpf_map { char *name; + /* real_name is defined for special internal maps (.rodata*, + * .data*, .bss, .kconfig) and preserves their original ELF section + * name. This is important to be be able to find corresponding BTF + * DATASEC information. + */ + char *real_name; int fd; int sec_idx; size_t sec_offset; @@ -377,6 +395,8 @@ struct bpf_map { char *pin_path; bool pinned; bool reused; + bool skipped; + __u64 map_extra; }; enum extern_type { @@ -419,6 +439,11 @@ struct extern_desc { /* local btf_id of the ksym extern's type. */ __u32 type_id; + /* BTF fd index to be patched in for insn->off, this is + * 0 for vmlinux BTF, index in obj->fd_array for module + * BTF + */ + __s16 btf_fd_idx; } ksym; }; }; @@ -430,6 +455,41 @@ struct module_btf { char *name; __u32 id; int fd; + int fd_array_idx; +}; + +enum sec_type { + SEC_UNUSED = 0, + SEC_RELO, + SEC_BSS, + SEC_DATA, + SEC_RODATA, +}; + +struct elf_sec_desc { + enum sec_type sec_type; + Elf64_Shdr *shdr; + Elf_Data *data; +}; + +struct elf_state { + int fd; + const void *obj_buf; + size_t obj_buf_sz; + Elf *elf; + Elf64_Ehdr *ehdr; + Elf_Data *symbols; + Elf_Data *st_ops_data; + size_t shstrndx; /* section index for section name strings */ + size_t strtabidx; + struct elf_sec_desc *secs; + int sec_cnt; + int maps_shndx; + int btf_maps_shndx; + __u32 btf_maps_sec_btf_id; + int text_shndx; + int symbols_shndx; + int st_ops_shndx; }; struct bpf_object { @@ -447,47 +507,17 @@ struct bpf_object { struct extern_desc *externs; int nr_extern; int kconfig_map_idx; - int rodata_map_idx; bool loaded; bool has_subcalls; + bool has_rodata; struct bpf_gen *gen_loader; + /* Information when doing ELF related work. Only valid if efile.elf is not NULL */ + struct elf_state efile; /* - * Information when doing elf related work. Only valid if fd - * is valid. - */ - struct { - int fd; - const void *obj_buf; - size_t obj_buf_sz; - Elf *elf; - GElf_Ehdr ehdr; - Elf_Data *symbols; - Elf_Data *data; - Elf_Data *rodata; - Elf_Data *bss; - Elf_Data *st_ops_data; - size_t shstrndx; /* section index for section name strings */ - size_t strtabidx; - struct { - GElf_Shdr shdr; - Elf_Data *data; - } *reloc_sects; - int nr_reloc_sects; - int maps_shndx; - int btf_maps_shndx; - __u32 btf_maps_sec_btf_id; - int text_shndx; - int symbols_shndx; - int data_shndx; - int rodata_shndx; - int bss_shndx; - int st_ops_shndx; - } efile; - /* - * All loaded bpf_object is linked in a list, which is + * All loaded bpf_object are linked in a list, which is * hidden to caller. bpf_objects__ handlers deal with * all objects. */ @@ -512,20 +542,30 @@ struct bpf_object { size_t btf_module_cnt; size_t btf_module_cap; + /* optional log settings passed to BPF_BTF_LOAD and BPF_PROG_LOAD commands */ + char *log_buf; + size_t log_size; + __u32 log_level; + void *priv; bpf_object_clear_priv_t clear_priv; + int *fd_array; + size_t fd_array_cap; + size_t fd_array_cnt; + char path[]; }; -#define obj_elf_valid(o) ((o)->efile.elf) static const char *elf_sym_str(const struct bpf_object *obj, size_t off); static const char *elf_sec_str(const struct bpf_object *obj, size_t off); static Elf_Scn *elf_sec_by_idx(const struct bpf_object *obj, size_t idx); static Elf_Scn *elf_sec_by_name(const struct bpf_object *obj, const char *name); -static int elf_sec_hdr(const struct bpf_object *obj, Elf_Scn *scn, GElf_Shdr *hdr); +static Elf64_Shdr *elf_sec_hdr(const struct bpf_object *obj, Elf_Scn *scn); static const char *elf_sec_name(const struct bpf_object *obj, Elf_Scn *scn); static Elf_Data *elf_sec_data(const struct bpf_object *obj, Elf_Scn *scn); +static Elf64_Sym *elf_sym_by_idx(const struct bpf_object *obj, size_t idx); +static Elf64_Rel *elf_rel_by_idx(Elf_Data *data, size_t idx); void bpf_program__unload(struct bpf_program *prog) { @@ -580,7 +620,16 @@ static char *__bpf_program__pin_name(struct bpf_program *prog) { char *name, *p; - name = p = strdup(prog->sec_name); + if (libbpf_mode & LIBBPF_STRICT_SEC_NAME) + name = strdup(prog->name); + else + name = strdup(prog->sec_name); + + if (!name) + return NULL; + + p = name; + while ((p = strchr(p, '/'))) *p = '_'; @@ -633,6 +682,9 @@ bpf_object__init_prog(struct bpf_object *obj, struct bpf_program *prog, prog->instances.fds = NULL; prog->instances.nr = -1; + /* inherit object's log_level */ + prog->log_level = obj->log_level; + prog->sec_name = strdup(sec_name); if (!prog->sec_name) goto errout; @@ -667,25 +719,25 @@ bpf_object__add_programs(struct bpf_object *obj, Elf_Data *sec_data, size_t sec_sz = sec_data->d_size, sec_off, prog_sz, nr_syms; int nr_progs, err, i; const char *name; - GElf_Sym sym; + Elf64_Sym *sym; progs = obj->programs; nr_progs = obj->nr_programs; - nr_syms = symbols->d_size / sizeof(GElf_Sym); + nr_syms = symbols->d_size / sizeof(Elf64_Sym); sec_off = 0; for (i = 0; i < nr_syms; i++) { - if (!gelf_getsym(symbols, i, &sym)) + sym = elf_sym_by_idx(obj, i); + + if (sym->st_shndx != sec_idx) continue; - if (sym.st_shndx != sec_idx) - continue; - if (GELF_ST_TYPE(sym.st_info) != STT_FUNC) + if (ELF64_ST_TYPE(sym->st_info) != STT_FUNC) continue; - prog_sz = sym.st_size; - sec_off = sym.st_value; + prog_sz = sym->st_size; + sec_off = sym->st_value; - name = elf_sym_str(obj, sym.st_name); + name = elf_sym_str(obj, sym->st_name); if (!name) { pr_warn("sec '%s': failed to get symbol name for offset %zu\n", sec_name, sec_off); @@ -698,7 +750,7 @@ bpf_object__add_programs(struct bpf_object *obj, Elf_Data *sec_data, return -LIBBPF_ERRNO__FORMAT; } - if (sec_idx != obj->efile.text_shndx && GELF_ST_BIND(sym.st_info) == STB_LOCAL) { + if (sec_idx != obj->efile.text_shndx && ELF64_ST_BIND(sym->st_info) == STB_LOCAL) { pr_warn("sec '%s': program '%s' is static and not supported\n", sec_name, name); return -ENOTSUP; } @@ -731,9 +783,9 @@ bpf_object__add_programs(struct bpf_object *obj, Elf_Data *sec_data, * as static to enable more permissive BPF verification mode * with more outside context available to BPF verifier */ - if (GELF_ST_BIND(sym.st_info) != STB_LOCAL - && (GELF_ST_VISIBILITY(sym.st_other) == STV_HIDDEN - || GELF_ST_VISIBILITY(sym.st_other) == STV_INTERNAL)) + if (ELF64_ST_BIND(sym->st_info) != STB_LOCAL + && (ELF64_ST_VISIBILITY(sym->st_other) == STV_HIDDEN + || ELF64_ST_VISIBILITY(sym->st_other) == STV_INTERNAL)) prog->mark_btf_static = true; nr_progs++; @@ -743,11 +795,36 @@ bpf_object__add_programs(struct bpf_object *obj, Elf_Data *sec_data, return 0; } -static __u32 get_kernel_version(void) +__u32 get_kernel_version(void) { + /* On Ubuntu LINUX_VERSION_CODE doesn't correspond to info.release, + * but Ubuntu provides /proc/version_signature file, as described at + * https://ubuntu.com/kernel, with an example contents below, which we + * can use to get a proper LINUX_VERSION_CODE. + * + * Ubuntu 5.4.0-12.15-generic 5.4.8 + * + * In the above, 5.4.8 is what kernel is actually expecting, while + * uname() call will return 5.4.0 in info.release. + */ + const char *ubuntu_kver_file = "/proc/version_signature"; __u32 major, minor, patch; struct utsname info; + if (access(ubuntu_kver_file, R_OK) == 0) { + FILE *f; + + f = fopen(ubuntu_kver_file, "r"); + if (f) { + if (fscanf(f, "%*s %*s %d.%d.%d\n", &major, &minor, &patch) == 3) { + fclose(f); + return KERNEL_VERSION(major, minor, patch); + } + fclose(f); + } + /* something went wrong, fall back to uname() approach */ + } + uname(&info); if (sscanf(info.release, "%u.%u.%u", &major, &minor, &patch) != 3) return 0; @@ -1101,6 +1178,7 @@ static struct bpf_object *bpf_object__new(const char *path, size_t obj_buf_sz, const char *obj_name) { + bool strict = (libbpf_mode & LIBBPF_STRICT_NO_OBJECT_LIST); struct bpf_object *obj; char *end; @@ -1112,12 +1190,10 @@ static struct bpf_object *bpf_object__new(const char *path, strcpy(obj->path, path); if (obj_name) { - strncpy(obj->name, obj_name, sizeof(obj->name) - 1); - obj->name[sizeof(obj->name) - 1] = 0; + libbpf_strlcpy(obj->name, obj_name, sizeof(obj->name)); } else { /* Using basename() GNU version which doesn't modify arg. */ - strncpy(obj->name, basename((void *)path), - sizeof(obj->name) - 1); + libbpf_strlcpy(obj->name, basename((void *)path), sizeof(obj->name)); end = strchr(obj->name, '.'); if (end) *end = 0; @@ -1134,24 +1210,21 @@ static struct bpf_object *bpf_object__new(const char *path, obj->efile.obj_buf_sz = obj_buf_sz; obj->efile.maps_shndx = -1; obj->efile.btf_maps_shndx = -1; - obj->efile.data_shndx = -1; - obj->efile.rodata_shndx = -1; - obj->efile.bss_shndx = -1; obj->efile.st_ops_shndx = -1; obj->kconfig_map_idx = -1; - obj->rodata_map_idx = -1; obj->kern_version = get_kernel_version(); obj->loaded = false; INIT_LIST_HEAD(&obj->list); - list_add(&obj->list, &bpf_objects_list); + if (!strict) + list_add(&obj->list, &bpf_objects_list); return obj; } static void bpf_object__elf_finish(struct bpf_object *obj) { - if (!obj_elf_valid(obj)) + if (!obj->efile.elf) return; if (obj->efile.elf) { @@ -1159,13 +1232,10 @@ static void bpf_object__elf_finish(struct bpf_object *obj) obj->efile.elf = NULL; } obj->efile.symbols = NULL; - obj->efile.data = NULL; - obj->efile.rodata = NULL; - obj->efile.bss = NULL; obj->efile.st_ops_data = NULL; - zfree(&obj->efile.reloc_sects); - obj->efile.nr_reloc_sects = 0; + zfree(&obj->efile.secs); + obj->efile.sec_cnt = 0; zclose(obj->efile.fd); obj->efile.obj_buf = NULL; obj->efile.obj_buf_sz = 0; @@ -1173,10 +1243,11 @@ static void bpf_object__elf_finish(struct bpf_object *obj) static int bpf_object__elf_init(struct bpf_object *obj) { + Elf64_Ehdr *ehdr; int err = 0; - GElf_Ehdr *ep; + Elf *elf; - if (obj_elf_valid(obj)) { + if (obj->efile.elf) { pr_warn("elf: init internal error\n"); return -LIBBPF_ERRNO__LIBELF; } @@ -1186,10 +1257,9 @@ static int bpf_object__elf_init(struct bpf_object *obj) * obj_buf should have been validated by * bpf_object__open_buffer(). */ - obj->efile.elf = elf_memory((char *)obj->efile.obj_buf, - obj->efile.obj_buf_sz); + elf = elf_memory((char *)obj->efile.obj_buf, obj->efile.obj_buf_sz); } else { - obj->efile.fd = open(obj->path, O_RDONLY); + obj->efile.fd = open(obj->path, O_RDONLY | O_CLOEXEC); if (obj->efile.fd < 0) { char errmsg[STRERR_BUFSIZE], *cp; @@ -1199,23 +1269,37 @@ static int bpf_object__elf_init(struct bpf_object *obj) return err; } - obj->efile.elf = elf_begin(obj->efile.fd, ELF_C_READ_MMAP, NULL); + elf = elf_begin(obj->efile.fd, ELF_C_READ_MMAP, NULL); } - if (!obj->efile.elf) { + if (!elf) { pr_warn("elf: failed to open %s as ELF file: %s\n", obj->path, elf_errmsg(-1)); err = -LIBBPF_ERRNO__LIBELF; goto errout; } - if (!gelf_getehdr(obj->efile.elf, &obj->efile.ehdr)) { + obj->efile.elf = elf; + + if (elf_kind(elf) != ELF_K_ELF) { + err = -LIBBPF_ERRNO__FORMAT; + pr_warn("elf: '%s' is not a proper ELF object\n", obj->path); + goto errout; + } + + if (gelf_getclass(elf) != ELFCLASS64) { + err = -LIBBPF_ERRNO__FORMAT; + pr_warn("elf: '%s' is not a 64-bit ELF object\n", obj->path); + goto errout; + } + + obj->efile.ehdr = ehdr = elf64_getehdr(elf); + if (!obj->efile.ehdr) { pr_warn("elf: failed to get ELF header from %s: %s\n", obj->path, elf_errmsg(-1)); err = -LIBBPF_ERRNO__FORMAT; goto errout; } - ep = &obj->efile.ehdr; - if (elf_getshdrstrndx(obj->efile.elf, &obj->efile.shstrndx)) { + if (elf_getshdrstrndx(elf, &obj->efile.shstrndx)) { pr_warn("elf: failed to get section names section index for %s: %s\n", obj->path, elf_errmsg(-1)); err = -LIBBPF_ERRNO__FORMAT; @@ -1223,7 +1307,7 @@ static int bpf_object__elf_init(struct bpf_object *obj) } /* Elf is corrupted/truncated, avoid calling elf_strptr. */ - if (!elf_rawdata(elf_getscn(obj->efile.elf, obj->efile.shstrndx), NULL)) { + if (!elf_rawdata(elf_getscn(elf, obj->efile.shstrndx), NULL)) { pr_warn("elf: failed to get section names strings from %s: %s\n", obj->path, elf_errmsg(-1)); err = -LIBBPF_ERRNO__FORMAT; @@ -1231,8 +1315,7 @@ static int bpf_object__elf_init(struct bpf_object *obj) } /* Old LLVM set e_machine to EM_NONE */ - if (ep->e_type != ET_REL || - (ep->e_machine && ep->e_machine != EM_BPF)) { + if (ehdr->e_type != ET_REL || (ehdr->e_machine && ehdr->e_machine != EM_BPF)) { pr_warn("elf: %s is not a valid eBPF object file\n", obj->path); err = -LIBBPF_ERRNO__FORMAT; goto errout; @@ -1246,11 +1329,11 @@ static int bpf_object__elf_init(struct bpf_object *obj) static int bpf_object__check_endianness(struct bpf_object *obj) { -#if __BYTE_ORDER == __LITTLE_ENDIAN - if (obj->efile.ehdr.e_ident[EI_DATA] == ELFDATA2LSB) +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ + if (obj->efile.ehdr->e_ident[EI_DATA] == ELFDATA2LSB) return 0; -#elif __BYTE_ORDER == __BIG_ENDIAN - if (obj->efile.ehdr.e_ident[EI_DATA] == ELFDATA2MSB) +#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ + if (obj->efile.ehdr->e_ident[EI_DATA] == ELFDATA2MSB) return 0; #else # error "Unrecognized __BYTE_ORDER__" @@ -1262,7 +1345,10 @@ static int bpf_object__check_endianness(struct bpf_object *obj) static int bpf_object__init_license(struct bpf_object *obj, void *data, size_t size) { - memcpy(obj->license, data, min(size, sizeof(obj->license) - 1)); + /* libbpf_strlcpy() only copies first N - 1 bytes, so size + 1 won't + * go over allowed ELF data section buffer + */ + libbpf_strlcpy(obj->license, data, min(size + 1, sizeof(obj->license))); pr_debug("license of %s is %s\n", obj->path, obj->license); return 0; } @@ -1290,41 +1376,27 @@ static bool bpf_map_type__is_map_in_map(enum bpf_map_type type) return false; } -int bpf_object__section_size(const struct bpf_object *obj, const char *name, - __u32 *size) +static int find_elf_sec_sz(const struct bpf_object *obj, const char *name, __u32 *size) { int ret = -ENOENT; + Elf_Data *data; + Elf_Scn *scn; *size = 0; - if (!name) { + if (!name) return -EINVAL; - } else if (!strcmp(name, DATA_SEC)) { - if (obj->efile.data) - *size = obj->efile.data->d_size; - } else if (!strcmp(name, BSS_SEC)) { - if (obj->efile.bss) - *size = obj->efile.bss->d_size; - } else if (!strcmp(name, RODATA_SEC)) { - if (obj->efile.rodata) - *size = obj->efile.rodata->d_size; - } else if (!strcmp(name, STRUCT_OPS_SEC)) { - if (obj->efile.st_ops_data) - *size = obj->efile.st_ops_data->d_size; - } else { - Elf_Scn *scn = elf_sec_by_name(obj, name); - Elf_Data *data = elf_sec_data(obj, scn); - if (data) { - ret = 0; /* found it */ - *size = data->d_size; - } + scn = elf_sec_by_name(obj, name); + data = elf_sec_data(obj, scn); + if (data) { + ret = 0; /* found it */ + *size = data->d_size; } return *size ? 0 : ret; } -int bpf_object__variable_offset(const struct bpf_object *obj, const char *name, - __u32 *off) +static int find_elf_var_offset(const struct bpf_object *obj, const char *name, __u32 *off) { Elf_Data *symbols = obj->efile.symbols; const char *sname; @@ -1333,23 +1405,20 @@ int bpf_object__variable_offset(const struct bpf_object *obj, const char *name, if (!name || !off) return -EINVAL; - for (si = 0; si < symbols->d_size / sizeof(GElf_Sym); si++) { - GElf_Sym sym; + for (si = 0; si < symbols->d_size / sizeof(Elf64_Sym); si++) { + Elf64_Sym *sym = elf_sym_by_idx(obj, si); - if (!gelf_getsym(symbols, si, &sym)) - continue; - if (GELF_ST_BIND(sym.st_info) != STB_GLOBAL || - GELF_ST_TYPE(sym.st_info) != STT_OBJECT) + if (ELF64_ST_BIND(sym->st_info) != STB_GLOBAL || + ELF64_ST_TYPE(sym->st_info) != STT_OBJECT) continue; - sname = elf_sym_str(obj, sym.st_name); + sname = elf_sym_str(obj, sym->st_name); if (!sname) { - pr_warn("failed to get sym name string for var %s\n", - name); + pr_warn("failed to get sym name string for var %s\n", name); return -EIO; } if (strcmp(name, sname) == 0) { - *off = sym.st_value; + *off = sym->st_value; return 0; } } @@ -1401,17 +1470,55 @@ static size_t bpf_map_mmap_sz(const struct bpf_map *map) return map_sz; } -static char *internal_map_name(struct bpf_object *obj, - enum libbpf_map_type type) +static char *internal_map_name(struct bpf_object *obj, const char *real_name) { char map_name[BPF_OBJ_NAME_LEN], *p; - const char *sfx = libbpf_type_to_btf_name[type]; - int sfx_len = max((size_t)7, strlen(sfx)); - int pfx_len = min((size_t)BPF_OBJ_NAME_LEN - sfx_len - 1, - strlen(obj->name)); + int pfx_len, sfx_len = max((size_t)7, strlen(real_name)); + + /* This is one of the more confusing parts of libbpf for various + * reasons, some of which are historical. The original idea for naming + * internal names was to include as much of BPF object name prefix as + * possible, so that it can be distinguished from similar internal + * maps of a different BPF object. + * As an example, let's say we have bpf_object named 'my_object_name' + * and internal map corresponding to '.rodata' ELF section. The final + * map name advertised to user and to the kernel will be + * 'my_objec.rodata', taking first 8 characters of object name and + * entire 7 characters of '.rodata'. + * Somewhat confusingly, if internal map ELF section name is shorter + * than 7 characters, e.g., '.bss', we still reserve 7 characters + * for the suffix, even though we only have 4 actual characters, and + * resulting map will be called 'my_objec.bss', not even using all 15 + * characters allowed by the kernel. Oh well, at least the truncated + * object name is somewhat consistent in this case. But if the map + * name is '.kconfig', we'll still have entirety of '.kconfig' added + * (8 chars) and thus will be left with only first 7 characters of the + * object name ('my_obje'). Happy guessing, user, that the final map + * name will be "my_obje.kconfig". + * Now, with libbpf starting to support arbitrarily named .rodata.* + * and .data.* data sections, it's possible that ELF section name is + * longer than allowed 15 chars, so we now need to be careful to take + * only up to 15 first characters of ELF name, taking no BPF object + * name characters at all. So '.rodata.abracadabra' will result in + * '.rodata.abracad' kernel and user-visible name. + * We need to keep this convoluted logic intact for .data, .bss and + * .rodata maps, but for new custom .data.custom and .rodata.custom + * maps we use their ELF names as is, not prepending bpf_object name + * in front. We still need to truncate them to 15 characters for the + * kernel. Full name can be recovered for such maps by using DATASEC + * BTF type associated with such map's value type, though. + */ + if (sfx_len >= BPF_OBJ_NAME_LEN) + sfx_len = BPF_OBJ_NAME_LEN - 1; + + /* if there are two or more dots in map name, it's a custom dot map */ + if (strchr(real_name + 1, '.') != NULL) + pfx_len = 0; + else + pfx_len = min((size_t)BPF_OBJ_NAME_LEN - sfx_len - 1, strlen(obj->name)); snprintf(map_name, sizeof(map_name), "%.*s%.*s", pfx_len, obj->name, - sfx_len, libbpf_type_to_btf_name[type]); + sfx_len, real_name); /* sanitise map name to characters allowed by kernel */ for (p = map_name; *p && p < map_name + sizeof(map_name); p++) @@ -1423,7 +1530,7 @@ static char *internal_map_name(struct bpf_object *obj, static int bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type, - int sec_idx, void *data, size_t data_sz) + const char *real_name, int sec_idx, void *data, size_t data_sz) { struct bpf_map_def *def; struct bpf_map *map; @@ -1436,9 +1543,11 @@ bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type, map->libbpf_type = type; map->sec_idx = sec_idx; map->sec_offset = 0; - map->name = internal_map_name(obj, type); - if (!map->name) { - pr_warn("failed to alloc map name\n"); + map->real_name = strdup(real_name); + map->name = internal_map_name(obj, real_name); + if (!map->real_name || !map->name) { + zfree(&map->real_name); + zfree(&map->name); return -ENOMEM; } @@ -1461,6 +1570,7 @@ bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type, map->mmaped = NULL; pr_warn("failed to alloc map '%s' content buffer: %d\n", map->name, err); + zfree(&map->real_name); zfree(&map->name); return err; } @@ -1474,34 +1584,43 @@ bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type, static int bpf_object__init_global_data_maps(struct bpf_object *obj) { - int err; + struct elf_sec_desc *sec_desc; + const char *sec_name; + int err = 0, sec_idx; /* * Populate obj->maps with libbpf internal maps. */ - if (obj->efile.data_shndx >= 0) { - err = bpf_object__init_internal_map(obj, LIBBPF_MAP_DATA, - obj->efile.data_shndx, - obj->efile.data->d_buf, - obj->efile.data->d_size); - if (err) - return err; - } - if (obj->efile.rodata_shndx >= 0) { - err = bpf_object__init_internal_map(obj, LIBBPF_MAP_RODATA, - obj->efile.rodata_shndx, - obj->efile.rodata->d_buf, - obj->efile.rodata->d_size); - if (err) - return err; + for (sec_idx = 1; sec_idx < obj->efile.sec_cnt; sec_idx++) { + sec_desc = &obj->efile.secs[sec_idx]; - obj->rodata_map_idx = obj->nr_maps - 1; - } - if (obj->efile.bss_shndx >= 0) { - err = bpf_object__init_internal_map(obj, LIBBPF_MAP_BSS, - obj->efile.bss_shndx, - NULL, - obj->efile.bss->d_size); + switch (sec_desc->sec_type) { + case SEC_DATA: + sec_name = elf_sec_name(obj, elf_sec_by_idx(obj, sec_idx)); + err = bpf_object__init_internal_map(obj, LIBBPF_MAP_DATA, + sec_name, sec_idx, + sec_desc->data->d_buf, + sec_desc->data->d_size); + break; + case SEC_RODATA: + obj->has_rodata = true; + sec_name = elf_sec_name(obj, elf_sec_by_idx(obj, sec_idx)); + err = bpf_object__init_internal_map(obj, LIBBPF_MAP_RODATA, + sec_name, sec_idx, + sec_desc->data->d_buf, + sec_desc->data->d_size); + break; + case SEC_BSS: + sec_name = elf_sec_name(obj, elf_sec_by_idx(obj, sec_idx)); + err = bpf_object__init_internal_map(obj, LIBBPF_MAP_BSS, + sec_name, sec_idx, + NULL, + sec_desc->data->d_size); + break; + default: + /* skip */ + break; + } if (err) return err; } @@ -1664,7 +1783,7 @@ static int bpf_object__process_kconfig_line(struct bpf_object *obj, void *ext_val; __u64 num; - if (strncmp(buf, "CONFIG_", 7)) + if (!str_has_pfx(buf, "CONFIG_")) return 0; sep = strchr(buf, '='); @@ -1798,7 +1917,7 @@ static int bpf_object__init_kconfig_map(struct bpf_object *obj) map_sz = last_ext->kcfg.data_off + last_ext->kcfg.sz; err = bpf_object__init_internal_map(obj, LIBBPF_MAP_KCONFIG, - obj->efile.symbols_shndx, + ".kconfig", obj->efile.symbols_shndx, NULL, map_sz); if (err) return err; @@ -1836,13 +1955,13 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict) * * TODO: Detect array of map and report error. */ - nr_syms = symbols->d_size / sizeof(GElf_Sym); + nr_syms = symbols->d_size / sizeof(Elf64_Sym); for (i = 0; i < nr_syms; i++) { - GElf_Sym sym; + Elf64_Sym *sym = elf_sym_by_idx(obj, i); - if (!gelf_getsym(symbols, i, &sym)) + if (sym->st_shndx != obj->efile.maps_shndx) continue; - if (sym.st_shndx != obj->efile.maps_shndx) + if (ELF64_ST_TYPE(sym->st_info) == STT_SECTION) continue; nr_maps++; } @@ -1859,39 +1978,38 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict) /* Fill obj->maps using data in "maps" section. */ for (i = 0; i < nr_syms; i++) { - GElf_Sym sym; + Elf64_Sym *sym = elf_sym_by_idx(obj, i); const char *map_name; struct bpf_map_def *def; struct bpf_map *map; - if (!gelf_getsym(symbols, i, &sym)) + if (sym->st_shndx != obj->efile.maps_shndx) continue; - if (sym.st_shndx != obj->efile.maps_shndx) + if (ELF64_ST_TYPE(sym->st_info) == STT_SECTION) continue; map = bpf_object__add_map(obj); if (IS_ERR(map)) return PTR_ERR(map); - map_name = elf_sym_str(obj, sym.st_name); + map_name = elf_sym_str(obj, sym->st_name); if (!map_name) { pr_warn("failed to get map #%d name sym string for obj %s\n", i, obj->path); return -LIBBPF_ERRNO__FORMAT; } - if (GELF_ST_TYPE(sym.st_info) == STT_SECTION - || GELF_ST_BIND(sym.st_info) == STB_LOCAL) { + if (ELF64_ST_BIND(sym->st_info) == STB_LOCAL) { pr_warn("map '%s' (legacy): static maps are not supported\n", map_name); return -ENOTSUP; } map->libbpf_type = LIBBPF_MAP_UNSPEC; - map->sec_idx = sym.st_shndx; - map->sec_offset = sym.st_value; + map->sec_idx = sym->st_shndx; + map->sec_offset = sym->st_value; pr_debug("map '%s' (legacy): at sec_idx %d, offset %zu.\n", map_name, map->sec_idx, map->sec_offset); - if (sym.st_value + map_def_sz > data->d_size) { + if (sym->st_value + map_def_sz > data->d_size) { pr_warn("corrupted maps section in %s: last map \"%s\" too small\n", obj->path, map_name); return -EINVAL; @@ -1899,11 +2017,11 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict) map->name = strdup(map_name); if (!map->name) { - pr_warn("failed to alloc map name\n"); + pr_warn("map '%s': failed to alloc map name\n", map_name); return -ENOMEM; } pr_debug("map %d is \"%s\"\n", i, map->name); - def = (struct bpf_map_def *)(data->d_buf + sym.st_value); + def = (struct bpf_map_def *)(data->d_buf + sym->st_value); /* * If the definition of the map in the object file fits in * bpf_map_def, copy it. Any extra fields in our version @@ -1987,6 +2105,8 @@ static const char *__btf_kind_str(__u16 kind) case BTF_KIND_VAR: return "var"; case BTF_KIND_DATASEC: return "datasec"; case BTF_KIND_FLOAT: return "float"; + case BTF_KIND_DECL_TAG: return "decl_tag"; + case BTF_KIND_TYPE_TAG: return "type_tag"; default: return "unknown"; } } @@ -2166,6 +2286,9 @@ int parse_btf_map_def(const char *map_name, struct btf *btf, map_def->parts |= MAP_DEF_VALUE_SIZE | MAP_DEF_VALUE_TYPE; } else if (strcmp(name, "values") == 0) { + bool is_map_in_map = bpf_map_type__is_map_in_map(map_def->map_type); + bool is_prog_array = map_def->map_type == BPF_MAP_TYPE_PROG_ARRAY; + const char *desc = is_map_in_map ? "map-in-map inner" : "prog-array value"; char inner_map_name[128]; int err; @@ -2179,8 +2302,8 @@ int parse_btf_map_def(const char *map_name, struct btf *btf, map_name, name); return -EINVAL; } - if (!bpf_map_type__is_map_in_map(map_def->map_type)) { - pr_warn("map '%s': should be map-in-map.\n", + if (!is_map_in_map && !is_prog_array) { + pr_warn("map '%s': should be map-in-map or prog-array.\n", map_name); return -ENOTSUP; } @@ -2192,22 +2315,30 @@ int parse_btf_map_def(const char *map_name, struct btf *btf, map_def->value_size = 4; t = btf__type_by_id(btf, m->type); if (!t) { - pr_warn("map '%s': map-in-map inner type [%d] not found.\n", - map_name, m->type); + pr_warn("map '%s': %s type [%d] not found.\n", + map_name, desc, m->type); return -EINVAL; } if (!btf_is_array(t) || btf_array(t)->nelems) { - pr_warn("map '%s': map-in-map inner spec is not a zero-sized array.\n", - map_name); + pr_warn("map '%s': %s spec is not a zero-sized array.\n", + map_name, desc); return -EINVAL; } t = skip_mods_and_typedefs(btf, btf_array(t)->type, NULL); if (!btf_is_ptr(t)) { - pr_warn("map '%s': map-in-map inner def is of unexpected kind %s.\n", - map_name, btf_kind_str(t)); + pr_warn("map '%s': %s def is of unexpected kind %s.\n", + map_name, desc, btf_kind_str(t)); return -EINVAL; } t = skip_mods_and_typedefs(btf, t->type, NULL); + if (is_prog_array) { + if (!btf_is_func_proto(t)) { + pr_warn("map '%s': prog-array value def is of unexpected kind %s.\n", + map_name, btf_kind_str(t)); + return -EINVAL; + } + continue; + } if (!btf_is_struct(t)) { pr_warn("map '%s': map-in-map inner def is of unexpected kind %s.\n", map_name, btf_kind_str(t)); @@ -2236,6 +2367,13 @@ int parse_btf_map_def(const char *map_name, struct btf *btf, } map_def->pinning = val; map_def->parts |= MAP_DEF_PINNING; + } else if (strcmp(name, "map_extra") == 0) { + __u32 map_extra; + + if (!get_map_field_int(map_name, btf, m, &map_extra)) + return -EINVAL; + map_def->map_extra = map_extra; + map_def->parts |= MAP_DEF_MAP_EXTRA; } else { if (strict) { pr_warn("map '%s': unknown field '%s'.\n", map_name, name); @@ -2260,6 +2398,7 @@ static void fill_map_from_def(struct bpf_map *map, const struct btf_map_def *def map->def.value_size = def->value_size; map->def.max_entries = def->max_entries; map->def.map_flags = def->map_flags; + map->map_extra = def->map_extra; map->numa_node = def->numa_node; map->btf_key_type_id = def->key_type_id; @@ -2283,7 +2422,10 @@ static void fill_map_from_def(struct bpf_map *map, const struct btf_map_def *def if (def->parts & MAP_DEF_MAX_ENTRIES) pr_debug("map '%s': found max_entries = %u.\n", map->name, def->max_entries); if (def->parts & MAP_DEF_MAP_FLAGS) - pr_debug("map '%s': found map_flags = %u.\n", map->name, def->map_flags); + pr_debug("map '%s': found map_flags = 0x%x.\n", map->name, def->map_flags); + if (def->parts & MAP_DEF_MAP_EXTRA) + pr_debug("map '%s': found map_extra = 0x%llx.\n", map->name, + (unsigned long long)def->map_extra); if (def->parts & MAP_DEF_PINNING) pr_debug("map '%s': found pinning = %u.\n", map->name, def->pinning); if (def->parts & MAP_DEF_NUMA_NODE) @@ -2420,8 +2562,8 @@ static int bpf_object__init_user_btf_maps(struct bpf_object *obj, bool strict, return -EINVAL; } - nr_types = btf__get_nr_types(obj->btf); - for (i = 1; i <= nr_types; i++) { + nr_types = btf__type_cnt(obj->btf); + for (i = 1; i < nr_types; i++) { t = btf__type_by_id(obj->btf, i); if (!btf_is_datasec(t)) continue; @@ -2472,12 +2614,13 @@ static int bpf_object__init_maps(struct bpf_object *obj, static bool section_have_execinstr(struct bpf_object *obj, int idx) { - GElf_Shdr sh; + Elf64_Shdr *sh; - if (elf_sec_hdr(obj, elf_sec_by_idx(obj, idx), &sh)) + sh = elf_sec_hdr(obj, elf_sec_by_idx(obj, idx)); + if (!sh) return false; - return sh.sh_flags & SHF_EXECINSTR; + return sh->sh_flags & SHF_EXECINSTR; } static bool btf_needs_sanitization(struct bpf_object *obj) @@ -2486,8 +2629,11 @@ static bool btf_needs_sanitization(struct bpf_object *obj) bool has_datasec = kernel_supports(obj, FEAT_BTF_DATASEC); bool has_float = kernel_supports(obj, FEAT_BTF_FLOAT); bool has_func = kernel_supports(obj, FEAT_BTF_FUNC); + bool has_decl_tag = kernel_supports(obj, FEAT_BTF_DECL_TAG); + bool has_type_tag = kernel_supports(obj, FEAT_BTF_TYPE_TAG); - return !has_func || !has_datasec || !has_func_global || !has_float; + return !has_func || !has_datasec || !has_func_global || !has_float || + !has_decl_tag || !has_type_tag; } static void bpf_object__sanitize_btf(struct bpf_object *obj, struct btf *btf) @@ -2496,14 +2642,16 @@ static void bpf_object__sanitize_btf(struct bpf_object *obj, struct btf *btf) bool has_datasec = kernel_supports(obj, FEAT_BTF_DATASEC); bool has_float = kernel_supports(obj, FEAT_BTF_FLOAT); bool has_func = kernel_supports(obj, FEAT_BTF_FUNC); + bool has_decl_tag = kernel_supports(obj, FEAT_BTF_DECL_TAG); + bool has_type_tag = kernel_supports(obj, FEAT_BTF_TYPE_TAG); struct btf_type *t; int i, j, vlen; - for (i = 1; i <= btf__get_nr_types(btf); i++) { + for (i = 1; i < btf__type_cnt(btf); i++) { t = (struct btf_type *)btf__type_by_id(btf, i); - if (!has_datasec && btf_is_var(t)) { - /* replace VAR with INT */ + if ((!has_datasec && btf_is_var(t)) || (!has_decl_tag && btf_is_decl_tag(t))) { + /* replace VAR/DECL_TAG with INT */ t->info = BTF_INFO_ENC(BTF_KIND_INT, 0, 0); /* * using size = 1 is the safest choice, 4 will be too @@ -2554,6 +2702,10 @@ static void bpf_object__sanitize_btf(struct bpf_object *obj, struct btf *btf) */ t->name_off = 0; t->info = BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 0); + } else if (!has_type_tag && btf_is_type_tag(t)) { + /* replace TYPE_TAG with a CONST */ + t->name_off = 0; + t->info = BTF_INFO_ENC(BTF_KIND_CONST, 0, 0); } } } @@ -2610,6 +2762,103 @@ static int bpf_object__init_btf(struct bpf_object *obj, return 0; } +static int compare_vsi_off(const void *_a, const void *_b) +{ + const struct btf_var_secinfo *a = _a; + const struct btf_var_secinfo *b = _b; + + return a->offset - b->offset; +} + +static int btf_fixup_datasec(struct bpf_object *obj, struct btf *btf, + struct btf_type *t) +{ + __u32 size = 0, off = 0, i, vars = btf_vlen(t); + const char *name = btf__name_by_offset(btf, t->name_off); + const struct btf_type *t_var; + struct btf_var_secinfo *vsi; + const struct btf_var *var; + int ret; + + if (!name) { + pr_debug("No name found in string section for DATASEC kind.\n"); + return -ENOENT; + } + + /* .extern datasec size and var offsets were set correctly during + * extern collection step, so just skip straight to sorting variables + */ + if (t->size) + goto sort_vars; + + ret = find_elf_sec_sz(obj, name, &size); + if (ret || !size || (t->size && t->size != size)) { + pr_debug("Invalid size for section %s: %u bytes\n", name, size); + return -ENOENT; + } + + t->size = size; + + for (i = 0, vsi = btf_var_secinfos(t); i < vars; i++, vsi++) { + t_var = btf__type_by_id(btf, vsi->type); + if (!t_var || !btf_is_var(t_var)) { + pr_debug("Non-VAR type seen in section %s\n", name); + return -EINVAL; + } + + var = btf_var(t_var); + if (var->linkage == BTF_VAR_STATIC) + continue; + + name = btf__name_by_offset(btf, t_var->name_off); + if (!name) { + pr_debug("No name found in string section for VAR kind\n"); + return -ENOENT; + } + + ret = find_elf_var_offset(obj, name, &off); + if (ret) { + pr_debug("No offset found in symbol table for VAR %s\n", + name); + return -ENOENT; + } + + vsi->offset = off; + } + +sort_vars: + qsort(btf_var_secinfos(t), vars, sizeof(*vsi), compare_vsi_off); + return 0; +} + +static int btf_finalize_data(struct bpf_object *obj, struct btf *btf) +{ + int err = 0; + __u32 i, n = btf__type_cnt(btf); + + for (i = 1; i < n; i++) { + struct btf_type *t = btf_type_by_id(btf, i); + + /* Loader needs to fix up some of the things compiler + * couldn't get its hands on while emitting BTF. This + * is section size and global variable offset. We use + * the info from the ELF itself for this purpose. + */ + if (btf_is_datasec(t)) { + err = btf_fixup_datasec(obj, btf, t); + if (err) + break; + } + } + + return libbpf_err(err); +} + +int btf__finalize_data(struct bpf_object *obj, struct btf *btf) +{ + return btf_finalize_data(obj, btf); +} + static int bpf_object__finalize_btf(struct bpf_object *obj) { int err; @@ -2617,7 +2866,7 @@ static int bpf_object__finalize_btf(struct bpf_object *obj) if (!obj->btf) return 0; - err = btf__finalize_data(obj, obj->btf); + err = btf_finalize_data(obj, obj->btf); if (err) { pr_warn("Error finalizing %s: %d.\n", BTF_ELF_SEC, err); return err; @@ -2727,8 +2976,8 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj) if (!prog->mark_btf_static || !prog_is_subprog(obj, prog)) continue; - n = btf__get_nr_types(obj->btf); - for (j = 1; j <= n; j++) { + n = btf__type_cnt(obj->btf); + for (j = 1; j < n; j++) { t = btf_type_by_id(obj->btf, j); if (!btf_is_func(t) || btf_func_linkage(t) != BTF_FUNC_GLOBAL) continue; @@ -2748,7 +2997,7 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj) __u32 sz; /* clone BTF to sanitize a copy and leave the original intact */ - raw_data = btf__get_raw_data(obj->btf, &sz); + raw_data = btf__raw_data(obj->btf, &sz); kern_btf = btf__new(raw_data, sz); err = libbpf_get_error(kern_btf); if (err) @@ -2761,7 +3010,7 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj) if (obj->gen_loader) { __u32 raw_size = 0; - const void *raw_data = btf__get_raw_data(kern_btf, &raw_size); + const void *raw_data = btf__raw_data(kern_btf, &raw_size); if (!raw_data) return -ENOMEM; @@ -2771,7 +3020,9 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj) */ btf__set_fd(kern_btf, 0); } else { - err = btf__load_into_kernel(kern_btf); + /* currently BPF_BTF_LOAD only supports log_level 1 */ + err = btf_load_into_kernel(kern_btf, obj->log_buf, obj->log_size, + obj->log_level ? 1 : 0); } if (sanitize) { if (!err) { @@ -2853,32 +3104,36 @@ static Elf_Scn *elf_sec_by_name(const struct bpf_object *obj, const char *name) return NULL; } -static int elf_sec_hdr(const struct bpf_object *obj, Elf_Scn *scn, GElf_Shdr *hdr) +static Elf64_Shdr *elf_sec_hdr(const struct bpf_object *obj, Elf_Scn *scn) { - if (!scn) - return -EINVAL; + Elf64_Shdr *shdr; - if (gelf_getshdr(scn, hdr) != hdr) { + if (!scn) + return NULL; + + shdr = elf64_getshdr(scn); + if (!shdr) { pr_warn("elf: failed to get section(%zu) header from %s: %s\n", elf_ndxscn(scn), obj->path, elf_errmsg(-1)); - return -EINVAL; + return NULL; } - return 0; + return shdr; } static const char *elf_sec_name(const struct bpf_object *obj, Elf_Scn *scn) { const char *name; - GElf_Shdr sh; + Elf64_Shdr *sh; if (!scn) return NULL; - if (elf_sec_hdr(obj, scn, &sh)) + sh = elf_sec_hdr(obj, scn); + if (!sh) return NULL; - name = elf_sec_str(obj, sh.sh_name); + name = elf_sec_str(obj, sh->sh_name); if (!name) { pr_warn("elf: failed to get section(%zu) name from %s: %s\n", elf_ndxscn(scn), obj->path, elf_errmsg(-1)); @@ -2906,13 +3161,29 @@ static Elf_Data *elf_sec_data(const struct bpf_object *obj, Elf_Scn *scn) return data; } +static Elf64_Sym *elf_sym_by_idx(const struct bpf_object *obj, size_t idx) +{ + if (idx >= obj->efile.symbols->d_size / sizeof(Elf64_Sym)) + return NULL; + + return (Elf64_Sym *)obj->efile.symbols->d_buf + idx; +} + +static Elf64_Rel *elf_rel_by_idx(Elf_Data *data, size_t idx) +{ + if (idx >= data->d_size / sizeof(Elf64_Rel)) + return NULL; + + return (Elf64_Rel *)data->d_buf + idx; +} + static bool is_sec_name_dwarf(const char *name) { /* approximation, but the actual list is too long */ - return strncmp(name, ".debug_", sizeof(".debug_") - 1) == 0; + return str_has_pfx(name, ".debug_"); } -static bool ignore_elf_section(GElf_Shdr *hdr, const char *name) +static bool ignore_elf_section(Elf64_Shdr *hdr, const char *name) { /* no special handling of .strtab */ if (hdr->sh_type == SHT_STRTAB) @@ -2931,7 +3202,7 @@ static bool ignore_elf_section(GElf_Shdr *hdr, const char *name) if (is_sec_name_dwarf(name)) return true; - if (strncmp(name, ".rel", sizeof(".rel") - 1) == 0) { + if (str_has_pfx(name, ".rel")) { name += sizeof(".rel") - 1; /* DWARF section relocations */ if (is_sec_name_dwarf(name)) @@ -2960,6 +3231,7 @@ static int cmp_progs(const void *_a, const void *_b) static int bpf_object__elf_collect(struct bpf_object *obj) { + struct elf_sec_desc *sec_desc; Elf *elf = obj->efile.elf; Elf_Data *btf_ext_data = NULL; Elf_Data *btf_data = NULL; @@ -2967,17 +3239,27 @@ static int bpf_object__elf_collect(struct bpf_object *obj) const char *name; Elf_Data *data; Elf_Scn *scn; - GElf_Shdr sh; + Elf64_Shdr *sh; + + /* ELF section indices are 0-based, but sec #0 is special "invalid" + * section. e_shnum does include sec #0, so e_shnum is the necessary + * size of an array to keep all the sections. + */ + obj->efile.sec_cnt = obj->efile.ehdr->e_shnum; + obj->efile.secs = calloc(obj->efile.sec_cnt, sizeof(*obj->efile.secs)); + if (!obj->efile.secs) + return -ENOMEM; /* a bunch of ELF parsing functionality depends on processing symbols, * so do the first pass and find the symbol table */ scn = NULL; while ((scn = elf_nextscn(elf, scn)) != NULL) { - if (elf_sec_hdr(obj, scn, &sh)) + sh = elf_sec_hdr(obj, scn); + if (!sh) return -LIBBPF_ERRNO__FORMAT; - if (sh.sh_type == SHT_SYMTAB) { + if (sh->sh_type == SHT_SYMTAB) { if (obj->efile.symbols) { pr_warn("elf: multiple symbol tables in %s\n", obj->path); return -LIBBPF_ERRNO__FORMAT; @@ -2987,9 +3269,11 @@ static int bpf_object__elf_collect(struct bpf_object *obj) if (!data) return -LIBBPF_ERRNO__FORMAT; + idx = elf_ndxscn(scn); + obj->efile.symbols = data; - obj->efile.symbols_shndx = elf_ndxscn(scn); - obj->efile.strtabidx = sh.sh_link; + obj->efile.symbols_shndx = idx; + obj->efile.strtabidx = sh->sh_link; } } @@ -3001,16 +3285,18 @@ static int bpf_object__elf_collect(struct bpf_object *obj) scn = NULL; while ((scn = elf_nextscn(elf, scn)) != NULL) { - idx++; + idx = elf_ndxscn(scn); + sec_desc = &obj->efile.secs[idx]; - if (elf_sec_hdr(obj, scn, &sh)) + sh = elf_sec_hdr(obj, scn); + if (!sh) return -LIBBPF_ERRNO__FORMAT; - name = elf_sec_str(obj, sh.sh_name); + name = elf_sec_str(obj, sh->sh_name); if (!name) return -LIBBPF_ERRNO__FORMAT; - if (ignore_elf_section(&sh, name)) + if (ignore_elf_section(sh, name)) continue; data = elf_sec_data(obj, scn); @@ -3019,8 +3305,8 @@ static int bpf_object__elf_collect(struct bpf_object *obj) pr_debug("elf: section(%d) %s, size %ld, link %d, flags %lx, type=%d\n", idx, name, (unsigned long)data->d_size, - (int)sh.sh_link, (unsigned long)sh.sh_flags, - (int)sh.sh_type); + (int)sh->sh_link, (unsigned long)sh->sh_flags, + (int)sh->sh_type); if (strcmp(name, "license") == 0) { err = bpf_object__init_license(obj, data->d_buf, data->d_size); @@ -3035,24 +3321,32 @@ static int bpf_object__elf_collect(struct bpf_object *obj) } else if (strcmp(name, MAPS_ELF_SEC) == 0) { obj->efile.btf_maps_shndx = idx; } else if (strcmp(name, BTF_ELF_SEC) == 0) { + if (sh->sh_type != SHT_PROGBITS) + return -LIBBPF_ERRNO__FORMAT; btf_data = data; } else if (strcmp(name, BTF_EXT_ELF_SEC) == 0) { + if (sh->sh_type != SHT_PROGBITS) + return -LIBBPF_ERRNO__FORMAT; btf_ext_data = data; - } else if (sh.sh_type == SHT_SYMTAB) { + } else if (sh->sh_type == SHT_SYMTAB) { /* already processed during the first pass above */ - } else if (sh.sh_type == SHT_PROGBITS && data->d_size > 0) { - if (sh.sh_flags & SHF_EXECINSTR) { + } else if (sh->sh_type == SHT_PROGBITS && data->d_size > 0) { + if (sh->sh_flags & SHF_EXECINSTR) { if (strcmp(name, ".text") == 0) obj->efile.text_shndx = idx; err = bpf_object__add_programs(obj, data, name, idx); if (err) return err; - } else if (strcmp(name, DATA_SEC) == 0) { - obj->efile.data = data; - obj->efile.data_shndx = idx; - } else if (strcmp(name, RODATA_SEC) == 0) { - obj->efile.rodata = data; - obj->efile.rodata_shndx = idx; + } else if (strcmp(name, DATA_SEC) == 0 || + str_has_pfx(name, DATA_SEC ".")) { + sec_desc->sec_type = SEC_DATA; + sec_desc->shdr = sh; + sec_desc->data = data; + } else if (strcmp(name, RODATA_SEC) == 0 || + str_has_pfx(name, RODATA_SEC ".")) { + sec_desc->sec_type = SEC_RODATA; + sec_desc->shdr = sh; + sec_desc->data = data; } else if (strcmp(name, STRUCT_OPS_SEC) == 0) { obj->efile.st_ops_data = data; obj->efile.st_ops_shndx = idx; @@ -3060,37 +3354,33 @@ static int bpf_object__elf_collect(struct bpf_object *obj) pr_info("elf: skipping unrecognized data section(%d) %s\n", idx, name); } - } else if (sh.sh_type == SHT_REL) { - int nr_sects = obj->efile.nr_reloc_sects; - void *sects = obj->efile.reloc_sects; - int sec = sh.sh_info; /* points to other section */ + } else if (sh->sh_type == SHT_REL) { + int targ_sec_idx = sh->sh_info; /* points to other section */ + + if (sh->sh_entsize != sizeof(Elf64_Rel) || + targ_sec_idx >= obj->efile.sec_cnt) + return -LIBBPF_ERRNO__FORMAT; /* Only do relo for section with exec instructions */ - if (!section_have_execinstr(obj, sec) && + if (!section_have_execinstr(obj, targ_sec_idx) && strcmp(name, ".rel" STRUCT_OPS_SEC) && strcmp(name, ".rel" MAPS_ELF_SEC)) { pr_info("elf: skipping relo section(%d) %s for section(%d) %s\n", - idx, name, sec, - elf_sec_name(obj, elf_sec_by_idx(obj, sec)) ?: ""); + idx, name, targ_sec_idx, + elf_sec_name(obj, elf_sec_by_idx(obj, targ_sec_idx)) ?: ""); continue; } - sects = libbpf_reallocarray(sects, nr_sects + 1, - sizeof(*obj->efile.reloc_sects)); - if (!sects) - return -ENOMEM; - - obj->efile.reloc_sects = sects; - obj->efile.nr_reloc_sects++; - - obj->efile.reloc_sects[nr_sects].shdr = sh; - obj->efile.reloc_sects[nr_sects].data = data; - } else if (sh.sh_type == SHT_NOBITS && strcmp(name, BSS_SEC) == 0) { - obj->efile.bss = data; - obj->efile.bss_shndx = idx; + sec_desc->sec_type = SEC_RELO; + sec_desc->shdr = sh; + sec_desc->data = data; + } else if (sh->sh_type == SHT_NOBITS && strcmp(name, BSS_SEC) == 0) { + sec_desc->sec_type = SEC_BSS; + sec_desc->shdr = sh; + sec_desc->data = data; } else { pr_info("elf: skipping section(%d) %s (size %zu)\n", idx, name, - (size_t)sh.sh_size); + (size_t)sh->sh_size); } } @@ -3101,24 +3391,25 @@ static int bpf_object__elf_collect(struct bpf_object *obj) /* sort BPF programs by section name and in-section instruction offset * for faster search */ - qsort(obj->programs, obj->nr_programs, sizeof(*obj->programs), cmp_progs); + if (obj->nr_programs) + qsort(obj->programs, obj->nr_programs, sizeof(*obj->programs), cmp_progs); return bpf_object__init_btf(obj, btf_data, btf_ext_data); } -static bool sym_is_extern(const GElf_Sym *sym) +static bool sym_is_extern(const Elf64_Sym *sym) { - int bind = GELF_ST_BIND(sym->st_info); + int bind = ELF64_ST_BIND(sym->st_info); /* externs are symbols w/ type=NOTYPE, bind=GLOBAL|WEAK, section=UND */ return sym->st_shndx == SHN_UNDEF && (bind == STB_GLOBAL || bind == STB_WEAK) && - GELF_ST_TYPE(sym->st_info) == STT_NOTYPE; + ELF64_ST_TYPE(sym->st_info) == STT_NOTYPE; } -static bool sym_is_subprog(const GElf_Sym *sym, int text_shndx) +static bool sym_is_subprog(const Elf64_Sym *sym, int text_shndx) { - int bind = GELF_ST_BIND(sym->st_info); - int type = GELF_ST_TYPE(sym->st_info); + int bind = ELF64_ST_BIND(sym->st_info); + int type = ELF64_ST_TYPE(sym->st_info); /* in .text section */ if (sym->st_shndx != text_shndx) @@ -3141,8 +3432,8 @@ static int find_extern_btf_id(const struct btf *btf, const char *ext_name) if (!btf) return -ESRCH; - n = btf__get_nr_types(btf); - for (i = 1; i <= n; i++) { + n = btf__type_cnt(btf); + for (i = 1; i < n; i++) { t = btf__type_by_id(btf, i); if (!btf_is_var(t) && !btf_is_func(t)) @@ -3173,8 +3464,8 @@ static int find_extern_sec_btf_id(struct btf *btf, int ext_btf_id) { if (!btf) return -ESRCH; - n = btf__get_nr_types(btf); - for (i = 1; i <= n; i++) { + n = btf__type_cnt(btf); + for (i = 1; i < n; i++) { t = btf__type_by_id(btf, i); if (!btf_is_datasec(t)) @@ -3258,8 +3549,8 @@ static int find_int_btf_id(const struct btf *btf) const struct btf_type *t; int i, n; - n = btf__get_nr_types(btf); - for (i = 1; i <= n; i++) { + n = btf__type_cnt(btf); + for (i = 1; i < n; i++) { t = btf__type_by_id(btf, i); if (btf_is_int(t) && btf_int_bits(t) == 32) @@ -3316,30 +3607,31 @@ static int bpf_object__collect_externs(struct bpf_object *obj) int i, n, off, dummy_var_btf_id; const char *ext_name, *sec_name; Elf_Scn *scn; - GElf_Shdr sh; + Elf64_Shdr *sh; if (!obj->efile.symbols) return 0; scn = elf_sec_by_idx(obj, obj->efile.symbols_shndx); - if (elf_sec_hdr(obj, scn, &sh)) + sh = elf_sec_hdr(obj, scn); + if (!sh || sh->sh_entsize != sizeof(Elf64_Sym)) return -LIBBPF_ERRNO__FORMAT; dummy_var_btf_id = add_dummy_ksym_var(obj->btf); if (dummy_var_btf_id < 0) return dummy_var_btf_id; - n = sh.sh_size / sh.sh_entsize; + n = sh->sh_size / sh->sh_entsize; pr_debug("looking for externs among %d symbols...\n", n); for (i = 0; i < n; i++) { - GElf_Sym sym; + Elf64_Sym *sym = elf_sym_by_idx(obj, i); - if (!gelf_getsym(obj->efile.symbols, i, &sym)) + if (!sym) return -LIBBPF_ERRNO__FORMAT; - if (!sym_is_extern(&sym)) + if (!sym_is_extern(sym)) continue; - ext_name = elf_sym_str(obj, sym.st_name); + ext_name = elf_sym_str(obj, sym->st_name); if (!ext_name || !ext_name[0]) continue; @@ -3361,7 +3653,7 @@ static int bpf_object__collect_externs(struct bpf_object *obj) t = btf__type_by_id(obj->btf, ext->btf_id); ext->name = btf__name_by_offset(obj->btf, t->name_off); ext->sym_idx = i; - ext->is_weak = GELF_ST_BIND(sym.st_info) == STB_WEAK; + ext->is_weak = ELF64_ST_BIND(sym->st_info) == STB_WEAK; ext->sec_btf_id = find_extern_sec_btf_id(obj->btf, ext->btf_id); if (ext->sec_btf_id <= 0) { @@ -3399,11 +3691,6 @@ static int bpf_object__collect_externs(struct bpf_object *obj) return -ENOTSUP; } } else if (strcmp(sec_name, KSYMS_SEC) == 0) { - if (btf_is_func(t) && ext->is_weak) { - pr_warn("extern weak function %s is unsupported\n", - ext->name); - return -ENOTSUP; - } ksym_sec = sec; ext->type = EXT_KSYM; skip_mods_and_typedefs(obj->btf, t->type, @@ -3571,9 +3858,14 @@ bpf_object__find_program_by_name(const struct bpf_object *obj, static bool bpf_object__shndx_is_data(const struct bpf_object *obj, int shndx) { - return shndx == obj->efile.data_shndx || - shndx == obj->efile.bss_shndx || - shndx == obj->efile.rodata_shndx; + switch (obj->efile.secs[shndx].sec_type) { + case SEC_BSS: + case SEC_DATA: + case SEC_RODATA: + return true; + default: + return false; + } } static bool bpf_object__shndx_is_maps(const struct bpf_object *obj, @@ -3586,22 +3878,25 @@ static bool bpf_object__shndx_is_maps(const struct bpf_object *obj, static enum libbpf_map_type bpf_object__section_to_libbpf_map_type(const struct bpf_object *obj, int shndx) { - if (shndx == obj->efile.data_shndx) - return LIBBPF_MAP_DATA; - else if (shndx == obj->efile.bss_shndx) - return LIBBPF_MAP_BSS; - else if (shndx == obj->efile.rodata_shndx) - return LIBBPF_MAP_RODATA; - else if (shndx == obj->efile.symbols_shndx) + if (shndx == obj->efile.symbols_shndx) return LIBBPF_MAP_KCONFIG; - else + + switch (obj->efile.secs[shndx].sec_type) { + case SEC_BSS: + return LIBBPF_MAP_BSS; + case SEC_DATA: + return LIBBPF_MAP_DATA; + case SEC_RODATA: + return LIBBPF_MAP_RODATA; + default: return LIBBPF_MAP_UNSPEC; + } } static int bpf_program__record_reloc(struct bpf_program *prog, struct reloc_desc *reloc_desc, __u32 insn_idx, const char *sym_name, - const GElf_Sym *sym, const GElf_Rel *rel) + const Elf64_Sym *sym, const Elf64_Rel *rel) { struct bpf_insn *insn = &prog->insns[insn_idx]; size_t map_idx, nr_maps = prog->obj->nr_maps; @@ -3618,7 +3913,7 @@ static int bpf_program__record_reloc(struct bpf_program *prog, } if (sym_is_extern(sym)) { - int sym_idx = GELF_R_SYM(rel->r_info); + int sym_idx = ELF64_R_SYM(rel->r_info); int i, n = obj->nr_extern; struct extern_desc *ext; @@ -3731,7 +4026,7 @@ static int bpf_program__record_reloc(struct bpf_program *prog, } for (map_idx = 0; map_idx < nr_maps; map_idx++) { map = &obj->maps[map_idx]; - if (map->libbpf_type != type) + if (map->libbpf_type != type || map->sec_idx != sym->st_shndx) continue; pr_debug("prog '%s': found data map %zd (%s, sec %d, off %zu) for insn %u\n", prog->name, map_idx, map->name, map->sec_idx, @@ -3783,11 +4078,10 @@ static struct bpf_program *find_prog_by_sec_insn(const struct bpf_object *obj, } static int -bpf_object__collect_prog_relos(struct bpf_object *obj, GElf_Shdr *shdr, Elf_Data *data) +bpf_object__collect_prog_relos(struct bpf_object *obj, Elf64_Shdr *shdr, Elf_Data *data) { - Elf_Data *symbols = obj->efile.symbols; const char *relo_sec_name, *sec_name; - size_t sec_idx = shdr->sh_info; + size_t sec_idx = shdr->sh_info, sym_idx; struct bpf_program *prog; struct reloc_desc *relos; int err, i, nrels; @@ -3795,8 +4089,11 @@ bpf_object__collect_prog_relos(struct bpf_object *obj, GElf_Shdr *shdr, Elf_Data __u32 insn_idx; Elf_Scn *scn; Elf_Data *scn_data; - GElf_Sym sym; - GElf_Rel rel; + Elf64_Sym *sym; + Elf64_Rel *rel; + + if (sec_idx >= obj->efile.sec_cnt) + return -EINVAL; scn = elf_sec_by_idx(obj, sec_idx); scn_data = elf_sec_data(obj, scn); @@ -3811,33 +4108,43 @@ bpf_object__collect_prog_relos(struct bpf_object *obj, GElf_Shdr *shdr, Elf_Data nrels = shdr->sh_size / shdr->sh_entsize; for (i = 0; i < nrels; i++) { - if (!gelf_getrel(data, i, &rel)) { + rel = elf_rel_by_idx(data, i); + if (!rel) { pr_warn("sec '%s': failed to get relo #%d\n", relo_sec_name, i); return -LIBBPF_ERRNO__FORMAT; } - if (!gelf_getsym(symbols, GELF_R_SYM(rel.r_info), &sym)) { - pr_warn("sec '%s': symbol 0x%zx not found for relo #%d\n", - relo_sec_name, (size_t)GELF_R_SYM(rel.r_info), i); + + sym_idx = ELF64_R_SYM(rel->r_info); + sym = elf_sym_by_idx(obj, sym_idx); + if (!sym) { + pr_warn("sec '%s': symbol #%zu not found for relo #%d\n", + relo_sec_name, sym_idx, i); return -LIBBPF_ERRNO__FORMAT; } - if (rel.r_offset % BPF_INSN_SZ || rel.r_offset >= scn_data->d_size) { + if (sym->st_shndx >= obj->efile.sec_cnt) { + pr_warn("sec '%s': corrupted symbol #%zu pointing to invalid section #%zu for relo #%d\n", + relo_sec_name, sym_idx, (size_t)sym->st_shndx, i); + return -LIBBPF_ERRNO__FORMAT; + } + + if (rel->r_offset % BPF_INSN_SZ || rel->r_offset >= scn_data->d_size) { pr_warn("sec '%s': invalid offset 0x%zx for relo #%d\n", - relo_sec_name, (size_t)GELF_R_SYM(rel.r_info), i); + relo_sec_name, (size_t)rel->r_offset, i); return -LIBBPF_ERRNO__FORMAT; } - insn_idx = rel.r_offset / BPF_INSN_SZ; + insn_idx = rel->r_offset / BPF_INSN_SZ; /* relocations against static functions are recorded as * relocations against the section that contains a function; * in such case, symbol will be STT_SECTION and sym.st_name * will point to empty string (0), so fetch section name * instead */ - if (GELF_ST_TYPE(sym.st_info) == STT_SECTION && sym.st_name == 0) - sym_name = elf_sec_name(obj, elf_sec_by_idx(obj, sym.st_shndx)); + if (ELF64_ST_TYPE(sym->st_info) == STT_SECTION && sym->st_name == 0) + sym_name = elf_sec_name(obj, elf_sec_by_idx(obj, sym->st_shndx)); else - sym_name = elf_sym_str(obj, sym.st_name); + sym_name = elf_sym_str(obj, sym->st_name); sym_name = sym_name ?: "sec_insn_off; err = bpf_program__record_reloc(prog, &relos[prog->nr_reloc], - insn_idx, sym_name, &sym, &rel); + insn_idx, sym_name, sym, rel); if (err) return err; @@ -3891,8 +4198,7 @@ static int bpf_map_find_btf_info(struct bpf_object *obj, struct bpf_map *map) * LLVM annotates global data differently in BTF, that is, * only as '.data', '.bss' or '.rodata'. */ - ret = btf__find_by_name(obj->btf, - libbpf_type_to_btf_name[map->libbpf_type]); + ret = btf__find_by_name(obj->btf, map->real_name); } if (ret < 0) return ret; @@ -3985,6 +4291,7 @@ int bpf_map__reuse_fd(struct bpf_map *map, int fd) map->btf_key_type_id = info.btf_key_type_id; map->btf_value_type_id = info.btf_value_type_id; map->reused = true; + map->map_extra = info.map_extra; return 0; @@ -4027,30 +4334,24 @@ int bpf_map__resize(struct bpf_map *map, __u32 max_entries) static int bpf_object__probe_loading(struct bpf_object *obj) { - struct bpf_load_program_attr attr; char *cp, errmsg[STRERR_BUFSIZE]; struct bpf_insn insns[] = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }; - int ret; + int ret, insn_cnt = ARRAY_SIZE(insns); if (obj->gen_loader) return 0; + ret = bump_rlimit_memlock(); + if (ret) + pr_warn("Failed to bump RLIMIT_MEMLOCK (err = %d), you might need to do it explicitly!\n", ret); + /* make sure basic loading works */ - - memset(&attr, 0, sizeof(attr)); - attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER; - attr.insns = insns; - attr.insns_cnt = ARRAY_SIZE(insns); - attr.license = "GPL"; - - ret = bpf_load_program_xattr(&attr, NULL, 0); - if (ret < 0) { - attr.prog_type = BPF_PROG_TYPE_TRACEPOINT; - ret = bpf_load_program_xattr(&attr, NULL, 0); - } + ret = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, NULL); + if (ret < 0) + ret = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", insns, insn_cnt, NULL); if (ret < 0) { ret = errno; cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg)); @@ -4074,29 +4375,19 @@ static int probe_fd(int fd) static int probe_kern_prog_name(void) { - struct bpf_load_program_attr attr; struct bpf_insn insns[] = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }; - int ret; + int ret, insn_cnt = ARRAY_SIZE(insns); /* make sure loading with name works */ - - memset(&attr, 0, sizeof(attr)); - attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER; - attr.insns = insns; - attr.insns_cnt = ARRAY_SIZE(insns); - attr.license = "GPL"; - attr.name = "test"; - ret = bpf_load_program_xattr(&attr, NULL, 0); + ret = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, "test", "GPL", insns, insn_cnt, NULL); return probe_fd(ret); } static int probe_kern_global_data(void) { - struct bpf_load_program_attr prg_attr; - struct bpf_create_map_attr map_attr; char *cp, errmsg[STRERR_BUFSIZE]; struct bpf_insn insns[] = { BPF_LD_MAP_VALUE(BPF_REG_1, 0, 16), @@ -4104,15 +4395,9 @@ static int probe_kern_global_data(void) BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }; - int ret, map; + int ret, map, insn_cnt = ARRAY_SIZE(insns); - memset(&map_attr, 0, sizeof(map_attr)); - map_attr.map_type = BPF_MAP_TYPE_ARRAY; - map_attr.key_size = sizeof(int); - map_attr.value_size = 32; - map_attr.max_entries = 1; - - map = bpf_create_map_xattr(&map_attr); + map = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, sizeof(int), 32, 1, NULL); if (map < 0) { ret = -errno; cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg)); @@ -4123,13 +4408,7 @@ static int probe_kern_global_data(void) insns[0].imm = map; - memset(&prg_attr, 0, sizeof(prg_attr)); - prg_attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER; - prg_attr.insns = insns; - prg_attr.insns_cnt = ARRAY_SIZE(insns); - prg_attr.license = "GPL"; - - ret = bpf_load_program_xattr(&prg_attr, NULL, 0); + ret = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, NULL); close(map); return probe_fd(ret); } @@ -4213,45 +4492,68 @@ static int probe_kern_btf_float(void) strs, sizeof(strs))); } -static int probe_kern_array_mmap(void) +static int probe_kern_btf_decl_tag(void) { - struct bpf_create_map_attr attr = { - .map_type = BPF_MAP_TYPE_ARRAY, - .map_flags = BPF_F_MMAPABLE, - .key_size = sizeof(int), - .value_size = sizeof(int), - .max_entries = 1, + static const char strs[] = "\0tag"; + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* VAR x */ /* [2] */ + BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), 1), + BTF_VAR_STATIC, + /* attr */ + BTF_TYPE_DECL_TAG_ENC(1, 2, -1), }; - return probe_fd(bpf_create_map_xattr(&attr)); + return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs))); +} + +static int probe_kern_btf_type_tag(void) +{ + static const char strs[] = "\0tag"; + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* attr */ + BTF_TYPE_TYPE_TAG_ENC(1, 1), /* [2] */ + /* ptr */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 2), /* [3] */ + }; + + return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs))); +} + +static int probe_kern_array_mmap(void) +{ + LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = BPF_F_MMAPABLE); + int fd; + + fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, sizeof(int), sizeof(int), 1, &opts); + return probe_fd(fd); } static int probe_kern_exp_attach_type(void) { - struct bpf_load_program_attr attr; + LIBBPF_OPTS(bpf_prog_load_opts, opts, .expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE); struct bpf_insn insns[] = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }; + int fd, insn_cnt = ARRAY_SIZE(insns); - memset(&attr, 0, sizeof(attr)); /* use any valid combination of program type and (optional) * non-zero expected attach type (i.e., not a BPF_CGROUP_INET_INGRESS) * to see if kernel supports expected_attach_type field for * BPF_PROG_LOAD command */ - attr.prog_type = BPF_PROG_TYPE_CGROUP_SOCK; - attr.expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE; - attr.insns = insns; - attr.insns_cnt = ARRAY_SIZE(insns); - attr.license = "GPL"; - - return probe_fd(bpf_load_program_xattr(&attr, NULL, 0)); + fd = bpf_prog_load(BPF_PROG_TYPE_CGROUP_SOCK, NULL, "GPL", insns, insn_cnt, &opts); + return probe_fd(fd); } static int probe_kern_probe_read_kernel(void) { - struct bpf_load_program_attr attr; struct bpf_insn insns[] = { BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), /* r1 = r10 (fp) */ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), /* r1 += -8 */ @@ -4260,34 +4562,22 @@ static int probe_kern_probe_read_kernel(void) BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_probe_read_kernel), BPF_EXIT_INSN(), }; + int fd, insn_cnt = ARRAY_SIZE(insns); - memset(&attr, 0, sizeof(attr)); - attr.prog_type = BPF_PROG_TYPE_KPROBE; - attr.insns = insns; - attr.insns_cnt = ARRAY_SIZE(insns); - attr.license = "GPL"; - - return probe_fd(bpf_load_program_xattr(&attr, NULL, 0)); + fd = bpf_prog_load(BPF_PROG_TYPE_KPROBE, NULL, "GPL", insns, insn_cnt, NULL); + return probe_fd(fd); } static int probe_prog_bind_map(void) { - struct bpf_load_program_attr prg_attr; - struct bpf_create_map_attr map_attr; char *cp, errmsg[STRERR_BUFSIZE]; struct bpf_insn insns[] = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }; - int ret, map, prog; + int ret, map, prog, insn_cnt = ARRAY_SIZE(insns); - memset(&map_attr, 0, sizeof(map_attr)); - map_attr.map_type = BPF_MAP_TYPE_ARRAY; - map_attr.key_size = sizeof(int); - map_attr.value_size = 32; - map_attr.max_entries = 1; - - map = bpf_create_map_xattr(&map_attr); + map = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, sizeof(int), 32, 1, NULL); if (map < 0) { ret = -errno; cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg)); @@ -4296,13 +4586,7 @@ static int probe_prog_bind_map(void) return ret; } - memset(&prg_attr, 0, sizeof(prg_attr)); - prg_attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER; - prg_attr.insns = insns; - prg_attr.insns_cnt = ARRAY_SIZE(insns); - prg_attr.license = "GPL"; - - prog = bpf_load_program_xattr(&prg_attr, NULL, 0); + prog = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, NULL); if (prog < 0) { close(map); return 0; @@ -4347,19 +4631,14 @@ static int probe_module_btf(void) static int probe_perf_link(void) { - struct bpf_load_program_attr attr; struct bpf_insn insns[] = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }; int prog_fd, link_fd, err; - memset(&attr, 0, sizeof(attr)); - attr.prog_type = BPF_PROG_TYPE_TRACEPOINT; - attr.insns = insns; - attr.insns_cnt = ARRAY_SIZE(insns); - attr.license = "GPL"; - prog_fd = bpf_load_program_xattr(&attr, NULL, 0); + prog_fd = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", + insns, ARRAY_SIZE(insns), NULL); if (prog_fd < 0) return -errno; @@ -4429,14 +4708,23 @@ static struct kern_feature_desc { [FEAT_PERF_LINK] = { "BPF perf link support", probe_perf_link, }, + [FEAT_BTF_DECL_TAG] = { + "BTF_KIND_DECL_TAG support", probe_kern_btf_decl_tag, + }, + [FEAT_BTF_TYPE_TAG] = { + "BTF_KIND_TYPE_TAG support", probe_kern_btf_type_tag, + }, + [FEAT_MEMCG_ACCOUNT] = { + "memcg-based memory accounting", probe_memcg_account, + }, }; -static bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id) +bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id) { struct kern_feature_desc *feat = &feature_probes[feat_id]; int ret; - if (obj->gen_loader) + if (obj && obj->gen_loader) /* To generate loader program assume the latest kernel * to avoid doing extra prog_load, map_create syscalls. */ @@ -4479,7 +4767,8 @@ static bool map_is_reuse_compat(const struct bpf_map *map, int map_fd) map_info.key_size == map->def.key_size && map_info.value_size == map->def.value_size && map_info.max_entries == map->def.max_entries && - map_info.map_flags == map->def.map_flags); + map_info.map_flags == map->def.map_flags && + map_info.map_extra == map->map_extra); } static int @@ -4562,20 +4851,18 @@ static void bpf_map__destroy(struct bpf_map *map); static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, bool is_inner) { - struct bpf_create_map_attr create_attr; + LIBBPF_OPTS(bpf_map_create_opts, create_attr); struct bpf_map_def *def = &map->def; + const char *map_name = NULL; + __u32 max_entries; int err = 0; - memset(&create_attr, 0, sizeof(create_attr)); - if (kernel_supports(obj, FEAT_PROG_NAME)) - create_attr.name = map->name; + map_name = map->name; create_attr.map_ifindex = map->map_ifindex; - create_attr.map_type = def->type; create_attr.map_flags = def->map_flags; - create_attr.key_size = def->key_size; - create_attr.value_size = def->value_size; create_attr.numa_node = map->numa_node; + create_attr.map_extra = map->map_extra; if (def->type == BPF_MAP_TYPE_PERF_EVENT_ARRAY && !def->max_entries) { int nr_cpus; @@ -4587,18 +4874,14 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b return nr_cpus; } pr_debug("map '%s': setting size to %d\n", map->name, nr_cpus); - create_attr.max_entries = nr_cpus; + max_entries = nr_cpus; } else { - create_attr.max_entries = def->max_entries; + max_entries = def->max_entries; } if (bpf_map__is_struct_ops(map)) - create_attr.btf_vmlinux_value_type_id = - map->btf_vmlinux_value_type_id; + create_attr.btf_vmlinux_value_type_id = map->btf_vmlinux_value_type_id; - create_attr.btf_fd = 0; - create_attr.btf_key_type_id = 0; - create_attr.btf_value_type_id = 0; if (obj->btf && btf__fd(obj->btf) >= 0 && !bpf_map_find_btf_info(obj, map)) { create_attr.btf_fd = btf__fd(obj->btf); create_attr.btf_key_type_id = map->btf_key_type_id; @@ -4619,14 +4902,42 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b create_attr.inner_map_fd = map->inner_map_fd; } + switch (def->type) { + case BPF_MAP_TYPE_PERF_EVENT_ARRAY: + case BPF_MAP_TYPE_CGROUP_ARRAY: + case BPF_MAP_TYPE_STACK_TRACE: + case BPF_MAP_TYPE_ARRAY_OF_MAPS: + case BPF_MAP_TYPE_HASH_OF_MAPS: + case BPF_MAP_TYPE_DEVMAP: + case BPF_MAP_TYPE_DEVMAP_HASH: + case BPF_MAP_TYPE_CPUMAP: + case BPF_MAP_TYPE_XSKMAP: + case BPF_MAP_TYPE_SOCKMAP: + case BPF_MAP_TYPE_SOCKHASH: + case BPF_MAP_TYPE_QUEUE: + case BPF_MAP_TYPE_STACK: + case BPF_MAP_TYPE_RINGBUF: + create_attr.btf_fd = 0; + create_attr.btf_key_type_id = 0; + create_attr.btf_value_type_id = 0; + map->btf_key_type_id = 0; + map->btf_value_type_id = 0; + default: + break; + } + if (obj->gen_loader) { - bpf_gen__map_create(obj->gen_loader, &create_attr, is_inner ? -1 : map - obj->maps); + bpf_gen__map_create(obj->gen_loader, def->type, map_name, + def->key_size, def->value_size, max_entries, + &create_attr, is_inner ? -1 : map - obj->maps); /* Pretend to have valid FD to pass various fd >= 0 checks. * This fd == 0 will not be used with any syscall and will be reset to -1 eventually. */ map->fd = 0; } else { - map->fd = bpf_create_map_xattr(&create_attr); + map->fd = bpf_map_create(def->type, map_name, + def->key_size, def->value_size, + max_entries, &create_attr); } if (map->fd < 0 && (create_attr.btf_key_type_id || create_attr.btf_value_type_id)) { @@ -4641,7 +4952,9 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b create_attr.btf_value_type_id = 0; map->btf_key_type_id = 0; map->btf_value_type_id = 0; - map->fd = bpf_create_map_xattr(&create_attr); + map->fd = bpf_map_create(def->type, map_name, + def->key_size, def->value_size, + max_entries, &create_attr); } err = map->fd < 0 ? -errno : 0; @@ -4656,7 +4969,7 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b return err; } -static int init_map_slots(struct bpf_object *obj, struct bpf_map *map) +static int init_map_in_map_slots(struct bpf_object *obj, struct bpf_map *map) { const struct bpf_map *targ_map; unsigned int i; @@ -4668,18 +4981,18 @@ static int init_map_slots(struct bpf_object *obj, struct bpf_map *map) targ_map = map->init_slots[i]; fd = bpf_map__fd(targ_map); + if (obj->gen_loader) { - pr_warn("// TODO map_update_elem: idx %td key %d value==map_idx %td\n", - map - obj->maps, i, targ_map - obj->maps); - return -ENOTSUP; + bpf_gen__populate_outer_map(obj->gen_loader, + map - obj->maps, i, + targ_map - obj->maps); } else { err = bpf_map_update_elem(map->fd, &i, &fd, 0); } if (err) { err = -errno; pr_warn("map '%s': failed to initialize slot [%d] to map '%s' fd=%d: %d\n", - map->name, i, targ_map->name, - fd, err); + map->name, i, targ_map->name, fd, err); return err; } pr_debug("map '%s': slot [%d] set to map '%s' fd=%d\n", @@ -4692,6 +5005,59 @@ static int init_map_slots(struct bpf_object *obj, struct bpf_map *map) return 0; } +static int init_prog_array_slots(struct bpf_object *obj, struct bpf_map *map) +{ + const struct bpf_program *targ_prog; + unsigned int i; + int fd, err; + + if (obj->gen_loader) + return -ENOTSUP; + + for (i = 0; i < map->init_slots_sz; i++) { + if (!map->init_slots[i]) + continue; + + targ_prog = map->init_slots[i]; + fd = bpf_program__fd(targ_prog); + + err = bpf_map_update_elem(map->fd, &i, &fd, 0); + if (err) { + err = -errno; + pr_warn("map '%s': failed to initialize slot [%d] to prog '%s' fd=%d: %d\n", + map->name, i, targ_prog->name, fd, err); + return err; + } + pr_debug("map '%s': slot [%d] set to prog '%s' fd=%d\n", + map->name, i, targ_prog->name, fd); + } + + zfree(&map->init_slots); + map->init_slots_sz = 0; + + return 0; +} + +static int bpf_object_init_prog_arrays(struct bpf_object *obj) +{ + struct bpf_map *map; + int i, err; + + for (i = 0; i < obj->nr_maps; i++) { + map = &obj->maps[i]; + + if (!map->init_slots_sz || map->def.type != BPF_MAP_TYPE_PROG_ARRAY) + continue; + + err = init_prog_array_slots(obj, map); + if (err < 0) { + zclose(map->fd); + return err; + } + } + return 0; +} + static int bpf_object__create_maps(struct bpf_object *obj) { @@ -4704,6 +5070,26 @@ bpf_object__create_maps(struct bpf_object *obj) for (i = 0; i < obj->nr_maps; i++) { map = &obj->maps[i]; + /* To support old kernels, we skip creating global data maps + * (.rodata, .data, .kconfig, etc); later on, during program + * loading, if we detect that at least one of the to-be-loaded + * programs is referencing any global data map, we'll error + * out with program name and relocation index logged. + * This approach allows to accommodate Clang emitting + * unnecessary .rodata.str1.1 sections for string literals, + * but also it allows to have CO-RE applications that use + * global variables in some of BPF programs, but not others. + * If those global variable-using programs are not loaded at + * runtime due to bpf_program__set_autoload(prog, false), + * bpf_object loading will succeed just fine even on old + * kernels. + */ + if (bpf_map__is_internal(map) && + !kernel_supports(obj, FEAT_GLOBAL_DATA)) { + map->skipped = true; + continue; + } + retried = false; retry: if (map->pin_path) { @@ -4740,8 +5126,8 @@ bpf_object__create_maps(struct bpf_object *obj) } } - if (map->init_slots_sz) { - err = init_map_slots(obj, map); + if (map->init_slots_sz && map->def.type != BPF_MAP_TYPE_PROG_ARRAY) { + err = init_map_in_map_slots(obj, map); if (err < 0) { zclose(map->fd); goto err_out; @@ -4813,15 +5199,18 @@ static int bpf_core_add_cands(struct bpf_core_cand *local_cand, struct bpf_core_cand_list *cands) { struct bpf_core_cand *new_cands, *cand; - const struct btf_type *t; - const char *targ_name; + const struct btf_type *t, *local_t; + const char *targ_name, *local_name; size_t targ_essent_len; int n, i; - n = btf__get_nr_types(targ_btf); - for (i = targ_start_id; i <= n; i++) { + local_t = btf__type_by_id(local_cand->btf, local_cand->id); + local_name = btf__str_by_offset(local_cand->btf, local_t->name_off); + + n = btf__type_cnt(targ_btf); + for (i = targ_start_id; i < n; i++) { t = btf__type_by_id(targ_btf, i); - if (btf_kind(t) != btf_kind(local_cand->t)) + if (btf_kind(t) != btf_kind(local_t)) continue; targ_name = btf__name_by_offset(targ_btf, t->name_off); @@ -4832,12 +5221,12 @@ static int bpf_core_add_cands(struct bpf_core_cand *local_cand, if (targ_essent_len != local_essent_len) continue; - if (strncmp(local_cand->name, targ_name, local_essent_len) != 0) + if (strncmp(local_name, targ_name, local_essent_len) != 0) continue; pr_debug("CO-RE relocating [%d] %s %s: found target candidate [%d] %s %s in [%s]\n", - local_cand->id, btf_kind_str(local_cand->t), - local_cand->name, i, btf_kind_str(t), targ_name, + local_cand->id, btf_kind_str(local_t), + local_name, i, btf_kind_str(t), targ_name, targ_btf_name); new_cands = libbpf_reallocarray(cands->cands, cands->len + 1, sizeof(*cands->cands)); @@ -4846,8 +5235,6 @@ static int bpf_core_add_cands(struct bpf_core_cand *local_cand, cand = &new_cands[cands->len]; cand->btf = targ_btf; - cand->t = t; - cand->name = targ_name; cand->id = i; cands->cands = new_cands; @@ -4954,18 +5341,21 @@ bpf_core_find_cands(struct bpf_object *obj, const struct btf *local_btf, __u32 l struct bpf_core_cand local_cand = {}; struct bpf_core_cand_list *cands; const struct btf *main_btf; + const struct btf_type *local_t; + const char *local_name; size_t local_essent_len; int err, i; local_cand.btf = local_btf; - local_cand.t = btf__type_by_id(local_btf, local_type_id); - if (!local_cand.t) + local_cand.id = local_type_id; + local_t = btf__type_by_id(local_btf, local_type_id); + if (!local_t) return ERR_PTR(-EINVAL); - local_cand.name = btf__name_by_offset(local_btf, local_cand.t->name_off); - if (str_is_empty(local_cand.name)) + local_name = btf__name_by_offset(local_btf, local_t->name_off); + if (str_is_empty(local_name)) return ERR_PTR(-EINVAL); - local_essent_len = bpf_core_essential_name_len(local_cand.name); + local_essent_len = bpf_core_essential_name_len(local_name); cands = calloc(1, sizeof(*cands)); if (!cands) @@ -4994,7 +5384,7 @@ bpf_core_find_cands(struct bpf_object *obj, const struct btf *local_btf, __u32 l err = bpf_core_add_cands(&local_cand, local_essent_len, obj->btf_modules[i].btf, obj->btf_modules[i].name, - btf__get_nr_types(obj->btf_vmlinux) + 1, + btf__type_cnt(obj->btf_vmlinux), cands); if (err) goto err_out; @@ -5115,12 +5505,31 @@ static void *u32_as_hash_key(__u32 x) return (void *)(uintptr_t)x; } +static int record_relo_core(struct bpf_program *prog, + const struct bpf_core_relo *core_relo, int insn_idx) +{ + struct reloc_desc *relos, *relo; + + relos = libbpf_reallocarray(prog->reloc_desc, + prog->nr_reloc + 1, sizeof(*relos)); + if (!relos) + return -ENOMEM; + relo = &relos[prog->nr_reloc]; + relo->type = RELO_CORE; + relo->insn_idx = insn_idx; + relo->core_relo = core_relo; + prog->reloc_desc = relos; + prog->nr_reloc++; + return 0; +} + static int bpf_core_apply_relo(struct bpf_program *prog, const struct bpf_core_relo *relo, int relo_idx, const struct btf *local_btf, struct hashmap *cand_cache) { + struct bpf_core_spec specs_scratch[3] = {}; const void *type_key = u32_as_hash_key(relo->type_id); struct bpf_core_cand_list *cands = NULL; const char *prog_name = prog->name; @@ -5151,13 +5560,15 @@ static int bpf_core_apply_relo(struct bpf_program *prog, return -EINVAL; if (prog->obj->gen_loader) { - pr_warn("// TODO core_relo: prog %td insn[%d] %s kind %d\n", + const char *spec_str = btf__name_by_offset(local_btf, relo->access_str_off); + + pr_debug("record_relo_core: prog %td insn[%d] %s %s %s final insn_idx %d\n", prog - prog->obj->programs, relo->insn_off / 8, - local_name, relo->kind); - return -ENOTSUP; + btf_kind_str(local_type), local_name, spec_str, insn_idx); + return record_relo_core(prog, relo, insn_idx); } - if (relo->kind != BPF_TYPE_ID_LOCAL && + if (relo->kind != BPF_CORE_TYPE_ID_LOCAL && !hashmap__find(cand_cache, type_key, (void **)&cands)) { cands = bpf_core_find_cands(prog->obj, local_btf, local_id); if (IS_ERR(cands)) { @@ -5173,7 +5584,8 @@ static int bpf_core_apply_relo(struct bpf_program *prog, } } - return bpf_core_apply_relo_insn(prog_name, insn, insn_idx, relo, relo_idx, local_btf, cands); + return bpf_core_apply_relo_insn(prog_name, insn, insn_idx, relo, + relo_idx, local_btf, cands, specs_scratch); } static int @@ -5303,6 +5715,13 @@ bpf_object__relocate_data(struct bpf_object *obj, struct bpf_program *prog) insn[0].src_reg = BPF_PSEUDO_MAP_IDX_VALUE; insn[0].imm = relo->map_idx; } else { + const struct bpf_map *map = &obj->maps[relo->map_idx]; + + if (map->skipped) { + pr_warn("prog '%s': relo #%d: kernel doesn't support global data\n", + prog->name, i); + return -ENOTSUP; + } insn[0].src_reg = BPF_PSEUDO_MAP_VALUE; insn[0].imm = obj->maps[relo->map_idx].fd; } @@ -5332,7 +5751,13 @@ bpf_object__relocate_data(struct bpf_object *obj, struct bpf_program *prog) case RELO_EXTERN_FUNC: ext = &obj->externs[relo->sym_off]; insn[0].src_reg = BPF_PSEUDO_KFUNC_CALL; - insn[0].imm = ext->ksym.kernel_btf_id; + if (ext->is_set) { + insn[0].imm = ext->ksym.kernel_btf_id; + insn[0].off = ext->ksym.btf_fd_idx; + } else { /* unresolved weak kfunc */ + insn[0].imm = 0; + insn[0].off = 0; + } break; case RELO_SUBPROG_ADDR: if (insn[0].src_reg != BPF_PSEUDO_FUNC) { @@ -5345,6 +5770,9 @@ bpf_object__relocate_data(struct bpf_object *obj, struct bpf_program *prog) case RELO_CALL: /* handled already */ break; + case RELO_CORE: + /* will be handled by bpf_program_record_relos() */ + break; default: pr_warn("prog '%s': relo #%d: bad relo type %d\n", prog->name, i, relo->type); @@ -5508,6 +5936,8 @@ static int cmp_relo_by_insn_idx(const void *key, const void *elem) static struct reloc_desc *find_prog_insn_relo(const struct bpf_program *prog, size_t insn_idx) { + if (!prog->nr_reloc) + return NULL; return bsearch(&insn_idx, prog->reloc_desc, prog->nr_reloc, sizeof(*prog->reloc_desc), cmp_relo_by_insn_idx); } @@ -5523,8 +5953,9 @@ static int append_subprog_relos(struct bpf_program *main_prog, struct bpf_progra relos = libbpf_reallocarray(main_prog->reloc_desc, new_cnt, sizeof(*relos)); if (!relos) return -ENOMEM; - memcpy(relos + main_prog->nr_reloc, subprog->reloc_desc, - sizeof(*relos) * subprog->nr_reloc); + if (subprog->nr_reloc) + memcpy(relos + main_prog->nr_reloc, subprog->reloc_desc, + sizeof(*relos) * subprog->nr_reloc); for (i = main_prog->nr_reloc; i < new_cnt; i++) relos[i].insn_idx += subprog->sub_insn_off; @@ -5782,6 +6213,35 @@ bpf_object__free_relocs(struct bpf_object *obj) } } +static int cmp_relocs(const void *_a, const void *_b) +{ + const struct reloc_desc *a = _a; + const struct reloc_desc *b = _b; + + if (a->insn_idx != b->insn_idx) + return a->insn_idx < b->insn_idx ? -1 : 1; + + /* no two relocations should have the same insn_idx, but ... */ + if (a->type != b->type) + return a->type < b->type ? -1 : 1; + + return 0; +} + +static void bpf_object__sort_relos(struct bpf_object *obj) +{ + int i; + + for (i = 0; i < obj->nr_programs; i++) { + struct bpf_program *p = &obj->programs[i]; + + if (!p->nr_reloc) + continue; + + qsort(p->reloc_desc, p->nr_reloc, sizeof(*p->reloc_desc), cmp_relocs); + } +} + static int bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path) { @@ -5796,6 +6256,8 @@ bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path) err); return err; } + if (obj->gen_loader) + bpf_object__sort_relos(obj); } /* Before relocating calls pre-process relocations and mark @@ -5831,6 +6293,8 @@ bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path) */ if (prog_is_subprog(obj, prog)) continue; + if (!prog->load) + continue; err = bpf_object__relocate_calls(obj, prog); if (err) { @@ -5844,6 +6308,8 @@ bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path) prog = &obj->programs[i]; if (prog_is_subprog(obj, prog)) continue; + if (!prog->load) + continue; err = bpf_object__relocate_data(obj, prog); if (err) { pr_warn("prog '%s': failed to relocate data references: %d\n", @@ -5857,22 +6323,23 @@ bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path) } static int bpf_object__collect_st_ops_relos(struct bpf_object *obj, - GElf_Shdr *shdr, Elf_Data *data); + Elf64_Shdr *shdr, Elf_Data *data); static int bpf_object__collect_map_relos(struct bpf_object *obj, - GElf_Shdr *shdr, Elf_Data *data) + Elf64_Shdr *shdr, Elf_Data *data) { const int bpf_ptr_sz = 8, host_ptr_sz = sizeof(void *); int i, j, nrels, new_sz; const struct btf_var_secinfo *vi = NULL; const struct btf_type *sec, *var, *def; - struct bpf_map *map = NULL, *targ_map; + struct bpf_map *map = NULL, *targ_map = NULL; + struct bpf_program *targ_prog = NULL; + bool is_prog_array, is_map_in_map; const struct btf_member *member; - const char *name, *mname; - Elf_Data *symbols; + const char *name, *mname, *type; unsigned int moff; - GElf_Sym sym; - GElf_Rel rel; + Elf64_Sym *sym; + Elf64_Rel *rel; void *tmp; if (!obj->efile.btf_maps_sec_btf_id || !obj->btf) @@ -5881,28 +6348,25 @@ static int bpf_object__collect_map_relos(struct bpf_object *obj, if (!sec) return -EINVAL; - symbols = obj->efile.symbols; nrels = shdr->sh_size / shdr->sh_entsize; for (i = 0; i < nrels; i++) { - if (!gelf_getrel(data, i, &rel)) { + rel = elf_rel_by_idx(data, i); + if (!rel) { pr_warn(".maps relo #%d: failed to get ELF relo\n", i); return -LIBBPF_ERRNO__FORMAT; } - if (!gelf_getsym(symbols, GELF_R_SYM(rel.r_info), &sym)) { + + sym = elf_sym_by_idx(obj, ELF64_R_SYM(rel->r_info)); + if (!sym) { pr_warn(".maps relo #%d: symbol %zx not found\n", - i, (size_t)GELF_R_SYM(rel.r_info)); + i, (size_t)ELF64_R_SYM(rel->r_info)); return -LIBBPF_ERRNO__FORMAT; } - name = elf_sym_str(obj, sym.st_name) ?: ""; - if (sym.st_shndx != obj->efile.btf_maps_shndx) { - pr_warn(".maps relo #%d: '%s' isn't a BTF-defined map\n", - i, name); - return -LIBBPF_ERRNO__RELOC; - } + name = elf_sym_str(obj, sym->st_name) ?: ""; - pr_debug(".maps relo #%d: for %zd value %zd rel.r_offset %zu name %d ('%s')\n", - i, (ssize_t)(rel.r_info >> 32), (size_t)sym.st_value, - (size_t)rel.r_offset, sym.st_name, name); + pr_debug(".maps relo #%d: for %zd value %zd rel->r_offset %zu name %d ('%s')\n", + i, (ssize_t)(rel->r_info >> 32), (size_t)sym->st_value, + (size_t)rel->r_offset, sym->st_name, name); for (j = 0; j < obj->nr_maps; j++) { map = &obj->maps[j]; @@ -5910,29 +6374,55 @@ static int bpf_object__collect_map_relos(struct bpf_object *obj, continue; vi = btf_var_secinfos(sec) + map->btf_var_idx; - if (vi->offset <= rel.r_offset && - rel.r_offset + bpf_ptr_sz <= vi->offset + vi->size) + if (vi->offset <= rel->r_offset && + rel->r_offset + bpf_ptr_sz <= vi->offset + vi->size) break; } if (j == obj->nr_maps) { - pr_warn(".maps relo #%d: cannot find map '%s' at rel.r_offset %zu\n", - i, name, (size_t)rel.r_offset); + pr_warn(".maps relo #%d: cannot find map '%s' at rel->r_offset %zu\n", + i, name, (size_t)rel->r_offset); return -EINVAL; } - if (!bpf_map_type__is_map_in_map(map->def.type)) - return -EINVAL; - if (map->def.type == BPF_MAP_TYPE_HASH_OF_MAPS && - map->def.key_size != sizeof(int)) { - pr_warn(".maps relo #%d: hash-of-maps '%s' should have key size %zu.\n", - i, map->name, sizeof(int)); + is_map_in_map = bpf_map_type__is_map_in_map(map->def.type); + is_prog_array = map->def.type == BPF_MAP_TYPE_PROG_ARRAY; + type = is_map_in_map ? "map" : "prog"; + if (is_map_in_map) { + if (sym->st_shndx != obj->efile.btf_maps_shndx) { + pr_warn(".maps relo #%d: '%s' isn't a BTF-defined map\n", + i, name); + return -LIBBPF_ERRNO__RELOC; + } + if (map->def.type == BPF_MAP_TYPE_HASH_OF_MAPS && + map->def.key_size != sizeof(int)) { + pr_warn(".maps relo #%d: hash-of-maps '%s' should have key size %zu.\n", + i, map->name, sizeof(int)); + return -EINVAL; + } + targ_map = bpf_object__find_map_by_name(obj, name); + if (!targ_map) { + pr_warn(".maps relo #%d: '%s' isn't a valid map reference\n", + i, name); + return -ESRCH; + } + } else if (is_prog_array) { + targ_prog = bpf_object__find_program_by_name(obj, name); + if (!targ_prog) { + pr_warn(".maps relo #%d: '%s' isn't a valid program reference\n", + i, name); + return -ESRCH; + } + if (targ_prog->sec_idx != sym->st_shndx || + targ_prog->sec_insn_off * 8 != sym->st_value || + prog_is_subprog(obj, targ_prog)) { + pr_warn(".maps relo #%d: '%s' isn't an entry-point program\n", + i, name); + return -LIBBPF_ERRNO__RELOC; + } + } else { return -EINVAL; } - targ_map = bpf_object__find_map_by_name(obj, name); - if (!targ_map) - return -ESRCH; - var = btf__type_by_id(obj->btf, vi->type); def = skip_mods_and_typedefs(obj->btf, var->type, NULL); if (btf_vlen(def) == 0) @@ -5943,10 +6433,10 @@ static int bpf_object__collect_map_relos(struct bpf_object *obj, return -EINVAL; moff = btf_member_bit_offset(def, btf_vlen(def) - 1) / 8; - if (rel.r_offset - vi->offset < moff) + if (rel->r_offset - vi->offset < moff) return -EINVAL; - moff = rel.r_offset - vi->offset - moff; + moff = rel->r_offset - vi->offset - moff; /* here we use BPF pointer size, which is always 64 bit, as we * are parsing ELF that was built for BPF target */ @@ -5963,38 +6453,31 @@ static int bpf_object__collect_map_relos(struct bpf_object *obj, (new_sz - map->init_slots_sz) * host_ptr_sz); map->init_slots_sz = new_sz; } - map->init_slots[moff] = targ_map; + map->init_slots[moff] = is_map_in_map ? (void *)targ_map : (void *)targ_prog; - pr_debug(".maps relo #%d: map '%s' slot [%d] points to map '%s'\n", - i, map->name, moff, name); + pr_debug(".maps relo #%d: map '%s' slot [%d] points to %s '%s'\n", + i, map->name, moff, type, name); } return 0; } -static int cmp_relocs(const void *_a, const void *_b) -{ - const struct reloc_desc *a = _a; - const struct reloc_desc *b = _b; - - if (a->insn_idx != b->insn_idx) - return a->insn_idx < b->insn_idx ? -1 : 1; - - /* no two relocations should have the same insn_idx, but ... */ - if (a->type != b->type) - return a->type < b->type ? -1 : 1; - - return 0; -} - static int bpf_object__collect_relos(struct bpf_object *obj) { int i, err; - for (i = 0; i < obj->efile.nr_reloc_sects; i++) { - GElf_Shdr *shdr = &obj->efile.reloc_sects[i].shdr; - Elf_Data *data = obj->efile.reloc_sects[i].data; - int idx = shdr->sh_info; + for (i = 0; i < obj->efile.sec_cnt; i++) { + struct elf_sec_desc *sec_desc = &obj->efile.secs[i]; + Elf64_Shdr *shdr; + Elf_Data *data; + int idx; + + if (sec_desc->sec_type != SEC_RELO) + continue; + + shdr = sec_desc->shdr; + data = sec_desc->data; + idx = shdr->sh_info; if (shdr->sh_type != SHT_REL) { pr_warn("internal error at %d\n", __LINE__); @@ -6011,14 +6494,7 @@ static int bpf_object__collect_relos(struct bpf_object *obj) return err; } - for (i = 0; i < obj->nr_programs; i++) { - struct bpf_program *p = &obj->programs[i]; - - if (!p->nr_reloc) - continue; - - qsort(p->reloc_desc, p->nr_reloc, sizeof(*p->reloc_desc), cmp_relocs); - } + bpf_object__sort_relos(obj); return 0; } @@ -6070,15 +6546,61 @@ static int bpf_object__sanitize_prog(struct bpf_object *obj, struct bpf_program return 0; } -static int -load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt, - char *license, __u32 kern_version, int *pfd) +static int libbpf_find_attach_btf_id(struct bpf_program *prog, const char *attach_name, + int *btf_obj_fd, int *btf_type_id); + +/* this is called as prog->sec_def->preload_fn for libbpf-supported sec_defs */ +static int libbpf_preload_prog(struct bpf_program *prog, + struct bpf_prog_load_opts *opts, long cookie) { - struct bpf_prog_load_params load_attr = {}; + enum sec_def_flags def = cookie; + + /* old kernels might not support specifying expected_attach_type */ + if ((def & SEC_EXP_ATTACH_OPT) && !kernel_supports(prog->obj, FEAT_EXP_ATTACH_TYPE)) + opts->expected_attach_type = 0; + + if (def & SEC_SLEEPABLE) + opts->prog_flags |= BPF_F_SLEEPABLE; + + if ((prog->type == BPF_PROG_TYPE_TRACING || + prog->type == BPF_PROG_TYPE_LSM || + prog->type == BPF_PROG_TYPE_EXT) && !prog->attach_btf_id) { + int btf_obj_fd = 0, btf_type_id = 0, err; + const char *attach_name; + + attach_name = strchr(prog->sec_name, '/') + 1; + err = libbpf_find_attach_btf_id(prog, attach_name, &btf_obj_fd, &btf_type_id); + if (err) + return err; + + /* cache resolved BTF FD and BTF type ID in the prog */ + prog->attach_btf_obj_fd = btf_obj_fd; + prog->attach_btf_id = btf_type_id; + + /* but by now libbpf common logic is not utilizing + * prog->atach_btf_obj_fd/prog->attach_btf_id anymore because + * this callback is called after opts were populated by + * libbpf, so this callback has to update opts explicitly here + */ + opts->attach_btf_obj_fd = btf_obj_fd; + opts->attach_btf_id = btf_type_id; + } + return 0; +} + +static int bpf_object_load_prog_instance(struct bpf_object *obj, struct bpf_program *prog, + struct bpf_insn *insns, int insns_cnt, + const char *license, __u32 kern_version, + int *prog_fd) +{ + LIBBPF_OPTS(bpf_prog_load_opts, load_attr); + const char *prog_name = NULL; char *cp, errmsg[STRERR_BUFSIZE]; size_t log_buf_size = 0; - char *log_buf = NULL; - int btf_fd, ret; + char *log_buf = NULL, *tmp; + int btf_fd, ret, err; + bool own_log_buf = true; + __u32 log_level = prog->log_level; if (prog->type == BPF_PROG_TYPE_UNSPEC) { /* @@ -6093,30 +6615,18 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt, if (!insns || !insns_cnt) return -EINVAL; - load_attr.prog_type = prog->type; - /* old kernels might not support specifying expected_attach_type */ - if (!kernel_supports(prog->obj, FEAT_EXP_ATTACH_TYPE) && prog->sec_def && - prog->sec_def->is_exp_attach_type_optional) - load_attr.expected_attach_type = 0; - else - load_attr.expected_attach_type = prog->expected_attach_type; - if (kernel_supports(prog->obj, FEAT_PROG_NAME)) - load_attr.name = prog->name; - load_attr.insns = insns; - load_attr.insn_cnt = insns_cnt; - load_attr.license = license; - load_attr.attach_btf_id = prog->attach_btf_id; - if (prog->attach_prog_fd) - load_attr.attach_prog_fd = prog->attach_prog_fd; - else - load_attr.attach_btf_obj_fd = prog->attach_btf_obj_fd; + load_attr.expected_attach_type = prog->expected_attach_type; + if (kernel_supports(obj, FEAT_PROG_NAME)) + prog_name = prog->name; + load_attr.attach_prog_fd = prog->attach_prog_fd; + load_attr.attach_btf_obj_fd = prog->attach_btf_obj_fd; load_attr.attach_btf_id = prog->attach_btf_id; load_attr.kern_version = kern_version; load_attr.prog_ifindex = prog->prog_ifindex; /* specify func_info/line_info only if kernel supports them */ - btf_fd = bpf_object__btf_fd(prog->obj); - if (btf_fd >= 0 && kernel_supports(prog->obj, FEAT_BTF_FUNC)) { + btf_fd = bpf_object__btf_fd(obj); + if (btf_fd >= 0 && kernel_supports(obj, FEAT_BTF_FUNC)) { load_attr.prog_btf_fd = btf_fd; load_attr.func_info = prog->func_info; load_attr.func_info_rec_size = prog->func_info_rec_size; @@ -6125,93 +6635,125 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt, load_attr.line_info_rec_size = prog->line_info_rec_size; load_attr.line_info_cnt = prog->line_info_cnt; } - load_attr.log_level = prog->log_level; + load_attr.log_level = log_level; load_attr.prog_flags = prog->prog_flags; + load_attr.fd_array = obj->fd_array; - if (prog->obj->gen_loader) { - bpf_gen__prog_load(prog->obj->gen_loader, &load_attr, - prog - prog->obj->programs); - *pfd = -1; + /* adjust load_attr if sec_def provides custom preload callback */ + if (prog->sec_def && prog->sec_def->preload_fn) { + err = prog->sec_def->preload_fn(prog, &load_attr, prog->sec_def->cookie); + if (err < 0) { + pr_warn("prog '%s': failed to prepare load attributes: %d\n", + prog->name, err); + return err; + } + } + + if (obj->gen_loader) { + bpf_gen__prog_load(obj->gen_loader, prog->type, prog->name, + license, insns, insns_cnt, &load_attr, + prog - obj->programs); + *prog_fd = -1; return 0; } -retry_load: - if (log_buf_size) { - log_buf = malloc(log_buf_size); - if (!log_buf) - return -ENOMEM; - *log_buf = 0; +retry_load: + /* if log_level is zero, we don't request logs initiallly even if + * custom log_buf is specified; if the program load fails, then we'll + * bump log_level to 1 and use either custom log_buf or we'll allocate + * our own and retry the load to get details on what failed + */ + if (log_level) { + if (prog->log_buf) { + log_buf = prog->log_buf; + log_buf_size = prog->log_size; + own_log_buf = false; + } else if (obj->log_buf) { + log_buf = obj->log_buf; + log_buf_size = obj->log_size; + own_log_buf = false; + } else { + log_buf_size = max((size_t)BPF_LOG_BUF_SIZE, log_buf_size * 2); + tmp = realloc(log_buf, log_buf_size); + if (!tmp) { + ret = -ENOMEM; + goto out; + } + log_buf = tmp; + log_buf[0] = '\0'; + own_log_buf = true; + } } load_attr.log_buf = log_buf; - load_attr.log_buf_sz = log_buf_size; - ret = libbpf__bpf_prog_load(&load_attr); + load_attr.log_size = log_buf_size; + load_attr.log_level = log_level; + ret = bpf_prog_load(prog->type, prog_name, license, insns, insns_cnt, &load_attr); if (ret >= 0) { - if (log_buf && load_attr.log_level) - pr_debug("verifier log:\n%s", log_buf); + if (log_level && own_log_buf) { + pr_debug("prog '%s': -- BEGIN PROG LOAD LOG --\n%s-- END PROG LOAD LOG --\n", + prog->name, log_buf); + } - if (prog->obj->rodata_map_idx >= 0 && - kernel_supports(prog->obj, FEAT_PROG_BIND_MAP)) { - struct bpf_map *rodata_map = - &prog->obj->maps[prog->obj->rodata_map_idx]; + if (obj->has_rodata && kernel_supports(obj, FEAT_PROG_BIND_MAP)) { + struct bpf_map *map; + int i; - if (bpf_prog_bind_map(ret, bpf_map__fd(rodata_map), NULL)) { - cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); - pr_warn("prog '%s': failed to bind .rodata map: %s\n", - prog->name, cp); - /* Don't fail hard if can't bind rodata. */ + for (i = 0; i < obj->nr_maps; i++) { + map = &prog->obj->maps[i]; + if (map->libbpf_type != LIBBPF_MAP_RODATA) + continue; + + if (bpf_prog_bind_map(ret, bpf_map__fd(map), NULL)) { + cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); + pr_warn("prog '%s': failed to bind map '%s': %s\n", + prog->name, map->real_name, cp); + /* Don't fail hard if can't bind rodata. */ + } } } - *pfd = ret; + *prog_fd = ret; ret = 0; goto out; } - if (!log_buf || errno == ENOSPC) { - log_buf_size = max((size_t)BPF_LOG_BUF_SIZE, - log_buf_size << 1); - - free(log_buf); + if (log_level == 0) { + log_level = 1; goto retry_load; } - ret = errno ? -errno : -LIBBPF_ERRNO__LOAD; + /* On ENOSPC, increase log buffer size and retry, unless custom + * log_buf is specified. + * Be careful to not overflow u32, though. Kernel's log buf size limit + * isn't part of UAPI so it can always be bumped to full 4GB. So don't + * multiply by 2 unless we are sure we'll fit within 32 bits. + * Currently, we'll get -EINVAL when we reach (UINT_MAX >> 2). + */ + if (own_log_buf && errno == ENOSPC && log_buf_size <= UINT_MAX / 2) + goto retry_load; + + ret = -errno; cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); - pr_warn("load bpf program failed: %s\n", cp); + pr_warn("prog '%s': BPF program load failed: %s\n", prog->name, cp); pr_perm_msg(ret); - if (log_buf && log_buf[0] != '\0') { - ret = -LIBBPF_ERRNO__VERIFY; - pr_warn("-- BEGIN DUMP LOG ---\n"); - pr_warn("\n%s\n", log_buf); - pr_warn("-- END LOG --\n"); - } else if (load_attr.insn_cnt >= BPF_MAXINSNS) { - pr_warn("Program too large (%zu insns), at most %d insns\n", - load_attr.insn_cnt, BPF_MAXINSNS); - ret = -LIBBPF_ERRNO__PROG2BIG; - } else if (load_attr.prog_type != BPF_PROG_TYPE_KPROBE) { - /* Wrong program type? */ - int fd; - - load_attr.prog_type = BPF_PROG_TYPE_KPROBE; - load_attr.expected_attach_type = 0; - load_attr.log_buf = NULL; - load_attr.log_buf_sz = 0; - fd = libbpf__bpf_prog_load(&load_attr); - if (fd >= 0) { - close(fd); - ret = -LIBBPF_ERRNO__PROGTYPE; - goto out; - } + if (own_log_buf && log_buf && log_buf[0] != '\0') { + pr_warn("prog '%s': -- BEGIN PROG LOAD LOG --\n%s-- END PROG LOAD LOG --\n", + prog->name, log_buf); + } + if (insns_cnt >= BPF_MAXINSNS) { + pr_warn("prog '%s': program too large (%d insns), at most %d insns\n", + prog->name, insns_cnt, BPF_MAXINSNS); } out: - free(log_buf); + if (own_log_buf) + free(log_buf); return ret; } -static int bpf_program__record_externs(struct bpf_program *prog) +static int bpf_program_record_relos(struct bpf_program *prog) { struct bpf_object *obj = prog->obj; int i; @@ -6224,18 +6766,26 @@ static int bpf_program__record_externs(struct bpf_program *prog) case RELO_EXTERN_VAR: if (ext->type != EXT_KSYM) continue; - if (!ext->ksym.type_id) { - pr_warn("typeless ksym %s is not supported yet\n", - ext->name); - return -ENOTSUP; - } - bpf_gen__record_extern(obj->gen_loader, ext->name, BTF_KIND_VAR, - relo->insn_idx); + bpf_gen__record_extern(obj->gen_loader, ext->name, + ext->is_weak, !ext->ksym.type_id, + BTF_KIND_VAR, relo->insn_idx); break; case RELO_EXTERN_FUNC: - bpf_gen__record_extern(obj->gen_loader, ext->name, BTF_KIND_FUNC, + bpf_gen__record_extern(obj->gen_loader, ext->name, + ext->is_weak, false, BTF_KIND_FUNC, relo->insn_idx); break; + case RELO_CORE: { + struct bpf_core_relo cr = { + .insn_off = relo->insn_idx * 8, + .type_id = relo->core_relo->type_id, + .access_str_off = relo->core_relo->access_str_off, + .kind = relo->core_relo->kind, + }; + + bpf_gen__record_relo_core(obj->gen_loader, &cr); + break; + } default: continue; } @@ -6243,30 +6793,16 @@ static int bpf_program__record_externs(struct bpf_program *prog) return 0; } -static int libbpf_find_attach_btf_id(struct bpf_program *prog, int *btf_obj_fd, int *btf_type_id); - -int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_ver) +static int bpf_object_load_prog(struct bpf_object *obj, struct bpf_program *prog, + const char *license, __u32 kern_ver) { int err = 0, fd, i; - if (prog->obj->loaded) { + if (obj->loaded) { pr_warn("prog '%s': can't load after object was loaded\n", prog->name); return libbpf_err(-EINVAL); } - if ((prog->type == BPF_PROG_TYPE_TRACING || - prog->type == BPF_PROG_TYPE_LSM || - prog->type == BPF_PROG_TYPE_EXT) && !prog->attach_btf_id) { - int btf_obj_fd = 0, btf_type_id = 0; - - err = libbpf_find_attach_btf_id(prog, &btf_obj_fd, &btf_type_id); - if (err) - return libbpf_err(err); - - prog->attach_btf_obj_fd = btf_obj_fd; - prog->attach_btf_id = btf_type_id; - } - if (prog->instances.nr < 0 || !prog->instances.fds) { if (prog->preprocessor) { pr_warn("Internal error: can't load program '%s'\n", @@ -6288,10 +6824,11 @@ int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_ver) pr_warn("prog '%s': inconsistent nr(%d) != 1\n", prog->name, prog->instances.nr); } - if (prog->obj->gen_loader) - bpf_program__record_externs(prog); - err = load_program(prog, prog->insns, prog->insns_cnt, - license, kern_ver, &fd); + if (obj->gen_loader) + bpf_program_record_relos(prog); + err = bpf_object_load_prog_instance(obj, prog, + prog->insns, prog->insns_cnt, + license, kern_ver, &fd); if (!err) prog->instances.fds[0] = fd; goto out; @@ -6319,8 +6856,9 @@ int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_ver) continue; } - err = load_program(prog, result.new_insn_ptr, - result.new_insn_cnt, license, kern_ver, &fd); + err = bpf_object_load_prog_instance(obj, prog, + result.new_insn_ptr, result.new_insn_cnt, + license, kern_ver, &fd); if (err) { pr_warn("Loading the %dth instance of program '%s' failed\n", i, prog->name); @@ -6334,11 +6872,14 @@ int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_ver) out: if (err) pr_warn("failed to load program '%s'\n", prog->name); - zfree(&prog->insns); - prog->insns_cnt = 0; return libbpf_err(err); } +int bpf_program__load(struct bpf_program *prog, const char *license, __u32 kern_ver) +{ + return bpf_object_load_prog(prog->obj, prog, license, kern_ver); +} + static int bpf_object__load_progs(struct bpf_object *obj, int log_level) { @@ -6362,7 +6903,7 @@ bpf_object__load_progs(struct bpf_object *obj, int log_level) continue; } prog->log_level |= log_level; - err = bpf_program__load(prog, obj->license, obj->kern_version); + err = bpf_object_load_prog(obj, prog, obj->license, obj->kern_version); if (err) return err; } @@ -6373,15 +6914,56 @@ bpf_object__load_progs(struct bpf_object *obj, int log_level) static const struct bpf_sec_def *find_sec_def(const char *sec_name); -static struct bpf_object * -__bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz, - const struct bpf_object_open_opts *opts) +static int bpf_object_init_progs(struct bpf_object *obj, const struct bpf_object_open_opts *opts) +{ + struct bpf_program *prog; + int err; + + bpf_object__for_each_program(prog, obj) { + prog->sec_def = find_sec_def(prog->sec_name); + if (!prog->sec_def) { + /* couldn't guess, but user might manually specify */ + pr_debug("prog '%s': unrecognized ELF section name '%s'\n", + prog->name, prog->sec_name); + continue; + } + + bpf_program__set_type(prog, prog->sec_def->prog_type); + bpf_program__set_expected_attach_type(prog, prog->sec_def->expected_attach_type); + +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wdeprecated-declarations" + if (prog->sec_def->prog_type == BPF_PROG_TYPE_TRACING || + prog->sec_def->prog_type == BPF_PROG_TYPE_EXT) + prog->attach_prog_fd = OPTS_GET(opts, attach_prog_fd, 0); +#pragma GCC diagnostic pop + + /* sec_def can have custom callback which should be called + * after bpf_program is initialized to adjust its properties + */ + if (prog->sec_def->init_fn) { + err = prog->sec_def->init_fn(prog, prog->sec_def->cookie); + if (err < 0) { + pr_warn("prog '%s': failed to initialize: %d\n", + prog->name, err); + return err; + } + } + } + + return 0; +} + +static struct bpf_object *bpf_object_open(const char *path, const void *obj_buf, size_t obj_buf_sz, + const struct bpf_object_open_opts *opts) { const char *obj_name, *kconfig, *btf_tmp_path; - struct bpf_program *prog; struct bpf_object *obj; char tmp_name[64]; int err; + char *log_buf; + size_t log_size; + __u32 log_level; if (elf_version(EV_CURRENT) == EV_NONE) { pr_warn("failed to init libelf for %s\n", @@ -6404,10 +6986,22 @@ __bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz, pr_debug("loading object '%s' from buffer\n", obj_name); } + log_buf = OPTS_GET(opts, kernel_log_buf, NULL); + log_size = OPTS_GET(opts, kernel_log_size, 0); + log_level = OPTS_GET(opts, kernel_log_level, 0); + if (log_size > UINT_MAX) + return ERR_PTR(-EINVAL); + if (log_size && !log_buf) + return ERR_PTR(-EINVAL); + obj = bpf_object__new(path, obj_buf, obj_buf_sz, obj_name); if (IS_ERR(obj)) return obj; + obj->log_buf = log_buf; + obj->log_size = log_size; + obj->log_level = log_level; + btf_tmp_path = OPTS_GET(opts, btf_custom_path, NULL); if (btf_tmp_path) { if (strlen(btf_tmp_path) >= PATH_MAX) { @@ -6436,31 +7030,13 @@ __bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz, err = err ? : bpf_object__collect_externs(obj); err = err ? : bpf_object__finalize_btf(obj); err = err ? : bpf_object__init_maps(obj, opts); + err = err ? : bpf_object_init_progs(obj, opts); err = err ? : bpf_object__collect_relos(obj); if (err) goto out; + bpf_object__elf_finish(obj); - bpf_object__for_each_program(prog, obj) { - prog->sec_def = find_sec_def(prog->sec_name); - if (!prog->sec_def) { - /* couldn't guess, but user might manually specify */ - pr_debug("prog '%s': unrecognized ELF section name '%s'\n", - prog->name, prog->sec_name); - continue; - } - - if (prog->sec_def->is_sleepable) - prog->prog_flags |= BPF_F_SLEEPABLE; - bpf_program__set_type(prog, prog->sec_def->prog_type); - bpf_program__set_expected_attach_type(prog, - prog->sec_def->expected_attach_type); - - if (prog->sec_def->prog_type == BPF_PROG_TYPE_TRACING || - prog->sec_def->prog_type == BPF_PROG_TYPE_EXT) - prog->attach_prog_fd = OPTS_GET(opts, attach_prog_fd, 0); - } - return obj; out: bpf_object__close(obj); @@ -6479,7 +7055,7 @@ __bpf_object__open_xattr(struct bpf_object_open_attr *attr, int flags) return NULL; pr_debug("loading %s\n", attr->file); - return __bpf_object__open(attr->file, NULL, 0, &opts); + return bpf_object_open(attr->file, NULL, 0, &opts); } struct bpf_object *bpf_object__open_xattr(struct bpf_object_open_attr *attr) @@ -6505,7 +7081,7 @@ bpf_object__open_file(const char *path, const struct bpf_object_open_opts *opts) pr_debug("loading %s\n", path); - return libbpf_ptr(__bpf_object__open(path, NULL, 0, opts)); + return libbpf_ptr(bpf_object_open(path, NULL, 0, opts)); } struct bpf_object * @@ -6515,7 +7091,7 @@ bpf_object__open_mem(const void *obj_buf, size_t obj_buf_sz, if (!obj_buf || obj_buf_sz == 0) return libbpf_err_ptr(-EINVAL); - return libbpf_ptr(__bpf_object__open(NULL, obj_buf, obj_buf_sz, opts)); + return libbpf_ptr(bpf_object_open(NULL, obj_buf, obj_buf_sz, opts)); } struct bpf_object * @@ -6532,10 +7108,10 @@ bpf_object__open_buffer(const void *obj_buf, size_t obj_buf_sz, if (!obj_buf || obj_buf_sz == 0) return errno = EINVAL, NULL; - return libbpf_ptr(__bpf_object__open(NULL, obj_buf, obj_buf_sz, &opts)); + return libbpf_ptr(bpf_object_open(NULL, obj_buf, obj_buf_sz, &opts)); } -int bpf_object__unload(struct bpf_object *obj) +static int bpf_object_unload(struct bpf_object *obj) { size_t i; @@ -6554,6 +7130,8 @@ int bpf_object__unload(struct bpf_object *obj) return 0; } +int bpf_object__unload(struct bpf_object *obj) __attribute__((alias("bpf_object_unload"))); + static int bpf_object__sanitize_maps(struct bpf_object *obj) { struct bpf_map *m; @@ -6561,10 +7139,6 @@ static int bpf_object__sanitize_maps(struct bpf_object *obj) bpf_object__for_each_map(m, obj) { if (!bpf_map__is_internal(m)) continue; - if (!kernel_supports(obj, FEAT_GLOBAL_DATA)) { - pr_warn("kernel doesn't support global data\n"); - return -ENOTSUP; - } if (!kernel_supports(obj, FEAT_ARRAY_MMAP)) m->def.map_flags ^= BPF_F_MMAPABLE; } @@ -6627,13 +7201,14 @@ static int bpf_object__read_kallsyms_file(struct bpf_object *obj) static int find_ksym_btf_id(struct bpf_object *obj, const char *ksym_name, __u16 kind, struct btf **res_btf, - int *res_btf_fd) + struct module_btf **res_mod_btf) { - int i, id, btf_fd, err; + struct module_btf *mod_btf; struct btf *btf; + int i, id, err; btf = obj->btf_vmlinux; - btf_fd = 0; + mod_btf = NULL; id = btf__find_by_name_kind(btf, ksym_name, kind); if (id == -ENOENT) { @@ -6642,10 +7217,10 @@ static int find_ksym_btf_id(struct bpf_object *obj, const char *ksym_name, return err; for (i = 0; i < obj->btf_module_cnt; i++) { - btf = obj->btf_modules[i].btf; - /* we assume module BTF FD is always >0 */ - btf_fd = obj->btf_modules[i].fd; - id = btf__find_by_name_kind(btf, ksym_name, kind); + /* we assume module_btf's BTF FD is always >0 */ + mod_btf = &obj->btf_modules[i]; + btf = mod_btf->btf; + id = btf__find_by_name_kind_own(btf, ksym_name, kind); if (id != -ENOENT) break; } @@ -6654,7 +7229,7 @@ static int find_ksym_btf_id(struct bpf_object *obj, const char *ksym_name, return -ESRCH; *res_btf = btf; - *res_btf_fd = btf_fd; + *res_mod_btf = mod_btf; return id; } @@ -6663,14 +7238,15 @@ static int bpf_object__resolve_ksym_var_btf_id(struct bpf_object *obj, { const struct btf_type *targ_var, *targ_type; __u32 targ_type_id, local_type_id; + struct module_btf *mod_btf = NULL; const char *targ_var_name; - int id, btf_fd = 0, err; struct btf *btf = NULL; + int id, err; - id = find_ksym_btf_id(obj, ext->name, BTF_KIND_VAR, &btf, &btf_fd); - if (id == -ESRCH && ext->is_weak) { - return 0; - } else if (id < 0) { + id = find_ksym_btf_id(obj, ext->name, BTF_KIND_VAR, &btf, &mod_btf); + if (id < 0) { + if (id == -ESRCH && ext->is_weak) + return 0; pr_warn("extern (var ksym) '%s': not found in kernel BTF\n", ext->name); return id; @@ -6702,7 +7278,7 @@ static int bpf_object__resolve_ksym_var_btf_id(struct bpf_object *obj, } ext->is_set = true; - ext->ksym.kernel_btf_obj_fd = btf_fd; + ext->ksym.kernel_btf_obj_fd = mod_btf ? mod_btf->fd : 0; ext->ksym.kernel_btf_id = id; pr_debug("extern (var ksym) '%s': resolved to [%d] %s %s\n", ext->name, id, btf_kind_str(targ_var), targ_var_name); @@ -6714,26 +7290,22 @@ static int bpf_object__resolve_ksym_func_btf_id(struct bpf_object *obj, struct extern_desc *ext) { int local_func_proto_id, kfunc_proto_id, kfunc_id; + struct module_btf *mod_btf = NULL; const struct btf_type *kern_func; struct btf *kern_btf = NULL; - int ret, kern_btf_fd = 0; + int ret; local_func_proto_id = ext->ksym.type_id; - kfunc_id = find_ksym_btf_id(obj, ext->name, BTF_KIND_FUNC, - &kern_btf, &kern_btf_fd); + kfunc_id = find_ksym_btf_id(obj, ext->name, BTF_KIND_FUNC, &kern_btf, &mod_btf); if (kfunc_id < 0) { - pr_warn("extern (func ksym) '%s': not found in kernel BTF\n", + if (kfunc_id == -ESRCH && ext->is_weak) + return 0; + pr_warn("extern (func ksym) '%s': not found in kernel or module BTFs\n", ext->name); return kfunc_id; } - if (kern_btf != obj->btf_vmlinux) { - pr_warn("extern (func ksym) '%s': function in kernel module is not supported\n", - ext->name); - return -ENOTSUP; - } - kern_func = btf__type_by_id(kern_btf, kfunc_id); kfunc_proto_id = kern_func->type; @@ -6745,9 +7317,30 @@ static int bpf_object__resolve_ksym_func_btf_id(struct bpf_object *obj, return -EINVAL; } + /* set index for module BTF fd in fd_array, if unset */ + if (mod_btf && !mod_btf->fd_array_idx) { + /* insn->off is s16 */ + if (obj->fd_array_cnt == INT16_MAX) { + pr_warn("extern (func ksym) '%s': module BTF fd index %d too big to fit in bpf_insn offset\n", + ext->name, mod_btf->fd_array_idx); + return -E2BIG; + } + /* Cannot use index 0 for module BTF fd */ + if (!obj->fd_array_cnt) + obj->fd_array_cnt = 1; + + ret = libbpf_ensure_mem((void **)&obj->fd_array, &obj->fd_array_cap, sizeof(int), + obj->fd_array_cnt + 1); + if (ret) + return ret; + mod_btf->fd_array_idx = obj->fd_array_cnt; + /* we assume module BTF FD is always >0 */ + obj->fd_array[obj->fd_array_cnt++] = mod_btf->fd; + } + ext->is_set = true; - ext->ksym.kernel_btf_obj_fd = kern_btf_fd; ext->ksym.kernel_btf_id = kfunc_id; + ext->ksym.btf_fd_idx = mod_btf ? mod_btf->fd_array_idx : 0; pr_debug("extern (func ksym) '%s': resolved to kernel [%d]\n", ext->name, kfunc_id); @@ -6813,8 +7406,7 @@ static int bpf_object__resolve_externs(struct bpf_object *obj, if (err) return err; pr_debug("extern (kcfg) %s=0x%x\n", ext->name, kver); - } else if (ext->type == EXT_KCFG && - strncmp(ext->name, "CONFIG_", 7) == 0) { + } else if (ext->type == EXT_KCFG && str_has_pfx(ext->name, "CONFIG_")) { need_config = true; } else if (ext->type == EXT_KSYM) { if (ext->ksym.type_id) @@ -6869,14 +7461,10 @@ static int bpf_object__resolve_externs(struct bpf_object *obj, return 0; } -int bpf_object__load_xattr(struct bpf_object_load_attr *attr) +static int bpf_object_load(struct bpf_object *obj, int extra_log_level, const char *target_btf_path) { - struct bpf_object *obj; int err, i; - if (!attr) - return libbpf_err(-EINVAL); - obj = attr->obj; if (!obj) return libbpf_err(-EINVAL); @@ -6886,7 +7474,7 @@ int bpf_object__load_xattr(struct bpf_object_load_attr *attr) } if (obj->gen_loader) - bpf_gen__init(obj->gen_loader, attr->log_level); + bpf_gen__init(obj->gen_loader, extra_log_level, obj->nr_programs, obj->nr_maps); err = bpf_object__probe_loading(obj); err = err ? : bpf_object__load_vmlinux_btf(obj, false); @@ -6895,8 +7483,9 @@ int bpf_object__load_xattr(struct bpf_object_load_attr *attr) err = err ? : bpf_object__sanitize_maps(obj); err = err ? : bpf_object__init_kern_struct_ops_maps(obj); err = err ? : bpf_object__create_maps(obj); - err = err ? : bpf_object__relocate(obj, obj->btf_custom_path ? : attr->target_btf_path); - err = err ? : bpf_object__load_progs(obj, attr->log_level); + err = err ? : bpf_object__relocate(obj, obj->btf_custom_path ? : target_btf_path); + err = err ? : bpf_object__load_progs(obj, extra_log_level); + err = err ? : bpf_object_init_prog_arrays(obj); if (obj->gen_loader) { /* reset FDs */ @@ -6905,9 +7494,12 @@ int bpf_object__load_xattr(struct bpf_object_load_attr *attr) for (i = 0; i < obj->nr_maps; i++) obj->maps[i].fd = -1; if (!err) - err = bpf_gen__finish(obj->gen_loader); + err = bpf_gen__finish(obj->gen_loader, obj->nr_programs, obj->nr_maps); } + /* clean up fd_array */ + zfree(&obj->fd_array); + /* clean up module BTFs */ for (i = 0; i < obj->btf_module_cnt; i++) { close(obj->btf_modules[i].fd); @@ -6932,18 +7524,19 @@ int bpf_object__load_xattr(struct bpf_object_load_attr *attr) if (obj->maps[i].pinned && !obj->maps[i].reused) bpf_map__unpin(&obj->maps[i], NULL); - bpf_object__unload(obj); + bpf_object_unload(obj); pr_warn("failed to load object '%s'\n", obj->path); return libbpf_err(err); } +int bpf_object__load_xattr(struct bpf_object_load_attr *attr) +{ + return bpf_object_load(attr->obj, attr->log_level, attr->target_btf_path); +} + int bpf_object__load(struct bpf_object *obj) { - struct bpf_object_load_attr attr = { - .obj = obj, - }; - - return bpf_object__load_xattr(&attr); + return bpf_object_load(obj, 0, NULL); } static int make_parent_dir(const char *path) @@ -6998,8 +7591,7 @@ static int check_path(const char *path) return err; } -int bpf_program__pin_instance(struct bpf_program *prog, const char *path, - int instance) +static int bpf_program_pin_instance(struct bpf_program *prog, const char *path, int instance) { char *cp, errmsg[STRERR_BUFSIZE]; int err; @@ -7034,8 +7626,7 @@ int bpf_program__pin_instance(struct bpf_program *prog, const char *path, return 0; } -int bpf_program__unpin_instance(struct bpf_program *prog, const char *path, - int instance) +static int bpf_program_unpin_instance(struct bpf_program *prog, const char *path, int instance) { int err; @@ -7063,6 +7654,12 @@ int bpf_program__unpin_instance(struct bpf_program *prog, const char *path, return 0; } +__attribute__((alias("bpf_program_pin_instance"))) +int bpf_object__pin_instance(struct bpf_program *prog, const char *path, int instance); + +__attribute__((alias("bpf_program_unpin_instance"))) +int bpf_program__unpin_instance(struct bpf_program *prog, const char *path, int instance); + int bpf_program__pin(struct bpf_program *prog, const char *path) { int i, err; @@ -7087,7 +7684,7 @@ int bpf_program__pin(struct bpf_program *prog, const char *path) if (prog->instances.nr == 1) { /* don't create subdirs when pinning single instance */ - return bpf_program__pin_instance(prog, path, 0); + return bpf_program_pin_instance(prog, path, 0); } for (i = 0; i < prog->instances.nr; i++) { @@ -7103,7 +7700,7 @@ int bpf_program__pin(struct bpf_program *prog, const char *path) goto err_unpin; } - err = bpf_program__pin_instance(prog, buf, i); + err = bpf_program_pin_instance(prog, buf, i); if (err) goto err_unpin; } @@ -7121,7 +7718,7 @@ int bpf_program__pin(struct bpf_program *prog, const char *path) else if (len >= PATH_MAX) continue; - bpf_program__unpin_instance(prog, buf, i); + bpf_program_unpin_instance(prog, buf, i); } rmdir(path); @@ -7149,7 +7746,7 @@ int bpf_program__unpin(struct bpf_program *prog, const char *path) if (prog->instances.nr == 1) { /* don't create subdirs when pinning single instance */ - return bpf_program__unpin_instance(prog, path, 0); + return bpf_program_unpin_instance(prog, path, 0); } for (i = 0; i < prog->instances.nr; i++) { @@ -7162,7 +7759,7 @@ int bpf_program__unpin(struct bpf_program *prog, const char *path) else if (len >= PATH_MAX) return libbpf_err(-ENAMETOOLONG); - err = bpf_program__unpin_instance(prog, buf, i); + err = bpf_program_unpin_instance(prog, buf, i); if (err) return err; } @@ -7328,6 +7925,9 @@ int bpf_object__pin_maps(struct bpf_object *obj, const char *path) char *pin_path = NULL; char buf[PATH_MAX]; + if (map->skipped) + continue; + if (path) { int len; @@ -7354,7 +7954,7 @@ int bpf_object__pin_maps(struct bpf_object *obj, const char *path) return 0; err_unpin_maps: - while ((map = bpf_map__prev(map, obj))) { + while ((map = bpf_object__prev_map(obj, map))) { if (!map->pin_path) continue; @@ -7434,7 +8034,7 @@ int bpf_object__pin_programs(struct bpf_object *obj, const char *path) return 0; err_unpin_programs: - while ((prog = bpf_program__prev(prog, obj))) { + while ((prog = bpf_object__prev_program(obj, prog))) { char buf[PATH_MAX]; int len; @@ -7523,6 +8123,7 @@ static void bpf_map__destroy(struct bpf_map *map) } zfree(&map->name); + zfree(&map->real_name); zfree(&map->pin_path); if (map->fd >= 0) @@ -7541,7 +8142,7 @@ void bpf_object__close(struct bpf_object *obj) bpf_gen__free(obj->gen_loader); bpf_object__elf_finish(obj); - bpf_object__unload(obj); + bpf_object_unload(obj); btf__free(obj->btf); btf_ext__free(obj->btf_ext); @@ -7570,6 +8171,10 @@ struct bpf_object * bpf_object__next(struct bpf_object *prev) { struct bpf_object *next; + bool strict = (libbpf_mode & LIBBPF_STRICT_NO_OBJECT_LIST); + + if (strict) + return NULL; if (!prev) next = list_first_entry(&bpf_objects_list, @@ -7675,6 +8280,12 @@ __bpf_program__iter(const struct bpf_program *p, const struct bpf_object *obj, struct bpf_program * bpf_program__next(struct bpf_program *prev, const struct bpf_object *obj) +{ + return bpf_object__next_program(obj, prev); +} + +struct bpf_program * +bpf_object__next_program(const struct bpf_object *obj, struct bpf_program *prev) { struct bpf_program *prog = prev; @@ -7687,6 +8298,12 @@ bpf_program__next(struct bpf_program *prev, const struct bpf_object *obj) struct bpf_program * bpf_program__prev(struct bpf_program *next, const struct bpf_object *obj) +{ + return bpf_object__prev_program(obj, next); +} + +struct bpf_program * +bpf_object__prev_program(const struct bpf_object *obj, struct bpf_program *next) { struct bpf_program *prog = next; @@ -7758,9 +8375,11 @@ int bpf_program__set_autoload(struct bpf_program *prog, bool autoload) return 0; } +static int bpf_program_nth_fd(const struct bpf_program *prog, int n); + int bpf_program__fd(const struct bpf_program *prog) { - return bpf_program__nth_fd(prog, 0); + return bpf_program_nth_fd(prog, 0); } size_t bpf_program__size(const struct bpf_program *prog) @@ -7768,6 +8387,16 @@ size_t bpf_program__size(const struct bpf_program *prog) return prog->insns_cnt * BPF_INSN_SZ; } +const struct bpf_insn *bpf_program__insns(const struct bpf_program *prog) +{ + return prog->insns; +} + +size_t bpf_program__insn_cnt(const struct bpf_program *prog) +{ + return prog->insns_cnt; +} + int bpf_program__set_prep(struct bpf_program *prog, int nr_instances, bpf_program_prep_t prep) { @@ -7796,7 +8425,10 @@ int bpf_program__set_prep(struct bpf_program *prog, int nr_instances, return 0; } -int bpf_program__nth_fd(const struct bpf_program *prog, int n) +__attribute__((alias("bpf_program_nth_fd"))) +int bpf_program__nth_fd(const struct bpf_program *prog, int n); + +static int bpf_program_nth_fd(const struct bpf_program *prog, int n) { int fd; @@ -7875,223 +8507,193 @@ void bpf_program__set_expected_attach_type(struct bpf_program *prog, prog->expected_attach_type = type; } -#define BPF_PROG_SEC_IMPL(string, ptype, eatype, eatype_optional, \ - attachable, attach_btf) \ - { \ - .sec = string, \ - .len = sizeof(string) - 1, \ - .prog_type = ptype, \ - .expected_attach_type = eatype, \ - .is_exp_attach_type_optional = eatype_optional, \ - .is_attachable = attachable, \ - .is_attach_btf = attach_btf, \ - } +__u32 bpf_program__flags(const struct bpf_program *prog) +{ + return prog->prog_flags; +} -/* Programs that can NOT be attached. */ -#define BPF_PROG_SEC(string, ptype) BPF_PROG_SEC_IMPL(string, ptype, 0, 0, 0, 0) +int bpf_program__set_flags(struct bpf_program *prog, __u32 flags) +{ + if (prog->obj->loaded) + return libbpf_err(-EBUSY); -/* Programs that can be attached. */ -#define BPF_APROG_SEC(string, ptype, atype) \ - BPF_PROG_SEC_IMPL(string, ptype, atype, true, 1, 0) + prog->prog_flags = flags; + return 0; +} -/* Programs that must specify expected attach type at load time. */ -#define BPF_EAPROG_SEC(string, ptype, eatype) \ - BPF_PROG_SEC_IMPL(string, ptype, eatype, false, 1, 0) +__u32 bpf_program__log_level(const struct bpf_program *prog) +{ + return prog->log_level; +} -/* Programs that use BTF to identify attach point */ -#define BPF_PROG_BTF(string, ptype, eatype) \ - BPF_PROG_SEC_IMPL(string, ptype, eatype, false, 0, 1) +int bpf_program__set_log_level(struct bpf_program *prog, __u32 log_level) +{ + if (prog->obj->loaded) + return libbpf_err(-EBUSY); -/* Programs that can be attached but attach type can't be identified by section - * name. Kept for backward compatibility. - */ -#define BPF_APROG_COMPAT(string, ptype) BPF_PROG_SEC(string, ptype) + prog->log_level = log_level; + return 0; +} -#define SEC_DEF(sec_pfx, ptype, ...) { \ +const char *bpf_program__log_buf(const struct bpf_program *prog, size_t *log_size) +{ + *log_size = prog->log_size; + return prog->log_buf; +} + +int bpf_program__set_log_buf(struct bpf_program *prog, char *log_buf, size_t log_size) +{ + if (log_size && !log_buf) + return -EINVAL; + if (prog->log_size > UINT_MAX) + return -EINVAL; + if (prog->obj->loaded) + return -EBUSY; + + prog->log_buf = log_buf; + prog->log_size = log_size; + return 0; +} + +#define SEC_DEF(sec_pfx, ptype, atype, flags, ...) { \ .sec = sec_pfx, \ - .len = sizeof(sec_pfx) - 1, \ .prog_type = BPF_PROG_TYPE_##ptype, \ + .expected_attach_type = atype, \ + .cookie = (long)(flags), \ + .preload_fn = libbpf_preload_prog, \ __VA_ARGS__ \ } -static struct bpf_link *attach_kprobe(const struct bpf_sec_def *sec, - struct bpf_program *prog); -static struct bpf_link *attach_tp(const struct bpf_sec_def *sec, - struct bpf_program *prog); -static struct bpf_link *attach_raw_tp(const struct bpf_sec_def *sec, - struct bpf_program *prog); -static struct bpf_link *attach_trace(const struct bpf_sec_def *sec, - struct bpf_program *prog); -static struct bpf_link *attach_lsm(const struct bpf_sec_def *sec, - struct bpf_program *prog); -static struct bpf_link *attach_iter(const struct bpf_sec_def *sec, - struct bpf_program *prog); +static struct bpf_link *attach_kprobe(const struct bpf_program *prog, long cookie); +static struct bpf_link *attach_tp(const struct bpf_program *prog, long cookie); +static struct bpf_link *attach_raw_tp(const struct bpf_program *prog, long cookie); +static struct bpf_link *attach_trace(const struct bpf_program *prog, long cookie); +static struct bpf_link *attach_lsm(const struct bpf_program *prog, long cookie); +static struct bpf_link *attach_iter(const struct bpf_program *prog, long cookie); static const struct bpf_sec_def section_defs[] = { - BPF_PROG_SEC("socket", BPF_PROG_TYPE_SOCKET_FILTER), - BPF_EAPROG_SEC("sk_reuseport/migrate", BPF_PROG_TYPE_SK_REUSEPORT, - BPF_SK_REUSEPORT_SELECT_OR_MIGRATE), - BPF_EAPROG_SEC("sk_reuseport", BPF_PROG_TYPE_SK_REUSEPORT, - BPF_SK_REUSEPORT_SELECT), - SEC_DEF("kprobe/", KPROBE, - .attach_fn = attach_kprobe), - BPF_PROG_SEC("uprobe/", BPF_PROG_TYPE_KPROBE), - SEC_DEF("kretprobe/", KPROBE, - .attach_fn = attach_kprobe), - BPF_PROG_SEC("uretprobe/", BPF_PROG_TYPE_KPROBE), - BPF_PROG_SEC("classifier", BPF_PROG_TYPE_SCHED_CLS), - BPF_PROG_SEC("action", BPF_PROG_TYPE_SCHED_ACT), - SEC_DEF("tracepoint/", TRACEPOINT, - .attach_fn = attach_tp), - SEC_DEF("tp/", TRACEPOINT, - .attach_fn = attach_tp), - SEC_DEF("raw_tracepoint/", RAW_TRACEPOINT, - .attach_fn = attach_raw_tp), - SEC_DEF("raw_tp/", RAW_TRACEPOINT, - .attach_fn = attach_raw_tp), - SEC_DEF("tp_btf/", TRACING, - .expected_attach_type = BPF_TRACE_RAW_TP, - .is_attach_btf = true, - .attach_fn = attach_trace), - SEC_DEF("fentry/", TRACING, - .expected_attach_type = BPF_TRACE_FENTRY, - .is_attach_btf = true, - .attach_fn = attach_trace), - SEC_DEF("fmod_ret/", TRACING, - .expected_attach_type = BPF_MODIFY_RETURN, - .is_attach_btf = true, - .attach_fn = attach_trace), - SEC_DEF("fexit/", TRACING, - .expected_attach_type = BPF_TRACE_FEXIT, - .is_attach_btf = true, - .attach_fn = attach_trace), - SEC_DEF("fentry.s/", TRACING, - .expected_attach_type = BPF_TRACE_FENTRY, - .is_attach_btf = true, - .is_sleepable = true, - .attach_fn = attach_trace), - SEC_DEF("fmod_ret.s/", TRACING, - .expected_attach_type = BPF_MODIFY_RETURN, - .is_attach_btf = true, - .is_sleepable = true, - .attach_fn = attach_trace), - SEC_DEF("fexit.s/", TRACING, - .expected_attach_type = BPF_TRACE_FEXIT, - .is_attach_btf = true, - .is_sleepable = true, - .attach_fn = attach_trace), - SEC_DEF("freplace/", EXT, - .is_attach_btf = true, - .attach_fn = attach_trace), - SEC_DEF("lsm/", LSM, - .is_attach_btf = true, - .expected_attach_type = BPF_LSM_MAC, - .attach_fn = attach_lsm), - SEC_DEF("lsm.s/", LSM, - .is_attach_btf = true, - .is_sleepable = true, - .expected_attach_type = BPF_LSM_MAC, - .attach_fn = attach_lsm), - SEC_DEF("iter/", TRACING, - .expected_attach_type = BPF_TRACE_ITER, - .is_attach_btf = true, - .attach_fn = attach_iter), - SEC_DEF("syscall", SYSCALL, - .is_sleepable = true), - BPF_EAPROG_SEC("xdp_devmap/", BPF_PROG_TYPE_XDP, - BPF_XDP_DEVMAP), - BPF_EAPROG_SEC("xdp_cpumap/", BPF_PROG_TYPE_XDP, - BPF_XDP_CPUMAP), - BPF_APROG_SEC("xdp", BPF_PROG_TYPE_XDP, - BPF_XDP), - BPF_PROG_SEC("perf_event", BPF_PROG_TYPE_PERF_EVENT), - BPF_PROG_SEC("lwt_in", BPF_PROG_TYPE_LWT_IN), - BPF_PROG_SEC("lwt_out", BPF_PROG_TYPE_LWT_OUT), - BPF_PROG_SEC("lwt_xmit", BPF_PROG_TYPE_LWT_XMIT), - BPF_PROG_SEC("lwt_seg6local", BPF_PROG_TYPE_LWT_SEG6LOCAL), - BPF_APROG_SEC("cgroup_skb/ingress", BPF_PROG_TYPE_CGROUP_SKB, - BPF_CGROUP_INET_INGRESS), - BPF_APROG_SEC("cgroup_skb/egress", BPF_PROG_TYPE_CGROUP_SKB, - BPF_CGROUP_INET_EGRESS), - BPF_APROG_COMPAT("cgroup/skb", BPF_PROG_TYPE_CGROUP_SKB), - BPF_EAPROG_SEC("cgroup/sock_create", BPF_PROG_TYPE_CGROUP_SOCK, - BPF_CGROUP_INET_SOCK_CREATE), - BPF_EAPROG_SEC("cgroup/sock_release", BPF_PROG_TYPE_CGROUP_SOCK, - BPF_CGROUP_INET_SOCK_RELEASE), - BPF_APROG_SEC("cgroup/sock", BPF_PROG_TYPE_CGROUP_SOCK, - BPF_CGROUP_INET_SOCK_CREATE), - BPF_EAPROG_SEC("cgroup/post_bind4", BPF_PROG_TYPE_CGROUP_SOCK, - BPF_CGROUP_INET4_POST_BIND), - BPF_EAPROG_SEC("cgroup/post_bind6", BPF_PROG_TYPE_CGROUP_SOCK, - BPF_CGROUP_INET6_POST_BIND), - BPF_APROG_SEC("cgroup/dev", BPF_PROG_TYPE_CGROUP_DEVICE, - BPF_CGROUP_DEVICE), - BPF_APROG_SEC("sockops", BPF_PROG_TYPE_SOCK_OPS, - BPF_CGROUP_SOCK_OPS), - BPF_APROG_SEC("sk_skb/stream_parser", BPF_PROG_TYPE_SK_SKB, - BPF_SK_SKB_STREAM_PARSER), - BPF_APROG_SEC("sk_skb/stream_verdict", BPF_PROG_TYPE_SK_SKB, - BPF_SK_SKB_STREAM_VERDICT), - BPF_APROG_COMPAT("sk_skb", BPF_PROG_TYPE_SK_SKB), - BPF_APROG_SEC("sk_msg", BPF_PROG_TYPE_SK_MSG, - BPF_SK_MSG_VERDICT), - BPF_APROG_SEC("lirc_mode2", BPF_PROG_TYPE_LIRC_MODE2, - BPF_LIRC_MODE2), - BPF_APROG_SEC("flow_dissector", BPF_PROG_TYPE_FLOW_DISSECTOR, - BPF_FLOW_DISSECTOR), - BPF_EAPROG_SEC("cgroup/bind4", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, - BPF_CGROUP_INET4_BIND), - BPF_EAPROG_SEC("cgroup/bind6", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, - BPF_CGROUP_INET6_BIND), - BPF_EAPROG_SEC("cgroup/connect4", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, - BPF_CGROUP_INET4_CONNECT), - BPF_EAPROG_SEC("cgroup/connect6", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, - BPF_CGROUP_INET6_CONNECT), - BPF_EAPROG_SEC("cgroup/sendmsg4", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, - BPF_CGROUP_UDP4_SENDMSG), - BPF_EAPROG_SEC("cgroup/sendmsg6", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, - BPF_CGROUP_UDP6_SENDMSG), - BPF_EAPROG_SEC("cgroup/recvmsg4", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, - BPF_CGROUP_UDP4_RECVMSG), - BPF_EAPROG_SEC("cgroup/recvmsg6", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, - BPF_CGROUP_UDP6_RECVMSG), - BPF_EAPROG_SEC("cgroup/getpeername4", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, - BPF_CGROUP_INET4_GETPEERNAME), - BPF_EAPROG_SEC("cgroup/getpeername6", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, - BPF_CGROUP_INET6_GETPEERNAME), - BPF_EAPROG_SEC("cgroup/getsockname4", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, - BPF_CGROUP_INET4_GETSOCKNAME), - BPF_EAPROG_SEC("cgroup/getsockname6", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, - BPF_CGROUP_INET6_GETSOCKNAME), - BPF_EAPROG_SEC("cgroup/sysctl", BPF_PROG_TYPE_CGROUP_SYSCTL, - BPF_CGROUP_SYSCTL), - BPF_EAPROG_SEC("cgroup/getsockopt", BPF_PROG_TYPE_CGROUP_SOCKOPT, - BPF_CGROUP_GETSOCKOPT), - BPF_EAPROG_SEC("cgroup/setsockopt", BPF_PROG_TYPE_CGROUP_SOCKOPT, - BPF_CGROUP_SETSOCKOPT), - BPF_PROG_SEC("struct_ops", BPF_PROG_TYPE_STRUCT_OPS), - BPF_EAPROG_SEC("sk_lookup/", BPF_PROG_TYPE_SK_LOOKUP, - BPF_SK_LOOKUP), + SEC_DEF("socket", SOCKET_FILTER, 0, SEC_NONE | SEC_SLOPPY_PFX), + SEC_DEF("sk_reuseport/migrate", SK_REUSEPORT, BPF_SK_REUSEPORT_SELECT_OR_MIGRATE, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("sk_reuseport", SK_REUSEPORT, BPF_SK_REUSEPORT_SELECT, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("kprobe/", KPROBE, 0, SEC_NONE, attach_kprobe), + SEC_DEF("uprobe/", KPROBE, 0, SEC_NONE), + SEC_DEF("kretprobe/", KPROBE, 0, SEC_NONE, attach_kprobe), + SEC_DEF("uretprobe/", KPROBE, 0, SEC_NONE), + SEC_DEF("tc", SCHED_CLS, 0, SEC_NONE), + SEC_DEF("classifier", SCHED_CLS, 0, SEC_NONE | SEC_SLOPPY_PFX), + SEC_DEF("action", SCHED_ACT, 0, SEC_NONE | SEC_SLOPPY_PFX), + SEC_DEF("tracepoint/", TRACEPOINT, 0, SEC_NONE, attach_tp), + SEC_DEF("tp/", TRACEPOINT, 0, SEC_NONE, attach_tp), + SEC_DEF("raw_tracepoint/", RAW_TRACEPOINT, 0, SEC_NONE, attach_raw_tp), + SEC_DEF("raw_tp/", RAW_TRACEPOINT, 0, SEC_NONE, attach_raw_tp), + SEC_DEF("raw_tracepoint.w/", RAW_TRACEPOINT_WRITABLE, 0, SEC_NONE, attach_raw_tp), + SEC_DEF("raw_tp.w/", RAW_TRACEPOINT_WRITABLE, 0, SEC_NONE, attach_raw_tp), + SEC_DEF("tp_btf/", TRACING, BPF_TRACE_RAW_TP, SEC_ATTACH_BTF, attach_trace), + SEC_DEF("fentry/", TRACING, BPF_TRACE_FENTRY, SEC_ATTACH_BTF, attach_trace), + SEC_DEF("fmod_ret/", TRACING, BPF_MODIFY_RETURN, SEC_ATTACH_BTF, attach_trace), + SEC_DEF("fexit/", TRACING, BPF_TRACE_FEXIT, SEC_ATTACH_BTF, attach_trace), + SEC_DEF("fentry.s/", TRACING, BPF_TRACE_FENTRY, SEC_ATTACH_BTF | SEC_SLEEPABLE, attach_trace), + SEC_DEF("fmod_ret.s/", TRACING, BPF_MODIFY_RETURN, SEC_ATTACH_BTF | SEC_SLEEPABLE, attach_trace), + SEC_DEF("fexit.s/", TRACING, BPF_TRACE_FEXIT, SEC_ATTACH_BTF | SEC_SLEEPABLE, attach_trace), + SEC_DEF("freplace/", EXT, 0, SEC_ATTACH_BTF, attach_trace), + SEC_DEF("lsm/", LSM, BPF_LSM_MAC, SEC_ATTACH_BTF, attach_lsm), + SEC_DEF("lsm.s/", LSM, BPF_LSM_MAC, SEC_ATTACH_BTF | SEC_SLEEPABLE, attach_lsm), + SEC_DEF("iter/", TRACING, BPF_TRACE_ITER, SEC_ATTACH_BTF, attach_iter), + SEC_DEF("syscall", SYSCALL, 0, SEC_SLEEPABLE), + SEC_DEF("xdp_devmap/", XDP, BPF_XDP_DEVMAP, SEC_ATTACHABLE), + SEC_DEF("xdp_cpumap/", XDP, BPF_XDP_CPUMAP, SEC_ATTACHABLE), + SEC_DEF("xdp", XDP, BPF_XDP, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), + SEC_DEF("perf_event", PERF_EVENT, 0, SEC_NONE | SEC_SLOPPY_PFX), + SEC_DEF("lwt_in", LWT_IN, 0, SEC_NONE | SEC_SLOPPY_PFX), + SEC_DEF("lwt_out", LWT_OUT, 0, SEC_NONE | SEC_SLOPPY_PFX), + SEC_DEF("lwt_xmit", LWT_XMIT, 0, SEC_NONE | SEC_SLOPPY_PFX), + SEC_DEF("lwt_seg6local", LWT_SEG6LOCAL, 0, SEC_NONE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup_skb/ingress", CGROUP_SKB, BPF_CGROUP_INET_INGRESS, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), + SEC_DEF("cgroup_skb/egress", CGROUP_SKB, BPF_CGROUP_INET_EGRESS, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/skb", CGROUP_SKB, 0, SEC_NONE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/sock_create", CGROUP_SOCK, BPF_CGROUP_INET_SOCK_CREATE, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/sock_release", CGROUP_SOCK, BPF_CGROUP_INET_SOCK_RELEASE, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/sock", CGROUP_SOCK, BPF_CGROUP_INET_SOCK_CREATE, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/post_bind4", CGROUP_SOCK, BPF_CGROUP_INET4_POST_BIND, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/post_bind6", CGROUP_SOCK, BPF_CGROUP_INET6_POST_BIND, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/dev", CGROUP_DEVICE, BPF_CGROUP_DEVICE, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), + SEC_DEF("sockops", SOCK_OPS, BPF_CGROUP_SOCK_OPS, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), + SEC_DEF("sk_skb/stream_parser", SK_SKB, BPF_SK_SKB_STREAM_PARSER, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), + SEC_DEF("sk_skb/stream_verdict",SK_SKB, BPF_SK_SKB_STREAM_VERDICT, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), + SEC_DEF("sk_skb", SK_SKB, 0, SEC_NONE | SEC_SLOPPY_PFX), + SEC_DEF("sk_msg", SK_MSG, BPF_SK_MSG_VERDICT, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), + SEC_DEF("lirc_mode2", LIRC_MODE2, BPF_LIRC_MODE2, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), + SEC_DEF("flow_dissector", FLOW_DISSECTOR, BPF_FLOW_DISSECTOR, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/bind4", CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_BIND, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/bind6", CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_BIND, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/connect4", CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_CONNECT, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/connect6", CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_CONNECT, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/sendmsg4", CGROUP_SOCK_ADDR, BPF_CGROUP_UDP4_SENDMSG, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/sendmsg6", CGROUP_SOCK_ADDR, BPF_CGROUP_UDP6_SENDMSG, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/recvmsg4", CGROUP_SOCK_ADDR, BPF_CGROUP_UDP4_RECVMSG, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/recvmsg6", CGROUP_SOCK_ADDR, BPF_CGROUP_UDP6_RECVMSG, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/getpeername4", CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_GETPEERNAME, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/getpeername6", CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_GETPEERNAME, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/getsockname4", CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_GETSOCKNAME, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/getsockname6", CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_GETSOCKNAME, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/sysctl", CGROUP_SYSCTL, BPF_CGROUP_SYSCTL, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/getsockopt", CGROUP_SOCKOPT, BPF_CGROUP_GETSOCKOPT, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/setsockopt", CGROUP_SOCKOPT, BPF_CGROUP_SETSOCKOPT, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("struct_ops+", STRUCT_OPS, 0, SEC_NONE), + SEC_DEF("sk_lookup", SK_LOOKUP, BPF_SK_LOOKUP, SEC_ATTACHABLE | SEC_SLOPPY_PFX), }; -#undef BPF_PROG_SEC_IMPL -#undef BPF_PROG_SEC -#undef BPF_APROG_SEC -#undef BPF_EAPROG_SEC -#undef BPF_APROG_COMPAT -#undef SEC_DEF - #define MAX_TYPE_NAME_SIZE 32 static const struct bpf_sec_def *find_sec_def(const char *sec_name) { - int i, n = ARRAY_SIZE(section_defs); + const struct bpf_sec_def *sec_def; + enum sec_def_flags sec_flags; + int i, n = ARRAY_SIZE(section_defs), len; + bool strict = libbpf_mode & LIBBPF_STRICT_SEC_NAME; for (i = 0; i < n; i++) { - if (strncmp(sec_name, - section_defs[i].sec, section_defs[i].len)) + sec_def = §ion_defs[i]; + sec_flags = sec_def->cookie; + len = strlen(sec_def->sec); + + /* "type/" always has to have proper SEC("type/extras") form */ + if (sec_def->sec[len - 1] == '/') { + if (str_has_pfx(sec_name, sec_def->sec)) + return sec_def; continue; - return §ion_defs[i]; + } + + /* "type+" means it can be either exact SEC("type") or + * well-formed SEC("type/extras") with proper '/' separator + */ + if (sec_def->sec[len - 1] == '+') { + len--; + /* not even a prefix */ + if (strncmp(sec_name, sec_def->sec, len) != 0) + continue; + /* exact match or has '/' separator */ + if (sec_name[len] == '\0' || sec_name[len] == '/') + return sec_def; + continue; + } + + /* SEC_SLOPPY_PFX definitions are allowed to be just prefix + * matches, unless strict section name mode + * (LIBBPF_STRICT_SEC_NAME) is enabled, in which case the + * match has to be exact. + */ + if ((sec_flags & SEC_SLOPPY_PFX) && !strict) { + if (str_has_pfx(sec_name, sec_def->sec)) + return sec_def; + continue; + } + + /* Definitions not marked SEC_SLOPPY_PFX (e.g., + * SEC("syscall")) are exact matches in both modes. + */ + if (strcmp(sec_name, sec_def->sec) == 0) + return sec_def; } return NULL; } @@ -8108,8 +8710,15 @@ static char *libbpf_get_type_names(bool attach_type) buf[0] = '\0'; /* Forge string buf with all available names */ for (i = 0; i < ARRAY_SIZE(section_defs); i++) { - if (attach_type && !section_defs[i].is_attachable) - continue; + const struct bpf_sec_def *sec_def = §ion_defs[i]; + + if (attach_type) { + if (sec_def->preload_fn != libbpf_preload_prog) + continue; + + if (!(sec_def->cookie & SEC_ATTACHABLE)) + continue; + } if (strlen(buf) + strlen(section_defs[i].sec) + 2 > len) { free(buf); @@ -8168,7 +8777,7 @@ static struct bpf_map *find_struct_ops_map_by_offset(struct bpf_object *obj, /* Collect the reloc from ELF and populate the st_ops->progs[] */ static int bpf_object__collect_st_ops_relos(struct bpf_object *obj, - GElf_Shdr *shdr, Elf_Data *data) + Elf64_Shdr *shdr, Elf_Data *data) { const struct btf_member *member; struct bpf_struct_ops *st_ops; @@ -8176,58 +8785,58 @@ static int bpf_object__collect_st_ops_relos(struct bpf_object *obj, unsigned int shdr_idx; const struct btf *btf; struct bpf_map *map; - Elf_Data *symbols; unsigned int moff, insn_idx; const char *name; __u32 member_idx; - GElf_Sym sym; - GElf_Rel rel; + Elf64_Sym *sym; + Elf64_Rel *rel; int i, nrels; - symbols = obj->efile.symbols; btf = obj->btf; nrels = shdr->sh_size / shdr->sh_entsize; for (i = 0; i < nrels; i++) { - if (!gelf_getrel(data, i, &rel)) { + rel = elf_rel_by_idx(data, i); + if (!rel) { pr_warn("struct_ops reloc: failed to get %d reloc\n", i); return -LIBBPF_ERRNO__FORMAT; } - if (!gelf_getsym(symbols, GELF_R_SYM(rel.r_info), &sym)) { + sym = elf_sym_by_idx(obj, ELF64_R_SYM(rel->r_info)); + if (!sym) { pr_warn("struct_ops reloc: symbol %zx not found\n", - (size_t)GELF_R_SYM(rel.r_info)); + (size_t)ELF64_R_SYM(rel->r_info)); return -LIBBPF_ERRNO__FORMAT; } - name = elf_sym_str(obj, sym.st_name) ?: ""; - map = find_struct_ops_map_by_offset(obj, rel.r_offset); + name = elf_sym_str(obj, sym->st_name) ?: ""; + map = find_struct_ops_map_by_offset(obj, rel->r_offset); if (!map) { - pr_warn("struct_ops reloc: cannot find map at rel.r_offset %zu\n", - (size_t)rel.r_offset); + pr_warn("struct_ops reloc: cannot find map at rel->r_offset %zu\n", + (size_t)rel->r_offset); return -EINVAL; } - moff = rel.r_offset - map->sec_offset; - shdr_idx = sym.st_shndx; + moff = rel->r_offset - map->sec_offset; + shdr_idx = sym->st_shndx; st_ops = map->st_ops; - pr_debug("struct_ops reloc %s: for %lld value %lld shdr_idx %u rel.r_offset %zu map->sec_offset %zu name %d (\'%s\')\n", + pr_debug("struct_ops reloc %s: for %lld value %lld shdr_idx %u rel->r_offset %zu map->sec_offset %zu name %d (\'%s\')\n", map->name, - (long long)(rel.r_info >> 32), - (long long)sym.st_value, - shdr_idx, (size_t)rel.r_offset, - map->sec_offset, sym.st_name, name); + (long long)(rel->r_info >> 32), + (long long)sym->st_value, + shdr_idx, (size_t)rel->r_offset, + map->sec_offset, sym->st_name, name); if (shdr_idx >= SHN_LORESERVE) { - pr_warn("struct_ops reloc %s: rel.r_offset %zu shdr_idx %u unsupported non-static function\n", - map->name, (size_t)rel.r_offset, shdr_idx); + pr_warn("struct_ops reloc %s: rel->r_offset %zu shdr_idx %u unsupported non-static function\n", + map->name, (size_t)rel->r_offset, shdr_idx); return -LIBBPF_ERRNO__RELOC; } - if (sym.st_value % BPF_INSN_SZ) { + if (sym->st_value % BPF_INSN_SZ) { pr_warn("struct_ops reloc %s: invalid target program offset %llu\n", - map->name, (unsigned long long)sym.st_value); + map->name, (unsigned long long)sym->st_value); return -LIBBPF_ERRNO__FORMAT; } - insn_idx = sym.st_value / BPF_INSN_SZ; + insn_idx = sym->st_value / BPF_INSN_SZ; member = find_member_by_offset(st_ops->type, moff * 8); if (!member) { @@ -8251,35 +8860,37 @@ static int bpf_object__collect_st_ops_relos(struct bpf_object *obj, return -EINVAL; } - if (prog->type == BPF_PROG_TYPE_UNSPEC) { - const struct bpf_sec_def *sec_def; + /* prevent the use of BPF prog with invalid type */ + if (prog->type != BPF_PROG_TYPE_STRUCT_OPS) { + pr_warn("struct_ops reloc %s: prog %s is not struct_ops BPF program\n", + map->name, prog->name); + return -EINVAL; + } - sec_def = find_sec_def(prog->sec_name); - if (sec_def && - sec_def->prog_type != BPF_PROG_TYPE_STRUCT_OPS) { - /* for pr_warn */ - prog->type = sec_def->prog_type; - goto invalid_prog; - } - - prog->type = BPF_PROG_TYPE_STRUCT_OPS; + /* if we haven't yet processed this BPF program, record proper + * attach_btf_id and member_idx + */ + if (!prog->attach_btf_id) { prog->attach_btf_id = st_ops->type_id; prog->expected_attach_type = member_idx; - } else if (prog->type != BPF_PROG_TYPE_STRUCT_OPS || - prog->attach_btf_id != st_ops->type_id || - prog->expected_attach_type != member_idx) { - goto invalid_prog; } + + /* struct_ops BPF prog can be re-used between multiple + * .struct_ops as long as it's the same struct_ops struct + * definition and the same function pointer field + */ + if (prog->attach_btf_id != st_ops->type_id || + prog->expected_attach_type != member_idx) { + pr_warn("struct_ops reloc %s: cannot use prog %s in sec %s with type %u attach_btf_id %u expected_attach_type %u for func ptr %s\n", + map->name, prog->name, prog->sec_name, prog->type, + prog->attach_btf_id, prog->expected_attach_type, name); + return -EINVAL; + } + st_ops->progs[member_idx] = prog; } return 0; - -invalid_prog: - pr_warn("struct_ops reloc %s: cannot use prog %s in sec %s with type %u attach_btf_id %u expected_attach_type %u for func ptr %s\n", - map->name, prog->name, prog->sec_name, prog->type, - prog->attach_btf_id, prog->expected_attach_type, name); - return -EINVAL; } #define BTF_TRACE_PREFIX "btf_trace_" @@ -8359,28 +8970,27 @@ int libbpf_find_vmlinux_btf_id(const char *name, static int libbpf_find_prog_btf_id(const char *name, __u32 attach_prog_fd) { - struct bpf_prog_info_linear *info_linear; - struct bpf_prog_info *info; + struct bpf_prog_info info = {}; + __u32 info_len = sizeof(info); struct btf *btf; int err; - info_linear = bpf_program__get_prog_info_linear(attach_prog_fd, 0); - err = libbpf_get_error(info_linear); + err = bpf_obj_get_info_by_fd(attach_prog_fd, &info, &info_len); if (err) { - pr_warn("failed get_prog_info_linear for FD %d\n", - attach_prog_fd); + pr_warn("failed bpf_obj_get_info_by_fd for FD %d: %d\n", + attach_prog_fd, err); return err; } err = -EINVAL; - info = &info_linear->info; - if (!info->btf_id) { + if (!info.btf_id) { pr_warn("The target program doesn't have BTF\n"); goto out; } - btf = btf__load_from_kernel_by_id(info->btf_id); - if (libbpf_get_error(btf)) { - pr_warn("Failed to get BTF of the program\n"); + btf = btf__load_from_kernel_by_id(info.btf_id); + err = libbpf_get_error(btf); + if (err) { + pr_warn("Failed to get BTF %d of the program: %d\n", info.btf_id, err); goto out; } err = btf__find_by_name_kind(btf, name, BTF_KIND_FUNC); @@ -8390,7 +9000,6 @@ static int libbpf_find_prog_btf_id(const char *name, __u32 attach_prog_fd) goto out; } out: - free(info_linear); return err; } @@ -8431,32 +9040,12 @@ static int find_kernel_btf_id(struct bpf_object *obj, const char *attach_name, return -ESRCH; } -static int libbpf_find_attach_btf_id(struct bpf_program *prog, int *btf_obj_fd, int *btf_type_id) +static int libbpf_find_attach_btf_id(struct bpf_program *prog, const char *attach_name, + int *btf_obj_fd, int *btf_type_id) { enum bpf_attach_type attach_type = prog->expected_attach_type; __u32 attach_prog_fd = prog->attach_prog_fd; - const char *name = prog->sec_name, *attach_name; - const struct bpf_sec_def *sec = NULL; - int i, err = 0; - - if (!name) - return -EINVAL; - - for (i = 0; i < ARRAY_SIZE(section_defs); i++) { - if (!section_defs[i].is_attach_btf) - continue; - if (strncmp(name, section_defs[i].sec, section_defs[i].len)) - continue; - - sec = §ion_defs[i]; - break; - } - - if (!sec) { - pr_warn("failed to identify BTF ID based on ELF section name '%s'\n", name); - return -ESRCH; - } - attach_name = name + sec->len; + int err = 0; /* BPF program's BTF ID */ if (attach_prog_fd) { @@ -8490,27 +9079,30 @@ int libbpf_attach_type_by_name(const char *name, enum bpf_attach_type *attach_type) { char *type_names; - int i; + const struct bpf_sec_def *sec_def; if (!name) return libbpf_err(-EINVAL); - for (i = 0; i < ARRAY_SIZE(section_defs); i++) { - if (strncmp(name, section_defs[i].sec, section_defs[i].len)) - continue; - if (!section_defs[i].is_attachable) - return libbpf_err(-EINVAL); - *attach_type = section_defs[i].expected_attach_type; - return 0; - } - pr_debug("failed to guess attach type based on ELF section name '%s'\n", name); - type_names = libbpf_get_type_names(true); - if (type_names != NULL) { - pr_debug("attachable section(type) names are:%s\n", type_names); - free(type_names); + sec_def = find_sec_def(name); + if (!sec_def) { + pr_debug("failed to guess attach type based on ELF section name '%s'\n", name); + type_names = libbpf_get_type_names(true); + if (type_names != NULL) { + pr_debug("attachable section(type) names are:%s\n", type_names); + free(type_names); + } + + return libbpf_err(-EINVAL); } - return libbpf_err(-EINVAL); + if (sec_def->preload_fn != libbpf_preload_prog) + return libbpf_err(-EINVAL); + if (!(sec_def->cookie & SEC_ATTACHABLE)) + return libbpf_err(-EINVAL); + + *attach_type = sec_def->expected_attach_type; + return 0; } int bpf_map__fd(const struct bpf_map *map) @@ -8523,9 +9115,30 @@ const struct bpf_map_def *bpf_map__def(const struct bpf_map *map) return map ? &map->def : libbpf_err_ptr(-EINVAL); } +static bool map_uses_real_name(const struct bpf_map *map) +{ + /* Since libbpf started to support custom .data.* and .rodata.* maps, + * their user-visible name differs from kernel-visible name. Users see + * such map's corresponding ELF section name as a map name. + * This check distinguishes .data/.rodata from .data.* and .rodata.* + * maps to know which name has to be returned to the user. + */ + if (map->libbpf_type == LIBBPF_MAP_DATA && strcmp(map->real_name, DATA_SEC) != 0) + return true; + if (map->libbpf_type == LIBBPF_MAP_RODATA && strcmp(map->real_name, RODATA_SEC) != 0) + return true; + return false; +} + const char *bpf_map__name(const struct bpf_map *map) { - return map ? map->name : NULL; + if (!map) + return NULL; + + if (map_uses_real_name(map)) + return map->real_name; + + return map->name; } enum bpf_map_type bpf_map__type(const struct bpf_map *map) @@ -8554,6 +9167,19 @@ int bpf_map__set_map_flags(struct bpf_map *map, __u32 flags) return 0; } +__u64 bpf_map__map_extra(const struct bpf_map *map) +{ + return map->map_extra; +} + +int bpf_map__set_map_extra(struct bpf_map *map, __u64 map_extra) +{ + if (map->fd >= 0) + return libbpf_err(-EBUSY); + map->map_extra = map_extra; + return 0; +} + __u32 bpf_map__numa_node(const struct bpf_map *map) { return map->numa_node; @@ -8710,6 +9336,12 @@ __bpf_map__iter(const struct bpf_map *m, const struct bpf_object *obj, int i) struct bpf_map * bpf_map__next(const struct bpf_map *prev, const struct bpf_object *obj) +{ + return bpf_object__next_map(obj, prev); +} + +struct bpf_map * +bpf_object__next_map(const struct bpf_object *obj, const struct bpf_map *prev) { if (prev == NULL) return obj->maps; @@ -8719,6 +9351,12 @@ bpf_map__next(const struct bpf_map *prev, const struct bpf_object *obj) struct bpf_map * bpf_map__prev(const struct bpf_map *next, const struct bpf_object *obj) +{ + return bpf_object__prev_map(obj, next); +} + +struct bpf_map * +bpf_object__prev_map(const struct bpf_object *obj, const struct bpf_map *next) { if (next == NULL) { if (!obj->nr_maps) @@ -8735,7 +9373,22 @@ bpf_object__find_map_by_name(const struct bpf_object *obj, const char *name) struct bpf_map *pos; bpf_object__for_each_map(pos, obj) { - if (pos->name && !strcmp(pos->name, name)) + /* if it's a special internal map name (which always starts + * with dot) then check if that special name matches the + * real map name (ELF section name) + */ + if (name[0] == '.') { + if (pos->real_name && strcmp(pos->real_name, name) == 0) + return pos; + continue; + } + /* otherwise map name has to be an exact match */ + if (map_uses_real_name(pos)) { + if (strcmp(pos->real_name, name) == 0) + return pos; + continue; + } + if (strcmp(pos->name, name) == 0) return pos; } return errno = ENOENT, NULL; @@ -8769,21 +9422,12 @@ long libbpf_get_error(const void *ptr) return -errno; } -int bpf_prog_load(const char *file, enum bpf_prog_type type, - struct bpf_object **pobj, int *prog_fd) -{ - struct bpf_prog_load_attr attr; - - memset(&attr, 0, sizeof(struct bpf_prog_load_attr)); - attr.file = file; - attr.prog_type = type; - attr.expected_attach_type = 0; - - return bpf_prog_load_xattr(&attr, pobj, prog_fd); -} - +__attribute__((alias("bpf_prog_load_xattr2"))) int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, - struct bpf_object **pobj, int *prog_fd) + struct bpf_object **pobj, int *prog_fd); + +static int bpf_prog_load_xattr2(const struct bpf_prog_load_attr *attr, + struct bpf_object **pobj, int *prog_fd) { struct bpf_object_open_attr open_attr = {}; struct bpf_program *prog, *first_prog = NULL; @@ -8854,6 +9498,20 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, return 0; } +COMPAT_VERSION(bpf_prog_load_deprecated, bpf_prog_load, LIBBPF_0.0.1) +int bpf_prog_load_deprecated(const char *file, enum bpf_prog_type type, + struct bpf_object **pobj, int *prog_fd) +{ + struct bpf_prog_load_attr attr; + + memset(&attr, 0, sizeof(struct bpf_prog_load_attr)); + attr.file = file; + attr.prog_type = type; + attr.expected_attach_type = 0; + + return bpf_prog_load_xattr2(&attr, pobj, prog_fd); +} + struct bpf_link { int (*detach)(struct bpf_link *link); void (*dealloc)(struct bpf_link *link); @@ -9000,8 +9658,15 @@ int bpf_link__unpin(struct bpf_link *link) struct bpf_link_perf { struct bpf_link link; int perf_event_fd; + /* legacy kprobe support: keep track of probe identifier and type */ + char *legacy_probe_name; + bool legacy_is_kprobe; + bool legacy_is_retprobe; }; +static int remove_kprobe_event_legacy(const char *probe_name, bool retprobe); +static int remove_uprobe_event_legacy(const char *probe_name, bool retprobe); + static int bpf_link_perf_detach(struct bpf_link *link) { struct bpf_link_perf *perf_link = container_of(link, struct bpf_link_perf, link); @@ -9014,17 +9679,29 @@ static int bpf_link_perf_detach(struct bpf_link *link) close(perf_link->perf_event_fd); close(link->fd); - return libbpf_err(err); + /* legacy uprobe/kprobe needs to be removed after perf event fd closure */ + if (perf_link->legacy_probe_name) { + if (perf_link->legacy_is_kprobe) { + err = remove_kprobe_event_legacy(perf_link->legacy_probe_name, + perf_link->legacy_is_retprobe); + } else { + err = remove_uprobe_event_legacy(perf_link->legacy_probe_name, + perf_link->legacy_is_retprobe); + } + } + + return err; } static void bpf_link_perf_dealloc(struct bpf_link *link) { struct bpf_link_perf *perf_link = container_of(link, struct bpf_link_perf, link); + free(perf_link->legacy_probe_name); free(perf_link); } -struct bpf_link *bpf_program__attach_perf_event_opts(struct bpf_program *prog, int pfd, +struct bpf_link *bpf_program__attach_perf_event_opts(const struct bpf_program *prog, int pfd, const struct bpf_perf_event_opts *opts) { char errmsg[STRERR_BUFSIZE]; @@ -9099,7 +9776,7 @@ struct bpf_link *bpf_program__attach_perf_event_opts(struct bpf_program *prog, i return libbpf_err_ptr(err); } -struct bpf_link *bpf_program__attach_perf_event(struct bpf_program *prog, int pfd) +struct bpf_link *bpf_program__attach_perf_event(const struct bpf_program *prog, int pfd) { return bpf_program__attach_perf_event_opts(prog, pfd, NULL); } @@ -9216,16 +9893,113 @@ static int perf_event_open_probe(bool uprobe, bool retprobe, const char *name, return pfd; } +static int append_to_file(const char *file, const char *fmt, ...) +{ + int fd, n, err = 0; + va_list ap; + + fd = open(file, O_WRONLY | O_APPEND | O_CLOEXEC, 0); + if (fd < 0) + return -errno; + + va_start(ap, fmt); + n = vdprintf(fd, fmt, ap); + va_end(ap); + + if (n < 0) + err = -errno; + + close(fd); + return err; +} + +static void gen_kprobe_legacy_event_name(char *buf, size_t buf_sz, + const char *kfunc_name, size_t offset) +{ + static int index = 0; + + snprintf(buf, buf_sz, "libbpf_%u_%s_0x%zx_%d", getpid(), kfunc_name, offset, + __sync_fetch_and_add(&index, 1)); +} + +static int add_kprobe_event_legacy(const char *probe_name, bool retprobe, + const char *kfunc_name, size_t offset) +{ + const char *file = "/sys/kernel/debug/tracing/kprobe_events"; + + return append_to_file(file, "%c:%s/%s %s+0x%zx", + retprobe ? 'r' : 'p', + retprobe ? "kretprobes" : "kprobes", + probe_name, kfunc_name, offset); +} + +static int remove_kprobe_event_legacy(const char *probe_name, bool retprobe) +{ + const char *file = "/sys/kernel/debug/tracing/kprobe_events"; + + return append_to_file(file, "-:%s/%s", retprobe ? "kretprobes" : "kprobes", probe_name); +} + +static int determine_kprobe_perf_type_legacy(const char *probe_name, bool retprobe) +{ + char file[256]; + + snprintf(file, sizeof(file), + "/sys/kernel/debug/tracing/events/%s/%s/id", + retprobe ? "kretprobes" : "kprobes", probe_name); + + return parse_uint_from_file(file, "%d\n"); +} + +static int perf_event_kprobe_open_legacy(const char *probe_name, bool retprobe, + const char *kfunc_name, size_t offset, int pid) +{ + struct perf_event_attr attr = {}; + char errmsg[STRERR_BUFSIZE]; + int type, pfd, err; + + err = add_kprobe_event_legacy(probe_name, retprobe, kfunc_name, offset); + if (err < 0) { + pr_warn("failed to add legacy kprobe event for '%s+0x%zx': %s\n", + kfunc_name, offset, + libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + return err; + } + type = determine_kprobe_perf_type_legacy(probe_name, retprobe); + if (type < 0) { + pr_warn("failed to determine legacy kprobe event id for '%s+0x%zx': %s\n", + kfunc_name, offset, + libbpf_strerror_r(type, errmsg, sizeof(errmsg))); + return type; + } + attr.size = sizeof(attr); + attr.config = type; + attr.type = PERF_TYPE_TRACEPOINT; + + pfd = syscall(__NR_perf_event_open, &attr, + pid < 0 ? -1 : pid, /* pid */ + pid == -1 ? 0 : -1, /* cpu */ + -1 /* group_fd */, PERF_FLAG_FD_CLOEXEC); + if (pfd < 0) { + err = -errno; + pr_warn("legacy kprobe perf_event_open() failed: %s\n", + libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + return err; + } + return pfd; +} + struct bpf_link * -bpf_program__attach_kprobe_opts(struct bpf_program *prog, +bpf_program__attach_kprobe_opts(const struct bpf_program *prog, const char *func_name, const struct bpf_kprobe_opts *opts) { DECLARE_LIBBPF_OPTS(bpf_perf_event_opts, pe_opts); char errmsg[STRERR_BUFSIZE]; + char *legacy_probe = NULL; struct bpf_link *link; - unsigned long offset; - bool retprobe; + size_t offset; + bool retprobe, legacy; int pfd, err; if (!OPTS_VALID(opts, bpf_kprobe_opts)) @@ -9235,27 +10009,57 @@ bpf_program__attach_kprobe_opts(struct bpf_program *prog, offset = OPTS_GET(opts, offset, 0); pe_opts.bpf_cookie = OPTS_GET(opts, bpf_cookie, 0); - pfd = perf_event_open_probe(false /* uprobe */, retprobe, func_name, - offset, -1 /* pid */, 0 /* ref_ctr_off */); + legacy = determine_kprobe_perf_type() < 0; + if (!legacy) { + pfd = perf_event_open_probe(false /* uprobe */, retprobe, + func_name, offset, + -1 /* pid */, 0 /* ref_ctr_off */); + } else { + char probe_name[256]; + + gen_kprobe_legacy_event_name(probe_name, sizeof(probe_name), + func_name, offset); + + legacy_probe = strdup(probe_name); + if (!legacy_probe) + return libbpf_err_ptr(-ENOMEM); + + pfd = perf_event_kprobe_open_legacy(legacy_probe, retprobe, func_name, + offset, -1 /* pid */); + } if (pfd < 0) { - pr_warn("prog '%s': failed to create %s '%s' perf event: %s\n", - prog->name, retprobe ? "kretprobe" : "kprobe", func_name, - libbpf_strerror_r(pfd, errmsg, sizeof(errmsg))); - return libbpf_err_ptr(pfd); + err = -errno; + pr_warn("prog '%s': failed to create %s '%s+0x%zx' perf event: %s\n", + prog->name, retprobe ? "kretprobe" : "kprobe", + func_name, offset, + libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + goto err_out; } link = bpf_program__attach_perf_event_opts(prog, pfd, &pe_opts); err = libbpf_get_error(link); if (err) { close(pfd); - pr_warn("prog '%s': failed to attach to %s '%s': %s\n", - prog->name, retprobe ? "kretprobe" : "kprobe", func_name, + pr_warn("prog '%s': failed to attach to %s '%s+0x%zx': %s\n", + prog->name, retprobe ? "kretprobe" : "kprobe", + func_name, offset, libbpf_strerror_r(err, errmsg, sizeof(errmsg))); - return libbpf_err_ptr(err); + goto err_out; } + if (legacy) { + struct bpf_link_perf *perf_link = container_of(link, struct bpf_link_perf, link); + + perf_link->legacy_probe_name = legacy_probe; + perf_link->legacy_is_kprobe = true; + perf_link->legacy_is_retprobe = retprobe; + } + return link; +err_out: + free(legacy_probe); + return libbpf_err_ptr(err); } -struct bpf_link *bpf_program__attach_kprobe(struct bpf_program *prog, +struct bpf_link *bpf_program__attach_kprobe(const struct bpf_program *prog, bool retprobe, const char *func_name) { @@ -9266,8 +10070,7 @@ struct bpf_link *bpf_program__attach_kprobe(struct bpf_program *prog, return bpf_program__attach_kprobe_opts(prog, func_name, &opts); } -static struct bpf_link *attach_kprobe(const struct bpf_sec_def *sec, - struct bpf_program *prog) +static struct bpf_link *attach_kprobe(const struct bpf_program *prog, long cookie) { DECLARE_LIBBPF_OPTS(bpf_kprobe_opts, opts); unsigned long offset = 0; @@ -9276,8 +10079,11 @@ static struct bpf_link *attach_kprobe(const struct bpf_sec_def *sec, char *func; int n, err; - func_name = prog->sec_name + sec->len; - opts.retprobe = strcmp(sec->sec, "kretprobe/") == 0; + opts.retprobe = str_has_pfx(prog->sec_name, "kretprobe/"); + if (opts.retprobe) + func_name = prog->sec_name + sizeof("kretprobe/") - 1; + else + func_name = prog->sec_name + sizeof("kprobe/") - 1; n = sscanf(func_name, "%m[a-zA-Z0-9_.]+%li", &func, &offset); if (n < 1) { @@ -9298,17 +10104,96 @@ static struct bpf_link *attach_kprobe(const struct bpf_sec_def *sec, return link; } +static void gen_uprobe_legacy_event_name(char *buf, size_t buf_sz, + const char *binary_path, uint64_t offset) +{ + int i; + + snprintf(buf, buf_sz, "libbpf_%u_%s_0x%zx", getpid(), binary_path, (size_t)offset); + + /* sanitize binary_path in the probe name */ + for (i = 0; buf[i]; i++) { + if (!isalnum(buf[i])) + buf[i] = '_'; + } +} + +static inline int add_uprobe_event_legacy(const char *probe_name, bool retprobe, + const char *binary_path, size_t offset) +{ + const char *file = "/sys/kernel/debug/tracing/uprobe_events"; + + return append_to_file(file, "%c:%s/%s %s:0x%zx", + retprobe ? 'r' : 'p', + retprobe ? "uretprobes" : "uprobes", + probe_name, binary_path, offset); +} + +static inline int remove_uprobe_event_legacy(const char *probe_name, bool retprobe) +{ + const char *file = "/sys/kernel/debug/tracing/uprobe_events"; + + return append_to_file(file, "-:%s/%s", retprobe ? "uretprobes" : "uprobes", probe_name); +} + +static int determine_uprobe_perf_type_legacy(const char *probe_name, bool retprobe) +{ + char file[512]; + + snprintf(file, sizeof(file), + "/sys/kernel/debug/tracing/events/%s/%s/id", + retprobe ? "uretprobes" : "uprobes", probe_name); + + return parse_uint_from_file(file, "%d\n"); +} + +static int perf_event_uprobe_open_legacy(const char *probe_name, bool retprobe, + const char *binary_path, size_t offset, int pid) +{ + struct perf_event_attr attr; + int type, pfd, err; + + err = add_uprobe_event_legacy(probe_name, retprobe, binary_path, offset); + if (err < 0) { + pr_warn("failed to add legacy uprobe event for %s:0x%zx: %d\n", + binary_path, (size_t)offset, err); + return err; + } + type = determine_uprobe_perf_type_legacy(probe_name, retprobe); + if (type < 0) { + pr_warn("failed to determine legacy uprobe event id for %s:0x%zx: %d\n", + binary_path, offset, err); + return type; + } + + memset(&attr, 0, sizeof(attr)); + attr.size = sizeof(attr); + attr.config = type; + attr.type = PERF_TYPE_TRACEPOINT; + + pfd = syscall(__NR_perf_event_open, &attr, + pid < 0 ? -1 : pid, /* pid */ + pid == -1 ? 0 : -1, /* cpu */ + -1 /* group_fd */, PERF_FLAG_FD_CLOEXEC); + if (pfd < 0) { + err = -errno; + pr_warn("legacy uprobe perf_event_open() failed: %d\n", err); + return err; + } + return pfd; +} + LIBBPF_API struct bpf_link * -bpf_program__attach_uprobe_opts(struct bpf_program *prog, pid_t pid, +bpf_program__attach_uprobe_opts(const struct bpf_program *prog, pid_t pid, const char *binary_path, size_t func_offset, const struct bpf_uprobe_opts *opts) { DECLARE_LIBBPF_OPTS(bpf_perf_event_opts, pe_opts); - char errmsg[STRERR_BUFSIZE]; + char errmsg[STRERR_BUFSIZE], *legacy_probe = NULL; struct bpf_link *link; size_t ref_ctr_off; int pfd, err; - bool retprobe; + bool retprobe, legacy; if (!OPTS_VALID(opts, bpf_uprobe_opts)) return libbpf_err_ptr(-EINVAL); @@ -9317,15 +10202,35 @@ bpf_program__attach_uprobe_opts(struct bpf_program *prog, pid_t pid, ref_ctr_off = OPTS_GET(opts, ref_ctr_offset, 0); pe_opts.bpf_cookie = OPTS_GET(opts, bpf_cookie, 0); - pfd = perf_event_open_probe(true /* uprobe */, retprobe, binary_path, - func_offset, pid, ref_ctr_off); + legacy = determine_uprobe_perf_type() < 0; + if (!legacy) { + pfd = perf_event_open_probe(true /* uprobe */, retprobe, binary_path, + func_offset, pid, ref_ctr_off); + } else { + char probe_name[512]; + + if (ref_ctr_off) + return libbpf_err_ptr(-EINVAL); + + gen_uprobe_legacy_event_name(probe_name, sizeof(probe_name), + binary_path, func_offset); + + legacy_probe = strdup(probe_name); + if (!legacy_probe) + return libbpf_err_ptr(-ENOMEM); + + pfd = perf_event_uprobe_open_legacy(legacy_probe, retprobe, + binary_path, func_offset, pid); + } if (pfd < 0) { + err = -errno; pr_warn("prog '%s': failed to create %s '%s:0x%zx' perf event: %s\n", prog->name, retprobe ? "uretprobe" : "uprobe", binary_path, func_offset, - libbpf_strerror_r(pfd, errmsg, sizeof(errmsg))); - return libbpf_err_ptr(pfd); + libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + goto err_out; } + link = bpf_program__attach_perf_event_opts(prog, pfd, &pe_opts); err = libbpf_get_error(link); if (err) { @@ -9334,12 +10239,23 @@ bpf_program__attach_uprobe_opts(struct bpf_program *prog, pid_t pid, prog->name, retprobe ? "uretprobe" : "uprobe", binary_path, func_offset, libbpf_strerror_r(err, errmsg, sizeof(errmsg))); - return libbpf_err_ptr(err); + goto err_out; + } + if (legacy) { + struct bpf_link_perf *perf_link = container_of(link, struct bpf_link_perf, link); + + perf_link->legacy_probe_name = legacy_probe; + perf_link->legacy_is_kprobe = false; + perf_link->legacy_is_retprobe = retprobe; } return link; +err_out: + free(legacy_probe); + return libbpf_err_ptr(err); + } -struct bpf_link *bpf_program__attach_uprobe(struct bpf_program *prog, +struct bpf_link *bpf_program__attach_uprobe(const struct bpf_program *prog, bool retprobe, pid_t pid, const char *binary_path, size_t func_offset) @@ -9399,7 +10315,7 @@ static int perf_event_open_tracepoint(const char *tp_category, return pfd; } -struct bpf_link *bpf_program__attach_tracepoint_opts(struct bpf_program *prog, +struct bpf_link *bpf_program__attach_tracepoint_opts(const struct bpf_program *prog, const char *tp_category, const char *tp_name, const struct bpf_tracepoint_opts *opts) @@ -9433,15 +10349,14 @@ struct bpf_link *bpf_program__attach_tracepoint_opts(struct bpf_program *prog, return link; } -struct bpf_link *bpf_program__attach_tracepoint(struct bpf_program *prog, +struct bpf_link *bpf_program__attach_tracepoint(const struct bpf_program *prog, const char *tp_category, const char *tp_name) { return bpf_program__attach_tracepoint_opts(prog, tp_category, tp_name, NULL); } -static struct bpf_link *attach_tp(const struct bpf_sec_def *sec, - struct bpf_program *prog) +static struct bpf_link *attach_tp(const struct bpf_program *prog, long cookie) { char *sec_name, *tp_cat, *tp_name; struct bpf_link *link; @@ -9450,8 +10365,11 @@ static struct bpf_link *attach_tp(const struct bpf_sec_def *sec, if (!sec_name) return libbpf_err_ptr(-ENOMEM); - /* extract "tp//" */ - tp_cat = sec_name + sec->len; + /* extract "tp//" or "tracepoint//" */ + if (str_has_pfx(prog->sec_name, "tp/")) + tp_cat = sec_name + sizeof("tp/") - 1; + else + tp_cat = sec_name + sizeof("tracepoint/") - 1; tp_name = strchr(tp_cat, '/'); if (!tp_name) { free(sec_name); @@ -9465,7 +10383,7 @@ static struct bpf_link *attach_tp(const struct bpf_sec_def *sec, return link; } -struct bpf_link *bpf_program__attach_raw_tracepoint(struct bpf_program *prog, +struct bpf_link *bpf_program__attach_raw_tracepoint(const struct bpf_program *prog, const char *tp_name) { char errmsg[STRERR_BUFSIZE]; @@ -9495,16 +10413,34 @@ struct bpf_link *bpf_program__attach_raw_tracepoint(struct bpf_program *prog, return link; } -static struct bpf_link *attach_raw_tp(const struct bpf_sec_def *sec, - struct bpf_program *prog) +static struct bpf_link *attach_raw_tp(const struct bpf_program *prog, long cookie) { - const char *tp_name = prog->sec_name + sec->len; + static const char *const prefixes[] = { + "raw_tp/", + "raw_tracepoint/", + "raw_tp.w/", + "raw_tracepoint.w/", + }; + size_t i; + const char *tp_name = NULL; + + for (i = 0; i < ARRAY_SIZE(prefixes); i++) { + if (str_has_pfx(prog->sec_name, prefixes[i])) { + tp_name = prog->sec_name + strlen(prefixes[i]); + break; + } + } + if (!tp_name) { + pr_warn("prog '%s': invalid section name '%s'\n", + prog->name, prog->sec_name); + return libbpf_err_ptr(-EINVAL); + } return bpf_program__attach_raw_tracepoint(prog, tp_name); } /* Common logic for all BPF program types that attach to a btf_id */ -static struct bpf_link *bpf_program__attach_btf_id(struct bpf_program *prog) +static struct bpf_link *bpf_program__attach_btf_id(const struct bpf_program *prog) { char errmsg[STRERR_BUFSIZE]; struct bpf_link *link; @@ -9533,30 +10469,28 @@ static struct bpf_link *bpf_program__attach_btf_id(struct bpf_program *prog) return (struct bpf_link *)link; } -struct bpf_link *bpf_program__attach_trace(struct bpf_program *prog) +struct bpf_link *bpf_program__attach_trace(const struct bpf_program *prog) { return bpf_program__attach_btf_id(prog); } -struct bpf_link *bpf_program__attach_lsm(struct bpf_program *prog) +struct bpf_link *bpf_program__attach_lsm(const struct bpf_program *prog) { return bpf_program__attach_btf_id(prog); } -static struct bpf_link *attach_trace(const struct bpf_sec_def *sec, - struct bpf_program *prog) +static struct bpf_link *attach_trace(const struct bpf_program *prog, long cookie) { return bpf_program__attach_trace(prog); } -static struct bpf_link *attach_lsm(const struct bpf_sec_def *sec, - struct bpf_program *prog) +static struct bpf_link *attach_lsm(const struct bpf_program *prog, long cookie) { return bpf_program__attach_lsm(prog); } static struct bpf_link * -bpf_program__attach_fd(struct bpf_program *prog, int target_fd, int btf_id, +bpf_program__attach_fd(const struct bpf_program *prog, int target_fd, int btf_id, const char *target_name) { DECLARE_LIBBPF_OPTS(bpf_link_create_opts, opts, @@ -9592,24 +10526,24 @@ bpf_program__attach_fd(struct bpf_program *prog, int target_fd, int btf_id, } struct bpf_link * -bpf_program__attach_cgroup(struct bpf_program *prog, int cgroup_fd) +bpf_program__attach_cgroup(const struct bpf_program *prog, int cgroup_fd) { return bpf_program__attach_fd(prog, cgroup_fd, 0, "cgroup"); } struct bpf_link * -bpf_program__attach_netns(struct bpf_program *prog, int netns_fd) +bpf_program__attach_netns(const struct bpf_program *prog, int netns_fd) { return bpf_program__attach_fd(prog, netns_fd, 0, "netns"); } -struct bpf_link *bpf_program__attach_xdp(struct bpf_program *prog, int ifindex) +struct bpf_link *bpf_program__attach_xdp(const struct bpf_program *prog, int ifindex) { /* target_fd/target_ifindex use the same field in LINK_CREATE */ return bpf_program__attach_fd(prog, ifindex, 0, "xdp"); } -struct bpf_link *bpf_program__attach_freplace(struct bpf_program *prog, +struct bpf_link *bpf_program__attach_freplace(const struct bpf_program *prog, int target_fd, const char *attach_func_name) { @@ -9642,7 +10576,7 @@ struct bpf_link *bpf_program__attach_freplace(struct bpf_program *prog, } struct bpf_link * -bpf_program__attach_iter(struct bpf_program *prog, +bpf_program__attach_iter(const struct bpf_program *prog, const struct bpf_iter_attach_opts *opts) { DECLARE_LIBBPF_OPTS(bpf_link_create_opts, link_create_opts); @@ -9681,21 +10615,17 @@ bpf_program__attach_iter(struct bpf_program *prog, return link; } -static struct bpf_link *attach_iter(const struct bpf_sec_def *sec, - struct bpf_program *prog) +static struct bpf_link *attach_iter(const struct bpf_program *prog, long cookie) { return bpf_program__attach_iter(prog, NULL); } -struct bpf_link *bpf_program__attach(struct bpf_program *prog) +struct bpf_link *bpf_program__attach(const struct bpf_program *prog) { - const struct bpf_sec_def *sec_def; - - sec_def = find_sec_def(prog->sec_name); - if (!sec_def || !sec_def->attach_fn) + if (!prog->sec_def || !prog->sec_def->attach_fn) return libbpf_err_ptr(-ESRCH); - return sec_def->attach_fn(sec_def, prog); + return prog->sec_def->attach_fn(prog, prog->sec_def->cookie); } static int bpf_link__detach_struct_ops(struct bpf_link *link) @@ -9708,7 +10638,7 @@ static int bpf_link__detach_struct_ops(struct bpf_link *link) return 0; } -struct bpf_link *bpf_map__attach_struct_ops(struct bpf_map *map) +struct bpf_link *bpf_map__attach_struct_ops(const struct bpf_map *map) { struct bpf_struct_ops *st_ops; struct bpf_link *link; @@ -9749,10 +10679,10 @@ struct bpf_link *bpf_map__attach_struct_ops(struct bpf_map *map) return link; } -enum bpf_perf_event_ret -bpf_perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size, - void **copy_mem, size_t *copy_size, - bpf_perf_event_print_t fn, void *private_data) +static enum bpf_perf_event_ret +perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size, + void **copy_mem, size_t *copy_size, + bpf_perf_event_print_t fn, void *private_data) { struct perf_event_mmap_page *header = mmap_mem; __u64 data_head = ring_buffer_read_head(header); @@ -9797,6 +10727,12 @@ bpf_perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size, return libbpf_err(ret); } +__attribute__((alias("perf_event_read_simple"))) +enum bpf_perf_event_ret +bpf_perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size, + void **copy_mem, size_t *copy_size, + bpf_perf_event_print_t fn, void *private_data); + struct perf_buffer; struct perf_buffer_params { @@ -9930,11 +10866,18 @@ perf_buffer__open_cpu_buf(struct perf_buffer *pb, struct perf_event_attr *attr, static struct perf_buffer *__perf_buffer__new(int map_fd, size_t page_cnt, struct perf_buffer_params *p); -struct perf_buffer *perf_buffer__new(int map_fd, size_t page_cnt, - const struct perf_buffer_opts *opts) +DEFAULT_VERSION(perf_buffer__new_v0_6_0, perf_buffer__new, LIBBPF_0.6.0) +struct perf_buffer *perf_buffer__new_v0_6_0(int map_fd, size_t page_cnt, + perf_buffer_sample_fn sample_cb, + perf_buffer_lost_fn lost_cb, + void *ctx, + const struct perf_buffer_opts *opts) { struct perf_buffer_params p = {}; - struct perf_event_attr attr = { 0, }; + struct perf_event_attr attr = {}; + + if (!OPTS_VALID(opts, perf_buffer_opts)) + return libbpf_err_ptr(-EINVAL); attr.config = PERF_COUNT_SW_BPF_OUTPUT; attr.type = PERF_TYPE_SOFTWARE; @@ -9943,29 +10886,62 @@ struct perf_buffer *perf_buffer__new(int map_fd, size_t page_cnt, attr.wakeup_events = 1; p.attr = &attr; - p.sample_cb = opts ? opts->sample_cb : NULL; - p.lost_cb = opts ? opts->lost_cb : NULL; - p.ctx = opts ? opts->ctx : NULL; + p.sample_cb = sample_cb; + p.lost_cb = lost_cb; + p.ctx = ctx; return libbpf_ptr(__perf_buffer__new(map_fd, page_cnt, &p)); } -struct perf_buffer * -perf_buffer__new_raw(int map_fd, size_t page_cnt, - const struct perf_buffer_raw_opts *opts) +COMPAT_VERSION(perf_buffer__new_deprecated, perf_buffer__new, LIBBPF_0.0.4) +struct perf_buffer *perf_buffer__new_deprecated(int map_fd, size_t page_cnt, + const struct perf_buffer_opts *opts) +{ + return perf_buffer__new_v0_6_0(map_fd, page_cnt, + opts ? opts->sample_cb : NULL, + opts ? opts->lost_cb : NULL, + opts ? opts->ctx : NULL, + NULL); +} + +DEFAULT_VERSION(perf_buffer__new_raw_v0_6_0, perf_buffer__new_raw, LIBBPF_0.6.0) +struct perf_buffer *perf_buffer__new_raw_v0_6_0(int map_fd, size_t page_cnt, + struct perf_event_attr *attr, + perf_buffer_event_fn event_cb, void *ctx, + const struct perf_buffer_raw_opts *opts) { struct perf_buffer_params p = {}; - p.attr = opts->attr; - p.event_cb = opts->event_cb; - p.ctx = opts->ctx; - p.cpu_cnt = opts->cpu_cnt; - p.cpus = opts->cpus; - p.map_keys = opts->map_keys; + if (page_cnt == 0 || !attr) + return libbpf_err_ptr(-EINVAL); + + if (!OPTS_VALID(opts, perf_buffer_raw_opts)) + return libbpf_err_ptr(-EINVAL); + + p.attr = attr; + p.event_cb = event_cb; + p.ctx = ctx; + p.cpu_cnt = OPTS_GET(opts, cpu_cnt, 0); + p.cpus = OPTS_GET(opts, cpus, NULL); + p.map_keys = OPTS_GET(opts, map_keys, NULL); return libbpf_ptr(__perf_buffer__new(map_fd, page_cnt, &p)); } +COMPAT_VERSION(perf_buffer__new_raw_deprecated, perf_buffer__new_raw, LIBBPF_0.0.4) +struct perf_buffer *perf_buffer__new_raw_deprecated(int map_fd, size_t page_cnt, + const struct perf_buffer_raw_opts *opts) +{ + LIBBPF_OPTS(perf_buffer_raw_opts, inner_opts, + .cpu_cnt = opts->cpu_cnt, + .cpus = opts->cpus, + .map_keys = opts->map_keys, + ); + + return perf_buffer__new_raw_v0_6_0(map_fd, page_cnt, opts->attr, + opts->event_cb, opts->ctx, &inner_opts); +} + static struct perf_buffer *__perf_buffer__new(int map_fd, size_t page_cnt, struct perf_buffer_params *p) { @@ -10165,10 +11141,10 @@ static int perf_buffer__process_records(struct perf_buffer *pb, { enum bpf_perf_event_ret ret; - ret = bpf_perf_event_read_simple(cpu_buf->base, pb->mmap_size, - pb->page_size, &cpu_buf->buf, - &cpu_buf->buf_size, - perf_buffer__process_record, cpu_buf); + ret = perf_event_read_simple(cpu_buf->base, pb->mmap_size, + pb->page_size, &cpu_buf->buf, + &cpu_buf->buf_size, + perf_buffer__process_record, cpu_buf); if (ret != LIBBPF_PERF_EVENT_CONT) return ret; return 0; @@ -10521,18 +11497,29 @@ int bpf_program__set_attach_target(struct bpf_program *prog, { int btf_obj_fd = 0, btf_id = 0, err; - if (!prog || attach_prog_fd < 0 || !attach_func_name) + if (!prog || attach_prog_fd < 0) return libbpf_err(-EINVAL); if (prog->obj->loaded) return libbpf_err(-EINVAL); + if (attach_prog_fd && !attach_func_name) { + /* remember attach_prog_fd and let bpf_program__load() find + * BTF ID during the program load + */ + prog->attach_prog_fd = attach_prog_fd; + return 0; + } + if (attach_prog_fd) { btf_id = libbpf_find_prog_btf_id(attach_func_name, attach_prog_fd); if (btf_id < 0) return libbpf_err(btf_id); } else { + if (!attach_func_name) + return libbpf_err(-EINVAL); + /* load btf_vmlinux, if not yet */ err = bpf_object__load_vmlinux_btf(prog->obj, true); if (err) @@ -10605,7 +11592,7 @@ int parse_cpu_mask_file(const char *fcpu, bool **mask, int *mask_sz) int fd, err = 0, len; char buf[128]; - fd = open(fcpu, O_RDONLY); + fd = open(fcpu, O_RDONLY | O_CLOEXEC); if (fd < 0) { err = -errno; pr_warn("Failed to open cpu mask file %s: %d\n", fcpu, err); @@ -10774,16 +11761,15 @@ int bpf_object__attach_skeleton(struct bpf_object_skeleton *s) for (i = 0; i < s->prog_cnt; i++) { struct bpf_program *prog = *s->progs[i].prog; struct bpf_link **link = s->progs[i].link; - const struct bpf_sec_def *sec_def; if (!prog->load) continue; - sec_def = find_sec_def(prog->sec_name); - if (!sec_def || !sec_def->attach_fn) + /* auto-attaching not supported for this program */ + if (!prog->sec_def || !prog->sec_def->attach_fn) continue; - *link = sec_def->attach_fn(sec_def, prog); + *link = bpf_program__attach(prog); err = libbpf_get_error(*link); if (err) { pr_warn("failed to auto-attach program '%s': %d\n", diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index f177d897c5..8b9bc5e90c 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -24,6 +24,10 @@ extern "C" { #endif +LIBBPF_API __u32 libbpf_major_version(void); +LIBBPF_API __u32 libbpf_minor_version(void); +LIBBPF_API const char *libbpf_version_string(void); + enum libbpf_errno { __LIBBPF_ERRNO__START = 4000, @@ -83,12 +87,15 @@ struct bpf_object_open_opts { * Non-relocatable instructions are replaced with invalid ones to * prevent accidental errors. * */ + LIBBPF_DEPRECATED_SINCE(0, 6, "field has no effect") bool relaxed_core_relocs; /* maps that set the 'pinning' attribute in their definition will have * their pin_path attribute set to a file in this directory, and be * auto-pinned to that path on load; defaults to "/sys/fs/bpf". */ const char *pin_root_path; + + LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_program__set_attach_target() on each individual bpf_program") __u32 attach_prog_fd; /* Additional kernel config content that augments and overrides * system Kconfig for CONFIG_xxx externs. @@ -101,12 +108,73 @@ struct bpf_object_open_opts { * struct_ops, etc) will need actual kernel BTF at /sys/kernel/btf/vmlinux. */ const char *btf_custom_path; + /* Pointer to a buffer for storing kernel logs for applicable BPF + * commands. Valid kernel_log_size has to be specified as well and are + * passed-through to bpf() syscall. Keep in mind that kernel might + * fail operation with -ENOSPC error if provided buffer is too small + * to contain entire log output. + * See the comment below for kernel_log_level for interaction between + * log_buf and log_level settings. + * + * If specified, this log buffer will be passed for: + * - each BPF progral load (BPF_PROG_LOAD) attempt, unless overriden + * with bpf_program__set_log() on per-program level, to get + * BPF verifier log output. + * - during BPF object's BTF load into kernel (BPF_BTF_LOAD) to get + * BTF sanity checking log. + * + * Each BPF command (BPF_BTF_LOAD or BPF_PROG_LOAD) will overwrite + * previous contents, so if you need more fine-grained control, set + * per-program buffer with bpf_program__set_log_buf() to preserve each + * individual program's verification log. Keep using kernel_log_buf + * for BTF verification log, if necessary. + */ + char *kernel_log_buf; + size_t kernel_log_size; + /* + * Log level can be set independently from log buffer. Log_level=0 + * means that libbpf will attempt loading BTF or program without any + * logging requested, but will retry with either its own or custom log + * buffer, if provided, and log_level=1 on any error. + * And vice versa, setting log_level>0 will request BTF or prog + * loading with verbose log from the first attempt (and as such also + * for successfully loaded BTF or program), and the actual log buffer + * could be either libbpf's own auto-allocated log buffer, if + * kernel_log_buffer is NULL, or user-provided custom kernel_log_buf. + * If user didn't provide custom log buffer, libbpf will emit captured + * logs through its print callback. + */ + __u32 kernel_log_level; + + size_t :0; }; -#define bpf_object_open_opts__last_field btf_custom_path +#define bpf_object_open_opts__last_field kernel_log_level LIBBPF_API struct bpf_object *bpf_object__open(const char *path); + +/** + * @brief **bpf_object__open_file()** creates a bpf_object by opening + * the BPF ELF object file pointed to by the passed path and loading it + * into memory. + * @param path BPF object file path + * @param opts options for how to load the bpf object, this parameter is + * optional and can be set to NULL + * @return pointer to the new bpf_object; or NULL is returned on error, + * error code is stored in errno + */ LIBBPF_API struct bpf_object * bpf_object__open_file(const char *path, const struct bpf_object_open_opts *opts); + +/** + * @brief **bpf_object__open_mem()** creates a bpf_object by reading + * the BPF objects raw bytes from a memory buffer containing a valid + * BPF ELF object file. + * @param obj_buf pointer to the buffer containing ELF file bytes + * @param obj_buf_sz number of bytes in the buffer + * @param opts options for how to load the bpf object + * @return pointer to the new bpf_object; or NULL is returned on error, + * error code is stored in errno + */ LIBBPF_API struct bpf_object * bpf_object__open_mem(const void *obj_buf, size_t obj_buf_sz, const struct bpf_object_open_opts *opts); @@ -146,7 +214,9 @@ struct bpf_object_load_attr { /* Load/unload object into/from kernel */ LIBBPF_API int bpf_object__load(struct bpf_object *obj); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_object__load() instead") LIBBPF_API int bpf_object__load_xattr(struct bpf_object_load_attr *attr); +LIBBPF_DEPRECATED_SINCE(0, 6, "bpf_object__unload() is deprecated, use bpf_object__close() instead") LIBBPF_API int bpf_object__unload(struct bpf_object *obj); LIBBPF_API const char *bpf_object__name(const struct bpf_object *obj); @@ -157,6 +227,7 @@ struct btf; LIBBPF_API struct btf *bpf_object__btf(const struct bpf_object *obj); LIBBPF_API int bpf_object__btf_fd(const struct bpf_object *obj); +LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_object__find_program_by_name() instead") LIBBPF_API struct bpf_program * bpf_object__find_program_by_title(const struct bpf_object *obj, const char *title); @@ -164,7 +235,8 @@ LIBBPF_API struct bpf_program * bpf_object__find_program_by_name(const struct bpf_object *obj, const char *name); -LIBBPF_API struct bpf_object *bpf_object__next(struct bpf_object *prev); +LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "track bpf_objects in application code instead") +struct bpf_object *bpf_object__next(struct bpf_object *prev); #define bpf_object__for_each_safe(pos, tmp) \ for ((pos) = bpf_object__next(NULL), \ (tmp) = bpf_object__next(pos); \ @@ -186,16 +258,22 @@ LIBBPF_API int libbpf_find_vmlinux_btf_id(const char *name, /* Accessors of bpf_program */ struct bpf_program; -LIBBPF_API struct bpf_program *bpf_program__next(struct bpf_program *prog, - const struct bpf_object *obj); +LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_object__next_program() instead") +struct bpf_program *bpf_program__next(struct bpf_program *prog, + const struct bpf_object *obj); +LIBBPF_API struct bpf_program * +bpf_object__next_program(const struct bpf_object *obj, struct bpf_program *prog); -#define bpf_object__for_each_program(pos, obj) \ - for ((pos) = bpf_program__next(NULL, (obj)); \ - (pos) != NULL; \ - (pos) = bpf_program__next((pos), (obj))) +#define bpf_object__for_each_program(pos, obj) \ + for ((pos) = bpf_object__next_program((obj), NULL); \ + (pos) != NULL; \ + (pos) = bpf_object__next_program((obj), (pos))) -LIBBPF_API struct bpf_program *bpf_program__prev(struct bpf_program *prog, - const struct bpf_object *obj); +LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_object__prev_program() instead") +struct bpf_program *bpf_program__prev(struct bpf_program *prog, + const struct bpf_object *obj); +LIBBPF_API struct bpf_program * +bpf_object__prev_program(const struct bpf_object *obj, struct bpf_program *prog); typedef void (*bpf_program_clear_priv_t)(struct bpf_program *, void *); @@ -214,18 +292,79 @@ LIBBPF_API bool bpf_program__autoload(const struct bpf_program *prog); LIBBPF_API int bpf_program__set_autoload(struct bpf_program *prog, bool autoload); /* returns program size in bytes */ +LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_program__insn_cnt() instead") LIBBPF_API size_t bpf_program__size(const struct bpf_program *prog); -LIBBPF_API int bpf_program__load(struct bpf_program *prog, char *license, - __u32 kern_version); +struct bpf_insn; + +/** + * @brief **bpf_program__insns()** gives read-only access to BPF program's + * underlying BPF instructions. + * @param prog BPF program for which to return instructions + * @return a pointer to an array of BPF instructions that belong to the + * specified BPF program + * + * Returned pointer is always valid and not NULL. Number of `struct bpf_insn` + * pointed to can be fetched using **bpf_program__insn_cnt()** API. + * + * Keep in mind, libbpf can modify and append/delete BPF program's + * instructions as it processes BPF object file and prepares everything for + * uploading into the kernel. So depending on the point in BPF object + * lifetime, **bpf_program__insns()** can return different sets of + * instructions. As an example, during BPF object load phase BPF program + * instructions will be CO-RE-relocated, BPF subprograms instructions will be + * appended, ldimm64 instructions will have FDs embedded, etc. So instructions + * returned before **bpf_object__load()** and after it might be quite + * different. + */ +LIBBPF_API const struct bpf_insn *bpf_program__insns(const struct bpf_program *prog); +/** + * @brief **bpf_program__insn_cnt()** returns number of `struct bpf_insn`'s + * that form specified BPF program. + * @param prog BPF program for which to return number of BPF instructions + * + * See **bpf_program__insns()** documentation for notes on how libbpf can + * change instructions and their count during different phases of + * **bpf_object** lifetime. + */ +LIBBPF_API size_t bpf_program__insn_cnt(const struct bpf_program *prog); + +LIBBPF_DEPRECATED_SINCE(0, 6, "use bpf_object__load() instead") +LIBBPF_API int bpf_program__load(struct bpf_program *prog, const char *license, __u32 kern_version); LIBBPF_API int bpf_program__fd(const struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 7, "multi-instance bpf_program support is deprecated") LIBBPF_API int bpf_program__pin_instance(struct bpf_program *prog, const char *path, int instance); +LIBBPF_DEPRECATED_SINCE(0, 7, "multi-instance bpf_program support is deprecated") LIBBPF_API int bpf_program__unpin_instance(struct bpf_program *prog, const char *path, int instance); + +/** + * @brief **bpf_program__pin()** pins the BPF program to a file + * in the BPF FS specified by a path. This increments the programs + * reference count, allowing it to stay loaded after the process + * which loaded it has exited. + * + * @param prog BPF program to pin, must already be loaded + * @param path file path in a BPF file system + * @return 0, on success; negative error code, otherwise + */ LIBBPF_API int bpf_program__pin(struct bpf_program *prog, const char *path); + +/** + * @brief **bpf_program__unpin()** unpins the BPF program from a file + * in the BPFFS specified by a path. This decrements the programs + * reference count. + * + * The file pinning the BPF program can also be unlinked by a different + * process in which case this function will return an error. + * + * @param prog BPF program to unpin + * @param path file path to the pin in a BPF file system + * @return 0, on success; negative error code, otherwise + */ LIBBPF_API int bpf_program__unpin(struct bpf_program *prog, const char *path); LIBBPF_API void bpf_program__unload(struct bpf_program *prog); @@ -243,7 +382,7 @@ LIBBPF_API int bpf_link__detach(struct bpf_link *link); LIBBPF_API int bpf_link__destroy(struct bpf_link *link); LIBBPF_API struct bpf_link * -bpf_program__attach(struct bpf_program *prog); +bpf_program__attach(const struct bpf_program *prog); struct bpf_perf_event_opts { /* size of this struct, for forward/backward compatiblity */ @@ -254,10 +393,10 @@ struct bpf_perf_event_opts { #define bpf_perf_event_opts__last_field bpf_cookie LIBBPF_API struct bpf_link * -bpf_program__attach_perf_event(struct bpf_program *prog, int pfd); +bpf_program__attach_perf_event(const struct bpf_program *prog, int pfd); LIBBPF_API struct bpf_link * -bpf_program__attach_perf_event_opts(struct bpf_program *prog, int pfd, +bpf_program__attach_perf_event_opts(const struct bpf_program *prog, int pfd, const struct bpf_perf_event_opts *opts); struct bpf_kprobe_opts { @@ -266,7 +405,7 @@ struct bpf_kprobe_opts { /* custom user-provided value fetchable through bpf_get_attach_cookie() */ __u64 bpf_cookie; /* function's offset to install kprobe to */ - unsigned long offset; + size_t offset; /* kprobe is return probe */ bool retprobe; size_t :0; @@ -274,10 +413,10 @@ struct bpf_kprobe_opts { #define bpf_kprobe_opts__last_field retprobe LIBBPF_API struct bpf_link * -bpf_program__attach_kprobe(struct bpf_program *prog, bool retprobe, +bpf_program__attach_kprobe(const struct bpf_program *prog, bool retprobe, const char *func_name); LIBBPF_API struct bpf_link * -bpf_program__attach_kprobe_opts(struct bpf_program *prog, +bpf_program__attach_kprobe_opts(const struct bpf_program *prog, const char *func_name, const struct bpf_kprobe_opts *opts); @@ -296,12 +435,43 @@ struct bpf_uprobe_opts { }; #define bpf_uprobe_opts__last_field retprobe +/** + * @brief **bpf_program__attach_uprobe()** attaches a BPF program + * to the userspace function which is found by binary path and + * offset. You can optionally specify a particular proccess to attach + * to. You can also optionally attach the program to the function + * exit instead of entry. + * + * @param prog BPF program to attach + * @param retprobe Attach to function exit + * @param pid Process ID to attach the uprobe to, 0 for self (own process), + * -1 for all processes + * @param binary_path Path to binary that contains the function symbol + * @param func_offset Offset within the binary of the function symbol + * @return Reference to the newly created BPF link; or NULL is returned on error, + * error code is stored in errno + */ LIBBPF_API struct bpf_link * -bpf_program__attach_uprobe(struct bpf_program *prog, bool retprobe, +bpf_program__attach_uprobe(const struct bpf_program *prog, bool retprobe, pid_t pid, const char *binary_path, size_t func_offset); + +/** + * @brief **bpf_program__attach_uprobe_opts()** is just like + * bpf_program__attach_uprobe() except with a options struct + * for various configurations. + * + * @param prog BPF program to attach + * @param pid Process ID to attach the uprobe to, 0 for self (own process), + * -1 for all processes + * @param binary_path Path to binary that contains the function symbol + * @param func_offset Offset within the binary of the function symbol + * @param opts Options for altering program attachment + * @return Reference to the newly created BPF link; or NULL is returned on error, + * error code is stored in errno + */ LIBBPF_API struct bpf_link * -bpf_program__attach_uprobe_opts(struct bpf_program *prog, pid_t pid, +bpf_program__attach_uprobe_opts(const struct bpf_program *prog, pid_t pid, const char *binary_path, size_t func_offset, const struct bpf_uprobe_opts *opts); @@ -314,35 +484,35 @@ struct bpf_tracepoint_opts { #define bpf_tracepoint_opts__last_field bpf_cookie LIBBPF_API struct bpf_link * -bpf_program__attach_tracepoint(struct bpf_program *prog, +bpf_program__attach_tracepoint(const struct bpf_program *prog, const char *tp_category, const char *tp_name); LIBBPF_API struct bpf_link * -bpf_program__attach_tracepoint_opts(struct bpf_program *prog, +bpf_program__attach_tracepoint_opts(const struct bpf_program *prog, const char *tp_category, const char *tp_name, const struct bpf_tracepoint_opts *opts); LIBBPF_API struct bpf_link * -bpf_program__attach_raw_tracepoint(struct bpf_program *prog, +bpf_program__attach_raw_tracepoint(const struct bpf_program *prog, const char *tp_name); LIBBPF_API struct bpf_link * -bpf_program__attach_trace(struct bpf_program *prog); +bpf_program__attach_trace(const struct bpf_program *prog); LIBBPF_API struct bpf_link * -bpf_program__attach_lsm(struct bpf_program *prog); +bpf_program__attach_lsm(const struct bpf_program *prog); LIBBPF_API struct bpf_link * -bpf_program__attach_cgroup(struct bpf_program *prog, int cgroup_fd); +bpf_program__attach_cgroup(const struct bpf_program *prog, int cgroup_fd); LIBBPF_API struct bpf_link * -bpf_program__attach_netns(struct bpf_program *prog, int netns_fd); +bpf_program__attach_netns(const struct bpf_program *prog, int netns_fd); LIBBPF_API struct bpf_link * -bpf_program__attach_xdp(struct bpf_program *prog, int ifindex); +bpf_program__attach_xdp(const struct bpf_program *prog, int ifindex); LIBBPF_API struct bpf_link * -bpf_program__attach_freplace(struct bpf_program *prog, +bpf_program__attach_freplace(const struct bpf_program *prog, int target_fd, const char *attach_func_name); struct bpf_map; -LIBBPF_API struct bpf_link *bpf_map__attach_struct_ops(struct bpf_map *map); +LIBBPF_API struct bpf_link *bpf_map__attach_struct_ops(const struct bpf_map *map); struct bpf_iter_attach_opts { size_t sz; /* size of this struct for forward/backward compatibility */ @@ -352,11 +522,9 @@ struct bpf_iter_attach_opts { #define bpf_iter_attach_opts__last_field link_info_len LIBBPF_API struct bpf_link * -bpf_program__attach_iter(struct bpf_program *prog, +bpf_program__attach_iter(const struct bpf_program *prog, const struct bpf_iter_attach_opts *opts); -struct bpf_insn; - /* * Libbpf allows callers to adjust BPF programs before being loaded * into kernel. One program in an object file can be transformed into @@ -385,7 +553,6 @@ struct bpf_insn; * one instance. In this case bpf_program__fd(prog) is equal to * bpf_program__nth_fd(prog, 0). */ - struct bpf_prog_prep_result { /* * If not NULL, load new instruction array. @@ -414,9 +581,11 @@ typedef int (*bpf_program_prep_t)(struct bpf_program *prog, int n, struct bpf_insn *insns, int insns_cnt, struct bpf_prog_prep_result *res); +LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_program__insns() for getting bpf_program instructions") LIBBPF_API int bpf_program__set_prep(struct bpf_program *prog, int nr_instance, bpf_program_prep_t prep); +LIBBPF_DEPRECATED_SINCE(0, 7, "multi-instance bpf_program support is deprecated") LIBBPF_API int bpf_program__nth_fd(const struct bpf_program *prog, int n); /* @@ -446,6 +615,18 @@ LIBBPF_API void bpf_program__set_expected_attach_type(struct bpf_program *prog, enum bpf_attach_type type); +LIBBPF_API __u32 bpf_program__flags(const struct bpf_program *prog); +LIBBPF_API int bpf_program__set_flags(struct bpf_program *prog, __u32 flags); + +/* Per-program log level and log buffer getters/setters. + * See bpf_object_open_opts comments regarding log_level and log_buf + * interactions. + */ +LIBBPF_API __u32 bpf_program__log_level(const struct bpf_program *prog); +LIBBPF_API int bpf_program__set_log_level(struct bpf_program *prog, __u32 log_level); +LIBBPF_API const char *bpf_program__log_buf(const struct bpf_program *prog, size_t *log_size); +LIBBPF_API int bpf_program__set_log_buf(struct bpf_program *prog, char *log_buf, size_t log_size); + LIBBPF_API int bpf_program__set_attach_target(struct bpf_program *prog, int attach_prog_fd, const char *attach_func_name); @@ -478,9 +659,13 @@ struct bpf_map_def { unsigned int map_flags; }; -/* - * The 'struct bpf_map' in include/linux/bpf.h is internal to the kernel, - * so no need to worry about a name clash. +/** + * @brief **bpf_object__find_map_by_name()** returns BPF map of + * the given name, if it exists within the passed BPF object + * @param obj BPF object + * @param name name of the BPF map + * @return BPF map instance, if such map exists within the BPF object; + * or NULL otherwise. */ LIBBPF_API struct bpf_map * bpf_object__find_map_by_name(const struct bpf_object *obj, const char *name); @@ -492,21 +677,32 @@ bpf_object__find_map_fd_by_name(const struct bpf_object *obj, const char *name); * Get bpf_map through the offset of corresponding struct bpf_map_def * in the BPF object file. */ -LIBBPF_API struct bpf_map * +LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_object__find_map_by_name() instead") +struct bpf_map * bpf_object__find_map_by_offset(struct bpf_object *obj, size_t offset); +LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_object__next_map() instead") +struct bpf_map *bpf_map__next(const struct bpf_map *map, const struct bpf_object *obj); LIBBPF_API struct bpf_map * -bpf_map__next(const struct bpf_map *map, const struct bpf_object *obj); +bpf_object__next_map(const struct bpf_object *obj, const struct bpf_map *map); + #define bpf_object__for_each_map(pos, obj) \ - for ((pos) = bpf_map__next(NULL, (obj)); \ + for ((pos) = bpf_object__next_map((obj), NULL); \ (pos) != NULL; \ - (pos) = bpf_map__next((pos), (obj))) + (pos) = bpf_object__next_map((obj), (pos))) #define bpf_map__for_each bpf_object__for_each_map +LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_object__prev_map() instead") +struct bpf_map *bpf_map__prev(const struct bpf_map *map, const struct bpf_object *obj); LIBBPF_API struct bpf_map * -bpf_map__prev(const struct bpf_map *map, const struct bpf_object *obj); +bpf_object__prev_map(const struct bpf_object *obj, const struct bpf_map *map); -/* get/set map FD */ +/** + * @brief **bpf_map__fd()** gets the file descriptor of the passed + * BPF map + * @param map the BPF map instance + * @return the file descriptor; or -EINVAL in case of an error + */ LIBBPF_API int bpf_map__fd(const struct bpf_map *map); LIBBPF_API int bpf_map__reuse_fd(struct bpf_map *map, int fd); /* get map definition */ @@ -538,6 +734,9 @@ LIBBPF_API __u32 bpf_map__btf_value_type_id(const struct bpf_map *map); /* get/set map if_index */ LIBBPF_API __u32 bpf_map__ifindex(const struct bpf_map *map); LIBBPF_API int bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex); +/* get/set map map_extra flags */ +LIBBPF_API __u64 bpf_map__map_extra(const struct bpf_map *map); +LIBBPF_API int bpf_map__set_map_extra(struct bpf_map *map, __u64 map_extra); typedef void (*bpf_map_clear_priv_t)(struct bpf_map *, void *); LIBBPF_API int bpf_map__set_priv(struct bpf_map *map, void *priv, @@ -546,7 +745,16 @@ LIBBPF_API void *bpf_map__priv(const struct bpf_map *map); LIBBPF_API int bpf_map__set_initial_value(struct bpf_map *map, const void *data, size_t size); LIBBPF_API const void *bpf_map__initial_value(struct bpf_map *map, size_t *psize); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_map__type() instead") LIBBPF_API bool bpf_map__is_offload_neutral(const struct bpf_map *map); + +/** + * @brief **bpf_map__is_internal()** tells the caller whether or not the + * passed map is a special map created by libbpf automatically for things like + * global variables, __ksym externs, Kconfig values, etc + * @param map the bpf_map + * @return true, if the map is an internal map; false, otherwise + */ LIBBPF_API bool bpf_map__is_internal(const struct bpf_map *map); LIBBPF_API int bpf_map__set_pin_path(struct bpf_map *map, const char *path); LIBBPF_API const char *bpf_map__get_pin_path(const struct bpf_map *map); @@ -558,6 +766,38 @@ LIBBPF_API int bpf_map__unpin(struct bpf_map *map, const char *path); LIBBPF_API int bpf_map__set_inner_map_fd(struct bpf_map *map, int fd); LIBBPF_API struct bpf_map *bpf_map__inner_map(struct bpf_map *map); +/** + * @brief **libbpf_get_error()** extracts the error code from the passed + * pointer + * @param ptr pointer returned from libbpf API function + * @return error code; or 0 if no error occured + * + * Many libbpf API functions which return pointers have logic to encode error + * codes as pointers, and do not return NULL. Meaning **libbpf_get_error()** + * should be used on the return value from these functions immediately after + * calling the API function, with no intervening calls that could clobber the + * `errno` variable. Consult the individual functions documentation to verify + * if this logic applies should be used. + * + * For these API functions, if `libbpf_set_strict_mode(LIBBPF_STRICT_CLEAN_PTRS)` + * is enabled, NULL is returned on error instead. + * + * If ptr is NULL, then errno should be already set by the failing + * API, because libbpf never returns NULL on success and it now always + * sets errno on error. + * + * Example usage: + * + * struct perf_buffer *pb; + * + * pb = perf_buffer__new(bpf_map__fd(obj->maps.events), PERF_BUFFER_PAGES, &opts); + * err = libbpf_get_error(pb); + * if (err) { + * pb = NULL; + * fprintf(stderr, "failed to open perf buffer: %d\n", err); + * goto cleanup; + * } + */ LIBBPF_API long libbpf_get_error(const void *ptr); struct bpf_prog_load_attr { @@ -569,10 +809,12 @@ struct bpf_prog_load_attr { int prog_flags; }; +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_object__open() and bpf_object__load() instead") LIBBPF_API int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, struct bpf_object **pobj, int *prog_fd); -LIBBPF_API int bpf_prog_load(const char *file, enum bpf_prog_type type, - struct bpf_object **pobj, int *prog_fd); +LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_object__open() and bpf_object__load() instead") +LIBBPF_API int bpf_prog_load_deprecated(const char *file, enum bpf_prog_type type, + struct bpf_object **pobj, int *prog_fd); /* XDP related API */ struct xdp_link_info { @@ -670,18 +912,52 @@ typedef void (*perf_buffer_lost_fn)(void *ctx, int cpu, __u64 cnt); /* common use perf buffer options */ struct perf_buffer_opts { - /* if specified, sample_cb is called for each sample */ - perf_buffer_sample_fn sample_cb; - /* if specified, lost_cb is called for each batch of lost samples */ - perf_buffer_lost_fn lost_cb; - /* ctx is provided to sample_cb and lost_cb */ - void *ctx; + union { + size_t sz; + struct { /* DEPRECATED: will be removed in v1.0 */ + /* if specified, sample_cb is called for each sample */ + perf_buffer_sample_fn sample_cb; + /* if specified, lost_cb is called for each batch of lost samples */ + perf_buffer_lost_fn lost_cb; + /* ctx is provided to sample_cb and lost_cb */ + void *ctx; + }; + }; }; +#define perf_buffer_opts__last_field sz +/** + * @brief **perf_buffer__new()** creates BPF perfbuf manager for a specified + * BPF_PERF_EVENT_ARRAY map + * @param map_fd FD of BPF_PERF_EVENT_ARRAY BPF map that will be used by BPF + * code to send data over to user-space + * @param page_cnt number of memory pages allocated for each per-CPU buffer + * @param sample_cb function called on each received data record + * @param lost_cb function called when record loss has occurred + * @param ctx user-provided extra context passed into *sample_cb* and *lost_cb* + * @return a new instance of struct perf_buffer on success, NULL on error with + * *errno* containing an error code + */ LIBBPF_API struct perf_buffer * perf_buffer__new(int map_fd, size_t page_cnt, + perf_buffer_sample_fn sample_cb, perf_buffer_lost_fn lost_cb, void *ctx, const struct perf_buffer_opts *opts); +LIBBPF_API struct perf_buffer * +perf_buffer__new_v0_6_0(int map_fd, size_t page_cnt, + perf_buffer_sample_fn sample_cb, perf_buffer_lost_fn lost_cb, void *ctx, + const struct perf_buffer_opts *opts); + +LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "use new variant of perf_buffer__new() instead") +struct perf_buffer *perf_buffer__new_deprecated(int map_fd, size_t page_cnt, + const struct perf_buffer_opts *opts); + +#define perf_buffer__new(...) ___libbpf_overload(___perf_buffer_new, __VA_ARGS__) +#define ___perf_buffer_new6(map_fd, page_cnt, sample_cb, lost_cb, ctx, opts) \ + perf_buffer__new(map_fd, page_cnt, sample_cb, lost_cb, ctx, opts) +#define ___perf_buffer_new3(map_fd, page_cnt, opts) \ + perf_buffer__new_deprecated(map_fd, page_cnt, opts) + enum bpf_perf_event_ret { LIBBPF_PERF_EVENT_DONE = 0, LIBBPF_PERF_EVENT_ERROR = -1, @@ -695,12 +971,21 @@ typedef enum bpf_perf_event_ret /* raw perf buffer options, giving most power and control */ struct perf_buffer_raw_opts { - /* perf event attrs passed directly into perf_event_open() */ - struct perf_event_attr *attr; - /* raw event callback */ - perf_buffer_event_fn event_cb; - /* ctx is provided to event_cb */ - void *ctx; + union { + struct { + size_t sz; + long :0; + long :0; + }; + struct { /* DEPRECATED: will be removed in v1.0 */ + /* perf event attrs passed directly into perf_event_open() */ + struct perf_event_attr *attr; + /* raw event callback */ + perf_buffer_event_fn event_cb; + /* ctx is provided to event_cb */ + void *ctx; + }; + }; /* if cpu_cnt == 0, open all on all possible CPUs (up to the number of * max_entries of given PERF_EVENT_ARRAY map) */ @@ -710,11 +995,28 @@ struct perf_buffer_raw_opts { /* if cpu_cnt > 0, map_keys specify map keys to set per-CPU FDs for */ int *map_keys; }; +#define perf_buffer_raw_opts__last_field map_keys LIBBPF_API struct perf_buffer * -perf_buffer__new_raw(int map_fd, size_t page_cnt, +perf_buffer__new_raw(int map_fd, size_t page_cnt, struct perf_event_attr *attr, + perf_buffer_event_fn event_cb, void *ctx, const struct perf_buffer_raw_opts *opts); +LIBBPF_API struct perf_buffer * +perf_buffer__new_raw_v0_6_0(int map_fd, size_t page_cnt, struct perf_event_attr *attr, + perf_buffer_event_fn event_cb, void *ctx, + const struct perf_buffer_raw_opts *opts); + +LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "use new variant of perf_buffer__new_raw() instead") +struct perf_buffer *perf_buffer__new_raw_deprecated(int map_fd, size_t page_cnt, + const struct perf_buffer_raw_opts *opts); + +#define perf_buffer__new_raw(...) ___libbpf_overload(___perf_buffer_new_raw, __VA_ARGS__) +#define ___perf_buffer_new_raw6(map_fd, page_cnt, attr, event_cb, ctx, opts) \ + perf_buffer__new_raw(map_fd, page_cnt, attr, event_cb, ctx, opts) +#define ___perf_buffer_new_raw3(map_fd, page_cnt, opts) \ + perf_buffer__new_raw_deprecated(map_fd, page_cnt, opts) + LIBBPF_API void perf_buffer__free(struct perf_buffer *pb); LIBBPF_API int perf_buffer__epoll_fd(const struct perf_buffer *pb); LIBBPF_API int perf_buffer__poll(struct perf_buffer *pb, int timeout_ms); @@ -726,6 +1028,7 @@ LIBBPF_API int perf_buffer__buffer_fd(const struct perf_buffer *pb, size_t buf_i typedef enum bpf_perf_event_ret (*bpf_perf_event_print_t)(struct perf_event_header *hdr, void *private_data); +LIBBPF_DEPRECATED_SINCE(0, 8, "use perf_buffer__poll() or perf_buffer__consume() instead") LIBBPF_API enum bpf_perf_event_ret bpf_perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size, void **copy_mem, size_t *copy_size, @@ -752,13 +1055,57 @@ bpf_prog_linfo__lfind(const struct bpf_prog_linfo *prog_linfo, * user, causing subsequent probes to fail. In this case, the caller may want * to adjust that limit with setrlimit(). */ -LIBBPF_API bool bpf_probe_prog_type(enum bpf_prog_type prog_type, - __u32 ifindex); +LIBBPF_DEPRECATED_SINCE(0, 8, "use libbpf_probe_bpf_prog_type() instead") +LIBBPF_API bool bpf_probe_prog_type(enum bpf_prog_type prog_type, __u32 ifindex); +LIBBPF_DEPRECATED_SINCE(0, 8, "use libbpf_probe_bpf_map_type() instead") LIBBPF_API bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex); -LIBBPF_API bool bpf_probe_helper(enum bpf_func_id id, - enum bpf_prog_type prog_type, __u32 ifindex); +LIBBPF_DEPRECATED_SINCE(0, 8, "use libbpf_probe_bpf_helper() instead") +LIBBPF_API bool bpf_probe_helper(enum bpf_func_id id, enum bpf_prog_type prog_type, __u32 ifindex); +LIBBPF_DEPRECATED_SINCE(0, 8, "implement your own or use bpftool for feature detection") LIBBPF_API bool bpf_probe_large_insn_limit(__u32 ifindex); +/** + * @brief **libbpf_probe_bpf_prog_type()** detects if host kernel supports + * BPF programs of a given type. + * @param prog_type BPF program type to detect kernel support for + * @param opts reserved for future extensibility, should be NULL + * @return 1, if given program type is supported; 0, if given program type is + * not supported; negative error code if feature detection failed or can't be + * performed + * + * Make sure the process has required set of CAP_* permissions (or runs as + * root) when performing feature checking. + */ +LIBBPF_API int libbpf_probe_bpf_prog_type(enum bpf_prog_type prog_type, const void *opts); +/** + * @brief **libbpf_probe_bpf_map_type()** detects if host kernel supports + * BPF maps of a given type. + * @param map_type BPF map type to detect kernel support for + * @param opts reserved for future extensibility, should be NULL + * @return 1, if given map type is supported; 0, if given map type is + * not supported; negative error code if feature detection failed or can't be + * performed + * + * Make sure the process has required set of CAP_* permissions (or runs as + * root) when performing feature checking. + */ +LIBBPF_API int libbpf_probe_bpf_map_type(enum bpf_map_type map_type, const void *opts); +/** + * @brief **libbpf_probe_bpf_helper()** detects if host kernel supports the + * use of a given BPF helper from specified BPF program type. + * @param prog_type BPF program type used to check the support of BPF helper + * @param helper_id BPF helper ID (enum bpf_func_id) to check support for + * @param opts reserved for future extensibility, should be NULL + * @return 1, if given combination of program type and helper is supported; 0, + * if the combination is not supported; negative error code if feature + * detection for provided input arguments failed or can't be performed + * + * Make sure the process has required set of CAP_* permissions (or runs as + * root) when performing feature checking. + */ +LIBBPF_API int libbpf_probe_bpf_helper(enum bpf_prog_type prog_type, + enum bpf_func_id helper_id, const void *opts); + /* * Get bpf_prog_info in continuous memory * @@ -813,18 +1160,22 @@ struct bpf_prog_info_linear { __u8 data[]; }; +LIBBPF_DEPRECATED_SINCE(0, 6, "use a custom linear prog_info wrapper") LIBBPF_API struct bpf_prog_info_linear * bpf_program__get_prog_info_linear(int fd, __u64 arrays); +LIBBPF_DEPRECATED_SINCE(0, 6, "use a custom linear prog_info wrapper") LIBBPF_API void bpf_program__bpil_addr_to_offs(struct bpf_prog_info_linear *info_linear); +LIBBPF_DEPRECATED_SINCE(0, 6, "use a custom linear prog_info wrapper") LIBBPF_API void bpf_program__bpil_offs_to_addr(struct bpf_prog_info_linear *info_linear); -/* - * A helper function to get the number of possible CPUs before looking up - * per-CPU maps. Negative errno is returned on failure. +/** + * @brief **libbpf_num_possible_cpus()** is a helper function to get the + * number of possible CPUs that the host kernel supports and expects. + * @return number of possible CPUs; or error code on failure * * Example usage: * @@ -834,7 +1185,6 @@ bpf_program__bpil_offs_to_addr(struct bpf_prog_info_linear *info_linear); * } * long values[ncpus]; * bpf_map_lookup_elem(per_cpu_map_fd, key, values); - * */ LIBBPF_API int libbpf_num_possible_cpus(void); @@ -854,17 +1204,17 @@ struct bpf_object_skeleton { size_t sz; /* size of this struct, for forward/backward compatibility */ const char *name; - void *data; + const void *data; size_t data_sz; struct bpf_object **obj; int map_cnt; - int map_skel_sz; /* sizeof(struct bpf_skeleton_map) */ + int map_skel_sz; /* sizeof(struct bpf_map_skeleton) */ struct bpf_map_skeleton *maps; int prog_cnt; - int prog_skel_sz; /* sizeof(struct bpf_skeleton_prog) */ + int prog_skel_sz; /* sizeof(struct bpf_prog_skeleton) */ struct bpf_prog_skeleton *progs; }; diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index bbc53bb25f..5297839677 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -386,3 +386,49 @@ LIBBPF_0.5.0 { btf_dump__dump_type_data; libbpf_set_strict_mode; } LIBBPF_0.4.0; + +LIBBPF_0.6.0 { + global: + bpf_map__map_extra; + bpf_map__set_map_extra; + bpf_map_create; + bpf_object__next_map; + bpf_object__next_program; + bpf_object__prev_map; + bpf_object__prev_program; + bpf_prog_load_deprecated; + bpf_prog_load; + bpf_program__flags; + bpf_program__insn_cnt; + bpf_program__insns; + bpf_program__set_flags; + btf__add_btf; + btf__add_decl_tag; + btf__add_type_tag; + btf__dedup; + btf__dedup_deprecated; + btf__raw_data; + btf__type_cnt; + btf_dump__new; + btf_dump__new_deprecated; + libbpf_major_version; + libbpf_minor_version; + libbpf_version_string; + perf_buffer__new; + perf_buffer__new_deprecated; + perf_buffer__new_raw; + perf_buffer__new_raw_deprecated; +} LIBBPF_0.5.0; + +LIBBPF_0.7.0 { + global: + bpf_btf_load; + bpf_program__log_buf; + bpf_program__log_level; + bpf_program__set_log_buf; + bpf_program__set_log_level; + libbpf_probe_bpf_helper; + libbpf_probe_bpf_map_type; + libbpf_probe_bpf_prog_type; + libbpf_set_memlock_rlim_max; +}; diff --git a/tools/lib/bpf/libbpf_common.h b/tools/lib/bpf/libbpf_common.h index 947d8bd8a7..000e37798f 100644 --- a/tools/lib/bpf/libbpf_common.h +++ b/tools/lib/bpf/libbpf_common.h @@ -10,6 +10,7 @@ #define __LIBBPF_LIBBPF_COMMON_H #include +#include "libbpf_version.h" #ifndef LIBBPF_API #define LIBBPF_API __attribute__((visibility("default"))) @@ -17,6 +18,46 @@ #define LIBBPF_DEPRECATED(msg) __attribute__((deprecated(msg))) +/* Mark a symbol as deprecated when libbpf version is >= {major}.{minor} */ +#define LIBBPF_DEPRECATED_SINCE(major, minor, msg) \ + __LIBBPF_MARK_DEPRECATED_ ## major ## _ ## minor \ + (LIBBPF_DEPRECATED("libbpf v" # major "." # minor "+: " msg)) + +#define __LIBBPF_CURRENT_VERSION_GEQ(major, minor) \ + (LIBBPF_MAJOR_VERSION > (major) || \ + (LIBBPF_MAJOR_VERSION == (major) && LIBBPF_MINOR_VERSION >= (minor))) + +/* Add checks for other versions below when planning deprecation of API symbols + * with the LIBBPF_DEPRECATED_SINCE macro. + */ +#if __LIBBPF_CURRENT_VERSION_GEQ(0, 6) +#define __LIBBPF_MARK_DEPRECATED_0_6(X) X +#else +#define __LIBBPF_MARK_DEPRECATED_0_6(X) +#endif +#if __LIBBPF_CURRENT_VERSION_GEQ(0, 7) +#define __LIBBPF_MARK_DEPRECATED_0_7(X) X +#else +#define __LIBBPF_MARK_DEPRECATED_0_7(X) +#endif +#if __LIBBPF_CURRENT_VERSION_GEQ(0, 8) +#define __LIBBPF_MARK_DEPRECATED_0_8(X) X +#else +#define __LIBBPF_MARK_DEPRECATED_0_8(X) +#endif + +/* This set of internal macros allows to do "function overloading" based on + * number of arguments provided by used in backwards-compatible way during the + * transition to libbpf 1.0 + * It's ugly but necessary evil that will be cleaned up when we get to 1.0. + * See bpf_prog_load() overload for example. + */ +#define ___libbpf_cat(A, B) A ## B +#define ___libbpf_select(NAME, NUM) ___libbpf_cat(NAME, NUM) +#define ___libbpf_nth(_1, _2, _3, _4, _5, _6, N, ...) N +#define ___libbpf_cnt(...) ___libbpf_nth(__VA_ARGS__, 6, 5, 4, 3, 2, 1) +#define ___libbpf_overload(NAME, ...) ___libbpf_select(NAME, ___libbpf_cnt(__VA_ARGS__))(__VA_ARGS__) + /* Helper macro to declare and initialize libbpf options struct * * This dance with uninitialized declaration, followed by memset to zero, @@ -30,7 +71,7 @@ * including any extra padding, it with memset() and then assigns initial * values provided by users in struct initializer-syntax as varargs. */ -#define DECLARE_LIBBPF_OPTS(TYPE, NAME, ...) \ +#define LIBBPF_OPTS(TYPE, NAME, ...) \ struct TYPE NAME = ({ \ memset(&NAME, 0, sizeof(struct TYPE)); \ (struct TYPE) { \ diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index 533b0211f4..1565679eb4 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -13,6 +13,8 @@ #include #include #include +#include +#include #include "libbpf_legacy.h" #include "relo_core.h" @@ -52,8 +54,8 @@ #endif /* Older libelf all end up in this expression, for both 32 and 64 bit */ -#ifndef GELF_ST_VISIBILITY -#define GELF_ST_VISIBILITY(o) ((o) & 0x03) +#ifndef ELF64_ST_VISIBILITY +#define ELF64_ST_VISIBILITY(o) ((o) & 0x03) #endif #define BTF_INFO_ENC(kind, kind_flag, vlen) \ @@ -69,6 +71,10 @@ #define BTF_VAR_SECINFO_ENC(type, offset, size) (type), (offset), (size) #define BTF_TYPE_FLOAT_ENC(name, sz) \ BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_FLOAT, 0, 0), sz) +#define BTF_TYPE_DECL_TAG_ENC(value, type, component_idx) \ + BTF_TYPE_ENC(value, BTF_INFO_ENC(BTF_KIND_DECL_TAG, 0, 0), type), (component_idx) +#define BTF_TYPE_TYPE_TAG_ENC(value, type) \ + BTF_TYPE_ENC(value, BTF_INFO_ENC(BTF_KIND_TYPE_TAG, 0, 0), type) #ifndef likely #define likely(x) __builtin_expect(!!(x), 1) @@ -87,20 +93,40 @@ (offsetof(TYPE, FIELD) + sizeof(((TYPE *)0)->FIELD)) #endif +/* Check whether a string `str` has prefix `pfx`, regardless if `pfx` is + * a string literal known at compilation time or char * pointer known only at + * runtime. + */ +#define str_has_pfx(str, pfx) \ + (strncmp(str, pfx, __builtin_constant_p(pfx) ? sizeof(pfx) - 1 : strlen(pfx)) == 0) + /* Symbol versioning is different between static and shared library. * Properly versioned symbols are needed for shared library, but * only the symbol of the new version is needed for static library. + * Starting with GNU C 10, use symver attribute instead of .symver assembler + * directive, which works better with GCC LTO builds. */ -#ifdef SHARED -# define COMPAT_VERSION(internal_name, api_name, version) \ +#if defined(SHARED) && defined(__GNUC__) && __GNUC__ >= 10 + +#define DEFAULT_VERSION(internal_name, api_name, version) \ + __attribute__((symver(#api_name "@@" #version))) +#define COMPAT_VERSION(internal_name, api_name, version) \ + __attribute__((symver(#api_name "@" #version))) + +#elif defined(SHARED) + +#define COMPAT_VERSION(internal_name, api_name, version) \ asm(".symver " #internal_name "," #api_name "@" #version); -# define DEFAULT_VERSION(internal_name, api_name, version) \ +#define DEFAULT_VERSION(internal_name, api_name, version) \ asm(".symver " #internal_name "," #api_name "@@" #version); -#else -# define COMPAT_VERSION(internal_name, api_name, version) -# define DEFAULT_VERSION(internal_name, api_name, version) \ + +#else /* !SHARED */ + +#define COMPAT_VERSION(internal_name, api_name, version) +#define DEFAULT_VERSION(internal_name, api_name, version) \ extern typeof(internal_name) api_name \ __attribute__((alias(#internal_name))); + #endif extern void libbpf_print(enum libbpf_print_level level, @@ -143,10 +169,31 @@ static inline void *libbpf_reallocarray(void *ptr, size_t nmemb, size_t size) return realloc(ptr, total); } +/* Copy up to sz - 1 bytes from zero-terminated src string and ensure that dst + * is zero-terminated string no matter what (unless sz == 0, in which case + * it's a no-op). It's conceptually close to FreeBSD's strlcpy(), but differs + * in what is returned. Given this is internal helper, it's trivial to extend + * this, when necessary. Use this instead of strncpy inside libbpf source code. + */ +static inline void libbpf_strlcpy(char *dst, const char *src, size_t sz) +{ + size_t i; + + if (sz == 0) + return; + + sz--; + for (i = 0; i < sz && src[i]; i++) + dst[i] = src[i]; + dst[i] = '\0'; +} + +__u32 get_kernel_version(void); + struct btf; struct btf_type; -struct btf_type *btf_type_by_id(struct btf *btf, __u32 type_id); +struct btf_type *btf_type_by_id(const struct btf *btf, __u32 type_id); const char *btf_kind_str(const struct btf_type *t); const struct btf_type *skip_mods_and_typedefs(const struct btf *btf, __u32 id, __u32 *res_id); @@ -171,8 +218,9 @@ enum map_def_parts { MAP_DEF_NUMA_NODE = 0x080, MAP_DEF_PINNING = 0x100, MAP_DEF_INNER_MAP = 0x200, + MAP_DEF_MAP_EXTRA = 0x400, - MAP_DEF_ALL = 0x3ff, /* combination of all above */ + MAP_DEF_ALL = 0x7ff, /* combination of all above */ }; struct btf_map_def { @@ -186,6 +234,7 @@ struct btf_map_def { __u32 map_flags; __u32 numa_node; __u32 pinning; + __u64 map_extra; }; int parse_btf_map_def(const char *map_name, struct btf *btf, @@ -244,46 +293,52 @@ static inline bool libbpf_validate_opts(const char *opts, (opts)->sz - __off); \ }) +enum kern_feature_id { + /* v4.14: kernel support for program & map names. */ + FEAT_PROG_NAME, + /* v5.2: kernel support for global data sections. */ + FEAT_GLOBAL_DATA, + /* BTF support */ + FEAT_BTF, + /* BTF_KIND_FUNC and BTF_KIND_FUNC_PROTO support */ + FEAT_BTF_FUNC, + /* BTF_KIND_VAR and BTF_KIND_DATASEC support */ + FEAT_BTF_DATASEC, + /* BTF_FUNC_GLOBAL is supported */ + FEAT_BTF_GLOBAL_FUNC, + /* BPF_F_MMAPABLE is supported for arrays */ + FEAT_ARRAY_MMAP, + /* kernel support for expected_attach_type in BPF_PROG_LOAD */ + FEAT_EXP_ATTACH_TYPE, + /* bpf_probe_read_{kernel,user}[_str] helpers */ + FEAT_PROBE_READ_KERN, + /* BPF_PROG_BIND_MAP is supported */ + FEAT_PROG_BIND_MAP, + /* Kernel support for module BTFs */ + FEAT_MODULE_BTF, + /* BTF_KIND_FLOAT support */ + FEAT_BTF_FLOAT, + /* BPF perf link support */ + FEAT_PERF_LINK, + /* BTF_KIND_DECL_TAG support */ + FEAT_BTF_DECL_TAG, + /* BTF_KIND_TYPE_TAG support */ + FEAT_BTF_TYPE_TAG, + /* memcg-based accounting for BPF maps and progs */ + FEAT_MEMCG_ACCOUNT, + __FEAT_CNT, +}; + +int probe_memcg_account(void); +bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id); +int bump_rlimit_memlock(void); int parse_cpu_mask_str(const char *s, bool **mask, int *mask_sz); int parse_cpu_mask_file(const char *fcpu, bool **mask, int *mask_sz); int libbpf__load_raw_btf(const char *raw_types, size_t types_len, const char *str_sec, size_t str_len); +int btf_load_into_kernel(struct btf *btf, char *log_buf, size_t log_sz, __u32 log_level); -struct bpf_prog_load_params { - enum bpf_prog_type prog_type; - enum bpf_attach_type expected_attach_type; - const char *name; - const struct bpf_insn *insns; - size_t insn_cnt; - const char *license; - __u32 kern_version; - __u32 attach_prog_fd; - __u32 attach_btf_obj_fd; - __u32 attach_btf_id; - __u32 prog_ifindex; - __u32 prog_btf_fd; - __u32 prog_flags; - - __u32 func_info_rec_size; - const void *func_info; - __u32 func_info_cnt; - - __u32 line_info_rec_size; - const void *line_info; - __u32 line_info_cnt; - - __u32 log_level; - char *log_buf; - size_t log_buf_sz; -}; - -int libbpf__bpf_prog_load(const struct bpf_prog_load_params *load_attr); - -int bpf_object__section_size(const struct bpf_object *obj, const char *name, - __u32 *size); -int bpf_object__variable_offset(const struct bpf_object *obj, const char *name, - __u32 *off); struct btf *btf_get_from_fd(int btf_fd, struct btf *base_btf); void btf_get_kernel_prefix_kind(enum bpf_attach_type attach_type, const char **prefix, int *kind); @@ -386,6 +441,8 @@ int btf_type_visit_type_ids(struct btf_type *t, type_id_visit_fn visit, void *ct int btf_type_visit_str_offs(struct btf_type *t, str_off_visit_fn visit, void *ctx); int btf_ext_visit_type_ids(struct btf_ext *btf_ext, type_id_visit_fn visit, void *ctx); int btf_ext_visit_str_offs(struct btf_ext *btf_ext, str_off_visit_fn visit, void *ctx); +__s32 btf__find_by_name_kind_own(const struct btf *btf, const char *type_name, + __u32 kind); extern enum libbpf_strict_mode libbpf_mode; @@ -447,4 +504,26 @@ static inline bool is_ldimm64_insn(struct bpf_insn *insn) return insn->code == (BPF_LD | BPF_IMM | BPF_DW); } +/* if fd is stdin, stdout, or stderr, dup to a fd greater than 2 + * Takes ownership of the fd passed in, and closes it if calling + * fcntl(fd, F_DUPFD_CLOEXEC, 3). + */ +static inline int ensure_good_fd(int fd) +{ + int old_fd = fd, saved_errno; + + if (fd < 0) + return fd; + if (fd < 3) { + fd = fcntl(fd, F_DUPFD_CLOEXEC, 3); + saved_errno = errno; + close(old_fd); + if (fd < 0) { + pr_warn("failed to dup FD %d to FD > 2: %d\n", old_fd, -saved_errno); + errno = saved_errno; + } + } + return fd; +} + #endif /* __LIBBPF_LIBBPF_INTERNAL_H */ diff --git a/tools/lib/bpf/libbpf_legacy.h b/tools/lib/bpf/libbpf_legacy.h index df0d03dcff..79131f761a 100644 --- a/tools/lib/bpf/libbpf_legacy.h +++ b/tools/lib/bpf/libbpf_legacy.h @@ -45,12 +45,41 @@ enum libbpf_strict_mode { * (positive) error code. */ LIBBPF_STRICT_DIRECT_ERRS = 0x02, + /* + * Enforce strict BPF program section (SEC()) names. + * E.g., while prefiously SEC("xdp_whatever") or SEC("perf_event_blah") were + * allowed, with LIBBPF_STRICT_SEC_PREFIX this will become + * unrecognized by libbpf and would have to be just SEC("xdp") and + * SEC("xdp") and SEC("perf_event"). + * + * Note, in this mode the program pin path will be based on the + * function name instead of section name. + */ + LIBBPF_STRICT_SEC_NAME = 0x04, + /* + * Disable the global 'bpf_objects_list'. Maintaining this list adds + * a race condition to bpf_object__open() and bpf_object__close(). + * Clients can maintain it on their own if it is valuable for them. + */ + LIBBPF_STRICT_NO_OBJECT_LIST = 0x08, + /* + * Automatically bump RLIMIT_MEMLOCK using setrlimit() before the + * first BPF program or map creation operation. This is done only if + * kernel is too old to support memcg-based memory accounting for BPF + * subsystem. By default, RLIMIT_MEMLOCK limit is set to RLIM_INFINITY, + * but it can be overriden with libbpf_set_memlock_rlim_max() API. + * Note that libbpf_set_memlock_rlim_max() needs to be called before + * the very first bpf_prog_load(), bpf_map_create() or bpf_object__load() + * operation. + */ + LIBBPF_STRICT_AUTO_RLIMIT_MEMLOCK = 0x10, __LIBBPF_STRICT_LAST, }; LIBBPF_API int libbpf_set_strict_mode(enum libbpf_strict_mode mode); +#define DECLARE_LIBBPF_OPTS LIBBPF_OPTS #ifdef __cplusplus } /* extern "C" */ diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c index cd8c703dde..97b06cede5 100644 --- a/tools/lib/bpf/libbpf_probes.c +++ b/tools/lib/bpf/libbpf_probes.c @@ -33,7 +33,7 @@ static int get_vendor_id(int ifindex) snprintf(path, sizeof(path), "/sys/class/net/%s/device/vendor", ifname); - fd = open(path, O_RDONLY); + fd = open(path, O_RDONLY | O_CLOEXEC); if (fd < 0) return -1; @@ -48,41 +48,65 @@ static int get_vendor_id(int ifindex) return strtol(buf, NULL, 0); } -static int get_kernel_version(void) +static int probe_prog_load(enum bpf_prog_type prog_type, + const struct bpf_insn *insns, size_t insns_cnt, + char *log_buf, size_t log_buf_sz, + __u32 ifindex) { - int version, subversion, patchlevel; - struct utsname utsn; - - /* Return 0 on failure, and attempt to probe with empty kversion */ - if (uname(&utsn)) - return 0; - - if (sscanf(utsn.release, "%d.%d.%d", - &version, &subversion, &patchlevel) != 3) - return 0; - - return (version << 16) + (subversion << 8) + patchlevel; -} - -static void -probe_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns, - size_t insns_cnt, char *buf, size_t buf_len, __u32 ifindex) -{ - struct bpf_load_program_attr xattr = {}; - int fd; + LIBBPF_OPTS(bpf_prog_load_opts, opts, + .log_buf = log_buf, + .log_size = log_buf_sz, + .log_level = log_buf ? 1 : 0, + .prog_ifindex = ifindex, + ); + int fd, err, exp_err = 0; + const char *exp_msg = NULL; + char buf[4096]; switch (prog_type) { case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: - xattr.expected_attach_type = BPF_CGROUP_INET4_CONNECT; + opts.expected_attach_type = BPF_CGROUP_INET4_CONNECT; break; case BPF_PROG_TYPE_CGROUP_SOCKOPT: - xattr.expected_attach_type = BPF_CGROUP_GETSOCKOPT; + opts.expected_attach_type = BPF_CGROUP_GETSOCKOPT; break; case BPF_PROG_TYPE_SK_LOOKUP: - xattr.expected_attach_type = BPF_SK_LOOKUP; + opts.expected_attach_type = BPF_SK_LOOKUP; break; case BPF_PROG_TYPE_KPROBE: - xattr.kern_version = get_kernel_version(); + opts.kern_version = get_kernel_version(); + break; + case BPF_PROG_TYPE_LIRC_MODE2: + opts.expected_attach_type = BPF_LIRC_MODE2; + break; + case BPF_PROG_TYPE_TRACING: + case BPF_PROG_TYPE_LSM: + opts.log_buf = buf; + opts.log_size = sizeof(buf); + opts.log_level = 1; + if (prog_type == BPF_PROG_TYPE_TRACING) + opts.expected_attach_type = BPF_TRACE_FENTRY; + else + opts.expected_attach_type = BPF_MODIFY_RETURN; + opts.attach_btf_id = 1; + + exp_err = -EINVAL; + exp_msg = "attach_btf_id 1 is not a function"; + break; + case BPF_PROG_TYPE_EXT: + opts.log_buf = buf; + opts.log_size = sizeof(buf); + opts.log_level = 1; + opts.attach_btf_id = 1; + + exp_err = -EINVAL; + exp_msg = "Cannot replace kernel functions"; + break; + case BPF_PROG_TYPE_SYSCALL: + opts.prog_flags = BPF_F_SLEEPABLE; + break; + case BPF_PROG_TYPE_STRUCT_OPS: + exp_err = -524; /* -ENOTSUPP */ break; case BPF_PROG_TYPE_UNSPEC: case BPF_PROG_TYPE_SOCKET_FILTER: @@ -103,27 +127,42 @@ probe_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns, case BPF_PROG_TYPE_RAW_TRACEPOINT: case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE: case BPF_PROG_TYPE_LWT_SEG6LOCAL: - case BPF_PROG_TYPE_LIRC_MODE2: case BPF_PROG_TYPE_SK_REUSEPORT: case BPF_PROG_TYPE_FLOW_DISSECTOR: case BPF_PROG_TYPE_CGROUP_SYSCTL: - case BPF_PROG_TYPE_TRACING: - case BPF_PROG_TYPE_STRUCT_OPS: - case BPF_PROG_TYPE_EXT: - case BPF_PROG_TYPE_LSM: - default: break; + default: + return -EOPNOTSUPP; } - xattr.prog_type = prog_type; - xattr.insns = insns; - xattr.insns_cnt = insns_cnt; - xattr.license = "GPL"; - xattr.prog_ifindex = ifindex; - - fd = bpf_load_program_xattr(&xattr, buf, buf_len); + fd = bpf_prog_load(prog_type, NULL, "GPL", insns, insns_cnt, &opts); + err = -errno; if (fd >= 0) close(fd); + if (exp_err) { + if (fd >= 0 || err != exp_err) + return 0; + if (exp_msg && !strstr(buf, exp_msg)) + return 0; + return 1; + } + return fd >= 0 ? 1 : 0; +} + +int libbpf_probe_bpf_prog_type(enum bpf_prog_type prog_type, const void *opts) +{ + struct bpf_insn insns[] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN() + }; + const size_t insn_cnt = ARRAY_SIZE(insns); + int ret; + + if (opts) + return libbpf_err(-EINVAL); + + ret = probe_prog_load(prog_type, insns, insn_cnt, NULL, 0, 0); + return libbpf_err(ret); } bool bpf_probe_prog_type(enum bpf_prog_type prog_type, __u32 ifindex) @@ -133,12 +172,16 @@ bool bpf_probe_prog_type(enum bpf_prog_type prog_type, __u32 ifindex) BPF_EXIT_INSN() }; + /* prefer libbpf_probe_bpf_prog_type() unless offload is requested */ + if (ifindex == 0) + return libbpf_probe_bpf_prog_type(prog_type, NULL) == 1; + if (ifindex && prog_type == BPF_PROG_TYPE_SCHED_CLS) /* nfp returns -EINVAL on exit(0) with TC offload */ insns[0].imm = 2; errno = 0; - probe_load(prog_type, insns, ARRAY_SIZE(insns), NULL, 0, ifindex); + probe_prog_load(prog_type, insns, ARRAY_SIZE(insns), NULL, 0, ifindex); return errno != EINVAL && errno != EOPNOTSUPP; } @@ -166,7 +209,7 @@ int libbpf__load_raw_btf(const char *raw_types, size_t types_len, memcpy(raw_btf + hdr.hdr_len, raw_types, hdr.type_len); memcpy(raw_btf + hdr.hdr_len + hdr.type_len, str_sec, hdr.str_len); - btf_fd = bpf_load_btf(raw_btf, btf_len, NULL, 0, false); + btf_fd = bpf_btf_load(raw_btf, btf_len, NULL); free(raw_btf); return btf_fd; @@ -199,17 +242,18 @@ static int load_local_storage_btf(void) strs, sizeof(strs)); } -bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex) +static int probe_map_create(enum bpf_map_type map_type, __u32 ifindex) { - int key_size, value_size, max_entries, map_flags; + LIBBPF_OPTS(bpf_map_create_opts, opts); + int key_size, value_size, max_entries; __u32 btf_key_type_id = 0, btf_value_type_id = 0; - struct bpf_create_map_attr attr = {}; - int fd = -1, btf_fd = -1, fd_inner; + int fd = -1, btf_fd = -1, fd_inner = -1, exp_err = 0, err; + + opts.map_ifindex = ifindex; key_size = sizeof(__u32); value_size = sizeof(__u32); max_entries = 1; - map_flags = 0; switch (map_type) { case BPF_MAP_TYPE_STACK_TRACE: @@ -218,7 +262,7 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex) case BPF_MAP_TYPE_LPM_TRIE: key_size = sizeof(__u64); value_size = sizeof(__u64); - map_flags = BPF_F_NO_PREALLOC; + opts.map_flags = BPF_F_NO_PREALLOC; break; case BPF_MAP_TYPE_CGROUP_STORAGE: case BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE: @@ -237,17 +281,25 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex) btf_value_type_id = 3; value_size = 8; max_entries = 0; - map_flags = BPF_F_NO_PREALLOC; + opts.map_flags = BPF_F_NO_PREALLOC; btf_fd = load_local_storage_btf(); if (btf_fd < 0) - return false; + return btf_fd; break; case BPF_MAP_TYPE_RINGBUF: key_size = 0; value_size = 0; max_entries = 4096; break; - case BPF_MAP_TYPE_UNSPEC: + case BPF_MAP_TYPE_STRUCT_OPS: + /* we'll get -ENOTSUPP for invalid BTF type ID for struct_ops */ + opts.btf_vmlinux_value_type_id = 1; + exp_err = -524; /* -ENOTSUPP */ + break; + case BPF_MAP_TYPE_BLOOM_FILTER: + key_size = 0; + max_entries = 1; + break; case BPF_MAP_TYPE_HASH: case BPF_MAP_TYPE_ARRAY: case BPF_MAP_TYPE_PROG_ARRAY: @@ -266,9 +318,10 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex) case BPF_MAP_TYPE_XSKMAP: case BPF_MAP_TYPE_SOCKHASH: case BPF_MAP_TYPE_REUSEPORT_SOCKARRAY: - case BPF_MAP_TYPE_STRUCT_OPS: - default: break; + case BPF_MAP_TYPE_UNSPEC: + default: + return -EOPNOTSUPP; } if (map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS || @@ -277,37 +330,102 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex) * map-in-map for offload */ if (ifindex) - return false; + goto cleanup; - fd_inner = bpf_create_map(BPF_MAP_TYPE_HASH, - sizeof(__u32), sizeof(__u32), 1, 0); + fd_inner = bpf_map_create(BPF_MAP_TYPE_HASH, NULL, + sizeof(__u32), sizeof(__u32), 1, NULL); if (fd_inner < 0) - return false; - fd = bpf_create_map_in_map(map_type, NULL, sizeof(__u32), - fd_inner, 1, 0); - close(fd_inner); - } else { - /* Note: No other restriction on map type probes for offload */ - attr.map_type = map_type; - attr.key_size = key_size; - attr.value_size = value_size; - attr.max_entries = max_entries; - attr.map_flags = map_flags; - attr.map_ifindex = ifindex; - if (btf_fd >= 0) { - attr.btf_fd = btf_fd; - attr.btf_key_type_id = btf_key_type_id; - attr.btf_value_type_id = btf_value_type_id; - } + goto cleanup; - fd = bpf_create_map_xattr(&attr); + opts.inner_map_fd = fd_inner; } + + if (btf_fd >= 0) { + opts.btf_fd = btf_fd; + opts.btf_key_type_id = btf_key_type_id; + opts.btf_value_type_id = btf_value_type_id; + } + + fd = bpf_map_create(map_type, NULL, key_size, value_size, max_entries, &opts); + err = -errno; + +cleanup: if (fd >= 0) close(fd); + if (fd_inner >= 0) + close(fd_inner); if (btf_fd >= 0) close(btf_fd); - return fd >= 0; + if (exp_err) + return fd < 0 && err == exp_err ? 1 : 0; + else + return fd >= 0 ? 1 : 0; +} + +int libbpf_probe_bpf_map_type(enum bpf_map_type map_type, const void *opts) +{ + int ret; + + if (opts) + return libbpf_err(-EINVAL); + + ret = probe_map_create(map_type, 0); + return libbpf_err(ret); +} + +bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex) +{ + return probe_map_create(map_type, ifindex) == 1; +} + +int libbpf_probe_bpf_helper(enum bpf_prog_type prog_type, enum bpf_func_id helper_id, + const void *opts) +{ + struct bpf_insn insns[] = { + BPF_EMIT_CALL((__u32)helper_id), + BPF_EXIT_INSN(), + }; + const size_t insn_cnt = ARRAY_SIZE(insns); + char buf[4096]; + int ret; + + if (opts) + return libbpf_err(-EINVAL); + + /* we can't successfully load all prog types to check for BPF helper + * support, so bail out with -EOPNOTSUPP error + */ + switch (prog_type) { + case BPF_PROG_TYPE_TRACING: + case BPF_PROG_TYPE_EXT: + case BPF_PROG_TYPE_LSM: + case BPF_PROG_TYPE_STRUCT_OPS: + return -EOPNOTSUPP; + default: + break; + } + + buf[0] = '\0'; + ret = probe_prog_load(prog_type, insns, insn_cnt, buf, sizeof(buf), 0); + if (ret < 0) + return libbpf_err(ret); + + /* If BPF verifier doesn't recognize BPF helper ID (enum bpf_func_id) + * at all, it will emit something like "invalid func unknown#181". + * If BPF verifier recognizes BPF helper but it's not supported for + * given BPF program type, it will emit "unknown func bpf_sys_bpf#166". + * In both cases, provided combination of BPF program type and BPF + * helper is not supported by the kernel. + * In all other cases, probe_prog_load() above will either succeed (e.g., + * because BPF helper happens to accept no input arguments or it + * accepts one input argument and initial PTR_TO_CTX is fine for + * that), or we'll get some more specific BPF verifier error about + * some unsatisfied conditions. + */ + if (ret == 0 && (strstr(buf, "invalid func ") || strstr(buf, "unknown func "))) + return 0; + return 1; /* assume supported */ } bool bpf_probe_helper(enum bpf_func_id id, enum bpf_prog_type prog_type, @@ -320,8 +438,7 @@ bool bpf_probe_helper(enum bpf_func_id id, enum bpf_prog_type prog_type, char buf[4096] = {}; bool res; - probe_load(prog_type, insns, ARRAY_SIZE(insns), buf, sizeof(buf), - ifindex); + probe_prog_load(prog_type, insns, ARRAY_SIZE(insns), buf, sizeof(buf), ifindex); res = !grep(buf, "invalid func ") && !grep(buf, "unknown func "); if (ifindex) { @@ -353,8 +470,8 @@ bool bpf_probe_large_insn_limit(__u32 ifindex) insns[BPF_MAXINSNS] = BPF_EXIT_INSN(); errno = 0; - probe_load(BPF_PROG_TYPE_SCHED_CLS, insns, ARRAY_SIZE(insns), NULL, 0, - ifindex); + probe_prog_load(BPF_PROG_TYPE_SCHED_CLS, insns, ARRAY_SIZE(insns), NULL, 0, + ifindex); return errno != E2BIG && errno != EINVAL; } diff --git a/tools/lib/bpf/linker.c b/tools/lib/bpf/linker.c index 6b2f59ddb6..9aa016fb55 100644 --- a/tools/lib/bpf/linker.c +++ b/tools/lib/bpf/linker.c @@ -15,7 +15,6 @@ #include #include #include -#include #include #include "libbpf.h" #include "btf.h" @@ -303,7 +302,7 @@ static int init_output_elf(struct bpf_linker *linker, const char *file) if (!linker->filename) return -ENOMEM; - linker->fd = open(file, O_WRONLY | O_CREAT | O_TRUNC, 0644); + linker->fd = open(file, O_WRONLY | O_CREAT | O_TRUNC | O_CLOEXEC, 0644); if (linker->fd < 0) { err = -errno; pr_warn("failed to create '%s': %d\n", file, err); @@ -325,12 +324,12 @@ static int init_output_elf(struct bpf_linker *linker, const char *file) linker->elf_hdr->e_machine = EM_BPF; linker->elf_hdr->e_type = ET_REL; -#if __BYTE_ORDER == __LITTLE_ENDIAN +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ linker->elf_hdr->e_ident[EI_DATA] = ELFDATA2LSB; -#elif __BYTE_ORDER == __BIG_ENDIAN +#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ linker->elf_hdr->e_ident[EI_DATA] = ELFDATA2MSB; #else -#error "Unknown __BYTE_ORDER" +#error "Unknown __BYTE_ORDER__" #endif /* STRTAB */ @@ -540,12 +539,12 @@ static int linker_load_obj_file(struct bpf_linker *linker, const char *filename, const struct bpf_linker_file_opts *opts, struct src_obj *obj) { -#if __BYTE_ORDER == __LITTLE_ENDIAN +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ const int host_endianness = ELFDATA2LSB; -#elif __BYTE_ORDER == __BIG_ENDIAN +#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ const int host_endianness = ELFDATA2MSB; #else -#error "Unknown __BYTE_ORDER" +#error "Unknown __BYTE_ORDER__" #endif int err = 0; Elf_Scn *scn; @@ -558,7 +557,7 @@ static int linker_load_obj_file(struct bpf_linker *linker, const char *filename, obj->filename = filename; - obj->fd = open(filename, O_RDONLY); + obj->fd = open(filename, O_RDONLY | O_CLOEXEC); if (obj->fd < 0) { err = -errno; pr_warn("failed to open file '%s': %d\n", filename, err); @@ -922,7 +921,7 @@ static int check_btf_type_id(__u32 *type_id, void *ctx) { struct btf *btf = ctx; - if (*type_id > btf__get_nr_types(btf)) + if (*type_id >= btf__type_cnt(btf)) return -EINVAL; return 0; @@ -949,8 +948,8 @@ static int linker_sanity_check_btf(struct src_obj *obj) if (!obj->btf) return 0; - n = btf__get_nr_types(obj->btf); - for (i = 1; i <= n; i++) { + n = btf__type_cnt(obj->btf); + for (i = 1; i < n; i++) { t = btf_type_by_id(obj->btf, i); err = err ?: btf_type_visit_type_ids(t, check_btf_type_id, obj->btf); @@ -1660,8 +1659,8 @@ static int find_glob_sym_btf(struct src_obj *obj, Elf64_Sym *sym, const char *sy return -EINVAL; } - n = btf__get_nr_types(obj->btf); - for (i = 1; i <= n; i++) { + n = btf__type_cnt(obj->btf); + for (i = 1; i < n; i++) { t = btf__type_by_id(obj->btf, i); /* some global and extern FUNCs and VARs might not be associated with any @@ -2135,8 +2134,8 @@ static int linker_fixup_btf(struct src_obj *obj) if (!obj->btf) return 0; - n = btf__get_nr_types(obj->btf); - for (i = 1; i <= n; i++) { + n = btf__type_cnt(obj->btf); + for (i = 1; i < n; i++) { struct btf_var_secinfo *vi; struct btf_type *t; @@ -2239,14 +2238,14 @@ static int linker_append_btf(struct bpf_linker *linker, struct src_obj *obj) if (!obj->btf) return 0; - start_id = btf__get_nr_types(linker->btf) + 1; - n = btf__get_nr_types(obj->btf); + start_id = btf__type_cnt(linker->btf); + n = btf__type_cnt(obj->btf); obj->btf_type_map = calloc(n + 1, sizeof(int)); if (!obj->btf_type_map) return -ENOMEM; - for (i = 1; i <= n; i++) { + for (i = 1; i < n; i++) { struct glob_sym *glob_sym = NULL; t = btf__type_by_id(obj->btf, i); @@ -2301,8 +2300,8 @@ static int linker_append_btf(struct bpf_linker *linker, struct src_obj *obj) } /* remap all the types except DATASECs */ - n = btf__get_nr_types(linker->btf); - for (i = start_id; i <= n; i++) { + n = btf__type_cnt(linker->btf); + for (i = start_id; i < n; i++) { struct btf_type *dst_t = btf_type_by_id(linker->btf, i); if (btf_type_visit_type_ids(dst_t, remap_type_id, obj->btf_type_map)) @@ -2655,13 +2654,14 @@ static int emit_elf_data_sec(struct bpf_linker *linker, const char *sec_name, static int finalize_btf(struct bpf_linker *linker) { + LIBBPF_OPTS(btf_dedup_opts, opts); struct btf *btf = linker->btf; const void *raw_data; int i, j, id, err; __u32 raw_sz; /* bail out if no BTF data was produced */ - if (btf__get_nr_types(linker->btf) == 0) + if (btf__type_cnt(linker->btf) == 1) return 0; for (i = 1; i < linker->sec_cnt; i++) { @@ -2691,14 +2691,15 @@ static int finalize_btf(struct bpf_linker *linker) return err; } - err = btf__dedup(linker->btf, linker->btf_ext, NULL); + opts.btf_ext = linker->btf_ext; + err = btf__dedup(linker->btf, &opts); if (err) { pr_warn("BTF dedup failed: %d\n", err); return err; } /* Emit .BTF section */ - raw_data = btf__get_raw_data(linker->btf, &raw_sz); + raw_data = btf__raw_data(linker->btf, &raw_sz); if (!raw_data) return -ENOMEM; diff --git a/tools/lib/bpf/relo_core.c b/tools/lib/bpf/relo_core.c index 4016ed492d..910865e29e 100644 --- a/tools/lib/bpf/relo_core.c +++ b/tools/lib/bpf/relo_core.c @@ -1,6 +1,60 @@ // SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) /* Copyright (c) 2019 Facebook */ +#ifdef __KERNEL__ +#include +#include +#include +#include +#include "relo_core.h" + +static const char *btf_kind_str(const struct btf_type *t) +{ + return btf_type_str(t); +} + +static bool is_ldimm64_insn(struct bpf_insn *insn) +{ + return insn->code == (BPF_LD | BPF_IMM | BPF_DW); +} + +static const struct btf_type * +skip_mods_and_typedefs(const struct btf *btf, u32 id, u32 *res_id) +{ + return btf_type_skip_modifiers(btf, id, res_id); +} + +static const char *btf__name_by_offset(const struct btf *btf, u32 offset) +{ + return btf_name_by_offset(btf, offset); +} + +static s64 btf__resolve_size(const struct btf *btf, u32 type_id) +{ + const struct btf_type *t; + int size; + + t = btf_type_by_id(btf, type_id); + t = btf_resolve_size(btf, t, &size); + if (IS_ERR(t)) + return PTR_ERR(t); + return size; +} + +enum libbpf_print_level { + LIBBPF_WARN, + LIBBPF_INFO, + LIBBPF_DEBUG, +}; + +#undef pr_warn +#undef pr_info +#undef pr_debug +#define pr_warn(fmt, log, ...) bpf_log((void *)log, fmt, "", ##__VA_ARGS__) +#define pr_info(fmt, log, ...) bpf_log((void *)log, fmt, "", ##__VA_ARGS__) +#define pr_debug(fmt, log, ...) bpf_log((void *)log, fmt, "", ##__VA_ARGS__) +#define libbpf_print(level, fmt, ...) bpf_log((void *)prog_name, fmt, ##__VA_ARGS__) +#else #include #include #include @@ -12,33 +66,7 @@ #include "btf.h" #include "str_error.h" #include "libbpf_internal.h" - -#define BPF_CORE_SPEC_MAX_LEN 64 - -/* represents BPF CO-RE field or array element accessor */ -struct bpf_core_accessor { - __u32 type_id; /* struct/union type or array element type */ - __u32 idx; /* field index or array index */ - const char *name; /* field name or NULL for array accessor */ -}; - -struct bpf_core_spec { - const struct btf *btf; - /* high-level spec: named fields and array indices only */ - struct bpf_core_accessor spec[BPF_CORE_SPEC_MAX_LEN]; - /* original unresolved (no skip_mods_or_typedefs) root type ID */ - __u32 root_type_id; - /* CO-RE relocation kind */ - enum bpf_core_relo_kind relo_kind; - /* high-level spec length */ - int len; - /* raw, low-level spec: 1-to-1 with accessor spec string */ - int raw_spec[BPF_CORE_SPEC_MAX_LEN]; - /* raw spec length */ - int raw_len; - /* field bit offset represented by spec */ - __u32 bit_offset; -}; +#endif static bool is_flex_arr(const struct btf *btf, const struct bpf_core_accessor *acc, @@ -51,25 +79,25 @@ static bool is_flex_arr(const struct btf *btf, return false; /* has to be the last member of enclosing struct */ - t = btf__type_by_id(btf, acc->type_id); + t = btf_type_by_id(btf, acc->type_id); return acc->idx == btf_vlen(t) - 1; } static const char *core_relo_kind_str(enum bpf_core_relo_kind kind) { switch (kind) { - case BPF_FIELD_BYTE_OFFSET: return "byte_off"; - case BPF_FIELD_BYTE_SIZE: return "byte_sz"; - case BPF_FIELD_EXISTS: return "field_exists"; - case BPF_FIELD_SIGNED: return "signed"; - case BPF_FIELD_LSHIFT_U64: return "lshift_u64"; - case BPF_FIELD_RSHIFT_U64: return "rshift_u64"; - case BPF_TYPE_ID_LOCAL: return "local_type_id"; - case BPF_TYPE_ID_TARGET: return "target_type_id"; - case BPF_TYPE_EXISTS: return "type_exists"; - case BPF_TYPE_SIZE: return "type_size"; - case BPF_ENUMVAL_EXISTS: return "enumval_exists"; - case BPF_ENUMVAL_VALUE: return "enumval_value"; + case BPF_CORE_FIELD_BYTE_OFFSET: return "byte_off"; + case BPF_CORE_FIELD_BYTE_SIZE: return "byte_sz"; + case BPF_CORE_FIELD_EXISTS: return "field_exists"; + case BPF_CORE_FIELD_SIGNED: return "signed"; + case BPF_CORE_FIELD_LSHIFT_U64: return "lshift_u64"; + case BPF_CORE_FIELD_RSHIFT_U64: return "rshift_u64"; + case BPF_CORE_TYPE_ID_LOCAL: return "local_type_id"; + case BPF_CORE_TYPE_ID_TARGET: return "target_type_id"; + case BPF_CORE_TYPE_EXISTS: return "type_exists"; + case BPF_CORE_TYPE_SIZE: return "type_size"; + case BPF_CORE_ENUMVAL_EXISTS: return "enumval_exists"; + case BPF_CORE_ENUMVAL_VALUE: return "enumval_value"; default: return "unknown"; } } @@ -77,12 +105,12 @@ static const char *core_relo_kind_str(enum bpf_core_relo_kind kind) static bool core_relo_is_field_based(enum bpf_core_relo_kind kind) { switch (kind) { - case BPF_FIELD_BYTE_OFFSET: - case BPF_FIELD_BYTE_SIZE: - case BPF_FIELD_EXISTS: - case BPF_FIELD_SIGNED: - case BPF_FIELD_LSHIFT_U64: - case BPF_FIELD_RSHIFT_U64: + case BPF_CORE_FIELD_BYTE_OFFSET: + case BPF_CORE_FIELD_BYTE_SIZE: + case BPF_CORE_FIELD_EXISTS: + case BPF_CORE_FIELD_SIGNED: + case BPF_CORE_FIELD_LSHIFT_U64: + case BPF_CORE_FIELD_RSHIFT_U64: return true; default: return false; @@ -92,10 +120,10 @@ static bool core_relo_is_field_based(enum bpf_core_relo_kind kind) static bool core_relo_is_type_based(enum bpf_core_relo_kind kind) { switch (kind) { - case BPF_TYPE_ID_LOCAL: - case BPF_TYPE_ID_TARGET: - case BPF_TYPE_EXISTS: - case BPF_TYPE_SIZE: + case BPF_CORE_TYPE_ID_LOCAL: + case BPF_CORE_TYPE_ID_TARGET: + case BPF_CORE_TYPE_EXISTS: + case BPF_CORE_TYPE_SIZE: return true; default: return false; @@ -105,8 +133,8 @@ static bool core_relo_is_type_based(enum bpf_core_relo_kind kind) static bool core_relo_is_enumval_based(enum bpf_core_relo_kind kind) { switch (kind) { - case BPF_ENUMVAL_EXISTS: - case BPF_ENUMVAL_VALUE: + case BPF_CORE_ENUMVAL_EXISTS: + case BPF_CORE_ENUMVAL_VALUE: return true; default: return false; @@ -150,7 +178,7 @@ static bool core_relo_is_enumval_based(enum bpf_core_relo_kind kind) * Enum value-based relocations (ENUMVAL_EXISTS/ENUMVAL_VALUE) use access * string to specify enumerator's value index that need to be relocated. */ -static int bpf_core_parse_spec(const struct btf *btf, +static int bpf_core_parse_spec(const char *prog_name, const struct btf *btf, __u32 type_id, const char *spec_str, enum bpf_core_relo_kind relo_kind, @@ -272,8 +300,8 @@ static int bpf_core_parse_spec(const struct btf *btf, return sz; spec->bit_offset += access_idx * sz * 8; } else { - pr_warn("relo for [%u] %s (at idx %d) captures type [%d] of unexpected kind %s\n", - type_id, spec_str, i, id, btf_kind_str(t)); + pr_warn("prog '%s': relo for [%u] %s (at idx %d) captures type [%d] of unexpected kind %s\n", + prog_name, type_id, spec_str, i, id, btf_kind_str(t)); return -EINVAL; } } @@ -346,8 +374,6 @@ static int bpf_core_fields_are_compat(const struct btf *local_btf, targ_id = btf_array(targ_type)->type; goto recur; default: - pr_warn("unexpected kind %d relocated, local [%d], target [%d]\n", - btf_kind(local_type), local_id, targ_id); return 0; } } @@ -388,7 +414,7 @@ static int bpf_core_match_member(const struct btf *local_btf, return 0; local_id = local_acc->type_id; - local_type = btf__type_by_id(local_btf, local_id); + local_type = btf_type_by_id(local_btf, local_id); local_member = btf_members(local_type) + local_acc->idx; local_name = btf__name_by_offset(local_btf, local_member->name_off); @@ -571,7 +597,7 @@ static int bpf_core_calc_field_relo(const char *prog_name, *field_sz = 0; - if (relo->kind == BPF_FIELD_EXISTS) { + if (relo->kind == BPF_CORE_FIELD_EXISTS) { *val = spec ? 1 : 0; return 0; } @@ -580,11 +606,11 @@ static int bpf_core_calc_field_relo(const char *prog_name, return -EUCLEAN; /* request instruction poisoning */ acc = &spec->spec[spec->len - 1]; - t = btf__type_by_id(spec->btf, acc->type_id); + t = btf_type_by_id(spec->btf, acc->type_id); /* a[n] accessor needs special handling */ if (!acc->name) { - if (relo->kind == BPF_FIELD_BYTE_OFFSET) { + if (relo->kind == BPF_CORE_FIELD_BYTE_OFFSET) { *val = spec->bit_offset / 8; /* remember field size for load/store mem size */ sz = btf__resolve_size(spec->btf, acc->type_id); @@ -592,7 +618,7 @@ static int bpf_core_calc_field_relo(const char *prog_name, return -EINVAL; *field_sz = sz; *type_id = acc->type_id; - } else if (relo->kind == BPF_FIELD_BYTE_SIZE) { + } else if (relo->kind == BPF_CORE_FIELD_BYTE_SIZE) { sz = btf__resolve_size(spec->btf, acc->type_id); if (sz < 0) return -EINVAL; @@ -644,36 +670,36 @@ static int bpf_core_calc_field_relo(const char *prog_name, *validate = !bitfield; switch (relo->kind) { - case BPF_FIELD_BYTE_OFFSET: + case BPF_CORE_FIELD_BYTE_OFFSET: *val = byte_off; if (!bitfield) { *field_sz = byte_sz; *type_id = field_type_id; } break; - case BPF_FIELD_BYTE_SIZE: + case BPF_CORE_FIELD_BYTE_SIZE: *val = byte_sz; break; - case BPF_FIELD_SIGNED: + case BPF_CORE_FIELD_SIGNED: /* enums will be assumed unsigned */ *val = btf_is_enum(mt) || (btf_int_encoding(mt) & BTF_INT_SIGNED); if (validate) *validate = true; /* signedness is never ambiguous */ break; - case BPF_FIELD_LSHIFT_U64: -#if __BYTE_ORDER == __LITTLE_ENDIAN + case BPF_CORE_FIELD_LSHIFT_U64: +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ *val = 64 - (bit_off + bit_sz - byte_off * 8); #else *val = (8 - byte_sz) * 8 + (bit_off - byte_off * 8); #endif break; - case BPF_FIELD_RSHIFT_U64: + case BPF_CORE_FIELD_RSHIFT_U64: *val = 64 - bit_sz; if (validate) *validate = true; /* right shift is never ambiguous */ break; - case BPF_FIELD_EXISTS: + case BPF_CORE_FIELD_EXISTS: default: return -EOPNOTSUPP; } @@ -683,10 +709,14 @@ static int bpf_core_calc_field_relo(const char *prog_name, static int bpf_core_calc_type_relo(const struct bpf_core_relo *relo, const struct bpf_core_spec *spec, - __u32 *val) + __u32 *val, bool *validate) { __s64 sz; + /* by default, always check expected value in bpf_insn */ + if (validate) + *validate = true; + /* type-based relos return zero when target type is not found */ if (!spec) { *val = 0; @@ -694,20 +724,25 @@ static int bpf_core_calc_type_relo(const struct bpf_core_relo *relo, } switch (relo->kind) { - case BPF_TYPE_ID_TARGET: + case BPF_CORE_TYPE_ID_TARGET: *val = spec->root_type_id; + /* type ID, embedded in bpf_insn, might change during linking, + * so enforcing it is pointless + */ + if (validate) + *validate = false; break; - case BPF_TYPE_EXISTS: + case BPF_CORE_TYPE_EXISTS: *val = 1; break; - case BPF_TYPE_SIZE: + case BPF_CORE_TYPE_SIZE: sz = btf__resolve_size(spec->btf, spec->root_type_id); if (sz < 0) return -EINVAL; *val = sz; break; - case BPF_TYPE_ID_LOCAL: - /* BPF_TYPE_ID_LOCAL is handled specially and shouldn't get here */ + case BPF_CORE_TYPE_ID_LOCAL: + /* BPF_CORE_TYPE_ID_LOCAL is handled specially and shouldn't get here */ default: return -EOPNOTSUPP; } @@ -723,13 +758,13 @@ static int bpf_core_calc_enumval_relo(const struct bpf_core_relo *relo, const struct btf_enum *e; switch (relo->kind) { - case BPF_ENUMVAL_EXISTS: + case BPF_CORE_ENUMVAL_EXISTS: *val = spec ? 1 : 0; break; - case BPF_ENUMVAL_VALUE: + case BPF_CORE_ENUMVAL_VALUE: if (!spec) return -EUCLEAN; /* request instruction poisoning */ - t = btf__type_by_id(spec->btf, spec->spec[0].type_id); + t = btf_type_by_id(spec->btf, spec->spec[0].type_id); e = btf_enum(t) + spec->spec[0].idx; *val = e->val; break; @@ -805,8 +840,8 @@ static int bpf_core_calc_relo(const char *prog_name, if (res->orig_sz != res->new_sz) { const struct btf_type *orig_t, *new_t; - orig_t = btf__type_by_id(local_spec->btf, res->orig_type_id); - new_t = btf__type_by_id(targ_spec->btf, res->new_type_id); + orig_t = btf_type_by_id(local_spec->btf, res->orig_type_id); + new_t = btf_type_by_id(targ_spec->btf, res->new_type_id); /* There are two use cases in which it's safe to * adjust load/store's mem size: @@ -835,8 +870,8 @@ static int bpf_core_calc_relo(const char *prog_name, res->fail_memsz_adjust = true; } } else if (core_relo_is_type_based(relo->kind)) { - err = bpf_core_calc_type_relo(relo, local_spec, &res->orig_val); - err = err ?: bpf_core_calc_type_relo(relo, targ_spec, &res->new_val); + err = bpf_core_calc_type_relo(relo, local_spec, &res->orig_val, &res->validate); + err = err ?: bpf_core_calc_type_relo(relo, targ_spec, &res->new_val, NULL); } else if (core_relo_is_enumval_based(relo->kind)) { err = bpf_core_calc_enumval_relo(relo, local_spec, &res->orig_val); err = err ?: bpf_core_calc_enumval_relo(relo, targ_spec, &res->new_val); @@ -1045,7 +1080,7 @@ static int bpf_core_patch_insn(const char *prog_name, struct bpf_insn *insn, * [] () + => @, * where is a C-syntax view of recorded field access, e.g.: x.a[3].b */ -static void bpf_core_dump_spec(int level, const struct bpf_core_spec *spec) +static void bpf_core_dump_spec(const char *prog_name, int level, const struct bpf_core_spec *spec) { const struct btf_type *t; const struct btf_enum *e; @@ -1054,7 +1089,7 @@ static void bpf_core_dump_spec(int level, const struct bpf_core_spec *spec) int i; type_id = spec->root_type_id; - t = btf__type_by_id(spec->btf, type_id); + t = btf_type_by_id(spec->btf, type_id); s = btf__name_by_offset(spec->btf, t->name_off); libbpf_print(level, "[%u] %s %s", type_id, btf_kind_str(t), str_is_empty(s) ? "" : s); @@ -1147,9 +1182,12 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn, const struct bpf_core_relo *relo, int relo_idx, const struct btf *local_btf, - struct bpf_core_cand_list *cands) + struct bpf_core_cand_list *cands, + struct bpf_core_spec *specs_scratch) { - struct bpf_core_spec local_spec, cand_spec, targ_spec = {}; + struct bpf_core_spec *local_spec = &specs_scratch[0]; + struct bpf_core_spec *cand_spec = &specs_scratch[1]; + struct bpf_core_spec *targ_spec = &specs_scratch[2]; struct bpf_core_relo_res cand_res, targ_res; const struct btf_type *local_type; const char *local_name; @@ -1158,10 +1196,7 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn, int i, j, err; local_id = relo->type_id; - local_type = btf__type_by_id(local_btf, local_id); - if (!local_type) - return -EINVAL; - + local_type = btf_type_by_id(local_btf, local_id); local_name = btf__name_by_offset(local_btf, local_type->name_off); if (!local_name) return -EINVAL; @@ -1170,7 +1205,8 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn, if (str_is_empty(spec_str)) return -EINVAL; - err = bpf_core_parse_spec(local_btf, local_id, spec_str, relo->kind, &local_spec); + err = bpf_core_parse_spec(prog_name, local_btf, local_id, spec_str, + relo->kind, local_spec); if (err) { pr_warn("prog '%s': relo #%d: parsing [%d] %s %s + %s failed: %d\n", prog_name, relo_idx, local_id, btf_kind_str(local_type), @@ -1181,15 +1217,17 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn, pr_debug("prog '%s': relo #%d: kind <%s> (%d), spec is ", prog_name, relo_idx, core_relo_kind_str(relo->kind), relo->kind); - bpf_core_dump_spec(LIBBPF_DEBUG, &local_spec); + bpf_core_dump_spec(prog_name, LIBBPF_DEBUG, local_spec); libbpf_print(LIBBPF_DEBUG, "\n"); /* TYPE_ID_LOCAL relo is special and doesn't need candidate search */ - if (relo->kind == BPF_TYPE_ID_LOCAL) { - targ_res.validate = true; + if (relo->kind == BPF_CORE_TYPE_ID_LOCAL) { + /* bpf_insn's imm value could get out of sync during linking */ + memset(&targ_res, 0, sizeof(targ_res)); + targ_res.validate = false; targ_res.poison = false; - targ_res.orig_val = local_spec.root_type_id; - targ_res.new_val = local_spec.root_type_id; + targ_res.orig_val = local_spec->root_type_id; + targ_res.new_val = local_spec->root_type_id; goto patch_insn; } @@ -1200,40 +1238,39 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn, return -EOPNOTSUPP; } - for (i = 0, j = 0; i < cands->len; i++) { - err = bpf_core_spec_match(&local_spec, cands->cands[i].btf, - cands->cands[i].id, &cand_spec); + err = bpf_core_spec_match(local_spec, cands->cands[i].btf, + cands->cands[i].id, cand_spec); if (err < 0) { pr_warn("prog '%s': relo #%d: error matching candidate #%d ", prog_name, relo_idx, i); - bpf_core_dump_spec(LIBBPF_WARN, &cand_spec); + bpf_core_dump_spec(prog_name, LIBBPF_WARN, cand_spec); libbpf_print(LIBBPF_WARN, ": %d\n", err); return err; } pr_debug("prog '%s': relo #%d: %s candidate #%d ", prog_name, relo_idx, err == 0 ? "non-matching" : "matching", i); - bpf_core_dump_spec(LIBBPF_DEBUG, &cand_spec); + bpf_core_dump_spec(prog_name, LIBBPF_DEBUG, cand_spec); libbpf_print(LIBBPF_DEBUG, "\n"); if (err == 0) continue; - err = bpf_core_calc_relo(prog_name, relo, relo_idx, &local_spec, &cand_spec, &cand_res); + err = bpf_core_calc_relo(prog_name, relo, relo_idx, local_spec, cand_spec, &cand_res); if (err) return err; if (j == 0) { targ_res = cand_res; - targ_spec = cand_spec; - } else if (cand_spec.bit_offset != targ_spec.bit_offset) { + *targ_spec = *cand_spec; + } else if (cand_spec->bit_offset != targ_spec->bit_offset) { /* if there are many field relo candidates, they * should all resolve to the same bit offset */ pr_warn("prog '%s': relo #%d: field offset ambiguity: %u != %u\n", - prog_name, relo_idx, cand_spec.bit_offset, - targ_spec.bit_offset); + prog_name, relo_idx, cand_spec->bit_offset, + targ_spec->bit_offset); return -EINVAL; } else if (cand_res.poison != targ_res.poison || cand_res.new_val != targ_res.new_val) { /* all candidates should result in the same relocation @@ -1251,7 +1288,7 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn, } /* - * For BPF_FIELD_EXISTS relo or when used BPF program has field + * For BPF_CORE_FIELD_EXISTS relo or when used BPF program has field * existence checks or kernel version/config checks, it's expected * that we might not find any candidates. In this case, if field * wasn't found in any candidate, the list of candidates shouldn't @@ -1277,7 +1314,7 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn, prog_name, relo_idx); /* calculate single target relo result explicitly */ - err = bpf_core_calc_relo(prog_name, relo, relo_idx, &local_spec, NULL, &targ_res); + err = bpf_core_calc_relo(prog_name, relo, relo_idx, local_spec, NULL, &targ_res); if (err) return err; } diff --git a/tools/lib/bpf/relo_core.h b/tools/lib/bpf/relo_core.h index 3b9f8f1834..17799819ad 100644 --- a/tools/lib/bpf/relo_core.h +++ b/tools/lib/bpf/relo_core.h @@ -4,81 +4,10 @@ #ifndef __RELO_CORE_H #define __RELO_CORE_H -/* bpf_core_relo_kind encodes which aspect of captured field/type/enum value - * has to be adjusted by relocations. - */ -enum bpf_core_relo_kind { - BPF_FIELD_BYTE_OFFSET = 0, /* field byte offset */ - BPF_FIELD_BYTE_SIZE = 1, /* field size in bytes */ - BPF_FIELD_EXISTS = 2, /* field existence in target kernel */ - BPF_FIELD_SIGNED = 3, /* field signedness (0 - unsigned, 1 - signed) */ - BPF_FIELD_LSHIFT_U64 = 4, /* bitfield-specific left bitshift */ - BPF_FIELD_RSHIFT_U64 = 5, /* bitfield-specific right bitshift */ - BPF_TYPE_ID_LOCAL = 6, /* type ID in local BPF object */ - BPF_TYPE_ID_TARGET = 7, /* type ID in target kernel */ - BPF_TYPE_EXISTS = 8, /* type existence in target kernel */ - BPF_TYPE_SIZE = 9, /* type size in bytes */ - BPF_ENUMVAL_EXISTS = 10, /* enum value existence in target kernel */ - BPF_ENUMVAL_VALUE = 11, /* enum value integer value */ -}; - -/* The minimum bpf_core_relo checked by the loader - * - * CO-RE relocation captures the following data: - * - insn_off - instruction offset (in bytes) within a BPF program that needs - * its insn->imm field to be relocated with actual field info; - * - type_id - BTF type ID of the "root" (containing) entity of a relocatable - * type or field; - * - access_str_off - offset into corresponding .BTF string section. String - * interpretation depends on specific relocation kind: - * - for field-based relocations, string encodes an accessed field using - * a sequence of field and array indices, separated by colon (:). It's - * conceptually very close to LLVM's getelementptr ([0]) instruction's - * arguments for identifying offset to a field. - * - for type-based relocations, strings is expected to be just "0"; - * - for enum value-based relocations, string contains an index of enum - * value within its enum type; - * - * Example to provide a better feel. - * - * struct sample { - * int a; - * struct { - * int b[10]; - * }; - * }; - * - * struct sample *s = ...; - * int x = &s->a; // encoded as "0:0" (a is field #0) - * int y = &s->b[5]; // encoded as "0:1:0:5" (anon struct is field #1, - * // b is field #0 inside anon struct, accessing elem #5) - * int z = &s[10]->b; // encoded as "10:1" (ptr is used as an array) - * - * type_id for all relocs in this example will capture BTF type id of - * `struct sample`. - * - * Such relocation is emitted when using __builtin_preserve_access_index() - * Clang built-in, passing expression that captures field address, e.g.: - * - * bpf_probe_read(&dst, sizeof(dst), - * __builtin_preserve_access_index(&src->a.b.c)); - * - * In this case Clang will emit field relocation recording necessary data to - * be able to find offset of embedded `a.b.c` field within `src` struct. - * - * [0] https://llvm.org/docs/LangRef.html#getelementptr-instruction - */ -struct bpf_core_relo { - __u32 insn_off; - __u32 type_id; - __u32 access_str_off; - enum bpf_core_relo_kind kind; -}; +#include struct bpf_core_cand { const struct btf *btf; - const struct btf_type *t; - const char *name; __u32 id; }; @@ -88,11 +17,39 @@ struct bpf_core_cand_list { int len; }; +#define BPF_CORE_SPEC_MAX_LEN 64 + +/* represents BPF CO-RE field or array element accessor */ +struct bpf_core_accessor { + __u32 type_id; /* struct/union type or array element type */ + __u32 idx; /* field index or array index */ + const char *name; /* field name or NULL for array accessor */ +}; + +struct bpf_core_spec { + const struct btf *btf; + /* high-level spec: named fields and array indices only */ + struct bpf_core_accessor spec[BPF_CORE_SPEC_MAX_LEN]; + /* original unresolved (no skip_mods_or_typedefs) root type ID */ + __u32 root_type_id; + /* CO-RE relocation kind */ + enum bpf_core_relo_kind relo_kind; + /* high-level spec length */ + int len; + /* raw, low-level spec: 1-to-1 with accessor spec string */ + int raw_spec[BPF_CORE_SPEC_MAX_LEN]; + /* raw spec length */ + int raw_len; + /* field bit offset represented by spec */ + __u32 bit_offset; +}; + int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn, int insn_idx, const struct bpf_core_relo *relo, int relo_idx, const struct btf *local_btf, - struct bpf_core_cand_list *cands); + struct bpf_core_cand_list *cands, + struct bpf_core_spec *specs_scratch); int bpf_core_types_are_compat(const struct btf *local_btf, __u32 local_id, const struct btf *targ_btf, __u32 targ_id); diff --git a/tools/lib/bpf/skel_internal.h b/tools/lib/bpf/skel_internal.h index 9cf66702fa..0b84d8e6b7 100644 --- a/tools/lib/bpf/skel_internal.h +++ b/tools/lib/bpf/skel_internal.h @@ -7,6 +7,16 @@ #include #include +#ifndef __NR_bpf +# if defined(__mips__) && defined(_ABIO32) +# define __NR_bpf 4355 +# elif defined(__mips__) && defined(_ABIN32) +# define __NR_bpf 6319 +# elif defined(__mips__) && defined(_ABI64) +# define __NR_bpf 5315 +# endif +#endif + /* This file is a base header for auto-generated *.lskel.h files. * Its contents will change and may become part of auto-generation in the future. * @@ -65,8 +75,7 @@ static inline int bpf_load_and_run(struct bpf_load_and_run_opts *opts) int map_fd = -1, prog_fd = -1, key = 0, err; union bpf_attr attr; - map_fd = bpf_create_map_name(BPF_MAP_TYPE_ARRAY, "__loader.map", 4, - opts->data_sz, 1, 0); + map_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, "__loader.map", 4, opts->data_sz, 1, NULL); if (map_fd < 0) { opts->errstr = "failed to create loader map"; err = -errno; diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c index e9b619aa0c..edafe56664 100644 --- a/tools/lib/bpf/xsk.c +++ b/tools/lib/bpf/xsk.c @@ -35,6 +35,11 @@ #include "libbpf_internal.h" #include "xsk.h" +/* entire xsk.h and xsk.c is going away in libbpf 1.0, so ignore all internal + * uses of deprecated APIs + */ +#pragma GCC diagnostic ignored "-Wdeprecated-declarations" + #ifndef SOL_XDP #define SOL_XDP 283 #endif @@ -281,6 +286,7 @@ static int xsk_create_umem_rings(struct xsk_umem *umem, int fd, return err; } +DEFAULT_VERSION(xsk_umem__create_v0_0_4, xsk_umem__create, LIBBPF_0.0.4) int xsk_umem__create_v0_0_4(struct xsk_umem **umem_ptr, void *umem_area, __u64 size, struct xsk_ring_prod *fill, struct xsk_ring_cons *comp, @@ -299,7 +305,7 @@ int xsk_umem__create_v0_0_4(struct xsk_umem **umem_ptr, void *umem_area, if (!umem) return -ENOMEM; - umem->fd = socket(AF_XDP, SOCK_RAW, 0); + umem->fd = socket(AF_XDP, SOCK_RAW | SOCK_CLOEXEC, 0); if (umem->fd < 0) { err = -errno; goto out_umem_alloc; @@ -345,6 +351,7 @@ struct xsk_umem_config_v1 { __u32 frame_headroom; }; +COMPAT_VERSION(xsk_umem__create_v0_0_2, xsk_umem__create, LIBBPF_0.0.2) int xsk_umem__create_v0_0_2(struct xsk_umem **umem_ptr, void *umem_area, __u64 size, struct xsk_ring_prod *fill, struct xsk_ring_cons *comp, @@ -358,14 +365,10 @@ int xsk_umem__create_v0_0_2(struct xsk_umem **umem_ptr, void *umem_area, return xsk_umem__create_v0_0_4(umem_ptr, umem_area, size, fill, comp, &config); } -COMPAT_VERSION(xsk_umem__create_v0_0_2, xsk_umem__create, LIBBPF_0.0.2) -DEFAULT_VERSION(xsk_umem__create_v0_0_4, xsk_umem__create, LIBBPF_0.0.4) static enum xsk_prog get_xsk_prog(void) { enum xsk_prog detected = XSK_PROG_FALLBACK; - struct bpf_load_program_attr prog_attr; - struct bpf_create_map_attr map_attr; __u32 size_out, retval, duration; char data_in = 0, data_out; struct bpf_insn insns[] = { @@ -375,27 +378,15 @@ static enum xsk_prog get_xsk_prog(void) BPF_EMIT_CALL(BPF_FUNC_redirect_map), BPF_EXIT_INSN(), }; - int prog_fd, map_fd, ret; + int prog_fd, map_fd, ret, insn_cnt = ARRAY_SIZE(insns); - memset(&map_attr, 0, sizeof(map_attr)); - map_attr.map_type = BPF_MAP_TYPE_XSKMAP; - map_attr.key_size = sizeof(int); - map_attr.value_size = sizeof(int); - map_attr.max_entries = 1; - - map_fd = bpf_create_map_xattr(&map_attr); + map_fd = bpf_map_create(BPF_MAP_TYPE_XSKMAP, NULL, sizeof(int), sizeof(int), 1, NULL); if (map_fd < 0) return detected; insns[0].imm = map_fd; - memset(&prog_attr, 0, sizeof(prog_attr)); - prog_attr.prog_type = BPF_PROG_TYPE_XDP; - prog_attr.insns = insns; - prog_attr.insns_cnt = ARRAY_SIZE(insns); - prog_attr.license = "GPL"; - - prog_fd = bpf_load_program_xattr(&prog_attr, NULL, 0); + prog_fd = bpf_prog_load(BPF_PROG_TYPE_XDP, NULL, "GPL", insns, insn_cnt, NULL); if (prog_fd < 0) { close(map_fd); return detected; @@ -495,10 +486,13 @@ static int xsk_load_xdp_prog(struct xsk_socket *xsk) }; struct bpf_insn *progs[] = {prog, prog_redirect_flags}; enum xsk_prog option = get_xsk_prog(); + LIBBPF_OPTS(bpf_prog_load_opts, opts, + .log_buf = log_buf, + .log_size = log_buf_size, + ); - prog_fd = bpf_load_program(BPF_PROG_TYPE_XDP, progs[option], insns_cnt[option], - "LGPL-2.1 or BSD-2-Clause", 0, log_buf, - log_buf_size); + prog_fd = bpf_prog_load(BPF_PROG_TYPE_XDP, NULL, "LGPL-2.1 or BSD-2-Clause", + progs[option], insns_cnt[option], &opts); if (prog_fd < 0) { pr_warn("BPF log buffer:\n%s", log_buf); return prog_fd; @@ -549,13 +543,12 @@ static int xsk_get_max_queues(struct xsk_socket *xsk) struct ifreq ifr = {}; int fd, err, ret; - fd = socket(AF_LOCAL, SOCK_DGRAM, 0); + fd = socket(AF_LOCAL, SOCK_DGRAM | SOCK_CLOEXEC, 0); if (fd < 0) return -errno; ifr.ifr_data = (void *)&channels; - memcpy(ifr.ifr_name, ctx->ifname, IFNAMSIZ - 1); - ifr.ifr_name[IFNAMSIZ - 1] = '\0'; + libbpf_strlcpy(ifr.ifr_name, ctx->ifname, IFNAMSIZ); err = ioctl(fd, SIOCETHTOOL, &ifr); if (err && errno != EOPNOTSUPP) { ret = -errno; @@ -590,8 +583,8 @@ static int xsk_create_bpf_maps(struct xsk_socket *xsk) if (max_queues < 0) return max_queues; - fd = bpf_create_map_name(BPF_MAP_TYPE_XSKMAP, "xsks_map", - sizeof(int), sizeof(int), max_queues, 0); + fd = bpf_map_create(BPF_MAP_TYPE_XSKMAP, "xsks_map", + sizeof(int), sizeof(int), max_queues, NULL); if (fd < 0) return fd; @@ -725,14 +718,12 @@ static int xsk_link_lookup(int ifindex, __u32 *prog_id, int *link_fd) static bool xsk_probe_bpf_link(void) { - DECLARE_LIBBPF_OPTS(bpf_link_create_opts, opts, - .flags = XDP_FLAGS_SKB_MODE); - struct bpf_load_program_attr prog_attr; + LIBBPF_OPTS(bpf_link_create_opts, opts, .flags = XDP_FLAGS_SKB_MODE); struct bpf_insn insns[2] = { BPF_MOV64_IMM(BPF_REG_0, XDP_PASS), BPF_EXIT_INSN() }; - int prog_fd, link_fd = -1; + int prog_fd, link_fd = -1, insn_cnt = ARRAY_SIZE(insns); int ifindex_lo = 1; bool ret = false; int err; @@ -744,13 +735,7 @@ static bool xsk_probe_bpf_link(void) if (link_fd >= 0) return true; - memset(&prog_attr, 0, sizeof(prog_attr)); - prog_attr.prog_type = BPF_PROG_TYPE_XDP; - prog_attr.insns = insns; - prog_attr.insns_cnt = ARRAY_SIZE(insns); - prog_attr.license = "GPL"; - - prog_fd = bpf_load_program_xattr(&prog_attr, NULL, 0); + prog_fd = bpf_prog_load(BPF_PROG_TYPE_XDP, NULL, "GPL", insns, insn_cnt, NULL); if (prog_fd < 0) return ret; @@ -782,8 +767,7 @@ static int xsk_create_xsk_struct(int ifindex, struct xsk_socket *xsk) } ctx->ifindex = ifindex; - memcpy(ctx->ifname, ifname, IFNAMSIZ -1); - ctx->ifname[IFNAMSIZ - 1] = 0; + libbpf_strlcpy(ctx->ifname, ifname, IFNAMSIZ); xsk->ctx = ctx; xsk->ctx->has_bpf_link = xsk_probe_bpf_link(); @@ -965,8 +949,7 @@ static struct xsk_ctx *xsk_create_ctx(struct xsk_socket *xsk, ctx->refcount = 1; ctx->umem = umem; ctx->queue_id = queue_id; - memcpy(ctx->ifname, ifname, IFNAMSIZ - 1); - ctx->ifname[IFNAMSIZ - 1] = '\0'; + libbpf_strlcpy(ctx->ifname, ifname, IFNAMSIZ); ctx->fill = fill; ctx->comp = comp; @@ -1046,7 +1029,7 @@ int xsk_socket__create_shared(struct xsk_socket **xsk_ptr, } if (umem->refcount++ > 0) { - xsk->fd = socket(AF_XDP, SOCK_RAW, 0); + xsk->fd = socket(AF_XDP, SOCK_RAW | SOCK_CLOEXEC, 0); if (xsk->fd < 0) { err = -errno; goto out_xsk_alloc; diff --git a/tools/lib/bpf/xsk.h b/tools/lib/bpf/xsk.h index 01c12dca9c..64e9c57fd7 100644 --- a/tools/lib/bpf/xsk.h +++ b/tools/lib/bpf/xsk.h @@ -23,6 +23,12 @@ extern "C" { #endif +/* This whole API has been deprecated and moved to libxdp that can be found at + * https://github.com/xdp-project/xdp-tools. The APIs are exactly the same so + * it should just be linking with libxdp instead of libbpf for this set of + * functionality. If not, please submit a bug report on the aforementioned page. + */ + /* Load-Acquire Store-Release barriers used by the XDP socket * library. The following macros should *NOT* be considered part of * the xsk.h API, and is subject to change anytime. @@ -245,8 +251,10 @@ static inline __u64 xsk_umem__add_offset_to_addr(__u64 addr) return xsk_umem__extract_addr(addr) + xsk_umem__extract_offset(addr); } -LIBBPF_API int xsk_umem__fd(const struct xsk_umem *umem); -LIBBPF_API int xsk_socket__fd(const struct xsk_socket *xsk); +LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp") +int xsk_umem__fd(const struct xsk_umem *umem); +LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp") +int xsk_socket__fd(const struct xsk_socket *xsk); #define XSK_RING_CONS__DEFAULT_NUM_DESCS 2048 #define XSK_RING_PROD__DEFAULT_NUM_DESCS 2048 @@ -263,10 +271,10 @@ struct xsk_umem_config { __u32 flags; }; -LIBBPF_API int xsk_setup_xdp_prog(int ifindex, - int *xsks_map_fd); -LIBBPF_API int xsk_socket__update_xskmap(struct xsk_socket *xsk, - int xsks_map_fd); +LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp") +int xsk_setup_xdp_prog(int ifindex, int *xsks_map_fd); +LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp") +int xsk_socket__update_xskmap(struct xsk_socket *xsk, int xsks_map_fd); /* Flags for the libbpf_flags field. */ #define XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD (1 << 0) @@ -280,40 +288,46 @@ struct xsk_socket_config { }; /* Set config to NULL to get the default configuration. */ -LIBBPF_API int xsk_umem__create(struct xsk_umem **umem, - void *umem_area, __u64 size, - struct xsk_ring_prod *fill, - struct xsk_ring_cons *comp, - const struct xsk_umem_config *config); -LIBBPF_API int xsk_umem__create_v0_0_2(struct xsk_umem **umem, - void *umem_area, __u64 size, - struct xsk_ring_prod *fill, - struct xsk_ring_cons *comp, - const struct xsk_umem_config *config); -LIBBPF_API int xsk_umem__create_v0_0_4(struct xsk_umem **umem, - void *umem_area, __u64 size, - struct xsk_ring_prod *fill, - struct xsk_ring_cons *comp, - const struct xsk_umem_config *config); -LIBBPF_API int xsk_socket__create(struct xsk_socket **xsk, - const char *ifname, __u32 queue_id, - struct xsk_umem *umem, - struct xsk_ring_cons *rx, - struct xsk_ring_prod *tx, - const struct xsk_socket_config *config); -LIBBPF_API int -xsk_socket__create_shared(struct xsk_socket **xsk_ptr, - const char *ifname, - __u32 queue_id, struct xsk_umem *umem, - struct xsk_ring_cons *rx, - struct xsk_ring_prod *tx, - struct xsk_ring_prod *fill, - struct xsk_ring_cons *comp, - const struct xsk_socket_config *config); +LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp") +int xsk_umem__create(struct xsk_umem **umem, + void *umem_area, __u64 size, + struct xsk_ring_prod *fill, + struct xsk_ring_cons *comp, + const struct xsk_umem_config *config); +LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp") +int xsk_umem__create_v0_0_2(struct xsk_umem **umem, + void *umem_area, __u64 size, + struct xsk_ring_prod *fill, + struct xsk_ring_cons *comp, + const struct xsk_umem_config *config); +LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp") +int xsk_umem__create_v0_0_4(struct xsk_umem **umem, + void *umem_area, __u64 size, + struct xsk_ring_prod *fill, + struct xsk_ring_cons *comp, + const struct xsk_umem_config *config); +LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp") +int xsk_socket__create(struct xsk_socket **xsk, + const char *ifname, __u32 queue_id, + struct xsk_umem *umem, + struct xsk_ring_cons *rx, + struct xsk_ring_prod *tx, + const struct xsk_socket_config *config); +LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp") +int xsk_socket__create_shared(struct xsk_socket **xsk_ptr, + const char *ifname, + __u32 queue_id, struct xsk_umem *umem, + struct xsk_ring_cons *rx, + struct xsk_ring_prod *tx, + struct xsk_ring_prod *fill, + struct xsk_ring_cons *comp, + const struct xsk_socket_config *config); /* Returns 0 for success and -EBUSY if the umem is still in use. */ -LIBBPF_API int xsk_umem__delete(struct xsk_umem *umem); -LIBBPF_API void xsk_socket__delete(struct xsk_socket *xsk); +LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp") +int xsk_umem__delete(struct xsk_umem *umem); +LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp") +void xsk_socket__delete(struct xsk_socket *xsk); #ifdef __cplusplus } /* extern "C" */ diff --git a/tools/lib/find_bit.c b/tools/lib/find_bit.c index 109aa7ffcf..ba4b8d94e0 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 63ae5e0195..32c5051c24 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 6d8e521c59..ee66760f1e 100644 --- a/tools/lib/perf/cpumap.c +++ b/tools/lib/perf/cpumap.c @@ -10,15 +10,24 @@ #include #include -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 @@ struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list) 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) @@ -265,25 +276,47 @@ 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 i; + int low, high; - for (i = 0; i < cpus->nr; ++i) { - if (cpus->map[i] == cpu) - return i; + if (!cpus) + return -1; + + low = 0; + high = cpus->nr; + while (low < high) { + int idx = (low + high) / 2; + struct perf_cpu cpu_at_idx = cpus->map[idx]; + + if (cpu_at_idx.cpu == cpu.cpu) + return idx; + + if (cpu_at_idx.cpu > cpu.cpu) + high = idx; + else + low = idx + 1; } 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; } /* @@ -297,7 +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; @@ -311,19 +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 e37dfad313..9a770bfdc8 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 8441e3e1aa..210ea7c06c 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 840d403258..1973a18c09 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 +#include +/** + * 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 f366dbad6a..4cefade540 100644 --- a/tools/lib/perf/include/internal/evlist.h +++ b/tools/lib/perf/include/internal/evlist.h @@ -4,6 +4,7 @@ #include #include +#include #include #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 1f3eacbad2..cfc9ebd796 100644 --- a/tools/lib/perf/include/internal/evsel.h +++ b/tools/lib/perf/include/internal/evsel.h @@ -6,8 +6,8 @@ #include #include #include +#include -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 5e3422f40e..5a062af8e9 100644 --- a/tools/lib/perf/include/internal/mmap.h +++ b/tools/lib/perf/include/internal/mmap.h @@ -6,6 +6,7 @@ #include #include #include +#include /* 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 7c27766ea0..4a2edbdb5e 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 +#include #include #include -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/event.h b/tools/lib/perf/include/perf/event.h index 4d0c02ba3f..75ee385fb0 100644 --- a/tools/lib/perf/include/perf/event.h +++ b/tools/lib/perf/include/perf/event.h @@ -289,6 +289,11 @@ struct perf_record_itrace_start { __u32 tid; }; +struct perf_record_aux_output_hw_id { + struct perf_event_header header; + __u64 hw_id; +}; + struct perf_record_thread_map_entry { __u64 pid; char comm[16]; @@ -414,6 +419,7 @@ union perf_event { struct perf_record_auxtrace_error auxtrace_error; struct perf_record_aux aux; struct perf_record_itrace_start itrace_start; + struct perf_record_aux_output_hw_id aux_output_hw_id; struct perf_record_switch context_switch; struct perf_record_thread_map thread_map; struct perf_record_cpu_map cpu_map; diff --git a/tools/lib/perf/include/perf/evsel.h b/tools/lib/perf/include/perf/evsel.h index 60eae25076..2a9516b42d 100644 --- a/tools/lib/perf/include/perf/evsel.h +++ b/tools/lib/perf/include/perf/evsel.h @@ -4,6 +4,8 @@ #include #include +#include +#include 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 71468606e8..6fa0d65157 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 c89dfa5f67..0d1634cedf 100644 --- a/tools/lib/perf/mmap.c +++ b/tools/lib/perf/mmap.c @@ -13,6 +13,7 @@ #include #include #include +#include #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 + */ +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 d39378eaf8..87b0510a55 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 ce91a582f0..fa854c83b7 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 #include #include #include @@ -21,6 +22,9 @@ #include "tests.h" #include +#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 33ae933486..89be89afb2 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/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c index fe58843d04..8e24c4c78c 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 a67ad9a5b8..41d4f9f6a8 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 368826bb5a..5df177070d 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 5d72f3112e..394ee57d58 100644 --- a/tools/memory-model/Documentation/explanation.txt +++ b/tools/memory-model/Documentation/explanation.txt @@ -1813,15 +1813,16 @@ 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 +1831,9 @@ 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 +1843,10 @@ 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 +1873,13 @@ 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 +1909,12 @@ 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 9a84c45504..9edd402704 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 2a9b4fe4a8..d70315fdde 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/README b/tools/memory-model/litmus-tests/README index 681f9067fa..d311a0ff1a 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 77b51600e3..c10ef78df0 100644 --- a/tools/objtool/arch/x86/decode.c +++ b/tools/objtool/arch/x86/decode.c @@ -20,6 +20,7 @@ #include #include #include +#include #include static int is_x86_64(const struct elf *elf) @@ -102,12 +103,13 @@ unsigned long arch_jump_destination(struct instruction *insn) #define rm_is_mem(reg) (mod_is_mem() && !is_RIP() && rm_is(reg)) #define rm_is_reg(reg) (mod_is_reg() && modrm_rm == (reg)) -int arch_decode_instruction(const struct elf *elf, const struct section *sec, +int arch_decode_instruction(struct objtool_file *file, const struct section *sec, unsigned long offset, unsigned int maxlen, unsigned int *len, enum insn_type *type, unsigned long *immediate, struct list_head *ops_list) { + const struct elf *elf = file->elf; struct insn insn; int x86_64, ret; unsigned char op1, op2, @@ -529,6 +531,11 @@ int arch_decode_instruction(const struct elf *elf, const struct section *sec, } break; + case 0xcc: + /* int3 */ + *type = INSN_TRAP; + break; + case 0xe3: /* jecxz/jrcxz */ *type = INSN_JUMP_CONDITIONAL; @@ -544,6 +551,36 @@ int arch_decode_instruction(const struct elf *elf, const struct section *sec, *type = INSN_RETURN; break; + case 0xc7: /* mov imm, r/m */ + if (!noinstr) + break; + + if (insn.length == 3+4+4 && !strncmp(sec->name, ".init.text", 10)) { + struct reloc *immr, *disp; + struct symbol *func; + int idx; + + immr = find_reloc_by_dest(elf, (void *)sec, offset+3); + disp = find_reloc_by_dest(elf, (void *)sec, offset+7); + + if (!immr || strcmp(immr->sym->name, "pv_ops")) + break; + + idx = (immr->addend + 8) / sizeof(void *); + + func = disp->sym; + if (disp->sym->type == STT_SECTION) + func = find_symbol_by_offset(disp->sym->sec, disp->addend); + if (!func) { + WARN("no func for pv_ops[]"); + return -1; + } + + objtool_pv_add(file, idx, func); + } + + break; + case 0xcf: /* iret */ /* * Handle sync_core(), which has an IRET to self. @@ -665,10 +702,10 @@ 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) { @@ -679,154 +716,32 @@ const char *arch_ret_insn(int len) return ret[len-1]; } -/* asm/alternative.h ? */ - -#define ALTINSTR_FLAG_INV (1 << 15) -#define ALT_NOT(feat) ((feat) | ALTINSTR_FLAG_INV) - -struct alt_instr { - s32 instr_offset; /* original instruction */ - s32 repl_offset; /* offset to replacement instruction */ - u16 cpuid; /* cpuid bit set for replacement */ - u8 instrlen; /* length of original instruction */ - u8 replacementlen; /* length of new instruction */ -} __packed; - -static int elf_add_alternative(struct elf *elf, - struct instruction *orig, struct symbol *sym, - int cpuid, u8 orig_len, u8 repl_len) +int arch_decode_hint_reg(u8 sp_reg, int *base) { - const int size = sizeof(struct alt_instr); - struct alt_instr *alt; - struct section *sec; - Elf_Scn *s; - - sec = find_section_by_name(elf, ".altinstructions"); - if (!sec) { - sec = elf_create_section(elf, ".altinstructions", - SHF_ALLOC, 0, 0); - - if (!sec) { - WARN_ELF("elf_create_section"); - return -1; - } - } - - s = elf_getscn(elf->elf, sec->idx); - if (!s) { - WARN_ELF("elf_getscn"); - return -1; - } - - sec->data = elf_newdata(s); - if (!sec->data) { - WARN_ELF("elf_newdata"); - return -1; - } - - sec->data->d_size = size; - sec->data->d_align = 1; - - alt = sec->data->d_buf = malloc(size); - if (!sec->data->d_buf) { - perror("malloc"); - return -1; - } - memset(sec->data->d_buf, 0, size); - - if (elf_add_reloc_to_insn(elf, sec, sec->sh.sh_size, - R_X86_64_PC32, orig->sec, orig->offset)) { - WARN("elf_create_reloc: alt_instr::instr_offset"); - return -1; - } - - if (elf_add_reloc(elf, sec, sec->sh.sh_size + 4, - R_X86_64_PC32, sym, 0)) { - WARN("elf_create_reloc: alt_instr::repl_offset"); - return -1; - } - - alt->cpuid = bswap_if_needed(cpuid); - alt->instrlen = orig_len; - alt->replacementlen = repl_len; - - sec->sh.sh_size += size; - sec->changed = true; - - return 0; -} - -#define X86_FEATURE_RETPOLINE ( 7*32+12) - -int arch_rewrite_retpolines(struct objtool_file *file) -{ - struct instruction *insn; - struct reloc *reloc; - struct symbol *sym; - char name[32] = ""; - - list_for_each_entry(insn, &file->retpoline_call_list, call_node) { - - if (insn->type != INSN_JUMP_DYNAMIC && - insn->type != INSN_CALL_DYNAMIC) - continue; - - if (!strcmp(insn->sec->name, ".text.__x86.indirect_thunk")) - continue; - - reloc = insn->reloc; - - sprintf(name, "__x86_indirect_alt_%s_%s", - insn->type == INSN_JUMP_DYNAMIC ? "jmp" : "call", - reloc->sym->name + 21); - - sym = find_symbol_by_name(file->elf, name); - if (!sym) { - sym = elf_create_undef_symbol(file->elf, name); - if (!sym) { - WARN("elf_create_undef_symbol"); - return -1; - } - } - - if (elf_add_alternative(file->elf, insn, sym, - ALT_NOT(X86_FEATURE_RETPOLINE), 5, 5)) { - WARN("elf_add_alternative"); - return -1; - } - } - - return 0; -} - -int arch_decode_hint_reg(struct instruction *insn, u8 sp_reg) -{ - struct cfi_reg *cfa = &insn->cfi.cfa; - switch (sp_reg) { case ORC_REG_UNDEFINED: - cfa->base = CFI_UNDEFINED; + *base = CFI_UNDEFINED; break; case ORC_REG_SP: - cfa->base = CFI_SP; + *base = CFI_SP; break; case ORC_REG_BP: - cfa->base = CFI_BP; + *base = CFI_BP; break; case ORC_REG_SP_INDIRECT: - cfa->base = CFI_SP_INDIRECT; + *base = CFI_SP_INDIRECT; break; case ORC_REG_R10: - cfa->base = CFI_R10; + *base = CFI_R10; break; case ORC_REG_R13: - cfa->base = CFI_R13; + *base = CFI_R13; break; case ORC_REG_DI: - cfa->base = CFI_DI; + *base = CFI_DI; break; case ORC_REG_DX: - cfa->base = CFI_DX; + *base = CFI_DX; break; default: return -1; diff --git a/tools/objtool/builtin-check.c b/tools/objtool/builtin-check.c index 8b38b5d6fe..38070f2610 100644 --- a/tools/objtool/builtin-check.c +++ b/tools/objtool/builtin-check.c @@ -20,7 +20,7 @@ #include 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 [] 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 81982948f9..7c33ec67c4 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -5,6 +5,7 @@ #include #include +#include #include #include @@ -26,7 +27,11 @@ struct alternative { bool skip_orig; }; -struct cfi_init_state initial_func_cfi; +static unsigned long nr_cfi, nr_cfi_reused, nr_cfi_cache; + +static struct cfi_init_state initial_func_cfi; +static struct cfi_state init_cfi; +static struct cfi_state func_cfi; struct instruction *find_insn(struct objtool_file *file, struct section *sec, unsigned long offset) @@ -163,14 +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", @@ -266,6 +273,78 @@ static void init_insn_state(struct insn_state *state, struct section *sec) state->noinstr = sec->noinstr; } +static struct cfi_state *cfi_alloc(void) +{ + struct cfi_state *cfi = calloc(sizeof(struct cfi_state), 1); + if (!cfi) { + WARN("calloc failed"); + exit(1); + } + nr_cfi++; + return cfi; +} + +static int cfi_bits; +static struct hlist_head *cfi_hash; + +static inline bool cficmp(struct cfi_state *cfi1, struct cfi_state *cfi2) +{ + return memcmp((void *)cfi1 + sizeof(cfi1->hash), + (void *)cfi2 + sizeof(cfi2->hash), + sizeof(struct cfi_state) - sizeof(struct hlist_node)); +} + +static inline u32 cfi_key(struct cfi_state *cfi) +{ + return jhash((void *)cfi + sizeof(cfi->hash), + sizeof(*cfi) - sizeof(cfi->hash), 0); +} + +static struct cfi_state *cfi_hash_find_or_add(struct cfi_state *cfi) +{ + struct hlist_head *head = &cfi_hash[hash_min(cfi_key(cfi), cfi_bits)]; + struct cfi_state *obj; + + hlist_for_each_entry(obj, head, hash) { + if (!cficmp(cfi, obj)) { + nr_cfi_cache++; + return obj; + } + } + + obj = cfi_alloc(); + *obj = *cfi; + hlist_add_head(&obj->hash, head); + + return obj; +} + +static void cfi_hash_add(struct cfi_state *cfi) +{ + struct hlist_head *head = &cfi_hash[hash_min(cfi_key(cfi), cfi_bits)]; + + hlist_add_head(&cfi->hash, head); +} + +static void *cfi_hash_alloc(unsigned long size) +{ + cfi_bits = max(10, ilog2(size)); + cfi_hash = mmap(NULL, sizeof(struct hlist_head) << cfi_bits, + PROT_READ|PROT_WRITE, + MAP_PRIVATE|MAP_ANON, -1, 0); + if (cfi_hash == (void *)-1L) { + WARN("mmap fail cfi_hash"); + cfi_hash = NULL; + } else if (stats) { + printf("cfi_bits: %d\n", cfi_bits); + } + + return cfi_hash; +} + +static unsigned long nr_insns; +static unsigned long nr_insns_visited; + /* * Call the arch-specific instruction decoder for all the instructions and add * them to the global instruction list. @@ -276,7 +355,6 @@ static int decode_instructions(struct objtool_file *file) struct symbol *func; unsigned long offset; struct instruction *insn; - unsigned long nr_insns = 0; int ret; for_each_sec(file, sec) { @@ -302,12 +380,11 @@ static int decode_instructions(struct objtool_file *file) memset(insn, 0, sizeof(*insn)); INIT_LIST_HEAD(&insn->alts); INIT_LIST_HEAD(&insn->stack_ops); - init_cfi_state(&insn->cfi); insn->sec = sec; insn->offset = offset; - ret = arch_decode_instruction(file->elf, sec, offset, + ret = arch_decode_instruction(file, sec, offset, sec->sh.sh_size - offset, &insn->len, &insn->type, &insn->immediate, @@ -345,6 +422,82 @@ static int decode_instructions(struct objtool_file *file) return ret; } +/* + * Read the pv_ops[] .data table to find the static initialized values. + */ +static int add_pv_ops(struct objtool_file *file, const char *symname) +{ + struct symbol *sym, *func; + unsigned long off, end; + struct reloc *rel; + int idx; + + sym = find_symbol_by_name(file->elf, symname); + if (!sym) + return 0; + + off = sym->offset; + end = off + sym->len; + for (;;) { + rel = find_reloc_by_dest_range(file->elf, sym->sec, off, end - off); + if (!rel) + break; + + func = rel->sym; + if (func->type == STT_SECTION) + func = find_symbol_by_offset(rel->sym->sec, rel->addend); + + idx = (rel->offset - sym->offset) / sizeof(unsigned long); + + objtool_pv_add(file, idx, func); + + off = rel->offset + 1; + if (off > end) + break; + } + + return 0; +} + +/* + * Allocate and initialize file->pv_ops[]. + */ +static int init_pv_ops(struct objtool_file *file) +{ + static const char *pv_ops_tables[] = { + "pv_ops", + "xen_cpu_ops", + "xen_irq_ops", + "xen_mmu_ops", + NULL, + }; + const char *pv_ops; + struct symbol *sym; + int idx, nr; + + if (!noinstr) + return 0; + + file->pv_ops = NULL; + + sym = find_symbol_by_name(file->elf, "pv_ops"); + if (!sym) + return 0; + + nr = sym->len / sizeof(unsigned long); + file->pv_ops = calloc(sizeof(struct pv_state), nr); + if (!file->pv_ops) + return -1; + + for (idx = 0; idx < nr; idx++) + INIT_LIST_HEAD(&file->pv_ops[idx].targets); + + for (idx = 0; (pv_ops = pv_ops_tables[idx]); idx++) + add_pv_ops(file, pv_ops); + + return 0; +} + static struct instruction *find_last_insn(struct objtool_file *file, struct section *sec) { @@ -532,6 +685,52 @@ static int create_static_call_sections(struct objtool_file *file) return 0; } +static int create_retpoline_sites_sections(struct objtool_file *file) +{ + struct instruction *insn; + struct section *sec; + int idx; + + sec = find_section_by_name(file->elf, ".retpoline_sites"); + if (sec) { + WARN("file already has .retpoline_sites, skipping"); + return 0; + } + + idx = 0; + list_for_each_entry(insn, &file->retpoline_call_list, call_node) + idx++; + + if (!idx) + return 0; + + sec = elf_create_section(file->elf, ".retpoline_sites", 0, + sizeof(int), idx); + if (!sec) { + WARN("elf_create_section: .retpoline_sites"); + return -1; + } + + idx = 0; + list_for_each_entry(insn, &file->retpoline_call_list, call_node) { + + int *site = (int *)sec->data->d_buf + idx; + *site = 0; + + if (elf_add_reloc_to_insn(file->elf, sec, + idx * sizeof(int), + R_X86_64_PC32, + insn->sec, insn->offset)) { + WARN("elf_add_reloc_to_insn: .retpoline_sites"); + return -1; + } + + idx++; + } + + return 0; +} + static int create_mcount_loc_sections(struct objtool_file *file) { struct section *sec; @@ -550,7 +749,7 @@ static int create_mcount_loc_sections(struct objtool_file *file) return 0; idx = 0; - list_for_each_entry(insn, &file->mcount_loc_list, mcount_loc_node) + list_for_each_entry(insn, &file->mcount_loc_list, call_node) idx++; sec = elf_create_section(file->elf, "__mcount_loc", 0, sizeof(unsigned long), idx); @@ -558,7 +757,7 @@ static int create_mcount_loc_sections(struct objtool_file *file) return -1; idx = 0; - list_for_each_entry(insn, &file->mcount_loc_list, mcount_loc_node) { + list_for_each_entry(insn, &file->mcount_loc_list, call_node) { loc = (unsigned long *)sec->data->d_buf + idx; memset(loc, 0, sizeof(unsigned long)); @@ -652,6 +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", @@ -818,6 +1021,9 @@ static struct reloc *insn_reloc(struct objtool_file *file, struct instruction *i return NULL; if (!insn->reloc) { + if (!file) + return NULL; + insn->reloc = find_reloc_by_dest_range(file->elf, insn->sec, insn->offset, insn->len); if (!insn->reloc) { @@ -839,27 +1045,40 @@ static void remove_insn_ops(struct instruction *insn) } } -static void add_call_dest(struct objtool_file *file, struct instruction *insn, - struct symbol *dest, bool sibling) +static void annotate_call_site(struct objtool_file *file, + struct instruction *insn, bool sibling) { struct reloc *reloc = insn_reloc(file, insn); + struct symbol *sym = insn->call_dest; - insn->call_dest = dest; - if (!dest) + if (!sym) + sym = reloc->sym; + + /* + * Alternative replacement code is just template code which is + * sometimes copied to the original instruction. For now, don't + * annotate it. (In the future we might consider annotating the + * original instruction if/when it ever makes sense to do so.) + */ + if (!strcmp(insn->sec->name, ".altinstr_replacement")) return; - if (insn->call_dest->static_call_tramp) { - list_add_tail(&insn->call_node, - &file->static_call_list); + if (sym->static_call_tramp) { + list_add_tail(&insn->call_node, &file->static_call_list); + return; + } + + if (sym->retpoline_thunk) { + list_add_tail(&insn->call_node, &file->retpoline_call_list); + return; } /* - * 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 && - !strncmp(insn->call_dest->name, "__sanitizer_cov_", 16)) { + if (insn->sec->noinstr && sym->profiling_func) { if (reloc) { reloc->type = R_NONE; elf_write_reloc(file->elf, reloc); @@ -871,9 +1090,10 @@ static void add_call_dest(struct objtool_file *file, struct instruction *insn, : arch_nop_insn(insn->len)); insn->type = sibling ? INSN_RETURN : INSN_NOP; + return; } - if (mcount && !strcmp(insn->call_dest->name, "__fentry__")) { + if (mcount && sym->fentry) { if (sibling) WARN_FUNC("Tail call to __fentry__ !?!?", insn->sec, insn->offset); @@ -888,9 +1108,17 @@ static void add_call_dest(struct objtool_file *file, struct instruction *insn, insn->type = INSN_NOP; - list_add_tail(&insn->mcount_loc_node, - &file->mcount_loc_list); + list_add_tail(&insn->call_node, &file->mcount_loc_list); + return; } +} + +static void add_call_dest(struct objtool_file *file, struct instruction *insn, + struct symbol *dest, bool sibling) +{ + insn->call_dest = dest; + if (!dest) + return; /* * Whatever stack impact regular CALLs have, should be undone @@ -900,8 +1128,43 @@ static void add_call_dest(struct objtool_file *file, struct instruction *insn, * are converted to JUMP, see read_intra_function_calls(). */ remove_insn_ops(insn); + + annotate_call_site(file, insn, sibling); } +static void add_retpoline_call(struct objtool_file *file, struct instruction *insn) +{ + /* + * Retpoline calls/jumps are really dynamic calls/jumps in disguise, + * so convert them accordingly. + */ + switch (insn->type) { + case INSN_CALL: + insn->type = INSN_CALL_DYNAMIC; + break; + case INSN_JUMP_UNCONDITIONAL: + insn->type = INSN_JUMP_DYNAMIC; + break; + case INSN_JUMP_CONDITIONAL: + insn->type = INSN_JUMP_DYNAMIC_CONDITIONAL; + break; + default: + return; + } + + insn->retpoline_safe = true; + + /* + * Whatever stack impact regular CALLs have, should be undone + * by the RETURN of the called function. + * + * Annotated intra-function calls retain the stack_ops but + * are converted to JUMP, see read_intra_function_calls(). + */ + remove_insn_ops(insn); + + annotate_call_site(file, insn, false); +} /* * Find the destination instructions for all jumps. */ @@ -923,20 +1186,8 @@ static int add_jump_destinations(struct objtool_file *file) } else if (reloc->sym->type == STT_SECTION) { dest_sec = reloc->sym->sec; dest_off = arch_dest_reloc_offset(reloc->addend); - } else if (arch_is_retpoline(reloc->sym)) { - /* - * Retpoline jumps are really dynamic jumps in - * disguise, so convert them accordingly. - */ - if (insn->type == INSN_JUMP_UNCONDITIONAL) - insn->type = INSN_JUMP_DYNAMIC; - else - insn->type = INSN_JUMP_DYNAMIC_CONDITIONAL; - - list_add_tail(&insn->call_node, - &file->retpoline_call_list); - - insn->retpoline_safe = true; + } else if (reloc->sym->retpoline_thunk) { + add_retpoline_call(file, insn); continue; } else if (insn->func) { /* internal or external sibling call (with reloc) */ @@ -1064,19 +1315,8 @@ static int add_call_destinations(struct objtool_file *file) add_call_dest(file, insn, dest, false); - } else if (arch_is_retpoline(reloc->sym)) { - /* - * Retpoline calls are really dynamic calls in - * disguise, so convert them accordingly. - */ - insn->type = INSN_CALL_DYNAMIC; - insn->retpoline_safe = true; - - list_add_tail(&insn->call_node, - &file->retpoline_call_list); - - remove_insn_ops(insn); - continue; + } else if (reloc->sym->retpoline_thunk) { + add_retpoline_call(file, insn); } else add_call_dest(file, insn, reloc->sym, false); @@ -1147,7 +1387,6 @@ static int handle_group_alt(struct objtool_file *file, memset(nop, 0, sizeof(*nop)); INIT_LIST_HEAD(&nop->alts); INIT_LIST_HEAD(&nop->stack_ops); - init_cfi_state(&nop->cfi); nop->sec = special_alt->new_sec; nop->offset = special_alt->new_off + special_alt->new_len; @@ -1556,10 +1795,11 @@ static void set_func_state(struct cfi_state *state) static int read_unwind_hints(struct objtool_file *file) { + struct cfi_state cfi = init_cfi; struct section *sec, *relocsec; - struct reloc *reloc; struct unwind_hint *hint; struct instruction *insn; + struct reloc *reloc; int i; sec = find_section_by_name(file->elf, ".discard.unwind_hints"); @@ -1597,19 +1837,24 @@ static int read_unwind_hints(struct objtool_file *file) insn->hint = true; if (hint->type == UNWIND_HINT_TYPE_FUNC) { - set_func_state(&insn->cfi); + insn->cfi = &func_cfi; continue; } - if (arch_decode_hint_reg(insn, hint->sp_reg)) { + if (insn->cfi) + cfi = *(insn->cfi); + + if (arch_decode_hint_reg(hint->sp_reg, &cfi.cfa.base)) { WARN_FUNC("unsupported unwind_hint sp base reg %d", insn->sec, insn->offset, hint->sp_reg); return -1; } - insn->cfi.cfa.offset = bswap_if_needed(hint->sp_offset); - insn->cfi.type = hint->type; - insn->cfi.end = hint->end; + cfi.cfa.offset = bswap_if_needed(hint->sp_offset); + cfi.type = hint->type; + cfi.end = hint->end; + + insn->cfi = cfi_hash_find_or_add(&cfi); } return 0; @@ -1748,17 +1993,53 @@ static int read_intra_function_calls(struct objtool_file *file) return 0; } -static int read_static_call_tramps(struct objtool_file *file) +/* + * 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; struct symbol *func; for_each_sec(file, sec) { list_for_each_entry(func, &sec->symbol_list, list) { - if (func->bind == STB_GLOBAL && - !strncmp(func->name, STATIC_CALL_TRAMP_PREFIX_STR, + if (func->bind != STB_GLOBAL) + continue; + + if (!strncmp(func->name, STATIC_CALL_TRAMP_PREFIX_STR, strlen(STATIC_CALL_TRAMP_PREFIX_STR))) func->static_call_tramp = true; + + if (arch_is_retpoline(func)) + func->retpoline_thunk = true; + + if (!strcmp(func->name, "__fentry__")) + func->fentry = true; + + if (is_profiling_func(func->name)) + func->profiling_func = true; } } @@ -1791,17 +2072,16 @@ static void mark_rodata(struct objtool_file *file) file->rodata = found; } -__weak int arch_rewrite_retpolines(struct objtool_file *file) -{ - return 0; -} - static int decode_sections(struct objtool_file *file) { int ret; mark_rodata(file); + ret = init_pv_ops(file); + if (ret) + return ret; + ret = decode_instructions(file); if (ret) return ret; @@ -1820,7 +2100,7 @@ static int decode_sections(struct objtool_file *file) /* * Must be before add_{jump_call}_destination. */ - ret = read_static_call_tramps(file); + ret = classify_symbols(file); if (ret) return ret; @@ -1864,23 +2144,14 @@ static int decode_sections(struct objtool_file *file) if (ret) return ret; - /* - * Must be after add_special_section_alts(), since this will emit - * alternatives. Must be after add_{jump,call}_destination(), since - * those create the call insn lists. - */ - ret = arch_rewrite_retpolines(file); - if (ret) - return ret; - return 0; } static bool is_fentry_call(struct instruction *insn) { - if (insn->type == INSN_CALL && insn->call_dest && - insn->call_dest->type == STT_NOTYPE && - !strcmp(insn->call_dest->name, "__fentry__")) + if (insn->type == INSN_CALL && + insn->call_dest && + insn->call_dest->fentry) return true; return false; @@ -2463,13 +2734,18 @@ static int propagate_alt_cfi(struct objtool_file *file, struct instruction *insn if (!insn->alt_group) return 0; + if (!insn->cfi) { + WARN("CFI missing"); + return -1; + } + alt_cfi = insn->alt_group->cfi; group_off = insn->offset - insn->alt_group->first_insn->offset; if (!alt_cfi[group_off]) { - alt_cfi[group_off] = &insn->cfi; + alt_cfi[group_off] = insn->cfi; } else { - if (memcmp(alt_cfi[group_off], &insn->cfi, sizeof(struct cfi_state))) { + if (cficmp(alt_cfi[group_off], insn->cfi)) { WARN_FUNC("stack layout conflict in alternatives", insn->sec, insn->offset); return -1; @@ -2520,9 +2796,14 @@ static int handle_insn_ops(struct instruction *insn, static bool insn_cfi_match(struct instruction *insn, struct cfi_state *cfi2) { - struct cfi_state *cfi1 = &insn->cfi; + struct cfi_state *cfi1 = insn->cfi; int i; + if (!cfi1) { + WARN("CFI missing"); + return false; + } + if (memcmp(&cfi1->cfa, &cfi2->cfa, sizeof(cfi1->cfa))) { WARN_FUNC("stack state mismatch: cfa1=%d%+d cfa2=%d%+d", @@ -2573,20 +2854,64 @@ static inline bool func_uaccess_safe(struct symbol *func) static inline const char *call_dest_name(struct instruction *insn) { + static char pvname[19]; + struct reloc *rel; + int idx; + if (insn->call_dest) return insn->call_dest->name; + rel = insn_reloc(NULL, insn); + if (rel && !strcmp(rel->sym->name, "pv_ops")) { + idx = (rel->addend / sizeof(void *)); + snprintf(pvname, sizeof(pvname), "pv_ops[%d]", idx); + return pvname; + } + return "{dynamic}"; } -static inline bool noinstr_call_dest(struct symbol *func) +static bool pv_call_dest(struct objtool_file *file, struct instruction *insn) +{ + struct symbol *target; + struct reloc *rel; + int idx; + + rel = insn_reloc(file, insn); + if (!rel || strcmp(rel->sym->name, "pv_ops")) + return false; + + idx = (arch_dest_reloc_offset(rel->addend) / sizeof(void *)); + + if (file->pv_ops[idx].clean) + return true; + + file->pv_ops[idx].clean = true; + + list_for_each_entry(target, &file->pv_ops[idx].targets, pv_target) { + if (!target->sec->noinstr) { + WARN("pv_ops[%d]: %s", idx, target->name); + file->pv_ops[idx].clean = false; + } + } + + return file->pv_ops[idx].clean; +} + +static inline bool noinstr_call_dest(struct objtool_file *file, + struct instruction *insn, + struct symbol *func) { /* * We can't deal with indirect function calls at present; * assume they're instrumented. */ - if (!func) + if (!func) { + if (file->pv_ops) + return pv_call_dest(file, insn); + return false; + } /* * If the symbol is from a noinstr section; we good. @@ -2605,10 +2930,12 @@ static inline bool noinstr_call_dest(struct symbol *func) return false; } -static int validate_call(struct instruction *insn, struct insn_state *state) +static int validate_call(struct objtool_file *file, + struct instruction *insn, + struct insn_state *state) { if (state->noinstr && state->instr <= 0 && - !noinstr_call_dest(insn->call_dest)) { + !noinstr_call_dest(file, insn, insn->call_dest)) { WARN_FUNC("call to %s() leaves .noinstr.text section", insn->sec, insn->offset, call_dest_name(insn)); return 1; @@ -2629,7 +2956,9 @@ static int validate_call(struct instruction *insn, struct insn_state *state) return 0; } -static int validate_sibling_call(struct instruction *insn, struct insn_state *state) +static int validate_sibling_call(struct objtool_file *file, + struct instruction *insn, + struct insn_state *state) { if (has_modified_stack_frame(insn, state)) { WARN_FUNC("sibling call from callable instruction with modified stack frame", @@ -2637,7 +2966,7 @@ static int validate_sibling_call(struct instruction *insn, struct insn_state *st return 1; } - return validate_call(insn, state); + return validate_call(file, insn, state); } static int validate_return(struct symbol *func, struct instruction *insn, struct insn_state *state) @@ -2707,7 +3036,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, struct instruction *insn, struct insn_state state) { struct alternative *alt; - struct instruction *next_insn; + struct instruction *next_insn, *prev_insn = NULL; struct section *sec; u8 visited; int ret; @@ -2736,15 +3065,25 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, if (insn->visited & visited) return 0; + } else { + nr_insns_visited++; } if (state.noinstr) state.instr += insn->instr; - if (insn->hint) - state.cfi = insn->cfi; - else - insn->cfi = state.cfi; + if (insn->hint) { + state.cfi = *insn->cfi; + } else { + /* XXX track if we actually changed state.cfi */ + + if (prev_insn && !cficmp(prev_insn->cfi, &state.cfi)) { + insn->cfi = prev_insn->cfi; + nr_cfi_reused++; + } else { + insn->cfi = cfi_hash_find_or_add(&state.cfi); + } + } insn->visited |= visited; @@ -2776,11 +3115,17 @@ 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: case INSN_CALL_DYNAMIC: - ret = validate_call(insn, &state); + ret = validate_call(file, insn, &state); if (ret) return ret; @@ -2799,7 +3144,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, case INSN_JUMP_CONDITIONAL: case INSN_JUMP_UNCONDITIONAL: if (is_sibling_call(insn)) { - ret = validate_sibling_call(insn, &state); + ret = validate_sibling_call(file, insn, &state); if (ret) return ret; @@ -2819,9 +3164,17 @@ 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(insn, &state); + ret = validate_sibling_call(file, insn, &state); if (ret) return ret; } @@ -2894,6 +3247,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, return 1; } + prev_insn = insn; insn = next_insn; } @@ -2920,7 +3274,7 @@ static int validate_unwind_hints(struct objtool_file *file, struct section *sec) } while (&insn->list != &file->insn_list && (!sec || insn->sec == sec)) { - if (insn->hint && !insn->visited) { + if (insn->hint && !insn->visited && !insn->ignore) { ret = validate_branch(file, insn->func, insn, state); if (ret && backtrace) BT_FUNC("<=== (hint)", insn); @@ -2987,20 +3341,19 @@ 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; if (!insn->func) return false; + if (insn->func->static_call_tramp) + return true; + /* * CONFIG_UBSAN_TRAP inserts a UD2 when it sees * __builtin_unreachable(). The BUG() macro has an unreachable() after @@ -3149,10 +3502,20 @@ int check(struct objtool_file *file) int ret, warnings = 0; arch_initial_func_cfi_state(&initial_func_cfi); + init_cfi_state(&init_cfi); + init_cfi_state(&func_cfi); + set_func_state(&func_cfi); + + if (!cfi_hash_alloc(1UL << (file->elf->symbol_bits - 3))) + goto out; + + cfi_hash_add(&init_cfi); + cfi_hash_add(&func_cfi); ret = decode_sections(file); if (ret < 0) goto out; + warnings += ret; if (list_empty(&file->insn_list)) @@ -3196,6 +3559,13 @@ int check(struct objtool_file *file) goto out; warnings += ret; + if (retpoline) { + ret = create_retpoline_sites_sections(file); + if (ret < 0) + goto out; + warnings += ret; + } + if (mcount) { ret = create_mcount_loc_sections(file); if (ret < 0) @@ -3203,6 +3573,13 @@ int check(struct objtool_file *file) warnings += ret; } + if (stats) { + printf("nr_insns_visited: %ld\n", nr_insns_visited); + printf("nr_cfi: %ld\n", nr_cfi); + printf("nr_cfi_reused: %ld\n", nr_cfi_reused); + printf("nr_cfi_cache: %ld\n", nr_cfi_cache); + } + out: /* * For now, don't fail the kernel build on fatal warnings. These diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c index fee03b744a..4b384c9070 100644 --- a/tools/objtool/elf.c +++ b/tools/objtool/elf.c @@ -375,6 +375,7 @@ static int read_symbols(struct elf *elf) return -1; } memset(sym, 0, sizeof(*sym)); + INIT_LIST_HEAD(&sym->pv_target); sym->alias = sym; sym->idx = i; @@ -741,90 +742,6 @@ static int elf_add_string(struct elf *elf, struct section *strtab, char *str) return len; } -struct symbol *elf_create_undef_symbol(struct elf *elf, const char *name) -{ - struct section *symtab, *symtab_shndx; - struct symbol *sym; - Elf_Data *data; - Elf_Scn *s; - - sym = malloc(sizeof(*sym)); - if (!sym) { - perror("malloc"); - return NULL; - } - memset(sym, 0, sizeof(*sym)); - - sym->name = strdup(name); - - sym->sym.st_name = elf_add_string(elf, NULL, sym->name); - if (sym->sym.st_name == -1) - return NULL; - - sym->sym.st_info = GELF_ST_INFO(STB_GLOBAL, STT_NOTYPE); - // st_other 0 - // st_shndx 0 - // st_value 0 - // st_size 0 - - symtab = find_section_by_name(elf, ".symtab"); - if (!symtab) { - WARN("can't find .symtab"); - return NULL; - } - - s = elf_getscn(elf->elf, symtab->idx); - if (!s) { - WARN_ELF("elf_getscn"); - return NULL; - } - - data = elf_newdata(s); - if (!data) { - WARN_ELF("elf_newdata"); - return NULL; - } - - data->d_buf = &sym->sym; - data->d_size = sizeof(sym->sym); - data->d_align = 1; - data->d_type = ELF_T_SYM; - - sym->idx = symtab->sh.sh_size / sizeof(sym->sym); - - symtab->sh.sh_size += data->d_size; - symtab->changed = true; - - symtab_shndx = find_section_by_name(elf, ".symtab_shndx"); - if (symtab_shndx) { - s = elf_getscn(elf->elf, symtab_shndx->idx); - if (!s) { - WARN_ELF("elf_getscn"); - return NULL; - } - - data = elf_newdata(s); - if (!data) { - WARN_ELF("elf_newdata"); - return NULL; - } - - data->d_buf = &sym->sym.st_size; /* conveniently 0 */ - data->d_size = sizeof(Elf32_Word); - data->d_align = 4; - data->d_type = ELF_T_WORD; - - symtab_shndx->sh.sh_size += 4; - symtab_shndx->changed = true; - } - - sym->sec = find_section_by_index(elf, 0); - - elf_add_symbol(elf, sym); - - return sym; -} - struct section *elf_create_section(struct elf *elf, const char *name, unsigned int sh_flags, size_t entsize, int nr) { diff --git a/tools/objtool/include/objtool/arch.h b/tools/objtool/include/objtool/arch.h index 478e054fcd..76bae30782 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, }; @@ -69,7 +70,7 @@ struct instruction; void arch_initial_func_cfi_state(struct cfi_init_state *state); -int arch_decode_instruction(const struct elf *elf, const struct section *sec, +int arch_decode_instruction(struct objtool_file *file, const struct section *sec, unsigned long offset, unsigned int maxlen, unsigned int *len, enum insn_type *type, unsigned long *immediate, @@ -84,7 +85,7 @@ unsigned long arch_dest_reloc_offset(int addend); const char *arch_nop_insn(int len); const char *arch_ret_insn(int len); -int arch_decode_hint_reg(struct instruction *insn, u8 sp_reg); +int arch_decode_hint_reg(u8 sp_reg, int *base); bool arch_is_retpoline(struct symbol *sym); diff --git a/tools/objtool/include/objtool/builtin.h b/tools/objtool/include/objtool/builtin.h index 15ac0b7d3d..89ba869ed0 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/cfi.h b/tools/objtool/include/objtool/cfi.h index fd5cb0bed9..f11d1ac1da 100644 --- a/tools/objtool/include/objtool/cfi.h +++ b/tools/objtool/include/objtool/cfi.h @@ -7,6 +7,7 @@ #define _OBJTOOL_CFI_H #include +#include #define CFI_UNDEFINED -1 #define CFI_CFA -2 @@ -24,6 +25,7 @@ struct cfi_init_state { }; struct cfi_state { + struct hlist_node hash; /* must be first, cficmp() */ struct cfi_reg regs[CFI_NUM_REGS]; struct cfi_reg vals[CFI_NUM_REGS]; struct cfi_reg cfa; diff --git a/tools/objtool/include/objtool/check.h b/tools/objtool/include/objtool/check.h index 56d50bc50c..6cfff07889 100644 --- a/tools/objtool/include/objtool/check.h +++ b/tools/objtool/include/objtool/check.h @@ -40,7 +40,6 @@ struct instruction { struct list_head list; struct hlist_node hash; struct list_head call_node; - struct list_head mcount_loc_node; struct section *sec; unsigned long offset; unsigned int len; @@ -60,7 +59,7 @@ struct instruction { struct list_head alts; struct symbol *func; struct list_head stack_ops; - struct cfi_state cfi; + struct cfi_state *cfi; }; static inline bool is_static_jump(struct instruction *insn) diff --git a/tools/objtool/include/objtool/elf.h b/tools/objtool/include/objtool/elf.h index 075d8291b8..d223367814 100644 --- a/tools/objtool/include/objtool/elf.h +++ b/tools/objtool/include/objtool/elf.h @@ -54,8 +54,12 @@ struct symbol { unsigned long offset; unsigned int len; struct symbol *pfunc, *cfunc, *alias; - bool uaccess_safe; - bool static_call_tramp; + u8 uaccess_safe : 1; + u8 static_call_tramp : 1; + u8 retpoline_thunk : 1; + u8 fentry : 1; + u8 profiling_func : 1; + struct list_head pv_target; }; struct reloc { @@ -140,7 +144,6 @@ int elf_write_insn(struct elf *elf, struct section *sec, unsigned long offset, unsigned int len, const char *insn); int elf_write_reloc(struct elf *elf, struct reloc *reloc); -struct symbol *elf_create_undef_symbol(struct elf *elf, const char *name); int elf_write(struct elf *elf); void elf_close(struct elf *elf); diff --git a/tools/objtool/include/objtool/objtool.h b/tools/objtool/include/objtool/objtool.h index 24fa83634d..f99fbc6078 100644 --- a/tools/objtool/include/objtool/objtool.h +++ b/tools/objtool/include/objtool/objtool.h @@ -14,6 +14,11 @@ #define __weak __attribute__((weak)) +struct pv_state { + bool clean; + struct list_head targets; +}; + struct objtool_file { struct elf *elf; struct list_head insn_list; @@ -25,10 +30,14 @@ struct objtool_file { unsigned long jl_short, jl_long; unsigned long jl_nop_short, jl_nop_long; + + struct pv_state *pv_ops; }; struct objtool_file *objtool_open_read(const char *_objname); +void objtool_pv_add(struct objtool_file *file, int idx, struct symbol *func); + int check(struct objtool_file *file); int orc_dump(const char *objname); int orc_create(struct objtool_file *file); diff --git a/tools/objtool/objtool.c b/tools/objtool/objtool.c index e21db8bce4..bdf699f655 100644 --- a/tools/objtool/objtool.c +++ b/tools/objtool/objtool.c @@ -135,6 +135,32 @@ struct objtool_file *objtool_open_read(const char *_objname) return &file; } +void objtool_pv_add(struct objtool_file *f, int idx, struct symbol *func) +{ + if (!noinstr) + return; + + if (!f->pv_ops) { + WARN("paravirt confusion"); + return; + } + + /* + * These functions will be patched into native code, + * see paravirt_patch(). + */ + if (!strcmp(func->name, "_paravirt_nop") || + !strcmp(func->name, "_paravirt_ident_64")) + return; + + /* already added this function */ + if (!list_empty(&func->pv_target)) + return; + + list_add(&func->pv_target, &f->pv_ops[idx].targets); + f->pv_ops[idx].clean = false; +} + static void cmd_usage(void) { unsigned int i, longest = 0; diff --git a/tools/objtool/orc_gen.c b/tools/objtool/orc_gen.c index b5865e2450..dd3c64af9d 100644 --- a/tools/objtool/orc_gen.c +++ b/tools/objtool/orc_gen.c @@ -13,13 +13,19 @@ #include #include -static int init_orc_entry(struct orc_entry *orc, struct cfi_state *cfi) +static int init_orc_entry(struct orc_entry *orc, struct cfi_state *cfi, + struct instruction *insn) { - struct instruction *insn = container_of(cfi, struct instruction, cfi); struct cfi_reg *bp = &cfi->regs[CFI_BP]; memset(orc, 0, sizeof(*orc)); + if (!cfi) { + orc->end = 0; + orc->sp_reg = ORC_REG_UNDEFINED; + return 0; + } + orc->end = cfi->end; if (cfi->cfa.base == CFI_UNDEFINED) { @@ -162,7 +168,7 @@ int orc_create(struct objtool_file *file) int i; if (!alt_group) { - if (init_orc_entry(&orc, &insn->cfi)) + if (init_orc_entry(&orc, insn->cfi, insn)) return -1; if (!memcmp(&prev_orc, &orc, sizeof(orc))) continue; @@ -186,7 +192,8 @@ int orc_create(struct objtool_file *file) struct cfi_state *cfi = alt_group->cfi[i]; if (!cfi) continue; - if (init_orc_entry(&orc, cfi)) + /* errors are reported on the original insn */ + if (init_orc_entry(&orc, cfi, insn)) return -1; if (!memcmp(&prev_orc, &orc, sizeof(orc))) continue; diff --git a/tools/objtool/special.c b/tools/objtool/special.c index 06c3eacab3..e2223dd91c 100644 --- a/tools/objtool/special.c +++ b/tools/objtool/special.c @@ -109,14 +109,6 @@ static int get_alt_entry(struct elf *elf, struct special_entry *entry, return -1; } - /* - * Skip retpoline .altinstr_replacement... we already rewrite the - * instructions for retpolines anyway, see arch_is_retpoline() - * usage in add_{call,jump}_destinations(). - */ - if (arch_is_retpoline(new_reloc->sym)) - return 1; - reloc_to_sec_off(new_reloc, &alt->new_sec, &alt->new_off); /* _ASM_EXTABLE_EX hack */ diff --git a/tools/perf/Documentation/itrace.txt b/tools/perf/Documentation/itrace.txt index 2d586fe5e4..c52755481e 100644 --- a/tools/perf/Documentation/itrace.txt +++ b/tools/perf/Documentation/itrace.txt @@ -20,6 +20,7 @@ L synthesize last branch entries on existing event records s skip initial number of events q quicker (less detailed) decoding + A approximate IPC Z prefer to ignore timestamps (so-called "timeless" decoding) The default is all events i.e. the same as --itrace=ibxwpe, @@ -61,5 +62,6 @@ debug messages will or will not be logged. Each flag must be preceded by either '+' or '-'. The flags are: a all perf events + o output to stdout If supported, the 'q' option may be repeated to increase the effect. diff --git a/tools/perf/Documentation/perf-buildid-cache.txt b/tools/perf/Documentation/perf-buildid-cache.txt index cd8ce6e8ec..7e44b419d3 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 3bb75c1f25..0420e71698 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-inject.txt b/tools/perf/Documentation/perf-inject.txt index 91108fe3ad..0570a1ccd3 100644 --- a/tools/perf/Documentation/perf-inject.txt +++ b/tools/perf/Documentation/perf-inject.txt @@ -45,6 +45,13 @@ OPTIONS tasks slept. sched_switch contains a callchain where a task slept and sched_stat contains a timeslice how long a task slept. +-k:: +--vmlinux=:: + vmlinux pathname + +--ignore-vmlinux:: + Ignore vmlinux files. + --kallsyms=:: kallsyms pathname diff --git a/tools/perf/Documentation/perf-intel-pt.txt b/tools/perf/Documentation/perf-intel-pt.txt index db465fa7ee..cbb920f5d0 100644 --- a/tools/perf/Documentation/perf-intel-pt.txt +++ b/tools/perf/Documentation/perf-intel-pt.txt @@ -157,6 +157,17 @@ of instructions and number of cycles since the last update, and thus represent the average IPC since the last IPC for that event type. Note IPC for "branches" events is calculated separately from IPC for "instructions" events. +Even with the 'cyc' config term, it is possible to produce IPC information for +every change of timestamp, but at the expense of accuracy. That is selected by +specifying the itrace 'A' option. Due to the granularity of timestamps, the +actual number of cycles increases even though the cycles reported does not. +The number of instructions is known, but if IPC is reported, cycles can be too +low and so IPC is too high. Note that inaccuracy decreases as the period of +sampling increases i.e. if the number of cycles is too low by a small amount, +that becomes less significant if the number of cycles is large. It may also be +useful to use the 'A' option in conjunction with dlfilter-show-cycles.so to +provide higher granularity cycle information. + Also note that the IPC instruction count may or may not include the current instruction. If the cycle count is associated with an asynchronous branch (e.g. page fault or interrupt), then the instruction count does not include the @@ -873,6 +884,7 @@ The letters are: L synthesize last branch entries on existing event records s skip initial number of events q quicker (less detailed) decoding + A approximate IPC Z prefer to ignore timestamps (so-called "timeless" decoding) "Instructions" events look like they were recorded by "perf record -e @@ -941,6 +953,7 @@ by flags which affect what debug messages will or will not be logged. Each flag must be preceded by either '+' or '-'. The flags support by Intel PT are: -a Suppress logging of perf events +a Log all perf events + +o Output to stdout instead of "intel_pt.log" By default, logged perf events are filtered by any specified time ranges, but flag +a overrides that. @@ -1072,6 +1085,21 @@ The Z option is equivalent to having recorded a trace without TSC decoding a trace of a virtual machine. +dlfilter-show-cycles.so +~~~~~~~~~~~~~~~~~~~~~~~ + +Cycles can be displayed using dlfilter-show-cycles.so in which case the itrace A +option can be useful to provide higher granularity cycle information: + + perf script --itrace=A --call-trace --dlfilter dlfilter-show-cycles.so + +To see a list of dlfilters: + + perf script -v --list-dlfilters + +See also linkperf:perf-dlfilters[1] + + dump option ~~~~~~~~~~~ @@ -1144,7 +1172,12 @@ Recording is selected by using the aux-output config term e.g. perf record -c 10000 -e '{intel_pt/branch=0/,cycles/aux-output/ppp}' uname -Note that currently, software only supports redirecting at most one PEBS event. +Originally, software only supported redirecting at most one PEBS event because it +was not able to differentiate one event from another. To overcome that, more recent +kernels and perf tools add support for the PERF_RECORD_AUX_OUTPUT_HW_ID side-band event. +To check for the presence of that event in a PEBS-via-PT trace: + + perf script -D --no-itrace | grep PERF_RECORD_AUX_OUTPUT_HW_ID To display PEBS events from the Intel PT trace, use the itrace 'o' option e.g. diff --git a/tools/perf/Documentation/perf-kmem.txt b/tools/perf/Documentation/perf-kmem.txt index 85b8ac695c..f378ac5935 100644 --- a/tools/perf/Documentation/perf-kmem.txt +++ b/tools/perf/Documentation/perf-kmem.txt @@ -8,22 +8,25 @@ perf-kmem - Tool to trace/measure kernel memory properties SYNOPSIS -------- [verse] -'perf kmem' {record|stat} [] +'perf kmem' [] {record|stat} DESCRIPTION ----------- There are two variants of perf kmem: - 'perf kmem record ' to record the kmem events - of an arbitrary workload. + 'perf kmem [] record [] ' to + record the kmem events of an arbitrary workload. Additional 'perf + record' options may be specified after record, such as '-o' to + change the output file name. - 'perf kmem stat' to report kernel memory statistics. + 'perf kmem [] stat' to report kernel memory statistics. OPTIONS ------- -i :: --input=:: - Select the input file (default: perf.data unless stdin is a fifo) + For stat, select the input file (default: perf.data unless stdin is a + fifo) -f:: --force:: diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt index 4c7db1da8f..57384a97c0 100644 --- a/tools/perf/Documentation/perf-list.txt +++ b/tools/perf/Documentation/perf-list.txt @@ -39,6 +39,10 @@ any extra expressions computed by perf stat. --deprecated:: Print deprecated events. By default the deprecated events are hidden. +--cputype:: +Print events applying cpu with this type for hybrid platform +(e.g. --cputype core or --cputype atom) + [[EVENT_MODIFIERS]] EVENT MODIFIERS --------------- @@ -77,7 +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: @@ -90,10 +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 @@ -122,6 +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//format/ + +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. @@ -312,4 +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 f1079ee7f2..9ccc75935b 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 @@ -469,7 +471,7 @@ This option sets the time out limit. The default value is 500 ms. --switch-events:: Record context switch events i.e. events of type PERF_RECORD_SWITCH or -PERF_RECORD_SWITCH_CPU_WIDE. In some cases (e.g. Intel PT or CoreSight) +PERF_RECORD_SWITCH_CPU_WIDE. In some cases (e.g. Intel PT, CoreSight or Arm SPE) switch events will be enabled automatically, which can be suppressed by by the option --no-switch-events. @@ -596,6 +598,22 @@ options. 'perf record --dry-run -e' can act as a BPF script compiler if llvm.dump-obj in config file is set to true. +--synth=TYPE:: +Collect and synthesize given type of events (comma separated). Note that +this option controls the synthesis from the /proc filesystem which represent +task status for pre-existing threads. + +Kernel (and some other) events are recorded regardless of the +choice in this option. For example, --synth=no would have MMAP events for +kernel and modules. + +Available types are: + 'task' - synthesize FORK and COMM events for each task + 'mmap' - synthesize MMAP events for each process (implies 'task') + 'cgroup' - synthesize CGROUP events for each cgroup + 'all' - synthesize all events (default) + 'no' - do not synthesize any of the above events + --tail-synthesize:: Instead of collecting non-sample events (for example, fork, comm, mmap) at the beginning of record, collect them during finalizing an output file. @@ -697,6 +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-script.txt b/tools/perf/Documentation/perf-script.txt index c805152435..b007071878 100644 --- a/tools/perf/Documentation/perf-script.txt +++ b/tools/perf/Documentation/perf-script.txt @@ -130,7 +130,7 @@ OPTIONS comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff, srcline, period, iregs, uregs, brstack, brstacksym, flags, bpf-output, brstackinsn, brstackoff, callindent, insn, insnlen, synth, phys_addr, - metric, misc, srccode, ipc, data_page_size, code_page_size. + metric, misc, srccode, ipc, data_page_size, code_page_size, ins_lat. Field list can be prepended with the type, trace, sw or hw, to indicate to which event type the field list applies. e.g., -F sw:comm,tid,time,ip,sym and -F trace:time,cpu,trace diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt index 7e6fb7cbc0..c06c341e72 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 9898a32b8d..cac3dfbee7 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=:: 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=:: diff --git a/tools/perf/Documentation/perf.data-file-format.txt b/tools/perf/Documentation/perf.data-file-format.txt index e6ff8c898a..f56d0e0fbf 100644 --- a/tools/perf/Documentation/perf.data-file-format.txt +++ b/tools/perf/Documentation/perf.data-file-format.txt @@ -346,7 +346,7 @@ to special needs. HEADER_BPF_PROG_INFO = 25, -struct bpf_prog_info_linear, which contains detailed information about +struct perf_bpil, which contains detailed information about a BPF program, including type, id, tag, jited/xlated instructions, etc. HEADER_BPF_BTF = 26, diff --git a/tools/perf/bench/epoll-ctl.c b/tools/perf/bench/epoll-ctl.c index ddaca75c3b..134612bde0 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 79d13dbc0a..37de970c97 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 83e9897c64..de56601f69 100644 --- a/tools/perf/bench/evlist-open-close.c +++ b/tools/perf/bench/evlist-open-close.c @@ -25,6 +25,11 @@ static int iterations = 100; static int nr_events = 1; static const char *event_string = "dummy"; +static inline u64 timeval2usec(struct timeval *tv) +{ + return tv->tv_sec * USEC_PER_SEC + tv->tv_usec; +} + static struct record_opts opts = { .sample_time = true, .mmap_pages = UINT_MAX, @@ -66,14 +71,14 @@ 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; } static struct evlist *bench__create_evlist(char *evstr) { - struct parse_events_error err = { .idx = 0, }; + struct parse_events_error err; struct evlist *evlist = evlist__new(); int ret; @@ -82,14 +87,16 @@ static struct evlist *bench__create_evlist(char *evstr) return NULL; } + parse_events_error__init(&err); ret = parse_events(evlist, evstr, &err); if (ret) { - parse_events_print_error(&err, evstr); + parse_events_error__print(&err, evstr); + parse_events_error__exit(&err); pr_err("Run 'perf list' for a list of valid events\n"); ret = 1; goto out_delete_evlist; } - + parse_events_error__exit(&err); ret = evlist__create_maps(evlist, &opts.target); if (ret < 0) { pr_err("Not enough memory to create thread/cpu maps\n"); @@ -144,7 +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)); @@ -167,7 +174,7 @@ static int bench_evlist_open_close__run(char *evstr) gettimeofday(&end, NULL); timersub(&end, &start, &diff); - runtime_us = diff.tv_sec * USEC_PER_SEC + diff.tv_usec; + runtime_us = timeval2usec(&diff); update_stats(&time_stats, runtime_us); evlist__delete(evlist); diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c index fcdea3e449..dbcecec4ee 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 137890f78e..6fc9a3d55c 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 f7a5ffebb9..2f59d5d1c5 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 0983f40b4b..861deb9347 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 2226a475e7..cfda48bef1 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/bench/futex.h b/tools/perf/bench/futex.h index b3853aac30..ebdc2b032a 100644 --- a/tools/perf/bench/futex.h +++ b/tools/perf/bench/futex.h @@ -28,7 +28,7 @@ struct bench_futex_parameters { }; /** - * futex() - SYS_futex syscall wrapper + * futex_syscall() - SYS_futex syscall wrapper * @uaddr: address of first futex * @op: futex op code * @val: typically expected value of uaddr, but varies by op @@ -38,17 +38,26 @@ struct bench_futex_parameters { * @val3: varies by op * @opflags: flags to be bitwise OR'd with op, such as FUTEX_PRIVATE_FLAG * - * futex() is used by all the following futex op wrappers. It can also be + * futex_syscall() is used by all the following futex op wrappers. It can also be * used for misuse and abuse testing. Generally, the specific op wrappers - * should be used instead. It is a macro instead of an static inline function as - * some of the types over overloaded (timeout is used for nr_requeue for - * example). + * should be used instead. * * These argument descriptions are the defaults for all * like-named arguments in the following wrappers except where noted below. */ -#define futex(uaddr, op, val, timeout, uaddr2, val3, opflags) \ - syscall(SYS_futex, uaddr, op | opflags, val, timeout, uaddr2, val3) +static inline int +futex_syscall(volatile u_int32_t *uaddr, int op, u_int32_t val, struct timespec *timeout, + volatile u_int32_t *uaddr2, int val3, int opflags) +{ + return syscall(SYS_futex, uaddr, op | opflags, val, timeout, uaddr2, val3); +} + +static inline int +futex_syscall_nr_requeue(volatile u_int32_t *uaddr, int op, u_int32_t val, int nr_requeue, + volatile u_int32_t *uaddr2, int val3, int opflags) +{ + return syscall(SYS_futex, uaddr, op | opflags, val, nr_requeue, uaddr2, val3); +} /** * futex_wait() - block on uaddr with optional timeout @@ -57,7 +66,7 @@ struct bench_futex_parameters { static inline int futex_wait(u_int32_t *uaddr, u_int32_t val, struct timespec *timeout, int opflags) { - return futex(uaddr, FUTEX_WAIT, val, timeout, NULL, 0, opflags); + return futex_syscall(uaddr, FUTEX_WAIT, val, timeout, NULL, 0, opflags); } /** @@ -67,7 +76,7 @@ futex_wait(u_int32_t *uaddr, u_int32_t val, struct timespec *timeout, int opflag static inline int futex_wake(u_int32_t *uaddr, int nr_wake, int opflags) { - return futex(uaddr, FUTEX_WAKE, nr_wake, NULL, NULL, 0, opflags); + return futex_syscall(uaddr, FUTEX_WAKE, nr_wake, NULL, NULL, 0, opflags); } /** @@ -76,7 +85,7 @@ futex_wake(u_int32_t *uaddr, int nr_wake, int opflags) static inline int futex_lock_pi(u_int32_t *uaddr, struct timespec *timeout, int opflags) { - return futex(uaddr, FUTEX_LOCK_PI, 0, timeout, NULL, 0, opflags); + return futex_syscall(uaddr, FUTEX_LOCK_PI, 0, timeout, NULL, 0, opflags); } /** @@ -85,7 +94,7 @@ futex_lock_pi(u_int32_t *uaddr, struct timespec *timeout, int opflags) static inline int futex_unlock_pi(u_int32_t *uaddr, int opflags) { - return futex(uaddr, FUTEX_UNLOCK_PI, 0, NULL, NULL, 0, opflags); + return futex_syscall(uaddr, FUTEX_UNLOCK_PI, 0, NULL, NULL, 0, opflags); } /** @@ -97,8 +106,8 @@ static inline int futex_cmp_requeue(u_int32_t *uaddr, u_int32_t val, u_int32_t *uaddr2, int nr_wake, int nr_requeue, int opflags) { - return futex(uaddr, FUTEX_CMP_REQUEUE, nr_wake, nr_requeue, uaddr2, - val, opflags); + return futex_syscall_nr_requeue(uaddr, FUTEX_CMP_REQUEUE, nr_wake, nr_requeue, uaddr2, + val, opflags); } /** @@ -113,8 +122,8 @@ static inline int futex_wait_requeue_pi(u_int32_t *uaddr, u_int32_t val, u_int32_t *uaddr2, struct timespec *timeout, int opflags) { - return futex(uaddr, FUTEX_WAIT_REQUEUE_PI, val, timeout, uaddr2, 0, - opflags); + return futex_syscall(uaddr, FUTEX_WAIT_REQUEUE_PI, val, timeout, uaddr2, 0, + opflags); } /** @@ -130,8 +139,8 @@ static inline int futex_cmp_requeue_pi(u_int32_t *uaddr, u_int32_t val, u_int32_t *uaddr2, int nr_requeue, int opflags) { - return futex(uaddr, FUTEX_CMP_REQUEUE_PI, 1, nr_requeue, uaddr2, - val, opflags); + return futex_syscall_nr_requeue(uaddr, FUTEX_CMP_REQUEUE_PI, 1, nr_requeue, uaddr2, + val, opflags); } #endif /* _FUTEX_H */ diff --git a/tools/perf/bench/synthesize.c b/tools/perf/bench/synthesize.c index 05f7c923c7..7401ebbac1 100644 --- a/tools/perf/bench/synthesize.c +++ b/tools/perf/bench/synthesize.c @@ -80,7 +80,7 @@ static int do_run_single_threaded(struct perf_session *session, NULL, target, threads, process_synthesized_event, - data_mmap, + true, data_mmap, nr_threads_synthesize); if (err) return err; @@ -171,7 +171,7 @@ static int do_run_multi_threaded(struct target *target, NULL, target, NULL, process_synthesized_event, - false, + true, false, nr_threads_synthesize); if (err) { perf_session__delete(session); diff --git a/tools/perf/dlfilters/dlfilter-test-api-v0.c b/tools/perf/dlfilters/dlfilter-test-api-v0.c index 7565a1852c..b17eb52a06 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/ampere/emag/bus.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/bus.json index 9bea1ba1c4..cf48d0dfc7 100644 --- a/tools/perf/pmu-events/arch/arm64/ampere/emag/bus.json +++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/bus.json @@ -18,6 +18,6 @@ "ArchStdEvent": "BUS_ACCESS_PERIPH" }, { - "ArchStdEvent": "BUS_ACCESS", + "ArchStdEvent": "BUS_ACCESS" } ] diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/cache.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/cache.json index 1e25f2ae4a..4cc50b7da5 100644 --- a/tools/perf/pmu-events/arch/arm64/ampere/emag/cache.json +++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/cache.json @@ -39,31 +39,31 @@ "ArchStdEvent": "L2D_CACHE_INVAL" }, { - "ArchStdEvent": "L1I_CACHE_REFILL", + "ArchStdEvent": "L1I_CACHE_REFILL" }, { - "ArchStdEvent": "L1I_TLB_REFILL", + "ArchStdEvent": "L1I_TLB_REFILL" }, { - "ArchStdEvent": "L1D_CACHE_REFILL", + "ArchStdEvent": "L1D_CACHE_REFILL" }, { - "ArchStdEvent": "L1D_CACHE", + "ArchStdEvent": "L1D_CACHE" }, { - "ArchStdEvent": "L1D_TLB_REFILL", + "ArchStdEvent": "L1D_TLB_REFILL" }, { - "ArchStdEvent": "L1I_CACHE", + "ArchStdEvent": "L1I_CACHE" }, { - "ArchStdEvent": "L2D_CACHE", + "ArchStdEvent": "L2D_CACHE" }, { - "ArchStdEvent": "L2D_CACHE_REFILL", + "ArchStdEvent": "L2D_CACHE_REFILL" }, { - "ArchStdEvent": "L2D_CACHE_WB", + "ArchStdEvent": "L2D_CACHE_WB" }, { "PublicDescription": "This event counts any load or store operation which accesses the data L1 TLB", @@ -72,7 +72,7 @@ }, { "PublicDescription": "This event counts any instruction fetch which accesses the instruction L1 TLB", - "ArchStdEvent": "L1I_TLB", + "ArchStdEvent": "L1I_TLB" }, { "PublicDescription": "Level 2 access to data TLB that caused a page table walk. This event counts on any data access which causes L2D_TLB_REFILL to count", diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/clock.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/clock.json index 9076ca2daf..927a6f629a 100644 --- a/tools/perf/pmu-events/arch/arm64/ampere/emag/clock.json +++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/clock.json @@ -1,7 +1,7 @@ [ { "PublicDescription": "The number of core clock cycles", - "ArchStdEvent": "CPU_CYCLES", + "ArchStdEvent": "CPU_CYCLES" }, { "PublicDescription": "FSU clocking gated off cycle", diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/exception.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/exception.json index 9761433ad3..ada052e196 100644 --- a/tools/perf/pmu-events/arch/arm64/ampere/emag/exception.json +++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/exception.json @@ -36,9 +36,9 @@ "ArchStdEvent": "EXC_TRAP_FIQ" }, { - "ArchStdEvent": "EXC_TAKEN", + "ArchStdEvent": "EXC_TAKEN" }, { - "ArchStdEvent": "EXC_RETURN", + "ArchStdEvent": "EXC_RETURN" } ] diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/instruction.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/instruction.json index 482aa3f19e..62f6276e30 100644 --- a/tools/perf/pmu-events/arch/arm64/ampere/emag/instruction.json +++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/instruction.json @@ -44,25 +44,25 @@ "BriefDescription": "Software increment" }, { - "ArchStdEvent": "INST_RETIRED", + "ArchStdEvent": "INST_RETIRED" }, { "ArchStdEvent": "CID_WRITE_RETIRED", "BriefDescription": "Write to CONTEXTIDR" }, { - "ArchStdEvent": "INST_SPEC", + "ArchStdEvent": "INST_SPEC" }, { - "ArchStdEvent": "TTBR_WRITE_RETIRED", + "ArchStdEvent": "TTBR_WRITE_RETIRED" }, { "PublicDescription": "This event counts all branches, taken or not. This excludes exception entries, debug entries and CCFAIL branches", - "ArchStdEvent": "BR_RETIRED", + "ArchStdEvent": "BR_RETIRED" }, { "PublicDescription": "This event counts any branch counted by BR_RETIRED which is not correctly predicted and causes a pipeline flush", - "ArchStdEvent": "BR_MIS_PRED_RETIRED", + "ArchStdEvent": "BR_MIS_PRED_RETIRED" }, { "PublicDescription": "Operation speculatively executed, NOP", diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/memory.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/memory.json index 2e7555696c..50157e8c20 100644 --- a/tools/perf/pmu-events/arch/arm64/ampere/emag/memory.json +++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/memory.json @@ -15,10 +15,10 @@ "ArchStdEvent": "UNALIGNED_LDST_SPEC" }, { - "ArchStdEvent": "MEM_ACCESS", + "ArchStdEvent": "MEM_ACCESS" }, { "PublicDescription": "This event counts any correctable or uncorrectable memory error (ECC or parity) in the protected core RAMs", - "ArchStdEvent": "MEMORY_ERROR", + "ArchStdEvent": "MEMORY_ERROR" } ] diff --git a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/branch.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/branch.json index ec0dc92288..db68de1883 100644 --- a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/branch.json +++ b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/branch.json @@ -1,10 +1,10 @@ [ { "PublicDescription": "This event counts any predictable branch instruction which is mispredicted either due to dynamic misprediction or because the MMU is off and the branches are statically predicted not taken", - "ArchStdEvent": "BR_MIS_PRED", + "ArchStdEvent": "BR_MIS_PRED" }, { "PublicDescription": "This event counts all predictable branches.", - "ArchStdEvent": "BR_PRED", + "ArchStdEvent": "BR_PRED" } ] diff --git a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/bus.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/bus.json index 6263929efc..e0875d3a68 100644 --- a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/bus.json +++ b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/bus.json @@ -1,21 +1,21 @@ [ { - "PublicDescription": "The number of core clock cycles" + "PublicDescription": "The number of core clock cycles", "ArchStdEvent": "CPU_CYCLES", "BriefDescription": "The number of core clock cycles." }, { "PublicDescription": "This event counts for every beat of data transferred over the data channels between the core and the SCU. If both read and write data beats are transferred on a given cycle, this event is counted twice on that cycle. This event counts the sum of BUS_ACCESS_RD and BUS_ACCESS_WR.", - "ArchStdEvent": "BUS_ACCESS", + "ArchStdEvent": "BUS_ACCESS" }, { - "PublicDescription": "This event duplicates CPU_CYCLES." - "ArchStdEvent": "BUS_CYCLES", + "PublicDescription": "This event duplicates CPU_CYCLES.", + "ArchStdEvent": "BUS_CYCLES" }, { - "ArchStdEvent": "BUS_ACCESS_RD", + "ArchStdEvent": "BUS_ACCESS_RD" }, { - "ArchStdEvent": "BUS_ACCESS_WR", + "ArchStdEvent": "BUS_ACCESS_WR" } ] diff --git a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/cache.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/cache.json index cd67bb9df1..fc448c2d5e 100644 --- a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/cache.json +++ b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/cache.json @@ -1,47 +1,47 @@ [ { "PublicDescription": "This event counts any instruction fetch which misses in the cache.", - "ArchStdEvent": "L1I_CACHE_REFILL", + "ArchStdEvent": "L1I_CACHE_REFILL" }, { "PublicDescription": "This event counts any refill of the instruction L1 TLB from the L2 TLB. This includes refills that result in a translation fault.", - "ArchStdEvent": "L1I_TLB_REFILL", + "ArchStdEvent": "L1I_TLB_REFILL" }, { "PublicDescription": "This event counts any load or store operation or page table walk access which causes data to be read from outside the L1, including accesses which do not allocate into L1.", - "ArchStdEvent": "L1D_CACHE_REFILL", + "ArchStdEvent": "L1D_CACHE_REFILL" }, { "PublicDescription": "This event counts any load or store operation or page table walk access which looks up in the L1 data cache. In particular, any access which could count the L1D_CACHE_REFILL event causes this event to count.", - "ArchStdEvent": "L1D_CACHE", + "ArchStdEvent": "L1D_CACHE" }, { "PublicDescription": "This event counts any refill of the data L1 TLB from the L2 TLB. This includes refills that result in a translation fault.", - "ArchStdEvent": "L1D_TLB_REFILL", + "ArchStdEvent": "L1D_TLB_REFILL" }, - {, + { "PublicDescription": "Level 1 instruction cache access or Level 0 Macro-op cache access. This event counts any instruction fetch which accesses the L1 instruction cache or L0 Macro-op cache.", - "ArchStdEvent": "L1I_CACHE", + "ArchStdEvent": "L1I_CACHE" }, { "PublicDescription": "This event counts any write-back of data from the L1 data cache to L2 or L3. This counts both victim line evictions and snoops, including cache maintenance operations.", - "ArchStdEvent": "L1D_CACHE_WB", + "ArchStdEvent": "L1D_CACHE_WB" }, { "PublicDescription": "This event counts any transaction from L1 which looks up in the L2 cache, and any write-back from the L1 to the L2. Snoops from outside the core and cache maintenance operations are not counted.", - "ArchStdEvent": "L2D_CACHE", + "ArchStdEvent": "L2D_CACHE" }, { "PublicDescription": "L2 data cache refill. This event counts any cacheable transaction from L1 which causes data to be read from outside the core. L2 refills caused by stashes into L2 should not be counted", - "ArchStdEvent": "L2D_CACHE_REFILL", + "ArchStdEvent": "L2D_CACHE_REFILL" }, { "PublicDescription": "This event counts any write-back of data from the L2 cache to outside the core. This includes snoops to the L2 which return data, regardless of whether they cause an invalidation. Invalidations from the L2 which do not write data outside of the core and snoops which return data from the L1 are not counted", - "ArchStdEvent": "L2D_CACHE_WB", + "ArchStdEvent": "L2D_CACHE_WB" }, { "PublicDescription": "This event counts any full cache line write into the L2 cache which does not cause a linefill, including write-backs from L1 to L2 and full-line writes which do not allocate into L1.", - "ArchStdEvent": "L2D_CACHE_ALLOCATE", + "ArchStdEvent": "L2D_CACHE_ALLOCATE" }, { "PublicDescription": "This event counts any load or store operation which accesses the data L1 TLB. If both a load and a store are executed on a cycle, this event counts twice. This event counts regardless of whether the MMU is enabled.", @@ -75,21 +75,21 @@ }, { "PublicDescription": "This event counts on any access to the L2 TLB (caused by a refill of any of the L1 TLBs). This event does not count if the MMU is disabled.", - "ArchStdEvent": "L2D_TLB", + "ArchStdEvent": "L2D_TLB" }, { "PublicDescription": "This event counts on any data access which causes L2D_TLB_REFILL to count.", - "ArchStdEvent": "DTLB_WALK", + "ArchStdEvent": "DTLB_WALK" }, { "PublicDescription": "This event counts on any instruction access which causes L2D_TLB_REFILL to count.", - "ArchStdEvent": "ITLB_WALK", + "ArchStdEvent": "ITLB_WALK" }, { - "ArchStdEvent": "LL_CACHE_RD", + "ArchStdEvent": "LL_CACHE_RD" }, { - "ArchStdEvent": "LL_CACHE_MISS_RD", + "ArchStdEvent": "LL_CACHE_MISS_RD" }, { "ArchStdEvent": "L1D_CACHE_INVAL" diff --git a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/exception.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/exception.json index ea4631db41..ce942324ee 100644 --- a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/exception.json +++ b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/exception.json @@ -1,10 +1,10 @@ [ { - "ArchStdEvent": "EXC_TAKEN", + "ArchStdEvent": "EXC_TAKEN" }, { "PublicDescription": "This event counts any correctable or uncorrectable memory error (ECC or parity) in the protected core RAMs", - "ArchStdEvent": "MEMORY_ERROR", + "ArchStdEvent": "MEMORY_ERROR" }, { "ArchStdEvent": "EXC_DABORT" diff --git a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/instruction.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/instruction.json index 8e59566cba..b0b439a36a 100644 --- a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/instruction.json +++ b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/instruction.json @@ -1,32 +1,32 @@ [ { - "ArchStdEvent": "SW_INCR", + "ArchStdEvent": "SW_INCR" }, { "PublicDescription": "This event counts all retired instructions, including those that fail their condition check.", - "ArchStdEvent": "INST_RETIRED", + "ArchStdEvent": "INST_RETIRED" }, { - "ArchStdEvent": "EXC_RETURN", + "ArchStdEvent": "EXC_RETURN" }, { "PublicDescription": "This event only counts writes to CONTEXTIDR in AArch32 state, and via the CONTEXTIDR_EL1 mnemonic in AArch64 state.", - "ArchStdEvent": "CID_WRITE_RETIRED", + "ArchStdEvent": "CID_WRITE_RETIRED" }, { - "ArchStdEvent": "INST_SPEC", + "ArchStdEvent": "INST_SPEC" }, { "PublicDescription": "This event only counts writes to TTBR0/TTBR1 in AArch32 state and TTBR0_EL1/TTBR1_EL1 in AArch64 state.", - "ArchStdEvent": "TTBR_WRITE_RETIRED", + "ArchStdEvent": "TTBR_WRITE_RETIRED" }, - {, + { "PublicDescription": "This event counts all branches, taken or not. This excludes exception entries, debug entries and CCFAIL branches.", - "ArchStdEvent": "BR_RETIRED", + "ArchStdEvent": "BR_RETIRED" }, { "PublicDescription": "This event counts any branch counted by BR_RETIRED which is not correctly predicted and causes a pipeline flush.", - "ArchStdEvent": "BR_MIS_PRED_RETIRED", + "ArchStdEvent": "BR_MIS_PRED_RETIRED" }, { "ArchStdEvent": "ASE_SPEC" diff --git a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/memory.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/memory.json index f06f399051..20a929e772 100644 --- a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/memory.json +++ b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/memory.json @@ -1,7 +1,7 @@ [ { "PublicDescription": "This event counts memory accesses due to load or store instructions. This event counts the sum of MEM_ACCESS_RD and MEM_ACCESS_WR.", - "ArchStdEvent": "MEM_ACCESS", + "ArchStdEvent": "MEM_ACCESS" }, { "ArchStdEvent": "MEM_ACCESS_RD" diff --git a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/other.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/other.json index c2ccbf6fbf..20d8365756 100644 --- a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/other.json +++ b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/other.json @@ -1,5 +1,5 @@ [ { - "ArchStdEvent": "REMOTE_ACCESS", + "ArchStdEvent": "REMOTE_ACCESS" } ] diff --git a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/pipeline.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/pipeline.json index d79f0aeaf7..b4e96551d5 100644 --- a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/pipeline.json +++ b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/pipeline.json @@ -1,10 +1,10 @@ [ { "PublicDescription": "The counter counts on any cycle when there are no fetched instructions available to dispatch.", - "ArchStdEvent": "STALL_FRONTEND", + "ArchStdEvent": "STALL_FRONTEND" }, { "PublicDescription": "The counter counts on any cycle fetched instructions are not dispatched due to resource constraints.", - "ArchStdEvent": "STALL_BACKEND", + "ArchStdEvent": "STALL_BACKEND" } ] diff --git a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/metrics.json b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/metrics.json index dda8e59149..6970203cb2 100644 --- a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/metrics.json +++ b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/metrics.json @@ -229,5 +229,5 @@ "BriefDescription": "Store bound L3 topdown metric", "MetricGroup": "TopDownL3", "MetricName": "store_bound" - }, + } ] diff --git a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-ddrc.json b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-ddrc.json index 61514d3860..2b3cb55df2 100644 --- a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-ddrc.json +++ b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-ddrc.json @@ -1,56 +1,56 @@ [ { - "EventCode": "0x00", - "EventName": "uncore_hisi_ddrc.flux_wr", + "ConfigCode": "0x00", + "EventName": "flux_wr", "BriefDescription": "DDRC total write operations", "PublicDescription": "DDRC total write operations", "Unit": "hisi_sccl,ddrc" }, { - "EventCode": "0x01", - "EventName": "uncore_hisi_ddrc.flux_rd", + "ConfigCode": "0x01", + "EventName": "flux_rd", "BriefDescription": "DDRC total read operations", "PublicDescription": "DDRC total read operations", "Unit": "hisi_sccl,ddrc" }, { - "EventCode": "0x02", - "EventName": "uncore_hisi_ddrc.flux_wcmd", + "ConfigCode": "0x02", + "EventName": "flux_wcmd", "BriefDescription": "DDRC write commands", "PublicDescription": "DDRC write commands", "Unit": "hisi_sccl,ddrc" }, { - "EventCode": "0x03", - "EventName": "uncore_hisi_ddrc.flux_rcmd", + "ConfigCode": "0x03", + "EventName": "flux_rcmd", "BriefDescription": "DDRC read commands", "PublicDescription": "DDRC read commands", "Unit": "hisi_sccl,ddrc" }, { - "EventCode": "0x04", - "EventName": "uncore_hisi_ddrc.pre_cmd", + "ConfigCode": "0x04", + "EventName": "pre_cmd", "BriefDescription": "DDRC precharge commands", "PublicDescription": "DDRC precharge commands", "Unit": "hisi_sccl,ddrc" }, { - "EventCode": "0x05", - "EventName": "uncore_hisi_ddrc.act_cmd", + "ConfigCode": "0x05", + "EventName": "act_cmd", "BriefDescription": "DDRC active commands", "PublicDescription": "DDRC active commands", "Unit": "hisi_sccl,ddrc" }, { - "EventCode": "0x06", - "EventName": "uncore_hisi_ddrc.rnk_chg", + "ConfigCode": "0x06", + "EventName": "rnk_chg", "BriefDescription": "DDRC rank commands", "PublicDescription": "DDRC rank commands", "Unit": "hisi_sccl,ddrc" }, { - "EventCode": "0x07", - "EventName": "uncore_hisi_ddrc.rw_chg", + "ConfigCode": "0x07", + "EventName": "rw_chg", "BriefDescription": "DDRC read and write changes", "PublicDescription": "DDRC read and write changes", "Unit": "hisi_sccl,ddrc" diff --git a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-hha.json b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-hha.json index ada8678293..9a7ec7af20 100644 --- a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-hha.json +++ b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-hha.json @@ -1,72 +1,152 @@ [ { - "EventCode": "0x00", - "EventName": "uncore_hisi_hha.rx_ops_num", + "ConfigCode": "0x00", + "EventName": "rx_ops_num", "BriefDescription": "The number of all operations received by the HHA", "PublicDescription": "The number of all operations received by the HHA", "Unit": "hisi_sccl,hha" }, { - "EventCode": "0x01", - "EventName": "uncore_hisi_hha.rx_outer", + "ConfigCode": "0x01", + "EventName": "rx_outer", "BriefDescription": "The number of all operations received by the HHA from another socket", "PublicDescription": "The number of all operations received by the HHA from another socket", "Unit": "hisi_sccl,hha" }, { - "EventCode": "0x02", - "EventName": "uncore_hisi_hha.rx_sccl", + "ConfigCode": "0x02", + "EventName": "rx_sccl", "BriefDescription": "The number of all operations received by the HHA from another SCCL in this socket", "PublicDescription": "The number of all operations received by the HHA from another SCCL in this socket", "Unit": "hisi_sccl,hha" }, { - "EventCode": "0x03", - "EventName": "uncore_hisi_hha.rx_ccix", + "ConfigCode": "0x03", + "EventName": "rx_ccix", "BriefDescription": "Count of the number of operations that HHA has received from CCIX", "PublicDescription": "Count of the number of operations that HHA has received from CCIX", "Unit": "hisi_sccl,hha" }, { - "EventCode": "0x1c", - "EventName": "uncore_hisi_hha.rd_ddr_64b", + "ConfigCode": "0x4", + "EventName": "rx_wbi", + "Unit": "hisi_sccl,hha" + }, + { + "ConfigCode": "0x5", + "EventName": "rx_wbip", + "Unit": "hisi_sccl,hha" + }, + { + "ConfigCode": "0x11", + "EventName": "rx_wtistash", + "Unit": "hisi_sccl,hha" + }, + { + "ConfigCode": "0x1c", + "EventName": "rd_ddr_64b", "BriefDescription": "The number of read operations sent by HHA to DDRC which size is 64 bytes", "PublicDescription": "The number of read operations sent by HHA to DDRC which size is 64bytes", "Unit": "hisi_sccl,hha" }, { - "EventCode": "0x1d", - "EventName": "uncore_hisi_hha.wr_ddr_64b", + "ConfigCode": "0x1d", + "EventName": "wr_ddr_64b", "BriefDescription": "The number of write operations sent by HHA to DDRC which size is 64 bytes", "PublicDescription": "The number of write operations sent by HHA to DDRC which size is 64 bytes", "Unit": "hisi_sccl,hha" }, { - "EventCode": "0x1e", - "EventName": "uncore_hisi_hha.rd_ddr_128b", + "ConfigCode": "0x1e", + "EventName": "rd_ddr_128b", "BriefDescription": "The number of read operations sent by HHA to DDRC which size is 128 bytes", "PublicDescription": "The number of read operations sent by HHA to DDRC which size is 128 bytes", "Unit": "hisi_sccl,hha" }, { - "EventCode": "0x1f", - "EventName": "uncore_hisi_hha.wr_ddr_128b", + "ConfigCode": "0x1f", + "EventName": "wr_ddr_128b", "BriefDescription": "The number of write operations sent by HHA to DDRC which size is 128 bytes", "PublicDescription": "The number of write operations sent by HHA to DDRC which size is 128 bytes", "Unit": "hisi_sccl,hha" }, { - "EventCode": "0x20", - "EventName": "uncore_hisi_hha.spill_num", + "ConfigCode": "0x20", + "EventName": "spill_num", "BriefDescription": "Count of the number of spill operations that the HHA has sent", "PublicDescription": "Count of the number of spill operations that the HHA has sent", "Unit": "hisi_sccl,hha" }, { - "EventCode": "0x21", - "EventName": "uncore_hisi_hha.spill_success", + "ConfigCode": "0x21", + "EventName": "spill_success", "BriefDescription": "Count of the number of successful spill operations that the HHA has sent", "PublicDescription": "Count of the number of successful spill operations that the HHA has sent", "Unit": "hisi_sccl,hha" + }, + { + "ConfigCode": "0x23", + "EventName": "bi_num", + "Unit": "hisi_sccl,hha" + }, + { + "ConfigCode": "0x32", + "EventName": "mediated_num", + "Unit": "hisi_sccl,hha" + }, + { + "ConfigCode": "0x33", + "EventName": "tx_snp_num", + "Unit": "hisi_sccl,hha" + }, + { + "ConfigCode": "0x34", + "EventName": "tx_snp_outer", + "Unit": "hisi_sccl,hha" + }, + { + "ConfigCode": "0x35", + "EventName": "tx_snp_ccix", + "Unit": "hisi_sccl,hha" + }, + { + "ConfigCode": "0x38", + "EventName": "rx_snprspdata", + "Unit": "hisi_sccl,hha" + }, + { + "ConfigCode": "0x3c", + "EventName": "rx_snprsp_outer", + "Unit": "hisi_sccl,hha" + }, + { + "ConfigCode": "0x40", + "EventName": "sdir-lookup", + "Unit": "hisi_sccl,hha" + }, + { + "ConfigCode": "0x41", + "EventName": "edir-lookup", + "Unit": "hisi_sccl,hha" + }, + { + "ConfigCode": "0x42", + "EventName": "sdir-hit", + "Unit": "hisi_sccl,hha" + }, + { + "ConfigCode": "0x43", + "EventName": "edir-hit", + "Unit": "hisi_sccl,hha" + }, + { + "ConfigCode": "0x4c", + "EventName": "sdir-home-migrate", + "Unit": "hisi_sccl,hha" + }, + { + "ConfigCode": "0x4d", + "EventName": "edir-home-migrate", + "Unit": "hisi_sccl,hha" } ] diff --git a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-l3c.json b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-l3c.json index 67ab19e8cf..e3479b65be 100644 --- a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-l3c.json +++ b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-l3c.json @@ -1,91 +1,91 @@ [ { - "EventCode": "0x00", - "EventName": "uncore_hisi_l3c.rd_cpipe", + "ConfigCode": "0x00", + "EventName": "rd_cpipe", "BriefDescription": "Total read accesses", "PublicDescription": "Total read accesses", "Unit": "hisi_sccl,l3c" }, { - "EventCode": "0x01", - "EventName": "uncore_hisi_l3c.wr_cpipe", + "ConfigCode": "0x01", + "EventName": "wr_cpipe", "BriefDescription": "Total write accesses", "PublicDescription": "Total write accesses", "Unit": "hisi_sccl,l3c" }, { - "EventCode": "0x02", - "EventName": "uncore_hisi_l3c.rd_hit_cpipe", + "ConfigCode": "0x02", + "EventName": "rd_hit_cpipe", "BriefDescription": "Total read hits", "PublicDescription": "Total read hits", "Unit": "hisi_sccl,l3c" }, { - "EventCode": "0x03", - "EventName": "uncore_hisi_l3c.wr_hit_cpipe", + "ConfigCode": "0x03", + "EventName": "wr_hit_cpipe", "BriefDescription": "Total write hits", "PublicDescription": "Total write hits", "Unit": "hisi_sccl,l3c" }, { - "EventCode": "0x04", - "EventName": "uncore_hisi_l3c.victim_num", + "ConfigCode": "0x04", + "EventName": "victim_num", "BriefDescription": "l3c precharge commands", "PublicDescription": "l3c precharge commands", "Unit": "hisi_sccl,l3c" }, { - "EventCode": "0x20", - "EventName": "uncore_hisi_l3c.rd_spipe", + "ConfigCode": "0x20", + "EventName": "rd_spipe", "BriefDescription": "Count of the number of read lines that come from this cluster of CPU core in spipe", "PublicDescription": "Count of the number of read lines that come from this cluster of CPU core in spipe", "Unit": "hisi_sccl,l3c" }, { - "EventCode": "0x21", - "EventName": "uncore_hisi_l3c.wr_spipe", + "ConfigCode": "0x21", + "EventName": "wr_spipe", "BriefDescription": "Count of the number of write lines that come from this cluster of CPU core in spipe", "PublicDescription": "Count of the number of write lines that come from this cluster of CPU core in spipe", "Unit": "hisi_sccl,l3c" }, { - "EventCode": "0x22", - "EventName": "uncore_hisi_l3c.rd_hit_spipe", + "ConfigCode": "0x22", + "EventName": "rd_hit_spipe", "BriefDescription": "Count of the number of read lines that hits in spipe of this L3C", "PublicDescription": "Count of the number of read lines that hits in spipe of this L3C", "Unit": "hisi_sccl,l3c" }, { - "EventCode": "0x23", - "EventName": "uncore_hisi_l3c.wr_hit_spipe", + "ConfigCode": "0x23", + "EventName": "wr_hit_spipe", "BriefDescription": "Count of the number of write lines that hits in spipe of this L3C", "PublicDescription": "Count of the number of write lines that hits in spipe of this L3C", "Unit": "hisi_sccl,l3c" }, { - "EventCode": "0x29", - "EventName": "uncore_hisi_l3c.back_invalid", + "ConfigCode": "0x29", + "EventName": "back_invalid", "BriefDescription": "Count of the number of L3C back invalid operations", "PublicDescription": "Count of the number of L3C back invalid operations", "Unit": "hisi_sccl,l3c" }, { - "EventCode": "0x40", - "EventName": "uncore_hisi_l3c.retry_cpu", + "ConfigCode": "0x40", + "EventName": "retry_cpu", "BriefDescription": "Count of the number of retry that L3C suppresses the CPU operations", "PublicDescription": "Count of the number of retry that L3C suppresses the CPU operations", "Unit": "hisi_sccl,l3c" }, { - "EventCode": "0x41", - "EventName": "uncore_hisi_l3c.retry_ring", + "ConfigCode": "0x41", + "EventName": "retry_ring", "BriefDescription": "Count of the number of retry that L3C suppresses the ring operations", "PublicDescription": "Count of the number of retry that L3C suppresses the ring operations", "Unit": "hisi_sccl,l3c" }, { - "EventCode": "0x42", - "EventName": "uncore_hisi_l3c.prefetch_drop", + "ConfigCode": "0x42", + "EventName": "prefetch_drop", "BriefDescription": "Count of the number of prefetch drops from this L3C", "PublicDescription": "Count of the number of prefetch drops from this L3C", "Unit": "hisi_sccl,l3c" diff --git a/tools/perf/pmu-events/arch/arm64/mapfile.csv b/tools/perf/pmu-events/arch/arm64/mapfile.csv index c43591d831..b899db48c1 100644 --- a/tools/perf/pmu-events/arch/arm64/mapfile.csv +++ b/tools/perf/pmu-events/arch/arm64/mapfile.csv @@ -18,6 +18,8 @@ 0x00000000410fd080,v1,arm/cortex-a57-a72,core 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/nds32/n13/atcpmu.json b/tools/perf/pmu-events/arch/nds32/n13/atcpmu.json index 5347350c36..3e7ac409d8 100644 --- a/tools/perf/pmu-events/arch/nds32/n13/atcpmu.json +++ b/tools/perf/pmu-events/arch/nds32/n13/atcpmu.json @@ -286,5 +286,5 @@ "EventCode": "0x21e", "EventName": "pop25_inst", "BriefDescription": "V3 POP25 instructions" - }, + } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_z10/basic.json b/tools/perf/pmu-events/arch/s390/cf_z10/basic.json index 2dd8dafff2..783de7f1ae 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z10/basic.json +++ b/tools/perf/pmu-events/arch/s390/cf_z10/basic.json @@ -82,5 +82,5 @@ "EventName": "PROBLEM_STATE_L1D_PENALTY_CYCLES", "BriefDescription": "Problem-State L1D Penalty Cycles", "PublicDescription": "Problem-State Level-1 D-Cache Penalty Cycle Count" - }, + } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_z10/crypto.json b/tools/perf/pmu-events/arch/s390/cf_z10/crypto.json index db286f19e7..3f28007d38 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z10/crypto.json +++ b/tools/perf/pmu-events/arch/s390/cf_z10/crypto.json @@ -110,5 +110,5 @@ "EventName": "AES_BLOCKED_CYCLES", "BriefDescription": "AES Blocked Cycles", "PublicDescription": "Total number of CPU cycles blocked for the AES functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU" - }, + } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_z10/extended.json b/tools/perf/pmu-events/arch/s390/cf_z10/extended.json index b6b7f29ca8..86bd8ba939 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z10/extended.json +++ b/tools/perf/pmu-events/arch/s390/cf_z10/extended.json @@ -124,5 +124,5 @@ "EventName": "L2C_STORES_SENT", "BriefDescription": "L2C Stores Sent", "PublicDescription": "Incremented by one for every store sent to Level-2 (L1.5) cache" - }, + } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_z13/basic.json b/tools/perf/pmu-events/arch/s390/cf_z13/basic.json index 2dd8dafff2..783de7f1ae 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z13/basic.json +++ b/tools/perf/pmu-events/arch/s390/cf_z13/basic.json @@ -82,5 +82,5 @@ "EventName": "PROBLEM_STATE_L1D_PENALTY_CYCLES", "BriefDescription": "Problem-State L1D Penalty Cycles", "PublicDescription": "Problem-State Level-1 D-Cache Penalty Cycle Count" - }, + } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_z13/crypto.json b/tools/perf/pmu-events/arch/s390/cf_z13/crypto.json index db286f19e7..3f28007d38 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z13/crypto.json +++ b/tools/perf/pmu-events/arch/s390/cf_z13/crypto.json @@ -110,5 +110,5 @@ "EventName": "AES_BLOCKED_CYCLES", "BriefDescription": "AES Blocked Cycles", "PublicDescription": "Total number of CPU cycles blocked for the AES functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU" - }, + } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_z13/extended.json b/tools/perf/pmu-events/arch/s390/cf_z13/extended.json index 5da8296b66..1a5e4f89c5 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z13/extended.json +++ b/tools/perf/pmu-events/arch/s390/cf_z13/extended.json @@ -390,5 +390,5 @@ "EventName": "MT_DIAG_CYCLES_TWO_THR_ACTIVE", "BriefDescription": "Cycle count with two threads active", "PublicDescription": "Cycle count with two threads active" - }, + } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/basic.json b/tools/perf/pmu-events/arch/s390/cf_z14/basic.json index 17fb524192..fc762e9f1d 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z14/basic.json +++ b/tools/perf/pmu-events/arch/s390/cf_z14/basic.json @@ -54,5 +54,5 @@ "EventName": "PROBLEM_STATE_INSTRUCTIONS", "BriefDescription": "Problem-State Instructions", "PublicDescription": "Problem-State Instruction Count" - }, + } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/crypto.json b/tools/perf/pmu-events/arch/s390/cf_z14/crypto.json index db286f19e7..3f28007d38 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z14/crypto.json +++ b/tools/perf/pmu-events/arch/s390/cf_z14/crypto.json @@ -110,5 +110,5 @@ "EventName": "AES_BLOCKED_CYCLES", "BriefDescription": "AES Blocked Cycles", "PublicDescription": "Total number of CPU cycles blocked for the AES functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU" - }, + } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/extended.json b/tools/perf/pmu-events/arch/s390/cf_z14/extended.json index 89e070727e..4942b20a1e 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z14/extended.json +++ b/tools/perf/pmu-events/arch/s390/cf_z14/extended.json @@ -369,5 +369,5 @@ "EventName": "MT_DIAG_CYCLES_TWO_THR_ACTIVE", "BriefDescription": "Cycle count with two threads active", "PublicDescription": "Cycle count with two threads active" - }, + } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_z15/basic.json b/tools/perf/pmu-events/arch/s390/cf_z15/basic.json index 17fb524192..fc762e9f1d 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z15/basic.json +++ b/tools/perf/pmu-events/arch/s390/cf_z15/basic.json @@ -54,5 +54,5 @@ "EventName": "PROBLEM_STATE_INSTRUCTIONS", "BriefDescription": "Problem-State Instructions", "PublicDescription": "Problem-State Instruction Count" - }, + } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_z15/crypto.json b/tools/perf/pmu-events/arch/s390/cf_z15/crypto.json index db286f19e7..3f28007d38 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z15/crypto.json +++ b/tools/perf/pmu-events/arch/s390/cf_z15/crypto.json @@ -110,5 +110,5 @@ "EventName": "AES_BLOCKED_CYCLES", "BriefDescription": "AES Blocked Cycles", "PublicDescription": "Total number of CPU cycles blocked for the AES functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU" - }, + } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_z15/crypto6.json b/tools/perf/pmu-events/arch/s390/cf_z15/crypto6.json index c998e4f1d1..ad79189050 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z15/crypto6.json +++ b/tools/perf/pmu-events/arch/s390/cf_z15/crypto6.json @@ -26,5 +26,5 @@ "EventName": "ECC_BLOCKED_CYCLES_COUNT", "BriefDescription": "ECC Blocked Cycles Count", "PublicDescription": "This counter counts the total number of CPU cycles blocked for the elliptic-curve cryptography (ECC) functions issued by the CPU because the ECC coprocessor is busy performing a function issued by another CPU." - }, + } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_z15/extended.json b/tools/perf/pmu-events/arch/s390/cf_z15/extended.json index 24c4ba2a9a..8ac61f8f28 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z15/extended.json +++ b/tools/perf/pmu-events/arch/s390/cf_z15/extended.json @@ -397,5 +397,5 @@ "EventName": "MT_DIAG_CYCLES_TWO_THR_ACTIVE", "BriefDescription": "Cycle count with two threads active", "PublicDescription": "Cycle count with two threads active" - }, + } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_z196/basic.json b/tools/perf/pmu-events/arch/s390/cf_z196/basic.json index 2dd8dafff2..783de7f1ae 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z196/basic.json +++ b/tools/perf/pmu-events/arch/s390/cf_z196/basic.json @@ -82,5 +82,5 @@ "EventName": "PROBLEM_STATE_L1D_PENALTY_CYCLES", "BriefDescription": "Problem-State L1D Penalty Cycles", "PublicDescription": "Problem-State Level-1 D-Cache Penalty Cycle Count" - }, + } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_z196/crypto.json b/tools/perf/pmu-events/arch/s390/cf_z196/crypto.json index db286f19e7..3f28007d38 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z196/crypto.json +++ b/tools/perf/pmu-events/arch/s390/cf_z196/crypto.json @@ -110,5 +110,5 @@ "EventName": "AES_BLOCKED_CYCLES", "BriefDescription": "AES Blocked Cycles", "PublicDescription": "Total number of CPU cycles blocked for the AES functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU" - }, + } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_z196/extended.json b/tools/perf/pmu-events/arch/s390/cf_z196/extended.json index b7b42a870b..86b29fd181 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z196/extended.json +++ b/tools/perf/pmu-events/arch/s390/cf_z196/extended.json @@ -166,5 +166,5 @@ "EventName": "L1I_OFFCHIP_L3_SOURCED_WRITES", "BriefDescription": "L1I Off-Chip L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache" - }, + } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_zec12/basic.json b/tools/perf/pmu-events/arch/s390/cf_zec12/basic.json index 2dd8dafff2..783de7f1ae 100644 --- a/tools/perf/pmu-events/arch/s390/cf_zec12/basic.json +++ b/tools/perf/pmu-events/arch/s390/cf_zec12/basic.json @@ -82,5 +82,5 @@ "EventName": "PROBLEM_STATE_L1D_PENALTY_CYCLES", "BriefDescription": "Problem-State L1D Penalty Cycles", "PublicDescription": "Problem-State Level-1 D-Cache Penalty Cycle Count" - }, + } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_zec12/crypto.json b/tools/perf/pmu-events/arch/s390/cf_zec12/crypto.json index db286f19e7..3f28007d38 100644 --- a/tools/perf/pmu-events/arch/s390/cf_zec12/crypto.json +++ b/tools/perf/pmu-events/arch/s390/cf_zec12/crypto.json @@ -110,5 +110,5 @@ "EventName": "AES_BLOCKED_CYCLES", "BriefDescription": "AES Blocked Cycles", "PublicDescription": "Total number of CPU cycles blocked for the AES functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU" - }, + } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_zec12/extended.json b/tools/perf/pmu-events/arch/s390/cf_zec12/extended.json index 1622510372..f40cbed894 100644 --- a/tools/perf/pmu-events/arch/s390/cf_zec12/extended.json +++ b/tools/perf/pmu-events/arch/s390/cf_zec12/extended.json @@ -243,5 +243,5 @@ "EventName": "TX_C_TABORT_SPECIAL", "BriefDescription": "Aborted transactions in constrained TX mode using special completion logic", "PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is using special logic to allow the transaction to complete" - }, + } ] 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 788766f45d..41bac1c6a0 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 @@ -18,6 +18,22 @@ "Invert": "0", "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", @@ -38,5 +54,5 @@ "BriefDescription": "Total cache hits", "PublicDescription": "Total cache hits", "Unit": "imc" - }, + } ] diff --git a/tools/perf/pmu-events/arch/test/test_soc/sys/uncore.json b/tools/perf/pmu-events/arch/test/test_soc/sys/uncore.json index 0f681a6e10..c7e7528db3 100644 --- a/tools/perf/pmu-events/arch/test/test_soc/sys/uncore.json +++ b/tools/perf/pmu-events/arch/test/test_soc/sys/uncore.json @@ -6,4 +6,11 @@ "Unit": "sys_ddr_pmu", "Compat": "v8" }, + { + "BriefDescription": "ccn read-cycles event", + "ConfigCode": "0x2c", + "EventName": "sys_ccn_pmu.read_cycles", + "Unit": "sys_ccn_pmu", + "Compat": "0x01" + } ] diff --git a/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json b/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json index 57ddbb9f9b..14b9a8ab15 100644 --- a/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json @@ -311,5 +311,5 @@ "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", "MetricName": "C6_Pkg_Residency" - }, + } ] diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c index 7c887d37b8..1a57c3f81d 100644 --- a/tools/perf/pmu-events/jevents.c +++ b/tools/perf/pmu-events/jevents.c @@ -45,6 +45,7 @@ #include /* getrlimit */ #include #include +#include #include #include "jsmn.h" #include "json.h" @@ -70,7 +71,7 @@ struct json_event { char *metric_constraint; }; -enum aggr_mode_class convert(const char *aggr_mode) +static enum aggr_mode_class convert(const char *aggr_mode) { if (!strcmp(aggr_mode, "PerCore")) return PerCore; @@ -81,8 +82,6 @@ enum aggr_mode_class convert(const char *aggr_mode) return -1; } -typedef int (*func)(void *data, struct json_event *je); - static LIST_HEAD(sys_event_tables); struct sys_event_table { @@ -361,7 +360,7 @@ static int close_table; static void print_events_table_prefix(FILE *fp, const char *tblname) { - fprintf(fp, "struct pmu_event %s[] = {\n", tblname); + fprintf(fp, "static const struct pmu_event %s[] = {\n", tblname); close_table = 1; } @@ -369,7 +368,7 @@ static int print_events_table_entry(void *data, struct json_event *je) { struct perf_entry_data *pd = data; FILE *outfp = pd->outfp; - char *topic = pd->topic; + char *topic_local = pd->topic; /* * TODO: Remove formatting chars after debugging to reduce @@ -384,7 +383,7 @@ static int print_events_table_entry(void *data, struct json_event *je) fprintf(outfp, "\t.desc = \"%s\",\n", je->desc); if (je->compat) fprintf(outfp, "\t.compat = \"%s\",\n", je->compat); - fprintf(outfp, "\t.topic = \"%s\",\n", topic); + fprintf(outfp, "\t.topic = \"%s\",\n", topic_local); if (je->long_desc && je->long_desc[0]) fprintf(outfp, "\t.long_desc = \"%s\",\n", je->long_desc); if (je->pmu) @@ -470,7 +469,7 @@ static void free_arch_std_events(void) } } -static int save_arch_std_events(void *data, struct json_event *je) +static int save_arch_std_events(void *data __maybe_unused, struct json_event *je) { struct event_struct *es; @@ -575,10 +574,12 @@ static int json_events(const char *fn, struct json_event je = {}; char *arch_std = NULL; unsigned long long eventcode = 0; + unsigned long long configcode = 0; struct msrmap *msr = NULL; jsmntok_t *msrval = NULL; jsmntok_t *precise = NULL; jsmntok_t *obj = tok++; + bool configcode_present = false; EXPECT(obj->type == JSMN_OBJECT, obj, "expected object"); for (j = 0; j < obj->size; j += 2) { @@ -601,6 +602,12 @@ static int json_events(const char *fn, addfield(map, &code, "", "", val); eventcode |= strtoul(code, NULL, 0); free(code); + } else if (json_streq(map, field, "ConfigCode")) { + char *code = NULL; + addfield(map, &code, "", "", val); + configcode |= strtoul(code, NULL, 0); + free(code); + configcode_present = true; } else if (json_streq(map, field, "ExtSel")) { char *code = NULL; addfield(map, &code, "", "", val); @@ -665,8 +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++) @@ -682,7 +687,10 @@ static int json_events(const char *fn, addfield(map, &extra_desc, " ", "(Precise event)", NULL); } - snprintf(buf, sizeof buf, "event=%#llx", eventcode); + if (configcode_present) + snprintf(buf, sizeof buf, "config=%#llx", configcode); + else + snprintf(buf, sizeof buf, "event=%#llx", eventcode); addfield(map, &event, ",", buf, NULL); if (je.desc && extra_desc) addfield(map, &je.desc, " ", extra_desc, NULL); @@ -786,7 +794,7 @@ static bool is_sys_dir(char *fname) static void print_mapping_table_prefix(FILE *outfp) { - fprintf(outfp, "struct pmu_events_map pmu_events_map[] = {\n"); + fprintf(outfp, "const struct pmu_events_map pmu_events_map[] = {\n"); } static void print_mapping_table_suffix(FILE *outfp) @@ -820,7 +828,7 @@ static void print_mapping_test_table(FILE *outfp) static void print_system_event_mapping_table_prefix(FILE *outfp) { - fprintf(outfp, "\nstruct pmu_sys_events pmu_sys_event_tables[] = {"); + fprintf(outfp, "\nconst struct pmu_sys_events pmu_sys_event_tables[] = {"); } static void print_system_event_mapping_table_suffix(FILE *outfp) @@ -1196,7 +1204,7 @@ int main(int argc, char *argv[]) const char *arch; const char *output_file; const char *start_dirname; - char *err_string_ext = ""; + const char *err_string_ext = ""; struct stat stbuf; prog = basename(argv[0]); diff --git a/tools/perf/pmu-events/jsmn.c b/tools/perf/pmu-events/jsmn.c index 11d1fa18bf..831dc44c45 100644 --- a/tools/perf/pmu-events/jsmn.c +++ b/tools/perf/pmu-events/jsmn.c @@ -24,6 +24,7 @@ #include #include "jsmn.h" +#define JSMN_STRICT /* * Allocates a fresh unused token from the token pool. @@ -176,6 +177,14 @@ jsmnerr_t jsmn_parse(jsmn_parser *parser, const char *js, size_t len, jsmnerr_t r; int i; jsmntok_t *token; +#ifdef JSMN_STRICT + /* + * Keeps track of whether a new object/list/primitive is expected. New items are only + * allowed after an opening brace, comma or colon. A closing brace after a comma is not + * valid JSON. + */ + int expecting_item = 1; +#endif for (; parser->pos < len; parser->pos++) { char c; @@ -185,6 +194,10 @@ jsmnerr_t jsmn_parse(jsmn_parser *parser, const char *js, size_t len, switch (c) { case '{': case '[': +#ifdef JSMN_STRICT + if (!expecting_item) + return JSMN_ERROR_INVAL; +#endif token = jsmn_alloc_token(parser, tokens, num_tokens); if (token == NULL) return JSMN_ERROR_NOMEM; @@ -196,6 +209,10 @@ jsmnerr_t jsmn_parse(jsmn_parser *parser, const char *js, size_t len, break; case '}': case ']': +#ifdef JSMN_STRICT + if (expecting_item) + return JSMN_ERROR_INVAL; +#endif type = (c == '}' ? JSMN_OBJECT : JSMN_ARRAY); for (i = parser->toknext - 1; i >= 0; i--) { token = &tokens[i]; @@ -219,6 +236,11 @@ jsmnerr_t jsmn_parse(jsmn_parser *parser, const char *js, size_t len, } break; case '\"': +#ifdef JSMN_STRICT + if (!expecting_item) + return JSMN_ERROR_INVAL; + expecting_item = 0; +#endif r = jsmn_parse_string(parser, js, len, tokens, num_tokens); if (r < 0) @@ -229,11 +251,15 @@ jsmnerr_t jsmn_parse(jsmn_parser *parser, const char *js, size_t len, case '\t': case '\r': case '\n': - case ':': - case ',': case ' ': break; #ifdef JSMN_STRICT + case ':': + case ',': + if (expecting_item) + return JSMN_ERROR_INVAL; + expecting_item = 1; + break; /* * In strict mode primitives are: * numbers and booleans. @@ -253,6 +279,9 @@ jsmnerr_t jsmn_parse(jsmn_parser *parser, const char *js, size_t len, case 'f': case 'n': #else + case ':': + case ',': + break; /* * In non-strict mode every unquoted value * is a primitive. @@ -260,6 +289,12 @@ jsmnerr_t jsmn_parse(jsmn_parser *parser, const char *js, size_t len, /*FALL THROUGH */ default: #endif + +#ifdef JSMN_STRICT + if (!expecting_item) + return JSMN_ERROR_INVAL; + expecting_item = 0; +#endif r = jsmn_parse_primitive(parser, js, len, tokens, num_tokens); if (r < 0) @@ -282,7 +317,11 @@ jsmnerr_t jsmn_parse(jsmn_parser *parser, const char *js, size_t len, return JSMN_ERROR_PART; } +#ifdef JSMN_STRICT + return expecting_item ? JSMN_ERROR_INVAL : JSMN_SUCCESS; +#else return JSMN_SUCCESS; +#endif } /* diff --git a/tools/perf/pmu-events/pmu-events.h b/tools/perf/pmu-events/pmu-events.h index 5c2bf7275c..6efe739764 100644 --- a/tools/perf/pmu-events/pmu-events.h +++ b/tools/perf/pmu-events/pmu-events.h @@ -41,19 +41,19 @@ struct pmu_events_map { const char *cpuid; const char *version; const char *type; /* core, uncore etc */ - struct pmu_event *table; + const struct pmu_event *table; }; struct pmu_sys_events { const char *name; - struct pmu_event *table; + const struct pmu_event *table; }; /* * Global table mapping each known CPU for the architecture to its * table of PMU events. */ -extern struct pmu_events_map pmu_events_map[]; -extern struct pmu_sys_events pmu_sys_event_tables[]; +extern const struct pmu_events_map pmu_events_map[]; +extern const struct pmu_sys_events pmu_sys_event_tables[]; #endif diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build index 803ca426f8..af2b37ef7c 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/api-io.c b/tools/perf/tests/api-io.c index 2ada86ad60..e91cf2c127 100644 --- a/tools/perf/tests/api-io.c +++ b/tools/perf/tests/api-io.c @@ -289,8 +289,8 @@ static int test_get_dec(void) return ret; } -int test__api_io(struct test *test __maybe_unused, - int subtest __maybe_unused) +static int test__api_io(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { int ret = 0; @@ -302,3 +302,5 @@ int test__api_io(struct test *test __maybe_unused, ret = TEST_FAIL; return ret; } + +DEFINE_SUITE("Test api io", api_io); diff --git a/tools/perf/tests/attr.c b/tools/perf/tests/attr.c index 9b40a25376..56fba08a30 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; @@ -178,7 +178,7 @@ static int run_dir(const char *d, const char *perf) return system(cmd) ? TEST_FAIL : TEST_OK; } -int test__attr(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__attr(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct stat st; char path_perf[PATH_MAX]; @@ -207,3 +207,5 @@ int test__attr(struct test *test __maybe_unused, int subtest __maybe_unused) return TEST_SKIP; } + +DEFINE_SUITE("Setup struct perf_event_attr", attr); diff --git a/tools/perf/tests/attr/README b/tools/perf/tests/attr/README index a36f49fb4d..1116fc6bf2 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 5d8234d508..f0a18b4ea4 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-fp b/tools/perf/tests/attr/test-record-graph-fp index 5630521c0b..a6e60e8392 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/backward-ring-buffer.c b/tools/perf/tests/backward-ring-buffer.c index b4b9a9488d..79a980b1e7 100644 --- a/tools/perf/tests/backward-ring-buffer.c +++ b/tools/perf/tests/backward-ring-buffer.c @@ -82,7 +82,7 @@ static int do_test(struct evlist *evlist, int mmap_pages, } -int test__backward_ring_buffer(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__backward_ring_buffer(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { int ret = TEST_SKIP, err, sample_count = 0, comm_count = 0; char pid[16], sbuf[STRERR_BUFSIZE]; @@ -115,12 +115,13 @@ int test__backward_ring_buffer(struct test *test __maybe_unused, int subtest __m goto out_delete_evlist; } - bzero(&parse_error, sizeof(parse_error)); + parse_events_error__init(&parse_error); /* * Set backward bit, ring buffer should be writing from end. Record * it in aux evlist */ err = parse_events(evlist, "syscalls:sys_enter_prctl/overwrite/", &parse_error); + parse_events_error__exit(&parse_error); if (err) { pr_debug("Failed to parse tracepoint event, try use root\n"); ret = TEST_SKIP; @@ -166,3 +167,5 @@ int test__backward_ring_buffer(struct test *test __maybe_unused, int subtest __m evlist__delete(evlist); return ret; } + +DEFINE_SUITE("Read backward ring buffer", backward_ring_buffer); diff --git a/tools/perf/tests/bitmap.c b/tools/perf/tests/bitmap.c index 12b805efdc..4965dd6669 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) @@ -40,7 +40,7 @@ static int test_bitmap(const char *str) return ret; } -int test__bitmap_print(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__bitmap_print(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { TEST_ASSERT_VAL("failed to convert map", test_bitmap("1")); TEST_ASSERT_VAL("failed to convert map", test_bitmap("1,5")); @@ -51,3 +51,5 @@ int test__bitmap_print(struct test *test __maybe_unused, int subtest __maybe_unu TEST_ASSERT_VAL("failed to convert map", test_bitmap("1-10,12-20,22-30,32-40")); return 0; } + +DEFINE_SUITE("Print bitmap", bitmap_print); diff --git a/tools/perf/tests/bp_account.c b/tools/perf/tests/bp_account.c index 489b50604c..d1ebb5561e 100644 --- a/tools/perf/tests/bp_account.c +++ b/tools/perf/tests/bp_account.c @@ -19,6 +19,19 @@ #include "../perf-sys.h" #include "cloexec.h" +/* + * PowerPC and S390 do not support creation of instruction breakpoints using the + * perf_event interface. + * + * Just disable the test for these architectures until these issues are + * resolved. + */ +#if defined(__powerpc__) || defined(__s390x__) +#define BP_ACCOUNT_IS_SUPPORTED 0 +#else +#define BP_ACCOUNT_IS_SUPPORTED 1 +#endif + static volatile long the_var; static noinline int test_function(void) @@ -173,13 +186,18 @@ static int detect_share(int wp_cnt, int bp_cnt) * we create another watchpoint to ensure * the slot accounting is correct */ -int test__bp_accounting(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__bp_accounting(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { int has_ioctl = detect_ioctl(); int wp_cnt = detect_cnt(false); int bp_cnt = detect_cnt(true); int share = detect_share(wp_cnt, bp_cnt); + if (!BP_ACCOUNT_IS_SUPPORTED) { + pr_debug("Test not supported on this architecture"); + return TEST_SKIP; + } + pr_debug("watchpoints count %d, breakpoints count %d, has_ioctl %d, share %d\n", wp_cnt, bp_cnt, has_ioctl, share); @@ -189,18 +207,4 @@ int test__bp_accounting(struct test *test __maybe_unused, int subtest __maybe_un return bp_accounting(wp_cnt, share); } -bool test__bp_account_is_supported(void) -{ - /* - * PowerPC and S390 do not support creation of instruction - * breakpoints using the perf_event interface. - * - * Just disable the test for these architectures until these - * issues are resolved. - */ -#if defined(__powerpc__) || defined(__s390x__) - return false; -#else - return true; -#endif -} +DEFINE_SUITE("Breakpoint accounting", bp_accounting); diff --git a/tools/perf/tests/bp_signal.c b/tools/perf/tests/bp_signal.c index ef37353636..1f2908f023 100644 --- a/tools/perf/tests/bp_signal.c +++ b/tools/perf/tests/bp_signal.c @@ -161,11 +161,16 @@ static long long bp_count(int fd) return count; } -int test__bp_signal(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__bp_signal(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct sigaction sa; long long count1, count2, count3; + if (!BP_SIGNAL_IS_SUPPORTED) { + pr_debug("Test not supported on this architecture"); + return TEST_SKIP; + } + /* setup SIGIO signal handler */ memset(&sa, 0, sizeof(struct sigaction)); sa.sa_sigaction = (void *) sig_handler; @@ -285,29 +290,4 @@ int test__bp_signal(struct test *test __maybe_unused, int subtest __maybe_unused TEST_OK : TEST_FAIL; } -bool test__bp_signal_is_supported(void) -{ - /* - * PowerPC and S390 do not support creation of instruction - * breakpoints using the perf_event interface. - * - * ARM requires explicit rounding down of the instruction - * pointer in Thumb mode, and then requires the single-step - * to be handled explicitly in the overflow handler to avoid - * stepping into the SIGIO handler and getting stuck on the - * breakpointed instruction. - * - * Since arm64 has the same issue with arm for the single-step - * handling, this case also gets stuck on the breakpointed - * instruction. - * - * Just disable the test for these architectures until these - * issues are resolved. - */ -#if defined(__powerpc__) || defined(__s390x__) || defined(__arm__) || \ - defined(__aarch64__) - return false; -#else - return true; -#endif -} +DEFINE_SUITE("Breakpoint overflow signal handler", bp_signal); diff --git a/tools/perf/tests/bp_signal_overflow.c b/tools/perf/tests/bp_signal_overflow.c index eb4dbbddf4..4e897c2cf2 100644 --- a/tools/perf/tests/bp_signal_overflow.c +++ b/tools/perf/tests/bp_signal_overflow.c @@ -59,13 +59,18 @@ static long long bp_count(int fd) #define EXECUTIONS 10000 #define THRESHOLD 100 -int test__bp_signal_overflow(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__bp_signal_overflow(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct perf_event_attr pe; struct sigaction sa; long long count; int fd, i, fails = 0; + if (!BP_SIGNAL_IS_SUPPORTED) { + pr_debug("Test not supported on this architecture"); + return TEST_SKIP; + } + /* setup SIGIO signal handler */ memset(&sa, 0, sizeof(struct sigaction)); sa.sa_sigaction = (void *) sig_handler; @@ -133,3 +138,5 @@ int test__bp_signal_overflow(struct test *test __maybe_unused, int subtest __may return fails ? TEST_FAIL : TEST_OK; } + +DEFINE_SUITE("Breakpoint overflow sampling", bp_signal_overflow); diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c index fa03ff0dc0..5734905301 100644 --- a/tools/perf/tests/bpf.c +++ b/tools/perf/tests/bpf.c @@ -62,7 +62,6 @@ static int llseek_loop(void) static struct { enum test_llvm__testcase prog_id; - const char *desc; const char *name; const char *msg_compile_fail; const char *msg_load_fail; @@ -72,7 +71,6 @@ static struct { } bpf_testcase_table[] = { { .prog_id = LLVM_TESTCASE_BASE, - .desc = "Basic BPF filtering", .name = "[basic_bpf_test]", .msg_compile_fail = "fix 'perf test LLVM' first", .msg_load_fail = "load bpf object failed", @@ -81,7 +79,6 @@ static struct { }, { .prog_id = LLVM_TESTCASE_BASE, - .desc = "BPF pinning", .name = "[bpf_pinning]", .msg_compile_fail = "fix kbuild first", .msg_load_fail = "check your vmlinux setting?", @@ -92,7 +89,6 @@ static struct { #ifdef HAVE_BPF_PROLOGUE { .prog_id = LLVM_TESTCASE_BPF_PROLOGUE, - .desc = "BPF prologue generation", .name = "[bpf_prologue_test]", .msg_compile_fail = "fix kbuild first", .msg_load_fail = "check your vmlinux setting?", @@ -123,12 +119,13 @@ static int do_test(struct bpf_object *obj, int (*func)(void), struct parse_events_state parse_state; struct parse_events_error parse_error; - bzero(&parse_error, sizeof(parse_error)); + parse_events_error__init(&parse_error); bzero(&parse_state, sizeof(parse_state)); parse_state.error = &parse_error; INIT_LIST_HEAD(&parse_state.list); err = parse_events_load_bpf_obj(&parse_state, &parse_state.list, obj, NULL); + parse_events_error__exit(&parse_error); if (err || list_empty(&parse_state.list)) { pr_debug("Failed to add events selected by BPF\n"); return TEST_FAIL; @@ -282,18 +279,6 @@ static int __test__bpf(int idx) return ret; } -int test__bpf_subtest_get_nr(void) -{ - return (int)ARRAY_SIZE(bpf_testcase_table); -} - -const char *test__bpf_subtest_get_desc(int i) -{ - if (i < 0 || i >= (int)ARRAY_SIZE(bpf_testcase_table)) - return NULL; - return bpf_testcase_table[i].desc; -} - static int check_env(void) { int err; @@ -311,9 +296,13 @@ static int check_env(void) return err; } +/* temporarily disable libbpf deprecation warnings */ +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wdeprecated-declarations" err = bpf_load_program(BPF_PROG_TYPE_KPROBE, insns, - sizeof(insns) / sizeof(insns[0]), + ARRAY_SIZE(insns), license, kver_int, NULL, 0); +#pragma GCC diagnostic pop if (err < 0) { pr_err("Missing basic BPF support, skip this test: %s\n", strerror(errno)); @@ -324,7 +313,7 @@ static int check_env(void) return 0; } -int test__bpf(struct test *test __maybe_unused, int i) +static int test__bpf(int i) { int err; @@ -342,21 +331,60 @@ int test__bpf(struct test *test __maybe_unused, int i) err = __test__bpf(i); return err; } +#endif +static int test__basic_bpf_test(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) +{ +#ifdef HAVE_LIBBPF_SUPPORT + return test__bpf(0); #else -int test__bpf_subtest_get_nr(void) -{ - return 0; -} - -const char *test__bpf_subtest_get_desc(int i __maybe_unused) -{ - return NULL; -} - -int test__bpf(struct test *test __maybe_unused, int i __maybe_unused) -{ pr_debug("Skip BPF test because BPF support is not compiled\n"); return TEST_SKIP; -} #endif +} + +static int test__bpf_pinning(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) +{ +#ifdef HAVE_LIBBPF_SUPPORT + return test__bpf(1); +#else + pr_debug("Skip BPF test because BPF support is not compiled\n"); + return TEST_SKIP; +#endif +} + +static int test__bpf_prologue_test(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) +{ +#if defined(HAVE_LIBBPF_SUPPORT) && defined(HAVE_BPF_PROLOGUE) + return test__bpf(2); +#else + pr_debug("Skip BPF test because BPF support is not compiled\n"); + return TEST_SKIP; +#endif +} + + +static struct test_case bpf_tests[] = { +#ifdef HAVE_LIBBPF_SUPPORT + TEST_CASE("Basic BPF filtering", basic_bpf_test), + TEST_CASE("BPF pinning", bpf_pinning), +#ifdef HAVE_BPF_PROLOGUE + TEST_CASE("BPF prologue generation", bpf_prologue_test), +#else + TEST_CASE_REASON("BPF prologue generation", bpf_prologue_test, "not compiled in"), +#endif +#else + TEST_CASE_REASON("Basic BPF filtering", basic_bpf_test, "not compiled in"), + TEST_CASE_REASON("BPF pinning", bpf_pinning, "not compiled in"), + TEST_CASE_REASON("BPF prologue generation", bpf_prologue_test, "not compiled in"), +#endif + { .name = NULL, } +}; + +struct test_suite suite__bpf = { + .desc = "BPF filter", + .test_cases = bpf_tests, +}; diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c index da7dc5e45d..fac3717d9b 100644 --- a/tools/perf/tests/builtin-test.c +++ b/tools/perf/tests/builtin-test.c @@ -30,350 +30,135 @@ static bool dont_fork; -struct test __weak arch_tests[] = { - { - .func = NULL, - }, +struct test_suite *__weak arch_tests[] = { + NULL, }; -static struct test generic_tests[] = { - { - .desc = "vmlinux symtab matches kallsyms", - .func = test__vmlinux_matches_kallsyms, - }, - { - .desc = "Detect openat syscall event", - .func = test__openat_syscall_event, - }, - { - .desc = "Detect openat syscall event on all cpus", - .func = test__openat_syscall_event_on_all_cpus, - }, - { - .desc = "Read samples using the mmap interface", - .func = test__basic_mmap, - }, - { - .desc = "Test data source output", - .func = test__mem, - }, - { - .desc = "Parse event definition strings", - .func = test__parse_events, - }, - { - .desc = "Simple expression parser", - .func = test__expr, - }, - { - .desc = "PERF_RECORD_* events & perf_sample fields", - .func = test__PERF_RECORD, - }, - { - .desc = "Parse perf pmu format", - .func = test__pmu, - }, - { - .desc = "PMU events", - .func = test__pmu_events, - .subtest = { - .skip_if_fail = false, - .get_nr = test__pmu_events_subtest_get_nr, - .get_desc = test__pmu_events_subtest_get_desc, - .skip_reason = test__pmu_events_subtest_skip_reason, - }, - - }, - { - .desc = "DSO data read", - .func = test__dso_data, - }, - { - .desc = "DSO data cache", - .func = test__dso_data_cache, - }, - { - .desc = "DSO data reopen", - .func = test__dso_data_reopen, - }, - { - .desc = "Roundtrip evsel->name", - .func = test__perf_evsel__roundtrip_name_test, - }, - { - .desc = "Parse sched tracepoints fields", - .func = test__perf_evsel__tp_sched_test, - }, - { - .desc = "syscalls:sys_enter_openat event fields", - .func = test__syscall_openat_tp_fields, - }, - { - .desc = "Setup struct perf_event_attr", - .func = test__attr, - }, - { - .desc = "Match and link multiple hists", - .func = test__hists_link, - }, - { - .desc = "'import perf' in python", - .func = test__python_use, - }, - { - .desc = "Breakpoint overflow signal handler", - .func = test__bp_signal, - .is_supported = test__bp_signal_is_supported, - }, - { - .desc = "Breakpoint overflow sampling", - .func = test__bp_signal_overflow, - .is_supported = test__bp_signal_is_supported, - }, - { - .desc = "Breakpoint accounting", - .func = test__bp_accounting, - .is_supported = test__bp_account_is_supported, - }, - { - .desc = "Watchpoint", - .func = test__wp, - .is_supported = test__wp_is_supported, - .subtest = { - .skip_if_fail = false, - .get_nr = test__wp_subtest_get_nr, - .get_desc = test__wp_subtest_get_desc, - .skip_reason = test__wp_subtest_skip_reason, - }, - }, - { - .desc = "Number of exit events of a simple workload", - .func = test__task_exit, - }, - { - .desc = "Software clock events period values", - .func = test__sw_clock_freq, - }, - { - .desc = "Object code reading", - .func = test__code_reading, - }, - { - .desc = "Sample parsing", - .func = test__sample_parsing, - }, - { - .desc = "Use a dummy software event to keep tracking", - .func = test__keep_tracking, - }, - { - .desc = "Parse with no sample_id_all bit set", - .func = test__parse_no_sample_id_all, - }, - { - .desc = "Filter hist entries", - .func = test__hists_filter, - }, - { - .desc = "Lookup mmap thread", - .func = test__mmap_thread_lookup, - }, - { - .desc = "Share thread maps", - .func = test__thread_maps_share, - }, - { - .desc = "Sort output of hist entries", - .func = test__hists_output, - }, - { - .desc = "Cumulate child hist entries", - .func = test__hists_cumulate, - }, - { - .desc = "Track with sched_switch", - .func = test__switch_tracking, - }, - { - .desc = "Filter fds with revents mask in a fdarray", - .func = test__fdarray__filter, - }, - { - .desc = "Add fd to a fdarray, making it autogrow", - .func = test__fdarray__add, - }, - { - .desc = "kmod_path__parse", - .func = test__kmod_path__parse, - }, - { - .desc = "Thread map", - .func = test__thread_map, - }, - { - .desc = "LLVM search and compile", - .func = test__llvm, - .subtest = { - .skip_if_fail = true, - .get_nr = test__llvm_subtest_get_nr, - .get_desc = test__llvm_subtest_get_desc, - }, - }, - { - .desc = "Session topology", - .func = test__session_topology, - }, - { - .desc = "BPF filter", - .func = test__bpf, - .subtest = { - .skip_if_fail = true, - .get_nr = test__bpf_subtest_get_nr, - .get_desc = test__bpf_subtest_get_desc, - }, - }, - { - .desc = "Synthesize thread map", - .func = test__thread_map_synthesize, - }, - { - .desc = "Remove thread map", - .func = test__thread_map_remove, - }, - { - .desc = "Synthesize cpu map", - .func = test__cpu_map_synthesize, - }, - { - .desc = "Synthesize stat config", - .func = test__synthesize_stat_config, - }, - { - .desc = "Synthesize stat", - .func = test__synthesize_stat, - }, - { - .desc = "Synthesize stat round", - .func = test__synthesize_stat_round, - }, - { - .desc = "Synthesize attr update", - .func = test__event_update, - }, - { - .desc = "Event times", - .func = test__event_times, - }, - { - .desc = "Read backward ring buffer", - .func = test__backward_ring_buffer, - }, - { - .desc = "Print cpu map", - .func = test__cpu_map_print, - }, - { - .desc = "Merge cpu map", - .func = test__cpu_map_merge, - }, - - { - .desc = "Probe SDT events", - .func = test__sdt_event, - }, - { - .desc = "is_printable_array", - .func = test__is_printable_array, - }, - { - .desc = "Print bitmap", - .func = test__bitmap_print, - }, - { - .desc = "perf hooks", - .func = test__perf_hooks, - }, - { - .desc = "builtin clang support", - .func = test__clang, - .subtest = { - .skip_if_fail = true, - .get_nr = test__clang_subtest_get_nr, - .get_desc = test__clang_subtest_get_desc, - } - }, - { - .desc = "unit_number__scnprintf", - .func = test__unit_number__scnprint, - }, - { - .desc = "mem2node", - .func = test__mem2node, - }, - { - .desc = "time utils", - .func = test__time_utils, - }, - { - .desc = "Test jit_write_elf", - .func = test__jit_write_elf, - }, - { - .desc = "Test libpfm4 support", - .func = test__pfm, - .subtest = { - .skip_if_fail = true, - .get_nr = test__pfm_subtest_get_nr, - .get_desc = test__pfm_subtest_get_desc, - } - }, - { - .desc = "Test api io", - .func = test__api_io, - }, - { - .desc = "maps__merge_in", - .func = test__maps__merge_in, - }, - { - .desc = "Demangle Java", - .func = test__demangle_java, - }, - { - .desc = "Demangle OCaml", - .func = test__demangle_ocaml, - }, - { - .desc = "Parse and process metrics", - .func = test__parse_metric, - }, - { - .desc = "PE file support", - .func = test__pe_file_parsing, - }, - { - .desc = "Event expansion for cgroups", - .func = test__expand_cgroup_events, - }, - { - .desc = "Convert perf time to TSC", - .func = test__perf_time_to_tsc, - .is_supported = test__tsc_is_supported, - }, - { - .desc = "dlfilter C API", - .func = test__dlfilter, - }, - { - .func = NULL, - }, +static struct test_suite *generic_tests[] = { + &suite__vmlinux_matches_kallsyms, + &suite__openat_syscall_event, + &suite__openat_syscall_event_on_all_cpus, + &suite__basic_mmap, + &suite__mem, + &suite__parse_events, + &suite__expr, + &suite__PERF_RECORD, + &suite__pmu, + &suite__pmu_events, + &suite__dso_data, + &suite__dso_data_cache, + &suite__dso_data_reopen, + &suite__perf_evsel__roundtrip_name_test, + &suite__perf_evsel__tp_sched_test, + &suite__syscall_openat_tp_fields, + &suite__attr, + &suite__hists_link, + &suite__python_use, + &suite__bp_signal, + &suite__bp_signal_overflow, + &suite__bp_accounting, + &suite__wp, + &suite__task_exit, + &suite__sw_clock_freq, + &suite__code_reading, + &suite__sample_parsing, + &suite__keep_tracking, + &suite__parse_no_sample_id_all, + &suite__hists_filter, + &suite__mmap_thread_lookup, + &suite__thread_maps_share, + &suite__hists_output, + &suite__hists_cumulate, + &suite__switch_tracking, + &suite__fdarray__filter, + &suite__fdarray__add, + &suite__kmod_path__parse, + &suite__thread_map, + &suite__llvm, + &suite__session_topology, + &suite__bpf, + &suite__thread_map_synthesize, + &suite__thread_map_remove, + &suite__cpu_map_synthesize, + &suite__synthesize_stat_config, + &suite__synthesize_stat, + &suite__synthesize_stat_round, + &suite__event_update, + &suite__event_times, + &suite__backward_ring_buffer, + &suite__cpu_map_print, + &suite__cpu_map_merge, + &suite__sdt_event, + &suite__is_printable_array, + &suite__bitmap_print, + &suite__perf_hooks, + &suite__clang, + &suite__unit_number__scnprint, + &suite__mem2node, + &suite__time_utils, + &suite__jit_write_elf, + &suite__pfm, + &suite__api_io, + &suite__maps__merge_in, + &suite__demangle_java, + &suite__demangle_ocaml, + &suite__parse_metric, + &suite__pe_file_parsing, + &suite__expand_cgroup_events, + &suite__perf_time_to_tsc, + &suite__dlfilter, + &suite__sigtrap, + NULL, }; -static struct test *tests[] = { +static struct test_suite **tests[] = { generic_tests, arch_tests, }; +static int num_subtests(const struct test_suite *t) +{ + int num; + + if (!t->test_cases) + return 0; + + num = 0; + while (t->test_cases[num].name) + num++; + + return num; +} + +static bool has_subtests(const struct test_suite *t) +{ + return num_subtests(t) > 1; +} + +static const char *skip_reason(const struct test_suite *t, int subtest) +{ + if (t->test_cases && subtest >= 0) + return t->test_cases[subtest].skip_reason; + + return NULL; +} + +static const char *test_description(const struct test_suite *t, int subtest) +{ + if (t->test_cases && subtest >= 0) + return t->test_cases[subtest].desc; + + return t->desc; +} + +static test_fnptr test_function(const struct test_suite *t, int subtest) +{ + if (subtest <= 0) + return t->test_cases[0].run_case; + + return t->test_cases[subtest].run_case; +} + static bool perf_test__matches(const char *desc, int curr, int argc, const char *argv[]) { int i; @@ -398,7 +183,7 @@ static bool perf_test__matches(const char *desc, int curr, int argc, const char return false; } -static int run_test(struct test *test, int subtest) +static int run_test(struct test_suite *test, int subtest) { int status, err = -1, child = dont_fork ? 0 : fork(); char sbuf[STRERR_BUFSIZE]; @@ -430,7 +215,7 @@ static int run_test(struct test *test, int subtest) } } - err = test->func(test, subtest); + err = test_function(test, subtest)(test, subtest); if (!dont_fork) exit(err); } @@ -450,24 +235,19 @@ static int run_test(struct test *test, int subtest) return err; } -#define for_each_test(j, t) \ +#define for_each_test(j, k, t) \ for (j = 0; j < ARRAY_SIZE(tests); j++) \ - for (t = &tests[j][0]; t->func; t++) + for (k = 0, t = tests[j][k]; tests[j][k]; k++, t = tests[j][k]) -static int test_and_print(struct test *t, bool force_skip, int subtest) +static int test_and_print(struct test_suite *t, int subtest) { int err; - if (!force_skip) { - pr_debug("\n--- start ---\n"); - err = run_test(t, subtest); - pr_debug("---- end ----\n"); - } else { - pr_debug("\n--- force skipped ---\n"); - err = TEST_SKIP; - } + pr_debug("\n--- start ---\n"); + err = run_test(t, subtest); + pr_debug("---- end ----\n"); - if (!t->subtest.get_nr) + if (!has_subtests(t)) pr_debug("%s:", t->desc); else pr_debug("%s subtest %d:", t->desc, subtest + 1); @@ -477,11 +257,10 @@ static int test_and_print(struct test *t, bool force_skip, int subtest) pr_info(" Ok\n"); break; case TEST_SKIP: { - const char *skip_reason = NULL; - if (t->subtest.skip_reason) - skip_reason = t->subtest.skip_reason(subtest); - if (skip_reason) - color_fprintf(stderr, PERF_COLOR_YELLOW, " Skip (%s)\n", skip_reason); + const char *reason = skip_reason(t, subtest); + + if (reason) + color_fprintf(stderr, PERF_COLOR_YELLOW, " Skip (%s)\n", reason); else color_fprintf(stderr, PERF_COLOR_YELLOW, " Skip\n"); } @@ -580,7 +359,7 @@ struct shell_test { const char *file; }; -static int shell_test__run(struct test *test, int subdir __maybe_unused) +static int shell_test__run(struct test_suite *test, int subdir __maybe_unused) { int err; char script[PATH_MAX]; @@ -622,24 +401,34 @@ static int run_shell_tests(int argc, const char *argv[], int i, int width, for_each_shell_test(entlist, n_dirs, st.dir, ent) { int curr = i++; char desc[256]; - struct test test = { - .desc = shell_test__description(desc, sizeof(desc), st.dir, ent->d_name), - .func = shell_test__run, + struct test_case test_cases[] = { + { + .desc = shell_test__description(desc, + sizeof(desc), + st.dir, + ent->d_name), + .run_case = shell_test__run, + }, + { .name = NULL, } + }; + struct test_suite test_suite = { + .desc = test_cases[0].desc, + .test_cases = test_cases, .priv = &st, }; - if (!perf_test__matches(test.desc, curr, argc, argv)) + if (!perf_test__matches(test_suite.desc, curr, argc, argv)) continue; st.file = ent->d_name; - pr_info("%2d: %-*s:", i, width, test.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"); continue; } - test_and_print(&test, false, -1); + test_and_print(&test_suite, 0); } for (e = 0; e < n_dirs; e++) @@ -650,33 +439,31 @@ static int run_shell_tests(int argc, const char *argv[], int i, int width, static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist) { - struct test *t; - unsigned int j; + struct test_suite *t; + unsigned int j, k; int i = 0; int width = shell_tests__max_desc_width(); - for_each_test(j, t) { - int len = strlen(t->desc); + for_each_test(j, k, t) { + int len = strlen(test_description(t, -1)); if (width < len) width = len; } - for_each_test(j, t) { - int curr = i++, err; + for_each_test(j, k, t) { + int curr = i++; int subi; - if (!perf_test__matches(t->desc, curr, argc, argv)) { + if (!perf_test__matches(test_description(t, -1), curr, argc, argv)) { bool skip = true; int subn; - if (!t->subtest.get_nr) - continue; - - subn = t->subtest.get_nr(); + subn = num_subtests(t); for (subi = 0; subi < subn; subi++) { - if (perf_test__matches(t->subtest.get_desc(subi), curr, argc, argv)) + if (perf_test__matches(test_description(t, subi), + curr, argc, argv)) skip = false; } @@ -684,22 +471,17 @@ static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist) continue; } - if (t->is_supported && !t->is_supported()) { - pr_debug("%2d: %-*s: Disabled\n", i, width, t->desc); - continue; - } - - pr_info("%2d: %-*s:", i, width, t->desc); + 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"); continue; } - if (!t->subtest.get_nr) { - test_and_print(t, false, -1); + if (!has_subtests(t)) { + test_and_print(t, -1); } else { - int subn = t->subtest.get_nr(); + int subn = num_subtests(t); /* * minus 2 to align with normal testcases. * For subtest we print additional '.x' in number. @@ -709,7 +491,6 @@ static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist) * 35.1: Basic BPF llvm compiling test : Ok */ int subw = width > 2 ? width - 2 : width; - bool skip = false; if (subn <= 0) { color_fprintf(stderr, PERF_COLOR_YELLOW, @@ -719,21 +500,20 @@ static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist) pr_info("\n"); for (subi = 0; subi < subn; subi++) { - int len = strlen(t->subtest.get_desc(subi)); + int len = strlen(test_description(t, subi)); if (subw < len) subw = len; } for (subi = 0; subi < subn; subi++) { - if (!perf_test__matches(t->subtest.get_desc(subi), curr, argc, argv)) + if (!perf_test__matches(test_description(t, subi), + curr, argc, argv)) continue; - pr_info("%2d.%1d: %-*s:", i, subi + 1, subw, - t->subtest.get_desc(subi)); - err = test_and_print(t, skip, subi); - if (err != TEST_OK && t->subtest.skip_if_fail) - skip = true; + pr_info("%3d.%1d: %-*s:", i, subi + 1, subw, + test_description(t, subi)); + test_and_print(t, subi); } } } @@ -759,14 +539,14 @@ static int perf_test__list_shell(int argc, const char **argv, int i) for_each_shell_test(entlist, n_dirs, path, ent) { int curr = i++; char bf[256]; - struct test t = { + struct test_suite t = { .desc = shell_test__description(bf, sizeof(bf), path, ent->d_name), }; 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); } @@ -778,26 +558,25 @@ static int perf_test__list_shell(int argc, const char **argv, int i) static int perf_test__list(int argc, const char **argv) { - unsigned int j; - struct test *t; + unsigned int j, k; + struct test_suite *t; int i = 0; - for_each_test(j, t) { + for_each_test(j, k, t) { int curr = i++; - if (!perf_test__matches(t->desc, curr, argc, argv) || - (t->is_supported && !t->is_supported())) + if (!perf_test__matches(test_description(t, -1), curr, argc, argv)) continue; - pr_info("%2d: %s\n", i, t->desc); + pr_info("%3d: %s\n", i, test_description(t, -1)); - if (t->subtest.get_nr) { - int subn = t->subtest.get_nr(); + 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, - t->subtest.get_desc(subi)); + pr_info("%3d:%1d: %s\n", i, subi + 1, + test_description(t, subi)); } } @@ -828,6 +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/clang.c b/tools/perf/tests/clang.c index 2577d3ed15..a7111005d5 100644 --- a/tools/perf/tests/clang.c +++ b/tools/perf/tests/clang.c @@ -3,44 +3,30 @@ #include "c++/clang-c.h" #include -static struct { - int (*func)(void); - const char *desc; -} clang_testcase_table[] = { -#ifdef HAVE_LIBCLANGLLVM_SUPPORT - { - .func = test__clang_to_IR, - .desc = "builtin clang compile C source to IR", - }, - { - .func = test__clang_to_obj, - .desc = "builtin clang compile C source to ELF object", - }, -#endif -}; - -int test__clang_subtest_get_nr(void) -{ - return (int)ARRAY_SIZE(clang_testcase_table); -} - -const char *test__clang_subtest_get_desc(int i) -{ - if (i < 0 || i >= (int)ARRAY_SIZE(clang_testcase_table)) - return NULL; - return clang_testcase_table[i].desc; -} - #ifndef HAVE_LIBCLANGLLVM_SUPPORT -int test__clang(struct test *test __maybe_unused, int i __maybe_unused) +static int test__clang_to_IR(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { return TEST_SKIP; } -#else -int test__clang(struct test *test __maybe_unused, int i) + +static int test__clang_to_obj(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { - if (i < 0 || i >= (int)ARRAY_SIZE(clang_testcase_table)) - return TEST_FAIL; - return clang_testcase_table[i].func(); + return TEST_SKIP; } #endif + +static struct test_case clang_tests[] = { + TEST_CASE_REASON("builtin clang compile C source to IR", clang_to_IR, + "not compiled in"), + TEST_CASE_REASON("builtin clang compile C source to ELF object", + clang_to_obj, + "not compiled in"), + { .name = NULL, } +}; + +struct test_suite suite__clang = { + .desc = "builtin clang support", + .test_cases = clang_tests, +}; diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c index 9b4a765e4b..5610767b40 100644 --- a/tools/perf/tests/code-reading.c +++ b/tools/perf/tests/code-reading.c @@ -606,7 +606,8 @@ static int do_test_code_reading(bool try_kcore) } ret = perf_event__synthesize_thread_map(NULL, threads, - perf_event__process, machine, false); + perf_event__process, machine, + true, false); if (ret < 0) { pr_debug("perf_event__synthesize_thread_map failed\n"); goto out_err; @@ -715,7 +716,7 @@ static int do_test_code_reading(bool try_kcore) return err; } -int test__code_reading(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__code_reading(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { int ret; @@ -742,3 +743,5 @@ int test__code_reading(struct test *test __maybe_unused, int subtest __maybe_unu return -1; }; } + +DEFINE_SUITE("Object code reading", code_reading); diff --git a/tools/perf/tests/cpumap.c b/tools/perf/tests/cpumap.c index 0472b110fe..84e87e31f1 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); @@ -67,15 +67,15 @@ 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; } -int test__cpu_map_synthesize(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__cpu_map_synthesize(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct perf_cpu_map *cpus; @@ -111,7 +111,7 @@ static int cpu_map_print(const char *str) return !strcmp(buf, str); } -int test__cpu_map_print(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__cpu_map_print(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { TEST_ASSERT_VAL("failed to convert map", cpu_map_print("1")); TEST_ASSERT_VAL("failed to convert map", cpu_map_print("1,5")); @@ -123,7 +123,7 @@ int test__cpu_map_print(struct test *test __maybe_unused, int subtest __maybe_un return 0; } -int test__cpu_map_merge(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__cpu_map_merge(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct perf_cpu_map *a = perf_cpu_map__new("4,2,1"); struct perf_cpu_map *b = perf_cpu_map__new("4,5,7"); @@ -137,3 +137,7 @@ int test__cpu_map_merge(struct test *test __maybe_unused, int subtest __maybe_un perf_cpu_map__put(c); return 0; } + +DEFINE_SUITE("Synthesize cpu map", cpu_map_synthesize); +DEFINE_SUITE("Print cpu map", cpu_map_print); +DEFINE_SUITE("Merge cpu map", cpu_map_merge); diff --git a/tools/perf/tests/demangle-java-test.c b/tools/perf/tests/demangle-java-test.c index 8f3b90832f..44d1be303b 100644 --- a/tools/perf/tests/demangle-java-test.c +++ b/tools/perf/tests/demangle-java-test.c @@ -7,7 +7,7 @@ #include "debug.h" #include "demangle-java.h" -int test__demangle_java(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__demangle_java(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { int ret = TEST_OK; char *buf = NULL; @@ -40,3 +40,5 @@ int test__demangle_java(struct test *test __maybe_unused, int subtest __maybe_un return ret; } + +DEFINE_SUITE("Demangle Java", demangle_java); diff --git a/tools/perf/tests/demangle-ocaml-test.c b/tools/perf/tests/demangle-ocaml-test.c index 0043be8123..90a4285e2a 100644 --- a/tools/perf/tests/demangle-ocaml-test.c +++ b/tools/perf/tests/demangle-ocaml-test.c @@ -7,7 +7,7 @@ #include "debug.h" #include "demangle-ocaml.h" -int test__demangle_ocaml(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__demangle_ocaml(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { int ret = TEST_OK; char *buf = NULL; @@ -41,3 +41,5 @@ int test__demangle_ocaml(struct test *test __maybe_unused, int subtest __maybe_u return ret; } + +DEFINE_SUITE("Demangle OCaml", demangle_ocaml); diff --git a/tools/perf/tests/dlfilter-test.c b/tools/perf/tests/dlfilter-test.c index bc03b5df68..84352d5534 100644 --- a/tools/perf/tests/dlfilter-test.c +++ b/tools/perf/tests/dlfilter-test.c @@ -398,7 +398,7 @@ static void test_data__free(struct test_data *td) } } -int test__dlfilter(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__dlfilter(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct test_data td = {.fd = -1}; int pid = getpid(); @@ -414,3 +414,5 @@ int test__dlfilter(struct test *test __maybe_unused, int subtest __maybe_unused) test_data__free(&td); return err; } + +DEFINE_SUITE("dlfilter C API", dlfilter); diff --git a/tools/perf/tests/dso-data.c b/tools/perf/tests/dso-data.c index 43e1b01e5a..3419a4ab55 100644 --- a/tools/perf/tests/dso-data.c +++ b/tools/perf/tests/dso-data.c @@ -113,7 +113,7 @@ static int dso__data_fd(struct dso *dso, struct machine *machine) return fd; } -int test__dso_data(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__dso_data(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct machine machine; struct dso *dso; @@ -248,7 +248,7 @@ static int set_fd_limit(int n) return setrlimit(RLIMIT_NOFILE, &rlim); } -int test__dso_data_cache(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__dso_data_cache(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct machine machine; long nr_end, nr = open_files_cnt(); @@ -318,7 +318,7 @@ static long new_limit(int count) return ret; } -int test__dso_data_reopen(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__dso_data_reopen(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct machine machine; long nr_end, nr = open_files_cnt(), lim = new_limit(3); @@ -393,3 +393,7 @@ int test__dso_data_reopen(struct test *test __maybe_unused, int subtest __maybe_ TEST_ASSERT_VAL("failed leaking files", nr == nr_end); return 0; } + +DEFINE_SUITE("DSO data read", dso_data); +DEFINE_SUITE("DSO data cache", dso_data_cache); +DEFINE_SUITE("DSO data reopen", dso_data_reopen); diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c index c756284b3b..2dab2d2620 100644 --- a/tools/perf/tests/dwarf-unwind.c +++ b/tools/perf/tests/dwarf-unwind.c @@ -195,7 +195,8 @@ NO_TAIL_CALL_ATTRIBUTE noinline int test_dwarf_unwind__krava_1(struct thread *th return ret; } -int test__dwarf_unwind(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__dwarf_unwind(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { struct machine *machine; struct thread *thread; @@ -237,3 +238,5 @@ int test__dwarf_unwind(struct test *test __maybe_unused, int subtest __maybe_unu machine__delete(machine); return err; } + +DEFINE_SUITE("Test dwarf unwind", dwarf_unwind); diff --git a/tools/perf/tests/event-times.c b/tools/perf/tests/event-times.c index 04ce4401f7..7606eb3df9 100644 --- a/tools/perf/tests/event-times.c +++ b/tools/perf/tests/event-times.c @@ -216,7 +216,7 @@ static int test_times(int (attach)(struct evlist *), * and checks that enabled and running times * match. */ -int test__event_times(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__event_times(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { int err, ret = 0; @@ -239,3 +239,5 @@ int test__event_times(struct test *test __maybe_unused, int subtest __maybe_unus #undef _T return ret; } + +DEFINE_SUITE("Event times", event_times); diff --git a/tools/perf/tests/event_update.c b/tools/perf/tests/event_update.c index 44a50527f9..78db4d704e 100644 --- a/tools/perf/tests/event_update.c +++ b/tools/perf/tests/event_update.c @@ -75,20 +75,19 @@ 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; } -int test__event_update(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__event_update(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct evsel *evsel; struct event_name tmp; struct evlist *evlist = evlist__new_default(); - char *unit = strdup("KRAVA"); TEST_ASSERT_VAL("failed to get evlist", evlist); @@ -99,7 +98,8 @@ int test__event_update(struct test *test __maybe_unused, int subtest __maybe_unu perf_evlist__id_add(&evlist->core, &evsel->core, 0, 0, 123); - evsel->unit = unit; + free((char *)evsel->unit); + evsel->unit = strdup("KRAVA"); TEST_ASSERT_VAL("failed to synthesize attr update unit", !perf_event__synthesize_event_update_unit(NULL, evsel, process_event_unit)); @@ -119,7 +119,8 @@ int test__event_update(struct test *test __maybe_unused, int subtest __maybe_unu TEST_ASSERT_VAL("failed to synthesize attr update cpus", !perf_event__synthesize_event_update_cpus(&tmp.tool, evsel, process_event_cpus)); - free(unit); evlist__delete(evlist); return 0; } + +DEFINE_SUITE("Synthesize attr update", event_update); diff --git a/tools/perf/tests/evsel-roundtrip-name.c b/tools/perf/tests/evsel-roundtrip-name.c index 4e09f0a312..fdbf17642e 100644 --- a/tools/perf/tests/evsel-roundtrip-name.c +++ b/tools/perf/tests/evsel-roundtrip-name.c @@ -99,7 +99,8 @@ static int __perf_evsel__name_array_test(const char *names[], int nr_names, #define perf_evsel__name_array_test(names, distance) \ __perf_evsel__name_array_test(names, ARRAY_SIZE(names), distance) -int test__perf_evsel__roundtrip_name_test(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__perf_evsel__roundtrip_name_test(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { int err = 0, ret = 0; @@ -120,3 +121,5 @@ int test__perf_evsel__roundtrip_name_test(struct test *test __maybe_unused, int return ret; } + +DEFINE_SUITE("Roundtrip evsel->name", perf_evsel__roundtrip_name_test); diff --git a/tools/perf/tests/evsel-tp-sched.c b/tools/perf/tests/evsel-tp-sched.c index f9e34bd26c..cf4da3d748 100644 --- a/tools/perf/tests/evsel-tp-sched.c +++ b/tools/perf/tests/evsel-tp-sched.c @@ -32,7 +32,8 @@ static int evsel__test_field(struct evsel *evsel, const char *name, int size, bo return ret; } -int test__perf_evsel__tp_sched_test(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__perf_evsel__tp_sched_test(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { struct evsel *evsel = evsel__newtp("sched", "sched_switch"); int ret = 0; @@ -87,3 +88,5 @@ int test__perf_evsel__tp_sched_test(struct test *test __maybe_unused, int subtes evsel__delete(evsel); return ret; } + +DEFINE_SUITE("Parse sched tracepoints fields", perf_evsel__tp_sched_test); diff --git a/tools/perf/tests/expand-cgroup.c b/tools/perf/tests/expand-cgroup.c index 0e46aeb843..dfefe5b60e 100644 --- a/tools/perf/tests/expand-cgroup.c +++ b/tools/perf/tests/expand-cgroup.c @@ -124,17 +124,19 @@ static int expand_group_events(void) evlist = evlist__new(); TEST_ASSERT_VAL("failed to get evlist", evlist); + parse_events_error__init(&err); ret = parse_events(evlist, event_str, &err); if (ret < 0) { pr_debug("failed to parse event '%s', err %d, str '%s'\n", event_str, ret, err.str); - parse_events_print_error(&err, event_str); + parse_events_error__print(&err, event_str); goto out; } rblist__init(&metric_events); ret = test_expand_events(evlist, &metric_events); out: + parse_events_error__exit(&err); evlist__delete(evlist); return ret; } @@ -193,7 +195,7 @@ static int expand_metric_events(void) .metric_name = NULL, }, }; - struct pmu_events_map ev_map = { + const struct pmu_events_map ev_map = { .cpuid = "test", .version = "1", .type = "core", @@ -219,8 +221,8 @@ static int expand_metric_events(void) return ret; } -int test__expand_cgroup_events(struct test *test __maybe_unused, - int subtest __maybe_unused) +static int test__expand_cgroup_events(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { int ret; @@ -238,3 +240,5 @@ int test__expand_cgroup_events(struct test *test __maybe_unused, return ret; } + +DEFINE_SUITE("Event expansion for cgroups", expand_cgroup_events); diff --git a/tools/perf/tests/expr.c b/tools/perf/tests/expr.c index 4d01051951..d54c5371c6 100644 --- a/tools/perf/tests/expr.c +++ b/tools/perf/tests/expr.c @@ -1,88 +1,193 @@ // SPDX-License-Identifier: GPL-2.0 #include "util/debug.h" #include "util/expr.h" +#include "util/smt.h" #include "tests.h" #include #include #include +static int test_ids_union(void) +{ + struct hashmap *ids1, *ids2; + + /* Empty union. */ + ids1 = ids__new(); + TEST_ASSERT_VAL("ids__new", ids1); + ids2 = ids__new(); + TEST_ASSERT_VAL("ids__new", ids2); + + ids1 = ids__union(ids1, ids2); + TEST_ASSERT_EQUAL("union", (int)hashmap__size(ids1), 0); + + /* Union {foo, bar} against {}. */ + ids2 = ids__new(); + TEST_ASSERT_VAL("ids__new", ids2); + + TEST_ASSERT_EQUAL("ids__insert", ids__insert(ids1, strdup("foo")), 0); + TEST_ASSERT_EQUAL("ids__insert", ids__insert(ids1, strdup("bar")), 0); + + ids1 = ids__union(ids1, ids2); + TEST_ASSERT_EQUAL("union", (int)hashmap__size(ids1), 2); + + /* Union {foo, bar} against {foo}. */ + ids2 = ids__new(); + TEST_ASSERT_VAL("ids__new", ids2); + TEST_ASSERT_EQUAL("ids__insert", ids__insert(ids2, strdup("foo")), 0); + + ids1 = ids__union(ids1, ids2); + TEST_ASSERT_EQUAL("union", (int)hashmap__size(ids1), 2); + + /* Union {foo, bar} against {bar,baz}. */ + ids2 = ids__new(); + TEST_ASSERT_VAL("ids__new", ids2); + TEST_ASSERT_EQUAL("ids__insert", ids__insert(ids2, strdup("bar")), 0); + TEST_ASSERT_EQUAL("ids__insert", ids__insert(ids2, strdup("baz")), 0); + + ids1 = ids__union(ids1, ids2); + TEST_ASSERT_EQUAL("union", (int)hashmap__size(ids1), 3); + + ids__free(ids1); + + return 0; +} + static int test(struct expr_parse_ctx *ctx, const char *e, double val2) { double val; - if (expr__parse(&val, ctx, e, 1)) + if (expr__parse(&val, ctx, e)) TEST_ASSERT_VAL("parse test failed", 0); TEST_ASSERT_VAL("unexpected value", val == val2); return 0; } -int test__expr(struct test *t __maybe_unused, int subtest __maybe_unused) +static int test__expr(struct test_suite *t __maybe_unused, int subtest __maybe_unused) { struct expr_id_data *val_ptr; const char *p; - double val; + double val, num_cpus, num_cores, num_dies, num_packages; int ret; - struct expr_parse_ctx ctx; + struct expr_parse_ctx *ctx; - expr__ctx_init(&ctx); - expr__add_id_val(&ctx, strdup("FOO"), 1); - expr__add_id_val(&ctx, strdup("BAR"), 2); + TEST_ASSERT_EQUAL("ids_union", test_ids_union(), 0); - ret = test(&ctx, "1+1", 2); - ret |= test(&ctx, "FOO+BAR", 3); - ret |= test(&ctx, "(BAR/2)%2", 1); - ret |= test(&ctx, "1 - -4", 5); - ret |= test(&ctx, "(FOO-1)*2 + (BAR/2)%2 - -4", 5); - ret |= test(&ctx, "1-1 | 1", 1); - ret |= test(&ctx, "1-1 & 1", 0); - ret |= test(&ctx, "min(1,2) + 1", 2); - ret |= test(&ctx, "max(1,2) + 1", 3); - ret |= test(&ctx, "1+1 if 3*4 else 0", 2); - ret |= test(&ctx, "1.1 + 2.1", 3.2); - ret |= test(&ctx, ".1 + 2.", 2.1); - ret |= test(&ctx, "d_ratio(1, 2)", 0.5); - ret |= test(&ctx, "d_ratio(2.5, 0)", 0); - ret |= test(&ctx, "1.1 < 2.2", 1); - ret |= test(&ctx, "2.2 > 1.1", 1); - ret |= test(&ctx, "1.1 < 1.1", 0); - ret |= test(&ctx, "2.2 > 2.2", 0); - ret |= test(&ctx, "2.2 < 1.1", 0); - ret |= test(&ctx, "1.1 > 2.2", 0); + ctx = expr__ctx_new(); + TEST_ASSERT_VAL("expr__ctx_new", ctx); + expr__add_id_val(ctx, strdup("FOO"), 1); + expr__add_id_val(ctx, strdup("BAR"), 2); - if (ret) + ret = test(ctx, "1+1", 2); + ret |= test(ctx, "FOO+BAR", 3); + ret |= test(ctx, "(BAR/2)%2", 1); + ret |= test(ctx, "1 - -4", 5); + ret |= test(ctx, "(FOO-1)*2 + (BAR/2)%2 - -4", 5); + ret |= test(ctx, "1-1 | 1", 1); + ret |= test(ctx, "1-1 & 1", 0); + ret |= test(ctx, "min(1,2) + 1", 2); + ret |= test(ctx, "max(1,2) + 1", 3); + ret |= test(ctx, "1+1 if 3*4 else 0", 2); + ret |= test(ctx, "1.1 + 2.1", 3.2); + ret |= test(ctx, ".1 + 2.", 2.1); + ret |= test(ctx, "d_ratio(1, 2)", 0.5); + ret |= test(ctx, "d_ratio(2.5, 0)", 0); + ret |= test(ctx, "1.1 < 2.2", 1); + ret |= test(ctx, "2.2 > 1.1", 1); + ret |= test(ctx, "1.1 < 1.1", 0); + ret |= test(ctx, "2.2 > 2.2", 0); + ret |= test(ctx, "2.2 < 1.1", 0); + ret |= test(ctx, "1.1 > 2.2", 0); + + if (ret) { + expr__ctx_free(ctx); return ret; + } p = "FOO/0"; - ret = expr__parse(&val, &ctx, p, 1); + ret = expr__parse(&val, ctx, p); TEST_ASSERT_VAL("division by zero", ret == -1); p = "BAR/"; - ret = expr__parse(&val, &ctx, p, 1); + ret = expr__parse(&val, ctx, p); TEST_ASSERT_VAL("missing operand", ret == -1); - expr__ctx_clear(&ctx); - TEST_ASSERT_VAL("find other", - expr__find_other("FOO + BAR + BAZ + BOZO", "FOO", - &ctx, 1) == 0); - TEST_ASSERT_VAL("find other", hashmap__size(&ctx.ids) == 3); - TEST_ASSERT_VAL("find other", hashmap__find(&ctx.ids, "BAR", + expr__ctx_clear(ctx); + TEST_ASSERT_VAL("find ids", + expr__find_ids("FOO + BAR + BAZ + BOZO", "FOO", + ctx) == 0); + TEST_ASSERT_VAL("find ids", hashmap__size(ctx->ids) == 3); + TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "BAR", (void **)&val_ptr)); - TEST_ASSERT_VAL("find other", hashmap__find(&ctx.ids, "BAZ", + TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "BAZ", (void **)&val_ptr)); - TEST_ASSERT_VAL("find other", hashmap__find(&ctx.ids, "BOZO", + TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "BOZO", (void **)&val_ptr)); - expr__ctx_clear(&ctx); - TEST_ASSERT_VAL("find other", - expr__find_other("EVENT1\\,param\\=?@ + EVENT2\\,param\\=?@", - NULL, &ctx, 3) == 0); - TEST_ASSERT_VAL("find other", hashmap__size(&ctx.ids) == 2); - TEST_ASSERT_VAL("find other", hashmap__find(&ctx.ids, "EVENT1,param=3/", + expr__ctx_clear(ctx); + ctx->runtime = 3; + TEST_ASSERT_VAL("find ids", + expr__find_ids("EVENT1\\,param\\=?@ + EVENT2\\,param\\=?@", + NULL, ctx) == 0); + TEST_ASSERT_VAL("find ids", hashmap__size(ctx->ids) == 2); + TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "EVENT1,param=3@", (void **)&val_ptr)); - TEST_ASSERT_VAL("find other", hashmap__find(&ctx.ids, "EVENT2,param=3/", + TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "EVENT2,param=3@", (void **)&val_ptr)); - expr__ctx_clear(&ctx); + expr__ctx_clear(ctx); + TEST_ASSERT_VAL("find ids", + expr__find_ids("dash\\-event1 - dash\\-event2", + NULL, ctx) == 0); + TEST_ASSERT_VAL("find ids", hashmap__size(ctx->ids) == 2); + TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "dash-event1", + (void **)&val_ptr)); + TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "dash-event2", + (void **)&val_ptr)); + + /* Only EVENT1 or EVENT2 need be measured depending on the value of smt_on. */ + expr__ctx_clear(ctx); + TEST_ASSERT_VAL("find ids", + expr__find_ids("EVENT1 if #smt_on else EVENT2", + NULL, ctx) == 0); + TEST_ASSERT_VAL("find ids", hashmap__size(ctx->ids) == 1); + TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, + smt_on() ? "EVENT1" : "EVENT2", + (void **)&val_ptr)); + + /* The expression is a constant 1.0 without needing to evaluate EVENT1. */ + expr__ctx_clear(ctx); + TEST_ASSERT_VAL("find ids", + expr__find_ids("1.0 if EVENT1 > 100.0 else 1.0", + NULL, ctx) == 0); + TEST_ASSERT_VAL("find ids", hashmap__size(ctx->ids) == 0); + + /* Test toplogy constants appear well ordered. */ + expr__ctx_clear(ctx); + TEST_ASSERT_VAL("#num_cpus", expr__parse(&num_cpus, ctx, "#num_cpus") == 0); + TEST_ASSERT_VAL("#num_cores", expr__parse(&num_cores, ctx, "#num_cores") == 0); + TEST_ASSERT_VAL("#num_cpus >= #num_cores", num_cpus >= num_cores); + TEST_ASSERT_VAL("#num_dies", expr__parse(&num_dies, ctx, "#num_dies") == 0); + TEST_ASSERT_VAL("#num_cores >= #num_dies", num_cores >= num_dies); + TEST_ASSERT_VAL("#num_packages", expr__parse(&num_packages, ctx, "#num_packages") == 0); + + if (num_dies) // Some platforms do not have CPU die support, for example s390 + TEST_ASSERT_VAL("#num_dies >= #num_packages", num_dies >= num_packages); + + /* + * Source count returns the number of events aggregating in a leader + * event including the leader. Check parsing yields an id. + */ + expr__ctx_clear(ctx); + TEST_ASSERT_VAL("source count", + expr__find_ids("source_count(EVENT1)", + NULL, ctx) == 0); + TEST_ASSERT_VAL("source count", hashmap__size(ctx->ids) == 1); + TEST_ASSERT_VAL("source count", hashmap__find(ctx->ids, "EVENT1", + (void **)&val_ptr)); + + expr__ctx_free(ctx); return 0; } + +DEFINE_SUITE("Simple expression parser", expr); diff --git a/tools/perf/tests/fdarray.c b/tools/perf/tests/fdarray.c index d9eca8e86a..40983c3574 100644 --- a/tools/perf/tests/fdarray.c +++ b/tools/perf/tests/fdarray.c @@ -28,7 +28,7 @@ static int fdarray__fprintf_prefix(struct fdarray *fda, const char *prefix, FILE return printed + fdarray__fprintf(fda, fp); } -int test__fdarray__filter(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__fdarray__filter(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { int nr_fds, err = TEST_FAIL; struct fdarray *fda = fdarray__new(5, 5); @@ -89,7 +89,7 @@ int test__fdarray__filter(struct test *test __maybe_unused, int subtest __maybe_ return err; } -int test__fdarray__add(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__fdarray__add(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { int err = TEST_FAIL; struct fdarray *fda = fdarray__new(2, 2); @@ -158,3 +158,6 @@ int test__fdarray__add(struct test *test __maybe_unused, int subtest __maybe_unu out: return err; } + +DEFINE_SUITE("Filter fds with revents mask in a fdarray", fdarray__filter); +DEFINE_SUITE("Add fd to a fdarray, making it autogrow", fdarray__add); diff --git a/tools/perf/tests/genelf.c b/tools/perf/tests/genelf.c index f797f9823e..95f3be1b68 100644 --- a/tools/perf/tests/genelf.c +++ b/tools/perf/tests/genelf.c @@ -16,8 +16,8 @@ #define TEMPL "/tmp/perf-test-XXXXXX" -int test__jit_write_elf(struct test *test __maybe_unused, - int subtest __maybe_unused) +static int test__jit_write_elf(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { #ifdef HAVE_JITDUMP static unsigned char x86_code[] = { @@ -49,3 +49,5 @@ int test__jit_write_elf(struct test *test __maybe_unused, return TEST_SKIP; #endif } + +DEFINE_SUITE("Test jit_write_elf", jit_write_elf); diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c index 890cb1f5bf..17f4fcd6bd 100644 --- a/tools/perf/tests/hists_cumulate.c +++ b/tools/perf/tests/hists_cumulate.c @@ -689,7 +689,7 @@ static int test4(struct evsel *evsel, struct machine *machine) return err; } -int test__hists_cumulate(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__hists_cumulate(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { int err = TEST_FAIL; struct machines machines; @@ -736,3 +736,5 @@ int test__hists_cumulate(struct test *test __maybe_unused, int subtest __maybe_u return err; } + +DEFINE_SUITE("Cumulate child hist entries", hists_cumulate); diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c index ca6120cd1d..08cbeb9e39 100644 --- a/tools/perf/tests/hists_filter.c +++ b/tools/perf/tests/hists_filter.c @@ -101,7 +101,7 @@ static int add_hist_entries(struct evlist *evlist, return TEST_FAIL; } -int test__hists_filter(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__hists_filter(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { int err = TEST_FAIL; struct machines machines; @@ -325,3 +325,5 @@ int test__hists_filter(struct test *test __maybe_unused, int subtest __maybe_unu return err; } + +DEFINE_SUITE("Filter hist entries", hists_filter); diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c index a024d3f3a4..c575e13a85 100644 --- a/tools/perf/tests/hists_link.c +++ b/tools/perf/tests/hists_link.c @@ -264,7 +264,7 @@ static int validate_link(struct hists *leader, struct hists *other) return __validate_link(leader, 0) || __validate_link(other, 1); } -int test__hists_link(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__hists_link(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { int err = -1; struct hists *hists, *first_hists; @@ -339,3 +339,5 @@ int test__hists_link(struct test *test __maybe_unused, int subtest __maybe_unuse return err; } + +DEFINE_SUITE("Match and link multiple hists", hists_link); diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c index 8973f35df6..0bde4a768c 100644 --- a/tools/perf/tests/hists_output.c +++ b/tools/perf/tests/hists_output.c @@ -575,7 +575,7 @@ static int test5(struct evsel *evsel, struct machine *machine) return err; } -int test__hists_output(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__hists_output(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { int err = TEST_FAIL; struct machines machines; @@ -623,3 +623,5 @@ int test__hists_output(struct test *test __maybe_unused, int subtest __maybe_unu return err; } + +DEFINE_SUITE("Sort output of hist entries", hists_output); diff --git a/tools/perf/tests/is_printable_array.c b/tools/perf/tests/is_printable_array.c index 9c7b3baca4..f72de2457f 100644 --- a/tools/perf/tests/is_printable_array.c +++ b/tools/perf/tests/is_printable_array.c @@ -5,7 +5,7 @@ #include "debug.h" #include "print_binary.h" -int test__is_printable_array(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__is_printable_array(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { char buf1[] = { 'k', 'r', 4, 'v', 'a', 0 }; char buf2[] = { 'k', 'r', 'a', 'v', 4, 0 }; @@ -36,3 +36,5 @@ int test__is_printable_array(struct test *test __maybe_unused, int subtest __may return TEST_OK; } + +DEFINE_SUITE("is_printable_array", is_printable_array); diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c index a0438b0f08..dd20673124 100644 --- a/tools/perf/tests/keep-tracking.c +++ b/tools/perf/tests/keep-tracking.c @@ -61,7 +61,7 @@ static int find_comm(struct evlist *evlist, const char *comm) * when an event is disabled but a dummy software event is not disabled. If the * test passes %0 is returned, otherwise %-1 is returned. */ -int test__keep_tracking(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__keep_tracking(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct record_opts opts = { .mmap_pages = UINT_MAX, @@ -160,3 +160,5 @@ int test__keep_tracking(struct test *test __maybe_unused, int subtest __maybe_un return err; } + +DEFINE_SUITE("Use a dummy software event to keep tracking", keep_tracking); diff --git a/tools/perf/tests/kmod-path.c b/tools/perf/tests/kmod-path.c index e483210b17..dfe1bd5dab 100644 --- a/tools/perf/tests/kmod-path.c +++ b/tools/perf/tests/kmod-path.c @@ -47,7 +47,7 @@ static int test_is_kernel_module(const char *path, int cpumode, bool expect) #define M(path, c, e) \ TEST_ASSERT_VAL("failed", !test_is_kernel_module(path, c, e)) -int test__kmod_path__parse(struct test *t __maybe_unused, int subtest __maybe_unused) +static int test__kmod_path__parse(struct test_suite *t __maybe_unused, int subtest __maybe_unused) { /* path alloc_name kmod comp name */ T("/xxxx/xxxx/x-x.ko", true , true, 0 , "[x_x]"); @@ -159,3 +159,5 @@ int test__kmod_path__parse(struct test *t __maybe_unused, int subtest __maybe_un return 0; } + +DEFINE_SUITE("kmod_path__parse", kmod_path__parse); diff --git a/tools/perf/tests/llvm.c b/tools/perf/tests/llvm.c index 33e43cce90..8ac0a3a457 100644 --- a/tools/perf/tests/llvm.c +++ b/tools/perf/tests/llvm.c @@ -124,7 +124,7 @@ test_llvm__fetch_bpf_obj(void **p_obj_buf, return ret; } -int test__llvm(struct test *test __maybe_unused, int subtest) +static int test__llvm(int subtest) { int ret; void *obj_buf = NULL; @@ -148,32 +148,72 @@ int test__llvm(struct test *test __maybe_unused, int subtest) return ret; } +#endif //HAVE_LIBBPF_SUPPORT -int test__llvm_subtest_get_nr(void) -{ - return __LLVM_TESTCASE_MAX; -} - -const char *test__llvm_subtest_get_desc(int subtest) -{ - if ((subtest < 0) || (subtest >= __LLVM_TESTCASE_MAX)) - return NULL; - - return bpf_source_table[subtest].desc; -} -#else //HAVE_LIBBPF_SUPPORT -int test__llvm(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__llvm__bpf_base_prog(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { +#ifdef HAVE_LIBBPF_SUPPORT + return test__llvm(LLVM_TESTCASE_BASE); +#else + pr_debug("Skip LLVM test because BPF support is not compiled\n"); return TEST_SKIP; +#endif } -int test__llvm_subtest_get_nr(void) +static int test__llvm__bpf_test_kbuild_prog(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { - return 0; +#ifdef HAVE_LIBBPF_SUPPORT + return test__llvm(LLVM_TESTCASE_KBUILD); +#else + pr_debug("Skip LLVM test because BPF support is not compiled\n"); + return TEST_SKIP; +#endif } -const char *test__llvm_subtest_get_desc(int subtest __maybe_unused) +static int test__llvm__bpf_test_prologue_prog(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { - return NULL; +#ifdef HAVE_LIBBPF_SUPPORT + return test__llvm(LLVM_TESTCASE_BPF_PROLOGUE); +#else + pr_debug("Skip LLVM test because BPF support is not compiled\n"); + return TEST_SKIP; +#endif } -#endif // HAVE_LIBBPF_SUPPORT + +static int test__llvm__bpf_test_relocation(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) +{ +#ifdef HAVE_LIBBPF_SUPPORT + return test__llvm(LLVM_TESTCASE_BPF_RELOCATION); +#else + pr_debug("Skip LLVM test because BPF support is not compiled\n"); + return TEST_SKIP; +#endif +} + + +static struct test_case llvm_tests[] = { +#ifdef HAVE_LIBBPF_SUPPORT + TEST_CASE("Basic BPF llvm compile", llvm__bpf_base_prog), + TEST_CASE("kbuild searching", llvm__bpf_test_kbuild_prog), + TEST_CASE("Compile source for BPF prologue generation", + llvm__bpf_test_prologue_prog), + TEST_CASE("Compile source for BPF relocation", llvm__bpf_test_relocation), +#else + TEST_CASE_REASON("Basic BPF llvm compile", llvm__bpf_base_prog, "not compiled in"), + TEST_CASE_REASON("kbuild searching", llvm__bpf_test_kbuild_prog, "not compiled in"), + TEST_CASE_REASON("Compile source for BPF prologue generation", + llvm__bpf_test_prologue_prog, "not compiled in"), + TEST_CASE_REASON("Compile source for BPF relocation", + llvm__bpf_test_relocation, "not compiled in"), +#endif + { .name = NULL, } +}; + +struct test_suite suite__llvm = { + .desc = "LLVM search and compile", + .test_cases = llvm_tests, +}; diff --git a/tools/perf/tests/maps.c b/tools/perf/tests/maps.c index 1ac72919fa..e308a3296c 100644 --- a/tools/perf/tests/maps.c +++ b/tools/perf/tests/maps.c @@ -33,7 +33,7 @@ static int check_maps(struct map_def *merged, unsigned int size, struct maps *ma return TEST_OK; } -int test__maps__merge_in(struct test *t __maybe_unused, int subtest __maybe_unused) +static int test__maps__merge_in(struct test_suite *t __maybe_unused, int subtest __maybe_unused) { struct maps maps; unsigned int i; @@ -120,3 +120,5 @@ int test__maps__merge_in(struct test *t __maybe_unused, int subtest __maybe_unus maps__exit(&maps); return TEST_OK; } + +DEFINE_SUITE("maps__merge_in", maps__merge_in); diff --git a/tools/perf/tests/mem.c b/tools/perf/tests/mem.c index 673a11a6cd..56014ec7d4 100644 --- a/tools/perf/tests/mem.c +++ b/tools/perf/tests/mem.c @@ -23,7 +23,7 @@ static int check(union perf_mem_data_src data_src, return 0; } -int test__mem(struct test *text __maybe_unused, int subtest __maybe_unused) +static int test__mem(struct test_suite *text __maybe_unused, int subtest __maybe_unused) { int ret = 0; union perf_mem_data_src src; @@ -56,3 +56,5 @@ int test__mem(struct test *text __maybe_unused, int subtest __maybe_unused) return ret; } + +DEFINE_SUITE("Test data source output", mem); diff --git a/tools/perf/tests/mem2node.c b/tools/perf/tests/mem2node.c index e4d0d58b97..4c96829510 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) @@ -43,7 +44,7 @@ static unsigned long *get_bitmap(const char *str, int nbits) return bm && map ? bm : NULL; } -int test__mem2node(struct test *t __maybe_unused, int subtest __maybe_unused) +static int test__mem2node(struct test_suite *t __maybe_unused, int subtest __maybe_unused) { struct mem2node map; struct memory_node nodes[3]; @@ -77,3 +78,5 @@ int test__mem2node(struct test *t __maybe_unused, int subtest __maybe_unused) mem2node__exit(&map); return 0; } + +DEFINE_SUITE("mem2node", mem2node); diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c index d38757db2d..c3c17600f2 100644 --- a/tools/perf/tests/mmap-basic.c +++ b/tools/perf/tests/mmap-basic.c @@ -29,7 +29,7 @@ * Then it checks if the number of syscalls reported as perf events by * the kernel corresponds to the number of syscalls made. */ -int test__basic_mmap(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__basic_mmap(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { int err = -1; union perf_event *event; @@ -59,11 +59,12 @@ int test__basic_mmap(struct test *test __maybe_unused, int subtest __maybe_unuse } 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; } @@ -164,3 +165,5 @@ int test__basic_mmap(struct test *test __maybe_unused, int subtest __maybe_unuse perf_thread_map__put(threads); return err; } + +DEFINE_SUITE("Read samples using the mmap interface", basic_mmap); diff --git a/tools/perf/tests/mmap-thread-lookup.c b/tools/perf/tests/mmap-thread-lookup.c index 8d9d4cbff7..a4301fc7b7 100644 --- a/tools/perf/tests/mmap-thread-lookup.c +++ b/tools/perf/tests/mmap-thread-lookup.c @@ -135,7 +135,7 @@ static int synth_all(struct machine *machine) { return perf_event__synthesize_threads(NULL, perf_event__process, - machine, 0, 1); + machine, 1, 0, 1); } static int synth_process(struct machine *machine) @@ -147,7 +147,7 @@ static int synth_process(struct machine *machine) err = perf_event__synthesize_thread_map(NULL, map, perf_event__process, - machine, 0); + machine, 1, 0); perf_thread_map__put(map); return err; @@ -224,7 +224,7 @@ static int mmap_events(synth_cb synth) * * by using all thread objects. */ -int test__mmap_thread_lookup(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__mmap_thread_lookup(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { /* perf_event__synthesize_threads synthesize */ TEST_ASSERT_VAL("failed with sythesizing all", @@ -236,3 +236,5 @@ int test__mmap_thread_lookup(struct test *test __maybe_unused, int subtest __may return 0; } + +DEFINE_SUITE("Lookup mmap thread", mmap_thread_lookup); diff --git a/tools/perf/tests/openat-syscall-all-cpus.c b/tools/perf/tests/openat-syscall-all-cpus.c index f7dd6c463f..1ab362323d 100644 --- a/tools/perf/tests/openat-syscall-all-cpus.c +++ b/tools/perf/tests/openat-syscall-all-cpus.c @@ -19,9 +19,11 @@ #include "stat.h" #include "util/counts.h" -int test__openat_syscall_event_on_all_cpus(struct test *test __maybe_unused, int subtest __maybe_unused) +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; @@ -57,23 +59,23 @@ int test__openat_syscall_event_on_all_cpus(struct test *test __maybe_unused, int 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; } @@ -81,37 +83,29 @@ int test__openat_syscall_event_on_all_cpus(struct test *test __maybe_unused, int 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; } } @@ -127,3 +121,5 @@ int test__openat_syscall_event_on_all_cpus(struct test *test __maybe_unused, int perf_thread_map__put(threads); return err; } + +DEFINE_SUITE("Detect openat syscall event on all cpus", openat_syscall_event_on_all_cpus); diff --git a/tools/perf/tests/openat-syscall-tp-fields.c b/tools/perf/tests/openat-syscall-tp-fields.c index 5e4af2f0f1..a7b2800652 100644 --- a/tools/perf/tests/openat-syscall-tp-fields.c +++ b/tools/perf/tests/openat-syscall-tp-fields.c @@ -22,7 +22,8 @@ #define AT_FDCWD -100 #endif -int test__syscall_openat_tp_fields(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__syscall_openat_tp_fields(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { struct record_opts opts = { .target = { @@ -142,3 +143,5 @@ int test__syscall_openat_tp_fields(struct test *test __maybe_unused, int subtest out: return err; } + +DEFINE_SUITE("syscalls:sys_enter_openat event fields", syscall_openat_tp_fields); diff --git a/tools/perf/tests/openat-syscall.c b/tools/perf/tests/openat-syscall.c index 85a8f0fe7a..7f4c13c4b1 100644 --- a/tools/perf/tests/openat-syscall.c +++ b/tools/perf/tests/openat-syscall.c @@ -13,7 +13,8 @@ #include "tests.h" #include "util/counts.h" -int test__openat_syscall_event(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__openat_syscall_event(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { int err = -1, fd; struct evsel *evsel; @@ -66,3 +67,5 @@ int test__openat_syscall_event(struct test *test __maybe_unused, int subtest __m perf_thread_map__put(threads); return err; } + +DEFINE_SUITE("Detect openat syscall event", openat_syscall_event); diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c index fd3556cc9a..e71efadb24 100644 --- a/tools/perf/tests/parse-events.c +++ b/tools/perf/tests/parse-events.c @@ -605,7 +605,7 @@ static int test__checkterms_simple(struct list_head *terms) TEST_ASSERT_VAL("wrong type val", term->type_val == PARSE_EVENTS__TERM_TYPE_NUM); TEST_ASSERT_VAL("wrong val", term->val.num == 10); - TEST_ASSERT_VAL("wrong config", !term->config); + TEST_ASSERT_VAL("wrong config", !strcmp(term->config, "config")); /* config1 */ term = list_entry(term->list.next, struct parse_events_term, list); @@ -614,7 +614,7 @@ static int test__checkterms_simple(struct list_head *terms) TEST_ASSERT_VAL("wrong type val", term->type_val == PARSE_EVENTS__TERM_TYPE_NUM); TEST_ASSERT_VAL("wrong val", term->val.num == 1); - TEST_ASSERT_VAL("wrong config", !term->config); + TEST_ASSERT_VAL("wrong config", !strcmp(term->config, "config1")); /* config2=3 */ term = list_entry(term->list.next, struct parse_events_term, list); @@ -623,7 +623,7 @@ static int test__checkterms_simple(struct list_head *terms) TEST_ASSERT_VAL("wrong type val", term->type_val == PARSE_EVENTS__TERM_TYPE_NUM); TEST_ASSERT_VAL("wrong val", term->val.num == 3); - TEST_ASSERT_VAL("wrong config", !term->config); + TEST_ASSERT_VAL("wrong config", !strcmp(term->config, "config2")); /* umask=1*/ term = list_entry(term->list.next, struct parse_events_term, list); @@ -661,7 +661,7 @@ static int test__checkterms_simple(struct list_head *terms) TEST_ASSERT_VAL("wrong type val", term->type_val == PARSE_EVENTS__TERM_TYPE_NUM); TEST_ASSERT_VAL("wrong val", term->val.num == 0xead); - TEST_ASSERT_VAL("wrong config", !term->config); + TEST_ASSERT_VAL("wrong config", !strcmp(term->config, "config")); return 0; } @@ -2045,7 +2045,6 @@ static int test_event(struct evlist_test *e) struct evlist *evlist; int ret; - bzero(&err, sizeof(err)); if (e->valid && !e->valid()) { pr_debug("... SKIP"); return 0; @@ -2055,15 +2054,41 @@ static int test_event(struct evlist_test *e) if (evlist == NULL) return -ENOMEM; + parse_events_error__init(&err); ret = parse_events(evlist, e->name, &err); if (ret) { pr_debug("failed to parse event '%s', err %d, str '%s'\n", e->name, ret, err.str); - parse_events_print_error(&err, e->name); + parse_events_error__print(&err, e->name); } else { ret = e->check(evlist); } + parse_events_error__exit(&err); + evlist__delete(evlist); + 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; @@ -2276,7 +2301,27 @@ static int test_pmu_events_alias(char *event, char *alias) return test_event(&e); } -int test__parse_events(struct test *test __maybe_unused, int subtest __maybe_unused) +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; char *event, *alias; @@ -2313,9 +2358,15 @@ 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; return ret2; } + +DEFINE_SUITE("Parse event definition strings", parse_events); diff --git a/tools/perf/tests/parse-metric.c b/tools/perf/tests/parse-metric.c index 4f6f4904e8..07b6f4ec02 100644 --- a/tools/perf/tests/parse-metric.c +++ b/tools/perf/tests/parse-metric.c @@ -79,7 +79,7 @@ static struct pmu_event pme_test[] = { } }; -static struct pmu_events_map map = { +static const struct pmu_events_map map = { .cpuid = "test", .version = "1", .type = "core", @@ -109,6 +109,7 @@ static void load_runtime_stat(struct runtime_stat *st, struct evlist *evlist, struct evsel *evsel; u64 count; + perf_stat__reset_shadow_stats(); evlist__for_each_entry(evlist, evsel) { count = find_value(evsel->name, vals); perf_stat__update_shadow_stats(evsel, count, 0, st); @@ -369,7 +370,7 @@ static int test_metric_group(void) return 0; } -int test__parse_metric(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__parse_metric(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { TEST_ASSERT_VAL("IPC failed", test_ipc() == 0); TEST_ASSERT_VAL("frontend failed", test_frontend() == 0); @@ -383,3 +384,5 @@ int test__parse_metric(struct test *test __maybe_unused, int subtest __maybe_unu } return 0; } + +DEFINE_SUITE("Parse and process metrics", parse_metric); diff --git a/tools/perf/tests/parse-no-sample-id-all.c b/tools/perf/tests/parse-no-sample-id-all.c index 4712736767..d62e31595a 100644 --- a/tools/perf/tests/parse-no-sample-id-all.c +++ b/tools/perf/tests/parse-no-sample-id-all.c @@ -67,7 +67,8 @@ struct test_attr_event { * * Return: %0 on success, %-1 if the test fails. */ -int test__parse_no_sample_id_all(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__parse_no_sample_id_all(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { int err; @@ -103,3 +104,5 @@ int test__parse_no_sample_id_all(struct test *test __maybe_unused, int subtest _ return 0; } + +DEFINE_SUITE("Parse with no sample_id_all bit set", parse_no_sample_id_all); diff --git a/tools/perf/tests/pe-file-parsing.c b/tools/perf/tests/pe-file-parsing.c index 58b90c42eb..c09a9fae16 100644 --- a/tools/perf/tests/pe-file-parsing.c +++ b/tools/perf/tests/pe-file-parsing.c @@ -68,7 +68,7 @@ static int run_dir(const char *d) return TEST_OK; } -int test__pe_file_parsing(struct test *test __maybe_unused, +static int test__pe_file_parsing(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct stat st; @@ -89,10 +89,12 @@ int test__pe_file_parsing(struct test *test __maybe_unused, #else -int test__pe_file_parsing(struct test *test __maybe_unused, +static int test__pe_file_parsing(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { return TEST_SKIP; } #endif + +DEFINE_SUITE("PE file support", pe_file_parsing); diff --git a/tools/perf/tests/perf-hooks.c b/tools/perf/tests/perf-hooks.c index dd865e0bea..78cdeb8964 100644 --- a/tools/perf/tests/perf-hooks.c +++ b/tools/perf/tests/perf-hooks.c @@ -26,7 +26,7 @@ static void the_hook(void *_hook_flags) raise(SIGSEGV); } -int test__perf_hooks(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__perf_hooks(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { int hook_flags = 0; @@ -45,3 +45,5 @@ int test__perf_hooks(struct test *test __maybe_unused, int subtest __maybe_unuse return TEST_FAIL; return TEST_OK; } + +DEFINE_SUITE("perf hooks", perf_hooks); diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c index 0df471bf15..6354465067 100644 --- a/tools/perf/tests/perf-record.c +++ b/tools/perf/tests/perf-record.c @@ -41,7 +41,7 @@ static int sched__get_first_possible_cpu(pid_t pid, cpu_set_t *maskp) return cpu; } -int test__PERF_RECORD(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__PERF_RECORD(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct record_opts opts = { .target = { @@ -332,3 +332,5 @@ int test__PERF_RECORD(struct test *test __maybe_unused, int subtest __maybe_unus out: return (err < 0 || errs > 0) ? -1 : 0; } + +DEFINE_SUITE("PERF_RECORD_* events & perf_sample fields", PERF_RECORD); diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c index 7c56bc1f4c..d12d0ad818 100644 --- a/tools/perf/tests/perf-time-to-tsc.c +++ b/tools/perf/tests/perf-time-to-tsc.c @@ -23,6 +23,16 @@ #include "pmu.h" #include "pmu-hybrid.h" +/* + * Except x86_64/i386 and Arm64, other archs don't support TSC in perf. Just + * enable the test for x86_64/i386 and Arm64 archs. + */ +#if defined(__x86_64__) || defined(__i386__) || defined(__aarch64__) +#define TSC_IS_SUPPORTED 1 +#else +#define TSC_IS_SUPPORTED 0 +#endif + #define CHECK__(x) { \ while ((x) < 0) { \ pr_debug(#x " failed!\n"); \ @@ -45,7 +55,7 @@ * %0 is returned, otherwise %-1 is returned. If TSC conversion is not * supported then then the test passes but " (not supported)" is printed. */ -int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__perf_time_to_tsc(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct record_opts opts = { .mmap_pages = UINT_MAX, @@ -69,6 +79,11 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe u64 test_time, comm1_time = 0, comm2_time = 0; struct mmap *md; + if (!TSC_IS_SUPPORTED) { + pr_debug("Test not supported on this architecture"); + return TEST_SKIP; + } + threads = thread_map__new(-1, getpid(), UINT_MAX); CHECK_NOT_NULL__(threads); @@ -185,15 +200,4 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe return err; } -bool test__tsc_is_supported(void) -{ - /* - * Except x86_64/i386 and Arm64, other archs don't support TSC in perf. - * Just enable the test for x86_64/i386 and Arm64 archs. - */ -#if defined(__x86_64__) || defined(__i386__) || defined(__aarch64__) - return true; -#else - return false; -#endif -} +DEFINE_SUITE("Convert perf time to TSC", perf_time_to_tsc); diff --git a/tools/perf/tests/pfm.c b/tools/perf/tests/pfm.c index e8fd0da076..71b76deb1f 100644 --- a/tools/perf/tests/pfm.c +++ b/tools/perf/tests/pfm.c @@ -11,27 +11,6 @@ #include -#ifdef HAVE_LIBPFM -static int test__pfm_events(void); -static int test__pfm_group(void); -#endif - -static const struct { - int (*func)(void); - const char *desc; -} pfm_testcase_table[] = { -#ifdef HAVE_LIBPFM - { - .func = test__pfm_events, - .desc = "test of individual --pfm-events", - }, - { - .func = test__pfm_group, - .desc = "test groups of --pfm-events", - }, -#endif -}; - #ifdef HAVE_LIBPFM static int count_pfm_events(struct perf_evlist *evlist) { @@ -44,7 +23,8 @@ static int count_pfm_events(struct perf_evlist *evlist) return count; } -static int test__pfm_events(void) +static int test__pfm_events(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { struct evlist *evlist; struct option opt; @@ -104,7 +84,8 @@ static int test__pfm_events(void) return 0; } -static int test__pfm_group(void) +static int test__pfm_group(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { struct evlist *evlist; struct option opt; @@ -187,27 +168,27 @@ static int test__pfm_group(void) } return 0; } -#endif - -const char *test__pfm_subtest_get_desc(int i) -{ - if (i < 0 || i >= (int)ARRAY_SIZE(pfm_testcase_table)) - return NULL; - return pfm_testcase_table[i].desc; -} - -int test__pfm_subtest_get_nr(void) -{ - return (int)ARRAY_SIZE(pfm_testcase_table); -} - -int test__pfm(struct test *test __maybe_unused, int i __maybe_unused) -{ -#ifdef HAVE_LIBPFM - if (i < 0 || i >= (int)ARRAY_SIZE(pfm_testcase_table)) - return TEST_FAIL; - return pfm_testcase_table[i].func(); #else +static int test__pfm_events(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) +{ return TEST_SKIP; -#endif } + +static int test__pfm_group(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) +{ + return TEST_SKIP; +} +#endif + +static struct test_case pfm_tests[] = { + TEST_CASE_REASON("test of individual --pfm-events", pfm_events, "not compiled in"), + TEST_CASE_REASON("test groups of --pfm-events", pfm_group, "not compiled in"), + { .name = NULL, } +}; + +struct test_suite suite__pfm = { + .desc = "Test libpfm4 support", + .test_cases = pfm_tests, +}; diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c index 43743cf719..1c695fb5a7 100644 --- a/tools/perf/tests/pmu-events.c +++ b/tools/perf/tests/pmu-events.c @@ -67,7 +67,7 @@ static const struct perf_pmu_test_event segment_reg_loads_any = { .desc = "Number of segment register loads", .topic = "other", }, - .alias_str = "umask=0x80,(null)=0x30d40,event=0x6", + .alias_str = "umask=0x80,period=0x30d40,event=0x6", .alias_long_desc = "Number of segment register loads", }; @@ -78,7 +78,7 @@ static const struct perf_pmu_test_event dispatch_blocked_any = { .desc = "Memory cluster signals to block micro-op dispatch for any reason", .topic = "other", }, - .alias_str = "umask=0x20,(null)=0x30d40,event=0x9", + .alias_str = "umask=0x20,period=0x30d40,event=0x9", .alias_long_desc = "Memory cluster signals to block micro-op dispatch for any reason", }; @@ -89,7 +89,7 @@ static const struct perf_pmu_test_event eist_trans = { .desc = "Number of Enhanced Intel SpeedStep(R) Technology (EIST) transitions", .topic = "other", }, - .alias_str = "umask=0,(null)=0x30d40,event=0x3a", + .alias_str = "umask=0,period=0x30d40,event=0x3a", .alias_long_desc = "Number of Enhanced Intel SpeedStep(R) Technology (EIST) transitions", }; @@ -143,10 +143,38 @@ 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", - .event = "event=0x2", + .event = "event=0x7", .desc = "Total read hits. Unit: hisi_sccl,l3c ", .topic = "uncore", .long_desc = "Total read hits", @@ -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, @@ -208,8 +238,23 @@ static const struct perf_pmu_test_event sys_ddr_pmu_write_cycles = { .matching_pmu = "uncore_sys_ddr_pmu", }; +static const struct perf_pmu_test_event sys_ccn_pmu_read_cycles = { + .event = { + .name = "sys_ccn_pmu.read_cycles", + .event = "config=0x2c", + .desc = "ccn read-cycles event. Unit: uncore_sys_ccn_pmu ", + .topic = "uncore", + .pmu = "uncore_sys_ccn_pmu", + .compat = "0x01", + }, + .alias_str = "config=0x2c", + .alias_long_desc = "ccn read-cycles event. Unit: uncore_sys_ccn_pmu ", + .matching_pmu = "uncore_sys_ccn_pmu", +}; + static const struct perf_pmu_test_event *sys_events[] = { &sys_ddr_pmu_write_cycles, + &sys_ccn_pmu_read_cycles, NULL }; @@ -227,9 +272,9 @@ static bool is_same(const char *reference, const char *test) return !strcmp(reference, test); } -static struct pmu_events_map *__test_pmu_get_events_map(void) +static const struct pmu_events_map *__test_pmu_get_events_map(void) { - struct pmu_events_map *map; + const struct pmu_events_map *map; for (map = &pmu_events_map[0]; map->cpuid; map++) { if (!strcmp(map->cpuid, "testcpu")) @@ -241,9 +286,9 @@ static struct pmu_events_map *__test_pmu_get_events_map(void) return NULL; } -static struct pmu_event *__test_pmu_get_sys_events_table(void) +static const struct pmu_event *__test_pmu_get_sys_events_table(void) { - struct pmu_sys_events *tables = &pmu_sys_event_tables[0]; + const struct pmu_sys_events *tables = &pmu_sys_event_tables[0]; for ( ; tables->name; tables++) { if (!strcmp("pme_test_soc_sys", tables->name)) @@ -253,8 +298,26 @@ static struct pmu_event *__test_pmu_get_sys_events_table(void) return NULL; } -static int compare_pmu_events(struct pmu_event *e1, const struct pmu_event *e2) +static int compare_pmu_events(const struct pmu_event *e1, const struct pmu_event *e2) { + if (!is_same(e1->name, e2->name)) { + pr_debug2("testing event e1 %s: mismatched name string, %s vs %s\n", + e1->name, e1->name, e2->name); + return -1; + } + + if (!is_same(e1->compat, e2->compat)) { + pr_debug2("testing event e1 %s: mismatched compat string, %s vs %s\n", + e1->name, e1->compat, e2->compat); + return -1; + } + + if (!is_same(e1->event, e2->event)) { + pr_debug2("testing event e1 %s: mismatched event, %s vs %s\n", + e1->name, e1->event, e2->event); + return -1; + } + if (!is_same(e1->desc, e2->desc)) { pr_debug2("testing event e1 %s: mismatched desc, %s vs %s\n", e1->name, e1->desc, e2->desc); @@ -273,6 +336,12 @@ static int compare_pmu_events(struct pmu_event *e1, const struct pmu_event *e2) return -1; } + if (!is_same(e1->pmu, e2->pmu)) { + pr_debug2("testing event e1 %s: mismatched pmu string, %s vs %s\n", + e1->name, e1->pmu, e2->pmu); + return -1; + } + if (!is_same(e1->unit, e2->unit)) { pr_debug2("testing event e1 %s: mismatched unit, %s vs %s\n", e1->name, e1->unit, e2->unit); @@ -285,6 +354,12 @@ static int compare_pmu_events(struct pmu_event *e1, const struct pmu_event *e2) return -1; } + if (!is_same(e1->aggr_mode, e2->aggr_mode)) { + pr_debug2("testing event e1 %s: mismatched aggr_mode, %s vs %s\n", + e1->name, e1->aggr_mode, e2->aggr_mode); + return -1; + } + if (!is_same(e1->metric_expr, e2->metric_expr)) { pr_debug2("testing event e1 %s: mismatched metric_expr, %s vs %s\n", e1->name, e1->metric_expr, e2->metric_expr); @@ -297,21 +372,21 @@ static int compare_pmu_events(struct pmu_event *e1, const struct pmu_event *e2) return -1; } + if (!is_same(e1->metric_group, e2->metric_group)) { + pr_debug2("testing event e1 %s: mismatched metric_group, %s vs %s\n", + e1->name, e1->metric_group, e2->metric_group); + return -1; + } + if (!is_same(e1->deprecated, e2->deprecated)) { pr_debug2("testing event e1 %s: mismatched deprecated, %s vs %s\n", e1->name, e1->deprecated, e2->deprecated); return -1; } - if (!is_same(e1->pmu, e2->pmu)) { - pr_debug2("testing event e1 %s: mismatched pmu string, %s vs %s\n", - e1->name, e1->pmu, e2->pmu); - return -1; - } - - if (!is_same(e1->compat, e2->compat)) { - pr_debug2("testing event e1 %s: mismatched compat string, %s vs %s\n", - e1->name, e1->compat, e2->compat); + if (!is_same(e1->metric_constraint, e2->metric_constraint)) { + pr_debug2("testing event e1 %s: mismatched metric_constant, %s vs %s\n", + e1->name, e1->metric_constraint, e2->metric_constraint); return -1; } @@ -373,11 +448,12 @@ static int compare_alias_to_test_event(struct perf_pmu_alias *alias, } /* Verify generated events from pmu-events.c are as expected */ -static int test_pmu_event_table(void) +static int test__pmu_event_table(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { - struct pmu_event *sys_event_tables = __test_pmu_get_sys_events_table(); - struct pmu_events_map *map = __test_pmu_get_events_map(); - struct pmu_event *table; + const struct pmu_event *sys_event_tables = __test_pmu_get_sys_events_table(); + const struct pmu_events_map *map = __test_pmu_get_events_map(); + const struct pmu_event *table; int map_events = 0, expected_events; /* ignore 3x sentinels */ @@ -473,7 +549,7 @@ static int __test_core_pmu_event_aliases(char *pmu_name, int *count) struct perf_pmu *pmu; LIST_HEAD(aliases); int res = 0; - struct pmu_events_map *map = __test_pmu_get_events_map(); + const struct pmu_events_map *map = __test_pmu_get_events_map(); struct perf_pmu_alias *a, *tmp; if (!map) @@ -526,7 +602,7 @@ static int __test_uncore_pmu_event_aliases(struct perf_pmu_test_pmu *test_pmu) struct perf_pmu *pmu = &test_pmu->pmu; const char *pmu_name = pmu->name; struct perf_pmu_alias *a, *tmp, *alias; - struct pmu_events_map *map; + const struct pmu_events_map *map; LIST_HEAD(aliases); int res = 0; @@ -608,6 +684,8 @@ static struct perf_pmu_test_pmu test_pmus[] = { }, .aliases = { &unc_cbo_xsnp_response_miss_eviction, + &uncore_hyphen, + &uncore_two_hyph, }, }, { @@ -647,10 +725,21 @@ static struct perf_pmu_test_pmu test_pmus[] = { &sys_ddr_pmu_write_cycles, }, }, + { + .pmu = { + .name = (char *)"uncore_sys_ccn_pmu4", + .is_uncore = 1, + .id = (char *)"0x01", + }, + .aliases = { + &sys_ccn_pmu_read_cycles, + }, + }, }; /* Test that aliases generated are as expected */ -static int test_aliases(void) +static int test__aliases(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { struct perf_pmu *pmu = NULL; unsigned long i; @@ -706,6 +795,7 @@ static int check_parse_id(const char *id, struct parse_events_error *error, { struct evlist *evlist; int ret; + char *dup, *cur; /* Numbers are always valid. */ if (is_number(id)) @@ -714,16 +804,28 @@ static int check_parse_id(const char *id, struct parse_events_error *error, evlist = evlist__new(); if (!evlist) return -ENOMEM; - ret = __parse_events(evlist, id, error, fake_pmu); + + dup = strdup(id); + if (!dup) + return -ENOMEM; + + for (cur = strchr(dup, '@') ; cur; cur = strchr(++cur, '@')) + *cur = '/'; + + ret = __parse_events(evlist, dup, error, fake_pmu); + free(dup); + evlist__delete(evlist); return ret; } -static int check_parse_cpu(const char *id, bool same_cpu, struct pmu_event *pe) +static int check_parse_cpu(const char *id, bool same_cpu, const struct pmu_event *pe) { - struct parse_events_error error = { .idx = 0, }; + struct parse_events_error error; + int ret; - int ret = check_parse_id(id, &error, NULL); + parse_events_error__init(&error); + ret = check_parse_id(id, &error, NULL); if (ret && same_cpu) { pr_warning("Parse event failed metric '%s' id '%s' expr '%s'\n", pe->metric_name, id, pe->metric_expr); @@ -734,22 +836,18 @@ static int check_parse_cpu(const char *id, bool same_cpu, struct pmu_event *pe) id, pe->metric_name, pe->metric_expr); ret = 0; } - free(error.str); - free(error.help); - free(error.first_str); - free(error.first_help); + parse_events_error__exit(&error); return ret; } static int check_parse_fake(const char *id) { - struct parse_events_error error = { .idx = 0, }; - int ret = check_parse_id(id, &error, &perf_pmu__fake); + struct parse_events_error error; + int ret; - free(error.str); - free(error.help); - free(error.first_str); - free(error.first_help); + parse_events_error__init(&error); + ret = check_parse_id(id, &error, &perf_pmu__fake); + parse_events_error__exit(&error); return ret; } @@ -770,7 +868,7 @@ struct metric { static int resolve_metric_simple(struct expr_parse_ctx *pctx, struct list_head *compound_list, - struct pmu_events_map *map, + const struct pmu_events_map *map, const char *metric_name) { struct hashmap_entry *cur, *cur_tmp; @@ -781,9 +879,9 @@ static int resolve_metric_simple(struct expr_parse_ctx *pctx, do { all = true; - hashmap__for_each_entry_safe((&pctx->ids), cur, cur_tmp, bkt) { + hashmap__for_each_entry_safe(pctx->ids, cur, cur_tmp, bkt) { struct metric_ref *ref; - struct pmu_event *pe; + const struct pmu_event *pe; pe = metricgroup__find_metric(cur->key, map); if (!pe) @@ -811,7 +909,7 @@ static int resolve_metric_simple(struct expr_parse_ctx *pctx, ref->metric_expr = pe->metric_expr; list_add_tail(&metric->list, compound_list); - rc = expr__find_other(pe->metric_expr, NULL, pctx, 0); + rc = expr__find_ids(pe->metric_expr, NULL, pctx); if (rc) goto out_err; break; /* The hashmap has been modified, so restart */ @@ -828,16 +926,22 @@ static int resolve_metric_simple(struct expr_parse_ctx *pctx, } -static int test_parsing(void) +static int test__parsing(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { - struct pmu_events_map *cpus_map = pmu_events_map__find(); - struct pmu_events_map *map; - struct pmu_event *pe; + const struct pmu_events_map *cpus_map = pmu_events_map__find(); + const struct pmu_events_map *map; + const struct pmu_event *pe; int i, j, k; int ret = 0; - struct expr_parse_ctx ctx; + struct expr_parse_ctx *ctx; double result; + ctx = expr__ctx_new(); + if (!ctx) { + pr_debug("expr__ctx_new failed"); + return TEST_FAIL; + } i = 0; for (;;) { map = &pmu_events_map[i++]; @@ -855,15 +959,14 @@ static int test_parsing(void) break; if (!pe->metric_expr) continue; - expr__ctx_init(&ctx); - if (expr__find_other(pe->metric_expr, NULL, &ctx, 0) - < 0) { - expr_failure("Parse other failed", map, pe); + expr__ctx_clear(ctx); + if (expr__find_ids(pe->metric_expr, NULL, ctx) < 0) { + expr_failure("Parse find ids failed", map, pe); ret++; continue; } - if (resolve_metric_simple(&ctx, &compound_list, map, + if (resolve_metric_simple(ctx, &compound_list, map, pe->metric_name)) { expr_failure("Could not resolve metrics", map, pe); ret++; @@ -876,27 +979,27 @@ static int test_parsing(void) * make them unique. */ k = 1; - hashmap__for_each_entry((&ctx.ids), cur, bkt) - expr__add_id_val(&ctx, strdup(cur->key), k++); + hashmap__for_each_entry(ctx->ids, cur, bkt) + expr__add_id_val(ctx, strdup(cur->key), k++); - hashmap__for_each_entry((&ctx.ids), cur, bkt) { + hashmap__for_each_entry(ctx->ids, cur, bkt) { if (check_parse_cpu(cur->key, map == cpus_map, pe)) ret++; } list_for_each_entry_safe(metric, tmp, &compound_list, list) { - expr__add_ref(&ctx, &metric->metric_ref); + expr__add_ref(ctx, &metric->metric_ref); free(metric); } - if (expr__parse(&result, &ctx, pe->metric_expr, 0)) { + if (expr__parse(&result, ctx, pe->metric_expr)) { expr_failure("Parse failed", map, pe); ret++; } - expr__ctx_clear(&ctx); } } + expr__ctx_free(ctx); /* TODO: fail when not ok */ exit: return ret == 0 ? TEST_OK : TEST_SKIP; @@ -916,7 +1019,7 @@ static struct test_metric metrics[] = { static int metric_parse_fake(const char *str) { - struct expr_parse_ctx ctx; + struct expr_parse_ctx *ctx; struct hashmap_entry *cur; double result; int ret = -1; @@ -925,9 +1028,13 @@ static int metric_parse_fake(const char *str) pr_debug("parsing '%s'\n", str); - expr__ctx_init(&ctx); - if (expr__find_other(str, NULL, &ctx, 0) < 0) { - pr_err("expr__find_other failed\n"); + ctx = expr__ctx_new(); + if (!ctx) { + pr_debug("expr__ctx_new failed"); + return TEST_FAIL; + } + if (expr__find_ids(str, NULL, ctx) < 0) { + pr_err("expr__find_ids failed\n"); return -1; } @@ -937,23 +1044,23 @@ static int metric_parse_fake(const char *str) * make them unique. */ i = 1; - hashmap__for_each_entry((&ctx.ids), cur, bkt) - expr__add_id_val(&ctx, strdup(cur->key), i++); + hashmap__for_each_entry(ctx->ids, cur, bkt) + expr__add_id_val(ctx, strdup(cur->key), i++); - hashmap__for_each_entry((&ctx.ids), cur, bkt) { + hashmap__for_each_entry(ctx->ids, cur, bkt) { if (check_parse_fake(cur->key)) { pr_err("check_parse_fake failed\n"); goto out; } } - if (expr__parse(&result, &ctx, str, 0)) + if (expr__parse(&result, ctx, str)) pr_err("expr__parse failed\n"); else ret = 0; out: - expr__ctx_clear(&ctx); + expr__ctx_free(ctx); return ret; } @@ -962,10 +1069,11 @@ static int metric_parse_fake(const char *str) * or all defined cpus via the 'fake_pmu' * in parse_events. */ -static int test_parsing_fake(void) +static int test__parsing_fake(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { - struct pmu_events_map *map; - struct pmu_event *pe; + const struct pmu_events_map *map; + const struct pmu_event *pe; unsigned int i, j; int err = 0; @@ -996,55 +1104,16 @@ static int test_parsing_fake(void) return 0; } -static const struct { - int (*func)(void); - const char *desc; -} pmu_events_testcase_table[] = { - { - .func = test_pmu_event_table, - .desc = "PMU event table sanity", - }, - { - .func = test_aliases, - .desc = "PMU event map aliases", - }, - { - .func = test_parsing, - .desc = "Parsing of PMU event table metrics", - }, - { - .func = test_parsing_fake, - .desc = "Parsing of PMU event table metrics with fake PMUs", - }, +static struct test_case pmu_events_tests[] = { + TEST_CASE("PMU event table sanity", pmu_event_table), + TEST_CASE("PMU event map aliases", aliases), + TEST_CASE_REASON("Parsing of PMU event table metrics", parsing, + "some metrics failed"), + TEST_CASE("Parsing of PMU event table metrics with fake PMUs", parsing_fake), + { .name = NULL, } }; -const char *test__pmu_events_subtest_get_desc(int subtest) -{ - if (subtest < 0 || - subtest >= (int)ARRAY_SIZE(pmu_events_testcase_table)) - return NULL; - return pmu_events_testcase_table[subtest].desc; -} - -const char *test__pmu_events_subtest_skip_reason(int subtest) -{ - if (subtest < 0 || - subtest >= (int)ARRAY_SIZE(pmu_events_testcase_table)) - return NULL; - if (pmu_events_testcase_table[subtest].func != test_parsing) - return NULL; - return "some metrics failed"; -} - -int test__pmu_events_subtest_get_nr(void) -{ - return (int)ARRAY_SIZE(pmu_events_testcase_table); -} - -int test__pmu_events(struct test *test __maybe_unused, int subtest) -{ - if (subtest < 0 || - subtest >= (int)ARRAY_SIZE(pmu_events_testcase_table)) - return TEST_FAIL; - return pmu_events_testcase_table[subtest].func(); -} +struct test_suite suite__pmu_events = { + .desc = "PMU events", + .test_cases = pmu_events_tests, +}; diff --git a/tools/perf/tests/pmu.c b/tools/perf/tests/pmu.c index 714e6830a7..8507bd615e 100644 --- a/tools/perf/tests/pmu.c +++ b/tools/perf/tests/pmu.c @@ -137,7 +137,7 @@ static struct list_head *test_terms_list(void) return &terms; } -int test__pmu(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__pmu(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { char *format = test_format_dir_get(); LIST_HEAD(formats); @@ -177,3 +177,5 @@ int test__pmu(struct test *test __maybe_unused, int subtest __maybe_unused) test_format_dir_put(format); return ret; } + +DEFINE_SUITE("Parse perf pmu format", pmu); diff --git a/tools/perf/tests/python-use.c b/tools/perf/tests/python-use.c index 98c6d474aa..6b990ee385 100644 --- a/tools/perf/tests/python-use.c +++ b/tools/perf/tests/python-use.c @@ -9,7 +9,7 @@ #include "tests.h" #include "util/debug.h" -int test__python_use(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__python_use(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { char *cmd; int ret; @@ -23,3 +23,5 @@ int test__python_use(struct test *test __maybe_unused, int subtest __maybe_unuse free(cmd); return ret; } + +DEFINE_SUITE("'import perf' in python", python_use); diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c index 8fd8a4ef97..07f2411b0a 100644 --- a/tools/perf/tests/sample-parsing.c +++ b/tools/perf/tests/sample-parsing.c @@ -13,6 +13,7 @@ #include "evsel.h" #include "debug.h" #include "util/synthetic-events.h" +#include "util/trace-event.h" #include "tests.h" @@ -30,9 +31,18 @@ } \ } while (0) +/* + * Hardcode the expected values for branch_entry flags. + * These are based on the input value (213) specified + * in branch_stack variable. + */ +#define BS_EXPECTED_BE 0xa000d00000000000 +#define BS_EXPECTED_LE 0xd5000000 +#define FLAG(s) s->branch_stack->entries[i].flags + static bool samples_same(const struct perf_sample *s1, const struct perf_sample *s2, - u64 type, u64 read_format) + u64 type, u64 read_format, bool needs_swap) { size_t i; @@ -100,8 +110,14 @@ static bool samples_same(const struct perf_sample *s1, if (type & PERF_SAMPLE_BRANCH_STACK) { COMP(branch_stack->nr); COMP(branch_stack->hw_idx); - for (i = 0; i < s1->branch_stack->nr; i++) - MCOMP(branch_stack->entries[i]); + for (i = 0; i < s1->branch_stack->nr; i++) { + if (needs_swap) + return ((tep_is_bigendian()) ? + (FLAG(s2).value == BS_EXPECTED_BE) : + (FLAG(s2).value == BS_EXPECTED_LE)); + else + MCOMP(branch_stack->entries[i]); + } } if (type & PERF_SAMPLE_REGS_USER) { @@ -248,7 +264,7 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format) }, }; struct sample_read_value values[] = {{1, 5}, {9, 3}, {2, 7}, {6, 4},}; - struct perf_sample sample_out; + struct perf_sample sample_out, sample_out_endian; size_t i, sz, bufsz; int err, ret = -1; @@ -313,12 +329,29 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format) goto out_free; } - if (!samples_same(&sample, &sample_out, sample_type, read_format)) { + if (!samples_same(&sample, &sample_out, sample_type, read_format, evsel.needs_swap)) { pr_debug("parsing failed for sample_type %#"PRIx64"\n", sample_type); goto out_free; } + if (sample_type == PERF_SAMPLE_BRANCH_STACK) { + evsel.needs_swap = true; + evsel.sample_size = __evsel__sample_size(sample_type); + err = evsel__parse_sample(&evsel, event, &sample_out_endian); + if (err) { + pr_debug("%s failed for sample_type %#"PRIx64", error %d\n", + "evsel__parse_sample", sample_type, err); + goto out_free; + } + + if (!samples_same(&sample, &sample_out_endian, sample_type, read_format, evsel.needs_swap)) { + pr_debug("parsing failed for sample_type %#"PRIx64"\n", + sample_type); + goto out_free; + } + } + ret = 0; out_free: free(event); @@ -335,7 +368,7 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format) * checks sample format bits separately and together. If the test passes %0 is * returned, otherwise %-1 is returned. */ -int test__sample_parsing(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__sample_parsing(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { const u64 rf[] = {4, 5, 6, 7, 12, 13, 14, 15}; u64 sample_type; @@ -393,3 +426,5 @@ int test__sample_parsing(struct test *test __maybe_unused, int subtest __maybe_u return 0; } + +DEFINE_SUITE("Sample parsing", sample_parsing); diff --git a/tools/perf/tests/sdt.c b/tools/perf/tests/sdt.c index ed76c693f6..9197128992 100644 --- a/tools/perf/tests/sdt.c +++ b/tools/perf/tests/sdt.c @@ -76,7 +76,7 @@ static int search_cached_probe(const char *target, return ret; } -int test__sdt_event(struct test *test __maybe_unused, int subtests __maybe_unused) +static int test__sdt_event(struct test_suite *test __maybe_unused, int subtests __maybe_unused) { int ret = TEST_FAIL; char __tempdir[] = "./test-buildid-XXXXXX"; @@ -114,9 +114,11 @@ int test__sdt_event(struct test *test __maybe_unused, int subtests __maybe_unuse return ret; } #else -int test__sdt_event(struct test *test __maybe_unused, int subtests __maybe_unused) +static int test__sdt_event(struct test_suite *test __maybe_unused, int subtests __maybe_unused) { pr_debug("Skip SDT event test because SDT support is not compiled\n"); return TEST_SKIP; } #endif + +DEFINE_SUITE("Probe SDT events", sdt_event); diff --git a/tools/perf/tests/shell/stat_bpf_counters.sh b/tools/perf/tests/shell/stat_bpf_counters.sh index 2aed20dc22..13473aeba4 100644 --- a/tools/perf/tests/shell/stat_bpf_counters.sh +++ b/tools/perf/tests/shell/stat_bpf_counters.sh @@ -23,7 +23,7 @@ compare_number() # skip if --bpf-counters is not supported if ! perf stat --bpf-counters true > /dev/null 2>&1; then - if [ "$1" == "-v" ]; then + if [ "$1" = "-v" ]; then echo "Skipping: --bpf-counters not supported" perf --no-pager stat --bpf-counters true || true fi diff --git a/tools/perf/tests/shell/test_arm_coresight.sh b/tools/perf/tests/shell/test_arm_coresight.sh index c9eef0bba6..6de53b7ef5 100644 --- a/tools/perf/tests/shell/test_arm_coresight.sh +++ b/tools/perf/tests/shell/test_arm_coresight.sh @@ -9,8 +9,6 @@ # SPDX-License-Identifier: GPL-2.0 # Leo Yan , 2020 -perfdata=$(mktemp /tmp/__perf_test.perf.data.XXXXX) -file=$(mktemp /tmp/temporary_file.XXXXX) glb_err=0 skip_if_no_cs_etm_event() { @@ -22,13 +20,20 @@ skip_if_no_cs_etm_event() { skip_if_no_cs_etm_event || exit 2 +perfdata=$(mktemp /tmp/__perf_test.perf.data.XXXXX) +file=$(mktemp /tmp/temporary_file.XXXXX) + cleanup_files() { rm -f ${perfdata} rm -f ${file} + rm -f "${perfdata}.old" + trap - exit term int + kill -2 $$ + exit $glb_err } -trap cleanup_files exit +trap cleanup_files exit term int record_touch_file() { echo "Recording trace (only user mode) with path: CPU$2 => $1" diff --git a/tools/perf/tests/stat.c b/tools/perf/tests/stat.c index c1911501c3..500974040f 100644 --- a/tools/perf/tests/stat.c +++ b/tools/perf/tests/stat.c @@ -47,7 +47,8 @@ static int process_stat_config_event(struct perf_tool *tool __maybe_unused, return 0; } -int test__synthesize_stat_config(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__synthesize_stat_config(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { struct perf_stat_config stat_config = { .aggr_mode = AGGR_CORE, @@ -77,7 +78,7 @@ static int process_stat_event(struct perf_tool *tool __maybe_unused, return 0; } -int test__synthesize_stat(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__synthesize_stat(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct perf_counts_values count; @@ -86,7 +87,8 @@ int test__synthesize_stat(struct test *test __maybe_unused, int subtest __maybe_ 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; } @@ -103,7 +105,7 @@ static int process_stat_round_event(struct perf_tool *tool __maybe_unused, return 0; } -int test__synthesize_stat_round(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__synthesize_stat_round(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { TEST_ASSERT_VAL("failed to synthesize stat_config", !perf_event__synthesize_stat_round(NULL, 0xdeadbeef, PERF_STAT_ROUND_TYPE__INTERVAL, @@ -111,3 +113,7 @@ int test__synthesize_stat_round(struct test *test __maybe_unused, int subtest __ return 0; } + +DEFINE_SUITE("Synthesize stat config", synthesize_stat_config); +DEFINE_SUITE("Synthesize stat", synthesize_stat); +DEFINE_SUITE("Synthesize stat round", synthesize_stat_round); diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c index 74988846be..9cd6fec375 100644 --- a/tools/perf/tests/sw-clock.c +++ b/tools/perf/tests/sw-clock.c @@ -133,7 +133,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id) return err; } -int test__sw_clock_freq(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__sw_clock_freq(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { int ret; @@ -143,3 +143,5 @@ int test__sw_clock_freq(struct test *test __maybe_unused, int subtest __maybe_un return ret; } + +DEFINE_SUITE("Software clock events period values", sw_clock_freq); diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c index 62c0ec21aa..0c0c2328bf 100644 --- a/tools/perf/tests/switch-tracking.c +++ b/tools/perf/tests/switch-tracking.c @@ -321,7 +321,7 @@ static int process_events(struct evlist *evlist, * evsel->core.system_wide and evsel->tracking flags (respectively) with other events * sometimes enabled or disabled. */ -int test__switch_tracking(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__switch_tracking(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { const char *sched_switch = "sched:sched_switch"; struct switch_tracking switch_tracking = { .tids = NULL, }; @@ -588,3 +588,5 @@ int test__switch_tracking(struct test *test __maybe_unused, int subtest __maybe_ err = -1; goto out; } + +DEFINE_SUITE("Track with sched_switch", switch_tracking); diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c index 4c2969db59..25f075fa91 100644 --- a/tools/perf/tests/task-exit.c +++ b/tools/perf/tests/task-exit.c @@ -39,7 +39,7 @@ static void workload_exec_failed_signal(int signo __maybe_unused, * if the number of exit event reported by the kernel is 1 or not * in order to check the kernel returns correct number of event. */ -int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__task_exit(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { int err = -1; union perf_event *event; @@ -151,3 +151,5 @@ int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused evlist__delete(evlist); return err; } + +DEFINE_SUITE("Number of exit events of a simple workload", task_exit); diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h index fe1306f584..5bbb8f6a48 100644 --- a/tools/perf/tests/tests.h +++ b/tools/perf/tests/tests.h @@ -27,112 +27,147 @@ enum { TEST_SKIP = -2, }; -struct test { +struct test_suite; + +typedef int (*test_fnptr)(struct test_suite *, int); + +struct test_case { + const char *name; const char *desc; - int (*func)(struct test *test, int subtest); - struct { - bool skip_if_fail; - int (*get_nr)(void); - const char *(*get_desc)(int subtest); - const char *(*skip_reason)(int subtest); - } subtest; - bool (*is_supported)(void); + const char *skip_reason; + test_fnptr run_case; +}; + +struct test_suite { + const char *desc; + struct test_case *test_cases; void *priv; }; -/* Tests */ -int test__vmlinux_matches_kallsyms(struct test *test, int subtest); -int test__openat_syscall_event(struct test *test, int subtest); -int test__openat_syscall_event_on_all_cpus(struct test *test, int subtest); -int test__basic_mmap(struct test *test, int subtest); -int test__PERF_RECORD(struct test *test, int subtest); -int test__perf_evsel__roundtrip_name_test(struct test *test, int subtest); -int test__perf_evsel__tp_sched_test(struct test *test, int subtest); -int test__syscall_openat_tp_fields(struct test *test, int subtest); -int test__pmu(struct test *test, int subtest); -int test__pmu_events(struct test *test, int subtest); -const char *test__pmu_events_subtest_get_desc(int subtest); -const char *test__pmu_events_subtest_skip_reason(int subtest); -int test__pmu_events_subtest_get_nr(void); -int test__attr(struct test *test, int subtest); -int test__dso_data(struct test *test, int subtest); -int test__dso_data_cache(struct test *test, int subtest); -int test__dso_data_reopen(struct test *test, int subtest); -int test__parse_events(struct test *test, int subtest); -int test__hists_link(struct test *test, int subtest); -int test__python_use(struct test *test, int subtest); -int test__bp_signal(struct test *test, int subtest); -int test__bp_signal_overflow(struct test *test, int subtest); -int test__bp_accounting(struct test *test, int subtest); -int test__wp(struct test *test, int subtest); -const char *test__wp_subtest_get_desc(int subtest); -const char *test__wp_subtest_skip_reason(int subtest); -int test__wp_subtest_get_nr(void); -int test__task_exit(struct test *test, int subtest); -int test__mem(struct test *test, int subtest); -int test__sw_clock_freq(struct test *test, int subtest); -int test__code_reading(struct test *test, int subtest); -int test__sample_parsing(struct test *test, int subtest); -int test__keep_tracking(struct test *test, int subtest); -int test__parse_no_sample_id_all(struct test *test, int subtest); -int test__dwarf_unwind(struct test *test, int subtest); -int test__expr(struct test *test, int subtest); -int test__hists_filter(struct test *test, int subtest); -int test__mmap_thread_lookup(struct test *test, int subtest); -int test__thread_maps_share(struct test *test, int subtest); -int test__hists_output(struct test *test, int subtest); -int test__hists_cumulate(struct test *test, int subtest); -int test__switch_tracking(struct test *test, int subtest); -int test__fdarray__filter(struct test *test, int subtest); -int test__fdarray__add(struct test *test, int subtest); -int test__kmod_path__parse(struct test *test, int subtest); -int test__thread_map(struct test *test, int subtest); -int test__llvm(struct test *test, int subtest); -const char *test__llvm_subtest_get_desc(int subtest); -int test__llvm_subtest_get_nr(void); -int test__bpf(struct test *test, int subtest); -const char *test__bpf_subtest_get_desc(int subtest); -int test__bpf_subtest_get_nr(void); -int test__session_topology(struct test *test, int subtest); -int test__thread_map_synthesize(struct test *test, int subtest); -int test__thread_map_remove(struct test *test, int subtest); -int test__cpu_map_synthesize(struct test *test, int subtest); -int test__synthesize_stat_config(struct test *test, int subtest); -int test__synthesize_stat(struct test *test, int subtest); -int test__synthesize_stat_round(struct test *test, int subtest); -int test__event_update(struct test *test, int subtest); -int test__event_times(struct test *test, int subtest); -int test__backward_ring_buffer(struct test *test, int subtest); -int test__cpu_map_print(struct test *test, int subtest); -int test__cpu_map_merge(struct test *test, int subtest); -int test__sdt_event(struct test *test, int subtest); -int test__is_printable_array(struct test *test, int subtest); -int test__bitmap_print(struct test *test, int subtest); -int test__perf_hooks(struct test *test, int subtest); -int test__clang(struct test *test, int subtest); -const char *test__clang_subtest_get_desc(int subtest); -int test__clang_subtest_get_nr(void); -int test__unit_number__scnprint(struct test *test, int subtest); -int test__mem2node(struct test *t, int subtest); -int test__maps__merge_in(struct test *t, int subtest); -int test__time_utils(struct test *t, int subtest); -int test__jit_write_elf(struct test *test, int subtest); -int test__api_io(struct test *test, int subtest); -int test__demangle_java(struct test *test, int subtest); -int test__demangle_ocaml(struct test *test, int subtest); -int test__pfm(struct test *test, int subtest); -const char *test__pfm_subtest_get_desc(int subtest); -int test__pfm_subtest_get_nr(void); -int test__parse_metric(struct test *test, int subtest); -int test__pe_file_parsing(struct test *test, int subtest); -int test__expand_cgroup_events(struct test *test, int subtest); -int test__perf_time_to_tsc(struct test *test, int subtest); -int test__dlfilter(struct test *test, int subtest); +#define DECLARE_SUITE(name) \ + extern struct test_suite suite__##name; -bool test__bp_signal_is_supported(void); -bool test__bp_account_is_supported(void); -bool test__wp_is_supported(void); -bool test__tsc_is_supported(void); +#define TEST_CASE(description, _name) \ + { \ + .name = #_name, \ + .desc = description, \ + .run_case = test__##_name, \ + } + +#define TEST_CASE_REASON(description, _name, _reason) \ + { \ + .name = #_name, \ + .desc = description, \ + .run_case = test__##_name, \ + .skip_reason = _reason, \ + } + +#define DEFINE_SUITE(description, _name) \ + struct test_case tests__##_name[] = { \ + TEST_CASE(description, _name), \ + { .name = NULL, } \ + }; \ + struct test_suite suite__##_name = { \ + .desc = description, \ + .test_cases = tests__##_name, \ + } + +/* Tests */ +DECLARE_SUITE(vmlinux_matches_kallsyms); +DECLARE_SUITE(openat_syscall_event); +DECLARE_SUITE(openat_syscall_event_on_all_cpus); +DECLARE_SUITE(basic_mmap); +DECLARE_SUITE(PERF_RECORD); +DECLARE_SUITE(perf_evsel__roundtrip_name_test); +DECLARE_SUITE(perf_evsel__tp_sched_test); +DECLARE_SUITE(syscall_openat_tp_fields); +DECLARE_SUITE(pmu); +DECLARE_SUITE(pmu_events); +DECLARE_SUITE(attr); +DECLARE_SUITE(dso_data); +DECLARE_SUITE(dso_data_cache); +DECLARE_SUITE(dso_data_reopen); +DECLARE_SUITE(parse_events); +DECLARE_SUITE(hists_link); +DECLARE_SUITE(python_use); +DECLARE_SUITE(bp_signal); +DECLARE_SUITE(bp_signal_overflow); +DECLARE_SUITE(bp_accounting); +DECLARE_SUITE(wp); +DECLARE_SUITE(task_exit); +DECLARE_SUITE(mem); +DECLARE_SUITE(sw_clock_freq); +DECLARE_SUITE(code_reading); +DECLARE_SUITE(sample_parsing); +DECLARE_SUITE(keep_tracking); +DECLARE_SUITE(parse_no_sample_id_all); +DECLARE_SUITE(dwarf_unwind); +DECLARE_SUITE(expr); +DECLARE_SUITE(hists_filter); +DECLARE_SUITE(mmap_thread_lookup); +DECLARE_SUITE(thread_maps_share); +DECLARE_SUITE(hists_output); +DECLARE_SUITE(hists_cumulate); +DECLARE_SUITE(switch_tracking); +DECLARE_SUITE(fdarray__filter); +DECLARE_SUITE(fdarray__add); +DECLARE_SUITE(kmod_path__parse); +DECLARE_SUITE(thread_map); +DECLARE_SUITE(llvm); +DECLARE_SUITE(bpf); +DECLARE_SUITE(session_topology); +DECLARE_SUITE(thread_map_synthesize); +DECLARE_SUITE(thread_map_remove); +DECLARE_SUITE(cpu_map_synthesize); +DECLARE_SUITE(synthesize_stat_config); +DECLARE_SUITE(synthesize_stat); +DECLARE_SUITE(synthesize_stat_round); +DECLARE_SUITE(event_update); +DECLARE_SUITE(event_times); +DECLARE_SUITE(backward_ring_buffer); +DECLARE_SUITE(cpu_map_print); +DECLARE_SUITE(cpu_map_merge); +DECLARE_SUITE(sdt_event); +DECLARE_SUITE(is_printable_array); +DECLARE_SUITE(bitmap_print); +DECLARE_SUITE(perf_hooks); +DECLARE_SUITE(clang); +DECLARE_SUITE(unit_number__scnprint); +DECLARE_SUITE(mem2node); +DECLARE_SUITE(maps__merge_in); +DECLARE_SUITE(time_utils); +DECLARE_SUITE(jit_write_elf); +DECLARE_SUITE(api_io); +DECLARE_SUITE(demangle_java); +DECLARE_SUITE(demangle_ocaml); +DECLARE_SUITE(pfm); +DECLARE_SUITE(parse_metric); +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 + * perf_event interface. + * + * ARM requires explicit rounding down of the instruction pointer in Thumb mode, + * and then requires the single-step to be handled explicitly in the overflow + * handler to avoid stepping into the SIGIO handler and getting stuck on the + * breakpointed instruction. + * + * Since arm64 has the same issue with arm for the single-step handling, this + * case also gets stuck on the breakpointed instruction. + * + * Just disable the test for these architectures until these issues are + * resolved. + */ +#if defined(__powerpc__) || defined(__s390x__) || defined(__arm__) || defined(__aarch64__) +#define BP_SIGNAL_IS_SUPPORTED 0 +#else +#define BP_SIGNAL_IS_SUPPORTED 1 +#endif #ifdef HAVE_DWARF_UNWIND_SUPPORT struct thread; @@ -142,7 +177,7 @@ int test__arch_unwind_sample(struct perf_sample *sample, #endif #if defined(__arm__) -int test__vectors_page(struct test *test, int subtest); +DECLARE_SUITE(vectors_page); #endif #endif /* TESTS_H */ diff --git a/tools/perf/tests/thread-map.c b/tools/perf/tests/thread-map.c index d1e208b4a5..e413c1387f 100644 --- a/tools/perf/tests/thread-map.c +++ b/tools/perf/tests/thread-map.c @@ -19,7 +19,7 @@ struct machine; #define NAME (const char *) "perf" #define NAMEUL (unsigned long) NAME -int test__thread_map(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__thread_map(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct perf_thread_map *map; @@ -86,7 +86,7 @@ static int process_event(struct perf_tool *tool __maybe_unused, return 0; } -int test__thread_map_synthesize(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__thread_map_synthesize(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct perf_thread_map *threads; @@ -106,7 +106,7 @@ int test__thread_map_synthesize(struct test *test __maybe_unused, int subtest __ return 0; } -int test__thread_map_remove(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__thread_map_remove(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct perf_thread_map *threads; char *str; @@ -145,3 +145,7 @@ int test__thread_map_remove(struct test *test __maybe_unused, int subtest __mayb perf_thread_map__put(threads); return 0; } + +DEFINE_SUITE("Thread map", thread_map); +DEFINE_SUITE("Synthesize thread map", thread_map_synthesize); +DEFINE_SUITE("Remove thread map", thread_map_remove); diff --git a/tools/perf/tests/thread-maps-share.c b/tools/perf/tests/thread-maps-share.c index 9371484973..84edd82c51 100644 --- a/tools/perf/tests/thread-maps-share.c +++ b/tools/perf/tests/thread-maps-share.c @@ -4,7 +4,7 @@ #include "thread.h" #include "debug.h" -int test__thread_maps_share(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__thread_maps_share(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct machines machines; struct machine *machine; @@ -96,3 +96,5 @@ int test__thread_maps_share(struct test *test __maybe_unused, int subtest __mayb machines__exit(&machines); return 0; } + +DEFINE_SUITE("Share thread maps", thread_maps_share); diff --git a/tools/perf/tests/time-utils-test.c b/tools/perf/tests/time-utils-test.c index fe57ca3b6e..38df10373c 100644 --- a/tools/perf/tests/time-utils-test.c +++ b/tools/perf/tests/time-utils-test.c @@ -131,7 +131,7 @@ static bool test__perf_time__parse_for_ranges(struct test_data *d) return pass; } -int test__time_utils(struct test *t __maybe_unused, int subtest __maybe_unused) +static int test__time_utils(struct test_suite *t __maybe_unused, int subtest __maybe_unused) { bool pass = true; @@ -249,3 +249,5 @@ int test__time_utils(struct test *t __maybe_unused, int subtest __maybe_unused) return pass ? 0 : TEST_FAIL; } + +DEFINE_SUITE("time utils", time_utils); diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c index b9028e304d..ee1e3dcbc0 100644 --- a/tools/perf/tests/topology.c +++ b/tools/perf/tests/topology.c @@ -49,7 +49,9 @@ static int session_write_header(char *path) session->evlist = evlist__new(); TEST_ASSERT_VAL("can't get evlist", session->evlist); + parse_events_error__init(&err); parse_events(session->evlist, "cpu_core/cycles/", &err); + parse_events_error__exit(&err); } perf_header__set_feat(&session->header, HEADER_CPU_TOPOLOGY); @@ -110,62 +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); @@ -173,7 +201,7 @@ static int check_cpu_topology(char *path, struct perf_cpu_map *map) return 0; } -int test__session_topology(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__session_topology(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { char path[PATH_MAX]; struct perf_cpu_map *map; @@ -199,3 +227,5 @@ int test__session_topology(struct test *test __maybe_unused, int subtest __maybe unlink(path); return ret; } + +DEFINE_SUITE("Session topology", session_topology); diff --git a/tools/perf/tests/unit_number__scnprintf.c b/tools/perf/tests/unit_number__scnprintf.c index 3721757435..88bcada1c7 100644 --- a/tools/perf/tests/unit_number__scnprintf.c +++ b/tools/perf/tests/unit_number__scnprintf.c @@ -7,7 +7,7 @@ #include "units.h" #include "debug.h" -int test__unit_number__scnprint(struct test *t __maybe_unused, int subtest __maybe_unused) +static int test__unit_number__scnprint(struct test_suite *t __maybe_unused, int subtest __maybe_unused) { struct { u64 n; @@ -38,3 +38,5 @@ int test__unit_number__scnprint(struct test *t __maybe_unused, int subtest __may return TEST_OK; } + +DEFINE_SUITE("unit_number__scnprintf", unit_number__scnprint); diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c index 193b7c91b4..e80df13c04 100644 --- a/tools/perf/tests/vmlinux-kallsyms.c +++ b/tools/perf/tests/vmlinux-kallsyms.c @@ -3,6 +3,7 @@ #include #include #include +#include #include #include "dso.h" #include "map.h" @@ -14,7 +15,104 @@ #define UM(x) kallsyms_map->unmap_ip(kallsyms_map, (x)) -int test__vmlinux_matches_kallsyms(struct test *test __maybe_unused, int subtest __maybe_unused) +static bool is_ignored_symbol(const char *name, char type) +{ + /* Symbol names that exactly match to the following are ignored.*/ + static const char * const ignored_symbols[] = { + /* + * Symbols which vary between passes. Passes 1 and 2 must have + * identical symbol lists. The kallsyms_* symbols below are + * only added after pass 1, they would be included in pass 2 + * when --all-symbols is specified so exclude them to get a + * stable symbol list. + */ + "kallsyms_addresses", + "kallsyms_offsets", + "kallsyms_relative_base", + "kallsyms_num_syms", + "kallsyms_names", + "kallsyms_markers", + "kallsyms_token_table", + "kallsyms_token_index", + /* Exclude linker generated symbols which vary between passes */ + "_SDA_BASE_", /* ppc */ + "_SDA2_BASE_", /* ppc */ + NULL + }; + + /* Symbol names that begin with the following are ignored.*/ + static const char * const ignored_prefixes[] = { + "$", /* local symbols for ARM, MIPS, etc. */ + ".LASANPC", /* s390 kasan local symbols */ + "__crc_", /* modversions */ + "__efistub_", /* arm64 EFI stub namespace */ + "__kvm_nvhe_", /* arm64 non-VHE KVM namespace */ + "__AArch64ADRPThunk_", /* arm64 lld */ + "__ARMV5PILongThunk_", /* arm lld */ + "__ARMV7PILongThunk_", + "__ThumbV7PILongThunk_", + "__LA25Thunk_", /* mips lld */ + "__microLA25Thunk_", + NULL + }; + + /* Symbol names that end with the following are ignored.*/ + static const char * const ignored_suffixes[] = { + "_from_arm", /* arm */ + "_from_thumb", /* arm */ + "_veneer", /* arm */ + NULL + }; + + /* Symbol names that contain the following are ignored.*/ + static const char * const ignored_matches[] = { + ".long_branch.", /* ppc stub */ + ".plt_branch.", /* ppc stub */ + NULL + }; + + const char * const *p; + + for (p = ignored_symbols; *p; p++) + if (!strcmp(name, *p)) + return true; + + for (p = ignored_prefixes; *p; p++) + if (!strncmp(name, *p, strlen(*p))) + return true; + + for (p = ignored_suffixes; *p; p++) { + int l = strlen(name) - strlen(*p); + + if (l >= 0 && !strcmp(name + l, *p)) + return true; + } + + for (p = ignored_matches; *p; p++) { + if (strstr(name, *p)) + return true; + } + + if (type == 'U' || type == 'u') + return true; + /* exclude debugging symbols */ + if (type == 'N' || type == 'n') + return true; + + if (toupper(type) == 'A') { + /* Keep these useful absolute symbols */ + if (strcmp(name, "__kernel_syscall_via_break") && + strcmp(name, "__kernel_syscall_via_epc") && + strcmp(name, "__kernel_sigtramp") && + strcmp(name, "__gp")) + return true; + } + + return false; +} + +static int test__vmlinux_matches_kallsyms(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { int err = -1; struct rb_node *nd; @@ -169,6 +267,11 @@ int test__vmlinux_matches_kallsyms(struct test *test __maybe_unused, int subtest * such as __indirect_thunk_end. */ continue; + } else if (is_ignored_symbol(sym->name, sym->type)) { + /* + * Ignore hidden symbols, see scripts/kallsyms.c for the details + */ + continue; } else { pr_debug("ERR : %#" PRIx64 ": %s not on kallsyms\n", mem_start, sym->name); @@ -250,3 +353,5 @@ int test__vmlinux_matches_kallsyms(struct test *test __maybe_unused, int subtest machine__exit(&vmlinux); return err; } + +DEFINE_SUITE("vmlinux symtab matches kallsyms", vmlinux_matches_kallsyms); diff --git a/tools/perf/tests/wp.c b/tools/perf/tests/wp.c index 9387fa76fa..9d4c45184e 100644 --- a/tools/perf/tests/wp.c +++ b/tools/perf/tests/wp.c @@ -21,6 +21,7 @@ do { \ volatile u64 data1; volatile u8 data2[3]; +#ifndef __s390x__ static int wp_read(int fd, long long *count, int size) { int ret = read(fd, count, size); @@ -61,9 +62,14 @@ static int __event(int wp_type, void *wp_addr, unsigned long wp_len) return fd; } +#endif -static int wp_ro_test(void) +static int test__wp_ro(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { +#if defined(__s390x__) || defined(__x86_64__) || defined(__i386__) + return TEST_SKIP; +#else int fd; unsigned long tmp, tmp1 = rand(); @@ -79,10 +85,15 @@ static int wp_ro_test(void) close(fd); return 0; +#endif } -static int wp_wo_test(void) +static int test__wp_wo(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { +#if defined(__s390x__) + return TEST_SKIP; +#else int fd; unsigned long tmp, tmp1 = rand(); @@ -98,10 +109,15 @@ static int wp_wo_test(void) close(fd); return 0; +#endif } -static int wp_rw_test(void) +static int test__wp_rw(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { +#if defined(__s390x__) + return TEST_SKIP; +#else int fd; unsigned long tmp, tmp1 = rand(); @@ -118,10 +134,15 @@ static int wp_rw_test(void) close(fd); return 0; +#endif } -static int wp_modify_test(void) +static int test__wp_modify(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { +#if defined(__s390x__) + return TEST_SKIP; +#else int fd, ret; unsigned long tmp = rand(); struct perf_event_attr new_attr; @@ -163,93 +184,18 @@ static int wp_modify_test(void) close(fd); return 0; -} - -static bool wp_ro_supported(void) -{ -#if defined (__x86_64__) || defined (__i386__) - return false; -#else - return true; #endif } -static const char *wp_ro_skip_msg(void) -{ -#if defined (__x86_64__) || defined (__i386__) - return "missing hardware support"; -#else - return NULL; -#endif -} - -static struct { - const char *desc; - int (*target_func)(void); - bool (*is_supported)(void); - const char *(*skip_msg)(void); -} wp_testcase_table[] = { - { - .desc = "Read Only Watchpoint", - .target_func = &wp_ro_test, - .is_supported = &wp_ro_supported, - .skip_msg = &wp_ro_skip_msg, - }, - { - .desc = "Write Only Watchpoint", - .target_func = &wp_wo_test, - }, - { - .desc = "Read / Write Watchpoint", - .target_func = &wp_rw_test, - }, - { - .desc = "Modify Watchpoint", - .target_func = &wp_modify_test, - }, +static struct test_case wp_tests[] = { + TEST_CASE_REASON("Read Only Watchpoint", wp_ro, "missing hardware support"), + TEST_CASE_REASON("Write Only Watchpoint", wp_wo, "missing hardware support"), + TEST_CASE_REASON("Read / Write Watchpoint", wp_rw, "missing hardware support"), + TEST_CASE_REASON("Modify Watchpoint", wp_modify, "missing hardware support"), + { .name = NULL, } }; -int test__wp_subtest_get_nr(void) -{ - return (int)ARRAY_SIZE(wp_testcase_table); -} - -const char *test__wp_subtest_get_desc(int i) -{ - if (i < 0 || i >= (int)ARRAY_SIZE(wp_testcase_table)) - return NULL; - return wp_testcase_table[i].desc; -} - -const char *test__wp_subtest_skip_reason(int i) -{ - if (i < 0 || i >= (int)ARRAY_SIZE(wp_testcase_table)) - return NULL; - if (!wp_testcase_table[i].skip_msg) - return NULL; - return wp_testcase_table[i].skip_msg(); -} - -int test__wp(struct test *test __maybe_unused, int i) -{ - if (i < 0 || i >= (int)ARRAY_SIZE(wp_testcase_table)) - return TEST_FAIL; - - if (wp_testcase_table[i].is_supported && - !wp_testcase_table[i].is_supported()) - return TEST_SKIP; - - return !wp_testcase_table[i].target_func() ? TEST_OK : TEST_FAIL; -} - -/* The s390 so far does not have support for - * instruction breakpoint using the perf_event_open() system call. - */ -bool test__wp_is_supported(void) -{ -#if defined(__s390x__) - return false; -#else - return true; -#endif -} +struct test_suite suite__wp = { + .desc = "Watchpoint", + .test_cases = wp_tests, +}; diff --git a/tools/perf/trace/beauty/beauty.h b/tools/perf/trace/beauty/beauty.h index d6dfe68a76..f527a46ab4 100644 --- a/tools/perf/trace/beauty/beauty.h +++ b/tools/perf/trace/beauty/beauty.h @@ -62,6 +62,8 @@ size_t pid__scnprintf_fd(struct trace *trace, pid_t pid, int fd, char *bf, size_ extern struct strarray strarray__socket_families; +extern struct strarray strarray__socket_level; + /** * augmented_arg: extra payload for syscall pointer arguments @@ -230,6 +232,9 @@ size_t syscall_arg__scnprintf_sockaddr(char *bf, size_t size, struct syscall_arg size_t syscall_arg__scnprintf_socket_protocol(char *bf, size_t size, struct syscall_arg *arg); #define SCA_SK_PROTO syscall_arg__scnprintf_socket_protocol +size_t syscall_arg__scnprintf_socket_level(char *bf, size_t size, struct syscall_arg *arg); +#define SCA_SK_LEVEL syscall_arg__scnprintf_socket_level + size_t syscall_arg__scnprintf_statx_flags(char *bf, size_t size, struct syscall_arg *arg); #define SCA_STATX_FLAGS syscall_arg__scnprintf_statx_flags diff --git a/tools/perf/trace/beauty/include/linux/socket.h b/tools/perf/trace/beauty/include/linux/socket.h index 041d6032a3..8ef26d89ef 100644 --- a/tools/perf/trace/beauty/include/linux/socket.h +++ b/tools/perf/trace/beauty/include/linux/socket.h @@ -364,6 +364,8 @@ struct ucred { #define SOL_KCM 281 #define SOL_TLS 282 #define SOL_XDP 283 +#define SOL_MPTCP 284 +#define SOL_MCTP 285 /* IPX options */ #define IPX_TYPE 1 diff --git a/tools/perf/trace/beauty/prctl_option.sh b/tools/perf/trace/beauty/prctl_option.sh index 3109d7b05e..3d278785fe 100644 --- 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/trace/beauty/sockaddr.c b/tools/perf/trace/beauty/sockaddr.c index cd110634ab..2e0e867c0c 100644 --- a/tools/perf/trace/beauty/sockaddr.c +++ b/tools/perf/trace/beauty/sockaddr.c @@ -7,7 +7,7 @@ #include #include -#include "trace/beauty/generated/socket_arrays.c" +#include "trace/beauty/generated/sockaddr.c" DEFINE_STRARRAY(socket_families, "PF_"); static size_t af_inet__scnprintf(struct sockaddr *sa, char *bf, size_t size) diff --git a/tools/perf/trace/beauty/socket.c b/tools/perf/trace/beauty/socket.c index f23a3dda29..b0870c7b48 100644 --- a/tools/perf/trace/beauty/socket.c +++ b/tools/perf/trace/beauty/socket.c @@ -9,9 +9,10 @@ #include #include +#include "trace/beauty/generated/socket.c" + static size_t socket__scnprintf_ipproto(int protocol, char *bf, size_t size, bool show_prefix) { -#include "trace/beauty/generated/socket_ipproto_array.c" static DEFINE_STRARRAY(socket_ipproto, "IPPROTO_"); return strarray__scnprintf(&strarray__socket_ipproto, bf, size, "%d", show_prefix, protocol); @@ -26,3 +27,21 @@ size_t syscall_arg__scnprintf_socket_protocol(char *bf, size_t size, struct sysc return syscall_arg__scnprintf_int(bf, size, arg); } + +static size_t socket__scnprintf_level(int level, char *bf, size_t size, bool show_prefix) +{ +#if defined(__alpha__) || defined(__hppa__) || defined(__mips__) || defined(__sparc__) + const int sol_socket = 0xffff; +#else + const int sol_socket = 1; +#endif + if (level == sol_socket) + return scnprintf(bf, size, "%sSOCKET", show_prefix ? "SOL_" : ""); + + return strarray__scnprintf(&strarray__socket_level, bf, size, "%d", show_prefix, level); +} + +size_t syscall_arg__scnprintf_socket_level(char *bf, size_t size, struct syscall_arg *arg) +{ + return socket__scnprintf_level(arg->val, bf, size, arg->show_string_prefix); +} diff --git a/tools/perf/trace/beauty/socket.sh b/tools/perf/trace/beauty/socket.sh index 3820e5c822..76330acb27 100644 --- a/tools/perf/trace/beauty/socket.sh +++ b/tools/perf/trace/beauty/socket.sh @@ -1,24 +1,28 @@ #!/bin/sh # SPDX-License-Identifier: LGPL-2.1 -# This one uses a copy from the kernel sources headers that is in a -# place used just for these tools/perf/beauty/ usage, we shouldn't not -# put it in tools/include/linux otherwise they would be used in the -# normal compiler building process and would drag needless stuff from the -# kernel. +if [ $# -gt 0 ] ; then + uapi_header_dir=$1 + beauty_header_dir=$2 +else + uapi_header_dir=tools/include/uapi/linux/ + beauty_header_dir=tools/perf/trace/beauty/include/linux/ +fi -# When what these scripts need is already in tools/include/ then use it, -# otherwise grab and check the copy from the kernel sources just for these -# string table building scripts. +printf "static const char *socket_ipproto[] = {\n" +ipproto_regex='^[[:space:]]+IPPROTO_(\w+)[[:space:]]+=[[:space:]]+([[:digit:]]+),.*' -[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/perf/trace/beauty/include/linux/ +egrep $ipproto_regex ${uapi_header_dir}/in.h | \ + sed -r "s/$ipproto_regex/\2 \1/g" | \ + sort -n | xargs printf "\t[%s] = \"%s\",\n" +printf "};\n\n" -printf "static const char *socket_families[] = {\n" -# #define AF_LOCAL 1 /* POSIX name for AF_UNIX */ -regex='^#define[[:space:]]+AF_(\w+)[[:space:]]+([[:digit:]]+).*' +printf "static const char *socket_level[] = {\n" +socket_level_regex='^#define[[:space:]]+SOL_(\w+)[[:space:]]+([[:digit:]]+)([[:space:]]+\/.*)?' -egrep $regex ${header_dir}/socket.h | \ - sed -r "s/$regex/\2 \1/g" | \ - xargs printf "\t[%s] = \"%s\",\n" | \ - egrep -v "\"(UNIX|MAX)\"" -printf "};\n" +egrep $socket_level_regex ${beauty_header_dir}/socket.h | \ + sed -r "s/$socket_level_regex/\2 \1/g" | \ + sort -n | xargs printf "\t[%s] = \"%s\",\n" +printf "};\n\n" + +printf 'DEFINE_STRARRAY(socket_level, "SOL_");\n' diff --git a/tools/perf/ui/tui/setup.c b/tools/perf/ui/tui/setup.c index e9bfe856a5..b1be59b4e2 100644 --- a/tools/perf/ui/tui/setup.c +++ b/tools/perf/ui/tui/setup.c @@ -170,9 +170,11 @@ void ui__exit(bool wait_for_ok) "Press any key...", 0); SLtt_set_cursor_visibility(1); - SLsmg_refresh(); - SLsmg_reset_smg(); + if (!pthread_mutex_trylock(&ui__lock)) { + SLsmg_refresh(); + SLsmg_reset_smg(); + pthread_mutex_unlock(&ui__lock); + } SLang_reset_tty(); - perf_error__unregister(&perf_tui_eops); } diff --git a/tools/perf/util/Build b/tools/perf/util/Build index f2914d5bed..2a403cefca 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 @@ -138,11 +139,13 @@ perf-y += expr.o perf-y += branch.o perf-y += mem2node.o perf-y += clockid.o +perf-y += list_sort.o 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 @@ -201,6 +204,7 @@ endif perf-y += perf-hooks.o perf-$(CONFIG_LIBBPF) += bpf-event.o +perf-$(CONFIG_LIBBPF) += bpf-utils.o perf-$(CONFIG_CXX) += c++/ @@ -315,3 +319,7 @@ $(OUTPUT)util/hweight.o: ../lib/hweight.c FORCE $(OUTPUT)util/vsprintf.o: ../lib/vsprintf.c FORCE $(call rule_mkdir) $(call if_changed_dep,cc_o_c) + +$(OUTPUT)util/list_sort.o: ../lib/list_sort.c FORCE + $(call rule_mkdir) + $(call if_changed_dep,cc_o_c) diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 0bae061b2d..8190a124b9 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -28,6 +28,7 @@ #include "evsel.h" #include "evlist.h" #include "bpf-event.h" +#include "bpf-utils.h" #include "block-range.h" #include "string2.h" #include "util/event.h" @@ -151,6 +152,7 @@ static int arch__associate_ins_ops(struct arch* arch, const char *name, struct i #include "arch/mips/annotate/instructions.c" #include "arch/x86/annotate/instructions.c" #include "arch/powerpc/annotate/instructions.c" +#include "arch/riscv64/annotate/instructions.c" #include "arch/s390/annotate/instructions.c" #include "arch/sparc/annotate/instructions.c" @@ -183,7 +185,6 @@ static struct arch architectures[] = { .init = x86__annotate_init, .instructions = x86__instructions, .nr_instructions = ARRAY_SIZE(x86__instructions), - .ins_is_fused = x86__ins_is_fused, .objdump = { .comment_char = '#', }, @@ -192,6 +193,10 @@ static struct arch architectures[] = { .name = "powerpc", .init = powerpc__annotate_init, }, + { + .name = "riscv64", + .init = riscv64__annotate_init, + }, { .name = "s390", .init = s390__annotate_init, @@ -1250,6 +1255,17 @@ int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool r return ins__scnprintf(&dl->ins, bf, size, &dl->ops, max_ins_name); } +void annotation__init(struct annotation *notes) +{ + pthread_mutex_init(¬es->lock, NULL); +} + +void annotation__exit(struct annotation *notes) +{ + annotated_source__delete(notes->src); + pthread_mutex_destroy(¬es->lock); +} + static void annotation_line__add(struct annotation_line *al, struct list_head *head) { list_add_tail(&al->node, head); @@ -1700,12 +1716,12 @@ static int symbol__disassemble_bpf(struct symbol *sym, { struct annotation *notes = symbol__annotation(sym); struct annotation_options *opts = args->options; - struct bpf_prog_info_linear *info_linear; struct bpf_prog_linfo *prog_linfo = NULL; struct bpf_prog_info_node *info_node; int len = sym->end - sym->start; disassembler_ftype disassemble; struct map *map = args->ms.map; + struct perf_bpil *info_linear; struct disassemble_info info; struct dso *dso = map->dso; int pc = 0, count, sub_id; @@ -2020,6 +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; @@ -3127,7 +3144,7 @@ int symbol__annotate2(struct map_symbol *ms, struct evsel *evsel, notes->nr_events = nr_pcnt; annotation__update_column_widths(notes); - sym->annotate2 = true; + sym->annotate2 = 1; return 0; diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index 3757416bcf..986f2bbe48 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -299,6 +299,9 @@ struct annotation { struct annotated_source *src; }; +void annotation__init(struct annotation *notes); +void annotation__exit(struct annotation *notes); + static inline int annotation__cycles_width(struct annotation *notes) { if (notes->have_cycles && notes->options->show_minmax_cycle) 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 32fe41835f..5e390a1a79 100644 --- a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c +++ b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c @@ -151,6 +151,7 @@ static int arm_spe_read_record(struct arm_spe_decoder *decoder) u64 payload, ip; memset(&decoder->record, 0x0, sizeof(decoder->record)); + decoder->record.context_id = (u64)-1; while (1) { err = arm_spe_get_next_packet(decoder); @@ -178,8 +179,11 @@ 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; break; case ARM_SPE_OP_TYPE: if (idx == SPE_OP_PKT_HDR_CLASS_LD_ST_ATOMIC) { 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 59bdb73096..69b31084d6 100644 --- a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h +++ b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h @@ -33,11 +33,13 @@ struct arm_spe_record { enum arm_spe_sample_type type; int err; u32 op; + u32 latency; u64 from_ip; u64 to_ip; u64 timestamp; u64 virt_addr; u64 phys_addr; + u64 context_id; }; struct arm_spe_insn; diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c b/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c index 2e5eff4f8f..2f311189c6 100644 --- a/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c +++ b/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c @@ -13,7 +13,7 @@ #include "arm-spe-pkt-decoder.h" -#if __BYTE_ORDER == __BIG_ENDIAN +#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ #define le16_to_cpu bswap_16 #define le32_to_cpu bswap_32 #define le64_to_cpu bswap_64 diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c index 7054f23150..d2b64e3f58 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; @@ -68,10 +70,12 @@ struct arm_spe { u64 branch_miss_id; u64 remote_access_id; u64 memory_id; + u64 instructions_id; u64 kernel_start; unsigned long num_events; + u8 use_ctx_pkt_for_pid; }; struct arm_spe_queue { @@ -89,6 +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, @@ -101,7 +106,7 @@ static void arm_spe_dump(struct arm_spe *spe __maybe_unused, const char *color = PERF_COLOR_BLUE; color_fprintf(stdout, color, - ". ... ARM SPE data: size %zu bytes\n", + ". ... ARM SPE data: size %#zx bytes\n", len); while (len) { @@ -201,6 +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; @@ -227,6 +233,44 @@ static inline u8 arm_spe_cpumode(struct arm_spe *spe, u64 ip) PERF_RECORD_MISC_USER; } +static void arm_spe_set_pid_tid_cpu(struct arm_spe *spe, + struct auxtrace_queue *queue) +{ + struct arm_spe_queue *speq = queue->priv; + pid_t tid; + + tid = machine__get_current_tid(spe->machine, speq->cpu); + if (tid != -1) { + speq->tid = tid; + thread__zput(speq->thread); + } else + speq->tid = queue->tid; + + if ((!speq->thread) && (speq->tid != -1)) { + speq->thread = machine__find_thread(spe->machine, -1, + speq->tid); + } + + if (speq->thread) { + speq->pid = speq->thread->pid_; + if (queue->cpu == -1) + speq->cpu = speq->thread->cpu; + } +} + +static int arm_spe_set_tid(struct arm_spe_queue *speq, pid_t tid) +{ + struct arm_spe *spe = speq->spe; + int err = machine__set_current_tid(spe->machine, speq->cpu, -1, tid); + + if (err) + return err; + + arm_spe_set_pid_tid_cpu(spe, &spe->queues.queue_array[speq->queue_nr]); + + return 0; +} + static void arm_spe_prep_sample(struct arm_spe *spe, struct arm_spe_queue *speq, union perf_event *event, @@ -291,6 +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); } @@ -308,6 +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); } @@ -441,6 +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; } @@ -473,6 +554,19 @@ static int arm_spe_run_decoder(struct arm_spe_queue *speq, u64 *timestamp) * can correlate samples between Arm SPE trace data and other * perf events with correct time ordering. */ + + /* + * Update pid/tid info. + */ + record = &speq->decoder->record; + if (!spe->timeless_decoding && record->context_id != (u64)-1) { + ret = arm_spe_set_tid(speq, record->context_id); + if (ret) + return ret; + + spe->use_ctx_pkt_for_pid = true; + } + ret = arm_spe_sample(speq); if (ret) return ret; @@ -599,31 +693,6 @@ static bool arm_spe__is_timeless_decoding(struct arm_spe *spe) return timeless_decoding; } -static void arm_spe_set_pid_tid_cpu(struct arm_spe *spe, - struct auxtrace_queue *queue) -{ - struct arm_spe_queue *speq = queue->priv; - pid_t tid; - - tid = machine__get_current_tid(spe->machine, speq->cpu); - if (tid != -1) { - speq->tid = tid; - thread__zput(speq->thread); - } else - speq->tid = queue->tid; - - if ((!speq->thread) && (speq->tid != -1)) { - speq->thread = machine__find_thread(spe->machine, -1, - speq->tid); - } - - if (speq->thread) { - speq->pid = speq->thread->pid_; - if (queue->cpu == -1) - speq->cpu = speq->thread->cpu; - } -} - static int arm_spe_process_queues(struct arm_spe *spe, u64 timestamp) { unsigned int queue_nr; @@ -654,7 +723,12 @@ static int arm_spe_process_queues(struct arm_spe *spe, u64 timestamp) ts = timestamp; } - arm_spe_set_pid_tid_cpu(spe, queue); + /* + * A previous context-switch event has set pid/tid in the machine's context, so + * here we need to update the pid/tid in the thread and SPE queue. + */ + if (!spe->use_ctx_pkt_for_pid) + arm_spe_set_pid_tid_cpu(spe, queue); ret = arm_spe_run_decoder(speq, &ts); if (ret < 0) { @@ -694,6 +768,25 @@ static int arm_spe_process_timeless_queues(struct arm_spe *spe, pid_t tid, return 0; } +static int arm_spe_context_switch(struct arm_spe *spe, union perf_event *event, + struct perf_sample *sample) +{ + pid_t pid, tid; + int cpu; + + if (!(event->header.misc & PERF_RECORD_MISC_SWITCH_OUT)) + return 0; + + pid = event->context_switch.next_prev_pid; + tid = event->context_switch.next_prev_tid; + cpu = sample->cpu; + + if (tid == -1) + pr_warning("context_switch event has no tid\n"); + + return machine__set_current_tid(spe->machine, cpu, pid, tid); +} + static int arm_spe_process_event(struct perf_session *session, union perf_event *event, struct perf_sample *sample, @@ -731,6 +824,13 @@ static int arm_spe_process_event(struct perf_session *session, } } else if (timestamp) { err = arm_spe_process_queues(spe, timestamp); + if (err) + return err; + + if (!spe->use_ctx_pkt_for_pid && + (event->header.type == PERF_RECORD_SWITCH_CPU_WIDE || + event->header.type == PERF_RECORD_SWITCH)) + err = arm_spe_context_switch(spe, event, sample); } return err; @@ -796,7 +896,15 @@ static int arm_spe_flush(struct perf_session *session __maybe_unused, return arm_spe_process_timeless_queues(spe, -1, MAX_TIMESTAMP - 1); - return arm_spe_process_queues(spe, MAX_TIMESTAMP); + ret = arm_spe_process_queues(spe, MAX_TIMESTAMP); + if (ret) + return ret; + + if (!spe->use_ctx_pkt_for_pid) + ui__warning("Arm SPE CONTEXT packets not found in the traces.\n" + "Matching of TIDs to SPE events could be inaccurate.\n"); + + return 0; } static void arm_spe_free_queue(void *priv) @@ -927,7 +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 @@ -1041,8 +1150,30 @@ 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/auxtrace.c b/tools/perf/util/auxtrace.c index 8d2865b9ad..825336304a 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, @@ -1564,6 +1564,9 @@ int itrace_do_parse_synth_opts(struct itrace_synth_opts *synth_opts, case 'q': synth_opts->quick += 1; break; + case 'A': + synth_opts->approx_ipc = true; + break; case 'Z': synth_opts->timeless_decoding = true; break; diff --git a/tools/perf/util/bpf-event.h b/tools/perf/util/bpf-event.h index 68f315c3df..144a8a24cc 100644 --- a/tools/perf/util/bpf-event.h +++ b/tools/perf/util/bpf-event.h @@ -19,7 +19,7 @@ struct evlist; struct target; struct bpf_prog_info_node { - struct bpf_prog_info_linear *info_linear; + struct perf_bpil *info_linear; struct rb_node rb_node; }; diff --git a/tools/perf/util/bpf_counter.c b/tools/perf/util/bpf_counter.c index ba0f208536..3ce8d03cb7 100644 --- a/tools/perf/util/bpf_counter.c +++ b/tools/perf/util/bpf_counter.c @@ -13,6 +13,7 @@ #include #include "bpf_counter.h" +#include "bpf-utils.h" #include "counts.h" #include "debug.h" #include "evsel.h" @@ -61,14 +62,13 @@ static int bpf_program_profiler__destroy(struct evsel *evsel) static char *bpf_target_prog_name(int tgt_fd) { - struct bpf_prog_info_linear *info_linear; struct bpf_func_info *func_info; + struct perf_bpil *info_linear; const struct btf_type *t; struct btf *btf = NULL; char *name = NULL; - info_linear = bpf_program__get_prog_info_linear( - tgt_fd, 1UL << BPF_PROG_INFO_FUNC_INFO); + info_linear = get_bpf_prog_info_linear(tgt_fd, 1UL << PERF_BPIL_FUNC_INFO); if (IS_ERR_OR_NULL(info_linear)) { pr_debug("failed to get info_linear for prog FD %d\n", tgt_fd); return NULL; @@ -127,9 +127,9 @@ static int bpf_program_profiler_load_one(struct evsel *evsel, u32 prog_id) skel->rodata->num_cpu = evsel__nr_cpus(evsel); - bpf_map__resize(skel->maps.events, evsel__nr_cpus(evsel)); - bpf_map__resize(skel->maps.fentry_readings, 1); - bpf_map__resize(skel->maps.accum_readings, 1); + bpf_map__set_max_entries(skel->maps.events, evsel__nr_cpus(evsel)); + bpf_map__set_max_entries(skel->maps.fentry_readings, 1); + bpf_map__set_max_entries(skel->maps.accum_readings, 1); prog_name = bpf_target_prog_name(prog_fd); if (!prog_name) { @@ -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; } @@ -307,6 +307,20 @@ static bool bperf_attr_map_compatible(int attr_map_fd) (map_info.value_size == sizeof(struct perf_event_attr_map_entry)); } +int __weak +bpf_map_create(enum bpf_map_type map_type, + const char *map_name __maybe_unused, + __u32 key_size, + __u32 value_size, + __u32 max_entries, + const struct bpf_map_create_opts *opts __maybe_unused) +{ +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wdeprecated-declarations" + return bpf_create_map(map_type, key_size, value_size, max_entries, 0); +#pragma GCC diagnostic pop +} + static int bperf_lock_attr_map(struct target *target) { char path[PATH_MAX]; @@ -320,10 +334,10 @@ static int bperf_lock_attr_map(struct target *target) } if (access(path, F_OK)) { - map_fd = bpf_create_map(BPF_MAP_TYPE_HASH, + map_fd = bpf_map_create(BPF_MAP_TYPE_HASH, NULL, sizeof(struct perf_event_attr), sizeof(struct perf_event_attr_map_entry), - ATTR_MAP_SIZE, 0); + ATTR_MAP_SIZE, NULL); if (map_fd < 0) return -1; @@ -399,7 +413,7 @@ static int bperf_reload_leader_program(struct evsel *evsel, int attr_map_fd, return -1; } - bpf_map__resize(skel->maps.events, libbpf_num_possible_cpus()); + bpf_map__set_max_entries(skel->maps.events, libbpf_num_possible_cpus()); err = bperf_leader_bpf__load(skel); if (err) { pr_err("Failed to load leader skeleton\n"); @@ -540,7 +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; @@ -566,12 +580,12 @@ static int bperf__load(struct evsel *evsel, struct target *target) 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); } /* @@ -584,7 +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; @@ -605,15 +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); @@ -623,16 +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; @@ -757,11 +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_skel/bperf_follower.bpf.c b/tools/perf/util/bpf_skel/bperf_follower.bpf.c index 6d2ea67b16..f193998530 100644 --- a/tools/perf/util/bpf_skel/bperf_follower.bpf.c +++ b/tools/perf/util/bpf_skel/bperf_follower.bpf.c @@ -1,7 +1,6 @@ // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) // Copyright (c) 2021 Facebook -#include -#include +#include "vmlinux.h" #include #include #include "bperf_u.h" diff --git a/tools/perf/util/bpf_skel/bperf_leader.bpf.c b/tools/perf/util/bpf_skel/bperf_leader.bpf.c index d82e1633a2..e2a2d4cd77 100644 --- a/tools/perf/util/bpf_skel/bperf_leader.bpf.c +++ b/tools/perf/util/bpf_skel/bperf_leader.bpf.c @@ -1,7 +1,6 @@ // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) // Copyright (c) 2021 Facebook -#include -#include +#include "vmlinux.h" #include #include diff --git a/tools/perf/util/bpf_skel/bpf_prog_profiler.bpf.c b/tools/perf/util/bpf_skel/bpf_prog_profiler.bpf.c index ab12b4c4ec..97037d3b3d 100644 --- a/tools/perf/util/bpf_skel/bpf_prog_profiler.bpf.c +++ b/tools/perf/util/bpf_skel/bpf_prog_profiler.bpf.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) // Copyright (c) 2020 Facebook -#include +#include "vmlinux.h" #include #include diff --git a/tools/perf/util/c++/clang-c.h b/tools/perf/util/c++/clang-c.h index 2df8a45bd0..d3731a876b 100644 --- a/tools/perf/util/c++/clang-c.h +++ b/tools/perf/util/c++/clang-c.h @@ -12,8 +12,9 @@ extern "C" { extern void perf_clang__init(void); extern void perf_clang__cleanup(void); -extern int test__clang_to_IR(void); -extern int test__clang_to_obj(void); +struct test_suite; +extern int test__clang_to_IR(struct test_suite *test, int subtest); +extern int test__clang_to_obj(struct test_suite *test, int subtest); extern int perf_clang__compile_bpf(const char *filename, void **p_obj_buf, @@ -26,9 +27,6 @@ extern int perf_clang__compile_bpf(const char *filename, static inline void perf_clang__init(void) { } static inline void perf_clang__cleanup(void) { } -static inline int test__clang_to_IR(void) { return -1; } -static inline int test__clang_to_obj(void) { return -1;} - static inline int perf_clang__compile_bpf(const char *filename __maybe_unused, void **p_obj_buf __maybe_unused, diff --git a/tools/perf/util/c++/clang-test.cpp b/tools/perf/util/c++/clang-test.cpp index 21b23605f7..a4683ca536 100644 --- a/tools/perf/util/c++/clang-test.cpp +++ b/tools/perf/util/c++/clang-test.cpp @@ -35,7 +35,8 @@ __test__clang_to_IR(void) } extern "C" { -int test__clang_to_IR(void) +int test__clang_to_IR(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { perf_clang_scope _scope; @@ -48,7 +49,8 @@ int test__clang_to_IR(void) return -1; } -int test__clang_to_obj(void) +int test__clang_to_obj(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { perf_clang_scope _scope; diff --git a/tools/perf/util/c++/clang.cpp b/tools/perf/util/c++/clang.cpp index c8885dfa36..df7b18fb6b 100644 --- a/tools/perf/util/c++/clang.cpp +++ b/tools/perf/util/c++/clang.cpp @@ -43,8 +43,6 @@ createCompilerInvocation(llvm::opt::ArgStringList CFlags, StringRef& Path, "-cc1", "-triple", "bpf-pc-linux", "-fsyntax-only", - "-ferror-limit", "19", - "-fmessage-length", "127", "-O2", "-nostdsysteminc", "-nobuiltininc", @@ -55,7 +53,11 @@ createCompilerInvocation(llvm::opt::ArgStringList CFlags, StringRef& Path, "-x", "c"}; CCArgs.append(CFlags.begin(), CFlags.end()); - CompilerInvocation *CI = tooling::newInvocation(&Diags, CCArgs); + CompilerInvocation *CI = tooling::newInvocation(&Diags, CCArgs +#if CLANG_VERSION_MAJOR >= 11 + ,/*BinaryName=*/nullptr +#endif + ); FrontendOptions& Opts = CI->getFrontendOpts(); Opts.Inputs.clear(); @@ -151,13 +153,16 @@ getBPFObjectFromModule(llvm::Module *Module) legacy::PassManager PM; bool NotAdded; -#if CLANG_VERSION_MAJOR < 7 - NotAdded = TargetMachine->addPassesToEmitFile(PM, ostream, - TargetMachine::CGFT_ObjectFile); -#else - NotAdded = TargetMachine->addPassesToEmitFile(PM, ostream, nullptr, - TargetMachine::CGFT_ObjectFile); + NotAdded = TargetMachine->addPassesToEmitFile(PM, ostream +#if CLANG_VERSION_MAJOR >= 7 + , /*DwoOut=*/nullptr #endif +#if CLANG_VERSION_MAJOR < 10 + , TargetMachine::CGFT_ObjectFile +#else + , llvm::CGFT_ObjectFile +#endif + ); if (NotAdded) { llvm::errs() << "TargetMachine can't emit a file of this type\n"; return std::unique_ptr>(nullptr); diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 8e2777133b..131207b91d 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/counts.c b/tools/perf/util/counts.c index 582f3aeaf5..7a447d9184 100644 --- a/tools/perf/util/counts.c +++ b/tools/perf/util/counts.c @@ -4,6 +4,7 @@ #include #include "evsel.h" #include "counts.h" +#include #include 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/cpumap.h b/tools/perf/util/cpumap.h index a27eeaf086..703ae6d338 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 #include +#include #include #include +/** 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) -{ - if (!sock || s > sock->nr || s < 0) - return 0; - return sock->map[s]; -} - int cpu__setup_cpunode_map(void); int cpu__max_node(void); -int cpu__max_cpu(void); -int cpu__max_present_cpu(void); -int cpu__get_node(int cpu); +struct perf_cpu cpu__max_cpu(void); +struct perf_cpu cpu__max_present_cpu(void); -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); +/** + * 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) +{ + return perf_cpu_map__nr(cpus) == 1 && perf_cpu_map__cpu(cpus, 0).cpu == -1; +} -int cpu_map__cpu(struct perf_cpu_map *cpus, int idx); -bool cpu_map__has(struct perf_cpu_map *cpus, int cpu); +/** + * 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); -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); +/** + * 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); + +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); + + +/** + * 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/cs-etm.c b/tools/perf/util/cs-etm.c index f323adb1af..8b95fb3c4d 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. @@ -537,7 +535,7 @@ static void cs_etm__dump_event(struct cs_etm_queue *etmq, fprintf(stdout, "\n"); color_fprintf(stdout, color, - ". ... CoreSight %s Trace data: size %zu bytes\n", + ". ... CoreSight %s Trace data: size %#zx bytes\n", cs_etm_decoder__get_name(etmq->decoder), buffer->size); do { @@ -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/env.c b/tools/perf/util/env.c index 5b24eb0103..579e44c599 100644 --- a/tools/perf/util/env.c +++ b/tools/perf/util/env.c @@ -16,6 +16,7 @@ struct perf_env perf_env; #ifdef HAVE_LIBBPF_SUPPORT #include "bpf-event.h" +#include "bpf-utils.h" #include void perf_env__insert_bpf_prog_info(struct perf_env *env, @@ -284,13 +285,13 @@ int perf_env__set_cmdline(struct perf_env *env, int argc, const char *argv[]) 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) @@ -300,10 +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; @@ -380,7 +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; } @@ -486,7 +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; @@ -494,7 +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++; @@ -513,13 +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/event.c b/tools/perf/util/event.c index ac706304af..fe24801f8e 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -57,6 +57,7 @@ static const char *perf_event__names[] = { [PERF_RECORD_BPF_EVENT] = "BPF_EVENT", [PERF_RECORD_CGROUP] = "CGROUP", [PERF_RECORD_TEXT_POKE] = "TEXT_POKE", + [PERF_RECORD_AUX_OUTPUT_HW_ID] = "AUX_OUTPUT_HW_ID", [PERF_RECORD_HEADER_ATTR] = "ATTR", [PERF_RECORD_HEADER_EVENT_TYPE] = "EVENT_TYPE", [PERF_RECORD_HEADER_TRACING_DATA] = "TRACING_DATA", @@ -237,6 +238,14 @@ int perf_event__process_itrace_start(struct perf_tool *tool __maybe_unused, return machine__process_itrace_start_event(machine, event); } +int perf_event__process_aux_output_hw_id(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_sample *sample __maybe_unused, + struct machine *machine) +{ + return machine__process_aux_output_hw_id_event(machine, event); +} + int perf_event__process_lost_samples(struct perf_tool *tool __maybe_unused, union perf_event *event, struct perf_sample *sample, @@ -407,6 +416,12 @@ size_t perf_event__fprintf_itrace_start(union perf_event *event, FILE *fp) event->itrace_start.pid, event->itrace_start.tid); } +size_t perf_event__fprintf_aux_output_hw_id(union perf_event *event, FILE *fp) +{ + return fprintf(fp, " hw_id: %#"PRI_lx64"\n", + event->aux_output_hw_id.hw_id); +} + size_t perf_event__fprintf_switch(union perf_event *event, FILE *fp) { bool out = event->header.misc & PERF_RECORD_MISC_SWITCH_OUT; @@ -534,6 +549,9 @@ size_t perf_event__fprintf(union perf_event *event, struct machine *machine, FIL case PERF_RECORD_TEXT_POKE: ret += perf_event__fprintf_text_poke(event, machine, fp); break; + case PERF_RECORD_AUX_OUTPUT_HW_ID: + ret += perf_event__fprintf_aux_output_hw_id(event, fp); + break; default: ret += fprintf(fp, "\n"); } diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index 19ad64f2bd..c59331eea1 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -44,13 +44,16 @@ struct perf_event_attr; /* perf sample has 16 bits size limit */ #define PERF_SAMPLE_MAX_SIZE (1 << 16) +/* number of register is bound by the number of bits in regs_dump::mask (64) */ +#define PERF_SAMPLE_REGS_CACHE_SIZE (8 * sizeof(u64)) + struct regs_dump { u64 abi; u64 mask; u64 *regs; /* Cached values/mask filled by first register access. */ - u64 cache_regs[PERF_REGS_MAX]; + u64 cache_regs[PERF_SAMPLE_REGS_CACHE_SIZE]; u64 cache_mask; }; @@ -330,6 +333,10 @@ int perf_event__process_itrace_start(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct machine *machine); +int perf_event__process_aux_output_hw_id(struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine); int perf_event__process_switch(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, @@ -397,6 +404,7 @@ size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp); size_t perf_event__fprintf_task(union perf_event *event, FILE *fp); size_t perf_event__fprintf_aux(union perf_event *event, FILE *fp); size_t perf_event__fprintf_itrace_start(union perf_event *event, FILE *fp); +size_t perf_event__fprintf_aux_output_hw_id(union perf_event *event, FILE *fp); size_t perf_event__fprintf_switch(union perf_event *event, FILE *fp); size_t perf_event__fprintf_thread_map(union perf_event *event, FILE *fp); size_t perf_event__fprintf_cpu_map(union perf_event *event, FILE *fp); diff --git a/tools/perf/util/evlist-hybrid.c b/tools/perf/util/evlist-hybrid.c index f39c8ffc5a..57f02beef0 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); diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 97bfb8d0be..64cba56fbc 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 c87f9974c0..22d3267ce2 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -241,7 +241,7 @@ void evsel__init(struct evsel *evsel, { perf_evsel__init(&evsel->core, attr, idx); evsel->tracking = !idx; - evsel->unit = ""; + evsel->unit = strdup(""); evsel->scale = 1.0; evsel->max_events = ULONG_MAX; evsel->evlist = NULL; @@ -276,13 +276,8 @@ struct evsel *evsel__new_idx(struct perf_event_attr *attr, int idx) } if (evsel__is_clock(evsel)) { - /* - * The evsel->unit points to static alias->unit - * so it's ok to use static string in here. - */ - static const char *unit = "msec"; - - evsel->unit = unit; + free((char *)evsel->unit); + evsel->unit = strdup("msec"); evsel->scale = 1e-6; } @@ -294,7 +289,7 @@ static bool perf_event_can_profile_kernel(void) return perf_event_paranoid_check(1); } -struct evsel *evsel__new_cycles(bool precise, __u32 type, __u64 config) +struct evsel *evsel__new_cycles(bool precise __maybe_unused, __u32 type, __u64 config) { struct perf_event_attr attr = { .type = type, @@ -305,18 +300,16 @@ struct evsel *evsel__new_cycles(bool precise, __u32 type, __u64 config) event_attr_init(&attr); - if (!precise) - goto new_event; - /* * Now let the usual logic to set up the perf_event_attr defaults * to kick in when we return and before perf_evsel__open() is called. */ -new_event: evsel = evsel__new(&attr); if (evsel == NULL) goto out; + arch_evsel__fixup_new_cycles(&evsel->core.attr); + evsel->precise_max = true; /* use asprintf() because free(evsel) assumes name is allocated */ @@ -410,6 +403,11 @@ struct evsel *evsel__clone(struct evsel *orig) if (evsel->filter == NULL) goto out_err; } + if (orig->metric_id) { + evsel->metric_id = strdup(orig->metric_id); + if (evsel->metric_id == NULL) + goto out_err; + } evsel->cgrp = cgroup__get(orig->cgrp); evsel->tp_format = orig->tp_format; evsel->handler = orig->handler; @@ -417,7 +415,11 @@ struct evsel *evsel__clone(struct evsel *orig) evsel->max_events = orig->max_events; evsel->tool_event = orig->tool_event; - evsel->unit = orig->unit; + free((char *)evsel->unit); + evsel->unit = strdup(orig->unit); + if (evsel->unit == NULL) + goto out_err; + evsel->scale = orig->scale; evsel->snapshot = orig->snapshot; evsel->per_pkg = orig->per_pkg; @@ -779,6 +781,17 @@ const char *evsel__name(struct evsel *evsel) return "unknown"; } +const char *evsel__metric_id(const struct evsel *evsel) +{ + if (evsel->metric_id) + return evsel->metric_id; + + if (evsel->core.attr.type == PERF_TYPE_SOFTWARE && evsel->tool_event) + return "duration_time"; + + return "unknown"; +} + const char *evsel__group_name(struct evsel *evsel) { return evsel->group_name ?: "anon group"; @@ -1047,6 +1060,10 @@ void __weak arch_evsel__set_sample_weight(struct evsel *evsel) evsel__set_sample_bit(evsel, WEIGHT); } +void __weak arch_evsel__fixup_new_cycles(struct perf_event_attr *attr __maybe_unused) +{ +} + static void evsel__set_default_freq_period(struct record_opts *opts, struct perf_event_attr *attr) { @@ -1364,9 +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) @@ -1379,9 +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) @@ -1432,6 +1449,8 @@ void evsel__exit(struct evsel *evsel) zfree(&evsel->group_name); zfree(&evsel->name); zfree(&evsel->pmu_name); + zfree(&evsel->unit); + zfree(&evsel->metric_id); evsel__zero_per_pkg(evsel); hashmap__free(evsel->per_pkg_mask); evsel->per_pkg_mask = NULL; @@ -1445,7 +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; @@ -1453,12 +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; @@ -1466,46 +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; + return perf_evsel__read(&evsel->core, cpu_map_idx, thread, count); } -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); -} - -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; @@ -1524,7 +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; @@ -1533,13 +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; @@ -1560,67 +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; @@ -1634,11 +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; @@ -1652,16 +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); @@ -1675,10 +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); @@ -1701,7 +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)) @@ -1790,7 +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; @@ -1816,7 +1817,7 @@ static void evsel__disable_missing_features(struct evsel *evsel) evsel->open_flags &= ~(unsigned long)PERF_FLAG_FD_CLOEXEC; if (perf_missing_features.mmap2) evsel->core.attr.mmap2 = 0; - if (perf_missing_features.exclude_guest) + if (evsel->pmu && evsel->pmu->missing_features.exclude_guest) evsel->core.attr.exclude_guest = evsel->core.attr.exclude_host = 0; if (perf_missing_features.lbr_flags) evsel->core.attr.branch_sample_type &= ~(PERF_SAMPLE_BRANCH_NO_FLAGS | @@ -1909,10 +1910,27 @@ bool evsel__detect_missing_features(struct evsel *evsel) perf_missing_features.mmap2 = true; pr_debug2_peo("switching off mmap2\n"); return true; - } else if (!perf_missing_features.exclude_guest && - (evsel->core.attr.exclude_guest || evsel->core.attr.exclude_host)) { - perf_missing_features.exclude_guest = true; - pr_debug2_peo("switching off exclude_guest, exclude_host\n"); + } else if ((evsel->core.attr.exclude_guest || evsel->core.attr.exclude_host) && + (evsel->pmu == NULL || evsel->pmu->missing_features.exclude_guest)) { + if (evsel->pmu == NULL) { + evsel->pmu = evsel__find_pmu(evsel); + if (evsel->pmu) + evsel->pmu->missing_features.exclude_guest = true; + else { + /* we cannot find PMU, disable attrs now */ + evsel->core.attr.exclude_host = false; + evsel->core.attr.exclude_guest = false; + } + } + + if (evsel->exclude_GH) { + pr_debug2_peo("PMU has no exclude_host/guest support, bailing out\n"); + return false; + } + if (!perf_missing_features.exclude_guest) { + perf_missing_features.exclude_guest = true; + pr_debug2_peo("switching off exclude_guest, exclude_host\n"); + } return true; } else if (!perf_missing_features.sample_id_all) { perf_missing_features.sample_id_all = true; @@ -1966,9 +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; @@ -1995,7 +2013,7 @@ static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus, 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; @@ -2006,17 +2024,18 @@ static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus, 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; @@ -2026,10 +2045,11 @@ static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus, 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); } @@ -2070,7 +2090,8 @@ static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus, 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--; @@ -2085,7 +2106,7 @@ static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus, 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)) @@ -2097,12 +2118,12 @@ static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus, 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; } @@ -2110,7 +2131,7 @@ static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus, 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) @@ -2119,13 +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) @@ -2230,6 +2250,54 @@ void __weak arch_perf_parse_sample_weight(struct perf_sample *data, data->weight = *array; } +u64 evsel__bitfield_swap_branch_flags(u64 value) +{ + u64 new_val = 0; + + /* + * branch_flags + * union { + * u64 values; + * struct { + * mispred:1 //target mispredicted + * predicted:1 //target predicted + * in_tx:1 //in transaction + * abort:1 //transaction abort + * cycles:16 //cycle count to last branch + * type:4 //branch type + * reserved:40 + * } + * } + * + * Avoid bswap64() the entire branch_flag.value, + * as it has variable bit-field sizes. Instead the + * macro takes the bit-field position/size, + * swaps it based on the host endianness. + * + * tep_is_bigendian() is used here instead of + * bigendian() to avoid python test fails. + */ + if (tep_is_bigendian()) { + new_val = bitfield_swap(value, 0, 1); + new_val |= bitfield_swap(value, 1, 1); + new_val |= bitfield_swap(value, 2, 1); + new_val |= bitfield_swap(value, 3, 1); + new_val |= bitfield_swap(value, 4, 16); + new_val |= bitfield_swap(value, 20, 4); + new_val |= bitfield_swap(value, 24, 40); + } else { + new_val = bitfield_swap(value, 63, 1); + new_val |= bitfield_swap(value, 62, 1); + new_val |= bitfield_swap(value, 61, 1); + new_val |= bitfield_swap(value, 60, 1); + new_val |= bitfield_swap(value, 44, 16); + new_val |= bitfield_swap(value, 40, 4); + new_val |= bitfield_swap(value, 0, 40); + } + + return new_val; +} + int evsel__parse_sample(struct evsel *evsel, union perf_event *event, struct perf_sample *data) { @@ -2417,6 +2485,8 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event, if (type & PERF_SAMPLE_BRANCH_STACK) { const u64 max_branch_nr = UINT64_MAX / sizeof(struct branch_entry); + struct branch_entry *e; + unsigned int i; OVERFLOW_CHECK_u64(array); data->branch_stack = (struct branch_stack *)array++; @@ -2425,10 +2495,33 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event, return -EFAULT; sz = data->branch_stack->nr * sizeof(struct branch_entry); - if (evsel__has_branch_hw_idx(evsel)) + if (evsel__has_branch_hw_idx(evsel)) { sz += sizeof(u64); - else + e = &data->branch_stack->entries[0]; + } else { data->no_hw_idx = true; + /* + * if the PERF_SAMPLE_BRANCH_HW_INDEX is not applied, + * only nr and entries[] will be output by kernel. + */ + e = (struct branch_entry *)&data->branch_stack->hw_idx; + } + + if (swapped) { + /* + * struct branch_flag does not have endian + * specific bit field definition. And bswap + * will not resolve the issue, since these + * are bit fields. + * + * evsel__bitfield_swap_branch_flags() uses a + * bitfield_swap macro to swap the bit position + * based on the host endians. + */ + for (i = 0; i < data->branch_stack->nr; i++, e++) + e->flags.value = evsel__bitfield_swap_branch_flags(e->flags.value); + } + OVERFLOW_CHECK(array, sz, max_size); array = (void *)array + sz; } @@ -2606,6 +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; @@ -2850,6 +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. " @@ -2873,15 +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; } } @@ -2894,7 +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); @@ -2937,3 +3036,15 @@ void evsel__set_leader(struct evsel *evsel, struct evsel *leader) { evsel->core.leader = &leader->core; } + +int evsel__source_count(const struct evsel *evsel) +{ + struct evsel *pos; + int count = 0; + + evlist__for_each_entry(evsel->evlist, pos) { + if (pos->metric_leader == evsel) + count++; + } + return count; +} diff --git a/tools/perf/util/evsel_fprintf.c b/tools/perf/util/evsel_fprintf.c index bfedd7b235..8c2ea80013 100644 --- a/tools/perf/util/evsel_fprintf.c +++ b/tools/perf/util/evsel_fprintf.c @@ -11,6 +11,7 @@ #include "strlist.h" #include "symbol.h" #include "srcline.h" +#include "dso.h" static int comma_fprintf(FILE *fp, bool *first, const char *fmt, ...) { @@ -144,12 +145,17 @@ int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment, if (print_arrow && !first) printed += fprintf(fp, " <-"); - if (print_ip) - printed += fprintf(fp, "%c%16" PRIx64, s, node->ip); - if (map) addr = map->map_ip(map, node->ip); + if (print_ip) { + /* Show binary offset for userspace addr */ + if (map && !map->dso->kernel) + printed += fprintf(fp, "%c%16" PRIx64, s, addr); + else + printed += fprintf(fp, "%c%16" PRIx64, s, node->ip); + } + if (print_sym) { printed += fprintf(fp, " "); node_al.addr = addr; diff --git a/tools/perf/util/expr.h b/tools/perf/util/expr.h index 85df3e4771..bd2116983b 100644 --- a/tools/perf/util/expr.h +++ b/tools/perf/util/expr.h @@ -13,39 +13,51 @@ struct metric_ref; -struct expr_id { - char *id; - struct expr_id *parent; -}; - struct expr_parse_ctx { - struct hashmap ids; - struct expr_id *parent; + struct hashmap *ids; + int runtime; }; struct expr_id_data; struct expr_scanner_ctx { - int start_token; int runtime; }; -void expr__ctx_init(struct expr_parse_ctx *ctx); +struct hashmap *ids__new(void); +void ids__free(struct hashmap *ids); +int ids__insert(struct hashmap *ids, const char *id); +/* + * Union two sets of ids (hashmaps) and construct a third, freeing ids1 and + * ids2. + */ +struct hashmap *ids__union(struct hashmap *ids1, struct hashmap *ids2); + +struct expr_parse_ctx *expr__ctx_new(void); void expr__ctx_clear(struct expr_parse_ctx *ctx); +void expr__ctx_free(struct expr_parse_ctx *ctx); + void expr__del_id(struct expr_parse_ctx *ctx, const char *id); int expr__add_id(struct expr_parse_ctx *ctx, const char *id); int expr__add_id_val(struct expr_parse_ctx *ctx, const char *id, double val); +int expr__add_id_val_source_count(struct expr_parse_ctx *ctx, const char *id, + double val, int source_count); int expr__add_ref(struct expr_parse_ctx *ctx, struct metric_ref *ref); int expr__get_id(struct expr_parse_ctx *ctx, const char *id, struct expr_id_data **data); +bool expr__subset_of_ids(struct expr_parse_ctx *haystack, + struct expr_parse_ctx *needles); int expr__resolve_id(struct expr_parse_ctx *ctx, const char *id, struct expr_id_data **datap); + int expr__parse(double *final_val, struct expr_parse_ctx *ctx, - const char *expr, int runtime); -int expr__find_other(const char *expr, const char *one, - struct expr_parse_ctx *ids, int runtime); + const char *expr); + +int expr__find_ids(const char *expr, const char *one, + struct expr_parse_ctx *ids); double expr_id_data__value(const struct expr_id_data *data); -struct expr_id *expr_id_data__parent(struct expr_id_data *data); +double expr_id_data__source_count(const struct expr_id_data *data); +double expr__get_literal(const char *literal); #endif diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 1c7414f666..6da12e522e 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -48,6 +48,7 @@ #include "util/util.h" // perf_exe() #include "cputopo.h" #include "bpf-event.h" +#include "bpf-utils.h" #include "clockid.h" #include "pmu-hybrid.h" @@ -471,7 +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) @@ -582,21 +583,21 @@ static int write_cpu_topology(struct feat_fd *ff, if (!tp) return -1; - ret = do_write(ff, &tp->core_sib, sizeof(tp->core_sib)); + ret = do_write(ff, &tp->package_cpus_lists, sizeof(tp->package_cpus_lists)); if (ret < 0) goto done; - for (i = 0; i < tp->core_sib; i++) { - ret = do_write_string(ff, tp->core_siblings[i]); + for (i = 0; i < tp->package_cpus_lists; i++) { + ret = do_write_string(ff, tp->package_cpus_list[i]); if (ret < 0) goto done; } - ret = do_write(ff, &tp->thread_sib, sizeof(tp->thread_sib)); + ret = do_write(ff, &tp->core_cpus_lists, sizeof(tp->core_cpus_lists)); if (ret < 0) goto done; - for (i = 0; i < tp->thread_sib; i++) { - ret = do_write_string(ff, tp->thread_siblings[i]); + for (i = 0; i < tp->core_cpus_lists; i++) { + ret = do_write_string(ff, tp->core_cpus_list[i]); if (ret < 0) break; } @@ -616,15 +617,15 @@ static int write_cpu_topology(struct feat_fd *ff, return ret; } - if (!tp->die_sib) + if (!tp->die_cpus_lists) goto done; - ret = do_write(ff, &tp->die_sib, sizeof(tp->die_sib)); + ret = do_write(ff, &tp->die_cpus_lists, sizeof(tp->die_cpus_lists)); if (ret < 0) goto done; - for (i = 0; i < tp->die_sib; i++) { - ret = do_write_string(ff, tp->die_siblings[i]); + for (i = 0; i < tp->die_cpus_lists; i++) { + ret = do_write_string(ff, tp->die_cpus_list[i]); if (ret < 0) goto done; } @@ -1006,17 +1007,17 @@ static int write_bpf_prog_info(struct feat_fd *ff, node = rb_entry(next, struct bpf_prog_info_node, rb_node); next = rb_next(&node->rb_node); - len = sizeof(struct bpf_prog_info_linear) + + len = sizeof(struct perf_bpil) + node->info_linear->data_len; /* before writing to file, translate address to offset */ - bpf_program__bpil_addr_to_offs(node->info_linear); + bpil_addr_to_offs(node->info_linear); ret = do_write(ff, node->info_linear, len); /* * translate back to address even when do_write() fails, * so that this function never changes the data. */ - bpf_program__bpil_offs_to_addr(node->info_linear); + bpil_offs_to_addr(node->info_linear); if (ret < 0) goto out; } @@ -1162,7 +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++) { @@ -1194,7 +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; @@ -2320,6 +2321,7 @@ static int perf_header__read_build_ids(struct perf_header *header, #define FEAT_PROCESS_STR_FUN(__feat, __feat_env) \ static int process_##__feat(struct feat_fd *ff, void *data __maybe_unused) \ {\ + free(ff->ph->env.__feat_env); \ ff->ph->env.__feat_env = do_read_string(ff); \ return ff->ph->env.__feat_env ? 0 : -ENOMEM; \ } @@ -3018,9 +3020,9 @@ static int process_dir_format(struct feat_fd *ff, #ifdef HAVE_LIBBPF_SUPPORT static int process_bpf_prog_info(struct feat_fd *ff, void *data __maybe_unused) { - struct bpf_prog_info_linear *info_linear; struct bpf_prog_info_node *info_node; struct perf_env *env = &ff->ph->env; + struct perf_bpil *info_linear; u32 count, i; int err = -1; @@ -3049,7 +3051,7 @@ static int process_bpf_prog_info(struct feat_fd *ff, void *data __maybe_unused) goto out; } - info_linear = malloc(sizeof(struct bpf_prog_info_linear) + + info_linear = malloc(sizeof(struct perf_bpil) + data_len); if (!info_linear) goto out; @@ -3071,7 +3073,7 @@ static int process_bpf_prog_info(struct feat_fd *ff, void *data __maybe_unused) goto out; /* after reading from file, translate offset to address */ - bpf_program__bpil_offs_to_addr(info_linear); + bpil_offs_to_addr(info_linear); info_node->info_linear = info_linear; perf_env__insert_bpf_prog_info(env, info_node); } @@ -4123,6 +4125,7 @@ int perf_event__process_feature(struct perf_session *session, struct perf_record_header_feature *fe = (struct perf_record_header_feature *)event; int type = fe->header.type; u64 feat = fe->feat_id; + int ret = 0; if (type < 0 || type >= PERF_RECORD_HEADER_MAX) { pr_warning("invalid record type %d in pipe-mode\n", type); @@ -4140,11 +4143,13 @@ int perf_event__process_feature(struct perf_session *session, ff.size = event->header.size - sizeof(*fe); ff.ph = &session->header; - if (feat_ops[feat].process(&ff, NULL)) - return -1; + if (feat_ops[feat].process(&ff, NULL)) { + ret = -1; + goto out; + } if (!feat_ops[feat].print || !tool->show_feat_hdr) - return 0; + goto out; if (!feat_ops[feat].full_only || tool->show_feat_hdr >= SHOW_FEAT_HEADER_FULL_INFO) { @@ -4153,8 +4158,9 @@ int perf_event__process_feature(struct perf_session *session, fprintf(stdout, "# %s info available, use -I to display\n", feat_ops[feat].name); } - - return 0; +out: + free_event_desc(ff.events); + return ret; } size_t perf_event__fprintf_event_update(union perf_event *event, FILE *fp) @@ -4256,9 +4262,11 @@ int perf_event__process_event_update(struct perf_tool *tool __maybe_unused, switch (ev->type) { case PERF_EVENT_UPDATE__UNIT: + free((char *)evsel->unit); evsel->unit = strdup(ev->data); break; case PERF_EVENT_UPDATE__NAME: + free(evsel->name); evsel->name = strdup(ev->data); break; case PERF_EVENT_UPDATE__SCALE: @@ -4267,11 +4275,11 @@ int perf_event__process_event_update(struct perf_tool *tool __maybe_unused, break; case PERF_EVENT_UPDATE__CPUS: ev_cpus = (struct perf_record_event_update_cpus *)ev->data; - map = cpu_map__new_data(&ev_cpus->cpus); - if (map) + if (map) { + perf_cpu_map__put(evsel->core.own_cpus); evsel->core.own_cpus = map; - else + } else pr_err("failed to get event_update cpus\n"); default: break; diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index b776465e04..0a8033b09e 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 621f35ae1e..2a15e22fb8 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/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c index b0034ee4bb..0e013c2d9e 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c @@ -608,6 +608,7 @@ static inline void intel_pt_update_sample_time(struct intel_pt_decoder *decoder) { decoder->sample_timestamp = decoder->timestamp; decoder->sample_insn_cnt = decoder->timestamp_insn_cnt; + decoder->state.cycles = decoder->tot_cyc_cnt; } static void intel_pt_reposition(struct intel_pt_decoder *decoder) diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h index 4b5e79fcf5..8fd68f7a09 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h @@ -218,6 +218,7 @@ struct intel_pt_state { uint64_t to_ip; uint64_t tot_insn_cnt; uint64_t tot_cyc_cnt; + uint64_t cycles; uint64_t timestamp; uint64_t est_timestamp; uint64_t trace_nr; diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c index 593f20e977..9d5e65cec8 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c @@ -143,7 +143,7 @@ static void intel_pt_insn_decoder(struct insn *insn, if (branch == INTEL_PT_BR_CONDITIONAL || branch == INTEL_PT_BR_UNCONDITIONAL) { -#if __BYTE_ORDER == __BIG_ENDIAN +#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ switch (insn->immediate.nbytes) { case 1: intel_pt_insn->rel = insn->immediate.value; diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-log.c b/tools/perf/util/intel-pt-decoder/intel-pt-log.c index 09feb5b07d..5f5dfc8753 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-log.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-log.c @@ -82,10 +82,10 @@ static int intel_pt_log_open(void) if (f) return 0; - if (!log_name[0]) - return -1; - - f = fopen(log_name, "w+"); + if (log_name[0]) + f = fopen(log_name, "w+"); + else + f = stdout; if (!f) { intel_pt_enable_logging = false; return -1; diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c index 02a3395d6c..4bd154848c 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c @@ -16,7 +16,7 @@ #define BIT63 ((uint64_t)1 << 63) -#if __BYTE_ORDER == __BIG_ENDIAN +#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ #define le16_to_cpu bswap_16 #define le32_to_cpu bswap_32 #define le64_to_cpu bswap_64 diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index c3ceac1388..e8613cbda3 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -111,6 +111,7 @@ struct intel_pt { u64 cbr_id; u64 psb_id; + bool single_pebs; bool sample_pebs; struct evsel *pebs_evsel; @@ -148,6 +149,14 @@ enum switch_state { INTEL_PT_SS_EXPECTING_SWITCH_IP, }; +/* applicable_counters is 64-bits */ +#define INTEL_PT_MAX_PEBS 64 + +struct intel_pt_pebs_event { + struct evsel *evsel; + u64 id; +}; + struct intel_pt_queue { struct intel_pt *pt; unsigned int queue_nr; @@ -163,6 +172,7 @@ struct intel_pt_queue { bool step_through_buffers; bool use_buffer_pid_tid; bool sync_switch; + bool sample_ipc; pid_t pid, tid; int cpu; int switch_state; @@ -189,6 +199,7 @@ struct intel_pt_queue { u64 last_br_cyc_cnt; unsigned int cbr_seen; char insn[INTEL_PT_INSN_BUF_SZ]; + struct intel_pt_pebs_event pebs[INTEL_PT_MAX_PEBS]; }; static void intel_pt_dump(struct intel_pt *pt __maybe_unused, @@ -1571,7 +1582,7 @@ static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq) sample.branch_stack = (struct branch_stack *)&dummy_bs; } - if (ptq->state->flags & INTEL_PT_SAMPLE_IPC) + if (ptq->sample_ipc) sample.cyc_cnt = ptq->ipc_cyc_cnt - ptq->last_br_cyc_cnt; if (sample.cyc_cnt) { sample.insn_cnt = ptq->ipc_insn_cnt - ptq->last_br_insn_cnt; @@ -1622,7 +1633,7 @@ static int intel_pt_synth_instruction_sample(struct intel_pt_queue *ptq) else sample.period = ptq->state->tot_insn_cnt - ptq->last_insn_cnt; - if (ptq->state->flags & INTEL_PT_SAMPLE_IPC) + if (ptq->sample_ipc) sample.cyc_cnt = ptq->ipc_cyc_cnt - ptq->last_in_cyc_cnt; if (sample.cyc_cnt) { sample.insn_cnt = ptq->ipc_insn_cnt - ptq->last_in_insn_cnt; @@ -1978,15 +1989,13 @@ static void intel_pt_add_lbrs(struct branch_stack *br_stack, } } -static int intel_pt_synth_pebs_sample(struct intel_pt_queue *ptq) +static int intel_pt_do_synth_pebs_sample(struct intel_pt_queue *ptq, struct evsel *evsel, u64 id) { const struct intel_pt_blk_items *items = &ptq->state->items; struct perf_sample sample = { .ip = 0, }; union perf_event *event = ptq->event_buf; struct intel_pt *pt = ptq->pt; - struct evsel *evsel = pt->pebs_evsel; u64 sample_type = evsel->core.attr.sample_type; - u64 id = evsel->core.id[0]; u8 cpumode; u64 regs[8 * sizeof(sample.intr_regs.mask)]; @@ -2112,6 +2121,45 @@ static int intel_pt_synth_pebs_sample(struct intel_pt_queue *ptq) return intel_pt_deliver_synth_event(pt, event, &sample, sample_type); } +static int intel_pt_synth_single_pebs_sample(struct intel_pt_queue *ptq) +{ + struct intel_pt *pt = ptq->pt; + struct evsel *evsel = pt->pebs_evsel; + u64 id = evsel->core.id[0]; + + return intel_pt_do_synth_pebs_sample(ptq, evsel, id); +} + +static int intel_pt_synth_pebs_sample(struct intel_pt_queue *ptq) +{ + const struct intel_pt_blk_items *items = &ptq->state->items; + struct intel_pt_pebs_event *pe; + struct intel_pt *pt = ptq->pt; + int err = -EINVAL; + int hw_id; + + if (!items->has_applicable_counters || !items->applicable_counters) { + if (!pt->single_pebs) + pr_err("PEBS-via-PT record with no applicable_counters\n"); + return intel_pt_synth_single_pebs_sample(ptq); + } + + for_each_set_bit(hw_id, (unsigned long *)&items->applicable_counters, INTEL_PT_MAX_PEBS) { + pe = &ptq->pebs[hw_id]; + if (!pe->evsel) { + if (!pt->single_pebs) + pr_err("PEBS-via-PT record with no matching event, hw_id %d\n", + hw_id); + return intel_pt_synth_single_pebs_sample(ptq); + } + err = intel_pt_do_synth_pebs_sample(ptq, pe->evsel, pe->id); + if (err) + return err; + } + + return err; +} + static int intel_pt_synth_error(struct intel_pt *pt, int code, int cpu, pid_t pid, pid_t tid, u64 ip, u64 timestamp) { @@ -2198,8 +2246,15 @@ static int intel_pt_sample(struct intel_pt_queue *ptq) ptq->have_sample = false; - ptq->ipc_insn_cnt = ptq->state->tot_insn_cnt; - ptq->ipc_cyc_cnt = ptq->state->tot_cyc_cnt; + if (pt->synth_opts.approx_ipc) { + ptq->ipc_insn_cnt = ptq->state->tot_insn_cnt; + ptq->ipc_cyc_cnt = ptq->state->cycles; + ptq->sample_ipc = true; + } else { + ptq->ipc_insn_cnt = ptq->state->tot_insn_cnt; + ptq->ipc_cyc_cnt = ptq->state->tot_cyc_cnt; + ptq->sample_ipc = ptq->state->flags & INTEL_PT_SAMPLE_IPC; + } /* * Do PEBS first to allow for the possibility that the PEBS timestamp @@ -2883,6 +2938,30 @@ static int intel_pt_process_itrace_start(struct intel_pt *pt, event->itrace_start.tid); } +static int intel_pt_process_aux_output_hw_id(struct intel_pt *pt, + union perf_event *event, + struct perf_sample *sample) +{ + u64 hw_id = event->aux_output_hw_id.hw_id; + struct auxtrace_queue *queue; + struct intel_pt_queue *ptq; + struct evsel *evsel; + + queue = auxtrace_queues__sample_queue(&pt->queues, sample, pt->session); + evsel = evlist__id2evsel_strict(pt->session->evlist, sample->id); + if (!queue || !queue->priv || !evsel || hw_id > INTEL_PT_MAX_PEBS) { + pr_err("Bad AUX output hardware ID\n"); + return -EINVAL; + } + + ptq = queue->priv; + + ptq->pebs[hw_id].evsel = evsel; + ptq->pebs[hw_id].id = sample->id; + + return 0; +} + static int intel_pt_find_map(struct thread *thread, u8 cpumode, u64 addr, struct addr_location *al) { @@ -3010,6 +3089,8 @@ static int intel_pt_process_event(struct perf_session *session, err = intel_pt_process_switch(pt, sample); else if (event->header.type == PERF_RECORD_ITRACE_START) err = intel_pt_process_itrace_start(pt, event, sample); + else if (event->header.type == PERF_RECORD_AUX_OUTPUT_HW_ID) + err = intel_pt_process_aux_output_hw_id(pt, event, sample); else if (event->header.type == PERF_RECORD_SWITCH || event->header.type == PERF_RECORD_SWITCH_CPU_WIDE) err = intel_pt_context_switch(pt, event, sample); @@ -3394,9 +3475,13 @@ static void intel_pt_setup_pebs_events(struct intel_pt *pt) evlist__for_each_entry(pt->session->evlist, evsel) { if (evsel->core.attr.aux_output && evsel->core.id) { + if (pt->single_pebs) { + pt->single_pebs = false; + return; + } + pt->single_pebs = true; pt->sample_pebs = true; pt->pebs_evsel = evsel; - return; } } } @@ -3653,8 +3738,6 @@ int intel_pt_process_auxtrace_info(union perf_event *event, if (err) goto err_free; - intel_pt_log_set_name(INTEL_PT_PMU_NAME); - if (session->itrace_synth_opts->set) { pt->synth_opts = *session->itrace_synth_opts; } else { @@ -3669,6 +3752,9 @@ int intel_pt_process_auxtrace_info(union perf_event *event, pt->synth_opts.thread_stack = opts->thread_stack; } + if (!(pt->synth_opts.log_plus_flags & AUXTRACE_LOG_FLG_USE_STDOUT)) + intel_pt_log_set_name(INTEL_PT_PMU_NAME); + pt->session = session; pt->machine = &session->machines.host; /* No kvm support */ pt->auxtrace_type = auxtrace_info->type; diff --git a/tools/perf/util/libunwind/arm64.c b/tools/perf/util/libunwind/arm64.c index c397be0c2e..15f60fd094 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/mmap.c b/tools/perf/util/mmap.c index 512dc8b9c1..0e8ff8d1e2 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", @@ -350,3 +351,14 @@ int perf_mmap__push(struct mmap *md, void *to, out: return rc; } + +int mmap_cpu_mask__duplicate(struct mmap_cpu_mask *original, struct mmap_cpu_mask *clone) +{ + clone->nbits = original->nbits; + clone->bits = bitmap_zalloc(original->nbits); + if (!clone->bits) + return -ENOMEM; + + memcpy(clone->bits, original->bits, MMAP_CPU_MASK_BYTES(original)); + return 0; +} diff --git a/tools/perf/util/namespaces.c b/tools/perf/util/namespaces.c index 608b20c72a..48aa321730 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 ad9775db7b..9ceea96435 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.h b/tools/perf/util/parse-events-hybrid.h index f33bd67aa8..cbc05fec02 100644 --- a/tools/perf/util/parse-events-hybrid.h +++ b/tools/perf/util/parse-events-hybrid.h @@ -11,11 +11,13 @@ int parse_events__add_numeric_hybrid(struct parse_events_state *parse_state, struct list_head *list, struct perf_event_attr *attr, - char *name, struct list_head *config_terms, + const char *name, const char *metric_id, + struct list_head *config_terms, bool *hybrid); int parse_events__add_cache_hybrid(struct list_head *list, int *idx, - struct perf_event_attr *attr, char *name, + struct perf_event_attr *attr, + const char *name, const char *metric_id, struct list_head *config_terms, bool *hybrid, struct parse_events_state *parse_state); diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index d94e48e1ff..be8c517700 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 PE_VALUE @@ -87,7 +87,7 @@ static void inc_group_count(struct list_head *list, %type PE_MODIFIER_EVENT %type PE_MODIFIER_BP %type PE_EVENT_NAME -%type PE_PMU_EVENT_PRE PE_PMU_EVENT_SUF PE_KERNEL_PMU_EVENT PE_PMU_EVENT_FAKE +%type PE_PMU_EVENT_PRE PE_PMU_EVENT_SUF PE_PMU_EVENT_SUF2 PE_KERNEL_PMU_EVENT PE_PMU_EVENT_FAKE %type PE_DRV_CFG_TERM %type event_pmu_name %destructor { free ($$); } @@ -183,6 +183,11 @@ group_def ':' PE_MODIFIER_EVENT err = parse_events__modifier_group(list, $3); free($3); if (err) { + struct parse_events_state *parse_state = _parse_state; + struct parse_events_error *error = parse_state->error; + + parse_events_error__handle(error, @3.first_column, + strdup("Bad modifier"), NULL); free_list_evsel(list); YYABORT; } @@ -240,6 +245,11 @@ event_name PE_MODIFIER_EVENT err = parse_events__modifier_event(list, $2, false); free($2); if (err) { + struct parse_events_state *parse_state = _parse_state; + struct parse_events_error *error = parse_state->error; + + parse_events_error__handle(error, @2.first_column, + strdup("Bad modifier"), NULL); free_list_evsel(list); YYABORT; } @@ -342,13 +352,39 @@ PE_KERNEL_PMU_EVENT sep_dc struct list_head *list; int err; - err = parse_events_multi_pmu_add(_parse_state, $1, &list); + err = parse_events_multi_pmu_add(_parse_state, $1, NULL, &list); free($1); if (err < 0) YYABORT; $$ = list; } | +PE_KERNEL_PMU_EVENT opt_pmu_config +{ + struct list_head *list; + int err; + + /* frees $2 */ + err = parse_events_multi_pmu_add(_parse_state, $1, $2, &list); + free($1); + if (err < 0) + YYABORT; + $$ = list; +} +| +PE_PMU_EVENT_PRE '-' PE_PMU_EVENT_SUF '-' PE_PMU_EVENT_SUF2 sep_dc +{ + struct list_head *list; + char pmu_name[128]; + snprintf(pmu_name, sizeof(pmu_name), "%s-%s-%s", $1, $3, $5); + free($1); + free($3); + free($5); + if (parse_events_multi_pmu_add(_parse_state, pmu_name, NULL, &list) < 0) + YYABORT; + $$ = list; +} +| PE_PMU_EVENT_PRE '-' PE_PMU_EVENT_SUF sep_dc { struct list_head *list; @@ -357,7 +393,7 @@ PE_PMU_EVENT_PRE '-' PE_PMU_EVENT_SUF sep_dc snprintf(pmu_name, sizeof(pmu_name), "%s-%s", $1, $3); free($1); free($3); - if (parse_events_multi_pmu_add(_parse_state, pmu_name, &list) < 0) + if (parse_events_multi_pmu_add(_parse_state, pmu_name, NULL, &list) < 0) YYABORT; $$ = list; } diff --git a/tools/perf/util/perf_api_probe.c b/tools/perf/util/perf_api_probe.c index 020411682a..c28dd50bd5 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_regs.c b/tools/perf/util/perf_regs.c index 5ee47ae150..a982e40ee5 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 +#include #include "perf_regs.h" #include "event.h" @@ -20,11 +21,679 @@ 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; u64 mask = regs->mask; + if ((u64)id >= PERF_SAMPLE_REGS_CACHE_SIZE) + return -EINVAL; + if (regs->cache_mask & (1ULL << id)) goto out; diff --git a/tools/perf/util/perf_regs.h b/tools/perf/util/perf_regs.h index eeac181ebc..ce1127af05 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/pmu.c b/tools/perf/util/pmu.c index bdabd62170..8dfbba15ae 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -315,7 +315,7 @@ static bool perf_pmu_merge_alias(struct perf_pmu_alias *newalias, } static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name, - char *desc, char *val, struct pmu_event *pe) + char *desc, char *val, const struct pmu_event *pe) { struct parse_events_term *term; struct perf_pmu_alias *alias; @@ -710,9 +710,9 @@ static char *perf_pmu__getcpuid(struct perf_pmu *pmu) return cpuid; } -struct pmu_events_map *perf_pmu__find_map(struct perf_pmu *pmu) +const struct pmu_events_map *perf_pmu__find_map(struct perf_pmu *pmu) { - struct pmu_events_map *map; + const struct pmu_events_map *map; char *cpuid = perf_pmu__getcpuid(pmu); int i; @@ -737,7 +737,7 @@ struct pmu_events_map *perf_pmu__find_map(struct perf_pmu *pmu) return map; } -struct pmu_events_map *__weak pmu_events_map__find(void) +const struct pmu_events_map *__weak pmu_events_map__find(void) { return perf_pmu__find_map(NULL); } @@ -824,7 +824,7 @@ bool pmu_uncore_alias_match(const char *pmu_name, const char *name) * as aliases. */ void pmu_add_cpu_aliases_map(struct list_head *head, struct perf_pmu *pmu, - struct pmu_events_map *map) + const struct pmu_events_map *map) { int i; const char *name = pmu->name; @@ -834,7 +834,7 @@ void pmu_add_cpu_aliases_map(struct list_head *head, struct perf_pmu *pmu, i = 0; while (1) { const char *cpu_name = is_arm_pmu_core(name) ? name : "cpu"; - struct pmu_event *pe = &map->table[i++]; + const struct pmu_event *pe = &map->table[i++]; const char *pname = pe->pmu ? pe->pmu : cpu_name; if (!pe->name) { @@ -859,7 +859,7 @@ void pmu_add_cpu_aliases_map(struct list_head *head, struct perf_pmu *pmu, static void pmu_add_cpu_aliases(struct list_head *head, struct perf_pmu *pmu) { - struct pmu_events_map *map; + const struct pmu_events_map *map; map = perf_pmu__find_map(pmu); if (!map) @@ -873,7 +873,7 @@ void pmu_for_each_sys_event(pmu_sys_event_iter_fn fn, void *data) int i = 0; while (1) { - struct pmu_sys_events *event_table; + const struct pmu_sys_events *event_table; int j = 0; event_table = &pmu_sys_event_tables[i++]; @@ -882,7 +882,7 @@ void pmu_for_each_sys_event(pmu_sys_event_iter_fn fn, void *data) break; while (1) { - struct pmu_event *pe = &event_table->table[j++]; + const struct pmu_event *pe = &event_table->table[j++]; int ret; if (!pe->name && !pe->metric_group && !pe->metric_name) @@ -900,7 +900,7 @@ struct pmu_sys_event_iter_data { struct perf_pmu *pmu; }; -static int pmu_add_sys_aliases_iter_fn(struct pmu_event *pe, void *data) +static int pmu_add_sys_aliases_iter_fn(const struct pmu_event *pe, void *data) { struct pmu_sys_event_iter_data *idata = data; struct perf_pmu *pmu = idata->pmu; @@ -1283,7 +1283,7 @@ static int pmu_config_term(const char *pmu_name, unknown_term = NULL; help_msg = parse_events_formats_error_string(pmu_term); if (err) { - parse_events__handle_error(err, term->err_term, + parse_events_error__handle(err, term->err_term, unknown_term, help_msg); } else { @@ -1316,7 +1316,7 @@ static int pmu_config_term(const char *pmu_name, if (term->no_value && bitmap_weight(format->bits, PERF_PMU_FORMAT_BITS) > 1) { if (err) { - parse_events__handle_error(err, term->err_val, + parse_events_error__handle(err, term->err_val, strdup("no value assigned for term"), NULL); } @@ -1331,7 +1331,7 @@ static int pmu_config_term(const char *pmu_name, term->config, term->val.str); } if (err) { - parse_events__handle_error(err, term->err_val, + parse_events_error__handle(err, term->err_val, strdup("expected numeric value"), NULL); } @@ -1348,7 +1348,7 @@ static int pmu_config_term(const char *pmu_name, if (err) { char *err_str; - parse_events__handle_error(err, term->err_val, + parse_events_error__handle(err, term->err_val, asprintf(&err_str, "value too big for format, maximum is %llu", (unsigned long long)max_val) < 0 @@ -1608,6 +1608,7 @@ static int cmp_sevent(const void *a, const void *b) { const struct sevent *as = a; const struct sevent *bs = b; + int ret; /* Put extra events last */ if (!!as->desc != !!bs->desc) @@ -1623,7 +1624,13 @@ static int cmp_sevent(const void *a, const void *b) if (as->is_cpu != bs->is_cpu) return bs->is_cpu - as->is_cpu; - return strcmp(as->name, bs->name); + ret = strcmp(as->name, bs->name); + if (!ret) { + if (as->pmu && bs->pmu) + return strcmp(as->pmu, bs->pmu); + } + + return ret; } static void wordwrap(char *s, int start, int max, int corr) @@ -1652,8 +1659,24 @@ bool is_pmu_core(const char *name) return !strcmp(name, "cpu") || is_arm_pmu_core(name); } +static bool pmu_alias_is_duplicate(struct sevent *alias_a, + struct sevent *alias_b) +{ + /* Different names -> never duplicates */ + if (strcmp(alias_a->name, alias_b->name)) + return false; + + /* Don't remove duplicates for hybrid PMUs */ + if (perf_pmu__is_hybrid(alias_a->pmu) && + perf_pmu__is_hybrid(alias_b->pmu)) + return false; + + return true; +} + void print_pmu_events(const char *event_glob, bool name_only, bool quiet_flag, - bool long_desc, bool details_flag, bool deprecated) + bool long_desc, bool details_flag, bool deprecated, + const char *pmu_name) { struct perf_pmu *pmu; struct perf_pmu_alias *alias; @@ -1679,10 +1702,16 @@ void print_pmu_events(const char *event_glob, bool name_only, bool quiet_flag, pmu = NULL; j = 0; while ((pmu = perf_pmu__scan(pmu)) != NULL) { + if (pmu_name && perf_pmu__is_hybrid(pmu->name) && + strcmp(pmu_name, pmu->name)) { + continue; + } + list_for_each_entry(alias, &pmu->aliases, list) { char *name = alias->desc ? alias->name : format_alias(buf, sizeof(buf), pmu, alias); - bool is_cpu = is_pmu_core(pmu->name); + bool is_cpu = is_pmu_core(pmu->name) || + perf_pmu__is_hybrid(pmu->name); if (alias->deprecated && !deprecated) continue; @@ -1730,8 +1759,9 @@ void print_pmu_events(const char *event_glob, bool name_only, bool quiet_flag, qsort(aliases, len, sizeof(struct sevent), cmp_sevent); for (j = 0; j < len; j++) { /* Skip duplicates */ - if (j > 0 && !strcmp(aliases[j].name, aliases[j - 1].name)) + if (j > 0 && pmu_alias_is_duplicate(&aliases[j], &aliases[j - 1])) continue; + if (name_only) { printf("%s ", aliases[j].name); continue; @@ -1906,7 +1936,7 @@ int perf_pmu__caps_parse(struct perf_pmu *pmu) } void perf_pmu__warn_invalid_config(struct perf_pmu *pmu, __u64 config, - char *name) + const char *name) { struct perf_pmu_format *format; __u64 masks = 0, bits; diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c index bff669b615..007a646814 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 32a721b3e9..a5d945415b 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 c0c010350b..e752e1f4a5 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 352f16076e..498b05708d 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" @@ -44,7 +45,7 @@ static int perf_session__process_compressed_event(struct perf_session *session, size_t decomp_size, src_size; u64 decomp_last_rem = 0; size_t mmap_len, decomp_len = session->header.env.comp_mmap_len; - struct decomp *decomp, *decomp_last = session->decomp_last; + struct decomp *decomp, *decomp_last = session->active_decomp->decomp_last; if (decomp_last) { decomp_last_rem = decomp_last->size - decomp_last->head; @@ -71,7 +72,7 @@ static int perf_session__process_compressed_event(struct perf_session *session, src = (void *)event + sizeof(struct perf_record_compressed); src_size = event->pack.header.size - sizeof(struct perf_record_compressed); - decomp_size = zstd_decompress_stream(&(session->zstd_data), src, src_size, + decomp_size = zstd_decompress_stream(session->active_decomp->zstd_decomp, src, src_size, &(decomp->data[decomp_last_rem]), decomp_len - decomp_last_rem); if (!decomp_size) { munmap(decomp, mmap_len); @@ -81,13 +82,12 @@ static int perf_session__process_compressed_event(struct perf_session *session, decomp->size += decomp_size; - if (session->decomp == NULL) { - session->decomp = decomp; - session->decomp_last = decomp; - } else { - session->decomp_last->next = decomp; - session->decomp_last = decomp; - } + if (session->active_decomp->decomp == NULL) + session->active_decomp->decomp = decomp; + else + session->active_decomp->decomp_last->next = decomp; + + session->active_decomp->decomp_last = decomp; pr_debug("decomp (B): %zd to %zd\n", src_size, decomp_size); @@ -197,6 +197,8 @@ struct perf_session *__perf_session__new(struct perf_data *data, session->repipe = repipe; session->tool = tool; + session->decomp_data.zstd_decomp = &session->zstd_data; + session->active_decomp = &session->decomp_data; INIT_LIST_HEAD(&session->auxtrace_index); machines__init(&session->machines); ordered_events__init(&session->ordered_events, @@ -276,11 +278,11 @@ static void perf_session__delete_threads(struct perf_session *session) machine__delete_threads(&session->machines.host); } -static void perf_session__release_decomp_events(struct perf_session *session) +static void perf_decomp__release_events(struct decomp *next) { - struct decomp *next, *decomp; + struct decomp *decomp; size_t mmap_len; - next = session->decomp; + do { decomp = next; if (decomp == NULL) @@ -299,7 +301,7 @@ void perf_session__delete(struct perf_session *session) auxtrace_index__free(&session->auxtrace_index); perf_session__destroy_kernel_maps(session); perf_session__delete_threads(session); - perf_session__release_decomp_events(session); + perf_decomp__release_events(session->decomp_data.decomp); perf_env__exit(&session->header.env); machines__exit(&session->machines); if (session->data) { @@ -509,6 +511,8 @@ void perf_tool__fill_defaults(struct perf_tool *tool) tool->bpf = perf_event__process_bpf; if (tool->text_poke == NULL) tool->text_poke = perf_event__process_text_poke; + if (tool->aux_output_hw_id == NULL) + tool->aux_output_hw_id = perf_event__process_aux_output_hw_id; if (tool->read == NULL) tool->read = process_event_sample_stub; if (tool->throttle == NULL) @@ -1000,6 +1004,7 @@ static perf_event__swap_op perf_event__swap_ops[] = { [PERF_RECORD_NAMESPACES] = perf_event__namespaces_swap, [PERF_RECORD_CGROUP] = perf_event__cgroup_swap, [PERF_RECORD_TEXT_POKE] = perf_event__text_poke_swap, + [PERF_RECORD_AUX_OUTPUT_HW_ID] = perf_event__all64_swap, [PERF_RECORD_HEADER_ATTR] = perf_event__hdr_attr_swap, [PERF_RECORD_HEADER_EVENT_TYPE] = perf_event__event_type_swap, [PERF_RECORD_HEADER_TRACING_DATA] = perf_event__tracing_data_swap, @@ -1164,7 +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; @@ -1172,7 +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); } } @@ -1190,7 +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; @@ -1199,23 +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) @@ -1300,7 +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]; @@ -1321,10 +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); @@ -1498,11 +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); @@ -1556,6 +1562,8 @@ static int machines__deliver_event(struct machines *machines, return tool->bpf(tool, event, sample, machine); case PERF_RECORD_TEXT_POKE: return tool->text_poke(tool, event, sample, machine); + case PERF_RECORD_AUX_OUTPUT_HW_ID: + return tool->aux_output_hw_id(tool, event, sample, machine); default: ++evlist->stats.nr_unknown_events; return -1; @@ -2117,7 +2125,7 @@ static int __perf_session__process_decomp_events(struct perf_session *session) { s64 skip; u64 size; - struct decomp *decomp = session->decomp_last; + struct decomp *decomp = session->active_decomp->decomp_last; if (!decomp) return 0; @@ -2171,35 +2179,55 @@ struct reader { u64 data_offset; reader_cb_t process; bool in_place_update; + char *mmaps[NUM_MMAPS]; + size_t mmap_size; + int mmap_idx; + char *mmap_cur; + u64 file_pos; + u64 file_offset; + u64 head; + struct zstd_data zstd_data; + struct decomp_data decomp_data; }; static int -reader__process_events(struct reader *rd, struct perf_session *session, - struct ui_progress *prog) +reader__init(struct reader *rd, bool *one_mmap) { u64 data_size = rd->data_size; - u64 head, page_offset, file_offset, file_pos, size; - int err = 0, mmap_prot, mmap_flags, map_idx = 0; - size_t mmap_size; - char *buf, *mmaps[NUM_MMAPS]; - union perf_event *event; - s64 skip; - - page_offset = page_size * (rd->data_offset / page_size); - file_offset = page_offset; - head = rd->data_offset - page_offset; - - ui_progress__init_size(prog, data_size, "Processing events..."); + char **mmaps = rd->mmaps; + rd->head = rd->data_offset; data_size += rd->data_offset; - mmap_size = MMAP_SIZE; - if (mmap_size > data_size) { - mmap_size = data_size; - session->one_mmap = true; + rd->mmap_size = MMAP_SIZE; + if (rd->mmap_size > data_size) { + rd->mmap_size = data_size; + if (one_mmap) + *one_mmap = true; } - memset(mmaps, 0, sizeof(mmaps)); + memset(mmaps, 0, sizeof(rd->mmaps)); + + if (zstd_init(&rd->zstd_data, 0)) + return -1; + rd->decomp_data.zstd_decomp = &rd->zstd_data; + + return 0; +} + +static void +reader__release_decomp(struct reader *rd) +{ + perf_decomp__release_events(rd->decomp_data.decomp); + zstd_fini(&rd->zstd_data); +} + +static int +reader__mmap(struct reader *rd, struct perf_session *session) +{ + int mmap_prot, mmap_flags; + char *buf, **mmaps = rd->mmaps; + u64 page_offset; mmap_prot = PROT_READ; mmap_flags = MAP_SHARED; @@ -2210,47 +2238,63 @@ reader__process_events(struct reader *rd, struct perf_session *session, mmap_prot |= PROT_WRITE; mmap_flags = MAP_PRIVATE; } -remap: - buf = mmap(NULL, mmap_size, mmap_prot, mmap_flags, rd->fd, - file_offset); - if (buf == MAP_FAILED) { - pr_err("failed to mmap file\n"); - err = -errno; - goto out; - } - mmaps[map_idx] = buf; - map_idx = (map_idx + 1) & (ARRAY_SIZE(mmaps) - 1); - file_pos = file_offset + head; - if (session->one_mmap) { - session->one_mmap_addr = buf; - session->one_mmap_offset = file_offset; + + if (mmaps[rd->mmap_idx]) { + munmap(mmaps[rd->mmap_idx], rd->mmap_size); + mmaps[rd->mmap_idx] = NULL; } -more: - event = fetch_mmaped_event(head, mmap_size, buf, session->header.needs_swap); + page_offset = page_size * (rd->head / page_size); + rd->file_offset += page_offset; + rd->head -= page_offset; + + buf = mmap(NULL, rd->mmap_size, mmap_prot, mmap_flags, rd->fd, + rd->file_offset); + if (buf == MAP_FAILED) { + pr_err("failed to mmap file\n"); + return -errno; + } + mmaps[rd->mmap_idx] = rd->mmap_cur = buf; + rd->mmap_idx = (rd->mmap_idx + 1) & (ARRAY_SIZE(rd->mmaps) - 1); + rd->file_pos = rd->file_offset + rd->head; + if (session->one_mmap) { + session->one_mmap_addr = buf; + session->one_mmap_offset = rd->file_offset; + } + + return 0; +} + +enum { + READER_OK, + READER_NODATA, +}; + +static int +reader__read_event(struct reader *rd, struct perf_session *session, + struct ui_progress *prog) +{ + u64 size; + int err = READER_OK; + union perf_event *event; + s64 skip; + + event = fetch_mmaped_event(rd->head, rd->mmap_size, rd->mmap_cur, + session->header.needs_swap); if (IS_ERR(event)) return PTR_ERR(event); - if (!event) { - if (mmaps[map_idx]) { - munmap(mmaps[map_idx], mmap_size); - mmaps[map_idx] = NULL; - } - - page_offset = page_size * (head / page_size); - file_offset += page_offset; - head -= page_offset; - goto remap; - } + if (!event) + return READER_NODATA; size = event->header.size; skip = -EINVAL; if (size < sizeof(struct perf_event_header) || - (skip = rd->process(session, event, file_pos)) < 0) { + (skip = rd->process(session, event, rd->file_pos)) < 0) { pr_err("%#" PRIx64 " [%#x]: failed to process type: %d [%s]\n", - file_offset + head, event->header.size, + rd->file_offset + rd->head, event->header.size, event->header.type, strerror(-skip)); err = skip; goto out; @@ -2259,8 +2303,8 @@ reader__process_events(struct reader *rd, struct perf_session *session, if (skip) size += skip; - head += size; - file_pos += size; + rd->head += size; + rd->file_pos += size; err = __perf_session__process_decomp_events(session); if (err) @@ -2268,13 +2312,48 @@ reader__process_events(struct reader *rd, struct perf_session *session, ui_progress__update(prog, size); +out: + return err; +} + +static inline bool +reader__eof(struct reader *rd) +{ + return (rd->file_pos >= rd->data_size + rd->data_offset); +} + +static int +reader__process_events(struct reader *rd, struct perf_session *session, + struct ui_progress *prog) +{ + int err; + + err = reader__init(rd, &session->one_mmap); + if (err) + goto out; + + session->active_decomp = &rd->decomp_data; + +remap: + err = reader__mmap(rd, session); + if (err) + goto out; + +more: + err = reader__read_event(rd, session, prog); + if (err < 0) + goto out; + else if (err == READER_NODATA) + goto remap; + if (session_done()) goto out; - if (file_pos < data_size) + if (!reader__eof(rd)) goto more; out: + session->active_decomp = &session->decomp_data; return err; } @@ -2327,6 +2406,7 @@ static int __perf_session__process_events(struct perf_session *session) */ ordered_events__reinit(&session->ordered_events); auxtrace__free_events(session); + reader__release_decomp(&rd); session->one_mmap = false; return err; } @@ -2458,16 +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; @@ -2519,7 +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/session.h b/tools/perf/util/session.h index 5d8bd14a0a..46c854292a 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -20,6 +20,12 @@ struct thread; struct auxtrace; struct itrace_synth_opts; +struct decomp_data { + struct decomp *decomp; + struct decomp *decomp_last; + struct zstd_data *zstd_decomp; +}; + struct perf_session { struct perf_header header; struct machines machines; @@ -39,8 +45,8 @@ struct perf_session { u64 bytes_transferred; u64 bytes_compressed; struct zstd_data zstd_data; - struct decomp *decomp; - struct decomp *decomp_last; + struct decomp_data decomp_data; + struct decomp_data *active_decomp; }; struct decomp { diff --git a/tools/perf/util/smt.c b/tools/perf/util/smt.c index 34f1b1b117..2b0a36ebf2 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 a111065b48..2da081ef53 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/stat-display.c b/tools/perf/util/stat-display.c index db00ca6a67..9cbe351b14 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -4,6 +4,7 @@ #include #include #include +#include #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); } } @@ -628,25 +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. @@ -666,7 +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; @@ -696,10 +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) @@ -732,8 +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); @@ -779,7 +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; @@ -867,7 +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"); @@ -879,9 +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; } /* @@ -894,11 +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; @@ -910,8 +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); @@ -923,29 +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, @@ -1209,19 +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); } } @@ -1244,8 +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 34a7f5c1ff..10af7804e4 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -1,8 +1,10 @@ // SPDX-License-Identifier: GPL-2.0 +#include #include #include "evsel.h" #include "stat.h" #include "color.h" +#include "debug.h" #include "pmu.h" #include "rblist.h" #include "evlist.h" @@ -30,7 +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; @@ -45,8 +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. @@ -103,7 +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, @@ -113,7 +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, @@ -211,10 +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) @@ -227,7 +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; @@ -239,88 +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++; } @@ -370,12 +372,16 @@ void perf_stat__collect_metric_expr(struct evlist *evsel_list) { struct evsel *counter, *leader, **metric_events, *oc; bool found; - struct expr_parse_ctx ctx; + struct expr_parse_ctx *ctx; struct hashmap_entry *cur; size_t bkt; int i; - expr__ctx_init(&ctx); + ctx = expr__ctx_new(); + if (!ctx) { + pr_debug("expr__ctx_new failed"); + return; + } evlist__for_each_entry(evsel_list, counter) { bool invalid = false; @@ -383,25 +389,25 @@ void perf_stat__collect_metric_expr(struct evlist *evsel_list) if (!counter->metric_expr) continue; - expr__ctx_clear(&ctx); + expr__ctx_clear(ctx); metric_events = counter->metric_events; if (!metric_events) { - if (expr__find_other(counter->metric_expr, - counter->name, - &ctx, 1) < 0) + if (expr__find_ids(counter->metric_expr, + counter->name, + ctx) < 0) continue; metric_events = calloc(sizeof(struct evsel *), - hashmap__size(&ctx.ids) + 1); + hashmap__size(ctx->ids) + 1); if (!metric_events) { - expr__ctx_clear(&ctx); + expr__ctx_free(ctx); return; } counter->metric_events = metric_events; } i = 0; - hashmap__for_each_entry((&ctx.ids), cur, bkt) { + hashmap__for_each_entry(ctx->ids, cur, bkt) { const char *metric_name = (const char *)cur->key; found = false; @@ -438,6 +444,7 @@ void perf_stat__collect_metric_expr(struct evlist *evsel_list) "Add %s event to groups to get metric expression for %s\n", metric_name, counter->name); + free(printed); printed = strdup(metric_name); } invalid = true; @@ -453,16 +460,16 @@ void perf_stat__collect_metric_expr(struct evlist *evsel_list) counter->metric_expr = NULL; } } - expr__ctx_clear(&ctx); + expr__ctx_free(ctx); } 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; @@ -470,12 +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; @@ -483,7 +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) @@ -491,7 +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; @@ -506,7 +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) @@ -514,7 +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; @@ -525,7 +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) @@ -533,7 +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; @@ -544,7 +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) @@ -552,7 +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; @@ -563,7 +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) @@ -571,7 +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; @@ -581,7 +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) @@ -589,7 +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; @@ -599,7 +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) @@ -607,7 +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; @@ -617,7 +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) @@ -625,7 +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; @@ -683,61 +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); @@ -748,15 +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; @@ -768,23 +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) @@ -792,9 +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; @@ -811,51 +818,43 @@ 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; - char *n, *pn; + char *n; int i, j, ret; - expr__ctx_init(pctx); for (i = 0; metric_events[i]; i++) { struct saved_value *v; struct stats *stats; u64 metric_total = 0; + int source_count; if (!strcmp(metric_events[i]->name, "duration_time")) { stats = &walltime_nsecs_stats; 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) break; stats = &v->stats; scale = 1.0; + source_count = evsel__source_count(metric_events[i]); if (v->metric_other) metric_total = v->metric_total; } - - n = strdup(metric_events[i]->name); + n = strdup(evsel__metric_id(metric_events[i])); if (!n) return -ENOMEM; - /* - * This display code with --no-merge adds [cpu] postfixes. - * These are not supported by the parser. Remove everything - * after the space. - */ - pn = strchr(n, ' '); - if (pn) - *pn = 0; - if (metric_total) - expr__add_id_val(pctx, n, metric_total); - else - expr__add_id_val(pctx, n, avg_stats(stats)*scale); + expr__add_id_val_source_count(pctx, n, + metric_total ? : avg_stats(stats) * scale, + source_count); } for (j = 0; metric_refs && metric_refs[j].metric_name; j++) { @@ -875,22 +874,28 @@ 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) { print_metric_t print_metric = out->print_metric; - struct expr_parse_ctx pctx; + struct expr_parse_ctx *pctx; double ratio, scale; int i; void *ctxp = out->ctx; - i = prepare_metric(metric_events, metric_refs, &pctx, cpu, st); - if (i < 0) + pctx = expr__ctx_new(); + if (!pctx) return; + pctx->runtime = runtime; + i = prepare_metric(metric_events, metric_refs, pctx, cpu_map_idx, st); + if (i < 0) { + expr__ctx_free(pctx); + return; + } if (!metric_events[i]) { - if (expr__parse(&ratio, &pctx, metric_expr, runtime) == 0) { + if (expr__parse(&ratio, pctx, metric_expr) == 0) { char *unit; char metric_bf[64]; @@ -926,28 +931,32 @@ static void generic_metric(struct perf_stat_config *config, (metric_name ? metric_name : name) : "", 0); } - expr__ctx_clear(&pctx); + 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; + struct expr_parse_ctx *pctx; double ratio = 0.0; - if (prepare_metric(mexp->metric_events, mexp->metric_refs, &pctx, cpu, st) < 0) + pctx = expr__ctx_new(); + if (!pctx) + return NAN; + + 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, 1)) + if (expr__parse(&ratio, pctx, mexp->metric_expr)) ratio = 0.0; out: - expr__ctx_clear(&pctx); + expr__ctx_free(pctx); return ratio; } 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) @@ -966,7 +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; @@ -976,11 +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); @@ -990,8 +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 ( @@ -1000,8 +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 ( @@ -1010,8 +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 ( @@ -1020,8 +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 ( @@ -1030,8 +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 ( @@ -1040,27 +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; @@ -1069,7 +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, @@ -1079,8 +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; @@ -1090,19 +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; @@ -1115,28 +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; @@ -1149,14 +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) @@ -1164,8 +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) @@ -1173,8 +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) @@ -1182,8 +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) @@ -1191,11 +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; @@ -1211,11 +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; @@ -1231,11 +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; @@ -1251,11 +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; @@ -1272,12 +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); @@ -1285,7 +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; } @@ -1298,7 +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 09ea334586..ee6f034812 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/svghelper.c b/tools/perf/util/svghelper.c index 96f941e016..1e0c731fc5 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 0fc9a54107..dfde9eada2 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); } @@ -274,7 +274,7 @@ struct symbol *symbol__new(u64 start, u64 len, u8 binding, u8 type, const char * if (symbol_conf.priv_size) { if (symbol_conf.init_annotation) { struct annotation *notes = (void *)sym; - pthread_mutex_init(¬es->lock, NULL); + annotation__init(notes); } sym = ((void *)sym) + symbol_conf.priv_size; } @@ -294,6 +294,13 @@ struct symbol *symbol__new(u64 start, u64 len, u8 binding, u8 type, const char * void symbol__delete(struct symbol *sym) { + if (symbol_conf.priv_size) { + if (symbol_conf.init_annotation) { + struct annotation *notes = symbol__annotation(sym); + + annotation__exit(notes); + } + } free(((void *)sym) - symbol_conf.priv_size); } @@ -702,6 +709,10 @@ static int map__process_kallsym_symbol(void *arg, const char *name, if (!symbol_type__filter(type)) return 0; + /* Ignore local symbols for ARM modules */ + if (name[0] == '$') + return 0; + /* * module symbols are not sorted so we add all * symbols, setting length to 0, and rely on @@ -2630,3 +2641,25 @@ struct mem_info *mem_info__new(void) refcount_set(&mi->refcnt, 1); return mi; } + +/* + * Checks that user supplied symbol kernel files are accessible because + * the default mechanism for accessing elf files fails silently. i.e. if + * debug syms for a build ID aren't found perf carries on normally. When + * they are user supplied we should assume that the user doesn't want to + * silently fail. + */ +int symbol__validate_sym_arguments(void) +{ + if (symbol_conf.vmlinux_name && + access(symbol_conf.vmlinux_name, R_OK)) { + pr_err("Invalid file: %s\n", symbol_conf.vmlinux_name); + return -EINVAL; + } + if (symbol_conf.kallsyms_name && + access(symbol_conf.kallsyms_name, R_OK)) { + pr_err("Invalid file: %s\n", symbol_conf.kallsyms_name); + return -EINVAL; + } + return 0; +} diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c index a7e981b2d7..b654de0841 100644 --- a/tools/perf/util/synthetic-events.c +++ b/tools/perf/util/synthetic-events.c @@ -715,7 +715,8 @@ static int __event__synthesize_thread(union perf_event *comm_event, union perf_event *fork_event, union perf_event *namespaces_event, pid_t pid, int full, perf_event__handler_t process, - struct perf_tool *tool, struct machine *machine, bool mmap_data) + struct perf_tool *tool, struct machine *machine, + bool needs_mmap, bool mmap_data) { char filename[PATH_MAX]; struct dirent **dirent; @@ -739,7 +740,7 @@ static int __event__synthesize_thread(union perf_event *comm_event, * send mmap only for thread group leader * see thread__init_maps() */ - if (pid == tgid && + if (pid == tgid && needs_mmap && perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid, process, machine, mmap_data)) return -1; @@ -786,7 +787,7 @@ static int __event__synthesize_thread(union perf_event *comm_event, break; rc = 0; - if (_pid == pid && !kernel_thread) { + if (_pid == pid && !kernel_thread && needs_mmap) { /* process the parent's maps too */ rc = perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid, process, machine, mmap_data); @@ -806,7 +807,7 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool, struct perf_thread_map *threads, perf_event__handler_t process, struct machine *machine, - bool mmap_data) + bool needs_mmap, bool mmap_data) { union perf_event *comm_event, *mmap_event, *fork_event; union perf_event *namespaces_event; @@ -836,7 +837,7 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool, fork_event, namespaces_event, perf_thread_map__pid(threads, thread), 0, process, tool, machine, - mmap_data)) { + needs_mmap, mmap_data)) { err = -1; break; } @@ -862,7 +863,7 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool, fork_event, namespaces_event, comm_event->comm.pid, 0, process, tool, machine, - mmap_data)) { + needs_mmap, mmap_data)) { err = -1; break; } @@ -882,6 +883,7 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool, static int __perf_event__synthesize_threads(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine, + bool needs_mmap, bool mmap_data, struct dirent **dirent, int start, @@ -926,7 +928,7 @@ static int __perf_event__synthesize_threads(struct perf_tool *tool, */ __event__synthesize_thread(comm_event, mmap_event, fork_event, namespaces_event, pid, 1, process, - tool, machine, mmap_data); + tool, machine, needs_mmap, mmap_data); } err = 0; @@ -945,6 +947,7 @@ struct synthesize_threads_arg { struct perf_tool *tool; perf_event__handler_t process; struct machine *machine; + bool needs_mmap; bool mmap_data; struct dirent **dirent; int num; @@ -956,7 +959,8 @@ static void *synthesize_threads_worker(void *arg) struct synthesize_threads_arg *args = arg; __perf_event__synthesize_threads(args->tool, args->process, - args->machine, args->mmap_data, + args->machine, + args->needs_mmap, args->mmap_data, args->dirent, args->start, args->num); return NULL; @@ -965,7 +969,7 @@ static void *synthesize_threads_worker(void *arg) int perf_event__synthesize_threads(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine, - bool mmap_data, + bool needs_mmap, bool mmap_data, unsigned int nr_threads_synthesize) { struct synthesize_threads_arg *args = NULL; @@ -994,7 +998,8 @@ int perf_event__synthesize_threads(struct perf_tool *tool, if (thread_nr <= 1) { err = __perf_event__synthesize_threads(tool, process, - machine, mmap_data, + machine, + needs_mmap, mmap_data, dirent, base, n); goto free_dirent; } @@ -1015,6 +1020,7 @@ int perf_event__synthesize_threads(struct perf_tool *tool, args[i].tool = tool; args[i].process = process; args[i].machine = machine; + args[i].needs_mmap = needs_mmap; args[i].mmap_data = mmap_data; args[i].dirent = dirent; } @@ -1180,12 +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, @@ -1196,13 +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) @@ -1211,9 +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; @@ -1348,7 +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) @@ -1360,7 +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; @@ -1757,7 +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; } } @@ -1775,26 +1781,46 @@ int perf_event__synthesize_id_index(struct perf_tool *tool, perf_event__handler_ int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool, struct target *target, struct perf_thread_map *threads, - perf_event__handler_t process, bool data_mmap, - unsigned int nr_threads_synthesize) + 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, data_mmap); + return perf_event__synthesize_thread_map(tool, threads, process, machine, + needs_mmap, data_mmap); else if (target__has_cpu(target)) - return perf_event__synthesize_threads(tool, process, - machine, data_mmap, + return perf_event__synthesize_threads(tool, process, machine, + needs_mmap, data_mmap, nr_threads_synthesize); /* command specified */ return 0; } int machine__synthesize_threads(struct machine *machine, struct target *target, - struct perf_thread_map *threads, bool data_mmap, - unsigned int nr_threads_synthesize) + struct perf_thread_map *threads, bool needs_mmap, + bool data_mmap, unsigned int nr_threads_synthesize) { return __machine__synthesize_threads(machine, NULL, target, threads, - perf_event__process, data_mmap, - nr_threads_synthesize); + perf_event__process, needs_mmap, + data_mmap, nr_threads_synthesize); } static struct perf_record_event_update *event_update_event__new(size_t size, u64 type, u64 id) @@ -2230,3 +2256,31 @@ int perf_event__synthesize_for_pipe(struct perf_tool *tool, return ret; } + +int parse_synth_opt(char *synth) +{ + char *p, *q; + int ret = 0; + + if (synth == NULL) + return -1; + + for (q = synth; (p = strsep(&q, ",")); p = q) { + if (!strcasecmp(p, "no") || !strcasecmp(p, "none")) + return 0; + + if (!strcasecmp(p, "all")) + return PERF_SYNTH_ALL; + + if (!strcasecmp(p, "task")) + ret |= PERF_SYNTH_TASK; + else if (!strcasecmp(p, "mmap")) + ret |= PERF_SYNTH_TASK | PERF_SYNTH_MMAP; + else if (!strcasecmp(p, "cgroup")) + ret |= PERF_SYNTH_CGROUP; + else + return -1; + } + + return ret; +} diff --git a/tools/perf/util/synthetic-events.h b/tools/perf/util/synthetic-events.h index c845e2b9b4..78a0450db1 100644 --- a/tools/perf/util/synthetic-events.h +++ b/tools/perf/util/synthetic-events.h @@ -6,6 +6,7 @@ #include // pid_t #include #include +#include struct auxtrace_record; struct dso; @@ -27,6 +28,18 @@ struct target; union perf_event; +enum perf_record_synth { + PERF_SYNTH_TASK = 1 << 0, + PERF_SYNTH_MMAP = 1 << 1, + PERF_SYNTH_CGROUP = 1 << 2, + + /* last element */ + PERF_SYNTH_MAX = 1 << 3, +}; +#define PERF_SYNTH_ALL (PERF_SYNTH_MAX - 1) + +int parse_synth_opt(char *str); + typedef int (*perf_event__handler_t)(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct machine *machine); @@ -51,10 +64,10 @@ 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 mmap_data); -int perf_event__synthesize_threads(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine, bool mmap_data, unsigned int nr_threads_synthesize); +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); int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd, struct evlist *evlist, perf_event__handler_t process); int perf_event__synth_time_conv(const struct perf_event_mmap_page *pc, struct perf_tool *tool, perf_event__handler_t process, struct machine *machine); pid_t perf_event__synthesize_comm(struct perf_tool *tool, union perf_event *event, pid_t pid, perf_event__handler_t process, struct machine *machine); @@ -65,10 +78,10 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool, struct target *target, struct perf_thread_map *threads, - perf_event__handler_t process, bool data_mmap, + perf_event__handler_t process, bool needs_mmap, bool data_mmap, unsigned int nr_threads_synthesize); int machine__synthesize_threads(struct machine *machine, struct target *target, - struct perf_thread_map *threads, bool data_mmap, + struct perf_thread_map *threads, bool needs_mmap, bool data_mmap, unsigned int nr_threads_synthesize); #ifdef HAVE_AUXTRACE_SUPPORT diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h index bbbc0dcd46..ef873f2cc3 100644 --- a/tools/perf/util/tool.h +++ b/tools/perf/util/tool.h @@ -53,6 +53,7 @@ struct perf_tool { lost_samples, aux, itrace_start, + aux_output_hw_id, context_switch, throttle, unthrottle, diff --git a/tools/power/acpi/.gitignore b/tools/power/acpi/.gitignore index 0b319fc8bb..eada0297ef 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 a249c50ebf..5ff1d9c864 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.config b/tools/power/acpi/Makefile.config index 331f6d30f4..cd7106876a 100644 --- a/tools/power/acpi/Makefile.config +++ b/tools/power/acpi/Makefile.config @@ -69,6 +69,7 @@ KERNEL_INCLUDE := $(OUTPUT)include ACPICA_INCLUDE := $(srctree)/../../../drivers/acpi/acpica CFLAGS += -D_LINUX -I$(KERNEL_INCLUDE) -I$(ACPICA_INCLUDE) CFLAGS += $(WARNINGS) +MKDIR = mkdir ifeq ($(strip $(V)),false) QUIET=@ diff --git a/tools/power/acpi/Makefile.rules b/tools/power/acpi/Makefile.rules index 2a6c170b57..b71aada776 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) $@ @@ -21,6 +21,7 @@ $(KERNEL_INCLUDE): $(objdir)%.o: %.c $(KERNEL_INCLUDE) $(ECHO) " CC " $(subst $(OUTPUT),,$@) + $(QUIET) $(MKDIR) -p $(objdir) 2>/dev/null $(QUIET) $(CC) -c $(CFLAGS) -o $@ $< all: $(OUTPUT)$(TOOL) diff --git a/tools/power/x86/intel-speed-select/isst-config.c b/tools/power/x86/intel-speed-select/isst-config.c index bf9fd3549a..efe72fa482 100644 --- a/tools/power/x86/intel-speed-select/isst-config.c +++ b/tools/power/x86/intel-speed-select/isst-config.c @@ -15,7 +15,7 @@ struct process_cmd_struct { int arg; }; -static const char *version_str = "v1.10"; +static const char *version_str = "v1.11"; static const int supported_api_ver = 1; static struct isst_if_platform_info isst_platform_info; static char *progname; @@ -1599,6 +1599,7 @@ 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 +1616,7 @@ 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); } } diff --git a/tools/scripts/Makefile.arch b/tools/scripts/Makefile.arch index b10b7a27c3..0c6c7f4568 100644 --- a/tools/scripts/Makefile.arch +++ b/tools/scripts/Makefile.arch @@ -4,7 +4,8 @@ HOSTARCH := $(shell uname -m | sed -e s/i.86/x86/ -e s/x86_64/x86/ \ -e /arm64/!s/arm.*/arm/ -e s/sa110/arm/ \ -e s/s390x/s390/ -e s/parisc64/parisc/ \ -e s/ppc.*/powerpc/ -e s/mips.*/mips/ \ - -e s/sh[234].*/sh/ -e s/aarch64.*/arm64/ ) + -e s/sh[234].*/sh/ -e s/aarch64.*/arm64/ \ + -e s/riscv.*/riscv/) ifndef ARCH ARCH := $(HOSTARCH) diff --git a/tools/scripts/Makefile.include b/tools/scripts/Makefile.include index 071312f5eb..79d1023044 100644 --- a/tools/scripts/Makefile.include +++ b/tools/scripts/Makefile.include @@ -87,7 +87,18 @@ LLVM_STRIP ?= llvm-strip ifeq ($(CC_NO_CLANG), 1) EXTRA_WARNINGS += -Wstrict-aliasing=3 -endif + +else ifneq ($(CROSS_COMPILE),) +CLANG_CROSS_FLAGS := --target=$(notdir $(CROSS_COMPILE:%-=%)) +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 $(CROSS_COMPILE)gcc -print-sysroot) +CLANG_CROSS_FLAGS += --gcc-toolchain=$(realpath $(GCC_TOOLCHAIN_DIR)/..) +endif # GCC_TOOLCHAIN_DIR +CFLAGS += $(CLANG_CROSS_FLAGS) +AFLAGS += $(CLANG_CROSS_FLAGS) +endif # CROSS_COMPILE # Hack to avoid type-punned warnings on old systems such as RHEL5: # We should be changing CFLAGS and checking gcc version, but this diff --git a/tools/testing/kunit/kunit.py b/tools/testing/kunit/kunit.py index ac35c61f65..7a706f96f6 100644 --- a/tools/testing/kunit/kunit.py +++ b/tools/testing/kunit/kunit.py @@ -8,45 +8,64 @@ # Author: Brendan Higgins import argparse -import sys import os +import re +import sys import time assert sys.version_info >= (3, 7), "Python version is too old" -from collections import namedtuple +from dataclasses import dataclass from enum import Enum, auto -from typing import Iterable, Sequence +from typing import Any, Iterable, Sequence, List, Optional -import kunit_config import kunit_json import kunit_kernel import kunit_parser -KunitResult = namedtuple('KunitResult', ['status','result','elapsed_time']) - -KunitConfigRequest = namedtuple('KunitConfigRequest', - ['build_dir', 'make_options']) -KunitBuildRequest = namedtuple('KunitBuildRequest', - ['jobs', 'build_dir', 'alltests', - 'make_options']) -KunitExecRequest = namedtuple('KunitExecRequest', - ['timeout', 'build_dir', 'alltests', - 'filter_glob', 'kernel_args']) -KunitParseRequest = namedtuple('KunitParseRequest', - ['raw_output', 'input_data', 'build_dir', 'json']) -KunitRequest = namedtuple('KunitRequest', ['raw_output','timeout', 'jobs', - 'build_dir', 'alltests', 'filter_glob', - 'kernel_args', 'json', 'make_options']) - -KernelDirectoryPath = sys.argv[0].split('tools/testing/kunit/')[0] - class KunitStatus(Enum): SUCCESS = auto() CONFIG_FAILURE = auto() BUILD_FAILURE = auto() TEST_FAILURE = auto() +@dataclass +class KunitResult: + status: KunitStatus + result: Any + elapsed_time: float + +@dataclass +class KunitConfigRequest: + build_dir: str + make_options: Optional[List[str]] + +@dataclass +class KunitBuildRequest(KunitConfigRequest): + jobs: int + alltests: bool + +@dataclass +class KunitParseRequest: + raw_output: Optional[str] + build_dir: str + json: Optional[str] + +@dataclass +class KunitExecRequest(KunitParseRequest): + timeout: int + alltests: bool + filter_glob: str + kernel_args: Optional[List[str]] + run_isolated: Optional[str] + +@dataclass +class KunitRequest(KunitExecRequest, KunitBuildRequest): + pass + + +KernelDirectoryPath = sys.argv[0].split('tools/testing/kunit/')[0] + def get_kernel_root_path() -> str: path = sys.argv[0] if not __file__ else __file__ parts = os.path.realpath(path).split('tools/testing/kunit') @@ -91,31 +110,104 @@ def build_tests(linux: kunit_kernel.LinuxSourceTree, 'built kernel successfully', build_end - build_start) -def exec_tests(linux: kunit_kernel.LinuxSourceTree, - request: KunitExecRequest) -> KunitResult: - kunit_parser.print_with_timestamp('Starting KUnit Kernel ...') - test_start = time.time() - result = linux.run_kernel( - args=request.kernel_args, - timeout=None if request.alltests else request.timeout, - filter_glob=request.filter_glob, - build_dir=request.build_dir) +def config_and_build_tests(linux: kunit_kernel.LinuxSourceTree, + request: KunitBuildRequest) -> KunitResult: + config_result = config_tests(linux, request) + if config_result.status != KunitStatus.SUCCESS: + return config_result - test_end = time.time() + return build_tests(linux, request) - return KunitResult(KunitStatus.SUCCESS, - result, - test_end - test_start) +def _list_tests(linux: kunit_kernel.LinuxSourceTree, request: KunitExecRequest) -> List[str]: + args = ['kunit.action=list'] + if request.kernel_args: + args.extend(request.kernel_args) -def parse_tests(request: KunitParseRequest) -> KunitResult: + output = linux.run_kernel(args=args, + timeout=None if request.alltests else request.timeout, + filter_glob=request.filter_glob, + build_dir=request.build_dir) + lines = kunit_parser.extract_tap_lines(output) + # Hack! Drop the dummy TAP version header that the executor prints out. + lines.pop() + + # Filter out any extraneous non-test output that might have gotten mixed in. + return [l for l in lines if re.match('^[^\s.]+\.[^\s.]+$', l)] + +def _suites_from_test_list(tests: List[str]) -> List[str]: + """Extracts all the suites from an ordered list of tests.""" + suites = [] # type: List[str] + for t in tests: + parts = t.split('.', maxsplit=2) + if len(parts) != 2: + raise ValueError(f'internal KUnit error, test name should be of the form ".", got "{t}"') + suite, case = parts + if not suites or suites[-1] != suite: + suites.append(suite) + return suites + + + +def exec_tests(linux: kunit_kernel.LinuxSourceTree, request: KunitExecRequest) -> KunitResult: + filter_globs = [request.filter_glob] + if request.run_isolated: + tests = _list_tests(linux, request) + if request.run_isolated == 'test': + filter_globs = tests + if request.run_isolated == 'suite': + filter_globs = _suites_from_test_list(tests) + # Apply the test-part of the user's glob, if present. + if '.' in request.filter_glob: + test_glob = request.filter_glob.split('.', maxsplit=2)[1] + filter_globs = [g + '.'+ test_glob for g in filter_globs] + + test_counts = kunit_parser.TestCounts() + exec_time = 0.0 + for i, filter_glob in enumerate(filter_globs): + kunit_parser.print_with_timestamp('Starting KUnit Kernel ({}/{})...'.format(i+1, len(filter_globs))) + + test_start = time.time() + run_result = linux.run_kernel( + args=request.kernel_args, + timeout=None if request.alltests else request.timeout, + filter_glob=filter_glob, + build_dir=request.build_dir) + + result = parse_tests(request, run_result) + # run_kernel() doesn't block on the kernel exiting. + # That only happens after we get the last line of output from `run_result`. + # So exec_time here actually contains parsing + execution time, which is fine. + test_end = time.time() + exec_time += test_end - test_start + + test_counts.add_subtest_counts(result.result.counts) + + if len(filter_globs) == 1 and test_counts.crashed > 0: + bd = request.build_dir + print('The kernel seems to have crashed; you can decode the stack traces with:') + print('$ scripts/decode_stacktrace.sh {}/vmlinux {} < {} | tee {}/decoded.log | {} parse'.format( + bd, bd, kunit_kernel.get_outfile_path(bd), bd, sys.argv[0])) + + kunit_status = _map_to_overall_status(test_counts.get_status()) + return KunitResult(status=kunit_status, result=result, elapsed_time=exec_time) + +def _map_to_overall_status(test_status: kunit_parser.TestStatus) -> KunitStatus: + if test_status in (kunit_parser.TestStatus.SUCCESS, kunit_parser.TestStatus.SKIPPED): + return KunitStatus.SUCCESS + else: + return KunitStatus.TEST_FAILURE + +def parse_tests(request: KunitParseRequest, input_data: Iterable[str]) -> KunitResult: parse_start = time.time() - test_result = kunit_parser.TestResult(kunit_parser.TestStatus.SUCCESS, - [], - 'Tests not Parsed.') + test_result = kunit_parser.Test() if request.raw_output: - output: Iterable[str] = request.input_data + # Treat unparsed results as one passing test. + test_result.status = kunit_parser.TestStatus.SUCCESS + test_result.counts.passed = 1 + + output: Iterable[str] = input_data if request.raw_output == 'all': pass elif request.raw_output == 'kunit': @@ -126,12 +218,12 @@ def parse_tests(request: KunitParseRequest) -> KunitResult: print(line.rstrip()) else: - test_result = kunit_parser.parse_run_tests(request.input_data) + test_result = kunit_parser.parse_run_tests(input_data) parse_end = time.time() if request.json: json_obj = kunit_json.get_json_result( - test_result=test_result, + test=test_result, def_config='kunit_defconfig', build_dir=request.build_dir, json_path=request.json) @@ -149,31 +241,15 @@ def run_tests(linux: kunit_kernel.LinuxSourceTree, request: KunitRequest) -> KunitResult: run_start = time.time() - config_request = KunitConfigRequest(request.build_dir, - request.make_options) - config_result = config_tests(linux, config_request) + config_result = config_tests(linux, request) if config_result.status != KunitStatus.SUCCESS: return config_result - build_request = KunitBuildRequest(request.jobs, request.build_dir, - request.alltests, - request.make_options) - build_result = build_tests(linux, build_request) + build_result = build_tests(linux, request) if build_result.status != KunitStatus.SUCCESS: return build_result - exec_request = KunitExecRequest(request.timeout, request.build_dir, - request.alltests, request.filter_glob, - request.kernel_args) - exec_result = exec_tests(linux, exec_request) - if exec_result.status != KunitStatus.SUCCESS: - return exec_result - - parse_request = KunitParseRequest(request.raw_output, - exec_result.result, - request.build_dir, - request.json) - parse_result = parse_tests(parse_request) + exec_result = exec_tests(linux, request) run_end = time.time() @@ -184,7 +260,7 @@ def run_tests(linux: kunit_kernel.LinuxSourceTree, config_result.elapsed_time, build_result.elapsed_time, exec_result.elapsed_time)) - return parse_result + return exec_result # Problem: # $ kunit.py run --json @@ -206,6 +282,9 @@ def massage_argv(argv: Sequence[str]) -> Sequence[str]: return f'{arg}={pseudo_bool_flag_defaults[arg]}' return list(map(massage_arg, argv)) +def get_default_jobs() -> int: + return len(os.sched_getaffinity(0)) + def add_common_opts(parser) -> None: parser.add_argument('--build_dir', help='As in the make command, it specifies the build ' @@ -222,6 +301,10 @@ def add_common_opts(parser) -> None: ' If given a directory, (e.g. lib/kunit), "/.kunitconfig" ' 'will get automatically appended.', metavar='kunitconfig') + parser.add_argument('--kconfig_add', + help='Additional Kconfig options to append to the ' + '.kunitconfig, e.g. CONFIG_KASAN=y. Can be repeated.', + action='append') parser.add_argument('--arch', help=('Specifies the architecture to run tests under. ' @@ -252,7 +335,7 @@ def add_build_opts(parser) -> None: parser.add_argument('--jobs', help='As in the make command, "Specifies the number of ' 'jobs (commands) to run simultaneously."', - type=int, default=8, metavar='jobs') + type=int, default=get_default_jobs(), metavar='jobs') def add_exec_opts(parser) -> None: parser.add_argument('--timeout', @@ -263,9 +346,8 @@ def add_exec_opts(parser) -> None: default=300, metavar='timeout') parser.add_argument('filter_glob', - help='maximum number of seconds to allow for all tests ' - 'to run. This does not include time taken to build the ' - 'tests.', + help='Filter which KUnit test suites/tests run at ' + 'boot-time, e.g. list* or list*.*del_test', type=str, nargs='?', default='', @@ -273,6 +355,12 @@ def add_exec_opts(parser) -> None: parser.add_argument('--kernel_args', help='Kernel command-line parameters. Maybe be repeated', action='append') + parser.add_argument('--run_isolated', help='If set, boot the kernel for each ' + 'individual suite/test. This is can be useful for debugging ' + 'a non-hermetic test, one that might pass/fail based on ' + 'what ran before it.', + type=str, + choices=['suite', 'test']), def add_parse_opts(parser) -> None: parser.add_argument('--raw_output', help='If set don\'t format output from kernel. ' @@ -335,19 +423,21 @@ def main(argv, linux=None): if not linux: linux = kunit_kernel.LinuxSourceTree(cli_args.build_dir, kunitconfig_path=cli_args.kunitconfig, + kconfig_add=cli_args.kconfig_add, arch=cli_args.arch, cross_compile=cli_args.cross_compile, qemu_config_path=cli_args.qemu_config) - request = KunitRequest(cli_args.raw_output, - cli_args.timeout, - cli_args.jobs, - cli_args.build_dir, - cli_args.alltests, - cli_args.filter_glob, - cli_args.kernel_args, - cli_args.json, - cli_args.make_options) + request = KunitRequest(build_dir=cli_args.build_dir, + make_options=cli_args.make_options, + jobs=cli_args.jobs, + alltests=cli_args.alltests, + raw_output=cli_args.raw_output, + json=cli_args.json, + timeout=cli_args.timeout, + filter_glob=cli_args.filter_glob, + kernel_args=cli_args.kernel_args, + run_isolated=cli_args.run_isolated) result = run_tests(linux, request) if result.status != KunitStatus.SUCCESS: sys.exit(1) @@ -359,12 +449,13 @@ def main(argv, linux=None): if not linux: linux = kunit_kernel.LinuxSourceTree(cli_args.build_dir, kunitconfig_path=cli_args.kunitconfig, + kconfig_add=cli_args.kconfig_add, arch=cli_args.arch, cross_compile=cli_args.cross_compile, qemu_config_path=cli_args.qemu_config) - request = KunitConfigRequest(cli_args.build_dir, - cli_args.make_options) + request = KunitConfigRequest(build_dir=cli_args.build_dir, + make_options=cli_args.make_options) result = config_tests(linux, request) kunit_parser.print_with_timestamp(( 'Elapsed time: %.3fs\n') % ( @@ -375,15 +466,16 @@ def main(argv, linux=None): if not linux: linux = kunit_kernel.LinuxSourceTree(cli_args.build_dir, kunitconfig_path=cli_args.kunitconfig, + kconfig_add=cli_args.kconfig_add, arch=cli_args.arch, cross_compile=cli_args.cross_compile, qemu_config_path=cli_args.qemu_config) - request = KunitBuildRequest(cli_args.jobs, - cli_args.build_dir, - cli_args.alltests, - cli_args.make_options) - result = build_tests(linux, request) + request = KunitBuildRequest(build_dir=cli_args.build_dir, + make_options=cli_args.make_options, + jobs=cli_args.jobs, + alltests=cli_args.alltests) + result = config_and_build_tests(linux, request) kunit_parser.print_with_timestamp(( 'Elapsed time: %.3fs\n') % ( result.elapsed_time)) @@ -393,37 +485,35 @@ def main(argv, linux=None): if not linux: linux = kunit_kernel.LinuxSourceTree(cli_args.build_dir, kunitconfig_path=cli_args.kunitconfig, + kconfig_add=cli_args.kconfig_add, arch=cli_args.arch, cross_compile=cli_args.cross_compile, qemu_config_path=cli_args.qemu_config) - exec_request = KunitExecRequest(cli_args.timeout, - cli_args.build_dir, - cli_args.alltests, - cli_args.filter_glob, - cli_args.kernel_args) - exec_result = exec_tests(linux, exec_request) - parse_request = KunitParseRequest(cli_args.raw_output, - exec_result.result, - cli_args.build_dir, - cli_args.json) - result = parse_tests(parse_request) + exec_request = KunitExecRequest(raw_output=cli_args.raw_output, + build_dir=cli_args.build_dir, + json=cli_args.json, + timeout=cli_args.timeout, + alltests=cli_args.alltests, + filter_glob=cli_args.filter_glob, + kernel_args=cli_args.kernel_args, + run_isolated=cli_args.run_isolated) + result = exec_tests(linux, exec_request) kunit_parser.print_with_timestamp(( - 'Elapsed time: %.3fs\n') % ( - exec_result.elapsed_time)) + 'Elapsed time: %.3fs\n') % (result.elapsed_time)) if result.status != KunitStatus.SUCCESS: sys.exit(1) elif cli_args.subcommand == 'parse': if cli_args.file == None: + sys.stdin.reconfigure(errors='backslashreplace') # pytype: disable=attribute-error kunit_output = sys.stdin else: - with open(cli_args.file, 'r') as f: + with open(cli_args.file, 'r', errors='backslashreplace') as f: kunit_output = f.read().splitlines() - request = KunitParseRequest(cli_args.raw_output, - kunit_output, - None, - cli_args.json) - result = parse_tests(request) + request = KunitParseRequest(raw_output=cli_args.raw_output, + build_dir='', + json=cli_args.json) + result = parse_tests(request, kunit_output) if result.status != KunitStatus.SUCCESS: sys.exit(1) else: diff --git a/tools/testing/kunit/kunit_config.py b/tools/testing/kunit/kunit_config.py index c77c7d2ef6..6773545461 100644 --- a/tools/testing/kunit/kunit_config.py +++ b/tools/testing/kunit/kunit_config.py @@ -62,33 +62,34 @@ class Kconfig(object): for entry in self.entries(): f.write(str(entry) + '\n') - def parse_from_string(self, blob: str) -> None: - """Parses a string containing KconfigEntrys and populates this Kconfig.""" - self._entries = [] - is_not_set_matcher = re.compile(CONFIG_IS_NOT_SET_PATTERN) - config_matcher = re.compile(CONFIG_PATTERN) - for line in blob.split('\n'): - line = line.strip() - if not line: - continue +def parse_file(path: str) -> Kconfig: + with open(path, 'r') as f: + return parse_from_string(f.read()) - match = config_matcher.match(line) - if match: - entry = KconfigEntry(match.group(1), match.group(2)) - self.add_entry(entry) - continue +def parse_from_string(blob: str) -> Kconfig: + """Parses a string containing Kconfig entries.""" + kconfig = Kconfig() + is_not_set_matcher = re.compile(CONFIG_IS_NOT_SET_PATTERN) + config_matcher = re.compile(CONFIG_PATTERN) + for line in blob.split('\n'): + line = line.strip() + if not line: + continue - empty_match = is_not_set_matcher.match(line) - if empty_match: - entry = KconfigEntry(empty_match.group(1), 'n') - self.add_entry(entry) - continue + match = config_matcher.match(line) + if match: + entry = KconfigEntry(match.group(1), match.group(2)) + kconfig.add_entry(entry) + continue - if line[0] == '#': - continue - else: - raise KconfigParseError('Failed to parse: ' + line) + empty_match = is_not_set_matcher.match(line) + if empty_match: + entry = KconfigEntry(empty_match.group(1), 'n') + kconfig.add_entry(entry) + continue - def read_from_file(self, path: str) -> None: - with open(path, 'r') as f: - self.parse_from_string(f.read()) + if line[0] == '#': + continue + else: + raise KconfigParseError('Failed to parse: ' + line) + return kconfig diff --git a/tools/testing/kunit/kunit_json.py b/tools/testing/kunit/kunit_json.py index f5cca5c38c..6862671709 100644 --- a/tools/testing/kunit/kunit_json.py +++ b/tools/testing/kunit/kunit_json.py @@ -11,47 +11,49 @@ import os import kunit_parser -from kunit_parser import TestStatus +from kunit_parser import Test, TestStatus +from typing import Any, Dict, Optional -def get_json_result(test_result, def_config, build_dir, json_path) -> str: - sub_groups = [] +JsonObj = Dict[str, Any] - # Each test suite is mapped to a KernelCI sub_group - for test_suite in test_result.suites: - sub_group = { - "name": test_suite.name, - "arch": "UM", - "defconfig": def_config, - "build_environment": build_dir, - "test_cases": [], - "lab_name": None, - "kernel": None, - "job": None, - "git_branch": "kselftest", - } - test_cases = [] - # TODO: Add attachments attribute in test_case with detailed - # failure message, see https://api.kernelci.org/schema-test-case.html#get - for case in test_suite.cases: - test_case = {"name": case.name, "status": "FAIL"} - if case.status == TestStatus.SUCCESS: +def _get_group_json(test: Test, def_config: str, + build_dir: Optional[str]) -> JsonObj: + sub_groups = [] # List[JsonObj] + test_cases = [] # List[JsonObj] + + for subtest in test.subtests: + if len(subtest.subtests): + sub_group = _get_group_json(subtest, def_config, + build_dir) + sub_groups.append(sub_group) + else: + test_case = {"name": subtest.name, "status": "FAIL"} + if subtest.status == TestStatus.SUCCESS: test_case["status"] = "PASS" - elif case.status == TestStatus.TEST_CRASHED: + elif subtest.status == TestStatus.SKIPPED: + test_case["status"] = "SKIP" + elif subtest.status == TestStatus.TEST_CRASHED: test_case["status"] = "ERROR" test_cases.append(test_case) - sub_group["test_cases"] = test_cases - sub_groups.append(sub_group) + test_group = { - "name": "KUnit Test Group", + "name": test.name, "arch": "UM", "defconfig": def_config, "build_environment": build_dir, "sub_groups": sub_groups, + "test_cases": test_cases, "lab_name": None, "kernel": None, "job": None, "git_branch": "kselftest", } + return test_group + +def get_json_result(test: Test, def_config: str, + build_dir: Optional[str], json_path: str) -> str: + test_group = _get_group_json(test, def_config, build_dir) + test_group["name"] = "KUnit Test Group" json_obj = json.dumps(test_group, indent=4) if json_path != 'stdout': with open(json_path, 'w') as result_path: diff --git a/tools/testing/kunit/kunit_kernel.py b/tools/testing/kunit/kunit_kernel.py index 0874e512d1..3c4196cef3 100644 --- a/tools/testing/kunit/kunit_kernel.py +++ b/tools/testing/kunit/kunit_kernel.py @@ -13,11 +13,8 @@ import subprocess import os import shutil import signal -from typing import Iterator, Optional, Tuple - -from contextlib import ExitStack - -from collections import namedtuple +import threading +from typing import Iterator, List, Optional, Tuple import kunit_config import kunit_parser @@ -25,6 +22,7 @@ import qemu_config KCONFIG_PATH = '.config' KUNITCONFIG_PATH = '.kunitconfig' +OLD_KUNITCONFIG_PATH = 'last_used_kunitconfig' DEFAULT_KUNITCONFIG_PATH = 'tools/testing/kunit/configs/default.config' BROKEN_ALLCONFIG_PATH = 'tools/testing/kunit/configs/broken_on_uml.config' OUTFILE_PATH = 'test.log' @@ -104,8 +102,8 @@ class LinuxSourceTreeOperations(object): if stderr: # likely only due to build warnings print(stderr.decode()) - def run(self, params, timeout, build_dir, outfile) -> None: - pass + def start(self, params: List[str], build_dir: str) -> subprocess.Popen: + raise RuntimeError('not implemented!') class LinuxSourceTreeOperationsQemu(LinuxSourceTreeOperations): @@ -120,11 +118,10 @@ class LinuxSourceTreeOperationsQemu(LinuxSourceTreeOperations): self._extra_qemu_params = qemu_arch_params.extra_qemu_params def make_arch_qemuconfig(self, base_kunitconfig: kunit_config.Kconfig) -> None: - kconfig = kunit_config.Kconfig() - kconfig.parse_from_string(self._kconfig) + kconfig = kunit_config.parse_from_string(self._kconfig) base_kunitconfig.merge_in_entries(kconfig) - def run(self, params, timeout, build_dir, outfile): + def start(self, params: List[str], build_dir: str) -> subprocess.Popen: kernel_path = os.path.join(build_dir, self._kernel_path) qemu_command = ['qemu-system-' + self._qemu_arch, '-nodefaults', @@ -135,18 +132,11 @@ class LinuxSourceTreeOperationsQemu(LinuxSourceTreeOperations): '-nographic', '-serial stdio'] + self._extra_qemu_params print('Running tests with:\n$', ' '.join(qemu_command)) - with open(outfile, 'w') as output: - process = subprocess.Popen(' '.join(qemu_command), - stdin=subprocess.PIPE, - stdout=output, - stderr=subprocess.STDOUT, - text=True, shell=True) - try: - process.wait(timeout=timeout) - except Exception as e: - print(e) - process.terminate() - return process + return subprocess.Popen(' '.join(qemu_command), + stdin=subprocess.PIPE, + stdout=subprocess.PIPE, + stderr=subprocess.STDOUT, + text=True, shell=True, errors='backslashreplace') class LinuxSourceTreeOperationsUml(LinuxSourceTreeOperations): """An abstraction over command line operations performed on a source tree.""" @@ -169,24 +159,21 @@ class LinuxSourceTreeOperationsUml(LinuxSourceTreeOperations): process.wait() kunit_parser.print_with_timestamp( 'Disabling broken configs to run KUnit tests...') - with ExitStack() as es: - config = open(get_kconfig_path(build_dir), 'a') - disable = open(BROKEN_ALLCONFIG_PATH, 'r').read() - config.write(disable) + + with open(get_kconfig_path(build_dir), 'a') as config: + with open(BROKEN_ALLCONFIG_PATH, 'r') as disable: + config.write(disable.read()) kunit_parser.print_with_timestamp( 'Starting Kernel with all configs takes a few minutes...') - def run(self, params, timeout, build_dir, outfile): + def start(self, params: List[str], build_dir: str) -> subprocess.Popen: """Runs the Linux UML binary. Must be named 'linux'.""" linux_bin = get_file_path(build_dir, 'linux') - outfile = get_outfile_path(build_dir) - with open(outfile, 'w') as output: - process = subprocess.Popen([linux_bin] + params, - stdin=subprocess.PIPE, - stdout=output, - stderr=subprocess.STDOUT, - text=True) - process.wait(timeout) + return subprocess.Popen([linux_bin] + params, + stdin=subprocess.PIPE, + stdout=subprocess.PIPE, + stderr=subprocess.STDOUT, + text=True, errors='backslashreplace') def get_kconfig_path(build_dir) -> str: return get_file_path(build_dir, KCONFIG_PATH) @@ -194,6 +181,9 @@ def get_kconfig_path(build_dir) -> str: def get_kunitconfig_path(build_dir) -> str: return get_file_path(build_dir, KUNITCONFIG_PATH) +def get_old_kunitconfig_path(build_dir) -> str: + return get_file_path(build_dir, OLD_KUNITCONFIG_PATH) + def get_outfile_path(build_dir) -> str: return get_file_path(build_dir, OUTFILE_PATH) @@ -203,8 +193,9 @@ def get_source_tree_ops(arch: str, cross_compile: Optional[str]) -> LinuxSourceT return LinuxSourceTreeOperationsUml(cross_compile=cross_compile) elif os.path.isfile(config_path): return get_source_tree_ops_from_qemu_config(config_path, cross_compile)[1] - else: - raise ConfigError(arch + ' is not a valid arch') + + options = [f[:-3] for f in os.listdir(QEMU_CONFIGS_DIR) if f.endswith('.py')] + raise ConfigError(arch + ' is not a valid arch, options are ' + str(sorted(options))) def get_source_tree_ops_from_qemu_config(config_path: str, cross_compile: Optional[str]) -> Tuple[ @@ -219,13 +210,17 @@ def get_source_tree_ops_from_qemu_config(config_path: str, # exists as a file. module_path = '.' + os.path.join(os.path.basename(QEMU_CONFIGS_DIR), os.path.basename(config_path)) spec = importlib.util.spec_from_file_location(module_path, config_path) + assert spec is not None config = importlib.util.module_from_spec(spec) - # TODO(brendanhiggins@google.com): I looked this up and apparently other - # Python projects have noted that pytype complains that "No attribute - # 'exec_module' on _importlib_modulespec._Loader". Disabling for now. - spec.loader.exec_module(config) # pytype: disable=attribute-error - return config.QEMU_ARCH.linux_arch, LinuxSourceTreeOperationsQemu( - config.QEMU_ARCH, cross_compile=cross_compile) + # See https://github.com/python/typeshed/pull/2626 for context. + assert isinstance(spec.loader, importlib.abc.Loader) + spec.loader.exec_module(config) + + if not hasattr(config, 'QEMU_ARCH'): + raise ValueError('qemu_config module missing "QEMU_ARCH": ' + config_path) + params: qemu_config.QemuArchParams = config.QEMU_ARCH # type: ignore + return params.linux_arch, LinuxSourceTreeOperationsQemu( + params, cross_compile=cross_compile) class LinuxSourceTree(object): """Represents a Linux kernel source tree with KUnit tests.""" @@ -235,6 +230,7 @@ class LinuxSourceTree(object): build_dir: str, load_config=True, kunitconfig_path='', + kconfig_add: Optional[List[str]]=None, arch=None, cross_compile=None, qemu_config_path=None) -> None: @@ -259,8 +255,11 @@ class LinuxSourceTree(object): if not os.path.exists(kunitconfig_path): shutil.copyfile(DEFAULT_KUNITCONFIG_PATH, kunitconfig_path) - self._kconfig = kunit_config.Kconfig() - self._kconfig.read_from_file(kunitconfig_path) + self._kconfig = kunit_config.parse_file(kunitconfig_path) + if kconfig_add: + kconfig = kunit_config.parse_from_string('\n'.join(kconfig_add)) + self._kconfig.merge_in_entries(kconfig) + def clean(self) -> bool: try: @@ -272,17 +271,18 @@ class LinuxSourceTree(object): def validate_config(self, build_dir) -> bool: kconfig_path = get_kconfig_path(build_dir) - validated_kconfig = kunit_config.Kconfig() - validated_kconfig.read_from_file(kconfig_path) - if not self._kconfig.is_subset_of(validated_kconfig): - invalid = self._kconfig.entries() - validated_kconfig.entries() - message = 'Provided Kconfig is not contained in validated .config. Following fields found in kunitconfig, ' \ - 'but not in .config: %s' % ( - ', '.join([str(e) for e in invalid]) - ) - logging.error(message) - return False - return True + validated_kconfig = kunit_config.parse_file(kconfig_path) + if self._kconfig.is_subset_of(validated_kconfig): + return True + invalid = self._kconfig.entries() - validated_kconfig.entries() + message = 'Not all Kconfig options selected in kunitconfig were in the generated .config.\n' \ + 'This is probably due to unsatisfied dependencies.\n' \ + 'Missing: ' + ', '.join([str(e) for e in invalid]) + if self._arch == 'um': + message += '\nNote: many Kconfig options aren\'t available on UML. You can try running ' \ + 'on a different architecture with something like "--arch=x86_64".' + logging.error(message) + return False def build_config(self, build_dir, make_options) -> bool: kconfig_path = get_kconfig_path(build_dir) @@ -295,25 +295,38 @@ class LinuxSourceTree(object): except ConfigError as e: logging.error(e) return False - return self.validate_config(build_dir) + if not self.validate_config(build_dir): + return False + + old_path = get_old_kunitconfig_path(build_dir) + if os.path.exists(old_path): + os.remove(old_path) # write_to_file appends to the file + self._kconfig.write_to_file(old_path) + return True + + def _kunitconfig_changed(self, build_dir: str) -> bool: + old_path = get_old_kunitconfig_path(build_dir) + if not os.path.exists(old_path): + return True + + old_kconfig = kunit_config.parse_file(old_path) + return old_kconfig.entries() != self._kconfig.entries() def build_reconfig(self, build_dir, make_options) -> bool: """Creates a new .config if it is not a subset of the .kunitconfig.""" kconfig_path = get_kconfig_path(build_dir) - if os.path.exists(kconfig_path): - existing_kconfig = kunit_config.Kconfig() - existing_kconfig.read_from_file(kconfig_path) - self._ops.make_arch_qemuconfig(self._kconfig) - if not self._kconfig.is_subset_of(existing_kconfig): - print('Regenerating .config ...') - os.remove(kconfig_path) - return self.build_config(build_dir, make_options) - else: - return True - else: + if not os.path.exists(kconfig_path): print('Generating .config ...') return self.build_config(build_dir, make_options) + existing_kconfig = kunit_config.parse_file(kconfig_path) + self._ops.make_arch_qemuconfig(self._kconfig) + if self._kconfig.is_subset_of(existing_kconfig) and not self._kunitconfig_changed(build_dir): + return True + print('Regenerating .config ...') + os.remove(kconfig_path) + return self.build_config(build_dir, make_options) + def build_kernel(self, alltests, jobs, build_dir, make_options) -> bool: try: if alltests: @@ -331,12 +344,36 @@ class LinuxSourceTree(object): args.extend(['mem=1G', 'console=tty', 'kunit_shutdown=halt']) if filter_glob: args.append('kunit.filter_glob='+filter_glob) - outfile = get_outfile_path(build_dir) - self._ops.run(args, timeout, build_dir, outfile) - subprocess.call(['stty', 'sane']) - with open(outfile, 'r') as file: - for line in file: + + process = self._ops.start(args, build_dir) + assert process.stdout is not None # tell mypy it's set + + # Enforce the timeout in a background thread. + def _wait_proc(): + try: + process.wait(timeout=timeout) + except Exception as e: + print(e) + process.terminate() + process.wait() + waiter = threading.Thread(target=_wait_proc) + waiter.start() + + output = open(get_outfile_path(build_dir), 'w') + try: + # Tee the output to the file and to our caller in real time. + for line in process.stdout: + output.write(line) yield line + # This runs even if our caller doesn't consume every line. + finally: + # Flush any leftover output to the file + output.write(process.stdout.read()) + output.close() + process.stdout.close() + + waiter.join() + subprocess.call(['stty', 'sane']) def signal_handler(self, sig, frame) -> None: logging.error('Build interruption occurred. Cleaning console.') diff --git a/tools/testing/kunit/kunit_parser.py b/tools/testing/kunit/kunit_parser.py index 6310a641b1..05ff334761 100644 --- a/tools/testing/kunit/kunit_parser.py +++ b/tools/testing/kunit/kunit_parser.py @@ -1,46 +1,66 @@ # SPDX-License-Identifier: GPL-2.0 # -# Parses test results from a kernel dmesg log. +# Parses KTAP test results from a kernel dmesg log and incrementally prints +# results with reader-friendly format. Stores and returns test results in a +# Test object. # # Copyright (C) 2019, Google LLC. # Author: Felix Guo # Author: Brendan Higgins +# Author: Rae Moar +from __future__ import annotations import re -from collections import namedtuple -from datetime import datetime +import datetime from enum import Enum, auto from functools import reduce from typing import Iterable, Iterator, List, Optional, Tuple -TestResult = namedtuple('TestResult', ['status','suites','log']) +class Test(object): + """ + A class to represent a test parsed from KTAP results. All KTAP + results within a test log are stored in a main Test object as + subtests. -class TestSuite(object): + Attributes: + status : TestStatus - status of the test + name : str - name of the test + expected_count : int - expected number of subtests (0 if single + test case and None if unknown expected number of subtests) + subtests : List[Test] - list of subtests + log : List[str] - log of KTAP lines that correspond to the test + counts : TestCounts - counts of the test statuses and errors of + subtests or of the test itself if the test is a single + test case. + """ def __init__(self) -> None: - self.status = TestStatus.SUCCESS - self.name = '' - self.cases = [] # type: List[TestCase] - - def __str__(self) -> str: - return 'TestSuite(' + str(self.status) + ',' + self.name + ',' + str(self.cases) + ')' - - def __repr__(self) -> str: - return str(self) - -class TestCase(object): - def __init__(self) -> None: - self.status = TestStatus.SUCCESS + """Creates Test object with default attributes.""" + self.status = TestStatus.TEST_CRASHED self.name = '' + self.expected_count = 0 # type: Optional[int] + self.subtests = [] # type: List[Test] self.log = [] # type: List[str] + self.counts = TestCounts() def __str__(self) -> str: - return 'TestCase(' + str(self.status) + ',' + self.name + ',' + str(self.log) + ')' + """Returns string representation of a Test class object.""" + return ('Test(' + str(self.status) + ', ' + self.name + + ', ' + str(self.expected_count) + ', ' + + str(self.subtests) + ', ' + str(self.log) + ', ' + + str(self.counts) + ')') def __repr__(self) -> str: + """Returns string representation of a Test class object.""" return str(self) + def add_error(self, error_message: str) -> None: + """Records an error that occurred while parsing this test.""" + self.counts.errors += 1 + print_error('Test ' + self.name + ': ' + error_message) + class TestStatus(Enum): + """An enumeration class to represent the status of a test.""" SUCCESS = auto() FAILURE = auto() SKIPPED = auto() @@ -48,381 +68,761 @@ class TestStatus(Enum): NO_TESTS = auto() FAILURE_TO_PARSE_TESTS = auto() +class TestCounts: + """ + Tracks the counts of statuses of all test cases and any errors within + a Test. + + Attributes: + passed : int - the number of tests that have passed + failed : int - the number of tests that have failed + crashed : int - the number of tests that have crashed + skipped : int - the number of tests that have skipped + errors : int - the number of errors in the test and subtests + """ + def __init__(self): + """Creates TestCounts object with counts of all test + statuses and test errors set to 0. + """ + self.passed = 0 + self.failed = 0 + self.crashed = 0 + self.skipped = 0 + self.errors = 0 + + def __str__(self) -> str: + """Returns the string representation of a TestCounts object. + """ + return ('Passed: ' + str(self.passed) + + ', Failed: ' + str(self.failed) + + ', Crashed: ' + str(self.crashed) + + ', Skipped: ' + str(self.skipped) + + ', Errors: ' + str(self.errors)) + + def total(self) -> int: + """Returns the total number of test cases within a test + object, where a test case is a test with no subtests. + """ + return (self.passed + self.failed + self.crashed + + self.skipped) + + def add_subtest_counts(self, counts: TestCounts) -> None: + """ + Adds the counts of another TestCounts object to the current + TestCounts object. Used to add the counts of a subtest to the + parent test. + + Parameters: + counts - a different TestCounts object whose counts + will be added to the counts of the TestCounts object + """ + self.passed += counts.passed + self.failed += counts.failed + self.crashed += counts.crashed + self.skipped += counts.skipped + self.errors += counts.errors + + def get_status(self) -> TestStatus: + """Returns the aggregated status of a Test using test + counts. + """ + if self.total() == 0: + return TestStatus.NO_TESTS + elif self.crashed: + # If one of the subtests crash, the expected status + # of the Test is crashed. + return TestStatus.TEST_CRASHED + elif self.failed: + # Otherwise if one of the subtests fail, the + # expected status of the Test is failed. + return TestStatus.FAILURE + elif self.passed: + # Otherwise if one of the subtests pass, the + # expected status of the Test is passed. + return TestStatus.SUCCESS + else: + # Finally, if none of the subtests have failed, + # crashed, or passed, the expected status of the + # Test is skipped. + return TestStatus.SKIPPED + + def add_status(self, status: TestStatus) -> None: + """ + Increments count of inputted status. + + Parameters: + status - status to be added to the TestCounts object + """ + if status == TestStatus.SUCCESS: + self.passed += 1 + elif status == TestStatus.FAILURE: + self.failed += 1 + elif status == TestStatus.SKIPPED: + self.skipped += 1 + elif status != TestStatus.NO_TESTS: + self.crashed += 1 + class LineStream: - """Provides a peek()/pop() interface over an iterator of (line#, text).""" + """ + A class to represent the lines of kernel output. + Provides a lazy peek()/pop() interface over an iterator of + (line#, text). + """ _lines: Iterator[Tuple[int, str]] _next: Tuple[int, str] + _need_next: bool _done: bool def __init__(self, lines: Iterator[Tuple[int, str]]): + """Creates a new LineStream that wraps the given iterator.""" self._lines = lines self._done = False + self._need_next = True self._next = (0, '') - self._get_next() def _get_next(self) -> None: + """Advances the LineSteam to the next line, if necessary.""" + if not self._need_next: + return try: self._next = next(self._lines) except StopIteration: self._done = True + finally: + self._need_next = False def peek(self) -> str: + """Returns the current line, without advancing the LineStream. + """ + self._get_next() return self._next[1] def pop(self) -> str: - n = self._next - self._get_next() - return n[1] + """Returns the current line and advances the LineStream to + the next line. + """ + s = self.peek() + if self._done: + raise ValueError(f'LineStream: going past EOF, last line was {s}') + self._need_next = True + return s def __bool__(self) -> bool: + """Returns True if stream has more lines.""" + self._get_next() return not self._done # Only used by kunit_tool_test.py. def __iter__(self) -> Iterator[str]: + """Empties all lines stored in LineStream object into + Iterator object and returns the Iterator object. + """ while bool(self): yield self.pop() def line_number(self) -> int: + """Returns the line number of the current line.""" + self._get_next() return self._next[0] -kunit_start_re = re.compile(r'TAP version [0-9]+$') -kunit_end_re = re.compile('(List of all partitions:|' - 'Kernel panic - not syncing: VFS:|reboot: System halted)') +# Parsing helper methods: + +KTAP_START = re.compile(r'KTAP version ([0-9]+)$') +TAP_START = re.compile(r'TAP version ([0-9]+)$') +KTAP_END = re.compile('(List of all partitions:|' + 'Kernel panic - not syncing: VFS:|reboot: System halted)') def extract_tap_lines(kernel_output: Iterable[str]) -> LineStream: - def isolate_kunit_output(kernel_output: Iterable[str]) -> Iterator[Tuple[int, str]]: + """Extracts KTAP lines from the kernel output.""" + def isolate_ktap_output(kernel_output: Iterable[str]) \ + -> Iterator[Tuple[int, str]]: line_num = 0 started = False for line in kernel_output: line_num += 1 - line = line.rstrip() # line always has a trailing \n - if kunit_start_re.search(line): + line = line.rstrip() # remove trailing \n + if not started and KTAP_START.search(line): + # start extracting KTAP lines and set prefix + # to number of characters before version line + prefix_len = len( + line.split('KTAP version')[0]) + started = True + yield line_num, line[prefix_len:] + elif not started and TAP_START.search(line): + # start extracting KTAP lines and set prefix + # to number of characters before version line prefix_len = len(line.split('TAP version')[0]) started = True yield line_num, line[prefix_len:] - elif kunit_end_re.search(line): + elif started and KTAP_END.search(line): + # stop extracting KTAP lines break elif started: - yield line_num, line[prefix_len:] - return LineStream(lines=isolate_kunit_output(kernel_output)) + # remove prefix and any indention and yield + # line with line number + line = line[prefix_len:].lstrip() + yield line_num, line + return LineStream(lines=isolate_ktap_output(kernel_output)) + +KTAP_VERSIONS = [1] +TAP_VERSIONS = [13, 14] + +def check_version(version_num: int, accepted_versions: List[int], + version_type: str, test: Test) -> None: + """ + Adds error to test object if version number is too high or too + low. + + Parameters: + version_num - The inputted version number from the parsed KTAP or TAP + header line + accepted_version - List of accepted KTAP or TAP versions + version_type - 'KTAP' or 'TAP' depending on the type of + version line. + test - Test object for current test being parsed + """ + if version_num < min(accepted_versions): + test.add_error(version_type + + ' version lower than expected!') + elif version_num > max(accepted_versions): + test.add_error( + version_type + ' version higher than expected!') + +def parse_ktap_header(lines: LineStream, test: Test) -> bool: + """ + Parses KTAP/TAP header line and checks version number. + Returns False if fails to parse KTAP/TAP header line. + + Accepted formats: + - 'KTAP version [version number]' + - 'TAP version [version number]' + + Parameters: + lines - LineStream of KTAP output to parse + test - Test object for current test being parsed + + Return: + True if successfully parsed KTAP/TAP header line + """ + ktap_match = KTAP_START.match(lines.peek()) + tap_match = TAP_START.match(lines.peek()) + if ktap_match: + version_num = int(ktap_match.group(1)) + check_version(version_num, KTAP_VERSIONS, 'KTAP', test) + elif tap_match: + version_num = int(tap_match.group(1)) + check_version(version_num, TAP_VERSIONS, 'TAP', test) + else: + return False + test.log.append(lines.pop()) + return True + +TEST_HEADER = re.compile(r'^# Subtest: (.*)$') + +def parse_test_header(lines: LineStream, test: Test) -> bool: + """ + Parses test header and stores test name in test object. + Returns False if fails to parse test header line. + + Accepted format: + - '# Subtest: [test name]' + + Parameters: + lines - LineStream of KTAP output to parse + test - Test object for current test being parsed + + Return: + True if successfully parsed test header line + """ + match = TEST_HEADER.match(lines.peek()) + if not match: + return False + test.log.append(lines.pop()) + test.name = match.group(1) + return True + +TEST_PLAN = re.compile(r'1\.\.([0-9]+)') + +def parse_test_plan(lines: LineStream, test: Test) -> bool: + """ + Parses test plan line and stores the expected number of subtests in + test object. Reports an error if expected count is 0. + Returns False and sets expected_count to None if there is no valid test + plan. + + Accepted format: + - '1..[number of subtests]' + + Parameters: + lines - LineStream of KTAP output to parse + test - Test object for current test being parsed + + Return: + True if successfully parsed test plan line + """ + match = TEST_PLAN.match(lines.peek()) + if not match: + test.expected_count = None + return False + test.log.append(lines.pop()) + expected_count = int(match.group(1)) + test.expected_count = expected_count + return True + +TEST_RESULT = re.compile(r'^(ok|not ok) ([0-9]+) (- )?([^#]*)( # .*)?$') + +TEST_RESULT_SKIP = re.compile(r'^(ok|not ok) ([0-9]+) (- )?(.*) # SKIP(.*)$') + +def peek_test_name_match(lines: LineStream, test: Test) -> bool: + """ + Matches current line with the format of a test result line and checks + if the name matches the name of the current test. + Returns False if fails to match format or name. + + Accepted format: + - '[ok|not ok] [test number] [-] [test name] [optional skip + directive]' + + Parameters: + lines - LineStream of KTAP output to parse + test - Test object for current test being parsed + + Return: + True if matched a test result line and the name matching the + expected test name + """ + line = lines.peek() + match = TEST_RESULT.match(line) + if not match: + return False + name = match.group(4) + return (name == test.name) + +def parse_test_result(lines: LineStream, test: Test, + expected_num: int) -> bool: + """ + Parses test result line and stores the status and name in the test + object. Reports an error if the test number does not match expected + test number. + Returns False if fails to parse test result line. + + Note that the SKIP directive is the only direction that causes a + change in status. + + Accepted format: + - '[ok|not ok] [test number] [-] [test name] [optional skip + directive]' + + Parameters: + lines - LineStream of KTAP output to parse + test - Test object for current test being parsed + expected_num - expected test number for current test + + Return: + True if successfully parsed a test result line. + """ + line = lines.peek() + match = TEST_RESULT.match(line) + skip_match = TEST_RESULT_SKIP.match(line) + + # Check if line matches test result line format + if not match: + return False + test.log.append(lines.pop()) + + # Set name of test object + if skip_match: + test.name = skip_match.group(4) + else: + test.name = match.group(4) + + # Check test num + num = int(match.group(2)) + if num != expected_num: + test.add_error('Expected test number ' + + str(expected_num) + ' but found ' + str(num)) + + # Set status of test object + status = match.group(1) + if skip_match: + test.status = TestStatus.SKIPPED + elif status == 'ok': + test.status = TestStatus.SUCCESS + else: + test.status = TestStatus.FAILURE + return True + +def parse_diagnostic(lines: LineStream) -> List[str]: + """ + Parse lines that do not match the format of a test result line or + test header line and returns them in list. + + Line formats that are not parsed: + - '# Subtest: [test name]' + - '[ok|not ok] [test number] [-] [test name] [optional skip + directive]' + + Parameters: + lines - LineStream of KTAP output to parse + + Return: + Log of diagnostic lines + """ + log = [] # type: List[str] + while lines and not TEST_RESULT.match(lines.peek()) and not \ + TEST_HEADER.match(lines.peek()): + log.append(lines.pop()) + return log + +DIAGNOSTIC_CRASH_MESSAGE = re.compile(r'^# .*?: kunit test case crashed!$') + +def parse_crash_in_log(test: Test) -> bool: + """ + Iterate through the lines of the log to parse for crash message. + If crash message found, set status to crashed and return True. + Otherwise return False. + + Parameters: + test - Test object for current test being parsed + + Return: + True if crash message found in log + """ + for line in test.log: + if DIAGNOSTIC_CRASH_MESSAGE.match(line): + test.status = TestStatus.TEST_CRASHED + return True + return False + + +# Printing helper methods: DIVIDER = '=' * 60 RESET = '\033[0;0m' -def red(text) -> str: +def red(text: str) -> str: + """Returns inputted string with red color code.""" return '\033[1;31m' + text + RESET -def yellow(text) -> str: +def yellow(text: str) -> str: + """Returns inputted string with yellow color code.""" return '\033[1;33m' + text + RESET -def green(text) -> str: +def green(text: str) -> str: + """Returns inputted string with green color code.""" return '\033[1;32m' + text + RESET -def print_with_timestamp(message) -> None: - print('[%s] %s' % (datetime.now().strftime('%H:%M:%S'), message)) +ANSI_LEN = len(red('')) -def format_suite_divider(message) -> str: - return '======== ' + message + ' ========' +def print_with_timestamp(message: str) -> None: + """Prints message with timestamp at beginning.""" + print('[%s] %s' % (datetime.datetime.now().strftime('%H:%M:%S'), message)) -def print_suite_divider(message) -> None: - print_with_timestamp(DIVIDER) - print_with_timestamp(format_suite_divider(message)) +def format_test_divider(message: str, len_message: int) -> str: + """ + Returns string with message centered in fixed width divider. -def print_log(log) -> None: + Example: + '===================== message example =====================' + + Parameters: + message - message to be centered in divider line + len_message - length of the message to be printed such that + any characters of the color codes are not counted + + Return: + String containing message centered in fixed width divider + """ + default_count = 3 # default number of dashes + len_1 = default_count + len_2 = default_count + difference = len(DIVIDER) - len_message - 2 # 2 spaces added + if difference > 0: + # calculate number of dashes for each side of the divider + len_1 = int(difference / 2) + len_2 = difference - len_1 + return ('=' * len_1) + ' ' + message + ' ' + ('=' * len_2) + +def print_test_header(test: Test) -> None: + """ + Prints test header with test name and optionally the expected number + of subtests. + + Example: + '=================== example (2 subtests) ===================' + + Parameters: + test - Test object representing current test being printed + """ + message = test.name + if test.expected_count: + if test.expected_count == 1: + message += (' (' + str(test.expected_count) + + ' subtest)') + else: + message += (' (' + str(test.expected_count) + + ' subtests)') + print_with_timestamp(format_test_divider(message, len(message))) + +def print_log(log: Iterable[str]) -> None: + """ + Prints all strings in saved log for test in yellow. + + Parameters: + log - Iterable object with all strings saved in log for test + """ for m in log: - print_with_timestamp(m) + print_with_timestamp(yellow(m)) -TAP_ENTRIES = re.compile(r'^(TAP|[\s]*ok|[\s]*not ok|[\s]*[0-9]+\.\.[0-9]+|[\s]*# (Subtest:|.*: kunit test case crashed!)).*$') +def format_test_result(test: Test) -> str: + """ + Returns string with formatted test result with colored status and test + name. -def consume_non_diagnostic(lines: LineStream) -> None: - while lines and not TAP_ENTRIES.match(lines.peek()): - lines.pop() + Example: + '[PASSED] example' -def save_non_diagnostic(lines: LineStream, test_case: TestCase) -> None: - while lines and not TAP_ENTRIES.match(lines.peek()): - test_case.log.append(lines.peek()) - lines.pop() + Parameters: + test - Test object representing current test being printed -OkNotOkResult = namedtuple('OkNotOkResult', ['is_ok','description', 'text']) - -OK_NOT_OK_SKIP = re.compile(r'^[\s]*(ok|not ok) [0-9]+ - (.*) # SKIP(.*)$') - -OK_NOT_OK_SUBTEST = re.compile(r'^[\s]+(ok|not ok) [0-9]+ - (.*)$') - -OK_NOT_OK_MODULE = re.compile(r'^(ok|not ok) ([0-9]+) - (.*)$') - -def parse_ok_not_ok_test_case(lines: LineStream, test_case: TestCase) -> bool: - save_non_diagnostic(lines, test_case) - if not lines: - test_case.status = TestStatus.TEST_CRASHED - return True - line = lines.peek() - match = OK_NOT_OK_SUBTEST.match(line) - while not match and lines: - line = lines.pop() - match = OK_NOT_OK_SUBTEST.match(line) - if match: - test_case.log.append(lines.pop()) - test_case.name = match.group(2) - skip_match = OK_NOT_OK_SKIP.match(line) - if skip_match: - test_case.status = TestStatus.SKIPPED - return True - if test_case.status == TestStatus.TEST_CRASHED: - return True - if match.group(1) == 'ok': - test_case.status = TestStatus.SUCCESS - else: - test_case.status = TestStatus.FAILURE - return True + Return: + String containing formatted test result + """ + if test.status == TestStatus.SUCCESS: + return (green('[PASSED] ') + test.name) + elif test.status == TestStatus.SKIPPED: + return (yellow('[SKIPPED] ') + test.name) + elif test.status == TestStatus.NO_TESTS: + return (yellow('[NO TESTS RUN] ') + test.name) + elif test.status == TestStatus.TEST_CRASHED: + print_log(test.log) + return (red('[CRASHED] ') + test.name) else: - return False + print_log(test.log) + return (red('[FAILED] ') + test.name) -SUBTEST_DIAGNOSTIC = re.compile(r'^[\s]+# (.*)$') -DIAGNOSTIC_CRASH_MESSAGE = re.compile(r'^[\s]+# .*?: kunit test case crashed!$') +def print_test_result(test: Test) -> None: + """ + Prints result line with status of test. -def parse_diagnostic(lines: LineStream, test_case: TestCase) -> bool: - save_non_diagnostic(lines, test_case) - if not lines: - return False - line = lines.peek() - match = SUBTEST_DIAGNOSTIC.match(line) - if match: - test_case.log.append(lines.pop()) - crash_match = DIAGNOSTIC_CRASH_MESSAGE.match(line) - if crash_match: - test_case.status = TestStatus.TEST_CRASHED - return True + Example: + '[PASSED] example' + + Parameters: + test - Test object representing current test being printed + """ + print_with_timestamp(format_test_result(test)) + +def print_test_footer(test: Test) -> None: + """ + Prints test footer with status of test. + + Example: + '===================== [PASSED] example =====================' + + Parameters: + test - Test object representing current test being printed + """ + message = format_test_result(test) + print_with_timestamp(format_test_divider(message, + len(message) - ANSI_LEN)) + +def print_summary_line(test: Test) -> None: + """ + Prints summary line of test object. Color of line is dependent on + status of test. Color is green if test passes, yellow if test is + skipped, and red if the test fails or crashes. Summary line contains + counts of the statuses of the tests subtests or the test itself if it + has no subtests. + + Example: + "Testing complete. Passed: 2, Failed: 0, Crashed: 0, Skipped: 0, + Errors: 0" + + test - Test object representing current test being printed + """ + if test.status == TestStatus.SUCCESS: + color = green + elif test.status == TestStatus.SKIPPED or test.status == TestStatus.NO_TESTS: + color = yellow else: - return False + color = red + counts = test.counts + print_with_timestamp(color('Testing complete. ' + str(counts))) -def parse_test_case(lines: LineStream) -> Optional[TestCase]: - test_case = TestCase() - save_non_diagnostic(lines, test_case) - while parse_diagnostic(lines, test_case): - pass - if parse_ok_not_ok_test_case(lines, test_case): - return test_case +def print_error(error_message: str) -> None: + """ + Prints error message with error format. + + Example: + "[ERROR] Test example: missing test plan!" + + Parameters: + error_message - message describing error + """ + print_with_timestamp(red('[ERROR] ') + error_message) + +# Other methods: + +def bubble_up_test_results(test: Test) -> None: + """ + If the test has subtests, add the test counts of the subtests to the + test and check if any of the tests crashed and if so set the test + status to crashed. Otherwise if the test has no subtests add the + status of the test to the test counts. + + Parameters: + test - Test object for current test being parsed + """ + parse_crash_in_log(test) + subtests = test.subtests + counts = test.counts + status = test.status + for t in subtests: + counts.add_subtest_counts(t.counts) + if counts.total() == 0: + counts.add_status(status) + elif test.counts.get_status() == TestStatus.TEST_CRASHED: + test.status = TestStatus.TEST_CRASHED + +def parse_test(lines: LineStream, expected_num: int, log: List[str]) -> Test: + """ + Finds next test to parse in LineStream, creates new Test object, + parses any subtests of the test, populates Test object with all + information (status, name) about the test and the Test objects for + any subtests, and then returns the Test object. The method accepts + three formats of tests: + + Accepted test formats: + + - Main KTAP/TAP header + + Example: + + KTAP version 1 + 1..4 + [subtests] + + - Subtest header line + + Example: + + # Subtest: name + 1..3 + [subtests] + ok 1 name + + - Test result line + + Example: + + ok 1 - test + + Parameters: + lines - LineStream of KTAP output to parse + expected_num - expected test number for test to be parsed + log - list of strings containing any preceding diagnostic lines + corresponding to the current test + + Return: + Test object populated with characteristics and any subtests + """ + test = Test() + test.log.extend(log) + parent_test = False + main = parse_ktap_header(lines, test) + if main: + # If KTAP/TAP header is found, attempt to parse + # test plan + test.name = "main" + parse_test_plan(lines, test) + parent_test = True else: - return None - -SUBTEST_HEADER = re.compile(r'^[\s]+# Subtest: (.*)$') - -def parse_subtest_header(lines: LineStream) -> Optional[str]: - consume_non_diagnostic(lines) - if not lines: - return None - match = SUBTEST_HEADER.match(lines.peek()) - if match: - lines.pop() - return match.group(1) - else: - return None - -SUBTEST_PLAN = re.compile(r'[\s]+[0-9]+\.\.([0-9]+)') - -def parse_subtest_plan(lines: LineStream) -> Optional[int]: - consume_non_diagnostic(lines) - match = SUBTEST_PLAN.match(lines.peek()) - if match: - lines.pop() - return int(match.group(1)) - else: - return None - -def max_status(left: TestStatus, right: TestStatus) -> TestStatus: - if left == right: - return left - elif left == TestStatus.TEST_CRASHED or right == TestStatus.TEST_CRASHED: - return TestStatus.TEST_CRASHED - elif left == TestStatus.FAILURE or right == TestStatus.FAILURE: - return TestStatus.FAILURE - elif left == TestStatus.SKIPPED: - return right - else: - return left - -def parse_ok_not_ok_test_suite(lines: LineStream, - test_suite: TestSuite, - expected_suite_index: int) -> bool: - consume_non_diagnostic(lines) - if not lines: - test_suite.status = TestStatus.TEST_CRASHED - return False - line = lines.peek() - match = OK_NOT_OK_MODULE.match(line) - if match: - lines.pop() - if match.group(1) == 'ok': - test_suite.status = TestStatus.SUCCESS - else: - test_suite.status = TestStatus.FAILURE - skip_match = OK_NOT_OK_SKIP.match(line) - if skip_match: - test_suite.status = TestStatus.SKIPPED - suite_index = int(match.group(2)) - if suite_index != expected_suite_index: - print_with_timestamp( - red('[ERROR] ') + 'expected_suite_index ' + - str(expected_suite_index) + ', but got ' + - str(suite_index)) - return True - else: - return False - -def bubble_up_errors(status_list: Iterable[TestStatus]) -> TestStatus: - return reduce(max_status, status_list, TestStatus.SKIPPED) - -def bubble_up_test_case_errors(test_suite: TestSuite) -> TestStatus: - max_test_case_status = bubble_up_errors(x.status for x in test_suite.cases) - return max_status(max_test_case_status, test_suite.status) - -def parse_test_suite(lines: LineStream, expected_suite_index: int) -> Optional[TestSuite]: - if not lines: - return None - consume_non_diagnostic(lines) - test_suite = TestSuite() - test_suite.status = TestStatus.SUCCESS - name = parse_subtest_header(lines) - if not name: - return None - test_suite.name = name - expected_test_case_num = parse_subtest_plan(lines) - if expected_test_case_num is None: - return None - while expected_test_case_num > 0: - test_case = parse_test_case(lines) - if not test_case: - break - test_suite.cases.append(test_case) - expected_test_case_num -= 1 - if parse_ok_not_ok_test_suite(lines, test_suite, expected_suite_index): - test_suite.status = bubble_up_test_case_errors(test_suite) - return test_suite - elif not lines: - print_with_timestamp(red('[ERROR] ') + 'ran out of lines before end token') - return test_suite - else: - print(f'failed to parse end of suite "{name}", at line {lines.line_number()}: {lines.peek()}') - return None - -TAP_HEADER = re.compile(r'^TAP version 14$') - -def parse_tap_header(lines: LineStream) -> bool: - consume_non_diagnostic(lines) - if TAP_HEADER.match(lines.peek()): - lines.pop() - return True - else: - return False - -TEST_PLAN = re.compile(r'[0-9]+\.\.([0-9]+)') - -def parse_test_plan(lines: LineStream) -> Optional[int]: - consume_non_diagnostic(lines) - match = TEST_PLAN.match(lines.peek()) - if match: - lines.pop() - return int(match.group(1)) - else: - return None - -def bubble_up_suite_errors(test_suites: Iterable[TestSuite]) -> TestStatus: - return bubble_up_errors(x.status for x in test_suites) - -def parse_test_result(lines: LineStream) -> TestResult: - consume_non_diagnostic(lines) - if not lines or not parse_tap_header(lines): - return TestResult(TestStatus.FAILURE_TO_PARSE_TESTS, [], lines) - expected_test_suite_num = parse_test_plan(lines) - if expected_test_suite_num == 0: - return TestResult(TestStatus.NO_TESTS, [], lines) - elif expected_test_suite_num is None: - return TestResult(TestStatus.FAILURE_TO_PARSE_TESTS, [], lines) - test_suites = [] - for i in range(1, expected_test_suite_num + 1): - test_suite = parse_test_suite(lines, i) - if test_suite: - test_suites.append(test_suite) - else: - print_with_timestamp( - red('[ERROR] ') + ' expected ' + - str(expected_test_suite_num) + - ' test suites, but got ' + str(i - 2)) - break - test_suite = parse_test_suite(lines, -1) - if test_suite: - print_with_timestamp(red('[ERROR] ') + - 'got unexpected test suite: ' + test_suite.name) - if test_suites: - return TestResult(bubble_up_suite_errors(test_suites), test_suites, lines) - else: - return TestResult(TestStatus.NO_TESTS, [], lines) - -class TestCounts: - passed: int - failed: int - crashed: int - skipped: int - - def __init__(self): - self.passed = 0 - self.failed = 0 - self.crashed = 0 - self.skipped = 0 - - def total(self) -> int: - return self.passed + self.failed + self.crashed + self.skipped - -def print_and_count_results(test_result: TestResult) -> TestCounts: - counts = TestCounts() - for test_suite in test_result.suites: - if test_suite.status == TestStatus.SUCCESS: - print_suite_divider(green('[PASSED] ') + test_suite.name) - elif test_suite.status == TestStatus.SKIPPED: - print_suite_divider(yellow('[SKIPPED] ') + test_suite.name) - elif test_suite.status == TestStatus.TEST_CRASHED: - print_suite_divider(red('[CRASHED] ' + test_suite.name)) - else: - print_suite_divider(red('[FAILED] ') + test_suite.name) - for test_case in test_suite.cases: - if test_case.status == TestStatus.SUCCESS: - counts.passed += 1 - print_with_timestamp(green('[PASSED] ') + test_case.name) - elif test_case.status == TestStatus.SKIPPED: - counts.skipped += 1 - print_with_timestamp(yellow('[SKIPPED] ') + test_case.name) - elif test_case.status == TestStatus.TEST_CRASHED: - counts.crashed += 1 - print_with_timestamp(red('[CRASHED] ' + test_case.name)) - print_log(map(yellow, test_case.log)) - print_with_timestamp('') + # If KTAP/TAP header is not found, test must be subtest + # header or test result line so parse attempt to parser + # subtest header + parent_test = parse_test_header(lines, test) + if parent_test: + # If subtest header is found, attempt to parse + # test plan and print header + parse_test_plan(lines, test) + print_test_header(test) + expected_count = test.expected_count + subtests = [] + test_num = 1 + while parent_test and (expected_count is None or test_num <= expected_count): + # Loop to parse any subtests. + # Break after parsing expected number of tests or + # if expected number of tests is unknown break when test + # result line with matching name to subtest header is found + # or no more lines in stream. + sub_log = parse_diagnostic(lines) + sub_test = Test() + if not lines or (peek_test_name_match(lines, test) and + not main): + if expected_count and test_num <= expected_count: + # If parser reaches end of test before + # parsing expected number of subtests, print + # crashed subtest and record error + test.add_error('missing expected subtest!') + sub_test.log.extend(sub_log) + test.counts.add_status( + TestStatus.TEST_CRASHED) + print_test_result(sub_test) else: - counts.failed += 1 - print_with_timestamp(red('[FAILED] ') + test_case.name) - print_log(map(yellow, test_case.log)) - print_with_timestamp('') - return counts + test.log.extend(sub_log) + break + else: + sub_test = parse_test(lines, test_num, sub_log) + subtests.append(sub_test) + test_num += 1 + test.subtests = subtests + if not main: + # If not main test, look for test result line + test.log.extend(parse_diagnostic(lines)) + if (parent_test and peek_test_name_match(lines, test)) or \ + not parent_test: + parse_test_result(lines, test, expected_num) + else: + test.add_error('missing subtest result line!') -def parse_run_tests(kernel_output: Iterable[str]) -> TestResult: - counts = TestCounts() - lines = extract_tap_lines(kernel_output) - test_result = parse_test_result(lines) - if test_result.status == TestStatus.NO_TESTS: - print(red('[ERROR] ') + yellow('no tests run!')) - elif test_result.status == TestStatus.FAILURE_TO_PARSE_TESTS: - print(red('[ERROR] ') + yellow('could not parse test results!')) - else: - counts = print_and_count_results(test_result) + # Check for there being no tests + if parent_test and len(subtests) == 0: + test.status = TestStatus.NO_TESTS + test.add_error('0 tests run!') + + # Add statuses to TestCounts attribute in Test object + bubble_up_test_results(test) + if parent_test and not main: + # If test has subtests and is not the main test object, print + # footer. + print_test_footer(test) + elif not main: + print_test_result(test) + return test + +def parse_run_tests(kernel_output: Iterable[str]) -> Test: + """ + Using kernel output, extract KTAP lines, parse the lines for test + results and print condensed test results and summary line . + + Parameters: + kernel_output - Iterable object contains lines of kernel output + + Return: + Test - the main test object with all subtests. + """ print_with_timestamp(DIVIDER) - if test_result.status == TestStatus.SUCCESS: - fmt = green - elif test_result.status == TestStatus.SKIPPED: - fmt = yellow + lines = extract_tap_lines(kernel_output) + test = Test() + if not lines: + test.add_error('invalid KTAP input!') + test.status = TestStatus.FAILURE_TO_PARSE_TESTS else: - fmt =red - print_with_timestamp( - fmt('Testing complete. %d tests run. %d failed. %d crashed. %d skipped.' % - (counts.total(), counts.failed, counts.crashed, counts.skipped))) - return test_result + test = parse_test(lines, 0, []) + if test.status != TestStatus.NO_TESTS: + test.status = test.counts.get_status() + print_with_timestamp(DIVIDER) + print_summary_line(test) + return test diff --git a/tools/testing/kunit/kunit_tool_test.py b/tools/testing/kunit/kunit_tool_test.py index 1edcc8373b..352369dffb 100644 --- a/tools/testing/kunit/kunit_tool_test.py +++ b/tools/testing/kunit/kunit_tool_test.py @@ -13,8 +13,10 @@ import tempfile, shutil # Handling test_tmpdir import itertools import json -import signal import os +import signal +import subprocess +from typing import Iterable import kunit_config import kunit_parser @@ -49,10 +51,9 @@ class KconfigTest(unittest.TestCase): self.assertFalse(kconfig1.is_subset_of(kconfig0)) def test_read_from_file(self): - kconfig = kunit_config.Kconfig() kconfig_path = test_data_path('test_read_from_file.kconfig') - kconfig.read_from_file(kconfig_path) + kconfig = kunit_config.parse_file(kconfig_path) expected_kconfig = kunit_config.Kconfig() expected_kconfig.add_entry( @@ -85,8 +86,7 @@ class KconfigTest(unittest.TestCase): expected_kconfig.write_to_file(kconfig_path) - actual_kconfig = kunit_config.Kconfig() - actual_kconfig.read_from_file(kconfig_path) + actual_kconfig = kunit_config.parse_file(kconfig_path) self.assertEqual(actual_kconfig.entries(), expected_kconfig.entries()) @@ -106,10 +106,10 @@ class KUnitParserTest(unittest.TestCase): with open(log_path) as file: result = kunit_parser.extract_tap_lines(file.readlines()) self.assertContains('TAP version 14', result) - self.assertContains(' # Subtest: example', result) - self.assertContains(' 1..2', result) - self.assertContains(' ok 1 - example_simple_test', result) - self.assertContains(' ok 2 - example_mock_test', result) + self.assertContains('# Subtest: example', result) + self.assertContains('1..2', result) + self.assertContains('ok 1 - example_simple_test', result) + self.assertContains('ok 2 - example_mock_test', result) self.assertContains('ok 1 - example', result) def test_output_with_prefix_isolated_correctly(self): @@ -117,28 +117,28 @@ class KUnitParserTest(unittest.TestCase): with open(log_path) as file: result = kunit_parser.extract_tap_lines(file.readlines()) self.assertContains('TAP version 14', result) - self.assertContains(' # Subtest: kunit-resource-test', result) - self.assertContains(' 1..5', result) - self.assertContains(' ok 1 - kunit_resource_test_init_resources', result) - self.assertContains(' ok 2 - kunit_resource_test_alloc_resource', result) - self.assertContains(' ok 3 - kunit_resource_test_destroy_resource', result) - self.assertContains(' foo bar #', result) - self.assertContains(' ok 4 - kunit_resource_test_cleanup_resources', result) - self.assertContains(' ok 5 - kunit_resource_test_proper_free_ordering', result) + self.assertContains('# Subtest: kunit-resource-test', result) + self.assertContains('1..5', result) + self.assertContains('ok 1 - kunit_resource_test_init_resources', result) + self.assertContains('ok 2 - kunit_resource_test_alloc_resource', result) + self.assertContains('ok 3 - kunit_resource_test_destroy_resource', result) + self.assertContains('foo bar #', result) + self.assertContains('ok 4 - kunit_resource_test_cleanup_resources', result) + self.assertContains('ok 5 - kunit_resource_test_proper_free_ordering', result) self.assertContains('ok 1 - kunit-resource-test', result) - self.assertContains(' foo bar # non-kunit output', result) - self.assertContains(' # Subtest: kunit-try-catch-test', result) - self.assertContains(' 1..2', result) - self.assertContains(' ok 1 - kunit_test_try_catch_successful_try_no_catch', + self.assertContains('foo bar # non-kunit output', result) + self.assertContains('# Subtest: kunit-try-catch-test', result) + self.assertContains('1..2', result) + self.assertContains('ok 1 - kunit_test_try_catch_successful_try_no_catch', result) - self.assertContains(' ok 2 - kunit_test_try_catch_unsuccessful_try_does_catch', + self.assertContains('ok 2 - kunit_test_try_catch_unsuccessful_try_does_catch', result) self.assertContains('ok 2 - kunit-try-catch-test', result) - self.assertContains(' # Subtest: string-stream-test', result) - self.assertContains(' 1..3', result) - self.assertContains(' ok 1 - string_stream_test_empty_on_creation', result) - self.assertContains(' ok 2 - string_stream_test_not_empty_after_add', result) - self.assertContains(' ok 3 - string_stream_test_get_string', result) + self.assertContains('# Subtest: string-stream-test', result) + self.assertContains('1..3', result) + self.assertContains('ok 1 - string_stream_test_empty_on_creation', result) + self.assertContains('ok 2 - string_stream_test_not_empty_after_add', result) + self.assertContains('ok 3 - string_stream_test_get_string', result) self.assertContains('ok 3 - string-stream-test', result) def test_parse_successful_test_log(self): @@ -149,6 +149,22 @@ class KUnitParserTest(unittest.TestCase): kunit_parser.TestStatus.SUCCESS, result.status) + def test_parse_successful_nested_tests_log(self): + all_passed_log = test_data_path('test_is_test_passed-all_passed_nested.log') + with open(all_passed_log) as file: + result = kunit_parser.parse_run_tests(file.readlines()) + self.assertEqual( + kunit_parser.TestStatus.SUCCESS, + result.status) + + def test_kselftest_nested(self): + kselftest_log = test_data_path('test_is_test_passed-kselftest.log') + with open(kselftest_log) as file: + result = kunit_parser.parse_run_tests(file.readlines()) + self.assertEqual( + kunit_parser.TestStatus.SUCCESS, + result.status) + def test_parse_failed_test_log(self): failed_log = test_data_path('test_is_test_passed-failure.log') with open(failed_log) as file: @@ -162,58 +178,101 @@ class KUnitParserTest(unittest.TestCase): with open(empty_log) as file: result = kunit_parser.parse_run_tests( kunit_parser.extract_tap_lines(file.readlines())) - self.assertEqual(0, len(result.suites)) + self.assertEqual(0, len(result.subtests)) self.assertEqual( kunit_parser.TestStatus.FAILURE_TO_PARSE_TESTS, result.status) + def test_missing_test_plan(self): + missing_plan_log = test_data_path('test_is_test_passed-' + 'missing_plan.log') + with open(missing_plan_log) as file: + result = kunit_parser.parse_run_tests( + kunit_parser.extract_tap_lines( + file.readlines())) + # A missing test plan is not an error. + self.assertEqual(0, result.counts.errors) + # All tests should be accounted for. + self.assertEqual(10, result.counts.total()) + self.assertEqual( + kunit_parser.TestStatus.SUCCESS, + result.status) + def test_no_tests(self): - empty_log = test_data_path('test_is_test_passed-no_tests_run_with_header.log') - with open(empty_log) as file: + header_log = test_data_path('test_is_test_passed-no_tests_run_with_header.log') + with open(header_log) as file: result = kunit_parser.parse_run_tests( kunit_parser.extract_tap_lines(file.readlines())) - self.assertEqual(0, len(result.suites)) + self.assertEqual(0, len(result.subtests)) self.assertEqual( kunit_parser.TestStatus.NO_TESTS, result.status) + def test_no_tests_no_plan(self): + no_plan_log = test_data_path('test_is_test_passed-no_tests_no_plan.log') + with open(no_plan_log) as file: + result = kunit_parser.parse_run_tests( + kunit_parser.extract_tap_lines(file.readlines())) + self.assertEqual(0, len(result.subtests[0].subtests[0].subtests)) + self.assertEqual( + kunit_parser.TestStatus.NO_TESTS, + result.subtests[0].subtests[0].status) + self.assertEqual(1, result.counts.errors) + + def test_no_kunit_output(self): crash_log = test_data_path('test_insufficient_memory.log') print_mock = mock.patch('builtins.print').start() with open(crash_log) as file: result = kunit_parser.parse_run_tests( kunit_parser.extract_tap_lines(file.readlines())) - print_mock.assert_any_call(StrContains('could not parse test results!')) + print_mock.assert_any_call(StrContains('invalid KTAP input!')) print_mock.stop() - file.close() + self.assertEqual(0, len(result.subtests)) def test_crashed_test(self): crashed_log = test_data_path('test_is_test_passed-crash.log') with open(crashed_log) as file: - result = kunit_parser.parse_run_tests(file.readlines()) + result = kunit_parser.parse_run_tests( + file.readlines()) self.assertEqual( kunit_parser.TestStatus.TEST_CRASHED, result.status) def test_skipped_test(self): skipped_log = test_data_path('test_skip_tests.log') - file = open(skipped_log) + with open(skipped_log) as file: + result = kunit_parser.parse_run_tests(file.readlines()) + + # A skipped test does not fail the whole suite. + self.assertEqual( + kunit_parser.TestStatus.SUCCESS, + result.status) + + def test_skipped_all_tests(self): + skipped_log = test_data_path('test_skip_all_tests.log') + with open(skipped_log) as file: + result = kunit_parser.parse_run_tests(file.readlines()) + + self.assertEqual( + kunit_parser.TestStatus.SKIPPED, + result.status) + + def test_ignores_hyphen(self): + hyphen_log = test_data_path('test_strip_hyphen.log') + file = open(hyphen_log) result = kunit_parser.parse_run_tests(file.readlines()) # A skipped test does not fail the whole suite. self.assertEqual( kunit_parser.TestStatus.SUCCESS, result.status) - file.close() - - def test_skipped_all_tests(self): - skipped_log = test_data_path('test_skip_all_tests.log') - file = open(skipped_log) - result = kunit_parser.parse_run_tests(file.readlines()) - self.assertEqual( - kunit_parser.TestStatus.SKIPPED, - result.status) + "sysctl_test", + result.subtests[0].name) + self.assertEqual( + "example", + result.subtests[1].name) file.close() @@ -224,7 +283,7 @@ class KUnitParserTest(unittest.TestCase): self.assertEqual( kunit_parser.TestStatus.SUCCESS, result.status) - self.assertEqual('kunit-resource-test', result.suites[0].name) + self.assertEqual('kunit-resource-test', result.subtests[0].name) def test_ignores_multiple_prefixes(self): prefix_log = test_data_path('test_multiple_prefixes.log') @@ -233,7 +292,7 @@ class KUnitParserTest(unittest.TestCase): self.assertEqual( kunit_parser.TestStatus.SUCCESS, result.status) - self.assertEqual('kunit-resource-test', result.suites[0].name) + self.assertEqual('kunit-resource-test', result.subtests[0].name) def test_prefix_mixed_kernel_output(self): mixed_prefix_log = test_data_path('test_interrupted_tap_output.log') @@ -242,7 +301,7 @@ class KUnitParserTest(unittest.TestCase): self.assertEqual( kunit_parser.TestStatus.SUCCESS, result.status) - self.assertEqual('kunit-resource-test', result.suites[0].name) + self.assertEqual('kunit-resource-test', result.subtests[0].name) def test_prefix_poundsign(self): pound_log = test_data_path('test_pound_sign.log') @@ -251,7 +310,7 @@ class KUnitParserTest(unittest.TestCase): self.assertEqual( kunit_parser.TestStatus.SUCCESS, result.status) - self.assertEqual('kunit-resource-test', result.suites[0].name) + self.assertEqual('kunit-resource-test', result.subtests[0].name) def test_kernel_panic_end(self): panic_log = test_data_path('test_kernel_panic_interrupt.log') @@ -260,7 +319,7 @@ class KUnitParserTest(unittest.TestCase): self.assertEqual( kunit_parser.TestStatus.TEST_CRASHED, result.status) - self.assertEqual('kunit-resource-test', result.suites[0].name) + self.assertEqual('kunit-resource-test', result.subtests[0].name) def test_pound_no_prefix(self): pound_log = test_data_path('test_pound_no_prefix.log') @@ -269,7 +328,46 @@ class KUnitParserTest(unittest.TestCase): self.assertEqual( kunit_parser.TestStatus.SUCCESS, result.status) - self.assertEqual('kunit-resource-test', result.suites[0].name) + self.assertEqual('kunit-resource-test', result.subtests[0].name) + +def line_stream_from_strs(strs: Iterable[str]) -> kunit_parser.LineStream: + return kunit_parser.LineStream(enumerate(strs, start=1)) + +class LineStreamTest(unittest.TestCase): + + def test_basic(self): + stream = line_stream_from_strs(['hello', 'world']) + + self.assertTrue(stream, msg='Should be more input') + self.assertEqual(stream.line_number(), 1) + self.assertEqual(stream.peek(), 'hello') + self.assertEqual(stream.pop(), 'hello') + + self.assertTrue(stream, msg='Should be more input') + self.assertEqual(stream.line_number(), 2) + self.assertEqual(stream.peek(), 'world') + self.assertEqual(stream.pop(), 'world') + + self.assertFalse(stream, msg='Should be no more input') + with self.assertRaisesRegex(ValueError, 'LineStream: going past EOF'): + stream.pop() + + def test_is_lazy(self): + called_times = 0 + def generator(): + nonlocal called_times + for i in range(1,5): + called_times += 1 + yield called_times, str(called_times) + + stream = kunit_parser.LineStream(generator()) + self.assertEqual(called_times, 0) + + self.assertEqual(stream.pop(), '1') + self.assertEqual(called_times, 1) + + self.assertEqual(stream.pop(), '2') + self.assertEqual(called_times, 2) class LinuxSourceTreeTest(unittest.TestCase): @@ -283,13 +381,82 @@ class LinuxSourceTreeTest(unittest.TestCase): def test_valid_kunitconfig(self): with tempfile.NamedTemporaryFile('wt') as kunitconfig: - tree = kunit_kernel.LinuxSourceTree('', kunitconfig_path=kunitconfig.name) + kunit_kernel.LinuxSourceTree('', kunitconfig_path=kunitconfig.name) def test_dir_kunitconfig(self): with tempfile.TemporaryDirectory('') as dir: - with open(os.path.join(dir, '.kunitconfig'), 'w') as f: + with open(os.path.join(dir, '.kunitconfig'), 'w'): pass - tree = kunit_kernel.LinuxSourceTree('', kunitconfig_path=dir) + kunit_kernel.LinuxSourceTree('', kunitconfig_path=dir) + + def test_kconfig_add(self): + tree = kunit_kernel.LinuxSourceTree('', kconfig_add=['CONFIG_NOT_REAL=y']) + self.assertIn(kunit_config.KconfigEntry('NOT_REAL', 'y'), tree._kconfig.entries()) + + def test_invalid_arch(self): + with self.assertRaisesRegex(kunit_kernel.ConfigError, 'not a valid arch, options are.*x86_64'): + kunit_kernel.LinuxSourceTree('', arch='invalid') + + def test_run_kernel_hits_exception(self): + def fake_start(unused_args, unused_build_dir): + return subprocess.Popen(['echo "hi\nbye"'], shell=True, text=True, stdout=subprocess.PIPE) + + with tempfile.TemporaryDirectory('') as build_dir: + tree = kunit_kernel.LinuxSourceTree(build_dir, load_config=False) + mock.patch.object(tree._ops, 'start', side_effect=fake_start).start() + + with self.assertRaises(ValueError): + for line in tree.run_kernel(build_dir=build_dir): + self.assertEqual(line, 'hi\n') + raise ValueError('uh oh, did not read all output') + + with open(kunit_kernel.get_outfile_path(build_dir), 'rt') as outfile: + self.assertEqual(outfile.read(), 'hi\nbye\n', msg='Missing some output') + + def test_build_reconfig_no_config(self): + with tempfile.TemporaryDirectory('') as build_dir: + with open(kunit_kernel.get_kunitconfig_path(build_dir), 'w') as f: + f.write('CONFIG_KUNIT=y') + + tree = kunit_kernel.LinuxSourceTree(build_dir) + mock_build_config = mock.patch.object(tree, 'build_config').start() + + # Should generate the .config + self.assertTrue(tree.build_reconfig(build_dir, make_options=[])) + mock_build_config.assert_called_once_with(build_dir, []) + + def test_build_reconfig_existing_config(self): + with tempfile.TemporaryDirectory('') as build_dir: + # Existing .config is a superset, should not touch it + with open(kunit_kernel.get_kunitconfig_path(build_dir), 'w') as f: + f.write('CONFIG_KUNIT=y') + with open(kunit_kernel.get_old_kunitconfig_path(build_dir), 'w') as f: + f.write('CONFIG_KUNIT=y') + with open(kunit_kernel.get_kconfig_path(build_dir), 'w') as f: + f.write('CONFIG_KUNIT=y\nCONFIG_KUNIT_TEST=y') + + tree = kunit_kernel.LinuxSourceTree(build_dir) + mock_build_config = mock.patch.object(tree, 'build_config').start() + + self.assertTrue(tree.build_reconfig(build_dir, make_options=[])) + self.assertEqual(mock_build_config.call_count, 0) + + def test_build_reconfig_remove_option(self): + with tempfile.TemporaryDirectory('') as build_dir: + # We removed CONFIG_KUNIT_TEST=y from our .kunitconfig... + with open(kunit_kernel.get_kunitconfig_path(build_dir), 'w') as f: + f.write('CONFIG_KUNIT=y') + with open(kunit_kernel.get_old_kunitconfig_path(build_dir), 'w') as f: + f.write('CONFIG_KUNIT=y\nCONFIG_KUNIT_TEST=y') + with open(kunit_kernel.get_kconfig_path(build_dir), 'w') as f: + f.write('CONFIG_KUNIT=y\nCONFIG_KUNIT_TEST=y') + + tree = kunit_kernel.LinuxSourceTree(build_dir) + mock_build_config = mock.patch.object(tree, 'build_config').start() + + # ... so we should trigger a call to build_config() + self.assertTrue(tree.build_reconfig(build_dir, make_options=[])) + mock_build_config.assert_called_once_with(build_dir, []) # TODO: add more test cases. @@ -300,7 +467,7 @@ class KUnitJsonTest(unittest.TestCase): with open(test_data_path(log_file)) as file: test_result = kunit_parser.parse_run_tests(file) json_obj = kunit_json.get_json_result( - test_result=test_result, + test=test_result, def_config='kunit_defconfig', build_dir=None, json_path='stdout') @@ -318,10 +485,22 @@ class KUnitJsonTest(unittest.TestCase): {'name': 'example_simple_test', 'status': 'ERROR'}, result["sub_groups"][1]["test_cases"][0]) + def test_skipped_test_json(self): + result = self._json_for('test_skip_tests.log') + self.assertEqual( + {'name': 'example_skip_test', 'status': 'SKIP'}, + result["sub_groups"][1]["test_cases"][1]) + def test_no_tests_json(self): result = self._json_for('test_is_test_passed-no_tests_run_with_header.log') self.assertEqual(0, len(result['sub_groups'])) + def test_nested_json(self): + result = self._json_for('test_is_test_passed-all_passed_nested.log') + self.assertEqual( + {'name': 'example_simple_test', 'status': 'PASS'}, + result["sub_groups"][0]["sub_groups"][0]["test_cases"][0]) + class StrContains(str): def __eq__(self, other): return self in other @@ -347,8 +526,8 @@ class KUnitMainTest(unittest.TestCase): def test_build_passes_args_pass(self): kunit.main(['build'], self.linux_source_mock) - self.assertEqual(self.linux_source_mock.build_reconfig.call_count, 0) - self.linux_source_mock.build_kernel.assert_called_once_with(False, 8, '.kunit', None) + self.assertEqual(self.linux_source_mock.build_reconfig.call_count, 1) + self.linux_source_mock.build_kernel.assert_called_once_with(False, kunit.get_default_jobs(), '.kunit', None) self.assertEqual(self.linux_source_mock.run_kernel.call_count, 0) def test_exec_passes_args_pass(self): @@ -380,7 +559,15 @@ class KUnitMainTest(unittest.TestCase): self.assertEqual(e.exception.code, 1) self.assertEqual(self.linux_source_mock.build_reconfig.call_count, 1) self.assertEqual(self.linux_source_mock.run_kernel.call_count, 1) - self.print_mock.assert_any_call(StrContains(' 0 tests run')) + self.print_mock.assert_any_call(StrContains('invalid KTAP input!')) + + def test_exec_no_tests(self): + self.linux_source_mock.run_kernel = mock.Mock(return_value=['TAP version 14', '1..0']) + with self.assertRaises(SystemExit) as e: + kunit.main(['run'], self.linux_source_mock) + self.linux_source_mock.run_kernel.assert_called_once_with( + args=None, build_dir='.kunit', filter_glob='', timeout=300) + self.print_mock.assert_any_call(StrContains(' 0 tests run!')) def test_exec_raw_output(self): self.linux_source_mock.run_kernel = mock.Mock(return_value=[]) @@ -388,7 +575,7 @@ class KUnitMainTest(unittest.TestCase): self.assertEqual(self.linux_source_mock.run_kernel.call_count, 1) for call in self.print_mock.call_args_list: self.assertNotEqual(call, mock.call(StrContains('Testing complete.'))) - self.assertNotEqual(call, mock.call(StrContains(' 0 tests run'))) + self.assertNotEqual(call, mock.call(StrContains(' 0 tests run!'))) def test_run_raw_output(self): self.linux_source_mock.run_kernel = mock.Mock(return_value=[]) @@ -397,7 +584,7 @@ class KUnitMainTest(unittest.TestCase): self.assertEqual(self.linux_source_mock.run_kernel.call_count, 1) for call in self.print_mock.call_args_list: self.assertNotEqual(call, mock.call(StrContains('Testing complete.'))) - self.assertNotEqual(call, mock.call(StrContains(' 0 tests run'))) + self.assertNotEqual(call, mock.call(StrContains(' 0 tests run!'))) def test_run_raw_output_kunit(self): self.linux_source_mock.run_kernel = mock.Mock(return_value=[]) @@ -446,8 +633,9 @@ class KUnitMainTest(unittest.TestCase): def test_build_builddir(self): build_dir = '.kunit' + jobs = kunit.get_default_jobs() kunit.main(['build', '--build_dir', build_dir], self.linux_source_mock) - self.linux_source_mock.build_kernel.assert_called_once_with(False, 8, build_dir, None) + self.linux_source_mock.build_kernel.assert_called_once_with(False, jobs, build_dir, None) def test_exec_builddir(self): build_dir = '.kunit' @@ -463,6 +651,7 @@ class KUnitMainTest(unittest.TestCase): # Just verify that we parsed and initialized it correctly here. mock_linux_init.assert_called_once_with('.kunit', kunitconfig_path='mykunitconfig', + kconfig_add=None, arch='um', cross_compile=None, qemu_config_path=None) @@ -474,6 +663,19 @@ class KUnitMainTest(unittest.TestCase): # Just verify that we parsed and initialized it correctly here. mock_linux_init.assert_called_once_with('.kunit', kunitconfig_path='mykunitconfig', + kconfig_add=None, + arch='um', + cross_compile=None, + qemu_config_path=None) + + @mock.patch.object(kunit_kernel, 'LinuxSourceTree') + def test_run_kconfig_add(self, mock_linux_init): + mock_linux_init.return_value = self.linux_source_mock + kunit.main(['run', '--kconfig_add=CONFIG_KASAN=y', '--kconfig_add=CONFIG_KCSAN=y']) + # Just verify that we parsed and initialized it correctly here. + mock_linux_init.assert_called_once_with('.kunit', + kunitconfig_path=None, + kconfig_add=['CONFIG_KASAN=y', 'CONFIG_KCSAN=y'], arch='um', cross_compile=None, qemu_config_path=None) @@ -485,6 +687,46 @@ class KUnitMainTest(unittest.TestCase): args=['a=1','b=2'], build_dir='.kunit', filter_glob='', timeout=300) self.print_mock.assert_any_call(StrContains('Testing complete.')) + def test_list_tests(self): + want = ['suite.test1', 'suite.test2', 'suite2.test1'] + self.linux_source_mock.run_kernel.return_value = ['TAP version 14', 'init: random output'] + want + + got = kunit._list_tests(self.linux_source_mock, + kunit.KunitExecRequest(None, '.kunit', None, 300, False, 'suite*', None, 'suite')) + + self.assertEqual(got, want) + # Should respect the user's filter glob when listing tests. + self.linux_source_mock.run_kernel.assert_called_once_with( + args=['kunit.action=list'], build_dir='.kunit', filter_glob='suite*', timeout=300) + + + @mock.patch.object(kunit, '_list_tests') + def test_run_isolated_by_suite(self, mock_tests): + mock_tests.return_value = ['suite.test1', 'suite.test2', 'suite2.test1'] + kunit.main(['exec', '--run_isolated=suite', 'suite*.test*'], self.linux_source_mock) + + # Should respect the user's filter glob when listing tests. + mock_tests.assert_called_once_with(mock.ANY, + kunit.KunitExecRequest(None, '.kunit', None, 300, False, 'suite*.test*', None, 'suite')) + self.linux_source_mock.run_kernel.assert_has_calls([ + mock.call(args=None, build_dir='.kunit', filter_glob='suite.test*', timeout=300), + mock.call(args=None, build_dir='.kunit', filter_glob='suite2.test*', timeout=300), + ]) + + @mock.patch.object(kunit, '_list_tests') + def test_run_isolated_by_test(self, mock_tests): + mock_tests.return_value = ['suite.test1', 'suite.test2', 'suite2.test1'] + kunit.main(['exec', '--run_isolated=test', 'suite*'], self.linux_source_mock) + + # Should respect the user's filter glob when listing tests. + mock_tests.assert_called_once_with(mock.ANY, + kunit.KunitExecRequest(None, '.kunit', None, 300, False, 'suite*', None, 'test')) + self.linux_source_mock.run_kernel.assert_has_calls([ + mock.call(args=None, build_dir='.kunit', filter_glob='suite.test1', timeout=300), + mock.call(args=None, build_dir='.kunit', filter_glob='suite.test2', timeout=300), + mock.call(args=None, build_dir='.kunit', filter_glob='suite2.test1', timeout=300), + ]) + if __name__ == '__main__': unittest.main() diff --git a/tools/testing/nvdimm/Kbuild b/tools/testing/nvdimm/Kbuild index 47f9cc9dcd..c57d9e9d44 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/test/iomap.c b/tools/testing/nvdimm/test/iomap.c index ed563bdd88..b752ce47ea 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); + WARN_ON(!pgmap); - if (pgmap->ops && pgmap->ops->kill) - pgmap->ops->kill(pgmap); - else - percpu_ref_kill(pgmap->ref); + 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); - } + 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 6862915f1f..3ca7c32e93 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 b1bff5fb0f..0bc91ffee2 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/radix-tree/linux/lockdep.h b/tools/testing/radix-tree/linux/lockdep.h index 565fccdfe6..016cff473c 100644 --- a/tools/testing/radix-tree/linux/lockdep.h +++ b/tools/testing/radix-tree/linux/lockdep.h @@ -1,5 +1,8 @@ #ifndef _LINUX_LOCKDEP_H #define _LINUX_LOCKDEP_H + +#include + struct lock_class_key { unsigned int a; }; diff --git a/tools/testing/scatterlist/linux/mm.h b/tools/testing/scatterlist/linux/mm.h index 16ec895bbe..5bd9e6e806 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 c852eb40c4..d08fe4cfe8 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/arm64/Makefile b/tools/testing/selftests/arm64/Makefile index ced910fb40..1e8d9a8f59 100644 --- a/tools/testing/selftests/arm64/Makefile +++ b/tools/testing/selftests/arm64/Makefile @@ -4,7 +4,7 @@ ARCH ?= $(shell uname -m 2>/dev/null || echo not) ifneq (,$(filter $(ARCH),aarch64 arm64)) -ARM64_SUBTARGETS ?= tags signal pauth fp mte bti +ARM64_SUBTARGETS ?= tags signal pauth fp mte bti abi else ARM64_SUBTARGETS := endif diff --git a/tools/testing/selftests/arm64/fp/.gitignore b/tools/testing/selftests/arm64/fp/.gitignore index b67395903b..c50d86331e 100644 --- a/tools/testing/selftests/arm64/fp/.gitignore +++ b/tools/testing/selftests/arm64/fp/.gitignore @@ -1,3 +1,4 @@ +fp-pidbench fpsimd-test rdvl-sve sve-probe-vls diff --git a/tools/testing/selftests/arm64/fp/Makefile b/tools/testing/selftests/arm64/fp/Makefile index f2abdd6ba1..95f0b877a0 100644 --- a/tools/testing/selftests/arm64/fp/Makefile +++ b/tools/testing/selftests/arm64/fp/Makefile @@ -2,19 +2,21 @@ CFLAGS += -I../../../../../usr/include/ TEST_GEN_PROGS := sve-ptrace sve-probe-vls vec-syscfg -TEST_PROGS_EXTENDED := fpsimd-test fpsimd-stress \ +TEST_PROGS_EXTENDED := fp-pidbench fpsimd-test fpsimd-stress \ rdvl-sve \ sve-test sve-stress \ vlset all: $(TEST_GEN_PROGS) $(TEST_PROGS_EXTENDED) -fpsimd-test: fpsimd-test.o +fp-pidbench: fp-pidbench.S asm-utils.o + $(CC) -nostdlib $^ -o $@ +fpsimd-test: fpsimd-test.o asm-utils.o $(CC) -nostdlib $^ -o $@ rdvl-sve: rdvl-sve.o rdvl.o -sve-ptrace: sve-ptrace.o sve-ptrace-asm.o +sve-ptrace: sve-ptrace.o sve-probe-vls: sve-probe-vls.o rdvl.o -sve-test: sve-test.o +sve-test: sve-test.o asm-utils.o $(CC) -nostdlib $^ -o $@ vec-syscfg: vec-syscfg.o rdvl.o vlset: vlset.o diff --git a/tools/testing/selftests/arm64/fp/TODO b/tools/testing/selftests/arm64/fp/TODO index b6b7ebfcf3..44004e53da 100644 --- a/tools/testing/selftests/arm64/fp/TODO +++ b/tools/testing/selftests/arm64/fp/TODO @@ -1,4 +1,7 @@ - Test unsupported values in the ABIs. -- More coverage for ptrace (eg, vector length conversions). -- Coverage for signals. -- Test PR_SVE_VL_INHERITY after a double fork. +- More coverage for ptrace: + - Get/set of FFR. + - Ensure ptraced processes actually see the register state visible through + the ptrace interface. + - Big endian. +- Test PR_SVE_VL_INHERIT after a double fork. diff --git a/tools/testing/selftests/arm64/fp/assembler.h b/tools/testing/selftests/arm64/fp/assembler.h index 8944f21892..90bd433d26 100644 --- a/tools/testing/selftests/arm64/fp/assembler.h +++ b/tools/testing/selftests/arm64/fp/assembler.h @@ -54,4 +54,15 @@ endfunction .purgem \name\()_entry .endm +// Utility macro to print a literal string +// Clobbers x0-x4,x8 +.macro puts string + .pushsection .rodata.str1.1, "aMS", 1 +.L__puts_literal\@: .string "\string" + .popsection + + ldr x0, =.L__puts_literal\@ + bl puts +.endm + #endif /* ! ASSEMBLER_H */ diff --git a/tools/testing/selftests/arm64/fp/fpsimd-test.S b/tools/testing/selftests/arm64/fp/fpsimd-test.S index 0dbd594c27..e21e8ea52c 100644 --- a/tools/testing/selftests/arm64/fp/fpsimd-test.S +++ b/tools/testing/selftests/arm64/fp/fpsimd-test.S @@ -33,131 +33,6 @@ define_accessor setv, NVR, _vldr define_accessor getv, NVR, _vstr -// Print a single character x0 to stdout -// Clobbers x0-x2,x8 -function putc - str x0, [sp, #-16]! - - mov x0, #1 // STDOUT_FILENO - mov x1, sp - mov x2, #1 - mov x8, #__NR_write - svc #0 - - add sp, sp, #16 - ret -endfunction - -// Print a NUL-terminated string starting at address x0 to stdout -// Clobbers x0-x3,x8 -function puts - mov x1, x0 - - mov x2, #0 -0: ldrb w3, [x0], #1 - cbz w3, 1f - add x2, x2, #1 - b 0b - -1: mov w0, #1 // STDOUT_FILENO - mov x8, #__NR_write - svc #0 - - ret -endfunction - -// Utility macro to print a literal string -// Clobbers x0-x4,x8 -.macro puts string - .pushsection .rodata.str1.1, "aMS", 1 -.L__puts_literal\@: .string "\string" - .popsection - - ldr x0, =.L__puts_literal\@ - bl puts -.endm - -// Print an unsigned decimal number x0 to stdout -// Clobbers x0-x4,x8 -function putdec - mov x1, sp - str x30, [sp, #-32]! // Result can't be > 20 digits - - mov x2, #0 - strb w2, [x1, #-1]! // Write the NUL terminator - - mov x2, #10 -0: udiv x3, x0, x2 // div-mod loop to generate the digits - msub x0, x3, x2, x0 - add w0, w0, #'0' - strb w0, [x1, #-1]! - mov x0, x3 - cbnz x3, 0b - - ldrb w0, [x1] - cbnz w0, 1f - mov w0, #'0' // Print "0" for 0, not "" - strb w0, [x1, #-1]! - -1: mov x0, x1 - bl puts - - ldr x30, [sp], #32 - ret -endfunction - -// Print an unsigned decimal number x0 to stdout, followed by a newline -// Clobbers x0-x5,x8 -function putdecn - mov x5, x30 - - bl putdec - mov x0, #'\n' - bl putc - - ret x5 -endfunction - - -// Clobbers x0-x3,x8 -function puthexb - str x30, [sp, #-0x10]! - - mov w3, w0 - lsr w0, w0, #4 - bl puthexnibble - mov w0, w3 - - ldr x30, [sp], #0x10 - // fall through to puthexnibble -endfunction -// Clobbers x0-x2,x8 -function puthexnibble - and w0, w0, #0xf - cmp w0, #10 - blo 1f - add w0, w0, #'a' - ('9' + 1) -1: add w0, w0, #'0' - b putc -endfunction - -// x0=data in, x1=size in, clobbers x0-x5,x8 -function dumphex - str x30, [sp, #-0x10]! - - mov x4, x0 - mov x5, x1 - -0: subs x5, x5, #1 - b.lo 1f - ldrb w0, [x4], #1 - bl puthexb - b 0b - -1: ldr x30, [sp], #0x10 - ret -endfunction - // Declare some storate space to shadow the SVE register contents: .pushsection .text .data @@ -168,18 +43,6 @@ scratch: .space MAXVL_B .popsection -// Trivial memory copy: copy x2 bytes, starting at address x1, to address x0. -// Clobbers x0-x3 -function memcpy - cmp x2, #0 - b.eq 1f -0: ldrb w3, [x1], #1 - strb w3, [x0], #1 - subs x2, x2, #1 - b.ne 0b -1: ret -endfunction - // Generate a test pattern for storage in SVE registers // x0: pid (16 bits) // x1: register number (6 bits) @@ -227,33 +90,6 @@ function setup_vreg ret x4 endfunction -// Fill x1 bytes starting at x0 with 0xae (for canary purposes) -// Clobbers x1, x2. -function memfill_ae - mov w2, #0xae - b memfill -endfunction - -// Fill x1 bytes starting at x0 with 0. -// Clobbers x1, x2. -function memclr - mov w2, #0 -endfunction - // fall through to memfill - -// Trivial memory fill: fill x1 bytes starting at address x0 with byte w2 -// Clobbers x1 -function memfill - cmp x1, #0 - b.eq 1f - -0: strb w2, [x0], #1 - subs x1, x1, #1 - b.ne 0b - -1: ret -endfunction - // Trivial memory compare: compare x2 bytes starting at address x0 with // bytes starting at address x1. // Returns only if all bytes match; otherwise, the program is aborted. diff --git a/tools/testing/selftests/arm64/fp/sve-ptrace.c b/tools/testing/selftests/arm64/fp/sve-ptrace.c index 612d389961..a3c1e67441 100644 --- a/tools/testing/selftests/arm64/fp/sve-ptrace.c +++ b/tools/testing/selftests/arm64/fp/sve-ptrace.c @@ -1,15 +1,17 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Copyright (C) 2015-2020 ARM Limited. + * Copyright (C) 2015-2021 ARM Limited. * Original author: Dave Martin */ #include +#include #include #include #include #include #include #include +#include #include #include #include @@ -19,40 +21,43 @@ #include "../../kselftest.h" +#define ARRAY_SIZE(a) (sizeof(a) / sizeof(a[0])) + /* and don't like each other, so: */ #ifndef NT_ARM_SVE #define NT_ARM_SVE 0x405 #endif -/* Number of registers filled in by sve_store_patterns */ -#define NR_VREGS 5 +struct vec_type { + const char *name; + unsigned long hwcap_type; + unsigned long hwcap; + int regset; + int prctl_set; +}; -void sve_store_patterns(__uint128_t v[NR_VREGS]); +static const struct vec_type vec_types[] = { + { + .name = "SVE", + .hwcap_type = AT_HWCAP, + .hwcap = HWCAP_SVE, + .regset = NT_ARM_SVE, + .prctl_set = PR_SVE_SET_VL, + }, +}; -static void dump(const void *buf, size_t size) -{ - size_t i; - const unsigned char *p = buf; +#define VL_TESTS (((SVE_VQ_MAX - SVE_VQ_MIN) + 1) * 3) +#define FLAG_TESTS 2 +#define FPSIMD_TESTS 3 - for (i = 0; i < size; ++i) - printf(" %.2x", *p++); -} +#define EXPECTED_TESTS ((VL_TESTS + FLAG_TESTS + FPSIMD_TESTS) * ARRAY_SIZE(vec_types)) -static int check_vregs(const __uint128_t vregs[NR_VREGS]) +static void fill_buf(char *buf, size_t size) { int i; - int ok = 1; - for (i = 0; i < NR_VREGS; ++i) { - printf("# v[%d]:", i); - dump(&vregs[i], sizeof vregs[i]); - putchar('\n'); - - if (vregs[i] != vregs[0]) - ok = 0; - } - - return ok; + for (i = 0; i < size; i++) + buf[i] = random(); } static int do_child(void) @@ -66,7 +71,17 @@ static int do_child(void) return EXIT_SUCCESS; } -static struct user_sve_header *get_sve(pid_t pid, void **buf, size_t *size) +static int get_fpsimd(pid_t pid, struct user_fpsimd_state *fpsimd) +{ + struct iovec iov; + + iov.iov_base = fpsimd; + iov.iov_len = sizeof(*fpsimd); + return ptrace(PTRACE_GETREGSET, pid, NT_PRFPREG, &iov); +} + +static struct user_sve_header *get_sve(pid_t pid, const struct vec_type *type, + void **buf, size_t *size) { struct user_sve_header *sve; void *p; @@ -87,7 +102,7 @@ static struct user_sve_header *get_sve(pid_t pid, void **buf, size_t *size) iov.iov_base = *buf; iov.iov_len = sz; - if (ptrace(PTRACE_GETREGSET, pid, NT_ARM_SVE, &iov)) + if (ptrace(PTRACE_GETREGSET, pid, type->regset, &iov)) goto error; sve = *buf; @@ -103,49 +118,376 @@ static struct user_sve_header *get_sve(pid_t pid, void **buf, size_t *size) return NULL; } -static int set_sve(pid_t pid, const struct user_sve_header *sve) +static int set_sve(pid_t pid, const struct vec_type *type, + const struct user_sve_header *sve) { struct iovec iov; iov.iov_base = (void *)sve; iov.iov_len = sve->size; - return ptrace(PTRACE_SETREGSET, pid, NT_ARM_SVE, &iov); + return ptrace(PTRACE_SETREGSET, pid, type->regset, &iov); } -static void dump_sve_regs(const struct user_sve_header *sve, unsigned int num, - unsigned int vlmax) +/* Validate setting and getting the inherit flag */ +static void ptrace_set_get_inherit(pid_t child, const struct vec_type *type) { - unsigned int vq; - unsigned int i; + struct user_sve_header sve; + struct user_sve_header *new_sve = NULL; + size_t new_sve_size = 0; + int ret; - if ((sve->flags & SVE_PT_REGS_MASK) != SVE_PT_REGS_SVE) - ksft_exit_fail_msg("Dumping non-SVE register\n"); - - if (vlmax > sve->vl) - vlmax = sve->vl; - - vq = sve_vq_from_vl(sve->vl); - for (i = 0; i < num; ++i) { - printf("# z%u:", i); - dump((const char *)sve + SVE_PT_SVE_ZREG_OFFSET(vq, i), - vlmax); - printf("%s\n", vlmax == sve->vl ? "" : " ..."); + /* First set the flag */ + memset(&sve, 0, sizeof(sve)); + sve.size = sizeof(sve); + sve.vl = sve_vl_from_vq(SVE_VQ_MIN); + sve.flags = SVE_PT_VL_INHERIT; + ret = set_sve(child, type, &sve); + if (ret != 0) { + ksft_test_result_fail("Failed to set %s SVE_PT_VL_INHERIT\n", + type->name); + return; } + + /* + * Read back the new register state and verify that we have + * set the flags we expected. + */ + if (!get_sve(child, type, (void **)&new_sve, &new_sve_size)) { + ksft_test_result_fail("Failed to read %s SVE flags\n", + type->name); + return; + } + + ksft_test_result(new_sve->flags & SVE_PT_VL_INHERIT, + "%s SVE_PT_VL_INHERIT set\n", type->name); + + /* Now clear */ + sve.flags &= ~SVE_PT_VL_INHERIT; + ret = set_sve(child, type, &sve); + if (ret != 0) { + ksft_test_result_fail("Failed to clear %s SVE_PT_VL_INHERIT\n", + type->name); + return; + } + + if (!get_sve(child, type, (void **)&new_sve, &new_sve_size)) { + ksft_test_result_fail("Failed to read %s SVE flags\n", + type->name); + return; + } + + ksft_test_result(!(new_sve->flags & SVE_PT_VL_INHERIT), + "%s SVE_PT_VL_INHERIT cleared\n", type->name); + + free(new_sve); +} + +/* Validate attempting to set the specfied VL via ptrace */ +static void ptrace_set_get_vl(pid_t child, const struct vec_type *type, + unsigned int vl, bool *supported) +{ + struct user_sve_header sve; + struct user_sve_header *new_sve = NULL; + size_t new_sve_size = 0; + int ret, prctl_vl; + + *supported = false; + + /* Check if the VL is supported in this process */ + prctl_vl = prctl(type->prctl_set, vl); + if (prctl_vl == -1) + ksft_exit_fail_msg("prctl(PR_%s_SET_VL) failed: %s (%d)\n", + type->name, strerror(errno), errno); + + /* If the VL is not supported then a supported VL will be returned */ + *supported = (prctl_vl == vl); + + /* Set the VL by doing a set with no register payload */ + memset(&sve, 0, sizeof(sve)); + sve.size = sizeof(sve); + sve.vl = vl; + ret = set_sve(child, type, &sve); + if (ret != 0) { + ksft_test_result_fail("Failed to set %s VL %u\n", + type->name, vl); + return; + } + + /* + * Read back the new register state and verify that we have the + * same VL that we got from prctl() on ourselves. + */ + if (!get_sve(child, type, (void **)&new_sve, &new_sve_size)) { + ksft_test_result_fail("Failed to read %s VL %u\n", + type->name, vl); + return; + } + + ksft_test_result(new_sve->vl = prctl_vl, "Set %s VL %u\n", + type->name, vl); + + free(new_sve); +} + +static void check_u32(unsigned int vl, const char *reg, + uint32_t *in, uint32_t *out, int *errors) +{ + if (*in != *out) { + printf("# VL %d %s wrote %x read %x\n", + vl, reg, *in, *out); + (*errors)++; + } +} + +/* Access the FPSIMD registers via the SVE regset */ +static void ptrace_sve_fpsimd(pid_t child, const struct vec_type *type) +{ + void *svebuf = NULL; + size_t svebufsz = 0; + struct user_sve_header *sve; + struct user_fpsimd_state *fpsimd, new_fpsimd; + unsigned int i, j; + unsigned char *p; + + /* New process should start with FPSIMD registers only */ + sve = get_sve(child, type, &svebuf, &svebufsz); + if (!sve) { + ksft_test_result_fail("get_sve(%s): %s\n", + type->name, strerror(errno)); + + return; + } else { + ksft_test_result_pass("get_sve(%s FPSIMD)\n", type->name); + } + + ksft_test_result((sve->flags & SVE_PT_REGS_MASK) == SVE_PT_REGS_FPSIMD, + "Got FPSIMD registers via %s\n", type->name); + if ((sve->flags & SVE_PT_REGS_MASK) != SVE_PT_REGS_FPSIMD) + goto out; + + /* Try to set a known FPSIMD state via PT_REGS_SVE */ + fpsimd = (struct user_fpsimd_state *)((char *)sve + + SVE_PT_FPSIMD_OFFSET); + for (i = 0; i < 32; ++i) { + p = (unsigned char *)&fpsimd->vregs[i]; + + for (j = 0; j < sizeof(fpsimd->vregs[i]); ++j) + p[j] = j; + } + + if (set_sve(child, type, sve)) { + ksft_test_result_fail("set_sve(%s FPSIMD): %s\n", + type->name, strerror(errno)); + + goto out; + } + + /* Verify via the FPSIMD regset */ + if (get_fpsimd(child, &new_fpsimd)) { + ksft_test_result_fail("get_fpsimd(): %s\n", + strerror(errno)); + goto out; + } + if (memcmp(fpsimd, &new_fpsimd, sizeof(*fpsimd)) == 0) + ksft_test_result_pass("%s get_fpsimd() gave same state\n", + type->name); + else + ksft_test_result_fail("%s get_fpsimd() gave different state\n", + type->name); + +out: + free(svebuf); +} + +/* Validate attempting to set SVE data and read SVE data */ +static void ptrace_set_sve_get_sve_data(pid_t child, + const struct vec_type *type, + unsigned int vl) +{ + void *write_buf; + void *read_buf = NULL; + struct user_sve_header *write_sve; + struct user_sve_header *read_sve; + size_t read_sve_size = 0; + unsigned int vq = sve_vq_from_vl(vl); + int ret, i; + size_t data_size; + int errors = 0; + + data_size = SVE_PT_SVE_OFFSET + SVE_PT_SVE_SIZE(vq, SVE_PT_REGS_SVE); + write_buf = malloc(data_size); + if (!write_buf) { + ksft_test_result_fail("Error allocating %d byte buffer for %s VL %u\n", + data_size, type->name, vl); + return; + } + write_sve = write_buf; + + /* Set up some data and write it out */ + memset(write_sve, 0, data_size); + write_sve->size = data_size; + write_sve->vl = vl; + write_sve->flags = SVE_PT_REGS_SVE; + + for (i = 0; i < __SVE_NUM_ZREGS; i++) + fill_buf(write_buf + SVE_PT_SVE_ZREG_OFFSET(vq, i), + SVE_PT_SVE_ZREG_SIZE(vq)); + + for (i = 0; i < __SVE_NUM_PREGS; i++) + fill_buf(write_buf + SVE_PT_SVE_PREG_OFFSET(vq, i), + SVE_PT_SVE_PREG_SIZE(vq)); + + fill_buf(write_buf + SVE_PT_SVE_FPSR_OFFSET(vq), SVE_PT_SVE_FPSR_SIZE); + fill_buf(write_buf + SVE_PT_SVE_FPCR_OFFSET(vq), SVE_PT_SVE_FPCR_SIZE); + + /* TODO: Generate a valid FFR pattern */ + + ret = set_sve(child, type, write_sve); + if (ret != 0) { + ksft_test_result_fail("Failed to set %s VL %u data\n", + type->name, vl); + goto out; + } + + /* Read the data back */ + if (!get_sve(child, type, (void **)&read_buf, &read_sve_size)) { + ksft_test_result_fail("Failed to read %s VL %u data\n", + type->name, vl); + goto out; + } + read_sve = read_buf; + + /* We might read more data if there's extensions we don't know */ + if (read_sve->size < write_sve->size) { + ksft_test_result_fail("%s wrote %d bytes, only read %d\n", + type->name, write_sve->size, + read_sve->size); + goto out_read; + } + + for (i = 0; i < __SVE_NUM_ZREGS; i++) { + if (memcmp(write_buf + SVE_PT_SVE_ZREG_OFFSET(vq, i), + read_buf + SVE_PT_SVE_ZREG_OFFSET(vq, i), + SVE_PT_SVE_ZREG_SIZE(vq)) != 0) { + printf("# Mismatch in %u Z%d\n", vl, i); + errors++; + } + } + + for (i = 0; i < __SVE_NUM_PREGS; i++) { + if (memcmp(write_buf + SVE_PT_SVE_PREG_OFFSET(vq, i), + read_buf + SVE_PT_SVE_PREG_OFFSET(vq, i), + SVE_PT_SVE_PREG_SIZE(vq)) != 0) { + printf("# Mismatch in %u P%d\n", vl, i); + errors++; + } + } + + check_u32(vl, "FPSR", write_buf + SVE_PT_SVE_FPSR_OFFSET(vq), + read_buf + SVE_PT_SVE_FPSR_OFFSET(vq), &errors); + check_u32(vl, "FPCR", write_buf + SVE_PT_SVE_FPCR_OFFSET(vq), + read_buf + SVE_PT_SVE_FPCR_OFFSET(vq), &errors); + + ksft_test_result(errors == 0, "Set and get %s data for VL %u\n", + type->name, vl); + +out_read: + free(read_buf); +out: + free(write_buf); +} + +/* Validate attempting to set SVE data and read SVE data */ +static void ptrace_set_sve_get_fpsimd_data(pid_t child, + const struct vec_type *type, + unsigned int vl) +{ + void *write_buf; + struct user_sve_header *write_sve; + unsigned int vq = sve_vq_from_vl(vl); + struct user_fpsimd_state fpsimd_state; + int ret, i; + size_t data_size; + int errors = 0; + + if (__BYTE_ORDER == __BIG_ENDIAN) { + ksft_test_result_skip("Big endian not supported\n"); + return; + } + + data_size = SVE_PT_SVE_OFFSET + SVE_PT_SVE_SIZE(vq, SVE_PT_REGS_SVE); + write_buf = malloc(data_size); + if (!write_buf) { + ksft_test_result_fail("Error allocating %d byte buffer for %s VL %u\n", + data_size, type->name, vl); + return; + } + write_sve = write_buf; + + /* Set up some data and write it out */ + memset(write_sve, 0, data_size); + write_sve->size = data_size; + write_sve->vl = vl; + write_sve->flags = SVE_PT_REGS_SVE; + + for (i = 0; i < __SVE_NUM_ZREGS; i++) + fill_buf(write_buf + SVE_PT_SVE_ZREG_OFFSET(vq, i), + SVE_PT_SVE_ZREG_SIZE(vq)); + + fill_buf(write_buf + SVE_PT_SVE_FPSR_OFFSET(vq), SVE_PT_SVE_FPSR_SIZE); + fill_buf(write_buf + SVE_PT_SVE_FPCR_OFFSET(vq), SVE_PT_SVE_FPCR_SIZE); + + ret = set_sve(child, type, write_sve); + if (ret != 0) { + ksft_test_result_fail("Failed to set %s VL %u data\n", + type->name, vl); + goto out; + } + + /* Read the data back */ + if (get_fpsimd(child, &fpsimd_state)) { + ksft_test_result_fail("Failed to read %s VL %u FPSIMD data\n", + type->name, vl); + goto out; + } + + for (i = 0; i < __SVE_NUM_ZREGS; i++) { + __uint128_t tmp = 0; + + /* + * Z regs are stored endianness invariant, this won't + * work for big endian + */ + memcpy(&tmp, write_buf + SVE_PT_SVE_ZREG_OFFSET(vq, i), + sizeof(tmp)); + + if (tmp != fpsimd_state.vregs[i]) { + printf("# Mismatch in FPSIMD for %s VL %u Z%d\n", + type->name, vl, i); + errors++; + } + } + + check_u32(vl, "FPSR", write_buf + SVE_PT_SVE_FPSR_OFFSET(vq), + &fpsimd_state.fpsr, &errors); + check_u32(vl, "FPCR", write_buf + SVE_PT_SVE_FPCR_OFFSET(vq), + &fpsimd_state.fpcr, &errors); + + ksft_test_result(errors == 0, "Set and get FPSIMD data for %s VL %u\n", + type->name, vl); + +out: + free(write_buf); } static int do_parent(pid_t child) { int ret = EXIT_FAILURE; pid_t pid; - int status; + int status, i; siginfo_t si; - void *svebuf = NULL, *newsvebuf; - size_t svebufsz = 0, newsvebufsz; - struct user_sve_header *sve, *new_sve; - struct user_fpsimd_state *fpsimd; - unsigned int i, j; - unsigned char *p; - unsigned int vq; + unsigned int vq, vl; + bool vl_supported; /* Attach to the child */ while (1) { @@ -167,8 +509,6 @@ static int do_parent(pid_t child) if (WIFEXITED(status) || WIFSIGNALED(status)) ksft_exit_fail_msg("Child died unexpectedly\n"); - ksft_test_result(WIFSTOPPED(status), "WIFSTOPPED(%d)\n", - status); if (!WIFSTOPPED(status)) goto error; @@ -203,98 +543,55 @@ static int do_parent(pid_t child) } } - sve = get_sve(pid, &svebuf, &svebufsz); - if (!sve) { - int e = errno; + for (i = 0; i < ARRAY_SIZE(vec_types); i++) { + /* FPSIMD via SVE regset */ + if (getauxval(vec_types[i].hwcap_type) & vec_types[i].hwcap) { + ptrace_sve_fpsimd(child, &vec_types[i]); + } else { + ksft_test_result_skip("%s FPSIMD get via SVE\n", + vec_types[i].name); + ksft_test_result_skip("%s FPSIMD set via SVE\n", + vec_types[i].name); + ksft_test_result_skip("%s set read via FPSIMD\n", + vec_types[i].name); + } - ksft_test_result_fail("get_sve: %s\n", strerror(errno)); - if (e == ESRCH) - goto disappeared; + /* prctl() flags */ + 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); + } - goto error; - } else { - ksft_test_result_pass("get_sve\n"); - } + /* Step through every possible VQ */ + for (vq = SVE_VQ_MIN; vq <= SVE_VQ_MAX; vq++) { + vl = sve_vl_from_vq(vq); - ksft_test_result((sve->flags & SVE_PT_REGS_MASK) == SVE_PT_REGS_FPSIMD, - "FPSIMD registers\n"); - if ((sve->flags & SVE_PT_REGS_MASK) != SVE_PT_REGS_FPSIMD) - goto error; + /* First, try to set this vector length */ + if (getauxval(vec_types[i].hwcap_type) & + vec_types[i].hwcap) { + ptrace_set_get_vl(child, &vec_types[i], vl, + &vl_supported); + } else { + ksft_test_result_skip("%s get/set VL %d\n", + vec_types[i].name, vl); + vl_supported = false; + } - fpsimd = (struct user_fpsimd_state *)((char *)sve + - SVE_PT_FPSIMD_OFFSET); - for (i = 0; i < 32; ++i) { - p = (unsigned char *)&fpsimd->vregs[i]; - - for (j = 0; j < sizeof fpsimd->vregs[i]; ++j) - p[j] = j; - } - - if (set_sve(pid, sve)) { - int e = errno; - - ksft_test_result_fail("set_sve(FPSIMD): %s\n", - strerror(errno)); - if (e == ESRCH) - goto disappeared; - - goto error; - } - - vq = sve_vq_from_vl(sve->vl); - - newsvebufsz = SVE_PT_SVE_ZREG_OFFSET(vq, 1); - new_sve = newsvebuf = malloc(newsvebufsz); - if (!new_sve) { - errno = ENOMEM; - perror(NULL); - goto error; - } - - *new_sve = *sve; - new_sve->flags &= ~SVE_PT_REGS_MASK; - new_sve->flags |= SVE_PT_REGS_SVE; - memset((char *)new_sve + SVE_PT_SVE_ZREG_OFFSET(vq, 0), - 0, SVE_PT_SVE_ZREG_SIZE(vq)); - new_sve->size = SVE_PT_SVE_ZREG_OFFSET(vq, 1); - if (set_sve(pid, new_sve)) { - int e = errno; - - ksft_test_result_fail("set_sve(ZREG): %s\n", strerror(errno)); - if (e == ESRCH) - goto disappeared; - - goto error; - } - - new_sve = get_sve(pid, &newsvebuf, &newsvebufsz); - if (!new_sve) { - int e = errno; - - ksft_test_result_fail("get_sve(ZREG): %s\n", strerror(errno)); - if (e == ESRCH) - goto disappeared; - - goto error; - } - - ksft_test_result((new_sve->flags & SVE_PT_REGS_MASK) == SVE_PT_REGS_SVE, - "SVE registers\n"); - if ((new_sve->flags & SVE_PT_REGS_MASK) != SVE_PT_REGS_SVE) - goto error; - - dump_sve_regs(new_sve, 3, sizeof fpsimd->vregs[0]); - - p = (unsigned char *)new_sve + SVE_PT_SVE_ZREG_OFFSET(vq, 1); - for (i = 0; i < sizeof fpsimd->vregs[0]; ++i) { - unsigned char expected = i; - - if (__BYTE_ORDER == __BIG_ENDIAN) - expected = sizeof fpsimd->vregs[0] - 1 - expected; - - ksft_test_result(p[i] == expected, "p[%d] == expected\n", i); - if (p[i] != expected) - goto error; + /* If the VL is supported validate data set/get */ + if (vl_supported) { + ptrace_set_sve_get_sve_data(child, &vec_types[i], vl); + ptrace_set_sve_get_fpsimd_data(child, &vec_types[i], vl); + } else { + ksft_test_result_skip("%s set SVE get SVE for VL %d\n", + vec_types[i].name, vl); + ksft_test_result_skip("%s set SVE get FPSIMD for VL %d\n", + vec_types[i].name, vl); + } + } } ret = EXIT_SUCCESS; @@ -309,20 +606,16 @@ static int do_parent(pid_t child) int main(void) { int ret = EXIT_SUCCESS; - __uint128_t v[NR_VREGS]; pid_t child; + srandom(getpid()); + ksft_print_header(); - ksft_set_plan(20); + ksft_set_plan(EXPECTED_TESTS); if (!(getauxval(AT_HWCAP) & HWCAP_SVE)) ksft_exit_skip("SVE not available\n"); - sve_store_patterns(v); - - if (!check_vregs(v)) - ksft_exit_fail_msg("Initial check_vregs() failed\n"); - child = fork(); if (!child) return do_child(); diff --git a/tools/testing/selftests/arm64/fp/sve-test.S b/tools/testing/selftests/arm64/fp/sve-test.S index e3e08d9c70..f5b1b48fff 100644 --- a/tools/testing/selftests/arm64/fp/sve-test.S +++ b/tools/testing/selftests/arm64/fp/sve-test.S @@ -46,130 +46,6 @@ define_accessor getz, NZR, _sve_str_v define_accessor setp, NPR, _sve_ldr_p define_accessor getp, NPR, _sve_str_p -// Print a single character x0 to stdout -// Clobbers x0-x2,x8 -function putc - str x0, [sp, #-16]! - - mov x0, #1 // STDOUT_FILENO - mov x1, sp - mov x2, #1 - mov x8, #__NR_write - svc #0 - - add sp, sp, #16 - ret -endfunction - -// Print a NUL-terminated string starting at address x0 to stdout -// Clobbers x0-x3,x8 -function puts - mov x1, x0 - - mov x2, #0 -0: ldrb w3, [x0], #1 - cbz w3, 1f - add x2, x2, #1 - b 0b - -1: mov w0, #1 // STDOUT_FILENO - mov x8, #__NR_write - svc #0 - - ret -endfunction - -// Utility macro to print a literal string -// Clobbers x0-x4,x8 -.macro puts string - .pushsection .rodata.str1.1, "aMS", 1 -.L__puts_literal\@: .string "\string" - .popsection - - ldr x0, =.L__puts_literal\@ - bl puts -.endm - -// Print an unsigned decimal number x0 to stdout -// Clobbers x0-x4,x8 -function putdec - mov x1, sp - str x30, [sp, #-32]! // Result can't be > 20 digits - - mov x2, #0 - strb w2, [x1, #-1]! // Write the NUL terminator - - mov x2, #10 -0: udiv x3, x0, x2 // div-mod loop to generate the digits - msub x0, x3, x2, x0 - add w0, w0, #'0' - strb w0, [x1, #-1]! - mov x0, x3 - cbnz x3, 0b - - ldrb w0, [x1] - cbnz w0, 1f - mov w0, #'0' // Print "0" for 0, not "" - strb w0, [x1, #-1]! - -1: mov x0, x1 - bl puts - - ldr x30, [sp], #32 - ret -endfunction - -// Print an unsigned decimal number x0 to stdout, followed by a newline -// Clobbers x0-x5,x8 -function putdecn - mov x5, x30 - - bl putdec - mov x0, #'\n' - bl putc - - ret x5 -endfunction - -// Clobbers x0-x3,x8 -function puthexb - str x30, [sp, #-0x10]! - - mov w3, w0 - lsr w0, w0, #4 - bl puthexnibble - mov w0, w3 - - ldr x30, [sp], #0x10 - // fall through to puthexnibble -endfunction -// Clobbers x0-x2,x8 -function puthexnibble - and w0, w0, #0xf - cmp w0, #10 - blo 1f - add w0, w0, #'a' - ('9' + 1) -1: add w0, w0, #'0' - b putc -endfunction - -// x0=data in, x1=size in, clobbers x0-x5,x8 -function dumphex - str x30, [sp, #-0x10]! - - mov x4, x0 - mov x5, x1 - -0: subs x5, x5, #1 - b.lo 1f - ldrb w0, [x4], #1 - bl puthexb - b 0b - -1: ldr x30, [sp], #0x10 - ret -endfunction - // Declare some storate space to shadow the SVE register contents: .pushsection .text .data @@ -184,18 +60,6 @@ scratch: .space MAXVL_B .popsection -// Trivial memory copy: copy x2 bytes, starting at address x1, to address x0. -// Clobbers x0-x3 -function memcpy - cmp x2, #0 - b.eq 1f -0: ldrb w3, [x1], #1 - strb w3, [x0], #1 - subs x2, x2, #1 - b.ne 0b -1: ret -endfunction - // Generate a test pattern for storage in SVE registers // x0: pid (16 bits) // x1: register number (6 bits) @@ -316,33 +180,6 @@ function setup_ffr ret x4 endfunction -// Fill x1 bytes starting at x0 with 0xae (for canary purposes) -// Clobbers x1, x2. -function memfill_ae - mov w2, #0xae - b memfill -endfunction - -// Fill x1 bytes starting at x0 with 0. -// Clobbers x1, x2. -function memclr - mov w2, #0 -endfunction - // fall through to memfill - -// Trivial memory fill: fill x1 bytes starting at address x0 with byte w2 -// Clobbers x1 -function memfill - cmp x1, #0 - b.eq 1f - -0: strb w2, [x0], #1 - subs x1, x1, #1 - b.ne 0b - -1: ret -endfunction - // Trivial memory compare: compare x2 bytes starting at address x0 with // bytes starting at address x1. // Returns only if all bytes match; otherwise, the program is aborted. diff --git a/tools/testing/selftests/arm64/fp/vec-syscfg.c b/tools/testing/selftests/arm64/fp/vec-syscfg.c index c02071dcb5..c90658811a 100644 --- a/tools/testing/selftests/arm64/fp/vec-syscfg.c +++ b/tools/testing/selftests/arm64/fp/vec-syscfg.c @@ -21,8 +21,6 @@ #include "../../kselftest.h" #include "rdvl.h" -#define ARRAY_SIZE(a) (sizeof(a) / sizeof(a[0])) - #define ARCH_MIN_VL SVE_VL_MIN struct vec_data { @@ -109,7 +107,7 @@ static int get_child_rdvl(struct vec_data *data) /* exec() a new binary which puts the VL on stdout */ ret = execl(data->rdvl_binary, data->rdvl_binary, NULL); - fprintf(stderr, "execl(%s) failed: %d\n", + fprintf(stderr, "execl(%s) failed: %d (%s)\n", data->rdvl_binary, errno, strerror(errno)); exit(EXIT_FAILURE); @@ -180,7 +178,6 @@ static int file_read_integer(const char *name, int *val) static int file_write_integer(const char *name, int val) { FILE *f; - int ret; f = fopen(name, "w"); if (!f) { @@ -192,11 +189,6 @@ static int file_write_integer(const char *name, int val) fprintf(f, "%d", val); fclose(f); - if (ret < 0) { - ksft_test_result_fail("Error writing %d to %s\n", - val, name); - return -1; - } return 0; } @@ -335,12 +327,9 @@ static void prctl_set_same(struct vec_data *data) return; } - if (cur_vl != data->rdvl()) - ksft_test_result_pass("%s current VL is %d\n", - data->name, ret); - else - ksft_test_result_fail("%s prctl() VL %d but RDVL is %d\n", - data->name, ret, data->rdvl()); + ksft_test_result(cur_vl == data->rdvl(), + "%s set VL %d and have VL %d\n", + data->name, cur_vl, data->rdvl()); } /* Can we set a new VL for this process? */ @@ -549,6 +538,82 @@ static void prctl_set_onexec(struct vec_data *data) file_write_integer(data->default_vl_file, data->default_vl); } +/* For each VQ verify that setting via prctl() does the right thing */ +static void prctl_set_all_vqs(struct vec_data *data) +{ + int ret, vq, vl, new_vl; + int errors = 0; + + if (!data->min_vl || !data->max_vl) { + ksft_test_result_skip("%s Failed to enumerate VLs, not testing VL setting\n", + data->name); + return; + } + + for (vq = SVE_VQ_MIN; vq <= SVE_VQ_MAX; vq++) { + vl = sve_vl_from_vq(vq); + + /* Attempt to set the VL */ + ret = prctl(data->prctl_set, vl); + if (ret < 0) { + errors++; + ksft_print_msg("%s prctl set failed for %d: %d (%s)\n", + data->name, vl, + errno, strerror(errno)); + continue; + } + + new_vl = ret & PR_SVE_VL_LEN_MASK; + + /* Check that we actually have the reported new VL */ + if (data->rdvl() != new_vl) { + ksft_print_msg("Set %s VL %d but RDVL reports %d\n", + data->name, new_vl, data->rdvl()); + errors++; + } + + /* Was that the VL we asked for? */ + if (new_vl == vl) + continue; + + /* Should round up to the minimum VL if below it */ + if (vl < data->min_vl) { + if (new_vl != data->min_vl) { + ksft_print_msg("%s VL %d returned %d not minimum %d\n", + data->name, vl, new_vl, + data->min_vl); + errors++; + } + + continue; + } + + /* Should round down to maximum VL if above it */ + if (vl > data->max_vl) { + if (new_vl != data->max_vl) { + ksft_print_msg("%s VL %d returned %d not maximum %d\n", + data->name, vl, new_vl, + data->max_vl); + errors++; + } + + continue; + } + + /* Otherwise we should've rounded down */ + if (!(new_vl < vl)) { + ksft_print_msg("%s VL %d returned %d, did not round down\n", + data->name, vl, new_vl); + errors++; + + continue; + } + } + + ksft_test_result(errors == 0, "%s prctl() set all VLs, %d errors\n", + data->name, errors); +} + typedef void (*test_type)(struct vec_data *); static const test_type tests[] = { @@ -561,10 +626,12 @@ static const test_type tests[] = { proc_write_max, prctl_get, + prctl_set_same, prctl_set, prctl_set_no_child, prctl_set_for_child, prctl_set_onexec, + prctl_set_all_vqs, }; int main(void) diff --git a/tools/testing/selftests/arm64/signal/test_signals_utils.c b/tools/testing/selftests/arm64/signal/test_signals_utils.c index 22722abc9d..2f8c23af3b 100644 --- a/tools/testing/selftests/arm64/signal/test_signals_utils.c +++ b/tools/testing/selftests/arm64/signal/test_signals_utils.c @@ -310,14 +310,12 @@ int test_setup(struct tdescr *td) int test_run(struct tdescr *td) { - if (td->sig_trig) { - if (td->trigger) - return td->trigger(td); - else - return default_trigger(td); - } else { + if (td->trigger) + return td->trigger(td); + else if (td->sig_trig) + return default_trigger(td); + else return td->run(td, NULL, NULL); - } } void test_result(struct tdescr *td) diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore index 433f8bef26..1dad8d617d 100644 --- a/tools/testing/selftests/bpf/.gitignore +++ b/tools/testing/selftests/bpf/.gitignore @@ -9,8 +9,9 @@ test_tag FEATURE-DUMP.libbpf fixdep test_dev_cgroup -/test_progs* -!test_progs.h +/test_progs +/test_progs-no_alu32 +/test_progs-bpf_gcc test_verifier_log feature test_sock diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 799b88152e..42ffc24e9e 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -23,9 +23,8 @@ BPF_GCC ?= $(shell command -v bpf-gcc;) SAN_CFLAGS ?= CFLAGS += -g -O0 -rdynamic -Wall $(GENFLAGS) $(SAN_CFLAGS) \ -I$(CURDIR) -I$(INCLUDE_DIR) -I$(GENDIR) -I$(LIBDIR) \ - -I$(TOOLSINCDIR) -I$(APIDIR) -I$(OUTPUT) \ - -Dbpf_prog_load=bpf_prog_test_load \ - -Dbpf_load_program=bpf_test_load_program + -I$(TOOLSINCDIR) -I$(APIDIR) -I$(OUTPUT) +LDFLAGS += $(SAN_CFLAGS) LDLIBS += -lcap -lelf -lz -lrt -lpthread # Silence some warnings when compiled with clang @@ -46,10 +45,8 @@ ifneq ($(BPF_GCC),) TEST_GEN_PROGS += test_progs-bpf_gcc endif -TEST_GEN_FILES = test_lwt_ip_encap.o \ - test_tc_edt.o -TEST_FILES = xsk_prereqs.sh \ - $(wildcard progs/btf_dump_test_case_*.c) +TEST_GEN_FILES = test_lwt_ip_encap.o test_tc_edt.o +TEST_FILES = xsk_prereqs.sh $(wildcard progs/btf_dump_test_case_*.c) # Order correspond to 'make run_tests' order TEST_PROGS := test_kmod.sh \ @@ -108,7 +105,10 @@ endif OVERRIDE_TARGETS := 1 override define CLEAN $(call msg,CLEAN) - $(Q)$(RM) -r $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(EXTRA_CLEAN) + $(Q)$(RM) -r $(TEST_GEN_PROGS) + $(Q)$(RM) -r $(TEST_GEN_PROGS_EXTENDED) + $(Q)$(RM) -r $(TEST_GEN_FILES) + $(Q)$(RM) -r $(EXTRA_CLEAN) $(Q)$(MAKE) -C bpf_testmod clean $(Q)$(MAKE) docs-clean endef @@ -122,12 +122,15 @@ BPFOBJ := $(BUILD_DIR)/libbpf/libbpf.a ifneq ($(CROSS_COMPILE),) HOST_BUILD_DIR := $(BUILD_DIR)/host HOST_SCRATCH_DIR := $(OUTPUT)/host-tools +HOST_INCLUDE_DIR := $(HOST_SCRATCH_DIR)/include else HOST_BUILD_DIR := $(BUILD_DIR) HOST_SCRATCH_DIR := $(SCRATCH_DIR) +HOST_INCLUDE_DIR := $(INCLUDE_DIR) endif HOST_BPFOBJ := $(HOST_BUILD_DIR)/libbpf/libbpf.a RESOLVE_BTFIDS := $(HOST_BUILD_DIR)/resolve_btfids/resolve_btfids +RUNQSLOWER_OUTPUT := $(BUILD_DIR)/runqslower/ VMLINUX_BTF_PATHS ?= $(if $(O),$(O)/vmlinux) \ $(if $(KBUILD_OUTPUT),$(KBUILD_OUTPUT)/vmlinux) \ @@ -152,7 +155,7 @@ $(notdir $(TEST_GEN_PROGS) \ # sort removes libbpf duplicates when not cross-building MAKE_DIRS := $(sort $(BUILD_DIR)/libbpf $(HOST_BUILD_DIR)/libbpf \ $(HOST_BUILD_DIR)/bpftool $(HOST_BUILD_DIR)/resolve_btfids \ - $(INCLUDE_DIR)) + $(RUNQSLOWER_OUTPUT) $(INCLUDE_DIR)) $(MAKE_DIRS): $(call msg,MKDIR,,$@) $(Q)mkdir -p $@ @@ -167,7 +170,7 @@ $(OUTPUT)/%:%.c $(OUTPUT)/urandom_read: urandom_read.c $(call msg,BINARY,,$@) - $(Q)$(CC) $(LDFLAGS) -o $@ $< $(LDLIBS) -Wl,--build-id=sha1 + $(Q)$(CC) $(CFLAGS) $(LDFLAGS) $< $(LDLIBS) -Wl,--build-id=sha1 -o $@ $(OUTPUT)/bpf_testmod.ko: $(VMLINUX_BTF) $(wildcard bpf_testmod/Makefile bpf_testmod/*.[ch]) $(call msg,MOD,,$@) @@ -175,41 +178,51 @@ $(OUTPUT)/bpf_testmod.ko: $(VMLINUX_BTF) $(wildcard bpf_testmod/Makefile bpf_tes $(Q)$(MAKE) $(submake_extras) -C bpf_testmod $(Q)cp bpf_testmod/bpf_testmod.ko $@ -$(OUTPUT)/test_stub.o: test_stub.c $(BPFOBJ) - $(call msg,CC,,$@) - $(Q)$(CC) -c $(CFLAGS) -o $@ $< - DEFAULT_BPFTOOL := $(HOST_SCRATCH_DIR)/sbin/bpftool -$(OUTPUT)/runqslower: $(BPFOBJ) | $(DEFAULT_BPFTOOL) - $(Q)$(MAKE) $(submake_extras) -C $(TOOLSDIR)/bpf/runqslower \ - OUTPUT=$(SCRATCH_DIR)/ VMLINUX_BTF=$(VMLINUX_BTF) \ - BPFOBJ=$(BPFOBJ) BPF_INCLUDE=$(INCLUDE_DIR) && \ - cp $(SCRATCH_DIR)/runqslower $@ +$(OUTPUT)/runqslower: $(BPFOBJ) | $(DEFAULT_BPFTOOL) $(RUNQSLOWER_OUTPUT) + $(Q)$(MAKE) $(submake_extras) -C $(TOOLSDIR)/bpf/runqslower \ + OUTPUT=$(RUNQSLOWER_OUTPUT) VMLINUX_BTF=$(VMLINUX_BTF) \ + BPFTOOL_OUTPUT=$(HOST_BUILD_DIR)/bpftool/ \ + BPFOBJ_OUTPUT=$(BUILD_DIR)/libbpf \ + BPFOBJ=$(BPFOBJ) BPF_INCLUDE=$(INCLUDE_DIR) && \ + cp $(RUNQSLOWER_OUTPUT)runqslower $@ TEST_GEN_PROGS_EXTENDED += $(DEFAULT_BPFTOOL) -$(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED): $(OUTPUT)/test_stub.o $(BPFOBJ) +$(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED): $(BPFOBJ) -$(OUTPUT)/test_dev_cgroup: cgroup_helpers.c -$(OUTPUT)/test_skb_cgroup_id_user: cgroup_helpers.c -$(OUTPUT)/test_sock: cgroup_helpers.c -$(OUTPUT)/test_sock_addr: cgroup_helpers.c -$(OUTPUT)/test_sockmap: cgroup_helpers.c -$(OUTPUT)/test_tcpnotify_user: cgroup_helpers.c trace_helpers.c -$(OUTPUT)/get_cgroup_id_user: cgroup_helpers.c -$(OUTPUT)/test_cgroup_storage: cgroup_helpers.c -$(OUTPUT)/test_sock_fields: cgroup_helpers.c -$(OUTPUT)/test_sysctl: cgroup_helpers.c +CGROUP_HELPERS := $(OUTPUT)/cgroup_helpers.o +TESTING_HELPERS := $(OUTPUT)/testing_helpers.o +TRACE_HELPERS := $(OUTPUT)/trace_helpers.o + +$(OUTPUT)/test_dev_cgroup: $(CGROUP_HELPERS) $(TESTING_HELPERS) +$(OUTPUT)/test_skb_cgroup_id_user: $(CGROUP_HELPERS) $(TESTING_HELPERS) +$(OUTPUT)/test_sock: $(CGROUP_HELPERS) $(TESTING_HELPERS) +$(OUTPUT)/test_sock_addr: $(CGROUP_HELPERS) $(TESTING_HELPERS) +$(OUTPUT)/test_sockmap: $(CGROUP_HELPERS) $(TESTING_HELPERS) +$(OUTPUT)/test_tcpnotify_user: $(CGROUP_HELPERS) $(TESTING_HELPERS) $(TRACE_HELPERS) +$(OUTPUT)/get_cgroup_id_user: $(CGROUP_HELPERS) $(TESTING_HELPERS) +$(OUTPUT)/test_cgroup_storage: $(CGROUP_HELPERS) $(TESTING_HELPERS) +$(OUTPUT)/test_sock_fields: $(CGROUP_HELPERS) $(TESTING_HELPERS) +$(OUTPUT)/test_sysctl: $(CGROUP_HELPERS) $(TESTING_HELPERS) +$(OUTPUT)/test_tag: $(TESTING_HELPERS) +$(OUTPUT)/test_lirc_mode2_user: $(TESTING_HELPERS) +$(OUTPUT)/xdping: $(TESTING_HELPERS) +$(OUTPUT)/flow_dissector_load: $(TESTING_HELPERS) +$(OUTPUT)/test_maps: $(TESTING_HELPERS) +$(OUTPUT)/test_verifier: $(TESTING_HELPERS) BPFTOOL ?= $(DEFAULT_BPFTOOL) $(DEFAULT_BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile) \ $(HOST_BPFOBJ) | $(HOST_BUILD_DIR)/bpftool $(Q)$(MAKE) $(submake_extras) -C $(BPFTOOLDIR) \ - CC=$(HOSTCC) LD=$(HOSTLD) \ + ARCH= CROSS_COMPILE= CC=$(HOSTCC) LD=$(HOSTLD) \ EXTRA_CFLAGS='-g -O0' \ OUTPUT=$(HOST_BUILD_DIR)/bpftool/ \ - prefix= DESTDIR=$(HOST_SCRATCH_DIR)/ install + LIBBPF_OUTPUT=$(HOST_BUILD_DIR)/libbpf/ \ + LIBBPF_DESTDIR=$(HOST_SCRATCH_DIR)/ \ + prefix= DESTDIR=$(HOST_SCRATCH_DIR)/ install-bin all: docs @@ -224,18 +237,18 @@ docs-clean: prefix= OUTPUT=$(OUTPUT)/ DESTDIR=$(OUTPUT)/ $@ $(BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile) \ - ../../../include/uapi/linux/bpf.h \ - | $(INCLUDE_DIR) $(BUILD_DIR)/libbpf + $(APIDIR)/linux/bpf.h \ + | $(BUILD_DIR)/libbpf $(Q)$(MAKE) $(submake_extras) -C $(BPFDIR) OUTPUT=$(BUILD_DIR)/libbpf/ \ EXTRA_CFLAGS='-g -O0' \ DESTDIR=$(SCRATCH_DIR) prefix= all install_headers ifneq ($(BPFOBJ),$(HOST_BPFOBJ)) -$(HOST_BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile) \ - ../../../include/uapi/linux/bpf.h \ - | $(INCLUDE_DIR) $(HOST_BUILD_DIR)/libbpf +$(HOST_BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile) \ + $(APIDIR)/linux/bpf.h \ + | $(HOST_BUILD_DIR)/libbpf $(Q)$(MAKE) $(submake_extras) -C $(BPFDIR) \ - EXTRA_CFLAGS='-g -O0' \ + EXTRA_CFLAGS='-g -O0' ARCH= CROSS_COMPILE= \ OUTPUT=$(HOST_BUILD_DIR)/libbpf/ CC=$(HOSTCC) LD=$(HOSTLD) \ DESTDIR=$(HOST_SCRATCH_DIR)/ prefix= all install_headers endif @@ -258,6 +271,7 @@ $(RESOLVE_BTFIDS): $(HOST_BPFOBJ) | $(HOST_BUILD_DIR)/resolve_btfids \ $(TOOLSDIR)/lib/str_error_r.c $(Q)$(MAKE) $(submake_extras) -C $(TOOLSDIR)/bpf/resolve_btfids \ CC=$(HOSTCC) LD=$(HOSTLD) AR=$(HOSTAR) \ + LIBBPF_INCLUDE=$(HOST_INCLUDE_DIR) \ OUTPUT=$(HOST_BUILD_DIR)/resolve_btfids/ BPFOBJ=$(HOST_BPFOBJ) # Get Clang's default includes on this system, as opposed to those seen by @@ -269,7 +283,7 @@ $(RESOLVE_BTFIDS): $(HOST_BPFOBJ) | $(HOST_BUILD_DIR)/resolve_btfids \ define get_sys_includes $(shell $(1) -v -E - &1 \ | sed -n '/<...> search starts here:/,/End of search list./{ s| \(/.*\)|-idirafter \1|p }') \ -$(shell $(1) -dM -E - $$@ + $(Q)$$(BPFTOOL) gen skeleton -L $$(<:.o=.linked3.o) name $$(notdir $$(<:.o=_lskel)) > $$@ $(TRUNNER_BPF_SKELS_LINKED): $(TRUNNER_BPF_OBJS) $(BPFTOOL) | $(TRUNNER_OUTPUT) $$(call msg,LINK-BPF,$(TRUNNER_BINARY),$$(@:.skel.h=.o)) @@ -411,10 +428,9 @@ ifeq ($($(TRUNNER_TESTS_DIR)-tests-hdr),) $(TRUNNER_TESTS_DIR)-tests-hdr := y $(TRUNNER_TESTS_HDR): $(TRUNNER_TESTS_DIR)/*.c $$(call msg,TEST-HDR,$(TRUNNER_BINARY),$$@) - $$(shell ( cd $(TRUNNER_TESTS_DIR); \ - echo '/* Generated header, do not edit */'; \ - ls *.c 2> /dev/null | \ - sed -e 's@\([^\.]*\)\.c@DEFINE_TEST(\1)@'; \ + $$(shell (echo '/* Generated header, do not edit */'; \ + sed -n -E 's/^void (serial_)?test_([a-zA-Z0-9_]+)\((void)?\).*/DEFINE_TEST(\2)/p' \ + $(TRUNNER_TESTS_DIR)/*.c | sort ; \ ) > $$@) endif @@ -453,7 +469,7 @@ $(OUTPUT)/$(TRUNNER_BINARY): $(TRUNNER_TEST_OBJS) \ | $(TRUNNER_BINARY)-extras $$(call msg,BINARY,,$$@) $(Q)$$(CC) $$(CFLAGS) $$(filter %.a %.o,$$^) $$(LDLIBS) -o $$@ - $(Q)$(RESOLVE_BTFIDS) --no-fail --btf $(TRUNNER_OUTPUT)/btf_data.o $$@ + $(Q)$(RESOLVE_BTFIDS) --btf $(TRUNNER_OUTPUT)/btf_data.o $$@ endef @@ -462,13 +478,12 @@ TRUNNER_TESTS_DIR := prog_tests TRUNNER_BPF_PROGS_DIR := progs TRUNNER_EXTRA_SOURCES := test_progs.c cgroup_helpers.c trace_helpers.c \ network_helpers.c testing_helpers.c \ - btf_helpers.c flow_dissector_load.h + btf_helpers.c flow_dissector_load.h TRUNNER_EXTRA_FILES := $(OUTPUT)/urandom_read $(OUTPUT)/bpf_testmod.ko \ ima_setup.sh \ $(wildcard progs/btf_dump_test_case_*.c) TRUNNER_BPF_BUILD_RULE := CLANG_BPF_BUILD_RULE -TRUNNER_BPF_CFLAGS := $(BPF_CFLAGS) $(CLANG_CFLAGS) -TRUNNER_BPF_CFLAGS += -DENABLE_ATOMICS_TESTS +TRUNNER_BPF_CFLAGS := $(BPF_CFLAGS) $(CLANG_CFLAGS) -DENABLE_ATOMICS_TESTS $(eval $(call DEFINE_TEST_RUNNER,test_progs)) # Define test_progs-no_alu32 test runner. @@ -513,22 +528,30 @@ $(OUTPUT)/test_cpp: test_cpp.cpp $(OUTPUT)/test_core_extern.skel.h $(BPFOBJ) $(Q)$(CXX) $(CFLAGS) $(filter %.a %.o %.cpp,$^) $(LDLIBS) -o $@ # Benchmark runner -$(OUTPUT)/bench_%.o: benchs/bench_%.c bench.h +$(OUTPUT)/bench_%.o: benchs/bench_%.c bench.h $(BPFOBJ) $(call msg,CC,,$@) - $(Q)$(CC) $(CFLAGS) -c $(filter %.c,$^) $(LDLIBS) -o $@ + $(Q)$(CC) $(CFLAGS) -O2 -c $(filter %.c,$^) $(LDLIBS) -o $@ $(OUTPUT)/bench_rename.o: $(OUTPUT)/test_overhead.skel.h $(OUTPUT)/bench_trigger.o: $(OUTPUT)/trigger_bench.skel.h $(OUTPUT)/bench_ringbufs.o: $(OUTPUT)/ringbuf_bench.skel.h \ $(OUTPUT)/perfbuf_bench.skel.h -$(OUTPUT)/bench.o: bench.h testing_helpers.h +$(OUTPUT)/bench_bloom_filter_map.o: $(OUTPUT)/bloom_filter_bench.skel.h +$(OUTPUT)/bench_bpf_loop.o: $(OUTPUT)/bpf_loop_bench.skel.h +$(OUTPUT)/bench_strncmp.o: $(OUTPUT)/strncmp_bench.skel.h +$(OUTPUT)/bench.o: bench.h testing_helpers.h $(BPFOBJ) $(OUTPUT)/bench: LDLIBS += -lm -$(OUTPUT)/bench: $(OUTPUT)/bench.o $(OUTPUT)/testing_helpers.o \ +$(OUTPUT)/bench: $(OUTPUT)/bench.o \ + $(TESTING_HELPERS) \ + $(TRACE_HELPERS) \ $(OUTPUT)/bench_count.o \ $(OUTPUT)/bench_rename.o \ $(OUTPUT)/bench_trigger.o \ - $(OUTPUT)/bench_ringbufs.o + $(OUTPUT)/bench_ringbufs.o \ + $(OUTPUT)/bench_bloom_filter_map.o \ + $(OUTPUT)/bench_bpf_loop.o \ + $(OUTPUT)/bench_strncmp.o $(call msg,BINARY,,$@) - $(Q)$(CC) $(LDFLAGS) -o $@ $(filter %.a %.o,$^) $(LDLIBS) + $(Q)$(CC) $(CFLAGS) $(LDFLAGS) $(filter %.a %.o,$^) $(LDLIBS) -o $@ EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) $(SCRATCH_DIR) $(HOST_SCRATCH_DIR) \ prog_tests/tests.h map_tests/tests.h verifier/tests.h \ diff --git a/tools/testing/selftests/bpf/README.rst b/tools/testing/selftests/bpf/README.rst index 9b17f28674..42ef250c7a 100644 --- a/tools/testing/selftests/bpf/README.rst +++ b/tools/testing/selftests/bpf/README.rst @@ -201,6 +201,21 @@ Without it, the error from compiling bpf selftests looks like: __ https://reviews.llvm.org/D93563 +btf_tag test and Clang version +============================== + +The btf_tag selftest requires LLVM support to recognize the btf_decl_tag and +btf_type_tag attributes. They are introduced in `Clang 14` [0_, 1_]. + +Without them, the btf_tag selftest will be skipped and you will observe: + +.. code-block:: console + + # btf_tag:SKIP + +.. _0: https://reviews.llvm.org/D111588 +.. _1: https://reviews.llvm.org/D111199 + Clang dependencies for static linking tests =========================================== @@ -228,3 +243,16 @@ To fix this issue, user newer libbpf. .. Links .. _clang reloc patch: https://reviews.llvm.org/D102712 .. _kernel llvm reloc: /Documentation/bpf/llvm_reloc.rst + +Clang dependencies for the u32 spill test (xdpwall) +=================================================== +The xdpwall selftest requires a change in `Clang 14`__. + +Without it, the xdpwall selftest will fail and the error message +from running test_progs will look like: + +.. code-block:: console + + test_xdpwall:FAIL:Does LLVM have https://reviews.llvm.org/D109073? unexpected error: -4007 + +__ https://reviews.llvm.org/D109073 diff --git a/tools/testing/selftests/bpf/bench.c b/tools/testing/selftests/bpf/bench.c index 6ea15b93a2..f973320e6d 100644 --- a/tools/testing/selftests/bpf/bench.c +++ b/tools/testing/selftests/bpf/bench.c @@ -29,26 +29,39 @@ static int libbpf_print_fn(enum libbpf_print_level level, return vfprintf(stderr, format, args); } -static int bump_memlock_rlimit(void) +void setup_libbpf(void) { - struct rlimit rlim_new = { - .rlim_cur = RLIM_INFINITY, - .rlim_max = RLIM_INFINITY, - }; - - return setrlimit(RLIMIT_MEMLOCK, &rlim_new); -} - -void setup_libbpf() -{ - int err; - libbpf_set_strict_mode(LIBBPF_STRICT_ALL); libbpf_set_print(libbpf_print_fn); +} - err = bump_memlock_rlimit(); - if (err) - fprintf(stderr, "failed to increase RLIMIT_MEMLOCK: %d", err); +void false_hits_report_progress(int iter, struct bench_res *res, long delta_ns) +{ + long total = res->false_hits + res->hits + res->drops; + + printf("Iter %3d (%7.3lfus): ", + iter, (delta_ns - 1000000000) / 1000.0); + + printf("%ld false hits of %ld total operations. Percentage = %2.2f %%\n", + res->false_hits, total, ((float)res->false_hits / total) * 100); +} + +void false_hits_report_final(struct bench_res res[], int res_cnt) +{ + long total_hits = 0, total_drops = 0, total_false_hits = 0, total_ops = 0; + int i; + + for (i = 0; i < res_cnt; i++) { + total_hits += res[i].hits; + total_false_hits += res[i].false_hits; + total_drops += res[i].drops; + } + total_ops = total_hits + total_false_hits + total_drops; + + printf("Summary: %ld false hits of %ld total operations. ", + total_false_hits, total_ops); + printf("Percentage = %2.2f %%\n", + ((float)total_false_hits / total_ops) * 100); } void hits_drops_report_progress(int iter, struct bench_res *res, long delta_ns) @@ -63,20 +76,22 @@ void hits_drops_report_progress(int iter, struct bench_res *res, long delta_ns) printf("Iter %3d (%7.3lfus): ", iter, (delta_ns - 1000000000) / 1000.0); - printf("hits %8.3lfM/s (%7.3lfM/prod), drops %8.3lfM/s\n", - hits_per_sec, hits_per_prod, drops_per_sec); + printf("hits %8.3lfM/s (%7.3lfM/prod), drops %8.3lfM/s, total operations %8.3lfM/s\n", + hits_per_sec, hits_per_prod, drops_per_sec, hits_per_sec + drops_per_sec); } void hits_drops_report_final(struct bench_res res[], int res_cnt) { int i; - double hits_mean = 0.0, drops_mean = 0.0; - double hits_stddev = 0.0, drops_stddev = 0.0; + double hits_mean = 0.0, drops_mean = 0.0, total_ops_mean = 0.0; + double hits_stddev = 0.0, drops_stddev = 0.0, total_ops_stddev = 0.0; + double total_ops; for (i = 0; i < res_cnt; i++) { hits_mean += res[i].hits / 1000000.0 / (0.0 + res_cnt); drops_mean += res[i].drops / 1000000.0 / (0.0 + res_cnt); } + total_ops_mean = hits_mean + drops_mean; if (res_cnt > 1) { for (i = 0; i < res_cnt; i++) { @@ -86,14 +101,54 @@ void hits_drops_report_final(struct bench_res res[], int res_cnt) drops_stddev += (drops_mean - res[i].drops / 1000000.0) * (drops_mean - res[i].drops / 1000000.0) / (res_cnt - 1.0); + total_ops = res[i].hits + res[i].drops; + total_ops_stddev += (total_ops_mean - total_ops / 1000000.0) * + (total_ops_mean - total_ops / 1000000.0) / + (res_cnt - 1.0); } hits_stddev = sqrt(hits_stddev); drops_stddev = sqrt(drops_stddev); + total_ops_stddev = sqrt(total_ops_stddev); } printf("Summary: hits %8.3lf \u00B1 %5.3lfM/s (%7.3lfM/prod), ", hits_mean, hits_stddev, hits_mean / env.producer_cnt); - printf("drops %8.3lf \u00B1 %5.3lfM/s\n", + printf("drops %8.3lf \u00B1 %5.3lfM/s, ", drops_mean, drops_stddev); + printf("total operations %8.3lf \u00B1 %5.3lfM/s\n", + total_ops_mean, total_ops_stddev); +} + +void ops_report_progress(int iter, struct bench_res *res, long delta_ns) +{ + double hits_per_sec, hits_per_prod; + + hits_per_sec = res->hits / 1000000.0 / (delta_ns / 1000000000.0); + hits_per_prod = hits_per_sec / env.producer_cnt; + + printf("Iter %3d (%7.3lfus): ", iter, (delta_ns - 1000000000) / 1000.0); + + printf("hits %8.3lfM/s (%7.3lfM/prod)\n", hits_per_sec, hits_per_prod); +} + +void ops_report_final(struct bench_res res[], int res_cnt) +{ + double hits_mean = 0.0, hits_stddev = 0.0; + int i; + + for (i = 0; i < res_cnt; i++) + hits_mean += res[i].hits / 1000000.0 / (0.0 + res_cnt); + + if (res_cnt > 1) { + for (i = 0; i < res_cnt; i++) + hits_stddev += (hits_mean - res[i].hits / 1000000.0) * + (hits_mean - res[i].hits / 1000000.0) / + (res_cnt - 1.0); + + hits_stddev = sqrt(hits_stddev); + } + printf("Summary: throughput %8.3lf \u00B1 %5.3lf M ops/s (%7.3lfM ops/prod), ", + hits_mean, hits_stddev, hits_mean / env.producer_cnt); + printf("latency %8.3lf ns/op\n", 1000.0 / hits_mean * env.producer_cnt); } const char *argp_program_version = "benchmark"; @@ -132,9 +187,15 @@ static const struct argp_option opts[] = { }; extern struct argp bench_ringbufs_argp; +extern struct argp bench_bloom_map_argp; +extern struct argp bench_bpf_loop_argp; +extern struct argp bench_strncmp_argp; static const struct argp_child bench_parsers[] = { { &bench_ringbufs_argp, 0, "Ring buffers benchmark", 0 }, + { &bench_bloom_map_argp, 0, "Bloom filter map benchmark", 0 }, + { &bench_bpf_loop_argp, 0, "bpf_loop helper benchmark", 0 }, + { &bench_strncmp_argp, 0, "bpf_strncmp helper benchmark", 0 }, {}, }; @@ -319,10 +380,23 @@ extern const struct bench bench_trig_kprobe; extern const struct bench bench_trig_fentry; extern const struct bench bench_trig_fentry_sleep; extern const struct bench bench_trig_fmodret; +extern const struct bench bench_trig_uprobe_base; +extern const struct bench bench_trig_uprobe_with_nop; +extern const struct bench bench_trig_uretprobe_with_nop; +extern const struct bench bench_trig_uprobe_without_nop; +extern const struct bench bench_trig_uretprobe_without_nop; extern const struct bench bench_rb_libbpf; extern const struct bench bench_rb_custom; extern const struct bench bench_pb_libbpf; extern const struct bench bench_pb_custom; +extern const struct bench bench_bloom_lookup; +extern const struct bench bench_bloom_update; +extern const struct bench bench_bloom_false_positive; +extern const struct bench bench_hashmap_without_bloom; +extern const struct bench bench_hashmap_with_bloom; +extern const struct bench bench_bpf_loop; +extern const struct bench bench_strncmp_no_helper; +extern const struct bench bench_strncmp_helper; static const struct bench *benchs[] = { &bench_count_global, @@ -340,10 +414,23 @@ static const struct bench *benchs[] = { &bench_trig_fentry, &bench_trig_fentry_sleep, &bench_trig_fmodret, + &bench_trig_uprobe_base, + &bench_trig_uprobe_with_nop, + &bench_trig_uretprobe_with_nop, + &bench_trig_uprobe_without_nop, + &bench_trig_uretprobe_without_nop, &bench_rb_libbpf, &bench_rb_custom, &bench_pb_libbpf, &bench_pb_custom, + &bench_bloom_lookup, + &bench_bloom_update, + &bench_bloom_false_positive, + &bench_hashmap_without_bloom, + &bench_hashmap_with_bloom, + &bench_bpf_loop, + &bench_strncmp_no_helper, + &bench_strncmp_helper, }; static void setup_benchmark() diff --git a/tools/testing/selftests/bpf/bench.h b/tools/testing/selftests/bpf/bench.h index c1f48a473b..fb3e213df3 100644 --- a/tools/testing/selftests/bpf/bench.h +++ b/tools/testing/selftests/bpf/bench.h @@ -33,12 +33,13 @@ struct env { struct bench_res { long hits; long drops; + long false_hits; }; struct bench { const char *name; - void (*validate)(); - void (*setup)(); + void (*validate)(void); + void (*setup)(void); void *(*producer_thread)(void *ctx); void *(*consumer_thread)(void *ctx); void (*measure)(struct bench_res* res); @@ -53,11 +54,16 @@ struct counter { extern struct env env; extern const struct bench *bench; -void setup_libbpf(); +void setup_libbpf(void); void hits_drops_report_progress(int iter, struct bench_res *res, long delta_ns); void hits_drops_report_final(struct bench_res res[], int res_cnt); +void false_hits_report_progress(int iter, struct bench_res *res, long delta_ns); +void false_hits_report_final(struct bench_res res[], int res_cnt); +void ops_report_progress(int iter, struct bench_res *res, long delta_ns); +void ops_report_final(struct bench_res res[], int res_cnt); -static inline __u64 get_time_ns() { +static inline __u64 get_time_ns(void) +{ struct timespec t; clock_gettime(CLOCK_MONOTONIC, &t); diff --git a/tools/testing/selftests/bpf/benchs/bench_count.c b/tools/testing/selftests/bpf/benchs/bench_count.c index befba7a826..078972ce20 100644 --- a/tools/testing/selftests/bpf/benchs/bench_count.c +++ b/tools/testing/selftests/bpf/benchs/bench_count.c @@ -36,7 +36,7 @@ static struct count_local_ctx { struct counter *hits; } count_local_ctx; -static void count_local_setup() +static void count_local_setup(void) { struct count_local_ctx *ctx = &count_local_ctx; diff --git a/tools/testing/selftests/bpf/benchs/bench_rename.c b/tools/testing/selftests/bpf/benchs/bench_rename.c index c7ec114eca..3c203b6d6a 100644 --- a/tools/testing/selftests/bpf/benchs/bench_rename.c +++ b/tools/testing/selftests/bpf/benchs/bench_rename.c @@ -11,7 +11,7 @@ static struct ctx { int fd; } ctx; -static void validate() +static void validate(void) { if (env.producer_cnt != 1) { fprintf(stderr, "benchmark doesn't support multi-producer!\n"); @@ -43,7 +43,7 @@ static void measure(struct bench_res *res) res->hits = atomic_swap(&ctx.hits.value, 0); } -static void setup_ctx() +static void setup_ctx(void) { setup_libbpf(); @@ -71,36 +71,36 @@ static void attach_bpf(struct bpf_program *prog) } } -static void setup_base() +static void setup_base(void) { setup_ctx(); } -static void setup_kprobe() +static void setup_kprobe(void) { setup_ctx(); attach_bpf(ctx.skel->progs.prog1); } -static void setup_kretprobe() +static void setup_kretprobe(void) { setup_ctx(); attach_bpf(ctx.skel->progs.prog2); } -static void setup_rawtp() +static void setup_rawtp(void) { setup_ctx(); attach_bpf(ctx.skel->progs.prog3); } -static void setup_fentry() +static void setup_fentry(void) { setup_ctx(); attach_bpf(ctx.skel->progs.prog4); } -static void setup_fexit() +static void setup_fexit(void) { setup_ctx(); attach_bpf(ctx.skel->progs.prog5); diff --git a/tools/testing/selftests/bpf/benchs/bench_ringbufs.c b/tools/testing/selftests/bpf/benchs/bench_ringbufs.c index d167bffac6..da8593b349 100644 --- a/tools/testing/selftests/bpf/benchs/bench_ringbufs.c +++ b/tools/testing/selftests/bpf/benchs/bench_ringbufs.c @@ -88,12 +88,12 @@ const struct argp bench_ringbufs_argp = { static struct counter buf_hits; -static inline void bufs_trigger_batch() +static inline void bufs_trigger_batch(void) { (void)syscall(__NR_getpgid); } -static void bufs_validate() +static void bufs_validate(void) { if (env.consumer_cnt != 1) { fprintf(stderr, "rb-libbpf benchmark doesn't support multi-consumer!\n"); @@ -132,7 +132,7 @@ static void ringbuf_libbpf_measure(struct bench_res *res) res->drops = atomic_swap(&ctx->skel->bss->dropped, 0); } -static struct ringbuf_bench *ringbuf_setup_skeleton() +static struct ringbuf_bench *ringbuf_setup_skeleton(void) { struct ringbuf_bench *skel; @@ -167,7 +167,7 @@ static int buf_process_sample(void *ctx, void *data, size_t len) return 0; } -static void ringbuf_libbpf_setup() +static void ringbuf_libbpf_setup(void) { struct ringbuf_libbpf_ctx *ctx = &ringbuf_libbpf_ctx; struct bpf_link *link; @@ -223,7 +223,7 @@ static void ringbuf_custom_measure(struct bench_res *res) res->drops = atomic_swap(&ctx->skel->bss->dropped, 0); } -static void ringbuf_custom_setup() +static void ringbuf_custom_setup(void) { struct ringbuf_custom_ctx *ctx = &ringbuf_custom_ctx; const size_t page_size = getpagesize(); @@ -352,7 +352,7 @@ static void perfbuf_measure(struct bench_res *res) res->drops = atomic_swap(&ctx->skel->bss->dropped, 0); } -static struct perfbuf_bench *perfbuf_setup_skeleton() +static struct perfbuf_bench *perfbuf_setup_skeleton(void) { struct perfbuf_bench *skel; @@ -390,15 +390,10 @@ perfbuf_process_sample_raw(void *input_ctx, int cpu, return LIBBPF_PERF_EVENT_CONT; } -static void perfbuf_libbpf_setup() +static void perfbuf_libbpf_setup(void) { struct perfbuf_libbpf_ctx *ctx = &perfbuf_libbpf_ctx; struct perf_event_attr attr; - struct perf_buffer_raw_opts pb_opts = { - .event_cb = perfbuf_process_sample_raw, - .ctx = (void *)(long)0, - .attr = &attr, - }; struct bpf_link *link; ctx->skel = perfbuf_setup_skeleton(); @@ -423,7 +418,8 @@ static void perfbuf_libbpf_setup() } ctx->perfbuf = perf_buffer__new_raw(bpf_map__fd(ctx->skel->maps.perfbuf), - args.perfbuf_sz, &pb_opts); + args.perfbuf_sz, &attr, + perfbuf_process_sample_raw, NULL, NULL); if (!ctx->perfbuf) { fprintf(stderr, "failed to create perfbuf\n"); exit(1); diff --git a/tools/testing/selftests/bpf/benchs/bench_trigger.c b/tools/testing/selftests/bpf/benchs/bench_trigger.c index f41a491a8c..7f957c55a3 100644 --- a/tools/testing/selftests/bpf/benchs/bench_trigger.c +++ b/tools/testing/selftests/bpf/benchs/bench_trigger.c @@ -2,6 +2,7 @@ /* Copyright (c) 2020 Facebook */ #include "bench.h" #include "trigger_bench.skel.h" +#include "trace_helpers.h" /* BPF triggering benchmarks */ static struct trigger_ctx { @@ -10,7 +11,7 @@ static struct trigger_ctx { static struct counter base_hits; -static void trigger_validate() +static void trigger_validate(void) { if (env.consumer_cnt != 1) { fprintf(stderr, "benchmark doesn't support multi-consumer!\n"); @@ -44,7 +45,7 @@ static void trigger_measure(struct bench_res *res) res->hits = atomic_swap(&ctx.skel->bss->hits, 0); } -static void setup_ctx() +static void setup_ctx(void) { setup_libbpf(); @@ -66,37 +67,37 @@ static void attach_bpf(struct bpf_program *prog) } } -static void trigger_tp_setup() +static void trigger_tp_setup(void) { setup_ctx(); attach_bpf(ctx.skel->progs.bench_trigger_tp); } -static void trigger_rawtp_setup() +static void trigger_rawtp_setup(void) { setup_ctx(); attach_bpf(ctx.skel->progs.bench_trigger_raw_tp); } -static void trigger_kprobe_setup() +static void trigger_kprobe_setup(void) { setup_ctx(); attach_bpf(ctx.skel->progs.bench_trigger_kprobe); } -static void trigger_fentry_setup() +static void trigger_fentry_setup(void) { setup_ctx(); attach_bpf(ctx.skel->progs.bench_trigger_fentry); } -static void trigger_fentry_sleep_setup() +static void trigger_fentry_sleep_setup(void) { setup_ctx(); attach_bpf(ctx.skel->progs.bench_trigger_fentry_sleep); } -static void trigger_fmodret_setup() +static void trigger_fmodret_setup(void) { setup_ctx(); attach_bpf(ctx.skel->progs.bench_trigger_fmodret); @@ -107,6 +108,101 @@ static void *trigger_consumer(void *input) return NULL; } +/* make sure call is not inlined and not avoided by compiler, so __weak and + * inline asm volatile in the body of the function + * + * There is a performance difference between uprobing at nop location vs other + * instructions. So use two different targets, one of which starts with nop + * and another doesn't. + * + * GCC doesn't generate stack setup preample for these functions due to them + * having no input arguments and doing nothing in the body. + */ +__weak void uprobe_target_with_nop(void) +{ + asm volatile ("nop"); +} + +__weak void uprobe_target_without_nop(void) +{ + asm volatile (""); +} + +static void *uprobe_base_producer(void *input) +{ + while (true) { + uprobe_target_with_nop(); + atomic_inc(&base_hits.value); + } + return NULL; +} + +static void *uprobe_producer_with_nop(void *input) +{ + while (true) + uprobe_target_with_nop(); + return NULL; +} + +static void *uprobe_producer_without_nop(void *input) +{ + while (true) + uprobe_target_without_nop(); + return NULL; +} + +static void usetup(bool use_retprobe, bool use_nop) +{ + size_t uprobe_offset; + ssize_t base_addr; + struct bpf_link *link; + + setup_libbpf(); + + ctx.skel = trigger_bench__open_and_load(); + if (!ctx.skel) { + fprintf(stderr, "failed to open skeleton\n"); + exit(1); + } + + base_addr = get_base_addr(); + if (use_nop) + uprobe_offset = get_uprobe_offset(&uprobe_target_with_nop, base_addr); + else + uprobe_offset = get_uprobe_offset(&uprobe_target_without_nop, base_addr); + + link = bpf_program__attach_uprobe(ctx.skel->progs.bench_trigger_uprobe, + use_retprobe, + -1 /* all PIDs */, + "/proc/self/exe", + uprobe_offset); + if (!link) { + fprintf(stderr, "failed to attach uprobe!\n"); + exit(1); + } + ctx.skel->links.bench_trigger_uprobe = link; +} + +static void uprobe_setup_with_nop(void) +{ + usetup(false, true); +} + +static void uretprobe_setup_with_nop(void) +{ + usetup(true, true); +} + +static void uprobe_setup_without_nop(void) +{ + usetup(false, false); +} + +static void uretprobe_setup_without_nop(void) +{ + usetup(true, false); +} + const struct bench bench_trig_base = { .name = "trig-base", .validate = trigger_validate, @@ -182,3 +278,53 @@ const struct bench bench_trig_fmodret = { .report_progress = hits_drops_report_progress, .report_final = hits_drops_report_final, }; + +const struct bench bench_trig_uprobe_base = { + .name = "trig-uprobe-base", + .setup = NULL, /* no uprobe/uretprobe is attached */ + .producer_thread = uprobe_base_producer, + .consumer_thread = trigger_consumer, + .measure = trigger_base_measure, + .report_progress = hits_drops_report_progress, + .report_final = hits_drops_report_final, +}; + +const struct bench bench_trig_uprobe_with_nop = { + .name = "trig-uprobe-with-nop", + .setup = uprobe_setup_with_nop, + .producer_thread = uprobe_producer_with_nop, + .consumer_thread = trigger_consumer, + .measure = trigger_measure, + .report_progress = hits_drops_report_progress, + .report_final = hits_drops_report_final, +}; + +const struct bench bench_trig_uretprobe_with_nop = { + .name = "trig-uretprobe-with-nop", + .setup = uretprobe_setup_with_nop, + .producer_thread = uprobe_producer_with_nop, + .consumer_thread = trigger_consumer, + .measure = trigger_measure, + .report_progress = hits_drops_report_progress, + .report_final = hits_drops_report_final, +}; + +const struct bench bench_trig_uprobe_without_nop = { + .name = "trig-uprobe-without-nop", + .setup = uprobe_setup_without_nop, + .producer_thread = uprobe_producer_without_nop, + .consumer_thread = trigger_consumer, + .measure = trigger_measure, + .report_progress = hits_drops_report_progress, + .report_final = hits_drops_report_final, +}; + +const struct bench bench_trig_uretprobe_without_nop = { + .name = "trig-uretprobe-without-nop", + .setup = uretprobe_setup_without_nop, + .producer_thread = uprobe_producer_without_nop, + .consumer_thread = trigger_consumer, + .measure = trigger_measure, + .report_progress = hits_drops_report_progress, + .report_final = hits_drops_report_final, +}; diff --git a/tools/testing/selftests/bpf/benchs/run_bench_ringbufs.sh b/tools/testing/selftests/bpf/benchs/run_bench_ringbufs.sh index af4aa04cab..ada028aa90 100644 --- a/tools/testing/selftests/bpf/benchs/run_bench_ringbufs.sh +++ b/tools/testing/selftests/bpf/benchs/run_bench_ringbufs.sh @@ -1,35 +1,9 @@ #!/bin/bash +source ./benchs/run_common.sh + set -eufo pipefail -RUN_BENCH="sudo ./bench -w3 -d10 -a" - -function hits() -{ - echo "$*" | sed -E "s/.*hits\s+([0-9]+\.[0-9]+ ± [0-9]+\.[0-9]+M\/s).*/\1/" -} - -function drops() -{ - echo "$*" | sed -E "s/.*drops\s+([0-9]+\.[0-9]+ ± [0-9]+\.[0-9]+M\/s).*/\1/" -} - -function header() -{ - local len=${#1} - - printf "\n%s\n" "$1" - for i in $(seq 1 $len); do printf '='; done - printf '\n' -} - -function summarize() -{ - bench="$1" - summary=$(echo $2 | tail -n1) - printf "%-20s %s (drops %s)\n" "$bench" "$(hits $summary)" "$(drops $summary)" -} - header "Single-producer, parallel producer" for b in rb-libbpf rb-custom pb-libbpf pb-custom; do summarize $b "$($RUN_BENCH $b)" diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod-events.h b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod-events.h index 89c6d58e5d..11ee801e75 100644 --- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod-events.h +++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod-events.h @@ -34,6 +34,21 @@ DECLARE_TRACE(bpf_testmod_test_write_bare, TP_ARGS(task, ctx) ); +#undef BPF_TESTMOD_DECLARE_TRACE +#ifdef DECLARE_TRACE_WRITABLE +#define BPF_TESTMOD_DECLARE_TRACE(call, proto, args, size) \ + DECLARE_TRACE_WRITABLE(call, PARAMS(proto), PARAMS(args), size) +#else +#define BPF_TESTMOD_DECLARE_TRACE(call, proto, args, size) \ + DECLARE_TRACE(call, PARAMS(proto), PARAMS(args)) +#endif + +BPF_TESTMOD_DECLARE_TRACE(bpf_testmod_test_writable_bare, + TP_PROTO(struct bpf_testmod_test_writable_ctx *ctx), + TP_ARGS(ctx), + sizeof(struct bpf_testmod_test_writable_ctx) +); + #endif /* _BPF_TESTMOD_EVENTS_H */ #undef TRACE_INCLUDE_PATH diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c index 141d8da687..df3b292a8f 100644 --- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c +++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c @@ -1,5 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2020 Facebook */ +#include +#include #include #include #include @@ -13,6 +15,40 @@ DEFINE_PER_CPU(int, bpf_testmod_ksym_percpu) = 123; +noinline void +bpf_testmod_test_mod_kfunc(int i) +{ + *(int *)this_cpu_ptr(&bpf_testmod_ksym_percpu) = i; +} + +noinline int bpf_testmod_loop_test(int n) +{ + int i, sum = 0; + + /* the primary goal of this test is to test LBR. Create a lot of + * branches in the function, so we can catch it easily. + */ + for (i = 0; i < n; i++) + sum += i; + return sum; +} + +__weak noinline struct file *bpf_testmod_return_ptr(int arg) +{ + static struct file f = {}; + + switch (arg) { + case 1: return (void *)EINVAL; /* user addr */ + case 2: return (void *)0xcafe4a11; /* user addr */ + case 3: return (void *)-EINVAL; /* canonical, but invalid */ + case 4: return (void *)(1ull << 60); /* non-canonical and invalid */ + case 5: return (void *)~(1ull << 30); /* trigger extable */ + case 6: return &f; /* valid addr */ + case 7: return (void *)((long)&f | 1); /* kernel tricks */ + default: return NULL; + } +} + noinline ssize_t bpf_testmod_test_read(struct file *file, struct kobject *kobj, struct bin_attribute *bin_attr, @@ -23,8 +59,26 @@ bpf_testmod_test_read(struct file *file, struct kobject *kobj, .off = off, .len = len, }; + int i = 1; - trace_bpf_testmod_test_read(current, &ctx); + while (bpf_testmod_return_ptr(i)) + i++; + + /* This is always true. Use the check to make sure the compiler + * doesn't remove bpf_testmod_loop_test. + */ + if (bpf_testmod_loop_test(101) > 100) + trace_bpf_testmod_test_read(current, &ctx); + + /* Magic number to enable writable tp */ + if (len == 64) { + struct bpf_testmod_test_writable_ctx writable = { + .val = 1024, + }; + trace_bpf_testmod_test_writable_bare(&writable); + if (writable.early_ret) + return snprintf(buf, len, "%d\n", writable.val); + } return -EIO; /* always fail */ } @@ -55,13 +109,26 @@ static struct bin_attribute bin_attr_bpf_testmod_file __ro_after_init = { .write = bpf_testmod_test_write, }; +BTF_SET_START(bpf_testmod_kfunc_ids) +BTF_ID(func, bpf_testmod_test_mod_kfunc) +BTF_SET_END(bpf_testmod_kfunc_ids) + +static DEFINE_KFUNC_BTF_ID_SET(&bpf_testmod_kfunc_ids, bpf_testmod_kfunc_btf_set); + static int bpf_testmod_init(void) { - return sysfs_create_bin_file(kernel_kobj, &bin_attr_bpf_testmod_file); + int ret; + + ret = sysfs_create_bin_file(kernel_kobj, &bin_attr_bpf_testmod_file); + if (ret) + return ret; + register_kfunc_btf_id_set(&prog_test_kfunc_list, &bpf_testmod_kfunc_btf_set); + return 0; } static void bpf_testmod_exit(void) { + unregister_kfunc_btf_id_set(&prog_test_kfunc_list, &bpf_testmod_kfunc_btf_set); return sysfs_remove_bin_file(kernel_kobj, &bin_attr_bpf_testmod_file); } @@ -71,4 +138,3 @@ module_exit(bpf_testmod_exit); MODULE_AUTHOR("Andrii Nakryiko"); MODULE_DESCRIPTION("BPF selftests module"); MODULE_LICENSE("Dual BSD/GPL"); - diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.h b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.h index b3892dc401..0d71e26078 100644 --- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.h +++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.h @@ -17,4 +17,9 @@ struct bpf_testmod_test_write_ctx { size_t len; }; +struct bpf_testmod_test_writable_ctx { + bool early_ret; + int val; +}; + #endif /* _BPF_TESTMOD_H */ diff --git a/tools/testing/selftests/bpf/btf_helpers.c b/tools/testing/selftests/bpf/btf_helpers.c index 0a4ad7cb2c..b5941d514e 100644 --- a/tools/testing/selftests/bpf/btf_helpers.c +++ b/tools/testing/selftests/bpf/btf_helpers.c @@ -24,11 +24,13 @@ static const char * const btf_kind_str_mapping[] = { [BTF_KIND_VAR] = "VAR", [BTF_KIND_DATASEC] = "DATASEC", [BTF_KIND_FLOAT] = "FLOAT", + [BTF_KIND_DECL_TAG] = "DECL_TAG", + [BTF_KIND_TYPE_TAG] = "TYPE_TAG", }; static const char *btf_kind_str(__u16 kind) { - if (kind > BTF_KIND_DATASEC) + if (kind > BTF_KIND_TYPE_TAG) return "UNKNOWN"; return btf_kind_str_mapping[kind]; } @@ -108,6 +110,7 @@ int fprintf_btf_type_raw(FILE *out, const struct btf *btf, __u32 id) case BTF_KIND_VOLATILE: case BTF_KIND_RESTRICT: case BTF_KIND_TYPEDEF: + case BTF_KIND_TYPE_TAG: fprintf(out, " type_id=%u", t->type); break; case BTF_KIND_ARRAY: { @@ -177,6 +180,10 @@ int fprintf_btf_type_raw(FILE *out, const struct btf *btf, __u32 id) case BTF_KIND_FLOAT: fprintf(out, " size=%u", t->size); break; + case BTF_KIND_DECL_TAG: + fprintf(out, " type_id=%u component_idx=%d", + t->type, btf_decl_tag(t)->component_idx); + break; default: break; } @@ -210,7 +217,7 @@ int btf_validate_raw(struct btf *btf, int nr_types, const char *exp_types[]) int i; bool ok = true; - ASSERT_EQ(btf__get_nr_types(btf), nr_types, "btf_nr_types"); + ASSERT_EQ(btf__type_cnt(btf) - 1, nr_types, "btf_nr_types"); for (i = 1; i <= nr_types; i++) { if (!ASSERT_STREQ(btf_type_raw_dump(btf, i), exp_types[i - 1], "raw_dump")) @@ -233,7 +240,6 @@ const char *btf_type_c_dump(const struct btf *btf) static char buf[16 * 1024]; FILE *buf_file; struct btf_dump *d = NULL; - struct btf_dump_opts opts = {}; int err, i; buf_file = fmemopen(buf, sizeof(buf) - 1, "w"); @@ -242,14 +248,13 @@ const char *btf_type_c_dump(const struct btf *btf) return NULL; } - opts.ctx = buf_file; - d = btf_dump__new(btf, NULL, &opts, btf_dump_printf); + d = btf_dump__new(btf, btf_dump_printf, buf_file, NULL); if (libbpf_get_error(d)) { fprintf(stderr, "Failed to create btf_dump instance: %ld\n", libbpf_get_error(d)); goto err_out; } - for (i = 1; i <= btf__get_nr_types(btf); i++) { + for (i = 1; i < btf__type_cnt(btf); i++) { err = btf_dump__dump_type(d, i); if (err) { fprintf(stderr, "Failed to dump type [%d]: %d\n", i, err); diff --git a/tools/testing/selftests/bpf/cgroup_helpers.c b/tools/testing/selftests/bpf/cgroup_helpers.c index f3daa44a82..9d59c3990c 100644 --- a/tools/testing/selftests/bpf/cgroup_helpers.c +++ b/tools/testing/selftests/bpf/cgroup_helpers.c @@ -33,10 +33,9 @@ #define CGROUP_MOUNT_DFLT "/sys/fs/cgroup" #define NETCLS_MOUNT_PATH CGROUP_MOUNT_DFLT "/net_cls" #define CGROUP_WORK_DIR "/cgroup-test-work-dir" - #define format_cgroup_path(buf, path) \ - snprintf(buf, sizeof(buf), "%s%s%s", CGROUP_MOUNT_PATH, \ - CGROUP_WORK_DIR, path) + snprintf(buf, sizeof(buf), "%s%s%d%s", CGROUP_MOUNT_PATH, \ + CGROUP_WORK_DIR, getpid(), path) #define format_classid_path(buf) \ snprintf(buf, sizeof(buf), "%s%s", NETCLS_MOUNT_PATH, \ diff --git a/tools/testing/selftests/bpf/cgroup_helpers.h b/tools/testing/selftests/bpf/cgroup_helpers.h index 629da3854b..fcc9cb91b2 100644 --- a/tools/testing/selftests/bpf/cgroup_helpers.h +++ b/tools/testing/selftests/bpf/cgroup_helpers.h @@ -26,4 +26,4 @@ int join_classid(void); int setup_classid_environment(void); void cleanup_classid_environment(void); -#endif /* __CGROUP_HELPERS_H */ +#endif /* __CGROUP_HELPERS_H */ \ No newline at end of file diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config index 5192305159..f6287132fa 100644 --- a/tools/testing/selftests/bpf/config +++ b/tools/testing/selftests/bpf/config @@ -38,7 +38,9 @@ CONFIG_IPV6_SIT=m CONFIG_BPF_JIT=y CONFIG_BPF_LSM=y CONFIG_SECURITY=y +CONFIG_RC_CORE=y CONFIG_LIRC=y +CONFIG_BPF_LIRC_MODE2=y CONFIG_IMA=y CONFIG_SECURITYFS=y CONFIG_IMA_WRITE_POLICY=y diff --git a/tools/testing/selftests/bpf/flow_dissector_load.c b/tools/testing/selftests/bpf/flow_dissector_load.c index 3fd83b9dc1..87fd1aa323 100644 --- a/tools/testing/selftests/bpf/flow_dissector_load.c +++ b/tools/testing/selftests/bpf/flow_dissector_load.c @@ -17,7 +17,7 @@ const char *cfg_pin_path = "/sys/fs/bpf/flow_dissector"; const char *cfg_map_name = "jmp_table"; bool cfg_attach = true; -char *cfg_section_name; +char *cfg_prog_name; char *cfg_path_name; static void load_and_attach_program(void) @@ -25,7 +25,11 @@ static void load_and_attach_program(void) int prog_fd, ret; struct bpf_object *obj; - ret = bpf_flow_load(&obj, cfg_path_name, cfg_section_name, + ret = libbpf_set_strict_mode(LIBBPF_STRICT_ALL); + if (ret) + error(1, 0, "failed to enable libbpf strict mode: %d", ret); + + ret = bpf_flow_load(&obj, cfg_path_name, cfg_prog_name, cfg_map_name, NULL, &prog_fd, NULL); if (ret) error(1, 0, "bpf_flow_load %s", cfg_path_name); @@ -75,15 +79,15 @@ static void parse_opts(int argc, char **argv) break; case 'p': if (cfg_path_name) - error(1, 0, "only one prog name can be given"); + error(1, 0, "only one path can be given"); cfg_path_name = optarg; break; case 's': - if (cfg_section_name) - error(1, 0, "only one section can be given"); + if (cfg_prog_name) + error(1, 0, "only one prog can be given"); - cfg_section_name = optarg; + cfg_prog_name = optarg; break; } } @@ -94,7 +98,7 @@ static void parse_opts(int argc, char **argv) if (cfg_attach && !cfg_path_name) error(1, 0, "must provide a path to the BPF program"); - if (cfg_attach && !cfg_section_name) + if (cfg_attach && !cfg_prog_name) error(1, 0, "must provide a section name"); } diff --git a/tools/testing/selftests/bpf/flow_dissector_load.h b/tools/testing/selftests/bpf/flow_dissector_load.h index 7290401ec1..f40b585f4e 100644 --- a/tools/testing/selftests/bpf/flow_dissector_load.h +++ b/tools/testing/selftests/bpf/flow_dissector_load.h @@ -4,10 +4,11 @@ #include #include +#include "testing_helpers.h" static inline int bpf_flow_load(struct bpf_object **obj, const char *path, - const char *section_name, + const char *prog_name, const char *map_name, const char *keys_map_name, int *prog_fd, @@ -18,18 +19,12 @@ static inline int bpf_flow_load(struct bpf_object **obj, int prog_array_fd; int ret, fd, i; - ret = bpf_prog_load(path, BPF_PROG_TYPE_FLOW_DISSECTOR, obj, + ret = bpf_prog_test_load(path, BPF_PROG_TYPE_FLOW_DISSECTOR, obj, prog_fd); if (ret) return ret; - main_prog = NULL; - bpf_object__for_each_program(prog, *obj) { - if (strcmp(section_name, bpf_program__section_name(prog)) == 0) { - main_prog = prog; - break; - } - } + main_prog = bpf_object__find_program_by_name(*obj, prog_name); if (!main_prog) return -1; diff --git a/tools/testing/selftests/bpf/get_cgroup_id_user.c b/tools/testing/selftests/bpf/get_cgroup_id_user.c index 99628e1a1e..3a7b82bd9e 100644 --- a/tools/testing/selftests/bpf/get_cgroup_id_user.c +++ b/tools/testing/selftests/bpf/get_cgroup_id_user.c @@ -19,6 +19,7 @@ #include #include "cgroup_helpers.h" +#include "testing_helpers.h" #include "bpf_rlimit.h" #define CHECK(condition, tag, format...) ({ \ @@ -66,8 +67,8 @@ int main(int argc, char **argv) if (CHECK(cgroup_fd < 0, "cgroup_setup_and_join", "err %d errno %d\n", cgroup_fd, errno)) return 1; - err = bpf_prog_load(file, BPF_PROG_TYPE_TRACEPOINT, &obj, &prog_fd); - if (CHECK(err, "bpf_prog_load", "err %d errno %d\n", err, errno)) + err = bpf_prog_test_load(file, BPF_PROG_TYPE_TRACEPOINT, &obj, &prog_fd); + if (CHECK(err, "bpf_prog_test_load", "err %d errno %d\n", err, errno)) goto cleanup_cgroup_env; cgidmap_fd = bpf_find_map(__func__, obj, "cg_ids"); diff --git a/tools/testing/selftests/bpf/map_tests/array_map_batch_ops.c b/tools/testing/selftests/bpf/map_tests/array_map_batch_ops.c index f4d870da76..78c76496b1 100644 --- a/tools/testing/selftests/bpf/map_tests/array_map_batch_ops.c +++ b/tools/testing/selftests/bpf/map_tests/array_map_batch_ops.c @@ -68,13 +68,6 @@ static void map_batch_verify(int *visited, __u32 max_entries, int *keys, static void __test_map_lookup_and_update_batch(bool is_pcpu) { - struct bpf_create_map_attr xattr = { - .name = "array_map", - .map_type = is_pcpu ? BPF_MAP_TYPE_PERCPU_ARRAY : - BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(int), - .value_size = sizeof(__s64), - }; int map_fd, *keys, *visited; __u32 count, total, total_success; const __u32 max_entries = 10; @@ -86,10 +79,10 @@ static void __test_map_lookup_and_update_batch(bool is_pcpu) .flags = 0, ); - xattr.max_entries = max_entries; - map_fd = bpf_create_map_xattr(&xattr); + map_fd = bpf_map_create(is_pcpu ? BPF_MAP_TYPE_PERCPU_ARRAY : BPF_MAP_TYPE_ARRAY, + "array_map", sizeof(int), sizeof(__s64), max_entries, NULL); CHECK(map_fd == -1, - "bpf_create_map_xattr()", "error:%s\n", strerror(errno)); + "bpf_map_create()", "error:%s\n", strerror(errno)); value_size = sizeof(__s64); if (is_pcpu) diff --git a/tools/testing/selftests/bpf/map_tests/htab_map_batch_ops.c b/tools/testing/selftests/bpf/map_tests/htab_map_batch_ops.c index 976bf415fb..f807d53fd8 100644 --- a/tools/testing/selftests/bpf/map_tests/htab_map_batch_ops.c +++ b/tools/testing/selftests/bpf/map_tests/htab_map_batch_ops.c @@ -83,22 +83,15 @@ void __test_map_lookup_and_delete_batch(bool is_pcpu) int err, step, value_size; bool nospace_err; void *values; - struct bpf_create_map_attr xattr = { - .name = "hash_map", - .map_type = is_pcpu ? BPF_MAP_TYPE_PERCPU_HASH : - BPF_MAP_TYPE_HASH, - .key_size = sizeof(int), - .value_size = sizeof(int), - }; DECLARE_LIBBPF_OPTS(bpf_map_batch_opts, opts, .elem_flags = 0, .flags = 0, ); - xattr.max_entries = max_entries; - map_fd = bpf_create_map_xattr(&xattr); + map_fd = bpf_map_create(is_pcpu ? BPF_MAP_TYPE_PERCPU_HASH : BPF_MAP_TYPE_HASH, + "hash_map", sizeof(int), sizeof(int), max_entries, NULL); CHECK(map_fd == -1, - "bpf_create_map_xattr()", "error:%s\n", strerror(errno)); + "bpf_map_create()", "error:%s\n", strerror(errno)); value_size = is_pcpu ? sizeof(value) : sizeof(int); keys = malloc(max_entries * sizeof(int)); diff --git a/tools/testing/selftests/bpf/map_tests/lpm_trie_map_batch_ops.c b/tools/testing/selftests/bpf/map_tests/lpm_trie_map_batch_ops.c index 2e986e5e4c..87d07b596e 100644 --- a/tools/testing/selftests/bpf/map_tests/lpm_trie_map_batch_ops.c +++ b/tools/testing/selftests/bpf/map_tests/lpm_trie_map_batch_ops.c @@ -64,13 +64,7 @@ static void map_batch_verify(int *visited, __u32 max_entries, void test_lpm_trie_map_batch_ops(void) { - struct bpf_create_map_attr xattr = { - .name = "lpm_trie_map", - .map_type = BPF_MAP_TYPE_LPM_TRIE, - .key_size = sizeof(struct test_lpm_key), - .value_size = sizeof(int), - .map_flags = BPF_F_NO_PREALLOC, - }; + LIBBPF_OPTS(bpf_map_create_opts, create_opts, .map_flags = BPF_F_NO_PREALLOC); struct test_lpm_key *keys, key; int map_fd, *values, *visited; __u32 step, count, total, total_success; @@ -82,9 +76,10 @@ void test_lpm_trie_map_batch_ops(void) .flags = 0, ); - xattr.max_entries = max_entries; - map_fd = bpf_create_map_xattr(&xattr); - CHECK(map_fd == -1, "bpf_create_map_xattr()", "error:%s\n", + map_fd = bpf_map_create(BPF_MAP_TYPE_LPM_TRIE, "lpm_trie_map", + sizeof(struct test_lpm_key), sizeof(int), + max_entries, &create_opts); + CHECK(map_fd == -1, "bpf_map_create()", "error:%s\n", strerror(errno)); keys = malloc(max_entries * sizeof(struct test_lpm_key)); diff --git a/tools/testing/selftests/bpf/map_tests/sk_storage_map.c b/tools/testing/selftests/bpf/map_tests/sk_storage_map.c index e569edc679..099eb4dfd4 100644 --- a/tools/testing/selftests/bpf/map_tests/sk_storage_map.c +++ b/tools/testing/selftests/bpf/map_tests/sk_storage_map.c @@ -19,16 +19,12 @@ #include #include -static struct bpf_create_map_attr xattr = { - .name = "sk_storage_map", - .map_type = BPF_MAP_TYPE_SK_STORAGE, - .map_flags = BPF_F_NO_PREALLOC, - .max_entries = 0, - .key_size = 4, - .value_size = 8, +static struct bpf_map_create_opts map_opts = { + .sz = sizeof(map_opts), .btf_key_type_id = 1, .btf_value_type_id = 3, .btf_fd = -1, + .map_flags = BPF_F_NO_PREALLOC, }; static unsigned int nr_sk_threads_done; @@ -140,7 +136,7 @@ static int load_btf(void) memcpy(raw_btf + sizeof(btf_hdr) + sizeof(btf_raw_types), btf_str_sec, sizeof(btf_str_sec)); - return bpf_load_btf(raw_btf, sizeof(raw_btf), 0, 0, 0); + return bpf_btf_load(raw_btf, sizeof(raw_btf), NULL); } static int create_sk_storage_map(void) @@ -150,13 +146,13 @@ static int create_sk_storage_map(void) btf_fd = load_btf(); CHECK(btf_fd == -1, "bpf_load_btf", "btf_fd:%d errno:%d\n", btf_fd, errno); - xattr.btf_fd = btf_fd; + map_opts.btf_fd = btf_fd; - map_fd = bpf_create_map_xattr(&xattr); - xattr.btf_fd = -1; + map_fd = bpf_map_create(BPF_MAP_TYPE_SK_STORAGE, "sk_storage_map", 4, 8, 0, &map_opts); + map_opts.btf_fd = -1; close(btf_fd); CHECK(map_fd == -1, - "bpf_create_map_xattr()", "errno:%d\n", errno); + "bpf_map_create()", "errno:%d\n", errno); return map_fd; } @@ -463,20 +459,20 @@ static void test_sk_storage_map_basic(void) int cnt; int lock; } value = { .cnt = 0xeB9f, .lock = 0, }, lookup_value; - struct bpf_create_map_attr bad_xattr; + struct bpf_map_create_opts bad_xattr; int btf_fd, map_fd, sk_fd, err; btf_fd = load_btf(); CHECK(btf_fd == -1, "bpf_load_btf", "btf_fd:%d errno:%d\n", btf_fd, errno); - xattr.btf_fd = btf_fd; + map_opts.btf_fd = btf_fd; sk_fd = socket(AF_INET6, SOCK_STREAM, 0); CHECK(sk_fd == -1, "socket()", "sk_fd:%d errno:%d\n", sk_fd, errno); - map_fd = bpf_create_map_xattr(&xattr); - CHECK(map_fd == -1, "bpf_create_map_xattr(good_xattr)", + map_fd = bpf_map_create(BPF_MAP_TYPE_SK_STORAGE, "sk_storage_map", 4, 8, 0, &map_opts); + CHECK(map_fd == -1, "bpf_map_create(good_xattr)", "map_fd:%d errno:%d\n", map_fd, errno); /* Add new elem */ @@ -560,31 +556,29 @@ static void test_sk_storage_map_basic(void) CHECK(!err || errno != ENOENT, "bpf_map_delete_elem()", "err:%d errno:%d\n", err, errno); - memcpy(&bad_xattr, &xattr, sizeof(xattr)); + memcpy(&bad_xattr, &map_opts, sizeof(map_opts)); bad_xattr.btf_key_type_id = 0; - err = bpf_create_map_xattr(&bad_xattr); - CHECK(!err || errno != EINVAL, "bap_create_map_xattr(bad_xattr)", + err = bpf_map_create(BPF_MAP_TYPE_SK_STORAGE, "sk_storage_map", 4, 8, 0, &bad_xattr); + CHECK(!err || errno != EINVAL, "bpf_map_create(bad_xattr)", "err:%d errno:%d\n", err, errno); - memcpy(&bad_xattr, &xattr, sizeof(xattr)); + memcpy(&bad_xattr, &map_opts, sizeof(map_opts)); bad_xattr.btf_key_type_id = 3; - err = bpf_create_map_xattr(&bad_xattr); - CHECK(!err || errno != EINVAL, "bap_create_map_xattr(bad_xattr)", + err = bpf_map_create(BPF_MAP_TYPE_SK_STORAGE, "sk_storage_map", 4, 8, 0, &bad_xattr); + CHECK(!err || errno != EINVAL, "bpf_map_create(bad_xattr)", "err:%d errno:%d\n", err, errno); - memcpy(&bad_xattr, &xattr, sizeof(xattr)); - bad_xattr.max_entries = 1; - err = bpf_create_map_xattr(&bad_xattr); - CHECK(!err || errno != EINVAL, "bap_create_map_xattr(bad_xattr)", + err = bpf_map_create(BPF_MAP_TYPE_SK_STORAGE, "sk_storage_map", 4, 8, 1, &map_opts); + CHECK(!err || errno != EINVAL, "bpf_map_create(bad_xattr)", "err:%d errno:%d\n", err, errno); - memcpy(&bad_xattr, &xattr, sizeof(xattr)); + memcpy(&bad_xattr, &map_opts, sizeof(map_opts)); bad_xattr.map_flags = 0; - err = bpf_create_map_xattr(&bad_xattr); + err = bpf_map_create(BPF_MAP_TYPE_SK_STORAGE, "sk_storage_map", 4, 8, 0, &bad_xattr); CHECK(!err || errno != EINVAL, "bap_create_map_xattr(bad_xattr)", "err:%d errno:%d\n", err, errno); - xattr.btf_fd = -1; + map_opts.btf_fd = -1; close(btf_fd); close(map_fd); close(sk_fd); diff --git a/tools/testing/selftests/bpf/prog_tests/align.c b/tools/testing/selftests/bpf/prog_tests/align.c index 5861446d07..0ee29e11ea 100644 --- a/tools/testing/selftests/bpf/prog_tests/align.c +++ b/tools/testing/selftests/bpf/prog_tests/align.c @@ -39,13 +39,13 @@ static struct bpf_align_test tests[] = { }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .matches = { - {1, "R1=ctx(id=0,off=0,imm=0)"}, - {1, "R10=fp0"}, - {1, "R3_w=inv2"}, - {2, "R3_w=inv4"}, - {3, "R3_w=inv8"}, - {4, "R3_w=inv16"}, - {5, "R3_w=inv32"}, + {0, "R1=ctx(id=0,off=0,imm=0)"}, + {0, "R10=fp0"}, + {0, "R3_w=inv2"}, + {1, "R3_w=inv4"}, + {2, "R3_w=inv8"}, + {3, "R3_w=inv16"}, + {4, "R3_w=inv32"}, }, }, { @@ -67,19 +67,19 @@ static struct bpf_align_test tests[] = { }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .matches = { - {1, "R1=ctx(id=0,off=0,imm=0)"}, - {1, "R10=fp0"}, - {1, "R3_w=inv1"}, - {2, "R3_w=inv2"}, - {3, "R3_w=inv4"}, - {4, "R3_w=inv8"}, - {5, "R3_w=inv16"}, - {6, "R3_w=inv1"}, - {7, "R4_w=inv32"}, - {8, "R4_w=inv16"}, - {9, "R4_w=inv8"}, - {10, "R4_w=inv4"}, - {11, "R4_w=inv2"}, + {0, "R1=ctx(id=0,off=0,imm=0)"}, + {0, "R10=fp0"}, + {0, "R3_w=inv1"}, + {1, "R3_w=inv2"}, + {2, "R3_w=inv4"}, + {3, "R3_w=inv8"}, + {4, "R3_w=inv16"}, + {5, "R3_w=inv1"}, + {6, "R4_w=inv32"}, + {7, "R4_w=inv16"}, + {8, "R4_w=inv8"}, + {9, "R4_w=inv4"}, + {10, "R4_w=inv2"}, }, }, { @@ -96,14 +96,14 @@ static struct bpf_align_test tests[] = { }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .matches = { - {1, "R1=ctx(id=0,off=0,imm=0)"}, - {1, "R10=fp0"}, - {1, "R3_w=inv4"}, - {2, "R3_w=inv8"}, - {3, "R3_w=inv10"}, - {4, "R4_w=inv8"}, - {5, "R4_w=inv12"}, - {6, "R4_w=inv14"}, + {0, "R1=ctx(id=0,off=0,imm=0)"}, + {0, "R10=fp0"}, + {0, "R3_w=inv4"}, + {1, "R3_w=inv8"}, + {2, "R3_w=inv10"}, + {3, "R4_w=inv8"}, + {4, "R4_w=inv12"}, + {5, "R4_w=inv14"}, }, }, { @@ -118,12 +118,12 @@ static struct bpf_align_test tests[] = { }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .matches = { - {1, "R1=ctx(id=0,off=0,imm=0)"}, - {1, "R10=fp0"}, + {0, "R1=ctx(id=0,off=0,imm=0)"}, + {0, "R10=fp0"}, + {0, "R3_w=inv7"}, {1, "R3_w=inv7"}, - {2, "R3_w=inv7"}, - {3, "R3_w=inv14"}, - {4, "R3_w=inv56"}, + {2, "R3_w=inv14"}, + {3, "R3_w=inv56"}, }, }, @@ -161,19 +161,19 @@ static struct bpf_align_test tests[] = { }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .matches = { - {7, "R0_w=pkt(id=0,off=8,r=8,imm=0)"}, - {7, "R3_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, - {8, "R3_w=inv(id=0,umax_value=510,var_off=(0x0; 0x1fe))"}, - {9, "R3_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, - {10, "R3_w=inv(id=0,umax_value=2040,var_off=(0x0; 0x7f8))"}, - {11, "R3_w=inv(id=0,umax_value=4080,var_off=(0x0; 0xff0))"}, - {18, "R3=pkt_end(id=0,off=0,imm=0)"}, - {18, "R4_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, - {19, "R4_w=inv(id=0,umax_value=8160,var_off=(0x0; 0x1fe0))"}, - {20, "R4_w=inv(id=0,umax_value=4080,var_off=(0x0; 0xff0))"}, - {21, "R4_w=inv(id=0,umax_value=2040,var_off=(0x0; 0x7f8))"}, - {22, "R4_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, - {23, "R4_w=inv(id=0,umax_value=510,var_off=(0x0; 0x1fe))"}, + {6, "R0_w=pkt(id=0,off=8,r=8,imm=0)"}, + {6, "R3_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, + {7, "R3_w=inv(id=0,umax_value=510,var_off=(0x0; 0x1fe))"}, + {8, "R3_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {9, "R3_w=inv(id=0,umax_value=2040,var_off=(0x0; 0x7f8))"}, + {10, "R3_w=inv(id=0,umax_value=4080,var_off=(0x0; 0xff0))"}, + {12, "R3_w=pkt_end(id=0,off=0,imm=0)"}, + {17, "R4_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, + {18, "R4_w=inv(id=0,umax_value=8160,var_off=(0x0; 0x1fe0))"}, + {19, "R4_w=inv(id=0,umax_value=4080,var_off=(0x0; 0xff0))"}, + {20, "R4_w=inv(id=0,umax_value=2040,var_off=(0x0; 0x7f8))"}, + {21, "R4_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {22, "R4_w=inv(id=0,umax_value=510,var_off=(0x0; 0x1fe))"}, }, }, { @@ -194,16 +194,16 @@ static struct bpf_align_test tests[] = { }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .matches = { - {7, "R3_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, - {8, "R4_w=inv(id=1,umax_value=255,var_off=(0x0; 0xff))"}, - {9, "R4_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, - {10, "R4_w=inv(id=1,umax_value=255,var_off=(0x0; 0xff))"}, - {11, "R4_w=inv(id=0,umax_value=510,var_off=(0x0; 0x1fe))"}, - {12, "R4_w=inv(id=1,umax_value=255,var_off=(0x0; 0xff))"}, - {13, "R4_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, - {14, "R4_w=inv(id=1,umax_value=255,var_off=(0x0; 0xff))"}, - {15, "R4_w=inv(id=0,umax_value=2040,var_off=(0x0; 0x7f8))"}, - {16, "R4_w=inv(id=0,umax_value=4080,var_off=(0x0; 0xff0))"}, + {6, "R3_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, + {7, "R4_w=inv(id=1,umax_value=255,var_off=(0x0; 0xff))"}, + {8, "R4_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, + {9, "R4_w=inv(id=1,umax_value=255,var_off=(0x0; 0xff))"}, + {10, "R4_w=inv(id=0,umax_value=510,var_off=(0x0; 0x1fe))"}, + {11, "R4_w=inv(id=1,umax_value=255,var_off=(0x0; 0xff))"}, + {12, "R4_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {13, "R4_w=inv(id=1,umax_value=255,var_off=(0x0; 0xff))"}, + {14, "R4_w=inv(id=0,umax_value=2040,var_off=(0x0; 0x7f8))"}, + {15, "R4_w=inv(id=0,umax_value=4080,var_off=(0x0; 0xff0))"}, }, }, { @@ -234,14 +234,14 @@ static struct bpf_align_test tests[] = { }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .matches = { - {4, "R5_w=pkt(id=0,off=0,r=0,imm=0)"}, - {5, "R5_w=pkt(id=0,off=14,r=0,imm=0)"}, - {6, "R4_w=pkt(id=0,off=14,r=0,imm=0)"}, - {10, "R2=pkt(id=0,off=0,r=18,imm=0)"}, + {2, "R5_w=pkt(id=0,off=0,r=0,imm=0)"}, + {4, "R5_w=pkt(id=0,off=14,r=0,imm=0)"}, + {5, "R4_w=pkt(id=0,off=14,r=0,imm=0)"}, + {9, "R2=pkt(id=0,off=0,r=18,imm=0)"}, {10, "R5=pkt(id=0,off=14,r=18,imm=0)"}, {10, "R4_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, + {13, "R4_w=inv(id=0,umax_value=65535,var_off=(0x0; 0xffff))"}, {14, "R4_w=inv(id=0,umax_value=65535,var_off=(0x0; 0xffff))"}, - {15, "R4_w=inv(id=0,umax_value=65535,var_off=(0x0; 0xffff))"}, }, }, { @@ -296,8 +296,8 @@ static struct bpf_align_test tests[] = { /* Calculated offset in R6 has unknown value, but known * alignment of 4. */ - {8, "R2_w=pkt(id=0,off=0,r=8,imm=0)"}, - {8, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {6, "R2_w=pkt(id=0,off=0,r=8,imm=0)"}, + {7, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, /* Offset is added to packet pointer R5, resulting in * known fixed offset, and variable offset from R6. */ @@ -313,11 +313,11 @@ static struct bpf_align_test tests[] = { /* Variable offset is added to R5 packet pointer, * resulting in auxiliary alignment of 4. */ - {18, "R5_w=pkt(id=2,off=0,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {17, "R5_w=pkt(id=2,off=0,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, /* Constant offset is added to R5, resulting in * reg->off of 14. */ - {19, "R5_w=pkt(id=2,off=14,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {18, "R5_w=pkt(id=2,off=14,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, /* At the time the word size load is performed from R5, * its total fixed offset is NET_IP_ALIGN + reg->off * (14) which is 16. Then the variable offset is 4-byte @@ -329,18 +329,18 @@ static struct bpf_align_test tests[] = { /* Constant offset is added to R5 packet pointer, * resulting in reg->off value of 14. */ - {26, "R5_w=pkt(id=0,off=14,r=8"}, + {25, "R5_w=pkt(id=0,off=14,r=8"}, /* Variable offset is added to R5, resulting in a * variable offset of (4n). */ - {27, "R5_w=pkt(id=3,off=14,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {26, "R5_w=pkt(id=3,off=14,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, /* Constant is added to R5 again, setting reg->off to 18. */ - {28, "R5_w=pkt(id=3,off=18,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {27, "R5_w=pkt(id=3,off=18,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, /* And once more we add a variable; resulting var_off * is still (4n), fixed offset is not changed. * Also, we create a new reg->id. */ - {29, "R5_w=pkt(id=4,off=18,r=0,umax_value=2040,var_off=(0x0; 0x7fc)"}, + {28, "R5_w=pkt(id=4,off=18,r=0,umax_value=2040,var_off=(0x0; 0x7fc)"}, /* At the time the word size load is performed from R5, * its total fixed offset is NET_IP_ALIGN + reg->off (18) * which is 20. Then the variable offset is (4n), so @@ -386,13 +386,13 @@ static struct bpf_align_test tests[] = { /* Calculated offset in R6 has unknown value, but known * alignment of 4. */ - {8, "R2_w=pkt(id=0,off=0,r=8,imm=0)"}, - {8, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {6, "R2_w=pkt(id=0,off=0,r=8,imm=0)"}, + {7, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, /* Adding 14 makes R6 be (4n+2) */ - {9, "R6_w=inv(id=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"}, + {8, "R6_w=inv(id=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"}, /* Packet pointer has (4n+2) offset */ {11, "R5_w=pkt(id=1,off=0,r=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc)"}, - {13, "R4=pkt(id=1,off=4,r=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc)"}, + {12, "R4=pkt(id=1,off=4,r=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc)"}, /* At the time the word size load is performed from R5, * its total fixed offset is NET_IP_ALIGN + reg->off (0) * which is 2. Then the variable offset is (4n+2), so @@ -403,12 +403,12 @@ static struct bpf_align_test tests[] = { /* Newly read value in R6 was shifted left by 2, so has * known alignment of 4. */ - {18, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {17, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, /* Added (4n) to packet pointer's (4n+2) var_off, giving * another (4n+2). */ {19, "R5_w=pkt(id=2,off=0,r=0,umin_value=14,umax_value=2054,var_off=(0x2; 0xffc)"}, - {21, "R4=pkt(id=2,off=4,r=0,umin_value=14,umax_value=2054,var_off=(0x2; 0xffc)"}, + {20, "R4=pkt(id=2,off=4,r=0,umin_value=14,umax_value=2054,var_off=(0x2; 0xffc)"}, /* At the time the word size load is performed from R5, * its total fixed offset is NET_IP_ALIGN + reg->off (0) * which is 2. Then the variable offset is (4n+2), so @@ -448,18 +448,18 @@ static struct bpf_align_test tests[] = { .prog_type = BPF_PROG_TYPE_SCHED_CLS, .result = REJECT, .matches = { - {4, "R5_w=pkt_end(id=0,off=0,imm=0)"}, + {3, "R5_w=pkt_end(id=0,off=0,imm=0)"}, /* (ptr - ptr) << 2 == unknown, (4n) */ - {6, "R5_w=inv(id=0,smax_value=9223372036854775804,umax_value=18446744073709551612,var_off=(0x0; 0xfffffffffffffffc)"}, + {5, "R5_w=inv(id=0,smax_value=9223372036854775804,umax_value=18446744073709551612,var_off=(0x0; 0xfffffffffffffffc)"}, /* (4n) + 14 == (4n+2). We blow our bounds, because * the add could overflow. */ - {7, "R5_w=inv(id=0,smin_value=-9223372036854775806,smax_value=9223372036854775806,umin_value=2,umax_value=18446744073709551614,var_off=(0x2; 0xfffffffffffffffc)"}, + {6, "R5_w=inv(id=0,smin_value=-9223372036854775806,smax_value=9223372036854775806,umin_value=2,umax_value=18446744073709551614,var_off=(0x2; 0xfffffffffffffffc)"}, /* Checked s>=0 */ {9, "R5=inv(id=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"}, /* packet pointer + nonnegative (4n+2) */ {11, "R6_w=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"}, - {13, "R4_w=pkt(id=1,off=4,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"}, + {12, "R4_w=pkt(id=1,off=4,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"}, /* NET_IP_ALIGN + (4n+2) == (4n), alignment is fine. * We checked the bounds, but it might have been able * to overflow if the packet pointer started in the @@ -502,14 +502,14 @@ static struct bpf_align_test tests[] = { /* Calculated offset in R6 has unknown value, but known * alignment of 4. */ - {7, "R2_w=pkt(id=0,off=0,r=8,imm=0)"}, - {9, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {6, "R2_w=pkt(id=0,off=0,r=8,imm=0)"}, + {8, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, /* Adding 14 makes R6 be (4n+2) */ - {10, "R6_w=inv(id=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"}, + {9, "R6_w=inv(id=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"}, /* New unknown value in R7 is (4n) */ - {11, "R7_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {10, "R7_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, /* Subtracting it from R6 blows our unsigned bounds */ - {12, "R6=inv(id=0,smin_value=-1006,smax_value=1034,umin_value=2,umax_value=18446744073709551614,var_off=(0x2; 0xfffffffffffffffc)"}, + {11, "R6=inv(id=0,smin_value=-1006,smax_value=1034,umin_value=2,umax_value=18446744073709551614,var_off=(0x2; 0xfffffffffffffffc)"}, /* Checked s>= 0 */ {14, "R6=inv(id=0,umin_value=2,umax_value=1034,var_off=(0x2; 0x7fc))"}, /* At the time the word size load is performed from R5, @@ -556,14 +556,14 @@ static struct bpf_align_test tests[] = { /* Calculated offset in R6 has unknown value, but known * alignment of 4. */ - {7, "R2_w=pkt(id=0,off=0,r=8,imm=0)"}, - {10, "R6_w=inv(id=0,umax_value=60,var_off=(0x0; 0x3c))"}, + {6, "R2_w=pkt(id=0,off=0,r=8,imm=0)"}, + {9, "R6_w=inv(id=0,umax_value=60,var_off=(0x0; 0x3c))"}, /* Adding 14 makes R6 be (4n+2) */ - {11, "R6_w=inv(id=0,umin_value=14,umax_value=74,var_off=(0x2; 0x7c))"}, + {10, "R6_w=inv(id=0,umin_value=14,umax_value=74,var_off=(0x2; 0x7c))"}, /* Subtracting from packet pointer overflows ubounds */ {13, "R5_w=pkt(id=2,off=0,r=8,umin_value=18446744073709551542,umax_value=18446744073709551602,var_off=(0xffffffffffffff82; 0x7c)"}, /* New unknown value in R7 is (4n), >= 76 */ - {15, "R7_w=inv(id=0,umin_value=76,umax_value=1096,var_off=(0x0; 0x7fc))"}, + {14, "R7_w=inv(id=0,umin_value=76,umax_value=1096,var_off=(0x0; 0x7fc))"}, /* Adding it to packet pointer gives nice bounds again */ {16, "R5_w=pkt(id=3,off=0,r=0,umin_value=2,umax_value=1082,var_off=(0x2; 0xfffffffc)"}, /* At the time the word size load is performed from R5, @@ -594,6 +594,12 @@ static int do_test_single(struct bpf_align_test *test) struct bpf_insn *prog = test->insns; int prog_type = test->prog_type; char bpf_vlog_copy[32768]; + LIBBPF_OPTS(bpf_prog_load_opts, opts, + .prog_flags = BPF_F_STRICT_ALIGNMENT, + .log_buf = bpf_vlog, + .log_size = sizeof(bpf_vlog), + .log_level = 2, + ); const char *line_ptr; int cur_line = -1; int prog_len, i; @@ -601,9 +607,8 @@ static int do_test_single(struct bpf_align_test *test) int ret; prog_len = probe_filter_length(prog); - fd_prog = bpf_verify_program(prog_type ? : BPF_PROG_TYPE_SOCKET_FILTER, - prog, prog_len, BPF_F_STRICT_ALIGNMENT, - "GPL", 0, bpf_vlog, sizeof(bpf_vlog), 2); + fd_prog = bpf_prog_load(prog_type ? : BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", + prog, prog_len, &opts); if (fd_prog < 0 && test->result != REJECT) { printf("Failed to load program.\n"); printf("%s", bpf_vlog); @@ -620,12 +625,15 @@ static int do_test_single(struct bpf_align_test *test) line_ptr = strtok(bpf_vlog_copy, "\n"); for (i = 0; i < MAX_MATCHES; i++) { struct bpf_reg_match m = test->matches[i]; + int tmp; if (!m.match) break; while (line_ptr) { cur_line = -1; sscanf(line_ptr, "%u: ", &cur_line); + if (cur_line == -1) + sscanf(line_ptr, "from %u to %u: ", &tmp, &cur_line); if (cur_line == m.line) break; line_ptr = strtok(NULL, "\n"); @@ -637,7 +645,19 @@ static int do_test_single(struct bpf_align_test *test) printf("%s", bpf_vlog); break; } + /* Check the next line as well in case the previous line + * did not have a corresponding bpf insn. Example: + * func#0 @0 + * 0: R1=ctx(id=0,off=0,imm=0) R10=fp0 + * 0: (b7) r3 = 2 ; R3_w=inv2 + */ if (!strstr(line_ptr, m.match)) { + cur_line = -1; + line_ptr = strtok(NULL, "\n"); + sscanf(line_ptr, "%u: ", &cur_line); + } + if (cur_line != m.line || !line_ptr || + !strstr(line_ptr, m.match)) { printf("Failed to find match %u: %s\n", m.line, m.match); ret = 1; diff --git a/tools/testing/selftests/bpf/prog_tests/atomics.c b/tools/testing/selftests/bpf/prog_tests/atomics.c index ba0e1efe5a..86b7d5d84e 100644 --- a/tools/testing/selftests/bpf/prog_tests/atomics.c +++ b/tools/testing/selftests/bpf/prog_tests/atomics.c @@ -4,13 +4,13 @@ #include "atomics.lskel.h" -static void test_add(struct atomics *skel) +static void test_add(struct atomics_lskel *skel) { int err, prog_fd; __u32 duration = 0, retval; int link_fd; - link_fd = atomics__add__attach(skel); + link_fd = atomics_lskel__add__attach(skel); if (!ASSERT_GT(link_fd, 0, "attach(add)")) return; @@ -36,13 +36,13 @@ static void test_add(struct atomics *skel) close(link_fd); } -static void test_sub(struct atomics *skel) +static void test_sub(struct atomics_lskel *skel) { int err, prog_fd; __u32 duration = 0, retval; int link_fd; - link_fd = atomics__sub__attach(skel); + link_fd = atomics_lskel__sub__attach(skel); if (!ASSERT_GT(link_fd, 0, "attach(sub)")) return; @@ -69,13 +69,13 @@ static void test_sub(struct atomics *skel) close(link_fd); } -static void test_and(struct atomics *skel) +static void test_and(struct atomics_lskel *skel) { int err, prog_fd; __u32 duration = 0, retval; int link_fd; - link_fd = atomics__and__attach(skel); + link_fd = atomics_lskel__and__attach(skel); if (!ASSERT_GT(link_fd, 0, "attach(and)")) return; @@ -97,13 +97,13 @@ static void test_and(struct atomics *skel) close(link_fd); } -static void test_or(struct atomics *skel) +static void test_or(struct atomics_lskel *skel) { int err, prog_fd; __u32 duration = 0, retval; int link_fd; - link_fd = atomics__or__attach(skel); + link_fd = atomics_lskel__or__attach(skel); if (!ASSERT_GT(link_fd, 0, "attach(or)")) return; @@ -126,13 +126,13 @@ static void test_or(struct atomics *skel) close(link_fd); } -static void test_xor(struct atomics *skel) +static void test_xor(struct atomics_lskel *skel) { int err, prog_fd; __u32 duration = 0, retval; int link_fd; - link_fd = atomics__xor__attach(skel); + link_fd = atomics_lskel__xor__attach(skel); if (!ASSERT_GT(link_fd, 0, "attach(xor)")) return; @@ -154,20 +154,20 @@ static void test_xor(struct atomics *skel) close(link_fd); } -static void test_cmpxchg(struct atomics *skel) +static void test_cmpxchg(struct atomics_lskel *skel) { int err, prog_fd; __u32 duration = 0, retval; int link_fd; - link_fd = atomics__cmpxchg__attach(skel); + link_fd = atomics_lskel__cmpxchg__attach(skel); if (!ASSERT_GT(link_fd, 0, "attach(cmpxchg)")) return; prog_fd = skel->progs.cmpxchg.prog_fd; err = bpf_prog_test_run(prog_fd, 1, NULL, 0, NULL, NULL, &retval, &duration); - if (CHECK(err || retval, "test_run add", + if (CHECK(err || retval, "test_run cmpxchg", "err %d errno %d retval %d duration %d\n", err, errno, retval, duration)) goto cleanup; @@ -183,20 +183,20 @@ static void test_cmpxchg(struct atomics *skel) close(link_fd); } -static void test_xchg(struct atomics *skel) +static void test_xchg(struct atomics_lskel *skel) { int err, prog_fd; __u32 duration = 0, retval; int link_fd; - link_fd = atomics__xchg__attach(skel); + link_fd = atomics_lskel__xchg__attach(skel); if (!ASSERT_GT(link_fd, 0, "attach(xchg)")) return; prog_fd = skel->progs.xchg.prog_fd; err = bpf_prog_test_run(prog_fd, 1, NULL, 0, NULL, NULL, &retval, &duration); - if (CHECK(err || retval, "test_run add", + if (CHECK(err || retval, "test_run xchg", "err %d errno %d retval %d duration %d\n", err, errno, retval, duration)) goto cleanup; @@ -212,10 +212,10 @@ static void test_xchg(struct atomics *skel) void test_atomics(void) { - struct atomics *skel; + struct atomics_lskel *skel; __u32 duration = 0; - skel = atomics__open_and_load(); + skel = atomics_lskel__open_and_load(); if (CHECK(!skel, "skel_load", "atomics skeleton failed\n")) return; @@ -225,6 +225,7 @@ void test_atomics(void) test__skip(); goto cleanup; } + skel->bss->pid = getpid(); if (test__start_subtest("add")) test_add(skel); @@ -242,5 +243,5 @@ void test_atomics(void) test_xchg(skel); cleanup: - atomics__destroy(skel); + atomics_lskel__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/attach_probe.c b/tools/testing/selftests/bpf/prog_tests/attach_probe.c index bf307bb9e4..d0bd51eb23 100644 --- a/tools/testing/selftests/bpf/prog_tests/attach_probe.c +++ b/tools/testing/selftests/bpf/prog_tests/attach_probe.c @@ -5,6 +5,11 @@ /* this is how USDT semaphore is actually defined, except volatile modifier */ volatile unsigned short uprobe_ref_ctr __attribute__((unused)) __attribute((section(".probes"))); +/* attach point */ +static void method(void) { + return ; +} + void test_attach_probe(void) { DECLARE_LIBBPF_OPTS(bpf_uprobe_opts, uprobe_opts); @@ -14,12 +19,26 @@ void test_attach_probe(void) struct test_attach_probe* skel; size_t uprobe_offset; ssize_t base_addr, ref_ctr_offset; + bool legacy; + + /* Check if new-style kprobe/uprobe API is supported. + * Kernels that support new FD-based kprobe and uprobe BPF attachment + * through perf_event_open() syscall expose + * /sys/bus/event_source/devices/kprobe/type and + * /sys/bus/event_source/devices/uprobe/type files, respectively. They + * contain magic numbers that are passed as "type" field of + * perf_event_attr. Lack of such file in the system indicates legacy + * kernel with old-style kprobe/uprobe attach interface through + * creating per-probe event through tracefs. For such cases + * ref_ctr_offset feature is not supported, so we don't test it. + */ + legacy = access("/sys/bus/event_source/devices/kprobe/type", F_OK) != 0; base_addr = get_base_addr(); if (CHECK(base_addr < 0, "get_base_addr", "failed to find base addr: %zd", base_addr)) return; - uprobe_offset = get_uprobe_offset(&get_base_addr, base_addr); + uprobe_offset = get_uprobe_offset(&method, base_addr); ref_ctr_offset = get_rel_offset((uintptr_t)&uprobe_ref_ctr); if (!ASSERT_GE(ref_ctr_offset, 0, "ref_ctr_offset")) @@ -45,10 +64,11 @@ void test_attach_probe(void) goto cleanup; skel->links.handle_kretprobe = kretprobe_link; - ASSERT_EQ(uprobe_ref_ctr, 0, "uprobe_ref_ctr_before"); + if (!legacy) + ASSERT_EQ(uprobe_ref_ctr, 0, "uprobe_ref_ctr_before"); uprobe_opts.retprobe = false; - uprobe_opts.ref_ctr_offset = ref_ctr_offset; + uprobe_opts.ref_ctr_offset = legacy ? 0 : ref_ctr_offset; uprobe_link = bpf_program__attach_uprobe_opts(skel->progs.handle_uprobe, 0 /* self pid */, "/proc/self/exe", @@ -58,11 +78,12 @@ void test_attach_probe(void) goto cleanup; skel->links.handle_uprobe = uprobe_link; - ASSERT_GT(uprobe_ref_ctr, 0, "uprobe_ref_ctr_after"); + if (!legacy) + ASSERT_GT(uprobe_ref_ctr, 0, "uprobe_ref_ctr_after"); /* if uprobe uses ref_ctr, uretprobe has to use ref_ctr as well */ uprobe_opts.retprobe = true; - uprobe_opts.ref_ctr_offset = ref_ctr_offset; + uprobe_opts.ref_ctr_offset = legacy ? 0 : ref_ctr_offset; uretprobe_link = bpf_program__attach_uprobe_opts(skel->progs.handle_uretprobe, -1 /* any pid */, "/proc/self/exe", @@ -82,7 +103,7 @@ void test_attach_probe(void) goto cleanup; /* trigger & validate uprobe & uretprobe */ - get_base_addr(); + method(); if (CHECK(skel->bss->uprobe_res != 3, "check_uprobe_res", "wrong uprobe res: %d\n", skel->bss->uprobe_res)) diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c index dc18e5ae0f..b84f859b12 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c @@ -469,12 +469,12 @@ static void test_overflow(bool test_e2big_overflow, bool ret1) * fills seq_file buffer and then the other will trigger * overflow and needs restart. */ - map1_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, 4, 8, 1, 0); - if (CHECK(map1_fd < 0, "bpf_create_map", + map1_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, 4, 8, 1, NULL); + if (CHECK(map1_fd < 0, "bpf_map_create", "map_creation failed: %s\n", strerror(errno))) goto out; - map2_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, 4, 8, 1, 0); - if (CHECK(map2_fd < 0, "bpf_create_map", + map2_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, 4, 8, 1, NULL); + if (CHECK(map2_fd < 0, "bpf_map_create", "map_creation failed: %s\n", strerror(errno))) goto free_map1; @@ -589,7 +589,7 @@ static void test_overflow(bool test_e2big_overflow, bool ret1) static void test_bpf_hash_map(void) { - __u32 expected_key_a = 0, expected_key_b = 0, expected_key_c = 0; + __u32 expected_key_a = 0, expected_key_b = 0; DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts); struct bpf_iter_bpf_hash_map *skel; int err, i, len, map_fd, iter_fd; @@ -638,7 +638,6 @@ static void test_bpf_hash_map(void) val = i + 4; expected_key_a += key.a; expected_key_b += key.b; - expected_key_c += key.c; expected_val += val; err = bpf_map_update_elem(map_fd, &key, &val, BPF_ANY); @@ -685,7 +684,7 @@ static void test_bpf_hash_map(void) static void test_bpf_percpu_hash_map(void) { - __u32 expected_key_a = 0, expected_key_b = 0, expected_key_c = 0; + __u32 expected_key_a = 0, expected_key_b = 0; DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts); struct bpf_iter_bpf_percpu_hash_map *skel; int err, i, j, len, map_fd, iter_fd; @@ -700,14 +699,13 @@ static void test_bpf_percpu_hash_map(void) char buf[64]; void *val; - val = malloc(8 * bpf_num_possible_cpus()); - skel = bpf_iter_bpf_percpu_hash_map__open(); if (CHECK(!skel, "bpf_iter_bpf_percpu_hash_map__open", "skeleton open failed\n")) return; skel->rodata->num_cpus = bpf_num_possible_cpus(); + val = malloc(8 * bpf_num_possible_cpus()); err = bpf_iter_bpf_percpu_hash_map__load(skel); if (CHECK(!skel, "bpf_iter_bpf_percpu_hash_map__load", @@ -722,7 +720,6 @@ static void test_bpf_percpu_hash_map(void) key.c = i + 3; expected_key_a += key.a; expected_key_b += key.b; - expected_key_c += key.c; for (j = 0; j < bpf_num_possible_cpus(); j++) { *(__u32 *)(val + j * 8) = i + j; @@ -772,6 +769,7 @@ static void test_bpf_percpu_hash_map(void) bpf_link__destroy(link); out: bpf_iter_bpf_percpu_hash_map__destroy(skel); + free(val); } static void test_bpf_array_map(void) @@ -872,14 +870,13 @@ static void test_bpf_percpu_array_map(void) void *val; int len; - val = malloc(8 * bpf_num_possible_cpus()); - skel = bpf_iter_bpf_percpu_array_map__open(); if (CHECK(!skel, "bpf_iter_bpf_percpu_array_map__open", "skeleton open failed\n")) return; skel->rodata->num_cpus = bpf_num_possible_cpus(); + val = malloc(8 * bpf_num_possible_cpus()); err = bpf_iter_bpf_percpu_array_map__load(skel); if (CHECK(!skel, "bpf_iter_bpf_percpu_array_map__load", @@ -935,6 +932,7 @@ static void test_bpf_percpu_array_map(void) bpf_link__destroy(link); out: bpf_iter_bpf_percpu_array_map__destroy(skel); + free(val); } /* An iterator program deletes all local storage in a map. */ diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter_setsockopt.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter_setsockopt.c index 85babb0487..b52ff8ce34 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_iter_setsockopt.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter_setsockopt.c @@ -179,7 +179,7 @@ static void do_bpf_iter_setsockopt(struct bpf_iter_setsockopt *iter_skel, free_fds(est_fds, nr_est); } -void test_bpf_iter_setsockopt(void) +void serial_test_bpf_iter_setsockopt(void) { struct bpf_iter_setsockopt *iter_skel = NULL; struct bpf_cubic *cubic_skel = NULL; diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c b/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c index 284d5921c3..dbe56fa858 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c @@ -3,7 +3,7 @@ #define nr_iters 2 -void test_bpf_obj_id(void) +void serial_test_bpf_obj_id(void) { const __u64 array_magic_value = 0xfaceb00c; const __u32 array_key = 0; @@ -48,7 +48,7 @@ void test_bpf_obj_id(void) bzero(zeros, sizeof(zeros)); for (i = 0; i < nr_iters; i++) { now = time(NULL); - err = bpf_prog_load(file, BPF_PROG_TYPE_RAW_TRACEPOINT, + err = bpf_prog_test_load(file, BPF_PROG_TYPE_RAW_TRACEPOINT, &objs[i], &prog_fds[i]); /* test_obj_id.o is a dumb prog. It should never fail * to load. @@ -65,8 +65,8 @@ void test_bpf_obj_id(void) if (CHECK_FAIL(err)) goto done; - prog = bpf_object__find_program_by_title(objs[i], - "raw_tp/sys_enter"); + prog = bpf_object__find_program_by_name(objs[i], + "test_obj_id"); if (CHECK_FAIL(!prog)) goto done; links[i] = bpf_program__attach(prog); diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c index 94e03df69d..8f7a1cef7d 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c @@ -217,21 +217,22 @@ static bool found; static int libbpf_debug_print(enum libbpf_print_level level, const char *format, va_list args) { - char *log_buf; + const char *prog_name, *log_buf; if (level != LIBBPF_WARN || - strcmp(format, "libbpf: \n%s\n")) { + !strstr(format, "-- BEGIN PROG LOAD LOG --")) { vprintf(format, args); return 0; } + prog_name = va_arg(args, char *); log_buf = va_arg(args, char *); if (!log_buf) goto out; if (err_str && strstr(log_buf, err_str) != NULL) found = true; out: - printf(format, log_buf); + printf(format, prog_name, log_buf); return 0; } diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c index 3d002c245d..ff6cce9fef 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c @@ -19,16 +19,28 @@ extern int extra_prog_load_log_flags; static int check_load(const char *file, enum bpf_prog_type type) { - struct bpf_prog_load_attr attr; struct bpf_object *obj = NULL; - int err, prog_fd; + struct bpf_program *prog; + int err; - memset(&attr, 0, sizeof(struct bpf_prog_load_attr)); - attr.file = file; - attr.prog_type = type; - attr.log_level = 4 | extra_prog_load_log_flags; - attr.prog_flags = BPF_F_TEST_RND_HI32; - err = bpf_prog_load_xattr(&attr, &obj, &prog_fd); + obj = bpf_object__open_file(file, NULL); + err = libbpf_get_error(obj); + if (err) + return err; + + prog = bpf_object__next_program(obj, NULL); + if (!prog) { + err = -ENOENT; + goto err_out; + } + + bpf_program__set_type(prog, type); + bpf_program__set_flags(prog, BPF_F_TEST_RND_HI32); + bpf_program__set_log_level(prog, 4 | extra_prog_load_log_flags); + + err = bpf_object__load(obj); + +err_out: bpf_object__close(obj); return err; } @@ -39,82 +51,183 @@ struct scale_test_def { bool fails; }; -void test_bpf_verif_scale(void) +static void scale_test(const char *file, + enum bpf_prog_type attach_type, + bool should_fail) { - struct scale_test_def tests[] = { - { "loop3.o", BPF_PROG_TYPE_RAW_TRACEPOINT, true /* fails */ }, - - { "test_verif_scale1.o", BPF_PROG_TYPE_SCHED_CLS }, - { "test_verif_scale2.o", BPF_PROG_TYPE_SCHED_CLS }, - { "test_verif_scale3.o", BPF_PROG_TYPE_SCHED_CLS }, - - { "pyperf_global.o", BPF_PROG_TYPE_RAW_TRACEPOINT }, - { "pyperf_subprogs.o", BPF_PROG_TYPE_RAW_TRACEPOINT }, - - /* full unroll by llvm */ - { "pyperf50.o", BPF_PROG_TYPE_RAW_TRACEPOINT }, - { "pyperf100.o", BPF_PROG_TYPE_RAW_TRACEPOINT }, - { "pyperf180.o", BPF_PROG_TYPE_RAW_TRACEPOINT }, - - /* partial unroll. llvm will unroll loop ~150 times. - * C loop count -> 600. - * Asm loop count -> 4. - * 16k insns in loop body. - * Total of 5 such loops. Total program size ~82k insns. - */ - { "pyperf600.o", BPF_PROG_TYPE_RAW_TRACEPOINT }, - - /* no unroll at all. - * C loop count -> 600. - * ASM loop count -> 600. - * ~110 insns in loop body. - * Total of 5 such loops. Total program size ~1500 insns. - */ - { "pyperf600_nounroll.o", BPF_PROG_TYPE_RAW_TRACEPOINT }, - - { "loop1.o", BPF_PROG_TYPE_RAW_TRACEPOINT }, - { "loop2.o", BPF_PROG_TYPE_RAW_TRACEPOINT }, - { "loop4.o", BPF_PROG_TYPE_SCHED_CLS }, - { "loop5.o", BPF_PROG_TYPE_SCHED_CLS }, - { "loop6.o", BPF_PROG_TYPE_KPROBE }, - - /* partial unroll. 19k insn in a loop. - * Total program size 20.8k insn. - * ~350k processed_insns - */ - { "strobemeta.o", BPF_PROG_TYPE_RAW_TRACEPOINT }, - - /* no unroll, tiny loops */ - { "strobemeta_nounroll1.o", BPF_PROG_TYPE_RAW_TRACEPOINT }, - { "strobemeta_nounroll2.o", BPF_PROG_TYPE_RAW_TRACEPOINT }, - - /* non-inlined subprogs */ - { "strobemeta_subprogs.o", BPF_PROG_TYPE_RAW_TRACEPOINT }, - - { "test_sysctl_loop1.o", BPF_PROG_TYPE_CGROUP_SYSCTL }, - { "test_sysctl_loop2.o", BPF_PROG_TYPE_CGROUP_SYSCTL }, - - { "test_xdp_loop.o", BPF_PROG_TYPE_XDP }, - { "test_seg6_loop.o", BPF_PROG_TYPE_LWT_SEG6LOCAL }, - }; libbpf_print_fn_t old_print_fn = NULL; - int err, i; + int err; if (env.verifier_stats) { test__force_log(); old_print_fn = libbpf_set_print(libbpf_debug_print); } - for (i = 0; i < ARRAY_SIZE(tests); i++) { - const struct scale_test_def *test = &tests[i]; - - if (!test__start_subtest(test->file)) - continue; - - err = check_load(test->file, test->attach_type); - CHECK_FAIL(err && !test->fails); - } + err = check_load(file, attach_type); + if (should_fail) + ASSERT_ERR(err, "expect_error"); + else + ASSERT_OK(err, "expect_success"); if (env.verifier_stats) libbpf_set_print(old_print_fn); } + +void test_verif_scale1() +{ + scale_test("test_verif_scale1.o", BPF_PROG_TYPE_SCHED_CLS, false); +} + +void test_verif_scale2() +{ + scale_test("test_verif_scale2.o", BPF_PROG_TYPE_SCHED_CLS, false); +} + +void test_verif_scale3() +{ + scale_test("test_verif_scale3.o", BPF_PROG_TYPE_SCHED_CLS, false); +} + +void test_verif_scale_pyperf_global() +{ + scale_test("pyperf_global.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false); +} + +void test_verif_scale_pyperf_subprogs() +{ + scale_test("pyperf_subprogs.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false); +} + +void test_verif_scale_pyperf50() +{ + /* full unroll by llvm */ + scale_test("pyperf50.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false); +} + +void test_verif_scale_pyperf100() +{ + /* full unroll by llvm */ + scale_test("pyperf100.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false); +} + +void test_verif_scale_pyperf180() +{ + /* full unroll by llvm */ + scale_test("pyperf180.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false); +} + +void test_verif_scale_pyperf600() +{ + /* partial unroll. llvm will unroll loop ~150 times. + * C loop count -> 600. + * Asm loop count -> 4. + * 16k insns in loop body. + * Total of 5 such loops. Total program size ~82k insns. + */ + scale_test("pyperf600.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false); +} + +void test_verif_scale_pyperf600_bpf_loop(void) +{ + /* use the bpf_loop helper*/ + scale_test("pyperf600_bpf_loop.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false); +} + +void test_verif_scale_pyperf600_nounroll() +{ + /* no unroll at all. + * C loop count -> 600. + * ASM loop count -> 600. + * ~110 insns in loop body. + * Total of 5 such loops. Total program size ~1500 insns. + */ + scale_test("pyperf600_nounroll.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false); +} + +void test_verif_scale_loop1() +{ + scale_test("loop1.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false); +} + +void test_verif_scale_loop2() +{ + scale_test("loop2.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false); +} + +void test_verif_scale_loop3_fail() +{ + scale_test("loop3.o", BPF_PROG_TYPE_RAW_TRACEPOINT, true /* fails */); +} + +void test_verif_scale_loop4() +{ + scale_test("loop4.o", BPF_PROG_TYPE_SCHED_CLS, false); +} + +void test_verif_scale_loop5() +{ + scale_test("loop5.o", BPF_PROG_TYPE_SCHED_CLS, false); +} + +void test_verif_scale_loop6() +{ + scale_test("loop6.o", BPF_PROG_TYPE_KPROBE, false); +} + +void test_verif_scale_strobemeta() +{ + /* partial unroll. 19k insn in a loop. + * Total program size 20.8k insn. + * ~350k processed_insns + */ + scale_test("strobemeta.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false); +} + +void test_verif_scale_strobemeta_bpf_loop(void) +{ + /* use the bpf_loop helper*/ + scale_test("strobemeta_bpf_loop.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false); +} + +void test_verif_scale_strobemeta_nounroll1() +{ + /* no unroll, tiny loops */ + scale_test("strobemeta_nounroll1.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false); +} + +void test_verif_scale_strobemeta_nounroll2() +{ + /* no unroll, tiny loops */ + scale_test("strobemeta_nounroll2.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false); +} + +void test_verif_scale_strobemeta_subprogs() +{ + /* non-inlined subprogs */ + scale_test("strobemeta_subprogs.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false); +} + +void test_verif_scale_sysctl_loop1() +{ + scale_test("test_sysctl_loop1.o", BPF_PROG_TYPE_CGROUP_SYSCTL, false); +} + +void test_verif_scale_sysctl_loop2() +{ + scale_test("test_sysctl_loop2.o", BPF_PROG_TYPE_CGROUP_SYSCTL, false); +} + +void test_verif_scale_xdp_loop() +{ + scale_test("test_xdp_loop.o", BPF_PROG_TYPE_XDP, false); +} + +void test_verif_scale_seg6_loop() +{ + scale_test("test_seg6_loop.o", BPF_PROG_TYPE_LWT_SEG6LOCAL, false); +} + +void test_verif_twfw() +{ + scale_test("twfw.o", BPF_PROG_TYPE_CGROUP_SKB, false); +} diff --git a/tools/testing/selftests/bpf/prog_tests/btf.c b/tools/testing/selftests/bpf/prog_tests/btf.c index 649f87382c..8ba53acf9e 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf.c +++ b/tools/testing/selftests/bpf/prog_tests/btf.c @@ -22,7 +22,6 @@ #include #include -#include "bpf_rlimit.h" #include "bpf_util.h" #include "../test_btf.h" #include "test_progs.h" @@ -39,8 +38,8 @@ static bool always_log; #define BTF_END_RAW 0xdeadbeef #define NAME_TBD 0xdeadb33f -#define NAME_NTH(N) (0xffff0000 | N) -#define IS_NAME_NTH(X) ((X & 0xffff0000) == 0xffff0000) +#define NAME_NTH(N) (0xfffe0000 | N) +#define IS_NAME_NTH(X) ((X & 0xffff0000) == 0xfffe0000) #define GET_NAME_NTH_IDX(X) (X & 0x0000ffff) #define MAX_NR_RAW_U32 1024 @@ -3661,6 +3660,302 @@ static struct btf_raw_test raw_tests[] = { .err_str = "Invalid type_size", }, +{ + .descr = "decl_tag test #1, struct/member, well-formed", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_STRUCT_ENC(0, 2, 8), /* [2] */ + BTF_MEMBER_ENC(NAME_TBD, 1, 0), + BTF_MEMBER_ENC(NAME_TBD, 1, 32), + BTF_DECL_TAG_ENC(NAME_TBD, 2, -1), + BTF_DECL_TAG_ENC(NAME_TBD, 2, 0), + BTF_DECL_TAG_ENC(NAME_TBD, 2, 1), + BTF_END_RAW, + }, + BTF_STR_SEC("\0m1\0m2\0tag1\0tag2\0tag3"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "tag_type_check_btf", + .key_size = sizeof(int), + .value_size = 8, + .key_type_id = 1, + .value_type_id = 2, + .max_entries = 1, +}, +{ + .descr = "decl_tag test #2, union/member, well-formed", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_UNION_ENC(NAME_TBD, 2, 4), /* [2] */ + BTF_MEMBER_ENC(NAME_TBD, 1, 0), + BTF_MEMBER_ENC(NAME_TBD, 1, 0), + BTF_DECL_TAG_ENC(NAME_TBD, 2, -1), + BTF_DECL_TAG_ENC(NAME_TBD, 2, 0), + BTF_DECL_TAG_ENC(NAME_TBD, 2, 1), + BTF_END_RAW, + }, + BTF_STR_SEC("\0t\0m1\0m2\0tag1\0tag2\0tag3"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "tag_type_check_btf", + .key_size = sizeof(int), + .value_size = 4, + .key_type_id = 1, + .value_type_id = 2, + .max_entries = 1, +}, +{ + .descr = "decl_tag test #3, variable, well-formed", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_VAR_ENC(NAME_TBD, 1, 0), /* [2] */ + BTF_VAR_ENC(NAME_TBD, 1, 1), /* [3] */ + BTF_DECL_TAG_ENC(NAME_TBD, 2, -1), + BTF_DECL_TAG_ENC(NAME_TBD, 3, -1), + BTF_END_RAW, + }, + BTF_STR_SEC("\0local\0global\0tag1\0tag2"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "tag_type_check_btf", + .key_size = sizeof(int), + .value_size = 4, + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 1, +}, +{ + .descr = "decl_tag test #4, func/parameter, well-formed", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_FUNC_PROTO_ENC(0, 2), /* [2] */ + BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1), + BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1), + BTF_FUNC_ENC(NAME_TBD, 2), /* [3] */ + BTF_DECL_TAG_ENC(NAME_TBD, 3, -1), + BTF_DECL_TAG_ENC(NAME_TBD, 3, 0), + BTF_DECL_TAG_ENC(NAME_TBD, 3, 1), + BTF_END_RAW, + }, + BTF_STR_SEC("\0arg1\0arg2\0f\0tag1\0tag2\0tag3"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "tag_type_check_btf", + .key_size = sizeof(int), + .value_size = 4, + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 1, +}, +{ + .descr = "decl_tag test #5, invalid value", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_VAR_ENC(NAME_TBD, 1, 0), /* [2] */ + BTF_DECL_TAG_ENC(0, 2, -1), + BTF_END_RAW, + }, + BTF_STR_SEC("\0local\0tag"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "tag_type_check_btf", + .key_size = sizeof(int), + .value_size = 4, + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 1, + .btf_load_err = true, + .err_str = "Invalid value", +}, +{ + .descr = "decl_tag test #6, invalid target type", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_DECL_TAG_ENC(NAME_TBD, 1, -1), + BTF_END_RAW, + }, + BTF_STR_SEC("\0tag1"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "tag_type_check_btf", + .key_size = sizeof(int), + .value_size = 4, + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 1, + .btf_load_err = true, + .err_str = "Invalid type", +}, +{ + .descr = "decl_tag test #7, invalid vlen", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_VAR_ENC(NAME_TBD, 1, 0), /* [2] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DECL_TAG, 0, 1), 2), (0), + BTF_END_RAW, + }, + BTF_STR_SEC("\0local\0tag1"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "tag_type_check_btf", + .key_size = sizeof(int), + .value_size = 4, + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 1, + .btf_load_err = true, + .err_str = "vlen != 0", +}, +{ + .descr = "decl_tag test #8, invalid kflag", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_VAR_ENC(NAME_TBD, 1, 0), /* [2] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DECL_TAG, 1, 0), 2), (-1), + BTF_END_RAW, + }, + BTF_STR_SEC("\0local\0tag1"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "tag_type_check_btf", + .key_size = sizeof(int), + .value_size = 4, + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 1, + .btf_load_err = true, + .err_str = "Invalid btf_info kind_flag", +}, +{ + .descr = "decl_tag test #9, var, invalid component_idx", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_VAR_ENC(NAME_TBD, 1, 0), /* [2] */ + BTF_DECL_TAG_ENC(NAME_TBD, 2, 0), + BTF_END_RAW, + }, + BTF_STR_SEC("\0local\0tag"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "tag_type_check_btf", + .key_size = sizeof(int), + .value_size = 4, + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 1, + .btf_load_err = true, + .err_str = "Invalid component_idx", +}, +{ + .descr = "decl_tag test #10, struct member, invalid component_idx", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_STRUCT_ENC(0, 2, 8), /* [2] */ + BTF_MEMBER_ENC(NAME_TBD, 1, 0), + BTF_MEMBER_ENC(NAME_TBD, 1, 32), + BTF_DECL_TAG_ENC(NAME_TBD, 2, 2), + BTF_END_RAW, + }, + BTF_STR_SEC("\0m1\0m2\0tag"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "tag_type_check_btf", + .key_size = sizeof(int), + .value_size = 8, + .key_type_id = 1, + .value_type_id = 2, + .max_entries = 1, + .btf_load_err = true, + .err_str = "Invalid component_idx", +}, +{ + .descr = "decl_tag test #11, func parameter, invalid component_idx", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_FUNC_PROTO_ENC(0, 2), /* [2] */ + BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1), + BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1), + BTF_FUNC_ENC(NAME_TBD, 2), /* [3] */ + BTF_DECL_TAG_ENC(NAME_TBD, 3, 2), + BTF_END_RAW, + }, + BTF_STR_SEC("\0arg1\0arg2\0f\0tag"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "tag_type_check_btf", + .key_size = sizeof(int), + .value_size = 4, + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 1, + .btf_load_err = true, + .err_str = "Invalid component_idx", +}, +{ + .descr = "decl_tag test #12, < -1 component_idx", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_FUNC_PROTO_ENC(0, 2), /* [2] */ + BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1), + BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1), + BTF_FUNC_ENC(NAME_TBD, 2), /* [3] */ + BTF_DECL_TAG_ENC(NAME_TBD, 3, -2), + BTF_END_RAW, + }, + BTF_STR_SEC("\0arg1\0arg2\0f\0tag"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "tag_type_check_btf", + .key_size = sizeof(int), + .value_size = 4, + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 1, + .btf_load_err = true, + .err_str = "Invalid component_idx", +}, +{ + .descr = "decl_tag test #13, typedef, well-formed", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_TYPEDEF_ENC(NAME_TBD, 1), /* [2] */ + BTF_DECL_TAG_ENC(NAME_TBD, 2, -1), + BTF_END_RAW, + }, + BTF_STR_SEC("\0t\0tag"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "tag_type_check_btf", + .key_size = sizeof(int), + .value_size = 4, + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 1, +}, +{ + .descr = "decl_tag test #14, typedef, invalid component_idx", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_TYPEDEF_ENC(NAME_TBD, 1), /* [2] */ + BTF_DECL_TAG_ENC(NAME_TBD, 2, 0), + BTF_END_RAW, + }, + BTF_STR_SEC("\0local\0tag"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "tag_type_check_btf", + .key_size = sizeof(int), + .value_size = 4, + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 1, + .btf_load_err = true, + .err_str = "Invalid component_idx", +}, +{ + .descr = "type_tag test #1", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_TYPE_TAG_ENC(NAME_TBD, 1), /* [2] */ + BTF_PTR_ENC(2), /* [3] */ + BTF_END_RAW, + }, + BTF_STR_SEC("\0tag"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "tag_type_check_btf", + .key_size = sizeof(int), + .value_size = 4, + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 1, +}, + }; /* struct btf_raw_test raw_tests[] */ static const char *get_next_str(const char *start, const char *end) @@ -3767,20 +4062,40 @@ static void *btf_raw_create(const struct btf_header *hdr, next_str_idx < strs_cnt ? strs_idx[next_str_idx] : NULL; done: + free(strs_idx); if (err) { - if (raw_btf) - free(raw_btf); - if (strs_idx) - free(strs_idx); + free(raw_btf); return NULL; } return raw_btf; } +static int load_raw_btf(const void *raw_data, size_t raw_size) +{ + LIBBPF_OPTS(bpf_btf_load_opts, opts); + int btf_fd; + + if (always_log) { + opts.log_buf = btf_log_buf, + opts.log_size = BTF_LOG_BUF_SIZE, + opts.log_level = 1; + } + + btf_fd = bpf_btf_load(raw_data, raw_size, &opts); + if (btf_fd < 0 && !always_log) { + opts.log_buf = btf_log_buf, + opts.log_size = BTF_LOG_BUF_SIZE, + opts.log_level = 1; + btf_fd = bpf_btf_load(raw_data, raw_size, &opts); + } + + return btf_fd; +} + static void do_test_raw(unsigned int test_num) { struct btf_raw_test *test = &raw_tests[test_num - 1]; - struct bpf_create_map_attr create_attr = {}; + LIBBPF_OPTS(bpf_map_create_opts, opts); int map_fd = -1, btf_fd = -1; unsigned int raw_btf_size; struct btf_header *hdr; @@ -3806,16 +4121,14 @@ static void do_test_raw(unsigned int test_num) hdr->str_len = (int)hdr->str_len + test->str_len_delta; *btf_log_buf = '\0'; - btf_fd = bpf_load_btf(raw_btf, raw_btf_size, - btf_log_buf, BTF_LOG_BUF_SIZE, - always_log); + btf_fd = load_raw_btf(raw_btf, raw_btf_size); free(raw_btf); err = ((btf_fd < 0) != test->btf_load_err); if (CHECK(err, "btf_fd:%d test->btf_load_err:%u", btf_fd, test->btf_load_err) || CHECK(test->err_str && !strstr(btf_log_buf, test->err_str), - "expected err_str:%s", test->err_str)) { + "expected err_str:%s\n", test->err_str)) { err = -1; goto done; } @@ -3823,16 +4136,11 @@ static void do_test_raw(unsigned int test_num) if (err || btf_fd < 0) goto done; - create_attr.name = test->map_name; - create_attr.map_type = test->map_type; - create_attr.key_size = test->key_size; - create_attr.value_size = test->value_size; - create_attr.max_entries = test->max_entries; - create_attr.btf_fd = btf_fd; - create_attr.btf_key_type_id = test->key_type_id; - create_attr.btf_value_type_id = test->value_type_id; - - map_fd = bpf_create_map_xattr(&create_attr); + opts.btf_fd = btf_fd; + opts.btf_key_type_id = test->key_type_id; + opts.btf_value_type_id = test->value_type_id; + map_fd = bpf_map_create(test->map_type, test->map_name, + test->key_size, test->value_size, test->max_entries, &opts); err = ((map_fd < 0) != test->map_create_err); CHECK(err, "map_fd:%d test->map_create_err:%u", @@ -3938,9 +4246,7 @@ static int test_big_btf_info(unsigned int test_num) goto done; } - btf_fd = bpf_load_btf(raw_btf, raw_btf_size, - btf_log_buf, BTF_LOG_BUF_SIZE, - always_log); + btf_fd = load_raw_btf(raw_btf, raw_btf_size); if (CHECK(btf_fd < 0, "errno:%d", errno)) { err = -1; goto done; @@ -3996,7 +4302,7 @@ static int test_big_btf_info(unsigned int test_num) static int test_btf_id(unsigned int test_num) { const struct btf_get_info_test *test = &get_info_tests[test_num - 1]; - struct bpf_create_map_attr create_attr = {}; + LIBBPF_OPTS(bpf_map_create_opts, opts); uint8_t *raw_btf = NULL, *user_btf[2] = {}; int btf_fd[2] = {-1, -1}, map_fd = -1; struct bpf_map_info map_info = {}; @@ -4026,9 +4332,7 @@ static int test_btf_id(unsigned int test_num) info[i].btf_size = raw_btf_size; } - btf_fd[0] = bpf_load_btf(raw_btf, raw_btf_size, - btf_log_buf, BTF_LOG_BUF_SIZE, - always_log); + btf_fd[0] = load_raw_btf(raw_btf, raw_btf_size); if (CHECK(btf_fd[0] < 0, "errno:%d", errno)) { err = -1; goto done; @@ -4061,16 +4365,11 @@ static int test_btf_id(unsigned int test_num) } /* Test btf members in struct bpf_map_info */ - create_attr.name = "test_btf_id"; - create_attr.map_type = BPF_MAP_TYPE_ARRAY; - create_attr.key_size = sizeof(int); - create_attr.value_size = sizeof(unsigned int); - create_attr.max_entries = 4; - create_attr.btf_fd = btf_fd[0]; - create_attr.btf_key_type_id = 1; - create_attr.btf_value_type_id = 2; - - map_fd = bpf_create_map_xattr(&create_attr); + opts.btf_fd = btf_fd[0]; + opts.btf_key_type_id = 1; + opts.btf_value_type_id = 2; + map_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, "test_btf_id", + sizeof(int), sizeof(int), 4, &opts); if (CHECK(map_fd < 0, "errno:%d", errno)) { err = -1; goto done; @@ -4163,9 +4462,7 @@ static void do_test_get_info(unsigned int test_num) goto done; } - btf_fd = bpf_load_btf(raw_btf, raw_btf_size, - btf_log_buf, BTF_LOG_BUF_SIZE, - always_log); + btf_fd = load_raw_btf(raw_btf, raw_btf_size); if (CHECK(btf_fd <= 0, "errno:%d", errno)) { err = -1; goto done; @@ -4268,7 +4565,7 @@ static void do_test_file(unsigned int test_num) if (CHECK(err, "obj: %d", err)) return; - prog = bpf_program__next(NULL, obj); + prog = bpf_object__next_program(obj, NULL); if (CHECK(!prog, "Cannot find bpf_prog")) { err = -1; goto done; @@ -4859,7 +5156,7 @@ static void do_test_pprint(int test_num) { const struct btf_raw_test *test = &pprint_test_template[test_num]; enum pprint_mapv_kind_t mapv_kind = test->mapv_kind; - struct bpf_create_map_attr create_attr = {}; + LIBBPF_OPTS(bpf_map_create_opts, opts); bool ordered_map, lossless_map, percpu_map; int err, ret, num_cpus, rounded_value_size; unsigned int key, nr_read_elems; @@ -4885,26 +5182,19 @@ static void do_test_pprint(int test_num) return; *btf_log_buf = '\0'; - btf_fd = bpf_load_btf(raw_btf, raw_btf_size, - btf_log_buf, BTF_LOG_BUF_SIZE, - always_log); + btf_fd = load_raw_btf(raw_btf, raw_btf_size); free(raw_btf); - if (CHECK(btf_fd < 0, "errno:%d", errno)) { + if (CHECK(btf_fd < 0, "errno:%d\n", errno)) { err = -1; goto done; } - create_attr.name = test->map_name; - create_attr.map_type = test->map_type; - create_attr.key_size = test->key_size; - create_attr.value_size = test->value_size; - create_attr.max_entries = test->max_entries; - create_attr.btf_fd = btf_fd; - create_attr.btf_key_type_id = test->key_type_id; - create_attr.btf_value_type_id = test->value_type_id; - - map_fd = bpf_create_map_xattr(&create_attr); + opts.btf_fd = btf_fd; + opts.btf_key_type_id = test->key_type_id; + opts.btf_value_type_id = test->value_type_id; + map_fd = bpf_map_create(test->map_type, test->map_name, + test->key_size, test->value_size, test->max_entries, &opts); if (CHECK(map_fd < 0, "errno:%d", errno)) { err = -1; goto done; @@ -6259,9 +6549,7 @@ static void do_test_info_raw(unsigned int test_num) return; *btf_log_buf = '\0'; - btf_fd = bpf_load_btf(raw_btf, raw_btf_size, - btf_log_buf, BTF_LOG_BUF_SIZE, - always_log); + btf_fd = load_raw_btf(raw_btf, raw_btf_size); free(raw_btf); if (CHECK(btf_fd < 0, "invalid btf_fd errno:%d", errno)) { @@ -6350,7 +6638,7 @@ struct btf_dedup_test { struct btf_dedup_opts opts; }; -const struct btf_dedup_test dedup_tests[] = { +static struct btf_dedup_test dedup_tests[] = { { .descr = "dedup: unused strings filtering", @@ -6370,9 +6658,6 @@ const struct btf_dedup_test dedup_tests[] = { }, BTF_STR_SEC("\0int\0long"), }, - .opts = { - .dont_resolve_fwds = false, - }, }, { .descr = "dedup: strings deduplication", @@ -6395,9 +6680,6 @@ const struct btf_dedup_test dedup_tests[] = { }, BTF_STR_SEC("\0int\0long int"), }, - .opts = { - .dont_resolve_fwds = false, - }, }, { .descr = "dedup: struct example #1", @@ -6421,27 +6703,33 @@ const struct btf_dedup_test dedup_tests[] = { BTF_MEMBER_ENC(NAME_NTH(4), 5, 64), /* const int *a; */ BTF_MEMBER_ENC(NAME_NTH(5), 2, 128), /* int b[16]; */ BTF_MEMBER_ENC(NAME_NTH(6), 1, 640), /* int c; */ - BTF_MEMBER_ENC(NAME_NTH(8), 13, 672), /* float d; */ + BTF_MEMBER_ENC(NAME_NTH(8), 15, 672), /* float d; */ /* ptr -> [3] struct s */ BTF_PTR_ENC(3), /* [4] */ /* ptr -> [6] const int */ BTF_PTR_ENC(6), /* [5] */ /* const -> [1] int */ BTF_CONST_ENC(1), /* [6] */ + /* tag -> [3] struct s */ + BTF_DECL_TAG_ENC(NAME_NTH(2), 3, -1), /* [7] */ + /* tag -> [3] struct s, member 1 */ + BTF_DECL_TAG_ENC(NAME_NTH(2), 3, 1), /* [8] */ /* full copy of the above */ - BTF_TYPE_INT_ENC(NAME_NTH(1), BTF_INT_SIGNED, 0, 32, 4), /* [7] */ - BTF_TYPE_ARRAY_ENC(7, 7, 16), /* [8] */ - BTF_STRUCT_ENC(NAME_NTH(2), 5, 88), /* [9] */ - BTF_MEMBER_ENC(NAME_NTH(3), 10, 0), - BTF_MEMBER_ENC(NAME_NTH(4), 11, 64), - BTF_MEMBER_ENC(NAME_NTH(5), 8, 128), - BTF_MEMBER_ENC(NAME_NTH(6), 7, 640), - BTF_MEMBER_ENC(NAME_NTH(8), 13, 672), - BTF_PTR_ENC(9), /* [10] */ - BTF_PTR_ENC(12), /* [11] */ - BTF_CONST_ENC(7), /* [12] */ - BTF_TYPE_FLOAT_ENC(NAME_NTH(7), 4), /* [13] */ + BTF_TYPE_INT_ENC(NAME_NTH(1), BTF_INT_SIGNED, 0, 32, 4), /* [9] */ + BTF_TYPE_ARRAY_ENC(9, 9, 16), /* [10] */ + BTF_STRUCT_ENC(NAME_NTH(2), 5, 88), /* [11] */ + BTF_MEMBER_ENC(NAME_NTH(3), 12, 0), + BTF_MEMBER_ENC(NAME_NTH(4), 13, 64), + BTF_MEMBER_ENC(NAME_NTH(5), 10, 128), + BTF_MEMBER_ENC(NAME_NTH(6), 9, 640), + BTF_MEMBER_ENC(NAME_NTH(8), 15, 672), + BTF_PTR_ENC(11), /* [12] */ + BTF_PTR_ENC(14), /* [13] */ + BTF_CONST_ENC(9), /* [14] */ + BTF_TYPE_FLOAT_ENC(NAME_NTH(7), 4), /* [15] */ + BTF_DECL_TAG_ENC(NAME_NTH(2), 11, -1), /* [16] */ + BTF_DECL_TAG_ENC(NAME_NTH(2), 11, 1), /* [17] */ BTF_END_RAW, }, BTF_STR_SEC("\0int\0s\0next\0a\0b\0c\0float\0d"), @@ -6458,21 +6746,20 @@ const struct btf_dedup_test dedup_tests[] = { BTF_MEMBER_ENC(NAME_NTH(1), 5, 64), /* const int *a; */ BTF_MEMBER_ENC(NAME_NTH(2), 2, 128), /* int b[16]; */ BTF_MEMBER_ENC(NAME_NTH(3), 1, 640), /* int c; */ - BTF_MEMBER_ENC(NAME_NTH(4), 7, 672), /* float d; */ + BTF_MEMBER_ENC(NAME_NTH(4), 9, 672), /* float d; */ /* ptr -> [3] struct s */ BTF_PTR_ENC(3), /* [4] */ /* ptr -> [6] const int */ BTF_PTR_ENC(6), /* [5] */ /* const -> [1] int */ BTF_CONST_ENC(1), /* [6] */ - BTF_TYPE_FLOAT_ENC(NAME_NTH(7), 4), /* [7] */ + BTF_DECL_TAG_ENC(NAME_NTH(2), 3, -1), /* [7] */ + BTF_DECL_TAG_ENC(NAME_NTH(2), 3, 1), /* [8] */ + BTF_TYPE_FLOAT_ENC(NAME_NTH(7), 4), /* [9] */ BTF_END_RAW, }, BTF_STR_SEC("\0a\0b\0c\0d\0int\0float\0next\0s"), }, - .opts = { - .dont_resolve_fwds = false, - }, }, { .descr = "dedup: struct <-> fwd resolution w/ hash collision", @@ -6515,8 +6802,7 @@ const struct btf_dedup_test dedup_tests[] = { BTF_STR_SEC("\0s\0x"), }, .opts = { - .dont_resolve_fwds = false, - .dedup_table_size = 1, /* force hash collisions */ + .force_collisions = true, /* force hash collisions */ }, }, { @@ -6562,8 +6848,7 @@ const struct btf_dedup_test dedup_tests[] = { BTF_STR_SEC("\0s\0x"), }, .opts = { - .dont_resolve_fwds = false, - .dedup_table_size = 1, /* force hash collisions */ + .force_collisions = true, /* force hash collisions */ }, }, { @@ -6587,12 +6872,16 @@ const struct btf_dedup_test dedup_tests[] = { BTF_RESTRICT_ENC(8), /* [11] restrict */ BTF_FUNC_PROTO_ENC(1, 2), /* [12] func_proto */ BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1), - BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 8), + BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 18), BTF_FUNC_ENC(NAME_TBD, 12), /* [13] func */ BTF_TYPE_FLOAT_ENC(NAME_TBD, 2), /* [14] float */ + BTF_DECL_TAG_ENC(NAME_TBD, 13, -1), /* [15] decl_tag */ + BTF_DECL_TAG_ENC(NAME_TBD, 13, 1), /* [16] decl_tag */ + BTF_DECL_TAG_ENC(NAME_TBD, 7, -1), /* [17] decl_tag */ + BTF_TYPE_TAG_ENC(NAME_TBD, 8), /* [18] type_tag */ BTF_END_RAW, }, - BTF_STR_SEC("\0A\0B\0C\0D\0E\0F\0G\0H\0I\0J\0K\0L\0M\0N"), + BTF_STR_SEC("\0A\0B\0C\0D\0E\0F\0G\0H\0I\0J\0K\0L\0M\0N\0O\0P\0Q\0R"), }, .expect = { .raw_types = { @@ -6613,15 +6902,16 @@ const struct btf_dedup_test dedup_tests[] = { BTF_RESTRICT_ENC(8), /* [11] restrict */ BTF_FUNC_PROTO_ENC(1, 2), /* [12] func_proto */ BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1), - BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 8), + BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 18), BTF_FUNC_ENC(NAME_TBD, 12), /* [13] func */ BTF_TYPE_FLOAT_ENC(NAME_TBD, 2), /* [14] float */ + BTF_DECL_TAG_ENC(NAME_TBD, 13, -1), /* [15] decl_tag */ + BTF_DECL_TAG_ENC(NAME_TBD, 13, 1), /* [16] decl_tag */ + BTF_DECL_TAG_ENC(NAME_TBD, 7, -1), /* [17] decl_tag */ + BTF_TYPE_TAG_ENC(NAME_TBD, 8), /* [18] type_tag */ BTF_END_RAW, }, - BTF_STR_SEC("\0A\0B\0C\0D\0E\0F\0G\0H\0I\0J\0K\0L\0M\0N"), - }, - .opts = { - .dont_resolve_fwds = false, + BTF_STR_SEC("\0A\0B\0C\0D\0E\0F\0G\0H\0I\0J\0K\0L\0M\0N\0O\0P\0Q\0R"), }, }, { @@ -6674,9 +6964,6 @@ const struct btf_dedup_test dedup_tests[] = { }, BTF_STR_SEC("\0int\0some other int\0float"), }, - .opts = { - .dont_resolve_fwds = false, - }, }, { .descr = "dedup: enum fwd resolution", @@ -6718,9 +7005,6 @@ const struct btf_dedup_test dedup_tests[] = { }, BTF_STR_SEC("\0e1\0e1_val\0e2\0e2_val"), }, - .opts = { - .dont_resolve_fwds = false, - }, }, { .descr = "dedup: datasec and vars pass-through", @@ -6763,8 +7047,329 @@ const struct btf_dedup_test dedup_tests[] = { BTF_STR_SEC("\0.bss\0t"), }, .opts = { - .dont_resolve_fwds = false, - .dedup_table_size = 1 + .force_collisions = true + }, +}, +{ + .descr = "dedup: func/func_arg/var tags", + .input = { + .raw_types = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* static int t */ + BTF_VAR_ENC(NAME_NTH(1), 1, 0), /* [2] */ + /* void f(int a1, int a2) */ + BTF_FUNC_PROTO_ENC(0, 2), /* [3] */ + BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(2), 1), + BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(3), 1), + BTF_FUNC_ENC(NAME_NTH(4), 2), /* [4] */ + /* tag -> t */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 2, -1), /* [5] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 2, -1), /* [6] */ + /* tag -> func */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 4, -1), /* [7] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 4, -1), /* [8] */ + /* tag -> func arg a1 */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 4, 1), /* [9] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 4, 1), /* [10] */ + BTF_END_RAW, + }, + BTF_STR_SEC("\0t\0a1\0a2\0f\0tag"), + }, + .expect = { + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_VAR_ENC(NAME_NTH(1), 1, 0), /* [2] */ + BTF_FUNC_PROTO_ENC(0, 2), /* [3] */ + BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(2), 1), + BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(3), 1), + BTF_FUNC_ENC(NAME_NTH(4), 2), /* [4] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 2, -1), /* [5] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 4, -1), /* [6] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 4, 1), /* [7] */ + BTF_END_RAW, + }, + BTF_STR_SEC("\0t\0a1\0a2\0f\0tag"), + }, +}, +{ + .descr = "dedup: func/func_param tags", + .input = { + .raw_types = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* void f(int a1, int a2) */ + BTF_FUNC_PROTO_ENC(0, 2), /* [2] */ + BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(1), 1), + BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(2), 1), + BTF_FUNC_ENC(NAME_NTH(3), 2), /* [3] */ + /* void f(int a1, int a2) */ + BTF_FUNC_PROTO_ENC(0, 2), /* [4] */ + BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(1), 1), + BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(2), 1), + BTF_FUNC_ENC(NAME_NTH(3), 4), /* [5] */ + /* tag -> f: tag1, tag2 */ + BTF_DECL_TAG_ENC(NAME_NTH(4), 3, -1), /* [6] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 3, -1), /* [7] */ + /* tag -> f/a2: tag1, tag2 */ + BTF_DECL_TAG_ENC(NAME_NTH(4), 3, 1), /* [8] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 3, 1), /* [9] */ + /* tag -> f: tag1, tag3 */ + BTF_DECL_TAG_ENC(NAME_NTH(4), 5, -1), /* [10] */ + BTF_DECL_TAG_ENC(NAME_NTH(6), 5, -1), /* [11] */ + /* tag -> f/a2: tag1, tag3 */ + BTF_DECL_TAG_ENC(NAME_NTH(4), 5, 1), /* [12] */ + BTF_DECL_TAG_ENC(NAME_NTH(6), 5, 1), /* [13] */ + BTF_END_RAW, + }, + BTF_STR_SEC("\0a1\0a2\0f\0tag1\0tag2\0tag3"), + }, + .expect = { + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_FUNC_PROTO_ENC(0, 2), /* [2] */ + BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(1), 1), + BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(2), 1), + BTF_FUNC_ENC(NAME_NTH(3), 2), /* [3] */ + BTF_DECL_TAG_ENC(NAME_NTH(4), 3, -1), /* [4] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 3, -1), /* [5] */ + BTF_DECL_TAG_ENC(NAME_NTH(6), 3, -1), /* [6] */ + BTF_DECL_TAG_ENC(NAME_NTH(4), 3, 1), /* [7] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 3, 1), /* [8] */ + BTF_DECL_TAG_ENC(NAME_NTH(6), 3, 1), /* [9] */ + BTF_END_RAW, + }, + BTF_STR_SEC("\0a1\0a2\0f\0tag1\0tag2\0tag3"), + }, +}, +{ + .descr = "dedup: struct/struct_member tags", + .input = { + .raw_types = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_STRUCT_ENC(NAME_NTH(1), 2, 8), /* [2] */ + BTF_MEMBER_ENC(NAME_NTH(2), 1, 0), + BTF_MEMBER_ENC(NAME_NTH(3), 1, 32), + BTF_STRUCT_ENC(NAME_NTH(1), 2, 8), /* [3] */ + BTF_MEMBER_ENC(NAME_NTH(2), 1, 0), + BTF_MEMBER_ENC(NAME_NTH(3), 1, 32), + /* tag -> t: tag1, tag2 */ + BTF_DECL_TAG_ENC(NAME_NTH(4), 2, -1), /* [4] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 2, -1), /* [5] */ + /* tag -> t/m2: tag1, tag2 */ + BTF_DECL_TAG_ENC(NAME_NTH(4), 2, 1), /* [6] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 2, 1), /* [7] */ + /* tag -> t: tag1, tag3 */ + BTF_DECL_TAG_ENC(NAME_NTH(4), 3, -1), /* [8] */ + BTF_DECL_TAG_ENC(NAME_NTH(6), 3, -1), /* [9] */ + /* tag -> t/m2: tag1, tag3 */ + BTF_DECL_TAG_ENC(NAME_NTH(4), 3, 1), /* [10] */ + BTF_DECL_TAG_ENC(NAME_NTH(6), 3, 1), /* [11] */ + BTF_END_RAW, + }, + BTF_STR_SEC("\0t\0m1\0m2\0tag1\0tag2\0tag3"), + }, + .expect = { + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_STRUCT_ENC(NAME_NTH(1), 2, 8), /* [2] */ + BTF_MEMBER_ENC(NAME_NTH(2), 1, 0), + BTF_MEMBER_ENC(NAME_NTH(3), 1, 32), + BTF_DECL_TAG_ENC(NAME_NTH(4), 2, -1), /* [3] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 2, -1), /* [4] */ + BTF_DECL_TAG_ENC(NAME_NTH(6), 2, -1), /* [5] */ + BTF_DECL_TAG_ENC(NAME_NTH(4), 2, 1), /* [6] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 2, 1), /* [7] */ + BTF_DECL_TAG_ENC(NAME_NTH(6), 2, 1), /* [8] */ + BTF_END_RAW, + }, + BTF_STR_SEC("\0t\0m1\0m2\0tag1\0tag2\0tag3"), + }, +}, +{ + .descr = "dedup: typedef tags", + .input = { + .raw_types = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_TYPEDEF_ENC(NAME_NTH(1), 1), /* [2] */ + BTF_TYPEDEF_ENC(NAME_NTH(1), 1), /* [3] */ + /* tag -> t: tag1, tag2 */ + BTF_DECL_TAG_ENC(NAME_NTH(2), 2, -1), /* [4] */ + BTF_DECL_TAG_ENC(NAME_NTH(3), 2, -1), /* [5] */ + /* tag -> t: tag1, tag3 */ + BTF_DECL_TAG_ENC(NAME_NTH(2), 3, -1), /* [6] */ + BTF_DECL_TAG_ENC(NAME_NTH(4), 3, -1), /* [7] */ + BTF_END_RAW, + }, + BTF_STR_SEC("\0t\0tag1\0tag2\0tag3"), + }, + .expect = { + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_TYPEDEF_ENC(NAME_NTH(1), 1), /* [2] */ + BTF_DECL_TAG_ENC(NAME_NTH(2), 2, -1), /* [3] */ + BTF_DECL_TAG_ENC(NAME_NTH(3), 2, -1), /* [4] */ + BTF_DECL_TAG_ENC(NAME_NTH(4), 2, -1), /* [5] */ + BTF_END_RAW, + }, + BTF_STR_SEC("\0t\0tag1\0tag2\0tag3"), + }, +}, +{ + .descr = "dedup: btf_type_tag #1", + .input = { + .raw_types = { + /* ptr -> tag2 -> tag1 -> int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_TYPE_TAG_ENC(NAME_NTH(1), 1), /* [2] */ + BTF_TYPE_TAG_ENC(NAME_NTH(2), 2), /* [3] */ + BTF_PTR_ENC(3), /* [4] */ + /* ptr -> tag2 -> tag1 -> int */ + BTF_TYPE_TAG_ENC(NAME_NTH(1), 1), /* [5] */ + BTF_TYPE_TAG_ENC(NAME_NTH(2), 5), /* [6] */ + BTF_PTR_ENC(6), /* [7] */ + /* ptr -> tag1 -> int */ + BTF_TYPE_TAG_ENC(NAME_NTH(1), 1), /* [8] */ + BTF_PTR_ENC(8), /* [9] */ + BTF_END_RAW, + }, + BTF_STR_SEC("\0tag1\0tag2"), + }, + .expect = { + .raw_types = { + /* ptr -> tag2 -> tag1 -> int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_TYPE_TAG_ENC(NAME_NTH(1), 1), /* [2] */ + BTF_TYPE_TAG_ENC(NAME_NTH(2), 2), /* [3] */ + BTF_PTR_ENC(3), /* [4] */ + /* ptr -> tag1 -> int */ + BTF_PTR_ENC(2), /* [5] */ + BTF_END_RAW, + }, + BTF_STR_SEC("\0tag1\0tag2"), + }, +}, +{ + .descr = "dedup: btf_type_tag #2", + .input = { + .raw_types = { + /* ptr -> tag2 -> tag1 -> int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_TYPE_TAG_ENC(NAME_NTH(1), 1), /* [2] */ + BTF_TYPE_TAG_ENC(NAME_NTH(2), 2), /* [3] */ + BTF_PTR_ENC(3), /* [4] */ + /* ptr -> tag2 -> int */ + BTF_TYPE_TAG_ENC(NAME_NTH(2), 1), /* [5] */ + BTF_PTR_ENC(5), /* [6] */ + BTF_END_RAW, + }, + BTF_STR_SEC("\0tag1\0tag2"), + }, + .expect = { + .raw_types = { + /* ptr -> tag2 -> tag1 -> int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_TYPE_TAG_ENC(NAME_NTH(1), 1), /* [2] */ + BTF_TYPE_TAG_ENC(NAME_NTH(2), 2), /* [3] */ + BTF_PTR_ENC(3), /* [4] */ + /* ptr -> tag2 -> int */ + BTF_TYPE_TAG_ENC(NAME_NTH(2), 1), /* [5] */ + BTF_PTR_ENC(5), /* [6] */ + BTF_END_RAW, + }, + BTF_STR_SEC("\0tag1\0tag2"), + }, +}, +{ + .descr = "dedup: btf_type_tag #3", + .input = { + .raw_types = { + /* ptr -> tag2 -> tag1 -> int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_TYPE_TAG_ENC(NAME_NTH(1), 1), /* [2] */ + BTF_TYPE_TAG_ENC(NAME_NTH(2), 2), /* [3] */ + BTF_PTR_ENC(3), /* [4] */ + /* ptr -> tag1 -> tag2 -> int */ + BTF_TYPE_TAG_ENC(NAME_NTH(2), 1), /* [5] */ + BTF_TYPE_TAG_ENC(NAME_NTH(1), 5), /* [6] */ + BTF_PTR_ENC(6), /* [7] */ + BTF_END_RAW, + }, + BTF_STR_SEC("\0tag1\0tag2"), + }, + .expect = { + .raw_types = { + /* ptr -> tag2 -> tag1 -> int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_TYPE_TAG_ENC(NAME_NTH(1), 1), /* [2] */ + BTF_TYPE_TAG_ENC(NAME_NTH(2), 2), /* [3] */ + BTF_PTR_ENC(3), /* [4] */ + /* ptr -> tag1 -> tag2 -> int */ + BTF_TYPE_TAG_ENC(NAME_NTH(2), 1), /* [5] */ + BTF_TYPE_TAG_ENC(NAME_NTH(1), 5), /* [6] */ + BTF_PTR_ENC(6), /* [7] */ + BTF_END_RAW, + }, + BTF_STR_SEC("\0tag1\0tag2"), + }, +}, +{ + .descr = "dedup: btf_type_tag #4", + .input = { + .raw_types = { + /* ptr -> tag1 -> int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_TYPE_TAG_ENC(NAME_NTH(1), 1), /* [2] */ + BTF_PTR_ENC(2), /* [3] */ + /* ptr -> tag1 -> long */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 64, 8), /* [4] */ + BTF_TYPE_TAG_ENC(NAME_NTH(1), 4), /* [5] */ + BTF_PTR_ENC(5), /* [6] */ + BTF_END_RAW, + }, + BTF_STR_SEC("\0tag1"), + }, + .expect = { + .raw_types = { + /* ptr -> tag1 -> int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_TYPE_TAG_ENC(NAME_NTH(1), 1), /* [2] */ + BTF_PTR_ENC(2), /* [3] */ + /* ptr -> tag1 -> long */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 64, 8), /* [4] */ + BTF_TYPE_TAG_ENC(NAME_NTH(1), 4), /* [5] */ + BTF_PTR_ENC(5), /* [6] */ + BTF_END_RAW, + }, + BTF_STR_SEC("\0tag1"), + }, +}, +{ + .descr = "dedup: btf_type_tag #5, struct", + .input = { + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_TYPE_TAG_ENC(NAME_NTH(1), 1), /* [2] */ + BTF_TYPE_ENC(NAME_NTH(2), BTF_INFO_ENC(BTF_KIND_STRUCT, 1, 1), 4), /* [3] */ + BTF_MEMBER_ENC(NAME_NTH(3), 2, BTF_MEMBER_OFFSET(0, 0)), + BTF_TYPE_TAG_ENC(NAME_NTH(1), 1), /* [4] */ + BTF_TYPE_ENC(NAME_NTH(2), BTF_INFO_ENC(BTF_KIND_STRUCT, 1, 1), 4), /* [5] */ + BTF_MEMBER_ENC(NAME_NTH(3), 4, BTF_MEMBER_OFFSET(0, 0)), + BTF_END_RAW, + }, + BTF_STR_SEC("\0tag1\0t\0m"), + }, + .expect = { + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_TYPE_TAG_ENC(NAME_NTH(1), 1), /* [2] */ + BTF_TYPE_ENC(NAME_NTH(2), BTF_INFO_ENC(BTF_KIND_STRUCT, 1, 1), 4), /* [3] */ + BTF_MEMBER_ENC(NAME_NTH(3), 2, BTF_MEMBER_OFFSET(0, 0)), + BTF_END_RAW, + }, + BTF_STR_SEC("\0tag1\0t\0m"), }, }, @@ -6785,6 +7390,7 @@ static int btf_type_size(const struct btf_type *t) case BTF_KIND_TYPEDEF: case BTF_KIND_FUNC: case BTF_KIND_FLOAT: + case BTF_KIND_TYPE_TAG: return base_size; case BTF_KIND_INT: return base_size + sizeof(__u32); @@ -6801,6 +7407,8 @@ static int btf_type_size(const struct btf_type *t) return base_size + sizeof(struct btf_var); case BTF_KIND_DATASEC: return base_size + vlen * sizeof(struct btf_var_secinfo); + case BTF_KIND_DECL_TAG: + return base_size + sizeof(struct btf_decl_tag); default: fprintf(stderr, "Unsupported BTF_KIND:%u\n", kind); return -EINVAL; @@ -6821,7 +7429,7 @@ static void dump_btf_strings(const char *strs, __u32 len) static void do_test_dedup(unsigned int test_num) { - const struct btf_dedup_test *test = &dedup_tests[test_num - 1]; + struct btf_dedup_test *test = &dedup_tests[test_num - 1]; __u32 test_nr_types, expect_nr_types, test_btf_size, expect_btf_size; const struct btf_header *test_hdr, *expect_hdr; struct btf *test_btf = NULL, *expect_btf = NULL; @@ -6865,14 +7473,15 @@ static void do_test_dedup(unsigned int test_num) goto done; } - err = btf__dedup(test_btf, NULL, &test->opts); + test->opts.sz = sizeof(test->opts); + err = btf__dedup(test_btf, &test->opts); if (CHECK(err, "btf_dedup failed errno:%d", err)) { err = -1; goto done; } - test_btf_data = btf__get_raw_data(test_btf, &test_btf_size); - expect_btf_data = btf__get_raw_data(expect_btf, &expect_btf_size); + test_btf_data = btf__raw_data(test_btf, &test_btf_size); + expect_btf_data = btf__raw_data(expect_btf, &expect_btf_size); if (CHECK(test_btf_size != expect_btf_size, "test_btf_size:%u != expect_btf_size:%u", test_btf_size, expect_btf_size)) { @@ -6926,8 +7535,8 @@ static void do_test_dedup(unsigned int test_num) expect_str_cur += expect_len + 1; } - test_nr_types = btf__get_nr_types(test_btf); - expect_nr_types = btf__get_nr_types(expect_btf); + test_nr_types = btf__type_cnt(test_btf); + expect_nr_types = btf__type_cnt(expect_btf); if (CHECK(test_nr_types != expect_nr_types, "test_nr_types:%u != expect_nr_types:%u", test_nr_types, expect_nr_types)) { @@ -6935,7 +7544,7 @@ static void do_test_dedup(unsigned int test_num) goto done; } - for (i = 1; i <= test_nr_types; i++) { + for (i = 1; i < test_nr_types; i++) { const struct btf_type *test_type, *expect_type; int test_size, expect_size; diff --git a/tools/testing/selftests/bpf/prog_tests/btf_dedup_split.c b/tools/testing/selftests/bpf/prog_tests/btf_dedup_split.c index 64554fd335..90aac43757 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf_dedup_split.c +++ b/tools/testing/selftests/bpf/prog_tests/btf_dedup_split.c @@ -92,7 +92,7 @@ struct s2 {\n\ int *f3;\n\ };\n\n", "c_dump"); - err = btf__dedup(btf2, NULL, NULL); + err = btf__dedup(btf2, NULL); if (!ASSERT_OK(err, "btf_dedup")) goto cleanup; @@ -186,7 +186,7 @@ static void test_split_fwd_resolve() { "\t'f1' type_id=7 bits_offset=0\n" "\t'f2' type_id=9 bits_offset=64"); - err = btf__dedup(btf2, NULL, NULL); + err = btf__dedup(btf2, NULL); if (!ASSERT_OK(err, "btf_dedup")) goto cleanup; @@ -283,7 +283,7 @@ static void test_split_struct_duped() { "[13] STRUCT 's3' size=8 vlen=1\n" "\t'f1' type_id=12 bits_offset=0"); - err = btf__dedup(btf2, NULL, NULL); + err = btf__dedup(btf2, NULL); if (!ASSERT_OK(err, "btf_dedup")) goto cleanup; @@ -314,6 +314,117 @@ static void test_split_struct_duped() { btf__free(btf1); } +static void btf_add_dup_struct_in_cu(struct btf *btf, int start_id) +{ +#define ID(n) (start_id + n) + btf__set_pointer_size(btf, 8); /* enforce 64-bit arch */ + + btf__add_int(btf, "int", 4, BTF_INT_SIGNED); /* [1] int */ + + btf__add_struct(btf, "s", 8); /* [2] struct s { */ + btf__add_field(btf, "a", ID(3), 0, 0); /* struct anon a; */ + btf__add_field(btf, "b", ID(4), 0, 0); /* struct anon b; */ + /* } */ + + btf__add_struct(btf, "(anon)", 8); /* [3] struct anon { */ + btf__add_field(btf, "f1", ID(1), 0, 0); /* int f1; */ + btf__add_field(btf, "f2", ID(1), 32, 0); /* int f2; */ + /* } */ + + btf__add_struct(btf, "(anon)", 8); /* [4] struct anon { */ + btf__add_field(btf, "f1", ID(1), 0, 0); /* int f1; */ + btf__add_field(btf, "f2", ID(1), 32, 0); /* int f2; */ + /* } */ +#undef ID +} + +static void test_split_dup_struct_in_cu() +{ + struct btf *btf1, *btf2 = NULL; + int err; + + /* generate the base data.. */ + btf1 = btf__new_empty(); + if (!ASSERT_OK_PTR(btf1, "empty_main_btf")) + return; + + btf_add_dup_struct_in_cu(btf1, 0); + + VALIDATE_RAW_BTF( + btf1, + "[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED", + "[2] STRUCT 's' size=8 vlen=2\n" + "\t'a' type_id=3 bits_offset=0\n" + "\t'b' type_id=4 bits_offset=0", + "[3] STRUCT '(anon)' size=8 vlen=2\n" + "\t'f1' type_id=1 bits_offset=0\n" + "\t'f2' type_id=1 bits_offset=32", + "[4] STRUCT '(anon)' size=8 vlen=2\n" + "\t'f1' type_id=1 bits_offset=0\n" + "\t'f2' type_id=1 bits_offset=32"); + + /* ..dedup them... */ + err = btf__dedup(btf1, NULL); + if (!ASSERT_OK(err, "btf_dedup")) + goto cleanup; + + VALIDATE_RAW_BTF( + btf1, + "[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED", + "[2] STRUCT 's' size=8 vlen=2\n" + "\t'a' type_id=3 bits_offset=0\n" + "\t'b' type_id=3 bits_offset=0", + "[3] STRUCT '(anon)' size=8 vlen=2\n" + "\t'f1' type_id=1 bits_offset=0\n" + "\t'f2' type_id=1 bits_offset=32"); + + /* and add the same data on top of it */ + btf2 = btf__new_empty_split(btf1); + if (!ASSERT_OK_PTR(btf2, "empty_split_btf")) + goto cleanup; + + btf_add_dup_struct_in_cu(btf2, 3); + + VALIDATE_RAW_BTF( + btf2, + "[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED", + "[2] STRUCT 's' size=8 vlen=2\n" + "\t'a' type_id=3 bits_offset=0\n" + "\t'b' type_id=3 bits_offset=0", + "[3] STRUCT '(anon)' size=8 vlen=2\n" + "\t'f1' type_id=1 bits_offset=0\n" + "\t'f2' type_id=1 bits_offset=32", + "[4] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED", + "[5] STRUCT 's' size=8 vlen=2\n" + "\t'a' type_id=6 bits_offset=0\n" + "\t'b' type_id=7 bits_offset=0", + "[6] STRUCT '(anon)' size=8 vlen=2\n" + "\t'f1' type_id=4 bits_offset=0\n" + "\t'f2' type_id=4 bits_offset=32", + "[7] STRUCT '(anon)' size=8 vlen=2\n" + "\t'f1' type_id=4 bits_offset=0\n" + "\t'f2' type_id=4 bits_offset=32"); + + err = btf__dedup(btf2, NULL); + if (!ASSERT_OK(err, "btf_dedup")) + goto cleanup; + + /* after dedup it should match the original data */ + VALIDATE_RAW_BTF( + btf2, + "[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED", + "[2] STRUCT 's' size=8 vlen=2\n" + "\t'a' type_id=3 bits_offset=0\n" + "\t'b' type_id=3 bits_offset=0", + "[3] STRUCT '(anon)' size=8 vlen=2\n" + "\t'f1' type_id=1 bits_offset=0\n" + "\t'f2' type_id=1 bits_offset=32"); + +cleanup: + btf__free(btf2); + btf__free(btf1); +} + void test_btf_dedup_split() { if (test__start_subtest("split_simple")) @@ -322,4 +433,6 @@ void test_btf_dedup_split() test_split_struct_duped(); if (test__start_subtest("split_fwd_resolve")) test_split_fwd_resolve(); + if (test__start_subtest("split_dup_struct_in_cu")) + test_split_dup_struct_in_cu(); } diff --git a/tools/testing/selftests/bpf/prog_tests/btf_dump.c b/tools/testing/selftests/bpf/prog_tests/btf_dump.c index 52ccf0cf35..9e26903f91 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf_dump.c +++ b/tools/testing/selftests/bpf/prog_tests/btf_dump.c @@ -13,30 +13,28 @@ static struct btf_dump_test_case { const char *name; const char *file; bool known_ptr_sz; - struct btf_dump_opts opts; } btf_dump_test_cases[] = { - {"btf_dump: syntax", "btf_dump_test_case_syntax", true, {}}, - {"btf_dump: ordering", "btf_dump_test_case_ordering", false, {}}, - {"btf_dump: padding", "btf_dump_test_case_padding", true, {}}, - {"btf_dump: packing", "btf_dump_test_case_packing", true, {}}, - {"btf_dump: bitfields", "btf_dump_test_case_bitfields", true, {}}, - {"btf_dump: multidim", "btf_dump_test_case_multidim", false, {}}, - {"btf_dump: namespacing", "btf_dump_test_case_namespacing", false, {}}, + {"btf_dump: syntax", "btf_dump_test_case_syntax", true}, + {"btf_dump: ordering", "btf_dump_test_case_ordering", false}, + {"btf_dump: padding", "btf_dump_test_case_padding", true}, + {"btf_dump: packing", "btf_dump_test_case_packing", true}, + {"btf_dump: bitfields", "btf_dump_test_case_bitfields", true}, + {"btf_dump: multidim", "btf_dump_test_case_multidim", false}, + {"btf_dump: namespacing", "btf_dump_test_case_namespacing", false}, }; -static int btf_dump_all_types(const struct btf *btf, - const struct btf_dump_opts *opts) +static int btf_dump_all_types(const struct btf *btf, void *ctx) { - size_t type_cnt = btf__get_nr_types(btf); + size_t type_cnt = btf__type_cnt(btf); struct btf_dump *d; int err = 0, id; - d = btf_dump__new(btf, NULL, opts, btf_dump_printf); + d = btf_dump__new(btf, btf_dump_printf, ctx, NULL); err = libbpf_get_error(d); if (err) return err; - for (id = 1; id <= type_cnt; id++) { + for (id = 1; id < type_cnt; id++) { err = btf_dump__dump_type(d, id); if (err) goto done; @@ -88,8 +86,7 @@ static int test_btf_dump_case(int n, struct btf_dump_test_case *t) goto done; } - t->opts.ctx = f; - err = btf_dump_all_types(btf, &t->opts); + err = btf_dump_all_types(btf, f); fclose(f); close(fd); if (CHECK(err, "btf_dump", "failure during C dumping: %d\n", err)) { @@ -133,11 +130,10 @@ static char *dump_buf; static size_t dump_buf_sz; static FILE *dump_buf_file; -void test_btf_dump_incremental(void) +static void test_btf_dump_incremental(void) { struct btf *btf = NULL; struct btf_dump *d = NULL; - struct btf_dump_opts opts; int id, err, i; dump_buf_file = open_memstream(&dump_buf, &dump_buf_sz); @@ -146,8 +142,7 @@ void test_btf_dump_incremental(void) btf = btf__new_empty(); if (!ASSERT_OK_PTR(btf, "new_empty")) goto err_out; - opts.ctx = dump_buf_file; - d = btf_dump__new(btf, NULL, &opts, btf_dump_printf); + d = btf_dump__new(btf, btf_dump_printf, dump_buf_file, NULL); if (!ASSERT_OK(libbpf_get_error(d), "btf_dump__new")) goto err_out; @@ -171,7 +166,7 @@ void test_btf_dump_incremental(void) err = btf__add_field(btf, "x", 2, 0, 0); ASSERT_OK(err, "field_ok"); - for (i = 1; i <= btf__get_nr_types(btf); i++) { + for (i = 1; i < btf__type_cnt(btf); i++) { err = btf_dump__dump_type(d, i); ASSERT_OK(err, "dump_type_ok"); } @@ -210,7 +205,7 @@ void test_btf_dump_incremental(void) err = btf__add_field(btf, "s", 3, 32, 0); ASSERT_OK(err, "field_ok"); - for (i = 1; i <= btf__get_nr_types(btf); i++) { + for (i = 1; i < btf__type_cnt(btf); i++) { err = btf_dump__dump_type(d, i); ASSERT_OK(err, "dump_type_ok"); } @@ -328,7 +323,7 @@ static void test_btf_dump_int_data(struct btf *btf, struct btf_dump *d, char *str) { #ifdef __SIZEOF_INT128__ - __int128 i = 0xffffffffffffffff; + unsigned __int128 i = 0xffffffffffffffff; /* this dance is required because we cannot directly initialize * a 128-bit value to anything larger than a 64-bit value. @@ -358,12 +353,27 @@ static void test_btf_dump_int_data(struct btf *btf, struct btf_dump *d, TEST_BTF_DUMP_DATA_OVER(btf, d, NULL, str, int, sizeof(int)-1, "", 1); #ifdef __SIZEOF_INT128__ - TEST_BTF_DUMP_DATA(btf, d, NULL, str, __int128, BTF_F_COMPACT, - "(__int128)0xffffffffffffffff", - 0xffffffffffffffff); - ASSERT_OK(btf_dump_data(btf, d, "__int128", NULL, 0, &i, 16, str, - "(__int128)0xfffffffffffffffffffffffffffffffe"), - "dump __int128"); + /* gcc encode unsigned __int128 type with name "__int128 unsigned" in dwarf, + * and clang encode it with name "unsigned __int128" in dwarf. + * Do an availability test for either variant before doing actual test. + */ + if (btf__find_by_name(btf, "unsigned __int128") > 0) { + TEST_BTF_DUMP_DATA(btf, d, NULL, str, unsigned __int128, BTF_F_COMPACT, + "(unsigned __int128)0xffffffffffffffff", + 0xffffffffffffffff); + ASSERT_OK(btf_dump_data(btf, d, "unsigned __int128", NULL, 0, &i, 16, str, + "(unsigned __int128)0xfffffffffffffffffffffffffffffffe"), + "dump unsigned __int128"); + } else if (btf__find_by_name(btf, "__int128 unsigned") > 0) { + TEST_BTF_DUMP_DATA(btf, d, NULL, str, __int128 unsigned, BTF_F_COMPACT, + "(__int128 unsigned)0xffffffffffffffff", + 0xffffffffffffffff); + ASSERT_OK(btf_dump_data(btf, d, "__int128 unsigned", NULL, 0, &i, 16, str, + "(__int128 unsigned)0xfffffffffffffffffffffffffffffffe"), + "dump unsigned __int128"); + } else { + ASSERT_TRUE(false, "unsigned_int128_not_found"); + } #endif } @@ -746,7 +756,7 @@ static void test_btf_dump_struct_data(struct btf *btf, struct btf_dump *d, /* overflow bpf_sock_ops struct with final element nonzero/zero. * Regardless of the value of the final field, we don't have all the * data we need to display it, so we should trigger an overflow. - * In other words oveflow checking should trump "is field zero?" + * In other words overflow checking should trump "is field zero?" * checks because if we've overflowed, it shouldn't matter what the * field is - we can't trust its value so shouldn't display it. */ @@ -763,8 +773,10 @@ static void test_btf_dump_struct_data(struct btf *btf, struct btf_dump *d, static void test_btf_dump_var_data(struct btf *btf, struct btf_dump *d, char *str) { +#if defined(__i386__) || defined(__x86_64__) || defined(__aarch64__) TEST_BTF_DUMP_VAR(btf, d, NULL, str, "cpu_number", int, BTF_F_COMPACT, "int cpu_number = (int)100", 100); +#endif TEST_BTF_DUMP_VAR(btf, d, NULL, str, "cpu_profile_flip", int, BTF_F_COMPACT, "static int cpu_profile_flip = (int)2", 2); } @@ -797,26 +809,28 @@ static void test_btf_datasec(struct btf *btf, struct btf_dump *d, char *str, static void test_btf_dump_datasec_data(char *str) { - struct btf *btf = btf__parse("xdping_kern.o", NULL); - struct btf_dump_opts opts = { .ctx = str }; + struct btf *btf; char license[4] = "GPL"; struct btf_dump *d; + btf = btf__parse("xdping_kern.o", NULL); if (!ASSERT_OK_PTR(btf, "xdping_kern.o BTF not found")) return; - d = btf_dump__new(btf, NULL, &opts, btf_dump_snprintf); + d = btf_dump__new(btf, btf_dump_snprintf, str, NULL); if (!ASSERT_OK_PTR(d, "could not create BTF dump")) - return; + goto out; test_btf_datasec(btf, d, str, "license", "SEC(\"license\") char[4] _license = (char[4])['G','P','L',];", license, sizeof(license)); +out: + btf_dump__free(d); + btf__free(btf); } void test_btf_dump() { char str[STRSIZE]; - struct btf_dump_opts opts = { .ctx = str }; struct btf_dump *d; struct btf *btf; int i; @@ -836,7 +850,7 @@ void test_btf_dump() { if (!ASSERT_OK_PTR(btf, "no kernel BTF found")) return; - d = btf_dump__new(btf, NULL, &opts, btf_dump_snprintf); + d = btf_dump__new(btf, btf_dump_snprintf, str, NULL); if (!ASSERT_OK_PTR(d, "could not create BTF dump")) return; diff --git a/tools/testing/selftests/bpf/prog_tests/btf_endian.c b/tools/testing/selftests/bpf/prog_tests/btf_endian.c index 8ab5d3e358..8afbf3d0b8 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf_endian.c +++ b/tools/testing/selftests/bpf/prog_tests/btf_endian.c @@ -7,12 +7,12 @@ #include void test_btf_endian() { -#if __BYTE_ORDER == __LITTLE_ENDIAN +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ enum btf_endianness endian = BTF_LITTLE_ENDIAN; -#elif __BYTE_ORDER == __BIG_ENDIAN +#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ enum btf_endianness endian = BTF_BIG_ENDIAN; #else -#error "Unrecognized __BYTE_ORDER" +#error "Unrecognized __BYTE_ORDER__" #endif enum btf_endianness swap_endian = 1 - endian; struct btf *btf = NULL, *swap_btf = NULL; @@ -32,7 +32,7 @@ void test_btf_endian() { ASSERT_EQ(btf__endianness(btf), swap_endian, "endian"); /* Get raw BTF data in non-native endianness... */ - raw_data = btf__get_raw_data(btf, &raw_sz); + raw_data = btf__raw_data(btf, &raw_sz); if (!ASSERT_OK_PTR(raw_data, "raw_data_inverted")) goto err_out; @@ -42,9 +42,9 @@ void test_btf_endian() { goto err_out; ASSERT_EQ(btf__endianness(swap_btf), swap_endian, "endian"); - ASSERT_EQ(btf__get_nr_types(swap_btf), btf__get_nr_types(btf), "nr_types"); + ASSERT_EQ(btf__type_cnt(swap_btf), btf__type_cnt(btf), "nr_types"); - swap_raw_data = btf__get_raw_data(swap_btf, &swap_raw_sz); + swap_raw_data = btf__raw_data(swap_btf, &swap_raw_sz); if (!ASSERT_OK_PTR(swap_raw_data, "swap_raw_data")) goto err_out; @@ -58,7 +58,7 @@ void test_btf_endian() { /* swap it back to native endianness */ btf__set_endianness(swap_btf, endian); - swap_raw_data = btf__get_raw_data(swap_btf, &swap_raw_sz); + swap_raw_data = btf__raw_data(swap_btf, &swap_raw_sz); if (!ASSERT_OK_PTR(swap_raw_data, "swap_raw_data")) goto err_out; @@ -75,7 +75,7 @@ void test_btf_endian() { swap_btf = NULL; btf__set_endianness(btf, swap_endian); - raw_data = btf__get_raw_data(btf, &raw_sz); + raw_data = btf__raw_data(btf, &raw_sz); if (!ASSERT_OK_PTR(raw_data, "raw_data_inverted")) goto err_out; @@ -85,7 +85,7 @@ void test_btf_endian() { goto err_out; ASSERT_EQ(btf__endianness(swap_btf), swap_endian, "endian"); - ASSERT_EQ(btf__get_nr_types(swap_btf), btf__get_nr_types(btf), "nr_types"); + ASSERT_EQ(btf__type_cnt(swap_btf), btf__type_cnt(btf), "nr_types"); /* the type should appear as if it was stored in native endianness */ t = btf__type_by_id(swap_btf, var_id); diff --git a/tools/testing/selftests/bpf/prog_tests/btf_split.c b/tools/testing/selftests/bpf/prog_tests/btf_split.c index ca7c2a9161..eef1158676 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf_split.c +++ b/tools/testing/selftests/bpf/prog_tests/btf_split.c @@ -13,7 +13,6 @@ static void btf_dump_printf(void *ctx, const char *fmt, va_list args) } void test_btf_split() { - struct btf_dump_opts opts; struct btf_dump *d = NULL; const struct btf_type *t; struct btf *btf1, *btf2; @@ -68,11 +67,10 @@ void test_btf_split() { dump_buf_file = open_memstream(&dump_buf, &dump_buf_sz); if (!ASSERT_OK_PTR(dump_buf_file, "dump_memstream")) return; - opts.ctx = dump_buf_file; - d = btf_dump__new(btf2, NULL, &opts, btf_dump_printf); + d = btf_dump__new(btf2, btf_dump_printf, dump_buf_file, NULL); if (!ASSERT_OK_PTR(d, "btf_dump__new")) goto cleanup; - for (i = 1; i <= btf__get_nr_types(btf2); i++) { + for (i = 1; i < btf__type_cnt(btf2); i++) { err = btf_dump__dump_type(d, i); ASSERT_OK(err, "dump_type_ok"); } diff --git a/tools/testing/selftests/bpf/prog_tests/btf_write.c b/tools/testing/selftests/bpf/prog_tests/btf_write.c index 022c7d89d6..addf99c058 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf_write.c +++ b/tools/testing/selftests/bpf/prog_tests/btf_write.c @@ -4,19 +4,15 @@ #include #include "btf_helpers.h" -void test_btf_write() { +static void gen_btf(struct btf *btf) +{ const struct btf_var_secinfo *vi; const struct btf_type *t; const struct btf_member *m; const struct btf_enum *v; const struct btf_param *p; - struct btf *btf; int id, err, str_off; - btf = btf__new_empty(); - if (!ASSERT_OK_PTR(btf, "new_empty")) - return; - str_off = btf__find_str(btf, "int"); ASSERT_EQ(str_off, -ENOENT, "int_str_missing_off"); @@ -281,5 +277,172 @@ void test_btf_write() { "[17] DATASEC 'datasec1' size=12 vlen=1\n" "\ttype_id=1 offset=4 size=8", "raw_dump"); + /* DECL_TAG */ + id = btf__add_decl_tag(btf, "tag1", 16, -1); + ASSERT_EQ(id, 18, "tag_id"); + t = btf__type_by_id(btf, 18); + ASSERT_STREQ(btf__str_by_offset(btf, t->name_off), "tag1", "tag_value"); + ASSERT_EQ(btf_kind(t), BTF_KIND_DECL_TAG, "tag_kind"); + ASSERT_EQ(t->type, 16, "tag_type"); + ASSERT_EQ(btf_decl_tag(t)->component_idx, -1, "tag_component_idx"); + ASSERT_STREQ(btf_type_raw_dump(btf, 18), + "[18] DECL_TAG 'tag1' type_id=16 component_idx=-1", "raw_dump"); + + id = btf__add_decl_tag(btf, "tag2", 14, 1); + ASSERT_EQ(id, 19, "tag_id"); + t = btf__type_by_id(btf, 19); + ASSERT_STREQ(btf__str_by_offset(btf, t->name_off), "tag2", "tag_value"); + ASSERT_EQ(btf_kind(t), BTF_KIND_DECL_TAG, "tag_kind"); + ASSERT_EQ(t->type, 14, "tag_type"); + ASSERT_EQ(btf_decl_tag(t)->component_idx, 1, "tag_component_idx"); + ASSERT_STREQ(btf_type_raw_dump(btf, 19), + "[19] DECL_TAG 'tag2' type_id=14 component_idx=1", "raw_dump"); + + /* TYPE_TAG */ + id = btf__add_type_tag(btf, "tag1", 1); + ASSERT_EQ(id, 20, "tag_id"); + t = btf__type_by_id(btf, 20); + ASSERT_STREQ(btf__str_by_offset(btf, t->name_off), "tag1", "tag_value"); + ASSERT_EQ(btf_kind(t), BTF_KIND_TYPE_TAG, "tag_kind"); + ASSERT_EQ(t->type, 1, "tag_type"); + ASSERT_STREQ(btf_type_raw_dump(btf, 20), + "[20] TYPE_TAG 'tag1' type_id=1", "raw_dump"); +} + +static void test_btf_add() +{ + struct btf *btf; + + btf = btf__new_empty(); + if (!ASSERT_OK_PTR(btf, "new_empty")) + return; + + gen_btf(btf); + + VALIDATE_RAW_BTF( + btf, + "[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED", + "[2] PTR '(anon)' type_id=1", + "[3] CONST '(anon)' type_id=5", + "[4] VOLATILE '(anon)' type_id=3", + "[5] RESTRICT '(anon)' type_id=4", + "[6] ARRAY '(anon)' type_id=2 index_type_id=1 nr_elems=10", + "[7] STRUCT 's1' size=8 vlen=2\n" + "\t'f1' type_id=1 bits_offset=0\n" + "\t'f2' type_id=1 bits_offset=32 bitfield_size=16", + "[8] UNION 'u1' size=8 vlen=1\n" + "\t'f1' type_id=1 bits_offset=0 bitfield_size=16", + "[9] ENUM 'e1' size=4 vlen=2\n" + "\t'v1' val=1\n" + "\t'v2' val=2", + "[10] FWD 'struct_fwd' fwd_kind=struct", + "[11] FWD 'union_fwd' fwd_kind=union", + "[12] ENUM 'enum_fwd' size=4 vlen=0", + "[13] TYPEDEF 'typedef1' type_id=1", + "[14] FUNC 'func1' type_id=15 linkage=global", + "[15] FUNC_PROTO '(anon)' ret_type_id=1 vlen=2\n" + "\t'p1' type_id=1\n" + "\t'p2' type_id=2", + "[16] VAR 'var1' type_id=1, linkage=global-alloc", + "[17] DATASEC 'datasec1' size=12 vlen=1\n" + "\ttype_id=1 offset=4 size=8", + "[18] DECL_TAG 'tag1' type_id=16 component_idx=-1", + "[19] DECL_TAG 'tag2' type_id=14 component_idx=1", + "[20] TYPE_TAG 'tag1' type_id=1"); + btf__free(btf); } + +static void test_btf_add_btf() +{ + struct btf *btf1 = NULL, *btf2 = NULL; + int id; + + btf1 = btf__new_empty(); + if (!ASSERT_OK_PTR(btf1, "btf1")) + return; + + btf2 = btf__new_empty(); + if (!ASSERT_OK_PTR(btf2, "btf2")) + goto cleanup; + + gen_btf(btf1); + gen_btf(btf2); + + id = btf__add_btf(btf1, btf2); + if (!ASSERT_EQ(id, 21, "id")) + goto cleanup; + + VALIDATE_RAW_BTF( + btf1, + "[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED", + "[2] PTR '(anon)' type_id=1", + "[3] CONST '(anon)' type_id=5", + "[4] VOLATILE '(anon)' type_id=3", + "[5] RESTRICT '(anon)' type_id=4", + "[6] ARRAY '(anon)' type_id=2 index_type_id=1 nr_elems=10", + "[7] STRUCT 's1' size=8 vlen=2\n" + "\t'f1' type_id=1 bits_offset=0\n" + "\t'f2' type_id=1 bits_offset=32 bitfield_size=16", + "[8] UNION 'u1' size=8 vlen=1\n" + "\t'f1' type_id=1 bits_offset=0 bitfield_size=16", + "[9] ENUM 'e1' size=4 vlen=2\n" + "\t'v1' val=1\n" + "\t'v2' val=2", + "[10] FWD 'struct_fwd' fwd_kind=struct", + "[11] FWD 'union_fwd' fwd_kind=union", + "[12] ENUM 'enum_fwd' size=4 vlen=0", + "[13] TYPEDEF 'typedef1' type_id=1", + "[14] FUNC 'func1' type_id=15 linkage=global", + "[15] FUNC_PROTO '(anon)' ret_type_id=1 vlen=2\n" + "\t'p1' type_id=1\n" + "\t'p2' type_id=2", + "[16] VAR 'var1' type_id=1, linkage=global-alloc", + "[17] DATASEC 'datasec1' size=12 vlen=1\n" + "\ttype_id=1 offset=4 size=8", + "[18] DECL_TAG 'tag1' type_id=16 component_idx=-1", + "[19] DECL_TAG 'tag2' type_id=14 component_idx=1", + "[20] TYPE_TAG 'tag1' type_id=1", + + /* types appended from the second BTF */ + "[21] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED", + "[22] PTR '(anon)' type_id=21", + "[23] CONST '(anon)' type_id=25", + "[24] VOLATILE '(anon)' type_id=23", + "[25] RESTRICT '(anon)' type_id=24", + "[26] ARRAY '(anon)' type_id=22 index_type_id=21 nr_elems=10", + "[27] STRUCT 's1' size=8 vlen=2\n" + "\t'f1' type_id=21 bits_offset=0\n" + "\t'f2' type_id=21 bits_offset=32 bitfield_size=16", + "[28] UNION 'u1' size=8 vlen=1\n" + "\t'f1' type_id=21 bits_offset=0 bitfield_size=16", + "[29] ENUM 'e1' size=4 vlen=2\n" + "\t'v1' val=1\n" + "\t'v2' val=2", + "[30] FWD 'struct_fwd' fwd_kind=struct", + "[31] FWD 'union_fwd' fwd_kind=union", + "[32] ENUM 'enum_fwd' size=4 vlen=0", + "[33] TYPEDEF 'typedef1' type_id=21", + "[34] FUNC 'func1' type_id=35 linkage=global", + "[35] FUNC_PROTO '(anon)' ret_type_id=21 vlen=2\n" + "\t'p1' type_id=21\n" + "\t'p2' type_id=22", + "[36] VAR 'var1' type_id=21, linkage=global-alloc", + "[37] DATASEC 'datasec1' size=12 vlen=1\n" + "\ttype_id=21 offset=4 size=8", + "[38] DECL_TAG 'tag1' type_id=36 component_idx=-1", + "[39] DECL_TAG 'tag2' type_id=34 component_idx=1", + "[40] TYPE_TAG 'tag1' type_id=21"); + +cleanup: + btf__free(btf1); + btf__free(btf2); +} + +void test_btf_write() +{ + if (test__start_subtest("btf_add")) + test_btf_add(); + if (test__start_subtest("btf_add_btf")) + test_btf_add_btf(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/cg_storage_multi.c b/tools/testing/selftests/bpf/prog_tests/cg_storage_multi.c index 876be0ecb6..621c572221 100644 --- a/tools/testing/selftests/bpf/prog_tests/cg_storage_multi.c +++ b/tools/testing/selftests/bpf/prog_tests/cg_storage_multi.c @@ -363,7 +363,7 @@ static void test_shared(int parent_cgroup_fd, int child_cgroup_fd) cg_storage_multi_shared__destroy(obj); } -void test_cg_storage_multi(void) +void serial_test_cg_storage_multi(void) { int parent_cgroup_fd = -1, child_cgroup_fd = -1; diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_autodetach.c b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_autodetach.c index 70e94e7830..858916d11e 100644 --- a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_autodetach.c +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_autodetach.c @@ -16,12 +16,12 @@ static int prog_load(void) }; size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn); - return bpf_load_program(BPF_PROG_TYPE_CGROUP_SKB, + return bpf_test_load_program(BPF_PROG_TYPE_CGROUP_SKB, prog, insns_cnt, "GPL", 0, bpf_log_buf, BPF_LOG_BUF_SIZE); } -void test_cgroup_attach_autodetach(void) +void serial_test_cgroup_attach_autodetach(void) { __u32 duration = 0, prog_cnt = 4, attach_flags; int allow_prog[2] = {-1}; diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c index 20bb8831dd..d3e8f729c6 100644 --- a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c @@ -15,22 +15,22 @@ static int prog_load_cnt(int verdict, int val) int cgroup_storage_fd, percpu_cgroup_storage_fd; if (map_fd < 0) - map_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, 4, 8, 1, 0); + map_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, 4, 8, 1, NULL); if (map_fd < 0) { printf("failed to create map '%s'\n", strerror(errno)); return -1; } - cgroup_storage_fd = bpf_create_map(BPF_MAP_TYPE_CGROUP_STORAGE, - sizeof(struct bpf_cgroup_storage_key), 8, 0, 0); + cgroup_storage_fd = bpf_map_create(BPF_MAP_TYPE_CGROUP_STORAGE, NULL, + sizeof(struct bpf_cgroup_storage_key), 8, 0, NULL); if (cgroup_storage_fd < 0) { printf("failed to create map '%s'\n", strerror(errno)); return -1; } - percpu_cgroup_storage_fd = bpf_create_map( - BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE, - sizeof(struct bpf_cgroup_storage_key), 8, 0, 0); + percpu_cgroup_storage_fd = bpf_map_create( + BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE, NULL, + sizeof(struct bpf_cgroup_storage_key), 8, 0, NULL); if (percpu_cgroup_storage_fd < 0) { printf("failed to create map '%s'\n", strerror(errno)); return -1; @@ -66,7 +66,7 @@ static int prog_load_cnt(int verdict, int val) size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn); int ret; - ret = bpf_load_program(BPF_PROG_TYPE_CGROUP_SKB, + ret = bpf_test_load_program(BPF_PROG_TYPE_CGROUP_SKB, prog, insns_cnt, "GPL", 0, bpf_log_buf, BPF_LOG_BUF_SIZE); @@ -74,7 +74,7 @@ static int prog_load_cnt(int verdict, int val) return ret; } -void test_cgroup_attach_multi(void) +void serial_test_cgroup_attach_multi(void) { __u32 prog_ids[4], prog_cnt = 0, attach_flags, saved_prog_id; int cg1 = 0, cg2 = 0, cg3 = 0, cg4 = 0, cg5 = 0, key = 0; diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_override.c b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_override.c index 9e96f8d87f..356547e849 100644 --- a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_override.c +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_override.c @@ -18,12 +18,12 @@ static int prog_load(int verdict) }; size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn); - return bpf_load_program(BPF_PROG_TYPE_CGROUP_SKB, + return bpf_test_load_program(BPF_PROG_TYPE_CGROUP_SKB, prog, insns_cnt, "GPL", 0, bpf_log_buf, BPF_LOG_BUF_SIZE); } -void test_cgroup_attach_override(void) +void serial_test_cgroup_attach_override(void) { int drop_prog = -1, allow_prog = -1, foo = -1, bar = -1; __u32 duration = 0; diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_link.c b/tools/testing/selftests/bpf/prog_tests/cgroup_link.c index 9091524131..9e6e6aad34 100644 --- a/tools/testing/selftests/bpf/prog_tests/cgroup_link.c +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_link.c @@ -24,7 +24,7 @@ int ping_and_check(int exp_calls, int exp_alt_calls) return 0; } -void test_cgroup_link(void) +void serial_test_cgroup_link(void) { struct { const char *path; diff --git a/tools/testing/selftests/bpf/prog_tests/check_mtu.c b/tools/testing/selftests/bpf/prog_tests/check_mtu.c index 012068f33a..f73e6e36b7 100644 --- a/tools/testing/selftests/bpf/prog_tests/check_mtu.c +++ b/tools/testing/selftests/bpf/prog_tests/check_mtu.c @@ -195,7 +195,7 @@ static void test_check_mtu_tc(__u32 mtu, __u32 ifindex) test_check_mtu__destroy(skel); } -void test_check_mtu(void) +void serial_test_check_mtu(void) { __u32 mtu_lo; diff --git a/tools/testing/selftests/bpf/prog_tests/connect_force_port.c b/tools/testing/selftests/bpf/prog_tests/connect_force_port.c index 9229db2f5c..9c4325f4ae 100644 --- a/tools/testing/selftests/bpf/prog_tests/connect_force_port.c +++ b/tools/testing/selftests/bpf/prog_tests/connect_force_port.c @@ -51,24 +51,25 @@ static int run_test(int cgroup_fd, int server_fd, int family, int type) bool v4 = family == AF_INET; __u16 expected_local_port = v4 ? 22222 : 22223; __u16 expected_peer_port = 60000; - struct bpf_prog_load_attr attr = { - .file = v4 ? "./connect_force_port4.o" : - "./connect_force_port6.o", - }; struct bpf_program *prog; struct bpf_object *obj; - int xlate_fd, fd, err; + const char *obj_file = v4 ? "connect_force_port4.o" : "connect_force_port6.o"; + int fd, err; __u32 duration = 0; - err = bpf_prog_load_xattr(&attr, &obj, &xlate_fd); - if (err) { - log_err("Failed to load BPF object"); + obj = bpf_object__open_file(obj_file, NULL); + if (!ASSERT_OK_PTR(obj, "bpf_obj_open")) return -1; + + err = bpf_object__load(obj); + if (!ASSERT_OK(err, "bpf_obj_load")) { + err = -EIO; + goto close_bpf_object; } - prog = bpf_object__find_program_by_title(obj, v4 ? - "cgroup/connect4" : - "cgroup/connect6"); + prog = bpf_object__find_program_by_name(obj, v4 ? + "connect4" : + "connect6"); if (CHECK(!prog, "find_prog", "connect prog not found\n")) { err = -EIO; goto close_bpf_object; @@ -82,9 +83,9 @@ static int run_test(int cgroup_fd, int server_fd, int family, int type) goto close_bpf_object; } - prog = bpf_object__find_program_by_title(obj, v4 ? - "cgroup/getpeername4" : - "cgroup/getpeername6"); + prog = bpf_object__find_program_by_name(obj, v4 ? + "getpeername4" : + "getpeername6"); if (CHECK(!prog, "find_prog", "getpeername prog not found\n")) { err = -EIO; goto close_bpf_object; @@ -98,9 +99,9 @@ static int run_test(int cgroup_fd, int server_fd, int family, int type) goto close_bpf_object; } - prog = bpf_object__find_program_by_title(obj, v4 ? - "cgroup/getsockname4" : - "cgroup/getsockname6"); + prog = bpf_object__find_program_by_name(obj, v4 ? + "getsockname4" : + "getsockname6"); if (CHECK(!prog, "find_prog", "getsockname prog not found\n")) { err = -EIO; goto close_bpf_object; diff --git a/tools/testing/selftests/bpf/prog_tests/core_autosize.c b/tools/testing/selftests/bpf/prog_tests/core_autosize.c index 3d4b2a358d..1dfe14ff6a 100644 --- a/tools/testing/selftests/bpf/prog_tests/core_autosize.c +++ b/tools/testing/selftests/bpf/prog_tests/core_autosize.c @@ -112,7 +112,7 @@ void test_core_autosize(void) if (!ASSERT_OK_PTR(f, "btf_fdopen")) goto cleanup; - raw_data = btf__get_raw_data(btf, &raw_sz); + raw_data = btf__raw_data(btf, &raw_sz); if (!ASSERT_OK_PTR(raw_data, "raw_data")) goto cleanup; written = fwrite(raw_data, 1, raw_sz, f); @@ -163,7 +163,7 @@ void test_core_autosize(void) usleep(1); - bss_map = bpf_object__find_map_by_name(skel->obj, "test_cor.bss"); + bss_map = bpf_object__find_map_by_name(skel->obj, ".bss"); if (!ASSERT_OK_PTR(bss_map, "bss_map_find")) goto cleanup; diff --git a/tools/testing/selftests/bpf/prog_tests/core_reloc.c b/tools/testing/selftests/bpf/prog_tests/core_reloc.c index 4739b15b2a..b8bdd1c3ef 100644 --- a/tools/testing/selftests/bpf/prog_tests/core_reloc.c +++ b/tools/testing/selftests/bpf/prog_tests/core_reloc.c @@ -10,7 +10,7 @@ static int duration = 0; #define STRUCT_TO_CHAR_PTR(struct_name) (const char *)&(struct struct_name) -#define MODULES_CASE(name, sec_name, tp_name) { \ +#define MODULES_CASE(name, pg_name, tp_name) { \ .case_name = name, \ .bpf_obj_file = "test_core_reloc_module.o", \ .btf_src_file = NULL, /* find in kernel module BTFs */ \ @@ -28,9 +28,9 @@ static int duration = 0; .comm_len = sizeof("test_progs"), \ }, \ .output_len = sizeof(struct core_reloc_module_output), \ - .prog_sec_name = sec_name, \ + .prog_name = pg_name, \ .raw_tp_name = tp_name, \ - .trigger = trigger_module_test_read, \ + .trigger = __trigger_module_test_read, \ .needs_testmod = true, \ } @@ -43,7 +43,9 @@ static int duration = 0; #define FLAVORS_CASE_COMMON(name) \ .case_name = #name, \ .bpf_obj_file = "test_core_reloc_flavors.o", \ - .btf_src_file = "btf__core_reloc_" #name ".o" \ + .btf_src_file = "btf__core_reloc_" #name ".o", \ + .raw_tp_name = "sys_enter", \ + .prog_name = "test_core_flavors" \ #define FLAVORS_CASE(name) { \ FLAVORS_CASE_COMMON(name), \ @@ -66,7 +68,9 @@ static int duration = 0; #define NESTING_CASE_COMMON(name) \ .case_name = #name, \ .bpf_obj_file = "test_core_reloc_nesting.o", \ - .btf_src_file = "btf__core_reloc_" #name ".o" + .btf_src_file = "btf__core_reloc_" #name ".o", \ + .raw_tp_name = "sys_enter", \ + .prog_name = "test_core_nesting" \ #define NESTING_CASE(name) { \ NESTING_CASE_COMMON(name), \ @@ -91,7 +95,9 @@ static int duration = 0; #define ARRAYS_CASE_COMMON(name) \ .case_name = #name, \ .bpf_obj_file = "test_core_reloc_arrays.o", \ - .btf_src_file = "btf__core_reloc_" #name ".o" + .btf_src_file = "btf__core_reloc_" #name ".o", \ + .raw_tp_name = "sys_enter", \ + .prog_name = "test_core_arrays" \ #define ARRAYS_CASE(name) { \ ARRAYS_CASE_COMMON(name), \ @@ -123,7 +129,9 @@ static int duration = 0; #define PRIMITIVES_CASE_COMMON(name) \ .case_name = #name, \ .bpf_obj_file = "test_core_reloc_primitives.o", \ - .btf_src_file = "btf__core_reloc_" #name ".o" + .btf_src_file = "btf__core_reloc_" #name ".o", \ + .raw_tp_name = "sys_enter", \ + .prog_name = "test_core_primitives" \ #define PRIMITIVES_CASE(name) { \ PRIMITIVES_CASE_COMMON(name), \ @@ -158,6 +166,8 @@ static int duration = 0; .e = 5, .f = 6, .g = 7, .h = 8, \ }, \ .output_len = sizeof(struct core_reloc_mods_output), \ + .raw_tp_name = "sys_enter", \ + .prog_name = "test_core_mods", \ } #define PTR_AS_ARR_CASE(name) { \ @@ -174,6 +184,8 @@ static int duration = 0; .a = 3, \ }, \ .output_len = sizeof(struct core_reloc_ptr_as_arr), \ + .raw_tp_name = "sys_enter", \ + .prog_name = "test_core_ptr_as_arr", \ } #define INTS_DATA(struct_name) STRUCT_TO_CHAR_PTR(struct_name) { \ @@ -190,7 +202,9 @@ static int duration = 0; #define INTS_CASE_COMMON(name) \ .case_name = #name, \ .bpf_obj_file = "test_core_reloc_ints.o", \ - .btf_src_file = "btf__core_reloc_" #name ".o" + .btf_src_file = "btf__core_reloc_" #name ".o", \ + .raw_tp_name = "sys_enter", \ + .prog_name = "test_core_ints" #define INTS_CASE(name) { \ INTS_CASE_COMMON(name), \ @@ -208,7 +222,9 @@ static int duration = 0; #define FIELD_EXISTS_CASE_COMMON(name) \ .case_name = #name, \ .bpf_obj_file = "test_core_reloc_existence.o", \ - .btf_src_file = "btf__core_reloc_" #name ".o" \ + .btf_src_file = "btf__core_reloc_" #name ".o", \ + .raw_tp_name = "sys_enter", \ + .prog_name = "test_core_existence" #define BITFIELDS_CASE_COMMON(objfile, test_name_prefix, name) \ .case_name = test_name_prefix#name, \ @@ -223,6 +239,8 @@ static int duration = 0; .output = STRUCT_TO_CHAR_PTR(core_reloc_bitfields_output) \ __VA_ARGS__, \ .output_len = sizeof(struct core_reloc_bitfields_output), \ + .raw_tp_name = "sys_enter", \ + .prog_name = "test_core_bitfields", \ }, { \ BITFIELDS_CASE_COMMON("test_core_reloc_bitfields_direct.o", \ "direct:", name), \ @@ -231,7 +249,7 @@ static int duration = 0; .output = STRUCT_TO_CHAR_PTR(core_reloc_bitfields_output) \ __VA_ARGS__, \ .output_len = sizeof(struct core_reloc_bitfields_output), \ - .prog_sec_name = "tp_btf/sys_enter", \ + .prog_name = "test_core_bitfields_direct", \ } @@ -239,18 +257,21 @@ static int duration = 0; BITFIELDS_CASE_COMMON("test_core_reloc_bitfields_probed.o", \ "probed:", name), \ .fails = true, \ + .raw_tp_name = "sys_enter", \ + .prog_name = "test_core_bitfields", \ }, { \ BITFIELDS_CASE_COMMON("test_core_reloc_bitfields_direct.o", \ "direct:", name), \ - .prog_sec_name = "tp_btf/sys_enter", \ .fails = true, \ + .prog_name = "test_core_bitfields_direct", \ } #define SIZE_CASE_COMMON(name) \ .case_name = #name, \ .bpf_obj_file = "test_core_reloc_size.o", \ .btf_src_file = "btf__core_reloc_" #name ".o", \ - .relaxed_core_relocs = true + .raw_tp_name = "sys_enter", \ + .prog_name = "test_core_size" #define SIZE_OUTPUT_DATA(type) \ STRUCT_TO_CHAR_PTR(core_reloc_size_output) { \ @@ -278,8 +299,10 @@ static int duration = 0; #define TYPE_BASED_CASE_COMMON(name) \ .case_name = #name, \ - .bpf_obj_file = "test_core_reloc_type_based.o", \ - .btf_src_file = "btf__core_reloc_" #name ".o" \ + .bpf_obj_file = "test_core_reloc_type_based.o", \ + .btf_src_file = "btf__core_reloc_" #name ".o", \ + .raw_tp_name = "sys_enter", \ + .prog_name = "test_core_type_based" #define TYPE_BASED_CASE(name, ...) { \ TYPE_BASED_CASE_COMMON(name), \ @@ -296,7 +319,9 @@ static int duration = 0; #define TYPE_ID_CASE_COMMON(name) \ .case_name = #name, \ .bpf_obj_file = "test_core_reloc_type_id.o", \ - .btf_src_file = "btf__core_reloc_" #name ".o" \ + .btf_src_file = "btf__core_reloc_" #name ".o", \ + .raw_tp_name = "sys_enter", \ + .prog_name = "test_core_type_id" #define TYPE_ID_CASE(name, setup_fn) { \ TYPE_ID_CASE_COMMON(name), \ @@ -313,7 +338,9 @@ static int duration = 0; #define ENUMVAL_CASE_COMMON(name) \ .case_name = #name, \ .bpf_obj_file = "test_core_reloc_enumval.o", \ - .btf_src_file = "btf__core_reloc_" #name ".o" \ + .btf_src_file = "btf__core_reloc_" #name ".o", \ + .raw_tp_name = "sys_enter", \ + .prog_name = "test_core_enumval" #define ENUMVAL_CASE(name, ...) { \ ENUMVAL_CASE_COMMON(name), \ @@ -343,7 +370,7 @@ struct core_reloc_test_case { bool fails; bool needs_testmod; bool relaxed_core_relocs; - const char *prog_sec_name; + const char *prog_name; const char *raw_tp_name; setup_test_fn setup; trigger_test_fn trigger; @@ -382,7 +409,7 @@ static int setup_type_id_case_local(struct core_reloc_test_case *test) exp->local_anon_void_ptr = -1; exp->local_anon_arr = -1; - for (i = 1; i <= btf__get_nr_types(local_btf); i++) + for (i = 1; i < btf__type_cnt(local_btf); i++) { t = btf__type_by_id(local_btf, i); /* we are interested only in anonymous types */ @@ -434,7 +461,7 @@ static int setup_type_id_case_local(struct core_reloc_test_case *test) static int setup_type_id_case_success(struct core_reloc_test_case *test) { struct core_reloc_type_id_output *exp = (void *)test->output; - struct btf *targ_btf = btf__parse(test->btf_src_file, NULL); + struct btf *targ_btf; int err; err = setup_type_id_case_local(test); @@ -475,19 +502,11 @@ static int setup_type_id_case_failure(struct core_reloc_test_case *test) return 0; } -static int trigger_module_test_read(const struct core_reloc_test_case *test) +static int __trigger_module_test_read(const struct core_reloc_test_case *test) { struct core_reloc_module_output *exp = (void *)test->output; - int fd, err; - - fd = open("/sys/kernel/bpf_testmod", O_RDONLY); - err = -errno; - if (CHECK(fd < 0, "testmod_file_open", "failed: %d\n", err)) - return err; - - read(fd, NULL, exp->len); /* request expected number of bytes */ - close(fd); + trigger_module_test_read(exp->len); return 0; } @@ -506,11 +525,13 @@ static struct core_reloc_test_case test_cases[] = { .comm_len = sizeof("test_progs"), }, .output_len = sizeof(struct core_reloc_kernel_output), + .raw_tp_name = "sys_enter", + .prog_name = "test_core_kernel", }, /* validate we can find kernel module BTF types for relocs/attach */ - MODULES_CASE("module_probed", "raw_tp/bpf_testmod_test_read", "bpf_testmod_test_read"), - MODULES_CASE("module_direct", "tp_btf/bpf_testmod_test_read", NULL), + MODULES_CASE("module_probed", "test_core_module_probed", "bpf_testmod_test_read"), + MODULES_CASE("module_direct", "test_core_module_direct", NULL), /* validate BPF program can use multiple flavors to match against * single target BTF type @@ -589,6 +610,8 @@ static struct core_reloc_test_case test_cases[] = { .c = 0, /* BUG in clang, should be 3 */ }, .output_len = sizeof(struct core_reloc_misc_output), + .raw_tp_name = "sys_enter", + .prog_name = "test_core_misc", }, /* validate field existence checks */ @@ -857,14 +880,9 @@ void test_core_reloc(void) if (!ASSERT_OK_PTR(obj, "obj_open")) goto cleanup; - probe_name = "raw_tracepoint/sys_enter"; - tp_name = "sys_enter"; - if (test_case->prog_sec_name) { - probe_name = test_case->prog_sec_name; - tp_name = test_case->raw_tp_name; /* NULL for tp_btf */ - } - - prog = bpf_object__find_program_by_title(obj, probe_name); + probe_name = test_case->prog_name; + tp_name = test_case->raw_tp_name; /* NULL for tp_btf */ + prog = bpf_object__find_program_by_name(obj, probe_name); if (CHECK(!prog, "find_probe", "prog '%s' not found\n", probe_name)) goto cleanup; @@ -876,7 +894,7 @@ void test_core_reloc(void) goto cleanup; } - data_map = bpf_object__find_map_by_name(obj, "test_cor.bss"); + data_map = bpf_object__find_map_by_name(obj, ".bss"); if (CHECK(!data_map, "find_data_map", "data map not found\n")) goto cleanup; @@ -890,7 +908,8 @@ void test_core_reloc(void) data = mmap_data; memset(mmap_data, 0, sizeof(*data)); - memcpy(data->in, test_case->input, test_case->input_len); + if (test_case->input_len) + memcpy(data->in, test_case->input, test_case->input_len); data->my_pid_tgid = my_pid_tgid; link = bpf_program__attach_raw_tracepoint(prog, tp_name); diff --git a/tools/testing/selftests/bpf/prog_tests/d_path.c b/tools/testing/selftests/bpf/prog_tests/d_path.c index 0a577a248d..911345c526 100644 --- a/tools/testing/selftests/bpf/prog_tests/d_path.c +++ b/tools/testing/selftests/bpf/prog_tests/d_path.c @@ -9,6 +9,8 @@ #define MAX_FILES 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; @@ -99,7 +101,7 @@ static int trigger_fstat_events(pid_t pid) return ret; } -void test_d_path(void) +static void test_d_path_basic(void) { struct test_d_path__bss *bss; struct test_d_path *skel; @@ -155,3 +157,35 @@ void test_d_path(void) cleanup: test_d_path__destroy(skel); } + +static void test_d_path_check_rdonly_mem(void) +{ + struct test_d_path_check_rdonly_mem *skel; + + skel = test_d_path_check_rdonly_mem__open_and_load(); + ASSERT_ERR_PTR(skel, "unexpected_load_overwriting_rdonly_mem"); + + 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")) + test_d_path_basic(); + + 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/fentry_fexit.c b/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c index 91154c2ba2..4374ac8a8a 100644 --- a/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c +++ b/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c @@ -6,23 +6,23 @@ void test_fentry_fexit(void) { - struct fentry_test *fentry_skel = NULL; - struct fexit_test *fexit_skel = NULL; + struct fentry_test_lskel *fentry_skel = NULL; + struct fexit_test_lskel *fexit_skel = NULL; __u64 *fentry_res, *fexit_res; __u32 duration = 0, retval; int err, prog_fd, i; - fentry_skel = fentry_test__open_and_load(); + fentry_skel = fentry_test_lskel__open_and_load(); if (CHECK(!fentry_skel, "fentry_skel_load", "fentry skeleton failed\n")) goto close_prog; - fexit_skel = fexit_test__open_and_load(); + fexit_skel = fexit_test_lskel__open_and_load(); if (CHECK(!fexit_skel, "fexit_skel_load", "fexit skeleton failed\n")) goto close_prog; - err = fentry_test__attach(fentry_skel); + err = fentry_test_lskel__attach(fentry_skel); if (CHECK(err, "fentry_attach", "fentry attach failed: %d\n", err)) goto close_prog; - err = fexit_test__attach(fexit_skel); + err = fexit_test_lskel__attach(fexit_skel); if (CHECK(err, "fexit_attach", "fexit attach failed: %d\n", err)) goto close_prog; @@ -44,6 +44,6 @@ void test_fentry_fexit(void) } close_prog: - fentry_test__destroy(fentry_skel); - fexit_test__destroy(fexit_skel); + fentry_test_lskel__destroy(fentry_skel); + fexit_test_lskel__destroy(fexit_skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/fentry_test.c b/tools/testing/selftests/bpf/prog_tests/fentry_test.c index 174c89e745..12921b3850 100644 --- a/tools/testing/selftests/bpf/prog_tests/fentry_test.c +++ b/tools/testing/selftests/bpf/prog_tests/fentry_test.c @@ -3,19 +3,19 @@ #include #include "fentry_test.lskel.h" -static int fentry_test(struct fentry_test *fentry_skel) +static int fentry_test(struct fentry_test_lskel *fentry_skel) { int err, prog_fd, i; __u32 duration = 0, retval; int link_fd; __u64 *result; - err = fentry_test__attach(fentry_skel); + err = fentry_test_lskel__attach(fentry_skel); if (!ASSERT_OK(err, "fentry_attach")) return err; /* Check that already linked program can't be attached again. */ - link_fd = fentry_test__test1__attach(fentry_skel); + link_fd = fentry_test_lskel__test1__attach(fentry_skel); if (!ASSERT_LT(link_fd, 0, "fentry_attach_link")) return -1; @@ -31,7 +31,7 @@ static int fentry_test(struct fentry_test *fentry_skel) return -1; } - fentry_test__detach(fentry_skel); + fentry_test_lskel__detach(fentry_skel); /* zero results for re-attach test */ memset(fentry_skel->bss, 0, sizeof(*fentry_skel->bss)); @@ -40,10 +40,10 @@ static int fentry_test(struct fentry_test *fentry_skel) void test_fentry_test(void) { - struct fentry_test *fentry_skel = NULL; + struct fentry_test_lskel *fentry_skel = NULL; int err; - fentry_skel = fentry_test__open_and_load(); + fentry_skel = fentry_test_lskel__open_and_load(); if (!ASSERT_OK_PTR(fentry_skel, "fentry_skel_load")) goto cleanup; @@ -55,5 +55,5 @@ void test_fentry_test(void) ASSERT_OK(err, "fentry_second_attach"); cleanup: - fentry_test__destroy(fentry_skel); + fentry_test_lskel__destroy(fentry_skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c index 73b4c76e6b..c52f99f6a9 100644 --- a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c +++ b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c @@ -60,18 +60,15 @@ static void test_fexit_bpf2bpf_common(const char *obj_file, struct bpf_object *obj = NULL, *tgt_obj; __u32 retval, tgt_prog_id, info_len; struct bpf_prog_info prog_info = {}; - struct bpf_program **prog = NULL; + struct bpf_program **prog = NULL, *p; struct bpf_link **link = NULL; int err, tgt_fd, i; struct btf *btf; - err = bpf_prog_load(target_obj_file, BPF_PROG_TYPE_UNSPEC, + err = bpf_prog_test_load(target_obj_file, BPF_PROG_TYPE_UNSPEC, &tgt_obj, &tgt_fd); if (!ASSERT_OK(err, "tgt_prog_load")) return; - DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts, - .attach_prog_fd = tgt_fd, - ); info_len = sizeof(prog_info); err = bpf_obj_get_info_by_fd(tgt_fd, &prog_info, &info_len); @@ -89,16 +86,23 @@ static void test_fexit_bpf2bpf_common(const char *obj_file, if (!ASSERT_OK_PTR(prog, "prog_ptr")) goto close_prog; - obj = bpf_object__open_file(obj_file, &opts); + obj = bpf_object__open_file(obj_file, NULL); if (!ASSERT_OK_PTR(obj, "obj_open")) goto close_prog; + bpf_object__for_each_program(p, obj) { + err = bpf_program__set_attach_target(p, tgt_fd, NULL); + ASSERT_OK(err, "set_attach_target"); + } + err = bpf_object__load(obj); if (!ASSERT_OK(err, "obj_load")) goto close_prog; for (i = 0; i < prog_cnt; i++) { struct bpf_link_info link_info; + struct bpf_program *pos; + const char *pos_sec_name; char *tgt_name; __s32 btf_id; @@ -107,7 +111,14 @@ static void test_fexit_bpf2bpf_common(const char *obj_file, goto close_prog; btf_id = btf__find_by_name_kind(btf, tgt_name + 1, BTF_KIND_FUNC); - prog[i] = bpf_object__find_program_by_title(obj, prog_name[i]); + prog[i] = NULL; + bpf_object__for_each_program(pos, obj) { + pos_sec_name = bpf_program__section_name(pos); + if (pos_sec_name && !strcmp(pos_sec_name, prog_name[i])) { + prog[i] = pos; + break; + } + } if (!ASSERT_OK_PTR(prog[i], prog_name[i])) goto close_prog; @@ -209,8 +220,8 @@ static void test_func_replace_verify(void) static int test_second_attach(struct bpf_object *obj) { - const char *prog_name = "freplace/get_constant"; - const char *tgt_name = prog_name + 9; /* cut off freplace/ */ + const char *prog_name = "security_new_get_constant"; + const char *tgt_name = "get_constant"; const char *tgt_obj_file = "./test_pkt_access.o"; struct bpf_program *prog = NULL; struct bpf_object *tgt_obj; @@ -218,11 +229,11 @@ static int test_second_attach(struct bpf_object *obj) struct bpf_link *link; int err = 0, tgt_fd; - prog = bpf_object__find_program_by_title(obj, prog_name); + prog = bpf_object__find_program_by_name(obj, prog_name); if (CHECK(!prog, "find_prog", "prog %s not found\n", prog_name)) return -ENOENT; - err = bpf_prog_load(tgt_obj_file, BPF_PROG_TYPE_UNSPEC, + err = bpf_prog_test_load(tgt_obj_file, BPF_PROG_TYPE_UNSPEC, &tgt_obj, &tgt_fd); if (CHECK(err, "second_prog_load", "file %s err %d errno %d\n", tgt_obj_file, err, errno)) @@ -270,34 +281,40 @@ static void test_fmod_ret_freplace(void) struct bpf_link *freplace_link = NULL; struct bpf_program *prog; __u32 duration = 0; - int err, pkt_fd; + int err, pkt_fd, attach_prog_fd; - err = bpf_prog_load(tgt_name, BPF_PROG_TYPE_UNSPEC, + err = bpf_prog_test_load(tgt_name, BPF_PROG_TYPE_UNSPEC, &pkt_obj, &pkt_fd); /* the target prog should load fine */ if (CHECK(err, "tgt_prog_load", "file %s err %d errno %d\n", tgt_name, err, errno)) return; - opts.attach_prog_fd = pkt_fd; - freplace_obj = bpf_object__open_file(freplace_name, &opts); + freplace_obj = bpf_object__open_file(freplace_name, NULL); if (!ASSERT_OK_PTR(freplace_obj, "freplace_obj_open")) goto out; + prog = bpf_object__next_program(freplace_obj, NULL); + err = bpf_program__set_attach_target(prog, pkt_fd, NULL); + ASSERT_OK(err, "freplace__set_attach_target"); + err = bpf_object__load(freplace_obj); if (CHECK(err, "freplace_obj_load", "err %d\n", err)) goto out; - prog = bpf_program__next(NULL, freplace_obj); freplace_link = bpf_program__attach_trace(prog); if (!ASSERT_OK_PTR(freplace_link, "freplace_attach_trace")) goto out; - opts.attach_prog_fd = bpf_program__fd(prog); - fmod_obj = bpf_object__open_file(fmod_ret_name, &opts); + fmod_obj = bpf_object__open_file(fmod_ret_name, NULL); if (!ASSERT_OK_PTR(fmod_obj, "fmod_obj_open")) goto out; + attach_prog_fd = bpf_program__fd(prog); + prog = bpf_object__next_program(fmod_obj, NULL); + err = bpf_program__set_attach_target(prog, attach_prog_fd, NULL); + ASSERT_OK(err, "fmod_ret_set_attach_target"); + err = bpf_object__load(fmod_obj); if (CHECK(!err, "fmod_obj_load", "loading fmod_ret should fail\n")) goto out; @@ -322,31 +339,32 @@ static void test_func_sockmap_update(void) } static void test_obj_load_failure_common(const char *obj_file, - const char *target_obj_file) - + const char *target_obj_file) { /* * standalone test that asserts failure to load freplace prog * because of invalid return code. */ struct bpf_object *obj = NULL, *pkt_obj; + struct bpf_program *prog; int err, pkt_fd; __u32 duration = 0; - err = bpf_prog_load(target_obj_file, BPF_PROG_TYPE_UNSPEC, + err = bpf_prog_test_load(target_obj_file, BPF_PROG_TYPE_UNSPEC, &pkt_obj, &pkt_fd); /* the target prog should load fine */ if (CHECK(err, "tgt_prog_load", "file %s err %d errno %d\n", target_obj_file, err, errno)) return; - DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts, - .attach_prog_fd = pkt_fd, - ); - obj = bpf_object__open_file(obj_file, &opts); + obj = bpf_object__open_file(obj_file, NULL); if (!ASSERT_OK_PTR(obj, "obj_open")) goto close_prog; + prog = bpf_object__next_program(obj, NULL); + err = bpf_program__set_attach_target(prog, pkt_fd, NULL); + ASSERT_OK(err, "set_attach_target"); + /* It should fail to load the program */ err = bpf_object__load(obj); if (CHECK(!err, "bpf_obj_load should fail", "err %d\n", err)) @@ -371,7 +389,8 @@ static void test_func_map_prog_compatibility(void) "./test_attach_probe.o"); } -void test_fexit_bpf2bpf(void) +/* NOTE: affect other tests, must run in serial mode */ +void serial_test_fexit_bpf2bpf(void) { if (test__start_subtest("target_no_callees")) test_target_no_callees(); diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_sleep.c b/tools/testing/selftests/bpf/prog_tests/fexit_sleep.c index 4e7f4b42ea..f949647dbb 100644 --- a/tools/testing/selftests/bpf/prog_tests/fexit_sleep.c +++ b/tools/testing/selftests/bpf/prog_tests/fexit_sleep.c @@ -10,7 +10,7 @@ static int do_sleep(void *skel) { - struct fexit_sleep *fexit_skel = skel; + struct fexit_sleep_lskel *fexit_skel = skel; struct timespec ts1 = { .tv_nsec = 1 }; struct timespec ts2 = { .tv_sec = 10 }; @@ -25,16 +25,16 @@ static char child_stack[STACK_SIZE]; void test_fexit_sleep(void) { - struct fexit_sleep *fexit_skel = NULL; + struct fexit_sleep_lskel *fexit_skel = NULL; int wstatus, duration = 0; pid_t cpid; int err, fexit_cnt; - fexit_skel = fexit_sleep__open_and_load(); + fexit_skel = fexit_sleep_lskel__open_and_load(); if (CHECK(!fexit_skel, "fexit_skel_load", "fexit skeleton failed\n")) goto cleanup; - err = fexit_sleep__attach(fexit_skel); + err = fexit_sleep_lskel__attach(fexit_skel); if (CHECK(err, "fexit_attach", "fexit attach failed: %d\n", err)) goto cleanup; @@ -60,7 +60,7 @@ void test_fexit_sleep(void) */ close(fexit_skel->progs.nanosleep_fentry.prog_fd); close(fexit_skel->progs.nanosleep_fexit.prog_fd); - fexit_sleep__detach(fexit_skel); + fexit_sleep_lskel__detach(fexit_skel); /* kill the thread to unwind sys_nanosleep stack through the trampoline */ kill(cpid, 9); @@ -78,5 +78,5 @@ void test_fexit_sleep(void) goto cleanup; cleanup: - fexit_sleep__destroy(fexit_skel); + fexit_sleep_lskel__destroy(fexit_skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_stress.c b/tools/testing/selftests/bpf/prog_tests/fexit_stress.c index 7c9b62e971..e4cede6b4b 100644 --- a/tools/testing/selftests/bpf/prog_tests/fexit_stress.c +++ b/tools/testing/selftests/bpf/prog_tests/fexit_stress.c @@ -20,34 +20,33 @@ void test_fexit_stress(void) BPF_EXIT_INSN(), }; - struct bpf_load_program_attr load_attr = { - .prog_type = BPF_PROG_TYPE_TRACING, - .license = "GPL", - .insns = trace_program, - .insns_cnt = sizeof(trace_program) / sizeof(struct bpf_insn), + LIBBPF_OPTS(bpf_prog_load_opts, trace_opts, .expected_attach_type = BPF_TRACE_FEXIT, - }; + .log_buf = error, + .log_size = sizeof(error), + ); const struct bpf_insn skb_program[] = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }; - struct bpf_load_program_attr skb_load_attr = { - .prog_type = BPF_PROG_TYPE_SOCKET_FILTER, - .license = "GPL", - .insns = skb_program, - .insns_cnt = sizeof(skb_program) / sizeof(struct bpf_insn), - }; + LIBBPF_OPTS(bpf_prog_load_opts, skb_opts, + .log_buf = error, + .log_size = sizeof(error), + ); err = libbpf_find_vmlinux_btf_id("bpf_fentry_test1", - load_attr.expected_attach_type); + trace_opts.expected_attach_type); if (CHECK(err <= 0, "find_vmlinux_btf_id", "failed: %d\n", err)) goto out; - load_attr.attach_btf_id = err; + trace_opts.attach_btf_id = err; for (i = 0; i < CNT; i++) { - fexit_fd[i] = bpf_load_program_xattr(&load_attr, error, sizeof(error)); + fexit_fd[i] = bpf_prog_load(BPF_PROG_TYPE_TRACING, NULL, "GPL", + trace_program, + sizeof(trace_program) / sizeof(struct bpf_insn), + &trace_opts); if (CHECK(fexit_fd[i] < 0, "fexit loaded", "failed: %d errno %d\n", fexit_fd[i], errno)) goto out; @@ -57,7 +56,9 @@ void test_fexit_stress(void) goto out; } - filter_fd = bpf_load_program_xattr(&skb_load_attr, error, sizeof(error)); + filter_fd = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", + skb_program, sizeof(skb_program) / sizeof(struct bpf_insn), + &skb_opts); if (CHECK(filter_fd < 0, "test_program_loaded", "failed: %d errno %d\n", filter_fd, errno)) goto out; diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_test.c b/tools/testing/selftests/bpf/prog_tests/fexit_test.c index af3dba7267..d4887d8bb3 100644 --- a/tools/testing/selftests/bpf/prog_tests/fexit_test.c +++ b/tools/testing/selftests/bpf/prog_tests/fexit_test.c @@ -3,19 +3,19 @@ #include #include "fexit_test.lskel.h" -static int fexit_test(struct fexit_test *fexit_skel) +static int fexit_test(struct fexit_test_lskel *fexit_skel) { int err, prog_fd, i; __u32 duration = 0, retval; int link_fd; __u64 *result; - err = fexit_test__attach(fexit_skel); + err = fexit_test_lskel__attach(fexit_skel); if (!ASSERT_OK(err, "fexit_attach")) return err; /* Check that already linked program can't be attached again. */ - link_fd = fexit_test__test1__attach(fexit_skel); + link_fd = fexit_test_lskel__test1__attach(fexit_skel); if (!ASSERT_LT(link_fd, 0, "fexit_attach_link")) return -1; @@ -31,7 +31,7 @@ static int fexit_test(struct fexit_test *fexit_skel) return -1; } - fexit_test__detach(fexit_skel); + fexit_test_lskel__detach(fexit_skel); /* zero results for re-attach test */ memset(fexit_skel->bss, 0, sizeof(*fexit_skel->bss)); @@ -40,10 +40,10 @@ static int fexit_test(struct fexit_test *fexit_skel) void test_fexit_test(void) { - struct fexit_test *fexit_skel = NULL; + struct fexit_test_lskel *fexit_skel = NULL; int err; - fexit_skel = fexit_test__open_and_load(); + fexit_skel = fexit_test_lskel__open_and_load(); if (!ASSERT_OK_PTR(fexit_skel, "fexit_skel_load")) goto cleanup; @@ -55,5 +55,5 @@ void test_fexit_test(void) ASSERT_OK(err, "fexit_second_attach"); cleanup: - fexit_test__destroy(fexit_skel); + fexit_test_lskel__destroy(fexit_skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c index 225714f71a..ac54e3f91d 100644 --- a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c +++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c @@ -458,9 +458,9 @@ static int init_prog_array(struct bpf_object *obj, struct bpf_map *prog_array) return -1; for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { - snprintf(prog_name, sizeof(prog_name), "flow_dissector/%i", i); + snprintf(prog_name, sizeof(prog_name), "flow_dissector_%d", i); - prog = bpf_object__find_program_by_title(obj, prog_name); + prog = bpf_object__find_program_by_name(obj, prog_name); if (!prog) return -1; diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector_load_bytes.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector_load_bytes.c index 0e8a4d2f02..93ac3f2822 100644 --- a/tools/testing/selftests/bpf/prog_tests/flow_dissector_load_bytes.c +++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector_load_bytes.c @@ -2,7 +2,7 @@ #include #include -void test_flow_dissector_load_bytes(void) +void serial_test_flow_dissector_load_bytes(void) { struct bpf_flow_keys flow_keys; __u32 duration = 0, retval, size; @@ -30,7 +30,7 @@ void test_flow_dissector_load_bytes(void) /* make sure bpf_skb_load_bytes is not allowed from skb-less context */ - fd = bpf_load_program(BPF_PROG_TYPE_FLOW_DISSECTOR, prog, + fd = bpf_test_load_program(BPF_PROG_TYPE_FLOW_DISSECTOR, prog, ARRAY_SIZE(prog), "GPL", 0, NULL, 0); CHECK(fd < 0, "flow_dissector-bpf_skb_load_bytes-load", diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c index 3931ede5c5..7c79462d27 100644 --- a/tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c +++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c @@ -47,9 +47,9 @@ static int load_prog(enum bpf_prog_type type) }; int fd; - fd = bpf_load_program(type, prog, ARRAY_SIZE(prog), "GPL", 0, NULL, 0); + fd = bpf_test_load_program(type, prog, ARRAY_SIZE(prog), "GPL", 0, NULL, 0); if (CHECK_FAIL(fd < 0)) - perror("bpf_load_program"); + perror("bpf_test_load_program"); return fd; } @@ -628,7 +628,7 @@ static void run_tests(int netns) } } -void test_flow_dissector_reattach(void) +void serial_test_flow_dissector_reattach(void) { int err, new_net, saved_net; diff --git a/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c b/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c index 522237aa44..e834a01de1 100644 --- a/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c +++ b/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c @@ -24,13 +24,19 @@ static void get_stack_print_output(void *ctx, int cpu, void *data, __u32 size) { bool good_kern_stack = false, good_user_stack = false; const char *nonjit_func = "___bpf_prog_run"; - struct get_stack_trace_t *e = data; + /* perfbuf-submitted data is 4-byte aligned, but we need 8-byte + * alignment, so copy data into a local variable, for simplicity + */ + struct get_stack_trace_t e; int i, num_stack; static __u64 cnt; struct ksym *ks; cnt++; + memset(&e, 0, sizeof(e)); + memcpy(&e, data, size <= sizeof(e) ? size : sizeof(e)); + if (size < sizeof(struct get_stack_trace_t)) { __u64 *raw_data = data; bool found = false; @@ -57,19 +63,19 @@ static void get_stack_print_output(void *ctx, int cpu, void *data, __u32 size) good_user_stack = true; } } else { - num_stack = e->kern_stack_size / sizeof(__u64); + num_stack = e.kern_stack_size / sizeof(__u64); if (env.jit_enabled) { good_kern_stack = num_stack > 0; } else { for (i = 0; i < num_stack; i++) { - ks = ksym_search(e->kern_stack[i]); + ks = ksym_search(e.kern_stack[i]); if (ks && (strcmp(ks->name, nonjit_func) == 0)) { good_kern_stack = true; break; } } } - if (e->user_stack_size > 0 && e->user_stack_buildid_size > 0) + if (e.user_stack_size > 0 && e.user_stack_buildid_size > 0) good_user_stack = true; } @@ -83,9 +89,8 @@ void test_get_stack_raw_tp(void) { const char *file = "./test_get_stack_rawtp.o"; const char *file_err = "./test_get_stack_rawtp_err.o"; - const char *prog_name = "raw_tracepoint/sys_enter"; + const char *prog_name = "bpf_prog1"; int i, err, prog_fd, exp_cnt = MAX_CNT_RAWTP; - struct perf_buffer_opts pb_opts = {}; struct perf_buffer *pb = NULL; struct bpf_link *link = NULL; struct timespec tv = {0, 10}; @@ -94,15 +99,15 @@ void test_get_stack_raw_tp(void) struct bpf_map *map; cpu_set_t cpu_set; - err = bpf_prog_load(file_err, BPF_PROG_TYPE_RAW_TRACEPOINT, &obj, &prog_fd); + err = bpf_prog_test_load(file_err, BPF_PROG_TYPE_RAW_TRACEPOINT, &obj, &prog_fd); if (CHECK(err >= 0, "prog_load raw tp", "err %d errno %d\n", err, errno)) return; - err = bpf_prog_load(file, BPF_PROG_TYPE_RAW_TRACEPOINT, &obj, &prog_fd); + err = bpf_prog_test_load(file, BPF_PROG_TYPE_RAW_TRACEPOINT, &obj, &prog_fd); if (CHECK(err, "prog_load raw tp", "err %d errno %d\n", err, errno)) return; - prog = bpf_object__find_program_by_title(obj, prog_name); + prog = bpf_object__find_program_by_name(obj, prog_name); if (CHECK(!prog, "find_probe", "prog '%s' not found\n", prog_name)) goto close_prog; @@ -124,8 +129,8 @@ void test_get_stack_raw_tp(void) if (!ASSERT_OK_PTR(link, "attach_raw_tp")) goto close_prog; - pb_opts.sample_cb = get_stack_print_output; - pb = perf_buffer__new(bpf_map__fd(map), 8, &pb_opts); + pb = perf_buffer__new(bpf_map__fd(map), 8, get_stack_print_output, + NULL, NULL, NULL); if (!ASSERT_OK_PTR(pb, "perf_buf__new")) goto close_prog; diff --git a/tools/testing/selftests/bpf/prog_tests/global_data.c b/tools/testing/selftests/bpf/prog_tests/global_data.c index 9efa7e50ea..9da131b32e 100644 --- a/tools/testing/selftests/bpf/prog_tests/global_data.c +++ b/tools/testing/selftests/bpf/prog_tests/global_data.c @@ -103,11 +103,18 @@ static void test_global_data_struct(struct bpf_object *obj, __u32 duration) static void test_global_data_rdonly(struct bpf_object *obj, __u32 duration) { int err = -ENOMEM, map_fd, zero = 0; - struct bpf_map *map; + struct bpf_map *map, *map2; __u8 *buff; map = bpf_object__find_map_by_name(obj, "test_glo.rodata"); - if (CHECK_FAIL(!map || !bpf_map__is_internal(map))) + if (!ASSERT_OK_PTR(map, "map")) + return; + if (!ASSERT_TRUE(bpf_map__is_internal(map), "is_internal")) + return; + + /* ensure we can lookup internal maps by their ELF names */ + map2 = bpf_object__find_map_by_name(obj, ".rodata"); + if (!ASSERT_EQ(map, map2, "same_maps")) return; map_fd = bpf_map__fd(map); @@ -129,7 +136,7 @@ void test_global_data(void) struct bpf_object *obj; int err, prog_fd; - err = bpf_prog_load(file, BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); + err = bpf_prog_test_load(file, BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); if (CHECK(err, "load program", "error %d loading %s\n", err, file)) return; diff --git a/tools/testing/selftests/bpf/prog_tests/global_data_init.c b/tools/testing/selftests/bpf/prog_tests/global_data_init.c index ee46b11f1f..1db86eab10 100644 --- a/tools/testing/selftests/bpf/prog_tests/global_data_init.c +++ b/tools/testing/selftests/bpf/prog_tests/global_data_init.c @@ -16,7 +16,7 @@ void test_global_data_init(void) if (CHECK_FAIL(err)) return; - map = bpf_object__find_map_by_name(obj, "test_glo.rodata"); + map = bpf_object__find_map_by_name(obj, ".rodata"); if (CHECK_FAIL(!map || !bpf_map__is_internal(map))) goto out; diff --git a/tools/testing/selftests/bpf/prog_tests/global_func_args.c b/tools/testing/selftests/bpf/prog_tests/global_func_args.c index 8bcc286910..93a2439237 100644 --- a/tools/testing/selftests/bpf/prog_tests/global_func_args.c +++ b/tools/testing/selftests/bpf/prog_tests/global_func_args.c @@ -44,7 +44,7 @@ void test_global_func_args(void) struct bpf_object *obj; int err, prog_fd; - err = bpf_prog_load(file, BPF_PROG_TYPE_CGROUP_SKB, &obj, &prog_fd); + err = bpf_prog_test_load(file, BPF_PROG_TYPE_CGROUP_SKB, &obj, &prog_fd); if (CHECK(err, "load program", "error %d loading %s\n", err, file)) return; diff --git a/tools/testing/selftests/bpf/prog_tests/kfree_skb.c b/tools/testing/selftests/bpf/prog_tests/kfree_skb.c index ddfb6bf971..ce10d2fc3a 100644 --- a/tools/testing/selftests/bpf/prog_tests/kfree_skb.c +++ b/tools/testing/selftests/bpf/prog_tests/kfree_skb.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include #include +#include "kfree_skb.skel.h" struct meta { int ifindex; @@ -48,7 +49,8 @@ static void on_sample(void *ctx, int cpu, void *data, __u32 size) *(bool *)ctx = true; } -void test_kfree_skb(void) +/* TODO: fix kernel panic caused by this test in parallel mode */ +void serial_test_kfree_skb(void) { struct __sk_buff skb = {}; struct bpf_prog_test_run_attr tattr = { @@ -57,63 +59,43 @@ void test_kfree_skb(void) .ctx_in = &skb, .ctx_size_in = sizeof(skb), }; - struct bpf_prog_load_attr attr = { - .file = "./kfree_skb.o", - }; - - struct bpf_link *link = NULL, *link_fentry = NULL, *link_fexit = NULL; - struct bpf_map *perf_buf_map, *global_data; - struct bpf_program *prog, *fentry, *fexit; - struct bpf_object *obj, *obj2 = NULL; - struct perf_buffer_opts pb_opts = {}; + struct kfree_skb *skel = NULL; + struct bpf_link *link; + struct bpf_object *obj; struct perf_buffer *pb = NULL; - int err, kfree_skb_fd; + int err; bool passed = false; __u32 duration = 0; const int zero = 0; bool test_ok[2]; - err = bpf_prog_load("./test_pkt_access.o", BPF_PROG_TYPE_SCHED_CLS, + err = bpf_prog_test_load("./test_pkt_access.o", BPF_PROG_TYPE_SCHED_CLS, &obj, &tattr.prog_fd); if (CHECK(err, "prog_load sched cls", "err %d errno %d\n", err, errno)) return; - err = bpf_prog_load_xattr(&attr, &obj2, &kfree_skb_fd); - if (CHECK(err, "prog_load raw tp", "err %d errno %d\n", err, errno)) + skel = kfree_skb__open_and_load(); + if (!ASSERT_OK_PTR(skel, "kfree_skb_skel")) goto close_prog; - prog = bpf_object__find_program_by_title(obj2, "tp_btf/kfree_skb"); - if (CHECK(!prog, "find_prog", "prog kfree_skb not found\n")) - goto close_prog; - fentry = bpf_object__find_program_by_title(obj2, "fentry/eth_type_trans"); - if (CHECK(!fentry, "find_prog", "prog eth_type_trans not found\n")) - goto close_prog; - fexit = bpf_object__find_program_by_title(obj2, "fexit/eth_type_trans"); - if (CHECK(!fexit, "find_prog", "prog eth_type_trans not found\n")) - goto close_prog; - - global_data = bpf_object__find_map_by_name(obj2, "kfree_sk.bss"); - if (CHECK(!global_data, "find global data", "not found\n")) - goto close_prog; - - link = bpf_program__attach_raw_tracepoint(prog, NULL); + link = bpf_program__attach_raw_tracepoint(skel->progs.trace_kfree_skb, NULL); if (!ASSERT_OK_PTR(link, "attach_raw_tp")) goto close_prog; - link_fentry = bpf_program__attach_trace(fentry); - if (!ASSERT_OK_PTR(link_fentry, "attach fentry")) - goto close_prog; - link_fexit = bpf_program__attach_trace(fexit); - if (!ASSERT_OK_PTR(link_fexit, "attach fexit")) - goto close_prog; + skel->links.trace_kfree_skb = link; - perf_buf_map = bpf_object__find_map_by_name(obj2, "perf_buf_map"); - if (CHECK(!perf_buf_map, "find_perf_buf_map", "not found\n")) + link = bpf_program__attach_trace(skel->progs.fentry_eth_type_trans); + if (!ASSERT_OK_PTR(link, "attach fentry")) goto close_prog; + skel->links.fentry_eth_type_trans = link; + + link = bpf_program__attach_trace(skel->progs.fexit_eth_type_trans); + if (!ASSERT_OK_PTR(link, "attach fexit")) + goto close_prog; + skel->links.fexit_eth_type_trans = link; /* set up perf buffer */ - pb_opts.sample_cb = on_sample; - pb_opts.ctx = &passed; - pb = perf_buffer__new(bpf_map__fd(perf_buf_map), 1, &pb_opts); + pb = perf_buffer__new(bpf_map__fd(skel->maps.perf_buf_map), 1, + on_sample, NULL, &passed, NULL); if (!ASSERT_OK_PTR(pb, "perf_buf__new")) goto close_prog; @@ -134,7 +116,7 @@ void test_kfree_skb(void) */ ASSERT_TRUE(passed, "passed"); - err = bpf_map_lookup_elem(bpf_map__fd(global_data), &zero, test_ok); + err = bpf_map_lookup_elem(bpf_map__fd(skel->maps.bss), &zero, test_ok); if (CHECK(err, "get_result", "failed to get output data: %d\n", err)) goto close_prog; @@ -142,9 +124,6 @@ void test_kfree_skb(void) CHECK_FAIL(!test_ok[0] || !test_ok[1]); close_prog: perf_buffer__free(pb); - bpf_link__destroy(link); - bpf_link__destroy(link_fentry); - bpf_link__destroy(link_fexit); bpf_object__close(obj); - bpf_object__close(obj2); + kfree_skb__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/kfunc_call.c b/tools/testing/selftests/bpf/prog_tests/kfunc_call.c index 9611f2bc50..7d7445ccc1 100644 --- a/tools/testing/selftests/bpf/prog_tests/kfunc_call.c +++ b/tools/testing/selftests/bpf/prog_tests/kfunc_call.c @@ -4,13 +4,14 @@ #include #include "kfunc_call_test.lskel.h" #include "kfunc_call_test_subprog.skel.h" +#include "kfunc_call_test_subprog.lskel.h" static void test_main(void) { - struct kfunc_call_test *skel; + struct kfunc_call_test_lskel *skel; int prog_fd, retval, err; - skel = kfunc_call_test__open_and_load(); + skel = kfunc_call_test_lskel__open_and_load(); if (!ASSERT_OK_PTR(skel, "skel")) return; @@ -26,7 +27,7 @@ static void test_main(void) ASSERT_OK(err, "bpf_prog_test_run(test2)"); ASSERT_EQ(retval, 3, "test2-retval"); - kfunc_call_test__destroy(skel); + kfunc_call_test_lskel__destroy(skel); } static void test_subprog(void) @@ -49,6 +50,26 @@ static void test_subprog(void) kfunc_call_test_subprog__destroy(skel); } +static void test_subprog_lskel(void) +{ + struct kfunc_call_test_subprog_lskel *skel; + int prog_fd, retval, err; + + skel = kfunc_call_test_subprog_lskel__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel")) + return; + + prog_fd = skel->progs.kfunc_call_test1.prog_fd; + err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), + NULL, NULL, (__u32 *)&retval, NULL); + ASSERT_OK(err, "bpf_prog_test_run(test1)"); + ASSERT_EQ(retval, 10, "test1-retval"); + ASSERT_NEQ(skel->data->active_res, -1, "active_res"); + ASSERT_EQ(skel->data->sk_state_res, BPF_TCP_CLOSE, "sk_state_res"); + + kfunc_call_test_subprog_lskel__destroy(skel); +} + void test_kfunc_call(void) { if (test__start_subtest("main")) @@ -56,4 +77,7 @@ void test_kfunc_call(void) if (test__start_subtest("subprog")) test_subprog(); + + if (test__start_subtest("subprog_lskel")) + test_subprog_lskel(); } diff --git a/tools/testing/selftests/bpf/prog_tests/ksyms_btf.c b/tools/testing/selftests/bpf/prog_tests/ksyms_btf.c index cf3acfa5a9..f6933b06da 100644 --- a/tools/testing/selftests/bpf/prog_tests/ksyms_btf.c +++ b/tools/testing/selftests/bpf/prog_tests/ksyms_btf.c @@ -7,6 +7,8 @@ #include "test_ksyms_btf.skel.h" #include "test_ksyms_btf_null_check.skel.h" #include "test_ksyms_weak.skel.h" +#include "test_ksyms_weak.lskel.h" +#include "test_ksyms_btf_write_check.skel.h" static int duration; @@ -89,11 +91,11 @@ static void test_weak_syms(void) int err; skel = test_ksyms_weak__open_and_load(); - if (CHECK(!skel, "test_ksyms_weak__open_and_load", "failed\n")) + if (!ASSERT_OK_PTR(skel, "test_ksyms_weak__open_and_load")) return; err = test_ksyms_weak__attach(skel); - if (CHECK(err, "test_ksyms_weak__attach", "skeleton attach failed: %d\n", err)) + if (!ASSERT_OK(err, "test_ksyms_weak__attach")) goto cleanup; /* trigger tracepoint */ @@ -109,6 +111,43 @@ static void test_weak_syms(void) test_ksyms_weak__destroy(skel); } +static void test_weak_syms_lskel(void) +{ + struct test_ksyms_weak_lskel *skel; + struct test_ksyms_weak_lskel__data *data; + int err; + + skel = test_ksyms_weak_lskel__open_and_load(); + if (!ASSERT_OK_PTR(skel, "test_ksyms_weak_lskel__open_and_load")) + return; + + err = test_ksyms_weak_lskel__attach(skel); + if (!ASSERT_OK(err, "test_ksyms_weak_lskel__attach")) + goto cleanup; + + /* trigger tracepoint */ + usleep(1); + + data = skel->data; + ASSERT_EQ(data->out__existing_typed, 0, "existing typed ksym"); + ASSERT_NEQ(data->out__existing_typeless, -1, "existing typeless ksym"); + ASSERT_EQ(data->out__non_existent_typeless, 0, "nonexistent typeless ksym"); + ASSERT_EQ(data->out__non_existent_typed, 0, "nonexistent typed ksym"); + +cleanup: + test_ksyms_weak_lskel__destroy(skel); +} + +static void test_write_check(void) +{ + struct test_ksyms_btf_write_check *skel; + + skel = test_ksyms_btf_write_check__open_and_load(); + ASSERT_ERR_PTR(skel, "unexpected load of a prog writing to ksym memory\n"); + + test_ksyms_btf_write_check__destroy(skel); +} + void test_ksyms_btf(void) { int percpu_datasec; @@ -136,4 +175,10 @@ void test_ksyms_btf(void) if (test__start_subtest("weak_ksyms")) test_weak_syms(); + + if (test__start_subtest("weak_ksyms_lskel")) + test_weak_syms_lskel(); + + if (test__start_subtest("write_check")) + test_write_check(); } diff --git a/tools/testing/selftests/bpf/prog_tests/ksyms_module.c b/tools/testing/selftests/bpf/prog_tests/ksyms_module.c index 2cd5cded54..d490ad80ec 100644 --- a/tools/testing/selftests/bpf/prog_tests/ksyms_module.c +++ b/tools/testing/selftests/bpf/prog_tests/ksyms_module.c @@ -2,30 +2,61 @@ /* Copyright (c) 2021 Facebook */ #include -#include -#include +#include #include "test_ksyms_module.lskel.h" +#include "test_ksyms_module.skel.h" -static int duration; - -void test_ksyms_module(void) +void test_ksyms_module_lskel(void) { - struct test_ksyms_module* skel; + struct test_ksyms_module_lskel *skel; + int retval; int err; - skel = test_ksyms_module__open_and_load(); - if (CHECK(!skel, "skel_open", "failed to open skeleton\n")) + if (!env.has_testmod) { + test__skip(); return; + } - err = test_ksyms_module__attach(skel); - if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err)) + skel = test_ksyms_module_lskel__open_and_load(); + if (!ASSERT_OK_PTR(skel, "test_ksyms_module_lskel__open_and_load")) + return; + err = bpf_prog_test_run(skel->progs.load.prog_fd, 1, &pkt_v4, sizeof(pkt_v4), + NULL, NULL, (__u32 *)&retval, NULL); + if (!ASSERT_OK(err, "bpf_prog_test_run")) goto cleanup; + ASSERT_EQ(retval, 0, "retval"); + ASSERT_EQ(skel->bss->out_bpf_testmod_ksym, 42, "bpf_testmod_ksym"); +cleanup: + test_ksyms_module_lskel__destroy(skel); +} - usleep(1); +void test_ksyms_module_libbpf(void) +{ + struct test_ksyms_module *skel; + int retval, err; - ASSERT_EQ(skel->bss->triggered, true, "triggered"); - ASSERT_EQ(skel->bss->out_mod_ksym_global, 123, "global_ksym_val"); + if (!env.has_testmod) { + test__skip(); + return; + } + skel = test_ksyms_module__open_and_load(); + if (!ASSERT_OK_PTR(skel, "test_ksyms_module__open")) + return; + err = bpf_prog_test_run(bpf_program__fd(skel->progs.load), 1, &pkt_v4, + sizeof(pkt_v4), NULL, NULL, (__u32 *)&retval, NULL); + if (!ASSERT_OK(err, "bpf_prog_test_run")) + goto cleanup; + ASSERT_EQ(retval, 0, "retval"); + ASSERT_EQ(skel->bss->out_bpf_testmod_ksym, 42, "bpf_testmod_ksym"); cleanup: test_ksyms_module__destroy(skel); } + +void test_ksyms_module(void) +{ + if (test__start_subtest("lskel")) + test_ksyms_module_lskel(); + if (test__start_subtest("libbpf")) + test_ksyms_module_libbpf(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/l4lb_all.c b/tools/testing/selftests/bpf/prog_tests/l4lb_all.c index 8073105548..540ef28fab 100644 --- a/tools/testing/selftests/bpf/prog_tests/l4lb_all.c +++ b/tools/testing/selftests/bpf/prog_tests/l4lb_all.c @@ -30,7 +30,7 @@ static void test_l4lb(const char *file) char buf[128]; u32 *magic = (u32 *)buf; - err = bpf_prog_load(file, BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); + err = bpf_prog_test_load(file, BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); if (CHECK_FAIL(err)) return; diff --git a/tools/testing/selftests/bpf/prog_tests/load_bytes_relative.c b/tools/testing/selftests/bpf/prog_tests/load_bytes_relative.c index 5a2a689dbb..4e0b2ec057 100644 --- a/tools/testing/selftests/bpf/prog_tests/load_bytes_relative.c +++ b/tools/testing/selftests/bpf/prog_tests/load_bytes_relative.c @@ -27,7 +27,7 @@ void test_load_bytes_relative(void) if (CHECK_FAIL(server_fd < 0)) goto close_cgroup_fd; - err = bpf_prog_load("./load_bytes_relative.o", BPF_PROG_TYPE_CGROUP_SKB, + err = bpf_prog_test_load("./load_bytes_relative.o", BPF_PROG_TYPE_CGROUP_SKB, &obj, &prog_fd); if (CHECK_FAIL(err)) goto close_server_fd; diff --git a/tools/testing/selftests/bpf/prog_tests/map_lock.c b/tools/testing/selftests/bpf/prog_tests/map_lock.c index ce17b1ed87..23d19e9cf2 100644 --- a/tools/testing/selftests/bpf/prog_tests/map_lock.c +++ b/tools/testing/selftests/bpf/prog_tests/map_lock.c @@ -53,9 +53,9 @@ void test_map_lock(void) int err = 0, key = 0, i; void *ret; - err = bpf_prog_load(file, BPF_PROG_TYPE_CGROUP_SKB, &obj, &prog_fd); + err = bpf_prog_test_load(file, BPF_PROG_TYPE_CGROUP_SKB, &obj, &prog_fd); if (CHECK_FAIL(err)) { - printf("test_map_lock:bpf_prog_load errno %d\n", errno); + printf("test_map_lock:bpf_prog_test_load errno %d\n", errno); goto close_prog; } map_fd[0] = bpf_find_map(__func__, obj, "hash_map"); diff --git a/tools/testing/selftests/bpf/prog_tests/map_ptr.c b/tools/testing/selftests/bpf/prog_tests/map_ptr.c index 4972f92205..273725504f 100644 --- a/tools/testing/selftests/bpf/prog_tests/map_ptr.c +++ b/tools/testing/selftests/bpf/prog_tests/map_ptr.c @@ -4,31 +4,29 @@ #include #include -#include "map_ptr_kern.skel.h" +#include "map_ptr_kern.lskel.h" void test_map_ptr(void) { - struct map_ptr_kern *skel; + struct map_ptr_kern_lskel *skel; __u32 duration = 0, retval; char buf[128]; int err; int page_size = getpagesize(); - skel = map_ptr_kern__open(); + skel = map_ptr_kern_lskel__open(); if (!ASSERT_OK_PTR(skel, "skel_open")) return; - err = bpf_map__set_max_entries(skel->maps.m_ringbuf, page_size); - if (!ASSERT_OK(err, "bpf_map__set_max_entries")) - goto cleanup; + skel->maps.m_ringbuf.max_entries = page_size; - err = map_ptr_kern__load(skel); + err = map_ptr_kern_lskel__load(skel); if (!ASSERT_OK(err, "skel_load")) goto cleanup; skel->bss->page_size = page_size; - err = bpf_prog_test_run(bpf_program__fd(skel->progs.cg_skb), 1, &pkt_v4, + err = bpf_prog_test_run(skel->progs.cg_skb.prog_fd, 1, &pkt_v4, sizeof(pkt_v4), buf, NULL, &retval, NULL); if (CHECK(err, "test_run", "err=%d errno=%d\n", err, errno)) @@ -39,5 +37,5 @@ void test_map_ptr(void) goto cleanup; cleanup: - map_ptr_kern__destroy(skel); + map_ptr_kern_lskel__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/migrate_reuseport.c b/tools/testing/selftests/bpf/prog_tests/migrate_reuseport.c index 3c85247f96..eb2feaac81 100644 --- a/tools/testing/selftests/bpf/prog_tests/migrate_reuseport.c +++ b/tools/testing/selftests/bpf/prog_tests/migrate_reuseport.c @@ -541,7 +541,7 @@ static void run_test(struct migrate_reuseport_test_case *test_case, } } -void test_migrate_reuseport(void) +void serial_test_migrate_reuseport(void) { struct test_migrate_reuseport *skel; int i; diff --git a/tools/testing/selftests/bpf/prog_tests/modify_return.c b/tools/testing/selftests/bpf/prog_tests/modify_return.c index 97fec70c60..b772fe30ce 100644 --- a/tools/testing/selftests/bpf/prog_tests/modify_return.c +++ b/tools/testing/selftests/bpf/prog_tests/modify_return.c @@ -53,7 +53,8 @@ static void run_test(__u32 input_retval, __u16 want_side_effect, __s16 want_ret) modify_return__destroy(skel); } -void test_modify_return(void) +/* TODO: conflict with get_func_ip_test */ +void serial_test_modify_return(void) { run_test(0 /* input_retval */, 1 /* want_side_effect */, diff --git a/tools/testing/selftests/bpf/prog_tests/module_attach.c b/tools/testing/selftests/bpf/prog_tests/module_attach.c index d85a69b7ce..6d0e50dcf4 100644 --- a/tools/testing/selftests/bpf/prog_tests/module_attach.c +++ b/tools/testing/selftests/bpf/prog_tests/module_attach.c @@ -2,46 +2,33 @@ /* Copyright (c) 2020 Facebook */ #include +#include #include "test_module_attach.skel.h" static int duration; -static int trigger_module_test_read(int read_sz) +static int trigger_module_test_writable(int *val) { int fd, err; + char buf[65]; + ssize_t rd; - fd = open("/sys/kernel/bpf_testmod", O_RDONLY); + fd = open(BPF_TESTMOD_TEST_FILE, O_RDONLY); err = -errno; - if (CHECK(fd < 0, "testmod_file_open", "failed: %d\n", err)) + if (!ASSERT_GE(fd, 0, "testmode_file_open")) return err; - read(fd, NULL, read_sz); - close(fd); - - return 0; -} - -static int trigger_module_test_write(int write_sz) -{ - int fd, err; - char *buf = malloc(write_sz); - - if (!buf) - return -ENOMEM; - - memset(buf, 'a', write_sz); - buf[write_sz-1] = '\0'; - - fd = open("/sys/kernel/bpf_testmod", O_WRONLY); + rd = read(fd, buf, sizeof(buf) - 1); err = -errno; - if (CHECK(fd < 0, "testmod_file_open", "failed: %d\n", err)) { - free(buf); + if (!ASSERT_GT(rd, 0, "testmod_file_rd_val")) { + close(fd); return err; } - write(fd, buf, write_sz); + buf[rd] = '\0'; + *val = strtol(buf, NULL, 0); close(fd); - free(buf); + return 0; } @@ -58,6 +45,7 @@ void test_module_attach(void) struct test_module_attach__bss *bss; struct bpf_link *link; int err; + int writable_val = 0; skel = test_module_attach__open(); if (CHECK(!skel, "skel_open", "failed to open skeleton\n")) @@ -90,6 +78,14 @@ void test_module_attach(void) ASSERT_EQ(bss->fexit_ret, -EIO, "fexit_tet"); ASSERT_EQ(bss->fmod_ret_read_sz, READ_SZ, "fmod_ret"); + bss->raw_tp_writable_bare_early_ret = true; + bss->raw_tp_writable_bare_out_val = 0xf1f2f3f4; + ASSERT_OK(trigger_module_test_writable(&writable_val), + "trigger_writable"); + ASSERT_EQ(bss->raw_tp_writable_bare_in_val, 1024, "writable_test_in"); + ASSERT_EQ(bss->raw_tp_writable_bare_out_val, writable_val, + "writable_test_out"); + test_module_attach__detach(skel); /* attach fentry/fexit and make sure it get's module reference */ diff --git a/tools/testing/selftests/bpf/prog_tests/netcnt.c b/tools/testing/selftests/bpf/prog_tests/netcnt.c index 6ede48bde9..954964f0ac 100644 --- a/tools/testing/selftests/bpf/prog_tests/netcnt.c +++ b/tools/testing/selftests/bpf/prog_tests/netcnt.c @@ -8,7 +8,7 @@ #define CG_NAME "/netcnt" -void test_netcnt(void) +void serial_test_netcnt(void) { union percpu_net_cnt *percpu_netcnt = NULL; struct bpf_cgroup_storage_key key; diff --git a/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c b/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c index 2535788e13..24d493482f 100644 --- a/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c +++ b/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c @@ -78,7 +78,8 @@ static void test_ns_current_pid_tgid_new_ns(void) return; } -void test_ns_current_pid_tgid(void) +/* TODO: use a different tracepoint */ +void serial_test_ns_current_pid_tgid(void) { if (test__start_subtest("ns_current_pid_tgid_root_ns")) test_current_pid_tgid(NULL); diff --git a/tools/testing/selftests/bpf/prog_tests/perf_buffer.c b/tools/testing/selftests/bpf/prog_tests/perf_buffer.c index 7daaaab136..5fc2b3a071 100644 --- a/tools/testing/selftests/bpf/prog_tests/perf_buffer.c +++ b/tools/testing/selftests/bpf/prog_tests/perf_buffer.c @@ -43,10 +43,10 @@ int trigger_on_cpu(int cpu) return 0; } -void test_perf_buffer(void) +void serial_test_perf_buffer(void) { - int err, on_len, nr_on_cpus = 0, nr_cpus, i; - struct perf_buffer_opts pb_opts = {}; + int err, on_len, nr_on_cpus = 0, nr_cpus, i, j; + int zero = 0, my_pid = getpid(); struct test_perf_buffer *skel; cpu_set_t cpu_seen; struct perf_buffer *pb; @@ -71,15 +71,18 @@ void test_perf_buffer(void) if (CHECK(!skel, "skel_load", "skeleton open/load failed\n")) goto out_close; + err = bpf_map_update_elem(bpf_map__fd(skel->maps.my_pid_map), &zero, &my_pid, 0); + if (!ASSERT_OK(err, "my_pid_update")) + goto out_close; + /* attach probe */ err = test_perf_buffer__attach(skel); if (CHECK(err, "attach_kprobe", "err %d\n", err)) goto out_close; /* set up perf buffer */ - pb_opts.sample_cb = on_sample; - pb_opts.ctx = &cpu_seen; - pb = perf_buffer__new(bpf_map__fd(skel->maps.perf_buf_map), 1, &pb_opts); + pb = perf_buffer__new(bpf_map__fd(skel->maps.perf_buf_map), 1, + on_sample, NULL, &cpu_seen, NULL); if (!ASSERT_OK_PTR(pb, "perf_buf__new")) goto out_close; @@ -111,15 +114,15 @@ void test_perf_buffer(void) "got %zu, expected %d\n", perf_buffer__buffer_cnt(pb), nr_on_cpus)) goto out_close; - for (i = 0; i < nr_cpus; i++) { + for (i = 0, j = 0; i < nr_cpus; i++) { if (i >= on_len || !online[i]) continue; - fd = perf_buffer__buffer_fd(pb, i); + fd = perf_buffer__buffer_fd(pb, j); CHECK(fd < 0 || last_fd == fd, "fd_check", "last fd %d == fd %d\n", last_fd, fd); last_fd = fd; - err = perf_buffer__consume_buffer(pb, i); + err = perf_buffer__consume_buffer(pb, j); if (CHECK(err, "drain_buf", "cpu %d, err %d\n", i, err)) goto out_close; @@ -127,12 +130,13 @@ void test_perf_buffer(void) if (trigger_on_cpu(i)) goto out_close; - err = perf_buffer__consume_buffer(pb, i); - if (CHECK(err, "consume_buf", "cpu %d, err %d\n", i, err)) + err = perf_buffer__consume_buffer(pb, j); + if (CHECK(err, "consume_buf", "cpu %d, err %d\n", j, err)) goto out_close; if (CHECK(!CPU_ISSET(i, &cpu_seen), "cpu_seen", "cpu %d not seen\n", i)) goto out_close; + j++; } out_free_pb: diff --git a/tools/testing/selftests/bpf/prog_tests/perf_link.c b/tools/testing/selftests/bpf/prog_tests/perf_link.c index b1abd0c466..ede07344f2 100644 --- a/tools/testing/selftests/bpf/prog_tests/perf_link.c +++ b/tools/testing/selftests/bpf/prog_tests/perf_link.c @@ -23,7 +23,8 @@ static void burn_cpu(void) ++j; } -void test_perf_link(void) +/* TODO: often fails in concurrent mode */ +void serial_test_perf_link(void) { struct test_perf_link *skel = NULL; struct perf_event_attr attr; diff --git a/tools/testing/selftests/bpf/prog_tests/pinning.c b/tools/testing/selftests/bpf/prog_tests/pinning.c index d4b953ae34..31c09ba577 100644 --- a/tools/testing/selftests/bpf/prog_tests/pinning.c +++ b/tools/testing/selftests/bpf/prog_tests/pinning.c @@ -241,8 +241,8 @@ void test_pinning(void) goto out; } - map_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, sizeof(__u32), - sizeof(__u64), 1, 0); + map_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, sizeof(__u32), + sizeof(__u64), 1, NULL); if (CHECK(map_fd < 0, "create pinmap manually", "fd %d\n", map_fd)) goto out; diff --git a/tools/testing/selftests/bpf/prog_tests/pkt_access.c b/tools/testing/selftests/bpf/prog_tests/pkt_access.c index 44b514fabc..6628710ec3 100644 --- a/tools/testing/selftests/bpf/prog_tests/pkt_access.c +++ b/tools/testing/selftests/bpf/prog_tests/pkt_access.c @@ -9,7 +9,7 @@ void test_pkt_access(void) __u32 duration, retval; int err, prog_fd; - err = bpf_prog_load(file, BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); + err = bpf_prog_test_load(file, BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); if (CHECK_FAIL(err)) return; diff --git a/tools/testing/selftests/bpf/prog_tests/pkt_md_access.c b/tools/testing/selftests/bpf/prog_tests/pkt_md_access.c index 939015cd6d..c9d2d6a1bf 100644 --- a/tools/testing/selftests/bpf/prog_tests/pkt_md_access.c +++ b/tools/testing/selftests/bpf/prog_tests/pkt_md_access.c @@ -9,7 +9,7 @@ void test_pkt_md_access(void) __u32 duration, retval; int err, prog_fd; - err = bpf_prog_load(file, BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); + err = bpf_prog_test_load(file, BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); if (CHECK_FAIL(err)) return; diff --git a/tools/testing/selftests/bpf/prog_tests/probe_user.c b/tools/testing/selftests/bpf/prog_tests/probe_user.c index 95bd120973..abf890d066 100644 --- a/tools/testing/selftests/bpf/prog_tests/probe_user.c +++ b/tools/testing/selftests/bpf/prog_tests/probe_user.c @@ -1,9 +1,10 @@ // SPDX-License-Identifier: GPL-2.0 #include -void test_probe_user(void) +/* TODO: corrupts other tests uses connect() */ +void serial_test_probe_user(void) { - const char *prog_name = "kprobe/__sys_connect"; + const char *prog_name = "handle_sys_connect"; const char *obj_file = "./test_probe_user.o"; DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts, ); int err, results_map_fd, sock_fd, duration = 0; @@ -18,7 +19,7 @@ void test_probe_user(void) if (!ASSERT_OK_PTR(obj, "obj_open_file")) return; - kprobe_prog = bpf_object__find_program_by_title(obj, prog_name); + kprobe_prog = bpf_object__find_program_by_name(obj, prog_name); if (CHECK(!kprobe_prog, "find_probe", "prog '%s' not found\n", prog_name)) goto cleanup; diff --git a/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c b/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c index f47e7b1cb3..b9822f914e 100644 --- a/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c +++ b/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c @@ -14,7 +14,7 @@ static void test_queue_stack_map_by_type(int type) int i, err, prog_fd, map_in_fd, map_out_fd; char file[32], buf[128]; struct bpf_object *obj; - struct iphdr *iph = (void *)buf + sizeof(struct ethhdr); + struct iphdr iph; /* Fill test values to be used */ for (i = 0; i < MAP_SIZE; i++) @@ -27,7 +27,7 @@ static void test_queue_stack_map_by_type(int type) else return; - err = bpf_prog_load(file, BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); + err = bpf_prog_test_load(file, BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); if (CHECK_FAIL(err)) return; @@ -60,15 +60,17 @@ static void test_queue_stack_map_by_type(int type) err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), buf, &size, &retval, &duration); - if (err || retval || size != sizeof(pkt_v4) || - iph->daddr != val) + if (err || retval || size != sizeof(pkt_v4)) + break; + memcpy(&iph, buf + sizeof(struct ethhdr), sizeof(iph)); + if (iph.daddr != val) break; } - CHECK(err || retval || size != sizeof(pkt_v4) || iph->daddr != val, + CHECK(err || retval || size != sizeof(pkt_v4) || iph.daddr != val, "bpf_map_pop_elem", "err %d errno %d retval %d size %d iph->daddr %u\n", - err, errno, retval, size, iph->daddr); + err, errno, retval, size, iph.daddr); /* Queue is empty, program should return TC_ACT_SHOT */ err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), diff --git a/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_reject_nbd_invalid.c b/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_reject_nbd_invalid.c index 9807336a30..e2f1445b0e 100644 --- a/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_reject_nbd_invalid.c +++ b/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_reject_nbd_invalid.c @@ -18,15 +18,15 @@ void test_raw_tp_writable_reject_nbd_invalid(void) BPF_EXIT_INSN(), }; - struct bpf_load_program_attr load_attr = { - .prog_type = BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, - .license = "GPL v2", - .insns = program, - .insns_cnt = sizeof(program) / sizeof(struct bpf_insn), + LIBBPF_OPTS(bpf_prog_load_opts, opts, .log_level = 2, - }; + .log_buf = error, + .log_size = sizeof(error), + ); - bpf_fd = bpf_load_program_xattr(&load_attr, error, sizeof(error)); + bpf_fd = bpf_prog_load(BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, NULL, "GPL v2", + program, sizeof(program) / sizeof(struct bpf_insn), + &opts); if (CHECK(bpf_fd < 0, "bpf_raw_tracepoint_writable load", "failed: %d errno %d\n", bpf_fd, errno)) return; diff --git a/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_test_run.c b/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_test_run.c index 5c45424cac..239baccabc 100644 --- a/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_test_run.c +++ b/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_test_run.c @@ -3,7 +3,8 @@ #include #include -void test_raw_tp_writable_test_run(void) +/* NOTE: conflict with other tests. */ +void serial_test_raw_tp_writable_test_run(void) { __u32 duration = 0; char error[4096]; @@ -16,15 +17,15 @@ void test_raw_tp_writable_test_run(void) BPF_EXIT_INSN(), }; - struct bpf_load_program_attr load_attr = { - .prog_type = BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, - .license = "GPL v2", - .insns = trace_program, - .insns_cnt = sizeof(trace_program) / sizeof(struct bpf_insn), + LIBBPF_OPTS(bpf_prog_load_opts, trace_opts, .log_level = 2, - }; + .log_buf = error, + .log_size = sizeof(error), + ); - int bpf_fd = bpf_load_program_xattr(&load_attr, error, sizeof(error)); + int bpf_fd = bpf_prog_load(BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, NULL, "GPL v2", + trace_program, sizeof(trace_program) / sizeof(struct bpf_insn), + &trace_opts); if (CHECK(bpf_fd < 0, "bpf_raw_tracepoint_writable loaded", "failed: %d errno %d\n", bpf_fd, errno)) return; @@ -34,15 +35,14 @@ void test_raw_tp_writable_test_run(void) BPF_EXIT_INSN(), }; - struct bpf_load_program_attr skb_load_attr = { - .prog_type = BPF_PROG_TYPE_SOCKET_FILTER, - .license = "GPL v2", - .insns = skb_program, - .insns_cnt = sizeof(skb_program) / sizeof(struct bpf_insn), - }; + LIBBPF_OPTS(bpf_prog_load_opts, skb_opts, + .log_buf = error, + .log_size = sizeof(error), + ); - int filter_fd = - bpf_load_program_xattr(&skb_load_attr, error, sizeof(error)); + int filter_fd = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL v2", + skb_program, sizeof(skb_program) / sizeof(struct bpf_insn), + &skb_opts); if (CHECK(filter_fd < 0, "test_program_loaded", "failed: %d errno %d\n", filter_fd, errno)) goto out_bpffd; diff --git a/tools/testing/selftests/bpf/prog_tests/rdonly_maps.c b/tools/testing/selftests/bpf/prog_tests/rdonly_maps.c index 5f9eaa3ab5..fd5d2ddfb0 100644 --- a/tools/testing/selftests/bpf/prog_tests/rdonly_maps.c +++ b/tools/testing/selftests/bpf/prog_tests/rdonly_maps.c @@ -37,7 +37,7 @@ void test_rdonly_maps(void) if (CHECK(err, "obj_load", "err %d errno %d\n", err, errno)) goto cleanup; - bss_map = bpf_object__find_map_by_name(obj, "test_rdo.bss"); + bss_map = bpf_object__find_map_by_name(obj, ".bss"); if (CHECK(!bss_map, "find_bss_map", "failed\n")) goto cleanup; diff --git a/tools/testing/selftests/bpf/prog_tests/recursion.c b/tools/testing/selftests/bpf/prog_tests/recursion.c index 0e378d63fe..f3af2627b5 100644 --- a/tools/testing/selftests/bpf/prog_tests/recursion.c +++ b/tools/testing/selftests/bpf/prog_tests/recursion.c @@ -20,18 +20,18 @@ void test_recursion(void) goto out; ASSERT_EQ(skel->bss->pass1, 0, "pass1 == 0"); - bpf_map_lookup_elem(bpf_map__fd(skel->maps.hash1), &key, 0); + bpf_map_delete_elem(bpf_map__fd(skel->maps.hash1), &key); ASSERT_EQ(skel->bss->pass1, 1, "pass1 == 1"); - bpf_map_lookup_elem(bpf_map__fd(skel->maps.hash1), &key, 0); + bpf_map_delete_elem(bpf_map__fd(skel->maps.hash1), &key); ASSERT_EQ(skel->bss->pass1, 2, "pass1 == 2"); ASSERT_EQ(skel->bss->pass2, 0, "pass2 == 0"); - bpf_map_lookup_elem(bpf_map__fd(skel->maps.hash2), &key, 0); + bpf_map_delete_elem(bpf_map__fd(skel->maps.hash2), &key); ASSERT_EQ(skel->bss->pass2, 1, "pass2 == 1"); - bpf_map_lookup_elem(bpf_map__fd(skel->maps.hash2), &key, 0); + bpf_map_delete_elem(bpf_map__fd(skel->maps.hash2), &key); ASSERT_EQ(skel->bss->pass2, 2, "pass2 == 2"); - err = bpf_obj_get_info_by_fd(bpf_program__fd(skel->progs.on_lookup), + err = bpf_obj_get_info_by_fd(bpf_program__fd(skel->progs.on_delete), &prog_info, &prog_info_len); if (!ASSERT_OK(err, "get_prog_info")) goto out; diff --git a/tools/testing/selftests/bpf/prog_tests/reference_tracking.c b/tools/testing/selftests/bpf/prog_tests/reference_tracking.c index 4e91f4d646..873323fb18 100644 --- a/tools/testing/selftests/bpf/prog_tests/reference_tracking.c +++ b/tools/testing/selftests/bpf/prog_tests/reference_tracking.c @@ -1,6 +1,21 @@ // SPDX-License-Identifier: GPL-2.0 #include +static void toggle_object_autoload_progs(const struct bpf_object *obj, + const char *name_load) +{ + struct bpf_program *prog; + + bpf_object__for_each_program(prog, obj) { + const char *name = bpf_program__name(prog); + + if (!strcmp(name_load, name)) + bpf_program__set_autoload(prog, true); + else + bpf_program__set_autoload(prog, false); + } +} + void test_reference_tracking(void) { const char *file = "test_sk_lookup_kern.o"; @@ -9,44 +24,49 @@ void test_reference_tracking(void) .object_name = obj_name, .relaxed_maps = true, ); - struct bpf_object *obj; + struct bpf_object *obj_iter, *obj = NULL; struct bpf_program *prog; __u32 duration = 0; int err = 0; - obj = bpf_object__open_file(file, &open_opts); - if (!ASSERT_OK_PTR(obj, "obj_open_file")) + obj_iter = bpf_object__open_file(file, &open_opts); + if (!ASSERT_OK_PTR(obj_iter, "obj_iter_open_file")) return; - if (CHECK(strcmp(bpf_object__name(obj), obj_name), "obj_name", + if (CHECK(strcmp(bpf_object__name(obj_iter), obj_name), "obj_name", "wrong obj name '%s', expected '%s'\n", - bpf_object__name(obj), obj_name)) + bpf_object__name(obj_iter), obj_name)) goto cleanup; - bpf_object__for_each_program(prog, obj) { - const char *title; + bpf_object__for_each_program(prog, obj_iter) { + const char *name; - /* Ignore .text sections */ - title = bpf_program__section_name(prog); - if (strstr(title, ".text") != NULL) + name = bpf_program__name(prog); + if (!test__start_subtest(name)) continue; - if (!test__start_subtest(title)) - continue; + obj = bpf_object__open_file(file, &open_opts); + if (!ASSERT_OK_PTR(obj, "obj_open_file")) + goto cleanup; + toggle_object_autoload_progs(obj, name); /* Expect verifier failure if test name has 'err' */ - if (strstr(title, "err_") != NULL) { + if (strncmp(name, "err_", sizeof("err_") - 1) == 0) { libbpf_print_fn_t old_print_fn; old_print_fn = libbpf_set_print(NULL); - err = !bpf_program__load(prog, "GPL", 0); + err = !bpf_object__load(obj); libbpf_set_print(old_print_fn); } else { - err = bpf_program__load(prog, "GPL", 0); + err = bpf_object__load(obj); } - CHECK(err, title, "\n"); + ASSERT_OK(err, name); + + bpf_object__close(obj); + obj = NULL; } cleanup: bpf_object__close(obj); + bpf_object__close(obj_iter); } diff --git a/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c b/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c index f62361306f..f4a13d9dd5 100644 --- a/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c +++ b/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c @@ -106,9 +106,9 @@ static int resolve_symbols(void) "Failed to load BTF from btf_data.o\n")) return -1; - nr = btf__get_nr_types(btf); + nr = btf__type_cnt(btf); - for (type_id = 1; type_id <= nr; type_id++) { + for (type_id = 1; type_id < nr; type_id++) { if (__resolve_symbol(btf, type_id)) break; } @@ -117,14 +117,14 @@ static int resolve_symbols(void) return 0; } -int test_resolve_btfids(void) +void test_resolve_btfids(void) { __u32 *test_list, *test_lists[] = { test_list_local, test_list_global }; unsigned int i, j; int ret = 0; if (resolve_symbols()) - return -1; + return; /* Check BTF_ID_LIST(test_list_local) and * BTF_ID_LIST_GLOBAL(test_list_global) IDs @@ -138,7 +138,7 @@ int test_resolve_btfids(void) test_symbols[i].name, test_list[i], test_symbols[i].id); if (ret) - return ret; + return; } } @@ -161,9 +161,7 @@ int test_resolve_btfids(void) if (i > 0) { if (!ASSERT_LE(test_set.ids[i - 1], test_set.ids[i], "sort_check")) - return -1; + return; } } - - return ret; } diff --git a/tools/testing/selftests/bpf/prog_tests/ringbuf.c b/tools/testing/selftests/bpf/prog_tests/ringbuf.c index 4706cee843..9a80fe8a64 100644 --- a/tools/testing/selftests/bpf/prog_tests/ringbuf.c +++ b/tools/testing/selftests/bpf/prog_tests/ringbuf.c @@ -58,7 +58,7 @@ static int process_sample(void *ctx, void *data, size_t len) } } -static struct test_ringbuf *skel; +static struct test_ringbuf_lskel *skel; static struct ring_buffer *ringbuf; static void trigger_samples() @@ -90,13 +90,13 @@ void test_ringbuf(void) int page_size = getpagesize(); void *mmap_ptr, *tmp_ptr; - skel = test_ringbuf__open(); + skel = test_ringbuf_lskel__open(); if (CHECK(!skel, "skel_open", "skeleton open failed\n")) return; skel->maps.ringbuf.max_entries = page_size; - err = test_ringbuf__load(skel); + err = test_ringbuf_lskel__load(skel); if (CHECK(err != 0, "skel_load", "skeleton load failed\n")) goto cleanup; @@ -154,7 +154,7 @@ void test_ringbuf(void) if (CHECK(!ringbuf, "ringbuf_create", "failed to create ringbuf\n")) goto cleanup; - err = test_ringbuf__attach(skel); + err = test_ringbuf_lskel__attach(skel); if (CHECK(err, "skel_attach", "skeleton attachment failed: %d\n", err)) goto cleanup; @@ -292,8 +292,8 @@ void test_ringbuf(void) CHECK(skel->bss->discarded != 1, "err_discarded", "exp %ld, got %ld\n", 1L, skel->bss->discarded); - test_ringbuf__detach(skel); + test_ringbuf_lskel__detach(skel); cleanup: ring_buffer__free(ringbuf); - test_ringbuf__destroy(skel); + test_ringbuf_lskel__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c b/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c index 167cd8a2ed..e945195b24 100644 --- a/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c +++ b/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c @@ -62,8 +62,8 @@ void test_ringbuf_multi(void) if (CHECK(err != 0, "bpf_map__set_max_entries", "bpf_map__set_max_entries failed\n")) goto cleanup; - proto_fd = bpf_create_map(BPF_MAP_TYPE_RINGBUF, 0, 0, page_size, 0); - if (CHECK(proto_fd < 0, "bpf_create_map", "bpf_create_map failed\n")) + proto_fd = bpf_map_create(BPF_MAP_TYPE_RINGBUF, NULL, 0, 0, page_size, NULL); + if (CHECK(proto_fd < 0, "bpf_map_create", "bpf_map_create failed\n")) goto cleanup; err = bpf_map__set_inner_map_fd(skel->maps.ringbuf_hash, proto_fd); diff --git a/tools/testing/selftests/bpf/prog_tests/select_reuseport.c b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c index 4efd337d6a..1cbd8cd640 100644 --- a/tools/testing/selftests/bpf/prog_tests/select_reuseport.c +++ b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c @@ -18,7 +18,6 @@ #include #include #include -#include "bpf_rlimit.h" #include "bpf_util.h" #include "test_progs.h" @@ -66,29 +65,20 @@ static union sa46 { static int create_maps(enum bpf_map_type inner_type) { - struct bpf_create_map_attr attr = {}; + LIBBPF_OPTS(bpf_map_create_opts, opts); inner_map_type = inner_type; /* Creating reuseport_array */ - attr.name = "reuseport_array"; - attr.map_type = inner_type; - attr.key_size = sizeof(__u32); - attr.value_size = sizeof(__u32); - attr.max_entries = REUSEPORT_ARRAY_SIZE; - - reuseport_array = bpf_create_map_xattr(&attr); + reuseport_array = bpf_map_create(inner_type, "reuseport_array", + sizeof(__u32), sizeof(__u32), REUSEPORT_ARRAY_SIZE, NULL); RET_ERR(reuseport_array < 0, "creating reuseport_array", "reuseport_array:%d errno:%d\n", reuseport_array, errno); /* Creating outer_map */ - attr.name = "outer_map"; - attr.map_type = BPF_MAP_TYPE_ARRAY_OF_MAPS; - attr.key_size = sizeof(__u32); - attr.value_size = sizeof(__u32); - attr.max_entries = 1; - attr.inner_map_fd = reuseport_array; - outer_map = bpf_create_map_xattr(&attr); + opts.inner_map_fd = reuseport_array; + outer_map = bpf_map_create(BPF_MAP_TYPE_ARRAY_OF_MAPS, "outer_map", + sizeof(__u32), sizeof(__u32), 1, &opts); RET_ERR(outer_map < 0, "creating outer_map", "outer_map:%d errno:%d\n", outer_map, errno); @@ -114,7 +104,7 @@ static int prepare_bpf_obj(void) err = bpf_object__load(obj); RET_ERR(err, "load bpf_object", "err:%d\n", err); - prog = bpf_program__next(NULL, obj); + prog = bpf_object__next_program(obj, NULL); RET_ERR(!prog, "get first bpf_program", "!prog\n"); select_by_skb_data_prog = bpf_program__fd(prog); RET_ERR(select_by_skb_data_prog < 0, "get prog fd", @@ -858,7 +848,7 @@ void test_map_type(enum bpf_map_type mt) cleanup(); } -void test_select_reuseport(void) +void serial_test_select_reuseport(void) { saved_tcp_fo = read_int_sysctl(TCP_FO_SYSCTL); if (saved_tcp_fo < 0) diff --git a/tools/testing/selftests/bpf/prog_tests/send_signal_sched_switch.c b/tools/testing/selftests/bpf/prog_tests/send_signal_sched_switch.c index 189a34a7ad..15dacfcfaa 100644 --- a/tools/testing/selftests/bpf/prog_tests/send_signal_sched_switch.c +++ b/tools/testing/selftests/bpf/prog_tests/send_signal_sched_switch.c @@ -25,7 +25,8 @@ static void *worker(void *p) return NULL; } -void test_send_signal_sched_switch(void) +/* NOTE: cause events loss */ +void serial_test_send_signal_sched_switch(void) { struct test_send_signal_kern *skel; pthread_t threads[THREAD_COUNT]; diff --git a/tools/testing/selftests/bpf/prog_tests/signal_pending.c b/tools/testing/selftests/bpf/prog_tests/signal_pending.c index dfcbddcbe4..aecfe662c0 100644 --- a/tools/testing/selftests/bpf/prog_tests/signal_pending.c +++ b/tools/testing/selftests/bpf/prog_tests/signal_pending.c @@ -22,7 +22,7 @@ static void test_signal_pending_by_type(enum bpf_prog_type prog_type) prog[i] = BPF_ALU64_IMM(BPF_MOV, BPF_REG_0, 0); prog[ARRAY_SIZE(prog) - 1] = BPF_EXIT_INSN(); - prog_fd = bpf_load_program(prog_type, prog, ARRAY_SIZE(prog), + prog_fd = bpf_test_load_program(prog_type, prog, ARRAY_SIZE(prog), "GPL", 0, NULL, 0); CHECK(prog_fd < 0, "test-run", "errno %d\n", errno); @@ -42,7 +42,7 @@ static void test_signal_pending_by_type(enum bpf_prog_type prog_type) signal(SIGALRM, SIG_DFL); } -void test_signal_pending(enum bpf_prog_type prog_type) +void test_signal_pending(void) { test_signal_pending_by_type(BPF_PROG_TYPE_SOCKET_FILTER); test_signal_pending_by_type(BPF_PROG_TYPE_FLOW_DISSECTOR); diff --git a/tools/testing/selftests/bpf/prog_tests/sk_assign.c b/tools/testing/selftests/bpf/prog_tests/sk_assign.c index 3a469099f3..1d272e0518 100644 --- a/tools/testing/selftests/bpf/prog_tests/sk_assign.c +++ b/tools/testing/selftests/bpf/prog_tests/sk_assign.c @@ -48,7 +48,7 @@ configure_stack(void) return false; sprintf(tc_cmd, "%s %s %s %s", "tc filter add dev lo ingress bpf", "direct-action object-file ./test_sk_assign.o", - "section classifier/sk_assign_test", + "section tc", (env.verbosity < VERBOSE_VERY) ? " 2>/dev/null" : "verbose"); if (CHECK(system(tc_cmd), "BPF load failed;", "run with -vv for more info\n")) diff --git a/tools/testing/selftests/bpf/prog_tests/sk_lookup.c b/tools/testing/selftests/bpf/prog_tests/sk_lookup.c index 6db07401bc..597d0467a9 100644 --- a/tools/testing/selftests/bpf/prog_tests/sk_lookup.c +++ b/tools/testing/selftests/bpf/prog_tests/sk_lookup.c @@ -30,7 +30,6 @@ #include #include "test_progs.h" -#include "bpf_rlimit.h" #include "bpf_util.h" #include "cgroup_helpers.h" #include "network_helpers.h" @@ -937,6 +936,37 @@ static void test_drop_on_lookup(struct test_sk_lookup *skel) .connect_to = { EXT_IP6, EXT_PORT }, .listen_at = { EXT_IP6, INT_PORT }, }, + /* The program will drop on success, meaning that the ifindex + * was 1. + */ + { + .desc = "TCP IPv4 drop on valid ifindex", + .lookup_prog = skel->progs.check_ifindex, + .sotype = SOCK_STREAM, + .connect_to = { EXT_IP4, EXT_PORT }, + .listen_at = { EXT_IP4, EXT_PORT }, + }, + { + .desc = "TCP IPv6 drop on valid ifindex", + .lookup_prog = skel->progs.check_ifindex, + .sotype = SOCK_STREAM, + .connect_to = { EXT_IP6, EXT_PORT }, + .listen_at = { EXT_IP6, EXT_PORT }, + }, + { + .desc = "UDP IPv4 drop on valid ifindex", + .lookup_prog = skel->progs.check_ifindex, + .sotype = SOCK_DGRAM, + .connect_to = { EXT_IP4, EXT_PORT }, + .listen_at = { EXT_IP4, EXT_PORT }, + }, + { + .desc = "UDP IPv6 drop on valid ifindex", + .lookup_prog = skel->progs.check_ifindex, + .sotype = SOCK_DGRAM, + .connect_to = { EXT_IP6, EXT_PORT }, + .listen_at = { EXT_IP6, EXT_PORT }, + }, }; const struct test *t; diff --git a/tools/testing/selftests/bpf/prog_tests/sk_storage_tracing.c b/tools/testing/selftests/bpf/prog_tests/sk_storage_tracing.c index 2b392590e8..547ae53cde 100644 --- a/tools/testing/selftests/bpf/prog_tests/sk_storage_tracing.c +++ b/tools/testing/selftests/bpf/prog_tests/sk_storage_tracing.c @@ -105,7 +105,7 @@ static void do_test(void) close(listen_fd); } -void test_sk_storage_tracing(void) +void serial_test_sk_storage_tracing(void) { struct test_sk_storage_trace_itself *skel_itself; int err; diff --git a/tools/testing/selftests/bpf/prog_tests/skb_ctx.c b/tools/testing/selftests/bpf/prog_tests/skb_ctx.c index 23915be617..b5319ba2ee 100644 --- a/tools/testing/selftests/bpf/prog_tests/skb_ctx.c +++ b/tools/testing/selftests/bpf/prog_tests/skb_ctx.c @@ -11,12 +11,14 @@ void test_skb_ctx(void) .cb[3] = 4, .cb[4] = 5, .priority = 6, + .ingress_ifindex = 11, .ifindex = 1, .tstamp = 7, .wire_len = 100, .gso_segs = 8, .mark = 9, .gso_size = 10, + .hwtstamp = 11, }; struct bpf_prog_test_run_attr tattr = { .data_in = &pkt_v4, @@ -30,7 +32,7 @@ void test_skb_ctx(void) int err; int i; - err = bpf_prog_load("./test_skb_ctx.o", BPF_PROG_TYPE_SCHED_CLS, &obj, + err = bpf_prog_test_load("./test_skb_ctx.o", BPF_PROG_TYPE_SCHED_CLS, &obj, &tattr.prog_fd); if (CHECK_ATTR(err, "load", "err %d errno %d\n", err, errno)) return; @@ -97,6 +99,10 @@ void test_skb_ctx(void) "ctx_out_ifindex", "skb->ifindex == %d, expected %d\n", skb.ifindex, 1); + CHECK_ATTR(skb.ingress_ifindex != 11, + "ctx_out_ingress_ifindex", + "skb->ingress_ifindex == %d, expected %d\n", + skb.ingress_ifindex, 11); CHECK_ATTR(skb.tstamp != 8, "ctx_out_tstamp", "skb->tstamp == %lld, expected %d\n", diff --git a/tools/testing/selftests/bpf/prog_tests/skb_helpers.c b/tools/testing/selftests/bpf/prog_tests/skb_helpers.c index f302ad84a2..6f802a1c08 100644 --- a/tools/testing/selftests/bpf/prog_tests/skb_helpers.c +++ b/tools/testing/selftests/bpf/prog_tests/skb_helpers.c @@ -20,7 +20,7 @@ void test_skb_helpers(void) struct bpf_object *obj; int err; - err = bpf_prog_load("./test_skb_helpers.o", BPF_PROG_TYPE_SCHED_CLS, &obj, + err = bpf_prog_test_load("./test_skb_helpers.o", BPF_PROG_TYPE_SCHED_CLS, &obj, &tattr.prog_fd); if (CHECK_ATTR(err, "load", "err %d errno %d\n", err, errno)) return; diff --git a/tools/testing/selftests/bpf/prog_tests/skeleton.c b/tools/testing/selftests/bpf/prog_tests/skeleton.c index f6f130c99b..180afd632f 100644 --- a/tools/testing/selftests/bpf/prog_tests/skeleton.c +++ b/tools/testing/selftests/bpf/prog_tests/skeleton.c @@ -16,8 +16,13 @@ void test_skeleton(void) struct test_skeleton* skel; struct test_skeleton__bss *bss; struct test_skeleton__data *data; + struct test_skeleton__data_dyn *data_dyn; struct test_skeleton__rodata *rodata; + struct test_skeleton__rodata_dyn *rodata_dyn; struct test_skeleton__kconfig *kcfg; + const void *elf_bytes; + size_t elf_bytes_sz = 0; + int i; skel = test_skeleton__open(); if (CHECK(!skel, "skel_open", "failed to open skeleton\n")) @@ -28,7 +33,12 @@ void test_skeleton(void) bss = skel->bss; data = skel->data; + data_dyn = skel->data_dyn; rodata = skel->rodata; + rodata_dyn = skel->rodata_dyn; + + ASSERT_STREQ(bpf_map__name(skel->maps.rodata_dyn), ".rodata.dyn", "rodata_dyn_name"); + ASSERT_STREQ(bpf_map__name(skel->maps.data_dyn), ".data.dyn", "data_dyn_name"); /* validate values are pre-initialized correctly */ CHECK(data->in1 != -1, "in1", "got %d != exp %d\n", data->in1, -1); @@ -44,6 +54,12 @@ void test_skeleton(void) CHECK(rodata->in.in6 != 0, "in6", "got %d != exp %d\n", rodata->in.in6, 0); CHECK(bss->out6 != 0, "out6", "got %d != exp %d\n", bss->out6, 0); + ASSERT_EQ(rodata_dyn->in_dynarr_sz, 0, "in_dynarr_sz"); + for (i = 0; i < 4; i++) + ASSERT_EQ(rodata_dyn->in_dynarr[i], -(i + 1), "in_dynarr"); + for (i = 0; i < 4; i++) + ASSERT_EQ(data_dyn->out_dynarr[i], i + 1, "out_dynarr"); + /* validate we can pre-setup global variables, even in .bss */ data->in1 = 10; data->in2 = 11; @@ -51,6 +67,10 @@ void test_skeleton(void) bss->in4 = 13; rodata->in.in6 = 14; + rodata_dyn->in_dynarr_sz = 4; + for (i = 0; i < 4; i++) + rodata_dyn->in_dynarr[i] = i + 10; + err = test_skeleton__load(skel); if (CHECK(err, "skel_load", "failed to load skeleton: %d\n", err)) goto cleanup; @@ -62,6 +82,10 @@ void test_skeleton(void) CHECK(bss->in4 != 13, "in4", "got %lld != exp %lld\n", bss->in4, 13LL); CHECK(rodata->in.in6 != 14, "in6", "got %d != exp %d\n", rodata->in.in6, 14); + ASSERT_EQ(rodata_dyn->in_dynarr_sz, 4, "in_dynarr_sz"); + for (i = 0; i < 4; i++) + ASSERT_EQ(rodata_dyn->in_dynarr[i], i + 10, "in_dynarr"); + /* now set new values and attach to get them into outX variables */ data->in1 = 1; data->in2 = 2; @@ -71,6 +95,8 @@ void test_skeleton(void) bss->in5.b = 6; kcfg = skel->kconfig; + skel->data_read_mostly->read_mostly_var = 123; + err = test_skeleton__attach(skel); if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err)) goto cleanup; @@ -91,6 +117,15 @@ void test_skeleton(void) CHECK(bss->kern_ver != kcfg->LINUX_KERNEL_VERSION, "ext2", "got %d != exp %d\n", bss->kern_ver, kcfg->LINUX_KERNEL_VERSION); + for (i = 0; i < 4; i++) + ASSERT_EQ(data_dyn->out_dynarr[i], i + 10, "out_dynarr"); + + ASSERT_EQ(skel->bss->out_mostly_var, 123, "out_mostly_var"); + + elf_bytes = test_skeleton__elf_bytes(&elf_bytes_sz); + ASSERT_OK_PTR(elf_bytes, "elf_bytes"); + ASSERT_GE(elf_bytes_sz, 0, "elf_bytes_sz"); + cleanup: test_skeleton__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/snprintf.c b/tools/testing/selftests/bpf/prog_tests/snprintf.c index 8fd1b4b29a..394ebfc3bb 100644 --- a/tools/testing/selftests/bpf/prog_tests/snprintf.c +++ b/tools/testing/selftests/bpf/prog_tests/snprintf.c @@ -33,7 +33,7 @@ #define EXP_NO_BUF_RET 29 -void test_snprintf_positive(void) +static void test_snprintf_positive(void) { char exp_addr_out[] = EXP_ADDR_OUT; char exp_sym_out[] = EXP_SYM_OUT; @@ -103,7 +103,7 @@ static int load_single_snprintf(char *fmt) return ret; } -void test_snprintf_negative(void) +static void test_snprintf_negative(void) { ASSERT_OK(load_single_snprintf("valid %d"), "valid usage"); diff --git a/tools/testing/selftests/bpf/prog_tests/snprintf_btf.c b/tools/testing/selftests/bpf/prog_tests/snprintf_btf.c index 76e1f5fe18..dd41b826be 100644 --- a/tools/testing/selftests/bpf/prog_tests/snprintf_btf.c +++ b/tools/testing/selftests/bpf/prog_tests/snprintf_btf.c @@ -6,7 +6,7 @@ /* Demonstrate that bpf_snprintf_btf succeeds and that various data types * are formatted correctly. */ -void test_snprintf_btf(void) +void serial_test_snprintf_btf(void) { struct netif_receive_skb *skel; struct netif_receive_skb__bss *bss; diff --git a/tools/testing/selftests/bpf/prog_tests/sock_fields.c b/tools/testing/selftests/bpf/prog_tests/sock_fields.c index 577d619fb0..9fc040eaa4 100644 --- a/tools/testing/selftests/bpf/prog_tests/sock_fields.c +++ b/tools/testing/selftests/bpf/prog_tests/sock_fields.c @@ -15,7 +15,6 @@ #include "network_helpers.h" #include "cgroup_helpers.h" #include "test_progs.h" -#include "bpf_rlimit.h" #include "test_sock_fields.skel.h" enum bpf_linum_array_idx { @@ -329,7 +328,7 @@ static void test(void) close(listen_fd); } -void test_sock_fields(void) +void serial_test_sock_fields(void) { struct bpf_link *egress_link = NULL, *ingress_link = NULL; int parent_cg_fd = -1, child_cg_fd = -1; diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c index 1352ec1041..85db0f4cdd 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c @@ -91,9 +91,9 @@ static void test_sockmap_create_update_free(enum bpf_map_type map_type) if (CHECK_FAIL(s < 0)) return; - map = bpf_create_map(map_type, sizeof(int), sizeof(int), 1, 0); + map = bpf_map_create(map_type, NULL, sizeof(int), sizeof(int), 1, NULL); if (CHECK_FAIL(map < 0)) { - perror("bpf_create_map"); + perror("bpf_cmap_create"); goto out; } diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c b/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c index 7a0d64fdc1..af293ea154 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c @@ -97,7 +97,7 @@ static void run_tests(int family, enum bpf_map_type map_type) char test_name[MAX_TEST_NAME]; int map; - map = bpf_create_map(map_type, sizeof(int), sizeof(int), 1, 0); + map = bpf_map_create(map_type, NULL, sizeof(int), sizeof(int), 1, NULL); if (CHECK_FAIL(map < 0)) { perror("bpf_map_create"); return; diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c index d88bb65b74..7e21bfab63 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c @@ -502,8 +502,8 @@ static void test_lookup_32_bit_value(int family, int sotype, int mapfd) if (s < 0) return; - mapfd = bpf_create_map(BPF_MAP_TYPE_SOCKMAP, sizeof(key), - sizeof(value32), 1, 0); + mapfd = bpf_map_create(BPF_MAP_TYPE_SOCKMAP, NULL, sizeof(key), + sizeof(value32), 1, NULL); if (mapfd < 0) { FAIL_ERRNO("map_create"); goto close; @@ -2002,7 +2002,7 @@ static void run_tests(struct test_sockmap_listen *skel, struct bpf_map *map, test_udp_unix_redir(skel, map, family); } -void test_sockmap_listen(void) +void serial_test_sockmap_listen(void) { struct test_sockmap_listen *skel; diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt.c b/tools/testing/selftests/bpf/prog_tests/sockopt.c index 3e8517a839..cd09f4c7dd 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockopt.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt.c @@ -852,22 +852,21 @@ static struct sockopt_test { static int load_prog(const struct bpf_insn *insns, enum bpf_attach_type expected_attach_type) { - struct bpf_load_program_attr attr = { - .prog_type = BPF_PROG_TYPE_CGROUP_SOCKOPT, + LIBBPF_OPTS(bpf_prog_load_opts, opts, .expected_attach_type = expected_attach_type, - .insns = insns, - .license = "GPL", .log_level = 2, - }; - int fd; + .log_buf = bpf_log_buf, + .log_size = sizeof(bpf_log_buf), + ); + int fd, insns_cnt = 0; for (; - insns[attr.insns_cnt].code != (BPF_JMP | BPF_EXIT); - attr.insns_cnt++) { + insns[insns_cnt].code != (BPF_JMP | BPF_EXIT); + insns_cnt++) { } - attr.insns_cnt++; + insns_cnt++; - fd = bpf_load_program_xattr(&attr, bpf_log_buf, sizeof(bpf_log_buf)); + fd = bpf_prog_load(BPF_PROG_TYPE_CGROUP_SOCKOPT, NULL, "GPL", insns, insns_cnt, &opts); if (verbose && fd < 0) fprintf(stderr, "%s\n", bpf_log_buf); diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c b/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c index 86f97681ad..8ed78a9383 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c @@ -136,7 +136,8 @@ static int start_server(void) return fd; } -static int prog_attach(struct bpf_object *obj, int cgroup_fd, const char *title) +static int prog_attach(struct bpf_object *obj, int cgroup_fd, const char *title, + const char *prog_name) { enum bpf_attach_type attach_type; enum bpf_prog_type prog_type; @@ -145,20 +146,20 @@ static int prog_attach(struct bpf_object *obj, int cgroup_fd, const char *title) err = libbpf_prog_type_by_name(title, &prog_type, &attach_type); if (err) { - log_err("Failed to deduct types for %s BPF program", title); + log_err("Failed to deduct types for %s BPF program", prog_name); return -1; } - prog = bpf_object__find_program_by_title(obj, title); + prog = bpf_object__find_program_by_name(obj, prog_name); if (!prog) { - log_err("Failed to find %s BPF program", title); + log_err("Failed to find %s BPF program", prog_name); return -1; } err = bpf_prog_attach(bpf_program__fd(prog), cgroup_fd, attach_type, 0); if (err) { - log_err("Failed to attach %s BPF program", title); + log_err("Failed to attach %s BPF program", prog_name); return -1; } @@ -167,25 +168,25 @@ static int prog_attach(struct bpf_object *obj, int cgroup_fd, const char *title) static void run_test(int cgroup_fd) { - struct bpf_prog_load_attr attr = { - .file = "./sockopt_inherit.o", - }; int server_fd = -1, client_fd; struct bpf_object *obj; void *server_err; pthread_t tid; - int ignored; int err; - err = bpf_prog_load_xattr(&attr, &obj, &ignored); - if (CHECK_FAIL(err)) + obj = bpf_object__open_file("sockopt_inherit.o", NULL); + if (!ASSERT_OK_PTR(obj, "obj_open")) return; - err = prog_attach(obj, cgroup_fd, "cgroup/getsockopt"); + err = bpf_object__load(obj); + if (!ASSERT_OK(err, "obj_load")) + goto close_bpf_object; + + err = prog_attach(obj, cgroup_fd, "cgroup/getsockopt", "_getsockopt"); if (CHECK_FAIL(err)) goto close_bpf_object; - err = prog_attach(obj, cgroup_fd, "cgroup/setsockopt"); + err = prog_attach(obj, cgroup_fd, "cgroup/setsockopt", "_setsockopt"); if (CHECK_FAIL(err)) goto close_bpf_object; diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c b/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c index 51fac975b3..abce12ddcc 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c @@ -2,7 +2,7 @@ #include #include "cgroup_helpers.h" -static int prog_attach(struct bpf_object *obj, int cgroup_fd, const char *title) +static int prog_attach(struct bpf_object *obj, int cgroup_fd, const char *title, const char *name) { enum bpf_attach_type attach_type; enum bpf_prog_type prog_type; @@ -15,23 +15,23 @@ static int prog_attach(struct bpf_object *obj, int cgroup_fd, const char *title) return -1; } - prog = bpf_object__find_program_by_title(obj, title); + prog = bpf_object__find_program_by_name(obj, name); if (!prog) { - log_err("Failed to find %s BPF program", title); + log_err("Failed to find %s BPF program", name); return -1; } err = bpf_prog_attach(bpf_program__fd(prog), cgroup_fd, attach_type, BPF_F_ALLOW_MULTI); if (err) { - log_err("Failed to attach %s BPF program", title); + log_err("Failed to attach %s BPF program", name); return -1; } return 0; } -static int prog_detach(struct bpf_object *obj, int cgroup_fd, const char *title) +static int prog_detach(struct bpf_object *obj, int cgroup_fd, const char *title, const char *name) { enum bpf_attach_type attach_type; enum bpf_prog_type prog_type; @@ -42,7 +42,7 @@ static int prog_detach(struct bpf_object *obj, int cgroup_fd, const char *title) if (err) return -1; - prog = bpf_object__find_program_by_title(obj, title); + prog = bpf_object__find_program_by_name(obj, name); if (!prog) return -1; @@ -89,7 +89,7 @@ static int run_getsockopt_test(struct bpf_object *obj, int cg_parent, * - child: 0x80 -> 0x90 */ - err = prog_attach(obj, cg_child, "cgroup/getsockopt/child"); + err = prog_attach(obj, cg_child, "cgroup/getsockopt", "_getsockopt_child"); if (err) goto detach; @@ -113,7 +113,7 @@ static int run_getsockopt_test(struct bpf_object *obj, int cg_parent, * - parent: 0x90 -> 0xA0 */ - err = prog_attach(obj, cg_parent, "cgroup/getsockopt/parent"); + err = prog_attach(obj, cg_parent, "cgroup/getsockopt", "_getsockopt_parent"); if (err) goto detach; @@ -157,7 +157,7 @@ static int run_getsockopt_test(struct bpf_object *obj, int cg_parent, * - parent: unexpected 0x40, EPERM */ - err = prog_detach(obj, cg_child, "cgroup/getsockopt/child"); + err = prog_detach(obj, cg_child, "cgroup/getsockopt", "_getsockopt_child"); if (err) { log_err("Failed to detach child program"); goto detach; @@ -198,8 +198,8 @@ static int run_getsockopt_test(struct bpf_object *obj, int cg_parent, } detach: - prog_detach(obj, cg_child, "cgroup/getsockopt/child"); - prog_detach(obj, cg_parent, "cgroup/getsockopt/parent"); + prog_detach(obj, cg_child, "cgroup/getsockopt", "_getsockopt_child"); + prog_detach(obj, cg_parent, "cgroup/getsockopt", "_getsockopt_parent"); return err; } @@ -236,7 +236,7 @@ static int run_setsockopt_test(struct bpf_object *obj, int cg_parent, /* Attach child program and make sure it adds 0x10. */ - err = prog_attach(obj, cg_child, "cgroup/setsockopt"); + err = prog_attach(obj, cg_child, "cgroup/setsockopt", "_setsockopt"); if (err) goto detach; @@ -263,7 +263,7 @@ static int run_setsockopt_test(struct bpf_object *obj, int cg_parent, /* Attach parent program and make sure it adds another 0x10. */ - err = prog_attach(obj, cg_parent, "cgroup/setsockopt"); + err = prog_attach(obj, cg_parent, "cgroup/setsockopt", "_setsockopt"); if (err) goto detach; @@ -289,22 +289,18 @@ static int run_setsockopt_test(struct bpf_object *obj, int cg_parent, } detach: - prog_detach(obj, cg_child, "cgroup/setsockopt"); - prog_detach(obj, cg_parent, "cgroup/setsockopt"); + prog_detach(obj, cg_child, "cgroup/setsockopt", "_setsockopt"); + prog_detach(obj, cg_parent, "cgroup/setsockopt", "_setsockopt"); return err; } void test_sockopt_multi(void) { - struct bpf_prog_load_attr attr = { - .file = "./sockopt_multi.o", - }; int cg_parent = -1, cg_child = -1; struct bpf_object *obj = NULL; int sock_fd = -1; int err = -1; - int ignored; cg_parent = test__join_cgroup("/parent"); if (CHECK_FAIL(cg_parent < 0)) @@ -314,8 +310,12 @@ void test_sockopt_multi(void) if (CHECK_FAIL(cg_child < 0)) goto out; - err = bpf_prog_load_xattr(&attr, &obj, &ignored); - if (CHECK_FAIL(err)) + obj = bpf_object__open_file("sockopt_multi.o", NULL); + if (!ASSERT_OK_PTR(obj, "obj_load")) + goto out; + + err = bpf_object__load(obj); + if (!ASSERT_OK(err, "obj_load")) goto out; sock_fd = socket(AF_INET, SOCK_STREAM, 0); diff --git a/tools/testing/selftests/bpf/prog_tests/spinlock.c b/tools/testing/selftests/bpf/prog_tests/spinlock.c index 7577a77a4c..6307f5d2b4 100644 --- a/tools/testing/selftests/bpf/prog_tests/spinlock.c +++ b/tools/testing/selftests/bpf/prog_tests/spinlock.c @@ -24,9 +24,9 @@ void test_spinlock(void) int err = 0, i; void *ret; - err = bpf_prog_load(file, BPF_PROG_TYPE_CGROUP_SKB, &obj, &prog_fd); + err = bpf_prog_test_load(file, BPF_PROG_TYPE_CGROUP_SKB, &obj, &prog_fd); if (CHECK_FAIL(err)) { - printf("test_spin_lock:bpf_prog_load errno %d\n", errno); + printf("test_spin_lock:bpf_prog_test_load errno %d\n", errno); goto close_prog; } for (i = 0; i < 4; i++) diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_map.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_map.c index 04b476bd62..313f0a6623 100644 --- a/tools/testing/selftests/bpf/prog_tests/stacktrace_map.c +++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_map.c @@ -4,7 +4,7 @@ void test_stacktrace_map(void) { int control_map_fd, stackid_hmap_fd, stackmap_fd, stack_amap_fd; - const char *prog_name = "tracepoint/sched/sched_switch"; + const char *prog_name = "oncpu"; int err, prog_fd, stack_trace_len; const char *file = "./test_stacktrace_map.o"; __u32 key, val, duration = 0; @@ -12,11 +12,11 @@ void test_stacktrace_map(void) struct bpf_object *obj; struct bpf_link *link; - err = bpf_prog_load(file, BPF_PROG_TYPE_TRACEPOINT, &obj, &prog_fd); + err = bpf_prog_test_load(file, BPF_PROG_TYPE_TRACEPOINT, &obj, &prog_fd); if (CHECK(err, "prog_load", "err %d errno %d\n", err, errno)) return; - prog = bpf_object__find_program_by_title(obj, prog_name); + prog = bpf_object__find_program_by_name(obj, prog_name); if (CHECK(!prog, "find_prog", "prog '%s' not found\n", prog_name)) goto close_prog; diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_map_raw_tp.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_map_raw_tp.c index 4fd30bb651..1cb8dd36bd 100644 --- a/tools/testing/selftests/bpf/prog_tests/stacktrace_map_raw_tp.c +++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_map_raw_tp.c @@ -3,7 +3,7 @@ void test_stacktrace_map_raw_tp(void) { - const char *prog_name = "tracepoint/sched/sched_switch"; + const char *prog_name = "oncpu"; int control_map_fd, stackid_hmap_fd, stackmap_fd; const char *file = "./test_stacktrace_map.o"; __u32 key, val, duration = 0; @@ -12,11 +12,11 @@ void test_stacktrace_map_raw_tp(void) struct bpf_object *obj; struct bpf_link *link = NULL; - err = bpf_prog_load(file, BPF_PROG_TYPE_RAW_TRACEPOINT, &obj, &prog_fd); + err = bpf_prog_test_load(file, BPF_PROG_TYPE_RAW_TRACEPOINT, &obj, &prog_fd); if (CHECK(err, "prog_load raw tp", "err %d errno %d\n", err, errno)) return; - prog = bpf_object__find_program_by_title(obj, prog_name); + prog = bpf_object__find_program_by_name(obj, prog_name); if (CHECK(!prog, "find_prog", "prog '%s' not found\n", prog_name)) goto close_prog; diff --git a/tools/testing/selftests/bpf/prog_tests/tailcalls.c b/tools/testing/selftests/bpf/prog_tests/tailcalls.c index b5940e6ca6..5dc0f425bd 100644 --- a/tools/testing/selftests/bpf/prog_tests/tailcalls.c +++ b/tools/testing/selftests/bpf/prog_tests/tailcalls.c @@ -16,12 +16,12 @@ static void test_tailcall_1(void) char prog_name[32]; char buff[128] = {}; - err = bpf_prog_load("tailcall1.o", BPF_PROG_TYPE_SCHED_CLS, &obj, + err = bpf_prog_test_load("tailcall1.o", BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); if (CHECK_FAIL(err)) return; - prog = bpf_object__find_program_by_title(obj, "classifier"); + prog = bpf_object__find_program_by_name(obj, "entry"); if (CHECK_FAIL(!prog)) goto out; @@ -38,9 +38,9 @@ static void test_tailcall_1(void) goto out; for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { - snprintf(prog_name, sizeof(prog_name), "classifier/%i", i); + snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); - prog = bpf_object__find_program_by_title(obj, prog_name); + prog = bpf_object__find_program_by_name(obj, prog_name); if (CHECK_FAIL(!prog)) goto out; @@ -70,9 +70,9 @@ static void test_tailcall_1(void) err, errno, retval); for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { - snprintf(prog_name, sizeof(prog_name), "classifier/%i", i); + snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); - prog = bpf_object__find_program_by_title(obj, prog_name); + prog = bpf_object__find_program_by_name(obj, prog_name); if (CHECK_FAIL(!prog)) goto out; @@ -92,9 +92,9 @@ static void test_tailcall_1(void) for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { j = bpf_map__def(prog_array)->max_entries - 1 - i; - snprintf(prog_name, sizeof(prog_name), "classifier/%i", j); + snprintf(prog_name, sizeof(prog_name), "classifier_%d", j); - prog = bpf_object__find_program_by_title(obj, prog_name); + prog = bpf_object__find_program_by_name(obj, prog_name); if (CHECK_FAIL(!prog)) goto out; @@ -154,12 +154,12 @@ static void test_tailcall_2(void) char prog_name[32]; char buff[128] = {}; - err = bpf_prog_load("tailcall2.o", BPF_PROG_TYPE_SCHED_CLS, &obj, + err = bpf_prog_test_load("tailcall2.o", BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); if (CHECK_FAIL(err)) return; - prog = bpf_object__find_program_by_title(obj, "classifier"); + prog = bpf_object__find_program_by_name(obj, "entry"); if (CHECK_FAIL(!prog)) goto out; @@ -176,9 +176,9 @@ static void test_tailcall_2(void) goto out; for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { - snprintf(prog_name, sizeof(prog_name), "classifier/%i", i); + snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); - prog = bpf_object__find_program_by_title(obj, prog_name); + prog = bpf_object__find_program_by_name(obj, prog_name); if (CHECK_FAIL(!prog)) goto out; @@ -219,10 +219,7 @@ static void test_tailcall_2(void) bpf_object__close(obj); } -/* test_tailcall_3 checks that the count value of the tail call limit - * enforcement matches with expectations. - */ -static void test_tailcall_3(void) +static void test_tailcall_count(const char *which) { int err, map_fd, prog_fd, main_fd, data_fd, i, val; struct bpf_map *prog_array, *data_map; @@ -231,12 +228,12 @@ static void test_tailcall_3(void) __u32 retval, duration; char buff[128] = {}; - err = bpf_prog_load("tailcall3.o", BPF_PROG_TYPE_SCHED_CLS, &obj, + err = bpf_prog_test_load(which, BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); if (CHECK_FAIL(err)) return; - prog = bpf_object__find_program_by_title(obj, "classifier"); + prog = bpf_object__find_program_by_name(obj, "entry"); if (CHECK_FAIL(!prog)) goto out; @@ -252,7 +249,7 @@ static void test_tailcall_3(void) if (CHECK_FAIL(map_fd < 0)) goto out; - prog = bpf_object__find_program_by_title(obj, "classifier/0"); + prog = bpf_object__find_program_by_name(obj, "classifier_0"); if (CHECK_FAIL(!prog)) goto out; @@ -296,6 +293,22 @@ static void test_tailcall_3(void) bpf_object__close(obj); } +/* test_tailcall_3 checks that the count value of the tail call limit + * enforcement matches with expectations. JIT uses direct jump. + */ +static void test_tailcall_3(void) +{ + test_tailcall_count("tailcall3.o"); +} + +/* test_tailcall_6 checks that the count value of the tail call limit + * enforcement matches with expectations. JIT uses indirect jump. + */ +static void test_tailcall_6(void) +{ + test_tailcall_count("tailcall6.o"); +} + /* test_tailcall_4 checks that the kernel properly selects indirect jump * for the case where the key is not known. Latter is passed via global * data to select different targets we can compare return value of. @@ -311,12 +324,12 @@ static void test_tailcall_4(void) char buff[128] = {}; char prog_name[32]; - err = bpf_prog_load("tailcall4.o", BPF_PROG_TYPE_SCHED_CLS, &obj, + err = bpf_prog_test_load("tailcall4.o", BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); if (CHECK_FAIL(err)) return; - prog = bpf_object__find_program_by_title(obj, "classifier"); + prog = bpf_object__find_program_by_name(obj, "entry"); if (CHECK_FAIL(!prog)) goto out; @@ -341,9 +354,9 @@ static void test_tailcall_4(void) return; for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { - snprintf(prog_name, sizeof(prog_name), "classifier/%i", i); + snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); - prog = bpf_object__find_program_by_title(obj, prog_name); + prog = bpf_object__find_program_by_name(obj, prog_name); if (CHECK_FAIL(!prog)) goto out; @@ -399,12 +412,12 @@ static void test_tailcall_5(void) char buff[128] = {}; char prog_name[32]; - err = bpf_prog_load("tailcall5.o", BPF_PROG_TYPE_SCHED_CLS, &obj, + err = bpf_prog_test_load("tailcall5.o", BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); if (CHECK_FAIL(err)) return; - prog = bpf_object__find_program_by_title(obj, "classifier"); + prog = bpf_object__find_program_by_name(obj, "entry"); if (CHECK_FAIL(!prog)) goto out; @@ -429,9 +442,9 @@ static void test_tailcall_5(void) return; for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { - snprintf(prog_name, sizeof(prog_name), "classifier/%i", i); + snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); - prog = bpf_object__find_program_by_title(obj, prog_name); + prog = bpf_object__find_program_by_name(obj, prog_name); if (CHECK_FAIL(!prog)) goto out; @@ -485,12 +498,12 @@ static void test_tailcall_bpf2bpf_1(void) __u32 retval, duration; char prog_name[32]; - err = bpf_prog_load("tailcall_bpf2bpf1.o", BPF_PROG_TYPE_SCHED_CLS, + err = bpf_prog_test_load("tailcall_bpf2bpf1.o", BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); if (CHECK_FAIL(err)) return; - prog = bpf_object__find_program_by_title(obj, "classifier"); + prog = bpf_object__find_program_by_name(obj, "entry"); if (CHECK_FAIL(!prog)) goto out; @@ -508,9 +521,9 @@ static void test_tailcall_bpf2bpf_1(void) /* nop -> jmp */ for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { - snprintf(prog_name, sizeof(prog_name), "classifier/%i", i); + snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); - prog = bpf_object__find_program_by_title(obj, prog_name); + prog = bpf_object__find_program_by_name(obj, prog_name); if (CHECK_FAIL(!prog)) goto out; @@ -569,12 +582,12 @@ static void test_tailcall_bpf2bpf_2(void) __u32 retval, duration; char buff[128] = {}; - err = bpf_prog_load("tailcall_bpf2bpf2.o", BPF_PROG_TYPE_SCHED_CLS, + err = bpf_prog_test_load("tailcall_bpf2bpf2.o", BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); if (CHECK_FAIL(err)) return; - prog = bpf_object__find_program_by_title(obj, "classifier"); + prog = bpf_object__find_program_by_name(obj, "entry"); if (CHECK_FAIL(!prog)) goto out; @@ -590,7 +603,7 @@ static void test_tailcall_bpf2bpf_2(void) if (CHECK_FAIL(map_fd < 0)) goto out; - prog = bpf_object__find_program_by_title(obj, "classifier/0"); + prog = bpf_object__find_program_by_name(obj, "classifier_0"); if (CHECK_FAIL(!prog)) goto out; @@ -647,12 +660,12 @@ static void test_tailcall_bpf2bpf_3(void) __u32 retval, duration; char prog_name[32]; - err = bpf_prog_load("tailcall_bpf2bpf3.o", BPF_PROG_TYPE_SCHED_CLS, + err = bpf_prog_test_load("tailcall_bpf2bpf3.o", BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); if (CHECK_FAIL(err)) return; - prog = bpf_object__find_program_by_title(obj, "classifier"); + prog = bpf_object__find_program_by_name(obj, "entry"); if (CHECK_FAIL(!prog)) goto out; @@ -669,9 +682,9 @@ static void test_tailcall_bpf2bpf_3(void) goto out; for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { - snprintf(prog_name, sizeof(prog_name), "classifier/%i", i); + snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); - prog = bpf_object__find_program_by_title(obj, prog_name); + prog = bpf_object__find_program_by_name(obj, prog_name); if (CHECK_FAIL(!prog)) goto out; @@ -744,12 +757,12 @@ static void test_tailcall_bpf2bpf_4(bool noise) __u32 retval, duration; char prog_name[32]; - err = bpf_prog_load("tailcall_bpf2bpf4.o", BPF_PROG_TYPE_SCHED_CLS, + err = bpf_prog_test_load("tailcall_bpf2bpf4.o", BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); if (CHECK_FAIL(err)) return; - prog = bpf_object__find_program_by_title(obj, "classifier"); + prog = bpf_object__find_program_by_name(obj, "entry"); if (CHECK_FAIL(!prog)) goto out; @@ -766,9 +779,9 @@ static void test_tailcall_bpf2bpf_4(bool noise) goto out; for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { - snprintf(prog_name, sizeof(prog_name), "classifier/%i", i); + snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); - prog = bpf_object__find_program_by_title(obj, prog_name); + prog = bpf_object__find_program_by_name(obj, prog_name); if (CHECK_FAIL(!prog)) goto out; @@ -822,6 +835,8 @@ void test_tailcalls(void) test_tailcall_4(); if (test__start_subtest("tailcall_5")) test_tailcall_5(); + if (test__start_subtest("tailcall_6")) + test_tailcall_6(); if (test__start_subtest("tailcall_bpf2bpf_1")) test_tailcall_bpf2bpf_1(); if (test__start_subtest("tailcall_bpf2bpf_2")) diff --git a/tools/testing/selftests/bpf/prog_tests/task_fd_query_rawtp.c b/tools/testing/selftests/bpf/prog_tests/task_fd_query_rawtp.c index 1bdc1d86a5..17947c9e1d 100644 --- a/tools/testing/selftests/bpf/prog_tests/task_fd_query_rawtp.c +++ b/tools/testing/selftests/bpf/prog_tests/task_fd_query_rawtp.c @@ -11,7 +11,7 @@ void test_task_fd_query_rawtp(void) __u32 duration = 0; char buf[256]; - err = bpf_prog_load(file, BPF_PROG_TYPE_RAW_TRACEPOINT, &obj, &prog_fd); + err = bpf_prog_test_load(file, BPF_PROG_TYPE_RAW_TRACEPOINT, &obj, &prog_fd); if (CHECK(err, "prog_load raw tp", "err %d errno %d\n", err, errno)) return; diff --git a/tools/testing/selftests/bpf/prog_tests/task_fd_query_tp.c b/tools/testing/selftests/bpf/prog_tests/task_fd_query_tp.c index 3f131b8fe3..c2a98a7a8d 100644 --- a/tools/testing/selftests/bpf/prog_tests/task_fd_query_tp.c +++ b/tools/testing/selftests/bpf/prog_tests/task_fd_query_tp.c @@ -13,8 +13,8 @@ static void test_task_fd_query_tp_core(const char *probe_name, __u32 duration = 0; char buf[256]; - err = bpf_prog_load(file, BPF_PROG_TYPE_TRACEPOINT, &obj, &prog_fd); - if (CHECK(err, "bpf_prog_load", "err %d errno %d\n", err, errno)) + err = bpf_prog_test_load(file, BPF_PROG_TYPE_TRACEPOINT, &obj, &prog_fd); + if (CHECK(err, "bpf_prog_test_load", "err %d errno %d\n", err, errno)) goto close_prog; snprintf(buf, sizeof(buf), diff --git a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c index 47e3159729..c2426df58e 100644 --- a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c +++ b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c @@ -183,6 +183,18 @@ static int netns_setup_namespaces(const char *verb) return 0; } +static void netns_setup_namespaces_nofail(const char *verb) +{ + const char * const *ns = namespaces; + char cmd[128]; + + while (*ns) { + snprintf(cmd, sizeof(cmd), "ip netns %s %s > /dev/null 2>&1", verb, *ns); + system(cmd); + ns++; + } +} + struct netns_setup_result { int ifindex_veth_src_fwd; int ifindex_veth_dst_fwd; @@ -640,7 +652,7 @@ static void test_tc_redirect_peer_l3(struct netns_setup_result *setup_result) struct nstoken *nstoken = NULL; int err; int tunnel_pid = -1; - int src_fd, target_fd; + int src_fd, target_fd = -1; int ifindex; /* Start a L3 TUN/TAP tunnel between the src and dst namespaces. @@ -769,6 +781,8 @@ static void test_tc_redirect_peer_l3(struct netns_setup_result *setup_result) static void *test_tc_redirect_run_tests(void *arg) { + netns_setup_namespaces_nofail("delete"); + RUN_TEST(tc_redirect_peer); RUN_TEST(tc_redirect_peer_l3); RUN_TEST(tc_redirect_neigh); @@ -776,7 +790,7 @@ static void *test_tc_redirect_run_tests(void *arg) return NULL; } -void test_tc_redirect(void) +void serial_test_tc_redirect(void) { pthread_t test_thread; int err; diff --git a/tools/testing/selftests/bpf/prog_tests/tcp_estats.c b/tools/testing/selftests/bpf/prog_tests/tcp_estats.c index 594307dffd..11bf755be4 100644 --- a/tools/testing/selftests/bpf/prog_tests/tcp_estats.c +++ b/tools/testing/selftests/bpf/prog_tests/tcp_estats.c @@ -8,7 +8,7 @@ void test_tcp_estats(void) struct bpf_object *obj; __u32 duration = 0; - err = bpf_prog_load(file, BPF_PROG_TYPE_TRACEPOINT, &obj, &prog_fd); + err = bpf_prog_test_load(file, BPF_PROG_TYPE_TRACEPOINT, &obj, &prog_fd); CHECK(err, "", "err %d errno %d\n", err, errno); if (err) return; diff --git a/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c b/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c index d207e968e6..96ff2c20af 100644 --- a/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c +++ b/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c @@ -2,6 +2,7 @@ #include #include "cgroup_helpers.h" #include "network_helpers.h" +#include "tcp_rtt.skel.h" struct tcp_rtt_storage { __u32 invoked; @@ -91,26 +92,18 @@ static int verify_sk(int map_fd, int client_fd, const char *msg, __u32 invoked, static int run_test(int cgroup_fd, int server_fd) { - struct bpf_prog_load_attr attr = { - .prog_type = BPF_PROG_TYPE_SOCK_OPS, - .file = "./tcp_rtt.o", - .expected_attach_type = BPF_CGROUP_SOCK_OPS, - }; - struct bpf_object *obj; - struct bpf_map *map; + struct tcp_rtt *skel; int client_fd; int prog_fd; int map_fd; int err; - err = bpf_prog_load_xattr(&attr, &obj, &prog_fd); - if (err) { - log_err("Failed to load BPF object"); + skel = tcp_rtt__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_open_load")) return -1; - } - map = bpf_map__next(NULL, obj); - map_fd = bpf_map__fd(map); + map_fd = bpf_map__fd(skel->maps.socket_storage_map); + prog_fd = bpf_program__fd(skel->progs._sockops); err = bpf_prog_attach(prog_fd, cgroup_fd, BPF_CGROUP_SOCK_OPS, 0); if (err) { @@ -149,7 +142,7 @@ static int run_test(int cgroup_fd, int server_fd) close(client_fd); close_bpf_object: - bpf_object__close(obj); + tcp_rtt__destroy(skel); return err; } diff --git a/tools/testing/selftests/bpf/prog_tests/test_bpffs.c b/tools/testing/selftests/bpf/prog_tests/test_bpffs.c index 172c999e52..214d9f4a94 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_bpffs.c +++ b/tools/testing/selftests/bpf/prog_tests/test_bpffs.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2020 Facebook */ #define _GNU_SOURCE +#include #include #include #include @@ -18,55 +19,119 @@ static int read_iter(char *file) fd = open(file, 0); if (fd < 0) return -1; - while ((len = read(fd, buf, sizeof(buf))) > 0) + while ((len = read(fd, buf, sizeof(buf))) > 0) { + buf[sizeof(buf) - 1] = '\0'; if (strstr(buf, "iter")) { close(fd); return 0; } + } close(fd); return -1; } static int fn(void) { - int err, duration = 0; + struct stat a, b, c; + int err, map; err = unshare(CLONE_NEWNS); - if (CHECK(err, "unshare", "failed: %d\n", errno)) + if (!ASSERT_OK(err, "unshare")) goto out; err = mount("", "/", "", MS_REC | MS_PRIVATE, NULL); - if (CHECK(err, "mount /", "failed: %d\n", errno)) + if (!ASSERT_OK(err, "mount /")) goto out; err = umount(TDIR); - if (CHECK(err, "umount " TDIR, "failed: %d\n", errno)) + if (!ASSERT_OK(err, "umount " TDIR)) goto out; err = mount("none", TDIR, "tmpfs", 0, NULL); - if (CHECK(err, "mount", "mount root failed: %d\n", errno)) + if (!ASSERT_OK(err, "mount tmpfs")) goto out; err = mkdir(TDIR "/fs1", 0777); - if (CHECK(err, "mkdir "TDIR"/fs1", "failed: %d\n", errno)) + if (!ASSERT_OK(err, "mkdir " TDIR "/fs1")) goto out; err = mkdir(TDIR "/fs2", 0777); - if (CHECK(err, "mkdir "TDIR"/fs2", "failed: %d\n", errno)) + if (!ASSERT_OK(err, "mkdir " TDIR "/fs2")) goto out; err = mount("bpf", TDIR "/fs1", "bpf", 0, NULL); - if (CHECK(err, "mount bpffs "TDIR"/fs1", "failed: %d\n", errno)) + if (!ASSERT_OK(err, "mount bpffs " TDIR "/fs1")) goto out; err = mount("bpf", TDIR "/fs2", "bpf", 0, NULL); - if (CHECK(err, "mount bpffs " TDIR "/fs2", "failed: %d\n", errno)) + if (!ASSERT_OK(err, "mount bpffs " TDIR "/fs2")) goto out; err = read_iter(TDIR "/fs1/maps.debug"); - if (CHECK(err, "reading " TDIR "/fs1/maps.debug", "failed\n")) + if (!ASSERT_OK(err, "reading " TDIR "/fs1/maps.debug")) goto out; err = read_iter(TDIR "/fs2/progs.debug"); - if (CHECK(err, "reading " TDIR "/fs2/progs.debug", "failed\n")) + if (!ASSERT_OK(err, "reading " TDIR "/fs2/progs.debug")) goto out; + + err = mkdir(TDIR "/fs1/a", 0777); + if (!ASSERT_OK(err, "creating " TDIR "/fs1/a")) + goto out; + err = mkdir(TDIR "/fs1/a/1", 0777); + if (!ASSERT_OK(err, "creating " TDIR "/fs1/a/1")) + goto out; + err = mkdir(TDIR "/fs1/b", 0777); + if (!ASSERT_OK(err, "creating " TDIR "/fs1/b")) + goto out; + + map = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, 4, 4, 1, NULL); + if (!ASSERT_GT(map, 0, "create_map(ARRAY)")) + goto out; + err = bpf_obj_pin(map, TDIR "/fs1/c"); + if (!ASSERT_OK(err, "pin map")) + goto out; + close(map); + + /* Check that RENAME_EXCHANGE works for directories. */ + err = stat(TDIR "/fs1/a", &a); + if (!ASSERT_OK(err, "stat(" TDIR "/fs1/a)")) + goto out; + err = renameat2(0, TDIR "/fs1/a", 0, TDIR "/fs1/b", RENAME_EXCHANGE); + if (!ASSERT_OK(err, "renameat2(/fs1/a, /fs1/b, RENAME_EXCHANGE)")) + goto out; + err = stat(TDIR "/fs1/b", &b); + if (!ASSERT_OK(err, "stat(" TDIR "/fs1/b)")) + goto out; + if (!ASSERT_EQ(a.st_ino, b.st_ino, "b should have a's inode")) + goto out; + err = access(TDIR "/fs1/b/1", F_OK); + if (!ASSERT_OK(err, "access(" TDIR "/fs1/b/1)")) + goto out; + + /* Check that RENAME_EXCHANGE works for mixed file types. */ + err = stat(TDIR "/fs1/c", &c); + if (!ASSERT_OK(err, "stat(" TDIR "/fs1/map)")) + goto out; + err = renameat2(0, TDIR "/fs1/c", 0, TDIR "/fs1/b", RENAME_EXCHANGE); + if (!ASSERT_OK(err, "renameat2(/fs1/c, /fs1/b, RENAME_EXCHANGE)")) + goto out; + err = stat(TDIR "/fs1/b", &b); + if (!ASSERT_OK(err, "stat(" TDIR "/fs1/b)")) + goto out; + if (!ASSERT_EQ(c.st_ino, b.st_ino, "b should have c's inode")) + goto out; + err = access(TDIR "/fs1/c/1", F_OK); + if (!ASSERT_OK(err, "access(" TDIR "/fs1/c/1)")) + goto out; + + /* Check that RENAME_NOREPLACE works. */ + err = renameat2(0, TDIR "/fs1/b", 0, TDIR "/fs1/a", RENAME_NOREPLACE); + if (!ASSERT_ERR(err, "renameat2(RENAME_NOREPLACE)")) { + err = -EINVAL; + goto out; + } + err = access(TDIR "/fs1/b", F_OK); + if (!ASSERT_OK(err, "access(" TDIR "/fs1/b)")) + goto out; + out: umount(TDIR "/fs1"); umount(TDIR "/fs2"); diff --git a/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c b/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c index 7e13129f59..509e21d5cb 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c +++ b/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c @@ -30,17 +30,29 @@ extern int extra_prog_load_log_flags; static int check_load(const char *file) { - struct bpf_prog_load_attr attr; struct bpf_object *obj = NULL; - int err, prog_fd; + struct bpf_program *prog; + int err; - memset(&attr, 0, sizeof(struct bpf_prog_load_attr)); - attr.file = file; - attr.prog_type = BPF_PROG_TYPE_UNSPEC; - attr.log_level = extra_prog_load_log_flags; - attr.prog_flags = BPF_F_TEST_RND_HI32; found = false; - err = bpf_prog_load_xattr(&attr, &obj, &prog_fd); + + obj = bpf_object__open_file(file, NULL); + err = libbpf_get_error(obj); + if (err) + return err; + + prog = bpf_object__next_program(obj, NULL); + if (!prog) { + err = -ENOENT; + goto err_out; + } + + bpf_program__set_flags(prog, BPF_F_TEST_RND_HI32); + bpf_program__set_log_level(prog, extra_prog_load_log_flags); + + err = bpf_object__load(obj); + +err_out: bpf_object__close(obj); return err; } diff --git a/tools/testing/selftests/bpf/prog_tests/test_local_storage.c b/tools/testing/selftests/bpf/prog_tests/test_local_storage.c index d2c16eaae3..26ac26a880 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_local_storage.c +++ b/tools/testing/selftests/bpf/prog_tests/test_local_storage.c @@ -28,10 +28,6 @@ static unsigned int duration; struct storage { void *inode; unsigned int value; - /* Lock ensures that spin locked versions of local stoage operations - * also work, most operations in this tests are still single threaded - */ - struct bpf_spin_lock lock; }; /* Fork and exec the provided rm binary and return the exit code of the @@ -66,27 +62,24 @@ static int run_self_unlink(int *monitored_pid, const char *rm_path) static bool check_syscall_operations(int map_fd, int obj_fd) { - struct storage val = { .value = TEST_STORAGE_VALUE, .lock = { 0 } }, - lookup_val = { .value = 0, .lock = { 0 } }; + struct storage val = { .value = TEST_STORAGE_VALUE }, + lookup_val = { .value = 0 }; int err; /* Looking up an existing element should fail initially */ - err = bpf_map_lookup_elem_flags(map_fd, &obj_fd, &lookup_val, - BPF_F_LOCK); + err = bpf_map_lookup_elem_flags(map_fd, &obj_fd, &lookup_val, 0); if (CHECK(!err || errno != ENOENT, "bpf_map_lookup_elem", "err:%d errno:%d\n", err, errno)) return false; /* Create a new element */ - err = bpf_map_update_elem(map_fd, &obj_fd, &val, - BPF_NOEXIST | BPF_F_LOCK); + err = bpf_map_update_elem(map_fd, &obj_fd, &val, BPF_NOEXIST); if (CHECK(err < 0, "bpf_map_update_elem", "err:%d errno:%d\n", err, errno)) return false; /* Lookup the newly created element */ - err = bpf_map_lookup_elem_flags(map_fd, &obj_fd, &lookup_val, - BPF_F_LOCK); + err = bpf_map_lookup_elem_flags(map_fd, &obj_fd, &lookup_val, 0); if (CHECK(err < 0, "bpf_map_lookup_elem", "err:%d errno:%d", err, errno)) return false; @@ -102,8 +95,7 @@ static bool check_syscall_operations(int map_fd, int obj_fd) return false; /* The lookup should fail, now that the element has been deleted */ - err = bpf_map_lookup_elem_flags(map_fd, &obj_fd, &lookup_val, - BPF_F_LOCK); + err = bpf_map_lookup_elem_flags(map_fd, &obj_fd, &lookup_val, 0); if (CHECK(!err || errno != ENOENT, "bpf_map_lookup_elem", "err:%d errno:%d\n", err, errno)) return false; diff --git a/tools/testing/selftests/bpf/prog_tests/test_overhead.c b/tools/testing/selftests/bpf/prog_tests/test_overhead.c index 123c68c191..05acb376f7 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_overhead.c +++ b/tools/testing/selftests/bpf/prog_tests/test_overhead.c @@ -56,11 +56,11 @@ static void setaffinity(void) void test_test_overhead(void) { - const char *kprobe_name = "kprobe/__set_task_comm"; - const char *kretprobe_name = "kretprobe/__set_task_comm"; - const char *raw_tp_name = "raw_tp/task_rename"; - const char *fentry_name = "fentry/__set_task_comm"; - const char *fexit_name = "fexit/__set_task_comm"; + const char *kprobe_name = "prog1"; + const char *kretprobe_name = "prog2"; + const char *raw_tp_name = "prog3"; + const char *fentry_name = "prog4"; + const char *fexit_name = "prog5"; const char *kprobe_func = "__set_task_comm"; struct bpf_program *kprobe_prog, *kretprobe_prog, *raw_tp_prog; struct bpf_program *fentry_prog, *fexit_prog; @@ -76,23 +76,23 @@ void test_test_overhead(void) if (!ASSERT_OK_PTR(obj, "obj_open_file")) return; - kprobe_prog = bpf_object__find_program_by_title(obj, kprobe_name); + kprobe_prog = bpf_object__find_program_by_name(obj, kprobe_name); if (CHECK(!kprobe_prog, "find_probe", "prog '%s' not found\n", kprobe_name)) goto cleanup; - kretprobe_prog = bpf_object__find_program_by_title(obj, kretprobe_name); + kretprobe_prog = bpf_object__find_program_by_name(obj, kretprobe_name); if (CHECK(!kretprobe_prog, "find_probe", "prog '%s' not found\n", kretprobe_name)) goto cleanup; - raw_tp_prog = bpf_object__find_program_by_title(obj, raw_tp_name); + raw_tp_prog = bpf_object__find_program_by_name(obj, raw_tp_name); if (CHECK(!raw_tp_prog, "find_probe", "prog '%s' not found\n", raw_tp_name)) goto cleanup; - fentry_prog = bpf_object__find_program_by_title(obj, fentry_name); + fentry_prog = bpf_object__find_program_by_name(obj, fentry_name); if (CHECK(!fentry_prog, "find_probe", "prog '%s' not found\n", fentry_name)) goto cleanup; - fexit_prog = bpf_object__find_program_by_title(obj, fexit_name); + fexit_prog = bpf_object__find_program_by_name(obj, fexit_name); if (CHECK(!fexit_prog, "find_probe", "prog '%s' not found\n", fexit_name)) goto cleanup; diff --git a/tools/testing/selftests/bpf/prog_tests/timer.c b/tools/testing/selftests/bpf/prog_tests/timer.c index 25f40e1b99..0f4e49e622 100644 --- a/tools/testing/selftests/bpf/prog_tests/timer.c +++ b/tools/testing/selftests/bpf/prog_tests/timer.c @@ -39,7 +39,8 @@ static int timer(struct timer *timer_skel) return 0; } -void test_timer(void) +/* TODO: use pid filtering */ +void serial_test_timer(void) { struct timer *timer_skel = NULL; int err; diff --git a/tools/testing/selftests/bpf/prog_tests/timer_mim.c b/tools/testing/selftests/bpf/prog_tests/timer_mim.c index ced8f6cf34..949a061786 100644 --- a/tools/testing/selftests/bpf/prog_tests/timer_mim.c +++ b/tools/testing/selftests/bpf/prog_tests/timer_mim.c @@ -52,7 +52,7 @@ static int timer_mim(struct timer_mim *timer_skel) return 0; } -void test_timer_mim(void) +void serial_test_timer_mim(void) { struct timer_mim_reject *timer_reject_skel = NULL; libbpf_print_fn_t old_print_fn = NULL; diff --git a/tools/testing/selftests/bpf/prog_tests/tp_attach_query.c b/tools/testing/selftests/bpf/prog_tests/tp_attach_query.c index fb095e5cd9..39e79291c8 100644 --- a/tools/testing/selftests/bpf/prog_tests/tp_attach_query.c +++ b/tools/testing/selftests/bpf/prog_tests/tp_attach_query.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include -void test_tp_attach_query(void) +void serial_test_tp_attach_query(void) { const int num_progs = 3; int i, j, bytes, efd, err, prog_fd[num_progs], pmu_fd[num_progs]; @@ -35,7 +35,7 @@ void test_tp_attach_query(void) query = malloc(sizeof(*query) + sizeof(__u32) * num_progs); for (i = 0; i < num_progs; i++) { - err = bpf_prog_load(file, BPF_PROG_TYPE_TRACEPOINT, &obj[i], + err = bpf_prog_test_load(file, BPF_PROG_TYPE_TRACEPOINT, &obj[i], &prog_fd[i]); if (CHECK(err, "prog_load", "err %d errno %d\n", err, errno)) goto cleanup1; diff --git a/tools/testing/selftests/bpf/prog_tests/trace_printk.c b/tools/testing/selftests/bpf/prog_tests/trace_printk.c index d39bc00feb..cade7f1231 100644 --- a/tools/testing/selftests/bpf/prog_tests/trace_printk.c +++ b/tools/testing/selftests/bpf/prog_tests/trace_printk.c @@ -8,35 +8,34 @@ #define TRACEBUF "/sys/kernel/debug/tracing/trace_pipe" #define SEARCHMSG "testing,testing" -void test_trace_printk(void) +void serial_test_trace_printk(void) { - int err, iter = 0, duration = 0, found = 0; - struct trace_printk__bss *bss; - struct trace_printk *skel; + struct trace_printk_lskel__bss *bss; + int err = 0, iter = 0, found = 0; + struct trace_printk_lskel *skel; char *buf = NULL; FILE *fp = NULL; size_t buflen; - skel = trace_printk__open(); - if (CHECK(!skel, "skel_open", "failed to open skeleton\n")) + skel = trace_printk_lskel__open(); + if (!ASSERT_OK_PTR(skel, "trace_printk__open")) return; - ASSERT_EQ(skel->rodata->fmt[0], 'T', "invalid printk fmt string"); + ASSERT_EQ(skel->rodata->fmt[0], 'T', "skel->rodata->fmt[0]"); skel->rodata->fmt[0] = 't'; - err = trace_printk__load(skel); - if (CHECK(err, "skel_load", "failed to load skeleton: %d\n", err)) + err = trace_printk_lskel__load(skel); + if (!ASSERT_OK(err, "trace_printk__load")) goto cleanup; bss = skel->bss; - err = trace_printk__attach(skel); - if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err)) + err = trace_printk_lskel__attach(skel); + if (!ASSERT_OK(err, "trace_printk__attach")) goto cleanup; fp = fopen(TRACEBUF, "r"); - if (CHECK(fp == NULL, "could not open trace buffer", - "error %d opening %s", errno, TRACEBUF)) + if (!ASSERT_OK_PTR(fp, "fopen(TRACEBUF)")) goto cleanup; /* We do not want to wait forever if this test fails... */ @@ -44,16 +43,12 @@ void test_trace_printk(void) /* wait for tracepoint to trigger */ usleep(1); - trace_printk__detach(skel); + trace_printk_lskel__detach(skel); - if (CHECK(bss->trace_printk_ran == 0, - "bpf_trace_printk never ran", - "ran == %d", bss->trace_printk_ran)) + if (!ASSERT_GT(bss->trace_printk_ran, 0, "bss->trace_printk_ran")) goto cleanup; - if (CHECK(bss->trace_printk_ret <= 0, - "bpf_trace_printk returned <= 0 value", - "got %d", bss->trace_printk_ret)) + if (!ASSERT_GT(bss->trace_printk_ret, 0, "bss->trace_printk_ret")) goto cleanup; /* verify our search string is in the trace buffer */ @@ -66,12 +61,11 @@ void test_trace_printk(void) break; } - if (CHECK(!found, "message from bpf_trace_printk not found", - "no instance of %s in %s", SEARCHMSG, TRACEBUF)) + if (!ASSERT_EQ(found, bss->trace_printk_ran, "found")) goto cleanup; cleanup: - trace_printk__destroy(skel); + trace_printk_lskel__destroy(skel); free(buf); if (fp) fclose(fp); diff --git a/tools/testing/selftests/bpf/prog_tests/trampoline_count.c b/tools/testing/selftests/bpf/prog_tests/trampoline_count.c index d7f5a931d7..9c795ee52b 100644 --- a/tools/testing/selftests/bpf/prog_tests/trampoline_count.c +++ b/tools/testing/selftests/bpf/prog_tests/trampoline_count.c @@ -35,16 +35,17 @@ static struct bpf_link *load(struct bpf_object *obj, const char *name) struct bpf_program *prog; int duration = 0; - prog = bpf_object__find_program_by_title(obj, name); + prog = bpf_object__find_program_by_name(obj, name); if (CHECK(!prog, "find_probe", "prog '%s' not found\n", name)) return ERR_PTR(-EINVAL); return bpf_program__attach_trace(prog); } -void test_trampoline_count(void) +/* TODO: use different target function to run in concurrent mode */ +void serial_test_trampoline_count(void) { - const char *fentry_name = "fentry/__set_task_comm"; - const char *fexit_name = "fexit/__set_task_comm"; + const char *fentry_name = "prog1"; + const char *fexit_name = "prog2"; const char *object = "test_trampoline_count.o"; struct inst inst[MAX_TRAMP_PROGS] = {}; int err, i = 0, duration = 0; diff --git a/tools/testing/selftests/bpf/prog_tests/xdp.c b/tools/testing/selftests/bpf/prog_tests/xdp.c index 48921ff748..ac65456b7a 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp.c @@ -11,12 +11,12 @@ void test_xdp(void) const char *file = "./test_xdp.o"; struct bpf_object *obj; char buf[128]; - struct ipv6hdr *iph6 = (void *)buf + sizeof(struct ethhdr); - struct iphdr *iph = (void *)buf + sizeof(struct ethhdr); + struct ipv6hdr iph6; + struct iphdr iph; __u32 duration, retval, size; int err, prog_fd, map_fd; - err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd); + err = bpf_prog_test_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd); if (CHECK_FAIL(err)) return; @@ -28,16 +28,17 @@ void test_xdp(void) err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), buf, &size, &retval, &duration); - + memcpy(&iph, buf + sizeof(struct ethhdr), sizeof(iph)); CHECK(err || retval != XDP_TX || size != 74 || - iph->protocol != IPPROTO_IPIP, "ipv4", + iph.protocol != IPPROTO_IPIP, "ipv4", "err %d errno %d retval %d size %d\n", err, errno, retval, size); err = bpf_prog_test_run(prog_fd, 1, &pkt_v6, sizeof(pkt_v6), buf, &size, &retval, &duration); + memcpy(&iph6, buf + sizeof(struct ethhdr), sizeof(iph6)); CHECK(err || retval != XDP_TX || size != 114 || - iph6->nexthdr != IPPROTO_IPV6, "ipv6", + iph6.nexthdr != IPPROTO_IPV6, "ipv6", "err %d errno %d retval %d size %d\n", err, errno, retval, size); out: diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c b/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c index d5c98f2cb1..3f5a17c38b 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c @@ -2,7 +2,7 @@ #include #include -void test_xdp_adjust_tail_shrink(void) +static void test_xdp_adjust_tail_shrink(void) { const char *file = "./test_xdp_adjust_tail_shrink.o"; __u32 duration, retval, size, expect_sz; @@ -10,7 +10,7 @@ void test_xdp_adjust_tail_shrink(void) int err, prog_fd; char buf[128]; - err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd); + err = bpf_prog_test_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd); if (CHECK_FAIL(err)) return; @@ -30,7 +30,7 @@ void test_xdp_adjust_tail_shrink(void) bpf_object__close(obj); } -void test_xdp_adjust_tail_grow(void) +static void test_xdp_adjust_tail_grow(void) { const char *file = "./test_xdp_adjust_tail_grow.o"; struct bpf_object *obj; @@ -38,7 +38,7 @@ void test_xdp_adjust_tail_grow(void) __u32 duration, retval, size, expect_sz; int err, prog_fd; - err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd); + err = bpf_prog_test_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd); if (CHECK_FAIL(err)) return; @@ -58,7 +58,7 @@ void test_xdp_adjust_tail_grow(void) bpf_object__close(obj); } -void test_xdp_adjust_tail_grow2(void) +static void test_xdp_adjust_tail_grow2(void) { const char *file = "./test_xdp_adjust_tail_grow.o"; char buf[4096]; /* avoid segfault: large buf to hold grow results */ @@ -75,7 +75,7 @@ void test_xdp_adjust_tail_grow2(void) .data_size_out = 0, /* Per test */ }; - err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj, &tattr.prog_fd); + err = bpf_prog_test_load(file, BPF_PROG_TYPE_XDP, &obj, &tattr.prog_fd); if (CHECK_ATTR(err, "load", "err %d errno %d\n", err, errno)) return; diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_attach.c index 15ef353148..c6fa390e3a 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_attach.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_attach.c @@ -4,7 +4,7 @@ #define IFINDEX_LO 1 #define XDP_FLAGS_REPLACE (1U << 4) -void test_xdp_attach(void) +void serial_test_xdp_attach(void) { __u32 duration = 0, id1, id2, id0 = 0, len; struct bpf_object *obj1, *obj2, *obj3; @@ -16,7 +16,7 @@ void test_xdp_attach(void) len = sizeof(info); - err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj1, &fd1); + err = bpf_prog_test_load(file, BPF_PROG_TYPE_XDP, &obj1, &fd1); if (CHECK_FAIL(err)) return; err = bpf_obj_get_info_by_fd(fd1, &info, &len); @@ -24,7 +24,7 @@ void test_xdp_attach(void) goto out_1; id1 = info.id; - err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj2, &fd2); + err = bpf_prog_test_load(file, BPF_PROG_TYPE_XDP, &obj2, &fd2); if (CHECK_FAIL(err)) goto out_1; @@ -34,7 +34,7 @@ void test_xdp_attach(void) goto out_2; id2 = info.id; - err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj3, &fd3); + err = bpf_prog_test_load(file, BPF_PROG_TYPE_XDP, &obj3, &fd3); if (CHECK_FAIL(err)) goto out_2; diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c b/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c index ad3ba81b40..5e3a26b15e 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c @@ -218,9 +218,9 @@ static int send_udp_packets(int vary_dst_ip) .h_dest = BOND2_MAC, .h_proto = htons(ETH_P_IP), }; - uint8_t buf[128] = {}; - struct iphdr *iph = (struct iphdr *)(buf + sizeof(eh)); - struct udphdr *uh = (struct udphdr *)(buf + sizeof(eh) + sizeof(*iph)); + struct iphdr iph = {}; + struct udphdr uh = {}; + uint8_t buf[128]; int i, s = -1; int ifindex; @@ -232,17 +232,16 @@ static int send_udp_packets(int vary_dst_ip) if (!ASSERT_GT(ifindex, 0, "get bond1 ifindex")) goto err; - memcpy(buf, &eh, sizeof(eh)); - iph->ihl = 5; - iph->version = 4; - iph->tos = 16; - iph->id = 1; - iph->ttl = 64; - iph->protocol = IPPROTO_UDP; - iph->saddr = 1; - iph->daddr = 2; - iph->tot_len = htons(sizeof(buf) - ETH_HLEN); - iph->check = 0; + iph.ihl = 5; + iph.version = 4; + iph.tos = 16; + iph.id = 1; + iph.ttl = 64; + iph.protocol = IPPROTO_UDP; + iph.saddr = 1; + iph.daddr = 2; + iph.tot_len = htons(sizeof(buf) - ETH_HLEN); + iph.check = 0; for (i = 1; i <= NPACKETS; i++) { int n; @@ -253,10 +252,15 @@ static int send_udp_packets(int vary_dst_ip) }; /* vary the UDP destination port for even distribution with roundrobin/xor modes */ - uh->dest++; + uh.dest++; if (vary_dst_ip) - iph->daddr++; + iph.daddr++; + + /* construct a packet */ + memcpy(buf, &eh, sizeof(eh)); + memcpy(buf + sizeof(eh), &iph, sizeof(iph)); + memcpy(buf + sizeof(eh) + sizeof(iph), &uh, sizeof(uh)); n = sendto(s, buf, sizeof(buf), 0, (struct sockaddr *)&saddr_ll, sizeof(saddr_ll)); if (!ASSERT_EQ(n, sizeof(buf), "sendto")) @@ -519,7 +523,7 @@ static struct bond_test_case bond_test_cases[] = { { "xdp_bonding_xor_layer34", BOND_MODE_XOR, BOND_XMIT_POLICY_LAYER34, }, }; -void test_xdp_bonding(void) +void serial_test_xdp_bonding(void) { libbpf_print_fn_t old_print_fn; struct skeletons skeletons = {}; diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c index 3bd5904b4d..c98a897ad6 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c @@ -42,14 +42,13 @@ void test_xdp_bpf2bpf(void) char buf[128]; int err, pkt_fd, map_fd; bool passed = false; - struct iphdr *iph = (void *)buf + sizeof(struct ethhdr); + struct iphdr iph; struct iptnl_info value4 = {.family = AF_INET}; struct test_xdp *pkt_skel = NULL; struct test_xdp_bpf2bpf *ftrace_skel = NULL; struct vip key4 = {.protocol = 6, .family = AF_INET}; struct bpf_program *prog; struct perf_buffer *pb = NULL; - struct perf_buffer_opts pb_opts = {}; /* Load XDP program to introspect */ pkt_skel = test_xdp__open_and_load(); @@ -86,19 +85,17 @@ void test_xdp_bpf2bpf(void) goto out; /* Set up perf buffer */ - pb_opts.sample_cb = on_sample; - pb_opts.ctx = &passed; - pb = perf_buffer__new(bpf_map__fd(ftrace_skel->maps.perf_buf_map), - 1, &pb_opts); + pb = perf_buffer__new(bpf_map__fd(ftrace_skel->maps.perf_buf_map), 1, + on_sample, NULL, &passed, NULL); if (!ASSERT_OK_PTR(pb, "perf_buf__new")) goto out; /* Run test program */ err = bpf_prog_test_run(pkt_fd, 1, &pkt_v4, sizeof(pkt_v4), buf, &size, &retval, &duration); - + memcpy(&iph, buf + sizeof(struct ethhdr), sizeof(iph)); if (CHECK(err || retval != XDP_TX || size != 74 || - iph->protocol != IPPROTO_IPIP, "ipv4", + iph.protocol != IPPROTO_IPIP, "ipv4", "err %d errno %d retval %d size %d\n", err, errno, retval, size)) goto out; diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c index 8755effd80..fd812bd436 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c @@ -7,7 +7,7 @@ #define IFINDEX_LO 1 -void test_xdp_cpumap_attach(void) +void serial_test_xdp_cpumap_attach(void) { struct test_xdp_with_cpumap_helpers *skel; struct bpf_prog_info info = {}; diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c index c72af030ff..3079d5568f 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c @@ -8,7 +8,7 @@ #define IFINDEX_LO 1 -void test_xdp_with_devmap_helpers(void) +static void test_xdp_with_devmap_helpers(void) { struct test_xdp_with_devmap_helpers *skel; struct bpf_prog_info info = {}; @@ -60,7 +60,7 @@ void test_xdp_with_devmap_helpers(void) test_xdp_with_devmap_helpers__destroy(skel); } -void test_neg_xdp_devmap_helpers(void) +static void test_neg_xdp_devmap_helpers(void) { struct test_xdp_devmap_helpers *skel; @@ -72,7 +72,7 @@ void test_neg_xdp_devmap_helpers(void) } -void test_xdp_devmap_attach(void) +void serial_test_xdp_devmap_attach(void) { if (test__start_subtest("DEVMAP with programs in entries")) test_xdp_with_devmap_helpers(); diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_info.c b/tools/testing/selftests/bpf/prog_tests/xdp_info.c index d2d7a283d7..abe48e82e1 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_info.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_info.c @@ -4,7 +4,7 @@ #define IFINDEX_LO 1 -void test_xdp_info(void) +void serial_test_xdp_info(void) { __u32 len = sizeof(struct bpf_prog_info), duration = 0, prog_id; const char *file = "./xdp_dummy.o"; @@ -29,7 +29,7 @@ void test_xdp_info(void) /* Setup prog */ - err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd); + err = bpf_prog_test_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd); if (CHECK_FAIL(err)) return; diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_link.c b/tools/testing/selftests/bpf/prog_tests/xdp_link.c index 46eed0a33c..b2b357f8c7 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_link.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_link.c @@ -6,48 +6,49 @@ #define IFINDEX_LO 1 -void test_xdp_link(void) +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 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 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 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/prog_tests/xdp_perf.c b/tools/testing/selftests/bpf/prog_tests/xdp_perf.c index 7185bee16f..15a3900e43 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_perf.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_perf.c @@ -9,7 +9,7 @@ void test_xdp_perf(void) char in[128], out[128]; int err, prog_fd; - err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd); + err = bpf_prog_test_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd); if (CHECK_FAIL(err)) return; diff --git a/tools/testing/selftests/bpf/progs/atomics.c b/tools/testing/selftests/bpf/progs/atomics.c index c245345e41..16e5731320 100644 --- a/tools/testing/selftests/bpf/progs/atomics.c +++ b/tools/testing/selftests/bpf/progs/atomics.c @@ -10,6 +10,8 @@ bool skip_tests __attribute((__section__(".data"))) = false; bool skip_tests = true; #endif +__u32 pid = 0; + __u64 add64_value = 1; __u64 add64_result = 0; __u32 add32_value = 1; @@ -21,6 +23,8 @@ __u64 add_noreturn_value = 1; SEC("fentry/bpf_fentry_test1") int BPF_PROG(add, int a) { + if (pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; #ifdef ENABLE_ATOMICS_TESTS __u64 add_stack_value = 1; @@ -45,6 +49,8 @@ __s64 sub_noreturn_value = 1; SEC("fentry/bpf_fentry_test1") int BPF_PROG(sub, int a) { + if (pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; #ifdef ENABLE_ATOMICS_TESTS __u64 sub_stack_value = 1; @@ -67,6 +73,8 @@ __u64 and_noreturn_value = (0x110ull << 32); SEC("fentry/bpf_fentry_test1") int BPF_PROG(and, int a) { + if (pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; #ifdef ENABLE_ATOMICS_TESTS and64_result = __sync_fetch_and_and(&and64_value, 0x011ull << 32); @@ -86,6 +94,8 @@ __u64 or_noreturn_value = (0x110ull << 32); SEC("fentry/bpf_fentry_test1") int BPF_PROG(or, int a) { + if (pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; #ifdef ENABLE_ATOMICS_TESTS or64_result = __sync_fetch_and_or(&or64_value, 0x011ull << 32); or32_result = __sync_fetch_and_or(&or32_value, 0x011); @@ -104,6 +114,8 @@ __u64 xor_noreturn_value = (0x110ull << 32); SEC("fentry/bpf_fentry_test1") int BPF_PROG(xor, int a) { + if (pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; #ifdef ENABLE_ATOMICS_TESTS xor64_result = __sync_fetch_and_xor(&xor64_value, 0x011ull << 32); xor32_result = __sync_fetch_and_xor(&xor32_value, 0x011); @@ -123,6 +135,8 @@ __u32 cmpxchg32_result_succeed = 0; SEC("fentry/bpf_fentry_test1") int BPF_PROG(cmpxchg, int a) { + if (pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; #ifdef ENABLE_ATOMICS_TESTS cmpxchg64_result_fail = __sync_val_compare_and_swap(&cmpxchg64_value, 0, 3); cmpxchg64_result_succeed = __sync_val_compare_and_swap(&cmpxchg64_value, 1, 2); @@ -142,6 +156,8 @@ __u32 xchg32_result = 0; SEC("fentry/bpf_fentry_test1") int BPF_PROG(xchg, int a) { + if (pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; #ifdef ENABLE_ATOMICS_TESTS __u64 val64 = 2; __u32 val32 = 2; diff --git a/tools/testing/selftests/bpf/progs/bpf_cubic.c b/tools/testing/selftests/bpf/progs/bpf_cubic.c index f62df4d023..d9660e7200 100644 --- a/tools/testing/selftests/bpf/progs/bpf_cubic.c +++ b/tools/testing/selftests/bpf/progs/bpf_cubic.c @@ -169,11 +169,7 @@ static __always_inline void bictcp_hystart_reset(struct sock *sk) ca->sample_cnt = 0; } -/* "struct_ops/" prefix is not a requirement - * It will be recognized as BPF_PROG_TYPE_STRUCT_OPS - * as long as it is used in one of the func ptr - * under SEC(".struct_ops"). - */ +/* "struct_ops/" prefix is a requirement */ SEC("struct_ops/bpf_cubic_init") void BPF_PROG(bpf_cubic_init, struct sock *sk) { @@ -188,10 +184,8 @@ void BPF_PROG(bpf_cubic_init, struct sock *sk) tcp_sk(sk)->snd_ssthresh = initial_ssthresh; } -/* No prefix in SEC will also work. - * The remaining tcp-cubic functions have an easier way. - */ -SEC("no-sec-prefix-bictcp_cwnd_event") +/* "struct_ops" prefix is a requirement */ +SEC("struct_ops/bpf_cubic_cwnd_event") void BPF_PROG(bpf_cubic_cwnd_event, struct sock *sk, enum tcp_ca_event event) { if (event == CA_EVENT_TX_START) { diff --git a/tools/testing/selftests/bpf/progs/bpf_flow.c b/tools/testing/selftests/bpf/progs/bpf_flow.c index 95a5a0778e..f266c757b3 100644 --- a/tools/testing/selftests/bpf/progs/bpf_flow.c +++ b/tools/testing/selftests/bpf/progs/bpf_flow.c @@ -19,9 +19,8 @@ #include #include -int _version SEC("version") = 1; #define PROG(F) PROG_(F, _##F) -#define PROG_(NUM, NAME) SEC("flow_dissector/"#NUM) int bpf_func##NAME +#define PROG_(NUM, NAME) SEC("flow_dissector") int flow_dissector_##NUM /* These are the identifiers of the BPF programs that will be used in tail * calls. Name is limited to 16 characters, with the terminating character and diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_unix.c b/tools/testing/selftests/bpf/progs/bpf_iter_unix.c index 9442390268..c21e3f5453 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_unix.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_unix.c @@ -49,7 +49,7 @@ int dump_unix(struct bpf_iter__unix *ctx) sock_i_ino(sk)); if (unix_sk->addr) { - if (!UNIX_ABSTRACT(unix_sk)) { + if (unix_sk->addr->name->sun_path[0]) { BPF_SEQ_PRINTF(seq, " %s", unix_sk->addr->name->sun_path); } else { /* The name of the abstract UNIX domain socket starts diff --git a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h index eef5646ddb..e0f42601be 100644 --- a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h +++ b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h @@ -6,8 +6,6 @@ #define AF_INET6 10 #define __SO_ACCEPTCON (1 << 16) -#define UNIX_HASH_SIZE 256 -#define UNIX_ABSTRACT(unix_sk) (unix_sk->addr->hash < UNIX_HASH_SIZE) #define SOL_TCP 6 #define TCP_CONGESTION 13 diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_bitfields.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_bitfields.c index 8f44767a75..e5560a6560 100644 --- a/tools/testing/selftests/bpf/progs/btf_dump_test_case_bitfields.c +++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_bitfields.c @@ -11,7 +11,7 @@ /* *struct bitfields_only_mixed_types { * int a: 3; - * long int b: 2; + * long b: 2; * _Bool c: 1; * enum { * A = 0, @@ -27,7 +27,7 @@ struct bitfields_only_mixed_types { int a: 3; - long int b: 2; + long b: 2; bool c: 1; /* it's really a _Bool type */ enum { A, /* A = 0, dumper is very explicit */ @@ -44,8 +44,8 @@ struct bitfields_only_mixed_types { * char: 4; * int a: 4; * short b; - * long int c; - * long int d: 8; + * long c; + * long d: 8; * int e; * int f; *}; @@ -71,7 +71,7 @@ struct bitfield_mixed_with_others { *struct bitfield_flushed { * int a: 4; * long: 60; - * long int b: 16; + * long b: 16; *}; * */ diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_packing.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_packing.c index 1cef3bec1d..e304b6204b 100644 --- a/tools/testing/selftests/bpf/progs/btf_dump_test_case_packing.c +++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_packing.c @@ -29,7 +29,7 @@ struct non_packed_fields { struct nested_packed { char: 4; int a: 4; - long int b; + long b; struct { char c; int d; @@ -44,7 +44,7 @@ union union_is_never_packed { union union_does_not_need_packing { struct { - long int a; + long a; int b; } __attribute__((packed)); int c; diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_padding.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_padding.c index 35c512818a..f2661c8d2d 100644 --- a/tools/testing/selftests/bpf/progs/btf_dump_test_case_padding.c +++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_padding.c @@ -9,7 +9,7 @@ /* ----- START-EXPECTED-OUTPUT ----- */ struct padded_implicitly { int a; - long int b; + long b; char c; }; diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c index 8aaa24a003..1c7105fcae 100644 --- a/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c +++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c @@ -189,7 +189,7 @@ struct struct_with_embedded_stuff { const char *d; } e; union { - volatile long int f; + volatile long f; void * restrict g; }; }; diff --git a/tools/testing/selftests/bpf/progs/cg_storage_multi_isolated.c b/tools/testing/selftests/bpf/progs/cg_storage_multi_isolated.c index a253730020..3f81ff9218 100644 --- a/tools/testing/selftests/bpf/progs/cg_storage_multi_isolated.c +++ b/tools/testing/selftests/bpf/progs/cg_storage_multi_isolated.c @@ -20,7 +20,7 @@ struct { __u32 invocations = 0; -SEC("cgroup_skb/egress/1") +SEC("cgroup_skb/egress") int egress1(struct __sk_buff *skb) { struct cgroup_value *ptr_cg_storage = @@ -32,7 +32,7 @@ int egress1(struct __sk_buff *skb) return 1; } -SEC("cgroup_skb/egress/2") +SEC("cgroup_skb/egress") int egress2(struct __sk_buff *skb) { struct cgroup_value *ptr_cg_storage = diff --git a/tools/testing/selftests/bpf/progs/cg_storage_multi_shared.c b/tools/testing/selftests/bpf/progs/cg_storage_multi_shared.c index a149f33bc5..d662db27fe 100644 --- a/tools/testing/selftests/bpf/progs/cg_storage_multi_shared.c +++ b/tools/testing/selftests/bpf/progs/cg_storage_multi_shared.c @@ -20,7 +20,7 @@ struct { __u32 invocations = 0; -SEC("cgroup_skb/egress/1") +SEC("cgroup_skb/egress") int egress1(struct __sk_buff *skb) { struct cgroup_value *ptr_cg_storage = @@ -32,7 +32,7 @@ int egress1(struct __sk_buff *skb) return 1; } -SEC("cgroup_skb/egress/2") +SEC("cgroup_skb/egress") int egress2(struct __sk_buff *skb) { struct cgroup_value *ptr_cg_storage = diff --git a/tools/testing/selftests/bpf/progs/cgroup_skb_sk_lookup_kern.c b/tools/testing/selftests/bpf/progs/cgroup_skb_sk_lookup_kern.c index 3f757e30d7..88638315c5 100644 --- a/tools/testing/selftests/bpf/progs/cgroup_skb_sk_lookup_kern.c +++ b/tools/testing/selftests/bpf/progs/cgroup_skb_sk_lookup_kern.c @@ -14,7 +14,6 @@ #include #include -int _version SEC("version") = 1; char _license[] SEC("license") = "GPL"; __u16 g_serv_port = 0; diff --git a/tools/testing/selftests/bpf/progs/connect4_prog.c b/tools/testing/selftests/bpf/progs/connect4_prog.c index a943d394fd..b241932911 100644 --- a/tools/testing/selftests/bpf/progs/connect4_prog.c +++ b/tools/testing/selftests/bpf/progs/connect4_prog.c @@ -31,8 +31,6 @@ #define IFNAMSIZ 16 #endif -int _version SEC("version") = 1; - __attribute__ ((noinline)) int do_bind(struct bpf_sock_addr *ctx) { diff --git a/tools/testing/selftests/bpf/progs/connect6_prog.c b/tools/testing/selftests/bpf/progs/connect6_prog.c index 506d0f81a3..40266d2c73 100644 --- a/tools/testing/selftests/bpf/progs/connect6_prog.c +++ b/tools/testing/selftests/bpf/progs/connect6_prog.c @@ -24,8 +24,6 @@ #define DST_REWRITE_PORT6 6666 -int _version SEC("version") = 1; - SEC("cgroup/connect6") int connect_v6_prog(struct bpf_sock_addr *ctx) { diff --git a/tools/testing/selftests/bpf/progs/connect_force_port4.c b/tools/testing/selftests/bpf/progs/connect_force_port4.c index a979aaef2a..27a632dd38 100644 --- a/tools/testing/selftests/bpf/progs/connect_force_port4.c +++ b/tools/testing/selftests/bpf/progs/connect_force_port4.c @@ -13,7 +13,6 @@ #include char _license[] SEC("license") = "GPL"; -int _version SEC("version") = 1; struct svc_addr { __be32 addr; diff --git a/tools/testing/selftests/bpf/progs/connect_force_port6.c b/tools/testing/selftests/bpf/progs/connect_force_port6.c index afc8f1c5a9..19cad93e61 100644 --- a/tools/testing/selftests/bpf/progs/connect_force_port6.c +++ b/tools/testing/selftests/bpf/progs/connect_force_port6.c @@ -12,7 +12,6 @@ #include char _license[] SEC("license") = "GPL"; -int _version SEC("version") = 1; struct svc_addr { __be32 addr[4]; diff --git a/tools/testing/selftests/bpf/progs/dev_cgroup.c b/tools/testing/selftests/bpf/progs/dev_cgroup.c index 8924e06bde..79b54a4fa2 100644 --- a/tools/testing/selftests/bpf/progs/dev_cgroup.c +++ b/tools/testing/selftests/bpf/progs/dev_cgroup.c @@ -57,4 +57,3 @@ int bpf_prog1(struct bpf_cgroup_dev_ctx *ctx) } char _license[] SEC("license") = "GPL"; -__u32 _version SEC("version") = LINUX_VERSION_CODE; diff --git a/tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c b/tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c index 49a84a3a23..48cd14b437 100644 --- a/tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c +++ b/tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c @@ -73,7 +73,7 @@ int test_subprog2(struct args_subprog2 *ctx) __builtin_preserve_access_index(&skb->len)); ret = ctx->ret; - /* bpf_prog_load() loads "test_pkt_access.o" with BPF_F_TEST_RND_HI32 + /* bpf_prog_test_load() loads "test_pkt_access.o" with BPF_F_TEST_RND_HI32 * which randomizes upper 32 bits after BPF_ALU32 insns. * Hence after 'w0 <<= 1' upper bits of $rax are random. * That is expected and correct. Trim them. diff --git a/tools/testing/selftests/bpf/progs/fexit_sleep.c b/tools/testing/selftests/bpf/progs/fexit_sleep.c index 03a672d763..bca92c9bd2 100644 --- a/tools/testing/selftests/bpf/progs/fexit_sleep.c +++ b/tools/testing/selftests/bpf/progs/fexit_sleep.c @@ -13,7 +13,7 @@ int fexit_cnt = 0; SEC("fentry/__x64_sys_nanosleep") int BPF_PROG(nanosleep_fentry, const struct pt_regs *regs) { - if ((int)bpf_get_current_pid_tgid() != pid) + if (bpf_get_current_pid_tgid() >> 32 != pid) return 0; fentry_cnt++; @@ -23,7 +23,7 @@ int BPF_PROG(nanosleep_fentry, const struct pt_regs *regs) SEC("fexit/__x64_sys_nanosleep") int BPF_PROG(nanosleep_fexit, const struct pt_regs *regs, int ret) { - if ((int)bpf_get_current_pid_tgid() != pid) + if (bpf_get_current_pid_tgid() >> 32 != pid) return 0; fexit_cnt++; diff --git a/tools/testing/selftests/bpf/progs/for_each_array_map_elem.c b/tools/testing/selftests/bpf/progs/for_each_array_map_elem.c index 75e8e1069f..52f6995ff2 100644 --- a/tools/testing/selftests/bpf/progs/for_each_array_map_elem.c +++ b/tools/testing/selftests/bpf/progs/for_each_array_map_elem.c @@ -23,6 +23,16 @@ struct callback_ctx { int output; }; +const volatile int bypass_unused = 1; + +static __u64 +unused_subprog(struct bpf_map *map, __u32 *key, __u64 *val, + struct callback_ctx *data) +{ + data->output = 0; + return 1; +} + static __u64 check_array_elem(struct bpf_map *map, __u32 *key, __u64 *val, struct callback_ctx *data) @@ -47,13 +57,15 @@ check_percpu_elem(struct bpf_map *map, __u32 *key, __u64 *val, u32 arraymap_output = 0; -SEC("classifier") +SEC("tc") int test_pkt_access(struct __sk_buff *skb) { struct callback_ctx data; data.output = 0; bpf_for_each_map_elem(&arraymap, check_array_elem, &data, 0); + if (!bypass_unused) + bpf_for_each_map_elem(&arraymap, unused_subprog, &data, 0); arraymap_output = data.output; bpf_for_each_map_elem(&percpu_map, check_percpu_elem, (void *)0, 0); diff --git a/tools/testing/selftests/bpf/progs/for_each_hash_map_elem.c b/tools/testing/selftests/bpf/progs/for_each_hash_map_elem.c index 913dd91aaf..276994d5c0 100644 --- a/tools/testing/selftests/bpf/progs/for_each_hash_map_elem.c +++ b/tools/testing/selftests/bpf/progs/for_each_hash_map_elem.c @@ -78,7 +78,7 @@ int hashmap_output = 0; int hashmap_elems = 0; int percpu_map_elems = 0; -SEC("classifier") +SEC("tc") int test_pkt_access(struct __sk_buff *skb) { struct callback_ctx data; diff --git a/tools/testing/selftests/bpf/progs/get_cgroup_id_kern.c b/tools/testing/selftests/bpf/progs/get_cgroup_id_kern.c index 6b42db2fe3..68587b1de3 100644 --- a/tools/testing/selftests/bpf/progs/get_cgroup_id_kern.c +++ b/tools/testing/selftests/bpf/progs/get_cgroup_id_kern.c @@ -37,4 +37,3 @@ int trace(void *ctx) } char _license[] SEC("license") = "GPL"; -__u32 _version SEC("version") = 1; /* ignored by tracepoints, required by libbpf.a */ diff --git a/tools/testing/selftests/bpf/progs/kfree_skb.c b/tools/testing/selftests/bpf/progs/kfree_skb.c index 55e283050c..7236da72ce 100644 --- a/tools/testing/selftests/bpf/progs/kfree_skb.c +++ b/tools/testing/selftests/bpf/progs/kfree_skb.c @@ -9,8 +9,8 @@ char _license[] SEC("license") = "GPL"; struct { __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); - __uint(key_size, sizeof(int)); - __uint(value_size, sizeof(int)); + __type(key, int); + __type(value, int); } perf_buf_map SEC(".maps"); #define _(P) (__builtin_preserve_access_index(P)) diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_test.c b/tools/testing/selftests/bpf/progs/kfunc_call_test.c index 470f8723e4..8a8cf59017 100644 --- a/tools/testing/selftests/bpf/progs/kfunc_call_test.c +++ b/tools/testing/selftests/bpf/progs/kfunc_call_test.c @@ -8,7 +8,7 @@ extern int bpf_kfunc_call_test2(struct sock *sk, __u32 a, __u32 b) __ksym; extern __u64 bpf_kfunc_call_test1(struct sock *sk, __u32 a, __u64 b, __u32 c, __u64 d) __ksym; -SEC("classifier") +SEC("tc") int kfunc_call_test2(struct __sk_buff *skb) { struct bpf_sock *sk = skb->sk; @@ -23,7 +23,7 @@ int kfunc_call_test2(struct __sk_buff *skb) return bpf_kfunc_call_test2((struct sock *)sk, 1, 2); } -SEC("classifier") +SEC("tc") int kfunc_call_test1(struct __sk_buff *skb) { struct bpf_sock *sk = skb->sk; diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c b/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c index 5fbd9e232d..c1fdecabea 100644 --- a/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c +++ b/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c @@ -33,7 +33,7 @@ int __noinline f1(struct __sk_buff *skb) return (__u32)bpf_kfunc_call_test1((struct sock *)sk, 1, 2, 3, 4); } -SEC("classifier") +SEC("tc") int kfunc_call_test1(struct __sk_buff *skb) { return f1(skb); diff --git a/tools/testing/selftests/bpf/progs/local_storage.c b/tools/testing/selftests/bpf/progs/local_storage.c index 95868bc7ad..9b1f9b75d5 100644 --- a/tools/testing/selftests/bpf/progs/local_storage.c +++ b/tools/testing/selftests/bpf/progs/local_storage.c @@ -20,7 +20,6 @@ int sk_storage_result = -1; struct local_storage { struct inode *exec_inode; __u32 value; - struct bpf_spin_lock lock; }; struct { @@ -58,9 +57,7 @@ int BPF_PROG(unlink_hook, struct inode *dir, struct dentry *victim) bpf_get_current_task_btf(), 0, 0); if (storage) { /* Don't let an executable delete itself */ - bpf_spin_lock(&storage->lock); is_self_unlink = storage->exec_inode == victim->d_inode; - bpf_spin_unlock(&storage->lock); if (is_self_unlink) return -EPERM; } @@ -68,7 +65,7 @@ int BPF_PROG(unlink_hook, struct inode *dir, struct dentry *victim) return 0; } -SEC("lsm/inode_rename") +SEC("lsm.s/inode_rename") int BPF_PROG(inode_rename, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) @@ -89,10 +86,8 @@ int BPF_PROG(inode_rename, struct inode *old_dir, struct dentry *old_dentry, if (!storage) return 0; - bpf_spin_lock(&storage->lock); if (storage->value != DUMMY_STORAGE_VALUE) inode_storage_result = -1; - bpf_spin_unlock(&storage->lock); err = bpf_inode_storage_delete(&inode_storage_map, old_dentry->d_inode); if (!err) @@ -101,7 +96,7 @@ int BPF_PROG(inode_rename, struct inode *old_dir, struct dentry *old_dentry, return 0; } -SEC("lsm/socket_bind") +SEC("lsm.s/socket_bind") int BPF_PROG(socket_bind, struct socket *sock, struct sockaddr *address, int addrlen) { @@ -117,10 +112,8 @@ int BPF_PROG(socket_bind, struct socket *sock, struct sockaddr *address, if (!storage) return 0; - bpf_spin_lock(&storage->lock); if (storage->value != DUMMY_STORAGE_VALUE) sk_storage_result = -1; - bpf_spin_unlock(&storage->lock); err = bpf_sk_storage_delete(&sk_storage_map, sock->sk); if (!err) @@ -129,7 +122,7 @@ int BPF_PROG(socket_bind, struct socket *sock, struct sockaddr *address, return 0; } -SEC("lsm/socket_post_create") +SEC("lsm.s/socket_post_create") int BPF_PROG(socket_post_create, struct socket *sock, int family, int type, int protocol, int kern) { @@ -144,9 +137,7 @@ int BPF_PROG(socket_post_create, struct socket *sock, int family, int type, if (!storage) return 0; - bpf_spin_lock(&storage->lock); storage->value = DUMMY_STORAGE_VALUE; - bpf_spin_unlock(&storage->lock); return 0; } @@ -154,7 +145,7 @@ int BPF_PROG(socket_post_create, struct socket *sock, int family, int type, /* This uses the local storage to remember the inode of the binary that a * process was originally executing. */ -SEC("lsm/bprm_committed_creds") +SEC("lsm.s/bprm_committed_creds") void BPF_PROG(exec, struct linux_binprm *bprm) { __u32 pid = bpf_get_current_pid_tgid() >> 32; @@ -166,18 +157,13 @@ void BPF_PROG(exec, struct linux_binprm *bprm) storage = bpf_task_storage_get(&task_storage_map, bpf_get_current_task_btf(), 0, BPF_LOCAL_STORAGE_GET_F_CREATE); - if (storage) { - bpf_spin_lock(&storage->lock); + if (storage) storage->exec_inode = bprm->file->f_inode; - bpf_spin_unlock(&storage->lock); - } storage = bpf_inode_storage_get(&inode_storage_map, bprm->file->f_inode, 0, BPF_LOCAL_STORAGE_GET_F_CREATE); if (!storage) return; - bpf_spin_lock(&storage->lock); storage->value = DUMMY_STORAGE_VALUE; - bpf_spin_unlock(&storage->lock); } diff --git a/tools/testing/selftests/bpf/progs/map_ptr_kern.c b/tools/testing/selftests/bpf/progs/map_ptr_kern.c index d1d304c980..b64df94ec4 100644 --- a/tools/testing/selftests/bpf/progs/map_ptr_kern.c +++ b/tools/testing/selftests/bpf/progs/map_ptr_kern.c @@ -334,9 +334,11 @@ static inline int check_lpm_trie(void) return 1; } +#define INNER_MAX_ENTRIES 1234 + struct inner_map { __uint(type, BPF_MAP_TYPE_ARRAY); - __uint(max_entries, 1); + __uint(max_entries, INNER_MAX_ENTRIES); __type(key, __u32); __type(value, __u32); } inner_map SEC(".maps"); @@ -348,7 +350,7 @@ struct { __type(value, __u32); __array(values, struct { __uint(type, BPF_MAP_TYPE_ARRAY); - __uint(max_entries, 1); + __uint(max_entries, INNER_MAX_ENTRIES); __type(key, __u32); __type(value, __u32); }); @@ -360,8 +362,13 @@ static inline int check_array_of_maps(void) { struct bpf_array *array_of_maps = (struct bpf_array *)&m_array_of_maps; struct bpf_map *map = (struct bpf_map *)&m_array_of_maps; + struct bpf_array *inner_map; + int key = 0; VERIFY(check_default(&array_of_maps->map, map)); + inner_map = bpf_map_lookup_elem(array_of_maps, &key); + VERIFY(inner_map != 0); + VERIFY(inner_map->map.max_entries == INNER_MAX_ENTRIES); return 1; } @@ -382,8 +389,13 @@ static inline int check_hash_of_maps(void) { struct bpf_htab *hash_of_maps = (struct bpf_htab *)&m_hash_of_maps; struct bpf_map *map = (struct bpf_map *)&m_hash_of_maps; + struct bpf_htab *inner_map; + int key = 2; VERIFY(check_default(&hash_of_maps->map, map)); + inner_map = bpf_map_lookup_elem(hash_of_maps, &key); + VERIFY(inner_map != 0); + VERIFY(inner_map->map.max_entries == INNER_MAX_ENTRIES); return 1; } @@ -683,5 +695,4 @@ int cg_skb(void *ctx) return 1; } -__u32 _version SEC("version") = 1; char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/netcnt_prog.c b/tools/testing/selftests/bpf/progs/netcnt_prog.c index 43649bce4c..f718b2c212 100644 --- a/tools/testing/selftests/bpf/progs/netcnt_prog.c +++ b/tools/testing/selftests/bpf/progs/netcnt_prog.c @@ -68,4 +68,3 @@ int bpf_nextcnt(struct __sk_buff *skb) } char _license[] SEC("license") = "GPL"; -__u32 _version SEC("version") = LINUX_VERSION_CODE; diff --git a/tools/testing/selftests/bpf/progs/perf_event_stackmap.c b/tools/testing/selftests/bpf/progs/perf_event_stackmap.c index 25467d13c3..b3fcb5274e 100644 --- a/tools/testing/selftests/bpf/progs/perf_event_stackmap.c +++ b/tools/testing/selftests/bpf/progs/perf_event_stackmap.c @@ -11,8 +11,8 @@ typedef __u64 stack_trace_t[PERF_MAX_STACK_DEPTH]; struct { __uint(type, BPF_MAP_TYPE_STACK_TRACE); __uint(max_entries, 16384); - __uint(key_size, sizeof(__u32)); - __uint(value_size, sizeof(stack_trace_t)); + __type(key, __u32); + __type(value, stack_trace_t); } stackmap SEC(".maps"); struct { diff --git a/tools/testing/selftests/bpf/progs/pyperf.h b/tools/testing/selftests/bpf/progs/pyperf.h index 2fb7adafb6..1ed28882da 100644 --- a/tools/testing/selftests/bpf/progs/pyperf.h +++ b/tools/testing/selftests/bpf/progs/pyperf.h @@ -159,6 +159,59 @@ struct { __uint(value_size, sizeof(long long) * 127); } stackmap SEC(".maps"); +#ifdef USE_BPF_LOOP +struct process_frame_ctx { + int cur_cpu; + int32_t *symbol_counter; + void *frame_ptr; + FrameData *frame; + PidData *pidData; + Symbol *sym; + Event *event; + bool done; +}; + +#define barrier_var(var) asm volatile("" : "=r"(var) : "0"(var)) + +static int process_frame_callback(__u32 i, struct process_frame_ctx *ctx) +{ + int zero = 0; + void *frame_ptr = ctx->frame_ptr; + PidData *pidData = ctx->pidData; + FrameData *frame = ctx->frame; + int32_t *symbol_counter = ctx->symbol_counter; + int cur_cpu = ctx->cur_cpu; + Event *event = ctx->event; + Symbol *sym = ctx->sym; + + if (frame_ptr && get_frame_data(frame_ptr, pidData, frame, sym)) { + int32_t new_symbol_id = *symbol_counter * 64 + cur_cpu; + int32_t *symbol_id = bpf_map_lookup_elem(&symbolmap, sym); + + if (!symbol_id) { + bpf_map_update_elem(&symbolmap, sym, &zero, 0); + symbol_id = bpf_map_lookup_elem(&symbolmap, sym); + if (!symbol_id) { + ctx->done = true; + return 1; + } + } + if (*symbol_id == new_symbol_id) + (*symbol_counter)++; + + barrier_var(i); + if (i >= STACK_MAX_LEN) + return 1; + + event->stack[i] = *symbol_id; + + event->stack_len = i + 1; + frame_ptr = frame->f_back; + } + return 0; +} +#endif /* USE_BPF_LOOP */ + #ifdef GLOBAL_FUNC __noinline #elif defined(SUBPROGS) @@ -228,11 +281,26 @@ int __on_event(struct bpf_raw_tracepoint_args *ctx) int32_t* symbol_counter = bpf_map_lookup_elem(&symbolmap, &sym); if (symbol_counter == NULL) return 0; +#ifdef USE_BPF_LOOP + struct process_frame_ctx ctx = { + .cur_cpu = cur_cpu, + .symbol_counter = symbol_counter, + .frame_ptr = frame_ptr, + .frame = &frame, + .pidData = pidData, + .sym = &sym, + .event = event, + }; + + bpf_loop(STACK_MAX_LEN, process_frame_callback, &ctx, 0); + if (ctx.done) + return 0; +#else #ifdef NO_UNROLL #pragma clang loop unroll(disable) #else #pragma clang loop unroll(full) -#endif +#endif /* NO_UNROLL */ /* Unwind python stack */ for (int i = 0; i < STACK_MAX_LEN; ++i) { if (frame_ptr && get_frame_data(frame_ptr, pidData, &frame, &sym)) { @@ -251,6 +319,7 @@ int __on_event(struct bpf_raw_tracepoint_args *ctx) frame_ptr = frame.f_back; } } +#endif /* USE_BPF_LOOP */ event->stack_complete = frame_ptr == NULL; } else { event->stack_complete = 1; diff --git a/tools/testing/selftests/bpf/progs/recursion.c b/tools/testing/selftests/bpf/progs/recursion.c index 49f679375b..3c2423bb19 100644 --- a/tools/testing/selftests/bpf/progs/recursion.c +++ b/tools/testing/selftests/bpf/progs/recursion.c @@ -24,8 +24,8 @@ struct { int pass1 = 0; int pass2 = 0; -SEC("fentry/__htab_map_lookup_elem") -int BPF_PROG(on_lookup, struct bpf_map *map) +SEC("fentry/htab_map_delete_elem") +int BPF_PROG(on_delete, struct bpf_map *map) { int key = 0; @@ -35,10 +35,7 @@ int BPF_PROG(on_lookup, struct bpf_map *map) } if (map == (void *)&hash2) { pass2++; - /* htab_map_gen_lookup() will inline below call - * into direct call to __htab_map_lookup_elem() - */ - bpf_map_lookup_elem(&hash2, &key); + bpf_map_delete_elem(&hash2, &key); return 0; } diff --git a/tools/testing/selftests/bpf/progs/sendmsg4_prog.c b/tools/testing/selftests/bpf/progs/sendmsg4_prog.c index ac5abc34cd..ea75a44cb7 100644 --- a/tools/testing/selftests/bpf/progs/sendmsg4_prog.c +++ b/tools/testing/selftests/bpf/progs/sendmsg4_prog.c @@ -18,8 +18,6 @@ #define DST_PORT 4040 #define DST_REWRITE_PORT4 4444 -int _version SEC("version") = 1; - SEC("cgroup/sendmsg4") int sendmsg_v4_prog(struct bpf_sock_addr *ctx) { diff --git a/tools/testing/selftests/bpf/progs/sendmsg6_prog.c b/tools/testing/selftests/bpf/progs/sendmsg6_prog.c index 24694b1a8d..bf9b46b806 100644 --- a/tools/testing/selftests/bpf/progs/sendmsg6_prog.c +++ b/tools/testing/selftests/bpf/progs/sendmsg6_prog.c @@ -22,8 +22,6 @@ #define DST_REWRITE_PORT6 6666 -int _version SEC("version") = 1; - SEC("cgroup/sendmsg6") int sendmsg_v6_prog(struct bpf_sock_addr *ctx) { diff --git a/tools/testing/selftests/bpf/progs/skb_pkt_end.c b/tools/testing/selftests/bpf/progs/skb_pkt_end.c index 7f2eaa2f89..992b786100 100644 --- a/tools/testing/selftests/bpf/progs/skb_pkt_end.c +++ b/tools/testing/selftests/bpf/progs/skb_pkt_end.c @@ -25,7 +25,7 @@ static INLINE struct iphdr *get_iphdr(struct __sk_buff *skb) return ip; } -SEC("classifier/cls") +SEC("tc") int main_prog(struct __sk_buff *skb) { struct iphdr *ip = NULL; diff --git a/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c b/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c index ca283af80d..95d5b941bc 100644 --- a/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c +++ b/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c @@ -2,8 +2,6 @@ #include #include -int _version SEC("version") = 1; - SEC("sk_skb1") int bpf_prog1(struct __sk_buff *skb) { diff --git a/tools/testing/selftests/bpf/progs/sockmap_tcp_msg_prog.c b/tools/testing/selftests/bpf/progs/sockmap_tcp_msg_prog.c index eeaf6e75c9..80632954c5 100644 --- a/tools/testing/selftests/bpf/progs/sockmap_tcp_msg_prog.c +++ b/tools/testing/selftests/bpf/progs/sockmap_tcp_msg_prog.c @@ -3,8 +3,6 @@ #include #include -int _version SEC("version") = 1; - SEC("sk_msg1") int bpf_prog1(struct sk_msg_md *msg) { diff --git a/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c b/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c index 4797dc9850..e2468a6d01 100644 --- a/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c +++ b/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c @@ -2,27 +2,25 @@ #include #include -int _version SEC("version") = 1; - struct { __uint(type, BPF_MAP_TYPE_SOCKMAP); __uint(max_entries, 20); - __uint(key_size, sizeof(int)); - __uint(value_size, sizeof(int)); + __type(key, int); + __type(value, int); } sock_map_rx SEC(".maps"); struct { __uint(type, BPF_MAP_TYPE_SOCKMAP); __uint(max_entries, 20); - __uint(key_size, sizeof(int)); - __uint(value_size, sizeof(int)); + __type(key, int); + __type(value, int); } sock_map_tx SEC(".maps"); struct { __uint(type, BPF_MAP_TYPE_SOCKMAP); __uint(max_entries, 20); - __uint(key_size, sizeof(int)); - __uint(value_size, sizeof(int)); + __type(key, int); + __type(value, int); } sock_map_msg SEC(".maps"); struct { diff --git a/tools/testing/selftests/bpf/progs/sockopt_inherit.c b/tools/testing/selftests/bpf/progs/sockopt_inherit.c index c6d428a8d7..9fb241b972 100644 --- a/tools/testing/selftests/bpf/progs/sockopt_inherit.c +++ b/tools/testing/selftests/bpf/progs/sockopt_inherit.c @@ -3,7 +3,6 @@ #include char _license[] SEC("license") = "GPL"; -__u32 _version SEC("version") = 1; #define SOL_CUSTOM 0xdeadbeef #define CUSTOM_INHERIT1 0 diff --git a/tools/testing/selftests/bpf/progs/sockopt_multi.c b/tools/testing/selftests/bpf/progs/sockopt_multi.c index 9d8c212dde..177a59069d 100644 --- a/tools/testing/selftests/bpf/progs/sockopt_multi.c +++ b/tools/testing/selftests/bpf/progs/sockopt_multi.c @@ -4,9 +4,8 @@ #include char _license[] SEC("license") = "GPL"; -__u32 _version SEC("version") = 1; -SEC("cgroup/getsockopt/child") +SEC("cgroup/getsockopt") int _getsockopt_child(struct bpf_sockopt *ctx) { __u8 *optval_end = ctx->optval_end; @@ -29,7 +28,7 @@ int _getsockopt_child(struct bpf_sockopt *ctx) return 1; } -SEC("cgroup/getsockopt/parent") +SEC("cgroup/getsockopt") int _getsockopt_parent(struct bpf_sockopt *ctx) { __u8 *optval_end = ctx->optval_end; diff --git a/tools/testing/selftests/bpf/progs/strobemeta.h b/tools/testing/selftests/bpf/progs/strobemeta.h index 60c93aee2f..753718595c 100644 --- a/tools/testing/selftests/bpf/progs/strobemeta.h +++ b/tools/testing/selftests/bpf/progs/strobemeta.h @@ -445,6 +445,48 @@ static __always_inline void *read_map_var(struct strobemeta_cfg *cfg, return payload; } +#ifdef USE_BPF_LOOP +enum read_type { + READ_INT_VAR, + READ_MAP_VAR, + READ_STR_VAR, +}; + +struct read_var_ctx { + struct strobemeta_payload *data; + void *tls_base; + struct strobemeta_cfg *cfg; + void *payload; + /* value gets mutated */ + struct strobe_value_generic *value; + enum read_type type; +}; + +static int read_var_callback(__u32 index, struct read_var_ctx *ctx) +{ + switch (ctx->type) { + case READ_INT_VAR: + if (index >= STROBE_MAX_INTS) + return 1; + read_int_var(ctx->cfg, index, ctx->tls_base, ctx->value, ctx->data); + break; + case READ_MAP_VAR: + if (index >= STROBE_MAX_MAPS) + return 1; + ctx->payload = read_map_var(ctx->cfg, index, ctx->tls_base, + ctx->value, ctx->data, ctx->payload); + break; + case READ_STR_VAR: + if (index >= STROBE_MAX_STRS) + return 1; + ctx->payload += read_str_var(ctx->cfg, index, ctx->tls_base, + ctx->value, ctx->data, ctx->payload); + break; + } + return 0; +} +#endif /* USE_BPF_LOOP */ + /* * read_strobe_meta returns NULL, if no metadata was read; otherwise returns * pointer to *right after* payload ends @@ -475,11 +517,36 @@ static void *read_strobe_meta(struct task_struct *task, */ tls_base = (void *)task; +#ifdef USE_BPF_LOOP + struct read_var_ctx ctx = { + .cfg = cfg, + .tls_base = tls_base, + .value = &value, + .data = data, + .payload = payload, + }; + int err; + + ctx.type = READ_INT_VAR; + err = bpf_loop(STROBE_MAX_INTS, read_var_callback, &ctx, 0); + if (err != STROBE_MAX_INTS) + return NULL; + + ctx.type = READ_STR_VAR; + err = bpf_loop(STROBE_MAX_STRS, read_var_callback, &ctx, 0); + if (err != STROBE_MAX_STRS) + return NULL; + + ctx.type = READ_MAP_VAR; + err = bpf_loop(STROBE_MAX_MAPS, read_var_callback, &ctx, 0); + if (err != STROBE_MAX_MAPS) + return NULL; +#else #ifdef NO_UNROLL #pragma clang loop unroll(disable) #else #pragma unroll -#endif +#endif /* NO_UNROLL */ for (int i = 0; i < STROBE_MAX_INTS; ++i) { read_int_var(cfg, i, tls_base, &value, data); } @@ -487,7 +554,7 @@ static void *read_strobe_meta(struct task_struct *task, #pragma clang loop unroll(disable) #else #pragma unroll -#endif +#endif /* NO_UNROLL */ for (int i = 0; i < STROBE_MAX_STRS; ++i) { payload += read_str_var(cfg, i, tls_base, &value, data, payload); } @@ -495,10 +562,12 @@ static void *read_strobe_meta(struct task_struct *task, #pragma clang loop unroll(disable) #else #pragma unroll -#endif +#endif /* NO_UNROLL */ for (int i = 0; i < STROBE_MAX_MAPS; ++i) { payload = read_map_var(cfg, i, tls_base, &value, data, payload); } +#endif /* USE_BPF_LOOP */ + /* * return pointer right after end of payload, so it's possible to * calculate exact amount of useful data that needs to be sent diff --git a/tools/testing/selftests/bpf/progs/tailcall1.c b/tools/testing/selftests/bpf/progs/tailcall1.c index 7115bcefbe..8159a0b4a6 100644 --- a/tools/testing/selftests/bpf/progs/tailcall1.c +++ b/tools/testing/selftests/bpf/progs/tailcall1.c @@ -11,8 +11,8 @@ struct { } jmp_table SEC(".maps"); #define TAIL_FUNC(x) \ - SEC("classifier/" #x) \ - int bpf_func_##x(struct __sk_buff *skb) \ + SEC("tc") \ + int classifier_##x(struct __sk_buff *skb) \ { \ return x; \ } @@ -20,7 +20,7 @@ TAIL_FUNC(0) TAIL_FUNC(1) TAIL_FUNC(2) -SEC("classifier") +SEC("tc") int entry(struct __sk_buff *skb) { /* Multiple locations to make sure we patch @@ -45,4 +45,3 @@ int entry(struct __sk_buff *skb) } char __license[] SEC("license") = "GPL"; -int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/tailcall2.c b/tools/testing/selftests/bpf/progs/tailcall2.c index 0431e4fe7e..a5ff53e617 100644 --- a/tools/testing/selftests/bpf/progs/tailcall2.c +++ b/tools/testing/selftests/bpf/progs/tailcall2.c @@ -10,41 +10,41 @@ struct { __uint(value_size, sizeof(__u32)); } jmp_table SEC(".maps"); -SEC("classifier/0") -int bpf_func_0(struct __sk_buff *skb) +SEC("tc") +int classifier_0(struct __sk_buff *skb) { bpf_tail_call_static(skb, &jmp_table, 1); return 0; } -SEC("classifier/1") -int bpf_func_1(struct __sk_buff *skb) +SEC("tc") +int classifier_1(struct __sk_buff *skb) { bpf_tail_call_static(skb, &jmp_table, 2); return 1; } -SEC("classifier/2") -int bpf_func_2(struct __sk_buff *skb) +SEC("tc") +int classifier_2(struct __sk_buff *skb) { return 2; } -SEC("classifier/3") -int bpf_func_3(struct __sk_buff *skb) +SEC("tc") +int classifier_3(struct __sk_buff *skb) { bpf_tail_call_static(skb, &jmp_table, 4); return 3; } -SEC("classifier/4") -int bpf_func_4(struct __sk_buff *skb) +SEC("tc") +int classifier_4(struct __sk_buff *skb) { bpf_tail_call_static(skb, &jmp_table, 3); return 4; } -SEC("classifier") +SEC("tc") int entry(struct __sk_buff *skb) { bpf_tail_call_static(skb, &jmp_table, 0); @@ -56,4 +56,3 @@ int entry(struct __sk_buff *skb) } char __license[] SEC("license") = "GPL"; -int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/tailcall3.c b/tools/testing/selftests/bpf/progs/tailcall3.c index 910858fe07..f60bcd7b8d 100644 --- a/tools/testing/selftests/bpf/progs/tailcall3.c +++ b/tools/testing/selftests/bpf/progs/tailcall3.c @@ -12,15 +12,15 @@ struct { int count = 0; -SEC("classifier/0") -int bpf_func_0(struct __sk_buff *skb) +SEC("tc") +int classifier_0(struct __sk_buff *skb) { count++; bpf_tail_call_static(skb, &jmp_table, 0); return 1; } -SEC("classifier") +SEC("tc") int entry(struct __sk_buff *skb) { bpf_tail_call_static(skb, &jmp_table, 0); @@ -28,4 +28,3 @@ int entry(struct __sk_buff *skb) } char __license[] SEC("license") = "GPL"; -int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/tailcall4.c b/tools/testing/selftests/bpf/progs/tailcall4.c index bd4be135c3..a56bbc2313 100644 --- a/tools/testing/selftests/bpf/progs/tailcall4.c +++ b/tools/testing/selftests/bpf/progs/tailcall4.c @@ -13,8 +13,8 @@ struct { int selector = 0; #define TAIL_FUNC(x) \ - SEC("classifier/" #x) \ - int bpf_func_##x(struct __sk_buff *skb) \ + SEC("tc") \ + int classifier_##x(struct __sk_buff *skb) \ { \ return x; \ } @@ -22,7 +22,7 @@ TAIL_FUNC(0) TAIL_FUNC(1) TAIL_FUNC(2) -SEC("classifier") +SEC("tc") int entry(struct __sk_buff *skb) { bpf_tail_call(skb, &jmp_table, selector); @@ -30,4 +30,3 @@ int entry(struct __sk_buff *skb) } char __license[] SEC("license") = "GPL"; -int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/tailcall5.c b/tools/testing/selftests/bpf/progs/tailcall5.c index adf30a3306..8d03496eb6 100644 --- a/tools/testing/selftests/bpf/progs/tailcall5.c +++ b/tools/testing/selftests/bpf/progs/tailcall5.c @@ -13,8 +13,8 @@ struct { int selector = 0; #define TAIL_FUNC(x) \ - SEC("classifier/" #x) \ - int bpf_func_##x(struct __sk_buff *skb) \ + SEC("tc") \ + int classifier_##x(struct __sk_buff *skb) \ { \ return x; \ } @@ -22,7 +22,7 @@ TAIL_FUNC(0) TAIL_FUNC(1) TAIL_FUNC(2) -SEC("classifier") +SEC("tc") int entry(struct __sk_buff *skb) { int idx = 0; @@ -37,4 +37,3 @@ int entry(struct __sk_buff *skb) } char __license[] SEC("license") = "GPL"; -int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf1.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf1.c index 0103f3dd9f..8c91428deb 100644 --- a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf1.c +++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf1.c @@ -10,8 +10,8 @@ struct { } jmp_table SEC(".maps"); #define TAIL_FUNC(x) \ - SEC("classifier/" #x) \ - int bpf_func_##x(struct __sk_buff *skb) \ + SEC("tc") \ + int classifier_##x(struct __sk_buff *skb) \ { \ return x; \ } @@ -26,7 +26,7 @@ int subprog_tail(struct __sk_buff *skb) return skb->len * 2; } -SEC("classifier") +SEC("tc") int entry(struct __sk_buff *skb) { bpf_tail_call_static(skb, &jmp_table, 1); @@ -35,4 +35,3 @@ int entry(struct __sk_buff *skb) } char __license[] SEC("license") = "GPL"; -int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf2.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf2.c index 3cc4c12817..ce97d141da 100644 --- a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf2.c +++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf2.c @@ -22,14 +22,14 @@ int subprog_tail(struct __sk_buff *skb) int count = 0; -SEC("classifier/0") -int bpf_func_0(struct __sk_buff *skb) +SEC("tc") +int classifier_0(struct __sk_buff *skb) { count++; return subprog_tail(skb); } -SEC("classifier") +SEC("tc") int entry(struct __sk_buff *skb) { bpf_tail_call_static(skb, &jmp_table, 0); @@ -38,4 +38,3 @@ int entry(struct __sk_buff *skb) } char __license[] SEC("license") = "GPL"; -int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf3.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf3.c index 0d5482bea6..7fab39a3bb 100644 --- a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf3.c +++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf3.c @@ -33,23 +33,23 @@ int subprog_tail(struct __sk_buff *skb) return skb->len * 2; } -SEC("classifier/0") -int bpf_func_0(struct __sk_buff *skb) +SEC("tc") +int classifier_0(struct __sk_buff *skb) { volatile char arr[128] = {}; return subprog_tail2(skb); } -SEC("classifier/1") -int bpf_func_1(struct __sk_buff *skb) +SEC("tc") +int classifier_1(struct __sk_buff *skb) { volatile char arr[128] = {}; return skb->len * 3; } -SEC("classifier") +SEC("tc") int entry(struct __sk_buff *skb) { volatile char arr[128] = {}; @@ -58,4 +58,3 @@ int entry(struct __sk_buff *skb) } char __license[] SEC("license") = "GPL"; -int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf4.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf4.c index e89368a50b..b67e8022d5 100644 --- a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf4.c +++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf4.c @@ -50,30 +50,29 @@ int subprog_tail(struct __sk_buff *skb) return skb->len; } -SEC("classifier/1") -int bpf_func_1(struct __sk_buff *skb) +SEC("tc") +int classifier_1(struct __sk_buff *skb) { return subprog_tail_2(skb); } -SEC("classifier/2") -int bpf_func_2(struct __sk_buff *skb) +SEC("tc") +int classifier_2(struct __sk_buff *skb) { count++; return subprog_tail_2(skb); } -SEC("classifier/0") -int bpf_func_0(struct __sk_buff *skb) +SEC("tc") +int classifier_0(struct __sk_buff *skb) { return subprog_tail_1(skb); } -SEC("classifier") +SEC("tc") int entry(struct __sk_buff *skb) { return subprog_tail(skb); } char __license[] SEC("license") = "GPL"; -int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/tcp_rtt.c b/tools/testing/selftests/bpf/progs/tcp_rtt.c index 0cb3204ddb..0988d79f15 100644 --- a/tools/testing/selftests/bpf/progs/tcp_rtt.c +++ b/tools/testing/selftests/bpf/progs/tcp_rtt.c @@ -3,7 +3,6 @@ #include char _license[] SEC("license") = "GPL"; -__u32 _version SEC("version") = 1; struct tcp_rtt_storage { __u32 invoked; diff --git a/tools/testing/selftests/bpf/progs/test_btf_haskv.c b/tools/testing/selftests/bpf/progs/test_btf_haskv.c index 31538c9ed1..160ead6c67 100644 --- a/tools/testing/selftests/bpf/progs/test_btf_haskv.c +++ b/tools/testing/selftests/bpf/progs/test_btf_haskv.c @@ -4,8 +4,6 @@ #include #include "bpf_legacy.h" -int _version SEC("version") = 1; - struct ipv_counts { unsigned int v4; unsigned int v6; diff --git a/tools/testing/selftests/bpf/progs/test_btf_map_in_map.c b/tools/testing/selftests/bpf/progs/test_btf_map_in_map.c index c1e0c8c7c5..c218cf8989 100644 --- a/tools/testing/selftests/bpf/progs/test_btf_map_in_map.c +++ b/tools/testing/selftests/bpf/progs/test_btf_map_in_map.c @@ -21,8 +21,8 @@ struct inner_map_sz2 { struct outer_arr { __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); __uint(max_entries, 3); - __uint(key_size, sizeof(int)); - __uint(value_size, sizeof(int)); + __type(key, int); + __type(value, int); /* it's possible to use anonymous struct as inner map definition here */ __array(values, struct { __uint(type, BPF_MAP_TYPE_ARRAY); @@ -61,8 +61,8 @@ struct inner_map_sz4 { struct outer_arr_dyn { __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); __uint(max_entries, 3); - __uint(key_size, sizeof(int)); - __uint(value_size, sizeof(int)); + __type(key, int); + __type(value, int); __array(values, struct { __uint(type, BPF_MAP_TYPE_ARRAY); __uint(map_flags, BPF_F_INNER_MAP); @@ -81,7 +81,7 @@ struct outer_arr_dyn { struct outer_hash { __uint(type, BPF_MAP_TYPE_HASH_OF_MAPS); __uint(max_entries, 5); - __uint(key_size, sizeof(int)); + __type(key, int); /* Here everything works flawlessly due to reuse of struct inner_map * and compiler will complain at the attempt to use non-inner_map * references below. This is great experience. @@ -111,8 +111,8 @@ struct sockarr_sz2 { struct outer_sockarr_sz1 { __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); __uint(max_entries, 1); - __uint(key_size, sizeof(int)); - __uint(value_size, sizeof(int)); + __type(key, int); + __type(value, int); __array(values, struct sockarr_sz1); } outer_sockarr SEC(".maps") = { .values = { (void *)&sockarr_sz1 }, diff --git a/tools/testing/selftests/bpf/progs/test_btf_newkv.c b/tools/testing/selftests/bpf/progs/test_btf_newkv.c index 6c55601627..1884a5bd10 100644 --- a/tools/testing/selftests/bpf/progs/test_btf_newkv.c +++ b/tools/testing/selftests/bpf/progs/test_btf_newkv.c @@ -4,8 +4,6 @@ #include #include "bpf_legacy.h" -int _version SEC("version") = 1; - struct ipv_counts { unsigned int v4; unsigned int v6; diff --git a/tools/testing/selftests/bpf/progs/test_btf_nokv.c b/tools/testing/selftests/bpf/progs/test_btf_nokv.c index 506da7fd2d..15e0f9945f 100644 --- a/tools/testing/selftests/bpf/progs/test_btf_nokv.c +++ b/tools/testing/selftests/bpf/progs/test_btf_nokv.c @@ -3,8 +3,6 @@ #include #include -int _version SEC("version") = 1; - struct ipv_counts { unsigned int v4; unsigned int v6; diff --git a/tools/testing/selftests/bpf/progs/test_btf_skc_cls_ingress.c b/tools/testing/selftests/bpf/progs/test_btf_skc_cls_ingress.c index 9a6b85dd52..e2bea4da19 100644 --- a/tools/testing/selftests/bpf/progs/test_btf_skc_cls_ingress.c +++ b/tools/testing/selftests/bpf/progs/test_btf_skc_cls_ingress.c @@ -145,7 +145,7 @@ static int handle_ip6_tcp(struct ipv6hdr *ip6h, struct __sk_buff *skb) return TC_ACT_OK; } -SEC("classifier/ingress") +SEC("tc") int cls_ingress(struct __sk_buff *skb) { struct ipv6hdr *ip6h; diff --git a/tools/testing/selftests/bpf/progs/test_cgroup_link.c b/tools/testing/selftests/bpf/progs/test_cgroup_link.c index 77e47b9e44..4faba88e45 100644 --- a/tools/testing/selftests/bpf/progs/test_cgroup_link.c +++ b/tools/testing/selftests/bpf/progs/test_cgroup_link.c @@ -6,14 +6,14 @@ int calls = 0; int alt_calls = 0; -SEC("cgroup_skb/egress1") +SEC("cgroup_skb/egress") int egress(struct __sk_buff *skb) { __sync_fetch_and_add(&calls, 1); return 1; } -SEC("cgroup_skb/egress2") +SEC("cgroup_skb/egress") int egress_alt(struct __sk_buff *skb) { __sync_fetch_and_add(&alt_calls, 1); diff --git a/tools/testing/selftests/bpf/progs/test_check_mtu.c b/tools/testing/selftests/bpf/progs/test_check_mtu.c index 71184af577..2ec1de11a3 100644 --- a/tools/testing/selftests/bpf/progs/test_check_mtu.c +++ b/tools/testing/selftests/bpf/progs/test_check_mtu.c @@ -153,7 +153,7 @@ int xdp_input_len_exceed(struct xdp_md *ctx) return retval; } -SEC("classifier") +SEC("tc") int tc_use_helper(struct __sk_buff *ctx) { int retval = BPF_OK; /* Expected retval on successful test */ @@ -172,7 +172,7 @@ int tc_use_helper(struct __sk_buff *ctx) return retval; } -SEC("classifier") +SEC("tc") int tc_exceed_mtu(struct __sk_buff *ctx) { __u32 ifindex = GLOBAL_USER_IFINDEX; @@ -196,7 +196,7 @@ int tc_exceed_mtu(struct __sk_buff *ctx) return retval; } -SEC("classifier") +SEC("tc") int tc_exceed_mtu_da(struct __sk_buff *ctx) { /* SKB Direct-Access variant */ @@ -223,7 +223,7 @@ int tc_exceed_mtu_da(struct __sk_buff *ctx) return retval; } -SEC("classifier") +SEC("tc") int tc_minus_delta(struct __sk_buff *ctx) { int retval = BPF_OK; /* Expected retval on successful test */ @@ -245,7 +245,7 @@ int tc_minus_delta(struct __sk_buff *ctx) return retval; } -SEC("classifier") +SEC("tc") int tc_input_len(struct __sk_buff *ctx) { int retval = BPF_OK; /* Expected retval on successful test */ @@ -265,7 +265,7 @@ int tc_input_len(struct __sk_buff *ctx) return retval; } -SEC("classifier") +SEC("tc") int tc_input_len_exceed(struct __sk_buff *ctx) { int retval = BPF_DROP; /* Fail */ diff --git a/tools/testing/selftests/bpf/progs/test_cls_redirect.c b/tools/testing/selftests/bpf/progs/test_cls_redirect.c index e2a5acc478..2833ad722c 100644 --- a/tools/testing/selftests/bpf/progs/test_cls_redirect.c +++ b/tools/testing/selftests/bpf/progs/test_cls_redirect.c @@ -928,7 +928,7 @@ static INLINING verdict_t process_ipv6(buf_t *pkt, metrics_t *metrics) } } -SEC("classifier/cls_redirect") +SEC("tc") int cls_redirect(struct __sk_buff *skb) { metrics_t *metrics = get_global_metrics(); diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_mods.c b/tools/testing/selftests/bpf/progs/test_core_reloc_mods.c index 8b533db4a7..b2ded49757 100644 --- a/tools/testing/selftests/bpf/progs/test_core_reloc_mods.c +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_mods.c @@ -42,7 +42,16 @@ struct core_reloc_mods { core_reloc_mods_substruct_t h; }; +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ #define CORE_READ(dst, src) bpf_core_read(dst, sizeof(*(dst)), src) +#else +#define CORE_READ(dst, src) ({ \ + int __sz = sizeof(*(dst)) < sizeof(*(src)) ? sizeof(*(dst)) : \ + sizeof(*(src)); \ + bpf_core_read((char *)(dst) + sizeof(*(dst)) - __sz, __sz, \ + (const char *)(src) + sizeof(*(src)) - __sz); \ +}) +#endif SEC("raw_tracepoint/sys_enter") int test_core_mods(void *ctx) diff --git a/tools/testing/selftests/bpf/progs/test_enable_stats.c b/tools/testing/selftests/bpf/progs/test_enable_stats.c index 01a002ade5..1705097d01 100644 --- a/tools/testing/selftests/bpf/progs/test_enable_stats.c +++ b/tools/testing/selftests/bpf/progs/test_enable_stats.c @@ -13,6 +13,6 @@ __u64 count = 0; SEC("raw_tracepoint/sys_enter") int test_enable_stats(void *ctx) { - count += 1; + __sync_fetch_and_add(&count, 1); return 0; } diff --git a/tools/testing/selftests/bpf/progs/test_global_data.c b/tools/testing/selftests/bpf/progs/test_global_data.c index 1319be1c54..719e314ef3 100644 --- a/tools/testing/selftests/bpf/progs/test_global_data.c +++ b/tools/testing/selftests/bpf/progs/test_global_data.c @@ -68,7 +68,7 @@ static struct foo struct3 = { bpf_map_update_elem(&result_##map, &key, var, 0); \ } while (0) -SEC("classifier/static_data_load") +SEC("tc") int load_static_data(struct __sk_buff *skb) { static const __u64 bar = ~0; diff --git a/tools/testing/selftests/bpf/progs/test_global_func1.c b/tools/testing/selftests/bpf/progs/test_global_func1.c index 880260f6d5..7b42dad187 100644 --- a/tools/testing/selftests/bpf/progs/test_global_func1.c +++ b/tools/testing/selftests/bpf/progs/test_global_func1.c @@ -38,7 +38,7 @@ int f3(int val, struct __sk_buff *skb, int var) return skb->ifindex * val * var; } -SEC("classifier/test") +SEC("tc") int test_cls(struct __sk_buff *skb) { return f0(1, skb) + f1(skb) + f2(2, skb) + f3(3, skb, 4); diff --git a/tools/testing/selftests/bpf/progs/test_global_func3.c b/tools/testing/selftests/bpf/progs/test_global_func3.c index 86f0ecb304..01bf8275df 100644 --- a/tools/testing/selftests/bpf/progs/test_global_func3.c +++ b/tools/testing/selftests/bpf/progs/test_global_func3.c @@ -54,7 +54,7 @@ int f8(struct __sk_buff *skb) } #endif -SEC("classifier/test") +SEC("tc") int test_cls(struct __sk_buff *skb) { #ifndef NO_FN8 diff --git a/tools/testing/selftests/bpf/progs/test_global_func5.c b/tools/testing/selftests/bpf/progs/test_global_func5.c index 260c25b827..9248d03e0d 100644 --- a/tools/testing/selftests/bpf/progs/test_global_func5.c +++ b/tools/testing/selftests/bpf/progs/test_global_func5.c @@ -24,7 +24,7 @@ int f3(int val, struct __sk_buff *skb) return skb->ifindex * val; } -SEC("classifier/test") +SEC("tc") int test_cls(struct __sk_buff *skb) { return f1(skb) + f2(2, skb) + f3(3, skb); diff --git a/tools/testing/selftests/bpf/progs/test_global_func6.c b/tools/testing/selftests/bpf/progs/test_global_func6.c index 69e19c64e1..af8c78bdfb 100644 --- a/tools/testing/selftests/bpf/progs/test_global_func6.c +++ b/tools/testing/selftests/bpf/progs/test_global_func6.c @@ -24,7 +24,7 @@ int f3(int val, struct __sk_buff *skb) return skb->ifindex * val; } -SEC("classifier/test") +SEC("tc") int test_cls(struct __sk_buff *skb) { return f1(skb) + f2(2, skb) + f3(3, skb); diff --git a/tools/testing/selftests/bpf/progs/test_global_func7.c b/tools/testing/selftests/bpf/progs/test_global_func7.c index 309b3f6136..6cb8e2f525 100644 --- a/tools/testing/selftests/bpf/progs/test_global_func7.c +++ b/tools/testing/selftests/bpf/progs/test_global_func7.c @@ -10,7 +10,7 @@ void foo(struct __sk_buff *skb) skb->tc_index = 0; } -SEC("classifier/test") +SEC("tc") int test_cls(struct __sk_buff *skb) { foo(skb); diff --git a/tools/testing/selftests/bpf/progs/test_ksyms_module.c b/tools/testing/selftests/bpf/progs/test_ksyms_module.c index d6a0b3086b..0650d918c0 100644 --- a/tools/testing/selftests/bpf/progs/test_ksyms_module.c +++ b/tools/testing/selftests/bpf/progs/test_ksyms_module.c @@ -2,24 +2,48 @@ /* Copyright (c) 2021 Facebook */ #include "vmlinux.h" - #include +#define X_0(x) +#define X_1(x) x X_0(x) +#define X_2(x) x X_1(x) +#define X_3(x) x X_2(x) +#define X_4(x) x X_3(x) +#define X_5(x) x X_4(x) +#define X_6(x) x X_5(x) +#define X_7(x) x X_6(x) +#define X_8(x) x X_7(x) +#define X_9(x) x X_8(x) +#define X_10(x) x X_9(x) +#define REPEAT_256(Y) X_2(X_10(X_10(Y))) X_5(X_10(Y)) X_6(Y) + extern const int bpf_testmod_ksym_percpu __ksym; +extern void bpf_testmod_test_mod_kfunc(int i) __ksym; +extern void bpf_testmod_invalid_mod_kfunc(void) __ksym __weak; -int out_mod_ksym_global = 0; -bool triggered = false; +int out_bpf_testmod_ksym = 0; +const volatile int x = 0; -SEC("raw_tp/sys_enter") -int handler(const void *ctx) +SEC("tc") +int load(struct __sk_buff *skb) { - int *val; - __u32 cpu; - - val = (int *)bpf_this_cpu_ptr(&bpf_testmod_ksym_percpu); - out_mod_ksym_global = *val; - triggered = true; + /* This will be kept by clang, but removed by verifier. Since it is + * marked as __weak, libbpf and gen_loader don't error out if BTF ID + * is not found for it, instead imm and off is set to 0 for it. + */ + if (x) + bpf_testmod_invalid_mod_kfunc(); + bpf_testmod_test_mod_kfunc(42); + out_bpf_testmod_ksym = *(int *)bpf_this_cpu_ptr(&bpf_testmod_ksym_percpu); + return 0; +} +SEC("tc") +int load_256(struct __sk_buff *skb) +{ + /* this will fail if kfunc doesn't reuse its own btf fd index */ + REPEAT_256(bpf_testmod_test_mod_kfunc(42);); + bpf_testmod_test_mod_kfunc(42); return 0; } diff --git a/tools/testing/selftests/bpf/progs/test_l4lb.c b/tools/testing/selftests/bpf/progs/test_l4lb.c index 33493911d8..c26057ec46 100644 --- a/tools/testing/selftests/bpf/progs/test_l4lb.c +++ b/tools/testing/selftests/bpf/progs/test_l4lb.c @@ -21,8 +21,6 @@ #include "test_iptunnel_common.h" #include -int _version SEC("version") = 1; - static inline __u32 rol32(__u32 word, unsigned int shift) { return (word << shift) | (word >> ((-shift) & 31)); @@ -450,7 +448,7 @@ static __always_inline int process_packet(void *data, __u64 off, void *data_end, return bpf_redirect(ifindex, 0); } -SEC("l4lb-demo") +SEC("tc") int balancer_ingress(struct __sk_buff *ctx) { void *data_end = (void *)(long)ctx->data_end; diff --git a/tools/testing/selftests/bpf/progs/test_l4lb_noinline.c b/tools/testing/selftests/bpf/progs/test_l4lb_noinline.c index b9e2753f4f..19e4d2071c 100644 --- a/tools/testing/selftests/bpf/progs/test_l4lb_noinline.c +++ b/tools/testing/selftests/bpf/progs/test_l4lb_noinline.c @@ -447,7 +447,7 @@ static __noinline int process_packet(void *data, __u64 off, void *data_end, return bpf_redirect(ifindex, 0); } -SEC("l4lb-demo") +SEC("tc") int balancer_ingress(struct __sk_buff *ctx) { void *data_end = (void *)(long)ctx->data_end; diff --git a/tools/testing/selftests/bpf/progs/test_map_in_map.c b/tools/testing/selftests/bpf/progs/test_map_in_map.c index 1cfeb940cf..f416032ba8 100644 --- a/tools/testing/selftests/bpf/progs/test_map_in_map.c +++ b/tools/testing/selftests/bpf/progs/test_map_in_map.c @@ -9,21 +9,19 @@ struct { __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); __uint(max_entries, 1); __uint(map_flags, 0); - __uint(key_size, sizeof(__u32)); - /* must be sizeof(__u32) for map in map */ - __uint(value_size, sizeof(__u32)); + __type(key, __u32); + __type(value, __u32); } mim_array SEC(".maps"); struct { __uint(type, BPF_MAP_TYPE_HASH_OF_MAPS); __uint(max_entries, 1); __uint(map_flags, 0); - __uint(key_size, sizeof(int)); - /* must be sizeof(__u32) for map in map */ - __uint(value_size, sizeof(__u32)); + __type(key, int); + __type(value, __u32); } mim_hash SEC(".maps"); -SEC("xdp_mimtest") +SEC("xdp") int xdp_mimtest0(struct xdp_md *ctx) { int value = 123; @@ -49,5 +47,4 @@ int xdp_mimtest0(struct xdp_md *ctx) return XDP_PASS; } -int _version SEC("version") = 1; char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_map_in_map_invalid.c b/tools/testing/selftests/bpf/progs/test_map_in_map_invalid.c index 703c08e064..9c7d75cf0b 100644 --- a/tools/testing/selftests/bpf/progs/test_map_in_map_invalid.c +++ b/tools/testing/selftests/bpf/progs/test_map_in_map_invalid.c @@ -13,7 +13,7 @@ struct inner { struct { __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); __uint(max_entries, 0); /* This will make map creation to fail */ - __uint(key_size, sizeof(__u32)); + __type(key, __u32); __array(values, struct inner); } mim SEC(".maps"); diff --git a/tools/testing/selftests/bpf/progs/test_map_lock.c b/tools/testing/selftests/bpf/progs/test_map_lock.c index b5c07ae7b6..acf073db9e 100644 --- a/tools/testing/selftests/bpf/progs/test_map_lock.c +++ b/tools/testing/selftests/bpf/progs/test_map_lock.c @@ -30,7 +30,7 @@ struct { __type(value, struct array_elem); } array_map SEC(".maps"); -SEC("map_lock_demo") +SEC("cgroup/skb") int bpf_map_lock_test(struct __sk_buff *skb) { struct hmap_elem zero = {}, *val; diff --git a/tools/testing/selftests/bpf/progs/test_misc_tcp_hdr_options.c b/tools/testing/selftests/bpf/progs/test_misc_tcp_hdr_options.c index 6077a02509..2c121c5d66 100644 --- a/tools/testing/selftests/bpf/progs/test_misc_tcp_hdr_options.c +++ b/tools/testing/selftests/bpf/progs/test_misc_tcp_hdr_options.c @@ -293,7 +293,7 @@ static int handle_passive_estab(struct bpf_sock_ops *skops) return check_active_hdr_in(skops); } -SEC("sockops/misc_estab") +SEC("sockops") int misc_estab(struct bpf_sock_ops *skops) { int true_val = 1; diff --git a/tools/testing/selftests/bpf/progs/test_module_attach.c b/tools/testing/selftests/bpf/progs/test_module_attach.c index bd37ceec55..50ce16d02d 100644 --- a/tools/testing/selftests/bpf/progs/test_module_attach.c +++ b/tools/testing/selftests/bpf/progs/test_module_attach.c @@ -27,6 +27,20 @@ int BPF_PROG(handle_raw_tp_bare, return 0; } +int raw_tp_writable_bare_in_val = 0; +int raw_tp_writable_bare_early_ret = 0; +int raw_tp_writable_bare_out_val = 0; + +SEC("raw_tp.w/bpf_testmod_test_writable_bare") +int BPF_PROG(handle_raw_tp_writable_bare, + struct bpf_testmod_test_writable_ctx *writable) +{ + raw_tp_writable_bare_in_val = writable->val; + writable->early_ret = raw_tp_writable_bare_early_ret; + writable->val = raw_tp_writable_bare_out_val; + return 0; +} + __u32 tp_btf_read_sz = 0; SEC("tp_btf/bpf_testmod_test_read") @@ -73,6 +87,18 @@ int BPF_PROG(handle_fexit, return 0; } +SEC("fexit/bpf_testmod_return_ptr") +int BPF_PROG(handle_fexit_ret, int arg, struct file *ret) +{ + long buf = 0; + + bpf_probe_read_kernel(&buf, 8, ret); + bpf_probe_read_kernel(&buf, 8, (char *)ret + 256); + *(volatile long long *)ret; + *(volatile int *)&ret->f_mode; + return 0; +} + __u32 fmod_ret_read_sz = 0; SEC("fmod_ret/bpf_testmod_test_read") diff --git a/tools/testing/selftests/bpf/progs/test_pe_preserve_elems.c b/tools/testing/selftests/bpf/progs/test_pe_preserve_elems.c index fb22de7c36..1249a94569 100644 --- a/tools/testing/selftests/bpf/progs/test_pe_preserve_elems.c +++ b/tools/testing/selftests/bpf/progs/test_pe_preserve_elems.c @@ -7,15 +7,15 @@ struct { __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); __uint(max_entries, 1); - __uint(key_size, sizeof(int)); - __uint(value_size, sizeof(int)); + __type(key, int); + __type(value, int); } array_1 SEC(".maps"); struct { __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); __uint(max_entries, 1); - __uint(key_size, sizeof(int)); - __uint(value_size, sizeof(int)); + __type(key, int); + __type(value, int); __uint(map_flags, BPF_F_PRESERVE_ELEMS); } array_2 SEC(".maps"); diff --git a/tools/testing/selftests/bpf/progs/test_perf_buffer.c b/tools/testing/selftests/bpf/progs/test_perf_buffer.c index 8207a2dc2f..17d5b67744 100644 --- a/tools/testing/selftests/bpf/progs/test_perf_buffer.c +++ b/tools/testing/selftests/bpf/progs/test_perf_buffer.c @@ -6,20 +6,36 @@ #include #include +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, int); + __type(value, int); + __uint(max_entries, 1); +} my_pid_map SEC(".maps"); + struct { __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); - __uint(key_size, sizeof(int)); - __uint(value_size, sizeof(int)); + __type(key, int); + __type(value, int); } perf_buf_map SEC(".maps"); SEC("tp/raw_syscalls/sys_enter") int handle_sys_enter(void *ctx) { + int zero = 0, *my_pid, cur_pid; int cpu = bpf_get_smp_processor_id(); + my_pid = bpf_map_lookup_elem(&my_pid_map, &zero); + if (!my_pid) + return 1; + + cur_pid = bpf_get_current_pid_tgid() >> 32; + if (cur_pid != *my_pid) + return 1; + bpf_perf_event_output(ctx, &perf_buf_map, BPF_F_CURRENT_CPU, &cpu, sizeof(cpu)); - return 0; + return 1; } char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_pinning.c b/tools/testing/selftests/bpf/progs/test_pinning.c index 4ef2630292..0facea6cbb 100644 --- a/tools/testing/selftests/bpf/progs/test_pinning.c +++ b/tools/testing/selftests/bpf/progs/test_pinning.c @@ -3,8 +3,6 @@ #include #include -int _version SEC("version") = 1; - struct { __uint(type, BPF_MAP_TYPE_ARRAY); __uint(max_entries, 1); diff --git a/tools/testing/selftests/bpf/progs/test_pinning_invalid.c b/tools/testing/selftests/bpf/progs/test_pinning_invalid.c index 5412e0c732..2a56db1094 100644 --- a/tools/testing/selftests/bpf/progs/test_pinning_invalid.c +++ b/tools/testing/selftests/bpf/progs/test_pinning_invalid.c @@ -3,8 +3,6 @@ #include #include -int _version SEC("version") = 1; - struct { __uint(type, BPF_MAP_TYPE_ARRAY); __uint(max_entries, 1); diff --git a/tools/testing/selftests/bpf/progs/test_pkt_access.c b/tools/testing/selftests/bpf/progs/test_pkt_access.c index 8520510645..0558544e1f 100644 --- a/tools/testing/selftests/bpf/progs/test_pkt_access.c +++ b/tools/testing/selftests/bpf/progs/test_pkt_access.c @@ -15,7 +15,6 @@ #include #define barrier() __asm__ __volatile__("": : :"memory") -int _version SEC("version") = 1; /* llvm will optimize both subprograms into exactly the same BPF assembly * @@ -97,7 +96,7 @@ int test_pkt_write_access_subprog(struct __sk_buff *skb, __u32 off) return 0; } -SEC("classifier/test_pkt_access") +SEC("tc") int test_pkt_access(struct __sk_buff *skb) { void *data_end = (void *)(long)skb->data_end; diff --git a/tools/testing/selftests/bpf/progs/test_pkt_md_access.c b/tools/testing/selftests/bpf/progs/test_pkt_md_access.c index 610c74ea9f..d1839366f3 100644 --- a/tools/testing/selftests/bpf/progs/test_pkt_md_access.c +++ b/tools/testing/selftests/bpf/progs/test_pkt_md_access.c @@ -7,8 +7,6 @@ #include #include -int _version SEC("version") = 1; - #if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ #define TEST_FIELD(TYPE, FIELD, MASK) \ { \ @@ -27,7 +25,7 @@ int _version SEC("version") = 1; } #endif -SEC("classifier/test_pkt_md_access") +SEC("tc") int test_pkt_md_access(struct __sk_buff *skb) { TEST_FIELD(__u8, len, 0xFF); diff --git a/tools/testing/selftests/bpf/progs/test_probe_user.c b/tools/testing/selftests/bpf/progs/test_probe_user.c index 89b3532ccc..8812a90da4 100644 --- a/tools/testing/selftests/bpf/progs/test_probe_user.c +++ b/tools/testing/selftests/bpf/progs/test_probe_user.c @@ -8,13 +8,37 @@ #include #include +#if defined(__TARGET_ARCH_x86) +#define SYSCALL_WRAPPER 1 +#define SYS_PREFIX "__x64_" +#elif defined(__TARGET_ARCH_s390) +#define SYSCALL_WRAPPER 1 +#define SYS_PREFIX "__s390x_" +#elif defined(__TARGET_ARCH_arm64) +#define SYSCALL_WRAPPER 1 +#define SYS_PREFIX "__arm64_" +#else +#define SYSCALL_WRAPPER 0 +#define SYS_PREFIX "" +#endif + static struct sockaddr_in old; -SEC("kprobe/__sys_connect") +SEC("kprobe/" SYS_PREFIX "sys_connect") int BPF_KPROBE(handle_sys_connect) { - void *ptr = (void *)PT_REGS_PARM2(ctx); +#if SYSCALL_WRAPPER == 1 + struct pt_regs *real_regs; +#endif struct sockaddr_in new; + void *ptr; + +#if SYSCALL_WRAPPER == 0 + ptr = (void *)PT_REGS_PARM2(ctx); +#else + real_regs = (struct pt_regs *)PT_REGS_PARM1(ctx); + bpf_probe_read_kernel(&ptr, sizeof(ptr), &PT_REGS_PARM2(real_regs)); +#endif bpf_probe_read_user(&old, sizeof(old), ptr); __builtin_memset(&new, 0xab, sizeof(new)); diff --git a/tools/testing/selftests/bpf/progs/test_queue_stack_map.h b/tools/testing/selftests/bpf/progs/test_queue_stack_map.h index 4dd9806ad7..648e8cab7a 100644 --- a/tools/testing/selftests/bpf/progs/test_queue_stack_map.h +++ b/tools/testing/selftests/bpf/progs/test_queue_stack_map.h @@ -8,8 +8,6 @@ #include #include -int _version SEC("version") = 1; - struct { __uint(type, MAP_TYPE); __uint(max_entries, 32); @@ -26,7 +24,7 @@ struct { __uint(value_size, sizeof(__u32)); } map_out SEC(".maps"); -SEC("test") +SEC("tc") int _test(struct __sk_buff *skb) { void *data_end = (void *)(long)skb->data_end; diff --git a/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c b/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c index 26e77dcc7e..7d56ed47cd 100644 --- a/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c +++ b/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c @@ -15,8 +15,6 @@ #include #include "test_select_reuseport_common.h" -int _version SEC("version") = 1; - #ifndef offsetof #define offsetof(TYPE, MEMBER) ((size_t) &((TYPE *)0)->MEMBER) #endif @@ -24,8 +22,8 @@ int _version SEC("version") = 1; struct { __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); __uint(max_entries, 1); - __uint(key_size, sizeof(__u32)); - __uint(value_size, sizeof(__u32)); + __type(key, __u32); + __type(value, __u32); } outer_map SEC(".maps"); struct { diff --git a/tools/testing/selftests/bpf/progs/test_sk_assign.c b/tools/testing/selftests/bpf/progs/test_sk_assign.c index 1ecd987005..02f79356d5 100644 --- a/tools/testing/selftests/bpf/progs/test_sk_assign.c +++ b/tools/testing/selftests/bpf/progs/test_sk_assign.c @@ -36,7 +36,6 @@ struct { .pinning = PIN_GLOBAL_NS, }; -int _version SEC("version") = 1; char _license[] SEC("license") = "GPL"; /* Fill 'tuple' with L3 info, and attempt to find L4. On fail, return NULL. */ @@ -159,7 +158,7 @@ handle_tcp(struct __sk_buff *skb, struct bpf_sock_tuple *tuple, bool ipv4) return ret; } -SEC("classifier/sk_assign_test") +SEC("tc") int bpf_sk_assign_test(struct __sk_buff *skb) { struct bpf_sock_tuple *tuple, ln = {0}; diff --git a/tools/testing/selftests/bpf/progs/test_sk_lookup.c b/tools/testing/selftests/bpf/progs/test_sk_lookup.c index ac6f7f205e..83b0aaa52e 100644 --- a/tools/testing/selftests/bpf/progs/test_sk_lookup.c +++ b/tools/testing/selftests/bpf/progs/test_sk_lookup.c @@ -72,32 +72,40 @@ static const __u16 DST_PORT = 7007; /* Host byte order */ static const __u32 DST_IP4 = IP4(127, 0, 0, 1); static const __u32 DST_IP6[] = IP6(0xfd000000, 0x0, 0x0, 0x00000001); -SEC("sk_lookup/lookup_pass") +SEC("sk_lookup") int lookup_pass(struct bpf_sk_lookup *ctx) { return SK_PASS; } -SEC("sk_lookup/lookup_drop") +SEC("sk_lookup") int lookup_drop(struct bpf_sk_lookup *ctx) { return SK_DROP; } -SEC("sk_reuseport/reuse_pass") +SEC("sk_lookup") +int check_ifindex(struct bpf_sk_lookup *ctx) +{ + if (ctx->ingress_ifindex == 1) + return SK_DROP; + return SK_PASS; +} + +SEC("sk_reuseport") int reuseport_pass(struct sk_reuseport_md *ctx) { return SK_PASS; } -SEC("sk_reuseport/reuse_drop") +SEC("sk_reuseport") int reuseport_drop(struct sk_reuseport_md *ctx) { return SK_DROP; } /* Redirect packets destined for port DST_PORT to socket at redir_map[0]. */ -SEC("sk_lookup/redir_port") +SEC("sk_lookup") int redir_port(struct bpf_sk_lookup *ctx) { struct bpf_sock *sk; @@ -116,7 +124,7 @@ int redir_port(struct bpf_sk_lookup *ctx) } /* Redirect packets destined for DST_IP4 address to socket at redir_map[0]. */ -SEC("sk_lookup/redir_ip4") +SEC("sk_lookup") int redir_ip4(struct bpf_sk_lookup *ctx) { struct bpf_sock *sk; @@ -139,7 +147,7 @@ int redir_ip4(struct bpf_sk_lookup *ctx) } /* Redirect packets destined for DST_IP6 address to socket at redir_map[0]. */ -SEC("sk_lookup/redir_ip6") +SEC("sk_lookup") int redir_ip6(struct bpf_sk_lookup *ctx) { struct bpf_sock *sk; @@ -164,7 +172,7 @@ int redir_ip6(struct bpf_sk_lookup *ctx) return err ? SK_DROP : SK_PASS; } -SEC("sk_lookup/select_sock_a") +SEC("sk_lookup") int select_sock_a(struct bpf_sk_lookup *ctx) { struct bpf_sock *sk; @@ -179,7 +187,7 @@ int select_sock_a(struct bpf_sk_lookup *ctx) return err ? SK_DROP : SK_PASS; } -SEC("sk_lookup/select_sock_a_no_reuseport") +SEC("sk_lookup") int select_sock_a_no_reuseport(struct bpf_sk_lookup *ctx) { struct bpf_sock *sk; @@ -194,7 +202,7 @@ int select_sock_a_no_reuseport(struct bpf_sk_lookup *ctx) return err ? SK_DROP : SK_PASS; } -SEC("sk_reuseport/select_sock_b") +SEC("sk_reuseport") int select_sock_b(struct sk_reuseport_md *ctx) { __u32 key = KEY_SERVER_B; @@ -205,7 +213,7 @@ int select_sock_b(struct sk_reuseport_md *ctx) } /* Check that bpf_sk_assign() returns -EEXIST if socket already selected. */ -SEC("sk_lookup/sk_assign_eexist") +SEC("sk_lookup") int sk_assign_eexist(struct bpf_sk_lookup *ctx) { struct bpf_sock *sk; @@ -238,7 +246,7 @@ int sk_assign_eexist(struct bpf_sk_lookup *ctx) } /* Check that bpf_sk_assign(BPF_SK_LOOKUP_F_REPLACE) can override selection. */ -SEC("sk_lookup/sk_assign_replace_flag") +SEC("sk_lookup") int sk_assign_replace_flag(struct bpf_sk_lookup *ctx) { struct bpf_sock *sk; @@ -270,7 +278,7 @@ int sk_assign_replace_flag(struct bpf_sk_lookup *ctx) } /* Check that bpf_sk_assign(sk=NULL) is accepted. */ -SEC("sk_lookup/sk_assign_null") +SEC("sk_lookup") int sk_assign_null(struct bpf_sk_lookup *ctx) { struct bpf_sock *sk = NULL; @@ -313,7 +321,7 @@ int sk_assign_null(struct bpf_sk_lookup *ctx) } /* Check that selected sk is accessible through context. */ -SEC("sk_lookup/access_ctx_sk") +SEC("sk_lookup") int access_ctx_sk(struct bpf_sk_lookup *ctx) { struct bpf_sock *sk1 = NULL, *sk2 = NULL; @@ -379,7 +387,7 @@ int access_ctx_sk(struct bpf_sk_lookup *ctx) * are not covered because they give bogus results, that is the * verifier ignores the offset. */ -SEC("sk_lookup/ctx_narrow_access") +SEC("sk_lookup") int ctx_narrow_access(struct bpf_sk_lookup *ctx) { struct bpf_sock *sk; @@ -553,7 +561,7 @@ int ctx_narrow_access(struct bpf_sk_lookup *ctx) } /* Check that sk_assign rejects SERVER_A socket with -ESOCKNOSUPPORT */ -SEC("sk_lookup/sk_assign_esocknosupport") +SEC("sk_lookup") int sk_assign_esocknosupport(struct bpf_sk_lookup *ctx) { struct bpf_sock *sk; @@ -578,28 +586,28 @@ int sk_assign_esocknosupport(struct bpf_sk_lookup *ctx) return ret; } -SEC("sk_lookup/multi_prog_pass1") +SEC("sk_lookup") int multi_prog_pass1(struct bpf_sk_lookup *ctx) { bpf_map_update_elem(&run_map, &KEY_PROG1, &PROG_DONE, BPF_ANY); return SK_PASS; } -SEC("sk_lookup/multi_prog_pass2") +SEC("sk_lookup") int multi_prog_pass2(struct bpf_sk_lookup *ctx) { bpf_map_update_elem(&run_map, &KEY_PROG2, &PROG_DONE, BPF_ANY); return SK_PASS; } -SEC("sk_lookup/multi_prog_drop1") +SEC("sk_lookup") int multi_prog_drop1(struct bpf_sk_lookup *ctx) { bpf_map_update_elem(&run_map, &KEY_PROG1, &PROG_DONE, BPF_ANY); return SK_DROP; } -SEC("sk_lookup/multi_prog_drop2") +SEC("sk_lookup") int multi_prog_drop2(struct bpf_sk_lookup *ctx) { bpf_map_update_elem(&run_map, &KEY_PROG2, &PROG_DONE, BPF_ANY); @@ -623,7 +631,7 @@ static __always_inline int select_server_a(struct bpf_sk_lookup *ctx) return SK_PASS; } -SEC("sk_lookup/multi_prog_redir1") +SEC("sk_lookup") int multi_prog_redir1(struct bpf_sk_lookup *ctx) { int ret; @@ -633,7 +641,7 @@ int multi_prog_redir1(struct bpf_sk_lookup *ctx) return SK_PASS; } -SEC("sk_lookup/multi_prog_redir2") +SEC("sk_lookup") int multi_prog_redir2(struct bpf_sk_lookup *ctx) { int ret; @@ -644,4 +652,3 @@ int multi_prog_redir2(struct bpf_sk_lookup *ctx) } char _license[] SEC("license") = "Dual BSD/GPL"; -__u32 _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c b/tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c index 8249075f08..40f161480a 100644 --- a/tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c +++ b/tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c @@ -15,7 +15,6 @@ #include #include -int _version SEC("version") = 1; char _license[] SEC("license") = "GPL"; /* Fill 'tuple' with L3 info, and attempt to find L4. On fail, return NULL. */ @@ -53,8 +52,8 @@ static struct bpf_sock_tuple *get_tuple(void *data, __u64 nh_off, return result; } -SEC("classifier/sk_lookup_success") -int bpf_sk_lookup_test0(struct __sk_buff *skb) +SEC("tc") +int sk_lookup_success(struct __sk_buff *skb) { void *data_end = (void *)(long)skb->data_end; void *data = (void *)(long)skb->data; @@ -79,8 +78,8 @@ int bpf_sk_lookup_test0(struct __sk_buff *skb) return sk ? TC_ACT_OK : TC_ACT_UNSPEC; } -SEC("classifier/sk_lookup_success_simple") -int bpf_sk_lookup_test1(struct __sk_buff *skb) +SEC("tc") +int sk_lookup_success_simple(struct __sk_buff *skb) { struct bpf_sock_tuple tuple = {}; struct bpf_sock *sk; @@ -91,8 +90,8 @@ int bpf_sk_lookup_test1(struct __sk_buff *skb) return 0; } -SEC("classifier/err_use_after_free") -int bpf_sk_lookup_uaf(struct __sk_buff *skb) +SEC("tc") +int err_use_after_free(struct __sk_buff *skb) { struct bpf_sock_tuple tuple = {}; struct bpf_sock *sk; @@ -106,8 +105,8 @@ int bpf_sk_lookup_uaf(struct __sk_buff *skb) return family; } -SEC("classifier/err_modify_sk_pointer") -int bpf_sk_lookup_modptr(struct __sk_buff *skb) +SEC("tc") +int err_modify_sk_pointer(struct __sk_buff *skb) { struct bpf_sock_tuple tuple = {}; struct bpf_sock *sk; @@ -121,8 +120,8 @@ int bpf_sk_lookup_modptr(struct __sk_buff *skb) return 0; } -SEC("classifier/err_modify_sk_or_null_pointer") -int bpf_sk_lookup_modptr_or_null(struct __sk_buff *skb) +SEC("tc") +int err_modify_sk_or_null_pointer(struct __sk_buff *skb) { struct bpf_sock_tuple tuple = {}; struct bpf_sock *sk; @@ -135,8 +134,8 @@ int bpf_sk_lookup_modptr_or_null(struct __sk_buff *skb) return 0; } -SEC("classifier/err_no_release") -int bpf_sk_lookup_test2(struct __sk_buff *skb) +SEC("tc") +int err_no_release(struct __sk_buff *skb) { struct bpf_sock_tuple tuple = {}; @@ -144,8 +143,8 @@ int bpf_sk_lookup_test2(struct __sk_buff *skb) return 0; } -SEC("classifier/err_release_twice") -int bpf_sk_lookup_test3(struct __sk_buff *skb) +SEC("tc") +int err_release_twice(struct __sk_buff *skb) { struct bpf_sock_tuple tuple = {}; struct bpf_sock *sk; @@ -156,8 +155,8 @@ int bpf_sk_lookup_test3(struct __sk_buff *skb) return 0; } -SEC("classifier/err_release_unchecked") -int bpf_sk_lookup_test4(struct __sk_buff *skb) +SEC("tc") +int err_release_unchecked(struct __sk_buff *skb) { struct bpf_sock_tuple tuple = {}; struct bpf_sock *sk; @@ -173,8 +172,8 @@ void lookup_no_release(struct __sk_buff *skb) bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), BPF_F_CURRENT_NETNS, 0); } -SEC("classifier/err_no_release_subcall") -int bpf_sk_lookup_test5(struct __sk_buff *skb) +SEC("tc") +int err_no_release_subcall(struct __sk_buff *skb) { lookup_no_release(skb); return 0; diff --git a/tools/testing/selftests/bpf/progs/test_sk_storage_tracing.c b/tools/testing/selftests/bpf/progs/test_sk_storage_tracing.c index 8e94e5c080..6dc1f28fc4 100644 --- a/tools/testing/selftests/bpf/progs/test_sk_storage_tracing.c +++ b/tools/testing/selftests/bpf/progs/test_sk_storage_tracing.c @@ -68,7 +68,7 @@ static void set_task_info(struct sock *sk) } SEC("fentry/inet_csk_listen_start") -int BPF_PROG(trace_inet_csk_listen_start, struct sock *sk, int backlog) +int BPF_PROG(trace_inet_csk_listen_start, struct sock *sk) { set_task_info(sk); diff --git a/tools/testing/selftests/bpf/progs/test_skb_cgroup_id_kern.c b/tools/testing/selftests/bpf/progs/test_skb_cgroup_id_kern.c index 552f209066..c304cd5b8c 100644 --- a/tools/testing/selftests/bpf/progs/test_skb_cgroup_id_kern.c +++ b/tools/testing/selftests/bpf/progs/test_skb_cgroup_id_kern.c @@ -42,6 +42,4 @@ int log_cgroup_id(struct __sk_buff *skb) return TC_ACT_OK; } -int _version SEC("version") = 1; - char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_skb_ctx.c b/tools/testing/selftests/bpf/progs/test_skb_ctx.c index b02ea589ce..c482110cfc 100644 --- a/tools/testing/selftests/bpf/progs/test_skb_ctx.c +++ b/tools/testing/selftests/bpf/progs/test_skb_ctx.c @@ -3,10 +3,9 @@ #include #include -int _version SEC("version") = 1; char _license[] SEC("license") = "GPL"; -SEC("skb_ctx") +SEC("tc") int process(struct __sk_buff *skb) { #pragma clang loop unroll(full) @@ -25,6 +24,12 @@ int process(struct __sk_buff *skb) return 1; if (skb->gso_size != 10) return 1; + if (skb->ingress_ifindex != 11) + return 1; + if (skb->ifindex != 1) + return 1; + if (skb->hwtstamp != 11) + return 1; return 0; } diff --git a/tools/testing/selftests/bpf/progs/test_skb_helpers.c b/tools/testing/selftests/bpf/progs/test_skb_helpers.c index bb3fbf1a29..507215791c 100644 --- a/tools/testing/selftests/bpf/progs/test_skb_helpers.c +++ b/tools/testing/selftests/bpf/progs/test_skb_helpers.c @@ -14,7 +14,7 @@ struct { char _license[] SEC("license") = "GPL"; -SEC("classifier/test_skb_helpers") +SEC("tc") int test_skb_helpers(struct __sk_buff *skb) { struct task_struct *task; diff --git a/tools/testing/selftests/bpf/progs/test_skeleton.c b/tools/testing/selftests/bpf/progs/test_skeleton.c index 441fa1c552..1b1187d296 100644 --- a/tools/testing/selftests/bpf/progs/test_skeleton.c +++ b/tools/testing/selftests/bpf/progs/test_skeleton.c @@ -5,6 +5,8 @@ #include #include +#define __read_mostly SEC(".data.read_mostly") + struct s { int a; long long b; @@ -40,9 +42,20 @@ int kern_ver = 0; struct s out5 = {}; + +const volatile int in_dynarr_sz SEC(".rodata.dyn"); +const volatile int in_dynarr[4] SEC(".rodata.dyn") = { -1, -2, -3, -4 }; + +int out_dynarr[4] SEC(".data.dyn") = { 1, 2, 3, 4 }; + +int read_mostly_var __read_mostly; +int out_mostly_var; + SEC("raw_tp/sys_enter") int handler(const void *ctx) { + int i; + out1 = in1; out2 = in2; out3 = in3; @@ -53,6 +66,11 @@ int handler(const void *ctx) bpf_syscall = CONFIG_BPF_SYSCALL; kern_ver = LINUX_KERNEL_VERSION; + for (i = 0; i < in_dynarr_sz; i++) + out_dynarr[i] = in_dynarr[i]; + + out_mostly_var = read_mostly_var; + return 0; } diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_kern.h b/tools/testing/selftests/bpf/progs/test_sockmap_kern.h index 5cb90ca292..6c85b00f27 100644 --- a/tools/testing/selftests/bpf/progs/test_sockmap_kern.h +++ b/tools/testing/selftests/bpf/progs/test_sockmap_kern.h @@ -371,5 +371,4 @@ int bpf_prog10(struct sk_msg_md *msg) return SK_DROP; } -int _version SEC("version") = 1; char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_listen.c b/tools/testing/selftests/bpf/progs/test_sockmap_listen.c index a1cc58b10c..325c9f1934 100644 --- a/tools/testing/selftests/bpf/progs/test_sockmap_listen.c +++ b/tools/testing/selftests/bpf/progs/test_sockmap_listen.c @@ -56,7 +56,7 @@ int prog_stream_verdict(struct __sk_buff *skb) return verdict; } -SEC("sk_skb/skb_verdict") +SEC("sk_skb") int prog_skb_verdict(struct __sk_buff *skb) { unsigned int *count; @@ -116,5 +116,4 @@ int prog_reuseport(struct sk_reuseport_md *reuse) return verdict; } -int _version SEC("version") = 1; char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_skb_verdict_attach.c b/tools/testing/selftests/bpf/progs/test_sockmap_skb_verdict_attach.c index 2d31f66e4f..3c69aa9717 100644 --- a/tools/testing/selftests/bpf/progs/test_sockmap_skb_verdict_attach.c +++ b/tools/testing/selftests/bpf/progs/test_sockmap_skb_verdict_attach.c @@ -9,7 +9,7 @@ struct { __type(value, __u64); } sock_map SEC(".maps"); -SEC("sk_skb/skb_verdict") +SEC("sk_skb") int prog_skb_verdict(struct __sk_buff *skb) { return SK_DROP; diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_update.c b/tools/testing/selftests/bpf/progs/test_sockmap_update.c index 9d0c9f28ca..6d64ea536e 100644 --- a/tools/testing/selftests/bpf/progs/test_sockmap_update.c +++ b/tools/testing/selftests/bpf/progs/test_sockmap_update.c @@ -24,7 +24,7 @@ struct { __type(value, __u64); } dst_sock_hash SEC(".maps"); -SEC("classifier/copy_sock_map") +SEC("tc") int copy_sock_map(void *ctx) { struct bpf_sock *sk; diff --git a/tools/testing/selftests/bpf/progs/test_spin_lock.c b/tools/testing/selftests/bpf/progs/test_spin_lock.c index 0d31a3b350..7e88309d32 100644 --- a/tools/testing/selftests/bpf/progs/test_spin_lock.c +++ b/tools/testing/selftests/bpf/progs/test_spin_lock.c @@ -45,7 +45,7 @@ struct { #define CREDIT_PER_NS(delta, rate) (((delta) * rate) >> 20) -SEC("spin_lock_demo") +SEC("tc") int bpf_sping_lock_test(struct __sk_buff *skb) { volatile int credit = 0, max_credit = 100, pkt_len = 64; diff --git a/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c b/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c index 0cf0134631..36a707e7c7 100644 --- a/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c +++ b/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c @@ -28,8 +28,8 @@ struct { __uint(type, BPF_MAP_TYPE_STACK_TRACE); __uint(max_entries, 128); __uint(map_flags, BPF_F_STACK_BUILD_ID); - __uint(key_size, sizeof(__u32)); - __uint(value_size, sizeof(stack_trace_t)); + __type(key, __u32); + __type(value, stack_trace_t); } stackmap SEC(".maps"); struct { @@ -73,4 +73,3 @@ int oncpu(struct random_urandom_args *args) } char _license[] SEC("license") = "GPL"; -__u32 _version SEC("version") = 1; /* ignored by tracepoints, required by libbpf.a */ diff --git a/tools/testing/selftests/bpf/progs/test_stacktrace_map.c b/tools/testing/selftests/bpf/progs/test_stacktrace_map.c index 00ed486726..728dbd39ef 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 +#include #include #ifndef PERF_MAX_STACK_DEPTH @@ -27,8 +27,8 @@ typedef __u64 stack_trace_t[PERF_MAX_STACK_DEPTH]; struct { __uint(type, BPF_MAP_TYPE_STACK_TRACE); __uint(max_entries, 16384); - __uint(key_size, sizeof(__u32)); - __uint(value_size, sizeof(stack_trace_t)); + __type(key, __u32); + __type(value, stack_trace_t); } stackmap SEC(".maps"); struct { @@ -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_tc_bpf.c b/tools/testing/selftests/bpf/progs/test_tc_bpf.c index 18a3a7ed92..d28ca8d1f3 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_bpf.c +++ b/tools/testing/selftests/bpf/progs/test_tc_bpf.c @@ -5,7 +5,7 @@ /* Dummy prog to test TC-BPF API */ -SEC("classifier") +SEC("tc") int cls(struct __sk_buff *skb) { return 0; diff --git a/tools/testing/selftests/bpf/progs/test_tc_neigh.c b/tools/testing/selftests/bpf/progs/test_tc_neigh.c index 0c93d326a6..3e32ea375a 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_neigh.c +++ b/tools/testing/selftests/bpf/progs/test_tc_neigh.c @@ -70,7 +70,7 @@ static __always_inline bool is_remote_ep_v6(struct __sk_buff *skb, return v6_equal(ip6h->daddr, addr); } -SEC("classifier/chk_egress") +SEC("tc") int tc_chk(struct __sk_buff *skb) { void *data_end = ctx_ptr(skb->data_end); @@ -83,7 +83,7 @@ int tc_chk(struct __sk_buff *skb) return !raw[0] && !raw[1] && !raw[2] ? TC_ACT_SHOT : TC_ACT_OK; } -SEC("classifier/dst_ingress") +SEC("tc") int tc_dst(struct __sk_buff *skb) { __u8 zero[ETH_ALEN * 2]; @@ -108,7 +108,7 @@ int tc_dst(struct __sk_buff *skb) return bpf_redirect_neigh(IFINDEX_SRC, NULL, 0, 0); } -SEC("classifier/src_ingress") +SEC("tc") int tc_src(struct __sk_buff *skb) { __u8 zero[ETH_ALEN * 2]; diff --git a/tools/testing/selftests/bpf/progs/test_tc_neigh_fib.c b/tools/testing/selftests/bpf/progs/test_tc_neigh_fib.c index f7ab69cf01..ec4cce1936 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_neigh_fib.c +++ b/tools/testing/selftests/bpf/progs/test_tc_neigh_fib.c @@ -75,7 +75,7 @@ static __always_inline int fill_fib_params_v6(struct __sk_buff *skb, return 0; } -SEC("classifier/chk_egress") +SEC("tc") int tc_chk(struct __sk_buff *skb) { void *data_end = ctx_ptr(skb->data_end); @@ -143,13 +143,13 @@ static __always_inline int tc_redir(struct __sk_buff *skb) /* these are identical, but keep them separate for compatibility with the * section names expected by test_tc_redirect.sh */ -SEC("classifier/dst_ingress") +SEC("tc") int tc_dst(struct __sk_buff *skb) { return tc_redir(skb); } -SEC("classifier/src_ingress") +SEC("tc") int tc_src(struct __sk_buff *skb) { return tc_redir(skb); diff --git a/tools/testing/selftests/bpf/progs/test_tc_peer.c b/tools/testing/selftests/bpf/progs/test_tc_peer.c index fe818cd5f0..365eacb5dc 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_peer.c +++ b/tools/testing/selftests/bpf/progs/test_tc_peer.c @@ -16,31 +16,31 @@ volatile const __u32 IFINDEX_DST; static const __u8 src_mac[] = {0x00, 0x11, 0x22, 0x33, 0x44, 0x55}; static const __u8 dst_mac[] = {0x00, 0x22, 0x33, 0x44, 0x55, 0x66}; -SEC("classifier/chk_egress") +SEC("tc") int tc_chk(struct __sk_buff *skb) { return TC_ACT_SHOT; } -SEC("classifier/dst_ingress") +SEC("tc") int tc_dst(struct __sk_buff *skb) { return bpf_redirect_peer(IFINDEX_SRC, 0); } -SEC("classifier/src_ingress") +SEC("tc") int tc_src(struct __sk_buff *skb) { return bpf_redirect_peer(IFINDEX_DST, 0); } -SEC("classifier/dst_ingress_l3") +SEC("tc") int tc_dst_l3(struct __sk_buff *skb) { return bpf_redirect(IFINDEX_SRC, 0); } -SEC("classifier/src_ingress_l3") +SEC("tc") int tc_src_l3(struct __sk_buff *skb) { __u16 proto = skb->protocol; diff --git a/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c b/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c index 47cbe2eeae..cd747cd93d 100644 --- a/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c +++ b/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c @@ -148,7 +148,7 @@ static __always_inline void check_syncookie(void *ctx, void *data, bpf_sk_release(sk); } -SEC("clsact/check_syncookie") +SEC("tc") int check_syncookie_clsact(struct __sk_buff *skb) { check_syncookie(skb, (void *)(long)skb->data, @@ -156,7 +156,7 @@ int check_syncookie_clsact(struct __sk_buff *skb) return TC_ACT_OK; } -SEC("xdp/check_syncookie") +SEC("xdp") int check_syncookie_xdp(struct xdp_md *ctx) { check_syncookie(ctx, (void *)(long)ctx->data, diff --git a/tools/testing/selftests/bpf/progs/test_tcp_estats.c b/tools/testing/selftests/bpf/progs/test_tcp_estats.c index adc83a54c3..e2ae049c2f 100644 --- a/tools/testing/selftests/bpf/progs/test_tcp_estats.c +++ b/tools/testing/selftests/bpf/progs/test_tcp_estats.c @@ -244,7 +244,7 @@ static __always_inline void send_basic_event(struct sock *sk, bpf_map_update_elem(&ev_record_map, &key, &ev, BPF_ANY); } -SEC("dummy_tracepoint") +SEC("tp/dummy/tracepoint") int _dummy_tracepoint(struct dummy_tracepoint_args *arg) { if (!arg->sock) @@ -255,4 +255,3 @@ int _dummy_tracepoint(struct dummy_tracepoint_args *arg) } char _license[] SEC("license") = "GPL"; -__u32 _version SEC("version") = 1; /* ignored by tracepoints, required by libbpf.a */ diff --git a/tools/testing/selftests/bpf/progs/test_tcp_hdr_options.c b/tools/testing/selftests/bpf/progs/test_tcp_hdr_options.c index 678bd0fad2..5f4e87ee94 100644 --- a/tools/testing/selftests/bpf/progs/test_tcp_hdr_options.c +++ b/tools/testing/selftests/bpf/progs/test_tcp_hdr_options.c @@ -594,7 +594,7 @@ static int handle_parse_hdr(struct bpf_sock_ops *skops) return CG_OK; } -SEC("sockops/estab") +SEC("sockops") int estab(struct bpf_sock_ops *skops) { int true_val = 1; diff --git a/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c b/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c index 94f50f7e94..3ded052807 100644 --- a/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c +++ b/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c @@ -16,7 +16,6 @@ #include "test_tcpbpf.h" struct tcpbpf_globals global = {}; -int _version SEC("version") = 1; /** * SOL_TCP is defined in while diff --git a/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c b/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c index ac63410bb5..540181c115 100644 --- a/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c +++ b/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c @@ -24,12 +24,10 @@ struct { struct { __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); __uint(max_entries, 2); - __uint(key_size, sizeof(int)); - __uint(value_size, sizeof(__u32)); + __type(key, int); + __type(value, __u32); } perf_event_map SEC(".maps"); -int _version SEC("version") = 1; - SEC("sockops") int bpf_testcb(struct bpf_sock_ops *skops) { diff --git a/tools/testing/selftests/bpf/progs/test_tracepoint.c b/tools/testing/selftests/bpf/progs/test_tracepoint.c index 4b825ee122..43bd7a20cc 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 +#include #include /* 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; }; @@ -23,4 +23,3 @@ int oncpu(struct sched_switch_args *ctx) } char _license[] SEC("license") = "GPL"; -__u32 _version SEC("version") = 1; /* ignored by tracepoints, required by libbpf.a */ diff --git a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c index e7b6731174..ef0dde83b8 100644 --- a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c +++ b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c @@ -26,8 +26,6 @@ bpf_trace_printk(fmt, sizeof(fmt), __LINE__, ret); \ } while (0) -int _version SEC("version") = 1; - struct geneve_opt { __be16 opt_class; __u8 type; diff --git a/tools/testing/selftests/bpf/progs/test_verif_scale2.c b/tools/testing/selftests/bpf/progs/test_verif_scale2.c index f024154c7b..f90ffcafd1 100644 --- a/tools/testing/selftests/bpf/progs/test_verif_scale2.c +++ b/tools/testing/selftests/bpf/progs/test_verif_scale2.c @@ -1,11 +1,11 @@ // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2019 Facebook -#include +#include "vmlinux.h" #include #define ATTR __always_inline #include "test_jhash.h" -SEC("scale90_inline") +SEC("tc") int balancer_ingress(struct __sk_buff *ctx) { void *data_end = (void *)(long)ctx->data_end; diff --git a/tools/testing/selftests/bpf/progs/test_xdp.c b/tools/testing/selftests/bpf/progs/test_xdp.c index 31f9bce374..d7a9a74b72 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp.c +++ b/tools/testing/selftests/bpf/progs/test_xdp.c @@ -20,8 +20,6 @@ #include #include "test_iptunnel_common.h" -int _version SEC("version") = 1; - struct { __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); __uint(max_entries, 256); @@ -210,7 +208,7 @@ static __always_inline int handle_ipv6(struct xdp_md *xdp) return XDP_TX; } -SEC("xdp_tx_iptunnel") +SEC("xdp") int _xdp_tx_iptunnel(struct xdp_md *xdp) { void *data_end = (void *)(long)xdp->data_end; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c index 3d66599eee..199c61b7d0 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c @@ -2,7 +2,7 @@ #include #include -SEC("xdp_adjust_tail_grow") +SEC("xdp") int _xdp_adjust_tail_grow(struct xdp_md *xdp) { void *data_end = (void *)(long)xdp->data_end; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_shrink.c b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_shrink.c index 22065a9cfb..b7448253d1 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_shrink.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_shrink.c @@ -9,9 +9,7 @@ #include #include -int _version SEC("version") = 1; - -SEC("xdp_adjust_tail_shrink") +SEC("xdp") int _xdp_adjust_tail_shrink(struct xdp_md *xdp) { void *data_end = (void *)(long)xdp->data_end; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c b/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c index a038e827f8..58cf4345f5 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c @@ -36,8 +36,8 @@ struct meta { struct { __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); - __uint(key_size, sizeof(int)); - __uint(value_size, sizeof(int)); + __type(key, int); + __type(value, int); } perf_buf_map SEC(".maps"); __u64 test_result_fentry = 0; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_devmap_helpers.c b/tools/testing/selftests/bpf/progs/test_xdp_devmap_helpers.c index b360ba2bd4..807bf895f4 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_devmap_helpers.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_devmap_helpers.c @@ -5,7 +5,7 @@ #include #include -SEC("xdp_dm_log") +SEC("xdp") int xdpdm_devlog(struct xdp_md *ctx) { char fmt[] = "devmap redirect: dev %u -> dev %u len %u\n"; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_link.c b/tools/testing/selftests/bpf/progs/test_xdp_link.c index eb93ea95d1..64ff32eaae 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_link.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_link.c @@ -5,8 +5,14 @@ char LICENSE[] SEC("license") = "GPL"; -SEC("xdp/handler") +SEC("xdp") 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/test_xdp_loop.c b/tools/testing/selftests/bpf/progs/test_xdp_loop.c index fcabcda30b..c98fb44156 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_loop.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_loop.c @@ -16,8 +16,6 @@ #include #include "test_iptunnel_common.h" -int _version SEC("version") = 1; - struct { __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); __uint(max_entries, 256); @@ -206,7 +204,7 @@ static __always_inline int handle_ipv6(struct xdp_md *xdp) return XDP_TX; } -SEC("xdp_tx_iptunnel") +SEC("xdp") int _xdp_tx_iptunnel(struct xdp_md *xdp) { void *data_end = (void *)(long)xdp->data_end; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_noinline.c b/tools/testing/selftests/bpf/progs/test_xdp_noinline.c index 3a67921f62..596c4e71bf 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_noinline.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_noinline.c @@ -797,7 +797,7 @@ static int process_packet(void *data, __u64 off, void *data_end, return XDP_DROP; } -SEC("xdp-test-v4") +SEC("xdp") int balancer_ingress_v4(struct xdp_md *ctx) { void *data = (void *)(long)ctx->data; @@ -816,7 +816,7 @@ int balancer_ingress_v4(struct xdp_md *ctx) return XDP_DROP; } -SEC("xdp-test-v6") +SEC("xdp") int balancer_ingress_v6(struct xdp_md *ctx) { void *data = (void *)(long)ctx->data; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_redirect.c b/tools/testing/selftests/bpf/progs/test_xdp_redirect.c index a5337cd940..b778cad454 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_redirect.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_redirect.c @@ -12,8 +12,6 @@ #include #include -int _version SEC("version") = 1; - SEC("redirect_to_111") int xdp_redirect_to_111(struct xdp_md *xdp) { diff --git a/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c b/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c index 59ee4f182f..5320250577 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c @@ -12,13 +12,13 @@ struct { __uint(max_entries, 4); } cpu_map SEC(".maps"); -SEC("xdp_redir") +SEC("xdp") int xdp_redir_prog(struct xdp_md *ctx) { return bpf_redirect_map(&cpu_map, 1, 0); } -SEC("xdp_dummy") +SEC("xdp") int xdp_dummy_prog(struct xdp_md *ctx) { return XDP_PASS; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c b/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c index 0ac0864977..1e6b9c38ea 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c @@ -9,7 +9,7 @@ struct { __uint(max_entries, 4); } dm_ports SEC(".maps"); -SEC("xdp_redir") +SEC("xdp") int xdp_redir_prog(struct xdp_md *ctx) { return bpf_redirect_map(&dm_ports, 1, 0); @@ -18,7 +18,7 @@ int xdp_redir_prog(struct xdp_md *ctx) /* invalid program on DEVMAP entry; * SEC name means expected attach type not set */ -SEC("xdp_dummy") +SEC("xdp") int xdp_dummy_prog(struct xdp_md *ctx) { return XDP_PASS; diff --git a/tools/testing/selftests/bpf/progs/trigger_bench.c b/tools/testing/selftests/bpf/progs/trigger_bench.c index 9a4d09590b..2098f3f27f 100644 --- a/tools/testing/selftests/bpf/progs/trigger_bench.c +++ b/tools/testing/selftests/bpf/progs/trigger_bench.c @@ -52,3 +52,10 @@ int bench_trigger_fmodret(void *ctx) __sync_add_and_fetch(&hits, 1); return -22; } + +SEC("uprobe/self/uprobe_target") +int bench_trigger_uprobe(void *ctx) +{ + __sync_add_and_fetch(&hits, 1); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/xdp_dummy.c b/tools/testing/selftests/bpf/progs/xdp_dummy.c index ea25e88819..d988b2e0ce 100644 --- a/tools/testing/selftests/bpf/progs/xdp_dummy.c +++ b/tools/testing/selftests/bpf/progs/xdp_dummy.c @@ -4,7 +4,7 @@ #include #include -SEC("xdp_dummy") +SEC("xdp") int xdp_dummy_prog(struct xdp_md *ctx) { return XDP_PASS; diff --git a/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c b/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c index 880debcbcd..8395782b6e 100644 --- a/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c +++ b/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c @@ -34,7 +34,7 @@ struct { __uint(max_entries, 128); } mac_map SEC(".maps"); -SEC("xdp_redirect_map_multi") +SEC("xdp") int xdp_redirect_map_multi_prog(struct xdp_md *ctx) { void *data_end = (void *)(long)ctx->data_end; @@ -63,7 +63,7 @@ int xdp_redirect_map_multi_prog(struct xdp_md *ctx) } /* The following 2 progs are for 2nd devmap prog testing */ -SEC("xdp_redirect_map_ingress") +SEC("xdp") int xdp_redirect_map_all_prog(struct xdp_md *ctx) { return bpf_redirect_map(&map_egress, 0, diff --git a/tools/testing/selftests/bpf/progs/xdping_kern.c b/tools/testing/selftests/bpf/progs/xdping_kern.c index 6b9ca40bd1..4ad73847b8 100644 --- a/tools/testing/selftests/bpf/progs/xdping_kern.c +++ b/tools/testing/selftests/bpf/progs/xdping_kern.c @@ -86,7 +86,7 @@ static __always_inline int icmp_check(struct xdp_md *ctx, int type) return XDP_TX; } -SEC("xdpclient") +SEC("xdp") int xdping_client(struct xdp_md *ctx) { void *data_end = (void *)(long)ctx->data_end; @@ -150,7 +150,7 @@ int xdping_client(struct xdp_md *ctx) return XDP_TX; } -SEC("xdpserver") +SEC("xdp") int xdping_server(struct xdp_md *ctx) { void *data_end = (void *)(long)ctx->data_end; diff --git a/tools/testing/selftests/bpf/test_bpftool.py b/tools/testing/selftests/bpf/test_bpftool.py index 4fed2dc25c..1c2408ee1f 100644 --- a/tools/testing/selftests/bpf/test_bpftool.py +++ b/tools/testing/selftests/bpf/test_bpftool.py @@ -57,6 +57,11 @@ def default_iface(f): return f(*args, iface, **kwargs) return wrapper +DMESG_EMITTING_HELPERS = [ + "bpf_probe_write_user", + "bpf_trace_printk", + "bpf_trace_vprintk", + ] class TestBpftool(unittest.TestCase): @classmethod @@ -67,10 +72,7 @@ class TestBpftool(unittest.TestCase): @default_iface def test_feature_dev_json(self, iface): - unexpected_helpers = [ - "bpf_probe_write_user", - "bpf_trace_printk", - ] + unexpected_helpers = DMESG_EMITTING_HELPERS expected_keys = [ "syscall_config", "program_types", @@ -94,10 +96,7 @@ class TestBpftool(unittest.TestCase): bpftool_json(["feature", "probe"]), bpftool_json(["feature"]), ] - unexpected_helpers = [ - "bpf_probe_write_user", - "bpf_trace_printk", - ] + unexpected_helpers = DMESG_EMITTING_HELPERS expected_keys = [ "syscall_config", "system_config", @@ -121,10 +120,7 @@ class TestBpftool(unittest.TestCase): bpftool_json(["feature", "probe", "kernel", "full"]), bpftool_json(["feature", "probe", "full"]), ] - expected_helpers = [ - "bpf_probe_write_user", - "bpf_trace_printk", - ] + expected_helpers = DMESG_EMITTING_HELPERS for tc in test_cases: # Check if expected helpers are included at least once in any @@ -157,7 +153,7 @@ class TestBpftool(unittest.TestCase): not_full_set.add(helper) self.assertCountEqual(full_set - not_full_set, - {"bpf_probe_write_user", "bpf_trace_printk"}) + set(DMESG_EMITTING_HELPERS)) self.assertCountEqual(not_full_set - full_set, set()) def test_feature_macros(self): diff --git a/tools/testing/selftests/bpf/test_bpftool_build.sh b/tools/testing/selftests/bpf/test_bpftool_build.sh index b03a875715..1453a53ed5 100644 --- a/tools/testing/selftests/bpf/test_bpftool_build.sh +++ b/tools/testing/selftests/bpf/test_bpftool_build.sh @@ -90,6 +90,10 @@ echo -e "... through kbuild\n" if [ -f ".config" ] ; then make_and_clean tools/bpf + ## "make tools/bpf" sets $(OUTPUT) to ...tools/bpf/runqslower for + ## runqslower, but the default (used for the "clean" target) is .output. + ## Let's make sure we clean runqslower's directory properly. + make -C tools/bpf/runqslower OUTPUT=${KDIR_ROOT_DIR}/tools/bpf/runqslower/ clean ## $OUTPUT is overwritten in kbuild Makefile, and thus cannot be passed ## down from toplevel Makefile to bpftool's Makefile. diff --git a/tools/testing/selftests/bpf/test_bpftool_synctypes.py b/tools/testing/selftests/bpf/test_bpftool_synctypes.py index be54b7335a..6bf21e4788 100644 --- a/tools/testing/selftests/bpf/test_bpftool_synctypes.py +++ b/tools/testing/selftests/bpf/test_bpftool_synctypes.py @@ -9,7 +9,15 @@ import os, sys LINUX_ROOT = os.path.abspath(os.path.join(__file__, os.pardir, os.pardir, os.pardir, os.pardir, os.pardir)) -BPFTOOL_DIR = os.path.join(LINUX_ROOT, 'tools/bpf/bpftool') +BPFTOOL_DIR = os.getenv('BPFTOOL_DIR', + os.path.join(LINUX_ROOT, 'tools/bpf/bpftool')) +BPFTOOL_BASHCOMP_DIR = os.getenv('BPFTOOL_BASHCOMP_DIR', + os.path.join(BPFTOOL_DIR, 'bash-completion')) +BPFTOOL_DOC_DIR = os.getenv('BPFTOOL_DOC_DIR', + os.path.join(BPFTOOL_DIR, 'Documentation')) +INCLUDE_DIR = os.getenv('INCLUDE_DIR', + os.path.join(LINUX_ROOT, 'tools/include')) + retval = 0 class BlockParser(object): @@ -242,12 +250,6 @@ class FileExtractor(object): end_marker = re.compile('}\\\\n') return self.__get_description_list(start_marker, pattern, end_marker) - def default_options(self): - """ - Return the default options contained in HELP_SPEC_OPTIONS - """ - return { '-j', '--json', '-p', '--pretty', '-d', '--debug' } - def get_bashcomp_list(self, block_name): """ Search for and parse a list of type names from a variable in bash @@ -274,7 +276,56 @@ class SourceFileExtractor(FileExtractor): defined in children classes. """ def get_options(self): - return self.default_options().union(self.get_help_list_macro('HELP_SPEC_OPTIONS')) + return self.get_help_list_macro('HELP_SPEC_OPTIONS') + +class MainHeaderFileExtractor(SourceFileExtractor): + """ + An extractor for bpftool's main.h + """ + filename = os.path.join(BPFTOOL_DIR, 'main.h') + + def get_common_options(self): + """ + Parse the list of common options in main.h (options that apply to all + commands), which looks to the lists of options in other source files + but has different start and end markers: + + "OPTIONS := { {-j|--json} [{-p|--pretty}] | {-d|--debug} | {-l|--legacy}" + + Return a set containing all options, such as: + + {'-p', '-d', '--legacy', '--pretty', '--debug', '--json', '-l', '-j'} + """ + start_marker = re.compile(f'"OPTIONS :=') + pattern = re.compile('([\w-]+) ?(?:\||}[ }\]"])') + end_marker = re.compile('#define') + + parser = InlineListParser(self.reader) + parser.search_block(start_marker) + return parser.parse(pattern, end_marker) + +class ManSubstitutionsExtractor(SourceFileExtractor): + """ + An extractor for substitutions.rst + """ + filename = os.path.join(BPFTOOL_DOC_DIR, 'substitutions.rst') + + def get_common_options(self): + """ + Parse the list of common options in substitutions.rst (options that + apply to all commands). + + Return a set containing all options, such as: + + {'-p', '-d', '--legacy', '--pretty', '--debug', '--json', '-l', '-j'} + """ + start_marker = re.compile('\|COMMON_OPTIONS\| replace:: {') + pattern = re.compile('\*\*([\w/-]+)\*\*') + end_marker = re.compile('}$') + + parser = InlineListParser(self.reader) + parser.search_block(start_marker) + return parser.parse(pattern, end_marker) class ProgFileExtractor(SourceFileExtractor): """ @@ -350,7 +401,7 @@ class BpfHeaderExtractor(FileExtractor): """ An extractor for the UAPI BPF header. """ - filename = os.path.join(LINUX_ROOT, 'tools/include/uapi/linux/bpf.h') + filename = os.path.join(INCLUDE_DIR, 'uapi/linux/bpf.h') def get_prog_types(self): return self.get_enum('bpf_prog_type') @@ -374,7 +425,7 @@ class ManProgExtractor(ManPageExtractor): """ An extractor for bpftool-prog.rst. """ - filename = os.path.join(BPFTOOL_DIR, 'Documentation/bpftool-prog.rst') + filename = os.path.join(BPFTOOL_DOC_DIR, 'bpftool-prog.rst') def get_attach_types(self): return self.get_rst_list('ATTACH_TYPE') @@ -383,7 +434,7 @@ class ManMapExtractor(ManPageExtractor): """ An extractor for bpftool-map.rst. """ - filename = os.path.join(BPFTOOL_DIR, 'Documentation/bpftool-map.rst') + filename = os.path.join(BPFTOOL_DOC_DIR, 'bpftool-map.rst') def get_map_types(self): return self.get_rst_list('TYPE') @@ -392,7 +443,7 @@ class ManCgroupExtractor(ManPageExtractor): """ An extractor for bpftool-cgroup.rst. """ - filename = os.path.join(BPFTOOL_DIR, 'Documentation/bpftool-cgroup.rst') + filename = os.path.join(BPFTOOL_DOC_DIR, 'bpftool-cgroup.rst') def get_attach_types(self): return self.get_rst_list('ATTACH_TYPE') @@ -411,7 +462,7 @@ class BashcompExtractor(FileExtractor): """ An extractor for bpftool's bash completion file. """ - filename = os.path.join(BPFTOOL_DIR, 'bash-completion/bpftool') + filename = os.path.join(BPFTOOL_BASHCOMP_DIR, 'bpftool') def get_prog_attach_types(self): return self.get_bashcomp_list('BPFTOOL_PROG_ATTACH_TYPES') @@ -562,7 +613,7 @@ def main(): help_cmd_options = source_info.get_options() source_info.close() - man_cmd_info = ManGenericExtractor(os.path.join('Documentation', 'bpftool-' + cmd + '.rst')) + man_cmd_info = ManGenericExtractor(os.path.join(BPFTOOL_DOC_DIR, 'bpftool-' + cmd + '.rst')) man_cmd_options = man_cmd_info.get_options() man_cmd_info.close() @@ -573,13 +624,26 @@ def main(): help_main_options = source_main_info.get_options() source_main_info.close() - man_main_info = ManGenericExtractor(os.path.join('Documentation', 'bpftool.rst')) + man_main_info = ManGenericExtractor(os.path.join(BPFTOOL_DOC_DIR, 'bpftool.rst')) man_main_options = man_main_info.get_options() man_main_info.close() verify(help_main_options, man_main_options, f'Comparing {source_main_info.filename} (do_help() OPTIONS) and {man_main_info.filename} (OPTIONS):') + # Compare common options (options that apply to all commands) + + main_hdr_info = MainHeaderFileExtractor() + source_common_options = main_hdr_info.get_common_options() + main_hdr_info.close() + + man_substitutions = ManSubstitutionsExtractor() + man_common_options = man_substitutions.get_common_options() + man_substitutions.close() + + verify(source_common_options, man_common_options, + f'Comparing common options from {main_hdr_info.filename} (HELP_SPEC_OPTIONS) and {man_substitutions.filename}:') + sys.exit(retval) if __name__ == "__main__": diff --git a/tools/testing/selftests/bpf/test_btf.h b/tools/testing/selftests/bpf/test_btf.h index e2394eea4b..128989bed8 100644 --- a/tools/testing/selftests/bpf/test_btf.h +++ b/tools/testing/selftests/bpf/test_btf.h @@ -69,4 +69,10 @@ #define BTF_TYPE_FLOAT_ENC(name, sz) \ BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_FLOAT, 0, 0), sz) +#define BTF_DECL_TAG_ENC(value, type, component_idx) \ + BTF_TYPE_ENC(value, BTF_INFO_ENC(BTF_KIND_DECL_TAG, 0, 0), type), (component_idx) + +#define BTF_TYPE_TAG_ENC(value, type) \ + BTF_TYPE_ENC(value, BTF_INFO_ENC(BTF_KIND_TYPE_TAG, 0, 0), type) + #endif /* _TEST_BTF_H */ diff --git a/tools/testing/selftests/bpf/test_cgroup_storage.c b/tools/testing/selftests/bpf/test_cgroup_storage.c index 0cda61da5d..5b8314cd77 100644 --- a/tools/testing/selftests/bpf/test_cgroup_storage.c +++ b/tools/testing/selftests/bpf/test_cgroup_storage.c @@ -8,6 +8,7 @@ #include "bpf_rlimit.h" #include "cgroup_helpers.h" +#include "testing_helpers.h" char bpf_log_buf[BPF_LOG_BUF_SIZE]; @@ -50,15 +51,15 @@ int main(int argc, char **argv) goto err; } - map_fd = bpf_create_map(BPF_MAP_TYPE_CGROUP_STORAGE, sizeof(key), - sizeof(value), 0, 0); + map_fd = bpf_map_create(BPF_MAP_TYPE_CGROUP_STORAGE, NULL, sizeof(key), + sizeof(value), 0, NULL); if (map_fd < 0) { printf("Failed to create map: %s\n", strerror(errno)); goto out; } - percpu_map_fd = bpf_create_map(BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE, - sizeof(key), sizeof(value), 0, 0); + percpu_map_fd = bpf_map_create(BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE, NULL, + sizeof(key), sizeof(value), 0, NULL); if (percpu_map_fd < 0) { printf("Failed to create map: %s\n", strerror(errno)); goto out; @@ -66,7 +67,7 @@ int main(int argc, char **argv) prog[0].imm = percpu_map_fd; prog[7].imm = map_fd; - prog_fd = bpf_load_program(BPF_PROG_TYPE_CGROUP_SKB, + prog_fd = bpf_test_load_program(BPF_PROG_TYPE_CGROUP_SKB, prog, insns_cnt, "GPL", 0, bpf_log_buf, BPF_LOG_BUF_SIZE); if (prog_fd < 0) { diff --git a/tools/testing/selftests/bpf/test_cpp.cpp b/tools/testing/selftests/bpf/test_cpp.cpp index a8d2e9a87f..e00201de28 100644 --- a/tools/testing/selftests/bpf/test_cpp.cpp +++ b/tools/testing/selftests/bpf/test_cpp.cpp @@ -7,9 +7,15 @@ /* do nothing, just make sure we can link successfully */ +static void dump_printf(void *ctx, const char *fmt, va_list args) +{ +} + int main(int argc, char *argv[]) { + struct btf_dump_opts opts = { }; struct test_core_extern *skel; + struct btf *btf; /* libbpf.h */ libbpf_set_print(NULL); @@ -18,7 +24,8 @@ int main(int argc, char *argv[]) bpf_prog_get_fd_by_id(0); /* btf.h */ - btf__new(NULL, 0); + btf = btf__new(NULL, 0); + btf_dump__new(btf, dump_printf, nullptr, &opts); /* BPF skeleton */ skel = test_core_extern__open_and_load(); diff --git a/tools/testing/selftests/bpf/test_dev_cgroup.c b/tools/testing/selftests/bpf/test_dev_cgroup.c index 804dddd97d..c299d34526 100644 --- a/tools/testing/selftests/bpf/test_dev_cgroup.c +++ b/tools/testing/selftests/bpf/test_dev_cgroup.c @@ -14,6 +14,7 @@ #include #include "cgroup_helpers.h" +#include "testing_helpers.h" #include "bpf_rlimit.h" #define DEV_CGROUP_PROG "./dev_cgroup.o" @@ -27,7 +28,7 @@ int main(int argc, char **argv) int prog_fd, cgroup_fd; __u32 prog_cnt; - if (bpf_prog_load(DEV_CGROUP_PROG, BPF_PROG_TYPE_CGROUP_DEVICE, + if (bpf_prog_test_load(DEV_CGROUP_PROG, BPF_PROG_TYPE_CGROUP_DEVICE, &obj, &prog_fd)) { printf("Failed to load DEV_CGROUP program\n"); goto out; diff --git a/tools/testing/selftests/bpf/test_flow_dissector.sh b/tools/testing/selftests/bpf/test_flow_dissector.sh index 174b72a64a..dbd9122172 100644 --- a/tools/testing/selftests/bpf/test_flow_dissector.sh +++ b/tools/testing/selftests/bpf/test_flow_dissector.sh @@ -26,22 +26,22 @@ if [[ -z $(ip netns identify $$) ]]; then type flow_dissector if ! unshare --net $bpftool prog attach pinned \ - /sys/fs/bpf/flow/flow_dissector flow_dissector; then + /sys/fs/bpf/flow/_dissect flow_dissector; then echo "Unexpected unsuccessful attach in namespace" >&2 err=1 fi - $bpftool prog attach pinned /sys/fs/bpf/flow/flow_dissector \ + $bpftool prog attach pinned /sys/fs/bpf/flow/_dissect \ flow_dissector if unshare --net $bpftool prog attach pinned \ - /sys/fs/bpf/flow/flow_dissector flow_dissector; then + /sys/fs/bpf/flow/_dissect flow_dissector; then echo "Unexpected successful attach in namespace" >&2 err=1 fi if ! $bpftool prog detach pinned \ - /sys/fs/bpf/flow/flow_dissector flow_dissector; then + /sys/fs/bpf/flow/_dissect flow_dissector; then echo "Failed to detach flow dissector" >&2 err=1 fi @@ -95,7 +95,7 @@ else fi # Attach BPF program -./flow_dissector_load -p bpf_flow.o -s flow_dissector +./flow_dissector_load -p bpf_flow.o -s _dissect # Setup tc qdisc add dev lo ingress diff --git a/tools/testing/selftests/bpf/test_lirc_mode2_user.c b/tools/testing/selftests/bpf/test_lirc_mode2_user.c index fb5fd6841e..2893e9f2f1 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 -#include #include #include #include @@ -45,6 +44,8 @@ #include #include +#include "testing_helpers.h" + int main(int argc, char **argv) { struct bpf_object *obj; @@ -58,8 +59,8 @@ int main(int argc, char **argv) return 2; } - ret = bpf_prog_load("test_lirc_mode2_kern.o", - BPF_PROG_TYPE_LIRC_MODE2, &obj, &progfd); + ret = bpf_prog_test_load("test_lirc_mode2_kern.o", + BPF_PROG_TYPE_LIRC_MODE2, &obj, &progfd); if (ret) { printf("Failed to load bpf program\n"); return 1; diff --git a/tools/testing/selftests/bpf/test_lpm_map.c b/tools/testing/selftests/bpf/test_lpm_map.c index 006be39639..baa3e3ecae 100644 --- a/tools/testing/selftests/bpf/test_lpm_map.c +++ b/tools/testing/selftests/bpf/test_lpm_map.c @@ -208,6 +208,7 @@ static void test_lpm_order(void) static void test_lpm_map(int keysize) { + LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = BPF_F_NO_PREALLOC); size_t i, j, n_matches, n_matches_after_delete, n_nodes, n_lookups; struct tlpm_node *t, *list = NULL; struct bpf_lpm_trie_key *key; @@ -233,11 +234,11 @@ static void test_lpm_map(int keysize) key = alloca(sizeof(*key) + keysize); memset(key, 0, sizeof(*key) + keysize); - map = bpf_create_map(BPF_MAP_TYPE_LPM_TRIE, + map = bpf_map_create(BPF_MAP_TYPE_LPM_TRIE, NULL, sizeof(*key) + keysize, keysize + 1, 4096, - BPF_F_NO_PREALLOC); + &opts); assert(map >= 0); for (i = 0; i < n_nodes; ++i) { @@ -329,6 +330,7 @@ static void test_lpm_map(int keysize) static void test_lpm_ipaddr(void) { + LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = BPF_F_NO_PREALLOC); struct bpf_lpm_trie_key *key_ipv4; struct bpf_lpm_trie_key *key_ipv6; size_t key_size_ipv4; @@ -342,14 +344,14 @@ static void test_lpm_ipaddr(void) key_ipv4 = alloca(key_size_ipv4); key_ipv6 = alloca(key_size_ipv6); - map_fd_ipv4 = bpf_create_map(BPF_MAP_TYPE_LPM_TRIE, + map_fd_ipv4 = bpf_map_create(BPF_MAP_TYPE_LPM_TRIE, NULL, key_size_ipv4, sizeof(value), - 100, BPF_F_NO_PREALLOC); + 100, &opts); assert(map_fd_ipv4 >= 0); - map_fd_ipv6 = bpf_create_map(BPF_MAP_TYPE_LPM_TRIE, + map_fd_ipv6 = bpf_map_create(BPF_MAP_TYPE_LPM_TRIE, NULL, key_size_ipv6, sizeof(value), - 100, BPF_F_NO_PREALLOC); + 100, &opts); assert(map_fd_ipv6 >= 0); /* Fill data some IPv4 and IPv6 address ranges */ @@ -423,6 +425,7 @@ static void test_lpm_ipaddr(void) static void test_lpm_delete(void) { + LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = BPF_F_NO_PREALLOC); struct bpf_lpm_trie_key *key; size_t key_size; int map_fd; @@ -431,9 +434,9 @@ static void test_lpm_delete(void) key_size = sizeof(*key) + sizeof(__u32); key = alloca(key_size); - map_fd = bpf_create_map(BPF_MAP_TYPE_LPM_TRIE, + map_fd = bpf_map_create(BPF_MAP_TYPE_LPM_TRIE, NULL, key_size, sizeof(value), - 100, BPF_F_NO_PREALLOC); + 100, &opts); assert(map_fd >= 0); /* Add nodes: @@ -535,6 +538,7 @@ static void test_lpm_delete(void) static void test_lpm_get_next_key(void) { + LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = BPF_F_NO_PREALLOC); struct bpf_lpm_trie_key *key_p, *next_key_p; size_t key_size; __u32 value = 0; @@ -544,8 +548,7 @@ static void test_lpm_get_next_key(void) key_p = alloca(key_size); next_key_p = alloca(key_size); - map_fd = bpf_create_map(BPF_MAP_TYPE_LPM_TRIE, key_size, sizeof(value), - 100, BPF_F_NO_PREALLOC); + map_fd = bpf_map_create(BPF_MAP_TYPE_LPM_TRIE, NULL, key_size, sizeof(value), 100, &opts); assert(map_fd >= 0); /* empty tree. get_next_key should return ENOENT */ @@ -753,6 +756,7 @@ static void setup_lpm_mt_test_info(struct lpm_mt_test_info *info, int map_fd) static void test_lpm_multi_thread(void) { + LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = BPF_F_NO_PREALLOC); struct lpm_mt_test_info info[4]; size_t key_size, value_size; pthread_t thread_id[4]; @@ -762,8 +766,7 @@ static void test_lpm_multi_thread(void) /* create a trie */ value_size = sizeof(__u32); key_size = sizeof(struct bpf_lpm_trie_key) + value_size; - map_fd = bpf_create_map(BPF_MAP_TYPE_LPM_TRIE, key_size, value_size, - 100, BPF_F_NO_PREALLOC); + map_fd = bpf_map_create(BPF_MAP_TYPE_LPM_TRIE, NULL, key_size, value_size, 100, &opts); /* create 4 threads to test update, delete, lookup and get_next_key */ setup_lpm_mt_test_info(&info[0], map_fd); diff --git a/tools/testing/selftests/bpf/test_lru_map.c b/tools/testing/selftests/bpf/test_lru_map.c index 7e9049fa3e..b9f1bbbc8a 100644 --- a/tools/testing/selftests/bpf/test_lru_map.c +++ b/tools/testing/selftests/bpf/test_lru_map.c @@ -28,13 +28,14 @@ static int nr_cpus; static int create_map(int map_type, int map_flags, unsigned int size) { + LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = map_flags); int map_fd; - map_fd = bpf_create_map(map_type, sizeof(unsigned long long), - sizeof(unsigned long long), size, map_flags); + map_fd = bpf_map_create(map_type, NULL, sizeof(unsigned long long), + sizeof(unsigned long long), size, &opts); if (map_fd == -1) - perror("bpf_create_map"); + perror("bpf_map_create"); return map_fd; } @@ -42,8 +43,6 @@ static int create_map(int map_type, int map_flags, unsigned int size) static int bpf_map_lookup_elem_with_ref_bit(int fd, unsigned long long key, void *value) { - struct bpf_load_program_attr prog; - struct bpf_create_map_attr map; struct bpf_insn insns[] = { BPF_LD_MAP_VALUE(BPF_REG_9, 0, 0), BPF_LD_MAP_FD(BPF_REG_1, fd), @@ -64,25 +63,13 @@ static int bpf_map_lookup_elem_with_ref_bit(int fd, unsigned long long key, int mfd, pfd, ret, zero = 0; __u32 retval = 0; - memset(&map, 0, sizeof(map)); - map.map_type = BPF_MAP_TYPE_ARRAY; - map.key_size = sizeof(int); - map.value_size = sizeof(unsigned long long); - map.max_entries = 1; - - mfd = bpf_create_map_xattr(&map); + mfd = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, sizeof(int), sizeof(__u64), 1, NULL); if (mfd < 0) return -1; insns[0].imm = mfd; - memset(&prog, 0, sizeof(prog)); - prog.prog_type = BPF_PROG_TYPE_SCHED_CLS; - prog.insns = insns; - prog.insns_cnt = ARRAY_SIZE(insns); - prog.license = "GPL"; - - pfd = bpf_load_program_xattr(&prog, NULL, 0); + pfd = bpf_prog_load(BPF_PROG_TYPE_SCHED_CLS, NULL, "GPL", insns, ARRAY_SIZE(insns), NULL); if (pfd < 0) { close(mfd); return -1; diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c index c7a36a9378..50f7e74ca0 100644 --- a/tools/testing/selftests/bpf/test_maps.c +++ b/tools/testing/selftests/bpf/test_maps.c @@ -23,8 +23,8 @@ #include #include "bpf_util.h" -#include "bpf_rlimit.h" #include "test_maps.h" +#include "testing_helpers.h" #ifndef ENOTSUPP #define ENOTSUPP 524 @@ -32,15 +32,14 @@ static int skips; -static int map_flags; +static struct bpf_map_create_opts map_opts = { .sz = sizeof(map_opts) }; static void test_hashmap(unsigned int task, void *data) { long long key, next_key, first_key, value; int fd; - fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value), - 2, map_flags); + fd = bpf_map_create(BPF_MAP_TYPE_HASH, NULL, sizeof(key), sizeof(value), 2, &map_opts); if (fd < 0) { printf("Failed to create hashmap '%s'!\n", strerror(errno)); exit(1); @@ -137,8 +136,7 @@ static void test_hashmap_sizes(unsigned int task, void *data) for (i = 1; i <= 512; i <<= 1) for (j = 1; j <= 1 << 18; j <<= 1) { - fd = bpf_create_map(BPF_MAP_TYPE_HASH, i, j, - 2, map_flags); + fd = bpf_map_create(BPF_MAP_TYPE_HASH, NULL, i, j, 2, &map_opts); if (fd < 0) { if (errno == ENOMEM) return; @@ -159,8 +157,8 @@ static void test_hashmap_percpu(unsigned int task, void *data) int expected_key_mask = 0; int fd, i; - fd = bpf_create_map(BPF_MAP_TYPE_PERCPU_HASH, sizeof(key), - sizeof(bpf_percpu(value, 0)), 2, map_flags); + fd = bpf_map_create(BPF_MAP_TYPE_PERCPU_HASH, NULL, sizeof(key), + sizeof(bpf_percpu(value, 0)), 2, &map_opts); if (fd < 0) { printf("Failed to create hashmap '%s'!\n", strerror(errno)); exit(1); @@ -271,11 +269,11 @@ static int helper_fill_hashmap(int max_entries) int i, fd, ret; long long key, value; - fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value), - max_entries, map_flags); + fd = bpf_map_create(BPF_MAP_TYPE_HASH, NULL, sizeof(key), sizeof(value), + max_entries, &map_opts); CHECK(fd < 0, "failed to create hashmap", - "err: %s, flags: 0x%x\n", strerror(errno), map_flags); + "err: %s, flags: 0x%x\n", strerror(errno), map_opts.map_flags); for (i = 0; i < max_entries; i++) { key = i; value = key; @@ -331,8 +329,8 @@ static void test_hashmap_zero_seed(void) int i, first, second, old_flags; long long key, next_first, next_second; - old_flags = map_flags; - map_flags |= BPF_F_ZERO_SEED; + old_flags = map_opts.map_flags; + map_opts.map_flags |= BPF_F_ZERO_SEED; first = helper_fill_hashmap(3); second = helper_fill_hashmap(3); @@ -354,7 +352,7 @@ static void test_hashmap_zero_seed(void) key = next_first; } - map_flags = old_flags; + map_opts.map_flags = old_flags; close(first); close(second); } @@ -364,8 +362,7 @@ static void test_arraymap(unsigned int task, void *data) int key, next_key, fd; long long value; - fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, sizeof(key), sizeof(value), - 2, 0); + fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, sizeof(key), sizeof(value), 2, NULL); if (fd < 0) { printf("Failed to create arraymap '%s'!\n", strerror(errno)); exit(1); @@ -420,8 +417,8 @@ static void test_arraymap_percpu(unsigned int task, void *data) BPF_DECLARE_PERCPU(long, values); int key, next_key, fd, i; - fd = bpf_create_map(BPF_MAP_TYPE_PERCPU_ARRAY, sizeof(key), - sizeof(bpf_percpu(values, 0)), 2, 0); + fd = bpf_map_create(BPF_MAP_TYPE_PERCPU_ARRAY, NULL, sizeof(key), + sizeof(bpf_percpu(values, 0)), 2, NULL); if (fd < 0) { printf("Failed to create arraymap '%s'!\n", strerror(errno)); exit(1); @@ -483,8 +480,8 @@ static void test_arraymap_percpu_many_keys(void) unsigned int nr_keys = 2000; int key, fd, i; - fd = bpf_create_map(BPF_MAP_TYPE_PERCPU_ARRAY, sizeof(key), - sizeof(bpf_percpu(values, 0)), nr_keys, 0); + fd = bpf_map_create(BPF_MAP_TYPE_PERCPU_ARRAY, NULL, sizeof(key), + sizeof(bpf_percpu(values, 0)), nr_keys, NULL); if (fd < 0) { printf("Failed to create per-cpu arraymap '%s'!\n", strerror(errno)); @@ -515,8 +512,7 @@ static void test_devmap(unsigned int task, void *data) int fd; __u32 key, value; - fd = bpf_create_map(BPF_MAP_TYPE_DEVMAP, sizeof(key), sizeof(value), - 2, 0); + fd = bpf_map_create(BPF_MAP_TYPE_DEVMAP, NULL, sizeof(key), sizeof(value), 2, NULL); if (fd < 0) { printf("Failed to create devmap '%s'!\n", strerror(errno)); exit(1); @@ -530,8 +526,7 @@ static void test_devmap_hash(unsigned int task, void *data) int fd; __u32 key, value; - fd = bpf_create_map(BPF_MAP_TYPE_DEVMAP_HASH, sizeof(key), sizeof(value), - 2, 0); + fd = bpf_map_create(BPF_MAP_TYPE_DEVMAP_HASH, NULL, sizeof(key), sizeof(value), 2, NULL); if (fd < 0) { printf("Failed to create devmap_hash '%s'!\n", strerror(errno)); exit(1); @@ -551,14 +546,12 @@ static void test_queuemap(unsigned int task, void *data) vals[i] = rand(); /* Invalid key size */ - fd = bpf_create_map(BPF_MAP_TYPE_QUEUE, 4, sizeof(val), MAP_SIZE, - map_flags); + fd = bpf_map_create(BPF_MAP_TYPE_QUEUE, NULL, 4, sizeof(val), MAP_SIZE, &map_opts); assert(fd < 0 && errno == EINVAL); - fd = bpf_create_map(BPF_MAP_TYPE_QUEUE, 0, sizeof(val), MAP_SIZE, - map_flags); + fd = bpf_map_create(BPF_MAP_TYPE_QUEUE, NULL, 0, sizeof(val), MAP_SIZE, &map_opts); /* Queue map does not support BPF_F_NO_PREALLOC */ - if (map_flags & BPF_F_NO_PREALLOC) { + if (map_opts.map_flags & BPF_F_NO_PREALLOC) { assert(fd < 0 && errno == EINVAL); return; } @@ -609,14 +602,12 @@ static void test_stackmap(unsigned int task, void *data) vals[i] = rand(); /* Invalid key size */ - fd = bpf_create_map(BPF_MAP_TYPE_STACK, 4, sizeof(val), MAP_SIZE, - map_flags); + fd = bpf_map_create(BPF_MAP_TYPE_STACK, NULL, 4, sizeof(val), MAP_SIZE, &map_opts); assert(fd < 0 && errno == EINVAL); - fd = bpf_create_map(BPF_MAP_TYPE_STACK, 0, sizeof(val), MAP_SIZE, - map_flags); + fd = bpf_map_create(BPF_MAP_TYPE_STACK, NULL, 0, sizeof(val), MAP_SIZE, &map_opts); /* Stack map does not support BPF_F_NO_PREALLOC */ - if (map_flags & BPF_F_NO_PREALLOC) { + if (map_opts.map_flags & BPF_F_NO_PREALLOC) { assert(fd < 0 && errno == EINVAL); return; } @@ -743,9 +734,9 @@ static void test_sockmap(unsigned int tasks, void *data) } /* Test sockmap with connected sockets */ - fd = bpf_create_map(BPF_MAP_TYPE_SOCKMAP, + fd = bpf_map_create(BPF_MAP_TYPE_SOCKMAP, NULL, sizeof(key), sizeof(value), - 6, 0); + 6, NULL); if (fd < 0) { if (!bpf_probe_map_type(BPF_MAP_TYPE_SOCKMAP, 0)) { printf("%s SKIP (unsupported map type BPF_MAP_TYPE_SOCKMAP)\n", @@ -830,21 +821,21 @@ static void test_sockmap(unsigned int tasks, void *data) } /* Load SK_SKB program and Attach */ - err = bpf_prog_load(SOCKMAP_PARSE_PROG, + err = bpf_prog_test_load(SOCKMAP_PARSE_PROG, BPF_PROG_TYPE_SK_SKB, &obj, &parse_prog); if (err) { printf("Failed to load SK_SKB parse prog\n"); goto out_sockmap; } - err = bpf_prog_load(SOCKMAP_TCP_MSG_PROG, + err = bpf_prog_test_load(SOCKMAP_TCP_MSG_PROG, BPF_PROG_TYPE_SK_MSG, &obj, &msg_prog); if (err) { printf("Failed to load SK_SKB msg prog\n"); goto out_sockmap; } - err = bpf_prog_load(SOCKMAP_VERDICT_PROG, + err = bpf_prog_test_load(SOCKMAP_VERDICT_PROG, BPF_PROG_TYPE_SK_SKB, &obj, &verdict_prog); if (err) { printf("Failed to load SK_SKB verdict prog\n"); @@ -1167,8 +1158,7 @@ static void test_map_in_map(void) obj = bpf_object__open(MAPINMAP_PROG); - fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(int), sizeof(int), - 2, 0); + fd = bpf_map_create(BPF_MAP_TYPE_HASH, NULL, sizeof(int), sizeof(int), 2, NULL); if (fd < 0) { printf("Failed to create hashmap '%s'!\n", strerror(errno)); exit(1); @@ -1314,8 +1304,8 @@ static void test_map_large(void) } key; int fd, i, value; - fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value), - MAP_SIZE, map_flags); + fd = bpf_map_create(BPF_MAP_TYPE_HASH, NULL, sizeof(key), sizeof(value), + MAP_SIZE, &map_opts); if (fd < 0) { printf("Failed to create large map '%s'!\n", strerror(errno)); exit(1); @@ -1468,8 +1458,8 @@ static void test_map_parallel(void) int i, fd, key = 0, value = 0; int data[2]; - fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value), - MAP_SIZE, map_flags); + fd = bpf_map_create(BPF_MAP_TYPE_HASH, NULL, sizeof(key), sizeof(value), + MAP_SIZE, &map_opts); if (fd < 0) { printf("Failed to create map for parallel test '%s'!\n", strerror(errno)); @@ -1517,9 +1507,13 @@ static void test_map_parallel(void) static void test_map_rdonly(void) { int fd, key = 0, value = 0; + __u32 old_flags; - fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value), - MAP_SIZE, map_flags | BPF_F_RDONLY); + old_flags = map_opts.map_flags; + map_opts.map_flags |= BPF_F_RDONLY; + fd = bpf_map_create(BPF_MAP_TYPE_HASH, NULL, sizeof(key), sizeof(value), + MAP_SIZE, &map_opts); + map_opts.map_flags = old_flags; if (fd < 0) { printf("Failed to create map for read only test '%s'!\n", strerror(errno)); @@ -1542,9 +1536,13 @@ static void test_map_rdonly(void) static void test_map_wronly_hash(void) { int fd, key = 0, value = 0; + __u32 old_flags; - fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value), - MAP_SIZE, map_flags | BPF_F_WRONLY); + old_flags = map_opts.map_flags; + map_opts.map_flags |= BPF_F_WRONLY; + fd = bpf_map_create(BPF_MAP_TYPE_HASH, NULL, sizeof(key), sizeof(value), + MAP_SIZE, &map_opts); + map_opts.map_flags = old_flags; if (fd < 0) { printf("Failed to create map for write only test '%s'!\n", strerror(errno)); @@ -1566,13 +1564,17 @@ static void test_map_wronly_hash(void) static void test_map_wronly_stack_or_queue(enum bpf_map_type map_type) { int fd, value = 0; + __u32 old_flags; + assert(map_type == BPF_MAP_TYPE_QUEUE || map_type == BPF_MAP_TYPE_STACK); - fd = bpf_create_map(map_type, 0, sizeof(value), MAP_SIZE, - map_flags | BPF_F_WRONLY); + old_flags = map_opts.map_flags; + map_opts.map_flags |= BPF_F_WRONLY; + fd = bpf_map_create(map_type, NULL, 0, sizeof(value), MAP_SIZE, &map_opts); + map_opts.map_flags = old_flags; /* Stack/Queue maps do not support BPF_F_NO_PREALLOC */ - if (map_flags & BPF_F_NO_PREALLOC) { + if (map_opts.map_flags & BPF_F_NO_PREALLOC) { assert(fd < 0 && errno == EINVAL); return; } @@ -1699,8 +1701,8 @@ static void test_reuseport_array(void) __u32 fds_idx = 0; int fd; - map_fd = bpf_create_map(BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, - sizeof(__u32), sizeof(__u64), array_size, 0); + map_fd = bpf_map_create(BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, NULL, + sizeof(__u32), sizeof(__u64), array_size, NULL); CHECK(map_fd < 0, "reuseport array create", "map_fd:%d, errno:%d\n", map_fd, errno); @@ -1836,8 +1838,8 @@ static void test_reuseport_array(void) close(map_fd); /* Test 32 bit fd */ - map_fd = bpf_create_map(BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, - sizeof(__u32), sizeof(__u32), array_size, 0); + map_fd = bpf_map_create(BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, NULL, + sizeof(__u32), sizeof(__u32), array_size, NULL); CHECK(map_fd < 0, "reuseport array create", "map_fd:%d, errno:%d\n", map_fd, errno); prepare_reuseport_grp(SOCK_STREAM, map_fd, sizeof(__u32), &fd64, @@ -1895,10 +1897,10 @@ int main(void) libbpf_set_strict_mode(LIBBPF_STRICT_ALL); - map_flags = 0; + map_opts.map_flags = 0; run_all_tests(); - map_flags = BPF_F_NO_PREALLOC; + map_opts.map_flags = BPF_F_NO_PREALLOC; run_all_tests(); #define DEFINE_TEST(name) test_##name(); diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index e3fea6f281..2ecb73a652 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -4,7 +4,6 @@ #define _GNU_SOURCE #include "test_progs.h" #include "cgroup_helpers.h" -#include "bpf_rlimit.h" #include #include #include @@ -12,6 +11,11 @@ #include #include /* backtrace */ #include +#include /* get_nprocs */ +#include +#include +#include +#include /* Adapted from perf/util/string.c */ static bool glob_match(const char *str, const char *pat) @@ -45,9 +49,12 @@ struct prog_test_def { const char *test_name; int test_num; void (*run_test)(void); + void (*run_serial_test)(void); bool force_log; int error_cnt; int skip_cnt; + int sub_succ_cnt; + bool should_run; bool tested; bool need_cgroup_cleanup; @@ -97,6 +104,10 @@ static void dump_test_log(const struct prog_test_def *test, bool failed) if (stdout == env.stdout) return; + /* worker always holds log */ + if (env.worker_id != -1) + return; + fflush(stdout); /* exports env.log_buf & env.log_cnt */ if (env.verbosity > VERBOSE_NONE || test->force_log || failed) { @@ -107,8 +118,6 @@ static void dump_test_log(const struct prog_test_def *test, bool failed) fprintf(env.stdout, "\n"); } } - - fseeko(stdout, 0, SEEK_SET); /* rewind */ } static void skip_account(void) @@ -124,7 +133,8 @@ static void stdio_restore(void); /* A bunch of tests set custom affinity per-thread and/or per-process. Reset * it after each test/sub-test. */ -static void reset_affinity() { +static void reset_affinity(void) +{ cpu_set_t cpuset; int i, err; @@ -165,21 +175,21 @@ static void restore_netns(void) } } -void test__end_subtest() +void test__end_subtest(void) { struct prog_test_def *test = env.test; int sub_error_cnt = test->error_cnt - test->old_error_cnt; dump_test_log(test, sub_error_cnt); - fprintf(env.stdout, "#%d/%d %s/%s:%s\n", + fprintf(stdout, "#%d/%d %s/%s:%s\n", test->test_num, test->subtest_num, test->test_name, test->subtest_name, sub_error_cnt ? "FAIL" : (test->skip_cnt ? "SKIP" : "OK")); if (sub_error_cnt) - env.fail_cnt++; + test->error_cnt++; else if (test->skip_cnt == 0) - env.sub_succ_cnt++; + test->sub_succ_cnt++; skip_account(); free(test->subtest_name); @@ -217,7 +227,8 @@ bool test__start_subtest(const char *name) return true; } -void test__force_log() { +void test__force_log(void) +{ env.test->force_log = true; } @@ -446,23 +457,26 @@ static int load_bpf_testmod(void) } /* extern declarations for test funcs */ -#define DEFINE_TEST(name) extern void test_##name(void); +#define DEFINE_TEST(name) \ + extern void test_##name(void) __weak; \ + extern void serial_test_##name(void) __weak; #include #undef DEFINE_TEST static struct prog_test_def prog_test_defs[] = { -#define DEFINE_TEST(name) { \ - .test_name = #name, \ - .run_test = &test_##name, \ +#define DEFINE_TEST(name) { \ + .test_name = #name, \ + .run_test = &test_##name, \ + .run_serial_test = &serial_test_##name, \ }, #include #undef DEFINE_TEST }; -const int prog_test_cnt = ARRAY_SIZE(prog_test_defs); +static const int prog_test_cnt = ARRAY_SIZE(prog_test_defs); const char *argp_program_version = "test_progs 0.1"; const char *argp_program_bug_address = ""; -const char argp_program_doc[] = "BPF selftests test runner"; +static const char argp_program_doc[] = "BPF selftests test runner"; enum ARG_KEYS { ARG_TEST_NUM = 'n', @@ -474,6 +488,8 @@ enum ARG_KEYS { ARG_LIST_TEST_NAMES = 'l', ARG_TEST_NAME_GLOB_ALLOWLIST = 'a', ARG_TEST_NAME_GLOB_DENYLIST = 'd', + ARG_NUM_WORKERS = 'j', + ARG_DEBUG = -1, }; static const struct argp_option opts[] = { @@ -495,6 +511,10 @@ static const struct argp_option opts[] = { "Run tests with name matching the pattern (supports '*' wildcard)." }, { "deny", ARG_TEST_NAME_GLOB_DENYLIST, "NAMES", 0, "Don't run tests with name matching the pattern (supports '*' wildcard)." }, + { "workers", ARG_NUM_WORKERS, "WORKERS", OPTION_ARG_OPTIONAL, + "Number of workers to run in parallel, default to number of cpus." }, + { "debug", ARG_DEBUG, NULL, 0, + "print extra debug information for test_progs." }, {}, }; @@ -650,7 +670,7 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state) fprintf(stderr, "Unable to setenv SELFTESTS_VERBOSE=1 (errno=%d)", errno); - return -1; + return -EINVAL; } } @@ -661,6 +681,20 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state) case ARG_LIST_TEST_NAMES: env->list_test_names = true; break; + case ARG_NUM_WORKERS: + if (arg) { + env->workers = atoi(arg); + if (!env->workers) { + fprintf(stderr, "Invalid number of worker: %s.", arg); + return -EINVAL; + } + } else { + env->workers = get_nprocs(); + } + break; + case ARG_DEBUG: + env->debug = true; + break; case ARGP_KEY_ARG: argp_usage(state); break; @@ -678,7 +712,7 @@ static void stdio_hijack(void) env.stdout = stdout; env.stderr = stderr; - if (env.verbosity > VERBOSE_NONE) { + if (env.verbosity > VERBOSE_NONE && env.worker_id == -1) { /* nothing to do, output to stdout by default */ return; } @@ -704,10 +738,6 @@ static void stdio_restore(void) return; fclose(stdout); - free(env.log_buf); - - env.log_buf = NULL; - env.log_cnt = 0; stdout = env.stdout; stderr = env.stderr; @@ -743,6 +773,45 @@ int cd_flavor_subdir(const char *exec_name) return chdir(flavor); } +int trigger_module_test_read(int read_sz) +{ + int fd, err; + + fd = open(BPF_TESTMOD_TEST_FILE, O_RDONLY); + err = -errno; + if (!ASSERT_GE(fd, 0, "testmod_file_open")) + return err; + + read(fd, NULL, read_sz); + close(fd); + + return 0; +} + +int trigger_module_test_write(int write_sz) +{ + int fd, err; + char *buf = malloc(write_sz); + + if (!buf) + return -ENOMEM; + + memset(buf, 'a', write_sz); + buf[write_sz-1] = '\0'; + + fd = open(BPF_TESTMOD_TEST_FILE, O_WRONLY); + err = -errno; + if (!ASSERT_GE(fd, 0, "testmod_file_open")) { + free(buf); + return err; + } + + write(fd, buf, write_sz); + close(fd); + free(buf); + return 0; +} + #define MAX_BACKTRACE_SZ 128 void crash_handler(int signum) { @@ -755,11 +824,498 @@ void crash_handler(int signum) dump_test_log(env.test, true); if (env.stdout) stdio_restore(); - + if (env.worker_id != -1) + fprintf(stderr, "[%d]: ", env.worker_id); fprintf(stderr, "Caught signal #%d!\nStack trace:\n", signum); backtrace_symbols_fd(bt, sz, STDERR_FILENO); } +static void sigint_handler(int signum) +{ + int i; + + for (i = 0; i < env.workers; i++) + if (env.worker_socks[i] > 0) + close(env.worker_socks[i]); +} + +static int current_test_idx; +static pthread_mutex_t current_test_lock; +static pthread_mutex_t stdout_output_lock; + +struct test_result { + int error_cnt; + int skip_cnt; + int sub_succ_cnt; + + size_t log_cnt; + char *log_buf; +}; + +static struct test_result test_results[ARRAY_SIZE(prog_test_defs)]; + +static inline const char *str_msg(const struct msg *msg, char *buf) +{ + switch (msg->type) { + case MSG_DO_TEST: + sprintf(buf, "MSG_DO_TEST %d", msg->do_test.test_num); + break; + case MSG_TEST_DONE: + sprintf(buf, "MSG_TEST_DONE %d (log: %d)", + msg->test_done.test_num, + msg->test_done.have_log); + break; + case MSG_TEST_LOG: + sprintf(buf, "MSG_TEST_LOG (cnt: %ld, last: %d)", + strlen(msg->test_log.log_buf), + msg->test_log.is_last); + break; + case MSG_EXIT: + sprintf(buf, "MSG_EXIT"); + break; + default: + sprintf(buf, "UNKNOWN"); + break; + } + + return buf; +} + +static int send_message(int sock, const struct msg *msg) +{ + char buf[256]; + + if (env.debug) + fprintf(stderr, "Sending msg: %s\n", str_msg(msg, buf)); + return send(sock, msg, sizeof(*msg), 0); +} + +static int recv_message(int sock, struct msg *msg) +{ + int ret; + char buf[256]; + + memset(msg, 0, sizeof(*msg)); + ret = recv(sock, msg, sizeof(*msg), 0); + if (ret >= 0) { + if (env.debug) + fprintf(stderr, "Received msg: %s\n", str_msg(msg, buf)); + } + return ret; +} + +static void run_one_test(int test_num) +{ + struct prog_test_def *test = &prog_test_defs[test_num]; + + env.test = test; + + if (test->run_test) + test->run_test(); + else if (test->run_serial_test) + test->run_serial_test(); + + /* ensure last sub-test is finalized properly */ + if (test->subtest_name) + test__end_subtest(); + + test->tested = true; + + dump_test_log(test, test->error_cnt); + + reset_affinity(); + restore_netns(); + if (test->need_cgroup_cleanup) + cleanup_cgroup_environment(); +} + +struct dispatch_data { + int worker_id; + int sock_fd; +}; + +static void *dispatch_thread(void *ctx) +{ + struct dispatch_data *data = ctx; + int sock_fd; + FILE *log_fp = NULL; + + sock_fd = data->sock_fd; + + while (true) { + int test_to_run = -1; + struct prog_test_def *test; + struct test_result *result; + + /* grab a test */ + { + pthread_mutex_lock(¤t_test_lock); + + if (current_test_idx >= prog_test_cnt) { + pthread_mutex_unlock(¤t_test_lock); + goto done; + } + + test = &prog_test_defs[current_test_idx]; + test_to_run = current_test_idx; + current_test_idx++; + + pthread_mutex_unlock(¤t_test_lock); + } + + if (!test->should_run || test->run_serial_test) + continue; + + /* run test through worker */ + { + struct msg msg_do_test; + + msg_do_test.type = MSG_DO_TEST; + msg_do_test.do_test.test_num = test_to_run; + if (send_message(sock_fd, &msg_do_test) < 0) { + perror("Fail to send command"); + goto done; + } + env.worker_current_test[data->worker_id] = test_to_run; + } + + /* wait for test done */ + { + int err; + struct msg msg_test_done; + + err = recv_message(sock_fd, &msg_test_done); + if (err < 0) + goto error; + if (msg_test_done.type != MSG_TEST_DONE) + goto error; + if (test_to_run != msg_test_done.test_done.test_num) + goto error; + + test->tested = true; + result = &test_results[test_to_run]; + + result->error_cnt = msg_test_done.test_done.error_cnt; + result->skip_cnt = msg_test_done.test_done.skip_cnt; + result->sub_succ_cnt = msg_test_done.test_done.sub_succ_cnt; + + /* collect all logs */ + if (msg_test_done.test_done.have_log) { + log_fp = open_memstream(&result->log_buf, &result->log_cnt); + if (!log_fp) + goto error; + + while (true) { + struct msg msg_log; + + if (recv_message(sock_fd, &msg_log) < 0) + goto error; + if (msg_log.type != MSG_TEST_LOG) + goto error; + + fprintf(log_fp, "%s", msg_log.test_log.log_buf); + if (msg_log.test_log.is_last) + break; + } + fclose(log_fp); + log_fp = NULL; + } + /* output log */ + { + pthread_mutex_lock(&stdout_output_lock); + + if (result->log_cnt) { + result->log_buf[result->log_cnt] = '\0'; + fprintf(stdout, "%s", result->log_buf); + if (result->log_buf[result->log_cnt - 1] != '\n') + fprintf(stdout, "\n"); + } + + fprintf(stdout, "#%d %s:%s\n", + test->test_num, test->test_name, + result->error_cnt ? "FAIL" : (result->skip_cnt ? "SKIP" : "OK")); + + pthread_mutex_unlock(&stdout_output_lock); + } + + } /* wait for test done */ + } /* while (true) */ +error: + if (env.debug) + fprintf(stderr, "[%d]: Protocol/IO error: %s.\n", data->worker_id, strerror(errno)); + + if (log_fp) + fclose(log_fp); +done: + { + struct msg msg_exit; + + msg_exit.type = MSG_EXIT; + if (send_message(sock_fd, &msg_exit) < 0) { + if (env.debug) + fprintf(stderr, "[%d]: send_message msg_exit: %s.\n", + data->worker_id, strerror(errno)); + } + } + return NULL; +} + +static void print_all_error_logs(void) +{ + int i; + + if (env.fail_cnt) + fprintf(stdout, "\nAll error logs:\n"); + + /* print error logs again */ + for (i = 0; i < prog_test_cnt; i++) { + struct prog_test_def *test; + struct test_result *result; + + test = &prog_test_defs[i]; + result = &test_results[i]; + + if (!test->tested || !result->error_cnt) + continue; + + fprintf(stdout, "\n#%d %s:%s\n", + test->test_num, test->test_name, + result->error_cnt ? "FAIL" : (result->skip_cnt ? "SKIP" : "OK")); + + if (result->log_cnt) { + result->log_buf[result->log_cnt] = '\0'; + fprintf(stdout, "%s", result->log_buf); + if (result->log_buf[result->log_cnt - 1] != '\n') + fprintf(stdout, "\n"); + } + } +} + +static int server_main(void) +{ + pthread_t *dispatcher_threads; + struct dispatch_data *data; + struct sigaction sigact_int = { + .sa_handler = sigint_handler, + .sa_flags = SA_RESETHAND, + }; + int i; + + sigaction(SIGINT, &sigact_int, NULL); + + dispatcher_threads = calloc(sizeof(pthread_t), env.workers); + data = calloc(sizeof(struct dispatch_data), env.workers); + + env.worker_current_test = calloc(sizeof(int), env.workers); + for (i = 0; i < env.workers; i++) { + int rc; + + data[i].worker_id = i; + data[i].sock_fd = env.worker_socks[i]; + rc = pthread_create(&dispatcher_threads[i], NULL, dispatch_thread, &data[i]); + if (rc < 0) { + perror("Failed to launch dispatcher thread"); + exit(EXIT_ERR_SETUP_INFRA); + } + } + + /* wait for all dispatcher to finish */ + for (i = 0; i < env.workers; i++) { + while (true) { + int ret = pthread_tryjoin_np(dispatcher_threads[i], NULL); + + if (!ret) { + break; + } else if (ret == EBUSY) { + if (env.debug) + fprintf(stderr, "Still waiting for thread %d (test %d).\n", + i, env.worker_current_test[i] + 1); + usleep(1000 * 1000); + continue; + } else { + fprintf(stderr, "Unexpected error joining dispatcher thread: %d", ret); + break; + } + } + } + free(dispatcher_threads); + free(env.worker_current_test); + free(data); + + /* run serial tests */ + save_netns(); + + for (int i = 0; i < prog_test_cnt; i++) { + struct prog_test_def *test = &prog_test_defs[i]; + struct test_result *result = &test_results[i]; + + if (!test->should_run || !test->run_serial_test) + continue; + + stdio_hijack(); + + run_one_test(i); + + stdio_restore(); + if (env.log_buf) { + result->log_cnt = env.log_cnt; + result->log_buf = strdup(env.log_buf); + + free(env.log_buf); + env.log_buf = NULL; + env.log_cnt = 0; + } + restore_netns(); + + fprintf(stdout, "#%d %s:%s\n", + test->test_num, test->test_name, + test->error_cnt ? "FAIL" : (test->skip_cnt ? "SKIP" : "OK")); + + result->error_cnt = test->error_cnt; + result->skip_cnt = test->skip_cnt; + result->sub_succ_cnt = test->sub_succ_cnt; + } + + /* generate summary */ + fflush(stderr); + fflush(stdout); + + for (i = 0; i < prog_test_cnt; i++) { + struct prog_test_def *current_test; + struct test_result *result; + + current_test = &prog_test_defs[i]; + result = &test_results[i]; + + if (!current_test->tested) + continue; + + env.succ_cnt += result->error_cnt ? 0 : 1; + env.skip_cnt += result->skip_cnt; + if (result->error_cnt) + env.fail_cnt++; + env.sub_succ_cnt += result->sub_succ_cnt; + } + + print_all_error_logs(); + + fprintf(stdout, "Summary: %d/%d PASSED, %d SKIPPED, %d FAILED\n", + env.succ_cnt, env.sub_succ_cnt, env.skip_cnt, env.fail_cnt); + + /* reap all workers */ + for (i = 0; i < env.workers; i++) { + int wstatus, pid; + + pid = waitpid(env.worker_pids[i], &wstatus, 0); + if (pid != env.worker_pids[i]) + perror("Unable to reap worker"); + } + + return 0; +} + +static int worker_main(int sock) +{ + save_netns(); + + while (true) { + /* receive command */ + struct msg msg; + + if (recv_message(sock, &msg) < 0) + goto out; + + switch (msg.type) { + case MSG_EXIT: + if (env.debug) + fprintf(stderr, "[%d]: worker exit.\n", + env.worker_id); + goto out; + case MSG_DO_TEST: { + int test_to_run; + struct prog_test_def *test; + struct msg msg_done; + + test_to_run = msg.do_test.test_num; + test = &prog_test_defs[test_to_run]; + + if (env.debug) + fprintf(stderr, "[%d]: #%d:%s running.\n", + env.worker_id, + test_to_run + 1, + test->test_name); + + stdio_hijack(); + + run_one_test(test_to_run); + + stdio_restore(); + + memset(&msg_done, 0, sizeof(msg_done)); + msg_done.type = MSG_TEST_DONE; + msg_done.test_done.test_num = test_to_run; + msg_done.test_done.error_cnt = test->error_cnt; + msg_done.test_done.skip_cnt = test->skip_cnt; + msg_done.test_done.sub_succ_cnt = test->sub_succ_cnt; + msg_done.test_done.have_log = false; + + if (env.verbosity > VERBOSE_NONE || test->force_log || test->error_cnt) { + if (env.log_cnt) + msg_done.test_done.have_log = true; + } + if (send_message(sock, &msg_done) < 0) { + perror("Fail to send message done"); + goto out; + } + + /* send logs */ + if (msg_done.test_done.have_log) { + char *src; + size_t slen; + + src = env.log_buf; + slen = env.log_cnt; + while (slen) { + struct msg msg_log; + char *dest; + size_t len; + + memset(&msg_log, 0, sizeof(msg_log)); + msg_log.type = MSG_TEST_LOG; + dest = msg_log.test_log.log_buf; + len = slen >= MAX_LOG_TRUNK_SIZE ? MAX_LOG_TRUNK_SIZE : slen; + memcpy(dest, src, len); + + src += len; + slen -= len; + if (!slen) + msg_log.test_log.is_last = true; + + assert(send_message(sock, &msg_log) >= 0); + } + } + if (env.log_buf) { + free(env.log_buf); + env.log_buf = NULL; + env.log_cnt = 0; + } + if (env.debug) + fprintf(stderr, "[%d]: #%d:%s done.\n", + env.worker_id, + test_to_run + 1, + test->test_name); + break; + } /* case MSG_DO_TEST */ + default: + if (env.debug) + fprintf(stderr, "[%d]: unknown message.\n", env.worker_id); + return -1; + } + } +out: + return 0; +} + int main(int argc, char **argv) { static const struct argp argp = { @@ -770,7 +1326,7 @@ int main(int argc, char **argv) struct sigaction sigact = { .sa_handler = crash_handler, .sa_flags = SA_RESETHAND, - }; + }; int err, i; sigaction(SIGSEGV, &sigact, NULL); @@ -785,7 +1341,6 @@ int main(int argc, char **argv) /* Use libbpf 1.0 API mode */ libbpf_set_strict_mode(LIBBPF_STRICT_ALL); - libbpf_set_print(libbpf_print_fn); srand(time(NULL)); @@ -798,21 +1353,84 @@ int main(int argc, char **argv) return -1; } - save_netns(); - stdio_hijack(); + env.stdout = stdout; + env.stderr = stderr; + env.has_testmod = true; if (!env.list_test_names && load_bpf_testmod()) { fprintf(env.stderr, "WARNING! Selftests relying on bpf_testmod.ko will be skipped.\n"); env.has_testmod = false; } + + /* initializing tests */ for (i = 0; i < prog_test_cnt; i++) { struct prog_test_def *test = &prog_test_defs[i]; - env.test = test; test->test_num = i + 1; - - if (!should_run(&env.test_selector, + if (should_run(&env.test_selector, test->test_num, test->test_name)) + test->should_run = true; + else + test->should_run = false; + + if ((test->run_test == NULL && test->run_serial_test == NULL) || + (test->run_test != NULL && test->run_serial_test != NULL)) { + fprintf(stderr, "Test %d:%s must have either test_%s() or serial_test_%sl() defined.\n", + test->test_num, test->test_name, test->test_name, test->test_name); + exit(EXIT_ERR_SETUP_INFRA); + } + } + + /* ignore workers if we are just listing */ + if (env.get_test_cnt || env.list_test_names) + env.workers = 0; + + /* launch workers if requested */ + env.worker_id = -1; /* main process */ + if (env.workers) { + env.worker_pids = calloc(sizeof(__pid_t), env.workers); + env.worker_socks = calloc(sizeof(int), env.workers); + if (env.debug) + fprintf(stdout, "Launching %d workers.\n", env.workers); + for (i = 0; i < env.workers; i++) { + int sv[2]; + pid_t pid; + + if (socketpair(AF_UNIX, SOCK_SEQPACKET | SOCK_CLOEXEC, 0, sv) < 0) { + perror("Fail to create worker socket"); + return -1; + } + pid = fork(); + if (pid < 0) { + perror("Failed to fork worker"); + return -1; + } else if (pid != 0) { /* main process */ + close(sv[1]); + env.worker_pids[i] = pid; + env.worker_socks[i] = sv[0]; + } else { /* inside each worker process */ + close(sv[0]); + env.worker_id = i; + return worker_main(sv[1]); + } + } + + if (env.worker_id == -1) { + server_main(); + goto out; + } + } + + /* The rest of the main process */ + + /* on single mode */ + save_netns(); + + for (i = 0; i < prog_test_cnt; i++) { + struct prog_test_def *test = &prog_test_defs[i]; + struct test_result *result; + + if (!test->should_run) continue; if (env.get_test_cnt) { @@ -826,33 +1444,35 @@ int main(int argc, char **argv) continue; } - test->run_test(); - /* ensure last sub-test is finalized properly */ - if (test->subtest_name) - test__end_subtest(); + stdio_hijack(); - test->tested = true; + run_one_test(i); - dump_test_log(test, test->error_cnt); + stdio_restore(); fprintf(env.stdout, "#%d %s:%s\n", test->test_num, test->test_name, test->error_cnt ? "FAIL" : (test->skip_cnt ? "SKIP" : "OK")); + result = &test_results[i]; + result->error_cnt = test->error_cnt; + if (env.log_buf) { + result->log_buf = strdup(env.log_buf); + result->log_cnt = env.log_cnt; + + free(env.log_buf); + env.log_buf = NULL; + env.log_cnt = 0; + } + if (test->error_cnt) env.fail_cnt++; else env.succ_cnt++; - skip_account(); - reset_affinity(); - restore_netns(); - if (test->need_cgroup_cleanup) - cleanup_cgroup_environment(); + skip_account(); + env.sub_succ_cnt += test->sub_succ_cnt; } - if (!env.list_test_names && env.has_testmod) - unload_bpf_testmod(); - stdio_restore(); if (env.get_test_cnt) { printf("%d\n", env.succ_cnt); @@ -862,17 +1482,21 @@ int main(int argc, char **argv) if (env.list_test_names) goto out; + print_all_error_logs(); + fprintf(stdout, "Summary: %d/%d PASSED, %d SKIPPED, %d FAILED\n", env.succ_cnt, env.sub_succ_cnt, env.skip_cnt, env.fail_cnt); + close(env.saved_netns_fd); out: + if (!env.list_test_names && env.has_testmod) + unload_bpf_testmod(); free_str_set(&env.test_selector.blacklist); free_str_set(&env.test_selector.whitelist); free(env.test_selector.num_set); free_str_set(&env.subtest_selector.blacklist); free_str_set(&env.subtest_selector.whitelist); free(env.subtest_selector.num_set); - close(env.saved_netns_fd); if (env.succ_cnt + env.fail_cnt + env.skip_cnt == 0) return EXIT_NO_TEST; diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h index c8c2bf878f..93c1ff7055 100644 --- a/tools/testing/selftests/bpf/test_progs.h +++ b/tools/testing/selftests/bpf/test_progs.h @@ -62,6 +62,7 @@ struct test_env { struct test_selector test_selector; struct test_selector subtest_selector; bool verifier_stats; + bool debug; enum verbosity verbosity; bool jit_enabled; @@ -69,7 +70,8 @@ struct test_env { bool get_test_cnt; bool list_test_names; - struct prog_test_def *test; + struct prog_test_def *test; /* current running tests */ + FILE *stdout; FILE *stderr; char *log_buf; @@ -82,6 +84,38 @@ struct test_env { int skip_cnt; /* skipped tests */ int saved_netns_fd; + int workers; /* number of worker process */ + int worker_id; /* id number of current worker, main process is -1 */ + pid_t *worker_pids; /* array of worker pids */ + int *worker_socks; /* array of worker socks */ + int *worker_current_test; /* array of current running test for each worker */ +}; + +#define MAX_LOG_TRUNK_SIZE 8192 +enum msg_type { + MSG_DO_TEST = 0, + MSG_TEST_DONE = 1, + MSG_TEST_LOG = 2, + MSG_EXIT = 255, +}; +struct msg { + enum msg_type type; + union { + struct { + int test_num; + } do_test; + struct { + int test_num; + int sub_succ_cnt; + int error_cnt; + int skip_cnt; + bool have_log; + } test_done; + struct { + char log_buf[MAX_LOG_TRUNK_SIZE + 1]; + bool is_last; + } test_log; + }; }; extern struct test_env env; @@ -291,6 +325,8 @@ int compare_map_keys(int map1_fd, int map2_fd); int compare_stack_ips(int smap_fd, int amap_fd, int stack_trace_len); int extract_build_id(char *build_id, size_t size); int kern_sync_rcu(void); +int trigger_module_test_read(int read_sz); +int trigger_module_test_write(int write_sz); #ifdef __x86_64__ #define SYS_NANOSLEEP_KPROBE_NAME "__x64_sys_nanosleep" @@ -299,3 +335,5 @@ int kern_sync_rcu(void); #else #define SYS_NANOSLEEP_KPROBE_NAME "sys_nanosleep" #endif + +#define BPF_TESTMOD_TEST_FILE "/sys/kernel/bpf_testmod" diff --git a/tools/testing/selftests/bpf/test_sock.c b/tools/testing/selftests/bpf/test_sock.c index 9613f75388..fe10f81342 100644 --- a/tools/testing/selftests/bpf/test_sock.c +++ b/tools/testing/selftests/bpf/test_sock.c @@ -35,18 +35,21 @@ struct sock_test { /* Endpoint to bind() to */ const char *ip; unsigned short port; + unsigned short port_retry; /* Expected test result */ enum { LOAD_REJECT, ATTACH_REJECT, BIND_REJECT, SUCCESS, + RETRY_SUCCESS, + RETRY_REJECT } result; }; static struct sock_test tests[] = { { - "bind4 load with invalid access: src_ip6", + .descr = "bind4 load with invalid access: src_ip6", .insns = { BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6, @@ -54,16 +57,12 @@ static struct sock_test tests[] = { BPF_MOV64_IMM(BPF_REG_0, 1), BPF_EXIT_INSN(), }, - BPF_CGROUP_INET4_POST_BIND, - BPF_CGROUP_INET4_POST_BIND, - 0, - 0, - NULL, - 0, - LOAD_REJECT, + .expected_attach_type = BPF_CGROUP_INET4_POST_BIND, + .attach_type = BPF_CGROUP_INET4_POST_BIND, + .result = LOAD_REJECT, }, { - "bind4 load with invalid access: mark", + .descr = "bind4 load with invalid access: mark", .insns = { BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6, @@ -71,16 +70,12 @@ static struct sock_test tests[] = { BPF_MOV64_IMM(BPF_REG_0, 1), BPF_EXIT_INSN(), }, - BPF_CGROUP_INET4_POST_BIND, - BPF_CGROUP_INET4_POST_BIND, - 0, - 0, - NULL, - 0, - LOAD_REJECT, + .expected_attach_type = BPF_CGROUP_INET4_POST_BIND, + .attach_type = BPF_CGROUP_INET4_POST_BIND, + .result = LOAD_REJECT, }, { - "bind6 load with invalid access: src_ip4", + .descr = "bind6 load with invalid access: src_ip4", .insns = { BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6, @@ -88,16 +83,12 @@ static struct sock_test tests[] = { BPF_MOV64_IMM(BPF_REG_0, 1), BPF_EXIT_INSN(), }, - BPF_CGROUP_INET6_POST_BIND, - BPF_CGROUP_INET6_POST_BIND, - 0, - 0, - NULL, - 0, - LOAD_REJECT, + .expected_attach_type = BPF_CGROUP_INET6_POST_BIND, + .attach_type = BPF_CGROUP_INET6_POST_BIND, + .result = LOAD_REJECT, }, { - "sock_create load with invalid access: src_port", + .descr = "sock_create load with invalid access: src_port", .insns = { BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6, @@ -105,128 +96,106 @@ static struct sock_test tests[] = { BPF_MOV64_IMM(BPF_REG_0, 1), BPF_EXIT_INSN(), }, - BPF_CGROUP_INET_SOCK_CREATE, - BPF_CGROUP_INET_SOCK_CREATE, - 0, - 0, - NULL, - 0, - LOAD_REJECT, + .expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE, + .attach_type = BPF_CGROUP_INET_SOCK_CREATE, + .result = LOAD_REJECT, }, { - "sock_create load w/o expected_attach_type (compat mode)", + .descr = "sock_create load w/o expected_attach_type (compat mode)", .insns = { BPF_MOV64_IMM(BPF_REG_0, 1), BPF_EXIT_INSN(), }, - 0, - BPF_CGROUP_INET_SOCK_CREATE, - AF_INET, - SOCK_STREAM, - "127.0.0.1", - 8097, - SUCCESS, + .expected_attach_type = 0, + .attach_type = BPF_CGROUP_INET_SOCK_CREATE, + .domain = AF_INET, + .type = SOCK_STREAM, + .ip = "127.0.0.1", + .port = 8097, + .result = SUCCESS, }, { - "sock_create load w/ expected_attach_type", + .descr = "sock_create load w/ expected_attach_type", .insns = { BPF_MOV64_IMM(BPF_REG_0, 1), BPF_EXIT_INSN(), }, - BPF_CGROUP_INET_SOCK_CREATE, - BPF_CGROUP_INET_SOCK_CREATE, - AF_INET, - SOCK_STREAM, - "127.0.0.1", - 8097, - SUCCESS, + .expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE, + .attach_type = BPF_CGROUP_INET_SOCK_CREATE, + .domain = AF_INET, + .type = SOCK_STREAM, + .ip = "127.0.0.1", + .port = 8097, + .result = SUCCESS, }, { - "attach type mismatch bind4 vs bind6", + .descr = "attach type mismatch bind4 vs bind6", .insns = { BPF_MOV64_IMM(BPF_REG_0, 1), BPF_EXIT_INSN(), }, - BPF_CGROUP_INET4_POST_BIND, - BPF_CGROUP_INET6_POST_BIND, - 0, - 0, - NULL, - 0, - ATTACH_REJECT, + .expected_attach_type = BPF_CGROUP_INET4_POST_BIND, + .attach_type = BPF_CGROUP_INET6_POST_BIND, + .result = ATTACH_REJECT, }, { - "attach type mismatch bind6 vs bind4", + .descr = "attach type mismatch bind6 vs bind4", .insns = { BPF_MOV64_IMM(BPF_REG_0, 1), BPF_EXIT_INSN(), }, - BPF_CGROUP_INET6_POST_BIND, - BPF_CGROUP_INET4_POST_BIND, - 0, - 0, - NULL, - 0, - ATTACH_REJECT, + .expected_attach_type = BPF_CGROUP_INET6_POST_BIND, + .attach_type = BPF_CGROUP_INET4_POST_BIND, + .result = ATTACH_REJECT, }, { - "attach type mismatch default vs bind4", + .descr = "attach type mismatch default vs bind4", .insns = { BPF_MOV64_IMM(BPF_REG_0, 1), BPF_EXIT_INSN(), }, - 0, - BPF_CGROUP_INET4_POST_BIND, - 0, - 0, - NULL, - 0, - ATTACH_REJECT, + .expected_attach_type = 0, + .attach_type = BPF_CGROUP_INET4_POST_BIND, + .result = ATTACH_REJECT, }, { - "attach type mismatch bind6 vs sock_create", + .descr = "attach type mismatch bind6 vs sock_create", .insns = { BPF_MOV64_IMM(BPF_REG_0, 1), BPF_EXIT_INSN(), }, - BPF_CGROUP_INET6_POST_BIND, - BPF_CGROUP_INET_SOCK_CREATE, - 0, - 0, - NULL, - 0, - ATTACH_REJECT, + .expected_attach_type = BPF_CGROUP_INET6_POST_BIND, + .attach_type = BPF_CGROUP_INET_SOCK_CREATE, + .result = ATTACH_REJECT, }, { - "bind4 reject all", + .descr = "bind4 reject all", .insns = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - BPF_CGROUP_INET4_POST_BIND, - BPF_CGROUP_INET4_POST_BIND, - AF_INET, - SOCK_STREAM, - "0.0.0.0", - 0, - BIND_REJECT, + .expected_attach_type = BPF_CGROUP_INET4_POST_BIND, + .attach_type = BPF_CGROUP_INET4_POST_BIND, + .domain = AF_INET, + .type = SOCK_STREAM, + .ip = "0.0.0.0", + .result = BIND_REJECT, }, { - "bind6 reject all", + .descr = "bind6 reject all", .insns = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - BPF_CGROUP_INET6_POST_BIND, - BPF_CGROUP_INET6_POST_BIND, - AF_INET6, - SOCK_STREAM, - "::", - 0, - BIND_REJECT, + .expected_attach_type = BPF_CGROUP_INET6_POST_BIND, + .attach_type = BPF_CGROUP_INET6_POST_BIND, + .domain = AF_INET6, + .type = SOCK_STREAM, + .ip = "::", + .result = BIND_REJECT, }, { - "bind6 deny specific IP & port", + .descr = "bind6 deny specific IP & port", .insns = { BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), @@ -247,16 +216,16 @@ static struct sock_test tests[] = { BPF_MOV64_IMM(BPF_REG_0, 1), BPF_EXIT_INSN(), }, - BPF_CGROUP_INET6_POST_BIND, - BPF_CGROUP_INET6_POST_BIND, - AF_INET6, - SOCK_STREAM, - "::1", - 8193, - BIND_REJECT, + .expected_attach_type = BPF_CGROUP_INET6_POST_BIND, + .attach_type = BPF_CGROUP_INET6_POST_BIND, + .domain = AF_INET6, + .type = SOCK_STREAM, + .ip = "::1", + .port = 8193, + .result = BIND_REJECT, }, { - "bind4 allow specific IP & port", + .descr = "bind4 allow specific IP & port", .insns = { BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), @@ -277,41 +246,132 @@ static struct sock_test tests[] = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - BPF_CGROUP_INET4_POST_BIND, - BPF_CGROUP_INET4_POST_BIND, - AF_INET, - SOCK_STREAM, - "127.0.0.1", - 4098, - SUCCESS, + .expected_attach_type = BPF_CGROUP_INET4_POST_BIND, + .attach_type = BPF_CGROUP_INET4_POST_BIND, + .domain = AF_INET, + .type = SOCK_STREAM, + .ip = "127.0.0.1", + .port = 4098, + .result = SUCCESS, }, { - "bind4 allow all", + .descr = "bind4 deny specific IP & port of TCP, and retry", + .insns = { + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + + /* if (ip == expected && port == expected) */ + BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6, + offsetof(struct bpf_sock, src_ip4)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_7, + __bpf_constant_ntohl(0x7F000001), 4), + BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6, + offsetof(struct bpf_sock, src_port)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 0x1002, 2), + + /* return DENY; */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_JMP_A(1), + + /* else return ALLOW; */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .expected_attach_type = BPF_CGROUP_INET4_POST_BIND, + .attach_type = BPF_CGROUP_INET4_POST_BIND, + .domain = AF_INET, + .type = SOCK_STREAM, + .ip = "127.0.0.1", + .port = 4098, + .port_retry = 5000, + .result = RETRY_SUCCESS, + }, + { + .descr = "bind4 deny specific IP & port of UDP, and retry", + .insns = { + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + + /* if (ip == expected && port == expected) */ + BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6, + offsetof(struct bpf_sock, src_ip4)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_7, + __bpf_constant_ntohl(0x7F000001), 4), + BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6, + offsetof(struct bpf_sock, src_port)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 0x1002, 2), + + /* return DENY; */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_JMP_A(1), + + /* else return ALLOW; */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .expected_attach_type = BPF_CGROUP_INET4_POST_BIND, + .attach_type = BPF_CGROUP_INET4_POST_BIND, + .domain = AF_INET, + .type = SOCK_DGRAM, + .ip = "127.0.0.1", + .port = 4098, + .port_retry = 5000, + .result = RETRY_SUCCESS, + }, + { + .descr = "bind6 deny specific IP & port, and retry", + .insns = { + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + + /* if (ip == expected && port == expected) */ + BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6, + offsetof(struct bpf_sock, src_ip6[3])), + BPF_JMP_IMM(BPF_JNE, BPF_REG_7, + __bpf_constant_ntohl(0x00000001), 4), + BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6, + offsetof(struct bpf_sock, src_port)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 0x2001, 2), + + /* return DENY; */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_JMP_A(1), + + /* else return ALLOW; */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .expected_attach_type = BPF_CGROUP_INET6_POST_BIND, + .attach_type = BPF_CGROUP_INET6_POST_BIND, + .domain = AF_INET6, + .type = SOCK_STREAM, + .ip = "::1", + .port = 8193, + .port_retry = 9000, + .result = RETRY_SUCCESS, + }, + { + .descr = "bind4 allow all", .insns = { BPF_MOV64_IMM(BPF_REG_0, 1), BPF_EXIT_INSN(), }, - BPF_CGROUP_INET4_POST_BIND, - BPF_CGROUP_INET4_POST_BIND, - AF_INET, - SOCK_STREAM, - "0.0.0.0", - 0, - SUCCESS, + .expected_attach_type = BPF_CGROUP_INET4_POST_BIND, + .attach_type = BPF_CGROUP_INET4_POST_BIND, + .domain = AF_INET, + .type = SOCK_STREAM, + .ip = "0.0.0.0", + .result = SUCCESS, }, { - "bind6 allow all", + .descr = "bind6 allow all", .insns = { BPF_MOV64_IMM(BPF_REG_0, 1), BPF_EXIT_INSN(), }, - BPF_CGROUP_INET6_POST_BIND, - BPF_CGROUP_INET6_POST_BIND, - AF_INET6, - SOCK_STREAM, - "::", - 0, - SUCCESS, + .expected_attach_type = BPF_CGROUP_INET6_POST_BIND, + .attach_type = BPF_CGROUP_INET6_POST_BIND, + .domain = AF_INET6, + .type = SOCK_STREAM, + .ip = "::", + .result = SUCCESS, }, }; @@ -328,18 +388,17 @@ static size_t probe_prog_length(const struct bpf_insn *fp) static int load_sock_prog(const struct bpf_insn *prog, enum bpf_attach_type attach_type) { - struct bpf_load_program_attr attr; - int ret; + LIBBPF_OPTS(bpf_prog_load_opts, opts); + int ret, insn_cnt; - memset(&attr, 0, sizeof(struct bpf_load_program_attr)); - attr.prog_type = BPF_PROG_TYPE_CGROUP_SOCK; - attr.expected_attach_type = attach_type; - attr.insns = prog; - attr.insns_cnt = probe_prog_length(attr.insns); - attr.license = "GPL"; - attr.log_level = 2; + insn_cnt = probe_prog_length(prog); - ret = bpf_load_program_xattr(&attr, bpf_log_buf, BPF_LOG_BUF_SIZE); + opts.expected_attach_type = attach_type; + opts.log_buf = bpf_log_buf; + opts.log_size = BPF_LOG_BUF_SIZE; + opts.log_level = 2; + + ret = bpf_prog_load(BPF_PROG_TYPE_CGROUP_SOCK, NULL, "GPL", prog, insn_cnt, &opts); if (verbose && ret < 0) fprintf(stderr, "%s\n", bpf_log_buf); @@ -352,14 +411,15 @@ static int attach_sock_prog(int cgfd, int progfd, return bpf_prog_attach(progfd, cgfd, attach_type, BPF_F_ALLOW_OVERRIDE); } -static int bind_sock(int domain, int type, const char *ip, unsigned short port) +static int bind_sock(int domain, int type, const char *ip, + unsigned short port, unsigned short port_retry) { struct sockaddr_storage addr; struct sockaddr_in6 *addr6; struct sockaddr_in *addr4; int sockfd = -1; socklen_t len; - int err = 0; + int res = SUCCESS; sockfd = socket(domain, type, 0); if (sockfd < 0) @@ -385,21 +445,44 @@ static int bind_sock(int domain, int type, const char *ip, unsigned short port) goto err; } - if (bind(sockfd, (const struct sockaddr *)&addr, len) == -1) - goto err; + if (bind(sockfd, (const struct sockaddr *)&addr, len) == -1) { + /* sys_bind() may fail for different reasons, errno has to be + * checked to confirm that BPF program rejected it. + */ + if (errno != EPERM) + goto err; + if (port_retry) + goto retry; + res = BIND_REJECT; + goto out; + } + goto out; +retry: + if (domain == AF_INET) + addr4->sin_port = htons(port_retry); + else + addr6->sin6_port = htons(port_retry); + if (bind(sockfd, (const struct sockaddr *)&addr, len) == -1) { + if (errno != EPERM) + goto err; + res = RETRY_REJECT; + } else { + res = RETRY_SUCCESS; + } goto out; err: - err = -1; + res = -1; out: close(sockfd); - return err; + return res; } static int run_test_case(int cgfd, const struct sock_test *test) { int progfd = -1; int err = 0; + int res; printf("Test case: %s .. ", test->descr); progfd = load_sock_prog(test->insns, test->expected_attach_type); @@ -417,21 +500,11 @@ static int run_test_case(int cgfd, const struct sock_test *test) goto err; } - if (bind_sock(test->domain, test->type, test->ip, test->port) == -1) { - /* sys_bind() may fail for different reasons, errno has to be - * checked to confirm that BPF program rejected it. - */ - if (test->result == BIND_REJECT && errno == EPERM) - goto out; - else - goto err; - } + res = bind_sock(test->domain, test->type, test->ip, test->port, + test->port_retry); + if (res > 0 && test->result == res) + goto out; - - if (test->result != SUCCESS) - goto err; - - goto out; err: err = -1; out: diff --git a/tools/testing/selftests/bpf/test_sock_addr.c b/tools/testing/selftests/bpf/test_sock_addr.c index aa3f185fcb..f0c8d05ba6 100644 --- a/tools/testing/selftests/bpf/test_sock_addr.c +++ b/tools/testing/selftests/bpf/test_sock_addr.c @@ -645,17 +645,14 @@ static int mk_sockaddr(int domain, const char *ip, unsigned short port, static int load_insns(const struct sock_addr_test *test, const struct bpf_insn *insns, size_t insns_cnt) { - struct bpf_load_program_attr load_attr; + LIBBPF_OPTS(bpf_prog_load_opts, opts); int ret; - memset(&load_attr, 0, sizeof(struct bpf_load_program_attr)); - load_attr.prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR; - load_attr.expected_attach_type = test->expected_attach_type; - load_attr.insns = insns; - load_attr.insns_cnt = insns_cnt; - load_attr.license = "GPL"; + opts.expected_attach_type = test->expected_attach_type; + opts.log_buf = bpf_log_buf; + opts.log_size = BPF_LOG_BUF_SIZE; - ret = bpf_load_program_xattr(&load_attr, bpf_log_buf, BPF_LOG_BUF_SIZE); + ret = bpf_prog_load(BPF_PROG_TYPE_CGROUP_SOCK_ADDR, NULL, "GPL", insns, insns_cnt, &opts); if (ret < 0 && test->expected_result != LOAD_REJECT) { log_err(">>> Loading program error.\n" ">>> Verifier output:\n%s\n-------\n", bpf_log_buf); @@ -666,23 +663,36 @@ static int load_insns(const struct sock_addr_test *test, static int load_path(const struct sock_addr_test *test, const char *path) { - struct bpf_prog_load_attr attr; struct bpf_object *obj; - int prog_fd; + struct bpf_program *prog; + int err; - memset(&attr, 0, sizeof(struct bpf_prog_load_attr)); - attr.file = path; - attr.prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR; - attr.expected_attach_type = test->expected_attach_type; - attr.prog_flags = BPF_F_TEST_RND_HI32; - - if (bpf_prog_load_xattr(&attr, &obj, &prog_fd)) { - if (test->expected_result != LOAD_REJECT) - log_err(">>> Loading program (%s) error.\n", path); + obj = bpf_object__open_file(path, NULL); + err = libbpf_get_error(obj); + if (err) { + log_err(">>> Opening BPF object (%s) error.\n", path); return -1; } - return prog_fd; + prog = bpf_object__next_program(obj, NULL); + if (!prog) + goto err_out; + + bpf_program__set_type(prog, BPF_PROG_TYPE_CGROUP_SOCK_ADDR); + bpf_program__set_expected_attach_type(prog, test->expected_attach_type); + bpf_program__set_flags(prog, BPF_F_TEST_RND_HI32); + + err = bpf_object__load(obj); + if (err) { + if (test->expected_result != LOAD_REJECT) + log_err(">>> Loading program (%s) error.\n", path); + goto err_out; + } + + return bpf_program__fd(prog); +err_out: + bpf_object__close(obj); + return -1; } static int bind4_prog_load(const struct sock_addr_test *test) diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c index eefd445b96..1ba7e7346a 100644 --- a/tools/testing/selftests/bpf/test_sockmap.c +++ b/tools/testing/selftests/bpf/test_sockmap.c @@ -139,6 +139,7 @@ struct sockmap_options { bool sendpage; bool data_test; bool drop_expected; + bool check_recved_len; int iov_count; int iov_length; int rate; @@ -556,8 +557,12 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt, int err, i, flags = MSG_NOSIGNAL; bool drop = opt->drop_expected; bool data = opt->data_test; + int iov_alloc_length = iov_length; - err = msg_alloc_iov(&msg, iov_count, iov_length, data, tx); + if (!tx && opt->check_recved_len) + iov_alloc_length *= 2; + + err = msg_alloc_iov(&msg, iov_count, iov_alloc_length, data, tx); if (err) goto out_errno; if (peek_flag) { @@ -665,6 +670,13 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt, s->bytes_recvd += recv; + if (opt->check_recved_len && s->bytes_recvd > total_bytes) { + errno = EMSGSIZE; + fprintf(stderr, "recv failed(), bytes_recvd:%zd, total_bytes:%f\n", + s->bytes_recvd, total_bytes); + goto out_errno; + } + if (data) { int chunk_sz = opt->sendpage ? iov_length * cnt : @@ -744,7 +756,8 @@ static int sendmsg_test(struct sockmap_options *opt) rxpid = fork(); if (rxpid == 0) { - iov_buf -= (txmsg_pop - txmsg_start_pop + 1); + if (txmsg_pop || txmsg_start_pop) + iov_buf -= (txmsg_pop - txmsg_start_pop + 1); if (opt->drop_expected || txmsg_ktls_skb_drop) _exit(0); @@ -1680,12 +1693,27 @@ static void test_txmsg_ingress_parser(int cgrp, struct sockmap_options *opt) { txmsg_pass = 1; skb_use_parser = 512; + if (ktls == 1) + skb_use_parser = 570; opt->iov_length = 256; opt->iov_count = 1; opt->rate = 2; test_exec(cgrp, opt); } +static void test_txmsg_ingress_parser2(int cgrp, struct sockmap_options *opt) +{ + if (ktls == 1) + return; + skb_use_parser = 10; + opt->iov_length = 20; + opt->iov_count = 1; + opt->rate = 1; + opt->check_recved_len = true; + test_exec(cgrp, opt); + opt->check_recved_len = false; +} + char *map_names[] = { "sock_map", "sock_map_txmsg", @@ -1784,7 +1812,8 @@ struct _test test[] = { {"txmsg test pull-data", test_txmsg_pull}, {"txmsg test pop-data", test_txmsg_pop}, {"txmsg test push/pop data", test_txmsg_push_pop}, - {"txmsg text ingress parser", test_txmsg_ingress_parser}, + {"txmsg test ingress parser", test_txmsg_ingress_parser}, + {"txmsg test ingress parser2", test_txmsg_ingress_parser2}, }; static int check_whitelist(struct _test *t, struct sockmap_options *opt) diff --git a/tools/testing/selftests/bpf/test_sysctl.c b/tools/testing/selftests/bpf/test_sysctl.c index a20a919244..4f6cf833b5 100644 --- a/tools/testing/selftests/bpf/test_sysctl.c +++ b/tools/testing/selftests/bpf/test_sysctl.c @@ -17,6 +17,7 @@ #include "bpf_rlimit.h" #include "bpf_util.h" #include "cgroup_helpers.h" +#include "testing_helpers.h" #define CG_PATH "/foo" #define MAX_INSNS 512 @@ -124,7 +125,7 @@ static struct sysctl_test tests[] = { .descr = "ctx:write sysctl:write read ok narrow", .insns = { /* u64 w = (u16)write & 1; */ -#if __BYTE_ORDER == __LITTLE_ENDIAN +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ BPF_LDX_MEM(BPF_H, BPF_REG_7, BPF_REG_1, offsetof(struct bpf_sysctl, write)), #else @@ -184,7 +185,7 @@ static struct sysctl_test tests[] = { .descr = "ctx:file_pos sysctl:read read ok narrow", .insns = { /* If (file_pos == X) */ -#if __BYTE_ORDER == __LITTLE_ENDIAN +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_1, offsetof(struct bpf_sysctl, file_pos)), #else @@ -1435,14 +1436,10 @@ static int load_sysctl_prog_insns(struct sysctl_test *test, const char *sysctl_path) { struct bpf_insn *prog = test->insns; - struct bpf_load_program_attr attr; - int ret; + LIBBPF_OPTS(bpf_prog_load_opts, opts); + int ret, insn_cnt; - memset(&attr, 0, sizeof(struct bpf_load_program_attr)); - attr.prog_type = BPF_PROG_TYPE_CGROUP_SYSCTL; - attr.insns = prog; - attr.insns_cnt = probe_prog_length(attr.insns); - attr.license = "GPL"; + insn_cnt = probe_prog_length(prog); if (test->fixup_value_insn) { char buf[128]; @@ -1465,7 +1462,10 @@ static int load_sysctl_prog_insns(struct sysctl_test *test, return -1; } - ret = bpf_load_program_xattr(&attr, bpf_log_buf, BPF_LOG_BUF_SIZE); + opts.log_buf = bpf_log_buf; + opts.log_size = BPF_LOG_BUF_SIZE; + + ret = bpf_prog_load(BPF_PROG_TYPE_CGROUP_SYSCTL, NULL, "GPL", prog, insn_cnt, &opts); if (ret < 0 && test->result != LOAD_REJECT) { log_err(">>> Loading program error.\n" ">>> Verifier output:\n%s\n-------\n", bpf_log_buf); @@ -1476,15 +1476,10 @@ static int load_sysctl_prog_insns(struct sysctl_test *test, static int load_sysctl_prog_file(struct sysctl_test *test) { - struct bpf_prog_load_attr attr; struct bpf_object *obj; int prog_fd; - memset(&attr, 0, sizeof(struct bpf_prog_load_attr)); - attr.file = test->prog_file; - attr.prog_type = BPF_PROG_TYPE_CGROUP_SYSCTL; - - if (bpf_prog_load_xattr(&attr, &obj, &prog_fd)) { + if (bpf_prog_test_load(test->prog_file, BPF_PROG_TYPE_CGROUP_SYSCTL, &obj, &prog_fd)) { if (test->result != LOAD_REJECT) log_err(">>> Loading program (%s) error.\n", test->prog_file); diff --git a/tools/testing/selftests/bpf/test_tag.c b/tools/testing/selftests/bpf/test_tag.c index 6272c784ca..0851c42ee3 100644 --- a/tools/testing/selftests/bpf/test_tag.c +++ b/tools/testing/selftests/bpf/test_tag.c @@ -21,6 +21,7 @@ #include "../../../include/linux/filter.h" #include "bpf_rlimit.h" +#include "testing_helpers.h" static struct bpf_insn prog[BPF_MAXINSNS]; @@ -57,7 +58,7 @@ static int bpf_try_load_prog(int insns, int fd_map, int fd_prog; bpf_filler(insns, fd_map); - fd_prog = bpf_load_program(BPF_PROG_TYPE_SCHED_CLS, prog, insns, "", 0, + fd_prog = bpf_test_load_program(BPF_PROG_TYPE_SCHED_CLS, prog, insns, "", 0, NULL, 0); assert(fd_prog > 0); if (fd_map > 0) @@ -184,11 +185,12 @@ static void do_test(uint32_t *tests, int start_insns, int fd_map, int main(void) { + LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = BPF_F_NO_PREALLOC); uint32_t tests = 0; int i, fd_map; - fd_map = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(int), - sizeof(int), 1, BPF_F_NO_PREALLOC); + fd_map = bpf_map_create(BPF_MAP_TYPE_HASH, NULL, sizeof(int), + sizeof(int), 1, &opts); assert(fd_map > 0); for (i = 0; i < 5; i++) { diff --git a/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh b/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh index 9b3617d770..6413c14725 100644 --- a/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh +++ b/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh @@ -76,8 +76,8 @@ DIR=$(dirname $0) TEST_IF=lo MAX_PING_TRIES=5 BPF_PROG_OBJ="${DIR}/test_tcp_check_syncookie_kern.o" -CLSACT_SECTION="clsact/check_syncookie" -XDP_SECTION="xdp/check_syncookie" +CLSACT_SECTION="tc" +XDP_SECTION="xdp" BPF_PROG_ID=0 PROG="${DIR}/test_tcp_check_syncookie_user" diff --git a/tools/testing/selftests/bpf/test_tcpnotify_user.c b/tools/testing/selftests/bpf/test_tcpnotify_user.c index 4a39304cc5..4c5114765b 100644 --- a/tools/testing/selftests/bpf/test_tcpnotify_user.c +++ b/tools/testing/selftests/bpf/test_tcpnotify_user.c @@ -25,6 +25,7 @@ #include "test_tcpnotify.h" #include "trace_helpers.h" +#include "testing_helpers.h" #define SOCKET_BUFFER_SIZE (getpagesize() < 8192L ? getpagesize() : 8192L) @@ -71,7 +72,6 @@ int main(int argc, char **argv) { const char *file = "test_tcpnotify_kern.o"; struct bpf_map *perf_map, *global_map; - struct perf_buffer_opts pb_opts = {}; struct tcpnotify_globals g = {0}; struct perf_buffer *pb = NULL; const char *cg_path = "/foo"; @@ -92,7 +92,7 @@ int main(int argc, char **argv) if (cg_fd < 0) goto err; - if (bpf_prog_load(file, BPF_PROG_TYPE_SOCK_OPS, &obj, &prog_fd)) { + if (bpf_prog_test_load(file, BPF_PROG_TYPE_SOCK_OPS, &obj, &prog_fd)) { printf("FAILED: load_bpf_file failed for: %s\n", file); goto err; } @@ -116,8 +116,7 @@ int main(int argc, char **argv) return -1; } - pb_opts.sample_cb = dummyfn; - pb = perf_buffer__new(bpf_map__fd(perf_map), 8, &pb_opts); + pb = perf_buffer__new(bpf_map__fd(perf_map), 8, dummyfn, NULL, NULL, NULL); if (!pb) goto err; diff --git a/tools/testing/selftests/bpf/test_tunnel.sh b/tools/testing/selftests/bpf/test_tunnel.sh index 1ccbe804e8..ca13729240 100644 --- a/tools/testing/selftests/bpf/test_tunnel.sh +++ b/tools/testing/selftests/bpf/test_tunnel.sh @@ -168,14 +168,15 @@ add_vxlan_tunnel() ip netns exec at_ns0 \ ip link set dev $DEV_NS address 52:54:00:d9:01:00 up ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 - ip netns exec at_ns0 arp -s 10.1.1.200 52:54:00:d9:02:00 + ip netns exec at_ns0 \ + ip neigh add 10.1.1.200 lladdr 52:54:00:d9:02:00 dev $DEV_NS ip netns exec at_ns0 iptables -A OUTPUT -j MARK --set-mark 0x800FF # root namespace ip link add dev $DEV type $TYPE external gbp dstport 4789 ip link set dev $DEV address 52:54:00:d9:02:00 up ip addr add dev $DEV 10.1.1.200/24 - arp -s 10.1.1.100 52:54:00:d9:01:00 + ip neigh add 10.1.1.100 lladdr 52:54:00:d9:01:00 dev $DEV } add_ip6vxlan_tunnel() diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 3a9e332c5e..76cd903117 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -41,16 +41,19 @@ # define CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS 1 # endif #endif -#include "bpf_rlimit.h" #include "bpf_rand.h" #include "bpf_util.h" #include "test_btf.h" #include "../../../include/linux/filter.h" +#ifndef ENOTSUPP +#define ENOTSUPP 524 +#endif + #define MAX_INSNS BPF_MAXINSNS #define MAX_TEST_INSNS 1000000 #define MAX_FIXUPS 8 -#define MAX_NR_MAPS 21 +#define MAX_NR_MAPS 22 #define MAX_TEST_RUNS 8 #define POINTER_VALUE 0xcafe4all #define TEST_DATA_LEN 64 @@ -88,6 +91,7 @@ struct bpf_test { int fixup_map_event_output[MAX_FIXUPS]; int fixup_map_reuseport_array[MAX_FIXUPS]; int fixup_map_ringbuf[MAX_FIXUPS]; + int fixup_map_timer[MAX_FIXUPS]; /* Expected verifier log output for result REJECT or VERBOSE_ACCEPT. * Can be a tab-separated sequence of expected strings. An empty string * means no log verification. @@ -457,11 +461,11 @@ static int __create_map(uint32_t type, uint32_t size_key, uint32_t size_value, uint32_t max_elem, uint32_t extra_flags) { + LIBBPF_OPTS(bpf_map_create_opts, opts); int fd; - fd = bpf_create_map(type, size_key, size_value, max_elem, - (type == BPF_MAP_TYPE_HASH ? - BPF_F_NO_PREALLOC : 0) | extra_flags); + opts.map_flags = (type == BPF_MAP_TYPE_HASH ? BPF_F_NO_PREALLOC : 0) | extra_flags; + fd = bpf_map_create(type, NULL, size_key, size_value, max_elem, &opts); if (fd < 0) { if (skip_unsupported_map(type)) return -1; @@ -494,8 +498,7 @@ static int create_prog_dummy_simple(enum bpf_prog_type prog_type, int ret) BPF_EXIT_INSN(), }; - return bpf_load_program(prog_type, prog, - ARRAY_SIZE(prog), "GPL", 0, NULL, 0); + return bpf_prog_load(prog_type, NULL, "GPL", prog, ARRAY_SIZE(prog), NULL); } static int create_prog_dummy_loop(enum bpf_prog_type prog_type, int mfd, @@ -510,8 +513,7 @@ static int create_prog_dummy_loop(enum bpf_prog_type prog_type, int mfd, BPF_EXIT_INSN(), }; - return bpf_load_program(prog_type, prog, - ARRAY_SIZE(prog), "GPL", 0, NULL, 0); + return bpf_prog_load(prog_type, NULL, "GPL", prog, ARRAY_SIZE(prog), NULL); } static int create_prog_array(enum bpf_prog_type prog_type, uint32_t max_elem, @@ -519,8 +521,8 @@ static int create_prog_array(enum bpf_prog_type prog_type, uint32_t max_elem, { int mfd, p1fd, p2fd, p3fd; - mfd = bpf_create_map(BPF_MAP_TYPE_PROG_ARRAY, sizeof(int), - sizeof(int), max_elem, 0); + mfd = bpf_map_create(BPF_MAP_TYPE_PROG_ARRAY, NULL, sizeof(int), + sizeof(int), max_elem, NULL); if (mfd < 0) { if (skip_unsupported_map(BPF_MAP_TYPE_PROG_ARRAY)) return -1; @@ -550,10 +552,11 @@ static int create_prog_array(enum bpf_prog_type prog_type, uint32_t max_elem, static int create_map_in_map(void) { + LIBBPF_OPTS(bpf_map_create_opts, opts); int inner_map_fd, outer_map_fd; - inner_map_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, sizeof(int), - sizeof(int), 1, 0); + inner_map_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, sizeof(int), + sizeof(int), 1, NULL); if (inner_map_fd < 0) { if (skip_unsupported_map(BPF_MAP_TYPE_ARRAY)) return -1; @@ -561,8 +564,9 @@ static int create_map_in_map(void) return inner_map_fd; } - outer_map_fd = bpf_create_map_in_map(BPF_MAP_TYPE_ARRAY_OF_MAPS, NULL, - sizeof(int), inner_map_fd, 1, 0); + opts.inner_map_fd = inner_map_fd; + outer_map_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY_OF_MAPS, NULL, + sizeof(int), sizeof(int), 1, &opts); if (outer_map_fd < 0) { if (skip_unsupported_map(BPF_MAP_TYPE_ARRAY_OF_MAPS)) return -1; @@ -581,8 +585,8 @@ static int create_cgroup_storage(bool percpu) BPF_MAP_TYPE_CGROUP_STORAGE; int fd; - fd = bpf_create_map(type, sizeof(struct bpf_cgroup_storage_key), - TEST_DATA_LEN, 0, 0); + fd = bpf_map_create(type, NULL, sizeof(struct bpf_cgroup_storage_key), + TEST_DATA_LEN, 0, NULL); if (fd < 0) { if (skip_unsupported_map(type)) return -1; @@ -600,8 +604,15 @@ static int create_cgroup_storage(bool percpu) * int cnt; * struct bpf_spin_lock l; * }; + * struct bpf_timer { + * __u64 :64; + * __u64 :64; + * } __attribute__((aligned(8))); + * struct timer { + * struct bpf_timer t; + * }; */ -static const char btf_str_sec[] = "\0bpf_spin_lock\0val\0cnt\0l"; +static const char btf_str_sec[] = "\0bpf_spin_lock\0val\0cnt\0l\0bpf_timer\0timer\0t"; static __u32 btf_raw_types[] = { /* int */ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ @@ -612,6 +623,11 @@ static __u32 btf_raw_types[] = { BTF_TYPE_ENC(15, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), 8), BTF_MEMBER_ENC(19, 1, 0), /* int cnt; */ BTF_MEMBER_ENC(23, 2, 32),/* struct bpf_spin_lock l; */ + /* struct bpf_timer */ /* [4] */ + BTF_TYPE_ENC(25, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 0), 16), + /* struct timer */ /* [5] */ + BTF_TYPE_ENC(35, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 1), 16), + BTF_MEMBER_ENC(41, 4, 0), /* struct bpf_timer t; */ }; static int load_btf(void) @@ -637,7 +653,7 @@ static int load_btf(void) memcpy(ptr, btf_str_sec, hdr.str_len); ptr += hdr.str_len; - btf_fd = bpf_load_btf(raw_btf, ptr - raw_btf, 0, 0, 0); + btf_fd = bpf_btf_load(raw_btf, ptr - raw_btf, NULL); free(raw_btf); if (btf_fd < 0) return -1; @@ -646,22 +662,17 @@ static int load_btf(void) static int create_map_spin_lock(void) { - struct bpf_create_map_attr attr = { - .name = "test_map", - .map_type = BPF_MAP_TYPE_ARRAY, - .key_size = 4, - .value_size = 8, - .max_entries = 1, + LIBBPF_OPTS(bpf_map_create_opts, opts, .btf_key_type_id = 1, .btf_value_type_id = 3, - }; + ); int fd, btf_fd; btf_fd = load_btf(); if (btf_fd < 0) return -1; - attr.btf_fd = btf_fd; - fd = bpf_create_map_xattr(&attr); + opts.btf_fd = btf_fd; + fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, "test_map", 4, 8, 1, &opts); if (fd < 0) printf("Failed to create map with spin_lock\n"); return fd; @@ -669,29 +680,43 @@ static int create_map_spin_lock(void) static int create_sk_storage_map(void) { - struct bpf_create_map_attr attr = { - .name = "test_map", - .map_type = BPF_MAP_TYPE_SK_STORAGE, - .key_size = 4, - .value_size = 8, - .max_entries = 0, + LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = BPF_F_NO_PREALLOC, .btf_key_type_id = 1, .btf_value_type_id = 3, - }; + ); int fd, btf_fd; btf_fd = load_btf(); if (btf_fd < 0) return -1; - attr.btf_fd = btf_fd; - fd = bpf_create_map_xattr(&attr); - close(attr.btf_fd); + opts.btf_fd = btf_fd; + fd = bpf_map_create(BPF_MAP_TYPE_SK_STORAGE, "test_map", 4, 8, 0, &opts); + close(opts.btf_fd); if (fd < 0) printf("Failed to create sk_storage_map\n"); return fd; } +static int create_map_timer(void) +{ + LIBBPF_OPTS(bpf_map_create_opts, opts, + .btf_key_type_id = 1, + .btf_value_type_id = 5, + ); + int fd, btf_fd; + + btf_fd = load_btf(); + if (btf_fd < 0) + return -1; + + opts.btf_fd = btf_fd; + fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, "test_map", 4, 16, 1, &opts); + if (fd < 0) + printf("Failed to create map with timer\n"); + return fd; +} + static char bpf_vlog[UINT_MAX >> 8]; static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, @@ -718,6 +743,7 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, int *fixup_map_event_output = test->fixup_map_event_output; int *fixup_map_reuseport_array = test->fixup_map_reuseport_array; int *fixup_map_ringbuf = test->fixup_map_ringbuf; + int *fixup_map_timer = test->fixup_map_timer; if (test->fill_helper) { test->fill_insns = calloc(MAX_TEST_INSNS, sizeof(struct bpf_insn)); @@ -903,6 +929,13 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, fixup_map_ringbuf++; } while (*fixup_map_ringbuf); } + if (*fixup_map_timer) { + map_fds[21] = create_map_timer(); + do { + prog[*fixup_map_timer].imm = map_fds[21]; + fixup_map_timer++; + } while (*fixup_map_timer); + } } struct libcap { @@ -974,7 +1007,7 @@ static int do_prog_test_run(int fd_prog, bool unpriv, uint32_t expected_val, if (err) { switch (saved_errno) { - case 524/*ENOTSUPP*/: + case ENOTSUPP: printf("Did not run the program (not supported) "); return 0; case EPERM: @@ -1041,7 +1074,7 @@ static void do_test_single(struct bpf_test *test, bool unpriv, int fd_prog, expected_ret, alignment_prevented_execution; int prog_len, prog_type = test->prog_type; struct bpf_insn *prog = test->insns; - struct bpf_load_program_attr attr; + LIBBPF_OPTS(bpf_prog_load_opts, opts); int run_errs, run_successes; int map_fds[MAX_NR_MAPS]; const char *expected_err; @@ -1081,32 +1114,34 @@ static void do_test_single(struct bpf_test *test, bool unpriv, test->result_unpriv : test->result; expected_err = unpriv && test->errstr_unpriv ? test->errstr_unpriv : test->errstr; - memset(&attr, 0, sizeof(attr)); - attr.prog_type = prog_type; - attr.expected_attach_type = test->expected_attach_type; - attr.insns = prog; - attr.insns_cnt = prog_len; - attr.license = "GPL"; + + opts.expected_attach_type = test->expected_attach_type; if (verbose) - attr.log_level = 1; + opts.log_level = 1; else if (expected_ret == VERBOSE_ACCEPT) - attr.log_level = 2; + opts.log_level = 2; else - attr.log_level = 4; - attr.prog_flags = pflags; + opts.log_level = 4; + opts.prog_flags = pflags; if (prog_type == BPF_PROG_TYPE_TRACING && test->kfunc) { - attr.attach_btf_id = libbpf_find_vmlinux_btf_id(test->kfunc, - attr.expected_attach_type); - if (attr.attach_btf_id < 0) { + int attach_btf_id; + + attach_btf_id = libbpf_find_vmlinux_btf_id(test->kfunc, + opts.expected_attach_type); + if (attach_btf_id < 0) { printf("FAIL\nFailed to find BTF ID for '%s'!\n", test->kfunc); (*errors)++; return; } + + opts.attach_btf_id = attach_btf_id; } - fd_prog = bpf_load_program_xattr(&attr, bpf_vlog, sizeof(bpf_vlog)); + opts.log_buf = bpf_vlog; + opts.log_size = sizeof(bpf_vlog); + fd_prog = bpf_prog_load(prog_type, NULL, "GPL", prog, prog_len, &opts); saved_errno = errno; /* BPF_PROG_TYPE_TRACING requires more setup and @@ -1119,6 +1154,12 @@ static void do_test_single(struct bpf_test *test, bool unpriv, goto close_fds; } + if (fd_prog < 0 && saved_errno == ENOTSUPP) { + printf("SKIP (program uses an unsupported feature)\n"); + skips++; + goto close_fds; + } + alignment_prevented_execution = 0; if (expected_ret == ACCEPT || expected_ret == VERBOSE_ACCEPT) { @@ -1353,6 +1394,9 @@ int main(int argc, char **argv) return EXIT_FAILURE; } + /* Use libbpf 1.0 API mode */ + libbpf_set_strict_mode(LIBBPF_STRICT_ALL); + bpf_semi_rand_init(); return do_test(unpriv, from, to); } diff --git a/tools/testing/selftests/bpf/test_xdp_meta.sh b/tools/testing/selftests/bpf/test_xdp_meta.sh index 637fcf4fe4..d10cefd6eb 100644 --- a/tools/testing/selftests/bpf/test_xdp_meta.sh +++ b/tools/testing/selftests/bpf/test_xdp_meta.sh @@ -1,5 +1,8 @@ #!/bin/sh +# Kselftest framework requirement - SKIP code is 4. +readonly KSFT_SKIP=4 + cleanup() { if [ "$?" = "0" ]; then @@ -17,7 +20,7 @@ cleanup() ip link set dev lo xdp off 2>/dev/null > /dev/null if [ $? -ne 0 ];then echo "selftests: [SKIP] Could not run test without the ip xdp support" - exit 0 + exit $KSFT_SKIP fi set -e diff --git a/tools/testing/selftests/bpf/test_xdp_redirect.sh b/tools/testing/selftests/bpf/test_xdp_redirect.sh index c033850886..57c8db9972 100644 --- a/tools/testing/selftests/bpf/test_xdp_redirect.sh +++ b/tools/testing/selftests/bpf/test_xdp_redirect.sh @@ -52,8 +52,8 @@ test_xdp_redirect() return 0 fi - ip -n ns1 link set veth11 $xdpmode obj xdp_dummy.o sec xdp_dummy &> /dev/null - ip -n ns2 link set veth22 $xdpmode obj xdp_dummy.o sec xdp_dummy &> /dev/null + ip -n ns1 link set veth11 $xdpmode obj xdp_dummy.o sec xdp &> /dev/null + ip -n ns2 link set veth22 $xdpmode obj xdp_dummy.o sec xdp &> /dev/null ip link set dev veth1 $xdpmode obj test_xdp_redirect.o sec redirect_to_222 &> /dev/null ip link set dev veth2 $xdpmode obj test_xdp_redirect.o sec redirect_to_111 &> /dev/null diff --git a/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh b/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh index bedff7aa70..05f8727409 100644 --- a/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh +++ b/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh @@ -92,7 +92,7 @@ setup_ns() # Add a neigh entry for IPv4 ping test ip -n ns$i neigh add 192.0.2.253 lladdr 00:00:00:00:00:01 dev veth0 ip -n ns$i link set veth0 $mode obj \ - xdp_dummy.o sec xdp_dummy &> /dev/null || \ + xdp_dummy.o sec xdp &> /dev/null || \ { test_fail "Unable to load dummy xdp" && exit 1; } IFACES="$IFACES veth$i" veth_mac[$i]=$(ip -n ns0 link show veth$i | awk '/link\/ether/ {print $2}') diff --git a/tools/testing/selftests/bpf/test_xdp_veth.sh b/tools/testing/selftests/bpf/test_xdp_veth.sh index 995278e684..a3a1eaee26 100644 --- a/tools/testing/selftests/bpf/test_xdp_veth.sh +++ b/tools/testing/selftests/bpf/test_xdp_veth.sh @@ -107,9 +107,9 @@ ip link set dev veth1 xdp pinned $BPF_DIR/progs/redirect_map_0 ip link set dev veth2 xdp pinned $BPF_DIR/progs/redirect_map_1 ip link set dev veth3 xdp pinned $BPF_DIR/progs/redirect_map_2 -ip -n ns1 link set dev veth11 xdp obj xdp_dummy.o sec xdp_dummy +ip -n ns1 link set dev veth11 xdp obj xdp_dummy.o sec xdp ip -n ns2 link set dev veth22 xdp obj xdp_tx.o sec xdp -ip -n ns3 link set dev veth33 xdp obj xdp_dummy.o sec xdp_dummy +ip -n ns3 link set dev veth33 xdp obj xdp_dummy.o sec xdp trap cleanup EXIT diff --git a/tools/testing/selftests/bpf/test_xdp_vlan.sh b/tools/testing/selftests/bpf/test_xdp_vlan.sh index bb8b0da916..0cbc7604a2 100644 --- a/tools/testing/selftests/bpf/test_xdp_vlan.sh +++ b/tools/testing/selftests/bpf/test_xdp_vlan.sh @@ -2,6 +2,9 @@ # SPDX-License-Identifier: GPL-2.0 # Author: Jesper Dangaard Brouer +# Kselftest framework requirement - SKIP code is 4. +readonly KSFT_SKIP=4 + # Allow wrapper scripts to name test if [ -z "$TESTNAME" ]; then TESTNAME=xdp_vlan @@ -94,7 +97,7 @@ while true; do -h | --help ) usage; echo "selftests: $TESTNAME [SKIP] usage help info requested" - exit 0 + exit $KSFT_SKIP ;; * ) shift @@ -117,7 +120,7 @@ fi ip link set dev lo xdpgeneric off 2>/dev/null > /dev/null if [ $? -ne 0 ]; then echo "selftests: $TESTNAME [SKIP] need ip xdp support" - exit 0 + exit $KSFT_SKIP fi # Interactive mode likely require us to cleanup netns diff --git a/tools/testing/selftests/bpf/testing_helpers.c b/tools/testing/selftests/bpf/testing_helpers.c index 800d503e5c..795b6798cc 100644 --- a/tools/testing/selftests/bpf/testing_helpers.c +++ b/tools/testing/selftests/bpf/testing_helpers.c @@ -1,7 +1,11 @@ // SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +/* Copyright (C) 2019 Netronome Systems, Inc. */ /* Copyright (C) 2020 Facebook, Inc. */ #include +#include #include +#include +#include #include "testing_helpers.h" int parse_num_list(const char *s, bool **num_set, int *num_set_len) @@ -78,3 +82,61 @@ __u32 link_info_prog_id(const struct bpf_link *link, struct bpf_link_info *info) } return info->prog_id; } + +int extra_prog_load_log_flags = 0; + +int bpf_prog_test_load(const char *file, enum bpf_prog_type type, + struct bpf_object **pobj, int *prog_fd) +{ + LIBBPF_OPTS(bpf_object_open_opts, opts, + .kernel_log_level = extra_prog_load_log_flags, + ); + struct bpf_object *obj; + struct bpf_program *prog; + __u32 flags; + int err; + + obj = bpf_object__open_file(file, &opts); + if (!obj) + return -errno; + + prog = bpf_object__next_program(obj, NULL); + if (!prog) { + err = -ENOENT; + goto err_out; + } + + if (type != BPF_PROG_TYPE_UNSPEC) + bpf_program__set_type(prog, type); + + flags = bpf_program__flags(prog) | BPF_F_TEST_RND_HI32; + bpf_program__set_flags(prog, flags); + + err = bpf_object__load(obj); + if (err) + goto err_out; + + *pobj = obj; + *prog_fd = bpf_program__fd(prog); + + return 0; +err_out: + bpf_object__close(obj); + return err; +} + +int bpf_test_load_program(enum bpf_prog_type type, const struct bpf_insn *insns, + size_t insns_cnt, const char *license, + __u32 kern_version, char *log_buf, + size_t log_buf_sz) +{ + LIBBPF_OPTS(bpf_prog_load_opts, opts, + .kern_version = kern_version, + .prog_flags = BPF_F_TEST_RND_HI32, + .log_level = extra_prog_load_log_flags, + .log_buf = log_buf, + .log_size = log_buf_sz, + ); + + return bpf_prog_load(type, NULL, license, insns, insns_cnt, &opts); +} diff --git a/tools/testing/selftests/bpf/testing_helpers.h b/tools/testing/selftests/bpf/testing_helpers.h index d4f8e74961..f46ebc476e 100644 --- a/tools/testing/selftests/bpf/testing_helpers.h +++ b/tools/testing/selftests/bpf/testing_helpers.h @@ -6,3 +6,9 @@ int parse_num_list(const char *s, bool **set, int *set_len); __u32 link_info_prog_id(const struct bpf_link *link, struct bpf_link_info *info); +int bpf_prog_test_load(const char *file, enum bpf_prog_type type, + struct bpf_object **pobj, int *prog_fd); +int bpf_test_load_program(enum bpf_prog_type type, const struct bpf_insn *insns, + size_t insns_cnt, const char *license, + __u32 kern_version, char *log_buf, + size_t log_buf_sz); diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c index e7a19b04d4..7b7f918eda 100644 --- a/tools/testing/selftests/bpf/trace_helpers.c +++ b/tools/testing/selftests/bpf/trace_helpers.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 +#include #include #include #include diff --git a/tools/testing/selftests/bpf/verifier/atomic_cmpxchg.c b/tools/testing/selftests/bpf/verifier/atomic_cmpxchg.c index 6fb52d8cfd..b39665f335 100644 --- a/tools/testing/selftests/bpf/verifier/atomic_cmpxchg.c +++ b/tools/testing/selftests/bpf/verifier/atomic_cmpxchg.c @@ -71,8 +71,6 @@ BPF_EXIT_INSN(), }, .result = ACCEPT, - .result_unpriv = REJECT, - .errstr_unpriv = "R0 leaks addr into mem", }, { "Can't use cmpxchg on uninit src reg", @@ -120,6 +118,46 @@ BPF_EXIT_INSN(), }, .result = ACCEPT, +}, +{ + "Dest pointer in r0 - fail", + .insns = { + /* val = 0; */ + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + /* r0 = &val */ + BPF_MOV64_REG(BPF_REG_0, BPF_REG_10), + /* r0 = atomic_cmpxchg(&val, r0, 1); */ + BPF_MOV64_IMM(BPF_REG_1, 1), + BPF_ATOMIC_OP(BPF_DW, BPF_CMPXCHG, BPF_REG_10, BPF_REG_1, -8), + /* if (r0 != 0) exit(1); */ + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + /* exit(0); */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .result_unpriv = REJECT, + .errstr_unpriv = "R0 leaks addr into mem", +}, +{ + "Dest pointer in r0 - succeed", + .insns = { + /* r0 = &val */ + BPF_MOV64_REG(BPF_REG_0, BPF_REG_10), + /* val = r0; */ + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8), + /* r0 = atomic_cmpxchg(&val, r0, 0); */ + BPF_MOV64_IMM(BPF_REG_1, 0), + BPF_ATOMIC_OP(BPF_DW, BPF_CMPXCHG, BPF_REG_10, BPF_REG_1, -8), + /* r1 = *r0 */ + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, -8), + /* exit(0); */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, .result_unpriv = REJECT, .errstr_unpriv = "R0 leaks addr into mem", }, diff --git a/tools/testing/selftests/bpf/verifier/calls.c b/tools/testing/selftests/bpf/verifier/calls.c index 336a749673..d7b74eb283 100644 --- a/tools/testing/selftests/bpf/verifier/calls.c +++ b/tools/testing/selftests/bpf/verifier/calls.c @@ -1,3 +1,26 @@ +{ + "calls: invalid kfunc call not eliminated", + .insns = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .result = REJECT, + .errstr = "invalid kernel function call not eliminated in verifier pass", +}, +{ + "calls: invalid kfunc call unreachable", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_JMP_IMM(BPF_JGT, BPF_REG_0, 0, 2), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .result = ACCEPT, +}, { "calls: basic sanity", .insns = { diff --git a/tools/testing/selftests/bpf/verifier/ctx_sk_lookup.c b/tools/testing/selftests/bpf/verifier/ctx_sk_lookup.c index d78627be06..a2b006e2fd 100644 --- a/tools/testing/selftests/bpf/verifier/ctx_sk_lookup.c +++ b/tools/testing/selftests/bpf/verifier/ctx_sk_lookup.c @@ -229,6 +229,24 @@ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, offsetof(struct bpf_sk_lookup, local_port)), + /* 1-byte read from ingress_ifindex field */ + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, ingress_ifindex)), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, ingress_ifindex) + 1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, ingress_ifindex) + 2), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, ingress_ifindex) + 3), + /* 2-byte read from ingress_ifindex field */ + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, ingress_ifindex)), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, ingress_ifindex) + 2), + /* 4-byte read from ingress_ifindex field */ + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, ingress_ifindex)), + /* 8-byte read from sk field */ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, offsetof(struct bpf_sk_lookup, sk)), @@ -351,6 +369,20 @@ .expected_attach_type = BPF_SK_LOOKUP, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, +{ + "invalid 8-byte read from bpf_sk_lookup ingress_ifindex field", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, ingress_ifindex)), + BPF_MOV32_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SK_LOOKUP, + .expected_attach_type = BPF_SK_LOOKUP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, /* invalid 1,2,4-byte reads from 8-byte fields in bpf_sk_lookup */ { "invalid 4-byte read from bpf_sk_lookup sk field", diff --git a/tools/testing/selftests/bpf/verifier/ctx_skb.c b/tools/testing/selftests/bpf/verifier/ctx_skb.c index 2022c0f2cd..83cecfbd67 100644 --- a/tools/testing/selftests/bpf/verifier/ctx_skb.c +++ b/tools/testing/selftests/bpf/verifier/ctx_skb.c @@ -502,7 +502,7 @@ "check skb->hash byte load permitted", .insns = { BPF_MOV64_IMM(BPF_REG_0, 0), -#if __BYTE_ORDER == __LITTLE_ENDIAN +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, offsetof(struct __sk_buff, hash)), #else @@ -537,7 +537,7 @@ "check skb->hash byte load permitted 3", .insns = { BPF_MOV64_IMM(BPF_REG_0, 0), -#if __BYTE_ORDER == __LITTLE_ENDIAN +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, offsetof(struct __sk_buff, hash) + 3), #else @@ -646,7 +646,7 @@ "check skb->hash half load permitted", .insns = { BPF_MOV64_IMM(BPF_REG_0, 0), -#if __BYTE_ORDER == __LITTLE_ENDIAN +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, offsetof(struct __sk_buff, hash)), #else @@ -661,7 +661,7 @@ "check skb->hash half load permitted 2", .insns = { BPF_MOV64_IMM(BPF_REG_0, 0), -#if __BYTE_ORDER == __LITTLE_ENDIAN +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, offsetof(struct __sk_buff, hash) + 2), #else @@ -676,7 +676,7 @@ "check skb->hash half load not permitted, unaligned 1", .insns = { BPF_MOV64_IMM(BPF_REG_0, 0), -#if __BYTE_ORDER == __LITTLE_ENDIAN +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, offsetof(struct __sk_buff, hash) + 1), #else @@ -693,7 +693,7 @@ "check skb->hash half load not permitted, unaligned 3", .insns = { BPF_MOV64_IMM(BPF_REG_0, 0), -#if __BYTE_ORDER == __LITTLE_ENDIAN +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, offsetof(struct __sk_buff, hash) + 3), #else @@ -951,7 +951,7 @@ "check skb->data half load not permitted", .insns = { BPF_MOV64_IMM(BPF_REG_0, 0), -#if __BYTE_ORDER == __LITTLE_ENDIAN +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, offsetof(struct __sk_buff, data)), #else @@ -1057,6 +1057,66 @@ .result = ACCEPT, .prog_type = BPF_PROG_TYPE_SCHED_CLS, }, +{ + "padding after gso_size is not accessible", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetofend(struct __sk_buff, gso_size)), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .result_unpriv = REJECT, + .errstr = "invalid bpf_context access off=180 size=4", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, +}, +{ + "read hwtstamp from CGROUP_SKB", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, hwtstamp)), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, +}, +{ + "read hwtstamp from CGROUP_SKB", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, + offsetof(struct __sk_buff, hwtstamp)), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, +}, +{ + "write hwtstamp from CGROUP_SKB", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, hwtstamp)), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .result_unpriv = REJECT, + .errstr = "invalid bpf_context access off=184 size=8", + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, +}, +{ + "read hwtstamp from CLS", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, hwtstamp)), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, +}, { "check wire_len is not readable by sockets", .insns = { diff --git a/tools/testing/selftests/bpf/verifier/jit.c b/tools/testing/selftests/bpf/verifier/jit.c index df215e0045..79021c30e5 100644 --- a/tools/testing/selftests/bpf/verifier/jit.c +++ b/tools/testing/selftests/bpf/verifier/jit.c @@ -62,6 +62,11 @@ BPF_JMP_REG(BPF_JEQ, BPF_REG_3, BPF_REG_2, 2), BPF_MOV64_IMM(BPF_REG_0, 1), BPF_EXIT_INSN(), + BPF_LD_IMM64(BPF_REG_3, 0xfefefeULL), + BPF_ALU64_IMM(BPF_MUL, BPF_REG_3, 0xefefef), + BPF_JMP_REG(BPF_JEQ, BPF_REG_3, BPF_REG_2, 2), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), BPF_MOV32_REG(BPF_REG_2, BPF_REG_2), BPF_LD_IMM64(BPF_REG_0, 0xfefefeULL), BPF_ALU32_REG(BPF_MUL, BPF_REG_0, BPF_REG_1), @@ -73,11 +78,69 @@ BPF_JMP_REG(BPF_JEQ, BPF_REG_3, BPF_REG_2, 2), BPF_MOV64_IMM(BPF_REG_0, 1), BPF_EXIT_INSN(), + BPF_LD_IMM64(BPF_REG_3, 0xfefefeULL), + BPF_ALU32_IMM(BPF_MUL, BPF_REG_3, 0xefefef), + BPF_JMP_REG(BPF_JEQ, BPF_REG_3, BPF_REG_2, 2), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + BPF_LD_IMM64(BPF_REG_0, 0xfefefeULL), + BPF_LD_IMM64(BPF_REG_2, 0x2ad4d4aaULL), + BPF_ALU32_IMM(BPF_MUL, BPF_REG_0, 0x2b), + BPF_JMP_REG(BPF_JEQ, BPF_REG_0, BPF_REG_2, 2), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), BPF_LD_IMM64(BPF_REG_0, 0x952a7bbcULL), BPF_LD_IMM64(BPF_REG_1, 0xfefefeULL), - BPF_LD_IMM64(BPF_REG_2, 0xeeff0d413122ULL), - BPF_ALU32_REG(BPF_MUL, BPF_REG_2, BPF_REG_1), - BPF_JMP_REG(BPF_JEQ, BPF_REG_2, BPF_REG_0, 2), + BPF_LD_IMM64(BPF_REG_5, 0xeeff0d413122ULL), + BPF_ALU32_REG(BPF_MUL, BPF_REG_5, BPF_REG_1), + BPF_JMP_REG(BPF_JEQ, BPF_REG_5, BPF_REG_0, 2), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_0, 2), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .retval = 2, +}, +{ + "jit: various div tests", + .insns = { + BPF_LD_IMM64(BPF_REG_2, 0xefeffeULL), + BPF_LD_IMM64(BPF_REG_0, 0xeeff0d413122ULL), + BPF_LD_IMM64(BPF_REG_1, 0xfefeeeULL), + BPF_ALU64_REG(BPF_DIV, BPF_REG_0, BPF_REG_1), + BPF_JMP_REG(BPF_JEQ, BPF_REG_0, BPF_REG_2, 2), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + BPF_LD_IMM64(BPF_REG_3, 0xeeff0d413122ULL), + BPF_ALU64_IMM(BPF_DIV, BPF_REG_3, 0xfefeeeULL), + BPF_JMP_REG(BPF_JEQ, BPF_REG_3, BPF_REG_2, 2), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + BPF_LD_IMM64(BPF_REG_2, 0xaa93ULL), + BPF_ALU64_IMM(BPF_MOD, BPF_REG_1, 0xbeefULL), + BPF_JMP_REG(BPF_JEQ, BPF_REG_1, BPF_REG_2, 2), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + BPF_LD_IMM64(BPF_REG_1, 0xfefeeeULL), + BPF_LD_IMM64(BPF_REG_3, 0xbeefULL), + BPF_ALU64_REG(BPF_MOD, BPF_REG_1, BPF_REG_3), + BPF_JMP_REG(BPF_JEQ, BPF_REG_1, BPF_REG_2, 2), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + BPF_LD_IMM64(BPF_REG_2, 0x5ee1dULL), + BPF_LD_IMM64(BPF_REG_1, 0xfefeeeULL), + BPF_LD_IMM64(BPF_REG_3, 0x2bULL), + BPF_ALU32_REG(BPF_DIV, BPF_REG_1, BPF_REG_3), + BPF_JMP_REG(BPF_JEQ, BPF_REG_1, BPF_REG_2, 2), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + BPF_ALU32_REG(BPF_DIV, BPF_REG_1, BPF_REG_1), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 1, 2), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + BPF_ALU64_REG(BPF_MOD, BPF_REG_2, BPF_REG_2), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_2, 0, 2), BPF_MOV64_IMM(BPF_REG_0, 1), BPF_EXIT_INSN(), BPF_MOV64_IMM(BPF_REG_0, 2), diff --git a/tools/testing/selftests/bpf/verifier/lwt.c b/tools/testing/selftests/bpf/verifier/lwt.c index 2cab6a3966..5c8944d0b0 100644 --- a/tools/testing/selftests/bpf/verifier/lwt.c +++ b/tools/testing/selftests/bpf/verifier/lwt.c @@ -174,7 +174,7 @@ "check skb->tc_classid half load not permitted for lwt prog", .insns = { BPF_MOV64_IMM(BPF_REG_0, 0), -#if __BYTE_ORDER == __LITTLE_ENDIAN +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, offsetof(struct __sk_buff, tc_classid)), #else diff --git a/tools/testing/selftests/bpf/verifier/map_in_map.c b/tools/testing/selftests/bpf/verifier/map_in_map.c index 2798927ee9..128a348b76 100644 --- a/tools/testing/selftests/bpf/verifier/map_in_map.c +++ b/tools/testing/selftests/bpf/verifier/map_in_map.c @@ -18,6 +18,40 @@ .fixup_map_in_map = { 3 }, .result = ACCEPT, }, +{ + "map in map state pruning", + .insns = { + BPF_ST_MEM(0, BPF_REG_10, -4, 0), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -4), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_6), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_6), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 11), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_6), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_6), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_in_map = { 4, 14 }, + .flags = BPF_F_TEST_STATE_FREQ, + .result = VERBOSE_ACCEPT, + .errstr = "processed 25 insns", + .prog_type = BPF_PROG_TYPE_XDP, +}, { "invalid inner map pointer", .insns = { diff --git a/tools/testing/selftests/bpf/verifier/perf_event_sample_period.c b/tools/testing/selftests/bpf/verifier/perf_event_sample_period.c index 471c1a5950..d8a9b1a1f9 100644 --- a/tools/testing/selftests/bpf/verifier/perf_event_sample_period.c +++ b/tools/testing/selftests/bpf/verifier/perf_event_sample_period.c @@ -2,7 +2,7 @@ "check bpf_perf_event_data->sample_period byte load permitted", .insns = { BPF_MOV64_IMM(BPF_REG_0, 0), -#if __BYTE_ORDER == __LITTLE_ENDIAN +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, offsetof(struct bpf_perf_event_data, sample_period)), #else @@ -18,7 +18,7 @@ "check bpf_perf_event_data->sample_period half load permitted", .insns = { BPF_MOV64_IMM(BPF_REG_0, 0), -#if __BYTE_ORDER == __LITTLE_ENDIAN +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, offsetof(struct bpf_perf_event_data, sample_period)), #else @@ -34,7 +34,7 @@ "check bpf_perf_event_data->sample_period word load permitted", .insns = { BPF_MOV64_IMM(BPF_REG_0, 0), -#if __BYTE_ORDER == __LITTLE_ENDIAN +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, offsetof(struct bpf_perf_event_data, sample_period)), #else diff --git a/tools/testing/selftests/bpf/verifier/search_pruning.c b/tools/testing/selftests/bpf/verifier/search_pruning.c index 7e50cb8087..682519769f 100644 --- a/tools/testing/selftests/bpf/verifier/search_pruning.c +++ b/tools/testing/selftests/bpf/verifier/search_pruning.c @@ -132,6 +132,77 @@ .result = REJECT, .prog_type = BPF_PROG_TYPE_TRACEPOINT, }, +{ + "precision tracking for u32 spill/fill", + .insns = { + BPF_MOV64_REG(BPF_REG_7, BPF_REG_1), + BPF_EMIT_CALL(BPF_FUNC_get_prandom_u32), + BPF_MOV32_IMM(BPF_REG_6, 32), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), + BPF_MOV32_IMM(BPF_REG_6, 4), + /* Additional insns to introduce a pruning point. */ + BPF_EMIT_CALL(BPF_FUNC_get_prandom_u32), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), + BPF_MOV64_IMM(BPF_REG_3, 0), + /* u32 spill/fill */ + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_6, -8), + BPF_LDX_MEM(BPF_W, BPF_REG_8, BPF_REG_10, -8), + /* out-of-bound map value access for r6=32 */ + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -16), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_8), + BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_hash_8b = { 15 }, + .result = REJECT, + .errstr = "R0 min value is outside of the allowed memory range", + .prog_type = BPF_PROG_TYPE_TRACEPOINT, +}, +{ + "precision tracking for u32 spills, u64 fill", + .insns = { + BPF_EMIT_CALL(BPF_FUNC_get_prandom_u32), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + BPF_MOV32_IMM(BPF_REG_7, 0xffffffff), + /* Additional insns to introduce a pruning point. */ + BPF_MOV64_IMM(BPF_REG_3, 1), + BPF_MOV64_IMM(BPF_REG_3, 1), + BPF_MOV64_IMM(BPF_REG_3, 1), + BPF_MOV64_IMM(BPF_REG_3, 1), + BPF_EMIT_CALL(BPF_FUNC_get_prandom_u32), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), + BPF_MOV64_IMM(BPF_REG_3, 1), + BPF_ALU32_IMM(BPF_DIV, BPF_REG_3, 0), + /* u32 spills, u64 fill */ + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_6, -4), + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_7, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_8, BPF_REG_10, -8), + /* if r8 != X goto pc+1 r8 known in fallthrough branch */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_8, 0xffffffff, 1), + BPF_MOV64_IMM(BPF_REG_3, 1), + /* if r8 == X goto pc+1 condition always true on first + * traversal, so starts backtracking to mark r8 as requiring + * precision. r7 marked as needing precision. r6 not marked + * since it's not tracked. + */ + BPF_JMP_IMM(BPF_JEQ, BPF_REG_8, 0xffffffff, 1), + /* fails if r8 correctly marked unknown after fill. */ + BPF_ALU32_IMM(BPF_DIV, BPF_REG_3, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "div by zero", + .prog_type = BPF_PROG_TYPE_TRACEPOINT, +}, { "allocated_stack", .insns = { diff --git a/tools/testing/selftests/bpf/verifier/spill_fill.c b/tools/testing/selftests/bpf/verifier/spill_fill.c index 0b943897aa..8cfc5349d2 100644 --- a/tools/testing/selftests/bpf/verifier/spill_fill.c +++ b/tools/testing/selftests/bpf/verifier/spill_fill.c @@ -58,6 +58,34 @@ .result = ACCEPT, .result_unpriv = ACCEPT, }, +{ + "check with invalid reg offset 0", + .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), + /* add invalid offset to memory or NULL */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1), + /* check whether the reservation was successful */ + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + /* should not be able to access *(R7) = 0 */ + BPF_ST_MEM(BPF_W, BPF_REG_6, 0, 0), + /* submit the reserved ringbuf memory */ + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + 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 = "R0 pointer arithmetic on alloc_mem_or_null prohibited", +}, { "check corrupted spill/fill", .insns = { @@ -104,3 +132,213 @@ .result = ACCEPT, .retval = POINTER_VALUE, }, +{ + "Spill and refill a u32 const scalar. Offset to skb->data", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + /* r4 = 20 */ + BPF_MOV32_IMM(BPF_REG_4, 20), + /* *(u32 *)(r10 -8) = r4 */ + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_4, -8), + /* r4 = *(u32 *)(r10 -8) */ + BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_10, -8), + /* r0 = r2 */ + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + /* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=inv20 */ + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_4), + /* if (r0 > r3) R0=pkt,off=20 R2=pkt R3=pkt_end R4=inv20 */ + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1), + /* r0 = *(u32 *)r2 R0=pkt,off=20,r=20 R2=pkt,r=20 R3=pkt_end R4=inv20 */ + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, +}, +{ + "Spill a u32 const, refill from another half of the uninit u32 from the stack", + .insns = { + /* r4 = 20 */ + BPF_MOV32_IMM(BPF_REG_4, 20), + /* *(u32 *)(r10 -8) = r4 */ + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_4, -8), + /* r4 = *(u32 *)(r10 -4) fp-8=????rrrr*/ + BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_10, -4), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid read from stack off -4+0 size 4", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, +}, +{ + "Spill a u32 const scalar. Refill as u16. Offset to skb->data", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + /* r4 = 20 */ + BPF_MOV32_IMM(BPF_REG_4, 20), + /* *(u32 *)(r10 -8) = r4 */ + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_4, -8), + /* r4 = *(u16 *)(r10 -8) */ + BPF_LDX_MEM(BPF_H, BPF_REG_4, BPF_REG_10, -8), + /* r0 = r2 */ + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + /* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=inv,umax=65535 */ + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_4), + /* if (r0 > r3) R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=inv,umax=65535 */ + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1), + /* r0 = *(u32 *)r2 R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=inv20 */ + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid access to packet", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, +}, +{ + "Spill u32 const scalars. Refill as u64. Offset to skb->data", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + /* r6 = 0 */ + BPF_MOV32_IMM(BPF_REG_6, 0), + /* r7 = 20 */ + BPF_MOV32_IMM(BPF_REG_7, 20), + /* *(u32 *)(r10 -4) = r6 */ + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_6, -4), + /* *(u32 *)(r10 -8) = r7 */ + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_7, -8), + /* r4 = *(u64 *)(r10 -8) */ + BPF_LDX_MEM(BPF_H, BPF_REG_4, BPF_REG_10, -8), + /* r0 = r2 */ + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + /* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=inv,umax=65535 */ + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_4), + /* if (r0 > r3) R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=inv,umax=65535 */ + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1), + /* r0 = *(u32 *)r2 R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=inv20 */ + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid access to packet", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, +}, +{ + "Spill a u32 const scalar. Refill as u16 from fp-6. Offset to skb->data", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + /* r4 = 20 */ + BPF_MOV32_IMM(BPF_REG_4, 20), + /* *(u32 *)(r10 -8) = r4 */ + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_4, -8), + /* r4 = *(u16 *)(r10 -6) */ + BPF_LDX_MEM(BPF_H, BPF_REG_4, BPF_REG_10, -6), + /* r0 = r2 */ + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + /* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=inv,umax=65535 */ + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_4), + /* if (r0 > r3) R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=inv,umax=65535 */ + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1), + /* r0 = *(u32 *)r2 R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=inv20 */ + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid access to packet", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, +}, +{ + "Spill and refill a u32 const scalar at non 8byte aligned stack addr. Offset to skb->data", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + /* r4 = 20 */ + BPF_MOV32_IMM(BPF_REG_4, 20), + /* *(u32 *)(r10 -8) = r4 */ + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_4, -8), + /* *(u32 *)(r10 -4) = r4 */ + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_4, -4), + /* r4 = *(u32 *)(r10 -4), */ + BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_10, -4), + /* r0 = r2 */ + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + /* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=inv,umax=U32_MAX */ + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_4), + /* if (r0 > r3) R0=pkt,umax=U32_MAX R2=pkt R3=pkt_end R4=inv */ + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1), + /* r0 = *(u32 *)r2 R0=pkt,umax=U32_MAX R2=pkt R3=pkt_end R4=inv */ + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid access to packet", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, +}, +{ + "Spill and refill a umax=40 bounded scalar. Offset to skb->data", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_1, + offsetof(struct __sk_buff, tstamp)), + BPF_JMP_IMM(BPF_JLE, BPF_REG_4, 40, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + /* *(u32 *)(r10 -8) = r4 R4=inv,umax=40 */ + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_4, -8), + /* r4 = (*u32 *)(r10 - 8) */ + BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_10, -8), + /* r2 += r4 R2=pkt R4=inv,umax=40 */ + BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_4), + /* r0 = r2 R2=pkt,umax=40 R4=inv,umax=40 */ + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + /* r2 += 20 R0=pkt,umax=40 R2=pkt,umax=40 */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 20), + /* if (r2 > r3) R0=pkt,umax=40 R2=pkt,off=20,umax=40 */ + BPF_JMP_REG(BPF_JGT, BPF_REG_2, BPF_REG_3, 1), + /* r0 = *(u32 *)r0 R0=pkt,r=20,umax=40 R2=pkt,off=20,r=20,umax=40 */ + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, +}, +{ + "Spill a u32 scalar at fp-4 and then at fp-8", + .insns = { + /* r4 = 4321 */ + BPF_MOV32_IMM(BPF_REG_4, 4321), + /* *(u32 *)(r10 -4) = r4 */ + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_4, -4), + /* *(u32 *)(r10 -8) = r4 */ + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_4, -8), + /* r4 = *(u64 *)(r10 -8) */ + BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_10, -8), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, +}, diff --git a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c index 4d347bc53a..359f3e8f8b 100644 --- a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c +++ b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c @@ -1078,7 +1078,7 @@ .errstr_unpriv = "R0 pointer -= pointer prohibited", }, { - "map access: trying to leak tained dst reg", + "map access: trying to leak tainted dst reg", .insns = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), diff --git a/tools/testing/selftests/bpf/vmtest.sh b/tools/testing/selftests/bpf/vmtest.sh index 8889b3f552..b3afd43549 100644 --- a/tools/testing/selftests/bpf/vmtest.sh +++ b/tools/testing/selftests/bpf/vmtest.sh @@ -4,18 +4,35 @@ set -u set -e -# This script currently only works for x86_64, as -# it is based on the VM image used by the BPF CI which is -# x86_64. -QEMU_BINARY="${QEMU_BINARY:="qemu-system-x86_64"}" -X86_BZIMAGE="arch/x86/boot/bzImage" +# This script currently only works for x86_64 and s390x, as +# it is based on the VM image used by the BPF CI, which is +# available only for these architectures. +ARCH="$(uname -m)" +case "${ARCH}" in +s390x) + QEMU_BINARY=qemu-system-s390x + QEMU_CONSOLE="ttyS1" + QEMU_FLAGS=(-smp 2) + BZIMAGE="arch/s390/boot/compressed/vmlinux" + ;; +x86_64) + QEMU_BINARY=qemu-system-x86_64 + QEMU_CONSOLE="ttyS0,115200" + QEMU_FLAGS=(-cpu host -smp 8) + BZIMAGE="arch/x86/boot/bzImage" + ;; +*) + echo "Unsupported architecture" + exit 1 + ;; +esac DEFAULT_COMMAND="./test_progs" MOUNT_DIR="mnt" ROOTFS_IMAGE="root.img" OUTPUT_DIR="$HOME/.bpf_selftests" -KCONFIG_URL="https://raw.githubusercontent.com/libbpf/libbpf/master/travis-ci/vmtest/configs/latest.config" -KCONFIG_API_URL="https://api.github.com/repos/libbpf/libbpf/contents/travis-ci/vmtest/configs/latest.config" -INDEX_URL="https://raw.githubusercontent.com/libbpf/libbpf/master/travis-ci/vmtest/configs/INDEX" +KCONFIG_URL="https://raw.githubusercontent.com/libbpf/libbpf/master/travis-ci/vmtest/configs/config-latest.${ARCH}" +KCONFIG_API_URL="https://api.github.com/repos/libbpf/libbpf/contents/travis-ci/vmtest/configs/config-latest.${ARCH}" +INDEX_URL="https://raw.githubusercontent.com/libbpf/ci/master/INDEX" NUM_COMPILE_JOBS="$(nproc)" LOG_FILE_BASE="$(date +"bpf_selftests.%Y-%m-%d_%H-%M-%S")" LOG_FILE="${LOG_FILE_BASE}.log" @@ -85,7 +102,7 @@ newest_rootfs_version() { { for file in "${!URLS[@]}"; do - if [[ $file =~ ^libbpf-vmtest-rootfs-(.*)\.tar\.zst$ ]]; then + if [[ $file =~ ^"${ARCH}"/libbpf-vmtest-rootfs-(.*)\.tar\.zst$ ]]; then echo "${BASH_REMATCH[1]}" fi done @@ -102,7 +119,7 @@ download_rootfs() exit 1 fi - download "libbpf-vmtest-rootfs-$rootfsversion.tar.zst" | + download "${ARCH}/libbpf-vmtest-rootfs-$rootfsversion.tar.zst" | zstd -d | sudo tar -C "$dir" -x } @@ -224,13 +241,12 @@ EOF -nodefaults \ -display none \ -serial mon:stdio \ - -cpu kvm64 \ + "${qemu_flags[@]}" \ -enable-kvm \ - -smp 4 \ - -m 2G \ + -m 4G \ -drive file="${rootfs_img}",format=raw,index=1,media=disk,if=virtio,cache=none \ -kernel "${kernel_bzimage}" \ - -append "root=/dev/vda rw console=ttyS0,115200" + -append "root=/dev/vda rw console=${QEMU_CONSOLE}" } copy_logs() @@ -282,7 +298,7 @@ main() local kernel_checkout=$(realpath "${script_dir}"/../../../../) # By default the script searches for the kernel in the checkout directory but # it also obeys environment variables O= and KBUILD_OUTPUT= - local kernel_bzimage="${kernel_checkout}/${X86_BZIMAGE}" + local kernel_bzimage="${kernel_checkout}/${BZIMAGE}" local command="${DEFAULT_COMMAND}" local update_image="no" local exit_command="poweroff -f" @@ -337,13 +353,13 @@ main() if is_rel_path "${O}"; then O="$(realpath "${PWD}/${O}")" fi - kernel_bzimage="${O}/${X86_BZIMAGE}" + kernel_bzimage="${O}/${BZIMAGE}" make_command="${make_command} O=${O}" elif [[ "${KBUILD_OUTPUT:=""}" != "" ]]; then if is_rel_path "${KBUILD_OUTPUT}"; then KBUILD_OUTPUT="$(realpath "${PWD}/${KBUILD_OUTPUT}")" fi - kernel_bzimage="${KBUILD_OUTPUT}/${X86_BZIMAGE}" + kernel_bzimage="${KBUILD_OUTPUT}/${BZIMAGE}" make_command="${make_command} KBUILD_OUTPUT=${KBUILD_OUTPUT}" fi diff --git a/tools/testing/selftests/bpf/xdp_redirect_multi.c b/tools/testing/selftests/bpf/xdp_redirect_multi.c index f5ffba341c..51c8224b4c 100644 --- a/tools/testing/selftests/bpf/xdp_redirect_multi.c +++ b/tools/testing/selftests/bpf/xdp_redirect_multi.c @@ -85,10 +85,7 @@ int main(int argc, char **argv) { int prog_fd, group_all, mac_map; struct bpf_program *ingress_prog, *egress_prog; - struct bpf_prog_load_attr prog_load_attr = { - .prog_type = BPF_PROG_TYPE_UNSPEC, - }; - int i, ret, opt, egress_prog_fd = 0; + int i, err, ret, opt, egress_prog_fd = 0; struct bpf_devmap_val devmap_val; bool attach_egress_prog = false; unsigned char mac_addr[6]; @@ -147,10 +144,14 @@ int main(int argc, char **argv) printf("\n"); snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); - prog_load_attr.file = filename; - - if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd)) + obj = bpf_object__open_file(filename, NULL); + err = libbpf_get_error(obj); + if (err) goto err_out; + err = bpf_object__load(obj); + if (err) + goto err_out; + prog_fd = bpf_program__fd(bpf_object__next_program(obj, NULL)); if (attach_egress_prog) group_all = bpf_object__find_map_fd_by_name(obj, "map_egress"); diff --git a/tools/testing/selftests/bpf/xdping.c b/tools/testing/selftests/bpf/xdping.c index 842d9155d3..baa870a759 100644 --- a/tools/testing/selftests/bpf/xdping.c +++ b/tools/testing/selftests/bpf/xdping.c @@ -22,6 +22,7 @@ #include "bpf/libbpf.h" #include "xdping.h" +#include "testing_helpers.h" static int ifindex; static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST; @@ -173,14 +174,13 @@ int main(int argc, char **argv) snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); - if (bpf_prog_load(filename, BPF_PROG_TYPE_XDP, &obj, &prog_fd)) { + if (bpf_prog_test_load(filename, BPF_PROG_TYPE_XDP, &obj, &prog_fd)) { fprintf(stderr, "load of %s failed\n", filename); return 1; } - main_prog = bpf_object__find_program_by_title(obj, - server ? "xdpserver" : - "xdpclient"); + main_prog = bpf_object__find_program_by_name(obj, + server ? "xdping_server" : "xdping_client"); if (main_prog) prog_fd = bpf_program__fd(main_prog); if (!main_prog || prog_fd < 0) { @@ -188,7 +188,7 @@ int main(int argc, char **argv) return 1; } - map = bpf_map__next(NULL, obj); + map = bpf_object__next_map(obj, NULL); if (map) map_fd = bpf_map__fd(map); if (!map || map_fd < 0) { diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c index f53ce2683f..0a5d23da48 100644 --- a/tools/testing/selftests/bpf/xdpxceiver.c +++ b/tools/testing/selftests/bpf/xdpxceiver.c @@ -19,7 +19,7 @@ * Virtual Ethernet interfaces. * * For each mode, the following tests are run: - * a. nopoll - soft-irq processing + * a. nopoll - soft-irq processing in run-to-completion mode * b. poll - using poll() syscall * c. Socket Teardown * Create a Tx and a Rx socket, Tx from one socket, Rx on another. Destroy @@ -45,6 +45,10 @@ * Configure sockets at indexes 0 and 1, run a traffic on queue ids 0, * then remove xsk sockets from queue 0 on both veth interfaces and * finally run a traffic on queues ids 1 + * g. unaligned mode + * h. tests for invalid and corner case Tx descriptors so that the correct ones + * are discarded and let through, respectively. + * i. 2K frame size tests * * Total tests: 12 * @@ -96,6 +100,12 @@ #include "xdpxceiver.h" #include "../kselftest.h" +/* AF_XDP APIs were moved into libxdp and marked as deprecated in libbpf. + * Until xdpxceiver is either moved or re-writed into libxdp, suppress + * deprecation warnings in this file + */ +#pragma GCC diagnostic ignored "-Wdeprecated-declarations" + static const char *MAC1 = "\x00\x0A\x56\x9E\xEE\x62"; static const char *MAC2 = "\x00\x0A\x56\x9E\xEE\x61"; static const char *IP1 = "192.168.100.162"; @@ -112,13 +122,10 @@ static void __exit_with_error(int error, const char *file, const char *func, int #define exit_with_error(error) __exit_with_error(error, __FILE__, __func__, __LINE__) -#define print_ksft_result(void)\ - (ksft_test_result_pass("PASS: %s %s %s%s%s%s\n", configured_mode ? "DRV" : "SKB",\ - test_type == TEST_TYPE_POLL ? "POLL" : "NOPOLL",\ - test_type == TEST_TYPE_TEARDOWN ? "Socket Teardown" : "",\ - test_type == TEST_TYPE_BIDI ? "Bi-directional Sockets" : "",\ - test_type == TEST_TYPE_STATS ? "Stats" : "",\ - test_type == TEST_TYPE_BPF_RES ? "BPF RES" : "")) +#define mode_string(test) (test)->ifobj_tx->xdp_flags & XDP_FLAGS_SKB_MODE ? "SKB" : "DRV" + +#define print_ksft_result(test) \ + (ksft_test_result_pass("PASS: %s %s\n", mode_string(test), (test)->name)) static void memset32_htonl(void *dest, u32 val, u32 size) { @@ -235,80 +242,46 @@ static void gen_udp_csum(struct udphdr *udp_hdr, struct iphdr *ip_hdr) udp_csum(ip_hdr->saddr, ip_hdr->daddr, UDP_PKT_SIZE, IPPROTO_UDP, (u16 *)udp_hdr); } -static void xsk_configure_umem(struct ifobject *data, void *buffer, u64 size, int idx) +static int xsk_configure_umem(struct xsk_umem_info *umem, void *buffer, u64 size) { struct xsk_umem_config cfg = { .fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS, .comp_size = XSK_RING_CONS__DEFAULT_NUM_DESCS, - .frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE, - .frame_headroom = frame_headroom, + .frame_size = umem->frame_size, + .frame_headroom = umem->frame_headroom, .flags = XSK_UMEM__DEFAULT_FLAGS }; - struct xsk_umem_info *umem; int ret; - umem = calloc(1, sizeof(struct xsk_umem_info)); - if (!umem) - exit_with_error(errno); + if (umem->unaligned_mode) + cfg.flags |= XDP_UMEM_UNALIGNED_CHUNK_FLAG; ret = xsk_umem__create(&umem->umem, buffer, size, &umem->fq, &umem->cq, &cfg); if (ret) - exit_with_error(-ret); + return ret; umem->buffer = buffer; - - data->umem_arr[idx] = umem; + return 0; } -static void xsk_populate_fill_ring(struct xsk_umem_info *umem) -{ - int ret, i; - u32 idx = 0; - - ret = xsk_ring_prod__reserve(&umem->fq, XSK_RING_PROD__DEFAULT_NUM_DESCS, &idx); - if (ret != XSK_RING_PROD__DEFAULT_NUM_DESCS) - exit_with_error(-ret); - for (i = 0; i < XSK_RING_PROD__DEFAULT_NUM_DESCS; i++) - *xsk_ring_prod__fill_addr(&umem->fq, idx++) = i * XSK_UMEM__DEFAULT_FRAME_SIZE; - xsk_ring_prod__submit(&umem->fq, XSK_RING_PROD__DEFAULT_NUM_DESCS); -} - -static int xsk_configure_socket(struct ifobject *ifobject, int idx) +static int xsk_configure_socket(struct xsk_socket_info *xsk, struct xsk_umem_info *umem, + struct ifobject *ifobject, u32 qid) { struct xsk_socket_config cfg; - struct xsk_socket_info *xsk; struct xsk_ring_cons *rxr; struct xsk_ring_prod *txr; - int ret; - xsk = calloc(1, sizeof(struct xsk_socket_info)); - if (!xsk) - exit_with_error(errno); - - xsk->umem = ifobject->umem; - cfg.rx_size = rxqsize; + xsk->umem = umem; + cfg.rx_size = xsk->rxqsize; cfg.tx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS; cfg.libbpf_flags = 0; - cfg.xdp_flags = xdp_flags; - cfg.bind_flags = xdp_bind_flags; + cfg.xdp_flags = ifobject->xdp_flags; + cfg.bind_flags = ifobject->bind_flags; - if (test_type != TEST_TYPE_BIDI) { - rxr = (ifobject->fv.vector == rx) ? &xsk->rx : NULL; - txr = (ifobject->fv.vector == tx) ? &xsk->tx : NULL; - } else { - rxr = &xsk->rx; - txr = &xsk->tx; - } - - ret = xsk_socket__create(&xsk->xsk, ifobject->ifname, idx, - ifobject->umem->umem, rxr, txr, &cfg); - if (ret) - return 1; - - ifobject->xsk_arr[idx] = xsk; - - return 0; + txr = ifobject->tx_on ? &xsk->tx : NULL; + rxr = ifobject->rx_on ? &xsk->rx : NULL; + return xsk_socket__create(&xsk->xsk, ifobject->ifname, qid, umem->umem, rxr, txr, &cfg); } static struct option long_options[] = { @@ -354,45 +327,44 @@ static int switch_namespace(const char *nsname) return nsfd; } -static int validate_interfaces(void) +static bool validate_interface(struct ifobject *ifobj) { - bool ret = true; - - for (int i = 0; i < MAX_INTERFACES; i++) { - if (!strcmp(ifdict[i]->ifname, "")) { - ret = false; - ksft_test_result_fail("ERROR: interfaces: -i , -i ,."); - } - } - return ret; + if (!strcmp(ifobj->ifname, "")) + return false; + return true; } -static void parse_command_line(int argc, char **argv) +static void parse_command_line(struct ifobject *ifobj_tx, struct ifobject *ifobj_rx, int argc, + char **argv) { - int option_index, interface_index = 0, c; + struct ifobject *ifobj; + u32 interface_nb = 0; + int option_index, c; opterr = 0; for (;;) { - c = getopt_long(argc, argv, "i:Dv", long_options, &option_index); + char *sptr, *token; + c = getopt_long(argc, argv, "i:Dv", long_options, &option_index); if (c == -1) break; switch (c) { case 'i': - if (interface_index == MAX_INTERFACES) + if (interface_nb == 0) + ifobj = ifobj_tx; + else if (interface_nb == 1) + ifobj = ifobj_rx; + else break; - char *sptr, *token; sptr = strndupa(optarg, strlen(optarg)); - memcpy(ifdict[interface_index]->ifname, - strsep(&sptr, ","), MAX_INTERFACE_NAME_CHARS); + memcpy(ifobj->ifname, strsep(&sptr, ","), MAX_INTERFACE_NAME_CHARS); token = strsep(&sptr, ","); if (token) - memcpy(ifdict[interface_index]->nsname, token, - MAX_INTERFACES_NAMESPACE_CHARS); - interface_index++; + memcpy(ifobj->nsname, token, MAX_INTERFACES_NAMESPACE_CHARS); + interface_nb++; break; case 'D': opt_pkt_dump = true; @@ -405,11 +377,85 @@ static void parse_command_line(int argc, char **argv) ksft_exit_xfail(); } } +} - if (!validate_interfaces()) { - usage(basename(argv[0])); - ksft_exit_xfail(); +static void __test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx, + struct ifobject *ifobj_rx) +{ + u32 i, j; + + for (i = 0; i < MAX_INTERFACES; i++) { + struct ifobject *ifobj = i ? ifobj_rx : ifobj_tx; + + ifobj->umem = &ifobj->umem_arr[0]; + ifobj->xsk = &ifobj->xsk_arr[0]; + ifobj->use_poll = false; + ifobj->pacing_on = true; + ifobj->pkt_stream = test->pkt_stream_default; + + if (i == 0) { + ifobj->rx_on = false; + ifobj->tx_on = true; + } else { + ifobj->rx_on = true; + ifobj->tx_on = false; + } + + for (j = 0; j < MAX_SOCKETS; j++) { + memset(&ifobj->umem_arr[j], 0, sizeof(ifobj->umem_arr[j])); + memset(&ifobj->xsk_arr[j], 0, sizeof(ifobj->xsk_arr[j])); + ifobj->umem_arr[j].num_frames = DEFAULT_UMEM_BUFFERS; + ifobj->umem_arr[j].frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE; + ifobj->xsk_arr[j].rxqsize = XSK_RING_CONS__DEFAULT_NUM_DESCS; + } } + + test->ifobj_tx = ifobj_tx; + test->ifobj_rx = ifobj_rx; + test->current_step = 0; + test->total_steps = 1; + test->nb_sockets = 1; +} + +static void test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx, + struct ifobject *ifobj_rx, enum test_mode mode) +{ + struct pkt_stream *pkt_stream; + u32 i; + + pkt_stream = test->pkt_stream_default; + memset(test, 0, sizeof(*test)); + test->pkt_stream_default = pkt_stream; + + for (i = 0; i < MAX_INTERFACES; i++) { + struct ifobject *ifobj = i ? ifobj_rx : ifobj_tx; + + ifobj->xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST; + if (mode == TEST_MODE_SKB) + ifobj->xdp_flags |= XDP_FLAGS_SKB_MODE; + else + ifobj->xdp_flags |= XDP_FLAGS_DRV_MODE; + + ifobj->bind_flags = XDP_USE_NEED_WAKEUP | XDP_COPY; + } + + __test_spec_init(test, ifobj_tx, ifobj_rx); +} + +static void test_spec_reset(struct test_spec *test) +{ + __test_spec_init(test, test->ifobj_tx, test->ifobj_rx); +} + +static void test_spec_set_name(struct test_spec *test, const char *name) +{ + strncpy(test->name, name, MAX_TEST_NAME_SIZE); +} + +static void pkt_stream_reset(struct pkt_stream *pkt_stream) +{ + if (pkt_stream) + pkt_stream->rx_pkt_nb = 0; } static struct pkt *pkt_stream_get_pkt(struct pkt_stream *pkt_stream, u32 pkt_nb) @@ -420,29 +466,104 @@ static struct pkt *pkt_stream_get_pkt(struct pkt_stream *pkt_stream, u32 pkt_nb) return &pkt_stream->pkts[pkt_nb]; } -static struct pkt_stream *pkt_stream_generate(u32 nb_pkts, u32 pkt_len) +static struct pkt *pkt_stream_get_next_rx_pkt(struct pkt_stream *pkt_stream) +{ + while (pkt_stream->rx_pkt_nb < pkt_stream->nb_pkts) { + if (pkt_stream->pkts[pkt_stream->rx_pkt_nb].valid) + return &pkt_stream->pkts[pkt_stream->rx_pkt_nb++]; + pkt_stream->rx_pkt_nb++; + } + return NULL; +} + +static void pkt_stream_delete(struct pkt_stream *pkt_stream) +{ + free(pkt_stream->pkts); + free(pkt_stream); +} + +static void pkt_stream_restore_default(struct test_spec *test) +{ + if (test->ifobj_tx->pkt_stream != test->pkt_stream_default) { + pkt_stream_delete(test->ifobj_tx->pkt_stream); + test->ifobj_tx->pkt_stream = test->pkt_stream_default; + } + test->ifobj_rx->pkt_stream = test->pkt_stream_default; +} + +static struct pkt_stream *__pkt_stream_alloc(u32 nb_pkts) +{ + struct pkt_stream *pkt_stream; + + pkt_stream = calloc(1, sizeof(*pkt_stream)); + if (!pkt_stream) + return NULL; + + pkt_stream->pkts = calloc(nb_pkts, sizeof(*pkt_stream->pkts)); + if (!pkt_stream->pkts) { + free(pkt_stream); + return NULL; + } + + pkt_stream->nb_pkts = nb_pkts; + return pkt_stream; +} + +static struct pkt_stream *pkt_stream_generate(struct xsk_umem_info *umem, u32 nb_pkts, u32 pkt_len) { struct pkt_stream *pkt_stream; u32 i; - pkt_stream = malloc(sizeof(*pkt_stream)); + pkt_stream = __pkt_stream_alloc(nb_pkts); if (!pkt_stream) exit_with_error(ENOMEM); - pkt_stream->pkts = calloc(nb_pkts, sizeof(*pkt_stream->pkts)); - if (!pkt_stream->pkts) - exit_with_error(ENOMEM); - pkt_stream->nb_pkts = nb_pkts; for (i = 0; i < nb_pkts; i++) { - pkt_stream->pkts[i].addr = (i % num_frames) * XSK_UMEM__DEFAULT_FRAME_SIZE; + pkt_stream->pkts[i].addr = (i % umem->num_frames) * umem->frame_size; pkt_stream->pkts[i].len = pkt_len; pkt_stream->pkts[i].payload = i; + + if (pkt_len > umem->frame_size) + pkt_stream->pkts[i].valid = false; + else + pkt_stream->pkts[i].valid = true; } return pkt_stream; } +static struct pkt_stream *pkt_stream_clone(struct xsk_umem_info *umem, + struct pkt_stream *pkt_stream) +{ + return pkt_stream_generate(umem, pkt_stream->nb_pkts, pkt_stream->pkts[0].len); +} + +static void pkt_stream_replace(struct test_spec *test, u32 nb_pkts, u32 pkt_len) +{ + struct pkt_stream *pkt_stream; + + pkt_stream = pkt_stream_generate(test->ifobj_tx->umem, nb_pkts, pkt_len); + test->ifobj_tx->pkt_stream = pkt_stream; + test->ifobj_rx->pkt_stream = pkt_stream; +} + +static void pkt_stream_replace_half(struct test_spec *test, u32 pkt_len, int offset) +{ + struct xsk_umem_info *umem = test->ifobj_tx->umem; + struct pkt_stream *pkt_stream; + u32 i; + + pkt_stream = pkt_stream_clone(umem, test->pkt_stream_default); + for (i = 1; i < test->pkt_stream_default->nb_pkts; i += 2) { + pkt_stream->pkts[i].addr = (i % umem->num_frames) * umem->frame_size + offset; + pkt_stream->pkts[i].len = pkt_len; + } + + test->ifobj_tx->pkt_stream = pkt_stream; + test->ifobj_rx->pkt_stream = pkt_stream; +} + static struct pkt *pkt_generate(struct ifobject *ifobject, u32 pkt_nb) { struct pkt *pkt = pkt_stream_get_pkt(ifobject->pkt_stream, pkt_nb); @@ -453,6 +574,8 @@ static struct pkt *pkt_generate(struct ifobject *ifobject, u32 pkt_nb) if (!pkt) return NULL; + if (!pkt->valid || pkt->len < PKT_SIZE) + return pkt; data = xsk_umem__get_data(ifobject->umem->buffer, pkt->addr); udp_hdr = (struct udphdr *)(data + sizeof(struct ethhdr) + sizeof(struct iphdr)); @@ -467,6 +590,26 @@ static struct pkt *pkt_generate(struct ifobject *ifobject, u32 pkt_nb) return pkt; } +static void pkt_stream_generate_custom(struct test_spec *test, struct pkt *pkts, u32 nb_pkts) +{ + struct pkt_stream *pkt_stream; + u32 i; + + pkt_stream = __pkt_stream_alloc(nb_pkts); + if (!pkt_stream) + exit_with_error(ENOMEM); + + test->ifobj_tx->pkt_stream = pkt_stream; + test->ifobj_rx->pkt_stream = pkt_stream; + + for (i = 0; i < nb_pkts; i++) { + pkt_stream->pkts[i].addr = pkts[i].addr; + pkt_stream->pkts[i].len = pkts[i].len; + pkt_stream->pkts[i].payload = i; + pkt_stream->pkts[i].valid = pkts[i].valid; + } +} + static void pkt_dump(void *pkt, u32 len) { char s[INET_ADDRSTRLEN]; @@ -504,9 +647,28 @@ static void pkt_dump(void *pkt, u32 len) fprintf(stdout, "---------------------------------------\n"); } -static bool is_pkt_valid(struct pkt *pkt, void *buffer, const struct xdp_desc *desc) +static bool is_offset_correct(struct xsk_umem_info *umem, struct pkt_stream *pkt_stream, u64 addr, + u64 pkt_stream_addr) { - void *data = xsk_umem__get_data(buffer, desc->addr); + u32 headroom = umem->unaligned_mode ? 0 : umem->frame_headroom; + u32 offset = addr % umem->frame_size, expected_offset = 0; + + if (!pkt_stream->use_addr_for_fill) + pkt_stream_addr = 0; + + expected_offset += (pkt_stream_addr + headroom + XDP_PACKET_HEADROOM) % umem->frame_size; + + if (offset == expected_offset) + return true; + + ksft_test_result_fail("ERROR: [%s] expected [%u], got [%u]\n", __func__, expected_offset, + offset); + return false; +} + +static bool is_pkt_valid(struct pkt *pkt, void *buffer, u64 addr, u32 len) +{ + void *data = xsk_umem__get_data(buffer, addr); struct iphdr *iphdr = (struct iphdr *)(data + sizeof(struct ethhdr)); if (!pkt) { @@ -514,19 +676,24 @@ static bool is_pkt_valid(struct pkt *pkt, void *buffer, const struct xdp_desc *d return false; } + if (len < PKT_SIZE) { + /*Do not try to verify packets that are smaller than minimum size. */ + return true; + } + + if (pkt->len != len) { + ksft_test_result_fail + ("ERROR: [%s] expected length [%d], got length [%d]\n", + __func__, pkt->len, len); + return false; + } + if (iphdr->version == IP_PKT_VER && iphdr->tos == IP_PKT_TOS) { u32 seqnum = ntohl(*((u32 *)(data + PKT_HDR_SIZE))); - if (opt_pkt_dump && test_type != TEST_TYPE_STATS) + if (opt_pkt_dump) pkt_dump(data, PKT_SIZE); - if (pkt->len != desc->len) { - ksft_test_result_fail - ("ERROR: [%s] expected length [%d], got length [%d]\n", - __func__, pkt->len, desc->len); - return false; - } - if (pkt->payload != seqnum) { ksft_test_result_fail ("ERROR: [%s] expected seqnum [%d], got seqnum [%d]\n", @@ -558,14 +725,20 @@ static void complete_pkts(struct xsk_socket_info *xsk, int batch_size) unsigned int rcvd; u32 idx; - if (!xsk->outstanding_tx) - return; - if (xsk_ring_prod__needs_wakeup(&xsk->tx)) kick_tx(xsk); rcvd = xsk_ring_cons__peek(&xsk->umem->cq, batch_size, &idx); if (rcvd) { + if (rcvd > xsk->outstanding_tx) { + u64 addr = *xsk_ring_cons__comp_addr(&xsk->umem->cq, idx + rcvd - 1); + + ksft_test_result_fail("ERROR: [%s] Too many packets completed\n", + __func__); + ksft_print_msg("Last completion address: %llx\n", addr); + return; + } + xsk_ring_cons__release(&xsk->umem->cq, rcvd); xsk->outstanding_tx -= rcvd; } @@ -574,15 +747,15 @@ static void complete_pkts(struct xsk_socket_info *xsk, int batch_size) static void receive_pkts(struct pkt_stream *pkt_stream, struct xsk_socket_info *xsk, struct pollfd *fds) { - u32 idx_rx = 0, idx_fq = 0, rcvd, i, pkt_count = 0; - struct pkt *pkt; + struct pkt *pkt = pkt_stream_get_next_rx_pkt(pkt_stream); + struct xsk_umem_info *umem = xsk->umem; + u32 idx_rx = 0, idx_fq = 0, rcvd, i; int ret; - pkt = pkt_stream_get_pkt(pkt_stream, pkt_count++); while (pkt) { rcvd = xsk_ring_cons__peek(&xsk->rx, BATCH_SIZE, &idx_rx); if (!rcvd) { - if (xsk_ring_prod__needs_wakeup(&xsk->umem->fq)) { + if (xsk_ring_prod__needs_wakeup(&umem->fq)) { ret = poll(fds, 1, POLL_TMOUT); if (ret < 0) exit_with_error(-ret); @@ -590,40 +763,57 @@ static void receive_pkts(struct pkt_stream *pkt_stream, struct xsk_socket_info * continue; } - ret = xsk_ring_prod__reserve(&xsk->umem->fq, rcvd, &idx_fq); + ret = xsk_ring_prod__reserve(&umem->fq, rcvd, &idx_fq); while (ret != rcvd) { if (ret < 0) exit_with_error(-ret); - if (xsk_ring_prod__needs_wakeup(&xsk->umem->fq)) { + if (xsk_ring_prod__needs_wakeup(&umem->fq)) { ret = poll(fds, 1, POLL_TMOUT); if (ret < 0) exit_with_error(-ret); } - ret = xsk_ring_prod__reserve(&xsk->umem->fq, rcvd, &idx_fq); + ret = xsk_ring_prod__reserve(&umem->fq, rcvd, &idx_fq); } for (i = 0; i < rcvd; i++) { const struct xdp_desc *desc = xsk_ring_cons__rx_desc(&xsk->rx, idx_rx++); u64 addr = desc->addr, orig; + if (!pkt) { + ksft_test_result_fail("ERROR: [%s] Received too many packets.\n", + __func__); + ksft_print_msg("Last packet has addr: %llx len: %u\n", + addr, desc->len); + return; + } + orig = xsk_umem__extract_addr(addr); addr = xsk_umem__add_offset_to_addr(addr); - if (!is_pkt_valid(pkt, xsk->umem->buffer, desc)) + + if (!is_pkt_valid(pkt, umem->buffer, addr, desc->len)) + return; + if (!is_offset_correct(umem, pkt_stream, addr, pkt->addr)) return; - *xsk_ring_prod__fill_addr(&xsk->umem->fq, idx_fq++) = orig; - pkt = pkt_stream_get_pkt(pkt_stream, pkt_count++); + *xsk_ring_prod__fill_addr(&umem->fq, idx_fq++) = orig; + pkt = pkt_stream_get_next_rx_pkt(pkt_stream); } - xsk_ring_prod__submit(&xsk->umem->fq, rcvd); + xsk_ring_prod__submit(&umem->fq, rcvd); xsk_ring_cons__release(&xsk->rx, rcvd); + + pthread_mutex_lock(&pacing_mutex); + pkts_in_flight -= rcvd; + if (pkts_in_flight < umem->num_frames) + pthread_cond_signal(&pacing_cond); + pthread_mutex_unlock(&pacing_mutex); } } static u32 __send_pkts(struct ifobject *ifobject, u32 pkt_nb) { struct xsk_socket_info *xsk = ifobject->xsk; - u32 i, idx; + u32 i, idx, valid_pkts = 0; while (xsk_ring_prod__reserve(&xsk->tx, BATCH_SIZE, &idx) < BATCH_SIZE) complete_pkts(xsk, BATCH_SIZE); @@ -638,15 +828,23 @@ static u32 __send_pkts(struct ifobject *ifobject, u32 pkt_nb) tx_desc->addr = pkt->addr; tx_desc->len = pkt->len; pkt_nb++; + if (pkt->valid) + valid_pkts++; } - xsk_ring_prod__submit(&xsk->tx, i); - if (stat_test_type != STAT_TEST_TX_INVALID) - xsk->outstanding_tx += i; - else if (xsk_ring_prod__needs_wakeup(&xsk->tx)) + pthread_mutex_lock(&pacing_mutex); + pkts_in_flight += valid_pkts; + if (ifobject->pacing_on && pkts_in_flight >= ifobject->umem->num_frames - BATCH_SIZE) { kick_tx(xsk); + pthread_cond_wait(&pacing_cond, &pacing_mutex); + } + pthread_mutex_unlock(&pacing_mutex); + + xsk_ring_prod__submit(&xsk->tx, i); + xsk->outstanding_tx += valid_pkts; complete_pkts(xsk, i); + usleep(10); return i; } @@ -658,29 +856,25 @@ static void wait_for_tx_completion(struct xsk_socket_info *xsk) static void send_pkts(struct ifobject *ifobject) { - struct pollfd fds[MAX_SOCKS] = { }; + struct pollfd fds = { }; u32 pkt_cnt = 0; - fds[0].fd = xsk_socket__fd(ifobject->xsk->xsk); - fds[0].events = POLLOUT; + fds.fd = xsk_socket__fd(ifobject->xsk->xsk); + fds.events = POLLOUT; while (pkt_cnt < ifobject->pkt_stream->nb_pkts) { - u32 sent; - - if (test_type == TEST_TYPE_POLL) { + if (ifobject->use_poll) { int ret; - ret = poll(fds, 1, POLL_TMOUT); + ret = poll(&fds, 1, POLL_TMOUT); if (ret <= 0) continue; - if (!(fds[0].revents & POLLOUT)) + if (!(fds.revents & POLLOUT)) continue; } - sent = __send_pkts(ifobject, pkt_cnt); - pkt_cnt += sent; - usleep(10); + pkt_cnt += __send_pkts(ifobject, pkt_cnt); } wait_for_tx_completion(ifobject->xsk); @@ -698,7 +892,7 @@ static bool rx_stats_are_valid(struct ifobject *ifobject) optlen = sizeof(stats); err = getsockopt(fd, SOL_XDP, XDP_STATISTICS, &stats, &optlen); if (err) { - ksft_test_result_fail("ERROR: [%s] getsockopt(XDP_STATISTICS) error %u %s\n", + ksft_test_result_fail("ERROR Rx: [%s] getsockopt(XDP_STATISTICS) error %u %s\n", __func__, -err, strerror(-err)); return true; } @@ -739,7 +933,7 @@ static void tx_stats_validate(struct ifobject *ifobject) optlen = sizeof(stats); err = getsockopt(fd, SOL_XDP, XDP_STATISTICS, &stats, &optlen); if (err) { - ksft_test_result_fail("ERROR: [%s] getsockopt(XDP_STATISTICS) error %u %s\n", + ksft_test_result_fail("ERROR Tx: [%s] getsockopt(XDP_STATISTICS) error %u %s\n", __func__, -err, strerror(-err)); return; } @@ -751,71 +945,62 @@ static void tx_stats_validate(struct ifobject *ifobject) __func__, stats.tx_invalid_descs, ifobject->pkt_stream->nb_pkts); } -static void thread_common_ops(struct ifobject *ifobject, void *bufs) +static void thread_common_ops(struct test_spec *test, struct ifobject *ifobject) { - u64 umem_sz = num_frames * XSK_UMEM__DEFAULT_FRAME_SIZE; int mmap_flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE; - size_t mmap_sz = umem_sz; - int ctr = 0; - int ret; + u32 i; ifobject->ns_fd = switch_namespace(ifobject->nsname); - if (test_type == TEST_TYPE_BPF_RES) - mmap_sz *= 2; + if (ifobject->umem->unaligned_mode) + mmap_flags |= MAP_HUGETLB; - bufs = mmap(NULL, mmap_sz, PROT_READ | PROT_WRITE, mmap_flags, -1, 0); - if (bufs == MAP_FAILED) - exit_with_error(errno); + for (i = 0; i < test->nb_sockets; i++) { + u64 umem_sz = ifobject->umem->num_frames * ifobject->umem->frame_size; + u32 ctr = 0; + void *bufs; + int ret; - while (ctr++ < SOCK_RECONF_CTR) { - xsk_configure_umem(ifobject, bufs, umem_sz, 0); - ifobject->umem = ifobject->umem_arr[0]; - ret = xsk_configure_socket(ifobject, 0); - if (!ret) - break; + bufs = mmap(NULL, umem_sz, PROT_READ | PROT_WRITE, mmap_flags, -1, 0); + if (bufs == MAP_FAILED) + exit_with_error(errno); - /* Retry Create Socket if it fails as xsk_socket__create() is asynchronous */ - usleep(USLEEP_MAX); - if (ctr >= SOCK_RECONF_CTR) + ret = xsk_configure_umem(&ifobject->umem_arr[i], bufs, umem_sz); + if (ret) exit_with_error(-ret); + + while (ctr++ < SOCK_RECONF_CTR) { + ret = xsk_configure_socket(&ifobject->xsk_arr[i], &ifobject->umem_arr[i], + ifobject, i); + if (!ret) + break; + + /* Retry if it fails as xsk_socket__create() is asynchronous */ + if (ctr >= SOCK_RECONF_CTR) + exit_with_error(-ret); + usleep(USLEEP_MAX); + } } - ifobject->umem = ifobject->umem_arr[0]; - ifobject->xsk = ifobject->xsk_arr[0]; - - if (test_type == TEST_TYPE_BPF_RES) { - xsk_configure_umem(ifobject, (u8 *)bufs + umem_sz, umem_sz, 1); - ifobject->umem = ifobject->umem_arr[1]; - ret = xsk_configure_socket(ifobject, 1); - } - - ifobject->umem = ifobject->umem_arr[0]; - ifobject->xsk = ifobject->xsk_arr[0]; - print_verbose("Interface [%s] vector [%s]\n", - ifobject->ifname, ifobject->fv.vector == tx ? "Tx" : "Rx"); -} - -static bool testapp_is_test_two_stepped(void) -{ - return (test_type != TEST_TYPE_BIDI && test_type != TEST_TYPE_BPF_RES) || second_step; + ifobject->umem = &ifobject->umem_arr[0]; + ifobject->xsk = &ifobject->xsk_arr[0]; } static void testapp_cleanup_xsk_res(struct ifobject *ifobj) { - if (testapp_is_test_two_stepped()) { - xsk_socket__delete(ifobj->xsk->xsk); - (void)xsk_umem__delete(ifobj->umem->umem); - } + print_verbose("Destroying socket\n"); + xsk_socket__delete(ifobj->xsk->xsk); + munmap(ifobj->umem->buffer, ifobj->umem->num_frames * ifobj->umem->frame_size); + xsk_umem__delete(ifobj->umem->umem); } static void *worker_testapp_validate_tx(void *arg) { - struct ifobject *ifobject = (struct ifobject *)arg; - void *bufs = NULL; + struct test_spec *test = (struct test_spec *)arg; + struct ifobject *ifobject = test->ifobj_tx; - if (!second_step) - thread_common_ops(ifobject, bufs); + if (test->current_step == 1) + thread_common_ops(test, ifobject); print_verbose("Sending %d packets on interface %s\n", ifobject->pkt_stream->nb_pkts, ifobject->ifname); @@ -824,24 +1009,55 @@ static void *worker_testapp_validate_tx(void *arg) if (stat_test_type == STAT_TEST_TX_INVALID) tx_stats_validate(ifobject); - testapp_cleanup_xsk_res(ifobject); + if (test->total_steps == test->current_step) + testapp_cleanup_xsk_res(ifobject); pthread_exit(NULL); } +static void xsk_populate_fill_ring(struct xsk_umem_info *umem, struct pkt_stream *pkt_stream) +{ + u32 idx = 0, i, buffers_to_fill; + int ret; + + if (umem->num_frames < XSK_RING_PROD__DEFAULT_NUM_DESCS) + buffers_to_fill = umem->num_frames; + else + buffers_to_fill = XSK_RING_PROD__DEFAULT_NUM_DESCS; + + ret = xsk_ring_prod__reserve(&umem->fq, buffers_to_fill, &idx); + if (ret != buffers_to_fill) + exit_with_error(ENOSPC); + for (i = 0; i < buffers_to_fill; i++) { + u64 addr; + + if (pkt_stream->use_addr_for_fill) { + struct pkt *pkt = pkt_stream_get_pkt(pkt_stream, i); + + if (!pkt) + break; + addr = pkt->addr; + } else { + addr = i * umem->frame_size; + } + + *xsk_ring_prod__fill_addr(&umem->fq, idx++) = addr; + } + xsk_ring_prod__submit(&umem->fq, buffers_to_fill); +} + static void *worker_testapp_validate_rx(void *arg) { - struct ifobject *ifobject = (struct ifobject *)arg; - struct pollfd fds[MAX_SOCKS] = { }; - void *bufs = NULL; + struct test_spec *test = (struct test_spec *)arg; + struct ifobject *ifobject = test->ifobj_rx; + struct pollfd fds = { }; - if (!second_step) - thread_common_ops(ifobject, bufs); + if (test->current_step == 1) + thread_common_ops(test, ifobject); - if (stat_test_type != STAT_TEST_RX_FILL_EMPTY) - xsk_populate_fill_ring(ifobject->umem); + xsk_populate_fill_ring(ifobject->umem, ifobject->pkt_stream); - fds[0].fd = xsk_socket__fd(ifobject->xsk->xsk); - fds[0].events = POLLIN; + fds.fd = xsk_socket__fd(ifobject->xsk->xsk); + fds.events = POLLIN; pthread_barrier_wait(&barr); @@ -849,151 +1065,239 @@ static void *worker_testapp_validate_rx(void *arg) while (!rx_stats_are_valid(ifobject)) continue; else - receive_pkts(ifobject->pkt_stream, ifobject->xsk, fds); + receive_pkts(ifobject->pkt_stream, ifobject->xsk, &fds); - if (test_type == TEST_TYPE_TEARDOWN) - print_verbose("Destroying socket\n"); - - testapp_cleanup_xsk_res(ifobject); + if (test->total_steps == test->current_step) + testapp_cleanup_xsk_res(ifobject); pthread_exit(NULL); } -static void testapp_validate(void) +static void testapp_validate_traffic(struct test_spec *test) { - bool bidi = test_type == TEST_TYPE_BIDI; - bool bpf = test_type == TEST_TYPE_BPF_RES; - struct pkt_stream *pkt_stream; + struct ifobject *ifobj_tx = test->ifobj_tx; + struct ifobject *ifobj_rx = test->ifobj_rx; + pthread_t t0, t1; if (pthread_barrier_init(&barr, NULL, 2)) exit_with_error(errno); - if (stat_test_type == STAT_TEST_TX_INVALID) - pkt_stream = pkt_stream_generate(DEFAULT_PKT_CNT, XSK_UMEM__INVALID_FRAME_SIZE); - else - pkt_stream = pkt_stream_generate(DEFAULT_PKT_CNT, PKT_SIZE); - ifdict_tx->pkt_stream = pkt_stream; - ifdict_rx->pkt_stream = pkt_stream; + test->current_step++; + pkt_stream_reset(ifobj_rx->pkt_stream); + pkts_in_flight = 0; /*Spawn RX thread */ - pthread_create(&t0, NULL, ifdict_rx->func_ptr, ifdict_rx); + pthread_create(&t0, NULL, ifobj_rx->func_ptr, test); pthread_barrier_wait(&barr); if (pthread_barrier_destroy(&barr)) exit_with_error(errno); /*Spawn TX thread */ - pthread_create(&t1, NULL, ifdict_tx->func_ptr, ifdict_tx); + pthread_create(&t1, NULL, ifobj_tx->func_ptr, test); pthread_join(t1, NULL); pthread_join(t0, NULL); - - if (!(test_type == TEST_TYPE_TEARDOWN) && !bidi && !bpf && !(test_type == TEST_TYPE_STATS)) - print_ksft_result(); } -static void testapp_teardown(void) +static void testapp_teardown(struct test_spec *test) { int i; + test_spec_set_name(test, "TEARDOWN"); for (i = 0; i < MAX_TEARDOWN_ITER; i++) { - print_verbose("Creating socket\n"); - testapp_validate(); + testapp_validate_traffic(test); + test_spec_reset(test); } - - print_ksft_result(); } -static void swap_vectors(struct ifobject *ifobj1, struct ifobject *ifobj2) +static void swap_directions(struct ifobject **ifobj1, struct ifobject **ifobj2) { - void *(*tmp_func_ptr)(void *) = ifobj1->func_ptr; - enum fvector tmp_vector = ifobj1->fv.vector; + thread_func_t tmp_func_ptr = (*ifobj1)->func_ptr; + struct ifobject *tmp_ifobj = (*ifobj1); - ifobj1->func_ptr = ifobj2->func_ptr; - ifobj1->fv.vector = ifobj2->fv.vector; + (*ifobj1)->func_ptr = (*ifobj2)->func_ptr; + (*ifobj2)->func_ptr = tmp_func_ptr; - ifobj2->func_ptr = tmp_func_ptr; - ifobj2->fv.vector = tmp_vector; - - ifdict_tx = ifobj1; - ifdict_rx = ifobj2; + *ifobj1 = *ifobj2; + *ifobj2 = tmp_ifobj; } -static void testapp_bidi(void) +static void testapp_bidi(struct test_spec *test) { - for (int i = 0; i < MAX_BIDI_ITER; i++) { - print_verbose("Creating socket\n"); - testapp_validate(); - if (!second_step) { - print_verbose("Switching Tx/Rx vectors\n"); - swap_vectors(ifdict[1], ifdict[0]); - } - second_step = true; - } + test_spec_set_name(test, "BIDIRECTIONAL"); + test->ifobj_tx->rx_on = true; + test->ifobj_rx->tx_on = true; + test->total_steps = 2; + testapp_validate_traffic(test); - swap_vectors(ifdict[0], ifdict[1]); + print_verbose("Switching Tx/Rx vectors\n"); + swap_directions(&test->ifobj_rx, &test->ifobj_tx); + testapp_validate_traffic(test); - print_ksft_result(); + swap_directions(&test->ifobj_rx, &test->ifobj_tx); } -static void swap_xsk_res(void) +static void swap_xsk_resources(struct ifobject *ifobj_tx, struct ifobject *ifobj_rx) { - xsk_socket__delete(ifdict_tx->xsk->xsk); - xsk_umem__delete(ifdict_tx->umem->umem); - xsk_socket__delete(ifdict_rx->xsk->xsk); - xsk_umem__delete(ifdict_rx->umem->umem); - ifdict_tx->umem = ifdict_tx->umem_arr[1]; - ifdict_tx->xsk = ifdict_tx->xsk_arr[1]; - ifdict_rx->umem = ifdict_rx->umem_arr[1]; - ifdict_rx->xsk = ifdict_rx->xsk_arr[1]; + xsk_socket__delete(ifobj_tx->xsk->xsk); + xsk_umem__delete(ifobj_tx->umem->umem); + xsk_socket__delete(ifobj_rx->xsk->xsk); + xsk_umem__delete(ifobj_rx->umem->umem); + ifobj_tx->umem = &ifobj_tx->umem_arr[1]; + ifobj_tx->xsk = &ifobj_tx->xsk_arr[1]; + ifobj_rx->umem = &ifobj_rx->umem_arr[1]; + ifobj_rx->xsk = &ifobj_rx->xsk_arr[1]; } -static void testapp_bpf_res(void) +static void testapp_bpf_res(struct test_spec *test) +{ + test_spec_set_name(test, "BPF_RES"); + test->total_steps = 2; + test->nb_sockets = 2; + testapp_validate_traffic(test); + + swap_xsk_resources(test->ifobj_tx, test->ifobj_rx); + testapp_validate_traffic(test); +} + +static void testapp_headroom(struct test_spec *test) +{ + test_spec_set_name(test, "UMEM_HEADROOM"); + test->ifobj_rx->umem->frame_headroom = UMEM_HEADROOM_TEST_SIZE; + testapp_validate_traffic(test); +} + +static void testapp_stats(struct test_spec *test) { int i; - for (i = 0; i < MAX_BPF_ITER; i++) { - print_verbose("Creating socket\n"); - testapp_validate(); - if (!second_step) - swap_xsk_res(); - second_step = true; - } - - print_ksft_result(); -} - -static void testapp_stats(void) -{ - for (int i = 0; i < STAT_TEST_TYPE_MAX; i++) { + for (i = 0; i < STAT_TEST_TYPE_MAX; i++) { + test_spec_reset(test); stat_test_type = i; - - /* reset defaults */ - rxqsize = XSK_RING_CONS__DEFAULT_NUM_DESCS; - frame_headroom = XSK_UMEM__DEFAULT_FRAME_HEADROOM; + /* No or few packets will be received so cannot pace packets */ + test->ifobj_tx->pacing_on = false; switch (stat_test_type) { case STAT_TEST_RX_DROPPED: - frame_headroom = XSK_UMEM__DEFAULT_FRAME_SIZE - - XDP_PACKET_HEADROOM - 1; + test_spec_set_name(test, "STAT_RX_DROPPED"); + test->ifobj_rx->umem->frame_headroom = test->ifobj_rx->umem->frame_size - + XDP_PACKET_HEADROOM - 1; + testapp_validate_traffic(test); break; case STAT_TEST_RX_FULL: - rxqsize = RX_FULL_RXQSIZE; + test_spec_set_name(test, "STAT_RX_FULL"); + test->ifobj_rx->xsk->rxqsize = RX_FULL_RXQSIZE; + testapp_validate_traffic(test); break; case STAT_TEST_TX_INVALID: - continue; + test_spec_set_name(test, "STAT_TX_INVALID"); + pkt_stream_replace(test, DEFAULT_PKT_CNT, XSK_UMEM__INVALID_FRAME_SIZE); + testapp_validate_traffic(test); + + pkt_stream_restore_default(test); + break; + case STAT_TEST_RX_FILL_EMPTY: + test_spec_set_name(test, "STAT_RX_FILL_EMPTY"); + test->ifobj_rx->pkt_stream = pkt_stream_generate(test->ifobj_rx->umem, 0, + MIN_PKT_SIZE); + if (!test->ifobj_rx->pkt_stream) + exit_with_error(ENOMEM); + test->ifobj_rx->pkt_stream->use_addr_for_fill = true; + testapp_validate_traffic(test); + + pkt_stream_restore_default(test); + break; default: break; } - testapp_validate(); } - print_ksft_result(); + /* To only see the whole stat set being completed unless an individual test fails. */ + test_spec_set_name(test, "STATS"); } -static void init_iface(struct ifobject *ifobj, const char *dst_mac, - const char *src_mac, const char *dst_ip, - const char *src_ip, const u16 dst_port, - const u16 src_port, enum fvector vector) +/* Simple test */ +static bool hugepages_present(struct ifobject *ifobject) +{ + const size_t mmap_sz = 2 * ifobject->umem->num_frames * ifobject->umem->frame_size; + void *bufs; + + bufs = mmap(NULL, mmap_sz, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB, -1, 0); + if (bufs == MAP_FAILED) + return false; + + munmap(bufs, mmap_sz); + return true; +} + +static bool testapp_unaligned(struct test_spec *test) +{ + if (!hugepages_present(test->ifobj_tx)) { + ksft_test_result_skip("No 2M huge pages present.\n"); + return false; + } + + test_spec_set_name(test, "UNALIGNED_MODE"); + test->ifobj_tx->umem->unaligned_mode = true; + test->ifobj_rx->umem->unaligned_mode = true; + /* Let half of the packets straddle a buffer boundrary */ + pkt_stream_replace_half(test, PKT_SIZE, -PKT_SIZE / 2); + test->ifobj_rx->pkt_stream->use_addr_for_fill = true; + testapp_validate_traffic(test); + + pkt_stream_restore_default(test); + return true; +} + +static void testapp_single_pkt(struct test_spec *test) +{ + struct pkt pkts[] = {{0x1000, PKT_SIZE, 0, true}}; + + pkt_stream_generate_custom(test, pkts, ARRAY_SIZE(pkts)); + testapp_validate_traffic(test); + pkt_stream_restore_default(test); +} + +static void testapp_invalid_desc(struct test_spec *test) +{ + struct pkt pkts[] = { + /* Zero packet length at address zero allowed */ + {0, 0, 0, true}, + /* Zero packet length allowed */ + {0x1000, 0, 0, true}, + /* Straddling the start of umem */ + {-2, PKT_SIZE, 0, false}, + /* Packet too large */ + {0x2000, XSK_UMEM__INVALID_FRAME_SIZE, 0, false}, + /* After umem ends */ + {UMEM_SIZE, PKT_SIZE, 0, false}, + /* Straddle the end of umem */ + {UMEM_SIZE - PKT_SIZE / 2, PKT_SIZE, 0, false}, + /* Straddle a page boundrary */ + {0x3000 - PKT_SIZE / 2, PKT_SIZE, 0, false}, + /* Straddle a 2K boundrary */ + {0x3800 - PKT_SIZE / 2, PKT_SIZE, 0, true}, + /* Valid packet for synch so that something is received */ + {0x4000, PKT_SIZE, 0, true}}; + + if (test->ifobj_tx->umem->unaligned_mode) { + /* Crossing a page boundrary allowed */ + pkts[6].valid = true; + } + if (test->ifobj_tx->umem->frame_size == XSK_UMEM__DEFAULT_FRAME_SIZE / 2) { + /* Crossing a 2K frame size boundrary not allowed */ + pkts[7].valid = false; + } + + pkt_stream_generate_custom(test, pkts, ARRAY_SIZE(pkts)); + testapp_validate_traffic(test); + pkt_stream_restore_default(test); +} + +static void init_iface(struct ifobject *ifobj, const char *dst_mac, const char *src_mac, + const char *dst_ip, const char *src_ip, const u16 dst_port, + const u16 src_port, thread_func_t func_ptr) { struct in_addr ip; @@ -1009,58 +1313,84 @@ static void init_iface(struct ifobject *ifobj, const char *dst_mac, ifobj->dst_port = dst_port; ifobj->src_port = src_port; - if (vector == tx) { - ifobj->fv.vector = tx; - ifobj->func_ptr = worker_testapp_validate_tx; - ifdict_tx = ifobj; - } else { - ifobj->fv.vector = rx; - ifobj->func_ptr = worker_testapp_validate_rx; - ifdict_rx = ifobj; - } + ifobj->func_ptr = func_ptr; } -static void run_pkt_test(int mode, int type) +static void run_pkt_test(struct test_spec *test, enum test_mode mode, enum test_type type) { test_type = type; /* reset defaults after potential previous test */ - xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST; - second_step = 0; stat_test_type = -1; - rxqsize = XSK_RING_CONS__DEFAULT_NUM_DESCS; - frame_headroom = XSK_UMEM__DEFAULT_FRAME_HEADROOM; - - configured_mode = mode; - - switch (mode) { - case (TEST_MODE_SKB): - xdp_flags |= XDP_FLAGS_SKB_MODE; - break; - case (TEST_MODE_DRV): - xdp_flags |= XDP_FLAGS_DRV_MODE; - break; - default: - break; - } switch (test_type) { case TEST_TYPE_STATS: - testapp_stats(); + testapp_stats(test); break; case TEST_TYPE_TEARDOWN: - testapp_teardown(); + testapp_teardown(test); break; case TEST_TYPE_BIDI: - testapp_bidi(); + testapp_bidi(test); break; case TEST_TYPE_BPF_RES: - testapp_bpf_res(); + testapp_bpf_res(test); + break; + case TEST_TYPE_RUN_TO_COMPLETION: + test_spec_set_name(test, "RUN_TO_COMPLETION"); + testapp_validate_traffic(test); + break; + case TEST_TYPE_RUN_TO_COMPLETION_SINGLE_PKT: + test_spec_set_name(test, "RUN_TO_COMPLETION_SINGLE_PKT"); + testapp_single_pkt(test); + break; + case TEST_TYPE_RUN_TO_COMPLETION_2K_FRAME: + test_spec_set_name(test, "RUN_TO_COMPLETION_2K_FRAME_SIZE"); + test->ifobj_tx->umem->frame_size = 2048; + test->ifobj_rx->umem->frame_size = 2048; + pkt_stream_replace(test, DEFAULT_PKT_CNT, MIN_PKT_SIZE); + testapp_validate_traffic(test); + + pkt_stream_restore_default(test); + break; + case TEST_TYPE_POLL: + test->ifobj_tx->use_poll = true; + test->ifobj_rx->use_poll = true; + test_spec_set_name(test, "POLL"); + testapp_validate_traffic(test); + break; + case TEST_TYPE_ALIGNED_INV_DESC: + test_spec_set_name(test, "ALIGNED_INV_DESC"); + testapp_invalid_desc(test); + break; + case TEST_TYPE_ALIGNED_INV_DESC_2K_FRAME: + test_spec_set_name(test, "ALIGNED_INV_DESC_2K_FRAME_SIZE"); + test->ifobj_tx->umem->frame_size = 2048; + test->ifobj_rx->umem->frame_size = 2048; + testapp_invalid_desc(test); + break; + case TEST_TYPE_UNALIGNED_INV_DESC: + if (!hugepages_present(test->ifobj_tx)) { + ksft_test_result_skip("No 2M huge pages present.\n"); + return; + } + test_spec_set_name(test, "UNALIGNED_INV_DESC"); + test->ifobj_tx->umem->unaligned_mode = true; + test->ifobj_rx->umem->unaligned_mode = true; + testapp_invalid_desc(test); + break; + case TEST_TYPE_UNALIGNED: + if (!testapp_unaligned(test)) + return; + break; + case TEST_TYPE_HEADROOM: + testapp_headroom(test); break; default: - testapp_validate(); break; } + + print_ksft_result(test); } static struct ifobject *ifobject_create(void) @@ -1071,11 +1401,11 @@ static struct ifobject *ifobject_create(void) if (!ifobj) return NULL; - ifobj->xsk_arr = calloc(2, sizeof(struct xsk_socket_info *)); + ifobj->xsk_arr = calloc(MAX_SOCKETS, sizeof(*ifobj->xsk_arr)); if (!ifobj->xsk_arr) goto out_xsk_arr; - ifobj->umem_arr = calloc(2, sizeof(struct xsk_umem_info *)); + ifobj->umem_arr = calloc(MAX_SOCKETS, sizeof(*ifobj->umem_arr)); if (!ifobj->umem_arr) goto out_umem_arr; @@ -1098,34 +1428,53 @@ static void ifobject_delete(struct ifobject *ifobj) int main(int argc, char **argv) { struct rlimit _rlim = { RLIM_INFINITY, RLIM_INFINITY }; - int i, j; + struct pkt_stream *pkt_stream_default; + struct ifobject *ifobj_tx, *ifobj_rx; + struct test_spec test; + u32 i, j; if (setrlimit(RLIMIT_MEMLOCK, &_rlim)) exit_with_error(errno); - for (i = 0; i < MAX_INTERFACES; i++) { - ifdict[i] = ifobject_create(); - if (!ifdict[i]) - exit_with_error(ENOMEM); - } + ifobj_tx = ifobject_create(); + if (!ifobj_tx) + exit_with_error(ENOMEM); + ifobj_rx = ifobject_create(); + if (!ifobj_rx) + exit_with_error(ENOMEM); setlocale(LC_ALL, ""); - parse_command_line(argc, argv); + parse_command_line(ifobj_tx, ifobj_rx, argc, argv); - init_iface(ifdict[tx], MAC1, MAC2, IP1, IP2, UDP_PORT1, UDP_PORT2, tx); - init_iface(ifdict[rx], MAC2, MAC1, IP2, IP1, UDP_PORT2, UDP_PORT1, rx); + if (!validate_interface(ifobj_tx) || !validate_interface(ifobj_rx)) { + usage(basename(argv[0])); + ksft_exit_xfail(); + } + + init_iface(ifobj_tx, MAC1, MAC2, IP1, IP2, UDP_PORT1, UDP_PORT2, + worker_testapp_validate_tx); + init_iface(ifobj_rx, MAC2, MAC1, IP2, IP1, UDP_PORT2, UDP_PORT1, + worker_testapp_validate_rx); + + test_spec_init(&test, ifobj_tx, ifobj_rx, 0); + pkt_stream_default = pkt_stream_generate(ifobj_tx->umem, DEFAULT_PKT_CNT, PKT_SIZE); + if (!pkt_stream_default) + exit_with_error(ENOMEM); + test.pkt_stream_default = pkt_stream_default; ksft_set_plan(TEST_MODE_MAX * TEST_TYPE_MAX); for (i = 0; i < TEST_MODE_MAX; i++) for (j = 0; j < TEST_TYPE_MAX; j++) { - run_pkt_test(i, j); + test_spec_init(&test, ifobj_tx, ifobj_rx, i); + run_pkt_test(&test, i, j); usleep(USLEEP_MAX); } - for (i = 0; i < MAX_INTERFACES; i++) - ifobject_delete(ifdict[i]); + pkt_stream_delete(pkt_stream_default); + ifobject_delete(ifobj_tx); + ifobject_delete(ifobj_rx); ksft_exit_pass(); return 0; diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h index 7e49b9fbe2..2f705f44b7 100644 --- a/tools/testing/selftests/bpf/xdpxceiver.h +++ b/tools/testing/selftests/bpf/xdpxceiver.h @@ -20,10 +20,9 @@ #define MAX_INTERFACES 2 #define MAX_INTERFACE_NAME_CHARS 7 #define MAX_INTERFACES_NAMESPACE_CHARS 10 -#define MAX_SOCKS 1 +#define MAX_SOCKETS 2 +#define MAX_TEST_NAME_SIZE 32 #define MAX_TEARDOWN_ITER 10 -#define MAX_BIDI_ITER 2 -#define MAX_BPF_ITER 2 #define PKT_HDR_SIZE (sizeof(struct ethhdr) + sizeof(struct iphdr) + \ sizeof(struct udphdr)) #define MIN_PKT_SIZE 64 @@ -36,10 +35,13 @@ #define UDP_PKT_DATA_SIZE (UDP_PKT_SIZE - sizeof(struct udphdr)) #define USLEEP_MAX 10000 #define SOCK_RECONF_CTR 10 -#define BATCH_SIZE 8 +#define BATCH_SIZE 64 #define POLL_TMOUT 1000 #define DEFAULT_PKT_CNT (4 * 1024) +#define DEFAULT_UMEM_BUFFERS (DEFAULT_PKT_CNT / 4) +#define UMEM_SIZE (DEFAULT_UMEM_BUFFERS * XSK_UMEM__DEFAULT_FRAME_SIZE) #define RX_FULL_RXQSIZE 32 +#define UMEM_HEADROOM_TEST_SIZE 128 #define XSK_UMEM__INVALID_FRAME_SIZE (XSK_UMEM__DEFAULT_FRAME_SIZE + 1) #define print_verbose(x...) do { if (opt_verbose) ksft_print_msg(x); } while (0) @@ -51,8 +53,15 @@ enum test_mode { }; enum test_type { - TEST_TYPE_NOPOLL, + TEST_TYPE_RUN_TO_COMPLETION, + TEST_TYPE_RUN_TO_COMPLETION_2K_FRAME, + TEST_TYPE_RUN_TO_COMPLETION_SINGLE_PKT, TEST_TYPE_POLL, + TEST_TYPE_UNALIGNED, + TEST_TYPE_ALIGNED_INV_DESC, + TEST_TYPE_ALIGNED_INV_DESC_2K_FRAME, + TEST_TYPE_UNALIGNED_INV_DESC, + TEST_TYPE_HEADROOM, TEST_TYPE_TEARDOWN, TEST_TYPE_BIDI, TEST_TYPE_STATS, @@ -68,25 +77,21 @@ enum stat_test_type { STAT_TEST_TYPE_MAX }; -static int configured_mode; static bool opt_pkt_dump; -static u32 num_frames = DEFAULT_PKT_CNT / 4; -static bool second_step; static int test_type; static bool opt_verbose; - -static u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST; -static u32 xdp_bind_flags = XDP_USE_NEED_WAKEUP | XDP_COPY; static int stat_test_type; -static u32 rxqsize; -static u32 frame_headroom; struct xsk_umem_info { struct xsk_ring_prod fq; struct xsk_ring_cons cq; struct xsk_umem *umem; + u32 num_frames; + u32 frame_headroom; void *buffer; + u32 frame_size; + bool unaligned_mode; }; struct xsk_socket_info { @@ -95,51 +100,63 @@ struct xsk_socket_info { struct xsk_umem_info *umem; struct xsk_socket *xsk; u32 outstanding_tx; -}; - -struct flow_vector { - enum fvector { - tx, - rx, - } vector; + u32 rxqsize; }; struct pkt { u64 addr; u32 len; u32 payload; + bool valid; }; struct pkt_stream { u32 nb_pkts; + u32 rx_pkt_nb; struct pkt *pkts; + bool use_addr_for_fill; }; +typedef void *(*thread_func_t)(void *arg); + struct ifobject { char ifname[MAX_INTERFACE_NAME_CHARS]; char nsname[MAX_INTERFACES_NAMESPACE_CHARS]; struct xsk_socket_info *xsk; - struct xsk_socket_info **xsk_arr; - struct xsk_umem_info **umem_arr; + struct xsk_socket_info *xsk_arr; struct xsk_umem_info *umem; - void *(*func_ptr)(void *arg); - struct flow_vector fv; + struct xsk_umem_info *umem_arr; + thread_func_t func_ptr; struct pkt_stream *pkt_stream; int ns_fd; u32 dst_ip; u32 src_ip; + u32 xdp_flags; + u32 bind_flags; u16 src_port; u16 dst_port; + bool tx_on; + bool rx_on; + bool use_poll; + bool pacing_on; u8 dst_mac[ETH_ALEN]; u8 src_mac[ETH_ALEN]; }; -static struct ifobject *ifdict[MAX_INTERFACES]; -static struct ifobject *ifdict_rx; -static struct ifobject *ifdict_tx; +struct test_spec { + struct ifobject *ifobj_tx; + struct ifobject *ifobj_rx; + struct pkt_stream *pkt_stream_default; + u16 total_steps; + u16 current_step; + u16 nb_sockets; + char name[MAX_TEST_NAME_SIZE]; +}; -/*threads*/ pthread_barrier_t barr; -pthread_t t0, t1; +pthread_mutex_t pacing_mutex = PTHREAD_MUTEX_INITIALIZER; +pthread_cond_t pacing_cond = PTHREAD_COND_INITIALIZER; + +u32 pkts_in_flight; #endif /* XDPXCEIVER_H */ diff --git a/tools/testing/selftests/cgroup/Makefile b/tools/testing/selftests/cgroup/Makefile index 59e2224605..745fe25fa0 100644 --- a/tools/testing/selftests/cgroup/Makefile +++ b/tools/testing/selftests/cgroup/Makefile @@ -11,10 +11,12 @@ TEST_GEN_PROGS += test_core TEST_GEN_PROGS += test_freezer TEST_GEN_PROGS += test_kill +LOCAL_HDRS += $(selfdir)/clone3/clone3_selftests.h $(selfdir)/pidfd/pidfd.h + include ../lib.mk -$(OUTPUT)/test_memcontrol: cgroup_util.c ../clone3/clone3_selftests.h -$(OUTPUT)/test_kmem: cgroup_util.c ../clone3/clone3_selftests.h -$(OUTPUT)/test_core: cgroup_util.c ../clone3/clone3_selftests.h -$(OUTPUT)/test_freezer: cgroup_util.c ../clone3/clone3_selftests.h -$(OUTPUT)/test_kill: cgroup_util.c ../clone3/clone3_selftests.h ../pidfd/pidfd.h +$(OUTPUT)/test_memcontrol: cgroup_util.c +$(OUTPUT)/test_kmem: cgroup_util.c +$(OUTPUT)/test_core: cgroup_util.c +$(OUTPUT)/test_freezer: cgroup_util.c +$(OUTPUT)/test_kill: cgroup_util.c diff --git a/tools/testing/selftests/cgroup/cgroup_util.h b/tools/testing/selftests/cgroup/cgroup_util.h index 82e59cdf16..4f66d10626 100644 --- a/tools/testing/selftests/cgroup/cgroup_util.h +++ b/tools/testing/selftests/cgroup/cgroup_util.h @@ -2,9 +2,9 @@ #include #include -#define PAGE_SIZE 4096 +#include "../kselftest.h" -#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0])) +#define PAGE_SIZE 4096 #define MB(x) (x << 20) diff --git a/tools/testing/selftests/cgroup/test_core.c b/tools/testing/selftests/cgroup/test_core.c index 3df648c378..6001235030 100644 --- a/tools/testing/selftests/cgroup/test_core.c +++ b/tools/testing/selftests/cgroup/test_core.c @@ -1,11 +1,14 @@ /* SPDX-License-Identifier: GPL-2.0 */ +#define _GNU_SOURCE #include +#include #include #include #include #include #include +#include #include #include #include @@ -674,6 +677,166 @@ static int test_cgcore_thread_migration(const char *root) return ret; } +/* + * cgroup migration permission check should be performed based on the + * credentials at the time of open instead of write. + */ +static int test_cgcore_lesser_euid_open(const char *root) +{ + const uid_t test_euid = 65534; /* usually nobody, any !root is fine */ + int ret = KSFT_FAIL; + char *cg_test_a = NULL, *cg_test_b = NULL; + char *cg_test_a_procs = NULL, *cg_test_b_procs = NULL; + int cg_test_b_procs_fd = -1; + uid_t saved_uid; + + cg_test_a = cg_name(root, "cg_test_a"); + cg_test_b = cg_name(root, "cg_test_b"); + + if (!cg_test_a || !cg_test_b) + goto cleanup; + + cg_test_a_procs = cg_name(cg_test_a, "cgroup.procs"); + cg_test_b_procs = cg_name(cg_test_b, "cgroup.procs"); + + if (!cg_test_a_procs || !cg_test_b_procs) + goto cleanup; + + if (cg_create(cg_test_a) || cg_create(cg_test_b)) + goto cleanup; + + if (cg_enter_current(cg_test_a)) + goto cleanup; + + if (chown(cg_test_a_procs, test_euid, -1) || + chown(cg_test_b_procs, test_euid, -1)) + goto cleanup; + + saved_uid = geteuid(); + if (seteuid(test_euid)) + goto cleanup; + + cg_test_b_procs_fd = open(cg_test_b_procs, O_RDWR); + + if (seteuid(saved_uid)) + goto cleanup; + + if (cg_test_b_procs_fd < 0) + goto cleanup; + + if (write(cg_test_b_procs_fd, "0", 1) >= 0 || errno != EACCES) + goto cleanup; + + ret = KSFT_PASS; + +cleanup: + cg_enter_current(root); + if (cg_test_b_procs_fd >= 0) + close(cg_test_b_procs_fd); + if (cg_test_b) + cg_destroy(cg_test_b); + if (cg_test_a) + cg_destroy(cg_test_a); + free(cg_test_b_procs); + free(cg_test_a_procs); + free(cg_test_b); + free(cg_test_a); + return ret; +} + +struct lesser_ns_open_thread_arg { + const char *path; + int fd; + int err; +}; + +static int lesser_ns_open_thread_fn(void *arg) +{ + struct lesser_ns_open_thread_arg *targ = arg; + + targ->fd = open(targ->path, O_RDWR); + targ->err = errno; + return 0; +} + +/* + * cgroup migration permission check should be performed based on the cgroup + * namespace at the time of open instead of write. + */ +static int test_cgcore_lesser_ns_open(const char *root) +{ + static char stack[65536]; + const uid_t test_euid = 65534; /* usually nobody, any !root is fine */ + int ret = KSFT_FAIL; + char *cg_test_a = NULL, *cg_test_b = NULL; + char *cg_test_a_procs = NULL, *cg_test_b_procs = NULL; + int cg_test_b_procs_fd = -1; + struct lesser_ns_open_thread_arg targ = { .fd = -1 }; + pid_t pid; + int status; + + cg_test_a = cg_name(root, "cg_test_a"); + cg_test_b = cg_name(root, "cg_test_b"); + + if (!cg_test_a || !cg_test_b) + goto cleanup; + + cg_test_a_procs = cg_name(cg_test_a, "cgroup.procs"); + cg_test_b_procs = cg_name(cg_test_b, "cgroup.procs"); + + if (!cg_test_a_procs || !cg_test_b_procs) + goto cleanup; + + if (cg_create(cg_test_a) || cg_create(cg_test_b)) + goto cleanup; + + if (cg_enter_current(cg_test_b)) + goto cleanup; + + if (chown(cg_test_a_procs, test_euid, -1) || + chown(cg_test_b_procs, test_euid, -1)) + goto cleanup; + + targ.path = cg_test_b_procs; + pid = clone(lesser_ns_open_thread_fn, stack + sizeof(stack), + CLONE_NEWCGROUP | CLONE_FILES | CLONE_VM | SIGCHLD, + &targ); + if (pid < 0) + goto cleanup; + + if (waitpid(pid, &status, 0) < 0) + goto cleanup; + + if (!WIFEXITED(status)) + goto cleanup; + + cg_test_b_procs_fd = targ.fd; + if (cg_test_b_procs_fd < 0) + goto cleanup; + + if (cg_enter_current(cg_test_a)) + goto cleanup; + + if ((status = write(cg_test_b_procs_fd, "0", 1)) >= 0 || errno != ENOENT) + goto cleanup; + + ret = KSFT_PASS; + +cleanup: + cg_enter_current(root); + if (cg_test_b_procs_fd >= 0) + close(cg_test_b_procs_fd); + if (cg_test_b) + cg_destroy(cg_test_b); + if (cg_test_a) + cg_destroy(cg_test_a); + free(cg_test_b_procs); + free(cg_test_a_procs); + free(cg_test_b); + free(cg_test_a); + return ret; +} + #define T(x) { x, #x } struct corecg_test { int (*fn)(const char *root); @@ -689,6 +852,8 @@ struct corecg_test { T(test_cgcore_proc_migration), T(test_cgcore_thread_migration), T(test_cgcore_destroy), + T(test_cgcore_lesser_euid_open), + T(test_cgcore_lesser_ns_open), }; #undef T diff --git a/tools/testing/selftests/core/close_range_test.c b/tools/testing/selftests/core/close_range_test.c index aa7d13d919..749239930c 100644 --- a/tools/testing/selftests/core/close_range_test.c +++ b/tools/testing/selftests/core/close_range_test.c @@ -50,10 +50,6 @@ static inline int sys_close_range(unsigned int fd, unsigned int max_fd, return syscall(__NR_close_range, fd, max_fd, flags); } -#ifndef ARRAY_SIZE -#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) -#endif - TEST(core_close_range) { int i, ret; diff --git a/tools/testing/selftests/cpufreq/main.sh b/tools/testing/selftests/cpufreq/main.sh index 31f8c9a76c..60ce18ed06 100644 --- 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 f0aa954b5d..937d36ae9a 100644 --- a/tools/testing/selftests/damon/Makefile +++ b/tools/testing/selftests/damon/Makefile @@ -3,7 +3,8 @@ TEST_GEN_FILES += huge_count_read_write -TEST_FILES = _chk_dependency.sh -TEST_PROGS = debugfs_attrs.sh +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 include ../lib.mk diff --git a/tools/testing/selftests/damon/debugfs_attrs.sh b/tools/testing/selftests/damon/debugfs_attrs.sh index ecda972e87..902e312bca 100644 --- a/tools/testing/selftests/damon/debugfs_attrs.sh +++ b/tools/testing/selftests/damon/debugfs_attrs.sh @@ -1,48 +1,7 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 -test_write_result() { - file=$1 - content=$2 - orig_content=$3 - expect_reason=$4 - expected=$5 - - echo "$content" > "$file" - if [ $? -ne "$expected" ] - then - echo "writing $content to $file doesn't return $expected" - echo "expected because: $expect_reason" - echo "$orig_content" > "$file" - exit 1 - fi -} - -test_write_succ() { - test_write_result "$1" "$2" "$3" "$4" 0 -} - -test_write_fail() { - test_write_result "$1" "$2" "$3" "$4" 1 -} - -test_content() { - file=$1 - orig_content=$2 - expected=$3 - expect_reason=$4 - - content=$(cat "$file") - if [ "$content" != "$expected" ] - then - echo "reading $file expected $expected but $content" - echo "expected because: $expect_reason" - echo "$orig_content" > "$file" - exit 1 - fi -} - -source ./_chk_dependency.sh +source _debugfs_common.sh # Test attrs file # =============== @@ -56,38 +15,3 @@ test_write_fail "$file" "1 2 3 5 4" "$orig_content" \ "min_nr_regions > max_nr_regions" test_content "$file" "$orig_content" "1 2 3 4 5" "successfully written" echo "$orig_content" > "$file" - -# Test target_ids file -# ==================== - -file="$DBGFS/target_ids" -orig_content=$(cat "$file") - -test_write_succ "$file" "1 2 3 4" "$orig_content" "valid input" -test_write_succ "$file" "1 2 abc 4" "$orig_content" "still valid input" -test_content "$file" "$orig_content" "1 2" "non-integer was there" -test_write_succ "$file" "abc 2 3" "$orig_content" "the file allows wrong input" -test_content "$file" "$orig_content" "" "wrong input written" -test_write_succ "$file" "" "$orig_content" "empty input" -test_content "$file" "$orig_content" "" "empty input written" -echo "$orig_content" > "$file" - -# Test huge count read write -# ========================== - -dmesg -C - -for file in "$DBGFS/"* -do - ./huge_count_read_write "$file" -done - -if dmesg | grep -q WARNING -then - dmesg - exit 1 -else - exit 0 -fi - -echo "PASS" diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_control.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_control.sh index a37273473c..d3a891d421 100644 --- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_control.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_control.sh @@ -87,6 +87,7 @@ ALL_TESTS=" NUM_NETIFS=4 source $lib_dir/lib.sh source $lib_dir/devlink_lib.sh +source mlxsw_lib.sh h1_create() { @@ -626,8 +627,7 @@ ipv6_redirect_test() ptp_event_test() { - # PTP is only supported on Spectrum-1, for now. - [[ "$DEVLINK_VIDDID" != "15b3:cb84" ]] && return + mlxsw_only_on_spectrum 1 || return # PTP Sync (0) devlink_trap_stats_test "PTP Time-Critical Event Message" "ptp_event" \ @@ -638,8 +638,7 @@ ptp_event_test() ptp_general_test() { - # PTP is only supported on Spectrum-1, for now. - [[ "$DEVLINK_VIDDID" != "15b3:cb84" ]] && return + mlxsw_only_on_spectrum 1 || return # PTP Announce (b) devlink_trap_stats_test "PTP General Message" "ptp_general" \ diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_policer.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_policer.sh index 508a702f00..0bd5ffc218 100644 --- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_policer.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_policer.sh @@ -272,13 +272,17 @@ __rate_test() rate_test() { - local id + local last_policer=$(devlink -j -p trap policer show | + jq '[.[]["'$DEVLINK_DEV'"][].policer] | max') - for id in $(devlink_trap_policer_ids_get); do - echo - log_info "Running rate test for policer $id" - __rate_test $id - done + log_info "Running rate test for policer 1" + __rate_test 1 + + log_info "Running rate test for policer $((last_policer / 2))" + __rate_test $((last_policer / 2)) + + log_info "Running rate test for policer $last_policer" + __rate_test $last_policer } __burst_test() @@ -342,13 +346,17 @@ __burst_test() burst_test() { - local id + local last_policer=$(devlink -j -p trap policer show | + jq '[.[]["'$DEVLINK_DEV'"][].policer] | max') - for id in $(devlink_trap_policer_ids_get); do - echo - log_info "Running burst size test for policer $id" - __burst_test $id - done + log_info "Running burst test for policer 1" + __burst_test 1 + + log_info "Running burst test for policer $((last_policer / 2))" + __burst_test $((last_policer / 2)) + + log_info "Running burst test for policer $last_policer" + __burst_test $last_policer } trap cleanup EXIT diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh index 8817851da7..e9a82cae8c 100644 --- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh @@ -13,7 +13,7 @@ # | # +-------------------|-----+ # | SW1 | | -# | $swp1 + | +# | $swp1 + | # | 192.0.2.2/28 | # | | # | + g1a (gre) | @@ -27,8 +27,8 @@ # | # +--|----------------------+ # | | VRF2 | -# | + $rp2 | -# | 198.51.100.2/28 | +# | + $rp2 | +# | 198.51.100.2/28 | # +-------------------------+ lib_dir=$(dirname $0)/../../../net/forwarding @@ -116,12 +116,16 @@ cleanup() forwarding_restore } -ecn_payload_get() +ipip_payload_get() { + local flags=$1; shift + local key=$1; shift + p=$(: - )"0"$( : GRE flags + )"$flags"$( : GRE flags )"0:00:"$( : Reserved + version )"08:00:"$( : ETH protocol type + )"$key"$( : Key )"4"$( : IP version )"5:"$( : IHL )"00:"$( : IP TOS @@ -137,6 +141,11 @@ ecn_payload_get() echo $p } +ecn_payload_get() +{ + echo $(ipip_payload_get "0") +} + ecn_decap_test() { local trap_name="decap_error" @@ -171,31 +180,6 @@ ecn_decap_test() tc filter del dev $swp1 egress protocol ip pref 1 handle 101 flower } -ipip_payload_get() -{ - local flags=$1; shift - local key=$1; shift - - p=$(: - )"$flags"$( : GRE flags - )"0:00:"$( : Reserved + version - )"08:00:"$( : ETH protocol type - )"$key"$( : Key - )"4"$( : IP version - )"5:"$( : IHL - )"00:"$( : IP TOS - )"00:14:"$( : IP total length - )"00:00:"$( : IP identification - )"20:00:"$( : IP flags + frag off - )"30:"$( : IP TTL - )"01:"$( : IP proto - )"E7:E6:"$( : IP header csum - )"C0:00:01:01:"$( : IP saddr : 192.0.1.1 - )"C0:00:02:01:"$( : IP daddr : 192.0.2.1 - ) - echo $p -} - no_matching_tunnel_test() { local trap_name="decap_error" @@ -239,7 +223,8 @@ decap_error_test() no_matching_tunnel_test "Decap error: Source IP check failed" \ 192.0.2.68 "0" no_matching_tunnel_test \ - "Decap error: Key exists but was not expected" $sip "2" ":E9:" + "Decap error: Key exists but was not expected" $sip "2" \ + "00:00:00:E9:" # Destroy the tunnel and create new one with key __addr_add_del g1 del 192.0.2.65/32 @@ -251,7 +236,8 @@ decap_error_test() no_matching_tunnel_test \ "Decap error: Key does not exist but was expected" $sip "0" no_matching_tunnel_test \ - "Decap error: Packet has a wrong key field" $sip "2" "E8:" + "Decap error: Packet has a wrong key field" $sip "2" \ + "00:00:00:E8:" } trap cleanup EXIT diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan.sh index 10e0f3dbc9..5f6eb965cf 100644 --- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan.sh @@ -217,9 +217,11 @@ short_payload_get() dest_mac=$(mac_get $h1) p=$(: )"08:"$( : VXLAN flags - )"01:00:00:"$( : VXLAN reserved + )"00:00:00:"$( : VXLAN reserved )"00:03:e8:"$( : VXLAN VNI : 1000 )"00:"$( : VXLAN reserved + )"$dest_mac:"$( : ETH daddr + )"00:00:00:00:00:00:"$( : ETH saddr ) echo $p } @@ -263,7 +265,8 @@ decap_error_test() corrupted_packet_test "Decap error: Reserved bits in use" \ "reserved_bits_payload_get" - corrupted_packet_test "Decap error: No L2 header" "short_payload_get" + corrupted_packet_test "Decap error: Too short inner packet" \ + "short_payload_get" } mc_smac_payload_get() diff --git a/tools/testing/selftests/drivers/net/mlxsw/mlxsw_lib.sh b/tools/testing/selftests/drivers/net/mlxsw/mlxsw_lib.sh index cbe50f260a..a95856aafd 100644 --- a/tools/testing/selftests/drivers/net/mlxsw/mlxsw_lib.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/mlxsw_lib.sh @@ -11,3 +11,53 @@ if [[ ! -v MLXSW_CHIP ]]; then exit 1 fi fi + +MLXSW_SPECTRUM_REV=$(case $MLXSW_CHIP in + mlxsw_spectrum) + echo 1 ;; + mlxsw_spectrum*) + echo ${MLXSW_CHIP#mlxsw_spectrum} ;; + *) + echo "Couldn't determine Spectrum chip revision." \ + > /dev/stderr ;; + esac) + +mlxsw_on_spectrum() +{ + local rev=$1; shift + local op="==" + local rev2=${rev%+} + + if [[ $rev2 != $rev ]]; then + op=">=" + fi + + ((MLXSW_SPECTRUM_REV $op rev2)) +} + +__mlxsw_only_on_spectrum() +{ + local rev=$1; shift + local caller=$1; shift + local src=$1; shift + + if ! mlxsw_on_spectrum "$rev"; then + log_test_skip $src:$caller "(Spectrum-$rev only)" + return 1 + fi +} + +mlxsw_only_on_spectrum() +{ + local caller=${FUNCNAME[1]} + local src=${BASH_SOURCE[1]} + local rev + + for rev in "$@"; do + if __mlxsw_only_on_spectrum "$rev" "$caller" "$src"; then + return 0 + fi + done + + return 1 +} diff --git a/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh b/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh index a217f9f677..04f03ae9d8 100644 --- a/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh @@ -10,9 +10,7 @@ lib_dir=$(dirname $0)/../../../net/forwarding ALL_TESTS=" - rif_set_addr_test rif_vrf_set_addr_test - rif_inherit_bridge_addr_test rif_non_inherit_bridge_addr_test vlan_interface_deletion_test bridge_deletion_test @@ -60,55 +58,6 @@ cleanup() ip link set dev $swp1 down } -rif_set_addr_test() -{ - local swp1_mac=$(mac_get $swp1) - local swp2_mac=$(mac_get $swp2) - - RET=0 - - # $swp1 and $swp2 likely got their IPv6 local addresses already, but - # here we need to test the transition to RIF. - ip addr flush dev $swp1 - ip addr flush dev $swp2 - sleep .1 - - ip addr add dev $swp1 192.0.2.1/28 - check_err $? - - ip link set dev $swp1 addr 00:11:22:33:44:55 - check_err $? - - # IP address enablement should be rejected if the MAC address prefix - # doesn't match other RIFs. - ip addr add dev $swp2 192.0.2.2/28 &>/dev/null - check_fail $? "IP address addition passed for a device with a wrong MAC" - ip addr add dev $swp2 192.0.2.2/28 2>&1 >/dev/null \ - | grep -q mlxsw_spectrum - check_err $? "no extack for IP address addition" - - ip link set dev $swp2 addr 00:11:22:33:44:66 - check_err $? - ip addr add dev $swp2 192.0.2.2/28 &>/dev/null - check_err $? - - # Change of MAC address of a RIF should be forbidden if the new MAC - # doesn't share the prefix with other MAC addresses. - ip link set dev $swp2 addr 00:11:22:33:00:66 &>/dev/null - check_fail $? "change of MAC address passed for a wrong MAC" - ip link set dev $swp2 addr 00:11:22:33:00:66 2>&1 >/dev/null \ - | grep -q mlxsw_spectrum - check_err $? "no extack for MAC address change" - - log_test "RIF - bad MAC change" - - ip addr del dev $swp2 192.0.2.2/28 - ip addr del dev $swp1 192.0.2.1/28 - - ip link set dev $swp2 addr $swp2_mac - ip link set dev $swp1 addr $swp1_mac -} - rif_vrf_set_addr_test() { # Test that it is possible to set an IP address on a VRF upper despite @@ -128,45 +77,6 @@ rif_vrf_set_addr_test() ip link del dev vrf-test } -rif_inherit_bridge_addr_test() -{ - RET=0 - - # Create first RIF - ip addr add dev $swp1 192.0.2.1/28 - check_err $? - - # Create a FID RIF - ip link add name br1 up type bridge vlan_filtering 0 - ip link set dev $swp2 master br1 - ip addr add dev br1 192.0.2.17/28 - check_err $? - - # Prepare a device with a low MAC address - ip link add name d up type dummy - ip link set dev d addr 00:11:22:33:44:55 - - # Attach the device to br1. That prompts bridge address change, which - # should be vetoed, thus preventing the attachment. - ip link set dev d master br1 &>/dev/null - check_fail $? "Device with low MAC was permitted to attach a bridge with RIF" - ip link set dev d master br1 2>&1 >/dev/null \ - | grep -q mlxsw_spectrum - check_err $? "no extack for bridge attach rejection" - - ip link set dev $swp2 addr 00:11:22:33:44:55 &>/dev/null - check_fail $? "Changing swp2's MAC address permitted" - ip link set dev $swp2 addr 00:11:22:33:44:55 2>&1 >/dev/null \ - | grep -q mlxsw_spectrum - check_err $? "no extack for bridge port MAC address change rejection" - - log_test "RIF - attach port with bad MAC to bridge" - - ip link del dev d - ip link del dev br1 - ip addr del dev $swp1 192.0.2.1/28 -} - rif_non_inherit_bridge_addr_test() { local swp2_mac=$(mac_get $swp2) @@ -779,7 +689,7 @@ nexthop_obj_offload_test() setup_wait ip nexthop add id 1 via 192.0.2.2 dev $swp1 - ip neigh replace 192.0.2.2 lladdr 00:11:22:33:44:55 nud reachable \ + ip neigh replace 192.0.2.2 lladdr 00:11:22:33:44:55 nud perm \ dev $swp1 busywait "$TIMEOUT" wait_for_offload \ @@ -791,7 +701,7 @@ nexthop_obj_offload_test() ip nexthop show id 1 check_err $? "nexthop marked as offloaded after setting neigh to failed state" - ip neigh replace 192.0.2.2 lladdr 00:11:22:33:44:55 nud reachable \ + ip neigh replace 192.0.2.2 lladdr 00:11:22:33:44:55 nud perm \ dev $swp1 busywait "$TIMEOUT" wait_for_offload \ ip nexthop show id 1 @@ -828,11 +738,11 @@ nexthop_obj_group_offload_test() ip nexthop add id 1 via 192.0.2.2 dev $swp1 ip nexthop add id 2 via 2001:db8:1::2 dev $swp1 ip nexthop add id 10 group 1/2 - ip neigh replace 192.0.2.2 lladdr 00:11:22:33:44:55 nud reachable \ + ip neigh replace 192.0.2.2 lladdr 00:11:22:33:44:55 nud perm \ dev $swp1 - ip neigh replace 192.0.2.3 lladdr 00:11:22:33:44:55 nud reachable \ + ip neigh replace 192.0.2.3 lladdr 00:11:22:33:44:55 nud perm \ dev $swp1 - ip neigh replace 2001:db8:1::2 lladdr 00:11:22:33:44:55 nud reachable \ + ip neigh replace 2001:db8:1::2 lladdr 00:11:22:33:44:55 nud perm \ dev $swp1 busywait "$TIMEOUT" wait_for_offload \ @@ -888,11 +798,11 @@ nexthop_obj_bucket_offload_test() ip nexthop add id 1 via 192.0.2.2 dev $swp1 ip nexthop add id 2 via 2001:db8:1::2 dev $swp1 ip nexthop add id 10 group 1/2 type resilient buckets 32 idle_timer 0 - ip neigh replace 192.0.2.2 lladdr 00:11:22:33:44:55 nud reachable \ + ip neigh replace 192.0.2.2 lladdr 00:11:22:33:44:55 nud perm \ dev $swp1 - ip neigh replace 192.0.2.3 lladdr 00:11:22:33:44:55 nud reachable \ + ip neigh replace 192.0.2.3 lladdr 00:11:22:33:44:55 nud perm \ dev $swp1 - ip neigh replace 2001:db8:1::2 lladdr 00:11:22:33:44:55 nud reachable \ + ip neigh replace 2001:db8:1::2 lladdr 00:11:22:33:44:55 nud perm \ dev $swp1 busywait "$TIMEOUT" wait_for_offload \ @@ -921,7 +831,7 @@ nexthop_obj_bucket_offload_test() check_err $? "nexthop bucket not marked as offloaded after revalidating nexthop" # Revalidate nexthop id 2 by changing its neighbour - ip neigh replace 2001:db8:1::2 lladdr 00:11:22:33:44:55 nud reachable \ + ip neigh replace 2001:db8:1::2 lladdr 00:11:22:33:44:55 nud perm \ dev $swp1 busywait "$TIMEOUT" wait_for_offload \ ip nexthop bucket show nhid 2 @@ -971,9 +881,9 @@ nexthop_obj_route_offload_test() setup_wait ip nexthop add id 1 via 192.0.2.2 dev $swp1 - ip neigh replace 192.0.2.2 lladdr 00:11:22:33:44:55 nud reachable \ + ip neigh replace 192.0.2.2 lladdr 00:11:22:33:44:55 nud perm \ dev $swp1 - ip neigh replace 192.0.2.3 lladdr 00:11:22:33:44:55 nud reachable \ + ip neigh replace 192.0.2.3 lladdr 00:11:22:33:44:55 nud perm \ dev $swp1 ip route replace 198.51.100.0/24 nhid 1 diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh index 33ddd01689..f260f01db0 100644 --- a/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh @@ -73,6 +73,7 @@ CHECK_TC="yes" lib_dir=$(dirname $0)/../../../net/forwarding source $lib_dir/lib.sh source $lib_dir/devlink_lib.sh +source mlxsw_lib.sh source qos_lib.sh ipaddr() @@ -331,6 +332,14 @@ get_nmarked() ethtool_stats_get $swp3 ecn_marked } +get_qdisc_nmarked() +{ + local vlan=$1; shift + + busywait_for_counter 1100 +1 \ + qdisc_stats_get $swp3 $(get_qdisc_handle $vlan) .marked +} + get_qdisc_npackets() { local vlan=$1; shift @@ -384,14 +393,15 @@ build_backlog() check_marking() { + local get_nmarked=$1; shift local vlan=$1; shift local cond=$1; shift local npackets_0=$(get_qdisc_npackets $vlan) - local nmarked_0=$(get_nmarked $vlan) + local nmarked_0=$($get_nmarked $vlan) sleep 5 local npackets_1=$(get_qdisc_npackets $vlan) - local nmarked_1=$(get_nmarked $vlan) + local nmarked_1=$($get_nmarked $vlan) local nmarked_d=$((nmarked_1 - nmarked_0)) local npackets_d=$((npackets_1 - npackets_0)) @@ -404,6 +414,7 @@ check_marking() ecn_test_common() { local name=$1; shift + local get_nmarked=$1; shift local vlan=$1; shift local limit=$1; shift local backlog @@ -416,7 +427,7 @@ ecn_test_common() RET=0 backlog=$(build_backlog $vlan $((2 * limit / 3)) udp) check_err $? "Could not build the requested backlog" - pct=$(check_marking $vlan "== 0") + pct=$(check_marking "$get_nmarked" $vlan "== 0") check_err $? "backlog $backlog / $limit Got $pct% marked packets, expected == 0." log_test "TC $((vlan - 10)): $name backlog < limit" @@ -426,22 +437,23 @@ ecn_test_common() RET=0 backlog=$(build_backlog $vlan $((3 * limit / 2)) tcp tos=0x01) check_err $? "Could not build the requested backlog" - pct=$(check_marking $vlan ">= 95") + pct=$(check_marking "$get_nmarked" $vlan ">= 95") check_err $? "backlog $backlog / $limit Got $pct% marked packets, expected >= 95." log_test "TC $((vlan - 10)): $name backlog > limit" } -do_ecn_test() +__do_ecn_test() { + local get_nmarked=$1; shift local vlan=$1; shift local limit=$1; shift - local name=ECN + local name=${1-ECN}; shift start_tcp_traffic $h1.$vlan $(ipaddr 1 $vlan) $(ipaddr 3 $vlan) \ $h3_mac tos=0x01 sleep 1 - ecn_test_common "$name" $vlan $limit + ecn_test_common "$name" "$get_nmarked" $vlan $limit # Up there we saw that UDP gets accepted when backlog is below the # limit. Now that it is above, it should all get dropped, and backlog @@ -455,6 +467,23 @@ do_ecn_test() sleep 1 } +do_ecn_test() +{ + local vlan=$1; shift + local limit=$1; shift + + __do_ecn_test get_nmarked "$vlan" "$limit" +} + +do_ecn_test_perband() +{ + local vlan=$1; shift + local limit=$1; shift + + mlxsw_only_on_spectrum 3+ || return + __do_ecn_test get_qdisc_nmarked "$vlan" "$limit" "per-band ECN" +} + do_ecn_nodrop_test() { local vlan=$1; shift @@ -465,7 +494,7 @@ do_ecn_nodrop_test() $h3_mac tos=0x01 sleep 1 - ecn_test_common "$name" $vlan $limit + ecn_test_common "$name" get_nmarked $vlan $limit # Up there we saw that UDP gets accepted when backlog is below the # limit. Now that it is above, in nodrop mode, make sure it goes to @@ -495,7 +524,7 @@ do_red_test() RET=0 backlog=$(build_backlog $vlan $((2 * limit / 3)) tcp tos=0x01) check_err $? "Could not build the requested backlog" - pct=$(check_marking $vlan "== 0") + pct=$(check_marking get_nmarked $vlan "== 0") check_err $? "backlog $backlog / $limit Got $pct% marked packets, expected == 0." log_test "TC $((vlan - 10)): RED backlog < limit" @@ -503,7 +532,7 @@ do_red_test() RET=0 backlog=$(build_backlog $vlan $((3 * limit / 2)) tcp tos=0x01) check_fail $? "Traffic went into backlog instead of being early-dropped" - pct=$(check_marking $vlan "== 0") + pct=$(check_marking get_nmarked $vlan "== 0") check_err $? "backlog $backlog / $limit Got $pct% marked packets, expected == 0." local diff=$((limit - backlog)) pct=$((100 * diff / limit)) @@ -544,6 +573,55 @@ do_mc_backlog_test() log_test "TC $((vlan - 10)): Qdisc reports MC backlog" } +do_mark_test() +{ + local vlan=$1; shift + local limit=$1; shift + local subtest=$1; shift + local fetch_counter=$1; shift + local should_fail=$1; shift + local base + + mlxsw_only_on_spectrum 2+ || return + + RET=0 + + start_tcp_traffic $h1.$vlan $(ipaddr 1 $vlan) $(ipaddr 3 $vlan) \ + $h3_mac tos=0x01 + + # Create a bit of a backlog and observe no mirroring due to marks. + qevent_rule_install_$subtest + + build_backlog $vlan $((2 * limit / 3)) tcp tos=0x01 >/dev/null + + base=$($fetch_counter) + count=$(busywait 1100 until_counter_is ">= $((base + 1))" \ + $fetch_counter) + check_fail $? "Spurious packets ($base -> $count) observed without buffer pressure" + + # Above limit, everything should be mirrored, we should see lots of + # packets. + build_backlog $vlan $((3 * limit / 2)) tcp tos=0x01 >/dev/null + busywait_for_counter 1100 +10000 \ + $fetch_counter > /dev/null + check_err_fail "$should_fail" $? "ECN-marked packets $subtest'd" + + # When the rule is uninstalled, there should be no mirroring. + qevent_rule_uninstall_$subtest + busywait_for_counter 1100 +10 \ + $fetch_counter > /dev/null + check_fail $? "Spurious packets observed after uninstall" + + if ((should_fail)); then + log_test "TC $((vlan - 10)): marked packets not $subtest'd" + else + log_test "TC $((vlan - 10)): marked packets $subtest'd" + fi + + stop_traffic + sleep 1 +} + do_drop_test() { local vlan=$1; shift @@ -551,10 +629,10 @@ do_drop_test() local trigger=$1; shift local subtest=$1; shift local fetch_counter=$1; shift - local backlog local base local now - local pct + + mlxsw_only_on_spectrum 2+ || return RET=0 @@ -628,6 +706,22 @@ do_drop_mirror_test() tc filter del dev $h2 ingress pref 1 handle 101 flower } +do_mark_mirror_test() +{ + local vlan=$1; shift + local limit=$1; shift + + tc filter add dev $h2 ingress pref 1 handle 101 prot ip \ + flower skip_sw ip_proto tcp \ + action drop + + do_mark_test "$vlan" "$limit" mirror \ + qevent_counter_fetch_mirror \ + $(: should_fail=)0 + + tc filter del dev $h2 ingress pref 1 handle 101 flower +} + qevent_rule_install_trap() { tc filter add block 10 pref 1234 handle 102 matchall skip_sw \ @@ -655,3 +749,14 @@ do_drop_trap_test() do_drop_test "$vlan" "$limit" "$trap_name" trap \ "qevent_counter_fetch_trap $trap_name" } + +qevent_rule_install_trap_fwd() +{ + tc filter add block 10 pref 1234 handle 102 matchall skip_sw \ + action trap_fwd hw_stats disabled +} + +qevent_rule_uninstall_trap_fwd() +{ + tc filter del block 10 pref 1234 handle 102 matchall +} diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh index f3ef3274f9..1e5ad32094 100644 --- a/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh @@ -4,11 +4,13 @@ ALL_TESTS=" ping_ipv4 ecn_test + ecn_test_perband ecn_nodrop_test red_test mc_backlog_test red_mirror_test red_trap_test + ecn_mirror_test " : ${QDISC:=ets} source sch_red_core.sh @@ -21,26 +23,58 @@ source sch_red_core.sh BACKLOG1=200000 BACKLOG2=500000 -install_qdisc() +install_root_qdisc() +{ + tc qdisc add dev $swp3 root handle 10: $QDISC \ + bands 8 priomap 7 6 5 4 3 2 1 0 +} + +install_qdisc_tc0() { local -a args=("$@") - tc qdisc add dev $swp3 root handle 10: $QDISC \ - bands 8 priomap 7 6 5 4 3 2 1 0 tc qdisc add dev $swp3 parent 10:8 handle 108: red \ limit 1000000 min $BACKLOG1 max $((BACKLOG1 + 1)) \ probability 1.0 avpkt 8000 burst 38 "${args[@]}" +} + +install_qdisc_tc1() +{ + local -a args=("$@") + tc qdisc add dev $swp3 parent 10:7 handle 107: red \ limit 1000000 min $BACKLOG2 max $((BACKLOG2 + 1)) \ probability 1.0 avpkt 8000 burst 63 "${args[@]}" +} + +install_qdisc() +{ + install_root_qdisc + install_qdisc_tc0 "$@" + install_qdisc_tc1 "$@" sleep 1 } +uninstall_qdisc_tc0() +{ + tc qdisc del dev $swp3 parent 10:8 +} + +uninstall_qdisc_tc1() +{ + tc qdisc del dev $swp3 parent 10:7 +} + +uninstall_root_qdisc() +{ + tc qdisc del dev $swp3 root +} + uninstall_qdisc() { - tc qdisc del dev $swp3 parent 10:7 - tc qdisc del dev $swp3 parent 10:8 - tc qdisc del dev $swp3 root + uninstall_qdisc_tc0 + uninstall_qdisc_tc1 + uninstall_root_qdisc } ecn_test() @@ -53,6 +87,16 @@ ecn_test() uninstall_qdisc } +ecn_test_perband() +{ + install_qdisc ecn + + do_ecn_test_perband 10 $BACKLOG1 + do_ecn_test_perband 11 $BACKLOG2 + + uninstall_qdisc +} + ecn_nodrop_test() { install_qdisc ecn nodrop @@ -112,6 +156,16 @@ red_trap_test() uninstall_qdisc } +ecn_mirror_test() +{ + install_qdisc ecn qevent mark block 10 + + do_mark_mirror_test 10 $BACKLOG1 + do_mark_mirror_test 11 $BACKLOG2 + + uninstall_qdisc +} + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_root.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_root.sh index ede9c38d3e..d79a82f317 100644 --- a/tools/testing/selftests/drivers/net/mlxsw/sch_red_root.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_root.sh @@ -4,6 +4,7 @@ ALL_TESTS=" ping_ipv4 ecn_test + ecn_test_perband ecn_nodrop_test red_test mc_backlog_test @@ -35,6 +36,13 @@ ecn_test() uninstall_qdisc } +ecn_test_perband() +{ + install_qdisc ecn + do_ecn_test_perband 10 $BACKLOG + uninstall_qdisc +} + ecn_nodrop_test() { install_qdisc ecn nodrop diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh index 50654f8a8c..e9f65bd2e2 100644 --- a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh @@ -7,12 +7,9 @@ NUM_NETIFS=6 source $lib_dir/lib.sh source $lib_dir/tc_common.sh source $lib_dir/devlink_lib.sh +source ../mlxsw_lib.sh -if [[ "$DEVLINK_VIDDID" != "15b3:cf6c" && \ - "$DEVLINK_VIDDID" != "15b3:cf70" ]]; then - echo "SKIP: test is tailored for Mellanox Spectrum-2 and Spectrum-3" - exit 1 -fi +mlxsw_only_on_spectrum 2+ || exit 1 current_test="" @@ -28,7 +25,7 @@ cleanup() trap cleanup EXIT -ALL_TESTS="router tc_flower mirror_gre tc_police port" +ALL_TESTS="router tc_flower mirror_gre tc_police port rif_mac_profile" for current_test in ${TESTS:-$ALL_TESTS}; do RET_FIN=0 source ${current_test}_scale.sh diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum/devlink_lib_spectrum.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum/devlink_lib_spectrum.sh index 73035e2508..06a80f40da 100644 --- a/tools/testing/selftests/drivers/net/mlxsw/spectrum/devlink_lib_spectrum.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum/devlink_lib_spectrum.sh @@ -2,11 +2,9 @@ # SPDX-License-Identifier: GPL-2.0 source "../../../../net/forwarding/devlink_lib.sh" +source ../mlxsw_lib.sh -if [ "$DEVLINK_VIDDID" != "15b3:cb84" ]; then - echo "SKIP: test is tailored for Mellanox Spectrum" - exit 1 -fi +mlxsw_only_on_spectrum 1 || exit 1 # Needed for returning to default declare -A KVD_DEFAULTS 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 b9b8274643..dea33dc937 100644 --- a/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh @@ -22,7 +22,7 @@ cleanup() devlink_sp_read_kvd_defaults trap cleanup EXIT -ALL_TESTS="router tc_flower mirror_gre tc_police port" +ALL_TESTS="router tc_flower mirror_gre tc_police port rif_mac_profile" for current_test in ${TESTS:-$ALL_TESTS}; do RET_FIN=0 source ${current_test}_scale.sh diff --git a/tools/testing/selftests/drivers/net/mlxsw/tc_restrictions.sh b/tools/testing/selftests/drivers/net/mlxsw/tc_restrictions.sh index 5ec3beb637..0441a18f09 100644 --- a/tools/testing/selftests/drivers/net/mlxsw/tc_restrictions.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/tc_restrictions.sh @@ -20,6 +20,7 @@ NUM_NETIFS=2 source $lib_dir/tc_common.sh source $lib_dir/lib.sh source $lib_dir/devlink_lib.sh +source mlxsw_lib.sh switch_create() { @@ -169,7 +170,7 @@ matchall_sample_egress_test() # It is forbidden in mlxsw driver to have matchall with sample action # bound on egress. Spectrum-1 specific restriction - [[ "$DEVLINK_VIDDID" != "15b3:cb84" ]] && return + mlxsw_only_on_spectrum 1 || return tc qdisc add dev $swp1 clsact diff --git a/tools/testing/selftests/drivers/net/mlxsw/tc_sample.sh b/tools/testing/selftests/drivers/net/mlxsw/tc_sample.sh index 373d5f2a84..83a0210e75 100644 --- a/tools/testing/selftests/drivers/net/mlxsw/tc_sample.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/tc_sample.sh @@ -51,6 +51,7 @@ NUM_NETIFS=8 CAPTURE_FILE=$(mktemp) source $lib_dir/lib.sh source $lib_dir/devlink_lib.sh +source mlxsw_lib.sh # Available at https://github.com/Mellanox/libpsample require_command psample @@ -431,7 +432,7 @@ tc_sample_md_out_tc_test() RET=0 # Output traffic class is not supported on Spectrum-1. - [[ "$DEVLINK_VIDDID" == "15b3:cb84" ]] && return + mlxsw_only_on_spectrum 2+ || return tc filter add dev $rp1 ingress protocol all pref 1 handle 101 matchall \ skip_sw action sample rate 5 group 1 @@ -477,7 +478,7 @@ tc_sample_md_out_tc_occ_test() RET=0 # Output traffic class occupancy is not supported on Spectrum-1. - [[ "$DEVLINK_VIDDID" == "15b3:cb84" ]] && return + mlxsw_only_on_spectrum 2+ || return tc filter add dev $rp1 ingress protocol all pref 1 handle 101 matchall \ skip_sw action sample rate 1024 group 1 @@ -521,7 +522,7 @@ tc_sample_md_latency_test() RET=0 # Egress sampling not supported on Spectrum-1. - [[ "$DEVLINK_VIDDID" == "15b3:cb84" ]] && return + mlxsw_only_on_spectrum 2+ || return tc filter add dev $rp2 egress protocol all pref 1 handle 101 matchall \ skip_sw action sample rate 5 group 1 @@ -550,7 +551,7 @@ tc_sample_acl_group_conflict_test() # port with different groups. # Policy-based sampling is not supported on Spectrum-1. - [[ "$DEVLINK_VIDDID" == "15b3:cb84" ]] && return + mlxsw_only_on_spectrum 2+ || return tc filter add dev $rp1 ingress protocol ip pref 1 handle 101 flower \ skip_sw action sample rate 1024 group 1 @@ -579,7 +580,7 @@ __tc_sample_acl_rate_test() RET=0 # Policy-based sampling is not supported on Spectrum-1. - [[ "$DEVLINK_VIDDID" == "15b3:cb84" ]] && return + mlxsw_only_on_spectrum 2+ || return tc filter add dev $port $bind protocol ip pref 1 handle 101 flower \ skip_sw dst_ip 198.51.100.1 action sample rate 32 group 1 @@ -631,7 +632,7 @@ tc_sample_acl_max_rate_test() RET=0 # Policy-based sampling is not supported on Spectrum-1. - [[ "$DEVLINK_VIDDID" == "15b3:cb84" ]] && return + mlxsw_only_on_spectrum 2+ || return tc filter add dev $rp1 ingress protocol ip pref 1 handle 101 flower \ skip_sw action sample rate $((2 ** 24 - 1)) group 1 diff --git a/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh b/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh index 729a86cc4e..99a332b712 100644 --- a/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh @@ -4,10 +4,35 @@ # Test various aspects of VxLAN offloading which are specific to mlxsw, such # as sanitization of invalid configurations and offload indication. -lib_dir=$(dirname $0)/../../../net/forwarding +: ${ADDR_FAMILY:=ipv4} +export ADDR_FAMILY -ALL_TESTS="sanitization_test offload_indication_test \ - sanitization_vlan_aware_test offload_indication_vlan_aware_test" +: ${LOCAL_IP_1:=198.51.100.1} +export LOCAL_IP_1 + +: ${LOCAL_IP_2:=198.51.100.2} +export LOCAL_IP_2 + +: ${PREFIX_LEN:=32} +export PREFIX_LEN + +: ${UDPCSUM_FLAFS:=noudpcsum} +export UDPCSUM_FLAFS + +: ${MC_IP:=239.0.0.1} +export MC_IP + +: ${IP_FLAG:=""} +export IP_FLAG + +: ${ALL_TESTS:=" + sanitization_test + offload_indication_test + sanitization_vlan_aware_test + offload_indication_vlan_aware_test +"} + +lib_dir=$(dirname $0)/../../../net/forwarding NUM_NETIFS=2 : ${TIMEOUT:=20000} # ms source $lib_dir/lib.sh @@ -63,8 +88,8 @@ sanitization_single_dev_valid_test() ip link add dev br0 type bridge mcast_snooping 0 - ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \ - ttl 20 tos inherit local 198.51.100.1 dstport 4789 + ip link add name vxlan0 up type vxlan id 10 nolearning $UDPCSUM_FLAFS \ + ttl 20 tos inherit local $LOCAL_IP_1 dstport 4789 sanitization_single_dev_test_pass @@ -80,8 +105,8 @@ sanitization_single_dev_vlan_aware_test() ip link add dev br0 type bridge mcast_snooping 0 vlan_filtering 1 - ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \ - ttl 20 tos inherit local 198.51.100.1 dstport 4789 + ip link add name vxlan0 up type vxlan id 10 nolearning $UDPCSUM_FLAFS \ + ttl 20 tos inherit local $LOCAL_IP_1 dstport 4789 sanitization_single_dev_test_pass @@ -97,8 +122,8 @@ sanitization_single_dev_mcast_enabled_test() ip link add dev br0 type bridge - ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \ - ttl 20 tos inherit local 198.51.100.1 dstport 4789 + ip link add name vxlan0 up type vxlan id 10 nolearning $UDPCSUM_FLAFS \ + ttl 20 tos inherit local $LOCAL_IP_1 dstport 4789 sanitization_single_dev_test_fail @@ -115,9 +140,9 @@ sanitization_single_dev_mcast_group_test() ip link add dev br0 type bridge mcast_snooping 0 ip link add name dummy1 up type dummy - ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \ - ttl 20 tos inherit local 198.51.100.1 dstport 4789 \ - dev dummy1 group 239.0.0.1 + ip link add name vxlan0 up type vxlan id 10 nolearning $UDPCSUM_FLAFS \ + ttl 20 tos inherit local $LOCAL_IP_1 dstport 4789 \ + dev dummy1 group $MC_IP sanitization_single_dev_test_fail @@ -134,7 +159,7 @@ sanitization_single_dev_no_local_ip_test() ip link add dev br0 type bridge mcast_snooping 0 - ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \ + ip link add name vxlan0 up type vxlan id 10 nolearning $UDPCSUM_FLAFS \ ttl 20 tos inherit dstport 4789 sanitization_single_dev_test_fail @@ -145,31 +170,14 @@ sanitization_single_dev_no_local_ip_test() log_test "vxlan device with no local ip" } -sanitization_single_dev_local_ipv6_test() +sanitization_single_dev_learning_enabled_ipv4_test() { RET=0 ip link add dev br0 type bridge mcast_snooping 0 - ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \ - ttl 20 tos inherit local 2001:db8::1 dstport 4789 - - sanitization_single_dev_test_fail - - ip link del dev vxlan0 - ip link del dev br0 - - log_test "vxlan device with local ipv6 address" -} - -sanitization_single_dev_learning_enabled_test() -{ - RET=0 - - ip link add dev br0 type bridge mcast_snooping 0 - - ip link add name vxlan0 up type vxlan id 10 learning noudpcsum \ - ttl 20 tos inherit local 198.51.100.1 dstport 4789 + ip link add name vxlan0 up type vxlan id 10 learning $UDPCSUM_FLAFS \ + ttl 20 tos inherit local $LOCAL_IP_1 dstport 4789 sanitization_single_dev_test_pass @@ -186,8 +194,8 @@ sanitization_single_dev_local_interface_test() ip link add dev br0 type bridge mcast_snooping 0 ip link add name dummy1 up type dummy - ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \ - ttl 20 tos inherit local 198.51.100.1 dstport 4789 dev dummy1 + ip link add name vxlan0 up type vxlan id 10 nolearning $UDPCSUM_FLAFS \ + ttl 20 tos inherit local $LOCAL_IP_1 dstport 4789 dev dummy1 sanitization_single_dev_test_fail @@ -204,8 +212,8 @@ sanitization_single_dev_port_range_test() ip link add dev br0 type bridge mcast_snooping 0 - ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \ - ttl 20 tos inherit local 198.51.100.1 dstport 4789 \ + ip link add name vxlan0 up type vxlan id 10 nolearning $UDPCSUM_FLAFS \ + ttl 20 tos inherit local $LOCAL_IP_1 dstport 4789 \ srcport 4000 5000 sanitization_single_dev_test_fail @@ -222,8 +230,8 @@ sanitization_single_dev_tos_static_test() ip link add dev br0 type bridge mcast_snooping 0 - ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \ - ttl 20 tos 20 local 198.51.100.1 dstport 4789 + ip link add name vxlan0 up type vxlan id 10 nolearning $UDPCSUM_FLAFS \ + ttl 20 tos 20 local $LOCAL_IP_1 dstport 4789 sanitization_single_dev_test_fail @@ -239,8 +247,8 @@ sanitization_single_dev_ttl_inherit_test() ip link add dev br0 type bridge mcast_snooping 0 - ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \ - ttl inherit tos inherit local 198.51.100.1 dstport 4789 + ip link add name vxlan0 up type vxlan id 10 nolearning $UDPCSUM_FLAFS \ + ttl inherit tos inherit local $LOCAL_IP_1 dstport 4789 sanitization_single_dev_test_fail @@ -250,14 +258,14 @@ sanitization_single_dev_ttl_inherit_test() log_test "vxlan device with inherit ttl" } -sanitization_single_dev_udp_checksum_test() +sanitization_single_dev_udp_checksum_ipv4_test() { RET=0 ip link add dev br0 type bridge mcast_snooping 0 ip link add name vxlan0 up type vxlan id 10 nolearning udpcsum \ - ttl 20 tos inherit local 198.51.100.1 dstport 4789 + ttl 20 tos inherit local $LOCAL_IP_1 dstport 4789 sanitization_single_dev_test_fail @@ -276,13 +284,12 @@ sanitization_single_dev_test() sanitization_single_dev_mcast_enabled_test sanitization_single_dev_mcast_group_test sanitization_single_dev_no_local_ip_test - sanitization_single_dev_local_ipv6_test - sanitization_single_dev_learning_enabled_test + sanitization_single_dev_learning_enabled_"$ADDR_FAMILY"_test sanitization_single_dev_local_interface_test sanitization_single_dev_port_range_test sanitization_single_dev_tos_static_test sanitization_single_dev_ttl_inherit_test - sanitization_single_dev_udp_checksum_test + sanitization_single_dev_udp_checksum_"$ADDR_FAMILY"_test } sanitization_multi_devs_test_pass() @@ -334,10 +341,10 @@ sanitization_multi_devs_valid_test() ip link add dev br0 type bridge mcast_snooping 0 ip link add dev br1 type bridge mcast_snooping 0 - ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \ - ttl 20 tos inherit local 198.51.100.1 dstport 4789 - ip link add name vxlan1 up type vxlan id 20 nolearning noudpcsum \ - ttl 20 tos inherit local 198.51.100.1 dstport 4789 + ip link add name vxlan0 up type vxlan id 10 nolearning $UDPCSUM_FLAFS \ + ttl 20 tos inherit local $LOCAL_IP_1 dstport 4789 + ip link add name vxlan1 up type vxlan id 20 nolearning $UDPCSUM_FLAFS \ + ttl 20 tos inherit local $LOCAL_IP_1 dstport 4789 sanitization_multi_devs_test_pass @@ -356,10 +363,10 @@ sanitization_multi_devs_ttl_test() ip link add dev br0 type bridge mcast_snooping 0 ip link add dev br1 type bridge mcast_snooping 0 - ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \ - ttl 20 tos inherit local 198.51.100.1 dstport 4789 - ip link add name vxlan1 up type vxlan id 20 nolearning noudpcsum \ - ttl 40 tos inherit local 198.51.100.1 dstport 4789 + ip link add name vxlan0 up type vxlan id 10 nolearning $UDPCSUM_FLAFS \ + ttl 20 tos inherit local $LOCAL_IP_1 dstport 4789 + ip link add name vxlan1 up type vxlan id 20 nolearning $UDPCSUM_FLAFS \ + ttl 40 tos inherit local $LOCAL_IP_1 dstport 4789 sanitization_multi_devs_test_fail @@ -378,10 +385,10 @@ sanitization_multi_devs_udp_dstport_test() ip link add dev br0 type bridge mcast_snooping 0 ip link add dev br1 type bridge mcast_snooping 0 - ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \ - ttl 20 tos inherit local 198.51.100.1 dstport 4789 - ip link add name vxlan1 up type vxlan id 20 nolearning noudpcsum \ - ttl 20 tos inherit local 198.51.100.1 dstport 5789 + ip link add name vxlan0 up type vxlan id 10 nolearning $UDPCSUM_FLAFS \ + ttl 20 tos inherit local $LOCAL_IP_1 dstport 4789 + ip link add name vxlan1 up type vxlan id 20 nolearning $UDPCSUM_FLAFS \ + ttl 20 tos inherit local $LOCAL_IP_1 dstport 5789 sanitization_multi_devs_test_fail @@ -400,10 +407,10 @@ sanitization_multi_devs_local_ip_test() ip link add dev br0 type bridge mcast_snooping 0 ip link add dev br1 type bridge mcast_snooping 0 - ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \ - ttl 20 tos inherit local 198.51.100.1 dstport 4789 - ip link add name vxlan1 up type vxlan id 20 nolearning noudpcsum \ - ttl 20 tos inherit local 198.51.100.2 dstport 4789 + ip link add name vxlan0 up type vxlan id 10 nolearning $UDPCSUM_FLAFS \ + ttl 20 tos inherit local $LOCAL_IP_1 dstport 4789 + ip link add name vxlan1 up type vxlan id 20 nolearning $UDPCSUM_FLAFS \ + ttl 20 tos inherit local $LOCAL_IP_2 dstport 4789 sanitization_multi_devs_test_fail @@ -443,12 +450,12 @@ offload_indication_setup_create() ip link set dev $swp1 master br0 ip link set dev $swp2 master br1 - ip address add 198.51.100.1/32 dev lo + ip address add $LOCAL_IP_1/$PREFIX_LEN dev lo ip link add name vxlan0 up master br0 type vxlan id 10 nolearning \ - noudpcsum ttl 20 tos inherit local 198.51.100.1 dstport 4789 + $UDPCSUM_FLAFS ttl 20 tos inherit local $LOCAL_IP_1 dstport 4789 ip link add name vxlan1 up master br1 type vxlan id 20 nolearning \ - noudpcsum ttl 20 tos inherit local 198.51.100.1 dstport 4789 + $UDPCSUM_FLAFS ttl 20 tos inherit local $LOCAL_IP_1 dstport 4789 } offload_indication_setup_destroy() @@ -456,7 +463,7 @@ offload_indication_setup_destroy() ip link del dev vxlan1 ip link del dev vxlan0 - ip address del 198.51.100.1/32 dev lo + ip address del $LOCAL_IP_1/$PREFIX_LEN dev lo ip link set dev $swp2 nomaster ip link set dev $swp1 nomaster @@ -469,7 +476,7 @@ offload_indication_fdb_flood_test() { RET=0 - bridge fdb append 00:00:00:00:00:00 dev vxlan0 self dst 198.51.100.2 + bridge fdb append 00:00:00:00:00:00 dev vxlan0 self dst $LOCAL_IP_2 busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb 00:00:00:00:00:00 \ bridge fdb show brport vxlan0 @@ -485,7 +492,7 @@ offload_indication_fdb_bridge_test() RET=0 bridge fdb add de:ad:be:ef:13:37 dev vxlan0 self master static \ - dst 198.51.100.2 + dst $LOCAL_IP_2 busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb \ de:ad:be:ef:13:37 self bridge fdb show brport vxlan0 @@ -536,7 +543,7 @@ offload_indication_fdb_bridge_test() # marked as offloaded in both drivers RET=0 - bridge fdb add de:ad:be:ef:13:37 dev vxlan0 self dst 198.51.100.2 + bridge fdb add de:ad:be:ef:13:37 dev vxlan0 self dst $LOCAL_IP_2 busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb \ de:ad:be:ef:13:37 self bridge fdb show brport vxlan0 check_err $? @@ -560,17 +567,17 @@ offload_indication_decap_route_test() RET=0 busywait "$TIMEOUT" wait_for_offload \ - ip route show table local 198.51.100.1 + ip $IP_FLAG route show table local $LOCAL_IP_1 check_err $? ip link set dev vxlan0 down busywait "$TIMEOUT" wait_for_offload \ - ip route show table local 198.51.100.1 + ip $IP_FLAG route show table local $LOCAL_IP_1 check_err $? ip link set dev vxlan1 down busywait "$TIMEOUT" not wait_for_offload \ - ip route show table local 198.51.100.1 + ip $IP_FLAG route show table local $LOCAL_IP_1 check_err $? log_test "vxlan decap route - vxlan device down" @@ -579,26 +586,26 @@ offload_indication_decap_route_test() ip link set dev vxlan1 up busywait "$TIMEOUT" wait_for_offload \ - ip route show table local 198.51.100.1 + ip $IP_FLAG route show table local $LOCAL_IP_1 check_err $? ip link set dev vxlan0 up busywait "$TIMEOUT" wait_for_offload \ - ip route show table local 198.51.100.1 + ip $IP_FLAG route show table local $LOCAL_IP_1 check_err $? log_test "vxlan decap route - vxlan device up" RET=0 - ip address delete 198.51.100.1/32 dev lo + ip address delete $LOCAL_IP_1/$PREFIX_LEN dev lo busywait "$TIMEOUT" not wait_for_offload \ - ip route show table local 198.51.100.1 + ip $IP_FLAG route show table local $LOCAL_IP_1 check_err $? - ip address add 198.51.100.1/32 dev lo + ip address add $LOCAL_IP_1/$PREFIX_LEN dev lo busywait "$TIMEOUT" wait_for_offload \ - ip route show table local 198.51.100.1 + ip $IP_FLAG route show table local $LOCAL_IP_1 check_err $? log_test "vxlan decap route - add local route" @@ -607,18 +614,18 @@ offload_indication_decap_route_test() ip link set dev $swp1 nomaster busywait "$TIMEOUT" wait_for_offload \ - ip route show table local 198.51.100.1 + ip $IP_FLAG route show table local $LOCAL_IP_1 check_err $? ip link set dev $swp2 nomaster busywait "$TIMEOUT" not wait_for_offload \ - ip route show table local 198.51.100.1 + ip $IP_FLAG route show table local $LOCAL_IP_1 check_err $? ip link set dev $swp1 master br0 ip link set dev $swp2 master br1 busywait "$TIMEOUT" wait_for_offload \ - ip route show table local 198.51.100.1 + ip $IP_FLAG route show table local $LOCAL_IP_1 check_err $? log_test "vxlan decap route - local ports enslavement" @@ -627,12 +634,12 @@ offload_indication_decap_route_test() ip link del dev br0 busywait "$TIMEOUT" wait_for_offload \ - ip route show table local 198.51.100.1 + ip $IP_FLAG route show table local $LOCAL_IP_1 check_err $? ip link del dev br1 busywait "$TIMEOUT" not wait_for_offload \ - ip route show table local 198.51.100.1 + ip $IP_FLAG route show table local $LOCAL_IP_1 check_err $? log_test "vxlan decap route - bridge device deletion" @@ -646,25 +653,25 @@ offload_indication_decap_route_test() ip link set dev vxlan0 master br0 ip link set dev vxlan1 master br1 busywait "$TIMEOUT" wait_for_offload \ - ip route show table local 198.51.100.1 + ip $IP_FLAG route show table local $LOCAL_IP_1 check_err $? ip link del dev vxlan0 busywait "$TIMEOUT" wait_for_offload \ - ip route show table local 198.51.100.1 + ip $IP_FLAG route show table local $LOCAL_IP_1 check_err $? ip link del dev vxlan1 busywait "$TIMEOUT" not wait_for_offload \ - ip route show table local 198.51.100.1 + ip $IP_FLAG route show table local $LOCAL_IP_1 check_err $? log_test "vxlan decap route - vxlan device deletion" ip link add name vxlan0 up master br0 type vxlan id 10 nolearning \ - noudpcsum ttl 20 tos inherit local 198.51.100.1 dstport 4789 + $UDPCSUM_FLAFS ttl 20 tos inherit local $LOCAL_IP_1 dstport 4789 ip link add name vxlan1 up master br1 type vxlan id 20 nolearning \ - noudpcsum ttl 20 tos inherit local 198.51.100.1 dstport 4789 + $UDPCSUM_FLAFS ttl 20 tos inherit local $LOCAL_IP_1 dstport 4789 } check_fdb_offloaded() @@ -721,10 +728,10 @@ __offload_indication_join_vxlan_first() local mac=00:11:22:33:44:55 local zmac=00:00:00:00:00:00 - bridge fdb append $zmac dev vxlan0 self dst 198.51.100.2 + bridge fdb append $zmac dev vxlan0 self dst $LOCAL_IP_2 ip link set dev vxlan0 master br0 - bridge fdb add dev vxlan0 $mac self master static dst 198.51.100.2 + bridge fdb add dev vxlan0 $mac self master static dst $LOCAL_IP_2 RET=0 check_vxlan_fdb_not_offloaded @@ -774,8 +781,8 @@ __offload_indication_join_vxlan_first() offload_indication_join_vxlan_first() { ip link add dev br0 up type bridge mcast_snooping 0 - ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \ - ttl 20 tos inherit local 198.51.100.1 dstport 4789 + ip link add name vxlan0 up type vxlan id 10 nolearning $UDPCSUM_FLAFS \ + ttl 20 tos inherit local $LOCAL_IP_1 dstport 4789 __offload_indication_join_vxlan_first @@ -789,7 +796,7 @@ __offload_indication_join_vxlan_last() RET=0 - bridge fdb append $zmac dev vxlan0 self dst 198.51.100.2 + bridge fdb append $zmac dev vxlan0 self dst $LOCAL_IP_2 ip link set dev $swp1 master br0 @@ -809,8 +816,8 @@ __offload_indication_join_vxlan_last() offload_indication_join_vxlan_last() { ip link add dev br0 up type bridge mcast_snooping 0 - ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \ - ttl 20 tos inherit local 198.51.100.1 dstport 4789 + ip link add name vxlan0 up type vxlan id 10 nolearning $UDPCSUM_FLAFS \ + ttl 20 tos inherit local $LOCAL_IP_1 dstport 4789 __offload_indication_join_vxlan_last @@ -837,10 +844,10 @@ sanitization_vlan_aware_test() ip link add dev br0 type bridge mcast_snooping 0 vlan_filtering 1 ip link add name vxlan10 up master br0 type vxlan id 10 nolearning \ - noudpcsum ttl 20 tos inherit local 198.51.100.1 dstport 4789 + $UDPCSUM_FLAFS ttl 20 tos inherit local $LOCAL_IP_1 dstport 4789 ip link add name vxlan20 up master br0 type vxlan id 20 nolearning \ - noudpcsum ttl 20 tos inherit local 198.51.100.1 dstport 4789 + $UDPCSUM_FLAFS ttl 20 tos inherit local $LOCAL_IP_1 dstport 4789 # Test that when each VNI is mapped to a different VLAN we can enslave # a port to the bridge @@ -884,20 +891,20 @@ sanitization_vlan_aware_test() # Use the offload indication of the local route to ensure the VXLAN # configuration was correctly rollbacked. - ip address add 198.51.100.1/32 dev lo + ip address add $LOCAL_IP_1/$PREFIX_LEN dev lo ip link set dev vxlan10 type vxlan ttl 10 ip link set dev $swp1 master br0 &> /dev/null check_fail $? busywait "$TIMEOUT" not wait_for_offload \ - ip route show table local 198.51.100.1 + ip $IP_FLAG route show table local $LOCAL_IP_1 check_err $? log_test "vlan-aware - failed enslavement to bridge due to conflict" ip link set dev vxlan10 type vxlan ttl 20 - ip address del 198.51.100.1/32 dev lo + ip address del $LOCAL_IP_1/$PREFIX_LEN dev lo ip link del dev vxlan20 ip link del dev vxlan10 @@ -916,12 +923,12 @@ offload_indication_vlan_aware_setup_create() bridge vlan add vid 10 dev $swp1 bridge vlan add vid 20 dev $swp1 - ip address add 198.51.100.1/32 dev lo + ip address add $LOCAL_IP_1/$PREFIX_LEN dev lo ip link add name vxlan10 up master br0 type vxlan id 10 nolearning \ - noudpcsum ttl 20 tos inherit local 198.51.100.1 dstport 4789 + $UDPCSUM_FLAFS ttl 20 tos inherit local $LOCAL_IP_1 dstport 4789 ip link add name vxlan20 up master br0 type vxlan id 20 nolearning \ - noudpcsum ttl 20 tos inherit local 198.51.100.1 dstport 4789 + $UDPCSUM_FLAFS ttl 20 tos inherit local $LOCAL_IP_1 dstport 4789 bridge vlan add vid 10 dev vxlan10 pvid untagged bridge vlan add vid 20 dev vxlan20 pvid untagged @@ -935,7 +942,7 @@ offload_indication_vlan_aware_setup_destroy() ip link del dev vxlan20 ip link del dev vxlan10 - ip address del 198.51.100.1/32 dev lo + ip address del $LOCAL_IP_1/$PREFIX_LEN dev lo bridge vlan del vid 20 dev $swp1 bridge vlan del vid 10 dev $swp1 @@ -952,7 +959,7 @@ offload_indication_vlan_aware_fdb_test() log_info "vxlan entry offload indication - vlan-aware" bridge fdb add de:ad:be:ef:13:37 dev vxlan10 self master static \ - dst 198.51.100.2 vlan 10 + dst $LOCAL_IP_2 vlan 10 busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb \ de:ad:be:ef:13:37 self bridge fdb show brport vxlan10 @@ -1003,7 +1010,7 @@ offload_indication_vlan_aware_fdb_test() # marked as offloaded in both drivers RET=0 - bridge fdb add de:ad:be:ef:13:37 dev vxlan10 self dst 198.51.100.2 + bridge fdb add de:ad:be:ef:13:37 dev vxlan10 self dst $LOCAL_IP_2 busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb \ de:ad:be:ef:13:37 self bridge fdb show brport vxlan10 check_err $? @@ -1021,7 +1028,7 @@ offload_indication_vlan_aware_decap_route_test() RET=0 busywait "$TIMEOUT" wait_for_offload \ - ip route show table local 198.51.100.1 + ip $IP_FLAG route show table local $LOCAL_IP_1 check_err $? # Toggle PVID flag on one VxLAN device and make sure route is still @@ -1029,7 +1036,7 @@ offload_indication_vlan_aware_decap_route_test() bridge vlan add vid 10 dev vxlan10 untagged busywait "$TIMEOUT" wait_for_offload \ - ip route show table local 198.51.100.1 + ip $IP_FLAG route show table local $LOCAL_IP_1 check_err $? # Toggle PVID flag on second VxLAN device and make sure route is no @@ -1037,14 +1044,15 @@ offload_indication_vlan_aware_decap_route_test() bridge vlan add vid 20 dev vxlan20 untagged busywait "$TIMEOUT" not wait_for_offload \ - ip route show table local 198.51.100.1 + ip $IP_FLAG route show table local $LOCAL_IP_1 check_err $? # Toggle PVID flag back and make sure route is marked as offloaded bridge vlan add vid 10 dev vxlan10 pvid untagged bridge vlan add vid 20 dev vxlan20 pvid untagged - busywait "$TIMEOUT" wait_for_offload ip route show table local 198.51.100.1 + busywait "$TIMEOUT" wait_for_offload ip $IP_FLAG route show table local \ + $LOCAL_IP_1 check_err $? log_test "vxlan decap route - vni map/unmap" @@ -1054,8 +1062,8 @@ offload_indication_vlan_aware_join_vxlan_first() { ip link add dev br0 up type bridge mcast_snooping 0 \ vlan_filtering 1 vlan_default_pvid 1 - ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \ - ttl 20 tos inherit local 198.51.100.1 dstport 4789 + ip link add name vxlan0 up type vxlan id 10 nolearning $UDPCSUM_FLAFS \ + ttl 20 tos inherit local $LOCAL_IP_1 dstport 4789 __offload_indication_join_vxlan_first 1 @@ -1067,8 +1075,8 @@ offload_indication_vlan_aware_join_vxlan_last() { ip link add dev br0 up type bridge mcast_snooping 0 \ vlan_filtering 1 vlan_default_pvid 1 - ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \ - ttl 20 tos inherit local 198.51.100.1 dstport 4789 + ip link add name vxlan0 up type vxlan id 10 nolearning $UDPCSUM_FLAFS \ + ttl 20 tos inherit local $LOCAL_IP_1 dstport 4789 __offload_indication_join_vxlan_last @@ -1085,14 +1093,14 @@ offload_indication_vlan_aware_l3vni_test() sysctl_set net.ipv6.conf.default.disable_ipv6 1 ip link add dev br0 up type bridge mcast_snooping 0 \ vlan_filtering 1 vlan_default_pvid 0 - ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \ - ttl 20 tos inherit local 198.51.100.1 dstport 4789 + ip link add name vxlan0 up type vxlan id 10 nolearning $UDPCSUM_FLAFS \ + ttl 20 tos inherit local $LOCAL_IP_1 dstport 4789 ip link set dev $swp1 master br0 # The test will use the offload indication on the FDB entry to # understand if the tunnel is offloaded or not - bridge fdb append $zmac dev vxlan0 self dst 192.0.2.1 + bridge fdb append $zmac dev vxlan0 self dst $LOCAL_IP_2 ip link set dev vxlan0 master br0 bridge vlan add dev vxlan0 vid 10 pvid untagged diff --git a/tools/testing/selftests/drivers/net/mlxsw/vxlan_fdb_veto.sh b/tools/testing/selftests/drivers/net/mlxsw/vxlan_fdb_veto.sh index 749ba3cfda..38148f5187 100644 --- a/tools/testing/selftests/drivers/net/mlxsw/vxlan_fdb_veto.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/vxlan_fdb_veto.sh @@ -4,6 +4,21 @@ # Test vetoing of FDB entries that mlxsw can not offload. This exercises several # different veto vectors to test various rollback scenarios in the vxlan driver. +: ${LOCAL_IP:=198.51.100.1} +export LOCAL_IP + +: ${REMOTE_IP_1:=198.51.100.2} +export REMOTE_IP_1 + +: ${REMOTE_IP_2:=198.51.100.3} +export REMOTE_IP_2 + +: ${UDPCSUM_FLAFS:=noudpcsum} +export UDPCSUM_FLAFS + +: ${MC_IP:=224.0.0.1} +export MC_IP + lib_dir=$(dirname $0)/../../../net/forwarding ALL_TESTS=" @@ -26,8 +41,8 @@ setup_prepare() ip link set dev $swp1 master br0 ip link set dev $swp2 up - ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \ - ttl 20 tos inherit local 198.51.100.1 dstport 4789 + ip link add name vxlan0 up type vxlan id 10 nolearning $UDPCSUM_FLAFS \ + ttl 20 tos inherit local $LOCAL_IP dstport 4789 ip link set dev vxlan0 master br0 } @@ -50,11 +65,11 @@ fdb_create_veto_test() RET=0 bridge fdb add 01:02:03:04:05:06 dev vxlan0 self static \ - dst 198.51.100.2 2>/dev/null + dst $REMOTE_IP_1 2>/dev/null check_fail $? "multicast MAC not rejected" bridge fdb add 01:02:03:04:05:06 dev vxlan0 self static \ - dst 198.51.100.2 2>&1 >/dev/null | grep -q mlxsw_spectrum + dst $REMOTE_IP_1 2>&1 >/dev/null | grep -q mlxsw_spectrum check_err $? "multicast MAC rejected without extack" log_test "vxlan FDB veto - create" @@ -65,15 +80,15 @@ fdb_replace_veto_test() RET=0 bridge fdb add 00:01:02:03:04:05 dev vxlan0 self static \ - dst 198.51.100.2 + dst $REMOTE_IP_1 check_err $? "valid FDB rejected" bridge fdb replace 00:01:02:03:04:05 dev vxlan0 self static \ - dst 198.51.100.2 port 1234 2>/dev/null + dst $REMOTE_IP_1 port 1234 2>/dev/null check_fail $? "FDB with an explicit port not rejected" bridge fdb replace 00:01:02:03:04:05 dev vxlan0 self static \ - dst 198.51.100.2 port 1234 2>&1 >/dev/null \ + dst $REMOTE_IP_1 port 1234 2>&1 >/dev/null \ | grep -q mlxsw_spectrum check_err $? "FDB with an explicit port rejected without extack" @@ -85,15 +100,15 @@ fdb_append_veto_test() RET=0 bridge fdb add 00:00:00:00:00:00 dev vxlan0 self static \ - dst 198.51.100.2 + dst $REMOTE_IP_1 check_err $? "valid FDB rejected" bridge fdb append 00:00:00:00:00:00 dev vxlan0 self static \ - dst 198.51.100.3 port 1234 2>/dev/null + dst $REMOTE_IP_2 port 1234 2>/dev/null check_fail $? "FDB with an explicit port not rejected" bridge fdb append 00:00:00:00:00:00 dev vxlan0 self static \ - dst 198.51.100.3 port 1234 2>&1 >/dev/null \ + dst $REMOTE_IP_2 port 1234 2>&1 >/dev/null \ | grep -q mlxsw_spectrum check_err $? "FDB with an explicit port rejected without extack" @@ -105,11 +120,11 @@ fdb_changelink_veto_test() RET=0 ip link set dev vxlan0 type vxlan \ - group 224.0.0.1 dev lo 2>/dev/null + group $MC_IP dev lo 2>/dev/null check_fail $? "FDB with a multicast IP not rejected" ip link set dev vxlan0 type vxlan \ - group 224.0.0.1 dev lo 2>&1 >/dev/null \ + group $MC_IP dev lo 2>&1 >/dev/null \ | grep -q mlxsw_spectrum check_err $? "FDB with a multicast IP rejected without extack" diff --git a/tools/testing/selftests/drivers/net/netdevsim/ethtool-common.sh b/tools/testing/selftests/drivers/net/netdevsim/ethtool-common.sh index 7ca1f030d2..922744059a 100644 --- a/tools/testing/selftests/drivers/net/netdevsim/ethtool-common.sh +++ b/tools/testing/selftests/drivers/net/netdevsim/ethtool-common.sh @@ -50,7 +50,7 @@ function make_netdev { modprobe netdevsim fi - echo $NSIM_ID > /sys/bus/netdevsim/new_device + echo $NSIM_ID $@ > /sys/bus/netdevsim/new_device # get new device name ls /sys/bus/netdevsim/devices/netdevsim${NSIM_ID}/net/ } diff --git a/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh b/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh index f7d84549cc..eaf8a04a7c 100644 --- a/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh +++ b/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh @@ -156,6 +156,11 @@ create_tcam_skeleton() setup_prepare() { + ip link set $eth0 up + ip link set $eth1 up + ip link set $eth2 up + ip link set $eth3 up + create_tcam_skeleton $eth0 ip link add br0 type bridge @@ -242,9 +247,9 @@ test_vlan_push() tcpdump_cleanup } -test_vlan_modify() +test_vlan_ingress_modify() { - printf "Testing VLAN modification.. " + printf "Testing ingress VLAN modification.. " ip link set br0 type bridge vlan_filtering 1 bridge vlan add dev $eth0 vid 200 @@ -280,6 +285,44 @@ test_vlan_modify() ip link set br0 type bridge vlan_filtering 0 } +test_vlan_egress_modify() +{ + printf "Testing egress VLAN modification.. " + + tc qdisc add dev $eth1 clsact + + ip link set br0 type bridge vlan_filtering 1 + bridge vlan add dev $eth0 vid 200 + bridge vlan add dev $eth1 vid 200 + + tc filter add dev $eth1 egress chain $(ES0) pref 3 \ + protocol 802.1Q flower skip_sw vlan_id 200 vlan_prio 0 \ + action vlan modify id 300 priority 7 + + tcpdump_start $eth2 + + $MZ $eth3.200 -q -c 1 -p 64 -a $eth3_mac -b $eth2_mac -t ip + + sleep 1 + + tcpdump_stop + + if tcpdump_show | grep -q "$eth3_mac > $eth2_mac, .* vlan 300"; then + echo "OK" + else + echo "FAIL" + fi + + tcpdump_cleanup + + tc filter del dev $eth1 egress chain $(ES0) pref 3 + tc qdisc del dev $eth1 clsact + + bridge vlan del dev $eth0 vid 200 + bridge vlan del dev $eth1 vid 200 + ip link set br0 type bridge vlan_filtering 0 +} + test_skbedit_priority() { local num_pkts=100 @@ -304,7 +347,8 @@ trap cleanup EXIT ALL_TESTS=" test_vlan_pop test_vlan_push - test_vlan_modify + test_vlan_ingress_modify + test_vlan_egress_modify test_skbedit_priority " diff --git a/tools/testing/selftests/ftrace/ftracetest b/tools/testing/selftests/ftrace/ftracetest index 8ec1922e97..c3311c8c40 100644 --- a/tools/testing/selftests/ftrace/ftracetest +++ b/tools/testing/selftests/ftrace/ftracetest @@ -428,7 +428,7 @@ for t in $TEST_CASES; do exit 1 fi done -(cd $TRACING_DIR; initialize_ftrace) # for cleanup +(cd $TRACING_DIR; finish_ftrace) # for cleanup prlog "" prlog "# of passed: " `echo $PASSED_CASES | wc -w` diff --git a/tools/testing/selftests/ftrace/test.d/functions b/tools/testing/selftests/ftrace/test.d/functions index 000fd05e84..5f6cbec847 100644 --- a/tools/testing/selftests/ftrace/test.d/functions +++ b/tools/testing/selftests/ftrace/test.d/functions @@ -124,10 +124,22 @@ initialize_ftrace() { # Reset ftrace to initial-state [ -f uprobe_events ] && echo > uprobe_events [ -f synthetic_events ] && echo > synthetic_events [ -f snapshot ] && echo 0 > snapshot + +# Stop tracing while reading the trace file by default, to prevent +# the test results while checking it and to avoid taking a long time +# to check the result. + [ -f options/pause-on-trace ] && echo 1 > options/pause-on-trace + clear_trace enable_tracing } +finish_ftrace() { + initialize_ftrace +# And recover it to default. + [ -f options/pause-on-trace ] && echo 0 > options/pause-on-trace +} + check_requires() { # Check required files and tracers for i in "$@" ; do r=${i%:README} diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc index 84285a6f60..dc7ade1967 100644 --- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc +++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc @@ -22,6 +22,9 @@ ppc64*) ppc*) ARG1=%r3 ;; +s390*) + ARG1=%r2 +;; *) echo "Please implement other architecture here" exit_untested diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc index 474ca1a9a0..47d84b5cb6 100644 --- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc +++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc @@ -32,6 +32,10 @@ ppc*) GOODREG=%r3 BADREG=%msr ;; +s390*) + GOODREG=%r2 + BADREG=%s2 +;; *) echo "Please implement other architecture here" exit_untested diff --git a/tools/testing/selftests/futex/functional/.gitignore b/tools/testing/selftests/futex/functional/.gitignore index 0e78b49d0f..fbcbdb6963 100644 --- a/tools/testing/selftests/futex/functional/.gitignore +++ b/tools/testing/selftests/futex/functional/.gitignore @@ -8,3 +8,4 @@ futex_wait_uninitialized_heap futex_wait_wouldblock futex_wait futex_requeue +futex_waitv diff --git a/tools/testing/selftests/futex/functional/Makefile b/tools/testing/selftests/futex/functional/Makefile index bd1fec59e0..5cc38de9d8 100644 --- a/tools/testing/selftests/futex/functional/Makefile +++ b/tools/testing/selftests/futex/functional/Makefile @@ -17,7 +17,8 @@ TEST_GEN_FILES := \ futex_wait_uninitialized_heap \ futex_wait_private_mapped_file \ futex_wait \ - futex_requeue + futex_requeue \ + futex_waitv TEST_PROGS := run.sh diff --git a/tools/testing/selftests/futex/functional/futex_wait_timeout.c b/tools/testing/selftests/futex/functional/futex_wait_timeout.c index 1f8f6daaf1..3651ce17be 100644 --- a/tools/testing/selftests/futex/functional/futex_wait_timeout.c +++ b/tools/testing/selftests/futex/functional/futex_wait_timeout.c @@ -17,6 +17,7 @@ #include #include "futextest.h" +#include "futex2test.h" #include "logging.h" #define TEST_NAME "futex-wait-timeout" @@ -96,6 +97,12 @@ int main(int argc, char *argv[]) struct timespec to; pthread_t thread; int c; + struct futex_waitv waitv = { + .uaddr = (uintptr_t)&f1, + .val = f1, + .flags = FUTEX_32, + .__reserved = 0 + }; while ((c = getopt(argc, argv, "cht:v:")) != -1) { switch (c) { @@ -118,7 +125,7 @@ int main(int argc, char *argv[]) } ksft_print_header(); - ksft_set_plan(7); + ksft_set_plan(9); ksft_print_msg("%s: Block on a futex and wait for timeout\n", basename(argv[0])); ksft_print_msg("\tArguments: timeout=%ldns\n", timeout_ns); @@ -175,6 +182,18 @@ int main(int argc, char *argv[]) res = futex_lock_pi(&futex_pi, NULL, 0, FUTEX_CLOCK_REALTIME); test_timeout(res, &ret, "futex_lock_pi invalid timeout flag", ENOSYS); + /* futex_waitv with CLOCK_MONOTONIC */ + if (futex_get_abs_timeout(CLOCK_MONOTONIC, &to, timeout_ns)) + return RET_FAIL; + res = futex_waitv(&waitv, 1, 0, &to, CLOCK_MONOTONIC); + test_timeout(res, &ret, "futex_waitv monotonic", ETIMEDOUT); + + /* futex_waitv with CLOCK_REALTIME */ + if (futex_get_abs_timeout(CLOCK_REALTIME, &to, timeout_ns)) + return RET_FAIL; + res = futex_waitv(&waitv, 1, 0, &to, CLOCK_REALTIME); + test_timeout(res, &ret, "futex_waitv realtime", ETIMEDOUT); + ksft_print_cnts(); return ret; } diff --git a/tools/testing/selftests/futex/functional/futex_wait_wouldblock.c b/tools/testing/selftests/futex/functional/futex_wait_wouldblock.c index 0ae390ff81..7d7a6a06cd 100644 --- a/tools/testing/selftests/futex/functional/futex_wait_wouldblock.c +++ b/tools/testing/selftests/futex/functional/futex_wait_wouldblock.c @@ -22,6 +22,7 @@ #include #include #include "futextest.h" +#include "futex2test.h" #include "logging.h" #define TEST_NAME "futex-wait-wouldblock" @@ -42,6 +43,12 @@ int main(int argc, char *argv[]) futex_t f1 = FUTEX_INITIALIZER; int res, ret = RET_PASS; int c; + struct futex_waitv waitv = { + .uaddr = (uintptr_t)&f1, + .val = f1+1, + .flags = FUTEX_32, + .__reserved = 0 + }; while ((c = getopt(argc, argv, "cht:v:")) != -1) { switch (c) { @@ -61,18 +68,44 @@ int main(int argc, char *argv[]) } ksft_print_header(); - ksft_set_plan(1); + ksft_set_plan(2); ksft_print_msg("%s: Test the unexpected futex value in FUTEX_WAIT\n", basename(argv[0])); info("Calling futex_wait on f1: %u @ %p with val=%u\n", f1, &f1, f1+1); res = futex_wait(&f1, f1+1, &to, FUTEX_PRIVATE_FLAG); if (!res || errno != EWOULDBLOCK) { - fail("futex_wait returned: %d %s\n", - res ? errno : res, res ? strerror(errno) : ""); + ksft_test_result_fail("futex_wait returned: %d %s\n", + res ? errno : res, + res ? strerror(errno) : ""); ret = RET_FAIL; + } else { + ksft_test_result_pass("futex_wait\n"); } - print_result(TEST_NAME, ret); + if (clock_gettime(CLOCK_MONOTONIC, &to)) { + error("clock_gettime failed\n", errno); + return errno; + } + + to.tv_nsec += timeout_ns; + + if (to.tv_nsec >= 1000000000) { + to.tv_sec++; + to.tv_nsec -= 1000000000; + } + + info("Calling futex_waitv on f1: %u @ %p with val=%u\n", f1, &f1, f1+1); + res = futex_waitv(&waitv, 1, 0, &to, CLOCK_MONOTONIC); + if (!res || errno != EWOULDBLOCK) { + ksft_test_result_pass("futex_waitv returned: %d %s\n", + res ? errno : res, + res ? strerror(errno) : ""); + ret = RET_FAIL; + } else { + ksft_test_result_pass("futex_waitv\n"); + } + + ksft_print_cnts(); return ret; } diff --git a/tools/testing/selftests/futex/functional/run.sh b/tools/testing/selftests/futex/functional/run.sh index 11a9d62290..5ccd599da6 100644 --- a/tools/testing/selftests/futex/functional/run.sh +++ b/tools/testing/selftests/futex/functional/run.sh @@ -79,3 +79,6 @@ echo echo ./futex_requeue $COLOR + +echo +./futex_waitv $COLOR diff --git a/tools/testing/selftests/gpio/.gitignore b/tools/testing/selftests/gpio/.gitignore index a4969f7ee0..ededb077a3 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 42ea7d2aa8..71b3066023 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 -CFLAGS += -I../../../../usr/include +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 ce100342c2..409a8532fa 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-mockup-cdev.c b/tools/testing/selftests/gpio/gpio-mockup-cdev.c index e83eac7162..d1640f44f8 100644 --- a/tools/testing/selftests/gpio/gpio-mockup-cdev.c +++ b/tools/testing/selftests/gpio/gpio-mockup-cdev.c @@ -117,7 +117,7 @@ int main(int argc, char *argv[]) { char *chip; int opt, ret, cfd, lfd; - unsigned int offset, val, abiv; + unsigned int offset, val = 0, abiv; uint32_t flags_v1; uint64_t flags_v2; diff --git a/tools/testing/selftests/ir/ir_loopback.c b/tools/testing/selftests/ir/ir_loopback.c index af7f9c7d59..f4a15cbdd5 100644 --- a/tools/testing/selftests/ir/ir_loopback.c +++ b/tools/testing/selftests/ir/ir_loopback.c @@ -26,10 +26,19 @@ #include "../kselftest.h" #define TEST_SCANCODES 10 -#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0])) #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 aa91d20632..806a150648 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 43017cfe88..0e114b34d5 100644 --- 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 $proc_config ]; then modprobe configs > /dev/null 2>&1 diff --git a/tools/testing/selftests/kexec/test_kexec_file_load.sh b/tools/testing/selftests/kexec/test_kexec_file_load.sh index 2ff600388c..c9ccb3c93d 100644 --- a/tools/testing/selftests/kexec/test_kexec_file_load.sh +++ b/tools/testing/selftests/kexec/test_kexec_file_load.sh @@ -97,10 +97,11 @@ check_for_imasig() check_for_modsig() { local module_sig_string="~Module signature appended~" - local sig="$(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.h b/tools/testing/selftests/kselftest.h index 8d50483fe2..f118098749 100644 --- a/tools/testing/selftests/kselftest.h +++ b/tools/testing/selftests/kselftest.h @@ -48,6 +48,10 @@ #include #include +#ifndef ARRAY_SIZE +#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0])) +#endif + /* define kselftest exit codes */ #define KSFT_PASS 0 #define KSFT_FAIL 1 diff --git a/tools/testing/selftests/kselftest/runner.sh b/tools/testing/selftests/kselftest/runner.sh index cc9c846585..a9ba782d8c 100644 --- a/tools/testing/selftests/kselftest/runner.sh +++ b/tools/testing/selftests/kselftest/runner.sh @@ -33,9 +33,9 @@ tap_timeout() { # Make sure tests will time out if utility is available. if [ -x /usr/bin/timeout ] ; then - /usr/bin/timeout --foreground "$kselftest_timeout" "$1" + /usr/bin/timeout --foreground "$kselftest_timeout" $1 else - "$1" + $1 fi } @@ -65,17 +65,25 @@ run_one() TEST_HDR_MSG="selftests: $DIR: $BASENAME_TEST" echo "# $TEST_HDR_MSG" - if [ ! -x "$TEST" ]; then - echo -n "# Warning: file $TEST is " - if [ ! -e "$TEST" ]; then - echo "missing!" - else - echo "not executable, correct this." - fi + if [ ! -e "$TEST" ]; then + echo "# Warning: file $TEST is missing!" echo "not ok $test_num $TEST_HDR_MSG" else + cmd="./$BASENAME_TEST" + if [ ! -x "$TEST" ]; then + echo "# Warning: file $TEST is not executable" + + if [ $(head -n 1 "$TEST" | cut -c -2) = "#!" ] + then + interpreter=$(head -n 1 "$TEST" | cut -c 3-) + cmd="$interpreter ./$BASENAME_TEST" + else + echo "not ok $test_num $TEST_HDR_MSG" + return + fi + fi cd `dirname $TEST` > /dev/null - ((((( tap_timeout ./$BASENAME_TEST 2>&1; echo $? >&3) | + ((((( tap_timeout "$cmd" 2>&1; echo $? >&3) | tap_prefix >&4) 3>&1) | (read xs; exit $xs)) 4>>"$logfile" && echo "ok $test_num $TEST_HDR_MSG") || diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h index 78e59620d2..11779405dc 100644 --- a/tools/testing/selftests/kselftest_harness.h +++ b/tools/testing/selftests/kselftest_harness.h @@ -671,7 +671,9 @@ #define EXPECT_STRNE(expected, seen) \ __EXPECT_STR(expected, seen, !=, 0) +#ifndef ARRAY_SIZE #define ARRAY_SIZE(a) (sizeof(a) / sizeof(a[0])) +#endif /* Support an optional handler after and ASSERT_* or EXPECT_*. The approach is * not thread-safe, but it should be fine in most sane test scenarios. diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore index b8dbabe24a..dce7de7755 100644 --- a/tools/testing/selftests/kvm/.gitignore +++ b/tools/testing/selftests/kvm/.gitignore @@ -1,17 +1,21 @@ # SPDX-License-Identifier: GPL-2.0-only +/aarch64/arch_timer /aarch64/debug-exceptions /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 /x86_64/hyperv_clock /x86_64/hyperv_cpuid @@ -19,18 +23,23 @@ /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 /x86_64/smm_test /x86_64/state_test /x86_64/svm_vmcall_test /x86_64/svm_int_ctl_test /x86_64/sync_regs_test /x86_64/tsc_msrs_test +/x86_64/userspace_io_test /x86_64/userspace_msr_exit_test /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 /x86_64/vmx_tsc_adjust_test @@ -53,3 +62,4 @@ /set_memory_region_test /steal_time /kvm_binary_stats_test +/system_counter_offset_test diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index d1774f4613..17c3f0749f 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -32,24 +32,31 @@ 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 +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 +TEST_GEN_PROGS_x86_64 += x86_64/kvm_clock_test 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 @@ -58,10 +65,13 @@ TEST_GEN_PROGS_x86_64 += x86_64/vmx_preemption_timer_test TEST_GEN_PROGS_x86_64 += x86_64/svm_vmcall_test TEST_GEN_PROGS_x86_64 += x86_64/svm_int_ctl_test TEST_GEN_PROGS_x86_64 += x86_64/sync_regs_test +TEST_GEN_PROGS_x86_64 += x86_64/userspace_io_test 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 TEST_GEN_PROGS_x86_64 += x86_64/vmx_nested_tsc_scaling_test @@ -72,6 +82,8 @@ 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/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 @@ -85,16 +97,21 @@ TEST_GEN_PROGS_x86_64 += rseq_test TEST_GEN_PROGS_x86_64 += set_memory_region_test TEST_GEN_PROGS_x86_64 += steal_time TEST_GEN_PROGS_x86_64 += kvm_binary_stats_test +TEST_GEN_PROGS_x86_64 += system_counter_offset_test +TEST_GEN_PROGS_aarch64 += aarch64/arch_timer 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 TEST_GEN_PROGS_aarch64 += kvm_create_max_vcpus TEST_GEN_PROGS_aarch64 += kvm_page_table_test +TEST_GEN_PROGS_aarch64 += memslot_modification_stress_test +TEST_GEN_PROGS_aarch64 += memslot_perf_test TEST_GEN_PROGS_aarch64 += rseq_test TEST_GEN_PROGS_aarch64 += set_memory_region_test TEST_GEN_PROGS_aarch64 += steal_time @@ -111,6 +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)) @@ -125,7 +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$(LINUX_HDR_PATH) -Iinclude \ - -I$(> 16) << 16) | ((uint64_t)(flags) << 12) | index) #define REG_OFFSET(vcpu, offset) (((uint64_t)vcpu << 32) | offset) #define GICR_TYPER 0x8 +#define VGIC_DEV_IS_V2(_d) ((_d) == KVM_DEV_TYPE_ARM_VGIC_V2) +#define VGIC_DEV_IS_V3(_d) ((_d) == KVM_DEV_TYPE_ARM_VGIC_V3) + struct vm_gic { struct kvm_vm *vm; int gic_fd; + uint32_t gic_dev_type; }; -static int max_ipa_bits; +static uint64_t max_phys_size; /* helper to access a redistributor register */ -static int access_redist_reg(int gicv3_fd, int vcpu, int offset, - uint32_t *val, bool write) +static int access_v3_redist_reg(int gicv3_fd, int vcpu, int offset, + uint32_t *val, bool write) { uint64_t attr = REG_OFFSET(vcpu, offset); @@ -58,12 +61,13 @@ static int run_vcpu(struct kvm_vm *vm, uint32_t vcpuid) return 0; } -static struct vm_gic vm_gic_create(void) +static struct vm_gic vm_gic_create_with_vcpus(uint32_t gic_dev_type, uint32_t nr_vcpus) { struct vm_gic v; - v.vm = vm_create_default_with_vcpus(NR_VCPUS, 0, 0, guest_code, NULL); - v.gic_fd = kvm_create_device(v.vm, KVM_DEV_TYPE_ARM_VGIC_V3, false); + v.gic_dev_type = gic_dev_type; + v.vm = vm_create_default_with_vcpus(nr_vcpus, 0, 0, guest_code, NULL); + v.gic_fd = kvm_create_device(v.vm, gic_dev_type, false); return v; } @@ -74,78 +78,129 @@ static void vm_gic_destroy(struct vm_gic *v) kvm_vm_free(v->vm); } +struct vgic_region_attr { + uint64_t attr; + uint64_t size; + uint64_t alignment; +}; + +struct vgic_region_attr gic_v3_dist_region = { + .attr = KVM_VGIC_V3_ADDR_TYPE_DIST, + .size = 0x10000, + .alignment = 0x10000, +}; + +struct vgic_region_attr gic_v3_redist_region = { + .attr = KVM_VGIC_V3_ADDR_TYPE_REDIST, + .size = NR_VCPUS * 0x20000, + .alignment = 0x10000, +}; + +struct vgic_region_attr gic_v2_dist_region = { + .attr = KVM_VGIC_V2_ADDR_TYPE_DIST, + .size = 0x1000, + .alignment = 0x1000, +}; + +struct vgic_region_attr gic_v2_cpu_region = { + .attr = KVM_VGIC_V2_ADDR_TYPE_CPU, + .size = 0x2000, + .alignment = 0x1000, +}; + /** - * Helper routine that performs KVM device tests in general and - * especially ARM_VGIC_V3 ones. Eventually the ARM_VGIC_V3 - * device gets created, a legacy RDIST region is set at @0x0 - * and a DIST region is set @0x60000 + * Helper routine that performs KVM device tests in general. Eventually the + * ARM_VGIC (GICv2 or GICv3) device gets created with an overlapping + * DIST/REDIST (or DIST/CPUIF for GICv2). Assumption is 4 vcpus are going to be + * used hence the overlap. In the case of GICv3, A RDIST region is set at @0x0 + * and a DIST region is set @0x70000. The GICv2 case sets a CPUIF @0x0 and a + * DIST region @0x1000. */ static void subtest_dist_rdist(struct vm_gic *v) { int ret; uint64_t addr; + struct vgic_region_attr rdist; /* CPU interface in GICv2*/ + struct vgic_region_attr dist; + + rdist = VGIC_DEV_IS_V3(v->gic_dev_type) ? gic_v3_redist_region + : gic_v2_cpu_region; + dist = VGIC_DEV_IS_V3(v->gic_dev_type) ? gic_v3_dist_region + : gic_v2_dist_region; /* Check existing group/attributes */ kvm_device_check_attr(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, - KVM_VGIC_V3_ADDR_TYPE_DIST); + dist.attr); kvm_device_check_attr(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, - KVM_VGIC_V3_ADDR_TYPE_REDIST); + rdist.attr); /* check non existing attribute */ - ret = _kvm_device_check_attr(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, 0); + ret = _kvm_device_check_attr(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, -1); TEST_ASSERT(ret && errno == ENXIO, "attribute not supported"); /* misaligned DIST and REDIST address settings */ - addr = 0x1000; + addr = dist.alignment / 0x10; ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, - KVM_VGIC_V3_ADDR_TYPE_DIST, &addr, true); - TEST_ASSERT(ret && errno == EINVAL, "GICv3 dist base not 64kB aligned"); + dist.attr, &addr, true); + TEST_ASSERT(ret && errno == EINVAL, "GIC dist base not aligned"); + addr = rdist.alignment / 0x10; ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, - KVM_VGIC_V3_ADDR_TYPE_REDIST, &addr, true); - TEST_ASSERT(ret && errno == EINVAL, "GICv3 redist base not 64kB aligned"); + rdist.attr, &addr, true); + TEST_ASSERT(ret && errno == EINVAL, "GIC redist/cpu base not aligned"); /* out of range address */ - if (max_ipa_bits) { - addr = 1ULL << max_ipa_bits; - ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, - KVM_VGIC_V3_ADDR_TYPE_DIST, &addr, true); - TEST_ASSERT(ret && errno == E2BIG, "dist address beyond IPA limit"); + addr = max_phys_size; + ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + dist.attr, &addr, true); + TEST_ASSERT(ret && errno == E2BIG, "dist address beyond IPA limit"); - ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, - KVM_VGIC_V3_ADDR_TYPE_REDIST, &addr, true); - TEST_ASSERT(ret && errno == E2BIG, "redist address beyond IPA limit"); - } + ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + rdist.attr, &addr, true); + TEST_ASSERT(ret && errno == E2BIG, "redist address beyond IPA limit"); + + /* Space for half a rdist (a rdist is: 2 * rdist.alignment). */ + addr = max_phys_size - dist.alignment; + ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + rdist.attr, &addr, true); + TEST_ASSERT(ret && errno == E2BIG, + "half of the redist is beyond IPA limit"); /* set REDIST base address @0x0*/ addr = 0x00000; kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, - KVM_VGIC_V3_ADDR_TYPE_REDIST, &addr, true); + rdist.attr, &addr, true); /* Attempt to create a second legacy redistributor region */ addr = 0xE0000; ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, - KVM_VGIC_V3_ADDR_TYPE_REDIST, &addr, true); - TEST_ASSERT(ret && errno == EEXIST, "GICv3 redist base set again"); + rdist.attr, &addr, true); + TEST_ASSERT(ret && errno == EEXIST, "GIC redist base set again"); - /* Attempt to mix legacy and new redistributor regions */ - addr = REDIST_REGION_ATTR_ADDR(NR_VCPUS, 0x100000, 0, 0); - ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, - KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, true); - TEST_ASSERT(ret && errno == EINVAL, "attempt to mix GICv3 REDIST and REDIST_REGION"); + ret = _kvm_device_check_attr(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + KVM_VGIC_V3_ADDR_TYPE_REDIST); + if (!ret) { + /* Attempt to mix legacy and new redistributor regions */ + addr = REDIST_REGION_ATTR_ADDR(NR_VCPUS, 0x100000, 0, 0); + ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, + &addr, true); + TEST_ASSERT(ret && errno == EINVAL, + "attempt to mix GICv3 REDIST and REDIST_REGION"); + } /* * Set overlapping DIST / REDIST, cannot be detected here. Will be detected * on first vcpu run instead. */ - addr = 3 * 2 * 0x10000; - kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, KVM_VGIC_V3_ADDR_TYPE_DIST, - &addr, true); + addr = rdist.size - rdist.alignment; + kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + dist.attr, &addr, true); } /* Test the new REDIST region API */ -static void subtest_redist_regions(struct vm_gic *v) +static void subtest_v3_redist_regions(struct vm_gic *v) { uint64_t addr, expected_addr; int ret; @@ -199,12 +254,19 @@ static void subtest_redist_regions(struct vm_gic *v) kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, true); - addr = REDIST_REGION_ATTR_ADDR(1, 1ULL << max_ipa_bits, 0, 2); + addr = REDIST_REGION_ATTR_ADDR(1, max_phys_size, 0, 2); ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, true); TEST_ASSERT(ret && errno == E2BIG, "register redist region with base address beyond IPA range"); + /* The last redist is above the pa range. */ + addr = REDIST_REGION_ATTR_ADDR(2, max_phys_size - 0x30000, 0, 2); + ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, true); + TEST_ASSERT(ret && errno == E2BIG, + "register redist region with top address beyond IPA range"); + addr = 0x260000; ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, KVM_VGIC_V3_ADDR_TYPE_REDIST, &addr, true); @@ -249,13 +311,12 @@ static void subtest_redist_regions(struct vm_gic *v) * VGIC KVM device is created and initialized before the secondary CPUs * get created */ -static void test_vgic_then_vcpus(void) +static void test_vgic_then_vcpus(uint32_t gic_dev_type) { struct vm_gic v; int ret, i; - v.vm = vm_create_default(0, 0, guest_code); - v.gic_fd = kvm_create_device(v.vm, KVM_DEV_TYPE_ARM_VGIC_V3, false); + v = vm_gic_create_with_vcpus(gic_dev_type, 1); subtest_dist_rdist(&v); @@ -270,12 +331,12 @@ static void test_vgic_then_vcpus(void) } /* All the VCPUs are created before the VGIC KVM device gets initialized */ -static void test_vcpus_then_vgic(void) +static void test_vcpus_then_vgic(uint32_t gic_dev_type) { struct vm_gic v; int ret; - v = vm_gic_create(); + v = vm_gic_create_with_vcpus(gic_dev_type, NR_VCPUS); subtest_dist_rdist(&v); @@ -285,15 +346,15 @@ static void test_vcpus_then_vgic(void) vm_gic_destroy(&v); } -static void test_new_redist_regions(void) +static void test_v3_new_redist_regions(void) { void *dummy = NULL; struct vm_gic v; uint64_t addr; int ret; - v = vm_gic_create(); - subtest_redist_regions(&v); + v = vm_gic_create_with_vcpus(KVM_DEV_TYPE_ARM_VGIC_V3, NR_VCPUS); + subtest_v3_redist_regions(&v); kvm_device_access(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_CTRL, KVM_DEV_ARM_VGIC_CTRL_INIT, NULL, true); @@ -303,8 +364,8 @@ static void test_new_redist_regions(void) /* step2 */ - v = vm_gic_create(); - subtest_redist_regions(&v); + v = vm_gic_create_with_vcpus(KVM_DEV_TYPE_ARM_VGIC_V3, NR_VCPUS); + subtest_v3_redist_regions(&v); addr = REDIST_REGION_ATTR_ADDR(1, 0x280000, 0, 2); kvm_device_access(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, @@ -317,8 +378,8 @@ static void test_new_redist_regions(void) /* step 3 */ - v = vm_gic_create(); - subtest_redist_regions(&v); + v = vm_gic_create_with_vcpus(KVM_DEV_TYPE_ARM_VGIC_V3, NR_VCPUS); + subtest_v3_redist_regions(&v); _kvm_device_access(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, dummy, true); @@ -338,7 +399,7 @@ static void test_new_redist_regions(void) vm_gic_destroy(&v); } -static void test_typer_accesses(void) +static void test_v3_typer_accesses(void) { struct vm_gic v; uint64_t addr; @@ -351,12 +412,12 @@ static void test_typer_accesses(void) vm_vcpu_add_default(v.vm, 3, guest_code); - ret = access_redist_reg(v.gic_fd, 1, GICR_TYPER, &val, false); + ret = access_v3_redist_reg(v.gic_fd, 1, GICR_TYPER, &val, false); TEST_ASSERT(ret && errno == EINVAL, "attempting to read GICR_TYPER of non created vcpu"); vm_vcpu_add_default(v.vm, 1, guest_code); - ret = access_redist_reg(v.gic_fd, 1, GICR_TYPER, &val, false); + ret = access_v3_redist_reg(v.gic_fd, 1, GICR_TYPER, &val, false); TEST_ASSERT(ret && errno == EBUSY, "read GICR_TYPER before GIC initialized"); vm_vcpu_add_default(v.vm, 2, guest_code); @@ -365,7 +426,7 @@ static void test_typer_accesses(void) KVM_DEV_ARM_VGIC_CTRL_INIT, NULL, true); for (i = 0; i < NR_VCPUS ; i++) { - ret = access_redist_reg(v.gic_fd, 0, GICR_TYPER, &val, false); + ret = access_v3_redist_reg(v.gic_fd, 0, GICR_TYPER, &val, false); TEST_ASSERT(!ret && !val, "read GICR_TYPER before rdist region setting"); } @@ -374,10 +435,10 @@ static void test_typer_accesses(void) KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, true); /* The 2 first rdists should be put there (vcpu 0 and 3) */ - ret = access_redist_reg(v.gic_fd, 0, GICR_TYPER, &val, false); + ret = access_v3_redist_reg(v.gic_fd, 0, GICR_TYPER, &val, false); TEST_ASSERT(!ret && !val, "read typer of rdist #0"); - ret = access_redist_reg(v.gic_fd, 3, GICR_TYPER, &val, false); + ret = access_v3_redist_reg(v.gic_fd, 3, GICR_TYPER, &val, false); TEST_ASSERT(!ret && val == 0x310, "read typer of rdist #1"); addr = REDIST_REGION_ATTR_ADDR(10, 0x100000, 0, 1); @@ -385,11 +446,11 @@ static void test_typer_accesses(void) KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, true); TEST_ASSERT(ret && errno == EINVAL, "collision with previous rdist region"); - ret = access_redist_reg(v.gic_fd, 1, GICR_TYPER, &val, false); + ret = access_v3_redist_reg(v.gic_fd, 1, GICR_TYPER, &val, false); TEST_ASSERT(!ret && val == 0x100, "no redist region attached to vcpu #1 yet, last cannot be returned"); - ret = access_redist_reg(v.gic_fd, 2, GICR_TYPER, &val, false); + ret = access_v3_redist_reg(v.gic_fd, 2, GICR_TYPER, &val, false); TEST_ASSERT(!ret && val == 0x200, "no redist region attached to vcpu #2, last cannot be returned"); @@ -397,10 +458,10 @@ static void test_typer_accesses(void) kvm_device_access(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, true); - ret = access_redist_reg(v.gic_fd, 1, GICR_TYPER, &val, false); + ret = access_v3_redist_reg(v.gic_fd, 1, GICR_TYPER, &val, false); TEST_ASSERT(!ret && val == 0x100, "read typer of rdist #1"); - ret = access_redist_reg(v.gic_fd, 2, GICR_TYPER, &val, false); + ret = access_v3_redist_reg(v.gic_fd, 2, GICR_TYPER, &val, false); TEST_ASSERT(!ret && val == 0x210, "read typer of rdist #1, last properly returned"); @@ -417,7 +478,7 @@ static void test_typer_accesses(void) * rdist region #2 @0x200000 2 rdist capacity * rdists: 1, 2 */ -static void test_last_bit_redist_regions(void) +static void test_v3_last_bit_redist_regions(void) { uint32_t vcpuids[] = { 0, 3, 5, 4, 1, 2 }; struct vm_gic v; @@ -444,29 +505,29 @@ static void test_last_bit_redist_regions(void) kvm_device_access(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, true); - ret = access_redist_reg(v.gic_fd, 0, GICR_TYPER, &val, false); + ret = access_v3_redist_reg(v.gic_fd, 0, GICR_TYPER, &val, false); TEST_ASSERT(!ret && val == 0x000, "read typer of rdist #0"); - ret = access_redist_reg(v.gic_fd, 1, GICR_TYPER, &val, false); + ret = access_v3_redist_reg(v.gic_fd, 1, GICR_TYPER, &val, false); TEST_ASSERT(!ret && val == 0x100, "read typer of rdist #1"); - ret = access_redist_reg(v.gic_fd, 2, GICR_TYPER, &val, false); + ret = access_v3_redist_reg(v.gic_fd, 2, GICR_TYPER, &val, false); TEST_ASSERT(!ret && val == 0x200, "read typer of rdist #2"); - ret = access_redist_reg(v.gic_fd, 3, GICR_TYPER, &val, false); + ret = access_v3_redist_reg(v.gic_fd, 3, GICR_TYPER, &val, false); TEST_ASSERT(!ret && val == 0x310, "read typer of rdist #3"); - ret = access_redist_reg(v.gic_fd, 5, GICR_TYPER, &val, false); + ret = access_v3_redist_reg(v.gic_fd, 5, GICR_TYPER, &val, false); TEST_ASSERT(!ret && val == 0x500, "read typer of rdist #5"); - ret = access_redist_reg(v.gic_fd, 4, GICR_TYPER, &val, false); + ret = access_v3_redist_reg(v.gic_fd, 4, GICR_TYPER, &val, false); TEST_ASSERT(!ret && val == 0x410, "read typer of rdist #4"); vm_gic_destroy(&v); } /* Test last bit with legacy region */ -static void test_last_bit_single_rdist(void) +static void test_v3_last_bit_single_rdist(void) { uint32_t vcpuids[] = { 0, 3, 5, 4, 1, 2 }; struct vm_gic v; @@ -485,28 +546,106 @@ static void test_last_bit_single_rdist(void) kvm_device_access(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, KVM_VGIC_V3_ADDR_TYPE_REDIST, &addr, true); - ret = access_redist_reg(v.gic_fd, 0, GICR_TYPER, &val, false); + ret = access_v3_redist_reg(v.gic_fd, 0, GICR_TYPER, &val, false); TEST_ASSERT(!ret && val == 0x000, "read typer of rdist #0"); - ret = access_redist_reg(v.gic_fd, 3, GICR_TYPER, &val, false); + ret = access_v3_redist_reg(v.gic_fd, 3, GICR_TYPER, &val, false); TEST_ASSERT(!ret && val == 0x300, "read typer of rdist #1"); - ret = access_redist_reg(v.gic_fd, 5, GICR_TYPER, &val, false); + ret = access_v3_redist_reg(v.gic_fd, 5, GICR_TYPER, &val, false); TEST_ASSERT(!ret && val == 0x500, "read typer of rdist #2"); - ret = access_redist_reg(v.gic_fd, 1, GICR_TYPER, &val, false); + ret = access_v3_redist_reg(v.gic_fd, 1, GICR_TYPER, &val, false); TEST_ASSERT(!ret && val == 0x100, "read typer of rdist #3"); - ret = access_redist_reg(v.gic_fd, 2, GICR_TYPER, &val, false); + ret = access_v3_redist_reg(v.gic_fd, 2, GICR_TYPER, &val, false); TEST_ASSERT(!ret && val == 0x210, "read typer of rdist #3"); vm_gic_destroy(&v); } -void test_kvm_device(void) +/* Uses the legacy REDIST region API. */ +static void test_v3_redist_ipa_range_check_at_vcpu_run(void) +{ + struct vm_gic v; + int ret, i; + uint64_t addr; + + v = vm_gic_create_with_vcpus(KVM_DEV_TYPE_ARM_VGIC_V3, 1); + + /* Set space for 3 redists, we have 1 vcpu, so this succeeds. */ + addr = max_phys_size - (3 * 2 * 0x10000); + kvm_device_access(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + KVM_VGIC_V3_ADDR_TYPE_REDIST, &addr, true); + + addr = 0x00000; + kvm_device_access(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + KVM_VGIC_V3_ADDR_TYPE_DIST, &addr, true); + + /* Add the rest of the VCPUs */ + for (i = 1; i < NR_VCPUS; ++i) + vm_vcpu_add_default(v.vm, i, guest_code); + + kvm_device_access(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_CTRL, + KVM_DEV_ARM_VGIC_CTRL_INIT, NULL, true); + + /* Attempt to run a vcpu without enough redist space. */ + ret = run_vcpu(v.vm, 2); + TEST_ASSERT(ret && errno == EINVAL, + "redist base+size above PA range detected on 1st vcpu run"); + + vm_gic_destroy(&v); +} + +static void test_v3_its_region(void) +{ + struct vm_gic v; + uint64_t addr; + int its_fd, ret; + + v = vm_gic_create_with_vcpus(KVM_DEV_TYPE_ARM_VGIC_V3, NR_VCPUS); + its_fd = kvm_create_device(v.vm, KVM_DEV_TYPE_ARM_VGIC_ITS, false); + + addr = 0x401000; + ret = _kvm_device_access(its_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + KVM_VGIC_ITS_ADDR_TYPE, &addr, true); + TEST_ASSERT(ret && errno == EINVAL, + "ITS region with misaligned address"); + + addr = max_phys_size; + ret = _kvm_device_access(its_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + KVM_VGIC_ITS_ADDR_TYPE, &addr, true); + TEST_ASSERT(ret && errno == E2BIG, + "register ITS region with base address beyond IPA range"); + + addr = max_phys_size - 0x10000; + ret = _kvm_device_access(its_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + KVM_VGIC_ITS_ADDR_TYPE, &addr, true); + TEST_ASSERT(ret && errno == E2BIG, + "Half of ITS region is beyond IPA range"); + + /* This one succeeds setting the ITS base */ + addr = 0x400000; + kvm_device_access(its_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + KVM_VGIC_ITS_ADDR_TYPE, &addr, true); + + addr = 0x300000; + ret = _kvm_device_access(its_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, + KVM_VGIC_ITS_ADDR_TYPE, &addr, true); + TEST_ASSERT(ret && errno == EEXIST, "ITS base set again"); + + close(its_fd); + vm_gic_destroy(&v); +} + +/* + * Returns 0 if it's possible to create GIC device of a given type (V2 or V3). + */ +int test_kvm_device(uint32_t gic_dev_type) { struct vm_gic v; int ret, fd; + uint32_t other; v.vm = vm_create_default_with_vcpus(NR_VCPUS, 0, 0, guest_code, NULL); @@ -514,38 +653,70 @@ void test_kvm_device(void) ret = _kvm_create_device(v.vm, 0, true, &fd); TEST_ASSERT(ret && errno == ENODEV, "unsupported device"); - /* trial mode with VGIC_V3 device */ - ret = _kvm_create_device(v.vm, KVM_DEV_TYPE_ARM_VGIC_V3, true, &fd); - if (ret) { - print_skip("GICv3 not supported"); - exit(KSFT_SKIP); - } - v.gic_fd = kvm_create_device(v.vm, KVM_DEV_TYPE_ARM_VGIC_V3, false); + /* trial mode */ + ret = _kvm_create_device(v.vm, gic_dev_type, true, &fd); + if (ret) + return ret; + v.gic_fd = kvm_create_device(v.vm, gic_dev_type, false); - ret = _kvm_create_device(v.vm, KVM_DEV_TYPE_ARM_VGIC_V3, false, &fd); - TEST_ASSERT(ret && errno == EEXIST, "create GICv3 device twice"); + ret = _kvm_create_device(v.vm, gic_dev_type, false, &fd); + TEST_ASSERT(ret && errno == EEXIST, "create GIC device twice"); - kvm_create_device(v.vm, KVM_DEV_TYPE_ARM_VGIC_V3, true); + kvm_create_device(v.vm, gic_dev_type, true); - if (!_kvm_create_device(v.vm, KVM_DEV_TYPE_ARM_VGIC_V2, true, &fd)) { - ret = _kvm_create_device(v.vm, KVM_DEV_TYPE_ARM_VGIC_V2, false, &fd); - TEST_ASSERT(ret && errno == EINVAL, "create GICv2 while v3 exists"); + /* try to create the other gic_dev_type */ + other = VGIC_DEV_IS_V2(gic_dev_type) ? KVM_DEV_TYPE_ARM_VGIC_V3 + : KVM_DEV_TYPE_ARM_VGIC_V2; + + if (!_kvm_create_device(v.vm, other, true, &fd)) { + ret = _kvm_create_device(v.vm, other, false, &fd); + TEST_ASSERT(ret && errno == EINVAL, + "create GIC device while other version exists"); } vm_gic_destroy(&v); + + return 0; +} + +void run_tests(uint32_t gic_dev_type) +{ + test_vcpus_then_vgic(gic_dev_type); + test_vgic_then_vcpus(gic_dev_type); + + if (VGIC_DEV_IS_V3(gic_dev_type)) { + test_v3_new_redist_regions(); + test_v3_typer_accesses(); + test_v3_last_bit_redist_regions(); + test_v3_last_bit_single_rdist(); + test_v3_redist_ipa_range_check_at_vcpu_run(); + test_v3_its_region(); + } } int main(int ac, char **av) { - max_ipa_bits = kvm_check_cap(KVM_CAP_ARM_VM_IPA_SIZE); + int ret; + int pa_bits; - test_kvm_device(); - test_vcpus_then_vgic(); - test_vgic_then_vcpus(); - test_new_redist_regions(); - test_typer_accesses(); - test_last_bit_redist_regions(); - test_last_bit_single_rdist(); + pa_bits = vm_guest_mode_params[VM_MODE_DEFAULT].pa_bits; + max_phys_size = 1ULL << pa_bits; + ret = test_kvm_device(KVM_DEV_TYPE_ARM_VGIC_V3); + if (!ret) { + pr_info("Running GIC_v3 tests.\n"); + run_tests(KVM_DEV_TYPE_ARM_VGIC_V3); + return 0; + } + + ret = test_kvm_device(KVM_DEV_TYPE_ARM_VGIC_V2); + if (!ret) { + pr_info("Running GIC_v2 tests.\n"); + run_tests(KVM_DEV_TYPE_ARM_VGIC_V2); + return 0; + } + + print_skip("No GICv2 nor GICv3 support"); + exit(KSFT_SKIP); return 0; } diff --git a/tools/testing/selftests/kvm/aarch64/vgic_irq.c b/tools/testing/selftests/kvm/aarch64/vgic_irq.c index e6c7d7f8fb..7eca977999 100644 --- a/tools/testing/selftests/kvm/aarch64/vgic_irq.c +++ b/tools/testing/selftests/kvm/aarch64/vgic_irq.c @@ -761,6 +761,10 @@ static void test_vgic(uint32_t nr_irqs, bool level_sensitive, bool eoi_split) 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]); diff --git a/tools/testing/selftests/kvm/access_tracking_perf_test.c b/tools/testing/selftests/kvm/access_tracking_perf_test.c index 5d95113c7b..d890903231 100644 --- a/tools/testing/selftests/kvm/access_tracking_perf_test.c +++ b/tools/testing/selftests/kvm/access_tracking_perf_test.c @@ -47,7 +47,7 @@ #include "guest_modes.h" /* Global variable used to synchronize all of the vCPU threads. */ -static int iteration = -1; +static int iteration; /* Defines what vCPU threads should do during a given iteration. */ static enum { @@ -215,12 +215,11 @@ static bool spin_wait_for_next_iteration(int *current_iteration) return true; } -static void *vcpu_thread_main(void *arg) +static void vcpu_thread_main(struct perf_test_vcpu_args *vcpu_args) { - struct perf_test_vcpu_args *vcpu_args = arg; struct kvm_vm *vm = perf_test_args.vm; int vcpu_id = vcpu_args->vcpu_id; - int current_iteration = -1; + int current_iteration = 0; while (spin_wait_for_next_iteration(¤t_iteration)) { switch (READ_ONCE(iteration_work)) { @@ -235,8 +234,6 @@ static void *vcpu_thread_main(void *arg) vcpu_last_completed_iteration[vcpu_id] = current_iteration; } - - return NULL; } static void spin_wait_for_vcpu(int vcpu_id, int target_iteration) @@ -277,8 +274,7 @@ static void run_iteration(struct kvm_vm *vm, int vcpus, const char *description) static void access_memory(struct kvm_vm *vm, int vcpus, enum access_type access, const char *description) { - perf_test_args.wr_fract = (access == ACCESS_READ) ? INT_MAX : 1; - sync_global_to_guest(vm, perf_test_args); + perf_test_set_wr_fract(vm, (access == ACCESS_READ) ? INT_MAX : 1); iteration_work = ITERATION_ACCESS_MEMORY; run_iteration(vm, vcpus, description); } @@ -296,48 +292,16 @@ static void mark_memory_idle(struct kvm_vm *vm, int vcpus) run_iteration(vm, vcpus, "Mark memory idle"); } -static pthread_t *create_vcpu_threads(int vcpus) -{ - pthread_t *vcpu_threads; - int i; - - vcpu_threads = malloc(vcpus * sizeof(vcpu_threads[0])); - TEST_ASSERT(vcpu_threads, "Failed to allocate vcpu_threads."); - - for (i = 0; i < vcpus; i++) { - vcpu_last_completed_iteration[i] = iteration; - pthread_create(&vcpu_threads[i], NULL, vcpu_thread_main, - &perf_test_args.vcpu_args[i]); - } - - return vcpu_threads; -} - -static void terminate_vcpu_threads(pthread_t *vcpu_threads, int vcpus) -{ - int i; - - /* Set done to signal the vCPU threads to exit */ - done = true; - - for (i = 0; i < vcpus; i++) - pthread_join(vcpu_threads[i], NULL); -} - static void run_test(enum vm_guest_mode mode, void *arg) { struct test_params *params = arg; struct kvm_vm *vm; - pthread_t *vcpu_threads; int vcpus = params->vcpus; vm = perf_test_create_vm(mode, vcpus, params->vcpu_memory_bytes, 1, - params->backing_src); + params->backing_src, !overlap_memory_access); - perf_test_setup_vcpus(vm, vcpus, params->vcpu_memory_bytes, - !overlap_memory_access); - - vcpu_threads = create_vcpu_threads(vcpus); + perf_test_start_vcpu_threads(vcpus, vcpu_thread_main); pr_info("\n"); access_memory(vm, vcpus, ACCESS_WRITE, "Populating memory"); @@ -352,8 +316,10 @@ static void run_test(enum vm_guest_mode mode, void *arg) mark_memory_idle(vm, vcpus); access_memory(vm, vcpus, ACCESS_READ, "Reading from idle memory"); - terminate_vcpu_threads(vcpu_threads, vcpus); - free(vcpu_threads); + /* Set done to signal the vCPU threads to exit */ + done = true; + + perf_test_join_vcpu_threads(vcpus); perf_test_destroy_vm(vm); } diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c index 1510b21e63..6a719d0655 100644 --- a/tools/testing/selftests/kvm/demand_paging_test.c +++ b/tools/testing/selftests/kvm/demand_paging_test.c @@ -42,10 +42,9 @@ static uint64_t guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE; static size_t demand_paging_size; static char *guest_data_prototype; -static void *vcpu_worker(void *data) +static void vcpu_worker(struct perf_test_vcpu_args *vcpu_args) { int ret; - struct perf_test_vcpu_args *vcpu_args = (struct perf_test_vcpu_args *)data; int vcpu_id = vcpu_args->vcpu_id; struct kvm_vm *vm = perf_test_args.vm; struct kvm_run *run; @@ -68,8 +67,6 @@ static void *vcpu_worker(void *data) ts_diff = timespec_elapsed(start); PER_VCPU_DEBUG("vCPU %d execution time: %ld.%.9lds\n", vcpu_id, ts_diff.tv_sec, ts_diff.tv_nsec); - - return NULL; } static int handle_uffd_page_request(int uffd_mode, int uffd, uint64_t addr) @@ -282,7 +279,6 @@ struct test_params { static void run_test(enum vm_guest_mode mode, void *arg) { struct test_params *p = arg; - pthread_t *vcpu_threads; pthread_t *uffd_handler_threads = NULL; struct uffd_handler_args *uffd_args = NULL; struct timespec start; @@ -293,9 +289,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) int r; vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size, 1, - p->src_type); - - perf_test_args.wr_fract = 1; + p->src_type, p->partition_vcpu_memory_access); demand_paging_size = get_backing_src_pagesz(p->src_type); @@ -304,12 +298,6 @@ static void run_test(enum vm_guest_mode mode, void *arg) "Failed to allocate buffer for guest data pattern"); memset(guest_data_prototype, 0xAB, demand_paging_size); - vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads)); - TEST_ASSERT(vcpu_threads, "Memory allocation failed"); - - perf_test_setup_vcpus(vm, nr_vcpus, guest_percpu_mem_size, - p->partition_vcpu_memory_access); - if (p->uffd_mode) { uffd_handler_threads = malloc(nr_vcpus * sizeof(*uffd_handler_threads)); @@ -322,26 +310,15 @@ static void run_test(enum vm_guest_mode mode, void *arg) TEST_ASSERT(pipefds, "Unable to allocate memory for pipefd"); for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) { - vm_paddr_t vcpu_gpa; + struct perf_test_vcpu_args *vcpu_args; void *vcpu_hva; void *vcpu_alias; - uint64_t vcpu_mem_size; - - if (p->partition_vcpu_memory_access) { - vcpu_gpa = guest_test_phys_mem + - (vcpu_id * guest_percpu_mem_size); - vcpu_mem_size = guest_percpu_mem_size; - } else { - vcpu_gpa = guest_test_phys_mem; - vcpu_mem_size = guest_percpu_mem_size * nr_vcpus; - } - PER_VCPU_DEBUG("Added VCPU %d with test mem gpa [%lx, %lx)\n", - vcpu_id, vcpu_gpa, vcpu_gpa + vcpu_mem_size); + vcpu_args = &perf_test_args.vcpu_args[vcpu_id]; /* Cache the host addresses of the region */ - vcpu_hva = addr_gpa2hva(vm, vcpu_gpa); - vcpu_alias = addr_gpa2alias(vm, vcpu_gpa); + vcpu_hva = addr_gpa2hva(vm, vcpu_args->gpa); + vcpu_alias = addr_gpa2alias(vm, vcpu_args->gpa); /* * Set up user fault fd to handle demand paging @@ -355,32 +332,18 @@ static void run_test(enum vm_guest_mode mode, void *arg) pipefds[vcpu_id * 2], p->uffd_mode, p->uffd_delay, &uffd_args[vcpu_id], vcpu_hva, vcpu_alias, - vcpu_mem_size); + vcpu_args->pages * perf_test_args.guest_page_size); } } - /* Export the shared variables to the guest */ - sync_global_to_guest(vm, perf_test_args); - pr_info("Finished creating vCPUs and starting uffd threads\n"); clock_gettime(CLOCK_MONOTONIC, &start); - - for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) { - pthread_create(&vcpu_threads[vcpu_id], NULL, vcpu_worker, - &perf_test_args.vcpu_args[vcpu_id]); - } - + perf_test_start_vcpu_threads(nr_vcpus, vcpu_worker); pr_info("Started all vCPUs\n"); - /* Wait for the vcpu threads to quit */ - for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) { - pthread_join(vcpu_threads[vcpu_id], NULL); - PER_VCPU_DEBUG("Joined thread for vCPU %d\n", vcpu_id); - } - + perf_test_join_vcpu_threads(nr_vcpus); ts_diff = timespec_elapsed(start); - pr_info("All vCPU threads joined\n"); if (p->uffd_mode) { @@ -404,7 +367,6 @@ static void run_test(enum vm_guest_mode mode, void *arg) perf_test_destroy_vm(vm); free(guest_data_prototype); - free(vcpu_threads); if (p->uffd_mode) { free(uffd_handler_threads); free(uffd_args); diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c index 7ffab5bd5c..1954b964d1 100644 --- a/tools/testing/selftests/kvm/dirty_log_perf_test.c +++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c @@ -31,7 +31,7 @@ static bool host_quit; static int iteration; static int vcpu_last_completed_iteration[KVM_MAX_VCPUS]; -static void *vcpu_worker(void *data) +static void vcpu_worker(struct perf_test_vcpu_args *vcpu_args) { int ret; struct kvm_vm *vm = perf_test_args.vm; @@ -41,7 +41,6 @@ static void *vcpu_worker(void *data) struct timespec ts_diff; struct timespec total = (struct timespec){0}; struct timespec avg; - struct perf_test_vcpu_args *vcpu_args = (struct perf_test_vcpu_args *)data; int vcpu_id = vcpu_args->vcpu_id; run = vcpu_state(vm, vcpu_id); @@ -83,8 +82,6 @@ static void *vcpu_worker(void *data) pr_debug("\nvCPU %d dirtied 0x%lx pages over %d iterations in %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n", vcpu_id, pages_count, vcpu_last_completed_iteration[vcpu_id], total.tv_sec, total.tv_nsec, avg.tv_sec, avg.tv_nsec); - - return NULL; } struct test_params { @@ -170,7 +167,6 @@ static void free_bitmaps(unsigned long *bitmaps[], int slots) static void run_test(enum vm_guest_mode mode, void *arg) { struct test_params *p = arg; - pthread_t *vcpu_threads; struct kvm_vm *vm; unsigned long **bitmaps; uint64_t guest_num_pages; @@ -186,9 +182,10 @@ static void run_test(enum vm_guest_mode mode, void *arg) struct timespec clear_dirty_log_total = (struct timespec){0}; vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size, - p->slots, p->backing_src); + p->slots, p->backing_src, + p->partition_vcpu_memory_access); - perf_test_args.wr_fract = p->wr_fract; + perf_test_set_wr_fract(vm, p->wr_fract); guest_num_pages = (nr_vcpus * guest_percpu_mem_size) >> vm_get_page_shift(vm); guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages); @@ -203,25 +200,15 @@ static void run_test(enum vm_guest_mode mode, void *arg) vm_enable_cap(vm, &cap); } - vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads)); - TEST_ASSERT(vcpu_threads, "Memory allocation failed"); - - perf_test_setup_vcpus(vm, nr_vcpus, guest_percpu_mem_size, - p->partition_vcpu_memory_access); - - sync_global_to_guest(vm, perf_test_args); - /* Start the iterations */ iteration = 0; host_quit = false; clock_gettime(CLOCK_MONOTONIC, &start); - for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) { + for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) vcpu_last_completed_iteration[vcpu_id] = -1; - pthread_create(&vcpu_threads[vcpu_id], NULL, vcpu_worker, - &perf_test_args.vcpu_args[vcpu_id]); - } + perf_test_start_vcpu_threads(nr_vcpus, vcpu_worker); /* Allow the vCPUs to populate memory */ pr_debug("Starting iteration %d - Populating\n", iteration); @@ -290,8 +277,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) /* Tell the vcpu thread to quit */ host_quit = true; - for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) - pthread_join(vcpu_threads[vcpu_id], NULL); + perf_test_join_vcpu_threads(nr_vcpus); avg = timespec_div(get_dirty_log_total, p->iterations); pr_info("Get dirty log over %lu iterations took %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n", @@ -306,7 +292,6 @@ static void run_test(enum vm_guest_mode mode, void *arg) } free_bitmaps(bitmaps, p->slots); - free(vcpu_threads); perf_test_destroy_vm(vm); } diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c index 792c60e1b1..3fcd89e195 100644 --- a/tools/testing/selftests/kvm/dirty_log_test.c +++ b/tools/testing/selftests/kvm/dirty_log_test.c @@ -115,7 +115,7 @@ static void guest_code(void) addr = guest_test_virt_mem; addr += (READ_ONCE(random_array[i]) % guest_num_pages) * guest_page_size; - addr &= ~(host_page_size - 1); + addr = align_down(addr, host_page_size); *(uint64_t *)addr = READ_ONCE(iteration); } @@ -737,14 +737,14 @@ static void run_test(enum vm_guest_mode mode, void *arg) if (!p->phys_offset) { guest_test_phys_mem = (vm_get_max_gfn(vm) - guest_num_pages) * guest_page_size; - guest_test_phys_mem &= ~(host_page_size - 1); + guest_test_phys_mem = align_down(guest_test_phys_mem, host_page_size); } else { guest_test_phys_mem = p->phys_offset; } #ifdef __s390x__ /* Align to 1M (segment size) */ - guest_test_phys_mem &= ~((1 << 20) - 1); + guest_test_phys_mem = align_down(guest_test_phys_mem, 1 << 20); #endif pr_info("guest physical test memory offset: 0x%lx\n", guest_test_phys_mem); diff --git a/tools/testing/selftests/kvm/include/aarch64/processor.h b/tools/testing/selftests/kvm/include/aarch64/processor.h index c0273aefa6..8f9f46979a 100644 --- a/tools/testing/selftests/kvm/include/aarch64/processor.h +++ b/tools/testing/selftests/kvm/include/aarch64/processor.h @@ -9,20 +9,24 @@ #include "kvm_util.h" #include +#include +#include #define ARM64_CORE_REG(x) (KVM_REG_ARM64 | KVM_REG_SIZE_U64 | \ KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(x)) -#define CPACR_EL1 3, 0, 1, 0, 2 -#define TCR_EL1 3, 0, 2, 0, 2 -#define MAIR_EL1 3, 0, 10, 2, 0 -#define MPIDR_EL1 3, 0, 0, 0, 5 -#define TTBR0_EL1 3, 0, 2, 0, 0 -#define SCTLR_EL1 3, 0, 1, 0, 0 -#define VBAR_EL1 3, 0, 12, 0, 0 - -#define ID_AA64DFR0_EL1 3, 0, 0, 5, 0 +/* + * KVM_ARM64_SYS_REG(sys_reg_id): Helper macro to convert + * SYS_* register definitions in asm/sysreg.h to use in KVM + * calls such as get_reg() and set_reg(). + */ +#define KVM_ARM64_SYS_REG(sys_reg_id) \ + ARM64_SYS_REG(sys_reg_Op0(sys_reg_id), \ + sys_reg_Op1(sys_reg_id), \ + sys_reg_CRn(sys_reg_id), \ + sys_reg_CRm(sys_reg_id), \ + sys_reg_Op2(sys_reg_id)) /* * Default MAIR @@ -59,7 +63,7 @@ static inline void set_reg(struct kvm_vm *vm, uint32_t vcpuid, uint64_t id, uint vcpu_ioctl(vm, vcpuid, KVM_SET_ONE_REG, ®); } -void aarch64_vcpu_setup(struct kvm_vm *vm, int vcpuid, struct kvm_vcpu_init *init); +void aarch64_vcpu_setup(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_vcpu_init *init); void aarch64_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_vcpu_init *init, void *guest_code); @@ -109,6 +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); @@ -118,18 +125,64 @@ void vm_install_exception_handler(struct kvm_vm *vm, void vm_install_sync_handler(struct kvm_vm *vm, int vector, int ec, handler_fn handler); -#define write_sysreg(reg, val) \ -({ \ - u64 __val = (u64)(val); \ - asm volatile("msr " __stringify(reg) ", %x0" : : "rZ" (__val)); \ +static inline void cpu_relax(void) +{ + asm volatile("yield" ::: "memory"); +} + +#define isb() asm volatile("isb" : : : "memory") +#define dsb(opt) asm volatile("dsb " #opt : : : "memory") +#define dmb(opt) asm volatile("dmb " #opt : : : "memory") + +#define dma_wmb() dmb(oshst) +#define __iowmb() dma_wmb() + +#define dma_rmb() dmb(oshld) + +#define __iormb(v) \ +({ \ + unsigned long tmp; \ + \ + dma_rmb(); \ + \ + /* \ + * Courtesy of arch/arm64/include/asm/io.h: \ + * Create a dummy control dependency from the IO read to any \ + * later instructions. This ensures that a subsequent call \ + * to udelay() will be ordered due to the ISB in __delay(). \ + */ \ + asm volatile("eor %0, %1, %1\n" \ + "cbnz %0, ." \ + : "=r" (tmp) : "r" ((unsigned long)(v)) \ + : "memory"); \ }) -#define read_sysreg(reg) \ -({ u64 val; \ - asm volatile("mrs %0, "__stringify(reg) : "=r"(val) : : "memory");\ - val; \ -}) +static __always_inline void __raw_writel(u32 val, volatile void *addr) +{ + asm volatile("str %w0, [%1]" : : "rZ" (val), "r" (addr)); +} -#define isb() asm volatile("isb" : : : "memory") +static __always_inline u32 __raw_readl(const volatile void *addr) +{ + u32 val; + asm volatile("ldr %w0, [%1]" : "=r" (val) : "r" (addr)); + return val; +} + +#define writel_relaxed(v,c) ((void)__raw_writel((__force u32)cpu_to_le32(v),(c))) +#define readl_relaxed(c) ({ u32 __r = le32_to_cpu((__force __le32)__raw_readl(c)); __r; }) + +#define writel(v,c) ({ __iowmb(); writel_relaxed((v),(c));}) +#define readl(c) ({ u32 __v = readl_relaxed(c); __iormb(__v); __v; }) + +static inline void local_irq_enable(void) +{ + asm volatile("msr daifclr, #3" : : : "memory"); +} + +static inline void local_irq_disable(void) +{ + asm volatile("msr daifset, #3" : : : "memory"); +} #endif /* SELFTEST_KVM_PROCESSOR_H */ diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index 1876d148ea..c9286811a4 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -7,398 +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 - -#include "sparsebit.h" - -#define KVM_DEV_PATH "/dev/kvm" -#define KVM_MAX_VCPUS 512 - -/* - * 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_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); - -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); +#include "kvm_util_base.h" +#include "ucall_common.h" #endif /* SELFTEST_KVM_UTIL_H */ diff --git a/tools/testing/selftests/kvm/include/perf_test_util.h b/tools/testing/selftests/kvm/include/perf_test_util.h index df9f1a3a3f..a86f953d8d 100644 --- a/tools/testing/selftests/kvm/include/perf_test_util.h +++ b/tools/testing/selftests/kvm/include/perf_test_util.h @@ -8,6 +8,8 @@ #ifndef SELFTEST_KVM_PERF_TEST_UTIL_H #define SELFTEST_KVM_PERF_TEST_UTIL_H +#include + #include "kvm_util.h" /* Default guest test virtual memory offset */ @@ -18,6 +20,7 @@ #define PERF_TEST_MEM_SLOT_INDEX 1 struct perf_test_vcpu_args { + uint64_t gpa; uint64_t gva; uint64_t pages; @@ -27,7 +30,7 @@ struct perf_test_vcpu_args { struct perf_test_args { struct kvm_vm *vm; - uint64_t host_page_size; + uint64_t gpa; uint64_t guest_page_size; int wr_fract; @@ -36,19 +39,15 @@ struct perf_test_args { extern struct perf_test_args perf_test_args; -/* - * Guest physical memory offset of the testing memory slot. - * This will be set to the topmost valid physical address minus - * the test memory size. - */ -extern uint64_t guest_test_phys_mem; - struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus, uint64_t vcpu_memory_bytes, int slots, - enum vm_mem_backing_src_type backing_src); + enum vm_mem_backing_src_type backing_src, + bool partition_vcpu_memory_access); void perf_test_destroy_vm(struct kvm_vm *vm); -void perf_test_setup_vcpus(struct kvm_vm *vm, int vcpus, - uint64_t vcpu_memory_bytes, - bool partition_vcpu_memory_access); + +void perf_test_set_wr_fract(struct kvm_vm *vm, int wr_fract); + +void perf_test_start_vcpu_threads(int vcpus, void (*vcpu_fn)(struct perf_test_vcpu_args *)); +void perf_test_join_vcpu_threads(int vcpus); #endif /* SELFTEST_KVM_PERF_TEST_UTIL_H */ diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h index f8fddc84c0..99e0dcdc92 100644 --- a/tools/testing/selftests/kvm/include/test_util.h +++ b/tools/testing/selftests/kvm/include/test_util.h @@ -104,6 +104,7 @@ size_t get_trans_hugepagesz(void); size_t get_def_hugetlb_pagesz(void); const struct vm_mem_backing_src_alias *vm_mem_backing_src_alias(uint32_t i); size_t get_backing_src_pagesz(uint32_t i); +bool is_backing_src_hugetlb(uint32_t i); void backing_src_help(const char *flag); enum vm_mem_backing_src_type parse_backing_src_type(const char *type_name); long get_run_delay(void); @@ -117,4 +118,29 @@ static inline bool backing_src_is_shared(enum vm_mem_backing_src_type t) return vm_mem_backing_src_alias(t)->flag & MAP_SHARED; } +/* Aligns x up to the next multiple of size. Size must be a power of 2. */ +static inline uint64_t align_up(uint64_t x, uint64_t size) +{ + uint64_t mask = size - 1; + + TEST_ASSERT(size != 0 && !(size & (size - 1)), + "size not a power of 2: %lu", size); + return ((x + mask) & ~mask); +} + +static inline uint64_t align_down(uint64_t x, uint64_t size) +{ + uint64_t x_aligned_up = align_up(x, size); + + if (x == x_aligned_up) + return x; + else + return x_aligned_up - size; +} + +static inline void *align_ptr_up(void *x, size_t size) +{ + return (void *)align_up((unsigned long)x, size); +} + #endif /* SELFTEST_KVM_TEST_UTIL_H */ diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index 05e65ca1c3..8a470da7b7 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 #include +#include #include +#include #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); @@ -401,6 +438,11 @@ uint64_t vm_get_page_table_entry(struct kvm_vm *vm, int vcpuid, uint64_t vaddr); 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 @@ -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/include/x86_64/svm_util.h b/tools/testing/selftests/kvm/include/x86_64/svm_util.h index b7531c83b8..587fbe408b 100644 --- a/tools/testing/selftests/kvm/include/x86_64/svm_util.h +++ b/tools/testing/selftests/kvm/include/x86_64/svm_util.h @@ -46,4 +46,6 @@ static inline bool cpu_has_svm(void) return ecx & CPUID_SVM; } +int open_sev_dev_path_or_exit(void); + #endif /* SELFTEST_KVM_SVM_UTILS_H */ diff --git a/tools/testing/selftests/kvm/kvm_create_max_vcpus.c b/tools/testing/selftests/kvm/kvm_create_max_vcpus.c index aa3795cd7b..aed9dc3ca1 100644 --- a/tools/testing/selftests/kvm/kvm_create_max_vcpus.c +++ b/tools/testing/selftests/kvm/kvm_create_max_vcpus.c @@ -83,7 +83,7 @@ int main(int argc, char *argv[]) kvm_max_vcpu_id = kvm_max_vcpus; TEST_ASSERT(kvm_max_vcpu_id >= kvm_max_vcpus, - "KVM_MAX_VCPU_ID (%d) must be at least as large as KVM_MAX_VCPUS (%d).", + "KVM_MAX_VCPU_IDS (%d) must be at least as large as KVM_MAX_VCPUS (%d).", kvm_max_vcpu_id, kvm_max_vcpus); test_vcpu_creation(0, kvm_max_vcpus); diff --git a/tools/testing/selftests/kvm/kvm_page_table_test.c b/tools/testing/selftests/kvm/kvm_page_table_test.c index 36407cb0ec..ba1fdc3dcf 100644 --- a/tools/testing/selftests/kvm/kvm_page_table_test.c +++ b/tools/testing/selftests/kvm/kvm_page_table_test.c @@ -280,7 +280,7 @@ static struct kvm_vm *pre_init_before_test(enum vm_guest_mode mode, void *arg) #ifdef __s390x__ alignment = max(0x100000, alignment); #endif - guest_test_phys_mem &= ~(alignment - 1); + guest_test_phys_mem = align_down(guest_test_phys_mem, alignment); /* Set up the shared data structure test_args */ test_args.vm = vm; diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c index 632b74d6b3..9343d82519 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/processor.c +++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c @@ -8,6 +8,7 @@ #include #include +#include "guest_modes.h" #include "kvm_util.h" #include "../kvm_util_internal.h" #include "processor.h" @@ -212,7 +213,7 @@ void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) } } -void aarch64_vcpu_setup(struct kvm_vm *vm, int vcpuid, struct kvm_vcpu_init *init) +void aarch64_vcpu_setup(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_vcpu_init *init) { struct kvm_vcpu_init default_init = { .target = -1, }; uint64_t sctlr_el1, tcr_el1; @@ -232,11 +233,12 @@ void aarch64_vcpu_setup(struct kvm_vm *vm, int vcpuid, struct kvm_vcpu_init *ini * Enable FP/ASIMD to avoid trapping when accessing Q0-Q15 * registers, which the variable argument list macros do. */ - set_reg(vm, vcpuid, ARM64_SYS_REG(CPACR_EL1), 3 << 20); + set_reg(vm, vcpuid, KVM_ARM64_SYS_REG(SYS_CPACR_EL1), 3 << 20); - get_reg(vm, vcpuid, ARM64_SYS_REG(SCTLR_EL1), &sctlr_el1); - get_reg(vm, vcpuid, ARM64_SYS_REG(TCR_EL1), &tcr_el1); + 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 " @@ -245,24 +247,46 @@ void aarch64_vcpu_setup(struct kvm_vm *vm, int vcpuid, struct kvm_vcpu_init *ini 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 */ + 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 */ + 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: - tcr_el1 |= 0ul << 14; /* TG0 = 4KB */ - tcr_el1 |= 5ul << 32; /* IPS = 48 bits */ - break; + 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 */ + case VM_MODE_P40V48_16K: + case VM_MODE_P40V48_64K: tcr_el1 |= 2ul << 32; /* IPS = 40 bits */ break; - case VM_MODE_P40V48_64K: - tcr_el1 |= 1ul << 14; /* TG0 = 64KB */ - tcr_el1 |= 2ul << 32; /* IPS = 40 bits */ + 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); @@ -273,10 +297,11 @@ void aarch64_vcpu_setup(struct kvm_vm *vm, int vcpuid, struct kvm_vcpu_init *ini tcr_el1 |= (1 << 8) | (1 << 10) | (3 << 12); tcr_el1 |= (64 - vm->va_bits) /* T0SZ */; - set_reg(vm, vcpuid, ARM64_SYS_REG(SCTLR_EL1), sctlr_el1); - set_reg(vm, vcpuid, ARM64_SYS_REG(TCR_EL1), tcr_el1); - set_reg(vm, vcpuid, ARM64_SYS_REG(MAIR_EL1), DEFAULT_MAIR_EL1); - set_reg(vm, vcpuid, ARM64_SYS_REG(TTBR0_EL1), vm->pgd); + set_reg(vm, vcpuid, KVM_ARM64_SYS_REG(SYS_SCTLR_EL1), sctlr_el1); + set_reg(vm, vcpuid, KVM_ARM64_SYS_REG(SYS_TCR_EL1), tcr_el1); + set_reg(vm, vcpuid, KVM_ARM64_SYS_REG(SYS_MAIR_EL1), DEFAULT_MAIR_EL1); + set_reg(vm, vcpuid, KVM_ARM64_SYS_REG(SYS_TTBR0_EL1), vm->pgd); + set_reg(vm, vcpuid, KVM_ARM64_SYS_REG(SYS_TPIDR_EL1), vcpuid); } void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid, uint8_t indent) @@ -362,7 +387,7 @@ void vcpu_init_descriptor_tables(struct kvm_vm *vm, uint32_t vcpuid) { extern char vectors; - set_reg(vm, vcpuid, ARM64_SYS_REG(VBAR_EL1), (uint64_t)&vectors); + set_reg(vm, vcpuid, KVM_ARM64_SYS_REG(SYS_VBAR_EL1), (uint64_t)&vectors); } void route_exception(struct ex_regs *regs, int vector) @@ -426,3 +451,52 @@ void vm_install_exception_handler(struct kvm_vm *vm, int vector, assert(vector < VECTOR_NUM); handlers->exception_handlers[vector][0] = handler; } + +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, ®); + 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 b3a0fca0d7..f5cd0c536d 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/vgic.c +++ b/tools/testing/selftests/kvm/lib/aarch64/vgic.c @@ -52,7 +52,9 @@ int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, uint32_t nr_irqs, 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); diff --git a/tools/testing/selftests/kvm/lib/elf.c b/tools/testing/selftests/kvm/lib/elf.c index eac44f5d0d..13e8e3dcf9 100644 --- a/tools/testing/selftests/kvm/lib/elf.c +++ b/tools/testing/selftests/kvm/lib/elf.c @@ -157,8 +157,7 @@ void kvm_vm_elf_load(struct kvm_vm *vm, const char *filename) "memsize of 0,\n" " phdr index: %u p_memsz: 0x%" PRIx64, n1, (uint64_t) phdr.p_memsz); - vm_vaddr_t seg_vstart = phdr.p_vaddr; - seg_vstart &= ~(vm_vaddr_t)(vm->page_size - 1); + vm_vaddr_t seg_vstart = align_down(phdr.p_vaddr, vm->page_size); vm_vaddr_t seg_vend = phdr.p_vaddr + phdr.p_memsz - 1; seg_vend |= vm->page_size - 1; size_t seg_size = seg_vend - seg_vstart + 1; diff --git a/tools/testing/selftests/kvm/lib/guest_modes.c b/tools/testing/selftests/kvm/lib/guest_modes.c index c330f414ef..8784013b74 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 e9d0ab9567..d8cf851ab1 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -22,13 +22,17 @@ static int vcpu_mmap_sz(void); -/* Aligns x up to the next multiple of size. Size must be a power of 2. */ -static void *align(void *x, size_t size) +int open_path_or_exit(const char *path, int flags) { - size_t mask = size - 1; - TEST_ASSERT(size != 0 && !(size & (size - 1)), - "size not a power of 2: %lu", size); - return (void *) (((size_t) x + mask) & ~mask); + int fd; + + fd = open(path, flags); + if (fd < 0) { + print_skip("%s not available (errno: %d)", path, errno); + exit(KSFT_SKIP); + } + + return fd; } /* @@ -42,16 +46,7 @@ static void *align(void *x, size_t size) */ static int _open_kvm_dev_path_or_exit(int flags) { - int fd; - - fd = open(KVM_DEV_PATH, flags); - if (fd < 0) { - print_skip("%s not available, is KVM loaded? (errno: %d)", - KVM_DEV_PATH, errno); - exit(KSFT_SKIP); - } - - return fd; + return open_path_or_exit(KVM_DEV_PATH, flags); } int open_kvm_dev_path_or_exit(void) @@ -90,6 +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: @@ -171,12 +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?"); @@ -187,15 +215,21 @@ const char *vm_guest_mode_string(uint32_t i) } const struct vm_guest_mode_params vm_guest_mode_params[] = { - { 52, 48, 0x1000, 12 }, - { 52, 48, 0x10000, 16 }, - { 48, 48, 0x1000, 12 }, - { 48, 48, 0x10000, 16 }, - { 40, 48, 0x1000, 12 }, - { 40, 48, 0x10000, 16 }, - { 0, 0, 0x1000, 12 }, - { 47, 64, 0x1000, 12 }, - { 44, 64, 0x1000, 12 }, + [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?"); @@ -257,9 +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: @@ -448,9 +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); @@ -875,9 +921,17 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, alignment = 1; #endif + /* + * When using THP mmap is not guaranteed to returned a hugepage aligned + * address so we have to pad the mmap. Padding is not needed for HugeTLB + * because mmap will always return an address aligned to the HugeTLB + * page size. + */ if (src_type == VM_MEM_SRC_ANONYMOUS_THP) alignment = max(backing_src_pagesz, alignment); + ASSERT_EQ(guest_paddr, align_up(guest_paddr, backing_src_pagesz)); + /* Add enough memory to align up if necessary */ if (alignment > 1) region->mmap_size += alignment; @@ -910,8 +964,13 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, "test_malloc failed, mmap_start: %p errno: %i", region->mmap_start, errno); + TEST_ASSERT(!is_backing_src_hugetlb(src_type) || + region->mmap_start == align_ptr_up(region->mmap_start, backing_src_pagesz), + "mmap_start %p is not aligned to HugeTLB page size 0x%lx", + region->mmap_start, backing_src_pagesz); + /* Align host address */ - region->host_mem = align(region->mmap_start, alignment); + region->host_mem = align_ptr_up(region->mmap_start, alignment); /* As needed perform madvise */ if ((src_type == VM_MEM_SRC_ANONYMOUS || @@ -954,7 +1013,7 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, "mmap of alias failed, errno: %i", errno); /* Align host alias address */ - region->host_alias = align(region->mmap_alias, alignment); + region->host_alias = align_ptr_up(region->mmap_alias, alignment); } } @@ -1792,7 +1851,7 @@ 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 ret = _vcpu_sregs_set(vm, vcpuid, sregs); - TEST_ASSERT(ret == 0, "KVM_RUN IOCTL failed, " + TEST_ASSERT(ret == 0, "KVM_SET_SREGS IOCTL failed, " "rc: %i errno: %i", ret, errno); } @@ -1984,7 +2043,7 @@ int kvm_device_check_attr(int dev_fd, uint32_t group, uint64_t attr) { int ret = _kvm_device_check_attr(dev_fd, group, attr); - TEST_ASSERT(ret >= 0, "KVM_HAS_DEVICE_ATTR failed, rc: %i errno: %i", ret, errno); + TEST_ASSERT(!ret, "KVM_HAS_DEVICE_ATTR failed, rc: %i errno: %i", ret, errno); return ret; } @@ -2008,7 +2067,7 @@ int kvm_create_device(struct kvm_vm *vm, uint64_t type, bool test) ret = _kvm_create_device(vm, type, test, &fd); if (!test) { - TEST_ASSERT(ret >= 0, + TEST_ASSERT(!ret, "KVM_CREATE_DEVICE IOCTL failed, rc: %i errno: %i", ret, errno); return fd; } @@ -2036,10 +2095,120 @@ int kvm_device_access(int dev_fd, uint32_t group, uint64_t attr, { int ret = _kvm_device_access(dev_fd, group, attr, val, write); - TEST_ASSERT(ret >= 0, "KVM_SET|GET_DEVICE_ATTR IOCTL failed, rc: %i errno: %i", ret, errno); + TEST_ASSERT(!ret, "KVM_SET|GET_DEVICE_ATTR IOCTL failed, rc: %i errno: %i", ret, errno); return ret; } +int _vcpu_has_device_attr(struct kvm_vm *vm, uint32_t vcpuid, uint32_t group, + uint64_t attr) +{ + struct vcpu *vcpu = vcpu_find(vm, vcpuid); + + TEST_ASSERT(vcpu, "nonexistent vcpu id: %d", vcpuid); + + return _kvm_device_check_attr(vcpu->fd, group, attr); +} + +int vcpu_has_device_attr(struct kvm_vm *vm, uint32_t vcpuid, uint32_t group, + uint64_t attr) +{ + int ret = _vcpu_has_device_attr(vm, vcpuid, group, attr); + + TEST_ASSERT(!ret, "KVM_HAS_DEVICE_ATTR IOCTL failed, rc: %i errno: %i", ret, errno); + return ret; +} + +int _vcpu_access_device_attr(struct kvm_vm *vm, uint32_t vcpuid, uint32_t group, + uint64_t attr, void *val, bool write) +{ + struct vcpu *vcpu = vcpu_find(vm, vcpuid); + + TEST_ASSERT(vcpu, "nonexistent vcpu id: %d", vcpuid); + + return _kvm_device_access(vcpu->fd, group, attr, val, write); +} + +int vcpu_access_device_attr(struct kvm_vm *vm, uint32_t vcpuid, uint32_t group, + uint64_t attr, void *val, bool write) +{ + int ret = _vcpu_access_device_attr(vm, vcpuid, group, attr, val, write); + + TEST_ASSERT(!ret, "KVM_SET|GET_DEVICE_ATTR IOCTL failed, rc: %i errno: %i", ret, errno); + return ret; +} + +/* + * 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 * diff --git a/tools/testing/selftests/kvm/lib/perf_test_util.c b/tools/testing/selftests/kvm/lib/perf_test_util.c index 0ef80dbdc1..722df3a287 100644 --- a/tools/testing/selftests/kvm/lib/perf_test_util.c +++ b/tools/testing/selftests/kvm/lib/perf_test_util.c @@ -10,21 +10,40 @@ struct perf_test_args perf_test_args; -uint64_t guest_test_phys_mem; - /* * Guest virtual memory offset of the testing memory slot. * Must not conflict with identity mapped test code. */ static uint64_t guest_test_virt_mem = DEFAULT_GUEST_TEST_MEM; +struct vcpu_thread { + /* The id of the vCPU. */ + int vcpu_id; + + /* The pthread backing the vCPU. */ + pthread_t thread; + + /* Set to true once the vCPU thread is up and running. */ + bool running; +}; + +/* The vCPU threads involved in this test. */ +static struct vcpu_thread vcpu_threads[KVM_MAX_VCPUS]; + +/* The function run by each vCPU thread, as provided by the test. */ +static void (*vcpu_thread_fn)(struct perf_test_vcpu_args *); + +/* Set to true once all vCPU threads are up and running. */ +static bool all_vcpu_threads_running; + /* * Continuously write to the first 8 bytes of each page in the * specified region. */ static void guest_code(uint32_t vcpu_id) { - struct perf_test_vcpu_args *vcpu_args = &perf_test_args.vcpu_args[vcpu_id]; + struct perf_test_args *pta = &perf_test_args; + struct perf_test_vcpu_args *vcpu_args = &pta->vcpu_args[vcpu_id]; uint64_t gva; uint64_t pages; int i; @@ -37,9 +56,9 @@ static void guest_code(uint32_t vcpu_id) while (true) { for (i = 0; i < pages; i++) { - uint64_t addr = gva + (i * perf_test_args.guest_page_size); + uint64_t addr = gva + (i * pta->guest_page_size); - if (i % perf_test_args.wr_fract == 0) + if (i % pta->wr_fract == 0) *(uint64_t *)addr = 0x0123456789ABCDEF; else READ_ONCE(*(uint64_t *)addr); @@ -49,35 +68,81 @@ static void guest_code(uint32_t vcpu_id) } } +void perf_test_setup_vcpus(struct kvm_vm *vm, int vcpus, + uint64_t vcpu_memory_bytes, + bool partition_vcpu_memory_access) +{ + struct perf_test_args *pta = &perf_test_args; + struct perf_test_vcpu_args *vcpu_args; + int vcpu_id; + + for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) { + vcpu_args = &pta->vcpu_args[vcpu_id]; + + vcpu_args->vcpu_id = vcpu_id; + if (partition_vcpu_memory_access) { + vcpu_args->gva = guest_test_virt_mem + + (vcpu_id * vcpu_memory_bytes); + vcpu_args->pages = vcpu_memory_bytes / + pta->guest_page_size; + vcpu_args->gpa = pta->gpa + (vcpu_id * vcpu_memory_bytes); + } else { + vcpu_args->gva = guest_test_virt_mem; + vcpu_args->pages = (vcpus * vcpu_memory_bytes) / + pta->guest_page_size; + vcpu_args->gpa = pta->gpa; + } + + vcpu_args_set(vm, vcpu_id, 1, vcpu_id); + + pr_debug("Added VCPU %d with test mem gpa [%lx, %lx)\n", + vcpu_id, vcpu_args->gpa, vcpu_args->gpa + + (vcpu_args->pages * pta->guest_page_size)); + } +} + struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus, uint64_t vcpu_memory_bytes, int slots, - enum vm_mem_backing_src_type backing_src) + enum vm_mem_backing_src_type backing_src, + bool partition_vcpu_memory_access) { + struct perf_test_args *pta = &perf_test_args; struct kvm_vm *vm; uint64_t guest_num_pages; + uint64_t backing_src_pagesz = get_backing_src_pagesz(backing_src); int i; pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode)); - perf_test_args.host_page_size = getpagesize(); - perf_test_args.guest_page_size = vm_guest_mode_params[mode].page_size; + /* By default vCPUs will write to memory. */ + pta->wr_fract = 1; + + /* + * Snapshot the non-huge page size. This is used by the guest code to + * access/dirty pages at the logging granularity. + */ + pta->guest_page_size = vm_guest_mode_params[mode].page_size; guest_num_pages = vm_adjust_num_guest_pages(mode, - (vcpus * vcpu_memory_bytes) / perf_test_args.guest_page_size); + (vcpus * vcpu_memory_bytes) / pta->guest_page_size); - TEST_ASSERT(vcpu_memory_bytes % perf_test_args.host_page_size == 0, + TEST_ASSERT(vcpu_memory_bytes % getpagesize() == 0, "Guest memory size is not host page size aligned."); - TEST_ASSERT(vcpu_memory_bytes % perf_test_args.guest_page_size == 0, + TEST_ASSERT(vcpu_memory_bytes % pta->guest_page_size == 0, "Guest memory size is not guest page size aligned."); TEST_ASSERT(guest_num_pages % slots == 0, "Guest memory cannot be evenly divided into %d slots.", slots); + /* + * Pass guest_num_pages to populate the page tables for test memory. + * The memory is also added to memslot 0, but that's a benign side + * effect as KVM allows aliasing HVAs in meslots. + */ vm = vm_create_with_vcpus(mode, vcpus, DEFAULT_GUEST_PHY_PAGES, - (vcpus * vcpu_memory_bytes) / perf_test_args.guest_page_size, - 0, guest_code, NULL); + guest_num_pages, 0, guest_code, NULL); - perf_test_args.vm = vm; + pta->vm = vm; /* * If there should be more memory in the guest test region than there @@ -90,20 +155,18 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus, guest_num_pages, vm_get_max_gfn(vm), vcpus, vcpu_memory_bytes); - guest_test_phys_mem = (vm_get_max_gfn(vm) - guest_num_pages) * - perf_test_args.guest_page_size; - guest_test_phys_mem &= ~(perf_test_args.host_page_size - 1); + pta->gpa = (vm_get_max_gfn(vm) - guest_num_pages) * pta->guest_page_size; + pta->gpa = align_down(pta->gpa, backing_src_pagesz); #ifdef __s390x__ /* Align to 1M (segment size) */ - guest_test_phys_mem &= ~((1 << 20) - 1); + pta->gpa = align_down(pta->gpa, 1 << 20); #endif - pr_info("guest physical test memory offset: 0x%lx\n", guest_test_phys_mem); + pr_info("guest physical test memory offset: 0x%lx\n", pta->gpa); /* Add extra memory slots for testing */ for (i = 0; i < slots; i++) { uint64_t region_pages = guest_num_pages / slots; - vm_paddr_t region_start = guest_test_phys_mem + - region_pages * perf_test_args.guest_page_size * i; + vm_paddr_t region_start = pta->gpa + region_pages * pta->guest_page_size * i; vm_userspace_mem_region_add(vm, backing_src, region_start, PERF_TEST_MEM_SLOT_INDEX + i, @@ -111,10 +174,15 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus, } /* Do mapping for the demand paging memory slot */ - virt_map(vm, guest_test_virt_mem, guest_test_phys_mem, guest_num_pages); + virt_map(vm, guest_test_virt_mem, pta->gpa, guest_num_pages); + + perf_test_setup_vcpus(vm, vcpus, vcpu_memory_bytes, partition_vcpu_memory_access); ucall_init(vm, NULL); + /* Export the shared variables to the guest. */ + sync_global_to_guest(vm, perf_test_args); + return vm; } @@ -124,36 +192,60 @@ void perf_test_destroy_vm(struct kvm_vm *vm) kvm_vm_free(vm); } -void perf_test_setup_vcpus(struct kvm_vm *vm, int vcpus, - uint64_t vcpu_memory_bytes, - bool partition_vcpu_memory_access) +void perf_test_set_wr_fract(struct kvm_vm *vm, int wr_fract) +{ + perf_test_args.wr_fract = wr_fract; + sync_global_to_guest(vm, perf_test_args); +} + +static void *vcpu_thread_main(void *data) +{ + struct vcpu_thread *vcpu = data; + + WRITE_ONCE(vcpu->running, true); + + /* + * Wait for all vCPU threads to be up and running before calling the test- + * provided vCPU thread function. This prevents thread creation (which + * requires taking the mmap_sem in write mode) from interfering with the + * guest faulting in its memory. + */ + while (!READ_ONCE(all_vcpu_threads_running)) + ; + + vcpu_thread_fn(&perf_test_args.vcpu_args[vcpu->vcpu_id]); + + return NULL; +} + +void perf_test_start_vcpu_threads(int vcpus, void (*vcpu_fn)(struct perf_test_vcpu_args *)) { - vm_paddr_t vcpu_gpa; - struct perf_test_vcpu_args *vcpu_args; int vcpu_id; + vcpu_thread_fn = vcpu_fn; + WRITE_ONCE(all_vcpu_threads_running, false); + for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) { - vcpu_args = &perf_test_args.vcpu_args[vcpu_id]; + struct vcpu_thread *vcpu = &vcpu_threads[vcpu_id]; - vcpu_args->vcpu_id = vcpu_id; - if (partition_vcpu_memory_access) { - vcpu_args->gva = guest_test_virt_mem + - (vcpu_id * vcpu_memory_bytes); - vcpu_args->pages = vcpu_memory_bytes / - perf_test_args.guest_page_size; - vcpu_gpa = guest_test_phys_mem + - (vcpu_id * vcpu_memory_bytes); - } else { - vcpu_args->gva = guest_test_virt_mem; - vcpu_args->pages = (vcpus * vcpu_memory_bytes) / - perf_test_args.guest_page_size; - vcpu_gpa = guest_test_phys_mem; - } + vcpu->vcpu_id = vcpu_id; + WRITE_ONCE(vcpu->running, false); - vcpu_args_set(vm, vcpu_id, 1, vcpu_id); - - pr_debug("Added VCPU %d with test mem gpa [%lx, %lx)\n", - vcpu_id, vcpu_gpa, vcpu_gpa + - (vcpu_args->pages * perf_test_args.guest_page_size)); + pthread_create(&vcpu->thread, NULL, vcpu_thread_main, vcpu); } + + for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) { + while (!READ_ONCE(vcpu_threads[vcpu_id].running)) + ; + } + + WRITE_ONCE(all_vcpu_threads_running, true); +} + +void perf_test_join_vcpu_threads(int vcpus) +{ + int vcpu_id; + + for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) + pthread_join(vcpu_threads[vcpu_id].thread, NULL); } diff --git a/tools/testing/selftests/kvm/lib/sparsebit.c b/tools/testing/selftests/kvm/lib/sparsebit.c index a0d0c83d83..50e0cf41a7 100644 --- a/tools/testing/selftests/kvm/lib/sparsebit.c +++ b/tools/testing/selftests/kvm/lib/sparsebit.c @@ -1866,7 +1866,7 @@ void sparsebit_validate_internal(struct sparsebit *s) * of total bits set. */ if (s->num_set != total_bits_set) { - fprintf(stderr, "Number of bits set missmatch,\n" + fprintf(stderr, "Number of bits set mismatch,\n" " s->num_set: 0x%lx total_bits_set: 0x%lx", s->num_set, total_bits_set); diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c index b724291089..6d23878bbf 100644 --- a/tools/testing/selftests/kvm/lib/test_util.c +++ b/tools/testing/selftests/kvm/lib/test_util.c @@ -283,6 +283,11 @@ size_t get_backing_src_pagesz(uint32_t i) } } +bool is_backing_src_hugetlb(uint32_t i) +{ + return !!(vm_mem_backing_src_alias(i)->flag & MAP_HUGETLB); +} + static void print_available_backing_src_types(const char *prefix) { int i; diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index da73b97e1e..9f000dfb55 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; @@ -660,6 +714,7 @@ void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code) /* Create VCPU */ vm_vcpu_add(vm, vcpuid); + vcpu_set_cpuid(vm, vcpuid, kvm_get_supported_cpuid()); vcpu_setup(vm, vcpuid); /* Setup guest general purpose registers */ @@ -672,9 +727,6 @@ void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code) /* Setup the MP state */ mp_state.mp_state = 0; vcpu_set_mp_state(vm, vcpuid, &mp_state); - - /* Setup supported CPUIDs */ - vcpu_set_cpuid(vm, vcpuid, kvm_get_supported_cpuid()); } /* @@ -849,6 +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 * @@ -866,12 +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); @@ -1019,21 +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; @@ -1071,6 +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); @@ -1098,25 +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); @@ -1125,17 +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; @@ -1143,12 +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; @@ -1159,9 +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); @@ -1169,41 +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__( @@ -1212,10 +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; @@ -1339,6 +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) { @@ -1434,22 +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 */ @@ -1459,11 +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 */ @@ -1473,6 +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/lib/x86_64/svm.c b/tools/testing/selftests/kvm/lib/x86_64/svm.c index 161eba7cd1..0ebc03ce07 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/svm.c +++ b/tools/testing/selftests/kvm/lib/x86_64/svm.c @@ -13,6 +13,8 @@ #include "processor.h" #include "svm_util.h" +#define SEV_DEV_PATH "/dev/sev" + struct gpr64_regs guest_regs; u64 rflags; @@ -172,3 +174,14 @@ void nested_svm_check_supported(void) exit(KSFT_SKIP); } } + +/* + * Open SEV_DEV_PATH if available, otherwise exit the entire program. + * + * Return: + * The opened file descriptor of /dev/sev. + */ +int open_sev_dev_path_or_exit(void) +{ + return open_path_or_exit(SEV_DEV_PATH, 0); +} diff --git a/tools/testing/selftests/kvm/memslot_modification_stress_test.c b/tools/testing/selftests/kvm/memslot_modification_stress_test.c index 4cfcafea9f..1410d0a914 100644 --- a/tools/testing/selftests/kvm/memslot_modification_stress_test.c +++ b/tools/testing/selftests/kvm/memslot_modification_stress_test.c @@ -36,11 +36,9 @@ static uint64_t guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE; static bool run_vcpus = true; -static void *vcpu_worker(void *data) +static void vcpu_worker(struct perf_test_vcpu_args *vcpu_args) { int ret; - struct perf_test_vcpu_args *vcpu_args = - (struct perf_test_vcpu_args *)data; int vcpu_id = vcpu_args->vcpu_id; struct kvm_vm *vm = perf_test_args.vm; struct kvm_run *run; @@ -59,8 +57,6 @@ static void *vcpu_worker(void *data) "Invalid guest sync status: exit_reason=%s\n", exit_reason_str(run->exit_reason)); } - - return NULL; } struct memslot_antagonist_args { @@ -80,7 +76,7 @@ static void add_remove_memslot(struct kvm_vm *vm, useconds_t delay, * Add the dummy memslot just below the perf_test_util memslot, which is * at the top of the guest physical address space. */ - gpa = guest_test_phys_mem - pages * vm_get_page_size(vm); + gpa = perf_test_args.gpa - pages * vm_get_page_size(vm); for (i = 0; i < nr_modifications; i++) { usleep(delay); @@ -100,29 +96,15 @@ struct test_params { static void run_test(enum vm_guest_mode mode, void *arg) { struct test_params *p = arg; - pthread_t *vcpu_threads; struct kvm_vm *vm; - int vcpu_id; vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size, 1, - VM_MEM_SRC_ANONYMOUS); - - perf_test_args.wr_fract = 1; - - vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads)); - TEST_ASSERT(vcpu_threads, "Memory allocation failed"); - - perf_test_setup_vcpus(vm, nr_vcpus, guest_percpu_mem_size, - p->partition_vcpu_memory_access); - - /* Export the shared variables to the guest */ - sync_global_to_guest(vm, perf_test_args); + VM_MEM_SRC_ANONYMOUS, + p->partition_vcpu_memory_access); pr_info("Finished creating vCPUs\n"); - for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) - pthread_create(&vcpu_threads[vcpu_id], NULL, vcpu_worker, - &perf_test_args.vcpu_args[vcpu_id]); + perf_test_start_vcpu_threads(nr_vcpus, vcpu_worker); pr_info("Started all vCPUs\n"); @@ -131,16 +113,10 @@ static void run_test(enum vm_guest_mode mode, void *arg) run_vcpus = false; - /* Wait for the vcpu threads to quit */ - for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) - pthread_join(vcpu_threads[vcpu_id], NULL); - + perf_test_join_vcpu_threads(nr_vcpus); pr_info("All vCPU threads joined\n"); - ucall_uninit(vm); - kvm_vm_free(vm); - - free(vcpu_threads); + perf_test_destroy_vm(vm); } static void help(char *name) diff --git a/tools/testing/selftests/kvm/memslot_perf_test.c b/tools/testing/selftests/kvm/memslot_perf_test.c index d6e381e01d..1727f75e0c 100644 --- a/tools/testing/selftests/kvm/memslot_perf_test.c +++ b/tools/testing/selftests/kvm/memslot_perf_test.c @@ -127,43 +127,54 @@ static bool verbose; pr_info(__VA_ARGS__); \ } while (0) +static void check_mmio_access(struct vm_data *vm, struct kvm_run *run) +{ + TEST_ASSERT(vm->mmio_ok, "Unexpected mmio exit"); + TEST_ASSERT(run->mmio.is_write, "Unexpected mmio read"); + TEST_ASSERT(run->mmio.len == 8, + "Unexpected exit mmio size = %u", run->mmio.len); + TEST_ASSERT(run->mmio.phys_addr >= vm->mmio_gpa_min && + run->mmio.phys_addr <= vm->mmio_gpa_max, + "Unexpected exit mmio address = 0x%llx", + run->mmio.phys_addr); +} + static void *vcpu_worker(void *data) { struct vm_data *vm = data; struct kvm_run *run; struct ucall uc; - uint64_t cmd; run = vcpu_state(vm->vm, VCPU_ID); while (1) { vcpu_run(vm->vm, VCPU_ID); - if (run->exit_reason == KVM_EXIT_IO) { - cmd = get_ucall(vm->vm, VCPU_ID, &uc); - if (cmd != UCALL_SYNC) - break; - + switch (get_ucall(vm->vm, VCPU_ID, &uc)) { + case UCALL_SYNC: + TEST_ASSERT(uc.args[1] == 0, + "Unexpected sync ucall, got %lx", + (ulong)uc.args[1]); sem_post(&vcpu_ready); continue; - } - - if (run->exit_reason != KVM_EXIT_MMIO) + case UCALL_NONE: + if (run->exit_reason == KVM_EXIT_MMIO) + check_mmio_access(vm, run); + else + goto done; break; - - TEST_ASSERT(vm->mmio_ok, "Unexpected mmio exit"); - TEST_ASSERT(run->mmio.is_write, "Unexpected mmio read"); - TEST_ASSERT(run->mmio.len == 8, - "Unexpected exit mmio size = %u", run->mmio.len); - TEST_ASSERT(run->mmio.phys_addr >= vm->mmio_gpa_min && - run->mmio.phys_addr <= vm->mmio_gpa_max, - "Unexpected exit mmio address = 0x%llx", - run->mmio.phys_addr); + case UCALL_ABORT: + TEST_FAIL("%s at %s:%ld, val = %lu", + (const char *)uc.args[0], + __FILE__, uc.args[1], uc.args[2]); + break; + case UCALL_DONE: + goto done; + default: + TEST_FAIL("Unknown ucall %lu", uc.cmd); + } } - if (run->exit_reason == KVM_EXIT_IO && cmd == UCALL_ABORT) - TEST_FAIL("%s at %s:%ld, val = %lu", (const char *)uc.args[0], - __FILE__, uc.args[1], uc.args[2]); - +done: return NULL; } @@ -268,6 +279,7 @@ static bool prepare_vm(struct vm_data *data, int nslots, uint64_t *maxslots, TEST_ASSERT(data->hva_slots, "malloc() fail"); data->vm = vm_create_default(VCPU_ID, mempages, guest_code); + ucall_init(data->vm, NULL); pr_info_v("Adding slots 1..%i, each slot with %"PRIu64" pages + %"PRIu64" extra pages last\n", max_mem_slots - 1, data->pages_per_slot, rempages); diff --git a/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c b/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c index f40fd097cb..6f6fd189dd 100644 --- a/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c +++ b/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c @@ -109,8 +109,7 @@ int main(int argc, char *argv[]) } } - kvm_vm_free(vm); - done: + kvm_vm_free(vm); return 0; } diff --git a/tools/testing/selftests/kvm/x86_64/evmcs_test.c b/tools/testing/selftests/kvm/x86_64/evmcs_test.c index 2b46dcca86..4c7841dfd4 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(®s2, 0, sizeof(regs2)); vcpu_regs_get(vm, VCPU_ID, ®s2); diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_features.c b/tools/testing/selftests/kvm/x86_64/hyperv_features.c index 91d88aaa98..672915ce73 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_features.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_features.c @@ -165,10 +165,10 @@ static void hv_set_cpuid(struct kvm_vm *vm, struct kvm_cpuid2 *cpuid, vcpu_set_cpuid(vm, VCPU_ID, cpuid); } -static void guest_test_msrs_access(struct kvm_vm *vm, struct msr_data *msr, - struct kvm_cpuid2 *best) +static void guest_test_msrs_access(void) { struct kvm_run *run; + struct kvm_vm *vm; struct ucall uc; int stage = 0, r; struct kvm_cpuid_entry2 feat = { @@ -180,11 +180,34 @@ static void guest_test_msrs_access(struct kvm_vm *vm, struct msr_data *msr, struct kvm_cpuid_entry2 dbg = { .function = HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES }; - struct kvm_enable_cap cap = {0}; - - run = vcpu_state(vm, VCPU_ID); + struct kvm_cpuid2 *best; + vm_vaddr_t msr_gva; + struct kvm_enable_cap cap = { + .cap = KVM_CAP_HYPERV_ENFORCE_CPUID, + .args = {1} + }; + struct msr_data *msr; while (true) { + vm = vm_create_default(VCPU_ID, 0, guest_msr); + + msr_gva = vm_vaddr_alloc_page(vm); + memset(addr_gva2hva(vm, msr_gva), 0x0, getpagesize()); + msr = addr_gva2hva(vm, msr_gva); + + vcpu_args_set(vm, VCPU_ID, 1, msr_gva); + vcpu_enable_cap(vm, VCPU_ID, &cap); + + vcpu_set_hv_cpuid(vm, VCPU_ID); + + best = kvm_get_supported_hv_cpuid(); + + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(vm, VCPU_ID); + vm_install_exception_handler(vm, GP_VECTOR, guest_gp_handler); + + run = vcpu_state(vm, VCPU_ID); + switch (stage) { case 0: /* @@ -315,6 +338,7 @@ static void guest_test_msrs_access(struct kvm_vm *vm, struct msr_data *msr, * capability enabled and guest visible CPUID bit unset. */ cap.cap = KVM_CAP_HYPERV_SYNIC2; + cap.args[0] = 0; vcpu_enable_cap(vm, VCPU_ID, &cap); break; case 22: @@ -461,9 +485,9 @@ static void guest_test_msrs_access(struct kvm_vm *vm, struct msr_data *msr, switch (get_ucall(vm, VCPU_ID, &uc)) { case UCALL_SYNC: - TEST_ASSERT(uc.args[1] == stage, - "Unexpected stage: %ld (%d expected)\n", - uc.args[1], stage); + TEST_ASSERT(uc.args[1] == 0, + "Unexpected stage: %ld (0 expected)\n", + uc.args[1]); break; case UCALL_ABORT: TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0], @@ -474,13 +498,14 @@ static void guest_test_msrs_access(struct kvm_vm *vm, struct msr_data *msr, } stage++; + kvm_vm_free(vm); } } -static void guest_test_hcalls_access(struct kvm_vm *vm, struct hcall_data *hcall, - void *input, void *output, struct kvm_cpuid2 *best) +static void guest_test_hcalls_access(void) { struct kvm_run *run; + struct kvm_vm *vm; struct ucall uc; int stage = 0, r; struct kvm_cpuid_entry2 feat = { @@ -493,10 +518,38 @@ static void guest_test_hcalls_access(struct kvm_vm *vm, struct hcall_data *hcall struct kvm_cpuid_entry2 dbg = { .function = HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES }; - - run = vcpu_state(vm, VCPU_ID); + struct kvm_enable_cap cap = { + .cap = KVM_CAP_HYPERV_ENFORCE_CPUID, + .args = {1} + }; + vm_vaddr_t hcall_page, hcall_params; + struct hcall_data *hcall; + struct kvm_cpuid2 *best; while (true) { + vm = vm_create_default(VCPU_ID, 0, guest_hcall); + + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(vm, VCPU_ID); + vm_install_exception_handler(vm, UD_VECTOR, guest_ud_handler); + + /* Hypercall input/output */ + hcall_page = vm_vaddr_alloc_pages(vm, 2); + hcall = addr_gva2hva(vm, hcall_page); + memset(addr_gva2hva(vm, hcall_page), 0x0, 2 * getpagesize()); + + hcall_params = vm_vaddr_alloc_page(vm); + memset(addr_gva2hva(vm, hcall_params), 0x0, getpagesize()); + + vcpu_args_set(vm, VCPU_ID, 2, addr_gva2gpa(vm, hcall_page), hcall_params); + vcpu_enable_cap(vm, VCPU_ID, &cap); + + vcpu_set_hv_cpuid(vm, VCPU_ID); + + best = kvm_get_supported_hv_cpuid(); + + run = vcpu_state(vm, VCPU_ID); + switch (stage) { case 0: hcall->control = 0xdeadbeef; @@ -606,9 +659,9 @@ static void guest_test_hcalls_access(struct kvm_vm *vm, struct hcall_data *hcall switch (get_ucall(vm, VCPU_ID, &uc)) { case UCALL_SYNC: - TEST_ASSERT(uc.args[1] == stage, - "Unexpected stage: %ld (%d expected)\n", - uc.args[1], stage); + TEST_ASSERT(uc.args[1] == 0, + "Unexpected stage: %ld (0 expected)\n", + uc.args[1]); break; case UCALL_ABORT: TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0], @@ -619,66 +672,15 @@ static void guest_test_hcalls_access(struct kvm_vm *vm, struct hcall_data *hcall } stage++; + kvm_vm_free(vm); } } int main(void) { - struct kvm_cpuid2 *best; - struct kvm_vm *vm; - vm_vaddr_t msr_gva, hcall_page, hcall_params; - struct kvm_enable_cap cap = { - .cap = KVM_CAP_HYPERV_ENFORCE_CPUID, - .args = {1} - }; - - /* Test MSRs */ - vm = vm_create_default(VCPU_ID, 0, guest_msr); - - msr_gva = vm_vaddr_alloc_page(vm); - memset(addr_gva2hva(vm, msr_gva), 0x0, getpagesize()); - vcpu_args_set(vm, VCPU_ID, 1, msr_gva); - vcpu_enable_cap(vm, VCPU_ID, &cap); - - vcpu_set_hv_cpuid(vm, VCPU_ID); - - best = kvm_get_supported_hv_cpuid(); - - vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vm, VCPU_ID); - vm_install_exception_handler(vm, GP_VECTOR, guest_gp_handler); - pr_info("Testing access to Hyper-V specific MSRs\n"); - guest_test_msrs_access(vm, addr_gva2hva(vm, msr_gva), - best); - kvm_vm_free(vm); - - /* Test hypercalls */ - vm = vm_create_default(VCPU_ID, 0, guest_hcall); - - vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vm, VCPU_ID); - vm_install_exception_handler(vm, UD_VECTOR, guest_ud_handler); - - /* Hypercall input/output */ - hcall_page = vm_vaddr_alloc_pages(vm, 2); - memset(addr_gva2hva(vm, hcall_page), 0x0, 2 * getpagesize()); - - hcall_params = vm_vaddr_alloc_page(vm); - memset(addr_gva2hva(vm, hcall_params), 0x0, getpagesize()); - - vcpu_args_set(vm, VCPU_ID, 2, addr_gva2gpa(vm, hcall_page), hcall_params); - vcpu_enable_cap(vm, VCPU_ID, &cap); - - vcpu_set_hv_cpuid(vm, VCPU_ID); - - best = kvm_get_supported_hv_cpuid(); + guest_test_msrs_access(); pr_info("Testing access to Hyper-V hypercalls\n"); - guest_test_hcalls_access(vm, addr_gva2hva(vm, hcall_params), - addr_gva2hva(vm, hcall_page), - addr_gva2hva(vm, hcall_page) + getpagesize(), - best); - - kvm_vm_free(vm); + guest_test_hcalls_access(); } diff --git a/tools/testing/selftests/kvm/x86_64/smm_test.c b/tools/testing/selftests/kvm/x86_64/smm_test.c index db2a17559c..a626d40fdb 100644 --- a/tools/testing/selftests/kvm/x86_64/smm_test.c +++ b/tools/testing/selftests/kvm/x86_64/smm_test.c @@ -211,7 +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 32854c1462..2e0a92da8f 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(®s2, 0, sizeof(regs2)); vcpu_regs_get(vm, VCPU_ID, ®s2); diff --git a/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c b/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c index df04f56ce8..30a81038df 100644 --- a/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c +++ b/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c @@ -75,7 +75,7 @@ static void l1_guest_code(struct svm_test_data *svm) vmcb->control.int_ctl &= ~V_INTR_MASKING_MASK; /* No intercepts for real and virtual interrupts */ - vmcb->control.intercept &= ~(1ULL << INTERCEPT_INTR | INTERCEPT_VINTR); + vmcb->control.intercept &= ~(BIT(INTERCEPT_INTR) | BIT(INTERCEPT_VINTR)); /* Make a virtual interrupt VINTR_IRQ_NUMBER pending */ vmcb->control.int_ctl |= V_IRQ_MASK | (0x1 << V_INTR_PRIO_SHIFT); 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 5a6a662f2e..a426078b16 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 2835a17f1b..edac8839e7 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_pmu_msrs_test.c b/tools/testing/selftests/kvm/x86_64/vmx_pmu_msrs_test.c index 23051d84b9..2454a1f2ca 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_pmu_msrs_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_pmu_msrs_test.c @@ -110,22 +110,5 @@ int main(int argc, char *argv[]) ret = _vcpu_set_msr(vm, 0, MSR_IA32_PERF_CAPABILITIES, PMU_CAP_LBR_FMT); TEST_ASSERT(ret == 0, "Bad PERF_CAPABILITIES didn't fail."); - /* testcase 4, set capabilities when we don't have PDCM bit */ - entry_1_0->ecx &= ~X86_FEATURE_PDCM; - vcpu_set_cpuid(vm, VCPU_ID, cpuid); - ret = _vcpu_set_msr(vm, 0, MSR_IA32_PERF_CAPABILITIES, host_cap.capabilities); - TEST_ASSERT(ret == 0, "Bad PERF_CAPABILITIES didn't fail."); - - /* testcase 5, set capabilities when we don't have PMU version bits */ - entry_1_0->ecx |= X86_FEATURE_PDCM; - eax.split.version_id = 0; - entry_1_0->ecx = eax.full; - vcpu_set_cpuid(vm, VCPU_ID, cpuid); - ret = _vcpu_set_msr(vm, 0, MSR_IA32_PERF_CAPABILITIES, PMU_CAP_FW_WRITES); - TEST_ASSERT(ret == 0, "Bad PERF_CAPABILITIES didn't fail."); - - vcpu_set_msr(vm, 0, MSR_IA32_PERF_CAPABILITIES, 0); - ASSERT_EQ(vcpu_get_msr(vm, VCPU_ID, MSR_IA32_PERF_CAPABILITIES), 0); - kvm_vm_free(vm); } 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 a07480aed3..ff92e25b6f 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(®s2, 0, sizeof(regs2)); vcpu_regs_get(vm, VCPU_ID, ®s2); 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 eda0d2a512..865e171468 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 #include #include +#include + +#include #define VCPU_ID 5 @@ -22,10 +25,19 @@ #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) + +#define EVTCHN_VECTOR 0x10 static struct kvm_vm *vm; @@ -34,20 +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 { @@ -56,15 +68,66 @@ struct vcpu_runstate_info { uint64_t time[4]; }; +struct arch_vcpu_info { + unsigned long cr2; + unsigned long pad; /* sizeof(vcpu_info_t) == 64 */ +}; + +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; +}; /* 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); +} + static void guest_code(void) { struct vcpu_runstate_info *rs = (void *)RUNSTATE_VADDR; + __asm__ __volatile__( + "sti\n" + "nop\n" + ); + + /* Trigger an interrupt injection */ + GUEST_SYNC(0); + /* Test having the host set runstates manually */ GUEST_SYNC(RUNSTATE_runnable); GUEST_ASSERT(rs->time[RUNSTATE_runnable] != 0); @@ -94,7 +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) @@ -111,9 +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) ) { @@ -122,6 +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); @@ -133,6 +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, @@ -151,9 +247,19 @@ 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 = SHINFO_REGION_GPA + 0x40, + .u.gpa = VCPU_INFO_ADDR, }; vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &vi); @@ -163,6 +269,16 @@ int main(int argc, char *argv[]) }; vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &pvclock); + struct kvm_xen_hvm_attr vec = { + .type = KVM_XEN_ATTR_TYPE_UPCALL_VECTOR, + .u.vector = EVTCHN_VECTOR, + }; + vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &vec); + + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(vm, VCPU_ID); + vm_install_exception_handler(vm, EVTCHN_VECTOR, evtchn_handler); + if (do_runstate_tests) { struct kvm_xen_vcpu_attr st = { .type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR, @@ -171,9 +287,57 @@ 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; + struct vcpu_runstate_info *rs = addr_gpa2hva(vm, RUNSTATE_ADDR); rs->state = 0x5a; + bool evtchn_irq_expected = false; + for (;;) { volatile struct kvm_run *run = vcpu_state(vm, VCPU_ID); struct ucall uc; @@ -193,21 +357,33 @@ int main(int argc, char *argv[]) struct kvm_xen_vcpu_attr rst; long rundelay; - /* If no runstate support, bail out early */ - if (!do_runstate_tests) - goto done; - - TEST_ASSERT(rs->state_entry_time == rs->time[0] + - rs->time[1] + rs->time[2] + rs->time[3], - "runstate times don't add up"); + if (do_runstate_tests) + TEST_ASSERT(rs->state_entry_time == rs->time[0] + + rs->time[1] + rs->time[2] + rs->time[3], + "runstate times don't add up"); switch (uc.args[1]) { - case RUNSTATE_running...RUNSTATE_offline: + case 0: + if (verbose) + printf("Delivering evtchn upcall\n"); + evtchn_irq_expected = true; + vinfo->evtchn_upcall_pending = 1; + break; + + case RUNSTATE_runnable...RUNSTATE_offline: + 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; @@ -221,6 +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; @@ -229,13 +407,55 @@ 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; } @@ -261,9 +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"); @@ -284,6 +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/landlock/common.h b/tools/testing/selftests/landlock/common.h index 20e2a9286d..183b7e8e1b 100644 --- a/tools/testing/selftests/landlock/common.h +++ b/tools/testing/selftests/landlock/common.h @@ -17,10 +17,6 @@ #include "../kselftest_harness.h" -#ifndef ARRAY_SIZE -#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) -#endif - /* * TEST_F_FORK() is useful when a test drop privileges but the corresponding * FIXTURE_TEARDOWN() requires them (e.g. to remove files from a directory diff --git a/tools/testing/selftests/lkdtm/config b/tools/testing/selftests/lkdtm/config index 38edea2563..a26a3fa9e9 100644 --- a/tools/testing/selftests/lkdtm/config +++ b/tools/testing/selftests/lkdtm/config @@ -8,3 +8,4 @@ CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT=y CONFIG_INIT_ON_ALLOC_DEFAULT_ON=y CONFIG_UBSAN_BOUNDS=y CONFIG_UBSAN_TRAP=y +CONFIG_STACKPROTECTOR_STRONG=y diff --git a/tools/testing/selftests/lkdtm/run.sh b/tools/testing/selftests/lkdtm/run.sh index e95e79bd31..95e9049592 100644 --- a/tools/testing/selftests/lkdtm/run.sh +++ b/tools/testing/selftests/lkdtm/run.sh @@ -56,8 +56,14 @@ if echo "$test" | grep -q '^#' ; then fi # If no expected output given, assume an Oops with back trace is success. +repeat=1 if [ -z "$expect" ]; then expect="call trace:" +else + if echo "$expect" | grep -q '^repeat:' ; then + repeat=$(echo "$expect" | cut -d' ' -f1 | cut -d: -f2) + expect=$(echo "$expect" | cut -d' ' -f2-) + fi fi # Prepare log for report checking @@ -83,7 +89,9 @@ dmesg > "$DMESG" # the signal that killed the subprocess, we must ignore the failure and # continue. However we don't silence stderr since there might be other # useful details reported there in the case of other unexpected conditions. -echo "$test" | cat >"$TRIGGER" || true +for i in $(seq 1 $repeat); do + echo "$test" | cat >"$TRIGGER" || true +done # Record and dump the results dmesg | comm --nocheck-order -13 "$DMESG" - > "$LOG" || true diff --git a/tools/testing/selftests/lkdtm/stack-entropy.sh b/tools/testing/selftests/lkdtm/stack-entropy.sh index 1b4d95d575..14fedeef76 100644 --- a/tools/testing/selftests/lkdtm/stack-entropy.sh +++ b/tools/testing/selftests/lkdtm/stack-entropy.sh @@ -4,13 +4,27 @@ # Measure kernel stack entropy by sampling via LKDTM's REPORT_STACK test. set -e samples="${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/lkdtm/tests.txt b/tools/testing/selftests/lkdtm/tests.txt index 09f7bfa383..6b36b7f5dc 100644 --- a/tools/testing/selftests/lkdtm/tests.txt +++ b/tools/testing/selftests/lkdtm/tests.txt @@ -12,6 +12,7 @@ CORRUPT_LIST_ADD list_add corruption CORRUPT_LIST_DEL list_del corruption STACK_GUARD_PAGE_LEADING STACK_GUARD_PAGE_TRAILING +REPORT_STACK_CANARY repeat:2 ok: stack canaries differ UNSET_SMEP pinned CR4 bits changed: DOUBLE_FAULT CORRUPT_PAC diff --git a/tools/testing/selftests/memory-hotplug/config b/tools/testing/selftests/memory-hotplug/config index a7e8cd5bb2..1eef042a31 100644 --- a/tools/testing/selftests/memory-hotplug/config +++ b/tools/testing/selftests/memory-hotplug/config @@ -1,5 +1,4 @@ CONFIG_MEMORY_HOTPLUG=y -CONFIG_MEMORY_HOTPLUG_SPARSE=y CONFIG_NOTIFIER_ERROR_INJECTION=y CONFIG_MEMORY_NOTIFIER_ERROR_INJECT=m CONFIG_MEMORY_HOTREMOVE=y diff --git a/tools/testing/selftests/mount/unprivileged-remount-test.c b/tools/testing/selftests/mount/unprivileged-remount-test.c index 584dc6bc3b..d2917054fe 100644 --- a/tools/testing/selftests/mount/unprivileged-remount-test.c +++ b/tools/testing/selftests/mount/unprivileged-remount-test.c @@ -204,7 +204,7 @@ bool test_unpriv_remount(const char *fstype, const char *mount_options, if (!WIFEXITED(status)) { die("child did not terminate cleanly\n"); } - return WEXITSTATUS(status) == EXIT_SUCCESS ? true : false; + return WEXITSTATUS(status) == EXIT_SUCCESS; } create_and_enter_userns(); @@ -282,7 +282,7 @@ static bool test_priv_mount_unpriv_remount(void) if (!WIFEXITED(status)) { die("child did not terminate cleanly\n"); } - return WEXITSTATUS(status) == EXIT_SUCCESS ? true : false; + return WEXITSTATUS(status) == EXIT_SUCCESS; } orig_mnt_flags = read_mnt_flags(orig_path); diff --git a/tools/testing/selftests/move_mount_set_group/move_mount_set_group_test.c b/tools/testing/selftests/move_mount_set_group/move_mount_set_group_test.c index 860198f83a..50ed5d475d 100644 --- a/tools/testing/selftests/move_mount_set_group/move_mount_set_group_test.c +++ b/tools/testing/selftests/move_mount_set_group/move_mount_set_group_test.c @@ -191,7 +191,7 @@ static bool is_shared_mount(const char *path) #define SET_GROUP_FROM "/tmp/move_mount_set_group_supported_from" #define SET_GROUP_TO "/tmp/move_mount_set_group_supported_to" -static int move_mount_set_group_supported(void) +static bool move_mount_set_group_supported(void) { int ret; @@ -222,7 +222,7 @@ static int move_mount_set_group_supported(void) AT_FDCWD, SET_GROUP_TO, MOVE_MOUNT_SET_GROUP); umount2("/tmp", MNT_DETACH); - return ret < 0 ? false : true; + return ret >= 0; } FIXTURE(move_mount_set_group) { @@ -232,7 +232,7 @@ FIXTURE(move_mount_set_group) { FIXTURE_SETUP(move_mount_set_group) { - int ret; + bool ret; ASSERT_EQ(prepare_unpriv_mountns(), 0); @@ -254,7 +254,7 @@ FIXTURE_SETUP(move_mount_set_group) FIXTURE_TEARDOWN(move_mount_set_group) { - int ret; + bool ret; ret = move_mount_set_group_supported(); ASSERT_GE(ret, 0); @@ -348,7 +348,7 @@ TEST_F(move_mount_set_group, complex_sharing_copying) .shared = false, }; pid_t pid; - int ret; + bool ret; ret = move_mount_set_group_supported(); ASSERT_GE(ret, 0); diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index 19deb9cdf7..7581a7348e 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -31,3 +31,8 @@ rxtimestamp timestamping txtimestamp so_netns_cookie +test_unix_oob +gro +ioam6_parser +toeplitz +cmsg_so_mark diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 6a953ec793..9897fa9ab9 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -22,16 +22,19 @@ TEST_PROGS += devlink_port_split.py TEST_PROGS += drop_monitor_tests.sh TEST_PROGS += vrf_route_leaking.sh TEST_PROGS += bareudp.sh +TEST_PROGS += amt.sh TEST_PROGS += unicast_extensions.sh TEST_PROGS += udpgro_fwd.sh TEST_PROGS += veth.sh TEST_PROGS += ioam6.sh TEST_PROGS += gro.sh TEST_PROGS += gre_gso.sh +TEST_PROGS += cmsg_so_mark.sh TEST_PROGS += srv6_end_dt46_l3vpn_test.sh TEST_PROGS += srv6_end_dt4_l3vpn_test.sh TEST_PROGS += srv6_end_dt6_l3vpn_test.sh TEST_PROGS += vrf_strict_mode_test.sh +TEST_PROGS += arp_ndisc_evict_nocarrier.sh TEST_PROGS_EXTENDED := in_netns.sh setup_loopback.sh setup_veth.sh TEST_PROGS_EXTENDED += toeplitz_client.sh toeplitz.sh TEST_GEN_FILES = socket nettest @@ -49,6 +52,7 @@ TEST_GEN_FILES += gro TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict tls TEST_GEN_FILES += toeplitz +TEST_GEN_FILES += cmsg_so_mark TEST_FILES := settings diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config index 86ab429fe7..ead7963b9b 100644 --- a/tools/testing/selftests/net/config +++ b/tools/testing/selftests/net/config @@ -44,3 +44,4 @@ CONFIG_NET_ACT_MIRRED=m CONFIG_BAREUDP=m CONFIG_IPV6_IOAM6_LWTUNNEL=y CONFIG_CRYPTO_SM4=y +CONFIG_AMT=m diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh index aec9e784d0..3f4c8cfe7a 100644 --- a/tools/testing/selftests/net/fcnal-test.sh +++ b/tools/testing/selftests/net/fcnal-test.sh @@ -66,6 +66,10 @@ NSB_LO_IP=172.16.2.2 NSA_LO_IP6=2001:db8:2::1 NSB_LO_IP6=2001:db8:2::2 +# non-local addresses for freebind tests +NL_IP=172.17.1.1 +NL_IP6=2001:db8:4::1 + MD5_PW=abc123 MD5_WRONG_PW=abc1234 @@ -316,6 +320,9 @@ addr2str() ${NSB_LO_IP6}) echo "ns-B loopback IPv6";; ${NSB_LINKIP6}|${NSB_LINKIP6}%*) echo "ns-B IPv6 LLA";; + ${NL_IP}) echo "nonlocal IP";; + ${NL_IP6}) echo "nonlocal IPv6";; + ${VRF_IP}) echo "VRF IP";; ${VRF_IP6}) echo "VRF IPv6";; @@ -1779,6 +1786,14 @@ ipv4_addr_bind_novrf() log_test_addr ${a} $? 0 "Raw socket bind to local address after device bind" done + # + # raw socket with nonlocal bind + # + a=${NL_IP} + log_start + run_cmd nettest -s -R -P icmp -f -l ${a} -I ${NSA_DEV} -b + log_test_addr ${a} $? 0 "Raw socket bind to nonlocal address after device bind" + # # tcp sockets # @@ -1828,6 +1843,14 @@ ipv4_addr_bind_vrf() run_cmd nettest -s -R -P icmp -l ${a} -I ${VRF} -b log_test_addr ${a} $? 1 "Raw socket bind to out of scope address after VRF bind" + # + # raw socket with nonlocal bind + # + a=${NL_IP} + log_start + run_cmd nettest -s -R -P icmp -f -l ${a} -I ${VRF} -b + log_test_addr ${a} $? 0 "Raw socket bind to nonlocal address after VRF bind" + # # tcp sockets # @@ -1978,6 +2001,7 @@ ipv4_rt() a=${NSA_IP} log_start + run_cmd nettest ${varg} -s & sleep 1 run_cmd nettest ${varg} -d ${NSA_DEV} -r ${a} & @@ -3417,6 +3441,14 @@ ipv6_addr_bind_novrf() log_test_addr ${a} $? 0 "Raw socket bind to local address after device bind" done + # + # raw socket with nonlocal bind + # + a=${NL_IP6} + log_start + run_cmd nettest -6 -s -R -P icmp -f -l ${a} -I ${NSA_DEV} -b + log_test_addr ${a} $? 0 "Raw socket bind to nonlocal address" + # # tcp sockets # @@ -3461,6 +3493,14 @@ ipv6_addr_bind_vrf() run_cmd nettest -6 -s -R -P ipv6-icmp -l ${a} -I ${VRF} -b log_test_addr ${a} $? 1 "Raw socket bind to invalid local address after vrf bind" + # + # raw socket with nonlocal bind + # + a=${NL_IP6} + log_start + run_cmd nettest -6 -s -R -P icmp -f -l ${a} -I ${VRF} -b + log_test_addr ${a} $? 0 "Raw socket bind to nonlocal address after VRF bind" + # # tcp sockets # @@ -4019,6 +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 } @@ -4091,8 +4134,6 @@ do # setup namespaces and config, but do not run any tests setup) setup; exit 0;; vrf_setup) setup "yes"; exit 0;; - - help) echo "Test names: $TESTS"; exit 0;; esac done @@ -4100,3 +4141,11 @@ cleanup 2>/dev/null printf "\nTests passed: %3d\n" ${nsuccess} printf "Tests failed: %3d\n" ${nfail} + +if [ $nfail -ne 0 ]; then + exit 1 # KSFT_FAIL +elif [ $nsuccess -eq 0 ]; then + exit $ksft_skip +fi + +exit 0 # KSFT_PASS diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh index b5a69ad191..d444ee6aa3 100644 --- a/tools/testing/selftests/net/fib_nexthops.sh +++ b/tools/testing/selftests/net/fib_nexthops.sh @@ -629,6 +629,66 @@ ipv6_fcnal() log_test $? 0 "Nexthops removed on admin down" } +ipv6_grp_refs() +{ + if [ ! -x "$(command -v mausezahn)" ]; then + echo "SKIP: Could not run test; need mausezahn tool" + return + fi + + run_cmd "$IP link set dev veth1 up" + run_cmd "$IP link add veth1.10 link veth1 up type vlan id 10" + run_cmd "$IP link add veth1.20 link veth1 up type vlan id 20" + run_cmd "$IP -6 addr add 2001:db8:91::1/64 dev veth1.10" + run_cmd "$IP -6 addr add 2001:db8:92::1/64 dev veth1.20" + run_cmd "$IP -6 neigh add 2001:db8:91::2 lladdr 00:11:22:33:44:55 dev veth1.10" + run_cmd "$IP -6 neigh add 2001:db8:92::2 lladdr 00:11:22:33:44:55 dev veth1.20" + run_cmd "$IP nexthop add id 100 via 2001:db8:91::2 dev veth1.10" + run_cmd "$IP nexthop add id 101 via 2001:db8:92::2 dev veth1.20" + run_cmd "$IP nexthop add id 102 group 100" + run_cmd "$IP route add 2001:db8:101::1/128 nhid 102" + + # create per-cpu dsts through nh 100 + run_cmd "ip netns exec me mausezahn -6 veth1.10 -B 2001:db8:101::1 -A 2001:db8:91::1 -c 5 -t tcp "dp=1-1023, flags=syn" >/dev/null 2>&1" + + # remove nh 100 from the group to delete the route potentially leaving + # a stale per-cpu dst which holds a reference to the nexthop's net + # device and to the IPv6 route + run_cmd "$IP nexthop replace id 102 group 101" + run_cmd "$IP route del 2001:db8:101::1/128" + + # add both nexthops to the group so a reference is taken on them + run_cmd "$IP nexthop replace id 102 group 100/101" + + # if the bug described in commit "net: nexthop: release IPv6 per-cpu + # dsts when replacing a nexthop group" exists at this point we have + # an unlinked IPv6 route (but not freed due to stale dst) with a + # reference over the group so we delete the group which will again + # only unlink it due to the route reference + run_cmd "$IP nexthop del id 102" + + # delete the nexthop with stale dst, since we have an unlinked + # group with a ref to it and an unlinked IPv6 route with ref to the + # group, the nh will only be unlinked and not freed so the stale dst + # remains forever and we get a net device refcount imbalance + run_cmd "$IP nexthop del id 100" + + # if a reference was lost this command will hang because the net device + # cannot be removed + timeout -s KILL 5 ip netns exec me ip link del veth1.10 >/dev/null 2>&1 + + # we can't cleanup if the command is hung trying to delete the netdev + if [ $? -eq 137 ]; then + return 1 + fi + + # cleanup + run_cmd "$IP link del veth1.20" + run_cmd "$IP nexthop flush" + + return 0 +} + ipv6_grp_fcnal() { local rc @@ -734,6 +794,9 @@ ipv6_grp_fcnal() run_cmd "$IP nexthop add id 108 group 31/24" log_test $? 2 "Nexthop group can not have a blackhole and another nexthop" + + ipv6_grp_refs + log_test $? 0 "Nexthop group replace refcounts" } ipv6_res_grp_fcnal() diff --git a/tools/testing/selftests/net/forwarding/config b/tools/testing/selftests/net/forwarding/config index a4bd1b0873..697994a927 100644 --- a/tools/testing/selftests/net/forwarding/config +++ b/tools/testing/selftests/net/forwarding/config @@ -6,6 +6,7 @@ CONFIG_IPV6_MULTIPLE_TABLES=y CONFIG_NET_VRF=m CONFIG_BPF_SYSCALL=y CONFIG_CGROUP_BPF=y +CONFIG_NET_ACT_CT=m CONFIG_NET_ACT_MIRRED=m CONFIG_NET_ACT_MPLS=m CONFIG_NET_ACT_VLAN=m diff --git a/tools/testing/selftests/net/forwarding/devlink_lib.sh b/tools/testing/selftests/net/forwarding/devlink_lib.sh index 2c14a86ada..de9944d420 100644 --- a/tools/testing/selftests/net/forwarding/devlink_lib.sh +++ b/tools/testing/selftests/net/forwarding/devlink_lib.sh @@ -563,12 +563,6 @@ devlink_trap_group_policer_get() | jq '.[][][]["policer"]' } -devlink_trap_policer_ids_get() -{ - devlink -j -p trap policer show \ - | jq '.[]["'$DEVLINK_DEV'"][]["policer"]' -} - devlink_port_by_netdev() { local if_name=$1 diff --git a/tools/testing/selftests/net/forwarding/forwarding.config.sample b/tools/testing/selftests/net/forwarding/forwarding.config.sample index e51def39fd..b0980a2efa 100644 --- a/tools/testing/selftests/net/forwarding/forwarding.config.sample +++ b/tools/testing/selftests/net/forwarding/forwarding.config.sample @@ -41,5 +41,9 @@ NETIF_CREATE=yes # Timeout (in seconds) before ping exits regardless of how many packets have # been sent or received PING_TIMEOUT=5 +# Flag for tc match, supposed to be skip_sw/skip_hw which means do not process +# filter by software/hardware +TC_FLAG=skip_hw # IPv6 traceroute utility name. TROUTE6=traceroute6 + diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 92087d423b..7da783d6f4 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -20,9 +20,12 @@ NETIF_TYPE=${NETIF_TYPE:=veth} NETIF_CREATE=${NETIF_CREATE:=yes} MCD=${MCD:=smcrouted} MC_CLI=${MC_CLI:=smcroutectl} +PING_COUNT=${PING_COUNT:=10} PING_TIMEOUT=${PING_TIMEOUT:=5} WAIT_TIMEOUT=${WAIT_TIMEOUT:=20} INTERFACE_TIMEOUT=${INTERFACE_TIMEOUT:=600} +REQUIRE_JQ=${REQUIRE_JQ:=yes} +REQUIRE_MZ=${REQUIRE_MZ:=yes} relative_path="${BASH_SOURCE%/*}" if [[ "$relative_path" == "${BASH_SOURCE}" ]]; then @@ -141,8 +144,12 @@ require_command() fi } -require_command jq -require_command $MZ +if [[ "$REQUIRE_JQ" = "yes" ]]; then + require_command jq +fi +if [[ "$REQUIRE_MZ" = "yes" ]]; then + require_command $MZ +fi if [[ ! -v NUM_NETIFS ]]; then echo "SKIP: importer does not define \"NUM_NETIFS\"" @@ -280,6 +287,15 @@ log_test() return 0 } +log_test_skip() +{ + local test_name=$1 + local opt_str=$2 + + printf "TEST: %-60s [SKIP]\n" "$test_name $opt_str" + return 0 +} + log_info() { local msg=$1 @@ -1096,7 +1112,8 @@ ping_do() vrf_name=$(master_name_get $if_name) ip vrf exec $vrf_name \ - $PING $args $dip -c 10 -i 0.1 -w $PING_TIMEOUT &> /dev/null + $PING $args $dip -c $PING_COUNT -i 0.1 \ + -w $PING_TIMEOUT &> /dev/null } ping_test() @@ -1117,7 +1134,8 @@ ping6_do() vrf_name=$(master_name_get $if_name) ip vrf exec $vrf_name \ - $PING6 $args $dip -c 10 -i 0.1 -w $PING_TIMEOUT &> /dev/null + $PING6 $args $dip -c $PING_COUNT -i 0.1 \ + -w $PING_TIMEOUT &> /dev/null } ping6_test() diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d_vlan.sh b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d_vlan.sh index f8cda822c1..1b27f2b0f1 100644 --- a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d_vlan.sh +++ b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d_vlan.sh @@ -80,7 +80,7 @@ test_gretap() test_ip6gretap() { - test_vlan_match gt6 'skip_hw vlan_id 555 vlan_ethtype ip' \ + test_vlan_match gt6 'skip_hw vlan_id 555 vlan_ethtype ipv6' \ "mirror to ip6gretap" } diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_changes.sh b/tools/testing/selftests/net/forwarding/mirror_gre_changes.sh index 472bd023e2..aff88f78e3 100644 --- a/tools/testing/selftests/net/forwarding/mirror_gre_changes.sh +++ b/tools/testing/selftests/net/forwarding/mirror_gre_changes.sh @@ -74,7 +74,7 @@ test_span_gre_ttl() mirror_install $swp1 ingress $tundev "matchall $tcflags" tc filter add dev $h3 ingress pref 77 prot $prot \ - flower ip_ttl 50 action pass + flower skip_hw ip_ttl 50 action pass mirror_test v$h1 192.0.2.1 192.0.2.2 $h3 77 0 diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh b/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh index 880e3ab9d0..c8a9b5bd84 100644 --- a/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh +++ b/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh @@ -141,7 +141,7 @@ test_gretap() test_ip6gretap() { - test_vlan_match gt6 'skip_hw vlan_id 555 vlan_ethtype ip' \ + test_vlan_match gt6 'skip_hw vlan_id 555 vlan_ethtype ipv6' \ "mirror to ip6gretap" } @@ -218,6 +218,7 @@ test_ip6gretap_forbidden_egress() test_span_gre_untagged_egress() { local tundev=$1; shift + local ul_proto=$1; shift local what=$1; shift RET=0 @@ -225,7 +226,7 @@ test_span_gre_untagged_egress() mirror_install $swp1 ingress $tundev "matchall $tcflags" quick_test_span_gre_dir $tundev ingress - quick_test_span_vlan_dir $h3 555 ingress + quick_test_span_vlan_dir $h3 555 ingress "$ul_proto" h3_addr_add_del del $h3.555 bridge vlan add dev $swp3 vid 555 pvid untagged @@ -233,7 +234,7 @@ test_span_gre_untagged_egress() sleep 5 quick_test_span_gre_dir $tundev ingress - fail_test_span_vlan_dir $h3 555 ingress + fail_test_span_vlan_dir $h3 555 ingress "$ul_proto" h3_addr_add_del del $h3 bridge vlan add dev $swp3 vid 555 @@ -241,7 +242,7 @@ test_span_gre_untagged_egress() sleep 5 quick_test_span_gre_dir $tundev ingress - quick_test_span_vlan_dir $h3 555 ingress + quick_test_span_vlan_dir $h3 555 ingress "$ul_proto" mirror_uninstall $swp1 ingress @@ -250,12 +251,12 @@ test_span_gre_untagged_egress() test_gretap_untagged_egress() { - test_span_gre_untagged_egress gt4 "mirror to gretap" + test_span_gre_untagged_egress gt4 ip "mirror to gretap" } test_ip6gretap_untagged_egress() { - test_span_gre_untagged_egress gt6 "mirror to ip6gretap" + test_span_gre_untagged_egress gt6 ipv6 "mirror to ip6gretap" } test_span_gre_fdb_roaming() diff --git a/tools/testing/selftests/net/forwarding/mirror_lib.sh b/tools/testing/selftests/net/forwarding/mirror_lib.sh index 6406cd76a1..3e8ebeff30 100644 --- a/tools/testing/selftests/net/forwarding/mirror_lib.sh +++ b/tools/testing/selftests/net/forwarding/mirror_lib.sh @@ -115,13 +115,14 @@ do_test_span_vlan_dir_ips() local dev=$1; shift local vid=$1; shift local direction=$1; shift + local ul_proto=$1; shift local ip1=$1; shift local ip2=$1; shift # Install the capture as skip_hw to avoid double-counting of packets. # The traffic is meant for local box anyway, so will be trapped to # kernel. - vlan_capture_install $dev "skip_hw vlan_id $vid vlan_ethtype ip" + vlan_capture_install $dev "skip_hw vlan_id $vid vlan_ethtype $ul_proto" mirror_test v$h1 $ip1 $ip2 $dev 100 $expect mirror_test v$h2 $ip2 $ip1 $dev 100 $expect vlan_capture_uninstall $dev diff --git a/tools/testing/selftests/net/forwarding/mirror_vlan.sh b/tools/testing/selftests/net/forwarding/mirror_vlan.sh index 9ab2ce77b3..0b44e14823 100644 --- a/tools/testing/selftests/net/forwarding/mirror_vlan.sh +++ b/tools/testing/selftests/net/forwarding/mirror_vlan.sh @@ -85,9 +85,9 @@ test_tagged_vlan_dir() RET=0 mirror_install $swp1 $direction $swp3.555 "matchall $tcflags" - do_test_span_vlan_dir_ips 10 "$h3.555" 111 "$direction" \ + do_test_span_vlan_dir_ips 10 "$h3.555" 111 "$direction" ip \ 192.0.2.17 192.0.2.18 - do_test_span_vlan_dir_ips 0 "$h3.555" 555 "$direction" \ + do_test_span_vlan_dir_ips 0 "$h3.555" 555 "$direction" ip \ 192.0.2.17 192.0.2.18 mirror_uninstall $swp1 $direction diff --git a/tools/testing/selftests/net/forwarding/sch_tbf_etsprio.sh b/tools/testing/selftests/net/forwarding/sch_tbf_etsprio.sh index 8bd85da190..75a37c189e 100644 --- a/tools/testing/selftests/net/forwarding/sch_tbf_etsprio.sh +++ b/tools/testing/selftests/net/forwarding/sch_tbf_etsprio.sh @@ -4,9 +4,12 @@ ALL_TESTS=" ping_ipv4 tbf_test + tbf_root_test " source $lib_dir/sch_tbf_core.sh +QDISC_TYPE=${QDISC% *} + tbf_test_one() { local bs=$1; shift @@ -22,6 +25,8 @@ tbf_test_one() tbf_test() { + log_info "Testing root-$QDISC_TYPE-tbf" + # This test is used for both ETS and PRIO. Even though we only need two # bands, PRIO demands a minimum of three. tc qdisc add dev $swp2 root handle 10: $QDISC 3 priomap 2 1 0 @@ -29,6 +34,29 @@ tbf_test() tc qdisc del dev $swp2 root } +tbf_root_test() +{ + local bs=128K + + log_info "Testing root-tbf-$QDISC_TYPE" + + tc qdisc replace dev $swp2 root handle 1: \ + tbf rate 400Mbit burst $bs limit 1M + tc qdisc replace dev $swp2 parent 1:1 handle 10: \ + $QDISC 3 priomap 2 1 0 + tc qdisc replace dev $swp2 parent 10:3 handle 103: \ + bfifo limit 1M + tc qdisc replace dev $swp2 parent 10:2 handle 102: \ + bfifo limit 1M + tc qdisc replace dev $swp2 parent 10:1 handle 101: \ + bfifo limit 1M + + do_tbf_test 10 400 $bs + do_tbf_test 11 400 $bs + + tc qdisc del dev $swp2 root +} + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/net/forwarding/tc_actions.sh b/tools/testing/selftests/net/forwarding/tc_actions.sh index d9eca22713..de19eb6c38 100644 --- a/tools/testing/selftests/net/forwarding/tc_actions.sh +++ b/tools/testing/selftests/net/forwarding/tc_actions.sh @@ -3,7 +3,7 @@ ALL_TESTS="gact_drop_and_ok_test mirred_egress_redirect_test \ mirred_egress_mirror_test matchall_mirred_egress_mirror_test \ - gact_trap_test" + gact_trap_test mirred_egress_to_ingress_test" NUM_NETIFS=4 source tc_common.sh source lib.sh @@ -13,10 +13,12 @@ tcflags="skip_hw" h1_create() { simple_if_init $h1 192.0.2.1/24 + tc qdisc add dev $h1 clsact } h1_destroy() { + tc qdisc del dev $h1 clsact simple_if_fini $h1 192.0.2.1/24 } @@ -153,6 +155,49 @@ gact_trap_test() log_test "trap ($tcflags)" } +mirred_egress_to_ingress_test() +{ + RET=0 + + tc filter add dev $h1 protocol ip pref 100 handle 100 egress flower \ + ip_proto icmp src_ip 192.0.2.1 dst_ip 192.0.2.2 type 8 action \ + ct commit nat src addr 192.0.2.2 pipe \ + ct clear pipe \ + ct commit nat dst addr 192.0.2.1 pipe \ + mirred ingress redirect dev $h1 + + tc filter add dev $swp1 protocol ip pref 11 handle 111 ingress flower \ + ip_proto icmp src_ip 192.0.2.1 dst_ip 192.0.2.2 type 8 action drop + tc filter add dev $swp1 protocol ip pref 12 handle 112 ingress flower \ + ip_proto icmp src_ip 192.0.2.1 dst_ip 192.0.2.2 type 0 action pass + + $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \ + -t icmp "ping,id=42,seq=10" -q + + tc_check_packets "dev $h1 egress" 100 1 + check_err $? "didn't mirror first packet" + + tc_check_packets "dev $swp1 ingress" 111 1 + check_fail $? "didn't redirect first packet" + tc_check_packets "dev $swp1 ingress" 112 1 + check_err $? "didn't receive reply to first packet" + + ping 192.0.2.2 -I$h1 -c1 -w1 -q 1>/dev/null 2>&1 + + tc_check_packets "dev $h1 egress" 100 2 + check_err $? "didn't mirror second packet" + tc_check_packets "dev $swp1 ingress" 111 1 + check_fail $? "didn't redirect second packet" + tc_check_packets "dev $swp1 ingress" 112 2 + check_err $? "didn't receive reply to second packet" + + tc filter del dev $h1 egress protocol ip pref 100 handle 100 flower + tc filter del dev $swp1 ingress protocol ip pref 11 handle 111 flower + tc filter del dev $swp1 ingress protocol ip pref 12 handle 112 flower + + log_test "mirred_egress_to_ingress ($tcflags)" +} + setup_prepare() { h1=${NETIFS[p1]} diff --git a/tools/testing/selftests/net/forwarding/tc_common.sh b/tools/testing/selftests/net/forwarding/tc_common.sh index 0e18e8be6e..bce8bb8d2b 100644 --- a/tools/testing/selftests/net/forwarding/tc_common.sh +++ b/tools/testing/selftests/net/forwarding/tc_common.sh @@ -16,6 +16,16 @@ tc_check_packets() tc_rule_handle_stats_get "$id" "$handle" > /dev/null } +tc_check_at_least_x_packets() +{ + local id=$1 + local handle=$2 + local count=$3 + + busywait "$TC_HIT_TIMEOUT" until_counter_is ">= $count" \ + tc_rule_handle_stats_get "$id" "$handle" > /dev/null +} + tc_check_packets_hitting() { local id=$1 diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1q.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1q.sh index a5789721ba..a596bbf3ed 100644 --- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1q.sh +++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1q.sh @@ -680,26 +680,6 @@ test_pvid() log_test "VXLAN: flood after vlan re-add" } -vxlan_ping_test() -{ - local ping_dev=$1; shift - local ping_dip=$1; shift - local ping_args=$1; shift - local capture_dev=$1; shift - local capture_dir=$1; shift - local capture_pref=$1; shift - local expect=$1; shift - - local t0=$(tc_rule_stats_get $capture_dev $capture_pref $capture_dir) - ping_do $ping_dev $ping_dip "$ping_args" - local t1=$(tc_rule_stats_get $capture_dev $capture_pref $capture_dir) - local delta=$((t1 - t0)) - - # Tolerate a couple stray extra packets. - ((expect <= delta && delta <= expect + 2)) - check_err $? "$capture_dev: Expected to capture $expect packets, got $delta." -} - __test_learning() { local -a expects=(0 0 0 0 0) diff --git a/tools/testing/selftests/net/gro.c b/tools/testing/selftests/net/gro.c index cf37ce86b0..30024d0ed3 100644 --- a/tools/testing/selftests/net/gro.c +++ b/tools/testing/selftests/net/gro.c @@ -57,17 +57,14 @@ #include #include +#include "../kselftest.h" + #define DPORT 8000 #define SPORT 1500 #define PAYLOAD_LEN 100 -#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0])) #define NUM_PACKETS 4 #define START_SEQ 100 #define START_ACK 100 -#define SIP6 "fdaa::2" -#define DIP6 "fdaa::1" -#define SIP4 "192.168.1.200" -#define DIP4 "192.168.1.100" #define ETH_P_NONE 0 #define TOTAL_HDR_LEN (ETH_HLEN + sizeof(struct ipv6hdr) + sizeof(struct tcphdr)) #define MSS (4096 - sizeof(struct tcphdr) - sizeof(struct ipv6hdr)) @@ -75,6 +72,10 @@ #define NUM_LARGE_PKT (MAX_PAYLOAD / MSS) #define MAX_HDR_LEN (ETH_HLEN + sizeof(struct ipv6hdr) + sizeof(struct tcphdr)) +static const char *addr6_src = "fdaa::2"; +static const char *addr6_dst = "fdaa::1"; +static const char *addr4_src = "192.168.1.200"; +static const char *addr4_dst = "192.168.1.100"; static int proto = -1; static uint8_t src_mac[ETH_ALEN], dst_mac[ETH_ALEN]; static char *testname = "data"; @@ -178,18 +179,18 @@ static uint16_t tcp_checksum(void *buf, int payload_len) uint32_t sum = 0; if (proto == PF_INET6) { - if (inet_pton(AF_INET6, SIP6, &ph6.saddr) != 1) + if (inet_pton(AF_INET6, addr6_src, &ph6.saddr) != 1) error(1, errno, "inet_pton6 source ip pseudo"); - if (inet_pton(AF_INET6, DIP6, &ph6.daddr) != 1) + if (inet_pton(AF_INET6, addr6_dst, &ph6.daddr) != 1) error(1, errno, "inet_pton6 dest ip pseudo"); ph6.protocol = htons(IPPROTO_TCP); ph6.payload_len = htons(sizeof(struct tcphdr) + payload_len); sum = checksum_nofold(&ph6, sizeof(ph6), 0); } else if (proto == PF_INET) { - if (inet_pton(AF_INET, SIP4, &ph4.saddr) != 1) + if (inet_pton(AF_INET, addr4_src, &ph4.saddr) != 1) error(1, errno, "inet_pton source ip pseudo"); - if (inet_pton(AF_INET, DIP4, &ph4.daddr) != 1) + if (inet_pton(AF_INET, addr4_dst, &ph4.daddr) != 1) error(1, errno, "inet_pton dest ip pseudo"); ph4.protocol = htons(IPPROTO_TCP); ph4.payload_len = htons(sizeof(struct tcphdr) + payload_len); @@ -229,9 +230,9 @@ static void fill_networklayer(void *buf, int payload_len) ip6h->payload_len = htons(sizeof(struct tcphdr) + payload_len); ip6h->nexthdr = IPPROTO_TCP; ip6h->hop_limit = 8; - if (inet_pton(AF_INET6, SIP6, &ip6h->saddr) != 1) + if (inet_pton(AF_INET6, addr6_src, &ip6h->saddr) != 1) error(1, errno, "inet_pton source ip6"); - if (inet_pton(AF_INET6, DIP6, &ip6h->daddr) != 1) + if (inet_pton(AF_INET6, addr6_dst, &ip6h->daddr) != 1) error(1, errno, "inet_pton dest ip6"); } else if (proto == PF_INET) { memset(iph, 0, sizeof(*iph)); @@ -243,9 +244,9 @@ static void fill_networklayer(void *buf, int payload_len) iph->tot_len = htons(sizeof(struct tcphdr) + payload_len + sizeof(struct iphdr)); iph->frag_off = htons(0x4000); /* DF = 1, MF = 0 */ - if (inet_pton(AF_INET, SIP4, &iph->saddr) != 1) + if (inet_pton(AF_INET, addr4_src, &iph->saddr) != 1) error(1, errno, "inet_pton source ip"); - if (inet_pton(AF_INET, DIP4, &iph->daddr) != 1) + if (inet_pton(AF_INET, addr4_dst, &iph->daddr) != 1) error(1, errno, "inet_pton dest ip"); iph->check = checksum_fold(buf, sizeof(struct iphdr), 0); } @@ -731,7 +732,7 @@ static void set_timeout(int fd) { struct timeval timeout; - timeout.tv_sec = 120; + timeout.tv_sec = 3; timeout.tv_usec = 0; if (setsockopt(fd, SOL_SOCKET, SO_RCVTIMEO, (char *)&timeout, sizeof(timeout)) < 0) @@ -1023,11 +1024,13 @@ static void gro_receiver(void) static void parse_args(int argc, char **argv) { static const struct option opts[] = { + { "daddr", required_argument, NULL, 'd' }, { "dmac", required_argument, NULL, 'D' }, { "iface", required_argument, NULL, 'i' }, { "ipv4", no_argument, NULL, '4' }, { "ipv6", no_argument, NULL, '6' }, { "rx", no_argument, NULL, 'r' }, + { "saddr", required_argument, NULL, 's' }, { "smac", required_argument, NULL, 'S' }, { "test", required_argument, NULL, 't' }, { "verbose", no_argument, NULL, 'v' }, @@ -1035,7 +1038,7 @@ static void parse_args(int argc, char **argv) }; int c; - while ((c = getopt_long(argc, argv, "46D:i:rS:t:v", opts, NULL)) != -1) { + while ((c = getopt_long(argc, argv, "46d:D:i:rs:S:t:v", opts, NULL)) != -1) { switch (c) { case '4': proto = PF_INET; @@ -1045,6 +1048,9 @@ static void parse_args(int argc, char **argv) proto = PF_INET6; ethhdr_proto = htons(ETH_P_IPV6); break; + case 'd': + addr4_dst = addr6_dst = optarg; + break; case 'D': dmac = optarg; break; @@ -1054,6 +1060,9 @@ static void parse_args(int argc, char **argv) case 'r': tx_socket = false; break; + case 's': + addr4_src = addr6_src = optarg; + break; case 'S': smac = optarg; break; @@ -1091,5 +1100,7 @@ int main(int argc, char **argv) gro_sender(); else gro_receiver(); + + fprintf(stderr, "Gro::%s test passed.\n", testname); return 0; } diff --git a/tools/testing/selftests/net/ioam6.sh b/tools/testing/selftests/net/ioam6.sh index a2489ec398..a2b9fad5a9 100644 --- a/tools/testing/selftests/net/ioam6.sh +++ b/tools/testing/selftests/net/ioam6.sh @@ -6,7 +6,7 @@ # This script evaluates the IOAM insertion for IPv6 by checking the IOAM data # consistency directly inside packets on the receiver side. Tests are divided # into three categories: OUTPUT (evaluates the IOAM processing by the sender), -# INPUT (evaluates the IOAM processing by the receiver) and GLOBAL (evaluates +# INPUT (evaluates the IOAM processing by a receiver) and GLOBAL (evaluates # wider use cases that do not fall into the other two categories). Both OUTPUT # and INPUT tests only use a two-node topology (alpha and beta), while GLOBAL # tests use the entire three-node topology (alpha, beta, gamma). Each test is @@ -200,7 +200,7 @@ check_kernel_compatibility() ip -netns ioam-tmp-node link set veth0 up ip -netns ioam-tmp-node link set veth1 up - ip -netns ioam-tmp-node ioam namespace add 0 &>/dev/null + ip -netns ioam-tmp-node ioam namespace add 0 ns_ad=$? ip -netns ioam-tmp-node ioam namespace show | grep -q "namespace 0" @@ -214,11 +214,11 @@ check_kernel_compatibility() exit 1 fi - ip -netns ioam-tmp-node route add db02::/64 encap ioam6 trace prealloc \ - type 0x800000 ns 0 size 4 dev veth0 &>/dev/null + ip -netns ioam-tmp-node route add db02::/64 encap ioam6 mode inline \ + trace prealloc type 0x800000 ns 0 size 4 dev veth0 tr_ad=$? - ip -netns ioam-tmp-node -6 route | grep -q "encap ioam6 trace" + ip -netns ioam-tmp-node -6 route | grep -q "encap ioam6" tr_sh=$? if [[ $tr_ad != 0 || $tr_sh != 0 ]] @@ -232,6 +232,30 @@ check_kernel_compatibility() ip link del veth0 2>/dev/null || true ip netns del ioam-tmp-node || true + + lsmod | grep -q "ip6_tunnel" + ip6tnl_loaded=$? + + if [ $ip6tnl_loaded = 0 ] + then + encap_tests=0 + else + modprobe ip6_tunnel &>/dev/null + lsmod | grep -q "ip6_tunnel" + encap_tests=$? + + if [ $encap_tests != 0 ] + then + ip a | grep -q "ip6tnl0" + encap_tests=$? + + if [ $encap_tests != 0 ] + then + echo "Note: ip6_tunnel not found neither as a module nor inside the" \ + "kernel, tests that require it (encap mode) will be omitted" + fi + fi + fi } cleanup() @@ -242,6 +266,11 @@ cleanup() ip netns del ioam-node-alpha || true ip netns del ioam-node-beta || true ip netns del ioam-node-gamma || true + + if [ $ip6tnl_loaded != 0 ] + then + modprobe -r ip6_tunnel 2>/dev/null || true + fi } setup() @@ -329,6 +358,12 @@ log_test_failed() printf "TEST: %-60s [FAIL]\n" "${desc}" } +log_results() +{ + echo "- Tests passed: ${npassed}" + echo "- Tests failed: ${nfailed}" +} + run_test() { local name=$1 @@ -349,16 +384,26 @@ run_test() ip netns exec $node_src ping6 -t 64 -c 1 -W 1 $ip6_dst &>/dev/null if [ $? != 0 ] then + nfailed=$((nfailed+1)) log_test_failed "${desc}" kill -2 $spid &>/dev/null else wait $spid - [ $? = 0 ] && log_test_passed "${desc}" || log_test_failed "${desc}" + if [ $? = 0 ] + then + npassed=$((npassed+1)) + log_test_passed "${desc}" + else + nfailed=$((nfailed+1)) + log_test_failed "${desc}" + fi fi } run() { + echo + printf "%0.s-" {1..74} echo echo "OUTPUT tests" printf "%0.s-" {1..74} @@ -369,7 +414,8 @@ run() for t in $TESTS_OUTPUT do - $t + $t "inline" + [ $encap_tests = 0 ] && $t "encap" done # clean OUTPUT settings @@ -377,6 +423,8 @@ run() ip -netns ioam-node-alpha route change db01::/64 dev veth0 + echo + printf "%0.s-" {1..74} echo echo "INPUT tests" printf "%0.s-" {1..74} @@ -387,7 +435,8 @@ run() for t in $TESTS_INPUT do - $t + $t "inline" + [ $encap_tests = 0 ] && $t "encap" done # clean INPUT settings @@ -396,7 +445,8 @@ run() ip -netns ioam-node-alpha ioam namespace set 123 schema ${ALPHA[8]} ip -netns ioam-node-alpha route change db01::/64 dev veth0 - + echo + printf "%0.s-" {1..74} echo echo "GLOBAL tests" printf "%0.s-" {1..74} @@ -404,8 +454,12 @@ run() for t in $TESTS_GLOBAL do - $t + $t "inline" + [ $encap_tests = 0 ] && $t "encap" done + + echo + log_results } bit2type=( @@ -431,11 +485,16 @@ out_undef_ns() ############################################################################## local desc="Unknown IOAM namespace" - ip -netns ioam-node-alpha route change db01::/64 encap ioam6 trace prealloc \ - type 0x800000 ns 0 size 4 dev veth0 + [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1" + [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 up - run_test ${FUNCNAME[0]} "${desc}" ioam-node-alpha ioam-node-beta db01::2 \ - db01::1 veth0 0x800000 0 + ip -netns ioam-node-alpha route change db01::/64 encap ioam6 mode $mode \ + trace prealloc type 0x800000 ns 0 size 4 dev veth0 + + run_test ${FUNCNAME[0]} "${desc} ($1 mode)" ioam-node-alpha ioam-node-beta \ + db01::2 db01::1 veth0 0x800000 0 + + [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 down } out_no_room() @@ -446,11 +505,16 @@ out_no_room() ############################################################################## local desc="Missing trace room" - ip -netns ioam-node-alpha route change db01::/64 encap ioam6 trace prealloc \ - type 0xc00000 ns 123 size 4 dev veth0 + [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1" + [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 up - run_test ${FUNCNAME[0]} "${desc}" ioam-node-alpha ioam-node-beta db01::2 \ - db01::1 veth0 0xc00000 123 + ip -netns ioam-node-alpha route change db01::/64 encap ioam6 mode $mode \ + trace prealloc type 0xc00000 ns 123 size 4 dev veth0 + + run_test ${FUNCNAME[0]} "${desc} ($1 mode)" ioam-node-alpha ioam-node-beta \ + db01::2 db01::1 veth0 0xc00000 123 + + [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 down } out_bits() @@ -465,10 +529,13 @@ out_bits() local tmp=${bit2size[22]} bit2size[22]=$(( $tmp + ${#ALPHA[9]} + ((4 - (${#ALPHA[9]} % 4)) % 4) )) + [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1" + [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 up + for i in {0..22} do - ip -netns ioam-node-alpha route change db01::/64 encap ioam6 trace \ - prealloc type ${bit2type[$i]} ns 123 size ${bit2size[$i]} \ + ip -netns ioam-node-alpha route change db01::/64 encap ioam6 mode $mode \ + trace prealloc type ${bit2type[$i]} ns 123 size ${bit2size[$i]} \ dev veth0 &>/dev/null local cmd_res=$? @@ -485,11 +552,13 @@ out_bits() log_test_failed "$descr" fi else - run_test "out_bit$i" "$descr" ioam-node-alpha ioam-node-beta \ - db01::2 db01::1 veth0 ${bit2type[$i]} 123 + run_test "out_bit$i" "$descr ($1 mode)" ioam-node-alpha \ + ioam-node-beta db01::2 db01::1 veth0 ${bit2type[$i]} 123 fi done + [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 down + bit2size[22]=$tmp } @@ -501,11 +570,16 @@ out_full_supp_trace() ############################################################################## local desc="Full supported trace" - ip -netns ioam-node-alpha route change db01::/64 encap ioam6 trace prealloc \ - type 0xfff002 ns 123 size 100 dev veth0 + [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1" + [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 up - run_test ${FUNCNAME[0]} "${desc}" ioam-node-alpha ioam-node-beta db01::2 \ - db01::1 veth0 0xfff002 123 + ip -netns ioam-node-alpha route change db01::/64 encap ioam6 mode $mode \ + trace prealloc type 0xfff002 ns 123 size 100 dev veth0 + + run_test ${FUNCNAME[0]} "${desc} ($1 mode)" ioam-node-alpha ioam-node-beta \ + db01::2 db01::1 veth0 0xfff002 123 + + [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 down } @@ -526,11 +600,16 @@ in_undef_ns() ############################################################################## local desc="Unknown IOAM namespace" - ip -netns ioam-node-alpha route change db01::/64 encap ioam6 trace prealloc \ - type 0x800000 ns 0 size 4 dev veth0 + [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1" + [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 up - run_test ${FUNCNAME[0]} "${desc}" ioam-node-alpha ioam-node-beta db01::2 \ - db01::1 veth0 0x800000 0 + ip -netns ioam-node-alpha route change db01::/64 encap ioam6 mode $mode \ + trace prealloc type 0x800000 ns 0 size 4 dev veth0 + + run_test ${FUNCNAME[0]} "${desc} ($1 mode)" ioam-node-alpha ioam-node-beta \ + db01::2 db01::1 veth0 0x800000 0 + + [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 down } in_no_room() @@ -541,11 +620,16 @@ in_no_room() ############################################################################## local desc="Missing trace room" - ip -netns ioam-node-alpha route change db01::/64 encap ioam6 trace prealloc \ - type 0xc00000 ns 123 size 4 dev veth0 + [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1" + [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 up - run_test ${FUNCNAME[0]} "${desc}" ioam-node-alpha ioam-node-beta db01::2 \ - db01::1 veth0 0xc00000 123 + ip -netns ioam-node-alpha route change db01::/64 encap ioam6 mode $mode \ + trace prealloc type 0xc00000 ns 123 size 4 dev veth0 + + run_test ${FUNCNAME[0]} "${desc} ($1 mode)" ioam-node-alpha ioam-node-beta \ + db01::2 db01::1 veth0 0xc00000 123 + + [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 down } in_bits() @@ -560,15 +644,21 @@ in_bits() local tmp=${bit2size[22]} bit2size[22]=$(( $tmp + ${#BETA[9]} + ((4 - (${#BETA[9]} % 4)) % 4) )) + [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1" + [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 up + for i in {0..11} {22..22} do - ip -netns ioam-node-alpha route change db01::/64 encap ioam6 trace \ - prealloc type ${bit2type[$i]} ns 123 size ${bit2size[$i]} dev veth0 + ip -netns ioam-node-alpha route change db01::/64 encap ioam6 mode $mode \ + trace prealloc type ${bit2type[$i]} ns 123 size ${bit2size[$i]} \ + dev veth0 - run_test "in_bit$i" "${desc//$i}" ioam-node-alpha ioam-node-beta \ - db01::2 db01::1 veth0 ${bit2type[$i]} 123 + run_test "in_bit$i" "${desc//$i} ($1 mode)" ioam-node-alpha \ + ioam-node-beta db01::2 db01::1 veth0 ${bit2type[$i]} 123 done + [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 down + bit2size[22]=$tmp } @@ -585,11 +675,16 @@ in_oflag() # back the IOAM namespace that was previously configured on the sender. ip -netns ioam-node-alpha ioam namespace add 123 - ip -netns ioam-node-alpha route change db01::/64 encap ioam6 trace prealloc \ - type 0xc00000 ns 123 size 4 dev veth0 + [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1" + [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 up - run_test ${FUNCNAME[0]} "${desc}" ioam-node-alpha ioam-node-beta db01::2 \ - db01::1 veth0 0xc00000 123 + ip -netns ioam-node-alpha route change db01::/64 encap ioam6 mode $mode \ + trace prealloc type 0xc00000 ns 123 size 4 dev veth0 + + run_test ${FUNCNAME[0]} "${desc} ($1 mode)" ioam-node-alpha ioam-node-beta \ + db01::2 db01::1 veth0 0xc00000 123 + + [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 down # And we clean the exception for this test to get things back to normal for # other INPUT tests @@ -604,11 +699,16 @@ in_full_supp_trace() ############################################################################## local desc="Full supported trace" - ip -netns ioam-node-alpha route change db01::/64 encap ioam6 trace prealloc \ - type 0xfff002 ns 123 size 80 dev veth0 + [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1" + [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 up - run_test ${FUNCNAME[0]} "${desc}" ioam-node-alpha ioam-node-beta db01::2 \ - db01::1 veth0 0xfff002 123 + ip -netns ioam-node-alpha route change db01::/64 encap ioam6 mode $mode \ + trace prealloc type 0xfff002 ns 123 size 80 dev veth0 + + run_test ${FUNCNAME[0]} "${desc} ($1 mode)" ioam-node-alpha ioam-node-beta \ + db01::2 db01::1 veth0 0xfff002 123 + + [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 down } @@ -627,11 +727,16 @@ fwd_full_supp_trace() ############################################################################## local desc="Forward - Full supported trace" - ip -netns ioam-node-alpha route change db02::/64 encap ioam6 trace prealloc \ - type 0xfff002 ns 123 size 244 via db01::1 dev veth0 + [ "$1" = "encap" ] && mode="$1 tundst db02::2" || mode="$1" + [ "$1" = "encap" ] && ip -netns ioam-node-gamma link set ip6tnl0 up - run_test ${FUNCNAME[0]} "${desc}" ioam-node-alpha ioam-node-gamma db01::2 \ - db02::2 veth0 0xfff002 123 + ip -netns ioam-node-alpha route change db02::/64 encap ioam6 mode $mode \ + trace prealloc type 0xfff002 ns 123 size 244 via db01::1 dev veth0 + + run_test ${FUNCNAME[0]} "${desc} ($1 mode)" ioam-node-alpha ioam-node-gamma \ + db01::2 db02::2 veth0 0xfff002 123 + + [ "$1" = "encap" ] && ip -netns ioam-node-gamma link set ip6tnl0 down } @@ -641,6 +746,9 @@ fwd_full_supp_trace() # # ################################################################################ +npassed=0 +nfailed=0 + if [ "$(id -u)" -ne 0 ] then echo "SKIP: Need root privileges" diff --git a/tools/testing/selftests/net/ioam6_parser.c b/tools/testing/selftests/net/ioam6_parser.c index 8f6997d358..d9d1d41901 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/ipsec.c b/tools/testing/selftests/net/ipsec.c index 3d7dde2c32..cc10c10c5e 100644 --- a/tools/testing/selftests/net/ipsec.c +++ b/tools/testing/selftests/net/ipsec.c @@ -41,7 +41,6 @@ #define pr_err(fmt, ...) printk(fmt ": %m", ##__VA_ARGS__) -#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0])) #define BUILD_BUG_ON(condition) ((void)sizeof(char[1 - 2*!!(condition)])) #define IPV4_STR_SZ 16 /* xxx.xxx.xxx.xxx is longest + \0 */ diff --git a/tools/testing/selftests/net/mptcp/.gitignore b/tools/testing/selftests/net/mptcp/.gitignore index 260336d5f0..49daae73c4 100644 --- a/tools/testing/selftests/net/mptcp/.gitignore +++ b/tools/testing/selftests/net/mptcp/.gitignore @@ -1,4 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only mptcp_connect +mptcp_inq +mptcp_sockopt pm_nl_ctl *.pcap diff --git a/tools/testing/selftests/net/mptcp/Makefile b/tools/testing/selftests/net/mptcp/Makefile index f1464f09b0..0356c4501c 100644 --- a/tools/testing/selftests/net/mptcp/Makefile +++ b/tools/testing/selftests/net/mptcp/Makefile @@ -8,7 +8,7 @@ CFLAGS = -Wall -Wl,--no-as-needed -O2 -g -I$(top_srcdir)/usr/include TEST_PROGS := mptcp_connect.sh pm_netlink.sh mptcp_join.sh diag.sh \ simult_flows.sh mptcp_sockopt.sh -TEST_GEN_FILES = mptcp_connect pm_nl_ctl +TEST_GEN_FILES = mptcp_connect pm_nl_ctl mptcp_sockopt mptcp_inq TEST_FILES := settings diff --git a/tools/testing/selftests/net/mptcp/config b/tools/testing/selftests/net/mptcp/config index 0faaccd214..d36b7da508 100644 --- a/tools/testing/selftests/net/mptcp/config +++ b/tools/testing/selftests/net/mptcp/config @@ -9,9 +9,13 @@ CONFIG_NETFILTER=y CONFIG_NETFILTER_ADVANCED=y CONFIG_NETFILTER_NETLINK=m CONFIG_NF_TABLES=m -CONFIG_NFT_COUNTER=m CONFIG_NFT_COMPAT=m CONFIG_NETFILTER_XTABLES=m CONFIG_NETFILTER_XT_MATCH_BPF=m -CONFIG_NF_TABLES_IPV4=y -CONFIG_NF_TABLES_IPV6=y +CONFIG_NF_TABLES_INET=y +CONFIG_NFT_TPROXY=m +CONFIG_NFT_SOCKET=m +CONFIG_IP_ADVANCED_ROUTER=y +CONFIG_IP_MULTIPLE_TABLES=y +CONFIG_IP_NF_TARGET_REJECT=m +CONFIG_IPV6_MULTIPLE_TABLES=y diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c index 89c4753c27..8628aa61b7 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.c +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c @@ -14,7 +14,9 @@ #include #include #include +#include +#include #include #include #include @@ -27,6 +29,7 @@ #include #include +#include extern int optind; @@ -58,40 +61,65 @@ static enum cfg_peek cfg_peek = CFG_NONE_PEEK; static const char *cfg_host; static const char *cfg_port = "12000"; static int cfg_sock_proto = IPPROTO_MPTCP; -static bool tcpulp_audit; static int pf = AF_INET; static int cfg_sndbuf; static int cfg_rcvbuf; static bool cfg_join; static bool cfg_remove; +static unsigned int cfg_time; static unsigned int cfg_do_w; static int cfg_wait; static uint32_t cfg_mark; +static char *cfg_input; +static int cfg_repeat = 1; struct cfg_cmsg_types { unsigned int cmsg_enabled:1; unsigned int timestampns:1; + unsigned int tcp_inq:1; }; +struct cfg_sockopt_types { + unsigned int transparent:1; +}; + +struct tcp_inq_state { + unsigned int last; + bool expect_eof; +}; + +static struct tcp_inq_state tcp_inq; + static struct cfg_cmsg_types cfg_cmsg_types; +static struct cfg_sockopt_types cfg_sockopt_types; static void die_usage(void) { - fprintf(stderr, "Usage: mptcp_connect [-6] [-u] [-s MPTCP|TCP] [-p port] [-m mode]" - "[-l] [-w sec] connect_address\n"); + fprintf(stderr, "Usage: mptcp_connect [-6] [-c cmsg] [-i file] [-I num] [-j] [-l] " + "[-m mode] [-M mark] [-o option] [-p port] [-P mode] [-j] [-l] [-r num] " + "[-s MPTCP|TCP] [-S num] [-r num] [-t num] [-T num] [-u] [-w sec] connect_address\n"); fprintf(stderr, "\t-6 use ipv6\n"); - fprintf(stderr, "\t-t num -- set poll timeout to num\n"); - fprintf(stderr, "\t-S num -- set SO_SNDBUF to num\n"); - fprintf(stderr, "\t-R num -- set SO_RCVBUF to num\n"); - fprintf(stderr, "\t-p num -- use port num\n"); - fprintf(stderr, "\t-s [MPTCP|TCP] -- use mptcp(default) or tcp sockets\n"); + fprintf(stderr, "\t-c cmsg -- test cmsg type \n"); + fprintf(stderr, "\t-i file -- read the data to send from the given file instead of stdin"); + fprintf(stderr, "\t-I num -- repeat the transfer 'num' times. In listen mode accepts num " + "incoming connections, in client mode, disconnect and reconnect to the server\n"); + fprintf(stderr, "\t-j -- add additional sleep at connection start and tear down " + "-- for MPJ tests\n"); + fprintf(stderr, "\t-l -- listens mode, accepts incoming connection\n"); fprintf(stderr, "\t-m [poll|mmap|sendfile] -- use poll(default)/mmap+write/sendfile\n"); fprintf(stderr, "\t-M mark -- set socket packet mark\n"); - fprintf(stderr, "\t-u -- check mptcp ulp\n"); - fprintf(stderr, "\t-w num -- wait num sec before closing the socket\n"); - fprintf(stderr, "\t-c cmsg -- test cmsg type \n"); + fprintf(stderr, "\t-o option -- test sockopt