aboutsummaryrefslogtreecommitdiffstats
path: root/tools
diff options
context:
space:
mode:
Diffstat (limited to 'tools')
-rw-r--r--tools/arch/alpha/include/uapi/asm/mman.h2
-rw-r--r--tools/arch/arc/include/uapi/asm/unistd.h51
-rw-r--r--tools/arch/arm64/include/asm/barrier.h10
-rw-r--r--tools/arch/arm64/include/uapi/asm/unistd.h2
-rw-r--r--tools/arch/hexagon/include/uapi/asm/unistd.h40
-rw-r--r--tools/arch/mips/include/uapi/asm/mman.h2
-rw-r--r--tools/arch/parisc/include/uapi/asm/mman.h2
-rw-r--r--tools/arch/powerpc/include/uapi/asm/kvm.h2
-rw-r--r--tools/arch/riscv/include/uapi/asm/unistd.h42
-rw-r--r--tools/arch/x86/include/asm/barrier.h7
-rw-r--r--tools/arch/x86/include/asm/cpufeatures.h1
-rw-r--r--tools/arch/x86/include/uapi/asm/vmx.h1
-rw-r--r--tools/arch/xtensa/include/uapi/asm/mman.h2
-rw-r--r--tools/bpf/bpftool/.gitignore2
-rw-r--r--tools/bpf/bpftool/Documentation/bpftool-btf.rst222
-rw-r--r--tools/bpf/bpftool/Documentation/bpftool-cgroup.rst10
-rw-r--r--tools/bpf/bpftool/Documentation/bpftool-feature.rst5
-rw-r--r--tools/bpf/bpftool/Documentation/bpftool-map.rst5
-rw-r--r--tools/bpf/bpftool/Documentation/bpftool-net.rst5
-rw-r--r--tools/bpf/bpftool/Documentation/bpftool-perf.rst5
-rw-r--r--tools/bpf/bpftool/Documentation/bpftool-prog.rst18
-rw-r--r--tools/bpf/bpftool/Documentation/bpftool.rst5
-rw-r--r--tools/bpf/bpftool/bash-completion/bpftool75
-rw-r--r--tools/bpf/bpftool/btf.c586
-rw-r--r--tools/bpf/bpftool/btf_dumper.c59
-rw-r--r--tools/bpf/bpftool/cgroup.c10
-rw-r--r--tools/bpf/bpftool/main.c3
-rw-r--r--tools/bpf/bpftool/main.h2
-rw-r--r--tools/bpf/bpftool/map.c67
-rw-r--r--tools/bpf/bpftool/net.c54
-rw-r--r--tools/bpf/bpftool/prog.c274
-rw-r--r--tools/bpf/bpftool/xlated_dumper.c3
-rw-r--r--tools/build/Makefile.feature8
-rw-r--r--tools/build/feature/Makefile6
-rw-r--r--tools/build/feature/test-all.c10
-rw-r--r--tools/build/feature/test-libopencsd.c4
-rw-r--r--tools/build/feature/test-libzstd.c12
-rw-r--r--tools/include/linux/coresight-pmu.h2
-rw-r--r--tools/include/linux/filter.h21
-rw-r--r--tools/include/uapi/asm-generic/mman-common-tools.h23
-rw-r--r--tools/include/uapi/asm-generic/mman-common.h4
-rw-r--r--tools/include/uapi/asm-generic/mman.h2
-rw-r--r--tools/include/uapi/asm-generic/unistd.h158
-rw-r--r--tools/include/uapi/drm/i915_drm.h64
-rw-r--r--tools/include/uapi/linux/bpf.h477
-rw-r--r--tools/include/uapi/linux/btf.h32
-rw-r--r--tools/include/uapi/linux/fcntl.h1
-rw-r--r--tools/include/uapi/linux/in.h9
-rw-r--r--tools/include/uapi/linux/mman.h4
-rw-r--r--tools/include/uapi/sound/asound.h1
-rw-r--r--tools/io_uring/io_uring-bench.c32
-rw-r--r--tools/lib/bpf/.gitignore2
-rw-r--r--tools/lib/bpf/Makefile62
-rw-r--r--tools/lib/bpf/README.rst1
-rw-r--r--tools/lib/bpf/bpf.c38
-rw-r--r--tools/lib/bpf/bpf.h9
-rw-r--r--tools/lib/bpf/btf.c176
-rw-r--r--tools/lib/bpf/btf.h3
-rw-r--r--tools/lib/bpf/libbpf.c898
-rw-r--r--tools/lib/bpf/libbpf.h70
-rw-r--r--tools/lib/bpf/libbpf.map10
-rw-r--r--tools/lib/bpf/libbpf.pc.template12
-rw-r--r--tools/lib/bpf/libbpf_probes.c76
-rw-r--r--tools/lib/bpf/libbpf_util.h30
-rw-r--r--tools/lib/bpf/xsk.c208
-rw-r--r--tools/lib/bpf/xsk.h22
-rw-r--r--tools/lib/traceevent/event-parse-api.c278
-rw-r--r--tools/lib/traceevent/event-parse-local.h6
-rw-r--r--tools/lib/traceevent/event-parse.c911
-rw-r--r--tools/lib/traceevent/event-parse.h154
-rw-r--r--tools/lib/traceevent/event-plugin.c32
-rw-r--r--tools/lib/traceevent/kbuffer-parse.c49
-rw-r--r--tools/lib/traceevent/kbuffer.h13
-rw-r--r--tools/lib/traceevent/parse-filter.c216
-rw-r--r--tools/lib/traceevent/parse-utils.c2
-rw-r--r--tools/lib/traceevent/plugin_cfg80211.c8
-rw-r--r--tools/lib/traceevent/plugin_function.c14
-rw-r--r--tools/lib/traceevent/plugin_hrtimer.c12
-rw-r--r--tools/lib/traceevent/plugin_jbd2.c12
-rw-r--r--tools/lib/traceevent/plugin_kmem.c32
-rw-r--r--tools/lib/traceevent/plugin_kvm.c48
-rw-r--r--tools/lib/traceevent/plugin_mac80211.c8
-rw-r--r--tools/lib/traceevent/plugin_sched_switch.c18
-rw-r--r--tools/lib/traceevent/plugin_scsi.c8
-rw-r--r--tools/lib/traceevent/plugin_xen.c8
-rw-r--r--tools/memory-model/Documentation/explanation.txt289
-rw-r--r--tools/memory-model/README33
-rw-r--r--tools/memory-model/linux-kernel.bell35
-rw-r--r--tools/memory-model/linux-kernel.cat39
-rw-r--r--tools/memory-model/linux-kernel.def6
-rw-r--r--tools/memory-model/lock.cat3
-rw-r--r--tools/objtool/Makefile7
-rw-r--r--tools/objtool/arch.h8
-rw-r--r--tools/objtool/arch/x86/decode.c21
-rw-r--r--tools/objtool/builtin-check.c4
-rw-r--r--tools/objtool/builtin.h2
-rw-r--r--tools/objtool/check.c404
-rw-r--r--tools/objtool/check.h4
-rw-r--r--tools/objtool/elf.c15
-rw-r--r--tools/objtool/elf.h3
-rw-r--r--tools/objtool/special.c18
-rw-r--r--tools/objtool/special.h1
-rw-r--r--tools/objtool/warn.h8
-rw-r--r--tools/perf/Documentation/Build.txt24
-rw-r--r--tools/perf/Documentation/perf-config.txt16
-rw-r--r--tools/perf/Documentation/perf-record.txt23
-rw-r--r--tools/perf/Documentation/perf-report.txt13
-rw-r--r--tools/perf/Documentation/perf-script.txt3
-rw-r--r--tools/perf/Documentation/perf-stat.txt5
-rw-r--r--tools/perf/Documentation/tips.txt7
-rw-r--r--tools/perf/Makefile.config35
-rw-r--r--tools/perf/Makefile.perf7
-rw-r--r--tools/perf/arch/x86/entry/syscalls/syscall_64.tbl10
-rw-r--r--tools/perf/arch/x86/util/Build1
-rw-r--r--tools/perf/arch/x86/util/archinsn.c26
-rw-r--r--tools/perf/bench/epoll-ctl.c2
-rw-r--r--tools/perf/bench/epoll-wait.c2
-rw-r--r--tools/perf/bench/numa.c4
-rw-r--r--tools/perf/builtin-kmem.c2
-rw-r--r--tools/perf/builtin-list.c8
-rw-r--r--tools/perf/builtin-record.c119
-rw-r--r--tools/perf/builtin-report.c50
-rw-r--r--tools/perf/builtin-script.c129
-rw-r--r--tools/perf/builtin-stat.c32
-rw-r--r--tools/perf/builtin-top.c63
-rw-r--r--tools/perf/builtin-version.c2
-rw-r--r--tools/perf/builtin.h3
-rwxr-xr-xtools/perf/check-headers.sh2
-rw-r--r--tools/perf/examples/bpf/augmented_raw_syscalls.c196
-rw-r--r--tools/perf/perf.c1
-rw-r--r--tools/perf/perf.h3
-rw-r--r--tools/perf/pmu-events/arch/powerpc/power8/other.json594
-rw-r--r--tools/perf/pmu-events/arch/s390/cf_z14/extended.json2
-rw-r--r--tools/perf/pmu-events/arch/x86/amdfam17h/branch.json12
-rw-r--r--tools/perf/pmu-events/arch/x86/amdfam17h/cache.json287
-rw-r--r--tools/perf/pmu-events/arch/x86/amdfam17h/core.json134
-rw-r--r--tools/perf/pmu-events/arch/x86/amdfam17h/floating-point.json168
-rw-r--r--tools/perf/pmu-events/arch/x86/amdfam17h/memory.json162
-rw-r--r--tools/perf/pmu-events/arch/x86/amdfam17h/other.json65
-rw-r--r--tools/perf/pmu-events/arch/x86/bonnell/frontend.json2
-rw-r--r--tools/perf/pmu-events/arch/x86/bonnell/pipeline.json2
-rw-r--r--tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json260
-rw-r--r--tools/perf/pmu-events/arch/x86/broadwell/cache.json1630
-rw-r--r--tools/perf/pmu-events/arch/x86/broadwell/floating-point.json51
-rw-r--r--tools/perf/pmu-events/arch/x86/broadwell/frontend.json4
-rw-r--r--tools/perf/pmu-events/arch/x86/broadwell/memory.json1640
-rw-r--r--tools/perf/pmu-events/arch/x86/broadwell/pipeline.json36
-rw-r--r--tools/perf/pmu-events/arch/x86/broadwellde/cache.json4
-rw-r--r--tools/perf/pmu-events/arch/x86/broadwellde/pipeline.json6
-rw-r--r--tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json278
-rw-r--r--tools/perf/pmu-events/arch/x86/broadwellx/cache.json161
-rw-r--r--tools/perf/pmu-events/arch/x86/broadwellx/floating-point.json16
-rw-r--r--tools/perf/pmu-events/arch/x86/broadwellx/memory.json148
-rw-r--r--tools/perf/pmu-events/arch/x86/broadwellx/pipeline.json50
-rw-r--r--tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json304
-rw-r--r--tools/perf/pmu-events/arch/x86/goldmont/cache.json980
-rw-r--r--tools/perf/pmu-events/arch/x86/goldmont/memory.json260
-rw-r--r--tools/perf/pmu-events/arch/x86/goldmont/pipeline.json5
-rw-r--r--tools/perf/pmu-events/arch/x86/goldmont/virtual-memory.json9
-rw-r--r--tools/perf/pmu-events/arch/x86/goldmontplus/cache.json74
-rw-r--r--tools/perf/pmu-events/arch/x86/goldmontplus/pipeline.json5
-rw-r--r--tools/perf/pmu-events/arch/x86/goldmontplus/virtual-memory.json9
-rw-r--r--tools/perf/pmu-events/arch/x86/haswell/cache.json175
-rw-r--r--tools/perf/pmu-events/arch/x86/haswell/floating-point.json33
-rw-r--r--tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json234
-rw-r--r--tools/perf/pmu-events/arch/x86/haswell/memory.json172
-rw-r--r--tools/perf/pmu-events/arch/x86/haswell/pipeline.json33
-rw-r--r--tools/perf/pmu-events/arch/x86/haswellx/cache.json173
-rw-r--r--tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json252
-rw-r--r--tools/perf/pmu-events/arch/x86/haswellx/memory.json172
-rw-r--r--tools/perf/pmu-events/arch/x86/haswellx/pipeline.json10
-rw-r--r--tools/perf/pmu-events/arch/x86/ivybridge/cache.json10
-rw-r--r--tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json250
-rw-r--r--tools/perf/pmu-events/arch/x86/ivybridge/pipeline.json4
-rw-r--r--tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json256
-rw-r--r--tools/perf/pmu-events/arch/x86/ivytown/pipeline.json4
-rw-r--r--tools/perf/pmu-events/arch/x86/jaketown/cache.json6
-rw-r--r--tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json150
-rw-r--r--tools/perf/pmu-events/arch/x86/jaketown/pipeline.json12
-rw-r--r--tools/perf/pmu-events/arch/x86/knightslanding/cache.json666
-rw-r--r--tools/perf/pmu-events/arch/x86/knightslanding/memory.json268
-rw-r--r--tools/perf/pmu-events/arch/x86/knightslanding/pipeline.json15
-rw-r--r--tools/perf/pmu-events/arch/x86/knightslanding/virtual-memory.json2
-rw-r--r--tools/perf/pmu-events/arch/x86/mapfile.csv1
-rw-r--r--tools/perf/pmu-events/arch/x86/sandybridge/cache.json680
-rw-r--r--tools/perf/pmu-events/arch/x86/sandybridge/floating-point.json126
-rw-r--r--tools/perf/pmu-events/arch/x86/sandybridge/frontend.json268
-rw-r--r--tools/perf/pmu-events/arch/x86/sandybridge/memory.json68
-rw-r--r--tools/perf/pmu-events/arch/x86/sandybridge/other.json18
-rw-r--r--tools/perf/pmu-events/arch/x86/sandybridge/pipeline.json1328
-rw-r--r--tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json144
-rw-r--r--tools/perf/pmu-events/arch/x86/sandybridge/virtual-memory.json108
-rw-r--r--tools/perf/pmu-events/arch/x86/silvermont/cache.json2
-rw-r--r--tools/perf/pmu-events/arch/x86/silvermont/other.json20
-rw-r--r--tools/perf/pmu-events/arch/x86/silvermont/pipeline.json5
-rw-r--r--tools/perf/pmu-events/arch/x86/skylake/cache.json2157
-rw-r--r--tools/perf/pmu-events/arch/x86/skylake/frontend.json14
-rw-r--r--tools/perf/pmu-events/arch/x86/skylake/memory.json1121
-rw-r--r--tools/perf/pmu-events/arch/x86/skylake/pipeline.json39
-rw-r--r--tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json274
-rw-r--r--tools/perf/pmu-events/arch/x86/skylakex/cache.json786
-rw-r--r--tools/perf/pmu-events/arch/x86/skylakex/floating-point.json2
-rw-r--r--tools/perf/pmu-events/arch/x86/skylakex/frontend.json234
-rw-r--r--tools/perf/pmu-events/arch/x86/skylakex/memory.json751
-rw-r--r--tools/perf/pmu-events/arch/x86/skylakex/pipeline.json173
-rw-r--r--tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json304
-rw-r--r--tools/perf/scripts/python/export-to-postgresql.py61
-rw-r--r--tools/perf/scripts/python/export-to-sqlite.py28
-rwxr-xr-xtools/perf/scripts/python/exported-sql-viewer.py119
-rw-r--r--tools/perf/tests/attr/test-record-C02
-rw-r--r--tools/perf/tests/attr/test-record-basic2
-rw-r--r--tools/perf/tests/attr/test-record-branch-any2
-rw-r--r--tools/perf/tests/attr/test-record-branch-filter-any2
-rw-r--r--tools/perf/tests/attr/test-record-branch-filter-any_call2
-rw-r--r--tools/perf/tests/attr/test-record-branch-filter-any_ret2
-rw-r--r--tools/perf/tests/attr/test-record-branch-filter-hv2
-rw-r--r--tools/perf/tests/attr/test-record-branch-filter-ind_call2
-rw-r--r--tools/perf/tests/attr/test-record-branch-filter-k2
-rw-r--r--tools/perf/tests/attr/test-record-branch-filter-u2
-rw-r--r--tools/perf/tests/attr/test-record-count2
-rw-r--r--tools/perf/tests/attr/test-record-data2
-rw-r--r--tools/perf/tests/attr/test-record-freq2
-rw-r--r--tools/perf/tests/attr/test-record-graph-default2
-rw-r--r--tools/perf/tests/attr/test-record-graph-dwarf2
-rw-r--r--tools/perf/tests/attr/test-record-graph-fp2
-rw-r--r--tools/perf/tests/attr/test-record-group2
-rw-r--r--tools/perf/tests/attr/test-record-group-sampling2
-rw-r--r--tools/perf/tests/attr/test-record-group12
-rw-r--r--tools/perf/tests/attr/test-record-no-buffering2
-rw-r--r--tools/perf/tests/attr/test-record-no-inherit2
-rw-r--r--tools/perf/tests/attr/test-record-no-samples2
-rw-r--r--tools/perf/tests/attr/test-record-period2
-rw-r--r--tools/perf/tests/attr/test-record-raw2
-rw-r--r--tools/perf/tests/backward-ring-buffer.c2
-rw-r--r--tools/perf/tests/evsel-tp-sched.c1
-rw-r--r--tools/perf/tests/expr.c5
-rw-r--r--tools/perf/tests/openat-syscall-all-cpus.c4
-rwxr-xr-xtools/perf/trace/beauty/mmap_flags.sh14
-rw-r--r--tools/perf/trace/beauty/renameat.c1
-rw-r--r--tools/perf/trace/strace/groups/string65
-rw-r--r--tools/perf/ui/browser.c10
-rw-r--r--tools/perf/ui/browsers/Build1
-rw-r--r--tools/perf/ui/browsers/annotate.c2
-rw-r--r--tools/perf/ui/browsers/hists.c141
-rw-r--r--tools/perf/ui/browsers/res_sample.c91
-rw-r--r--tools/perf/ui/browsers/scripts.c274
-rw-r--r--tools/perf/util/annotate.c163
-rw-r--r--tools/perf/util/annotate.h1
-rw-r--r--tools/perf/util/archinsn.h12
-rw-r--r--tools/perf/util/bpf-event.c425
-rw-r--r--tools/perf/util/bpf-event.h42
-rw-r--r--tools/perf/util/build-id.c1
-rw-r--r--tools/perf/util/cloexec.c1
-rw-r--r--tools/perf/util/config.c3
-rw-r--r--tools/perf/util/cs-etm-decoder/cs-etm-decoder.c1
-rw-r--r--tools/perf/util/cs-etm.c14
-rw-r--r--tools/perf/util/data-convert-bt.c4
-rw-r--r--tools/perf/util/data.c107
-rw-r--r--tools/perf/util/data.h14
-rw-r--r--tools/perf/util/dso.c43
-rw-r--r--tools/perf/util/dso.h8
-rw-r--r--tools/perf/util/env.c159
-rw-r--r--tools/perf/util/env.h24
-rw-r--r--tools/perf/util/event.h1
-rw-r--r--tools/perf/util/evlist.c158
-rw-r--r--tools/perf/util/evlist.h17
-rw-r--r--tools/perf/util/evsel.c103
-rw-r--r--tools/perf/util/evsel.h12
-rw-r--r--tools/perf/util/header.c299
-rw-r--r--tools/perf/util/header.h7
-rw-r--r--tools/perf/util/hist.c54
-rw-r--r--tools/perf/util/hist.h31
-rw-r--r--tools/perf/util/intel-pt-decoder/intel-pt-decoder.c20
-rw-r--r--tools/perf/util/machine.c32
-rw-r--r--tools/perf/util/map.c38
-rw-r--r--tools/perf/util/map.h4
-rw-r--r--tools/perf/util/mmap.c4
-rw-r--r--tools/perf/util/mmap.h3
-rw-r--r--tools/perf/util/ordered-events.c2
-rw-r--r--tools/perf/util/parse-events.c60
-rw-r--r--tools/perf/util/parse-events.h5
-rw-r--r--tools/perf/util/parse-events.l11
-rw-r--r--tools/perf/util/parse-events.y12
-rw-r--r--tools/perf/util/pmu.c10
-rw-r--r--tools/perf/util/probe-event.c6
-rw-r--r--tools/perf/util/python.c2
-rw-r--r--tools/perf/util/scripting-engines/trace-event-perl.c2
-rw-r--r--tools/perf/util/scripting-engines/trace-event-python.c2
-rw-r--r--tools/perf/util/session.c36
-rw-r--r--tools/perf/util/sort.c91
-rw-r--r--tools/perf/util/sort.h12
-rw-r--r--tools/perf/util/stat-display.c18
-rw-r--r--tools/perf/util/stat.c12
-rw-r--r--tools/perf/util/symbol.c5
-rw-r--r--tools/perf/util/symbol_conf.h3
-rw-r--r--tools/perf/util/time-utils.c8
-rw-r--r--tools/perf/util/time-utils.h1
-rw-r--r--tools/perf/util/trace-event-parse.c2
-rw-r--r--tools/perf/util/trace-event-read.c2
-rw-r--r--tools/perf/util/trace-event.c4
-rw-r--r--tools/power/acpi/os_specific/service_layers/oslinuxtbl.c48
-rw-r--r--tools/power/acpi/tools/acpidump/apdump.c8
-rw-r--r--tools/power/acpi/tools/acpidump/apfiles.c8
-rw-r--r--tools/power/x86/turbostat/turbostat.c280
-rwxr-xr-xtools/testing/ktest/ktest.pl41
-rw-r--r--tools/testing/ktest/sample.conf4
-rw-r--r--tools/testing/nvdimm/test/nfit.c17
-rw-r--r--tools/testing/selftests/Makefile63
-rw-r--r--tools/testing/selftests/bpf/.gitignore1
-rw-r--r--tools/testing/selftests/bpf/Makefile41
-rw-r--r--tools/testing/selftests/bpf/bpf_helpers.h60
-rw-r--r--tools/testing/selftests/bpf/config11
-rw-r--r--tools/testing/selftests/bpf/flow_dissector_load.c4
-rw-r--r--tools/testing/selftests/bpf/flow_dissector_load.h24
-rw-r--r--tools/testing/selftests/bpf/map_tests/sk_storage_map.c629
-rw-r--r--tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c8
-rw-r--r--tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c49
-rw-r--r--tools/testing/selftests/bpf/prog_tests/flow_dissector.c258
-rw-r--r--tools/testing/selftests/bpf/prog_tests/flow_dissector_load_bytes.c48
-rw-r--r--tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c4
-rw-r--r--tools/testing/selftests/bpf/prog_tests/global_data.c157
-rw-r--r--tools/testing/selftests/bpf/prog_tests/map_lock.c2
-rw-r--r--tools/testing/selftests/bpf/prog_tests/raw_tp_writable_reject_nbd_invalid.c42
-rw-r--r--tools/testing/selftests/bpf/prog_tests/raw_tp_writable_test_run.c80
-rw-r--r--tools/testing/selftests/bpf/prog_tests/skb_ctx.c89
-rw-r--r--tools/testing/selftests/bpf/prog_tests/spinlock.c2
-rw-r--r--tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c16
-rw-r--r--tools/testing/selftests/bpf/progs/bpf_flow.c98
-rw-r--r--tools/testing/selftests/bpf/progs/test_global_data.c106
-rw-r--r--tools/testing/selftests/bpf/progs/test_jhash.h70
-rw-r--r--tools/testing/selftests/bpf/progs/test_skb_ctx.c21
-rw-r--r--tools/testing/selftests/bpf/progs/test_sock_fields_kern.c141
-rw-r--r--tools/testing/selftests/bpf/progs/test_sysctl_prog.c70
-rw-r--r--tools/testing/selftests/bpf/progs/test_tc_edt.c109
-rw-r--r--tools/testing/selftests/bpf/progs/test_tc_tunnel.c536
-rw-r--r--tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c129
-rw-r--r--tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c2
-rw-r--r--tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c2
-rw-r--r--tools/testing/selftests/bpf/progs/test_verif_scale1.c30
-rw-r--r--tools/testing/selftests/bpf/progs/test_verif_scale2.c30
-rw-r--r--tools/testing/selftests/bpf/progs/test_verif_scale3.c30
-rw-r--r--tools/testing/selftests/bpf/test_btf.c890
-rw-r--r--tools/testing/selftests/bpf/test_btf.h69
-rw-r--r--tools/testing/selftests/bpf/test_libbpf_open.c2
-rwxr-xr-xtools/testing/selftests/bpf/test_lwt_ip_encap.sh134
-rw-r--r--tools/testing/selftests/bpf/test_maps.c18
-rw-r--r--tools/testing/selftests/bpf/test_maps.h17
-rwxr-xr-xtools/testing/selftests/bpf/test_offload.py227
-rw-r--r--tools/testing/selftests/bpf/test_progs.c6
-rw-r--r--tools/testing/selftests/bpf/test_progs.h1
-rw-r--r--tools/testing/selftests/bpf/test_section_names.c5
-rw-r--r--tools/testing/selftests/bpf/test_sock_fields.c249
-rw-r--r--tools/testing/selftests/bpf/test_sysctl.c1567
-rwxr-xr-xtools/testing/selftests/bpf/test_tc_edt.sh99
-rwxr-xr-xtools/testing/selftests/bpf/test_tc_tunnel.sh290
-rwxr-xr-xtools/testing/selftests/bpf/test_tcp_check_syncookie.sh81
-rw-r--r--tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c212
-rw-r--r--tools/testing/selftests/bpf/test_verifier.c215
-rw-r--r--tools/testing/selftests/bpf/trace_helpers.c4
-rw-r--r--tools/testing/selftests/bpf/urandom_read.c15
-rw-r--r--tools/testing/selftests/bpf/verifier/array_access.c159
-rw-r--r--tools/testing/selftests/bpf/verifier/calls.c88
-rw-r--r--tools/testing/selftests/bpf/verifier/ctx_skb.c1
-rw-r--r--tools/testing/selftests/bpf/verifier/direct_packet_access.c22
-rw-r--r--tools/testing/selftests/bpf/verifier/direct_value_access.c347
-rw-r--r--tools/testing/selftests/bpf/verifier/int_ptr.c160
-rw-r--r--tools/testing/selftests/bpf/verifier/jit.c19
-rw-r--r--tools/testing/selftests/bpf/verifier/ld_dw.c9
-rw-r--r--tools/testing/selftests/bpf/verifier/raw_tp_writable.c34
-rw-r--r--tools/testing/selftests/bpf/verifier/ref_tracking.c280
-rw-r--r--tools/testing/selftests/bpf/verifier/scale.c18
-rw-r--r--tools/testing/selftests/bpf/verifier/sock.c120
-rw-r--r--tools/testing/selftests/bpf/verifier/unpriv.c8
-rw-r--r--tools/testing/selftests/bpf/verifier/var_off.c186
-rw-r--r--tools/testing/selftests/cgroup/test_memcontrol.c38
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/qos_ets_strict.sh311
-rw-r--r--tools/testing/selftests/drivers/net/mlxsw/qos_lib.sh98
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh122
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh46
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh1
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/spectrum/devlink_resources.sh3
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh5
-rwxr-xr-xtools/testing/selftests/efivarfs/efivarfs.sh28
-rw-r--r--tools/testing/selftests/gpio/gpio-mockup-chardev.c1
-rw-r--r--tools/testing/selftests/ima/config4
-rwxr-xr-xtools/testing/selftests/ima/test_kexec_load.sh54
-rw-r--r--tools/testing/selftests/ipc/msgque.c11
-rw-r--r--tools/testing/selftests/kexec/Makefile (renamed from tools/testing/selftests/ima/Makefile)5
-rw-r--r--tools/testing/selftests/kexec/config3
-rwxr-xr-xtools/testing/selftests/kexec/kexec_common_lib.sh220
-rwxr-xr-xtools/testing/selftests/kexec/test_kexec_file_load.sh208
-rwxr-xr-xtools/testing/selftests/kexec/test_kexec_load.sh47
-rw-r--r--tools/testing/selftests/kselftest_harness.h2
-rw-r--r--tools/testing/selftests/kselftest_module.h48
-rwxr-xr-xtools/testing/selftests/kselftest_module.sh84
-rw-r--r--tools/testing/selftests/kvm/Makefile11
-rw-r--r--tools/testing/selftests/kvm/dirty_log_test.c9
-rw-r--r--tools/testing/selftests/kvm/include/kvm_util.h1
-rw-r--r--tools/testing/selftests/kvm/include/x86_64/processor.h27
-rw-r--r--tools/testing/selftests/kvm/lib/kvm_util.c21
-rw-r--r--tools/testing/selftests/kvm/lib/x86_64/processor.c20
-rw-r--r--tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c35
-rw-r--r--tools/testing/selftests/kvm/x86_64/evmcs_test.c5
-rw-r--r--tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c9
-rw-r--r--tools/testing/selftests/kvm/x86_64/smm_test.c157
-rw-r--r--tools/testing/selftests/kvm/x86_64/state_test.c5
-rw-r--r--tools/testing/selftests/lib.mk38
-rw-r--r--tools/testing/selftests/lib/Makefile2
-rwxr-xr-xtools/testing/selftests/lib/bitmap.sh18
-rw-r--r--tools/testing/selftests/lib/config1
-rwxr-xr-xtools/testing/selftests/lib/prime_numbers.sh17
-rwxr-xr-xtools/testing/selftests/lib/printf.sh19
-rwxr-xr-xtools/testing/selftests/lib/strscpy.sh3
-rw-r--r--tools/testing/selftests/livepatch/Makefile3
-rw-r--r--tools/testing/selftests/net/config2
-rwxr-xr-xtools/testing/selftests/net/fib_rule_tests.sh10
-rwxr-xr-xtools/testing/selftests/net/fib_tests.sh164
-rwxr-xr-xtools/testing/selftests/net/forwarding/bridge_igmp.sh152
-rw-r--r--tools/testing/selftests/net/forwarding/devlink_lib.sh110
-rwxr-xr-xtools/testing/selftests/net/forwarding/loopback.sh94
-rwxr-xr-xtools/testing/selftests/net/forwarding/router_multicast.sh107
-rwxr-xr-xtools/testing/selftests/net/forwarding/tc_flower.sh59
-rwxr-xr-xtools/testing/selftests/net/forwarding/tc_vlan_modify.sh164
-rwxr-xr-xtools/testing/selftests/net/pmtu.sh213
-rwxr-xr-xtools/testing/selftests/net/rtnetlink.sh11
-rwxr-xr-xtools/testing/selftests/net/run_afpackettests5
-rwxr-xr-xtools/testing/selftests/net/run_netsocktests2
-rw-r--r--tools/testing/selftests/netfilter/Makefile3
-rwxr-xr-xtools/testing/selftests/netfilter/bridge_brouter.sh146
-rwxr-xr-xtools/testing/selftests/netfilter/conntrack_icmp_related.sh283
-rwxr-xr-xtools/testing/selftests/netfilter/nft_nat.sh182
-rw-r--r--tools/testing/selftests/proc/proc-pid-vm.c4
-rw-r--r--tools/testing/selftests/proc/proc-self-map-files-002.c20
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/configNR_CPUS.sh17
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/config_override.sh17
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/configcheck.sh19
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/configinit.sh17
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/cpus2use.sh17
-rw-r--r--tools/testing/selftests/rcutorture/bin/functions.sh17
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/jitter.sh17
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm-build.sh17
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm-find-errors.sh5
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm-recheck-lock.sh17
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh17
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm-recheck-rcuperf-ftrace.sh17
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm-recheck-rcuperf.sh17
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm-recheck.sh17
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh17
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm.sh17
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/mkinitrd.sh15
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/parse-build.sh17
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/parse-console.sh17
-rw-r--r--tools/testing/selftests/rcutorture/configs/lock/ver_functions.sh17
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh17
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcuperf/ver_functions.sh17
-rw-r--r--tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/types.h4
-rw-r--r--tools/testing/selftests/rseq/rseq-s390.h9
-rw-r--r--tools/testing/selftests/rseq/rseq.h1
-rwxr-xr-xtools/testing/selftests/rseq/run_param_test.sh7
-rw-r--r--tools/testing/selftests/seccomp/seccomp_bpf.c77
-rw-r--r--tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json25
-rw-r--r--tools/testing/selftests/tc-testing/tc-tests/actions/connmark.json25
-rw-r--r--tools/testing/selftests/tc-testing/tc-tests/actions/csum.json25
-rw-r--r--tools/testing/selftests/tc-testing/tc-tests/actions/gact.json25
-rw-r--r--tools/testing/selftests/tc-testing/tc-tests/actions/ife.json25
-rw-r--r--tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json25
-rw-r--r--tools/testing/selftests/tc-testing/tc-tests/actions/nat.json25
-rw-r--r--tools/testing/selftests/tc-testing/tc-tests/actions/pedit.json954
-rw-r--r--tools/testing/selftests/tc-testing/tc-tests/actions/police.json25
-rw-r--r--tools/testing/selftests/tc-testing/tc-tests/actions/sample.json49
-rw-r--r--tools/testing/selftests/tc-testing/tc-tests/actions/simple.json25
-rw-r--r--tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json25
-rw-r--r--tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json25
-rw-r--r--tools/testing/selftests/tc-testing/tc-tests/actions/tunnel_key.json25
-rw-r--r--tools/testing/selftests/tc-testing/tc-tests/actions/vlan.json25
-rw-r--r--tools/testing/selftests/tc-testing/tc-tests/filters/tests.json40
-rw-r--r--tools/testing/selftests/timers/skew_consistency.c1
-rw-r--r--tools/testing/selftests/tpm2/tpm2.py5
-rw-r--r--tools/testing/selftests/tpm2/tpm2_tests.py63
-rw-r--r--tools/testing/selftests/x86/mpx-dig.c2
480 files changed, 32421 insertions, 11303 deletions
diff --git a/tools/arch/alpha/include/uapi/asm/mman.h b/tools/arch/alpha/include/uapi/asm/mman.h
index c317d3e6867a..ea6a255ae61f 100644
--- a/tools/arch/alpha/include/uapi/asm/mman.h
+++ b/tools/arch/alpha/include/uapi/asm/mman.h
@@ -27,8 +27,6 @@
#define MAP_NONBLOCK 0x40000
#define MAP_NORESERVE 0x10000
#define MAP_POPULATE 0x20000
-#define MAP_PRIVATE 0x02
-#define MAP_SHARED 0x01
#define MAP_STACK 0x80000
#define PROT_EXEC 0x4
#define PROT_GROWSDOWN 0x01000000
diff --git a/tools/arch/arc/include/uapi/asm/unistd.h b/tools/arch/arc/include/uapi/asm/unistd.h
new file mode 100644
index 000000000000..5eafa1115162
--- /dev/null
+++ b/tools/arch/arc/include/uapi/asm/unistd.h
@@ -0,0 +1,51 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/******** no-legacy-syscalls-ABI *******/
+
+/*
+ * Non-typical guard macro to enable inclusion twice in ARCH sys.c
+ * That is how the Generic syscall wrapper generator works
+ */
+#if !defined(_UAPI_ASM_ARC_UNISTD_H) || defined(__SYSCALL)
+#define _UAPI_ASM_ARC_UNISTD_H
+
+#define __ARCH_WANT_RENAMEAT
+#define __ARCH_WANT_STAT64
+#define __ARCH_WANT_SET_GET_RLIMIT
+#define __ARCH_WANT_SYS_EXECVE
+#define __ARCH_WANT_SYS_CLONE
+#define __ARCH_WANT_SYS_VFORK
+#define __ARCH_WANT_SYS_FORK
+#define __ARCH_WANT_TIME32_SYSCALLS
+
+#define sys_mmap2 sys_mmap_pgoff
+
+#include <asm-generic/unistd.h>
+
+#define NR_syscalls __NR_syscalls
+
+/* Generic syscall (fs/filesystems.c - lost in asm-generic/unistd.h */
+#define __NR_sysfs (__NR_arch_specific_syscall + 3)
+
+/* ARC specific syscall */
+#define __NR_cacheflush (__NR_arch_specific_syscall + 0)
+#define __NR_arc_settls (__NR_arch_specific_syscall + 1)
+#define __NR_arc_gettls (__NR_arch_specific_syscall + 2)
+#define __NR_arc_usr_cmpxchg (__NR_arch_specific_syscall + 4)
+
+__SYSCALL(__NR_cacheflush, sys_cacheflush)
+__SYSCALL(__NR_arc_settls, sys_arc_settls)
+__SYSCALL(__NR_arc_gettls, sys_arc_gettls)
+__SYSCALL(__NR_arc_usr_cmpxchg, sys_arc_usr_cmpxchg)
+__SYSCALL(__NR_sysfs, sys_sysfs)
+
+#undef __SYSCALL
+
+#endif
diff --git a/tools/arch/arm64/include/asm/barrier.h b/tools/arch/arm64/include/asm/barrier.h
index 378c051fa177..3b9b41331c4f 100644
--- a/tools/arch/arm64/include/asm/barrier.h
+++ b/tools/arch/arm64/include/asm/barrier.h
@@ -14,6 +14,16 @@
#define wmb() asm volatile("dmb ishst" ::: "memory")
#define rmb() asm volatile("dmb ishld" ::: "memory")
+/*
+ * Kernel uses dmb variants on arm64 for smp_*() barriers. Pretty much the same
+ * implementation as above mb()/wmb()/rmb(), though for the latter kernel uses
+ * dsb. In any case, should above mb()/wmb()/rmb() change, make sure the below
+ * smp_*() don't.
+ */
+#define smp_mb() asm volatile("dmb ish" ::: "memory")
+#define smp_wmb() asm volatile("dmb ishst" ::: "memory")
+#define smp_rmb() asm volatile("dmb ishld" ::: "memory")
+
#define smp_store_release(p, v) \
do { \
union { typeof(*p) __val; char __c[1]; } __u = \
diff --git a/tools/arch/arm64/include/uapi/asm/unistd.h b/tools/arch/arm64/include/uapi/asm/unistd.h
index dae1584cf017..4703d218663a 100644
--- a/tools/arch/arm64/include/uapi/asm/unistd.h
+++ b/tools/arch/arm64/include/uapi/asm/unistd.h
@@ -17,5 +17,7 @@
#define __ARCH_WANT_RENAMEAT
#define __ARCH_WANT_NEW_STAT
+#define __ARCH_WANT_SET_GET_RLIMIT
+#define __ARCH_WANT_TIME32_SYSCALLS
#include <asm-generic/unistd.h>
diff --git a/tools/arch/hexagon/include/uapi/asm/unistd.h b/tools/arch/hexagon/include/uapi/asm/unistd.h
new file mode 100644
index 000000000000..432c4db1b623
--- /dev/null
+++ b/tools/arch/hexagon/include/uapi/asm/unistd.h
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Syscall support for Hexagon
+ *
+ * Copyright (c) 2010-2011, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA.
+ */
+
+/*
+ * The kernel pulls this unistd.h in three different ways:
+ * 1. the "normal" way which gets all the __NR defines
+ * 2. with __SYSCALL defined to produce function declarations
+ * 3. with __SYSCALL defined to produce syscall table initialization
+ * See also: syscalltab.c
+ */
+
+#define sys_mmap2 sys_mmap_pgoff
+#define __ARCH_WANT_RENAMEAT
+#define __ARCH_WANT_STAT64
+#define __ARCH_WANT_SET_GET_RLIMIT
+#define __ARCH_WANT_SYS_EXECVE
+#define __ARCH_WANT_SYS_CLONE
+#define __ARCH_WANT_SYS_VFORK
+#define __ARCH_WANT_SYS_FORK
+#define __ARCH_WANT_TIME32_SYSCALLS
+
+#include <asm-generic/unistd.h>
diff --git a/tools/arch/mips/include/uapi/asm/mman.h b/tools/arch/mips/include/uapi/asm/mman.h
index de2206883abc..c8acaa138d46 100644
--- a/tools/arch/mips/include/uapi/asm/mman.h
+++ b/tools/arch/mips/include/uapi/asm/mman.h
@@ -28,8 +28,6 @@
#define MAP_NONBLOCK 0x20000
#define MAP_NORESERVE 0x0400
#define MAP_POPULATE 0x10000
-#define MAP_PRIVATE 0x002
-#define MAP_SHARED 0x001
#define MAP_STACK 0x40000
#define PROT_EXEC 0x04
#define PROT_GROWSDOWN 0x01000000
diff --git a/tools/arch/parisc/include/uapi/asm/mman.h b/tools/arch/parisc/include/uapi/asm/mman.h
index 1bd78758bde9..f9fd1325f5bd 100644
--- a/tools/arch/parisc/include/uapi/asm/mman.h
+++ b/tools/arch/parisc/include/uapi/asm/mman.h
@@ -27,8 +27,6 @@
#define MAP_NONBLOCK 0x20000
#define MAP_NORESERVE 0x4000
#define MAP_POPULATE 0x10000
-#define MAP_PRIVATE 0x02
-#define MAP_SHARED 0x01
#define MAP_STACK 0x40000
#define PROT_EXEC 0x4
#define PROT_GROWSDOWN 0x01000000
diff --git a/tools/arch/powerpc/include/uapi/asm/kvm.h b/tools/arch/powerpc/include/uapi/asm/kvm.h
index 8c876c166ef2..26ca425f4c2c 100644
--- a/tools/arch/powerpc/include/uapi/asm/kvm.h
+++ b/tools/arch/powerpc/include/uapi/asm/kvm.h
@@ -463,10 +463,12 @@ struct kvm_ppc_cpu_char {
#define KVM_PPC_CPU_CHAR_BR_HINT_HONOURED (1ULL << 58)
#define KVM_PPC_CPU_CHAR_MTTRIG_THR_RECONF (1ULL << 57)
#define KVM_PPC_CPU_CHAR_COUNT_CACHE_DIS (1ULL << 56)
+#define KVM_PPC_CPU_CHAR_BCCTR_FLUSH_ASSIST (1ull << 54)
#define KVM_PPC_CPU_BEHAV_FAVOUR_SECURITY (1ULL << 63)
#define KVM_PPC_CPU_BEHAV_L1D_FLUSH_PR (1ULL << 62)
#define KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR (1ULL << 61)
+#define KVM_PPC_CPU_BEHAV_FLUSH_COUNT_CACHE (1ull << 58)
/* Per-vcpu XICS interrupt controller state */
#define KVM_REG_PPC_ICP_STATE (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x8c)
diff --git a/tools/arch/riscv/include/uapi/asm/unistd.h b/tools/arch/riscv/include/uapi/asm/unistd.h
new file mode 100644
index 000000000000..0e2eeeb1fd27
--- /dev/null
+++ b/tools/arch/riscv/include/uapi/asm/unistd.h
@@ -0,0 +1,42 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Copyright (C) 2018 David Abdurachmanov <david.abdurachmanov@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifdef __LP64__
+#define __ARCH_WANT_NEW_STAT
+#define __ARCH_WANT_SET_GET_RLIMIT
+#endif /* __LP64__ */
+
+#include <asm-generic/unistd.h>
+
+/*
+ * Allows the instruction cache to be flushed from userspace. Despite RISC-V
+ * having a direct 'fence.i' instruction available to userspace (which we
+ * can't trap!), that's not actually viable when running on Linux because the
+ * kernel might schedule a process on another hart. There is no way for
+ * userspace to handle this without invoking the kernel (as it doesn't know the
+ * thread->hart mappings), so we've defined a RISC-V specific system call to
+ * flush the instruction cache.
+ *
+ * __NR_riscv_flush_icache is defined to flush the instruction cache over an
+ * address range, with the flush applying to either all threads or just the
+ * caller. We don't currently do anything with the address range, that's just
+ * in there for forwards compatibility.
+ */
+#ifndef __NR_riscv_flush_icache
+#define __NR_riscv_flush_icache (__NR_arch_specific_syscall + 15)
+#endif
+__SYSCALL(__NR_riscv_flush_icache, sys_riscv_flush_icache)
diff --git a/tools/arch/x86/include/asm/barrier.h b/tools/arch/x86/include/asm/barrier.h
index 58919868473c..0adf295dd5b6 100644
--- a/tools/arch/x86/include/asm/barrier.h
+++ b/tools/arch/x86/include/asm/barrier.h
@@ -21,9 +21,12 @@
#define rmb() asm volatile("lock; addl $0,0(%%esp)" ::: "memory")
#define wmb() asm volatile("lock; addl $0,0(%%esp)" ::: "memory")
#elif defined(__x86_64__)
-#define mb() asm volatile("mfence":::"memory")
-#define rmb() asm volatile("lfence":::"memory")
+#define mb() asm volatile("mfence" ::: "memory")
+#define rmb() asm volatile("lfence" ::: "memory")
#define wmb() asm volatile("sfence" ::: "memory")
+#define smp_rmb() barrier()
+#define smp_wmb() barrier()
+#define smp_mb() asm volatile("lock; addl $0,-132(%%rsp)" ::: "memory", "cc")
#endif
#if defined(__x86_64__)
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 6d6122524711..981ff9479648 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -344,6 +344,7 @@
/* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */
#define X86_FEATURE_AVX512_4VNNIW (18*32+ 2) /* AVX-512 Neural Network Instructions */
#define X86_FEATURE_AVX512_4FMAPS (18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */
+#define X86_FEATURE_TSX_FORCE_ABORT (18*32+13) /* "" TSX_FORCE_ABORT */
#define X86_FEATURE_PCONFIG (18*32+18) /* Intel PCONFIG */
#define X86_FEATURE_SPEC_CTRL (18*32+26) /* "" Speculation Control (IBRS + IBPB) */
#define X86_FEATURE_INTEL_STIBP (18*32+27) /* "" Single Thread Indirect Branch Predictors */
diff --git a/tools/arch/x86/include/uapi/asm/vmx.h b/tools/arch/x86/include/uapi/asm/vmx.h
index f0b0c90dd398..d213ec5c3766 100644
--- a/tools/arch/x86/include/uapi/asm/vmx.h
+++ b/tools/arch/x86/include/uapi/asm/vmx.h
@@ -146,6 +146,7 @@
#define VMX_ABORT_SAVE_GUEST_MSR_FAIL 1
#define VMX_ABORT_LOAD_HOST_PDPTE_FAIL 2
+#define VMX_ABORT_VMCS_CORRUPTED 3
#define VMX_ABORT_LOAD_HOST_MSR_FAIL 4
#endif /* _UAPIVMX_H */
diff --git a/tools/arch/xtensa/include/uapi/asm/mman.h b/tools/arch/xtensa/include/uapi/asm/mman.h
index 34dde6f44dae..f2b08c990afc 100644
--- a/tools/arch/xtensa/include/uapi/asm/mman.h
+++ b/tools/arch/xtensa/include/uapi/asm/mman.h
@@ -27,8 +27,6 @@
#define MAP_NONBLOCK 0x20000
#define MAP_NORESERVE 0x0400
#define MAP_POPULATE 0x10000
-#define MAP_PRIVATE 0x002
-#define MAP_SHARED 0x001
#define MAP_STACK 0x40000
#define PROT_EXEC 0x4
#define PROT_GROWSDOWN 0x01000000
diff --git a/tools/bpf/bpftool/.gitignore b/tools/bpf/bpftool/.gitignore
index 67167e44b726..8248b8dd89d4 100644
--- a/tools/bpf/bpftool/.gitignore
+++ b/tools/bpf/bpftool/.gitignore
@@ -1,5 +1,5 @@
*.d
-bpftool
+/bpftool
bpftool*.8
bpf-helpers.*
FEATURE-DUMP.bpftool
diff --git a/tools/bpf/bpftool/Documentation/bpftool-btf.rst b/tools/bpf/bpftool/Documentation/bpftool-btf.rst
new file mode 100644
index 000000000000..2dbc1413fabd
--- /dev/null
+++ b/tools/bpf/bpftool/Documentation/bpftool-btf.rst
@@ -0,0 +1,222 @@
+================
+bpftool-btf
+================
+-------------------------------------------------------------------------------
+tool for inspection of BTF data
+-------------------------------------------------------------------------------
+
+:Manual section: 8
+
+SYNOPSIS
+========
+
+ **bpftool** [*OPTIONS*] **btf** *COMMAND*
+
+ *OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] }
+
+ *COMMANDS* := { **dump** | **help** }
+
+BTF COMMANDS
+=============
+
+| **bpftool** **btf dump** *BTF_SRC*
+| **bpftool** **btf help**
+|
+| *BTF_SRC* := { **id** *BTF_ID* | **prog** *PROG* | **map** *MAP* [{**key** | **value** | **kv** | **all**}] | **file** *FILE* }
+| *MAP* := { **id** *MAP_ID* | **pinned** *FILE* }
+| *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* }
+
+DESCRIPTION
+===========
+ **bpftool btf dump** *BTF_SRC*
+ Dump BTF entries from a given *BTF_SRC*.
+
+ When **id** is specified, BTF object with that ID will be
+ loaded and all its BTF types emitted.
+
+ When **map** is provided, it's expected that map has
+ associated BTF object with BTF types describing key and
+ value. It's possible to select whether to dump only BTF
+ type(s) associated with key (**key**), value (**value**),
+ both key and value (**kv**), or all BTF types present in
+ associated BTF object (**all**). If not specified, **kv**
+ is assumed.
+
+ When **prog** is provided, it's expected that program has
+ associated BTF object with BTF types.
+
+ When specifying *FILE*, an ELF file is expected, containing
+ .BTF section with well-defined BTF binary format data,
+ typically produced by clang or pahole.
+
+ **bpftool btf help**
+ Print short help message.
+
+OPTIONS
+=======
+ -h, --help
+ Print short generic help message (similar to **bpftool help**).
+
+ -V, --version
+ Print version number (similar to **bpftool version**).
+
+ -j, --json
+ Generate JSON output. For commands that cannot produce JSON, this
+ option has no effect.
+
+ -p, --pretty
+ Generate human-readable JSON output. Implies **-j**.
+
+EXAMPLES
+========
+**# bpftool btf dump id 1226**
+::
+
+ [1] PTR '(anon)' type_id=2
+ [2] STRUCT 'dummy_tracepoint_args' size=16 vlen=2
+ 'pad' type_id=3 bits_offset=0
+ 'sock' type_id=4 bits_offset=64
+ [3] INT 'long long unsigned int' size=8 bits_offset=0 nr_bits=64 encoding=(none)
+ [4] PTR '(anon)' type_id=5
+ [5] FWD 'sock' fwd_kind=union
+
+This gives an example of default output for all supported BTF kinds.
+
+**$ cat prog.c**
+::
+
+ struct fwd_struct;
+
+ enum my_enum {
+ VAL1 = 3,
+ VAL2 = 7,
+ };
+
+ typedef struct my_struct my_struct_t;
+
+ struct my_struct {
+ const unsigned int const_int_field;
+ int bitfield_field: 4;
+ char arr_field[16];
+ const struct fwd_struct *restrict fwd_field;
+ enum my_enum enum_field;
+ volatile my_struct_t *typedef_ptr_field;
+ };
+
+ union my_union {
+ int a;
+ struct my_struct b;
+ };
+
+ struct my_struct struct_global_var __attribute__((section("data_sec"))) = {
+ .bitfield_field = 3,
+ .enum_field = VAL1,
+ };
+ int global_var __attribute__((section("data_sec"))) = 7;
+
+ __attribute__((noinline))
+ int my_func(union my_union *arg1, int arg2)
+ {
+ static int static_var __attribute__((section("data_sec"))) = 123;
+ static_var++;
+ return static_var;
+ }
+
+**$ bpftool btf dump file prog.o**
+::
+
+ [1] PTR '(anon)' type_id=2
+ [2] UNION 'my_union' size=48 vlen=2
+ 'a' type_id=3 bits_offset=0
+ 'b' type_id=4 bits_offset=0
+ [3] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED
+ [4] STRUCT 'my_struct' size=48 vlen=6
+ 'const_int_field' type_id=5 bits_offset=0
+ 'bitfield_field' type_id=3 bits_offset=32 bitfield_size=4
+ 'arr_field' type_id=8 bits_offset=40
+ 'fwd_field' type_id=10 bits_offset=192
+ 'enum_field' type_id=14 bits_offset=256
+ 'typedef_ptr_field' type_id=15 bits_offset=320
+ [5] CONST '(anon)' type_id=6
+ [6] INT 'unsigned int' size=4 bits_offset=0 nr_bits=32 encoding=(none)
+ [7] INT 'char' size=1 bits_offset=0 nr_bits=8 encoding=SIGNED
+ [8] ARRAY '(anon)' type_id=7 index_type_id=9 nr_elems=16
+ [9] INT '__ARRAY_SIZE_TYPE__' size=4 bits_offset=0 nr_bits=32 encoding=(none)
+ [10] RESTRICT '(anon)' type_id=11
+ [11] PTR '(anon)' type_id=12
+ [12] CONST '(anon)' type_id=13
+ [13] FWD 'fwd_struct' fwd_kind=union
+ [14] ENUM 'my_enum' size=4 vlen=2
+ 'VAL1' val=3
+ 'VAL2' val=7
+ [15] PTR '(anon)' type_id=16
+ [16] VOLATILE '(anon)' type_id=17
+ [17] TYPEDEF 'my_struct_t' type_id=4
+ [18] FUNC_PROTO '(anon)' ret_type_id=3 vlen=2
+ 'arg1' type_id=1
+ 'arg2' type_id=3
+ [19] FUNC 'my_func' type_id=18
+ [20] VAR 'struct_global_var' type_id=4, linkage=global-alloc
+ [21] VAR 'global_var' type_id=3, linkage=global-alloc
+ [22] VAR 'my_func.static_var' type_id=3, linkage=static
+ [23] DATASEC 'data_sec' size=0 vlen=3
+ type_id=20 offset=0 size=48
+ type_id=21 offset=0 size=4
+ type_id=22 offset=52 size=4
+
+The following commands print BTF types associated with specified map's key,
+value, both key and value, and all BTF types, respectively. By default, both
+key and value types will be printed.
+
+**# bpftool btf dump map id 123 key**
+
+::
+
+ [39] TYPEDEF 'u32' type_id=37
+
+**# bpftool btf dump map id 123 value**
+
+::
+
+ [86] PTR '(anon)' type_id=87
+
+**# bpftool btf dump map id 123 kv**
+
+::
+
+ [39] TYPEDEF 'u32' type_id=37
+ [86] PTR '(anon)' type_id=87
+
+**# bpftool btf dump map id 123 all**
+
+::
+
+ [1] PTR '(anon)' type_id=0
+ .
+ .
+ .
+ [2866] ARRAY '(anon)' type_id=52 index_type_id=51 nr_elems=4
+
+All the standard ways to specify map or program are supported:
+
+**# bpftool btf dump map id 123**
+
+**# bpftool btf dump map pinned /sys/fs/bpf/map_name**
+
+**# bpftool btf dump prog id 456**
+
+**# bpftool btf dump prog tag b88e0a09b1d9759d**
+
+**# bpftool btf dump prog pinned /sys/fs/bpf/prog_name**
+
+SEE ALSO
+========
+ **bpf**\ (2),
+ **bpf-helpers**\ (7),
+ **bpftool**\ (8),
+ **bpftool-map**\ (8),
+ **bpftool-prog**\ (8),
+ **bpftool-cgroup**\ (8),
+ **bpftool-feature**\ (8),
+ **bpftool-net**\ (8),
+ **bpftool-perf**\ (8)
diff --git a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst
index 9bb9ace54ba8..ac26876389c2 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst
@@ -29,7 +29,7 @@ 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** |
-| **sendmsg4** | **sendmsg6** }
+| **sendmsg4** | **sendmsg6** | **sysctl** }
| *ATTACH_FLAGS* := { **multi** | **override** }
DESCRIPTION
@@ -85,7 +85,8 @@ DESCRIPTION
**sendmsg4** call to sendto(2), sendmsg(2), sendmmsg(2) for an
unconnected udp4 socket (since 4.18);
**sendmsg6** call to sendto(2), sendmsg(2), sendmmsg(2) for an
- unconnected udp6 socket (since 4.18).
+ unconnected udp6 socket (since 4.18);
+ **sysctl** sysctl access (since 5.2).
**bpftool cgroup detach** *CGROUP* *ATTACH_TYPE* *PROG*
Detach *PROG* from the cgroup *CGROUP* and attach type
@@ -99,7 +100,7 @@ OPTIONS
-h, --help
Print short generic help message (similar to **bpftool help**).
- -v, --version
+ -V, --version
Print version number (similar to **bpftool version**).
-j, --json
@@ -144,4 +145,5 @@ SEE ALSO
**bpftool-map**\ (8),
**bpftool-feature**\ (8),
**bpftool-net**\ (8),
- **bpftool-perf**\ (8)
+ **bpftool-perf**\ (8),
+ **bpftool-btf**\ (8)
diff --git a/tools/bpf/bpftool/Documentation/bpftool-feature.rst b/tools/bpf/bpftool/Documentation/bpftool-feature.rst
index 82de03dd8f52..14180e887082 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-feature.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-feature.rst
@@ -63,7 +63,7 @@ OPTIONS
-h, --help
Print short generic help message (similar to **bpftool help**).
- -v, --version
+ -V, --version
Print version number (similar to **bpftool version**).
-j, --json
@@ -82,4 +82,5 @@ SEE ALSO
**bpftool-map**\ (8),
**bpftool-cgroup**\ (8),
**bpftool-net**\ (8),
- **bpftool-perf**\ (8)
+ **bpftool-perf**\ (8),
+ **bpftool-btf**\ (8)
diff --git a/tools/bpf/bpftool/Documentation/bpftool-map.rst b/tools/bpf/bpftool/Documentation/bpftool-map.rst
index 5c984ffc9f01..13ef27b39f20 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-map.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst
@@ -135,7 +135,7 @@ OPTIONS
-h, --help
Print short generic help message (similar to **bpftool help**).
- -v, --version
+ -V, --version
Print version number (similar to **bpftool version**).
-j, --json
@@ -258,4 +258,5 @@ SEE ALSO
**bpftool-cgroup**\ (8),
**bpftool-feature**\ (8),
**bpftool-net**\ (8),
- **bpftool-perf**\ (8)
+ **bpftool-perf**\ (8),
+ **bpftool-btf**\ (8)
diff --git a/tools/bpf/bpftool/Documentation/bpftool-net.rst b/tools/bpf/bpftool/Documentation/bpftool-net.rst
index 779dab3650ee..934580850f42 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-net.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-net.rst
@@ -55,7 +55,7 @@ OPTIONS
-h, --help
Print short generic help message (similar to **bpftool help**).
- -v, --version
+ -V, --version
Print version number (similar to **bpftool version**).
-j, --json
@@ -143,4 +143,5 @@ SEE ALSO
**bpftool-map**\ (8),
**bpftool-cgroup**\ (8),
**bpftool-feature**\ (8),
- **bpftool-perf**\ (8)
+ **bpftool-perf**\ (8),
+ **bpftool-btf**\ (8)
diff --git a/tools/bpf/bpftool/Documentation/bpftool-perf.rst b/tools/bpf/bpftool/Documentation/bpftool-perf.rst
index bca5590a80d0..0c7576523a21 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-perf.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-perf.rst
@@ -43,7 +43,7 @@ OPTIONS
-h, --help
Print short generic help message (similar to **bpftool help**).
- -v, --version
+ -V, --version
Print version number (similar to **bpftool version**).
-j, --json
@@ -85,4 +85,5 @@ SEE ALSO
**bpftool-map**\ (8),
**bpftool-cgroup**\ (8),
**bpftool-feature**\ (8),
- **bpftool-net**\ (8)
+ **bpftool-net**\ (8),
+ **bpftool-btf**\ (8)
diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
index 9386bd6e0396..e8118544d118 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
@@ -25,7 +25,7 @@ PROG COMMANDS
| **bpftool** **prog dump xlated** *PROG* [{**file** *FILE* | **opcodes** | **visual** | **linum**}]
| **bpftool** **prog dump jited** *PROG* [{**file** *FILE* | **opcodes** | **linum**}]
| **bpftool** **prog pin** *PROG* *FILE*
-| **bpftool** **prog { load | loadall }** *OBJ* *PATH* [**type** *TYPE*] [**map** {**idx** *IDX* | **name** *NAME*} *MAP*] [**dev** *NAME*]
+| **bpftool** **prog { load | loadall }** *OBJ* *PATH* [**type** *TYPE*] [**map** {**idx** *IDX* | **name** *NAME*} *MAP*] [**dev** *NAME*] [**pinmaps** *MAP_DIR*]
| **bpftool** **prog attach** *PROG* *ATTACH_TYPE* [*MAP*]
| **bpftool** **prog detach** *PROG* *ATTACH_TYPE* [*MAP*]
| **bpftool** **prog tracelog**
@@ -39,7 +39,8 @@ PROG COMMANDS
| **cgroup/sock** | **cgroup/dev** | **lwt_in** | **lwt_out** | **lwt_xmit** |
| **lwt_seg6local** | **sockops** | **sk_skb** | **sk_msg** | **lirc_mode2** |
| **cgroup/bind4** | **cgroup/bind6** | **cgroup/post_bind4** | **cgroup/post_bind6** |
-| **cgroup/connect4** | **cgroup/connect6** | **cgroup/sendmsg4** | **cgroup/sendmsg6**
+| **cgroup/connect4** | **cgroup/connect6** | **cgroup/sendmsg4** | **cgroup/sendmsg6** |
+| **cgroup/sysctl**
| }
| *ATTACH_TYPE* := {
| **msg_verdict** | **stream_verdict** | **stream_parser** | **flow_dissector**
@@ -56,6 +57,14 @@ DESCRIPTION
Output will start with program ID followed by program type and
zero or more named attributes (depending on kernel version).
+ Since Linux 5.1 the kernel can collect statistics on BPF
+ programs (such as the total time spent running the program,
+ and the number of times it was run). If available, bpftool
+ shows such statistics. However, the kernel does not collect
+ them by defaults, as it slightly impacts performance on each
+ program run. Activation or deactivation of the feature is
+ performed via the **kernel.bpf_stats_enabled** sysctl knob.
+
**bpftool prog dump xlated** *PROG* [{ **file** *FILE* | **opcodes** | **visual** | **linum** }]
Dump eBPF instructions of the program from the kernel. By
default, eBPF will be disassembled and printed to standard
@@ -144,7 +153,7 @@ OPTIONS
-h, --help
Print short generic help message (similar to **bpftool help**).
- -v, --version
+ -V, --version
Print version number (similar to **bpftool version**).
-j, --json
@@ -262,4 +271,5 @@ SEE ALSO
**bpftool-cgroup**\ (8),
**bpftool-feature**\ (8),
**bpftool-net**\ (8),
- **bpftool-perf**\ (8)
+ **bpftool-perf**\ (8),
+ **bpftool-btf**\ (8)
diff --git a/tools/bpf/bpftool/Documentation/bpftool.rst b/tools/bpf/bpftool/Documentation/bpftool.rst
index 4f2188845dd8..3e562d7fd56f 100644
--- a/tools/bpf/bpftool/Documentation/bpftool.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool.rst
@@ -49,7 +49,7 @@ OPTIONS
-h, --help
Print short help message (similar to **bpftool help**).
- -v, --version
+ -V, --version
Print version number (similar to **bpftool version**).
-j, --json
@@ -76,4 +76,5 @@ SEE ALSO
**bpftool-cgroup**\ (8),
**bpftool-feature**\ (8),
**bpftool-net**\ (8),
- **bpftool-perf**\ (8)
+ **bpftool-perf**\ (8),
+ **bpftool-btf**\ (8)
diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool
index b803827d01e8..50e402a5a9c8 100644
--- a/tools/bpf/bpftool/bash-completion/bpftool
+++ b/tools/bpf/bpftool/bash-completion/bpftool
@@ -217,6 +217,7 @@ _bpftool()
done
cur=${words[cword]}
prev=${words[cword - 1]}
+ pprev=${words[cword - 2]}
local object=${words[1]} command=${words[2]}
@@ -272,17 +273,17 @@ _bpftool()
"$cur" ) )
return 0
;;
- *)
- _bpftool_once_attr 'file'
- if _bpftool_search_list 'xlated'; then
- COMPREPLY+=( $( compgen -W 'opcodes visual linum' -- \
- "$cur" ) )
- else
- COMPREPLY+=( $( compgen -W 'opcodes linum' -- \
- "$cur" ) )
- fi
- return 0
- ;;
+ *)
+ _bpftool_once_attr 'file'
+ if _bpftool_search_list 'xlated'; then
+ COMPREPLY+=( $( compgen -W 'opcodes visual linum' -- \
+ "$cur" ) )
+ else
+ COMPREPLY+=( $( compgen -W 'opcodes linum' -- \
+ "$cur" ) )
+ fi
+ return 0
+ ;;
esac
;;
pin)
@@ -370,7 +371,8 @@ _bpftool()
lirc_mode2 cgroup/bind4 cgroup/bind6 \
cgroup/connect4 cgroup/connect6 \
cgroup/sendmsg4 cgroup/sendmsg6 \
- cgroup/post_bind4 cgroup/post_bind6" -- \
+ cgroup/post_bind4 cgroup/post_bind6 \
+ cgroup/sysctl" -- \
"$cur" ) )
return 0
;;
@@ -606,6 +608,51 @@ _bpftool()
;;
esac
;;
+ btf)
+ local PROG_TYPE='id pinned tag'
+ local MAP_TYPE='id pinned'
+ case $command in
+ dump)
+ case $prev in
+ $command)
+ COMPREPLY+=( $( compgen -W "id map prog file" -- \
+ "$cur" ) )
+ return 0
+ ;;
+ prog)
+ COMPREPLY=( $( compgen -W "$PROG_TYPE" -- "$cur" ) )
+ return 0
+ ;;
+ map)
+ COMPREPLY=( $( compgen -W "$MAP_TYPE" -- "$cur" ) )
+ return 0
+ ;;
+ id)
+ case $pprev in
+ prog)
+ _bpftool_get_prog_ids
+ ;;
+ map)
+ _bpftool_get_map_ids
+ ;;
+ esac
+ return 0
+ ;;
+ *)
+ if [[ $cword == 6 ]] && [[ ${words[3]} == "map" ]]; then
+ COMPREPLY+=( $( compgen -W 'key value kv all' -- \
+ "$cur" ) )
+ fi
+ return 0
+ ;;
+ esac
+ ;;
+ *)
+ [[ $prev == $object ]] && \
+ COMPREPLY=( $( compgen -W 'dump help' -- "$cur" ) )
+ ;;
+ esac
+ ;;
cgroup)
case $command in
show|list)
@@ -619,7 +666,7 @@ _bpftool()
attach|detach)
local ATTACH_TYPES='ingress egress sock_create sock_ops \
device bind4 bind6 post_bind4 post_bind6 connect4 \
- connect6 sendmsg4 sendmsg6'
+ connect6 sendmsg4 sendmsg6 sysctl'
local ATTACH_FLAGS='multi override'
local PROG_TYPE='id pinned tag'
case $prev in
@@ -629,7 +676,7 @@ _bpftool()
;;
ingress|egress|sock_create|sock_ops|device|bind4|bind6|\
post_bind4|post_bind6|connect4|connect6|sendmsg4|\
- sendmsg6)
+ sendmsg6|sysctl)
COMPREPLY=( $( compgen -W "$PROG_TYPE" -- \
"$cur" ) )
return 0
diff --git a/tools/bpf/bpftool/btf.c b/tools/bpf/bpftool/btf.c
new file mode 100644
index 000000000000..58a2cd002a4b
--- /dev/null
+++ b/tools/bpf/bpftool/btf.c
@@ -0,0 +1,586 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+/* Copyright (C) 2019 Facebook */
+
+#include <errno.h>
+#include <fcntl.h>
+#include <linux/err.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <string.h>
+#include <unistd.h>
+#include <gelf.h>
+#include <bpf.h>
+#include <linux/btf.h>
+
+#include "btf.h"
+#include "json_writer.h"
+#include "main.h"
+
+static const char * const btf_kind_str[NR_BTF_KINDS] = {
+ [BTF_KIND_UNKN] = "UNKNOWN",
+ [BTF_KIND_INT] = "INT",
+ [BTF_KIND_PTR] = "PTR",
+ [BTF_KIND_ARRAY] = "ARRAY",
+ [BTF_KIND_STRUCT] = "STRUCT",
+ [BTF_KIND_UNION] = "UNION",
+ [BTF_KIND_ENUM] = "ENUM",
+ [BTF_KIND_FWD] = "FWD",
+ [BTF_KIND_TYPEDEF] = "TYPEDEF",
+ [BTF_KIND_VOLATILE] = "VOLATILE",
+ [BTF_KIND_CONST] = "CONST",
+ [BTF_KIND_RESTRICT] = "RESTRICT",
+ [BTF_KIND_FUNC] = "FUNC",
+ [BTF_KIND_FUNC_PROTO] = "FUNC_PROTO",
+ [BTF_KIND_VAR] = "VAR",
+ [BTF_KIND_DATASEC] = "DATASEC",
+};
+
+static const char *btf_int_enc_str(__u8 encoding)
+{
+ switch (encoding) {
+ case 0:
+ return "(none)";
+ case BTF_INT_SIGNED:
+ return "SIGNED";
+ case BTF_INT_CHAR:
+ return "CHAR";
+ case BTF_INT_BOOL:
+ return "BOOL";
+ default:
+ return "UNKN";
+ }
+}
+
+static const char *btf_var_linkage_str(__u32 linkage)
+{
+ switch (linkage) {
+ case BTF_VAR_STATIC:
+ return "static";
+ case BTF_VAR_GLOBAL_ALLOCATED:
+ return "global-alloc";
+ default:
+ return "(unknown)";
+ }
+}
+
+static const char *btf_str(const struct btf *btf, __u32 off)
+{
+ if (!off)
+ return "(anon)";
+ return btf__name_by_offset(btf, off) ? : "(invalid)";
+}
+
+static int dump_btf_type(const struct btf *btf, __u32 id,
+ const struct btf_type *t)
+{
+ json_writer_t *w = json_wtr;
+ int kind, safe_kind;
+
+ kind = BTF_INFO_KIND(t->info);
+ safe_kind = kind <= BTF_KIND_MAX ? kind : BTF_KIND_UNKN;
+
+ if (json_output) {
+ jsonw_start_object(w);
+ jsonw_uint_field(w, "id", id);
+ jsonw_string_field(w, "kind", btf_kind_str[safe_kind]);
+ jsonw_string_field(w, "name", btf_str(btf, t->name_off));
+ } else {
+ printf("[%u] %s '%s'", id, btf_kind_str[safe_kind],
+ btf_str(btf, t->name_off));
+ }
+
+ switch (BTF_INFO_KIND(t->info)) {
+ case BTF_KIND_INT: {
+ __u32 v = *(__u32 *)(t + 1);
+ const char *enc;
+
+ enc = btf_int_enc_str(BTF_INT_ENCODING(v));
+
+ if (json_output) {
+ jsonw_uint_field(w, "size", t->size);
+ jsonw_uint_field(w, "bits_offset", BTF_INT_OFFSET(v));
+ jsonw_uint_field(w, "nr_bits", BTF_INT_BITS(v));
+ jsonw_string_field(w, "encoding", enc);
+ } else {
+ printf(" size=%u bits_offset=%u nr_bits=%u encoding=%s",
+ t->size, BTF_INT_OFFSET(v), BTF_INT_BITS(v),
+ enc);
+ }
+ break;
+ }
+ case BTF_KIND_PTR:
+ case BTF_KIND_CONST:
+ case BTF_KIND_VOLATILE:
+ case BTF_KIND_RESTRICT:
+ case BTF_KIND_TYPEDEF:
+ if (json_output)
+ jsonw_uint_field(w, "type_id", t->type);
+ else
+ printf(" type_id=%u", t->type);
+ break;
+ case BTF_KIND_ARRAY: {
+ const struct btf_array *arr = (const void *)(t + 1);
+
+ if (json_output) {
+ jsonw_uint_field(w, "type_id", arr->type);
+ jsonw_uint_field(w, "index_type_id", arr->index_type);
+ jsonw_uint_field(w, "nr_elems", arr->nelems);
+ } else {
+ printf(" type_id=%u index_type_id=%u nr_elems=%u",
+ arr->type, arr->index_type, arr->nelems);
+ }
+ break;
+ }
+ case BTF_KIND_STRUCT:
+ case BTF_KIND_UNION: {
+ const struct btf_member *m = (const void *)(t + 1);
+ __u16 vlen = BTF_INFO_VLEN(t->info);
+ int i;
+
+ if (json_output) {
+ jsonw_uint_field(w, "size", t->size);
+ jsonw_uint_field(w, "vlen", vlen);
+ jsonw_name(w, "members");
+ jsonw_start_array(w);
+ } else {
+ printf(" size=%u vlen=%u", t->size, vlen);
+ }
+ for (i = 0; i < vlen; i++, m++) {
+ const char *name = btf_str(btf, m->name_off);
+ __u32 bit_off, bit_sz;
+
+ if (BTF_INFO_KFLAG(t->info)) {
+ bit_off = BTF_MEMBER_BIT_OFFSET(m->offset);
+ bit_sz = BTF_MEMBER_BITFIELD_SIZE(m->offset);
+ } else {
+ bit_off = m->offset;
+ bit_sz = 0;
+ }
+
+ if (json_output) {
+ jsonw_start_object(w);
+ jsonw_string_field(w, "name", name);
+ jsonw_uint_field(w, "type_id", m->type);
+ jsonw_uint_field(w, "bits_offset", bit_off);
+ if (bit_sz) {
+ jsonw_uint_field(w, "bitfield_size",
+ bit_sz);
+ }
+ jsonw_end_object(w);
+ } else {
+ printf("\n\t'%s' type_id=%u bits_offset=%u",
+ name, m->type, bit_off);
+ if (bit_sz)
+ printf(" bitfield_size=%u", bit_sz);
+ }
+ }
+ if (json_output)
+ jsonw_end_array(w);
+ break;
+ }
+ case BTF_KIND_ENUM: {
+ const struct btf_enum *v = (const void *)(t + 1);
+ __u16 vlen = BTF_INFO_VLEN(t->info);
+ int i;
+
+ if (json_output) {
+ jsonw_uint_field(w, "size", t->size);
+ jsonw_uint_field(w, "vlen", vlen);
+ jsonw_name(w, "values");
+ jsonw_start_array(w);
+ } else {
+ printf(" size=%u vlen=%u", t->size, vlen);
+ }
+ for (i = 0; i < vlen; i++, v++) {
+ const char *name = btf_str(btf, v->name_off);
+
+ if (json_output) {
+ jsonw_start_object(w);
+ jsonw_string_field(w, "name", name);
+ jsonw_uint_field(w, "val", v->val);
+ jsonw_end_object(w);
+ } else {
+ printf("\n\t'%s' val=%u", name, v->val);
+ }
+ }
+ if (json_output)
+ jsonw_end_array(w);
+ break;
+ }
+ case BTF_KIND_FWD: {
+ const char *fwd_kind = BTF_INFO_KIND(t->info) ? "union"
+ : "struct";
+
+ if (json_output)
+ jsonw_string_field(w, "fwd_kind", fwd_kind);
+ else
+ printf(" fwd_kind=%s", fwd_kind);
+ break;
+ }
+ case BTF_KIND_FUNC:
+ if (json_output)
+ jsonw_uint_field(w, "type_id", t->type);
+ else
+ printf(" type_id=%u", t->type);
+ break;
+ case BTF_KIND_FUNC_PROTO: {
+ const struct btf_param *p = (const void *)(t + 1);
+ __u16 vlen = BTF_INFO_VLEN(t->info);
+ int i;
+
+ if (json_output) {
+ jsonw_uint_field(w, "ret_type_id", t->type);
+ jsonw_uint_field(w, "vlen", vlen);
+ jsonw_name(w, "params");
+ jsonw_start_array(w);
+ } else {
+ printf(" ret_type_id=%u vlen=%u", t->type, vlen);
+ }
+ for (i = 0; i < vlen; i++, p++) {
+ const char *name = btf_str(btf, p->name_off);
+
+ if (json_output) {
+ jsonw_start_object(w);
+ jsonw_string_field(w, "name", name);
+ jsonw_uint_field(w, "type_id", p->type);
+ jsonw_end_object(w);
+ } else {
+ printf("\n\t'%s' type_id=%u", name, p->type);
+ }
+ }
+ if (json_output)
+ jsonw_end_array(w);
+ break;
+ }
+ case BTF_KIND_VAR: {
+ const struct btf_var *v = (const void *)(t + 1);
+ const char *linkage;
+
+ linkage = btf_var_linkage_str(v->linkage);
+
+ if (json_output) {
+ jsonw_uint_field(w, "type_id", t->type);
+ jsonw_string_field(w, "linkage", linkage);
+ } else {
+ printf(" type_id=%u, linkage=%s", t->type, linkage);
+ }
+ break;
+ }
+ case BTF_KIND_DATASEC: {
+ const struct btf_var_secinfo *v = (const void *)(t+1);
+ __u16 vlen = BTF_INFO_VLEN(t->info);
+ int i;
+
+ if (json_output) {
+ jsonw_uint_field(w, "size", t->size);
+ jsonw_uint_field(w, "vlen", vlen);
+ jsonw_name(w, "vars");
+ jsonw_start_array(w);
+ } else {
+ printf(" size=%u vlen=%u", t->size, vlen);
+ }
+ for (i = 0; i < vlen; i++, v++) {
+ if (json_output) {
+ jsonw_start_object(w);
+ jsonw_uint_field(w, "type_id", v->type);
+ jsonw_uint_field(w, "offset", v->offset);
+ jsonw_uint_field(w, "size", v->size);
+ jsonw_end_object(w);
+ } else {
+ printf("\n\ttype_id=%u offset=%u size=%u",
+ v->type, v->offset, v->size);
+ }
+ }
+ if (json_output)
+ jsonw_end_array(w);
+ break;
+ }
+ default:
+ break;
+ }
+
+ if (json_output)
+ jsonw_end_object(json_wtr);
+ else
+ printf("\n");
+
+ return 0;
+}
+
+static int dump_btf_raw(const struct btf *btf,
+ __u32 *root_type_ids, int root_type_cnt)
+{
+ const struct btf_type *t;
+ int i;
+
+ if (json_output) {
+ jsonw_start_object(json_wtr);
+ jsonw_name(json_wtr, "types");
+ jsonw_start_array(json_wtr);
+ }
+
+ if (root_type_cnt) {
+ for (i = 0; i < root_type_cnt; i++) {
+ t = btf__type_by_id(btf, root_type_ids[i]);
+ dump_btf_type(btf, root_type_ids[i], t);
+ }
+ } else {
+ int cnt = btf__get_nr_types(btf);
+
+ for (i = 1; i <= cnt; i++) {
+ t = btf__type_by_id(btf, i);
+ dump_btf_type(btf, i, t);
+ }
+ }
+
+ if (json_output) {
+ jsonw_end_array(json_wtr);
+ jsonw_end_object(json_wtr);
+ }
+ return 0;
+}
+
+static bool check_btf_endianness(GElf_Ehdr *ehdr)
+{
+ static unsigned int const endian = 1;
+
+ switch (ehdr->e_ident[EI_DATA]) {
+ case ELFDATA2LSB:
+ return *(unsigned char const *)&endian == 1;
+ case ELFDATA2MSB:
+ return *(unsigned char const *)&endian == 0;
+ default:
+ return 0;
+ }
+}
+
+static int btf_load_from_elf(const char *path, struct btf **btf)
+{
+ int err = -1, fd = -1, idx = 0;
+ Elf_Data *btf_data = NULL;
+ Elf_Scn *scn = NULL;
+ Elf *elf = NULL;
+ GElf_Ehdr ehdr;
+
+ if (elf_version(EV_CURRENT) == EV_NONE) {
+ p_err("failed to init libelf for %s", path);
+ return -1;
+ }
+
+ fd = open(path, O_RDONLY);
+ if (fd < 0) {
+ p_err("failed to open %s: %s", path, strerror(errno));
+ return -1;
+ }
+
+ elf = elf_begin(fd, ELF_C_READ, NULL);
+ if (!elf) {
+ p_err("failed to open %s as ELF file", path);
+ goto done;
+ }
+ if (!gelf_getehdr(elf, &ehdr)) {
+ p_err("failed to get EHDR from %s", path);
+ goto done;
+ }
+ if (!check_btf_endianness(&ehdr)) {
+ p_err("non-native ELF endianness is not supported");
+ goto done;
+ }
+ if (!elf_rawdata(elf_getscn(elf, ehdr.e_shstrndx), NULL)) {
+ p_err("failed to get e_shstrndx from %s\n", path);
+ goto done;
+ }
+
+ while ((scn = elf_nextscn(elf, scn)) != NULL) {
+ GElf_Shdr sh;
+ char *name;
+
+ idx++;
+ if (gelf_getshdr(scn, &sh) != &sh) {
+ p_err("failed to get section(%d) header from %s",
+ idx, path);
+ goto done;
+ }
+ name = elf_strptr(elf, ehdr.e_shstrndx, sh.sh_name);
+ if (!name) {
+ p_err("failed to get section(%d) name from %s",
+ idx, path);
+ goto done;
+ }
+ if (strcmp(name, BTF_ELF_SEC) == 0) {
+ btf_data = elf_getdata(scn, 0);
+ if (!btf_data) {
+ p_err("failed to get section(%d, %s) data from %s",
+ idx, name, path);
+ goto done;
+ }
+ break;
+ }
+ }
+
+ if (!btf_data) {
+ p_err("%s ELF section not found in %s", BTF_ELF_SEC, path);
+ goto done;
+ }
+
+ *btf = btf__new(btf_data->d_buf, btf_data->d_size);
+ if (IS_ERR(*btf)) {
+ err = PTR_ERR(*btf);
+ *btf = NULL;
+ p_err("failed to load BTF data from %s: %s",
+ path, strerror(err));
+ goto done;
+ }
+
+ err = 0;
+done:
+ if (err) {
+ if (*btf) {
+ btf__free(*btf);
+ *btf = NULL;
+ }
+ }
+ if (elf)
+ elf_end(elf);
+ close(fd);
+ return err;
+}
+
+static int do_dump(int argc, char **argv)
+{
+ struct btf *btf = NULL;
+ __u32 root_type_ids[2];
+ int root_type_cnt = 0;
+ __u32 btf_id = -1;
+ const char *src;
+ int fd = -1;
+ int err;
+
+ if (!REQ_ARGS(2)) {
+ usage();
+ return -1;
+ }
+ src = GET_ARG();
+
+ if (is_prefix(src, "map")) {
+ struct bpf_map_info info = {};
+ __u32 len = sizeof(info);
+
+ if (!REQ_ARGS(2)) {
+ usage();
+ return -1;
+ }
+
+ fd = map_parse_fd_and_info(&argc, &argv, &info, &len);
+ if (fd < 0)
+ return -1;
+
+ btf_id = info.btf_id;
+ if (argc && is_prefix(*argv, "key")) {
+ root_type_ids[root_type_cnt++] = info.btf_key_type_id;
+ NEXT_ARG();
+ } else if (argc && is_prefix(*argv, "value")) {
+ root_type_ids[root_type_cnt++] = info.btf_value_type_id;
+ NEXT_ARG();
+ } else if (argc && is_prefix(*argv, "all")) {
+ NEXT_ARG();
+ } else if (argc && is_prefix(*argv, "kv")) {
+ root_type_ids[root_type_cnt++] = info.btf_key_type_id;
+ root_type_ids[root_type_cnt++] = info.btf_value_type_id;
+ NEXT_ARG();
+ } else {
+ root_type_ids[root_type_cnt++] = info.btf_key_type_id;
+ root_type_ids[root_type_cnt++] = info.btf_value_type_id;
+ }
+ } else if (is_prefix(src, "prog")) {
+ struct bpf_prog_info info = {};
+ __u32 len = sizeof(info);
+
+ if (!REQ_ARGS(2)) {
+ usage();
+ return -1;
+ }
+
+ fd = prog_parse_fd(&argc, &argv);
+ if (fd < 0)
+ return -1;
+
+ err = bpf_obj_get_info_by_fd(fd, &info, &len);
+ if (err) {
+ p_err("can't get prog info: %s", strerror(errno));
+ goto done;
+ }
+
+ btf_id = info.btf_id;
+ } else if (is_prefix(src, "id")) {
+ char *endptr;
+
+ btf_id = strtoul(*argv, &endptr, 0);
+ if (*endptr) {
+ p_err("can't parse %s as ID", **argv);
+ return -1;
+ }
+ NEXT_ARG();
+ } else if (is_prefix(src, "file")) {
+ err = btf_load_from_elf(*argv, &btf);
+ if (err)
+ goto done;
+ NEXT_ARG();
+ } else {
+ err = -1;
+ p_err("unrecognized BTF source specifier: '%s'", src);
+ goto done;
+ }
+
+ if (!btf) {
+ err = btf__get_from_id(btf_id, &btf);
+ if (err) {
+ p_err("get btf by id (%u): %s", btf_id, strerror(err));
+ goto done;
+ }
+ if (!btf) {
+ err = ENOENT;
+ p_err("can't find btf with ID (%u)", btf_id);
+ goto done;
+ }
+ }
+
+ dump_btf_raw(btf, root_type_ids, root_type_cnt);
+
+done:
+ close(fd);
+ btf__free(btf);
+ return err;
+}
+
+static int do_help(int argc, char **argv)
+{
+ if (json_output) {
+ jsonw_null(json_wtr);
+ return 0;
+ }
+
+ fprintf(stderr,
+ "Usage: %s btf dump BTF_SRC\n"
+ " %s btf help\n"
+ "\n"
+ " BTF_SRC := { id BTF_ID | prog PROG | map MAP [{key | value | kv | all}] | file FILE }\n"
+ " " HELP_SPEC_MAP "\n"
+ " " HELP_SPEC_PROGRAM "\n"
+ " " HELP_SPEC_OPTIONS "\n"
+ "",
+ bin_name, bin_name);
+
+ return 0;
+}
+
+static const struct cmd cmds[] = {
+ { "help", do_help },
+ { "dump", do_dump },
+ { 0 }
+};
+
+int do_btf(int argc, char **argv)
+{
+ return cmd_select(cmds, argc, argv, do_help);
+}
diff --git a/tools/bpf/bpftool/btf_dumper.c b/tools/bpf/bpftool/btf_dumper.c
index e63bce0755eb..8cafb9b31467 100644
--- a/tools/bpf/bpftool/btf_dumper.c
+++ b/tools/bpf/bpftool/btf_dumper.c
@@ -309,6 +309,48 @@ static int btf_dumper_struct(const struct btf_dumper *d, __u32 type_id,
return ret;
}
+static int btf_dumper_var(const struct btf_dumper *d, __u32 type_id,
+ __u8 bit_offset, const void *data)
+{
+ const struct btf_type *t = btf__type_by_id(d->btf, type_id);
+ int ret;
+
+ jsonw_start_object(d->jw);
+ jsonw_name(d->jw, btf__name_by_offset(d->btf, t->name_off));
+ ret = btf_dumper_do_type(d, t->type, bit_offset, data);
+ jsonw_end_object(d->jw);
+
+ return ret;
+}
+
+static int btf_dumper_datasec(const struct btf_dumper *d, __u32 type_id,
+ const void *data)
+{
+ struct btf_var_secinfo *vsi;
+ const struct btf_type *t;
+ int ret = 0, i, vlen;
+
+ t = btf__type_by_id(d->btf, type_id);
+ if (!t)
+ return -EINVAL;
+
+ vlen = BTF_INFO_VLEN(t->info);
+ vsi = (struct btf_var_secinfo *)(t + 1);
+
+ jsonw_start_object(d->jw);
+ jsonw_name(d->jw, btf__name_by_offset(d->btf, t->name_off));
+ jsonw_start_array(d->jw);
+ for (i = 0; i < vlen; i++) {
+ ret = btf_dumper_do_type(d, vsi[i].type, 0, data + vsi[i].offset);
+ if (ret)
+ break;
+ }
+ jsonw_end_array(d->jw);
+ jsonw_end_object(d->jw);
+
+ return ret;
+}
+
static int btf_dumper_do_type(const struct btf_dumper *d, __u32 type_id,
__u8 bit_offset, const void *data)
{
@@ -341,6 +383,10 @@ static int btf_dumper_do_type(const struct btf_dumper *d, __u32 type_id,
case BTF_KIND_CONST:
case BTF_KIND_RESTRICT:
return btf_dumper_modifier(d, type_id, bit_offset, data);
+ case BTF_KIND_VAR:
+ return btf_dumper_var(d, type_id, bit_offset, data);
+ case BTF_KIND_DATASEC:
+ return btf_dumper_datasec(d, type_id, data);
default:
jsonw_printf(d->jw, "(unsupported-kind");
return -EINVAL;
@@ -377,6 +423,7 @@ static int __btf_dumper_type_only(const struct btf *btf, __u32 type_id,
{
const struct btf_type *proto_type;
const struct btf_array *array;
+ const struct btf_var *var;
const struct btf_type *t;
if (!type_id) {
@@ -440,6 +487,18 @@ static int __btf_dumper_type_only(const struct btf *btf, __u32 type_id,
if (pos == -1)
return -1;
break;
+ case BTF_KIND_VAR:
+ var = (struct btf_var *)(t + 1);
+ if (var->linkage == BTF_VAR_STATIC)
+ BTF_PRINT_ARG("static ");
+ BTF_PRINT_TYPE(t->type);
+ BTF_PRINT_ARG(" %s",
+ btf__name_by_offset(btf, t->name_off));
+ break;
+ case BTF_KIND_DATASEC:
+ BTF_PRINT_ARG("section (\"%s\") ",
+ btf__name_by_offset(btf, t->name_off));
+ break;
case BTF_KIND_UNKN:
default:
return -1;
diff --git a/tools/bpf/bpftool/cgroup.c b/tools/bpf/bpftool/cgroup.c
index 4b5c8da2a7c0..7e22f115c8c1 100644
--- a/tools/bpf/bpftool/cgroup.c
+++ b/tools/bpf/bpftool/cgroup.c
@@ -25,7 +25,7 @@
" ATTACH_TYPE := { ingress | egress | sock_create |\n" \
" sock_ops | device | bind4 | bind6 |\n" \
" post_bind4 | post_bind6 | connect4 |\n" \
- " connect6 | sendmsg4 | sendmsg6 }"
+ " connect6 | sendmsg4 | sendmsg6 | sysctl }"
static const char * const attach_type_strings[] = {
[BPF_CGROUP_INET_INGRESS] = "ingress",
@@ -41,6 +41,7 @@ static const char * const attach_type_strings[] = {
[BPF_CGROUP_INET6_POST_BIND] = "post_bind6",
[BPF_CGROUP_UDP4_SENDMSG] = "sendmsg4",
[BPF_CGROUP_UDP6_SENDMSG] = "sendmsg6",
+ [BPF_CGROUP_SYSCTL] = "sysctl",
[__MAX_BPF_ATTACH_TYPE] = NULL,
};
@@ -248,6 +249,13 @@ static int do_show_tree_fn(const char *fpath, const struct stat *sb,
for (type = 0; type < __MAX_BPF_ATTACH_TYPE; type++)
show_attached_bpf_progs(cgroup_fd, type, ftw->level);
+ if (errno == EINVAL)
+ /* Last attach type does not support query.
+ * Do not report an error for this, especially because batch
+ * mode would stop processing commands.
+ */
+ errno = 0;
+
if (json_output) {
jsonw_end_array(json_wtr);
jsonw_end_object(json_wtr);
diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c
index a9d5e9e6a732..1ac1fc520e6a 100644
--- a/tools/bpf/bpftool/main.c
+++ b/tools/bpf/bpftool/main.c
@@ -56,7 +56,7 @@ static int do_help(int argc, char **argv)
" %s batch file FILE\n"
" %s version\n"
"\n"
- " OBJECT := { prog | map | cgroup | perf | net | feature }\n"
+ " OBJECT := { prog | map | cgroup | perf | net | feature | btf }\n"
" " HELP_SPEC_OPTIONS "\n"
"",
bin_name, bin_name, bin_name);
@@ -188,6 +188,7 @@ static const struct cmd cmds[] = {
{ "perf", do_perf },
{ "net", do_net },
{ "feature", do_feature },
+ { "btf", do_btf },
{ "version", do_version },
{ 0 }
};
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index d7dd84d3c660..3d63feb7f852 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -73,6 +73,7 @@ static const char * const prog_type_name[] = {
[BPF_PROG_TYPE_LIRC_MODE2] = "lirc_mode2",
[BPF_PROG_TYPE_SK_REUSEPORT] = "sk_reuseport",
[BPF_PROG_TYPE_FLOW_DISSECTOR] = "flow_dissector",
+ [BPF_PROG_TYPE_CGROUP_SYSCTL] = "cgroup_sysctl",
};
extern const char * const map_type_name[];
@@ -149,6 +150,7 @@ int do_perf(int argc, char **arg);
int do_net(int argc, char **arg);
int do_tracelog(int argc, char **arg);
int do_feature(int argc, char **argv);
+int do_btf(int argc, char **argv);
int parse_u32_arg(int *argc, char ***argv, __u32 *val, const char *what);
int prog_parse_fd(int *argc, char ***argv);
diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index e0c650d91784..3ec82904ccec 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -46,6 +46,7 @@ const char * const map_type_name[] = {
[BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE] = "percpu_cgroup_storage",
[BPF_MAP_TYPE_QUEUE] = "queue",
[BPF_MAP_TYPE_STACK] = "stack",
+ [BPF_MAP_TYPE_SK_STORAGE] = "sk_storage",
};
const size_t map_type_name_size = ARRAY_SIZE(map_type_name);
@@ -153,11 +154,13 @@ static int do_dump_btf(const struct btf_dumper *d,
/* start of key-value pair */
jsonw_start_object(d->jw);
- jsonw_name(d->jw, "key");
+ if (map_info->btf_key_type_id) {
+ jsonw_name(d->jw, "key");
- ret = btf_dumper_type(d, map_info->btf_key_type_id, key);
- if (ret)
- goto err_end_obj;
+ ret = btf_dumper_type(d, map_info->btf_key_type_id, key);
+ if (ret)
+ goto err_end_obj;
+ }
if (!map_is_per_cpu(map_info->type)) {
jsonw_name(d->jw, "value");
@@ -259,20 +262,20 @@ static void print_entry_json(struct bpf_map_info *info, unsigned char *key,
}
static void print_entry_error(struct bpf_map_info *info, unsigned char *key,
- const char *value)
+ const char *error_msg)
{
- int value_size = strlen(value);
+ int msg_size = strlen(error_msg);
bool single_line, break_names;
- break_names = info->key_size > 16 || value_size > 16;
- single_line = info->key_size + value_size <= 24 && !break_names;
+ break_names = info->key_size > 16 || msg_size > 16;
+ single_line = info->key_size + msg_size <= 24 && !break_names;
printf("key:%c", break_names ? '\n' : ' ');
fprint_hex(stdout, key, info->key_size, " ");
printf(single_line ? " " : "\n");
- printf("value:%c%s", break_names ? '\n' : ' ', value);
+ printf("value:%c%s", break_names ? '\n' : ' ', error_msg);
printf("\n");
}
@@ -296,11 +299,7 @@ static void print_entry_plain(struct bpf_map_info *info, unsigned char *key,
if (info->value_size) {
printf("value:%c", break_names ? '\n' : ' ');
- if (value)
- fprint_hex(stdout, value, info->value_size,
- " ");
- else
- printf("<no entry>");
+ fprint_hex(stdout, value, info->value_size, " ");
}
printf("\n");
@@ -319,11 +318,8 @@ static void print_entry_plain(struct bpf_map_info *info, unsigned char *key,
for (i = 0; i < n; i++) {
printf("value (CPU %02d):%c",
i, info->value_size > 16 ? '\n' : ' ');
- if (value)
- fprint_hex(stdout, value + i * step,
- info->value_size, " ");
- else
- printf("<no entry>");
+ fprint_hex(stdout, value + i * step,
+ info->value_size, " ");
printf("\n");
}
}
@@ -536,6 +532,9 @@ static int show_map_close_json(int fd, struct bpf_map_info *info)
}
close(fd);
+ if (info->btf_id)
+ jsonw_int_field(json_wtr, "btf_id", info->btf_id);
+
if (!hash_empty(map_table.table)) {
struct pinned_obj *obj;
@@ -602,15 +601,19 @@ static int show_map_close_plain(int fd, struct bpf_map_info *info)
}
close(fd);
- printf("\n");
if (!hash_empty(map_table.table)) {
struct pinned_obj *obj;
hash_for_each_possible(map_table.table, obj, hash, info->id) {
if (obj->id == info->id)
- printf("\tpinned %s\n", obj->path);
+ printf("\n\tpinned %s", obj->path);
}
}
+
+ if (info->btf_id)
+ printf("\n\tbtf_id %d", info->btf_id);
+
+ printf("\n");
return 0;
}
@@ -720,11 +723,16 @@ static int dump_map_elem(int fd, void *key, void *value,
jsonw_string_field(json_wtr, "error", strerror(lookup_errno));
jsonw_end_object(json_wtr);
} else {
- if (errno == ENOENT)
- print_entry_plain(map_info, key, NULL);
- else
- print_entry_error(map_info, key,
- strerror(lookup_errno));
+ const char *msg = NULL;
+
+ if (lookup_errno == ENOENT)
+ msg = "<no entry>";
+ else if (lookup_errno == ENOSPC &&
+ map_info->type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY)
+ msg = "<cannot read>";
+
+ print_entry_error(map_info, key,
+ msg ? : strerror(lookup_errno));
}
return 0;
@@ -778,6 +786,10 @@ static int do_dump(int argc, char **argv)
}
}
+ if (info.type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY &&
+ info.value_size != 8)
+ p_info("Warning: cannot read values from %s map with value_size != 8",
+ map_type_name[info.type]);
while (true) {
err = bpf_map_get_next_key(fd, prev_key, key);
if (err) {
@@ -1151,6 +1163,9 @@ static int do_create(int argc, char **argv)
return -1;
}
NEXT_ARG();
+ } else {
+ p_err("unknown arg %s", *argv);
+ return -1;
}
}
diff --git a/tools/bpf/bpftool/net.c b/tools/bpf/bpftool/net.c
index db0e7de49d49..67e99c56bc88 100644
--- a/tools/bpf/bpftool/net.c
+++ b/tools/bpf/bpftool/net.c
@@ -3,6 +3,7 @@
#define _GNU_SOURCE
#include <errno.h>
+#include <fcntl.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
@@ -12,6 +13,8 @@
#include <linux/rtnetlink.h>
#include <linux/tc_act/tc_bpf.h>
#include <sys/socket.h>
+#include <sys/stat.h>
+#include <sys/types.h>
#include <bpf.h>
#include <nlattr.h>
@@ -48,6 +51,10 @@ struct bpf_filter_t {
int ifindex;
};
+struct bpf_attach_info {
+ __u32 flow_dissector_id;
+};
+
static int dump_link_nlmsg(void *cookie, void *msg, struct nlattr **tb)
{
struct bpf_netdev_t *netinfo = cookie;
@@ -180,8 +187,45 @@ out:
return 0;
}
+static int query_flow_dissector(struct bpf_attach_info *attach_info)
+{
+ __u32 attach_flags;
+ __u32 prog_ids[1];
+ __u32 prog_cnt;
+ int err;
+ int fd;
+
+ fd = open("/proc/self/ns/net", O_RDONLY);
+ if (fd < 0) {
+ p_err("can't open /proc/self/ns/net: %d",
+ strerror(errno));
+ return -1;
+ }
+ prog_cnt = ARRAY_SIZE(prog_ids);
+ err = bpf_prog_query(fd, BPF_FLOW_DISSECTOR, 0,
+ &attach_flags, prog_ids, &prog_cnt);
+ close(fd);
+ if (err) {
+ if (errno == EINVAL) {
+ /* Older kernel's don't support querying
+ * flow dissector programs.
+ */
+ errno = 0;
+ return 0;
+ }
+ p_err("can't query prog: %s", strerror(errno));
+ return -1;
+ }
+
+ if (prog_cnt == 1)
+ attach_info->flow_dissector_id = prog_ids[0];
+
+ return 0;
+}
+
static int do_show(int argc, char **argv)
{
+ struct bpf_attach_info attach_info = {};
int i, sock, ret, filter_idx = -1;
struct bpf_netdev_t dev_array;
unsigned int nl_pid;
@@ -199,6 +243,10 @@ static int do_show(int argc, char **argv)
usage();
}
+ ret = query_flow_dissector(&attach_info);
+ if (ret)
+ return -1;
+
sock = libbpf_netlink_open(&nl_pid);
if (sock < 0) {
fprintf(stderr, "failed to open netlink sock\n");
@@ -227,6 +275,12 @@ static int do_show(int argc, char **argv)
}
NET_END_ARRAY("\n");
}
+
+ NET_START_ARRAY("flow_dissector", "%s:\n");
+ if (attach_info.flow_dissector_id > 0)
+ NET_DUMP_UINT("id", "id %u", attach_info.flow_dissector_id);
+ NET_END_ARRAY("\n");
+
NET_END_OBJECT;
if (json_output)
jsonw_end_array(json_wtr);
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 8ef80d65a474..fc495b27f0fc 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -249,6 +249,9 @@ static void print_prog_json(struct bpf_prog_info *info, int fd)
if (info->nr_map_ids)
show_prog_maps(fd, info->nr_map_ids);
+ if (info->btf_id)
+ jsonw_int_field(json_wtr, "btf_id", info->btf_id);
+
if (!hash_empty(prog_table.table)) {
struct pinned_obj *obj;
@@ -319,6 +322,9 @@ static void print_prog_plain(struct bpf_prog_info *info, int fd)
}
}
+ if (info->btf_id)
+ printf("\n\tbtf_id %d", info->btf_id);
+
printf("\n");
}
@@ -401,41 +407,31 @@ static int do_show(int argc, char **argv)
static int do_dump(int argc, char **argv)
{
- unsigned int finfo_rec_size, linfo_rec_size, jited_linfo_rec_size;
- void *func_info = NULL, *linfo = NULL, *jited_linfo = NULL;
- unsigned int nr_finfo, nr_linfo = 0, nr_jited_linfo = 0;
+ struct bpf_prog_info_linear *info_linear;
struct bpf_prog_linfo *prog_linfo = NULL;
- unsigned long *func_ksyms = NULL;
- struct bpf_prog_info info = {};
- unsigned int *func_lens = NULL;
+ enum {DUMP_JITED, DUMP_XLATED} mode;
const char *disasm_opt = NULL;
- unsigned int nr_func_ksyms;
- unsigned int nr_func_lens;
+ struct bpf_prog_info *info;
struct dump_data dd = {};
- __u32 len = sizeof(info);
+ void *func_info = NULL;
struct btf *btf = NULL;
- unsigned int buf_size;
char *filepath = NULL;
bool opcodes = false;
bool visual = false;
char func_sig[1024];
unsigned char *buf;
bool linum = false;
- __u32 *member_len;
- __u64 *member_ptr;
+ __u32 member_len;
+ __u64 arrays;
ssize_t n;
- int err;
int fd;
if (is_prefix(*argv, "jited")) {
if (disasm_init())
return -1;
-
- member_len = &info.jited_prog_len;
- member_ptr = &info.jited_prog_insns;
+ mode = DUMP_JITED;
} else if (is_prefix(*argv, "xlated")) {
- member_len = &info.xlated_prog_len;
- member_ptr = &info.xlated_prog_insns;
+ mode = DUMP_XLATED;
} else {
p_err("expected 'xlated' or 'jited', got: %s", *argv);
return -1;
@@ -474,175 +470,50 @@ static int do_dump(int argc, char **argv)
return -1;
}
- err = bpf_obj_get_info_by_fd(fd, &info, &len);
- if (err) {
- p_err("can't get prog info: %s", strerror(errno));
- return -1;
- }
-
- if (!*member_len) {
- p_info("no instructions returned");
- close(fd);
- return 0;
- }
+ if (mode == DUMP_JITED)
+ arrays = 1UL << BPF_PROG_INFO_JITED_INSNS;
+ else
+ arrays = 1UL << BPF_PROG_INFO_XLATED_INSNS;
- buf_size = *member_len;
+ 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;
- buf = malloc(buf_size);
- if (!buf) {
- p_err("mem alloc failed");
- close(fd);
+ info_linear = bpf_program__get_prog_info_linear(fd, arrays);
+ close(fd);
+ if (IS_ERR_OR_NULL(info_linear)) {
+ p_err("can't get prog info: %s", strerror(errno));
return -1;
}
- nr_func_ksyms = info.nr_jited_ksyms;
- if (nr_func_ksyms) {
- func_ksyms = malloc(nr_func_ksyms * sizeof(__u64));
- if (!func_ksyms) {
- p_err("mem alloc failed");
- close(fd);
+ info = &info_linear->info;
+ if (mode == DUMP_JITED) {
+ if (info->jited_prog_len == 0) {
+ p_info("no instructions returned");
goto err_free;
}
- }
-
- nr_func_lens = info.nr_jited_func_lens;
- if (nr_func_lens) {
- func_lens = malloc(nr_func_lens * sizeof(__u32));
- if (!func_lens) {
- p_err("mem alloc failed");
- close(fd);
- goto err_free;
- }
- }
-
- nr_finfo = info.nr_func_info;
- finfo_rec_size = info.func_info_rec_size;
- if (nr_finfo && finfo_rec_size) {
- func_info = malloc(nr_finfo * finfo_rec_size);
- if (!func_info) {
- p_err("mem alloc failed");
- close(fd);
+ buf = (unsigned char *)(info->jited_prog_insns);
+ member_len = info->jited_prog_len;
+ } else { /* DUMP_XLATED */
+ if (info->xlated_prog_len == 0) {
+ p_err("error retrieving insn dump: kernel.kptr_restrict set?");
goto err_free;
}
+ buf = (unsigned char *)info->xlated_prog_insns;
+ member_len = info->xlated_prog_len;
}
- linfo_rec_size = info.line_info_rec_size;
- if (info.nr_line_info && linfo_rec_size && info.btf_id) {
- nr_linfo = info.nr_line_info;
- linfo = malloc(nr_linfo * linfo_rec_size);
- if (!linfo) {
- p_err("mem alloc failed");
- close(fd);
- goto err_free;
- }
- }
-
- jited_linfo_rec_size = info.jited_line_info_rec_size;
- if (info.nr_jited_line_info &&
- jited_linfo_rec_size &&
- info.nr_jited_ksyms &&
- info.nr_jited_func_lens &&
- info.btf_id) {
- nr_jited_linfo = info.nr_jited_line_info;
- jited_linfo = malloc(nr_jited_linfo * jited_linfo_rec_size);
- if (!jited_linfo) {
- p_err("mem alloc failed");
- close(fd);
- goto err_free;
- }
- }
-
- memset(&info, 0, sizeof(info));
-
- *member_ptr = ptr_to_u64(buf);
- *member_len = buf_size;
- info.jited_ksyms = ptr_to_u64(func_ksyms);
- info.nr_jited_ksyms = nr_func_ksyms;
- info.jited_func_lens = ptr_to_u64(func_lens);
- info.nr_jited_func_lens = nr_func_lens;
- info.nr_func_info = nr_finfo;
- info.func_info_rec_size = finfo_rec_size;
- info.func_info = ptr_to_u64(func_info);
- info.nr_line_info = nr_linfo;
- info.line_info_rec_size = linfo_rec_size;
- info.line_info = ptr_to_u64(linfo);
- info.nr_jited_line_info = nr_jited_linfo;
- info.jited_line_info_rec_size = jited_linfo_rec_size;
- info.jited_line_info = ptr_to_u64(jited_linfo);
-
- err = bpf_obj_get_info_by_fd(fd, &info, &len);
- close(fd);
- if (err) {
- p_err("can't get prog info: %s", strerror(errno));
- goto err_free;
- }
-
- if (*member_len > buf_size) {
- p_err("too many instructions returned");
- goto err_free;
- }
-
- if (info.nr_jited_ksyms > nr_func_ksyms) {
- p_err("too many addresses returned");
- goto err_free;
- }
-
- if (info.nr_jited_func_lens > nr_func_lens) {
- p_err("too many values returned");
- goto err_free;
- }
-
- if (info.nr_func_info != nr_finfo) {
- p_err("incorrect nr_func_info %d vs. expected %d",
- info.nr_func_info, nr_finfo);
- goto err_free;
- }
-
- if (info.func_info_rec_size != finfo_rec_size) {
- p_err("incorrect func_info_rec_size %d vs. expected %d",
- info.func_info_rec_size, finfo_rec_size);
- goto err_free;
- }
-
- if (linfo && info.nr_line_info != nr_linfo) {
- p_err("incorrect nr_line_info %u vs. expected %u",
- info.nr_line_info, nr_linfo);
- goto err_free;
- }
-
- if (info.line_info_rec_size != linfo_rec_size) {
- p_err("incorrect line_info_rec_size %u vs. expected %u",
- info.line_info_rec_size, linfo_rec_size);
- goto err_free;
- }
-
- if (jited_linfo && info.nr_jited_line_info != nr_jited_linfo) {
- p_err("incorrect nr_jited_line_info %u vs. expected %u",
- info.nr_jited_line_info, nr_jited_linfo);
- goto err_free;
- }
-
- if (info.jited_line_info_rec_size != jited_linfo_rec_size) {
- p_err("incorrect jited_line_info_rec_size %u vs. expected %u",
- info.jited_line_info_rec_size, jited_linfo_rec_size);
- goto err_free;
- }
-
- if ((member_len == &info.jited_prog_len &&
- info.jited_prog_insns == 0) ||
- (member_len == &info.xlated_prog_len &&
- info.xlated_prog_insns == 0)) {
- p_err("error retrieving insn dump: kernel.kptr_restrict set?");
- goto err_free;
- }
-
- if (info.btf_id && btf__get_from_id(info.btf_id, &btf)) {
+ if (info->btf_id && btf__get_from_id(info->btf_id, &btf)) {
p_err("failed to get btf");
goto err_free;
}
- if (nr_linfo) {
- prog_linfo = bpf_prog_linfo__new(&info);
+ func_info = (void *)info->func_info;
+
+ if (info->nr_line_info) {
+ prog_linfo = bpf_prog_linfo__new(info);
if (!prog_linfo)
p_info("error in processing bpf_line_info. continue without it.");
}
@@ -655,9 +526,9 @@ static int do_dump(int argc, char **argv)
goto err_free;
}
- n = write(fd, buf, *member_len);
+ n = write(fd, buf, member_len);
close(fd);
- if (n != *member_len) {
+ if (n != member_len) {
p_err("error writing output file: %s",
n < 0 ? strerror(errno) : "short write");
goto err_free;
@@ -665,19 +536,19 @@ static int do_dump(int argc, char **argv)
if (json_output)
jsonw_null(json_wtr);
- } else if (member_len == &info.jited_prog_len) {
+ } else if (mode == DUMP_JITED) {
const char *name = NULL;
- if (info.ifindex) {
- name = ifindex_to_bfd_params(info.ifindex,
- info.netns_dev,
- info.netns_ino,
+ if (info->ifindex) {
+ name = ifindex_to_bfd_params(info->ifindex,
+ info->netns_dev,
+ info->netns_ino,
&disasm_opt);
if (!name)
goto err_free;
}
- if (info.nr_jited_func_lens && info.jited_func_lens) {
+ if (info->nr_jited_func_lens && info->jited_func_lens) {
struct kernel_sym *sym = NULL;
struct bpf_func_info *record;
char sym_name[SYM_MAX_NAME];
@@ -685,17 +556,16 @@ static int do_dump(int argc, char **argv)
__u64 *ksyms = NULL;
__u32 *lens;
__u32 i;
-
- if (info.nr_jited_ksyms) {
+ if (info->nr_jited_ksyms) {
kernel_syms_load(&dd);
- ksyms = (__u64 *) info.jited_ksyms;
+ ksyms = (__u64 *) info->jited_ksyms;
}
if (json_output)
jsonw_start_array(json_wtr);
- lens = (__u32 *) info.jited_func_lens;
- for (i = 0; i < info.nr_jited_func_lens; i++) {
+ lens = (__u32 *) info->jited_func_lens;
+ for (i = 0; i < info->nr_jited_func_lens; i++) {
if (ksyms) {
sym = kernel_syms_search(&dd, ksyms[i]);
if (sym)
@@ -707,7 +577,7 @@ static int do_dump(int argc, char **argv)
}
if (func_info) {
- record = func_info + i * finfo_rec_size;
+ record = func_info + i * info->func_info_rec_size;
btf_dumper_type_only(btf, record->type_id,
func_sig,
sizeof(func_sig));
@@ -744,49 +614,37 @@ static int do_dump(int argc, char **argv)
if (json_output)
jsonw_end_array(json_wtr);
} else {
- disasm_print_insn(buf, *member_len, opcodes, name,
+ disasm_print_insn(buf, member_len, opcodes, name,
disasm_opt, btf, NULL, 0, 0, false);
}
} else if (visual) {
if (json_output)
jsonw_null(json_wtr);
else
- dump_xlated_cfg(buf, *member_len);
+ dump_xlated_cfg(buf, member_len);
} else {
kernel_syms_load(&dd);
- dd.nr_jited_ksyms = info.nr_jited_ksyms;
- dd.jited_ksyms = (__u64 *) info.jited_ksyms;
+ dd.nr_jited_ksyms = info->nr_jited_ksyms;
+ dd.jited_ksyms = (__u64 *) info->jited_ksyms;
dd.btf = btf;
dd.func_info = func_info;
- dd.finfo_rec_size = finfo_rec_size;
+ dd.finfo_rec_size = info->func_info_rec_size;
dd.prog_linfo = prog_linfo;
if (json_output)
- dump_xlated_json(&dd, buf, *member_len, opcodes,
+ dump_xlated_json(&dd, buf, member_len, opcodes,
linum);
else
- dump_xlated_plain(&dd, buf, *member_len, opcodes,
+ dump_xlated_plain(&dd, buf, member_len, opcodes,
linum);
kernel_syms_destroy(&dd);
}
- free(buf);
- free(func_ksyms);
- free(func_lens);
- free(func_info);
- free(linfo);
- free(jited_linfo);
- bpf_prog_linfo__free(prog_linfo);
+ free(info_linear);
return 0;
err_free:
- free(buf);
- free(func_ksyms);
- free(func_lens);
- free(func_info);
- free(linfo);
- free(jited_linfo);
- bpf_prog_linfo__free(prog_linfo);
+ free(info_linear);
return -1;
}
@@ -1202,7 +1060,7 @@ static int do_help(int argc, char **argv)
" tracepoint | raw_tracepoint | xdp | perf_event | cgroup/skb |\n"
" cgroup/sock | cgroup/dev | lwt_in | lwt_out | lwt_xmit |\n"
" lwt_seg6local | sockops | sk_skb | sk_msg | lirc_mode2 |\n"
- " sk_reuseport | flow_dissector |\n"
+ " sk_reuseport | flow_dissector | cgroup/sysctl |\n"
" cgroup/bind4 | cgroup/bind6 | cgroup/post_bind4 |\n"
" cgroup/post_bind6 | cgroup/connect4 | cgroup/connect6 |\n"
" cgroup/sendmsg4 | cgroup/sendmsg6 }\n"
diff --git a/tools/bpf/bpftool/xlated_dumper.c b/tools/bpf/bpftool/xlated_dumper.c
index 7073dbe1ff27..0bb17bf88b18 100644
--- a/tools/bpf/bpftool/xlated_dumper.c
+++ b/tools/bpf/bpftool/xlated_dumper.c
@@ -195,6 +195,9 @@ static const char *print_imm(void *private_data,
if (insn->src_reg == BPF_PSEUDO_MAP_FD)
snprintf(dd->scratch_buff, sizeof(dd->scratch_buff),
"map[id:%u]", insn->imm);
+ else if (insn->src_reg == BPF_PSEUDO_MAP_VALUE)
+ snprintf(dd->scratch_buff, sizeof(dd->scratch_buff),
+ "map[id:%u][0]+%u", insn->imm, (insn + 1)->imm);
else
snprintf(dd->scratch_buff, sizeof(dd->scratch_buff),
"0x%llx", (unsigned long long)full_imm);
diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature
index 61e46d54a67c..361207387b1b 100644
--- a/tools/build/Makefile.feature
+++ b/tools/build/Makefile.feature
@@ -66,7 +66,9 @@ FEATURE_TESTS_BASIC := \
sched_getcpu \
sdt \
setns \
- libaio
+ libaio \
+ libzstd \
+ disassembler-four-args
# FEATURE_TESTS_BASIC + FEATURE_TESTS_EXTRA is the complete list
# of all feature tests
@@ -118,7 +120,9 @@ FEATURE_DISPLAY ?= \
lzma \
get_cpuid \
bpf \
- libaio
+ libaio \
+ libzstd \
+ disassembler-four-args
# Set FEATURE_CHECK_(C|LD)FLAGS-all for all FEATURE_TESTS features.
# If in the future we need per-feature checks/flags for features not
diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index 7ceb4441b627..4b8244ee65ce 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -62,7 +62,8 @@ FILES= \
test-clang.bin \
test-llvm.bin \
test-llvm-version.bin \
- test-libaio.bin
+ test-libaio.bin \
+ test-libzstd.bin
FILES := $(addprefix $(OUTPUT),$(FILES))
@@ -301,6 +302,9 @@ $(OUTPUT)test-clang.bin:
$(OUTPUT)test-libaio.bin:
$(BUILD) -lrt
+$(OUTPUT)test-libzstd.bin:
+ $(BUILD) -lzstd
+
###############################
clean:
diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c
index e903b86b742f..a59c53705093 100644
--- a/tools/build/feature/test-all.c
+++ b/tools/build/feature/test-all.c
@@ -178,6 +178,14 @@
# include "test-reallocarray.c"
#undef main
+#define main main_test_disassembler_four_args
+# include "test-disassembler-four-args.c"
+#undef main
+
+#define main main_test_zstd
+# include "test-libzstd.c"
+#undef main
+
int main(int argc, char *argv[])
{
main_test_libpython();
@@ -219,6 +227,8 @@ int main(int argc, char *argv[])
main_test_setns();
main_test_libaio();
main_test_reallocarray();
+ main_test_disassembler_four_args();
+ main_test_libzstd();
return 0;
}
diff --git a/tools/build/feature/test-libopencsd.c b/tools/build/feature/test-libopencsd.c
index d68eb4fb40cc..2b0e02c38870 100644
--- a/tools/build/feature/test-libopencsd.c
+++ b/tools/build/feature/test-libopencsd.c
@@ -4,9 +4,9 @@
/*
* Check OpenCSD library version is sufficient to provide required features
*/
-#define OCSD_MIN_VER ((0 << 16) | (10 << 8) | (0))
+#define OCSD_MIN_VER ((0 << 16) | (11 << 8) | (0))
#if !defined(OCSD_VER_NUM) || (OCSD_VER_NUM < OCSD_MIN_VER)
-#error "OpenCSD >= 0.10.0 is required"
+#error "OpenCSD >= 0.11.0 is required"
#endif
int main(void)
diff --git a/tools/build/feature/test-libzstd.c b/tools/build/feature/test-libzstd.c
new file mode 100644
index 000000000000..55268c01b84d
--- /dev/null
+++ b/tools/build/feature/test-libzstd.c
@@ -0,0 +1,12 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <zstd.h>
+
+int main(void)
+{
+ ZSTD_CStream *cstream;
+
+ cstream = ZSTD_createCStream();
+ ZSTD_freeCStream(cstream);
+
+ return 0;
+}
diff --git a/tools/include/linux/coresight-pmu.h b/tools/include/linux/coresight-pmu.h
index a1a959ba24ff..b0e35eec6499 100644
--- a/tools/include/linux/coresight-pmu.h
+++ b/tools/include/linux/coresight-pmu.h
@@ -12,11 +12,13 @@
/* ETMv3.5/PTM's ETMCR config bit */
#define ETM_OPT_CYCACC 12
+#define ETM_OPT_CTXTID 14
#define ETM_OPT_TS 28
#define ETM_OPT_RETSTK 29
/* ETMv4 CONFIGR programming bits for the ETM OPTs */
#define ETM4_CFG_BIT_CYCACC 4
+#define ETM4_CFG_BIT_CTXTID 6
#define ETM4_CFG_BIT_TS 11
#define ETM4_CFG_BIT_RETSTK 12
diff --git a/tools/include/linux/filter.h b/tools/include/linux/filter.h
index cce0b02c0e28..ca28b6ab8db7 100644
--- a/tools/include/linux/filter.h
+++ b/tools/include/linux/filter.h
@@ -278,10 +278,29 @@
.off = 0, \
.imm = ((__u64) (IMM)) >> 32 })
+#define BPF_LD_IMM64_RAW_FULL(DST, SRC, OFF1, OFF2, IMM1, IMM2) \
+ ((struct bpf_insn) { \
+ .code = BPF_LD | BPF_DW | BPF_IMM, \
+ .dst_reg = DST, \
+ .src_reg = SRC, \
+ .off = OFF1, \
+ .imm = IMM1 }), \
+ ((struct bpf_insn) { \
+ .code = 0, /* zero is reserved opcode */ \
+ .dst_reg = 0, \
+ .src_reg = 0, \
+ .off = OFF2, \
+ .imm = IMM2 })
+
/* pseudo BPF_LD_IMM64 insn used to refer to process-local map_fd */
#define BPF_LD_MAP_FD(DST, MAP_FD) \
- BPF_LD_IMM64_RAW(DST, BPF_PSEUDO_MAP_FD, MAP_FD)
+ BPF_LD_IMM64_RAW_FULL(DST, BPF_PSEUDO_MAP_FD, 0, 0, \
+ MAP_FD, 0)
+
+#define BPF_LD_MAP_VALUE(DST, MAP_FD, VALUE_OFF) \
+ BPF_LD_IMM64_RAW_FULL(DST, BPF_PSEUDO_MAP_VALUE, 0, 0, \
+ MAP_FD, VALUE_OFF)
/* Relative call */
diff --git a/tools/include/uapi/asm-generic/mman-common-tools.h b/tools/include/uapi/asm-generic/mman-common-tools.h
new file mode 100644
index 000000000000..af7d0d3a3182
--- /dev/null
+++ b/tools/include/uapi/asm-generic/mman-common-tools.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __ASM_GENERIC_MMAN_COMMON_TOOLS_ONLY_H
+#define __ASM_GENERIC_MMAN_COMMON_TOOLS_ONLY_H
+
+#include <asm-generic/mman-common.h>
+
+/* We need this because we need to have tools/include/uapi/ included in the tools
+ * header search path to get access to stuff that is not yet in the system's
+ * copy of the files in that directory, but since this cset:
+ *
+ * 746c9398f5ac ("arch: move common mmap flags to linux/mman.h")
+ *
+ * We end up making sys/mman.h, that is in the system headers, to not find the
+ * MAP_SHARED and MAP_PRIVATE defines because they are not anymore in our copy
+ * of asm-generic/mman-common.h. So we define them here and include this header
+ * from each of the per arch mman.h headers.
+ */
+#ifndef MAP_SHARED
+#define MAP_SHARED 0x01 /* Share changes */
+#define MAP_PRIVATE 0x02 /* Changes are private */
+#define MAP_SHARED_VALIDATE 0x03 /* share + validate extension flags */
+#endif
+#endif // __ASM_GENERIC_MMAN_COMMON_TOOLS_ONLY_H
diff --git a/tools/include/uapi/asm-generic/mman-common.h b/tools/include/uapi/asm-generic/mman-common.h
index e7ee32861d51..abd238d0f7a4 100644
--- a/tools/include/uapi/asm-generic/mman-common.h
+++ b/tools/include/uapi/asm-generic/mman-common.h
@@ -15,9 +15,7 @@
#define PROT_GROWSDOWN 0x01000000 /* mprotect flag: extend change to start of growsdown vma */
#define PROT_GROWSUP 0x02000000 /* mprotect flag: extend change to end of growsup vma */
-#define MAP_SHARED 0x01 /* Share changes */
-#define MAP_PRIVATE 0x02 /* Changes are private */
-#define MAP_SHARED_VALIDATE 0x03 /* share + validate extension flags */
+/* 0x01 - 0x03 are defined in linux/mman.h */
#define MAP_TYPE 0x0f /* Mask for type of mapping */
#define MAP_FIXED 0x10 /* Interpret addr exactly */
#define MAP_ANONYMOUS 0x20 /* don't use a file */
diff --git a/tools/include/uapi/asm-generic/mman.h b/tools/include/uapi/asm-generic/mman.h
index 653687d9771b..36c197fc44a0 100644
--- a/tools/include/uapi/asm-generic/mman.h
+++ b/tools/include/uapi/asm-generic/mman.h
@@ -2,7 +2,7 @@
#ifndef __ASM_GENERIC_MMAN_H
#define __ASM_GENERIC_MMAN_H
-#include <asm-generic/mman-common.h>
+#include <asm-generic/mman-common-tools.h>
#define MAP_GROWSDOWN 0x0100 /* stack-like segment */
#define MAP_DENYWRITE 0x0800 /* ETXTBSY */
diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
index d90127298f12..dee7292e1df6 100644
--- a/tools/include/uapi/asm-generic/unistd.h
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -38,8 +38,10 @@ __SYSCALL(__NR_io_destroy, sys_io_destroy)
__SC_COMP(__NR_io_submit, sys_io_submit, compat_sys_io_submit)
#define __NR_io_cancel 3
__SYSCALL(__NR_io_cancel, sys_io_cancel)
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
#define __NR_io_getevents 4
-__SC_COMP(__NR_io_getevents, sys_io_getevents, compat_sys_io_getevents)
+__SC_3264(__NR_io_getevents, sys_io_getevents_time32, sys_io_getevents)
+#endif
/* fs/xattr.c */
#define __NR_setxattr 5
@@ -179,7 +181,7 @@ __SYSCALL(__NR_fchownat, sys_fchownat)
#define __NR_fchown 55
__SYSCALL(__NR_fchown, sys_fchown)
#define __NR_openat 56
-__SC_COMP(__NR_openat, sys_openat, compat_sys_openat)
+__SYSCALL(__NR_openat, sys_openat)
#define __NR_close 57
__SYSCALL(__NR_close, sys_close)
#define __NR_vhangup 58
@@ -222,10 +224,12 @@ __SC_COMP(__NR_pwritev, sys_pwritev, compat_sys_pwritev)
__SYSCALL(__NR3264_sendfile, sys_sendfile64)
/* fs/select.c */
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
#define __NR_pselect6 72
-__SC_COMP(__NR_pselect6, sys_pselect6, compat_sys_pselect6)
+__SC_COMP_3264(__NR_pselect6, sys_pselect6_time32, sys_pselect6, compat_sys_pselect6_time32)
#define __NR_ppoll 73
-__SC_COMP(__NR_ppoll, sys_ppoll, compat_sys_ppoll)
+__SC_COMP_3264(__NR_ppoll, sys_ppoll_time32, sys_ppoll, compat_sys_ppoll_time32)
+#endif
/* fs/signalfd.c */
#define __NR_signalfd4 74
@@ -269,16 +273,20 @@ __SC_COMP(__NR_sync_file_range, sys_sync_file_range, \
/* fs/timerfd.c */
#define __NR_timerfd_create 85
__SYSCALL(__NR_timerfd_create, sys_timerfd_create)
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
#define __NR_timerfd_settime 86
-__SC_COMP(__NR_timerfd_settime, sys_timerfd_settime, \
- compat_sys_timerfd_settime)
+__SC_3264(__NR_timerfd_settime, sys_timerfd_settime32, \
+ sys_timerfd_settime)
#define __NR_timerfd_gettime 87
-__SC_COMP(__NR_timerfd_gettime, sys_timerfd_gettime, \
- compat_sys_timerfd_gettime)
+__SC_3264(__NR_timerfd_gettime, sys_timerfd_gettime32, \
+ sys_timerfd_gettime)
+#endif
/* fs/utimes.c */
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
#define __NR_utimensat 88
-__SC_COMP(__NR_utimensat, sys_utimensat, compat_sys_utimensat)
+__SC_3264(__NR_utimensat, sys_utimensat_time32, sys_utimensat)
+#endif
/* kernel/acct.c */
#define __NR_acct 89
@@ -309,8 +317,10 @@ __SYSCALL(__NR_set_tid_address, sys_set_tid_address)
__SYSCALL(__NR_unshare, sys_unshare)
/* kernel/futex.c */
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
#define __NR_futex 98
-__SC_COMP(__NR_futex, sys_futex, compat_sys_futex)
+__SC_3264(__NR_futex, sys_futex_time32, sys_futex)
+#endif
#define __NR_set_robust_list 99
__SC_COMP(__NR_set_robust_list, sys_set_robust_list, \
compat_sys_set_robust_list)
@@ -319,8 +329,10 @@ __SC_COMP(__NR_get_robust_list, sys_get_robust_list, \
compat_sys_get_robust_list)
/* kernel/hrtimer.c */
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
#define __NR_nanosleep 101
-__SC_COMP(__NR_nanosleep, sys_nanosleep, compat_sys_nanosleep)
+__SC_3264(__NR_nanosleep, sys_nanosleep_time32, sys_nanosleep)
+#endif
/* kernel/itimer.c */
#define __NR_getitimer 102
@@ -341,23 +353,29 @@ __SYSCALL(__NR_delete_module, sys_delete_module)
/* kernel/posix-timers.c */
#define __NR_timer_create 107
__SC_COMP(__NR_timer_create, sys_timer_create, compat_sys_timer_create)
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
#define __NR_timer_gettime 108
-__SC_COMP(__NR_timer_gettime, sys_timer_gettime, compat_sys_timer_gettime)
+__SC_3264(__NR_timer_gettime, sys_timer_gettime32, sys_timer_gettime)
+#endif
#define __NR_timer_getoverrun 109
__SYSCALL(__NR_timer_getoverrun, sys_timer_getoverrun)
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
#define __NR_timer_settime 110
-__SC_COMP(__NR_timer_settime, sys_timer_settime, compat_sys_timer_settime)
+__SC_3264(__NR_timer_settime, sys_timer_settime32, sys_timer_settime)
+#endif
#define __NR_timer_delete 111
__SYSCALL(__NR_timer_delete, sys_timer_delete)
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
#define __NR_clock_settime 112
-__SC_COMP(__NR_clock_settime, sys_clock_settime, compat_sys_clock_settime)
+__SC_3264(__NR_clock_settime, sys_clock_settime32, sys_clock_settime)
#define __NR_clock_gettime 113
-__SC_COMP(__NR_clock_gettime, sys_clock_gettime, compat_sys_clock_gettime)
+__SC_3264(__NR_clock_gettime, sys_clock_gettime32, sys_clock_gettime)
#define __NR_clock_getres 114
-__SC_COMP(__NR_clock_getres, sys_clock_getres, compat_sys_clock_getres)
+__SC_3264(__NR_clock_getres, sys_clock_getres_time32, sys_clock_getres)
#define __NR_clock_nanosleep 115
-__SC_COMP(__NR_clock_nanosleep, sys_clock_nanosleep, \
- compat_sys_clock_nanosleep)
+__SC_3264(__NR_clock_nanosleep, sys_clock_nanosleep_time32, \
+ sys_clock_nanosleep)
+#endif
/* kernel/printk.c */
#define __NR_syslog 116
@@ -388,9 +406,11 @@ __SYSCALL(__NR_sched_yield, sys_sched_yield)
__SYSCALL(__NR_sched_get_priority_max, sys_sched_get_priority_max)
#define __NR_sched_get_priority_min 126
__SYSCALL(__NR_sched_get_priority_min, sys_sched_get_priority_min)
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
#define __NR_sched_rr_get_interval 127
-__SC_COMP(__NR_sched_rr_get_interval, sys_sched_rr_get_interval, \
- compat_sys_sched_rr_get_interval)
+__SC_3264(__NR_sched_rr_get_interval, sys_sched_rr_get_interval_time32, \
+ sys_sched_rr_get_interval)
+#endif
/* kernel/signal.c */
#define __NR_restart_syscall 128
@@ -411,9 +431,11 @@ __SC_COMP(__NR_rt_sigaction, sys_rt_sigaction, compat_sys_rt_sigaction)
__SC_COMP(__NR_rt_sigprocmask, sys_rt_sigprocmask, compat_sys_rt_sigprocmask)
#define __NR_rt_sigpending 136
__SC_COMP(__NR_rt_sigpending, sys_rt_sigpending, compat_sys_rt_sigpending)
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
#define __NR_rt_sigtimedwait 137
-__SC_COMP(__NR_rt_sigtimedwait, sys_rt_sigtimedwait, \
- compat_sys_rt_sigtimedwait)
+__SC_COMP_3264(__NR_rt_sigtimedwait, sys_rt_sigtimedwait_time32, \
+ sys_rt_sigtimedwait, compat_sys_rt_sigtimedwait_time32)
+#endif
#define __NR_rt_sigqueueinfo 138
__SC_COMP(__NR_rt_sigqueueinfo, sys_rt_sigqueueinfo, \
compat_sys_rt_sigqueueinfo)
@@ -467,10 +489,15 @@ __SYSCALL(__NR_uname, sys_newuname)
__SYSCALL(__NR_sethostname, sys_sethostname)
#define __NR_setdomainname 162
__SYSCALL(__NR_setdomainname, sys_setdomainname)
+
+#ifdef __ARCH_WANT_SET_GET_RLIMIT
+/* getrlimit and setrlimit are superseded with prlimit64 */
#define __NR_getrlimit 163
__SC_COMP(__NR_getrlimit, sys_getrlimit, compat_sys_getrlimit)
#define __NR_setrlimit 164
__SC_COMP(__NR_setrlimit, sys_setrlimit, compat_sys_setrlimit)
+#endif
+
#define __NR_getrusage 165
__SC_COMP(__NR_getrusage, sys_getrusage, compat_sys_getrusage)
#define __NR_umask 166
@@ -481,12 +508,14 @@ __SYSCALL(__NR_prctl, sys_prctl)
__SYSCALL(__NR_getcpu, sys_getcpu)
/* kernel/time.c */
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
#define __NR_gettimeofday 169
__SC_COMP(__NR_gettimeofday, sys_gettimeofday, compat_sys_gettimeofday)
#define __NR_settimeofday 170
__SC_COMP(__NR_settimeofday, sys_settimeofday, compat_sys_settimeofday)
#define __NR_adjtimex 171
-__SC_COMP(__NR_adjtimex, sys_adjtimex, compat_sys_adjtimex)
+__SC_3264(__NR_adjtimex, sys_adjtimex_time32, sys_adjtimex)
+#endif
/* kernel/timer.c */
#define __NR_getpid 172
@@ -511,11 +540,13 @@ __SC_COMP(__NR_sysinfo, sys_sysinfo, compat_sys_sysinfo)
__SC_COMP(__NR_mq_open, sys_mq_open, compat_sys_mq_open)
#define __NR_mq_unlink 181
__SYSCALL(__NR_mq_unlink, sys_mq_unlink)
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
#define __NR_mq_timedsend 182
-__SC_COMP(__NR_mq_timedsend, sys_mq_timedsend, compat_sys_mq_timedsend)
+__SC_3264(__NR_mq_timedsend, sys_mq_timedsend_time32, sys_mq_timedsend)
#define __NR_mq_timedreceive 183
-__SC_COMP(__NR_mq_timedreceive, sys_mq_timedreceive, \
- compat_sys_mq_timedreceive)
+__SC_3264(__NR_mq_timedreceive, sys_mq_timedreceive_time32, \
+ sys_mq_timedreceive)
+#endif
#define __NR_mq_notify 184
__SC_COMP(__NR_mq_notify, sys_mq_notify, compat_sys_mq_notify)
#define __NR_mq_getsetattr 185
@@ -536,8 +567,10 @@ __SC_COMP(__NR_msgsnd, sys_msgsnd, compat_sys_msgsnd)
__SYSCALL(__NR_semget, sys_semget)
#define __NR_semctl 191
__SC_COMP(__NR_semctl, sys_semctl, compat_sys_semctl)
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
#define __NR_semtimedop 192
-__SC_COMP(__NR_semtimedop, sys_semtimedop, compat_sys_semtimedop)
+__SC_COMP(__NR_semtimedop, sys_semtimedop, sys_semtimedop_time32)
+#endif
#define __NR_semop 193
__SYSCALL(__NR_semop, sys_semop)
@@ -658,8 +691,10 @@ __SC_COMP(__NR_rt_tgsigqueueinfo, sys_rt_tgsigqueueinfo, \
__SYSCALL(__NR_perf_event_open, sys_perf_event_open)
#define __NR_accept4 242
__SYSCALL(__NR_accept4, sys_accept4)
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
#define __NR_recvmmsg 243
-__SC_COMP(__NR_recvmmsg, sys_recvmmsg, compat_sys_recvmmsg)
+__SC_COMP_3264(__NR_recvmmsg, sys_recvmmsg_time32, sys_recvmmsg, compat_sys_recvmmsg_time32)
+#endif
/*
* Architectures may provide up to 16 syscalls of their own
@@ -667,8 +702,10 @@ __SC_COMP(__NR_recvmmsg, sys_recvmmsg, compat_sys_recvmmsg)
*/
#define __NR_arch_specific_syscall 244
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
#define __NR_wait4 260
__SC_COMP(__NR_wait4, sys_wait4, compat_sys_wait4)
+#endif
#define __NR_prlimit64 261
__SYSCALL(__NR_prlimit64, sys_prlimit64)
#define __NR_fanotify_init 262
@@ -678,10 +715,11 @@ __SYSCALL(__NR_fanotify_mark, sys_fanotify_mark)
#define __NR_name_to_handle_at 264
__SYSCALL(__NR_name_to_handle_at, sys_name_to_handle_at)
#define __NR_open_by_handle_at 265
-__SC_COMP(__NR_open_by_handle_at, sys_open_by_handle_at, \
- compat_sys_open_by_handle_at)
+__SYSCALL(__NR_open_by_handle_at, sys_open_by_handle_at)
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
#define __NR_clock_adjtime 266
-__SC_COMP(__NR_clock_adjtime, sys_clock_adjtime, compat_sys_clock_adjtime)
+__SC_3264(__NR_clock_adjtime, sys_clock_adjtime32, sys_clock_adjtime)
+#endif
#define __NR_syncfs 267
__SYSCALL(__NR_syncfs, sys_syncfs)
#define __NR_setns 268
@@ -734,15 +772,69 @@ __SYSCALL(__NR_pkey_alloc, sys_pkey_alloc)
__SYSCALL(__NR_pkey_free, sys_pkey_free)
#define __NR_statx 291
__SYSCALL(__NR_statx, sys_statx)
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
#define __NR_io_pgetevents 292
-__SC_COMP(__NR_io_pgetevents, sys_io_pgetevents, compat_sys_io_pgetevents)
+__SC_COMP_3264(__NR_io_pgetevents, sys_io_pgetevents_time32, sys_io_pgetevents, compat_sys_io_pgetevents)
+#endif
#define __NR_rseq 293
__SYSCALL(__NR_rseq, sys_rseq)
#define __NR_kexec_file_load 294
__SYSCALL(__NR_kexec_file_load, sys_kexec_file_load)
+/* 295 through 402 are unassigned to sync up with generic numbers, don't use */
+#if __BITS_PER_LONG == 32
+#define __NR_clock_gettime64 403
+__SYSCALL(__NR_clock_gettime64, sys_clock_gettime)
+#define __NR_clock_settime64 404
+__SYSCALL(__NR_clock_settime64, sys_clock_settime)
+#define __NR_clock_adjtime64 405
+__SYSCALL(__NR_clock_adjtime64, sys_clock_adjtime)
+#define __NR_clock_getres_time64 406
+__SYSCALL(__NR_clock_getres_time64, sys_clock_getres)
+#define __NR_clock_nanosleep_time64 407
+__SYSCALL(__NR_clock_nanosleep_time64, sys_clock_nanosleep)
+#define __NR_timer_gettime64 408
+__SYSCALL(__NR_timer_gettime64, sys_timer_gettime)
+#define __NR_timer_settime64 409
+__SYSCALL(__NR_timer_settime64, sys_timer_settime)
+#define __NR_timerfd_gettime64 410
+__SYSCALL(__NR_timerfd_gettime64, sys_timerfd_gettime)
+#define __NR_timerfd_settime64 411
+__SYSCALL(__NR_timerfd_settime64, sys_timerfd_settime)
+#define __NR_utimensat_time64 412
+__SYSCALL(__NR_utimensat_time64, sys_utimensat)
+#define __NR_pselect6_time64 413
+__SC_COMP(__NR_pselect6_time64, sys_pselect6, compat_sys_pselect6_time64)
+#define __NR_ppoll_time64 414
+__SC_COMP(__NR_ppoll_time64, sys_ppoll, compat_sys_ppoll_time64)
+#define __NR_io_pgetevents_time64 416
+__SYSCALL(__NR_io_pgetevents_time64, sys_io_pgetevents)
+#define __NR_recvmmsg_time64 417
+__SC_COMP(__NR_recvmmsg_time64, sys_recvmmsg, compat_sys_recvmmsg_time64)
+#define __NR_mq_timedsend_time64 418
+__SYSCALL(__NR_mq_timedsend_time64, sys_mq_timedsend)
+#define __NR_mq_timedreceive_time64 419
+__SYSCALL(__NR_mq_timedreceive_time64, sys_mq_timedreceive)
+#define __NR_semtimedop_time64 420
+__SYSCALL(__NR_semtimedop_time64, sys_semtimedop)
+#define __NR_rt_sigtimedwait_time64 421
+__SC_COMP(__NR_rt_sigtimedwait_time64, sys_rt_sigtimedwait, compat_sys_rt_sigtimedwait_time64)
+#define __NR_futex_time64 422
+__SYSCALL(__NR_futex_time64, sys_futex)
+#define __NR_sched_rr_get_interval_time64 423
+__SYSCALL(__NR_sched_rr_get_interval_time64, sys_sched_rr_get_interval)
+#endif
+
+#define __NR_pidfd_send_signal 424
+__SYSCALL(__NR_pidfd_send_signal, sys_pidfd_send_signal)
+#define __NR_io_uring_setup 425
+__SYSCALL(__NR_io_uring_setup, sys_io_uring_setup)
+#define __NR_io_uring_enter 426
+__SYSCALL(__NR_io_uring_enter, sys_io_uring_enter)
+#define __NR_io_uring_register 427
+__SYSCALL(__NR_io_uring_register, sys_io_uring_register)
#undef __NR_syscalls
-#define __NR_syscalls 295
+#define __NR_syscalls 428
/*
* 32 bit systems traditionally used different
diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h
index 298b2e197744..397810fa2d33 100644
--- a/tools/include/uapi/drm/i915_drm.h
+++ b/tools/include/uapi/drm/i915_drm.h
@@ -1486,9 +1486,73 @@ struct drm_i915_gem_context_param {
#define I915_CONTEXT_MAX_USER_PRIORITY 1023 /* inclusive */
#define I915_CONTEXT_DEFAULT_PRIORITY 0
#define I915_CONTEXT_MIN_USER_PRIORITY -1023 /* inclusive */
+ /*
+ * When using the following param, value should be a pointer to
+ * drm_i915_gem_context_param_sseu.
+ */
+#define I915_CONTEXT_PARAM_SSEU 0x7
__u64 value;
};
+/**
+ * Context SSEU programming
+ *
+ * It may be necessary for either functional or performance reason to configure
+ * a context to run with a reduced number of SSEU (where SSEU stands for Slice/
+ * Sub-slice/EU).
+ *
+ * This is done by configuring SSEU configuration using the below
+ * @struct drm_i915_gem_context_param_sseu for every supported engine which
+ * userspace intends to use.
+ *
+ * Not all GPUs or engines support this functionality in which case an error
+ * code -ENODEV will be returned.
+ *
+ * Also, flexibility of possible SSEU configuration permutations varies between
+ * GPU generations and software imposed limitations. Requesting such a
+ * combination will return an error code of -EINVAL.
+ *
+ * NOTE: When perf/OA is active the context's SSEU configuration is ignored in
+ * favour of a single global setting.
+ */
+struct drm_i915_gem_context_param_sseu {
+ /*
+ * Engine class & instance to be configured or queried.
+ */
+ __u16 engine_class;
+ __u16 engine_instance;
+
+ /*
+ * Unused for now. Must be cleared to zero.
+ */
+ __u32 flags;
+
+ /*
+ * Mask of slices to enable for the context. Valid values are a subset
+ * of the bitmask value returned for I915_PARAM_SLICE_MASK.
+ */
+ __u64 slice_mask;
+
+ /*
+ * Mask of subslices to enable for the context. Valid values are a
+ * subset of the bitmask value return by I915_PARAM_SUBSLICE_MASK.
+ */
+ __u64 subslice_mask;
+
+ /*
+ * Minimum/Maximum number of EUs to enable per subslice for the
+ * context. min_eus_per_subslice must be inferior or equal to
+ * max_eus_per_subslice.
+ */
+ __u16 min_eus_per_subslice;
+ __u16 max_eus_per_subslice;
+
+ /*
+ * Unused for now. Must be cleared to zero.
+ */
+ __u32 rsvd;
+};
+
enum drm_i915_oa_format {
I915_OA_FORMAT_A13 = 1, /* HSW only */
I915_OA_FORMAT_A29, /* HSW only */
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 3c38ac9a92a7..72336bac7573 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -105,6 +105,7 @@ enum bpf_cmd {
BPF_BTF_GET_FD_BY_ID,
BPF_TASK_FD_QUERY,
BPF_MAP_LOOKUP_AND_DELETE_ELEM,
+ BPF_MAP_FREEZE,
};
enum bpf_map_type {
@@ -132,6 +133,7 @@ enum bpf_map_type {
BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE,
BPF_MAP_TYPE_QUEUE,
BPF_MAP_TYPE_STACK,
+ BPF_MAP_TYPE_SK_STORAGE,
};
/* Note that tracing related programs such as
@@ -166,6 +168,8 @@ enum bpf_prog_type {
BPF_PROG_TYPE_LIRC_MODE2,
BPF_PROG_TYPE_SK_REUSEPORT,
BPF_PROG_TYPE_FLOW_DISSECTOR,
+ BPF_PROG_TYPE_CGROUP_SYSCTL,
+ BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE,
};
enum bpf_attach_type {
@@ -187,6 +191,7 @@ enum bpf_attach_type {
BPF_CGROUP_UDP6_SENDMSG,
BPF_LIRC_MODE2,
BPF_FLOW_DISSECTOR,
+ BPF_CGROUP_SYSCTL,
__MAX_BPF_ATTACH_TYPE
};
@@ -255,8 +260,19 @@ enum bpf_attach_type {
*/
#define BPF_F_ANY_ALIGNMENT (1U << 1)
-/* when bpf_ldimm64->src_reg == BPF_PSEUDO_MAP_FD, bpf_ldimm64->imm == fd */
+/* When BPF ldimm64's insn[0].src_reg != 0 then this can have
+ * two extensions:
+ *
+ * insn[0].src_reg: BPF_PSEUDO_MAP_FD BPF_PSEUDO_MAP_VALUE
+ * insn[0].imm: map fd map fd
+ * insn[1].imm: 0 offset into value
+ * insn[0].off: 0 0
+ * insn[1].off: 0 0
+ * ldimm64 rewrite: address of map address of map[0]+offset
+ * verifier type: CONST_PTR_TO_MAP PTR_TO_MAP_VALUE
+ */
#define BPF_PSEUDO_MAP_FD 1
+#define BPF_PSEUDO_MAP_VALUE 2
/* when bpf_call->src_reg == BPF_PSEUDO_CALL, bpf_call->imm == pc-relative
* offset to another bpf function
@@ -283,7 +299,7 @@ enum bpf_attach_type {
#define BPF_OBJ_NAME_LEN 16U
-/* Flags for accessing BPF object */
+/* Flags for accessing BPF object from syscall side. */
#define BPF_F_RDONLY (1U << 3)
#define BPF_F_WRONLY (1U << 4)
@@ -293,6 +309,10 @@ enum bpf_attach_type {
/* Zero-initialize hash function seed. This should only be used for testing. */
#define BPF_F_ZERO_SEED (1U << 6)
+/* Flags for accessing BPF object from program side. */
+#define BPF_F_RDONLY_PROG (1U << 7)
+#define BPF_F_WRONLY_PROG (1U << 8)
+
/* flags for BPF_PROG_QUERY */
#define BPF_F_QUERY_EFFECTIVE (1U << 0)
@@ -396,6 +416,13 @@ union bpf_attr {
__aligned_u64 data_out;
__u32 repeat;
__u32 duration;
+ __u32 ctx_size_in; /* input: len of ctx_in */
+ __u32 ctx_size_out; /* input/output: len of ctx_out
+ * returns ENOSPC if ctx_out
+ * is too small.
+ */
+ __aligned_u64 ctx_in;
+ __aligned_u64 ctx_out;
} test;
struct { /* anonymous struct used by BPF_*_GET_*_ID */
@@ -502,16 +529,6 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_map_push_elem(struct bpf_map *map, const void *value, u64 flags)
- * Description
- * Push an element *value* in *map*. *flags* is one of:
- *
- * **BPF_EXIST**
- * If the queue/stack is full, the oldest element is removed to
- * make room for this.
- * Return
- * 0 on success, or a negative error in case of failure.
- *
* int bpf_probe_read(void *dst, u32 size, const void *src)
* Description
* For tracing programs, safely attempt to read *size* bytes from
@@ -1435,14 +1452,14 @@ union bpf_attr {
* u64 bpf_get_socket_cookie(struct bpf_sock_addr *ctx)
* Description
* Equivalent to bpf_get_socket_cookie() helper that accepts
- * *skb*, but gets socket from **struct bpf_sock_addr** contex.
+ * *skb*, but gets socket from **struct bpf_sock_addr** context.
* Return
* A 8-byte long non-decreasing number.
*
* u64 bpf_get_socket_cookie(struct bpf_sock_ops *ctx)
* Description
* Equivalent to bpf_get_socket_cookie() helper that accepts
- * *skb*, but gets socket from **struct bpf_sock_ops** contex.
+ * *skb*, but gets socket from **struct bpf_sock_ops** context.
* Return
* A 8-byte long non-decreasing number.
*
@@ -1488,13 +1505,31 @@ union bpf_attr {
* Grow or shrink the room for data in the packet associated to
* *skb* by *len_diff*, and according to the selected *mode*.
*
- * There is a single supported mode at this time:
+ * There are two supported modes at this time:
+ *
+ * * **BPF_ADJ_ROOM_MAC**: Adjust room at the mac layer
+ * (room space is added or removed below the layer 2 header).
*
* * **BPF_ADJ_ROOM_NET**: Adjust room at the network layer
* (room space is added or removed below the layer 3 header).
*
- * All values for *flags* are reserved for future usage, and must
- * be left at zero.
+ * The following flags are supported at this time:
+ *
+ * * **BPF_F_ADJ_ROOM_FIXED_GSO**: Do not adjust gso_size.
+ * Adjusting mss in this way is not allowed for datagrams.
+ *
+ * * **BPF_F_ADJ_ROOM_ENCAP_L3_IPV4 **:
+ * * **BPF_F_ADJ_ROOM_ENCAP_L3_IPV6 **:
+ * Any new space is reserved to hold a tunnel header.
+ * Configure skb offsets and other fields accordingly.
+ *
+ * * **BPF_F_ADJ_ROOM_ENCAP_L4_GRE **:
+ * * **BPF_F_ADJ_ROOM_ENCAP_L4_UDP **:
+ * Use with ENCAP_L3 flags to further specify the tunnel type.
+ *
+ * * **BPF_F_ADJ_ROOM_ENCAP_L2(len) **:
+ * Use with ENCAP_L3/L4 flags to further specify the tunnel
+ * type; **len** is the length of the inner MAC header.
*
* A call to this helper is susceptible to change the underlaying
* packet buffer. Therefore, at load time, all checks on pointers
@@ -1704,12 +1739,19 @@ union bpf_attr {
* error if an eBPF program tries to set a callback that is not
* supported in the current kernel.
*
- * The supported callback values that *argval* can combine are:
+ * *argval* is a flag array which can combine these flags:
*
* * **BPF_SOCK_OPS_RTO_CB_FLAG** (retransmission time out)
* * **BPF_SOCK_OPS_RETRANS_CB_FLAG** (retransmission)
* * **BPF_SOCK_OPS_STATE_CB_FLAG** (TCP state change)
*
+ * Therefore, this function can be used to clear a callback flag by
+ * setting the appropriate bit to zero. e.g. to disable the RTO
+ * callback:
+ *
+ * **bpf_sock_ops_cb_flags_set(bpf_sock,**
+ * **bpf_sock->bpf_sock_ops_cb_flags & ~BPF_SOCK_OPS_RTO_CB_FLAG)**
+ *
* Here are some examples of where one could call such eBPF
* program:
*
@@ -2098,52 +2140,52 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_rc_keydown(void *ctx, u32 protocol, u64 scancode, u32 toggle)
+ * int bpf_rc_repeat(void *ctx)
* Description
* This helper is used in programs implementing IR decoding, to
- * report a successfully decoded key press with *scancode*,
- * *toggle* value in the given *protocol*. The scancode will be
- * translated to a keycode using the rc keymap, and reported as
- * an input key down event. After a period a key up event is
- * generated. This period can be extended by calling either
- * **bpf_rc_keydown**\ () again with the same values, or calling
- * **bpf_rc_repeat**\ ().
+ * report a successfully decoded repeat key message. This delays
+ * the generation of a key up event for previously generated
+ * key down event.
*
- * Some protocols include a toggle bit, in case the button was
- * released and pressed again between consecutive scancodes.
+ * Some IR protocols like NEC have a special IR message for
+ * repeating last button, for when a button is held down.
*
* The *ctx* should point to the lirc sample as passed into
* the program.
*
- * The *protocol* is the decoded protocol number (see
- * **enum rc_proto** for some predefined values).
- *
* This helper is only available is the kernel was compiled with
* the **CONFIG_BPF_LIRC_MODE2** configuration option set to
* "**y**".
* Return
* 0
*
- * int bpf_rc_repeat(void *ctx)
+ * int bpf_rc_keydown(void *ctx, u32 protocol, u64 scancode, u32 toggle)
* Description
* This helper is used in programs implementing IR decoding, to
- * report a successfully decoded repeat key message. This delays
- * the generation of a key up event for previously generated
- * key down event.
+ * report a successfully decoded key press with *scancode*,
+ * *toggle* value in the given *protocol*. The scancode will be
+ * translated to a keycode using the rc keymap, and reported as
+ * an input key down event. After a period a key up event is
+ * generated. This period can be extended by calling either
+ * **bpf_rc_keydown**\ () again with the same values, or calling
+ * **bpf_rc_repeat**\ ().
*
- * Some IR protocols like NEC have a special IR message for
- * repeating last button, for when a button is held down.
+ * Some protocols include a toggle bit, in case the button was
+ * released and pressed again between consecutive scancodes.
*
* The *ctx* should point to the lirc sample as passed into
* the program.
*
+ * The *protocol* is the decoded protocol number (see
+ * **enum rc_proto** for some predefined values).
+ *
* This helper is only available is the kernel was compiled with
* the **CONFIG_BPF_LIRC_MODE2** configuration option set to
* "**y**".
* Return
* 0
*
- * uint64_t bpf_skb_cgroup_id(struct sk_buff *skb)
+ * u64 bpf_skb_cgroup_id(struct sk_buff *skb)
* Description
* Return the cgroup v2 id of the socket associated with the *skb*.
* This is roughly similar to the **bpf_get_cgroup_classid**\ ()
@@ -2159,30 +2201,12 @@ union bpf_attr {
* Return
* The id is returned or 0 in case the id could not be retrieved.
*
- * u64 bpf_skb_ancestor_cgroup_id(struct sk_buff *skb, int ancestor_level)
- * Description
- * Return id of cgroup v2 that is ancestor of cgroup associated
- * with the *skb* at the *ancestor_level*. The root cgroup is at
- * *ancestor_level* zero and each step down the hierarchy
- * increments the level. If *ancestor_level* == level of cgroup
- * associated with *skb*, then return value will be same as that
- * of **bpf_skb_cgroup_id**\ ().
- *
- * The helper is useful to implement policies based on cgroups
- * that are upper in hierarchy than immediate cgroup associated
- * with *skb*.
- *
- * The format of returned id and helper limitations are same as in
- * **bpf_skb_cgroup_id**\ ().
- * Return
- * The id is returned or 0 in case the id could not be retrieved.
- *
* u64 bpf_get_current_cgroup_id(void)
* Return
* A 64-bit integer containing the current cgroup id based
* on the cgroup within which the current task is running.
*
- * void* get_local_storage(void *map, u64 flags)
+ * void *bpf_get_local_storage(void *map, u64 flags)
* Description
* Get the pointer to the local storage area.
* The type and the size of the local storage is defined
@@ -2209,6 +2233,24 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
+ * u64 bpf_skb_ancestor_cgroup_id(struct sk_buff *skb, int ancestor_level)
+ * Description
+ * Return id of cgroup v2 that is ancestor of cgroup associated
+ * with the *skb* at the *ancestor_level*. The root cgroup is at
+ * *ancestor_level* zero and each step down the hierarchy
+ * increments the level. If *ancestor_level* == level of cgroup
+ * associated with *skb*, then return value will be same as that
+ * of **bpf_skb_cgroup_id**\ ().
+ *
+ * The helper is useful to implement policies based on cgroups
+ * that are upper in hierarchy than immediate cgroup associated
+ * with *skb*.
+ *
+ * The format of returned id and helper limitations are same as in
+ * **bpf_skb_cgroup_id**\ ().
+ * Return
+ * The id is returned or 0 in case the id could not be retrieved.
+ *
* struct bpf_sock *bpf_sk_lookup_tcp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags)
* Description
* Look for TCP socket matching *tuple*, optionally in a child
@@ -2289,6 +2331,16 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
+ * int bpf_map_push_elem(struct bpf_map *map, const void *value, u64 flags)
+ * Description
+ * Push an element *value* in *map*. *flags* is one of:
+ *
+ * **BPF_EXIST**
+ * If the queue/stack is full, the oldest element is
+ * removed to make room for this.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
* int bpf_map_pop_elem(struct bpf_map *map, void *value)
* Description
* Pop an element from *map*.
@@ -2343,29 +2395,278 @@ union bpf_attr {
* Return
* 0
*
+ * int bpf_spin_lock(struct bpf_spin_lock *lock)
+ * Description
+ * Acquire a spinlock represented by the pointer *lock*, which is
+ * stored as part of a value of a map. Taking the lock allows to
+ * safely update the rest of the fields in that value. The
+ * spinlock can (and must) later be released with a call to
+ * **bpf_spin_unlock**\ (\ *lock*\ ).
+ *
+ * Spinlocks in BPF programs come with a number of restrictions
+ * and constraints:
+ *
+ * * **bpf_spin_lock** objects are only allowed inside maps of
+ * types **BPF_MAP_TYPE_HASH** and **BPF_MAP_TYPE_ARRAY** (this
+ * list could be extended in the future).
+ * * BTF description of the map is mandatory.
+ * * The BPF program can take ONE lock at a time, since taking two
+ * or more could cause dead locks.
+ * * Only one **struct bpf_spin_lock** is allowed per map element.
+ * * When the lock is taken, calls (either BPF to BPF or helpers)
+ * are not allowed.
+ * * The **BPF_LD_ABS** and **BPF_LD_IND** instructions are not
+ * allowed inside a spinlock-ed region.
+ * * The BPF program MUST call **bpf_spin_unlock**\ () to release
+ * the lock, on all execution paths, before it returns.
+ * * The BPF program can access **struct bpf_spin_lock** only via
+ * the **bpf_spin_lock**\ () and **bpf_spin_unlock**\ ()
+ * helpers. Loading or storing data into the **struct
+ * bpf_spin_lock** *lock*\ **;** field of a map is not allowed.
+ * * To use the **bpf_spin_lock**\ () helper, the BTF description
+ * of the map value must be a struct and have **struct
+ * bpf_spin_lock** *anyname*\ **;** field at the top level.
+ * Nested lock inside another struct is not allowed.
+ * * The **struct bpf_spin_lock** *lock* field in a map value must
+ * be aligned on a multiple of 4 bytes in that value.
+ * * Syscall with command **BPF_MAP_LOOKUP_ELEM** does not copy
+ * the **bpf_spin_lock** field to user space.
+ * * Syscall with command **BPF_MAP_UPDATE_ELEM**, or update from
+ * a BPF program, do not update the **bpf_spin_lock** field.
+ * * **bpf_spin_lock** cannot be on the stack or inside a
+ * networking packet (it can only be inside of a map values).
+ * * **bpf_spin_lock** is available to root only.
+ * * Tracing programs and socket filter programs cannot use
+ * **bpf_spin_lock**\ () due to insufficient preemption checks
+ * (but this may change in the future).
+ * * **bpf_spin_lock** is not allowed in inner maps of map-in-map.
+ * Return
+ * 0
+ *
+ * int bpf_spin_unlock(struct bpf_spin_lock *lock)
+ * Description
+ * Release the *lock* previously locked by a call to
+ * **bpf_spin_lock**\ (\ *lock*\ ).
+ * Return
+ * 0
+ *
* struct bpf_sock *bpf_sk_fullsock(struct bpf_sock *sk)
* Description
* This helper gets a **struct bpf_sock** pointer such
- * that all the fields in bpf_sock can be accessed.
+ * that all the fields in this **bpf_sock** can be accessed.
* Return
- * A **struct bpf_sock** pointer on success, or NULL in
+ * A **struct bpf_sock** pointer on success, or **NULL** in
* case of failure.
*
* struct bpf_tcp_sock *bpf_tcp_sock(struct bpf_sock *sk)
* Description
* This helper gets a **struct bpf_tcp_sock** pointer from a
* **struct bpf_sock** pointer.
- *
* Return
- * A **struct bpf_tcp_sock** pointer on success, or NULL in
+ * A **struct bpf_tcp_sock** pointer on success, or **NULL** in
* case of failure.
*
* int bpf_skb_ecn_set_ce(struct sk_buf *skb)
- * Description
- * Sets ECN of IP header to ce (congestion encountered) if
- * current value is ect (ECN capable). Works with IPv6 and IPv4.
- * Return
- * 1 if set, 0 if not set.
+ * Description
+ * Set ECN (Explicit Congestion Notification) field of IP header
+ * to **CE** (Congestion Encountered) if current value is **ECT**
+ * (ECN Capable Transport). Otherwise, do nothing. Works with IPv6
+ * and IPv4.
+ * Return
+ * 1 if the **CE** flag is set (either by the current helper call
+ * or because it was already present), 0 if it is not set.
+ *
+ * struct bpf_sock *bpf_get_listener_sock(struct bpf_sock *sk)
+ * Description
+ * Return a **struct bpf_sock** pointer in **TCP_LISTEN** state.
+ * **bpf_sk_release**\ () is unnecessary and not allowed.
+ * Return
+ * A **struct bpf_sock** pointer on success, or **NULL** in
+ * case of failure.
+ *
+ * struct bpf_sock *bpf_skc_lookup_tcp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags)
+ * Description
+ * Look for TCP socket matching *tuple*, optionally in a child
+ * network namespace *netns*. The return value must be checked,
+ * and if non-**NULL**, released via **bpf_sk_release**\ ().
+ *
+ * This function is identical to bpf_sk_lookup_tcp, except that it
+ * also returns timewait or request sockets. Use bpf_sk_fullsock
+ * or bpf_tcp_socket to access the full structure.
+ *
+ * This helper is available only if the kernel was compiled with
+ * **CONFIG_NET** configuration option.
+ * Return
+ * Pointer to **struct bpf_sock**, or **NULL** in case of failure.
+ * For sockets with reuseport option, the **struct bpf_sock**
+ * result is from **reuse->socks**\ [] using the hash of the tuple.
+ *
+ * int bpf_tcp_check_syncookie(struct bpf_sock *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len)
+ * Description
+ * Check whether iph and th contain a valid SYN cookie ACK for
+ * the listening socket in sk.
+ *
+ * iph points to the start of the IPv4 or IPv6 header, while
+ * iph_len contains sizeof(struct iphdr) or sizeof(struct ip6hdr).
+ *
+ * th points to the start of the TCP header, while th_len contains
+ * sizeof(struct tcphdr).
+ *
+ * Return
+ * 0 if iph and th are a valid SYN cookie ACK, or a negative error
+ * otherwise.
+ *
+ * int bpf_sysctl_get_name(struct bpf_sysctl *ctx, char *buf, size_t buf_len, u64 flags)
+ * Description
+ * Get name of sysctl in /proc/sys/ and copy it into provided by
+ * program buffer *buf* of size *buf_len*.
+ *
+ * The buffer is always NUL terminated, unless it's zero-sized.
+ *
+ * If *flags* is zero, full name (e.g. "net/ipv4/tcp_mem") is
+ * copied. Use **BPF_F_SYSCTL_BASE_NAME** flag to copy base name
+ * only (e.g. "tcp_mem").
+ * Return
+ * Number of character copied (not including the trailing NUL).
+ *
+ * **-E2BIG** if the buffer wasn't big enough (*buf* will contain
+ * truncated name in this case).
+ *
+ * int bpf_sysctl_get_current_value(struct bpf_sysctl *ctx, char *buf, size_t buf_len)
+ * Description
+ * Get current value of sysctl as it is presented in /proc/sys
+ * (incl. newline, etc), and copy it as a string into provided
+ * by program buffer *buf* of size *buf_len*.
+ *
+ * The whole value is copied, no matter what file position user
+ * space issued e.g. sys_read at.
+ *
+ * The buffer is always NUL terminated, unless it's zero-sized.
+ * Return
+ * Number of character copied (not including the trailing NUL).
+ *
+ * **-E2BIG** if the buffer wasn't big enough (*buf* will contain
+ * truncated name in this case).
+ *
+ * **-EINVAL** if current value was unavailable, e.g. because
+ * sysctl is uninitialized and read returns -EIO for it.
+ *
+ * int bpf_sysctl_get_new_value(struct bpf_sysctl *ctx, char *buf, size_t buf_len)
+ * Description
+ * Get new value being written by user space to sysctl (before
+ * the actual write happens) and copy it as a string into
+ * provided by program buffer *buf* of size *buf_len*.
+ *
+ * User space may write new value at file position > 0.
+ *
+ * The buffer is always NUL terminated, unless it's zero-sized.
+ * Return
+ * Number of character copied (not including the trailing NUL).
+ *
+ * **-E2BIG** if the buffer wasn't big enough (*buf* will contain
+ * truncated name in this case).
+ *
+ * **-EINVAL** if sysctl is being read.
+ *
+ * int bpf_sysctl_set_new_value(struct bpf_sysctl *ctx, const char *buf, size_t buf_len)
+ * Description
+ * Override new value being written by user space to sysctl with
+ * value provided by program in buffer *buf* of size *buf_len*.
+ *
+ * *buf* should contain a string in same form as provided by user
+ * space on sysctl write.
+ *
+ * User space may write new value at file position > 0. To override
+ * the whole sysctl value file position should be set to zero.
+ * Return
+ * 0 on success.
+ *
+ * **-E2BIG** if the *buf_len* is too big.
+ *
+ * **-EINVAL** if sysctl is being read.
+ *
+ * int bpf_strtol(const char *buf, size_t buf_len, u64 flags, long *res)
+ * Description
+ * Convert the initial part of the string from buffer *buf* of
+ * size *buf_len* to a long integer according to the given base
+ * and save the result in *res*.
+ *
+ * The string may begin with an arbitrary amount of white space
+ * (as determined by isspace(3)) followed by a single optional '-'
+ * sign.
+ *
+ * Five least significant bits of *flags* encode base, other bits
+ * are currently unused.
+ *
+ * Base must be either 8, 10, 16 or 0 to detect it automatically
+ * similar to user space strtol(3).
+ * Return
+ * Number of characters consumed on success. Must be positive but
+ * no more than buf_len.
+ *
+ * **-EINVAL** if no valid digits were found or unsupported base
+ * was provided.
+ *
+ * **-ERANGE** if resulting value was out of range.
+ *
+ * int bpf_strtoul(const char *buf, size_t buf_len, u64 flags, unsigned long *res)
+ * Description
+ * Convert the initial part of the string from buffer *buf* of
+ * size *buf_len* to an unsigned long integer according to the
+ * given base and save the result in *res*.
+ *
+ * The string may begin with an arbitrary amount of white space
+ * (as determined by isspace(3)).
+ *
+ * Five least significant bits of *flags* encode base, other bits
+ * are currently unused.
+ *
+ * Base must be either 8, 10, 16 or 0 to detect it automatically
+ * similar to user space strtoul(3).
+ * Return
+ * Number of characters consumed on success. Must be positive but
+ * no more than buf_len.
+ *
+ * **-EINVAL** if no valid digits were found or unsupported base
+ * was provided.
+ *
+ * **-ERANGE** if resulting value was out of range.
+ *
+ * void *bpf_sk_storage_get(struct bpf_map *map, struct bpf_sock *sk, void *value, u64 flags)
+ * Description
+ * Get a bpf-local-storage from a sk.
+ *
+ * Logically, it could be thought of getting the value from
+ * a *map* with *sk* as the **key**. From this
+ * perspective, the usage is not much different from
+ * **bpf_map_lookup_elem(map, &sk)** except this
+ * helper enforces the key must be a **bpf_fullsock()**
+ * and the map must be a BPF_MAP_TYPE_SK_STORAGE also.
+ *
+ * Underneath, the value is stored locally at *sk* instead of
+ * the map. The *map* is used as the bpf-local-storage **type**.
+ * The bpf-local-storage **type** (i.e. the *map*) is searched
+ * against all bpf-local-storages residing at sk.
+ *
+ * An optional *flags* (BPF_SK_STORAGE_GET_F_CREATE) can be
+ * used such that a new bpf-local-storage will be
+ * created if one does not exist. *value* can be used
+ * together with BPF_SK_STORAGE_GET_F_CREATE to specify
+ * the initial value of a bpf-local-storage. If *value* is
+ * NULL, the new bpf-local-storage will be zero initialized.
+ * Return
+ * A bpf-local-storage pointer is returned on success.
+ *
+ * **NULL** if not found or there was an error in adding
+ * a new bpf-local-storage.
+ *
+ * int bpf_sk_storage_delete(struct bpf_map *map, struct bpf_sock *sk)
+ * Description
+ * Delete a bpf-local-storage from a sk.
+ * Return
+ * 0 on success.
+ *
+ * **-ENOENT** if the bpf-local-storage cannot be found.
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
@@ -2465,7 +2766,18 @@ union bpf_attr {
FN(spin_unlock), \
FN(sk_fullsock), \
FN(tcp_sock), \
- FN(skb_ecn_set_ce),
+ FN(skb_ecn_set_ce), \
+ FN(get_listener_sock), \
+ FN(skc_lookup_tcp), \
+ FN(tcp_check_syncookie), \
+ FN(sysctl_get_name), \
+ FN(sysctl_get_current_value), \
+ FN(sysctl_get_new_value), \
+ FN(sysctl_set_new_value), \
+ FN(strtol), \
+ FN(strtoul), \
+ FN(sk_storage_get), \
+ FN(sk_storage_delete),
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
* function eBPF program intends to call
@@ -2524,9 +2836,30 @@ enum bpf_func_id {
/* Current network namespace */
#define BPF_F_CURRENT_NETNS (-1L)
+/* BPF_FUNC_skb_adjust_room flags. */
+#define BPF_F_ADJ_ROOM_FIXED_GSO (1ULL << 0)
+
+#define BPF_ADJ_ROOM_ENCAP_L2_MASK 0xff
+#define BPF_ADJ_ROOM_ENCAP_L2_SHIFT 56
+
+#define BPF_F_ADJ_ROOM_ENCAP_L3_IPV4 (1ULL << 1)
+#define BPF_F_ADJ_ROOM_ENCAP_L3_IPV6 (1ULL << 2)
+#define BPF_F_ADJ_ROOM_ENCAP_L4_GRE (1ULL << 3)
+#define BPF_F_ADJ_ROOM_ENCAP_L4_UDP (1ULL << 4)
+#define BPF_F_ADJ_ROOM_ENCAP_L2(len) (((__u64)len & \
+ BPF_ADJ_ROOM_ENCAP_L2_MASK) \
+ << BPF_ADJ_ROOM_ENCAP_L2_SHIFT)
+
+/* BPF_FUNC_sysctl_get_name flags. */
+#define BPF_F_SYSCTL_BASE_NAME (1ULL << 0)
+
+/* BPF_FUNC_sk_storage_get flags */
+#define BPF_SK_STORAGE_GET_F_CREATE (1ULL << 0)
+
/* Mode for BPF_FUNC_skb_adjust_room helper. */
enum bpf_adj_room_mode {
BPF_ADJ_ROOM_NET,
+ BPF_ADJ_ROOM_MAC,
};
/* Mode for BPF_FUNC_skb_load_bytes_relative helper. */
@@ -3152,4 +3485,14 @@ struct bpf_line_info {
struct bpf_spin_lock {
__u32 val;
};
+
+struct bpf_sysctl {
+ __u32 write; /* Sysctl is being read (= 0) or written (= 1).
+ * Allows 1,2,4-byte read, but no write.
+ */
+ __u32 file_pos; /* Sysctl file position to read from, write to.
+ * Allows 1,2,4-byte read an 4-byte write.
+ */
+};
+
#endif /* _UAPI__LINUX_BPF_H__ */
diff --git a/tools/include/uapi/linux/btf.h b/tools/include/uapi/linux/btf.h
index 7b7475ef2f17..9310652ca4f9 100644
--- a/tools/include/uapi/linux/btf.h
+++ b/tools/include/uapi/linux/btf.h
@@ -39,11 +39,11 @@ struct btf_type {
* struct, union and fwd
*/
__u32 info;
- /* "size" is used by INT, ENUM, STRUCT and UNION.
+ /* "size" is used by INT, ENUM, STRUCT, UNION and DATASEC.
* "size" tells the size of the type it is describing.
*
* "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT,
- * FUNC and FUNC_PROTO.
+ * FUNC, FUNC_PROTO and VAR.
* "type" is a type_id referring to another type.
*/
union {
@@ -70,8 +70,10 @@ struct btf_type {
#define BTF_KIND_RESTRICT 11 /* Restrict */
#define BTF_KIND_FUNC 12 /* Function */
#define BTF_KIND_FUNC_PROTO 13 /* Function Proto */
-#define BTF_KIND_MAX 13
-#define NR_BTF_KINDS 14
+#define BTF_KIND_VAR 14 /* Variable */
+#define BTF_KIND_DATASEC 15 /* Section */
+#define BTF_KIND_MAX BTF_KIND_DATASEC
+#define NR_BTF_KINDS (BTF_KIND_MAX + 1)
/* For some specific BTF_KIND, "struct btf_type" is immediately
* followed by extra data.
@@ -138,4 +140,26 @@ struct btf_param {
__u32 type;
};
+enum {
+ BTF_VAR_STATIC = 0,
+ BTF_VAR_GLOBAL_ALLOCATED,
+};
+
+/* BTF_KIND_VAR is followed by a single "struct btf_var" to describe
+ * additional information related to the variable such as its linkage.
+ */
+struct btf_var {
+ __u32 linkage;
+};
+
+/* BTF_KIND_DATASEC is followed by multiple "struct btf_var_secinfo"
+ * to describe all BTF_KIND_VAR types it contains along with it's
+ * in-section offset as well as size.
+ */
+struct btf_var_secinfo {
+ __u32 type;
+ __u32 offset;
+ __u32 size;
+};
+
#endif /* _UAPI__LINUX_BTF_H__ */
diff --git a/tools/include/uapi/linux/fcntl.h b/tools/include/uapi/linux/fcntl.h
index 6448cdd9a350..a2f8658f1c55 100644
--- a/tools/include/uapi/linux/fcntl.h
+++ b/tools/include/uapi/linux/fcntl.h
@@ -41,6 +41,7 @@
#define F_SEAL_SHRINK 0x0002 /* prevent file from shrinking */
#define F_SEAL_GROW 0x0004 /* prevent file from growing */
#define F_SEAL_WRITE 0x0008 /* prevent writes */
+#define F_SEAL_FUTURE_WRITE 0x0010 /* prevent future writes while mapped */
/* (1U << 31) is reserved for signed error codes */
/*
diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h
index a55cb8b10165..e7ad9d350a28 100644
--- a/tools/include/uapi/linux/in.h
+++ b/tools/include/uapi/linux/in.h
@@ -292,10 +292,11 @@ struct sockaddr_in {
#define IN_LOOPBACK(a) ((((long int) (a)) & 0xff000000) == 0x7f000000)
/* Defines for Multicast INADDR */
-#define INADDR_UNSPEC_GROUP 0xe0000000U /* 224.0.0.0 */
-#define INADDR_ALLHOSTS_GROUP 0xe0000001U /* 224.0.0.1 */
-#define INADDR_ALLRTRS_GROUP 0xe0000002U /* 224.0.0.2 */
-#define INADDR_MAX_LOCAL_GROUP 0xe00000ffU /* 224.0.0.255 */
+#define INADDR_UNSPEC_GROUP 0xe0000000U /* 224.0.0.0 */
+#define INADDR_ALLHOSTS_GROUP 0xe0000001U /* 224.0.0.1 */
+#define INADDR_ALLRTRS_GROUP 0xe0000002U /* 224.0.0.2 */
+#define INADDR_ALLSNOOPERS_GROUP 0xe000006aU /* 224.0.0.106 */
+#define INADDR_MAX_LOCAL_GROUP 0xe00000ffU /* 224.0.0.255 */
#endif
/* <asm/byteorder.h> contains the htonl type stuff.. */
diff --git a/tools/include/uapi/linux/mman.h b/tools/include/uapi/linux/mman.h
index d0f515d53299..fc1a64c3447b 100644
--- a/tools/include/uapi/linux/mman.h
+++ b/tools/include/uapi/linux/mman.h
@@ -12,6 +12,10 @@
#define OVERCOMMIT_ALWAYS 1
#define OVERCOMMIT_NEVER 2
+#define MAP_SHARED 0x01 /* Share changes */
+#define MAP_PRIVATE 0x02 /* Changes are private */
+#define MAP_SHARED_VALIDATE 0x03 /* share + validate extension flags */
+
/*
* Huge page size encoding when MAP_HUGETLB is specified, and a huge page
* size other than the default is desired. See hugetlb_encode.h.
diff --git a/tools/include/uapi/sound/asound.h b/tools/include/uapi/sound/asound.h
index 404d4b9ffe76..df1153cea0b7 100644
--- a/tools/include/uapi/sound/asound.h
+++ b/tools/include/uapi/sound/asound.h
@@ -32,6 +32,7 @@
#ifndef __KERNEL__
#include <stdlib.h>
+#include <time.h>
#endif
/*
diff --git a/tools/io_uring/io_uring-bench.c b/tools/io_uring/io_uring-bench.c
index 512306a37531..0f257139b003 100644
--- a/tools/io_uring/io_uring-bench.c
+++ b/tools/io_uring/io_uring-bench.c
@@ -32,10 +32,6 @@
#include "liburing.h"
#include "barrier.h"
-#ifndef IOCQE_FLAG_CACHEHIT
-#define IOCQE_FLAG_CACHEHIT (1U << 0)
-#endif
-
#define min(a, b) ((a < b) ? (a) : (b))
struct io_sq_ring {
@@ -85,7 +81,6 @@ struct submitter {
unsigned long reaps;
unsigned long done;
unsigned long calls;
- unsigned long cachehit, cachemiss;
volatile int finish;
__s32 *fds;
@@ -270,10 +265,6 @@ static int reap_events(struct submitter *s)
return -1;
}
}
- if (cqe->flags & IOCQE_FLAG_CACHEHIT)
- s->cachehit++;
- else
- s->cachemiss++;
reaped++;
head++;
} while (1);
@@ -489,7 +480,7 @@ static void file_depths(char *buf)
int main(int argc, char *argv[])
{
struct submitter *s = &submitters[0];
- unsigned long done, calls, reap, cache_hit, cache_miss;
+ unsigned long done, calls, reap;
int err, i, flags, fd;
char *fdepths;
void *ret;
@@ -569,44 +560,29 @@ int main(int argc, char *argv[])
pthread_create(&s->thread, NULL, submitter_fn, s);
fdepths = malloc(8 * s->nr_files);
- cache_hit = cache_miss = reap = calls = done = 0;
+ reap = calls = done = 0;
do {
unsigned long this_done = 0;
unsigned long this_reap = 0;
unsigned long this_call = 0;
- unsigned long this_cache_hit = 0;
- unsigned long this_cache_miss = 0;
unsigned long rpc = 0, ipc = 0;
- double hit = 0.0;
sleep(1);
this_done += s->done;
this_call += s->calls;
this_reap += s->reaps;
- this_cache_hit += s->cachehit;
- this_cache_miss += s->cachemiss;
- if (this_cache_hit && this_cache_miss) {
- unsigned long hits, total;
-
- hits = this_cache_hit - cache_hit;
- total = hits + this_cache_miss - cache_miss;
- hit = (double) hits / (double) total;
- hit *= 100.0;
- }
if (this_call - calls) {
rpc = (this_done - done) / (this_call - calls);
ipc = (this_reap - reap) / (this_call - calls);
} else
rpc = ipc = -1;
file_depths(fdepths);
- printf("IOPS=%lu, IOS/call=%ld/%ld, inflight=%u (%s), Cachehit=%0.2f%%\n",
+ printf("IOPS=%lu, IOS/call=%ld/%ld, inflight=%u (%s)\n",
this_done - done, rpc, ipc, s->inflight,
- fdepths, hit);
+ fdepths);
done = this_done;
calls = this_call;
reap = this_reap;
- cache_hit = s->cachehit;
- cache_miss = s->cachemiss;
} while (!finish);
pthread_join(s->thread, &ret);
diff --git a/tools/lib/bpf/.gitignore b/tools/lib/bpf/.gitignore
index 4db74758c674..d9e9dec04605 100644
--- a/tools/lib/bpf/.gitignore
+++ b/tools/lib/bpf/.gitignore
@@ -1,3 +1,5 @@
libbpf_version.h
+libbpf.pc
FEATURE-DUMP.libbpf
test_libbpf
+libbpf.so.*
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index 61aaacf0cfa1..f91639bf5650 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -3,7 +3,7 @@
BPF_VERSION = 0
BPF_PATCHLEVEL = 0
-BPF_EXTRAVERSION = 1
+BPF_EXTRAVERSION = 3
MAKEFLAGS += --no-print-directory
@@ -79,8 +79,6 @@ export prefix libdir src obj
libdir_SQ = $(subst ','\'',$(libdir))
libdir_relative_SQ = $(subst ','\'',$(libdir_relative))
-LIB_FILE = libbpf.a libbpf.so
-
VERSION = $(BPF_VERSION)
PATCHLEVEL = $(BPF_PATCHLEVEL)
EXTRAVERSION = $(BPF_EXTRAVERSION)
@@ -88,7 +86,11 @@ EXTRAVERSION = $(BPF_EXTRAVERSION)
OBJ = $@
N =
-LIBBPF_VERSION = $(BPF_VERSION).$(BPF_PATCHLEVEL).$(BPF_EXTRAVERSION)
+LIBBPF_VERSION = $(BPF_VERSION).$(BPF_PATCHLEVEL).$(BPF_EXTRAVERSION)
+
+LIB_TARGET = libbpf.a libbpf.so.$(LIBBPF_VERSION)
+LIB_FILE = libbpf.a libbpf.so*
+PC_FILE = libbpf.pc
# Set compile option CFLAGS
ifdef EXTRA_CFLAGS
@@ -128,16 +130,19 @@ all:
export srctree OUTPUT CC LD CFLAGS V
include $(srctree)/tools/build/Makefile.include
-BPF_IN := $(OUTPUT)libbpf-in.o
-LIB_FILE := $(addprefix $(OUTPUT),$(LIB_FILE))
-VERSION_SCRIPT := libbpf.map
+BPF_IN := $(OUTPUT)libbpf-in.o
+VERSION_SCRIPT := libbpf.map
+
+LIB_TARGET := $(addprefix $(OUTPUT),$(LIB_TARGET))
+LIB_FILE := $(addprefix $(OUTPUT),$(LIB_FILE))
+PC_FILE := $(addprefix $(OUTPUT),$(PC_FILE))
GLOBAL_SYM_COUNT = $(shell readelf -s --wide $(BPF_IN) | \
awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {s++} END{print s}')
VERSIONED_SYM_COUNT = $(shell readelf -s --wide $(OUTPUT)libbpf.so | \
grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 | sort -u | wc -l)
-CMD_TARGETS = $(LIB_FILE)
+CMD_TARGETS = $(LIB_TARGET) $(PC_FILE)
CXX_TEST_TARGET = $(OUTPUT)test_libbpf
@@ -170,9 +175,13 @@ $(BPF_IN): force elfdep bpfdep
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)libbpf.so: $(BPF_IN)
- $(QUIET_LINK)$(CC) --shared -Wl,--version-script=$(VERSION_SCRIPT) \
- $^ -o $@
+$(OUTPUT)libbpf.so: $(OUTPUT)libbpf.so.$(LIBBPF_VERSION)
+
+$(OUTPUT)libbpf.so.$(LIBBPF_VERSION): $(BPF_IN)
+ $(QUIET_LINK)$(CC) --shared -Wl,-soname,libbpf.so.$(VERSION) \
+ -Wl,--version-script=$(VERSION_SCRIPT) $^ -lelf -o $@
+ @ln -sf $(@F) $(OUTPUT)libbpf.so
+ @ln -sf $(@F) $(OUTPUT)libbpf.so.$(VERSION)
$(OUTPUT)libbpf.a: $(BPF_IN)
$(QUIET_LINK)$(RM) $@; $(AR) rcs $@ $^
@@ -180,6 +189,12 @@ $(OUTPUT)libbpf.a: $(BPF_IN)
$(OUTPUT)test_libbpf: test_libbpf.cpp $(OUTPUT)libbpf.a
$(QUIET_LINK)$(CXX) $(INCLUDES) $^ -lelf -o $@
+$(OUTPUT)libbpf.pc:
+ $(QUIET_GEN)sed -e "s|@PREFIX@|$(prefix)|" \
+ -e "s|@LIBDIR@|$(libdir_SQ)|" \
+ -e "s|@VERSION@|$(LIBBPF_VERSION)|" \
+ < libbpf.pc.template > $@
+
check: check_abi
check_abi: $(OUTPUT)libbpf.so
@@ -192,6 +207,12 @@ check_abi: $(OUTPUT)libbpf.so
exit 1; \
fi
+define do_install_mkdir
+ if [ ! -d '$(DESTDIR_SQ)$1' ]; then \
+ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$1'; \
+ fi
+endef
+
define do_install
if [ ! -d '$(DESTDIR_SQ)$2' ]; then \
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$2'; \
@@ -200,16 +221,23 @@ define do_install
endef
install_lib: all_cmd
- $(call QUIET_INSTALL, $(LIB_FILE)) \
- $(call do_install,$(LIB_FILE),$(libdir_SQ))
+ $(call QUIET_INSTALL, $(LIB_TARGET)) \
+ $(call do_install_mkdir,$(libdir_SQ)); \
+ cp -fpR $(LIB_FILE) $(DESTDIR)$(libdir_SQ)
install_headers:
$(call QUIET_INSTALL, headers) \
$(call do_install,bpf.h,$(prefix)/include/bpf,644); \
- $(call do_install,libbpf.h,$(prefix)/include/bpf,644);
- $(call do_install,btf.h,$(prefix)/include/bpf,644);
+ $(call do_install,libbpf.h,$(prefix)/include/bpf,644); \
+ $(call do_install,btf.h,$(prefix)/include/bpf,644); \
+ $(call do_install,libbpf_util.h,$(prefix)/include/bpf,644); \
+ $(call do_install,xsk.h,$(prefix)/include/bpf,644);
+
+install_pkgconfig: $(PC_FILE)
+ $(call QUIET_INSTALL, $(PC_FILE)) \
+ $(call do_install,$(PC_FILE),$(libdir_SQ)/pkgconfig,644)
-install: install_lib
+install: install_lib install_pkgconfig
### Cleaning rules
@@ -219,7 +247,7 @@ config-clean:
clean:
$(call QUIET_CLEAN, libbpf) $(RM) $(TARGETS) $(CXX_TEST_TARGET) \
- *.o *~ *.a *.so .*.d .*.cmd LIBBPF-CFLAGS
+ *.o *~ *.a *.so *.so.$(VERSION) .*.d .*.cmd *.pc LIBBPF-CFLAGS
$(call QUIET_CLEAN, core-gen) $(RM) $(OUTPUT)FEATURE-DUMP.libbpf
diff --git a/tools/lib/bpf/README.rst b/tools/lib/bpf/README.rst
index 5788479384ca..cef7b77eab69 100644
--- a/tools/lib/bpf/README.rst
+++ b/tools/lib/bpf/README.rst
@@ -111,6 +111,7 @@ starting from ``0.0.1``.
Every time ABI is being changed, e.g. because a new symbol is added or
semantic of existing symbol is changed, ABI version should be bumped.
+This bump in ABI version is at most once per kernel development cycle.
For example, if current state of ``libbpf.map`` is:
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 9cd015574e83..c4a48086dc9a 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -46,6 +46,8 @@
# define __NR_bpf 349
# elif defined(__s390__)
# define __NR_bpf 351
+# elif defined(__arc__)
+# define __NR_bpf 280
# else
# error __NR_bpf not defined. libbpf does not support your arch.
# endif
@@ -79,7 +81,6 @@ static inline int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size)
int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr)
{
- __u32 name_len = create_attr->name ? strlen(create_attr->name) : 0;
union bpf_attr attr;
memset(&attr, '\0', sizeof(attr));
@@ -89,8 +90,9 @@ int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr)
attr.value_size = create_attr->value_size;
attr.max_entries = create_attr->max_entries;
attr.map_flags = create_attr->map_flags;
- memcpy(attr.map_name, create_attr->name,
- min(name_len, BPF_OBJ_NAME_LEN - 1));
+ 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;
@@ -155,7 +157,6 @@ 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)
{
- __u32 name_len = name ? strlen(name) : 0;
union bpf_attr attr;
memset(&attr, '\0', sizeof(attr));
@@ -166,7 +167,9 @@ int bpf_create_map_in_map_node(enum bpf_map_type map_type, const char *name,
attr.inner_map_fd = inner_map_fd;
attr.max_entries = max_entries;
attr.map_flags = map_flags;
- memcpy(attr.map_name, name, min(name_len, BPF_OBJ_NAME_LEN - 1));
+ if (name)
+ memcpy(attr.map_name, name,
+ min(strlen(name), BPF_OBJ_NAME_LEN - 1));
if (node >= 0) {
attr.map_flags |= BPF_F_NUMA_NODE;
@@ -216,18 +219,15 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
void *finfo = NULL, *linfo = NULL;
union bpf_attr attr;
__u32 log_level;
- __u32 name_len;
int fd;
if (!load_attr || !log_buf != !log_buf_sz)
return -EINVAL;
log_level = load_attr->log_level;
- if (log_level > 2 || (log_level && !log_buf))
+ if (log_level > (4 | 2 | 1) || (log_level && !log_buf))
return -EINVAL;
- name_len = load_attr->name ? strlen(load_attr->name) : 0;
-
memset(&attr, 0, sizeof(attr));
attr.prog_type = load_attr->prog_type;
attr.expected_attach_type = load_attr->expected_attach_type;
@@ -253,8 +253,9 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
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);
- memcpy(attr.prog_name, load_attr->name,
- min(name_len, BPF_OBJ_NAME_LEN - 1));
+ if (load_attr->name)
+ memcpy(attr.prog_name, load_attr->name,
+ min(strlen(load_attr->name), BPF_OBJ_NAME_LEN - 1));
fd = sys_bpf_prog_load(&attr, sizeof(attr));
if (fd >= 0)
@@ -429,6 +430,16 @@ int bpf_map_get_next_key(int fd, const void *key, void *next_key)
return sys_bpf(BPF_MAP_GET_NEXT_KEY, &attr, sizeof(attr));
}
+int bpf_map_freeze(int fd)
+{
+ union bpf_attr attr;
+
+ memset(&attr, 0, sizeof(attr));
+ attr.map_fd = fd;
+
+ return sys_bpf(BPF_MAP_FREEZE, &attr, sizeof(attr));
+}
+
int bpf_obj_pin(int fd, const char *pathname)
{
union bpf_attr attr;
@@ -545,10 +556,15 @@ int bpf_prog_test_run_xattr(struct bpf_prog_test_run_attr *test_attr)
attr.test.data_out = ptr_to_u64(test_attr->data_out);
attr.test.data_size_in = test_attr->data_size_in;
attr.test.data_size_out = test_attr->data_size_out;
+ attr.test.ctx_in = ptr_to_u64(test_attr->ctx_in);
+ attr.test.ctx_out = ptr_to_u64(test_attr->ctx_out);
+ attr.test.ctx_size_in = test_attr->ctx_size_in;
+ attr.test.ctx_size_out = test_attr->ctx_size_out;
attr.test.repeat = test_attr->repeat;
ret = sys_bpf(BPF_PROG_TEST_RUN, &attr, sizeof(attr));
test_attr->data_size_out = attr.test.data_size_out;
+ test_attr->ctx_size_out = attr.test.ctx_size_out;
test_attr->retval = attr.test.retval;
test_attr->duration = attr.test.duration;
return ret;
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 6ffdd79bea89..9593fec75652 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -26,6 +26,7 @@
#include <linux/bpf.h>
#include <stdbool.h>
#include <stddef.h>
+#include <stdint.h>
#ifdef __cplusplus
extern "C" {
@@ -92,7 +93,7 @@ struct bpf_load_program_attr {
#define MAPS_RELAX_COMPAT 0x01
/* Recommend log buffer size */
-#define BPF_LOG_BUF_SIZE (256 * 1024)
+#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);
@@ -117,6 +118,7 @@ LIBBPF_API int bpf_map_lookup_and_delete_elem(int fd, const void *key,
void *value);
LIBBPF_API int bpf_map_delete_elem(int fd, const void *key);
LIBBPF_API int bpf_map_get_next_key(int fd, const void *key, void *next_key);
+LIBBPF_API int bpf_map_freeze(int fd);
LIBBPF_API int bpf_obj_pin(int fd, const char *pathname);
LIBBPF_API int bpf_obj_get(const char *pathname);
LIBBPF_API int bpf_prog_attach(int prog_fd, int attachable_fd,
@@ -135,6 +137,11 @@ struct bpf_prog_test_run_attr {
* out: length of data_out */
__u32 retval; /* out: return code of the BPF program */
__u32 duration; /* out: average per repetition in ns */
+ const void *ctx_in; /* optional */
+ __u32 ctx_size_in;
+ void *ctx_out; /* optional */
+ __u32 ctx_size_out; /* in: max length of ctx_out
+ * out: length of cxt_out */
};
LIBBPF_API int bpf_prog_test_run_xattr(struct bpf_prog_test_run_attr *test_attr);
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 1b8d8cdd3575..75eaf10b9e1a 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -24,6 +24,8 @@
((k) == BTF_KIND_CONST) || \
((k) == BTF_KIND_RESTRICT))
+#define IS_VAR(k) ((k) == BTF_KIND_VAR)
+
static struct btf_type btf_void;
struct btf {
@@ -212,6 +214,10 @@ static int btf_type_size(struct btf_type *t)
return base_size + vlen * sizeof(struct btf_member);
case BTF_KIND_FUNC_PROTO:
return base_size + vlen * sizeof(struct btf_param);
+ case BTF_KIND_VAR:
+ return base_size + sizeof(struct btf_var);
+ case BTF_KIND_DATASEC:
+ return base_size + vlen * sizeof(struct btf_var_secinfo);
default:
pr_debug("Unsupported BTF_KIND:%u\n", BTF_INFO_KIND(t->info));
return -EINVAL;
@@ -283,6 +289,7 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id)
case BTF_KIND_STRUCT:
case BTF_KIND_UNION:
case BTF_KIND_ENUM:
+ case BTF_KIND_DATASEC:
size = t->size;
goto done;
case BTF_KIND_PTR:
@@ -292,6 +299,7 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id)
case BTF_KIND_VOLATILE:
case BTF_KIND_CONST:
case BTF_KIND_RESTRICT:
+ case BTF_KIND_VAR:
type_id = t->type;
break;
case BTF_KIND_ARRAY:
@@ -326,7 +334,8 @@ int btf__resolve_type(const struct btf *btf, __u32 type_id)
t = btf__type_by_id(btf, type_id);
while (depth < MAX_RESOLVE_DEPTH &&
!btf_type_is_void_or_null(t) &&
- IS_MODIFIER(BTF_INFO_KIND(t->info))) {
+ (IS_MODIFIER(BTF_INFO_KIND(t->info)) ||
+ IS_VAR(BTF_INFO_KIND(t->info)))) {
type_id = t->type;
t = btf__type_by_id(btf, type_id);
depth++;
@@ -408,6 +417,92 @@ done:
return btf;
}
+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_INFO_VLEN(t->info);
+ const char *name = btf__name_by_offset(btf, t->name_off);
+ const struct btf_type *t_var;
+ struct btf_var_secinfo *vsi;
+ struct btf_var *var;
+ int ret;
+
+ if (!name) {
+ pr_debug("No name found in string section for DATASEC kind.\n");
+ return -ENOENT;
+ }
+
+ 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 = (struct btf_var_secinfo *)(t + 1);
+ i < vars; i++, vsi++) {
+ t_var = btf__type_by_id(btf, vsi->type);
+ var = (struct btf_var *)(t_var + 1);
+
+ if (BTF_INFO_KIND(t_var->info) != BTF_KIND_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;
+ }
+
+ qsort(t + 1, 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->types[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_INFO_KIND(t->info) == BTF_KIND_DATASEC) {
+ err = btf_fixup_datasec(obj, btf, t);
+ if (err)
+ break;
+ }
+ }
+
+ return err;
+}
+
int btf__load(struct btf *btf)
{
__u32 log_buf_size = BPF_LOG_BUF_SIZE;
@@ -1259,8 +1354,16 @@ static struct btf_dedup *btf_dedup_new(struct btf *btf, struct btf_ext *btf_ext,
}
/* special BTF "void" type is made canonical immediately */
d->map[0] = 0;
- for (i = 1; i <= btf->nr_types; i++)
- d->map[i] = BTF_UNPROCESSED_ID;
+ for (i = 1; i <= btf->nr_types; i++) {
+ struct btf_type *t = d->btf->types[i];
+ __u16 kind = BTF_INFO_KIND(t->info);
+
+ /* VAR and DATASEC are never deduped and are self-canonical */
+ if (kind == BTF_KIND_VAR || kind == BTF_KIND_DATASEC)
+ d->map[i] = i;
+ else
+ d->map[i] = BTF_UNPROCESSED_ID;
+ }
d->hypot_map = malloc(sizeof(__u32) * (1 + btf->nr_types));
if (!d->hypot_map) {
@@ -1602,16 +1705,12 @@ static bool btf_equal_int(struct btf_type *t1, struct btf_type *t2)
/* Calculate type signature hash of ENUM. */
static __u32 btf_hash_enum(struct btf_type *t)
{
- struct btf_enum *member = (struct btf_enum *)(t + 1);
- __u32 vlen = BTF_INFO_VLEN(t->info);
- __u32 h = btf_hash_common(t);
- int i;
+ __u32 h;
- for (i = 0; i < vlen; i++) {
- h = hash_combine(h, member->name_off);
- h = hash_combine(h, member->val);
- member++;
- }
+ /* don't hash vlen and enum members to support enum fwd resolving */
+ h = hash_combine(0, t->name_off);
+ h = hash_combine(h, t->info & ~0xffff);
+ h = hash_combine(h, t->size);
return h;
}
@@ -1637,6 +1736,22 @@ static bool btf_equal_enum(struct btf_type *t1, struct btf_type *t2)
return true;
}
+static inline bool btf_is_enum_fwd(struct btf_type *t)
+{
+ return BTF_INFO_KIND(t->info) == BTF_KIND_ENUM &&
+ BTF_INFO_VLEN(t->info) == 0;
+}
+
+static bool btf_compat_enum(struct btf_type *t1, struct btf_type *t2)
+{
+ if (!btf_is_enum_fwd(t1) && !btf_is_enum_fwd(t2))
+ return btf_equal_enum(t1, t2);
+ /* ignore vlen when comparing */
+ return t1->name_off == t2->name_off &&
+ (t1->info & ~0xffff) == (t2->info & ~0xffff) &&
+ t1->size == t2->size;
+}
+
/*
* Calculate type signature hash of STRUCT/UNION, ignoring referenced type IDs,
* as referenced type IDs equivalence is established separately during type
@@ -1839,6 +1954,8 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id)
case BTF_KIND_UNION:
case BTF_KIND_FUNC:
case BTF_KIND_FUNC_PROTO:
+ case BTF_KIND_VAR:
+ case BTF_KIND_DATASEC:
return 0;
case BTF_KIND_INT:
@@ -1860,6 +1977,17 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id)
new_id = cand_node->type_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 */
+ new_id = cand_node->type_id;
+ break;
+ }
+ /* resolve canonical enum fwd to full enum */
+ d->map[cand_node->type_id] = type_id;
+ }
}
break;
@@ -2084,7 +2212,7 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id,
return fwd_kind == real_kind;
}
- if (cand_type->info != canon_type->info)
+ if (cand_kind != canon_kind)
return 0;
switch (cand_kind) {
@@ -2092,7 +2220,10 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id,
return btf_equal_int(cand_type, canon_type);
case BTF_KIND_ENUM:
- return btf_equal_enum(cand_type, canon_type);
+ if (d->opts.dont_resolve_fwds)
+ return btf_equal_enum(cand_type, canon_type);
+ else
+ return btf_compat_enum(cand_type, canon_type);
case BTF_KIND_FWD:
return btf_equal_common(cand_type, canon_type);
@@ -2103,6 +2234,8 @@ 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:
+ if (cand_type->info != canon_type->info)
+ return 0;
return btf_dedup_is_equiv(d, cand_type->type, canon_type->type);
case BTF_KIND_ARRAY: {
@@ -2576,6 +2709,7 @@ static int btf_dedup_remap_type(struct btf_dedup *d, __u32 type_id)
case BTF_KIND_PTR:
case BTF_KIND_TYPEDEF:
case BTF_KIND_FUNC:
+ case BTF_KIND_VAR:
r = btf_dedup_remap_type_id(d, t->type);
if (r < 0)
return r;
@@ -2630,6 +2764,20 @@ static int btf_dedup_remap_type(struct btf_dedup *d, __u32 type_id)
break;
}
+ case BTF_KIND_DATASEC: {
+ struct btf_var_secinfo *var = (struct btf_var_secinfo *)(t + 1);
+ __u16 vlen = BTF_INFO_VLEN(t->info);
+
+ for (i = 0; i < vlen; i++) {
+ r = btf_dedup_remap_type_id(d, var->type);
+ if (r < 0)
+ return r;
+ var->type = r;
+ var++;
+ }
+ break;
+ }
+
default:
return -EINVAL;
}
diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h
index 28a1e1e59861..c7b399e81fce 100644
--- a/tools/lib/bpf/btf.h
+++ b/tools/lib/bpf/btf.h
@@ -21,6 +21,8 @@ struct btf;
struct btf_ext;
struct btf_type;
+struct bpf_object;
+
/*
* The .BTF.ext ELF section layout defined as
* struct btf_ext_header
@@ -57,6 +59,7 @@ struct btf_ext_header {
LIBBPF_API void btf__free(struct btf *btf);
LIBBPF_API struct btf *btf__new(__u8 *data, __u32 size);
+LIBBPF_API int btf__finalize_data(struct bpf_object *obj, struct btf *btf);
LIBBPF_API int btf__load(struct btf *btf);
LIBBPF_API __s32 btf__find_by_name(const struct btf *btf,
const char *type_name);
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index d5b830d60601..11a65db4b93f 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -7,6 +7,7 @@
* Copyright (C) 2015 Wang Nan <wangnan0@huawei.com>
* Copyright (C) 2015 Huawei Inc.
* Copyright (C) 2017 Nicira, Inc.
+ * Copyright (C) 2019 Isovalent, Inc.
*/
#ifndef _GNU_SOURCE
@@ -52,6 +53,11 @@
#define BPF_FS_MAGIC 0xcafe4a11
#endif
+/* vsprintf() in __base_pr() uses nonliteral format string. It may break
+ * compilation if user enables corresponding warning. Disable it explicitly.
+ */
+#pragma GCC diagnostic ignored "-Wformat-nonliteral"
+
#define __printf(a, b) __attribute__((format(printf, a, b)))
static int __base_pr(enum libbpf_print_level level, const char *format,
@@ -112,9 +118,16 @@ void libbpf_print(enum libbpf_print_level level, const char *format, ...)
# define LIBBPF_ELF_C_READ_MMAP ELF_C_READ
#endif
+static inline __u64 ptr_to_u64(const void *ptr)
+{
+ return (__u64) (unsigned long) ptr;
+}
+
struct bpf_capabilities {
/* v4.14: kernel support for program & map names. */
__u32 name:1;
+ /* v5.2: kernel support for global data sections. */
+ __u32 global_data:1;
};
/*
@@ -139,6 +152,7 @@ struct bpf_program {
enum {
RELO_LD64,
RELO_CALL,
+ RELO_DATA,
} type;
int insn_idx;
union {
@@ -147,6 +161,7 @@ struct bpf_program {
};
} *reloc_desc;
int nr_reloc;
+ int log_level;
struct {
int nr;
@@ -171,6 +186,19 @@ struct bpf_program {
__u32 line_info_cnt;
};
+enum libbpf_map_type {
+ LIBBPF_MAP_UNSPEC,
+ LIBBPF_MAP_DATA,
+ LIBBPF_MAP_BSS,
+ LIBBPF_MAP_RODATA,
+};
+
+static const char * const libbpf_type_to_btf_name[] = {
+ [LIBBPF_MAP_DATA] = ".data",
+ [LIBBPF_MAP_BSS] = ".bss",
+ [LIBBPF_MAP_RODATA] = ".rodata",
+};
+
struct bpf_map {
int fd;
char *name;
@@ -182,11 +210,18 @@ struct bpf_map {
__u32 btf_value_type_id;
void *priv;
bpf_map_clear_priv_t clear_priv;
+ enum libbpf_map_type libbpf_type;
+};
+
+struct bpf_secdata {
+ void *rodata;
+ void *data;
};
static LIST_HEAD(bpf_objects_list);
struct bpf_object {
+ char name[BPF_OBJ_NAME_LEN];
char license[64];
__u32 kern_version;
@@ -194,6 +229,7 @@ struct bpf_object {
size_t nr_programs;
struct bpf_map *maps;
size_t nr_maps;
+ struct bpf_secdata sections;
bool loaded;
bool has_pseudo_calls;
@@ -209,6 +245,9 @@ struct bpf_object {
Elf *elf;
GElf_Ehdr ehdr;
Elf_Data *symbols;
+ Elf_Data *data;
+ Elf_Data *rodata;
+ Elf_Data *bss;
size_t strtabidx;
struct {
GElf_Shdr shdr;
@@ -217,6 +256,9 @@ struct bpf_object {
int nr_reloc;
int maps_shndx;
int text_shndx;
+ int data_shndx;
+ int rodata_shndx;
+ int bss_shndx;
} efile;
/*
* All loaded bpf_object is linked in a list, which is
@@ -438,6 +480,7 @@ static struct bpf_object *bpf_object__new(const char *path,
size_t obj_buf_sz)
{
struct bpf_object *obj;
+ char *end;
obj = calloc(1, sizeof(struct bpf_object) + strlen(path) + 1);
if (!obj) {
@@ -446,8 +489,14 @@ static struct bpf_object *bpf_object__new(const char *path,
}
strcpy(obj->path, path);
- obj->efile.fd = -1;
+ /* Using basename() GNU version which doesn't modify arg. */
+ strncpy(obj->name, basename((void *)path),
+ sizeof(obj->name) - 1);
+ end = strchr(obj->name, '.');
+ if (end)
+ *end = 0;
+ obj->efile.fd = -1;
/*
* Caller of this function should also calls
* bpf_object__elf_finish() after data collection to return
@@ -457,6 +506,9 @@ static struct bpf_object *bpf_object__new(const char *path,
obj->efile.obj_buf = obj_buf;
obj->efile.obj_buf_sz = obj_buf_sz;
obj->efile.maps_shndx = -1;
+ obj->efile.data_shndx = -1;
+ obj->efile.rodata_shndx = -1;
+ obj->efile.bss_shndx = -1;
obj->loaded = false;
@@ -475,6 +527,9 @@ 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;
zfree(&obj->efile.reloc);
obj->efile.nr_reloc = 0;
@@ -616,27 +671,182 @@ static bool bpf_map_type__is_map_in_map(enum bpf_map_type type)
return false;
}
+static int bpf_object_search_section_size(const struct bpf_object *obj,
+ const char *name, size_t *d_size)
+{
+ const GElf_Ehdr *ep = &obj->efile.ehdr;
+ Elf *elf = obj->efile.elf;
+ Elf_Scn *scn = NULL;
+ int idx = 0;
+
+ while ((scn = elf_nextscn(elf, scn)) != NULL) {
+ const char *sec_name;
+ Elf_Data *data;
+ GElf_Shdr sh;
+
+ idx++;
+ if (gelf_getshdr(scn, &sh) != &sh) {
+ pr_warning("failed to get section(%d) header from %s\n",
+ idx, obj->path);
+ return -EIO;
+ }
+
+ sec_name = elf_strptr(elf, ep->e_shstrndx, sh.sh_name);
+ if (!sec_name) {
+ pr_warning("failed to get section(%d) name from %s\n",
+ idx, obj->path);
+ return -EIO;
+ }
+
+ if (strcmp(name, sec_name))
+ continue;
+
+ data = elf_getdata(scn, 0);
+ if (!data) {
+ pr_warning("failed to get section(%d) data from %s(%s)\n",
+ idx, name, obj->path);
+ return -EIO;
+ }
+
+ *d_size = data->d_size;
+ return 0;
+ }
+
+ return -ENOENT;
+}
+
+int bpf_object__section_size(const struct bpf_object *obj, const char *name,
+ __u32 *size)
+{
+ int ret = -ENOENT;
+ size_t d_size;
+
+ *size = 0;
+ if (!name) {
+ return -EINVAL;
+ } else if (!strcmp(name, ".data")) {
+ if (obj->efile.data)
+ *size = obj->efile.data->d_size;
+ } else if (!strcmp(name, ".bss")) {
+ if (obj->efile.bss)
+ *size = obj->efile.bss->d_size;
+ } else if (!strcmp(name, ".rodata")) {
+ if (obj->efile.rodata)
+ *size = obj->efile.rodata->d_size;
+ } else {
+ ret = bpf_object_search_section_size(obj, name, &d_size);
+ if (!ret)
+ *size = d_size;
+ }
+
+ return *size ? 0 : ret;
+}
+
+int bpf_object__variable_offset(const struct bpf_object *obj, const char *name,
+ __u32 *off)
+{
+ Elf_Data *symbols = obj->efile.symbols;
+ const char *sname;
+ size_t si;
+
+ if (!name || !off)
+ return -EINVAL;
+
+ for (si = 0; si < symbols->d_size / sizeof(GElf_Sym); si++) {
+ GElf_Sym sym;
+
+ if (!gelf_getsym(symbols, si, &sym))
+ continue;
+ if (GELF_ST_BIND(sym.st_info) != STB_GLOBAL ||
+ GELF_ST_TYPE(sym.st_info) != STT_OBJECT)
+ continue;
+
+ sname = elf_strptr(obj->efile.elf, obj->efile.strtabidx,
+ sym.st_name);
+ if (!sname) {
+ pr_warning("failed to get sym name string for var %s\n",
+ name);
+ return -EIO;
+ }
+ if (strcmp(name, sname) == 0) {
+ *off = sym.st_value;
+ return 0;
+ }
+ }
+
+ return -ENOENT;
+}
+
+static bool bpf_object__has_maps(const struct bpf_object *obj)
+{
+ return obj->efile.maps_shndx >= 0 ||
+ obj->efile.data_shndx >= 0 ||
+ obj->efile.rodata_shndx >= 0 ||
+ obj->efile.bss_shndx >= 0;
+}
+
+static int
+bpf_object__init_internal_map(struct bpf_object *obj, struct bpf_map *map,
+ enum libbpf_map_type type, Elf_Data *data,
+ void **data_buff)
+{
+ struct bpf_map_def *def = &map->def;
+ char map_name[BPF_OBJ_NAME_LEN];
+
+ map->libbpf_type = type;
+ map->offset = ~(typeof(map->offset))0;
+ snprintf(map_name, sizeof(map_name), "%.8s%.7s", obj->name,
+ libbpf_type_to_btf_name[type]);
+ map->name = strdup(map_name);
+ if (!map->name) {
+ pr_warning("failed to alloc map name\n");
+ return -ENOMEM;
+ }
+
+ def->type = BPF_MAP_TYPE_ARRAY;
+ def->key_size = sizeof(int);
+ def->value_size = data->d_size;
+ def->max_entries = 1;
+ def->map_flags = type == LIBBPF_MAP_RODATA ?
+ BPF_F_RDONLY_PROG : 0;
+ if (data_buff) {
+ *data_buff = malloc(data->d_size);
+ if (!*data_buff) {
+ zfree(&map->name);
+ pr_warning("failed to alloc map content buffer\n");
+ return -ENOMEM;
+ }
+ memcpy(*data_buff, data->d_buf, data->d_size);
+ }
+
+ pr_debug("map %td is \"%s\"\n", map - obj->maps, map->name);
+ return 0;
+}
+
static int
bpf_object__init_maps(struct bpf_object *obj, int flags)
{
+ int i, map_idx, map_def_sz = 0, nr_syms, nr_maps = 0, nr_maps_glob = 0;
bool strict = !(flags & MAPS_RELAX_COMPAT);
- int i, map_idx, map_def_sz, nr_maps = 0;
- Elf_Scn *scn;
- Elf_Data *data;
Elf_Data *symbols = obj->efile.symbols;
+ Elf_Data *data = NULL;
+ int ret = 0;
- if (obj->efile.maps_shndx < 0)
- return -EINVAL;
if (!symbols)
return -EINVAL;
+ nr_syms = symbols->d_size / sizeof(GElf_Sym);
- scn = elf_getscn(obj->efile.elf, obj->efile.maps_shndx);
- if (scn)
- data = elf_getdata(scn, NULL);
- if (!scn || !data) {
- pr_warning("failed to get Elf_Data from map section %d\n",
- obj->efile.maps_shndx);
- return -EINVAL;
+ if (obj->efile.maps_shndx >= 0) {
+ Elf_Scn *scn = elf_getscn(obj->efile.elf,
+ obj->efile.maps_shndx);
+
+ if (scn)
+ data = elf_getdata(scn, NULL);
+ if (!scn || !data) {
+ pr_warning("failed to get Elf_Data from map section %d\n",
+ obj->efile.maps_shndx);
+ return -EINVAL;
+ }
}
/*
@@ -646,7 +856,16 @@ bpf_object__init_maps(struct bpf_object *obj, int flags)
*
* TODO: Detect array of map and report error.
*/
- for (i = 0; i < symbols->d_size / sizeof(GElf_Sym); i++) {
+ if (obj->caps.global_data) {
+ if (obj->efile.data_shndx >= 0)
+ nr_maps_glob++;
+ if (obj->efile.rodata_shndx >= 0)
+ nr_maps_glob++;
+ if (obj->efile.bss_shndx >= 0)
+ nr_maps_glob++;
+ }
+
+ for (i = 0; data && i < nr_syms; i++) {
GElf_Sym sym;
if (!gelf_getsym(symbols, i, &sym))
@@ -656,22 +875,24 @@ bpf_object__init_maps(struct bpf_object *obj, int flags)
nr_maps++;
}
- /* Alloc obj->maps and fill nr_maps. */
- pr_debug("maps in %s: %d maps in %zd bytes\n", obj->path,
- nr_maps, data->d_size);
-
- if (!nr_maps)
+ if (!nr_maps && !nr_maps_glob)
return 0;
/* Assume equally sized map definitions */
- map_def_sz = data->d_size / nr_maps;
- if (!data->d_size || (data->d_size % nr_maps) != 0) {
- pr_warning("unable to determine map definition size "
- "section %s, %d maps in %zd bytes\n",
- obj->path, nr_maps, data->d_size);
- return -EINVAL;
+ if (data) {
+ pr_debug("maps in %s: %d maps in %zd bytes\n", obj->path,
+ nr_maps, data->d_size);
+
+ map_def_sz = data->d_size / nr_maps;
+ if (!data->d_size || (data->d_size % nr_maps) != 0) {
+ pr_warning("unable to determine map definition size "
+ "section %s, %d maps in %zd bytes\n",
+ obj->path, nr_maps, data->d_size);
+ return -EINVAL;
+ }
}
+ nr_maps += nr_maps_glob;
obj->maps = calloc(nr_maps, sizeof(obj->maps[0]));
if (!obj->maps) {
pr_warning("alloc maps for object failed\n");
@@ -692,7 +913,7 @@ bpf_object__init_maps(struct bpf_object *obj, int flags)
/*
* Fill obj->maps using data in "maps" section.
*/
- for (i = 0, map_idx = 0; i < symbols->d_size / sizeof(GElf_Sym); i++) {
+ for (i = 0, map_idx = 0; data && i < nr_syms; i++) {
GElf_Sym sym;
const char *map_name;
struct bpf_map_def *def;
@@ -705,6 +926,8 @@ bpf_object__init_maps(struct bpf_object *obj, int flags)
map_name = elf_strptr(obj->efile.elf,
obj->efile.strtabidx,
sym.st_name);
+
+ obj->maps[map_idx].libbpf_type = LIBBPF_MAP_UNSPEC;
obj->maps[map_idx].offset = sym.st_value;
if (sym.st_value + map_def_sz > data->d_size) {
pr_warning("corrupted maps section in %s: last map \"%s\" too small\n",
@@ -753,8 +976,31 @@ bpf_object__init_maps(struct bpf_object *obj, int flags)
map_idx++;
}
- qsort(obj->maps, obj->nr_maps, sizeof(obj->maps[0]), compare_bpf_map);
- return 0;
+ if (!obj->caps.global_data)
+ goto finalize;
+
+ /*
+ * Populate rest of obj->maps with libbpf internal maps.
+ */
+ if (obj->efile.data_shndx >= 0)
+ ret = bpf_object__init_internal_map(obj, &obj->maps[map_idx++],
+ LIBBPF_MAP_DATA,
+ obj->efile.data,
+ &obj->sections.data);
+ if (!ret && obj->efile.rodata_shndx >= 0)
+ ret = bpf_object__init_internal_map(obj, &obj->maps[map_idx++],
+ LIBBPF_MAP_RODATA,
+ obj->efile.rodata,
+ &obj->sections.rodata);
+ if (!ret && obj->efile.bss_shndx >= 0)
+ ret = bpf_object__init_internal_map(obj, &obj->maps[map_idx++],
+ LIBBPF_MAP_BSS,
+ obj->efile.bss, NULL);
+finalize:
+ if (!ret)
+ qsort(obj->maps, obj->nr_maps, sizeof(obj->maps[0]),
+ compare_bpf_map);
+ return ret;
}
static bool section_have_execinstr(struct bpf_object *obj, int idx)
@@ -780,6 +1026,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags)
Elf *elf = obj->efile.elf;
GElf_Ehdr *ep = &obj->efile.ehdr;
Elf_Data *btf_ext_data = NULL;
+ Elf_Data *btf_data = NULL;
Elf_Scn *scn = NULL;
int idx = 0, err = 0;
@@ -823,25 +1070,18 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags)
(int)sh.sh_link, (unsigned long)sh.sh_flags,
(int)sh.sh_type);
- if (strcmp(name, "license") == 0)
+ if (strcmp(name, "license") == 0) {
err = bpf_object__init_license(obj,
data->d_buf,
data->d_size);
- else if (strcmp(name, "version") == 0)
+ } else if (strcmp(name, "version") == 0) {
err = bpf_object__init_kversion(obj,
data->d_buf,
data->d_size);
- else if (strcmp(name, "maps") == 0)
+ } else if (strcmp(name, "maps") == 0) {
obj->efile.maps_shndx = idx;
- else if (strcmp(name, BTF_ELF_SEC) == 0) {
- obj->btf = btf__new(data->d_buf, data->d_size);
- if (IS_ERR(obj->btf) || btf__load(obj->btf)) {
- pr_warning("Error loading ELF section %s: %ld. Ignored and continue.\n",
- BTF_ELF_SEC, PTR_ERR(obj->btf));
- if (!IS_ERR(obj->btf))
- btf__free(obj->btf);
- obj->btf = NULL;
- }
+ } else if (strcmp(name, BTF_ELF_SEC) == 0) {
+ btf_data = data;
} else if (strcmp(name, BTF_EXT_ELF_SEC) == 0) {
btf_ext_data = data;
} else if (sh.sh_type == SHT_SYMTAB) {
@@ -853,20 +1093,28 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags)
obj->efile.symbols = data;
obj->efile.strtabidx = sh.sh_link;
}
- } else if ((sh.sh_type == SHT_PROGBITS) &&
- (sh.sh_flags & SHF_EXECINSTR) &&
- (data->d_size > 0)) {
- if (strcmp(name, ".text") == 0)
- obj->efile.text_shndx = idx;
- err = bpf_object__add_program(obj, data->d_buf,
- data->d_size, name, idx);
- if (err) {
- char errmsg[STRERR_BUFSIZE];
- char *cp = libbpf_strerror_r(-err, errmsg,
- sizeof(errmsg));
-
- pr_warning("failed to alloc program %s (%s): %s",
- name, obj->path, cp);
+ } 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_program(obj, data->d_buf,
+ data->d_size, name, idx);
+ if (err) {
+ char errmsg[STRERR_BUFSIZE];
+ char *cp = libbpf_strerror_r(-err, errmsg,
+ sizeof(errmsg));
+
+ pr_warning("failed to alloc program %s (%s): %s",
+ name, obj->path, cp);
+ }
+ } else if (strcmp(name, ".data") == 0) {
+ obj->efile.data = data;
+ obj->efile.data_shndx = idx;
+ } else if (strcmp(name, ".rodata") == 0) {
+ obj->efile.rodata = data;
+ obj->efile.rodata_shndx = idx;
+ } else {
+ pr_debug("skip section(%d) %s\n", idx, name);
}
} else if (sh.sh_type == SHT_REL) {
void *reloc = obj->efile.reloc;
@@ -894,6 +1142,9 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags)
obj->efile.reloc[n].shdr = sh;
obj->efile.reloc[n].data = data;
}
+ } else if (sh.sh_type == SHT_NOBITS && strcmp(name, ".bss") == 0) {
+ obj->efile.bss = data;
+ obj->efile.bss_shndx = idx;
} else {
pr_debug("skip section(%d) %s\n", idx, name);
}
@@ -905,6 +1156,25 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags)
pr_warning("Corrupted ELF file: index of strtab invalid\n");
return LIBBPF_ERRNO__FORMAT;
}
+ if (btf_data) {
+ obj->btf = btf__new(btf_data->d_buf, btf_data->d_size);
+ if (IS_ERR(obj->btf)) {
+ pr_warning("Error loading ELF section %s: %ld. Ignored and continue.\n",
+ BTF_ELF_SEC, PTR_ERR(obj->btf));
+ obj->btf = NULL;
+ } else {
+ err = btf__finalize_data(obj, obj->btf);
+ if (!err)
+ err = btf__load(obj->btf);
+ if (err) {
+ pr_warning("Error finalizing and loading %s into kernel: %d. Ignored and continue.\n",
+ BTF_ELF_SEC, err);
+ btf__free(obj->btf);
+ obj->btf = NULL;
+ err = 0;
+ }
+ }
+ }
if (btf_ext_data) {
if (!obj->btf) {
pr_debug("Ignore ELF section %s because its depending ELF section %s is not found.\n",
@@ -920,7 +1190,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags)
}
}
}
- if (obj->efile.maps_shndx >= 0) {
+ if (bpf_object__has_maps(obj)) {
err = bpf_object__init_maps(obj, flags);
if (err)
goto out;
@@ -956,13 +1226,46 @@ bpf_object__find_program_by_title(struct bpf_object *obj, const char *title)
return NULL;
}
+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;
+}
+
+static bool bpf_object__shndx_is_maps(const struct bpf_object *obj,
+ int shndx)
+{
+ return shndx == obj->efile.maps_shndx;
+}
+
+static bool bpf_object__relo_in_known_section(const struct bpf_object *obj,
+ int shndx)
+{
+ return shndx == obj->efile.text_shndx ||
+ bpf_object__shndx_is_maps(obj, shndx) ||
+ bpf_object__shndx_is_data(obj, shndx);
+}
+
+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
+ return LIBBPF_MAP_UNSPEC;
+}
+
static int
bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr,
Elf_Data *data, struct bpf_object *obj)
{
Elf_Data *symbols = obj->efile.symbols;
- int text_shndx = obj->efile.text_shndx;
- int maps_shndx = obj->efile.maps_shndx;
struct bpf_map *maps = obj->maps;
size_t nr_maps = obj->nr_maps;
int i, nrels;
@@ -982,7 +1285,10 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr,
GElf_Sym sym;
GElf_Rel rel;
unsigned int insn_idx;
+ unsigned int shdr_idx;
struct bpf_insn *insns = prog->insns;
+ enum libbpf_map_type type;
+ const char *name;
size_t map_idx;
if (!gelf_getrel(data, i, &rel)) {
@@ -997,13 +1303,18 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr,
GELF_R_SYM(rel.r_info));
return -LIBBPF_ERRNO__FORMAT;
}
- pr_debug("relo for %lld value %lld name %d\n",
+
+ name = elf_strptr(obj->efile.elf, obj->efile.strtabidx,
+ sym.st_name) ? : "<?>";
+
+ pr_debug("relo for %lld value %lld name %d (\'%s\')\n",
(long long) (rel.r_info >> 32),
- (long long) sym.st_value, sym.st_name);
+ (long long) sym.st_value, sym.st_name, name);
- if (sym.st_shndx != maps_shndx && sym.st_shndx != text_shndx) {
- pr_warning("Program '%s' contains non-map related relo data pointing to section %u\n",
- prog->section_name, sym.st_shndx);
+ shdr_idx = sym.st_shndx;
+ if (!bpf_object__relo_in_known_section(obj, shdr_idx)) {
+ pr_warning("Program '%s' contains unrecognized relo data pointing to section %u\n",
+ prog->section_name, shdr_idx);
return -LIBBPF_ERRNO__RELOC;
}
@@ -1028,24 +1339,45 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr,
return -LIBBPF_ERRNO__RELOC;
}
- /* TODO: 'maps' is sorted. We can use bsearch to make it faster. */
- for (map_idx = 0; map_idx < nr_maps; map_idx++) {
- if (maps[map_idx].offset == sym.st_value) {
- pr_debug("relocation: find map %zd (%s) for insn %u\n",
- map_idx, maps[map_idx].name, insn_idx);
- break;
+ if (bpf_object__shndx_is_maps(obj, shdr_idx) ||
+ bpf_object__shndx_is_data(obj, shdr_idx)) {
+ type = bpf_object__section_to_libbpf_map_type(obj, shdr_idx);
+ if (type != LIBBPF_MAP_UNSPEC) {
+ if (GELF_ST_BIND(sym.st_info) == STB_GLOBAL) {
+ pr_warning("bpf: relocation: not yet supported relo for non-static global \'%s\' variable found in insns[%d].code 0x%x\n",
+ name, insn_idx, insns[insn_idx].code);
+ return -LIBBPF_ERRNO__RELOC;
+ }
+ if (!obj->caps.global_data) {
+ pr_warning("bpf: relocation: kernel does not support global \'%s\' variable access in insns[%d]\n",
+ name, insn_idx);
+ return -LIBBPF_ERRNO__RELOC;
+ }
}
- }
- if (map_idx >= nr_maps) {
- pr_warning("bpf relocation: map_idx %d large than %d\n",
- (int)map_idx, (int)nr_maps - 1);
- return -LIBBPF_ERRNO__RELOC;
- }
+ for (map_idx = 0; map_idx < nr_maps; map_idx++) {
+ if (maps[map_idx].libbpf_type != type)
+ continue;
+ if (type != LIBBPF_MAP_UNSPEC ||
+ (type == LIBBPF_MAP_UNSPEC &&
+ maps[map_idx].offset == sym.st_value)) {
+ pr_debug("relocation: find map %zd (%s) for insn %u\n",
+ map_idx, maps[map_idx].name, insn_idx);
+ break;
+ }
+ }
- prog->reloc_desc[i].type = RELO_LD64;
- prog->reloc_desc[i].insn_idx = insn_idx;
- prog->reloc_desc[i].map_idx = map_idx;
+ if (map_idx >= nr_maps) {
+ pr_warning("bpf relocation: map_idx %d large than %d\n",
+ (int)map_idx, (int)nr_maps - 1);
+ return -LIBBPF_ERRNO__RELOC;
+ }
+
+ prog->reloc_desc[i].type = type != LIBBPF_MAP_UNSPEC ?
+ RELO_DATA : RELO_LD64;
+ prog->reloc_desc[i].insn_idx = insn_idx;
+ prog->reloc_desc[i].map_idx = map_idx;
+ }
}
return 0;
}
@@ -1053,18 +1385,27 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr,
static int bpf_map_find_btf_info(struct bpf_map *map, const struct btf *btf)
{
struct bpf_map_def *def = &map->def;
- __u32 key_type_id, value_type_id;
+ __u32 key_type_id = 0, value_type_id = 0;
int ret;
- ret = btf__get_map_kv_tids(btf, map->name, def->key_size,
- def->value_size, &key_type_id,
- &value_type_id);
- if (ret)
+ if (!bpf_map__is_internal(map)) {
+ ret = btf__get_map_kv_tids(btf, map->name, def->key_size,
+ def->value_size, &key_type_id,
+ &value_type_id);
+ } else {
+ /*
+ * LLVM annotates global data differently in BTF, that is,
+ * only as '.data', '.bss' or '.rodata'.
+ */
+ ret = btf__find_by_name(btf,
+ libbpf_type_to_btf_name[map->libbpf_type]);
+ }
+ if (ret < 0)
return ret;
map->btf_key_type_id = key_type_id;
- map->btf_value_type_id = value_type_id;
-
+ map->btf_value_type_id = bpf_map__is_internal(map) ?
+ ret : value_type_id;
return 0;
}
@@ -1170,9 +1511,95 @@ bpf_object__probe_name(struct bpf_object *obj)
}
static int
+bpf_object__probe_global_data(struct bpf_object *obj)
+{
+ 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),
+ BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 42),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ };
+ int ret, map;
+
+ 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);
+ if (map < 0) {
+ cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
+ pr_warning("Error in %s():%s(%d). Couldn't create simple array map.\n",
+ __func__, cp, errno);
+ return -errno;
+ }
+
+ 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);
+ if (ret >= 0) {
+ obj->caps.global_data = 1;
+ close(ret);
+ }
+
+ close(map);
+ return 0;
+}
+
+static int
bpf_object__probe_caps(struct bpf_object *obj)
{
- return bpf_object__probe_name(obj);
+ int (*probe_fn[])(struct bpf_object *obj) = {
+ bpf_object__probe_name,
+ bpf_object__probe_global_data,
+ };
+ int i, ret;
+
+ for (i = 0; i < ARRAY_SIZE(probe_fn); i++) {
+ ret = probe_fn[i](obj);
+ if (ret < 0)
+ return ret;
+ }
+
+ return 0;
+}
+
+static int
+bpf_object__populate_internal_map(struct bpf_object *obj, struct bpf_map *map)
+{
+ char *cp, errmsg[STRERR_BUFSIZE];
+ int err, zero = 0;
+ __u8 *data;
+
+ /* Nothing to do here since kernel already zero-initializes .bss map. */
+ if (map->libbpf_type == LIBBPF_MAP_BSS)
+ return 0;
+
+ data = map->libbpf_type == LIBBPF_MAP_DATA ?
+ obj->sections.data : obj->sections.rodata;
+
+ err = bpf_map_update_elem(map->fd, &zero, data, 0);
+ /* Freeze .rodata map as read-only from syscall side. */
+ if (!err && map->libbpf_type == LIBBPF_MAP_RODATA) {
+ err = bpf_map_freeze(map->fd);
+ if (err) {
+ cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
+ pr_warning("Error freezing map(%s) as read-only: %s\n",
+ map->name, cp);
+ err = 0;
+ }
+ }
+ return err;
}
static int
@@ -1232,6 +1659,7 @@ bpf_object__create_maps(struct bpf_object *obj)
size_t j;
err = *pfd;
+err_out:
cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
pr_warning("failed to create map (name: '%s'): %s\n",
map->name, cp);
@@ -1239,6 +1667,15 @@ bpf_object__create_maps(struct bpf_object *obj)
zclose(obj->maps[j].fd);
return err;
}
+
+ if (bpf_map__is_internal(map)) {
+ err = bpf_object__populate_internal_map(obj, map);
+ if (err < 0) {
+ zclose(*pfd);
+ goto err_out;
+ }
+ }
+
pr_debug("create map %s: fd=%d\n", map->name, *pfd);
}
@@ -1393,21 +1830,29 @@ bpf_program__relocate(struct bpf_program *prog, struct bpf_object *obj)
return 0;
for (i = 0; i < prog->nr_reloc; i++) {
- if (prog->reloc_desc[i].type == RELO_LD64) {
+ if (prog->reloc_desc[i].type == RELO_LD64 ||
+ prog->reloc_desc[i].type == RELO_DATA) {
+ bool relo_data = prog->reloc_desc[i].type == RELO_DATA;
struct bpf_insn *insns = prog->insns;
int insn_idx, map_idx;
insn_idx = prog->reloc_desc[i].insn_idx;
map_idx = prog->reloc_desc[i].map_idx;
- if (insn_idx >= (int)prog->insns_cnt) {
+ if (insn_idx + 1 >= (int)prog->insns_cnt) {
pr_warning("relocation out of range: '%s'\n",
prog->section_name);
return -LIBBPF_ERRNO__RELOC;
}
- insns[insn_idx].src_reg = BPF_PSEUDO_MAP_FD;
+
+ if (!relo_data) {
+ insns[insn_idx].src_reg = BPF_PSEUDO_MAP_FD;
+ } else {
+ insns[insn_idx].src_reg = BPF_PSEUDO_MAP_VALUE;
+ insns[insn_idx + 1].imm = insns[insn_idx].imm;
+ }
insns[insn_idx].imm = obj->maps[map_idx].fd;
- } else {
+ } else if (prog->reloc_desc[i].type == RELO_CALL) {
err = bpf_program__reloc_text(prog, obj,
&prog->reloc_desc[i]);
if (err)
@@ -1482,6 +1927,7 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
{
struct bpf_load_program_attr load_attr;
char *cp, errmsg[STRERR_BUFSIZE];
+ int log_buf_size = BPF_LOG_BUF_SIZE;
char *log_buf;
int ret;
@@ -1502,21 +1948,30 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
load_attr.line_info = prog->line_info;
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;
if (!load_attr.insns || !load_attr.insns_cnt)
return -EINVAL;
- log_buf = malloc(BPF_LOG_BUF_SIZE);
+retry_load:
+ log_buf = malloc(log_buf_size);
if (!log_buf)
pr_warning("Alloc log buffer for bpf loader error, continue without log\n");
- ret = bpf_load_program_xattr(&load_attr, log_buf, BPF_LOG_BUF_SIZE);
+ ret = bpf_load_program_xattr(&load_attr, log_buf, log_buf_size);
if (ret >= 0) {
+ if (load_attr.log_level)
+ pr_debug("verifier log:\n%s", log_buf);
*pfd = ret;
ret = 0;
goto out;
}
+ if (errno == ENOSPC) {
+ log_buf_size <<= 1;
+ free(log_buf);
+ goto retry_load;
+ }
ret = -LIBBPF_ERRNO__LOAD;
cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
pr_warning("load bpf program failed: %s\n", cp);
@@ -1681,7 +2136,9 @@ static bool bpf_prog_type__needs_kver(enum bpf_prog_type type)
case BPF_PROG_TYPE_UNSPEC:
case BPF_PROG_TYPE_TRACEPOINT:
case BPF_PROG_TYPE_RAW_TRACEPOINT:
+ case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE:
case BPF_PROG_TYPE_PERF_EVENT:
+ case BPF_PROG_TYPE_CGROUP_SYSCTL:
return false;
case BPF_PROG_TYPE_KPROBE:
default:
@@ -1717,6 +2174,7 @@ __bpf_object__open(const char *path, void *obj_buf, size_t obj_buf_sz,
CHECK_ERR(bpf_object__elf_init(obj), err, out);
CHECK_ERR(bpf_object__check_endianness(obj), err, out);
+ CHECK_ERR(bpf_object__probe_caps(obj), err, out);
CHECK_ERR(bpf_object__elf_collect(obj, flags), err, out);
CHECK_ERR(bpf_object__collect_reloc(obj), err, out);
CHECK_ERR(bpf_object__validate(obj, needs_kver), err, out);
@@ -1810,7 +2268,6 @@ int bpf_object__load(struct bpf_object *obj)
obj->loaded = true;
- CHECK_ERR(bpf_object__probe_caps(obj), err, out);
CHECK_ERR(bpf_object__create_maps(obj), err, out);
CHECK_ERR(bpf_object__relocate(obj), err, out);
CHECK_ERR(bpf_object__load_progs(obj), err, out);
@@ -2291,6 +2748,9 @@ void bpf_object__close(struct bpf_object *obj)
obj->maps[i].priv = NULL;
obj->maps[i].clear_priv = NULL;
}
+
+ zfree(&obj->sections.rodata);
+ zfree(&obj->sections.data);
zfree(&obj->maps);
obj->nr_maps = 0;
@@ -2619,6 +3079,8 @@ static const struct {
BPF_CGROUP_UDP4_SENDMSG),
BPF_EAPROG_SEC("cgroup/sendmsg6", BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
BPF_CGROUP_UDP6_SENDMSG),
+ BPF_EAPROG_SEC("cgroup/sysctl", BPF_PROG_TYPE_CGROUP_SYSCTL,
+ BPF_CGROUP_SYSCTL),
};
#undef BPF_PROG_SEC_IMPL
@@ -2768,6 +3230,11 @@ bool bpf_map__is_offload_neutral(struct bpf_map *map)
return map->def.type == BPF_MAP_TYPE_PERF_EVENT_ARRAY;
}
+bool bpf_map__is_internal(struct bpf_map *map)
+{
+ return map->libbpf_type != LIBBPF_MAP_UNSPEC;
+}
+
void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex)
{
map->map_ifindex = ifindex;
@@ -2926,6 +3393,7 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
bpf_program__set_expected_attach_type(prog,
expected_attach_type);
+ prog->log_level = attr->log_level;
if (!first_prog)
first_prog = prog;
}
@@ -2999,3 +3467,249 @@ bpf_perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size,
ring_buffer_write_tail(header, data_tail);
return ret;
}
+
+struct bpf_prog_info_array_desc {
+ int array_offset; /* e.g. offset of jited_prog_insns */
+ int count_offset; /* e.g. offset of jited_prog_len */
+ int size_offset; /* > 0: offset of rec size,
+ * < 0: fix size of -size_offset
+ */
+};
+
+static struct bpf_prog_info_array_desc bpf_prog_info_array_desc[] = {
+ [BPF_PROG_INFO_JITED_INSNS] = {
+ offsetof(struct bpf_prog_info, jited_prog_insns),
+ offsetof(struct bpf_prog_info, jited_prog_len),
+ -1,
+ },
+ [BPF_PROG_INFO_XLATED_INSNS] = {
+ offsetof(struct bpf_prog_info, xlated_prog_insns),
+ offsetof(struct bpf_prog_info, xlated_prog_len),
+ -1,
+ },
+ [BPF_PROG_INFO_MAP_IDS] = {
+ offsetof(struct bpf_prog_info, map_ids),
+ offsetof(struct bpf_prog_info, nr_map_ids),
+ -(int)sizeof(__u32),
+ },
+ [BPF_PROG_INFO_JITED_KSYMS] = {
+ offsetof(struct bpf_prog_info, jited_ksyms),
+ offsetof(struct bpf_prog_info, nr_jited_ksyms),
+ -(int)sizeof(__u64),
+ },
+ [BPF_PROG_INFO_JITED_FUNC_LENS] = {
+ offsetof(struct bpf_prog_info, jited_func_lens),
+ offsetof(struct bpf_prog_info, nr_jited_func_lens),
+ -(int)sizeof(__u32),
+ },
+ [BPF_PROG_INFO_FUNC_INFO] = {
+ offsetof(struct bpf_prog_info, func_info),
+ offsetof(struct bpf_prog_info, nr_func_info),
+ offsetof(struct bpf_prog_info, func_info_rec_size),
+ },
+ [BPF_PROG_INFO_LINE_INFO] = {
+ offsetof(struct bpf_prog_info, line_info),
+ offsetof(struct bpf_prog_info, nr_line_info),
+ offsetof(struct bpf_prog_info, line_info_rec_size),
+ },
+ [BPF_PROG_INFO_JITED_LINE_INFO] = {
+ offsetof(struct bpf_prog_info, jited_line_info),
+ offsetof(struct bpf_prog_info, nr_jited_line_info),
+ offsetof(struct bpf_prog_info, jited_line_info_rec_size),
+ },
+ [BPF_PROG_INFO_PROG_TAGS] = {
+ offsetof(struct bpf_prog_info, prog_tags),
+ offsetof(struct bpf_prog_info, nr_prog_tags),
+ -(int)sizeof(__u8) * BPF_TAG_SIZE,
+ },
+
+};
+
+static __u32 bpf_prog_info_read_offset_u32(struct bpf_prog_info *info, int offset)
+{
+ __u32 *array = (__u32 *)info;
+
+ if (offset >= 0)
+ return array[offset / sizeof(__u32)];
+ return -(int)offset;
+}
+
+static __u64 bpf_prog_info_read_offset_u64(struct bpf_prog_info *info, int offset)
+{
+ __u64 *array = (__u64 *)info;
+
+ if (offset >= 0)
+ return array[offset / sizeof(__u64)];
+ return -(int)offset;
+}
+
+static void bpf_prog_info_set_offset_u32(struct bpf_prog_info *info, int offset,
+ __u32 val)
+{
+ __u32 *array = (__u32 *)info;
+
+ if (offset >= 0)
+ array[offset / sizeof(__u32)] = val;
+}
+
+static void bpf_prog_info_set_offset_u64(struct bpf_prog_info *info, int offset,
+ __u64 val)
+{
+ __u64 *array = (__u64 *)info;
+
+ if (offset >= 0)
+ array[offset / sizeof(__u64)] = val;
+}
+
+struct bpf_prog_info_linear *
+bpf_program__get_prog_info_linear(int fd, __u64 arrays)
+{
+ struct bpf_prog_info_linear *info_linear;
+ struct bpf_prog_info info = {};
+ __u32 info_len = sizeof(info);
+ __u32 data_len = 0;
+ int i, err;
+ void *ptr;
+
+ if (arrays >> BPF_PROG_INFO_LAST_ARRAY)
+ return ERR_PTR(-EINVAL);
+
+ /* step 1: get array dimensions */
+ err = bpf_obj_get_info_by_fd(fd, &info, &info_len);
+ if (err) {
+ pr_debug("can't get prog info: %s", strerror(errno));
+ return ERR_PTR(-EFAULT);
+ }
+
+ /* step 2: calculate total size of all arrays */
+ for (i = BPF_PROG_INFO_FIRST_ARRAY; i < BPF_PROG_INFO_LAST_ARRAY; ++i) {
+ bool include_array = (arrays & (1UL << i)) > 0;
+ struct bpf_prog_info_array_desc *desc;
+ __u32 count, size;
+
+ desc = bpf_prog_info_array_desc + i;
+
+ /* kernel is too old to support this field */
+ if (info_len < desc->array_offset + sizeof(__u32) ||
+ info_len < desc->count_offset + sizeof(__u32) ||
+ (desc->size_offset > 0 && info_len < desc->size_offset))
+ include_array = false;
+
+ if (!include_array) {
+ arrays &= ~(1UL << i); /* clear the bit */
+ continue;
+ }
+
+ count = bpf_prog_info_read_offset_u32(&info, desc->count_offset);
+ size = bpf_prog_info_read_offset_u32(&info, desc->size_offset);
+
+ data_len += count * size;
+ }
+
+ /* step 3: allocate continuous memory */
+ data_len = roundup(data_len, sizeof(__u64));
+ info_linear = malloc(sizeof(struct bpf_prog_info_linear) + data_len);
+ if (!info_linear)
+ return ERR_PTR(-ENOMEM);
+
+ /* step 4: fill data to info_linear->info */
+ info_linear->arrays = arrays;
+ memset(&info_linear->info, 0, sizeof(info));
+ ptr = info_linear->data;
+
+ for (i = BPF_PROG_INFO_FIRST_ARRAY; i < BPF_PROG_INFO_LAST_ARRAY; ++i) {
+ struct bpf_prog_info_array_desc *desc;
+ __u32 count, size;
+
+ if ((arrays & (1UL << i)) == 0)
+ continue;
+
+ desc = bpf_prog_info_array_desc + i;
+ count = bpf_prog_info_read_offset_u32(&info, desc->count_offset);
+ size = bpf_prog_info_read_offset_u32(&info, desc->size_offset);
+ bpf_prog_info_set_offset_u32(&info_linear->info,
+ desc->count_offset, count);
+ bpf_prog_info_set_offset_u32(&info_linear->info,
+ desc->size_offset, size);
+ bpf_prog_info_set_offset_u64(&info_linear->info,
+ desc->array_offset,
+ ptr_to_u64(ptr));
+ ptr += count * size;
+ }
+
+ /* step 5: call syscall again to get required arrays */
+ err = bpf_obj_get_info_by_fd(fd, &info_linear->info, &info_len);
+ if (err) {
+ pr_debug("can't get prog info: %s", strerror(errno));
+ free(info_linear);
+ return ERR_PTR(-EFAULT);
+ }
+
+ /* step 6: verify the data */
+ for (i = BPF_PROG_INFO_FIRST_ARRAY; i < BPF_PROG_INFO_LAST_ARRAY; ++i) {
+ struct bpf_prog_info_array_desc *desc;
+ __u32 v1, v2;
+
+ if ((arrays & (1UL << i)) == 0)
+ continue;
+
+ desc = bpf_prog_info_array_desc + i;
+ v1 = bpf_prog_info_read_offset_u32(&info, desc->count_offset);
+ v2 = bpf_prog_info_read_offset_u32(&info_linear->info,
+ desc->count_offset);
+ if (v1 != v2)
+ pr_warning("%s: mismatch in element count\n", __func__);
+
+ v1 = bpf_prog_info_read_offset_u32(&info, desc->size_offset);
+ v2 = bpf_prog_info_read_offset_u32(&info_linear->info,
+ desc->size_offset);
+ if (v1 != v2)
+ pr_warning("%s: mismatch in rec size\n", __func__);
+ }
+
+ /* step 7: update info_len and data_len */
+ info_linear->info_len = sizeof(struct bpf_prog_info);
+ info_linear->data_len = data_len;
+
+ return info_linear;
+}
+
+void bpf_program__bpil_addr_to_offs(struct bpf_prog_info_linear *info_linear)
+{
+ int i;
+
+ for (i = BPF_PROG_INFO_FIRST_ARRAY; i < BPF_PROG_INFO_LAST_ARRAY; ++i) {
+ struct bpf_prog_info_array_desc *desc;
+ __u64 addr, offs;
+
+ if ((info_linear->arrays & (1UL << i)) == 0)
+ continue;
+
+ desc = bpf_prog_info_array_desc + i;
+ addr = bpf_prog_info_read_offset_u64(&info_linear->info,
+ desc->array_offset);
+ offs = addr - ptr_to_u64(info_linear->data);
+ bpf_prog_info_set_offset_u64(&info_linear->info,
+ desc->array_offset, offs);
+ }
+}
+
+void bpf_program__bpil_offs_to_addr(struct bpf_prog_info_linear *info_linear)
+{
+ int i;
+
+ for (i = BPF_PROG_INFO_FIRST_ARRAY; i < BPF_PROG_INFO_LAST_ARRAY; ++i) {
+ struct bpf_prog_info_array_desc *desc;
+ __u64 addr, offs;
+
+ if ((info_linear->arrays & (1UL << i)) == 0)
+ continue;
+
+ desc = bpf_prog_info_array_desc + i;
+ offs = bpf_prog_info_read_offset_u64(&info_linear->info,
+ desc->array_offset);
+ addr = offs + ptr_to_u64(info_linear->data);
+ bpf_prog_info_set_offset_u64(&info_linear->info,
+ desc->array_offset, addr);
+ }
+}
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index b4652aa1a58a..c5ff00515ce7 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -10,6 +10,7 @@
#ifndef __LIBBPF_LIBBPF_H
#define __LIBBPF_LIBBPF_H
+#include <stdarg.h>
#include <stdio.h>
#include <stdint.h>
#include <stdbool.h>
@@ -74,6 +75,10 @@ struct bpf_object *__bpf_object__open_xattr(struct bpf_object_open_attr *attr,
LIBBPF_API struct bpf_object *bpf_object__open_buffer(void *obj_buf,
size_t obj_buf_sz,
const char *name);
+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);
LIBBPF_API int bpf_object__pin_maps(struct bpf_object *obj, const char *path);
LIBBPF_API int bpf_object__unpin_maps(struct bpf_object *obj,
const char *path);
@@ -300,6 +305,7 @@ LIBBPF_API void *bpf_map__priv(struct bpf_map *map);
LIBBPF_API int bpf_map__reuse_fd(struct bpf_map *map, int fd);
LIBBPF_API int bpf_map__resize(struct bpf_map *map, __u32 max_entries);
LIBBPF_API bool bpf_map__is_offload_neutral(struct bpf_map *map);
+LIBBPF_API bool bpf_map__is_internal(struct bpf_map *map);
LIBBPF_API void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex);
LIBBPF_API int bpf_map__pin(struct bpf_map *map, const char *path);
LIBBPF_API int bpf_map__unpin(struct bpf_map *map, const char *path);
@@ -313,6 +319,7 @@ struct bpf_prog_load_attr {
enum bpf_prog_type prog_type;
enum bpf_attach_type expected_attach_type;
int ifindex;
+ int log_level;
};
LIBBPF_API int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
@@ -377,6 +384,69 @@ 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);
+/*
+ * Get bpf_prog_info in continuous memory
+ *
+ * struct bpf_prog_info has multiple arrays. The user has option to choose
+ * arrays to fetch from kernel. The following APIs provide an uniform way to
+ * fetch these data. All arrays in bpf_prog_info are stored in a single
+ * continuous memory region. This makes it easy to store the info in a
+ * file.
+ *
+ * Before writing bpf_prog_info_linear to files, it is necessary to
+ * translate pointers in bpf_prog_info to offsets. Helper functions
+ * bpf_program__bpil_addr_to_offs() and bpf_program__bpil_offs_to_addr()
+ * are introduced to switch between pointers and offsets.
+ *
+ * Examples:
+ * # To fetch map_ids and prog_tags:
+ * __u64 arrays = (1UL << BPF_PROG_INFO_MAP_IDS) |
+ * (1UL << BPF_PROG_INFO_PROG_TAGS);
+ * struct bpf_prog_info_linear *info_linear =
+ * bpf_program__get_prog_info_linear(fd, arrays);
+ *
+ * # To save data in file
+ * bpf_program__bpil_addr_to_offs(info_linear);
+ * write(f, info_linear, sizeof(*info_linear) + info_linear->data_len);
+ *
+ * # To read data from file
+ * read(f, info_linear, <proper_size>);
+ * bpf_program__bpil_offs_to_addr(info_linear);
+ */
+enum bpf_prog_info_array {
+ BPF_PROG_INFO_FIRST_ARRAY = 0,
+ BPF_PROG_INFO_JITED_INSNS = 0,
+ BPF_PROG_INFO_XLATED_INSNS,
+ BPF_PROG_INFO_MAP_IDS,
+ BPF_PROG_INFO_JITED_KSYMS,
+ BPF_PROG_INFO_JITED_FUNC_LENS,
+ BPF_PROG_INFO_FUNC_INFO,
+ BPF_PROG_INFO_LINE_INFO,
+ BPF_PROG_INFO_JITED_LINE_INFO,
+ BPF_PROG_INFO_PROG_TAGS,
+ BPF_PROG_INFO_LAST_ARRAY,
+};
+
+struct bpf_prog_info_linear {
+ /* size of struct bpf_prog_info, when the tool is compiled */
+ __u32 info_len;
+ /* total bytes allocated for data, round up to 8 bytes */
+ __u32 data_len;
+ /* which arrays are included in data */
+ __u64 arrays;
+ struct bpf_prog_info info;
+ __u8 data[];
+};
+
+LIBBPF_API struct bpf_prog_info_linear *
+bpf_program__get_prog_info_linear(int fd, __u64 arrays);
+
+LIBBPF_API void
+bpf_program__bpil_addr_to_offs(struct bpf_prog_info_linear *info_linear);
+
+LIBBPF_API void
+bpf_program__bpil_offs_to_addr(struct bpf_prog_info_linear *info_linear);
+
#ifdef __cplusplus
} /* extern "C" */
#endif
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index 778a26702a70..673001787cba 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -153,4 +153,14 @@ LIBBPF_0.0.2 {
xsk_socket__delete;
xsk_umem__fd;
xsk_socket__fd;
+ bpf_program__get_prog_info_linear;
+ bpf_program__bpil_addr_to_offs;
+ bpf_program__bpil_offs_to_addr;
} LIBBPF_0.0.1;
+
+LIBBPF_0.0.3 {
+ global:
+ bpf_map__is_internal;
+ bpf_map_freeze;
+ btf__finalize_data;
+} LIBBPF_0.0.2;
diff --git a/tools/lib/bpf/libbpf.pc.template b/tools/lib/bpf/libbpf.pc.template
new file mode 100644
index 000000000000..ac17fcef2108
--- /dev/null
+++ b/tools/lib/bpf/libbpf.pc.template
@@ -0,0 +1,12 @@
+# SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+
+prefix=@PREFIX@
+libdir=@LIBDIR@
+includedir=${prefix}/include
+
+Name: libbpf
+Description: BPF library
+Version: @VERSION@
+Libs: -L${libdir} -lbpf
+Requires.private: libelf
+Cflags: -I${includedir}
diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c
index 8c3a1c04dcb2..a2c64a9ce1a6 100644
--- a/tools/lib/bpf/libbpf_probes.c
+++ b/tools/lib/bpf/libbpf_probes.c
@@ -9,6 +9,7 @@
#include <net/if.h>
#include <sys/utsname.h>
+#include <linux/btf.h>
#include <linux/filter.h>
#include <linux/kernel.h>
@@ -93,10 +94,12 @@ probe_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns,
case BPF_PROG_TYPE_CGROUP_DEVICE:
case BPF_PROG_TYPE_SK_MSG:
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:
default:
break;
}
@@ -129,11 +132,65 @@ bool bpf_probe_prog_type(enum bpf_prog_type prog_type, __u32 ifindex)
return errno != EINVAL && errno != EOPNOTSUPP;
}
+static int load_btf(void)
+{
+#define BTF_INFO_ENC(kind, kind_flag, vlen) \
+ ((!!(kind_flag) << 31) | ((kind) << 24) | ((vlen) & BTF_MAX_VLEN))
+#define BTF_TYPE_ENC(name, info, size_or_type) \
+ (name), (info), (size_or_type)
+#define BTF_INT_ENC(encoding, bits_offset, nr_bits) \
+ ((encoding) << 24 | (bits_offset) << 16 | (nr_bits))
+#define BTF_TYPE_INT_ENC(name, encoding, bits_offset, bits, sz) \
+ BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_INT, 0, 0), sz), \
+ BTF_INT_ENC(encoding, bits_offset, bits)
+#define BTF_MEMBER_ENC(name, type, bits_offset) \
+ (name), (type), (bits_offset)
+
+ const char btf_str_sec[] = "\0bpf_spin_lock\0val\0cnt\0l";
+ /* struct bpf_spin_lock {
+ * int val;
+ * };
+ * struct val {
+ * int cnt;
+ * struct bpf_spin_lock l;
+ * };
+ */
+ __u32 btf_raw_types[] = {
+ /* int */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ /* struct bpf_spin_lock */ /* [2] */
+ BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 1), 4),
+ BTF_MEMBER_ENC(15, 1, 0), /* int val; */
+ /* struct val */ /* [3] */
+ 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 btf_header btf_hdr = {
+ .magic = BTF_MAGIC,
+ .version = BTF_VERSION,
+ .hdr_len = sizeof(struct btf_header),
+ .type_len = sizeof(btf_raw_types),
+ .str_off = sizeof(btf_raw_types),
+ .str_len = sizeof(btf_str_sec),
+ };
+ __u8 raw_btf[sizeof(struct btf_header) + sizeof(btf_raw_types) +
+ sizeof(btf_str_sec)];
+
+ memcpy(raw_btf, &btf_hdr, sizeof(btf_hdr));
+ memcpy(raw_btf + sizeof(btf_hdr), btf_raw_types, sizeof(btf_raw_types));
+ 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);
+}
+
bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex)
{
int key_size, value_size, max_entries, map_flags;
+ __u32 btf_key_type_id = 0, btf_value_type_id = 0;
struct bpf_create_map_attr attr = {};
- int fd = -1, fd_inner;
+ int fd = -1, btf_fd = -1, fd_inner;
key_size = sizeof(__u32);
value_size = sizeof(__u32);
@@ -159,6 +216,16 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex)
case BPF_MAP_TYPE_STACK:
key_size = 0;
break;
+ case BPF_MAP_TYPE_SK_STORAGE:
+ btf_key_type_id = 1;
+ btf_value_type_id = 3;
+ value_size = 8;
+ max_entries = 0;
+ map_flags = BPF_F_NO_PREALLOC;
+ btf_fd = load_btf();
+ if (btf_fd < 0)
+ return false;
+ break;
case BPF_MAP_TYPE_UNSPEC:
case BPF_MAP_TYPE_HASH:
case BPF_MAP_TYPE_ARRAY:
@@ -204,11 +271,18 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex)
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;
+ }
fd = bpf_create_map_xattr(&attr);
}
if (fd >= 0)
close(fd);
+ if (btf_fd >= 0)
+ close(btf_fd);
return fd >= 0;
}
diff --git a/tools/lib/bpf/libbpf_util.h b/tools/lib/bpf/libbpf_util.h
index 81ecda0cb9c9..da94c4cb2e4d 100644
--- a/tools/lib/bpf/libbpf_util.h
+++ b/tools/lib/bpf/libbpf_util.h
@@ -23,6 +23,36 @@ do { \
#define pr_info(fmt, ...) __pr(LIBBPF_INFO, fmt, ##__VA_ARGS__)
#define pr_debug(fmt, ...) __pr(LIBBPF_DEBUG, fmt, ##__VA_ARGS__)
+/* Use these barrier functions instead of smp_[rw]mb() when they are
+ * used in a libbpf header file. That way they can be built into the
+ * application that uses libbpf.
+ */
+#if defined(__i386__) || defined(__x86_64__)
+# define libbpf_smp_rmb() asm volatile("" : : : "memory")
+# define libbpf_smp_wmb() asm volatile("" : : : "memory")
+# define libbpf_smp_mb() \
+ asm volatile("lock; addl $0,-4(%%rsp)" : : : "memory", "cc")
+/* Hinders stores to be observed before older loads. */
+# define libbpf_smp_rwmb() asm volatile("" : : : "memory")
+#elif defined(__aarch64__)
+# define libbpf_smp_rmb() asm volatile("dmb ishld" : : : "memory")
+# define libbpf_smp_wmb() asm volatile("dmb ishst" : : : "memory")
+# define libbpf_smp_mb() asm volatile("dmb ish" : : : "memory")
+# define libbpf_smp_rwmb() libbpf_smp_mb()
+#elif defined(__arm__)
+/* These are only valid for armv7 and above */
+# define libbpf_smp_rmb() asm volatile("dmb ish" : : : "memory")
+# define libbpf_smp_wmb() asm volatile("dmb ishst" : : : "memory")
+# define libbpf_smp_mb() asm volatile("dmb ish" : : : "memory")
+# define libbpf_smp_rwmb() libbpf_smp_mb()
+#else
+/* Architecture missing native barrier functions. */
+# define libbpf_smp_rmb() __sync_synchronize()
+# define libbpf_smp_wmb() __sync_synchronize()
+# define libbpf_smp_mb() __sync_synchronize()
+# define libbpf_smp_rwmb() __sync_synchronize()
+#endif
+
#ifdef __cplusplus
} /* extern "C" */
#endif
diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c
index f98ac82c9aea..a3d1a302bc9c 100644
--- a/tools/lib/bpf/xsk.c
+++ b/tools/lib/bpf/xsk.c
@@ -126,8 +126,8 @@ static void xsk_set_umem_config(struct xsk_umem_config *cfg,
cfg->frame_headroom = usr_cfg->frame_headroom;
}
-static void xsk_set_xdp_socket_config(struct xsk_socket_config *cfg,
- const struct xsk_socket_config *usr_cfg)
+static int xsk_set_xdp_socket_config(struct xsk_socket_config *cfg,
+ const struct xsk_socket_config *usr_cfg)
{
if (!usr_cfg) {
cfg->rx_size = XSK_RING_CONS__DEFAULT_NUM_DESCS;
@@ -135,14 +135,19 @@ static void xsk_set_xdp_socket_config(struct xsk_socket_config *cfg,
cfg->libbpf_flags = 0;
cfg->xdp_flags = 0;
cfg->bind_flags = 0;
- return;
+ return 0;
}
+ if (usr_cfg->libbpf_flags & ~XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD)
+ return -EINVAL;
+
cfg->rx_size = usr_cfg->rx_size;
cfg->tx_size = usr_cfg->tx_size;
cfg->libbpf_flags = usr_cfg->libbpf_flags;
cfg->xdp_flags = usr_cfg->xdp_flags;
cfg->bind_flags = usr_cfg->bind_flags;
+
+ return 0;
}
int xsk_umem__create(struct xsk_umem **umem_ptr, void *umem_area, __u64 size,
@@ -243,8 +248,7 @@ int xsk_umem__create(struct xsk_umem **umem_ptr, void *umem_area, __u64 size,
return 0;
out_mmap:
- munmap(umem->fill,
- off.fr.desc + umem->config.fill_size * sizeof(__u64));
+ munmap(map, off.fr.desc + umem->config.fill_size * sizeof(__u64));
out_socket:
close(umem->fd);
out_umem_alloc:
@@ -254,7 +258,8 @@ out_umem_alloc:
static int xsk_load_xdp_prog(struct xsk_socket *xsk)
{
- char bpf_log_buf[BPF_LOG_BUF_SIZE];
+ static const int log_buf_size = 16 * 1024;
+ char log_buf[log_buf_size];
int err, prog_fd;
/* This is the C-program:
@@ -303,10 +308,10 @@ static int xsk_load_xdp_prog(struct xsk_socket *xsk)
size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn);
prog_fd = bpf_load_program(BPF_PROG_TYPE_XDP, prog, insns_cnt,
- "LGPL-2.1 or BSD-2-Clause", 0, bpf_log_buf,
- BPF_LOG_BUF_SIZE);
+ "LGPL-2.1 or BSD-2-Clause", 0, log_buf,
+ log_buf_size);
if (prog_fd < 0) {
- pr_warning("BPF log buffer:\n%s", bpf_log_buf);
+ pr_warning("BPF log buffer:\n%s", log_buf);
return prog_fd;
}
@@ -382,21 +387,17 @@ static void xsk_delete_bpf_maps(struct xsk_socket *xsk)
{
close(xsk->qidconf_map_fd);
close(xsk->xsks_map_fd);
+ xsk->qidconf_map_fd = -1;
+ xsk->xsks_map_fd = -1;
}
-static int xsk_update_bpf_maps(struct xsk_socket *xsk, int qidconf_value,
- int xsks_value)
+static int xsk_lookup_bpf_maps(struct xsk_socket *xsk)
{
- bool qidconf_map_updated = false, xsks_map_updated = false;
+ __u32 i, *map_ids, num_maps, prog_len = sizeof(struct bpf_prog_info);
+ __u32 map_len = sizeof(struct bpf_map_info);
struct bpf_prog_info prog_info = {};
- __u32 prog_len = sizeof(prog_info);
struct bpf_map_info map_info;
- __u32 map_len = sizeof(map_info);
- __u32 *map_ids;
- int reset_value = 0;
- __u32 num_maps;
- unsigned int i;
- int err;
+ int fd, err;
err = bpf_obj_get_info_by_fd(xsk->prog_fd, &prog_info, &prog_len);
if (err)
@@ -417,66 +418,71 @@ static int xsk_update_bpf_maps(struct xsk_socket *xsk, int qidconf_value,
goto out_map_ids;
for (i = 0; i < prog_info.nr_map_ids; i++) {
- int fd;
+ if (xsk->qidconf_map_fd != -1 && xsk->xsks_map_fd != -1)
+ break;
fd = bpf_map_get_fd_by_id(map_ids[i]);
- if (fd < 0) {
- err = -errno;
- goto out_maps;
- }
+ if (fd < 0)
+ continue;
err = bpf_obj_get_info_by_fd(fd, &map_info, &map_len);
- if (err)
- goto out_maps;
+ if (err) {
+ close(fd);
+ continue;
+ }
if (!strcmp(map_info.name, "qidconf_map")) {
- err = bpf_map_update_elem(fd, &xsk->queue_id,
- &qidconf_value, 0);
- if (err)
- goto out_maps;
- qidconf_map_updated = true;
xsk->qidconf_map_fd = fd;
- } else if (!strcmp(map_info.name, "xsks_map")) {
- err = bpf_map_update_elem(fd, &xsk->queue_id,
- &xsks_value, 0);
- if (err)
- goto out_maps;
- xsks_map_updated = true;
+ continue;
+ }
+
+ if (!strcmp(map_info.name, "xsks_map")) {
xsk->xsks_map_fd = fd;
+ continue;
}
- if (qidconf_map_updated && xsks_map_updated)
- break;
+ close(fd);
}
- if (!(qidconf_map_updated && xsks_map_updated)) {
+ err = 0;
+ if (xsk->qidconf_map_fd < 0 || xsk->xsks_map_fd < 0) {
err = -ENOENT;
- goto out_maps;
+ xsk_delete_bpf_maps(xsk);
}
- err = 0;
- goto out_success;
-
-out_maps:
- if (qidconf_map_updated)
- (void)bpf_map_update_elem(xsk->qidconf_map_fd, &xsk->queue_id,
- &reset_value, 0);
- if (xsks_map_updated)
- (void)bpf_map_update_elem(xsk->xsks_map_fd, &xsk->queue_id,
- &reset_value, 0);
-out_success:
- if (qidconf_map_updated)
- close(xsk->qidconf_map_fd);
- if (xsks_map_updated)
- close(xsk->xsks_map_fd);
out_map_ids:
free(map_ids);
return err;
}
+static void xsk_clear_bpf_maps(struct xsk_socket *xsk)
+{
+ int qid = false;
+
+ bpf_map_update_elem(xsk->qidconf_map_fd, &xsk->queue_id, &qid, 0);
+ bpf_map_delete_elem(xsk->xsks_map_fd, &xsk->queue_id);
+}
+
+static int xsk_set_bpf_maps(struct xsk_socket *xsk)
+{
+ int qid = true, fd = xsk->fd, err;
+
+ err = bpf_map_update_elem(xsk->qidconf_map_fd, &xsk->queue_id, &qid, 0);
+ if (err)
+ goto out;
+
+ err = bpf_map_update_elem(xsk->xsks_map_fd, &xsk->queue_id, &fd, 0);
+ if (err)
+ goto out;
+
+ return 0;
+out:
+ xsk_clear_bpf_maps(xsk);
+ return err;
+}
+
static int xsk_setup_xdp_prog(struct xsk_socket *xsk)
{
- bool prog_attached = false;
__u32 prog_id = 0;
int err;
@@ -486,7 +492,6 @@ static int xsk_setup_xdp_prog(struct xsk_socket *xsk)
return err;
if (!prog_id) {
- prog_attached = true;
err = xsk_create_bpf_maps(xsk);
if (err)
return err;
@@ -496,20 +501,21 @@ static int xsk_setup_xdp_prog(struct xsk_socket *xsk)
goto out_maps;
} else {
xsk->prog_fd = bpf_prog_get_fd_by_id(prog_id);
+ err = xsk_lookup_bpf_maps(xsk);
+ if (err)
+ goto out_load;
}
- err = xsk_update_bpf_maps(xsk, true, xsk->fd);
+ err = xsk_set_bpf_maps(xsk);
if (err)
goto out_load;
return 0;
out_load:
- if (prog_attached)
- close(xsk->prog_fd);
+ close(xsk->prog_fd);
out_maps:
- if (prog_attached)
- xsk_delete_bpf_maps(xsk);
+ xsk_delete_bpf_maps(xsk);
return err;
}
@@ -518,11 +524,11 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname,
struct xsk_ring_cons *rx, struct xsk_ring_prod *tx,
const struct xsk_socket_config *usr_config)
{
+ void *rx_map = NULL, *tx_map = NULL;
struct sockaddr_xdp sxdp = {};
struct xdp_mmap_offsets off;
struct xsk_socket *xsk;
socklen_t optlen;
- void *map;
int err;
if (!umem || !xsk_ptr || !rx || !tx)
@@ -557,7 +563,9 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname,
}
strncpy(xsk->ifname, ifname, IFNAMSIZ);
- xsk_set_xdp_socket_config(&xsk->config, usr_config);
+ err = xsk_set_xdp_socket_config(&xsk->config, usr_config);
+ if (err)
+ goto out_socket;
if (rx) {
err = setsockopt(xsk->fd, SOL_XDP, XDP_RX_RING,
@@ -586,40 +594,40 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname,
}
if (rx) {
- map = xsk_mmap(NULL, off.rx.desc +
- xsk->config.rx_size * sizeof(struct xdp_desc),
- PROT_READ | PROT_WRITE,
- MAP_SHARED | MAP_POPULATE,
- xsk->fd, XDP_PGOFF_RX_RING);
- if (map == MAP_FAILED) {
+ rx_map = xsk_mmap(NULL, off.rx.desc +
+ xsk->config.rx_size * sizeof(struct xdp_desc),
+ PROT_READ | PROT_WRITE,
+ MAP_SHARED | MAP_POPULATE,
+ xsk->fd, XDP_PGOFF_RX_RING);
+ if (rx_map == MAP_FAILED) {
err = -errno;
goto out_socket;
}
rx->mask = xsk->config.rx_size - 1;
rx->size = xsk->config.rx_size;
- rx->producer = map + off.rx.producer;
- rx->consumer = map + off.rx.consumer;
- rx->ring = map + off.rx.desc;
+ rx->producer = rx_map + off.rx.producer;
+ rx->consumer = rx_map + off.rx.consumer;
+ rx->ring = rx_map + off.rx.desc;
}
xsk->rx = rx;
if (tx) {
- map = xsk_mmap(NULL, off.tx.desc +
- xsk->config.tx_size * sizeof(struct xdp_desc),
- PROT_READ | PROT_WRITE,
- MAP_SHARED | MAP_POPULATE,
- xsk->fd, XDP_PGOFF_TX_RING);
- if (map == MAP_FAILED) {
+ tx_map = xsk_mmap(NULL, off.tx.desc +
+ xsk->config.tx_size * sizeof(struct xdp_desc),
+ PROT_READ | PROT_WRITE,
+ MAP_SHARED | MAP_POPULATE,
+ xsk->fd, XDP_PGOFF_TX_RING);
+ if (tx_map == MAP_FAILED) {
err = -errno;
goto out_mmap_rx;
}
tx->mask = xsk->config.tx_size - 1;
tx->size = xsk->config.tx_size;
- tx->producer = map + off.tx.producer;
- tx->consumer = map + off.tx.consumer;
- tx->ring = map + off.tx.desc;
+ tx->producer = tx_map + off.tx.producer;
+ tx->consumer = tx_map + off.tx.consumer;
+ tx->ring = tx_map + off.tx.desc;
tx->cached_cons = xsk->config.tx_size;
}
xsk->tx = tx;
@@ -635,6 +643,9 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname,
goto out_mmap_tx;
}
+ xsk->qidconf_map_fd = -1;
+ xsk->xsks_map_fd = -1;
+
if (!(xsk->config.libbpf_flags & XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD)) {
err = xsk_setup_xdp_prog(xsk);
if (err)
@@ -646,13 +657,11 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname,
out_mmap_tx:
if (tx)
- munmap(xsk->tx,
- off.tx.desc +
+ munmap(tx_map, off.tx.desc +
xsk->config.tx_size * sizeof(struct xdp_desc));
out_mmap_rx:
if (rx)
- munmap(xsk->rx,
- off.rx.desc +
+ munmap(rx_map, off.rx.desc +
xsk->config.rx_size * sizeof(struct xdp_desc));
out_socket:
if (--umem->refcount)
@@ -677,9 +686,9 @@ int xsk_umem__delete(struct xsk_umem *umem)
optlen = sizeof(off);
err = getsockopt(umem->fd, SOL_XDP, XDP_MMAP_OFFSETS, &off, &optlen);
if (!err) {
- munmap(umem->fill->ring,
+ munmap(umem->fill->ring - off.fr.desc,
off.fr.desc + umem->config.fill_size * sizeof(__u64));
- munmap(umem->comp->ring,
+ munmap(umem->comp->ring - off.cr.desc,
off.cr.desc + umem->config.comp_size * sizeof(__u64));
}
@@ -691,6 +700,7 @@ int xsk_umem__delete(struct xsk_umem *umem)
void xsk_socket__delete(struct xsk_socket *xsk)
{
+ size_t desc_sz = sizeof(struct xdp_desc);
struct xdp_mmap_offsets off;
socklen_t optlen;
int err;
@@ -698,19 +708,21 @@ void xsk_socket__delete(struct xsk_socket *xsk)
if (!xsk)
return;
- (void)xsk_update_bpf_maps(xsk, 0, 0);
+ xsk_clear_bpf_maps(xsk);
+ xsk_delete_bpf_maps(xsk);
optlen = sizeof(off);
err = getsockopt(xsk->fd, SOL_XDP, XDP_MMAP_OFFSETS, &off, &optlen);
if (!err) {
- if (xsk->rx)
- munmap(xsk->rx->ring,
- off.rx.desc +
- xsk->config.rx_size * sizeof(struct xdp_desc));
- if (xsk->tx)
- munmap(xsk->tx->ring,
- off.tx.desc +
- xsk->config.tx_size * sizeof(struct xdp_desc));
+ if (xsk->rx) {
+ munmap(xsk->rx->ring - off.rx.desc,
+ off.rx.desc + xsk->config.rx_size * desc_sz);
+ }
+ if (xsk->tx) {
+ munmap(xsk->tx->ring - off.tx.desc,
+ off.tx.desc + xsk->config.tx_size * desc_sz);
+ }
+
}
xsk->umem->refcount--;
diff --git a/tools/lib/bpf/xsk.h b/tools/lib/bpf/xsk.h
index a497f00e2962..82ea71a0f3ec 100644
--- a/tools/lib/bpf/xsk.h
+++ b/tools/lib/bpf/xsk.h
@@ -16,6 +16,7 @@
#include <linux/if_xdp.h>
#include "libbpf.h"
+#include "libbpf_util.h"
#ifdef __cplusplus
extern "C" {
@@ -36,6 +37,10 @@ struct name { \
DEFINE_XSK_RING(xsk_ring_prod);
DEFINE_XSK_RING(xsk_ring_cons);
+/* For a detailed explanation on the memory barriers associated with the
+ * ring, please take a look at net/xdp/xsk_queue.h.
+ */
+
struct xsk_umem;
struct xsk_socket;
@@ -105,7 +110,7 @@ static inline __u32 xsk_cons_nb_avail(struct xsk_ring_cons *r, __u32 nb)
static inline size_t xsk_ring_prod__reserve(struct xsk_ring_prod *prod,
size_t nb, __u32 *idx)
{
- if (unlikely(xsk_prod_nb_free(prod, nb) < nb))
+ if (xsk_prod_nb_free(prod, nb) < nb)
return 0;
*idx = prod->cached_prod;
@@ -116,10 +121,10 @@ static inline size_t xsk_ring_prod__reserve(struct xsk_ring_prod *prod,
static inline void xsk_ring_prod__submit(struct xsk_ring_prod *prod, size_t nb)
{
- /* Make sure everything has been written to the ring before signalling
- * this to the kernel.
+ /* Make sure everything has been written to the ring before indicating
+ * this to the kernel by writing the producer pointer.
*/
- smp_wmb();
+ libbpf_smp_wmb();
*prod->producer += nb;
}
@@ -129,11 +134,11 @@ static inline size_t xsk_ring_cons__peek(struct xsk_ring_cons *cons,
{
size_t entries = xsk_cons_nb_avail(cons, nb);
- if (likely(entries > 0)) {
+ if (entries > 0) {
/* Make sure we do not speculatively read the data before
* we have received the packet buffers from the ring.
*/
- smp_rmb();
+ libbpf_smp_rmb();
*idx = cons->cached_cons;
cons->cached_cons += entries;
@@ -144,6 +149,11 @@ static inline size_t xsk_ring_cons__peek(struct xsk_ring_cons *cons,
static inline void xsk_ring_cons__release(struct xsk_ring_cons *cons, size_t nb)
{
+ /* Make sure data has been read before indicating we are done
+ * with the entries by updating the consumer pointer.
+ */
+ libbpf_smp_rwmb();
+
*cons->consumer += nb;
}
diff --git a/tools/lib/traceevent/event-parse-api.c b/tools/lib/traceevent/event-parse-api.c
index d463761a58f4..988587840c80 100644
--- a/tools/lib/traceevent/event-parse-api.c
+++ b/tools/lib/traceevent/event-parse-api.c
@@ -9,6 +9,22 @@
#include "event-utils.h"
/**
+ * tep_get_event - returns the event with the given index
+ * @tep: a handle to the tep_handle
+ * @index: index of the requested event, in the range 0 .. nr_events
+ *
+ * This returns pointer to the element of the events array with the given index
+ * If @tep is NULL, or @index is not in the range 0 .. nr_events, NULL is returned.
+ */
+struct tep_event *tep_get_event(struct tep_handle *tep, int index)
+{
+ if (tep && tep->events && index < tep->nr_events)
+ return tep->events[index];
+
+ return NULL;
+}
+
+/**
* tep_get_first_event - returns the first event in the events array
* @tep: a handle to the tep_handle
*
@@ -17,10 +33,7 @@
*/
struct tep_event *tep_get_first_event(struct tep_handle *tep)
{
- if (tep && tep->events)
- return tep->events[0];
-
- return NULL;
+ return tep_get_event(tep, 0);
}
/**
@@ -32,7 +45,7 @@ struct tep_event *tep_get_first_event(struct tep_handle *tep)
*/
int tep_get_events_count(struct tep_handle *tep)
{
- if(tep)
+ if (tep)
return tep->nr_events;
return 0;
}
@@ -43,19 +56,47 @@ int tep_get_events_count(struct tep_handle *tep)
* @flag: flag, or combination of flags to be set
* can be any combination from enum tep_flag
*
- * This sets a flag or mbination of flags from enum tep_flag
- */
+ * This sets a flag or combination of flags from enum tep_flag
+ */
void tep_set_flag(struct tep_handle *tep, int flag)
{
- if(tep)
+ if (tep)
tep->flags |= flag;
}
-unsigned short tep_data2host2(struct tep_handle *pevent, unsigned short data)
+/**
+ * tep_clear_flag - clear event parser flag
+ * @tep: a handle to the tep_handle
+ * @flag: flag to be cleared
+ *
+ * This clears a tep flag
+ */
+void tep_clear_flag(struct tep_handle *tep, enum tep_flag flag)
+{
+ if (tep)
+ tep->flags &= ~flag;
+}
+
+/**
+ * tep_test_flag - check the state of event parser flag
+ * @tep: a handle to the tep_handle
+ * @flag: flag to be checked
+ *
+ * This returns the state of the requested tep flag.
+ * Returns: true if the flag is set, false otherwise.
+ */
+bool tep_test_flag(struct tep_handle *tep, enum tep_flag flag)
+{
+ if (tep)
+ return tep->flags & flag;
+ return false;
+}
+
+unsigned short tep_data2host2(struct tep_handle *tep, unsigned short data)
{
unsigned short swap;
- if (!pevent || pevent->host_bigendian == pevent->file_bigendian)
+ if (!tep || tep->host_bigendian == tep->file_bigendian)
return data;
swap = ((data & 0xffULL) << 8) |
@@ -64,11 +105,11 @@ unsigned short tep_data2host2(struct tep_handle *pevent, unsigned short data)
return swap;
}
-unsigned int tep_data2host4(struct tep_handle *pevent, unsigned int data)
+unsigned int tep_data2host4(struct tep_handle *tep, unsigned int data)
{
unsigned int swap;
- if (!pevent || pevent->host_bigendian == pevent->file_bigendian)
+ if (!tep || tep->host_bigendian == tep->file_bigendian)
return data;
swap = ((data & 0xffULL) << 24) |
@@ -80,11 +121,11 @@ unsigned int tep_data2host4(struct tep_handle *pevent, unsigned int data)
}
unsigned long long
-tep_data2host8(struct tep_handle *pevent, unsigned long long data)
+tep_data2host8(struct tep_handle *tep, unsigned long long data)
{
unsigned long long swap;
- if (!pevent || pevent->host_bigendian == pevent->file_bigendian)
+ if (!tep || tep->host_bigendian == tep->file_bigendian)
return data;
swap = ((data & 0xffULL) << 56) |
@@ -101,175 +142,232 @@ tep_data2host8(struct tep_handle *pevent, unsigned long long data)
/**
* tep_get_header_page_size - get size of the header page
- * @pevent: a handle to the tep_handle
+ * @tep: a handle to the tep_handle
*
* This returns size of the header page
- * If @pevent is NULL, 0 is returned.
+ * If @tep is NULL, 0 is returned.
+ */
+int tep_get_header_page_size(struct tep_handle *tep)
+{
+ if (tep)
+ return tep->header_page_size_size;
+ return 0;
+}
+
+/**
+ * tep_get_header_timestamp_size - get size of the timestamp in the header page
+ * @tep: a handle to the tep_handle
+ *
+ * This returns size of the timestamp in the header page
+ * If @tep is NULL, 0 is returned.
*/
-int tep_get_header_page_size(struct tep_handle *pevent)
+int tep_get_header_timestamp_size(struct tep_handle *tep)
{
- if(pevent)
- return pevent->header_page_size_size;
+ if (tep)
+ return tep->header_page_ts_size;
return 0;
}
/**
* tep_get_cpus - get the number of CPUs
- * @pevent: a handle to the tep_handle
+ * @tep: a handle to the tep_handle
*
* This returns the number of CPUs
- * If @pevent is NULL, 0 is returned.
+ * If @tep is NULL, 0 is returned.
*/
-int tep_get_cpus(struct tep_handle *pevent)
+int tep_get_cpus(struct tep_handle *tep)
{
- if(pevent)
- return pevent->cpus;
+ if (tep)
+ return tep->cpus;
return 0;
}
/**
* tep_set_cpus - set the number of CPUs
- * @pevent: a handle to the tep_handle
+ * @tep: a handle to the tep_handle
*
* This sets the number of CPUs
*/
-void tep_set_cpus(struct tep_handle *pevent, int cpus)
+void tep_set_cpus(struct tep_handle *tep, int cpus)
{
- if(pevent)
- pevent->cpus = cpus;
+ if (tep)
+ tep->cpus = cpus;
}
/**
- * tep_get_long_size - get the size of a long integer on the current machine
- * @pevent: a handle to the tep_handle
+ * tep_get_long_size - get the size of a long integer on the traced machine
+ * @tep: a handle to the tep_handle
*
- * This returns the size of a long integer on the current machine
- * If @pevent is NULL, 0 is returned.
+ * This returns the size of a long integer on the traced machine
+ * If @tep is NULL, 0 is returned.
*/
-int tep_get_long_size(struct tep_handle *pevent)
+int tep_get_long_size(struct tep_handle *tep)
{
- if(pevent)
- return pevent->long_size;
+ if (tep)
+ return tep->long_size;
return 0;
}
/**
- * tep_set_long_size - set the size of a long integer on the current machine
- * @pevent: a handle to the tep_handle
+ * tep_set_long_size - set the size of a long integer on the traced machine
+ * @tep: a handle to the tep_handle
* @size: size, in bytes, of a long integer
*
- * This sets the size of a long integer on the current machine
+ * This sets the size of a long integer on the traced machine
*/
-void tep_set_long_size(struct tep_handle *pevent, int long_size)
+void tep_set_long_size(struct tep_handle *tep, int long_size)
{
- if(pevent)
- pevent->long_size = long_size;
+ if (tep)
+ tep->long_size = long_size;
}
/**
- * tep_get_page_size - get the size of a memory page on the current machine
- * @pevent: a handle to the tep_handle
+ * tep_get_page_size - get the size of a memory page on the traced machine
+ * @tep: a handle to the tep_handle
*
- * This returns the size of a memory page on the current machine
- * If @pevent is NULL, 0 is returned.
+ * This returns the size of a memory page on the traced machine
+ * If @tep is NULL, 0 is returned.
*/
-int tep_get_page_size(struct tep_handle *pevent)
+int tep_get_page_size(struct tep_handle *tep)
{
- if(pevent)
- return pevent->page_size;
+ if (tep)
+ return tep->page_size;
return 0;
}
/**
- * tep_set_page_size - set the size of a memory page on the current machine
- * @pevent: a handle to the tep_handle
+ * tep_set_page_size - set the size of a memory page on the traced machine
+ * @tep: a handle to the tep_handle
* @_page_size: size of a memory page, in bytes
*
- * This sets the size of a memory page on the current machine
+ * This sets the size of a memory page on the traced machine
*/
-void tep_set_page_size(struct tep_handle *pevent, int _page_size)
+void tep_set_page_size(struct tep_handle *tep, int _page_size)
{
- if(pevent)
- pevent->page_size = _page_size;
+ if (tep)
+ tep->page_size = _page_size;
}
/**
- * tep_file_bigendian - get if the file is in big endian order
- * @pevent: a handle to the tep_handle
+ * tep_is_file_bigendian - return the endian of the file
+ * @tep: a handle to the tep_handle
*
- * This returns if the file is in big endian order
- * If @pevent is NULL, 0 is returned.
+ * This returns true if the file is in big endian order
+ * If @tep is NULL, false is returned.
*/
-int tep_file_bigendian(struct tep_handle *pevent)
+bool tep_is_file_bigendian(struct tep_handle *tep)
{
- if(pevent)
- return pevent->file_bigendian;
- return 0;
+ if (tep)
+ return (tep->file_bigendian == TEP_BIG_ENDIAN);
+ return false;
}
/**
* tep_set_file_bigendian - set if the file is in big endian order
- * @pevent: a handle to the tep_handle
+ * @tep: a handle to the tep_handle
* @endian: non zero, if the file is in big endian order
*
* This sets if the file is in big endian order
*/
-void tep_set_file_bigendian(struct tep_handle *pevent, enum tep_endian endian)
+void tep_set_file_bigendian(struct tep_handle *tep, enum tep_endian endian)
{
- if(pevent)
- pevent->file_bigendian = endian;
+ if (tep)
+ tep->file_bigendian = endian;
}
/**
- * tep_is_host_bigendian - get if the order of the current host is big endian
- * @pevent: a handle to the tep_handle
+ * tep_is_local_bigendian - return the endian of the saved local machine
+ * @tep: a handle to the tep_handle
*
- * This gets if the order of the current host is big endian
- * If @pevent is NULL, 0 is returned.
+ * This returns true if the saved local machine in @tep is big endian.
+ * If @tep is NULL, false is returned.
*/
-int tep_is_host_bigendian(struct tep_handle *pevent)
+bool tep_is_local_bigendian(struct tep_handle *tep)
{
- if(pevent)
- return pevent->host_bigendian;
+ if (tep)
+ return (tep->host_bigendian == TEP_BIG_ENDIAN);
return 0;
}
/**
- * tep_set_host_bigendian - set the order of the local host
- * @pevent: a handle to the tep_handle
+ * tep_set_local_bigendian - set the stored local machine endian order
+ * @tep: a handle to the tep_handle
* @endian: non zero, if the local host has big endian order
*
- * This sets the order of the local host
+ * This sets the endian order for the local machine.
*/
-void tep_set_host_bigendian(struct tep_handle *pevent, enum tep_endian endian)
+void tep_set_local_bigendian(struct tep_handle *tep, enum tep_endian endian)
{
- if(pevent)
- pevent->host_bigendian = endian;
+ if (tep)
+ tep->host_bigendian = endian;
}
/**
* tep_is_latency_format - get if the latency output format is configured
- * @pevent: a handle to the tep_handle
+ * @tep: a handle to the tep_handle
*
- * This gets if the latency output format is configured
- * If @pevent is NULL, 0 is returned.
+ * This returns true if the latency output format is configured
+ * If @tep is NULL, false is returned.
*/
-int tep_is_latency_format(struct tep_handle *pevent)
+bool tep_is_latency_format(struct tep_handle *tep)
{
- if(pevent)
- return pevent->latency_format;
- return 0;
+ if (tep)
+ return (tep->latency_format);
+ return false;
}
/**
* tep_set_latency_format - set the latency output format
- * @pevent: a handle to the tep_handle
+ * @tep: a handle to the tep_handle
* @lat: non zero for latency output format
*
* This sets the latency output format
*/
-void tep_set_latency_format(struct tep_handle *pevent, int lat)
+void tep_set_latency_format(struct tep_handle *tep, int lat)
+{
+ if (tep)
+ tep->latency_format = lat;
+}
+
+/**
+ * tep_is_old_format - get if an old kernel is used
+ * @tep: a handle to the tep_handle
+ *
+ * This returns true, if an old kernel is used to generate the tracing events or
+ * false if a new kernel is used. Old kernels did not have header page info.
+ * If @tep is NULL, false is returned.
+ */
+bool tep_is_old_format(struct tep_handle *tep)
+{
+ if (tep)
+ return tep->old_format;
+ return false;
+}
+
+/**
+ * tep_set_print_raw - set a flag to force print in raw format
+ * @tep: a handle to the tep_handle
+ * @print_raw: the new value of the print_raw flag
+ *
+ * This sets a flag to force print in raw format
+ */
+void tep_set_print_raw(struct tep_handle *tep, int print_raw)
+{
+ if (tep)
+ tep->print_raw = print_raw;
+}
+
+/**
+ * tep_set_test_filters - set a flag to test a filter string
+ * @tep: a handle to the tep_handle
+ * @test_filters: the new value of the test_filters flag
+ *
+ * This sets a flag to test a filter string. If this flag is set, when
+ * tep_filter_add_filter_str() API as called,it will print the filter string
+ * instead of adding it.
+ */
+void tep_set_test_filters(struct tep_handle *tep, int test_filters)
{
- if(pevent)
- pevent->latency_format = lat;
+ if (tep)
+ tep->test_filters = test_filters;
}
diff --git a/tools/lib/traceevent/event-parse-local.h b/tools/lib/traceevent/event-parse-local.h
index 35833ee32d6c..09aa142f7fdd 100644
--- a/tools/lib/traceevent/event-parse-local.h
+++ b/tools/lib/traceevent/event-parse-local.h
@@ -92,8 +92,8 @@ struct tep_handle {
void tep_free_event(struct tep_event *event);
void tep_free_format_field(struct tep_format_field *field);
-unsigned short tep_data2host2(struct tep_handle *pevent, unsigned short data);
-unsigned int tep_data2host4(struct tep_handle *pevent, unsigned int data);
-unsigned long long tep_data2host8(struct tep_handle *pevent, unsigned long long data);
+unsigned short tep_data2host2(struct tep_handle *tep, unsigned short data);
+unsigned int tep_data2host4(struct tep_handle *tep, unsigned int data);
+unsigned long long tep_data2host8(struct tep_handle *tep, unsigned long long data);
#endif /* _PARSE_EVENTS_INT_H */
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 87494c7c619d..b36b536a9fcb 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -148,14 +148,14 @@ struct cmdline_list {
int pid;
};
-static int cmdline_init(struct tep_handle *pevent)
+static int cmdline_init(struct tep_handle *tep)
{
- struct cmdline_list *cmdlist = pevent->cmdlist;
+ struct cmdline_list *cmdlist = tep->cmdlist;
struct cmdline_list *item;
struct tep_cmdline *cmdlines;
int i;
- cmdlines = malloc(sizeof(*cmdlines) * pevent->cmdline_count);
+ cmdlines = malloc(sizeof(*cmdlines) * tep->cmdline_count);
if (!cmdlines)
return -1;
@@ -169,15 +169,15 @@ static int cmdline_init(struct tep_handle *pevent)
free(item);
}
- qsort(cmdlines, pevent->cmdline_count, sizeof(*cmdlines), cmdline_cmp);
+ qsort(cmdlines, tep->cmdline_count, sizeof(*cmdlines), cmdline_cmp);
- pevent->cmdlines = cmdlines;
- pevent->cmdlist = NULL;
+ tep->cmdlines = cmdlines;
+ tep->cmdlist = NULL;
return 0;
}
-static const char *find_cmdline(struct tep_handle *pevent, int pid)
+static const char *find_cmdline(struct tep_handle *tep, int pid)
{
const struct tep_cmdline *comm;
struct tep_cmdline key;
@@ -185,13 +185,13 @@ static const char *find_cmdline(struct tep_handle *pevent, int pid)
if (!pid)
return "<idle>";
- if (!pevent->cmdlines && cmdline_init(pevent))
+ if (!tep->cmdlines && cmdline_init(tep))
return "<not enough memory for cmdlines!>";
key.pid = pid;
- comm = bsearch(&key, pevent->cmdlines, pevent->cmdline_count,
- sizeof(*pevent->cmdlines), cmdline_cmp);
+ comm = bsearch(&key, tep->cmdlines, tep->cmdline_count,
+ sizeof(*tep->cmdlines), cmdline_cmp);
if (comm)
return comm->comm;
@@ -199,32 +199,32 @@ static const char *find_cmdline(struct tep_handle *pevent, int pid)
}
/**
- * tep_pid_is_registered - return if a pid has a cmdline registered
- * @pevent: handle for the pevent
+ * tep_is_pid_registered - return if a pid has a cmdline registered
+ * @tep: a handle to the trace event parser context
* @pid: The pid to check if it has a cmdline registered with.
*
- * Returns 1 if the pid has a cmdline mapped to it
- * 0 otherwise.
+ * Returns true if the pid has a cmdline mapped to it
+ * false otherwise.
*/
-int tep_pid_is_registered(struct tep_handle *pevent, int pid)
+bool tep_is_pid_registered(struct tep_handle *tep, int pid)
{
const struct tep_cmdline *comm;
struct tep_cmdline key;
if (!pid)
- return 1;
+ return true;
- if (!pevent->cmdlines && cmdline_init(pevent))
- return 0;
+ if (!tep->cmdlines && cmdline_init(tep))
+ return false;
key.pid = pid;
- comm = bsearch(&key, pevent->cmdlines, pevent->cmdline_count,
- sizeof(*pevent->cmdlines), cmdline_cmp);
+ comm = bsearch(&key, tep->cmdlines, tep->cmdline_count,
+ sizeof(*tep->cmdlines), cmdline_cmp);
if (comm)
- return 1;
- return 0;
+ return true;
+ return false;
}
/*
@@ -232,10 +232,10 @@ int tep_pid_is_registered(struct tep_handle *pevent, int pid)
* we must add this pid. This is much slower than when cmdlines
* are added before the array is initialized.
*/
-static int add_new_comm(struct tep_handle *pevent,
+static int add_new_comm(struct tep_handle *tep,
const char *comm, int pid, bool override)
{
- struct tep_cmdline *cmdlines = pevent->cmdlines;
+ struct tep_cmdline *cmdlines = tep->cmdlines;
struct tep_cmdline *cmdline;
struct tep_cmdline key;
char *new_comm;
@@ -246,8 +246,8 @@ static int add_new_comm(struct tep_handle *pevent,
/* avoid duplicates */
key.pid = pid;
- cmdline = bsearch(&key, pevent->cmdlines, pevent->cmdline_count,
- sizeof(*pevent->cmdlines), cmdline_cmp);
+ cmdline = bsearch(&key, tep->cmdlines, tep->cmdline_count,
+ sizeof(*tep->cmdlines), cmdline_cmp);
if (cmdline) {
if (!override) {
errno = EEXIST;
@@ -264,37 +264,37 @@ static int add_new_comm(struct tep_handle *pevent,
return 0;
}
- cmdlines = realloc(cmdlines, sizeof(*cmdlines) * (pevent->cmdline_count + 1));
+ cmdlines = realloc(cmdlines, sizeof(*cmdlines) * (tep->cmdline_count + 1));
if (!cmdlines) {
errno = ENOMEM;
return -1;
}
- cmdlines[pevent->cmdline_count].comm = strdup(comm);
- if (!cmdlines[pevent->cmdline_count].comm) {
+ cmdlines[tep->cmdline_count].comm = strdup(comm);
+ if (!cmdlines[tep->cmdline_count].comm) {
free(cmdlines);
errno = ENOMEM;
return -1;
}
- cmdlines[pevent->cmdline_count].pid = pid;
+ cmdlines[tep->cmdline_count].pid = pid;
- if (cmdlines[pevent->cmdline_count].comm)
- pevent->cmdline_count++;
+ if (cmdlines[tep->cmdline_count].comm)
+ tep->cmdline_count++;
- qsort(cmdlines, pevent->cmdline_count, sizeof(*cmdlines), cmdline_cmp);
- pevent->cmdlines = cmdlines;
+ qsort(cmdlines, tep->cmdline_count, sizeof(*cmdlines), cmdline_cmp);
+ tep->cmdlines = cmdlines;
return 0;
}
-static int _tep_register_comm(struct tep_handle *pevent,
+static int _tep_register_comm(struct tep_handle *tep,
const char *comm, int pid, bool override)
{
struct cmdline_list *item;
- if (pevent->cmdlines)
- return add_new_comm(pevent, comm, pid, override);
+ if (tep->cmdlines)
+ return add_new_comm(tep, comm, pid, override);
item = malloc(sizeof(*item));
if (!item)
@@ -309,17 +309,17 @@ static int _tep_register_comm(struct tep_handle *pevent,
return -1;
}
item->pid = pid;
- item->next = pevent->cmdlist;
+ item->next = tep->cmdlist;
- pevent->cmdlist = item;
- pevent->cmdline_count++;
+ tep->cmdlist = item;
+ tep->cmdline_count++;
return 0;
}
/**
* tep_register_comm - register a pid / comm mapping
- * @pevent: handle for the pevent
+ * @tep: a handle to the trace event parser context
* @comm: the command line to register
* @pid: the pid to map the command line to
*
@@ -327,14 +327,14 @@ static int _tep_register_comm(struct tep_handle *pevent,
* a given pid. The comm is duplicated. If a command with the same pid
* already exist, -1 is returned and errno is set to EEXIST
*/
-int tep_register_comm(struct tep_handle *pevent, const char *comm, int pid)
+int tep_register_comm(struct tep_handle *tep, const char *comm, int pid)
{
- return _tep_register_comm(pevent, comm, pid, false);
+ return _tep_register_comm(tep, comm, pid, false);
}
/**
* tep_override_comm - register a pid / comm mapping
- * @pevent: handle for the pevent
+ * @tep: a handle to the trace event parser context
* @comm: the command line to register
* @pid: the pid to map the command line to
*
@@ -342,19 +342,19 @@ int tep_register_comm(struct tep_handle *pevent, const char *comm, int pid)
* a given pid. The comm is duplicated. If a command with the same pid
* already exist, the command string is udapted with the new one
*/
-int tep_override_comm(struct tep_handle *pevent, const char *comm, int pid)
+int tep_override_comm(struct tep_handle *tep, const char *comm, int pid)
{
- if (!pevent->cmdlines && cmdline_init(pevent)) {
+ if (!tep->cmdlines && cmdline_init(tep)) {
errno = ENOMEM;
return -1;
}
- return _tep_register_comm(pevent, comm, pid, true);
+ return _tep_register_comm(tep, comm, pid, true);
}
-int tep_register_trace_clock(struct tep_handle *pevent, const char *trace_clock)
+int tep_register_trace_clock(struct tep_handle *tep, const char *trace_clock)
{
- pevent->trace_clock = strdup(trace_clock);
- if (!pevent->trace_clock) {
+ tep->trace_clock = strdup(trace_clock);
+ if (!tep->trace_clock) {
errno = ENOMEM;
return -1;
}
@@ -408,18 +408,18 @@ static int func_bcmp(const void *a, const void *b)
return 1;
}
-static int func_map_init(struct tep_handle *pevent)
+static int func_map_init(struct tep_handle *tep)
{
struct func_list *funclist;
struct func_list *item;
struct func_map *func_map;
int i;
- func_map = malloc(sizeof(*func_map) * (pevent->func_count + 1));
+ func_map = malloc(sizeof(*func_map) * (tep->func_count + 1));
if (!func_map)
return -1;
- funclist = pevent->funclist;
+ funclist = tep->funclist;
i = 0;
while (funclist) {
@@ -432,34 +432,34 @@ static int func_map_init(struct tep_handle *pevent)
free(item);
}
- qsort(func_map, pevent->func_count, sizeof(*func_map), func_cmp);
+ qsort(func_map, tep->func_count, sizeof(*func_map), func_cmp);
/*
* Add a special record at the end.
*/
- func_map[pevent->func_count].func = NULL;
- func_map[pevent->func_count].addr = 0;
- func_map[pevent->func_count].mod = NULL;
+ func_map[tep->func_count].func = NULL;
+ func_map[tep->func_count].addr = 0;
+ func_map[tep->func_count].mod = NULL;
- pevent->func_map = func_map;
- pevent->funclist = NULL;
+ tep->func_map = func_map;
+ tep->funclist = NULL;
return 0;
}
static struct func_map *
-__find_func(struct tep_handle *pevent, unsigned long long addr)
+__find_func(struct tep_handle *tep, unsigned long long addr)
{
struct func_map *func;
struct func_map key;
- if (!pevent->func_map)
- func_map_init(pevent);
+ if (!tep->func_map)
+ func_map_init(tep);
key.addr = addr;
- func = bsearch(&key, pevent->func_map, pevent->func_count,
- sizeof(*pevent->func_map), func_bcmp);
+ func = bsearch(&key, tep->func_map, tep->func_count,
+ sizeof(*tep->func_map), func_bcmp);
return func;
}
@@ -472,15 +472,14 @@ struct func_resolver {
/**
* tep_set_function_resolver - set an alternative function resolver
- * @pevent: handle for the pevent
+ * @tep: a handle to the trace event parser context
* @resolver: function to be used
* @priv: resolver function private state.
*
* Some tools may have already a way to resolve kernel functions, allow them to
- * keep using it instead of duplicating all the entries inside
- * pevent->funclist.
+ * keep using it instead of duplicating all the entries inside tep->funclist.
*/
-int tep_set_function_resolver(struct tep_handle *pevent,
+int tep_set_function_resolver(struct tep_handle *tep,
tep_func_resolver_t *func, void *priv)
{
struct func_resolver *resolver = malloc(sizeof(*resolver));
@@ -491,38 +490,38 @@ int tep_set_function_resolver(struct tep_handle *pevent,
resolver->func = func;
resolver->priv = priv;
- free(pevent->func_resolver);
- pevent->func_resolver = resolver;
+ free(tep->func_resolver);
+ tep->func_resolver = resolver;
return 0;
}
/**
* tep_reset_function_resolver - reset alternative function resolver
- * @pevent: handle for the pevent
+ * @tep: a handle to the trace event parser context
*
* Stop using whatever alternative resolver was set, use the default
* one instead.
*/
-void tep_reset_function_resolver(struct tep_handle *pevent)
+void tep_reset_function_resolver(struct tep_handle *tep)
{
- free(pevent->func_resolver);
- pevent->func_resolver = NULL;
+ free(tep->func_resolver);
+ tep->func_resolver = NULL;
}
static struct func_map *
-find_func(struct tep_handle *pevent, unsigned long long addr)
+find_func(struct tep_handle *tep, unsigned long long addr)
{
struct func_map *map;
- if (!pevent->func_resolver)
- return __find_func(pevent, addr);
+ if (!tep->func_resolver)
+ return __find_func(tep, addr);
- map = &pevent->func_resolver->map;
+ map = &tep->func_resolver->map;
map->mod = NULL;
map->addr = addr;
- map->func = pevent->func_resolver->func(pevent->func_resolver->priv,
- &map->addr, &map->mod);
+ map->func = tep->func_resolver->func(tep->func_resolver->priv,
+ &map->addr, &map->mod);
if (map->func == NULL)
return NULL;
@@ -531,18 +530,18 @@ find_func(struct tep_handle *pevent, unsigned long long addr)
/**
* tep_find_function - find a function by a given address
- * @pevent: handle for the pevent
+ * @tep: a handle to the trace event parser context
* @addr: the address to find the function with
*
* Returns a pointer to the function stored that has the given
* address. Note, the address does not have to be exact, it
* will select the function that would contain the address.
*/
-const char *tep_find_function(struct tep_handle *pevent, unsigned long long addr)
+const char *tep_find_function(struct tep_handle *tep, unsigned long long addr)
{
struct func_map *map;
- map = find_func(pevent, addr);
+ map = find_func(tep, addr);
if (!map)
return NULL;
@@ -551,7 +550,7 @@ const char *tep_find_function(struct tep_handle *pevent, unsigned long long addr
/**
* tep_find_function_address - find a function address by a given address
- * @pevent: handle for the pevent
+ * @tep: a handle to the trace event parser context
* @addr: the address to find the function with
*
* Returns the address the function starts at. This can be used in
@@ -559,11 +558,11 @@ const char *tep_find_function(struct tep_handle *pevent, unsigned long long addr
* name and the function offset.
*/
unsigned long long
-tep_find_function_address(struct tep_handle *pevent, unsigned long long addr)
+tep_find_function_address(struct tep_handle *tep, unsigned long long addr)
{
struct func_map *map;
- map = find_func(pevent, addr);
+ map = find_func(tep, addr);
if (!map)
return 0;
@@ -572,7 +571,7 @@ tep_find_function_address(struct tep_handle *pevent, unsigned long long addr)
/**
* tep_register_function - register a function with a given address
- * @pevent: handle for the pevent
+ * @tep: a handle to the trace event parser context
* @function: the function name to register
* @addr: the address the function starts at
* @mod: the kernel module the function may be in (NULL for none)
@@ -580,7 +579,7 @@ tep_find_function_address(struct tep_handle *pevent, unsigned long long addr)
* This registers a function name with an address and module.
* The @func passed in is duplicated.
*/
-int tep_register_function(struct tep_handle *pevent, char *func,
+int tep_register_function(struct tep_handle *tep, char *func,
unsigned long long addr, char *mod)
{
struct func_list *item = malloc(sizeof(*item));
@@ -588,7 +587,7 @@ int tep_register_function(struct tep_handle *pevent, char *func,
if (!item)
return -1;
- item->next = pevent->funclist;
+ item->next = tep->funclist;
item->func = strdup(func);
if (!item->func)
goto out_free;
@@ -601,8 +600,8 @@ int tep_register_function(struct tep_handle *pevent, char *func,
item->mod = NULL;
item->addr = addr;
- pevent->funclist = item;
- pevent->func_count++;
+ tep->funclist = item;
+ tep->func_count++;
return 0;
@@ -617,23 +616,23 @@ out_free:
/**
* tep_print_funcs - print out the stored functions
- * @pevent: handle for the pevent
+ * @tep: a handle to the trace event parser context
*
* This prints out the stored functions.
*/
-void tep_print_funcs(struct tep_handle *pevent)
+void tep_print_funcs(struct tep_handle *tep)
{
int i;
- if (!pevent->func_map)
- func_map_init(pevent);
+ if (!tep->func_map)
+ func_map_init(tep);
- for (i = 0; i < (int)pevent->func_count; i++) {
+ for (i = 0; i < (int)tep->func_count; i++) {
printf("%016llx %s",
- pevent->func_map[i].addr,
- pevent->func_map[i].func);
- if (pevent->func_map[i].mod)
- printf(" [%s]\n", pevent->func_map[i].mod);
+ tep->func_map[i].addr,
+ tep->func_map[i].func);
+ if (tep->func_map[i].mod)
+ printf(" [%s]\n", tep->func_map[i].mod);
else
printf("\n");
}
@@ -663,18 +662,18 @@ static int printk_cmp(const void *a, const void *b)
return 0;
}
-static int printk_map_init(struct tep_handle *pevent)
+static int printk_map_init(struct tep_handle *tep)
{
struct printk_list *printklist;
struct printk_list *item;
struct printk_map *printk_map;
int i;
- printk_map = malloc(sizeof(*printk_map) * (pevent->printk_count + 1));
+ printk_map = malloc(sizeof(*printk_map) * (tep->printk_count + 1));
if (!printk_map)
return -1;
- printklist = pevent->printklist;
+ printklist = tep->printklist;
i = 0;
while (printklist) {
@@ -686,41 +685,41 @@ static int printk_map_init(struct tep_handle *pevent)
free(item);
}
- qsort(printk_map, pevent->printk_count, sizeof(*printk_map), printk_cmp);
+ qsort(printk_map, tep->printk_count, sizeof(*printk_map), printk_cmp);
- pevent->printk_map = printk_map;
- pevent->printklist = NULL;
+ tep->printk_map = printk_map;
+ tep->printklist = NULL;
return 0;
}
static struct printk_map *
-find_printk(struct tep_handle *pevent, unsigned long long addr)
+find_printk(struct tep_handle *tep, unsigned long long addr)
{
struct printk_map *printk;
struct printk_map key;
- if (!pevent->printk_map && printk_map_init(pevent))
+ if (!tep->printk_map && printk_map_init(tep))
return NULL;
key.addr = addr;
- printk = bsearch(&key, pevent->printk_map, pevent->printk_count,
- sizeof(*pevent->printk_map), printk_cmp);
+ printk = bsearch(&key, tep->printk_map, tep->printk_count,
+ sizeof(*tep->printk_map), printk_cmp);
return printk;
}
/**
* tep_register_print_string - register a string by its address
- * @pevent: handle for the pevent
+ * @tep: a handle to the trace event parser context
* @fmt: the string format to register
* @addr: the address the string was located at
*
* This registers a string by the address it was stored in the kernel.
* The @fmt passed in is duplicated.
*/
-int tep_register_print_string(struct tep_handle *pevent, const char *fmt,
+int tep_register_print_string(struct tep_handle *tep, const char *fmt,
unsigned long long addr)
{
struct printk_list *item = malloc(sizeof(*item));
@@ -729,7 +728,7 @@ int tep_register_print_string(struct tep_handle *pevent, const char *fmt,
if (!item)
return -1;
- item->next = pevent->printklist;
+ item->next = tep->printklist;
item->addr = addr;
/* Strip off quotes and '\n' from the end */
@@ -747,8 +746,8 @@ int tep_register_print_string(struct tep_handle *pevent, const char *fmt,
if (strcmp(p, "\\n") == 0)
*p = 0;
- pevent->printklist = item;
- pevent->printk_count++;
+ tep->printklist = item;
+ tep->printk_count++;
return 0;
@@ -760,21 +759,21 @@ out_free:
/**
* tep_print_printk - print out the stored strings
- * @pevent: handle for the pevent
+ * @tep: a handle to the trace event parser context
*
* This prints the string formats that were stored.
*/
-void tep_print_printk(struct tep_handle *pevent)
+void tep_print_printk(struct tep_handle *tep)
{
int i;
- if (!pevent->printk_map)
- printk_map_init(pevent);
+ if (!tep->printk_map)
+ printk_map_init(tep);
- for (i = 0; i < (int)pevent->printk_count; i++) {
+ for (i = 0; i < (int)tep->printk_count; i++) {
printf("%016llx %s\n",
- pevent->printk_map[i].addr,
- pevent->printk_map[i].printk);
+ tep->printk_map[i].addr,
+ tep->printk_map[i].printk);
}
}
@@ -783,29 +782,29 @@ static struct tep_event *alloc_event(void)
return calloc(1, sizeof(struct tep_event));
}
-static int add_event(struct tep_handle *pevent, struct tep_event *event)
+static int add_event(struct tep_handle *tep, struct tep_event *event)
{
int i;
- struct tep_event **events = realloc(pevent->events, sizeof(event) *
- (pevent->nr_events + 1));
+ struct tep_event **events = realloc(tep->events, sizeof(event) *
+ (tep->nr_events + 1));
if (!events)
return -1;
- pevent->events = events;
+ tep->events = events;
- for (i = 0; i < pevent->nr_events; i++) {
- if (pevent->events[i]->id > event->id)
+ for (i = 0; i < tep->nr_events; i++) {
+ if (tep->events[i]->id > event->id)
break;
}
- if (i < pevent->nr_events)
- memmove(&pevent->events[i + 1],
- &pevent->events[i],
- sizeof(event) * (pevent->nr_events - i));
+ if (i < tep->nr_events)
+ memmove(&tep->events[i + 1],
+ &tep->events[i],
+ sizeof(event) * (tep->nr_events - i));
- pevent->events[i] = event;
- pevent->nr_events++;
+ tep->events[i] = event;
+ tep->nr_events++;
- event->pevent = pevent;
+ event->tep = tep;
return 0;
}
@@ -1184,7 +1183,7 @@ static enum tep_event_type read_token(char **tok)
}
/**
- * tep_read_token - access to utilities to use the pevent parser
+ * tep_read_token - access to utilities to use the tep parser
* @tok: The token to return
*
* This will parse tokens from the string given by
@@ -1657,8 +1656,8 @@ static int event_read_fields(struct tep_event *event, struct tep_format_field **
else if (field->flags & TEP_FIELD_IS_STRING)
field->elementsize = 1;
else if (field->flags & TEP_FIELD_IS_LONG)
- field->elementsize = event->pevent ?
- event->pevent->long_size :
+ field->elementsize = event->tep ?
+ event->tep->long_size :
sizeof(long);
} else
field->elementsize = field->size;
@@ -2233,7 +2232,7 @@ eval_type_str(unsigned long long val, const char *type, int pointer)
return val & 0xffffffff;
if (strcmp(type, "u64") == 0 ||
- strcmp(type, "s64"))
+ strcmp(type, "s64") == 0)
return val;
if (strcmp(type, "s8") == 0)
@@ -2942,14 +2941,14 @@ process_bitmask(struct tep_event *event __maybe_unused, struct tep_print_arg *ar
}
static struct tep_function_handler *
-find_func_handler(struct tep_handle *pevent, char *func_name)
+find_func_handler(struct tep_handle *tep, char *func_name)
{
struct tep_function_handler *func;
- if (!pevent)
+ if (!tep)
return NULL;
- for (func = pevent->func_handlers; func; func = func->next) {
+ for (func = tep->func_handlers; func; func = func->next) {
if (strcmp(func->name, func_name) == 0)
break;
}
@@ -2957,12 +2956,12 @@ find_func_handler(struct tep_handle *pevent, char *func_name)
return func;
}
-static void remove_func_handler(struct tep_handle *pevent, char *func_name)
+static void remove_func_handler(struct tep_handle *tep, char *func_name)
{
struct tep_function_handler *func;
struct tep_function_handler **next;
- next = &pevent->func_handlers;
+ next = &tep->func_handlers;
while ((func = *next)) {
if (strcmp(func->name, func_name) == 0) {
*next = func->next;
@@ -3076,7 +3075,7 @@ process_function(struct tep_event *event, struct tep_print_arg *arg,
return process_dynamic_array_len(event, arg, tok);
}
- func = find_func_handler(event->pevent, token);
+ func = find_func_handler(event->tep, token);
if (func) {
free_token(token);
return process_func_handler(event, func, arg, tok);
@@ -3357,14 +3356,14 @@ tep_find_any_field(struct tep_event *event, const char *name)
/**
* tep_read_number - read a number from data
- * @pevent: handle for the pevent
+ * @tep: a handle to the trace event parser context
* @ptr: the raw data
* @size: the size of the data that holds the number
*
* Returns the number (converted to host) from the
* raw data.
*/
-unsigned long long tep_read_number(struct tep_handle *pevent,
+unsigned long long tep_read_number(struct tep_handle *tep,
const void *ptr, int size)
{
unsigned long long val;
@@ -3373,12 +3372,12 @@ unsigned long long tep_read_number(struct tep_handle *pevent,
case 1:
return *(unsigned char *)ptr;
case 2:
- return tep_data2host2(pevent, *(unsigned short *)ptr);
+ return tep_data2host2(tep, *(unsigned short *)ptr);
case 4:
- return tep_data2host4(pevent, *(unsigned int *)ptr);
+ return tep_data2host4(tep, *(unsigned int *)ptr);
case 8:
memcpy(&val, (ptr), sizeof(unsigned long long));
- return tep_data2host8(pevent, val);
+ return tep_data2host8(tep, val);
default:
/* BUG! */
return 0;
@@ -3406,7 +3405,7 @@ int tep_read_number_field(struct tep_format_field *field, const void *data,
case 2:
case 4:
case 8:
- *value = tep_read_number(field->event->pevent,
+ *value = tep_read_number(field->event->tep,
data + field->offset, field->size);
return 0;
default:
@@ -3414,7 +3413,7 @@ int tep_read_number_field(struct tep_format_field *field, const void *data,
}
}
-static int get_common_info(struct tep_handle *pevent,
+static int get_common_info(struct tep_handle *tep,
const char *type, int *offset, int *size)
{
struct tep_event *event;
@@ -3424,12 +3423,12 @@ static int get_common_info(struct tep_handle *pevent,
* All events should have the same common elements.
* Pick any event to find where the type is;
*/
- if (!pevent->events) {
+ if (!tep->events) {
do_warning("no event_list!");
return -1;
}
- event = pevent->events[0];
+ event = tep->events[0];
field = tep_find_common_field(event, type);
if (!field)
return -1;
@@ -3440,58 +3439,58 @@ static int get_common_info(struct tep_handle *pevent,
return 0;
}
-static int __parse_common(struct tep_handle *pevent, void *data,
+static int __parse_common(struct tep_handle *tep, void *data,
int *size, int *offset, const char *name)
{
int ret;
if (!*size) {
- ret = get_common_info(pevent, name, offset, size);
+ ret = get_common_info(tep, name, offset, size);
if (ret < 0)
return ret;
}
- return tep_read_number(pevent, data + *offset, *size);
+ return tep_read_number(tep, data + *offset, *size);
}
-static int trace_parse_common_type(struct tep_handle *pevent, void *data)
+static int trace_parse_common_type(struct tep_handle *tep, void *data)
{
- return __parse_common(pevent, data,
- &pevent->type_size, &pevent->type_offset,
+ return __parse_common(tep, data,
+ &tep->type_size, &tep->type_offset,
"common_type");
}
-static int parse_common_pid(struct tep_handle *pevent, void *data)
+static int parse_common_pid(struct tep_handle *tep, void *data)
{
- return __parse_common(pevent, data,
- &pevent->pid_size, &pevent->pid_offset,
+ return __parse_common(tep, data,
+ &tep->pid_size, &tep->pid_offset,
"common_pid");
}
-static int parse_common_pc(struct tep_handle *pevent, void *data)
+static int parse_common_pc(struct tep_handle *tep, void *data)
{
- return __parse_common(pevent, data,
- &pevent->pc_size, &pevent->pc_offset,
+ return __parse_common(tep, data,
+ &tep->pc_size, &tep->pc_offset,
"common_preempt_count");
}
-static int parse_common_flags(struct tep_handle *pevent, void *data)
+static int parse_common_flags(struct tep_handle *tep, void *data)
{
- return __parse_common(pevent, data,
- &pevent->flags_size, &pevent->flags_offset,
+ return __parse_common(tep, data,
+ &tep->flags_size, &tep->flags_offset,
"common_flags");
}
-static int parse_common_lock_depth(struct tep_handle *pevent, void *data)
+static int parse_common_lock_depth(struct tep_handle *tep, void *data)
{
- return __parse_common(pevent, data,
- &pevent->ld_size, &pevent->ld_offset,
+ return __parse_common(tep, data,
+ &tep->ld_size, &tep->ld_offset,
"common_lock_depth");
}
-static int parse_common_migrate_disable(struct tep_handle *pevent, void *data)
+static int parse_common_migrate_disable(struct tep_handle *tep, void *data)
{
- return __parse_common(pevent, data,
- &pevent->ld_size, &pevent->ld_offset,
+ return __parse_common(tep, data,
+ &tep->ld_size, &tep->ld_offset,
"common_migrate_disable");
}
@@ -3499,28 +3498,28 @@ static int events_id_cmp(const void *a, const void *b);
/**
* tep_find_event - find an event by given id
- * @pevent: a handle to the pevent
+ * @tep: a handle to the trace event parser context
* @id: the id of the event
*
* Returns an event that has a given @id.
*/
-struct tep_event *tep_find_event(struct tep_handle *pevent, int id)
+struct tep_event *tep_find_event(struct tep_handle *tep, int id)
{
struct tep_event **eventptr;
struct tep_event key;
struct tep_event *pkey = &key;
/* Check cache first */
- if (pevent->last_event && pevent->last_event->id == id)
- return pevent->last_event;
+ if (tep->last_event && tep->last_event->id == id)
+ return tep->last_event;
key.id = id;
- eventptr = bsearch(&pkey, pevent->events, pevent->nr_events,
- sizeof(*pevent->events), events_id_cmp);
+ eventptr = bsearch(&pkey, tep->events, tep->nr_events,
+ sizeof(*tep->events), events_id_cmp);
if (eventptr) {
- pevent->last_event = *eventptr;
+ tep->last_event = *eventptr;
return *eventptr;
}
@@ -3529,7 +3528,7 @@ struct tep_event *tep_find_event(struct tep_handle *pevent, int id)
/**
* tep_find_event_by_name - find an event by given name
- * @pevent: a handle to the pevent
+ * @tep: a handle to the trace event parser context
* @sys: the system name to search for
* @name: the name of the event to search for
*
@@ -3537,19 +3536,19 @@ struct tep_event *tep_find_event(struct tep_handle *pevent, int id)
* @sys. If @sys is NULL the first event with @name is returned.
*/
struct tep_event *
-tep_find_event_by_name(struct tep_handle *pevent,
+tep_find_event_by_name(struct tep_handle *tep,
const char *sys, const char *name)
{
struct tep_event *event = NULL;
int i;
- if (pevent->last_event &&
- strcmp(pevent->last_event->name, name) == 0 &&
- (!sys || strcmp(pevent->last_event->system, sys) == 0))
- return pevent->last_event;
+ if (tep->last_event &&
+ strcmp(tep->last_event->name, name) == 0 &&
+ (!sys || strcmp(tep->last_event->system, sys) == 0))
+ return tep->last_event;
- for (i = 0; i < pevent->nr_events; i++) {
- event = pevent->events[i];
+ for (i = 0; i < tep->nr_events; i++) {
+ event = tep->events[i];
if (strcmp(event->name, name) == 0) {
if (!sys)
break;
@@ -3557,17 +3556,17 @@ tep_find_event_by_name(struct tep_handle *pevent,
break;
}
}
- if (i == pevent->nr_events)
+ if (i == tep->nr_events)
event = NULL;
- pevent->last_event = event;
+ tep->last_event = event;
return event;
}
static unsigned long long
eval_num_arg(void *data, int size, struct tep_event *event, struct tep_print_arg *arg)
{
- struct tep_handle *pevent = event->pevent;
+ struct tep_handle *tep = event->tep;
unsigned long long val = 0;
unsigned long long left, right;
struct tep_print_arg *typearg = NULL;
@@ -3589,7 +3588,7 @@ eval_num_arg(void *data, int size, struct tep_event *event, struct tep_print_arg
}
/* must be a number */
- val = tep_read_number(pevent, data + arg->field.field->offset,
+ val = tep_read_number(tep, data + arg->field.field->offset,
arg->field.field->size);
break;
case TEP_PRINT_FLAGS:
@@ -3629,11 +3628,11 @@ eval_num_arg(void *data, int size, struct tep_event *event, struct tep_print_arg
}
/* Default to long size */
- field_size = pevent->long_size;
+ field_size = tep->long_size;
switch (larg->type) {
case TEP_PRINT_DYNAMIC_ARRAY:
- offset = tep_read_number(pevent,
+ offset = tep_read_number(tep,
data + larg->dynarray.field->offset,
larg->dynarray.field->size);
if (larg->dynarray.field->elementsize)
@@ -3662,7 +3661,7 @@ eval_num_arg(void *data, int size, struct tep_event *event, struct tep_print_arg
default:
goto default_op; /* oops, all bets off */
}
- val = tep_read_number(pevent,
+ val = tep_read_number(tep,
data + offset, field_size);
if (typearg)
val = eval_type(val, typearg, 1);
@@ -3763,7 +3762,7 @@ eval_num_arg(void *data, int size, struct tep_event *event, struct tep_print_arg
}
break;
case TEP_PRINT_DYNAMIC_ARRAY_LEN:
- offset = tep_read_number(pevent,
+ offset = tep_read_number(tep,
data + arg->dynarray.field->offset,
arg->dynarray.field->size);
/*
@@ -3775,7 +3774,7 @@ eval_num_arg(void *data, int size, struct tep_event *event, struct tep_print_arg
break;
case TEP_PRINT_DYNAMIC_ARRAY:
/* Without [], we pass the address to the dynamic data */
- offset = tep_read_number(pevent,
+ offset = tep_read_number(tep,
data + arg->dynarray.field->offset,
arg->dynarray.field->size);
/*
@@ -3850,7 +3849,7 @@ static void print_str_to_seq(struct trace_seq *s, const char *format,
trace_seq_printf(s, format, str);
}
-static void print_bitmask_to_seq(struct tep_handle *pevent,
+static void print_bitmask_to_seq(struct tep_handle *tep,
struct trace_seq *s, const char *format,
int len_arg, const void *data, int size)
{
@@ -3882,7 +3881,7 @@ static void print_bitmask_to_seq(struct tep_handle *pevent,
* In the kernel, this is an array of long words, thus
* endianness is very important.
*/
- if (pevent->file_bigendian)
+ if (tep->file_bigendian)
index = size - (len + 1);
else
index = len;
@@ -3908,7 +3907,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
struct tep_event *event, const char *format,
int len_arg, struct tep_print_arg *arg)
{
- struct tep_handle *pevent = event->pevent;
+ struct tep_handle *tep = event->tep;
struct tep_print_flag_sym *flag;
struct tep_format_field *field;
struct printk_map *printk;
@@ -3945,7 +3944,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
* is a pointer.
*/
if (!(field->flags & TEP_FIELD_IS_ARRAY) &&
- field->size == pevent->long_size) {
+ field->size == tep->long_size) {
/* Handle heterogeneous recording and processing
* architectures
@@ -3960,12 +3959,12 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
* on 32-bit devices:
* In this case, 64 bits must be read.
*/
- addr = (pevent->long_size == 8) ?
+ addr = (tep->long_size == 8) ?
*(unsigned long long *)(data + field->offset) :
(unsigned long long)*(unsigned int *)(data + field->offset);
/* Check if it matches a print format */
- printk = find_printk(pevent, addr);
+ printk = find_printk(tep, addr);
if (printk)
trace_seq_puts(s, printk->printk);
else
@@ -4022,7 +4021,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
case TEP_PRINT_HEX_STR:
if (arg->hex.field->type == TEP_PRINT_DYNAMIC_ARRAY) {
unsigned long offset;
- offset = tep_read_number(pevent,
+ offset = tep_read_number(tep,
data + arg->hex.field->dynarray.field->offset,
arg->hex.field->dynarray.field->size);
hex = data + (offset & 0xffff);
@@ -4053,7 +4052,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
unsigned long offset;
struct tep_format_field *field =
arg->int_array.field->dynarray.field;
- offset = tep_read_number(pevent,
+ offset = tep_read_number(tep,
data + field->offset,
field->size);
num = data + (offset & 0xffff);
@@ -4104,7 +4103,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
f = tep_find_any_field(event, arg->string.string);
arg->string.offset = f->offset;
}
- str_offset = tep_data2host4(pevent, *(unsigned int *)(data + arg->string.offset));
+ str_offset = tep_data2host4(tep, *(unsigned int *)(data + arg->string.offset));
str_offset &= 0xffff;
print_str_to_seq(s, format, len_arg, ((char *)data) + str_offset);
break;
@@ -4122,10 +4121,10 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
f = tep_find_any_field(event, arg->bitmask.bitmask);
arg->bitmask.offset = f->offset;
}
- bitmask_offset = tep_data2host4(pevent, *(unsigned int *)(data + arg->bitmask.offset));
+ bitmask_offset = tep_data2host4(tep, *(unsigned int *)(data + arg->bitmask.offset));
bitmask_size = bitmask_offset >> 16;
bitmask_offset &= 0xffff;
- print_bitmask_to_seq(pevent, s, format, len_arg,
+ print_bitmask_to_seq(tep, s, format, len_arg,
data + bitmask_offset, bitmask_size);
break;
}
@@ -4257,7 +4256,7 @@ static void free_args(struct tep_print_arg *args)
static struct tep_print_arg *make_bprint_args(char *fmt, void *data, int size, struct tep_event *event)
{
- struct tep_handle *pevent = event->pevent;
+ struct tep_handle *tep = event->tep;
struct tep_format_field *field, *ip_field;
struct tep_print_arg *args, *arg, **next;
unsigned long long ip, val;
@@ -4265,8 +4264,8 @@ static struct tep_print_arg *make_bprint_args(char *fmt, void *data, int size, s
void *bptr;
int vsize = 0;
- field = pevent->bprint_buf_field;
- ip_field = pevent->bprint_ip_field;
+ field = tep->bprint_buf_field;
+ ip_field = tep->bprint_ip_field;
if (!field) {
field = tep_find_field(event, "buf");
@@ -4279,11 +4278,11 @@ static struct tep_print_arg *make_bprint_args(char *fmt, void *data, int size, s
do_warning_event(event, "can't find ip field for binary printk");
return NULL;
}
- pevent->bprint_buf_field = field;
- pevent->bprint_ip_field = ip_field;
+ tep->bprint_buf_field = field;
+ tep->bprint_ip_field = ip_field;
}
- ip = tep_read_number(pevent, data + ip_field->offset, ip_field->size);
+ ip = tep_read_number(tep, data + ip_field->offset, ip_field->size);
/*
* The first arg is the IP pointer.
@@ -4338,6 +4337,7 @@ static struct tep_print_arg *make_bprint_args(char *fmt, void *data, int size, s
case 'S':
case 'f':
case 'F':
+ case 'x':
break;
default:
/*
@@ -4360,7 +4360,7 @@ static struct tep_print_arg *make_bprint_args(char *fmt, void *data, int size, s
vsize = 4;
break;
case 1:
- vsize = pevent->long_size;
+ vsize = tep->long_size;
break;
case 2:
vsize = 8;
@@ -4377,7 +4377,7 @@ static struct tep_print_arg *make_bprint_args(char *fmt, void *data, int size, s
/* the pointers are always 4 bytes aligned */
bptr = (void *)(((unsigned long)bptr + 3) &
~3);
- val = tep_read_number(pevent, bptr, vsize);
+ val = tep_read_number(tep, bptr, vsize);
bptr += vsize;
arg = alloc_arg();
if (!arg) {
@@ -4434,13 +4434,13 @@ static char *
get_bprint_format(void *data, int size __maybe_unused,
struct tep_event *event)
{
- struct tep_handle *pevent = event->pevent;
+ struct tep_handle *tep = event->tep;
unsigned long long addr;
struct tep_format_field *field;
struct printk_map *printk;
char *format;
- field = pevent->bprint_fmt_field;
+ field = tep->bprint_fmt_field;
if (!field) {
field = tep_find_field(event, "fmt");
@@ -4448,12 +4448,12 @@ get_bprint_format(void *data, int size __maybe_unused,
do_warning_event(event, "can't find format field for binary printk");
return NULL;
}
- pevent->bprint_fmt_field = field;
+ tep->bprint_fmt_field = field;
}
- addr = tep_read_number(pevent, data + field->offset, field->size);
+ addr = tep_read_number(tep, data + field->offset, field->size);
- printk = find_printk(pevent, addr);
+ printk = find_printk(tep, addr);
if (!printk) {
if (asprintf(&format, "%%pf: (NO FORMAT FOUND at %llx)\n", addr) < 0)
return NULL;
@@ -4835,13 +4835,13 @@ void tep_print_field(struct trace_seq *s, void *data,
{
unsigned long long val;
unsigned int offset, len, i;
- struct tep_handle *pevent = field->event->pevent;
+ struct tep_handle *tep = field->event->tep;
if (field->flags & TEP_FIELD_IS_ARRAY) {
offset = field->offset;
len = field->size;
if (field->flags & TEP_FIELD_IS_DYNAMIC) {
- val = tep_read_number(pevent, data + offset, len);
+ val = tep_read_number(tep, data + offset, len);
offset = val;
len = offset >> 16;
offset &= 0xffff;
@@ -4861,7 +4861,7 @@ void tep_print_field(struct trace_seq *s, void *data,
field->flags &= ~TEP_FIELD_IS_STRING;
}
} else {
- val = tep_read_number(pevent, data + field->offset,
+ val = tep_read_number(tep, data + field->offset,
field->size);
if (field->flags & TEP_FIELD_IS_POINTER) {
trace_seq_printf(s, "0x%llx", val);
@@ -4910,7 +4910,7 @@ void tep_print_fields(struct trace_seq *s, void *data,
static void pretty_print(struct trace_seq *s, void *data, int size, struct tep_event *event)
{
- struct tep_handle *pevent = event->pevent;
+ struct tep_handle *tep = event->tep;
struct tep_print_fmt *print_fmt = &event->print_fmt;
struct tep_print_arg *arg = print_fmt->args;
struct tep_print_arg *args = NULL;
@@ -5002,7 +5002,7 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct tep_e
case '-':
goto cont_process;
case 'p':
- if (pevent->long_size == 4)
+ if (tep->long_size == 4)
ls = 1;
else
ls = 2;
@@ -5063,7 +5063,7 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct tep_e
arg = arg->next;
if (show_func) {
- func = find_func(pevent, val);
+ func = find_func(tep, val);
if (func) {
trace_seq_puts(s, func->func);
if (show_func == 'F')
@@ -5073,7 +5073,7 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct tep_e
break;
}
}
- if (pevent->long_size == 8 && ls == 1 &&
+ if (tep->long_size == 8 && ls == 1 &&
sizeof(long) != 8) {
char *p;
@@ -5171,8 +5171,8 @@ out_failed:
}
/**
- * tep_data_lat_fmt - parse the data for the latency format
- * @pevent: a handle to the pevent
+ * tep_data_latency_format - parse the data for the latency format
+ * @tep: a handle to the trace event parser context
* @s: the trace_seq to write to
* @record: the record to read from
*
@@ -5180,8 +5180,8 @@ out_failed:
* need rescheduling, in hard/soft interrupt, preempt count
* and lock depth) and places it into the trace_seq.
*/
-void tep_data_lat_fmt(struct tep_handle *pevent,
- struct trace_seq *s, struct tep_record *record)
+void tep_data_latency_format(struct tep_handle *tep,
+ struct trace_seq *s, struct tep_record *record)
{
static int check_lock_depth = 1;
static int check_migrate_disable = 1;
@@ -5195,13 +5195,13 @@ void tep_data_lat_fmt(struct tep_handle *pevent,
int softirq;
void *data = record->data;
- lat_flags = parse_common_flags(pevent, data);
- pc = parse_common_pc(pevent, data);
+ lat_flags = parse_common_flags(tep, data);
+ pc = parse_common_pc(tep, data);
/* lock_depth may not always exist */
if (lock_depth_exists)
- lock_depth = parse_common_lock_depth(pevent, data);
+ lock_depth = parse_common_lock_depth(tep, data);
else if (check_lock_depth) {
- lock_depth = parse_common_lock_depth(pevent, data);
+ lock_depth = parse_common_lock_depth(tep, data);
if (lock_depth < 0)
check_lock_depth = 0;
else
@@ -5210,9 +5210,9 @@ void tep_data_lat_fmt(struct tep_handle *pevent,
/* migrate_disable may not always exist */
if (migrate_disable_exists)
- migrate_disable = parse_common_migrate_disable(pevent, data);
+ migrate_disable = parse_common_migrate_disable(tep, data);
else if (check_migrate_disable) {
- migrate_disable = parse_common_migrate_disable(pevent, data);
+ migrate_disable = parse_common_migrate_disable(tep, data);
if (migrate_disable < 0)
check_migrate_disable = 0;
else
@@ -5255,79 +5255,79 @@ void tep_data_lat_fmt(struct tep_handle *pevent,
/**
* tep_data_type - parse out the given event type
- * @pevent: a handle to the pevent
+ * @tep: a handle to the trace event parser context
* @rec: the record to read from
*
* This returns the event id from the @rec.
*/
-int tep_data_type(struct tep_handle *pevent, struct tep_record *rec)
+int tep_data_type(struct tep_handle *tep, struct tep_record *rec)
{
- return trace_parse_common_type(pevent, rec->data);
+ return trace_parse_common_type(tep, rec->data);
}
/**
* tep_data_pid - parse the PID from record
- * @pevent: a handle to the pevent
+ * @tep: a handle to the trace event parser context
* @rec: the record to parse
*
* This returns the PID from a record.
*/
-int tep_data_pid(struct tep_handle *pevent, struct tep_record *rec)
+int tep_data_pid(struct tep_handle *tep, struct tep_record *rec)
{
- return parse_common_pid(pevent, rec->data);
+ return parse_common_pid(tep, rec->data);
}
/**
* tep_data_preempt_count - parse the preempt count from the record
- * @pevent: a handle to the pevent
+ * @tep: a handle to the trace event parser context
* @rec: the record to parse
*
* This returns the preempt count from a record.
*/
-int tep_data_preempt_count(struct tep_handle *pevent, struct tep_record *rec)
+int tep_data_preempt_count(struct tep_handle *tep, struct tep_record *rec)
{
- return parse_common_pc(pevent, rec->data);
+ return parse_common_pc(tep, rec->data);
}
/**
* tep_data_flags - parse the latency flags from the record
- * @pevent: a handle to the pevent
+ * @tep: a handle to the trace event parser context
* @rec: the record to parse
*
* This returns the latency flags from a record.
*
* Use trace_flag_type enum for the flags (see event-parse.h).
*/
-int tep_data_flags(struct tep_handle *pevent, struct tep_record *rec)
+int tep_data_flags(struct tep_handle *tep, struct tep_record *rec)
{
- return parse_common_flags(pevent, rec->data);
+ return parse_common_flags(tep, rec->data);
}
/**
* tep_data_comm_from_pid - return the command line from PID
- * @pevent: a handle to the pevent
+ * @tep: a handle to the trace event parser context
* @pid: the PID of the task to search for
*
* This returns a pointer to the command line that has the given
* @pid.
*/
-const char *tep_data_comm_from_pid(struct tep_handle *pevent, int pid)
+const char *tep_data_comm_from_pid(struct tep_handle *tep, int pid)
{
const char *comm;
- comm = find_cmdline(pevent, pid);
+ comm = find_cmdline(tep, pid);
return comm;
}
static struct tep_cmdline *
-pid_from_cmdlist(struct tep_handle *pevent, const char *comm, struct tep_cmdline *next)
+pid_from_cmdlist(struct tep_handle *tep, const char *comm, struct tep_cmdline *next)
{
struct cmdline_list *cmdlist = (struct cmdline_list *)next;
if (cmdlist)
cmdlist = cmdlist->next;
else
- cmdlist = pevent->cmdlist;
+ cmdlist = tep->cmdlist;
while (cmdlist && strcmp(cmdlist->comm, comm) != 0)
cmdlist = cmdlist->next;
@@ -5337,7 +5337,7 @@ pid_from_cmdlist(struct tep_handle *pevent, const char *comm, struct tep_cmdline
/**
* tep_data_pid_from_comm - return the pid from a given comm
- * @pevent: a handle to the pevent
+ * @tep: a handle to the trace event parser context
* @comm: the cmdline to find the pid from
* @next: the cmdline structure to find the next comm
*
@@ -5348,7 +5348,7 @@ pid_from_cmdlist(struct tep_handle *pevent, const char *comm, struct tep_cmdline
* next pid.
* Also, it does a linear search, so it may be slow.
*/
-struct tep_cmdline *tep_data_pid_from_comm(struct tep_handle *pevent, const char *comm,
+struct tep_cmdline *tep_data_pid_from_comm(struct tep_handle *tep, const char *comm,
struct tep_cmdline *next)
{
struct tep_cmdline *cmdline;
@@ -5357,25 +5357,25 @@ struct tep_cmdline *tep_data_pid_from_comm(struct tep_handle *pevent, const char
* If the cmdlines have not been converted yet, then use
* the list.
*/
- if (!pevent->cmdlines)
- return pid_from_cmdlist(pevent, comm, next);
+ if (!tep->cmdlines)
+ return pid_from_cmdlist(tep, comm, next);
if (next) {
/*
* The next pointer could have been still from
* a previous call before cmdlines were created
*/
- if (next < pevent->cmdlines ||
- next >= pevent->cmdlines + pevent->cmdline_count)
+ if (next < tep->cmdlines ||
+ next >= tep->cmdlines + tep->cmdline_count)
next = NULL;
else
cmdline = next++;
}
if (!next)
- cmdline = pevent->cmdlines;
+ cmdline = tep->cmdlines;
- while (cmdline < pevent->cmdlines + pevent->cmdline_count) {
+ while (cmdline < tep->cmdlines + tep->cmdline_count) {
if (strcmp(cmdline->comm, comm) == 0)
return cmdline;
cmdline++;
@@ -5385,12 +5385,13 @@ struct tep_cmdline *tep_data_pid_from_comm(struct tep_handle *pevent, const char
/**
* tep_cmdline_pid - return the pid associated to a given cmdline
+ * @tep: a handle to the trace event parser context
* @cmdline: The cmdline structure to get the pid from
*
* Returns the pid for a give cmdline. If @cmdline is NULL, then
* -1 is returned.
*/
-int tep_cmdline_pid(struct tep_handle *pevent, struct tep_cmdline *cmdline)
+int tep_cmdline_pid(struct tep_handle *tep, struct tep_cmdline *cmdline)
{
struct cmdline_list *cmdlist = (struct cmdline_list *)cmdline;
@@ -5401,9 +5402,9 @@ int tep_cmdline_pid(struct tep_handle *pevent, struct tep_cmdline *cmdline)
* If cmdlines have not been created yet, or cmdline is
* not part of the array, then treat it as a cmdlist instead.
*/
- if (!pevent->cmdlines ||
- cmdline < pevent->cmdlines ||
- cmdline >= pevent->cmdlines + pevent->cmdline_count)
+ if (!tep->cmdlines ||
+ cmdline < tep->cmdlines ||
+ cmdline >= tep->cmdlines + tep->cmdline_count)
return cmdlist->pid;
return cmdline->pid;
@@ -5423,7 +5424,7 @@ void tep_event_info(struct trace_seq *s, struct tep_event *event,
{
int print_pretty = 1;
- if (event->pevent->print_raw || (event->flags & TEP_EVENT_FL_PRINTRAW))
+ if (event->tep->print_raw || (event->flags & TEP_EVENT_FL_PRINTRAW))
tep_print_fields(s, record->data, record->size, event);
else {
@@ -5444,7 +5445,8 @@ static bool is_timestamp_in_us(char *trace_clock, bool use_trace_clock)
return true;
if (!strcmp(trace_clock, "local") || !strcmp(trace_clock, "global")
- || !strcmp(trace_clock, "uptime") || !strcmp(trace_clock, "perf"))
+ || !strcmp(trace_clock, "uptime") || !strcmp(trace_clock, "perf")
+ || !strncmp(trace_clock, "mono", 4))
return true;
/* trace_clock is setting in tsc or counter mode */
@@ -5453,14 +5455,14 @@ static bool is_timestamp_in_us(char *trace_clock, bool use_trace_clock)
/**
* tep_find_event_by_record - return the event from a given record
- * @pevent: a handle to the pevent
+ * @tep: a handle to the trace event parser context
* @record: The record to get the event from
*
* Returns the associated event for a given record, or NULL if non is
* is found.
*/
struct tep_event *
-tep_find_event_by_record(struct tep_handle *pevent, struct tep_record *record)
+tep_find_event_by_record(struct tep_handle *tep, struct tep_record *record)
{
int type;
@@ -5469,21 +5471,21 @@ tep_find_event_by_record(struct tep_handle *pevent, struct tep_record *record)
return NULL;
}
- type = trace_parse_common_type(pevent, record->data);
+ type = trace_parse_common_type(tep, record->data);
- return tep_find_event(pevent, type);
+ return tep_find_event(tep, type);
}
/**
* tep_print_event_task - Write the event task comm, pid and CPU
- * @pevent: a handle to the pevent
+ * @tep: a handle to the trace event parser context
* @s: the trace_seq to write to
* @event: the handle to the record's event
* @record: The record to get the event from
*
* Writes the tasks comm, pid and CPU to @s.
*/
-void tep_print_event_task(struct tep_handle *pevent, struct trace_seq *s,
+void tep_print_event_task(struct tep_handle *tep, struct trace_seq *s,
struct tep_event *event,
struct tep_record *record)
{
@@ -5491,27 +5493,26 @@ void tep_print_event_task(struct tep_handle *pevent, struct trace_seq *s,
const char *comm;
int pid;
- pid = parse_common_pid(pevent, data);
- comm = find_cmdline(pevent, pid);
+ pid = parse_common_pid(tep, data);
+ comm = find_cmdline(tep, pid);
- if (pevent->latency_format) {
- trace_seq_printf(s, "%8.8s-%-5d %3d",
- comm, pid, record->cpu);
- } else
+ if (tep->latency_format)
+ trace_seq_printf(s, "%8.8s-%-5d %3d", comm, pid, record->cpu);
+ else
trace_seq_printf(s, "%16s-%-5d [%03d]", comm, pid, record->cpu);
}
/**
* tep_print_event_time - Write the event timestamp
- * @pevent: a handle to the pevent
+ * @tep: a handle to the trace event parser context
* @s: the trace_seq to write to
* @event: the handle to the record's event
* @record: The record to get the event from
- * @use_trace_clock: Set to parse according to the @pevent->trace_clock
+ * @use_trace_clock: Set to parse according to the @tep->trace_clock
*
* Writes the timestamp of the record into @s.
*/
-void tep_print_event_time(struct tep_handle *pevent, struct trace_seq *s,
+void tep_print_event_time(struct tep_handle *tep, struct trace_seq *s,
struct tep_event *event,
struct tep_record *record,
bool use_trace_clock)
@@ -5522,19 +5523,18 @@ void tep_print_event_time(struct tep_handle *pevent, struct trace_seq *s,
int p;
bool use_usec_format;
- use_usec_format = is_timestamp_in_us(pevent->trace_clock,
- use_trace_clock);
+ use_usec_format = is_timestamp_in_us(tep->trace_clock, use_trace_clock);
if (use_usec_format) {
secs = record->ts / NSEC_PER_SEC;
nsecs = record->ts - secs * NSEC_PER_SEC;
}
- if (pevent->latency_format) {
- tep_data_lat_fmt(pevent, s, record);
+ if (tep->latency_format) {
+ tep_data_latency_format(tep, s, record);
}
if (use_usec_format) {
- if (pevent->flags & TEP_NSEC_OUTPUT) {
+ if (tep->flags & TEP_NSEC_OUTPUT) {
usecs = nsecs;
p = 9;
} else {
@@ -5554,14 +5554,14 @@ void tep_print_event_time(struct tep_handle *pevent, struct trace_seq *s,
/**
* tep_print_event_data - Write the event data section
- * @pevent: a handle to the pevent
+ * @tep: a handle to the trace event parser context
* @s: the trace_seq to write to
* @event: the handle to the record's event
* @record: The record to get the event from
*
* Writes the parsing of the record's data to @s.
*/
-void tep_print_event_data(struct tep_handle *pevent, struct trace_seq *s,
+void tep_print_event_data(struct tep_handle *tep, struct trace_seq *s,
struct tep_event *event,
struct tep_record *record)
{
@@ -5578,15 +5578,15 @@ void tep_print_event_data(struct tep_handle *pevent, struct trace_seq *s,
tep_event_info(s, event, record);
}
-void tep_print_event(struct tep_handle *pevent, struct trace_seq *s,
+void tep_print_event(struct tep_handle *tep, struct trace_seq *s,
struct tep_record *record, bool use_trace_clock)
{
struct tep_event *event;
- event = tep_find_event_by_record(pevent, record);
+ event = tep_find_event_by_record(tep, record);
if (!event) {
int i;
- int type = trace_parse_common_type(pevent, record->data);
+ int type = trace_parse_common_type(tep, record->data);
do_warning("ug! no event found for type %d", type);
trace_seq_printf(s, "[UNKNOWN TYPE %d]", type);
@@ -5596,9 +5596,9 @@ void tep_print_event(struct tep_handle *pevent, struct trace_seq *s,
return;
}
- tep_print_event_task(pevent, s, event, record);
- tep_print_event_time(pevent, s, event, record, use_trace_clock);
- tep_print_event_data(pevent, s, event, record);
+ tep_print_event_task(tep, s, event, record);
+ tep_print_event_time(tep, s, event, record, use_trace_clock);
+ tep_print_event_data(tep, s, event, record);
}
static int events_id_cmp(const void *a, const void *b)
@@ -5649,32 +5649,26 @@ static int events_system_cmp(const void *a, const void *b)
return events_id_cmp(a, b);
}
-struct tep_event **tep_list_events(struct tep_handle *pevent, enum tep_event_sort_type sort_type)
+static struct tep_event **list_events_copy(struct tep_handle *tep)
{
struct tep_event **events;
- int (*sort)(const void *a, const void *b);
-
- events = pevent->sort_events;
-
- if (events && pevent->last_type == sort_type)
- return events;
- if (!events) {
- events = malloc(sizeof(*events) * (pevent->nr_events + 1));
- if (!events)
- return NULL;
+ if (!tep)
+ return NULL;
- memcpy(events, pevent->events, sizeof(*events) * pevent->nr_events);
- events[pevent->nr_events] = NULL;
+ events = malloc(sizeof(*events) * (tep->nr_events + 1));
+ if (!events)
+ return NULL;
- pevent->sort_events = events;
+ memcpy(events, tep->events, sizeof(*events) * tep->nr_events);
+ events[tep->nr_events] = NULL;
+ return events;
+}
- /* the internal events are sorted by id */
- if (sort_type == TEP_EVENT_SORT_ID) {
- pevent->last_type = sort_type;
- return events;
- }
- }
+static void list_events_sort(struct tep_event **events, int nr_events,
+ enum tep_event_sort_type sort_type)
+{
+ int (*sort)(const void *a, const void *b);
switch (sort_type) {
case TEP_EVENT_SORT_ID:
@@ -5687,11 +5681,82 @@ struct tep_event **tep_list_events(struct tep_handle *pevent, enum tep_event_sor
sort = events_system_cmp;
break;
default:
+ sort = NULL;
+ }
+
+ if (sort)
+ qsort(events, nr_events, sizeof(*events), sort);
+}
+
+/**
+ * tep_list_events - Get events, sorted by given criteria.
+ * @tep: a handle to the tep context
+ * @sort_type: desired sort order of the events in the array
+ *
+ * Returns an array of pointers to all events, sorted by the given
+ * @sort_type criteria. The last element of the array is NULL. The returned
+ * memory must not be freed, it is managed by the library.
+ * The function is not thread safe.
+ */
+struct tep_event **tep_list_events(struct tep_handle *tep,
+ enum tep_event_sort_type sort_type)
+{
+ struct tep_event **events;
+
+ if (!tep)
+ return NULL;
+
+ events = tep->sort_events;
+ if (events && tep->last_type == sort_type)
return events;
+
+ if (!events) {
+ events = list_events_copy(tep);
+ if (!events)
+ return NULL;
+
+ tep->sort_events = events;
+
+ /* the internal events are sorted by id */
+ if (sort_type == TEP_EVENT_SORT_ID) {
+ tep->last_type = sort_type;
+ return events;
+ }
}
- qsort(events, pevent->nr_events, sizeof(*events), sort);
- pevent->last_type = sort_type;
+ list_events_sort(events, tep->nr_events, sort_type);
+ tep->last_type = sort_type;
+
+ return events;
+}
+
+
+/**
+ * tep_list_events_copy - Thread safe version of tep_list_events()
+ * @tep: a handle to the tep context
+ * @sort_type: desired sort order of the events in the array
+ *
+ * Returns an array of pointers to all events, sorted by the given
+ * @sort_type criteria. The last element of the array is NULL. The returned
+ * array is newly allocated inside the function and must be freed by the caller
+ */
+struct tep_event **tep_list_events_copy(struct tep_handle *tep,
+ enum tep_event_sort_type sort_type)
+{
+ struct tep_event **events;
+
+ if (!tep)
+ return NULL;
+
+ events = list_events_copy(tep);
+ if (!events)
+ return NULL;
+
+ /* the internal events are sorted by id */
+ if (sort_type == TEP_EVENT_SORT_ID)
+ return events;
+
+ list_events_sort(events, tep->nr_events, sort_type);
return events;
}
@@ -5950,7 +6015,7 @@ static void parse_header_field(const char *field,
/**
* tep_parse_header_page - parse the data stored in the header page
- * @pevent: the handle to the pevent
+ * @tep: a handle to the trace event parser context
* @buf: the buffer storing the header page format string
* @size: the size of @buf
* @long_size: the long size to use if there is no header
@@ -5960,7 +6025,7 @@ static void parse_header_field(const char *field,
*
* /sys/kernel/debug/tracing/events/header_page
*/
-int tep_parse_header_page(struct tep_handle *pevent, char *buf, unsigned long size,
+int tep_parse_header_page(struct tep_handle *tep, char *buf, unsigned long size,
int long_size)
{
int ignore;
@@ -5970,22 +6035,22 @@ int tep_parse_header_page(struct tep_handle *pevent, char *buf, unsigned long si
* Old kernels did not have header page info.
* Sorry but we just use what we find here in user space.
*/
- pevent->header_page_ts_size = sizeof(long long);
- pevent->header_page_size_size = long_size;
- pevent->header_page_data_offset = sizeof(long long) + long_size;
- pevent->old_format = 1;
+ tep->header_page_ts_size = sizeof(long long);
+ tep->header_page_size_size = long_size;
+ tep->header_page_data_offset = sizeof(long long) + long_size;
+ tep->old_format = 1;
return -1;
}
init_input_buf(buf, size);
- parse_header_field("timestamp", &pevent->header_page_ts_offset,
- &pevent->header_page_ts_size, 1);
- parse_header_field("commit", &pevent->header_page_size_offset,
- &pevent->header_page_size_size, 1);
- parse_header_field("overwrite", &pevent->header_page_overwrite,
+ parse_header_field("timestamp", &tep->header_page_ts_offset,
+ &tep->header_page_ts_size, 1);
+ parse_header_field("commit", &tep->header_page_size_offset,
+ &tep->header_page_size_size, 1);
+ parse_header_field("overwrite", &tep->header_page_overwrite,
&ignore, 0);
- parse_header_field("data", &pevent->header_page_data_offset,
- &pevent->header_page_data_size, 1);
+ parse_header_field("data", &tep->header_page_data_offset,
+ &tep->header_page_data_size, 1);
return 0;
}
@@ -6013,11 +6078,11 @@ static void free_handler(struct event_handler *handle)
free(handle);
}
-static int find_event_handle(struct tep_handle *pevent, struct tep_event *event)
+static int find_event_handle(struct tep_handle *tep, struct tep_event *event)
{
struct event_handler *handle, **next;
- for (next = &pevent->handlers; *next;
+ for (next = &tep->handlers; *next;
next = &(*next)->next) {
handle = *next;
if (event_matches(event, handle->id,
@@ -6055,7 +6120,7 @@ static int find_event_handle(struct tep_handle *pevent, struct tep_event *event)
* /sys/kernel/debug/tracing/events/.../.../format
*/
enum tep_errno __tep_parse_format(struct tep_event **eventp,
- struct tep_handle *pevent, const char *buf,
+ struct tep_handle *tep, const char *buf,
unsigned long size, const char *sys)
{
struct tep_event *event;
@@ -6097,8 +6162,8 @@ enum tep_errno __tep_parse_format(struct tep_event **eventp,
goto event_alloc_failed;
}
- /* Add pevent to event so that it can be referenced */
- event->pevent = pevent;
+ /* Add tep to event so that it can be referenced */
+ event->tep = tep;
ret = event_read_format(event);
if (ret < 0) {
@@ -6110,7 +6175,7 @@ enum tep_errno __tep_parse_format(struct tep_event **eventp,
* If the event has an override, don't print warnings if the event
* print format fails to parse.
*/
- if (pevent && find_event_handle(pevent, event))
+ if (tep && find_event_handle(tep, event))
show_warning = 0;
ret = event_read_print(event);
@@ -6162,18 +6227,18 @@ enum tep_errno __tep_parse_format(struct tep_event **eventp,
}
static enum tep_errno
-__parse_event(struct tep_handle *pevent,
+__parse_event(struct tep_handle *tep,
struct tep_event **eventp,
const char *buf, unsigned long size,
const char *sys)
{
- int ret = __tep_parse_format(eventp, pevent, buf, size, sys);
+ int ret = __tep_parse_format(eventp, tep, buf, size, sys);
struct tep_event *event = *eventp;
if (event == NULL)
return ret;
- if (pevent && add_event(pevent, event)) {
+ if (tep && add_event(tep, event)) {
ret = TEP_ERRNO__MEM_ALLOC_FAILED;
goto event_add_failed;
}
@@ -6191,7 +6256,7 @@ event_add_failed:
/**
* tep_parse_format - parse the event format
- * @pevent: the handle to the pevent
+ * @tep: a handle to the trace event parser context
* @eventp: returned format
* @buf: the buffer storing the event format string
* @size: the size of @buf
@@ -6204,17 +6269,17 @@ event_add_failed:
*
* /sys/kernel/debug/tracing/events/.../.../format
*/
-enum tep_errno tep_parse_format(struct tep_handle *pevent,
+enum tep_errno tep_parse_format(struct tep_handle *tep,
struct tep_event **eventp,
const char *buf,
unsigned long size, const char *sys)
{
- return __parse_event(pevent, eventp, buf, size, sys);
+ return __parse_event(tep, eventp, buf, size, sys);
}
/**
* tep_parse_event - parse the event format
- * @pevent: the handle to the pevent
+ * @tep: a handle to the trace event parser context
* @buf: the buffer storing the event format string
* @size: the size of @buf
* @sys: the system the event belongs to
@@ -6226,11 +6291,11 @@ enum tep_errno tep_parse_format(struct tep_handle *pevent,
*
* /sys/kernel/debug/tracing/events/.../.../format
*/
-enum tep_errno tep_parse_event(struct tep_handle *pevent, const char *buf,
+enum tep_errno tep_parse_event(struct tep_handle *tep, const char *buf,
unsigned long size, const char *sys)
{
struct tep_event *event = NULL;
- return __parse_event(pevent, &event, buf, size, sys);
+ return __parse_event(tep, &event, buf, size, sys);
}
int get_field_val(struct trace_seq *s, struct tep_format_field *field,
@@ -6292,8 +6357,8 @@ void *tep_get_field_raw(struct trace_seq *s, struct tep_event *event,
offset = field->offset;
if (field->flags & TEP_FIELD_IS_DYNAMIC) {
- offset = tep_read_number(event->pevent,
- data + offset, field->size);
+ offset = tep_read_number(event->tep,
+ data + offset, field->size);
*len = offset >> 16;
offset &= 0xffff;
} else
@@ -6386,7 +6451,8 @@ int tep_get_any_field_val(struct trace_seq *s, struct tep_event *event,
* @record: The record with the field name.
* @err: print default error if failed.
*
- * Returns: 0 on success, -1 field not found, or 1 if buffer is full.
+ * Returns positive value on success, negative in case of an error,
+ * or 0 if buffer is full.
*/
int tep_print_num_field(struct trace_seq *s, const char *fmt,
struct tep_event *event, const char *name,
@@ -6418,14 +6484,15 @@ int tep_print_num_field(struct trace_seq *s, const char *fmt,
* @record: The record with the field name.
* @err: print default error if failed.
*
- * Returns: 0 on success, -1 field not found, or 1 if buffer is full.
+ * Returns positive value on success, negative in case of an error,
+ * or 0 if buffer is full.
*/
int tep_print_func_field(struct trace_seq *s, const char *fmt,
struct tep_event *event, const char *name,
struct tep_record *record, int err)
{
struct tep_format_field *field = tep_find_field(event, name);
- struct tep_handle *pevent = event->pevent;
+ struct tep_handle *tep = event->tep;
unsigned long long val;
struct func_map *func;
char tmp[128];
@@ -6436,7 +6503,7 @@ int tep_print_func_field(struct trace_seq *s, const char *fmt,
if (tep_read_number_field(field, record->data, &val))
goto failed;
- func = find_func(pevent, val);
+ func = find_func(tep, val);
if (func)
snprintf(tmp, 128, "%s/0x%llx", func->func, func->addr - val);
@@ -6468,7 +6535,7 @@ static void free_func_handle(struct tep_function_handler *func)
/**
* tep_register_print_function - register a helper function
- * @pevent: the handle to the pevent
+ * @tep: a handle to the trace event parser context
* @func: the function to process the helper function
* @ret_type: the return type of the helper function
* @name: the name of the helper function
@@ -6481,7 +6548,7 @@ static void free_func_handle(struct tep_function_handler *func)
* The @parameters is a variable list of tep_func_arg_type enums that
* must end with TEP_FUNC_ARG_VOID.
*/
-int tep_register_print_function(struct tep_handle *pevent,
+int tep_register_print_function(struct tep_handle *tep,
tep_func_handler func,
enum tep_func_arg_type ret_type,
char *name, ...)
@@ -6493,7 +6560,7 @@ int tep_register_print_function(struct tep_handle *pevent,
va_list ap;
int ret;
- func_handle = find_func_handler(pevent, name);
+ func_handle = find_func_handler(tep, name);
if (func_handle) {
/*
* This is most like caused by the users own
@@ -6501,7 +6568,7 @@ int tep_register_print_function(struct tep_handle *pevent,
* system defaults.
*/
pr_stat("override of function helper '%s'", name);
- remove_func_handler(pevent, name);
+ remove_func_handler(tep, name);
}
func_handle = calloc(1, sizeof(*func_handle));
@@ -6548,8 +6615,8 @@ int tep_register_print_function(struct tep_handle *pevent,
}
va_end(ap);
- func_handle->next = pevent->func_handlers;
- pevent->func_handlers = func_handle;
+ func_handle->next = tep->func_handlers;
+ tep->func_handlers = func_handle;
return 0;
out_free:
@@ -6560,7 +6627,7 @@ int tep_register_print_function(struct tep_handle *pevent,
/**
* tep_unregister_print_function - unregister a helper function
- * @pevent: the handle to the pevent
+ * @tep: a handle to the trace event parser context
* @func: the function to process the helper function
* @name: the name of the helper function
*
@@ -6568,20 +6635,20 @@ int tep_register_print_function(struct tep_handle *pevent,
*
* Returns 0 if the handler was removed successully, -1 otherwise.
*/
-int tep_unregister_print_function(struct tep_handle *pevent,
+int tep_unregister_print_function(struct tep_handle *tep,
tep_func_handler func, char *name)
{
struct tep_function_handler *func_handle;
- func_handle = find_func_handler(pevent, name);
+ func_handle = find_func_handler(tep, name);
if (func_handle && func_handle->func == func) {
- remove_func_handler(pevent, name);
+ remove_func_handler(tep, name);
return 0;
}
return -1;
}
-static struct tep_event *search_event(struct tep_handle *pevent, int id,
+static struct tep_event *search_event(struct tep_handle *tep, int id,
const char *sys_name,
const char *event_name)
{
@@ -6589,7 +6656,7 @@ static struct tep_event *search_event(struct tep_handle *pevent, int id,
if (id >= 0) {
/* search by id */
- event = tep_find_event(pevent, id);
+ event = tep_find_event(tep, id);
if (!event)
return NULL;
if (event_name && (strcmp(event_name, event->name) != 0))
@@ -6597,7 +6664,7 @@ static struct tep_event *search_event(struct tep_handle *pevent, int id,
if (sys_name && (strcmp(sys_name, event->system) != 0))
return NULL;
} else {
- event = tep_find_event_by_name(pevent, sys_name, event_name);
+ event = tep_find_event_by_name(tep, sys_name, event_name);
if (!event)
return NULL;
}
@@ -6606,7 +6673,7 @@ static struct tep_event *search_event(struct tep_handle *pevent, int id,
/**
* tep_register_event_handler - register a way to parse an event
- * @pevent: the handle to the pevent
+ * @tep: a handle to the trace event parser context
* @id: the id of the event to register
* @sys_name: the system name the event belongs to
* @event_name: the name of the event
@@ -6627,14 +6694,14 @@ static struct tep_event *search_event(struct tep_handle *pevent, int id,
* negative TEP_ERRNO_... in case of an error
*
*/
-int tep_register_event_handler(struct tep_handle *pevent, int id,
+int tep_register_event_handler(struct tep_handle *tep, int id,
const char *sys_name, const char *event_name,
tep_event_handler_func func, void *context)
{
struct tep_event *event;
struct event_handler *handle;
- event = search_event(pevent, id, sys_name, event_name);
+ event = search_event(tep, id, sys_name, event_name);
if (event == NULL)
goto not_found;
@@ -6669,8 +6736,8 @@ int tep_register_event_handler(struct tep_handle *pevent, int id,
}
handle->func = func;
- handle->next = pevent->handlers;
- pevent->handlers = handle;
+ handle->next = tep->handlers;
+ tep->handlers = handle;
handle->context = context;
return TEP_REGISTER_SUCCESS;
@@ -6697,7 +6764,7 @@ static int handle_matches(struct event_handler *handler, int id,
/**
* tep_unregister_event_handler - unregister an existing event handler
- * @pevent: the handle to the pevent
+ * @tep: a handle to the trace event parser context
* @id: the id of the event to unregister
* @sys_name: the system name the handler belongs to
* @event_name: the name of the event handler
@@ -6711,7 +6778,7 @@ static int handle_matches(struct event_handler *handler, int id,
*
* Returns 0 if handler was removed successfully, -1 if event was not found.
*/
-int tep_unregister_event_handler(struct tep_handle *pevent, int id,
+int tep_unregister_event_handler(struct tep_handle *tep, int id,
const char *sys_name, const char *event_name,
tep_event_handler_func func, void *context)
{
@@ -6719,7 +6786,7 @@ int tep_unregister_event_handler(struct tep_handle *pevent, int id,
struct event_handler *handle;
struct event_handler **next;
- event = search_event(pevent, id, sys_name, event_name);
+ event = search_event(tep, id, sys_name, event_name);
if (event == NULL)
goto not_found;
@@ -6733,7 +6800,7 @@ int tep_unregister_event_handler(struct tep_handle *pevent, int id,
}
not_found:
- for (next = &pevent->handlers; *next; next = &(*next)->next) {
+ for (next = &tep->handlers; *next; next = &(*next)->next) {
handle = *next;
if (handle_matches(handle, id, sys_name, event_name,
func, context))
@@ -6750,23 +6817,23 @@ not_found:
}
/**
- * tep_alloc - create a pevent handle
+ * tep_alloc - create a tep handle
*/
struct tep_handle *tep_alloc(void)
{
- struct tep_handle *pevent = calloc(1, sizeof(*pevent));
+ struct tep_handle *tep = calloc(1, sizeof(*tep));
- if (pevent) {
- pevent->ref_count = 1;
- pevent->host_bigendian = tep_host_bigendian();
+ if (tep) {
+ tep->ref_count = 1;
+ tep->host_bigendian = tep_is_bigendian();
}
- return pevent;
+ return tep;
}
-void tep_ref(struct tep_handle *pevent)
+void tep_ref(struct tep_handle *tep)
{
- pevent->ref_count++;
+ tep->ref_count++;
}
int tep_get_ref(struct tep_handle *tep)
@@ -6816,10 +6883,10 @@ void tep_free_event(struct tep_event *event)
}
/**
- * tep_free - free a pevent handle
- * @pevent: the pevent handle to free
+ * tep_free - free a tep handle
+ * @tep: the tep handle to free
*/
-void tep_free(struct tep_handle *pevent)
+void tep_free(struct tep_handle *tep)
{
struct cmdline_list *cmdlist, *cmdnext;
struct func_list *funclist, *funcnext;
@@ -6828,21 +6895,21 @@ void tep_free(struct tep_handle *pevent)
struct event_handler *handle;
int i;
- if (!pevent)
+ if (!tep)
return;
- cmdlist = pevent->cmdlist;
- funclist = pevent->funclist;
- printklist = pevent->printklist;
+ cmdlist = tep->cmdlist;
+ funclist = tep->funclist;
+ printklist = tep->printklist;
- pevent->ref_count--;
- if (pevent->ref_count)
+ tep->ref_count--;
+ if (tep->ref_count)
return;
- if (pevent->cmdlines) {
- for (i = 0; i < pevent->cmdline_count; i++)
- free(pevent->cmdlines[i].comm);
- free(pevent->cmdlines);
+ if (tep->cmdlines) {
+ for (i = 0; i < tep->cmdline_count; i++)
+ free(tep->cmdlines[i].comm);
+ free(tep->cmdlines);
}
while (cmdlist) {
@@ -6852,12 +6919,12 @@ void tep_free(struct tep_handle *pevent)
cmdlist = cmdnext;
}
- if (pevent->func_map) {
- for (i = 0; i < (int)pevent->func_count; i++) {
- free(pevent->func_map[i].func);
- free(pevent->func_map[i].mod);
+ if (tep->func_map) {
+ for (i = 0; i < (int)tep->func_count; i++) {
+ free(tep->func_map[i].func);
+ free(tep->func_map[i].mod);
}
- free(pevent->func_map);
+ free(tep->func_map);
}
while (funclist) {
@@ -6868,16 +6935,16 @@ void tep_free(struct tep_handle *pevent)
funclist = funcnext;
}
- while (pevent->func_handlers) {
- func_handler = pevent->func_handlers;
- pevent->func_handlers = func_handler->next;
+ while (tep->func_handlers) {
+ func_handler = tep->func_handlers;
+ tep->func_handlers = func_handler->next;
free_func_handle(func_handler);
}
- if (pevent->printk_map) {
- for (i = 0; i < (int)pevent->printk_count; i++)
- free(pevent->printk_map[i].printk);
- free(pevent->printk_map);
+ if (tep->printk_map) {
+ for (i = 0; i < (int)tep->printk_count; i++)
+ free(tep->printk_map[i].printk);
+ free(tep->printk_map);
}
while (printklist) {
@@ -6887,24 +6954,24 @@ void tep_free(struct tep_handle *pevent)
printklist = printknext;
}
- for (i = 0; i < pevent->nr_events; i++)
- tep_free_event(pevent->events[i]);
+ for (i = 0; i < tep->nr_events; i++)
+ tep_free_event(tep->events[i]);
- while (pevent->handlers) {
- handle = pevent->handlers;
- pevent->handlers = handle->next;
+ while (tep->handlers) {
+ handle = tep->handlers;
+ tep->handlers = handle->next;
free_handler(handle);
}
- free(pevent->trace_clock);
- free(pevent->events);
- free(pevent->sort_events);
- free(pevent->func_resolver);
+ free(tep->trace_clock);
+ free(tep->events);
+ free(tep->sort_events);
+ free(tep->func_resolver);
- free(pevent);
+ free(tep);
}
-void tep_unref(struct tep_handle *pevent)
+void tep_unref(struct tep_handle *tep)
{
- tep_free(pevent);
+ tep_free(tep);
}
diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index aec48f2aea8a..642f68ab5fb2 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -64,8 +64,8 @@ typedef int (*tep_event_handler_func)(struct trace_seq *s,
struct tep_event *event,
void *context);
-typedef int (*tep_plugin_load_func)(struct tep_handle *pevent);
-typedef int (*tep_plugin_unload_func)(struct tep_handle *pevent);
+typedef int (*tep_plugin_load_func)(struct tep_handle *tep);
+typedef int (*tep_plugin_unload_func)(struct tep_handle *tep);
struct tep_plugin_option {
struct tep_plugin_option *next;
@@ -85,12 +85,12 @@ struct tep_plugin_option {
* TEP_PLUGIN_LOADER: (required)
* The function name to initialized the plugin.
*
- * int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
+ * int TEP_PLUGIN_LOADER(struct tep_handle *tep)
*
* TEP_PLUGIN_UNLOADER: (optional)
* The function called just before unloading
*
- * int TEP_PLUGIN_UNLOADER(struct tep_handle *pevent)
+ * int TEP_PLUGIN_UNLOADER(struct tep_handle *tep)
*
* TEP_PLUGIN_OPTIONS: (optional)
* Plugin options that can be set before loading
@@ -278,7 +278,7 @@ struct tep_print_fmt {
};
struct tep_event {
- struct tep_handle *pevent;
+ struct tep_handle *tep;
char *name;
int id;
int flags;
@@ -393,9 +393,9 @@ struct tep_plugin_list;
#define INVALID_PLUGIN_LIST_OPTION ((char **)((unsigned long)-1))
-struct tep_plugin_list *tep_load_plugins(struct tep_handle *pevent);
+struct tep_plugin_list *tep_load_plugins(struct tep_handle *tep);
void tep_unload_plugins(struct tep_plugin_list *plugin_list,
- struct tep_handle *pevent);
+ struct tep_handle *tep);
char **tep_plugin_list_options(void);
void tep_plugin_free_options_list(char **list);
int tep_plugin_add_options(const char *name,
@@ -409,8 +409,10 @@ void tep_print_plugins(struct trace_seq *s,
typedef char *(tep_func_resolver_t)(void *priv,
unsigned long long *addrp, char **modp);
void tep_set_flag(struct tep_handle *tep, int flag);
+void tep_clear_flag(struct tep_handle *tep, enum tep_flag flag);
+bool tep_test_flag(struct tep_handle *tep, enum tep_flag flags);
-static inline int tep_host_bigendian(void)
+static inline int tep_is_bigendian(void)
{
unsigned char str[] = { 0x1, 0x2, 0x3, 0x4 };
unsigned int val;
@@ -428,37 +430,37 @@ enum trace_flag_type {
TRACE_FLAG_SOFTIRQ = 0x10,
};
-int tep_set_function_resolver(struct tep_handle *pevent,
+int tep_set_function_resolver(struct tep_handle *tep,
tep_func_resolver_t *func, void *priv);
-void tep_reset_function_resolver(struct tep_handle *pevent);
-int tep_register_comm(struct tep_handle *pevent, const char *comm, int pid);
-int tep_override_comm(struct tep_handle *pevent, const char *comm, int pid);
-int tep_register_trace_clock(struct tep_handle *pevent, const char *trace_clock);
-int tep_register_function(struct tep_handle *pevent, char *name,
+void tep_reset_function_resolver(struct tep_handle *tep);
+int tep_register_comm(struct tep_handle *tep, const char *comm, int pid);
+int tep_override_comm(struct tep_handle *tep, const char *comm, int pid);
+int tep_register_trace_clock(struct tep_handle *tep, const char *trace_clock);
+int tep_register_function(struct tep_handle *tep, char *name,
unsigned long long addr, char *mod);
-int tep_register_print_string(struct tep_handle *pevent, const char *fmt,
+int tep_register_print_string(struct tep_handle *tep, const char *fmt,
unsigned long long addr);
-int tep_pid_is_registered(struct tep_handle *pevent, int pid);
+bool tep_is_pid_registered(struct tep_handle *tep, int pid);
-void tep_print_event_task(struct tep_handle *pevent, struct trace_seq *s,
+void tep_print_event_task(struct tep_handle *tep, struct trace_seq *s,
struct tep_event *event,
struct tep_record *record);
-void tep_print_event_time(struct tep_handle *pevent, struct trace_seq *s,
+void tep_print_event_time(struct tep_handle *tep, struct trace_seq *s,
struct tep_event *event,
struct tep_record *record,
bool use_trace_clock);
-void tep_print_event_data(struct tep_handle *pevent, struct trace_seq *s,
+void tep_print_event_data(struct tep_handle *tep, struct trace_seq *s,
struct tep_event *event,
struct tep_record *record);
-void tep_print_event(struct tep_handle *pevent, struct trace_seq *s,
+void tep_print_event(struct tep_handle *tep, struct trace_seq *s,
struct tep_record *record, bool use_trace_clock);
-int tep_parse_header_page(struct tep_handle *pevent, char *buf, unsigned long size,
+int tep_parse_header_page(struct tep_handle *tep, char *buf, unsigned long size,
int long_size);
-enum tep_errno tep_parse_event(struct tep_handle *pevent, const char *buf,
+enum tep_errno tep_parse_event(struct tep_handle *tep, const char *buf,
unsigned long size, const char *sys);
-enum tep_errno tep_parse_format(struct tep_handle *pevent,
+enum tep_errno tep_parse_format(struct tep_handle *tep,
struct tep_event **eventp,
const char *buf,
unsigned long size, const char *sys);
@@ -490,50 +492,50 @@ enum tep_reg_handler {
TEP_REGISTER_SUCCESS_OVERWRITE,
};
-int tep_register_event_handler(struct tep_handle *pevent, int id,
+int tep_register_event_handler(struct tep_handle *tep, int id,
const char *sys_name, const char *event_name,
tep_event_handler_func func, void *context);
-int tep_unregister_event_handler(struct tep_handle *pevent, int id,
+int tep_unregister_event_handler(struct tep_handle *tep, int id,
const char *sys_name, const char *event_name,
tep_event_handler_func func, void *context);
-int tep_register_print_function(struct tep_handle *pevent,
+int tep_register_print_function(struct tep_handle *tep,
tep_func_handler func,
enum tep_func_arg_type ret_type,
char *name, ...);
-int tep_unregister_print_function(struct tep_handle *pevent,
+int tep_unregister_print_function(struct tep_handle *tep,
tep_func_handler func, char *name);
struct tep_format_field *tep_find_common_field(struct tep_event *event, const char *name);
struct tep_format_field *tep_find_field(struct tep_event *event, const char *name);
struct tep_format_field *tep_find_any_field(struct tep_event *event, const char *name);
-const char *tep_find_function(struct tep_handle *pevent, unsigned long long addr);
+const char *tep_find_function(struct tep_handle *tep, unsigned long long addr);
unsigned long long
-tep_find_function_address(struct tep_handle *pevent, unsigned long long addr);
-unsigned long long tep_read_number(struct tep_handle *pevent, const void *ptr, int size);
+tep_find_function_address(struct tep_handle *tep, unsigned long long addr);
+unsigned long long tep_read_number(struct tep_handle *tep, const void *ptr, int size);
int tep_read_number_field(struct tep_format_field *field, const void *data,
unsigned long long *value);
struct tep_event *tep_get_first_event(struct tep_handle *tep);
int tep_get_events_count(struct tep_handle *tep);
-struct tep_event *tep_find_event(struct tep_handle *pevent, int id);
+struct tep_event *tep_find_event(struct tep_handle *tep, int id);
struct tep_event *
-tep_find_event_by_name(struct tep_handle *pevent, const char *sys, const char *name);
+tep_find_event_by_name(struct tep_handle *tep, const char *sys, const char *name);
struct tep_event *
-tep_find_event_by_record(struct tep_handle *pevent, struct tep_record *record);
-
-void tep_data_lat_fmt(struct tep_handle *pevent,
- struct trace_seq *s, struct tep_record *record);
-int tep_data_type(struct tep_handle *pevent, struct tep_record *rec);
-int tep_data_pid(struct tep_handle *pevent, struct tep_record *rec);
-int tep_data_preempt_count(struct tep_handle *pevent, struct tep_record *rec);
-int tep_data_flags(struct tep_handle *pevent, struct tep_record *rec);
-const char *tep_data_comm_from_pid(struct tep_handle *pevent, int pid);
+tep_find_event_by_record(struct tep_handle *tep, struct tep_record *record);
+
+void tep_data_latency_format(struct tep_handle *tep,
+ struct trace_seq *s, struct tep_record *record);
+int tep_data_type(struct tep_handle *tep, struct tep_record *rec);
+int tep_data_pid(struct tep_handle *tep, struct tep_record *rec);
+int tep_data_preempt_count(struct tep_handle *tep, struct tep_record *rec);
+int tep_data_flags(struct tep_handle *tep, struct tep_record *rec);
+const char *tep_data_comm_from_pid(struct tep_handle *tep, int pid);
struct tep_cmdline;
-struct tep_cmdline *tep_data_pid_from_comm(struct tep_handle *pevent, const char *comm,
+struct tep_cmdline *tep_data_pid_from_comm(struct tep_handle *tep, const char *comm,
struct tep_cmdline *next);
-int tep_cmdline_pid(struct tep_handle *pevent, struct tep_cmdline *cmdline);
+int tep_cmdline_pid(struct tep_handle *tep, struct tep_cmdline *cmdline);
void tep_print_field(struct trace_seq *s, void *data,
struct tep_format_field *field);
@@ -541,10 +543,12 @@ void tep_print_fields(struct trace_seq *s, void *data,
int size __maybe_unused, struct tep_event *event);
void tep_event_info(struct trace_seq *s, struct tep_event *event,
struct tep_record *record);
-int tep_strerror(struct tep_handle *pevent, enum tep_errno errnum,
+int tep_strerror(struct tep_handle *tep, enum tep_errno errnum,
char *buf, size_t buflen);
-struct tep_event **tep_list_events(struct tep_handle *pevent, enum tep_event_sort_type);
+struct tep_event **tep_list_events(struct tep_handle *tep, enum tep_event_sort_type);
+struct tep_event **tep_list_events_copy(struct tep_handle *tep,
+ enum tep_event_sort_type);
struct tep_format_field **tep_event_common_fields(struct tep_event *event);
struct tep_format_field **tep_event_fields(struct tep_event *event);
@@ -552,24 +556,28 @@ enum tep_endian {
TEP_LITTLE_ENDIAN = 0,
TEP_BIG_ENDIAN
};
-int tep_get_cpus(struct tep_handle *pevent);
-void tep_set_cpus(struct tep_handle *pevent, int cpus);
-int tep_get_long_size(struct tep_handle *pevent);
-void tep_set_long_size(struct tep_handle *pevent, int long_size);
-int tep_get_page_size(struct tep_handle *pevent);
-void tep_set_page_size(struct tep_handle *pevent, int _page_size);
-int tep_file_bigendian(struct tep_handle *pevent);
-void tep_set_file_bigendian(struct tep_handle *pevent, enum tep_endian endian);
-int tep_is_host_bigendian(struct tep_handle *pevent);
-void tep_set_host_bigendian(struct tep_handle *pevent, enum tep_endian endian);
-int tep_is_latency_format(struct tep_handle *pevent);
-void tep_set_latency_format(struct tep_handle *pevent, int lat);
-int tep_get_header_page_size(struct tep_handle *pevent);
+int tep_get_cpus(struct tep_handle *tep);
+void tep_set_cpus(struct tep_handle *tep, int cpus);
+int tep_get_long_size(struct tep_handle *tep);
+void tep_set_long_size(struct tep_handle *tep, int long_size);
+int tep_get_page_size(struct tep_handle *tep);
+void tep_set_page_size(struct tep_handle *tep, int _page_size);
+bool tep_is_file_bigendian(struct tep_handle *tep);
+void tep_set_file_bigendian(struct tep_handle *tep, enum tep_endian endian);
+bool tep_is_local_bigendian(struct tep_handle *tep);
+void tep_set_local_bigendian(struct tep_handle *tep, enum tep_endian endian);
+bool tep_is_latency_format(struct tep_handle *tep);
+void tep_set_latency_format(struct tep_handle *tep, int lat);
+int tep_get_header_page_size(struct tep_handle *tep);
+int tep_get_header_timestamp_size(struct tep_handle *tep);
+bool tep_is_old_format(struct tep_handle *tep);
+void tep_set_print_raw(struct tep_handle *tep, int print_raw);
+void tep_set_test_filters(struct tep_handle *tep, int test_filters);
struct tep_handle *tep_alloc(void);
-void tep_free(struct tep_handle *pevent);
-void tep_ref(struct tep_handle *pevent);
-void tep_unref(struct tep_handle *pevent);
+void tep_free(struct tep_handle *tep);
+void tep_ref(struct tep_handle *tep);
+void tep_unref(struct tep_handle *tep);
int tep_get_ref(struct tep_handle *tep);
/* access to the internal parser */
@@ -581,8 +589,8 @@ const char *tep_get_input_buf(void);
unsigned long long tep_get_input_buf_ptr(void);
/* for debugging */
-void tep_print_funcs(struct tep_handle *pevent);
-void tep_print_printk(struct tep_handle *pevent);
+void tep_print_funcs(struct tep_handle *tep);
+void tep_print_printk(struct tep_handle *tep);
/* ----------------------- filtering ----------------------- */
@@ -709,13 +717,13 @@ struct tep_filter_type {
#define TEP_FILTER_ERROR_BUFSZ 1024
struct tep_event_filter {
- struct tep_handle *pevent;
+ struct tep_handle *tep;
int filters;
struct tep_filter_type *event_filters;
char error_buffer[TEP_FILTER_ERROR_BUFSZ];
};
-struct tep_event_filter *tep_filter_alloc(struct tep_handle *pevent);
+struct tep_event_filter *tep_filter_alloc(struct tep_handle *tep);
/* for backward compatibility */
#define FILTER_NONE TEP_ERRNO__NO_FILTER
@@ -723,12 +731,6 @@ struct tep_event_filter *tep_filter_alloc(struct tep_handle *pevent);
#define FILTER_MISS TEP_ERRNO__FILTER_MISS
#define FILTER_MATCH TEP_ERRNO__FILTER_MATCH
-enum tep_filter_trivial_type {
- TEP_FILTER_TRIVIAL_FALSE,
- TEP_FILTER_TRIVIAL_TRUE,
- TEP_FILTER_TRIVIAL_BOTH,
-};
-
enum tep_errno tep_filter_add_filter_str(struct tep_event_filter *filter,
const char *filter_str);
@@ -743,9 +745,6 @@ int tep_event_filtered(struct tep_event_filter *filter,
void tep_filter_reset(struct tep_event_filter *filter);
-int tep_filter_clear_trivial(struct tep_event_filter *filter,
- enum tep_filter_trivial_type type);
-
void tep_filter_free(struct tep_event_filter *filter);
char *tep_filter_make_string(struct tep_event_filter *filter, int event_id);
@@ -753,15 +752,8 @@ char *tep_filter_make_string(struct tep_event_filter *filter, int event_id);
int tep_filter_remove_event(struct tep_event_filter *filter,
int event_id);
-int tep_filter_event_has_trivial(struct tep_event_filter *filter,
- int event_id,
- enum tep_filter_trivial_type type);
-
int tep_filter_copy(struct tep_event_filter *dest, struct tep_event_filter *source);
-int tep_update_trivial(struct tep_event_filter *dest, struct tep_event_filter *source,
- enum tep_filter_trivial_type type);
-
int tep_filter_compare(struct tep_event_filter *filter1, struct tep_event_filter *filter2);
#endif /* _PARSE_EVENTS_H */
diff --git a/tools/lib/traceevent/event-plugin.c b/tools/lib/traceevent/event-plugin.c
index e74f16c88398..8ca28de9337a 100644
--- a/tools/lib/traceevent/event-plugin.c
+++ b/tools/lib/traceevent/event-plugin.c
@@ -269,7 +269,7 @@ void tep_print_plugins(struct trace_seq *s,
}
static void
-load_plugin(struct tep_handle *pevent, const char *path,
+load_plugin(struct tep_handle *tep, const char *path,
const char *file, void *data)
{
struct tep_plugin_list **plugin_list = data;
@@ -316,7 +316,7 @@ load_plugin(struct tep_handle *pevent, const char *path,
*plugin_list = list;
pr_stat("registering plugin: %s", plugin);
- func(pevent);
+ func(tep);
return;
out_free:
@@ -324,9 +324,9 @@ load_plugin(struct tep_handle *pevent, const char *path,
}
static void
-load_plugins_dir(struct tep_handle *pevent, const char *suffix,
+load_plugins_dir(struct tep_handle *tep, const char *suffix,
const char *path,
- void (*load_plugin)(struct tep_handle *pevent,
+ void (*load_plugin)(struct tep_handle *tep,
const char *path,
const char *name,
void *data),
@@ -359,15 +359,15 @@ load_plugins_dir(struct tep_handle *pevent, const char *suffix,
if (strcmp(name + (strlen(name) - strlen(suffix)), suffix) != 0)
continue;
- load_plugin(pevent, path, name, data);
+ load_plugin(tep, path, name, data);
}
closedir(dir);
}
static void
-load_plugins(struct tep_handle *pevent, const char *suffix,
- void (*load_plugin)(struct tep_handle *pevent,
+load_plugins(struct tep_handle *tep, const char *suffix,
+ void (*load_plugin)(struct tep_handle *tep,
const char *path,
const char *name,
void *data),
@@ -378,7 +378,7 @@ load_plugins(struct tep_handle *pevent, const char *suffix,
char *envdir;
int ret;
- if (pevent->flags & TEP_DISABLE_PLUGINS)
+ if (tep->flags & TEP_DISABLE_PLUGINS)
return;
/*
@@ -386,8 +386,8 @@ load_plugins(struct tep_handle *pevent, const char *suffix,
* check that first.
*/
#ifdef PLUGIN_DIR
- if (!(pevent->flags & TEP_DISABLE_SYS_PLUGINS))
- load_plugins_dir(pevent, suffix, PLUGIN_DIR,
+ if (!(tep->flags & TEP_DISABLE_SYS_PLUGINS))
+ load_plugins_dir(tep, suffix, PLUGIN_DIR,
load_plugin, data);
#endif
@@ -397,7 +397,7 @@ load_plugins(struct tep_handle *pevent, const char *suffix,
*/
envdir = getenv("TRACEEVENT_PLUGIN_DIR");
if (envdir)
- load_plugins_dir(pevent, suffix, envdir, load_plugin, data);
+ load_plugins_dir(tep, suffix, envdir, load_plugin, data);
/*
* Now let the home directory override the environment
@@ -413,22 +413,22 @@ load_plugins(struct tep_handle *pevent, const char *suffix,
return;
}
- load_plugins_dir(pevent, suffix, path, load_plugin, data);
+ load_plugins_dir(tep, suffix, path, load_plugin, data);
free(path);
}
struct tep_plugin_list*
-tep_load_plugins(struct tep_handle *pevent)
+tep_load_plugins(struct tep_handle *tep)
{
struct tep_plugin_list *list = NULL;
- load_plugins(pevent, ".so", load_plugin, &list);
+ load_plugins(tep, ".so", load_plugin, &list);
return list;
}
void
-tep_unload_plugins(struct tep_plugin_list *plugin_list, struct tep_handle *pevent)
+tep_unload_plugins(struct tep_plugin_list *plugin_list, struct tep_handle *tep)
{
tep_plugin_unload_func func;
struct tep_plugin_list *list;
@@ -438,7 +438,7 @@ tep_unload_plugins(struct tep_plugin_list *plugin_list, struct tep_handle *peven
plugin_list = list->next;
func = dlsym(list->handle, TEP_PLUGIN_UNLOADER_NAME);
if (func)
- func(pevent);
+ func(tep);
dlclose(list->handle);
free(list->name);
free(list);
diff --git a/tools/lib/traceevent/kbuffer-parse.c b/tools/lib/traceevent/kbuffer-parse.c
index af2a1f3b7424..b887e7437d67 100644
--- a/tools/lib/traceevent/kbuffer-parse.c
+++ b/tools/lib/traceevent/kbuffer-parse.c
@@ -727,3 +727,52 @@ int kbuffer_start_of_data(struct kbuffer *kbuf)
{
return kbuf->start;
}
+
+/**
+ * kbuffer_raw_get - get raw buffer info
+ * @kbuf: The kbuffer
+ * @subbuf: Start of mapped subbuffer
+ * @info: Info descriptor to fill in
+ *
+ * For debugging. This can return internals of the ring buffer.
+ * Expects to have info->next set to what it will read.
+ * The type, length and timestamp delta will be filled in, and
+ * @info->next will be updated to the next element.
+ * The @subbuf is used to know if the info is passed the end of
+ * data and NULL will be returned if it is.
+ */
+struct kbuffer_raw_info *
+kbuffer_raw_get(struct kbuffer *kbuf, void *subbuf, struct kbuffer_raw_info *info)
+{
+ unsigned long long flags;
+ unsigned long long delta;
+ unsigned int type_len;
+ unsigned int size;
+ int start;
+ int length;
+ void *ptr = info->next;
+
+ if (!kbuf || !subbuf)
+ return NULL;
+
+ if (kbuf->flags & KBUFFER_FL_LONG_8)
+ start = 16;
+ else
+ start = 12;
+
+ flags = read_long(kbuf, subbuf + 8);
+ size = (unsigned int)flags & COMMIT_MASK;
+
+ if (ptr < subbuf || ptr >= subbuf + start + size)
+ return NULL;
+
+ type_len = translate_data(kbuf, ptr, &ptr, &delta, &length);
+
+ info->next = ptr + length;
+
+ info->type = type_len;
+ info->delta = delta;
+ info->length = length;
+
+ return info;
+}
diff --git a/tools/lib/traceevent/kbuffer.h b/tools/lib/traceevent/kbuffer.h
index 03dce757553f..ed4d697fc137 100644
--- a/tools/lib/traceevent/kbuffer.h
+++ b/tools/lib/traceevent/kbuffer.h
@@ -65,4 +65,17 @@ int kbuffer_subbuffer_size(struct kbuffer *kbuf);
void kbuffer_set_old_format(struct kbuffer *kbuf);
int kbuffer_start_of_data(struct kbuffer *kbuf);
+/* Debugging */
+
+struct kbuffer_raw_info {
+ int type;
+ int length;
+ unsigned long long delta;
+ void *next;
+};
+
+/* Read raw data */
+struct kbuffer_raw_info *kbuffer_raw_get(struct kbuffer *kbuf, void *subbuf,
+ struct kbuffer_raw_info *info);
+
#endif /* _K_BUFFER_H */
diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c
index cb5ce66dab6e..552592d153fb 100644
--- a/tools/lib/traceevent/parse-filter.c
+++ b/tools/lib/traceevent/parse-filter.c
@@ -154,7 +154,7 @@ add_filter_type(struct tep_event_filter *filter, int id)
filter_type = &filter->event_filters[i];
filter_type->event_id = id;
- filter_type->event = tep_find_event(filter->pevent, id);
+ filter_type->event = tep_find_event(filter->tep, id);
filter_type->filter = NULL;
filter->filters++;
@@ -164,9 +164,9 @@ add_filter_type(struct tep_event_filter *filter, int id)
/**
* tep_filter_alloc - create a new event filter
- * @pevent: The pevent that this filter is associated with
+ * @tep: The tep that this filter is associated with
*/
-struct tep_event_filter *tep_filter_alloc(struct tep_handle *pevent)
+struct tep_event_filter *tep_filter_alloc(struct tep_handle *tep)
{
struct tep_event_filter *filter;
@@ -175,8 +175,8 @@ struct tep_event_filter *tep_filter_alloc(struct tep_handle *pevent)
return NULL;
memset(filter, 0, sizeof(*filter));
- filter->pevent = pevent;
- tep_ref(pevent);
+ filter->tep = tep;
+ tep_ref(tep);
return filter;
}
@@ -256,7 +256,7 @@ static int event_match(struct tep_event *event,
}
static enum tep_errno
-find_event(struct tep_handle *pevent, struct event_list **events,
+find_event(struct tep_handle *tep, struct event_list **events,
char *sys_name, char *event_name)
{
struct tep_event *event;
@@ -299,8 +299,8 @@ find_event(struct tep_handle *pevent, struct event_list **events,
}
}
- for (i = 0; i < pevent->nr_events; i++) {
- event = pevent->events[i];
+ for (i = 0; i < tep->nr_events; i++) {
+ event = tep->events[i];
if (event_match(event, sys_name ? &sreg : NULL, &ereg)) {
match = 1;
if (add_event(events, event) < 0) {
@@ -1257,7 +1257,7 @@ static void filter_init_error_buf(struct tep_event_filter *filter)
enum tep_errno tep_filter_add_filter_str(struct tep_event_filter *filter,
const char *filter_str)
{
- struct tep_handle *pevent = filter->pevent;
+ struct tep_handle *tep = filter->tep;
struct event_list *event;
struct event_list *events = NULL;
const char *filter_start;
@@ -1313,7 +1313,7 @@ enum tep_errno tep_filter_add_filter_str(struct tep_event_filter *filter,
}
/* Find this event */
- ret = find_event(pevent, &events, strim(sys_name), strim(event_name));
+ ret = find_event(tep, &events, strim(sys_name), strim(event_name));
if (ret < 0) {
free_events(events);
free(this_event);
@@ -1334,7 +1334,7 @@ enum tep_errno tep_filter_add_filter_str(struct tep_event_filter *filter,
if (ret < 0)
rtn = ret;
- if (ret >= 0 && pevent->test_filters) {
+ if (ret >= 0 && tep->test_filters) {
char *test;
test = tep_filter_make_string(filter, event->event->id);
if (test) {
@@ -1346,9 +1346,6 @@ enum tep_errno tep_filter_add_filter_str(struct tep_event_filter *filter,
free_events(events);
- if (rtn >= 0 && pevent->test_filters)
- exit(0);
-
return rtn;
}
@@ -1380,7 +1377,7 @@ int tep_filter_strerror(struct tep_event_filter *filter, enum tep_errno err,
return 0;
}
- return tep_strerror(filter->pevent, err, buf, buflen);
+ return tep_strerror(filter->tep, err, buf, buflen);
}
/**
@@ -1443,7 +1440,7 @@ void tep_filter_reset(struct tep_event_filter *filter)
void tep_filter_free(struct tep_event_filter *filter)
{
- tep_unref(filter->pevent);
+ tep_unref(filter->tep);
tep_filter_reset(filter);
@@ -1462,10 +1459,10 @@ static int copy_filter_type(struct tep_event_filter *filter,
const char *name;
char *str;
- /* Can't assume that the pevent's are the same */
+ /* Can't assume that the tep's are the same */
sys = filter_type->event->system;
name = filter_type->event->name;
- event = tep_find_event_by_name(filter->pevent, sys, name);
+ event = tep_find_event_by_name(filter->tep, sys, name);
if (!event)
return -1;
@@ -1522,167 +1519,6 @@ int tep_filter_copy(struct tep_event_filter *dest, struct tep_event_filter *sour
return ret;
}
-
-/**
- * tep_update_trivial - update the trivial filters with the given filter
- * @dest - the filter to update
- * @source - the filter as the source of the update
- * @type - the type of trivial filter to update.
- *
- * Scan dest for trivial events matching @type to replace with the source.
- *
- * Returns 0 on success and -1 if there was a problem updating, but
- * events may have still been updated on error.
- */
-int tep_update_trivial(struct tep_event_filter *dest, struct tep_event_filter *source,
- enum tep_filter_trivial_type type)
-{
- struct tep_handle *src_pevent;
- struct tep_handle *dest_pevent;
- struct tep_event *event;
- struct tep_filter_type *filter_type;
- struct tep_filter_arg *arg;
- char *str;
- int i;
-
- src_pevent = source->pevent;
- dest_pevent = dest->pevent;
-
- /* Do nothing if either of the filters has nothing to filter */
- if (!dest->filters || !source->filters)
- return 0;
-
- for (i = 0; i < dest->filters; i++) {
- filter_type = &dest->event_filters[i];
- arg = filter_type->filter;
- if (arg->type != TEP_FILTER_ARG_BOOLEAN)
- continue;
- if ((arg->boolean.value && type == TEP_FILTER_TRIVIAL_FALSE) ||
- (!arg->boolean.value && type == TEP_FILTER_TRIVIAL_TRUE))
- continue;
-
- event = filter_type->event;
-
- if (src_pevent != dest_pevent) {
- /* do a look up */
- event = tep_find_event_by_name(src_pevent,
- event->system,
- event->name);
- if (!event)
- return -1;
- }
-
- str = tep_filter_make_string(source, event->id);
- if (!str)
- continue;
-
- /* Don't bother if the filter is trivial too */
- if (strcmp(str, "TRUE") != 0 && strcmp(str, "FALSE") != 0)
- filter_event(dest, event, str, NULL);
- free(str);
- }
- return 0;
-}
-
-/**
- * tep_filter_clear_trivial - clear TRUE and FALSE filters
- * @filter: the filter to remove trivial filters from
- * @type: remove only true, false, or both
- *
- * Removes filters that only contain a TRUE or FALES boolean arg.
- *
- * Returns 0 on success and -1 if there was a problem.
- */
-int tep_filter_clear_trivial(struct tep_event_filter *filter,
- enum tep_filter_trivial_type type)
-{
- struct tep_filter_type *filter_type;
- int count = 0;
- int *ids = NULL;
- int i;
-
- if (!filter->filters)
- return 0;
-
- /*
- * Two steps, first get all ids with trivial filters.
- * then remove those ids.
- */
- for (i = 0; i < filter->filters; i++) {
- int *new_ids;
-
- filter_type = &filter->event_filters[i];
- if (filter_type->filter->type != TEP_FILTER_ARG_BOOLEAN)
- continue;
- switch (type) {
- case TEP_FILTER_TRIVIAL_FALSE:
- if (filter_type->filter->boolean.value)
- continue;
- break;
- case TEP_FILTER_TRIVIAL_TRUE:
- if (!filter_type->filter->boolean.value)
- continue;
- default:
- break;
- }
-
- new_ids = realloc(ids, sizeof(*ids) * (count + 1));
- if (!new_ids) {
- free(ids);
- return -1;
- }
-
- ids = new_ids;
- ids[count++] = filter_type->event_id;
- }
-
- if (!count)
- return 0;
-
- for (i = 0; i < count; i++)
- tep_filter_remove_event(filter, ids[i]);
-
- free(ids);
- return 0;
-}
-
-/**
- * tep_filter_event_has_trivial - return true event contains trivial filter
- * @filter: the filter with the information
- * @event_id: the id of the event to test
- * @type: trivial type to test for (TRUE, FALSE, EITHER)
- *
- * Returns 1 if the event contains a matching trivial type
- * otherwise 0.
- */
-int tep_filter_event_has_trivial(struct tep_event_filter *filter,
- int event_id,
- enum tep_filter_trivial_type type)
-{
- struct tep_filter_type *filter_type;
-
- if (!filter->filters)
- return 0;
-
- filter_type = find_filter_type(filter, event_id);
-
- if (!filter_type)
- return 0;
-
- if (filter_type->filter->type != TEP_FILTER_ARG_BOOLEAN)
- return 0;
-
- switch (type) {
- case TEP_FILTER_TRIVIAL_FALSE:
- return !filter_type->filter->boolean.value;
-
- case TEP_FILTER_TRIVIAL_TRUE:
- return filter_type->filter->boolean.value;
- default:
- return 1;
- }
-}
-
static int test_filter(struct tep_event *event, struct tep_filter_arg *arg,
struct tep_record *record, enum tep_errno *err);
@@ -1692,8 +1528,8 @@ get_comm(struct tep_event *event, struct tep_record *record)
const char *comm;
int pid;
- pid = tep_data_pid(event->pevent, record);
- comm = tep_data_comm_from_pid(event->pevent, pid);
+ pid = tep_data_pid(event->tep, record);
+ comm = tep_data_comm_from_pid(event->tep, pid);
return comm;
}
@@ -1861,7 +1697,7 @@ static int test_num(struct tep_event *event, struct tep_filter_arg *arg,
static const char *get_field_str(struct tep_filter_arg *arg, struct tep_record *record)
{
struct tep_event *event;
- struct tep_handle *pevent;
+ struct tep_handle *tep;
unsigned long long addr;
const char *val = NULL;
unsigned int size;
@@ -1891,12 +1727,12 @@ static const char *get_field_str(struct tep_filter_arg *arg, struct tep_record *
} else {
event = arg->str.field->event;
- pevent = event->pevent;
+ tep = event->tep;
addr = get_value(event, arg->str.field, record);
if (arg->str.field->flags & (TEP_FIELD_IS_POINTER | TEP_FIELD_IS_LONG))
/* convert to a kernel symbol */
- val = tep_find_function(pevent, addr);
+ val = tep_find_function(tep, addr);
if (val == NULL) {
/* just use the hex of the string name */
@@ -2036,7 +1872,7 @@ int tep_event_filtered(struct tep_event_filter *filter, int event_id)
enum tep_errno tep_filter_match(struct tep_event_filter *filter,
struct tep_record *record)
{
- struct tep_handle *pevent = filter->pevent;
+ struct tep_handle *tep = filter->tep;
struct tep_filter_type *filter_type;
int event_id;
int ret;
@@ -2047,7 +1883,7 @@ enum tep_errno tep_filter_match(struct tep_event_filter *filter,
if (!filter->filters)
return TEP_ERRNO__NO_FILTER;
- event_id = tep_data_type(pevent, record);
+ event_id = tep_data_type(tep, record);
filter_type = find_filter_type(filter, event_id);
if (!filter_type)
@@ -2409,14 +2245,6 @@ int tep_filter_compare(struct tep_event_filter *filter1, struct tep_event_filter
break;
if (filter_type1->filter->type != filter_type2->filter->type)
break;
- switch (filter_type1->filter->type) {
- case TEP_FILTER_TRIVIAL_FALSE:
- case TEP_FILTER_TRIVIAL_TRUE:
- /* trivial types just need the type compared */
- continue;
- default:
- break;
- }
/* The best way to compare complex filters is with strings */
str1 = arg_to_str(filter1, filter_type1->filter);
str2 = arg_to_str(filter2, filter_type2->filter);
diff --git a/tools/lib/traceevent/parse-utils.c b/tools/lib/traceevent/parse-utils.c
index 77e4ec6402dd..e99867111387 100644
--- a/tools/lib/traceevent/parse-utils.c
+++ b/tools/lib/traceevent/parse-utils.c
@@ -14,7 +14,7 @@
void __vwarning(const char *fmt, va_list ap)
{
if (errno)
- perror("trace-cmd");
+ perror("libtraceevent");
errno = 0;
fprintf(stderr, " ");
diff --git a/tools/lib/traceevent/plugin_cfg80211.c b/tools/lib/traceevent/plugin_cfg80211.c
index a51b366f47da..3d43b56a6c98 100644
--- a/tools/lib/traceevent/plugin_cfg80211.c
+++ b/tools/lib/traceevent/plugin_cfg80211.c
@@ -25,9 +25,9 @@ process___le16_to_cpup(struct trace_seq *s, unsigned long long *args)
return val ? (long long) le16toh(*val) : 0;
}
-int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
+int TEP_PLUGIN_LOADER(struct tep_handle *tep)
{
- tep_register_print_function(pevent,
+ tep_register_print_function(tep,
process___le16_to_cpup,
TEP_FUNC_ARG_INT,
"__le16_to_cpup",
@@ -36,8 +36,8 @@ int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
return 0;
}
-void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent)
+void TEP_PLUGIN_UNLOADER(struct tep_handle *tep)
{
- tep_unregister_print_function(pevent, process___le16_to_cpup,
+ tep_unregister_print_function(tep, process___le16_to_cpup,
"__le16_to_cpup");
}
diff --git a/tools/lib/traceevent/plugin_function.c b/tools/lib/traceevent/plugin_function.c
index a73eca34a8f9..7770fcb78e0f 100644
--- a/tools/lib/traceevent/plugin_function.c
+++ b/tools/lib/traceevent/plugin_function.c
@@ -126,7 +126,7 @@ static int add_and_get_index(const char *parent, const char *child, int cpu)
static int function_handler(struct trace_seq *s, struct tep_record *record,
struct tep_event *event, void *context)
{
- struct tep_handle *pevent = event->pevent;
+ struct tep_handle *tep = event->tep;
unsigned long long function;
unsigned long long pfunction;
const char *func;
@@ -136,12 +136,12 @@ static int function_handler(struct trace_seq *s, struct tep_record *record,
if (tep_get_field_val(s, event, "ip", record, &function, 1))
return trace_seq_putc(s, '!');
- func = tep_find_function(pevent, function);
+ func = tep_find_function(tep, function);
if (tep_get_field_val(s, event, "parent_ip", record, &pfunction, 1))
return trace_seq_putc(s, '!');
- parent = tep_find_function(pevent, pfunction);
+ parent = tep_find_function(tep, pfunction);
if (parent && ftrace_indent->set)
index = add_and_get_index(parent, func, record->cpu);
@@ -164,9 +164,9 @@ static int function_handler(struct trace_seq *s, struct tep_record *record,
return 0;
}
-int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
+int TEP_PLUGIN_LOADER(struct tep_handle *tep)
{
- tep_register_event_handler(pevent, -1, "ftrace", "function",
+ tep_register_event_handler(tep, -1, "ftrace", "function",
function_handler, NULL);
tep_plugin_add_options("ftrace", plugin_options);
@@ -174,11 +174,11 @@ int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
return 0;
}
-void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent)
+void TEP_PLUGIN_UNLOADER(struct tep_handle *tep)
{
int i, x;
- tep_unregister_event_handler(pevent, -1, "ftrace", "function",
+ tep_unregister_event_handler(tep, -1, "ftrace", "function",
function_handler, NULL);
for (i = 0; i <= cpus; i++) {
diff --git a/tools/lib/traceevent/plugin_hrtimer.c b/tools/lib/traceevent/plugin_hrtimer.c
index 5db5e401275f..bb434e0ed03a 100644
--- a/tools/lib/traceevent/plugin_hrtimer.c
+++ b/tools/lib/traceevent/plugin_hrtimer.c
@@ -67,23 +67,23 @@ static int timer_start_handler(struct trace_seq *s,
return 0;
}
-int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
+int TEP_PLUGIN_LOADER(struct tep_handle *tep)
{
- tep_register_event_handler(pevent, -1,
+ tep_register_event_handler(tep, -1,
"timer", "hrtimer_expire_entry",
timer_expire_handler, NULL);
- tep_register_event_handler(pevent, -1, "timer", "hrtimer_start",
+ tep_register_event_handler(tep, -1, "timer", "hrtimer_start",
timer_start_handler, NULL);
return 0;
}
-void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent)
+void TEP_PLUGIN_UNLOADER(struct tep_handle *tep)
{
- tep_unregister_event_handler(pevent, -1,
+ tep_unregister_event_handler(tep, -1,
"timer", "hrtimer_expire_entry",
timer_expire_handler, NULL);
- tep_unregister_event_handler(pevent, -1, "timer", "hrtimer_start",
+ tep_unregister_event_handler(tep, -1, "timer", "hrtimer_start",
timer_start_handler, NULL);
}
diff --git a/tools/lib/traceevent/plugin_jbd2.c b/tools/lib/traceevent/plugin_jbd2.c
index a5e34135dd6a..04fc125f38cb 100644
--- a/tools/lib/traceevent/plugin_jbd2.c
+++ b/tools/lib/traceevent/plugin_jbd2.c
@@ -48,16 +48,16 @@ process_jiffies_to_msecs(struct trace_seq *s, unsigned long long *args)
return jiffies;
}
-int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
+int TEP_PLUGIN_LOADER(struct tep_handle *tep)
{
- tep_register_print_function(pevent,
+ tep_register_print_function(tep,
process_jbd2_dev_to_name,
TEP_FUNC_ARG_STRING,
"jbd2_dev_to_name",
TEP_FUNC_ARG_INT,
TEP_FUNC_ARG_VOID);
- tep_register_print_function(pevent,
+ tep_register_print_function(tep,
process_jiffies_to_msecs,
TEP_FUNC_ARG_LONG,
"jiffies_to_msecs",
@@ -66,11 +66,11 @@ int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
return 0;
}
-void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent)
+void TEP_PLUGIN_UNLOADER(struct tep_handle *tep)
{
- tep_unregister_print_function(pevent, process_jbd2_dev_to_name,
+ tep_unregister_print_function(tep, process_jbd2_dev_to_name,
"jbd2_dev_to_name");
- tep_unregister_print_function(pevent, process_jiffies_to_msecs,
+ tep_unregister_print_function(tep, process_jiffies_to_msecs,
"jiffies_to_msecs");
}
diff --git a/tools/lib/traceevent/plugin_kmem.c b/tools/lib/traceevent/plugin_kmem.c
index 0e3c601f9ed1..edaec5d962c3 100644
--- a/tools/lib/traceevent/plugin_kmem.c
+++ b/tools/lib/traceevent/plugin_kmem.c
@@ -39,57 +39,57 @@ static int call_site_handler(struct trace_seq *s, struct tep_record *record,
if (tep_read_number_field(field, data, &val))
return 1;
- func = tep_find_function(event->pevent, val);
+ func = tep_find_function(event->tep, val);
if (!func)
return 1;
- addr = tep_find_function_address(event->pevent, val);
+ addr = tep_find_function_address(event->tep, val);
trace_seq_printf(s, "(%s+0x%x) ", func, (int)(val - addr));
return 1;
}
-int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
+int TEP_PLUGIN_LOADER(struct tep_handle *tep)
{
- tep_register_event_handler(pevent, -1, "kmem", "kfree",
+ tep_register_event_handler(tep, -1, "kmem", "kfree",
call_site_handler, NULL);
- tep_register_event_handler(pevent, -1, "kmem", "kmalloc",
+ tep_register_event_handler(tep, -1, "kmem", "kmalloc",
call_site_handler, NULL);
- tep_register_event_handler(pevent, -1, "kmem", "kmalloc_node",
+ tep_register_event_handler(tep, -1, "kmem", "kmalloc_node",
call_site_handler, NULL);
- tep_register_event_handler(pevent, -1, "kmem", "kmem_cache_alloc",
+ tep_register_event_handler(tep, -1, "kmem", "kmem_cache_alloc",
call_site_handler, NULL);
- tep_register_event_handler(pevent, -1, "kmem",
+ tep_register_event_handler(tep, -1, "kmem",
"kmem_cache_alloc_node",
call_site_handler, NULL);
- tep_register_event_handler(pevent, -1, "kmem", "kmem_cache_free",
+ tep_register_event_handler(tep, -1, "kmem", "kmem_cache_free",
call_site_handler, NULL);
return 0;
}
-void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent)
+void TEP_PLUGIN_UNLOADER(struct tep_handle *tep)
{
- tep_unregister_event_handler(pevent, -1, "kmem", "kfree",
+ tep_unregister_event_handler(tep, -1, "kmem", "kfree",
call_site_handler, NULL);
- tep_unregister_event_handler(pevent, -1, "kmem", "kmalloc",
+ tep_unregister_event_handler(tep, -1, "kmem", "kmalloc",
call_site_handler, NULL);
- tep_unregister_event_handler(pevent, -1, "kmem", "kmalloc_node",
+ tep_unregister_event_handler(tep, -1, "kmem", "kmalloc_node",
call_site_handler, NULL);
- tep_unregister_event_handler(pevent, -1, "kmem", "kmem_cache_alloc",
+ tep_unregister_event_handler(tep, -1, "kmem", "kmem_cache_alloc",
call_site_handler, NULL);
- tep_unregister_event_handler(pevent, -1, "kmem",
+ tep_unregister_event_handler(tep, -1, "kmem",
"kmem_cache_alloc_node",
call_site_handler, NULL);
- tep_unregister_event_handler(pevent, -1, "kmem", "kmem_cache_free",
+ tep_unregister_event_handler(tep, -1, "kmem", "kmem_cache_free",
call_site_handler, NULL);
}
diff --git a/tools/lib/traceevent/plugin_kvm.c b/tools/lib/traceevent/plugin_kvm.c
index 64b9c25a1fd3..c8e623065a7e 100644
--- a/tools/lib/traceevent/plugin_kvm.c
+++ b/tools/lib/traceevent/plugin_kvm.c
@@ -389,8 +389,8 @@ static int kvm_mmu_print_role(struct trace_seq *s, struct tep_record *record,
* We can only use the structure if file is of the same
* endianness.
*/
- if (tep_file_bigendian(event->pevent) ==
- tep_is_host_bigendian(event->pevent)) {
+ if (tep_is_file_bigendian(event->tep) ==
+ tep_is_local_bigendian(event->tep)) {
trace_seq_printf(s, "%u q%u%s %s%s %spae %snxe %swp%s%s%s",
role.level,
@@ -445,40 +445,40 @@ process_is_writable_pte(struct trace_seq *s, unsigned long long *args)
return pte & PT_WRITABLE_MASK;
}
-int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
+int TEP_PLUGIN_LOADER(struct tep_handle *tep)
{
init_disassembler();
- tep_register_event_handler(pevent, -1, "kvm", "kvm_exit",
+ tep_register_event_handler(tep, -1, "kvm", "kvm_exit",
kvm_exit_handler, NULL);
- tep_register_event_handler(pevent, -1, "kvm", "kvm_emulate_insn",
+ tep_register_event_handler(tep, -1, "kvm", "kvm_emulate_insn",
kvm_emulate_insn_handler, NULL);
- tep_register_event_handler(pevent, -1, "kvm", "kvm_nested_vmexit",
+ tep_register_event_handler(tep, -1, "kvm", "kvm_nested_vmexit",
kvm_nested_vmexit_handler, NULL);
- tep_register_event_handler(pevent, -1, "kvm", "kvm_nested_vmexit_inject",
+ tep_register_event_handler(tep, -1, "kvm", "kvm_nested_vmexit_inject",
kvm_nested_vmexit_inject_handler, NULL);
- tep_register_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_get_page",
+ tep_register_event_handler(tep, -1, "kvmmmu", "kvm_mmu_get_page",
kvm_mmu_get_page_handler, NULL);
- tep_register_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_sync_page",
+ tep_register_event_handler(tep, -1, "kvmmmu", "kvm_mmu_sync_page",
kvm_mmu_print_role, NULL);
- tep_register_event_handler(pevent, -1,
+ tep_register_event_handler(tep, -1,
"kvmmmu", "kvm_mmu_unsync_page",
kvm_mmu_print_role, NULL);
- tep_register_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_zap_page",
+ tep_register_event_handler(tep, -1, "kvmmmu", "kvm_mmu_zap_page",
kvm_mmu_print_role, NULL);
- tep_register_event_handler(pevent, -1, "kvmmmu",
+ tep_register_event_handler(tep, -1, "kvmmmu",
"kvm_mmu_prepare_zap_page", kvm_mmu_print_role,
NULL);
- tep_register_print_function(pevent,
+ tep_register_print_function(tep,
process_is_writable_pte,
TEP_FUNC_ARG_INT,
"is_writable_pte",
@@ -487,37 +487,37 @@ int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
return 0;
}
-void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent)
+void TEP_PLUGIN_UNLOADER(struct tep_handle *tep)
{
- tep_unregister_event_handler(pevent, -1, "kvm", "kvm_exit",
+ tep_unregister_event_handler(tep, -1, "kvm", "kvm_exit",
kvm_exit_handler, NULL);
- tep_unregister_event_handler(pevent, -1, "kvm", "kvm_emulate_insn",
+ tep_unregister_event_handler(tep, -1, "kvm", "kvm_emulate_insn",
kvm_emulate_insn_handler, NULL);
- tep_unregister_event_handler(pevent, -1, "kvm", "kvm_nested_vmexit",
+ tep_unregister_event_handler(tep, -1, "kvm", "kvm_nested_vmexit",
kvm_nested_vmexit_handler, NULL);
- tep_unregister_event_handler(pevent, -1, "kvm", "kvm_nested_vmexit_inject",
+ tep_unregister_event_handler(tep, -1, "kvm", "kvm_nested_vmexit_inject",
kvm_nested_vmexit_inject_handler, NULL);
- tep_unregister_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_get_page",
+ tep_unregister_event_handler(tep, -1, "kvmmmu", "kvm_mmu_get_page",
kvm_mmu_get_page_handler, NULL);
- tep_unregister_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_sync_page",
+ tep_unregister_event_handler(tep, -1, "kvmmmu", "kvm_mmu_sync_page",
kvm_mmu_print_role, NULL);
- tep_unregister_event_handler(pevent, -1,
+ tep_unregister_event_handler(tep, -1,
"kvmmmu", "kvm_mmu_unsync_page",
kvm_mmu_print_role, NULL);
- tep_unregister_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_zap_page",
+ tep_unregister_event_handler(tep, -1, "kvmmmu", "kvm_mmu_zap_page",
kvm_mmu_print_role, NULL);
- tep_unregister_event_handler(pevent, -1, "kvmmmu",
+ tep_unregister_event_handler(tep, -1, "kvmmmu",
"kvm_mmu_prepare_zap_page", kvm_mmu_print_role,
NULL);
- tep_unregister_print_function(pevent, process_is_writable_pte,
+ tep_unregister_print_function(tep, process_is_writable_pte,
"is_writable_pte");
}
diff --git a/tools/lib/traceevent/plugin_mac80211.c b/tools/lib/traceevent/plugin_mac80211.c
index e38b9477aad2..884303c26b5c 100644
--- a/tools/lib/traceevent/plugin_mac80211.c
+++ b/tools/lib/traceevent/plugin_mac80211.c
@@ -87,17 +87,17 @@ static int drv_bss_info_changed(struct trace_seq *s,
return 0;
}
-int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
+int TEP_PLUGIN_LOADER(struct tep_handle *tep)
{
- tep_register_event_handler(pevent, -1, "mac80211",
+ tep_register_event_handler(tep, -1, "mac80211",
"drv_bss_info_changed",
drv_bss_info_changed, NULL);
return 0;
}
-void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent)
+void TEP_PLUGIN_UNLOADER(struct tep_handle *tep)
{
- tep_unregister_event_handler(pevent, -1, "mac80211",
+ tep_unregister_event_handler(tep, -1, "mac80211",
"drv_bss_info_changed",
drv_bss_info_changed, NULL);
}
diff --git a/tools/lib/traceevent/plugin_sched_switch.c b/tools/lib/traceevent/plugin_sched_switch.c
index 834c9e378ff8..957389a0ff7a 100644
--- a/tools/lib/traceevent/plugin_sched_switch.c
+++ b/tools/lib/traceevent/plugin_sched_switch.c
@@ -62,7 +62,7 @@ static void write_and_save_comm(struct tep_format_field *field,
comm = &s->buffer[len];
/* Help out the comm to ids. This will handle dups */
- tep_register_comm(field->event->pevent, comm, pid);
+ tep_register_comm(field->event->tep, comm, pid);
}
static int sched_wakeup_handler(struct trace_seq *s,
@@ -135,27 +135,27 @@ static int sched_switch_handler(struct trace_seq *s,
return 0;
}
-int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
+int TEP_PLUGIN_LOADER(struct tep_handle *tep)
{
- tep_register_event_handler(pevent, -1, "sched", "sched_switch",
+ tep_register_event_handler(tep, -1, "sched", "sched_switch",
sched_switch_handler, NULL);
- tep_register_event_handler(pevent, -1, "sched", "sched_wakeup",
+ tep_register_event_handler(tep, -1, "sched", "sched_wakeup",
sched_wakeup_handler, NULL);
- tep_register_event_handler(pevent, -1, "sched", "sched_wakeup_new",
+ tep_register_event_handler(tep, -1, "sched", "sched_wakeup_new",
sched_wakeup_handler, NULL);
return 0;
}
-void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent)
+void TEP_PLUGIN_UNLOADER(struct tep_handle *tep)
{
- tep_unregister_event_handler(pevent, -1, "sched", "sched_switch",
+ tep_unregister_event_handler(tep, -1, "sched", "sched_switch",
sched_switch_handler, NULL);
- tep_unregister_event_handler(pevent, -1, "sched", "sched_wakeup",
+ tep_unregister_event_handler(tep, -1, "sched", "sched_wakeup",
sched_wakeup_handler, NULL);
- tep_unregister_event_handler(pevent, -1, "sched", "sched_wakeup_new",
+ tep_unregister_event_handler(tep, -1, "sched", "sched_wakeup_new",
sched_wakeup_handler, NULL);
}
diff --git a/tools/lib/traceevent/plugin_scsi.c b/tools/lib/traceevent/plugin_scsi.c
index 4eba25cc1431..5d0387a4b65a 100644
--- a/tools/lib/traceevent/plugin_scsi.c
+++ b/tools/lib/traceevent/plugin_scsi.c
@@ -414,9 +414,9 @@ unsigned long long process_scsi_trace_parse_cdb(struct trace_seq *s,
return 0;
}
-int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
+int TEP_PLUGIN_LOADER(struct tep_handle *tep)
{
- tep_register_print_function(pevent,
+ tep_register_print_function(tep,
process_scsi_trace_parse_cdb,
TEP_FUNC_ARG_STRING,
"scsi_trace_parse_cdb",
@@ -427,8 +427,8 @@ int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
return 0;
}
-void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent)
+void TEP_PLUGIN_UNLOADER(struct tep_handle *tep)
{
- tep_unregister_print_function(pevent, process_scsi_trace_parse_cdb,
+ tep_unregister_print_function(tep, process_scsi_trace_parse_cdb,
"scsi_trace_parse_cdb");
}
diff --git a/tools/lib/traceevent/plugin_xen.c b/tools/lib/traceevent/plugin_xen.c
index bc0496e4c296..993b208d0323 100644
--- a/tools/lib/traceevent/plugin_xen.c
+++ b/tools/lib/traceevent/plugin_xen.c
@@ -120,9 +120,9 @@ unsigned long long process_xen_hypercall_name(struct trace_seq *s,
return 0;
}
-int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
+int TEP_PLUGIN_LOADER(struct tep_handle *tep)
{
- tep_register_print_function(pevent,
+ tep_register_print_function(tep,
process_xen_hypercall_name,
TEP_FUNC_ARG_STRING,
"xen_hypercall_name",
@@ -131,8 +131,8 @@ int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
return 0;
}
-void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent)
+void TEP_PLUGIN_UNLOADER(struct tep_handle *tep)
{
- tep_unregister_print_function(pevent, process_xen_hypercall_name,
+ tep_unregister_print_function(tep, process_xen_hypercall_name,
"xen_hypercall_name");
}
diff --git a/tools/memory-model/Documentation/explanation.txt b/tools/memory-model/Documentation/explanation.txt
index 35bff92cc773..68caa9a976d0 100644
--- a/tools/memory-model/Documentation/explanation.txt
+++ b/tools/memory-model/Documentation/explanation.txt
@@ -27,7 +27,7 @@ Explanation of the Linux-Kernel Memory Consistency Model
19. AND THEN THERE WAS ALPHA
20. THE HAPPENS-BEFORE RELATION: hb
21. THE PROPAGATES-BEFORE RELATION: pb
- 22. RCU RELATIONS: rcu-link, gp, rscs, rcu-fence, and rb
+ 22. RCU RELATIONS: rcu-link, rcu-gp, rcu-rscsi, rcu-fence, and rb
23. LOCKING
24. ODDS AND ENDS
@@ -1430,8 +1430,8 @@ they execute means that it cannot have cycles. This requirement is
the content of the LKMM's "propagation" axiom.
-RCU RELATIONS: rcu-link, gp, rscs, rcu-fence, and rb
-----------------------------------------------------
+RCU RELATIONS: rcu-link, rcu-gp, rcu-rscsi, rcu-fence, and rb
+-------------------------------------------------------------
RCU (Read-Copy-Update) is a powerful synchronization mechanism. It
rests on two concepts: grace periods and read-side critical sections.
@@ -1446,17 +1446,19 @@ As far as memory models are concerned, RCU's main feature is its
Grace-Period Guarantee, which states that a critical section can never
span a full grace period. In more detail, the Guarantee says:
- If a critical section starts before a grace period then it
- must end before the grace period does. In addition, every
- store that propagates to the critical section's CPU before the
- end of the critical section must propagate to every CPU before
- the end of the grace period.
+ For any critical section C and any grace period G, at least
+ one of the following statements must hold:
- If a critical section ends after a grace period ends then it
- must start after the grace period does. In addition, every
- store that propagates to the grace period's CPU before the
- start of the grace period must propagate to every CPU before
- the start of the critical section.
+(1) C ends before G does, and in addition, every store that
+ propagates to C's CPU before the end of C must propagate to
+ every CPU before G ends.
+
+(2) G starts before C does, and in addition, every store that
+ propagates to G's CPU before the start of G must propagate
+ to every CPU before C starts.
+
+In particular, it is not possible for a critical section to both start
+before and end after a grace period.
Here is a simple example of RCU in action:
@@ -1483,10 +1485,11 @@ The Grace Period Guarantee tells us that when this code runs, it will
never end with r1 = 1 and r2 = 0. The reasoning is as follows. r1 = 1
means that P0's store to x propagated to P1 before P1 called
synchronize_rcu(), so P0's critical section must have started before
-P1's grace period. On the other hand, r2 = 0 means that P0's store to
-y, which occurs before the end of the critical section, did not
-propagate to P1 before the end of the grace period, violating the
-Guarantee.
+P1's grace period, contrary to part (2) of the Guarantee. On the
+other hand, r2 = 0 means that P0's store to y, which occurs before the
+end of the critical section, did not propagate to P1 before the end of
+the grace period, contrary to part (1). Together the results violate
+the Guarantee.
In the kernel's implementations of RCU, the requirements for stores
to propagate to every CPU are fulfilled by placing strong fences at
@@ -1504,11 +1507,11 @@ before" or "ends after" a grace period? Some aspects of the meaning
are pretty obvious, as in the example above, but the details aren't
entirely clear. The LKMM formalizes this notion by means of the
rcu-link relation. rcu-link encompasses a very general notion of
-"before": Among other things, X ->rcu-link Z includes cases where X
-happens-before or is equal to some event Y which is equal to or comes
-before Z in the coherence order. When Y = Z this says that X ->rfe Z
-implies X ->rcu-link Z. In addition, when Y = X it says that X ->fr Z
-and X ->co Z each imply X ->rcu-link Z.
+"before": If E and F are RCU fence events (i.e., rcu_read_lock(),
+rcu_read_unlock(), or synchronize_rcu()) then among other things,
+E ->rcu-link F includes cases where E is po-before some memory-access
+event X, F is po-after some memory-access event Y, and we have any of
+X ->rfe Y, X ->co Y, or X ->fr Y.
The formal definition of the rcu-link relation is more than a little
obscure, and we won't give it here. It is closely related to the pb
@@ -1516,171 +1519,173 @@ relation, and the details don't matter unless you want to comb through
a somewhat lengthy formal proof. Pretty much all you need to know
about rcu-link is the information in the preceding paragraph.
-The LKMM also defines the gp and rscs relations. They bring grace
-periods and read-side critical sections into the picture, in the
+The LKMM also defines the rcu-gp and rcu-rscsi relations. They bring
+grace periods and read-side critical sections into the picture, in the
following way:
- E ->gp F means there is a synchronize_rcu() fence event S such
- that E ->po S and either S ->po F or S = F. In simple terms,
- there is a grace period po-between E and F.
+ E ->rcu-gp F means that E and F are in fact the same event,
+ and that event is a synchronize_rcu() fence (i.e., a grace
+ period).
- E ->rscs F means there is a critical section delimited by an
- rcu_read_lock() fence L and an rcu_read_unlock() fence U, such
- that E ->po U and either L ->po F or L = F. You can think of
- this as saying that E and F are in the same critical section
- (in fact, it also allows E to be po-before the start of the
- critical section and F to be po-after the end).
+ E ->rcu-rscsi F means that E and F are the rcu_read_unlock()
+ and rcu_read_lock() fence events delimiting some read-side
+ critical section. (The 'i' at the end of the name emphasizes
+ that this relation is "inverted": It links the end of the
+ critical section to the start.)
If we think of the rcu-link relation as standing for an extended
-"before", then X ->gp Y ->rcu-link Z says that X executes before a
-grace period which ends before Z executes. (In fact it covers more
-than this, because it also includes cases where X executes before a
-grace period and some store propagates to Z's CPU before Z executes
-but doesn't propagate to some other CPU until after the grace period
-ends.) Similarly, X ->rscs Y ->rcu-link Z says that X is part of (or
-before the start of) a critical section which starts before Z
-executes.
-
-The LKMM goes on to define the rcu-fence relation as a sequence of gp
-and rscs links separated by rcu-link links, in which the number of gp
-links is >= the number of rscs links. For example:
+"before", then X ->rcu-gp Y ->rcu-link Z roughly says that X is a
+grace period which ends before Z begins. (In fact it covers more than
+this, because it also includes cases where some store propagates to
+Z's CPU before Z begins but doesn't propagate to some other CPU until
+after X ends.) Similarly, X ->rcu-rscsi Y ->rcu-link Z says that X is
+the end of a critical section which starts before Z begins.
+
+The LKMM goes on to define the rcu-fence relation as a sequence of
+rcu-gp and rcu-rscsi links separated by rcu-link links, in which the
+number of rcu-gp links is >= the number of rcu-rscsi links. For
+example:
- X ->gp Y ->rcu-link Z ->rscs T ->rcu-link U ->gp V
+ X ->rcu-gp Y ->rcu-link Z ->rcu-rscsi T ->rcu-link U ->rcu-gp V
would imply that X ->rcu-fence V, because this sequence contains two
-gp links and only one rscs link. (It also implies that X ->rcu-fence T
-and Z ->rcu-fence V.) On the other hand:
+rcu-gp links and one rcu-rscsi link. (It also implies that
+X ->rcu-fence T and Z ->rcu-fence V.) On the other hand:
- X ->rscs Y ->rcu-link Z ->rscs T ->rcu-link U ->gp V
+ X ->rcu-rscsi Y ->rcu-link Z ->rcu-rscsi T ->rcu-link U ->rcu-gp V
does not imply X ->rcu-fence V, because the sequence contains only
-one gp link but two rscs links.
+one rcu-gp link but two rcu-rscsi links.
The rcu-fence relation is important because the Grace Period Guarantee
means that rcu-fence acts kind of like a strong fence. In particular,
-if W is a write and we have W ->rcu-fence Z, the Guarantee says that W
-will propagate to every CPU before Z executes.
+E ->rcu-fence F implies not only that E begins before F ends, but also
+that any write po-before E will propagate to every CPU before any
+instruction po-after F can execute. (However, it does not imply that
+E must execute before F; in fact, each synchronize_rcu() fence event
+is linked to itself by rcu-fence as a degenerate case.)
To prove this in full generality requires some intellectual effort.
We'll consider just a very simple case:
- W ->gp X ->rcu-link Y ->rscs Z.
+ G ->rcu-gp W ->rcu-link Z ->rcu-rscsi F.
-This formula means that there is a grace period G and a critical
-section C such that:
+This formula means that G and W are the same event (a grace period),
+and there are events X, Y and a read-side critical section C such that:
- 1. W is po-before G;
+ 1. G = W is po-before or equal to X;
- 2. X is equal to or po-after G;
+ 2. X comes "before" Y in some sense (including rfe, co and fr);
- 3. X comes "before" Y in some sense;
+ 2. Y is po-before Z;
- 4. Y is po-before the end of C;
+ 4. Z is the rcu_read_unlock() event marking the end of C;
- 5. Z is equal to or po-after the start of C.
+ 5. F is the rcu_read_lock() event marking the start of C.
-From 2 - 4 we deduce that the grace period G ends before the critical
-section C. Then the second part of the Grace Period Guarantee says
-not only that G starts before C does, but also that W (which executes
-on G's CPU before G starts) must propagate to every CPU before C
-starts. In particular, W propagates to every CPU before Z executes
-(or finishes executing, in the case where Z is equal to the
-rcu_read_lock() fence event which starts C.) This sort of reasoning
-can be expanded to handle all the situations covered by rcu-fence.
+From 1 - 4 we deduce that the grace period G ends before the critical
+section C. Then part (2) of the Grace Period Guarantee says not only
+that G starts before C does, but also that any write which executes on
+G's CPU before G starts must propagate to every CPU before C starts.
+In particular, the write propagates to every CPU before F finishes
+executing and hence before any instruction po-after F can execute.
+This sort of reasoning can be extended to handle all the situations
+covered by rcu-fence.
Finally, the LKMM defines the RCU-before (rb) relation in terms of
rcu-fence. This is done in essentially the same way as the pb
relation was defined in terms of strong-fence. We will omit the
-details; the end result is that E ->rb F implies E must execute before
-F, just as E ->pb F does (and for much the same reasons).
+details; the end result is that E ->rb F implies E must execute
+before F, just as E ->pb F does (and for much the same reasons).
Putting this all together, the LKMM expresses the Grace Period
Guarantee by requiring that the rb relation does not contain a cycle.
-Equivalently, this "rcu" axiom requires that there are no events E and
-F with E ->rcu-link F ->rcu-fence E. Or to put it a third way, the
-axiom requires that there are no cycles consisting of gp and rscs
-alternating with rcu-link, where the number of gp links is >= the
-number of rscs links.
+Equivalently, this "rcu" axiom requires that there are no events E
+and F with E ->rcu-link F ->rcu-fence E. Or to put it a third way,
+the axiom requires that there are no cycles consisting of rcu-gp and
+rcu-rscsi alternating with rcu-link, where the number of rcu-gp links
+is >= the number of rcu-rscsi links.
Justifying the axiom isn't easy, but it is in fact a valid
formalization of the Grace Period Guarantee. We won't attempt to go
through the detailed argument, but the following analysis gives a
-taste of what is involved. Suppose we have a violation of the first
-part of the Guarantee: A critical section starts before a grace
-period, and some store propagates to the critical section's CPU before
-the end of the critical section but doesn't propagate to some other
-CPU until after the end of the grace period.
+taste of what is involved. Suppose both parts of the Guarantee are
+violated: A critical section starts before a grace period, and some
+store propagates to the critical section's CPU before the end of the
+critical section but doesn't propagate to some other CPU until after
+the end of the grace period.
Putting symbols to these ideas, let L and U be the rcu_read_lock() and
rcu_read_unlock() fence events delimiting the critical section in
question, and let S be the synchronize_rcu() fence event for the grace
period. Saying that the critical section starts before S means there
-are events E and F where E is po-after L (which marks the start of the
-critical section), E is "before" F in the sense of the rcu-link
-relation, and F is po-before the grace period S:
+are events Q and R where Q is po-after L (which marks the start of the
+critical section), Q is "before" R in the sense used by the rcu-link
+relation, and R is po-before the grace period S. Thus we have:
- L ->po E ->rcu-link F ->po S.
+ L ->rcu-link S.
-Let W be the store mentioned above, let Z come before the end of the
+Let W be the store mentioned above, let Y come before the end of the
critical section and witness that W propagates to the critical
-section's CPU by reading from W, and let Y on some arbitrary CPU be a
-witness that W has not propagated to that CPU, where Y happens after
+section's CPU by reading from W, and let Z on some arbitrary CPU be a
+witness that W has not propagated to that CPU, where Z happens after
some event X which is po-after S. Symbolically, this amounts to:
- S ->po X ->hb* Y ->fr W ->rf Z ->po U.
+ S ->po X ->hb* Z ->fr W ->rf Y ->po U.
-The fr link from Y to W indicates that W has not propagated to Y's CPU
-at the time that Y executes. From this, it can be shown (see the
-discussion of the rcu-link relation earlier) that X and Z are related
-by rcu-link, yielding:
+The fr link from Z to W indicates that W has not propagated to Z's CPU
+at the time that Z executes. From this, it can be shown (see the
+discussion of the rcu-link relation earlier) that S and U are related
+by rcu-link:
- S ->po X ->rcu-link Z ->po U.
+ S ->rcu-link U.
-The formulas say that S is po-between F and X, hence F ->gp X. They
-also say that Z comes before the end of the critical section and E
-comes after its start, hence Z ->rscs E. From all this we obtain:
+Since S is a grace period we have S ->rcu-gp S, and since L and U are
+the start and end of the critical section C we have U ->rcu-rscsi L.
+From this we obtain:
- F ->gp X ->rcu-link Z ->rscs E ->rcu-link F,
+ S ->rcu-gp S ->rcu-link U ->rcu-rscsi L ->rcu-link S,
a forbidden cycle. Thus the "rcu" axiom rules out this violation of
the Grace Period Guarantee.
For something a little more down-to-earth, let's see how the axiom
works out in practice. Consider the RCU code example from above, this
-time with statement labels added to the memory access instructions:
+time with statement labels added:
int x, y;
P0()
{
- rcu_read_lock();
- W: WRITE_ONCE(x, 1);
- X: WRITE_ONCE(y, 1);
- rcu_read_unlock();
+ L: rcu_read_lock();
+ X: WRITE_ONCE(x, 1);
+ Y: WRITE_ONCE(y, 1);
+ U: rcu_read_unlock();
}
P1()
{
int r1, r2;
- Y: r1 = READ_ONCE(x);
- synchronize_rcu();
- Z: r2 = READ_ONCE(y);
+ Z: r1 = READ_ONCE(x);
+ S: synchronize_rcu();
+ W: r2 = READ_ONCE(y);
}
-If r2 = 0 at the end then P0's store at X overwrites the value that
-P1's load at Z reads from, so we have Z ->fre X and thus Z ->rcu-link X.
-In addition, there is a synchronize_rcu() between Y and Z, so therefore
-we have Y ->gp Z.
+If r2 = 0 at the end then P0's store at Y overwrites the value that
+P1's load at W reads from, so we have W ->fre Y. Since S ->po W and
+also Y ->po U, we get S ->rcu-link U. In addition, S ->rcu-gp S
+because S is a grace period.
-If r1 = 1 at the end then P1's load at Y reads from P0's store at W,
-so we have W ->rcu-link Y. In addition, W and X are in the same critical
-section, so therefore we have X ->rscs W.
+If r1 = 1 at the end then P1's load at Z reads from P0's store at X,
+so we have X ->rfe Z. Together with L ->po X and Z ->po S, this
+yields L ->rcu-link S. And since L and U are the start and end of a
+critical section, we have U ->rcu-rscsi L.
-Then X ->rscs W ->rcu-link Y ->gp Z ->rcu-link X is a forbidden cycle,
-violating the "rcu" axiom. Hence the outcome is not allowed by the
-LKMM, as we would expect.
+Then U ->rcu-rscsi L ->rcu-link S ->rcu-gp S ->rcu-link U is a
+forbidden cycle, violating the "rcu" axiom. Hence the outcome is not
+allowed by the LKMM, as we would expect.
For contrast, let's see what can happen in a more complicated example:
@@ -1690,51 +1695,52 @@ For contrast, let's see what can happen in a more complicated example:
{
int r0;
- rcu_read_lock();
- W: r0 = READ_ONCE(x);
- X: WRITE_ONCE(y, 1);
- rcu_read_unlock();
+ L0: rcu_read_lock();
+ r0 = READ_ONCE(x);
+ WRITE_ONCE(y, 1);
+ U0: rcu_read_unlock();
}
P1()
{
int r1;
- Y: r1 = READ_ONCE(y);
- synchronize_rcu();
- Z: WRITE_ONCE(z, 1);
+ r1 = READ_ONCE(y);
+ S1: synchronize_rcu();
+ WRITE_ONCE(z, 1);
}
P2()
{
int r2;
- rcu_read_lock();
- U: r2 = READ_ONCE(z);
- V: WRITE_ONCE(x, 1);
- rcu_read_unlock();
+ L2: rcu_read_lock();
+ r2 = READ_ONCE(z);
+ WRITE_ONCE(x, 1);
+ U2: rcu_read_unlock();
}
If r0 = r1 = r2 = 1 at the end, then similar reasoning to before shows
-that W ->rscs X ->rcu-link Y ->gp Z ->rcu-link U ->rscs V ->rcu-link W.
-However this cycle is not forbidden, because the sequence of relations
-contains fewer instances of gp (one) than of rscs (two). Consequently
-the outcome is allowed by the LKMM. The following instruction timing
-diagram shows how it might actually occur:
+that U0 ->rcu-rscsi L0 ->rcu-link S1 ->rcu-gp S1 ->rcu-link U2 ->rcu-rscsi
+L2 ->rcu-link U0. However this cycle is not forbidden, because the
+sequence of relations contains fewer instances of rcu-gp (one) than of
+rcu-rscsi (two). Consequently the outcome is allowed by the LKMM.
+The following instruction timing diagram shows how it might actually
+occur:
P0 P1 P2
-------------------- -------------------- --------------------
rcu_read_lock()
-X: WRITE_ONCE(y, 1)
- Y: r1 = READ_ONCE(y)
+WRITE_ONCE(y, 1)
+ r1 = READ_ONCE(y)
synchronize_rcu() starts
. rcu_read_lock()
- . V: WRITE_ONCE(x, 1)
-W: r0 = READ_ONCE(x) .
+ . WRITE_ONCE(x, 1)
+r0 = READ_ONCE(x) .
rcu_read_unlock() .
synchronize_rcu() ends
- Z: WRITE_ONCE(z, 1)
- U: r2 = READ_ONCE(z)
+ WRITE_ONCE(z, 1)
+ r2 = READ_ONCE(z)
rcu_read_unlock()
This requires P0 and P2 to execute their loads and stores out of
@@ -1744,6 +1750,15 @@ section in P0 both starts before P1's grace period does and ends
before it does, and the critical section in P2 both starts after P1's
grace period does and ends after it does.
+Addendum: The LKMM now supports SRCU (Sleepable Read-Copy-Update) in
+addition to normal RCU. The ideas involved are much the same as
+above, with new relations srcu-gp and srcu-rscsi added to represent
+SRCU grace periods and read-side critical sections. There is a
+restriction on the srcu-gp and srcu-rscsi links that can appear in an
+rcu-fence sequence (the srcu-rscsi links must be paired with srcu-gp
+links having the same SRCU domain with proper nesting); the details
+are relatively unimportant.
+
LOCKING
-------
diff --git a/tools/memory-model/README b/tools/memory-model/README
index 0f2c366518c6..2b87f3971548 100644
--- a/tools/memory-model/README
+++ b/tools/memory-model/README
@@ -20,13 +20,17 @@ that litmus test to be exercised within the Linux kernel.
REQUIREMENTS
============
-Version 7.49 of the "herd7" and "klitmus7" tools must be downloaded
-separately:
+Version 7.52 or higher of the "herd7" and "klitmus7" tools must be
+downloaded separately:
https://github.com/herd/herdtools7
See "herdtools7/INSTALL.md" for installation instructions.
+Note that although these tools usually provide backwards compatibility,
+this is not absolutely guaranteed. Therefore, if a later version does
+not work, please try using the exact version called out above.
+
==================
BASIC USAGE: HERD7
@@ -221,8 +225,29 @@ The Linux-kernel memory model has the following limitations:
additional call_rcu() process to the site of the
emulated rcu-barrier().
- e. Sleepable RCU (SRCU) is not modeled. It can be
- emulated, but perhaps not simply.
+ e. Although sleepable RCU (SRCU) is now modeled, there
+ are some subtle differences between its semantics and
+ those in the Linux kernel. For example, the kernel
+ might interpret the following sequence as two partially
+ overlapping SRCU read-side critical sections:
+
+ 1 r1 = srcu_read_lock(&my_srcu);
+ 2 do_something_1();
+ 3 r2 = srcu_read_lock(&my_srcu);
+ 4 do_something_2();
+ 5 srcu_read_unlock(&my_srcu, r1);
+ 6 do_something_3();
+ 7 srcu_read_unlock(&my_srcu, r2);
+
+ In contrast, LKMM will interpret this as a nested pair of
+ SRCU read-side critical sections, with the outer critical
+ section spanning lines 1-7 and the inner critical section
+ spanning lines 3-5.
+
+ This difference would be more of a concern had anyone
+ identified a reasonable use case for partially overlapping
+ SRCU read-side critical sections. For more information,
+ please see: https://paulmck.livejournal.com/40593.html
f. Reader-writer locking is not modeled. It can be
emulated in litmus tests using atomic read-modify-write
diff --git a/tools/memory-model/linux-kernel.bell b/tools/memory-model/linux-kernel.bell
index 796513362c05..def9131d3d8e 100644
--- a/tools/memory-model/linux-kernel.bell
+++ b/tools/memory-model/linux-kernel.bell
@@ -33,8 +33,14 @@ enum Barriers = 'wmb (*smp_wmb*) ||
'after-unlock-lock (*smp_mb__after_unlock_lock*)
instructions F[Barriers]
+(* SRCU *)
+enum SRCU = 'srcu-lock || 'srcu-unlock || 'sync-srcu
+instructions SRCU[SRCU]
+(* All srcu events *)
+let Srcu = Srcu-lock | Srcu-unlock | Sync-srcu
+
(* Compute matching pairs of nested Rcu-lock and Rcu-unlock *)
-let matched = let rec
+let rcu-rscs = let rec
unmatched-locks = Rcu-lock \ domain(matched)
and unmatched-unlocks = Rcu-unlock \ range(matched)
and unmatched = unmatched-locks | unmatched-unlocks
@@ -46,8 +52,27 @@ let matched = let rec
in matched
(* Validate nesting *)
-flag ~empty Rcu-lock \ domain(matched) as unbalanced-rcu-locking
-flag ~empty Rcu-unlock \ range(matched) as unbalanced-rcu-locking
+flag ~empty Rcu-lock \ domain(rcu-rscs) as unbalanced-rcu-locking
+flag ~empty Rcu-unlock \ range(rcu-rscs) as unbalanced-rcu-locking
+
+(* Compute matching pairs of nested Srcu-lock and Srcu-unlock *)
+let srcu-rscs = let rec
+ unmatched-locks = Srcu-lock \ domain(matched)
+ and unmatched-unlocks = Srcu-unlock \ range(matched)
+ and unmatched = unmatched-locks | unmatched-unlocks
+ and unmatched-po = ([unmatched] ; po ; [unmatched]) & loc
+ and unmatched-locks-to-unlocks =
+ ([unmatched-locks] ; po ; [unmatched-unlocks]) & loc
+ and matched = matched | (unmatched-locks-to-unlocks \
+ (unmatched-po ; unmatched-po))
+ in matched
+
+(* Validate nesting *)
+flag ~empty Srcu-lock \ domain(srcu-rscs) as unbalanced-srcu-locking
+flag ~empty Srcu-unlock \ range(srcu-rscs) as unbalanced-srcu-locking
+
+(* Check for use of synchronize_srcu() inside an RCU critical section *)
+flag ~empty rcu-rscs & (po ; [Sync-srcu] ; po) as invalid-sleep
-(* Outermost level of nesting only *)
-let crit = matched \ (po^-1 ; matched ; po^-1)
+(* Validate SRCU dynamic match *)
+flag ~empty different-values(srcu-rscs) as srcu-bad-nesting
diff --git a/tools/memory-model/linux-kernel.cat b/tools/memory-model/linux-kernel.cat
index 8f23c74a96fd..8dcb37835b61 100644
--- a/tools/memory-model/linux-kernel.cat
+++ b/tools/memory-model/linux-kernel.cat
@@ -33,7 +33,7 @@ let mb = ([M] ; fencerel(Mb) ; [M]) |
([M] ; po? ; [LKW] ; fencerel(After-spinlock) ; [M]) |
([M] ; po ; [UL] ; (co | po) ; [LKW] ;
fencerel(After-unlock-lock) ; [M])
-let gp = po ; [Sync-rcu] ; po?
+let gp = po ; [Sync-rcu | Sync-srcu] ; po?
let strong-fence = mb | gp
@@ -91,32 +91,47 @@ acyclic pb as propagation
(*******)
(*
- * Effect of read-side critical section proceeds from the rcu_read_lock()
- * onward on the one hand and from the rcu_read_unlock() backwards on the
- * other hand.
+ * Effects of read-side critical sections proceed from the rcu_read_unlock()
+ * or srcu_read_unlock() backwards on the one hand, and from the
+ * rcu_read_lock() or srcu_read_lock() forwards on the other hand.
+ *
+ * In the definition of rcu-fence below, the po term at the left-hand side
+ * of each disjunct and the po? term at the right-hand end have been factored
+ * out. They have been moved into the definitions of rcu-link and rb.
+ * This was necessary in order to apply the "& loc" tests correctly.
*)
-let rscs = po ; crit^-1 ; po?
+let rcu-gp = [Sync-rcu] (* Compare with gp *)
+let srcu-gp = [Sync-srcu]
+let rcu-rscsi = rcu-rscs^-1
+let srcu-rscsi = srcu-rscs^-1
(*
* The synchronize_rcu() strong fence is special in that it can order not
* one but two non-rf relations, but only in conjunction with an RCU
* read-side critical section.
*)
-let rcu-link = hb* ; pb* ; prop
+let rcu-link = po? ; hb* ; pb* ; prop ; po
(*
* Any sequence containing at least as many grace periods as RCU read-side
* critical sections (joined by rcu-link) acts as a generalized strong fence.
+ * Likewise for SRCU grace periods and read-side critical sections, provided
+ * the synchronize_srcu() and srcu_read_[un]lock() calls refer to the same
+ * struct srcu_struct location.
*)
-let rec rcu-fence = gp |
- (gp ; rcu-link ; rscs) |
- (rscs ; rcu-link ; gp) |
- (gp ; rcu-link ; rcu-fence ; rcu-link ; rscs) |
- (rscs ; rcu-link ; rcu-fence ; rcu-link ; gp) |
+let rec rcu-fence = rcu-gp | srcu-gp |
+ (rcu-gp ; rcu-link ; rcu-rscsi) |
+ ((srcu-gp ; rcu-link ; srcu-rscsi) & loc) |
+ (rcu-rscsi ; rcu-link ; rcu-gp) |
+ ((srcu-rscsi ; rcu-link ; srcu-gp) & loc) |
+ (rcu-gp ; rcu-link ; rcu-fence ; rcu-link ; rcu-rscsi) |
+ ((srcu-gp ; rcu-link ; rcu-fence ; rcu-link ; srcu-rscsi) & loc) |
+ (rcu-rscsi ; rcu-link ; rcu-fence ; rcu-link ; rcu-gp) |
+ ((srcu-rscsi ; rcu-link ; rcu-fence ; rcu-link ; srcu-gp) & loc) |
(rcu-fence ; rcu-link ; rcu-fence)
(* rb orders instructions just as pb does *)
-let rb = prop ; rcu-fence ; hb* ; pb*
+let rb = prop ; po ; rcu-fence ; po? ; hb* ; pb*
irreflexive rb as rcu
diff --git a/tools/memory-model/linux-kernel.def b/tools/memory-model/linux-kernel.def
index b27911cc087d..551eeaa389d4 100644
--- a/tools/memory-model/linux-kernel.def
+++ b/tools/memory-model/linux-kernel.def
@@ -47,6 +47,12 @@ rcu_read_unlock() { __fence{rcu-unlock}; }
synchronize_rcu() { __fence{sync-rcu}; }
synchronize_rcu_expedited() { __fence{sync-rcu}; }
+// SRCU
+srcu_read_lock(X) __srcu{srcu-lock}(X)
+srcu_read_unlock(X,Y) { __srcu{srcu-unlock}(X,Y); }
+synchronize_srcu(X) { __srcu{sync-srcu}(X); }
+synchronize_srcu_expedited(X) { __srcu{sync-srcu}(X); }
+
// Atomic
atomic_read(X) READ_ONCE(*X)
atomic_set(X,V) { WRITE_ONCE(*X,V); }
diff --git a/tools/memory-model/lock.cat b/tools/memory-model/lock.cat
index 305ded17e741..a059d1a6d8a2 100644
--- a/tools/memory-model/lock.cat
+++ b/tools/memory-model/lock.cat
@@ -6,9 +6,6 @@
(*
* Generate coherence orders and handle lock operations
- *
- * Warning: spin_is_locked() crashes herd7 versions strictly before 7.48.
- * spin_is_locked() is functional from herd7 version 7.49.
*)
include "cross.cat"
diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile
index c9d038f91af6..53f8be0f4a1f 100644
--- a/tools/objtool/Makefile
+++ b/tools/objtool/Makefile
@@ -25,14 +25,17 @@ LIBSUBCMD = $(LIBSUBCMD_OUTPUT)libsubcmd.a
OBJTOOL := $(OUTPUT)objtool
OBJTOOL_IN := $(OBJTOOL)-in.o
+LIBELF_FLAGS := $(shell pkg-config libelf --cflags 2>/dev/null)
+LIBELF_LIBS := $(shell pkg-config libelf --libs 2>/dev/null || echo -lelf)
+
all: $(OBJTOOL)
INCLUDES := -I$(srctree)/tools/include \
-I$(srctree)/tools/arch/$(HOSTARCH)/include/uapi \
-I$(srctree)/tools/objtool/arch/$(ARCH)/include
WARNINGS := $(EXTRA_WARNINGS) -Wno-switch-default -Wno-switch-enum -Wno-packed
-CFLAGS += -Werror $(WARNINGS) $(KBUILD_HOSTCFLAGS) -g $(INCLUDES)
-LDFLAGS += -lelf $(LIBSUBCMD) $(KBUILD_HOSTLDFLAGS)
+CFLAGS += -Werror $(WARNINGS) $(KBUILD_HOSTCFLAGS) -g $(INCLUDES) $(LIBELF_FLAGS)
+LDFLAGS += $(LIBELF_LIBS) $(LIBSUBCMD) $(KBUILD_HOSTLDFLAGS)
# Allow old libelf to be used:
elfshdr := $(shell echo '$(pound)include <libelf.h>' | $(CC) $(CFLAGS) -x c -E - | grep elf_getshdr)
diff --git a/tools/objtool/arch.h b/tools/objtool/arch.h
index b0d7dc3d71b5..7a111a77b7aa 100644
--- a/tools/objtool/arch.h
+++ b/tools/objtool/arch.h
@@ -33,7 +33,11 @@
#define INSN_STACK 8
#define INSN_BUG 9
#define INSN_NOP 10
-#define INSN_OTHER 11
+#define INSN_STAC 11
+#define INSN_CLAC 12
+#define INSN_STD 13
+#define INSN_CLD 14
+#define INSN_OTHER 15
#define INSN_LAST INSN_OTHER
enum op_dest_type {
@@ -41,6 +45,7 @@ enum op_dest_type {
OP_DEST_REG_INDIRECT,
OP_DEST_MEM,
OP_DEST_PUSH,
+ OP_DEST_PUSHF,
OP_DEST_LEAVE,
};
@@ -55,6 +60,7 @@ enum op_src_type {
OP_SRC_REG_INDIRECT,
OP_SRC_CONST,
OP_SRC_POP,
+ OP_SRC_POPF,
OP_SRC_ADD,
OP_SRC_AND,
};
diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c
index 540a209b78ab..472e991f6512 100644
--- a/tools/objtool/arch/x86/decode.c
+++ b/tools/objtool/arch/x86/decode.c
@@ -357,19 +357,26 @@ int arch_decode_instruction(struct elf *elf, struct section *sec,
/* pushf */
*type = INSN_STACK;
op->src.type = OP_SRC_CONST;
- op->dest.type = OP_DEST_PUSH;
+ op->dest.type = OP_DEST_PUSHF;
break;
case 0x9d:
/* popf */
*type = INSN_STACK;
- op->src.type = OP_SRC_POP;
+ op->src.type = OP_SRC_POPF;
op->dest.type = OP_DEST_MEM;
break;
case 0x0f:
- if (op2 >= 0x80 && op2 <= 0x8f) {
+ if (op2 == 0x01) {
+
+ if (modrm == 0xca)
+ *type = INSN_CLAC;
+ else if (modrm == 0xcb)
+ *type = INSN_STAC;
+
+ } else if (op2 >= 0x80 && op2 <= 0x8f) {
*type = INSN_JUMP_CONDITIONAL;
@@ -444,6 +451,14 @@ int arch_decode_instruction(struct elf *elf, struct section *sec,
*type = INSN_CALL;
break;
+ case 0xfc:
+ *type = INSN_CLD;
+ break;
+
+ case 0xfd:
+ *type = INSN_STD;
+ break;
+
case 0xff:
if (modrm_reg == 2 || modrm_reg == 3)
diff --git a/tools/objtool/builtin-check.c b/tools/objtool/builtin-check.c
index 694abc628e9b..f3b378126011 100644
--- a/tools/objtool/builtin-check.c
+++ b/tools/objtool/builtin-check.c
@@ -29,7 +29,7 @@
#include "builtin.h"
#include "check.h"
-bool no_fp, no_unreachable, retpoline, module;
+bool no_fp, no_unreachable, retpoline, module, backtrace, uaccess;
static const char * const check_usage[] = {
"objtool check [<options>] file.o",
@@ -41,6 +41,8 @@ const struct option check_options[] = {
OPT_BOOLEAN('u', "no-unreachable", &no_unreachable, "Skip 'unreachable instruction' warnings"),
OPT_BOOLEAN('r', "retpoline", &retpoline, "Validate retpoline assumptions"),
OPT_BOOLEAN('m', "module", &module, "Indicates the object will be part of a kernel module"),
+ OPT_BOOLEAN('b', "backtrace", &backtrace, "unwind on error"),
+ OPT_BOOLEAN('a', "uaccess", &uaccess, "enable uaccess checking"),
OPT_END(),
};
diff --git a/tools/objtool/builtin.h b/tools/objtool/builtin.h
index 28ff40e19a14..69762f9c5602 100644
--- a/tools/objtool/builtin.h
+++ b/tools/objtool/builtin.h
@@ -20,7 +20,7 @@
#include <subcmd/parse-options.h>
extern const struct option check_options[];
-extern bool no_fp, no_unreachable, retpoline, module;
+extern bool no_fp, no_unreachable, retpoline, module, backtrace, uaccess;
extern int cmd_check(int argc, const char **argv);
extern int cmd_orc(int argc, const char **argv);
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 0414a0d52262..ac743a1d53ab 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -31,6 +31,7 @@
struct alternative {
struct list_head list;
struct instruction *insn;
+ bool skip_orig;
};
const char *objname;
@@ -105,29 +106,6 @@ static struct instruction *next_insn_same_func(struct objtool_file *file,
insn = next_insn_same_sec(file, insn))
/*
- * Check if the function has been manually whitelisted with the
- * STACK_FRAME_NON_STANDARD macro, or if it should be automatically whitelisted
- * due to its use of a context switching instruction.
- */
-static bool ignore_func(struct objtool_file *file, struct symbol *func)
-{
- struct rela *rela;
-
- /* check for STACK_FRAME_NON_STANDARD */
- if (file->whitelist && file->whitelist->rela)
- list_for_each_entry(rela, &file->whitelist->rela->rela_list, list) {
- if (rela->sym->type == STT_SECTION &&
- rela->sym->sec == func->sec &&
- rela->addend == func->offset)
- return true;
- if (rela->sym->type == STT_FUNC && rela->sym == func)
- return true;
- }
-
- return false;
-}
-
-/*
* This checks to see if the given function is a "noreturn" function.
*
* For global functions which are outside the scope of this object file, we
@@ -165,6 +143,7 @@ static int __dead_end_function(struct objtool_file *file, struct symbol *func,
"fortify_panic",
"usercopy_abort",
"machine_real_restart",
+ "rewind_stack_do_exit",
};
if (func->bind == STB_WEAK)
@@ -436,18 +415,107 @@ static void add_ignores(struct objtool_file *file)
struct instruction *insn;
struct section *sec;
struct symbol *func;
+ struct rela *rela;
- for_each_sec(file, sec) {
- list_for_each_entry(func, &sec->symbol_list, list) {
- if (func->type != STT_FUNC)
- continue;
+ sec = find_section_by_name(file->elf, ".rela.discard.func_stack_frame_non_standard");
+ if (!sec)
+ return;
+
+ list_for_each_entry(rela, &sec->rela_list, list) {
+ switch (rela->sym->type) {
+ case STT_FUNC:
+ func = rela->sym;
+ break;
- if (!ignore_func(file, func))
+ case STT_SECTION:
+ func = find_symbol_by_offset(rela->sym->sec, rela->addend);
+ if (!func || func->type != STT_FUNC)
continue;
+ break;
- func_for_each_insn_all(file, func, insn)
- insn->ignore = true;
+ default:
+ WARN("unexpected relocation symbol type in %s: %d", sec->name, rela->sym->type);
+ continue;
}
+
+ func_for_each_insn_all(file, func, insn)
+ insn->ignore = true;
+ }
+}
+
+/*
+ * This is a whitelist of functions that is allowed to be called with AC set.
+ * The list is meant to be minimal and only contains compiler instrumentation
+ * ABI and a few functions used to implement *_{to,from}_user() functions.
+ *
+ * These functions must not directly change AC, but may PUSHF/POPF.
+ */
+static const char *uaccess_safe_builtin[] = {
+ /* KASAN */
+ "kasan_report",
+ "check_memory_region",
+ /* KASAN out-of-line */
+ "__asan_loadN_noabort",
+ "__asan_load1_noabort",
+ "__asan_load2_noabort",
+ "__asan_load4_noabort",
+ "__asan_load8_noabort",
+ "__asan_load16_noabort",
+ "__asan_storeN_noabort",
+ "__asan_store1_noabort",
+ "__asan_store2_noabort",
+ "__asan_store4_noabort",
+ "__asan_store8_noabort",
+ "__asan_store16_noabort",
+ /* KASAN in-line */
+ "__asan_report_load_n_noabort",
+ "__asan_report_load1_noabort",
+ "__asan_report_load2_noabort",
+ "__asan_report_load4_noabort",
+ "__asan_report_load8_noabort",
+ "__asan_report_load16_noabort",
+ "__asan_report_store_n_noabort",
+ "__asan_report_store1_noabort",
+ "__asan_report_store2_noabort",
+ "__asan_report_store4_noabort",
+ "__asan_report_store8_noabort",
+ "__asan_report_store16_noabort",
+ /* KCOV */
+ "write_comp_data",
+ "__sanitizer_cov_trace_pc",
+ "__sanitizer_cov_trace_const_cmp1",
+ "__sanitizer_cov_trace_const_cmp2",
+ "__sanitizer_cov_trace_const_cmp4",
+ "__sanitizer_cov_trace_const_cmp8",
+ "__sanitizer_cov_trace_cmp1",
+ "__sanitizer_cov_trace_cmp2",
+ "__sanitizer_cov_trace_cmp4",
+ "__sanitizer_cov_trace_cmp8",
+ /* UBSAN */
+ "ubsan_type_mismatch_common",
+ "__ubsan_handle_type_mismatch",
+ "__ubsan_handle_type_mismatch_v1",
+ /* misc */
+ "csum_partial_copy_generic",
+ "__memcpy_mcsafe",
+ "ftrace_likely_update", /* CONFIG_TRACE_BRANCH_PROFILING */
+ NULL
+};
+
+static void add_uaccess_safe(struct objtool_file *file)
+{
+ struct symbol *func;
+ const char **name;
+
+ if (!uaccess)
+ return;
+
+ for (name = uaccess_safe_builtin; *name; name++) {
+ func = find_symbol_by_name(file->elf, *name);
+ if (!func)
+ continue;
+
+ func->alias->uaccess_safe = true;
}
}
@@ -457,13 +525,13 @@ static void add_ignores(struct objtool_file *file)
* But it at least allows objtool to understand the control flow *around* the
* retpoline.
*/
-static int add_nospec_ignores(struct objtool_file *file)
+static int add_ignore_alternatives(struct objtool_file *file)
{
struct section *sec;
struct rela *rela;
struct instruction *insn;
- sec = find_section_by_name(file->elf, ".rela.discard.nospec");
+ sec = find_section_by_name(file->elf, ".rela.discard.ignore_alts");
if (!sec)
return 0;
@@ -475,7 +543,7 @@ static int add_nospec_ignores(struct objtool_file *file)
insn = find_insn(file, rela->sym->sec, rela->addend);
if (!insn) {
- WARN("bad .discard.nospec entry");
+ WARN("bad .discard.ignore_alts entry");
return -1;
}
@@ -524,7 +592,8 @@ static int add_jump_destinations(struct objtool_file *file)
continue;
} else {
/* sibling call */
- insn->jump_dest = 0;
+ insn->call_dest = rela->sym;
+ insn->jump_dest = NULL;
continue;
}
@@ -546,25 +615,38 @@ static int add_jump_destinations(struct objtool_file *file)
}
/*
- * For GCC 8+, create parent/child links for any cold
- * subfunctions. This is _mostly_ redundant with a similar
- * initialization in read_symbols().
- *
- * If a function has aliases, we want the *first* such function
- * in the symbol table to be the subfunction's parent. In that
- * case we overwrite the initialization done in read_symbols().
- *
- * However this code can't completely replace the
- * read_symbols() code because this doesn't detect the case
- * where the parent function's only reference to a subfunction
- * is through a switch table.
+ * Cross-function jump.
*/
if (insn->func && insn->jump_dest->func &&
- insn->func != insn->jump_dest->func &&
- !strstr(insn->func->name, ".cold.") &&
- strstr(insn->jump_dest->func->name, ".cold.")) {
- insn->func->cfunc = insn->jump_dest->func;
- insn->jump_dest->func->pfunc = insn->func;
+ insn->func != insn->jump_dest->func) {
+
+ /*
+ * For GCC 8+, create parent/child links for any cold
+ * subfunctions. This is _mostly_ redundant with a
+ * similar initialization in read_symbols().
+ *
+ * If a function has aliases, we want the *first* such
+ * function in the symbol table to be the subfunction's
+ * parent. In that case we overwrite the
+ * initialization done in read_symbols().
+ *
+ * However this code can't completely replace the
+ * read_symbols() code because this doesn't detect the
+ * case where the parent function's only reference to a
+ * subfunction is through a switch table.
+ */
+ if (!strstr(insn->func->name, ".cold.") &&
+ strstr(insn->jump_dest->func->name, ".cold.")) {
+ insn->func->cfunc = insn->jump_dest->func;
+ insn->jump_dest->func->pfunc = insn->func;
+
+ } else if (insn->jump_dest->func->pfunc != insn->func->pfunc &&
+ insn->jump_dest->offset == insn->jump_dest->func->offset) {
+
+ /* sibling class */
+ insn->call_dest = insn->jump_dest->func;
+ insn->jump_dest = NULL;
+ }
}
}
@@ -633,9 +715,6 @@ static int add_call_destinations(struct objtool_file *file)
* conditionally jumps to the _end_ of the entry. We have to modify these
* jumps' destinations to point back to .text rather than the end of the
* entry in .altinstr_replacement.
- *
- * 4. It has been requested that we don't validate the !POPCNT feature path
- * which is a "very very small percentage of machines".
*/
static int handle_group_alt(struct objtool_file *file,
struct special_alt *special_alt,
@@ -651,9 +730,6 @@ static int handle_group_alt(struct objtool_file *file,
if (insn->offset >= special_alt->orig_off + special_alt->orig_len)
break;
- if (special_alt->skip_orig)
- insn->type = INSN_NOP;
-
insn->alt_group = true;
last_orig_insn = insn;
}
@@ -695,6 +771,7 @@ static int handle_group_alt(struct objtool_file *file,
last_new_insn = insn;
insn->ignore = orig_insn->ignore_alts;
+ insn->func = orig_insn->func;
if (insn->type != INSN_JUMP_CONDITIONAL &&
insn->type != INSN_JUMP_UNCONDITIONAL)
@@ -817,6 +894,8 @@ static int add_special_section_alts(struct objtool_file *file)
}
alt->insn = new_insn;
+ alt->skip_orig = special_alt->skip_orig;
+ orig_insn->ignore_alts |= special_alt->skip_alt;
list_add_tail(&alt->list, &orig_insn->alts);
list_del(&special_alt->list);
@@ -1238,8 +1317,9 @@ static int decode_sections(struct objtool_file *file)
return ret;
add_ignores(file);
+ add_uaccess_safe(file);
- ret = add_nospec_ignores(file);
+ ret = add_ignore_alternatives(file);
if (ret)
return ret;
@@ -1319,11 +1399,11 @@ static int update_insn_state_regs(struct instruction *insn, struct insn_state *s
return 0;
/* push */
- if (op->dest.type == OP_DEST_PUSH)
+ if (op->dest.type == OP_DEST_PUSH || op->dest.type == OP_DEST_PUSHF)
cfa->offset += 8;
/* pop */
- if (op->src.type == OP_SRC_POP)
+ if (op->src.type == OP_SRC_POP || op->src.type == OP_SRC_POPF)
cfa->offset -= 8;
/* add immediate to sp */
@@ -1580,6 +1660,7 @@ static int update_insn_state(struct instruction *insn, struct insn_state *state)
break;
case OP_SRC_POP:
+ case OP_SRC_POPF:
if (!state->drap && op->dest.type == OP_DEST_REG &&
op->dest.reg == cfa->base) {
@@ -1644,6 +1725,7 @@ static int update_insn_state(struct instruction *insn, struct insn_state *state)
break;
case OP_DEST_PUSH:
+ case OP_DEST_PUSHF:
state->stack_size += 8;
if (cfa->base == CFI_SP)
cfa->offset += 8;
@@ -1734,7 +1816,7 @@ static int update_insn_state(struct instruction *insn, struct insn_state *state)
break;
case OP_DEST_MEM:
- if (op->src.type != OP_SRC_POP) {
+ if (op->src.type != OP_SRC_POP && op->src.type != OP_SRC_POPF) {
WARN_FUNC("unknown stack-related memory operation",
insn->sec, insn->offset);
return -1;
@@ -1798,6 +1880,50 @@ static bool insn_state_match(struct instruction *insn, struct insn_state *state)
return false;
}
+static inline bool func_uaccess_safe(struct symbol *func)
+{
+ if (func)
+ return func->alias->uaccess_safe;
+
+ return false;
+}
+
+static inline const char *insn_dest_name(struct instruction *insn)
+{
+ if (insn->call_dest)
+ return insn->call_dest->name;
+
+ return "{dynamic}";
+}
+
+static int validate_call(struct instruction *insn, struct insn_state *state)
+{
+ if (state->uaccess && !func_uaccess_safe(insn->call_dest)) {
+ WARN_FUNC("call to %s() with UACCESS enabled",
+ insn->sec, insn->offset, insn_dest_name(insn));
+ return 1;
+ }
+
+ if (state->df) {
+ WARN_FUNC("call to %s() with DF set",
+ insn->sec, insn->offset, insn_dest_name(insn));
+ return 1;
+ }
+
+ return 0;
+}
+
+static int validate_sibling_call(struct instruction *insn, struct insn_state *state)
+{
+ if (has_modified_stack_frame(state)) {
+ WARN_FUNC("sibling call from callable instruction with modified stack frame",
+ insn->sec, insn->offset);
+ return 1;
+ }
+
+ return validate_call(insn, state);
+}
+
/*
* Follow the branch starting at the given instruction, and recursively follow
* any other branches (jumps). Meanwhile, track the frame pointer state at
@@ -1843,7 +1969,9 @@ static int validate_branch(struct objtool_file *file, struct instruction *first,
if (!insn->hint && !insn_state_match(insn, &state))
return 1;
- return 0;
+ /* If we were here with AC=0, but now have AC=1, go again */
+ if (insn->state.uaccess || !state.uaccess)
+ return 0;
}
if (insn->hint) {
@@ -1892,16 +2020,42 @@ static int validate_branch(struct objtool_file *file, struct instruction *first,
insn->visited = true;
if (!insn->ignore_alts) {
+ bool skip_orig = false;
+
list_for_each_entry(alt, &insn->alts, list) {
+ if (alt->skip_orig)
+ skip_orig = true;
+
ret = validate_branch(file, alt->insn, state);
- if (ret)
- return 1;
+ if (ret) {
+ if (backtrace)
+ BT_FUNC("(alt)", insn);
+ return ret;
+ }
}
+
+ if (skip_orig)
+ return 0;
}
switch (insn->type) {
case INSN_RETURN:
+ if (state.uaccess && !func_uaccess_safe(func)) {
+ WARN_FUNC("return with UACCESS enabled", sec, insn->offset);
+ return 1;
+ }
+
+ if (!state.uaccess && func_uaccess_safe(func)) {
+ WARN_FUNC("return with UACCESS disabled from a UACCESS-safe function", sec, insn->offset);
+ return 1;
+ }
+
+ if (state.df) {
+ WARN_FUNC("return with DF set", sec, insn->offset);
+ return 1;
+ }
+
if (func && has_modified_stack_frame(&state)) {
WARN_FUNC("return with modified stack frame",
sec, insn->offset);
@@ -1917,17 +2071,22 @@ static int validate_branch(struct objtool_file *file, struct instruction *first,
return 0;
case INSN_CALL:
- if (is_fentry_call(insn))
- break;
+ case INSN_CALL_DYNAMIC:
+ ret = validate_call(insn, &state);
+ if (ret)
+ return ret;
- ret = dead_end_function(file, insn->call_dest);
- if (ret == 1)
- return 0;
- if (ret == -1)
- return 1;
+ if (insn->type == INSN_CALL) {
+ if (is_fentry_call(insn))
+ break;
+
+ ret = dead_end_function(file, insn->call_dest);
+ if (ret == 1)
+ return 0;
+ if (ret == -1)
+ return 1;
+ }
- /* fallthrough */
- case INSN_CALL_DYNAMIC:
if (!no_fp && func && !has_valid_stack_frame(&state)) {
WARN_FUNC("call without frame pointer save/setup",
sec, insn->offset);
@@ -1937,18 +2096,21 @@ static int validate_branch(struct objtool_file *file, struct instruction *first,
case INSN_JUMP_CONDITIONAL:
case INSN_JUMP_UNCONDITIONAL:
- if (insn->jump_dest &&
- (!func || !insn->jump_dest->func ||
- insn->jump_dest->func->pfunc == func)) {
- ret = validate_branch(file, insn->jump_dest,
- state);
+ if (func && !insn->jump_dest) {
+ ret = validate_sibling_call(insn, &state);
if (ret)
- return 1;
+ return ret;
- } else if (func && has_modified_stack_frame(&state)) {
- WARN_FUNC("sibling call from callable instruction with modified stack frame",
- sec, insn->offset);
- return 1;
+ } else if (insn->jump_dest &&
+ (!func || !insn->jump_dest->func ||
+ insn->jump_dest->func->pfunc == func)) {
+ ret = validate_branch(file, insn->jump_dest,
+ state);
+ if (ret) {
+ if (backtrace)
+ BT_FUNC("(branch)", insn);
+ return ret;
+ }
}
if (insn->type == INSN_JUMP_UNCONDITIONAL)
@@ -1957,11 +2119,10 @@ static int validate_branch(struct objtool_file *file, struct instruction *first,
break;
case INSN_JUMP_DYNAMIC:
- if (func && list_empty(&insn->alts) &&
- has_modified_stack_frame(&state)) {
- WARN_FUNC("sibling call from callable instruction with modified stack frame",
- sec, insn->offset);
- return 1;
+ if (func && list_empty(&insn->alts)) {
+ ret = validate_sibling_call(insn, &state);
+ if (ret)
+ return ret;
}
return 0;
@@ -1978,6 +2139,63 @@ static int validate_branch(struct objtool_file *file, struct instruction *first,
if (update_insn_state(insn, &state))
return 1;
+ if (insn->stack_op.dest.type == OP_DEST_PUSHF) {
+ if (!state.uaccess_stack) {
+ state.uaccess_stack = 1;
+ } else if (state.uaccess_stack >> 31) {
+ WARN_FUNC("PUSHF stack exhausted", sec, insn->offset);
+ return 1;
+ }
+ state.uaccess_stack <<= 1;
+ state.uaccess_stack |= state.uaccess;
+ }
+
+ if (insn->stack_op.src.type == OP_SRC_POPF) {
+ if (state.uaccess_stack) {
+ state.uaccess = state.uaccess_stack & 1;
+ state.uaccess_stack >>= 1;
+ if (state.uaccess_stack == 1)
+ state.uaccess_stack = 0;
+ }
+ }
+
+ break;
+
+ case INSN_STAC:
+ if (state.uaccess) {
+ WARN_FUNC("recursive UACCESS enable", sec, insn->offset);
+ return 1;
+ }
+
+ state.uaccess = true;
+ break;
+
+ case INSN_CLAC:
+ if (!state.uaccess && insn->func) {
+ WARN_FUNC("redundant UACCESS disable", sec, insn->offset);
+ return 1;
+ }
+
+ if (func_uaccess_safe(func) && !state.uaccess_stack) {
+ WARN_FUNC("UACCESS-safe disables UACCESS", sec, insn->offset);
+ return 1;
+ }
+
+ state.uaccess = false;
+ break;
+
+ case INSN_STD:
+ if (state.df)
+ WARN_FUNC("recursive STD", sec, insn->offset);
+
+ state.df = true;
+ break;
+
+ case INSN_CLD:
+ if (!state.df && insn->func)
+ WARN_FUNC("redundant CLD", sec, insn->offset);
+
+ state.df = false;
break;
default:
@@ -2014,6 +2232,8 @@ static int validate_unwind_hints(struct objtool_file *file)
for_each_insn(file, insn) {
if (insn->hint && !insn->visited) {
ret = validate_branch(file, insn, state);
+ if (ret && backtrace)
+ BT_FUNC("<=== (hint)", insn);
warnings += ret;
}
}
@@ -2141,7 +2361,11 @@ static int validate_functions(struct objtool_file *file)
if (!insn || insn->ignore)
continue;
+ state.uaccess = func->alias->uaccess_safe;
+
ret = validate_branch(file, insn, state);
+ if (ret && backtrace)
+ BT_FUNC("<=== (func)", insn);
warnings += ret;
}
}
@@ -2184,9 +2408,10 @@ static void cleanup(struct objtool_file *file)
elf_close(file->elf);
}
+static struct objtool_file file;
+
int check(const char *_objname, bool orc)
{
- struct objtool_file file;
int ret, warnings = 0;
objname = _objname;
@@ -2197,7 +2422,6 @@ int check(const char *_objname, bool orc)
INIT_LIST_HEAD(&file.insn_list);
hash_init(file.insn_hash);
- file.whitelist = find_section_by_name(file.elf, ".discard.func_stack_frame_non_standard");
file.c_file = find_section_by_name(file.elf, ".comment");
file.ignore_unreachables = no_unreachable;
file.hints = false;
diff --git a/tools/objtool/check.h b/tools/objtool/check.h
index e6e8a655b556..71e54f97dbcd 100644
--- a/tools/objtool/check.h
+++ b/tools/objtool/check.h
@@ -31,7 +31,8 @@ struct insn_state {
int stack_size;
unsigned char type;
bool bp_scratch;
- bool drap, end;
+ bool drap, end, uaccess, df;
+ unsigned int uaccess_stack;
int drap_reg, drap_offset;
struct cfi_reg vals[CFI_NUM_REGS];
};
@@ -60,7 +61,6 @@ struct objtool_file {
struct elf *elf;
struct list_head insn_list;
DECLARE_HASHTABLE(insn_hash, 16);
- struct section *whitelist;
bool ignore_unreachables, c_file, hints, rodata;
};
diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c
index b8f3cca8e58b..dd198d53387d 100644
--- a/tools/objtool/elf.c
+++ b/tools/objtool/elf.c
@@ -219,7 +219,7 @@ static int read_sections(struct elf *elf)
static int read_symbols(struct elf *elf)
{
struct section *symtab, *sec;
- struct symbol *sym, *pfunc;
+ struct symbol *sym, *pfunc, *alias;
struct list_head *entry, *tmp;
int symbols_nr, i;
char *coldstr;
@@ -239,6 +239,7 @@ static int read_symbols(struct elf *elf)
return -1;
}
memset(sym, 0, sizeof(*sym));
+ alias = sym;
sym->idx = i;
@@ -288,11 +289,17 @@ static int read_symbols(struct elf *elf)
break;
}
- if (sym->offset == s->offset && sym->len >= s->len) {
- entry = tmp;
- break;
+ if (sym->offset == s->offset) {
+ if (sym->len == s->len && alias == sym)
+ alias = s;
+
+ if (sym->len >= s->len) {
+ entry = tmp;
+ break;
+ }
}
}
+ sym->alias = alias;
list_add(&sym->list, entry);
hash_add(sym->sec->symbol_hash, &sym->hash, sym->idx);
}
diff --git a/tools/objtool/elf.h b/tools/objtool/elf.h
index bc97ed86b9cd..2cc2ed49322d 100644
--- a/tools/objtool/elf.h
+++ b/tools/objtool/elf.h
@@ -61,7 +61,8 @@ struct symbol {
unsigned char bind, type;
unsigned long offset;
unsigned int len;
- struct symbol *pfunc, *cfunc;
+ struct symbol *pfunc, *cfunc, *alias;
+ bool uaccess_safe;
};
struct rela {
diff --git a/tools/objtool/special.c b/tools/objtool/special.c
index 50af4e1274b3..4e50563d87c6 100644
--- a/tools/objtool/special.c
+++ b/tools/objtool/special.c
@@ -23,6 +23,7 @@
#include <stdlib.h>
#include <string.h>
+#include "builtin.h"
#include "special.h"
#include "warn.h"
@@ -42,6 +43,7 @@
#define ALT_NEW_LEN_OFFSET 11
#define X86_FEATURE_POPCNT (4*32+23)
+#define X86_FEATURE_SMAP (9*32+20)
struct special_entry {
const char *sec;
@@ -110,6 +112,22 @@ static int get_alt_entry(struct elf *elf, struct special_entry *entry,
*/
if (feature == X86_FEATURE_POPCNT)
alt->skip_orig = true;
+
+ /*
+ * If UACCESS validation is enabled; force that alternative;
+ * otherwise force it the other way.
+ *
+ * What we want to avoid is having both the original and the
+ * alternative code flow at the same time, in that case we can
+ * find paths that see the STAC but take the NOP instead of
+ * CLAC and the other way around.
+ */
+ if (feature == X86_FEATURE_SMAP) {
+ if (uaccess)
+ alt->skip_orig = true;
+ else
+ alt->skip_alt = true;
+ }
}
orig_rela = find_rela_by_dest(sec, offset + entry->orig);
diff --git a/tools/objtool/special.h b/tools/objtool/special.h
index fad1d092f679..d5c062e718ef 100644
--- a/tools/objtool/special.h
+++ b/tools/objtool/special.h
@@ -26,6 +26,7 @@ struct special_alt {
bool group;
bool skip_orig;
+ bool skip_alt;
bool jump_or_nop;
struct section *orig_sec;
diff --git a/tools/objtool/warn.h b/tools/objtool/warn.h
index afd9f7a05f6d..f4fbb972b611 100644
--- a/tools/objtool/warn.h
+++ b/tools/objtool/warn.h
@@ -64,6 +64,14 @@ static inline char *offstr(struct section *sec, unsigned long offset)
free(_str); \
})
+#define BT_FUNC(format, insn, ...) \
+({ \
+ struct instruction *_insn = (insn); \
+ char *_str = offstr(_insn->sec, _insn->offset); \
+ WARN(" %s: " format, _str, ##__VA_ARGS__); \
+ free(_str); \
+})
+
#define WARN_ELF(format, ...) \
WARN(format ": %s", ##__VA_ARGS__, elf_errmsg(-1))
diff --git a/tools/perf/Documentation/Build.txt b/tools/perf/Documentation/Build.txt
index f6fc6507ba55..3766886c4bca 100644
--- a/tools/perf/Documentation/Build.txt
+++ b/tools/perf/Documentation/Build.txt
@@ -47,3 +47,27 @@ Those objects are then used in final linking:
NOTE this description is omitting other libraries involved, only
focusing on build framework outcomes
+
+3) Build with ASan or UBSan
+==========================
+ $ cd tools/perf
+ $ make DESTDIR=/usr
+ $ make DESTDIR=/usr install
+
+AddressSanitizer (or ASan) is a GCC feature that detects memory corruption bugs
+such as buffer overflows and memory leaks.
+
+ $ cd tools/perf
+ $ make DEBUG=1 EXTRA_CFLAGS='-fno-omit-frame-pointer -fsanitize=address'
+ $ ASAN_OPTIONS=log_path=asan.log ./perf record -a
+
+ASan outputs all detected issues into a log file named 'asan.log.<pid>'.
+
+UndefinedBehaviorSanitizer (or UBSan) is a fast undefined behavior detector
+supported by GCC. UBSan detects undefined behaviors of programs at runtime.
+
+ $ cd tools/perf
+ $ make DEBUG=1 EXTRA_CFLAGS='-fno-omit-frame-pointer -fsanitize=undefined'
+ $ UBSAN_OPTIONS=print_stacktrace=1 ./perf record -a
+
+If UBSan detects any problem at runtime, it outputs a “runtime error:” message.
diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt
index 86f3dcc15f83..462b3cde0675 100644
--- a/tools/perf/Documentation/perf-config.txt
+++ b/tools/perf/Documentation/perf-config.txt
@@ -114,7 +114,7 @@ Given a $HOME/.perfconfig like this:
[report]
# Defaults
- sort-order = comm,dso,symbol
+ sort_order = comm,dso,symbol
percent-limit = 0
queue-size = 0
children = true
@@ -584,6 +584,20 @@ llvm.*::
llvm.opts::
Options passed to llc.
+samples.*::
+
+ samples.context::
+ Define how many ns worth of time to show
+ around samples in perf report sample context browser.
+
+scripts.*::
+
+ Any option defines a script that is added to the scripts menu
+ in the interactive perf browser and whose output is displayed.
+ The name of the option is the name, the value is a script command line.
+ The script gets the same options passed as a full perf script,
+ in particular -i perfdata file, --cpu, --tid
+
SEE ALSO
--------
linkperf:perf[1]
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 8f0c2be34848..58986f4cc190 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -459,6 +459,25 @@ Set affinity mask of trace reading thread according to the policy defined by 'mo
node - thread affinity mask is set to NUMA node cpu mask of the processed mmap buffer
cpu - thread affinity mask is set to cpu of the processed mmap buffer
+--mmap-flush=number::
+
+Specify minimal number of bytes that is extracted from mmap data pages and
+processed for output. One can specify the number using B/K/M/G suffixes.
+
+The maximal allowed value is a quarter of the size of mmaped data pages.
+
+The default option value is 1 byte which means that every time that the output
+writing thread finds some new data in the mmaped buffer the data is extracted,
+possibly compressed (-z) and written to the output, perf.data or pipe.
+
+Larger data chunks are compressed more effectively in comparison to smaller
+chunks so extraction of larger chunks from the mmap data pages is preferable
+from the perspective of output size reduction.
+
+Also at some cases executing less output write syscalls with bigger data size
+can take less time than executing more output write syscalls with smaller data
+size thus lowering runtime profiling overhead.
+
--all-kernel::
Configure all used events to run in kernel space.
@@ -495,6 +514,10 @@ overhead. You can still switch them on with:
--switch-output --no-no-buildid --no-no-buildid-cache
+--switch-max-files=N::
+
+When rotating perf.data with --switch-output, only keep N files.
+
--dry-run::
Parse options then exit. --dry-run can be used to detect errors in cmdline
options.
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 1a27bfe05039..f441baa794ce 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -105,6 +105,8 @@ OPTIONS
guest machine
- sample: Number of sample
- period: Raw number of event count of sample
+ - time: Separate the samples by time stamp with the resolution specified by
+ --time-quantum (default 100ms). Specify with overhead and before it.
By default, comm, dso and symbol keys are used.
(i.e. --sort comm,dso,symbol)
@@ -459,6 +461,10 @@ include::itrace.txt[]
--socket-filter::
Only report the samples on the processor socket that match with this filter
+--samples=N::
+ Save N individual samples for each histogram entry to show context in perf
+ report tui browser.
+
--raw-trace::
When displaying traceevent output, do not use print fmt or plugins.
@@ -477,6 +483,9 @@ include::itrace.txt[]
Please note that not all mmaps are stored, options affecting which ones
are include 'perf record --data', for instance.
+--ns::
+ Show time stamps in nanoseconds.
+
--stats::
Display overall events statistics without any further processing.
(like the one at the end of the perf report -D command)
@@ -494,6 +503,10 @@ include::itrace.txt[]
The period/hits keywords set the base the percentage is computed
on - the samples period or the number of samples (hits).
+--time-quantum::
+ Configure time quantum for time sort key. Default 100ms.
+ Accepts s, us, ms, ns units.
+
include::callchain-overhead-calculation.txt[]
SEE ALSO
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 2e19fd7ffe35..9b0d04dd2a61 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -380,6 +380,9 @@ include::itrace.txt[]
Set the maximum number of program blocks to print with brstackasm for
each sample.
+--reltime::
+ Print time stamps relative to trace start.
+
--per-event-dump::
Create per event files with a "perf.data.EVENT.dump" name instead of
printing to stdout, useful, for instance, for generating flamegraphs.
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 4bc2085e5197..39c05f89104e 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -72,9 +72,8 @@ report::
--all-cpus::
system-wide collection from all CPUs (default if no target is specified)
--c::
---scale::
- scale/normalize counter values
+--no-scale::
+ Don't scale/normalize counter values
-d::
--detailed::
diff --git a/tools/perf/Documentation/tips.txt b/tools/perf/Documentation/tips.txt
index 849599f39c5e..869965d629ce 100644
--- a/tools/perf/Documentation/tips.txt
+++ b/tools/perf/Documentation/tips.txt
@@ -15,6 +15,7 @@ To see callchains in a more compact form: perf report -g folded
Show individual samples with: perf script
Limit to show entries above 5% only: perf report --percent-limit 5
Profiling branch (mis)predictions with: perf record -b / perf report
+To show assembler sample contexts use perf record -b / perf script -F +brstackinsn --xed
Treat branches as callchains: perf report --branch-history
To count events in every 1000 msec: perf stat -I 1000
Print event counts in CSV format with: perf stat -x,
@@ -34,3 +35,9 @@ Show current config key-value pairs: perf config --list
Show user configuration overrides: perf config --user --list
To add Node.js USDT(User-Level Statically Defined Tracing): perf buildid-cache --add `which node`
To report cacheline events from previous recording: perf c2c report
+To browse sample contexts use perf report --sample 10 and select in context menu
+To separate samples by time use perf report --sort time,overhead,sym
+To set sample time separation other than 100ms with --sort time use --time-quantum
+Add -I to perf report to sample register values visible in perf report context.
+To show IPC for sampling periods use perf record -e '{cycles,instructions}:S' and then browse context
+To show context switches in perf report sample context add --switch-events to perf record.
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 0f11d5891301..0c52a01dc759 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -152,6 +152,13 @@ endif
FEATURE_CHECK_CFLAGS-libbabeltrace := $(LIBBABELTRACE_CFLAGS)
FEATURE_CHECK_LDFLAGS-libbabeltrace := $(LIBBABELTRACE_LDFLAGS) -lbabeltrace-ctf
+ifdef LIBZSTD_DIR
+ LIBZSTD_CFLAGS := -I$(LIBZSTD_DIR)/lib
+ LIBZSTD_LDFLAGS := -L$(LIBZSTD_DIR)/lib
+endif
+FEATURE_CHECK_CFLAGS-libzstd := $(LIBZSTD_CFLAGS)
+FEATURE_CHECK_LDFLAGS-libzstd := $(LIBZSTD_LDFLAGS)
+
FEATURE_CHECK_CFLAGS-bpf = -I. -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(SRCARCH)/include/uapi -I$(srctree)/tools/include/uapi
# include ARCH specific config
-include $(src-perf)/arch/$(SRCARCH)/Makefile
@@ -227,6 +234,8 @@ FEATURE_CHECK_LDFLAGS-libpython-version := $(PYTHON_EMBED_LDOPTS)
FEATURE_CHECK_LDFLAGS-libaio = -lrt
+FEATURE_CHECK_LDFLAGS-disassembler-four-args = -lbfd -lopcodes -ldl
+
CFLAGS += -fno-omit-frame-pointer
CFLAGS += -ggdb3
CFLAGS += -funwind-tables
@@ -713,7 +722,7 @@ else
endif
ifeq ($(feature-libbfd), 1)
- EXTLIBS += -lbfd
+ EXTLIBS += -lbfd -lopcodes
else
# we are on a system that requires -liberty and (maybe) -lz
# to link against -lbfd; test each case individually here
@@ -724,12 +733,15 @@ else
$(call feature_check,libbfd-liberty-z)
ifeq ($(feature-libbfd-liberty), 1)
- EXTLIBS += -lbfd -liberty
+ EXTLIBS += -lbfd -lopcodes -liberty
+ FEATURE_CHECK_LDFLAGS-disassembler-four-args += -liberty -ldl
else
ifeq ($(feature-libbfd-liberty-z), 1)
- EXTLIBS += -lbfd -liberty -lz
+ EXTLIBS += -lbfd -lopcodes -liberty -lz
+ FEATURE_CHECK_LDFLAGS-disassembler-four-args += -liberty -lz -ldl
endif
endif
+ $(call feature_check,disassembler-four-args)
endif
ifdef NO_DEMANGLE
@@ -782,6 +794,19 @@ ifndef NO_LZMA
endif
endif
+ifndef NO_LIBZSTD
+ ifeq ($(feature-libzstd), 1)
+ CFLAGS += -DHAVE_ZSTD_SUPPORT
+ CFLAGS += $(LIBZSTD_CFLAGS)
+ LDFLAGS += $(LIBZSTD_LDFLAGS)
+ EXTLIBS += -lzstd
+ $(call detected,CONFIG_ZSTD)
+ else
+ msg := $(warning No libzstd found, disables trace compression, please install libzstd-dev[el] and/or set LIBZSTD_DIR);
+ NO_LIBZSTD := 1
+ endif
+endif
+
ifndef NO_BACKTRACE
ifeq ($(feature-backtrace), 1)
CFLAGS += -DHAVE_BACKTRACE_SUPPORT
@@ -808,6 +833,10 @@ ifdef HAVE_KVM_STAT_SUPPORT
CFLAGS += -DHAVE_KVM_STAT_SUPPORT
endif
+ifeq ($(feature-disassembler-four-args), 1)
+ CFLAGS += -DDISASM_FOUR_ARGS_SIGNATURE
+endif
+
ifeq (${IS_64_BIT}, 1)
ifndef NO_PERF_READ_VDSO32
$(call feature_check,compile-32)
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 01f7555fd933..c706548d5b10 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -108,6 +108,9 @@ include ../scripts/utilities.mak
# streaming for record mode. Currently Posix AIO trace streaming is
# supported only when linking with glibc.
#
+# Define NO_LIBZSTD if you do not want support of Zstandard based runtime
+# trace compression in record mode.
+#
# As per kernel Makefile, avoid funny character set dependencies
unexport LC_ALL
@@ -481,8 +484,8 @@ $(madvise_behavior_array): $(madvise_hdr_dir)/mman-common.h $(madvise_behavior_t
mmap_flags_array := $(beauty_outdir)/mmap_flags_array.c
mmap_flags_tbl := $(srctree)/tools/perf/trace/beauty/mmap_flags.sh
-$(mmap_flags_array): $(asm_generic_uapi_dir)/mman.h $(asm_generic_uapi_dir)/mman-common.h $(mmap_flags_tbl)
- $(Q)$(SHELL) '$(mmap_flags_tbl)' $(asm_generic_uapi_dir) $(arch_asm_uapi_dir) > $@
+$(mmap_flags_array): $(linux_uapi_dir)/mman.h $(asm_generic_uapi_dir)/mman.h $(asm_generic_uapi_dir)/mman-common.h $(mmap_flags_tbl)
+ $(Q)$(SHELL) '$(mmap_flags_tbl)' $(linux_uapi_dir) $(asm_generic_uapi_dir) $(arch_asm_uapi_dir) > $@
mount_flags_array := $(beauty_outdir)/mount_flags_array.c
mount_flags_tbl := $(srctree)/tools/perf/trace/beauty/mount_flags.sh
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index f0b1709a5ffb..92ee0b4378d4 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -343,6 +343,12 @@
332 common statx __x64_sys_statx
333 common io_pgetevents __x64_sys_io_pgetevents
334 common rseq __x64_sys_rseq
+# don't use numbers 387 through 423, add new calls after the last
+# 'common' entry
+424 common pidfd_send_signal __x64_sys_pidfd_send_signal
+425 common io_uring_setup __x64_sys_io_uring_setup
+426 common io_uring_enter __x64_sys_io_uring_enter
+427 common io_uring_register __x64_sys_io_uring_register
#
# x32-specific system call numbers start at 512 to avoid cache impact
@@ -361,7 +367,7 @@
520 x32 execve __x32_compat_sys_execve/ptregs
521 x32 ptrace __x32_compat_sys_ptrace
522 x32 rt_sigpending __x32_compat_sys_rt_sigpending
-523 x32 rt_sigtimedwait __x32_compat_sys_rt_sigtimedwait
+523 x32 rt_sigtimedwait __x32_compat_sys_rt_sigtimedwait_time64
524 x32 rt_sigqueueinfo __x32_compat_sys_rt_sigqueueinfo
525 x32 sigaltstack __x32_compat_sys_sigaltstack
526 x32 timer_create __x32_compat_sys_timer_create
@@ -375,7 +381,7 @@
534 x32 preadv __x32_compat_sys_preadv64
535 x32 pwritev __x32_compat_sys_pwritev64
536 x32 rt_tgsigqueueinfo __x32_compat_sys_rt_tgsigqueueinfo
-537 x32 recvmmsg __x32_compat_sys_recvmmsg
+537 x32 recvmmsg __x32_compat_sys_recvmmsg_time64
538 x32 sendmmsg __x32_compat_sys_sendmmsg
539 x32 process_vm_readv __x32_compat_sys_process_vm_readv
540 x32 process_vm_writev __x32_compat_sys_process_vm_writev
diff --git a/tools/perf/arch/x86/util/Build b/tools/perf/arch/x86/util/Build
index 7aab0be5fc5f..47f9c56e744f 100644
--- a/tools/perf/arch/x86/util/Build
+++ b/tools/perf/arch/x86/util/Build
@@ -14,5 +14,6 @@ perf-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind.o
perf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
perf-$(CONFIG_AUXTRACE) += auxtrace.o
+perf-$(CONFIG_AUXTRACE) += archinsn.o
perf-$(CONFIG_AUXTRACE) += intel-pt.o
perf-$(CONFIG_AUXTRACE) += intel-bts.o
diff --git a/tools/perf/arch/x86/util/archinsn.c b/tools/perf/arch/x86/util/archinsn.c
new file mode 100644
index 000000000000..4237bb2e7fa2
--- /dev/null
+++ b/tools/perf/arch/x86/util/archinsn.c
@@ -0,0 +1,26 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "perf.h"
+#include "archinsn.h"
+#include "util/intel-pt-decoder/insn.h"
+#include "machine.h"
+#include "thread.h"
+#include "symbol.h"
+
+void arch_fetch_insn(struct perf_sample *sample,
+ struct thread *thread,
+ struct machine *machine)
+{
+ struct insn insn;
+ int len;
+ bool is64bit = false;
+
+ if (!sample->ip)
+ return;
+ len = thread__memcpy(thread, machine, sample->insn, sample->ip, sizeof(sample->insn), &is64bit);
+ if (len <= 0)
+ return;
+ insn_init(&insn, sample->insn, len, is64bit);
+ insn_get_length(&insn);
+ if (insn_complete(&insn) && insn.length <= len)
+ sample->insn_len = insn.length;
+}
diff --git a/tools/perf/bench/epoll-ctl.c b/tools/perf/bench/epoll-ctl.c
index 0c0a6e824934..2af067859966 100644
--- a/tools/perf/bench/epoll-ctl.c
+++ b/tools/perf/bench/epoll-ctl.c
@@ -224,7 +224,7 @@ static int do_threads(struct worker *worker, struct cpu_map *cpu)
pthread_attr_t thread_attr, *attrp = NULL;
cpu_set_t cpuset;
unsigned int i, j;
- int ret;
+ int ret = 0;
if (!noaffinity)
pthread_attr_init(&thread_attr);
diff --git a/tools/perf/bench/epoll-wait.c b/tools/perf/bench/epoll-wait.c
index 5a11534e96a0..fe85448abd45 100644
--- a/tools/perf/bench/epoll-wait.c
+++ b/tools/perf/bench/epoll-wait.c
@@ -293,7 +293,7 @@ static int do_threads(struct worker *worker, struct cpu_map *cpu)
pthread_attr_t thread_attr, *attrp = NULL;
cpu_set_t cpuset;
unsigned int i, j;
- int ret, events = EPOLLIN;
+ int ret = 0, events = EPOLLIN;
if (oneshot)
events |= EPOLLONESHOT;
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index 98ad783efc69..a7784554a80d 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -39,6 +39,10 @@
#include <numa.h>
#include <numaif.h>
+#ifndef RUSAGE_THREAD
+# define RUSAGE_THREAD 1
+#endif
+
/*
* Regular printout to the terminal, supressed if -q is specified:
*/
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index fa520f4b8095..b80eee455111 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -1975,7 +1975,7 @@ int cmd_kmem(int argc, const char **argv)
goto out_delete;
}
- kmem_page_size = tep_get_page_size(evsel->tp_format->pevent);
+ kmem_page_size = tep_get_page_size(evsel->tp_format->tep);
symbol_conf.use_callchain = true;
}
diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c
index c9f98d00c0e9..e0312a1c4792 100644
--- a/tools/perf/builtin-list.c
+++ b/tools/perf/builtin-list.c
@@ -70,10 +70,11 @@ int cmd_list(int argc, const char **argv)
print_symbol_events(NULL, PERF_TYPE_HARDWARE,
event_symbols_hw, PERF_COUNT_HW_MAX, raw_dump);
else if (strcmp(argv[i], "sw") == 0 ||
- strcmp(argv[i], "software") == 0)
+ strcmp(argv[i], "software") == 0) {
print_symbol_events(NULL, PERF_TYPE_SOFTWARE,
event_symbols_sw, PERF_COUNT_SW_MAX, raw_dump);
- else if (strcmp(argv[i], "cache") == 0 ||
+ print_tool_events(NULL, raw_dump);
+ } else if (strcmp(argv[i], "cache") == 0 ||
strcmp(argv[i], "hwcache") == 0)
print_hwcache_events(NULL, raw_dump);
else if (strcmp(argv[i], "pmu") == 0)
@@ -113,13 +114,14 @@ int cmd_list(int argc, const char **argv)
event_symbols_hw, PERF_COUNT_HW_MAX, raw_dump);
print_symbol_events(s, PERF_TYPE_SOFTWARE,
event_symbols_sw, PERF_COUNT_SW_MAX, raw_dump);
+ print_tool_events(s, raw_dump);
print_hwcache_events(s, raw_dump);
print_pmu_events(s, raw_dump, !desc_flag,
long_desc_flag,
details_flag);
print_tracepoint_events(NULL, s, raw_dump);
print_sdt_events(NULL, s, raw_dump);
- metricgroup__print(true, true, NULL, raw_dump, details_flag);
+ metricgroup__print(true, true, s, raw_dump, details_flag);
free(s);
}
}
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index f3f7f3100336..c5e10552776a 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -62,6 +62,9 @@ struct switch_output {
unsigned long time;
const char *str;
bool set;
+ char **filenames;
+ int num_files;
+ int cur_file;
};
struct record {
@@ -334,6 +337,41 @@ static int record__aio_enabled(struct record *rec)
return rec->opts.nr_cblocks > 0;
}
+#define MMAP_FLUSH_DEFAULT 1
+static int record__mmap_flush_parse(const struct option *opt,
+ const char *str,
+ int unset)
+{
+ int flush_max;
+ struct record_opts *opts = (struct record_opts *)opt->value;
+ static struct parse_tag tags[] = {
+ { .tag = 'B', .mult = 1 },
+ { .tag = 'K', .mult = 1 << 10 },
+ { .tag = 'M', .mult = 1 << 20 },
+ { .tag = 'G', .mult = 1 << 30 },
+ { .tag = 0 },
+ };
+
+ if (unset)
+ return 0;
+
+ if (str) {
+ opts->mmap_flush = parse_tag_value(str, tags);
+ if (opts->mmap_flush == (int)-1)
+ opts->mmap_flush = strtol(str, NULL, 0);
+ }
+
+ if (!opts->mmap_flush)
+ opts->mmap_flush = MMAP_FLUSH_DEFAULT;
+
+ flush_max = perf_evlist__mmap_size(opts->mmap_pages);
+ flush_max /= 4;
+ if (opts->mmap_flush > flush_max)
+ opts->mmap_flush = flush_max;
+
+ return 0;
+}
+
static int process_synthesized_event(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample __maybe_unused,
@@ -392,7 +430,7 @@ static int record__process_auxtrace(struct perf_tool *tool,
size_t padding;
u8 pad[8] = {0};
- if (!perf_data__is_pipe(data)) {
+ if (!perf_data__is_pipe(data) && !perf_data__is_dir(data)) {
off_t file_offset;
int fd = perf_data__fd(data);
int err;
@@ -543,7 +581,8 @@ static int record__mmap_evlist(struct record *rec,
if (perf_evlist__mmap_ex(evlist, opts->mmap_pages,
opts->auxtrace_mmap_pages,
opts->auxtrace_snapshot_mode,
- opts->nr_cblocks, opts->affinity) < 0) {
+ opts->nr_cblocks, opts->affinity,
+ opts->mmap_flush) < 0) {
if (errno == EPERM) {
pr_err("Permission error mapping pages.\n"
"Consider increasing "
@@ -733,7 +772,7 @@ static void record__adjust_affinity(struct record *rec, struct perf_mmap *map)
}
static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evlist,
- bool overwrite)
+ bool overwrite, bool synch)
{
u64 bytes_written = rec->bytes_written;
int i;
@@ -756,12 +795,19 @@ static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evli
off = record__aio_get_pos(trace_fd);
for (i = 0; i < evlist->nr_mmaps; i++) {
+ u64 flush = 0;
struct perf_mmap *map = &maps[i];
if (map->base) {
record__adjust_affinity(rec, map);
+ if (synch) {
+ flush = map->flush;
+ map->flush = 1;
+ }
if (!record__aio_enabled(rec)) {
if (perf_mmap__push(map, rec, record__pushfn) != 0) {
+ if (synch)
+ map->flush = flush;
rc = -1;
goto out;
}
@@ -774,10 +820,14 @@ static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evli
idx = record__aio_sync(map, false);
if (perf_mmap__aio_push(map, rec, idx, record__aio_pushfn, &off) != 0) {
record__aio_set_pos(trace_fd, off);
+ if (synch)
+ map->flush = flush;
rc = -1;
goto out;
}
}
+ if (synch)
+ map->flush = flush;
}
if (map->auxtrace_mmap.base && !rec->opts.auxtrace_snapshot_mode &&
@@ -803,15 +853,15 @@ out:
return rc;
}
-static int record__mmap_read_all(struct record *rec)
+static int record__mmap_read_all(struct record *rec, bool synch)
{
int err;
- err = record__mmap_read_evlist(rec, rec->evlist, false);
+ err = record__mmap_read_evlist(rec, rec->evlist, false, synch);
if (err)
return err;
- return record__mmap_read_evlist(rec, rec->evlist, true);
+ return record__mmap_read_evlist(rec, rec->evlist, true, synch);
}
static void record__init_features(struct record *rec)
@@ -837,6 +887,8 @@ static void record__init_features(struct record *rec)
if (!(rec->opts.use_clockid && rec->opts.clockid_res_ns))
perf_header__clear_feat(&session->header, HEADER_CLOCKID);
+ perf_header__clear_feat(&session->header, HEADER_DIR_FORMAT);
+
perf_header__clear_feat(&session->header, HEADER_STAT);
}
@@ -890,6 +942,7 @@ record__switch_output(struct record *rec, bool at_exit)
{
struct perf_data *data = &rec->data;
int fd, err;
+ char *new_filename;
/* Same Size: "2015122520103046"*/
char timestamp[] = "InvalidTimestamp";
@@ -910,7 +963,7 @@ record__switch_output(struct record *rec, bool at_exit)
fd = perf_data__switch(data, timestamp,
rec->session->header.data_offset,
- at_exit);
+ at_exit, &new_filename);
if (fd >= 0 && !at_exit) {
rec->bytes_written = 0;
rec->session->header.data_size = 0;
@@ -920,6 +973,21 @@ record__switch_output(struct record *rec, bool at_exit)
fprintf(stderr, "[ perf record: Dump %s.%s ]\n",
data->path, timestamp);
+ if (rec->switch_output.num_files) {
+ int n = rec->switch_output.cur_file + 1;
+
+ if (n >= rec->switch_output.num_files)
+ n = 0;
+ rec->switch_output.cur_file = n;
+ if (rec->switch_output.filenames[n]) {
+ remove(rec->switch_output.filenames[n]);
+ free(rec->switch_output.filenames[n]);
+ }
+ rec->switch_output.filenames[n] = new_filename;
+ } else {
+ free(new_filename);
+ }
+
/* Output tracking events */
if (!at_exit) {
record__synthesize(rec, false);
@@ -1093,7 +1161,7 @@ static int record__synthesize(struct record *rec, bool tail)
return err;
}
- err = perf_event__synthesize_bpf_events(tool, process_synthesized_event,
+ err = perf_event__synthesize_bpf_events(session, process_synthesized_event,
machine, opts);
if (err < 0)
pr_warning("Couldn't synthesize bpf events.\n");
@@ -1116,6 +1184,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
struct perf_data *data = &rec->data;
struct perf_session *session;
bool disabled = false, draining = false;
+ struct perf_evlist *sb_evlist = NULL;
int fd;
atexit(record__sig_exit);
@@ -1216,6 +1285,14 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
goto out_child;
}
+ if (!opts->no_bpf_event)
+ bpf_event__add_sb_event(&sb_evlist, &session->header.env);
+
+ if (perf_evlist__start_sb_thread(sb_evlist, &rec->opts.target)) {
+ pr_debug("Couldn't start the BPF side band thread:\nBPF programs starting from now on won't be annotatable\n");
+ opts->no_bpf_event = true;
+ }
+
err = record__synthesize(rec, false);
if (err < 0)
goto out_child;
@@ -1310,7 +1387,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
if (trigger_is_hit(&switch_output_trigger) || done || draining)
perf_evlist__toggle_bkw_mmap(rec->evlist, BKW_MMAP_DATA_PENDING);
- if (record__mmap_read_all(rec) < 0) {
+ if (record__mmap_read_all(rec, false) < 0) {
trigger_error(&auxtrace_snapshot_trigger);
trigger_error(&switch_output_trigger);
err = -1;
@@ -1411,6 +1488,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
record__synthesize_workload(rec, true);
out_child:
+ record__mmap_read_all(rec, true);
record__aio_mmap_read_sync(rec);
if (forks) {
@@ -1466,6 +1544,9 @@ out_child:
out_delete_session:
perf_session__delete(session);
+
+ if (!opts->no_bpf_event)
+ perf_evlist__stop_sb_thread(sb_evlist);
return status;
}
@@ -1813,6 +1894,7 @@ static struct record record = {
.uses_mmap = true,
.default_per_cpu = true,
},
+ .mmap_flush = MMAP_FLUSH_DEFAULT,
},
.tool = {
.sample = process_sample_event,
@@ -1870,7 +1952,7 @@ static struct option __record_options[] = {
OPT_BOOLEAN(0, "tail-synthesize", &record.opts.tail_synthesize,
"synthesize non-sample events at the end of output"),
OPT_BOOLEAN(0, "overwrite", &record.opts.overwrite, "use overwrite mode"),
- OPT_BOOLEAN(0, "bpf-event", &record.opts.bpf_event, "record bpf events"),
+ OPT_BOOLEAN(0, "no-bpf-event", &record.opts.no_bpf_event, "record bpf events"),
OPT_BOOLEAN(0, "strict-freq", &record.opts.strict_freq,
"Fail if the specified frequency can't be used"),
OPT_CALLBACK('F', "freq", &record.opts, "freq or 'max'",
@@ -1879,6 +1961,9 @@ static struct option __record_options[] = {
OPT_CALLBACK('m', "mmap-pages", &record.opts, "pages[,pages]",
"number of mmap data pages and AUX area tracing mmap pages",
record__parse_mmap_pages),
+ OPT_CALLBACK(0, "mmap-flush", &record.opts, "number",
+ "Minimal number of bytes that is extracted from mmap data pages (default: 1)",
+ record__mmap_flush_parse),
OPT_BOOLEAN(0, "group", &record.opts.group,
"put the counters into a counter group"),
OPT_CALLBACK_NOOPT('g', NULL, &callchain_param,
@@ -1968,9 +2053,11 @@ static struct option __record_options[] = {
OPT_BOOLEAN(0, "timestamp-boundary", &record.timestamp_boundary,
"Record timestamp boundary (time of first/last samples)"),
OPT_STRING_OPTARG_SET(0, "switch-output", &record.switch_output.str,
- &record.switch_output.set, "signal,size,time",
- "Switch output when receive SIGUSR2 or cross size,time threshold",
+ &record.switch_output.set, "signal or size[BKMG] or time[smhd]",
+ "Switch output when receiving SIGUSR2 (signal) or cross a size or time threshold",
"signal"),
+ OPT_INTEGER(0, "switch-max-files", &record.switch_output.num_files,
+ "Limit number of switch output generated files"),
OPT_BOOLEAN(0, "dry-run", &dry_run,
"Parse options then exit"),
#ifdef HAVE_AIO_SUPPORT
@@ -2057,6 +2144,13 @@ int cmd_record(int argc, const char **argv)
alarm(rec->switch_output.time);
}
+ if (rec->switch_output.num_files) {
+ rec->switch_output.filenames = calloc(sizeof(char *),
+ rec->switch_output.num_files);
+ if (!rec->switch_output.filenames)
+ return -EINVAL;
+ }
+
/*
* Allow aliases to facilitate the lookup of symbols for address
* filters. Refer to auxtrace_parse_filters().
@@ -2182,6 +2276,7 @@ int cmd_record(int argc, const char **argv)
pr_info("nr_cblocks: %d\n", rec->opts.nr_cblocks);
pr_debug("affinity: %s\n", affinity_tags[rec->opts.affinity]);
+ pr_debug("mmap flush: %d\n", rec->opts.mmap_flush);
err = __cmd_record(&record, argc, argv);
out:
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index ee93c18a6685..4054eb1f98ac 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -47,9 +47,11 @@
#include <errno.h>
#include <inttypes.h>
#include <regex.h>
+#include "sane_ctype.h"
#include <signal.h>
#include <linux/bitmap.h>
#include <linux/stringify.h>
+#include <linux/time64.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <unistd.h>
@@ -926,6 +928,43 @@ report_parse_callchain_opt(const struct option *opt, const char *arg, int unset)
return parse_callchain_report_opt(arg);
}
+static int
+parse_time_quantum(const struct option *opt, const char *arg,
+ int unset __maybe_unused)
+{
+ unsigned long *time_q = opt->value;
+ char *end;
+
+ *time_q = strtoul(arg, &end, 0);
+ if (end == arg)
+ goto parse_err;
+ if (*time_q == 0) {
+ pr_err("time quantum cannot be 0");
+ return -1;
+ }
+ while (isspace(*end))
+ end++;
+ if (*end == 0)
+ return 0;
+ if (!strcmp(end, "s")) {
+ *time_q *= NSEC_PER_SEC;
+ return 0;
+ }
+ if (!strcmp(end, "ms")) {
+ *time_q *= NSEC_PER_MSEC;
+ return 0;
+ }
+ if (!strcmp(end, "us")) {
+ *time_q *= NSEC_PER_USEC;
+ return 0;
+ }
+ if (!strcmp(end, "ns"))
+ return 0;
+parse_err:
+ pr_err("Cannot parse time quantum `%s'\n", arg);
+ return -1;
+}
+
int
report_parse_ignore_callees_opt(const struct option *opt __maybe_unused,
const char *arg, int unset __maybe_unused)
@@ -1044,10 +1083,9 @@ int cmd_report(int argc, const char **argv)
OPT_BOOLEAN(0, "header-only", &report.header_only,
"Show only data header."),
OPT_STRING('s', "sort", &sort_order, "key[,key2...]",
- "sort by key(s): pid, comm, dso, symbol, parent, cpu, srcline, ..."
- " Please refer the man page for the complete list."),
+ sort_help("sort by key(s):")),
OPT_STRING('F', "fields", &field_order, "key[,keys...]",
- "output field(s): overhead, period, sample plus all of sort keys"),
+ sort_help("output field(s): overhead period sample ")),
OPT_BOOLEAN(0, "show-cpu-utilization", &symbol_conf.show_cpu_utilization,
"Show sample percentage for different cpu modes"),
OPT_BOOLEAN_FLAG(0, "showcpuutilization", &symbol_conf.show_cpu_utilization,
@@ -1120,6 +1158,8 @@ int cmd_report(int argc, const char **argv)
OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel,
"Enable kernel symbol demangling"),
OPT_BOOLEAN(0, "mem-mode", &report.mem_mode, "mem access profile"),
+ OPT_INTEGER(0, "samples", &symbol_conf.res_sample,
+ "Number of samples to save per histogram entry for individual browsing"),
OPT_CALLBACK(0, "percent-limit", &report, "percent",
"Don't show entries under that percent", parse_percent_limit),
OPT_CALLBACK(0, "percentage", NULL, "relative|absolute",
@@ -1147,6 +1187,10 @@ int cmd_report(int argc, const char **argv)
OPT_CALLBACK(0, "percent-type", &report.annotation_opts, "local-period",
"Set percent type local/global-period/hits",
annotate_parse_percent_type),
+ OPT_BOOLEAN(0, "ns", &symbol_conf.nanosecs, "Show times in nanosecs"),
+ OPT_CALLBACK(0, "time-quantum", &symbol_conf.time_quantum, "time (ms|us|ns|s)",
+ "Set time quantum for time sort key (default 100ms)",
+ parse_time_quantum),
OPT_END()
};
struct perf_data data = {
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 53f78cf3113f..61cfd8f70989 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -29,10 +29,12 @@
#include "util/time-utils.h"
#include "util/path.h"
#include "print_binary.h"
+#include "archinsn.h"
#include <linux/bitmap.h>
#include <linux/kernel.h>
#include <linux/stringify.h>
#include <linux/time64.h>
+#include <sys/utsname.h>
#include "asm/bug.h"
#include "util/mem-events.h"
#include "util/dump-insn.h"
@@ -51,6 +53,8 @@
static char const *script_name;
static char const *generate_script_lang;
+static bool reltime;
+static u64 initial_time;
static bool debug_mode;
static u64 last_timestamp;
static u64 nr_unordered;
@@ -58,11 +62,11 @@ static bool no_callchain;
static bool latency_format;
static bool system_wide;
static bool print_flags;
-static bool nanosecs;
static const char *cpu_list;
static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
static struct perf_stat_config stat_config;
static int max_blocks;
+static bool native_arch;
unsigned int scripting_max_stack = PERF_MAX_STACK_DEPTH;
@@ -684,15 +688,21 @@ static int perf_sample__fprintf_start(struct perf_sample *sample,
}
if (PRINT_FIELD(TIME)) {
- nsecs = sample->time;
+ u64 t = sample->time;
+ if (reltime) {
+ if (!initial_time)
+ initial_time = sample->time;
+ t = sample->time - initial_time;
+ }
+ nsecs = t;
secs = nsecs / NSEC_PER_SEC;
nsecs -= secs * NSEC_PER_SEC;
- if (nanosecs)
+ if (symbol_conf.nanosecs)
printed += fprintf(fp, "%5lu.%09llu: ", secs, nsecs);
else {
char sample_time[32];
- timestamp__scnprintf_usec(sample->time, sample_time, sizeof(sample_time));
+ timestamp__scnprintf_usec(t, sample_time, sizeof(sample_time));
printed += fprintf(fp, "%12s: ", sample_time);
}
}
@@ -1227,6 +1237,12 @@ static int perf_sample__fprintf_callindent(struct perf_sample *sample,
return len + dlen;
}
+__weak void arch_fetch_insn(struct perf_sample *sample __maybe_unused,
+ struct thread *thread __maybe_unused,
+ struct machine *machine __maybe_unused)
+{
+}
+
static int perf_sample__fprintf_insn(struct perf_sample *sample,
struct perf_event_attr *attr,
struct thread *thread,
@@ -1234,9 +1250,12 @@ static int perf_sample__fprintf_insn(struct perf_sample *sample,
{
int printed = 0;
+ if (sample->insn_len == 0 && native_arch)
+ arch_fetch_insn(sample, thread, machine);
+
if (PRINT_FIELD(INSNLEN))
printed += fprintf(fp, " ilen: %d", sample->insn_len);
- if (PRINT_FIELD(INSN)) {
+ if (PRINT_FIELD(INSN) && sample->insn_len) {
int i;
printed += fprintf(fp, " insn:");
@@ -1922,6 +1941,13 @@ static int cleanup_scripting(void)
return scripting_ops ? scripting_ops->stop_script() : 0;
}
+static bool filter_cpu(struct perf_sample *sample)
+{
+ if (cpu_list)
+ return !test_bit(sample->cpu, cpu_bitmap);
+ return false;
+}
+
static int process_sample_event(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample,
@@ -1956,7 +1982,7 @@ static int process_sample_event(struct perf_tool *tool,
if (al.filtered)
goto out_put;
- if (cpu_list && !test_bit(sample->cpu, cpu_bitmap))
+ if (filter_cpu(sample))
goto out_put;
if (scripting_ops)
@@ -2041,9 +2067,11 @@ static int process_comm_event(struct perf_tool *tool,
sample->tid = event->comm.tid;
sample->pid = event->comm.pid;
}
- perf_sample__fprintf_start(sample, thread, evsel,
+ if (!filter_cpu(sample)) {
+ perf_sample__fprintf_start(sample, thread, evsel,
PERF_RECORD_COMM, stdout);
- perf_event__fprintf(event, stdout);
+ perf_event__fprintf(event, stdout);
+ }
ret = 0;
out:
thread__put(thread);
@@ -2077,9 +2105,11 @@ static int process_namespaces_event(struct perf_tool *tool,
sample->tid = event->namespaces.tid;
sample->pid = event->namespaces.pid;
}
- perf_sample__fprintf_start(sample, thread, evsel,
- PERF_RECORD_NAMESPACES, stdout);
- perf_event__fprintf(event, stdout);
+ if (!filter_cpu(sample)) {
+ perf_sample__fprintf_start(sample, thread, evsel,
+ PERF_RECORD_NAMESPACES, stdout);
+ perf_event__fprintf(event, stdout);
+ }
ret = 0;
out:
thread__put(thread);
@@ -2111,9 +2141,11 @@ static int process_fork_event(struct perf_tool *tool,
sample->tid = event->fork.tid;
sample->pid = event->fork.pid;
}
- perf_sample__fprintf_start(sample, thread, evsel,
- PERF_RECORD_FORK, stdout);
- perf_event__fprintf(event, stdout);
+ if (!filter_cpu(sample)) {
+ perf_sample__fprintf_start(sample, thread, evsel,
+ PERF_RECORD_FORK, stdout);
+ perf_event__fprintf(event, stdout);
+ }
thread__put(thread);
return 0;
@@ -2141,9 +2173,11 @@ static int process_exit_event(struct perf_tool *tool,
sample->tid = event->fork.tid;
sample->pid = event->fork.pid;
}
- perf_sample__fprintf_start(sample, thread, evsel,
- PERF_RECORD_EXIT, stdout);
- perf_event__fprintf(event, stdout);
+ if (!filter_cpu(sample)) {
+ perf_sample__fprintf_start(sample, thread, evsel,
+ PERF_RECORD_EXIT, stdout);
+ perf_event__fprintf(event, stdout);
+ }
if (perf_event__process_exit(tool, event, sample, machine) < 0)
err = -1;
@@ -2177,9 +2211,11 @@ static int process_mmap_event(struct perf_tool *tool,
sample->tid = event->mmap.tid;
sample->pid = event->mmap.pid;
}
- perf_sample__fprintf_start(sample, thread, evsel,
- PERF_RECORD_MMAP, stdout);
- perf_event__fprintf(event, stdout);
+ if (!filter_cpu(sample)) {
+ perf_sample__fprintf_start(sample, thread, evsel,
+ PERF_RECORD_MMAP, stdout);
+ perf_event__fprintf(event, stdout);
+ }
thread__put(thread);
return 0;
}
@@ -2209,9 +2245,11 @@ static int process_mmap2_event(struct perf_tool *tool,
sample->tid = event->mmap2.tid;
sample->pid = event->mmap2.pid;
}
- perf_sample__fprintf_start(sample, thread, evsel,
- PERF_RECORD_MMAP2, stdout);
- perf_event__fprintf(event, stdout);
+ if (!filter_cpu(sample)) {
+ perf_sample__fprintf_start(sample, thread, evsel,
+ PERF_RECORD_MMAP2, stdout);
+ perf_event__fprintf(event, stdout);
+ }
thread__put(thread);
return 0;
}
@@ -2236,9 +2274,11 @@ static int process_switch_event(struct perf_tool *tool,
return -1;
}
- perf_sample__fprintf_start(sample, thread, evsel,
- PERF_RECORD_SWITCH, stdout);
- perf_event__fprintf(event, stdout);
+ if (!filter_cpu(sample)) {
+ perf_sample__fprintf_start(sample, thread, evsel,
+ PERF_RECORD_SWITCH, stdout);
+ perf_event__fprintf(event, stdout);
+ }
thread__put(thread);
return 0;
}
@@ -2259,9 +2299,11 @@ process_lost_event(struct perf_tool *tool,
if (thread == NULL)
return -1;
- perf_sample__fprintf_start(sample, thread, evsel,
- PERF_RECORD_LOST, stdout);
- perf_event__fprintf(event, stdout);
+ if (!filter_cpu(sample)) {
+ perf_sample__fprintf_start(sample, thread, evsel,
+ PERF_RECORD_LOST, stdout);
+ perf_event__fprintf(event, stdout);
+ }
thread__put(thread);
return 0;
}
@@ -2948,7 +2990,8 @@ static int check_ev_match(char *dir_name, char *scriptname,
* will list all statically runnable scripts, select one, execute it and
* show the output in a perf browser.
*/
-int find_scripts(char **scripts_array, char **scripts_path_array)
+int find_scripts(char **scripts_array, char **scripts_path_array, int num,
+ int pathlen)
{
struct dirent *script_dirent, *lang_dirent;
char scripts_path[MAXPATHLEN], lang_path[MAXPATHLEN];
@@ -2993,7 +3036,10 @@ int find_scripts(char **scripts_array, char **scripts_path_array)
/* Skip those real time scripts: xxxtop.p[yl] */
if (strstr(script_dirent->d_name, "top."))
continue;
- sprintf(scripts_path_array[i], "%s/%s", lang_path,
+ if (i >= num)
+ break;
+ snprintf(scripts_path_array[i], pathlen, "%s/%s",
+ lang_path,
script_dirent->d_name);
temp = strchr(script_dirent->d_name, '.');
snprintf(scripts_array[i],
@@ -3232,7 +3278,7 @@ static int parse_insn_trace(const struct option *opt __maybe_unused,
{
parse_output_fields(NULL, "+insn,-event,-period", 0);
itrace_parse_synth_opts(opt, "i0ns", 0);
- nanosecs = true;
+ symbol_conf.nanosecs = true;
return 0;
}
@@ -3250,7 +3296,7 @@ static int parse_call_trace(const struct option *opt __maybe_unused,
{
parse_output_fields(NULL, "-ip,-addr,-event,-period,+callindent", 0);
itrace_parse_synth_opts(opt, "cewp", 0);
- nanosecs = true;
+ symbol_conf.nanosecs = true;
return 0;
}
@@ -3260,7 +3306,7 @@ static int parse_callret_trace(const struct option *opt __maybe_unused,
{
parse_output_fields(NULL, "-ip,-addr,-event,-period,+callindent,+flags", 0);
itrace_parse_synth_opts(opt, "crewp", 0);
- nanosecs = true;
+ symbol_conf.nanosecs = true;
return 0;
}
@@ -3277,6 +3323,7 @@ int cmd_script(int argc, const char **argv)
.set = false,
.default_no_sample = true,
};
+ struct utsname uts;
char *script_path = NULL;
const char **__argv;
int i, j, err = 0;
@@ -3374,6 +3421,7 @@ int cmd_script(int argc, const char **argv)
"Set the maximum stack depth when parsing the callchain, "
"anything beyond the specified depth will be ignored. "
"Default: kernel.perf_event_max_stack or " __stringify(PERF_MAX_STACK_DEPTH)),
+ OPT_BOOLEAN(0, "reltime", &reltime, "Show time stamps relative to start"),
OPT_BOOLEAN('I', "show-info", &show_full_info,
"display extended information from perf.data file"),
OPT_BOOLEAN('\0', "show-kernel-path", &symbol_conf.show_kernel_path,
@@ -3395,7 +3443,7 @@ int cmd_script(int argc, const char **argv)
OPT_BOOLEAN('f', "force", &symbol_conf.force, "don't complain, do it"),
OPT_INTEGER(0, "max-blocks", &max_blocks,
"Maximum number of code blocks to dump with brstackinsn"),
- OPT_BOOLEAN(0, "ns", &nanosecs,
+ OPT_BOOLEAN(0, "ns", &symbol_conf.nanosecs,
"Use 9 decimal places when displaying time"),
OPT_CALLBACK_OPTARG(0, "itrace", &itrace_synth_opts, NULL, "opts",
"Instruction Tracing options\n" ITRACE_HELP,
@@ -3448,6 +3496,11 @@ int cmd_script(int argc, const char **argv)
}
}
+ if (script.time_str && reltime) {
+ fprintf(stderr, "Don't combine --reltime with --time\n");
+ return -1;
+ }
+
if (itrace_synth_opts.callchain &&
itrace_synth_opts.callchain_sz > scripting_max_stack)
scripting_max_stack = itrace_synth_opts.callchain_sz;
@@ -3615,6 +3668,12 @@ int cmd_script(int argc, const char **argv)
if (symbol__init(&session->header.env) < 0)
goto out_delete;
+ uname(&uts);
+ if (!strcmp(uts.machine, session->header.env.arch) ||
+ (!strcmp(uts.machine, "x86_64") &&
+ !strcmp(session->header.env.arch, "i386")))
+ native_arch = true;
+
script.session = session;
script__setup_sample_type(&script);
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 7b8f09b0b8bf..a3c060878faa 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -244,11 +244,25 @@ perf_evsel__write_stat_event(struct perf_evsel *counter, u32 cpu, u32 thread,
process_synthesized_event, NULL);
}
+static int read_single_counter(struct perf_evsel *counter, int cpu,
+ int thread, struct timespec *rs)
+{
+ if (counter->tool_event == PERF_TOOL_DURATION_TIME) {
+ u64 val = rs->tv_nsec + rs->tv_sec*1000000000ULL;
+ struct perf_counts_values *count =
+ perf_counts(counter->counts, cpu, thread);
+ count->ena = count->run = val;
+ count->val = val;
+ return 0;
+ }
+ return perf_evsel__read_counter(counter, cpu, thread);
+}
+
/*
* Read out the results of a single counter:
* do not aggregate counts across CPUs in system-wide mode
*/
-static int read_counter(struct perf_evsel *counter)
+static int read_counter(struct perf_evsel *counter, struct timespec *rs)
{
int nthreads = thread_map__nr(evsel_list->threads);
int ncpus, cpu, thread;
@@ -275,7 +289,7 @@ static int read_counter(struct perf_evsel *counter)
* (via perf_evsel__read_counter) and sets threir count->loaded.
*/
if (!count->loaded &&
- perf_evsel__read_counter(counter, cpu, thread)) {
+ read_single_counter(counter, cpu, thread, rs)) {
counter->counts->scaled = -1;
perf_counts(counter->counts, cpu, thread)->ena = 0;
perf_counts(counter->counts, cpu, thread)->run = 0;
@@ -304,13 +318,13 @@ static int read_counter(struct perf_evsel *counter)
return 0;
}
-static void read_counters(void)
+static void read_counters(struct timespec *rs)
{
struct perf_evsel *counter;
int ret;
evlist__for_each_entry(evsel_list, counter) {
- ret = read_counter(counter);
+ ret = read_counter(counter, rs);
if (ret)
pr_debug("failed to read counter %s\n", counter->name);
@@ -323,11 +337,11 @@ static void process_interval(void)
{
struct timespec ts, rs;
- read_counters();
-
clock_gettime(CLOCK_MONOTONIC, &ts);
diff_timespec(&rs, &ts, &ref_time);
+ read_counters(&rs);
+
if (STAT_RECORD) {
if (WRITE_STAT_ROUND_EVENT(rs.tv_sec * NSEC_PER_SEC + rs.tv_nsec, INTERVAL))
pr_err("failed to write stat round event\n");
@@ -593,7 +607,7 @@ try_again:
* avoid arbitrary skew, we must read all counters before closing any
* group leaders.
*/
- read_counters();
+ read_counters(&(struct timespec) { .tv_nsec = t1-t0 });
perf_evlist__close(evsel_list);
return WEXITSTATUS(status);
@@ -718,7 +732,8 @@ static struct option stat_options[] = {
"system-wide collection from all CPUs"),
OPT_BOOLEAN('g', "group", &group,
"put the counters into a counter group"),
- OPT_BOOLEAN('c', "scale", &stat_config.scale, "scale/normalize counters"),
+ OPT_BOOLEAN(0, "scale", &stat_config.scale,
+ "Use --no-scale to disable counter scaling for multiplexing"),
OPT_INCR('v', "verbose", &verbose,
"be more verbose (show counter open errors, etc)"),
OPT_INTEGER('r', "repeat", &stat_config.run_count,
@@ -1307,6 +1322,7 @@ static void init_features(struct perf_session *session)
for (feat = HEADER_FIRST_FEATURE; feat < HEADER_LAST_FEATURE; feat++)
perf_header__set_feat(&session->header, feat);
+ perf_header__clear_feat(&session->header, HEADER_DIR_FORMAT);
perf_header__clear_feat(&session->header, HEADER_BUILD_ID);
perf_header__clear_feat(&session->header, HEADER_TRACING_DATA);
perf_header__clear_feat(&session->header, HEADER_BRANCH_STACK);
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 231a90daa958..fbbb0da43abb 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -1189,30 +1189,26 @@ static int __cmd_top(struct perf_top *top)
pthread_t thread, thread_process;
int ret;
- top->session = perf_session__new(NULL, false, NULL);
- if (top->session == NULL)
- return -1;
-
if (!top->annotation_opts.objdump_path) {
ret = perf_env__lookup_objdump(&top->session->header.env,
&top->annotation_opts.objdump_path);
if (ret)
- goto out_delete;
+ return ret;
}
ret = callchain_param__setup_sample_type(&callchain_param);
if (ret)
- goto out_delete;
+ return ret;
if (perf_session__register_idle_thread(top->session) < 0)
- goto out_delete;
+ return ret;
if (top->nr_threads_synthesize > 1)
perf_set_multithreaded();
init_process_thread(top);
- ret = perf_event__synthesize_bpf_events(&top->tool, perf_event__process,
+ ret = perf_event__synthesize_bpf_events(top->session, perf_event__process,
&top->session->machines.host,
&top->record_opts);
if (ret < 0)
@@ -1227,13 +1223,18 @@ static int __cmd_top(struct perf_top *top)
if (perf_hpp_list.socket) {
ret = perf_env__read_cpu_topology_map(&perf_env);
- if (ret < 0)
- goto out_err_cpu_topo;
+ if (ret < 0) {
+ char errbuf[BUFSIZ];
+ const char *err = str_error_r(-ret, errbuf, sizeof(errbuf));
+
+ ui__error("Could not read the CPU topology map: %s\n", err);
+ return ret;
+ }
}
ret = perf_top__start_counters(top);
if (ret)
- goto out_delete;
+ return ret;
top->session->evlist = top->evlist;
perf_session__set_id_hdr_size(top->session);
@@ -1252,7 +1253,7 @@ static int __cmd_top(struct perf_top *top)
ret = -1;
if (pthread_create(&thread_process, NULL, process_thread, top)) {
ui__error("Could not create process thread.\n");
- goto out_delete;
+ return ret;
}
if (pthread_create(&thread, NULL, (use_browser > 0 ? display_thread_tui :
@@ -1296,19 +1297,7 @@ out_join:
out_join_thread:
pthread_cond_signal(&top->qe.cond);
pthread_join(thread_process, NULL);
-out_delete:
- perf_session__delete(top->session);
- top->session = NULL;
-
return ret;
-
-out_err_cpu_topo: {
- char errbuf[BUFSIZ];
- const char *err = str_error_r(-ret, errbuf, sizeof(errbuf));
-
- ui__error("Could not read the CPU topology map: %s\n", err);
- goto out_delete;
-}
}
static int
@@ -1388,6 +1377,7 @@ int cmd_top(int argc, const char **argv)
* */
.overwrite = 0,
.sample_time = true,
+ .sample_time_set = true,
},
.max_stack = sysctl__max_stack(),
.annotation_opts = annotation__default_options,
@@ -1480,6 +1470,7 @@ int cmd_top(int argc, const char **argv)
"Display raw encoding of assembly instructions (default)"),
OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel,
"Enable kernel symbol demangling"),
+ OPT_BOOLEAN(0, "no-bpf-event", &top.record_opts.no_bpf_event, "do not record bpf events"),
OPT_STRING(0, "objdump", &top.annotation_opts.objdump_path, "path",
"objdump binary to use for disassembly and annotations"),
OPT_STRING('M', "disassembler-style", &top.annotation_opts.disassembler_style, "disassembler style",
@@ -1511,6 +1502,7 @@ int cmd_top(int argc, const char **argv)
"number of thread to run event synthesize"),
OPT_END()
};
+ struct perf_evlist *sb_evlist = NULL;
const char * const top_usage[] = {
"perf top [<options>]",
NULL
@@ -1628,8 +1620,9 @@ int cmd_top(int argc, const char **argv)
annotation_config__init();
symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL);
- if (symbol__init(NULL) < 0)
- return -1;
+ status = symbol__init(NULL);
+ if (status < 0)
+ goto out_delete_evlist;
sort__setup_elide(stdout);
@@ -1639,10 +1632,28 @@ int cmd_top(int argc, const char **argv)
signal(SIGWINCH, winch_sig);
}
+ top.session = perf_session__new(NULL, false, NULL);
+ if (top.session == NULL) {
+ status = -1;
+ goto out_delete_evlist;
+ }
+
+ if (!top.record_opts.no_bpf_event)
+ bpf_event__add_sb_event(&sb_evlist, &perf_env);
+
+ if (perf_evlist__start_sb_thread(sb_evlist, target)) {
+ pr_debug("Couldn't start the BPF side band thread:\nBPF programs starting from now on won't be annotatable\n");
+ opts->no_bpf_event = true;
+ }
+
status = __cmd_top(&top);
+ if (!opts->no_bpf_event)
+ perf_evlist__stop_sb_thread(sb_evlist);
+
out_delete_evlist:
perf_evlist__delete(top.evlist);
+ perf_session__delete(top.session);
return status;
}
diff --git a/tools/perf/builtin-version.c b/tools/perf/builtin-version.c
index 50df168be326..f470144d1a70 100644
--- a/tools/perf/builtin-version.c
+++ b/tools/perf/builtin-version.c
@@ -78,6 +78,8 @@ static void library_status(void)
STATUS(HAVE_LZMA_SUPPORT, lzma);
STATUS(HAVE_AUXTRACE_SUPPORT, get_cpuid);
STATUS(HAVE_LIBBPF_SUPPORT, bpf);
+ STATUS(HAVE_AIO_SUPPORT, aio);
+ STATUS(HAVE_ZSTD_SUPPORT, zstd);
}
int cmd_version(int argc, const char **argv)
diff --git a/tools/perf/builtin.h b/tools/perf/builtin.h
index 05745f3ce912..999fe9170122 100644
--- a/tools/perf/builtin.h
+++ b/tools/perf/builtin.h
@@ -40,5 +40,6 @@ int cmd_mem(int argc, const char **argv);
int cmd_data(int argc, const char **argv);
int cmd_ftrace(int argc, const char **argv);
-int find_scripts(char **scripts_array, char **scripts_path_array);
+int find_scripts(char **scripts_array, char **scripts_path_array, int num,
+ int pathlen);
#endif
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index 7b55613924de..c68ee06cae63 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -103,7 +103,7 @@ done
# diff with extra ignore lines
check arch/x86/lib/memcpy_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"'
check arch/x86/lib/memset_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"'
-check include/uapi/asm-generic/mman.h '-I "^#include <\(uapi/\)*asm-generic/mman-common.h>"'
+check include/uapi/asm-generic/mman.h '-I "^#include <\(uapi/\)*asm-generic/mman-common\(-tools\)*.h>"'
check include/uapi/linux/mman.h '-I "^#include <\(uapi/\)*asm/mman.h>"'
# diff non-symmetric files
diff --git a/tools/perf/examples/bpf/augmented_raw_syscalls.c b/tools/perf/examples/bpf/augmented_raw_syscalls.c
index f9b2161e1ca4..2422894a8194 100644
--- a/tools/perf/examples/bpf/augmented_raw_syscalls.c
+++ b/tools/perf/examples/bpf/augmented_raw_syscalls.c
@@ -15,6 +15,7 @@
*/
#include <unistd.h>
+#include <linux/limits.h>
#include <pid_filter.h>
/* bpf-output associated map */
@@ -41,32 +42,110 @@ struct syscall_exit_args {
struct augmented_filename {
unsigned int size;
int reserved;
- char value[256];
+ char value[PATH_MAX];
};
-#define SYS_OPEN 2
-#define SYS_ACCESS 21
-#define SYS_OPENAT 257
+/* syscalls where the first arg is a string */
+#define SYS_OPEN 2
+#define SYS_STAT 4
+#define SYS_LSTAT 6
+#define SYS_ACCESS 21
+#define SYS_EXECVE 59
+#define SYS_TRUNCATE 76
+#define SYS_CHDIR 80
+#define SYS_RENAME 82
+#define SYS_MKDIR 83
+#define SYS_RMDIR 84
+#define SYS_CREAT 85
+#define SYS_LINK 86
+#define SYS_UNLINK 87
+#define SYS_SYMLINK 88
+#define SYS_READLINK 89
+#define SYS_CHMOD 90
+#define SYS_CHOWN 92
+#define SYS_LCHOWN 94
+#define SYS_MKNOD 133
+#define SYS_STATFS 137
+#define SYS_PIVOT_ROOT 155
+#define SYS_CHROOT 161
+#define SYS_ACCT 163
+#define SYS_SWAPON 167
+#define SYS_SWAPOFF 168
+#define SYS_DELETE_MODULE 176
+#define SYS_SETXATTR 188
+#define SYS_LSETXATTR 189
+#define SYS_GETXATTR 191
+#define SYS_LGETXATTR 192
+#define SYS_LISTXATTR 194
+#define SYS_LLISTXATTR 195
+#define SYS_REMOVEXATTR 197
+#define SYS_LREMOVEXATTR 198
+#define SYS_MQ_OPEN 240
+#define SYS_MQ_UNLINK 241
+#define SYS_ADD_KEY 248
+#define SYS_REQUEST_KEY 249
+#define SYS_SYMLINKAT 266
+#define SYS_MEMFD_CREATE 319
+
+/* syscalls where the first arg is a string */
+
+#define SYS_PWRITE64 18
+#define SYS_EXECVE 59
+#define SYS_RENAME 82
+#define SYS_QUOTACTL 179
+#define SYS_FSETXATTR 190
+#define SYS_FGETXATTR 193
+#define SYS_FREMOVEXATTR 199
+#define SYS_MQ_TIMEDSEND 242
+#define SYS_REQUEST_KEY 249
+#define SYS_INOTIFY_ADD_WATCH 254
+#define SYS_OPENAT 257
+#define SYS_MKDIRAT 258
+#define SYS_MKNODAT 259
+#define SYS_FCHOWNAT 260
+#define SYS_FUTIMESAT 261
+#define SYS_NEWFSTATAT 262
+#define SYS_UNLINKAT 263
+#define SYS_RENAMEAT 264
+#define SYS_LINKAT 265
+#define SYS_READLINKAT 267
+#define SYS_FCHMODAT 268
+#define SYS_FACCESSAT 269
+#define SYS_UTIMENSAT 280
+#define SYS_NAME_TO_HANDLE_AT 303
+#define SYS_FINIT_MODULE 313
+#define SYS_RENAMEAT2 316
+#define SYS_EXECVEAT 322
+#define SYS_STATX 332
pid_filter(pids_filtered);
+struct augmented_args_filename {
+ struct syscall_enter_args args;
+ struct augmented_filename filename;
+};
+
+bpf_map(augmented_filename_map, PERCPU_ARRAY, int, struct augmented_args_filename, 1);
+
SEC("raw_syscalls:sys_enter")
int sys_enter(struct syscall_enter_args *args)
{
- struct {
- struct syscall_enter_args args;
- struct augmented_filename filename;
- } augmented_args;
- struct syscall *syscall;
- unsigned int len = sizeof(augmented_args);
+ struct augmented_args_filename *augmented_args;
+ unsigned int len = sizeof(*augmented_args);
const void *filename_arg = NULL;
+ struct syscall *syscall;
+ int key = 0;
+
+ augmented_args = bpf_map_lookup_elem(&augmented_filename_map, &key);
+ if (augmented_args == NULL)
+ return 1;
if (pid_filter__has(&pids_filtered, getpid()))
return 0;
- probe_read(&augmented_args.args, sizeof(augmented_args.args), args);
+ probe_read(&augmented_args->args, sizeof(augmented_args->args), args);
- syscall = bpf_map_lookup_elem(&syscalls, &augmented_args.args.syscall_nr);
+ syscall = bpf_map_lookup_elem(&syscalls, &augmented_args->args.syscall_nr);
if (syscall == NULL || !syscall->enabled)
return 0;
/*
@@ -109,30 +188,105 @@ int sys_enter(struct syscall_enter_args *args)
*
* after the ctx memory access to prevent their down stream merging.
*/
- switch (augmented_args.args.syscall_nr) {
+ /*
+ * This table of what args are strings will be provided by userspace,
+ * in the syscalls map, i.e. we will already have to do the lookup to
+ * see if this specific syscall is filtered, so we can as well get more
+ * info about what syscall args are strings or pointers, and how many
+ * bytes to copy, per arg, etc.
+ *
+ * For now hard code it, till we have all the basic mechanisms in place
+ * to automate everything and make the kernel part be completely driven
+ * by information obtained in userspace for each kernel version and
+ * processor architecture, making the kernel part the same no matter what
+ * kernel version or processor architecture it runs on.
+ */
+ switch (augmented_args->args.syscall_nr) {
+ case SYS_ACCT:
+ case SYS_ADD_KEY:
+ case SYS_CHDIR:
+ case SYS_CHMOD:
+ case SYS_CHOWN:
+ case SYS_CHROOT:
+ case SYS_CREAT:
+ case SYS_DELETE_MODULE:
+ case SYS_EXECVE:
+ case SYS_GETXATTR:
+ case SYS_LCHOWN:
+ case SYS_LGETXATTR:
+ case SYS_LINK:
+ case SYS_LISTXATTR:
+ case SYS_LLISTXATTR:
+ case SYS_LREMOVEXATTR:
+ case SYS_LSETXATTR:
+ case SYS_LSTAT:
+ case SYS_MEMFD_CREATE:
+ case SYS_MKDIR:
+ case SYS_MKNOD:
+ case SYS_MQ_OPEN:
+ case SYS_MQ_UNLINK:
+ case SYS_PIVOT_ROOT:
+ case SYS_READLINK:
+ case SYS_REMOVEXATTR:
+ case SYS_RENAME:
+ case SYS_REQUEST_KEY:
+ case SYS_RMDIR:
+ case SYS_SETXATTR:
+ case SYS_STAT:
+ case SYS_STATFS:
+ case SYS_SWAPOFF:
+ case SYS_SWAPON:
+ case SYS_SYMLINK:
+ case SYS_SYMLINKAT:
+ case SYS_TRUNCATE:
+ case SYS_UNLINK:
case SYS_ACCESS:
case SYS_OPEN: filename_arg = (const void *)args->args[0];
__asm__ __volatile__("": : :"memory");
break;
+ case SYS_EXECVEAT:
+ case SYS_FACCESSAT:
+ case SYS_FCHMODAT:
+ case SYS_FCHOWNAT:
+ case SYS_FGETXATTR:
+ case SYS_FINIT_MODULE:
+ case SYS_FREMOVEXATTR:
+ case SYS_FSETXATTR:
+ case SYS_FUTIMESAT:
+ case SYS_INOTIFY_ADD_WATCH:
+ case SYS_LINKAT:
+ case SYS_MKDIRAT:
+ case SYS_MKNODAT:
+ case SYS_MQ_TIMEDSEND:
+ case SYS_NAME_TO_HANDLE_AT:
+ case SYS_NEWFSTATAT:
+ case SYS_PWRITE64:
+ case SYS_QUOTACTL:
+ case SYS_READLINKAT:
+ case SYS_RENAMEAT:
+ case SYS_RENAMEAT2:
+ case SYS_STATX:
+ case SYS_UNLINKAT:
+ case SYS_UTIMENSAT:
case SYS_OPENAT: filename_arg = (const void *)args->args[1];
break;
}
if (filename_arg != NULL) {
- augmented_args.filename.reserved = 0;
- augmented_args.filename.size = probe_read_str(&augmented_args.filename.value,
- sizeof(augmented_args.filename.value),
+ augmented_args->filename.reserved = 0;
+ augmented_args->filename.size = probe_read_str(&augmented_args->filename.value,
+ sizeof(augmented_args->filename.value),
filename_arg);
- if (augmented_args.filename.size < sizeof(augmented_args.filename.value)) {
- len -= sizeof(augmented_args.filename.value) - augmented_args.filename.size;
- len &= sizeof(augmented_args.filename.value) - 1;
+ if (augmented_args->filename.size < sizeof(augmented_args->filename.value)) {
+ len -= sizeof(augmented_args->filename.value) -