aboutsummaryrefslogtreecommitdiffstats
path: root/tools
diff options
context:
space:
mode:
Diffstat (limited to 'tools')
-rw-r--r--tools/Makefile7
-rw-r--r--tools/arch/arm/include/uapi/asm/kvm.h9
-rw-r--r--tools/arch/powerpc/include/uapi/asm/kvm.h5
-rw-r--r--tools/arch/x86/include/asm/cpufeatures.h13
-rw-r--r--tools/arch/x86/include/uapi/asm/vmx.h5
-rw-r--r--tools/build/Build.include22
-rw-r--r--tools/build/Documentation/Build.txt6
-rw-r--r--tools/build/Makefile6
-rw-r--r--tools/build/Makefile.build10
-rw-r--r--tools/build/Makefile.feature138
-rw-r--r--tools/build/Makefile.include3
-rw-r--r--tools/build/feature/Makefile126
-rw-r--r--tools/build/feature/test-clang.cpp21
-rw-r--r--tools/build/feature/test-jvmti.c13
-rw-r--r--tools/build/feature/test-llvm-version.cpp11
-rw-r--r--tools/build/feature/test-llvm.cpp13
-rw-r--r--tools/build/fixdep.c5
-rw-r--r--tools/gpio/.gitignore4
-rw-r--r--tools/gpio/Makefile2
-rw-r--r--tools/gpio/gpio-hammer.c67
-rw-r--r--tools/gpio/gpio-utils.c256
-rw-r--r--tools/gpio/gpio-utils.h16
-rw-r--r--tools/hv/Makefile3
-rwxr-xr-xtools/hv/bondvf.sh4
-rw-r--r--tools/hv/hv_fcopy_daemon.c7
-rw-r--r--tools/hv/hv_kvp_daemon.c20
-rw-r--r--tools/iio/iio_event_monitor.c2
-rw-r--r--tools/iio/iio_generic_buffer.c18
-rw-r--r--tools/include/asm-generic/bitops.h1
-rw-r--r--tools/include/asm-generic/bitops/__ffz.h (renamed from tools/testing/radix-tree/linux/bitops/ffz.h)0
-rw-r--r--tools/include/asm-generic/bitops/atomic.h3
-rw-r--r--tools/include/asm-generic/bitops/find.h28
-rw-r--r--tools/include/asm/bug.h19
-rw-r--r--tools/include/linux/bitmap.h27
-rw-r--r--tools/include/linux/bitops.h6
-rw-r--r--tools/include/linux/compiler-gcc.h14
-rw-r--r--tools/include/linux/compiler.h13
-rw-r--r--tools/include/linux/filter.h24
-rw-r--r--tools/include/linux/log2.h13
-rw-r--r--tools/include/linux/spinlock.h5
-rw-r--r--tools/include/linux/types.h4
-rw-r--r--tools/include/uapi/asm-generic/mman-common.h5
-rw-r--r--tools/include/uapi/linux/bpf.h621
-rw-r--r--tools/include/uapi/linux/hw_breakpoint.h4
-rw-r--r--tools/leds/.gitignore1
-rw-r--r--tools/leds/Makefile13
-rw-r--r--tools/leds/led_hw_brightness_mon.c84
-rw-r--r--tools/leds/uledmon.c63
-rw-r--r--tools/lib/api/Makefile10
-rw-r--r--tools/lib/api/fs/fs.c16
-rw-r--r--tools/lib/api/fs/fs.h1
-rw-r--r--tools/lib/api/fs/tracing_path.c32
-rw-r--r--tools/lib/bpf/Makefile2
-rw-r--r--tools/lib/bpf/bpf.c102
-rw-r--r--tools/lib/bpf/bpf.h24
-rw-r--r--tools/lib/bpf/libbpf.c444
-rw-r--r--tools/lib/bpf/libbpf.h32
-rw-r--r--tools/lib/find_bit.c27
-rw-r--r--tools/lib/lockdep/Makefile2
-rw-r--r--tools/lib/subcmd/Makefile10
-rw-r--r--tools/lib/subcmd/parse-options.c21
-rw-r--r--tools/lib/subcmd/parse-options.h24
-rw-r--r--tools/lib/traceevent/Makefile56
-rw-r--r--tools/lib/traceevent/event-parse.c75
-rw-r--r--tools/lib/traceevent/event-parse.h6
-rw-r--r--tools/lib/traceevent/kbuffer-parse.c1
-rw-r--r--tools/lib/traceevent/plugin_function.c2
-rw-r--r--tools/lib/traceevent/plugin_sched_switch.c4
-rw-r--r--tools/objtool/Makefile4
-rw-r--r--tools/objtool/arch.h5
-rw-r--r--tools/objtool/arch/x86/decode.c5
-rw-r--r--tools/objtool/builtin-check.c77
-rw-r--r--tools/objtool/elf.c12
-rw-r--r--tools/objtool/elf.h1
-rw-r--r--tools/perf/Build6
-rw-r--r--tools/perf/Documentation/intel-pt.txt19
-rw-r--r--tools/perf/Documentation/jitdump-specification.txt170
-rw-r--r--tools/perf/Documentation/perf-annotate.txt4
-rw-r--r--tools/perf/Documentation/perf-c2c.txt290
-rw-r--r--tools/perf/Documentation/perf-config.txt47
-rw-r--r--tools/perf/Documentation/perf-diff.txt19
-rw-r--r--tools/perf/Documentation/perf-ftrace.txt36
-rw-r--r--tools/perf/Documentation/perf-kallsyms.txt24
-rw-r--r--tools/perf/Documentation/perf-kmem.txt7
-rw-r--r--tools/perf/Documentation/perf-record.txt29
-rw-r--r--tools/perf/Documentation/perf-report.txt14
-rw-r--r--tools/perf/Documentation/perf-sched.txt84
-rw-r--r--tools/perf/Documentation/perf-script.txt20
-rw-r--r--tools/perf/Documentation/perf-stat.txt2
-rw-r--r--tools/perf/Documentation/perf-top.txt1
-rw-r--r--tools/perf/Documentation/perf-trace.txt13
-rw-r--r--tools/perf/Documentation/tips.txt2
-rw-r--r--tools/perf/MANIFEST2
-rw-r--r--tools/perf/Makefile.config111
-rw-r--r--tools/perf/Makefile.perf251
-rw-r--r--tools/perf/arch/arm/annotate/instructions.c59
-rw-r--r--tools/perf/arch/arm/util/cs-etm.c2
-rw-r--r--tools/perf/arch/arm64/Makefile1
-rw-r--r--tools/perf/arch/arm64/annotate/instructions.c62
-rw-r--r--tools/perf/arch/arm64/include/dwarf-regs-table.h12
-rw-r--r--tools/perf/arch/arm64/util/dwarf-regs.c15
-rw-r--r--tools/perf/arch/powerpc/annotate/instructions.c58
-rw-r--r--tools/perf/arch/x86/annotate/instructions.c78
-rw-r--r--tools/perf/arch/x86/entry/syscalls/syscall_64.tbl7
-rw-r--r--tools/perf/arch/x86/tests/arch-tests.c10
-rw-r--r--tools/perf/bench/futex-hash.c6
-rw-r--r--tools/perf/bench/futex-lock-pi.c6
-rw-r--r--tools/perf/bench/mem-functions.c77
-rw-r--r--tools/perf/bench/numa.c7
-rw-r--r--tools/perf/builtin-annotate.c4
-rw-r--r--tools/perf/builtin-c2c.c2780
-rw-r--r--tools/perf/builtin-config.c137
-rw-r--r--tools/perf/builtin-diff.c94
-rw-r--r--tools/perf/builtin-ftrace.c265
-rw-r--r--tools/perf/builtin-help.c8
-rw-r--r--tools/perf/builtin-kallsyms.c67
-rw-r--r--tools/perf/builtin-kmem.c49
-rw-r--r--tools/perf/builtin-list.c3
-rw-r--r--tools/perf/builtin-mem.c8
-rw-r--r--tools/perf/builtin-probe.c2
-rw-r--r--tools/perf/builtin-record.c203
-rw-r--r--tools/perf/builtin-report.c56
-rw-r--r--tools/perf/builtin-sched.c1434
-rw-r--r--tools/perf/builtin-script.c54
-rw-r--r--tools/perf/builtin-stat.c19
-rw-r--r--tools/perf/builtin-top.c12
-rw-r--r--tools/perf/builtin-trace.c194
-rw-r--r--tools/perf/builtin.h3
-rwxr-xr-xtools/perf/check-headers.sh59
-rw-r--r--tools/perf/command-list.txt2
-rw-r--r--tools/perf/jvmti/Build8
-rw-r--r--tools/perf/jvmti/Makefile89
-rw-r--r--tools/perf/jvmti/jvmti_agent.c38
-rw-r--r--tools/perf/jvmti/libjvmti.c39
-rw-r--r--tools/perf/perf.c21
-rw-r--r--tools/perf/perf.h1
-rw-r--r--tools/perf/pmu-events/arch/powerpc/mapfile.csv21
-rw-r--r--tools/perf/pmu-events/arch/powerpc/power8/cache.json176
-rw-r--r--tools/perf/pmu-events/arch/powerpc/power8/floating-point.json14
-rw-r--r--tools/perf/pmu-events/arch/powerpc/power8/frontend.json470
-rw-r--r--tools/perf/pmu-events/arch/powerpc/power8/marked.json794
-rw-r--r--tools/perf/pmu-events/arch/powerpc/power8/memory.json212
-rw-r--r--tools/perf/pmu-events/arch/powerpc/power8/other.json4064
-rw-r--r--tools/perf/pmu-events/arch/powerpc/power8/pipeline.json350
-rw-r--r--tools/perf/pmu-events/arch/powerpc/power8/pmc.json140
-rw-r--r--tools/perf/pmu-events/arch/powerpc/power8/translation.json176
-rw-r--r--tools/perf/pmu-events/arch/x86/bonnell/cache.json746
-rw-r--r--tools/perf/pmu-events/arch/x86/bonnell/floating-point.json261
-rw-r--r--tools/perf/pmu-events/arch/x86/bonnell/frontend.json83
-rw-r--r--tools/perf/pmu-events/arch/x86/bonnell/memory.json154
-rw-r--r--tools/perf/pmu-events/arch/x86/bonnell/other.json450
-rw-r--r--tools/perf/pmu-events/arch/x86/bonnell/pipeline.json364
-rw-r--r--tools/perf/pmu-events/arch/x86/bonnell/virtual-memory.json124
-rw-r--r--tools/perf/pmu-events/arch/x86/broadwell/cache.json3198
-rw-r--r--tools/perf/pmu-events/arch/x86/broadwell/floating-point.json171
-rw-r--r--tools/perf/pmu-events/arch/x86/broadwell/frontend.json286
-rw-r--r--tools/perf/pmu-events/arch/x86/broadwell/memory.json2845
-rw-r--r--tools/perf/pmu-events/arch/x86/broadwell/other.json44
-rw-r--r--tools/perf/pmu-events/arch/x86/broadwell/pipeline.json1417
-rw-r--r--tools/perf/pmu-events/arch/x86/broadwell/virtual-memory.json388
-rw-r--r--tools/perf/pmu-events/arch/x86/broadwellde/cache.json774
-rw-r--r--tools/perf/pmu-events/arch/x86/broadwellde/floating-point.json171
-rw-r--r--tools/perf/pmu-events/arch/x86/broadwellde/frontend.json286
-rw-r--r--tools/perf/pmu-events/arch/x86/broadwellde/memory.json433
-rw-r--r--tools/perf/pmu-events/arch/x86/broadwellde/other.json44
-rw-r--r--tools/perf/pmu-events/arch/x86/broadwellde/pipeline.json1417
-rw-r--r--tools/perf/pmu-events/arch/x86/broadwellde/uncore-cache.json317
-rw-r--r--tools/perf/pmu-events/arch/x86/broadwellde/uncore-memory.json83
-rw-r--r--tools/perf/pmu-events/arch/x86/broadwellde/uncore-power.json84
-rw-r--r--tools/perf/pmu-events/arch/x86/broadwellde/virtual-memory.json388
-rw-r--r--tools/perf/pmu-events/arch/x86/broadwellx/cache.json942
-rw-r--r--tools/perf/pmu-events/arch/x86/broadwellx/floating-point.json171
-rw-r--r--tools/perf/pmu-events/arch/x86/broadwellx/frontend.json286
-rw-r--r--tools/perf/pmu-events/arch/x86/broadwellx/memory.json649
-rw-r--r--tools/perf/pmu-events/arch/x86/broadwellx/other.json44
-rw-r--r--tools/perf/pmu-events/arch/x86/broadwellx/pipeline.json1417
-rw-r--r--tools/perf/pmu-events/arch/x86/broadwellx/uncore-cache.json317
-rw-r--r--tools/perf/pmu-events/arch/x86/broadwellx/uncore-interconnect.json28
-rw-r--r--tools/perf/pmu-events/arch/x86/broadwellx/uncore-memory.json83
-rw-r--r--tools/perf/pmu-events/arch/x86/broadwellx/uncore-power.json84
-rw-r--r--tools/perf/pmu-events/arch/x86/broadwellx/virtual-memory.json388
-rw-r--r--tools/perf/pmu-events/arch/x86/goldmont/cache.json1127
-rw-r--r--tools/perf/pmu-events/arch/x86/goldmont/frontend.json52
-rw-r--r--tools/perf/pmu-events/arch/x86/goldmont/memory.json34
-rw-r--r--tools/perf/pmu-events/arch/x86/goldmont/other.json52
-rw-r--r--tools/perf/pmu-events/arch/x86/goldmont/pipeline.json433
-rw-r--r--tools/perf/pmu-events/arch/x86/goldmont/virtual-memory.json75
-rw-r--r--tools/perf/pmu-events/arch/x86/haswell/cache.json1041
-rw-r--r--tools/perf/pmu-events/arch/x86/haswell/floating-point.json83
-rw-r--r--tools/perf/pmu-events/arch/x86/haswell/frontend.json294
-rw-r--r--tools/perf/pmu-events/arch/x86/haswell/memory.json655
-rw-r--r--tools/perf/pmu-events/arch/x86/haswell/other.json43
-rw-r--r--tools/perf/pmu-events/arch/x86/haswell/pipeline.json1329
-rw-r--r--tools/perf/pmu-events/arch/x86/haswell/virtual-memory.json484
-rw-r--r--tools/perf/pmu-events/arch/x86/haswellx/cache.json1077
-rw-r--r--tools/perf/pmu-events/arch/x86/haswellx/floating-point.json83
-rw-r--r--tools/perf/pmu-events/arch/x86/haswellx/frontend.json294
-rw-r--r--tools/perf/pmu-events/arch/x86/haswellx/memory.json739
-rw-r--r--tools/perf/pmu-events/arch/x86/haswellx/other.json43
-rw-r--r--tools/perf/pmu-events/arch/x86/haswellx/pipeline.json1329
-rw-r--r--tools/perf/pmu-events/arch/x86/haswellx/uncore-cache.json317
-rw-r--r--tools/perf/pmu-events/arch/x86/haswellx/uncore-interconnect.json28
-rw-r--r--tools/perf/pmu-events/arch/x86/haswellx/uncore-memory.json83
-rw-r--r--tools/perf/pmu-events/arch/x86/haswellx/uncore-power.json84
-rw-r--r--tools/perf/pmu-events/arch/x86/haswellx/virtual-memory.json484
-rw-r--r--tools/perf/pmu-events/arch/x86/ivybridge/cache.json1123
-rw-r--r--tools/perf/pmu-events/arch/x86/ivybridge/floating-point.json151
-rw-r--r--tools/perf/pmu-events/arch/x86/ivybridge/frontend.json305
-rw-r--r--tools/perf/pmu-events/arch/x86/ivybridge/memory.json236
-rw-r--r--tools/perf/pmu-events/arch/x86/ivybridge/other.json44
-rw-r--r--tools/perf/pmu-events/arch/x86/ivybridge/pipeline.json1307
-rw-r--r--tools/perf/pmu-events/arch/x86/ivybridge/virtual-memory.json180
-rw-r--r--tools/perf/pmu-events/arch/x86/ivytown/cache.json1272
-rw-r--r--tools/perf/pmu-events/arch/x86/ivytown/floating-point.json151
-rw-r--r--tools/perf/pmu-events/arch/x86/ivytown/frontend.json305
-rw-r--r--tools/perf/pmu-events/arch/x86/ivytown/memory.json503
-rw-r--r--tools/perf/pmu-events/arch/x86/ivytown/other.json44
-rw-r--r--tools/perf/pmu-events/arch/x86/ivytown/pipeline.json1307
-rw-r--r--tools/perf/pmu-events/arch/x86/ivytown/uncore-cache.json322
-rw-r--r--tools/perf/pmu-events/arch/x86/ivytown/uncore-interconnect.json46
-rw-r--r--tools/perf/pmu-events/arch/x86/ivytown/uncore-memory.json75
-rw-r--r--tools/perf/pmu-events/arch/x86/ivytown/uncore-power.json249
-rw-r--r--tools/perf/pmu-events/arch/x86/ivytown/virtual-memory.json198
-rw-r--r--tools/perf/pmu-events/arch/x86/jaketown/cache.json1290
-rw-r--r--tools/perf/pmu-events/arch/x86/jaketown/floating-point.json138
-rw-r--r--tools/perf/pmu-events/arch/x86/jaketown/frontend.json305
-rw-r--r--tools/perf/pmu-events/arch/x86/jaketown/memory.json422
-rw-r--r--tools/perf/pmu-events/arch/x86/jaketown/other.json58
-rw-r--r--tools/perf/pmu-events/arch/x86/jaketown/pipeline.json1220
-rw-r--r--tools/perf/pmu-events/arch/x86/jaketown/uncore-cache.json209
-rw-r--r--tools/perf/pmu-events/arch/x86/jaketown/uncore-interconnect.json46
-rw-r--r--tools/perf/pmu-events/arch/x86/jaketown/uncore-memory.json79
-rw-r--r--tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json248
-rw-r--r--tools/perf/pmu-events/arch/x86/jaketown/virtual-memory.json149
-rw-r--r--tools/perf/pmu-events/arch/x86/knightslanding/cache.json2305
-rw-r--r--tools/perf/pmu-events/arch/x86/knightslanding/frontend.json34
-rw-r--r--tools/perf/pmu-events/arch/x86/knightslanding/memory.json1110
-rw-r--r--tools/perf/pmu-events/arch/x86/knightslanding/pipeline.json435
-rw-r--r--tools/perf/pmu-events/arch/x86/knightslanding/uncore-memory.json42
-rw-r--r--tools/perf/pmu-events/arch/x86/knightslanding/virtual-memory.json65
-rw-r--r--tools/perf/pmu-events/arch/x86/mapfile.csv35
-rw-r--r--tools/perf/pmu-events/arch/x86/nehalemep/cache.json3229
-rw-r--r--tools/perf/pmu-events/arch/x86/nehalemep/floating-point.json229
-rw-r--r--tools/perf/pmu-events/arch/x86/nehalemep/frontend.json26
-rw-r--r--tools/perf/pmu-events/arch/x86/nehalemep/memory.json739
-rw-r--r--tools/perf/pmu-events/arch/x86/nehalemep/other.json210
-rw-r--r--tools/perf/pmu-events/arch/x86/nehalemep/pipeline.json881
-rw-r--r--tools/perf/pmu-events/arch/x86/nehalemep/virtual-memory.json109
-rw-r--r--tools/perf/pmu-events/arch/x86/nehalemex/cache.json3184
-rw-r--r--tools/perf/pmu-events/arch/x86/nehalemex/floating-point.json229
-rw-r--r--tools/perf/pmu-events/arch/x86/nehalemex/frontend.json26
-rw-r--r--tools/perf/pmu-events/arch/x86/nehalemex/memory.json739
-rw-r--r--tools/perf/pmu-events/arch/x86/nehalemex/other.json210
-rw-r--r--tools/perf/pmu-events/arch/x86/nehalemex/pipeline.json881
-rw-r--r--tools/perf/pmu-events/arch/x86/nehalemex/virtual-memory.json109
-rw-r--r--tools/perf/pmu-events/arch/x86/sandybridge/cache.json1879
-rw-r--r--tools/perf/pmu-events/arch/x86/sandybridge/floating-point.json138
-rw-r--r--tools/perf/pmu-events/arch/x86/sandybridge/frontend.json305
-rw-r--r--tools/perf/pmu-events/arch/x86/sandybridge/memory.json445
-rw-r--r--tools/perf/pmu-events/arch/x86/sandybridge/other.json58
-rw-r--r--tools/perf/pmu-events/arch/x86/sandybridge/pipeline.json1220
-rw-r--r--tools/perf/pmu-events/arch/x86/sandybridge/virtual-memory.json149
-rw-r--r--tools/perf/pmu-events/arch/x86/silvermont/cache.json811
-rw-r--r--tools/perf/pmu-events/arch/x86/silvermont/frontend.json47
-rw-r--r--tools/perf/pmu-events/arch/x86/silvermont/memory.json11
-rw-r--r--tools/perf/pmu-events/arch/x86/silvermont/pipeline.json359
-rw-r--r--tools/perf/pmu-events/arch/x86/silvermont/virtual-memory.json69
-rw-r--r--tools/perf/pmu-events/arch/x86/skylake/cache.json4299
-rw-r--r--tools/perf/pmu-events/arch/x86/skylake/floating-point.json68
-rw-r--r--tools/perf/pmu-events/arch/x86/skylake/frontend.json472
-rw-r--r--tools/perf/pmu-events/arch/x86/skylake/memory.json2309
-rw-r--r--tools/perf/pmu-events/arch/x86/skylake/other.json12
-rw-r--r--tools/perf/pmu-events/arch/x86/skylake/pipeline.json939
-rw-r--r--tools/perf/pmu-events/arch/x86/skylake/virtual-memory.json272
-rw-r--r--tools/perf/pmu-events/arch/x86/westmereep-dp/cache.json2817
-rw-r--r--tools/perf/pmu-events/arch/x86/westmereep-dp/floating-point.json229
-rw-r--r--tools/perf/pmu-events/arch/x86/westmereep-dp/frontend.json26
-rw-r--r--tools/perf/pmu-events/arch/x86/westmereep-dp/memory.json758
-rw-r--r--tools/perf/pmu-events/arch/x86/westmereep-dp/other.json287
-rw-r--r--tools/perf/pmu-events/arch/x86/westmereep-dp/pipeline.json899
-rw-r--r--tools/perf/pmu-events/arch/x86/westmereep-dp/virtual-memory.json173
-rw-r--r--tools/perf/pmu-events/arch/x86/westmereep-sp/cache.json3233
-rw-r--r--tools/perf/pmu-events/arch/x86/westmereep-sp/floating-point.json229
-rw-r--r--tools/perf/pmu-events/arch/x86/westmereep-sp/frontend.json26
-rw-r--r--tools/perf/pmu-events/arch/x86/westmereep-sp/memory.json739
-rw-r--r--tools/perf/pmu-events/arch/x86/westmereep-sp/other.json287
-rw-r--r--tools/perf/pmu-events/arch/x86/westmereep-sp/pipeline.json899
-rw-r--r--tools/perf/pmu-events/arch/x86/westmereep-sp/virtual-memory.json149
-rw-r--r--tools/perf/pmu-events/arch/x86/westmereex/cache.json3225
-rw-r--r--tools/perf/pmu-events/arch/x86/westmereex/floating-point.json229
-rw-r--r--tools/perf/pmu-events/arch/x86/westmereex/frontend.json26
-rw-r--r--tools/perf/pmu-events/arch/x86/westmereex/memory.json747
-rw-r--r--tools/perf/pmu-events/arch/x86/westmereex/other.json287
-rw-r--r--tools/perf/pmu-events/arch/x86/westmereex/pipeline.json905
-rw-r--r--tools/perf/pmu-events/arch/x86/westmereex/virtual-memory.json173
-rw-r--r--tools/perf/pmu-events/jevents.c84
-rw-r--r--tools/perf/pmu-events/jevents.h4
-rw-r--r--tools/perf/pmu-events/json.c2
-rw-r--r--tools/perf/pmu-events/pmu-events.h3
-rw-r--r--tools/perf/tests/Build3
-rw-r--r--tools/perf/tests/attr.c2
-rw-r--r--tools/perf/tests/backward-ring-buffer.c2
-rw-r--r--tools/perf/tests/bpf.c50
-rw-r--r--tools/perf/tests/builtin-test.c115
-rw-r--r--tools/perf/tests/clang.c46
-rw-r--r--tools/perf/tests/code-reading.c2
-rw-r--r--tools/perf/tests/fdarray.c2
-rw-r--r--tools/perf/tests/llvm.c12
-rw-r--r--tools/perf/tests/llvm.h7
-rw-r--r--tools/perf/tests/make8
-rw-r--r--tools/perf/tests/parse-events.c10
-rw-r--r--tools/perf/tests/parse-no-sample-id-all.c19
-rw-r--r--tools/perf/tests/perf-hooks.c48
-rw-r--r--tools/perf/tests/perf-record.c6
-rw-r--r--tools/perf/tests/python-use.c2
-rw-r--r--tools/perf/tests/tests.h6
-rw-r--r--tools/perf/tests/thread-map.c44
-rw-r--r--tools/perf/tests/topology.c4
-rw-r--r--tools/perf/tests/unit_number__scnprintf.c37
-rw-r--r--tools/perf/tests/vmlinux-kallsyms.c2
-rw-r--r--tools/perf/trace/beauty/mmap.c2
-rw-r--r--tools/perf/ui/browsers/annotate.c31
-rw-r--r--tools/perf/ui/browsers/hists.c87
-rw-r--r--tools/perf/ui/browsers/hists.h1
-rw-r--r--tools/perf/ui/browsers/map.c6
-rw-r--r--tools/perf/ui/gtk/annotate.c2
-rw-r--r--tools/perf/ui/helpline.c10
-rw-r--r--tools/perf/ui/helpline.h1
-rw-r--r--tools/perf/ui/hist.c12
-rw-r--r--tools/perf/ui/setup.c1
-rw-r--r--tools/perf/ui/stdio/hist.c35
-rw-r--r--tools/perf/util/Build8
-rw-r--r--tools/perf/util/annotate.c415
-rw-r--r--tools/perf/util/annotate.h28
-rw-r--r--tools/perf/util/bpf-loader.c37
-rw-r--r--tools/perf/util/c++/Build2
-rw-r--r--tools/perf/util/c++/clang-c.h43
-rw-r--r--tools/perf/util/c++/clang-test.cpp62
-rw-r--r--tools/perf/util/c++/clang.cpp195
-rw-r--r--tools/perf/util/c++/clang.h26
-rw-r--r--tools/perf/util/callchain.c259
-rw-r--r--tools/perf/util/callchain.h35
-rw-r--r--tools/perf/util/cgroup.c26
-rw-r--r--tools/perf/util/config.c43
-rw-r--r--tools/perf/util/config.h4
-rw-r--r--tools/perf/util/cpumap.c22
-rw-r--r--tools/perf/util/cpumap.h1
-rw-r--r--tools/perf/util/data-convert-bt.c7
-rw-r--r--tools/perf/util/debug.c17
-rw-r--r--tools/perf/util/debug.h1
-rw-r--r--tools/perf/util/dso.c52
-rw-r--r--tools/perf/util/env.c2
-rw-r--r--tools/perf/util/event.c2
-rw-r--r--tools/perf/util/event.h3
-rw-r--r--tools/perf/util/evlist.c12
-rw-r--r--tools/perf/util/evlist.h2
-rw-r--r--tools/perf/util/evsel.c140
-rw-r--r--tools/perf/util/evsel.h5
-rw-r--r--tools/perf/util/evsel_fprintf.c24
-rw-r--r--tools/perf/util/genelf.c113
-rw-r--r--tools/perf/util/genelf.h5
-rw-r--r--tools/perf/util/header.c59
-rw-r--r--tools/perf/util/hist.c18
-rw-r--r--tools/perf/util/hist.h8
-rw-r--r--tools/perf/util/intel-bts.c9
-rw-r--r--tools/perf/util/intel-pt-decoder/Build6
-rw-r--r--tools/perf/util/intel-pt-decoder/intel-pt-decoder.c7
-rw-r--r--tools/perf/util/intel-pt-decoder/intel-pt-decoder.h1
-rw-r--r--tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c15
-rw-r--r--tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.h6
-rw-r--r--tools/perf/util/intel-pt-decoder/intel-pt-log.c4
-rw-r--r--tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c2
-rw-r--r--tools/perf/util/intel-pt.c23
-rw-r--r--tools/perf/util/jitdump.c82
-rw-r--r--tools/perf/util/jitdump.h12
-rw-r--r--tools/perf/util/llvm-utils.c82
-rw-r--r--tools/perf/util/llvm-utils.h6
-rw-r--r--tools/perf/util/machine.c107
-rw-r--r--tools/perf/util/machine.h1
-rw-r--r--tools/perf/util/map.c21
-rw-r--r--tools/perf/util/mem-events.c136
-rw-r--r--tools/perf/util/mem-events.h38
-rw-r--r--tools/perf/util/parse-branch-options.c85
-rw-r--r--tools/perf/util/parse-branch-options.h3
-rw-r--r--tools/perf/util/parse-events.c170
-rw-r--r--tools/perf/util/parse-events.h2
-rw-r--r--tools/perf/util/parse-events.y49
-rw-r--r--tools/perf/util/perf-hooks-list.h3
-rw-r--r--tools/perf/util/perf-hooks.c88
-rw-r--r--tools/perf/util/perf-hooks.h39
-rw-r--r--tools/perf/util/pmu.c146
-rw-r--r--tools/perf/util/pmu.h1
-rw-r--r--tools/perf/util/probe-event.c181
-rw-r--r--tools/perf/util/probe-event.h2
-rw-r--r--tools/perf/util/probe-finder.c19
-rw-r--r--tools/perf/util/probe-finder.h3
-rw-r--r--tools/perf/util/python-ext-sources1
-rw-r--r--tools/perf/util/quote.c2
-rw-r--r--tools/perf/util/scripting-engines/Build2
-rw-r--r--tools/perf/util/scripting-engines/trace-event-perl.c11
-rw-r--r--tools/perf/util/scripting-engines/trace-event-python.c5
-rw-r--r--tools/perf/util/session.c16
-rw-r--r--tools/perf/util/setup.py9
-rw-r--r--tools/perf/util/sort.c10
-rw-r--r--tools/perf/util/sort.h3
-rw-r--r--tools/perf/util/stat.c2
-rw-r--r--tools/perf/util/strfilter.c1
-rw-r--r--tools/perf/util/string.c23
-rw-r--r--tools/perf/util/symbol-elf.c8
-rw-r--r--tools/perf/util/symbol.c17
-rw-r--r--tools/perf/util/symbol.h11
-rw-r--r--tools/perf/util/symbol_fprintf.c13
-rw-r--r--tools/perf/util/thread_map.c24
-rw-r--r--tools/perf/util/thread_map.h1
-rw-r--r--tools/perf/util/time-utils.c119
-rw-r--r--tools/perf/util/time-utils.h14
-rw-r--r--tools/perf/util/trace-event-info.c71
-rw-r--r--tools/perf/util/trace-event-parse.c17
-rw-r--r--tools/perf/util/trace-event-read.c77
-rw-r--r--tools/perf/util/trace-event-scripting.c39
-rw-r--r--tools/perf/util/trace-event.h1
-rw-r--r--tools/perf/util/unwind-libunwind-local.c58
-rw-r--r--tools/perf/util/util-cxx.h26
-rw-r--r--tools/perf/util/util.c103
-rw-r--r--tools/perf/util/util.h9
-rw-r--r--tools/perf/util/values.c81
-rw-r--r--tools/perf/util/values.h4
-rw-r--r--tools/power/acpi/common/cmfsize.c2
-rw-r--r--tools/power/acpi/common/getopt.c2
-rw-r--r--tools/power/acpi/os_specific/service_layers/oslinuxtbl.c2
-rw-r--r--tools/power/acpi/os_specific/service_layers/osunixdir.c2
-rw-r--r--tools/power/acpi/os_specific/service_layers/osunixmap.c2
-rw-r--r--tools/power/acpi/os_specific/service_layers/osunixxf.c37
-rw-r--r--tools/power/acpi/tools/acpidump/acpidump.h2
-rw-r--r--tools/power/acpi/tools/acpidump/apdump.c2
-rw-r--r--tools/power/acpi/tools/acpidump/apfiles.c2
-rw-r--r--tools/power/acpi/tools/acpidump/apmain.c2
-rw-r--r--tools/power/acpi/tools/ec/ec_access.c2
-rw-r--r--tools/power/cpupower/Makefile3
-rw-r--r--tools/power/cpupower/debug/kernel/Makefile3
-rw-r--r--tools/power/cpupower/utils/cpufreq-info.c21
-rwxr-xr-xtools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py569
-rw-r--r--tools/power/x86/turbostat/Makefile1
-rw-r--r--tools/power/x86/turbostat/turbostat.8277
-rw-r--r--tools/power/x86/turbostat/turbostat.c2569
-rw-r--r--tools/scripts/Makefile.include17
-rw-r--r--tools/spi/spidev_test.c2
-rwxr-xr-xtools/testing/ktest/ktest.pl8
-rw-r--r--tools/testing/nvdimm/test/nfit.c44
-rw-r--r--tools/testing/radix-tree/.gitignore4
-rw-r--r--tools/testing/radix-tree/Makefile50
-rw-r--r--tools/testing/radix-tree/benchmark.c257
-rw-r--r--tools/testing/radix-tree/find_next_bit.c57
-rw-r--r--tools/testing/radix-tree/generated/autoconf.h2
-rw-r--r--tools/testing/radix-tree/idr-test.c516
-rw-r--r--tools/testing/radix-tree/iteration_check.c123
-rw-r--r--tools/testing/radix-tree/linux.c90
-rw-r--r--tools/testing/radix-tree/linux/bitops.h150
-rw-r--r--tools/testing/radix-tree/linux/bitops/__ffs.h43
-rw-r--r--tools/testing/radix-tree/linux/bitops/ffs.h41
-rw-r--r--tools/testing/radix-tree/linux/bitops/find.h13
-rw-r--r--tools/testing/radix-tree/linux/bitops/fls.h41
-rw-r--r--tools/testing/radix-tree/linux/bitops/fls64.h14
-rw-r--r--tools/testing/radix-tree/linux/bitops/hweight.h11
-rw-r--r--tools/testing/radix-tree/linux/bitops/le.h53
-rw-r--r--tools/testing/radix-tree/linux/bitops/non-atomic.h111
-rw-r--r--tools/testing/radix-tree/linux/bug.h2
-rw-r--r--tools/testing/radix-tree/linux/cpu.h22
-rw-r--r--tools/testing/radix-tree/linux/export.h2
-rw-r--r--tools/testing/radix-tree/linux/gfp.h26
-rw-r--r--tools/testing/radix-tree/linux/idr.h1
-rw-r--r--tools/testing/radix-tree/linux/init.h2
-rw-r--r--tools/testing/radix-tree/linux/kernel.h37
-rw-r--r--tools/testing/radix-tree/linux/mempool.h16
-rw-r--r--tools/testing/radix-tree/linux/notifier.h8
-rw-r--r--tools/testing/radix-tree/linux/percpu.h5
-rw-r--r--tools/testing/radix-tree/linux/preempt.h16
-rw-r--r--tools/testing/radix-tree/linux/radix-tree.h25
-rw-r--r--tools/testing/radix-tree/linux/slab.h11
-rw-r--r--tools/testing/radix-tree/linux/types.h25
-rw-r--r--tools/testing/radix-tree/main.c105
-rw-r--r--tools/testing/radix-tree/multiorder.c361
-rw-r--r--tools/testing/radix-tree/rcupdate.c86
-rw-r--r--tools/testing/radix-tree/regression1.c4
-rw-r--r--tools/testing/radix-tree/regression2.c13
-rw-r--r--tools/testing/radix-tree/regression3.c36
-rw-r--r--tools/testing/radix-tree/tag_check.c63
-rw-r--r--tools/testing/radix-tree/test.c112
-rw-r--r--tools/testing/radix-tree/test.h24
-rw-r--r--tools/testing/selftests/.gitignore1
-rw-r--r--tools/testing/selftests/Makefile46
-rw-r--r--tools/testing/selftests/bpf/.gitignore5
-rw-r--r--tools/testing/selftests/bpf/Makefile20
-rw-r--r--tools/testing/selftests/bpf/bpf_util.h38
-rw-r--r--tools/testing/selftests/bpf/config5
-rwxr-xr-xtools/testing/selftests/bpf/test_kmod.sh39
-rw-r--r--tools/testing/selftests/bpf/test_lpm_map.c358
-rw-r--r--tools/testing/selftests/bpf/test_lru_map.c602
-rw-r--r--tools/testing/selftests/bpf/test_maps.c530
-rw-r--r--tools/testing/selftests/bpf/test_tag.c203
-rw-r--r--tools/testing/selftests/bpf/test_verifier.c4684
-rw-r--r--tools/testing/selftests/breakpoints/Makefile11
-rw-r--r--tools/testing/selftests/breakpoints/breakpoint_test_arm64.c236
-rw-r--r--tools/testing/selftests/capabilities/Makefile11
-rw-r--r--tools/testing/selftests/cpufreq/Makefile8
-rwxr-xr-xtools/testing/selftests/cpufreq/cpu.sh84
-rwxr-xr-xtools/testing/selftests/cpufreq/cpufreq.sh241
-rwxr-xr-xtools/testing/selftests/cpufreq/governor.sh153
-rwxr-xr-xtools/testing/selftests/cpufreq/main.sh194
-rwxr-xr-xtools/testing/selftests/cpufreq/module.sh243
-rwxr-xr-xtools/testing/selftests/cpufreq/special-tests.sh115
-rwxr-xr-xtools/testing/selftests/drivers/gpu/drm_mm.sh15
-rwxr-xr-xtools/testing/selftests/drivers/gpu/i915.sh14
-rw-r--r--tools/testing/selftests/efivarfs/Makefile8
-rw-r--r--tools/testing/selftests/exec/Makefile32
-rw-r--r--tools/testing/selftests/firmware/Makefile2
-rwxr-xr-xtools/testing/selftests/firmware/fw_fallback.sh224
-rwxr-xr-xtools/testing/selftests/firmware/fw_filesystem.sh25
-rwxr-xr-xtools/testing/selftests/firmware/fw_userhelper.sh99
-rw-r--r--tools/testing/selftests/ftrace/.gitignore1
-rw-r--r--tools/testing/selftests/ftrace/Makefile6
-rwxr-xr-xtools/testing/selftests/ftrace/ftracetest16
-rw-r--r--tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc49
-rw-r--r--tools/testing/selftests/ftrace/test.d/functions28
-rw-r--r--tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc37
-rw-r--r--tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-mod.tc2
-rw-r--r--tools/testing/selftests/ftrace/test.d/trigger/trigger-snapshot.tc5
-rw-r--r--tools/testing/selftests/futex/Makefile21
-rw-r--r--tools/testing/selftests/futex/README2
-rw-r--r--tools/testing/selftests/futex/functional/Makefile17
-rw-r--r--tools/testing/selftests/futex/include/logging.h1
-rw-r--r--tools/testing/selftests/gpio/.gitignore1
-rw-r--r--tools/testing/selftests/gpio/Makefile23
-rw-r--r--tools/testing/selftests/gpio/gpio-mockup-chardev.c324
-rwxr-xr-xtools/testing/selftests/gpio/gpio-mockup-sysfs.sh134
-rwxr-xr-xtools/testing/selftests/gpio/gpio-mockup.sh201
-rw-r--r--tools/testing/selftests/intel_pstate/Makefile13
-rw-r--r--tools/testing/selftests/intel_pstate/aperf.c2
-rw-r--r--tools/testing/selftests/ipc/.gitignore1
-rw-r--r--tools/testing/selftests/ipc/Makefile7
-rw-r--r--tools/testing/selftests/kcmp/Makefile6
-rw-r--r--tools/testing/selftests/lib.mk40
-rwxr-xr-xtools/testing/selftests/lib/prime_numbers.sh15
-rw-r--r--tools/testing/selftests/locking/ww_mutex.sh10
-rw-r--r--tools/testing/selftests/membarrier/Makefile6
-rw-r--r--tools/testing/selftests/memfd/Makefile15
-rw-r--r--tools/testing/selftests/mount/Makefile7
-rw-r--r--tools/testing/selftests/mqueue/Makefile6
-rw-r--r--tools/testing/selftests/net/.gitignore1
-rw-r--r--tools/testing/selftests/net/Makefile16
-rw-r--r--tools/testing/selftests/net/psock_lib.h39
-rw-r--r--tools/testing/selftests/net/psock_tpacket.c97
-rw-r--r--tools/testing/selftests/net/reuseport_bpf_numa.c255
-rwxr-xr-xtools/testing/selftests/net/run_netsocktests2
-rw-r--r--tools/testing/selftests/nsfs/.gitignore2
-rw-r--r--tools/testing/selftests/nsfs/Makefile9
-rw-r--r--tools/testing/selftests/powerpc/Makefile19
-rw-r--r--tools/testing/selftests/powerpc/alignment/Makefile9
-rw-r--r--tools/testing/selftests/powerpc/benchmarks/.gitignore3
-rw-r--r--tools/testing/selftests/powerpc/benchmarks/Makefile17
-rw-r--r--tools/testing/selftests/powerpc/benchmarks/context_switch.c2
-rw-r--r--tools/testing/selftests/powerpc/benchmarks/null_syscall.c157
-rw-r--r--tools/testing/selftests/powerpc/context_switch/Makefile9
-rw-r--r--tools/testing/selftests/powerpc/copyloops/Makefile19
-rw-r--r--tools/testing/selftests/powerpc/copyloops/asm/ppc_asm.h2
-rw-r--r--tools/testing/selftests/powerpc/copyloops/validate.c2
-rw-r--r--tools/testing/selftests/powerpc/dscr/Makefile13
-rw-r--r--tools/testing/selftests/powerpc/dscr/dscr.h10
-rw-r--r--tools/testing/selftests/powerpc/harness.c6
-rw-r--r--tools/testing/selftests/powerpc/include/basic_asm.h (renamed from tools/testing/selftests/powerpc/basic_asm.h)37
-rw-r--r--tools/testing/selftests/powerpc/include/fpu_asm.h (renamed from tools/testing/selftests/powerpc/fpu_asm.h)0
-rw-r--r--tools/testing/selftests/powerpc/include/gpr_asm.h (renamed from tools/testing/selftests/powerpc/gpr_asm.h)0
-rw-r--r--tools/testing/selftests/powerpc/include/instructions.h (renamed from tools/testing/selftests/powerpc/instructions.h)0
-rw-r--r--tools/testing/selftests/powerpc/include/reg.h145
-rw-r--r--tools/testing/selftests/powerpc/include/subunit.h (renamed from tools/testing/selftests/powerpc/subunit.h)0
-rw-r--r--tools/testing/selftests/powerpc/include/utils.h (renamed from tools/testing/selftests/powerpc/utils.h)0
-rw-r--r--tools/testing/selftests/powerpc/include/vmx_asm.h (renamed from tools/testing/selftests/powerpc/vmx_asm.h)0
-rw-r--r--tools/testing/selftests/powerpc/include/vsx_asm.h (renamed from tools/testing/selftests/powerpc/vsx_asm.h)0
-rw-r--r--tools/testing/selftests/powerpc/lib/reg.S397
-rw-r--r--tools/testing/selftests/powerpc/math/Makefile29
-rw-r--r--tools/testing/selftests/powerpc/math/fpu_asm.S4
-rw-r--r--tools/testing/selftests/powerpc/math/vmx_asm.S4
-rw-r--r--tools/testing/selftests/powerpc/math/vsx_asm.S4
-rw-r--r--tools/testing/selftests/powerpc/mm/Makefile18
-rw-r--r--tools/testing/selftests/powerpc/pmu/Makefile26
-rw-r--r--tools/testing/selftests/powerpc/pmu/ebb/.gitignore2
-rw-r--r--tools/testing/selftests/powerpc/pmu/ebb/Makefile17
-rw-r--r--tools/testing/selftests/powerpc/pmu/ebb/ebb_lmr.c143
-rw-r--r--tools/testing/selftests/powerpc/pmu/ebb/ebb_lmr.h39
-rw-r--r--tools/testing/selftests/powerpc/pmu/ebb/ebb_lmr_regs.c37
-rw-r--r--tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c2
-rw-r--r--tools/testing/selftests/powerpc/pmu/lib.c6
-rw-r--r--tools/testing/selftests/powerpc/primitives/Makefile9
-rw-r--r--tools/testing/selftests/powerpc/primitives/asm/firmware.h0
l---------tools/testing/selftests/powerpc/primitives/asm/ppc_asm.h1
-rw-r--r--tools/testing/selftests/powerpc/primitives/asm/processor.h0
-rw-r--r--tools/testing/selftests/powerpc/primitives/linux/stringify.h0
-rw-r--r--tools/testing/selftests/powerpc/primitives/load_unaligned_zeropad.c21
-rw-r--r--tools/testing/selftests/powerpc/ptrace/.gitignore10
-rw-r--r--tools/testing/selftests/powerpc/ptrace/Makefile14
-rw-r--r--tools/testing/selftests/powerpc/ptrace/ptrace-gpr.c123
-rw-r--r--tools/testing/selftests/powerpc/ptrace/ptrace-gpr.h74
-rw-r--r--tools/testing/selftests/powerpc/ptrace/ptrace-tar.c135
-rw-r--r--tools/testing/selftests/powerpc/ptrace/ptrace-tar.h50
-rw-r--r--tools/testing/selftests/powerpc/ptrace/ptrace-tm-gpr.c158
-rw-r--r--tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-gpr.c169
-rw-r--r--tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-tar.c174
-rw-r--r--tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-vsx.c185
-rw-r--r--tools/testing/selftests/powerpc/ptrace/ptrace-tm-spr.c168
-rw-r--r--tools/testing/selftests/powerpc/ptrace/ptrace-tm-tar.c160
-rw-r--r--tools/testing/selftests/powerpc/ptrace/ptrace-tm-vsx.c168
-rw-r--r--tools/testing/selftests/powerpc/ptrace/ptrace-vsx.c117
-rw-r--r--tools/testing/selftests/powerpc/ptrace/ptrace-vsx.h127
-rw-r--r--tools/testing/selftests/powerpc/ptrace/ptrace.h711
-rw-r--r--tools/testing/selftests/powerpc/reg.h60
-rw-r--r--tools/testing/selftests/powerpc/signal/signal.S2
-rw-r--r--tools/testing/selftests/powerpc/stringloops/Makefile9
-rw-r--r--tools/testing/selftests/powerpc/stringloops/memcmp.c2
-rw-r--r--tools/testing/selftests/powerpc/switch_endian/Makefile17
-rw-r--r--tools/testing/selftests/powerpc/syscalls/Makefile9
-rw-r--r--tools/testing/selftests/powerpc/tm/Makefile18
-rw-r--r--tools/testing/selftests/powerpc/tm/tm-signal.S10
-rw-r--r--tools/testing/selftests/powerpc/tm/tm.h2
-rw-r--r--tools/testing/selftests/powerpc/vphn/Makefile10
-rw-r--r--tools/testing/selftests/pstore/Makefile4
-rw-r--r--tools/testing/selftests/ptrace/Makefile8
-rw-r--r--tools/testing/selftests/rcutorture/.gitignore2
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm.sh5
-rw-r--r--tools/testing/selftests/rcutorture/configs/lock/CFLIST1
-rw-r--r--tools/testing/selftests/rcutorture/configs/lock/LOCK076
-rw-r--r--tools/testing/selftests/rcutorture/configs/lock/LOCK07.boot1
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/CFcommon3
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/TINY011
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/TINY023
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/TREE013
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/TREE024
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/TREE033
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/TREE044
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/TREE053
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/TREE063
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/TREE073
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/TREE084
-rw-r--r--tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt33
-rw-r--r--tools/testing/selftests/rcutorture/formal/srcu-cbmc/.gitignore1
-rw-r--r--tools/testing/selftests/rcutorture/formal/srcu-cbmc/Makefile16
-rw-r--r--tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/delay.h0
-rw-r--r--tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/export.h0
-rw-r--r--tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/mutex.h0
-rw-r--r--tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/percpu.h0
-rw-r--r--tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/preempt.h0
-rw-r--r--tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/rcupdate.h0
-rw-r--r--tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/sched.h0
-rw-r--r--tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/smp.h0
-rw-r--r--tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/workqueue.h0
-rw-r--r--tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/uapi/linux/types.h0
-rw-r--r--tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/.gitignore1
-rw-r--r--tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/kconfig.h1
-rw-r--r--tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/types.h155
-rwxr-xr-xtools/testing/selftests/rcutorture/formal/srcu-cbmc/modify_srcu.awk375
-rw-r--r--tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/assume.h16
-rw-r--r--tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/barriers.h41
-rw-r--r--tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/bug_on.h13
-rw-r--r--tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/combined_source.c13
-rw-r--r--tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/config.h27
-rw-r--r--tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/include_srcu.c31
-rw-r--r--tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/int_typedefs.h33
-rw-r--r--tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/locks.h220
-rw-r--r--tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/misc.c11
-rw-r--r--tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/misc.h58
-rw-r--r--tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/percpu.h92
-rw-r--r--tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/preempt.c78
-rw-r--r--tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/preempt.h58
-rw-r--r--tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/simple_sync_srcu.c50
-rw-r--r--tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/workqueues.h102
-rw-r--r--tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/.gitignore1
-rw-r--r--tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/Makefile11
-rw-r--r--tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/assert_end.fail1
-rw-r--r--tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/force.fail1
-rw-r--r--tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/force2.fail1
-rw-r--r--tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/force3.fail1
-rw-r--r--tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/main.pass0
-rw-r--r--tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/test.c72
-rwxr-xr-xtools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/test_script.sh102
-rw-r--r--tools/testing/selftests/seccomp/Makefile6
-rw-r--r--tools/testing/selftests/sigaltstack/.gitignore1
-rw-r--r--tools/testing/selftests/sigaltstack/Makefile5
-rw-r--r--tools/testing/selftests/sigaltstack/sas.c7
-rw-r--r--tools/testing/selftests/size/Makefile10
-rw-r--r--tools/testing/selftests/splice/Makefile8
-rw-r--r--tools/testing/selftests/splice/default_file_splice_read.c8
-rwxr-xr-xtools/testing/selftests/splice/default_file_splice_read.sh7
-rw-r--r--tools/testing/selftests/sync/.gitignore1
-rw-r--r--tools/testing/selftests/sync/Makefile24
-rw-r--r--tools/testing/selftests/sync/sw_sync.h46
-rw-r--r--tools/testing/selftests/sync/sync.c221
-rw-r--r--tools/testing/selftests/sync/sync.h40
-rw-r--r--tools/testing/selftests/sync/sync_alloc.c74
-rw-r--r--tools/testing/selftests/sync/sync_fence.c132
-rw-r--r--tools/testing/selftests/sync/sync_merge.c60
-rw-r--r--tools/testing/selftests/sync/sync_stress_consumer.c185
-rw-r--r--tools/testing/selftests/sync/sync_stress_merge.c115
-rw-r--r--tools/testing/selftests/sync/sync_stress_parallelism.c111
-rw-r--r--tools/testing/selftests/sync/sync_test.c79
-rw-r--r--tools/testing/selftests/sync/sync_wait.c91
-rw-r--r--tools/testing/selftests/sync/synctest.h66
-rw-r--r--tools/testing/selftests/timers/.gitignore1
-rw-r--r--tools/testing/selftests/timers/Makefile10
-rw-r--r--tools/testing/selftests/timers/skew_consistency.c2
-rw-r--r--tools/testing/selftests/vm/Makefile50
-rwxr-xr-xtools/testing/selftests/vm/run_vmtests24
-rw-r--r--tools/testing/selftests/vm/userfaultfd.c484
-rw-r--r--tools/testing/selftests/x86/Makefile23
-rw-r--r--tools/testing/selftests/x86/fsgsbase.c2
-rw-r--r--tools/testing/selftests/x86/ioperm.c170
-rw-r--r--tools/testing/selftests/x86/ldt_gdt.c16
-rw-r--r--tools/testing/selftests/x86/protection_keys.c21
-rw-r--r--tools/testing/selftests/x86/ptrace_syscall.c3
-rw-r--r--tools/testing/selftests/x86/single_step_syscall.c5
-rw-r--r--tools/testing/selftests/x86/sysret_rip.c195
-rw-r--r--tools/testing/selftests/x86/test_vdso.c123
-rw-r--r--tools/testing/selftests/zram/Makefile3
-rw-r--r--tools/usb/ffs-test.c52
-rw-r--r--tools/usb/usbip/.gitignore4
-rw-r--r--tools/usb/usbip/README57
-rw-r--r--tools/usb/usbip/src/usbipd.c7
-rwxr-xr-xtools/usb/usbip/vudc/vudc_server_example.sh107
-rw-r--r--tools/virtio/linux/compiler.h2
-rw-r--r--tools/virtio/linux/uaccess.h9
-rw-r--r--tools/virtio/ringtest/main.h12
-rwxr-xr-xtools/virtio/ringtest/run-on-all.sh5
-rw-r--r--tools/vm/Makefile8
731 files changed, 126288 insertions, 4880 deletions
diff --git a/tools/Makefile b/tools/Makefile
index daa8fb3e4363..00caacd3ed92 100644
--- a/tools/Makefile
+++ b/tools/Makefile
@@ -17,6 +17,7 @@ help:
@echo ' hv - tools used when in Hyper-V clients'
@echo ' iio - IIO tools'
@echo ' kvm_stat - top-like utility for displaying kvm statistics'
+ @echo ' leds - LEDs tools'
@echo ' lguest - a minimal 32-bit x86 hypervisor'
@echo ' net - misc networking tools'
@echo ' perf - Linux performance measurement and analysis tool'
@@ -56,7 +57,7 @@ acpi: FORCE
cpupower: FORCE
$(call descend,power/$@)
-cgroup firewire hv guest spi usb virtio vm net iio gpio objtool: FORCE
+cgroup firewire hv guest spi usb virtio vm net iio gpio objtool leds: FORCE
$(call descend,$@)
liblockdep: FORCE
@@ -126,7 +127,7 @@ acpi_clean:
cpupower_clean:
$(call descend,power/cpupower,clean)
-cgroup_clean hv_clean firewire_clean lguest_clean spi_clean usb_clean virtio_clean vm_clean net_clean iio_clean gpio_clean objtool_clean:
+cgroup_clean hv_clean firewire_clean lguest_clean spi_clean usb_clean virtio_clean vm_clean net_clean iio_clean gpio_clean objtool_clean leds_clean:
$(call descend,$(@:_clean=),clean)
liblockdep_clean:
@@ -164,6 +165,6 @@ clean: acpi_clean cgroup_clean cpupower_clean hv_clean firewire_clean lguest_cle
perf_clean selftests_clean turbostat_clean spi_clean usb_clean virtio_clean \
vm_clean net_clean iio_clean x86_energy_perf_policy_clean tmon_clean \
freefall_clean build_clean libbpf_clean libsubcmd_clean liblockdep_clean \
- gpio_clean objtool_clean
+ gpio_clean objtool_clean leds_clean
.PHONY: FORCE
diff --git a/tools/arch/arm/include/uapi/asm/kvm.h b/tools/arch/arm/include/uapi/asm/kvm.h
index a2b3eb313a25..af05f8e0903e 100644
--- a/tools/arch/arm/include/uapi/asm/kvm.h
+++ b/tools/arch/arm/include/uapi/asm/kvm.h
@@ -84,6 +84,15 @@ struct kvm_regs {
#define KVM_VGIC_V2_DIST_SIZE 0x1000
#define KVM_VGIC_V2_CPU_SIZE 0x2000
+/* Supported VGICv3 address types */
+#define KVM_VGIC_V3_ADDR_TYPE_DIST 2
+#define KVM_VGIC_V3_ADDR_TYPE_REDIST 3
+#define KVM_VGIC_ITS_ADDR_TYPE 4
+
+#define KVM_VGIC_V3_DIST_SIZE SZ_64K
+#define KVM_VGIC_V3_REDIST_SIZE (2 * SZ_64K)
+#define KVM_VGIC_V3_ITS_SIZE (2 * SZ_64K)
+
#define KVM_ARM_VCPU_POWER_OFF 0 /* CPU is started in OFF state */
#define KVM_ARM_VCPU_PSCI_0_2 1 /* CPU uses PSCI v0.2 */
diff --git a/tools/arch/powerpc/include/uapi/asm/kvm.h b/tools/arch/powerpc/include/uapi/asm/kvm.h
index c93cf35ce379..3603b6f51b11 100644
--- a/tools/arch/powerpc/include/uapi/asm/kvm.h
+++ b/tools/arch/powerpc/include/uapi/asm/kvm.h
@@ -573,6 +573,10 @@ struct kvm_get_htab_header {
#define KVM_REG_PPC_SPRG9 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xba)
#define KVM_REG_PPC_DBSR (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xbb)
+/* POWER9 registers */
+#define KVM_REG_PPC_TIDR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbc)
+#define KVM_REG_PPC_PSSCR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbd)
+
/* Transactional Memory checkpointed state:
* This is all GPRs, all VSX regs and a subset of SPRs
*/
@@ -596,6 +600,7 @@ struct kvm_get_htab_header {
#define KVM_REG_PPC_TM_VSCR (KVM_REG_PPC_TM | KVM_REG_SIZE_U32 | 0x67)
#define KVM_REG_PPC_TM_DSCR (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x68)
#define KVM_REG_PPC_TM_TAR (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x69)
+#define KVM_REG_PPC_TM_XER (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x6a)
/* PPC64 eXternal Interrupt Controller Specification */
#define KVM_DEV_XICS_GRP_SOURCES 1 /* 64-bit source attributes */
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index a39629206864..293149a1c6a1 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -104,8 +104,8 @@
#define X86_FEATURE_EXTD_APICID ( 3*32+26) /* has extended APICID (8 bits) */
#define X86_FEATURE_AMD_DCM ( 3*32+27) /* multi-node processor */
#define X86_FEATURE_APERFMPERF ( 3*32+28) /* APERFMPERF */
-#define X86_FEATURE_EAGER_FPU ( 3*32+29) /* "eagerfpu" Non lazy FPU restore */
#define X86_FEATURE_NONSTOP_TSC_S3 ( 3*32+30) /* TSC doesn't stop in S3 state */
+#define X86_FEATURE_TSC_KNOWN_FREQ ( 3*32+31) /* TSC has known frequency */
/* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
#define X86_FEATURE_XMM3 ( 4*32+ 0) /* "pni" SSE-3 */
@@ -189,10 +189,14 @@
#define X86_FEATURE_CPB ( 7*32+ 2) /* AMD Core Performance Boost */
#define X86_FEATURE_EPB ( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */
+#define X86_FEATURE_CAT_L3 ( 7*32+ 4) /* Cache Allocation Technology L3 */
+#define X86_FEATURE_CAT_L2 ( 7*32+ 5) /* Cache Allocation Technology L2 */
+#define X86_FEATURE_CDP_L3 ( 7*32+ 6) /* Code and Data Prioritization L3 */
#define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */
#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */
+#define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */
#define X86_FEATURE_INTEL_PT ( 7*32+15) /* Intel Processor Trace */
#define X86_FEATURE_AVX512_4VNNIW (7*32+16) /* AVX-512 Neural Network Instructions */
#define X86_FEATURE_AVX512_4FMAPS (7*32+17) /* AVX-512 Multiply Accumulation Single precision */
@@ -221,11 +225,13 @@
#define X86_FEATURE_RTM ( 9*32+11) /* Restricted Transactional Memory */
#define X86_FEATURE_CQM ( 9*32+12) /* Cache QoS Monitoring */
#define X86_FEATURE_MPX ( 9*32+14) /* Memory Protection Extension */
+#define X86_FEATURE_RDT_A ( 9*32+15) /* Resource Director Technology Allocation */
#define X86_FEATURE_AVX512F ( 9*32+16) /* AVX-512 Foundation */
#define X86_FEATURE_AVX512DQ ( 9*32+17) /* AVX-512 DQ (Double/Quad granular) Instructions */
#define X86_FEATURE_RDSEED ( 9*32+18) /* The RDSEED instruction */
#define X86_FEATURE_ADX ( 9*32+19) /* The ADCX and ADOX instructions */
#define X86_FEATURE_SMAP ( 9*32+20) /* Supervisor Mode Access Prevention */
+#define X86_FEATURE_AVX512IFMA ( 9*32+21) /* AVX-512 Integer Fused Multiply-Add instructions */
#define X86_FEATURE_CLFLUSHOPT ( 9*32+23) /* CLFLUSHOPT instruction */
#define X86_FEATURE_CLWB ( 9*32+24) /* CLWB instruction */
#define X86_FEATURE_AVX512PF ( 9*32+26) /* AVX-512 Prefetch */
@@ -279,8 +285,11 @@
#define X86_FEATURE_AVIC (15*32+13) /* Virtual Interrupt Controller */
/* Intel-defined CPU features, CPUID level 0x00000007:0 (ecx), word 16 */
+#define X86_FEATURE_AVX512VBMI (16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/
#define X86_FEATURE_PKU (16*32+ 3) /* Protection Keys for Userspace */
#define X86_FEATURE_OSPKE (16*32+ 4) /* OS Protection Keys Enable */
+#define X86_FEATURE_AVX512_VPOPCNTDQ (16*32+14) /* POPCNT for vectors of DW/QW */
+#define X86_FEATURE_RDPID (16*32+ 22) /* RDPID instruction */
/* AMD-defined CPU features, CPUID level 0x80000007 (ebx), word 17 */
#define X86_FEATURE_OVERFLOW_RECOV (17*32+0) /* MCA overflow recovery support */
@@ -311,4 +320,6 @@
#define X86_BUG_NULL_SEG X86_BUG(10) /* Nulling a selector preserves the base */
#define X86_BUG_SWAPGS_FENCE X86_BUG(11) /* SWAPGS without input dep on GS */
#define X86_BUG_MONITOR X86_BUG(12) /* IPI required to wake up remote CPU */
+#define X86_BUG_AMD_E400 X86_BUG(13) /* CPU is among the affected by Erratum 400 */
+
#endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/tools/arch/x86/include/uapi/asm/vmx.h b/tools/arch/x86/include/uapi/asm/vmx.h
index 37fee272618f..14458658e988 100644
--- a/tools/arch/x86/include/uapi/asm/vmx.h
+++ b/tools/arch/x86/include/uapi/asm/vmx.h
@@ -65,6 +65,8 @@
#define EXIT_REASON_TPR_BELOW_THRESHOLD 43
#define EXIT_REASON_APIC_ACCESS 44
#define EXIT_REASON_EOI_INDUCED 45
+#define EXIT_REASON_GDTR_IDTR 46
+#define EXIT_REASON_LDTR_TR 47
#define EXIT_REASON_EPT_VIOLATION 48
#define EXIT_REASON_EPT_MISCONFIG 49
#define EXIT_REASON_INVEPT 50
@@ -113,6 +115,8 @@
{ EXIT_REASON_MCE_DURING_VMENTRY, "MCE_DURING_VMENTRY" }, \
{ EXIT_REASON_TPR_BELOW_THRESHOLD, "TPR_BELOW_THRESHOLD" }, \
{ EXIT_REASON_APIC_ACCESS, "APIC_ACCESS" }, \
+ { EXIT_REASON_GDTR_IDTR, "GDTR_IDTR" }, \
+ { EXIT_REASON_LDTR_TR, "LDTR_TR" }, \
{ EXIT_REASON_EPT_VIOLATION, "EPT_VIOLATION" }, \
{ EXIT_REASON_EPT_MISCONFIG, "EPT_MISCONFIG" }, \
{ EXIT_REASON_INVEPT, "INVEPT" }, \
@@ -129,6 +133,7 @@
{ EXIT_REASON_XRSTORS, "XRSTORS" }
#define VMX_ABORT_SAVE_GUEST_MSR_FAIL 1
+#define VMX_ABORT_LOAD_HOST_PDPTE_FAIL 2
#define VMX_ABORT_LOAD_HOST_MSR_FAIL 4
#endif /* _UAPIVMX_H */
diff --git a/tools/build/Build.include b/tools/build/Build.include
index 1dcb95e76f70..418871d02ebf 100644
--- a/tools/build/Build.include
+++ b/tools/build/Build.include
@@ -65,22 +65,22 @@ dep-cmd = $(if $(wildcard $(fixdep)),
printf '\# cannot find fixdep (%s)\n' $(fixdep) > $(dot-target).cmd; \
printf '\# using basic dep data\n\n' >> $(dot-target).cmd; \
cat $(depfile) >> $(dot-target).cmd; \
- printf '%s\n' 'cmd_$@ := $(make-cmd)' >> $(dot-target).cmd)
+ printf '\n%s\n' 'cmd_$@ := $(make-cmd)' >> $(dot-target).cmd)
###
# if_changed_dep - execute command if any prerequisite is newer than
# target, or command line has changed and update
# dependencies in the cmd file
if_changed_dep = $(if $(strip $(any-prereq) $(arg-check)), \
- @set -e; \
- $(echo-cmd) $(cmd_$(1)) && $(dep-cmd))
+ @set -e; \
+ $(echo-cmd) $(cmd_$(1)) && $(dep-cmd))
# if_changed - execute command if any prerequisite is newer than
# target, or command line has changed
-if_changed = $(if $(strip $(any-prereq) $(arg-check)), \
- @set -e; \
- $(echo-cmd) $(cmd_$(1)); \
- printf '%s\n' 'cmd_$@ := $(make-cmd)' > $(dot-target).cmd)
+if_changed = $(if $(strip $(any-prereq) $(arg-check)), \
+ @set -e; \
+ $(echo-cmd) $(cmd_$(1)); \
+ printf '%s\n' 'cmd_$@ := $(make-cmd)' > $(dot-target).cmd)
###
# C flags to be used in rule definitions, includes:
@@ -89,10 +89,12 @@ if_changed = $(if $(strip $(any-prereq) $(arg-check)), \
# - per target C flags
# - per object C flags
# - BUILD_STR macro to allow '-D"$(variable)"' constructs
-c_flags = -Wp,-MD,$(depfile),-MT,$@ $(CFLAGS) -D"BUILD_STR(s)=\#s" $(CFLAGS_$(basetarget).o) $(CFLAGS_$(obj))
-cxx_flags = -Wp,-MD,$(depfile),-MT,$@ $(CXXFLAGS) -D"BUILD_STR(s)=\#s" $(CXXFLAGS_$(basetarget).o) $(CXXFLAGS_$(obj))
+c_flags_1 = -Wp,-MD,$(depfile) -Wp,-MT,$@ $(CFLAGS) -D"BUILD_STR(s)=\#s" $(CFLAGS_$(basetarget).o) $(CFLAGS_$(obj))
+c_flags_2 = $(filter-out $(CFLAGS_REMOVE_$(basetarget).o), $(c_flags_1))
+c_flags = $(filter-out $(CFLAGS_REMOVE_$(obj)), $(c_flags_2))
+cxx_flags = -Wp,-MD,$(depfile) -Wp,-MT,$@ $(CXXFLAGS) -D"BUILD_STR(s)=\#s" $(CXXFLAGS_$(basetarget).o) $(CXXFLAGS_$(obj))
###
## HOSTCC C flags
-host_c_flags = -Wp,-MD,$(depfile),-MT,$@ $(CHOSTFLAGS) -D"BUILD_STR(s)=\#s" $(CHOSTFLAGS_$(basetarget).o) $(CHOSTFLAGS_$(obj))
+host_c_flags = -Wp,-MD,$(depfile) -Wp,-MT,$@ $(CHOSTFLAGS) -D"BUILD_STR(s)=\#s" $(CHOSTFLAGS_$(basetarget).o) $(CHOSTFLAGS_$(obj))
diff --git a/tools/build/Documentation/Build.txt b/tools/build/Documentation/Build.txt
index a47bffbae159..a22587475dbe 100644
--- a/tools/build/Documentation/Build.txt
+++ b/tools/build/Documentation/Build.txt
@@ -135,8 +135,10 @@ CFLAGS
It's possible to alter the standard object C flags in the following way:
- CFLAGS_perf.o += '...' - alters CFLAGS for perf.o object
- CFLAGS_gtk += '...' - alters CFLAGS for gtk build object
+ CFLAGS_perf.o += '...' - adds CFLAGS for perf.o object
+ CFLAGS_gtk += '...' - adds CFLAGS for gtk build object
+ CFLAGS_REMOVE_perf.o += '...' - removes CFLAGS for perf.o object
+ CFLAGS_REMOVE_gtk += '...' - removes CFLAGS for gtk build object
This C flags changes has the scope of the Build makefile they are defined in.
diff --git a/tools/build/Makefile b/tools/build/Makefile
index 8332959fbca4..477f00eda591 100644
--- a/tools/build/Makefile
+++ b/tools/build/Makefile
@@ -1,5 +1,5 @@
ifeq ($(srctree),)
-srctree := $(patsubst %/,%,$(dir $(shell pwd)))
+srctree := $(patsubst %/,%,$(dir $(CURDIR)))
srctree := $(patsubst %/,%,$(dir $(srctree)))
endif
@@ -35,8 +35,8 @@ all: $(OUTPUT)fixdep
clean:
$(call QUIET_CLEAN, fixdep)
- $(Q)find . -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete
- $(Q)rm -f fixdep
+ $(Q)find $(if $(OUTPUT),$(OUTPUT),.) -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete
+ $(Q)rm -f $(OUTPUT)fixdep
$(OUTPUT)fixdep-in.o: FORCE
$(Q)$(MAKE) $(build)=fixdep
diff --git a/tools/build/Makefile.build b/tools/build/Makefile.build
index 99c0ccd2f176..e279a71c650d 100644
--- a/tools/build/Makefile.build
+++ b/tools/build/Makefile.build
@@ -19,6 +19,16 @@ else
Q=@
endif
+ifneq ($(filter 4.%,$(MAKE_VERSION)),) # make-4
+ifneq ($(filter %s ,$(firstword x$(MAKEFLAGS))),)
+ quiet=silent_
+endif
+else # make-3.8x
+ifneq ($(filter s% -s%,$(MAKEFLAGS)),)
+ quiet=silent_
+endif
+endif
+
build-dir := $(srctree)/tools/build
# Define $(fixdep) for dep-cmd function
diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature
index ae52e029dd22..e3fb5ecbdcb6 100644
--- a/tools/build/Makefile.feature
+++ b/tools/build/Makefile.feature
@@ -27,58 +27,58 @@ endef
# the rule that uses them - an example for that is the 'bionic'
# feature check. ]
#
-FEATURE_TESTS_BASIC := \
- backtrace \
- dwarf \
- dwarf_getlocations \
- fortify-source \
- sync-compare-and-swap \
- glibc \
- gtk2 \
- gtk2-infobar \
- libaudit \
- libbfd \
- libelf \
- libelf-getphdrnum \
- libelf-gelf_getnote \
- libelf-getshdrstrndx \
- libelf-mmap \
- libnuma \
- numa_num_possible_cpus \
- libperl \
- libpython \
- libpython-version \
- libslang \
- libcrypto \
- libunwind \
- libunwind-x86 \
- libunwind-x86_64 \
- libunwind-arm \
- libunwind-aarch64 \
- pthread-attr-setaffinity-np \
- stackprotector-all \
- timerfd \
- libdw-dwarf-unwind \
- zlib \
- lzma \
- get_cpuid \
- bpf \
- sdt
+FEATURE_TESTS_BASIC := \
+ backtrace \
+ dwarf \
+ dwarf_getlocations \
+ fortify-source \
+ sync-compare-and-swap \
+ glibc \
+ gtk2 \
+ gtk2-infobar \
+ libaudit \
+ libbfd \
+ libelf \
+ libelf-getphdrnum \
+ libelf-gelf_getnote \
+ libelf-getshdrstrndx \
+ libelf-mmap \
+ libnuma \
+ numa_num_possible_cpus \
+ libperl \
+ libpython \
+ libpython-version \
+ libslang \
+ libcrypto \
+ libunwind \
+ libunwind-x86 \
+ libunwind-x86_64 \
+ libunwind-arm \
+ libunwind-aarch64 \
+ pthread-attr-setaffinity-np \
+ stackprotector-all \
+ timerfd \
+ libdw-dwarf-unwind \
+ zlib \
+ lzma \
+ get_cpuid \
+ bpf \
+ sdt
# FEATURE_TESTS_BASIC + FEATURE_TESTS_EXTRA is the complete list
# of all feature tests
-FEATURE_TESTS_EXTRA := \
- bionic \
- compile-32 \
- compile-x32 \
- cplus-demangle \
- hello \
- libbabeltrace \
- liberty \
- liberty-z \
- libunwind-debug-frame \
- libunwind-debug-frame-arm \
- libunwind-debug-frame-aarch64
+FEATURE_TESTS_EXTRA := \
+ bionic \
+ compile-32 \
+ compile-x32 \
+ cplus-demangle \
+ hello \
+ libbabeltrace \
+ liberty \
+ liberty-z \
+ libunwind-debug-frame \
+ libunwind-debug-frame-arm \
+ libunwind-debug-frame-aarch64
FEATURE_TESTS ?= $(FEATURE_TESTS_BASIC)
@@ -86,26 +86,26 @@ ifeq ($(FEATURE_TESTS),all)
FEATURE_TESTS := $(FEATURE_TESTS_BASIC) $(FEATURE_TESTS_EXTRA)
endif
-FEATURE_DISPLAY ?= \
- dwarf \
- dwarf_getlocations \
- glibc \
- gtk2 \
- libaudit \
- libbfd \
- libelf \
- libnuma \
- numa_num_possible_cpus \
- libperl \
- libpython \
- libslang \
- libcrypto \
- libunwind \
- libdw-dwarf-unwind \
- zlib \
- lzma \
- get_cpuid \
- bpf
+FEATURE_DISPLAY ?= \
+ dwarf \
+ dwarf_getlocations \
+ glibc \
+ gtk2 \
+ libaudit \
+ libbfd \
+ libelf \
+ libnuma \
+ numa_num_possible_cpus \
+ libperl \
+ libpython \
+ libslang \
+ libcrypto \
+ libunwind \
+ libdw-dwarf-unwind \
+ zlib \
+ lzma \
+ get_cpuid \
+ bpf
# 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/Makefile.include b/tools/build/Makefile.include
index ad22e4e7bc59..d360f39a445b 100644
--- a/tools/build/Makefile.include
+++ b/tools/build/Makefile.include
@@ -3,4 +3,7 @@ build := -f $(srctree)/tools/build/Makefile.build dir=. obj
fixdep:
$(Q)$(MAKE) -C $(srctree)/tools/build CFLAGS= LDFLAGS= $(OUTPUT)fixdep
+fixdep-clean:
+ $(Q)$(MAKE) -C $(srctree)/tools/build clean
+
.PHONY: fixdep
diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index ac9c477a2a48..b564a2eea039 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -1,59 +1,61 @@
-FILES= \
- test-all.bin \
- test-backtrace.bin \
- test-bionic.bin \
- test-dwarf.bin \
- test-dwarf_getlocations.bin \
- test-fortify-source.bin \
- test-sync-compare-and-swap.bin \
- test-glibc.bin \
- test-gtk2.bin \
- test-gtk2-infobar.bin \
- test-hello.bin \
- test-libaudit.bin \
- test-libbfd.bin \
- test-liberty.bin \
- test-liberty-z.bin \
- test-cplus-demangle.bin \
- test-libelf.bin \
- test-libelf-getphdrnum.bin \
- test-libelf-gelf_getnote.bin \
- test-libelf-getshdrstrndx.bin \
- test-libelf-mmap.bin \
- test-libnuma.bin \
- test-numa_num_possible_cpus.bin \
- test-libperl.bin \
- test-libpython.bin \
- test-libpython-version.bin \
- test-libslang.bin \
- test-libcrypto.bin \
- test-libunwind.bin \
- test-libunwind-debug-frame.bin \
- test-libunwind-x86.bin \
- test-libunwind-x86_64.bin \
- test-libunwind-arm.bin \
- test-libunwind-aarch64.bin \
- test-libunwind-debug-frame-arm.bin \
- test-libunwind-debug-frame-aarch64.bin \
- test-pthread-attr-setaffinity-np.bin \
- test-stackprotector-all.bin \
- test-timerfd.bin \
- test-libdw-dwarf-unwind.bin \
- test-libbabeltrace.bin \
- test-compile-32.bin \
- test-compile-x32.bin \
- test-zlib.bin \
- test-lzma.bin \
- test-bpf.bin \
- test-get_cpuid.bin \
- test-sdt.bin \
- test-cxx.bin
+FILES= \
+ test-all.bin \
+ test-backtrace.bin \
+ test-bionic.bin \
+ test-dwarf.bin \
+ test-dwarf_getlocations.bin \
+ test-fortify-source.bin \
+ test-sync-compare-and-swap.bin \
+ test-glibc.bin \
+ test-gtk2.bin \
+ test-gtk2-infobar.bin \
+ test-hello.bin \
+ test-libaudit.bin \
+ test-libbfd.bin \
+ test-liberty.bin \
+ test-liberty-z.bin \
+ test-cplus-demangle.bin \
+ test-libelf.bin \
+ test-libelf-getphdrnum.bin \
+ test-libelf-gelf_getnote.bin \
+ test-libelf-getshdrstrndx.bin \
+ test-libelf-mmap.bin \
+ test-libnuma.bin \
+ test-numa_num_possible_cpus.bin \
+ test-libperl.bin \
+ test-libpython.bin \
+ test-libpython-version.bin \
+ test-libslang.bin \
+ test-libcrypto.bin \
+ test-libunwind.bin \
+ test-libunwind-debug-frame.bin \
+ test-libunwind-x86.bin \
+ test-libunwind-x86_64.bin \
+ test-libunwind-arm.bin \
+ test-libunwind-aarch64.bin \
+ test-libunwind-debug-frame-arm.bin \
+ test-libunwind-debug-frame-aarch64.bin \
+ test-pthread-attr-setaffinity-np.bin \
+ test-stackprotector-all.bin \
+ test-timerfd.bin \
+ test-libdw-dwarf-unwind.bin \
+ test-libbabeltrace.bin \
+ test-compile-32.bin \
+ test-compile-x32.bin \
+ test-zlib.bin \
+ test-lzma.bin \
+ test-bpf.bin \
+ test-get_cpuid.bin \
+ test-sdt.bin \
+ test-cxx.bin \
+ test-jvmti.bin
FILES := $(addprefix $(OUTPUT),$(FILES))
CC := $(CROSS_COMPILE)gcc -MD
CXX := $(CROSS_COMPILE)g++ -MD
PKG_CONFIG := $(CROSS_COMPILE)pkg-config
+LLVM_CONFIG ?= llvm-config
all: $(FILES)
@@ -225,6 +227,30 @@ $(OUTPUT)test-sdt.bin:
$(OUTPUT)test-cxx.bin:
$(BUILDXX) -std=gnu++11
+$(OUTPUT)test-jvmti.bin:
+ $(BUILD)
+
+$(OUTPUT)test-llvm.bin:
+ $(BUILDXX) -std=gnu++11 \
+ -I$(shell $(LLVM_CONFIG) --includedir) \
+ -L$(shell $(LLVM_CONFIG) --libdir) \
+ $(shell $(LLVM_CONFIG) --libs Core BPF) \
+ $(shell $(LLVM_CONFIG) --system-libs)
+
+$(OUTPUT)test-llvm-version.bin:
+ $(BUILDXX) -std=gnu++11 \
+ -I$(shell $(LLVM_CONFIG) --includedir)
+
+$(OUTPUT)test-clang.bin:
+ $(BUILDXX) -std=gnu++11 \
+ -I$(shell $(LLVM_CONFIG) --includedir) \
+ -L$(shell $(LLVM_CONFIG) --libdir) \
+ -Wl,--start-group -lclangBasic -lclangDriver \
+ -lclangFrontend -lclangEdit -lclangLex \
+ -lclangAST -Wl,--end-group \
+ $(shell $(LLVM_CONFIG) --libs Core option) \
+ $(shell $(LLVM_CONFIG) --system-libs)
+
-include $(OUTPUT)*.d
###############################
diff --git a/tools/build/feature/test-clang.cpp b/tools/build/feature/test-clang.cpp
new file mode 100644
index 000000000000..e23c1b1f1b91
--- /dev/null
+++ b/tools/build/feature/test-clang.cpp
@@ -0,0 +1,21 @@
+#include "clang/Basic/VirtualFileSystem.h"
+#include "clang/Driver/Driver.h"
+#include "clang/Frontend/TextDiagnosticPrinter.h"
+#include "llvm/ADT/IntrusiveRefCntPtr.h"
+#include "llvm/Support/ManagedStatic.h"
+#include "llvm/Support/raw_ostream.h"
+
+using namespace clang;
+using namespace clang::driver;
+
+int main()
+{
+ IntrusiveRefCntPtr<DiagnosticIDs> DiagID(new DiagnosticIDs());
+ IntrusiveRefCntPtr<DiagnosticOptions> DiagOpts = new DiagnosticOptions();
+
+ DiagnosticsEngine Diags(DiagID, &*DiagOpts);
+ Driver TheDriver("test", "bpf-pc-linux", Diags);
+
+ llvm::llvm_shutdown();
+ return 0;
+}
diff --git a/tools/build/feature/test-jvmti.c b/tools/build/feature/test-jvmti.c
new file mode 100644
index 000000000000..1c665f09b9d6
--- /dev/null
+++ b/tools/build/feature/test-jvmti.c
@@ -0,0 +1,13 @@
+#include <jvmti.h>
+#include <jvmticmlr.h>
+
+int main(void)
+{
+ JavaVM jvm __attribute__((unused));
+ jvmtiEventCallbacks cb __attribute__((unused));
+ jvmtiCapabilities caps __attribute__((unused));
+ jvmtiJlocationFormat format __attribute__((unused));
+ jvmtiEnv jvmti __attribute__((unused));
+
+ return 0;
+}
diff --git a/tools/build/feature/test-llvm-version.cpp b/tools/build/feature/test-llvm-version.cpp
new file mode 100644
index 000000000000..896d31724568
--- /dev/null
+++ b/tools/build/feature/test-llvm-version.cpp
@@ -0,0 +1,11 @@
+#include <cstdio>
+#include "llvm/Config/llvm-config.h"
+
+#define NUM_VERSION (((LLVM_VERSION_MAJOR) << 16) + (LLVM_VERSION_MINOR << 8) + LLVM_VERSION_PATCH)
+#define pass int main() {printf("%x\n", NUM_VERSION); return 0;}
+
+#if NUM_VERSION >= 0x030900
+pass
+#else
+# error This LLVM is not tested yet.
+#endif
diff --git a/tools/build/feature/test-llvm.cpp b/tools/build/feature/test-llvm.cpp
new file mode 100644
index 000000000000..455a332dc8a8
--- /dev/null
+++ b/tools/build/feature/test-llvm.cpp
@@ -0,0 +1,13 @@
+#include "llvm/Support/ManagedStatic.h"
+#include "llvm/Support/raw_ostream.h"
+#define NUM_VERSION (((LLVM_VERSION_MAJOR) << 16) + (LLVM_VERSION_MINOR << 8) + LLVM_VERSION_PATCH)
+
+#if NUM_VERSION < 0x030900
+# error "LLVM version too low"
+#endif
+int main()
+{
+ llvm::errs() << "Hello World!\n";
+ llvm::llvm_shutdown();
+ return 0;
+}
diff --git a/tools/build/fixdep.c b/tools/build/fixdep.c
index 1521d36cef0d..734d1547cbae 100644
--- a/tools/build/fixdep.c
+++ b/tools/build/fixdep.c
@@ -49,7 +49,7 @@ static void parse_dep_file(void *map, size_t len)
char *end = m + len;
char *p;
char s[PATH_MAX];
- int is_target;
+ int is_target, has_target = 0;
int saw_any_target = 0;
int is_first_dep = 0;
@@ -67,7 +67,8 @@ static void parse_dep_file(void *map, size_t len)
if (is_target) {
/* The /next/ file is the first dependency */
is_first_dep = 1;
- } else {
+ has_target = 1;
+ } else if (has_target) {
/* Save this token/filename */
memcpy(s, m, p-m);
s[p - m] = 0;
diff --git a/tools/gpio/.gitignore b/tools/gpio/.gitignore
new file mode 100644
index 000000000000..9e9dd4b681b2
--- /dev/null
+++ b/tools/gpio/.gitignore
@@ -0,0 +1,4 @@
+gpio-event-mon
+gpio-hammer
+lsgpio
+
diff --git a/tools/gpio/Makefile b/tools/gpio/Makefile
index 250a891e6ef0..b4401536cfa9 100644
--- a/tools/gpio/Makefile
+++ b/tools/gpio/Makefile
@@ -3,7 +3,7 @@ include ../scripts/Makefile.include
bindir ?= /usr/bin
ifeq ($(srctree),)
-srctree := $(patsubst %/,%,$(dir $(shell pwd)))
+srctree := $(patsubst %/,%,$(dir $(CURDIR)))
srctree := $(patsubst %/,%,$(dir $(srctree)))
endif
diff --git a/tools/gpio/gpio-hammer.c b/tools/gpio/gpio-hammer.c
index 37b3f141053d..4bcb234c0fca 100644
--- a/tools/gpio/gpio-hammer.c
+++ b/tools/gpio/gpio-hammer.c
@@ -23,54 +23,31 @@
#include <getopt.h>
#include <sys/ioctl.h>
#include <linux/gpio.h>
+#include "gpio-utils.h"
int hammer_device(const char *device_name, unsigned int *lines, int nlines,
unsigned int loops)
{
- struct gpiohandle_request req;
struct gpiohandle_data data;
- char *chrdev_name;
char swirr[] = "-\\|/";
int fd;
int ret;
int i, j;
unsigned int iteration = 0;
- ret = asprintf(&chrdev_name, "/dev/%s", device_name);
+ memset(&data.values, 0, sizeof(data.values));
+ ret = gpiotools_request_linehandle(device_name, lines, nlines,
+ GPIOHANDLE_REQUEST_OUTPUT, &data,
+ "gpio-hammer");
if (ret < 0)
- return -ENOMEM;
+ goto exit_error;
+ else
+ fd = ret;
- fd = open(chrdev_name, 0);
- if (fd == -1) {
- ret = -errno;
- fprintf(stderr, "Failed to open %s\n", chrdev_name);
- goto exit_close_error;
- }
-
- /* Request lines as output */
- for (i = 0; i < nlines; i++)
- req.lineoffsets[i] = lines[i];
- req.flags = GPIOHANDLE_REQUEST_OUTPUT; /* Request as output */
- strcpy(req.consumer_label, "gpio-hammer");
- req.lines = nlines;
- ret = ioctl(fd, GPIO_GET_LINEHANDLE_IOCTL, &req);
- if (ret == -1) {
- ret = -errno;
- fprintf(stderr, "Failed to issue GET LINEHANDLE "
- "IOCTL (%d)\n",
- ret);
+ ret = gpiotools_get_values(fd, &data);
+ if (ret < 0)
goto exit_close_error;
- }
- /* Read initial states */
- ret = ioctl(req.fd, GPIOHANDLE_GET_LINE_VALUES_IOCTL, &data);
- if (ret == -1) {
- ret = -errno;
- fprintf(stderr, "Failed to issue GPIOHANDLE GET LINE "
- "VALUES IOCTL (%d)\n",
- ret);
- goto exit_close_error;
- }
fprintf(stdout, "Hammer lines [");
for (i = 0; i < nlines; i++) {
fprintf(stdout, "%d", lines[i]);
@@ -92,23 +69,14 @@ int hammer_device(const char *device_name, unsigned int *lines, int nlines,
for (i = 0; i < nlines; i++)
data.values[i] = !data.values[i];
- ret = ioctl(req.fd, GPIOHANDLE_SET_LINE_VALUES_IOCTL, &data);
- if (ret == -1) {
- ret = -errno;
- fprintf(stderr, "Failed to issue GPIOHANDLE SET LINE "
- "VALUES IOCTL (%d)\n",
- ret);
+ ret = gpiotools_set_values(fd, &data);
+ if (ret < 0)
goto exit_close_error;
- }
+
/* Re-read values to get status */
- ret = ioctl(req.fd, GPIOHANDLE_GET_LINE_VALUES_IOCTL, &data);
- if (ret == -1) {
- ret = -errno;
- fprintf(stderr, "Failed to issue GPIOHANDLE GET LINE "
- "VALUES IOCTL (%d)\n",
- ret);
+ ret = gpiotools_get_values(fd, &data);
+ if (ret < 0)
goto exit_close_error;
- }
fprintf(stdout, "[%c] ", swirr[j]);
j++;
@@ -132,9 +100,8 @@ int hammer_device(const char *device_name, unsigned int *lines, int nlines,
ret = 0;
exit_close_error:
- if (close(fd) == -1)
- perror("Failed to close GPIO character device file");
- free(chrdev_name);
+ gpiotools_release_linehandle(fd);
+exit_error:
return ret;
}
diff --git a/tools/gpio/gpio-utils.c b/tools/gpio/gpio-utils.c
index 8208718f2c99..b86a32d90d88 100644
--- a/tools/gpio/gpio-utils.c
+++ b/tools/gpio/gpio-utils.c
@@ -2,10 +2,266 @@
* GPIO tools - helpers library for the GPIO tools
*
* Copyright (C) 2015 Linus Walleij
+ * Copyright (C) 2016 Bamvor Jian Zhang
*
* 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.
*/
+#include <unistd.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <errno.h>
+#include <string.h>
+#include <fcntl.h>
+#include <getopt.h>
+#include <sys/ioctl.h>
+#include <linux/gpio.h>
#include "gpio-utils.h"
+
+#define COMSUMER "gpio-utils"
+
+/**
+ * doc: Operation of gpio
+ *
+ * Provide the api of gpiochip for chardev interface. There are two
+ * types of api. The first one provide as same function as each
+ * ioctl, including request and release for lines of gpio, read/write
+ * the value of gpio. If the user want to do lots of read and write of
+ * lines of gpio, user should use this type of api.
+ *
+ * The second one provide the easy to use api for user. Each of the
+ * following api will request gpio lines, do the operation and then
+ * release these lines.
+ */
+/**
+ * gpiotools_request_linehandle() - request gpio lines in a gpiochip
+ * @device_name: The name of gpiochip without prefix "/dev/",
+ * such as "gpiochip0"
+ * @lines: An array desired lines, specified by offset
+ * index for the associated GPIO device.
+ * @nline: The number of lines to request.
+ * @flag: The new flag for requsted gpio. Reference
+ * "linux/gpio.h" for the meaning of flag.
+ * @data: Default value will be set to gpio when flag is
+ * GPIOHANDLE_REQUEST_OUTPUT.
+ * @consumer_label: The name of consumer, such as "sysfs",
+ * "powerkey". This is useful for other users to
+ * know who is using.
+ *
+ * Request gpio lines through the ioctl provided by chardev. User
+ * could call gpiotools_set_values() and gpiotools_get_values() to
+ * read and write respectively through the returned fd. Call
+ * gpiotools_release_linehandle() to release these lines after that.
+ *
+ * Return: On success return the fd;
+ * On failure return the errno.
+ */
+int gpiotools_request_linehandle(const char *device_name, unsigned int *lines,
+ unsigned int nlines, unsigned int flag,
+ struct gpiohandle_data *data,
+ const char *consumer_label)
+{
+ struct gpiohandle_request req;
+ char *chrdev_name;
+ int fd;
+ int i;
+ int ret;
+
+ ret = asprintf(&chrdev_name, "/dev/%s", device_name);
+ if (ret < 0)
+ return -ENOMEM;
+
+ fd = open(chrdev_name, 0);
+ if (fd == -1) {
+ ret = -errno;
+ fprintf(stderr, "Failed to open %s\n", chrdev_name);
+ goto exit_close_error;
+ }
+
+ for (i = 0; i < nlines; i++)
+ req.lineoffsets[i] = lines[i];
+
+ req.flags = flag;
+ strcpy(req.consumer_label, consumer_label);
+ req.lines = nlines;
+ if (flag & GPIOHANDLE_REQUEST_OUTPUT)
+ memcpy(req.default_values, data, sizeof(req.default_values));
+
+ ret = ioctl(fd, GPIO_GET_LINEHANDLE_IOCTL, &req);
+ if (ret == -1) {
+ ret = -errno;
+ fprintf(stderr, "Failed to issue GET LINEHANDLE IOCTL (%d)\n",
+ ret);
+ }
+
+exit_close_error:
+ if (close(fd) == -1)
+ perror("Failed to close GPIO character device file");
+ free(chrdev_name);
+ return ret < 0 ? ret : req.fd;
+}
+/**
+ * gpiotools_set_values(): Set the value of gpio(s)
+ * @fd: The fd returned by
+ * gpiotools_request_linehandle().
+ * @data: The array of values want to set.
+ *
+ * Return: On success return 0;
+ * On failure return the errno.
+ */
+int gpiotools_set_values(const int fd, struct gpiohandle_data *data)
+{
+ int ret;
+
+ ret = ioctl(fd, GPIOHANDLE_SET_LINE_VALUES_IOCTL, data);
+ if (ret == -1) {
+ ret = -errno;
+ fprintf(stderr, "Failed to issue %s (%d)\n",
+ "GPIOHANDLE_SET_LINE_VALUES_IOCTL", ret);
+ }
+
+ return ret;
+}
+
+/**
+ * gpiotools_get_values(): Get the value of gpio(s)
+ * @fd: The fd returned by
+ * gpiotools_request_linehandle().
+ * @data: The array of values get from hardware.
+ *
+ * Return: On success return 0;
+ * On failure return the errno.
+ */
+int gpiotools_get_values(const int fd, struct gpiohandle_data *data)
+{
+ int ret;
+
+ ret = ioctl(fd, GPIOHANDLE_GET_LINE_VALUES_IOCTL, data);
+ if (ret == -1) {
+ ret = -errno;
+ fprintf(stderr, "Failed to issue %s (%d)\n",
+ "GPIOHANDLE_GET_LINE_VALUES_IOCTL", ret);
+ }
+
+ return ret;
+}
+
+/**
+ * gpiotools_release_linehandle(): Release the line(s) of gpiochip
+ * @fd: The fd returned by
+ * gpiotools_request_linehandle().
+ *
+ * Return: On success return 0;
+ * On failure return the errno.
+ */
+int gpiotools_release_linehandle(const int fd)
+{
+ int ret;
+
+ ret = close(fd);
+ if (ret == -1) {
+ perror("Failed to close GPIO LINEHANDLE device file");
+ ret = -errno;
+ }
+
+ return ret;
+}
+
+/**
+ * gpiotools_get(): Get value from specific line
+ * @device_name: The name of gpiochip without prefix "/dev/",
+ * such as "gpiochip0"
+ * @line: number of line, such as 2.
+ *
+ * Return: On success return 0;
+ * On failure return the errno.
+ */
+int gpiotools_get(const char *device_name, unsigned int line)
+{
+ struct gpiohandle_data data;
+ unsigned int lines[] = {line};
+
+ gpiotools_gets(device_name, lines, 1, &data);
+ return data.values[0];
+}
+
+
+/**
+ * gpiotools_gets(): Get values from specific lines.
+ * @device_name: The name of gpiochip without prefix "/dev/",
+ * such as "gpiochip0".
+ * @lines: An array desired lines, specified by offset
+ * index for the associated GPIO device.
+ * @nline: The number of lines to request.
+ * @data: The array of values get from gpiochip.
+ *
+ * Return: On success return 0;
+ * On failure return the errno.
+ */
+int gpiotools_gets(const char *device_name, unsigned int *lines,
+ unsigned int nlines, struct gpiohandle_data *data)
+{
+ int fd;
+ int ret;
+ int ret_close;
+
+ ret = gpiotools_request_linehandle(device_name, lines, nlines,
+ GPIOHANDLE_REQUEST_INPUT, data,
+ COMSUMER);
+ if (ret < 0)
+ return ret;
+
+ fd = ret;
+ ret = gpiotools_get_values(fd, data);
+ ret_close = gpiotools_release_linehandle(fd);
+ return ret < 0 ? ret : ret_close;
+}
+
+/**
+ * gpiotools_set(): Set value to specific line
+ * @device_name: The name of gpiochip without prefix "/dev/",
+ * such as "gpiochip0"
+ * @line: number of line, such as 2.
+ * @value: The value of gpio, must be 0(low) or 1(high).
+ *
+ * Return: On success return 0;
+ * On failure return the errno.
+ */
+int gpiotools_set(const char *device_name, unsigned int line,
+ unsigned int value)
+{
+ struct gpiohandle_data data;
+ unsigned int lines[] = {line};
+
+ data.values[0] = value;
+ return gpiotools_sets(device_name, lines, 1, &data);
+}
+
+/**
+ * gpiotools_sets(): Set values to specific lines.
+ * @device_name: The name of gpiochip without prefix "/dev/",
+ * such as "gpiochip0".
+ * @lines: An array desired lines, specified by offset
+ * index for the associated GPIO device.
+ * @nline: The number of lines to request.
+ * @data: The array of values set to gpiochip, must be
+ * 0(low) or 1(high).
+ *
+ * Return: On success return 0;
+ * On failure return the errno.
+ */
+int gpiotools_sets(const char *device_name, unsigned int *lines,
+ unsigned int nlines, struct gpiohandle_data *data)
+{
+ int ret;
+
+ ret = gpiotools_request_linehandle(device_name, lines, nlines,
+ GPIOHANDLE_REQUEST_OUTPUT, data,
+ COMSUMER);
+ if (ret < 0)
+ return ret;
+
+ return gpiotools_release_linehandle(ret);
+}
diff --git a/tools/gpio/gpio-utils.h b/tools/gpio/gpio-utils.h
index 5f57133b8c04..344ea041f8d4 100644
--- a/tools/gpio/gpio-utils.h
+++ b/tools/gpio/gpio-utils.h
@@ -24,4 +24,20 @@ static inline int check_prefix(const char *str, const char *prefix)
strncmp(str, prefix, strlen(prefix)) == 0;
}
+int gpiotools_request_linehandle(const char *device_name, unsigned int *lines,
+ unsigned int nlines, unsigned int flag,
+ struct gpiohandle_data *data,
+ const char *consumer_label);
+int gpiotools_set_values(const int fd, struct gpiohandle_data *data);
+int gpiotools_get_values(const int fd, struct gpiohandle_data *data);
+int gpiotools_release_linehandle(const int fd);
+
+int gpiotools_get(const char *device_name, unsigned int line);
+int gpiotools_gets(const char *device_name, unsigned int *lines,
+ unsigned int nlines, struct gpiohandle_data *data);
+int gpiotools_set(const char *device_name, unsigned int line,
+ unsigned int value);
+int gpiotools_sets(const char *device_name, unsigned int *lines,
+ unsigned int nlines, struct gpiohandle_data *data);
+
#endif /* _GPIO_UTILS_H_ */
diff --git a/tools/hv/Makefile b/tools/hv/Makefile
index a8c4644022a6..0d1e61b81844 100644
--- a/tools/hv/Makefile
+++ b/tools/hv/Makefile
@@ -1,9 +1,8 @@
# Makefile for Hyper-V tools
CC = $(CROSS_COMPILE)gcc
-PTHREAD_LIBS = -lpthread
WARNINGS = -Wall -Wextra
-CFLAGS = $(WARNINGS) -g $(PTHREAD_LIBS) $(shell getconf LFS_CFLAGS)
+CFLAGS = $(WARNINGS) -g $(shell getconf LFS_CFLAGS)
CFLAGS += -D__EXPORTED_HEADERS__ -I../../include/uapi -I../../include
diff --git a/tools/hv/bondvf.sh b/tools/hv/bondvf.sh
index 8e960234013d..4aa5369ffa4e 100755
--- a/tools/hv/bondvf.sh
+++ b/tools/hv/bondvf.sh
@@ -74,8 +74,8 @@ function create_eth_cfg_redhat {
echo DEVICE=$1 >>$fn
echo TYPE=Ethernet >>$fn
echo BOOTPROTO=none >>$fn
+ echo UUID=`uuidgen` >>$fn
echo ONBOOT=yes >>$fn
- echo NM_CONTROLLED=no >>$fn
echo PEERDNS=yes >>$fn
echo IPV6INIT=yes >>$fn
echo MASTER=$2 >>$fn
@@ -93,8 +93,8 @@ function create_bond_cfg_redhat {
echo DEVICE=$1 >>$fn
echo TYPE=Bond >>$fn
echo BOOTPROTO=dhcp >>$fn
+ echo UUID=`uuidgen` >>$fn
echo ONBOOT=yes >>$fn
- echo NM_CONTROLLED=no >>$fn
echo PEERDNS=yes >>$fn
echo IPV6INIT=yes >>$fn
echo BONDING_MASTER=yes >>$fn
diff --git a/tools/hv/hv_fcopy_daemon.c b/tools/hv/hv_fcopy_daemon.c
index fdc9ca4c0356..26ae609a9448 100644
--- a/tools/hv/hv_fcopy_daemon.c
+++ b/tools/hv/hv_fcopy_daemon.c
@@ -18,21 +18,14 @@
#include <sys/types.h>
-#include <sys/socket.h>
-#include <sys/poll.h>
-#include <linux/types.h>
-#include <linux/kdev_t.h>
#include <stdio.h>
#include <stdlib.h>
#include <unistd.h>
-#include <string.h>
-#include <ctype.h>
#include <errno.h>
#include <linux/hyperv.h>
#include <syslog.h>
#include <sys/stat.h>
#include <fcntl.h>
-#include <dirent.h>
#include <getopt.h>
static int target_fd;
diff --git a/tools/hv/hv_kvp_daemon.c b/tools/hv/hv_kvp_daemon.c
index bc7adb84e679..f1758fcbc37d 100644
--- a/tools/hv/hv_kvp_daemon.c
+++ b/tools/hv/hv_kvp_daemon.c
@@ -22,8 +22,6 @@
*/
-#include <sys/types.h>
-#include <sys/socket.h>
#include <sys/poll.h>
#include <sys/utsname.h>
#include <stdio.h>
@@ -34,7 +32,6 @@
#include <errno.h>
#include <arpa/inet.h>
#include <linux/hyperv.h>
-#include <linux/netlink.h>
#include <ifaddrs.h>
#include <netdb.h>
#include <syslog.h>
@@ -96,13 +93,13 @@ static struct utsname uts_buf;
#define KVP_CONFIG_LOC "/var/lib/hyperv"
+#ifndef KVP_SCRIPTS_PATH
+#define KVP_SCRIPTS_PATH "/usr/libexec/hypervkvpd/"
+#endif
+
#define MAX_FILE_NAME 100
#define ENTRIES_PER_BLOCK 50
-#ifndef SOL_NETLINK
-#define SOL_NETLINK 270
-#endif
-
struct kvp_record {
char key[HV_KVP_EXCHANGE_MAX_KEY_SIZE];
char value[HV_KVP_EXCHANGE_MAX_VALUE_SIZE];
@@ -702,7 +699,7 @@ static char *kvp_mac_to_if_name(char *mac)
if (dir == NULL)
return NULL;
- snprintf(dev_id, sizeof(dev_id), kvp_net_dir);
+ snprintf(dev_id, sizeof(dev_id), "%s", kvp_net_dir);
q = dev_id + strlen(kvp_net_dir);
while ((entry = readdir(dir)) != NULL) {
@@ -825,7 +822,7 @@ static void kvp_get_ipconfig_info(char *if_name,
* .
*/
- sprintf(cmd, "%s", "hv_get_dns_info");
+ sprintf(cmd, KVP_SCRIPTS_PATH "%s", "hv_get_dns_info");
/*
* Execute the command to gather DNS info.
@@ -842,7 +839,7 @@ static void kvp_get_ipconfig_info(char *if_name,
* Enabled: DHCP enabled.
*/
- sprintf(cmd, "%s %s", "hv_get_dhcp_info", if_name);
+ sprintf(cmd, KVP_SCRIPTS_PATH "%s %s", "hv_get_dhcp_info", if_name);
file = popen(cmd, "r");
if (file == NULL)
@@ -1348,7 +1345,8 @@ static int kvp_set_ip_info(char *if_name, struct hv_kvp_ipaddr_value *new_val)
* invoke the external script to do its magic.
*/
- snprintf(cmd, sizeof(cmd), "%s %s", "hv_set_ifconfig", if_file);
+ snprintf(cmd, sizeof(cmd), KVP_SCRIPTS_PATH "%s %s",
+ "hv_set_ifconfig", if_file);
if (system(cmd)) {
syslog(LOG_ERR, "Failed to execute cmd '%s'; error: %d %s",
cmd, errno, strerror(errno));
diff --git a/tools/iio/iio_event_monitor.c b/tools/iio/iio_event_monitor.c
index d9b7e0f306c6..b61245e1181d 100644
--- a/tools/iio/iio_event_monitor.c
+++ b/tools/iio/iio_event_monitor.c
@@ -57,6 +57,7 @@ static const char * const iio_chan_type_name_spec[] = {
[IIO_RESISTANCE] = "resistance",
[IIO_PH] = "ph",
[IIO_UVINDEX] = "uvindex",
+ [IIO_GRAVITY] = "gravity",
};
static const char * const iio_ev_type_text[] = {
@@ -149,6 +150,7 @@ static bool event_is_known(struct iio_event_data *event)
case IIO_RESISTANCE:
case IIO_PH:
case IIO_UVINDEX:
+ case IIO_GRAVITY:
break;
default:
return false;
diff --git a/tools/iio/iio_generic_buffer.c b/tools/iio/iio_generic_buffer.c
index f39c0e9c0d5c..f0c6f54a8b2f 100644
--- a/tools/iio/iio_generic_buffer.c
+++ b/tools/iio/iio_generic_buffer.c
@@ -247,6 +247,7 @@ void print_usage(void)
fprintf(stderr, "Usage: generic_buffer [options]...\n"
"Capture, convert and output data from IIO device buffer\n"
" -a Auto-activate all available channels\n"
+ " -A Force-activate ALL channels\n"
" -c <n> Do n conversions\n"
" -e Disable wait for event (new data)\n"
" -g Use trigger-less mode\n"
@@ -347,16 +348,22 @@ int main(int argc, char **argv)
int noevents = 0;
int notrigger = 0;
char *dummy;
+ bool force_autochannels = false;
struct iio_channel_info *channels = NULL;
register_cleanup();
- while ((c = getopt_long(argc, argv, "ac:egl:n:N:t:T:w:", longopts, NULL)) != -1) {
+ while ((c = getopt_long(argc, argv, "aAc:egl:n:N:t:T:w:?", longopts,
+ NULL)) != -1) {
switch (c) {
case 'a':
autochannels = AUTOCHANNELS_ENABLED;
break;
+ case 'A':
+ autochannels = AUTOCHANNELS_ENABLED;
+ force_autochannels = true;
+ break;
case 'c':
errno = 0;
num_loops = strtoul(optarg, &dummy, 10);
@@ -519,15 +526,16 @@ int main(int argc, char **argv)
"diag %s\n", dev_dir_name);
goto error;
}
- if (num_channels && autochannels == AUTOCHANNELS_ENABLED) {
+ if (num_channels && autochannels == AUTOCHANNELS_ENABLED &&
+ !force_autochannels) {
fprintf(stderr, "Auto-channels selected but some channels "
"are already activated in sysfs\n");
fprintf(stderr, "Proceeding without activating any channels\n");
}
- if (!num_channels && autochannels == AUTOCHANNELS_ENABLED) {
- fprintf(stderr,
- "No channels are enabled, enabling all channels\n");
+ if ((!num_channels && autochannels == AUTOCHANNELS_ENABLED) ||
+ (autochannels == AUTOCHANNELS_ENABLED && force_autochannels)) {
+ fprintf(stderr, "Enabling all channels\n");
ret = enable_disable_all_channels(dev_dir_name, 1);
if (ret) {
diff --git a/tools/include/asm-generic/bitops.h b/tools/include/asm-generic/bitops.h
index 653d1bad77de..0304600121da 100644
--- a/tools/include/asm-generic/bitops.h
+++ b/tools/include/asm-generic/bitops.h
@@ -13,6 +13,7 @@
*/
#include <asm-generic/bitops/__ffs.h>
+#include <asm-generic/bitops/__ffz.h>
#include <asm-generic/bitops/fls.h>
#include <asm-generic/bitops/__fls.h>
#include <asm-generic/bitops/fls64.h>
diff --git a/tools/testing/radix-tree/linux/bitops/ffz.h b/tools/include/asm-generic/bitops/__ffz.h
index 6744bd4cdf46..6744bd4cdf46 100644
--- a/tools/testing/radix-tree/linux/bitops/ffz.h
+++ b/tools/include/asm-generic/bitops/__ffz.h
diff --git a/tools/include/asm-generic/bitops/atomic.h b/tools/include/asm-generic/bitops/atomic.h
index 18663f59d72f..68b8c1516c5a 100644
--- a/tools/include/asm-generic/bitops/atomic.h
+++ b/tools/include/asm-generic/bitops/atomic.h
@@ -20,4 +20,7 @@ static __always_inline int test_bit(unsigned int nr, const unsigned long *addr)
(((unsigned long *)addr)[nr / __BITS_PER_LONG])) != 0;
}
+#define __set_bit(nr, addr) set_bit(nr, addr)
+#define __clear_bit(nr, addr) clear_bit(nr, addr)
+
#endif /* _TOOLS_LINUX_ASM_GENERIC_BITOPS_ATOMIC_H_ */
diff --git a/tools/include/asm-generic/bitops/find.h b/tools/include/asm-generic/bitops/find.h
index 31f51547fcd4..5538ecdc964a 100644
--- a/tools/include/asm-generic/bitops/find.h
+++ b/tools/include/asm-generic/bitops/find.h
@@ -15,6 +15,21 @@ extern unsigned long find_next_bit(const unsigned long *addr, unsigned long
size, unsigned long offset);
#endif
+#ifndef find_next_zero_bit
+
+/**
+ * find_next_zero_bit - find the next cleared bit in a memory region
+ * @addr: The address to base the search on
+ * @offset: The bitnumber to start searching at
+ * @size: The bitmap size in bits
+ *
+ * Returns the bit number of the next zero bit
+ * If no bits are zero, returns @size.
+ */
+unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size,
+ unsigned long offset);
+#endif
+
#ifndef find_first_bit
/**
@@ -30,4 +45,17 @@ extern unsigned long find_first_bit(const unsigned long *addr,
#endif /* find_first_bit */
+#ifndef find_first_zero_bit
+
+/**
+ * find_first_zero_bit - find the first cleared bit in a memory region
+ * @addr: The address to start the search at
+ * @size: The maximum number of bits to search
+ *
+ * Returns the bit number of the first cleared bit.
+ * If no bits are zero, returns @size.
+ */
+unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size);
+#endif
+
#endif /*_TOOLS_LINUX_ASM_GENERIC_BITOPS_FIND_H_ */
diff --git a/tools/include/asm/bug.h b/tools/include/asm/bug.h
index 9e5f4846967f..4790f047a89c 100644
--- a/tools/include/asm/bug.h
+++ b/tools/include/asm/bug.h
@@ -12,6 +12,25 @@
unlikely(__ret_warn_on); \
})
+#define WARN_ON(condition) ({ \
+ int __ret_warn_on = !!(condition); \
+ if (unlikely(__ret_warn_on)) \
+ __WARN_printf("assertion failed at %s:%d\n", \
+ __FILE__, __LINE__); \
+ unlikely(__ret_warn_on); \
+})
+
+#define WARN_ON_ONCE(condition) ({ \
+ static int __warned; \
+ int __ret_warn_once = !!(condition); \
+ \
+ if (unlikely(__ret_warn_once && !__warned)) { \
+ __warned = true; \
+ WARN_ON(1); \
+ } \
+ unlikely(__ret_warn_once); \
+})
+
#define WARN_ONCE(condition, format...) ({ \
static int __warned; \
int __ret_warn_once = !!(condition); \
diff --git a/tools/include/linux/bitmap.h b/tools/include/linux/bitmap.h
index 43c1c5021e4b..e8b9f518e36b 100644
--- a/tools/include/linux/bitmap.h
+++ b/tools/include/linux/bitmap.h
@@ -4,6 +4,7 @@
#include <string.h>
#include <linux/bitops.h>
#include <stdlib.h>
+#include <linux/kernel.h>
#define DECLARE_BITMAP(name,bits) \
unsigned long name[BITS_TO_LONGS(bits)]
@@ -35,6 +36,32 @@ static inline void bitmap_zero(unsigned long *dst, int nbits)
}
}
+static inline void bitmap_fill(unsigned long *dst, unsigned int nbits)
+{
+ unsigned int nlongs = BITS_TO_LONGS(nbits);
+ if (!small_const_nbits(nbits)) {
+ unsigned int len = (nlongs - 1) * sizeof(unsigned long);
+ memset(dst, 0xff, len);
+ }
+ dst[nlongs - 1] = BITMAP_LAST_WORD_MASK(nbits);
+}
+
+static inline int bitmap_empty(const unsigned long *src, unsigned nbits)
+{
+ if (small_const_nbits(nbits))
+ return ! (*src & BITMAP_LAST_WORD_MASK(nbits));
+
+ return find_first_bit(src, nbits) == nbits;
+}
+
+static inline int bitmap_full(const unsigned long *src, unsigned int nbits)
+{
+ if (small_const_nbits(nbits))
+ return ! (~(*src) & BITMAP_LAST_WORD_MASK(nbits));
+
+ return find_first_zero_bit(src, nbits) == nbits;
+}
+
static inline int bitmap_weight(const unsigned long *src, int nbits)
{
if (small_const_nbits(nbits))
diff --git a/tools/include/linux/bitops.h b/tools/include/linux/bitops.h
index 49c929a104ee..1aecad369af5 100644
--- a/tools/include/linux/bitops.h
+++ b/tools/include/linux/bitops.h
@@ -2,7 +2,6 @@
#define _TOOLS_LINUX_BITOPS_H_
#include <asm/types.h>
-#include <linux/kernel.h>
#include <linux/compiler.h>
#ifndef __WORDSIZE
@@ -39,6 +38,11 @@ extern unsigned long __sw_hweight64(__u64 w);
(bit) < (size); \
(bit) = find_next_bit((addr), (size), (bit) + 1))
+#define for_each_clear_bit(bit, addr, size) \
+ for ((bit) = find_first_zero_bit((addr), (size)); \
+ (bit) < (size); \
+ (bit) = find_next_zero_bit((addr), (size), (bit) + 1))
+
/* same as for_each_set_bit() but use bit as value to start with */
#define for_each_set_bit_from(bit, addr, size) \
for ((bit) = find_next_bit((addr), (size), (bit)); \
diff --git a/tools/include/linux/compiler-gcc.h b/tools/include/linux/compiler-gcc.h
new file mode 100644
index 000000000000..48af2f10a42d
--- /dev/null
+++ b/tools/include/linux/compiler-gcc.h
@@ -0,0 +1,14 @@
+#ifndef _TOOLS_LINUX_COMPILER_H_
+#error "Please don't include <linux/compiler-gcc.h> directly, include <linux/compiler.h> instead."
+#endif
+
+/*
+ * Common definitions for all gcc versions go here.
+ */
+#define GCC_VERSION (__GNUC__ * 10000 \
+ + __GNUC_MINOR__ * 100 \
+ + __GNUC_PATCHLEVEL__)
+
+#if GCC_VERSION >= 70000 && !defined(__CHECKER__)
+# define __fallthrough __attribute__ ((fallthrough))
+#endif
diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h
index e33fc1df3935..8de163b17c0d 100644
--- a/tools/include/linux/compiler.h
+++ b/tools/include/linux/compiler.h
@@ -1,6 +1,10 @@
#ifndef _TOOLS_LINUX_COMPILER_H_
#define _TOOLS_LINUX_COMPILER_H_
+#ifdef __GNUC__
+#include <linux/compiler-gcc.h>
+#endif
+
/* Optimization barrier */
/* The "volatile" is due to gcc bugs */
#define barrier() __asm__ __volatile__("": : :"memory")
@@ -21,6 +25,8 @@
#endif
#define __user
+#define __rcu
+#define __read_mostly
#ifndef __attribute_const__
# define __attribute_const__
@@ -50,6 +56,8 @@
# define unlikely(x) __builtin_expect(!!(x), 0)
#endif
+#define uninitialized_var(x) x = *(&(x))
+
#define ACCESS_ONCE(x) (*(volatile typeof(x) *)&(x))
#include <linux/types.h>
@@ -126,4 +134,9 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s
#define WRITE_ONCE(x, val) \
({ union { typeof(x) __val; char __c[1]; } __u = { .__val = (val) }; __write_once_size(&(x), __u.__c, sizeof(x)); __u.__val; })
+
+#ifndef __fallthrough
+# define __fallthrough
+#endif
+
#endif /* _TOOLS_LINUX_COMPILER_H */
diff --git a/tools/include/linux/filter.h b/tools/include/linux/filter.h
index 3276625595b2..122153b16ea4 100644
--- a/tools/include/linux/filter.h
+++ b/tools/include/linux/filter.h
@@ -218,6 +218,30 @@
.off = OFF, \
.imm = IMM })
+/* BPF_LD_IMM64 macro encodes single 'load 64-bit immediate' insn */
+
+#define BPF_LD_IMM64(DST, IMM) \
+ BPF_LD_IMM64_RAW(DST, 0, IMM)
+
+#define BPF_LD_IMM64_RAW(DST, SRC, IMM) \
+ ((struct bpf_insn) { \
+ .code = BPF_LD | BPF_DW | BPF_IMM, \
+ .dst_reg = DST, \
+ .src_reg = SRC, \
+ .off = 0, \
+ .imm = (__u32) (IMM) }), \
+ ((struct bpf_insn) { \
+ .code = 0, /* zero is reserved opcode */ \
+ .dst_reg = 0, \
+ .src_reg = 0, \
+ .off = 0, \
+ .imm = ((__u64) (IMM)) >> 32 })
+
+/* 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)
+
/* Program exit */
#define BPF_EXIT_INSN() \
diff --git a/tools/include/linux/log2.h b/tools/include/linux/log2.h
index 41446668ccce..d5677d39c1e4 100644
--- a/tools/include/linux/log2.h
+++ b/tools/include/linux/log2.h
@@ -13,12 +13,6 @@
#define _TOOLS_LINUX_LOG2_H
/*
- * deal with unrepresentable constant logarithms
- */
-extern __attribute__((const, noreturn))
-int ____ilog2_NaN(void);
-
-/*
* non-constant log of base 2 calculators
* - the arch may override these in asm/bitops.h if they can be implemented
* more efficiently than using fls() and fls64()
@@ -78,7 +72,7 @@ unsigned long __rounddown_pow_of_two(unsigned long n)
#define ilog2(n) \
( \
__builtin_constant_p(n) ? ( \
- (n) < 1 ? ____ilog2_NaN() : \
+ (n) < 2 ? 0 : \
(n) & (1ULL << 63) ? 63 : \
(n) & (1ULL << 62) ? 62 : \
(n) & (1ULL << 61) ? 61 : \
@@ -141,10 +135,7 @@ unsigned long __rounddown_pow_of_two(unsigned long n)
(n) & (1ULL << 4) ? 4 : \
(n) & (1ULL << 3) ? 3 : \
(n) & (1ULL << 2) ? 2 : \
- (n) & (1ULL << 1) ? 1 : \
- (n) & (1ULL << 0) ? 0 : \
- ____ilog2_NaN() \
- ) : \
+ 1 ) : \
(sizeof(n) <= 4) ? \
__ilog2_u32(n) : \
__ilog2_u64(n) \
diff --git a/tools/include/linux/spinlock.h b/tools/include/linux/spinlock.h
new file mode 100644
index 000000000000..58397dcb19d6
--- /dev/null
+++ b/tools/include/linux/spinlock.h
@@ -0,0 +1,5 @@
+#define spinlock_t pthread_mutex_t
+#define DEFINE_SPINLOCK(x) pthread_mutex_t x = PTHREAD_MUTEX_INITIALIZER;
+
+#define spin_lock_irqsave(x, f) (void)f, pthread_mutex_lock(x)
+#define spin_unlock_irqrestore(x, f) (void)f, pthread_mutex_unlock(x)
diff --git a/tools/include/linux/types.h b/tools/include/linux/types.h
index 8ebf6278b2ef..c24b3e3ae296 100644
--- a/tools/include/linux/types.h
+++ b/tools/include/linux/types.h
@@ -42,11 +42,7 @@ typedef __s8 s8;
#else
#define __bitwise__
#endif
-#ifdef __CHECK_ENDIAN__
#define __bitwise __bitwise__
-#else
-#define __bitwise
-#endif
#define __force
#define __user
diff --git a/tools/include/uapi/asm-generic/mman-common.h b/tools/include/uapi/asm-generic/mman-common.h
index 58274382a616..8c27db0c5c08 100644
--- a/tools/include/uapi/asm-generic/mman-common.h
+++ b/tools/include/uapi/asm-generic/mman-common.h
@@ -72,4 +72,9 @@
#define MAP_HUGE_SHIFT 26
#define MAP_HUGE_MASK 0x3f
+#define PKEY_DISABLE_ACCESS 0x1
+#define PKEY_DISABLE_WRITE 0x2
+#define PKEY_ACCESS_MASK (PKEY_DISABLE_ACCESS |\
+ PKEY_DISABLE_WRITE)
+
#endif /* __ASM_GENERIC_MMAN_COMMON_H */
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 9e5fc168c8a3..0539a0ceef38 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -63,6 +63,12 @@ struct bpf_insn {
__s32 imm; /* signed immediate constant */
};
+/* Key of an a BPF_MAP_TYPE_LPM_TRIE entry */
+struct bpf_lpm_trie_key {
+ __u32 prefixlen; /* up to 32 for AF_INET, 128 for AF_INET6 */
+ __u8 data[0]; /* Arbitrary size */
+};
+
/* BPF syscall commands, see bpf(2) man-page for details. */
enum bpf_cmd {
BPF_MAP_CREATE,
@@ -73,6 +79,8 @@ enum bpf_cmd {
BPF_PROG_LOAD,
BPF_OBJ_PIN,
BPF_OBJ_GET,
+ BPF_PROG_ATTACH,
+ BPF_PROG_DETACH,
};
enum bpf_map_type {
@@ -85,6 +93,9 @@ enum bpf_map_type {
BPF_MAP_TYPE_PERCPU_ARRAY,
BPF_MAP_TYPE_STACK_TRACE,
BPF_MAP_TYPE_CGROUP_ARRAY,
+ BPF_MAP_TYPE_LRU_HASH,
+ BPF_MAP_TYPE_LRU_PERCPU_HASH,
+ BPF_MAP_TYPE_LPM_TRIE,
};
enum bpf_prog_type {
@@ -95,8 +106,29 @@ enum bpf_prog_type {
BPF_PROG_TYPE_SCHED_ACT,
BPF_PROG_TYPE_TRACEPOINT,
BPF_PROG_TYPE_XDP,
+ BPF_PROG_TYPE_PERF_EVENT,
+ BPF_PROG_TYPE_CGROUP_SKB,
+ BPF_PROG_TYPE_CGROUP_SOCK,
+ BPF_PROG_TYPE_LWT_IN,
+ BPF_PROG_TYPE_LWT_OUT,
+ BPF_PROG_TYPE_LWT_XMIT,
+};
+
+enum bpf_attach_type {
+ BPF_CGROUP_INET_INGRESS,
+ BPF_CGROUP_INET_EGRESS,
+ BPF_CGROUP_INET_SOCK_CREATE,
+ __MAX_BPF_ATTACH_TYPE
};
+#define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE
+
+/* If BPF_F_ALLOW_OVERRIDE flag is used in BPF_PROG_ATTACH command
+ * to the given target_fd cgroup the descendent cgroup will be able to
+ * override effective bpf program that was inherited from this cgroup
+ */
+#define BPF_F_ALLOW_OVERRIDE (1U << 0)
+
#define BPF_PSEUDO_MAP_FD 1
/* flags for BPF_MAP_UPDATE_ELEM command */
@@ -105,6 +137,13 @@ enum bpf_prog_type {
#define BPF_EXIST 2 /* update existing element */
#define BPF_F_NO_PREALLOC (1U << 0)
+/* Instead of having one common LRU list in the
+ * BPF_MAP_TYPE_LRU_[PERCPU_]HASH map, use a percpu LRU list
+ * which can scale and perform better.
+ * Note, the LRU nodes (including free nodes) cannot be moved
+ * across different LRU lists.
+ */
+#define BPF_F_NO_COMMON_LRU (1U << 1)
union bpf_attr {
struct { /* anonymous struct used by BPF_MAP_CREATE command */
@@ -140,243 +179,341 @@ union bpf_attr {
__aligned_u64 pathname;
__u32 bpf_fd;
};
+
+ struct { /* anonymous struct used by BPF_PROG_ATTACH/DETACH commands */
+ __u32 target_fd; /* container object to attach to */
+ __u32 attach_bpf_fd; /* eBPF program to attach */
+ __u32 attach_type;
+ __u32 attach_flags;
+ };
} __attribute__((aligned(8)));
+/* BPF helper function descriptions:
+ *
+ * void *bpf_map_lookup_elem(&map, &key)
+ * Return: Map value or NULL
+ *
+ * int bpf_map_update_elem(&map, &key, &value, flags)
+ * Return: 0 on success or negative error
+ *
+ * int bpf_map_delete_elem(&map, &key)
+ * Return: 0 on success or negative error
+ *
+ * int bpf_probe_read(void *dst, int size, void *src)
+ * Return: 0 on success or negative error
+ *
+ * u64 bpf_ktime_get_ns(void)
+ * Return: current ktime
+ *
+ * int bpf_trace_printk(const char *fmt, int fmt_size, ...)
+ * Return: length of buffer written or negative error
+ *
+ * u32 bpf_prandom_u32(void)
+ * Return: random value
+ *
+ * u32 bpf_raw_smp_processor_id(void)
+ * Return: SMP processor ID
+ *
+ * int bpf_skb_store_bytes(skb, offset, from, len, flags)
+ * store bytes into packet
+ * @skb: pointer to skb
+ * @offset: offset within packet from skb->mac_header
+ * @from: pointer where to copy bytes from
+ * @len: number of bytes to store into packet
+ * @flags: bit 0 - if true, recompute skb->csum
+ * other bits - reserved
+ * Return: 0 on success or negative error
+ *
+ * int bpf_l3_csum_replace(skb, offset, from, to, flags)
+ * recompute IP checksum
+ * @skb: pointer to skb
+ * @offset: offset within packet where IP checksum is located
+ * @from: old value of header field
+ * @to: new value of header field
+ * @flags: bits 0-3 - size of header field
+ * other bits - reserved
+ * Return: 0 on success or negative error
+ *
+ * int bpf_l4_csum_replace(skb, offset, from, to, flags)
+ * recompute TCP/UDP checksum
+ * @skb: pointer to skb
+ * @offset: offset within packet where TCP/UDP checksum is located
+ * @from: old value of header field
+ * @to: new value of header field
+ * @flags: bits 0-3 - size of header field
+ * bit 4 - is pseudo header
+ * other bits - reserved
+ * Return: 0 on success or negative error
+ *
+ * int bpf_tail_call(ctx, prog_array_map, index)
+ * jump into another BPF program
+ * @ctx: context pointer passed to next program
+ * @prog_array_map: pointer to map which type is BPF_MAP_TYPE_PROG_ARRAY
+ * @index: index inside array that selects specific program to run
+ * Return: 0 on success or negative error
+ *
+ * int bpf_clone_redirect(skb, ifindex, flags)
+ * redirect to another netdev
+ * @skb: pointer to skb
+ * @ifindex: ifindex of the net device
+ * @flags: bit 0 - if set, redirect to ingress instead of egress
+ * other bits - reserved
+ * Return: 0 on success or negative error
+ *
+ * u64 bpf_get_current_pid_tgid(void)
+ * Return: current->tgid << 32 | current->pid
+ *
+ * u64 bpf_get_current_uid_gid(void)
+ * Return: current_gid << 32 | current_uid
+ *
+ * int bpf_get_current_comm(char *buf, int size_of_buf)
+ * stores current->comm into buf
+ * Return: 0 on success or negative error
+ *
+ * u32 bpf_get_cgroup_classid(skb)
+ * retrieve a proc's classid
+ * @skb: pointer to skb
+ * Return: classid if != 0
+ *
+ * int bpf_skb_vlan_push(skb, vlan_proto, vlan_tci)
+ * Return: 0 on success or negative error
+ *
+ * int bpf_skb_vlan_pop(skb)
+ * Return: 0 on success or negative error
+ *
+ * int bpf_skb_get_tunnel_key(skb, key, size, flags)
+ * int bpf_skb_set_tunnel_key(skb, key, size, flags)
+ * retrieve or populate tunnel metadata
+ * @skb: pointer to skb
+ * @key: pointer to 'struct bpf_tunnel_key'
+ * @size: size of 'struct bpf_tunnel_key'
+ * @flags: room for future extensions
+ * Return: 0 on success or negative error
+ *
+ * u64 bpf_perf_event_read(&map, index)
+ * Return: Number events read or error code
+ *
+ * int bpf_redirect(ifindex, flags)
+ * redirect to another netdev
+ * @ifindex: ifindex of the net device
+ * @flags: bit 0 - if set, redirect to ingress instead of egress
+ * other bits - reserved
+ * Return: TC_ACT_REDIRECT
+ *
+ * u32 bpf_get_route_realm(skb)
+ * retrieve a dst's tclassid
+ * @skb: pointer to skb
+ * Return: realm if != 0
+ *
+ * int bpf_perf_event_output(ctx, map, index, data, size)
+ * output perf raw sample
+ * @ctx: struct pt_regs*
+ * @map: pointer to perf_event_array map
+ * @index: index of event in the map
+ * @data: data on stack to be output as raw data
+ * @size: size of data
+ * Return: 0 on success or negative error
+ *
+ * int bpf_get_stackid(ctx, map, flags)
+ * walk user or kernel stack and return id
+ * @ctx: struct pt_regs*
+ * @map: pointer to stack_trace map
+ * @flags: bits 0-7 - numer of stack frames to skip
+ * bit 8 - collect user stack instead of kernel
+ * bit 9 - compare stacks by hash only
+ * bit 10 - if two different stacks hash into the same stackid
+ * discard old
+ * other bits - reserved
+ * Return: >= 0 stackid on success or negative error
+ *
+ * s64 bpf_csum_diff(from, from_size, to, to_size, seed)
+ * calculate csum diff
+ * @from: raw from buffer
+ * @from_size: length of from buffer
+ * @to: raw to buffer
+ * @to_size: length of to buffer
+ * @seed: optional seed
+ * Return: csum result or negative error code
+ *
+ * int bpf_skb_get_tunnel_opt(skb, opt, size)
+ * retrieve tunnel options metadata
+ * @skb: pointer to skb
+ * @opt: pointer to raw tunnel option data
+ * @size: size of @opt
+ * Return: option size
+ *
+ * int bpf_skb_set_tunnel_opt(skb, opt, size)
+ * populate tunnel options metadata
+ * @skb: pointer to skb
+ * @opt: pointer to raw tunnel option data
+ * @size: size of @opt
+ * Return: 0 on success or negative error
+ *
+ * int bpf_skb_change_proto(skb, proto, flags)
+ * Change protocol of the skb. Currently supported is v4 -> v6,
+ * v6 -> v4 transitions. The helper will also resize the skb. eBPF
+ * program is expected to fill the new headers via skb_store_bytes
+ * and lX_csum_replace.
+ * @skb: pointer to skb
+ * @proto: new skb->protocol type
+ * @flags: reserved
+ * Return: 0 on success or negative error
+ *
+ * int bpf_skb_change_type(skb, type)
+ * Change packet type of skb.
+ * @skb: pointer to skb
+ * @type: new skb->pkt_type type
+ * Return: 0 on success or negative error
+ *
+ * int bpf_skb_under_cgroup(skb, map, index)
+ * Check cgroup2 membership of skb
+ * @skb: pointer to skb
+ * @map: pointer to bpf_map in BPF_MAP_TYPE_CGROUP_ARRAY type
+ * @index: index of the cgroup in the bpf_map
+ * Return:
+ * == 0 skb failed the cgroup2 descendant test
+ * == 1 skb succeeded the cgroup2 descendant test
+ * < 0 error
+ *
+ * u32 bpf_get_hash_recalc(skb)
+ * Retrieve and possibly recalculate skb->hash.
+ * @skb: pointer to skb
+ * Return: hash
+ *
+ * u64 bpf_get_current_task(void)
+ * Returns current task_struct
+ * Return: current
+ *
+ * int bpf_probe_write_user(void *dst, void *src, int len)
+ * safely attempt to write to a location
+ * @dst: destination address in userspace
+ * @src: source address on stack
+ * @len: number of bytes to copy
+ * Return: 0 on success or negative error
+ *
+ * int bpf_current_task_under_cgroup(map, index)
+ * Check cgroup2 membership of current task
+ * @map: pointer to bpf_map in BPF_MAP_TYPE_CGROUP_ARRAY type
+ * @index: index of the cgroup in the bpf_map
+ * Return:
+ * == 0 current failed the cgroup2 descendant test
+ * == 1 current succeeded the cgroup2 descendant test
+ * < 0 error
+ *
+ * int bpf_skb_change_tail(skb, len, flags)
+ * The helper will resize the skb to the given new size, to be used f.e.
+ * with control messages.
+ * @skb: pointer to skb
+ * @len: new skb length
+ * @flags: reserved
+ * Return: 0 on success or negative error
+ *
+ * int bpf_skb_pull_data(skb, len)
+ * The helper will pull in non-linear data in case the skb is non-linear
+ * and not all of len are part of the linear section. Only needed for
+ * read/write with direct packet access.
+ * @skb: pointer to skb
+ * @len: len to make read/writeable
+ * Return: 0 on success or negative error
+ *
+ * s64 bpf_csum_update(skb, csum)
+ * Adds csum into skb->csum in case of CHECKSUM_COMPLETE.
+ * @skb: pointer to skb
+ * @csum: csum to add
+ * Return: csum on success or negative error
+ *
+ * void bpf_set_hash_invalid(skb)
+ * Invalidate current skb->hash.
+ * @skb: pointer to skb
+ *
+ * int bpf_get_numa_node_id()
+ * Return: Id of current NUMA node.
+ *
+ * int bpf_skb_change_head()
+ * Grows headroom of skb and adjusts MAC header offset accordingly.
+ * Will extends/reallocae as required automatically.
+ * May change skb data pointer and will thus invalidate any check
+ * performed for direct packet access.
+ * @skb: pointer to skb
+ * @len: length of header to be pushed in front
+ * @flags: Flags (unused for now)
+ * Return: 0 on success or negative error
+ *
+ * int bpf_xdp_adjust_head(xdp_md, delta)
+ * Adjust the xdp_md.data by delta
+ * @xdp_md: pointer to xdp_md
+ * @delta: An positive/negative integer to be added to xdp_md.data
+ * Return: 0 on success or negative on error
+ *
+ * int bpf_probe_read_str(void *dst, int size, const void *unsafe_ptr)
+ * Copy a NUL terminated string from unsafe address. In case the string
+ * length is smaller than size, the target is not padded with further NUL
+ * bytes. In case the string length is larger than size, just count-1
+ * bytes are copied and the last byte is set to NUL.
+ * @dst: destination address
+ * @size: maximum number of bytes to copy, including the trailing NUL
+ * @unsafe_ptr: unsafe address
+ * Return:
+ * > 0 length of the string including the trailing NUL on success
+ * < 0 error
+ */
+#define __BPF_FUNC_MAPPER(FN) \
+ FN(unspec), \
+ FN(map_lookup_elem), \
+ FN(map_update_elem), \
+ FN(map_delete_elem), \
+ FN(probe_read), \
+ FN(ktime_get_ns), \
+ FN(trace_printk), \
+ FN(get_prandom_u32), \
+ FN(get_smp_processor_id), \
+ FN(skb_store_bytes), \
+ FN(l3_csum_replace), \
+ FN(l4_csum_replace), \
+ FN(tail_call), \
+ FN(clone_redirect), \
+ FN(get_current_pid_tgid), \
+ FN(get_current_uid_gid), \
+ FN(get_current_comm), \
+ FN(get_cgroup_classid), \
+ FN(skb_vlan_push), \
+ FN(skb_vlan_pop), \
+ FN(skb_get_tunnel_key), \
+ FN(skb_set_tunnel_key), \
+ FN(perf_event_read), \
+ FN(redirect), \
+ FN(get_route_realm), \
+ FN(perf_event_output), \
+ FN(skb_load_bytes), \
+ FN(get_stackid), \
+ FN(csum_diff), \
+ FN(skb_get_tunnel_opt), \
+ FN(skb_set_tunnel_opt), \
+ FN(skb_change_proto), \
+ FN(skb_change_type), \
+ FN(skb_under_cgroup), \
+ FN(get_hash_recalc), \
+ FN(get_current_task), \
+ FN(probe_write_user), \
+ FN(current_task_under_cgroup), \
+ FN(skb_change_tail), \
+ FN(skb_pull_data), \
+ FN(csum_update), \
+ FN(set_hash_invalid), \
+ FN(get_numa_node_id), \
+ FN(skb_change_head), \
+ FN(xdp_adjust_head), \
+ FN(probe_read_str),
+
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
* function eBPF program intends to call
*/
+#define __BPF_ENUM_FN(x) BPF_FUNC_ ## x
enum bpf_func_id {
- BPF_FUNC_unspec,
- BPF_FUNC_map_lookup_elem, /* void *map_lookup_elem(&map, &key) */
- BPF_FUNC_map_update_elem, /* int map_update_elem(&map, &key, &value, flags) */
- BPF_FUNC_map_delete_elem, /* int map_delete_elem(&map, &key) */
- BPF_FUNC_probe_read, /* int bpf_probe_read(void *dst, int size, void *src) */
- BPF_FUNC_ktime_get_ns, /* u64 bpf_ktime_get_ns(void) */
- BPF_FUNC_trace_printk, /* int bpf_trace_printk(const char *fmt, int fmt_size, ...) */
- BPF_FUNC_get_prandom_u32, /* u32 prandom_u32(void) */
- BPF_FUNC_get_smp_processor_id, /* u32 raw_smp_processor_id(void) */
-
- /**
- * skb_store_bytes(skb, offset, from, len, flags) - store bytes into packet
- * @skb: pointer to skb
- * @offset: offset within packet from skb->mac_header
- * @from: pointer where to copy bytes from
- * @len: number of bytes to store into packet
- * @flags: bit 0 - if true, recompute skb->csum
- * other bits - reserved
- * Return: 0 on success
- */
- BPF_FUNC_skb_store_bytes,
-
- /**
- * l3_csum_replace(skb, offset, from, to, flags) - recompute IP checksum
- * @skb: pointer to skb
- * @offset: offset within packet where IP checksum is located
- * @from: old value of header field
- * @to: new value of header field
- * @flags: bits 0-3 - size of header field
- * other bits - reserved
- * Return: 0 on success
- */
- BPF_FUNC_l3_csum_replace,
-
- /**
- * l4_csum_replace(skb, offset, from, to, flags) - recompute TCP/UDP checksum
- * @skb: pointer to skb
- * @offset: offset within packet where TCP/UDP checksum is located
- * @from: old value of header field
- * @to: new value of header field
- * @flags: bits 0-3 - size of header field
- * bit 4 - is pseudo header
- * other bits - reserved
- * Return: 0 on success
- */
- BPF_FUNC_l4_csum_replace,
-
- /**
- * bpf_tail_call(ctx, prog_array_map, index) - jump into another BPF program
- * @ctx: context pointer passed to next program
- * @prog_array_map: pointer to map which type is BPF_MAP_TYPE_PROG_ARRAY
- * @index: index inside array that selects specific program to run
- * Return: 0 on success
- */
- BPF_FUNC_tail_call,
-
- /**
- * bpf_clone_redirect(skb, ifindex, flags) - redirect to another netdev
- * @skb: pointer to skb
- * @ifindex: ifindex of the net device
- * @flags: bit 0 - if set, redirect to ingress instead of egress
- * other bits - reserved
- * Return: 0 on success
- */
- BPF_FUNC_clone_redirect,
-
- /**
- * u64 bpf_get_current_pid_tgid(void)
- * Return: current->tgid << 32 | current->pid
- */
- BPF_FUNC_get_current_pid_tgid,
-
- /**
- * u64 bpf_get_current_uid_gid(void)
- * Return: current_gid << 32 | current_uid
- */
- BPF_FUNC_get_current_uid_gid,
-
- /**
- * bpf_get_current_comm(char *buf, int size_of_buf)
- * stores current->comm into buf
- * Return: 0 on success
- */
- BPF_FUNC_get_current_comm,
-
- /**
- * bpf_get_cgroup_classid(skb) - retrieve a proc's classid
- * @skb: pointer to skb
- * Return: classid if != 0
- */
- BPF_FUNC_get_cgroup_classid,
- BPF_FUNC_skb_vlan_push, /* bpf_skb_vlan_push(skb, vlan_proto, vlan_tci) */
- BPF_FUNC_skb_vlan_pop, /* bpf_skb_vlan_pop(skb) */
-
- /**
- * bpf_skb_[gs]et_tunnel_key(skb, key, size, flags)
- * retrieve or populate tunnel metadata
- * @skb: pointer to skb
- * @key: pointer to 'struct bpf_tunnel_key'
- * @size: size of 'struct bpf_tunnel_key'
- * @flags: room for future extensions
- * Retrun: 0 on success
- */
- BPF_FUNC_skb_get_tunnel_key,
- BPF_FUNC_skb_set_tunnel_key,
- BPF_FUNC_perf_event_read, /* u64 bpf_perf_event_read(&map, index) */
- /**
- * bpf_redirect(ifindex, flags) - redirect to another netdev
- * @ifindex: ifindex of the net device
- * @flags: bit 0 - if set, redirect to ingress instead of egress
- * other bits - reserved
- * Return: TC_ACT_REDIRECT
- */
- BPF_FUNC_redirect,
-
- /**
- * bpf_get_route_realm(skb) - retrieve a dst's tclassid
- * @skb: pointer to skb
- * Return: realm if != 0
- */
- BPF_FUNC_get_route_realm,
-
- /**
- * bpf_perf_event_output(ctx, map, index, data, size) - output perf raw sample
- * @ctx: struct pt_regs*
- * @map: pointer to perf_event_array map
- * @index: index of event in the map
- * @data: data on stack to be output as raw data
- * @size: size of data
- * Return: 0 on success
- */
- BPF_FUNC_perf_event_output,
- BPF_FUNC_skb_load_bytes,
-
- /**
- * bpf_get_stackid(ctx, map, flags) - walk user or kernel stack and return id
- * @ctx: struct pt_regs*
- * @map: pointer to stack_trace map
- * @flags: bits 0-7 - numer of stack frames to skip
- * bit 8 - collect user stack instead of kernel
- * bit 9 - compare stacks by hash only
- * bit 10 - if two different stacks hash into the same stackid
- * discard old
- * other bits - reserved
- * Return: >= 0 stackid on success or negative error
- */
- BPF_FUNC_get_stackid,
-
- /**
- * bpf_csum_diff(from, from_size, to, to_size, seed) - calculate csum diff
- * @from: raw from buffer
- * @from_size: length of from buffer
- * @to: raw to buffer
- * @to_size: length of to buffer
- * @seed: optional seed
- * Return: csum result
- */
- BPF_FUNC_csum_diff,
-
- /**
- * bpf_skb_[gs]et_tunnel_opt(skb, opt, size)
- * retrieve or populate tunnel options metadata
- * @skb: pointer to skb
- * @opt: pointer to raw tunnel option data
- * @size: size of @opt
- * Return: 0 on success for set, option size for get
- */
- BPF_FUNC_skb_get_tunnel_opt,
- BPF_FUNC_skb_set_tunnel_opt,
-
- /**
- * bpf_skb_change_proto(skb, proto, flags)
- * Change protocol of the skb. Currently supported is
- * v4 -> v6, v6 -> v4 transitions. The helper will also
- * resize the skb. eBPF program is expected to fill the
- * new headers via skb_store_bytes and lX_csum_replace.
- * @skb: pointer to skb
- * @proto: new skb->protocol type
- * @flags: reserved
- * Return: 0 on success or negative error
- */
- BPF_FUNC_skb_change_proto,
-
- /**
- * bpf_skb_change_type(skb, type)
- * Change packet type of skb.
- * @skb: pointer to skb
- * @type: new skb->pkt_type type
- * Return: 0 on success or negative error
- */
- BPF_FUNC_skb_change_type,
-
- /**
- * bpf_skb_under_cgroup(skb, map, index) - Check cgroup2 membership of skb
- * @skb: pointer to skb
- * @map: pointer to bpf_map in BPF_MAP_TYPE_CGROUP_ARRAY type
- * @index: index of the cgroup in the bpf_map
- * Return:
- * == 0 skb failed the cgroup2 descendant test
- * == 1 skb succeeded the cgroup2 descendant test
- * < 0 error
- */
- BPF_FUNC_skb_under_cgroup,
-
- /**
- * bpf_get_hash_recalc(skb)
- * Retrieve and possibly recalculate skb->hash.
- * @skb: pointer to skb
- * Return: hash
- */
- BPF_FUNC_get_hash_recalc,
-
- /**
- * u64 bpf_get_current_task(void)
- * Returns current task_struct
- * Return: current
- */
- BPF_FUNC_get_current_task,
-
- /**
- * bpf_probe_write_user(void *dst, void *src, int len)
- * safely attempt to write to a location
- * @dst: destination address in userspace
- * @src: source address on stack
- * @len: number of bytes to copy
- * Return: 0 on success or negative error
- */
- BPF_FUNC_probe_write_user,
-
+ __BPF_FUNC_MAPPER(__BPF_ENUM_FN)
__BPF_FUNC_MAX_ID,
};
+#undef __BPF_ENUM_FN
/* All flags used by eBPF helper functions, placed here. */
@@ -392,6 +529,7 @@ enum bpf_func_id {
/* BPF_FUNC_l4_csum_replace flags. */
#define BPF_F_PSEUDO_HDR (1ULL << 4)
#define BPF_F_MARK_MANGLED_0 (1ULL << 5)
+#define BPF_F_MARK_ENFORCE (1ULL << 6)
/* BPF_FUNC_clone_redirect and BPF_FUNC_redirect flags. */
#define BPF_F_INGRESS (1ULL << 0)
@@ -450,6 +588,31 @@ struct bpf_tunnel_key {
__u32 tunnel_label;
};
+/* Generic BPF return codes which all BPF program types may support.
+ * The values are binary compatible with their TC_ACT_* counter-part to
+ * provide backwards compatibility with existing SCHED_CLS and SCHED_ACT
+ * programs.
+ *
+ * XDP is handled seprately, see XDP_*.
+ */
+enum bpf_ret_code {
+ BPF_OK = 0,
+ /* 1 reserved */
+ BPF_DROP = 2,
+ /* 3-6 reserved */
+ BPF_REDIRECT = 7,
+ /* >127 are reserved for prog type specific return codes */
+};
+
+struct bpf_sock {
+ __u32 bound_dev_if;
+ __u32 family;
+ __u32 type;
+ __u32 protocol;
+};
+
+#define XDP_PACKET_HEADROOM 256
+
/* User return codes for XDP prog type.
* A valid XDP program must return one of these defined values. All other
* return codes are reserved for future use. Unknown return codes will result
diff --git a/tools/include/uapi/linux/hw_breakpoint.h b/tools/include/uapi/linux/hw_breakpoint.h
index b04000a2296a..2b65efd19a46 100644
--- a/tools/include/uapi/linux/hw_breakpoint.h
+++ b/tools/include/uapi/linux/hw_breakpoint.h
@@ -4,7 +4,11 @@
enum {
HW_BREAKPOINT_LEN_1 = 1,
HW_BREAKPOINT_LEN_2 = 2,
+ HW_BREAKPOINT_LEN_3 = 3,
HW_BREAKPOINT_LEN_4 = 4,
+ HW_BREAKPOINT_LEN_5 = 5,
+ HW_BREAKPOINT_LEN_6 = 6,
+ HW_BREAKPOINT_LEN_7 = 7,
HW_BREAKPOINT_LEN_8 = 8,
};
diff --git a/tools/leds/.gitignore b/tools/leds/.gitignore
new file mode 100644
index 000000000000..ac96d9f53dfc
--- /dev/null
+++ b/tools/leds/.gitignore
@@ -0,0 +1 @@
+uledmon
diff --git a/tools/leds/Makefile b/tools/leds/Makefile
new file mode 100644
index 000000000000..078b666fd78b
--- /dev/null
+++ b/tools/leds/Makefile
@@ -0,0 +1,13 @@
+# Makefile for LEDs tools
+
+CC = $(CROSS_COMPILE)gcc
+CFLAGS = -Wall -Wextra -g -I../../include/uapi
+
+all: uledmon led_hw_brightness_mon
+%: %.c
+ $(CC) $(CFLAGS) -o $@ $^
+
+clean:
+ $(RM) uledmon led_hw_brightness_mon
+
+.PHONY: all clean
diff --git a/tools/leds/led_hw_brightness_mon.c b/tools/leds/led_hw_brightness_mon.c
new file mode 100644
index 000000000000..64642ccfe442
--- /dev/null
+++ b/tools/leds/led_hw_brightness_mon.c
@@ -0,0 +1,84 @@
+/*
+ * led_hw_brightness_mon.c
+ *
+ * This program monitors LED brightness level changes having its origin
+ * in hardware/firmware, i.e. outside of kernel control.
+ * A timestamp and brightness value is printed each time the brightness changes.
+ *
+ * Usage: led_hw_brightness_mon <device-name>
+ *
+ * <device-name> is the name of the LED class device to be monitored. Pressing
+ * CTRL+C will exit.
+ */
+
+#include <errno.h>
+#include <fcntl.h>
+#include <poll.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <time.h>
+#include <unistd.h>
+
+#include <linux/uleds.h>
+
+int main(int argc, char const *argv[])
+{
+ int fd, ret;
+ char brightness_file_path[LED_MAX_NAME_SIZE + 11];
+ struct pollfd pollfd;
+ struct timespec ts;
+ char buf[11];
+
+ if (argc != 2) {
+ fprintf(stderr, "Requires <device-name> argument\n");
+ return 1;
+ }
+
+ snprintf(brightness_file_path, LED_MAX_NAME_SIZE,
+ "/sys/class/leds/%s/brightness_hw_changed", argv[1]);
+
+ fd = open(brightness_file_path, O_RDONLY);
+ if (fd == -1) {
+ printf("Failed to open %s file\n", brightness_file_path);
+ return 1;
+ }
+
+ /*
+ * read may fail if no hw brightness change has occurred so far,
+ * but it is required to avoid spurious poll notifications in
+ * the opposite case.
+ */
+ read(fd, buf, sizeof(buf));
+
+ pollfd.fd = fd;
+ pollfd.events = POLLPRI;
+
+ while (1) {
+ ret = poll(&pollfd, 1, -1);
+ if (ret == -1) {
+ printf("Failed to poll %s file (%d)\n",
+ brightness_file_path, ret);
+ ret = 1;
+ break;
+ }
+
+ clock_gettime(CLOCK_MONOTONIC, &ts);
+
+ ret = read(fd, buf, sizeof(buf));
+ if (ret < 0)
+ break;
+
+ ret = lseek(pollfd.fd, 0, SEEK_SET);
+ if (ret < 0) {
+ printf("lseek failed (%d)\n", ret);
+ break;
+ }
+
+ printf("[%ld.%09ld] %d\n", ts.tv_sec, ts.tv_nsec, atoi(buf));
+ }
+
+ close(fd);
+
+ return ret;
+}
diff --git a/tools/leds/uledmon.c b/tools/leds/uledmon.c
new file mode 100644
index 000000000000..25cbc7acf50a
--- /dev/null
+++ b/tools/leds/uledmon.c
@@ -0,0 +1,63 @@
+/*
+ * uledmon.c
+ *
+ * This program creates a new userspace LED class device and monitors it. A
+ * timestamp and brightness value is printed each time the brightness changes.
+ *
+ * Usage: uledmon <device-name>
+ *
+ * <device-name> is the name of the LED class device to be created. Pressing
+ * CTRL+C will exit.
+ */
+
+#include <fcntl.h>
+#include <stdio.h>
+#include <string.h>
+#include <time.h>
+#include <unistd.h>
+
+#include <linux/uleds.h>
+
+int main(int argc, char const *argv[])
+{
+ struct uleds_user_dev uleds_dev;
+ int fd, ret;
+ int brightness;
+ struct timespec ts;
+
+ if (argc != 2) {
+ fprintf(stderr, "Requires <device-name> argument\n");
+ return 1;
+ }
+
+ strncpy(uleds_dev.name, argv[1], LED_MAX_NAME_SIZE);
+ uleds_dev.max_brightness = 100;
+
+ fd = open("/dev/uleds", O_RDWR);
+ if (fd == -1) {
+ perror("Failed to open /dev/uleds");
+ return 1;
+ }
+
+ ret = write(fd, &uleds_dev, sizeof(uleds_dev));
+ if (ret == -1) {
+ perror("Failed to write to /dev/uleds");
+ close(fd);
+ return 1;
+ }
+
+ while (1) {
+ ret = read(fd, &brightness, sizeof(brightness));
+ if (ret == -1) {
+ perror("Failed to read from /dev/uleds");
+ close(fd);
+ return 1;
+ }
+ clock_gettime(CLOCK_MONOTONIC, &ts);
+ printf("[%ld.%09ld] %u\n", ts.tv_sec, ts.tv_nsec, brightness);
+ }
+
+ close(fd);
+
+ return 0;
+}
diff --git a/tools/lib/api/Makefile b/tools/lib/api/Makefile
index 0a6fda9837f7..eb6e0b36bfc1 100644
--- a/tools/lib/api/Makefile
+++ b/tools/lib/api/Makefile
@@ -2,7 +2,7 @@ include ../../scripts/Makefile.include
include ../../scripts/utilities.mak # QUIET_CLEAN
ifeq ($(srctree),)
-srctree := $(patsubst %/,%,$(dir $(shell pwd)))
+srctree := $(patsubst %/,%,$(dir $(CURDIR)))
srctree := $(patsubst %/,%,$(dir $(srctree)))
srctree := $(patsubst %/,%,$(dir $(srctree)))
#$(info Determined 'srctree' to be $(srctree))
@@ -17,7 +17,13 @@ MAKEFLAGS += --no-print-directory
LIBFILE = $(OUTPUT)libapi.a
CFLAGS := $(EXTRA_WARNINGS) $(EXTRA_CFLAGS)
-CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -O6 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -fPIC
+CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -fPIC
+
+ifeq ($(CC), clang)
+ CFLAGS += -O3
+else
+ CFLAGS += -O6
+endif
# Treat warnings as errors unless directed not to
ifneq ($(WERROR),0)
diff --git a/tools/lib/api/fs/fs.c b/tools/lib/api/fs/fs.c
index f99f49e4a31e..4b6bfc43cccf 100644
--- a/tools/lib/api/fs/fs.c
+++ b/tools/lib/api/fs/fs.c
@@ -38,6 +38,10 @@
#define HUGETLBFS_MAGIC 0x958458f6
#endif
+#ifndef BPF_FS_MAGIC
+#define BPF_FS_MAGIC 0xcafe4a11
+#endif
+
static const char * const sysfs__fs_known_mountpoints[] = {
"/sys",
0,
@@ -75,6 +79,11 @@ static const char * const hugetlbfs__known_mountpoints[] = {
0,
};
+static const char * const bpf_fs__known_mountpoints[] = {
+ "/sys/fs/bpf",
+ 0,
+};
+
struct fs {
const char *name;
const char * const *mounts;
@@ -89,6 +98,7 @@ enum {
FS__DEBUGFS = 2,
FS__TRACEFS = 3,
FS__HUGETLBFS = 4,
+ FS__BPF_FS = 5,
};
#ifndef TRACEFS_MAGIC
@@ -121,6 +131,11 @@ static struct fs fs__entries[] = {
.mounts = hugetlbfs__known_mountpoints,
.magic = HUGETLBFS_MAGIC,
},
+ [FS__BPF_FS] = {
+ .name = "bpf",
+ .mounts = bpf_fs__known_mountpoints,
+ .magic = BPF_FS_MAGIC,
+ },
};
static bool fs__read_mounts(struct fs *fs)
@@ -280,6 +295,7 @@ FS(procfs, FS__PROCFS);
FS(debugfs, FS__DEBUGFS);
FS(tracefs, FS__TRACEFS);
FS(hugetlbfs, FS__HUGETLBFS);
+FS(bpf_fs, FS__BPF_FS);
int filename__read_int(const char *filename, int *value)
{
diff --git a/tools/lib/api/fs/fs.h b/tools/lib/api/fs/fs.h
index a63269f5d20c..6b332dc74498 100644
--- a/tools/lib/api/fs/fs.h
+++ b/tools/lib/api/fs/fs.h
@@ -22,6 +22,7 @@ FS(procfs)
FS(debugfs)
FS(tracefs)
FS(hugetlbfs)
+FS(bpf_fs)
#undef FS
diff --git a/tools/lib/api/fs/tracing_path.c b/tools/lib/api/fs/tracing_path.c
index 251b7c342a87..3e606b9c443e 100644
--- a/tools/lib/api/fs/tracing_path.c
+++ b/tools/lib/api/fs/tracing_path.c
@@ -86,9 +86,13 @@ void put_tracing_file(char *file)
free(file);
}
-static int strerror_open(int err, char *buf, size_t size, const char *filename)
+int tracing_path__strerror_open_tp(int err, char *buf, size_t size,
+ const char *sys, const char *name)
{
char sbuf[128];
+ char filename[PATH_MAX];
+
+ snprintf(filename, PATH_MAX, "%s/%s", sys, name ?: "*");
switch (err) {
case ENOENT:
@@ -99,10 +103,19 @@ static int strerror_open(int err, char *buf, size_t size, const char *filename)
* - jirka
*/
if (debugfs__configured() || tracefs__configured()) {
- snprintf(buf, size,
- "Error:\tFile %s/%s not found.\n"
- "Hint:\tPerhaps this kernel misses some CONFIG_ setting to enable this feature?.\n",
- tracing_events_path, filename);
+ /* sdt markers */
+ if (!strncmp(filename, "sdt_", 4)) {
+ snprintf(buf, size,
+ "Error:\tFile %s/%s not found.\n"
+ "Hint:\tSDT event cannot be directly recorded on.\n"
+ "\tPlease first use 'perf probe %s:%s' before recording it.\n",
+ tracing_events_path, filename, sys, name);
+ } else {
+ snprintf(buf, size,
+ "Error:\tFile %s/%s not found.\n"
+ "Hint:\tPerhaps this kernel misses some CONFIG_ setting to enable this feature?.\n",
+ tracing_events_path, filename);
+ }
break;
}
snprintf(buf, size, "%s",
@@ -125,12 +138,3 @@ static int strerror_open(int err, char *buf, size_t size, const char *filename)
return 0;
}
-
-int tracing_path__strerror_open_tp(int err, char *buf, size_t size, const char *sys, const char *name)
-{
- char path[PATH_MAX];
-
- snprintf(path, PATH_MAX, "%s/%s", sys, name ?: "*");
-
- return strerror_open(err, buf, size, path);
-}
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index 62d89d50fcbd..e2efddf10231 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -7,7 +7,7 @@ BPF_EXTRAVERSION = 1
MAKEFLAGS += --no-print-directory
ifeq ($(srctree),)
-srctree := $(patsubst %/,%,$(dir $(shell pwd)))
+srctree := $(patsubst %/,%,$(dir $(CURDIR)))
srctree := $(patsubst %/,%,$(dir $(srctree)))
srctree := $(patsubst %/,%,$(dir $(srctree)))
#$(info Determined 'srctree' to be $(srctree))
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 4212ed62235b..207c2eeddab0 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -27,7 +27,7 @@
#include "bpf.h"
/*
- * When building perf, unistd.h is overrided. __NR_bpf is
+ * When building perf, unistd.h is overridden. __NR_bpf is
* required to be defined explicitly.
*/
#ifndef __NR_bpf
@@ -42,19 +42,19 @@
# endif
#endif
-static __u64 ptr_to_u64(void *ptr)
+static inline __u64 ptr_to_u64(const void *ptr)
{
return (__u64) (unsigned long) ptr;
}
-static int sys_bpf(enum bpf_cmd cmd, union bpf_attr *attr,
- unsigned int size)
+static inline int sys_bpf(enum bpf_cmd cmd, union bpf_attr *attr,
+ unsigned int size)
{
return syscall(__NR_bpf, cmd, attr, size);
}
int bpf_create_map(enum bpf_map_type map_type, int key_size,
- int value_size, int max_entries)
+ int value_size, int max_entries, __u32 map_flags)
{
union bpf_attr attr;
@@ -64,13 +64,14 @@ int bpf_create_map(enum bpf_map_type map_type, int key_size,
attr.key_size = key_size;
attr.value_size = value_size;
attr.max_entries = max_entries;
+ attr.map_flags = map_flags;
return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
}
-int bpf_load_program(enum bpf_prog_type type, struct bpf_insn *insns,
- size_t insns_cnt, char *license,
- u32 kern_version, char *log_buf, size_t log_buf_sz)
+int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns,
+ size_t insns_cnt, const char *license,
+ __u32 kern_version, char *log_buf, size_t log_buf_sz)
{
int fd;
union bpf_attr attr;
@@ -97,8 +98,8 @@ int bpf_load_program(enum bpf_prog_type type, struct bpf_insn *insns,
return sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr));
}
-int bpf_map_update_elem(int fd, void *key, void *value,
- u64 flags)
+int bpf_map_update_elem(int fd, const void *key, const void *value,
+ __u64 flags)
{
union bpf_attr attr;
@@ -110,3 +111,84 @@ int bpf_map_update_elem(int fd, void *key, void *value,
return sys_bpf(BPF_MAP_UPDATE_ELEM, &attr, sizeof(attr));
}
+
+int bpf_map_lookup_elem(int fd, const void *key, void *value)
+{
+ union bpf_attr attr;
+
+ bzero(&attr, sizeof(attr));
+ attr.map_fd = fd;
+ attr.key = ptr_to_u64(key);
+ attr.value = ptr_to_u64(value);
+
+ return sys_bpf(BPF_MAP_LOOKUP_ELEM, &attr, sizeof(attr));
+}
+
+int bpf_map_delete_elem(int fd, const void *key)
+{
+ union bpf_attr attr;
+
+ bzero(&attr, sizeof(attr));
+ attr.map_fd = fd;
+ attr.key = ptr_to_u64(key);
+
+ return sys_bpf(BPF_MAP_DELETE_ELEM, &attr, sizeof(attr));
+}
+
+int bpf_map_get_next_key(int fd, const void *key, void *next_key)
+{
+ union bpf_attr attr;
+
+ bzero(&attr, sizeof(attr));
+ attr.map_fd = fd;
+ attr.key = ptr_to_u64(key);
+ attr.next_key = ptr_to_u64(next_key);
+
+ return sys_bpf(BPF_MAP_GET_NEXT_KEY, &attr, sizeof(attr));
+}
+
+int bpf_obj_pin(int fd, const char *pathname)
+{
+ union bpf_attr attr;
+
+ bzero(&attr, sizeof(attr));
+ attr.pathname = ptr_to_u64((void *)pathname);
+ attr.bpf_fd = fd;
+
+ return sys_bpf(BPF_OBJ_PIN, &attr, sizeof(attr));
+}
+
+int bpf_obj_get(const char *pathname)
+{
+ union bpf_attr attr;
+
+ bzero(&attr, sizeof(attr));
+ attr.pathname = ptr_to_u64((void *)pathname);
+
+ return sys_bpf(BPF_OBJ_GET, &attr, sizeof(attr));
+}
+
+int bpf_prog_attach(int prog_fd, int target_fd, enum bpf_attach_type type,
+ unsigned int flags)
+{
+ union bpf_attr attr;
+
+ bzero(&attr, sizeof(attr));
+ attr.target_fd = target_fd;
+ attr.attach_bpf_fd = prog_fd;
+ attr.attach_type = type;
+ attr.attach_flags = flags;
+
+ return sys_bpf(BPF_PROG_ATTACH, &attr, sizeof(attr));
+}
+
+int bpf_prog_detach(int target_fd, enum bpf_attach_type type)
+{
+ union bpf_attr attr;
+
+ bzero(&attr, sizeof(attr));
+ attr.target_fd = target_fd;
+ attr.attach_type = type;
+
+ return sys_bpf(BPF_PROG_DETACH, &attr, sizeof(attr));
+}
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index e8ba54087497..09c3dcac0496 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -22,17 +22,29 @@
#define __BPF_BPF_H
#include <linux/bpf.h>
+#include <stddef.h>
int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size,
- int max_entries);
+ int max_entries, __u32 map_flags);
/* Recommend log buffer size */
#define BPF_LOG_BUF_SIZE 65536
-int bpf_load_program(enum bpf_prog_type type, struct bpf_insn *insns,
- size_t insns_cnt, char *license,
- u32 kern_version, char *log_buf,
+int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns,
+ size_t insns_cnt, const char *license,
+ __u32 kern_version, char *log_buf,
size_t log_buf_sz);
-int bpf_map_update_elem(int fd, void *key, void *value,
- u64 flags);
+int bpf_map_update_elem(int fd, const void *key, const void *value,
+ __u64 flags);
+
+int bpf_map_lookup_elem(int fd, const void *key, void *value);
+int bpf_map_delete_elem(int fd, const void *key);
+int bpf_map_get_next_key(int fd, const void *key, void *next_key);
+int bpf_obj_pin(int fd, const char *pathname);
+int bpf_obj_get(const char *pathname);
+int bpf_prog_attach(int prog_fd, int attachable_fd, enum bpf_attach_type type,
+ unsigned int flags);
+int bpf_prog_detach(int attachable_fd, enum bpf_attach_type type);
+
+
#endif
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index b699aea9a025..ac6eb863b2a4 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -4,6 +4,7 @@
* Copyright (C) 2013-2015 Alexei Starovoitov <ast@kernel.org>
* Copyright (C) 2015 Wang Nan <wangnan0@huawei.com>
* Copyright (C) 2015 Huawei Inc.
+ * Copyright (C) 2017 Nicira, Inc.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
@@ -22,15 +23,21 @@
#include <stdlib.h>
#include <stdio.h>
#include <stdarg.h>
+#include <libgen.h>
#include <inttypes.h>
#include <string.h>
#include <unistd.h>
#include <fcntl.h>
#include <errno.h>
#include <asm/unistd.h>
+#include <linux/err.h>
#include <linux/kernel.h>
#include <linux/bpf.h>
#include <linux/list.h>
+#include <linux/limits.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <sys/vfs.h>
#include <libelf.h>
#include <gelf.h>
@@ -41,6 +48,10 @@
#define EM_BPF 247
#endif
+#ifndef BPF_FS_MAGIC
+#define BPF_FS_MAGIC 0xcafe4a11
+#endif
+
#define __printf(a, b) __attribute__((format(printf, a, b)))
__printf(1, 2)
@@ -185,6 +196,7 @@ struct bpf_program {
struct bpf_map {
int fd;
char *name;
+ size_t offset;
struct bpf_map_def def;
void *priv;
bpf_map_clear_priv_t clear_priv;
@@ -228,6 +240,10 @@ struct bpf_object {
* all objects.
*/
struct list_head list;
+
+ void *priv;
+ bpf_object_clear_priv_t clear_priv;
+
char path[];
};
#define obj_elf_valid(o) ((o)->efile.elf)
@@ -513,57 +529,106 @@ bpf_object__init_kversion(struct bpf_object *obj,
}
static int
-bpf_object__init_maps(struct bpf_object *obj, void *data,
- size_t size)
+bpf_object__validate_maps(struct bpf_object *obj)
{
- size_t nr_maps;
int i;
- nr_maps = size / sizeof(struct bpf_map_def);
- if (!data || !nr_maps) {
- pr_debug("%s doesn't need map definition\n",
- obj->path);
+ /*
+ * If there's only 1 map, the only error case should have been
+ * catched in bpf_object__init_maps().
+ */
+ if (!obj->maps || !obj->nr_maps || (obj->nr_maps == 1))
return 0;
- }
- pr_debug("maps in %s: %zd bytes\n", obj->path, size);
+ for (i = 1; i < obj->nr_maps; i++) {
+ const struct bpf_map *a = &obj->maps[i - 1];
+ const struct bpf_map *b = &obj->maps[i];
- obj->maps = calloc(nr_maps, sizeof(obj->maps[0]));
- if (!obj->maps) {
- pr_warning("alloc maps for object failed\n");
- return -ENOMEM;
+ if (b->offset - a->offset < sizeof(struct bpf_map_def)) {
+ pr_warning("corrupted map section in %s: map \"%s\" too small\n",
+ obj->path, a->name);
+ return -EINVAL;
+ }
}
- obj->nr_maps = nr_maps;
-
- for (i = 0; i < nr_maps; i++) {
- struct bpf_map_def *def = &obj->maps[i].def;
+ return 0;
+}
- /*
- * fill all fd with -1 so won't close incorrect
- * fd (fd=0 is stdin) when failure (zclose won't close
- * negative fd)).
- */
- obj->maps[i].fd = -1;
+static int compare_bpf_map(const void *_a, const void *_b)
+{
+ const struct bpf_map *a = _a;
+ const struct bpf_map *b = _b;
- /* Save map definition into obj->maps */
- *def = ((struct bpf_map_def *)data)[i];
- }
- return 0;
+ return a->offset - b->offset;
}
static int
-bpf_object__init_maps_name(struct bpf_object *obj)
+bpf_object__init_maps(struct bpf_object *obj)
{
- int i;
+ int i, map_idx, nr_maps = 0;
+ Elf_Scn *scn;
+ Elf_Data *data;
Elf_Data *symbols = obj->efile.symbols;
- if (!symbols || obj->efile.maps_shndx < 0)
+ if (obj->efile.maps_shndx < 0)
+ return -EINVAL;
+ if (!symbols)
return -EINVAL;
+ 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;
+ }
+
+ /*
+ * Count number of maps. Each map has a name.
+ * Array of maps is not supported: only the first element is
+ * considered.
+ *
+ * TODO: Detect array of map and report error.
+ */
for (i = 0; i < symbols->d_size / sizeof(GElf_Sym); i++) {
GElf_Sym sym;
- size_t map_idx;
+
+ if (!gelf_getsym(symbols, i, &sym))
+ continue;
+ if (sym.st_shndx != obj->efile.maps_shndx)
+ continue;
+ 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)
+ return 0;
+
+ obj->maps = calloc(nr_maps, sizeof(obj->maps[0]));
+ if (!obj->maps) {
+ pr_warning("alloc maps for object failed\n");
+ return -ENOMEM;
+ }
+ obj->nr_maps = nr_maps;
+
+ /*
+ * fill all fd with -1 so won't close incorrect
+ * fd (fd=0 is stdin) when failure (zclose won't close
+ * negative fd)).
+ */
+ for (i = 0; i < nr_maps; i++)
+ obj->maps[i].fd = -1;
+
+ /*
+ * Fill obj->maps using data in "maps" section.
+ */
+ for (i = 0, map_idx = 0; i < symbols->d_size / sizeof(GElf_Sym); i++) {
+ GElf_Sym sym;
const char *map_name;
+ struct bpf_map_def *def;
if (!gelf_getsym(symbols, i, &sym))
continue;
@@ -573,21 +638,27 @@ bpf_object__init_maps_name(struct bpf_object *obj)
map_name = elf_strptr(obj->efile.elf,
obj->efile.strtabidx,
sym.st_name);
- map_idx = sym.st_value / sizeof(struct bpf_map_def);
- if (map_idx >= obj->nr_maps) {
- pr_warning("index of map \"%s\" is buggy: %zu > %zu\n",
- map_name, map_idx, obj->nr_maps);
- continue;
+ obj->maps[map_idx].offset = sym.st_value;
+ if (sym.st_value + sizeof(struct bpf_map_def) > data->d_size) {
+ pr_warning("corrupted maps section in %s: last map \"%s\" too small\n",
+ obj->path, map_name);
+ return -EINVAL;
}
+
obj->maps[map_idx].name = strdup(map_name);
if (!obj->maps[map_idx].name) {
pr_warning("failed to alloc map name\n");
return -ENOMEM;
}
- pr_debug("map %zu is \"%s\"\n", map_idx,
+ pr_debug("map %d is \"%s\"\n", map_idx,
obj->maps[map_idx].name);
+ def = (struct bpf_map_def *)(data->d_buf + sym.st_value);
+ obj->maps[map_idx].def = *def;
+ map_idx++;
}
- return 0;
+
+ qsort(obj->maps, obj->nr_maps, sizeof(obj->maps[0]), compare_bpf_map);
+ return bpf_object__validate_maps(obj);
}
static int bpf_object__elf_collect(struct bpf_object *obj)
@@ -645,11 +716,9 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
err = bpf_object__init_kversion(obj,
data->d_buf,
data->d_size);
- else if (strcmp(name, "maps") == 0) {
- err = bpf_object__init_maps(obj, data->d_buf,
- data->d_size);
+ else if (strcmp(name, "maps") == 0)
obj->efile.maps_shndx = idx;
- } else if (sh.sh_type == SHT_SYMTAB) {
+ else if (sh.sh_type == SHT_SYMTAB) {
if (obj->efile.symbols) {
pr_warning("bpf: multiple SYMTAB in %s\n",
obj->path);
@@ -698,7 +767,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
return LIBBPF_ERRNO__FORMAT;
}
if (obj->efile.maps_shndx >= 0)
- err = bpf_object__init_maps_name(obj);
+ err = bpf_object__init_maps(obj);
out:
return err;
}
@@ -721,7 +790,7 @@ static int
bpf_program__collect_reloc(struct bpf_program *prog,
size_t nr_maps, GElf_Shdr *shdr,
Elf_Data *data, Elf_Data *symbols,
- int maps_shndx)
+ int maps_shndx, struct bpf_map *maps)
{
int i, nrels;
@@ -771,7 +840,15 @@ bpf_program__collect_reloc(struct bpf_program *prog,
return -LIBBPF_ERRNO__RELOC;
}
- map_idx = sym.st_value / sizeof(struct bpf_map_def);
+ /* 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 (map_idx >= nr_maps) {
pr_warning("bpf relocation: map_idx %d large than %d\n",
(int)map_idx, (int)nr_maps - 1);
@@ -796,7 +873,8 @@ bpf_object__create_maps(struct bpf_object *obj)
*pfd = bpf_create_map(def->type,
def->key_size,
def->value_size,
- def->max_entries);
+ def->max_entries,
+ 0);
if (*pfd < 0) {
size_t j;
int err = *pfd;
@@ -807,7 +885,7 @@ bpf_object__create_maps(struct bpf_object *obj)
zclose(obj->maps[j].fd);
return err;
}
- pr_debug("create map: fd=%d\n", *pfd);
+ pr_debug("create map %s: fd=%d\n", obj->maps[i].name, *pfd);
}
return 0;
@@ -894,7 +972,8 @@ static int bpf_object__collect_reloc(struct bpf_object *obj)
err = bpf_program__collect_reloc(prog, nr_maps,
shdr, data,
obj->efile.symbols,
- obj->efile.maps_shndx);
+ obj->efile.maps_shndx,
+ obj->maps);
if (err)
return err;
}
@@ -1168,6 +1247,191 @@ out:
return err;
}
+static int check_path(const char *path)
+{
+ struct statfs st_fs;
+ char *dname, *dir;
+ int err = 0;
+
+ if (path == NULL)
+ return -EINVAL;
+
+ dname = strdup(path);
+ if (dname == NULL)
+ return -ENOMEM;
+
+ dir = dirname(dname);
+ if (statfs(dir, &st_fs)) {
+ pr_warning("failed to statfs %s: %s\n", dir, strerror(errno));
+ err = -errno;
+ }
+ free(dname);
+
+ if (!err && st_fs.f_type != BPF_FS_MAGIC) {
+ pr_warning("specified path %s is not on BPF FS\n", path);
+ err = -EINVAL;
+ }
+
+ return err;
+}
+
+int bpf_program__pin_instance(struct bpf_program *prog, const char *path,
+ int instance)
+{
+ int err;
+
+ err = check_path(path);
+ if (err)
+ return err;
+
+ if (prog == NULL) {
+ pr_warning("invalid program pointer\n");
+ return -EINVAL;
+ }
+
+ if (instance < 0 || instance >= prog->instances.nr) {
+ pr_warning("invalid prog instance %d of prog %s (max %d)\n",
+ instance, prog->section_name, prog->instances.nr);
+ return -EINVAL;
+ }
+
+ if (bpf_obj_pin(prog->instances.fds[instance], path)) {
+ pr_warning("failed to pin program: %s\n", strerror(errno));
+ return -errno;
+ }
+ pr_debug("pinned program '%s'\n", path);
+
+ return 0;
+}
+
+static int make_dir(const char *path)
+{
+ int err = 0;
+
+ if (mkdir(path, 0700) && errno != EEXIST)
+ err = -errno;
+
+ if (err)
+ pr_warning("failed to mkdir %s: %s\n", path, strerror(-err));
+ return err;
+}
+
+int bpf_program__pin(struct bpf_program *prog, const char *path)
+{
+ int i, err;
+
+ err = check_path(path);
+ if (err)
+ return err;
+
+ if (prog == NULL) {
+ pr_warning("invalid program pointer\n");
+ return -EINVAL;
+ }
+
+ if (prog->instances.nr <= 0) {
+ pr_warning("no instances of prog %s to pin\n",
+ prog->section_name);
+ return -EINVAL;
+ }
+
+ err = make_dir(path);
+ if (err)
+ return err;
+
+ for (i = 0; i < prog->instances.nr; i++) {
+ char buf[PATH_MAX];
+ int len;
+
+ len = snprintf(buf, PATH_MAX, "%s/%d", path, i);
+ if (len < 0)
+ return -EINVAL;
+ else if (len >= PATH_MAX)
+ return -ENAMETOOLONG;
+
+ err = bpf_program__pin_instance(prog, buf, i);
+ if (err)
+ return err;
+ }
+
+ return 0;
+}
+
+int bpf_map__pin(struct bpf_map *map, const char *path)
+{
+ int err;
+
+ err = check_path(path);
+ if (err)
+ return err;
+
+ if (map == NULL) {
+ pr_warning("invalid map pointer\n");
+ return -EINVAL;
+ }
+
+ if (bpf_obj_pin(map->fd, path)) {
+ pr_warning("failed to pin map: %s\n", strerror(errno));
+ return -errno;
+ }
+
+ pr_debug("pinned map '%s'\n", path);
+ return 0;
+}
+
+int bpf_object__pin(struct bpf_object *obj, const char *path)
+{
+ struct bpf_program *prog;
+ struct bpf_map *map;
+ int err;
+
+ if (!obj)
+ return -ENOENT;
+
+ if (!obj->loaded) {
+ pr_warning("object not yet loaded; load it first\n");
+ return -ENOENT;
+ }
+
+ err = make_dir(path);
+ if (err)
+ return err;
+
+ bpf_map__for_each(map, obj) {
+ char buf[PATH_MAX];
+ int len;
+
+ len = snprintf(buf, PATH_MAX, "%s/%s", path,
+ bpf_map__name(map));
+ if (len < 0)
+ return -EINVAL;
+ else if (len >= PATH_MAX)
+ return -ENAMETOOLONG;
+
+ err = bpf_map__pin(map, buf);
+ if (err)
+ return err;
+ }
+
+ bpf_object__for_each_program(prog, obj) {
+ char buf[PATH_MAX];
+ int len;
+
+ len = snprintf(buf, PATH_MAX, "%s/%s", path,
+ prog->section_name);
+ if (len < 0)
+ return -EINVAL;
+ else if (len >= PATH_MAX)
+ return -ENAMETOOLONG;
+
+ err = bpf_program__pin(prog, buf);
+ if (err)
+ return err;
+ }
+
+ return 0;
+}
+
void bpf_object__close(struct bpf_object *obj)
{
size_t i;
@@ -1175,6 +1439,9 @@ void bpf_object__close(struct bpf_object *obj)
if (!obj)
return;
+ if (obj->clear_priv)
+ obj->clear_priv(obj, obj->priv);
+
bpf_object__elf_finish(obj);
bpf_object__unload(obj);
@@ -1228,6 +1495,22 @@ unsigned int bpf_object__kversion(struct bpf_object *obj)
return obj ? obj->kern_version : 0;
}
+int bpf_object__set_priv(struct bpf_object *obj, void *priv,
+ bpf_object_clear_priv_t clear_priv)
+{
+ if (obj->priv && obj->clear_priv)
+ obj->clear_priv(obj, obj->priv);
+
+ obj->priv = priv;
+ obj->clear_priv = clear_priv;
+ return 0;
+}
+
+void *bpf_object__priv(struct bpf_object *obj)
+{
+ return obj ? obj->priv : ERR_PTR(-EINVAL);
+}
+
struct bpf_program *
bpf_program__next(struct bpf_program *prev, struct bpf_object *obj)
{
@@ -1341,37 +1624,33 @@ static void bpf_program__set_type(struct bpf_program *prog,
prog->type = type;
}
-int bpf_program__set_tracepoint(struct bpf_program *prog)
-{
- if (!prog)
- return -EINVAL;
- bpf_program__set_type(prog, BPF_PROG_TYPE_TRACEPOINT);
- return 0;
-}
-
-int bpf_program__set_kprobe(struct bpf_program *prog)
-{
- if (!prog)
- return -EINVAL;
- bpf_program__set_type(prog, BPF_PROG_TYPE_KPROBE);
- return 0;
-}
-
static bool bpf_program__is_type(struct bpf_program *prog,
enum bpf_prog_type type)
{
return prog ? (prog->type == type) : false;
}
-bool bpf_program__is_tracepoint(struct bpf_program *prog)
-{
- return bpf_program__is_type(prog, BPF_PROG_TYPE_TRACEPOINT);
-}
-
-bool bpf_program__is_kprobe(struct bpf_program *prog)
-{
- return bpf_program__is_type(prog, BPF_PROG_TYPE_KPROBE);
-}
+#define BPF_PROG_TYPE_FNS(NAME, TYPE) \
+int bpf_program__set_##NAME(struct bpf_program *prog) \
+{ \
+ if (!prog) \
+ return -EINVAL; \
+ bpf_program__set_type(prog, TYPE); \
+ return 0; \
+} \
+ \
+bool bpf_program__is_##NAME(struct bpf_program *prog) \
+{ \
+ return bpf_program__is_type(prog, TYPE); \
+} \
+
+BPF_PROG_TYPE_FNS(socket_filter, BPF_PROG_TYPE_SOCKET_FILTER);
+BPF_PROG_TYPE_FNS(kprobe, BPF_PROG_TYPE_KPROBE);
+BPF_PROG_TYPE_FNS(sched_cls, BPF_PROG_TYPE_SCHED_CLS);
+BPF_PROG_TYPE_FNS(sched_act, BPF_PROG_TYPE_SCHED_ACT);
+BPF_PROG_TYPE_FNS(tracepoint, BPF_PROG_TYPE_TRACEPOINT);
+BPF_PROG_TYPE_FNS(xdp, BPF_PROG_TYPE_XDP);
+BPF_PROG_TYPE_FNS(perf_event, BPF_PROG_TYPE_PERF_EVENT);
int bpf_map__fd(struct bpf_map *map)
{
@@ -1447,3 +1726,22 @@ bpf_object__find_map_by_name(struct bpf_object *obj, const char *name)
}
return NULL;
}
+
+struct bpf_map *
+bpf_object__find_map_by_offset(struct bpf_object *obj, size_t offset)
+{
+ int i;
+
+ for (i = 0; i < obj->nr_maps; i++) {
+ if (obj->maps[i].offset == offset)
+ return &obj->maps[i];
+ }
+ return ERR_PTR(-ENOENT);
+}
+
+long libbpf_get_error(const void *ptr)
+{
+ if (IS_ERR(ptr))
+ return PTR_ERR(ptr);
+ return 0;
+}
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index dd7a513efb10..b30394f9947a 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -22,8 +22,9 @@
#define __BPF_LIBBPF_H
#include <stdio.h>
+#include <stdint.h>
#include <stdbool.h>
-#include <linux/err.h>
+#include <sys/types.h> // for size_t
enum libbpf_errno {
__LIBBPF_ERRNO__START = 4000,
@@ -64,6 +65,7 @@ struct bpf_object *bpf_object__open(const char *path);
struct bpf_object *bpf_object__open_buffer(void *obj_buf,
size_t obj_buf_sz,
const char *name);
+int bpf_object__pin(struct bpf_object *object, const char *path);
void bpf_object__close(struct bpf_object *object);
/* Load/unload object into/from kernel */
@@ -79,6 +81,11 @@ struct bpf_object *bpf_object__next(struct bpf_object *prev);
(pos) != NULL; \
(pos) = (tmp), (tmp) = bpf_object__next(tmp))
+typedef void (*bpf_object_clear_priv_t)(struct bpf_object *, void *);
+int bpf_object__set_priv(struct bpf_object *obj, void *priv,
+ bpf_object_clear_priv_t clear_priv);
+void *bpf_object__priv(struct bpf_object *prog);
+
/* Accessors of bpf_program. */
struct bpf_program;
struct bpf_program *bpf_program__next(struct bpf_program *prog,
@@ -100,6 +107,9 @@ void *bpf_program__priv(struct bpf_program *prog);
const char *bpf_program__title(struct bpf_program *prog, bool needs_copy);
int bpf_program__fd(struct bpf_program *prog);
+int bpf_program__pin_instance(struct bpf_program *prog, const char *path,
+ int instance);
+int bpf_program__pin(struct bpf_program *prog, const char *path);
struct bpf_insn;
@@ -168,11 +178,21 @@ int bpf_program__nth_fd(struct bpf_program *prog, int n);
/*
* Adjust type of bpf program. Default is kprobe.
*/
+int bpf_program__set_socket_filter(struct bpf_program *prog);
int bpf_program__set_tracepoint(struct bpf_program *prog);
int bpf_program__set_kprobe(struct bpf_program *prog);
+int bpf_program__set_sched_cls(struct bpf_program *prog);
+int bpf_program__set_sched_act(struct bpf_program *prog);
+int bpf_program__set_xdp(struct bpf_program *prog);
+int bpf_program__set_perf_event(struct bpf_program *prog);
+bool bpf_program__is_socket_filter(struct bpf_program *prog);
bool bpf_program__is_tracepoint(struct bpf_program *prog);
bool bpf_program__is_kprobe(struct bpf_program *prog);
+bool bpf_program__is_sched_cls(struct bpf_program *prog);
+bool bpf_program__is_sched_act(struct bpf_program *prog);
+bool bpf_program__is_xdp(struct bpf_program *prog);
+bool bpf_program__is_perf_event(struct bpf_program *prog);
/*
* We don't need __attribute__((packed)) now since it is
@@ -195,6 +215,13 @@ struct bpf_map;
struct bpf_map *
bpf_object__find_map_by_name(struct bpf_object *obj, const char *name);
+/*
+ * Get bpf_map through the offset of corresponding struct bpf_map_def
+ * in the bpf object file.
+ */
+struct bpf_map *
+bpf_object__find_map_by_offset(struct bpf_object *obj, size_t offset);
+
struct bpf_map *
bpf_map__next(struct bpf_map *map, struct bpf_object *obj);
#define bpf_map__for_each(pos, obj) \
@@ -210,5 +237,8 @@ typedef void (*bpf_map_clear_priv_t)(struct bpf_map *, void *);
int bpf_map__set_priv(struct bpf_map *map, void *priv,
bpf_map_clear_priv_t clear_priv);
void *bpf_map__priv(struct bpf_map *map);
+int bpf_map__pin(struct bpf_map *map, const char *path);
+
+long libbpf_get_error(const void *ptr);
#endif
diff --git a/tools/lib/find_bit.c b/tools/lib/find_bit.c
index 9122a9e80046..42c15f906aac 100644
--- a/tools/lib/find_bit.c
+++ b/tools/lib/find_bit.c
@@ -34,7 +34,7 @@ static unsigned long _find_next_bit(const unsigned long *addr,
{
unsigned long tmp;
- if (!nbits || start >= nbits)
+ if (unlikely(start >= nbits))
return nbits;
tmp = addr[start / BITS_PER_LONG] ^ invert;
@@ -82,3 +82,28 @@ unsigned long find_first_bit(const unsigned long *addr, unsigned long size)
return size;
}
#endif
+
+#ifndef find_first_zero_bit
+/*
+ * Find the first cleared bit in a memory region.
+ */
+unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size)
+{
+ unsigned long idx;
+
+ for (idx = 0; idx * BITS_PER_LONG < size; idx++) {
+ if (addr[idx] != ~0UL)
+ return min(idx * BITS_PER_LONG + ffz(addr[idx]), size);
+ }
+
+ return size;
+}
+#endif
+
+#ifndef find_next_zero_bit
+unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size,
+ unsigned long offset)
+{
+ return _find_next_bit(addr, size, offset, ~0UL);
+}
+#endif
diff --git a/tools/lib/lockdep/Makefile b/tools/lib/lockdep/Makefile
index 1d57af56814b..3bc0ef9f8923 100644
--- a/tools/lib/lockdep/Makefile
+++ b/tools/lib/lockdep/Makefile
@@ -50,7 +50,7 @@ ifndef VERBOSE
endif
ifeq ($(srctree),)
-srctree := $(patsubst %/,%,$(dir $(shell pwd)))
+srctree := $(patsubst %/,%,$(dir $(CURDIR)))
srctree := $(patsubst %/,%,$(dir $(srctree)))
srctree := $(patsubst %/,%,$(dir $(srctree)))
#$(info Determined 'srctree' to be $(srctree))
diff --git a/tools/lib/subcmd/Makefile b/tools/lib/subcmd/Makefile
index ce4b7e527566..3d1c3b5b5150 100644
--- a/tools/lib/subcmd/Makefile
+++ b/tools/lib/subcmd/Makefile
@@ -2,7 +2,7 @@ include ../../scripts/Makefile.include
include ../../scripts/utilities.mak # QUIET_CLEAN
ifeq ($(srctree),)
-srctree := $(patsubst %/,%,$(dir $(shell pwd)))
+srctree := $(patsubst %/,%,$(dir $(CURDIR)))
srctree := $(patsubst %/,%,$(dir $(srctree)))
srctree := $(patsubst %/,%,$(dir $(srctree)))
#$(info Determined 'srctree' to be $(srctree))
@@ -19,7 +19,13 @@ MAKEFLAGS += --no-print-directory
LIBFILE = $(OUTPUT)libsubcmd.a
CFLAGS := $(EXTRA_WARNINGS) $(EXTRA_CFLAGS)
-CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -O6 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -fPIC
+CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -fPIC
+
+ifeq ($(CC), clang)
+ CFLAGS += -O3
+else
+ CFLAGS += -O6
+endif
# Treat warnings as errors unless directed not to
ifneq ($(WERROR),0)
diff --git a/tools/lib/subcmd/parse-options.c b/tools/lib/subcmd/parse-options.c
index 981bb4481fd5..6bc24025d054 100644
--- a/tools/lib/subcmd/parse-options.c
+++ b/tools/lib/subcmd/parse-options.c
@@ -213,6 +213,9 @@ static int get_value(struct parse_opt_ctx_t *p,
else
err = get_arg(p, opt, flags, (const char **)opt->value);
+ if (opt->set)
+ *(bool *)opt->set = true;
+
/* PARSE_OPT_NOEMPTY: Allow NULL but disallow empty string. */
if (opt->flags & PARSE_OPT_NOEMPTY) {
const char *val = *(const char **)opt->value;
@@ -267,6 +270,8 @@ static int get_value(struct parse_opt_ctx_t *p,
}
if (get_arg(p, opt, flags, &arg))
return -1;
+ if (arg[0] == '-')
+ return opterror(opt, "expects an unsigned numerical value", flags);
*(unsigned int *)opt->value = strtol(arg, (char **)&s, 10);
if (*s)
return opterror(opt, "expects a numerical value", flags);
@@ -299,6 +304,8 @@ static int get_value(struct parse_opt_ctx_t *p,
}
if (get_arg(p, opt, flags, &arg))
return -1;
+ if (arg[0] == '-')
+ return opterror(opt, "expects an unsigned numerical value", flags);
*(u64 *)opt->value = strtoull(arg, (char **)&s, 10);
if (*s)
return opterror(opt, "expects a numerical value", flags);
@@ -314,12 +321,19 @@ static int get_value(struct parse_opt_ctx_t *p,
static int parse_short_opt(struct parse_opt_ctx_t *p, const struct option *options)
{
+retry:
for (; options->type != OPTION_END; options++) {
if (options->short_name == *p->opt) {
p->opt = p->opt[1] ? p->opt + 1 : NULL;
return get_value(p, options, OPT_SHORT);
}
}
+
+ if (options->parent) {
+ options = options->parent;
+ goto retry;
+ }
+
return -2;
}
@@ -333,6 +347,7 @@ static int parse_long_opt(struct parse_opt_ctx_t *p, const char *arg,
if (!arg_end)
arg_end = arg + strlen(arg);
+retry:
for (; options->type != OPTION_END; options++) {
const char *rest;
int flags = 0;
@@ -426,6 +441,12 @@ match:
}
if (abbrev_option)
return get_value(p, abbrev_option, abbrev_flags);
+
+ if (options->parent) {
+ options = options->parent;
+ goto retry;
+ }
+
return -2;
}
diff --git a/tools/lib/subcmd/parse-options.h b/tools/lib/subcmd/parse-options.h
index d60cab2726da..f054ca1b899d 100644
--- a/tools/lib/subcmd/parse-options.h
+++ b/tools/lib/subcmd/parse-options.h
@@ -1,6 +1,7 @@
#ifndef __SUBCMD_PARSE_OPTIONS_H
#define __SUBCMD_PARSE_OPTIONS_H
+#include <linux/kernel.h>
#include <stdbool.h>
#include <stdint.h>
@@ -109,11 +110,13 @@ struct option {
intptr_t defval;
bool *set;
void *data;
+ const struct option *parent;
};
#define check_vtype(v, type) ( BUILD_BUG_ON_ZERO(!__builtin_types_compatible_p(typeof(v), type)) + v )
#define OPT_END() { .type = OPTION_END }
+#define OPT_PARENT(p) { .type = OPTION_END, .parent = (p) }
#define OPT_ARGUMENT(l, h) { .type = OPTION_ARGUMENT, .long_name = (l), .help = (h) }
#define OPT_GROUP(h) { .type = OPTION_GROUP, .help = (h) }
#define OPT_BIT(s, l, v, h, b) { .type = OPTION_BIT, .short_name = (s), .long_name = (l), .value = check_vtype(v, int *), .help = (h), .defval = (b) }
@@ -130,27 +133,32 @@ struct option {
#define OPT_UINTEGER(s, l, v, h) { .type = OPTION_UINTEGER, .short_name = (s), .long_name = (l), .value = check_vtype(v, unsigned int *), .help = (h) }
#define OPT_LONG(s, l, v, h) { .type = OPTION_LONG, .short_name = (s), .long_name = (l), .value = check_vtype(v, long *), .help = (h) }
#define OPT_U64(s, l, v, h) { .type = OPTION_U64, .short_name = (s), .long_name = (l), .value = check_vtype(v, u64 *), .help = (h) }
-#define OPT_STRING(s, l, v, a, h) { .type = OPTION_STRING, .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), (a), .help = (h) }
+#define OPT_STRING(s, l, v, a, h) { .type = OPTION_STRING, .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), .argh = (a), .help = (h) }
#define OPT_STRING_OPTARG(s, l, v, a, h, d) \
{ .type = OPTION_STRING, .short_name = (s), .long_name = (l), \
- .value = check_vtype(v, const char **), (a), .help = (h), \
+ .value = check_vtype(v, const char **), .argh =(a), .help = (h), \
.flags = PARSE_OPT_OPTARG, .defval = (intptr_t)(d) }
-#define OPT_STRING_NOEMPTY(s, l, v, a, h) { .type = OPTION_STRING, .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), (a), .help = (h), .flags = PARSE_OPT_NOEMPTY}
+#define OPT_STRING_OPTARG_SET(s, l, v, os, a, h, d) \
+ { .type = OPTION_STRING, .short_name = (s), .long_name = (l), \
+ .value = check_vtype(v, const char **), .argh = (a), .help = (h), \
+ .flags = PARSE_OPT_OPTARG, .defval = (intptr_t)(d), \
+ .set = check_vtype(os, bool *)}
+#define OPT_STRING_NOEMPTY(s, l, v, a, h) { .type = OPTION_STRING, .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), .argh = (a), .help = (h), .flags = PARSE_OPT_NOEMPTY}
#define OPT_DATE(s, l, v, h) \
{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = "time", .help = (h), .callback = parse_opt_approxidate_cb }
#define OPT_CALLBACK(s, l, v, a, h, f) \
- { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), (a), .help = (h), .callback = (f) }
+ { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = (a), .help = (h), .callback = (f) }
#define OPT_CALLBACK_NOOPT(s, l, v, a, h, f) \
- { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), (a), .help = (h), .callback = (f), .flags = PARSE_OPT_NOARG }
+ { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = (a), .help = (h), .callback = (f), .flags = PARSE_OPT_NOARG }
#define OPT_CALLBACK_DEFAULT(s, l, v, a, h, f, d) \
- { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), (a), .help = (h), .callback = (f), .defval = (intptr_t)d, .flags = PARSE_OPT_LASTARG_DEFAULT }
+ { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = (a), .help = (h), .callback = (f), .defval = (intptr_t)d, .flags = PARSE_OPT_LASTARG_DEFAULT }
#define OPT_CALLBACK_DEFAULT_NOOPT(s, l, v, a, h, f, d) \
{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l),\
- .value = (v), (a), .help = (h), .callback = (f), .defval = (intptr_t)d,\
+ .value = (v), .arg = (a), .help = (h), .callback = (f), .defval = (intptr_t)d,\
.flags = PARSE_OPT_LASTARG_DEFAULT | PARSE_OPT_NOARG}
#define OPT_CALLBACK_OPTARG(s, l, v, d, a, h, f) \
{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), \
- .value = (v), (a), .help = (h), .callback = (f), \
+ .value = (v), .argh = (a), .help = (h), .callback = (f), \
.flags = PARSE_OPT_OPTARG, .data = (d) }
/* parse_options() will filter out the processed options and leave the
diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index 7851df1490e0..47076b15eebe 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -86,7 +86,7 @@ ifndef VERBOSE
endif
ifeq ($(srctree),)
-srctree := $(patsubst %/,%,$(dir $(shell pwd)))
+srctree := $(patsubst %/,%,$(dir $(CURDIR)))
srctree := $(patsubst %/,%,$(dir $(srctree)))
srctree := $(patsubst %/,%,$(dir $(srctree)))
#$(info Determined 'srctree' to be $(srctree))
@@ -99,8 +99,6 @@ libdir_SQ = $(subst ','\'',$(libdir))
libdir_relative_SQ = $(subst ','\'',$(libdir_relative))
plugin_dir_SQ = $(subst ','\'',$(plugin_dir))
-LIB_FILE = libtraceevent.a libtraceevent.so
-
CONFIG_INCLUDES =
CONFIG_LIBS =
CONFIG_FLAGS =
@@ -114,6 +112,9 @@ N =
EVENT_PARSE_VERSION = $(EP_VERSION).$(EP_PATCHLEVEL).$(EP_EXTRAVERSION)
+LIB_TARGET = libtraceevent.a libtraceevent.so.$(EVENT_PARSE_VERSION)
+LIB_INSTALL = libtraceevent.a libtraceevent.so*
+
INCLUDES = -I. -I $(srctree)/tools/include $(CONFIG_INCLUDES)
# Set compile option CFLAGS
@@ -156,11 +157,11 @@ PLUGINS += plugin_cfg80211.so
PLUGINS := $(addprefix $(OUTPUT),$(PLUGINS))
PLUGINS_IN := $(PLUGINS:.so=-in.o)
-TE_IN := $(OUTPUT)libtraceevent-in.o
-LIB_FILE := $(addprefix $(OUTPUT),$(LIB_FILE))
+TE_IN := $(OUTPUT)libtraceevent-in.o
+LIB_TARGET := $(addprefix $(OUTPUT),$(LIB_TARGET))
DYNAMIC_LIST_FILE := $(OUTPUT)libtraceevent-dynamic-list
-CMD_TARGETS = $(LIB_FILE) $(PLUGINS) $(DYNAMIC_LIST_FILE)
+CMD_TARGETS = $(LIB_TARGET) $(PLUGINS) $(DYNAMIC_LIST_FILE)
TARGETS = $(CMD_TARGETS)
@@ -171,8 +172,10 @@ all_cmd: $(CMD_TARGETS)
$(TE_IN): force
$(Q)$(MAKE) $(build)=libtraceevent
-$(OUTPUT)libtraceevent.so: $(TE_IN)
- $(QUIET_LINK)$(CC) --shared $^ -o $@
+$(OUTPUT)libtraceevent.so.$(EVENT_PARSE_VERSION): $(TE_IN)
+ $(QUIET_LINK)$(CC) --shared $^ -Wl,-soname,libtraceevent.so.$(EP_VERSION) -o $@
+ @ln -sf $(@F) $(OUTPUT)libtraceevent.so
+ @ln -sf $(@F) $(OUTPUT)libtraceevent.so.$(EP_VERSION)
$(OUTPUT)libtraceevent.a: $(TE_IN)
$(QUIET_LINK)$(RM) $@; $(AR) rcs $@ $^
@@ -236,11 +239,15 @@ TAGS: force
find . -name '*.[ch]' | xargs etags \
--regex='/_PE(\([^,)]*\).*/PEVENT_ERRNO__\1/'
+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'; \
- fi; \
- $(INSTALL) $1 '$(DESTDIR_SQ)$2'
+ $(call do_install_mkdir,$2); \
+ $(INSTALL) $(if $3,-m $3,) $1 '$(DESTDIR_SQ)$2'
endef
define do_install_plugins
@@ -250,20 +257,33 @@ define do_install_plugins
endef
define do_generate_dynamic_list_file
- (echo '{'; \
- $(NM) -u -D $1 | awk 'NF>1 {print "\t"$$2";"}' | sort -u; \
- echo '};'; \
- ) > $2
+ symbol_type=`$(NM) -u -D $1 | awk 'NF>1 {print $$1}' | \
+ xargs echo "U W w" | tr ' ' '\n' | sort -u | xargs echo`;\
+ if [ "$$symbol_type" = "U W w" ];then \
+ (echo '{'; \
+ $(NM) -u -D $1 | awk 'NF>1 {print "\t"$$2";"}' | sort -u;\
+ echo '};'; \
+ ) > $2; \
+ else \
+ (echo Either missing one of [$1] or bad version of $(NM)) 1>&2;\
+ fi
endef
install_lib: all_cmd install_plugins
- $(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_INSTALL) $(DESTDIR)$(libdir_SQ)
install_plugins: $(PLUGINS)
$(call QUIET_INSTALL, trace_plugins) \
$(call do_install_plugins, $(PLUGINS))
+install_headers:
+ $(call QUIET_INSTALL, headers) \
+ $(call do_install,event-parse.h,$(prefix)/include/traceevent,644); \
+ $(call do_install,event-utils.h,$(prefix)/include/traceevent,644); \
+ $(call do_install,kbuffer.h,$(prefix)/include/traceevent,644)
+
install: install_lib
clean:
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 664c90c8e22b..7ce724fc0544 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -33,6 +33,7 @@
#include <stdint.h>
#include <limits.h>
#include <linux/string.h>
+#include <linux/time64.h>
#include <netinet/in.h>
#include "event-parse.h"
@@ -830,6 +831,7 @@ static void free_arg(struct print_arg *arg)
free_flag_sym(arg->symbol.symbols);
break;
case PRINT_HEX:
+ case PRINT_HEX_STR:
free_arg(arg->hex.field);
free_arg(arg->hex.size);
break;
@@ -2628,10 +2630,11 @@ out_free:
}
static enum event_type
-process_hex(struct event_format *event, struct print_arg *arg, char **tok)
+process_hex_common(struct event_format *event, struct print_arg *arg,
+ char **tok, enum print_arg_type type)
{
memset(arg, 0, sizeof(*arg));
- arg->type = PRINT_HEX;
+ arg->type = type;
if (alloc_and_process_delim(event, ",", &arg->hex.field))
goto out;
@@ -2650,6 +2653,19 @@ out:
}
static enum event_type
+process_hex(struct event_format *event, struct print_arg *arg, char **tok)
+{
+ return process_hex_common(event, arg, tok, PRINT_HEX);
+}
+
+static enum event_type
+process_hex_str(struct event_format *event, struct print_arg *arg,
+ char **tok)
+{
+ return process_hex_common(event, arg, tok, PRINT_HEX_STR);
+}
+
+static enum event_type
process_int_array(struct event_format *event, struct print_arg *arg, char **tok)
{
memset(arg, 0, sizeof(*arg));
@@ -3008,6 +3024,10 @@ process_function(struct event_format *event, struct print_arg *arg,
free_token(token);
return process_hex(event, arg, tok);
}
+ if (strcmp(token, "__print_hex_str") == 0) {
+ free_token(token);
+ return process_hex_str(event, arg, tok);
+ }
if (strcmp(token, "__print_array") == 0) {
free_token(token);
return process_int_array(event, arg, tok);
@@ -3546,6 +3566,7 @@ eval_num_arg(void *data, int size, struct event_format *event, struct print_arg
case PRINT_SYMBOL:
case PRINT_INT_ARRAY:
case PRINT_HEX:
+ case PRINT_HEX_STR:
break;
case PRINT_TYPE:
val = eval_num_arg(data, size, event, arg->typecast.item);
@@ -3961,6 +3982,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
}
break;
case PRINT_HEX:
+ case PRINT_HEX_STR:
if (arg->hex.field->type == PRINT_DYNAMIC_ARRAY) {
unsigned long offset;
offset = pevent_read_number(pevent,
@@ -3980,7 +4002,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
}
len = eval_num_arg(data, size, event, arg->hex.size);
for (i = 0; i < len; i++) {
- if (i)
+ if (i && arg->type == PRINT_HEX)
trace_seq_putc(s, ' ');
trace_seq_printf(s, "%02x", hex[i]);
}
@@ -5191,11 +5213,11 @@ struct event_format *pevent_data_event_from_type(struct pevent *pevent, int type
}
/**
- * pevent_data_pid - parse the PID from raw data
+ * pevent_data_pid - parse the PID from record
* @pevent: a handle to the pevent
* @rec: the record to parse
*
- * This returns the PID from a raw data.
+ * This returns the PID from a record.
*/
int pevent_data_pid(struct pevent *pevent, struct pevent_record *rec)
{
@@ -5203,6 +5225,32 @@ int pevent_data_pid(struct pevent *pevent, struct pevent_record *rec)
}
/**
+ * pevent_data_preempt_count - parse the preempt count from the record
+ * @pevent: a handle to the pevent
+ * @rec: the record to parse
+ *
+ * This returns the preempt count from a record.
+ */
+int pevent_data_preempt_count(struct pevent *pevent, struct pevent_record *rec)
+{
+ return parse_common_pc(pevent, rec->data);
+}
+
+/**
+ * pevent_data_flags - parse the latency flags from the record
+ * @pevent: a handle to the pevent
+ * @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 pevent_data_flags(struct pevent *pevent, struct pevent_record *rec)
+{
+ return parse_common_flags(pevent, rec->data);
+}
+
+/**
* pevent_data_comm_from_pid - return the command line from PID
* @pevent: a handle to the pevent
* @pid: the PID of the task to search for
@@ -5424,8 +5472,8 @@ void pevent_print_event_time(struct pevent *pevent, struct trace_seq *s,
use_usec_format = is_timestamp_in_us(pevent->trace_clock,
use_trace_clock);
if (use_usec_format) {
- secs = record->ts / NSECS_PER_SEC;
- nsecs = record->ts - secs * NSECS_PER_SEC;
+ secs = record->ts / NSEC_PER_SEC;
+ nsecs = record->ts - secs * NSEC_PER_SEC;
}
if (pevent->latency_format) {
@@ -5437,10 +5485,10 @@ void pevent_print_event_time(struct pevent *pevent, struct trace_seq *s,
usecs = nsecs;
p = 9;
} else {
- usecs = (nsecs + 500) / NSECS_PER_USEC;
+ usecs = (nsecs + 500) / NSEC_PER_USEC;
/* To avoid usecs larger than 1 sec */
- if (usecs >= 1000000) {
- usecs -= 1000000;
+ if (usecs >= USEC_PER_SEC) {
+ usecs -= USEC_PER_SEC;
secs++;
}
p = 6;
@@ -5700,6 +5748,13 @@ static void print_args(struct print_arg *args)
print_args(args->hex.size);
printf(")");
break;
+ case PRINT_HEX_STR:
+ printf("__print_hex_str(");
+ print_args(args->hex.field);
+ printf(", ");
+ print_args(args->hex.size);
+ printf(")");
+ break;
case PRINT_INT_ARRAY:
printf("__print_array(");
print_args(args->int_array.field);
diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index 9ffde377e89d..66342804161c 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -172,9 +172,6 @@ struct pevent_plugin_option {
#define PEVENT_PLUGIN_OPTIONS_NAME MAKE_STR(PEVENT_PLUGIN_OPTIONS)
#define PEVENT_PLUGIN_ALIAS_NAME MAKE_STR(PEVENT_PLUGIN_ALIAS)
-#define NSECS_PER_SEC 1000000000ULL
-#define NSECS_PER_USEC 1000ULL
-
enum format_flags {
FIELD_IS_ARRAY = 1,
FIELD_IS_POINTER = 2,
@@ -295,6 +292,7 @@ enum print_arg_type {
PRINT_FUNC,
PRINT_BITMASK,
PRINT_DYNAMIC_ARRAY_LEN,
+ PRINT_HEX_STR,
};
struct print_arg {
@@ -712,6 +710,8 @@ void pevent_data_lat_fmt(struct pevent *pevent,
int pevent_data_type(struct pevent *pevent, struct pevent_record *rec);
struct event_format *pevent_data_event_from_type(struct pevent *pevent, int type);
int pevent_data_pid(struct pevent *pevent, struct pevent_record *rec);
+int pevent_data_preempt_count(struct pevent *pevent, struct pevent_record *rec);
+int pevent_data_flags(struct pevent *pevent, struct pevent_record *rec);
const char *pevent_data_comm_from_pid(struct pevent *pevent, int pid);
struct cmdline;
struct cmdline *pevent_data_pid_from_comm(struct pevent *pevent, const char *comm,
diff --git a/tools/lib/traceevent/kbuffer-parse.c b/tools/lib/traceevent/kbuffer-parse.c
index 65984f1c2974..c94e3641b046 100644
--- a/tools/lib/traceevent/kbuffer-parse.c
+++ b/tools/lib/traceevent/kbuffer-parse.c
@@ -315,6 +315,7 @@ static unsigned int old_update_pointers(struct kbuffer *kbuf)
extend += delta;
delta = extend;
ptr += 4;
+ length = 0;
break;
case OLD_RINGBUF_TYPE_TIME_STAMP:
diff --git a/tools/lib/traceevent/plugin_function.c b/tools/lib/traceevent/plugin_function.c
index a00ec190821a..42dbf73758f3 100644
--- a/tools/lib/traceevent/plugin_function.c
+++ b/tools/lib/traceevent/plugin_function.c
@@ -130,7 +130,7 @@ static int function_handler(struct trace_seq *s, struct pevent_record *record,
unsigned long long pfunction;
const char *func;
const char *parent;
- int index;
+ int index = 0;
if (pevent_get_field_val(s, event, "ip", record, &function, 1))
return trace_seq_putc(s, '!');
diff --git a/tools/lib/traceevent/plugin_sched_switch.c b/tools/lib/traceevent/plugin_sched_switch.c
index f1ce60065258..ec30c2fcbac0 100644
--- a/tools/lib/traceevent/plugin_sched_switch.c
+++ b/tools/lib/traceevent/plugin_sched_switch.c
@@ -111,7 +111,7 @@ static int sched_switch_handler(struct trace_seq *s,
trace_seq_printf(s, "%lld ", val);
if (pevent_get_field_val(s, event, "prev_prio", record, &val, 0) == 0)
- trace_seq_printf(s, "[%lld] ", val);
+ trace_seq_printf(s, "[%d] ", (int) val);
if (pevent_get_field_val(s, event, "prev_state", record, &val, 0) == 0)
write_state(s, val);
@@ -129,7 +129,7 @@ static int sched_switch_handler(struct trace_seq *s,
trace_seq_printf(s, "%lld", val);
if (pevent_get_field_val(s, event, "next_prio", record, &val, 0) == 0)
- trace_seq_printf(s, " [%lld]", val);
+ trace_seq_printf(s, " [%d]", (int) val);
return 0;
}
diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile
index 041b493ad3ab..27e019c09bd2 100644
--- a/tools/objtool/Makefile
+++ b/tools/objtool/Makefile
@@ -11,12 +11,12 @@ LD = ld
AR = ar
ifeq ($(srctree),)
-srctree := $(patsubst %/,%,$(dir $(shell pwd)))
+srctree := $(patsubst %/,%,$(dir $(CURDIR)))
srctree := $(patsubst %/,%,$(dir $(srctree)))
endif
SUBCMD_SRCDIR = $(srctree)/tools/lib/subcmd/
-LIBSUBCMD_OUTPUT = $(if $(OUTPUT),$(OUTPUT),$(PWD)/)
+LIBSUBCMD_OUTPUT = $(if $(OUTPUT),$(OUTPUT),$(CURDIR)/)
LIBSUBCMD = $(LIBSUBCMD_OUTPUT)libsubcmd.a
OBJTOOL := $(OUTPUT)objtool
diff --git a/tools/objtool/arch.h b/tools/objtool/arch.h
index f7350fcedc70..a59e061c0b4a 100644
--- a/tools/objtool/arch.h
+++ b/tools/objtool/arch.h
@@ -31,9 +31,8 @@
#define INSN_CALL_DYNAMIC 8
#define INSN_RETURN 9
#define INSN_CONTEXT_SWITCH 10
-#define INSN_BUG 11
-#define INSN_NOP 12
-#define INSN_OTHER 13
+#define INSN_NOP 11
+#define INSN_OTHER 12
#define INSN_LAST INSN_OTHER
int arch_decode_instruction(struct elf *elf, struct section *sec,
diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c
index 5e0dea2cdc01..6ac99e3266eb 100644
--- a/tools/objtool/arch/x86/decode.c
+++ b/tools/objtool/arch/x86/decode.c
@@ -118,9 +118,6 @@ int arch_decode_instruction(struct elf *elf, struct section *sec,
op2 == 0x35)
/* sysenter, sysret */
*type = INSN_CONTEXT_SWITCH;
- else if (op2 == 0x0b || op2 == 0xb9)
- /* ud2 */
- *type = INSN_BUG;
else if (op2 == 0x0d || op2 == 0x1f)
/* nopl/nopw */
*type = INSN_NOP;
@@ -150,9 +147,9 @@ int arch_decode_instruction(struct elf *elf, struct section *sec,
*type = INSN_RETURN;
break;
- case 0xc5: /* iret */
case 0xca: /* retf */
case 0xcb: /* retf */
+ case 0xcf: /* iret */
*type = INSN_CONTEXT_SWITCH;
break;
diff --git a/tools/objtool/builtin-check.c b/tools/objtool/builtin-check.c
index e8a1f699058a..066086dd59a8 100644
--- a/tools/objtool/builtin-check.c
+++ b/tools/objtool/builtin-check.c
@@ -51,7 +51,7 @@ struct instruction {
unsigned int len, state;
unsigned char type;
unsigned long immediate;
- bool alt_group, visited;
+ bool alt_group, visited, dead_end;
struct symbol *call_dest;
struct instruction *jump_dest;
struct list_head alts;
@@ -330,6 +330,54 @@ static int decode_instructions(struct objtool_file *file)
}
/*
+ * Find all uses of the unreachable() macro, which are code path dead ends.
+ */
+static int add_dead_ends(struct objtool_file *file)
+{
+ struct section *sec;
+ struct rela *rela;
+ struct instruction *insn;
+ bool found;
+
+ sec = find_section_by_name(file->elf, ".rela.discard.unreachable");
+ if (!sec)
+ return 0;
+
+ list_for_each_entry(rela, &sec->rela_list, list) {
+ if (rela->sym->type != STT_SECTION) {
+ WARN("unexpected relocation symbol type in %s", sec->name);
+ return -1;
+ }
+ insn = find_insn(file, rela->sym->sec, rela->addend);
+ if (insn)
+ insn = list_prev_entry(insn, list);
+ else if (rela->addend == rela->sym->sec->len) {
+ found = false;
+ list_for_each_entry_reverse(insn, &file->insn_list, list) {
+ if (insn->sec == rela->sym->sec) {
+ found = true;
+ break;
+ }
+ }
+
+ if (!found) {
+ WARN("can't find unreachable insn at %s+0x%x",
+ rela->sym->sec->name, rela->addend);
+ return -1;
+ }
+ } else {
+ WARN("can't find unreachable insn at %s+0x%x",
+ rela->sym->sec->name, rela->addend);
+ return -1;
+ }
+
+ insn->dead_end = true;
+ }
+
+ return 0;
+}
+
+/*
* Warnings shouldn't be reported for ignored functions.
*/
static void add_ignores(struct objtool_file *file)
@@ -757,11 +805,20 @@ static struct rela *find_switch_table(struct objtool_file *file,
insn->jump_dest->offset > orig_insn->offset))
break;
+ /* look for a relocation which references .rodata */
text_rela = find_rela_by_dest_range(insn->sec, insn->offset,
insn->len);
- if (text_rela && text_rela->sym == file->rodata->sym)
- return find_rela_by_dest(file->rodata,
- text_rela->addend);
+ if (!text_rela || text_rela->sym != file->rodata->sym)
+ continue;
+
+ /*
+ * Make sure the .rodata address isn't associated with a
+ * symbol. gcc jump tables are anonymous data.
+ */
+ if (find_symbol_containing(file->rodata, text_rela->addend))
+ continue;
+
+ return find_rela_by_dest(file->rodata, text_rela->addend);
}
return NULL;
@@ -843,6 +900,10 @@ static int decode_sections(struct objtool_file *file)
if (ret)
return ret;
+ ret = add_dead_ends(file);
+ if (ret)
+ return ret;
+
add_ignores(file);
ret = add_jump_destinations(file);
@@ -1037,13 +1098,13 @@ static int validate_branch(struct objtool_file *file,
return 0;
- case INSN_BUG:
- return 0;
-
default:
break;
}
+ if (insn->dead_end)
+ return 0;
+
insn = next_insn_same_sec(file, insn);
if (!insn) {
WARN("%s: unexpected end of section", sec->name);
@@ -1220,7 +1281,7 @@ int cmd_check(int argc, const char **argv)
INIT_LIST_HEAD(&file.insn_list);
hash_init(file.insn_hash);
- file.whitelist = find_section_by_name(file.elf, "__func_stack_frame_non_standard");
+ file.whitelist = find_section_by_name(file.elf, ".discard.func_stack_frame_non_standard");
file.rodata = find_section_by_name(file.elf, ".rodata");
file.ignore_unreachables = false;
file.c_file = find_section_by_name(file.elf, ".comment");
diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c
index 0d7983ac63ef..d897702ce742 100644
--- a/tools/objtool/elf.c
+++ b/tools/objtool/elf.c
@@ -85,6 +85,18 @@ struct symbol *find_symbol_by_offset(struct section *sec, unsigned long offset)
return NULL;
}
+struct symbol *find_symbol_containing(struct section *sec, unsigned long offset)
+{
+ struct symbol *sym;
+
+ list_for_each_entry(sym, &sec->symbol_list, list)
+ if (sym->type != STT_SECTION &&
+ offset >= sym->offset && offset < sym->offset + sym->len)
+ return sym;
+
+ return NULL;
+}
+
struct rela *find_rela_by_dest_range(struct section *sec, unsigned long offset,
unsigned int len)
{
diff --git a/tools/objtool/elf.h b/tools/objtool/elf.h
index aa1ff6596684..731973e1a3f5 100644
--- a/tools/objtool/elf.h
+++ b/tools/objtool/elf.h
@@ -79,6 +79,7 @@ struct elf {
struct elf *elf_open(const char *name);
struct section *find_section_by_name(struct elf *elf, const char *name);
struct symbol *find_symbol_by_offset(struct section *sec, unsigned long offset);
+struct symbol *find_symbol_containing(struct section *sec, unsigned long offset);
struct rela *find_rela_by_dest(struct section *sec, unsigned long offset);
struct rela *find_rela_by_dest_range(struct section *sec, unsigned long offset,
unsigned int len);
diff --git a/tools/perf/Build b/tools/perf/Build
index a43fae7f439a..9b79f8d7db50 100644
--- a/tools/perf/Build
+++ b/tools/perf/Build
@@ -3,10 +3,12 @@ perf-y += builtin-annotate.o
perf-y += builtin-config.o
perf-y += builtin-diff.o
perf-y += builtin-evlist.o
+perf-y += builtin-ftrace.o
perf-y += builtin-help.o
perf-y += builtin-sched.o
perf-y += builtin-buildid-list.o
perf-y += builtin-buildid-cache.o
+perf-y += builtin-kallsyms.o
perf-y += builtin-list.o
perf-y += builtin-record.o
perf-y += builtin-report.o
@@ -21,6 +23,7 @@ perf-y += builtin-inject.o
perf-y += builtin-mem.o
perf-y += builtin-data.o
perf-y += builtin-version.o
+perf-y += builtin-c2c.o
perf-$(CONFIG_AUDIT) += builtin-trace.o
perf-$(CONFIG_LIBELF) += builtin-probe.o
@@ -38,8 +41,7 @@ CFLAGS_builtin-help.o += $(paths)
CFLAGS_builtin-timechart.o += $(paths)
CFLAGS_perf.o += -DPERF_HTML_PATH="BUILD_STR($(htmldir_SQ))" \
-DPERF_EXEC_PATH="BUILD_STR($(perfexecdir_SQ))" \
- -DPREFIX="BUILD_STR($(prefix_SQ))" \
- -include $(OUTPUT)PERF-VERSION-FILE
+ -DPREFIX="BUILD_STR($(prefix_SQ))"
CFLAGS_builtin-trace.o += -DSTRACE_GROUPS_DIR="BUILD_STR($(STRACE_GROUPS_DIR_SQ))"
CFLAGS_builtin-report.o += -DTIPDIR="BUILD_STR($(tipdir_SQ))"
CFLAGS_builtin-report.o += -DDOCDIR="BUILD_STR($(srcdir_SQ)/Documentation)"
diff --git a/tools/perf/Documentation/intel-pt.txt b/tools/perf/Documentation/intel-pt.txt
index c6c8318e38a2..b0b3007d3c9c 100644
--- a/tools/perf/Documentation/intel-pt.txt
+++ b/tools/perf/Documentation/intel-pt.txt
@@ -550,6 +550,18 @@ Unless /proc/sys/kernel/perf_event_paranoid is set to -1, unprivileged users
have memory limits imposed upon them. That affects what buffer sizes they can
have as outlined above.
+The v4.2 kernel introduced support for a context switch metadata event,
+PERF_RECORD_SWITCH, which allows unprivileged users to see when their processes
+are scheduled out and in, just not by whom, which is left for the
+PERF_RECORD_SWITCH_CPU_WIDE, that is only accessible in system wide context,
+which in turn requires CAP_SYS_ADMIN.
+
+Please see the 45ac1403f564 ("perf: Add PERF_RECORD_SWITCH to indicate context
+switches") commit, that introduces these metadata events for further info.
+
+When working with kernels < v4.2, the following considerations must be taken,
+as the sched:sched_switch tracepoints will be used to receive such information:
+
Unless /proc/sys/kernel/perf_event_paranoid is set to -1, unprivileged users are
not permitted to use tracepoints which means there is insufficient side-band
information to decode Intel PT in per-cpu mode, and potentially workload-only
@@ -564,8 +576,11 @@ sched_switch tracepoint
-----------------------
The sched_switch tracepoint is used to provide side-band data for Intel PT
-decoding. sched_switch events are automatically added. e.g. the second event
-shown below
+decoding in kernels where the PERF_RECORD_SWITCH metadata event isn't
+available.
+
+The sched_switch events are automatically added. e.g. the second event shown
+below:
$ perf record -vv -e intel_pt//u uname
------------------------------------------------------------
diff --git a/tools/perf/Documentation/jitdump-specification.txt b/tools/perf/Documentation/jitdump-specification.txt
new file mode 100644
index 000000000000..4c62b0713651
--- /dev/null
+++ b/tools/perf/Documentation/jitdump-specification.txt
@@ -0,0 +1,170 @@
+JITDUMP specification version 2
+Last Revised: 09/15/2016
+Author: Stephane Eranian <eranian@gmail.com>
+
+--------------------------------------------------------
+| Revision | Date | Description |
+--------------------------------------------------------
+| 1 | 09/07/2016 | Initial revision |
+--------------------------------------------------------
+| 2 | 09/15/2016 | Add JIT_CODE_UNWINDING_INFO |
+--------------------------------------------------------
+
+
+I/ Introduction
+
+
+This document describes the jitdump file format. The file is generated by Just-In-time compiler runtimes to save meta-data information about the generated code, such as address, size, and name of generated functions, the native code generated, the source line information. The data may then be used by performance tools, such as Linux perf to generate function and assembly level profiles.
+
+The format is not specific to any particular programming language. It can be extended as need be.
+
+The format of the file is binary. It is self-describing in terms of endianness and is portable across multiple processor architectures.
+
+
+II/ Overview of the format
+
+
+The format requires only sequential accesses, i.e., append only mode. The file starts with a fixed size file header describing the version of the specification, the endianness.
+
+The header is followed by a series of records, each starting with a fixed size header describing the type of record and its size. It is, itself, followed by the payload for the record. Records can have a variable size even for a given type.
+
+Each entry in the file is timestamped. All timestamps must use the same clock source. The CLOCK_MONOTONIC clock source is recommended.
+
+
+III/ Jitdump file header format
+
+Each jitdump file starts with a fixed size header containing the following fields in order:
+
+
+* uint32_t magic : a magic number tagging the file type. The value is 4-byte long and represents the string "JiTD" in ASCII form. It is 0x4A695444 or 0x4454694a depending on the endianness. The field can be used to detect the endianness of the file
+* uint32_t version : a 4-byte value representing the format version. It is currently set to 2
+* uint32_t total_size: size in bytes of file header
+* uint32_t elf_mach : ELF architecture encoding (ELF e_machine value as specified in /usr/include/elf.h)
+* uint32_t pad1 : padding. Reserved for future use
+* uint32_t pid : JIT runtime process identification (OS specific)
+* uint64_t timestamp : timestamp of when the file was created
+* uint64_t flags : a bitmask of flags
+
+The flags currently defined are as follows:
+ * bit 0: JITDUMP_FLAGS_ARCH_TIMESTAMP : set if the jitdump file is using an architecture-specific timestamp clock source. For instance, on x86, one could use TSC directly
+
+IV/ Record header
+
+The file header is immediately followed by records. Each record starts with a fixed size header describing the record that follows.
+
+The record header is specified in order as follows:
+* uint32_t id : a value identifying the record type (see below)
+* uint32_t total_size: the size in bytes of the record including the header.
+* uint64_t timestamp : a timestamp of when the record was created.
+
+The following record types are defined:
+ * Value 0 : JIT_CODE_LOAD : record describing a jitted function
+ * Value 1 : JIT_CODE_MOVE : record describing an already jitted function which is moved
+ * Value 2 : JIT_CODE_DEBUG_INFO: record describing the debug information for a jitted function
+ * Value 3 : JIT_CODE_CLOSE : record marking the end of the jit runtime (optional)
+ * Value 4 : JIT_CODE_UNWINDING_INFO: record describing a function unwinding information
+
+ The payload of the record must immediately follow the record header without padding.
+
+V/ JIT_CODE_LOAD record
+
+
+ The record has the following fields following the fixed-size record header in order:
+ * uint32_t pid: OS process id of the runtime generating the jitted code
+ * uint32_t tid: OS thread identification of the runtime thread generating the jitted code
+ * uint64_t vma: virtual address of jitted code start
+ * uint64_t code_addr: code start address for the jitted code. By default vma = code_addr
+ * uint64_t code_size: size in bytes of the generated jitted code
+ * uint64_t code_index: unique identifier for the jitted code (see below)
+ * char[n]: function name in ASCII including the null termination
+ * native code: raw byte encoding of the jitted code
+
+ The record header total_size field is inclusive of all components:
+ * record header
+ * fixed-sized fields
+ * function name string, including termination
+ * native code length
+ * record specific variable data (e.g., array of data entries)
+
+The code_index is used to uniquely identify each jitted function. The index can be a monotonically increasing 64-bit value. Each time a function is jitted it gets a new number. This value is used in case the code for a function is moved and avoids having to issue another JIT_CODE_LOAD record.
+
+The format supports empty functions with no native code.
+
+
+VI/ JIT_CODE_MOVE record
+
+ The record type is optional.
+
+ The record has the following fields following the fixed-size record header in order:
+ * uint32_t pid : OS process id of the runtime generating the jitted code
+ * uint32_t tid : OS thread identification of the runtime thread generating the jitted code
+ * uint64_t vma : new virtual address of jitted code start
+ * uint64_t old_code_addr: previous code address for the same function
+ * uint64_t new_code_addr: alternate new code started address for the jitted code. By default it should be equal to the vma address.
+ * uint64_t code_size : size in bytes of the jitted code
+ * uint64_t code_index : index referring to the JIT_CODE_LOAD code_index record of when the function was initially jitted
+
+
+The MOVE record can be used in case an already jitted function is simply moved by the runtime inside the code cache.
+
+The JIT_CODE_MOVE record cannot come before the JIT_CODE_LOAD record for the same function name. The function cannot have changed name, otherwise a new JIT_CODE_LOAD record must be emitted.
+
+The code size of the function cannot change.
+
+
+VII/ JIT_DEBUG_INFO record
+
+The record type is optional.
+
+The record contains source lines debug information, i.e., a way to map a code address back to a source line. This information may be used by the performance tool.
+
+The record has the following fields following the fixed-size record header in order:
+ * uint64_t code_addr: address of function for which the debug information is generated
+ * uint64_t nr_entry : number of debug entries for the function
+ * debug_entry[n]: array of nr_entry debug entries for the function
+
+The debug_entry describes the source line information. It is defined as follows in order:
+* uint64_t code_addr: address of function for which the debug information is generated
+* uint32_t line : source file line number (starting at 1)
+* uint32_t discrim : column discriminator, 0 is default
+* char name[n] : source file name in ASCII, including null termination
+
+The debug_entry entries are saved in sequence but given that they have variable sizes due to the file name string, they cannot be indexed directly.
+They need to be walked sequentially. The next debug_entry is found at sizeof(debug_entry) + strlen(name) + 1.
+
+IMPORTANT:
+ The JIT_CODE_DEBUG for a given function must always be generated BEFORE the JIT_CODE_LOAD for the function. This facilitates greatly the parser for the jitdump file.
+
+
+VIII/ JIT_CODE_CLOSE record
+
+
+The record type is optional.
+
+The record is used as a marker for the end of the jitted runtime. It can be replaced by the end of the file.
+
+The JIT_CODE_CLOSE record does not have any specific fields, the record header contains all the information needed.
+
+
+IX/ JIT_CODE_UNWINDING_INFO
+
+
+The record type is optional.
+
+The record is used to describe the unwinding information for a jitted function.
+
+The record has the following fields following the fixed-size record header in order:
+
+uint64_t unwind_data_size : the size in bytes of the unwinding data table at the end of the record
+uint64_t eh_frame_hdr_size : the size in bytes of the DWARF EH Frame Header at the start of the unwinding data table at the end of the record
+uint64_t mapped_size : the size of the unwinding data mapped in memory
+const char unwinding_data[n]: an array of unwinding data, consisting of the EH Frame Header, followed by the actual EH Frame
+
+
+The EH Frame header follows the Linux Standard Base (LSB) specification as described in the document at https://refspecs.linuxfoundation.org/LSB_1.3.0/gLSB/gLSB/ehframehdr.html
+
+
+The EH Frame follows the LSB specicfication as described in the document at https://refspecs.linuxbase.org/LSB_3.0.0/LSB-PDA/LSB-PDA/ehframechpt.html
+
+
+NOTE: The mapped_size is generally either the same as unwind_data_size (if the unwinding data was mapped in memory by the running process) or zero (if the unwinding data is not mapped by the process). If the unwinding data was not mapped, then only the EH Frame Header will be read, which can be used to specify FP based unwinding for a function which does not have unwinding information.
diff --git a/tools/perf/Documentation/perf-annotate.txt b/tools/perf/Documentation/perf-annotate.txt
index 8ffbd272952d..a89273d8e744 100644
--- a/tools/perf/Documentation/perf-annotate.txt
+++ b/tools/perf/Documentation/perf-annotate.txt
@@ -39,6 +39,10 @@ OPTIONS
--verbose::
Be more verbose. (Show symbol address, etc)
+-q::
+--quiet::
+ Do not show any message. (Suppress -v)
+
-D::
--dump-raw-trace::
Dump raw trace in ASCII.
diff --git a/tools/perf/Documentation/perf-c2c.txt b/tools/perf/Documentation/perf-c2c.txt
new file mode 100644
index 000000000000..2da07e51e119
--- /dev/null
+++ b/tools/perf/Documentation/perf-c2c.txt
@@ -0,0 +1,290 @@
+perf-c2c(1)
+===========
+
+NAME
+----
+perf-c2c - Shared Data C2C/HITM Analyzer.
+
+SYNOPSIS
+--------
+[verse]
+'perf c2c record' [<options>] <command>
+'perf c2c record' [<options>] -- [<record command options>] <command>
+'perf c2c report' [<options>]
+
+DESCRIPTION
+-----------
+C2C stands for Cache To Cache.
+
+The perf c2c tool provides means for Shared Data C2C/HITM analysis. It allows
+you to track down the cacheline contentions.
+
+The tool is based on x86's load latency and precise store facility events
+provided by Intel CPUs. These events provide:
+ - memory address of the access
+ - type of the access (load and store details)
+ - latency (in cycles) of the load access
+
+The c2c tool provide means to record this data and report back access details
+for cachelines with highest contention - highest number of HITM accesses.
+
+The basic workflow with this tool follows the standard record/report phase.
+User uses the record command to record events data and report command to
+display it.
+
+
+RECORD OPTIONS
+--------------
+-e::
+--event=::
+ Select the PMU event. Use 'perf mem record -e list'
+ to list available events.
+
+-v::
+--verbose::
+ Be more verbose (show counter open errors, etc).
+
+-l::
+--ldlat::
+ Configure mem-loads latency.
+
+-k::
+--all-kernel::
+ Configure all used events to run in kernel space.
+
+-u::
+--all-user::
+ Configure all used events to run in user space.
+
+REPORT OPTIONS
+--------------
+-k::
+--vmlinux=<file>::
+ vmlinux pathname
+
+-v::
+--verbose::
+ Be more verbose (show counter open errors, etc).
+
+-i::
+--input::
+ Specify the input file to process.
+
+-N::
+--node-info::
+ Show extra node info in report (see NODE INFO section)
+
+-c::
+--coalesce::
+ Specify sorintg fields for single cacheline display.
+ Following fields are available: tid,pid,iaddr,dso
+ (see COALESCE)
+
+-g::
+--call-graph::
+ Setup callchains parameters.
+ Please refer to perf-report man page for details.
+
+--stdio::
+ Force the stdio output (see STDIO OUTPUT)
+
+--stats::
+ Display only statistic tables and force stdio mode.
+
+--full-symbols::
+ Display full length of symbols.
+
+--no-source::
+ Do not display Source:Line column.
+
+--show-all::
+ Show all captured HITM lines, with no regard to HITM % 0.0005 limit.
+
+-f::
+--force::
+ Don't do ownership validation.
+
+-d::
+--display::
+ Siwtch to HITM type (rmt, lcl) to display and sort on. Total HITMs as default.
+
+C2C RECORD
+----------
+The perf c2c record command setup options related to HITM cacheline analysis
+and calls standard perf record command.
+
+Following perf record options are configured by default:
+(check perf record man page for details)
+
+ -W,-d,--sample-cpu
+
+Unless specified otherwise with '-e' option, following events are monitored by
+default:
+
+ cpu/mem-loads,ldlat=30/P
+ cpu/mem-stores/P
+
+User can pass any 'perf record' option behind '--' mark, like (to enable
+callchains and system wide monitoring):
+
+ $ perf c2c record -- -g -a
+
+Please check RECORD OPTIONS section for specific c2c record options.
+
+C2C REPORT
+----------
+The perf c2c report command displays shared data analysis. It comes in two
+display modes: stdio and tui (default).
+
+The report command workflow is following:
+ - sort all the data based on the cacheline address
+ - store access details for each cacheline
+ - sort all cachelines based on user settings
+ - display data
+
+In general perf report output consist of 2 basic views:
+ 1) most expensive cachelines list
+ 2) offsets details for each cacheline
+
+For each cacheline in the 1) list we display following data:
+(Both stdio and TUI modes follow the same fields output)
+
+ Index
+ - zero based index to identify the cacheline
+
+ Cacheline
+ - cacheline address (hex number)
+
+ Total records
+ - sum of all cachelines accesses
+
+ Rmt/Lcl Hitm
+ - cacheline percentage of all Remote/Local HITM accesses
+
+ LLC Load Hitm - Total, Lcl, Rmt
+ - count of Total/Local/Remote load HITMs
+
+ Store Reference - Total, L1Hit, L1Miss
+ Total - all store accesses
+ L1Hit - store accesses that hit L1
+ L1Hit - store accesses that missed L1
+
+ Load Dram
+ - count of local and remote DRAM accesses
+
+ LLC Ld Miss
+ - count of all accesses that missed LLC
+
+ Total Loads
+ - sum of all load accesses
+
+ Core Load Hit - FB, L1, L2
+ - count of load hits in FB (Fill Buffer), L1 and L2 cache
+
+ LLC Load Hit - Llc, Rmt
+ - count of LLC and Remote load hits
+
+For each offset in the 2) list we display following data:
+
+ HITM - Rmt, Lcl
+ - % of Remote/Local HITM accesses for given offset within cacheline
+
+ Store Refs - L1 Hit, L1 Miss
+ - % of store accesses that hit/missed L1 for given offset within cacheline
+
+ Data address - Offset
+ - offset address
+
+ Pid
+ - pid of the process responsible for the accesses
+
+ Tid
+ - tid of the process responsible for the accesses
+
+ Code address
+ - code address responsible for the accesses
+
+ cycles - rmt hitm, lcl hitm, load
+ - sum of cycles for given accesses - Remote/Local HITM and generic load
+
+ cpu cnt
+ - number of cpus that participated on the access
+
+ Symbol
+ - code symbol related to the 'Code address' value
+
+ Shared Object
+ - shared object name related to the 'Code address' value
+
+ Source:Line
+ - source information related to the 'Code address' value
+
+ Node
+ - nodes participating on the access (see NODE INFO section)
+
+NODE INFO
+---------
+The 'Node' field displays nodes that accesses given cacheline
+offset. Its output comes in 3 flavors:
+ - node IDs separated by ','
+ - node IDs with stats for each ID, in following format:
+ Node{cpus %hitms %stores}
+ - node IDs with list of affected CPUs in following format:
+ Node{cpu list}
+
+User can switch between above flavors with -N option or
+use 'n' key to interactively switch in TUI mode.
+
+COALESCE
+--------
+User can specify how to sort offsets for cacheline.
+
+Following fields are available and governs the final
+output fields set for caheline offsets output:
+
+ tid - coalesced by process TIDs
+ pid - coalesced by process PIDs
+ iaddr - coalesced by code address, following fields are displayed:
+ Code address, Code symbol, Shared Object, Source line
+ dso - coalesced by shared object
+
+By default the coalescing is setup with 'pid,iaddr'.
+
+STDIO OUTPUT
+------------
+The stdio output displays data on standard output.
+
+Following tables are displayed:
+ Trace Event Information
+ - overall statistics of memory accesses
+
+ Global Shared Cache Line Event Information
+ - overall statistics on shared cachelines
+
+ Shared Data Cache Line Table
+ - list of most expensive cachelines
+
+ Shared Cache Line Distribution Pareto
+ - list of all accessed offsets for each cacheline
+
+TUI OUTPUT
+----------
+The TUI output provides interactive interface to navigate
+through cachelines list and to display offset details.
+
+For details please refer to the help window by pressing '?' key.
+
+CREDITS
+-------
+Although Don Zickus, Dick Fowles and Joe Mario worked together
+to get this implemented, we got lots of early help from Arnaldo
+Carvalho de Melo, Stephane Eranian, Jiri Olsa and Andi Kleen.
+
+C2C BLOG
+--------
+Check Joe's blog on c2c tool for detailed use case explanation:
+ https://joemario.github.io/blog/2016/09/01/c2c-blog/
+
+SEE ALSO
+--------
+linkperf:perf-record[1], linkperf:perf-mem[1]
diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt
index cb081ac59fd1..5b4fff3adc4b 100644
--- a/tools/perf/Documentation/perf-config.txt
+++ b/tools/perf/Documentation/perf-config.txt
@@ -8,6 +8,8 @@ perf-config - Get and set variables in a configuration file.
SYNOPSIS
--------
[verse]
+'perf config' [<file-option>] [section.name[=value] ...]
+or
'perf config' [<file-option>] -l | --list
DESCRIPTION
@@ -118,6 +120,39 @@ Given a $HOME/.perfconfig like this:
children = true
group = true
+You can hide source code of annotate feature setting the config to false with
+
+ % perf config annotate.hide_src_code=true
+
+If you want to add or modify several config items, you can do like
+
+ % perf config ui.show-headers=false kmem.default=slab
+
+To modify the sort order of report functionality in user config file(i.e. `~/.perfconfig`), do
+
+ % perf config --user report sort-order=srcline
+
+To change colors of selected line to other foreground and background colors
+in system config file (i.e. `$(sysconf)/perfconfig`), do
+
+ % perf config --system colors.selected=yellow,green
+
+To query the record mode of call graph, do
+
+ % perf config call-graph.record-mode
+
+If you want to know multiple config key/value pairs, you can do like
+
+ % perf config report.queue-size call-graph.order report.children
+
+To query the config value of sort order of call graph in user config file (i.e. `~/.perfconfig`), do
+
+ % perf config --user call-graph.sort-order
+
+To query the config value of buildid directory in system config file (i.e. `$(sysconf)/perfconfig`), do
+
+ % perf config --system buildid.dir
+
Variables
~~~~~~~~~
@@ -463,6 +498,18 @@ record.*::
But if this option is 'no-cache', it will not update the build-id cache.
'skip' skips post-processing and does not update the cache.
+diff.*::
+ diff.order::
+ This option sets the number of columns to sort the result.
+ The default is 0, which means sorting by baseline.
+ Setting it to 1 will sort the result by delta (or other
+ compute method selected).
+
+ diff.compute::
+ This options sets the method for computing the diff result.
+ Possible values are 'delta', 'delta-abs', 'ratio' and
+ 'wdiff'. Default is 'delta'.
+
SEE ALSO
--------
linkperf:perf[1]
diff --git a/tools/perf/Documentation/perf-diff.txt b/tools/perf/Documentation/perf-diff.txt
index 3e9490b9c533..a79c84ae61aa 100644
--- a/tools/perf/Documentation/perf-diff.txt
+++ b/tools/perf/Documentation/perf-diff.txt
@@ -73,6 +73,10 @@ OPTIONS
Be verbose, for instance, show the raw counts in addition to the
diff.
+-q::
+--quiet::
+ Do not show any message. (Suppress -v)
+
-f::
--force::
Don't do ownership validation.
@@ -86,8 +90,9 @@ OPTIONS
-c::
--compute::
- Differential computation selection - delta,ratio,wdiff (default is delta).
- See COMPARISON METHODS section for more info.
+ Differential computation selection - delta, ratio, wdiff, delta-abs
+ (default is delta-abs). Default can be changed using diff.compute
+ config option. See COMPARISON METHODS section for more info.
-p::
--period::
@@ -99,7 +104,11 @@ OPTIONS
-o::
--order::
- Specify compute sorting column number.
+ Specify compute sorting column number. 0 means sorting by baseline
+ overhead and 1 (default) means sorting by computed value of column 1
+ (data from the first file other base baseline). Values more than 1
+ can be used only if enough data files are provided.
+ The default value can be set using the diff.order config option.
--percentage::
Determine how to display the overhead percentage of filtered entries.
@@ -181,6 +190,10 @@ with:
relative to how entries are filtered. Use --percentage=absolute to
prevent such fluctuation.
+delta-abs
+~~~~~~~~~
+Same as 'delta` method, but sort the result with the absolute values.
+
ratio
~~~~~
If specified the 'Ratio' column is displayed with value 'r' computed as:
diff --git a/tools/perf/Documentation/perf-ftrace.txt b/tools/perf/Documentation/perf-ftrace.txt
new file mode 100644
index 000000000000..2d96de6132a9
--- /dev/null
+++ b/tools/perf/Documentation/perf-ftrace.txt
@@ -0,0 +1,36 @@
+perf-ftrace(1)
+=============
+
+NAME
+----
+perf-ftrace - simple wrapper for kernel's ftrace functionality
+
+
+SYNOPSIS
+--------
+[verse]
+'perf ftrace' <command>
+
+DESCRIPTION
+-----------
+The 'perf ftrace' command is a simple wrapper of kernel's ftrace
+functionality. It only supports single thread tracing currently and
+just reads trace_pipe in text and then write it to stdout.
+
+The following options apply to perf ftrace.
+
+OPTIONS
+-------
+
+-t::
+--tracer=::
+ Tracer to use: function_graph or function.
+
+-v::
+--verbose=::
+ Verbosity level.
+
+
+SEE ALSO
+--------
+linkperf:perf-record[1], linkperf:perf-trace[1]
diff --git a/tools/perf/Documentation/perf-kallsyms.txt b/tools/perf/Documentation/perf-kallsyms.txt
new file mode 100644
index 000000000000..954ea9e21236
--- /dev/null
+++ b/tools/perf/Documentation/perf-kallsyms.txt
@@ -0,0 +1,24 @@
+perf-kallsyms(1)
+==============
+
+NAME
+----
+perf-kallsyms - Searches running kernel for symbols
+
+SYNOPSIS
+--------
+[verse]
+'perf kallsyms <options> symbol_name[,symbol_name...]'
+
+DESCRIPTION
+-----------
+This command searches the running kernel kallsyms file for the given symbol(s)
+and prints information about it, including the DSO, the kallsyms begin/end
+addresses and the addresses in the ELF kallsyms symbol table (for symbols in
+modules).
+
+OPTIONS
+-------
+-v::
+--verbose=::
+ Increase verbosity level, showing details about symbol table loading, etc.
diff --git a/tools/perf/Documentation/perf-kmem.txt b/tools/perf/Documentation/perf-kmem.txt
index ff0f433b3fce..479fc3261a50 100644
--- a/tools/perf/Documentation/perf-kmem.txt
+++ b/tools/perf/Documentation/perf-kmem.txt
@@ -61,6 +61,13 @@ OPTIONS
default, but this option shows live (currently allocated) pages
instead. (This option works with --page option only)
+--time::
+ Only analyze samples within given time window: <start>,<stop>. Times
+ have the format seconds.microseconds. If start is not given (i.e., time
+ string is ',x.y') then analysis starts at the beginning of the file. If
+ stop time is not given (i.e, time string is 'x.y,') then analysis goes
+ to end of file.
+
SEE ALSO
--------
linkperf:perf-record[1]
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 92335193dc33..b16003ec14a7 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -45,9 +45,9 @@ OPTIONS
param1 and param2 are defined as formats for the PMU in:
/sys/bus/event_source/devices/<pmu>/format/*
- There are also some params which are not defined in .../<pmu>/format/*.
+ There are also some parameters which are not defined in .../<pmu>/format/*.
These params can be used to overload default config values per event.
- Here is a list of the params.
+ Here are some common parameters:
- 'period': Set event sampling period
- 'freq': Set event sampling frequency
- 'time': Disable/enable time stamping. Acceptable values are 1 for
@@ -57,8 +57,11 @@ OPTIONS
FP mode, "dwarf" for DWARF mode, "lbr" for LBR mode and
"no" for disable callgraph.
- 'stack-size': user stack size for dwarf mode
+
+ See the linkperf:perf-list[1] man page for more parameters.
+
Note: If user explicitly sets options which conflict with the params,
- the value set by the params will be overridden.
+ the value set by the parameters will be overridden.
Also not defined in .../<pmu>/format/* are PMU driver specific
configuration parameters. Any configuration parameter preceded by
@@ -154,7 +157,7 @@ OPTIONS
-a::
--all-cpus::
- System-wide collection from all CPUs.
+ System-wide collection from all CPUs (default if no target is specified).
-p::
--pid=::
@@ -418,15 +421,29 @@ Configure all used events to run in user space.
--timestamp-filename
Append timestamp to output file name.
---switch-output::
+--switch-output[=mode]::
Generate multiple perf.data files, timestamp prefixed, switching to a new one
-when receiving a SIGUSR2.
+based on 'mode' value:
+ "signal" - when receiving a SIGUSR2 (default value) or
+ <size> - when reaching the size threshold, size is expected to
+ be a number with appended unit character - B/K/M/G
+ <time> - when reaching the time threshold, size is expected to
+ be a number with appended unit character - s/m/h/d
+
+ Note: the precision of the size threshold hugely depends
+ on your configuration - the number and size of your ring
+ buffers (-m). It is generally more precise for higher sizes
+ (like >5M), for lower values expect different sizes.
A possible use case is to, given an external event, slice the perf.data file
that gets then processed, possibly via a perf script, to decide if that
particular perf.data snapshot should be kept or not.
Implies --timestamp-filename, --no-buildid and --no-buildid-cache.
+The reason for the latter two is to reduce the data file switching
+overhead. You can still switch them on with:
+
+ --switch-output --no-no-buildid --no-no-buildid-cache
--dry-run::
Parse options then exit. --dry-run can be used to detect errors in cmdline
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 2d1746295abf..c04cc0647c16 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -25,6 +25,10 @@ OPTIONS
--verbose::
Be more verbose. (show symbol address, etc)
+-q::
+--quiet::
+ Do not show any message. (Suppress -v)
+
-n::
--show-nr-samples::
Show the number of samples for each symbol
@@ -239,7 +243,8 @@ OPTIONS
Accumulate callchain of children to parent entry so that then can
show up in the output. The output will have a new "Children" column
and will be sorted on the data. It requires callchains are recorded.
- See the `overhead calculation' section for more details.
+ See the `overhead calculation' section for more details. Enabled by
+ default, disable with --no-children.
--max-stack::
Set the stack depth limit when parsing the callchain, anything
@@ -382,6 +387,13 @@ OPTIONS
--header-only::
Show only perf.data header (forces --stdio).
+--time::
+ Only analyze samples within given time window: <start>,<stop>. Times
+ have the format seconds.microseconds. If start is not given (i.e., time
+ string is ',x.y') then analysis starts at the beginning of the file. If
+ stop time is not given (i.e, time string is 'x.y,') then analysis goes
+ to end of file.
+
--itrace::
Options for decoding instruction tracing data. The options are:
diff --git a/tools/perf/Documentation/perf-sched.txt b/tools/perf/Documentation/perf-sched.txt
index 1cc08cc47ac5..d33deddb0146 100644
--- a/tools/perf/Documentation/perf-sched.txt
+++ b/tools/perf/Documentation/perf-sched.txt
@@ -8,11 +8,11 @@ perf-sched - Tool to trace/measure scheduler properties (latencies)
SYNOPSIS
--------
[verse]
-'perf sched' {record|latency|map|replay|script}
+'perf sched' {record|latency|map|replay|script|timehist}
DESCRIPTION
-----------
-There are five variants of perf sched:
+There are several variants of 'perf sched':
'perf sched record <command>' to record the scheduling events
of an arbitrary workload.
@@ -36,6 +36,30 @@ There are five variants of perf sched:
are running on a CPU. A '*' denotes the CPU that had the event, and
a dot signals an idle CPU.
+ 'perf sched timehist' provides an analysis of scheduling events.
+
+ Example usage:
+ perf sched record -- sleep 1
+ perf sched timehist
+
+ By default it shows the individual schedule events, including the wait
+ time (time between sched-out and next sched-in events for the task), the
+ task scheduling delay (time between wakeup and actually running) and run
+ time for the task:
+
+ time cpu task name wait time sch delay run time
+ [tid/pid] (msec) (msec) (msec)
+ -------------- ------ -------------------- --------- --------- ---------
+ 79371.874569 [0011] gcc[31949] 0.014 0.000 1.148
+ 79371.874591 [0010] gcc[31951] 0.000 0.000 0.024
+ 79371.874603 [0010] migration/10[59] 3.350 0.004 0.011
+ 79371.874604 [0011] <idle> 1.148 0.000 0.035
+ 79371.874723 [0005] <idle> 0.016 0.000 1.383
+ 79371.874746 [0005] gcc[31949] 0.153 0.078 0.022
+ ...
+
+ Times are in msec.usec.
+
OPTIONS
-------
-i::
@@ -66,6 +90,62 @@ OPTIONS for 'perf sched map'
--color-pids::
Highlight the given pids.
+OPTIONS for 'perf sched timehist'
+---------------------------------
+-k::
+--vmlinux=<file>::
+ vmlinux pathname
+
+--kallsyms=<file>::
+ kallsyms pathname
+
+-g::
+--no-call-graph::
+ Do not display call chains if present.
+
+--max-stack::
+ Maximum number of functions to display in backtrace, default 5.
+
+-s::
+--summary::
+ Show only a summary of scheduling by thread with min, max, and average
+ run times (in sec) and relative stddev.
+
+-S::
+--with-summary::
+ Show all scheduling events followed by a summary by thread with min,
+ max, and average run times (in sec) and relative stddev.
+
+--symfs=<directory>::
+ Look for files with symbols relative to this directory.
+
+-V::
+--cpu-visual::
+ Show visual aid for sched switches by CPU: 'i' marks idle time,
+ 's' are scheduler events.
+
+-w::
+--wakeups::
+ Show wakeup events.
+
+-M::
+--migrations::
+ Show migration events.
+
+-I::
+--idle-hist::
+ Show idle-related events only.
+
+--time::
+ Only analyze samples within given time window: <start>,<stop>. Times
+ have the format seconds.microseconds. If start is not given (i.e., time
+ string is ',x.y') then analysis starts at the beginning of the file. If
+ stop time is not given (i.e, time string is 'x.y,') then analysis goes
+ to end of file.
+
+--state::
+ Show task state when it switched out.
+
SEE ALSO
--------
linkperf:perf-record[1]
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 053bbbd84ece..4ed5f239ba7d 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -36,7 +36,7 @@ There are several variants of perf script:
'perf script report <script> [args]' to run and display the results
of <script>. <script> is the name displayed in the output of 'perf
- trace --list' i.e. the actual script name minus any language
+ script --list' i.e. the actual script name minus any language
extension. The perf.data output from a previous run of 'perf script
record <script>' is used and should be present for this command to
succeed. [args] refers to the (mainly optional) args expected by
@@ -76,7 +76,7 @@ OPTIONS
Any command you can specify in a shell.
-D::
---dump-raw-script=::
+--dump-raw-trace=::
Display verbose dump of the trace data.
-L::
@@ -117,7 +117,7 @@ OPTIONS
Comma separated list of fields to print. Options are:
comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff,
srcline, period, iregs, brstack, brstacksym, flags, bpf-output,
- callindent. Field list can be prepended with the type, trace, sw or hw,
+ callindent, insn, insnlen. Field list can be prepended with the type, trace, sw or hw,
to indicate to which event type the field list applies.
e.g., -F sw:comm,tid,time,ip,sym and -F trace:time,cpu,trace
@@ -181,6 +181,10 @@ OPTIONS
Instruction Trace decoding. For calls and returns, it will display the
name of the symbol indented with spaces to reflect the stack depth.
+ When doing instruction trace decoding insn and insnlen give the
+ instruction bytes and the instruction length of the current
+ instruction.
+
Finally, a user may not set fields to none for all event types.
i.e., -F "" is not allowed.
@@ -208,6 +212,9 @@ OPTIONS
--hide-call-graph::
When printing symbols do not display call chain.
+--stop-bt::
+ Stop display of callgraph at these symbols
+
-C::
--cpu:: Only report samples for the list of CPUs provided. Multiple CPUs can
be provided as a comma-separated list with no space: 0,1. Ranges of
@@ -285,6 +292,13 @@ include::itrace.txt[]
--force::
Don't do ownership validation.
+--time::
+ Only analyze samples within given time window: <start>,<stop>. Times
+ have the format seconds.microseconds. If start is not given (i.e., time
+ string is ',x.y') then analysis starts at the beginning of the file. If
+ stop time is not given (i.e, time string is 'x.y,') then analysis goes
+ to end of file.
+
SEE ALSO
--------
linkperf:perf-record[1], linkperf:perf-script-perl[1],
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index d96ccd4844df..aecf2a87e7d6 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -63,7 +63,7 @@ report::
-a::
--all-cpus::
- system-wide collection from all CPUs
+ system-wide collection from all CPUs (default if no target is specified)
-c::
--scale::
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index 91d638df3a6b..e71d63843f45 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -170,6 +170,7 @@ Default is to monitor all CPUS.
show up in the output. The output will have a new "Children" column
and will be sorted on the data. It requires -g/--call-graph option
enabled. See the `overhead calculation' section for more details.
+ Enabled by default, disable with --no-children.
--max-stack::
Set the stack depth limit when parsing the callchain, anything
diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt
index 1ab0782369b1..afd728672b6f 100644
--- a/tools/perf/Documentation/perf-trace.txt
+++ b/tools/perf/Documentation/perf-trace.txt
@@ -35,10 +35,18 @@ OPTIONS
-e::
--expr::
- List of syscalls to show, currently only syscall names.
+--event::
+ List of syscalls and other perf events (tracepoints, HW cache events,
+ etc) to show.
+ See 'perf list' for a complete list of events.
Prefixing with ! shows all syscalls but the ones specified. You may
need to escape it.
+-D msecs::
+--delay msecs::
+After starting the program, wait msecs before measuring. This is useful to
+filter out the startup phase of the program, which is often very different.
+
-o::
--output=::
Output file name.
@@ -130,9 +138,6 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs.
--kernel-syscall-graph::
Show the kernel callchains on the syscall exit path.
---event::
- Trace other events, see 'perf list' for a complete list.
-
--max-stack::
Set the stack depth limit when parsing the callchain, anything
beyond the specified depth will be ignored. Note that at this point
diff --git a/tools/perf/Documentation/tips.txt b/tools/perf/Documentation/tips.txt
index 8a6479c0eac9..170b0289a7bc 100644
--- a/tools/perf/Documentation/tips.txt
+++ b/tools/perf/Documentation/tips.txt
@@ -22,7 +22,7 @@ If you have debuginfo enabled, try: perf report -s sym,srcline
For memory address profiling, try: perf mem record / perf mem report
For tracepoint events, try: perf report -s trace_fields
To record callchains for each sample: perf record -g
-To record every process run by an user: perf record -u <user>
+To record every process run by a user: perf record -u <user>
Skip collecing build-id when recording: perf record -B
To change sampling frequency to 100 Hz: perf record -F 100
See assembly instructions with percentage: perf annotate <symbol>
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index 0bda2cca2b3a..8672f835ae4e 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -51,6 +51,7 @@ tools/include/asm-generic/bitops/arch_hweight.h
tools/include/asm-generic/bitops/atomic.h
tools/include/asm-generic/bitops/const_hweight.h
tools/include/asm-generic/bitops/__ffs.h
+tools/include/asm-generic/bitops/__ffz.h
tools/include/asm-generic/bitops/__fls.h
tools/include/asm-generic/bitops/find.h
tools/include/asm-generic/bitops/fls64.h
@@ -60,6 +61,7 @@ tools/include/asm-generic/bitops.h
tools/include/linux/atomic.h
tools/include/linux/bitops.h
tools/include/linux/compiler.h
+tools/include/linux/compiler-gcc.h
tools/include/linux/coresight-pmu.h
tools/include/linux/filter.h
tools/include/linux/hash.h
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 72edf83d76b7..27c9fbca7bd9 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -136,6 +136,7 @@ endif
# Treat warnings as errors unless directed not to
ifneq ($(WERROR),0)
CFLAGS += -Werror
+ CXXFLAGS += -Werror
endif
ifndef DEBUG
@@ -143,8 +144,12 @@ ifndef DEBUG
endif
ifeq ($(DEBUG),0)
+ifeq ($(CC), clang)
+ CFLAGS += -O3
+else
CFLAGS += -O6
endif
+endif
ifdef PARSER_DEBUG
PARSER_DEBUG_BISON := -t
@@ -170,6 +175,10 @@ PYTHON_CONFIG_SQ := $(call shell-sq,$(PYTHON_CONFIG))
PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null)
PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null)
+ifeq ($(CC), clang)
+ PYTHON_EMBED_CCOPTS := $(filter-out -specs=%,$(PYTHON_EMBED_CCOPTS))
+endif
+
FEATURE_CHECK_CFLAGS-libpython := $(PYTHON_EMBED_CCOPTS)
FEATURE_CHECK_LDFLAGS-libpython := $(PYTHON_EMBED_LDOPTS)
FEATURE_CHECK_CFLAGS-libpython-version := $(PYTHON_EMBED_CCOPTS)
@@ -182,6 +191,13 @@ CFLAGS += -Wall
CFLAGS += -Wextra
CFLAGS += -std=gnu99
+CXXFLAGS += -std=gnu++11 -fno-exceptions -fno-rtti
+CXXFLAGS += -Wall
+CXXFLAGS += -fno-omit-frame-pointer
+CXXFLAGS += -ggdb3
+CXXFLAGS += -funwind-tables
+CXXFLAGS += -Wno-strict-aliasing
+
# Enforce a non-executable stack, as we may regress (again) in the future by
# adding assembler files missing the .GNU-stack linker note.
LDFLAGS += -Wl,-z,noexecstack
@@ -204,24 +220,27 @@ ifeq ($(DEBUG),0)
endif
endif
-CFLAGS += -I$(src-perf)/util/include
-CFLAGS += -I$(src-perf)/arch/$(ARCH)/include
-CFLAGS += -I$(srctree)/tools/include/uapi
-CFLAGS += -I$(srctree)/tools/include/
-CFLAGS += -I$(srctree)/tools/arch/$(ARCH)/include/uapi
-CFLAGS += -I$(srctree)/tools/arch/$(ARCH)/include/
-CFLAGS += -I$(srctree)/tools/arch/$(ARCH)/
+INC_FLAGS += -I$(src-perf)/util/include
+INC_FLAGS += -I$(src-perf)/arch/$(ARCH)/include
+INC_FLAGS += -I$(srctree)/tools/include/uapi
+INC_FLAGS += -I$(srctree)/tools/include/
+INC_FLAGS += -I$(srctree)/tools/arch/$(ARCH)/include/uapi
+INC_FLAGS += -I$(srctree)/tools/arch/$(ARCH)/include/
+INC_FLAGS += -I$(srctree)/tools/arch/$(ARCH)/
# $(obj-perf) for generated common-cmds.h
# $(obj-perf)/util for generated bison/flex headers
ifneq ($(OUTPUT),)
-CFLAGS += -I$(obj-perf)/util
-CFLAGS += -I$(obj-perf)
+INC_FLAGS += -I$(obj-perf)/util
+INC_FLAGS += -I$(obj-perf)
endif
-CFLAGS += -I$(src-perf)/util
-CFLAGS += -I$(src-perf)
-CFLAGS += -I$(srctree)/tools/lib/
+INC_FLAGS += -I$(src-perf)/util
+INC_FLAGS += -I$(src-perf)
+INC_FLAGS += -I$(srctree)/tools/lib/
+
+CFLAGS += $(INC_FLAGS)
+CXXFLAGS += $(INC_FLAGS)
CFLAGS += -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE
@@ -280,8 +299,10 @@ else
endif
endif
ifneq ($(feature-dwarf), 1)
- msg := $(warning No libdw.h found or old libdw.h found or elfutils is older than 0.138, disables dwarf support. Please install new elfutils-devel/libdw-dev);
- NO_DWARF := 1
+ ifndef NO_DWARF
+ msg := $(warning No libdw.h found or old libdw.h found or elfutils is older than 0.138, disables dwarf support. Please install new elfutils-devel/libdw-dev);
+ NO_DWARF := 1
+ endif
else
ifneq ($(feature-dwarf_getlocations), 1)
msg := $(warning Old libdw.h, finding variables at given 'perf probe' point will not work, install elfutils-devel/libdw-dev >= 0.157);
@@ -366,7 +387,7 @@ ifndef NO_SDT
endif
ifdef PERF_HAVE_JITDUMP
- ifndef NO_DWARF
+ ifndef NO_LIBELF
$(call detected,CONFIG_JITDUMP)
CFLAGS += -DHAVE_JITDUMP
endif
@@ -584,6 +605,9 @@ else
PYTHON_EMBED_LDFLAGS := $(call strip-libs,$(PYTHON_EMBED_LDOPTS))
PYTHON_EMBED_LIBADD := $(call grep-libs,$(PYTHON_EMBED_LDOPTS)) -lutil
PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null)
+ ifeq ($(CC), clang)
+ PYTHON_EMBED_CCOPTS := $(filter-out -specs=%,$(PYTHON_EMBED_CCOPTS))
+ endif
FLAGS_PYTHON_EMBED := $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS)
ifneq ($(feature-libpython), 1)
@@ -758,6 +782,62 @@ ifndef NO_AUXTRACE
endif
endif
+ifndef NO_JVMTI
+ ifneq (,$(wildcard /usr/sbin/update-java-alternatives))
+ JDIR=$(shell /usr/sbin/update-java-alternatives -l | head -1 | awk '{print $$3}')
+ else
+ ifneq (,$(wildcard /usr/sbin/alternatives))
+ JDIR=$(shell alternatives --display java | tail -1 | cut -d' ' -f 5 | sed 's%/jre/bin/java.%%g')
+ endif
+ endif
+ ifndef JDIR
+ $(warning No alternatives command found, you need to set JDIR= to point to the root of your Java directory)
+ NO_JVMTI := 1
+ endif
+endif
+
+ifndef NO_JVMTI
+ FEATURE_CHECK_CFLAGS-jvmti := -I$(JDIR)/include -I$(JDIR)/include/linux
+ $(call feature_check,jvmti)
+ ifeq ($(feature-jvmti), 1)
+ $(call detected_var,JDIR)
+ else
+ $(warning No openjdk development package found, please install JDK package)
+ NO_JVMTI := 1
+ endif
+endif
+
+USE_CXX = 0
+USE_CLANGLLVM = 0
+ifdef LIBCLANGLLVM
+ $(call feature_check,cxx)
+ ifneq ($(feature-cxx), 1)
+ msg := $(warning No g++ found, disable clang and llvm support. Please install g++)
+ else
+ $(call feature_check,llvm)
+ $(call feature_check,llvm-version)
+ ifneq ($(feature-llvm), 1)
+ msg := $(warning No suitable libLLVM found, disabling builtin clang and LLVM support. Please install llvm-dev(el) (>= 3.9.0))
+ else
+ $(call feature_check,clang)
+ ifneq ($(feature-clang), 1)
+ msg := $(warning No suitable libclang found, disabling builtin clang and LLVM support. Please install libclang-dev(el) (>= 3.9.0))
+ else
+ CFLAGS += -DHAVE_LIBCLANGLLVM_SUPPORT
+ CXXFLAGS += -DHAVE_LIBCLANGLLVM_SUPPORT -I$(shell $(LLVM_CONFIG) --includedir)
+ $(call detected,CONFIG_CXX)
+ $(call detected,CONFIG_CLANGLLVM)
+ USE_CXX = 1
+ USE_LLVM = 1
+ USE_CLANG = 1
+ ifneq ($(feature-llvm-version),1)
+ msg := $(warning This version of LLVM is not tested. May cause build errors)
+ endif
+ endif
+ endif
+ endif
+endif
+
# Among the variables below, these:
# perfexecdir
# template_dir
@@ -850,6 +930,7 @@ ifeq ($(VF),1)
$(call print_var,sysconfdir)
$(call print_var,LIBUNWIND_DIR)
$(call print_var,LIBDW_DIR)
+ $(call print_var,JDIR)
ifeq ($(dwarf-post-unwind),1)
$(call feature_print_text,"DWARF post unwind library", $(dwarf-post-unwind-text))
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 982d6439bb07..79fe31f20a17 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -86,6 +86,12 @@ include ../scripts/utilities.mak
#
# Define FEATURES_DUMP to provide features detection dump file
# and bypass the feature detection
+#
+# Define NO_JVMTI if you do not want jvmti agent built
+#
+# Define LIBCLANGLLVM if you DO want builtin clang and llvm support.
+# When selected, pass LLVM_CONFIG=/path/to/llvm-config to `make' if
+# llvm-config is not in $PATH.
# As per kernel Makefile, avoid funny character set dependencies
unexport LC_ALL
@@ -94,7 +100,7 @@ LC_NUMERIC=C
export LC_COLLATE LC_NUMERIC
ifeq ($(srctree),)
-srctree := $(patsubst %/,%,$(dir $(shell pwd)))
+srctree := $(patsubst %/,%,$(dir $(CURDIR)))
srctree := $(patsubst %/,%,$(dir $(srctree)))
#$(info Determined 'srctree' to be $(srctree))
endif
@@ -122,10 +128,6 @@ endif
# (this improves performance and avoids hard-to-debug behaviour);
MAKEFLAGS += -r
-$(OUTPUT)PERF-VERSION-FILE: ../../.git/HEAD
- $(Q)$(SHELL_PATH) util/PERF-VERSION-GEN $(OUTPUT)
- $(Q)touch $(OUTPUT)PERF-VERSION-FILE
-
# Makefiles suck: This macro sets a default value of $(2) for the
# variable named by $(1), unless the variable has been set by
# environment or command line. This is necessary for CC and AR
@@ -141,6 +143,7 @@ endef
$(call allow-override,CC,$(CROSS_COMPILE)gcc)
$(call allow-override,AR,$(CROSS_COMPILE)ar)
$(call allow-override,LD,$(CROSS_COMPILE)ld)
+$(call allow-override,CXX,$(CROSS_COMPILE)g++)
LD += $(EXTRA_LDFLAGS)
@@ -149,6 +152,7 @@ HOSTLD ?= ld
HOSTAR ?= ar
PKG_CONFIG = $(CROSS_COMPILE)pkg-config
+LLVM_CONFIG ?= llvm-config
RM = rm -f
LN = ln -f
@@ -160,16 +164,11 @@ BISON = bison
STRIP = strip
AWK = awk
-LIB_DIR = $(srctree)/tools/lib/api/
-TRACE_EVENT_DIR = $(srctree)/tools/lib/traceevent/
-BPF_DIR = $(srctree)/tools/lib/bpf/
-SUBCMD_DIR = $(srctree)/tools/lib/subcmd/
-
# include Makefile.config by default and rule out
# non-config cases
config := 1
-NON_CONFIG_TARGETS := clean TAGS tags cscope help install-doc
+NON_CONFIG_TARGETS := clean TAGS tags cscope help install-doc install-man install-html install-info install-pdf doc man html info pdf
ifdef MAKECMDGOALS
ifeq ($(filter-out $(NON_CONFIG_TARGETS),$(MAKECMDGOALS)),)
@@ -177,6 +176,41 @@ ifeq ($(filter-out $(NON_CONFIG_TARGETS),$(MAKECMDGOALS)),)
endif
endif
+# The fixdep build - we force fixdep tool to be built as
+# the first target in the separate make session not to be
+# disturbed by any parallel make jobs. Once fixdep is done
+# we issue the requested build with FIXDEP=1 variable.
+#
+# The fixdep build is disabled for $(NON_CONFIG_TARGETS)
+# targets, because it's not necessary.
+
+ifdef FIXDEP
+ force_fixdep := 0
+else
+ force_fixdep := $(config)
+endif
+
+export srctree OUTPUT RM CC CXX LD AR CFLAGS CXXFLAGS V BISON FLEX AWK
+export HOSTCC HOSTLD HOSTAR
+
+include $(srctree)/tools/build/Makefile.include
+
+ifeq ($(force_fixdep),1)
+goals := $(filter-out all sub-make, $(MAKECMDGOALS))
+
+$(goals) all: sub-make
+
+sub-make: fixdep
+ @./check-headers.sh
+ $(Q)$(MAKE) FIXDEP=1 -f Makefile.perf $(goals)
+
+else # force_fixdep
+
+LIB_DIR = $(srctree)/tools/lib/api/
+TRACE_EVENT_DIR = $(srctree)/tools/lib/traceevent/
+BPF_DIR = $(srctree)/tools/lib/bpf/
+SUBCMD_DIR = $(srctree)/tools/lib/subcmd/
+
# Set FEATURE_TESTS to 'all' so all possible feature checkers are executed.
# Without this setting the output feature dump file misses some features, for
# example, liberty. Select all checkers so we won't get an incomplete feature
@@ -260,17 +294,6 @@ python-clean := $(call QUIET_CLEAN, python) $(RM) -r $(PYTHON_EXTBUILD) $(OUTPUT
PYTHON_EXT_SRCS := $(shell grep -v ^\# util/python-ext-sources)
PYTHON_EXT_DEPS := util/python-ext-sources util/setup.py $(LIBTRACEEVENT) $(LIBAPI)
-$(OUTPUT)python/perf.so: $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS) $(LIBTRACEEVENT_DYNAMIC_LIST)
- $(QUIET_GEN)LDSHARED="$(CC) -pthread -shared" \
- CFLAGS='$(CFLAGS)' LDFLAGS='$(LDFLAGS) $(LIBTRACEEVENT_DYNAMIC_LIST_LDFLAGS)' \
- $(PYTHON_WORD) util/setup.py \
- --quiet build_ext; \
- mkdir -p $(OUTPUT)python && \
- cp $(PYTHON_EXTBUILD_LIB)perf.so $(OUTPUT)python/
-#
-# No Perl scripts right now:
-#
-
SCRIPTS = $(patsubst %.sh,%,$(SCRIPT_SH))
PROGRAMS += $(OUTPUT)perf
@@ -283,6 +306,12 @@ ifndef NO_PERF_READ_VDSOX32
PROGRAMS += $(OUTPUT)perf-read-vdsox32
endif
+LIBJVMTI = libperf-jvmti.so
+
+ifndef NO_JVMTI
+PROGRAMS += $(OUTPUT)$(LIBJVMTI)
+endif
+
# what 'all' will build and 'install' will install, in perfexecdir
ALL_PROGRAMS = $(PROGRAMS) $(SCRIPTS)
@@ -317,11 +346,6 @@ endif
ifndef NO_GTK2
ALL_PROGRAMS += $(OUTPUT)libperf-gtk.so
GTK_IN := $(OUTPUT)gtk-in.o
-
-install-gtk: $(OUTPUT)libperf-gtk.so
- $(call QUIET_INSTALL, 'GTK UI') \
- $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(libdir_SQ)'; \
- $(INSTALL) $(OUTPUT)libperf-gtk.so '$(DESTDIR_SQ)$(libdir_SQ)'
endif
ifdef ASCIIDOC8
@@ -330,6 +354,21 @@ endif
LIBS = -Wl,--whole-archive $(PERFLIBS) -Wl,--no-whole-archive -Wl,--start-group $(EXTLIBS) -Wl,--end-group
+ifeq ($(USE_CLANG), 1)
+ CLANGLIBS_LIST = AST Basic CodeGen Driver Frontend Lex Tooling Edit Sema Analysis Parse Serialization
+ LIBCLANG = $(foreach l,$(CLANGLIBS_LIST),$(wildcard $(shell $(LLVM_CONFIG) --libdir)/libclang$(l).a))
+ LIBS += -Wl,--start-group $(LIBCLANG) -Wl,--end-group
+endif
+
+ifeq ($(USE_LLVM), 1)
+ LIBLLVM = $(shell $(LLVM_CONFIG) --libs all) $(shell $(LLVM_CONFIG) --system-libs)
+ LIBS += -L$(shell $(LLVM_CONFIG) --libdir) $(LIBLLVM)
+endif
+
+ifeq ($(USE_CXX), 1)
+ LIBS += -lstdc++
+endif
+
export INSTALL SHELL_PATH
### Build rules
@@ -338,6 +377,14 @@ SHELL = $(SHELL_PATH)
all: shell_compatibility_test $(ALL_PROGRAMS) $(LANG_BINDINGS) $(OTHER_PROGRAMS)
+$(OUTPUT)python/perf.so: $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS) $(LIBTRACEEVENT_DYNAMIC_LIST)
+ $(QUIET_GEN)LDSHARED="$(CC) -pthread -shared" \
+ CFLAGS='$(CFLAGS)' LDFLAGS='$(LDFLAGS) $(LIBTRACEEVENT_DYNAMIC_LIST_LDFLAGS)' \
+ $(PYTHON_WORD) util/setup.py \
+ --quiet build_ext; \
+ mkdir -p $(OUTPUT)python && \
+ cp $(PYTHON_EXTBUILD_LIB)perf.so $(OUTPUT)python/
+
please_set_SHELL_PATH_to_a_more_modern_shell:
$(Q)$$(:)
@@ -348,10 +395,6 @@ strip: $(PROGRAMS) $(OUTPUT)perf
PERF_IN := $(OUTPUT)perf-in.o
-export srctree OUTPUT RM CC LD AR CFLAGS V BISON FLEX AWK
-export HOSTCC HOSTLD HOSTAR
-include $(srctree)/tools/build/Makefile.include
-
JEVENTS := $(OUTPUT)pmu-events/jevents
JEVENTS_IN := $(OUTPUT)pmu-events/jevents-in.o
@@ -362,99 +405,6 @@ export JEVENTS
build := -f $(srctree)/tools/build/Makefile.build dir=. obj
$(PERF_IN): prepare FORCE
- @(test -f ../../include/uapi/linux/perf_event.h && ( \
- (diff -B ../include/uapi/linux/perf_event.h ../../include/uapi/linux/perf_event.h >/dev/null) \
- || echo "Warning: tools/include/uapi/linux/perf_event.h differs from kernel" >&2 )) || true
- @(test -f ../../include/linux/hash.h && ( \
- (diff -B ../include/linux/hash.h ../../include/linux/hash.h >/dev/null) \
- || echo "Warning: tools/include/linux/hash.h differs from kernel" >&2 )) || true
- @(test -f ../../include/uapi/linux/hw_breakpoint.h && ( \
- (diff -B ../include/uapi/linux/hw_breakpoint.h ../../include/uapi/linux/hw_breakpoint.h >/dev/null) \
- || echo "Warning: tools/include/uapi/linux/hw_breakpoint.h differs from kernel" >&2 )) || true
- @(test -f ../../arch/x86/include/asm/disabled-features.h && ( \
- (diff -B ../arch/x86/include/asm/disabled-features.h ../../arch/x86/include/asm/disabled-features.h >/dev/null) \
- || echo "Warning: tools/arch/x86/include/asm/disabled-features.h differs from kernel" >&2 )) || true
- @(test -f ../../arch/x86/include/asm/required-features.h && ( \
- (diff -B ../arch/x86/include/asm/required-features.h ../../arch/x86/include/asm/required-features.h >/dev/null) \
- || echo "Warning: tools/arch/x86/include/asm/required-features.h differs from kernel" >&2 )) || true
- @(test -f ../../arch/x86/include/asm/cpufeatures.h && ( \
- (diff -B ../arch/x86/include/asm/cpufeatures.h ../../arch/x86/include/asm/cpufeatures.h >/dev/null) \
- || echo "Warning: tools/arch/x86/include/asm/cpufeatures.h differs from kernel" >&2 )) || true
- @(test -f ../../arch/x86/lib/memcpy_64.S && ( \
- (diff -B ../arch/x86/lib/memcpy_64.S ../../arch/x86/lib/memcpy_64.S >/dev/null) \
- || echo "Warning: tools/arch/x86/lib/memcpy_64.S differs from kernel" >&2 )) || true
- @(test -f ../../arch/x86/lib/memset_64.S && ( \
- (diff -B ../arch/x86/lib/memset_64.S ../../arch/x86/lib/memset_64.S >/dev/null) \
- || echo "Warning: tools/arch/x86/lib/memset_64.S differs from kernel" >&2 )) || true
- @(test -f ../../arch/arm/include/uapi/asm/perf_regs.h && ( \
- (diff -B ../arch/arm/include/uapi/asm/perf_regs.h ../../arch/arm/include/uapi/asm/perf_regs.h >/dev/null) \
- || echo "Warning: tools/arch/arm/include/uapi/asm/perf_regs.h differs from kernel" >&2 )) || true
- @(test -f ../../arch/arm64/include/uapi/asm/perf_regs.h && ( \
- (diff -B ../arch/arm64/include/uapi/asm/perf_regs.h ../../arch/arm64/include/uapi/asm/perf_regs.h >/dev/null) \
- || echo "Warning: tools/arch/arm64/include/uapi/asm/perf_regs.h differs from kernel" >&2 )) || true
- @(test -f ../../arch/powerpc/include/uapi/asm/perf_regs.h && ( \
- (diff -B ../arch/powerpc/include/uapi/asm/perf_regs.h ../../arch/powerpc/include/uapi/asm/perf_regs.h >/dev/null) \
- || echo "Warning: tools/arch/powerpc/include/uapi/asm/perf_regs.h differs from kernel" >&2 )) || true
- @(test -f ../../arch/x86/include/uapi/asm/perf_regs.h && ( \
- (diff -B ../arch/x86/include/uapi/asm/perf_regs.h ../../arch/x86/include/uapi/asm/perf_regs.h >/dev/null) \
- || echo "Warning: tools/arch/x86/include/uapi/asm/perf_regs.h differs from kernel" >&2 )) || true
- @(test -f ../../arch/x86/include/uapi/asm/kvm.h && ( \
- (diff -B ../arch/x86/include/uapi/asm/kvm.h ../../arch/x86/include/uapi/asm/kvm.h >/dev/null) \
- || echo "Warning: tools/arch/x86/include/uapi/asm/kvm.h differs from kernel" >&2 )) || true
- @(test -f ../../arch/x86/include/uapi/asm/kvm_perf.h && ( \
- (diff -B ../arch/x86/include/uapi/asm/kvm_perf.h ../../arch/x86/include/uapi/asm/kvm_perf.h >/dev/null) \
- || echo "Warning: tools/arch/x86/include/uapi/asm/kvm_perf.h differs from kernel" >&2 )) || true
- @(test -f ../../arch/x86/include/uapi/asm/svm.h && ( \
- (diff -B ../arch/x86/include/uapi/asm/svm.h ../../arch/x86/include/uapi/asm/svm.h >/dev/null) \
- || echo "Warning: tools/arch/x86/include/uapi/asm/svm.h differs from kernel" >&2 )) || true
- @(test -f ../../arch/x86/include/uapi/asm/vmx.h && ( \
- (diff -B ../arch/x86/include/uapi/asm/vmx.h ../../arch/x86/include/uapi/asm/vmx.h >/dev/null) \
- || echo "Warning: tools/arch/x86/include/uapi/asm/vmx.h differs from kernel" >&2 )) || true
- @(test -f ../../arch/powerpc/include/uapi/asm/kvm.h && ( \
- (diff -B ../arch/powerpc/include/uapi/asm/kvm.h ../../arch/powerpc/include/uapi/asm/kvm.h >/dev/null) \
- || echo "Warning: tools/arch/powerpc/include/uapi/asm/kvm.h differs from kernel" >&2 )) || true
- @(test -f ../../arch/s390/include/uapi/asm/kvm.h && ( \
- (diff -B ../arch/s390/include/uapi/asm/kvm.h ../../arch/s390/include/uapi/asm/kvm.h >/dev/null) \
- || echo "Warning: tools/arch/s390/include/uapi/asm/kvm.h differs from kernel" >&2 )) || true
- @(test -f ../../arch/s390/include/uapi/asm/kvm_perf.h && ( \
- (diff -B ../arch/s390/include/uapi/asm/kvm_perf.h ../../arch/s390/include/uapi/asm/kvm_perf.h >/dev/null) \
- || echo "Warning: tools/arch/s390/include/uapi/asm/kvm_perf.h differs from kernel" >&2 )) || true
- @(test -f ../../arch/s390/include/uapi/asm/sie.h && ( \
- (diff -B ../arch/s390/include/uapi/asm/sie.h ../../arch/s390/include/uapi/asm/sie.h >/dev/null) \
- || echo "Warning: tools/arch/s390/include/uapi/asm/sie.h differs from kernel" >&2 )) || true
- @(test -f ../../arch/arm/include/uapi/asm/kvm.h && ( \
- (diff -B ../arch/arm/include/uapi/asm/kvm.h ../../arch/arm/include/uapi/asm/kvm.h >/dev/null) \
- || echo "Warning: tools/arch/arm/include/uapi/asm/kvm.h differs from kernel" >&2 )) || true
- @(test -f ../../arch/arm64/include/uapi/asm/kvm.h && ( \
- (diff -B ../arch/arm64/include/uapi/asm/kvm.h ../../arch/arm64/include/uapi/asm/kvm.h >/dev/null) \
- || echo "Warning: tools/arch/arm64/include/uapi/asm/kvm.h differs from kernel" >&2 )) || true
- @(test -f ../../include/asm-generic/bitops/arch_hweight.h && ( \
- (diff -B ../include/asm-generic/bitops/arch_hweight.h ../../include/asm-generic/bitops/arch_hweight.h >/dev/null) \
- || echo "Warning: tools/include/asm-generic/bitops/arch_hweight.h differs from kernel" >&2 )) || true
- @(test -f ../../include/asm-generic/bitops/const_hweight.h && ( \
- (diff -B ../include/asm-generic/bitops/const_hweight.h ../../include/asm-generic/bitops/const_hweight.h >/dev/null) \
- || echo "Warning: tools/include/asm-generic/bitops/const_hweight.h differs from kernel" >&2 )) || true
- @(test -f ../../include/asm-generic/bitops/__fls.h && ( \
- (diff -B ../include/asm-generic/bitops/__fls.h ../../include/asm-generic/bitops/__fls.h >/dev/null) \
- || echo "Warning: tools/include/asm-generic/bitops/__fls.h differs from kernel" >&2 )) || true
- @(test -f ../../include/asm-generic/bitops/fls.h && ( \
- (diff -B ../include/asm-generic/bitops/fls.h ../../include/asm-generic/bitops/fls.h >/dev/null) \
- || echo "Warning: tools/include/asm-generic/bitops/fls.h differs from kernel" >&2 )) || true
- @(test -f ../../include/asm-generic/bitops/fls64.h && ( \
- (diff -B ../include/asm-generic/bitops/fls64.h ../../include/asm-generic/bitops/fls64.h >/dev/null) \
- || echo "Warning: tools/include/asm-generic/bitops/fls64.h differs from kernel" >&2 )) || true
- @(test -f ../../include/linux/coresight-pmu.h && ( \
- (diff -B ../include/linux/coresight-pmu.h ../../include/linux/coresight-pmu.h >/dev/null) \
- || echo "Warning: tools/include/linux/coresight-pmu.h differs from kernel" >&2 )) || true
- @(test -f ../../include/uapi/asm-generic/mman-common.h && ( \
- (diff -B ../include/uapi/asm-generic/mman-common.h ../../include/uapi/asm-generic/mman-common.h >/dev/null) \
- || echo "Warning: tools/include/uapi/asm-generic/mman-common.h differs from kernel" >&2 )) || true
- @(test -f ../../include/uapi/asm-generic/mman.h && ( \
- (diff -B -I "^#include <\(uapi/\)*asm-generic/mman-common.h>$$" ../include/uapi/asm-generic/mman.h ../../include/uapi/asm-generic/mman.h >/dev/null) \
- || echo "Warning: tools/include/uapi/asm-generic/mman.h differs from kernel" >&2 )) || true
- @(test -f ../../include/uapi/linux/mman.h && ( \
- (diff -B -I "^#include <\(uapi/\)*asm/mman.h>$$" ../include/uapi/linux/mman.h ../../include/uapi/linux/mman.h >/dev/null) \
- || echo "Warning: tools/include/uapi/linux/mman.h differs from kernel" >&2 )) || true
$(Q)$(MAKE) $(build)=perf
$(JEVENTS_IN): FORCE
@@ -470,7 +420,7 @@ $(OUTPUT)perf: $(PERFLIBS) $(PERF_IN) $(PMU_EVENTS_IN) $(LIBTRACEEVENT_DYNAMIC_L
$(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $(LIBTRACEEVENT_DYNAMIC_LIST_LDFLAGS) \
$(PERF_IN) $(PMU_EVENTS_IN) $(LIBS) -o $@
-$(GTK_IN): fixdep FORCE
+$(GTK_IN): FORCE
$(Q)$(MAKE) $(build)=gtk
$(OUTPUT)libperf-gtk.so: $(GTK_IN) $(PERFLIBS)
@@ -484,6 +434,10 @@ $(OUTPUT)common-cmds.h: $(wildcard Documentation/perf-*.txt)
$(SCRIPTS) : % : %.sh
$(QUIET_GEN)$(INSTALL) '$@.sh' '$(OUTPUT)$@'
+$(OUTPUT)PERF-VERSION-FILE: ../../.git/HEAD
+ $(Q)$(SHELL_PATH) util/PERF-VERSION-GEN $(OUTPUT)
+ $(Q)touch $(OUTPUT)PERF-VERSION-FILE
+
# These can record PERF_VERSION
perf.spec $(SCRIPTS) \
: $(OUTPUT)PERF-VERSION-FILE
@@ -515,7 +469,7 @@ endif
__build-dir = $(subst $(OUTPUT),,$(dir $@))
build-dir = $(if $(__build-dir),$(__build-dir),.)
-prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h fixdep archheaders
+prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h archheaders
$(OUTPUT)%.o: %.c prepare FORCE
$(Q)$(MAKE) -f $(srctree)/tools/build/Makefile.build dir=$(build-dir) $@
@@ -551,11 +505,21 @@ $(OUTPUT)perf-read-vdsox32: perf-read-vdso.c util/find-vdso-map.c
$(QUIET_CC)$(CC) -mx32 $(filter -static,$(LDFLAGS)) -Wall -Werror -o $@ perf-read-vdso.c
endif
+ifndef NO_JVMTI
+LIBJVMTI_IN := $(OUTPUT)jvmti/jvmti-in.o
+
+$(LIBJVMTI_IN): FORCE
+ $(Q)$(MAKE) -f $(srctree)/tools/build/Makefile.build dir=jvmti obj=jvmti
+
+$(OUTPUT)$(LIBJVMTI): $(LIBJVMTI_IN)
+ $(QUIET_LINK)$(CC) -shared -Wl,-soname -Wl,$(LIBJVMTI) -o $@ $< -lelf -lrt
+endif
+
$(patsubst perf-%,%.o,$(PROGRAMS)): $(wildcard */*.h)
LIBPERF_IN := $(OUTPUT)libperf-in.o
-$(LIBPERF_IN): prepare fixdep FORCE
+$(LIBPERF_IN): prepare FORCE
$(Q)$(MAKE) $(build)=libperf
$(LIB_FILE): $(LIBPERF_IN)
@@ -563,10 +527,10 @@ $(LIB_FILE): $(LIBPERF_IN)
LIBTRACEEVENT_FLAGS += plugin_dir=$(plugindir_SQ)
-$(LIBTRACEEVENT): fixdep FORCE
+$(LIBTRACEEVENT): FORCE
$(Q)$(MAKE) -C $(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) O=$(OUTPUT) $(OUTPUT)libtraceevent.a
-libtraceevent_plugins: fixdep FORCE
+libtraceevent_plugins: FORCE
$(Q)$(MAKE) -C $(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) O=$(OUTPUT) plugins
$(LIBTRACEEVENT_DYNAMIC_LIST): libtraceevent_plugins
@@ -579,21 +543,21 @@ $(LIBTRACEEVENT)-clean:
install-traceevent-plugins: libtraceevent_plugins
$(Q)$(MAKE) -C $(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) O=$(OUTPUT) install_plugins
-$(LIBAPI): fixdep FORCE
+$(LIBAPI): FORCE
$(Q)$(MAKE) -C $(LIB_DIR) O=$(OUTPUT) $(OUTPUT)libapi.a
$(LIBAPI)-clean:
$(call QUIET_CLEAN, libapi)
$(Q)$(MAKE) -C $(LIB_DIR) O=$(OUTPUT) clean >/dev/null
-$(LIBBPF): fixdep FORCE
+$(LIBBPF): FORCE
$(Q)$(MAKE) -C $(BPF_DIR) O=$(OUTPUT) $(OUTPUT)libbpf.a FEATURES_DUMP=$(FEATURE_DUMP_EXPORT)
$(LIBBPF)-clean:
$(call QUIET_CLEAN, libbpf)
$(Q)$(MAKE) -C $(BPF_DIR) O=$(OUTPUT) clean >/dev/null
-$(LIBSUBCMD): fixdep FORCE
+$(LIBSUBCMD): FORCE
$(Q)$(MAKE) -C $(SUBCMD_DIR) O=$(OUTPUT) $(OUTPUT)libsubcmd.a
$(LIBSUBCMD)-clean:
@@ -673,7 +637,14 @@ check: $(OUTPUT)common-cmds.h
### Installation rules
+ifndef NO_GTK2
+install-gtk: $(OUTPUT)libperf-gtk.so
+ $(call QUIET_INSTALL, 'GTK UI') \
+ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(libdir_SQ)'; \
+ $(INSTALL) $(OUTPUT)libperf-gtk.so '$(DESTDIR_SQ)$(libdir_SQ)'
+else
install-gtk:
+endif
install-tools: all install-gtk
$(call QUIET_INSTALL, binaries) \
@@ -688,6 +659,11 @@ ifndef NO_PERF_READ_VDSOX32
$(call QUIET_INSTALL, perf-read-vdsox32) \
$(INSTALL) $(OUTPUT)perf-read-vdsox32 '$(DESTDIR_SQ)$(bindir_SQ)';
endif
+ifndef NO_JVMTI
+ $(call QUIET_INSTALL, $(LIBJVMTI)) \
+ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(libdir_SQ)'; \
+ $(INSTALL) $(OUTPUT)$(LIBJVMTI) '$(DESTDIR_SQ)$(libdir_SQ)';
+endif
$(call QUIET_INSTALL, libexec) \
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
$(call QUIET_INSTALL, perf-archive) \
@@ -729,9 +705,9 @@ install-tests: all install-gtk
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'; \
$(INSTALL) tests/attr/* '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'
-install-bin: install-tools install-tests
+install-bin: install-tools install-tests install-traceevent-plugins
-install: install-bin try-install-man install-traceevent-plugins
+install: install-bin try-install-man
install-python_ext:
$(PYTHON_WORD) util/setup.py --quiet install --root='/$(DESTDIR_SQ)'
@@ -750,13 +726,13 @@ config-clean:
$(call QUIET_CLEAN, config)
$(Q)$(MAKE) -C $(srctree)/tools/build/feature/ $(if $(OUTPUT),OUTPUT=$(OUTPUT)feature/,) clean >/dev/null
-clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean config-clean
+clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean config-clean fixdep-clean
$(call QUIET_CLEAN, core-objs) $(RM) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf-with-kcore $(LANG_BINDINGS)
$(Q)find $(if $(OUTPUT),$(OUTPUT),.) -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete
$(Q)$(RM) $(OUTPUT).config-detected
- $(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf perf-read-vdso32 perf-read-vdsox32 $(OUTPUT)pmu-events/jevents
+ $(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf perf-read-vdso32 perf-read-vdsox32 $(OUTPUT)pmu-events/jevents $(OUTPUT)$(LIBJVMTI).so
$(call QUIET_CLEAN, core-gen) $(RM) *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)FEATURE-DUMP $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex* \
- $(OUTPUT)util/intel-pt-decoder/inat-tables.c $(OUTPUT)fixdep \
+ $(OUTPUT)util/intel-pt-decoder/inat-tables.c \
$(OUTPUT)tests/llvm-src-{base,kbuild,prologue,relocation}.c \
$(OUTPUT)pmu-events/pmu-events.c
$(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean
@@ -790,3 +766,4 @@ FORCE:
.PHONY: $(GIT-HEAD-PHONY) TAGS tags cscope FORCE prepare
.PHONY: libtraceevent_plugins archheaders
+endif # force_fixdep
diff --git a/tools/perf/arch/arm/annotate/instructions.c b/tools/perf/arch/arm/annotate/instructions.c
new file mode 100644
index 000000000000..1ce0872b1726
--- /dev/null
+++ b/tools/perf/arch/arm/annotate/instructions.c
@@ -0,0 +1,59 @@
+#include <sys/types.h>
+#include <regex.h>
+
+struct arm_annotate {
+ regex_t call_insn,
+ jump_insn;
+};
+
+static struct ins_ops *arm__associate_instruction_ops(struct arch *arch, const char *name)
+{
+ struct arm_annotate *arm = arch->priv;
+ struct ins_ops *ops;
+ regmatch_t match[2];
+
+ if (!regexec(&arm->call_insn, name, 2, match, 0))
+ ops = &call_ops;
+ else if (!regexec(&arm->jump_insn, name, 2, match, 0))
+ ops = &jump_ops;
+ else
+ return NULL;
+
+ arch__associate_ins_ops(arch, name, ops);
+ return ops;
+}
+
+static int arm__annotate_init(struct arch *arch)
+{
+ struct arm_annotate *arm;
+ int err;
+
+ if (arch->initialized)
+ return 0;
+
+ arm = zalloc(sizeof(*arm));
+ if (!arm)
+ return -1;
+
+#define ARM_CONDS "(cc|cs|eq|ge|gt|hi|le|ls|lt|mi|ne|pl|vc|vs)"
+ err = regcomp(&arm->call_insn, "^blx?" ARM_CONDS "?$", REG_EXTENDED);
+ if (err)
+ goto out_free_arm;
+ err = regcomp(&arm->jump_insn, "^bx?" ARM_CONDS "?$", REG_EXTENDED);
+ if (err)
+ goto out_free_call;
+#undef ARM_CONDS
+
+ arch->initialized = true;
+ arch->priv = arm;
+ arch->associate_instruction_ops = arm__associate_instruction_ops;
+ arch->objdump.comment_char = ';';
+ arch->objdump.skip_functions_char = '+';
+ return 0;
+
+out_free_call:
+ regfree(&arm->call_insn);
+out_free_arm:
+ free(arm);
+ return -1;
+}
diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c
index 47d584da5819..dfea6b635525 100644
--- a/tools/perf/arch/arm/util/cs-etm.c
+++ b/tools/perf/arch/arm/util/cs-etm.c
@@ -575,8 +575,6 @@ static FILE *cs_device__open_file(const char *name)
snprintf(path, PATH_MAX,
"%s" CS_BUS_DEVICE_PATH "%s", sysfs, name);
- printf("path: %s\n", path);
-
if (stat(path, &st) < 0)
return NULL;
diff --git a/tools/perf/arch/arm64/Makefile b/tools/perf/arch/arm64/Makefile
index 18b13518d8d8..eebe1ec9d2ee 100644
--- a/tools/perf/arch/arm64/Makefile
+++ b/tools/perf/arch/arm64/Makefile
@@ -2,3 +2,4 @@ ifndef NO_DWARF
PERF_HAVE_DWARF_REGS := 1
endif
PERF_HAVE_JITDUMP := 1
+PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1
diff --git a/tools/perf/arch/arm64/annotate/instructions.c b/tools/perf/arch/arm64/annotate/instructions.c
new file mode 100644
index 000000000000..44eafd6f2d50
--- /dev/null
+++ b/tools/perf/arch/arm64/annotate/instructions.c
@@ -0,0 +1,62 @@
+#include <sys/types.h>
+#include <regex.h>
+
+struct arm64_annotate {
+ regex_t call_insn,
+ jump_insn;
+};
+
+static struct ins_ops *arm64__associate_instruction_ops(struct arch *arch, const char *name)
+{
+ struct arm64_annotate *arm = arch->priv;
+ struct ins_ops *ops;
+ regmatch_t match[2];
+
+ if (!regexec(&arm->jump_insn, name, 2, match, 0))
+ ops = &jump_ops;
+ else if (!regexec(&arm->call_insn, name, 2, match, 0))
+ ops = &call_ops;
+ else if (!strcmp(name, "ret"))
+ ops = &ret_ops;
+ else
+ return NULL;
+
+ arch__associate_ins_ops(arch, name, ops);
+ return ops;
+}
+
+static int arm64__annotate_init(struct arch *arch)
+{
+ struct arm64_annotate *arm;
+ int err;
+
+ if (arch->initialized)
+ return 0;
+
+ arm = zalloc(sizeof(*arm));
+ if (!arm)
+ return -1;
+
+ /* bl, blr */
+ err = regcomp(&arm->call_insn, "^blr?$", REG_EXTENDED);
+ if (err)
+ goto out_free_arm;
+ /* b, b.cond, br, cbz/cbnz, tbz/tbnz */
+ err = regcomp(&arm->jump_insn, "^[ct]?br?\\.?(cc|cs|eq|ge|gt|hi|le|ls|lt|mi|ne|pl)?n?z?$",
+ REG_EXTENDED);
+ if (err)
+ goto out_free_call;
+
+ arch->initialized = true;
+ arch->priv = arm;
+ arch->associate_instruction_ops = arm64__associate_instruction_ops;
+ arch->objdump.comment_char = ';';
+ arch->objdump.skip_functions_char = '+';
+ return 0;
+
+out_free_call:
+ regfree(&arm->call_insn);
+out_free_arm:
+ free(arm);
+ return -1;
+}
diff --git a/tools/perf/arch/arm64/include/dwarf-regs-table.h b/tools/perf/arch/arm64/include/dwarf-regs-table.h
index 26759363f921..36e375f5a211 100644
--- a/tools/perf/arch/arm64/include/dwarf-regs-table.h
+++ b/tools/perf/arch/arm64/include/dwarf-regs-table.h
@@ -2,12 +2,12 @@
/* This is included in perf/util/dwarf-regs.c */
static const char * const aarch64_regstr_tbl[] = {
- "%r0", "%r1", "%r2", "%r3", "%r4",
- "%r5", "%r6", "%r7", "%r8", "%r9",
- "%r10", "%r11", "%r12", "%r13", "%r14",
- "%r15", "%r16", "%r17", "%r18", "%r19",
- "%r20", "%r21", "%r22", "%r23", "%r24",
- "%r25", "%r26", "%r27", "%r28", "%r29",
+ "%x0", "%x1", "%x2", "%x3", "%x4",
+ "%x5", "%x6", "%x7", "%x8", "%x9",
+ "%x10", "%x11", "%x12", "%x13", "%x14",
+ "%x15", "%x16", "%x17", "%x18", "%x19",
+ "%x20", "%x21", "%x22", "%x23", "%x24",
+ "%x25", "%x26", "%x27", "%x28", "%x29",
"%lr", "%sp",
};
#endif
diff --git a/tools/perf/arch/arm64/util/dwarf-regs.c b/tools/perf/arch/arm64/util/dwarf-regs.c
index d49efeb8172e..068b6189157b 100644
--- a/tools/perf/arch/arm64/util/dwarf-regs.c
+++ b/tools/perf/arch/arm64/util/dwarf-regs.c
@@ -10,17 +10,20 @@
#include <stddef.h>
#include <dwarf-regs.h>
+#include <linux/ptrace.h> /* for struct user_pt_regs */
+#include "util.h"
struct pt_regs_dwarfnum {
const char *name;
unsigned int dwarfnum;
};
-#define STR(s) #s
#define REG_DWARFNUM_NAME(r, num) {.name = r, .dwarfnum = num}
#define GPR_DWARFNUM_NAME(num) \
{.name = STR(%x##num), .dwarfnum = num}
#define REG_DWARFNUM_END {.name = NULL, .dwarfnum = 0}
+#define DWARFNUM2OFFSET(index) \
+ (index * sizeof((struct user_pt_regs *)0)->regs[0])
/*
* Reference:
@@ -78,3 +81,13 @@ const char *get_arch_regstr(unsigned int n)
return roff->name;
return NULL;
}
+
+int regs_query_register_offset(const char *name)
+{
+ const struct pt_regs_dwarfnum *roff;
+
+ for (roff = regdwarfnum_table; roff->name != NULL; roff++)
+ if (!strcmp(roff->name, name))
+ return DWARFNUM2OFFSET(roff->dwarfnum);
+ return -EINVAL;
+}
diff --git a/tools/perf/arch/powerpc/annotate/instructions.c b/tools/perf/arch/powerpc/annotate/instructions.c
new file mode 100644
index 000000000000..3c4004db81b9
--- /dev/null
+++ b/tools/perf/arch/powerpc/annotate/instructions.c
@@ -0,0 +1,58 @@
+static struct ins_ops *powerpc__associate_instruction_ops(struct arch *arch, const char *name)
+{
+ int i;
+ struct ins_ops *ops;
+
+ /*
+ * - Interested only if instruction starts with 'b'.
+ * - Few start with 'b', but aren't branch instructions.
+ */
+ if (name[0] != 'b' ||
+ !strncmp(name, "bcd", 3) ||
+ !strncmp(name, "brinc", 5) ||
+ !strncmp(name, "bper", 4))
+ return NULL;
+
+ ops = &jump_ops;
+
+ i = strlen(name) - 1;
+ if (i < 0)
+ return NULL;
+
+ /* ignore optional hints at the end of the instructions */
+ if (name[i] == '+' || name[i] == '-')
+ i--;
+
+ if (name[i] == 'l' || (name[i] == 'a' && name[i-1] == 'l')) {
+ /*
+ * if the instruction ends up with 'l' or 'la', then
+ * those are considered 'calls' since they update LR.
+ * ... except for 'bnl' which is branch if not less than
+ * and the absolute form of the same.
+ */
+ if (strcmp(name, "bnl") && strcmp(name, "bnl+") &&
+ strcmp(name, "bnl-") && strcmp(name, "bnla") &&
+ strcmp(name, "bnla+") && strcmp(name, "bnla-"))
+ ops = &call_ops;
+ }
+ if (name[i] == 'r' && name[i-1] == 'l')
+ /*
+ * instructions ending with 'lr' are considered to be
+ * return instructions
+ */
+ ops = &ret_ops;
+
+ arch__associate_ins_ops(arch, name, ops);
+ return ops;
+}
+
+static int powerpc__annotate_init(struct arch *arch)
+{
+ if (!arch->initialized) {
+ arch->initialized = true;
+ arch->associate_instruction_ops = powerpc__associate_instruction_ops;
+ arch->objdump.comment_char = '#';
+ }
+
+ return 0;
+}
diff --git a/tools/perf/arch/x86/annotate/instructions.c b/tools/perf/arch/x86/annotate/instructions.c
new file mode 100644
index 000000000000..c1625f256df3
--- /dev/null
+++ b/tools/perf/arch/x86/annotate/instructions.c
@@ -0,0 +1,78 @@
+static struct ins x86__instructions[] = {
+ { .name = "add", .ops = &mov_ops, },
+ { .name = "addl", .ops = &mov_ops, },
+ { .name = "addq", .ops = &mov_ops, },
+ { .name = "addw", .ops = &mov_ops, },
+ { .name = "and", .ops = &mov_ops, },
+ { .name = "bts", .ops = &mov_ops, },
+ { .name = "call", .ops = &call_ops, },
+ { .name = "callq", .ops = &call_ops, },
+ { .name = "cmp", .ops = &mov_ops, },
+ { .name = "cmpb", .ops = &mov_ops, },
+ { .name = "cmpl", .ops = &mov_ops, },
+ { .name = "cmpq", .ops = &mov_ops, },
+ { .name = "cmpw", .ops = &mov_ops, },
+ { .name = "cmpxch", .ops = &mov_ops, },
+ { .name = "dec", .ops = &dec_ops, },
+ { .name = "decl", .ops = &dec_ops, },
+ { .name = "imul", .ops = &mov_ops, },
+ { .name = "inc", .ops = &dec_ops, },
+ { .name = "incl", .ops = &dec_ops, },
+ { .name = "ja", .ops = &jump_ops, },
+ { .name = "jae", .ops = &jump_ops, },
+ { .name = "jb", .ops = &jump_ops, },
+ { .name = "jbe", .ops = &jump_ops, },
+ { .name = "jc", .ops = &jump_ops, },
+ { .name = "jcxz", .ops = &jump_ops, },
+ { .name = "je", .ops = &jump_ops, },
+ { .name = "jecxz", .ops = &jump_ops, },
+ { .name = "jg", .ops = &jump_ops, },
+ { .name = "jge", .ops = &jump_ops, },
+ { .name = "jl", .ops = &jump_ops, },
+ { .name = "jle", .ops = &jump_ops, },
+ { .name = "jmp", .ops = &jump_ops, },
+ { .name = "jmpq", .ops = &jump_ops, },
+ { .name = "jna", .ops = &jump_ops, },
+ { .name = "jnae", .ops = &jump_ops, },
+ { .name = "jnb", .ops = &jump_ops, },
+ { .name = "jnbe", .ops = &jump_ops, },
+ { .name = "jnc", .ops = &jump_ops, },
+ { .name = "jne", .ops = &jump_ops, },
+ { .name = "jng", .ops = &jump_ops, },
+ { .name = "jnge", .ops = &jump_ops, },
+ { .name = "jnl", .ops = &jump_ops, },
+ { .name = "jnle", .ops = &jump_ops, },
+ { .name = "jno", .ops = &jump_ops, },
+ { .name = "jnp", .ops = &jump_ops, },
+ { .name = "jns", .ops = &jump_ops, },
+ { .name = "jnz", .ops = &jump_ops, },
+ { .name = "jo", .ops = &jump_ops, },
+ { .name = "jp", .ops = &jump_ops, },
+ { .name = "jpe", .ops = &jump_ops, },
+ { .name = "jpo", .ops = &jump_ops, },
+ { .name = "jrcxz", .ops = &jump_ops, },
+ { .name = "js", .ops = &jump_ops, },
+ { .name = "jz", .ops = &jump_ops, },
+ { .name = "lea", .ops = &mov_ops, },
+ { .name = "lock", .ops = &lock_ops, },
+ { .name = "mov", .ops = &mov_ops, },
+ { .name = "movb", .ops = &mov_ops, },
+ { .name = "movdqa", .ops = &mov_ops, },
+ { .name = "movl", .ops = &mov_ops, },
+ { .name = "movq", .ops = &mov_ops, },
+ { .name = "movslq", .ops = &mov_ops, },
+ { .name = "movzbl", .ops = &mov_ops, },
+ { .name = "movzwl", .ops = &mov_ops, },
+ { .name = "nop", .ops = &nop_ops, },
+ { .name = "nopl", .ops = &nop_ops, },
+ { .name = "nopw", .ops = &nop_ops, },
+ { .name = "or", .ops = &mov_ops, },
+ { .name = "orl", .ops = &mov_ops, },
+ { .name = "test", .ops = &mov_ops, },
+ { .name = "testb", .ops = &mov_ops, },
+ { .name = "testl", .ops = &mov_ops, },
+ { .name = "xadd", .ops = &mov_ops, },
+ { .name = "xbeginl", .ops = &jump_ops, },
+ { .name = "xbeginq", .ops = &jump_ops, },
+ { .name = "retq", .ops = &ret_ops, },
+};
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index 555263e385c9..e93ef0b38db8 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -335,6 +335,9 @@
326 common copy_file_range sys_copy_file_range
327 64 preadv2 sys_preadv2
328 64 pwritev2 sys_pwritev2
+329 common pkey_mprotect sys_pkey_mprotect
+330 common pkey_alloc sys_pkey_alloc
+331 common pkey_free sys_pkey_free
#
# x32-specific system call numbers start at 512 to avoid cache impact
@@ -374,5 +377,5 @@
543 x32 io_setup compat_sys_io_setup
544 x32 io_submit compat_sys_io_submit
545 x32 execveat compat_sys_execveat/ptregs
-534 x32 preadv2 compat_sys_preadv2
-535 x32 pwritev2 compat_sys_pwritev2
+546 x32 preadv2 compat_sys_preadv64v2
+547 x32 pwritev2 compat_sys_pwritev64v2
diff --git a/tools/perf/arch/x86/tests/arch-tests.c b/tools/perf/arch/x86/tests/arch-tests.c
index 2218cb64f840..99d66191e56c 100644
--- a/tools/perf/arch/x86/tests/arch-tests.c
+++ b/tools/perf/arch/x86/tests/arch-tests.c
@@ -4,27 +4,27 @@
struct test arch_tests[] = {
{
- .desc = "x86 rdpmc test",
+ .desc = "x86 rdpmc",
.func = test__rdpmc,
},
{
- .desc = "Test converting perf time to TSC",
+ .desc = "Convert perf time to TSC",
.func = test__perf_time_to_tsc,
},
#ifdef HAVE_DWARF_UNWIND_SUPPORT
{
- .desc = "Test dwarf unwind",
+ .desc = "DWARF unwind",
.func = test__dwarf_unwind,
},
#endif
#ifdef HAVE_AUXTRACE_SUPPORT
{
- .desc = "Test x86 instruction decoder - new instructions",
+ .desc = "x86 instruction decoder - new instructions",
.func = test__insn_x86,
},
#endif
{
- .desc = "Test intel cqm nmi context read",
+ .desc = "Intel cqm nmi context read",
.func = test__intel_cqm_count_nmi_context,
},
{
diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c
index 8024cd5febd2..da04b8c5568a 100644
--- a/tools/perf/bench/futex-hash.c
+++ b/tools/perf/bench/futex-hash.c
@@ -63,8 +63,9 @@ static const char * const bench_futex_hash_usage[] = {
static void *workerfn(void *arg)
{
int ret;
- unsigned int i;
struct worker *w = (struct worker *) arg;
+ unsigned int i;
+ unsigned long ops = w->ops; /* avoid cacheline bouncing */
pthread_mutex_lock(&thread_lock);
threads_starting--;
@@ -74,7 +75,7 @@ static void *workerfn(void *arg)
pthread_mutex_unlock(&thread_lock);
do {
- for (i = 0; i < nfutexes; i++, w->ops++) {
+ for (i = 0; i < nfutexes; i++, ops++) {
/*
* We want the futex calls to fail in order to stress
* the hashing of uaddr and not measure other steps,
@@ -88,6 +89,7 @@ static void *workerfn(void *arg)
}
} while (!done);
+ w->ops = ops;
return NULL;
}
diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c
index 936d89d30483..91877777ec6e 100644
--- a/tools/perf/bench/futex-lock-pi.c
+++ b/tools/perf/bench/futex-lock-pi.c
@@ -48,7 +48,7 @@ static const struct option options[] = {
};
static const char * const bench_futex_lock_pi_usage[] = {
- "perf bench futex requeue <options>",
+ "perf bench futex lock-pi <options>",
NULL
};
@@ -75,6 +75,7 @@ static void toggle_done(int sig __maybe_unused,
static void *workerfn(void *arg)
{
struct worker *w = (struct worker *) arg;
+ unsigned long ops = w->ops;
pthread_mutex_lock(&thread_lock);
threads_starting--;
@@ -103,9 +104,10 @@ static void *workerfn(void *arg)
if (ret && !silent)
warn("thread %d: Could not unlock pi-lock for %p (%d)",
w->tid, w->futex, ret);
- w->ops++; /* account for thread's share of work */
+ ops++; /* account for thread's share of work */
} while (!done);
+ w->ops = ops;
return NULL;
}
diff --git a/tools/perf/bench/mem-functions.c b/tools/perf/bench/mem-functions.c
index c684910e5a48..52504a83b5a1 100644
--- a/tools/perf/bench/mem-functions.c
+++ b/tools/perf/bench/mem-functions.c
@@ -106,9 +106,10 @@ static double timeval2double(struct timeval *ts)
struct bench_mem_info {
const struct function *functions;
- u64 (*do_cycles)(const struct function *r, size_t size);
- double (*do_gettimeofday)(const struct function *r, size_t size);
+ u64 (*do_cycles)(const struct function *r, size_t size, void *src, void *dst);
+ double (*do_gettimeofday)(const struct function *r, size_t size, void *src, void *dst);
const char *const *usage;
+ bool alloc_src;
};
static void __bench_mem_function(struct bench_mem_info *info, int r_idx, size_t size, double size_total)
@@ -116,16 +117,26 @@ static void __bench_mem_function(struct bench_mem_info *info, int r_idx, size_t
const struct function *r = &info->functions[r_idx];
double result_bps = 0.0;
u64 result_cycles = 0;
+ void *src = NULL, *dst = zalloc(size);
printf("# function '%s' (%s)\n", r->name, r->desc);
+ if (dst == NULL)
+ goto out_alloc_failed;
+
+ if (info->alloc_src) {
+ src = zalloc(size);
+ if (src == NULL)
+ goto out_alloc_failed;
+ }
+
if (bench_format == BENCH_FORMAT_DEFAULT)
printf("# Copying %s bytes ...\n\n", size_str);
if (use_cycles) {
- result_cycles = info->do_cycles(r, size);
+ result_cycles = info->do_cycles(r, size, src, dst);
} else {
- result_bps = info->do_gettimeofday(r, size);
+ result_bps = info->do_gettimeofday(r, size, src, dst);
}
switch (bench_format) {
@@ -149,6 +160,14 @@ static void __bench_mem_function(struct bench_mem_info *info, int r_idx, size_t
BUG_ON(1);
break;
}
+
+out_free:
+ free(src);
+ free(dst);
+ return;
+out_alloc_failed:
+ printf("# Memory allocation failed - maybe size (%s) is too large?\n", size_str);
+ goto out_free;
}
static int bench_mem_common(int argc, const char **argv, struct bench_mem_info *info)
@@ -201,28 +220,14 @@ static int bench_mem_common(int argc, const char **argv, struct bench_mem_info *
return 0;
}
-static void memcpy_alloc_mem(void **dst, void **src, size_t size)
-{
- *dst = zalloc(size);
- if (!*dst)
- die("memory allocation failed - maybe size is too large?\n");
-
- *src = zalloc(size);
- if (!*src)
- die("memory allocation failed - maybe size is too large?\n");
-
- /* Make sure to always prefault zero pages even if MMAP_THRESH is crossed: */
- memset(*src, 0, size);
-}
-
-static u64 do_memcpy_cycles(const struct function *r, size_t size)
+static u64 do_memcpy_cycles(const struct function *r, size_t size, void *src, void *dst)
{
u64 cycle_start = 0ULL, cycle_end = 0ULL;
- void *src = NULL, *dst = NULL;
memcpy_t fn = r->fn.memcpy;
int i;
- memcpy_alloc_mem(&dst, &src, size);
+ /* Make sure to always prefault zero pages even if MMAP_THRESH is crossed: */
+ memset(src, 0, size);
/*
* We prefault the freshly allocated memory range here,
@@ -235,20 +240,15 @@ static u64 do_memcpy_cycles(const struct function *r, size_t size)
fn(dst, src, size);
cycle_end = get_cycles();
- free(src);
- free(dst);
return cycle_end - cycle_start;
}
-static double do_memcpy_gettimeofday(const struct function *r, size_t size)
+static double do_memcpy_gettimeofday(const struct function *r, size_t size, void *src, void *dst)
{
struct timeval tv_start, tv_end, tv_diff;
memcpy_t fn = r->fn.memcpy;
- void *src = NULL, *dst = NULL;
int i;
- memcpy_alloc_mem(&dst, &src, size);
-
/*
* We prefault the freshly allocated memory range here,
* to not measure page fault overhead:
@@ -262,9 +262,6 @@ static double do_memcpy_gettimeofday(const struct function *r, size_t size)
timersub(&tv_end, &tv_start, &tv_diff);
- free(src);
- free(dst);
-
return (double)(((double)size * nr_loops) / timeval2double(&tv_diff));
}
@@ -294,27 +291,18 @@ int bench_mem_memcpy(int argc, const char **argv, const char *prefix __maybe_unu
.do_cycles = do_memcpy_cycles,
.do_gettimeofday = do_memcpy_gettimeofday,
.usage = bench_mem_memcpy_usage,
+ .alloc_src = true,
};
return bench_mem_common(argc, argv, &info);
}
-static void memset_alloc_mem(void **dst, size_t size)
-{
- *dst = zalloc(size);
- if (!*dst)
- die("memory allocation failed - maybe size is too large?\n");
-}
-
-static u64 do_memset_cycles(const struct function *r, size_t size)
+static u64 do_memset_cycles(const struct function *r, size_t size, void *src __maybe_unused, void *dst)
{
u64 cycle_start = 0ULL, cycle_end = 0ULL;
memset_t fn = r->fn.memset;
- void *dst = NULL;
int i;
- memset_alloc_mem(&dst, size);
-
/*
* We prefault the freshly allocated memory range here,
* to not measure page fault overhead:
@@ -326,19 +314,15 @@ static u64 do_memset_cycles(const struct function *r, size_t size)
fn(dst, i, size);
cycle_end = get_cycles();
- free(dst);
return cycle_end - cycle_start;
}
-static double do_memset_gettimeofday(const struct function *r, size_t size)
+static double do_memset_gettimeofday(const struct function *r, size_t size, void *src __maybe_unused, void *dst)
{
struct timeval tv_start, tv_end, tv_diff;
memset_t fn = r->fn.memset;
- void *dst = NULL;
int i;
- memset_alloc_mem(&dst, size);
-
/*
* We prefault the freshly allocated memory range here,
* to not measure page fault overhead:
@@ -352,7 +336,6 @@ static double do_memset_gettimeofday(const struct function *r, size_t size)
timersub(&tv_end, &tv_start, &tv_diff);
- free(dst);
return (double)(((double)size * nr_loops) / timeval2double(&tv_diff));
}
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index 8efe904e486b..3083fc36282b 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -43,6 +43,7 @@
/*
* Debug printf:
*/
+#undef dprintf
#define dprintf(x...) do { if (g && g->p.show_details >= 1) printf(x); } while (0)
struct thread_data {
@@ -1573,13 +1574,13 @@ static int __bench_numa(const char *name)
"GB/sec,", "total-speed", "GB/sec total speed");
if (g->p.show_details >= 2) {
- char tname[32];
+ char tname[14 + 2 * 10 + 1];
struct thread_data *td;
for (p = 0; p < g->p.nr_proc; p++) {
for (t = 0; t < g->p.nr_threads; t++) {
- memset(tname, 0, 32);
+ memset(tname, 0, sizeof(tname));
td = g->threads + p*g->p.nr_threads + t;
- snprintf(tname, 32, "process%d:thread%d", p, t);
+ snprintf(tname, sizeof(tname), "process%d:thread%d", p, t);
print_res(tname, td->speed_gbs,
"GB/sec", "thread-speed", "GB/sec/thread speed");
print_res(tname, td->system_time_ns / NSEC_PER_SEC,
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index ebb628332a6e..4f52d85f5ebc 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -410,6 +410,7 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
OPT_BOOLEAN('f', "force", &file.force, "don't complain, do it"),
OPT_INCR('v', "verbose", &verbose,
"be more verbose (show symbol address, etc)"),
+ OPT_BOOLEAN('q', "quiet", &quiet, "do now show any message"),
OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
"dump raw trace in ASCII"),
OPT_BOOLEAN(0, "gtk", &annotate.use_gtk, "Use the GTK interface"),
@@ -463,6 +464,9 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
annotate.sym_hist_filter = argv[0];
}
+ if (quiet)
+ perf_quiet_option();
+
file.path = input_name;
annotate.session = perf_session__new(&file, false, &annotate.tool);
diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
new file mode 100644
index 000000000000..e2b21723bbf8
--- /dev/null
+++ b/tools/perf/builtin-c2c.c
@@ -0,0 +1,2780 @@
+/*
+ * This is rewrite of original c2c tool introduced in here:
+ * http://lwn.net/Articles/588866/
+ *
+ * The original tool was changed to fit in current perf state.
+ *
+ * Original authors:
+ * Don Zickus <dzickus@redhat.com>
+ * Dick Fowles <fowles@inreach.com>
+ * Joe Mario <jmario@redhat.com>
+ */
+#include <linux/compiler.h>
+#include <linux/kernel.h>
+#include <linux/stringify.h>
+#include <asm/bug.h>
+#include "util.h"
+#include "debug.h"
+#include "builtin.h"
+#include <subcmd/parse-options.h>
+#include "mem-events.h"
+#include "session.h"
+#include "hist.h"
+#include "sort.h"
+#include "tool.h"
+#include "data.h"
+#include "sort.h"
+#include "evlist.h"
+#include "evsel.h"
+#include <asm/bug.h>
+#include "ui/browsers/hists.h"
+#include "evlist.h"
+
+struct c2c_hists {
+ struct hists hists;
+ struct perf_hpp_list list;
+ struct c2c_stats stats;
+};
+
+struct compute_stats {
+ struct stats lcl_hitm;
+ struct stats rmt_hitm;
+ struct stats load;
+};
+
+struct c2c_hist_entry {
+ struct c2c_hists *hists;
+ struct c2c_stats stats;
+ unsigned long *cpuset;
+ struct c2c_stats *node_stats;
+ unsigned int cacheline_idx;
+
+ struct compute_stats cstats;
+
+ /*
+ * must be at the end,
+ * because of its callchain dynamic entry
+ */
+ struct hist_entry he;
+};
+
+static char const *coalesce_default = "pid,iaddr";
+
+struct perf_c2c {
+ struct perf_tool tool;
+ struct c2c_hists hists;
+
+ unsigned long **nodes;
+ int nodes_cnt;
+ int cpus_cnt;
+ int *cpu2node;
+ int node_info;
+
+ bool show_src;
+ bool show_all;
+ bool use_stdio;
+ bool stats_only;
+ bool symbol_full;
+
+ /* HITM shared clines stats */
+ struct c2c_stats hitm_stats;
+ int shared_clines;
+
+ int display;
+
+ const char *coalesce;
+ char *cl_sort;
+ char *cl_resort;
+ char *cl_output;
+};
+
+enum {
+ DISPLAY_LCL,
+ DISPLAY_RMT,
+ DISPLAY_TOT,
+ DISPLAY_MAX,
+};
+
+static const char *display_str[DISPLAY_MAX] = {
+ [DISPLAY_LCL] = "Local",
+ [DISPLAY_RMT] = "Remote",
+ [DISPLAY_TOT] = "Total",
+};
+
+static const struct option c2c_options[] = {
+ OPT_INCR('v', "verbose", &verbose, "be more verbose (show counter open errors, etc)"),
+ OPT_END()
+};
+
+static struct perf_c2c c2c;
+
+static void *c2c_he_zalloc(size_t size)
+{
+ struct c2c_hist_entry *c2c_he;
+
+ c2c_he = zalloc(size + sizeof(*c2c_he));
+ if (!c2c_he)
+ return NULL;
+
+ c2c_he->cpuset = bitmap_alloc(c2c.cpus_cnt);
+ if (!c2c_he->cpuset)
+ return NULL;
+
+ c2c_he->node_stats = zalloc(c2c.nodes_cnt * sizeof(*c2c_he->node_stats));
+ if (!c2c_he->node_stats)
+ return NULL;
+
+ init_stats(&c2c_he->cstats.lcl_hitm);
+ init_stats(&c2c_he->cstats.rmt_hitm);
+ init_stats(&c2c_he->cstats.load);
+
+ return &c2c_he->he;
+}
+
+static void c2c_he_free(void *he)
+{
+ struct c2c_hist_entry *c2c_he;
+
+ c2c_he = container_of(he, struct c2c_hist_entry, he);
+ if (c2c_he->hists) {
+ hists__delete_entries(&c2c_he->hists->hists);
+ free(c2c_he->hists);
+ }
+
+ free(c2c_he->cpuset);
+ free(c2c_he->node_stats);
+ free(c2c_he);
+}
+
+static struct hist_entry_ops c2c_entry_ops = {
+ .new = c2c_he_zalloc,
+ .free = c2c_he_free,
+};
+
+static int c2c_hists__init(struct c2c_hists *hists,
+ const char *sort,
+ int nr_header_lines);
+
+static struct c2c_hists*
+he__get_c2c_hists(struct hist_entry *he,
+ const char *sort,
+ int nr_header_lines)
+{
+ struct c2c_hist_entry *c2c_he;
+ struct c2c_hists *hists;
+ int ret;
+
+ c2c_he = container_of(he, struct c2c_hist_entry, he);
+ if (c2c_he->hists)
+ return c2c_he->hists;
+
+ hists = c2c_he->hists = zalloc(sizeof(*hists));
+ if (!hists)
+ return NULL;
+
+ ret = c2c_hists__init(hists, sort, nr_header_lines);
+ if (ret) {
+ free(hists);
+ return NULL;
+ }
+
+ return hists;
+}
+
+static void c2c_he__set_cpu(struct c2c_hist_entry *c2c_he,
+ struct perf_sample *sample)
+{
+ if (WARN_ONCE(sample->cpu == (unsigned int) -1,
+ "WARNING: no sample cpu value"))
+ return;
+
+ set_bit(sample->cpu, c2c_he->cpuset);
+}
+
+static void compute_stats(struct c2c_hist_entry *c2c_he,
+ struct c2c_stats *stats,
+ u64 weight)
+{
+ struct compute_stats *cstats = &c2c_he->cstats;
+
+ if (stats->rmt_hitm)
+ update_stats(&cstats->rmt_hitm, weight);
+ else if (stats->lcl_hitm)
+ update_stats(&cstats->lcl_hitm, weight);
+ else if (stats->load)
+ update_stats(&cstats->load, weight);
+}
+
+static int process_sample_event(struct perf_tool *tool __maybe_unused,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct perf_evsel *evsel,
+ struct machine *machine)
+{
+ struct c2c_hists *c2c_hists = &c2c.hists;
+ struct c2c_hist_entry *c2c_he;
+ struct c2c_stats stats = { .nr_entries = 0, };
+ struct hist_entry *he;
+ struct addr_location al;
+ struct mem_info *mi, *mi_dup;
+ int ret;
+
+ if (machine__resolve(machine, &al, sample) < 0) {
+ pr_debug("problem processing %d event, skipping it.\n",
+ event->header.type);
+ return -1;
+ }
+
+ ret = sample__resolve_callchain(sample, &callchain_cursor, NULL,
+ evsel, &al, sysctl_perf_event_max_stack);
+ if (ret)
+ goto out;
+
+ mi = sample__resolve_mem(sample, &al);
+ if (mi == NULL)
+ return -ENOMEM;
+
+ mi_dup = memdup(mi, sizeof(*mi));
+ if (!mi_dup)
+ goto free_mi;
+
+ c2c_decode_stats(&stats, mi);
+
+ he = hists__add_entry_ops(&c2c_hists->hists, &c2c_entry_ops,
+ &al, NULL, NULL, mi,
+ sample, true);
+ if (he == NULL)
+ goto free_mi_dup;
+
+ c2c_he = container_of(he, struct c2c_hist_entry, he);
+ c2c_add_stats(&c2c_he->stats, &stats);
+ c2c_add_stats(&c2c_hists->stats, &stats);
+
+ c2c_he__set_cpu(c2c_he, sample);
+
+ hists__inc_nr_samples(&c2c_hists->hists, he->filtered);
+ ret = hist_entry__append_callchain(he, sample);
+
+ if (!ret) {
+ /*
+ * There's already been warning about missing
+ * sample's cpu value. Let's account all to
+ * node 0 in this case, without any further
+ * warning.
+ *
+ * Doing node stats only for single callchain data.
+ */
+ int cpu = sample->cpu == (unsigned int) -1 ? 0 : sample->cpu;
+ int node = c2c.cpu2node[cpu];
+
+ mi = mi_dup;
+
+ mi_dup = memdup(mi, sizeof(*mi));
+ if (!mi_dup)
+ goto free_mi;
+
+ c2c_hists = he__get_c2c_hists(he, c2c.cl_sort, 2);
+ if (!c2c_hists)
+ goto free_mi_dup;
+
+ he = hists__add_entry_ops(&c2c_hists->hists, &c2c_entry_ops,
+ &al, NULL, NULL, mi,
+ sample, true);
+ if (he == NULL)
+ goto free_mi_dup;
+
+ c2c_he = container_of(he, struct c2c_hist_entry, he);
+ c2c_add_stats(&c2c_he->stats, &stats);
+ c2c_add_stats(&c2c_hists->stats, &stats);
+ c2c_add_stats(&c2c_he->node_stats[node], &stats);
+
+ compute_stats(c2c_he, &stats, sample->weight);
+
+ c2c_he__set_cpu(c2c_he, sample);
+
+ hists__inc_nr_samples(&c2c_hists->hists, he->filtered);
+ ret = hist_entry__append_callchain(he, sample);
+ }
+
+out:
+ addr_location__put(&al);
+ return ret;
+
+free_mi_dup:
+ free(mi_dup);
+free_mi:
+ free(mi);
+ ret = -ENOMEM;
+ goto out;
+}
+
+static struct perf_c2c c2c = {
+ .tool = {
+ .sample = process_sample_event,
+ .mmap = perf_event__process_mmap,
+ .mmap2 = perf_event__process_mmap2,
+ .comm = perf_event__process_comm,
+ .exit = perf_event__process_exit,
+ .fork = perf_event__process_fork,
+ .lost = perf_event__process_lost,
+ .ordered_events = true,
+ .ordering_requires_timestamps = true,
+ },
+};
+
+static const char * const c2c_usage[] = {
+ "perf c2c {record|report}",
+ NULL
+};
+
+static const char * const __usage_report[] = {
+ "perf c2c report",
+ NULL
+};
+
+static const char * const *report_c2c_usage = __usage_report;
+
+#define C2C_HEADER_MAX 2
+
+struct c2c_header {
+ struct {
+ const char *text;
+ int span;
+ } line[C2C_HEADER_MAX];
+};
+
+struct c2c_dimension {
+ struct c2c_header header;
+ const char *name;
+ int width;
+ struct sort_entry *se;
+
+ int64_t (*cmp)(struct perf_hpp_fmt *fmt,
+ struct hist_entry *, struct hist_entry *);
+ int (*entry)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+ struct hist_entry *he);
+ int (*color)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+ struct hist_entry *he);
+};
+
+struct c2c_fmt {
+ struct perf_hpp_fmt fmt;
+ struct c2c_dimension *dim;
+};
+
+#define SYMBOL_WIDTH 30
+
+static struct c2c_dimension dim_symbol;
+static struct c2c_dimension dim_srcline;
+
+static int symbol_width(struct hists *hists, struct sort_entry *se)
+{
+ int width = hists__col_len(hists, se->se_width_idx);
+
+ if (!c2c.symbol_full)
+ width = MIN(width, SYMBOL_WIDTH);
+
+ return width;
+}
+
+static int c2c_width(struct perf_hpp_fmt *fmt,
+ struct perf_hpp *hpp __maybe_unused,
+ struct hists *hists)
+{
+ struct c2c_fmt *c2c_fmt;
+ struct c2c_dimension *dim;
+
+ c2c_fmt = container_of(fmt, struct c2c_fmt, fmt);
+ dim = c2c_fmt->dim;
+
+ if (dim == &dim_symbol || dim == &dim_srcline)
+ return symbol_width(hists, dim->se);
+
+ return dim->se ? hists__col_len(hists, dim->se->se_width_idx) :
+ c2c_fmt->dim->width;
+}
+
+static int c2c_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+ struct hists *hists, int line, int *span)
+{
+ struct perf_hpp_list *hpp_list = hists->hpp_list;
+ struct c2c_fmt *c2c_fmt;
+ struct c2c_dimension *dim;
+ const char *text = NULL;
+ int width = c2c_width(fmt, hpp, hists);
+
+ c2c_fmt = container_of(fmt, struct c2c_fmt, fmt);
+ dim = c2c_fmt->dim;
+
+ if (dim->se) {
+ text = dim->header.line[line].text;
+ /* Use the last line from sort_entry if not defined. */
+ if (!text && (line == hpp_list->nr_header_lines - 1))
+ text = dim->se->se_header;
+ } else {
+ text = dim->header.line[line].text;
+
+ if (*span) {
+ (*span)--;
+ return 0;
+ } else {
+ *span = dim->header.line[line].span;
+ }
+ }
+
+ if (text == NULL)
+ text = "";
+
+ return scnprintf(hpp->buf, hpp->size, "%*s", width, text);
+}
+
+#define HEX_STR(__s, __v) \
+({ \
+ scnprintf(__s, sizeof(__s), "0x%" PRIx64, __v); \
+ __s; \
+})
+
+static int64_t
+dcacheline_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
+ struct hist_entry *left, struct hist_entry *right)
+{
+ return sort__dcacheline_cmp(left, right);
+}
+
+static int dcacheline_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+ struct hist_entry *he)
+{
+ uint64_t addr = 0;
+ int width = c2c_width(fmt, hpp, he->hists);
+ char buf[20];
+
+ if (he->mem_info)
+ addr = cl_address(he->mem_info->daddr.addr);
+
+ return scnprintf(hpp->buf, hpp->size, "%*s", width, HEX_STR(buf, addr));
+}
+
+static int offset_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+ struct hist_entry *he)
+{
+ uint64_t addr = 0;
+ int width = c2c_width(fmt, hpp, he->hists);
+ char buf[20];
+
+ if (he->mem_info)
+ addr = cl_offset(he->mem_info->daddr.al_addr);
+
+ return scnprintf(hpp->buf, hpp->size, "%*s", width, HEX_STR(buf, addr));
+}
+
+static int64_t
+offset_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
+ struct hist_entry *left, struct hist_entry *right)
+{
+ uint64_t l = 0, r = 0;
+
+ if (left->mem_info)
+ l = cl_offset(left->mem_info->daddr.addr);
+ if (right->mem_info)
+ r = cl_offset(right->mem_info->daddr.addr);
+
+ return (int64_t)(r - l);
+}
+
+static int
+iaddr_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+ struct hist_entry *he)
+{
+ uint64_t addr = 0;
+ int width = c2c_width(fmt, hpp, he->hists);
+ char buf[20];
+
+ if (he->mem_info)
+ addr = he->mem_info->iaddr.addr;
+
+ return scnprintf(hpp->buf, hpp->size, "%*s", width, HEX_STR(buf, addr));
+}
+
+static int64_t
+iaddr_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
+ struct hist_entry *left, struct hist_entry *right)
+{
+ return sort__iaddr_cmp(left, right);
+}
+
+static int
+tot_hitm_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+ struct hist_entry *he)
+{
+ struct c2c_hist_entry *c2c_he;
+ int width = c2c_width(fmt, hpp, he->hists);
+ unsigned int tot_hitm;
+
+ c2c_he = container_of(he, struct c2c_hist_entry, he);
+ tot_hitm = c2c_he->stats.lcl_hitm + c2c_he->stats.rmt_hitm;
+
+ return scnprintf(hpp->buf, hpp->size, "%*u", width, tot_hitm);
+}
+
+static int64_t
+tot_hitm_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
+ struct hist_entry *left, struct hist_entry *right)
+{
+ struct c2c_hist_entry *c2c_left;
+ struct c2c_hist_entry *c2c_right;
+ unsigned int tot_hitm_left;
+ unsigned int tot_hitm_right;
+
+ c2c_left = container_of(left, struct c2c_hist_entry, he);
+ c2c_right = container_of(right, struct c2c_hist_entry, he);
+
+ tot_hitm_left = c2c_left->stats.lcl_hitm + c2c_left->stats.rmt_hitm;
+ tot_hitm_right = c2c_right->stats.lcl_hitm + c2c_right->stats.rmt_hitm;
+
+ return tot_hitm_left - tot_hitm_right;
+}
+
+#define STAT_FN_ENTRY(__f) \
+static int \
+__f ## _entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, \
+ struct hist_entry *he) \
+{ \
+ struct c2c_hist_entry *c2c_he; \
+ int width = c2c_width(fmt, hpp, he->hists); \
+ \
+ c2c_he = container_of(he, struct c2c_hist_entry, he); \
+ return scnprintf(hpp->buf, hpp->size, "%*u", width, \
+ c2c_he->stats.__f); \
+}
+
+#define STAT_FN_CMP(__f) \
+static int64_t \
+__f ## _cmp(struct perf_hpp_fmt *fmt __maybe_unused, \
+ struct hist_entry *left, struct hist_entry *right) \
+{ \
+ struct c2c_hist_entry *c2c_left, *c2c_right; \
+ \
+ c2c_left = container_of(left, struct c2c_hist_entry, he); \
+ c2c_right = container_of(right, struct c2c_hist_entry, he); \
+ return c2c_left->stats.__f - c2c_right->stats.__f; \
+}
+
+#define STAT_FN(__f) \
+ STAT_FN_ENTRY(__f) \
+ STAT_FN_CMP(__f)
+
+STAT_FN(rmt_hitm)
+STAT_FN(lcl_hitm)
+STAT_FN(store)
+STAT_FN(st_l1hit)
+STAT_FN(st_l1miss)
+STAT_FN(ld_fbhit)
+STAT_FN(ld_l1hit)
+STAT_FN(ld_l2hit)
+STAT_FN(ld_llchit)
+STAT_FN(rmt_hit)
+
+static uint64_t llc_miss(struct c2c_stats *stats)
+{
+ uint64_t llcmiss;
+
+ llcmiss = stats->lcl_dram +
+ stats->rmt_dram +
+ stats->rmt_hitm +
+ stats->rmt_hit;
+
+ return llcmiss;
+}
+
+static int
+ld_llcmiss_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+ struct hist_entry *he)
+{
+ struct c2c_hist_entry *c2c_he;
+ int width = c2c_width(fmt, hpp, he->hists);
+
+ c2c_he = container_of(he, struct c2c_hist_entry, he);
+
+ return scnprintf(hpp->buf, hpp->size, "%*lu", width,
+ llc_miss(&c2c_he->stats));
+}
+
+static int64_t
+ld_llcmiss_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
+ struct hist_entry *left, struct hist_entry *right)
+{
+ struct c2c_hist_entry *c2c_left;
+ struct c2c_hist_entry *c2c_right;
+
+ c2c_left = container_of(left, struct c2c_hist_entry, he);
+ c2c_right = container_of(right, struct c2c_hist_entry, he);
+
+ return llc_miss(&c2c_left->stats) - llc_miss(&c2c_right->stats);
+}
+
+static uint64_t total_records(struct c2c_stats *stats)
+{
+ uint64_t lclmiss, ldcnt, total;
+
+ lclmiss = stats->lcl_dram +
+ stats->rmt_dram +
+ stats->rmt_hitm +
+ stats->rmt_hit;
+
+ ldcnt = lclmiss +
+ stats->ld_fbhit +
+ stats->ld_l1hit +
+ stats->ld_l2hit +
+ stats->ld_llchit +
+ stats->lcl_hitm;
+
+ total = ldcnt +
+ stats->st_l1hit +
+ stats->st_l1miss;
+
+ return total;
+}
+
+static int
+tot_recs_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+ struct hist_entry *he)
+{
+ struct c2c_hist_entry *c2c_he;
+ int width = c2c_width(fmt, hpp, he->hists);
+ uint64_t tot_recs;
+
+ c2c_he = container_of(he, struct c2c_hist_entry, he);
+ tot_recs = total_records(&c2c_he->stats);
+
+ return scnprintf(hpp->buf, hpp->size, "%*" PRIu64, width, tot_recs);
+}
+
+static int64_t
+tot_recs_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
+ struct hist_entry *left, struct hist_entry *right)
+{
+ struct c2c_hist_entry *c2c_left;
+ struct c2c_hist_entry *c2c_right;
+ uint64_t tot_recs_left;
+ uint64_t tot_recs_right;
+
+ c2c_left = container_of(left, struct c2c_hist_entry, he);
+ c2c_right = container_of(right, struct c2c_hist_entry, he);
+
+ tot_recs_left = total_records(&c2c_left->stats);
+ tot_recs_right = total_records(&c2c_right->stats);
+
+ return tot_recs_left - tot_recs_right;
+}
+
+static uint64_t total_loads(struct c2c_stats *stats)
+{
+ uint64_t lclmiss, ldcnt;
+
+ lclmiss = stats->lcl_dram +
+ stats->rmt_dram +
+ stats->rmt_hitm +
+ stats->rmt_hit;
+
+ ldcnt = lclmiss +
+ stats->ld_fbhit +
+ stats->ld_l1hit +
+ stats->ld_l2hit +
+ stats->ld_llchit +
+ stats->lcl_hitm;
+
+ return ldcnt;
+}
+
+static int
+tot_loads_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+ struct hist_entry *he)
+{
+ struct c2c_hist_entry *c2c_he;
+ int width = c2c_width(fmt, hpp, he->hists);
+ uint64_t tot_recs;
+
+ c2c_he = container_of(he, struct c2c_hist_entry, he);
+ tot_recs = total_loads(&c2c_he->stats);
+
+ return scnprintf(hpp->buf, hpp->size, "%*" PRIu64, width, tot_recs);
+}
+
+static int64_t
+tot_loads_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
+ struct hist_entry *left, struct hist_entry *right)
+{
+ struct c2c_hist_entry *c2c_left;
+ struct c2c_hist_entry *c2c_right;
+ uint64_t tot_recs_left;
+ uint64_t tot_recs_right;
+
+ c2c_left = container_of(left, struct c2c_hist_entry, he);
+ c2c_right = container_of(right, struct c2c_hist_entry, he);
+
+ tot_recs_left = total_loads(&c2c_left->stats);
+ tot_recs_right = total_loads(&c2c_right->stats);
+
+ return tot_recs_left - tot_recs_right;
+}
+
+typedef double (get_percent_cb)(struct c2c_hist_entry *);
+
+static int
+percent_color(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+ struct hist_entry *he, get_percent_cb get_percent)
+{
+ struct c2c_hist_entry *c2c_he;
+ int width = c2c_width(fmt, hpp, he->hists);
+ double per;
+
+ c2c_he = container_of(he, struct c2c_hist_entry, he);
+ per = get_percent(c2c_he);
+
+#ifdef HAVE_SLANG_SUPPORT
+ if (use_browser)
+ return __hpp__slsmg_color_printf(hpp, "%*.2f%%", width - 1, per);
+#endif
+ return hpp_color_scnprintf(hpp, "%*.2f%%", width - 1, per);
+}
+
+static double percent_hitm(struct c2c_hist_entry *c2c_he)
+{
+ struct c2c_hists *hists;
+ struct c2c_stats *stats;
+ struct c2c_stats *total;
+ int tot = 0, st = 0;
+ double p;
+
+ hists = container_of(c2c_he->he.hists, struct c2c_hists, hists);
+ stats = &c2c_he->stats;
+ total = &hists->stats;
+
+ switch (c2c.display) {
+ case DISPLAY_RMT:
+ st = stats->rmt_hitm;
+ tot = total->rmt_hitm;
+ break;
+ case DISPLAY_LCL:
+ st = stats->lcl_hitm;
+ tot = total->lcl_hitm;
+ break;
+ case DISPLAY_TOT:
+ st = stats->tot_hitm;
+ tot = total->tot_hitm;
+ default:
+ break;
+ }
+
+ p = tot ? (double) st / tot : 0;
+
+ return 100 * p;
+}
+
+#define PERC_STR(__s, __v) \
+({ \
+ scnprintf(__s, sizeof(__s), "%.2F%%", __v); \
+ __s; \
+})
+
+static int
+percent_hitm_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+ struct hist_entry *he)
+{
+ struct c2c_hist_entry *c2c_he;
+ int width = c2c_width(fmt, hpp, he->hists);
+ char buf[10];
+ double per;
+
+ c2c_he = container_of(he, struct c2c_hist_entry, he);
+ per = percent_hitm(c2c_he);
+ return scnprintf(hpp->buf, hpp->size, "%*s", width, PERC_STR(buf, per));
+}
+
+static int
+percent_hitm_color(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+ struct hist_entry *he)
+{
+ return percent_color(fmt, hpp, he, percent_hitm);
+}
+
+static int64_t
+percent_hitm_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
+ struct hist_entry *left, struct hist_entry *right)
+{
+ struct c2c_hist_entry *c2c_left;
+ struct c2c_hist_entry *c2c_right;
+ double per_left;
+ double per_right;
+
+ c2c_left = container_of(left, struct c2c_hist_entry, he);
+ c2c_right = container_of(right, struct c2c_hist_entry, he);
+
+ per_left = percent_hitm(c2c_left);
+ per_right = percent_hitm(c2c_right);
+
+ return per_left - per_right;
+}
+
+static struct c2c_stats *he_stats(struct hist_entry *he)
+{
+ struct c2c_hist_entry *c2c_he;
+
+ c2c_he = container_of(he, struct c2c_hist_entry, he);
+ return &c2c_he->stats;
+}
+
+static struct c2c_stats *total_stats(struct hist_entry *he)
+{
+ struct c2c_hists *hists;
+
+ hists = container_of(he->hists, struct c2c_hists, hists);
+ return &hists->stats;
+}
+
+static double percent(int st, int tot)
+{
+ return tot ? 100. * (double) st / (double) tot : 0;
+}
+
+#define PERCENT(__h, __f) percent(he_stats(__h)->__f, total_stats(__h)->__f)
+
+#define PERCENT_FN(__f) \
+static double percent_ ## __f(struct c2c_hist_entry *c2c_he) \
+{ \
+ struct c2c_hists *hists; \
+ \
+ hists = container_of(c2c_he->he.hists, struct c2c_hists, hists); \
+ return percent(c2c_he->stats.__f, hists->stats.__f); \
+}
+
+PERCENT_FN(rmt_hitm)
+PERCENT_FN(lcl_hitm)
+PERCENT_FN(st_l1hit)
+PERCENT_FN(st_l1miss)
+
+static int
+percent_rmt_hitm_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+ struct hist_entry *he)
+{
+ int width = c2c_width(fmt, hpp, he->hists);
+ double per = PERCENT(he, rmt_hitm);
+ char buf[10];
+
+ return scnprintf(hpp->buf, hpp->size, "%*s", width, PERC_STR(buf, per));
+}
+
+static int
+percent_rmt_hitm_color(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+ struct hist_entry *he)
+{
+ return percent_color(fmt, hpp, he, percent_rmt_hitm);
+}
+
+static int64_t
+percent_rmt_hitm_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
+ struct hist_entry *left, struct hist_entry *right)
+{
+ double per_left;
+ double per_right;
+
+ per_left = PERCENT(left, lcl_hitm);
+ per_right = PERCENT(right, lcl_hitm);
+
+ return per_left - per_right;
+}
+
+static int
+percent_lcl_hitm_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+ struct hist_entry *he)
+{
+ int width = c2c_width(fmt, hpp, he->hists);
+ double per = PERCENT(he, lcl_hitm);
+ char buf[10];
+
+ return scnprintf(hpp->buf, hpp->size, "%*s", width, PERC_STR(buf, per));
+}
+
+static int
+percent_lcl_hitm_color(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+ struct hist_entry *he)
+{
+ return percent_color(fmt, hpp, he, percent_lcl_hitm);
+}
+
+static int64_t
+percent_lcl_hitm_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
+ struct hist_entry *left, struct hist_entry *right)
+{
+ double per_left;
+ double per_right;
+
+ per_left = PERCENT(left, lcl_hitm);
+ per_right = PERCENT(right, lcl_hitm);
+
+ return per_left - per_right;
+}
+
+static int
+percent_stores_l1hit_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+ struct hist_entry *he)
+{
+ int width = c2c_width(fmt, hpp, he->hists);
+ double per = PERCENT(he, st_l1hit);
+ char buf[10];
+
+ return scnprintf(hpp->buf, hpp->size, "%*s", width, PERC_STR(buf, per));
+}
+
+static int
+percent_stores_l1hit_color(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+ struct hist_entry *he)
+{
+ return percent_color(fmt, hpp, he, percent_st_l1hit);
+}
+
+static int64_t
+percent_stores_l1hit_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
+ struct hist_entry *left, struct hist_entry *right)
+{
+ double per_left;
+ double per_right;
+
+ per_left = PERCENT(left, st_l1hit);
+ per_right = PERCENT(right, st_l1hit);
+
+ return per_left - per_right;
+}
+
+static int
+percent_stores_l1miss_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+ struct hist_entry *he)
+{
+ int width = c2c_width(fmt, hpp, he->hists);
+ double per = PERCENT(he, st_l1miss);
+ char buf[10];
+
+ return scnprintf(hpp->buf, hpp->size, "%*s", width, PERC_STR(buf, per));
+}
+
+static int
+percent_stores_l1miss_color(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+ struct hist_entry *he)
+{
+ return percent_color(fmt, hpp, he, percent_st_l1miss);
+}
+
+static int64_t
+percent_stores_l1miss_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
+ struct hist_entry *left, struct hist_entry *right)
+{
+ double per_left;
+ double per_right;
+
+ per_left = PERCENT(left, st_l1miss);
+ per_right = PERCENT(right, st_l1miss);
+
+ return per_left - per_right;
+}
+
+STAT_FN(lcl_dram)
+STAT_FN(rmt_dram)
+
+static int
+pid_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+ struct hist_entry *he)
+{
+ int width = c2c_width(fmt, hpp, he->hists);
+
+ return scnprintf(hpp->buf, hpp->size, "%*d", width, he->thread->pid_);
+}
+
+static int64_t
+pid_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
+ struct hist_entry *left, struct hist_entry *right)
+{
+ return left->thread->pid_ - right->thread->pid_;
+}
+
+static int64_t
+empty_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
+ struct hist_entry *left __maybe_unused,
+ struct hist_entry *right __maybe_unused)
+{
+ return 0;
+}
+
+static int
+node_entry(struct perf_hpp_fmt *fmt __maybe_unused, struct perf_hpp *hpp,
+ struct hist_entry *he)
+{
+ struct c2c_hist_entry *c2c_he;
+ bool first = true;
+ int node;
+ int ret = 0;
+
+ c2c_he = container_of(he, struct c2c_hist_entry, he);
+
+ for (node = 0; node < c2c.nodes_cnt; node++) {
+ DECLARE_BITMAP(set, c2c.cpus_cnt);
+
+ bitmap_zero(set, c2c.cpus_cnt);
+ bitmap_and(set, c2c_he->cpuset, c2c.nodes[node], c2c.cpus_cnt);
+
+ if (!bitmap_weight(set, c2c.cpus_cnt)) {
+ if (c2c.node_info == 1) {
+ ret = scnprintf(hpp->buf, hpp->size, "%21s", " ");
+ advance_hpp(hpp, ret);
+ }
+ continue;
+ }
+
+ if (!first) {
+ ret = scnprintf(hpp->buf, hpp->size, " ");
+ advance_hpp(hpp, ret);
+ }
+
+ switch (c2c.node_info) {
+ case 0:
+ ret = scnprintf(hpp->buf, hpp->size, "%2d", node);
+ advance_hpp(hpp, ret);
+ break;
+ case 1:
+ {
+ int num = bitmap_weight(c2c_he->cpuset, c2c.cpus_cnt);
+ struct c2c_stats *stats = &c2c_he->node_stats[node];
+
+ ret = scnprintf(hpp->buf, hpp->size, "%2d{%2d ", node, num);
+ advance_hpp(hpp, ret);
+
+ #define DISPLAY_HITM(__h) \
+ if (c2c_he->stats.__h> 0) { \
+ ret = scnprintf(hpp->buf, hpp->size, "%5.1f%% ", \
+ percent(stats->__h, c2c_he->stats.__h));\
+ } else { \
+ ret = scnprintf(hpp->buf, hpp->size, "%6s ", "n/a"); \
+ }
+
+ switch (c2c.display) {
+ case DISPLAY_RMT:
+ DISPLAY_HITM(rmt_hitm);
+ break;
+ case DISPLAY_LCL:
+ DISPLAY_HITM(lcl_hitm);
+ break;
+ case DISPLAY_TOT:
+ DISPLAY_HITM(tot_hitm);
+ default:
+ break;
+ }
+
+ #undef DISPLAY_HITM
+
+ advance_hpp(hpp, ret);
+
+ if (c2c_he->stats.store > 0) {
+ ret = scnprintf(hpp->buf, hpp->size, "%5.1f%%}",
+ percent(stats->store, c2c_he->stats.store));
+ } else {
+ ret = scnprintf(hpp->buf, hpp->size, "%6s}", "n/a");
+ }
+
+ advance_hpp(hpp, ret);
+ break;
+ }
+ case 2:
+ ret = scnprintf(hpp->buf, hpp->size, "%2d{", node);
+ advance_hpp(hpp, ret);
+
+ ret = bitmap_scnprintf(set, c2c.cpus_cnt, hpp->buf, hpp->size);
+ advance_hpp(hpp, ret);
+
+ ret = scnprintf(hpp->buf, hpp->size, "}");
+ advance_hpp(hpp, ret);
+ break;
+ default:
+ break;
+ }
+
+ first = false;
+ }
+
+ return 0;
+}
+
+static int
+mean_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+ struct hist_entry *he, double mean)
+{
+ int width = c2c_width(fmt, hpp, he->hists);
+ char buf[10];
+
+ scnprintf(buf, 10, "%6.0f", mean);
+ return scnprintf(hpp->buf, hpp->size, "%*s", width, buf);
+}
+
+#define MEAN_ENTRY(__func, __val) \
+static int \
+__func(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, struct hist_entry *he) \
+{ \
+ struct c2c_hist_entry *c2c_he; \
+ c2c_he = container_of(he, struct c2c_hist_entry, he); \
+ return mean_entry(fmt, hpp, he, avg_stats(&c2c_he->cstats.__val)); \
+}
+
+MEAN_ENTRY(mean_rmt_entry, rmt_hitm);
+MEAN_ENTRY(mean_lcl_entry, lcl_hitm);
+MEAN_ENTRY(mean_load_entry, load);
+
+static int
+cpucnt_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+ struct hist_entry *he)
+{
+ struct c2c_hist_entry *c2c_he;
+ int width = c2c_width(fmt, hpp, he->hists);
+ char buf[10];
+
+ c2c_he = container_of(he, struct c2c_hist_entry, he);
+
+ scnprintf(buf, 10, "%d", bitmap_weight(c2c_he->cpuset, c2c.cpus_cnt));
+ return scnprintf(hpp->buf, hpp->size, "%*s", width, buf);
+}
+
+static int
+cl_idx_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+ struct hist_entry *he)
+{
+ struct c2c_hist_entry *c2c_he;
+ int width = c2c_width(fmt, hpp, he->hists);
+ char buf[10];
+
+ c2c_he = container_of(he, struct c2c_hist_entry, he);
+
+ scnprintf(buf, 10, "%u", c2c_he->cacheline_idx);
+ return scnprintf(hpp->buf, hpp->size, "%*s", width, buf);
+}
+
+static int
+cl_idx_empty_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+ struct hist_entry *he)
+{
+ int width = c2c_width(fmt, hpp, he->hists);
+
+ return scnprintf(hpp->buf, hpp->size, "%*s", width, "");
+}
+
+#define HEADER_LOW(__h) \
+ { \
+ .line[1] = { \
+ .text = __h, \
+ }, \
+ }
+
+#define HEADER_BOTH(__h0, __h1) \
+ { \
+ .line[0] = { \
+ .text = __h0, \
+ }, \
+ .line[1] = { \
+ .text = __h1, \
+ }, \
+ }
+
+#define HEADER_SPAN(__h0, __h1, __s) \
+ { \
+ .line[0] = { \
+ .text = __h0, \
+ .span = __s, \
+ }, \
+ .line[1] = { \
+ .text = __h1, \
+ }, \
+ }
+
+#define HEADER_SPAN_LOW(__h) \
+ { \
+ .line[1] = { \
+ .text = __h, \
+ }, \
+ }
+
+static struct c2c_dimension dim_dcacheline = {
+ .header = HEADER_LOW("Cacheline"),
+ .name = "dcacheline",
+ .cmp = dcacheline_cmp,
+ .entry = dcacheline_entry,
+ .width = 18,
+};
+
+static struct c2c_header header_offset_tui = HEADER_LOW("Off");
+
+static struct c2c_dimension dim_offset = {
+ .header = HEADER_BOTH("Data address", "Offset"),
+ .name = "offset",
+ .cmp = offset_cmp,
+ .entry = offset_entry,
+ .width = 18,
+};
+
+static struct c2c_dimension dim_iaddr = {
+ .header = HEADER_LOW("Code address"),
+ .name = "iaddr",
+ .cmp = iaddr_cmp,
+ .entry = iaddr_entry,
+ .width = 18,
+};
+
+static struct c2c_dimension dim_tot_hitm = {
+ .header = HEADER_SPAN("----- LLC Load Hitm -----", "Total", 2),
+ .name = "tot_hitm",
+ .cmp = tot_hitm_cmp,
+ .entry = tot_hitm_entry,
+ .width = 7,
+};
+
+static struct c2c_dimension dim_lcl_hitm = {
+ .header = HEADER_SPAN_LOW("Lcl"),
+ .name = "lcl_hitm",
+ .cmp = lcl_hitm_cmp,
+ .entry = lcl_hitm_entry,
+ .width = 7,
+};
+
+static struct c2c_dimension dim_rmt_hitm = {
+ .header = HEADER_SPAN_LOW("Rmt"),
+ .name = "rmt_hitm",
+ .cmp = rmt_hitm_cmp,
+ .entry = rmt_hitm_entry,
+ .width = 7,
+};
+
+static struct c2c_dimension dim_cl_rmt_hitm = {
+ .header = HEADER_SPAN("----- HITM -----", "Rmt", 1),
+ .name = "cl_rmt_hitm",
+ .cmp = rmt_hitm_cmp,
+ .entry = rmt_hitm_entry,
+ .width = 7,
+};
+
+static struct c2c_dimension dim_cl_lcl_hitm = {
+ .header = HEADER_SPAN_LOW("Lcl"),
+ .name = "cl_lcl_hitm",
+ .cmp = lcl_hitm_cmp,
+ .entry = lcl_hitm_entry,
+ .width = 7,
+};
+
+static struct c2c_dimension dim_stores = {
+ .header = HEADER_SPAN("---- Store Reference ----", "Total", 2),
+ .name = "stores",
+ .cmp = store_cmp,
+ .entry = store_entry,
+ .width = 7,
+};
+
+static struct c2c_dimension dim_stores_l1hit = {
+ .header = HEADER_SPAN_LOW("L1Hit"),
+ .name = "stores_l1hit",
+ .cmp = st_l1hit_cmp,
+ .entry = st_l1hit_entry,
+ .width = 7,
+};
+
+static struct c2c_dimension dim_stores_l1miss = {
+ .header = HEADER_SPAN_LOW("L1Miss"),
+ .name = "stores_l1miss",
+ .cmp = st_l1miss_cmp,
+ .entry = st_l1miss_entry,
+ .width = 7,
+};
+
+static struct c2c_dimension dim_cl_stores_l1hit = {
+ .header = HEADER_SPAN("-- Store Refs --", "L1 Hit", 1),
+ .name = "cl_stores_l1hit",
+ .cmp = st_l1hit_cmp,
+ .entry = st_l1hit_entry,
+ .width = 7,
+};
+
+static struct c2c_dimension dim_cl_stores_l1miss = {
+ .header = HEADER_SPAN_LOW("L1 Miss"),
+ .name = "cl_stores_l1miss",
+ .cmp = st_l1miss_cmp,
+ .entry = st_l1miss_entry,
+ .width = 7,
+};
+
+static struct c2c_dimension dim_ld_fbhit = {
+ .header = HEADER_SPAN("----- Core Load Hit -----", "FB", 2),
+ .name = "ld_fbhit",
+ .cmp = ld_fbhit_cmp,
+ .entry = ld_fbhit_entry,
+ .width = 7,
+};
+
+static struct c2c_dimension dim_ld_l1hit = {
+ .header = HEADER_SPAN_LOW("L1"),
+ .name = "ld_l1hit",
+ .cmp = ld_l1hit_cmp,
+ .entry = ld_l1hit_entry,
+ .width = 7,
+};
+
+static struct c2c_dimension dim_ld_l2hit = {
+ .header = HEADER_SPAN_LOW("L2"),
+ .name = "ld_l2hit",
+ .cmp = ld_l2hit_cmp,
+ .entry = ld_l2hit_entry,
+ .width = 7,
+};
+
+static struct c2c_dimension dim_ld_llchit = {
+ .header = HEADER_SPAN("-- LLC Load Hit --", "Llc", 1),
+ .name = "ld_lclhit",
+ .cmp = ld_llchit_cmp,
+ .entry = ld_llchit_entry,
+ .width = 8,
+};
+
+static struct c2c_dimension dim_ld_rmthit = {
+ .header = HEADER_SPAN_LOW("Rmt"),
+ .name = "ld_rmthit",
+ .cmp = rmt_hit_cmp,
+ .entry = rmt_hit_entry,
+ .width = 8,
+};
+
+static struct c2c_dimension dim_ld_llcmiss = {
+ .header = HEADER_BOTH("LLC", "Ld Miss"),
+ .name = "ld_llcmiss",
+ .cmp = ld_llcmiss_cmp,
+ .entry = ld_llcmiss_entry,
+ .width = 7,
+};
+
+static struct c2c_dimension dim_tot_recs = {
+ .header = HEADER_BOTH("Total", "records"),
+ .name = "tot_recs",
+ .cmp = tot_recs_cmp,
+ .entry = tot_recs_entry,
+ .width = 7,
+};
+
+static struct c2c_dimension dim_tot_loads = {
+ .header = HEADER_BOTH("Total", "Loads"),
+ .name = "tot_loads",
+ .cmp = tot_loads_cmp,
+ .entry = tot_loads_entry,
+ .width = 7,
+};
+
+static struct c2c_header percent_hitm_header[] = {
+ [DISPLAY_LCL] = HEADER_BOTH("Lcl", "Hitm"),
+ [DISPLAY_RMT] = HEADER_BOTH("Rmt", "Hitm"),
+ [DISPLAY_TOT] = HEADER_BOTH("Tot", "Hitm"),
+};
+
+static struct c2c_dimension dim_percent_hitm = {
+ .name = "percent_hitm",
+ .cmp = percent_hitm_cmp,
+ .entry = percent_hitm_entry,
+ .color = percent_hitm_color,
+ .width = 7,
+};
+
+static struct c2c_dimension dim_percent_rmt_hitm = {
+ .header = HEADER_SPAN("----- HITM -----", "Rmt", 1),
+ .name = "percent_rmt_hitm",
+ .cmp = percent_rmt_hitm_cmp,
+ .entry = percent_rmt_hitm_entry,
+ .color = percent_rmt_hitm_color,
+ .width = 7,
+};
+
+static struct c2c_dimension dim_percent_lcl_hitm = {
+ .header = HEADER_SPAN_LOW("Lcl"),
+ .name = "percent_lcl_hitm",
+ .cmp = percent_lcl_hitm_cmp,
+ .entry = percent_lcl_hitm_entry,
+ .color = percent_lcl_hitm_color,
+ .width = 7,
+};
+
+static struct c2c_dimension dim_percent_stores_l1hit = {
+ .header = HEADER_SPAN("-- Store Refs --", "L1 Hit", 1),
+ .name = "percent_stores_l1hit",
+ .cmp = percent_stores_l1hit_cmp,
+ .entry = percent_stores_l1hit_entry,
+ .color = percent_stores_l1hit_color,
+ .width = 7,
+};
+
+static struct c2c_dimension dim_percent_stores_l1miss = {
+ .header = HEADER_SPAN_LOW("L1 Miss"),
+ .name = "percent_stores_l1miss",
+ .cmp = percent_stores_l1miss_cmp,
+ .entry = percent_stores_l1miss_entry,
+ .color = percent_stores_l1miss_color,
+ .width = 7,
+};
+
+static struct c2c_dimension dim_dram_lcl = {
+ .header = HEADER_SPAN("--- Load Dram ----", "Lcl", 1),
+ .name = "dram_lcl",
+ .cmp = lcl_dram_cmp,
+ .entry = lcl_dram_entry,
+ .width = 8,
+};
+
+static struct c2c_dimension dim_dram_rmt = {
+ .header = HEADER_SPAN_LOW("Rmt"),
+ .name = "dram_rmt",
+ .cmp = rmt_dram_cmp,
+ .entry = rmt_dram_entry,
+ .width = 8,
+};
+
+static struct c2c_dimension dim_pid = {
+ .header = HEADER_LOW("Pid"),
+ .name = "pid",
+ .cmp = pid_cmp,
+ .entry = pid_entry,
+ .width = 7,
+};
+
+static struct c2c_dimension dim_tid = {
+ .header = HEADER_LOW("Tid"),
+ .name = "tid",
+ .se = &sort_thread,
+};
+
+static struct c2c_dimension dim_symbol = {
+ .name = "symbol",
+ .se = &sort_sym,
+};
+
+static struct c2c_dimension dim_dso = {
+ .header = HEADER_BOTH("Shared", "Object"),
+ .name = "dso",
+ .se = &sort_dso,
+};
+
+static struct c2c_header header_node[3] = {
+ HEADER_LOW("Node"),
+ HEADER_LOW("Node{cpus %hitms %stores}"),
+ HEADER_LOW("Node{cpu list}"),
+};
+
+static struct c2c_dimension dim_node = {
+ .name = "node",
+ .cmp = empty_cmp,
+ .entry = node_entry,
+ .width = 4,
+};
+
+static struct c2c_dimension dim_mean_rmt = {
+ .header = HEADER_SPAN("---------- cycles ----------", "rmt hitm", 2),
+ .name = "mean_rmt",
+ .cmp = empty_cmp,
+ .entry = mean_rmt_entry,
+ .width = 8,
+};
+
+static struct c2c_dimension dim_mean_lcl = {
+ .header = HEADER_SPAN_LOW("lcl hitm"),
+ .name = "mean_lcl",
+ .cmp = empty_cmp,
+ .entry = mean_lcl_entry,
+ .width = 8,
+};
+
+static struct c2c_dimension dim_mean_load = {
+ .header = HEADER_SPAN_LOW("load"),
+ .name = "mean_load",
+ .cmp = empty_cmp,
+ .entry = mean_load_entry,
+ .width = 8,
+};
+
+static struct c2c_dimension dim_cpucnt = {
+ .header = HEADER_BOTH("cpu", "cnt"),
+ .name = "cpucnt",
+ .cmp = empty_cmp,
+ .entry = cpucnt_entry,
+ .width = 8,
+};
+
+static struct c2c_dimension dim_srcline = {
+ .name = "cl_srcline",
+ .se = &sort_srcline,
+};
+
+static struct c2c_dimension dim_dcacheline_idx = {
+ .header = HEADER_LOW("Index"),
+ .name = "cl_idx",
+ .cmp = empty_cmp,
+ .entry = cl_idx_entry,
+ .width = 5,
+};
+
+static struct c2c_dimension dim_dcacheline_num = {
+ .header = HEADER_LOW("Num"),
+ .name = "cl_num",
+ .cmp = empty_cmp,
+ .entry = cl_idx_entry,
+ .width = 5,
+};
+
+static struct c2c_dimension dim_dcacheline_num_empty = {
+ .header = HEADER_LOW("Num"),
+ .name = "cl_num_empty",
+ .cmp = empty_cmp,
+ .entry = cl_idx_empty_entry,
+ .width = 5,
+};
+
+static struct c2c_dimension *dimensions[] = {
+ &dim_dcacheline,
+ &dim_offset,
+ &dim_iaddr,
+ &dim_tot_hitm,
+ &dim_lcl_hitm,
+ &dim_rmt_hitm,
+ &dim_cl_lcl_hitm,
+ &dim_cl_rmt_hitm,
+ &dim_stores,
+ &dim_stores_l1hit,
+ &dim_stores_l1miss,
+ &dim_cl_stores_l1hit,
+ &dim_cl_stores_l1miss,
+ &dim_ld_fbhit,
+ &dim_ld_l1hit,
+ &dim_ld_l2hit,
+ &dim_ld_llchit,
+ &dim_ld_rmthit,
+ &dim_ld_llcmiss,
+ &dim_tot_recs,
+ &dim_tot_loads,
+ &dim_percent_hitm,
+ &dim_percent_rmt_hitm,
+ &dim_percent_lcl_hitm,
+ &dim_percent_stores_l1hit,
+ &dim_percent_stores_l1miss,
+ &dim_dram_lcl,
+ &dim_dram_rmt,
+ &dim_pid,
+ &dim_tid,
+ &dim_symbol,
+ &dim_dso,
+ &dim_node,
+ &dim_mean_rmt,
+ &dim_mean_lcl,
+ &dim_mean_load,
+ &dim_cpucnt,
+ &dim_srcline,
+ &dim_dcacheline_idx,
+ &dim_dcacheline_num,
+ &dim_dcacheline_num_empty,
+ NULL,
+};
+
+static void fmt_free(struct perf_hpp_fmt *fmt)
+{
+ struct c2c_fmt *c2c_fmt;
+
+ c2c_fmt = container_of(fmt, struct c2c_fmt, fmt);
+ free(c2c_fmt);
+}
+
+static bool fmt_equal(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b)
+{
+ struct c2c_fmt *c2c_a = container_of(a, struct c2c_fmt, fmt);
+ struct c2c_fmt *c2c_b = container_of(b, struct c2c_fmt, fmt);
+
+ return c2c_a->dim == c2c_b->dim;
+}
+
+static struct c2c_dimension *get_dimension(const char *name)
+{
+ unsigned int i;
+
+ for (i = 0; dimensions[i]; i++) {
+ struct c2c_dimension *dim = dimensions[i];
+
+ if (!strcmp(dim->name, name))
+ return dim;
+ };
+
+ return NULL;
+}
+
+static int c2c_se_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+ struct hist_entry *he)
+{
+ struct c2c_fmt *c2c_fmt = container_of(fmt, struct c2c_fmt, fmt);
+ struct c2c_dimension *dim = c2c_fmt->dim;
+ size_t len = fmt->user_len;
+
+ if (!len) {
+ len = hists__col_len(he->hists, dim->se->se_width_idx);
+
+ if (dim == &dim_symbol || dim == &dim_srcline)
+ len = symbol_width(he->hists, dim->se);
+ }
+
+ return dim->se->se_snprintf(he, hpp->buf, hpp->size, len);
+}
+
+static int64_t c2c_se_cmp(struct perf_hpp_fmt *fmt,
+ struct hist_entry *a, struct hist_entry *b)
+{
+ struct c2c_fmt *c2c_fmt = container_of(fmt, struct c2c_fmt, fmt);
+ struct c2c_dimension *dim = c2c_fmt->dim;
+
+ return dim->se->se_cmp(a, b);
+}
+
+static int64_t c2c_se_collapse(struct perf_hpp_fmt *fmt,
+ struct hist_entry *a, struct hist_entry *b)
+{
+ struct c2c_fmt *c2c_fmt = container_of(fmt, struct c2c_fmt, fmt);
+ struct c2c_dimension *dim = c2c_fmt->dim;
+ int64_t (*collapse_fn)(struct hist_entry *, struct hist_entry *);
+
+ collapse_fn = dim->se->se_collapse ?: dim->se->se_cmp;
+ return collapse_fn(a, b);
+}
+
+static struct c2c_fmt *get_format(const char *name)
+{
+ struct c2c_dimension *dim = get_dimension(name);
+ struct c2c_fmt *c2c_fmt;
+ struct perf_hpp_fmt *fmt;
+
+ if (!dim)
+ return NULL;
+
+ c2c_fmt = zalloc(sizeof(*c2c_fmt));
+ if (!c2c_fmt)
+ return NULL;
+
+ c2c_fmt->dim = dim;
+
+ fmt = &c2c_fmt->fmt;
+ INIT_LIST_HEAD(&fmt->list);
+ INIT_LIST_HEAD(&fmt->sort_list);
+
+ fmt->cmp = dim->se ? c2c_se_cmp : dim->cmp;
+ fmt->sort = dim->se ? c2c_se_cmp : dim->cmp;
+ fmt->color = dim->se ? NULL : dim->color;
+ fmt->entry = dim->se ? c2c_se_entry : dim->entry;
+ fmt->header = c2c_header;
+ fmt->width = c2c_width;
+ fmt->collapse = dim->se ? c2c_se_collapse : dim->cmp;
+ fmt->equal = fmt_equal;
+ fmt->free = fmt_free;
+
+ return c2c_fmt;
+}
+
+static int c2c_hists__init_output(struct perf_hpp_list *hpp_list, char *name)
+{
+ struct c2c_fmt *c2c_fmt = get_format(name);
+
+ if (!c2c_fmt) {
+ reset_dimensions();
+ return output_field_add(hpp_list, name);
+ }
+
+ perf_hpp_list__column_register(hpp_list, &c2c_fmt->fmt);
+ return 0;
+}
+
+static int c2c_hists__init_sort(struct perf_hpp_list *hpp_list, char *name)
+{
+ struct c2c_fmt *c2c_fmt = get_format(name);
+ struct c2c_dimension *dim;
+
+ if (!c2c_fmt) {
+ reset_dimensions();
+ return sort_dimension__add(hpp_list, name, NULL, 0);
+ }
+
+ dim = c2c_fmt->dim;
+ if (dim == &dim_dso)
+ hpp_list->dso = 1;
+
+ perf_hpp_list__register_sort_field(hpp_list, &c2c_fmt->fmt);
+ return 0;
+}
+
+#define PARSE_LIST(_list, _fn) \
+ do { \
+ char *tmp, *tok; \
+ ret = 0; \
+ \
+ if (!_list) \
+ break; \
+ \
+ for (tok = strtok_r((char *)_list, ", ", &tmp); \
+ tok; tok = strtok_r(NULL, ", ", &tmp)) { \
+ ret = _fn(hpp_list, tok); \
+ if (ret == -EINVAL) { \
+ error("Invalid --fields key: `%s'", tok); \
+ break; \
+ } else if (ret == -ESRCH) { \
+ error("Unknown --fields key: `%s'", tok); \
+ break; \
+ } \
+ } \
+ } while (0)
+
+static int hpp_list__parse(struct perf_hpp_list *hpp_list,
+ const char *output_,
+ const char *sort_)
+{
+ char *output = output_ ? strdup(output_) : NULL;
+ char *sort = sort_ ? strdup(sort_) : NULL;
+ int ret;
+
+ PARSE_LIST(output, c2c_hists__init_output);
+ PARSE_LIST(sort, c2c_hists__init_sort);
+
+ /* copy sort keys to output fields */
+ perf_hpp__setup_output_field(hpp_list);
+
+ /*
+ * We dont need other sorting keys other than those
+ * we already specified. It also really slows down
+ * the processing a lot with big number of output
+ * fields, so switching this off for c2c.
+ */
+
+#if 0
+ /* and then copy output fields to sort keys */
+ perf_hpp__append_sort_keys(&hists->list);
+#endif
+
+ free(output);
+ free(sort);
+ return ret;
+}
+
+static int c2c_hists__init(struct c2c_hists *hists,
+ const char *sort,
+ int nr_header_lines)
+{
+ __hists__init(&hists->hists, &hists->list);
+
+ /*
+ * Initialize only with sort fields, we need to resort
+ * later anyway, and that's where we add output fields
+ * as well.
+ */
+ perf_hpp_list__init(&hists->list);
+
+ /* Overload number of header lines.*/
+ hists->list.nr_header_lines = nr_header_lines;
+
+ return hpp_list__parse(&hists->list, NULL, sort);
+}
+
+static int c2c_hists__reinit(struct c2c_hists *c2c_hists,
+ const char *output,
+ const char *sort)
+{
+ perf_hpp__reset_output_field(&c2c_hists->list);
+ return hpp_list__parse(&c2c_hists->list, output, sort);
+}
+
+#define DISPLAY_LINE_LIMIT 0.0005
+
+static bool he__display(struct hist_entry *he, struct c2c_stats *stats)
+{
+ struct c2c_hist_entry *c2c_he;
+ double ld_dist;
+
+ if (c2c.show_all)
+ return true;
+
+ c2c_he = container_of(he, struct c2c_hist_entry, he);
+
+#define FILTER_HITM(__h) \
+ if (stats->__h) { \
+ ld_dist = ((double)c2c_he->stats.__h / stats->__h); \
+ if (ld_dist < DISPLAY_LINE_LIMIT) \
+ he->filtered = HIST_FILTER__C2C; \
+ } else { \
+ he->filtered = HIST_FILTER__C2C; \
+ }
+
+ switch (c2c.display) {
+ case DISPLAY_LCL:
+ FILTER_HITM(lcl_hitm);
+ break;
+ case DISPLAY_RMT:
+ FILTER_HITM(rmt_hitm);
+ break;
+ case DISPLAY_TOT:
+ FILTER_HITM(tot_hitm);
+ default:
+ break;
+ };
+
+#undef FILTER_HITM
+
+ return he->filtered == 0;
+}
+
+static inline int valid_hitm_or_store(struct hist_entry *he)
+{
+ struct c2c_hist_entry *c2c_he;
+ bool has_hitm;
+
+ c2c_he = container_of(he, struct c2c_hist_entry, he);
+ has_hitm = c2c.display == DISPLAY_TOT ? c2c_he->stats.tot_hitm :
+ c2c.display == DISPLAY_LCL ? c2c_he->stats.lcl_hitm :
+ c2c_he->stats.rmt_hitm;
+ return has_hitm || c2c_he->stats.store;
+}
+
+static void calc_width(struct hist_entry *he)
+{
+ struct c2c_hists *c2c_hists;
+
+ c2c_hists = container_of(he->hists, struct c2c_hists, hists);
+ hists__calc_col_len(&c2c_hists->hists, he);
+}
+
+static int filter_cb(struct hist_entry *he)
+{
+ if (c2c.show_src && !he->srcline)
+ he->srcline = hist_entry__get_srcline(he);
+
+ calc_width(he);
+
+ if (!valid_hitm_or_store(he))
+ he->filtered = HIST_FILTER__C2C;
+
+ return 0;
+}
+
+static int resort_cl_cb(struct hist_entry *he)
+{
+ struct c2c_hist_entry *c2c_he;
+ struct c2c_hists *c2c_hists;
+ bool display = he__display(he, &c2c.hitm_stats);
+
+ c2c_he = container_of(he, struct c2c_hist_entry, he);
+ c2c_hists = c2c_he->hists;
+
+ calc_width(he);
+
+ if (display && c2c_hists) {
+ static unsigned int idx;
+
+ c2c_he->cacheline_idx = idx++;
+
+ c2c_hists__reinit(c2c_hists, c2c.cl_output, c2c.cl_resort);
+
+ hists__collapse_resort(&c2c_hists->hists, NULL);
+ hists__output_resort_cb(&c2c_hists->hists, NULL, filter_cb);
+ }
+
+ return 0;
+}
+
+static void setup_nodes_header(void)
+{
+ dim_node.header = header_node[c2c.node_info];
+}
+
+static int setup_nodes(struct perf_session *session)
+{
+ struct numa_node *n;
+ unsigned long **nodes;
+ int node, cpu;
+ int *cpu2node;
+
+ if (c2c.node_info > 2)
+ c2c.node_info = 2;
+
+ c2c.nodes_cnt = session->header.env.nr_numa_nodes;
+ c2c.cpus_cnt = session->header.env.nr_cpus_online;
+
+ n = session->header.env.numa_nodes;
+ if (!n)
+ return -EINVAL;
+
+ nodes = zalloc(sizeof(unsigned long *) * c2c.nodes_cnt);
+ if (!nodes)
+ return -ENOMEM;
+
+ c2c.nodes = nodes;
+
+ cpu2node = zalloc(sizeof(int) * c2c.cpus_cnt);
+ if (!cpu2node)
+ return -ENOMEM;
+
+ for (cpu = 0; cpu < c2c.cpus_cnt; cpu++)
+ cpu2node[cpu] = -1;
+
+ c2c.cpu2node = cpu2node;
+
+ for (node = 0; node < c2c.nodes_cnt; node++) {
+ struct cpu_map *map = n[node].map;
+ unsigned long *set;
+
+ set = bitmap_alloc(c2c.cpus_cnt);
+ if (!set)
+ return -ENOMEM;
+
+ for (cpu = 0; cpu < map->nr; cpu++) {
+ set_bit(map->map[cpu], set);
+
+ if (WARN_ONCE(cpu2node[map->map[cpu]] != -1, "node/cpu topology bug"))
+ return -EINVAL;
+
+ cpu2node[map->map[cpu]] = node;
+ }
+
+ nodes[node] = set;
+ }
+
+ setup_nodes_header();
+ return 0;
+}
+
+#define HAS_HITMS(__h) ((__h)->stats.lcl_hitm || (__h)->stats.rmt_hitm)
+
+static int resort_hitm_cb(struct hist_entry *he)
+{
+ struct c2c_hist_entry *c2c_he;
+ c2c_he = container_of(he, struct c2c_hist_entry, he);
+
+ if (HAS_HITMS(c2c_he)) {
+ c2c.shared_clines++;
+ c2c_add_stats(&c2c.hitm_stats, &c2c_he->stats);
+ }
+
+ return 0;
+}
+
+static int hists__iterate_cb(struct hists *hists, hists__resort_cb_t cb)
+{
+ struct rb_node *next = rb_first(&hists->entries);
+ int ret = 0;
+
+ while (next) {
+ struct hist_entry *he;
+
+ he = rb_entry(next, struct hist_entry, rb_node);
+ ret = cb(he);
+ if (ret)
+ break;
+ next = rb_next(&he->rb_node);
+ }
+
+ return ret;
+}
+
+static void print_c2c__display_stats(FILE *out)
+{
+ int llc_misses;
+ struct c2c_stats *stats = &c2c.hists.stats;
+
+ llc_misses = stats->lcl_dram +
+ stats->rmt_dram +
+ stats->rmt_hit +
+ stats->rmt_hitm;
+
+ fprintf(out, "=================================================\n");
+ fprintf(out, " Trace Event Information \n");
+ fprintf(out, "=================================================\n");
+ fprintf(out, " Total records : %10d\n", stats->nr_entries);
+ fprintf(out, " Locked Load/Store Operations : %10d\n", stats->locks);
+ fprintf(out, " Load Operations : %10d\n", stats->load);
+ fprintf(out, " Loads - uncacheable : %10d\n", stats->ld_uncache);
+ fprintf(out, " Loads - IO : %10d\n", stats->ld_io);
+ fprintf(out, " Loads - Miss : %10d\n", stats->ld_miss);
+ fprintf(out, " Loads - no mapping : %10d\n", stats->ld_noadrs);
+ fprintf(out, " Load Fill Buffer Hit : %10d\n", stats->ld_fbhit);
+ fprintf(out, " Load L1D hit : %10d\n", stats->ld_l1hit);
+ fprintf(out, " Load L2D hit : %10d\n", stats->ld_l2hit);
+ fprintf(out, " Load LLC hit : %10d\n", stats->ld_llchit + stats->lcl_hitm);
+ fprintf(out, " Load Local HITM : %10d\n", stats->lcl_hitm);
+ fprintf(out, " Load Remote HITM : %10d\n", stats->rmt_hitm);
+ fprintf(out, " Load Remote HIT : %10d\n", stats->rmt_hit);
+ fprintf(out, " Load Local DRAM : %10d\n", stats->lcl_dram);
+ fprintf(out, " Load Remote DRAM : %10d\n", stats->rmt_dram);
+ fprintf(out, " Load MESI State Exclusive : %10d\n", stats->ld_excl);
+ fprintf(out, " Load MESI State Shared : %10d\n", stats->ld_shared);
+ fprintf(out, " Load LLC Misses : %10d\n", llc_misses);
+ fprintf(out, " LLC Misses to Local DRAM : %10.1f%%\n", ((double)stats->lcl_dram/(double)llc_misses) * 100.);
+ fprintf(out, " LLC Misses to Remote DRAM : %10.1f%%\n", ((double)stats->rmt_dram/(double)llc_misses) * 100.);
+ fprintf(out, " LLC Misses to Remote cache (HIT) : %10.1f%%\n", ((double)stats->rmt_hit /(double)llc_misses) * 100.);
+ fprintf(out, " LLC Misses to Remote cache (HITM) : %10.1f%%\n", ((double)stats->rmt_hitm/(double)llc_misses) * 100.);
+ fprintf(out, " Store Operations : %10d\n", stats->store);
+ fprintf(out, " Store - uncacheable : %10d\n", stats->st_uncache);
+ fprintf(out, " Store - no mapping : %10d\n", stats->st_noadrs);
+ fprintf(out, " Store L1D Hit : %10d\n", stats->st_l1hit);
+ fprintf(out, " Store L1D Miss : %10d\n", stats->st_l1miss);
+ fprintf(out, " No Page Map Rejects : %10d\n", stats->nomap);
+ fprintf(out, " Unable to parse data source : %10d\n", stats->noparse);
+}
+
+static void print_shared_cacheline_info(FILE *out)
+{
+ struct c2c_stats *stats = &c2c.hitm_stats;
+ int hitm_cnt = stats->lcl_hitm + stats->rmt_hitm;
+
+ fprintf(out, "=================================================\n");
+ fprintf(out, " Global Shared Cache Line Event Information \n");
+ fprintf(out, "=================================================\n");
+ fprintf(out, " Total Shared Cache Lines : %10d\n", c2c.shared_clines);
+ fprintf(out, " Load HITs on shared lines : %10d\n", stats->load);
+ fprintf(out, " Fill Buffer Hits on shared lines : %10d\n", stats->ld_fbhit);
+ fprintf(out, " L1D hits on shared lines : %10d\n", stats->ld_l1hit);
+ fprintf(out, " L2D hits on shared lines : %10d\n", stats->ld_l2hit);
+ fprintf(out, " LLC hits on shared lines : %10d\n", stats->ld_llchit + stats->lcl_hitm);
+ fprintf(out, " Locked Access on shared lines : %10d\n", stats->locks);
+ fprintf(out, " Store HITs on shared lines : %10d\n", stats->store);
+ fprintf(out, " Store L1D hits on shared lines : %10d\n", stats->st_l1hit);
+ fprintf(out, " Total Merged records : %10d\n", hitm_cnt + stats->store);
+}
+
+static void print_cacheline(struct c2c_hists *c2c_hists,
+ struct hist_entry *he_cl,
+ struct perf_hpp_list *hpp_list,
+ FILE *out)
+{
+ char bf[1000];
+ struct perf_hpp hpp = {
+ .buf = bf,
+ .size = 1000,
+ };
+ static bool once;
+
+ if (!once) {
+ hists__fprintf_headers(&c2c_hists->hists, out);
+ once = true;
+ } else {
+ fprintf(out, "\n");
+ }
+
+ fprintf(out, " -------------------------------------------------------------\n");
+ __hist_entry__snprintf(he_cl, &hpp, hpp_list);
+ fprintf(out, "%s\n", bf);
+ fprintf(out, " -------------------------------------------------------------\n");
+
+ hists__fprintf(&c2c_hists->hists, false, 0, 0, 0, out, true);
+}
+
+static void print_pareto(FILE *out)
+{
+ struct perf_hpp_list hpp_list;
+ struct rb_node *nd;
+ int ret;
+
+ perf_hpp_list__init(&hpp_list);
+ ret = hpp_list__parse(&hpp_list,
+ "cl_num,"
+ "cl_rmt_hitm,"
+ "cl_lcl_hitm,"
+ "cl_stores_l1hit,"
+ "cl_stores_l1miss,"
+ "dcacheline",
+ NULL);
+
+ if (WARN_ONCE(ret, "failed to setup sort entries\n"))
+ return;
+
+ nd = rb_first(&c2c.hists.hists.entries);
+
+ for (; nd; nd = rb_next(nd)) {
+ struct hist_entry *he = rb_entry(nd, struct hist_entry, rb_node);
+ struct c2c_hist_entry *c2c_he;
+
+ if (he->filtered)
+ continue;
+
+ c2c_he = container_of(he, struct c2c_hist_entry, he);
+ print_cacheline(c2c_he->hists, he, &hpp_list, out);
+ }
+}
+
+static void print_c2c_info(FILE *out, struct perf_session *session)
+{
+ struct perf_evlist *evlist = session->evlist;
+ struct perf_evsel *evsel;
+ bool first = true;
+
+ fprintf(out, "=================================================\n");
+ fprintf(out, " c2c details \n");
+ fprintf(out, "=================================================\n");
+
+ evlist__for_each_entry(evlist, evsel) {
+ fprintf(out, "%-36s: %s\n", first ? " Events" : "",
+ perf_evsel__name(evsel));
+ first = false;
+ }
+ fprintf(out, " Cachelines sort on : %s HITMs\n",
+ display_str[c2c.display]);
+ fprintf(out, " Cacheline data grouping : %s\n", c2c.cl_sort);
+}
+
+static void perf_c2c__hists_fprintf(FILE *out, struct perf_session *session)
+{
+ setup_pager();
+
+ print_c2c__display_stats(out);
+ fprintf(out, "\n");
+ print_shared_cacheline_info(out);
+ fprintf(out, "\n");
+ print_c2c_info(out, session);
+
+ if (c2c.stats_only)
+ return;
+
+ fprintf(out, "\n");
+ fprintf(out, "=================================================\n");
+ fprintf(out, " Shared Data Cache Line Table \n");
+ fprintf(out, "=================================================\n");
+ fprintf(out, "#\n");
+
+ hists__fprintf(&c2c.hists.hists, true, 0, 0, 0, stdout, false);
+
+ fprintf(out, "\n");
+ fprintf(out, "=================================================\n");
+ fprintf(out, " Shared Cache Line Distribution Pareto \n");
+ fprintf(out, "=================================================\n");
+ fprintf(out, "#\n");
+
+ print_pareto(out);
+}
+
+#ifdef HAVE_SLANG_SUPPORT
+static void c2c_browser__update_nr_entries(struct hist_browser *hb)
+{
+ u64 nr_entries = 0;
+ struct rb_node *nd = rb_first(&hb->hists->entries);
+
+ while (nd) {
+ struct hist_entry *he = rb_entry(nd, struct hist_entry, rb_node);
+
+ if (!he->filtered)
+ nr_entries++;
+
+ nd = rb_next(nd);
+ }
+
+ hb->nr_non_filtered_entries = nr_entries;
+}
+
+struct c2c_cacheline_browser {
+ struct hist_browser hb;
+ struct hist_entry *he;
+};
+
+static int
+perf_c2c_cacheline_browser__title(struct hist_browser *browser,
+ char *bf, size_t size)
+{
+ struct c2c_cacheline_browser *cl_browser;
+ struct hist_entry *he;
+ uint64_t addr = 0;
+
+ cl_browser = container_of(browser, struct c2c_cacheline_browser, hb);
+ he = cl_browser->he;
+
+ if (he->mem_info)
+ addr = cl_address(he->mem_info->daddr.addr);
+
+ scnprintf(bf, size, "Cacheline 0x%lx", addr);
+ return 0;
+}
+
+static struct c2c_cacheline_browser*
+c2c_cacheline_browser__new(struct hists *hists, struct hist_entry *he)
+{
+ struct c2c_cacheline_browser *browser;
+
+ browser = zalloc(sizeof(*browser));
+ if (browser) {
+ hist_browser__init(&browser->hb, hists);
+ browser->hb.c2c_filter = true;
+ browser->hb.title = perf_c2c_cacheline_browser__title;
+ browser->he = he;
+ }
+
+ return browser;
+}
+
+static int perf_c2c__browse_cacheline(struct hist_entry *he)
+{
+ struct c2c_hist_entry *c2c_he;
+ struct c2c_hists *c2c_hists;
+ struct c2c_cacheline_browser *cl_browser;
+ struct hist_browser *browser;
+ int key = -1;
+ const char help[] =
+ " ENTER Togle callchains (if present) \n"
+ " n Togle Node details info \n"
+ " s Togle full lenght of symbol and source line columns \n"
+ " q Return back to cacheline list \n";
+
+ /* Display compact version first. */
+ c2c.symbol_full = false;
+
+ c2c_he = container_of(he, struct c2c_hist_entry, he);
+ c2c_hists = c2c_he->hists;
+
+ cl_browser = c2c_cacheline_browser__new(&c2c_hists->hists, he);
+ if (cl_browser == NULL)
+ return -1;
+
+ browser = &cl_browser->hb;
+
+ /* reset abort key so that it can get Ctrl-C as a key */
+ SLang_reset_tty();
+ SLang_init_tty(0, 0, 0);
+
+ c2c_browser__update_nr_entries(browser);
+
+ while (1) {
+ key = hist_browser__run(browser, "? - help");
+
+ switch (key) {
+ case 's':
+ c2c.symbol_full = !c2c.symbol_full;
+ break;
+ case 'n':
+ c2c.node_info = (c2c.node_info + 1) % 3;
+ setup_nodes_header();
+ break;
+ case 'q':
+ goto out;
+ case '?':
+ ui_browser__help_window(&browser->b, help);
+ break;
+ default:
+ break;
+ }
+ }
+
+out:
+ free(cl_browser);
+ return 0;
+}
+
+static int perf_c2c_browser__title(struct hist_browser *browser,
+ char *bf, size_t size)
+{
+ scnprintf(bf, size,
+ "Shared Data Cache Line Table "
+ "(%lu entries, sorted on %s HITMs)",
+ browser->nr_non_filtered_entries,
+ display_str[c2c.display]);
+ return 0;
+}
+
+static struct hist_browser*
+perf_c2c_browser__new(struct hists *hists)
+{
+ struct hist_browser *browser = hist_browser__new(hists);
+
+ if (browser) {
+ browser->title = perf_c2c_browser__title;
+ browser->c2c_filter = true;
+ }
+
+ return browser;
+}
+
+static int perf_c2c__hists_browse(struct hists *hists)
+{
+ struct hist_browser *browser;
+ int key = -1;
+ const char help[] =
+ " d Display cacheline details \n"
+ " ENTER Togle callchains (if present) \n"
+ " q Quit \n";
+
+ browser = perf_c2c_browser__new(hists);
+ if (browser == NULL)
+ return -1;
+
+ /* reset abort key so that it can get Ctrl-C as a key */
+ SLang_reset_tty();
+ SLang_init_tty(0, 0, 0);
+
+ c2c_browser__update_nr_entries(browser);
+
+ while (1) {
+ key = hist_browser__run(browser, "? - help");
+
+ switch (key) {
+ case 'q':
+ goto out;
+ case 'd':
+ perf_c2c__browse_cacheline(browser->he_selection);
+ break;
+ case '?':
+ ui_browser__help_window(&browser->b, help);
+ break;
+ default:
+ break;
+ }
+ }
+
+out:
+ hist_browser__delete(browser);
+ return 0;
+}
+
+static void perf_c2c_display(struct perf_session *session)
+{
+ if (c2c.use_stdio)
+ perf_c2c__hists_fprintf(stdout, session);
+ else
+ perf_c2c__hists_browse(&c2c.hists.hists);
+}
+#else
+static void perf_c2c_display(struct perf_session *session)
+{
+ use_browser = 0;
+ perf_c2c__hists_fprintf(stdout, session);
+}
+#endif /* HAVE_SLANG_SUPPORT */
+
+static void ui_quirks(void)
+{
+ if (!c2c.use_stdio) {
+ dim_offset.width = 5;
+ dim_offset.header = header_offset_tui;
+ }
+
+ dim_percent_hitm.header = percent_hitm_header[c2c.display];
+}
+
+#define CALLCHAIN_DEFAULT_OPT "graph,0.5,caller,function,percent"
+
+const char callchain_help[] = "Display call graph (stack chain/backtrace):\n\n"
+ CALLCHAIN_REPORT_HELP
+ "\n\t\t\t\tDefault: " CALLCHAIN_DEFAULT_OPT;
+
+static int
+parse_callchain_opt(const struct option *opt, const char *arg, int unset)
+{
+ struct callchain_param *callchain = opt->value;
+
+ callchain->enabled = !unset;
+ /*
+ * --no-call-graph
+ */
+ if (unset) {
+ symbol_conf.use_callchain = false;
+ callchain->mode = CHAIN_NONE;
+ return 0;
+ }
+
+ return parse_callchain_report_opt(arg);
+}
+
+static int setup_callchain(struct perf_evlist *evlist)
+{
+ u64 sample_type = perf_evlist__combined_sample_type(evlist);
+ enum perf_call_graph_mode mode = CALLCHAIN_NONE;
+
+ if ((sample_type & PERF_SAMPLE_REGS_USER) &&
+ (sample_type & PERF_SAMPLE_STACK_USER))
+ mode = CALLCHAIN_DWARF;
+ else if (sample_type & PERF_SAMPLE_BRANCH_STACK)
+ mode = CALLCHAIN_LBR;
+ else if (sample_type & PERF_SAMPLE_CALLCHAIN)
+ mode = CALLCHAIN_FP;
+
+ if (!callchain_param.enabled &&
+ callchain_param.mode != CHAIN_NONE &&
+ mode != CALLCHAIN_NONE) {
+ symbol_conf.use_callchain = true;
+ if (callchain_register_param(&callchain_param) < 0) {
+ ui__error("Can't register callchain params.\n");
+ return -EINVAL;
+ }
+ }
+
+ callchain_param.record_mode = mode;
+ callchain_param.min_percent = 0;
+ return 0;
+}
+
+static int setup_display(const char *str)
+{
+ const char *display = str ?: "tot";
+
+ if (!strcmp(display, "tot"))
+ c2c.display = DISPLAY_TOT;
+ else if (!strcmp(display, "rmt"))
+ c2c.display = DISPLAY_RMT;
+ else if (!strcmp(display, "lcl"))
+ c2c.display = DISPLAY_LCL;
+ else {
+ pr_err("failed: unknown display type: %s\n", str);
+ return -1;
+ }
+
+ return 0;
+}
+
+#define for_each_token(__tok, __buf, __sep, __tmp) \
+ for (__tok = strtok_r(__buf, __sep, &__tmp); __tok; \
+ __tok = strtok_r(NULL, __sep, &__tmp))
+
+static int build_cl_output(char *cl_sort, bool no_source)
+{
+ char *tok, *tmp, *buf = strdup(cl_sort);
+ bool add_pid = false;
+ bool add_tid = false;
+ bool add_iaddr = false;
+ bool add_sym = false;
+ bool add_dso = false;
+ bool add_src = false;
+
+ if (!buf)
+ return -ENOMEM;
+
+ for_each_token(tok, buf, ",", tmp) {
+ if (!strcmp(tok, "tid")) {
+ add_tid = true;
+ } else if (!strcmp(tok, "pid")) {
+ add_pid = true;
+ } else if (!strcmp(tok, "iaddr")) {
+ add_iaddr = true;
+ add_sym = true;
+ add_dso = true;
+ add_src = no_source ? false : true;
+ } else if (!strcmp(tok, "dso")) {
+ add_dso = true;
+ } else if (strcmp(tok, "offset")) {
+ pr_err("unrecognized sort token: %s\n", tok);
+ return -EINVAL;
+ }
+ }
+
+ if (asprintf(&c2c.cl_output,
+ "%s%s%s%s%s%s%s%s%s%s",
+ c2c.use_stdio ? "cl_num_empty," : "",
+ "percent_rmt_hitm,"
+ "percent_lcl_hitm,"
+ "percent_stores_l1hit,"
+ "percent_stores_l1miss,"
+ "offset,",
+ add_pid ? "pid," : "",
+ add_tid ? "tid," : "",
+ add_iaddr ? "iaddr," : "",
+ "mean_rmt,"
+ "mean_lcl,"
+ "mean_load,"
+ "tot_recs,"
+ "cpucnt,",
+ add_sym ? "symbol," : "",
+ add_dso ? "dso," : "",
+ add_src ? "cl_srcline," : "",
+ "node") < 0)
+ return -ENOMEM;
+
+ c2c.show_src = add_src;
+
+ free(buf);
+ return 0;
+}
+
+static int setup_coalesce(const char *coalesce, bool no_source)
+{
+ const char *c = coalesce ?: coalesce_default;
+
+ if (asprintf(&c2c.cl_sort, "offset,%s", c) < 0)
+ return -ENOMEM;
+
+ if (build_cl_output(c2c.cl_sort, no_source))
+ return -1;
+
+ if (asprintf(&c2c.cl_resort, "offset,%s",
+ c2c.display == DISPLAY_TOT ?
+ "tot_hitm" :
+ c2c.display == DISPLAY_RMT ?
+ "rmt_hitm,lcl_hitm" :
+ "lcl_hitm,rmt_hitm") < 0)
+ return -ENOMEM;
+
+ pr_debug("coalesce sort fields: %s\n", c2c.cl_sort);
+ pr_debug("coalesce resort fields: %s\n", c2c.cl_resort);
+ pr_debug("coalesce output fields: %s\n", c2c.cl_output);
+ return 0;
+}
+
+static int perf_c2c__report(int argc, const char **argv)
+{
+ struct perf_session *session;
+ struct ui_progress prog;
+ struct perf_data_file file = {
+ .mode = PERF_DATA_MODE_READ,
+ };
+ char callchain_default_opt[] = CALLCHAIN_DEFAULT_OPT;
+ const char *display = NULL;
+ const char *coalesce = NULL;
+ bool no_source = false;
+ const struct option options[] = {
+ OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name,
+ "file", "vmlinux pathname"),
+ OPT_STRING('i', "input", &input_name, "file",
+ "the input file to process"),
+ OPT_INCR('N', "node-info", &c2c.node_info,
+ "show extra node info in report (repeat for more info)"),
+#ifdef HAVE_SLANG_SUPPORT
+ OPT_BOOLEAN(0, "stdio", &c2c.use_stdio, "Use the stdio interface"),
+#endif
+ OPT_BOOLEAN(0, "stats", &c2c.stats_only,
+ "Use the stdio interface"),
+ OPT_BOOLEAN(0, "full-symbols", &c2c.symbol_full,
+ "Display full length of symbols"),
+ OPT_BOOLEAN(0, "no-source", &no_source,
+ "Do not display Source Line column"),
+ OPT_BOOLEAN(0, "show-all", &c2c.show_all,
+ "Show all captured HITM lines."),
+ OPT_CALLBACK_DEFAULT('g', "call-graph", &callchain_param,
+ "print_type,threshold[,print_limit],order,sort_key[,branch],value",
+ callchain_help, &parse_callchain_opt,
+ callchain_default_opt),
+ OPT_STRING('d', "display", &display, "Switch HITM output type", "lcl,rmt"),
+ OPT_STRING('c', "coalesce", &coalesce, "coalesce fields",
+ "coalesce fields: pid,tid,iaddr,dso"),
+ OPT_BOOLEAN('f', "force", &symbol_conf.force, "don't complain, do it"),
+ OPT_PARENT(c2c_options),
+ OPT_END()
+ };
+ int err = 0;
+
+ argc = parse_options(argc, argv, options, report_c2c_usage,
+ PARSE_OPT_STOP_AT_NON_OPTION);
+ if (argc)
+ usage_with_options(report_c2c_usage, options);
+
+ if (c2c.stats_only)
+ c2c.use_stdio = true;
+
+ if (!input_name || !strlen(input_name))
+ input_name = "perf.data";
+
+ file.path = input_name;
+ file.force = symbol_conf.force;
+
+ err = setup_display(display);
+ if (err)
+ goto out;
+
+ err = setup_coalesce(coalesce, no_source);
+ if (err) {
+ pr_debug("Failed to initialize hists\n");
+ goto out;
+ }
+
+ err = c2c_hists__init(&c2c.hists, "dcacheline", 2);
+ if (err) {
+ pr_debug("Failed to initialize hists\n");
+ goto out;
+ }
+
+ session = perf_session__new(&file, 0, &c2c.tool);
+ if (session == NULL) {
+ pr_debug("No memory for session\n");
+ goto out;
+ }
+
+ err = setup_nodes(session);
+ if (err) {
+ pr_err("Failed setup nodes\n");
+ goto out;
+ }
+
+ err = setup_callchain(session->evlist);
+ if (err)
+ goto out_session;
+
+ if (symbol__init(&session->header.env) < 0)
+ goto out_session;
+
+ /* No pipe support at the moment. */
+ if (perf_data_file__is_pipe(session->file)) {
+ pr_debug("No pipe support at the moment.\n");
+ goto out_session;
+ }
+
+ if (c2c.use_stdio)
+ use_browser = 0;
+ else
+ use_browser = 1;
+
+ setup_browser(false);
+
+ err = perf_session__process_events(session);
+ if (err) {
+ pr_err("failed to process sample\n");
+ goto out_session;
+ }
+
+ c2c_hists__reinit(&c2c.hists,
+ "cl_idx,"
+ "dcacheline,"
+ "tot_recs,"
+ "percent_hitm,"
+ "tot_hitm,lcl_hitm,rmt_hitm,"
+ "stores,stores_l1hit,stores_l1miss,"
+ "dram_lcl,dram_rmt,"
+ "ld_llcmiss,"
+ "tot_loads,"
+ "ld_fbhit,ld_l1hit,ld_l2hit,"
+ "ld_lclhit,ld_rmthit",
+ c2c.display == DISPLAY_TOT ? "tot_hitm" :
+ c2c.display == DISPLAY_LCL ? "lcl_hitm" : "rmt_hitm"
+ );
+
+ ui_progress__init(&prog, c2c.hists.hists.nr_entries, "Sorting...");
+
+ hists__collapse_resort(&c2c.hists.hists, NULL);
+ hists__output_resort_cb(&c2c.hists.hists, &prog, resort_hitm_cb);
+ hists__iterate_cb(&c2c.hists.hists, resort_cl_cb);
+
+ ui_progress__finish();
+
+ ui_quirks();
+
+ perf_c2c_display(session);
+
+out_session:
+ perf_session__delete(session);
+out:
+ return err;
+}
+
+static int parse_record_events(const struct option *opt,
+ const char *str, int unset __maybe_unused)
+{
+ bool *event_set = (bool *) opt->value;
+
+ *event_set = true;
+ return perf_mem_events__parse(str);
+}
+
+
+static const char * const __usage_record[] = {
+ "perf c2c record [<options>] [<command>]",
+ "perf c2c record [<options>] -- <command> [<options>]",
+ NULL
+};
+
+static const char * const *record_mem_usage = __usage_record;
+
+static int perf_c2c__record(int argc, const char **argv)
+{
+ int rec_argc, i = 0, j;
+ const char **rec_argv;
+ int ret;
+ bool all_user = false, all_kernel = false;
+ bool event_set = false;
+ struct option options[] = {
+ OPT_CALLBACK('e', "event", &event_set, "event",
+ "event selector. Use 'perf mem record -e list' to list available events",
+ parse_record_events),
+ OPT_BOOLEAN('u', "all-user", &all_user, "collect only user level data"),
+ OPT_BOOLEAN('k', "all-kernel", &all_kernel, "collect only kernel level data"),
+ OPT_UINTEGER('l', "ldlat", &perf_mem_events__loads_ldlat, "setup mem-loads latency"),
+ OPT_PARENT(c2c_options),
+ OPT_END()
+ };
+
+ if (perf_mem_events__init()) {
+ pr_err("failed: memory events not supported\n");
+ return -1;
+ }
+
+ argc = parse_options(argc, argv, options, record_mem_usage,
+ PARSE_OPT_KEEP_UNKNOWN);
+
+ rec_argc = argc + 10; /* max number of arguments */
+ rec_argv = calloc(rec_argc + 1, sizeof(char *));
+ if (!rec_argv)
+ return -1;
+
+ rec_argv[i++] = "record";
+
+ if (!event_set) {
+ perf_mem_events[PERF_MEM_EVENTS__LOAD].record = true;
+ perf_mem_events[PERF_MEM_EVENTS__STORE].record = true;
+ }
+
+ if (perf_mem_events[PERF_MEM_EVENTS__LOAD].record)
+ rec_argv[i++] = "-W";
+
+ rec_argv[i++] = "-d";
+ rec_argv[i++] = "--sample-cpu";
+
+ for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
+ if (!perf_mem_events[j].record)
+ continue;
+
+ if (!perf_mem_events[j].supported) {
+ pr_err("failed: event '%s' not supported\n",
+ perf_mem_events[j].name);
+ return -1;
+ }
+
+ rec_argv[i++] = "-e";
+ rec_argv[i++] = perf_mem_events__name(j);
+ };
+
+ if (all_user)
+ rec_argv[i++] = "--all-user";
+
+ if (all_kernel)
+ rec_argv[i++] = "--all-kernel";
+
+ for (j = 0; j < argc; j++, i++)
+ rec_argv[i] = argv[j];
+
+ if (verbose > 0) {
+ pr_debug("calling: ");
+
+ j = 0;
+
+ while (rec_argv[j]) {
+ pr_debug("%s ", rec_argv[j]);
+ j++;
+ }
+ pr_debug("\n");
+ }
+
+ ret = cmd_record(i, rec_argv, NULL);
+ free(rec_argv);
+ return ret;
+}
+
+int cmd_c2c(int argc, const char **argv, const char *prefix __maybe_unused)
+{
+ argc = parse_options(argc, argv, c2c_options, c2c_usage,
+ PARSE_OPT_STOP_AT_NON_OPTION);
+
+ if (!argc)
+ usage_with_options(c2c_usage, c2c_options);
+
+ if (!strncmp(argv[0], "rec", 3)) {
+ return perf_c2c__record(argc, argv);
+ } else if (!strncmp(argv[0], "rep", 3)) {
+ return perf_c2c__report(argc, argv);
+ } else {
+ usage_with_options(c2c_usage, c2c_options);
+ }
+
+ return 0;
+}
diff --git a/tools/perf/builtin-config.c b/tools/perf/builtin-config.c
index e4207a23b52c..8c0d93b7c2f0 100644
--- a/tools/perf/builtin-config.c
+++ b/tools/perf/builtin-config.c
@@ -17,7 +17,7 @@
static bool use_system_config, use_user_config;
static const char * const config_usage[] = {
- "perf config [<file-option>] [options]",
+ "perf config [<file-option>] [options] [section.name[=value] ...]",
NULL
};
@@ -33,6 +33,73 @@ static struct option config_options[] = {
OPT_END()
};
+static int set_config(struct perf_config_set *set, const char *file_name,
+ const char *var, const char *value)
+{
+ struct perf_config_section *section = NULL;
+ struct perf_config_item *item = NULL;
+ const char *first_line = "# this file is auto-generated.";
+ FILE *fp;
+
+ if (set == NULL)
+ return -1;
+
+ fp = fopen(file_name, "w");
+ if (!fp)
+ return -1;
+
+ perf_config_set__collect(set, file_name, var, value);
+ fprintf(fp, "%s\n", first_line);
+
+ /* overwrite configvariables */
+ perf_config_items__for_each_entry(&set->sections, section) {
+ if (!use_system_config && section->from_system_config)
+ continue;
+ fprintf(fp, "[%s]\n", section->name);
+
+ perf_config_items__for_each_entry(&section->items, item) {
+ if (!use_system_config && section->from_system_config)
+ continue;
+ if (item->value)
+ fprintf(fp, "\t%s = %s\n",
+ item->name, item->value);
+ }
+ }
+ fclose(fp);
+
+ return 0;
+}
+
+static int show_spec_config(struct perf_config_set *set, const char *var)
+{
+ struct perf_config_section *section;
+ struct perf_config_item *item;
+
+ if (set == NULL)
+ return -1;
+
+ perf_config_items__for_each_entry(&set->sections, section) {
+ if (prefixcmp(var, section->name) != 0)
+ continue;
+
+ perf_config_items__for_each_entry(&section->items, item) {
+ const char *name = var + strlen(section->name) + 1;
+
+ if (strcmp(name, item->name) == 0) {
+ char *value = item->value;
+
+ if (value) {
+ printf("%s=%s\n", var, value);
+ return 0;
+ }
+ }
+
+ }
+ }
+
+ return 0;
+}
+
static int show_config(struct perf_config_set *set)
{
struct perf_config_section *section;
@@ -52,9 +119,44 @@ static int show_config(struct perf_config_set *set)
return 0;
}
+static int parse_config_arg(char *arg, char **var, char **value)
+{
+ const char *last_dot = strchr(arg, '.');
+
+ /*
+ * Since "var" actually contains the section name and the real
+ * config variable name separated by a dot, we have to know where the dot is.
+ */
+ if (last_dot == NULL || last_dot == arg) {
+ pr_err("The config variable does not contain a section name: %s\n", arg);
+ return -1;
+ }
+ if (!last_dot[1]) {
+ pr_err("The config variable does not contain a variable name: %s\n", arg);
+ return -1;
+ }
+
+ *value = strchr(arg, '=');
+ if (*value == NULL)
+ *var = arg;
+ else if (!strcmp(*value, "=")) {
+ pr_err("The config variable does not contain a value: %s\n", arg);
+ return -1;
+ } else {
+ *value = *value + 1; /* excluding a first character '=' */
+ *var = strsep(&arg, "=");
+ if (*var[0] == '\0') {
+ pr_err("invalid config variable: %s\n", arg);
+ return -1;
+ }
+ }
+
+ return 0;
+}
+
int cmd_config(int argc, const char **argv, const char *prefix __maybe_unused)
{
- int ret = 0;
+ int i, ret = 0;
struct perf_config_set *set;
char *user_config = mkpath("%s/.perfconfig", getenv("HOME"));
@@ -100,7 +202,36 @@ int cmd_config(int argc, const char **argv, const char *prefix __maybe_unused)
}
break;
default:
- usage_with_options(config_usage, config_options);
+ if (argc) {
+ for (i = 0; argv[i]; i++) {
+ char *var, *value;
+ char *arg = strdup(argv[i]);
+
+ if (!arg) {
+ pr_err("%s: strdup failed\n", __func__);
+ ret = -1;
+ break;
+ }
+
+ if (parse_config_arg(arg, &var, &value) < 0) {
+ free(arg);
+ ret = -1;
+ break;
+ }
+
+ if (value == NULL)
+ ret = show_spec_config(set, var);
+ else {
+ const char *config_filename = config_exclusive_filename;
+
+ if (!config_exclusive_filename)
+ config_filename = user_config;
+ ret = set_config(set, config_filename, var, value);
+ }
+ free(arg);
+ }
+ } else
+ usage_with_options(config_usage, config_options);
}
perf_config_set__delete(set);
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 9ff0db4e2d0c..1b96a3122228 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -17,6 +17,7 @@
#include "util/symbol.h"
#include "util/util.h"
#include "util/data.h"
+#include "util/config.h"
#include <stdlib.h>
#include <math.h>
@@ -30,6 +31,7 @@ enum {
PERF_HPP_DIFF__RATIO,
PERF_HPP_DIFF__WEIGHTED_DIFF,
PERF_HPP_DIFF__FORMULA,
+ PERF_HPP_DIFF__DELTA_ABS,
PERF_HPP_DIFF__MAX_INDEX
};
@@ -64,7 +66,7 @@ static bool force;
static bool show_period;
static bool show_formula;
static bool show_baseline_only;
-static unsigned int sort_compute;
+static unsigned int sort_compute = 1;
static s64 compute_wdiff_w1;
static s64 compute_wdiff_w2;
@@ -73,19 +75,22 @@ enum {
COMPUTE_DELTA,
COMPUTE_RATIO,
COMPUTE_WEIGHTED_DIFF,
+ COMPUTE_DELTA_ABS,
COMPUTE_MAX,
};
const char *compute_names[COMPUTE_MAX] = {
[COMPUTE_DELTA] = "delta",
+ [COMPUTE_DELTA_ABS] = "delta-abs",
[COMPUTE_RATIO] = "ratio",
[COMPUTE_WEIGHTED_DIFF] = "wdiff",
};
-static int compute;
+static int compute = COMPUTE_DELTA_ABS;
static int compute_2_hpp[COMPUTE_MAX] = {
[COMPUTE_DELTA] = PERF_HPP_DIFF__DELTA,
+ [COMPUTE_DELTA_ABS] = PERF_HPP_DIFF__DELTA_ABS,
[COMPUTE_RATIO] = PERF_HPP_DIFF__RATIO,
[COMPUTE_WEIGHTED_DIFF] = PERF_HPP_DIFF__WEIGHTED_DIFF,
};
@@ -111,6 +116,10 @@ static struct header_column {
.name = "Delta",
.width = 7,
},
+ [PERF_HPP_DIFF__DELTA_ABS] = {
+ .name = "Delta Abs",
+ .width = 7,
+ },
[PERF_HPP_DIFF__RATIO] = {
.name = "Ratio",
.width = 14,
@@ -298,6 +307,7 @@ static int formula_fprintf(struct hist_entry *he, struct hist_entry *pair,
{
switch (compute) {
case COMPUTE_DELTA:
+ case COMPUTE_DELTA_ABS:
return formula_delta(he, pair, buf, size);
case COMPUTE_RATIO:
return formula_ratio(he, pair, buf, size);
@@ -461,6 +471,7 @@ static void hists__precompute(struct hists *hists)
switch (compute) {
case COMPUTE_DELTA:
+ case COMPUTE_DELTA_ABS:
compute_delta(he, pair);
break;
case COMPUTE_RATIO:
@@ -498,6 +509,13 @@ __hist_entry__cmp_compute(struct hist_entry *left, struct hist_entry *right,
return cmp_doubles(l, r);
}
+ case COMPUTE_DELTA_ABS:
+ {
+ double l = fabs(left->diff.period_ratio_delta);
+ double r = fabs(right->diff.period_ratio_delta);
+
+ return cmp_doubles(l, r);
+ }
case COMPUTE_RATIO:
{
double l = left->diff.period_ratio;
@@ -564,7 +582,7 @@ hist_entry__cmp_compute_idx(struct hist_entry *left, struct hist_entry *right,
if (!p_left || !p_right)
return p_left ? -1 : 1;
- if (c != COMPUTE_DELTA) {
+ if (c != COMPUTE_DELTA && c != COMPUTE_DELTA_ABS) {
/*
* The delta can be computed without the baseline, but
* others are not. Put those entries which have no
@@ -607,6 +625,15 @@ hist_entry__cmp_delta(struct perf_hpp_fmt *fmt,
}
static int64_t
+hist_entry__cmp_delta_abs(struct perf_hpp_fmt *fmt,
+ struct hist_entry *left, struct hist_entry *right)
+{
+ struct data__file *d = fmt_to_data_file(fmt);
+
+ return hist_entry__cmp_compute(right, left, COMPUTE_DELTA_ABS, d->idx);
+}
+
+static int64_t
hist_entry__cmp_ratio(struct perf_hpp_fmt *fmt,
struct hist_entry *left, struct hist_entry *right)
{
@@ -633,6 +660,14 @@ hist_entry__cmp_delta_idx(struct perf_hpp_fmt *fmt __maybe_unused,
}
static int64_t
+hist_entry__cmp_delta_abs_idx(struct perf_hpp_fmt *fmt __maybe_unused,
+ struct hist_entry *left, struct hist_entry *right)
+{
+ return hist_entry__cmp_compute_idx(right, left, COMPUTE_DELTA_ABS,
+ sort_compute);
+}
+
+static int64_t
hist_entry__cmp_ratio_idx(struct perf_hpp_fmt *fmt __maybe_unused,
struct hist_entry *left, struct hist_entry *right)
{
@@ -656,7 +691,7 @@ static void hists__process(struct hists *hists)
hists__precompute(hists);
hists__output_resort(hists, NULL);
- hists__fprintf(hists, true, 0, 0, 0, stdout,
+ hists__fprintf(hists, !quiet, 0, 0, 0, stdout,
symbol_conf.use_callchain);
}
@@ -704,12 +739,14 @@ static void data_process(void)
hists__link(hists_base, hists);
}
- fprintf(stdout, "%s# Event '%s'\n#\n", first ? "" : "\n",
- perf_evsel__name(evsel_base));
+ if (!quiet) {
+ fprintf(stdout, "%s# Event '%s'\n#\n", first ? "" : "\n",
+ perf_evsel__name(evsel_base));
+ }
first = false;
- if (verbose || data__files_cnt > 2)
+ if (verbose > 0 || ((data__files_cnt > 2) && !quiet))
data__fprintf();
/* Don't sort callchain for perf diff */
@@ -772,10 +809,11 @@ static const char * const diff_usage[] = {
static const struct option options[] = {
OPT_INCR('v', "verbose", &verbose,
"be more verbose (show symbol address, etc)"),
+ OPT_BOOLEAN('q', "quiet", &quiet, "Do not show any message"),
OPT_BOOLEAN('b', "baseline-only", &show_baseline_only,
"Show only items with match in baseline"),
OPT_CALLBACK('c', "compute", &compute,
- "delta,ratio,wdiff:w1,w2 (default delta)",
+ "delta,delta-abs,ratio,wdiff:w1,w2 (default delta-abs)",
"Entries differential computation selection",
setup_compute),
OPT_BOOLEAN('p', "period", &show_period,
@@ -945,6 +983,7 @@ hpp__entry_pair(struct hist_entry *he, struct hist_entry *pair,
switch (idx) {
case PERF_HPP_DIFF__DELTA:
+ case PERF_HPP_DIFF__DELTA_ABS:
if (pair->diff.computed)
diff = pair->diff.period_ratio_delta;
else
@@ -1118,6 +1157,10 @@ static void data__hpp_register(struct data__file *d, int idx)
fmt->color = hpp__color_wdiff;
fmt->sort = hist_entry__cmp_wdiff;
break;
+ case PERF_HPP_DIFF__DELTA_ABS:
+ fmt->color = hpp__color_delta;
+ fmt->sort = hist_entry__cmp_delta_abs;
+ break;
default:
fmt->sort = hist_entry__cmp_nop;
break;
@@ -1195,11 +1238,14 @@ static int ui_init(void)
case COMPUTE_WEIGHTED_DIFF:
fmt->sort = hist_entry__cmp_wdiff_idx;
break;
+ case COMPUTE_DELTA_ABS:
+ fmt->sort = hist_entry__cmp_delta_abs_idx;
+ break;
default:
BUG_ON(1);
}
- perf_hpp__register_sort_field(fmt);
+ perf_hpp__prepend_sort_field(fmt);
return 0;
}
@@ -1249,6 +1295,31 @@ static int data_init(int argc, const char **argv)
return 0;
}
+static int diff__config(const char *var, const char *value,
+ void *cb __maybe_unused)
+{
+ if (!strcmp(var, "diff.order")) {
+ sort_compute = perf_config_int(var, value);
+ return 0;
+ }
+ if (!strcmp(var, "diff.compute")) {
+ if (!strcmp(value, "delta")) {
+ compute = COMPUTE_DELTA;
+ } else if (!strcmp(value, "delta-abs")) {
+ compute = COMPUTE_DELTA_ABS;
+ } else if (!strcmp(value, "ratio")) {
+ compute = COMPUTE_RATIO;
+ } else if (!strcmp(value, "wdiff")) {
+ compute = COMPUTE_WEIGHTED_DIFF;
+ } else {
+ pr_err("Invalid compute method: %s\n", value);
+ return -1;
+ }
+ }
+
+ return 0;
+}
+
int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused)
{
int ret = hists__init();
@@ -1256,8 +1327,13 @@ int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused)
if (ret < 0)
return ret;
+ perf_config(diff__config, NULL);
+
argc = parse_options(argc, argv, options, diff_usage, 0);
+ if (quiet)
+ perf_quiet_option();
+
if (symbol__init(NULL) < 0)
return -1;
diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c
new file mode 100644
index 000000000000..c3e643666c72
--- /dev/null
+++ b/tools/perf/builtin-ftrace.c
@@ -0,0 +1,265 @@
+/*
+ * builtin-ftrace.c
+ *
+ * Copyright (c) 2013 LG Electronics, Namhyung Kim <namhyung@kernel.org>
+ *
+ * Released under the GPL v2.
+ */
+
+#include "builtin.h"
+#include "perf.h"
+
+#include <unistd.h>
+#include <signal.h>
+
+#include "debug.h"
+#include <subcmd/parse-options.h>
+#include "evlist.h"
+#include "target.h"
+#include "thread_map.h"
+#include "util/config.h"
+
+
+#define DEFAULT_TRACER "function_graph"
+
+struct perf_ftrace {
+ struct perf_evlist *evlist;
+ struct target target;
+ const char *tracer;
+};
+
+static bool done;
+
+static void sig_handler(int sig __maybe_unused)
+{
+ done = true;
+}
+
+/*
+ * perf_evlist__prepare_workload will send a SIGUSR1 if the fork fails, since
+ * we asked by setting its exec_error to the function below,
+ * ftrace__workload_exec_failed_signal.
+ *
+ * XXX We need to handle this more appropriately, emitting an error, etc.
+ */
+static void ftrace__workload_exec_failed_signal(int signo __maybe_unused,
+ siginfo_t *info __maybe_unused,
+ void *ucontext __maybe_unused)
+{
+ /* workload_exec_errno = info->si_value.sival_int; */
+ done = true;
+}
+
+static int write_tracing_file(const char *name, const char *val)
+{
+ char *file;
+ int fd, ret = -1;
+ ssize_t size = strlen(val);
+
+ file = get_tracing_file(name);
+ if (!file) {
+ pr_debug("cannot get tracing file: %s\n", name);
+ return -1;
+ }
+
+ fd = open(file, O_WRONLY);
+ if (fd < 0) {
+ pr_debug("cannot open tracing file: %s\n", name);
+ goto out;
+ }
+
+ if (write(fd, val, size) == size)
+ ret = 0;
+ else
+ pr_debug("write '%s' to tracing/%s failed\n", val, name);
+
+ close(fd);
+out:
+ put_tracing_file(file);
+ return ret;
+}
+
+static int reset_tracing_files(struct perf_ftrace *ftrace __maybe_unused)
+{
+ if (write_tracing_file("tracing_on", "0") < 0)
+ return -1;
+
+ if (write_tracing_file("current_tracer", "nop") < 0)
+ return -1;
+
+ if (write_tracing_file("set_ftrace_pid", " ") < 0)
+ return -1;
+
+ return 0;
+}
+
+static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv)
+{
+ char *trace_file;
+ int trace_fd;
+ char *trace_pid;
+ char buf[4096];
+ struct pollfd pollfd = {
+ .events = POLLIN,
+ };
+
+ if (geteuid() != 0) {
+ pr_err("ftrace only works for root!\n");
+ return -1;
+ }
+
+ if (argc < 1)
+ return -1;
+
+ signal(SIGINT, sig_handler);
+ signal(SIGUSR1, sig_handler);
+ signal(SIGCHLD, sig_handler);
+
+ reset_tracing_files(ftrace);
+
+ /* reset ftrace buffer */
+ if (write_tracing_file("trace", "0") < 0)
+ goto out;
+
+ if (perf_evlist__prepare_workload(ftrace->evlist, &ftrace->target,
+ argv, false, ftrace__workload_exec_failed_signal) < 0)
+ goto out;
+
+ if (write_tracing_file("current_tracer", ftrace->tracer) < 0) {
+ pr_err("failed to set current_tracer to %s\n", ftrace->tracer);
+ goto out;
+ }
+
+ if (asprintf(&trace_pid, "%d", thread_map__pid(ftrace->evlist->threads, 0)) < 0) {
+ pr_err("failed to allocate pid string\n");
+ goto out;
+ }
+
+ if (write_tracing_file("set_ftrace_pid", trace_pid) < 0) {
+ pr_err("failed to set pid: %s\n", trace_pid);
+ goto out_free_pid;
+ }
+
+ trace_file = get_tracing_file("trace_pipe");
+ if (!trace_file) {
+ pr_err("failed to open trace_pipe\n");
+ goto out_free_pid;
+ }
+
+ trace_fd = open(trace_file, O_RDONLY);
+
+ put_tracing_file(trace_file);
+
+ if (trace_fd < 0) {
+ pr_err("failed to open trace_pipe\n");
+ goto out_free_pid;
+ }
+
+ fcntl(trace_fd, F_SETFL, O_NONBLOCK);
+ pollfd.fd = trace_fd;
+
+ if (write_tracing_file("tracing_on", "1") < 0) {
+ pr_err("can't enable tracing\n");
+ goto out_close_fd;
+ }
+
+ perf_evlist__start_workload(ftrace->evlist);
+
+ while (!done) {
+ if (poll(&pollfd, 1, -1) < 0)
+ break;
+
+ if (pollfd.revents & POLLIN) {
+ int n = read(trace_fd, buf, sizeof(buf));
+ if (n < 0)
+ break;
+ if (fwrite(buf, n, 1, stdout) != 1)
+ break;
+ }
+ }
+
+ write_tracing_file("tracing_on", "0");
+
+ /* read remaining buffer contents */
+ while (true) {
+ int n = read(trace_fd, buf, sizeof(buf));
+ if (n <= 0)
+ break;
+ if (fwrite(buf, n, 1, stdout) != 1)
+ break;
+ }
+
+out_close_fd:
+ close(trace_fd);
+out_free_pid:
+ free(trace_pid);
+out:
+ reset_tracing_files(ftrace);
+
+ return done ? 0 : -1;
+}
+
+static int perf_ftrace_config(const char *var, const char *value, void *cb)
+{
+ struct perf_ftrace *ftrace = cb;
+
+ if (prefixcmp(var, "ftrace."))
+ return 0;
+
+ if (strcmp(var, "ftrace.tracer"))
+ return -1;
+
+ if (!strcmp(value, "function_graph") ||
+ !strcmp(value, "function")) {
+ ftrace->tracer = value;
+ return 0;
+ }
+
+ pr_err("Please select \"function_graph\" (default) or \"function\"\n");
+ return -1;
+}
+
+int cmd_ftrace(int argc, const char **argv, const char *prefix __maybe_unused)
+{
+ int ret;
+ struct perf_ftrace ftrace = {
+ .tracer = DEFAULT_TRACER,
+ .target = { .uid = UINT_MAX, },
+ };
+ const char * const ftrace_usage[] = {
+ "perf ftrace [<options>] <command>",
+ "perf ftrace [<options>] -- <command> [<options>]",
+ NULL
+ };
+ const struct option ftrace_options[] = {
+ OPT_STRING('t', "tracer", &ftrace.tracer, "tracer",
+ "tracer to use: function_graph(default) or function"),
+ OPT_INCR('v', "verbose", &verbose,
+ "be more verbose"),
+ OPT_END()
+ };
+
+ ret = perf_config(perf_ftrace_config, &ftrace);
+ if (ret < 0)
+ return -1;
+
+ argc = parse_options(argc, argv, ftrace_options, ftrace_usage,
+ PARSE_OPT_STOP_AT_NON_OPTION);
+ if (!argc)
+ usage_with_options(ftrace_usage, ftrace_options);
+
+ ftrace.evlist = perf_evlist__new();
+ if (ftrace.evlist == NULL)
+ return -ENOMEM;
+
+ ret = perf_evlist__create_maps(ftrace.evlist, &ftrace.target);
+ if (ret < 0)
+ goto out_delete_evlist;
+
+ ret = __cmd_ftrace(&ftrace, argc, argv);
+
+out_delete_evlist:
+ perf_evlist__delete(ftrace.evlist);
+
+ return ret;
+}
diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c
index 3bdb2c78a21b..aed0d844e8c2 100644
--- a/tools/perf/builtin-help.c
+++ b/tools/perf/builtin-help.c
@@ -434,7 +434,7 @@ int cmd_help(int argc, const char **argv, const char *prefix __maybe_unused)
const char * const builtin_help_subcommands[] = {
"buildid-cache", "buildid-list", "diff", "evlist", "help", "list",
"record", "report", "bench", "stat", "timechart", "top", "annotate",
- "script", "sched", "kmem", "lock", "kvm", "test", "inject", "mem", "data",
+ "script", "sched", "kallsyms", "kmem", "lock", "kvm", "test", "inject", "mem", "data",
#ifdef HAVE_LIBELF_SUPPORT
"probe",
#endif
@@ -447,11 +447,13 @@ int cmd_help(int argc, const char **argv, const char *prefix __maybe_unused)
NULL
};
const char *alias;
- int rc = 0;
+ int rc;
load_command_list("perf-", &main_cmds, &other_cmds);
- perf_config(perf_help_config, &help_format);
+ rc = perf_config(perf_help_config, &help_format);
+ if (rc)
+ return rc;
argc = parse_options_subcommand(argc, argv, builtin_help_options,
builtin_help_subcommands, builtin_help_usage, 0);
diff --git a/tools/perf/builtin-kallsyms.c b/tools/perf/builtin-kallsyms.c
new file mode 100644
index 000000000000..224bfc454b4a
--- /dev/null
+++ b/tools/perf/builtin-kallsyms.c
@@ -0,0 +1,67 @@
+/*
+ * builtin-kallsyms.c
+ *
+ * Builtin command: Look for a symbol in the running kernel and its modules
+ *
+ * Copyright (C) 2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ *
+ * Released under the GPL v2. (and only v2, not any later version)
+ */
+#include "builtin.h"
+#include <linux/compiler.h>
+#include <subcmd/parse-options.h>
+#include "debug.h"
+#include "machine.h"
+#include "symbol.h"
+
+static int __cmd_kallsyms(int argc, const char **argv)
+{
+ int i;
+ struct machine *machine = machine__new_kallsyms();
+
+ if (machine == NULL) {
+ pr_err("Couldn't read /proc/kallsyms\n");
+ return -1;
+ }
+
+ for (i = 0; i < argc; ++i) {
+ struct map *map;
+ struct symbol *symbol = machine__find_kernel_function_by_name(machine, argv[i], &map);
+
+ if (symbol == NULL) {
+ printf("%s: not found\n", argv[i]);
+ continue;
+ }
+
+ printf("%s: %s %s %#" PRIx64 "-%#" PRIx64 " (%#" PRIx64 "-%#" PRIx64")\n",
+ symbol->name, map->dso->short_name, map->dso->long_name,
+ map->unmap_ip(map, symbol->start), map->unmap_ip(map, symbol->end),
+ symbol->start, symbol->end);
+ }
+
+ machine__delete(machine);
+ return 0;
+}
+
+int cmd_kallsyms(int argc, const char **argv, const char *prefix __maybe_unused)
+{
+ const struct option options[] = {
+ OPT_INCR('v', "verbose", &verbose, "be more verbose (show counter open errors, etc)"),
+ OPT_END()
+ };
+ const char * const kallsyms_usage[] = {
+ "perf kallsyms [<options>] symbol_name",
+ NULL
+ };
+
+ argc = parse_options(argc, argv, options, kallsyms_usage, 0);
+ if (argc < 1)
+ usage_with_options(kallsyms_usage, options);
+
+ symbol_conf.sort_by_name = true;
+ symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL);
+ if (symbol__init(NULL) < 0)
+ return -1;
+
+ return __cmd_kallsyms(argc, argv);
+}
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index d426dcb18ce9..6da8d083e4e5 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -11,6 +11,7 @@
#include "util/session.h"
#include "util/tool.h"
#include "util/callchain.h"
+#include "util/time-utils.h"
#include <subcmd/parse-options.h>
#include "util/trace-event.h"
@@ -49,6 +50,7 @@ struct alloc_stat {
u64 ptr;
u64 bytes_req;
u64 bytes_alloc;
+ u64 last_alloc;
u32 hit;
u32 pingpong;
@@ -62,9 +64,13 @@ static struct rb_root root_alloc_sorted;
static struct rb_root root_caller_stat;
static struct rb_root root_caller_sorted;
-static unsigned long total_requested, total_allocated;
+static unsigned long total_requested, total_allocated, total_freed;
static unsigned long nr_allocs, nr_cross_allocs;
+/* filters for controlling start and stop of time of analysis */
+static struct perf_time_interval ptime;
+const char *time_str;
+
static int insert_alloc_stat(unsigned long call_site, unsigned long ptr,
int bytes_req, int bytes_alloc, int cpu)
{
@@ -105,6 +111,8 @@ static int insert_alloc_stat(unsigned long call_site, unsigned long ptr,
}
data->call_site = call_site;
data->alloc_cpu = cpu;
+ data->last_alloc = bytes_alloc;
+
return 0;
}
@@ -223,6 +231,8 @@ static int perf_evsel__process_free_event(struct perf_evsel *evsel,
if (!s_alloc)
return 0;
+ total_freed += s_alloc->last_alloc;
+
if ((short)sample->cpu != s_alloc->alloc_cpu) {
s_alloc->pingpong++;
@@ -645,7 +655,6 @@ static const struct {
{ "__GFP_RECLAIM", "R" },
{ "__GFP_DIRECT_RECLAIM", "DR" },
{ "__GFP_KSWAPD_RECLAIM", "KR" },
- { "__GFP_OTHER_NODE", "ON" },
};
static size_t max_gfp_len;
@@ -907,6 +916,15 @@ static int perf_evsel__process_page_free_event(struct perf_evsel *evsel,
return 0;
}
+static bool perf_kmem__skip_sample(struct perf_sample *sample)
+{
+ /* skip sample based on time? */
+ if (perf_time__skip_sample(&ptime, sample->time))
+ return true;
+
+ return false;
+}
+
typedef int (*tracepoint_handler)(struct perf_evsel *evsel,
struct perf_sample *sample);
@@ -926,6 +944,9 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
return -1;
}
+ if (perf_kmem__skip_sample(sample))
+ return 0;
+
dump_printf(" ... thread: %s:%d\n", thread__comm_str(thread), thread->tid);
if (evsel->handler != NULL) {
@@ -1044,7 +1065,7 @@ static void __print_page_alloc_result(struct perf_session *session, int n_lines)
data = rb_entry(next, struct page_stat, node);
sym = machine__find_kernel_function(machine, data->callsite, &map);
- if (sym && sym->name)
+ if (sym)
caller = sym->name;
else
scnprintf(buf, sizeof(buf), "%"PRIx64, data->callsite);
@@ -1086,7 +1107,7 @@ static void __print_page_caller_result(struct perf_session *session, int n_lines
data = rb_entry(next, struct page_stat, node);
sym = machine__find_kernel_function(machine, data->callsite, &map);
- if (sym && sym->name)
+ if (sym)
caller = sym->name;
else
scnprintf(buf, sizeof(buf), "%"PRIx64, data->callsite);
@@ -1128,6 +1149,11 @@ static void print_slab_summary(void)
printf("\n========================\n");
printf("Total bytes requested: %'lu\n", total_requested);
printf("Total bytes allocated: %'lu\n", total_allocated);
+ printf("Total bytes freed: %'lu\n", total_freed);
+ if (total_allocated > total_freed) {
+ printf("Net total bytes allocated: %'lu\n",
+ total_allocated - total_freed);
+ }
printf("Total bytes wasted on internal fragmentation: %'lu\n",
total_allocated - total_requested);
printf("Internal fragmentation: %f%%\n",
@@ -1884,6 +1910,8 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
OPT_CALLBACK_NOOPT(0, "page", NULL, NULL, "Analyze page allocator",
parse_page_opt),
OPT_BOOLEAN(0, "live", &live_page, "Show live page stat"),
+ OPT_STRING(0, "time", &time_str, "str",
+ "Time span of interest (start,stop)"),
OPT_END()
};
const char *const kmem_subcommands[] = { "record", "stat", NULL };
@@ -1892,10 +1920,12 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
NULL
};
struct perf_session *session;
- int ret = -1;
const char errmsg[] = "No %s allocation events found. Have you run 'perf kmem record --%s'?\n";
+ int ret = perf_config(kmem_config, NULL);
+
+ if (ret)
+ return ret;
- perf_config(kmem_config, NULL);
argc = parse_options_subcommand(argc, argv, kmem_options,
kmem_subcommands, kmem_usage, 0);
@@ -1920,6 +1950,8 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
if (session == NULL)
return -1;
+ ret = -1;
+
if (kmem_slab) {
if (!perf_evlist__find_tracepoint_by_name(session->evlist,
"kmem:kmalloc")) {
@@ -1944,6 +1976,11 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
symbol__init(&session->header.env);
+ if (perf_time__parse_str(&ptime, time_str) != 0) {
+ pr_err("Invalid time string\n");
+ return -EINVAL;
+ }
+
if (!strcmp(argv[0], "stat")) {
setlocale(LC_ALL, "");
diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c
index ba9322ff858b..3b9d98b5feef 100644
--- a/tools/perf/builtin-list.c
+++ b/tools/perf/builtin-list.c
@@ -14,6 +14,7 @@
#include "util/parse-events.h"
#include "util/cache.h"
#include "util/pmu.h"
+#include "util/debug.h"
#include <subcmd/parse-options.h>
static bool desc_flag = true;
@@ -29,6 +30,8 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
"Print extra event descriptions. --no-desc to not print."),
OPT_BOOLEAN('v', "long-desc", &long_desc_flag,
"Print longer event descriptions."),
+ OPT_INCR(0, "debug", &verbose,
+ "Enable debugging output"),
OPT_END()
};
const char * const list_usage[] = {
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index d1ce29be560e..6114e07ca613 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -42,8 +42,8 @@ static int parse_record_events(const struct option *opt,
fprintf(stderr, "%-13s%-*s%s\n",
e->tag,
- verbose ? 25 : 0,
- verbose ? perf_mem_events__name(j) : "",
+ verbose > 0 ? 25 : 0,
+ verbose > 0 ? perf_mem_events__name(j) : "",
e->supported ? ": available" : "");
}
exit(0);
@@ -70,8 +70,8 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
OPT_UINTEGER(0, "ldlat", &perf_mem_events__loads_ldlat, "mem-loads latency"),
OPT_INCR('v', "verbose", &verbose,
"be more verbose (show counter open errors, etc)"),
- OPT_BOOLEAN('U', "--all-user", &all_user, "collect only user level data"),
- OPT_BOOLEAN('K', "--all-kernel", &all_kernel, "collect only kernel level data"),
+ OPT_BOOLEAN('U', "all-user", &all_user, "collect only user level data"),
+ OPT_BOOLEAN('K', "all-kernel", &all_kernel, "collect only kernel level data"),
OPT_END()
};
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index f87996b0cb29..1fcebc31a508 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -552,6 +552,8 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel,
"Enable kernel symbol demangling"),
OPT_BOOLEAN(0, "cache", &probe_conf.cache, "Manipulate probe cache"),
+ OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
+ "Look for files with symbols relative to this directory"),
OPT_END()
};
int ret;
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 67d2a9003294..bc84a375295d 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -37,6 +37,7 @@
#include "util/llvm-utils.h"
#include "util/bpf-loader.h"
#include "util/trigger.h"
+#include "util/perf-hooks.h"
#include "asm/bug.h"
#include <unistd.h>
@@ -45,6 +46,15 @@
#include <asm/bug.h>
#include <linux/time64.h>
+struct switch_output {
+ bool enabled;
+ bool signal;
+ unsigned long size;
+ unsigned long time;
+ const char *str;
+ bool set;
+};
+
struct record {
struct perf_tool tool;
struct record_opts opts;
@@ -61,10 +71,33 @@ struct record {
bool no_buildid_cache_set;
bool buildid_all;
bool timestamp_filename;
- bool switch_output;
+ struct switch_output switch_output;
unsigned long long samples;
};
+static volatile int auxtrace_record__snapshot_started;
+static DEFINE_TRIGGER(auxtrace_snapshot_trigger);
+static DEFINE_TRIGGER(switch_output_trigger);
+
+static bool switch_output_signal(struct record *rec)
+{
+ return rec->switch_output.signal &&
+ trigger_is_ready(&switch_output_trigger);
+}
+
+static bool switch_output_size(struct record *rec)
+{
+ return rec->switch_output.size &&
+ trigger_is_ready(&switch_output_trigger) &&
+ (rec->bytes_written >= rec->switch_output.size);
+}
+
+static bool switch_output_time(struct record *rec)
+{
+ return rec->switch_output.time &&
+ trigger_is_ready(&switch_output_trigger);
+}
+
static int record__write(struct record *rec, void *bf, size_t size)
{
if (perf_data_file__write(rec->session->file, bf, size) < 0) {
@@ -73,6 +106,10 @@ static int record__write(struct record *rec, void *bf, size_t size)
}
rec->bytes_written += size;
+
+ if (switch_output_size(rec))
+ trigger_hit(&switch_output_trigger);
+
return 0;
}
@@ -192,10 +229,6 @@ static volatile int done;
static volatile int signr = -1;
static volatile int child_finished;
-static volatile int auxtrace_record__snapshot_started;
-static DEFINE_TRIGGER(auxtrace_snapshot_trigger);
-static DEFINE_TRIGGER(switch_output_trigger);
-
static void sig_handler(int sig)
{
if (sig == SIGCHLD)
@@ -206,6 +239,12 @@ static void sig_handler(int sig)
done = 1;
}
+static void sigsegv_handler(int sig)
+{
+ perf_hooks__recover();
+ sighandler_dump_stack(sig);
+}
+
static void record__sig_exit(void)
{
if (signr == -1)
@@ -379,7 +418,7 @@ static int record__mmap(struct record *rec)
static int record__open(struct record *rec)
{
- char msg[512];
+ char msg[BUFSIZ];
struct perf_evsel *pos;
struct perf_evlist *evlist = rec->evlist;
struct perf_session *session = rec->session;
@@ -393,7 +432,7 @@ static int record__open(struct record *rec)
try_again:
if (perf_evsel__open(pos, pos->cpus, pos->threads) < 0) {
if (perf_evsel__fallback(pos, errno, msg, sizeof(msg))) {
- if (verbose)
+ if (verbose > 0)
ui__warning("%s\n", msg);
goto try_again;
}
@@ -616,22 +655,23 @@ record__finish_output(struct record *rec)
static int record__synthesize_workload(struct record *rec, bool tail)
{
- struct {
- struct thread_map map;
- struct thread_map_data map_data;
- } thread_map;
+ int err;
+ struct thread_map *thread_map;
if (rec->opts.tail_synthesize != tail)
return 0;
- thread_map.map.nr = 1;
- thread_map.map.map[0].pid = rec->evlist->workload.pid;
- thread_map.map.map[0].comm = NULL;
- return perf_event__synthesize_thread_map(&rec->tool, &thread_map.map,
+ thread_map = thread_map__new_by_tid(rec->evlist->workload.pid);
+ if (thread_map == NULL)
+ return -1;
+
+ err = perf_event__synthesize_thread_map(&rec->tool, thread_map,
process_synthesized_event,
&rec->session->machines.host,
rec->opts.sample_address,
rec->opts.proc_map_timeout);
+ thread_map__put(thread_map);
+ return err;
}
static int record__synthesize(struct record *rec, bool tail);
@@ -705,6 +745,7 @@ static void workload_exec_failed_signal(int signo __maybe_unused,
}
static void snapshot_sig_handler(int sig);
+static void alarm_sig_handler(int sig);
int __weak
perf_event__synth_time_conv(const struct perf_event_mmap_page *pc __maybe_unused,
@@ -833,12 +874,13 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
signal(SIGCHLD, sig_handler);
signal(SIGINT, sig_handler);
signal(SIGTERM, sig_handler);
+ signal(SIGSEGV, sigsegv_handler);
- if (rec->opts.auxtrace_snapshot_mode || rec->switch_output) {
+ if (rec->opts.auxtrace_snapshot_mode || rec->switch_output.enabled) {
signal(SIGUSR2, snapshot_sig_handler);
if (rec->opts.auxtrace_snapshot_mode)
trigger_on(&auxtrace_snapshot_trigger);
- if (rec->switch_output)
+ if (rec->switch_output.enabled)
trigger_on(&switch_output_trigger);
} else {
signal(SIGUSR2, SIG_IGN);
@@ -970,6 +1012,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
trigger_ready(&auxtrace_snapshot_trigger);
trigger_ready(&switch_output_trigger);
+ perf_hooks__invoke_record_start();
for (;;) {
unsigned long long hits = rec->samples;
@@ -1034,6 +1077,10 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
err = fd;
goto out_child;
}
+
+ /* re-arm the alarm */
+ if (rec->switch_output.time)
+ alarm(rec->switch_output.time);
}
if (hits == rec->samples) {
@@ -1114,6 +1161,8 @@ out_child:
}
}
+ perf_hooks__invoke_record_end();
+
if (!err && !quiet) {
char samples[128];
const char *postfix = rec->timestamp_filename ?
@@ -1341,6 +1390,78 @@ out_free:
return ret;
}
+static void switch_output_size_warn(struct record *rec)
+{
+ u64 wakeup_size = perf_evlist__mmap_size(rec->opts.mmap_pages);
+ struct switch_output *s = &rec->switch_output;
+
+ wakeup_size /= 2;
+
+ if (s->size < wakeup_size) {
+ char buf[100];
+
+ unit_number__scnprintf(buf, sizeof(buf), wakeup_size);
+ pr_warning("WARNING: switch-output data size lower than "
+ "wakeup kernel buffer size (%s) "
+ "expect bigger perf.data sizes\n", buf);
+ }
+}
+
+static int switch_output_setup(struct record *rec)
+{
+ struct switch_output *s = &rec->switch_output;
+ static struct parse_tag tags_size[] = {
+ { .tag = 'B', .mult = 1 },
+ { .tag = 'K', .mult = 1 << 10 },
+ { .tag = 'M', .mult = 1 << 20 },
+ { .tag = 'G', .mult = 1 << 30 },
+ { .tag = 0 },
+ };
+ static struct parse_tag tags_time[] = {
+ { .tag = 's', .mult = 1 },
+ { .tag = 'm', .mult = 60 },
+ { .tag = 'h', .mult = 60*60 },
+ { .tag = 'd', .mult = 60*60*24 },
+ { .tag = 0 },
+ };
+ unsigned long val;
+
+ if (!s->set)
+ return 0;
+
+ if (!strcmp(s->str, "signal")) {
+ s->signal = true;
+ pr_debug("switch-output with SIGUSR2 signal\n");
+ goto enabled;
+ }
+
+ val = parse_tag_value(s->str, tags_size);
+ if (val != (unsigned long) -1) {
+ s->size = val;
+ pr_debug("switch-output with %s size threshold\n", s->str);
+ goto enabled;
+ }
+
+ val = parse_tag_value(s->str, tags_time);
+ if (val != (unsigned long) -1) {
+ s->time = val;
+ pr_debug("switch-output with %s time threshold (%lu seconds)\n",
+ s->str, s->time);
+ goto enabled;
+ }
+
+ return -1;
+
+enabled:
+ rec->timestamp_filename = true;
+ s->enabled = true;
+
+ if (s->size && !rec->opts.no_buffering)
+ switch_output_size_warn(rec);
+
+ return 0;
+}
+
static const char * const __record_usage[] = {
"perf record [<options>] [<command>]",
"perf record [<options>] -- <command> [<options>]",
@@ -1394,7 +1515,7 @@ static bool dry_run;
* perf_evlist__prepare_workload, etc instead of fork+exec'in 'perf record',
* using pipes, etc.
*/
-struct option __record_options[] = {
+static struct option __record_options[] = {
OPT_CALLBACK('e', "event", &record.evlist, "event",
"event selector. use 'perf list' to list available events",
parse_events_option),
@@ -1508,8 +1629,10 @@ struct option __record_options[] = {
"Record build-id of all DSOs regardless of hits"),
OPT_BOOLEAN(0, "timestamp-filename", &record.timestamp_filename,
"append timestamp to output filename"),
- OPT_BOOLEAN(0, "switch-output", &record.switch_output,
- "Switch output when receive SIGUSR2"),
+ 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",
+ "signal"),
OPT_BOOLEAN(0, "dry-run", &dry_run,
"Parse options then exit"),
OPT_END()
@@ -1548,12 +1671,18 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
if (rec->evlist == NULL)
return -ENOMEM;
- perf_config(perf_record_config, rec);
+ err = perf_config(perf_record_config, rec);
+ if (err)
+ return err;
argc = parse_options(argc, argv, record_options, record_usage,
PARSE_OPT_STOP_AT_NON_OPTION);
+ if (quiet)
+ perf_quiet_option();
+
+ /* Make system wide (-a) the default target. */
if (!argc && target__none(&rec->opts.target))
- usage_with_options(record_usage, record_options);
+ rec->opts.target.system_wide = true;
if (nr_cgroups && !rec->opts.target.system_wide) {
usage_with_options_msg(record_usage, record_options,
@@ -1567,8 +1696,15 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
return -EINVAL;
}
- if (rec->switch_output)
- rec->timestamp_filename = true;
+ if (switch_output_setup(rec)) {
+ parse_options_usage(record_usage, record_options, "switch-output", 0);
+ return -EINVAL;
+ }
+
+ if (rec->switch_output.time) {
+ signal(SIGALRM, alarm_sig_handler);
+ alarm(rec->switch_output.time);
+ }
if (!rec->itr) {
rec->itr = auxtrace_record__init(rec->evlist, &err);
@@ -1618,14 +1754,14 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
if (rec->no_buildid_cache || rec->no_buildid) {
disable_buildid_cache();
- } else if (rec->switch_output) {
+ } else if (rec->switch_output.enabled) {
/*
* In 'perf record --switch-output', disable buildid
* generation by default to reduce data file switching
* overhead. Still generate buildid if they are required
* explicitly using
*
- * perf record --signal-trigger --no-no-buildid \
+ * perf record --switch-output --no-no-buildid \
* --no-no-buildid-cache
*
* Following code equals to:
@@ -1676,6 +1812,9 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
goto out;
}
+ /* Enable ignoring missing threads when -u option is defined. */
+ rec->opts.ignore_missing_thread = rec->opts.target.uid != UINT_MAX;
+
err = -ENOMEM;
if (perf_evlist__create_maps(rec->evlist, &rec->opts.target) < 0)
usage_with_options(record_usage, record_options);
@@ -1707,6 +1846,8 @@ out:
static void snapshot_sig_handler(int sig __maybe_unused)
{
+ struct record *rec = &record;
+
if (trigger_is_ready(&auxtrace_snapshot_trigger)) {
trigger_hit(&auxtrace_snapshot_trigger);
auxtrace_record__snapshot_started = 1;
@@ -1714,6 +1855,14 @@ static void snapshot_sig_handler(int sig __maybe_unused)
trigger_error(&auxtrace_snapshot_trigger);
}
- if (trigger_is_ready(&switch_output_trigger))
+ if (switch_output_signal(rec))
+ trigger_hit(&switch_output_trigger);
+}
+
+static void alarm_sig_handler(int sig __maybe_unused)
+{
+ struct record *rec = &record;
+
+ if (switch_output_time(rec))
trigger_hit(&switch_output_trigger);
}
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 6e88460cd13d..0a88670e56f3 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -36,7 +36,7 @@
#include "util/hist.h"
#include "util/data.h"
#include "arch/common.h"
-
+#include "util/time-utils.h"
#include "util/auxtrace.h"
#include <dlfcn.h>
@@ -59,6 +59,8 @@ struct report {
const char *pretty_printing_style;
const char *cpu_list;
const char *symbol_filter_str;
+ const char *time_str;
+ struct perf_time_interval ptime;
float min_percent;
u64 nr_entries;
u64 queue_size;
@@ -158,6 +160,9 @@ static int process_sample_event(struct perf_tool *tool,
};
int ret = 0;
+ if (perf_time__skip_sample(&rep->ptime, sample->time))
+ return 0;
+
if (machine__resolve(machine, &al, sample) < 0) {
pr_debug("problem processing %d event, skipping it.\n",
event->header.type);
@@ -207,11 +212,14 @@ static int process_read_event(struct perf_tool *tool,
if (rep->show_threads) {
const char *name = evsel ? perf_evsel__name(evsel) : "unknown";
- perf_read_values_add_value(&rep->show_threads_values,
+ int err = perf_read_values_add_value(&rep->show_threads_values,
event->read.pid, event->read.tid,
event->read.id,
name,
event->read.value);
+
+ if (err)
+ return err;
}
dump_printf(": %d %d %s %" PRIu64 "\n", event->read.pid, event->read.tid,
@@ -312,6 +320,9 @@ static size_t hists__fprintf_nr_sample_events(struct hists *hists, struct report
size_t size = sizeof(buf);
int socked_id = hists->socket_filter;
+ if (quiet)
+ return 0;
+
if (symbol_conf.filter_relative) {
nr_samples = hists->stats.nr_non_filtered_samples;
nr_events = hists->stats.total_non_filtered_period;
@@ -364,7 +375,11 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
{
struct perf_evsel *pos;
- fprintf(stdout, "#\n# Total Lost Samples: %" PRIu64 "\n#\n", evlist->stats.total_lost_samples);
+ if (!quiet) {
+ fprintf(stdout, "#\n# Total Lost Samples: %" PRIu64 "\n#\n",
+ evlist->stats.total_lost_samples);
+ }
+
evlist__for_each_entry(evlist, pos) {
struct hists *hists = evsel__hists(pos);
const char *evname = perf_evsel__name(pos);
@@ -374,7 +389,7 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
continue;
hists__fprintf_nr_sample_events(hists, rep, evname, stdout);
- hists__fprintf(hists, true, 0, 0, rep->min_percent, stdout,
+ hists__fprintf(hists, !quiet, 0, 0, rep->min_percent, stdout,
symbol_conf.use_callchain);
fprintf(stdout, "\n\n");
}
@@ -539,8 +554,11 @@ static int __cmd_report(struct report *rep)
}
}
- if (rep->show_threads)
- perf_read_values_init(&rep->show_threads_values);
+ if (rep->show_threads) {
+ ret = perf_read_values_init(&rep->show_threads_values);
+ if (ret)
+ return ret;
+ }
ret = report__setup_sample_type(rep);
if (ret) {
@@ -637,7 +655,7 @@ report_parse_ignore_callees_opt(const struct option *opt __maybe_unused,
}
static int
-parse_branch_mode(const struct option *opt __maybe_unused,
+parse_branch_mode(const struct option *opt,
const char *str __maybe_unused, int unset)
{
int *branch_mode = opt->value;
@@ -705,6 +723,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
"input file name"),
OPT_INCR('v', "verbose", &verbose,
"be more verbose (show symbol address, etc)"),
+ OPT_BOOLEAN('q', "quiet", &quiet, "Do not show any message"),
OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
"dump raw trace in ASCII"),
OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name,
@@ -824,6 +843,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
OPT_CALLBACK_DEFAULT(0, "stdio-color", NULL, "mode",
"'always' (default), 'never' or 'auto' only applicable to --stdio mode",
stdio__config_color, "always"),
+ OPT_STRING(0, "time", &report.time_str, "str",
+ "Time span of interest (start,stop)"),
OPT_END()
};
struct perf_data_file file = {
@@ -834,7 +855,9 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
if (ret < 0)
return ret;
- perf_config(report__config, &report);
+ ret = perf_config(report__config, &report);
+ if (ret)
+ return ret;
argc = parse_options(argc, argv, options, report_usage, 0);
if (argc) {
@@ -848,6 +871,9 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
report.symbol_filter_str = argv[0];
}
+ if (quiet)
+ perf_quiet_option();
+
if (symbol_conf.vmlinux_name &&
access(symbol_conf.vmlinux_name, R_OK)) {
pr_err("Invalid file: %s\n", symbol_conf.vmlinux_name);
@@ -905,6 +931,9 @@ repeat:
if (itrace_synth_opts.last_branch)
has_br_stack = true;
+ if (has_br_stack && branch_call_mode)
+ symbol_conf.show_branchflag_count = true;
+
/*
* Branch mode is a tristate:
* -1 means default, so decide based on the file having branch data.
@@ -965,14 +994,14 @@ repeat:
goto error;
}
- if (report.header || report.header_only) {
+ if ((report.header || report.header_only) && !quiet) {
perf_session__fprintf_info(session, stdout,
report.show_full_info);
if (report.header_only) {
ret = 0;
goto error;
}
- } else if (use_browser == 0) {
+ } else if (use_browser == 0 && !quiet) {
fputs("# To display the perf.data header info, please use --header/--header-only options.\n#\n",
stdout);
}
@@ -991,7 +1020,7 @@ repeat:
* providing it only in verbose mode not to bloat too
* much struct symbol.
*/
- if (verbose) {
+ if (verbose > 0) {
/*
* XXX: Need to provide a less kludgy way to ask for
* more space per symbol, the u32 is for the index on
@@ -1006,6 +1035,11 @@ repeat:
if (symbol__init(&session->header.env) < 0)
goto error;
+ if (perf_time__parse_str(&report.ptime, report.time_str) != 0) {
+ pr_err("Invalid time string\n");
+ return -EINVAL;
+ }
+
sort__setup_elide(stdout);
ret = __cmd_report(&report);
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index f5503ca22e1c..b94cf0de715a 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -13,12 +13,16 @@
#include "util/cloexec.h"
#include "util/thread_map.h"
#include "util/color.h"
+#include "util/stat.h"
+#include "util/callchain.h"
+#include "util/time-utils.h"
#include <subcmd/parse-options.h>
#include "util/trace-event.h"
#include "util/debug.h"
+#include <linux/log2.h>
#include <sys/prctl.h>
#include <sys/resource.h>
@@ -73,6 +77,22 @@ struct sched_atom {
#define TASK_STATE_TO_CHAR_STR "RSDTtZXxKWP"
+/* task state bitmask, copied from include/linux/sched.h */
+#define TASK_RUNNING 0
+#define TASK_INTERRUPTIBLE 1
+#define TASK_UNINTERRUPTIBLE 2
+#define __TASK_STOPPED 4
+#define __TASK_TRACED 8
+/* in tsk->exit_state */
+#define EXIT_DEAD 16
+#define EXIT_ZOMBIE 32
+#define EXIT_TRACE (EXIT_ZOMBIE | EXIT_DEAD)
+/* in tsk->state again */
+#define TASK_DEAD 64
+#define TASK_WAKEKILL 128
+#define TASK_WAKING 256
+#define TASK_PARKED 512
+
enum thread_state {
THREAD_SLEEPING = 0,
THREAD_WAIT_CPU,
@@ -192,8 +212,64 @@ struct perf_sched {
bool force;
bool skip_merge;
struct perf_sched_map map;
+
+ /* options for timehist command */
+ bool summary;
+ bool summary_only;
+ bool idle_hist;
+ bool show_callchain;
+ unsigned int max_stack;
+ bool show_cpu_visual;
+ bool show_wakeups;
+ bool show_migrations;
+ bool show_state;
+ u64 skipped_samples;
+ const char *time_str;
+ struct perf_time_interval ptime;
+ struct perf_time_interval hist_time;
};
+/* per thread run time data */
+struct thread_runtime {
+ u64 last_time; /* time of previous sched in/out event */
+ u64 dt_run; /* run time */
+ u64 dt_sleep; /* time between CPU access by sleep (off cpu) */
+ u64 dt_iowait; /* time between CPU access by iowait (off cpu) */
+ u64 dt_preempt; /* time between CPU access by preempt (off cpu) */
+ u64 dt_delay; /* time between wakeup and sched-in */
+ u64 ready_to_run; /* time of wakeup */
+
+ struct stats run_stats;
+ u64 total_run_time;
+ u64 total_sleep_time;
+ u64 total_iowait_time;
+ u64 total_preempt_time;
+ u64 total_delay_time;
+
+ int last_state;
+ u64 migrations;
+};
+
+/* per event run time data */
+struct evsel_runtime {
+ u64 *last_time; /* time this event was last seen per cpu */
+ u32 ncpu; /* highest cpu slot allocated */
+};
+
+/* per cpu idle time data */
+struct idle_thread_runtime {
+ struct thread_runtime tr;
+ struct thread *last_thread;
+ struct rb_root sorted_root;
+ struct callchain_root callchain;
+ struct callchain_cursor cursor;
+};
+
+/* track idle times per cpu */
+static struct thread **idle_threads;
+static int idle_max_cpu;
+static char idle_comm[] = "<idle>";
+
static u64 get_nsecs(void)
{
struct timespec ts;
@@ -384,7 +460,7 @@ static struct task_desc *register_pid(struct perf_sched *sched,
BUG_ON(!sched->tasks);
sched->tasks[task->nr] = task;
- if (verbose)
+ if (verbose > 0)
printf("registered task #%ld, PID %ld (%s)\n", sched->nr_tasks, pid, comm);
return task;
@@ -718,7 +794,7 @@ replay_wakeup_event(struct perf_sched *sched,
const u32 pid = perf_evsel__intval(evsel, sample, "pid");
struct task_desc *waker, *wakee;
- if (verbose) {
+ if (verbose > 0) {
printf("sched_wakeup event %p\n", evsel);
printf(" ... pid %d woke up %s/%d\n", sample->tid, comm, pid);
@@ -746,7 +822,7 @@ static int replay_switch_event(struct perf_sched *sched,
int cpu = sample->cpu;
s64 delta;
- if (verbose)
+ if (verbose > 0)
printf("sched_switch event %p\n", evsel);
if (cpu >= MAX_CPUS || cpu < 0)
@@ -794,7 +870,7 @@ static int replay_fork_event(struct perf_sched *sched,
goto out_put;
}
- if (verbose) {
+ if (verbose > 0) {
printf("fork event\n");
printf("... parent: %s/%d\n", thread__comm_str(parent), parent->tid);
printf("... child: %s/%d\n", thread__comm_str(child), child->tid);
@@ -1191,6 +1267,7 @@ static void output_lat_thread(struct perf_sched *sched, struct work_atoms *work_
int i;
int ret;
u64 avg;
+ char max_lat_at[32];
if (!work_list->nb_atoms)
return;
@@ -1212,12 +1289,13 @@ static void output_lat_thread(struct perf_sched *sched, struct work_atoms *work_
printf(" ");
avg = work_list->total_lat / work_list->nb_atoms;
+ timestamp__scnprintf_usec(work_list->max_lat_at, max_lat_at, sizeof(max_lat_at));
- printf("|%11.3f ms |%9" PRIu64 " | avg:%9.3f ms | max:%9.3f ms | max at: %13.6f s\n",
+ printf("|%11.3f ms |%9" PRIu64 " | avg:%9.3f ms | max:%9.3f ms | max at: %13s s\n",
(double)work_list->total_runtime / NSEC_PER_MSEC,
work_list->nb_atoms, (double)avg / NSEC_PER_MSEC,
(double)work_list->max_lat / NSEC_PER_MSEC,
- (double)work_list->max_lat_at / NSEC_PER_SEC);
+ max_lat_at);
}
static int pid_cmp(struct work_atoms *l, struct work_atoms *r)
@@ -1402,6 +1480,7 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel,
int cpus_nr;
bool new_cpu = false;
const char *color = PERF_COLOR_NORMAL;
+ char stimestamp[32];
BUG_ON(this_cpu >= MAX_CPUS || this_cpu < 0);
@@ -1479,7 +1558,7 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel,
cpu_color = COLOR_CPUS;
if (cpu != this_cpu)
- color_fprintf(stdout, cpu_color, " ");
+ color_fprintf(stdout, color, " ");
else
color_fprintf(stdout, cpu_color, "*");
@@ -1492,8 +1571,9 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel,
if (sched->map.cpus && !cpu_map__has(sched->map.cpus, this_cpu))
goto out;
- color_fprintf(stdout, color, " %12.6f secs ", (double)timestamp / NSEC_PER_SEC);
- if (new_shortname) {
+ timestamp__scnprintf_usec(timestamp, stimestamp, sizeof(stimestamp));
+ color_fprintf(stdout, color, " %12s secs ", stimestamp);
+ if (new_shortname || (verbose > 0 && sched_in->tid)) {
const char *pid_color = color;
if (thread__has_color(sched_in))
@@ -1650,6 +1730,1259 @@ out_delete:
return rc;
}
+/*
+ * scheduling times are printed as msec.usec
+ */
+static inline void print_sched_time(unsigned long long nsecs, int width)
+{
+ unsigned long msecs;
+ unsigned long usecs;
+
+ msecs = nsecs / NSEC_PER_MSEC;
+ nsecs -= msecs * NSEC_PER_MSEC;
+ usecs = nsecs / NSEC_PER_USEC;
+ printf("%*lu.%03lu ", width, msecs, usecs);
+}
+
+/*
+ * returns runtime data for event, allocating memory for it the
+ * first time it is used.
+ */
+static struct evsel_runtime *perf_evsel__get_runtime(struct perf_evsel *evsel)
+{
+ struct evsel_runtime *r = evsel->priv;
+
+ if (r == NULL) {
+ r = zalloc(sizeof(struct evsel_runtime));
+ evsel->priv = r;
+ }
+
+ return r;
+}
+
+/*
+ * save last time event was seen per cpu
+ */
+static void perf_evsel__save_time(struct perf_evsel *evsel,
+ u64 timestamp, u32 cpu)
+{
+ struct evsel_runtime *r = perf_evsel__get_runtime(evsel);
+
+ if (r == NULL)
+ return;
+
+ if ((cpu >= r->ncpu) || (r->last_time == NULL)) {
+ int i, n = __roundup_pow_of_two(cpu+1);
+ void *p = r->last_time;
+
+ p = realloc(r->last_time, n * sizeof(u64));
+ if (!p)
+ return;
+
+ r->last_time = p;
+ for (i = r->ncpu; i < n; ++i)
+ r->last_time[i] = (u64) 0;
+
+ r->ncpu = n;
+ }
+
+ r->last_time[cpu] = timestamp;
+}
+
+/* returns last time this event was seen on the given cpu */
+static u64 perf_evsel__get_time(struct perf_evsel *evsel, u32 cpu)
+{
+ struct evsel_runtime *r = perf_evsel__get_runtime(evsel);
+
+ if ((r == NULL) || (r->last_time == NULL) || (cpu >= r->ncpu))
+ return 0;
+
+ return r->last_time[cpu];
+}
+
+static int comm_width = 30;
+
+static char *timehist_get_commstr(struct thread *thread)
+{
+ static char str[32];
+ const char *comm = thread__comm_str(thread);
+ pid_t tid = thread->tid;
+ pid_t pid = thread->pid_;
+ int n;
+
+ if (pid == 0)
+ n = scnprintf(str, sizeof(str), "%s", comm);
+
+ else if (tid != pid)
+ n = scnprintf(str, sizeof(str), "%s[%d/%d]", comm, tid, pid);
+
+ else
+ n = scnprintf(str, sizeof(str), "%s[%d]", comm, tid);
+
+ if (n > comm_width)
+ comm_width = n;
+
+ return str;
+}
+
+static void timehist_header(struct perf_sched *sched)
+{
+ u32 ncpus = sched->max_cpu + 1;
+ u32 i, j;
+
+ printf("%15s %6s ", "time", "cpu");
+
+ if (sched->show_cpu_visual) {
+ printf(" ");
+ for (i = 0, j = 0; i < ncpus; ++i) {
+ printf("%x", j++);
+ if (j > 15)
+ j = 0;
+ }
+ printf(" ");
+ }
+
+ printf(" %-*s %9s %9s %9s", comm_width,
+ "task name", "wait time", "sch delay", "run time");
+
+ if (sched->show_state)
+ printf(" %s", "state");
+
+ printf("\n");
+
+ /*
+ * units row
+ */
+ printf("%15s %-6s ", "", "");
+
+ if (sched->show_cpu_visual)
+ printf(" %*s ", ncpus, "");
+
+ printf(" %-*s %9s %9s %9s", comm_width,
+ "[tid/pid]", "(msec)", "(msec)", "(msec)");
+
+ if (sched->show_state)
+ printf(" %5s", "");
+
+ printf("\n");
+
+ /*
+ * separator
+ */
+ printf("%.15s %.6s ", graph_dotted_line, graph_dotted_line);
+
+ if (sched->show_cpu_visual)
+ printf(" %.*s ", ncpus, graph_dotted_line);
+
+ printf(" %.*s %.9s %.9s %.9s", comm_width,
+ graph_dotted_line, graph_dotted_line, graph_dotted_line,
+ graph_dotted_line);
+
+ if (sched->show_state)
+ printf(" %.5s", graph_dotted_line);
+
+ printf("\n");
+}
+
+static char task_state_char(struct thread *thread, int state)
+{
+ static const char state_to_char[] = TASK_STATE_TO_CHAR_STR;
+ unsigned bit = state ? ffs(state) : 0;
+
+ /* 'I' for idle */
+ if (thread->tid == 0)
+ return 'I';
+
+ return bit < sizeof(state_to_char) - 1 ? state_to_char[bit] : '?';
+}
+
+static void timehist_print_sample(struct perf_sched *sched,
+ struct perf_sample *sample,
+ struct addr_location *al,
+ struct thread *thread,
+ u64 t, int state)
+{
+ struct thread_runtime *tr = thread__priv(thread);
+ u32 max_cpus = sched->max_cpu + 1;
+ char tstr[64];
+ u64 wait_time;
+
+ timestamp__scnprintf_usec(t, tstr, sizeof(tstr));
+ printf("%15s [%04d] ", tstr, sample->cpu);
+
+ if (sched->show_cpu_visual) {
+ u32 i;
+ char c;
+
+ printf(" ");
+ for (i = 0; i < max_cpus; ++i) {
+ /* flag idle times with 'i'; others are sched events */
+ if (i == sample->cpu)
+ c = (thread->tid == 0) ? 'i' : 's';
+ else
+ c = ' ';
+ printf("%c", c);
+ }
+ printf(" ");
+ }
+
+ printf(" %-*s ", comm_width, timehist_get_commstr(thread));
+
+ wait_time = tr->dt_sleep + tr->dt_iowait + tr->dt_preempt;
+ print_sched_time(wait_time, 6);
+
+ print_sched_time(tr->dt_delay, 6);
+ print_sched_time(tr->dt_run, 6);
+
+ if (sched->show_state)
+ printf(" %5c ", task_state_char(thread, state));
+
+ if (sched->show_wakeups)
+ printf(" %-*s", comm_width, "");
+
+ if (thread->tid == 0)
+ goto out;
+
+ if (sched->show_callchain)
+ printf(" ");
+
+ sample__fprintf_sym(sample, al, 0,
+ EVSEL__PRINT_SYM | EVSEL__PRINT_ONELINE |
+ EVSEL__PRINT_CALLCHAIN_ARROW |
+ EVSEL__PRINT_SKIP_IGNORED,
+ &callchain_cursor, stdout);
+
+out:
+ printf("\n");
+}
+
+/*
+ * Explanation of delta-time stats:
+ *
+ * t = time of current schedule out event
+ * tprev = time of previous sched out event
+ * also time of schedule-in event for current task
+ * last_time = time of last sched change event for current task
+ * (i.e, time process was last scheduled out)
+ * ready_to_run = time of wakeup for current task
+ *
+ * -----|------------|------------|------------|------
+ * last ready tprev t
+ * time to run
+ *
+ * |-------- dt_wait --------|
+ * |- dt_delay -|-- dt_run --|
+ *
+ * dt_run = run time of current task
+ * dt_wait = time between last schedule out event for task and tprev
+ * represents time spent off the cpu
+ * dt_delay = time between wakeup and schedule-in of task
+ */
+
+static void timehist_update_runtime_stats(struct thread_runtime *r,
+ u64 t, u64 tprev)
+{
+ r->dt_delay = 0;
+ r->dt_sleep = 0;
+ r->dt_iowait = 0;
+ r->dt_preempt = 0;
+ r->dt_run = 0;
+
+ if (tprev) {
+ r->dt_run = t - tprev;
+ if (r->ready_to_run) {
+ if (r->ready_to_run > tprev)
+ pr_debug("time travel: wakeup time for task > previous sched_switch event\n");
+ else
+ r->dt_delay = tprev - r->ready_to_run;
+ }
+
+ if (r->last_time > tprev)
+ pr_debug("time travel: last sched out time for task > previous sched_switch event\n");
+ else if (r->last_time) {
+ u64 dt_wait = tprev - r->last_time;
+
+ if (r->last_state == TASK_RUNNING)
+ r->dt_preempt = dt_wait;
+ else if (r->last_state == TASK_UNINTERRUPTIBLE)
+ r->dt_iowait = dt_wait;
+ else
+ r->dt_sleep = dt_wait;
+ }
+ }
+
+ update_stats(&r->run_stats, r->dt_run);
+
+ r->total_run_time += r->dt_run;
+ r->total_delay_time += r->dt_delay;
+ r->total_sleep_time += r->dt_sleep;
+ r->total_iowait_time += r->dt_iowait;
+ r->total_preempt_time += r->dt_preempt;
+}
+
+static bool is_idle_sample(struct perf_sample *sample,
+ struct perf_evsel *evsel)
+{
+ /* pid 0 == swapper == idle task */
+ if (strcmp(perf_evsel__name(evsel), "sched:sched_switch") == 0)
+ return perf_evsel__intval(evsel, sample, "prev_pid") == 0;
+
+ return sample->pid == 0;
+}
+
+static void save_task_callchain(struct perf_sched *sched,
+ struct perf_sample *sample,
+ struct perf_evsel *evsel,
+ struct machine *machine)
+{
+ struct callchain_cursor *cursor = &callchain_cursor;
+ struct thread *thread;
+
+ /* want main thread for process - has maps */
+ thread = machine__findnew_thread(machine, sample->pid, sample->pid);
+ if (thread == NULL) {
+ pr_debug("Failed to get thread for pid %d.\n", sample->pid);
+ return;
+ }
+
+ if (!symbol_conf.use_callchain || sample->callchain == NULL)
+ return;
+
+ if (thread__resolve_callchain(thread, cursor, evsel, sample,
+ NULL, NULL, sched->max_stack + 2) != 0) {
+ if (verbose > 0)
+ error("Failed to resolve callchain. Skipping\n");
+
+ return;
+ }
+
+ callchain_cursor_commit(cursor);
+
+ while (true) {
+ struct callchain_cursor_node *node;
+ struct symbol *sym;
+
+ node = callchain_cursor_current(cursor);
+ if (node == NULL)
+ break;
+
+ sym = node->sym;
+ if (sym) {
+ if (!strcmp(sym->name, "schedule") ||
+ !strcmp(sym->name, "__schedule") ||
+ !strcmp(sym->name, "preempt_schedule"))
+ sym->ignore = 1;
+ }
+
+ callchain_cursor_advance(cursor);
+ }
+}
+
+static int init_idle_thread(struct thread *thread)
+{
+ struct idle_thread_runtime *itr;
+
+ thread__set_comm(thread, idle_comm, 0);
+
+ itr = zalloc(sizeof(*itr));
+ if (itr == NULL)
+ return -ENOMEM;
+
+ init_stats(&itr->tr.run_stats);
+ callchain_init(&itr->callchain);
+ callchain_cursor_reset(&itr->cursor);
+ thread__set_priv(thread, itr);
+
+ return 0;
+}
+
+/*
+ * Track idle stats per cpu by maintaining a local thread
+ * struct for the idle task on each cpu.
+ */
+static int init_idle_threads(int ncpu)
+{
+ int i, ret;
+
+ idle_threads = zalloc(ncpu * sizeof(struct thread *));
+ if (!idle_threads)
+ return -ENOMEM;
+
+ idle_max_cpu = ncpu;
+
+ /* allocate the actual thread struct if needed */
+ for (i = 0; i < ncpu; ++i) {
+ idle_threads[i] = thread__new(0, 0);
+ if (idle_threads[i] == NULL)
+ return -ENOMEM;
+
+ ret = init_idle_thread(idle_threads[i]);
+ if (ret < 0)
+ return ret;
+ }
+
+ return 0;
+}
+
+static void free_idle_threads(void)
+{
+ int i;
+
+ if (idle_threads == NULL)
+ return;
+
+ for (i = 0; i < idle_max_cpu; ++i) {
+ if ((idle_threads[i]))
+ thread__delete(idle_threads[i]);
+ }
+
+ free(idle_threads);
+}
+
+static struct thread *get_idle_thread(int cpu)
+{
+ /*
+ * expand/allocate array of pointers to local thread
+ * structs if needed
+ */
+ if ((cpu >= idle_max_cpu) || (idle_threads == NULL)) {
+ int i, j = __roundup_pow_of_two(cpu+1);
+ void *p;
+
+ p = realloc(idle_threads, j * sizeof(struct thread *));
+ if (!p)
+ return NULL;
+
+ idle_threads = (struct thread **) p;
+ for (i = idle_max_cpu; i < j; ++i)
+ idle_threads[i] = NULL;
+
+ idle_max_cpu = j;
+ }
+
+ /* allocate a new thread struct if needed */
+ if (idle_threads[cpu] == NULL) {
+ idle_threads[cpu] = thread__new(0, 0);
+
+ if (idle_threads[cpu]) {
+ if (init_idle_thread(idle_threads[cpu]) < 0)
+ return NULL;
+ }
+ }
+
+ return idle_threads[cpu];
+}
+
+static void save_idle_callchain(struct idle_thread_runtime *itr,
+ struct perf_sample *sample)
+{
+ if (!symbol_conf.use_callchain || sample->callchain == NULL)
+ return;
+
+ callchain_cursor__copy(&itr->cursor, &callchain_cursor);
+}
+
+/*
+ * handle runtime stats saved per thread
+ */
+static struct thread_runtime *thread__init_runtime(struct thread *thread)
+{
+ struct thread_runtime *r;
+
+ r = zalloc(sizeof(struct thread_runtime));
+ if (!r)
+ return NULL;
+
+ init_stats(&r->run_stats);
+ thread__set_priv(thread, r);
+
+ return r;
+}
+
+static struct thread_runtime *thread__get_runtime(struct thread *thread)
+{
+ struct thread_runtime *tr;
+
+ tr = thread__priv(thread);
+ if (tr == NULL) {
+ tr = thread__init_runtime(thread);
+ if (tr == NULL)
+ pr_debug("Failed to malloc memory for runtime data.\n");
+ }
+
+ return tr;
+}
+
+static struct thread *timehist_get_thread(struct perf_sched *sched,
+ struct perf_sample *sample,
+ struct machine *machine,
+ struct perf_evsel *evsel)
+{
+ struct thread *thread;
+
+ if (is_idle_sample(sample, evsel)) {
+ thread = get_idle_thread(sample->cpu);
+ if (thread == NULL)
+ pr_err("Failed to get idle thread for cpu %d.\n", sample->cpu);
+
+ } else {
+ /* there were samples with tid 0 but non-zero pid */
+ thread = machine__findnew_thread(machine, sample->pid,
+ sample->tid ?: sample->pid);
+ if (thread == NULL) {
+ pr_debug("Failed to get thread for tid %d. skipping sample.\n",
+ sample->tid);
+ }
+
+ save_task_callchain(sched, sample, evsel, machine);
+ if (sched->idle_hist) {
+ struct thread *idle;
+ struct idle_thread_runtime *itr;
+
+ idle = get_idle_thread(sample->cpu);
+ if (idle == NULL) {
+ pr_err("Failed to get idle thread for cpu %d.\n", sample->cpu);
+ return NULL;
+ }
+
+ itr = thread__priv(idle);
+ if (itr == NULL)
+ return NULL;
+
+ itr->last_thread = thread;
+
+ /* copy task callchain when entering to idle */
+ if (perf_evsel__intval(evsel, sample, "next_pid") == 0)
+ save_idle_callchain(itr, sample);
+ }
+ }
+
+ return thread;
+}
+
+static bool timehist_skip_sample(struct perf_sched *sched,
+ struct thread *thread,
+ struct perf_evsel *evsel,
+ struct perf_sample *sample)
+{
+ bool rc = false;
+
+ if (thread__is_filtered(thread)) {
+ rc = true;
+ sched->skipped_samples++;
+ }
+
+ if (sched->idle_hist) {
+ if (strcmp(perf_evsel__name(evsel), "sched:sched_switch"))
+ rc = true;
+ else if (perf_evsel__intval(evsel, sample, "prev_pid") != 0 &&
+ perf_evsel__intval(evsel, sample, "next_pid") != 0)
+ rc = true;
+ }
+
+ return rc;
+}
+
+static void timehist_print_wakeup_event(struct perf_sched *sched,
+ struct perf_evsel *evsel,
+ struct perf_sample *sample,
+ struct machine *machine,
+ struct thread *awakened)
+{
+ struct thread *thread;
+ char tstr[64];
+
+ thread = machine__findnew_thread(machine, sample->pid, sample->tid);
+ if (thread == NULL)
+ return;
+
+ /* show wakeup unless both awakee and awaker are filtered */
+ if (timehist_skip_sample(sched, thread, evsel, sample) &&
+ timehist_skip_sample(sched, awakened, evsel, sample)) {
+ return;
+ }
+
+ timestamp__scnprintf_usec(sample->time, tstr, sizeof(tstr));
+ printf("%15s [%04d] ", tstr, sample->cpu);
+ if (sched->show_cpu_visual)
+ printf(" %*s ", sched->max_cpu + 1, "");
+
+ printf(" %-*s ", comm_width, timehist_get_commstr(thread));
+
+ /* dt spacer */
+ printf(" %9s %9s %9s ", "", "", "");
+
+ printf("awakened: %s", timehist_get_commstr(awakened));
+
+ printf("\n");
+}
+
+static int timehist_sched_wakeup_event(struct perf_tool *tool,
+ union perf_event *event __maybe_unused,
+ struct perf_evsel *evsel,
+ struct perf_sample *sample,
+ struct machine *machine)
+{
+ struct perf_sched *sched = container_of(tool, struct perf_sched, tool);
+ struct thread *thread;
+ struct thread_runtime *tr = NULL;
+ /* want pid of awakened task not pid in sample */
+ const u32 pid = perf_evsel__intval(evsel, sample, "pid");
+
+ thread = machine__findnew_thread(machine, 0, pid);
+ if (thread == NULL)
+ return -1;
+
+ tr = thread__get_runtime(thread);
+ if (tr == NULL)
+ return -1;
+
+ if (tr->ready_to_run == 0)
+ tr->ready_to_run = sample->time;
+
+ /* show wakeups if requested */
+ if (sched->show_wakeups &&
+ !perf_time__skip_sample(&sched->ptime, sample->time))
+ timehist_print_wakeup_event(sched, evsel, sample, machine, thread);
+
+ return 0;
+}
+
+static void timehist_print_migration_event(struct perf_sched *sched,
+ struct perf_evsel *evsel,
+ struct perf_sample *sample,
+ struct machine *machine,
+ struct thread *migrated)
+{
+ struct thread *thread;
+ char tstr[64];
+ u32 max_cpus = sched->max_cpu + 1;
+ u32 ocpu, dcpu;
+
+ if (sched->summary_only)
+ return;
+
+ max_cpus = sched->max_cpu + 1;
+ ocpu = perf_evsel__intval(evsel, sample, "orig_cpu");
+ dcpu = perf_evsel__intval(evsel, sample, "dest_cpu");
+
+ thread = machine__findnew_thread(machine, sample->pid, sample->tid);
+ if (thread == NULL)
+ return;
+
+ if (timehist_skip_sample(sched, thread, evsel, sample) &&
+ timehist_skip_sample(sched, migrated, evsel, sample)) {
+ return;
+ }
+
+ timestamp__scnprintf_usec(sample->time, tstr, sizeof(tstr));
+ printf("%15s [%04d] ", tstr, sample->cpu);
+
+ if (sched->show_cpu_visual) {
+ u32 i;
+ char c;
+
+ printf(" ");
+ for (i = 0; i < max_cpus; ++i) {
+ c = (i == sample->cpu) ? 'm' : ' ';
+ printf("%c", c);
+ }
+ printf(" ");
+ }
+
+ printf(" %-*s ", comm_width, timehist_get_commstr(thread));
+
+ /* dt spacer */
+ printf(" %9s %9s %9s ", "", "", "");
+
+ printf("migrated: %s", timehist_get_commstr(migrated));
+ printf(" cpu %d => %d", ocpu, dcpu);
+
+ printf("\n");
+}
+
+static int timehist_migrate_task_event(struct perf_tool *tool,
+ union perf_event *event __maybe_unused,
+ struct perf_evsel *evsel,
+ struct perf_sample *sample,
+ struct machine *machine)
+{
+ struct perf_sched *sched = container_of(tool, struct perf_sched, tool);
+ struct thread *thread;
+ struct thread_runtime *tr = NULL;
+ /* want pid of migrated task not pid in sample */
+ const u32 pid = perf_evsel__intval(evsel, sample, "pid");
+
+ thread = machine__findnew_thread(machine, 0, pid);
+ if (thread == NULL)
+ return -1;
+
+ tr = thread__get_runtime(thread);
+ if (tr == NULL)
+ return -1;
+
+ tr->migrations++;
+
+ /* show migrations if requested */
+ timehist_print_migration_event(sched, evsel, sample, machine, thread);
+
+ return 0;
+}
+
+static int timehist_sched_change_event(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_evsel *evsel,
+ struct perf_sample *sample,
+ struct machine *machine)
+{
+ struct perf_sched *sched = container_of(tool, struct perf_sched, tool);
+ struct perf_time_interval *ptime = &sched->ptime;
+ struct addr_location al;
+ struct thread *thread;
+ struct thread_runtime *tr = NULL;
+ u64 tprev, t = sample->time;
+ int rc = 0;
+ int state = perf_evsel__intval(evsel, sample, "prev_state");
+
+
+ if (machine__resolve(machine, &al, sample) < 0) {
+ pr_err("problem processing %d event. skipping it\n",
+ event->header.type);
+ rc = -1;
+ goto out;
+ }
+
+ thread = timehist_get_thread(sched, sample, machine, evsel);
+ if (thread == NULL) {
+ rc = -1;
+ goto out;
+ }
+
+ if (timehist_skip_sample(sched, thread, evsel, sample))
+ goto out;
+
+ tr = thread__get_runtime(thread);
+ if (tr == NULL) {
+ rc = -1;
+ goto out;
+ }
+
+ tprev = perf_evsel__get_time(evsel, sample->cpu);
+
+ /*
+ * If start time given:
+ * - sample time is under window user cares about - skip sample
+ * - tprev is under window user cares about - reset to start of window
+ */
+ if (ptime->start && ptime->start > t)
+ goto out;
+
+ if (tprev && ptime->start > tprev)
+ tprev = ptime->start;
+
+ /*
+ * If end time given:
+ * - previous sched event is out of window - we are done
+ * - sample time is beyond window user cares about - reset it
+ * to close out stats for time window interest
+ */
+ if (ptime->end) {
+ if (tprev > ptime->end)
+ goto out;
+
+ if (t > ptime->end)
+ t = ptime->end;
+ }
+
+ if (!sched->idle_hist || thread->tid == 0) {
+ timehist_update_runtime_stats(tr, t, tprev);
+
+ if (sched->idle_hist) {
+ struct idle_thread_runtime *itr = (void *)tr;
+ struct thread_runtime *last_tr;
+
+ BUG_ON(thread->tid != 0);
+
+ if (itr->last_thread == NULL)
+ goto out;
+
+ /* add current idle time as last thread's runtime */
+ last_tr = thread__get_runtime(itr->last_thread);
+ if (last_tr == NULL)
+ goto out;
+
+ timehist_update_runtime_stats(last_tr, t, tprev);
+ /*
+ * remove delta time of last thread as it's not updated
+ * and otherwise it will show an invalid value next
+ * time. we only care total run time and run stat.
+ */
+ last_tr->dt_run = 0;
+ last_tr->dt_delay = 0;
+ last_tr->dt_sleep = 0;
+ last_tr->dt_iowait = 0;
+ last_tr->dt_preempt = 0;
+
+ if (itr->cursor.nr)
+ callchain_append(&itr->callchain, &itr->cursor, t - tprev);
+
+ itr->last_thread = NULL;
+ }
+ }
+
+ if (!sched->summary_only)
+ timehist_print_sample(sched, sample, &al, thread, t, state);
+
+out:
+ if (sched->hist_time.start == 0 && t >= ptime->start)
+ sched->hist_time.start = t;
+ if (ptime->end == 0 || t <= ptime->end)
+ sched->hist_time.end = t;
+
+ if (tr) {
+ /* time of this sched_switch event becomes last time task seen */
+ tr->last_time = sample->time;
+
+ /* last state is used to determine where to account wait time */
+ tr->last_state = state;
+
+ /* sched out event for task so reset ready to run time */
+ tr->ready_to_run = 0;
+ }
+
+ perf_evsel__save_time(evsel, sample->time, sample->cpu);
+
+ return rc;
+}
+
+static int timehist_sched_switch_event(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_evsel *evsel,
+ struct perf_sample *sample,
+ struct machine *machine __maybe_unused)
+{
+ return timehist_sched_change_event(tool, event, evsel, sample, machine);
+}
+
+static int process_lost(struct perf_tool *tool __maybe_unused,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct machine *machine __maybe_unused)
+{
+ char tstr[64];
+
+ timestamp__scnprintf_usec(sample->time, tstr, sizeof(tstr));
+ printf("%15s ", tstr);
+ printf("lost %" PRIu64 " events on cpu %d\n", event->lost.lost, sample->cpu);
+
+ return 0;
+}
+
+
+static void print_thread_runtime(struct thread *t,
+ struct thread_runtime *r)
+{
+ double mean = avg_stats(&r->run_stats);
+ float stddev;
+
+ printf("%*s %5d %9" PRIu64 " ",
+ comm_width, timehist_get_commstr(t), t->ppid,
+ (u64) r->run_stats.n);
+
+ print_sched_time(r->total_run_time, 8);
+ stddev = rel_stddev_stats(stddev_stats(&r->run_stats), mean);
+ print_sched_time(r->run_stats.min, 6);
+ printf(" ");
+ print_sched_time((u64) mean, 6);
+ printf(" ");
+ print_sched