linux/tools/perf/util/Build
Jin Yao 9cbfa2f64c perf parse-events: Create two hybrid hardware events
Current hardware events has special perf types PERF_TYPE_HARDWARE.
But it doesn't pass the PMU type in the user interface. For a hybrid
system, the perf kernel doesn't know which PMU the events belong to.

So now this type is extended to be PMU aware type. The PMU type ID
is stored at attr.config[63:32].

PMU type ID is retrieved from sysfs.

  root@lkp-adl-d01:/sys/devices/cpu_atom# cat type
  8

  root@lkp-adl-d01:/sys/devices/cpu_core# cat type
  4

When enabling a hybrid hardware event without specified pmu, such as,
'perf stat -e cycles -a', two events are created automatically. One
is for atom, the other is for core.

  # perf stat -e cycles -a -vv -- sleep 1
  Control descriptor is not initialized
  ------------------------------------------------------------
  perf_event_attr:
    size                             120
    config                           0x400000000
    sample_type                      IDENTIFIER
    read_format                      TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING
    disabled                         1
    inherit                          1
    exclude_guest                    1
  ------------------------------------------------------------
  sys_perf_event_open: pid -1  cpu 0  group_fd -1  flags 0x8 = 3
  ------------------------------------------------------------
  ...
  ------------------------------------------------------------
  perf_event_attr:
    size                             120
    config                           0x400000000
    sample_type                      IDENTIFIER
    read_format                      TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING
    disabled                         1
    inherit                          1
    exclude_guest                    1
  ------------------------------------------------------------
  sys_perf_event_open: pid -1  cpu 15  group_fd -1  flags 0x8 = 19
  ------------------------------------------------------------
  perf_event_attr:
    size                             120
    config                           0x800000000
    sample_type                      IDENTIFIER
    read_format                      TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING
    disabled                         1
    inherit                          1
    exclude_guest                    1
  ------------------------------------------------------------
  sys_perf_event_open: pid -1  cpu 16  group_fd -1  flags 0x8 = 20
  ------------------------------------------------------------
  ...
  ------------------------------------------------------------
  perf_event_attr:
    size                             120
    config                           0x800000000
    sample_type                      IDENTIFIER
    read_format                      TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING
    disabled                         1
    inherit                          1
    exclude_guest                    1
  ------------------------------------------------------------
  sys_perf_event_open: pid -1  cpu 23  group_fd -1  flags 0x8 = 27
  cycles: 0: 836272 1001525722 1001525722
  cycles: 1: 628564 1001580453 1001580453
  cycles: 2: 872693 1001605997 1001605997
  cycles: 3: 70417 1001641369 1001641369
  cycles: 4: 88593 1001726722 1001726722
  cycles: 5: 470495 1001752993 1001752993
  cycles: 6: 484733 1001840440 1001840440
  cycles: 7: 1272477 1001593105 1001593105
  cycles: 8: 209185 1001608616 1001608616
  cycles: 9: 204391 1001633962 1001633962
  cycles: 10: 264121 1001661745 1001661745
  cycles: 11: 826104 1001689904 1001689904
  cycles: 12: 89935 1001728861 1001728861
  cycles: 13: 70639 1001756757 1001756757
  cycles: 14: 185266 1001784810 1001784810
  cycles: 15: 171094 1001825466 1001825466
  cycles: 0: 129624 1001854843 1001854843
  cycles: 1: 122533 1001840421 1001840421
  cycles: 2: 90055 1001882506 1001882506
  cycles: 3: 139607 1001896463 1001896463
  cycles: 4: 141791 1001907838 1001907838
  cycles: 5: 530927 1001883880 1001883880
  cycles: 6: 143246 1001852529 1001852529
  cycles: 7: 667769 1001872626 1001872626
  cycles: 6744979 16026956922 16026956922
  cycles: 1965552 8014991106 8014991106

   Performance counter stats for 'system wide':

           6,744,979      cpu_core/cycles/
           1,965,552      cpu_atom/cycles/

         1.001882711 seconds time elapsed

0x4 in 0x400000000 indicates the cpu_core pmu.
0x8 in 0x800000000 indicates the cpu_atom pmu.

Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Reviewed-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20210427070139.25256-9-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2021-04-29 10:30:59 -03:00

307 lines
9.0 KiB
Plaintext

perf-y += annotate.o
perf-y += block-info.o
perf-y += block-range.o
perf-y += build-id.o
perf-y += cacheline.o
perf-y += config.o
perf-y += copyfile.o
perf-y += ctype.o
perf-y += db-export.o
perf-y += env.o
perf-y += event.o
perf-y += evlist.o
perf-y += sideband_evlist.o
perf-y += evsel.o
perf-y += evsel_fprintf.o
perf-y += perf_event_attr_fprintf.o
perf-y += evswitch.o
perf-y += find_bit.o
perf-y += get_current_dir_name.o
perf-y += kallsyms.o
perf-y += levenshtein.o
perf-y += llvm-utils.o
perf-y += mmap.o
perf-y += memswap.o
perf-y += parse-events.o
perf-y += parse-events-hybrid.o
perf-y += perf_regs.o
perf-y += path.o
perf-y += print_binary.o
perf-y += rlimit.o
perf-y += argv_split.o
perf-y += rbtree.o
perf-y += libstring.o
perf-y += bitmap.o
perf-y += hweight.o
perf-y += smt.o
perf-y += strbuf.o
perf-y += string.o
perf-y += strlist.o
perf-y += strfilter.o
perf-y += top.o
perf-y += usage.o
perf-y += dso.o
perf-y += dsos.o
perf-y += symbol.o
perf-y += symbol_fprintf.o
perf-y += color.o
perf-y += color_config.o
perf-y += metricgroup.o
perf-y += header.o
perf-y += callchain.o
perf-y += values.o
perf-y += debug.o
perf-y += fncache.o
perf-y += machine.o
perf-y += map.o
perf-y += pstack.o
perf-y += session.o
perf-y += sample-raw.o
perf-y += s390-sample-raw.o
perf-$(CONFIG_TRACE) += syscalltbl.o
perf-y += ordered-events.o
perf-y += namespaces.o
perf-y += comm.o
perf-y += thread.o
perf-y += thread_map.o
perf-y += trace-event-parse.o
perf-y += parse-events-flex.o
perf-y += parse-events-bison.o
perf-y += pmu.o
perf-y += pmu-flex.o
perf-y += pmu-bison.o
perf-y += pmu-hybrid.o
perf-y += trace-event-read.o
perf-y += trace-event-info.o
perf-y += trace-event-scripting.o
perf-y += trace-event.o
perf-y += svghelper.o
perf-y += sort.o
perf-y += hist.o
perf-y += util.o
perf-y += cpumap.o
perf-y += affinity.o
perf-y += cputopo.o
perf-y += cgroup.o
perf-y += target.o
perf-y += rblist.o
perf-y += intlist.o
perf-y += vdso.o
perf-y += counts.o
perf-y += stat.o
perf-y += stat-shadow.o
perf-y += stat-display.o
perf-y += perf_api_probe.o
perf-y += record.o
perf-y += srcline.o
perf-y += srccode.o
perf-y += synthetic-events.o
perf-y += data.o
perf-y += tsc.o
perf-y += cloexec.o
perf-y += call-path.o
perf-y += rwsem.o
perf-y += thread-stack.o
perf-y += spark.o
perf-y += topdown.o
perf-y += iostat.o
perf-y += stream.o
perf-$(CONFIG_AUXTRACE) += auxtrace.o
perf-$(CONFIG_AUXTRACE) += intel-pt-decoder/
perf-$(CONFIG_AUXTRACE) += intel-pt.o
perf-$(CONFIG_AUXTRACE) += intel-bts.o
perf-$(CONFIG_AUXTRACE) += arm-spe.o
perf-$(CONFIG_AUXTRACE) += arm-spe-decoder/
perf-$(CONFIG_AUXTRACE) += s390-cpumsf.o
ifdef CONFIG_LIBOPENCSD
perf-$(CONFIG_AUXTRACE) += cs-etm.o
perf-$(CONFIG_AUXTRACE) += cs-etm-decoder/
endif
perf-y += parse-branch-options.o
perf-y += dump-insn.o
perf-y += parse-regs-options.o
perf-y += parse-sublevel-options.o
perf-y += term.o
perf-y += help-unknown-cmd.o
perf-y += mem-events.o
perf-y += vsprintf.o
perf-y += units.o
perf-y += time-utils.o
perf-y += expr-flex.o
perf-y += expr-bison.o
perf-y += expr.o
perf-y += branch.o
perf-y += mem2node.o
perf-y += clockid.o
perf-$(CONFIG_LIBBPF) += bpf-loader.o
perf-$(CONFIG_LIBBPF) += bpf_map.o
perf-$(CONFIG_PERF_BPF_SKEL) += bpf_counter.o
perf-$(CONFIG_BPF_PROLOGUE) += bpf-prologue.o
perf-$(CONFIG_LIBELF) += symbol-elf.o
perf-$(CONFIG_LIBELF) += probe-file.o
perf-$(CONFIG_LIBELF) += probe-event.o
ifndef CONFIG_LIBBPF
perf-y += hashmap.o
endif
ifndef CONFIG_LIBELF
perf-y += symbol-minimal.o
endif
ifndef CONFIG_SETNS
perf-y += setns.o
endif
perf-$(CONFIG_DWARF) += probe-finder.o
perf-$(CONFIG_DWARF) += dwarf-aux.o
perf-$(CONFIG_DWARF) += dwarf-regs.o
perf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
perf-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind-local.o
perf-$(CONFIG_LIBUNWIND) += unwind-libunwind.o
perf-$(CONFIG_LIBUNWIND_X86) += libunwind/x86_32.o
perf-$(CONFIG_LIBUNWIND_AARCH64) += libunwind/arm64.o
perf-$(CONFIG_LIBBABELTRACE) += data-convert-bt.o
perf-y += data-convert-json.o
perf-y += scripting-engines/
perf-$(CONFIG_ZLIB) += zlib.o
perf-$(CONFIG_LZMA) += lzma.o
perf-$(CONFIG_ZSTD) += zstd.o
perf-$(CONFIG_LIBCAP) += cap.o
perf-y += demangle-ocaml.o
perf-y += demangle-java.o
perf-y += demangle-rust.o
ifdef CONFIG_JITDUMP
perf-$(CONFIG_LIBELF) += jitdump.o
perf-$(CONFIG_LIBELF) += genelf.o
perf-$(CONFIG_DWARF) += genelf_debug.o
endif
perf-y += perf-hooks.o
perf-$(CONFIG_LIBBPF) += bpf-event.o
perf-$(CONFIG_CXX) += c++/
perf-$(CONFIG_LIBPFM4) += pfm.o
CFLAGS_config.o += -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
CFLAGS_llvm-utils.o += -DPERF_INCLUDE_DIR="BUILD_STR($(perf_include_dir_SQ))"
# avoid compiler warnings in 32-bit mode
CFLAGS_genelf_debug.o += -Wno-packed
$(OUTPUT)util/parse-events-flex.c $(OUTPUT)util/parse-events-flex.h: util/parse-events.l $(OUTPUT)util/parse-events-bison.c
$(call rule_mkdir)
$(Q)$(call echo-cmd,flex)$(FLEX) -o $(OUTPUT)util/parse-events-flex.c \
--header-file=$(OUTPUT)util/parse-events-flex.h $(PARSER_DEBUG_FLEX) $<
$(OUTPUT)util/parse-events-bison.c $(OUTPUT)util/parse-events-bison.h: util/parse-events.y
$(call rule_mkdir)
$(Q)$(call echo-cmd,bison)$(BISON) -v $< -d $(PARSER_DEBUG_BISON) \
-o $(OUTPUT)util/parse-events-bison.c -p parse_events_
$(OUTPUT)util/expr-flex.c $(OUTPUT)util/expr-flex.h: util/expr.l $(OUTPUT)util/expr-bison.c
$(call rule_mkdir)
$(Q)$(call echo-cmd,flex)$(FLEX) -o $(OUTPUT)util/expr-flex.c \
--header-file=$(OUTPUT)util/expr-flex.h $(PARSER_DEBUG_FLEX) $<
$(OUTPUT)util/expr-bison.c $(OUTPUT)util/expr-bison.h: util/expr.y
$(call rule_mkdir)
$(Q)$(call echo-cmd,bison)$(BISON) -v $< -d $(PARSER_DEBUG_BISON) \
-o $(OUTPUT)util/expr-bison.c -p expr_
$(OUTPUT)util/pmu-flex.c $(OUTPUT)util/pmu-flex.h: util/pmu.l $(OUTPUT)util/pmu-bison.c
$(call rule_mkdir)
$(Q)$(call echo-cmd,flex)$(FLEX) -o $(OUTPUT)util/pmu-flex.c \
--header-file=$(OUTPUT)util/pmu-flex.h $(PARSER_DEBUG_FLEX) $<
$(OUTPUT)util/pmu-bison.c $(OUTPUT)util/pmu-bison.h: util/pmu.y
$(call rule_mkdir)
$(Q)$(call echo-cmd,bison)$(BISON) -v $< -d $(PARSER_DEBUG_BISON) \
-o $(OUTPUT)util/pmu-bison.c -p perf_pmu_
FLEX_GE_26 := $(shell expr $(shell $(FLEX) --version | sed -e 's/flex \([0-9]\+\).\([0-9]\+\)/\1\2/g') \>\= 26)
ifeq ($(FLEX_GE_26),1)
flex_flags := -Wno-switch-enum -Wno-switch-default -Wno-unused-function -Wno-redundant-decls -Wno-sign-compare -Wno-unused-parameter -Wno-missing-prototypes -Wno-missing-declarations
CC_HASNT_MISLEADING_INDENTATION := $(shell echo "int main(void) { return 0 }" | $(CC) -Werror -Wno-misleading-indentation -o /dev/null -xc - 2>&1 | grep -q -- -Wno-misleading-indentation ; echo $$?)
ifeq ($(CC_HASNT_MISLEADING_INDENTATION), 1)
flex_flags += -Wno-misleading-indentation
endif
else
flex_flags := -w
endif
CFLAGS_parse-events-flex.o += $(flex_flags)
CFLAGS_pmu-flex.o += $(flex_flags)
CFLAGS_expr-flex.o += $(flex_flags)
bison_flags := -DYYENABLE_NLS=0
BISON_GE_35 := $(shell expr $(shell $(BISON) --version | grep bison | sed -e 's/.\+ \([0-9]\+\).\([0-9]\+\)/\1\2/g') \>\= 35)
ifeq ($(BISON_GE_35),1)
bison_flags += -Wno-unused-parameter -Wno-nested-externs -Wno-implicit-function-declaration -Wno-switch-enum
else
bison_flags += -w
endif
CFLAGS_parse-events-bison.o += $(bison_flags)
CFLAGS_pmu-bison.o += -DYYLTYPE_IS_TRIVIAL=0 $(bison_flags)
CFLAGS_expr-bison.o += -DYYLTYPE_IS_TRIVIAL=0 $(bison_flags)
$(OUTPUT)util/parse-events.o: $(OUTPUT)util/parse-events-flex.c $(OUTPUT)util/parse-events-bison.c
$(OUTPUT)util/pmu.o: $(OUTPUT)util/pmu-flex.c $(OUTPUT)util/pmu-bison.c
$(OUTPUT)util/expr.o: $(OUTPUT)util/expr-flex.c $(OUTPUT)util/expr-bison.c
CFLAGS_bitmap.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
CFLAGS_find_bit.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
CFLAGS_rbtree.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
CFLAGS_libstring.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
CFLAGS_hweight.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
CFLAGS_parse-events.o += -Wno-redundant-decls
CFLAGS_expr.o += -Wno-redundant-decls
CFLAGS_header.o += -include $(OUTPUT)PERF-VERSION-FILE
$(OUTPUT)util/kallsyms.o: ../lib/symbol/kallsyms.c FORCE
$(call rule_mkdir)
$(call if_changed_dep,cc_o_c)
$(OUTPUT)util/argv_split.o: ../lib/argv_split.c FORCE
$(call rule_mkdir)
$(call if_changed_dep,cc_o_c)
$(OUTPUT)util/bitmap.o: ../lib/bitmap.c FORCE
$(call rule_mkdir)
$(call if_changed_dep,cc_o_c)
$(OUTPUT)util/ctype.o: ../lib/ctype.c FORCE
$(call rule_mkdir)
$(call if_changed_dep,cc_o_c)
$(OUTPUT)util/find_bit.o: ../lib/find_bit.c FORCE
$(call rule_mkdir)
$(call if_changed_dep,cc_o_c)
$(OUTPUT)util/rbtree.o: ../lib/rbtree.c FORCE
$(call rule_mkdir)
$(call if_changed_dep,cc_o_c)
$(OUTPUT)util/libstring.o: ../lib/string.c FORCE
$(call rule_mkdir)
$(call if_changed_dep,cc_o_c)
$(OUTPUT)util/hweight.o: ../lib/hweight.c FORCE
$(call rule_mkdir)
$(call if_changed_dep,cc_o_c)
$(OUTPUT)util/vsprintf.o: ../lib/vsprintf.c FORCE
$(call rule_mkdir)
$(call if_changed_dep,cc_o_c)