diff options
Diffstat (limited to 'tools/perf/util')
50 files changed, 1109 insertions, 725 deletions
diff --git a/tools/perf/util/Build b/tools/perf/util/Build index da64efd8718f..0f18fe81ef0b 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -1,181 +1,181 @@ include $(srctree)/tools/scripts/Makefile.include include $(srctree)/tools/scripts/utilities.mak -perf-y += arm64-frame-pointer-unwind-support.o -perf-y += addr_location.o -perf-y += annotate.o -perf-y += block-info.o -perf-y += block-range.o -perf-y += build-id.o -perf-y += cacheline.o -perf-y += config.o -perf-y += copyfile.o -perf-y += ctype.o -perf-y += db-export.o -perf-y += disasm.o -perf-y += env.o -perf-y += event.o -perf-y += evlist.o -perf-y += sideband_evlist.o -perf-y += evsel.o -perf-y += evsel_fprintf.o -perf-y += perf_event_attr_fprintf.o -perf-y += evswitch.o -perf-y += find_bit.o -perf-y += get_current_dir_name.o -perf-y += levenshtein.o -perf-y += mmap.o -perf-y += memswap.o -perf-y += parse-events.o -perf-y += print-events.o -perf-y += tracepoint.o -perf-y += perf_regs.o -perf-y += perf-regs-arch/ -perf-y += path.o -perf-y += print_binary.o -perf-y += print_insn.o -perf-y += rlimit.o -perf-y += argv_split.o -perf-y += rbtree.o -perf-y += libstring.o -perf-y += bitmap.o -perf-y += hweight.o -perf-y += smt.o -perf-y += strbuf.o -perf-y += string.o -perf-y += strlist.o -perf-y += strfilter.o -perf-y += top.o -perf-y += usage.o -perf-y += dso.o -perf-y += dsos.o -perf-y += symbol.o -perf-y += symbol_fprintf.o -perf-y += map_symbol.o -perf-y += color.o -perf-y += color_config.o -perf-y += metricgroup.o -perf-y += header.o -perf-y += callchain.o -perf-y += values.o -perf-y += debug.o -perf-y += fncache.o -perf-y += machine.o -perf-y += map.o -perf-y += maps.o -perf-y += pstack.o -perf-y += session.o -perf-y += sample-raw.o -perf-y += s390-sample-raw.o -perf-y += amd-sample-raw.o -perf-$(CONFIG_TRACE) += syscalltbl.o -perf-y += ordered-events.o -perf-y += namespaces.o -perf-y += comm.o -perf-y += thread.o -perf-y += threads.o -perf-y += thread_map.o -perf-y += parse-events-flex.o -perf-y += parse-events-bison.o -perf-y += pmu.o -perf-y += pmus.o -perf-y += pmu-flex.o -perf-y += pmu-bison.o -perf-y += svghelper.o -perf-$(CONFIG_LIBTRACEEVENT) += trace-event-info.o -perf-y += trace-event-scripting.o -perf-$(CONFIG_LIBTRACEEVENT) += trace-event.o -perf-$(CONFIG_LIBTRACEEVENT) += trace-event-parse.o -perf-$(CONFIG_LIBTRACEEVENT) += trace-event-read.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-$(CONFIG_AUXTRACE) += hisi-ptt.o -perf-$(CONFIG_AUXTRACE) += hisi-ptt-decoder/ -perf-$(CONFIG_AUXTRACE) += s390-cpumsf.o +perf-util-y += arm64-frame-pointer-unwind-support.o +perf-util-y += addr_location.o +perf-util-y += annotate.o +perf-util-y += block-info.o +perf-util-y += block-range.o +perf-util-y += build-id.o +perf-util-y += cacheline.o +perf-util-y += config.o +perf-util-y += copyfile.o +perf-util-y += ctype.o +perf-util-y += db-export.o +perf-util-y += disasm.o +perf-util-y += env.o +perf-util-y += event.o +perf-util-y += evlist.o +perf-util-y += sideband_evlist.o +perf-util-y += evsel.o +perf-util-y += evsel_fprintf.o +perf-util-y += perf_event_attr_fprintf.o +perf-util-y += evswitch.o +perf-util-y += find_bit.o +perf-util-y += get_current_dir_name.o +perf-util-y += levenshtein.o +perf-util-y += mmap.o +perf-util-y += memswap.o +perf-util-y += parse-events.o +perf-util-y += print-events.o +perf-util-y += tracepoint.o +perf-util-y += perf_regs.o +perf-util-y += perf-regs-arch/ +perf-util-y += path.o +perf-util-y += print_binary.o +perf-util-y += print_insn.o +perf-util-y += rlimit.o +perf-util-y += argv_split.o +perf-util-y += rbtree.o +perf-util-y += libstring.o +perf-util-y += bitmap.o +perf-util-y += hweight.o +perf-util-y += smt.o +perf-util-y += strbuf.o +perf-util-y += string.o +perf-util-y += strlist.o +perf-util-y += strfilter.o +perf-util-y += top.o +perf-util-y += usage.o +perf-util-y += dso.o +perf-util-y += dsos.o +perf-util-y += symbol.o +perf-util-y += symbol_fprintf.o +perf-util-y += map_symbol.o +perf-util-y += color.o +perf-util-y += color_config.o +perf-util-y += metricgroup.o +perf-util-y += header.o +perf-util-y += callchain.o +perf-util-y += values.o +perf-util-y += debug.o +perf-util-y += fncache.o +perf-util-y += machine.o +perf-util-y += map.o +perf-util-y += maps.o +perf-util-y += pstack.o +perf-util-y += session.o +perf-util-y += sample-raw.o +perf-util-y += s390-sample-raw.o +perf-util-y += amd-sample-raw.o +perf-util-$(CONFIG_TRACE) += syscalltbl.o +perf-util-y += ordered-events.o +perf-util-y += namespaces.o +perf-util-y += comm.o +perf-util-y += thread.o +perf-util-y += threads.o +perf-util-y += thread_map.o +perf-util-y += parse-events-flex.o +perf-util-y += parse-events-bison.o +perf-util-y += pmu.o +perf-util-y += pmus.o +perf-util-y += pmu-flex.o +perf-util-y += pmu-bison.o +perf-util-y += svghelper.o +perf-util-$(CONFIG_LIBTRACEEVENT) += trace-event-info.o +perf-util-y += trace-event-scripting.o +perf-util-$(CONFIG_LIBTRACEEVENT) += trace-event.o +perf-util-$(CONFIG_LIBTRACEEVENT) += trace-event-parse.o +perf-util-$(CONFIG_LIBTRACEEVENT) += trace-event-read.o +perf-util-y += sort.o +perf-util-y += hist.o +perf-util-y += util.o +perf-util-y += cpumap.o +perf-util-y += affinity.o +perf-util-y += cputopo.o +perf-util-y += cgroup.o +perf-util-y += target.o +perf-util-y += rblist.o +perf-util-y += intlist.o +perf-util-y += vdso.o +perf-util-y += counts.o +perf-util-y += stat.o +perf-util-y += stat-shadow.o +perf-util-y += stat-display.o +perf-util-y += perf_api_probe.o +perf-util-y += record.o +perf-util-y += srcline.o +perf-util-y += srccode.o +perf-util-y += synthetic-events.o +perf-util-y += data.o +perf-util-y += tsc.o +perf-util-y += cloexec.o +perf-util-y += call-path.o +perf-util-y += rwsem.o +perf-util-y += thread-stack.o +perf-util-y += spark.o +perf-util-y += topdown.o +perf-util-y += iostat.o +perf-util-y += stream.o +perf-util-$(CONFIG_AUXTRACE) += auxtrace.o +perf-util-$(CONFIG_AUXTRACE) += intel-pt-decoder/ +perf-util-$(CONFIG_AUXTRACE) += intel-pt.o +perf-util-$(CONFIG_AUXTRACE) += intel-bts.o +perf-util-$(CONFIG_AUXTRACE) += arm-spe.o +perf-util-$(CONFIG_AUXTRACE) += arm-spe-decoder/ +perf-util-$(CONFIG_AUXTRACE) += hisi-ptt.o +perf-util-$(CONFIG_AUXTRACE) += hisi-ptt-decoder/ +perf-util-$(CONFIG_AUXTRACE) += s390-cpumsf.o ifdef CONFIG_LIBOPENCSD -perf-$(CONFIG_AUXTRACE) += cs-etm.o -perf-$(CONFIG_AUXTRACE) += cs-etm-decoder/ +perf-util-$(CONFIG_AUXTRACE) += cs-etm.o +perf-util-$(CONFIG_AUXTRACE) += cs-etm-decoder/ endif -perf-$(CONFIG_AUXTRACE) += cs-etm-base.o - -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 += dlfilter.o -perf-y += mem-events.o -perf-y += mem-info.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-y += list_sort.o -perf-y += mutex.o -perf-y += sharded_mutex.o - -perf-$(CONFIG_LIBBPF) += bpf_map.o -perf-$(CONFIG_PERF_BPF_SKEL) += bpf_counter.o -perf-$(CONFIG_PERF_BPF_SKEL) += bpf_counter_cgroup.o -perf-$(CONFIG_PERF_BPF_SKEL) += bpf_ftrace.o -perf-$(CONFIG_PERF_BPF_SKEL) += bpf_off_cpu.o -perf-$(CONFIG_PERF_BPF_SKEL) += bpf-filter.o -perf-$(CONFIG_PERF_BPF_SKEL) += bpf-filter-flex.o -perf-$(CONFIG_PERF_BPF_SKEL) += bpf-filter-bison.o +perf-util-$(CONFIG_AUXTRACE) += cs-etm-base.o + +perf-util-y += parse-branch-options.o +perf-util-y += dump-insn.o +perf-util-y += parse-regs-options.o +perf-util-y += parse-sublevel-options.o +perf-util-y += term.o +perf-util-y += help-unknown-cmd.o +perf-util-y += dlfilter.o +perf-util-y += mem-events.o +perf-util-y += mem-info.o +perf-util-y += vsprintf.o +perf-util-y += units.o +perf-util-y += time-utils.o +perf-util-y += expr-flex.o +perf-util-y += expr-bison.o +perf-util-y += expr.o +perf-util-y += branch.o +perf-util-y += mem2node.o +perf-util-y += clockid.o +perf-util-y += list_sort.o +perf-util-y += mutex.o +perf-util-y += sharded_mutex.o + +perf-util-$(CONFIG_LIBBPF) += bpf_map.o +perf-util-$(CONFIG_PERF_BPF_SKEL) += bpf_counter.o +perf-util-$(CONFIG_PERF_BPF_SKEL) += bpf_counter_cgroup.o +perf-util-$(CONFIG_PERF_BPF_SKEL) += bpf_ftrace.o +perf-util-$(CONFIG_PERF_BPF_SKEL) += bpf_off_cpu.o +perf-util-$(CONFIG_PERF_BPF_SKEL) += bpf-filter.o +perf-util-$(CONFIG_PERF_BPF_SKEL) += bpf-filter-flex.o +perf-util-$(CONFIG_PERF_BPF_SKEL) += bpf-filter-bison.o ifeq ($(CONFIG_LIBTRACEEVENT),y) - perf-$(CONFIG_PERF_BPF_SKEL) += bpf_lock_contention.o + perf-util-$(CONFIG_PERF_BPF_SKEL) += bpf_lock_contention.o endif ifeq ($(CONFIG_LIBTRACEEVENT),y) - perf-$(CONFIG_PERF_BPF_SKEL) += bpf_kwork.o - perf-$(CONFIG_PERF_BPF_SKEL) += bpf_kwork_top.o + perf-util-$(CONFIG_PERF_BPF_SKEL) += bpf_kwork.o + perf-util-$(CONFIG_PERF_BPF_SKEL) += bpf_kwork_top.o endif -perf-$(CONFIG_LIBELF) += symbol-elf.o -perf-$(CONFIG_LIBELF) += probe-file.o -perf-$(CONFIG_LIBELF) += probe-event.o +perf-util-$(CONFIG_LIBELF) += symbol-elf.o +perf-util-$(CONFIG_LIBELF) += probe-file.o +perf-util-$(CONFIG_LIBELF) += probe-event.o ifdef CONFIG_LIBBPF_DYNAMIC hashmap := 1 @@ -185,60 +185,60 @@ ifndef CONFIG_LIBBPF endif ifdef hashmap -perf-y += hashmap.o +perf-util-y += hashmap.o endif ifndef CONFIG_LIBELF -perf-y += symbol-minimal.o +perf-util-y += symbol-minimal.o endif ifndef CONFIG_SETNS -perf-y += setns.o +perf-util-y += setns.o endif -perf-$(CONFIG_DWARF) += probe-finder.o -perf-$(CONFIG_DWARF) += dwarf-aux.o -perf-$(CONFIG_DWARF) += dwarf-regs.o -perf-$(CONFIG_DWARF) += debuginfo.o -perf-$(CONFIG_DWARF) += annotate-data.o +perf-util-$(CONFIG_DWARF) += probe-finder.o +perf-util-$(CONFIG_DWARF) += dwarf-aux.o +perf-util-$(CONFIG_DWARF) += dwarf-regs.o +perf-util-$(CONFIG_DWARF) += debuginfo.o +perf-util-$(CONFIG_DWARF) += annotate-data.o -perf-$(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-util-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o +perf-util-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind-local.o +perf-util-$(CONFIG_LIBUNWIND) += unwind-libunwind.o +perf-util-$(CONFIG_LIBUNWIND_X86) += libunwind/x86_32.o +perf-util-$(CONFIG_LIBUNWIND_AARCH64) += libunwind/arm64.o ifeq ($(CONFIG_LIBTRACEEVENT),y) - perf-$(CONFIG_LIBBABELTRACE) += data-convert-bt.o + perf-util-$(CONFIG_LIBBABELTRACE) += data-convert-bt.o endif -perf-y += data-convert-json.o +perf-util-y += data-convert-json.o -perf-y += scripting-engines/ +perf-util-y += scripting-engines/ -perf-$(CONFIG_ZLIB) += zlib.o -perf-$(CONFIG_LZMA) += lzma.o -perf-$(CONFIG_ZSTD) += zstd.o +perf-util-$(CONFIG_ZLIB) += zlib.o +perf-util-$(CONFIG_LZMA) += lzma.o +perf-util-$(CONFIG_ZSTD) += zstd.o -perf-$(CONFIG_LIBCAP) += cap.o +perf-util-$(CONFIG_LIBCAP) += cap.o -perf-$(CONFIG_CXX_DEMANGLE) += demangle-cxx.o -perf-y += demangle-ocaml.o -perf-y += demangle-java.o -perf-y += demangle-rust.o +perf-util-$(CONFIG_CXX_DEMANGLE) += demangle-cxx.o +perf-util-y += demangle-ocaml.o +perf-util-y += demangle-java.o +perf-util-y += demangle-rust.o ifdef CONFIG_JITDUMP -perf-$(CONFIG_LIBELF) += jitdump.o -perf-$(CONFIG_LIBELF) += genelf.o -perf-$(CONFIG_DWARF) += genelf_debug.o +perf-util-$(CONFIG_LIBELF) += jitdump.o +perf-util-$(CONFIG_LIBELF) += genelf.o +perf-util-$(CONFIG_DWARF) += genelf_debug.o endif -perf-y += perf-hooks.o +perf-util-y += perf-hooks.o -perf-$(CONFIG_LIBBPF) += bpf-event.o -perf-$(CONFIG_LIBBPF) += bpf-utils.o +perf-util-$(CONFIG_LIBBPF) += bpf-event.o +perf-util-$(CONFIG_LIBBPF) += bpf-utils.o -perf-$(CONFIG_LIBPFM4) += pfm.o +perf-util-$(CONFIG_LIBPFM4) += pfm.o CFLAGS_config.o += -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))" @@ -403,4 +403,4 @@ $(OUTPUT)%.shellcheck_log: % $(call rule_mkdir) $(Q)$(call echo-cmd,test)shellcheck -a -S warning "$<" > $@ || (cat $@ && rm $@ && false) -perf-y += $(TEST_LOGS) +perf-util-y += $(TEST_LOGS) diff --git a/tools/perf/util/arm-spe-decoder/Build b/tools/perf/util/arm-spe-decoder/Build index f8dae13fc876..960062b3cb9e 100644 --- a/tools/perf/util/arm-spe-decoder/Build +++ b/tools/perf/util/arm-spe-decoder/Build @@ -1 +1 @@ -perf-$(CONFIG_AUXTRACE) += arm-spe-pkt-decoder.o arm-spe-decoder.o +perf-util-$(CONFIG_AUXTRACE) += arm-spe-pkt-decoder.o arm-spe-decoder.o diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c b/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c index a454c6737563..7bf607d0f6d8 100644 --- a/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c +++ b/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c @@ -10,24 +10,11 @@ #include <byteswap.h> #include <linux/bitops.h> #include <stdarg.h> +#include <linux/kernel.h> +#include <asm-generic/unaligned.h> #include "arm-spe-pkt-decoder.h" -#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ -#define le16_to_cpu bswap_16 -#define le32_to_cpu bswap_32 -#define le64_to_cpu bswap_64 -#define memcpy_le64(d, s, n) do { \ - memcpy((d), (s), (n)); \ - *(d) = le64_to_cpu(*(d)); \ -} while (0) -#else -#define le16_to_cpu -#define le32_to_cpu -#define le64_to_cpu -#define memcpy_le64 memcpy -#endif - static const char * const arm_spe_packet_name[] = { [ARM_SPE_PAD] = "PAD", [ARM_SPE_END] = "END", @@ -70,9 +57,9 @@ static int arm_spe_get_payload(const unsigned char *buf, size_t len, switch (payload_len) { case 1: packet->payload = *(uint8_t *)buf; break; - case 2: packet->payload = le16_to_cpu(*(uint16_t *)buf); break; - case 4: packet->payload = le32_to_cpu(*(uint32_t *)buf); break; - case 8: packet->payload = le64_to_cpu(*(uint64_t *)buf); break; + case 2: packet->payload = get_unaligned_le16(buf); break; + case 4: packet->payload = get_unaligned_le32(buf); break; + case 8: packet->payload = get_unaligned_le64(buf); break; default: return ARM_SPE_BAD_PACKET; } diff --git a/tools/perf/util/bpf-filter.c b/tools/perf/util/bpf-filter.c index b51544996046..04f98b6bb291 100644 --- a/tools/perf/util/bpf-filter.c +++ b/tools/perf/util/bpf-filter.c @@ -17,11 +17,11 @@ #define FD(e, x, y) (*(int *)xyarray__entry(e->core.fd, x, y)) -#define __PERF_SAMPLE_TYPE(st, opt) { st, #st, opt } -#define PERF_SAMPLE_TYPE(_st, opt) __PERF_SAMPLE_TYPE(PERF_SAMPLE_##_st, opt) +#define __PERF_SAMPLE_TYPE(tt, st, opt) { tt, #st, opt } +#define PERF_SAMPLE_TYPE(_st, opt) __PERF_SAMPLE_TYPE(PBF_TERM_##_st, PERF_SAMPLE_##_st, opt) static const struct perf_sample_info { - u64 type; + enum perf_bpf_filter_term type; const char *name; const char *option; } sample_table[] = { @@ -44,12 +44,12 @@ static const struct perf_sample_info { PERF_SAMPLE_TYPE(DATA_PAGE_SIZE, "--data-page-size"), }; -static const struct perf_sample_info *get_sample_info(u64 flags) +static const struct perf_sample_info *get_sample_info(enum perf_bpf_filter_term type) { size_t i; for (i = 0; i < ARRAY_SIZE(sample_table); i++) { - if (sample_table[i].type == flags) + if (sample_table[i].type == type) return &sample_table[i]; } return NULL; @@ -59,9 +59,15 @@ static int check_sample_flags(struct evsel *evsel, struct perf_bpf_filter_expr * { const struct perf_sample_info *info; - if (evsel->core.attr.sample_type & expr->sample_flags) + if (expr->term >= PBF_TERM_SAMPLE_START && expr->term <= PBF_TERM_SAMPLE_END && + (evsel->core.attr.sample_type & (1 << (expr->term - PBF_TERM_SAMPLE_START)))) return 0; + if (expr->term == PBF_TERM_UID || expr->term == PBF_TERM_GID) { + /* Not dependent on the sample_type as computed from a BPF helper. */ + return 0; + } + if (expr->op == PBF_OP_GROUP_BEGIN) { struct perf_bpf_filter_expr *group; @@ -72,10 +78,10 @@ static int check_sample_flags(struct evsel *evsel, struct perf_bpf_filter_expr * return 0; } - info = get_sample_info(expr->sample_flags); + info = get_sample_info(expr->term); if (info == NULL) { - pr_err("Error: %s event does not have sample flags %lx\n", - evsel__name(evsel), expr->sample_flags); + pr_err("Error: %s event does not have sample flags %d\n", + evsel__name(evsel), expr->term); return -1; } @@ -105,7 +111,7 @@ int perf_bpf_filter__prepare(struct evsel *evsel) struct perf_bpf_filter_entry entry = { .op = expr->op, .part = expr->part, - .flags = expr->sample_flags, + .term = expr->term, .value = expr->val, }; @@ -122,7 +128,7 @@ int perf_bpf_filter__prepare(struct evsel *evsel) struct perf_bpf_filter_entry group_entry = { .op = group->op, .part = group->part, - .flags = group->sample_flags, + .term = group->term, .value = group->val, }; bpf_map_update_elem(fd, &i, &group_entry, BPF_ANY); @@ -173,7 +179,8 @@ u64 perf_bpf_filter__lost_count(struct evsel *evsel) return skel ? skel->bss->dropped : 0; } -struct perf_bpf_filter_expr *perf_bpf_filter_expr__new(unsigned long sample_flags, int part, +struct perf_bpf_filter_expr *perf_bpf_filter_expr__new(enum perf_bpf_filter_term term, + int part, enum perf_bpf_filter_op op, unsigned long val) { @@ -181,7 +188,7 @@ struct perf_bpf_filter_expr *perf_bpf_filter_expr__new(unsigned long sample_flag expr = malloc(sizeof(*expr)); if (expr != NULL) { - expr->sample_flags = sample_flags; + expr->term = term; expr->part = part; expr->op = op; expr->val = val; diff --git a/tools/perf/util/bpf-filter.h b/tools/perf/util/bpf-filter.h index 7afd159411b8..cd6764442c16 100644 --- a/tools/perf/util/bpf-filter.h +++ b/tools/perf/util/bpf-filter.h @@ -11,14 +11,15 @@ struct perf_bpf_filter_expr { struct list_head groups; enum perf_bpf_filter_op op; int part; - unsigned long sample_flags; + enum perf_bpf_filter_term term; unsigned long val; }; struct evsel; #ifdef HAVE_BPF_SKEL -struct perf_bpf_filter_expr *perf_bpf_filter_expr__new(unsigned long sample_flags, int part, +struct perf_bpf_filter_expr *perf_bpf_filter_expr__new(enum perf_bpf_filter_term term, + int part, enum perf_bpf_filter_op op, unsigned long val); int perf_bpf_filter__parse(struct list_head *expr_head, const char *str); diff --git a/tools/perf/util/bpf-filter.l b/tools/perf/util/bpf-filter.l index d4ff0f1345cd..2a7c839f3fae 100644 --- a/tools/perf/util/bpf-filter.l +++ b/tools/perf/util/bpf-filter.l @@ -9,16 +9,16 @@ #include "bpf-filter.h" #include "bpf-filter-bison.h" -static int sample(unsigned long sample_flag) +static int sample(enum perf_bpf_filter_term term) { - perf_bpf_filter_lval.sample.type = sample_flag; + perf_bpf_filter_lval.sample.term = term; perf_bpf_filter_lval.sample.part = 0; return BFT_SAMPLE; } -static int sample_part(unsigned long sample_flag, int part) +static int sample_part(enum perf_bpf_filter_term term, int part) { - perf_bpf_filter_lval.sample.type = sample_flag; + perf_bpf_filter_lval.sample.term = term; perf_bpf_filter_lval.sample.part = part; return BFT_SAMPLE; } @@ -67,34 +67,36 @@ ident [_a-zA-Z][_a-zA-Z0-9]+ {num_hex} { return value(16); } {space} { } -ip { return sample(PERF_SAMPLE_IP); } -id { return sample(PERF_SAMPLE_ID); } -tid { return sample(PERF_SAMPLE_TID); } -pid { return sample_part(PERF_SAMPLE_TID, 1); } -cpu { return sample(PERF_SAMPLE_CPU); } -time { return sample(PERF_SAMPLE_TIME); } -addr { return sample(PERF_SAMPLE_ADDR); } -period { return sample(PERF_SAMPLE_PERIOD); } -txn { return sample(PERF_SAMPLE_TRANSACTION); } -weight { return sample(PERF_SAMPLE_WEIGHT); } -weight1 { return sample_part(PERF_SAMPLE_WEIGHT_STRUCT, 1); } -weight2 { return sample_part(PERF_SAMPLE_WEIGHT_STRUCT, 2); } -weight3 { return sample_part(PERF_SAMPLE_WEIGHT_STRUCT, 3); } -ins_lat { return sample_part(PERF_SAMPLE_WEIGHT_STRUCT, 2); } /* alias for weight2 */ -p_stage_cyc { return sample_part(PERF_SAMPLE_WEIGHT_STRUCT, 3); } /* alias for weight3 */ -retire_lat { return sample_part(PERF_SAMPLE_WEIGHT_STRUCT, 3); } /* alias for weight3 */ -phys_addr { return sample(PERF_SAMPLE_PHYS_ADDR); } -code_pgsz { return sample(PERF_SAMPLE_CODE_PAGE_SIZE); } -data_pgsz { return sample(PERF_SAMPLE_DATA_PAGE_SIZE); } -mem_op { return sample_part(PERF_SAMPLE_DATA_SRC, 1); } -mem_lvlnum { return sample_part(PERF_SAMPLE_DATA_SRC, 2); } -mem_lvl { return sample_part(PERF_SAMPLE_DATA_SRC, 2); } /* alias for mem_lvlnum */ -mem_snoop { return sample_part(PERF_SAMPLE_DATA_SRC, 3); } /* include snoopx */ -mem_remote { return sample_part(PERF_SAMPLE_DATA_SRC, 4); } -mem_lock { return sample_part(PERF_SAMPLE_DATA_SRC, 5); } -mem_dtlb { return sample_part(PERF_SAMPLE_DATA_SRC, 6); } -mem_blk { return sample_part(PERF_SAMPLE_DATA_SRC, 7); } -mem_hops { return sample_part(PERF_SAMPLE_DATA_SRC, 8); } +ip { return sample(PBF_TERM_IP); } +id { return sample(PBF_TERM_ID); } +tid { return sample(PBF_TERM_TID); } +pid { return sample_part(PBF_TERM_TID, 1); } +cpu { return sample(PBF_TERM_CPU); } +time { return sample(PBF_TERM_TIME); } +addr { return sample(PBF_TERM_ADDR); } +period { return sample(PBF_TERM_PERIOD); } +txn { return sample(PBF_TERM_TRANSACTION); } +weight { return sample(PBF_TERM_WEIGHT); } +weight1 { return sample_part(PBF_TERM_WEIGHT_STRUCT, 1); } +weight2 { return sample_part(PBF_TERM_WEIGHT_STRUCT, 2); } +weight3 { return sample_part(PBF_TERM_WEIGHT_STRUCT, 3); } +ins_lat { return sample_part(PBF_TERM_WEIGHT_STRUCT, 2); } /* alias for weight2 */ +p_stage_cyc { return sample_part(PBF_TERM_WEIGHT_STRUCT, 3); } /* alias for weight3 */ +retire_lat { return sample_part(PBF_TERM_WEIGHT_STRUCT, 3); } /* alias for weight3 */ +phys_addr { return sample(PBF_TERM_PHYS_ADDR); } +code_pgsz { return sample(PBF_TERM_CODE_PAGE_SIZE); } +data_pgsz { return sample(PBF_TERM_DATA_PAGE_SIZE); } +mem_op { return sample_part(PBF_TERM_DATA_SRC, 1); } +mem_lvlnum { return sample_part(PBF_TERM_DATA_SRC, 2); } +mem_lvl { return sample_part(PBF_TERM_DATA_SRC, 2); } /* alias for mem_lvlnum */ +mem_snoop { return sample_part(PBF_TERM_DATA_SRC, 3); } /* include snoopx */ +mem_remote { return sample_part(PBF_TERM_DATA_SRC, 4); } +mem_lock { return sample_part(PBF_TERM_DATA_SRC, 5); } +mem_dtlb { return sample_part(PBF_TERM_DATA_SRC, 6); } +mem_blk { return sample_part(PBF_TERM_DATA_SRC, 7); } +mem_hops { return sample_part(PBF_TERM_DATA_SRC, 8); } +uid { return sample(PBF_TERM_UID); } +gid { return sample(PBF_TERM_GID); } "==" { return operator(PBF_OP_EQ); } "!=" { return operator(PBF_OP_NEQ); } diff --git a/tools/perf/util/bpf-filter.y b/tools/perf/util/bpf-filter.y index 0e4d6de3c2ad..0c56fccb8874 100644 --- a/tools/perf/util/bpf-filter.y +++ b/tools/perf/util/bpf-filter.y @@ -27,7 +27,7 @@ static void perf_bpf_filter_error(struct list_head *expr __maybe_unused, { unsigned long num; struct { - unsigned long type; + enum perf_bpf_filter_term term; int part; } sample; enum perf_bpf_filter_op op; @@ -62,7 +62,8 @@ filter_term BFT_LOGICAL_OR filter_expr if ($1->op == PBF_OP_GROUP_BEGIN) { expr = $1; } else { - expr = perf_bpf_filter_expr__new(0, 0, PBF_OP_GROUP_BEGIN, 1); + expr = perf_bpf_filter_expr__new(PBF_TERM_NONE, /*part=*/0, + PBF_OP_GROUP_BEGIN, /*val=*/1); list_add_tail(&$1->list, &expr->groups); } expr->val++; @@ -78,7 +79,7 @@ filter_expr filter_expr: BFT_SAMPLE BFT_OP BFT_NUM { - $$ = perf_bpf_filter_expr__new($1.type, $1.part, $2, $3); + $$ = perf_bpf_filter_expr__new($1.term, $1.part, $2, $3); } %% diff --git a/tools/perf/util/bpf_skel/sample-filter.h b/tools/perf/util/bpf_skel/sample-filter.h index 2e96e1ab084a..350efa121026 100644 --- a/tools/perf/util/bpf_skel/sample-filter.h +++ b/tools/perf/util/bpf_skel/sample-filter.h @@ -16,12 +16,48 @@ enum perf_bpf_filter_op { PBF_OP_GROUP_END, }; +enum perf_bpf_filter_term { + /* No term is in use. */ + PBF_TERM_NONE = 0, + /* Terms that correspond to PERF_SAMPLE_xx values. */ + PBF_TERM_SAMPLE_START = PBF_TERM_NONE + 1, + PBF_TERM_IP = PBF_TERM_SAMPLE_START + 0, /* SAMPLE_IP = 1U << 0 */ + PBF_TERM_TID = PBF_TERM_SAMPLE_START + 1, /* SAMPLE_TID = 1U << 1 */ + PBF_TERM_TIME = PBF_TERM_SAMPLE_START + 2, /* SAMPLE_TIME = 1U << 2 */ + PBF_TERM_ADDR = PBF_TERM_SAMPLE_START + 3, /* SAMPLE_ADDR = 1U << 3 */ + __PBF_UNUSED_TERM4 = PBF_TERM_SAMPLE_START + 4, /* SAMPLE_READ = 1U << 4 */ + __PBF_UNUSED_TERM5 = PBF_TERM_SAMPLE_START + 5, /* SAMPLE_CALLCHAIN = 1U << 5 */ + PBF_TERM_ID = PBF_TERM_SAMPLE_START + 6, /* SAMPLE_ID = 1U << 6 */ + PBF_TERM_CPU = PBF_TERM_SAMPLE_START + 7, /* SAMPLE_CPU = 1U << 7 */ + PBF_TERM_PERIOD = PBF_TERM_SAMPLE_START + 8, /* SAMPLE_PERIOD = 1U << 8 */ + __PBF_UNUSED_TERM9 = PBF_TERM_SAMPLE_START + 9, /* SAMPLE_STREAM_ID = 1U << 9 */ + __PBF_UNUSED_TERM10 = PBF_TERM_SAMPLE_START + 10, /* SAMPLE_RAW = 1U << 10 */ + __PBF_UNUSED_TERM11 = PBF_TERM_SAMPLE_START + 11, /* SAMPLE_BRANCH_STACK = 1U << 11 */ + __PBF_UNUSED_TERM12 = PBF_TERM_SAMPLE_START + 12, /* SAMPLE_REGS_USER = 1U << 12 */ + __PBF_UNUSED_TERM13 = PBF_TERM_SAMPLE_START + 13, /* SAMPLE_STACK_USER = 1U << 13 */ + PBF_TERM_WEIGHT = PBF_TERM_SAMPLE_START + 14, /* SAMPLE_WEIGHT = 1U << 14 */ + PBF_TERM_DATA_SRC = PBF_TERM_SAMPLE_START + 15, /* SAMPLE_DATA_SRC = 1U << 15 */ + __PBF_UNUSED_TERM16 = PBF_TERM_SAMPLE_START + 16, /* SAMPLE_IDENTIFIER = 1U << 16 */ + PBF_TERM_TRANSACTION = PBF_TERM_SAMPLE_START + 17, /* SAMPLE_TRANSACTION = 1U << 17 */ + __PBF_UNUSED_TERM18 = PBF_TERM_SAMPLE_START + 18, /* SAMPLE_REGS_INTR = 1U << 18 */ + PBF_TERM_PHYS_ADDR = PBF_TERM_SAMPLE_START + 19, /* SAMPLE_PHYS_ADDR = 1U << 19 */ + __PBF_UNUSED_TERM20 = PBF_TERM_SAMPLE_START + 20, /* SAMPLE_AUX = 1U << 20 */ + __PBF_UNUSED_TERM21 = PBF_TERM_SAMPLE_START + 21, /* SAMPLE_CGROUP = 1U << 21 */ + PBF_TERM_DATA_PAGE_SIZE = PBF_TERM_SAMPLE_START + 22, /* SAMPLE_DATA_PAGE_SIZE = 1U << 22 */ + PBF_TERM_CODE_PAGE_SIZE = PBF_TERM_SAMPLE_START + 23, /* SAMPLE_CODE_PAGE_SIZE = 1U << 23 */ + PBF_TERM_WEIGHT_STRUCT = PBF_TERM_SAMPLE_START + 24, /* SAMPLE_WEIGHT_STRUCT = 1U << 24 */ + PBF_TERM_SAMPLE_END = PBF_TERM_WEIGHT_STRUCT, + /* Terms computed from BPF helpers. */ + PBF_TERM_UID, + PBF_TERM_GID, +}; + /* BPF map entry for filtering */ struct perf_bpf_filter_entry { enum perf_bpf_filter_op op; __u32 part; /* sub-sample type info when it has multiple values */ - __u64 flags; /* perf sample type flags */ + enum perf_bpf_filter_term term; __u64 value; }; -#endif /* PERF_UTIL_BPF_SKEL_SAMPLE_FILTER_H */
\ No newline at end of file +#endif /* PERF_UTIL_BPF_SKEL_SAMPLE_FILTER_H */ diff --git a/tools/perf/util/bpf_skel/sample_filter.bpf.c b/tools/perf/util/bpf_skel/sample_filter.bpf.c index fb94f5280626..f59985101973 100644 --- a/tools/perf/util/bpf_skel/sample_filter.bpf.c +++ b/tools/perf/util/bpf_skel/sample_filter.bpf.c @@ -48,31 +48,54 @@ static inline __u64 perf_get_sample(struct bpf_perf_event_data_kern *kctx, { struct perf_sample_data___new *data = (void *)kctx->data; - if (!bpf_core_field_exists(data->sample_flags) || - (data->sample_flags & entry->flags) == 0) + if (!bpf_core_field_exists(data->sample_flags)) return 0; - switch (entry->flags) { - case PERF_SAMPLE_IP: +#define BUILD_CHECK_SAMPLE(x) \ + _Static_assert((1 << (PBF_TERM_##x - PBF_TERM_SAMPLE_START)) == PERF_SAMPLE_##x, \ + "Mismatched PBF term to sample bit " #x) + BUILD_CHECK_SAMPLE(IP); + BUILD_CHECK_SAMPLE(TID); + BUILD_CHECK_SAMPLE(TIME); + BUILD_CHECK_SAMPLE(ADDR); + BUILD_CHECK_SAMPLE(ID); + BUILD_CHECK_SAMPLE(CPU); + BUILD_CHECK_SAMPLE(PERIOD); + BUILD_CHECK_SAMPLE(WEIGHT); + BUILD_CHECK_SAMPLE(DATA_SRC); + BUILD_CHECK_SAMPLE(TRANSACTION); + BUILD_CHECK_SAMPLE(PHYS_ADDR); + BUILD_CHECK_SAMPLE(DATA_PAGE_SIZE); + BUILD_CHECK_SAMPLE(CODE_PAGE_SIZE); + BUILD_CHECK_SAMPLE(WEIGHT_STRUCT); +#undef BUILD_CHECK_SAMPLE + + /* For sample terms check the sample bit is set. */ + if (entry->term >= PBF_TERM_SAMPLE_START && entry->term <= PBF_TERM_SAMPLE_END && + (data->sample_flags & (1 << (entry->term - PBF_TERM_SAMPLE_START))) == 0) + return 0; + + switch (entry->term) { + case PBF_TERM_IP: return kctx->data->ip; - case PERF_SAMPLE_ID: + case PBF_TERM_ID: return kctx->data->id; - case PERF_SAMPLE_TID: + case PBF_TERM_TID: if (entry->part) return kctx->data->tid_entry.pid; else return kctx->data->tid_entry.tid; - case PERF_SAMPLE_CPU: + case PBF_TERM_CPU: return kctx->data->cpu_entry.cpu; - case PERF_SAMPLE_TIME: + case PBF_TERM_TIME: return kctx->data->time; - case PERF_SAMPLE_ADDR: + case PBF_TERM_ADDR: return kctx->data->addr; - case PERF_SAMPLE_PERIOD: + case PBF_TERM_PERIOD: return kctx->data->period; - case PERF_SAMPLE_TRANSACTION: + case PBF_TERM_TRANSACTION: return kctx->data->txn; - case PERF_SAMPLE_WEIGHT_STRUCT: + case PBF_TERM_WEIGHT_STRUCT: if (entry->part == 1) return kctx->data->weight.var1_dw; if (entry->part == 2) @@ -80,15 +103,15 @@ static inline __u64 perf_get_sample(struct bpf_perf_event_data_kern *kctx, if (entry->part == 3) return kctx->data->weight.var3_w; /* fall through */ - case PERF_SAMPLE_WEIGHT: + case PBF_TERM_WEIGHT: return kctx->data->weight.full; - case PERF_SAMPLE_PHYS_ADDR: + case PBF_TERM_PHYS_ADDR: return kctx->data->phys_addr; - case PERF_SAMPLE_CODE_PAGE_SIZE: + case PBF_TERM_CODE_PAGE_SIZE: return kctx->data->code_page_size; - case PERF_SAMPLE_DATA_PAGE_SIZE: + case PBF_TERM_DATA_PAGE_SIZE: return kctx->data->data_page_size; - case PERF_SAMPLE_DATA_SRC: + case PBF_TERM_DATA_SRC: if (entry->part == 1) return kctx->data->data_src.mem_op; if (entry->part == 2) @@ -117,6 +140,22 @@ static inline __u64 perf_get_sample(struct bpf_perf_event_data_kern *kctx, } /* return the whole word */ return kctx->data->data_src.val; + case PBF_TERM_UID: + return bpf_get_current_uid_gid() & 0xFFFFFFFF; + case PBF_TERM_GID: + return bpf_get_current_uid_gid() >> 32; + case PBF_TERM_NONE: + case __PBF_UNUSED_TERM4: + case __PBF_UNUSED_TERM5: + case __PBF_UNUSED_TERM9: + case __PBF_UNUSED_TERM10: + case __PBF_UNUSED_TERM11: + case __PBF_UNUSED_TERM12: + case __PBF_UNUSED_TERM13: + case __PBF_UNUSED_TERM16: + case __PBF_UNUSED_TERM18: + case __PBF_UNUSED_TERM20: + case __PBF_UNUSED_TERM21: default: break; } diff --git a/tools/perf/util/comm.c b/tools/perf/util/comm.c index 233f2b6edf52..49b79cf0c5cc 100644 --- a/tools/perf/util/comm.c +++ b/tools/perf/util/comm.c @@ -86,14 +86,6 @@ static struct comm_str *comm_str__new(const char *str) return result; } -static int comm_str__cmp(const void *_lhs, const void *_rhs) -{ - const struct comm_str *lhs = *(const struct comm_str * const *)_lhs; - const struct comm_str *rhs = *(const struct comm_str * const *)_rhs; - - return strcmp(comm_str__str(lhs), comm_str__str(rhs)); -} - static int comm_str__search(const void *_key, const void *_member) { const char *key = _key; @@ -169,9 +161,24 @@ static struct comm_str *comm_strs__findnew(const char *str) } result = comm_str__new(str); if (result) { - comm_strs->strs[comm_strs->num_strs++] = result; - qsort(comm_strs->strs, comm_strs->num_strs, sizeof(struct comm_str *), - comm_str__cmp); + int low = 0, high = comm_strs->num_strs - 1; + int insert = comm_strs->num_strs; /* Default to inserting at the end. */ + + while (low <= high) { + int mid = low + (high - low) / 2; + int cmp = strcmp(comm_str__str(comm_strs->strs[mid]), str); + + if (cmp < 0) { + low = mid + 1; + } else { + high = mid - 1; + insert = mid; + } + } + memmove(&comm_strs->strs[insert + 1], &comm_strs->strs[insert], + (comm_strs->num_strs - insert) * sizeof(struct comm_str *)); + comm_strs->num_strs++; + comm_strs->strs[insert] = result; } } up_write(&comm_strs->lock); diff --git a/tools/perf/util/cs-etm-decoder/Build b/tools/perf/util/cs-etm-decoder/Build index 216cb17a3322..056d665f7f88 100644 --- a/tools/perf/util/cs-etm-decoder/Build +++ b/tools/perf/util/cs-etm-decoder/Build @@ -1 +1 @@ -perf-$(CONFIG_AUXTRACE) += cs-etm-decoder.o +perf-util-$(CONFIG_AUXTRACE) += cs-etm-decoder.o diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 32818bd7cd17..5e9fbcfad7d4 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -1013,7 +1013,7 @@ static u32 cs_etm__mem_access(struct cs_etm_queue *etmq, u8 trace_chan_id, if (!dso) goto out; - if (dso->data.status == DSO_DATA_STATUS_ERROR && + if (dso__data(dso)->status == DSO_DATA_STATUS_ERROR && dso__data_status_seen(dso, DSO_DATA_STATUS_SEEN_ITRACE)) goto out; @@ -1027,11 +1027,11 @@ static u32 cs_etm__mem_access(struct cs_etm_queue *etmq, u8 trace_chan_id, if (len <= 0) { ui__warning_once("CS ETM Trace: Missing DSO. Use 'perf archive' or debuginfod to export data from the traced system.\n" " Enable CONFIG_PROC_KCORE or use option '-k /path/to/vmlinux' for kernel symbols.\n"); - if (!dso->auxtrace_warned) { + if (!dso__auxtrace_warned(dso)) { pr_err("CS ETM Trace: Debug data not found for address %#"PRIx64" in %s\n", - address, - dso->long_name ? dso->long_name : "Unknown"); - dso->auxtrace_warned = true; + address, + dso__long_name(dso) ? dso__long_name(dso) : "Unknown"); + dso__set_auxtrace_warned(dso); } goto out; } diff --git a/tools/perf/util/disasm.c b/tools/perf/util/disasm.c index 72aec8f61b94..e10558b79504 100644 --- a/tools/perf/util/disasm.c +++ b/tools/perf/util/disasm.c @@ -1199,7 +1199,7 @@ static int symbol__disassemble_bpf(struct symbol *sym, int ret; FILE *s; - if (dso->binary_type != DSO_BINARY_TYPE__BPF_PROG_INFO) + if (dso__binary_type(dso) != DSO_BINARY_TYPE__BPF_PROG_INFO) return SYMBOL_ANNOTATE_ERRNO__BPF_INVALID_FILE; pr_debug("%s: handling sym %s addr %" PRIx64 " len %" PRIx64 "\n", __func__, @@ -1226,14 +1226,14 @@ static int symbol__disassemble_bpf(struct symbol *sym, info.arch = bfd_get_arch(bfdf); info.mach = bfd_get_mach(bfdf); - info_node = perf_env__find_bpf_prog_info(dso->bpf_prog.env, - dso->bpf_prog.id); + info_node = perf_env__find_bpf_prog_info(dso__bpf_prog(dso)->env, + dso__bpf_prog(dso)->id); if (!info_node) { ret = SYMBOL_ANNOTATE_ERRNO__BPF_MISSING_BTF; goto out; } info_linear = info_node->info_linear; - sub_id = dso->bpf_prog.sub_id; + sub_id = dso__bpf_prog(dso)->sub_id; info.buffer = (void *)(uintptr_t)(info_linear->info.jited_prog_insns); info.buffer_length = info_linear->info.jited_prog_len; @@ -1244,7 +1244,7 @@ static int symbol__disassemble_bpf(struct symbol *sym, if (info_linear->info.btf_id) { struct btf_node *node; - node = perf_env__find_btf(dso->bpf_prog.env, + node = perf_env__find_btf(dso__bpf_prog(dso)->env, info_linear->info.btf_id); if (node) btf = btf__new((__u8 *)(node->data), diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index dde706b71da7..2340c4f6d0c2 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -1652,3 +1652,15 @@ int dso__strerror_load(struct dso *dso, char *buf, size_t buflen) scnprintf(buf, buflen, "%s", dso_load__error_str[idx]); return 0; } + +bool perf_pid_map_tid(const char *dso_name, int *tid) +{ + return sscanf(dso_name, "/tmp/perf-%d.map", tid) == 1; +} + +bool is_perf_pid_map_name(const char *dso_name) +{ + int tid; + + return perf_pid_map_tid(dso_name, &tid); +} diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h index df2c98402af3..878c1f441868 100644 --- a/tools/perf/util/dso.h +++ b/tools/perf/util/dso.h @@ -280,6 +280,16 @@ static inline void dso__set_annotate_warned(struct dso *dso) RC_CHK_ACCESS(dso)->annotate_warned = 1; } +static inline bool dso__auxtrace_warned(const struct dso *dso) +{ + return RC_CHK_ACCESS(dso)->auxtrace_warned; +} + +static inline void dso__set_auxtrace_warned(struct dso *dso) +{ + RC_CHK_ACCESS(dso)->auxtrace_warned = 1; +} + static inline struct auxtrace_cache *dso__auxtrace_cache(struct dso *dso) { return RC_CHK_ACCESS(dso)->auxtrace_cache; @@ -809,4 +819,8 @@ void reset_fd_limit(void); u64 dso__find_global_type(struct dso *dso, u64 addr); u64 dso__findnew_global_type(struct dso *dso, u64 addr, u64 offset); +/* Check if dso name is of format "/tmp/perf-%d.map" */ +bool perf_pid_map_tid(const char *dso_name, int *tid); +bool is_perf_pid_map_name(const char *dso_name); + #endif /* __PERF_DSO */ diff --git a/tools/perf/util/dsos.c b/tools/perf/util/dsos.c index ab3d0c01dd63..d4acdb37f046 100644 --- a/tools/perf/util/dsos.c +++ b/tools/perf/util/dsos.c @@ -164,6 +164,9 @@ static struct dso *__dsos__find_by_longname_id(struct dsos *dsos, }; struct dso **res; + if (dsos->dsos == NULL) + return NULL; + if (!dsos->sorted) { if (!write_locked) { struct dso *dso; @@ -203,11 +206,27 @@ int __dsos__add(struct dsos *dsos, struct dso *dso) dsos->dsos = temp; dsos->allocated = to_allocate; } - dsos->dsos[dsos->cnt++] = dso__get(dso); - if (dsos->cnt >= 2 && dsos->sorted) { - dsos->sorted = dsos__cmp_long_name_id_short_name(&dsos->dsos[dsos->cnt - 2], - &dsos->dsos[dsos->cnt - 1]) - <= 0; + if (!dsos->sorted) { + dsos->dsos[dsos->cnt++] = dso__get(dso); + } else { + int low = 0, high = dsos->cnt - 1; + int insert = dsos->cnt; /* Default to inserting at the end. */ + + while (low <= high) { + int mid = low + (high - low) / 2; + int cmp = dsos__cmp_long_name_id_short_name(&dsos->dsos[mid], &dso); + + if (cmp < 0) { + low = mid + 1; + } else { + high = mid - 1; + insert = mid; + } + } + memmove(&dsos->dsos[insert + 1], &dsos->dsos[insert], + (dsos->cnt - insert) * sizeof(struct dso *)); + dsos->cnt++; + dsos->dsos[insert] = dso__get(dso); } dso__set_dsos(dso, dsos); return 0; @@ -275,7 +294,7 @@ static void dso__set_basename(struct dso *dso) char *base, *lname; int tid; - if (sscanf(dso__long_name(dso), "/tmp/perf-%d.map", &tid) == 1) { + if (perf_pid_map_tid(dso__long_name(dso), &tid)) { if (asprintf(&base, "[JIT] tid %d", tid) < 0) return; } else { diff --git a/tools/perf/util/events_stats.h b/tools/perf/util/events_stats.h index 8fecc9fbaecc..f43e5b1a366a 100644 --- a/tools/perf/util/events_stats.h +++ b/tools/perf/util/events_stats.h @@ -52,7 +52,6 @@ struct hists_stats { void events_stats__inc(struct events_stats *stats, u32 type); -size_t events_stats__fprintf(struct events_stats *stats, FILE *fp, - bool skip_empty); +size_t events_stats__fprintf(struct events_stats *stats, FILE *fp); #endif /* __PERF_EVENTS_STATS_ */ diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 4f818ab6b662..bc603193c477 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -10,6 +10,7 @@ #include <errno.h> #include <inttypes.h> #include <linux/bitops.h> +#include <api/io.h> #include <api/fs/fs.h> #include <api/fs/tracing_path.h> #include <linux/hw_breakpoint.h> @@ -30,6 +31,7 @@ #include "counts.h" #include "event.h" #include "evsel.h" +#include "time-utils.h" #include "util/env.h" #include "util/evsel_config.h" #include "util/evsel_fprintf.h" @@ -53,6 +55,7 @@ #include "../perf-sys.h" #include "util/parse-branch-options.h" #include "util/bpf-filter.h" +#include "util/hist.h" #include <internal/xyarray.h> #include <internal/lib.h> #include <internal/threadmap.h> @@ -830,16 +833,22 @@ const char *evsel__group_name(struct evsel *evsel) int evsel__group_desc(struct evsel *evsel, char *buf, size_t size) { int ret = 0; + bool first = true; struct evsel *pos; const char *group_name = evsel__group_name(evsel); if (!evsel->forced_leader) ret = scnprintf(buf, size, "%s { ", group_name); - ret += scnprintf(buf + ret, size - ret, "%s", evsel__name(evsel)); + for_each_group_evsel(pos, evsel) { + if (symbol_conf.skip_empty && + evsel__hists(pos)->stats.nr_samples == 0) + continue; - for_each_group_member(pos, evsel) - ret += scnprintf(buf + ret, size - ret, ", %s", evsel__name(pos)); + ret += scnprintf(buf + ret, size - ret, "%s%s", + first ? "" : ", ", evsel__name(pos)); + first = false; + } if (!evsel->forced_leader) ret += scnprintf(buf + ret, size - ret, " }"); @@ -1493,6 +1502,9 @@ void evsel__exit(struct evsel *evsel) evsel->per_pkg_mask = NULL; zfree(&evsel->metric_events); perf_evsel__object.fini(evsel); + if (evsel->tool_event == PERF_TOOL_SYSTEM_TIME || + evsel->tool_event == PERF_TOOL_USER_TIME) + xyarray__delete(evsel->start_times); } void evsel__delete(struct evsel *evsel) @@ -1606,11 +1618,173 @@ static int evsel__read_group(struct evsel *leader, int cpu_map_idx, int thread) return evsel__process_group_data(leader, cpu_map_idx, thread, data); } +static bool read_until_char(struct io *io, char e) +{ + int c; + + do { + c = io__get_char(io); + if (c == -1) + return false; + } while (c != e); + return true; +} + +static int read_stat_field(int fd, struct perf_cpu cpu, int field, __u64 *val) +{ + char buf[256]; + struct io io; + int i; + + io__init(&io, fd, buf, sizeof(buf)); + + /* Skip lines to relevant CPU. */ + for (i = -1; i < cpu.cpu; i++) { + if (!read_until_char(&io, '\n')) + return -EINVAL; + } + /* Skip to "cpu". */ + if (io__get_char(&io) != 'c') return -EINVAL; + if (io__get_char(&io) != 'p') return -EINVAL; + if (io__get_char(&io) != 'u') return -EINVAL; + + /* Skip N of cpuN. */ + if (!read_until_char(&io, ' ')) + return -EINVAL; + + i = 1; + while (true) { + if (io__get_dec(&io, val) != ' ') + break; + if (field == i) + return 0; + i++; + } + return -EINVAL; +} + +static int read_pid_stat_field(int fd, int field, __u64 *val) +{ + char buf[256]; + struct io io; + int c, i; + + io__init(&io, fd, buf, sizeof(buf)); + if (io__get_dec(&io, val) != ' ') + return -EINVAL; + if (field == 1) + return 0; + + /* Skip comm. */ + if (io__get_char(&io) != '(' || !read_until_char(&io, ')')) + return -EINVAL; + if (field == 2) + return -EINVAL; /* String can't be returned. */ + + /* Skip state */ + if (io__get_char(&io) != ' ' || io__get_char(&io) == -1) + return -EINVAL; + if (field == 3) + return -EINVAL; /* String can't be returned. */ + + /* Loop over numeric fields*/ + if (io__get_char(&io) != ' ') + return -EINVAL; + + i = 4; + while (true) { + c = io__get_dec(&io, val); + if (c == -1) + return -EINVAL; + if (c == -2) { + /* Assume a -ve was read */ + c = io__get_dec(&io, val); + *val *= -1; + } + if (c != ' ') + return -EINVAL; + if (field == i) + return 0; + i++; + } + return -EINVAL; +} + +static int evsel__read_tool(struct evsel *evsel, int cpu_map_idx, int thread) +{ + __u64 *start_time, cur_time, delta_start; + int fd, err = 0; + struct perf_counts_values *count; + bool adjust = false; + + count = perf_counts(evsel->counts, cpu_map_idx, thread); + + switch (evsel->tool_event) { + case PERF_TOOL_DURATION_TIME: + /* + * Pretend duration_time is only on the first CPU and thread, or + * else aggregation will scale duration_time by the number of + * CPUs/threads. + */ + start_time = &evsel->start_time; + if (cpu_map_idx == 0 && thread == 0) + cur_time = rdclock(); + else + cur_time = *start_time; + break; + case PERF_TOOL_USER_TIME: + case PERF_TOOL_SYSTEM_TIME: { + bool system = evsel->tool_event == PERF_TOOL_SYSTEM_TIME; + + start_time = xyarray__entry(evsel->start_times, cpu_map_idx, thread); + fd = FD(evsel, cpu_map_idx, thread); + lseek(fd, SEEK_SET, 0); + if (evsel->pid_stat) { + /* The event exists solely on 1 CPU. */ + if (cpu_map_idx == 0) + err = read_pid_stat_field(fd, system ? 15 : 14, &cur_time); + else + cur_time = 0; + } else { + /* The event is for all threads. */ + if (thread == 0) { + struct perf_cpu cpu = perf_cpu_map__cpu(evsel->core.cpus, + cpu_map_idx); + + err = read_stat_field(fd, cpu, system ? 3 : 1, &cur_time); + } else { + cur_time = 0; + } + } + adjust = true; + break; + } + case PERF_TOOL_NONE: + case PERF_TOOL_MAX: + default: + err = -EINVAL; + } + if (err) + return err; + + delta_start = cur_time - *start_time; + if (adjust) { + __u64 ticks_per_sec = sysconf(_SC_CLK_TCK); + + delta_start *= 1000000000 / ticks_per_sec; + } + count->val = delta_start; + count->ena = count->run = delta_start; + count->lost = 0; + return 0; +} + int evsel__read_counter(struct evsel *evsel, int cpu_map_idx, int thread) { - u64 read_format = evsel->core.attr.read_format; + if (evsel__is_tool(evsel)) + return evsel__read_tool(evsel, cpu_map_idx, thread); - if (read_format & PERF_FORMAT_GROUP) + if (evsel->core.attr.read_format & PERF_FORMAT_GROUP) return evsel__read_group(evsel, cpu_map_idx, thread); return evsel__read_one(evsel, cpu_map_idx, thread); @@ -1829,6 +2003,14 @@ static int __evsel__prepare_open(struct evsel *evsel, struct perf_cpu_map *cpus, perf_evsel__alloc_fd(&evsel->core, perf_cpu_map__nr(cpus), nthreads) < 0) return -ENOMEM; + if ((evsel->tool_event == PERF_TOOL_SYSTEM_TIME || + evsel->tool_event == PERF_TOOL_USER_TIME) && + !evsel->start_times) { + evsel->start_times = xyarray__new(perf_cpu_map__nr(cpus), nthreads, sizeof(__u64)); + if (!evsel->start_times) + return -ENOMEM; + } + evsel->open_flags = PERF_FLAG_FD_CLOEXEC; if (evsel->cgrp) evsel->open_flags |= PERF_FLAG_PID_CGROUP; @@ -2011,6 +2193,13 @@ static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus, int pid = -1, err, old_errno; enum rlimit_action set_rlimit = NO_CHANGE; + if (evsel->tool_event == PERF_TOOL_DURATION_TIME) { + if (evsel->core.attr.sample_period) /* no sampling */ + return -EINVAL; + evsel->start_time = rdclock(); + return 0; + } + err = __evsel__prepare_open(evsel, cpus, threads); if (err) return err; @@ -2043,6 +2232,46 @@ retry_open: if (!evsel->cgrp && !evsel->core.system_wide) pid = perf_thread_map__pid(threads, thread); + if (evsel->tool_event == PERF_TOOL_USER_TIME || + evsel->tool_event == PERF_TOOL_SYSTEM_TIME) { + bool system = evsel->tool_event == PERF_TOOL_SYSTEM_TIME; + __u64 *start_time = NULL; + + if (evsel->core.attr.sample_period) { + /* no sampling */ + err = -EINVAL; + goto out_close; + } + if (pid > -1) { + char buf[64]; + + snprintf(buf, sizeof(buf), "/proc/%d/stat", pid); + fd = open(buf, O_RDONLY); + evsel->pid_stat = true; + } else { + fd = open("/proc/stat", O_RDONLY); + } + FD(evsel, idx, thread) = fd; + if (fd < 0) { + err = -errno; + goto out_close; + } + start_time = xyarray__entry(evsel->start_times, idx, thread); + if (pid > -1) { + err = read_pid_stat_field(fd, system ? 15 : 14, + start_time); + } else { + struct perf_cpu cpu; + + cpu = perf_cpu_map__cpu(evsel->core.cpus, idx); + err = read_stat_field(fd, cpu, system ? 3 : 1, + start_time); + } + if (err) + goto out_close; + continue; + } + group_fd = get_group_fd(evsel, idx, thread); if (group_fd == -2) { diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 375a38e15cd9..80b5f6dd868e 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -170,6 +170,20 @@ struct evsel { /* for missing_features */ struct perf_pmu *pmu; + + /* For tool events */ + /* Beginning time subtracted when the counter is read. */ + union { + /* duration_time is a single global time. */ + __u64 start_time; + /* + * user_time and system_time read an initial value potentially + * per-CPU or per-pid. + */ + struct xyarray *start_times; + }; + /* Is the tool's fd for /proc/pid/stat or /proc/stat. */ + bool pid_stat; }; struct perf_missing_features { diff --git a/tools/perf/util/expr.c b/tools/perf/util/expr.c index b8875aac8f87..b2536a59c44e 100644 --- a/tools/perf/util/expr.c +++ b/tools/perf/util/expr.c @@ -25,10 +25,6 @@ #include <math.h> #include "pmu.h" -#ifdef PARSER_DEBUG -extern int expr_debug; -#endif - struct expr_id_data { union { struct { diff --git a/tools/perf/util/genelf.c b/tools/perf/util/genelf.c index ac17a3cb59dc..c8f6bee1fa61 100644 --- a/tools/perf/util/genelf.c +++ b/tools/perf/util/genelf.c @@ -54,11 +54,6 @@ typedef struct { char name[0]; /* Start of the name+desc data */ } Elf_Note; -struct options { - char *output; - int fd; -}; - static char shd_string_table[] = { 0, '.', 't', 'e', 'x', 't', 0, /* 1 */ diff --git a/tools/perf/util/hisi-ptt-decoder/Build b/tools/perf/util/hisi-ptt-decoder/Build index db3db8b75033..3298f7b7e308 100644 --- a/tools/perf/util/hisi-ptt-decoder/Build +++ b/tools/perf/util/hisi-ptt-decoder/Build @@ -1 +1 @@ -perf-$(CONFIG_AUXTRACE) += hisi-ptt-pkt-decoder.o +perf-util-$(CONFIG_AUXTRACE) += hisi-ptt-pkt-decoder.o diff --git a/tools/perf/util/hisi-ptt.c b/tools/perf/util/hisi-ptt.c index 52d0ce302ca0..37ea987017f6 100644 --- a/tools/perf/util/hisi-ptt.c +++ b/tools/perf/util/hisi-ptt.c @@ -35,11 +35,6 @@ struct hisi_ptt { u32 pmu_type; }; -struct hisi_ptt_queue { - struct hisi_ptt *ptt; - struct auxtrace_buffer *buffer; -}; - static enum hisi_ptt_pkt_type hisi_ptt_check_packet_type(unsigned char *buf) { uint32_t head = *(uint32_t *)buf; diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 2e9e193179dd..f028f113c4fd 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -2706,8 +2706,7 @@ void hist__account_cycles(struct branch_stack *bs, struct addr_location *al, } } -size_t evlist__fprintf_nr_events(struct evlist *evlist, FILE *fp, - bool skip_empty) +size_t evlist__fprintf_nr_events(struct evlist *evlist, FILE *fp) { struct evsel *pos; size_t ret = 0; @@ -2715,7 +2714,8 @@ size_t evlist__fprintf_nr_events(struct evlist *evlist, FILE *fp, evlist__for_each_entry(evlist, pos) { struct hists *hists = evsel__hists(pos); - if (skip_empty && !hists->stats.nr_samples && !hists->stats.nr_lost_samples) + if (symbol_conf.skip_empty && !hists->stats.nr_samples && + !hists->stats.nr_lost_samples) continue; ret += fprintf(fp, "%s stats:\n", evsel__name(pos)); diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 8fb3bdd29188..5273f5c37050 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -375,8 +375,7 @@ void hists__inc_nr_lost_samples(struct hists *hists, u32 lost); size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, int max_cols, float min_pcnt, FILE *fp, bool ignore_callchains); -size_t evlist__fprintf_nr_events(struct evlist *evlist, FILE *fp, - bool skip_empty); +size_t evlist__fprintf_nr_events(struct evlist *evlist, FILE *fp); void hists__filter_by_dso(struct hists *hists); void hists__filter_by_thread(struct hists *hists); diff --git a/tools/perf/util/intel-pt-decoder/Build b/tools/perf/util/intel-pt-decoder/Build index b41c2e9c6f88..30793d08c6d4 100644 --- a/tools/perf/util/intel-pt-decoder/Build +++ b/tools/perf/util/intel-pt-decoder/Build @@ -1,4 +1,4 @@ -perf-$(CONFIG_AUXTRACE) += intel-pt-pkt-decoder.o intel-pt-insn-decoder.o intel-pt-log.o intel-pt-decoder.o +perf-util-$(CONFIG_AUXTRACE) += intel-pt-pkt-decoder.o intel-pt-insn-decoder.o intel-pt-log.o intel-pt-decoder.o inat_tables_script = $(srctree)/tools/arch/x86/tools/gen-insn-attr-x86.awk inat_tables_maps = $(srctree)/tools/arch/x86/lib/x86-opcode-map.txt diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c index c5d57027ec23..4407130d91f8 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c @@ -92,6 +92,15 @@ static void intel_pt_insn_decoder(struct insn *insn, op = INTEL_PT_OP_JCC; branch = INTEL_PT_BR_CONDITIONAL; break; + case 0xa1: + if (insn_is_rex2(insn)) { /* jmpabs */ + intel_pt_insn->op = INTEL_PT_OP_JMP; + /* jmpabs causes a TIP packet like an indirect branch */ + intel_pt_insn->branch = INTEL_PT_BR_INDIRECT; + intel_pt_insn->length = insn->length; + return; + } + break; case 0xc2: /* near ret */ case 0xc3: /* near ret */ case 0xca: /* far ret */ diff --git a/tools/perf/util/maps.c b/tools/perf/util/maps.c index 16b39db594f4..432399cbe5dd 100644 --- a/tools/perf/util/maps.c +++ b/tools/perf/util/maps.c @@ -735,26 +735,79 @@ static unsigned int first_ending_after(struct maps *maps, const struct map *map) return first; } +static int __maps__insert_sorted(struct maps *maps, unsigned int first_after_index, + struct map *new1, struct map *new2) +{ + struct map **maps_by_address = maps__maps_by_address(maps); + struct map **maps_by_name = maps__maps_by_name(maps); + unsigned int nr_maps = maps__nr_maps(maps); + unsigned int nr_allocate = RC_CHK_ACCESS(maps)->nr_maps_allocated; + unsigned int to_add = new2 ? 2 : 1; + + assert(maps__maps_by_address_sorted(maps)); + assert(first_after_index == nr_maps || + map__end(new1) <= map__start(maps_by_address[first_after_index])); + assert(!new2 || map__end(new1) <= map__start(new2)); + assert(first_after_index == nr_maps || !new2 || + map__end(new2) <= map__start(maps_by_address[first_after_index])); + + if (nr_maps + to_add > nr_allocate) { + nr_allocate = !nr_allocate ? 32 : nr_allocate * 2; + + maps_by_address = realloc(maps_by_address, nr_allocate * sizeof(new1)); + if (!maps_by_address) + return -ENOMEM; + + maps__set_maps_by_address(maps, maps_by_address); + if (maps_by_name) { + maps_by_name = realloc(maps_by_name, nr_allocate * sizeof(new1)); + if (!maps_by_name) { + /* + * If by name fails, just disable by name and it will + * recompute next time it is required. + */ + __maps__free_maps_by_name(maps); + } + maps__set_maps_by_name(maps, maps_by_name); + } + RC_CHK_ACCESS(maps)->nr_maps_allocated = nr_allocate; + } + memmove(&maps_by_address[first_after_index+to_add], + &maps_by_address[first_after_index], + (nr_maps - first_after_index) * sizeof(new1)); + maps_by_address[first_after_index] = map__get(new1); + if (maps_by_name) + maps_by_name[nr_maps] = map__get(new1); + if (new2) { + maps_by_address[first_after_index + 1] = map__get(new2); + if (maps_by_name) + maps_by_name[nr_maps + 1] = map__get(new2); + } + RC_CHK_ACCESS(maps)->nr_maps = nr_maps + to_add; + maps__set_maps_by_name_sorted(maps, false); + check_invariants(maps); + return 0; +} + /* * Adds new to maps, if new overlaps existing entries then the existing maps are * adjusted or removed so that new fits without overlapping any entries. */ static int __maps__fixup_overlap_and_insert(struct maps *maps, struct map *new) { - struct map **maps_by_address; int err = 0; FILE *fp = debug_file(); + unsigned int i; -sort_again: if (!maps__maps_by_address_sorted(maps)) __maps__sort_by_address(maps); - maps_by_address = maps__maps_by_address(maps); /* * Iterate through entries where the end of the existing entry is * greater-than the new map's start. */ - for (unsigned int i = first_ending_after(maps, new); i < maps__nr_maps(maps); ) { + for (i = first_ending_after(maps, new); i < maps__nr_maps(maps); ) { + struct map **maps_by_address = maps__maps_by_address(maps); struct map *pos = maps_by_address[i]; struct map *before = NULL, *after = NULL; @@ -821,37 +874,55 @@ sort_again: /* Maps are still ordered, go to next one. */ i++; if (after) { - __maps__insert(maps, after); - map__put(after); - if (!maps__maps_by_address_sorted(maps)) { - /* - * Sorting broken so invariants don't - * hold, sort and go again. - */ - goto sort_again; - } /* - * Maps are still ordered, skip after and go to - * next one (terminate loop). + * 'before' and 'after' mean 'new' split the + * 'pos' mapping and therefore there are no + * later mappings. */ - i++; + err = __maps__insert_sorted(maps, i, new, after); + map__put(after); + check_invariants(maps); + return err; } + check_invariants(maps); } else if (after) { + /* + * 'after' means 'new' split 'pos' and there are no + * later mappings. + */ map__put(maps_by_address[i]); - maps_by_address[i] = after; - /* Maps are ordered, go to next one. */ - i++; + maps_by_address[i] = map__get(new); + err = __maps__insert_sorted(maps, i + 1, after, NULL); + map__put(after); + check_invariants(maps); + return err; } else { + struct map *next = NULL; + + if (i + 1 < maps__nr_maps(maps)) + next = maps_by_address[i + 1]; + + if (!next || map__start(next) >= map__end(new)) { + /* + * Replace existing mapping and end knowing + * there aren't later overlapping or any + * mappings. + */ + map__put(maps_by_address[i]); + maps_by_address[i] = map__get(new); + check_invariants(maps); + return err; + } __maps__remove(maps, pos); + check_invariants(maps); /* * Maps are ordered but no need to increase `i` as the * later maps were moved down. */ } - check_invariants(maps); } /* Add the map. */ - __maps__insert(maps, new); + err = __maps__insert_sorted(maps, i, new, NULL); out_err: return err; } diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c index 6dda47bb774f..be048bd02f36 100644 --- a/tools/perf/util/mem-events.c +++ b/tools/perf/util/mem-events.c @@ -8,6 +8,7 @@ #include <unistd.h> #include <api/fs/fs.h> #include <linux/kernel.h> +#include "cpumap.h" #include "map_symbol.h" #include "mem-events.h" #include "mem-info.h" @@ -86,7 +87,7 @@ static const char *perf_pmu__mem_events_name(int i, struct perf_pmu *pmu) return NULL; e = &pmu->mem_events[i]; - if (!e) + if (!e || !e->name) return NULL; if (i == PERF_MEM_EVENTS__LOAD || i == PERF_MEM_EVENTS__LOAD_STORE) { @@ -242,6 +243,7 @@ int perf_mem_events__record_args(const char **rec_argv, int *argv_nr) int i = *argv_nr; const char *s; char *copy; + struct perf_cpu_map *cpu_map = NULL; while ((pmu = perf_pmus__scan_mem(pmu)) != NULL) { for (int j = 0; j < PERF_MEM_EVENTS__MAX; j++) { @@ -266,7 +268,19 @@ int perf_mem_events__record_args(const char **rec_argv, int *argv_nr) rec_argv[i++] = "-e"; rec_argv[i++] = copy; + + cpu_map = perf_cpu_map__merge(cpu_map, pmu->cpus); + } + } + + if (cpu_map) { + if (!perf_cpu_map__equal(cpu_map, cpu_map__online())) { + char buf[200]; + + cpu_map__snprint(cpu_map, buf, sizeof(buf)); + pr_warning("Memory events are enabled on a subset of CPUs: %s\n", buf); } + perf_cpu_map__put(cpu_map); } *argv_nr = i; diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 6ed0f9c5581d..321586fb5556 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -31,9 +31,6 @@ #define MAX_NAME_LEN 100 -#ifdef PARSER_DEBUG -extern int parse_events_debug; -#endif static int get_config_terms(const struct parse_events_terms *head_config, struct list_head *head_terms); static int parse_events_terms__copy(const struct parse_events_terms *src, @@ -308,11 +305,16 @@ static int add_event_tool(struct list_head *list, int *idx, .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_DUMMY, }; + const char *cpu_list = NULL; + if (tool_event == PERF_TOOL_DURATION_TIME) { + /* Duration time is gathered globally, pretend it is only on CPU0. */ + cpu_list = "0"; + } evsel = __add_event(list, idx, &attr, /*init_attr=*/true, /*name=*/NULL, /*metric_id=*/NULL, /*pmu=*/NULL, /*config_terms=*/NULL, /*auto_merge_stats=*/false, - /*cpu_list=*/"0"); + cpu_list); if (!evsel) return -ENOMEM; evsel->tool_event = tool_event; diff --git a/tools/perf/util/perf-regs-arch/Build b/tools/perf/util/perf-regs-arch/Build index d9d596d330a7..be95402aa540 100644 --- a/tools/perf/util/perf-regs-arch/Build +++ b/tools/perf/util/perf-regs-arch/Build @@ -1,9 +1,9 @@ -perf-y += perf_regs_aarch64.o -perf-y += perf_regs_arm.o -perf-y += perf_regs_csky.o -perf-y += perf_regs_loongarch.o -perf-y += perf_regs_mips.o -perf-y += perf_regs_powerpc.o -perf-y += perf_regs_riscv.o -perf-y += perf_regs_s390.o -perf-y += perf_regs_x86.o +perf-util-y += perf_regs_aarch64.o +perf-util-y += perf_regs_arm.o +perf-util-y += perf_regs_csky.o +perf-util-y += perf_regs_loongarch.o +perf-util-y += perf_regs_mips.o +perf-util-y += perf_regs_powerpc.o +perf-util-y += perf_regs_riscv.o +perf-util-y += perf_regs_s390.o +perf-util-y += perf_regs_x86.o diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 888ce9912275..986166bc7c78 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -848,6 +848,23 @@ __weak const struct pmu_metrics_table *pmu_metrics_table__find(void) } /** + * Return the length of the PMU name not including the suffix for uncore PMUs. + * + * We want to deduplicate many similar uncore PMUs by stripping their suffixes, + * but there are never going to be too many core PMUs and the suffixes might be + * interesting. "arm_cortex_a53" vs "arm_cortex_a57" or "cpum_cf" for example. + * + * @skip_duplicate_pmus: False in verbose mode so all uncore PMUs are visible + */ +static size_t pmu_deduped_name_len(const struct perf_pmu *pmu, const char *name, + bool skip_duplicate_pmus) +{ + return skip_duplicate_pmus && !pmu->is_core + ? pmu_name_len_no_suffix(name) + : strlen(name); +} + +/** * perf_pmu__match_ignoring_suffix - Does the pmu_name match tok ignoring any * trailing suffix? The Suffix must be in form * tok_{digits}, or tok{digits}. @@ -856,26 +873,34 @@ __weak const struct pmu_metrics_table *pmu_metrics_table__find(void) */ static bool perf_pmu__match_ignoring_suffix(const char *pmu_name, const char *tok) { - const char *p; + const char *p, *suffix; + bool has_hex = false; if (strncmp(pmu_name, tok, strlen(tok))) return false; - p = pmu_name + strlen(tok); + suffix = p = pmu_name + strlen(tok); if (*p == 0) return true; - if (*p == '_') + if (*p == '_') { ++p; + ++suffix; + } /* Ensure we end in a number */ while (1) { - if (!isdigit(*p)) + if (!isxdigit(*p)) return false; + if (!has_hex) + has_hex = !isdigit(*p); if (*(++p) == 0) break; } + if (has_hex) + return (p - suffix) > 2; + return true; } @@ -1765,7 +1790,7 @@ size_t perf_pmu__num_events(struct perf_pmu *pmu) size_t nr; pmu_aliases_parse(pmu); - nr = pmu->sysfs_aliases + pmu->sys_json_aliases;; + nr = pmu->sysfs_aliases + pmu->sys_json_aliases; if (pmu->cpu_aliases_added) nr += pmu->cpu_json_aliases; @@ -1788,10 +1813,9 @@ static char *format_alias(char *buf, int len, const struct perf_pmu *pmu, const struct perf_pmu_alias *alias, bool skip_duplicate_pmus) { struct parse_events_term *term; - int pmu_name_len = skip_duplicate_pmus - ? pmu_name_len_no_suffix(pmu->name, /*num=*/NULL) - : (int)strlen(pmu->name); - int used = snprintf(buf, len, "%.*s/%s", pmu_name_len, pmu->name, alias->name); + size_t pmu_name_len = pmu_deduped_name_len(pmu, pmu->name, + skip_duplicate_pmus); + int used = snprintf(buf, len, "%.*s/%s", (int)pmu_name_len, pmu->name, alias->name); list_for_each_entry(term, &alias->terms.terms, list) { if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR) @@ -1828,13 +1852,11 @@ int perf_pmu__for_each_event(struct perf_pmu *pmu, bool skip_duplicate_pmus, pmu_aliases_parse(pmu); pmu_add_cpu_aliases(pmu); list_for_each_entry(event, &pmu->aliases, list) { - size_t buf_used; - int pmu_name_len; + size_t buf_used, pmu_name_len; info.pmu_name = event->pmu_name ?: pmu->name; - pmu_name_len = skip_duplicate_pmus - ? pmu_name_len_no_suffix(info.pmu_name, /*num=*/NULL) - : (int)strlen(info.pmu_name); + pmu_name_len = pmu_deduped_name_len(pmu, info.pmu_name, + skip_duplicate_pmus); info.alias = NULL; if (event->desc) { info.name = event->name; @@ -1859,7 +1881,7 @@ int perf_pmu__for_each_event(struct perf_pmu *pmu, bool skip_duplicate_pmus, info.encoding_desc = buf + buf_used; parse_events_terms__to_strbuf(&event->terms, &sb); buf_used += snprintf(buf + buf_used, sizeof(buf) - buf_used, - "%.*s/%s/", pmu_name_len, info.pmu_name, sb.buf) + 1; + "%.*s/%s/", (int)pmu_name_len, info.pmu_name, sb.buf) + 1; info.topic = event->topic; info.str = sb.buf; info.deprecated = event->deprecated; @@ -2143,7 +2165,7 @@ void perf_pmu__warn_invalid_config(struct perf_pmu *pmu, __u64 config, bool perf_pmu__match(const struct perf_pmu *pmu, const char *tok) { const char *name = pmu->name; - bool need_fnmatch = strchr(tok, '*') != NULL; + bool need_fnmatch = strisglob(tok); if (!strncmp(tok, "uncore_", 7)) tok += 7; diff --git a/tools/perf/util/pmus.c b/tools/perf/util/pmus.c index b9b4c5eb5002..3fcabfd8fca1 100644 --- a/tools/perf/util/pmus.c +++ b/tools/perf/util/pmus.c @@ -40,31 +40,52 @@ static bool read_sysfs_all_pmus; static void pmu_read_sysfs(bool core_only); -int pmu_name_len_no_suffix(const char *str, unsigned long *num) +size_t pmu_name_len_no_suffix(const char *str) { int orig_len, len; + bool has_hex_digits = false; orig_len = len = strlen(str); - /* Non-uncore PMUs have their full length, for example, i915. */ - if (!strstarts(str, "uncore_")) - return len; - - /* - * Count trailing digits and '_', if '_{num}' suffix isn't present use - * the full length. - */ - while (len > 0 && isdigit(str[len - 1])) + /* Count trailing digits. */ + while (len > 0 && isxdigit(str[len - 1])) { + if (!isdigit(str[len - 1])) + has_hex_digits = true; len--; + } if (len > 0 && len != orig_len && str[len - 1] == '_') { - if (num) - *num = strtoul(&str[len], NULL, 10); - return len - 1; + /* + * There is a '_{num}' suffix. For decimal suffixes any length + * will do, for hexadecimal ensure more than 2 hex digits so + * that S390's cpum_cf PMU doesn't match. + */ + if (!has_hex_digits || (orig_len - len) > 2) + return len - 1; } + /* Use the full length. */ return orig_len; } +int pmu_name_cmp(const char *lhs_pmu_name, const char *rhs_pmu_name) +{ + unsigned long lhs_num = 0, rhs_num = 0; + size_t lhs_pmu_name_len = pmu_name_len_no_suffix(lhs_pmu_name); + size_t rhs_pmu_name_len = pmu_name_len_no_suffix(rhs_pmu_name); + int ret = strncmp(lhs_pmu_name, rhs_pmu_name, + lhs_pmu_name_len < rhs_pmu_name_len ? lhs_pmu_name_len : rhs_pmu_name_len); + + if (lhs_pmu_name_len != rhs_pmu_name_len || ret != 0 || lhs_pmu_name_len == 0) + return ret; + + if (lhs_pmu_name_len + 1 < strlen(lhs_pmu_name)) + lhs_num = strtoul(&lhs_pmu_name[lhs_pmu_name_len + 1], NULL, 16); + if (rhs_pmu_name_len + 1 < strlen(rhs_pmu_name)) + rhs_num = strtoul(&rhs_pmu_name[rhs_pmu_name_len + 1], NULL, 16); + + return lhs_num < rhs_num ? -1 : (lhs_num > rhs_num ? 1 : 0); +} + void perf_pmus__destroy(void) { struct perf_pmu *pmu, *tmp; @@ -167,20 +188,10 @@ static struct perf_pmu *perf_pmu__find2(int dirfd, const char *name) static int pmus_cmp(void *priv __maybe_unused, const struct list_head *lhs, const struct list_head *rhs) { - unsigned long lhs_num = 0, rhs_num = 0; struct perf_pmu *lhs_pmu = container_of(lhs, struct perf_pmu, list); struct perf_pmu *rhs_pmu = container_of(rhs, struct perf_pmu, list); - const char *lhs_pmu_name = lhs_pmu->name ?: ""; - const char *rhs_pmu_name = rhs_pmu->name ?: ""; - int lhs_pmu_name_len = pmu_name_len_no_suffix(lhs_pmu_name, &lhs_num); - int rhs_pmu_name_len = pmu_name_len_no_suffix(rhs_pmu_name, &rhs_num); - int ret = strncmp(lhs_pmu_name, rhs_pmu_name, - lhs_pmu_name_len < rhs_pmu_name_len ? lhs_pmu_name_len : rhs_pmu_name_len); - - if (lhs_pmu_name_len != rhs_pmu_name_len || ret != 0 || lhs_pmu_name_len == 0) - return ret; - return lhs_num < rhs_num ? -1 : (lhs_num > rhs_num ? 1 : 0); + return pmu_name_cmp(lhs_pmu->name ?: "", rhs_pmu->name ?: ""); } /* Add all pmus in sysfs to pmu list: */ @@ -300,11 +311,11 @@ static struct perf_pmu *perf_pmus__scan_skip_duplicates(struct perf_pmu *pmu) pmu_read_sysfs(/*core_only=*/false); pmu = list_prepare_entry(pmu, &core_pmus, list); } else - last_pmu_name_len = pmu_name_len_no_suffix(pmu->name ?: "", NULL); + last_pmu_name_len = pmu_name_len_no_suffix(pmu->name ?: ""); if (use_core_pmus) { list_for_each_entry_continue(pmu, &core_pmus, list) { - int pmu_name_len = pmu_name_len_no_suffix(pmu->name ?: "", /*num=*/NULL); + int pmu_name_len = pmu_name_len_no_suffix(pmu->name ?: ""); if (last_pmu_name_len == pmu_name_len && !strncmp(last_pmu_name, pmu->name ?: "", pmu_name_len)) @@ -316,7 +327,7 @@ static struct perf_pmu *perf_pmus__scan_skip_duplicates(struct perf_pmu *pmu) pmu = list_prepare_entry(pmu, &other_pmus, list); } list_for_each_entry_continue(pmu, &other_pmus, list) { - int pmu_name_len = pmu_name_len_no_suffix(pmu->name ?: "", /*num=*/NULL); + int pmu_name_len = pmu_name_len_no_suffix(pmu->name ?: ""); if (last_pmu_name_len == pmu_name_len && !strncmp(last_pmu_name, pmu->name ?: "", pmu_name_len)) @@ -477,8 +488,8 @@ void perf_pmus__print_pmu_events(const struct print_callbacks *print_cb, void *p qsort(aliases, len, sizeof(struct sevent), cmp_sevent); for (int j = 0; j < len; j++) { /* Skip duplicates */ - if (j > 0 && pmu_alias_is_duplicate(&aliases[j], &aliases[j - 1])) - continue; + if (j < len - 1 && pmu_alias_is_duplicate(&aliases[j], &aliases[j + 1])) + goto free; print_cb->print_event(print_state, aliases[j].pmu_name, @@ -491,6 +502,7 @@ void perf_pmus__print_pmu_events(const struct print_callbacks *print_cb, void *p aliases[j].desc, aliases[j].long_desc, aliases[j].encoding_desc); +free: zfree(&aliases[j].name); zfree(&aliases[j].alias); zfree(&aliases[j].scale_unit); @@ -566,7 +578,7 @@ void perf_pmus__print_raw_pmu_events(const struct print_callbacks *print_cb, voi .long_string = STRBUF_INIT, .num_formats = 0, }; - int len = pmu_name_len_no_suffix(pmu->name, /*num=*/NULL); + int len = pmu_name_len_no_suffix(pmu->name); const char *desc = "(see 'man perf-list' or 'man perf-record' on how to encode it)"; if (!pmu->is_core) diff --git a/tools/perf/util/pmus.h b/tools/perf/util/pmus.h index 9d4ded80b8e9..bdbff02324bb 100644 --- a/tools/perf/util/pmus.h +++ b/tools/perf/util/pmus.h @@ -2,10 +2,15 @@ #ifndef __PMUS_H #define __PMUS_H +#include <stdbool.h> +#include <stddef.h> + struct perf_pmu; struct print_callbacks; -int pmu_name_len_no_suffix(const char *str, unsigned long *num); +size_t pmu_name_len_no_suffix(const char *str); +/* Exposed for testing only. */ +int pmu_name_cmp(const char *lhs_pmu_name, const char *rhs_pmu_name); void perf_pmus__destroy(void); diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources deleted file mode 100644 index 1bec945f4838..000000000000 --- a/tools/perf/util/python-ext-sources +++ /dev/null @@ -1,53 +0,0 @@ -# -# List of files needed by perf python extension -# -# Each source file must be placed on its own line so that it can be -# processed by Makefile and util/setup.py accordingly. -# - -util/python.c -../lib/ctype.c -util/cap.c -util/evlist.c -util/evsel.c -util/evsel_fprintf.c -util/perf_event_attr_fprintf.c -util/cpumap.c -util/memswap.c -util/mmap.c -util/namespaces.c -../lib/bitmap.c -../lib/find_bit.c -../lib/list_sort.c -../lib/hweight.c -../lib/string.c -../lib/vsprintf.c -util/thread_map.c -util/util.c -util/cgroup.c -util/parse-branch-options.c -util/rblist.c -util/counts.c -util/print_binary.c -util/strlist.c -util/trace-event.c -util/trace-event-parse.c -../lib/rbtree.c -util/string.c -util/symbol_fprintf.c -util/units.c -util/affinity.c -util/rwsem.c -util/hashmap.c -util/perf_regs.c -util/fncache.c -util/rlimit.c -util/perf-regs-arch/perf_regs_aarch64.c -util/perf-regs-arch/perf_regs_arm.c -util/perf-regs-arch/perf_regs_csky.c -util/perf-regs-arch/perf_regs_loongarch.c -util/perf-regs-arch/perf_regs_mips.c -util/perf-regs-arch/perf_regs_powerpc.c -util/perf-regs-arch/perf_regs_riscv.c -util/perf-regs-arch/perf_regs_s390.c -util/perf-regs-arch/perf_regs_x86.c diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index 0aeb97c11c03..3be882b2e845 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -10,21 +10,19 @@ #endif #include <perf/mmap.h> #include "evlist.h" -#include "callchain.h" #include "evsel.h" #include "event.h" #include "print_binary.h" #include "thread_map.h" #include "trace-event.h" #include "mmap.h" -#include "stat.h" -#include "metricgroup.h" #include "util/bpf-filter.h" #include "util/env.h" -#include "util/pmu.h" -#include "util/pmus.h" +#include "util/kvm-stat.h" +#include "util/kwork.h" +#include "util/lock-contention.h" #include <internal/lib.h> -#include "util.h" +#include "../builtin.h" #if PY_MAJOR_VERSION < 3 #define _PyUnicode_FromString(arg) \ @@ -50,166 +48,6 @@ #define Py_TYPE(ob) (((PyObject*)(ob))->ob_type) #endif -/* - * Avoid bringing in event parsing. - */ -int parse_event(struct evlist *evlist __maybe_unused, const char *str __maybe_unused) -{ - return 0; -} - -/* - * Provide these two so that we don't have to link against callchain.c and - * start dragging hist.c, etc. - */ -struct callchain_param callchain_param; - -int parse_callchain_record(const char *arg __maybe_unused, - struct callchain_param *param __maybe_unused) -{ - return 0; -} - -/* - * Add these not to drag util/env.c - */ -struct perf_env perf_env; - -const char *perf_env__cpuid(struct perf_env *env __maybe_unused) -{ - return NULL; -} - -// This one is a bit easier, wouldn't drag too much, but leave it as a stub we need it here -const char *perf_env__arch(struct perf_env *env __maybe_unused) -{ - return NULL; -} - -/* - * These ones are needed not to drag the PMU bandwagon, jevents generated - * pmu_sys_event_tables, etc and evsel__find_pmu() is used so far just for - * doing per PMU perf_event_attr.exclude_guest handling, not really needed, so - * far, for the perf python binding known usecases, revisit if this become - * necessary. - */ -struct perf_pmu *evsel__find_pmu(const struct evsel *evsel __maybe_unused) -{ - return NULL; -} - -int perf_pmu__scan_file(const struct perf_pmu *pmu, const char *name, const char *fmt, ...) -{ - return EOF; -} - -const char *perf_pmu__name_from_config(struct perf_pmu *pmu __maybe_unused, u64 config __maybe_unused) -{ - return NULL; -} - -struct perf_pmu *perf_pmus__find_by_type(unsigned int type __maybe_unused) -{ - return NULL; -} - -int perf_pmus__num_core_pmus(void) -{ - return 1; -} - -bool evsel__is_aux_event(const struct evsel *evsel __maybe_unused) -{ - return false; -} - -bool perf_pmus__supports_extended_type(void) -{ - return false; -} - -/* - * Add this one here not to drag util/metricgroup.c - */ -int metricgroup__copy_metric_events(struct evlist *evlist, struct cgroup *cgrp, - struct rblist *new_metric_events, - struct rblist *old_metric_events) -{ - return 0; -} - -/* - * Add this one here not to drag util/trace-event-info.c - */ -char *tracepoint_id_to_name(u64 config) -{ - return NULL; -} - -/* - * XXX: All these evsel destructors need some better mechanism, like a linked - * list of destructors registered when the relevant code indeed is used instead - * of having more and more calls in perf_evsel__delete(). -- acme - * - * For now, add some more: - * - * Not to drag the BPF bandwagon... - */ -void bpf_counter__destroy(struct evsel *evsel); -int bpf_counter__install_pe(struct evsel *evsel, int cpu, int fd); -int bpf_counter__disable(struct evsel *evsel); - -void bpf_counter__destroy(struct evsel *evsel __maybe_unused) -{ -} - -int bpf_counter__install_pe(struct evsel *evsel __maybe_unused, int cpu __maybe_unused, int fd __maybe_unused) -{ - return 0; -} - -int bpf_counter__disable(struct evsel *evsel __maybe_unused) -{ - return 0; -} - -// not to drag util/bpf-filter.c -#ifdef HAVE_BPF_SKEL -int perf_bpf_filter__prepare(struct evsel *evsel __maybe_unused) -{ - return 0; -} - -int perf_bpf_filter__destroy(struct evsel *evsel __maybe_unused) -{ - return 0; -} -#endif - -/* - * Support debug printing even though util/debug.c is not linked. That means - * implementing 'verbose' and 'eprintf'. - */ -int verbose; -int debug_kmaps; -int debug_peo_args; - -int eprintf(int level, int var, const char *fmt, ...); - -int eprintf(int level, int var, const char *fmt, ...) -{ - va_list args; - int ret = 0; - - if (var >= level) { - va_start(args, fmt); - ret = vfprintf(stderr, fmt, args); - va_end(args); - } - - return ret; -} - /* Define PyVarObject_HEAD_INIT for python 2.5 */ #ifndef PyVarObject_HEAD_INIT # define PyVarObject_HEAD_INIT(type, size) PyObject_HEAD_INIT(type) size, @@ -1510,15 +1348,102 @@ error: #endif } -/* - * Dummy, to avoid dragging all the test_attr infrastructure in the python - * binding. - */ -void test_attr__open(struct perf_event_attr *attr, pid_t pid, struct perf_cpu cpu, - int fd, int group_fd, unsigned long flags) + +/* The following are stubs to avoid dragging in builtin-* objects. */ +/* TODO: move the code out of the builtin-* file into util. */ + +unsigned int scripting_max_stack = PERF_MAX_STACK_DEPTH; + +bool kvm_entry_event(struct evsel *evsel __maybe_unused) { + return false; +} + +bool kvm_exit_event(struct evsel *evsel __maybe_unused) +{ + return false; +} + +bool exit_event_begin(struct evsel *evsel __maybe_unused, + struct perf_sample *sample __maybe_unused, + struct event_key *key __maybe_unused) +{ + return false; +} + +bool exit_event_end(struct evsel *evsel __maybe_unused, + struct perf_sample *sample __maybe_unused, + struct event_key *key __maybe_unused) +{ + return false; +} + +void exit_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused, + struct event_key *key __maybe_unused, + char *decode __maybe_unused) +{ +} + +int find_scripts(char **scripts_array __maybe_unused, char **scripts_path_array __maybe_unused, + int num __maybe_unused, int pathlen __maybe_unused) +{ + return -1; +} + +void perf_stat__set_no_csv_summary(int set __maybe_unused) +{ +} + +void perf_stat__set_big_num(int set __maybe_unused) +{ +} + +int script_spec_register(const char *spec __maybe_unused, struct scripting_ops *ops __maybe_unused) +{ + return -1; +} + +arch_syscalls__strerrno_t *arch_syscalls__strerrno_function(const char *arch __maybe_unused) +{ + return NULL; +} + +struct kwork_work *perf_kwork_add_work(struct perf_kwork *kwork __maybe_unused, + struct kwork_class *class __maybe_unused, + struct kwork_work *key __maybe_unused) +{ + return NULL; +} + +void script_fetch_insn(struct perf_sample *sample __maybe_unused, + struct thread *thread __maybe_unused, + struct machine *machine __maybe_unused) +{ +} + +int perf_sample__sprintf_flags(u32 flags __maybe_unused, char *str __maybe_unused, + size_t sz __maybe_unused) +{ + return -1; +} + +bool match_callstack_filter(struct machine *machine __maybe_unused, u64 *callstack __maybe_unused) +{ + return false; +} + +struct lock_stat *lock_stat_find(u64 addr __maybe_unused) +{ + return NULL; +} + +struct lock_stat *lock_stat_findnew(u64 addr __maybe_unused, const char *name __maybe_unused, + int flags __maybe_unused) +{ + return NULL; } -void evlist__free_stats(struct evlist *evlist) +int cmd_inject(int argc __maybe_unused, const char *argv[] __maybe_unused) { + return -1; } diff --git a/tools/perf/util/scripting-engines/Build b/tools/perf/util/scripting-engines/Build index 586b94e90f4e..2282fe3772f3 100644 --- a/tools/perf/util/scripting-engines/Build +++ b/tools/perf/util/scripting-engines/Build @@ -1,7 +1,7 @@ ifeq ($(CONFIG_LIBTRACEEVENT),y) - perf-$(CONFIG_LIBPERL) += trace-event-perl.o + perf-util-$(CONFIG_LIBPERL) += trace-event-perl.o endif -perf-$(CONFIG_LIBPYTHON) += trace-event-python.o +perf-util-$(CONFIG_LIBPYTHON) += trace-event-python.o CFLAGS_trace-event-perl.o += $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-nested-externs -Wno-undef -Wno-switch-default -Wno-bad-function-cast -Wno-declaration-after-statement -Wno-switch-enum diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index a10343b9dcd4..5596bed1b8c8 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -2050,6 +2050,7 @@ static int __perf_session__process_pipe_events(struct perf_session *session) { struct ordered_events *oe = &session->ordered_events; struct perf_tool *tool = session->tool; + struct ui_progress prog; union perf_event *event; uint32_t size, cur_size = 0; void *buf = NULL; @@ -2057,9 +2058,21 @@ static int __perf_session__process_pipe_events(struct perf_session *session) u64 head; ssize_t err; void *p; + bool update_prog = false; perf_tool__fill_defaults(tool); + /* + * If it's from a file saving pipe data (by redirection), it would have + * a file name other than "-". Then we can get the total size and show + * the progress. + */ + if (strcmp(session->data->path, "-") && session->data->file.size) { + ui_progress__init_size(&prog, session->data->file.size, + "Processing events..."); + update_prog = true; + } + head = 0; cur_size = sizeof(union perf_event); @@ -2131,6 +2144,9 @@ more: if (err) goto out_err; + if (update_prog) + ui_progress__update(&prog, size); + if (!session_done()) goto more; done: @@ -2144,6 +2160,8 @@ done: err = perf_session__flush_thread_stacks(session); out_err: free(buf); + if (update_prog) + ui_progress__finish(); if (!tool->no_warn) perf_session__warn_about_errors(session); ordered_events__free(&session->ordered_events); @@ -2523,7 +2541,7 @@ static int __perf_session__process_dir_events(struct perf_session *session) perf_tool__fill_defaults(tool); - ui_progress__init_size(&prog, total_size, "Sorting events..."); + ui_progress__init_size(&prog, total_size, "Processing events..."); nr_readers = 1; for (i = 0; i < data->dir.nr; i++) { @@ -2696,8 +2714,7 @@ size_t perf_session__fprintf_dsos_buildid(struct perf_session *session, FILE *fp return machines__fprintf_dsos_buildid(&session->machines, fp, skip, parm); } -size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp, - bool skip_empty) +size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp) { size_t ret; const char *msg = ""; @@ -2707,7 +2724,7 @@ size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp, ret = fprintf(fp, "\nAggregated stats:%s\n", msg); - ret += events_stats__fprintf(&session->evlist->stats, fp, skip_empty); + ret += events_stats__fprintf(&session->evlist->stats, fp); return ret; } diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index 3b0256e977a6..4c29dc86956f 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -130,8 +130,7 @@ size_t perf_session__fprintf_dsos(struct perf_session *session, FILE *fp); size_t perf_session__fprintf_dsos_buildid(struct perf_session *session, FILE *fp, bool (fn)(struct dso *dso, int parm), int parm); -size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp, - bool skip_empty); +size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp); void perf_session__dump_kmaps(struct perf_session *session); diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py index 3107f5aa8c9a..142e9d447ce7 100644 --- a/tools/perf/util/setup.py +++ b/tools/perf/util/setup.py @@ -60,7 +60,7 @@ class install_lib(_install_lib): cflags = getenv('CFLAGS', '').split() # switch off several checks (need to be at the end of cflags list) -cflags += ['-fno-strict-aliasing', '-Wno-write-strings', '-Wno-unused-parameter', '-Wno-redundant-decls', '-DPYTHON_PERF' ] +cflags += ['-fno-strict-aliasing', '-Wno-write-strings', '-Wno-unused-parameter', '-Wno-redundant-decls' ] if cc_is_clang: cflags += ["-Wno-unused-command-line-argument" ] else: @@ -72,36 +72,11 @@ cflags += [ "-Wno-declaration-after-statement" ] src_perf = getenv('srctree') + '/tools/perf' build_lib = getenv('PYTHON_EXTBUILD_LIB') build_tmp = getenv('PYTHON_EXTBUILD_TMP') -libtraceevent = getenv('LIBTRACEEVENT') -libapikfs = getenv('LIBAPI') -libperf = getenv('LIBPERF') - -ext_sources = [f.strip() for f in open('util/python-ext-sources') - if len(f.strip()) > 0 and f[0] != '#'] - -extra_libraries = [] - -if '-DHAVE_LIBTRACEEVENT' in cflags: - extra_libraries += [ 'traceevent' ] -else: - ext_sources.remove('util/trace-event.c') - ext_sources.remove('util/trace-event-parse.c') - -# use full paths with source files -ext_sources = list(map(lambda x: '%s/%s' % (src_perf, x) , ext_sources)) - -if '-DHAVE_LIBNUMA_SUPPORT' in cflags: - extra_libraries += [ 'numa' ] -if '-DHAVE_LIBCAP_SUPPORT' in cflags: - extra_libraries += [ 'cap' ] perf = Extension('perf', - sources = ext_sources, - include_dirs = ['util/include'], - libraries = extra_libraries, - extra_compile_args = cflags, - extra_objects = [ x for x in [libtraceevent, libapikfs, libperf] - if x is not None], + sources = [ src_perf + '/util/python.c' ], + include_dirs = ['util/include'], + extra_compile_args = cflags, ) setup(name='perf', diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index cd39ea972193..ab7c7ff35f9b 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -334,7 +334,7 @@ sort__sym_cmp(struct hist_entry *left, struct hist_entry *right) * comparing symbol address alone is not enough since it's a * relative address within a dso. */ - if (!hists__has(left->hists, dso) || hists__has(right->hists, dso)) { + if (!hists__has(left->hists, dso)) { ret = sort__dso_cmp(left, right); if (ret != 0) return ret; diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c index 9d670d8c1c08..760742fd4a7d 100644 --- a/tools/perf/util/srcline.c +++ b/tools/perf/util/srcline.c @@ -39,7 +39,7 @@ static const char *srcline_dso_name(struct dso *dso) if (dso_name[0] == '[') return NULL; - if (!strncmp(dso_name, "/tmp/perf-", 10)) + if (is_perf_pid_map_name(dso_name)) return NULL; return dso_name; @@ -288,7 +288,7 @@ static int inline_list__append_dso_a2l(struct dso *dso, struct inline_node *node, struct symbol *sym) { - struct a2l_data *a2l = dso->a2l; + struct a2l_data *a2l = dso__a2l(dso); struct symbol *inline_sym = new_inline_sym(dso, sym, a2l->funcname); char *srcline = NULL; @@ -304,11 +304,11 @@ static int addr2line(const char *dso_name, u64 addr, struct symbol *sym) { int ret = 0; - struct a2l_data *a2l = dso->a2l; + struct a2l_data *a2l = dso__a2l(dso); if (!a2l) { - dso->a2l = addr2line_init(dso_name); - a2l = dso->a2l; + a2l = addr2line_init(dso_name); + dso__set_a2l(dso, a2l); } if (a2l == NULL) { @@ -360,14 +360,14 @@ static int addr2line(const char *dso_name, u64 addr, void dso__free_a2l(struct dso *dso) { - struct a2l_data *a2l = dso->a2l; + struct a2l_data *a2l = dso__a2l(dso); if (!a2l) return; addr2line_cleanup(a2l); - dso->a2l = NULL; + dso__set_a2l(dso, NULL); } #else /* HAVE_LIBBFD_SUPPORT */ diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index 91d2f7f65df7..c38bcb6f4c78 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -38,6 +38,7 @@ static int aggr_header_lens[] = { [AGGR_CORE] = 18, [AGGR_CACHE] = 22, + [AGGR_CLUSTER] = 20, [AGGR_DIE] = 12, [AGGR_SOCKET] = 6, [AGGR_NODE] = 6, @@ -49,6 +50,7 @@ static int aggr_header_lens[] = { static const char *aggr_header_csv[] = { [AGGR_CORE] = "core,cpus,", [AGGR_CACHE] = "cache,cpus,", + [AGGR_CLUSTER] = "cluster,cpus,", [AGGR_DIE] = "die,cpus,", [AGGR_SOCKET] = "socket,cpus,", [AGGR_NONE] = "cpu,", @@ -60,6 +62,7 @@ static const char *aggr_header_csv[] = { static const char *aggr_header_std[] = { [AGGR_CORE] = "core", [AGGR_CACHE] = "cache", + [AGGR_CLUSTER] = "cluster", [AGGR_DIE] = "die", [AGGR_SOCKET] = "socket", [AGGR_NONE] = "cpu", @@ -1183,10 +1186,21 @@ static void print_metric_headers_std(struct perf_stat_config *config, static void print_metric_headers_csv(struct perf_stat_config *config, bool no_indent __maybe_unused) { + const char *p; + if (config->interval) - fputs("time,", config->output); - if (!config->iostat_run) - fputs(aggr_header_csv[config->aggr_mode], config->output); + fprintf(config->output, "time%s", config->csv_sep); + if (config->iostat_run) + return; + + p = aggr_header_csv[config->aggr_mode]; + while (*p) { + if (*p == ',') + fputs(config->csv_sep, config->output); + else + fputc(*p, config->output); + p++; + } } static void print_metric_headers_json(struct perf_stat_config *config __maybe_unused, diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index 3466aa952442..6bb975e46de3 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -176,6 +176,13 @@ static double find_stat(const struct evsel *evsel, int aggr_idx, enum stat_type if (type != evsel__stat_type(cur)) continue; + /* + * Except the SW CLOCK events, + * ignore if not the PMU we're looking for. + */ + if ((type != STAT_NSECS) && (evsel->pmu != cur->pmu)) + continue; + aggr = &cur->stats->aggr[aggr_idx]; if (type == STAT_NSECS) return aggr->counts.val; diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 9e5940b5bc59..19eb623e0826 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -1607,7 +1607,7 @@ int dso__load_bfd_symbols(struct dso *dso, const char *debugfile) if (!bfd_check_format(abfd, bfd_object)) { pr_debug2("%s: cannot read %s bfd file.\n", __func__, - dso->long_name); + dso__long_name(dso)); goto out_close; } @@ -1640,12 +1640,13 @@ int dso__load_bfd_symbols(struct dso *dso, const char *debugfile) } if (i < symbols_count) { /* PE symbols can only have 4 bytes, so use .text high bits */ - dso->text_offset = section->vma - (u32)section->vma; - dso->text_offset += (u32)bfd_asymbol_value(symbols[i]); - dso->text_end = (section->vma - dso->text_offset) + section->size; + u64 text_offset = (section->vma - (u32)section->vma) + + (u32)bfd_asymbol_value(symbols[i]); + dso__set_text_offset(dso, text_offset); + dso__set_text_end(dso, (section->vma - text_offset) + section->size); } else { - dso->text_offset = section->vma - section->filepos; - dso->text_end = section->filepos + section->size; + dso__set_text_offset(dso, section->vma - section->filepos); + dso__set_text_end(dso, section->filepos + section->size); } } @@ -1671,7 +1672,7 @@ int dso__load_bfd_symbols(struct dso *dso, const char *debugfile) else len = section->size - sym->value; - start = bfd_asymbol_value(sym) - dso->text_offset; + start = bfd_asymbol_value(sym) - dso__text_offset(dso); symbol = symbol__new(start, len, bfd2elf_binding(sym), STT_FUNC, bfd_asymbol_name(sym)); if (!symbol) @@ -1799,7 +1800,8 @@ int dso__load(struct dso *dso, struct map *map) const char *map_path = dso__long_name(dso); mutex_lock(dso__lock(dso)); - perfmap = strncmp(dso__name(dso), "/tmp/perf-", 10) == 0; + perfmap = is_perf_pid_map_name(map_path); + if (perfmap) { if (dso__nsinfo(dso) && (dso__find_perf_map(newmapname, sizeof(newmapname), @@ -1816,10 +1818,7 @@ int dso__load(struct dso *dso, struct map *map) goto out; } - kmod = dso__symtab_type(dso) == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE || - dso__symtab_type(dso) == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP || - dso__symtab_type(dso) == DSO_BINARY_TYPE__GUEST_KMODULE || - dso__symtab_type(dso) == DSO_BINARY_TYPE__GUEST_KMODULE_COMP; + kmod = dso__is_kmod(dso); if (dso__kernel(dso) && !kmod) { if (dso__kernel(dso) == DSO_SPACE__KERNEL) diff --git a/tools/perf/util/symbol_conf.h b/tools/perf/util/symbol_conf.h index c114bbceef40..657cfa5af43c 100644 --- a/tools/perf/util/symbol_conf.h +++ b/tools/perf/util/symbol_conf.h @@ -46,7 +46,8 @@ struct symbol_conf { lazy_load_kernel_maps, keep_exited_threads, annotate_data_member, - annotate_data_sample; + annotate_data_sample, + skip_empty; const char *vmlinux_name, *kallsyms_name, *source_prefix, diff --git a/tools/perf/util/syscalltbl.c b/tools/perf/util/syscalltbl.c index 63be7b58761d..0dd26b991b3f 100644 --- a/tools/perf/util/syscalltbl.c +++ b/tools/perf/util/syscalltbl.c @@ -123,6 +123,13 @@ int syscalltbl__id(struct syscalltbl *tbl, const char *name) return sc ? sc->id : -1; } +int syscalltbl__id_at_idx(struct syscalltbl *tbl, int idx) +{ + struct syscall *syscalls = tbl->syscalls.entries; + + return idx < tbl->syscalls.nr_entries ? syscalls[idx].id : -1; +} + int syscalltbl__strglobmatch_next(struct syscalltbl *tbl, const char *syscall_glob, int *idx) { int i; diff --git a/tools/perf/util/syscalltbl.h b/tools/perf/util/syscalltbl.h index a41d2ca9e4ae..2b53b7ed25a6 100644 --- a/tools/perf/util/syscalltbl.h +++ b/tools/perf/util/syscalltbl.h @@ -16,6 +16,7 @@ void syscalltbl__delete(struct syscalltbl *tbl); const char *syscalltbl__name(const struct syscalltbl *tbl, int id); int syscalltbl__id(struct syscalltbl *tbl, const char *name); +int syscalltbl__id_at_idx(struct syscalltbl *tbl, int idx); int syscalltbl__strglobmatch_first(struct syscalltbl *tbl, const char *syscall_glob, int *idx); int syscalltbl__strglobmatch_next(struct syscalltbl *tbl, const char *syscall_glob, int *idx); diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c index b38d322734b4..bde216e630d2 100644 --- a/tools/perf/util/unwind-libdw.c +++ b/tools/perf/util/unwind-libdw.c @@ -29,8 +29,8 @@ static int __find_debuginfo(Dwfl_Module *mod __maybe_unused, void **userdata, const struct dso *dso = *userdata; assert(dso); - if (dso->symsrc_filename && strcmp (file_name, dso->symsrc_filename)) - *debuginfo_file_name = strdup(dso->symsrc_filename); + if (dso__symsrc_filename(dso) && strcmp(file_name, dso__symsrc_filename(dso))) + *debuginfo_file_name = strdup(dso__symsrc_filename(dso)); return -1; } @@ -66,7 +66,7 @@ static int __report_module(struct addr_location *al, u64 ip, * a different code in another DSO. So just use the map->start * directly to pick the correct one. */ - if (!strncmp(dso->long_name, "/tmp/jitted-", 12)) + if (!strncmp(dso__long_name(dso), "/tmp/jitted-", 12)) base = map__start(al->map); else base = map__start(al->map) - map__pgoff(al->map); @@ -83,15 +83,15 @@ static int __report_module(struct addr_location *al, u64 ip, if (!mod) { char filename[PATH_MAX]; - __symbol__join_symfs(filename, sizeof(filename), dso->long_name); - mod = dwfl_report_elf(ui->dwfl, dso->short_name, filename, -1, + __symbol__join_symfs(filename, sizeof(filename), dso__long_name(dso)); + mod = dwfl_report_elf(ui->dwfl, dso__short_name(dso), filename, -1, base, false); } if (!mod) { char filename[PATH_MAX]; if (dso__build_id_filename(dso, filename, sizeof(filename), false)) - mod = dwfl_report_elf(ui->dwfl, dso->short_name, filename, -1, + mod = dwfl_report_elf(ui->dwfl, dso__short_name(dso), filename, -1, base, false); } diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c index cde267ea3e99..f6a6f6a91030 100644 --- a/tools/perf/util/unwind-libunwind-local.c +++ b/tools/perf/util/unwind-libunwind-local.c @@ -363,7 +363,7 @@ static int read_unwind_spec_debug_frame(struct dso *dso, struct machine *machine, u64 *offset) { int fd; - u64 ofs = dso->data.debug_frame_offset; + u64 ofs = dso__data(dso)->debug_frame_offset; /* debug_frame can reside in: * - dso @@ -379,7 +379,7 @@ static int read_unwind_spec_debug_frame(struct dso *dso, } if (ofs <= 0) { - fd = open(dso->symsrc_filename, O_RDONLY); + fd = open(dso__symsrc_filename(dso), O_RDONLY); if (fd >= 0) { ofs = elf_section_offset(fd, ".debug_frame"); close(fd); @@ -390,6 +390,11 @@ static int read_unwind_spec_debug_frame(struct dso *dso, char *debuglink = malloc(PATH_MAX); int ret = 0; + if (debuglink == NULL) { + pr_err("unwind: Can't read unwind spec debug frame.\n"); + return -ENOMEM; + } + ret = dso__read_binary_type_filename( dso, DSO_BINARY_TYPE__DEBUGLINK, machine->root_dir, debuglink, PATH_MAX); @@ -402,21 +407,21 @@ static int read_unwind_spec_debug_frame(struct dso *dso, } } if (ofs > 0) { - if (dso->symsrc_filename != NULL) { + if (dso__symsrc_filename(dso) != NULL) { pr_warning( "%s: overwrite symsrc(%s,%s)\n", __func__, - dso->symsrc_filename, + dso__symsrc_filename(dso), debuglink); - zfree(&dso->symsrc_filename); + zfree(&dso__symsrc_filename(dso)); } - dso->symsrc_filename = debuglink; + dso__set_symsrc_filename(dso, debuglink); } else { free(debuglink); } } - dso->data.debug_frame_offset = ofs; + dso__data(dso)->debug_frame_offset = ofs; } *offset = ofs; @@ -481,7 +486,7 @@ find_proc_info(unw_addr_space_t as, unw_word_t ip, unw_proc_info_t *pi, if (ret < 0 && !read_unwind_spec_debug_frame(dso, ui->machine, &segbase)) { int fd = dso__data_get_fd(dso, ui->machine); - int is_exec = elf_is_exec(fd, dso->name); + int is_exec = elf_is_exec(fd, dso__name(dso)); u64 start = map__start(map); unw_word_t base = is_exec ? 0 : start; const char *symfile; @@ -489,7 +494,7 @@ find_proc_info(unw_addr_space_t as, unw_word_t ip, unw_proc_info_t *pi, if (fd >= 0) dso__data_put_fd(dso); - symfile = dso->symsrc_filename ?: dso->name; + symfile = dso__symsrc_filename(dso) ?: dso__name(dso); memset(&di, 0, sizeof(di)); if (dwarf_find_debug_frame(0, &di, ip, base, symfile, start, map__end(map))) |