diff options
Diffstat (limited to 'tools/perf')
191 files changed, 7031 insertions, 2669 deletions
diff --git a/tools/perf/Documentation/Makefile b/tools/perf/Documentation/Makefile index 42261a9b280e..ac841bc5c35b 100644 --- a/tools/perf/Documentation/Makefile +++ b/tools/perf/Documentation/Makefile @@ -280,7 +280,7 @@ $(MAN_HTML): $(OUTPUT)%.html : %.txt mv $@+ $@ ifdef USE_ASCIIDOCTOR -$(OUTPUT)%.1 $(OUTPUT)%.5 $(OUTPUT)%.7 : $(OUTPUT)%.txt +$(OUTPUT)%.1 $(OUTPUT)%.5 $(OUTPUT)%.7 : %.txt $(QUIET_ASCIIDOC)$(RM) $@+ $@ && \ $(ASCIIDOC) -b manpage -d manpage \ $(ASCIIDOC_EXTRA) -aperf_version=$(PERF_VERSION) -o $@+ $< && \ diff --git a/tools/perf/Documentation/perf-annotate.txt b/tools/perf/Documentation/perf-annotate.txt index 749cc6055dac..e8c972f89357 100644 --- a/tools/perf/Documentation/perf-annotate.txt +++ b/tools/perf/Documentation/perf-annotate.txt @@ -118,6 +118,15 @@ OPTIONS --group:: Show event group information together +--percent-type:: + Set annotation percent type from following choices: + global-period, local-period, global-hits, local-hits + + The local/global keywords set if the percentage is computed + in the scope of the function (local) or the whole data (global). + The period/hits keywords set the base the percentage is computed + on - the samples period or the number of samples (hits). + SEE ALSO -------- linkperf:perf-record[1], linkperf:perf-report[1] diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt index 11300dbe35c5..236b9b97dfdb 100644 --- a/tools/perf/Documentation/perf-list.txt +++ b/tools/perf/Documentation/perf-list.txt @@ -18,6 +18,10 @@ various perf commands with the -e option. OPTIONS ------- +-d:: +--desc:: +Print extra event descriptions. (default) + --no-desc:: Don't print descriptions. @@ -25,11 +29,13 @@ Don't print descriptions. --long-desc:: Print longer event descriptions. +--debug:: +Enable debugging output. + --details:: Print how named events are resolved internally into perf events, and also any extra expressions computed by perf stat. - [[EVENT_MODIFIERS]] EVENT MODIFIERS --------------- @@ -234,7 +240,7 @@ perf also supports group leader sampling using the :S specifier. perf record -e '{cycles,instructions}:S' ... perf report --group -Normally all events in a event group sample, but with :S only +Normally all events in an event group sample, but with :S only the first event (the leader) samples, and it only reads the values of the other events in the group. diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index 04168da4268e..246dee081efd 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -94,7 +94,7 @@ OPTIONS "perf report" to view group events together. --filter=<filter>:: - Event filter. This option should follow a event selector (-e) which + Event filter. This option should follow an event selector (-e) which selects either tracepoint event(s) or a hardware trace PMU (e.g. Intel PT or CoreSight). @@ -153,7 +153,7 @@ OPTIONS --exclude-perf:: Don't record events issued by perf itself. This option should follow - a event selector (-e) which selects tracepoint event(s). It adds a + an event selector (-e) which selects tracepoint event(s). It adds a filter expression 'common_pid != $PERFPID' to filters. If other '--filter' exists, the new filter expression will be combined with them by '&&'. diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index 917e36fde6d8..474a4941f65d 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -477,6 +477,15 @@ include::itrace.txt[] Display monitored tasks stored in perf data. Displaying pid/tid/ppid plus the command string aligned to distinguish parent and child tasks. +--percent-type:: + Set annotation percent type from following choices: + global-period, local-period, global-hits, local-hits + + The local/global keywords set if the percentage is computed + in the scope of the function (local) or the whole data (global). + The period/hits keywords set the base the percentage is computed + on - the samples period or the number of samples (hits). + include::callchain-overhead-calculation.txt[] SEE ALSO diff --git a/tools/perf/Makefile b/tools/perf/Makefile index 225454416ed5..7902a5681fc8 100644 --- a/tools/perf/Makefile +++ b/tools/perf/Makefile @@ -84,10 +84,10 @@ endif # has_clean endif # MAKECMDGOALS # -# The clean target is not really parallel, don't print the jobs info: +# Explicitly disable parallelism for the clean target. # clean: - $(make) + $(make) -j1 # # The build-test target is not really parallel, don't print the jobs info, diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index f5a3b402589e..e30d20fb482d 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -54,6 +54,8 @@ endif ifeq ($(SRCARCH),arm64) NO_PERF_REGS := 0 + NO_SYSCALL_TABLE := 0 + CFLAGS += -I$(OUTPUT)arch/arm64/include/generated LIBUNWIND_LIBS = -lunwind -lunwind-aarch64 endif @@ -831,7 +833,7 @@ ifndef NO_JVMTI JDIR=$(shell /usr/sbin/update-java-alternatives -l | head -1 | awk '{print $$3}') else ifneq (,$(wildcard /usr/sbin/alternatives)) - JDIR=$(shell alternatives --display java | tail -1 | cut -d' ' -f 5 | sed 's%/jre/bin/java.%%g') + JDIR=$(shell /usr/sbin/alternatives --display java | tail -1 | cut -d' ' -f 5 | sed 's%/jre/bin/java.%%g') endif endif ifndef JDIR @@ -905,8 +907,8 @@ bindir = $(abspath $(prefix)/$(bindir_relative)) mandir = share/man infodir = share/info perfexecdir = libexec/perf-core -perf_include_dir = lib/include/perf -perf_examples_dir = lib/examples/perf +perf_include_dir = lib/perf/include +perf_examples_dir = lib/perf/examples sharedir = $(prefix)/share template_dir = share/perf-core/templates STRACE_GROUPS_DIR = share/perf-core/strace/groups diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index ecc9fc952655..2f3bf025e305 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -384,6 +384,8 @@ export INSTALL SHELL_PATH SHELL = $(SHELL_PATH) +linux_uapi_dir := $(srctree)/tools/include/uapi/linux + beauty_outdir := $(OUTPUT)trace/beauty/generated beauty_ioctl_outdir := $(beauty_outdir)/ioctl drm_ioctl_array := $(beauty_ioctl_outdir)/drm_ioctl_array.c @@ -431,6 +433,12 @@ kvm_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/kvm_ioctl.sh $(kvm_ioctl_array): $(kvm_hdr_dir)/kvm.h $(kvm_ioctl_tbl) $(Q)$(SHELL) '$(kvm_ioctl_tbl)' $(kvm_hdr_dir) > $@ +socket_ipproto_array := $(beauty_outdir)/socket_ipproto_array.c +socket_ipproto_tbl := $(srctree)/tools/perf/trace/beauty/socket_ipproto.sh + +$(socket_ipproto_array): $(linux_uapi_dir)/in.h $(socket_ipproto_tbl) + $(Q)$(SHELL) '$(socket_ipproto_tbl)' $(linux_uapi_dir) > $@ + vhost_virtio_ioctl_array := $(beauty_ioctl_outdir)/vhost_virtio_ioctl_array.c vhost_virtio_hdr_dir := $(srctree)/tools/include/uapi/linux vhost_virtio_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/vhost_virtio_ioctl.sh @@ -566,6 +574,7 @@ prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h archheaders $(drm_ioc $(sndrv_ctl_ioctl_array) \ $(kcmp_type_array) \ $(kvm_ioctl_array) \ + $(socket_ipproto_array) \ $(vhost_virtio_ioctl_array) \ $(madvise_behavior_array) \ $(perf_ioctl_array) \ @@ -626,7 +635,7 @@ $(LIBPERF_IN): prepare FORCE $(LIB_FILE): $(LIBPERF_IN) $(QUIET_AR)$(RM) $@ && $(AR) rcs $@ $(LIBPERF_IN) $(LIB_OBJS) -LIBTRACEEVENT_FLAGS += plugin_dir=$(plugindir_SQ) +LIBTRACEEVENT_FLAGS += plugin_dir=$(plugindir_SQ) 'EXTRA_CFLAGS=$(EXTRA_CFLAGS)' 'LDFLAGS=$(LDFLAGS)' $(LIBTRACEEVENT): FORCE $(Q)$(MAKE) -C $(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) O=$(OUTPUT) $(OUTPUT)libtraceevent.a @@ -768,14 +777,14 @@ endif $(call QUIET_INSTALL, libexec) \ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)' ifndef NO_LIBBPF - $(call QUIET_INSTALL, lib) \ - $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf' - $(call QUIET_INSTALL, include/bpf) \ - $(INSTALL) include/bpf/*.h '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf' - $(call QUIET_INSTALL, lib) \ - $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf' - $(call QUIET_INSTALL, examples/bpf) \ - $(INSTALL) examples/bpf/*.c '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf' + $(call QUIET_INSTALL, bpf-headers) \ + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf'; \ + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf/linux'; \ + $(INSTALL) include/bpf/*.h -t '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf'; \ + $(INSTALL) include/bpf/linux/*.h -t '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf/linux' + $(call QUIET_INSTALL, bpf-examples) \ + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf'; \ + $(INSTALL) examples/bpf/*.c -t '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf' endif $(call QUIET_INSTALL, perf-archive) \ $(INSTALL) $(OUTPUT)perf-archive -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)' @@ -860,6 +869,7 @@ clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clea $(OUTPUT)$(sndrv_pcm_ioctl_array) \ $(OUTPUT)$(kvm_ioctl_array) \ $(OUTPUT)$(kcmp_type_array) \ + $(OUTPUT)$(socket_ipproto_array) \ $(OUTPUT)$(vhost_virtio_ioctl_array) \ $(OUTPUT)$(perf_ioctl_array) \ $(OUTPUT)$(prctl_option_array) \ diff --git a/tools/perf/arch/arm64/Makefile b/tools/perf/arch/arm64/Makefile index 91de4860faad..dbef716a1913 100644 --- a/tools/perf/arch/arm64/Makefile +++ b/tools/perf/arch/arm64/Makefile @@ -4,3 +4,25 @@ PERF_HAVE_DWARF_REGS := 1 endif PERF_HAVE_JITDUMP := 1 PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1 + +# +# Syscall table generation for perf +# + +out := $(OUTPUT)arch/arm64/include/generated/asm +header := $(out)/syscalls.c +incpath := $(srctree)/tools +sysdef := $(srctree)/tools/arch/arm64/include/uapi/asm/unistd.h +sysprf := $(srctree)/tools/perf/arch/arm64/entry/syscalls/ +systbl := $(sysprf)/mksyscalltbl + +# Create output directory if not already present +_dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)') + +$(header): $(sysdef) $(systbl) + $(Q)$(SHELL) '$(systbl)' '$(CC)' '$(HOSTCC)' $(incpath) $(sysdef) > $@ + +clean:: + $(call QUIET_CLEAN, arm64) $(RM) $(header) + +archheaders: $(header) diff --git a/tools/perf/arch/arm64/annotate/instructions.c b/tools/perf/arch/arm64/annotate/instructions.c index 6688977e4ac7..76c6345a57d5 100644 --- a/tools/perf/arch/arm64/annotate/instructions.c +++ b/tools/perf/arch/arm64/annotate/instructions.c @@ -8,6 +8,63 @@ struct arm64_annotate { jump_insn; }; +static int arm64_mov__parse(struct arch *arch __maybe_unused, + struct ins_operands *ops, + struct map_symbol *ms __maybe_unused) +{ + char *s = strchr(ops->raw, ','), *target, *endptr; + + if (s == NULL) + return -1; + + *s = '\0'; + ops->source.raw = strdup(ops->raw); + *s = ','; + + if (ops->source.raw == NULL) + return -1; + + target = ++s; + ops->target.raw = strdup(target); + if (ops->target.raw == NULL) + goto out_free_source; + + ops->target.addr = strtoull(target, &endptr, 16); + if (endptr == target) + goto out_free_target; + + s = strchr(endptr, '<'); + if (s == NULL) + goto out_free_target; + endptr = strchr(s + 1, '>'); + if (endptr == NULL) + goto out_free_target; + + *endptr = '\0'; + *s = ' '; + ops->target.name = strdup(s); + *s = '<'; + *endptr = '>'; + if (ops->target.name == NULL) + goto out_free_target; + + return 0; + +out_free_target: + zfree(&ops->target.raw); +out_free_source: + zfree(&ops->source.raw); + return -1; +} + +static int mov__scnprintf(struct ins *ins, char *bf, size_t size, + struct ins_operands *ops); + +static struct ins_ops arm64_mov_ops = { + .parse = arm64_mov__parse, + .scnprintf = mov__scnprintf, +}; + static struct ins_ops *arm64__associate_instruction_ops(struct arch *arch, const char *name) { struct arm64_annotate *arm = arch->priv; @@ -21,7 +78,7 @@ static struct ins_ops *arm64__associate_instruction_ops(struct arch *arch, const else if (!strcmp(name, "ret")) ops = &ret_ops; else - return NULL; + ops = &arm64_mov_ops; arch__associate_ins_ops(arch, name, ops); return ops; diff --git a/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl b/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl new file mode 100755 index 000000000000..2dbb8cade048 --- /dev/null +++ b/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl @@ -0,0 +1,62 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# +# Generate system call table for perf. Derived from +# powerpc script. +# +# Copyright IBM Corp. 2017 +# Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com> +# Changed by: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com> +# Changed by: Kim Phillips <kim.phillips@arm.com> + +gcc=$1 +hostcc=$2 +incpath=$3 +input=$4 + +if ! test -r $input; then + echo "Could not read input file" >&2 + exit 1 +fi + +create_table_from_c() +{ + local sc nr last_sc + + create_table_exe=`mktemp /tmp/create-table-XXXXXX` + + { + + cat <<-_EoHEADER + #include <stdio.h> + #include "$input" + int main(int argc, char *argv[]) + { + _EoHEADER + + while read sc nr; do + printf "%s\n" " printf(\"\\t[%d] = \\\"$sc\\\",\\n\", __NR_$sc);" + last_sc=$sc + done + + printf "%s\n" " printf(\"#define SYSCALLTBL_ARM64_MAX_ID %d\\n\", __NR_$last_sc);" + printf "}\n" + + } | $hostcc -I $incpath/include/uapi -o $create_table_exe -x c - + + $create_table_exe + + rm -f $create_table_exe +} + +create_table() +{ + echo "static const char *syscalltbl_arm64[] = {" + create_table_from_c + echo "};" +} + +$gcc -E -dM -x c $input \ + |sed -ne 's/^#define __NR_//p' \ + |sort -t' ' -k2 -nu \ + |create_table diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c index 1120e39c1b00..5ccfce87e693 100644 --- a/tools/perf/arch/arm64/util/arm-spe.c +++ b/tools/perf/arch/arm64/util/arm-spe.c @@ -194,6 +194,7 @@ struct auxtrace_record *arm_spe_recording_init(int *err, sper->itr.read_finish = arm_spe_read_finish; sper->itr.alignment = 0; + *err = 0; return &sper->itr; } diff --git a/tools/perf/arch/powerpc/util/book3s_hv_exits.h b/tools/perf/arch/powerpc/util/book3s_hv_exits.h index 853b95d1e139..2011376c7ab5 100644 --- a/tools/perf/arch/powerpc/util/book3s_hv_exits.h +++ b/tools/perf/arch/powerpc/util/book3s_hv_exits.h @@ -15,7 +15,6 @@ {0x400, "INST_STORAGE"}, \ {0x480, "INST_SEGMENT"}, \ {0x500, "EXTERNAL"}, \ - {0x501, "EXTERNAL_LEVEL"}, \ {0x502, "EXTERNAL_HV"}, \ {0x600, "ALIGNMENT"}, \ {0x700, "PROGRAM"}, \ diff --git a/tools/perf/arch/powerpc/util/skip-callchain-idx.c b/tools/perf/arch/powerpc/util/skip-callchain-idx.c index ef5d59a5742e..7c6eeb4633fe 100644 --- a/tools/perf/arch/powerpc/util/skip-callchain-idx.c +++ b/tools/perf/arch/powerpc/util/skip-callchain-idx.c @@ -58,9 +58,13 @@ static int check_return_reg(int ra_regno, Dwarf_Frame *frame) } /* - * Check if return address is on the stack. + * Check if return address is on the stack. If return address + * is in a register (typically R0), it is yet to be saved on + * the stack. */ - if (nops != 0 || ops != NULL) + if ((nops != 0 || ops != NULL) && + !(nops == 1 && ops[0].atom == DW_OP_regx && + ops[0].number2 == 0 && ops[0].offset == 0)) return 0; /* @@ -246,7 +250,7 @@ int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain) if (!chain || chain->nr < 3) return skip_slot; - ip = chain->ips[2]; + ip = chain->ips[1]; thread__find_symbol(thread, PERF_RECORD_MISC_USER, ip, &al); diff --git a/tools/perf/arch/powerpc/util/sym-handling.c b/tools/perf/arch/powerpc/util/sym-handling.c index 53d83d7e6a09..10a44e946f77 100644 --- a/tools/perf/arch/powerpc/util/sym-handling.c +++ b/tools/perf/arch/powerpc/util/sym-handling.c @@ -22,15 +22,16 @@ bool elf__needs_adjust_symbols(GElf_Ehdr ehdr) #endif -#if !defined(_CALL_ELF) || _CALL_ELF != 2 int arch__choose_best_symbol(struct symbol *syma, struct symbol *symb __maybe_unused) { char *sym = syma->name; +#if !defined(_CALL_ELF) || _CALL_ELF != 2 /* Skip over any initial dot */ if (*sym == '.') sym++; +#endif /* Avoid "SyS" kernel syscall aliases */ if (strlen(sym) >= 3 && !strncmp(sym, "SyS", 3)) @@ -41,6 +42,7 @@ int arch__choose_best_symbol(struct symbol *syma, return SYMBOL_A; } +#if !defined(_CALL_ELF) || _CALL_ELF != 2 /* Allow matching against dot variants */ int arch__compare_symbol_names(const char *namea, const char *nameb) { @@ -141,8 +143,10 @@ void arch__post_process_probe_trace_events(struct perf_probe_event *pev, for (i = 0; i < ntevs; i++) { tev = &pev->tevs[i]; map__for_each_symbol(map, sym, tmp) { - if (map->unmap_ip(map, sym->start) == tev->point.address) + if (map->unmap_ip(map, sym->start) == tev->point.address) { arch__fix_tev_from_maps(pev, tev, map, sym); + break; + } } } } diff --git a/tools/perf/arch/s390/annotate/instructions.c b/tools/perf/arch/s390/annotate/instructions.c index cee4e2f7c057..de0dd66dbb48 100644 --- a/tools/perf/arch/s390/annotate/instructions.c +++ b/tools/perf/arch/s390/annotate/instructions.c @@ -100,8 +100,6 @@ out_free_source: return -1; } -static int mov__scnprintf(struct ins *ins, char *bf, size_t size, - struct ins_operands *ops); static struct ins_ops s390_mov_ops = { .parse = s390_mov__parse, diff --git a/tools/perf/arch/s390/util/auxtrace.c b/tools/perf/arch/s390/util/auxtrace.c index 3afe8256eff2..44c857388897 100644 --- a/tools/perf/arch/s390/util/auxtrace.c +++ b/tools/perf/arch/s390/util/auxtrace.c @@ -30,6 +30,7 @@ cpumsf_info_fill(struct auxtrace_record *itr __maybe_unused, struct auxtrace_info_event *auxtrace_info __maybe_unused, size_t priv_size __maybe_unused) { + auxtrace_info->type = PERF_AUXTRACE_S390_CPUMSF; return 0; } diff --git a/tools/perf/arch/s390/util/kvm-stat.c b/tools/perf/arch/s390/util/kvm-stat.c index d233e2eb9592..aaabab5e2830 100644 --- a/tools/perf/arch/s390/util/kvm-stat.c +++ b/tools/perf/arch/s390/util/kvm-stat.c @@ -102,7 +102,7 @@ const char * const kvm_skip_events[] = { int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid) { - if (strstr(cpuid, "IBM/S390")) { + if (strstr(cpuid, "IBM")) { kvm->exit_reasons = sie_exit_reasons; kvm->exit_reasons_isa = "SIE"; } else diff --git a/tools/perf/arch/x86/Makefile b/tools/perf/arch/x86/Makefile index 1a38e78117ce..8cc6642fce7a 100644 --- a/tools/perf/arch/x86/Makefile +++ b/tools/perf/arch/x86/Makefile @@ -19,9 +19,6 @@ systbl := $(sys)/syscalltbl.sh _dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)') $(header): $(sys)/syscall_64.tbl $(systbl) - @(test -d ../../kernel -a -d ../../tools -a -d ../perf && ( \ - (diff -B arch/x86/entry/syscalls/syscall_64.tbl ../../arch/x86/entry/syscalls/syscall_64.tbl >/dev/null) \ - || echo "Warning: Kernel ABI header at 'tools/perf/arch/x86/entry/syscalls/syscall_64.tbl' differs from latest version at 'arch/x86/entry/syscalls/syscall_64.tbl'" >&2 )) || true $(Q)$(SHELL) '$(systbl)' $(sys)/syscall_64.tbl 'x86_64' > $@ clean:: diff --git a/tools/perf/arch/x86/include/arch-tests.h b/tools/perf/arch/x86/include/arch-tests.h index c1bd979b957b..613709cfbbd0 100644 --- a/tools/perf/arch/x86/include/arch-tests.h +++ b/tools/perf/arch/x86/include/arch-tests.h @@ -9,6 +9,7 @@ struct test; int test__rdpmc(struct test *test __maybe_unused, int subtest); int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest); int test__insn_x86(struct test *test __maybe_unused, int subtest); +int test__bp_modify(struct test *test, int subtest); #ifdef HAVE_DWARF_UNWIND_SUPPORT struct thread; diff --git a/tools/perf/arch/x86/tests/Build b/tools/perf/arch/x86/tests/Build index 8e2c5a38c3b9..586849ff83a0 100644 --- a/tools/perf/arch/x86/tests/Build +++ b/tools/perf/arch/x86/tests/Build @@ -5,3 +5,4 @@ libperf-y += arch-tests.o libperf-y += rdpmc.o libperf-y += perf-time-to-tsc.o libperf-$(CONFIG_AUXTRACE) += insn-x86.o +libperf-$(CONFIG_X86_64) += bp-modify.o diff --git a/tools/perf/arch/x86/tests/arch-tests.c b/tools/perf/arch/x86/tests/arch-tests.c index cc1802ff5410..d47d3f8e3c8e 100644 --- a/tools/perf/arch/x86/tests/arch-tests.c +++ b/tools/perf/arch/x86/tests/arch-tests.c @@ -24,6 +24,12 @@ struct test arch_tests[] = { .func = test__insn_x86, }, #endif +#if defined(__x86_64__) + { + .desc = "x86 bp modify", + .func = test__bp_modify, + }, +#endif { .func = NULL, }, diff --git a/tools/perf/arch/x86/tests/bp-modify.c b/tools/perf/arch/x86/tests/bp-modify.c new file mode 100644 index 000000000000..f53e4406709f --- /dev/null +++ b/tools/perf/arch/x86/tests/bp-modify.c @@ -0,0 +1,213 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/compiler.h> +#include <sys/types.h> +#include <sys/wait.h> +#include <sys/user.h> +#include <syscall.h> +#include <unistd.h> +#include <stdio.h> +#include <stdlib.h> +#include <sys/ptrace.h> +#include <asm/ptrace.h> +#include <errno.h> +#include "debug.h" +#include "tests/tests.h" +#include "arch-tests.h" + +static noinline int bp_1(void) +{ + pr_debug("in %s\n", __func__); + return 0; +} + +static noinline int bp_2(void) +{ + pr_debug("in %s\n", __func__); + return 0; +} + +static int spawn_child(void) +{ + int child = fork(); + + if (child == 0) { + /* + * The child sets itself for as tracee and + * waits in signal for parent to trace it, + * then it calls bp_1 and quits. + */ + int err = ptrace(PTRACE_TRACEME, 0, NULL, NULL); + + if (err) { + pr_debug("failed to PTRACE_TRACEME\n"); + exit(1); + } + + raise(SIGCONT); + bp_1(); + exit(0); + } + + return child; +} + +/* + * This tests creates HW breakpoint, tries to + * change it and checks it was properly changed. + */ +static int bp_modify1(void) +{ + pid_t child; + int status; + unsigned long rip = 0, dr7 = 1; + + child = spawn_child(); + + waitpid(child, &status, 0); + if (WIFEXITED(status)) { + pr_debug("tracee exited prematurely 1\n"); + return TEST_FAIL; + } + + /* + * The parent does following steps: + * - creates a new breakpoint (id 0) for bp_2 function + * - changes that breakponit to bp_1 function + * - waits for the breakpoint to hit and checks + * it has proper rip of bp_1 function + * - detaches the child + */ + if (ptrace(PTRACE_POKEUSER, child, + offsetof(struct user, u_debugreg[0]), bp_2)) { + pr_debug("failed to set breakpoint, 1st time: %s\n", + strerror(errno)); + goto out; + } + + if (ptrace(PTRACE_POKEUSER, child, + offsetof(struct user, u_debugreg[0]), bp_1)) { + pr_debug("failed to set breakpoint, 2nd time: %s\n", + strerror(errno)); + goto out; + } + + if (ptrace(PTRACE_POKEUSER, child, + offsetof(struct user, u_debugreg[7]), dr7)) { + pr_debug("failed to set dr7: %s\n", strerror(errno)); + goto out; + } + + if (ptrace(PTRACE_CONT, child, NULL, NULL)) { + pr_debug("failed to PTRACE_CONT: %s\n", strerror(errno)); + goto out; + } + + waitpid(child, &status, 0); + if (WIFEXITED(status)) { + pr_debug("tracee exited prematurely 2\n"); + return TEST_FAIL; + } + + rip = ptrace(PTRACE_PEEKUSER, child, + offsetof(struct user_regs_struct, rip), NULL); + if (rip == (unsigned long) -1) { + pr_debug("failed to PTRACE_PEEKUSER: %s\n", + strerror(errno)); + goto out; + } + + pr_debug("rip %lx, bp_1 %p\n", rip, bp_1); + +out: + if (ptrace(PTRACE_DETACH, child, NULL, NULL)) { + pr_debug("failed to PTRACE_DETACH: %s", strerror(errno)); + return TEST_FAIL; + } + + return rip == (unsigned long) bp_1 ? TEST_OK : TEST_FAIL; +} + +/* + * This tests creates HW breakpoint, tries to + * change it to bogus value and checks the original + * breakpoint is hit. + */ +static int bp_modify2(void) +{ + pid_t child; + int status; + unsigned long rip = 0, dr7 = 1; + + child = spawn_child(); + + waitpid(child, &status, 0); + if (WIFEXITED(status)) { + pr_debug("tracee exited prematurely 1\n"); + return TEST_FAIL; + } + + /* + * The parent does following steps: + * - creates a new breakpoint (id 0) for bp_1 function + * - tries to change that breakpoint to (-1) address + * - waits for the breakpoint to hit and checks + * it has proper rip of bp_1 function + * - detaches the child + */ + if (ptrace(PTRACE_POKEUSER, child, + offsetof(struct user, u_debugreg[0]), bp_1)) { + pr_debug("failed to set breakpoint: %s\n", + strerror(errno)); + goto out; + } + + if (ptrace(PTRACE_POKEUSER, child, + offsetof(struct user, u_debugreg[7]), dr7)) { + pr_debug("failed to set dr7: %s\n", strerror(errno)); + goto out; + } + + if (!ptrace(PTRACE_POKEUSER, child, + offsetof(struct user, u_debugreg[0]), (unsigned long) (-1))) { + pr_debug("failed, breakpoint set to bogus address\n"); + goto out; + } + + if (ptrace(PTRACE_CONT, child, NULL, NULL)) { + pr_debug("failed to PTRACE_CONT: %s\n", strerror(errno)); + goto out; + } + + waitpid(child, &status, 0); + if (WIFEXITED(status)) { + pr_debug("tracee exited prematurely 2\n"); + return TEST_FAIL; + } + + rip = ptrace(PTRACE_PEEKUSER, child, + offsetof(struct user_regs_struct, rip), NULL); + if (rip == (unsigned long) -1) { + pr_debug("failed to PTRACE_PEEKUSER: %s\n", + strerror(errno)); + goto out; + } + + pr_debug("rip %lx, bp_1 %p\n", rip, bp_1); + +out: + if (ptrace(PTRACE_DETACH, child, NULL, NULL)) { + pr_debug("failed to PTRACE_DETACH: %s", strerror(errno)); + return TEST_FAIL; + } + + return rip == (unsigned long) bp_1 ? TEST_OK : TEST_FAIL; +} + +int test__bp_modify(struct test *test __maybe_unused, + int subtest __maybe_unused) +{ + TEST_ASSERT_VAL("modify test 1 failed\n", !bp_modify1()); + TEST_ASSERT_VAL("modify test 2 failed\n", !bp_modify2()); + + return 0; +} diff --git a/tools/perf/arch/x86/util/pmu.c b/tools/perf/arch/x86/util/pmu.c index 63a74c32ddc5..e33ef5bc31c5 100644 --- a/tools/perf/arch/x86/util/pmu.c +++ b/tools/perf/arch/x86/util/pmu.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <string.h> +#include <linux/stddef.h> #include <linux/perf_event.h> #include "../../util/intel-pt.h" diff --git a/tools/perf/arch/x86/util/tsc.c b/tools/perf/arch/x86/util/tsc.c index 06bae7023a51..950539f9a4f7 100644 --- a/tools/perf/arch/x86/util/tsc.c +++ b/tools/perf/arch/x86/util/tsc.c @@ -2,6 +2,7 @@ #include <stdbool.h> #include <errno.h> +#include <linux/stddef.h> #include <linux/perf_event.h> #include "../../perf.h" diff --git a/tools/perf/bench/Build b/tools/perf/bench/Build index 60bf11943047..eafce1a130a1 100644 --- a/tools/perf/bench/Build +++ b/tools/perf/bench/Build @@ -7,6 +7,7 @@ perf-y += futex-wake-parallel.o perf-y += futex-requeue.o perf-y += futex-lock-pi.o +perf-$(CONFIG_X86_64) += mem-memcpy-x86-64-lib.o perf-$(CONFIG_X86_64) += mem-memcpy-x86-64-asm.o perf-$(CONFIG_X86_64) += mem-memset-x86-64-asm.o diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm.S b/tools/perf/bench/mem-memcpy-x86-64-asm.S index b43f8d2a34ec..9ad015a1e202 100644 --- a/tools/perf/bench/mem-memcpy-x86-64-asm.S +++ b/tools/perf/bench/mem-memcpy-x86-64-asm.S @@ -6,6 +6,7 @@ #define altinstr_replacement text #define globl p2align 4; .globl #define _ASM_EXTABLE_FAULT(x, y) +#define _ASM_EXTABLE(x, y) #include "../../arch/x86/lib/memcpy_64.S" /* diff --git a/tools/perf/bench/mem-memcpy-x86-64-lib.c b/tools/perf/bench/mem-memcpy-x86-64-lib.c new file mode 100644 index 000000000000..4130734dde84 --- /dev/null +++ b/tools/perf/bench/mem-memcpy-x86-64-lib.c @@ -0,0 +1,24 @@ +/* + * From code in arch/x86/lib/usercopy_64.c, copied to keep tools/ copy + * of the kernel's arch/x86/lib/memcpy_64.s used in 'perf bench mem memcpy' + * happy. + */ +#include <linux/types.h> + +unsigned long __memcpy_mcsafe(void *dst, const void *src, size_t cnt); +unsigned long mcsafe_handle_tail(char *to, char *from, unsigned len); + +unsigned long mcsafe_handle_tail(char *to, char *from, unsigned len) +{ + for (; len; --len, to++, from++) { + /* + * Call the assembly routine back directly since + * memcpy_mcsafe() may silently fallback to memcpy. + */ + unsigned long rem = __memcpy_mcsafe(to, from, 1); + + if (rem) + break; + } + return len; +} diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index 8180319285af..93d679eaf1f4 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -283,12 +283,11 @@ out_put: return ret; } -static int process_feature_event(struct perf_tool *tool, - union perf_event *event, - struct perf_session *session) +static int process_feature_event(struct perf_session *session, + union perf_event *event) { if (event->feat.feat_id < HEADER_LAST_FEATURE) - return perf_event__process_feature(tool, event, session); + return perf_event__process_feature(session, event); return 0; } @@ -542,6 +541,10 @@ int cmd_annotate(int argc, const char **argv) OPT_CALLBACK_DEFAULT(0, "stdio-color", NULL, "mode", "'always' (default), 'never' or 'auto' only applicable to --stdio mode", stdio__config_color, "always"), + OPT_CALLBACK(0, "percent-type", &annotate.opts, "local-period", + "Set percent type local/global-period/hits", + annotate_parse_percent_type), + OPT_END() }; int ret; diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c index 6a8738f7ead3..f3aa9d02a5ab 100644 --- a/tools/perf/builtin-c2c.c +++ b/tools/perf/builtin-c2c.c @@ -2193,7 +2193,7 @@ static void print_cacheline(struct c2c_hists *c2c_hists, fprintf(out, "%s\n", bf); fprintf(out, " -------------------------------------------------------------\n"); - hists__fprintf(&c2c_hists->hists, false, 0, 0, 0, out, true); + hists__fprintf(&c2c_hists->hists, false, 0, 0, 0, out, false); } static void print_pareto(FILE *out) @@ -2268,7 +2268,7 @@ static void perf_c2c__hists_fprintf(FILE *out, struct perf_session *session) fprintf(out, "=================================================\n"); fprintf(out, "#\n"); - hists__fprintf(&c2c.hists.hists, true, 0, 0, 0, stdout, false); + hists__fprintf(&c2c.hists.hists, true, 0, 0, 0, stdout, true); fprintf(out, "\n"); fprintf(out, "=================================================\n"); @@ -2349,6 +2349,9 @@ static int perf_c2c__browse_cacheline(struct hist_entry *he) " s Toggle full length of symbol and source line columns \n" " q Return back to cacheline list \n"; + if (!he) + return 0; + /* Display compact version first. */ c2c.symbol_full = false; diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index d660cb7b222b..39db2ee32d48 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -696,7 +696,7 @@ static void hists__process(struct hists *hists) hists__output_resort(hists, NULL); hists__fprintf(hists, !quiet, 0, 0, 0, stdout, - symbol_conf.use_callchain); + !symbol_conf.use_callchain); } static void data__fprintf(void) diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index a3b346359ba0..eda41673c4f3 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -86,12 +86,10 @@ static int perf_event__drop_oe(struct perf_tool *tool __maybe_unused, } #endif -static int perf_event__repipe_op2_synth(struct perf_tool *tool, - union perf_event *event, - struct perf_session *session - __maybe_unused) +static int perf_event__repipe_op2_synth(struct perf_session *session, + union perf_event *event) { - return perf_event__repipe_synth(tool, event); + return perf_event__repipe_synth(session->tool, event); } static int perf_event__repipe_attr(struct perf_tool *tool, @@ -133,10 +131,10 @@ static int copy_bytes(struct perf_inject *inject, int fd, off_t size) return 0; } -static s64 perf_event__repipe_auxtrace(struct perf_tool *tool, - union perf_event *event, - struct perf_session *session) +static s64 perf_event__repipe_auxtrace(struct perf_session *session, + union perf_event *event) { + struct perf_tool *tool = session->tool; struct perf_inject *inject = container_of(tool, struct perf_inject, tool); int ret; @@ -174,9 +172,8 @@ static s64 perf_event__repipe_auxtrace(struct perf_tool *tool, #else static s64 -perf_event__repipe_auxtrace(struct perf_tool *tool __maybe_unused, - union perf_event *event __maybe_unused, - struct perf_session *session __maybe_unused) +perf_event__repipe_auxtrace(struct perf_session *session __maybe_unused, + union perf_event *event __maybe_unused) { pr_err("AUX area tracing not supported\n"); return -EINVAL; @@ -362,26 +359,24 @@ static int perf_event__repipe_exit(struct perf_tool *tool, return err; } -static int perf_event__repipe_tracing_data(struct perf_tool *tool, - union perf_event *event, - struct perf_session *session) +static int perf_event__repipe_tracing_data(struct perf_session *session, + union perf_event *event) { int err; - perf_event__repipe_synth(tool, event); - err = perf_event__process_tracing_data(tool, event, session); + perf_event__repipe_synth(session->tool, event); + err = perf_event__process_tracing_data(session, event); return err; } -static int perf_event__repipe_id_index(struct perf_tool *tool, - union perf_event *event, - struct perf_session *session) +static int perf_event__repipe_id_index(struct perf_session *session, + union perf_event *event) { int err; - perf_event__repipe_synth(tool, event); - err = perf_event__process_id_index(tool, event, session); + perf_event__repipe_synth(session->tool, event); + err = perf_event__process_id_index(session, event); return err; } @@ -803,7 +798,8 @@ int cmd_inject(int argc, const char **argv) "kallsyms pathname"), OPT_BOOLEAN('f', "force", &data.force, "don't complain, do it"), OPT_CALLBACK_OPTARG(0, "itrace", &inject.itrace_synth_opts, - NULL, "opts", "Instruction Tracing options", + NULL, "opts", "Instruction Tracing options\n" + ITRACE_HELP, itrace_parse_synth_opts), OPT_BOOLEAN(0, "strip", &inject.strip, "strip non-synthesized events (use with --itrace)"), diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index 54d3f21b0e62..b63bca4b0c2a 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -729,7 +729,7 @@ static char *compact_gfp_string(unsigned long gfp_flags) static int parse_gfp_flags(struct perf_evsel *evsel, struct perf_sample *sample, unsigned int gfp_flags) { - struct pevent_record record = { + struct tep_record record = { .cpu = sample->cpu, .data = sample->raw_data, .size = sample->raw_size, @@ -747,7 +747,7 @@ static int parse_gfp_flags(struct perf_evsel *evsel, struct perf_sample *sample, } trace_seq_init(&seq); - pevent_event_info(&seq, evsel->tp_format, &record); + tep_event_info(&seq, evsel->tp_format, &record); str = strtok_r(seq.buffer, " ", &pos); while (str) { @@ -1974,7 +1974,7 @@ int cmd_kmem(int argc, const char **argv) goto out_delete; } - kmem_page_size = pevent_get_page_size(evsel->tp_format->pevent); + kmem_page_size = tep_get_page_size(evsel->tp_format->pevent); symbol_conf.use_callchain = true; } diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 22ebeb92ac51..0980dfe3396b 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -106,9 +106,12 @@ static bool switch_output_time(struct record *rec) trigger_is_ready(&switch_output_trigger); } -static int record__write(struct record *rec, void *bf, size_t size) +static int record__write(struct record *rec, struct perf_mmap *map __maybe_unused, + void *bf, size_t size) { - if (perf_data__write(rec->session->data, bf, size) < 0) { + struct perf_data_file *file = &rec->session->data->file; + + if (perf_data_file__write(file, bf, size) < 0) { pr_err("failed to write perf data, error: %m\n"); return -1; } @@ -127,15 +130,15 @@ static int process_synthesized_event(struct perf_tool *tool, struct machine *machine __maybe_unused) { struct record *rec = container_of(tool, struct record, tool); - return record__write(rec, event, event->header.size); + return record__write(rec, NULL, event, event->header.size); } -static int record__pushfn(void *to, void *bf, size_t size) +static int record__pushfn(struct perf_mmap *map, void *to, void *bf, size_t size) { struct record *rec = to; rec->samples++; - return record__write(rec, bf, size); + return record__write(rec, map, bf, size); } static volatile int done; @@ -170,6 +173,7 @@ static void record__sig_exit(void) #ifdef HAVE_AUXTRACE_SUPPORT static int record__process_auxtrace(struct perf_tool *tool, + struct perf_mmap *map, union perf_event *event, void *data1, size_t len1, void *data2, size_t len2) { @@ -197,21 +201,21 @@ static int record__process_auxtrace(struct perf_tool *tool, if (padding) padding = 8 - padding; - record__write(rec, event, event->header.size); - record__write(rec, data1, len1); + record__write(rec, map, event, event->header.size); + record__write(rec, map, data1, len1); if (len2) - record__write(rec, data2, len2); - record__write(rec, &pad, padding); + record__write(rec, map, data2, len2); + record__write(rec, map, &pad, padding); return 0; } static int record__auxtrace_mmap_read(struct record *rec, - struct auxtrace_mmap *mm) + struct perf_mmap *map) { int ret; - ret = auxtrace_mmap__read(mm, rec->itr, &rec->tool, + ret = auxtrace_mmap__read(map, rec->itr, &rec->tool, record__process_auxtrace); if (ret < 0) return ret; @@ -223,11 +227,11 @@ static int record__auxtrace_mmap_read(struct record *rec, } static int record__auxtrace_mmap_read_snapshot(struct record *rec, - struct auxtrace_mmap *mm) + struct perf_mmap *map) { int ret; - ret = auxtrace_mmap__read_snapshot(mm, rec->itr, &rec->tool, + ret = auxtrace_mmap__read_snapshot(map, rec->itr, &rec->tool, record__process_auxtrace, rec->opts.auxtrace_snapshot_size); if (ret < 0) @@ -245,13 +249,12 @@ static int record__auxtrace_read_snapshot_all(struct record *rec) int rc = 0; for (i = 0; i < rec->evlist->nr_mmaps; i++) { - struct auxtrace_mmap *mm = - &rec->evlist->mmap[i].auxtrace_mmap; + struct perf_mmap *map = &rec->evlist->mmap[i]; - if (!mm->base) + if (!map->auxtrace_mmap.base) continue; - if (record__auxtrace_mmap_read_snapshot(rec, mm) != 0) { + if (record__auxtrace_mmap_read_snapshot(rec, map) != 0) { rc = -1; goto out; } @@ -295,7 +298,7 @@ static int record__auxtrace_init(struct record *rec) static inline int record__auxtrace_mmap_read(struct record *rec __maybe_unused, - struct auxtrace_mmap *mm __maybe_unused) + struct perf_mmap *map __maybe_unused) { return 0; } @@ -529,17 +532,17 @@ static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evli return 0; for (i = 0; i < evlist->nr_mmaps; i++) { - struct auxtrace_mmap *mm = &maps[i].auxtrace_mmap; + struct perf_mmap *map = &maps[i]; - if (maps[i].base) { - if (perf_mmap__push(&maps[i], rec, record__pushfn) != 0) { + if (map->base) { + if (perf_mmap__push(map, rec, record__pushfn) != 0) { rc = -1; goto out; } } - if (mm->base && !rec->opts.auxtrace_snapshot_mode && - record__auxtrace_mmap_read(rec, mm) != 0) { + if (map->auxtrace_mmap.base && !rec->opts.auxtrace_snapshot_mode && + record__auxtrace_mmap_read(rec, map) != 0) { rc = -1; goto out; } @@ -550,7 +553,7 @@ static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evli * at least one event. */ if (bytes_written != rec->bytes_written) - rc = record__write(rec, &finished_round_event, sizeof(finished_round_event)); + rc = record__write(rec, NULL, &finished_round_event, sizeof(finished_round_event)); if (overwrite) perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_EMPTY); @@ -758,7 +761,7 @@ static int record__synthesize(struct record *rec, bool tail) * We need to synthesize events first, because some * features works on top of them (on report side). */ - err = perf_event__synthesize_attrs(tool, session, + err = perf_event__synthesize_attrs(tool, rec->evlist, process_synthesized_event); if (err < 0) { pr_err("Couldn't synthesize attrs.\n"); diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index c04dc7b53797..257c9c18cb7e 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -201,14 +201,13 @@ static void setup_forced_leader(struct report *report, perf_evlist__force_leader(evlist); } -static int process_feature_event(struct perf_tool *tool, - union perf_event *event, - struct perf_session *session __maybe_unused) +static int process_feature_event(struct perf_session *session, + union perf_event *event) { - struct report *rep = container_of(tool, struct report, tool); + struct report *rep = container_of(session->tool, struct report, tool); if (event->feat.feat_id < HEADER_LAST_FEATURE) - return perf_event__process_feature(tool, event, session); + return perf_event__process_feature(session, event); if (event->feat.feat_id != HEADER_LAST_FEATURE) { pr_err("failed: wrong feature ID: %" PRIu64 "\n", @@ -478,8 +477,8 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist, hists__fprintf_nr_sample_events(hists, rep, evname, stdout); hists__fprintf(hists, !quiet, 0, 0, rep->min_percent, stdout, - symbol_conf.use_callchain || - symbol_conf.show_branchflag_count); + !(symbol_conf.use_callchain || + symbol_conf.show_branchflag_count)); fprintf(stdout, "\n\n"); } @@ -981,6 +980,7 @@ int cmd_report(int argc, const char **argv) .id_index = perf_event__process_id_index, .auxtrace_info = perf_event__process_auxtrace_info, .auxtrace = perf_event__process_auxtrace, + .event_update = perf_event__process_event_update, .feature = process_feature_event, .ordered_events = true, .ordering_requires_timestamps = true, @@ -1105,7 +1105,7 @@ int cmd_report(int argc, const char **argv) OPT_CALLBACK(0, "percentage", NULL, "relative|absolute", "how to display percentage of filtered entries", parse_filter_percentage), OPT_CALLBACK_OPTARG(0, "itrace", &itrace_synth_opts, NULL, "opts", - "Instruction Tracing options", + "Instruction Tracing options\n" ITRACE_HELP, itrace_parse_synth_opts), OPT_BOOLEAN(0, "full-source-path", &srcline_full_filename, "Show full source file name path for source lines"), @@ -1124,6 +1124,9 @@ int cmd_report(int argc, const char **argv) "Time span of interest (start,stop)"), OPT_BOOLEAN(0, "inline", &symbol_conf.inline_name, "Show inline function"), + OPT_CALLBACK(0, "percent-type", &report.annotation_opts, "local-period", + "Set percent type local/global-period/hits", + annotate_parse_percent_type), OPT_END() }; struct perf_data data = { @@ -1366,9 +1369,9 @@ repeat: } if (session->tevent.pevent && - pevent_set_function_resolver(session->tevent.pevent, - machine__resolve_kernel_addr, - &session->machines.host) < 0) { + tep_set_function_resolver(session->tevent.pevent, + machine__resolve_kernel_addr, + &session->machines.host) < 0) { pr_err("%s: failed to set libtraceevent function resolver\n", __func__); return -1; diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 568ddfac3213..4da5e32b9e03 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -406,9 +406,10 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel, PERF_OUTPUT_WEIGHT)) return -EINVAL; - if (PRINT_FIELD(SYM) && !PRINT_FIELD(IP) && !PRINT_FIELD(ADDR)) { + if (PRINT_FIELD(SYM) && + !(evsel->attr.sample_type & (PERF_SAMPLE_IP|PERF_SAMPLE_ADDR))) { pr_err("Display of symbols requested but neither sample IP nor " - "sample address\nis selected. Hence, no addresses to convert " + "sample address\navailable. Hence, no addresses to convert " "to symbols.\n"); return -EINVAL; } @@ -417,10 +418,9 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel, "selected.\n"); return -EINVAL; } - if (PRINT_FIELD(DSO) && !PRINT_FIELD(IP) && !PRINT_FIELD(ADDR) && - !PRINT_FIELD(BRSTACK) && !PRINT_FIELD(BRSTACKSYM) && !PRINT_FIELD(BRSTACKOFF)) { - pr_err("Display of DSO requested but no address to convert. Select\n" - "sample IP, sample address, brstack, brstacksym, or brstackoff.\n"); + if (PRINT_FIELD(DSO) && + !(evsel->attr.sample_type & (PERF_SAMPLE_IP|PERF_SAMPLE_ADDR))) { + pr_err("Display of DSO requested but no address to convert.\n"); return -EINVAL; } if (PRINT_FIELD(SRCLINE) && !PRINT_FIELD(IP)) { @@ -1115,6 +1115,7 @@ static int perf_sample__fprintf_callindent(struct perf_sample *sample, const char *name = NULL; static int spacing; int len = 0; + int dlen = 0; u64 ip = 0; /* @@ -1141,6 +1142,12 @@ static int perf_sample__fprintf_callindent(struct perf_sample *sample, ip = sample->ip; } + if (PRINT_FIELD(DSO) && !(PRINT_FIELD(IP) || PRINT_FIELD(ADDR))) { + dlen += fprintf(fp, "("); + dlen += map__fprintf_dsoname(al->map, fp); + dlen += fprintf(fp, ")\t"); + } + if (name) len = fprintf(fp, "%*s%s", (int)depth * 4, "", name); else if (ip) @@ -1159,7 +1166,7 @@ static int perf_sample__fprintf_callindent(struct perf_sample *sample, if (len < spacing) len += fprintf(fp, "%*s", spacing - len, ""); - return len; + return len + dlen; } static int perf_sample__fprintf_insn(struct perf_sample *sample, @@ -1255,6 +1262,18 @@ static struct { {0, NULL} }; +static const char *sample_flags_to_name(u32 flags) +{ + int i; + + for (i = 0; sample_flags[i].name ; i++) { + if (sample_flags[i].flags == flags) + return sample_flags[i].name; + } + + return NULL; +} + static int perf_sample__fprintf_flags(u32 flags, FILE *fp) { const char *chars = PERF_IP_FLAG_CHARS; @@ -1264,11 +1283,20 @@ static int perf_sample__fprintf_flags(u32 flags, FILE *fp) char str[33]; int i, pos = 0; - for (i = 0; sample_flags[i].name ; i++) { - if (sample_flags[i].flags == (flags & ~PERF_IP_FLAG_IN_TX)) { - name = sample_flags[i].name; - break; - } + name = sample_flags_to_name(flags & ~PERF_IP_FLAG_IN_TX); + if (name) + return fprintf(fp, " %-15s%4s ", name, in_tx ? "(x)" : ""); + + if (flags & PERF_IP_FLAG_TRACE_BEGIN) { + name = sample_flags_to_name(flags & ~(PERF_IP_FLAG_IN_TX | PERF_IP_FLAG_TRACE_BEGIN)); + if (name) + return fprintf(fp, " tr strt %-7s%4s ", name, in_tx ? "(x)" : ""); + } + + if (flags & PERF_IP_FLAG_TRACE_END) { + name = sample_flags_to_name(flags & ~(PERF_IP_FLAG_IN_TX | PERF_IP_FLAG_TRACE_END)); + if (name) + return fprintf(fp, " tr end %-7s%4s ", name, in_tx ? "(x)" : ""); } for (i = 0; i < n; i++, flags >>= 1) { @@ -1281,10 +1309,7 @@ static int perf_sample__fprintf_flags(u32 flags, FILE *fp) } str[pos] = 0; - if (name) - return fprintf(fp, " %-7s%4s ", name, in_tx ? "(x)" : ""); - - return fprintf(fp, " %-11s ", str); + return fprintf(fp, " %-19s ", str); } struct printer_data { @@ -1544,7 +1569,8 @@ struct metric_ctx { FILE *fp; }; -static void script_print_metric(void *ctx, const char *color, +static void script_print_metric(struct perf_stat_config *config __maybe_unused, + void *ctx, const char *color, const char *fmt, const char *unit, double val) { @@ -1562,7 +1588,8 @@ static void script_print_metric(void *ctx, const char *color, fprintf(mctx->fp, " %s\n", unit); } -static void script_new_line(void *ctx) +static void script_new_line(struct perf_stat_config *config __maybe_unused, + void *ctx) { struct metric_ctx *mctx = ctx; @@ -1608,7 +1635,7 @@ static void perf_sample__fprint_metric(struct perf_script *script, evsel_script(evsel)->val = val; if (evsel_script(evsel->leader)->gnum == evsel->leader->nr_members) { for_each_group_member (ev2, evsel->leader) { - perf_stat__print_shadow_stats(ev2, + perf_stat__print_shadow_stats(&stat_config, ev2, evsel_script(ev2)->val, sample->cpu, &ctx, @@ -2489,6 +2516,8 @@ parse: output[j].fields &= ~all_output_options[i].field; else output[j].fields |= all_output_options[i].field; + output[j].user_set = true; + output[j].wildcard_set = true; } } } else { @@ -2499,7 +2528,8 @@ parse: rc = -EINVAL; goto out; } - output[type].fields |= all_output_options[i].field; + output[type].user_set = true; + output[type].wildcard_set = true; } } @@ -2963,9 +2993,8 @@ static void script__setup_sample_type(struct perf_script *script) } } -static int process_stat_round_event(struct perf_tool *tool __maybe_unused, - union perf_event *event, - struct perf_session *session) +static int process_stat_round_event(struct perf_session *session, + union perf_event *event) { struct stat_round_event *round = &event->stat_round; struct perf_evsel *counter; @@ -2979,9 +3008,8 @@ static int process_stat_round_event(struct perf_tool *tool __maybe_unused, return 0; } -static int process_stat_config_event(struct perf_tool *tool __maybe_unused, - union perf_event *event, - struct perf_session *session __maybe_unused) +static int process_stat_config_event(struct perf_session *session __maybe_unused, + union perf_event *event) { perf_event__read_stat_config(&stat_config, &event->stat_config); return 0; @@ -3007,10 +3035,10 @@ static int set_maps(struct perf_script *script) } static -int process_thread_map_event(struct perf_tool *tool, - union perf_event *event, - struct perf_session *session __maybe_unused) +int process_thread_map_event(struct perf_session *session, + union perf_event *event) { + struct perf_tool *tool = session->tool; struct perf_script *script = container_of(tool, struct perf_script, tool); if (script->threads) { @@ -3026,10 +3054,10 @@ int process_thread_map_event(struct perf_tool *tool, } static -int process_cpu_map_event(struct perf_tool *tool __maybe_unused, - union perf_event *event, - struct perf_session *session __maybe_unused) +int process_cpu_map_event(struct perf_session *session, + union perf_event *event) { + struct perf_tool *tool = session->tool; struct perf_script *script = container_of(tool, struct perf_script, tool); if (script->cpus) { @@ -3044,21 +3072,21 @@ int process_cpu_map_event(struct perf_tool *tool __maybe_unused, return set_maps(script); } -static int process_feature_event(struct perf_tool *tool, - union perf_event *event, - struct perf_session *session) +static int process_feature_event(struct perf_session *session, + union perf_event *event) { if (event->feat.feat_id < HEADER_LAST_FEATURE) - return perf_event__process_feature(tool, event, session); + return perf_event__process_feature(session, event); return 0; } #ifdef HAVE_AUXTRACE_SUPPORT -static int perf_script__process_auxtrace_info(struct perf_tool *tool, - union perf_event *event, - struct perf_session *session) +static int perf_script__process_auxtrace_info(struct perf_session *session, + union perf_event *event) { - int ret = perf_event__process_auxtrace_info(tool, event, session); + struct perf_tool *tool = session->tool; + + int ret = perf_event__process_auxtrace_info(session, event); if (ret == 0) { struct perf_script *script = container_of(tool, struct perf_script, tool); @@ -3193,7 +3221,7 @@ int cmd_script(int argc, const char **argv) OPT_BOOLEAN(0, "ns", &nanosecs, "Use 9 decimal places when displaying time"), OPT_CALLBACK_OPTARG(0, "itrace", &itrace_synth_opts, NULL, "opts", - "Instruction Tracing options", + "Instruction Tracing options\n" ITRACE_HELP, itrace_parse_synth_opts), OPT_BOOLEAN(0, "full-source-path", &srcline_full_filename, "Show full source file name path for source lines"), @@ -3429,9 +3457,9 @@ int cmd_script(int argc, const char **argv) symbol_conf.use_callchain = false; if (session->tevent.pevent && - pevent_set_function_resolver(session->tevent.pevent, - machine__resolve_kernel_addr, - &session->machines.host) < 0) { + tep_set_function_resolver(session->tevent.pevent, + machine__resolve_kernel_addr, + &session->machines.host) < 0) { pr_err("%s: failed to set libtraceevent function resolver\n", __func__); err = -1; goto out_delete; diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 05be023c3f0e..b86aba1c8028 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -88,8 +88,6 @@ #include "sane_ctype.h" #define DEFAULT_SEPARATOR " " -#define CNTR_NOT_SUPPORTED "<not supported>" -#define CNTR_NOT_COUNTED "<not counted>" #define FREEZE_ON_SMI_PATH "devices/cpu/freeze_on_smi" static void print_counters(struct timespec *ts, int argc, const char **argv); @@ -137,54 +135,30 @@ static const char *smi_cost_attrs = { static struct perf_evlist *evsel_list; -static struct rblist metric_events; - static struct target target = { .uid = UINT_MAX, }; -typedef int (*aggr_get_id_t)(struct cpu_map *m, int cpu); - #define METRIC_ONLY_LEN 20 -static int run_count = 1; -static bool no_inherit = false; static volatile pid_t child_pid = -1; -static bool null_run = false; static int detailed_run = 0; static bool transaction_run; static bool topdown_run = false; static bool smi_cost = false; static bool smi_reset = false; -static bool big_num = true; static int big_num_opt = -1; -static const char *csv_sep = NULL; -static bool csv_output = false; static bool group = false; static const char *pre_cmd = NULL; static const char *post_cmd = NULL; static bool sync_run = false; -static unsigned int initial_delay = 0; -static unsigned int unit_width = 4; /* strlen("unit") */ static bool forever = false; -static bool metric_only = false; static bool force_metric_only = false; -static bool no_merge = false; -static bool walltime_run_table = false; static struct timespec ref_time; -static struct cpu_map *aggr_map; -static aggr_get_id_t aggr_get_id; static bool append_file; static bool interval_count; -static bool interval_clear; static const char *output_name; static int output_fd; -static int print_free_counters_hint; -static int print_mixed_hw_group_error; -static u64 *walltime_run; -static bool ru_display = false; -static struct rusage ru_data; -static unsigned int metric_only_len = METRIC_ONLY_LEN; struct perf_stat { bool record; @@ -204,15 +178,15 @@ static struct perf_stat perf_stat; static volatile int done = 0; static struct perf_stat_config stat_config = { - .aggr_mode = AGGR_GLOBAL, - .scale = true, + .aggr_mode = AGGR_GLOBAL, + .scale = true, + .unit_width = 4, /* strlen("unit") */ + .run_count = 1, + .metric_only_len = METRIC_ONLY_LEN, + .walltime_nsecs_stats = &walltime_nsecs_stats, + .big_num = true, }; -static bool is_duration_time(struct perf_evsel *evsel) -{ - return !strcmp(evsel->name, "duration_time"); -} - static inline void diff_timespec(struct timespec *r, struct timespec *a, struct timespec *b) { @@ -236,78 +210,6 @@ static void perf_stat__reset_stats(void) perf_stat__reset_shadow_per_stat(&stat_config.stats[i]); } -static int create_perf_stat_counter(struct perf_evsel *evsel) -{ - struct perf_event_attr *attr = &evsel->attr; - struct perf_evsel *leader = evsel->leader; - - if (stat_config.scale) { - attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED | - PERF_FORMAT_TOTAL_TIME_RUNNING; - } - - /* - * The event is part of non trivial group, let's enable - * the group read (for leader) and ID retrieval for all - * members. - */ - if (leader->nr_members > 1) - attr->read_format |= PERF_FORMAT_ID|PERF_FORMAT_GROUP; - - attr->inherit = !no_inherit; - - /* - * Some events get initialized with sample_(period/type) set, - * like tracepoints. Clear it up for counting. - */ - attr->sample_period = 0; - - /* - * But set sample_type to PERF_SAMPLE_IDENTIFIER, which should be harmless - * while avoiding that older tools show confusing messages. - * - * However for pipe sessions we need to keep it zero, - * because script's perf_evsel__check_attr is triggered - * by attr->sample_type != 0, and we can't run it on - * stat sessions. - */ - if (!(STAT_RECORD && perf_stat.data.is_pipe)) - attr->sample_type = PERF_SAMPLE_IDENTIFIER; - - /* - * Disabling all counters initially, they will be enabled - * either manually by us or by kernel via enable_on_exec - * set later. - */ - if (perf_evsel__is_group_leader(evsel)) { - attr->disabled = 1; - - /* - * In case of initial_delay we enable tracee - * events manually. - */ - if (target__none(&target) && !initial_delay) - attr->enable_on_exec = 1; - } - - if (target__has_cpu(&target) && !target__has_per_thread(&target)) - return perf_evsel__open_per_cpu(evsel, perf_evsel__cpus(evsel)); - - return perf_evsel__open_per_thread(evsel, evsel_list->threads); -} - -/* - * Does the counter have nsecs as a unit? - */ -static inline int nsec_counter(struct perf_evsel *evsel) -{ - if (perf_evsel__match(evsel, SOFTWARE, SW_CPU_CLOCK) || - perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK)) - return 1; - - return 0; -} - static int process_synthesized_event(struct perf_tool *tool __maybe_unused, union perf_event *event, struct perf_sample *sample __maybe_unused, @@ -440,15 +342,15 @@ static void process_interval(void) static void enable_counters(void) { - if (initial_delay) - usleep(initial_delay * USEC_PER_MSEC); + if (stat_config.initial_delay) + usleep(stat_config.initial_delay * USEC_PER_MSEC); /* * We need to enable counters only if: * - we don't have tracee (attaching to task or cpu) * - we have initial delay configured */ - if (!target__none(&target) || initial_delay) + if (!target__none(&target) || stat_config.initial_delay) perf_evlist__enable(evsel_list); } @@ -476,80 +378,6 @@ static void workload_exec_failed_signal(int signo __maybe_unused, siginfo_t *inf workload_exec_errno = info->si_value.sival_int; } -static int perf_stat_synthesize_config(bool is_pipe) -{ - int err; - - if (is_pipe) { - err = perf_event__synthesize_attrs(NULL, perf_stat.session, - process_synthesized_event); - if (err < 0) { - pr_err("Couldn't synthesize attrs.\n"); - return err; - } - } - - err = perf_event__synthesize_extra_attr(NULL, - evsel_list, - process_synthesized_event, - is_pipe); - - err = perf_event__synthesize_thread_map2(NULL, evsel_list->threads, - process_synthesized_event, - NULL); - if (err < 0) { - pr_err("Couldn't synthesize thread map.\n"); - return err; - } - - err = perf_event__synthesize_cpu_map(NULL, evsel_list->cpus, - process_synthesized_event, NULL); - if (err < 0) { - pr_err("Couldn't synthesize thread map.\n"); - return err; - } - - err = perf_event__synthesize_stat_config(NULL, &stat_config, - process_synthesized_event, NULL); - if (err < 0) { - pr_err("Couldn't synthesize config.\n"); - return err; - } - - return 0; -} - -#define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y)) - -static int __store_counter_ids(struct perf_evsel *counter) -{ - int cpu, thread; - - for (cpu = 0; cpu < xyarray__max_x(counter->fd); cpu++) { - for (thread = 0; thread < xyarray__max_y(counter->fd); - thread++) { - int fd = FD(counter, cpu, thread); - - if (perf_evlist__id_add_fd(evsel_list, counter, - cpu, thread, fd) < 0) - return -1; - } - } - - return 0; -} - -static int store_counter_ids(struct perf_evsel *counter) -{ - struct cpu_map *cpus = counter->cpus; - struct thread_map *threads = counter->threads; - - if (perf_evsel__alloc_id(counter, cpus->nr, threads->nr)) - return -ENOMEM; - - return __store_counter_ids(counter); -} - static bool perf_evsel__should_store_id(struct perf_evsel *counter) { return STAT_RECORD || counter->attr.read_format & PERF_FORMAT_ID; @@ -621,7 +449,7 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx) evlist__for_each_entry(evsel_list, counter) { try_again: - if (create_perf_stat_counter(counter) < 0) { + if (create_perf_stat_counter(counter, &stat_config, &target) < 0) { /* Weak group failed. Reset the group. */ if ((errno == EINVAL || errno == EBADF) && @@ -676,11 +504,11 @@ try_again: counter->supported = true; l = strlen(counter->unit); - if (l > unit_width) - unit_width = l; + if (l > stat_config.unit_width) + stat_config.unit_width = l; if (perf_evsel__should_store_id(counter) && - store_counter_ids(counter)) + perf_evsel__store_ids(counter, evsel_list)) return -1; } @@ -711,7 +539,8 @@ try_again: if (err < 0) return err; - err = perf_stat_synthesize_config(is_pipe); + err = perf_stat_synthesize_config(&stat_config, NULL, evsel_list, + process_synthesized_event, is_pipe); if (err < 0) return err; } @@ -736,7 +565,7 @@ try_again: break; } } - wait4(child_pid, &status, 0, &ru_data); + wait4(child_pid, &status, 0, &stat_config.ru_data); if (workload_exec_errno) { const char *emsg = str_error_r(workload_exec_errno, msg, sizeof(msg)); @@ -764,8 +593,8 @@ try_again: t1 = rdclock(); - if (walltime_run_table) - walltime_run[run_idx] = t1 - t0; + if (stat_config.walltime_run_table) + stat_config.walltime_run[run_idx] = t1 - t0; update_stats(&walltime_nsecs_stats, t1 - t0); @@ -807,1137 +636,14 @@ static int run_perf_stat(int argc, const char **argv, int run_idx) return ret; } -static void print_running(u64 run, u64 ena) -{ - if (csv_output) { - fprintf(stat_config.output, "%s%" PRIu64 "%s%.2f", - csv_sep, - run, - csv_sep, - ena ? 100.0 * run / ena : 100.0); - } else if (run != ena) { - fprintf(stat_config.output, " (%.2f%%)", 100.0 * run / ena); - } -} - -static void print_noise_pct(double total, double avg) -{ - double pct = rel_stddev_stats(total, avg); - - if (csv_output) - fprintf(stat_config.output, "%s%.2f%%", csv_sep, pct); - else if (pct) - fprintf(stat_config.output, " ( +-%6.2f%% )", pct); -} - -static void print_noise(struct perf_evsel *evsel, double avg) -{ - struct perf_stat_evsel *ps; - - if (run_count == 1) - return; - - ps = evsel->stats; - print_noise_pct(stddev_stats(&ps->res_stats[0]), avg); -} - -static void aggr_printout(struct perf_evsel *evsel, int id, int nr) -{ - switch (stat_config.aggr_mode) { - case AGGR_CORE: - fprintf(stat_config.output, "S%d-C%*d%s%*d%s", - cpu_map__id_to_socket(id), - csv_output ? 0 : -8, - cpu_map__id_to_cpu(id), - csv_sep, - csv_output ? 0 : 4, - nr, - csv_sep); - break; - case AGGR_SOCKET: - fprintf(stat_config.output, "S%*d%s%*d%s", - csv_output ? 0 : -5, - id, - csv_sep, - csv_output ? 0 : 4, - nr, - csv_sep); - break; - case AGGR_NONE: - fprintf(stat_config.output, "CPU%*d%s", - csv_output ? 0 : -4, - perf_evsel__cpus(evsel)->map[id], csv_sep); - break; - case AGGR_THREAD: - fprintf(stat_config.output, "%*s-%*d%s", - csv_output ? 0 : 16, - thread_map__comm(evsel->threads, id), - csv_output ? 0 : -8, - thread_map__pid(evsel->threads, id), - csv_sep); - break; - case AGGR_GLOBAL: - case AGGR_UNSET: - default: - break; - } -} - -struct outstate { - FILE *fh; - bool newline; - const char *prefix; - int nfields; - int id, nr; - struct perf_evsel *evsel; -}; - -#define METRIC_LEN 35 - -static void new_line_std(void *ctx) -{ - struct outstate *os = ctx; - - os->newline = true; -} - -static void do_new_line_std(struct outstate *os) -{ - fputc('\n', os->fh); - fputs(os->prefix, os->fh); - aggr_printout(os->evsel, os->id, os->nr); - if (stat_config.aggr_mode == AGGR_NONE) - fprintf(os->fh, " "); - fprintf(os->fh, " "); -} - -static void print_metric_std(void *ctx, const char *color, const char *fmt, - const char *unit, double val) -{ - struct outstate *os = ctx; - FILE *out = os->fh; - int n; - bool newline = os->newline; - - os->newline = false; - - if (unit == NULL || fmt == NULL) { - fprintf(out, "%-*s", METRIC_LEN, ""); - return; - } - - if (newline) - do_new_line_std(os); - - n = fprintf(out, " # "); - if (color) - n += color_fprintf(out, color, fmt, val); - else - n += fprintf(out, fmt, val); - fprintf(out, " %-*s", METRIC_LEN - n - 1, unit); -} - -static void new_line_csv(void *ctx) -{ - struct outstate *os = ctx; - int i; - - fputc('\n', os->fh); - if (os->prefix) - fprintf(os->fh, "%s%s", os->prefix, csv_sep); - aggr_printout(os->evsel, os->id, os->nr); - for (i = 0; i < os->nfields; i++) - fputs(csv_sep, os->fh); -} - -static void print_metric_csv(void *ctx, - const char *color __maybe_unused, - const char *fmt, const char *unit, double val) -{ - struct outstate *os = ctx; - FILE *out = os->fh; - char buf[64], *vals, *ends; - - if (unit == NULL || fmt == NULL) { - fprintf(out, "%s%s", csv_sep, csv_sep); - return; - } - snprintf(buf, sizeof(buf), fmt, val); - ends = vals = ltrim(buf); - while (isdigit(*ends) || *ends == '.') - ends++; - *ends = 0; - while (isspace(*unit)) - unit++; - fprintf(out, "%s%s%s%s", csv_sep, vals, csv_sep, unit); -} - -/* Filter out some columns that don't work well in metrics only mode */ - -static bool valid_only_metric(const char *unit) -{ - if (!unit) - return false; - if (strstr(unit, "/sec") || - strstr(unit, "hz") || - strstr(unit, "Hz") || - strstr(unit, "CPUs utilized")) - return false; - return true; -} - -static const char *fixunit(char *buf, struct perf_evsel *evsel, - const char *unit) -{ - if (!strncmp(unit, "of all", 6)) { - snprintf(buf, 1024, "%s %s", perf_evsel__name(evsel), - unit); - return buf; - } - return unit; -} - -static void print_metric_only(void *ctx, const char *color, const char *fmt, - const char *unit, double val) -{ - struct outstate *os = ctx; - FILE *out = os->fh; - char buf[1024], str[1024]; - unsigned mlen = metric_only_len; - - if (!valid_only_metric(unit)) - return; - unit = fixunit(buf, os->evsel, unit); - if (mlen < strlen(unit)) - mlen = strlen(unit) + 1; - - if (color) - mlen += strlen(color) + sizeof(PERF_COLOR_RESET) - 1; - - color_snprintf(str, sizeof(str), color ?: "", fmt, val); - fprintf(out, "%*s ", mlen, str); -} - -static void print_metric_only_csv(void *ctx, const char *color __maybe_unused, - const char *fmt, - const char *unit, double val) -{ - struct outstate *os = ctx; - FILE *out = os->fh; - char buf[64], *vals, *ends; - char tbuf[1024]; - - if (!valid_only_metric(unit)) - return; - unit = fixunit(tbuf, os->evsel, unit); - snprintf(buf, sizeof buf, fmt, val); - ends = vals = ltrim(buf); - while (isdigit(*ends) || *ends == '.') - ends++; - *ends = 0; - fprintf(out, "%s%s", vals, csv_sep); -} - -static void new_line_metric(void *ctx __maybe_unused) -{ -} - -static void print_metric_header(void *ctx, const char *color __maybe_unused, - const char *fmt __maybe_unused, - const char *unit, double val __maybe_unused) -{ - struct outstate *os = ctx; - char tbuf[1024]; - - if (!valid_only_metric(unit)) - return; - unit = fixunit(tbuf, os->evsel, unit); - if (csv_output) - fprintf(os->fh, "%s%s", unit, csv_sep); - else - fprintf(os->fh, "%*s ", metric_only_len, unit); -} - -static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg) -{ - FILE *output = stat_config.output; - double msecs = avg / NSEC_PER_MSEC; - const char *fmt_v, *fmt_n; - char name[25]; - - fmt_v = csv_output ? "%.6f%s" : "%18.6f%s"; - fmt_n = csv_output ? "%s" : "%-25s"; - - aggr_printout(evsel, id, nr); - - scnprintf(name, sizeof(name), "%s%s", - perf_evsel__name(evsel), csv_output ? "" : " (msec)"); - - fprintf(output, fmt_v, msecs, csv_sep); - - if (csv_output) - fprintf(output, "%s%s", evsel->unit, csv_sep); - else - fprintf(output, "%-*s%s", unit_width, evsel->unit, csv_sep); - - fprintf(output, fmt_n, name); - - if (evsel->cgrp) - fprintf(output, "%s%s", csv_sep, evsel->cgrp->name); -} - -static int first_shadow_cpu(struct perf_evsel *evsel, int id) -{ - int i; - - if (!aggr_get_id) - return 0; - - if (stat_config.aggr_mode == AGGR_NONE) - return id; - - if (stat_config.aggr_mode == AGGR_GLOBAL) - return 0; - - for (i = 0; i < perf_evsel__nr_cpus(evsel); i++) { - int cpu2 = perf_evsel__cpus(evsel)->map[i]; - - if (aggr_get_id(evsel_list->cpus, cpu2) == id) - return cpu2; - } - return 0; -} - -static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg) -{ - FILE *output = stat_config.output; - double sc = evsel->scale; - const char *fmt; - - if (csv_output) { - fmt = floor(sc) != sc ? "%.2f%s" : "%.0f%s"; - } else { - if (big_num) - fmt = floor(sc) != sc ? "%'18.2f%s" : "%'18.0f%s"; - else - fmt = floor(sc) != sc ? "%18.2f%s" : "%18.0f%s"; - } - - aggr_printout(evsel, id, nr); - - fprintf(output, fmt, avg, csv_sep); - - if (evsel->unit) - fprintf(output, "%-*s%s", - csv_output ? 0 : unit_width, - evsel->unit, csv_sep); - - fprintf(output, "%-*s", csv_output ? 0 : 25, perf_evsel__name(evsel)); - - if (evsel->cgrp) - fprintf(output, "%s%s", csv_sep, evsel->cgrp->name); -} - -static bool is_mixed_hw_group(struct perf_evsel *counter) -{ - struct perf_evlist *evlist = counter->evlist; - u32 pmu_type = counter->attr.type; - struct perf_evsel *pos; - - if (counter->nr_members < 2) - return false; - - evlist__for_each_entry(evlist, pos) { - /* software events can be part of any hardware group */ - if (pos->attr.type == PERF_TYPE_SOFTWARE) - continue; - if (pmu_type == PERF_TYPE_SOFTWARE) { - pmu_type = pos->attr.type; - continue; - } - if (pmu_type != pos->attr.type) - return true; - } - - return false; -} - -static void printout(int id, int nr, struct perf_evsel *counter, double uval, - char *prefix, u64 run, u64 ena, double noise, - struct runtime_stat *st) -{ - struct perf_stat_output_ctx out; - struct outstate os = { - .fh = stat_config.output, - .prefix = prefix ? prefix : "", - .id = id, - .nr = nr, - .evsel = counter, - }; - print_metric_t pm = print_metric_std; - void (*nl)(void *); - - if (metric_only) { - nl = new_line_metric; - if (csv_output) - pm = print_metric_only_csv; - else - pm = print_metric_only; - } else - nl = new_line_std; - - if (csv_output && !metric_only) { - static int aggr_fields[] = { - [AGGR_GLOBAL] = 0, - [AGGR_THREAD] = 1, - [AGGR_NONE] = 1, - [AGGR_SOCKET] = 2, - [AGGR_CORE] = 2, - }; - - pm = print_metric_csv; - nl = new_line_csv; - os.nfields = 3; - os.nfields += aggr_fields[stat_config.aggr_mode]; - if (counter->cgrp) - os.nfields++; - } - if (run == 0 || ena == 0 || counter->counts->scaled == -1) { - if (metric_only) { - pm(&os, NULL, "", "", 0); - return; - } - aggr_printout(counter, id, nr); - - fprintf(stat_config.output, "%*s%s", - csv_output ? 0 : 18, - counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED, - csv_sep); - - if (counter->supported) { - print_free_counters_hint = 1; - if (is_mixed_hw_group(counter)) - print_mixed_hw_group_error = 1; - } - - fprintf(stat_config.output, "%-*s%s", - csv_output ? 0 : unit_width, - counter->unit, csv_sep); - - fprintf(stat_config.output, "%*s", - csv_output ? 0 : -25, - perf_evsel__name(counter)); - - if (counter->cgrp) - fprintf(stat_config.output, "%s%s", - csv_sep, counter->cgrp->name); - - if (!csv_output) - pm(&os, NULL, NULL, "", 0); - print_noise(counter, noise); - print_running(run, ena); - if (csv_output) - pm(&os, NULL, NULL, "", 0); - return; - } - - if (metric_only) - /* nothing */; - else if (nsec_counter(counter)) - nsec_printout(id, nr, counter, uval); - else - abs_printout(id, nr, counter, uval); - - out.print_metric = pm; - out.new_line = nl; - out.ctx = &os; - out.force_header = false; - - if (csv_output && !metric_only) { - print_noise(counter, noise); - print_running(run, ena); - } - - perf_stat__print_shadow_stats(counter, uval, - first_shadow_cpu(counter, id), - &out, &metric_events, st); - if (!csv_output && !metric_only) { - print_noise(counter, noise); - print_running(run, ena); - } -} - -static void aggr_update_shadow(void) -{ - int cpu, s2, id, s; - u64 val; - struct perf_evsel *counter; - - for (s = 0; s < aggr_map->nr; s++) { - id = aggr_map->map[s]; - evlist__for_each_entry(evsel_list, counter) { - val = 0; - for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) { - s2 = aggr_get_id(evsel_list->cpus, cpu); - if (s2 != id) - continue; - val += perf_counts(counter->counts, cpu, 0)->val; - } - perf_stat__update_shadow_stats(counter, val, - first_shadow_cpu(counter, id), - &rt_stat); - } - } -} - -static void uniquify_event_name(struct perf_evsel *counter) -{ - char *new_name; - char *config; - - if (counter->uniquified_name || - !counter->pmu_name || !strncmp(counter->name, counter->pmu_name, - strlen(counter->pmu_name))) - return; - - config = strchr(counter->name, '/'); - if (config) { - if (asprintf(&new_name, - "%s%s", counter->pmu_name, config) > 0) { - free(counter->name); - counter->name = new_name; - } - } else { - if (asprintf(&new_name, - "%s [%s]", counter->name, counter->pmu_name) > 0) { - free(counter->name); - counter->name = new_name; - } - } - - counter->uniquified_name = true; -} - -static void collect_all_aliases(struct perf_evsel *counter, - void (*cb)(struct perf_evsel *counter, void *data, - bool first), - void *data) -{ - struct perf_evsel *alias; - - alias = list_prepare_entry(counter, &(evsel_list->entries), node); - list_for_each_entry_continue (alias, &evsel_list->entries, node) { - if (strcmp(perf_evsel__name(alias), perf_evsel__name(counter)) || - alias->scale != counter->scale || - alias->cgrp != counter->cgrp || - strcmp(alias->unit, counter->unit) || - nsec_counter(alias) != nsec_counter(counter)) - break; - alias->merged_stat = true; - cb(alias, data, false); - } -} - -static bool collect_data(struct perf_evsel *counter, - void (*cb)(struct perf_evsel *counter, void *data, - bool first), - void *data) -{ - if (counter->merged_stat) - return false; - cb(counter, data, true); - if (no_merge) - uniquify_event_name(counter); - else if (counter->auto_merge_stats) - collect_all_aliases(counter, cb, data); - return true; -} - -struct aggr_data { - u64 ena, run, val; - int id; - int nr; - int cpu; -}; - -static void aggr_cb(struct perf_evsel *counter, void *data, bool first) -{ - struct aggr_data *ad = data; - int cpu, s2; - - for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) { - struct perf_counts_values *counts; - - s2 = aggr_get_id(perf_evsel__cpus(counter), cpu); - if (s2 != ad->id) - continue; - if (first) - ad->nr++; - counts = perf_counts(counter->counts, cpu, 0); - /* - * When any result is bad, make them all to give - * consistent output in interval mode. - */ - if (counts->ena == 0 || counts->run == 0 || - counter->counts->scaled == -1) { - ad->ena = 0; - ad->run = 0; - break; - } - ad->val += counts->val; - ad->ena += counts->ena; - ad->run += counts->run; - } -} - -static void print_aggr(char *prefix) -{ - FILE *output = stat_config.output; - struct perf_evsel *counter; - int s, id, nr; - double uval; - u64 ena, run, val; - bool first; - - if (!(aggr_map || aggr_get_id)) - return; - - aggr_update_shadow(); - - /* - * With metric_only everything is on a single line. - * Without each counter has its own line. - */ - for (s = 0; s < aggr_map->nr; s++) { - struct aggr_data ad; - if (prefix && metric_only) - fprintf(output, "%s", prefix); - - ad.id = id = aggr_map->map[s]; - first = true; - evlist__for_each_entry(evsel_list, counter) { - if (is_duration_time(counter)) - continue; - - ad.val = ad.ena = ad.run = 0; - ad.nr = 0; - if (!collect_data(counter, aggr_cb, &ad)) - continue; - nr = ad.nr; - ena = ad.ena; - run = ad.run; - val = ad.val; - if (first && metric_only) { - first = false; - aggr_printout(counter, id, nr); - } - if (prefix && !metric_only) - fprintf(output, "%s", prefix); - - uval = val * counter->scale; - printout(id, nr, counter, uval, prefix, run, ena, 1.0, - &rt_stat); - if (!metric_only) - fputc('\n', output); - } - if (metric_only) - fputc('\n', output); - } -} - -static int cmp_val(const void *a, const void *b) -{ - return ((struct perf_aggr_thread_value *)b)->val - - ((struct perf_aggr_thread_value *)a)->val; -} - -static struct perf_aggr_thread_value *sort_aggr_thread( - struct perf_evsel *counter, - int nthreads, int ncpus, - int *ret) -{ - int cpu, thread, i = 0; - double uval; - struct perf_aggr_thread_value *buf; - - buf = calloc(nthreads, sizeof(struct perf_aggr_thread_value)); - if (!buf) - return NULL; - - for (thread = 0; thread < nthreads; thread++) { - u64 ena = 0, run = 0, val = 0; - - for (cpu = 0; cpu < ncpus; cpu++) { - val += perf_counts(counter->counts, cpu, thread)->val; - ena += perf_counts(counter->counts, cpu, thread)->ena; - run += perf_counts(counter->counts, cpu, thread)->run; - } - - uval = val * counter->scale; - - /* - * Skip value 0 when enabling --per-thread globally, - * otherwise too many 0 output. - */ - if (uval == 0.0 && target__has_per_thread(&target)) - continue; - - buf[i].counter = counter; - buf[i].id = thread; - buf[i].uval = uval; - buf[i].val = val; - buf[i].run = run; - buf[i].ena = ena; - i++; - } - - qsort(buf, i, sizeof(struct perf_aggr_thread_value), cmp_val); - - if (ret) - *ret = i; - - return buf; -} - -static void print_aggr_thread(struct perf_evsel *counter, char *prefix) -{ - FILE *output = stat_config.output; - int nthreads = thread_map__nr(counter->threads); - int ncpus = cpu_map__nr(counter->cpus); - int thread, sorted_threads, id; - struct perf_aggr_thread_value *buf; - - buf = sort_aggr_thread(counter, nthreads, ncpus, &sorted_threads); - if (!buf) { - perror("cannot sort aggr thread"); - return; - } - - for (thread = 0; thread < sorted_threads; thread++) { - if (prefix) - fprintf(output, "%s", prefix); - - id = buf[thread].id; - if (stat_config.stats) - printout(id, 0, buf[thread].counter, buf[thread].uval, - prefix, buf[thread].run, buf[thread].ena, 1.0, - &stat_config.stats[id]); - else - printout(id, 0, buf[thread].counter, buf[thread].uval, - prefix, buf[thread].run, buf[thread].ena, 1.0, - &rt_stat); - fputc('\n', output); - } - - free(buf); -} - -struct caggr_data { - double avg, avg_enabled, avg_running; -}; - -static void counter_aggr_cb(struct perf_evsel *counter, void *data, - bool first __maybe_unused) -{ - struct caggr_data *cd = data; - struct perf_stat_evsel *ps = counter->stats; - - cd->avg += avg_stats(&ps->res_stats[0]); - cd->avg_enabled += avg_stats(&ps->res_stats[1]); - cd->avg_running += avg_stats(&ps->res_stats[2]); -} - -/* - * Print out the results of a single counter: - * aggregated counts in system-wide mode - */ -static void print_counter_aggr(struct perf_evsel *counter, char *prefix) -{ - FILE *output = stat_config.output; - double uval; - struct caggr_data cd = { .avg = 0.0 }; - - if (!collect_data(counter, counter_aggr_cb, &cd)) - return; - - if (prefix && !metric_only) - fprintf(output, "%s", prefix); - - uval = cd.avg * counter->scale; - printout(-1, 0, counter, uval, prefix, cd.avg_running, cd.avg_enabled, - cd.avg, &rt_stat); - if (!metric_only) - fprintf(output, "\n"); -} - -static void counter_cb(struct perf_evsel *counter, void *data, - bool first __maybe_unused) -{ - struct aggr_data *ad = data; - - ad->val += perf_counts(counter->counts, ad->cpu, 0)->val; - ad->ena += perf_counts(counter->counts, ad->cpu, 0)->ena; - ad->run += perf_counts(counter->counts, ad->cpu, 0)->run; -} - -/* - * Print out the results of a single counter: - * does not use aggregated count in system-wide - */ -static void print_counter(struct perf_evsel *counter, char *prefix) -{ - FILE *output = stat_config.output; - u64 ena, run, val; - double uval; - int cpu; - - for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) { - struct aggr_data ad = { .cpu = cpu }; - - if (!collect_data(counter, counter_cb, &ad)) - return; - val = ad.val; - ena = ad.ena; - run = ad.run; - - if (prefix) - fprintf(output, "%s", prefix); - - uval = val * counter->scale; - printout(cpu, 0, counter, uval, prefix, run, ena, 1.0, - &rt_stat); - - fputc('\n', output); - } -} - -static void print_no_aggr_metric(char *prefix) -{ - int cpu; - int nrcpus = 0; - struct perf_evsel *counter; - u64 ena, run, val; - double uval; - - nrcpus = evsel_list->cpus->nr; - for (cpu = 0; cpu < nrcpus; cpu++) { - bool first = true; - - if (prefix) - fputs(prefix, stat_config.output); - evlist__for_each_entry(evsel_list, counter) { - if (is_duration_time(counter)) - continue; - if (first) { - aggr_printout(counter, cpu, 0); - first = false; - } - val = perf_counts(counter->counts, cpu, 0)->val; - ena = perf_counts(counter->counts, cpu, 0)->ena; - run = perf_counts(counter->counts, cpu, 0)->run; - - uval = val * counter->scale; - printout(cpu, 0, counter, uval, prefix, run, ena, 1.0, - &rt_stat); - } - fputc('\n', stat_config.output); - } -} - -static int aggr_header_lens[] = { - [AGGR_CORE] = 18, - [AGGR_SOCKET] = 12, - [AGGR_NONE] = 6, - [AGGR_THREAD] = 24, - [AGGR_GLOBAL] = 0, -}; - -static const char *aggr_header_csv[] = { - [AGGR_CORE] = "core,cpus,", - [AGGR_SOCKET] = "socket,cpus", - [AGGR_NONE] = "cpu,", - [AGGR_THREAD] = "comm-pid,", - [AGGR_GLOBAL] = "" -}; - -static void print_metric_headers(const char *prefix, bool no_indent) -{ - struct perf_stat_output_ctx out; - struct perf_evsel *counter; - struct outstate os = { - .fh = stat_config.output - }; - - if (prefix) - fprintf(stat_config.output, "%s", prefix); - - if (!csv_output && !no_indent) - fprintf(stat_config.output, "%*s", - aggr_header_lens[stat_config.aggr_mode], ""); - if (csv_output) { - if (stat_config.interval) - fputs("time,", stat_config.output); - fputs(aggr_header_csv[stat_config.aggr_mode], - stat_config.output); - } - - /* Print metrics headers only */ - evlist__for_each_entry(evsel_list, counter) { - if (is_duration_time(counter)) - continue; - os.evsel = counter; - out.ctx = &os; - out.print_metric = print_metric_header; - out.new_line = new_line_metric; - out.force_header = true; - os.evsel = counter; - perf_stat__print_shadow_stats(counter, 0, - 0, - &out, - &metric_events, - &rt_stat); - } - fputc('\n', stat_config.output); -} - -static void print_interval(char *prefix, struct timespec *ts) -{ - FILE *output = stat_config.output; - static int num_print_interval; - - if (interval_clear) - puts(CONSOLE_CLEAR); - - sprintf(prefix, "%6lu.%09lu%s", ts->tv_sec, ts->tv_nsec, csv_sep); - - if ((num_print_interval == 0 && !csv_output) || interval_clear) { - switch (stat_config.aggr_mode) { - case AGGR_SOCKET: - fprintf(output, "# time socket cpus"); - if (!metric_only) - fprintf(output, " counts %*s events\n", unit_width, "unit"); - break; - case AGGR_CORE: - fprintf(output, "# time core cpus"); - if (!metric_only) - fprintf(output, " counts %*s events\n", unit_width, "unit"); - break; - case AGGR_NONE: - fprintf(output, "# time CPU "); - if (!metric_only) - fprintf(output, " counts %*s events\n", unit_width, "unit"); - break; - case AGGR_THREAD: - fprintf(output, "# time comm-pid"); - if (!metric_only) - fprintf(output, " counts %*s events\n", unit_width, "unit"); - break; - case AGGR_GLOBAL: - default: - fprintf(output, "# time"); - if (!metric_only) - fprintf(output, " counts %*s events\n", unit_width, "unit"); - case AGGR_UNSET: - break; - } - } - - if ((num_print_interval == 0 || interval_clear) && metric_only) - print_metric_headers(" ", true); - if (++num_print_interval == 25) - num_print_interval = 0; -} - -static void print_header(int argc, const char **argv) -{ - FILE *output = stat_config.output; - int i; - - fflush(stdout); - - if (!csv_output) { - fprintf(output, "\n"); - fprintf(output, " Performance counter stats for "); - if (target.system_wide) - fprintf(output, "\'system wide"); - else if (target.cpu_list) - fprintf(output, "\'CPU(s) %s", target.cpu_list); - else if (!target__has_task(&target)) { - fprintf(output, "\'%s", argv ? argv[0] : "pipe"); - for (i = 1; argv && (i < argc); i++) - fprintf(output, " %s", argv[i]); - } else if (target.pid) - fprintf(output, "process id \'%s", target.pid); - else - fprintf(output, "thread id \'%s", target.tid); - - fprintf(output, "\'"); - if (run_count > 1) - fprintf(output, " (%d runs)", run_count); - fprintf(output, ":\n\n"); - } -} - -static int get_precision(double num) -{ - if (num > 1) - return 0; - - return lround(ceil(-log10(num))); -} - -static void print_table(FILE *output, int precision, double avg) -{ - char tmp[64]; - int idx, indent = 0; - - scnprintf(tmp, 64, " %17.*f", precision, avg); - while (tmp[indent] == ' ') - indent++; - - fprintf(output, "%*s# Table of individual measurements:\n", indent, ""); - - for (idx = 0; idx < run_count; idx++) { - double run = (double) walltime_run[idx] / NSEC_PER_SEC; - int h, n = 1 + abs((int) (100.0 * (run - avg)/run) / 5); - - fprintf(output, " %17.*f (%+.*f) ", - precision, run, precision, run - avg); - - for (h = 0; h < n; h++) - fprintf(output, "#"); - - fprintf(output, "\n"); - } - - fprintf(output, "\n%*s# Final result:\n", indent, ""); -} - -static double timeval2double(struct timeval *t) -{ - return t->tv_sec + (double) t->tv_usec/USEC_PER_SEC; -} - -static void print_footer(void) -{ - double avg = avg_stats(&walltime_nsecs_stats) / NSEC_PER_SEC; - FILE *output = stat_config.output; - int n; - - if (!null_run) - fprintf(output, "\n"); - - if (run_count == 1) { - fprintf(output, " %17.9f seconds time elapsed", avg); - - if (ru_display) { - double ru_utime = timeval2double(&ru_data.ru_utime); - double ru_stime = timeval2double(&ru_data.ru_stime); - - fprintf(output, "\n\n"); - fprintf(output, " %17.9f seconds user\n", ru_utime); - fprintf(output, " %17.9f seconds sys\n", ru_stime); - } - } else { - double sd = stddev_stats(&walltime_nsecs_stats) / NSEC_PER_SEC; - /* - * Display at most 2 more significant - * digits than the stddev inaccuracy. - */ - int precision = get_precision(sd) + 2; - - if (walltime_run_table) - print_table(output, precision, avg); - - fprintf(output, " %17.*f +- %.*f seconds time elapsed", - precision, avg, precision, sd); - - print_noise_pct(sd, avg); - } - fprintf(output, "\n\n"); - - if (print_free_counters_hint && - sysctl__read_int("kernel/nmi_watchdog", &n) >= 0 && - n > 0) - fprintf(output, -"Some events weren't counted. Try disabling the NMI watchdog:\n" -" echo 0 > /proc/sys/kernel/nmi_watchdog\n" -" perf stat ...\n" -" echo 1 > /proc/sys/kernel/nmi_watchdog\n"); - - if (print_mixed_hw_group_error) - fprintf(output, - "The events in group usually have to be from " - "the same PMU. Try reorganizing the group.\n"); -} - static void print_counters(struct timespec *ts, int argc, const char **argv) { - int interval = stat_config.interval; - struct perf_evsel *counter; - char buf[64], *prefix = NULL; - /* Do not print anything if we record to the pipe. */ if (STAT_RECORD && perf_stat.data.is_pipe) return; - if (interval) - print_interval(prefix = buf, ts); - else - print_header(argc, argv); - - if (metric_only) { - static int num_print_iv; - - if (num_print_iv == 0 && !interval) - print_metric_headers(prefix, false); - if (num_print_iv++ == 25) - num_print_iv = 0; - if (stat_config.aggr_mode == AGGR_GLOBAL && prefix) - fprintf(stat_config.output, "%s", prefix); - } - - switch (stat_config.aggr_mode) { - case AGGR_CORE: - case AGGR_SOCKET: - print_aggr(prefix); - break; - case AGGR_THREAD: - evlist__for_each_entry(evsel_list, counter) { - if (is_duration_time(counter)) - continue; - print_aggr_thread(counter, prefix); - } - break; - case AGGR_GLOBAL: - evlist__for_each_entry(evsel_list, counter) { - if (is_duration_time(counter)) - continue; - print_counter_aggr(counter, prefix); - } - if (metric_only) - fputc('\n', stat_config.output); - break; - case AGGR_NONE: - if (metric_only) - print_no_aggr_metric(prefix); - else { - evlist__for_each_entry(evsel_list, counter) { - if (is_duration_time(counter)) - continue; - print_counter(counter, prefix); - } - } - break; - case AGGR_UNSET: - default: - break; - } - - if (!interval && !csv_output) - print_footer(); - - fflush(stat_config.output); + perf_evlist__print_counters(evsel_list, &stat_config, &target, + ts, argc, argv); } static volatile int signr = -1; @@ -1994,7 +700,7 @@ static int enable_metric_only(const struct option *opt __maybe_unused, const char *s __maybe_unused, int unset) { force_metric_only = true; - metric_only = !unset; + stat_config.metric_only = !unset; return 0; } @@ -2002,7 +708,7 @@ static int parse_metric_groups(const struct option *opt, const char *str, int unset __maybe_unused) { - return metricgroup__parse_groups(opt, str, &metric_events); + return metricgroup__parse_groups(opt, str, &stat_config.metric_events); } static const struct option stat_options[] = { @@ -2013,7 +719,7 @@ static const struct option stat_options[] = { parse_events_option), OPT_CALLBACK(0, "filter", &evsel_list, "filter", "event filter", parse_filter), - OPT_BOOLEAN('i', "no-inherit", &no_inherit, + OPT_BOOLEAN('i', "no-inherit", &stat_config.no_inherit, "child tasks do not inherit counters"), OPT_STRING('p', "pid", &target.pid, "pid", "stat events on existing process id"), @@ -2026,11 +732,11 @@ static const struct option stat_options[] = { OPT_BOOLEAN('c', "scale", &stat_config.scale, "scale/normalize counters"), OPT_INCR('v', "verbose", &verbose, "be more verbose (show counter open errors, etc)"), - OPT_INTEGER('r', "repeat", &run_count, + OPT_INTEGER('r', "repeat", &stat_config.run_count, "repeat command and print average + stddev (max: 100, forever: 0)"), - OPT_BOOLEAN(0, "table", &walltime_run_table, + OPT_BOOLEAN(0, "table", &stat_config.walltime_run_table, "display details about each run (only with -r option)"), - OPT_BOOLEAN('n', "null", &null_run, + OPT_BOOLEAN('n', "null", &stat_config.null_run, "null run - dont start any counters"), OPT_INCR('d', "detailed", &detailed_run, "detailed run - start a lot of events"), @@ -2043,8 +749,8 @@ static const struct option stat_options[] = { "list of cpus to monitor in system-wide"), OPT_SET_UINT('A', "no-aggr", &stat_config.aggr_mode, "disable CPU count aggregation", AGGR_NONE), - OPT_BOOLEAN(0, "no-merge", &no_merge, "Do not merge identical named events"), - OPT_STRING('x', "field-separator", &csv_sep, "separator", + OPT_BOOLEAN(0, "no-merge", &stat_config.no_merge, "Do not merge identical named events"), + OPT_STRING('x', "field-separator", &stat_config.csv_sep, "separator", "print counts with custom separator"), OPT_CALLBACK('G', "cgroup", &evsel_list, "name", "monitor event in cgroup name only", parse_cgroups), @@ -2061,7 +767,7 @@ static const struct option stat_options[] = { "(overhead is possible for values <= 100ms)"), OPT_INTEGER(0, "interval-count", &stat_config.times, "print counts for fixed number of times"), - OPT_BOOLEAN(0, "interval-clear", &interval_clear, + OPT_BOOLEAN(0, "interval-clear", &stat_config.interval_clear, "clear screen in between new interval"), OPT_UINTEGER(0, "timeout", &stat_config.timeout, "stop workload and print counts after a timeout period in ms (>= 10ms)"), @@ -2071,9 +777,9 @@ static const struct option stat_options[] = { "aggregate counts per physical processor core", AGGR_CORE), OPT_SET_UINT(0, "per-thread", &stat_config.aggr_mode, "aggregate counts per thread", AGGR_THREAD), - OPT_UINTEGER('D', "delay", &initial_delay, + OPT_UINTEGER('D', "delay", &stat_config.initial_delay, "ms to wait before starting measurement after program start"), - OPT_CALLBACK_NOOPT(0, "metric-only", &metric_only, NULL, + OPT_CALLBACK_NOOPT(0, "metric-only", &stat_config.metric_only, NULL, "Only print computed metrics. No raw values", enable_metric_only), OPT_BOOLEAN(0, "topdown", &topdown_run, "measure topdown level 1 statistics"), @@ -2085,12 +791,14 @@ static const struct option stat_options[] = { OPT_END() }; -static int perf_stat__get_socket(struct cpu_map *map, int cpu) +static int perf_stat__get_socket(struct perf_stat_config *config __maybe_unused, + struct cpu_map *map, int cpu) { return cpu_map__get_socket(map, cpu, NULL); } -static int perf_stat__get_core(struct cpu_map *map, int cpu) +static int perf_stat__get_core(struct perf_stat_config *config __maybe_unused, + struct cpu_map *map, int cpu) { return cpu_map__get_core(map, cpu, NULL); } @@ -2107,9 +815,8 @@ static int cpu_map__get_max(struct cpu_map *map) return max; } -static struct cpu_map *cpus_aggr_map; - -static int perf_stat__get_aggr(aggr_get_id_t get_id, struct cpu_map *map, int idx) +static int perf_stat__get_aggr(struct perf_stat_config *config, + aggr_get_id_t get_id, struct cpu_map *map, int idx) { int cpu; @@ -2118,20 +825,22 @@ static int perf_stat__get_aggr(aggr_get_id_t get_id, struct cpu_map *map, int id cpu = map->map[idx]; - if (cpus_aggr_map->map[cpu] == -1) - cpus_aggr_map->map[cpu] = get_id(map, idx); + if (config->cpus_aggr_map->map[cpu] == -1) + config->cpus_aggr_map->map[cpu] = get_id(config, map, idx); - return cpus_aggr_map->map[cpu]; + return config->cpus_aggr_map->map[cpu]; } -static int perf_stat__get_socket_cached(struct cpu_map *map, int idx) +static int perf_stat__get_socket_cached(struct perf_stat_config *config, + struct cpu_map *map, int idx) { - return perf_stat__get_aggr(perf_stat__get_socket, map, idx); + return perf_stat__get_aggr(config, perf_stat__get_socket, map, idx); } -static int perf_stat__get_core_cached(struct cpu_map *map, int idx) +static int perf_stat__get_core_cached(struct perf_stat_config *config, + struct cpu_map *map, int idx) { - return perf_stat__get_aggr(perf_stat__get_core, map, idx); + return perf_stat__get_aggr(config, perf_stat__get_core, map, idx); } static int perf_stat_init_aggr_mode(void) @@ -2140,18 +849,18 @@ static int perf_stat_init_aggr_mode(void) switch (stat_config.aggr_mode) { case AGGR_SOCKET: - if (cpu_map__build_socket_map(evsel_list->cpus, &aggr_map)) { + if (cpu_map__build_socket_map(evsel_list->cpus, &stat_config.aggr_map)) { perror("cannot build socket map"); return -1; } - aggr_get_id = perf_stat__get_socket_cached; + stat_config.aggr_get_id = perf_stat__get_socket_cached; break; case AGGR_CORE: - if (cpu_map__build_core_map(evsel_list->cpus, &aggr_map)) { + if (cpu_map__build_core_map(evsel_list->cpus, &stat_config.aggr_map)) { perror("cannot build core map"); return -1; } - aggr_get_id = perf_stat__get_core_cached; + stat_config.aggr_get_id = perf_stat__get_core_cached; break; case AGGR_NONE: case AGGR_GLOBAL: @@ -2167,16 +876,16 @@ static int perf_stat_init_aggr_mode(void) * the aggregation translate cpumap. */ nr = cpu_map__get_max(evsel_list->cpus); - cpus_aggr_map = cpu_map__empty_new(nr + 1); - return cpus_aggr_map ? 0 : -ENOMEM; + stat_config.cpus_aggr_map = cpu_map__empty_new(nr + 1); + return stat_config.cpus_aggr_map ? 0 : -ENOMEM; } static void perf_stat__exit_aggr_mode(void) { - cpu_map__put(aggr_map); - cpu_map__put(cpus_aggr_map); - aggr_map = NULL; - cpus_aggr_map = NULL; + cpu_map__put(stat_config.aggr_map); + cpu_map__put(stat_config.cpus_aggr_map); + stat_config.aggr_map = NULL; + stat_config.cpus_aggr_map = NULL; } static inline int perf_env__get_cpu(struct perf_env *env, struct cpu_map *map, int idx) @@ -2234,12 +943,14 @@ static int perf_env__build_core_map(struct perf_env *env, struct cpu_map *cpus, return cpu_map__build_map(cpus, corep, perf_env__get_core, env); } -static int perf_stat__get_socket_file(struct cpu_map *map, int idx) +static int perf_stat__get_socket_file(struct perf_stat_config *config __maybe_unused, + struct cpu_map *map, int idx) { return perf_env__get_socket(map, idx, &perf_stat.session->header.env); } -static int perf_stat__get_core_file(struct cpu_map *map, int idx) +static int perf_stat__get_core_file(struct perf_stat_config *config __maybe_unused, + struct cpu_map *map, int idx) { return perf_env__get_core(map, idx, &perf_stat.session->header.env); } @@ -2250,18 +961,18 @@ static int perf_stat_init_aggr_mode_file(struct perf_stat *st) switch (stat_config.aggr_mode) { case AGGR_SOCKET: - if (perf_env__build_socket_map(env, evsel_list->cpus, &aggr_map)) { + if (perf_env__build_socket_map(env, evsel_list->cpus, &stat_config.aggr_map)) { perror("cannot build socket map"); return -1; } - aggr_get_id = perf_stat__get_socket_file; + stat_config.aggr_get_id = perf_stat__get_socket_file; break; case AGGR_CORE: - if (perf_env__build_core_map(env, evsel_list->cpus, &aggr_map)) { + if (perf_env__build_core_map(env, evsel_list->cpus, &stat_config.aggr_map)) { perror("cannot build core map"); return -1; } - aggr_get_id = perf_stat__get_core_file; + stat_config.aggr_get_id = perf_stat__get_core_file; break; case AGGR_NONE: case AGGR_GLOBAL: @@ -2445,10 +1156,22 @@ static int add_default_attributes(void) struct parse_events_error errinfo; /* Set attrs if no event is selected and !null_run: */ - if (null_run) + if (stat_config.null_run) return 0; if (transaction_run) { + /* Handle -T as -M transaction. Once platform specific metrics + * support has been added to the json files, all archictures + * will use this approach. To determine transaction support + * on an architecture test for such a metric name. + */ + if (metricgroup__has_metric("transaction")) { + struct option opt = { .value = &evsel_list }; + + return metricgroup__parse_groups(&opt, "transaction", + &stat_config.metric_events); + } + if (pmu_have_event("cpu", "cycles-ct") && pmu_have_event("cpu", "el-start")) err = parse_events(evsel_list, transaction_attrs, @@ -2484,7 +1207,7 @@ static int add_default_attributes(void) if (pmu_have_event("msr", "aperf") && pmu_have_event("msr", "smi")) { if (!force_metric_only) - metric_only = true; + stat_config.metric_only = true; err = parse_events(evsel_list, smi_cost_attrs, &errinfo); } else { fprintf(stderr, "To measure SMI cost, it needs " @@ -2515,7 +1238,7 @@ static int add_default_attributes(void) } if (!force_metric_only) - metric_only = true; + stat_config.metric_only = true; if (topdown_filter_events(topdown_attrs, &str, arch_topdown_check_group(&warn)) < 0) { pr_err("Out of memory\n"); @@ -2612,7 +1335,7 @@ static int __cmd_record(int argc, const char **argv) if (output_name) data->file.path = output_name; - if (run_count != 1 || forever) { + if (stat_config.run_count != 1 || forever) { pr_err("Cannot use -r option with perf stat record.\n"); return -1; } @@ -2631,9 +1354,8 @@ static int __cmd_record(int argc, const char **argv) return argc; } -static int process_stat_round_event(struct perf_tool *tool __maybe_unused, - union perf_event *event, - struct perf_session *session) +static int process_stat_round_event(struct perf_session *session, + union perf_event *event) { struct stat_round_event *stat_round = &event->stat_round; struct perf_evsel *counter; @@ -2658,10 +1380,10 @@ static int process_stat_round_event(struct perf_tool *tool __maybe_unused, } static -int process_stat_config_event(struct perf_tool *tool, - union perf_event *event, - struct perf_session *session __maybe_unused) +int process_stat_config_event(struct perf_session *session, + union perf_event *event) { + struct perf_tool *tool = session->tool; struct perf_stat *st = container_of(tool, struct perf_stat, tool); perf_event__read_stat_config(&stat_config, &event->stat_config); @@ -2701,10 +1423,10 @@ static int set_maps(struct perf_stat *st) } static -int process_thread_map_event(struct perf_tool *tool, - union perf_event *event, - struct perf_session *session __maybe_unused) +int process_thread_map_event(struct perf_session *session, + union perf_event *event) { + struct perf_tool *tool = session->tool; struct perf_stat *st = container_of(tool, struct perf_stat, tool); if (st->threads) { @@ -2720,10 +1442,10 @@ int process_thread_map_event(struct perf_tool *tool, } static -int process_cpu_map_event(struct perf_tool *tool, - union perf_event *event, - struct perf_session *session __maybe_unused) +int process_cpu_map_event(struct perf_session *session, + union perf_event *event) { + struct perf_tool *tool = session->tool; struct perf_stat *st = container_of(tool, struct perf_stat, tool); struct cpu_map *cpus; @@ -2885,12 +1607,12 @@ int cmd_stat(int argc, const char **argv) perf_stat__collect_metric_expr(evsel_list); perf_stat__init_shadow_stats(); - if (csv_sep) { - csv_output = true; - if (!strcmp(csv_sep, "\\t")) - csv_sep = "\t"; + if (stat_config.csv_sep) { + stat_config.csv_output = true; + if (!strcmp(stat_config.csv_sep, "\\t")) + stat_config.csv_sep = "\t"; } else - csv_sep = DEFAULT_SEPARATOR; + stat_config.csv_sep = DEFAULT_SEPARATOR; if (argc && !strncmp(argv[0], "rec", 3)) { argc = __cmd_record(argc, argv); @@ -2915,17 +1637,17 @@ int cmd_stat(int argc, const char **argv) goto out; } - if (metric_only && stat_config.aggr_mode == AGGR_THREAD) { + if (stat_config.metric_only && stat_config.aggr_mode == AGGR_THREAD) { fprintf(stderr, "--metric-only is not supported with --per-thread\n"); goto out; } - if (metric_only && run_count > 1) { + if (stat_config.metric_only && stat_config.run_count > 1) { fprintf(stderr, "--metric-only is not supported with -r\n"); goto out; } - if (walltime_run_table && run_count <= 1) { + if (stat_config.walltime_run_table && stat_config.run_count <= 1) { fprintf(stderr, "--table is only supported with -r\n"); parse_options_usage(stat_usage, stat_options, "r", 1); parse_options_usage(NULL, stat_options, "table", 0); @@ -2963,7 +1685,7 @@ int cmd_stat(int argc, const char **argv) /* * let the spreadsheet do the pretty-printing */ - if (csv_output) { + if (stat_config.csv_output) { /* User explicitly passed -B? */ if (big_num_opt == 1) { fprintf(stderr, "-B option not supported with -x\n"); @@ -2971,9 +1693,9 @@ int cmd_stat(int argc, const char **argv) parse_options_usage(NULL, stat_options, "x", 1); goto out; } else /* Nope, so disable big number formatting */ - big_num = false; + stat_config.big_num = false; } else if (big_num_opt == 0) /* User passed --no-big-num */ - big_num = false; + stat_config.big_num = false; setup_system_wide(argc); @@ -2981,21 +1703,21 @@ int cmd_stat(int argc, const char **argv) * Display user/system times only for single * run and when there's specified tracee. */ - if ((run_count == 1) && target__none(&target)) - ru_display = true; + if ((stat_config.run_count == 1) && target__none(&target)) + stat_config.ru_display = true; - if (run_count < 0) { + if (stat_config.run_count < 0) { pr_err("Run count must be a positive number\n"); parse_options_usage(stat_usage, stat_options, "r", 1); goto out; - } else if (run_count == 0) { + } else if (stat_config.run_count == 0) { forever = true; - run_count = 1; + stat_config.run_count = 1; } - if (walltime_run_table) { - walltime_run = zalloc(run_count * sizeof(walltime_run[0])); - if (!walltime_run) { + if (stat_config.walltime_run_table) { + stat_config.walltime_run = zalloc(stat_config.run_count * sizeof(stat_config.walltime_run[0])); + if (!stat_config.walltime_run) { pr_err("failed to setup -r option"); goto out; } @@ -3098,6 +1820,17 @@ int cmd_stat(int argc, const char **argv) goto out; /* + * Set sample_type to PERF_SAMPLE_IDENTIFIER, which should be harmless + * while avoiding that older tools show confusing messages. + * + * However for pipe sessions we need to keep it zero, + * because script's perf_evsel__check_attr is triggered + * by attr->sample_type != 0, and we can't run it on + * stat sessions. + */ + stat_config.identifier = !(STAT_RECORD && perf_stat.data.is_pipe); + + /* * We dont want to block the signals - that would cause * child tasks to inherit that and Ctrl-C would not work. * What we want is for Ctrl-C to work in the exec()-ed @@ -3111,8 +1844,8 @@ int cmd_stat(int argc, const char **argv) signal(SIGABRT, skip_signal); status = 0; - for (run_idx = 0; forever || run_idx < run_count; run_idx++) { - if (run_count != 1 && verbose > 0) + for (run_idx = 0; forever || run_idx < stat_config.run_count; run_idx++) { + if (stat_config.run_count != 1 && verbose > 0) fprintf(output, "[ perf stat: executing run #%d ... ]\n", run_idx + 1); @@ -3164,7 +1897,7 @@ int cmd_stat(int argc, const char **argv) perf_stat__exit_aggr_mode(); perf_evlist__free_stats(evsel_list); out: - free(walltime_run); + free(stat_config.walltime_run); if (smi_cost && smi_reset) sysfs__write_int(FREEZE_ON_SMI_PATH, 0); diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index ffdc2769ff9f..d21d8751e749 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -307,7 +307,7 @@ static void perf_top__print_sym_table(struct perf_top *top) hists__output_recalc_col_len(hists, top->print_entries - printed); putchar('\n'); hists__fprintf(hists, false, top->print_entries - printed, win_width, - top->min_percent, stdout, symbol_conf.use_callchain); + top->min_percent, stdout, !symbol_conf.use_callchain); } static void prompt_integer(int *target, const char *msg) diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 6a748eca2edb..90289f31dd87 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -77,7 +77,8 @@ struct trace { struct syscall *table; struct { struct perf_evsel *sys_enter, - *sys_exit; + *sys_exit, + *augmented; } events; } syscalls; struct record_opts opts; @@ -121,7 +122,6 @@ struct trace { bool force; bool vfs_getname; int trace_pgfaults; - int open_id; }; struct tp_field { @@ -157,13 +157,11 @@ TP_UINT_FIELD__SWAPPED(16); TP_UINT_FIELD__SWAPPED(32); TP_UINT_FIELD__SWAPPED(64); -static int tp_field__init_uint(struct tp_field *field, - struct format_field *format_field, - bool needs_swap) +static int __tp_field__init_uint(struct tp_field *field, int size, int offset, bool needs_swap) { - field->offset = format_field->offset; + field->offset = offset; - switch (format_field->size) { + switch (size) { case 1: field->integer = tp_field__u8; break; @@ -183,18 +181,28 @@ static int tp_field__init_uint(struct tp_field *field, return 0; } +static int tp_field__init_uint(struct tp_field *field, struct tep_format_field *format_field, bool needs_swap) +{ + return __tp_field__init_uint(field, format_field->size, format_field->offset, needs_swap); +} + static void *tp_field__ptr(struct tp_field *field, struct perf_sample *sample) { return sample->raw_data + field->offset; } -static int tp_field__init_ptr(struct tp_field *field, struct format_field *format_field) +static int __tp_field__init_ptr(struct tp_field *field, int offset) { - field->offset = format_field->offset; + field->offset = offset; field->pointer = tp_field__ptr; return 0; } +static int tp_field__init_ptr(struct tp_field *field, struct tep_format_field *format_field) +{ + return __tp_field__init_ptr(field, format_field->offset); +} + struct syscall_tp { struct tp_field id; union { @@ -206,7 +214,7 @@ static int perf_evsel__init_tp_uint_field(struct perf_evsel *evsel, struct tp_field *field, const char *name) { - struct format_field *format_field = perf_evsel__field(evsel, name); + struct tep_format_field *format_field = perf_evsel__field(evsel, name); if (format_field == NULL) return -1; @@ -222,7 +230,7 @@ static int perf_evsel__init_tp_ptr_field(struct perf_evsel *evsel, struct tp_field *field, const char *name) { - struct format_field *format_field = perf_evsel__field(evsel, name); + struct tep_format_field *format_field = perf_evsel__field(evsel, name); if (format_field == NULL) return -1; @@ -240,7 +248,54 @@ static void perf_evsel__delete_priv(struct perf_evsel *evsel) perf_evsel__delete(evsel); } -static int perf_evsel__init_syscall_tp(struct perf_evsel *evsel, void *handler) +static int perf_evsel__init_syscall_tp(struct perf_evsel *evsel) +{ + struct syscall_tp *sc = evsel->priv = malloc(sizeof(struct syscall_tp)); + + if (evsel->priv != NULL) { + if (perf_evsel__init_tp_uint_field(evsel, &sc->id, "__syscall_nr")) + goto out_delete; + return 0; + } + + return -ENOMEM; +out_delete: + zfree(&evsel->priv); + return -ENOENT; +} + +static int perf_evsel__init_augmented_syscall_tp(struct perf_evsel *evsel) +{ + struct syscall_tp *sc = evsel->priv = malloc(sizeof(struct syscall_tp)); + + if (evsel->priv != NULL) { /* field, sizeof_field, offsetof_field */ + if (__tp_field__init_uint(&sc->id, sizeof(long), sizeof(long long), evsel->needs_swap)) + goto out_delete; + + return 0; + } + + return -ENOMEM; +out_delete: + zfree(&evsel->priv); + return -EINVAL; +} + +static int perf_evsel__init_augmented_syscall_tp_args(struct perf_evsel *evsel) +{ + struct syscall_tp *sc = evsel->priv; + + return __tp_field__init_ptr(&sc->args, sc->id.offset + sizeof(u64)); +} + +static int perf_evsel__init_augmented_syscall_tp_ret(struct perf_evsel *evsel) +{ + struct syscall_tp *sc = evsel->priv; + + return __tp_field__init_uint(&sc->ret, sizeof(u64), sc->id.offset + sizeof(u64), evsel->needs_swap); +} + +static int perf_evsel__init_raw_syscall_tp(struct perf_evsel *evsel, void *handler) { evsel->priv = malloc(sizeof(struct syscall_tp)); if (evsel->priv != NULL) { @@ -258,7 +313,7 @@ out_delete: return -ENOENT; } -static struct perf_evsel *perf_evsel__syscall_newtp(const char *direction, void *handler) +static struct perf_evsel *perf_evsel__raw_syscall_newtp(const char *direction, void *handler) { struct perf_evsel *evsel = perf_evsel__newtp("raw_syscalls", direction); @@ -269,7 +324,7 @@ static struct perf_evsel *perf_evsel__syscall_newtp(const char *direction, void if (IS_ERR(evsel)) return NULL; - if (perf_evsel__init_syscall_tp(evsel, handler)) + if (perf_evsel__init_raw_syscall_tp(evsel, handler)) goto out_delete; return evsel; @@ -291,7 +346,7 @@ size_t strarray__scnprintf(struct strarray *sa, char *bf, size_t size, const cha { int idx = val - sa->offset; - if (idx < 0 || idx >= sa->nr_entries) + if (idx < 0 || idx >= sa->nr_entries || sa->entries[idx] == NULL) return scnprintf(bf, size, intfmt, val); return scnprintf(bf, size, "%s", sa->entries[idx]); @@ -450,16 +505,6 @@ static const char *clockid[] = { }; static DEFINE_STRARRAY(clockid); -static const char *socket_families[] = { - "UNSPEC", "LOCAL", "INET", "AX25", "IPX", "APPLETALK", "NETROM", - "BRIDGE", "ATMPVC", "X25", "INET6", "ROSE", "DECnet", "NETBEUI", - "SECURITY", "KEY", "NETLINK", "PACKET", "ASH", "ECONET", "ATMSVC", - "RDS", "SNA", "IRDA", "PPPOX", "WANPIPE", "LLC", "IB", "CAN", "TIPC", - "BLUETOOTH", "IUCV", "RXRPC", "ISDN", "PHONET", "IEEE802154", "CAIF", - "ALG", "NFC", "VSOCK", -}; -static DEFINE_STRARRAY(socket_families); - static size_t syscall_arg__scnprintf_access_mode(char *bf, size_t size, struct syscall_arg *arg) { @@ -583,6 +628,8 @@ static struct syscall_fmt { } syscall_fmts[] = { { .name = "access", .arg = { [1] = { .scnprintf = SCA_ACCMODE, /* mode */ }, }, }, + { .name = "bind", + .arg = { [1] = { .scnprintf = SCA_SOCKADDR, /* umyaddr */ }, }, }, { .name = "bpf", .arg = { [0] = STRARRAY(cmd, bpf_cmd), }, }, { .name = "brk", .hexret = true, @@ -597,6 +644,8 @@ static struct syscall_fmt { [4] = { .name = "tls", .scnprintf = SCA_HEX, }, }, }, { .name = "close", .arg = { [0] = { .scnprintf = SCA_CLOSE_FD, /* fd */ }, }, }, + { .name = "connect", + .arg = { [1] = { .scnprintf = SCA_SOCKADDR, /* servaddr */ }, }, }, { .name = "epoll_ctl", .arg = { [1] = STRARRAY(op, epoll_ctl_ops), }, }, { .name = "eventfd2", @@ -753,7 +802,8 @@ static struct syscall_fmt { { .name = "sendmsg", .arg = { [2] = { .scnprintf = SCA_MSG_FLAGS, /* flags */ }, }, }, { .name = "sendto", - .arg = { [3] = { .scnprintf = SCA_MSG_FLAGS, /* flags */ }, }, }, + .arg = { [3] = { .scnprintf = SCA_MSG_FLAGS, /* flags */ }, + [4] = { .scnprintf = SCA_SOCKADDR, /* addr */ }, }, }, { .name = "set_tid_address", .errpid = true, }, { .name = "setitimer", .arg = { [0] = STRARRAY(which, itimers), }, }, @@ -761,10 +811,12 @@ static struct syscall_fmt { .arg = { [0] = STRARRAY(resource, rlimit_resources), }, }, { .name = "socket", .arg = { [0] = STRARRAY(family, socket_families), - [1] = { .scnprintf = SCA_SK_TYPE, /* type */ }, }, }, + [1] = { .scnprintf = SCA_SK_TYPE, /* type */ }, + [2] = { .scnprintf = SCA_SK_PROTO, /* protocol */ }, }, }, { .name = "socketpair", .arg = { [0] = STRARRAY(family, socket_families), - [1] = { .scnprintf = SCA_SK_TYPE, /* type */ }, }, }, + [1] = { .scnprintf = SCA_SK_TYPE, /* type */ }, + [2] = { .scnprintf = SCA_SK_PROTO, /* protocol */ }, }, }, { .name = "stat", .alias = "newstat", }, { .name = "statx", .arg = { [0] = { .scnprintf = SCA_FDAT, /* fdat */ }, @@ -780,6 +832,7 @@ static struct syscall_fmt { .arg = { [2] = { .scnprintf = SCA_SIGNUM, /* sig */ }, }, }, { .name = "tkill", .arg = { [1] = { .scnprintf = SCA_SIGNUM, /* sig */ }, }, }, + { .name = "umount2", .alias = "umount", }, { .name = "uname", .alias = "newuname", }, { .name = "unlinkat", .arg = { [0] = { .scnprintf = SCA_FDAT, /* dfd */ }, }, }, @@ -803,12 +856,19 @@ static struct syscall_fmt *syscall_fmt__find(const char *name) return bsearch(name, syscall_fmts, nmemb, sizeof(struct syscall_fmt), syscall_fmt__cmp); } +/* + * is_exit: is this "exit" or "exit_group"? + * is_open: is this "open" or "openat"? To associate the fd returned in sys_exit with the pathname in sys_enter. + * args_size: sum of the sizes of the syscall arguments, anything after that is augmented stuff: pathname for openat, etc. + */ struct syscall { - struct event_format *tp_format; + struct tep_event_format *tp_format; int nr_args; - struct format_field *args; - const char *name; + int args_size; bool is_exit; + bool is_open; + struct tep_format_field *args; + const char *name; struct syscall_fmt *fmt; struct syscall_arg_fmt *arg_fmt; }; @@ -1040,11 +1100,21 @@ static void thread__set_filename_pos(struct thread *thread, const char *bf, ttrace->filename.entry_str_pos = bf - ttrace->entry_str; } +static size_t syscall_arg__scnprintf_augmented_string(struct syscall_arg *arg, char *bf, size_t size) +{ + struct augmented_arg *augmented_arg = arg->augmented.args; + + return scnprintf(bf, size, "%.*s", augmented_arg->size, augmented_arg->value); +} + static size_t syscall_arg__scnprintf_filename(char *bf, size_t size, struct syscall_arg *arg) { unsigned long ptr = arg->val; + if (arg->augmented.args) + return syscall_arg__scnprintf_augmented_string(arg, bf, size); + if (!arg->trace->vfs_getname) return scnprintf(bf, size, "%#x", ptr); @@ -1087,11 +1157,9 @@ static void sig_handler(int sig) interrupted = sig == SIGINT; } -static size_t trace__fprintf_entry_head(struct trace *trace, struct thread *thread, - u64 duration, bool duration_calculated, u64 tstamp, FILE *fp) +static size_t trace__fprintf_comm_tid(struct trace *trace, struct thread *thread, FILE *fp) { - size_t printed = trace__fprintf_tstamp(trace, tstamp, fp); - printed += fprintf_duration(duration, duration_calculated, fp); + size_t printed = 0; if (trace->multiple_threads) { if (trace->show_comm) @@ -1102,6 +1170,14 @@ static size_t trace__fprintf_entry_head(struct trace *trace, struct thread *thre return printed; } +static size_t trace__fprintf_entry_head(struct trace *trace, struct thread *thread, + u64 duration, bool duration_calculated, u64 tstamp, FILE *fp) +{ + size_t printed = trace__fprintf_tstamp(trace, tstamp, fp); + printed += fprintf_duration(duration, duration_calculated, fp); + return printed + trace__fprintf_comm_tid(trace, thread, fp); +} + static int trace__process_event(struct trace *trace, struct machine *machine, union perf_event *event, struct perf_sample *sample) { @@ -1203,10 +1279,12 @@ static int syscall__alloc_arg_fmts(struct syscall *sc, int nr_args) static int syscall__set_arg_fmts(struct syscall *sc) { - struct format_field *field; + struct tep_format_field *field, *last_field = NULL; int idx = 0, len; for (field = sc->args; field; field = field->next, ++idx) { + last_field = field; + if (sc->fmt && sc->fmt->arg[idx].scnprintf) continue; @@ -1215,7 +1293,7 @@ static int syscall__set_arg_fmts(struct syscall *sc) strcmp(field->name, "path") == 0 || strcmp(field->name, "pathname") == 0)) sc->arg_fmt[idx].scnprintf = SCA_FILENAME; - else if (field->flags & FIELD_IS_POINTER) + else if (field->flags & TEP_FIELD_IS_POINTER) sc->arg_fmt[idx].scnprintf = syscall_arg__scnprintf_hex; else if (strcmp(field->type, "pid_t") == 0) sc->arg_fmt[idx].scnprintf = SCA_PID; @@ -1237,6 +1315,9 @@ static int syscall__set_arg_fmts(struct syscall *sc) } } + if (last_field) + sc->args_size = last_field->offset + last_field->size; + return 0; } @@ -1297,6 +1378,7 @@ static int trace__read_syscall_info(struct trace *trace, int id) } sc->is_exit = !strcmp(name, "exit_group") || !strcmp(name, "exit"); + sc->is_open = !strcmp(name, "open") || !strcmp(name, "openat"); return syscall__set_arg_fmts(sc); } @@ -1416,14 +1498,18 @@ static size_t syscall__scnprintf_val(struct syscall *sc, char *bf, size_t size, } static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size, - unsigned char *args, struct trace *trace, - struct thread *thread) + unsigned char *args, void *augmented_args, int augmented_args_size, + struct trace *trace, struct thread *thread) { size_t printed = 0; unsigned long val; u8 bit = 1; struct syscall_arg arg = { .args = args, + .augmented = { + .size = augmented_args_size, + .args = augmented_args, + }, .idx = 0, .mask = 0, .trace = trace, @@ -1439,7 +1525,7 @@ static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size, ttrace->ret_scnprintf = NULL; if (sc->args != NULL) { - struct format_field *field; + struct tep_format_field *field; for (field = sc->args; field; field = field->next, ++arg.idx, bit <<= 1) { @@ -1598,6 +1684,17 @@ static int trace__fprintf_sample(struct trace *trace, struct perf_evsel *evsel, return printed; } +static void *syscall__augmented_args(struct syscall *sc, struct perf_sample *sample, int *augmented_args_size) +{ + void *augmented_args = NULL; + + *augmented_args_size = sample->raw_size - sc->args_size; + if (*augmented_args_size > 0) + augmented_args = sample->raw_data + sc->args_size; + + return augmented_args; +} + static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel, union perf_event *event __maybe_unused, struct perf_sample *sample) @@ -1607,6 +1704,8 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel, size_t printed = 0; struct thread *thread; int id = perf_evsel__sc_tp_uint(evsel, id, sample), err = -1; + int augmented_args_size = 0; + void *augmented_args = NULL; struct syscall *sc = trace__syscall_info(trace, evsel, id); struct thread_trace *ttrace; @@ -1630,13 +1729,24 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel, if (!(trace->duration_filter || trace->summary_only || trace->min_stack)) trace__printf_interrupted_entry(trace); - + /* + * If this is raw_syscalls.sys_enter, then it always comes with the 6 possible + * arguments, even if the syscall being handled, say "openat", uses only 4 arguments + * this breaks syscall__augmented_args() check for augmented args, as we calculate + * syscall->args_size using each syscalls:sys_enter_NAME tracefs format file, + * so when handling, say the openat syscall, we end up getting 6 args for the + * raw_syscalls:sys_enter event, when we expected just 4, we end up mistakenly + * thinking that the extra 2 u64 args are the augmented filename, so just check + * here and avoid using augmented syscalls when the evsel is the raw_syscalls one. + */ + if (evsel != trace->syscalls.events.sys_enter) + augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size); ttrace->entry_time = sample->time; msg = ttrace->entry_str; printed += scnprintf(msg + printed, trace__entry_str_size - printed, "%s(", sc->name); printed += syscall__scnprintf_args(sc, msg + printed, trace__entry_str_size - printed, - args, trace, thread); + args, augmented_args, augmented_args_size, trace, thread); if (sc->is_exit) { if (!(trace->duration_filter || trace->summary_only || trace->failure_only || trace->min_stack)) { @@ -1659,6 +1769,39 @@ out_put: return err; } +static int trace__fprintf_sys_enter(struct trace *trace, struct perf_evsel *evsel, + struct perf_sample *sample) +{ + struct thread_trace *ttrace; + struct thread *thread; + int id = perf_evsel__sc_tp_uint(evsel, id, sample), err = -1; + struct syscall *sc = trace__syscall_info(trace, evsel, id); + char msg[1024]; + void *args, *augmented_args = NULL; + int augmented_args_size; + + if (sc == NULL) + return -1; + + thread = machine__findnew_thread(trace->host, sample->pid, sample->tid); + ttrace = thread__trace(thread, trace->output); + /* + * We need to get ttrace just to make sure it is there when syscall__scnprintf_args() + * and the rest of the beautifiers accessing it via struct syscall_arg touches it. + */ + if (ttrace == NULL) + goto out_put; + + args = perf_evsel__sc_tp_ptr(evsel, args, sample); + augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size); + syscall__scnprintf_args(sc, msg, sizeof(msg), args, augmented_args, augmented_args_size, trace, thread); + fprintf(trace->output, "%s", msg); + err = 0; +out_put: + thread__put(thread); + return err; +} + static int trace__resolve_callchain(struct trace *trace, struct perf_evsel *evsel, struct perf_sample *sample, struct callchain_cursor *cursor) @@ -1720,7 +1863,7 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel, ret = perf_evsel__sc_tp_uint(evsel, ret, sample); - if (id == trace->open_id && ret >= 0 && ttrace->filename.pending_open) { + if (sc->is_open && ret >= 0 && ttrace->filename.pending_open) { trace__set_fd_pathname(thread, ret, ttrace->filename.name); ttrace->filename.pending_open = false; ++trace->stats.vfs_getname; @@ -1935,6 +2078,7 @@ static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel, union perf_event *event __maybe_unused, struct perf_sample *sample) { + struct thread *thread = machine__findnew_thread(trace->host, sample->pid, sample->tid); int callchain_ret = 0; if (sample->callchain) { @@ -1952,22 +2096,48 @@ static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel, if (trace->trace_syscalls) fprintf(trace->output, "( ): "); + if (thread) + trace__fprintf_comm_tid(trace, thread, trace->output); + + if (evsel == trace->syscalls.events.augmented) { + int id = perf_evsel__sc_tp_uint(evsel, id, sample); + struct syscall *sc = trace__syscall_info(trace, evsel, id); + + if (sc) { + fprintf(trace->output, "%s(", sc->name); + trace__fprintf_sys_enter(trace, evsel, sample); + fputc(')', trace->output); + goto newline; + } + + /* + * XXX: Not having the associated syscall info or not finding/adding + * the thread should never happen, but if it does... + * fall thru and print it as a bpf_output event. + */ + } + fprintf(trace->output, "%s:", evsel->name); if (perf_evsel__is_bpf_output(evsel)) { bpf_output__fprintf(trace, sample); } else if (evsel->tp_format) { - event_format__fprintf(evsel->tp_format, sample->cpu, - sample->raw_data, sample->raw_size, - trace->output); + if (strncmp(evsel->tp_format->name, "sys_enter_", 10) || + trace__fprintf_sys_enter(trace, evsel, sample)) { + event_format__fprintf(evsel->tp_format, sample->cpu, + sample->raw_data, sample->raw_size, + trace->output); + } } +newline: fprintf(trace->output, "\n"); if (callchain_ret > 0) trace__fprintf_callchain(trace, sample); else if (callchain_ret < 0) pr_err("Problem processing %s callchain, skipping...\n", perf_evsel__name(evsel)); + thread__put(thread); out: return 0; } @@ -2240,14 +2410,14 @@ static int trace__add_syscall_newtp(struct trace *trace) struct perf_evlist *evlist = trace->evlist; struct perf_evsel *sys_enter, *sys_exit; - sys_enter = perf_evsel__syscall_newtp("sys_enter", trace__sys_enter); + sys_enter = perf_evsel__raw_syscall_newtp("sys_enter", trace__sys_enter); if (sys_enter == NULL) goto out; if (perf_evsel__init_sc_tp_ptr_field(sys_enter, args)) goto out_delete_sys_enter; - sys_exit = perf_evsel__syscall_newtp("sys_exit", trace__sys_exit); + sys_exit = perf_evsel__raw_syscall_newtp("sys_exit", trace__sys_exit); if (sys_exit == NULL) goto out_delete_sys_enter; @@ -2669,7 +2839,7 @@ static int trace__replay(struct trace *trace) "syscalls:sys_enter"); if (evsel && - (perf_evsel__init_syscall_tp(evsel, trace__sys_enter) < 0 || + (perf_evsel__init_raw_syscall_tp(evsel, trace__sys_enter) < 0 || perf_evsel__init_sc_tp_ptr_field(evsel, args))) { pr_err("Error during initialize raw_syscalls:sys_enter event\n"); goto out; @@ -2681,7 +2851,7 @@ static int trace__replay(struct trace *trace) evsel = perf_evlist__find_tracepoint_by_name(session->evlist, "syscalls:sys_exit"); if (evsel && - (perf_evsel__init_syscall_tp(evsel, trace__sys_exit) < 0 || + (perf_evsel__init_raw_syscall_tp(evsel, trace__sys_exit) < 0 || perf_evsel__init_sc_tp_uint_field(evsel, ret))) { pr_err("Error during initialize raw_syscalls:sys_exit event\n"); goto out; @@ -2921,6 +3091,36 @@ static void evlist__set_evsel_handler(struct perf_evlist *evlist, void *handler) evsel->handler = handler; } +static int evlist__set_syscall_tp_fields(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel; + + evlist__for_each_entry(evlist, evsel) { + if (evsel->priv || !evsel->tp_format) + continue; + + if (strcmp(evsel->tp_format->system, "syscalls")) + continue; + + if (perf_evsel__init_syscall_tp(evsel)) + return -1; + + if (!strncmp(evsel->tp_format->name, "sys_enter_", 10)) { + struct syscall_tp *sc = evsel->priv; + + if (__tp_field__init_ptr(&sc->args, sc->id.offset + sizeof(u64))) + return -1; + } else if (!strncmp(evsel->tp_format->name, "sys_exit_", 9)) { + struct syscall_tp *sc = evsel->priv; + + if (__tp_field__init_uint(&sc->ret, sizeof(u64), sc->id.offset + sizeof(u64), evsel->needs_swap)) + return -1; + } + } + + return 0; +} + /* * XXX: Hackish, just splitting the combined -e+--event (syscalls * (raw_syscalls:{sys_{enter,exit}} + events (tracepoints, HW, SW, etc) to use @@ -2990,6 +3190,7 @@ static int trace__parse_events_option(const struct option *opt, const char *str, if (trace__validate_ev_qualifier(trace)) goto out; + trace->trace_syscalls = true; } err = 0; @@ -3045,7 +3246,7 @@ int cmd_trace(int argc, const char **argv) }, .output = stderr, .show_comm = true, - .trace_syscalls = true, + .trace_syscalls = false, .kernel_syscallchains = false, .max_stack = UINT_MAX, }; @@ -3120,8 +3321,9 @@ int cmd_trace(int argc, const char **argv) }; bool __maybe_unused max_stack_user_set = true; bool mmap_pages_user_set = true; + struct perf_evsel *evsel; const char * const trace_subcommands[] = { "record", NULL }; - int err; + int err = -1; char bf[BUFSIZ]; signal(SIGSEGV, sighandler_dump_stack); @@ -3144,6 +3346,16 @@ int cmd_trace(int argc, const char **argv) "cgroup monitoring only available in system-wide mode"); } + evsel = bpf__setup_output_event(trace.evlist, "__augmented_syscalls__"); + if (IS_ERR(evsel)) { + bpf__strerror_setup_output_event(trace.evlist, PTR_ERR(evsel), bf, sizeof(bf)); + pr_err("ERROR: Setup trace syscalls enter failed: %s\n", bf); + goto out; + } + + if (evsel) + trace.syscalls.events.augmented = evsel; + err = bpf__setup_stdout(trace.evlist); if (err) { bpf__strerror_setup_stdout(trace.evlist, err, bf, sizeof(bf)); @@ -3179,8 +3391,41 @@ int cmd_trace(int argc, const char **argv) symbol_conf.use_callchain = true; } - if (trace.evlist->nr_entries > 0) + if (trace.evlist->nr_entries > 0) { evlist__set_evsel_handler(trace.evlist, trace__event_handler); + if (evlist__set_syscall_tp_fields(trace.evlist)) { + perror("failed to set syscalls:* tracepoint fields"); + goto out; + } + } + + /* + * If we are augmenting syscalls, then combine what we put in the + * __augmented_syscalls__ BPF map with what is in the + * syscalls:sys_exit_FOO tracepoints, i.e. just like we do without BPF, + * combining raw_syscalls:sys_enter with raw_syscalls:sys_exit. + * + * We'll switch to look at two BPF maps, one for sys_enter and the + * other for sys_exit when we start augmenting the sys_exit paths with + * buffers that are being copied from kernel to userspace, think 'read' + * syscall. + */ + if (trace.syscalls.events.augmented) { + evsel = trace.syscalls.events.augmented; + + if (perf_evsel__init_augmented_syscall_tp(evsel) || + perf_evsel__init_augmented_syscall_tp_args(evsel)) + goto out; + evsel->handler = trace__sys_enter; + + evlist__for_each_entry(trace.evlist, evsel) { + if (strstarts(perf_evsel__name(evsel), "syscalls:sys_exit_")) { + perf_evsel__init_augmented_syscall_tp(evsel); + perf_evsel__init_augmented_syscall_tp_ret(evsel); + evsel->handler = trace__sys_exit; + } + } + } if ((argc >= 1) && (strcmp(argv[0], "record") == 0)) return trace__record(&trace, argc-1, &argv[1]); @@ -3191,13 +3436,7 @@ int cmd_trace(int argc, const char **argv) if (!trace.trace_syscalls && !trace.trace_pgfaults && trace.evlist->nr_entries == 0 /* Was --events used? */) { - pr_err("Please specify something to trace.\n"); - return -1; - } - - if (!trace.trace_syscalls && trace.ev_qualifier) { - pr_err("The -e option can't be used with --no-syscalls.\n"); - goto out; + trace.trace_syscalls = true; } if (output_name != NULL) { @@ -3208,8 +3447,6 @@ int cmd_trace(int argc, const char **argv) } } - trace.open_id = syscalltbl__id(trace.sctbl, "open"); - err = target__validate(&trace.opts.target); if (err) { target__strerror(&trace.opts.target, err, bf, sizeof(bf)); diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh index 10f333e2e825..c72cc73a6b09 100755 --- a/tools/perf/check-headers.sh +++ b/tools/perf/check-headers.sh @@ -7,12 +7,14 @@ include/uapi/drm/i915_drm.h include/uapi/linux/fcntl.h include/uapi/linux/kcmp.h include/uapi/linux/kvm.h +include/uapi/linux/in.h include/uapi/linux/perf_event.h include/uapi/linux/prctl.h include/uapi/linux/sched.h include/uapi/linux/stat.h include/uapi/linux/vhost.h include/uapi/sound/asound.h +include/linux/bits.h include/linux/hash.h include/uapi/linux/hw_breakpoint.h arch/x86/include/asm/disabled-features.h @@ -35,6 +37,7 @@ arch/s390/include/uapi/asm/ptrace.h arch/s390/include/uapi/asm/sie.h arch/arm/include/uapi/asm/kvm.h arch/arm64/include/uapi/asm/kvm.h +arch/arm64/include/uapi/asm/unistd.h arch/alpha/include/uapi/asm/errno.h arch/mips/include/asm/errno.h arch/mips/include/uapi/asm/errno.h @@ -53,6 +56,7 @@ include/uapi/asm-generic/errno.h include/uapi/asm-generic/errno-base.h include/uapi/asm-generic/ioctls.h include/uapi/asm-generic/mman-common.h +include/uapi/asm-generic/unistd.h ' check_2 () { @@ -64,8 +68,12 @@ check_2 () { cmd="diff $* $file1 $file2 > /dev/null" - test -f $file2 && - eval $cmd || echo "Warning: Kernel ABI header at 'tools/$file' differs from latest version at '$file'" >&2 + test -f $file2 && { + eval $cmd || { + echo "Warning: Kernel ABI header at '$file1' differs from latest version at '$file2'" >&2 + echo diff -u $file1 $file2 + } + } } check () { @@ -73,7 +81,7 @@ check () { shift - check_2 ../$file ../../$file $* + check_2 tools/$file $file $* } # Check if we have the kernel headers (tools/perf/../../include), else @@ -81,6 +89,8 @@ check () { # differences. test -d ../../include || exit 0 +cd ../.. + # simple diff check for i in $HEADERS; do check $i -B @@ -91,3 +101,8 @@ check arch/x86/lib/memcpy_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/ex check arch/x86/lib/memset_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"' check include/uapi/asm-generic/mman.h '-I "^#include <\(uapi/\)*asm-generic/mman-common.h>"' check include/uapi/linux/mman.h '-I "^#include <\(uapi/\)*asm/mman.h>"' + +# diff non-symmetric files +check_2 tools/perf/arch/x86/entry/syscalls/syscall_64.tbl arch/x86/entry/syscalls/syscall_64.tbl + +cd tools/perf diff --git a/tools/perf/command-list.txt b/tools/perf/command-list.txt index 2d0caf20ff3a..bc6c585f74fc 100644 --- a/tools/perf/command-list.txt +++ b/tools/perf/command-list.txt @@ -30,3 +30,4 @@ perf-test mainporcelain common perf-timechart mainporcelain common perf-top mainporcelain common perf-trace mainporcelain audit +perf-version mainporcelain common diff --git a/tools/perf/examples/bpf/augmented_syscalls.c b/tools/perf/examples/bpf/augmented_syscalls.c new file mode 100644 index 000000000000..2ae44813ef2d --- /dev/null +++ b/tools/perf/examples/bpf/augmented_syscalls.c @@ -0,0 +1,173 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Augment syscalls with the contents of the pointer arguments. + * + * Test it with: + * + * perf trace -e tools/perf/examples/bpf/augmented_syscalls.c cat /etc/passwd > /dev/null + * + * It'll catch some openat syscalls related to the dynamic linked and + * the last one should be the one for '/etc/passwd'. + * + * This matches what is marshalled into the raw_syscall:sys_enter payload + * expected by the 'perf trace' beautifiers, and can be used by them, that will + * check if perf_sample->raw_data is more than what is expected for each + * syscalls:sys_{enter,exit}_SYSCALL tracepoint, uing the extra data as the + * contents of pointer arguments. + */ + +#include <stdio.h> +#include <linux/socket.h> + +struct bpf_map SEC("maps") __augmented_syscalls__ = { + .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(u32), + .max_entries = __NR_CPUS__, +}; + +struct syscall_exit_args { + unsigned long long common_tp_fields; + long syscall_nr; + long ret; +}; + +struct augmented_filename { + unsigned int size; + int reserved; + char value[256]; +}; + +#define augmented_filename_syscall(syscall) \ +struct augmented_enter_##syscall##_args { \ + struct syscall_enter_##syscall##_args args; \ + struct augmented_filename filename; \ +}; \ +int syscall_enter(syscall)(struct syscall_enter_##syscall##_args *args) \ +{ \ + struct augmented_enter_##syscall##_args augmented_args = { .filename.reserved = 0, }; \ + unsigned int len = sizeof(augmented_args); \ + probe_read(&augmented_args.args, sizeof(augmented_args.args), args); \ + augmented_args.filename.size = probe_read_str(&augmented_args.filename.value, \ + sizeof(augmented_args.filename.value), \ + args->filename_ptr); \ + if (augmented_args.filename.size < sizeof(augmented_args.filename.value)) { \ + len -= sizeof(augmented_args.filename.value) - augmented_args.filename.size; \ + len &= sizeof(augmented_args.filename.value) - 1; \ + } \ + perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, \ + &augmented_args, len); \ + return 0; \ +} \ +int syscall_exit(syscall)(struct syscall_exit_args *args) \ +{ \ + return 1; /* 0 as soon as we start copying data returned by the kernel, e.g. 'read' */ \ +} + +struct syscall_enter_openat_args { + unsigned long long common_tp_fields; + long syscall_nr; + long dfd; + char *filename_ptr; + long flags; + long mode; +}; + +augmented_filename_syscall(openat); + +struct syscall_enter_open_args { + unsigned long long common_tp_fields; + long syscall_nr; + char *filename_ptr; + long flags; + long mode; +}; + +augmented_filename_syscall(open); + +struct syscall_enter_inotify_add_watch_args { + unsigned long long common_tp_fields; + long syscall_nr; + long fd; + char *filename_ptr; + long mask; +}; + +augmented_filename_syscall(inotify_add_watch); + +struct statbuf; + +struct syscall_enter_newstat_args { + unsigned long long common_tp_fields; + long syscall_nr; + char *filename_ptr; + struct stat *statbuf; +}; + +augmented_filename_syscall(newstat); + +#ifndef _K_SS_MAXSIZE +#define _K_SS_MAXSIZE 128 +#endif + +#define augmented_sockaddr_syscall(syscall) \ +struct augmented_enter_##syscall##_args { \ + struct syscall_enter_##syscall##_args args; \ + struct sockaddr_storage addr; \ +}; \ +int syscall_enter(syscall)(struct syscall_enter_##syscall##_args *args) \ +{ \ + struct augmented_enter_##syscall##_args augmented_args; \ + unsigned long addrlen = sizeof(augmented_args.addr); \ + probe_read(&augmented_args.args, sizeof(augmented_args.args), args); \ +/* FIXME_CLANG_OPTIMIZATION_THAT_ACCESSES_USER_CONTROLLED_ADDRLEN_DESPITE_THIS_CHECK */ \ +/* if (addrlen > augmented_args.args.addrlen) */ \ +/* addrlen = augmented_args.args.addrlen; */ \ +/* */ \ + probe_read(&augmented_args.addr, addrlen, args->addr_ptr); \ + perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, \ + &augmented_args, \ + sizeof(augmented_args) - sizeof(augmented_args.addr) + addrlen); \ + return 0; \ +} \ +int syscall_exit(syscall)(struct syscall_exit_args *args) \ +{ \ + return 1; /* 0 as soon as we start copying data returned by the kernel, e.g. 'read' */ \ +} + +struct sockaddr; + +struct syscall_enter_bind_args { + unsigned long long common_tp_fields; + long syscall_nr; + long fd; + struct sockaddr *addr_ptr; + unsigned long addrlen; +}; + +augmented_sockaddr_syscall(bind); + +struct syscall_enter_connect_args { + unsigned long long common_tp_fields; + long syscall_nr; + long fd; + struct sockaddr *addr_ptr; + unsigned long addrlen; +}; + +augmented_sockaddr_syscall(connect); + +struct syscall_enter_sendto_args { + unsigned long long common_tp_fields; + long syscall_nr; + long fd; + void *buff; + long len; + unsigned long flags; + struct sockaddr *addr_ptr; + long addr_len; +}; + +augmented_sockaddr_syscall(sendto); + +license(GPL); diff --git a/tools/perf/examples/bpf/etcsnoop.c b/tools/perf/examples/bpf/etcsnoop.c new file mode 100644 index 000000000000..b59e8812ee8c --- /dev/null +++ b/tools/perf/examples/bpf/etcsnoop.c @@ -0,0 +1,80 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Augment the filename syscalls with the contents of the filename pointer argument + * filtering only those that do not start with /etc/. + * + * Test it with: + * + * perf trace -e tools/perf/examples/bpf/augmented_syscalls.c cat /etc/passwd > /dev/null + * + * It'll catch some openat syscalls related to the dynamic linked and + * the last one should be the one for '/etc/passwd'. + * + * This matches what is marshalled into the raw_syscall:sys_enter payload + * expected by the 'perf trace' beautifiers, and can be used by them unmodified, + * which will be done as that feature is implemented in the next csets, for now + * it will appear in a dump done by the default tracepoint handler in 'perf trace', + * that uses bpf_output__fprintf() to just dump those contents, as done with + * the bpf-output event associated with the __bpf_output__ map declared in + * tools/perf/include/bpf/stdio.h. + */ + +#include <stdio.h> + +struct bpf_map SEC("maps") __augmented_syscalls__ = { + .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(u32), + .max_entries = __NR_CPUS__, +}; + +struct augmented_filename { + int size; + int reserved; + char value[64]; +}; + +#define augmented_filename_syscall_enter(syscall) \ +struct augmented_enter_##syscall##_args { \ + struct syscall_enter_##syscall##_args args; \ + struct augmented_filename filename; \ +}; \ +int syscall_enter(syscall)(struct syscall_enter_##syscall##_args *args) \ +{ \ + char etc[6] = "/etc/"; \ + struct augmented_enter_##syscall##_args augmented_args = { .filename.reserved = 0, }; \ + probe_read(&augmented_args.args, sizeof(augmented_args.args), args); \ + augmented_args.filename.size = probe_read_str(&augmented_args.filename.value, \ + sizeof(augmented_args.filename.value), \ + args->filename_ptr); \ + if (__builtin_memcmp(augmented_args.filename.value, etc, 4) != 0) \ + return 0; \ + perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, \ + &augmented_args, \ + (sizeof(augmented_args) - sizeof(augmented_args.filename.value) + \ + augmented_args.filename.size)); \ + return 0; \ +} + +struct syscall_enter_openat_args { + unsigned long long common_tp_fields; + long syscall_nr; + long dfd; + char *filename_ptr; + long flags; + long mode; +}; + +augmented_filename_syscall_enter(openat); + +struct syscall_enter_open_args { + unsigned long long common_tp_fields; + long syscall_nr; + char *filename_ptr; + long flags; + long mode; +}; + +augmented_filename_syscall_enter(open); + +license(GPL); diff --git a/tools/perf/examples/bpf/hello.c b/tools/perf/examples/bpf/hello.c new file mode 100644 index 000000000000..cf3c2fdc7f79 --- /dev/null +++ b/tools/perf/examples/bpf/hello.c @@ -0,0 +1,9 @@ +#include <stdio.h> + +int syscall_enter(openat)(void *args) +{ + puts("Hello, world\n"); + return 0; +} + +license(GPL); diff --git a/tools/perf/examples/bpf/sys_enter_openat.c b/tools/perf/examples/bpf/sys_enter_openat.c new file mode 100644 index 000000000000..9cd124b09392 --- /dev/null +++ b/tools/perf/examples/bpf/sys_enter_openat.c @@ -0,0 +1,33 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Hook into 'openat' syscall entry tracepoint + * + * Test it with: + * + * perf trace -e tools/perf/examples/bpf/sys_enter_openat.c cat /etc/passwd > /dev/null + * + * It'll catch some openat syscalls related to the dynamic linked and + * the last one should be the one for '/etc/passwd'. + * + * The syscall_enter_openat_args can be used to get the syscall fields + * and use them for filtering calls, i.e. use in expressions for + * the return value. + */ + +#include <bpf.h> + +struct syscall_enter_openat_args { + unsigned long long unused; + long syscall_nr; + long dfd; + char *filename_ptr; + long flags; + long mode; +}; + +int syscall_enter(openat)(struct syscall_enter_openat_args *args) +{ + return 1; +} + +license(GPL); diff --git a/tools/perf/include/bpf/bpf.h b/tools/perf/include/bpf/bpf.h index dd764ad5efdf..52b6d87fe822 100644 --- a/tools/perf/include/bpf/bpf.h +++ b/tools/perf/include/bpf/bpf.h @@ -1,13 +1,39 @@ // SPDX-License-Identifier: GPL-2.0 #ifndef _PERF_BPF_H #define _PERF_BPF_H + +#include <uapi/linux/bpf.h> + +/* + * A helper structure used by eBPF C program to describe map attributes to + * elf_bpf loader, taken from tools/testing/selftests/bpf/bpf_helpers.h: + */ +struct bpf_map { + unsigned int type; + unsigned int key_size; + unsigned int value_size; + unsigned int max_entries; + unsigned int map_flags; + unsigned int inner_map_idx; + unsigned int numa_node; +}; + #define SEC(NAME) __attribute__((section(NAME), used)) #define probe(function, vars) \ SEC(#function "=" #function " " #vars) function +#define syscall_enter(name) \ + SEC("syscalls:sys_enter_" #name) syscall_enter_ ## name + +#define syscall_exit(name) \ + SEC("syscalls:sys_exit_" #name) syscall_exit_ ## name + #define license(name) \ char _license[] SEC("license") = #name; \ int _version SEC("version") = LINUX_VERSION_CODE; +static int (*probe_read)(void *dst, int size, const void *unsafe_addr) = (void *)BPF_FUNC_probe_read; +static int (*probe_read_str)(void *dst, int size, const void *unsafe_addr) = (void *)BPF_FUNC_probe_read_str; + #endif /* _PERF_BPF_H */ diff --git a/tools/perf/include/bpf/linux/socket.h b/tools/perf/include/bpf/linux/socket.h new file mode 100644 index 000000000000..7f844568dab8 --- /dev/null +++ b/tools/perf/include/bpf/linux/socket.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI_LINUX_SOCKET_H +#define _UAPI_LINUX_SOCKET_H + +/* + * Desired design of maximum size and alignment (see RFC2553) + */ +#define _K_SS_MAXSIZE 128 /* Implementation specific max size */ +#define _K_SS_ALIGNSIZE (__alignof__ (struct sockaddr *)) + /* Implementation specific desired alignment */ + +typedef unsigned short __kernel_sa_family_t; + +struct __kernel_sockaddr_storage { + __kernel_sa_family_t ss_family; /* address family */ + /* Following field(s) are implementation specific */ + char __data[_K_SS_MAXSIZE - sizeof(unsigned short)]; + /* space to achieve desired size, */ + /* _SS_MAXSIZE value minus size of ss_family */ +} __attribute__ ((aligned(_K_SS_ALIGNSIZE))); /* force desired alignment */ + +#define sockaddr_storage __kernel_sockaddr_storage + +#endif /* _UAPI_LINUX_SOCKET_H */ diff --git a/tools/perf/include/bpf/stdio.h b/tools/perf/include/bpf/stdio.h new file mode 100644 index 000000000000..2899cb7bfed8 --- /dev/null +++ b/tools/perf/include/bpf/stdio.h @@ -0,0 +1,19 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <bpf.h> + +struct bpf_map SEC("maps") __bpf_stdout__ = { + .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(u32), + .max_entries = __NR_CPUS__, +}; + +static int (*perf_event_output)(void *, struct bpf_map *, int, void *, unsigned long) = + (void *)BPF_FUNC_perf_event_output; + +#define puts(from) \ + ({ const int __len = sizeof(from); \ + char __from[__len] = from; \ + perf_event_output(args, &__bpf_stdout__, BPF_F_CURRENT_CPU, \ + &__from, __len & (sizeof(from) - 1)); }) diff --git a/tools/perf/perf.h b/tools/perf/perf.h index a1a97956136f..21bf7f5a3cf5 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -5,6 +5,7 @@ #include <time.h> #include <stdbool.h> #include <linux/types.h> +#include <linux/stddef.h> #include <linux/perf_event.h> extern bool test_attr__enabled; @@ -24,7 +25,9 @@ static inline unsigned long long rdclock(void) return ts.tv_sec * 1000000000ULL + ts.tv_nsec; } +#ifndef MAX_NR_CPUS #define MAX_NR_CPUS 1024 +#endif extern const char *input_name; extern bool perf_host, perf_guest; diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/branch.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/branch.json new file mode 100644 index 000000000000..abc98b018446 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/branch.json @@ -0,0 +1,23 @@ +[ + { + "ArchStdEvent": "BR_IMMED_SPEC", + }, + { + "ArchStdEvent": "BR_RETURN_SPEC", + }, + { + "ArchStdEvent": "BR_INDIRECT_SPEC", + }, + { + "PublicDescription": "Mispredicted or not predicted branch speculatively executed", + "EventCode": "0x10", + "EventName": "BR_MIS_PRED", + "BriefDescription": "Branch mispredicted" + }, + { + "PublicDescription": "Predictable branch speculatively executed", + "EventCode": "0x12", + "EventName": "BR_PRED", + "BriefDescription": "Predictable branch" + }, +] diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/bus.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/bus.json new file mode 100644 index 000000000000..687b2629e1d1 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/bus.json @@ -0,0 +1,26 @@ +[ + { + "ArchStdEvent": "BUS_ACCESS_RD", + }, + { + "ArchStdEvent": "BUS_ACCESS_WR", + }, + { + "ArchStdEvent": "BUS_ACCESS_SHARED", + }, + { + "ArchStdEvent": "BUS_ACCESS_NOT_SHARED", + }, + { + "ArchStdEvent": "BUS_ACCESS_NORMAL", + }, + { + "ArchStdEvent": "BUS_ACCESS_PERIPH", + }, + { + "PublicDescription": "Bus access", + "EventCode": "0x19", + "EventName": "BUS_ACCESS", + "BriefDescription": "Bus access" + }, +] diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/cache.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/cache.json new file mode 100644 index 000000000000..df9201434cb6 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/cache.json @@ -0,0 +1,191 @@ +[ + { + "ArchStdEvent": "L1D_CACHE_RD", + }, + { + "ArchStdEvent": "L1D_CACHE_WR", + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_RD", + }, + { + "ArchStdEvent": "L1D_CACHE_INVAL", + }, + { + "ArchStdEvent": "L1D_TLB_REFILL_RD", + }, + { + "ArchStdEvent": "L1D_TLB_REFILL_WR", + }, + { + "ArchStdEvent": "L2D_CACHE_RD", + }, + { + "ArchStdEvent": "L2D_CACHE_WR", + }, + { + "ArchStdEvent": "L2D_CACHE_REFILL_RD", + }, + { + "ArchStdEvent": "L2D_CACHE_REFILL_WR", + }, + { + "ArchStdEvent": "L2D_CACHE_WB_VICTIM", + }, + { + "ArchStdEvent": "L2D_CACHE_WB_CLEAN", + }, + { + "ArchStdEvent": "L2D_CACHE_INVAL", + }, + { + "PublicDescription": "Level 1 instruction cache refill", + "EventCode": "0x01", + "EventName": "L1I_CACHE_REFILL", + "BriefDescription": "L1I cache refill" + }, + { + "PublicDescription": "Level 1 instruction TLB refill", + "EventCode": "0x02", + "EventName": "L1I_TLB_REFILL", + "BriefDescription": "L1I TLB refill" + }, + { + "PublicDescription": "Level 1 data cache refill", + "EventCode": "0x03", + "EventName": "L1D_CACHE_REFILL", + "BriefDescription": "L1D cache refill" + }, + { + "PublicDescription": "Level 1 data cache access", + "EventCode": "0x04", + "EventName": "L1D_CACHE_ACCESS", + "BriefDescription": "L1D cache access" + }, + { + "PublicDescription": "Level 1 data TLB refill", + "EventCode": "0x05", + "EventName": "L1D_TLB_REFILL", + "BriefDescription": "L1D TLB refill" + }, + { + "PublicDescription": "Level 1 instruction cache access", + "EventCode": "0x14", + "EventName": "L1I_CACHE_ACCESS", + "BriefDescription": "L1I cache access" + }, + { + "PublicDescription": "Level 2 data cache access", + "EventCode": "0x16", + "EventName": "L2D_CACHE_ACCESS", + "BriefDescription": "L2D cache access" + }, + { + "PublicDescription": "Level 2 data refill", + "EventCode": "0x17", + "EventName": "L2D_CACHE_REFILL", + "BriefDescription": "L2D cache refill" + }, + { + "PublicDescription": "Level 2 data cache, Write-Back", + "EventCode": "0x18", + "EventName": "L2D_CACHE_WB", + "BriefDescription": "L2D cache Write-Back" + }, + { + "PublicDescription": "Level 1 data TLB access. This event counts any load or store operation which accesses the data L1 TLB", + "EventCode": "0x25", + "EventName": "L1D_TLB_ACCESS", + "BriefDescription": "L1D TLB access" + }, + { + "PublicDescription": "Level 1 instruction TLB access. This event counts any instruction fetch which accesses the instruction L1 TLB", + "EventCode": "0x26", + "EventName": "L1I_TLB_ACCESS", + "BriefDescription": "L1I TLB access" + }, + { + "PublicDescription": "Level 2 access to data TLB that caused a page table walk. This event counts on any data access which causes L2D_TLB_REFILL to count", + "EventCode": "0x34", + "EventName": "L2D_TLB_ACCESS", + "BriefDescription": "L2D TLB access" + }, + { + "PublicDescription": "Level 2 access to instruciton TLB that caused a page table walk. This event counts on any instruciton access which causes L2I_TLB_REFILL to count", + "EventCode": "0x35", + "EventName": "L2I_TLB_ACCESS", + "BriefDescription": "L2D TLB access" + }, + { + "PublicDescription": "Branch target buffer misprediction", + "EventCode": "0x102", + "EventName": "BTB_MIS_PRED", + "BriefDescription": "BTB misprediction" + }, + { + "PublicDescription": "ITB miss", + "EventCode": "0x103", + "EventName": "ITB_MISS", + "BriefDescription": "ITB miss" + }, + { + "PublicDescription": "DTB miss", + "EventCode": "0x104", + "EventName": "DTB_MISS", + "BriefDescription": "DTB miss" + }, + { + "PublicDescription": "Level 1 data cache late miss", + "EventCode": "0x105", + "EventName": "L1D_CACHE_LATE_MISS", + "BriefDescription": "L1D cache late miss" + }, + { + "PublicDescription": "Level 1 data cache prefetch request", + "EventCode": "0x106", + "EventName": "L1D_CACHE_PREFETCH", + "BriefDescription": "L1D cache prefetch" + }, + { + "PublicDescription": "Level 2 data cache prefetch request", + "EventCode": "0x107", + "EventName": "L2D_CACHE_PREFETCH", + "BriefDescription": "L2D cache prefetch" + }, + { + "PublicDescription": "Level 1 stage 2 TLB refill", + "EventCode": "0x111", + "EventName": "L1_STAGE2_TLB_REFILL", + "BriefDescription": "L1 stage 2 TLB refill" + }, + { + "PublicDescription": "Page walk cache level-0 stage-1 hit", + "EventCode": "0x112", + "EventName": "PAGE_WALK_L0_STAGE1_HIT", + "BriefDescription": "Page walk, L0 stage-1 hit" + }, + { + "PublicDescription": "Page walk cache level-1 stage-1 hit", + "EventCode": "0x113", + "EventName": "PAGE_WALK_L1_STAGE1_HIT", + "BriefDescription": "Page walk, L1 stage-1 hit" + }, + { + "PublicDescription": "Page walk cache level-2 stage-1 hit", + "EventCode": "0x114", + "EventName": "PAGE_WALK_L2_STAGE1_HIT", + "BriefDescription": "Page walk, L2 stage-1 hit" + }, + { + "PublicDescription": "Page walk cache level-1 stage-2 hit", + "EventCode": "0x115", + "EventName": "PAGE_WALK_L1_STAGE2_HIT", + "BriefDescription": "Page walk, L1 stage-2 hit" + }, + { + "PublicDescription": "Page walk cache level-2 stage-2 hit", + "EventCode": "0x116", + "EventName": "PAGE_WALK_L2_STAGE2_HIT", + "BriefDescription": "Page walk, L2 stage-2 hit" + }, +] diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/clock.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/clock.json new file mode 100644 index 000000000000..38cd1f1a70dc --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/clock.json @@ -0,0 +1,20 @@ +[ + { + "PublicDescription": "The number of core clock cycles", + "EventCode": "0x11", + "EventName": "CPU_CYCLES", + "BriefDescription": "Clock cycles" + }, + { + "PublicDescription": "FSU clocking gated off cycle", + "EventCode": "0x101", + "EventName": "FSU_CLOCK_OFF_CYCLES", + "BriefDescription": "FSU clocking gated off cycle" + }, + { + "PublicDescription": "Wait state cycle", + "EventCode": "0x110", + "EventName": "Wait_CYCLES", + "BriefDescription": "Wait state cycle" + }, +] diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/exception.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/exception.json new file mode 100644 index 000000000000..3720dc28a15f --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/exception.json @@ -0,0 +1,50 @@ +[ + { + "ArchStdEvent": "EXC_UNDEF", + }, + { + "ArchStdEvent": "EXC_SVC", + }, + { + "ArchStdEvent": "EXC_PABORT", + }, + { + "ArchStdEvent": "EXC_DABORT", + }, + { + "ArchStdEvent": "EXC_IRQ", + }, + { + "ArchStdEvent": "EXC_FIQ", + }, + { + "ArchStdEvent": "EXC_HVC", + }, + { + "ArchStdEvent": "EXC_TRAP_PABORT", + }, + { + "ArchStdEvent": "EXC_TRAP_DABORT", + }, + { + "ArchStdEvent": "EXC_TRAP_OTHER", + }, + { + "ArchStdEvent": "EXC_TRAP_IRQ", + }, + { + "ArchStdEvent": "EXC_TRAP_FIQ", + }, + { + "PublicDescription": "Exception taken", + "EventCode": "0x09", + "EventName": "EXC_TAKEN", + "BriefDescription": "Exception taken" + }, + { + "PublicDescription": "Instruction architecturally executed, condition check pass, exception return", + "EventCode": "0x0a", + "EventName": "EXC_RETURN", + "BriefDescription": "Exception return" + }, +] diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/instruction.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/instruction.json new file mode 100644 index 000000000000..82cf753e6472 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/instruction.json @@ -0,0 +1,89 @@ +[ + { + "ArchStdEvent": "LD_SPEC", + }, + { + "ArchStdEvent": "ST_SPEC", + }, + { + "ArchStdEvent": "LDST_SPEC", + }, + { + "ArchStdEvent": "DP_SPEC", + }, + { + "ArchStdEvent": "ASE_SPEC", + }, + { + "ArchStdEvent": "VFP_SPEC", + }, + { + "ArchStdEvent": "PC_WRITE_SPEC", + }, + { + "ArchStdEvent": "CRYPTO_SPEC", + }, + { + "ArchStdEvent": "ISB_SPEC", + }, + { + "ArchStdEvent": "DSB_SPEC", + }, + { + "ArchStdEvent": "DMB_SPEC", + }, + { + "ArchStdEvent": "RC_LD_SPEC", + }, + { + "ArchStdEvent": "RC_ST_SPEC", + }, + { + "PublicDescription": "Instruction architecturally executed, software increment", + "EventCode": "0x00", + "EventName": "SW_INCR", + "BriefDescription": "Software increment" + }, + { + "PublicDescription": "Instruction architecturally executed", + "EventCode": "0x08", + "EventName": "INST_RETIRED", + "BriefDescription": "Instruction retired" + }, + { + "PublicDescription": "Instruction architecturally executed, condition code check pass, write to CONTEXTIDR", + "EventCode": "0x0b", + "EventName": "CID_WRITE_RETIRED", + "BriefDescription": "Write to CONTEXTIDR" + }, + { + "PublicDescription": "Operation speculatively executed", + "EventCode": "0x1b", + "EventName": "INST_SPEC", + "BriefDescription": "Speculatively executed" + }, + { + "PublicDescription": "Instruction architecturally executed (condition check pass), write to TTBR", + "EventCode": "0x1c", + "EventName": "TTBR_WRITE_RETIRED", + "BriefDescription": "Instruction executed, TTBR write" + }, + { + "PublicDescription": "Instruction architecturally executed, branch. This event counts all branches, taken or not. This excludes exception entries, debug entries and CCFAIL branches", + "EventCode": "0x21", + "EventName": "BR_RETIRED", + "BriefDescription": "Branch retired" + }, + { + "PublicDescription": "Instruction architecturally executed, mispredicted branch. This event counts any branch counted by BR_RETIRED which is not correctly predicted and causes a pipeline flush", + "EventCode": "0x22", + "EventName": "BR_MISPRED_RETIRED", + "BriefDescription": "Mispredicted branch retired" + }, + { + "PublicDescription": "Operation speculatively executed, NOP", + "EventCode": "0x100", + "EventName": "NOP_SPEC", + "BriefDescription": "Speculatively executed, NOP" + }, +] diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/intrinsic.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/intrinsic.json new file mode 100644 index 000000000000..2aecc5c2347d --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/intrinsic.json @@ -0,0 +1,14 @@ +[ + { + "ArchStdEvent": "LDREX_SPEC", + }, + { + "ArchStdEvent": "STREX_PASS_SPEC", + }, + { + "ArchStdEvent": "STREX_FAIL_SPEC", + }, + { + "ArchStdEvent": "STREX_SPEC", + }, +] diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/memory.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/memory.json new file mode 100644 index 000000000000..08508697b318 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/memory.json @@ -0,0 +1,29 @@ +[ + { + "ArchStdEvent": "MEM_ACCESS_RD", + }, + { + "ArchStdEvent": "MEM_ACCESS_WR", + }, + { + "ArchStdEvent": "UNALIGNED_LD_SPEC", + }, + { + "ArchStdEvent": "UNALIGNED_ST_SPEC", + }, + { + "ArchStdEvent": "UNALIGNED_LDST_SPEC", + }, + { + "PublicDescription": "Data memory access", + "EventCode": "0x13", + "EventName": "MEM_ACCESS", + "BriefDescription": "Memory access" + }, + { + "PublicDescription": "Local memory error. This event counts any correctable or uncorrectable memory error (ECC or parity) in the protected core RAMs", + "EventCode": "0x1a", + "EventName": "MEM_ERROR", + "BriefDescription": "Memory error" + }, +] diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/pipeline.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/pipeline.json new file mode 100644 index 000000000000..e2087de586bf --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/pipeline.json @@ -0,0 +1,50 @@ +[ + { + "PublicDescription": "Decode starved for instruction cycle", + "EventCode": "0x108", + "EventName": "DECODE_STALL", + "BriefDescription": "Decode starved" + }, + { + "PublicDescription": "Op dispatch stalled cycle", + "EventCode": "0x109", + "EventName": "DISPATCH_STALL", + "BriefDescription": "Dispatch stalled" + }, + { + "PublicDescription": "IXA Op non-issue", + "EventCode": "0x10a", + "EventName": "IXA_STALL", + "BriefDescription": "IXA stalled" + }, + { + "PublicDescription": "IXB Op non-issue", + "EventCode": "0x10b", + "EventName": "IXB_STALL", + "BriefDescription": "IXB stalled" + }, + { + "PublicDescription": "BX Op non-issue", + "EventCode": "0x10c", + "EventName": "BX_STALL", + "BriefDescription": "BX stalled" + }, + { + "PublicDescription": "LX Op non-issue", + "EventCode": "0x10d", + "EventName": "LX_STALL", + "BriefDescription": "LX stalled" + }, + { + "PublicDescription": "SX Op non-issue", + "EventCode": "0x10e", + "EventName": "SX_STALL", + "BriefDescription": "SX stalled" + }, + { + "PublicDescription": "FX Op non-issue", + "EventCode": "0x10f", + "EventName": "FX_STALL", + "BriefDescription": "FX stalled" + }, +] diff --git a/tools/perf/pmu-events/arch/arm64/cavium/thunderx2/core-imp-def.json b/tools/perf/pmu-events/arch/arm64/cavium/thunderx2/core-imp-def.json index bc03c06c3918..752e47eb6977 100644 --- a/tools/perf/pmu-events/arch/arm64/cavium/thunderx2/core-imp-def.json +++ b/tools/perf/pmu-events/arch/arm64/cavium/thunderx2/core-imp-def.json @@ -12,6 +12,21 @@ "ArchStdEvent": "L1D_CACHE_REFILL_WR", }, { + "ArchStdEvent": "L1D_CACHE_REFILL_INNER", + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_OUTER", + }, + { + "ArchStdEvent": "L1D_CACHE_WB_VICTIM", + }, + { + "ArchStdEvent": "L1D_CACHE_WB_CLEAN", + }, + { + "ArchStdEvent": "L1D_CACHE_INVAL", + }, + { "ArchStdEvent": "L1D_TLB_REFILL_RD", }, { @@ -24,9 +39,75 @@ "ArchStdEvent": "L1D_TLB_WR", }, { + "ArchStdEvent": "L2D_TLB_REFILL_RD", + }, + { + "ArchStdEvent": "L2D_TLB_REFILL_WR", + }, + { + "ArchStdEvent": "L2D_TLB_RD", + }, + { + "ArchStdEvent": "L2D_TLB_WR", + }, + { "ArchStdEvent": "BUS_ACCESS_RD", - }, - { + }, + { "ArchStdEvent": "BUS_ACCESS_WR", - } + }, + { + "ArchStdEvent": "MEM_ACCESS_RD", + }, + { + "ArchStdEvent": "MEM_ACCESS_WR", + }, + { + "ArchStdEvent": "UNALIGNED_LD_SPEC", + }, + { + "ArchStdEvent": "UNALIGNED_ST_SPEC", + }, + { + "ArchStdEvent": "UNALIGNED_LDST_SPEC", + }, + { + "ArchStdEvent": "EXC_UNDEF", + }, + { + "ArchStdEvent": "EXC_SVC", + }, + { + "ArchStdEvent": "EXC_PABORT", + }, + { + "ArchStdEvent": "EXC_DABORT", + }, + { + "ArchStdEvent": "EXC_IRQ", + }, + { + "ArchStdEvent": "EXC_FIQ", + }, + { + "ArchStdEvent": "EXC_SMC", + }, + { + "ArchStdEvent": "EXC_HVC", + }, + { + "ArchStdEvent": "EXC_TRAP_PABORT", + }, + { + "ArchStdEvent": "EXC_TRAP_DABORT", + }, + { + "ArchStdEvent": "EXC_TRAP_OTHER", + }, + { + "ArchStdEvent": "EXC_TRAP_IRQ", + }, + { + "ArchStdEvent": "EXC_TRAP_FIQ", + } ] diff --git a/tools/perf/pmu-events/arch/arm64/mapfile.csv b/tools/perf/pmu-events/arch/arm64/mapfile.csv index f03e26ecb658..59cd8604b0bd 100644 --- a/tools/perf/pmu-events/arch/arm64/mapfile.csv +++ b/tools/perf/pmu-events/arch/arm64/mapfile.csv @@ -16,3 +16,4 @@ 0x00000000420f5160,v1,cavium/thunderx2,core 0x00000000430f0af0,v1,cavium/thunderx2,core 0x00000000480fd010,v1,hisilicon/hip08,core +0x00000000500f0000,v1,ampere/emag,core diff --git a/tools/perf/pmu-events/arch/s390/cf_z10/basic.json b/tools/perf/pmu-events/arch/s390/cf_z10/basic.json index 8bf16759ca53..2dd8dafff2ef 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z10/basic.json +++ b/tools/perf/pmu-events/arch/s390/cf_z10/basic.json @@ -1,71 +1,83 @@ [ { + "Unit": "CPU-M-CF", "EventCode": "0", "EventName": "CPU_CYCLES", "BriefDescription": "CPU Cycles", "PublicDescription": "Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "1", "EventName": "INSTRUCTIONS", "BriefDescription": "Instructions", "PublicDescription": "Instruction Count" }, { + "Unit": "CPU-M-CF", "EventCode": "2", "EventName": "L1I_DIR_WRITES", "BriefDescription": "L1I Directory Writes", "PublicDescription": "Level-1 I-Cache Directory Write Count" }, { + "Unit": "CPU-M-CF", "EventCode": "3", "EventName": "L1I_PENALTY_CYCLES", "BriefDescription": "L1I Penalty Cycles", "PublicDescription": "Level-1 I-Cache Penalty Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "4", "EventName": "L1D_DIR_WRITES", "BriefDescription": "L1D Directory Writes", "PublicDescription": "Level-1 D-Cache Directory Write Count" }, { + "Unit": "CPU-M-CF", "EventCode": "5", "EventName": "L1D_PENALTY_CYCLES", "BriefDescription": "L1D Penalty Cycles", "PublicDescription": "Level-1 D-Cache Penalty Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "32", "EventName": "PROBLEM_STATE_CPU_CYCLES", "BriefDescription": "Problem-State CPU Cycles", "PublicDescription": "Problem-State Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "33", "EventName": "PROBLEM_STATE_INSTRUCTIONS", "BriefDescription": "Problem-State Instructions", "PublicDescription": "Problem-State Instruction Count" }, { + "Unit": "CPU-M-CF", "EventCode": "34", "EventName": "PROBLEM_STATE_L1I_DIR_WRITES", "BriefDescription": "Problem-State L1I Directory Writes", "PublicDescription": "Problem-State Level-1 I-Cache Directory Write Count" }, { + "Unit": "CPU-M-CF", "EventCode": "35", "EventName": "PROBLEM_STATE_L1I_PENALTY_CYCLES", "BriefDescription": "Problem-State L1I Penalty Cycles", "PublicDescription": "Problem-State Level-1 I-Cache Penalty Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "36", "EventName": "PROBLEM_STATE_L1D_DIR_WRITES", "BriefDescription": "Problem-State L1D Directory Writes", "PublicDescription": "Problem-State Level-1 D-Cache Directory Write Count" }, { + "Unit": "CPU-M-CF", "EventCode": "37", "EventName": "PROBLEM_STATE_L1D_PENALTY_CYCLES", "BriefDescription": "Problem-State L1D Penalty Cycles", diff --git a/tools/perf/pmu-events/arch/s390/cf_z10/crypto.json b/tools/perf/pmu-events/arch/s390/cf_z10/crypto.json index 7e5b72492141..db286f19e7b6 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z10/crypto.json +++ b/tools/perf/pmu-events/arch/s390/cf_z10/crypto.json @@ -1,95 +1,111 @@ [ { + "Unit": "CPU-M-CF", "EventCode": "64", "EventName": "PRNG_FUNCTIONS", "BriefDescription": "PRNG Functions", "PublicDescription": "Total number of the PRNG functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "65", "EventName": "PRNG_CYCLES", "BriefDescription": "PRNG Cycles", "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "66", "EventName": "PRNG_BLOCKED_FUNCTIONS", "BriefDescription": "PRNG Blocked Functions", "PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "67", "EventName": "PRNG_BLOCKED_CYCLES", "BriefDescription": "PRNG Blocked Cycles", "PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "68", "EventName": "SHA_FUNCTIONS", "BriefDescription": "SHA Functions", "PublicDescription": "Total number of SHA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "69", "EventName": "SHA_CYCLES", "BriefDescription": "SHA Cycles", "PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "70", "EventName": "SHA_BLOCKED_FUNCTIONS", "BriefDescription": "SHA Blocked Functions", "PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "71", "EventName": "SHA_BLOCKED_CYCLES", "BriefDescription": "SHA Bloced Cycles", "PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "72", "EventName": "DEA_FUNCTIONS", "BriefDescription": "DEA Functions", "PublicDescription": "Total number of the DEA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "73", "EventName": "DEA_CYCLES", "BriefDescription": "DEA Cycles", "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "74", "EventName": "DEA_BLOCKED_FUNCTIONS", "BriefDescription": "DEA Blocked Functions", "PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "75", "EventName": "DEA_BLOCKED_CYCLES", "BriefDescription": "DEA Blocked Cycles", "PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "76", "EventName": "AES_FUNCTIONS", "BriefDescription": "AES Functions", "PublicDescription": "Total number of AES functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "77", "EventName": "AES_CYCLES", "BriefDescription": "AES Cycles", "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "78", "EventName": "AES_BLOCKED_FUNCTIONS", "BriefDescription": "AES Blocked Functions", "PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "79", "EventName": "AES_BLOCKED_CYCLES", "BriefDescription": "AES Blocked Cycles", diff --git a/tools/perf/pmu-events/arch/s390/cf_z10/extended.json b/tools/perf/pmu-events/arch/s390/cf_z10/extended.json index 0feedb40f30f..b6b7f29ca831 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z10/extended.json +++ b/tools/perf/pmu-events/arch/s390/cf_z10/extended.json @@ -1,107 +1,125 @@ [ { + "Unit": "CPU-M-CF", "EventCode": "128", "EventName": "L1I_L2_SOURCED_WRITES", "BriefDescription": "L1I L2 Sourced Writes", "PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from the Level-2 (L1.5) cache" }, { + "Unit": "CPU-M-CF", "EventCode": "129", "EventName": "L1D_L2_SOURCED_WRITES", "BriefDescription": "L1D L2 Sourced Writes", "PublicDescription": "A directory write to the Level-1 D-Cache directory where the installed cache line was sourced from the Level-2 (L1.5) cache" }, { + "Unit": "CPU-M-CF", "EventCode": "130", "EventName": "L1I_L3_LOCAL_WRITES", "BriefDescription": "L1I L3 Local Writes", "PublicDescription": "A directory write to the Level-1 I-Cache directory where the installed cache line was sourced from the Level-3 cache that is on the same book as the Instruction cache (Local L2 cache)" }, { + "Unit": "CPU-M-CF", "EventCode": "131", "EventName": "L1D_L3_LOCAL_WRITES", "BriefDescription": "L1D L3 Local Writes", "PublicDescription": "A directory write to the Level-1 D-Cache directory where the installtion cache line was source from the Level-3 cache that is on the same book as the Data cache (Local L2 cache)" }, { + "Unit": "CPU-M-CF", "EventCode": "132", "EventName": "L1I_L3_REMOTE_WRITES", "BriefDescription": "L1I L3 Remote Writes", "PublicDescription": "A directory write to the Level-1 I-Cache directory where the installed cache line was sourced from a Level-3 cache that is not on the same book as the Instruction cache (Remote L2 cache)" }, { + "Unit": "CPU-M-CF", "EventCode": "133", "EventName": "L1D_L3_REMOTE_WRITES", "BriefDescription": "L1D L3 Remote Writes", "PublicDescription": "A directory write to the Level-1 D-Cache directory where the installed cache line was sourced from a Level-3 cache that is not on the same book as the Data cache (Remote L2 cache)" }, { + "Unit": "CPU-M-CF", "EventCode": "134", "EventName": "L1D_LMEM_SOURCED_WRITES", "BriefDescription": "L1D Local Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 D-Cache directory where the installed cache line was sourced from memory that is attached to the same book as the Data cache (Local Memory)" }, { + "Unit": "CPU-M-CF", "EventCode": "135", "EventName": "L1I_LMEM_SOURCED_WRITES", "BriefDescription": "L1I Local Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 I-Cache where the installed cache line was sourced from memory that is attached to the s ame book as the Instruction cache (Local Memory)" }, { + "Unit": "CPU-M-CF", "EventCode": "136", "EventName": "L1D_RO_EXCL_WRITES", "BriefDescription": "L1D Read-only Exclusive Writes", "PublicDescription": "A directory write to the Level-1 D-Cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line" }, { + "Unit": "CPU-M-CF", "EventCode": "137", "EventName": "L1I_CACHELINE_INVALIDATES", "BriefDescription": "L1I Cacheline Invalidates", "PublicDescription": "A cache line in the Level-1 I-Cache has been invalidated by a store on the same CPU as the Level-1 I-Cache" }, { + "Unit": "CPU-M-CF", "EventCode": "138", "EventName": "ITLB1_WRITES", "BriefDescription": "ITLB1 Writes", "PublicDescription": "A translation entry has been written into the Level-1 Instruction Translation Lookaside Buffer" }, { + "Unit": "CPU-M-CF", "EventCode": "139", "EventName": "DTLB1_WRITES", "BriefDescription": "DTLB1 Writes", "PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer" }, { + "Unit": "CPU-M-CF", "EventCode": "140", "EventName": "TLB2_PTE_WRITES", "BriefDescription": "TLB2 PTE Writes", "PublicDescription": "A translation entry has been written to the Level-2 TLB Page Table Entry arrays" }, { + "Unit": "CPU-M-CF", "EventCode": "141", "EventName": "TLB2_CRSTE_WRITES", "BriefDescription": "TLB2 CRSTE Writes", "PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays" }, { + "Unit": "CPU-M-CF", "EventCode": "142", "EventName": "TLB2_CRSTE_HPAGE_WRITES", "BriefDescription": "TLB2 CRSTE One-Megabyte Page Writes", "PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays for a one-megabyte large page translation" }, { + "Unit": "CPU-M-CF", "EventCode": "145", "EventName": "ITLB1_MISSES", "BriefDescription": "ITLB1 Misses", "PublicDescription": "Level-1 Instruction TLB miss in progress. Incremented by one for every cycle an ITLB1 miss is in progress" }, { + "Unit": "CPU-M-CF", "EventCode": "146", "EventName": "DTLB1_MISSES", "BriefDescription": "DTLB1 Misses", "PublicDescription": "Level-1 Data TLB miss in progress. Incremented by one for every cycle an DTLB1 miss is in progress" }, { + "Unit": "CPU-M-CF", "EventCode": "147", "EventName": "L2C_STORES_SENT", "BriefDescription": "L2C Stores Sent", diff --git a/tools/perf/pmu-events/arch/s390/cf_z13/basic.json b/tools/perf/pmu-events/arch/s390/cf_z13/basic.json index 8bf16759ca53..2dd8dafff2ef 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z13/basic.json +++ b/tools/perf/pmu-events/arch/s390/cf_z13/basic.json @@ -1,71 +1,83 @@ [ { + "Unit": "CPU-M-CF", "EventCode": "0", "EventName": "CPU_CYCLES", "BriefDescription": "CPU Cycles", "PublicDescription": "Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "1", "EventName": "INSTRUCTIONS", "BriefDescription": "Instructions", "PublicDescription": "Instruction Count" }, { + "Unit": "CPU-M-CF", "EventCode": "2", "EventName": "L1I_DIR_WRITES", "BriefDescription": "L1I Directory Writes", "PublicDescription": "Level-1 I-Cache Directory Write Count" }, { + "Unit": "CPU-M-CF", "EventCode": "3", "EventName": "L1I_PENALTY_CYCLES", "BriefDescription": "L1I Penalty Cycles", "PublicDescription": "Level-1 I-Cache Penalty Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "4", "EventName": "L1D_DIR_WRITES", "BriefDescription": "L1D Directory Writes", "PublicDescription": "Level-1 D-Cache Directory Write Count" }, { + "Unit": "CPU-M-CF", "EventCode": "5", "EventName": "L1D_PENALTY_CYCLES", "BriefDescription": "L1D Penalty Cycles", "PublicDescription": "Level-1 D-Cache Penalty Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "32", "EventName": "PROBLEM_STATE_CPU_CYCLES", "BriefDescription": "Problem-State CPU Cycles", "PublicDescription": "Problem-State Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "33", "EventName": "PROBLEM_STATE_INSTRUCTIONS", "BriefDescription": "Problem-State Instructions", "PublicDescription": "Problem-State Instruction Count" }, { + "Unit": "CPU-M-CF", "EventCode": "34", "EventName": "PROBLEM_STATE_L1I_DIR_WRITES", "BriefDescription": "Problem-State L1I Directory Writes", "PublicDescription": "Problem-State Level-1 I-Cache Directory Write Count" }, { + "Unit": "CPU-M-CF", "EventCode": "35", "EventName": "PROBLEM_STATE_L1I_PENALTY_CYCLES", "BriefDescription": "Problem-State L1I Penalty Cycles", "PublicDescription": "Problem-State Level-1 I-Cache Penalty Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "36", "EventName": "PROBLEM_STATE_L1D_DIR_WRITES", "BriefDescription": "Problem-State L1D Directory Writes", "PublicDescription": "Problem-State Level-1 D-Cache Directory Write Count" }, { + "Unit": "CPU-M-CF", "EventCode": "37", "EventName": "PROBLEM_STATE_L1D_PENALTY_CYCLES", "BriefDescription": "Problem-State L1D Penalty Cycles", diff --git a/tools/perf/pmu-events/arch/s390/cf_z13/crypto.json b/tools/perf/pmu-events/arch/s390/cf_z13/crypto.json index 7e5b72492141..db286f19e7b6 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z13/crypto.json +++ b/tools/perf/pmu-events/arch/s390/cf_z13/crypto.json @@ -1,95 +1,111 @@ [ { + "Unit": "CPU-M-CF", "EventCode": "64", "EventName": "PRNG_FUNCTIONS", "BriefDescription": "PRNG Functions", "PublicDescription": "Total number of the PRNG functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "65", "EventName": "PRNG_CYCLES", "BriefDescription": "PRNG Cycles", "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "66", "EventName": "PRNG_BLOCKED_FUNCTIONS", "BriefDescription": "PRNG Blocked Functions", "PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "67", "EventName": "PRNG_BLOCKED_CYCLES", "BriefDescription": "PRNG Blocked Cycles", "PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "68", "EventName": "SHA_FUNCTIONS", "BriefDescription": "SHA Functions", "PublicDescription": "Total number of SHA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "69", "EventName": "SHA_CYCLES", "BriefDescription": "SHA Cycles", "PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "70", "EventName": "SHA_BLOCKED_FUNCTIONS", "BriefDescription": "SHA Blocked Functions", "PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "71", "EventName": "SHA_BLOCKED_CYCLES", "BriefDescription": "SHA Bloced Cycles", "PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "72", "EventName": "DEA_FUNCTIONS", "BriefDescription": "DEA Functions", "PublicDescription": "Total number of the DEA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "73", "EventName": "DEA_CYCLES", "BriefDescription": "DEA Cycles", "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "74", "EventName": "DEA_BLOCKED_FUNCTIONS", "BriefDescription": "DEA Blocked Functions", "PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "75", "EventName": "DEA_BLOCKED_CYCLES", "BriefDescription": "DEA Blocked Cycles", "PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "76", "EventName": "AES_FUNCTIONS", "BriefDescription": "AES Functions", "PublicDescription": "Total number of AES functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "77", "EventName": "AES_CYCLES", "BriefDescription": "AES Cycles", "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "78", "EventName": "AES_BLOCKED_FUNCTIONS", "BriefDescription": "AES Blocked Functions", "PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "79", "EventName": "AES_BLOCKED_CYCLES", "BriefDescription": "AES Blocked Cycles", diff --git a/tools/perf/pmu-events/arch/s390/cf_z13/extended.json b/tools/perf/pmu-events/arch/s390/cf_z13/extended.json index 9a002b6967f1..436ce33f1182 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z13/extended.json +++ b/tools/perf/pmu-events/arch/s390/cf_z13/extended.json @@ -1,335 +1,391 @@ [ { + "Unit": "CPU-M-CF", "EventCode": "128", "EventName": "L1D_RO_EXCL_WRITES", "BriefDescription": "L1D Read-only Exclusive Writes", "PublicDescription": "A directory write to the Level-1 Data cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line." }, { + "Unit": "CPU-M-CF", "EventCode": "129", "EventName": "DTLB1_WRITES", "BriefDescription": "DTLB1 Writes", "PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer" }, { + "Unit": "CPU-M-CF", "EventCode": "130", "EventName": "DTLB1_MISSES", "BriefDescription": "DTLB1 Misses", "PublicDescription": "Level-1 Data TLB miss in progress. Incremented by one for every cycle a DTLB1 miss is in progress." }, { + "Unit": "CPU-M-CF", "EventCode": "131", "EventName": "DTLB1_HPAGE_WRITES", "BriefDescription": "DTLB1 One-Megabyte Page Writes", "PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer for a one-megabyte page" }, { + "Unit": "CPU-M-CF", "EventCode": "132", "EventName": "DTLB1_GPAGE_WRITES", "BriefDescription": "DTLB1 Two-Gigabyte Page Writes", "PublicDescription": "Counter:132 Name:DTLB1_GPAGE_WRITES A translation entry has been written to the Level-1 Data Translation Lookaside Buffer for a two-gigabyte page." }, { + "Unit": "CPU-M-CF", "EventCode": "133", "EventName": "L1D_L2D_SOURCED_WRITES", "BriefDescription": "L1D L2D Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from the Level-2 Data cache" }, { + "Unit": "CPU-M-CF", "EventCode": "134", "EventName": "ITLB1_WRITES", "BriefDescription": "ITLB1 Writes", "PublicDescription": "A translation entry has been written to the Level-1 Instruction Translation Lookaside Buffer" }, { + "Unit": "CPU-M-CF", "EventCode": "135", "EventName": "ITLB1_MISSES", "BriefDescription": "ITLB1 Misses", "PublicDescription": "Level-1 Instruction TLB miss in progress. Incremented by one for every cycle an ITLB1 miss is in progress" }, { + "Unit": "CPU-M-CF", "EventCode": "136", "EventName": "L1I_L2I_SOURCED_WRITES", "BriefDescription": "L1I L2I Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from the Level-2 Instruction cache" }, { + "Unit": "CPU-M-CF", "EventCode": "137", "EventName": "TLB2_PTE_WRITES", "BriefDescription": "TLB2 PTE Writes", "PublicDescription": "A translation entry has been written to the Level-2 TLB Page Table Entry arrays" }, { + "Unit": "CPU-M-CF", "EventCode": "138", "EventName": "TLB2_CRSTE_HPAGE_WRITES", "BriefDescription": "TLB2 CRSTE One-Megabyte Page Writes", "PublicDescription": "A translation entry has been written to the Level-2 TLB Combined Region Segment Table Entry arrays for a one-megabyte large page translation" }, { + "Unit": "CPU-M-CF", "EventCode": "139", "EventName": "TLB2_CRSTE_WRITES", "BriefDescription": "TLB2 CRSTE Writes", "PublicDescription": "A translation entry has been written to the Level-2 TLB Combined Region Segment Table Entry arrays" }, { + "Unit": "CPU-M-CF", "EventCode": "140", "EventName": "TX_C_TEND", "BriefDescription": "Completed TEND instructions in constrained TX mode", "PublicDescription": "A TEND instruction has completed in a constrained transactional-execution mode" }, { + "Unit": "CPU-M-CF", "EventCode": "141", "EventName": "TX_NC_TEND", "BriefDescription": "Completed TEND instructions in non-constrained TX mode", "PublicDescription": "A TEND instruction has completed in a non-constrained transactional-execution mode" }, { + "Unit": "CPU-M-CF", "EventCode": "143", "EventName": "L1C_TLB1_MISSES", "BriefDescription": "L1C TLB1 Misses", "PublicDescription": "Increments by one for any cycle where a Level-1 cache or Level-1 TLB miss is in progress." }, { + "Unit": "CPU-M-CF", "EventCode": "144", "EventName": "L1D_ONCHIP_L3_SOURCED_WRITES", "BriefDescription": "L1D On-Chip L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Chip Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "145", "EventName": "L1D_ONCHIP_L3_SOURCED_WRITES_IV", "BriefDescription": "L1D On-Chip L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Chip Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "146", "EventName": "L1D_ONNODE_L4_SOURCED_WRITES", "BriefDescription": "L1D On-Node L4 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Node Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "147", "EventName": "L1D_ONNODE_L3_SOURCED_WRITES_IV", "BriefDescription": "L1D On-Node L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Node Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "148", "EventName": "L1D_ONNODE_L3_SOURCED_WRITES", "BriefDescription": "L1D On-Node L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Node Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "149", "EventName": "L1D_ONDRAWER_L4_SOURCED_WRITES", "BriefDescription": "L1D On-Drawer L4 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Drawer Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "150", "EventName": "L1D_ONDRAWER_L3_SOURCED_WRITES_IV", "BriefDescription": "L1D On-Drawer L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Drawer Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "151", "EventName": "L1D_ONDRAWER_L3_SOURCED_WRITES", "BriefDescription": "L1D On-Drawer L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Drawer Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "152", "EventName": "L1D_OFFDRAWER_SCOL_L4_SOURCED_WRITES", "BriefDescription": "L1D Off-Drawer Same-Column L4 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "153", "EventName": "L1D_OFFDRAWER_SCOL_L3_SOURCED_WRITES_IV", "BriefDescription": "L1D Off-Drawer Same-Column L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "154", "EventName": "L1D_OFFDRAWER_SCOL_L3_SOURCED_WRITES", "BriefDescription": "L1D Off-Drawer Same-Column L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "155", "EventName": "L1D_OFFDRAWER_FCOL_L4_SOURCED_WRITES", "BriefDescription": "L1D Off-Drawer Far-Column L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "156", "EventName": "L1D_OFFDRAWER_FCOL_L3_SOURCED_WRITES_IV", "BriefDescription": "L1D Off-Drawer Far-Column L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "157", "EventName": "L1D_OFFDRAWER_FCOL_L3_SOURCED_WRITES", "BriefDescription": "L1D Off-Drawer Far-Column L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "158", "EventName": "L1D_ONNODE_MEM_SOURCED_WRITES", "BriefDescription": "L1D On-Node Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Node memory" }, { + "Unit": "CPU-M-CF", "EventCode": "159", "EventName": "L1D_ONDRAWER_MEM_SOURCED_WRITES", "BriefDescription": "L1D On-Drawer Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Drawer memory" }, { + "Unit": "CPU-M-CF", "EventCode": "160", "EventName": "L1D_OFFDRAWER_MEM_SOURCED_WRITES", "BriefDescription": "L1D Off-Drawer Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Drawer memory" }, { + "Unit": "CPU-M-CF", "EventCode": "161", "EventName": "L1D_ONCHIP_MEM_SOURCED_WRITES", "BriefDescription": "L1D On-Chip Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Chip memory" }, { + "Unit": "CPU-M-CF", "EventCode": "162", "EventName": "L1I_ONCHIP_L3_SOURCED_WRITES", "BriefDescription": "L1I On-Chip L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Chip Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "163", "EventName": "L1I_ONCHIP_L3_SOURCED_WRITES_IV", "BriefDescription": "L1I On-Chip L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On Chip Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "164", "EventName": "L1I_ONNODE_L4_SOURCED_WRITES", "BriefDescription": "L1I On-Chip L4 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Node Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "165", "EventName": "L1I_ONNODE_L3_SOURCED_WRITES_IV", "BriefDescription": "L1I On-Node L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Node Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "166", "EventName": "L1I_ONNODE_L3_SOURCED_WRITES", "BriefDescription": "L1I On-Node L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Node Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "167", "EventName": "L1I_ONDRAWER_L4_SOURCED_WRITES", "BriefDescription": "L1I On-Drawer L4 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Drawer Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "168", "EventName": "L1I_ONDRAWER_L3_SOURCED_WRITES_IV", "BriefDescription": "L1I On-Drawer L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Drawer Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "169", "EventName": "L1I_ONDRAWER_L3_SOURCED_WRITES", "BriefDescription": "L1I On-Drawer L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Drawer Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "170", "EventName": "L1I_OFFDRAWER_SCOL_L4_SOURCED_WRITES", "BriefDescription": "L1I Off-Drawer Same-Column L4 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "171", "EventName": "L1I_OFFDRAWER_SCOL_L3_SOURCED_WRITES_IV", "BriefDescription": "L1I Off-Drawer Same-Column L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "172", "EventName": "L1I_OFFDRAWER_SCOL_L3_SOURCED_WRITES", "BriefDescription": "L1I Off-Drawer Same-Column L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "173", "EventName": "L1I_OFFDRAWER_FCOL_L4_SOURCED_WRITES", "BriefDescription": "L1I Off-Drawer Far-Column L4 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "174", "EventName": "L1I_OFFDRAWER_FCOL_L3_SOURCED_WRITES_IV", "BriefDescription": "L1I Off-Drawer Far-Column L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "175", "EventName": "L1I_OFFDRAWER_FCOL_L3_SOURCED_WRITES", "BriefDescription": "L1I Off-Drawer Far-Column L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "176", "EventName": "L1I_ONNODE_MEM_SOURCED_WRITES", "BriefDescription": "L1I On-Node Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Node memory" }, { + "Unit": "CPU-M-CF", "EventCode": "177", "EventName": "L1I_ONDRAWER_MEM_SOURCED_WRITES", "BriefDescription": "L1I On-Drawer Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Drawer memory" }, { + "Unit": "CPU-M-CF", "EventCode": "178", "EventName": "L1I_OFFDRAWER_MEM_SOURCED_WRITES", "BriefDescription": "L1I Off-Drawer Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Drawer memory" }, { + "Unit": "CPU-M-CF", "EventCode": "179", "EventName": "L1I_ONCHIP_MEM_SOURCED_WRITES", "BriefDescription": "L1I On-Chip Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Chip memory" }, { + "Unit": "CPU-M-CF", "EventCode": "218", "EventName": "TX_NC_TABORT", "BriefDescription": "Aborted transactions in non-constrained TX mode", "PublicDescription": "A transaction abort has occurred in a non-constrained transactional-execution mode" }, { + "Unit": "CPU-M-CF", "EventCode": "219", "EventName": "TX_C_TABORT_NO_SPECIAL", "BriefDescription": "Aborted transactions in constrained TX mode not using special completion logic", "PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is not using any special logic to allow the transaction to complete" }, { + "Unit": "CPU-M-CF", "EventCode": "220", "EventName": "TX_C_TABORT_SPECIAL", "BriefDescription": "Aborted transactions in constrained TX mode using special completion logic", "PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is using special logic to allow the transaction to complete" }, { + "Unit": "CPU-M-CF", "EventCode": "448", "EventName": "MT_DIAG_CYCLES_ONE_THR_ACTIVE", "BriefDescription": "Cycle count with one thread active", "PublicDescription": "Cycle count with one thread active" }, { + "Unit": "CPU-M-CF", "EventCode": "449", "EventName": "MT_DIAG_CYCLES_TWO_THR_ACTIVE", "BriefDescription": "Cycle count with two threads active", diff --git a/tools/perf/pmu-events/arch/s390/cf_z13/transaction.json b/tools/perf/pmu-events/arch/s390/cf_z13/transaction.json new file mode 100644 index 000000000000..1a0034f79f73 --- /dev/null +++ b/tools/perf/pmu-events/arch/s390/cf_z13/transaction.json @@ -0,0 +1,7 @@ +[ + { + "BriefDescription": "Transaction count", + "MetricName": "transaction", + "MetricExpr": "TX_C_TEND + TX_NC_TEND + TX_NC_TABORT + TX_C_TABORT_SPECIAL + TX_C_TABORT_NO_SPECIAL" + } +] diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/basic.json b/tools/perf/pmu-events/arch/s390/cf_z14/basic.json index 8f653c9d899d..17fb5241928b 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z14/basic.json +++ b/tools/perf/pmu-events/arch/s390/cf_z14/basic.json @@ -1,47 +1,55 @@ [ { + "Unit": "CPU-M-CF", "EventCode": "0", "EventName": "CPU_CYCLES", "BriefDescription": "CPU Cycles", "PublicDescription": "Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "1", "EventName": "INSTRUCTIONS", "BriefDescription": "Instructions", "PublicDescription": "Instruction Count" }, { + "Unit": "CPU-M-CF", "EventCode": "2", "EventName": "L1I_DIR_WRITES", "BriefDescription": "L1I Directory Writes", "PublicDescription": "Level-1 I-Cache Directory Write Count" }, { + "Unit": "CPU-M-CF", "EventCode": "3", "EventName": "L1I_PENALTY_CYCLES", "BriefDescription": "L1I Penalty Cycles", "PublicDescription": "Level-1 I-Cache Penalty Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "4", "EventName": "L1D_DIR_WRITES", "BriefDescription": "L1D Directory Writes", "PublicDescription": "Level-1 D-Cache Directory Write Count" }, { + "Unit": "CPU-M-CF", "EventCode": "5", "EventName": "L1D_PENALTY_CYCLES", "BriefDescription": "L1D Penalty Cycles", "PublicDescription": "Level-1 D-Cache Penalty Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "32", "EventName": "PROBLEM_STATE_CPU_CYCLES", "BriefDescription": "Problem-State CPU Cycles", "PublicDescription": "Problem-State Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "33", "EventName": "PROBLEM_STATE_INSTRUCTIONS", "BriefDescription": "Problem-State Instructions", diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/crypto.json b/tools/perf/pmu-events/arch/s390/cf_z14/crypto.json index 7e5b72492141..db286f19e7b6 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z14/crypto.json +++ b/tools/perf/pmu-events/arch/s390/cf_z14/crypto.json @@ -1,95 +1,111 @@ [ { + "Unit": "CPU-M-CF", "EventCode": "64", "EventName": "PRNG_FUNCTIONS", "BriefDescription": "PRNG Functions", "PublicDescription": "Total number of the PRNG functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "65", "EventName": "PRNG_CYCLES", "BriefDescription": "PRNG Cycles", "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "66", "EventName": "PRNG_BLOCKED_FUNCTIONS", "BriefDescription": "PRNG Blocked Functions", "PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "67", "EventName": "PRNG_BLOCKED_CYCLES", "BriefDescription": "PRNG Blocked Cycles", "PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "68", "EventName": "SHA_FUNCTIONS", "BriefDescription": "SHA Functions", "PublicDescription": "Total number of SHA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "69", "EventName": "SHA_CYCLES", "BriefDescription": "SHA Cycles", "PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "70", "EventName": "SHA_BLOCKED_FUNCTIONS", "BriefDescription": "SHA Blocked Functions", "PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "71", "EventName": "SHA_BLOCKED_CYCLES", "BriefDescription": "SHA Bloced Cycles", "PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "72", "EventName": "DEA_FUNCTIONS", "BriefDescription": "DEA Functions", "PublicDescription": "Total number of the DEA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "73", "EventName": "DEA_CYCLES", "BriefDescription": "DEA Cycles", "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "74", "EventName": "DEA_BLOCKED_FUNCTIONS", "BriefDescription": "DEA Blocked Functions", "PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "75", "EventName": "DEA_BLOCKED_CYCLES", "BriefDescription": "DEA Blocked Cycles", "PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "76", "EventName": "AES_FUNCTIONS", "BriefDescription": "AES Functions", "PublicDescription": "Total number of AES functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "77", "EventName": "AES_CYCLES", "BriefDescription": "AES Cycles", "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "78", "EventName": "AES_BLOCKED_FUNCTIONS", "BriefDescription": "AES Blocked Functions", "PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "79", "EventName": "AES_BLOCKED_CYCLES", "BriefDescription": "AES Blocked Cycles", diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/extended.json b/tools/perf/pmu-events/arch/s390/cf_z14/extended.json index aa4dfb46b65b..e7a3524b748f 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z14/extended.json +++ b/tools/perf/pmu-events/arch/s390/cf_z14/extended.json @@ -1,317 +1,370 @@ [ { + "Unit": "CPU-M-CF", "EventCode": "128", "EventName": "L1D_RO_EXCL_WRITES", "BriefDescription": "L1D Read-only Exclusive Writes", "PublicDescription": "Counter:128 Name:L1D_RO_EXCL_WRITES A directory write to the Level-1 Data cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line" }, { + "Unit": "CPU-M-CF", "EventCode": "129", "EventName": "DTLB2_WRITES", "BriefDescription": "DTLB2 Writes", "PublicDescription": "A translation has been written into The Translation Lookaside Buffer 2 (TLB2) and the request was made by the data cache" }, { + "Unit": "CPU-M-CF", "EventCode": "130", "EventName": "DTLB2_MISSES", "BriefDescription": "DTLB2 Misses", "PublicDescription": "A TLB2 miss is in progress for a request made by the data cache. Incremented by one for every TLB2 miss in progress for the Level-1 Data cache on this cycle" }, { + "Unit": "CPU-M-CF", "EventCode": "131", "EventName": "DTLB2_HPAGE_WRITES", "BriefDescription": "DTLB2 One-Megabyte Page Writes", "PublicDescription": "A translation entry was written into the Combined Region and Segment Table Entry array in the Level-2 TLB for a one-megabyte page or a Last Host Translation was done" }, { + "Unit": "CPU-M-CF", "EventCode": "132", "EventName": "DTLB2_GPAGE_WRITES", "BriefDescription": "DTLB2 Two-Gigabyte Page Writes", "PublicDescription": "A translation entry for a two-gigabyte page was written into the Level-2 TLB" }, { + "Unit": "CPU-M-CF", "EventCode": "133", "EventName": "L1D_L2D_SOURCED_WRITES", "BriefDescription": "L1D L2D Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from the Level-2 Data cache" }, { + "Unit": "CPU-M-CF", "EventCode": "134", "EventName": "ITLB2_WRITES", "BriefDescription": "ITLB2 Writes", "PublicDescription": "A translation entry has been written into the Translation Lookaside Buffer 2 (TLB2) and the request was made by the instruction cache" }, { + "Unit": "CPU-M-CF", "EventCode": "135", "EventName": "ITLB2_MISSES", "BriefDescription": "ITLB2 Misses", "PublicDescription": "A TLB2 miss is in progress for a request made by the instruction cache. Incremented by one for every TLB2 miss in progress for the Level-1 Instruction cache in a cycle" }, { + "Unit": "CPU-M-CF", "EventCode": "136", "EventName": "L1I_L2I_SOURCED_WRITES", "BriefDescription": "L1I L2I Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from the Level-2 Instruction cache" }, { + "Unit": "CPU-M-CF", "EventCode": "137", "EventName": "TLB2_PTE_WRITES", "BriefDescription": "TLB2 PTE Writes", "PublicDescription": "A translation entry was written into the Page Table Entry array in the Level-2 TLB" }, { + "Unit": "CPU-M-CF", "EventCode": "138", "EventName": "TLB2_CRSTE_WRITES", "BriefDescription": "TLB2 CRSTE Writes", "PublicDescription": "Translation entries were written into the Combined Region and Segment Table Entry array and the Page Table Entry array in the Level-2 TLB" }, { + "Unit": "CPU-M-CF", "EventCode": "139", "EventName": "TLB2_ENGINES_BUSY", "BriefDescription": "TLB2 Engines Busy", "PublicDescription": "The number of Level-2 TLB translation engines busy in a cycle" }, { + "Unit": "CPU-M-CF", "EventCode": "140", "EventName": "TX_C_TEND", "BriefDescription": "Completed TEND instructions in constrained TX mode", "PublicDescription": "A TEND instruction has completed in a constrained transactional-execution mode" }, { + "Unit": "CPU-M-CF", "EventCode": "141", "EventName": "TX_NC_TEND", "BriefDescription": "Completed TEND instructions in non-constrained TX mode", "PublicDescription": "A TEND instruction has completed in a non-constrained transactional-execution mode" }, { + "Unit": "CPU-M-CF", "EventCode": "143", "EventName": "L1C_TLB2_MISSES", "BriefDescription": "L1C TLB2 Misses", "PublicDescription": "Increments by one for any cycle where a level-1 cache or level-2 TLB miss is in progress" }, { + "Unit": "CPU-M-CF", "EventCode": "144", "EventName": "L1D_ONCHIP_L3_SOURCED_WRITES", "BriefDescription": "L1D On-Chip L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Chip Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "145", "EventName": "L1D_ONCHIP_MEMORY_SOURCED_WRITES", "BriefDescription": "L1D On-Chip Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Chip memory" }, { + "Unit": "CPU-M-CF", "EventCode": "146", "EventName": "L1D_ONCHIP_L3_SOURCED_WRITES_IV", "BriefDescription": "L1D On-Chip L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Chip Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "147", "EventName": "L1D_ONCLUSTER_L3_SOURCED_WRITES", "BriefDescription": "L1D On-Cluster L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Cluster Level-3 cache withountervention" }, { + "Unit": "CPU-M-CF", "EventCode": "148", "EventName": "L1D_ONCLUSTER_MEMORY_SOURCED_WRITES", "BriefDescription": "L1D On-Cluster Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Cluster memory" }, { + "Unit": "CPU-M-CF", "EventCode": "149", "EventName": "L1D_ONCLUSTER_L3_SOURCED_WRITES_IV", "BriefDescription": "L1D On-Cluster L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Cluster Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "150", "EventName": "L1D_OFFCLUSTER_L3_SOURCED_WRITES", "BriefDescription": "L1D Off-Cluster L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "151", "EventName": "L1D_OFFCLUSTER_MEMORY_SOURCED_WRITES", "BriefDescription": "L1D Off-Cluster Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from Off-Cluster memory" }, { + "Unit": "CPU-M-CF", "EventCode": "152", "EventName": "L1D_OFFCLUSTER_L3_SOURCED_WRITES_IV", "BriefDescription": "L1D Off-Cluster L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "153", "EventName": "L1D_OFFDRAWER_L3_SOURCED_WRITES", "BriefDescription": "L1D Off-Drawer L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "154", "EventName": "L1D_OFFDRAWER_MEMORY_SOURCED_WRITES", "BriefDescription": "L1D Off-Drawer Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from Off-Drawer memory" }, { + "Unit": "CPU-M-CF", "EventCode": "155", "EventName": "L1D_OFFDRAWER_L3_SOURCED_WRITES_IV", "BriefDescription": "L1D Off-Drawer L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "156", "EventName": "L1D_ONDRAWER_L4_SOURCED_WRITES", "BriefDescription": "L1D On-Drawer L4 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Drawer Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "157", "EventName": "L1D_OFFDRAWER_L4_SOURCED_WRITES", "BriefDescription": "L1D Off-Drawer L4 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from Off-Drawer Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "158", "EventName": "L1D_ONCHIP_L3_SOURCED_WRITES_RO", "BriefDescription": "L1D On-Chip L3 Sourced Writes read-only", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Chip L3 but a read-only invalidate was done to remove other copies of the cache line" }, { + "Unit": "CPU-M-CF", "EventCode": "162", "EventName": "L1I_ONCHIP_L3_SOURCED_WRITES", "BriefDescription": "L1I On-Chip L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache ine was sourced from an On-Chip Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "163", "EventName": "L1I_ONCHIP_MEMORY_SOURCED_WRITES", "BriefDescription": "L1I On-Chip Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache ine was sourced from On-Chip memory" }, { + "Unit": "CPU-M-CF", "EventCode": "164", "EventName": "L1I_ONCHIP_L3_SOURCED_WRITES_IV", "BriefDescription": "L1I On-Chip L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache ine was sourced from an On-Chip Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "165", "EventName": "L1I_ONCLUSTER_L3_SOURCED_WRITES", "BriefDescription": "L1I On-Cluster L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Cluster Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "166", "EventName": "L1I_ONCLUSTER_MEMORY_SOURCED_WRITES", "BriefDescription": "L1I On-Cluster Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Cluster memory" }, { + "Unit": "CPU-M-CF", "EventCode": "167", "EventName": "L1I_ONCLUSTER_L3_SOURCED_WRITES_IV", "BriefDescription": "L1I On-Cluster L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Cluster Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "168", "EventName": "L1I_OFFCLUSTER_L3_SOURCED_WRITES", "BriefDescription": "L1I Off-Cluster L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "169", "EventName": "L1I_OFFCLUSTER_MEMORY_SOURCED_WRITES", "BriefDescription": "L1I Off-Cluster Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from Off-Cluster memory" }, { + "Unit": "CPU-M-CF", "EventCode": "170", "EventName": "L1I_OFFCLUSTER_L3_SOURCED_WRITES_IV", "BriefDescription": "L1I Off-Cluster L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "171", "EventName": "L1I_OFFDRAWER_L3_SOURCED_WRITES", "BriefDescription": "L1I Off-Drawer L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "172", "EventName": "L1I_OFFDRAWER_MEMORY_SOURCED_WRITES", "BriefDescription": "L1I Off-Drawer Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from Off-Drawer memory" }, { + "Unit": "CPU-M-CF", "EventCode": "173", "EventName": "L1I_OFFDRAWER_L3_SOURCED_WRITES_IV", "BriefDescription": "L1I Off-Drawer L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "174", "EventName": "L1I_ONDRAWER_L4_SOURCED_WRITES", "BriefDescription": "L1I On-Drawer L4 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Drawer Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "175", "EventName": "L1I_OFFDRAWER_L4_SOURCED_WRITES", "BriefDescription": "L1I Off-Drawer L4 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from Off-Drawer Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "224", "EventName": "BCD_DFP_EXECUTION_SLOTS", "BriefDescription": "BCD DFP Execution Slots", "PublicDescription": "Count of floating point execution slots used for finished Binary Coded Decimal to Decimal Floating Point conversions. Instructions: CDZT, CXZT, CZDT, CZXT" }, { + "Unit": "CPU-M-CF", "EventCode": "225", "EventName": "VX_BCD_EXECUTION_SLOTS", "BriefDescription": "VX BCD Execution Slots", "PublicDescription": "Count of floating point execution slots used for finished vector arithmetic Binary Coded Decimal instructions. Instructions: VAP, VSP, VMPVMSP, VDP, VSDP, VRP, VLIP, VSRP, VPSOPVCP, VTP, VPKZ, VUPKZ, VCVB, VCVBG, VCVDVCVDG" }, { + "Unit": "CPU-M-CF", "EventCode": "226", "EventName": "DECIMAL_INSTRUCTIONS", "BriefDescription": "Decimal Instructions", "PublicDescription": "Decimal instructions dispatched. Instructions: CVB, CVD, AP, CP, DP, ED, EDMK, MP, SRP, SP, ZAP" }, { + "Unit": "CPU-M-CF", "EventCode": "232", "EventName": "LAST_HOST_TRANSLATIONS", "BriefDescription": "Last host translation done", "PublicDescription": "Last Host Translation done" }, { + "Unit": "CPU-M-CF", "EventCode": "243", "EventName": "TX_NC_TABORT", "BriefDescription": "Aborted transactions in non-constrained TX mode", "PublicDescription": "A transaction abort has occurred in a non-constrained transactional-execution mode" }, { + "Unit": "CPU-M-CF", "EventCode": "244", "EventName": "TX_C_TABORT_NO_SPECIAL", "BriefDescription": "Aborted transactions in constrained TX mode not using special completion logic", "PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is not using any special logic to allow the transaction to complete" }, { + "Unit": "CPU-M-CF", "EventCode": "245", "EventName": "TX_C_TABORT_SPECIAL", "BriefDescription": "Aborted transactions in constrained TX mode using special completion logic", "PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is using special logic to allow the transaction to complete" }, { + "Unit": "CPU-M-CF", "EventCode": "448", "EventName": "MT_DIAG_CYCLES_ONE_THR_ACTIVE", "BriefDescription": "Cycle count with one thread active", "PublicDescription": "Cycle count with one thread active" }, { + "Unit": "CPU-M-CF", "EventCode": "449", "EventName": "MT_DIAG_CYCLES_TWO_THR_ACTIVE", "BriefDescription": "Cycle count with two threads active", diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/transaction.json b/tools/perf/pmu-events/arch/s390/cf_z14/transaction.json new file mode 100644 index 000000000000..1a0034f79f73 --- /dev/null +++ b/tools/perf/pmu-events/arch/s390/cf_z14/transaction.json @@ -0,0 +1,7 @@ +[ + { + "BriefDescription": "Transaction count", + "MetricName": "transaction", + "MetricExpr": "TX_C_TEND + TX_NC_TEND + TX_NC_TABORT + TX_C_TABORT_SPECIAL + TX_C_TABORT_NO_SPECIAL" + } +] diff --git a/tools/perf/pmu-events/arch/s390/cf_z196/basic.json b/tools/perf/pmu-events/arch/s390/cf_z196/basic.json index 8bf16759ca53..2dd8dafff2ef 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z196/basic.json +++ b/tools/perf/pmu-events/arch/s390/cf_z196/basic.json @@ -1,71 +1,83 @@ [ { + "Unit": "CPU-M-CF", "EventCode": "0", "EventName": "CPU_CYCLES", "BriefDescription": "CPU Cycles", "PublicDescription": "Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "1", "EventName": "INSTRUCTIONS", "BriefDescription": "Instructions", "PublicDescription": "Instruction Count" }, { + "Unit": "CPU-M-CF", "EventCode": "2", "EventName": "L1I_DIR_WRITES", "BriefDescription": "L1I Directory Writes", "PublicDescription": "Level-1 I-Cache Directory Write Count" }, { + "Unit": "CPU-M-CF", "EventCode": "3", "EventName": "L1I_PENALTY_CYCLES", "BriefDescription": "L1I Penalty Cycles", "PublicDescription": "Level-1 I-Cache Penalty Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "4", "EventName": "L1D_DIR_WRITES", "BriefDescription": "L1D Directory Writes", "PublicDescription": "Level-1 D-Cache Directory Write Count" }, { + "Unit": "CPU-M-CF", "EventCode": "5", "EventName": "L1D_PENALTY_CYCLES", "BriefDescription": "L1D Penalty Cycles", "PublicDescription": "Level-1 D-Cache Penalty Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "32", "EventName": "PROBLEM_STATE_CPU_CYCLES", "BriefDescription": "Problem-State CPU Cycles", "PublicDescription": "Problem-State Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "33", "EventName": "PROBLEM_STATE_INSTRUCTIONS", "BriefDescription": "Problem-State Instructions", "PublicDescription": "Problem-State Instruction Count" }, { + "Unit": "CPU-M-CF", "EventCode": "34", "EventName": "PROBLEM_STATE_L1I_DIR_WRITES", "BriefDescription": "Problem-State L1I Directory Writes", "PublicDescription": "Problem-State Level-1 I-Cache Directory Write Count" }, { + "Unit": "CPU-M-CF", "EventCode": "35", "EventName": "PROBLEM_STATE_L1I_PENALTY_CYCLES", "BriefDescription": "Problem-State L1I Penalty Cycles", "PublicDescription": "Problem-State Level-1 I-Cache Penalty Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "36", "EventName": "PROBLEM_STATE_L1D_DIR_WRITES", "BriefDescription": "Problem-State L1D Directory Writes", "PublicDescription": "Problem-State Level-1 D-Cache Directory Write Count" }, { + "Unit": "CPU-M-CF", "EventCode": "37", "EventName": "PROBLEM_STATE_L1D_PENALTY_CYCLES", "BriefDescription": "Problem-State L1D Penalty Cycles", diff --git a/tools/perf/pmu-events/arch/s390/cf_z196/crypto.json b/tools/perf/pmu-events/arch/s390/cf_z196/crypto.json index 7e5b72492141..db286f19e7b6 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z196/crypto.json +++ b/tools/perf/pmu-events/arch/s390/cf_z196/crypto.json @@ -1,95 +1,111 @@ [ { + "Unit": "CPU-M-CF", "EventCode": "64", "EventName": "PRNG_FUNCTIONS", "BriefDescription": "PRNG Functions", "PublicDescription": "Total number of the PRNG functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "65", "EventName": "PRNG_CYCLES", "BriefDescription": "PRNG Cycles", "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "66", "EventName": "PRNG_BLOCKED_FUNCTIONS", "BriefDescription": "PRNG Blocked Functions", "PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "67", "EventName": "PRNG_BLOCKED_CYCLES", "BriefDescription": "PRNG Blocked Cycles", "PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "68", "EventName": "SHA_FUNCTIONS", "BriefDescription": "SHA Functions", "PublicDescription": "Total number of SHA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "69", "EventName": "SHA_CYCLES", "BriefDescription": "SHA Cycles", "PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "70", "EventName": "SHA_BLOCKED_FUNCTIONS", "BriefDescription": "SHA Blocked Functions", "PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "71", "EventName": "SHA_BLOCKED_CYCLES", "BriefDescription": "SHA Bloced Cycles", "PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "72", "EventName": "DEA_FUNCTIONS", "BriefDescription": "DEA Functions", "PublicDescription": "Total number of the DEA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "73", "EventName": "DEA_CYCLES", "BriefDescription": "DEA Cycles", "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "74", "EventName": "DEA_BLOCKED_FUNCTIONS", "BriefDescription": "DEA Blocked Functions", "PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "75", "EventName": "DEA_BLOCKED_CYCLES", "BriefDescription": "DEA Blocked Cycles", "PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "76", "EventName": "AES_FUNCTIONS", "BriefDescription": "AES Functions", "PublicDescription": "Total number of AES functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "77", "EventName": "AES_CYCLES", "BriefDescription": "AES Cycles", "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "78", "EventName": "AES_BLOCKED_FUNCTIONS", "BriefDescription": "AES Blocked Functions", "PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "79", "EventName": "AES_BLOCKED_CYCLES", "BriefDescription": "AES Blocked Cycles", diff --git a/tools/perf/pmu-events/arch/s390/cf_z196/extended.json b/tools/perf/pmu-events/arch/s390/cf_z196/extended.json index b6d7fec7c2e7..b7b42a870bb0 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z196/extended.json +++ b/tools/perf/pmu-events/arch/s390/cf_z196/extended.json @@ -1,143 +1,167 @@ [ { + "Unit": "CPU-M-CF", "EventCode": "128", "EventName": "L1D_L2_SOURCED_WRITES", "BriefDescription": "L1D L2 Sourced Writes", "PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from the Level-2 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "129", "EventName": "L1I_L2_SOURCED_WRITES", "BriefDescription": "L1I L2 Sourced Writes", "PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from the Level-2 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "130", "EventName": "DTLB1_MISSES", "BriefDescription": "DTLB1 Misses", "PublicDescription": "Level-1 Data TLB miss in progress. Incremented by one for every cycle a DTLB1 miss is in progress." }, { + "Unit": "CPU-M-CF", "EventCode": "131", "EventName": "ITLB1_MISSES", "BriefDescription": "ITLB1 Misses", "PublicDescription": "Level-1 Instruction TLB miss in progress. Incremented by one for every cycle a ITLB1 miss is in progress." }, { + "Unit": "CPU-M-CF", "EventCode": "133", "EventName": "L2C_STORES_SENT", "BriefDescription": "L2C Stores Sent", "PublicDescription": "Incremented by one for every store sent to Level-2 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "134", "EventName": "L1D_OFFBOOK_L3_SOURCED_WRITES", "BriefDescription": "L1D Off-Book L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an Off Book Level-3 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "135", "EventName": "L1D_ONBOOK_L4_SOURCED_WRITES", "BriefDescription": "L1D On-Book L4 Sourced Writes", "PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an On Book Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "136", "EventName": "L1I_ONBOOK_L4_SOURCED_WRITES", "BriefDescription": "L1I On-Book L4 Sourced Writes", "PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from an On Book Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "137", "EventName": "L1D_RO_EXCL_WRITES", "BriefDescription": "L1D Read-only Exclusive Writes", "PublicDescription": "A directory write to the Level-1 D-Cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line" }, { + "Unit": "CPU-M-CF", "EventCode": "138", "EventName": "L1D_OFFBOOK_L4_SOURCED_WRITES", "BriefDescription": "L1D Off-Book L4 Sourced Writes", "PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an Off Book Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "139", "EventName": "L1I_OFFBOOK_L4_SOURCED_WRITES", "BriefDescription": "L1I Off-Book L4 Sourced Writes", "PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from an Off Book Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "140", "EventName": "DTLB1_HPAGE_WRITES", "BriefDescription": "DTLB1 One-Megabyte Page Writes", "PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer for a one-megabyte page" }, { + "Unit": "CPU-M-CF", "EventCode": "141", "EventName": "L1D_LMEM_SOURCED_WRITES", "BriefDescription": "L1D Local Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 D-Cache where the installed cache line was sourced from memory that is attached to the same book as the Data cache (Local Memory)" }, { + "Unit": "CPU-M-CF", "EventCode": "142", "EventName": "L1I_LMEM_SOURCED_WRITES", "BriefDescription": "L1I Local Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 I-Cache where the installed cache line was sourced from memory that is attached to the same book as the Instruction cache (Local Memory)" }, { + "Unit": "CPU-M-CF", "EventCode": "143", "EventName": "L1I_OFFBOOK_L3_SOURCED_WRITES", "BriefDescription": "L1I Off-Book L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from an Off Book Level-3 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "144", "EventName": "DTLB1_WRITES", "BriefDescription": "DTLB1 Writes", "PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer" }, { + "Unit": "CPU-M-CF", "EventCode": "145", "EventName": "ITLB1_WRITES", "BriefDescription": "ITLB1 Writes", "PublicDescription": "A translation entry has been written to the Level-1 Instruction Translation Lookaside Buffer" }, { + "Unit": "CPU-M-CF", "EventCode": "146", "EventName": "TLB2_PTE_WRITES", "BriefDescription": "TLB2 PTE Writes", "PublicDescription": "A translation entry has been written to the Level-2 TLB Page Table Entry arrays" }, { + "Unit": "CPU-M-CF", "EventCode": "147", "EventName": "TLB2_CRSTE_HPAGE_WRITES", "BriefDescription": "TLB2 CRSTE One-Megabyte Page Writes", "PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays for a one-megabyte large page translation" }, { + "Unit": "CPU-M-CF", "EventCode": "148", "EventName": "TLB2_CRSTE_WRITES", "BriefDescription": "TLB2 CRSTE Writes", "PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays" }, { + "Unit": "CPU-M-CF", "EventCode": "150", "EventName": "L1D_ONCHIP_L3_SOURCED_WRITES", "BriefDescription": "L1D On-Chip L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an On Chip Level-3 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "152", "EventName": "L1D_OFFCHIP_L3_SOURCED_WRITES", "BriefDescription": "L1D Off-Chip L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "153", "EventName": "L1I_ONCHIP_L3_SOURCED_WRITES", "BriefDescription": "L1I On-Chip L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from an On Chip Level-3 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "155", "EventName": "L1I_OFFCHIP_L3_SOURCED_WRITES", "BriefDescription": "L1I Off-Chip L3 Sourced Writes", diff --git a/tools/perf/pmu-events/arch/s390/cf_zec12/basic.json b/tools/perf/pmu-events/arch/s390/cf_zec12/basic.json index 8bf16759ca53..2dd8dafff2ef 100644 --- a/tools/perf/pmu-events/arch/s390/cf_zec12/basic.json +++ b/tools/perf/pmu-events/arch/s390/cf_zec12/basic.json @@ -1,71 +1,83 @@ [ { + "Unit": "CPU-M-CF", "EventCode": "0", "EventName": "CPU_CYCLES", "BriefDescription": "CPU Cycles", "PublicDescription": "Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "1", "EventName": "INSTRUCTIONS", "BriefDescription": "Instructions", "PublicDescription": "Instruction Count" }, { + "Unit": "CPU-M-CF", "EventCode": "2", "EventName": "L1I_DIR_WRITES", "BriefDescription": "L1I Directory Writes", "PublicDescription": "Level-1 I-Cache Directory Write Count" }, { + "Unit": "CPU-M-CF", "EventCode": "3", "EventName": "L1I_PENALTY_CYCLES", "BriefDescription": "L1I Penalty Cycles", "PublicDescription": "Level-1 I-Cache Penalty Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "4", "EventName": "L1D_DIR_WRITES", "BriefDescription": "L1D Directory Writes", "PublicDescription": "Level-1 D-Cache Directory Write Count" }, { + "Unit": "CPU-M-CF", "EventCode": "5", "EventName": "L1D_PENALTY_CYCLES", "BriefDescription": "L1D Penalty Cycles", "PublicDescription": "Level-1 D-Cache Penalty Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "32", "EventName": "PROBLEM_STATE_CPU_CYCLES", "BriefDescription": "Problem-State CPU Cycles", "PublicDescription": "Problem-State Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "33", "EventName": "PROBLEM_STATE_INSTRUCTIONS", "BriefDescription": "Problem-State Instructions", "PublicDescription": "Problem-State Instruction Count" }, { + "Unit": "CPU-M-CF", "EventCode": "34", "EventName": "PROBLEM_STATE_L1I_DIR_WRITES", "BriefDescription": "Problem-State L1I Directory Writes", "PublicDescription": "Problem-State Level-1 I-Cache Directory Write Count" }, { + "Unit": "CPU-M-CF", "EventCode": "35", "EventName": "PROBLEM_STATE_L1I_PENALTY_CYCLES", "BriefDescription": "Problem-State L1I Penalty Cycles", "PublicDescription": "Problem-State Level-1 I-Cache Penalty Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "36", "EventName": "PROBLEM_STATE_L1D_DIR_WRITES", "BriefDescription": "Problem-State L1D Directory Writes", "PublicDescription": "Problem-State Level-1 D-Cache Directory Write Count" }, { + "Unit": "CPU-M-CF", "EventCode": "37", "EventName": "PROBLEM_STATE_L1D_PENALTY_CYCLES", "BriefDescription": "Problem-State L1D Penalty Cycles", diff --git a/tools/perf/pmu-events/arch/s390/cf_zec12/crypto.json b/tools/perf/pmu-events/arch/s390/cf_zec12/crypto.json index 7e5b72492141..db286f19e7b6 100644 --- a/tools/perf/pmu-events/arch/s390/cf_zec12/crypto.json +++ b/tools/perf/pmu-events/arch/s390/cf_zec12/crypto.json @@ -1,95 +1,111 @@ [ { + "Unit": "CPU-M-CF", "EventCode": "64", "EventName": "PRNG_FUNCTIONS", "BriefDescription": "PRNG Functions", "PublicDescription": "Total number of the PRNG functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "65", "EventName": "PRNG_CYCLES", "BriefDescription": "PRNG Cycles", "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "66", "EventName": "PRNG_BLOCKED_FUNCTIONS", "BriefDescription": "PRNG Blocked Functions", "PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "67", "EventName": "PRNG_BLOCKED_CYCLES", "BriefDescription": "PRNG Blocked Cycles", "PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "68", "EventName": "SHA_FUNCTIONS", "BriefDescription": "SHA Functions", "PublicDescription": "Total number of SHA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "69", "EventName": "SHA_CYCLES", "BriefDescription": "SHA Cycles", "PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "70", "EventName": "SHA_BLOCKED_FUNCTIONS", "BriefDescription": "SHA Blocked Functions", "PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "71", "EventName": "SHA_BLOCKED_CYCLES", "BriefDescription": "SHA Bloced Cycles", "PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "72", "EventName": "DEA_FUNCTIONS", "BriefDescription": "DEA Functions", "PublicDescription": "Total number of the DEA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "73", "EventName": "DEA_CYCLES", "BriefDescription": "DEA Cycles", "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "74", "EventName": "DEA_BLOCKED_FUNCTIONS", "BriefDescription": "DEA Blocked Functions", "PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "75", "EventName": "DEA_BLOCKED_CYCLES", "BriefDescription": "DEA Blocked Cycles", "PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "76", "EventName": "AES_FUNCTIONS", "BriefDescription": "AES Functions", "PublicDescription": "Total number of AES functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "77", "EventName": "AES_CYCLES", "BriefDescription": "AES Cycles", "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "78", "EventName": "AES_BLOCKED_FUNCTIONS", "BriefDescription": "AES Blocked Functions", "PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "79", "EventName": "AES_BLOCKED_CYCLES", "BriefDescription": "AES Blocked Cycles", diff --git a/tools/perf/pmu-events/arch/s390/cf_zec12/extended.json b/tools/perf/pmu-events/arch/s390/cf_zec12/extended.json index 8682126aabb2..162251037219 100644 --- a/tools/perf/pmu-events/arch/s390/cf_zec12/extended.json +++ b/tools/perf/pmu-events/arch/s390/cf_zec12/extended.json @@ -1,209 +1,244 @@ [ { + "Unit": "CPU-M-CF", "EventCode": "128", "EventName": "DTLB1_MISSES", "BriefDescription": "DTLB1 Misses", "PublicDescription": "Level-1 Data TLB miss in progress. Incremented by one for every cycle a DTLB1 miss is in progress." }, { + "Unit": "CPU-M-CF", "EventCode": "129", "EventName": "ITLB1_MISSES", "BriefDescription": "ITLB1 Misses", "PublicDescription": "Level-1 Instruction TLB miss in progress. Incremented by one for every cycle a ITLB1 miss is in progress." }, { + "Unit": "CPU-M-CF", "EventCode": "130", "EventName": "L1D_L2I_SOURCED_WRITES", "BriefDescription": "L1D L2I Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from the Level-2 Instruction cache" }, { + "Unit": "CPU-M-CF", "EventCode": "131", "EventName": "L1I_L2I_SOURCED_WRITES", "BriefDescription": "L1I L2I Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from the Level-2 Instruction cache" }, { + "Unit": "CPU-M-CF", "EventCode": "132", "EventName": "L1D_L2D_SOURCED_WRITES", "BriefDescription": "L1D L2D Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from the Level-2 Data cache" }, { + "Unit": "CPU-M-CF", "EventCode": "133", "EventName": "DTLB1_WRITES", "BriefDescription": "DTLB1 Writes", "PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer" }, { + "Unit": "CPU-M-CF", "EventCode": "135", "EventName": "L1D_LMEM_SOURCED_WRITES", "BriefDescription": "L1D Local Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache where the installed cache line was sourced from memory that is attached to the same book as the Data cache (Local Memory)" }, { + "Unit": "CPU-M-CF", "EventCode": "137", "EventName": "L1I_LMEM_SOURCED_WRITES", "BriefDescription": "L1I Local Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache where the installed cache line was sourced from memory that is attached to the same book as the Instruction cache (Local Memory)" }, { + "Unit": "CPU-M-CF", "EventCode": "138", "EventName": "L1D_RO_EXCL_WRITES", "BriefDescription": "L1D Read-only Exclusive Writes", "PublicDescription": "A directory write to the Level-1 D-Cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line" }, { + "Unit": "CPU-M-CF", "EventCode": "139", "EventName": "DTLB1_HPAGE_WRITES", "BriefDescription": "DTLB1 One-Megabyte Page Writes", "PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer for a one-megabyte page" }, { + "Unit": "CPU-M-CF", "EventCode": "140", "EventName": "ITLB1_WRITES", "BriefDescription": "ITLB1 Writes", "PublicDescription": "A translation entry has been written to the Level-1 Instruction Translation Lookaside Buffer" }, { + "Unit": "CPU-M-CF", "EventCode": "141", "EventName": "TLB2_PTE_WRITES", "BriefDescription": "TLB2 PTE Writes", "PublicDescription": "A translation entry has been written to the Level-2 TLB Page Table Entry arrays" }, { + "Unit": "CPU-M-CF", "EventCode": "142", "EventName": "TLB2_CRSTE_HPAGE_WRITES", "BriefDescription": "TLB2 CRSTE One-Megabyte Page Writes", "PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays for a one-megabyte large page translation" }, { + "Unit": "CPU-M-CF", "EventCode": "143", "EventName": "TLB2_CRSTE_WRITES", "BriefDescription": "TLB2 CRSTE Writes", "PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays" }, { + "Unit": "CPU-M-CF", "EventCode": "144", "EventName": "L1D_ONCHIP_L3_SOURCED_WRITES", "BriefDescription": "L1D On-Chip L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On Chip Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "145", "EventName": "L1D_OFFCHIP_L3_SOURCED_WRITES", "BriefDescription": "L1D Off-Chip L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "146", "EventName": "L1D_OFFBOOK_L3_SOURCED_WRITES", "BriefDescription": "L1D Off-Book L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Book Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "147", "EventName": "L1D_ONBOOK_L4_SOURCED_WRITES", "BriefDescription": "L1D On-Book L4 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On Book Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "148", "EventName": "L1D_OFFBOOK_L4_SOURCED_WRITES", "BriefDescription": "L1D Off-Book L4 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Book Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "149", "EventName": "TX_NC_TEND", "BriefDescription": "Completed TEND instructions in non-constrained TX mode", "PublicDescription": "A TEND instruction has completed in a nonconstrained transactional-execution mode" }, { + "Unit": "CPU-M-CF", "EventCode": "150", "EventName": "L1D_ONCHIP_L3_SOURCED_WRITES_IV", "BriefDescription": "L1D On-Chip L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from a On Chip Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "151", "EventName": "L1D_OFFCHIP_L3_SOURCED_WRITES_IV", "BriefDescription": "L1D Off-Chip L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "152", "EventName": "L1D_OFFBOOK_L3_SOURCED_WRITES_IV", "BriefDescription": "L1D Off-Book L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Book Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "153", "EventName": "L1I_ONCHIP_L3_SOURCED_WRITES", "BriefDescription": "L1I On-Chip L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On Chip Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "154", "EventName": "L1I_OFFCHIP_L3_SOURCED_WRITES", "BriefDescription": "L1I Off-Chip L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "155", "EventName": "L1I_OFFBOOK_L3_SOURCED_WRITES", "BriefDescription": "L1I Off-Book L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Book Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "156", "EventName": "L1I_ONBOOK_L4_SOURCED_WRITES", "BriefDescription": "L1I On-Book L4 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On Book Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "157", "EventName": "L1I_OFFBOOK_L4_SOURCED_WRITES", "BriefDescription": "L1I Off-Book L4 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Book Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "158", "EventName": "TX_C_TEND", "BriefDescription": "Completed TEND instructions in constrained TX mode", "PublicDescription": "A TEND instruction has completed in a constrained transactional-execution mode" }, { + "Unit": "CPU-M-CF", "EventCode": "159", "EventName": "L1I_ONCHIP_L3_SOURCED_WRITES_IV", "BriefDescription": "L1I On-Chip L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On Chip Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "160", "EventName": "L1I_OFFCHIP_L3_SOURCED_WRITES_IV", "BriefDescription": "L1I Off-Chip L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "161", "EventName": "L1I_OFFBOOK_L3_SOURCED_WRITES_IV", "BriefDescription": "L1I Off-Book L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Book Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "177", "EventName": "TX_NC_TABORT", "BriefDescription": "Aborted transactions in non-constrained TX mode", "PublicDescription": "A transaction abort has occurred in a nonconstrained transactional-execution mode" }, { + "Unit": "CPU-M-CF", "EventCode": "178", "EventName": "TX_C_TABORT_NO_SPECIAL", "BriefDescription": "Aborted transactions in constrained TX mode not using special completion logic", "PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is not using any special logic to allow the transaction to complete" }, { + "Unit": "CPU-M-CF", "EventCode": "179", "EventName": "TX_C_TABORT_SPECIAL", "BriefDescription": "Aborted transactions in constrained TX mode using special completion logic", diff --git a/tools/perf/pmu-events/arch/s390/cf_zec12/transaction.json b/tools/perf/pmu-events/arch/s390/cf_zec12/transaction.json new file mode 100644 index 000000000000..1a0034f79f73 --- /dev/null +++ b/tools/perf/pmu-events/arch/s390/cf_zec12/transaction.json @@ -0,0 +1,7 @@ +[ + { + "BriefDescription": "Transaction count", + "MetricName": "transaction", + "MetricExpr": "TX_C_TEND + TX_NC_TEND + TX_NC_TABORT + TX_C_TABORT_SPECIAL + TX_C_TABORT_NO_SPECIAL" + } +] diff --git a/tools/perf/pmu-events/arch/x86/ivytown/uncore-power.json b/tools/perf/pmu-events/arch/x86/ivytown/uncore-power.json index d40498f2cb1e..635c09fda1d9 100644 --- a/tools/perf/pmu-events/arch/x86/ivytown/uncore-power.json +++ b/tools/perf/pmu-events/arch/x86/ivytown/uncore-power.json @@ -188,7 +188,7 @@ "Counter": "0,1,2,3", "EventCode": "0xb", "EventName": "UNC_P_FREQ_GE_1200MHZ_CYCLES", - "Filter": "filter_band0=1200", + "Filter": "filter_band0=12", "MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", "MetricName": "freq_ge_1200mhz_cycles %", "PerPkg": "1", @@ -199,7 +199,7 @@ "Counter": "0,1,2,3", "EventCode": "0xc", "EventName": "UNC_P_FREQ_GE_2000MHZ_CYCLES", - "Filter": "filter_band1=2000", + "Filter": "filter_band1=20", "MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", "MetricName": "freq_ge_2000mhz_cycles %", "PerPkg": "1", @@ -210,7 +210,7 @@ "Counter": "0,1,2,3", "EventCode": "0xd", "EventName": "UNC_P_FREQ_GE_3000MHZ_CYCLES", - "Filter": "filter_band2=3000", + "Filter": "filter_band2=30", "MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", "MetricName": "freq_ge_3000mhz_cycles %", "PerPkg": "1", @@ -221,7 +221,7 @@ "Counter": "0,1,2,3", "EventCode": "0xe", "EventName": "UNC_P_FREQ_GE_4000MHZ_CYCLES", - "Filter": "filter_band3=4000", + "Filter": "filter_band3=40", "MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", "MetricName": "freq_ge_4000mhz_cycles %", "PerPkg": "1", @@ -232,7 +232,7 @@ "Counter": "0,1,2,3", "EventCode": "0xb", "EventName": "UNC_P_FREQ_GE_1200MHZ_TRANSITIONS", - "Filter": "edge=1,filter_band0=1200", + "Filter": "edge=1,filter_band0=12", "MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", "MetricName": "freq_ge_1200mhz_cycles %", "PerPkg": "1", @@ -243,7 +243,7 @@ "Counter": "0,1,2,3", "EventCode": "0xc", "EventName": "UNC_P_FREQ_GE_2000MHZ_TRANSITIONS", - "Filter": "edge=1,filter_band1=2000", + "Filter": "edge=1,filter_band1=20", "MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", "MetricName": "freq_ge_2000mhz_cycles %", "PerPkg": "1", @@ -254,7 +254,7 @@ "Counter": "0,1,2,3", "EventCode": "0xd", "EventName": "UNC_P_FREQ_GE_3000MHZ_TRANSITIONS", - "Filter": "edge=1,filter_band2=4000", + "Filter": "edge=1,filter_band2=30", "MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", "MetricName": "freq_ge_3000mhz_cycles %", "PerPkg": "1", @@ -265,7 +265,7 @@ "Counter": "0,1,2,3", "EventCode": "0xe", "EventName": "UNC_P_FREQ_GE_4000MHZ_TRANSITIONS", - "Filter": "edge=1,filter_band3=4000", + "Filter": "edge=1,filter_band3=40", "MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", "MetricName": "freq_ge_4000mhz_cycles %", "PerPkg": "1", diff --git a/tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json b/tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json index 16034bfd06dd..8755693d86c6 100644 --- a/tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json +++ b/tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json @@ -187,7 +187,7 @@ "Counter": "0,1,2,3", "EventCode": "0xb", "EventName": "UNC_P_FREQ_GE_1200MHZ_CYCLES", - "Filter": "filter_band0=1200", + "Filter": "filter_band0=12", "MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", "MetricName": "freq_ge_1200mhz_cycles %", "PerPkg": "1", @@ -198,7 +198,7 @@ "Counter": "0,1,2,3", "EventCode": "0xc", "EventName": "UNC_P_FREQ_GE_2000MHZ_CYCLES", - "Filter": "filter_band1=2000", + "Filter": "filter_band1=20", "MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", "MetricName": "freq_ge_2000mhz_cycles %", "PerPkg": "1", @@ -209,7 +209,7 @@ "Counter": "0,1,2,3", "EventCode": "0xd", "EventName": "UNC_P_FREQ_GE_3000MHZ_CYCLES", - "Filter": "filter_band2=3000", + "Filter": "filter_band2=30", "MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", "MetricName": "freq_ge_3000mhz_cycles %", "PerPkg": "1", @@ -220,7 +220,7 @@ "Counter": "0,1,2,3", "EventCode": "0xe", "EventName": "UNC_P_FREQ_GE_4000MHZ_CYCLES", - "Filter": "filter_band3=4000", + "Filter": "filter_band3=40", "MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", "MetricName": "freq_ge_4000mhz_cycles %", "PerPkg": "1", @@ -231,7 +231,7 @@ "Counter": "0,1,2,3", "EventCode": "0xb", "EventName": "UNC_P_FREQ_GE_1200MHZ_TRANSITIONS", - "Filter": "edge=1,filter_band0=1200", + "Filter": "edge=1,filter_band0=12", "MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", "MetricName": "freq_ge_1200mhz_cycles %", "PerPkg": "1", @@ -242,7 +242,7 @@ "Counter": "0,1,2,3", "EventCode": "0xc", "EventName": "UNC_P_FREQ_GE_2000MHZ_TRANSITIONS", - "Filter": "edge=1,filter_band1=2000", + "Filter": "edge=1,filter_band1=20", "MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", "MetricName": "freq_ge_2000mhz_cycles %", "PerPkg": "1", @@ -253,7 +253,7 @@ "Counter": "0,1,2,3", "EventCode": "0xd", "EventName": "UNC_P_FREQ_GE_3000MHZ_TRANSITIONS", - "Filter": "edge=1,filter_band2=4000", + "Filter": "edge=1,filter_band2=30", "MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", "MetricName": "freq_ge_3000mhz_cycles %", "PerPkg": "1", @@ -264,7 +264,7 @@ "Counter": "0,1,2,3", "EventCode": "0xe", "EventName": "UNC_P_FREQ_GE_4000MHZ_TRANSITIONS", - "Filter": "edge=1,filter_band3=4000", + "Filter": "edge=1,filter_band3=40", "MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", "MetricName": "freq_ge_4000mhz_cycles %", "PerPkg": "1", diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c index db3a594ee1e4..68c92bb599ee 100644 --- a/tools/perf/pmu-events/jevents.c +++ b/tools/perf/pmu-events/jevents.c @@ -233,6 +233,8 @@ static struct map { { "QPI LL", "uncore_qpi" }, { "SBO", "uncore_sbox" }, { "iMPH-U", "uncore_arb" }, + { "CPU-M-CF", "cpum_cf" }, + { "CPU-M-SF", "cpum_sf" }, {} }; diff --git a/tools/perf/scripts/python/export-to-postgresql.py b/tools/perf/scripts/python/export-to-postgresql.py index efcaf6cac2eb..e46f51b17513 100644 --- a/tools/perf/scripts/python/export-to-postgresql.py +++ b/tools/perf/scripts/python/export-to-postgresql.py @@ -204,14 +204,23 @@ from ctypes import * libpq = CDLL("libpq.so.5") PQconnectdb = libpq.PQconnectdb PQconnectdb.restype = c_void_p +PQconnectdb.argtypes = [ c_char_p ] PQfinish = libpq.PQfinish +PQfinish.argtypes = [ c_void_p ] PQstatus = libpq.PQstatus +PQstatus.restype = c_int +PQstatus.argtypes = [ c_void_p ] PQexec = libpq.PQexec PQexec.restype = c_void_p +PQexec.argtypes = [ c_void_p, c_char_p ] PQresultStatus = libpq.PQresultStatus +PQresultStatus.restype = c_int +PQresultStatus.argtypes = [ c_void_p ] PQputCopyData = libpq.PQputCopyData +PQputCopyData.restype = c_int PQputCopyData.argtypes = [ c_void_p, c_void_p, c_int ] PQputCopyEnd = libpq.PQputCopyEnd +PQputCopyEnd.restype = c_int PQputCopyEnd.argtypes = [ c_void_p, c_void_p ] sys.path.append(os.environ['PERF_EXEC_PATH'] + \ diff --git a/tools/perf/scripts/python/export-to-sqlite.py b/tools/perf/scripts/python/export-to-sqlite.py index f827bf77e9d2..e4bb82c8aba9 100644 --- a/tools/perf/scripts/python/export-to-sqlite.py +++ b/tools/perf/scripts/python/export-to-sqlite.py @@ -440,7 +440,11 @@ def branch_type_table(*x): def sample_table(*x): if branches: - bind_exec(sample_query, 18, x) + for xx in x[0:15]: + sample_query.addBindValue(str(xx)) + for xx in x[19:22]: + sample_query.addBindValue(str(xx)) + do_query_(sample_query) else: bind_exec(sample_query, 22, x) diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build index 6c108fa79ae3..0b2b8305c965 100644 --- a/tools/perf/tests/Build +++ b/tools/perf/tests/Build @@ -21,6 +21,7 @@ perf-y += python-use.o perf-y += bp_signal.o perf-y += bp_signal_overflow.o perf-y += bp_account.o +perf-y += wp.o perf-y += task-exit.o perf-y += sw-clock.o perf-y += mmap-thread-lookup.o diff --git a/tools/perf/tests/bitmap.c b/tools/perf/tests/bitmap.c index 47bedf25ba69..96e7fc1ad3f9 100644 --- a/tools/perf/tests/bitmap.c +++ b/tools/perf/tests/bitmap.c @@ -16,8 +16,6 @@ static unsigned long *get_bitmap(const char *str, int nbits) bm = bitmap_alloc(nbits); if (map && bm) { - bitmap_zero(bm, nbits); - for (i = 0; i < map->nr; i++) set_bit(map->map[i], bm); } diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c index dd850a26d579..12c09e0ece71 100644 --- a/tools/perf/tests/builtin-test.c +++ b/tools/perf/tests/builtin-test.c @@ -121,6 +121,16 @@ static struct test generic_tests[] = { .is_supported = test__bp_signal_is_supported, }, { + .desc = "Watchpoint", + .func = test__wp, + .is_supported = test__wp_is_supported, + .subtest = { + .skip_if_fail = false, + .get_nr = test__wp_subtest_get_nr, + .get_desc = test__wp_subtest_get_desc, + }, + }, + { .desc = "Number of exit events of a simple workload", .func = test__task_exit, }, @@ -385,7 +395,7 @@ static int test_and_print(struct test *t, bool force_skip, int subtest) if (!t->subtest.get_nr) pr_debug("%s:", t->desc); else - pr_debug("%s subtest %d:", t->desc, subtest); + pr_debug("%s subtest %d:", t->desc, subtest + 1); switch (err) { case TEST_OK: diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c index 4892bd2dc33e..6b049f3f5cf4 100644 --- a/tools/perf/tests/code-reading.c +++ b/tools/perf/tests/code-reading.c @@ -232,6 +232,7 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode, u64 objdump_addr; const char *objdump_name; char decomp_name[KMOD_DECOMP_LEN]; + bool decomp = false; int ret; pr_debug("Reading object code for memory address: %#"PRIx64"\n", addr); @@ -305,6 +306,7 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode, return -1; } + decomp = true; objdump_name = decomp_name; } @@ -312,7 +314,7 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode, objdump_addr = map__rip_2objdump(al.map, al.addr); ret = read_via_objdump(objdump_name, objdump_addr, buf2, len); - if (dso__needs_decompress(al.map->dso)) + if (decomp) unlink(objdump_name); if (ret > 0) { diff --git a/tools/perf/tests/evsel-tp-sched.c b/tools/perf/tests/evsel-tp-sched.c index 699561fa512c..5f8501c68da4 100644 --- a/tools/perf/tests/evsel-tp-sched.c +++ b/tools/perf/tests/evsel-tp-sched.c @@ -8,7 +8,7 @@ static int perf_evsel__test_field(struct perf_evsel *evsel, const char *name, int size, bool should_be_signed) { - struct format_field *field = perf_evsel__field(evsel, name); + struct tep_format_field *field = perf_evsel__field(evsel, name); int is_signed; int ret = 0; @@ -17,7 +17,7 @@ static int perf_evsel__test_field(struct perf_evsel *evsel, const char *name, return -1; } - is_signed = !!(field->flags | FIELD_IS_SIGNED); + is_signed = !!(field->flags | TEP_FIELD_IS_SIGNED); if (should_be_signed && !is_signed) { pr_debug("%s: \"%s\" signedness(%d) is wrong, should be %d\n", evsel->name, name, is_signed, should_be_signed); diff --git a/tools/perf/tests/kmod-path.c b/tools/perf/tests/kmod-path.c index 148dd31cc201..0579a70bbbff 100644 --- a/tools/perf/tests/kmod-path.c +++ b/tools/perf/tests/kmod-path.c @@ -5,34 +5,28 @@ #include "dso.h" #include "debug.h" -static int test(const char *path, bool alloc_name, bool alloc_ext, - bool kmod, bool comp, const char *name, const char *ext) +static int test(const char *path, bool alloc_name, bool kmod, + int comp, const char *name) { struct kmod_path m; memset(&m, 0x0, sizeof(m)); TEST_ASSERT_VAL("kmod_path__parse", - !__kmod_path__parse(&m, path, alloc_name, alloc_ext)); + !__kmod_path__parse(&m, path, alloc_name)); - pr_debug("%s - alloc name %d, alloc ext %d, kmod %d, comp %d, name '%s', ext '%s'\n", - path, alloc_name, alloc_ext, m.kmod, m.comp, m.name, m.ext); + pr_debug("%s - alloc name %d, kmod %d, comp %d, name '%s'\n", + path, alloc_name, m.kmod, m.comp, m.name); TEST_ASSERT_VAL("wrong kmod", m.kmod == kmod); TEST_ASSERT_VAL("wrong comp", m.comp == comp); - if (ext) - TEST_ASSERT_VAL("wrong ext", m.ext && !strcmp(ext, m.ext)); - else - TEST_ASSERT_VAL("wrong ext", !m.ext); - if (name) TEST_ASSERT_VAL("wrong name", m.name && !strcmp(name, m.name)); else TEST_ASSERT_VAL("wrong name", !m.name); free(m.name); - free(m.ext); return 0; } @@ -45,118 +39,118 @@ static int test_is_kernel_module(const char *path, int cpumode, bool expect) return 0; } -#define T(path, an, ae, k, c, n, e) \ - TEST_ASSERT_VAL("failed", !test(path, an, ae, k, c, n, e)) +#define T(path, an, k, c, n) \ + TEST_ASSERT_VAL("failed", !test(path, an, k, c, n)) #define M(path, c, e) \ TEST_ASSERT_VAL("failed", !test_is_kernel_module(path, c, e)) int test__kmod_path__parse(struct test *t __maybe_unused, int subtest __maybe_unused) { - /* path alloc_name alloc_ext kmod comp name ext */ - T("/xxxx/xxxx/x-x.ko", true , true , true, false, "[x_x]", NULL); - T("/xxxx/xxxx/x-x.ko", false , true , true, false, NULL , NULL); - T("/xxxx/xxxx/x-x.ko", true , false , true, false, "[x_x]", NULL); - T("/xxxx/xxxx/x-x.ko", false , false , true, false, NULL , NULL); + /* path alloc_name kmod comp name */ + T("/xxxx/xxxx/x-x.ko", true , true, 0 , "[x_x]"); + T("/xxxx/xxxx/x-x.ko", false , true, 0 , NULL ); + T("/xxxx/xxxx/x-x.ko", true , true, 0 , "[x_x]"); + T("/xxxx/xxxx/x-x.ko", false , true, 0 , NULL ); M("/xxxx/xxxx/x-x.ko", PERF_RECORD_MISC_CPUMODE_UNKNOWN, true); M("/xxxx/xxxx/x-x.ko", PERF_RECORD_MISC_KERNEL, true); M("/xxxx/xxxx/x-x.ko", PERF_RECORD_MISC_USER, false); #ifdef HAVE_ZLIB_SUPPORT - /* path alloc_name alloc_ext kmod comp name ext */ - T("/xxxx/xxxx/x.ko.gz", true , true , true, true, "[x]", "gz"); - T("/xxxx/xxxx/x.ko.gz", false , true , true, true, NULL , "gz"); - T("/xxxx/xxxx/x.ko.gz", true , false , true, true, "[x]", NULL); - T("/xxxx/xxxx/x.ko.gz", false , false , true, true, NULL , NULL); + /* path alloc_name kmod comp name */ + T("/xxxx/xxxx/x.ko.gz", true , true, 1 , "[x]"); + T("/xxxx/xxxx/x.ko.gz", false , true, 1 , NULL ); + T("/xxxx/xxxx/x.ko.gz", true , true, 1 , "[x]"); + T("/xxxx/xxxx/x.ko.gz", false , true, 1 , NULL ); M("/xxxx/xxxx/x.ko.gz", PERF_RECORD_MISC_CPUMODE_UNKNOWN, true); M("/xxxx/xxxx/x.ko.gz", PERF_RECORD_MISC_KERNEL, true); M("/xxxx/xxxx/x.ko.gz", PERF_RECORD_MISC_USER, false); - /* path alloc_name alloc_ext kmod comp name ext */ - T("/xxxx/xxxx/x.gz", true , true , false, true, "x.gz" ,"gz"); - T("/xxxx/xxxx/x.gz", false , true , false, true, NULL ,"gz"); - T("/xxxx/xxxx/x.gz", true , false , false, true, "x.gz" , NULL); - T("/xxxx/xxxx/x.gz", false , false , false, true, NULL , NULL); + /* path alloc_name kmod comp name */ + T("/xxxx/xxxx/x.gz", true , false, 1 , "x.gz"); + T("/xxxx/xxxx/x.gz", false , false, 1 , NULL ); + T("/xxxx/xxxx/x.gz", true , false, 1 , "x.gz"); + T("/xxxx/xxxx/x.gz", false , false, 1 , NULL ); M("/xxxx/xxxx/x.gz", PERF_RECORD_MISC_CPUMODE_UNKNOWN, false); M("/xxxx/xxxx/x.gz", PERF_RECORD_MISC_KERNEL, false); M("/xxxx/xxxx/x.gz", PERF_RECORD_MISC_USER, false); - /* path alloc_name alloc_ext kmod comp name ext */ - T("x.gz", true , true , false, true, "x.gz", "gz"); - T("x.gz", false , true , false, true, NULL , "gz"); - T("x.gz", true , false , false, true, "x.gz", NULL); - T("x.gz", false , false , false, true, NULL , NULL); + /* path alloc_name kmod comp name */ + T("x.gz", true , false, 1 , "x.gz"); + T("x.gz", false , false, 1 , NULL ); + T("x.gz", true , false, 1 , "x.gz"); + T("x.gz", false , false, 1 , NULL ); M("x.gz", PERF_RECORD_MISC_CPUMODE_UNKNOWN, false); M("x.gz", PERF_RECORD_MISC_KERNEL, false); M("x.gz", PERF_RECORD_MISC_USER, false); - /* path alloc_name alloc_ext kmod comp name ext */ - T("x.ko.gz", true , true , true, true, "[x]", "gz"); - T("x.ko.gz", false , true , true, true, NULL , "gz"); - T("x.ko.gz", true , false , true, true, "[x]", NULL); - T("x.ko.gz", false , false , true, true, NULL , NULL); + /* path alloc_name kmod comp name */ + T("x.ko.gz", true , true, 1 , "[x]"); + T("x.ko.gz", false , true, 1 , NULL ); + T("x.ko.gz", true , true, 1 , "[x]"); + T("x.ko.gz", false , true, 1 , NULL ); M("x.ko.gz", PERF_RECORD_MISC_CPUMODE_UNKNOWN, true); M("x.ko.gz", PERF_RECORD_MISC_KERNEL, true); M("x.ko.gz", PERF_RECORD_MISC_USER, false); #endif - /* path alloc_name alloc_ext kmod comp name ext */ - T("[test_module]", true , true , true, false, "[test_module]", NULL); - T("[test_module]", false , true , true, false, NULL , NULL); - T("[test_module]", true , false , true, false, "[test_module]", NULL); - T("[test_module]", false , false , true, false, NULL , NULL); + /* path alloc_name kmod comp name */ + T("[test_module]", true , true, false, "[test_module]"); + T("[test_module]", false , true, false, NULL ); + T("[test_module]", true , true, false, "[test_module]"); + T("[test_module]", false , true, false, NULL ); M("[test_module]", PERF_RECORD_MISC_CPUMODE_UNKNOWN, true); M("[test_module]", PERF_RECORD_MISC_KERNEL, true); M("[test_module]", PERF_RECORD_MISC_USER, false); - /* path alloc_name alloc_ext kmod comp name ext */ - T("[test.module]", true , true , true, false, "[test.module]", NULL); - T("[test.module]", false , true , true, false, NULL , NULL); - T("[test.module]", true , false , true, false, "[test.module]", NULL); - T("[test.module]", false , false , true, false, NULL , NULL); + /* path alloc_name kmod comp name */ + T("[test.module]", true , true, false, "[test.module]"); + T("[test.module]", false , true, false, NULL ); + T("[test.module]", true , true, false, "[test.module]"); + T("[test.module]", false , true, false, NULL ); M("[test.module]", PERF_RECORD_MISC_CPUMODE_UNKNOWN, true); M("[test.module]", PERF_RECORD_MISC_KERNEL, true); M("[test.module]", PERF_RECORD_MISC_USER, false); - /* path alloc_name alloc_ext kmod comp name ext */ - T("[vdso]", true , true , false, false, "[vdso]", NULL); - T("[vdso]", false , true , false, false, NULL , NULL); - T("[vdso]", true , false , false, false, "[vdso]", NULL); - T("[vdso]", false , false , false, false, NULL , NULL); + /* path alloc_name kmod comp name */ + T("[vdso]", true , false, false, "[vdso]"); + T("[vdso]", false , false, false, NULL ); + T("[vdso]", true , false, false, "[vdso]"); + T("[vdso]", false , false, false, NULL ); M("[vdso]", PERF_RECORD_MISC_CPUMODE_UNKNOWN, false); M("[vdso]", PERF_RECORD_MISC_KERNEL, false); M("[vdso]", PERF_RECORD_MISC_USER, false); - T("[vdso32]", true , true , false, false, "[vdso32]", NULL); - T("[vdso32]", false , true , false, false, NULL , NULL); - T("[vdso32]", true , false , false, false, "[vdso32]", NULL); - T("[vdso32]", false , false , false, false, NULL , NULL); + T("[vdso32]", true , false, false, "[vdso32]"); + T("[vdso32]", false , false, false, NULL ); + T("[vdso32]", true , false, false, "[vdso32]"); + T("[vdso32]", false , false, false, NULL ); M("[vdso32]", PERF_RECORD_MISC_CPUMODE_UNKNOWN, false); M("[vdso32]", PERF_RECORD_MISC_KERNEL, false); M("[vdso32]", PERF_RECORD_MISC_USER, false); - T("[vdsox32]", true , true , false, false, "[vdsox32]", NULL); - T("[vdsox32]", false , true , false, false, NULL , NULL); - T("[vdsox32]", true , false , false, false, "[vdsox32]", NULL); - T("[vdsox32]", false , false , false, false, NULL , NULL); + T("[vdsox32]", true , false, false, "[vdsox32]"); + T("[vdsox32]", false , false, false, NULL ); + T("[vdsox32]", true , false, false, "[vdsox32]"); + T("[vdsox32]", false , false, false, NULL ); M("[vdsox32]", PERF_RECORD_MISC_CPUMODE_UNKNOWN, false); M("[vdsox32]", PERF_RECORD_MISC_KERNEL, false); M("[vdsox32]", PERF_RECORD_MISC_USER, false); - /* path alloc_name alloc_ext kmod comp name ext */ - T("[vsyscall]", true , true , false, false, "[vsyscall]", NULL); - T("[vsyscall]", false , true , false, false, NULL , NULL); - T("[vsyscall]", true , false , false, false, "[vsyscall]", NULL); - T("[vsyscall]", false , false , false, false, NULL , NULL); + /* path alloc_name kmod comp name */ + T("[vsyscall]", true , false, false, "[vsyscall]"); + T("[vsyscall]", false , false, false, NULL ); + T("[vsyscall]", true , false, false, "[vsyscall]"); + T("[vsyscall]", false , false, false, NULL ); M("[vsyscall]", PERF_RECORD_MISC_CPUMODE_UNKNOWN, false); M("[vsyscall]", PERF_RECORD_MISC_KERNEL, false); M("[vsyscall]", PERF_RECORD_MISC_USER, false); - /* path alloc_name alloc_ext kmod comp name ext */ - T("[kernel.kallsyms]", true , true , false, false, "[kernel.kallsyms]", NULL); - T("[kernel.kallsyms]", false , true , false, false, NULL , NULL); - T("[kernel.kallsyms]", true , false , false, false, "[kernel.kallsyms]", NULL); - T("[kernel.kallsyms]", false , false , false, false, NULL , NULL); + /* path alloc_name kmod comp name */ + T("[kernel.kallsyms]", true , false, false, "[kernel.kallsyms]"); + T("[kernel.kallsyms]", false , false, false, NULL ); + T("[kernel.kallsyms]", true , false, false, "[kernel.kallsyms]"); + T("[kernel.kallsyms]", false , false, false, NULL ); M("[kernel.kallsyms]", PERF_RECORD_MISC_CPUMODE_UNKNOWN, false); M("[kernel.kallsyms]", PERF_RECORD_MISC_KERNEL, false); M("[kernel.kallsyms]", PERF_RECORD_MISC_USER, false); diff --git a/tools/perf/tests/mem2node.c b/tools/perf/tests/mem2node.c index 0c3c87f86e03..9e9e4d37cc77 100644 --- a/tools/perf/tests/mem2node.c +++ b/tools/perf/tests/mem2node.c @@ -24,8 +24,6 @@ static unsigned long *get_bitmap(const char *str, int nbits) bm = bitmap_alloc(nbits); if (map && bm) { - bitmap_zero(bm, nbits); - for (i = 0; i < map->nr; i++) { set_bit(map->map[i], bm); } diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c index 61211918bfba..3b97ac018d5a 100644 --- a/tools/perf/tests/parse-events.c +++ b/tools/perf/tests/parse-events.c @@ -1322,6 +1322,14 @@ static int test__intel_pt(struct perf_evlist *evlist) return 0; } +static int test__checkevent_complex_name(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel = perf_evlist__first(evlist); + + TEST_ASSERT_VAL("wrong complex name parsing", strcmp(evsel->name, "COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks") == 0); + return 0; +} + static int count_tracepoints(void) { struct dirent *events_ent; @@ -1658,6 +1666,11 @@ static struct evlist_test test__events[] = { .check = test__intel_pt, .id = 52, }, + { + .name = "cycles/name='COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks'/Duk", + .check = test__checkevent_complex_name, + .id = 53 + } }; static struct evlist_test test__events_pmu[] = { @@ -1676,6 +1689,11 @@ static struct evlist_test test__events_pmu[] = { .check = test__checkevent_pmu_partial_time_callgraph, .id = 2, }, + { + .name = "cpu/name='COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks',period=0x1,event=0x2/ukp", + .check = test__checkevent_complex_name, + .id = 3, + } }; struct terms_test { diff --git a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh index 94e513e62b34..cab7b0aea6ea 100755 --- a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh +++ b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh @@ -13,11 +13,24 @@ libc=$(grep -w libc /proc/self/maps | head -1 | sed -r 's/.*[[:space:]](\/.*)/\1/g') nm -Dg $libc 2>/dev/null | fgrep -q inet_pton || exit 254 +event_pattern='probe_libc:inet_pton(\_[[:digit:]]+)?' + +add_libc_inet_pton_event() { + + event_name=$(perf probe -f -x $libc -a inet_pton 2>&1 | tail -n +2 | head -n -5 | \ + grep -P -o "$event_pattern(?=[[:space:]]\(on inet_pton in $libc\))") + + if [ $? -ne 0 -o -z "$event_name" ] ; then + printf "FAIL: could not add event\n" + return 1 + fi +} + trace_libc_inet_pton_backtrace() { expected=`mktemp -u /tmp/expected.XXX` - echo "ping[][0-9 \.:]+probe_libc:inet_pton: \([[:xdigit:]]+\)" > $expected + echo "ping[][0-9 \.:]+$event_name: \([[:xdigit:]]+\)" > $expected echo ".*inet_pton\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected case "$(uname -m)" in s390x) @@ -26,16 +39,22 @@ trace_libc_inet_pton_backtrace() { echo "(__GI_)?getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected echo "main\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$" >> $expected ;; + ppc64|ppc64le) + eventattr='max-stack=4' + echo "gaih_inet.*\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected + echo "getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected + echo ".*\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$" >> $expected + ;; *) eventattr='max-stack=3' echo "getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected - echo ".*\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$" >> $expected + echo ".*(\+0x[[:xdigit:]]+|\[unknown\])[[:space:]]\(.*/bin/ping.*\)$" >> $expected ;; esac perf_data=`mktemp -u /tmp/perf.data.XXX` perf_script=`mktemp -u /tmp/perf.script.XXX` - perf record -e probe_libc:inet_pton/$eventattr/ -o $perf_data ping -6 -c 1 ::1 > /dev/null 2>&1 + perf record -e $event_name/$eventattr/ -o $perf_data ping -6 -c 1 ::1 > /dev/null 2>&1 perf script -i $perf_data > $perf_script exec 3<$perf_script @@ -46,7 +65,7 @@ trace_libc_inet_pton_backtrace() { echo "$line" | egrep -q "$pattern" if [ $? -ne 0 ] ; then printf "FAIL: expected backtrace entry \"%s\" got \"%s\"\n" "$pattern" "$line" - exit 1 + return 1 fi done @@ -56,13 +75,20 @@ trace_libc_inet_pton_backtrace() { # even if the perf script output does not match. } +delete_libc_inet_pton_event() { + + if [ -n "$event_name" ] ; then + perf probe -q -d $event_name + fi +} + # Check for IPv6 interface existence ip a sh lo | fgrep -q inet6 || exit 2 skip_if_no_perf_probe && \ -perf probe -q $libc inet_pton && \ +add_libc_inet_pton_event && \ trace_libc_inet_pton_backtrace err=$? rm -f ${perf_data} ${perf_script} ${expected} -perf probe -q -d probe_libc:inet_pton +delete_libc_inet_pton_event exit $err diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h index a9760e790563..b82f55fcc294 100644 --- a/tools/perf/tests/tests.h +++ b/tools/perf/tests/tests.h @@ -59,6 +59,9 @@ int test__python_use(struct test *test, int subtest); int test__bp_signal(struct test *test, int subtest); int test__bp_signal_overflow(struct test *test, int subtest); int test__bp_accounting(struct test *test, int subtest); +int test__wp(struct test *test, int subtest); +const char *test__wp_subtest_get_desc(int subtest); +int test__wp_subtest_get_nr(void); int test__task_exit(struct test *test, int subtest); int test__mem(struct test *test, int subtest); int test__sw_clock_freq(struct test *test, int subtest); @@ -106,6 +109,7 @@ int test__unit_number__scnprint(struct test *test, int subtest); int test__mem2node(struct test *t, int subtest); bool test__bp_signal_is_supported(void); +bool test__wp_is_supported(void); #if defined(__arm__) || defined(__aarch64__) #ifdef HAVE_DWARF_UNWIND_SUPPORT diff --git a/tools/perf/tests/wp.c b/tools/perf/tests/wp.c new file mode 100644 index 000000000000..f89e6806557b --- /dev/null +++ b/tools/perf/tests/wp.c @@ -0,0 +1,241 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stdlib.h> +#include <sys/ioctl.h> +#include <linux/hw_breakpoint.h> +#include "tests.h" +#include "debug.h" +#include "cloexec.h" + +#define WP_TEST_ASSERT_VAL(fd, text, val) \ +do { \ + long long count; \ + wp_read(fd, &count, sizeof(long long)); \ + TEST_ASSERT_VAL(text, count == val); \ +} while (0) + +volatile u64 data1; +volatile u8 data2[3]; + +static int wp_read(int fd, long long *count, int size) +{ + int ret = read(fd, count, size); + + if (ret != size) { + pr_debug("failed to read: %d\n", ret); + return -1; + } + return 0; +} + +static void get__perf_event_attr(struct perf_event_attr *attr, int wp_type, + void *wp_addr, unsigned long wp_len) +{ + memset(attr, 0, sizeof(struct perf_event_attr)); + attr->type = PERF_TYPE_BREAKPOINT; + attr->size = sizeof(struct perf_event_attr); + attr->config = 0; + attr->bp_type = wp_type; + attr->bp_addr = (unsigned long)wp_addr; + attr->bp_len = wp_len; + attr->sample_period = 1; + attr->sample_type = PERF_SAMPLE_IP; + attr->exclude_kernel = 1; + attr->exclude_hv = 1; +} + +static int __event(int wp_type, void *wp_addr, unsigned long wp_len) +{ + int fd; + struct perf_event_attr attr; + + get__perf_event_attr(&attr, wp_type, wp_addr, wp_len); + fd = sys_perf_event_open(&attr, 0, -1, -1, + perf_event_open_cloexec_flag()); + if (fd < 0) + pr_debug("failed opening event %x\n", attr.bp_type); + + return fd; +} + +static int wp_ro_test(void) +{ + int fd; + unsigned long tmp, tmp1 = rand(); + + fd = __event(HW_BREAKPOINT_R, (void *)&data1, sizeof(data1)); + if (fd < 0) + return -1; + + tmp = data1; + WP_TEST_ASSERT_VAL(fd, "RO watchpoint", 1); + + data1 = tmp1 + tmp; + WP_TEST_ASSERT_VAL(fd, "RO watchpoint", 1); + + close(fd); + return 0; +} + +static int wp_wo_test(void) +{ + int fd; + unsigned long tmp, tmp1 = rand(); + + fd = __event(HW_BREAKPOINT_W, (void *)&data1, sizeof(data1)); + if (fd < 0) + return -1; + + tmp = data1; + WP_TEST_ASSERT_VAL(fd, "WO watchpoint", 0); + + data1 = tmp1 + tmp; + WP_TEST_ASSERT_VAL(fd, "WO watchpoint", 1); + + close(fd); + return 0; +} + +static int wp_rw_test(void) +{ + int fd; + unsigned long tmp, tmp1 = rand(); + + fd = __event(HW_BREAKPOINT_R | HW_BREAKPOINT_W, (void *)&data1, + sizeof(data1)); + if (fd < 0) + return -1; + + tmp = data1; + WP_TEST_ASSERT_VAL(fd, "RW watchpoint", 1); + + data1 = tmp1 + tmp; + WP_TEST_ASSERT_VAL(fd, "RW watchpoint", 2); + + close(fd); + return 0; +} + +static int wp_modify_test(void) +{ + int fd, ret; + unsigned long tmp = rand(); + struct perf_event_attr new_attr; + + fd = __event(HW_BREAKPOINT_W, (void *)&data1, sizeof(data1)); + if (fd < 0) + return -1; + + data1 = tmp; + WP_TEST_ASSERT_VAL(fd, "Modify watchpoint", 1); + + /* Modify watchpoint with disabled = 1 */ + get__perf_event_attr(&new_attr, HW_BREAKPOINT_W, (void *)&data2[0], + sizeof(u8) * 2); + new_attr.disabled = 1; + ret = ioctl(fd, PERF_EVENT_IOC_MODIFY_ATTRIBUTES, &new_attr); + if (ret < 0) { + pr_debug("ioctl(PERF_EVENT_IOC_MODIFY_ATTRIBUTES) failed\n"); + close(fd); + return ret; + } + + data2[1] = tmp; /* Not Counted */ + WP_TEST_ASSERT_VAL(fd, "Modify watchpoint", 1); + + /* Enable the event */ + ioctl(fd, PERF_EVENT_IOC_ENABLE, 0); + if (ret < 0) { + pr_debug("Failed to enable event\n"); + close(fd); + return ret; + } + + data2[1] = tmp; /* Counted */ + WP_TEST_ASSERT_VAL(fd, "Modify watchpoint", 2); + + data2[2] = tmp; /* Not Counted */ + WP_TEST_ASSERT_VAL(fd, "Modify watchpoint", 2); + + close(fd); + return 0; +} + +static bool wp_ro_supported(void) +{ +#if defined (__x86_64__) || defined (__i386__) + return false; +#else + return true; +#endif +} + +static void wp_ro_skip_msg(void) +{ +#if defined (__x86_64__) || defined (__i386__) + pr_debug("Hardware does not support read only watchpoints.\n"); +#endif +} + +static struct { + const char *desc; + int (*target_func)(void); + bool (*is_supported)(void); + void (*skip_msg)(void); +} wp_testcase_table[] = { + { + .desc = "Read Only Watchpoint", + .target_func = &wp_ro_test, + .is_supported = &wp_ro_supported, + .skip_msg = &wp_ro_skip_msg, + }, + { + .desc = "Write Only Watchpoint", + .target_func = &wp_wo_test, + }, + { + .desc = "Read / Write Watchpoint", + .target_func = &wp_rw_test, + }, + { + .desc = "Modify Watchpoint", + .target_func = &wp_modify_test, + }, +}; + +int test__wp_subtest_get_nr(void) +{ + return (int)ARRAY_SIZE(wp_testcase_table); +} + +const char *test__wp_subtest_get_desc(int i) +{ + if (i < 0 || i >= (int)ARRAY_SIZE(wp_testcase_table)) + return NULL; + return wp_testcase_table[i].desc; +} + +int test__wp(struct test *test __maybe_unused, int i) +{ + if (i < 0 || i >= (int)ARRAY_SIZE(wp_testcase_table)) + return TEST_FAIL; + + if (wp_testcase_table[i].is_supported && + !wp_testcase_table[i].is_supported()) { + wp_testcase_table[i].skip_msg(); + return TEST_SKIP; + } + + return !wp_testcase_table[i].target_func() ? TEST_OK : TEST_FAIL; +} + +/* The s390 so far does not have support for + * instruction breakpoint using the perf_event_open() system call. + */ +bool test__wp_is_supported(void) +{ +#if defined(__s390x__) + return false; +#else + return true; +#endif +} diff --git a/tools/perf/trace/beauty/Build b/tools/perf/trace/beauty/Build index 66330d4b739b..c3b0afd67760 100644 --- a/tools/perf/trace/beauty/Build +++ b/tools/perf/trace/beauty/Build @@ -7,4 +7,6 @@ endif libperf-y += kcmp.o libperf-y += pkey_alloc.o libperf-y += prctl.o +libperf-y += sockaddr.o +libperf-y += socket.o libperf-y += statx.o diff --git a/tools/perf/trace/beauty/beauty.h b/tools/perf/trace/beauty/beauty.h index 984a504d335c..2570152d3909 100644 --- a/tools/perf/trace/beauty/beauty.h +++ b/tools/perf/trace/beauty/beauty.h @@ -30,9 +30,36 @@ struct thread; size_t pid__scnprintf_fd(struct trace *trace, pid_t pid, int fd, char *bf, size_t size); +extern struct strarray strarray__socket_families; + +/** + * augmented_arg: extra payload for syscall pointer arguments + + * If perf_sample->raw_size is more than what a syscall sys_enter_FOO puts, + * then its the arguments contents, so that we can show more than just a + * pointer. This will be done initially with eBPF, the start of that is at the + * tools/perf/examples/bpf/augmented_syscalls.c example for the openat, but + * will eventually be done automagically caching the running kernel tracefs + * events data into an eBPF C script, that then gets compiled and its .o file + * cached for subsequent use. For char pointers like the ones for 'open' like + * syscalls its easy, for the rest we should use DWARF or better, BTF, much + * more compact. + * + * @size: 8 if all we need is an integer, otherwise all of the augmented arg. + * @int_arg: will be used for integer like pointer contents, like 'accept's 'upeer_addrlen' + * @value: u64 aligned, for structs, pathnames + */ +struct augmented_arg { + int size; + int int_arg; + u64 value[]; +}; + /** * @val: value of syscall argument being formatted * @args: All the args, use syscall_args__val(arg, nth) to access one + * @augmented_args: Extra data that can be collected, for instance, with eBPF for expanding the pathname for open, etc + * @augmented_args_size: augmented_args total payload size * @thread: tid state (maps, pid, tid, etc) * @trace: 'perf trace' internals: all threads, etc * @parm: private area, may be an strarray, for instance @@ -43,6 +70,10 @@ size_t pid__scnprintf_fd(struct trace *trace, pid_t pid, int fd, char *bf, size_ struct syscall_arg { unsigned long val; unsigned char *args; + struct { + struct augmented_arg *args; + int size; + } augmented; struct thread *thread; struct trace *trace; void *parm; @@ -106,6 +137,12 @@ size_t syscall_arg__scnprintf_prctl_arg2(char *bf, size_t size, struct syscall_a size_t syscall_arg__scnprintf_prctl_arg3(char *bf, size_t size, struct syscall_arg *arg); #define SCA_PRCTL_ARG3 syscall_arg__scnprintf_prctl_arg3 +size_t syscall_arg__scnprintf_sockaddr(char *bf, size_t size, struct syscall_arg *arg); +#define SCA_SOCKADDR syscall_arg__scnprintf_sockaddr + +size_t syscall_arg__scnprintf_socket_protocol(char *bf, size_t size, struct syscall_arg *arg); +#define SCA_SK_PROTO syscall_arg__scnprintf_socket_protocol + size_t syscall_arg__scnprintf_statx_flags(char *bf, size_t size, struct syscall_arg *arg); #define SCA_STATX_FLAGS syscall_arg__scnprintf_statx_flags diff --git a/tools/perf/trace/beauty/drm_ioctl.sh b/tools/perf/trace/beauty/drm_ioctl.sh index 2149d3a98e42..9d3816815e60 100755 --- a/tools/perf/trace/beauty/drm_ioctl.sh +++ b/tools/perf/trace/beauty/drm_ioctl.sh @@ -1,13 +1,14 @@ #!/bin/sh -drm_header_dir=$1 +[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/drm/ + printf "#ifndef DRM_COMMAND_BASE\n" -grep "#define DRM_COMMAND_BASE" $drm_header_dir/drm.h +grep "#define DRM_COMMAND_BASE" $header_dir/drm.h printf "#endif\n" printf "static const char *drm_ioctl_cmds[] = {\n" -grep "^#define DRM_IOCTL.*DRM_IO" $drm_header_dir/drm.h | \ +grep "^#define DRM_IOCTL.*DRM_IO" $header_dir/drm.h | \ sed -r 's/^#define +DRM_IOCTL_([A-Z0-9_]+)[ ]+DRM_IO[A-Z]* *\( *(0x[[:xdigit:]]+),*.*/ [\2] = "\1",/g' -grep "^#define DRM_I915_[A-Z_0-9]\+[ ]\+0x" $drm_header_dir/i915_drm.h | \ +grep "^#define DRM_I915_[A-Z_0-9]\+[ ]\+0x" $header_dir/i915_drm.h | \ sed -r 's/^#define +DRM_I915_([A-Z0-9_]+)[ ]+(0x[[:xdigit:]]+)/\t[DRM_COMMAND_BASE + \2] = "I915_\1",/g' printf "};\n" diff --git a/tools/perf/trace/beauty/kcmp_type.sh b/tools/perf/trace/beauty/kcmp_type.sh index 40d063b8c082..a3c304caa336 100755 --- a/tools/perf/trace/beauty/kcmp_type.sh +++ b/tools/perf/trace/beauty/kcmp_type.sh @@ -1,6 +1,6 @@ #!/bin/sh -header_dir=$1 +[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/ printf "static const char *kcmp_types[] = {\n" regex='^[[:space:]]+(KCMP_(\w+)),' diff --git a/tools/perf/trace/beauty/kvm_ioctl.sh b/tools/perf/trace/beauty/kvm_ioctl.sh index bd28817afced..c4699fd46bb6 100755 --- a/tools/perf/trace/beauty/kvm_ioctl.sh +++ b/tools/perf/trace/beauty/kvm_ioctl.sh @@ -1,10 +1,10 @@ #!/bin/sh -kvm_header_dir=$1 +[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/ printf "static const char *kvm_ioctl_cmds[] = {\n" regex='^#[[:space:]]*define[[:space:]]+KVM_(\w+)[[:space:]]+_IO[RW]*\([[:space:]]*KVMIO[[:space:]]*,[[:space:]]*(0x[[:xdigit:]]+).*' -egrep $regex ${kvm_header_dir}/kvm.h | \ +egrep $regex ${header_dir}/kvm.h | \ sed -r "s/$regex/\2 \1/g" | \ egrep -v " ((ARM|PPC|S390)_|[GS]ET_(DEBUGREGS|PIT2|XSAVE|TSC_KHZ)|CREATE_SPAPR_TCE_64)" | \ sort | xargs printf "\t[%s] = \"%s\",\n" diff --git a/tools/perf/trace/beauty/madvise_behavior.sh b/tools/perf/trace/beauty/madvise_behavior.sh index 60ef8640ee70..431639eb4d29 100755 --- a/tools/perf/trace/beauty/madvise_behavior.sh +++ b/tools/perf/trace/beauty/madvise_behavior.sh @@ -1,6 +1,6 @@ #!/bin/sh -header_dir=$1 +[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/asm-generic/ printf "static const char *madvise_advices[] = {\n" regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MADV_([[:alnum:]_]+)[[:space:]]+([[:digit:]]+)[[:space:]]*.*' diff --git a/tools/perf/trace/beauty/perf_ioctl.sh b/tools/perf/trace/beauty/perf_ioctl.sh index faea4237c793..6492c74df928 100755 --- a/tools/perf/trace/beauty/perf_ioctl.sh +++ b/tools/perf/trace/beauty/perf_ioctl.sh @@ -1,6 +1,6 @@ #!/bin/sh -header_dir=$1 +[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/ printf "static const char *perf_ioctl_cmds[] = {\n" regex='^#[[:space:]]*define[[:space:]]+PERF_EVENT_IOC_(\w+)[[:space:]]+_IO[RW]*[[:space:]]*\([[:space:]]*.\$.[[:space:]]*,[[:space:]]*([[:digit:]]+).*' diff --git a/tools/perf/trace/beauty/pkey_alloc_access_rights.sh b/tools/perf/trace/beauty/pkey_alloc_access_rights.sh index 62e51a02b839..e0a51aeb20b2 100755 --- a/tools/perf/trace/beauty/pkey_alloc_access_rights.sh +++ b/tools/perf/trace/beauty/pkey_alloc_access_rights.sh @@ -1,6 +1,6 @@ #!/bin/sh -header_dir=$1 +[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/asm-generic/ printf "static const char *pkey_alloc_access_rights[] = {\n" regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+PKEY_([[:alnum:]_]+)[[:space:]]+(0x[[:xdigit:]]+)[[:space:]]*' diff --git a/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh b/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh index aad5ab130539..eb511bb5fbd3 100755 --- a/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh +++ b/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh @@ -1,8 +1,8 @@ #!/bin/sh -sound_header_dir=$1 +[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/sound/ printf "static const char *sndrv_ctl_ioctl_cmds[] = {\n" -grep "^#define[\t ]\+SNDRV_CTL_IOCTL_" $sound_header_dir/asound.h | \ +grep "^#define[\t ]\+SNDRV_CTL_IOCTL_" $header_dir/asound.h | \ sed -r 's/^#define +SNDRV_CTL_IOCTL_([A-Z0-9_]+)[\t ]+_IO[RW]*\( *.U., *(0x[[:xdigit:]]+),?.*/\t[\2] = \"\1\",/g' printf "};\n" diff --git a/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh b/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh index b7e9ef6b2f55..6818392968b2 100755 --- a/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh +++ b/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh @@ -1,8 +1,8 @@ #!/bin/sh -sound_header_dir=$1 +[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/sound/ printf "static const char *sndrv_pcm_ioctl_cmds[] = {\n" -grep "^#define[\t ]\+SNDRV_PCM_IOCTL_" $sound_header_dir/asound.h | \ +grep "^#define[\t ]\+SNDRV_PCM_IOCTL_" $header_dir/asound.h | \ sed -r 's/^#define +SNDRV_PCM_IOCTL_([A-Z0-9_]+)[\t ]+_IO[RW]*\( *.A., *(0x[[:xdigit:]]+),?.*/\t[\2] = \"\1\",/g' printf "};\n" diff --git a/tools/perf/trace/beauty/sockaddr.c b/tools/perf/trace/beauty/sockaddr.c new file mode 100644 index 000000000000..71a79f72d9d9 --- /dev/null +++ b/tools/perf/trace/beauty/sockaddr.c @@ -0,0 +1,76 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (C) 2018, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com> + +#include "trace/beauty/beauty.h" +#include <sys/socket.h> +#include <sys/types.h> +#include <sys/un.h> +#include <arpa/inet.h> + +static const char *socket_families[] = { + "UNSPEC", "LOCAL", "INET", "AX25", "IPX", "APPLETALK", "NETROM", + "BRIDGE", "ATMPVC", "X25", "INET6", "ROSE", "DECnet", "NETBEUI", + "SECURITY", "KEY", "NETLINK", "PACKET", "ASH", "ECONET", "ATMSVC", + "RDS", "SNA", "IRDA", "PPPOX", "WANPIPE", "LLC", "IB", "CAN", "TIPC", + "BLUETOOTH", "IUCV", "RXRPC", "ISDN", "PHONET", "IEEE802154", "CAIF", + "ALG", "NFC", "VSOCK", +}; +DEFINE_STRARRAY(socket_families); + +static size_t af_inet__scnprintf(struct sockaddr *sa, char *bf, size_t size) +{ + struct sockaddr_in *sin = (struct sockaddr_in *)sa; + char tmp[16]; + return scnprintf(bf, size, ", port: %d, addr: %s", ntohs(sin->sin_port), + inet_ntop(sin->sin_family, &sin->sin_addr, tmp, sizeof(tmp))); +} + +static size_t af_inet6__scnprintf(struct sockaddr *sa, char *bf, size_t size) +{ + struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sa; + u32 flowinfo = ntohl(sin6->sin6_flowinfo); + char tmp[512]; + size_t printed = scnprintf(bf, size, ", port: %d, addr: %s", ntohs(sin6->sin6_port), + inet_ntop(sin6->sin6_family, &sin6->sin6_addr, tmp, sizeof(tmp))); + if (flowinfo != 0) + printed += scnprintf(bf + printed, size - printed, ", flowinfo: %lu", flowinfo); + if (sin6->sin6_scope_id != 0) + printed += scnprintf(bf + printed, size - printed, ", scope_id: %lu", sin6->sin6_scope_id); + + return printed; +} + +static size_t af_local__scnprintf(struct sockaddr *sa, char *bf, size_t size) +{ + struct sockaddr_un *sun = (struct sockaddr_un *)sa; + return scnprintf(bf, size, ", path: %s", sun->sun_path); +} + +static size_t (*af_scnprintfs[])(struct sockaddr *sa, char *bf, size_t size) = { + [AF_LOCAL] = af_local__scnprintf, + [AF_INET] = af_inet__scnprintf, + [AF_INET6] = af_inet6__scnprintf, +}; + +static size_t syscall_arg__scnprintf_augmented_sockaddr(struct syscall_arg *arg, char *bf, size_t size) +{ + struct sockaddr *sa = (struct sockaddr *)arg->augmented.args; + char family[32]; + size_t printed; + + strarray__scnprintf(&strarray__socket_families, family, sizeof(family), "%d", sa->sa_family); + printed = scnprintf(bf, size, "{ .family: %s", family); + + if (sa->sa_family < ARRAY_SIZE(af_scnprintfs) && af_scnprintfs[sa->sa_family]) + printed += af_scnprintfs[sa->sa_family](sa, bf + printed, size - printed); + + return printed + scnprintf(bf + printed, size - printed, " }"); +} + +size_t syscall_arg__scnprintf_sockaddr(char *bf, size_t size, struct syscall_arg *arg) +{ + if (arg->augmented.args) + return syscall_arg__scnprintf_augmented_sockaddr(arg, bf, size); + + return scnprintf(bf, size, "%#x", arg->val); +} diff --git a/tools/perf/trace/beauty/socket.c b/tools/perf/trace/beauty/socket.c new file mode 100644 index 000000000000..65227269384b --- /dev/null +++ b/tools/perf/trace/beauty/socket.c @@ -0,0 +1,28 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * trace/beauty/socket.c + * + * Copyright (C) 2018, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com> + */ + +#include "trace/beauty/beauty.h" +#include <sys/types.h> +#include <sys/socket.h> + +static size_t socket__scnprintf_ipproto(int protocol, char *bf, size_t size) +{ +#include "trace/beauty/generated/socket_ipproto_array.c" + static DEFINE_STRARRAY(socket_ipproto); + + return strarray__scnprintf(&strarray__socket_ipproto, bf, size, "%d", protocol); +} + +size_t syscall_arg__scnprintf_socket_protocol(char *bf, size_t size, struct syscall_arg *arg) +{ + int domain = syscall_arg__val(arg, 0); + + if (domain == AF_INET || domain == AF_INET6) + return socket__scnprintf_ipproto(arg->val, bf, size); + + return syscall_arg__scnprintf_int(bf, size, arg); +} diff --git a/tools/perf/trace/beauty/socket_ipproto.sh b/tools/perf/trace/beauty/socket_ipproto.sh new file mode 100755 index 000000000000..a3cc24633bec --- /dev/null +++ b/tools/perf/trace/beauty/socket_ipproto.sh @@ -0,0 +1,11 @@ +#!/bin/sh + +[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/ + +printf "static const char *socket_ipproto[] = {\n" +regex='^[[:space:]]+IPPROTO_(\w+)[[:space:]]+=[[:space:]]+([[:digit:]]+),.*' + +egrep $regex ${header_dir}/in.h | \ + sed -r "s/$regex/\2 \1/g" | \ + sort | xargs printf "\t[%s] = \"%s\",\n" +printf "};\n" diff --git a/tools/perf/trace/beauty/vhost_virtio_ioctl.sh b/tools/perf/trace/beauty/vhost_virtio_ioctl.sh index 76f1de697787..0f6a5197d0be 100755 --- a/tools/perf/trace/beauty/vhost_virtio_ioctl.sh +++ b/tools/perf/trace/beauty/vhost_virtio_ioctl.sh @@ -1,17 +1,17 @@ #!/bin/sh -vhost_virtio_header_dir=$1 +[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/ printf "static const char *vhost_virtio_ioctl_cmds[] = {\n" regex='^#[[:space:]]*define[[:space:]]+VHOST_(\w+)[[:space:]]+_IOW?\([[:space:]]*VHOST_VIRTIO[[:space:]]*,[[:space:]]*(0x[[:xdigit:]]+).*' -egrep $regex ${vhost_virtio_header_dir}/vhost.h | \ +egrep $regex ${header_dir}/vhost.h | \ sed -r "s/$regex/\2 \1/g" | \ sort | xargs printf "\t[%s] = \"%s\",\n" printf "};\n" printf "static const char *vhost_virtio_ioctl_read_cmds[] = {\n" regex='^#[[:space:]]*define[[:space:]]+VHOST_(\w+)[[:space:]]+_IOW?R\([[:space:]]*VHOST_VIRTIO[[:space:]]*,[[:space:]]*(0x[[:xdigit:]]+).*' -egrep $regex ${vhost_virtio_header_dir}/vhost.h | \ +egrep $regex ${header_dir}/vhost.h | \ sed -r "s/$regex/\2 \1/g" | \ sort | xargs printf "\t[%s] = \"%s\",\n" printf "};\n" diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c index 3b4f1c10ff57..1d00e5ec7906 100644 --- a/tools/perf/ui/browsers/annotate.c +++ b/tools/perf/ui/browsers/annotate.c @@ -15,6 +15,7 @@ #include <linux/kernel.h> #include <linux/string.h> #include <sys/ttydefaults.h> +#include <asm/bug.h> struct disasm_line_samples { double percent; @@ -115,7 +116,7 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int if (!browser->navkeypressed) ops.width += 1; - annotation_line__write(al, notes, &ops); + annotation_line__write(al, notes, &ops, ab->opts); if (ops.current_entry) ab->selection = al; @@ -227,10 +228,10 @@ static int disasm__cmp(struct annotation_line *a, struct annotation_line *b) { int i; - for (i = 0; i < a->samples_nr; i++) { - if (a->samples[i].percent == b->samples[i].percent) + for (i = 0; i < a->data_nr; i++) { + if (a->data[i].percent == b->data[i].percent) continue; - return a->samples[i].percent < b->samples[i].percent; + return a->data[i].percent < b->data[i].percent; } return 0; } @@ -314,11 +315,14 @@ static void annotate_browser__calc_percent(struct annotate_browser *browser, continue; } - for (i = 0; i < pos->al.samples_nr; i++) { - struct annotation_data *sample = &pos->al.samples[i]; + for (i = 0; i < pos->al.data_nr; i++) { + double percent; - if (max_percent < sample->percent) - max_percent = sample->percent; + percent = annotation_data__percent(&pos->al.data[i], + browser->opts->percent_type); + + if (max_percent < percent) + max_percent = percent; } if (max_percent < 0.01 && pos->al.ipc == 0) { @@ -380,9 +384,10 @@ static void ui_browser__init_asm_mode(struct ui_browser *browser) #define SYM_TITLE_MAX_SIZE (PATH_MAX + 64) static int sym_title(struct symbol *sym, struct map *map, char *title, - size_t sz) + size_t sz, int percent_type) { - return snprintf(title, sz, "%s %s", sym->name, map->dso->long_name); + return snprintf(title, sz, "%s %s [Percent: %s]", sym->name, map->dso->long_name, + percent_type_str(percent_type)); } /* @@ -420,7 +425,7 @@ static bool annotate_browser__callq(struct annotate_browser *browser, pthread_mutex_unlock(¬es->lock); symbol__tui_annotate(dl->ops.target.sym, ms->map, evsel, hbt, browser->opts); - sym_title(ms->sym, ms->map, title, sizeof(title)); + sym_title(ms->sym, ms->map, title, sizeof(title), browser->opts->percent_type); ui_browser__show_title(&browser->b, title); return true; } @@ -595,6 +600,7 @@ bool annotate_browser__continue_search_reverse(struct annotate_browser *browser, static int annotate_browser__show(struct ui_browser *browser, char *title, const char *help) { + struct annotate_browser *ab = container_of(browser, struct annotate_browser, b); struct map_symbol *ms = browser->priv; struct symbol *sym = ms->sym; char symbol_dso[SYM_TITLE_MAX_SIZE]; @@ -602,7 +608,7 @@ static int annotate_browser__show(struct ui_browser *browser, char *title, const if (ui_browser__show(browser, title, help) < 0) return -1; - sym_title(sym, ms->map, symbol_dso, sizeof(symbol_dso)); + sym_title(sym, ms->map, symbol_dso, sizeof(symbol_dso), ab->opts->percent_type); ui_browser__gotorc_title(browser, 0, 0); ui_browser__set_color(browser, HE_COLORSET_ROOT); @@ -610,6 +616,39 @@ static int annotate_browser__show(struct ui_browser *browser, char *title, const return 0; } +static void +switch_percent_type(struct annotation_options *opts, bool base) +{ + switch (opts->percent_type) { + case PERCENT_HITS_LOCAL: + if (base) + opts->percent_type = PERCENT_PERIOD_LOCAL; + else + opts->percent_type = PERCENT_HITS_GLOBAL; + break; + case PERCENT_HITS_GLOBAL: + if (base) + opts->percent_type = PERCENT_PERIOD_GLOBAL; + else + opts->percent_type = PERCENT_HITS_LOCAL; + break; + case PERCENT_PERIOD_LOCAL: + if (base) + opts->percent_type = PERCENT_HITS_LOCAL; + else + opts->percent_type = PERCENT_PERIOD_GLOBAL; + break; + case PERCENT_PERIOD_GLOBAL: + if (base) + opts->percent_type = PERCENT_HITS_GLOBAL; + else + opts->percent_type = PERCENT_PERIOD_LOCAL; + break; + default: + WARN_ON(1); + } +} + static int annotate_browser__run(struct annotate_browser *browser, struct perf_evsel *evsel, struct hist_browser_timer *hbt) @@ -624,8 +663,7 @@ static int annotate_browser__run(struct annotate_browser *browser, char title[256]; int key; - annotation__scnprintf_samples_period(notes, title, sizeof(title), evsel); - + hists__scnprintf_title(hists, title, sizeof(title)); if (annotate_browser__show(&browser->b, title, help) < 0) return -1; @@ -701,6 +739,8 @@ static int annotate_browser__run(struct annotate_browser *browser, "k Toggle line numbers\n" "P Print to [symbol_name].annotation file.\n" "r Run available scripts\n" + "p Toggle percent type [local/global]\n" + "b Toggle percent base [period/hits]\n" "? Search string backwards\n"); continue; case 'r': @@ -781,7 +821,7 @@ show_sup_ins: continue; } case 'P': - map_symbol__annotation_dump(ms, evsel); + map_symbol__annotation_dump(ms, evsel, browser->opts); continue; case 't': if (notes->options->show_total_period) { @@ -800,6 +840,12 @@ show_sup_ins: notes->options->show_minmax_cycle = true; annotation__update_column_widths(notes); continue; + case 'p': + case 'b': + switch_percent_type(browser->opts, key == 'b'); + hists__scnprintf_title(hists, title, sizeof(title)); + annotate_browser__show(&browser->b, title, help); + continue; case K_LEFT: case K_ESC: case 'q': diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c index 69b7a28f7a1c..74c4ae1f0a05 100644 --- a/tools/perf/ui/stdio/hist.c +++ b/tools/perf/ui/stdio/hist.c @@ -529,7 +529,7 @@ out: static int hist_entry__fprintf(struct hist_entry *he, size_t size, char *bf, size_t bfsz, FILE *fp, - bool use_callchain) + bool ignore_callchains) { int ret; int callchain_ret = 0; @@ -550,7 +550,7 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size, ret = fprintf(fp, "%s\n", bf); - if (hist_entry__has_callchains(he) && use_callchain) + if (hist_entry__has_callchains(he) && !ignore_callchains) callchain_ret = hist_entry_callchain__fprintf(he, total_period, 0, fp); @@ -755,7 +755,7 @@ int hists__fprintf_headers(struct hists *hists, FILE *fp) size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, int max_cols, float min_pcnt, FILE *fp, - bool use_callchain) + bool ignore_callchains) { struct rb_node *nd; size_t ret = 0; @@ -799,7 +799,7 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, if (percent < min_pcnt) continue; - ret += hist_entry__fprintf(h, max_cols, line, linesz, fp, use_callchain); + ret += hist_entry__fprintf(h, max_cols, line, linesz, fp, ignore_callchains); if (max_rows && ++nr_rows >= max_rows) break; diff --git a/tools/perf/util/Build b/tools/perf/util/Build index b604ef334dc9..ecd9f9ceda77 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -73,6 +73,7 @@ libperf-y += vdso.o libperf-y += counts.o libperf-y += stat.o libperf-y += stat-shadow.o +libperf-y += stat-display.o libperf-y += record.o libperf-y += srcline.o libperf-y += data.o @@ -87,6 +88,7 @@ libperf-$(CONFIG_AUXTRACE) += intel-pt.o libperf-$(CONFIG_AUXTRACE) += intel-bts.o libperf-$(CONFIG_AUXTRACE) += arm-spe.o libperf-$(CONFIG_AUXTRACE) += arm-spe-pkt-decoder.o +libperf-$(CONFIG_AUXTRACE) += s390-cpumsf.o ifdef CONFIG_LIBOPENCSD libperf-$(CONFIG_AUXTRACE) += cs-etm.o diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index f91775b4bc3c..28cd6a17491b 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -49,6 +49,7 @@ struct annotation_options annotation__default_options = { .jump_arrows = true, .annotate_src = true, .offset_level = ANNOTATION__OFFSET_JUMP_TARGETS, + .percent_type = PERCENT_PERIOD_LOCAL, }; static regex_t file_lineno; @@ -245,8 +246,14 @@ find_target: indirect_call: tok = strchr(endptr, '*'); - if (tok != NULL) - ops->target.addr = strtoull(tok + 1, NULL, 16); + if (tok != NULL) { + endptr++; + + /* Indirect call can use a non-rip register and offset: callq *0x8(%rbx). + * Do not parse such instruction. */ + if (strstr(endptr, "(%r") == NULL) + ops->target.addr = strtoull(endptr, NULL, 16); + } goto find_target; } @@ -275,7 +282,19 @@ bool ins__is_call(const struct ins *ins) return ins->ops == &call_ops || ins->ops == &s390_call_ops; } -static int jump__parse(struct arch *arch __maybe_unused, struct ins_operands *ops, struct map_symbol *ms) +/* + * Prevents from matching commas in the comment section, e.g.: + * ffff200008446e70: b.cs ffff2000084470f4 <generic_exec_single+0x314> // b.hs, b.nlast + */ +static inline const char *validate_comma(const char *c, struct ins_operands *ops) +{ + if (ops->raw_comment && c > ops->raw_comment) + return NULL; + + return c; +} + +static int jump__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms) { struct map *map = ms->map; struct symbol *sym = ms->sym; @@ -284,6 +303,10 @@ static int jump__parse(struct arch *arch __maybe_unused, struct ins_operands *op }; const char *c = strchr(ops->raw, ','); u64 start, end; + + ops->raw_comment = strchr(ops->raw, arch->objdump.comment_char); + c = validate_comma(c, ops); + /* * Examples of lines to parse for the _cpp_lex_token@@Base * function: @@ -303,6 +326,7 @@ static int jump__parse(struct arch *arch __maybe_unused, struct ins_operands *op ops->target.addr = strtoull(c, NULL, 16); if (!ops->target.addr) { c = strchr(c, ','); + c = validate_comma(c, ops); if (c++ != NULL) ops->target.addr = strtoull(c, NULL, 16); } @@ -360,9 +384,12 @@ static int jump__scnprintf(struct ins *ins, char *bf, size_t size, return scnprintf(bf, size, "%-6s %s", ins->name, ops->target.sym->name); c = strchr(ops->raw, ','); + c = validate_comma(c, ops); + if (c != NULL) { const char *c2 = strchr(c + 1, ','); + c2 = validate_comma(c2, ops); /* check for 3-op insn */ if (c2 != NULL) c = c2; @@ -1108,7 +1135,7 @@ annotation_line__new(struct annotate_args *args, size_t privsize) if (perf_evsel__is_group_event(evsel)) nr = evsel->nr_members; - size += sizeof(al->samples[0]) * nr; + size += sizeof(al->data[0]) * nr; al = zalloc(size); if (al) { @@ -1117,7 +1144,7 @@ annotation_line__new(struct annotate_args *args, size_t privsize) al->offset = args->offset; al->line = strdup(args->line); al->line_nr = args->line_nr; - al->samples_nr = nr; + al->data_nr = nr; } return al; @@ -1297,7 +1324,8 @@ static int disasm_line__print(struct disasm_line *dl, u64 start, int addr_fmt_wi static int annotation_line__print(struct annotation_line *al, struct symbol *sym, u64 start, struct perf_evsel *evsel, u64 len, int min_pcnt, int printed, - int max_lines, struct annotation_line *queue, int addr_fmt_width) + int max_lines, struct annotation_line *queue, int addr_fmt_width, + int percent_type) { struct disasm_line *dl = container_of(al, struct disasm_line, al); static const char *prev_line; @@ -1309,15 +1337,18 @@ annotation_line__print(struct annotation_line *al, struct symbol *sym, u64 start const char *color; struct annotation *notes = symbol__annotation(sym); - for (i = 0; i < al->samples_nr; i++) { - struct annotation_data *sample = &al->samples[i]; + for (i = 0; i < al->data_nr; i++) { + double percent; - if (sample->percent > max_percent) - max_percent = sample->percent; + percent = annotation_data__percent(&al->data[i], + percent_type); + + if (percent > max_percent) + max_percent = percent; } - if (al->samples_nr > nr_percent) - nr_percent = al->samples_nr; + if (al->data_nr > nr_percent) + nr_percent = al->data_nr; if (max_percent < min_pcnt) return -1; @@ -1330,7 +1361,8 @@ annotation_line__print(struct annotation_line *al, struct symbol *sym, u64 start if (queue == al) break; annotation_line__print(queue, sym, start, evsel, len, - 0, 0, 1, NULL, addr_fmt_width); + 0, 0, 1, NULL, addr_fmt_width, + percent_type); } } @@ -1351,18 +1383,20 @@ annotation_line__print(struct annotation_line *al, struct symbol *sym, u64 start } for (i = 0; i < nr_percent; i++) { - struct annotation_data *sample = &al->samples[i]; + struct annotation_data *data = &al->data[i]; + double percent; - color = get_percent_color(sample->percent); + percent = annotation_data__percent(data, percent_type); + color = get_percent_color(percent); if (symbol_conf.show_total_period) color_fprintf(stdout, color, " %11" PRIu64, - sample->he.period); + data->he.period); else if (symbol_conf.show_nr_samples) color_fprintf(stdout, color, " %7" PRIu64, - sample->he.nr_samples); + data->he.nr_samples); else - color_fprintf(stdout, color, " %7.2f", sample->percent); + color_fprintf(stdout, color, " %7.2f", percent); } printf(" : "); @@ -1621,6 +1655,7 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args) char symfs_filename[PATH_MAX]; struct kcore_extract kce; bool delete_extract = false; + bool decomp = false; int stdout_fd[2]; int lineno = 0; int nline; @@ -1654,6 +1689,7 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args) tmp, sizeof(tmp)) < 0) goto out; + decomp = true; strcpy(symfs_filename, tmp); } @@ -1740,7 +1776,7 @@ out_free_command: out_remove_tmp: close(stdout_fd[0]); - if (dso__needs_decompress(dso)) + if (decomp) unlink(symfs_filename); if (delete_extract) @@ -1753,34 +1789,45 @@ out_close_stdout: goto out_free_command; } -static void calc_percent(struct sym_hist *hist, - struct annotation_data *sample, +static void calc_percent(struct sym_hist *sym_hist, + struct hists *hists, + struct annotation_data *data, s64 offset, s64 end) { unsigned int hits = 0; u64 period = 0; while (offset < end) { - hits += hist->addr[offset].nr_samples; - period += hist->addr[offset].period; + hits += sym_hist->addr[offset].nr_samples; + period += sym_hist->addr[offset].period; ++offset; } - if (hist->nr_samples) { - sample->he.period = period; - sample->he.nr_samples = hits; - sample->percent = 100.0 * hits / hist->nr_samples; + if (sym_hist->nr_samples) { + data->he.period = period; + data->he.nr_samples = hits; + data->percent[PERCENT_HITS_LOCAL] = 100.0 * hits / sym_hist->nr_samples; } + + if (hists->stats.nr_non_filtered_samples) + data->percent[PERCENT_HITS_GLOBAL] = 100.0 * hits / hists->stats.nr_non_filtered_samples; + + if (sym_hist->period) + data->percent[PERCENT_PERIOD_LOCAL] = 100.0 * period / sym_hist->period; + + if (hists->stats.total_period) + data->percent[PERCENT_PERIOD_GLOBAL] = 100.0 * period / hists->stats.total_period; } static void annotation__calc_percent(struct annotation *notes, - struct perf_evsel *evsel, s64 len) + struct perf_evsel *leader, s64 len) { struct annotation_line *al, *next; + struct perf_evsel *evsel; list_for_each_entry(al, ¬es->src->source, node) { s64 end; - int i; + int i = 0; if (al->offset == -1) continue; @@ -1788,14 +1835,17 @@ static void annotation__calc_percent(struct annotation *notes, next = annotation_line__next(al, ¬es->src->source); end = next ? next->offset : len; - for (i = 0; i < al->samples_nr; i++) { - struct annotation_data *sample; - struct sym_hist *hist; + for_each_group_evsel(evsel, leader) { + struct hists *hists = evsel__hists(evsel); + struct annotation_data *data; + struct sym_hist *sym_hist; - hist = annotation__histogram(notes, evsel->idx + i); - sample = &al->samples[i]; + BUG_ON(i >= al->data_nr); - calc_percent(hist, sample, al->offset, end); + sym_hist = annotation__histogram(notes, evsel->idx); + data = &al->data[i++]; + + calc_percent(sym_hist, hists, data, al->offset, end); } } } @@ -1846,7 +1896,8 @@ int symbol__annotate(struct symbol *sym, struct map *map, return symbol__disassemble(sym, &args); } -static void insert_source_line(struct rb_root *root, struct annotation_line *al) +static void insert_source_line(struct rb_root *root, struct annotation_line *al, + struct annotation_options *opts) { struct annotation_line *iter; struct rb_node **p = &root->rb_node; @@ -1859,8 +1910,10 @@ static void insert_source_line(struct rb_root *root, struct annotation_line *al) ret = strcmp(iter->path, al->path); if (ret == 0) { - for (i = 0; i < al->samples_nr; i++) - iter->samples[i].percent_sum += al->samples[i].percent; + for (i = 0; i < al->data_nr; i++) { + iter->data[i].percent_sum += annotation_data__percent(&al->data[i], + opts->percent_type); + } return; } @@ -1870,8 +1923,10 @@ static void insert_source_line(struct rb_root *root, struct annotation_line *al) p = &(*p)->rb_right; } - for (i = 0; i < al->samples_nr; i++) - al->samples[i].percent_sum = al->samples[i].percent; + for (i = 0; i < al->data_nr; i++) { + al->data[i].percent_sum = annotation_data__percent(&al->data[i], + opts->percent_type); + } rb_link_node(&al->rb_node, parent, p); rb_insert_color(&al->rb_node, root); @@ -1881,10 +1936,10 @@ static int cmp_source_line(struct annotation_line *a, struct annotation_line *b) { int i; - for (i = 0; i < a->samples_nr; i++) { - if (a->samples[i].percent_sum == b->samples[i].percent_sum) + for (i = 0; i < a->data_nr; i++) { + if (a->data[i].percent_sum == b->data[i].percent_sum) continue; - return a->samples[i].percent_sum > b->samples[i].percent_sum; + return a->data[i].percent_sum > b->data[i].percent_sum; } return 0; @@ -1949,8 +2004,8 @@ static void print_summary(struct rb_root *root, const char *filename) int i; al = rb_entry(node, struct annotation_line, rb_node); - for (i = 0; i < al->samples_nr; i++) { - percent = al->samples[i].percent_sum; + for (i = 0; i < al->data_nr; i++) { + percent = al->data[i].percent_sum; color = get_percent_color(percent); color_fprintf(stdout, color, " %7.2f", percent); @@ -2029,10 +2084,12 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map, evsel_name = buf; } - graph_dotted_len = printf(" %-*.*s| Source code & Disassembly of %s for %s (%" PRIu64 " samples)\n", + graph_dotted_len = printf(" %-*.*s| Source code & Disassembly of %s for %s (%" PRIu64 " samples, " + "percent: %s)\n", width, width, symbol_conf.show_total_period ? "Period" : symbol_conf.show_nr_samples ? "Samples" : "Percent", - d_filename, evsel_name, h->nr_samples); + d_filename, evsel_name, h->nr_samples, + percent_type_str(opts->percent_type)); printf("%-*.*s----\n", graph_dotted_len, graph_dotted_len, graph_dotted_line); @@ -2052,7 +2109,7 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map, err = annotation_line__print(pos, sym, start, evsel, len, opts->min_pcnt, printed, opts->max_lines, - queue, addr_fmt_width); + queue, addr_fmt_width, opts->percent_type); switch (err) { case 0: @@ -2129,10 +2186,11 @@ static void FILE__write_graph(void *fp, int graph) fputs(s, fp); } -int symbol__annotate_fprintf2(struct symbol *sym, FILE *fp) +static int symbol__annotate_fprintf2(struct symbol *sym, FILE *fp, + struct annotation_options *opts) { struct annotation *notes = symbol__annotation(sym); - struct annotation_write_ops ops = { + struct annotation_write_ops wops = { .first_line = true, .obj = fp, .set_color = FILE__set_color, @@ -2146,15 +2204,16 @@ int symbol__annotate_fprintf2(struct symbol *sym, FILE *fp) list_for_each_entry(al, ¬es->src->source, node) { if (annotation_line__filter(al, notes)) continue; - annotation_line__write(al, notes, &ops); + annotation_line__write(al, notes, &wops, opts); fputc('\n', fp); - ops.first_line = false; + wops.first_line = false; } return 0; } -int map_symbol__annotation_dump(struct map_symbol *ms, struct perf_evsel *evsel) +int map_symbol__annotation_dump(struct map_symbol *ms, struct perf_evsel *evsel, + struct annotation_options *opts) { const char *ev_name = perf_evsel__name(evsel); char buf[1024]; @@ -2176,7 +2235,7 @@ int map_symbol__annotation_dump(struct map_symbol *ms, struct perf_evsel *evsel) fprintf(fp, "%s() %s\nEvent: %s\n\n", ms->sym->name, ms->map->dso->long_name, ev_name); - symbol__annotate_fprintf2(ms->sym, fp); + symbol__annotate_fprintf2(ms->sym, fp, opts); fclose(fp); err = 0; @@ -2346,7 +2405,8 @@ void annotation__update_column_widths(struct annotation *notes) } static void annotation__calc_lines(struct annotation *notes, struct map *map, - struct rb_root *root) + struct rb_root *root, + struct annotation_options *opts) { struct annotation_line *al; struct rb_root tmp_root = RB_ROOT; @@ -2355,13 +2415,14 @@ static void annotation__calc_lines(struct annotation *notes, struct map *map, double percent_max = 0.0; int i; - for (i = 0; i < al->samples_nr; i++) { - struct annotation_data *sample; + for (i = 0; i < al->data_nr; i++) { + double percent; - sample = &al->samples[i]; + percent = annotation_data__percent(&al->data[i], + opts->percent_type); - if (sample->percent > percent_max) - percent_max = sample->percent; + if (percent > percent_max) + percent_max = percent; } if (percent_max <= 0.5) @@ -2369,18 +2430,19 @@ static void annotation__calc_lines(struct annotation *notes, struct map *map, al->path = get_srcline(map->dso, notes->start + al->offset, NULL, false, true, notes->start + al->offset); - insert_source_line(&tmp_root, al); + insert_source_line(&tmp_root, al, opts); } resort_source_line(root, &tmp_root); } static void symbol__calc_lines(struct symbol *sym, struct map *map, - struct rb_root *root) + struct rb_root *root, + struct annotation_options *opts) { struct annotation *notes = symbol__annotation(sym); - annotation__calc_lines(notes, map, root); + annotation__calc_lines(notes, map, root, opts); } int symbol__tty_annotate2(struct symbol *sym, struct map *map, @@ -2389,7 +2451,7 @@ int symbol__tty_annotate2(struct symbol *sym, struct map *map, { struct dso *dso = map->dso; struct rb_root source_line = RB_ROOT; - struct annotation *notes = symbol__annotation(sym); + struct hists *hists = evsel__hists(evsel); char buf[1024]; if (symbol__annotate2(sym, map, evsel, opts, NULL) < 0) @@ -2397,13 +2459,14 @@ int symbol__tty_annotate2(struct symbol *sym, struct map *map, if (opts->print_lines) { srcline_full_filename = opts->full_path; - symbol__calc_lines(sym, map, &source_line); + symbol__calc_lines(sym, map, &source_line, opts); print_summary(&source_line, dso->long_name); } - annotation__scnprintf_samples_period(notes, buf, sizeof(buf), evsel); - fprintf(stdout, "%s\n%s() %s\n", buf, sym->name, dso->long_name); - symbol__annotate_fprintf2(sym, stdout); + hists__scnprintf_title(hists, buf, sizeof(buf)); + fprintf(stdout, "%s, [percent: %s]\n%s() %s\n", + buf, percent_type_str(opts->percent_type), sym->name, dso->long_name); + symbol__annotate_fprintf2(sym, stdout, opts); annotated_source__purge(symbol__annotation(sym)->src); @@ -2424,7 +2487,7 @@ int symbol__tty_annotate(struct symbol *sym, struct map *map, if (opts->print_lines) { srcline_full_filename = opts->full_path; - symbol__calc_lines(sym, map, &source_line); + symbol__calc_lines(sym, map, &source_line, opts); print_summary(&source_line, dso->long_name); } @@ -2441,14 +2504,21 @@ bool ui__has_annotation(void) } -double annotation_line__max_percent(struct annotation_line *al, struct annotation *notes) +static double annotation_line__max_percent(struct annotation_line *al, + struct annotation *notes, + unsigned int percent_type) { double percent_max = 0.0; int i; for (i = 0; i < notes->nr_events; i++) { - if (al->samples[i].percent > percent_max) - percent_max = al->samples[i].percent; + double percent; + + percent = annotation_data__percent(&al->data[i], + percent_type); + + if (percent > percent_max) + percent_max = percent; } return percent_max; @@ -2487,7 +2557,7 @@ call_like: static void __annotation_line__write(struct annotation_line *al, struct annotation *notes, bool first_line, bool current_entry, bool change_color, int width, - void *obj, + void *obj, unsigned int percent_type, int (*obj__set_color)(void *obj, int color), void (*obj__set_percent_color)(void *obj, double percent, bool current), int (*obj__set_jumps_percent_color)(void *obj, int nr, bool current), @@ -2495,7 +2565,7 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati void (*obj__write_graph)(void *obj, int graph)) { - double percent_max = annotation_line__max_percent(al, notes); + double percent_max = annotation_line__max_percent(al, notes, percent_type); int pcnt_width = annotation__pcnt_width(notes), cycles_width = annotation__cycles_width(notes); bool show_title = false; @@ -2514,15 +2584,18 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati int i; for (i = 0; i < notes->nr_events; i++) { - obj__set_percent_color(obj, al->samples[i].percent, current_entry); + double percent; + + percent = annotation_data__percent(&al->data[i], percent_type); + + obj__set_percent_color(obj, percent, current_entry); if (notes->options->show_total_period) { - obj__printf(obj, "%11" PRIu64 " ", al->samples[i].he.period); + obj__printf(obj, "%11" PRIu64 " ", al->data[i].he.period); } else if (notes->options->show_nr_samples) { obj__printf(obj, "%6" PRIu64 " ", - al->samples[i].he.nr_samples); + al->data[i].he.nr_samples); } else { - obj__printf(obj, "%6.2f ", - al->samples[i].percent); + obj__printf(obj, "%6.2f ", percent); } } } else { @@ -2640,13 +2713,15 @@ print_addr: } void annotation_line__write(struct annotation_line *al, struct annotation *notes, - struct annotation_write_ops *ops) + struct annotation_write_ops *wops, + struct annotation_options *opts) { - __annotation_line__write(al, notes, ops->first_line, ops->current_entry, - ops->change_color, ops->width, ops->obj, - ops->set_color, ops->set_percent_color, - ops->set_jumps_percent_color, ops->printf, - ops->write_graph); + __annotation_line__write(al, notes, wops->first_line, wops->current_entry, + wops->change_color, wops->width, wops->obj, + opts->percent_type, + wops->set_color, wops->set_percent_color, + wops->set_jumps_percent_color, wops->printf, + wops->write_graph); } int symbol__annotate2(struct symbol *sym, struct map *map, struct perf_evsel *evsel, @@ -2688,46 +2763,6 @@ out_free_offsets: return -1; } -int __annotation__scnprintf_samples_period(struct annotation *notes, - char *bf, size_t size, - struct perf_evsel *evsel, - bool show_freq) -{ - const char *ev_name = perf_evsel__name(evsel); - char buf[1024], ref[30] = " show reference callgraph, "; - char sample_freq_str[64] = ""; - unsigned long nr_samples = 0; - int nr_members = 1; - bool enable_ref = false; - u64 nr_events = 0; - char unit; - int i; - - if (perf_evsel__is_group_event(evsel)) { - perf_evsel__group_desc(evsel, buf, sizeof(buf)); - ev_name = buf; - nr_members = evsel->nr_members; - } - - for (i = 0; i < nr_members; i++) { - struct sym_hist *ah = annotation__histogram(notes, evsel->idx + i); - - nr_samples += ah->nr_samples; - nr_events += ah->period; - } - - if (symbol_conf.show_ref_callgraph && strstr(ev_name, "call-graph=no")) - enable_ref = true; - - if (show_freq) - scnprintf(sample_freq_str, sizeof(sample_freq_str), " %d Hz,", evsel->attr.sample_freq); - - nr_samples = convert_unit(nr_samples, &unit); - return scnprintf(bf, size, "Samples: %lu%c of event%s '%s',%s%sEvent count (approx.): %" PRIu64, - nr_samples, unit, evsel->nr_members > 1 ? "s" : "", - ev_name, sample_freq_str, enable_ref ? ref : " ", nr_events); -} - #define ANNOTATION__CFG(n) \ { .name = #n, .value = &annotation__default_options.n, } @@ -2792,3 +2827,55 @@ void annotation_config__init(void) annotation__default_options.show_total_period = symbol_conf.show_total_period; annotation__default_options.show_nr_samples = symbol_conf.show_nr_samples; } + +static unsigned int parse_percent_type(char *str1, char *str2) +{ + unsigned int type = (unsigned int) -1; + + if (!strcmp("period", str1)) { + if (!strcmp("local", str2)) + type = PERCENT_PERIOD_LOCAL; + else if (!strcmp("global", str2)) + type = PERCENT_PERIOD_GLOBAL; + } + + if (!strcmp("hits", str1)) { + if (!strcmp("local", str2)) + type = PERCENT_HITS_LOCAL; + else if (!strcmp("global", str2)) + type = PERCENT_HITS_GLOBAL; + } + + return type; +} + +int annotate_parse_percent_type(const struct option *opt, const char *_str, + int unset __maybe_unused) +{ + struct annotation_options *opts = opt->value; + unsigned int type; + char *str1, *str2; + int err = -1; + + str1 = strdup(_str); + if (!str1) + return -ENOMEM; + + str2 = strchr(str1, '-'); + if (!str2) + goto out; + + *str2++ = 0; + + type = parse_percent_type(str1, str2); + if (type == (unsigned int) -1) + type = parse_percent_type(str2, str1); + if (type != (unsigned int) -1) { + opts->percent_type = type; + err = 0; + } + +out: + free(str1); + return err; +} diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index a4c0d91907e6..5399ba2321bb 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -11,6 +11,7 @@ #include <linux/list.h> #include <linux/rbtree.h> #include <pthread.h> +#include <asm/bug.h> struct ins_ops; @@ -21,6 +22,7 @@ struct ins { struct ins_operands { char *raw; + char *raw_comment; struct { char *raw; char *name; @@ -82,6 +84,7 @@ struct annotation_options { int context; const char *objdump_path; const char *disassembler_style; + unsigned int percent_type; }; enum { @@ -101,8 +104,16 @@ struct sym_hist_entry { u64 period; }; +enum { + PERCENT_HITS_LOCAL, + PERCENT_HITS_GLOBAL, + PERCENT_PERIOD_LOCAL, + PERCENT_PERIOD_GLOBAL, + PERCENT_MAX, +}; + struct annotation_data { - double percent; + double percent[PERCENT_MAX]; double percent_sum; struct sym_hist_entry he; }; @@ -122,8 +133,8 @@ struct annotation_line { char *path; u32 idx; int idx_asm; - int samples_nr; - struct annotation_data samples[0]; + int data_nr; + struct annotation_data data[0]; }; struct disasm_line { @@ -134,6 +145,27 @@ struct disasm_line { struct annotation_line al; }; +static inline double annotation_data__percent(struct annotation_data *data, + unsigned int which) +{ + return which < PERCENT_MAX ? data->percent[which] : -1; +} + +static inline const char *percent_type_str(unsigned int type) +{ + static const char *str[PERCENT_MAX] = { + "local hits", + "global hits", + "local period", + "global period", + }; + + if (WARN_ON(type >= PERCENT_MAX)) + return "N/A"; + + return str[type]; +} + static inline struct disasm_line *disasm_line(struct annotation_line *al) { return al ? container_of(al, struct disasm_line, al) : NULL; @@ -169,22 +201,15 @@ struct annotation_write_ops { void (*write_graph)(void *obj, int graph); }; -double annotation_line__max_percent(struct annotation_line *al, struct annotation *notes); void annotation_line__write(struct annotation_line *al, struct annotation *notes, - struct annotation_write_ops *ops); + struct annotation_write_ops *ops, + struct annotation_options *opts); int __annotation__scnprintf_samples_period(struct annotation *notes, char *bf, size_t size, struct perf_evsel *evsel, bool show_freq); -static inline int annotation__scnprintf_samples_period(struct annotation *notes, - char *bf, size_t size, - struct perf_evsel *evsel) -{ - return __annotation__scnprintf_samples_period(notes, bf, size, evsel, true); -} - int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw); size_t disasm__fprintf(struct list_head *head, FILE *fp); void symbol__calc_percent(struct symbol *sym, struct perf_evsel *evsel); @@ -340,12 +365,12 @@ int symbol__strerror_disassemble(struct symbol *sym, struct map *map, int symbol__annotate_printf(struct symbol *sym, struct map *map, struct perf_evsel *evsel, struct annotation_options *options); -int symbol__annotate_fprintf2(struct symbol *sym, FILE *fp); void symbol__annotate_zero_histogram(struct symbol *sym, int evidx); void symbol__annotate_decay_histogram(struct symbol *sym, int evidx); void annotated_source__purge(struct annotated_source *as); -int map_symbol__annotation_dump(struct map_symbol *ms, struct perf_evsel *evsel); +int map_symbol__annotation_dump(struct map_symbol *ms, struct perf_evsel *evsel, + struct annotation_options *opts); bool ui__has_annotation(void); @@ -373,4 +398,6 @@ static inline int symbol__tui_annotate(struct symbol *sym __maybe_unused, void annotation_config__init(void); +int annotate_parse_percent_type(const struct option *opt, const char *_str, + int unset); #endif /* __PERF_ANNOTATE_H */ diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index d056447520a2..c4617bcfd521 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -56,6 +56,7 @@ #include "intel-pt.h" #include "intel-bts.h" #include "arm-spe.h" +#include "s390-cpumsf.h" #include "sane_ctype.h" #include "symbol/kallsyms.h" @@ -202,6 +203,9 @@ static int auxtrace_queues__grow(struct auxtrace_queues *queues, for (i = 0; i < queues->nr_queues; i++) { list_splice_tail(&queues->queue_array[i].head, &queue_array[i].head); + queue_array[i].tid = queues->queue_array[i].tid; + queue_array[i].cpu = queues->queue_array[i].cpu; + queue_array[i].set = queues->queue_array[i].set; queue_array[i].priv = queues->queue_array[i].priv; } @@ -902,9 +906,8 @@ out_free: return err; } -int perf_event__process_auxtrace_info(struct perf_tool *tool __maybe_unused, - union perf_event *event, - struct perf_session *session) +int perf_event__process_auxtrace_info(struct perf_session *session, + union perf_event *event) { enum auxtrace_type type = event->auxtrace_info.type; @@ -920,15 +923,16 @@ int perf_event__process_auxtrace_info(struct perf_tool *tool __maybe_unused, return arm_spe_process_auxtrace_info(event, session); case PERF_AUXTRACE_CS_ETM: return cs_etm__process_auxtrace_info(event, session); + case PERF_AUXTRACE_S390_CPUMSF: + return s390_cpumsf_process_auxtrace_info(event, session); case PERF_AUXTRACE_UNKNOWN: default: return -EINVAL; } } -s64 perf_event__process_auxtrace(struct perf_tool *tool, - union perf_event *event, - struct perf_session *session) +s64 perf_event__process_auxtrace(struct perf_session *session, + union perf_event *event) { s64 err; @@ -944,7 +948,7 @@ s64 perf_event__process_auxtrace(struct perf_tool *tool, if (!session->auxtrace || event->header.type != PERF_RECORD_AUXTRACE) return -EINVAL; - err = session->auxtrace->process_auxtrace_event(session, event, tool); + err = session->auxtrace->process_auxtrace_event(session, event, session->tool); if (err < 0) return err; @@ -1179,9 +1183,8 @@ void events_stats__auxtrace_error_warn(const struct events_stats *stats) } } -int perf_event__process_auxtrace_error(struct perf_tool *tool __maybe_unused, - union perf_event *event, - struct perf_session *session) +int perf_event__process_auxtrace_error(struct perf_session *session, + union perf_event *event) { if (auxtrace__dont_decode(session)) return 0; @@ -1190,11 +1193,12 @@ int perf_event__process_auxtrace_error(struct perf_tool *tool __maybe_unused, return 0; } -static int __auxtrace_mmap__read(struct auxtrace_mmap *mm, +static int __auxtrace_mmap__read(struct perf_mmap *map, struct auxtrace_record *itr, struct perf_tool *tool, process_auxtrace_t fn, bool snapshot, size_t snapshot_size) { + struct auxtrace_mmap *mm = &map->auxtrace_mmap; u64 head, old = mm->prev, offset, ref; unsigned char *data = mm->base; size_t size, head_off, old_off, len1, len2, padding; @@ -1281,7 +1285,7 @@ static int __auxtrace_mmap__read(struct auxtrace_mmap *mm, ev.auxtrace.tid = mm->tid; ev.auxtrace.cpu = mm->cpu; - if (fn(tool, &ev, data1, len1, data2, len2)) + if (fn(tool, map, &ev, data1, len1, data2, len2)) return -1; mm->prev = head; @@ -1300,18 +1304,18 @@ static int __auxtrace_mmap__read(struct auxtrace_mmap *mm, return 1; } -int auxtrace_mmap__read(struct auxtrace_mmap *mm, struct auxtrace_record *itr, +int auxtrace_mmap__read(struct perf_mmap *map, struct auxtrace_record *itr, struct perf_tool *tool, process_auxtrace_t fn) { - return __auxtrace_mmap__read(mm, itr, tool, fn, false, 0); + return __auxtrace_mmap__read(map, itr, tool, fn, false, 0); } -int auxtrace_mmap__read_snapshot(struct auxtrace_mmap *mm, +int auxtrace_mmap__read_snapshot(struct perf_mmap *map, struct auxtrace_record *itr, struct perf_tool *tool, process_auxtrace_t fn, size_t snapshot_size) { - return __auxtrace_mmap__read(mm, itr, tool, fn, true, snapshot_size); + return __auxtrace_mmap__read(map, itr, tool, fn, true, snapshot_size); } /** diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h index e731f55da072..d88f6e9eb461 100644 --- a/tools/perf/util/auxtrace.h +++ b/tools/perf/util/auxtrace.h @@ -23,6 +23,7 @@ #include <linux/list.h> #include <linux/perf_event.h> #include <linux/types.h> +#include <asm/bitsperlong.h> #include "../perf.h" #include "event.h" @@ -33,6 +34,7 @@ union perf_event; struct perf_session; struct perf_evlist; struct perf_tool; +struct perf_mmap; struct option; struct record_opts; struct auxtrace_info_event; @@ -44,6 +46,7 @@ enum auxtrace_type { PERF_AUXTRACE_INTEL_BTS, PERF_AUXTRACE_CS_ETM, PERF_AUXTRACE_ARM_SPE, + PERF_AUXTRACE_S390_CPUMSF, }; enum itrace_period_type { @@ -433,13 +436,14 @@ void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp, bool per_cpu); typedef int (*process_auxtrace_t)(struct perf_tool *tool, + struct perf_mmap *map, union perf_event *event, void *data1, size_t len1, void *data2, size_t len2); -int auxtrace_mmap__read(struct auxtrace_mmap *mm, struct auxtrace_record *itr, +int auxtrace_mmap__read(struct perf_mmap *map, struct auxtrace_record *itr, struct perf_tool *tool, process_auxtrace_t fn); -int auxtrace_mmap__read_snapshot(struct auxtrace_mmap *mm, +int auxtrace_mmap__read_snapshot(struct perf_mmap *map, struct auxtrace_record *itr, struct perf_tool *tool, process_auxtrace_t fn, size_t snapshot_size); @@ -516,15 +520,12 @@ int perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr, struct perf_tool *tool, struct perf_session *session, perf_event__handler_t process); -int perf_event__process_auxtrace_info(struct perf_tool *tool, - union perf_event *event, - struct perf_session *session); -s64 perf_event__process_auxtrace(struct perf_tool *tool, - union perf_event *event, - struct perf_session *session); -int perf_event__process_auxtrace_error(struct perf_tool *tool, - union perf_event *event, - struct perf_session *session); +int perf_event__process_auxtrace_info(struct perf_session *session, + union perf_event *event); +s64 perf_event__process_auxtrace(struct perf_session *session, + union perf_event *event); +int perf_event__process_auxtrace_error(struct perf_session *session, + union perf_event *event); int itrace_parse_synth_opts(const struct option *opt, const char *str, int unset); void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts); @@ -576,6 +577,23 @@ static inline void auxtrace__free(struct perf_session *session) return session->auxtrace->free(session); } +#define ITRACE_HELP \ +" i: synthesize instructions events\n" \ +" b: synthesize branches events\n" \ +" c: synthesize branches events (calls only)\n" \ +" r: synthesize branches events (returns only)\n" \ +" x: synthesize transactions events\n" \ +" w: synthesize ptwrite events\n" \ +" p: synthesize power events\n" \ +" e: synthesize error events\n" \ +" d: create a debug log\n" \ +" g[len]: synthesize a call chain (use with i or x)\n" \ +" l[len]: synthesize last branch entries (use with i or x)\n" \ +" sNUMBER: skip initial number of events\n" \ +" PERIOD[ns|us|ms|i|t]: specify period to sample stream\n" \ +" concatenate multiple options. Default is ibxwpe or cewp\n" + + #else static inline struct auxtrace_record * @@ -716,6 +734,8 @@ void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp, struct perf_evlist *evlist, int idx, bool per_cpu); +#define ITRACE_HELP "" + #endif #endif diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c index cee658733e2c..f9ae1a993806 100644 --- a/tools/perf/util/bpf-loader.c +++ b/tools/perf/util/bpf-loader.c @@ -747,7 +747,9 @@ int bpf__load(struct bpf_object *obj) err = bpf_object__load(obj); if (err) { - pr_debug("bpf: load objects failed\n"); + char bf[128]; + libbpf_strerror(err, bf, sizeof(bf)); + pr_debug("bpf: load objects failed: err=%d: (%s)\n", err, bf); return err; } return 0; @@ -1527,13 +1529,13 @@ int bpf__apply_obj_config(void) bpf_object__for_each_safe(obj, objtmp) \ bpf_map__for_each(pos, obj) -#define bpf__for_each_stdout_map(pos, obj, objtmp) \ +#define bpf__for_each_map_named(pos, obj, objtmp, name) \ bpf__for_each_map(pos, obj, objtmp) \ if (bpf_map__name(pos) && \ - (strcmp("__bpf_stdout__", \ + (strcmp(name, \ bpf_map__name(pos)) == 0)) -int bpf__setup_stdout(struct perf_evlist *evlist) +struct perf_evsel *bpf__setup_output_event(struct perf_evlist *evlist, const char *name) { struct bpf_map_priv *tmpl_priv = NULL; struct bpf_object *obj, *tmp; @@ -1542,11 +1544,11 @@ int bpf__setup_stdout(struct perf_evlist *evlist) int err; bool need_init = false; - bpf__for_each_stdout_map(map, obj, tmp) { + bpf__for_each_map_named(map, obj, tmp, name) { struct bpf_map_priv *priv = bpf_map__priv(map); if (IS_ERR(priv)) - return -BPF_LOADER_ERRNO__INTERNAL; + return ERR_PTR(-BPF_LOADER_ERRNO__INTERNAL); /* * No need to check map type: type should have been @@ -1559,49 +1561,61 @@ int bpf__setup_stdout(struct perf_evlist *evlist) } if (!need_init) - return 0; + return NULL; if (!tmpl_priv) { - err = parse_events(evlist, "bpf-output/no-inherit=1,name=__bpf_stdout__/", - NULL); + char *event_definition = NULL; + + if (asprintf(&event_definition, "bpf-output/no-inherit=1,name=%s/", name) < 0) + return ERR_PTR(-ENOMEM); + + err = parse_events(evlist, event_definition, NULL); + free(event_definition); + if (err) { - pr_debug("ERROR: failed to create bpf-output event\n"); - return -err; + pr_debug("ERROR: failed to create the \"%s\" bpf-output event\n", name); + return ERR_PTR(-err); } evsel = perf_evlist__last(evlist); } - bpf__for_each_stdout_map(map, obj, tmp) { + bpf__for_each_map_named(map, obj, tmp, name) { struct bpf_map_priv *priv = bpf_map__priv(map); if (IS_ERR(priv)) - return -BPF_LOADER_ERRNO__INTERNAL; + return ERR_PTR(-BPF_LOADER_ERRNO__INTERNAL); if (priv) continue; if (tmpl_priv) { priv = bpf_map_priv__clone(tmpl_priv); if (!priv) - return -ENOMEM; + return ERR_PTR(-ENOMEM); err = bpf_map__set_priv(map, priv, bpf_map_priv__clear); if (err) { bpf_map_priv__clear(map, priv); - return err; + return ERR_PTR(err); } } else if (evsel) { struct bpf_map_op *op; op = bpf_map__add_newop(map, NULL); if (IS_ERR(op)) - return PTR_ERR(op); + return ERR_PTR(PTR_ERR(op)); op->op_type = BPF_MAP_OP_SET_EVSEL; op->v.evsel = evsel; } } - return 0; + return evsel; +} + +int bpf__setup_stdout(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel = bpf__setup_output_event(evlist, "__bpf_stdout__"); + return PTR_ERR_OR_ZERO(evsel); } #define ERRNO_OFFSET(e) ((e) - __BPF_LOADER_ERRNO__START) @@ -1778,8 +1792,8 @@ int bpf__strerror_apply_obj_config(int err, char *buf, size_t size) return 0; } -int bpf__strerror_setup_stdout(struct perf_evlist *evlist __maybe_unused, - int err, char *buf, size_t size) +int bpf__strerror_setup_output_event(struct perf_evlist *evlist __maybe_unused, + int err, char *buf, size_t size) { bpf__strerror_head(err, buf, size); bpf__strerror_end(buf, size); diff --git a/tools/perf/util/bpf-loader.h b/tools/perf/util/bpf-loader.h index 5d3aefd6fae7..62d245a90e1d 100644 --- a/tools/perf/util/bpf-loader.h +++ b/tools/perf/util/bpf-loader.h @@ -43,6 +43,7 @@ enum bpf_loader_errno { __BPF_LOADER_ERRNO__END, }; +struct perf_evsel; struct bpf_object; struct parse_events_term; #define PERF_BPF_PROBE_GROUP "perf_bpf_probe" @@ -82,9 +83,8 @@ int bpf__apply_obj_config(void); int bpf__strerror_apply_obj_config(int err, char *buf, size_t size); int bpf__setup_stdout(struct perf_evlist *evlist); -int bpf__strerror_setup_stdout(struct perf_evlist *evlist, int err, - char *buf, size_t size); - +struct perf_evsel *bpf__setup_output_event(struct perf_evlist *evlist, const char *name); +int bpf__strerror_setup_output_event(struct perf_evlist *evlist, int err, char *buf, size_t size); #else #include <errno.h> @@ -138,6 +138,12 @@ bpf__setup_stdout(struct perf_evlist *evlist __maybe_unused) return 0; } +static inline struct perf_evsel * +bpf__setup_output_event(struct perf_evlist *evlist __maybe_unused, const char *name __maybe_unused) +{ + return NULL; +} + static inline int __bpf_strerror(char *buf, size_t size) { @@ -193,11 +199,16 @@ bpf__strerror_apply_obj_config(int err __maybe_unused, } static inline int -bpf__strerror_setup_stdout(struct perf_evlist *evlist __maybe_unused, - int err __maybe_unused, char *buf, - size_t size) +bpf__strerror_setup_output_event(struct perf_evlist *evlist __maybe_unused, + int err __maybe_unused, char *buf, size_t size) { return __bpf_strerror(buf, size); } + #endif + +static inline int bpf__strerror_setup_stdout(struct perf_evlist *evlist, int err, char *buf, size_t size) +{ + return bpf__strerror_setup_output_event(evlist, err, buf, size); +} #endif diff --git a/tools/perf/util/comm.c b/tools/perf/util/comm.c index 7798a2cc8a86..31279a7bd919 100644 --- a/tools/perf/util/comm.c +++ b/tools/perf/util/comm.c @@ -20,9 +20,10 @@ static struct rw_semaphore comm_str_lock = {.lock = PTHREAD_RWLOCK_INITIALIZER,} static struct comm_str *comm_str__get(struct comm_str *cs) { - if (cs) - refcount_inc(&cs->refcnt); - return cs; + if (cs && refcount_inc_not_zero(&cs->refcnt)) + return cs; + + return NULL; } static void comm_str__put(struct comm_str *cs) @@ -67,9 +68,14 @@ struct comm_str *__comm_str__findnew(const char *str, struct rb_root *root) parent = *p; iter = rb_entry(parent, struct comm_str, rb_node); + /* + * If we race with comm_str__put, iter->refcnt is 0 + * and it will be removed within comm_str__put call + * shortly, ignore it in this search. + */ cmp = strcmp(str, iter->str); - if (!cmp) - return comm_str__get(iter); + if (!cmp && comm_str__get(iter)) + return iter; if (cmp < 0) p = &(*p)->rb_left; diff --git a/tools/perf/util/compress.h b/tools/perf/util/compress.h index ecca688a25fb..892e92e7e7fc 100644 --- a/tools/perf/util/compress.h +++ b/tools/perf/util/compress.h @@ -4,10 +4,12 @@ #ifdef HAVE_ZLIB_SUPPORT int gzip_decompress_to_file(const char *input, int output_fd); +bool gzip_is_compressed(const char *input); #endif #ifdef HAVE_LZMA_SUPPORT int lzma_decompress_to_file(const char *input, int output_fd); +bool lzma_is_compressed(const char *input); #endif #endif /* PERF_COMPRESS_H */ diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c index 4d5fc374e730..938def6d0bb9 100644 --- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c +++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c @@ -31,6 +31,8 @@ #endif #endif +#define CS_ETM_INVAL_ADDR 0xdeadbeefdeadbeefUL + struct cs_etm_decoder { void *data; void (*packet_printer)(const char *msg); @@ -261,8 +263,8 @@ static void cs_etm_decoder__clear_buffer(struct cs_etm_decoder *decoder) decoder->tail = 0; decoder->packet_count = 0; for (i = 0; i < MAX_BUFFER; i++) { - decoder->packet_buffer[i].start_addr = 0xdeadbeefdeadbeefUL; - decoder->packet_buffer[i].end_addr = 0xdeadbeefdeadbeefUL; + decoder->packet_buffer[i].start_addr = CS_ETM_INVAL_ADDR; + decoder->packet_buffer[i].end_addr = CS_ETM_INVAL_ADDR; decoder->packet_buffer[i].last_instr_taken_branch = false; decoder->packet_buffer[i].exc = false; decoder->packet_buffer[i].exc_ret = false; @@ -295,8 +297,8 @@ cs_etm_decoder__buffer_packet(struct cs_etm_decoder *decoder, decoder->packet_buffer[et].exc = false; decoder->packet_buffer[et].exc_ret = false; decoder->packet_buffer[et].cpu = *((int *)inode->priv); - decoder->packet_buffer[et].start_addr = 0xdeadbeefdeadbeefUL; - decoder->packet_buffer[et].end_addr = 0xdeadbeefdeadbeefUL; + decoder->packet_buffer[et].start_addr = CS_ETM_INVAL_ADDR; + decoder->packet_buffer[et].end_addr = CS_ETM_INVAL_ADDR; if (decoder->packet_count == MAX_BUFFER - 1) return OCSD_RESP_WAIT; diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h index 743f5f444304..612b5755f742 100644 --- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h +++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h @@ -23,6 +23,7 @@ struct cs_etm_buffer { }; enum cs_etm_sample_type { + CS_ETM_EMPTY = 0, CS_ETM_RANGE = 1 << 0, CS_ETM_TRACE_ON = 1 << 1, }; diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 822ba915d144..2ae640257fdb 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -494,6 +494,10 @@ static inline void cs_etm__reset_last_branch_rb(struct cs_etm_queue *etmq) static inline u64 cs_etm__last_executed_instr(struct cs_etm_packet *packet) { + /* Returns 0 for the CS_ETM_TRACE_ON packet */ + if (packet->sample_type == CS_ETM_TRACE_ON) + return 0; + /* * The packet records the execution range with an exclusive end address * @@ -505,6 +509,15 @@ static inline u64 cs_etm__last_executed_instr(struct cs_etm_packet *packet) return packet->end_addr - A64_INSTR_SIZE; } +static inline u64 cs_etm__first_executed_instr(struct cs_etm_packet *packet) +{ + /* Returns 0 for the CS_ETM_TRACE_ON packet */ + if (packet->sample_type == CS_ETM_TRACE_ON) + return 0; + + return packet->start_addr; +} + static inline u64 cs_etm__instr_count(const struct cs_etm_packet *packet) { /* @@ -546,7 +559,7 @@ static void cs_etm__update_last_branch_rb(struct cs_etm_queue *etmq) be = &bs->entries[etmq->last_branch_pos]; be->from = cs_etm__last_executed_instr(etmq->prev_packet); - be->to = etmq->packet->start_addr; + be->to = cs_etm__first_executed_instr(etmq->packet); /* No support for mispredict */ be->flags.mispred = 0; be->flags.predicted = 1; @@ -701,7 +714,7 @@ static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq) sample.ip = cs_etm__last_executed_instr(etmq->prev_packet); sample.pid = etmq->pid; sample.tid = etmq->tid; - sample.addr = etmq->packet->start_addr; + sample.addr = cs_etm__first_executed_instr(etmq->packet); sample.id = etmq->etm->branches_id; sample.stream_id = etmq->etm->branches_id; sample.period = 1; @@ -897,13 +910,23 @@ static int cs_etm__sample(struct cs_etm_queue *etmq) etmq->period_instructions = instrs_over; } - if (etm->sample_branches && - etmq->prev_packet && - etmq->prev_packet->sample_type == CS_ETM_RANGE && - etmq->prev_packet->last_instr_taken_branch) { - ret = cs_etm__synth_branch_sample(etmq); - if (ret) - return ret; + if (etm->sample_branches && etmq->prev_packet) { + bool generate_sample = false; + + /* Generate sample for tracing on packet */ + if (etmq->prev_packet->sample_type == CS_ETM_TRACE_ON) + generate_sample = true; + + /* Generate sample for branch taken packet */ + if (etmq->prev_packet->sample_type == CS_ETM_RANGE && + etmq->prev_packet->last_instr_taken_branch) + generate_sample = true; + + if (generate_sample) { + ret = cs_etm__synth_branch_sample(etmq); + if (ret) + return ret; + } } if (etm->sample_branches || etm->synth_opts.last_branch) { @@ -922,10 +945,17 @@ static int cs_etm__sample(struct cs_etm_queue *etmq) static int cs_etm__flush(struct cs_etm_queue *etmq) { int err = 0; + struct cs_etm_auxtrace *etm = etmq->etm; struct cs_etm_packet *tmp; + if (!etmq->prev_packet) + return 0; + + /* Handle start tracing packet */ + if (etmq->prev_packet->sample_type == CS_ETM_EMPTY) + goto swap_packet; + if (etmq->etm->synth_opts.last_branch && - etmq->prev_packet && etmq->prev_packet->sample_type == CS_ETM_RANGE) { /* * Generate a last branch event for the branches left in the @@ -939,8 +969,22 @@ static int cs_etm__flush(struct cs_etm_queue *etmq) err = cs_etm__synth_instruction_sample( etmq, addr, etmq->period_instructions); + if (err) + return err; + etmq->period_instructions = 0; + } + + if (etm->sample_branches && + etmq->prev_packet->sample_type == CS_ETM_RANGE) { + err = cs_etm__synth_branch_sample(etmq); + if (err) + return err; + } + +swap_packet: + if (etmq->etm->synth_opts.last_branch) { /* * Swap PACKET with PREV_PACKET: PACKET becomes PREV_PACKET for * the next incoming packet. @@ -1020,6 +1064,13 @@ static int cs_etm__run_decoder(struct cs_etm_queue *etmq) */ cs_etm__flush(etmq); break; + case CS_ETM_EMPTY: + /* + * Should not receive empty packet, + * report error. + */ + pr_err("CS ETM Trace: empty packet\n"); + return -EINVAL; default: break; } diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c index 5744c12641a5..2a36fab76994 100644 --- a/tools/perf/util/data-convert-bt.c +++ b/tools/perf/util/data-convert-bt.c @@ -182,20 +182,20 @@ err_put_field: } static struct bt_ctf_field_type* -get_tracepoint_field_type(struct ctf_writer *cw, struct format_field *field) +get_tracepoint_field_type(struct ctf_writer *cw, struct tep_format_field *field) { unsigned long flags = field->flags; - if (flags & FIELD_IS_STRING) + if (flags & TEP_FIELD_IS_STRING) return cw->data.string; - if (!(flags & FIELD_IS_SIGNED)) { + if (!(flags & TEP_FIELD_IS_SIGNED)) { /* unsigned long are mostly pointers */ - if (flags & FIELD_IS_LONG || flags & FIELD_IS_POINTER) + if (flags & TEP_FIELD_IS_LONG || flags & TEP_FIELD_IS_POINTER) return cw->data.u64_hex; } - if (flags & FIELD_IS_SIGNED) { + if (flags & TEP_FIELD_IS_SIGNED) { if (field->size == 8) return cw->data.s64; else @@ -287,7 +287,7 @@ static int add_tracepoint_field_value(struct ctf_writer *cw, struct bt_ctf_event_class *event_class, struct bt_ctf_event *event, struct perf_sample *sample, - struct format_field *fmtf) + struct tep_format_field *fmtf) { struct bt_ctf_field_type *type; struct bt_ctf_field *array_field; @@ -304,20 +304,20 @@ static int add_tracepoint_field_value(struct ctf_writer *cw, name = fmtf->alias; offset = fmtf->offset; len = fmtf->size; - if (flags & FIELD_IS_STRING) - flags &= ~FIELD_IS_ARRAY; + if (flags & TEP_FIELD_IS_STRING) + flags &= ~TEP_FIELD_IS_ARRAY; - if (flags & FIELD_IS_DYNAMIC) { + if (flags & TEP_FIELD_IS_DYNAMIC) { unsigned long long tmp_val; - tmp_val = pevent_read_number(fmtf->event->pevent, - data + offset, len); + tmp_val = tep_read_number(fmtf->event->pevent, + data + offset, len); offset = tmp_val; len = offset >> 16; offset &= 0xffff; } - if (flags & FIELD_IS_ARRAY) { + if (flags & TEP_FIELD_IS_ARRAY) { type = bt_ctf_event_class_get_field_by_name( event_class, name); @@ -338,7 +338,7 @@ static int add_tracepoint_field_value(struct ctf_writer *cw, type = get_tracepoint_field_type(cw, fmtf); for (i = 0; i < n_items; i++) { - if (flags & FIELD_IS_ARRAY) + if (flags & TEP_FIELD_IS_ARRAY) field = bt_ctf_field_array_get_field(array_field, i); else field = bt_ctf_field_create(type); @@ -348,16 +348,16 @@ static int add_tracepoint_field_value(struct ctf_writer *cw, return -1; } - if (flags & FIELD_IS_STRING) + if (flags & TEP_FIELD_IS_STRING) ret = string_set_value(field, data + offset + i * len); else { unsigned long long value_int; - value_int = pevent_read_number( + value_int = tep_read_number( fmtf->event->pevent, data + offset + i * len, len); - if (!(flags & FIELD_IS_SIGNED)) + if (!(flags & TEP_FIELD_IS_SIGNED)) ret = bt_ctf_field_unsigned_integer_set_value( field, value_int); else @@ -369,7 +369,7 @@ static int add_tracepoint_field_value(struct ctf_writer *cw, pr_err("failed to set file value %s\n", name); goto err_put_field; } - if (!(flags & FIELD_IS_ARRAY)) { + if (!(flags & TEP_FIELD_IS_ARRAY)) { ret = bt_ctf_event_set_payload(event, name, field); if (ret) { pr_err("failed to set payload %s\n", name); @@ -378,7 +378,7 @@ static int add_tracepoint_field_value(struct ctf_writer *cw, } bt_ctf_field_put(field); } - if (flags & FIELD_IS_ARRAY) { + if (flags & TEP_FIELD_IS_ARRAY) { ret = bt_ctf_event_set_payload(event, name, array_field); if (ret) { pr_err("Failed add payload array %s\n", name); @@ -396,10 +396,10 @@ err_put_field: static int add_tracepoint_fields_values(struct ctf_writer *cw, struct bt_ctf_event_class *event_class, struct bt_ctf_event *event, - struct format_field *fields, + struct tep_format_field *fields, struct perf_sample *sample) { - struct format_field *field; + struct tep_format_field *field; int ret; for (field = fields; field; field = field->next) { @@ -417,8 +417,8 @@ static int add_tracepoint_values(struct ctf_writer *cw, struct perf_evsel *evsel, struct perf_sample *sample) { - struct format_field *common_fields = evsel->tp_format->format.common_fields; - struct format_field *fields = evsel->tp_format->format.fields; + struct tep_format_field *common_fields = evsel->tp_format->format.common_fields; + struct tep_format_field *fields = evsel->tp_format->format.fields; int ret; ret = add_tracepoint_fields_values(cw, event_class, event, @@ -970,7 +970,7 @@ out: static int event_class_add_field(struct bt_ctf_event_class *event_class, struct bt_ctf_field_type *type, - struct format_field *field) + struct tep_format_field *field) { struct bt_ctf_field_type *t = NULL; char *name; @@ -1009,10 +1009,10 @@ static int event_class_add_field(struct bt_ctf_event_class *event_class, } static int add_tracepoint_fields_types(struct ctf_writer *cw, - struct format_field *fields, + struct tep_format_field *fields, struct bt_ctf_event_class *event_class) { - struct format_field *field; + struct tep_format_field *field; int ret; for (field = fields; field; field = field->next) { @@ -1030,15 +1030,15 @@ static int add_tracepoint_fields_types(struct ctf_writer *cw, * type and don't care that it is an array. What we don't * support is an array of strings. */ - if (flags & FIELD_IS_STRING) - flags &= ~FIELD_IS_ARRAY; + if (flags & TEP_FIELD_IS_STRING) + flags &= ~TEP_FIELD_IS_ARRAY; - if (flags & FIELD_IS_ARRAY) + if (flags & TEP_FIELD_IS_ARRAY) type = bt_ctf_field_type_array_create(type, field->arraylen); ret = event_class_add_field(event_class, type, field); - if (flags & FIELD_IS_ARRAY) + if (flags & TEP_FIELD_IS_ARRAY) bt_ctf_field_type_put(type); if (ret) { @@ -1055,8 +1055,8 @@ static int add_tracepoint_types(struct ctf_writer *cw, struct perf_evsel *evsel, struct bt_ctf_event_class *class) { - struct format_field *common_fields = evsel->tp_format->format.common_fields; - struct format_field *fields = evsel->tp_format->format.fields; + struct tep_format_field *common_fields = evsel->tp_format->format.common_fields; + struct tep_format_field *fields = evsel->tp_format->format.fields; int ret; ret = add_tracepoint_fields_types(cw, common_fields, class); @@ -1578,7 +1578,7 @@ int bt_convert__perf2ctf(const char *input, const char *path, { struct perf_session *session; struct perf_data data = { - .file.path = input, + .file = { .path = input, .fd = -1 }, .mode = PERF_DATA_MODE_READ, .force = opts->force, }; diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c index 7123746edcf4..69fbb0a72d0c 100644 --- a/tools/perf/util/db-export.c +++ b/tools/perf/util/db-export.c @@ -463,6 +463,28 @@ int db_export__branch_types(struct db_export *dbe) if (err) break; } + + /* Add trace begin / end variants */ + for (i = 0; branch_types[i].name ; i++) { + const char *name = branch_types[i].name; + u32 type = branch_types[i].branch_type; + char buf[64]; + + if (type == PERF_IP_FLAG_BRANCH || + (type & (PERF_IP_FLAG_TRACE_BEGIN | PERF_IP_FLAG_TRACE_END))) + continue; + + snprintf(buf, sizeof(buf), "trace begin / %s", name); + err = db_export__branch_type(dbe, type | PERF_IP_FLAG_TRACE_BEGIN, buf); + if (err) + break; + + snprintf(buf, sizeof(buf), "%s / trace end", name); + err = db_export__branch_type(dbe, type | PERF_IP_FLAG_TRACE_END, buf); + if (err) + break; + } + return err; } diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index 51cf82cf1882..bbed90e5d9bb 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -189,28 +189,34 @@ int dso__read_binary_type_filename(const struct dso *dso, return ret; } +enum { + COMP_ID__NONE = 0, +}; + static const struct { const char *fmt; int (*decompress)(const char *input, int output); + bool (*is_compressed)(const char *input); } compressions[] = { + [COMP_ID__NONE] = { .fmt = NULL, }, #ifdef HAVE_ZLIB_SUPPORT - { "gz", gzip_decompress_to_file }, + { "gz", gzip_decompress_to_file, gzip_is_compressed }, #endif #ifdef HAVE_LZMA_SUPPORT - { "xz", lzma_decompress_to_file }, + { "xz", lzma_decompress_to_file, lzma_is_compressed }, #endif - { NULL, NULL }, + { NULL, NULL, NULL }, }; -bool is_supported_compression(const char *ext) +static int is_supported_compression(const char *ext) { unsigned i; - for (i = 0; compressions[i].fmt; i++) { + for (i = 1; compressions[i].fmt; i++) { if (!strcmp(ext, compressions[i].fmt)) - return true; + return i; } - return false; + return COMP_ID__NONE; } bool is_kernel_module(const char *pathname, int cpumode) @@ -239,80 +245,73 @@ bool is_kernel_module(const char *pathname, int cpumode) return m.kmod; } -bool decompress_to_file(const char *ext, const char *filename, int output_fd) -{ - unsigned i; - - for (i = 0; compressions[i].fmt; i++) { - if (!strcmp(ext, compressions[i].fmt)) - return !compressions[i].decompress(filename, - output_fd); - } - return false; -} - bool dso__needs_decompress(struct dso *dso) { return dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP || dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE_COMP; } -static int decompress_kmodule(struct dso *dso, const char *name, char *tmpbuf) +static int decompress_kmodule(struct dso *dso, const char *name, + char *pathname, size_t len) { + char tmpbuf[] = KMOD_DECOMP_NAME; int fd = -1; - struct kmod_path m; if (!dso__needs_decompress(dso)) return -1; - if (kmod_path__parse_ext(&m, dso->long_name)) + if (dso->comp == COMP_ID__NONE) return -1; - if (!m.comp) - goto out; + /* + * We have proper compression id for DSO and yet the file + * behind the 'name' can still be plain uncompressed object. + * + * The reason is behind the logic we open the DSO object files, + * when we try all possible 'debug' objects until we find the + * data. So even if the DSO is represented by 'krava.xz' module, + * we can end up here opening ~/.debug/....23432432/debug' file + * which is not compressed. + * + * To keep this transparent, we detect this and return the file + * descriptor to the uncompressed file. + */ + if (!compressions[dso->comp].is_compressed(name)) + return open(name, O_RDONLY); fd = mkstemp(tmpbuf); if (fd < 0) { dso->load_errno = errno; - goto out; + return -1; } - if (!decompress_to_file(m.ext, name, fd)) { + if (compressions[dso->comp].decompress(name, fd)) { dso->load_errno = DSO_LOAD_ERRNO__DECOMPRESSION_FAILURE; close(fd); fd = -1; } -out: - free(m.ext); + if (!pathname || (fd < 0)) + unlink(tmpbuf); + + if (pathname && (fd >= 0)) + strncpy(pathname, tmpbuf, len); + return fd; } int dso__decompress_kmodule_fd(struct dso *dso, const char *name) { - char tmpbuf[] = KMOD_DECOMP_NAME; - int fd; - - fd = decompress_kmodule(dso, name, tmpbuf); - unlink(tmpbuf); - return fd; + return decompress_kmodule(dso, name, NULL, 0); } int dso__decompress_kmodule_path(struct dso *dso, const char *name, char *pathname, size_t len) { - char tmpbuf[] = KMOD_DECOMP_NAME; - int fd; + int fd = decompress_kmodule(dso, name, pathname, len); - fd = decompress_kmodule(dso, name, tmpbuf); - if (fd < 0) { - unlink(tmpbuf); - return -1; - } - - strncpy(pathname, tmpbuf, len); close(fd); - return 0; + return fd >= 0 ? 0 : -1; } /* @@ -332,7 +331,7 @@ int dso__decompress_kmodule_path(struct dso *dso, const char *name, * Returns 0 if there's no strdup error, -ENOMEM otherwise. */ int __kmod_path__parse(struct kmod_path *m, const char *path, - bool alloc_name, bool alloc_ext) + bool alloc_name) { const char *name = strrchr(path, '/'); const char *ext = strrchr(path, '.'); @@ -372,10 +371,9 @@ int __kmod_path__parse(struct kmod_path *m, const char *path, return 0; } - if (is_supported_compression(ext + 1)) { - m->comp = true; + m->comp = is_supported_compression(ext + 1); + if (m->comp > COMP_ID__NONE) ext -= 3; - } /* Check .ko extension only if there's enough name left. */ if (ext > name) @@ -393,14 +391,6 @@ int __kmod_path__parse(struct kmod_path *m, const char *path, strxfrchar(m->name, '-', '_'); } - if (alloc_ext && m->comp) { - m->ext = strdup(ext + 4); - if (!m->ext) { - free((void *) m->name); - return -ENOMEM; - } - } - return 0; } @@ -413,8 +403,10 @@ void dso__set_module_info(struct dso *dso, struct kmod_path *m, dso->symtab_type = DSO_BINARY_TYPE__GUEST_KMODULE; /* _KMODULE_COMP should be next to _KMODULE */ - if (m->kmod && m->comp) + if (m->kmod && m->comp) { dso->symtab_type++; + dso->comp = m->comp; + } dso__set_short_name(dso, strdup(m->name), true); } @@ -468,6 +460,7 @@ static int __open_dso(struct dso *dso, struct machine *machine) int fd = -EINVAL; char *root_dir = (char *)""; char *name = malloc(PATH_MAX); + bool decomp = false; if (!name) return -ENOMEM; @@ -491,12 +484,13 @@ static int __open_dso(struct dso *dso, struct machine *machine) goto out; } + decomp = true; strcpy(name, newpath); } fd = do_open(name); - if (dso__needs_decompress(dso)) + if (decomp) unlink(name); out: @@ -1218,6 +1212,7 @@ struct dso *dso__new(const char *name) dso->a2l_fails = 1; dso->kernel = DSO_TYPE_USER; dso->needs_swap = DSO_SWAP__UNSET; + dso->comp = COMP_ID__NONE; RB_CLEAR_NODE(&dso->rb_node); dso->root = NULL; INIT_LIST_HEAD(&dso->node); diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h index ef69de2e69ea..c5380500bed4 100644 --- a/tools/perf/util/dso.h +++ b/tools/perf/util/dso.h @@ -175,6 +175,7 @@ struct dso { u16 short_name_len; void *dwfl; /* DWARF debug info */ struct auxtrace_cache *auxtrace_cache; + int comp; /* dso data file */ struct { @@ -250,9 +251,7 @@ int dso__kernel_module_get_build_id(struct dso *dso, const char *root_dir); char dso__symtab_origin(const struct dso *dso); int dso__read_binary_type_filename(const struct dso *dso, enum dso_binary_type type, char *root_dir, char *filename, size_t size); -bool is_supported_compression(const char *ext); bool is_kernel_module(const char *pathname, int cpumode); -bool decompress_to_file(const char *ext, const char *filename, int output_fd); bool dso__needs_decompress(struct dso *dso); int dso__decompress_kmodule_fd(struct dso *dso, const char *name); int dso__decompress_kmodule_path(struct dso *dso, const char *name, @@ -263,17 +262,15 @@ int dso__decompress_kmodule_path(struct dso *dso, const char *name, struct kmod_path { char *name; - char *ext; - bool comp; + int comp; bool kmod; }; int __kmod_path__parse(struct kmod_path *m, const char *path, - bool alloc_name, bool alloc_ext); + bool alloc_name); -#define kmod_path__parse(__m, __p) __kmod_path__parse(__m, __p, false, false) -#define kmod_path__parse_name(__m, __p) __kmod_path__parse(__m, __p, true , false) -#define kmod_path__parse_ext(__m, __p) __kmod_path__parse(__m, __p, false, true) +#define kmod_path__parse(__m, __p) __kmod_path__parse(__m, __p, false) +#define kmod_path__parse_name(__m, __p) __kmod_path__parse(__m, __p, true) void dso__set_module_info(struct dso *dso, struct kmod_path *m, struct machine *machine); diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 0c8ecf0c78a4..bc646185f8d9 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -541,10 +541,17 @@ static int __event__synthesize_thread(union perf_event *comm_event, tgid, process, machine) < 0) return -1; + /* + * send mmap only for thread group leader + * see thread__init_map_groups + */ + if (pid == tgid && + perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid, + process, machine, mmap_data, + proc_map_timeout)) + return -1; - return perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid, - process, machine, mmap_data, - proc_map_timeout); + return 0; } if (machine__is_default_guest(machine)) @@ -1074,6 +1081,7 @@ void *cpu_map_data__alloc(struct cpu_map *map, size_t *size, u16 *type, int *max } *size += sizeof(struct cpu_map_data); + *size = PERF_ALIGN(*size, sizeof(u64)); return zalloc(*size); } @@ -1553,26 +1561,9 @@ struct map *thread__find_map(struct thread *thread, u8 cpumode, u64 addr, return NULL; } -try_again: + al->map = map_groups__find(mg, al->addr); - if (al->map == NULL) { - /* - * If this is outside of all known maps, and is a negative - * address, try to look it up in the kernel dso, as it might be - * a vsyscall or vdso (which executes in user-mode). - * - * XXX This is nasty, we should have a symbol list in the - * "[vdso]" dso, but for now lets use the old trick of looking - * in the whole kernel symbol list. - */ - if (cpumode == PERF_RECORD_MISC_USER && machine && - mg != &machine->kmaps && - machine__kernel_ip(machine, al->addr)) { - mg = &machine->kmaps; - load_map = true; - goto try_again; - } - } else { + if (al->map != NULL) { /* * Kernel maps might be changed when loading symbols so loading * must be done prior to using kernel maps. diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index e7a4b31a84fb..be440df29615 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -803,7 +803,7 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx, if (*output == -1) { *output = fd; - if (perf_mmap__mmap(&maps[idx], mp, *output) < 0) + if (perf_mmap__mmap(&maps[idx], mp, *output, evlist_cpu) < 0) return -1; } else { if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, *output) != 0) diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 94fce4f537e9..29d7b97f66fb 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -251,8 +251,9 @@ struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx) { struct perf_evsel *evsel = zalloc(perf_evsel__object.size); - if (evsel != NULL) - perf_evsel__init(evsel, attr, idx); + if (!evsel) + return NULL; + perf_evsel__init(evsel, attr, idx); if (perf_evsel__is_bpf_output(evsel)) { evsel->attr.sample_type |= (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | @@ -260,6 +261,17 @@ struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx) evsel->attr.sample_period = 1; } + if (perf_evsel__is_clock(evsel)) { + /* + * The evsel->unit points to static alias->unit + * so it's ok to use static string in here. + */ + static const char *unit = "msec"; + + evsel->unit = unit; + evsel->scale = 1e-6; + } + return evsel; } @@ -848,6 +860,12 @@ static void apply_config_terms(struct perf_evsel *evsel, } } +static bool is_dummy_event(struct perf_evsel *evsel) +{ + return (evsel->attr.type == PERF_TYPE_SOFTWARE) && + (evsel->attr.config == PERF_COUNT_SW_DUMMY); +} + /* * The enable_on_exec/disabled value strategy: * @@ -1071,6 +1089,9 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts, attr->exclude_user = 1; } + if (evsel->own_cpus) + evsel->attr.read_format |= PERF_FORMAT_ID; + /* * Apply event specific term settings, * it overloads any global configuration. @@ -1086,6 +1107,14 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts, else perf_evsel__reset_sample_bit(evsel, PERIOD); } + + /* + * For initial_delay, a dummy event is added implicitly. + * The software event will trigger -EOPNOTSUPP error out, + * if BRANCH_STACK bit is set. + */ + if (opts->initial_delay && is_dummy_event(evsel)) + perf_evsel__reset_sample_bit(evsel, BRANCH_STACK); } static int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads) @@ -2656,15 +2685,15 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, return 0; } -struct format_field *perf_evsel__field(struct perf_evsel *evsel, const char *name) +struct tep_format_field *perf_evsel__field(struct perf_evsel *evsel, const char *name) { - return pevent_find_field(evsel->tp_format, name); + return tep_find_field(evsel->tp_format, name); } void *perf_evsel__rawptr(struct perf_evsel *evsel, struct perf_sample *sample, const char *name) { - struct format_field *field = perf_evsel__field(evsel, name); + struct tep_format_field *field = perf_evsel__field(evsel, name); int offset; if (!field) @@ -2672,7 +2701,7 @@ void *perf_evsel__rawptr(struct perf_evsel *evsel, struct perf_sample *sample, offset = field->offset; - if (field->flags & FIELD_IS_DYNAMIC) { + if (field->flags & TEP_FIELD_IS_DYNAMIC) { offset = *(int *)(sample->raw_data + field->offset); offset &= 0xffff; } @@ -2680,7 +2709,7 @@ void *perf_evsel__rawptr(struct perf_evsel *evsel, struct perf_sample *sample, return sample->raw_data + offset; } -u64 format_field__intval(struct format_field *field, struct perf_sample *sample, +u64 format_field__intval(struct tep_format_field *field, struct perf_sample *sample, bool needs_swap) { u64 value; @@ -2722,7 +2751,7 @@ u64 format_field__intval(struct format_field *field, struct perf_sample *sample, u64 perf_evsel__intval(struct perf_evsel *evsel, struct perf_sample *sample, const char *name) { - struct format_field *field = perf_evsel__field(evsel, name); + struct tep_format_field *field = perf_evsel__field(evsel, name); if (!field) return 0; @@ -2914,3 +2943,32 @@ struct perf_env *perf_evsel__env(struct perf_evsel *evsel) return evsel->evlist->env; return NULL; } + +static int store_evsel_ids(struct perf_evsel *evsel, struct perf_evlist *evlist) +{ + int cpu, thread; + + for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) { + for (thread = 0; thread < xyarray__max_y(evsel->fd); + thread++) { + int fd = FD(evsel, cpu, thread); + + if (perf_evlist__id_add_fd(evlist, evsel, + cpu, thread, fd) < 0) + return -1; + } + } + + return 0; +} + +int perf_evsel__store_ids(struct perf_evsel *evsel, struct perf_evlist *evlist) +{ + struct cpu_map *cpus = evsel->cpus; + struct thread_map *threads = evsel->threads; + + if (perf_evsel__alloc_id(evsel, cpus->nr, threads->nr)) + return -ENOMEM; + + return store_evsel_ids(evsel, evlist); +} diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index d277930b19a1..4107c39f4a54 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -102,7 +102,7 @@ struct perf_evsel { char *name; double scale; const char *unit; - struct event_format *tp_format; + struct tep_event_format *tp_format; off_t id_offset; struct perf_stat_evsel *stats; void *priv; @@ -211,7 +211,7 @@ static inline struct perf_evsel *perf_evsel__newtp(const char *sys, const char * struct perf_evsel *perf_evsel__new_cycles(bool precise); -struct event_format *event_format__new(const char *sys, const char *name); +struct tep_event_format *event_format__new(const char *sys, const char *name); void perf_evsel__init(struct perf_evsel *evsel, struct perf_event_attr *attr, int idx); @@ -296,11 +296,11 @@ static inline char *perf_evsel__strval(struct perf_evsel *evsel, return perf_evsel__rawptr(evsel, sample, name); } -struct format_field; +struct tep_format_field; -u64 format_field__intval(struct format_field *field, struct perf_sample *sample, bool needs_swap); +u64 format_field__intval(struct tep_format_field *field, struct perf_sample *sample, bool needs_swap); -struct format_field *perf_evsel__field(struct perf_evsel *evsel, const char *name); +struct tep_format_field *perf_evsel__field(struct perf_evsel *evsel, const char *name); #define perf_evsel__match(evsel, t, c) \ (evsel->attr.type == PERF_TYPE_##t && \ @@ -402,10 +402,13 @@ bool perf_evsel__is_function_event(struct perf_evsel *evsel); static inline bool perf_evsel__is_bpf_output(struct perf_evsel *evsel) { - struct perf_event_attr *attr = &evsel->attr; + return perf_evsel__match(evsel, SOFTWARE, SW_BPF_OUTPUT); +} - return (attr->config == PERF_COUNT_SW_BPF_OUTPUT) && - (attr->type == PERF_TYPE_SOFTWARE); +static inline bool perf_evsel__is_clock(struct perf_evsel *evsel) +{ + return perf_evsel__match(evsel, SOFTWARE, SW_CPU_CLOCK) || + perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK); } struct perf_attr_details { @@ -449,11 +452,18 @@ static inline int perf_evsel__group_idx(struct perf_evsel *evsel) return evsel->idx - evsel->leader->idx; } +/* Iterates group WITHOUT the leader. */ #define for_each_group_member(_evsel, _leader) \ for ((_evsel) = list_entry((_leader)->node.next, struct perf_evsel, node); \ (_evsel) && (_evsel)->leader == (_leader); \ (_evsel) = list_entry((_evsel)->node.next, struct perf_evsel, node)) +/* Iterates group WITH the leader. */ +#define for_each_group_evsel(_evsel, _leader) \ +for ((_evsel) = _leader; \ + (_evsel) && (_evsel)->leader == (_leader); \ + (_evsel) = list_entry((_evsel)->node.next, struct perf_evsel, node)) + static inline bool perf_evsel__has_branch_callstack(const struct perf_evsel *evsel) { return evsel->attr.branch_sample_type & PERF_SAMPLE_BRANCH_CALL_STACK; @@ -471,4 +481,5 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr, struct perf_env *perf_evsel__env(struct perf_evsel *evsel); +int perf_evsel__store_ids(struct perf_evsel *evsel, struct perf_evlist *evlist); #endif /* __PERF_EVSEL_H */ diff --git a/tools/perf/util/evsel_fprintf.c b/tools/perf/util/evsel_fprintf.c index 06dfb027879d..0d0a4c6f368b 100644 --- a/tools/perf/util/evsel_fprintf.c +++ b/tools/perf/util/evsel_fprintf.c @@ -73,7 +73,7 @@ int perf_evsel__fprintf(struct perf_evsel *evsel, } if (details->trace_fields) { - struct format_field *field; + struct tep_format_field *field; if (evsel->attr.type != PERF_TYPE_TRACEPOINT) { printed += comma_fprintf(fp, &first, " (not a tracepoint)"); diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 653ff65aa2c3..1ec1d9bc2d63 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -279,8 +279,6 @@ static int do_read_bitmap(struct feat_fd *ff, unsigned long **pset, u64 *psize) if (!set) return -ENOMEM; - bitmap_zero(set, size); - p = (u64 *) set; for (i = 0; (u64) i < BITS_TO_U64(size); i++) { @@ -1285,7 +1283,6 @@ static int memory_node__read(struct memory_node *n, unsigned long idx) return -ENOMEM; } - bitmap_zero(n->set, size); n->node = idx; n->size = size; @@ -2587,7 +2584,7 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = { FEAT_OPR(NUMA_TOPOLOGY, numa_topology, true), FEAT_OPN(BRANCH_STACK, branch_stack, false), FEAT_OPR(PMU_MAPPINGS, pmu_mappings, false), - FEAT_OPN(GROUP_DESC, group_desc, false), + FEAT_OPR(GROUP_DESC, group_desc, false), FEAT_OPN(AUXTRACE, auxtrace, false), FEAT_OPN(STAT, stat, false), FEAT_OPN(CACHE, cache, true), @@ -3207,9 +3204,9 @@ static int read_attr(int fd, struct perf_header *ph, } static int perf_evsel__prepare_tracepoint_event(struct perf_evsel *evsel, - struct pevent *pevent) + struct tep_handle *pevent) { - struct event_format *event; + struct tep_event_format *event; char bf[128]; /* already prepared */ @@ -3221,7 +3218,7 @@ static int perf_evsel__prepare_tracepoint_event(struct perf_evsel *evsel, return -1; } - event = pevent_find_event(pevent, evsel->attr.config); + event = tep_find_event(pevent, evsel->attr.config); if (event == NULL) { pr_debug("cannot find event format for %d\n", (int)evsel->attr.config); return -1; @@ -3239,7 +3236,7 @@ static int perf_evsel__prepare_tracepoint_event(struct perf_evsel *evsel, } static int perf_evlist__prepare_tracepoint_events(struct perf_evlist *evlist, - struct pevent *pevent) + struct tep_handle *pevent) { struct perf_evsel *pos; @@ -3451,10 +3448,10 @@ int perf_event__synthesize_features(struct perf_tool *tool, return ret; } -int perf_event__process_feature(struct perf_tool *tool, - union perf_event *event, - struct perf_session *session __maybe_unused) +int perf_event__process_feature(struct perf_session *session, + union perf_event *event) { + struct perf_tool *tool = session->tool; struct feat_fd ff = { .fd = 0 }; struct feature_event *fe = (struct feature_event *)event; int type = fe->header.type; @@ -3640,13 +3637,13 @@ size_t perf_event__fprintf_event_update(union perf_event *event, FILE *fp) } int perf_event__synthesize_attrs(struct perf_tool *tool, - struct perf_session *session, - perf_event__handler_t process) + struct perf_evlist *evlist, + perf_event__handler_t process) { struct perf_evsel *evsel; int err = 0; - evlist__for_each_entry(session->evlist, evsel) { + evlist__for_each_entry(evlist, evsel) { err = perf_event__synthesize_attr(tool, &evsel->attr, evsel->ids, evsel->id, process); if (err) { @@ -3859,9 +3856,8 @@ int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd, return aligned_size; } -int perf_event__process_tracing_data(struct perf_tool *tool __maybe_unused, - union perf_event *event, - struct perf_session *session) +int perf_event__process_tracing_data(struct perf_session *session, + union perf_event *event) { ssize_t size_read, padding, size = event->tracing_data.size; int fd = perf_data__fd(session->data); @@ -3927,9 +3923,8 @@ int perf_event__synthesize_build_id(struct perf_tool *tool, return err; } -int perf_event__process_build_id(struct perf_tool *tool __maybe_unused, - union perf_event *event, - struct perf_session *session) +int perf_event__process_build_id(struct perf_session *session, + union perf_event *event) { __event_process_build_id(&event->build_id, event->build_id.filename, diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index 90d4577a92dc..e17903caa71d 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -2,6 +2,7 @@ #ifndef __PERF_HEADER_H #define __PERF_HEADER_H +#include <linux/stddef.h> #include <linux/perf_event.h> #include <sys/types.h> #include <stdbool.h> @@ -115,15 +116,14 @@ int perf_event__synthesize_extra_attr(struct perf_tool *tool, perf_event__handler_t process, bool is_pipe); -int perf_event__process_feature(struct perf_tool *tool, - union perf_event *event, - struct perf_session *session); +int perf_event__process_feature(struct perf_session *session, + union perf_event *event); int perf_event__synthesize_attr(struct perf_tool *tool, struct perf_event_attr *attr, u32 ids, u64 *id, perf_event__handler_t process); int perf_event__synthesize_attrs(struct perf_tool *tool, - struct perf_session *session, + struct perf_evlist *evlist, perf_event__handler_t process); int perf_event__synthesize_event_update_unit(struct perf_tool *tool, struct perf_evsel *evsel, @@ -147,17 +147,15 @@ size_t perf_event__fprintf_event_update(union perf_event *event, FILE *fp); int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd, struct perf_evlist *evlist, perf_event__handler_t process); -int perf_event__process_tracing_data(struct perf_tool *tool, - union perf_event *event, - struct perf_session *session); +int perf_event__process_tracing_data(struct perf_session *session, + union perf_event *event); int perf_event__synthesize_build_id(struct perf_tool *tool, struct dso *pos, u16 misc, perf_event__handler_t process, struct machine *machine); -int perf_event__process_build_id(struct perf_tool *tool, - union perf_event *event, - struct perf_session *session); +int perf_event__process_build_id(struct perf_session *session, + union perf_event *event); bool is_perf_magic(u64 magic); #define NAME_ALIGN 64 diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 73049f7f0f60..3badd7f1e1b8 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -181,7 +181,7 @@ size_t events_stats__fprintf(struct events_stats *stats, FILE *fp); size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, int max_cols, float min_pcnt, FILE *fp, - bool use_callchain); + bool ignore_callchains); size_t perf_evlist__fprintf_nr_events(struct perf_evlist *evlist, FILE *fp); void hists__filter_by_dso(struct hists *hists); diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c index d404bed7003a..58f6a9ceb590 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c @@ -1165,7 +1165,7 @@ static int intel_pt_walk_tip(struct intel_pt_decoder *decoder) decoder->pge = false; decoder->continuous_period = false; decoder->pkt_state = INTEL_PT_STATE_IN_SYNC; - decoder->state.to_ip = 0; + decoder->state.type |= INTEL_PT_TRACE_END; return 0; } if (err == INTEL_PT_RETURN) @@ -1179,9 +1179,13 @@ static int intel_pt_walk_tip(struct intel_pt_decoder *decoder) decoder->continuous_period = false; decoder->pkt_state = INTEL_PT_STATE_IN_SYNC; decoder->state.from_ip = decoder->ip; - decoder->state.to_ip = 0; - if (decoder->packet.count != 0) + if (decoder->packet.count == 0) { + decoder->state.to_ip = 0; + } else { + decoder->state.to_ip = decoder->last_ip; decoder->ip = decoder->last_ip; + } + decoder->state.type |= INTEL_PT_TRACE_END; } else { decoder->pkt_state = INTEL_PT_STATE_IN_SYNC; decoder->state.from_ip = decoder->ip; @@ -1208,7 +1212,8 @@ static int intel_pt_walk_tip(struct intel_pt_decoder *decoder) decoder->pkt_state = INTEL_PT_STATE_IN_SYNC; decoder->ip = to_ip; decoder->state.from_ip = decoder->ip; - decoder->state.to_ip = 0; + decoder->state.to_ip = to_ip; + decoder->state.type |= INTEL_PT_TRACE_END; return 0; } intel_pt_log_at("ERROR: Conditional branch when expecting indirect branch", @@ -1640,14 +1645,15 @@ static int intel_pt_walk_fup_tip(struct intel_pt_decoder *decoder) case INTEL_PT_TIP_PGD: decoder->state.from_ip = decoder->ip; - decoder->state.to_ip = 0; - if (decoder->packet.count != 0) { + if (decoder->packet.count == 0) { + decoder->state.to_ip = 0; + } else { intel_pt_set_ip(decoder); - intel_pt_log("Omitting PGD ip " x64_fmt "\n", - decoder->ip); + decoder->state.to_ip = decoder->ip; } decoder->pge = false; decoder->continuous_period = false; + decoder->state.type |= INTEL_PT_TRACE_END; return 0; case INTEL_PT_TIP_PGE: @@ -1661,6 +1667,7 @@ static int intel_pt_walk_fup_tip(struct intel_pt_decoder *decoder) intel_pt_set_ip(decoder); decoder->state.to_ip = decoder->ip; } + decoder->state.type |= INTEL_PT_TRACE_BEGIN; return 0; case INTEL_PT_TIP: @@ -1739,6 +1746,7 @@ next: intel_pt_set_ip(decoder); decoder->state.from_ip = 0; decoder->state.to_ip = decoder->ip; + decoder->state.type |= INTEL_PT_TRACE_BEGIN; return 0; } @@ -2077,9 +2085,13 @@ static int intel_pt_walk_to_ip(struct intel_pt_decoder *decoder) decoder->pge = decoder->packet.type != INTEL_PT_TIP_PGD; if (intel_pt_have_ip(decoder)) intel_pt_set_ip(decoder); - if (decoder->ip) - return 0; - break; + if (!decoder->ip) + break; + if (decoder->packet.type == INTEL_PT_TIP_PGE) + decoder->state.type |= INTEL_PT_TRACE_BEGIN; + if (decoder->packet.type == INTEL_PT_TIP_PGD) + decoder->state.type |= INTEL_PT_TRACE_END; + return 0; case INTEL_PT_FUP: if (intel_pt_have_ip(decoder)) diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h index 51c18d67f4ca..ed088d4726ba 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h @@ -37,6 +37,8 @@ enum intel_pt_sample_type { INTEL_PT_EX_STOP = 1 << 6, INTEL_PT_PWR_EXIT = 1 << 7, INTEL_PT_CBR_CHG = 1 << 8, + INTEL_PT_TRACE_BEGIN = 1 << 9, + INTEL_PT_TRACE_END = 1 << 10, }; enum intel_pt_period_type { diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index aec68908d604..48c1d415c6b0 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -908,6 +908,11 @@ static void intel_pt_sample_flags(struct intel_pt_queue *ptq) ptq->insn_len = ptq->state->insn_len; memcpy(ptq->insn, ptq->state->insn, INTEL_PT_INSN_BUF_SZ); } + + if (ptq->state->type & INTEL_PT_TRACE_BEGIN) + ptq->flags |= PERF_IP_FLAG_TRACE_BEGIN; + if (ptq->state->type & INTEL_PT_TRACE_END) + ptq->flags |= PERF_IP_FLAG_TRACE_END; } static int intel_pt_setup_queue(struct intel_pt *pt, diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c index 5e94857dfca2..5b0b60f00275 100644 --- a/tools/perf/util/llvm-utils.c +++ b/tools/perf/util/llvm-utils.c @@ -19,15 +19,17 @@ #define CLANG_BPF_CMD_DEFAULT_TEMPLATE \ "$CLANG_EXEC -D__KERNEL__ -D__NR_CPUS__=$NR_CPUS "\ "-DLINUX_VERSION_CODE=$LINUX_VERSION_CODE " \ - "$CLANG_OPTIONS $KERNEL_INC_OPTIONS $PERF_BPF_INC_OPTIONS " \ + "$CLANG_OPTIONS $PERF_BPF_INC_OPTIONS $KERNEL_INC_OPTIONS " \ "-Wno-unused-value -Wno-pointer-sign " \ "-working-directory $WORKING_DIR " \ - "-c \"$CLANG_SOURCE\" -target bpf -O2 -o -" + "-c \"$CLANG_SOURCE\" -target bpf $CLANG_EMIT_LLVM -O2 -o - $LLVM_OPTIONS_PIPE" struct llvm_param llvm_param = { .clang_path = "clang", + .llc_path = "llc", .clang_bpf_cmd_template = CLANG_BPF_CMD_DEFAULT_TEMPLATE, .clang_opt = NULL, + .opts = NULL, .kbuild_dir = NULL, .kbuild_opts = NULL, .user_set_param = false, @@ -51,6 +53,8 @@ int perf_llvm_config(const char *var, const char *value) llvm_param.kbuild_opts = strdup(value); else if (!strcmp(var, "dump-obj")) llvm_param.dump_obj = !!perf_config_bool(var, value); + else if (!strcmp(var, "opts")) + llvm_param.opts = strdup(value); else { pr_debug("Invalid LLVM config option: %s\n", value); return -1; @@ -430,11 +434,13 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf, unsigned int kernel_version; char linux_version_code_str[64]; const char *clang_opt = llvm_param.clang_opt; - char clang_path[PATH_MAX], abspath[PATH_MAX], nr_cpus_avail_str[64]; + char clang_path[PATH_MAX], llc_path[PATH_MAX], abspath[PATH_MAX], nr_cpus_avail_str[64]; char serr[STRERR_BUFSIZE]; char *kbuild_dir = NULL, *kbuild_include_opts = NULL, *perf_bpf_include_opts = NULL; const char *template = llvm_param.clang_bpf_cmd_template; + char *pipe_template = NULL; + const char *opts = llvm_param.opts; char *command_echo = NULL, *command_out; char *perf_include_dir = system_path(PERF_INCLUDE_DIR); @@ -484,6 +490,26 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf, force_set_env("PERF_BPF_INC_OPTIONS", perf_bpf_include_opts); force_set_env("WORKING_DIR", kbuild_dir ? : "."); + if (opts) { + err = search_program(llvm_param.llc_path, "llc", llc_path); + if (err) { + pr_err("ERROR:\tunable to find llc.\n" + "Hint:\tTry to install latest clang/llvm to support BPF. Check your $PATH\n" + " \tand 'llc-path' option in [llvm] section of ~/.perfconfig.\n"); + version_notice(); + goto errout; + } + + if (asprintf(&pipe_template, "%s -emit-llvm | %s -march=bpf %s -filetype=obj -o -", + template, llc_path, opts) < 0) { + pr_err("ERROR:\tnot enough memory to setup command line\n"); + goto errout; + } + + template = pipe_template; + + } + /* * Since we may reset clang's working dir, path of source file * should be transferred into absolute path, except we want @@ -535,6 +561,7 @@ errout: free(obj_buf); free(perf_bpf_include_opts); free(perf_include_dir); + free(pipe_template); if (p_obj_buf) *p_obj_buf = NULL; if (p_obj_buf_sz) diff --git a/tools/perf/util/llvm-utils.h b/tools/perf/util/llvm-utils.h index d3ad8deb5db4..bf3f3f4c4fe2 100644 --- a/tools/perf/util/llvm-utils.h +++ b/tools/perf/util/llvm-utils.h @@ -11,6 +11,8 @@ struct llvm_param { /* Path of clang executable */ const char *clang_path; + /* Path of llc executable */ + const char *llc_path; /* * Template of clang bpf compiling. 5 env variables * can be used: @@ -23,6 +25,13 @@ struct llvm_param { const char *clang_bpf_cmd_template; /* Will be filled in $CLANG_OPTIONS */ const char *clang_opt; + /* + * If present it'll add -emit-llvm to $CLANG_OPTIONS to pipe + * the clang output to llc, useful for new llvm options not + * yet selectable via 'clang -mllvm option', such as -mattr=dwarfris + * in clang 6.0/llvm 7 + */ + const char *opts; /* Where to find kbuild system */ const char *kbuild_dir; /* diff --git a/tools/perf/util/lzma.c b/tools/perf/util/lzma.c index 07498eaddc08..b1dd29a9d915 100644 --- a/tools/perf/util/lzma.c +++ b/tools/perf/util/lzma.c @@ -3,9 +3,13 @@ #include <lzma.h> #include <stdio.h> #include <linux/compiler.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> #include "compress.h" #include "util.h" #include "debug.h" +#include <unistd.h> #define BUFSIZE 8192 @@ -99,3 +103,19 @@ err_fclose: fclose(infile); return err; } + +bool lzma_is_compressed(const char *input) +{ + int fd = open(input, O_RDONLY); + const uint8_t magic[6] = { 0xFD, '7', 'z', 'X', 'Z', 0x00 }; + char buf[6] = { 0 }; + ssize_t rc; + + if (fd < 0) + return -1; + + rc = read(fd, buf, sizeof(buf)); + close(fd); + return rc == sizeof(buf) ? + memcmp(buf, magic, sizeof(buf)) == 0 : false; +} diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index e7b4a8b513f2..111ae858cbcb 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -408,23 +408,16 @@ out_err: } /* - * Caller must eventually drop thread->refcnt returned with a successful - * lookup/new thread inserted. + * Front-end cache - TID lookups come in blocks, + * so most of the time we dont have to look up + * the full rbtree: */ -static struct thread *____machine__findnew_thread(struct machine *machine, - struct threads *threads, - pid_t pid, pid_t tid, - bool create) +static struct thread* +__threads__get_last_match(struct threads *threads, struct machine *machine, + int pid, int tid) { - struct rb_node **p = &threads->entries.rb_node; - struct rb_node *parent = NULL; struct thread *th; - /* - * Front-end cache - TID lookups come in blocks, - * so most of the time we dont have to look up - * the full rbtree: - */ th = threads->last_match; if (th != NULL) { if (th->tid == tid) { @@ -435,12 +428,57 @@ static struct thread *____machine__findnew_thread(struct machine *machine, threads->last_match = NULL; } + return NULL; +} + +static struct thread* +threads__get_last_match(struct threads *threads, struct machine *machine, + int pid, int tid) +{ + struct thread *th = NULL; + + if (perf_singlethreaded) + th = __threads__get_last_match(threads, machine, pid, tid); + + return th; +} + +static void +__threads__set_last_match(struct threads *threads, struct thread *th) +{ + threads->last_match = th; +} + +static void +threads__set_last_match(struct threads *threads, struct thread *th) +{ + if (perf_singlethreaded) + __threads__set_last_match(threads, th); +} + +/* + * Caller must eventually drop thread->refcnt returned with a successful + * lookup/new thread inserted. + */ +static struct thread *____machine__findnew_thread(struct machine *machine, + struct threads *threads, + pid_t pid, pid_t tid, + bool create) +{ + struct rb_node **p = &threads->entries.rb_node; + struct rb_node *parent = NULL; + struct thread *th; + + th = threads__get_last_match(threads, machine, pid, tid); + if (th) + return th; + while (*p != NULL) { parent = *p; th = rb_entry(parent, struct thread, rb_node); if (th->tid == tid) { - threads->last_match = th; + threads__set_last_match(threads, th); machine__update_thread_pid(machine, th, pid); return thread__get(th); } @@ -477,7 +515,7 @@ static struct thread *____machine__findnew_thread(struct machine *machine, * It is now in the rbtree, get a ref */ thread__get(th); - threads->last_match = th; + threads__set_last_match(threads, th); ++threads->nr; } @@ -1174,8 +1212,10 @@ static int map_groups__set_module_path(struct map_groups *mg, const char *path, * Full name could reveal us kmod compression, so * we need to update the symtab_type if needed. */ - if (m->comp && is_kmod_dso(map->dso)) + if (m->comp && is_kmod_dso(map->dso)) { map->dso->symtab_type++; + map->dso->comp = m->comp; + } return 0; } @@ -1635,7 +1675,7 @@ static void __machine__remove_thread(struct machine *machine, struct thread *th, struct threads *threads = machine__threads(machine, th->tid); if (threads->last_match == th) - threads->last_match = NULL; + threads__set_last_match(threads, NULL); BUG_ON(refcount_read(&th->refcnt) == 0); if (lock) @@ -2246,7 +2286,8 @@ static int append_inlines(struct callchain_cursor *cursor, if (!symbol_conf.inline_name || !map || !sym) return ret; - addr = map__rip_2objdump(map, ip); + addr = map__map_ip(map, ip); + addr = map__rip_2objdump(map, addr); inline_node = inlines__tree_find(&map->dso->inlined_nodes, addr); if (!inline_node) { @@ -2272,6 +2313,7 @@ static int unwind_entry(struct unwind_entry *entry, void *arg) { struct callchain_cursor *cursor = arg; const char *srcline = NULL; + u64 addr = entry->ip; if (symbol_conf.hide_unresolved && entry->sym == NULL) return 0; @@ -2279,7 +2321,14 @@ static int unwind_entry(struct unwind_entry *entry, void *arg) if (append_inlines(cursor, entry->map, entry->sym, entry->ip) == 0) return 0; - srcline = callchain_srcline(entry->map, entry->sym, entry->ip); + /* + * Convert entry->ip from a virtual address to an offset in + * its corresponding binary. + */ + if (entry->map) + addr = map__map_ip(entry->map, entry->ip); + + srcline = callchain_srcline(entry->map, entry->sym, addr); return callchain_cursor_append(cursor, entry->ip, entry->map, entry->sym, false, NULL, 0, 0, 0, srcline); diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index 1de7660d93e9..d856b85862e2 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -265,7 +265,7 @@ pid_t machine__get_current_tid(struct machine *machine, int cpu); int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid, pid_t tid); /* - * For use with libtraceevent's pevent_set_function_resolver() + * For use with libtraceevent's tep_set_function_resolver() */ char *machine__resolve_kernel_addr(void *vmachine, unsigned long long *addrp, char **modp); diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 89ac5b5dc218..354e54550d2b 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -320,12 +320,11 @@ int map__load(struct map *map) build_id__sprintf(map->dso->build_id, sizeof(map->dso->build_id), sbuild_id); - pr_warning("%s with build id %s not found", - name, sbuild_id); + pr_debug("%s with build id %s not found", name, sbuild_id); } else - pr_warning("Failed to open %s", name); + pr_debug("Failed to open %s", name); - pr_warning(", continuing without symbols\n"); + pr_debug(", continuing without symbols\n"); return -1; } else if (nr == 0) { #ifdef HAVE_LIBELF_SUPPORT @@ -334,12 +333,11 @@ int map__load(struct map *map) if (len > sizeof(DSO__DELETED) && strcmp(name + real_len + 1, DSO__DELETED) == 0) { - pr_warning("%.*s was updated (is prelink enabled?). " + pr_debug("%.*s was updated (is prelink enabled?). " "Restart the long running apps that use it!\n", (int)real_len, name); } else { - pr_warning("no symbols found in %s, maybe install " - "a debug package?\n", name); + pr_debug("no symbols found in %s, maybe install a debug package?\n", name); } #endif return -1; @@ -381,20 +379,6 @@ struct map *map__clone(struct map *from) return map; } -int map__overlap(struct map *l, struct map *r) -{ - if (l->start > r->start) { - struct map *t = l; - l = r; - r = t; - } - - if (l->end > r->start) - return 1; - - return 0; -} - size_t map__fprintf(struct map *map, FILE *fp) { return fprintf(fp, " %" PRIx64 "-%" PRIx64 " %" PRIx64 " %s\n", @@ -590,6 +574,13 @@ struct symbol *map_groups__find_symbol(struct map_groups *mg, return NULL; } +static bool map__contains_symbol(struct map *map, struct symbol *sym) +{ + u64 ip = map->unmap_ip(map, sym->start); + + return ip >= map->start && ip < map->end; +} + struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name, struct map **mapp) { @@ -605,6 +596,10 @@ struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name, if (sym == NULL) continue; + if (!map__contains_symbol(pos, sym)) { + sym = NULL; + continue; + } if (mapp != NULL) *mapp = pos; goto out; @@ -675,26 +670,47 @@ static void __map_groups__insert(struct map_groups *mg, struct map *map) static int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp) { struct rb_root *root; - struct rb_node *next; + struct rb_node *next, *first; int err = 0; down_write(&maps->lock); root = &maps->entries; - next = rb_first(root); + /* + * Find first map where end > map->start. + * Same as find_vma() in kernel. + */ + next = root->rb_node; + first = NULL; + while (next) { + struct map *pos = rb_entry(next, struct map, rb_node); + + if (pos->end > map->start) { + first = next; + if (pos->start <= map->start) + break; + next = next->rb_left; + } else + next = next->rb_right; + } + + next = first; while (next) { struct map *pos = rb_entry(next, struct map, rb_node); next = rb_next(&pos->rb_node); - if (!map__overlap(pos, map)) - continue; + /* + * Stop if current map starts after map->end. + * Maps are ordered by start: next will not overlap for sure. + */ + if (pos->start >= map->end) + break; if (verbose >= 2) { if (use_browser) { - pr_warning("overlapping maps in %s " - "(disable tui for more info)\n", + pr_debug("overlapping maps in %s (disable tui for more info)\n", map->dso->name); } else { fputs("overlapping maps:\n", fp); diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index 4cb90f242bed..e0f327b51e66 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -166,7 +166,6 @@ static inline void __map__zput(struct map **map) #define map__zput(map) __map__zput(&map) -int map__overlap(struct map *l, struct map *r); size_t map__fprintf(struct map *map, FILE *fp); size_t map__fprintf_dsoname(struct map *map, FILE *fp); char *map__srcline(struct map *map, u64 addr, struct symbol *sym); diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index 1ddc3d1d0147..a28f9b5cc4ff 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -326,8 +326,8 @@ void metricgroup__print(bool metrics, bool metricgroups, char *filter, if (raw) s = (char *)pe->metric_name; else { - if (asprintf(&s, "%s\n\t[%s]", - pe->metric_name, pe->desc) < 0) + if (asprintf(&s, "%s\n%*s%s]", + pe->metric_name, 8, "[", pe->desc) < 0) return; } @@ -490,3 +490,25 @@ out: metricgroup__free_egroups(&group_list); return ret; } + +bool metricgroup__has_metric(const char *metric) +{ + struct pmu_events_map *map = perf_pmu__find_map(NULL); + struct pmu_event *pe; + int i; + + if (!map) + return false; + + for (i = 0; ; i++) { + pe = &map->table[i]; + + if (!pe->name && !pe->metric_group && !pe->metric_name) + break; + if (!pe->metric_expr) + continue; + if (match_metric(pe->metric_name, metric)) + return true; + } + return false; +} diff --git a/tools/perf/util/metricgroup.h b/tools/perf/util/metricgroup.h index 06854e125ee7..8a155dba0581 100644 --- a/tools/perf/util/metricgroup.h +++ b/tools/perf/util/metricgroup.h @@ -28,4 +28,5 @@ int metricgroup__parse_groups(const struct option *opt, struct rblist *metric_events); void metricgroup__print(bool metrics, bool groups, char *filter, bool raw); +bool metricgroup__has_metric(const char *metric); #endif diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c index fc832676a798..cdb95b3a1213 100644 --- a/tools/perf/util/mmap.c +++ b/tools/perf/util/mmap.c @@ -164,7 +164,7 @@ void perf_mmap__munmap(struct perf_mmap *map) auxtrace_mmap__munmap(&map->auxtrace_mmap); } -int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd) +int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd, int cpu) { /* * The last one will be done at perf_mmap__consume(), so that we @@ -191,6 +191,7 @@ int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd) return -1; } map->fd = fd; + map->cpu = cpu; if (auxtrace_mmap__mmap(&map->auxtrace_mmap, &mp->auxtrace_mp, map->base, fd)) @@ -280,7 +281,7 @@ int perf_mmap__read_init(struct perf_mmap *map) } int perf_mmap__push(struct perf_mmap *md, void *to, - int push(void *to, void *buf, size_t size)) + int push(struct perf_mmap *map, void *to, void *buf, size_t size)) { u64 head = perf_mmap__read_head(md); unsigned char *data = md->base + page_size; @@ -299,7 +300,7 @@ int perf_mmap__push(struct perf_mmap *md, void *to, size = md->mask + 1 - (md->start & md->mask); md->start += size; - if (push(to, buf, size) < 0) { + if (push(md, to, buf, size) < 0) { rc = -1; goto out; } @@ -309,7 +310,7 @@ int perf_mmap__push(struct perf_mmap *md, void *to, size = md->end - md->start; md->start += size; - if (push(to, buf, size) < 0) { + if (push(md, to, buf, size) < 0) { rc = -1; goto out; } diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h index d82294db1295..cc5e2d6d17a9 100644 --- a/tools/perf/util/mmap.h +++ b/tools/perf/util/mmap.h @@ -4,7 +4,7 @@ #include <linux/compiler.h> #include <linux/refcount.h> #include <linux/types.h> -#include <asm/barrier.h> +#include <linux/ring_buffer.h> #include <stdbool.h> #include "auxtrace.h" #include "event.h" @@ -18,6 +18,7 @@ struct perf_mmap { void *base; int mask; int fd; + int cpu; refcount_t refcnt; u64 prev; u64 start; @@ -60,7 +61,7 @@ struct mmap_params { struct auxtrace_mmap_params auxtrace_mp; }; -int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd); +int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd, int cpu); void perf_mmap__munmap(struct perf_mmap *map); void perf_mmap__get(struct perf_mmap *map); @@ -70,21 +71,12 @@ void perf_mmap__consume(struct perf_mmap *map); static inline u64 perf_mmap__read_head(struct perf_mmap *mm) { - struct perf_event_mmap_page *pc = mm->base; - u64 head = READ_ONCE(pc->data_head); - rmb(); - return head; + return ring_buffer_read_head(mm->base); } static inline void perf_mmap__write_tail(struct perf_mmap *md, u64 tail) { - struct perf_event_mmap_page *pc = md->base; - - /* - * ensure all reads are done before we write the tail out. - */ - mb(); - pc->data_tail = tail; + ring_buffer_write_tail(md->base, tail); } union perf_event *perf_mmap__read_forward(struct perf_mmap *map); @@ -92,7 +84,7 @@ union perf_event *perf_mmap__read_forward(struct perf_mmap *map); union perf_event *perf_mmap__read_event(struct perf_mmap *map); int perf_mmap__push(struct perf_mmap *md, void *to, - int push(void *to, void *buf, size_t size)); + int push(struct perf_mmap *map, void *to, void *buf, size_t size)); size_t perf_mmap__mmap_len(struct perf_mmap *map); diff --git a/tools/perf/util/namespaces.c b/tools/perf/util/namespaces.c index 5be021701f34..cf8bd123cf73 100644 --- a/tools/perf/util/namespaces.c +++ b/tools/perf/util/namespaces.c @@ -139,6 +139,9 @@ struct nsinfo *nsinfo__copy(struct nsinfo *nsi) { struct nsinfo *nnsi; + if (nsi == NULL) + return NULL; + nnsi = calloc(1, sizeof(*nnsi)); if (nnsi != NULL) { nnsi->pid = nsi->pid; diff --git a/tools/perf/util/namespaces.h b/tools/perf/util/namespaces.h index 760558dcfd18..cae1a9a39722 100644 --- a/tools/perf/util/namespaces.h +++ b/tools/perf/util/namespaces.h @@ -10,6 +10,7 @@ #define __PERF_NAMESPACES_H #include <sys/types.h> +#include <linux/stddef.h> #include <linux/perf_event.h> #include <linux/refcount.h> #include <linux/types.h> diff --git a/tools/perf/util/ordered-events.c b/tools/perf/util/ordered-events.c index bad9e0296e9a..1904e7f6ec84 100644 --- a/tools/perf/util/ordered-events.c +++ b/tools/perf/util/ordered-events.c @@ -80,14 +80,20 @@ static union perf_event *dup_event(struct ordered_events *oe, return oe->copy_on_queue ? __dup_event(oe, event) : event; } -static void free_dup_event(struct ordered_events *oe, union perf_event *event) +static void __free_dup_event(struct ordered_events *oe, union perf_event *event) { - if (event && oe->copy_on_queue) { + if (event) { oe->cur_alloc_size -= event->header.size; free(event); } } +static void free_dup_event(struct ordered_events *oe, union perf_event *event) +{ + if (oe->copy_on_queue) + __free_dup_event(oe, event); +} + #define MAX_SAMPLE_BUFFER (64 * 1024 / sizeof(struct ordered_event)) static struct ordered_event *alloc_event(struct ordered_events *oe, union perf_event *event) @@ -95,21 +101,49 @@ static struct ordered_event *alloc_event(struct ordered_events *oe, struct list_head *cache = &oe->cache; struct ordered_event *new = NULL; union perf_event *new_event; + size_t size; new_event = dup_event(oe, event); if (!new_event) return NULL; + /* + * We maintain the following scheme of buffers for ordered + * event allocation: + * + * to_free list -> buffer1 (64K) + * buffer2 (64K) + * ... + * + * Each buffer keeps an array of ordered events objects: + * buffer -> event[0] + * event[1] + * ... + * + * Each allocated ordered event is linked to one of + * following lists: + * - time ordered list 'events' + * - list of currently removed events 'cache' + * + * Allocation of the ordered event uses the following order + * to get the memory: + * - use recently removed object from 'cache' list + * - use available object in current allocation buffer + * - allocate new buffer if the current buffer is full + * + * Removal of ordered event object moves it from events to + * the cache list. + */ + size = sizeof(*oe->buffer) + MAX_SAMPLE_BUFFER * sizeof(*new); + if (!list_empty(cache)) { new = list_entry(cache->next, struct ordered_event, list); list_del(&new->list); } else if (oe->buffer) { - new = oe->buffer + oe->buffer_idx; + new = &oe->buffer->event[oe->buffer_idx]; if (++oe->buffer_idx == MAX_SAMPLE_BUFFER) oe->buffer = NULL; - } else if (oe->cur_alloc_size < oe->max_alloc_size) { - size_t size = MAX_SAMPLE_BUFFER * sizeof(*new); - + } else if ((oe->cur_alloc_size + size) < oe->max_alloc_size) { oe->buffer = malloc(size); if (!oe->buffer) { free_dup_event(oe, new_event); @@ -122,11 +156,11 @@ static struct ordered_event *alloc_event(struct ordered_events *oe, oe->cur_alloc_size += size; list_add(&oe->buffer->list, &oe->to_free); - /* First entry is abused to maintain the to_free list. */ - oe->buffer_idx = 2; - new = oe->buffer + 1; + oe->buffer_idx = 1; + new = &oe->buffer->event[0]; } else { pr("allocation limit reached %" PRIu64 "B\n", oe->max_alloc_size); + return NULL; } new->event = new_event; @@ -300,15 +334,38 @@ void ordered_events__init(struct ordered_events *oe, ordered_events__deliver_t d oe->deliver = deliver; } +static void +ordered_events_buffer__free(struct ordered_events_buffer *buffer, + unsigned int max, struct ordered_events *oe) +{ + if (oe->copy_on_queue) { + unsigned int i; + + for (i = 0; i < max; i++) + __free_dup_event(oe, buffer->event[i].event); + } + + free(buffer); +} + void ordered_events__free(struct ordered_events *oe) { - while (!list_empty(&oe->to_free)) { - struct ordered_event *event; + struct ordered_events_buffer *buffer, *tmp; - event = list_entry(oe->to_free.next, struct ordered_event, list); - list_del(&event->list); - free_dup_event(oe, event->event); - free(event); + if (list_empty(&oe->to_free)) + return; + + /* + * Current buffer might not have all the events allocated + * yet, we need to free only allocated ones ... + */ + list_del(&oe->buffer->list); + ordered_events_buffer__free(oe->buffer, oe->buffer_idx, oe); + + /* ... and continue with the rest */ + list_for_each_entry_safe(buffer, tmp, &oe->to_free, list) { + list_del(&buffer->list); + ordered_events_buffer__free(buffer, MAX_SAMPLE_BUFFER, oe); } } diff --git a/tools/perf/util/ordered-events.h b/tools/perf/util/ordered-events.h index 8c7a2948593e..1338d5c345dc 100644 --- a/tools/perf/util/ordered-events.h +++ b/tools/perf/util/ordered-events.h @@ -25,23 +25,28 @@ struct ordered_events; typedef int (*ordered_events__deliver_t)(struct ordered_events *oe, struct ordered_event *event); +struct ordered_events_buffer { + struct list_head list; + struct ordered_event event[0]; +}; + struct ordered_events { - u64 last_flush; - u64 next_flush; - u64 max_timestamp; - u64 max_alloc_size; - u64 cur_alloc_size; - struct list_head events; - struct list_head cache; - struct list_head to_free; - struct ordered_event *buffer; - struct ordered_event *last; - ordered_events__deliver_t deliver; - int buffer_idx; - unsigned int nr_events; - enum oe_flush last_flush_type; - u32 nr_unordered_events; - bool copy_on_queue; + u64 last_flush; + u64 next_flush; + u64 max_timestamp; + u64 max_alloc_size; + u64 cur_alloc_size; + struct list_head events; + struct list_head cache; + struct list_head to_free; + struct ordered_events_buffer *buffer; + struct ordered_event *last; + ordered_events__deliver_t deliver; + int buffer_idx; + unsigned int nr_events; + enum oe_flush last_flush_type; + u32 nr_unordered_events; + bool copy_on_queue; }; int ordered_events__queue(struct ordered_events *oe, union perf_event *event, diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 15eec49e71a1..f8cd3e7c9186 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -1991,8 +1991,11 @@ static int set_filter(struct perf_evsel *evsel, const void *arg) int nr_addr_filters = 0; struct perf_pmu *pmu = NULL; - if (evsel == NULL) - goto err; + if (evsel == NULL) { + fprintf(stderr, + "--filter option should follow a -e tracepoint or HW tracer option\n"); + return -1; + } if (evsel->attr.type == PERF_TYPE_TRACEPOINT) { if (perf_evsel__append_tp_filter(evsel, str) < 0) { @@ -2014,8 +2017,11 @@ static int set_filter(struct perf_evsel *evsel, const void *arg) perf_pmu__scan_file(pmu, "nr_addr_filters", "%d", &nr_addr_filters); - if (!nr_addr_filters) - goto err; + if (!nr_addr_filters) { + fprintf(stderr, + "This CPU does not support address filtering\n"); + return -1; + } if (perf_evsel__append_addr_filter(evsel, str) < 0) { fprintf(stderr, @@ -2024,12 +2030,6 @@ static int set_filter(struct perf_evsel *evsel, const void *arg) } return 0; - -err: - fprintf(stderr, - "--filter option should follow a -e tracepoint or HW tracer option\n"); - - return -1; } int parse_filter(const struct option *opt, const char *str, diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 3ba6a1742f91..7799788f662f 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -652,12 +652,6 @@ static int is_arm_pmu_core(const char *name) if (stat(path, &st) == 0) return 1; - /* Look for cpu sysfs (specific to s390) */ - scnprintf(path, PATH_MAX, "%s/bus/event_source/devices/%s", - sysfs, name); - if (stat(path, &st) == 0 && !strncmp(name, "cpum_", 5)) - return 1; - return 0; } @@ -936,13 +930,14 @@ static void pmu_format_value(unsigned long *format, __u64 value, __u64 *v, static __u64 pmu_format_max_value(const unsigned long *format) { - __u64 w = 0; - int fbit; + int w; - for_each_set_bit(fbit, format, PERF_PMU_FORMAT_BITS) - w |= (1ULL << fbit); - - return w; + w = bitmap_weight(format, PERF_PMU_FORMAT_BITS); + if (!w) + return 0; + if (w < 64) + return (1ULL << w) - 1; + return -1; } /* diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index f119eb628dbb..e86f8be89157 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -1819,6 +1819,12 @@ int parse_probe_trace_command(const char *cmd, struct probe_trace_event *tev) tp->offset = strtoul(fmt2_str, NULL, 10); } + if (tev->uprobes) { + fmt2_str = strchr(p, '('); + if (fmt2_str) + tp->ref_ctr_offset = strtoul(fmt2_str + 1, NULL, 0); + } + tev->nargs = argc - 2; tev->args = zalloc(sizeof(struct probe_trace_arg) * tev->nargs); if (tev->args == NULL) { @@ -2012,6 +2018,22 @@ static int synthesize_probe_trace_arg(struct probe_trace_arg *arg, return err; } +static int +synthesize_uprobe_trace_def(struct probe_trace_event *tev, struct strbuf *buf) +{ + struct probe_trace_point *tp = &tev->point; + int err; + + err = strbuf_addf(buf, "%s:0x%lx", tp->module, tp->address); + + if (err >= 0 && tp->ref_ctr_offset) { + if (!uprobe_ref_ctr_is_supported()) + return -1; + err = strbuf_addf(buf, "(0x%lx)", tp->ref_ctr_offset); + } + return err >= 0 ? 0 : -1; +} + char *synthesize_probe_trace_command(struct probe_trace_event *tev) { struct probe_trace_point *tp = &tev->point; @@ -2041,15 +2063,17 @@ char *synthesize_probe_trace_command(struct probe_trace_event *tev) } /* Use the tp->address for uprobes */ - if (tev->uprobes) - err = strbuf_addf(&buf, "%s:0x%lx", tp->module, tp->address); - else if (!strncmp(tp->symbol, "0x", 2)) + if (tev->uprobes) { + err = synthesize_uprobe_trace_def(tev, &buf); + } else if (!strncmp(tp->symbol, "0x", 2)) { /* Absolute address. See try_to_find_absolute_address() */ err = strbuf_addf(&buf, "%s%s0x%lx", tp->module ?: "", tp->module ? ":" : "", tp->address); - else + } else { err = strbuf_addf(&buf, "%s%s%s+%lu", tp->module ?: "", tp->module ? ":" : "", tp->symbol, tp->offset); + } + if (err) goto error; @@ -2633,6 +2657,13 @@ static void warn_uprobe_event_compat(struct probe_trace_event *tev) { int i; char *buf = synthesize_probe_trace_command(tev); + struct probe_trace_point *tp = &tev->point; + + if (tp->ref_ctr_offset && !uprobe_ref_ctr_is_supported()) { + pr_warning("A semaphore is associated with %s:%s and " + "seems your kernel doesn't support it.\n", + tev->group, tev->event); + } /* Old uprobe event doesn't support memory dereference */ if (!tev->uprobes || tev->nargs == 0 || !buf) diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h index 45b14f020558..15a98c3a2a2f 100644 --- a/tools/perf/util/probe-event.h +++ b/tools/perf/util/probe-event.h @@ -27,6 +27,7 @@ struct probe_trace_point { char *symbol; /* Base symbol */ char *module; /* Module name */ unsigned long offset; /* Offset from symbol */ + unsigned long ref_ctr_offset; /* SDT reference counter offset */ unsigned long address; /* Actual address of the trace point */ bool retprobe; /* Return probe flag */ }; diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c index b76088fadf3d..aac7817d9e14 100644 --- a/tools/perf/util/probe-file.c +++ b/tools/perf/util/probe-file.c @@ -696,8 +696,16 @@ out_err: #ifdef HAVE_GELF_GETNOTE_SUPPORT static unsigned long long sdt_note__get_addr(struct sdt_note *note) { - return note->bit32 ? (unsigned long long)note->addr.a32[0] - : (unsigned long long)note->addr.a64[0]; + return note->bit32 ? + (unsigned long long)note->addr.a32[SDT_NOTE_IDX_LOC] : + (unsigned long long)note->addr.a64[SDT_NOTE_IDX_LOC]; +} + +static unsigned long long sdt_note__get_ref_ctr_offset(struct sdt_note *note) +{ + return note->bit32 ? + (unsigned long long)note->addr.a32[SDT_NOTE_IDX_REFCTR] : + (unsigned long long)note->addr.a64[SDT_NOTE_IDX_REFCTR]; } static const char * const type_to_suffix[] = { @@ -775,14 +783,21 @@ static char *synthesize_sdt_probe_command(struct sdt_note *note, { struct strbuf buf; char *ret = NULL, **args; - int i, args_count; + int i, args_count, err; + unsigned long long ref_ctr_offset; if (strbuf_init(&buf, 32) < 0) return NULL; - if (strbuf_addf(&buf, "p:%s/%s %s:0x%llx", - sdtgrp, note->name, pathname, - sdt_note__get_addr(note)) < 0) + err = strbuf_addf(&buf, "p:%s/%s %s:0x%llx", + sdtgrp, note->name, pathname, + sdt_note__get_addr(note)); + + ref_ctr_offset = sdt_note__get_ref_ctr_offset(note); + if (ref_ctr_offset && err >= 0) + err = strbuf_addf(&buf, "(0x%llx)", ref_ctr_offset); + + if (err < 0) goto error; if (!note->args) @@ -998,6 +1013,7 @@ int probe_cache__show_all_caches(struct strfilter *filter) enum ftrace_readme { FTRACE_README_PROBE_TYPE_X = 0, FTRACE_README_KRETPROBE_OFFSET, + FTRACE_README_UPROBE_REF_CTR, FTRACE_README_END, }; @@ -1009,6 +1025,7 @@ static struct { [idx] = {.pattern = pat, .avail = false} DEFINE_TYPE(FTRACE_README_PROBE_TYPE_X, "*type: * x8/16/32/64,*"), DEFINE_TYPE(FTRACE_README_KRETPROBE_OFFSET, "*place (kretprobe): *"), + DEFINE_TYPE(FTRACE_README_UPROBE_REF_CTR, "*ref_ctr_offset*"), }; static bool scan_ftrace_readme(enum ftrace_readme type) @@ -1064,3 +1081,8 @@ bool kretprobe_offset_is_supported(void) { return scan_ftrace_readme(FTRACE_README_KRETPROBE_OFFSET); } + +bool uprobe_ref_ctr_is_supported(void) +{ + return scan_ftrace_readme(FTRACE_README_UPROBE_REF_CTR); +} diff --git a/tools/perf/util/probe-file.h b/tools/perf/util/probe-file.h index 63f29b1d22c1..2a249182f2a6 100644 --- a/tools/perf/util/probe-file.h +++ b/tools/perf/util/probe-file.h @@ -69,6 +69,7 @@ struct probe_cache_entry *probe_cache__find_by_name(struct probe_cache *pcache, int probe_cache__show_all_caches(struct strfilter *filter); bool probe_type_is_available(enum probe_type type); bool kretprobe_offset_is_supported(void); +bool uprobe_ref_ctr_is_supported(void); #else /* ! HAVE_LIBELF_SUPPORT */ static inline struct probe_cache *probe_cache__new(const char *tgt __maybe_unused, struct nsinfo *nsi __maybe_unused) { diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index 863b61478edd..50150dfc0cdf 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -11,6 +11,7 @@ #include "cpumap.h" #include "print_binary.h" #include "thread_map.h" +#include "mmap.h" #if PY_MAJOR_VERSION < 3 #define _PyUnicode_FromString(arg) \ @@ -339,36 +340,36 @@ static bool is_tracepoint(struct pyrf_event *pevent) } static PyObject* -tracepoint_field(struct pyrf_event *pe, struct format_field *field) +tracepoint_field(struct pyrf_event *pe, struct tep_format_field *field) { - struct pevent *pevent = field->event->pevent; + struct tep_handle *pevent = field->event->pevent; void *data = pe->sample.raw_data; PyObject *ret = NULL; unsigned long long val; unsigned int offset, len; - if (field->flags & FIELD_IS_ARRAY) { + if (field->flags & TEP_FIELD_IS_ARRAY) { offset = field->offset; len = field->size; - if (field->flags & FIELD_IS_DYNAMIC) { - val = pevent_read_number(pevent, data + offset, len); + if (field->flags & TEP_FIELD_IS_DYNAMIC) { + val = tep_read_number(pevent, data + offset, len); offset = val; len = offset >> 16; offset &= 0xffff; } - if (field->flags & FIELD_IS_STRING && + if (field->flags & TEP_FIELD_IS_STRING && is_printable_array(data + offset, len)) { ret = _PyUnicode_FromString((char *)data + offset); } else { ret = PyByteArray_FromStringAndSize((const char *) data + offset, len); - field->flags &= ~FIELD_IS_STRING; + field->flags &= ~TEP_FIELD_IS_STRING; } } else { - val = pevent_read_number(pevent, data + field->offset, - field->size); - if (field->flags & FIELD_IS_POINTER) + val = tep_read_number(pevent, data + field->offset, + field->size); + if (field->flags & TEP_FIELD_IS_POINTER) ret = PyLong_FromUnsignedLong((unsigned long) val); - else if (field->flags & FIELD_IS_SIGNED) + else if (field->flags & TEP_FIELD_IS_SIGNED) ret = PyLong_FromLong((long) val); else ret = PyLong_FromUnsignedLong((unsigned long) val); @@ -382,10 +383,10 @@ get_tracepoint_field(struct pyrf_event *pevent, PyObject *attr_name) { const char *str = _PyUnicode_AsString(PyObject_Str(attr_name)); struct perf_evsel *evsel = pevent->evsel; - struct format_field *field; + struct tep_format_field *field; if (!evsel->tp_format) { - struct event_format *tp_format; + struct tep_event_format *tp_format; tp_format = trace_event__tp_format_id(evsel->attr.config); if (!tp_format) @@ -394,7 +395,7 @@ get_tracepoint_field(struct pyrf_event *pevent, PyObject *attr_name) evsel->tp_format = tp_format; } - field = pevent_find_any_field(evsel->tp_format, str); + field = tep_find_any_field(evsel->tp_format, str); if (!field) return NULL; @@ -976,6 +977,20 @@ static PyObject *pyrf_evlist__add(struct pyrf_evlist *pevlist, return Py_BuildValue("i", evlist->nr_entries); } +static struct perf_mmap *get_md(struct perf_evlist *evlist, int cpu) +{ + int i; + + for (i = 0; i < evlist->nr_mmaps; i++) { + struct perf_mmap *md = &evlist->mmap[i]; + + if (md->cpu == cpu) + return md; + } + + return NULL; +} + static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist, PyObject *args, PyObject *kwargs) { @@ -990,7 +1005,10 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist, &cpu, &sample_id_all)) return NULL; - md = &evlist->mmap[cpu]; + md = get_md(evlist, cpu); + if (!md) + return NULL; + if (perf_mmap__read_init(md) < 0) goto end; @@ -1222,7 +1240,7 @@ static struct { static PyObject *pyrf__tracepoint(struct pyrf_evsel *pevsel, PyObject *args, PyObject *kwargs) { - struct event_format *tp_format; + struct tep_event_format *tp_format; static char *kwlist[] = { "sys", "name", NULL }; char *sys = NULL; char *name = NULL; diff --git a/tools/perf/util/s390-cpumsf-kernel.h b/tools/perf/util/s390-cpumsf-kernel.h new file mode 100644 index 000000000000..de8c7ad0eca8 --- /dev/null +++ b/tools/perf/util/s390-cpumsf-kernel.h @@ -0,0 +1,71 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Auxtrace support for s390 CPU measurement sampling facility + * + * Copyright IBM Corp. 2018 + * Author(s): Hendrik Brueckner <brueckner@linux.ibm.com> + * Thomas Richter <tmricht@linux.ibm.com> + */ +#ifndef S390_CPUMSF_KERNEL_H +#define S390_CPUMSF_KERNEL_H + +#define S390_CPUMSF_PAGESZ 4096 /* Size of sample block units */ +#define S390_CPUMSF_DIAG_DEF_FIRST 0x8001 /* Diagnostic entry lowest id */ + +struct hws_basic_entry { + unsigned int def:16; /* 0-15 Data Entry Format */ + unsigned int R:4; /* 16-19 reserved */ + unsigned int U:4; /* 20-23 Number of unique instruct. */ + unsigned int z:2; /* zeros */ + unsigned int T:1; /* 26 PSW DAT mode */ + unsigned int W:1; /* 27 PSW wait state */ + unsigned int P:1; /* 28 PSW Problem state */ + unsigned int AS:2; /* 29-30 PSW address-space control */ + unsigned int I:1; /* 31 entry valid or invalid */ + unsigned int CL:2; /* 32-33 Configuration Level */ + unsigned int:14; + unsigned int prim_asn:16; /* primary ASN */ + unsigned long long ia; /* Instruction Address */ + unsigned long long gpp; /* Guest Program Parameter */ + unsigned long long hpp; /* Host Program Parameter */ +}; + +struct hws_diag_entry { + unsigned int def:16; /* 0-15 Data Entry Format */ + unsigned int R:15; /* 16-19 and 20-30 reserved */ + unsigned int I:1; /* 31 entry valid or invalid */ + u8 data[]; /* Machine-dependent sample data */ +}; + +struct hws_combined_entry { + struct hws_basic_entry basic; /* Basic-sampling data entry */ + struct hws_diag_entry diag; /* Diagnostic-sampling data entry */ +}; + +struct hws_trailer_entry { + union { + struct { + unsigned int f:1; /* 0 - Block Full Indicator */ + unsigned int a:1; /* 1 - Alert request control */ + unsigned int t:1; /* 2 - Timestamp format */ + unsigned int:29; /* 3 - 31: Reserved */ + unsigned int bsdes:16; /* 32-47: size of basic SDE */ + unsigned int dsdes:16; /* 48-63: size of diagnostic SDE */ + }; + unsigned long long flags; /* 0 - 64: All indicators */ + }; + unsigned long long overflow; /* 64 - sample Overflow count */ + unsigned char timestamp[16]; /* 16 - 31 timestamp */ + unsigned long long reserved1; /* 32 -Reserved */ + unsigned long long reserved2; /* */ + union { /* 48 - reserved for programming use */ + struct { + unsigned long long clock_base:1; /* in progusage2 */ + unsigned long long progusage1:63; + unsigned long long progusage2; + }; + unsigned long long progusage[2]; + }; +}; + +#endif diff --git a/tools/perf/util/s390-cpumsf.c b/tools/perf/util/s390-cpumsf.c new file mode 100644 index 000000000000..a2eeebbfb25f --- /dev/null +++ b/tools/perf/util/s390-cpumsf.c @@ -0,0 +1,1033 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright IBM Corp. 2018 + * Auxtrace support for s390 CPU-Measurement Sampling Facility + * + * Author(s): Thomas Richter <tmricht@linux.ibm.com> + * + * Auxiliary traces are collected during 'perf record' using rbd000 event. + * Several PERF_RECORD_XXX are generated during recording: + * + * PERF_RECORD_AUX: + * Records that new data landed in the AUX buffer part. + * PERF_RECORD_AUXTRACE: + * Defines auxtrace data. Followed by the actual data. The contents of + * the auxtrace data is dependent on the event and the CPU. + * This record is generated by perf record command. For details + * see Documentation/perf.data-file-format.txt. + * PERF_RECORD_AUXTRACE_INFO: + * Defines a table of contains for PERF_RECORD_AUXTRACE records. This + * record is generated during 'perf record' command. Each record contains up + * to 256 entries describing offset and size of the AUXTRACE data in the + * perf.data file. + * PERF_RECORD_AUXTRACE_ERROR: + * Indicates an error during AUXTRACE collection such as buffer overflow. + * PERF_RECORD_FINISHED_ROUND: + * Perf events are not necessarily in time stamp order, as they can be + * collected in parallel on different CPUs. If the events should be + * processed in time order they need to be sorted first. + * Perf report guarantees that there is no reordering over a + * PERF_RECORD_FINISHED_ROUND boundary event. All perf records with a + * time stamp lower than this record are processed (and displayed) before + * the succeeding perf record are processed. + * + * These records are evaluated during perf report command. + * + * 1. PERF_RECORD_AUXTRACE_INFO is used to set up the infrastructure for + * auxiliary trace data processing. See s390_cpumsf_process_auxtrace_info() + * below. + * Auxiliary trace data is collected per CPU. To merge the data into the report + * an auxtrace_queue is created for each CPU. It is assumed that the auxtrace + * data is in ascending order. + * + * Each queue has a double linked list of auxtrace_buffers. This list contains + * the offset and size of a CPU's auxtrace data. During auxtrace processing + * the data portion is mmap()'ed. + * + * To sort the queues in chronological order, all queue access is controlled + * by the auxtrace_heap. This is basicly a stack, each stack element has two + * entries, the queue number and a time stamp. However the stack is sorted by + * the time stamps. The highest time stamp is at the bottom the lowest + * (nearest) time stamp is at the top. That sort order is maintained at all + * times! + * + * After the auxtrace infrastructure has been setup, the auxtrace queues are + * filled with data (offset/size pairs) and the auxtrace_heap is populated. + * + * 2. PERF_RECORD_XXX processing triggers access to the auxtrace_queues. + * Each record is handled by s390_cpumsf_process_event(). The time stamp of + * the perf record is compared with the time stamp located on the auxtrace_heap + * top element. If that time stamp is lower than the time stamp from the + * record sample, the auxtrace queues will be processed. As auxtrace queues + * control many auxtrace_buffers and each buffer can be quite large, the + * auxtrace buffer might be processed only partially. In this case the + * position in the auxtrace_buffer of that queue is remembered and the time + * stamp of the last processed entry of the auxtrace_buffer replaces the + * current auxtrace_heap top. + * + * 3. Auxtrace_queues might run of out data and are feeded by the + * PERF_RECORD_AUXTRACE handling, see s390_cpumsf_process_auxtrace_event(). + * + * Event Generation + * Each sampling-data entry in the auxilary trace data generates a perf sample. + * This sample is filled + * with data from the auxtrace such as PID/TID, instruction address, CPU state, + * etc. This sample is processed with perf_session__deliver_synth_event() to + * be included into the GUI. + * + * 4. PERF_RECORD_FINISHED_ROUND event is used to process all the remaining + * auxiliary traces entries until the time stamp of this record is reached + * auxtrace_heap top. This is triggered by ordered_event->deliver(). + * + * + * Perf event processing. + * Event processing of PERF_RECORD_XXX entries relies on time stamp entries. + * This is the function call sequence: + * + * __cmd_report() + * | + * perf_session__process_events() + * | + * __perf_session__process_events() + * | + * perf_session__process_event() + * | This functions splits the PERF_RECORD_XXX records. + * | - Those generated by perf record command (type number equal or higher + * | than PERF_RECORD_USER_TYPE_START) are handled by + * | perf_session__process_user_event(see below) + * | - Those generated by the kernel are handled by + * | perf_evlist__parse_sample_timestamp() + * | + * perf_evlist__parse_sample_timestamp() + * | Extract time stamp from sample data. + * | + * perf_session__queue_event() + * | If timestamp is positive the sample is entered into an ordered_event + * | list, sort order is the timestamp. The event processing is deferred until + * | later (see perf_session__process_user_event()). + * | Other timestamps (0 or -1) are handled immediately by + * | perf_session__deliver_event(). These are events generated at start up + * | of command perf record. They create PERF_RECORD_COMM and PERF_RECORD_MMAP* + * | records. They are needed to create a list of running processes and its + * | memory mappings and layout. They are needed at the beginning to enable + * | command perf report to create process trees and memory mappings. + * | + * perf_session__deliver_event() + * | Delivers a PERF_RECORD_XXX entry for handling. + * | + * auxtrace__process_event() + * | The timestamp of the PERF_RECORD_XXX entry is taken to correlate with + * | time stamps from the auxiliary trace buffers. This enables + * | synchronization between auxiliary trace data and the events on the + * | perf.data file. + * | + * machine__deliver_event() + * | Handles the PERF_RECORD_XXX event. This depends on the record type. + * It might update the process tree, update a process memory map or enter + * a sample with IP and call back chain data into GUI data pool. + * + * + * Deferred processing determined by perf_session__process_user_event() is + * finally processed when a PERF_RECORD_FINISHED_ROUND is encountered. These + * are generated during command perf record. + * The timestamp of PERF_RECORD_FINISHED_ROUND event is taken to process all + * PERF_RECORD_XXX entries stored in the ordered_event list. This list was + * built up while reading the perf.data file. + * Each event is now processed by calling perf_session__deliver_event(). + * This enables time synchronization between the data in the perf.data file and + * the data in the auxiliary trace buffers. + */ + +#include <endian.h> +#include <errno.h> +#include <byteswap.h> +#include <inttypes.h> +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/bitops.h> +#include <linux/log2.h> + +#include <sys/stat.h> +#include <sys/types.h> + +#include "cpumap.h" +#include "color.h" +#include "evsel.h" +#include "evlist.h" +#include "machine.h" +#include "session.h" +#include "util.h" +#include "thread.h" +#include "debug.h" +#include "auxtrace.h" +#include "s390-cpumsf.h" +#include "s390-cpumsf-kernel.h" +#include "config.h" + +struct s390_cpumsf { + struct auxtrace auxtrace; + struct auxtrace_queues queues; + struct auxtrace_heap heap; + struct perf_session *session; + struct machine *machine; + u32 auxtrace_type; + u32 pmu_type; + u16 machine_type; + bool data_queued; + bool use_logfile; + char *logdir; +}; + +struct s390_cpumsf_queue { + struct s390_cpumsf *sf; + unsigned int queue_nr; + struct auxtrace_buffer *buffer; + int cpu; + FILE *logfile; +}; + +/* Display s390 CPU measurement facility basic-sampling data entry */ +static bool s390_cpumsf_basic_show(const char *color, size_t pos, + struct hws_basic_entry *basic) +{ + if (basic->def != 1) { + pr_err("Invalid AUX trace basic entry [%#08zx]\n", pos); + return false; + } + color_fprintf(stdout, color, " [%#08zx] Basic Def:%04x Inst:%#04x" + " %c%c%c%c AS:%d ASN:%#04x IA:%#018llx\n" + "\t\tCL:%d HPP:%#018llx GPP:%#018llx\n", + pos, basic->def, basic->U, + basic->T ? 'T' : ' ', + basic->W ? 'W' : ' ', + basic->P ? 'P' : ' ', + basic->I ? 'I' : ' ', + basic->AS, basic->prim_asn, basic->ia, basic->CL, + basic->hpp, basic->gpp); + return true; +} + +/* Display s390 CPU measurement facility diagnostic-sampling data entry */ +static bool s390_cpumsf_diag_show(const char *color, size_t pos, + struct hws_diag_entry *diag) +{ + if (diag->def < S390_CPUMSF_DIAG_DEF_FIRST) { + pr_err("Invalid AUX trace diagnostic entry [%#08zx]\n", pos); + return false; + } + color_fprintf(stdout, color, " [%#08zx] Diag Def:%04x %c\n", + pos, diag->def, diag->I ? 'I' : ' '); + return true; +} + +/* Return TOD timestamp contained in an trailer entry */ +static unsigned long long trailer_timestamp(struct hws_trailer_entry *te) +{ + /* te->t set: TOD in STCKE format, bytes 8-15 + * to->t not set: TOD in STCK format, bytes 0-7 + */ + unsigned long long ts; + + memcpy(&ts, &te->timestamp[te->t], sizeof(ts)); + return ts; +} + +/* Display s390 CPU measurement facility trailer entry */ +static bool s390_cpumsf_trailer_show(const char *color, size_t pos, + struct hws_trailer_entry *te) +{ + if (te->bsdes != sizeof(struct hws_basic_entry)) { + pr_err("Invalid AUX trace trailer entry [%#08zx]\n", pos); + return false; + } + color_fprintf(stdout, color, " [%#08zx] Trailer %c%c%c bsdes:%d" + " dsdes:%d Overflow:%lld Time:%#llx\n" + "\t\tC:%d TOD:%#lx 1:%#llx 2:%#llx\n", + pos, + te->f ? 'F' : ' ', + te->a ? 'A' : ' ', + te->t ? 'T' : ' ', + te->bsdes, te->dsdes, te->overflow, + trailer_timestamp(te), te->clock_base, te->progusage2, + te->progusage[0], te->progusage[1]); + return true; +} + +/* Test a sample data block. It must be 4KB or a multiple thereof in size and + * 4KB page aligned. Each sample data page has a trailer entry at the + * end which contains the sample entry data sizes. + * + * Return true if the sample data block passes the checks and set the + * basic set entry size and diagnostic set entry size. + * + * Return false on failure. + * + * Note: Old hardware does not set the basic or diagnostic entry sizes + * in the trailer entry. Use the type number instead. + */ +static bool s390_cpumsf_validate(int machine_type, + unsigned char *buf, size_t len, + unsigned short *bsdes, + unsigned short *dsdes) +{ + struct hws_basic_entry *basic = (struct hws_basic_entry *)buf; + struct hws_trailer_entry *te; + + *dsdes = *bsdes = 0; + if (len & (S390_CPUMSF_PAGESZ - 1)) /* Illegal size */ + return false; + if (basic->def != 1) /* No basic set entry, must be first */ + return false; + /* Check for trailer entry at end of SDB */ + te = (struct hws_trailer_entry *)(buf + S390_CPUMSF_PAGESZ + - sizeof(*te)); + *bsdes = te->bsdes; + *dsdes = te->dsdes; + if (!te->bsdes && !te->dsdes) { + /* Very old hardware, use CPUID */ + switch (machine_type) { + case 2097: + case 2098: + *dsdes = 64; + *bsdes = 32; + break; + case 2817: + case 2818: + *dsdes = 74; + *bsdes = 32; + break; + case 2827: + case 2828: + *dsdes = 85; + *bsdes = 32; + break; + default: + /* Illegal trailer entry */ + return false; + } + } + return true; +} + +/* Return true if there is room for another entry */ +static bool s390_cpumsf_reached_trailer(size_t entry_sz, size_t pos) +{ + size_t payload = S390_CPUMSF_PAGESZ - sizeof(struct hws_trailer_entry); + + if (payload - (pos & (S390_CPUMSF_PAGESZ - 1)) < entry_sz) + return false; + return true; +} + +/* Dump an auxiliary buffer. These buffers are multiple of + * 4KB SDB pages. + */ +static void s390_cpumsf_dump(struct s390_cpumsf *sf, + unsigned char *buf, size_t len) +{ + const char *color = PERF_COLOR_BLUE; + struct hws_basic_entry *basic; + struct hws_diag_entry *diag; + unsigned short bsdes, dsdes; + size_t pos = 0; + + color_fprintf(stdout, color, + ". ... s390 AUX data: size %zu bytes\n", + len); + + if (!s390_cpumsf_validate(sf->machine_type, buf, len, &bsdes, + &dsdes)) { + pr_err("Invalid AUX trace data block size:%zu" + " (type:%d bsdes:%hd dsdes:%hd)\n", + len, sf->machine_type, bsdes, dsdes); + return; + } + + /* s390 kernel always returns 4KB blocks fully occupied, + * no partially filled SDBs. + */ + while (pos < len) { + /* Handle Basic entry */ + basic = (struct hws_basic_entry *)(buf + pos); + if (s390_cpumsf_basic_show(color, pos, basic)) + pos += bsdes; + else + return; + + /* Handle Diagnostic entry */ + diag = (struct hws_diag_entry *)(buf + pos); + if (s390_cpumsf_diag_show(color, pos, diag)) + pos += dsdes; + else + return; + + /* Check for trailer entry */ + if (!s390_cpumsf_reached_trailer(bsdes + dsdes, pos)) { + /* Show trailer entry */ + struct hws_trailer_entry te; + + pos = (pos + S390_CPUMSF_PAGESZ) + & ~(S390_CPUMSF_PAGESZ - 1); + pos -= sizeof(te); + memcpy(&te, buf + pos, sizeof(te)); + /* Set descriptor sizes in case of old hardware + * where these values are not set. + */ + te.bsdes = bsdes; + te.dsdes = dsdes; + if (s390_cpumsf_trailer_show(color, pos, &te)) + pos += sizeof(te); + else + return; + } + } +} + +static void s390_cpumsf_dump_event(struct s390_cpumsf *sf, unsigned char *buf, + size_t len) +{ + printf(".\n"); + s390_cpumsf_dump(sf, buf, len); +} + +#define S390_LPP_PID_MASK 0xffffffff + +static bool s390_cpumsf_make_event(size_t pos, + struct hws_basic_entry *basic, + struct s390_cpumsf_queue *sfq) +{ + struct perf_sample sample = { + .ip = basic->ia, + .pid = basic->hpp & S390_LPP_PID_MASK, + .tid = basic->hpp & S390_LPP_PID_MASK, + .cpumode = PERF_RECORD_MISC_CPUMODE_UNKNOWN, + .cpu = sfq->cpu, + .period = 1 + }; + union perf_event event; + + memset(&event, 0, sizeof(event)); + if (basic->CL == 1) /* Native LPAR mode */ + sample.cpumode = basic->P ? PERF_RECORD_MISC_USER + : PERF_RECORD_MISC_KERNEL; + else if (basic->CL == 2) /* Guest kernel/user space */ + sample.cpumode = basic->P ? PERF_RECORD_MISC_GUEST_USER + : PERF_RECORD_MISC_GUEST_KERNEL; + else if (basic->gpp || basic->prim_asn != 0xffff) + /* Use heuristics on old hardware */ + sample.cpumode = basic->P ? PERF_RECORD_MISC_GUEST_USER + : PERF_RECORD_MISC_GUEST_KERNEL; + else + sample.cpumode = basic->P ? PERF_RECORD_MISC_USER + : PERF_RECORD_MISC_KERNEL; + + event.sample.header.type = PERF_RECORD_SAMPLE; + event.sample.header.misc = sample.cpumode; + event.sample.header.size = sizeof(struct perf_event_header); + + pr_debug4("%s pos:%#zx ip:%#" PRIx64 " P:%d CL:%d pid:%d.%d cpumode:%d cpu:%d\n", + __func__, pos, sample.ip, basic->P, basic->CL, sample.pid, + sample.tid, sample.cpumode, sample.cpu); + if (perf_session__deliver_synth_event(sfq->sf->session, &event, + &sample)) { + pr_err("s390 Auxiliary Trace: failed to deliver event\n"); + return false; + } + return true; +} + +static unsigned long long get_trailer_time(const unsigned char *buf) +{ + struct hws_trailer_entry *te; + unsigned long long aux_time; + + te = (struct hws_trailer_entry *)(buf + S390_CPUMSF_PAGESZ + - sizeof(*te)); + + if (!te->clock_base) /* TOD_CLOCK_BASE value missing */ + return 0; + + /* Correct calculation to convert time stamp in trailer entry to + * nano seconds (taken from arch/s390 function tod_to_ns()). + * TOD_CLOCK_BASE is stored in trailer entry member progusage2. + */ + aux_time = trailer_timestamp(te) - te->progusage2; + aux_time = (aux_time >> 9) * 125 + (((aux_time & 0x1ff) * 125) >> 9); + return aux_time; +} + +/* Process the data samples of a single queue. The first parameter is a + * pointer to the queue, the second parameter is the time stamp. This + * is the time stamp: + * - of the event that triggered this processing. + * - or the time stamp when the last proccesing of this queue stopped. + * In this case it stopped at a 4KB page boundary and record the + * position on where to continue processing on the next invocation + * (see buffer->use_data and buffer->use_size). + * + * When this function returns the second parameter is updated to + * reflect the time stamp of the last processed auxiliary data entry + * (taken from the trailer entry of that page). The caller uses this + * returned time stamp to record the last processed entry in this + * queue. + * + * The function returns: + * 0: Processing successful. The second parameter returns the + * time stamp from the trailer entry until which position + * processing took place. Subsequent calls resume from this + * position. + * <0: An error occurred during processing. The second parameter + * returns the maximum time stamp. + * >0: Done on this queue. The second parameter returns the + * maximum time stamp. + */ +static int s390_cpumsf_samples(struct s390_cpumsf_queue *sfq, u64 *ts) +{ + struct s390_cpumsf *sf = sfq->sf; + unsigned char *buf = sfq->buffer->use_data; + size_t len = sfq->buffer->use_size; + struct hws_basic_entry *basic; + unsigned short bsdes, dsdes; + size_t pos = 0; + int err = 1; + u64 aux_ts; + + if (!s390_cpumsf_validate(sf->machine_type, buf, len, &bsdes, + &dsdes)) { + *ts = ~0ULL; + return -1; + } + + /* Get trailer entry time stamp and check if entries in + * this auxiliary page are ready for processing. If the + * time stamp of the first entry is too high, whole buffer + * can be skipped. In this case return time stamp. + */ + aux_ts = get_trailer_time(buf); + if (!aux_ts) { + pr_err("[%#08" PRIx64 "] Invalid AUX trailer entry TOD clock base\n", + sfq->buffer->data_offset); + aux_ts = ~0ULL; + goto out; + } + if (aux_ts > *ts) { + *ts = aux_ts; + return 0; + } + + while (pos < len) { + /* Handle Basic entry */ + basic = (struct hws_basic_entry *)(buf + pos); + if (s390_cpumsf_make_event(pos, basic, sfq)) + pos += bsdes; + else { + err = -EBADF; + goto out; + } + + pos += dsdes; /* Skip diagnositic entry */ + + /* Check for trailer entry */ + if (!s390_cpumsf_reached_trailer(bsdes + dsdes, pos)) { + pos = (pos + S390_CPUMSF_PAGESZ) + & ~(S390_CPUMSF_PAGESZ - 1); + /* Check existence of next page */ + if (pos >= len) + break; + aux_ts = get_trailer_time(buf + pos); + if (!aux_ts) { + aux_ts = ~0ULL; + goto out; + } + if (aux_ts > *ts) { + *ts = aux_ts; + sfq->buffer->use_data += pos; + sfq->buffer->use_size -= pos; + return 0; + } + } + } +out: + *ts = aux_ts; + sfq->buffer->use_size = 0; + sfq->buffer->use_data = NULL; + return err; /* Buffer completely scanned or error */ +} + +/* Run the s390 auxiliary trace decoder. + * Select the queue buffer to operate on, the caller already selected + * the proper queue, depending on second parameter 'ts'. + * This is the time stamp until which the auxiliary entries should + * be processed. This value is updated by called functions and + * returned to the caller. + * + * Resume processing in the current buffer. If there is no buffer + * get a new buffer from the queue and setup start position for + * processing. + * When a buffer is completely processed remove it from the queue + * before returning. + * + * This function returns + * 1: When the queue is empty. Second parameter will be set to + * maximum time stamp. + * 0: Normal processing done. + * <0: Error during queue buffer setup. This causes the caller + * to stop processing completely. + */ +static int s390_cpumsf_run_decoder(struct s390_cpumsf_queue *sfq, + u64 *ts) +{ + + struct auxtrace_buffer *buffer; + struct auxtrace_queue *queue; + int err; + + queue = &sfq->sf->queues.queue_array[sfq->queue_nr]; + + /* Get buffer and last position in buffer to resume + * decoding the auxiliary entries. One buffer might be large + * and decoding might stop in between. This depends on the time + * stamp of the trailer entry in each page of the auxiliary + * data and the time stamp of the event triggering the decoding. + */ + if (sfq->buffer == NULL) { + sfq->buffer = buffer = auxtrace_buffer__next(queue, + sfq->buffer); + if (!buffer) { + *ts = ~0ULL; + return 1; /* Processing done on this queue */ + } + /* Start with a new buffer on this queue */ + if (buffer->data) { + buffer->use_size = buffer->size; + buffer->use_data = buffer->data; + } + if (sfq->logfile) { /* Write into log file */ + size_t rc = fwrite(buffer->data, buffer->size, 1, + sfq->logfile); + if (rc != 1) + pr_err("Failed to write auxiliary data\n"); + } + } else + buffer = sfq->buffer; + + if (!buffer->data) { + int fd = perf_data__fd(sfq->sf->session->data); + + buffer->data = auxtrace_buffer__get_data(buffer, fd); + if (!buffer->data) + return -ENOMEM; + buffer->use_size = buffer->size; + buffer->use_data = buffer->data; + + if (sfq->logfile) { /* Write into log file */ + size_t rc = fwrite(buffer->data, buffer->size, 1, + sfq->logfile); + if (rc != 1) + pr_err("Failed to write auxiliary data\n"); + } + } + pr_debug4("%s queue_nr:%d buffer:%" PRId64 " offset:%#" PRIx64 " size:%#zx rest:%#zx\n", + __func__, sfq->queue_nr, buffer->buffer_nr, buffer->offset, + buffer->size, buffer->use_size); + err = s390_cpumsf_samples(sfq, ts); + + /* If non-zero, there is either an error (err < 0) or the buffer is + * completely done (err > 0). The error is unrecoverable, usually + * some descriptors could not be read successfully, so continue with + * the next buffer. + * In both cases the parameter 'ts' has been updated. + */ + if (err) { + sfq->buffer = NULL; + list_del(&buffer->list); + auxtrace_buffer__free(buffer); + if (err > 0) /* Buffer done, no error */ + err = 0; + } + return err; +} + +static struct s390_cpumsf_queue * +s390_cpumsf_alloc_queue(struct s390_cpumsf *sf, unsigned int queue_nr) +{ + struct s390_cpumsf_queue *sfq; + + sfq = zalloc(sizeof(struct s390_cpumsf_queue)); + if (sfq == NULL) + return NULL; + + sfq->sf = sf; + sfq->queue_nr = queue_nr; + sfq->cpu = -1; + if (sf->use_logfile) { + char *name; + int rc; + + rc = (sf->logdir) + ? asprintf(&name, "%s/aux.smp.%02x", + sf->logdir, queue_nr) + : asprintf(&name, "aux.smp.%02x", queue_nr); + if (rc > 0) + sfq->logfile = fopen(name, "w"); + if (sfq->logfile == NULL) { + pr_err("Failed to open auxiliary log file %s," + "continue...\n", name); + sf->use_logfile = false; + } + free(name); + } + return sfq; +} + +static int s390_cpumsf_setup_queue(struct s390_cpumsf *sf, + struct auxtrace_queue *queue, + unsigned int queue_nr, u64 ts) +{ + struct s390_cpumsf_queue *sfq = queue->priv; + + if (list_empty(&queue->head)) + return 0; + + if (sfq == NULL) { + sfq = s390_cpumsf_alloc_queue(sf, queue_nr); + if (!sfq) + return -ENOMEM; + queue->priv = sfq; + + if (queue->cpu != -1) + sfq->cpu = queue->cpu; + } + return auxtrace_heap__add(&sf->heap, queue_nr, ts); +} + +static int s390_cpumsf_setup_queues(struct s390_cpumsf *sf, u64 ts) +{ + unsigned int i; + int ret = 0; + + for (i = 0; i < sf->queues.nr_queues; i++) { + ret = s390_cpumsf_setup_queue(sf, &sf->queues.queue_array[i], + i, ts); + if (ret) + break; + } + return ret; +} + +static int s390_cpumsf_update_queues(struct s390_cpumsf *sf, u64 ts) +{ + if (!sf->queues.new_data) + return 0; + + sf->queues.new_data = false; + return s390_cpumsf_setup_queues(sf, ts); +} + +static int s390_cpumsf_process_queues(struct s390_cpumsf *sf, u64 timestamp) +{ + unsigned int queue_nr; + u64 ts; + int ret; + + while (1) { + struct auxtrace_queue *queue; + struct s390_cpumsf_queue *sfq; + + if (!sf->heap.heap_cnt) + return 0; + + if (sf->heap.heap_array[0].ordinal >= timestamp) + return 0; + + queue_nr = sf->heap.heap_array[0].queue_nr; + queue = &sf->queues.queue_array[queue_nr]; + sfq = queue->priv; + + auxtrace_heap__pop(&sf->heap); + if (sf->heap.heap_cnt) { + ts = sf->heap.heap_array[0].ordinal + 1; + if (ts > timestamp) + ts = timestamp; + } else { + ts = timestamp; + } + + ret = s390_cpumsf_run_decoder(sfq, &ts); + if (ret < 0) { + auxtrace_heap__add(&sf->heap, queue_nr, ts); + return ret; + } + if (!ret) { + ret = auxtrace_heap__add(&sf->heap, queue_nr, ts); + if (ret < 0) + return ret; + } + } + return 0; +} + +static int s390_cpumsf_synth_error(struct s390_cpumsf *sf, int code, int cpu, + pid_t pid, pid_t tid, u64 ip) +{ + char msg[MAX_AUXTRACE_ERROR_MSG]; + union perf_event event; + int err; + + strncpy(msg, "Lost Auxiliary Trace Buffer", sizeof(msg) - 1); + auxtrace_synth_error(&event.auxtrace_error, PERF_AUXTRACE_ERROR_ITRACE, + code, cpu, pid, tid, ip, msg); + + err = perf_session__deliver_synth_event(sf->session, &event, NULL); + if (err) + pr_err("s390 Auxiliary Trace: failed to deliver error event," + "error %d\n", err); + return err; +} + +static int s390_cpumsf_lost(struct s390_cpumsf *sf, struct perf_sample *sample) +{ + return s390_cpumsf_synth_error(sf, 1, sample->cpu, + sample->pid, sample->tid, 0); +} + +static int +s390_cpumsf_process_event(struct perf_session *session __maybe_unused, + union perf_event *event, + struct perf_sample *sample, + struct perf_tool *tool) +{ + struct s390_cpumsf *sf = container_of(session->auxtrace, + struct s390_cpumsf, + auxtrace); + u64 timestamp = sample->time; + int err = 0; + + if (dump_trace) + return 0; + + if (!tool->ordered_events) { + pr_err("s390 Auxiliary Trace requires ordered events\n"); + return -EINVAL; + } + + if (event->header.type == PERF_RECORD_AUX && + event->aux.flags & PERF_AUX_FLAG_TRUNCATED) + return s390_cpumsf_lost(sf, sample); + + if (timestamp) { + err = s390_cpumsf_update_queues(sf, timestamp); + if (!err) + err = s390_cpumsf_process_queues(sf, timestamp); + } + return err; +} + +struct s390_cpumsf_synth { + struct perf_tool cpumsf_tool; + struct perf_session *session; +}; + +static int +s390_cpumsf_process_auxtrace_event(struct perf_session *session, + union perf_event *event __maybe_unused, + struct perf_tool *tool __maybe_unused) +{ + struct s390_cpumsf *sf = container_of(session->auxtrace, + struct s390_cpumsf, + auxtrace); + + int fd = perf_data__fd(session->data); + struct auxtrace_buffer *buffer; + off_t data_offset; + int err; + + if (sf->data_queued) + return 0; + + if (perf_data__is_pipe(session->data)) { + data_offset = 0; + } else { + data_offset = lseek(fd, 0, SEEK_CUR); + if (data_offset == -1) + return -errno; + } + + err = auxtrace_queues__add_event(&sf->queues, session, event, + data_offset, &buffer); + if (err) + return err; + + /* Dump here after copying piped trace out of the pipe */ + if (dump_trace) { + if (auxtrace_buffer__get_data(buffer, fd)) { + s390_cpumsf_dump_event(sf, buffer->data, + buffer->size); + auxtrace_buffer__put_data(buffer); + } + } + return 0; +} + +static void s390_cpumsf_free_events(struct perf_session *session __maybe_unused) +{ +} + +static int s390_cpumsf_flush(struct perf_session *session __maybe_unused, + struct perf_tool *tool __maybe_unused) +{ + return 0; +} + +static void s390_cpumsf_free_queues(struct perf_session *session) +{ + struct s390_cpumsf *sf = container_of(session->auxtrace, + struct s390_cpumsf, + auxtrace); + struct auxtrace_queues *queues = &sf->queues; + unsigned int i; + + for (i = 0; i < queues->nr_queues; i++) { + struct s390_cpumsf_queue *sfq = (struct s390_cpumsf_queue *) + queues->queue_array[i].priv; + + if (sfq != NULL && sfq->logfile) { + fclose(sfq->logfile); + sfq->logfile = NULL; + } + zfree(&queues->queue_array[i].priv); + } + auxtrace_queues__free(queues); +} + +static void s390_cpumsf_free(struct perf_session *session) +{ + struct s390_cpumsf *sf = container_of(session->auxtrace, + struct s390_cpumsf, + auxtrace); + + auxtrace_heap__free(&sf->heap); + s390_cpumsf_free_queues(session); + session->auxtrace = NULL; + free(sf->logdir); + free(sf); +} + +static int s390_cpumsf_get_type(const char *cpuid) +{ + int ret, family = 0; + + ret = sscanf(cpuid, "%*[^,],%u", &family); + return (ret == 1) ? family : 0; +} + +/* Check itrace options set on perf report command. + * Return true, if none are set or all options specified can be + * handled on s390 (currently only option 'd' for logging. + * Return false otherwise. + */ +static bool check_auxtrace_itrace(struct itrace_synth_opts *itops) +{ + bool ison = false; + + if (!itops || !itops->set) + return true; + ison = itops->inject || itops->instructions || itops->branches || + itops->transactions || itops->ptwrites || + itops->pwr_events || itops->errors || + itops->dont_decode || itops->calls || itops->returns || + itops->callchain || itops->thread_stack || + itops->last_branch; + if (!ison) + return true; + pr_err("Unsupported --itrace options specified\n"); + return false; +} + +/* Check for AUXTRACE dump directory if it is needed. + * On failure print an error message but continue. + * Return 0 on wrong keyword in config file and 1 otherwise. + */ +static int s390_cpumsf__config(const char *var, const char *value, void *cb) +{ + struct s390_cpumsf *sf = cb; + struct stat stbuf; + int rc; + + if (strcmp(var, "auxtrace.dumpdir")) + return 0; + sf->logdir = strdup(value); + if (sf->logdir == NULL) { + pr_err("Failed to find auxtrace log directory %s," + " continue with current directory...\n", value); + return 1; + } + rc = stat(sf->logdir, &stbuf); + if (rc == -1 || !S_ISDIR(stbuf.st_mode)) { + pr_err("Missing auxtrace log directory %s," + " continue with current directory...\n", value); + free(sf->logdir); + sf->logdir = NULL; + } + return 1; +} + +int s390_cpumsf_process_auxtrace_info(union perf_event *event, + struct perf_session *session) +{ + struct auxtrace_info_event *auxtrace_info = &event->auxtrace_info; + struct s390_cpumsf *sf; + int err; + + if (auxtrace_info->header.size < sizeof(struct auxtrace_info_event)) + return -EINVAL; + + sf = zalloc(sizeof(struct s390_cpumsf)); + if (sf == NULL) + return -ENOMEM; + + if (!check_auxtrace_itrace(session->itrace_synth_opts)) { + err = -EINVAL; + goto err_free; + } + sf->use_logfile = session->itrace_synth_opts->log; + if (sf->use_logfile) + perf_config(s390_cpumsf__config, sf); + + err = auxtrace_queues__init(&sf->queues); + if (err) + goto err_free; + + sf->session = session; + sf->machine = &session->machines.host; /* No kvm support */ + sf->auxtrace_type = auxtrace_info->type; + sf->pmu_type = PERF_TYPE_RAW; + sf->machine_type = s390_cpumsf_get_type(session->evlist->env->cpuid); + + sf->auxtrace.process_event = s390_cpumsf_process_event; + sf->auxtrace.process_auxtrace_event = s390_cpumsf_process_auxtrace_event; + sf->auxtrace.flush_events = s390_cpumsf_flush; + sf->auxtrace.free_events = s390_cpumsf_free_events; + sf->auxtrace.free = s390_cpumsf_free; + session->auxtrace = &sf->auxtrace; + + if (dump_trace) + return 0; + + err = auxtrace_queues__process_index(&sf->queues, session); + if (err) + goto err_free_queues; + + if (sf->queues.populated) + sf->data_queued = true; + + return 0; + +err_free_queues: + auxtrace_queues__free(&sf->queues); + session->auxtrace = NULL; +err_free: + free(sf->logdir); + free(sf); + return err; +} diff --git a/tools/perf/util/s390-cpumsf.h b/tools/perf/util/s390-cpumsf.h new file mode 100644 index 000000000000..fb64d100555c --- /dev/null +++ b/tools/perf/util/s390-cpumsf.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright IBM Corp. 2018 + * Auxtrace support for s390 CPU-Measurement Sampling Facility + * + * Author(s): Thomas Richter <tmricht@linux.ibm.com> + */ + +#ifndef INCLUDE__PERF_S390_CPUMSF_H +#define INCLUDE__PERF_S390_CPUMSF_H + +union perf_event; +struct perf_session; +struct perf_pmu; + +struct auxtrace_record * +s390_cpumsf_recording_init(int *err, struct perf_pmu *s390_cpumsf_pmu); + +int s390_cpumsf_process_auxtrace_info(union perf_event *event, + struct perf_session *session); +#endif diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c index 7b79c413486b..89cb887648f9 100644 --- a/tools/perf/util/scripting-engines/trace-event-perl.c +++ b/tools/perf/util/scripting-engines/trace-event-perl.c @@ -99,7 +99,7 @@ static void define_symbolic_value(const char *ev_name, LEAVE; } -static void define_symbolic_values(struct print_flag_sym *field, +static void define_symbolic_values(struct tep_print_flag_sym *field, const char *ev_name, const char *field_name) { @@ -157,7 +157,7 @@ static void define_flag_value(const char *ev_name, LEAVE; } -static void define_flag_values(struct print_flag_sym *field, +static void define_flag_values(struct tep_print_flag_sym *field, const char *ev_name, const char *field_name) { @@ -189,62 +189,62 @@ static void define_flag_field(const char *ev_name, LEAVE; } -static void define_event_symbols(struct event_format *event, +static void define_event_symbols(struct tep_event_format *event, const char *ev_name, - struct print_arg *args) + struct tep_print_arg *args) { if (args == NULL) return; switch (args->type) { - case PRINT_NULL: + case TEP_PRINT_NULL: break; - case PRINT_ATOM: + case TEP_PRINT_ATOM: define_flag_value(ev_name, cur_field_name, "0", args->atom.atom); zero_flag_atom = 0; break; - case PRINT_FIELD: + case TEP_PRINT_FIELD: free(cur_field_name); cur_field_name = strdup(args->field.name); break; - case PRINT_FLAGS: + case TEP_PRINT_FLAGS: define_event_symbols(event, ev_name, args->flags.field); define_flag_field(ev_name, cur_field_name, args->flags.delim); define_flag_values(args->flags.flags, ev_name, cur_field_name); break; - case PRINT_SYMBOL: + case TEP_PRINT_SYMBOL: define_event_symbols(event, ev_name, args->symbol.field); define_symbolic_field(ev_name, cur_field_name); define_symbolic_values(args->symbol.symbols, ev_name, cur_field_name); break; - case PRINT_HEX: - case PRINT_HEX_STR: + case TEP_PRINT_HEX: + case TEP_PRINT_HEX_STR: define_event_symbols(event, ev_name, args->hex.field); define_event_symbols(event, ev_name, args->hex.size); break; - case PRINT_INT_ARRAY: + case TEP_PRINT_INT_ARRAY: define_event_symbols(event, ev_name, args->int_array.field); define_event_symbols(event, ev_name, args->int_array.count); define_event_symbols(event, ev_name, args->int_array.el_size); break; - case PRINT_BSTRING: - case PRINT_DYNAMIC_ARRAY: - case PRINT_DYNAMIC_ARRAY_LEN: - case PRINT_STRING: - case PRINT_BITMASK: + case TEP_PRINT_BSTRING: + case TEP_PRINT_DYNAMIC_ARRAY: + case TEP_PRINT_DYNAMIC_ARRAY_LEN: + case TEP_PRINT_STRING: + case TEP_PRINT_BITMASK: break; - case PRINT_TYPE: + case TEP_PRINT_TYPE: define_event_symbols(event, ev_name, args->typecast.item); break; - case PRINT_OP: + case TEP_PRINT_OP: if (strcmp(args->op.op, ":") == 0) zero_flag_atom = 1; define_event_symbols(event, ev_name, args->op.left); define_event_symbols(event, ev_name, args->op.right); break; - case PRINT_FUNC: + case TEP_PRINT_FUNC: default: pr_err("Unsupported print arg type\n"); /* we should warn... */ @@ -338,8 +338,8 @@ static void perl_process_tracepoint(struct perf_sample *sample, struct addr_location *al) { struct thread *thread = al->thread; - struct event_format *event = evsel->tp_format; - struct format_field *field; + struct tep_event_format *event = evsel->tp_format; + struct tep_format_field *field; static char handler[256]; unsigned long long val; unsigned long s, ns; @@ -388,9 +388,9 @@ static void perl_process_tracepoint(struct perf_sample *sample, /* common fields other than pid can be accessed via xsub fns */ for (field = event->format.fields; field; field = field->next) { - if (field->flags & FIELD_IS_STRING) { + if (field->flags & TEP_FIELD_IS_STRING) { int offset; - if (field->flags & FIELD_IS_DYNAMIC) { + if (field->flags & TEP_FIELD_IS_DYNAMIC) { offset = *(int *)(data + field->offset); offset &= 0xffff; } else @@ -399,7 +399,7 @@ static void perl_process_tracepoint(struct perf_sample *sample, } else { /* FIELD_IS_NUMERIC */ val = read_size(event, data + field->offset, field->size); - if (field->flags & FIELD_IS_SIGNED) { + if (field->flags & TEP_FIELD_IS_SIGNED) { XPUSHs(sv_2mortal(newSViv(val))); } else { XPUSHs(sv_2mortal(newSVuv(val))); @@ -535,10 +535,10 @@ static int perl_stop_script(void) return 0; } -static int perl_generate_script(struct pevent *pevent, const char *outfile) +static int perl_generate_script(struct tep_handle *pevent, const char *outfile) { - struct event_format *event = NULL; - struct format_field *f; + struct tep_event_format *event = NULL; + struct tep_format_field *f; char fname[PATH_MAX]; int not_first, count; FILE *ofp; @@ -646,11 +646,11 @@ sub print_backtrace\n\ count++; fprintf(ofp, "%s=", f->name); - if (f->flags & FIELD_IS_STRING || - f->flags & FIELD_IS_FLAG || - f->flags & FIELD_IS_SYMBOLIC) + if (f->flags & TEP_FIELD_IS_STRING || + f->flags & TEP_FIELD_IS_FLAG || + f->flags & TEP_FIELD_IS_SYMBOLIC) fprintf(ofp, "%%s"); - else if (f->flags & FIELD_IS_SIGNED) + else if (f->flags & TEP_FIELD_IS_SIGNED) fprintf(ofp, "%%d"); else fprintf(ofp, "%%u"); @@ -668,7 +668,7 @@ sub print_backtrace\n\ if (++count % 5 == 0) fprintf(ofp, "\n\t "); - if (f->flags & FIELD_IS_FLAG) { + if (f->flags & TEP_FIELD_IS_FLAG) { if ((count - 1) % 5 != 0) { fprintf(ofp, "\n\t "); count = 4; @@ -678,7 +678,7 @@ sub print_backtrace\n\ event->name); fprintf(ofp, "\"%s\", $%s)", f->name, f->name); - } else if (f->flags & FIELD_IS_SYMBOLIC) { + } else if (f->flags & TEP_FIELD_IS_SYMBOLIC) { if ((count - 1) % 5 != 0) { fprintf(ofp, "\n\t "); count = 4; diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index bc32e57d17be..69aa93d4ee99 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -193,7 +193,7 @@ static void try_call_object(const char *handler_name, PyObject *args) call_object(handler, args, handler_name); } -static void define_value(enum print_arg_type field_type, +static void define_value(enum tep_print_arg_type field_type, const char *ev_name, const char *field_name, const char *field_value, @@ -204,7 +204,7 @@ static void define_value(enum print_arg_type field_type, unsigned long long value; unsigned n = 0; - if (field_type == PRINT_SYMBOL) + if (field_type == TEP_PRINT_SYMBOL) handler_name = "define_symbolic_value"; t = PyTuple_New(4); @@ -223,8 +223,8 @@ static void define_value(enum print_arg_type field_type, Py_DECREF(t); } -static void define_values(enum print_arg_type field_type, - struct print_flag_sym *field, +static void define_values(enum tep_print_arg_type field_type, + struct tep_print_flag_sym *field, const char *ev_name, const char *field_name) { @@ -235,7 +235,7 @@ static void define_values(enum print_arg_type field_type, define_values(field_type, field->next, ev_name, field_name); } -static void define_field(enum print_arg_type field_type, +static void define_field(enum tep_print_arg_type field_type, const char *ev_name, const char *field_name, const char *delim) @@ -244,10 +244,10 @@ static void define_field(enum print_arg_type field_type, PyObject *t; unsigned n = 0; - if (field_type == PRINT_SYMBOL) + if (field_type == TEP_PRINT_SYMBOL) handler_name = "define_symbolic_field"; - if (field_type == PRINT_FLAGS) + if (field_type == TEP_PRINT_FLAGS) t = PyTuple_New(3); else t = PyTuple_New(2); @@ -256,7 +256,7 @@ static void define_field(enum print_arg_type field_type, PyTuple_SetItem(t, n++, _PyUnicode_FromString(ev_name)); PyTuple_SetItem(t, n++, _PyUnicode_FromString(field_name)); - if (field_type == PRINT_FLAGS) + if (field_type == TEP_PRINT_FLAGS) PyTuple_SetItem(t, n++, _PyUnicode_FromString(delim)); try_call_object(handler_name, t); @@ -264,54 +264,54 @@ static void define_field(enum print_arg_type field_type, Py_DECREF(t); } -static void define_event_symbols(struct event_format *event, +static void define_event_symbols(struct tep_event_format *event, const char *ev_name, - struct print_arg *args) + struct tep_print_arg *args) { if (args == NULL) return; switch (args->type) { - case PRINT_NULL: + case TEP_PRINT_NULL: break; - case PRINT_ATOM: - define_value(PRINT_FLAGS, ev_name, cur_field_name, "0", + case TEP_PRINT_ATOM: + define_value(TEP_PRINT_FLAGS, ev_name, cur_field_name, "0", args->atom.atom); zero_flag_atom = 0; break; - case PRINT_FIELD: + case TEP_PRINT_FIELD: free(cur_field_name); cur_field_name = strdup(args->field.name); break; - case PRINT_FLAGS: + case TEP_PRINT_FLAGS: define_event_symbols(event, ev_name, args->flags.field); - define_field(PRINT_FLAGS, ev_name, cur_field_name, + define_field(TEP_PRINT_FLAGS, ev_name, cur_field_name, args->flags.delim); - define_values(PRINT_FLAGS, args->flags.flags, ev_name, + define_values(TEP_PRINT_FLAGS, args->flags.flags, ev_name, cur_field_name); break; - case PRINT_SYMBOL: + case TEP_PRINT_SYMBOL: define_event_symbols(event, ev_name, args->symbol.field); - define_field(PRINT_SYMBOL, ev_name, cur_field_name, NULL); - define_values(PRINT_SYMBOL, args->symbol.symbols, ev_name, + define_field(TEP_PRINT_SYMBOL, ev_name, cur_field_name, NULL); + define_values(TEP_PRINT_SYMBOL, args->symbol.symbols, ev_name, cur_field_name); break; - case PRINT_HEX: - case PRINT_HEX_STR: + case TEP_PRINT_HEX: + case TEP_PRINT_HEX_STR: define_event_symbols(event, ev_name, args->hex.field); define_event_symbols(event, ev_name, args->hex.size); break; - case PRINT_INT_ARRAY: + case TEP_PRINT_INT_ARRAY: define_event_symbols(event, ev_name, args->int_array.field); define_event_symbols(event, ev_name, args->int_array.count); define_event_symbols(event, ev_name, args->int_array.el_size); break; - case PRINT_STRING: + case TEP_PRINT_STRING: break; - case PRINT_TYPE: + case TEP_PRINT_TYPE: define_event_symbols(event, ev_name, args->typecast.item); break; - case PRINT_OP: + case TEP_PRINT_OP: if (strcmp(args->op.op, ":") == 0) zero_flag_atom = 1; define_event_symbols(event, ev_name, args->op.left); @@ -319,11 +319,11 @@ static void define_event_symbols(struct event_format *event, break; default: /* gcc warns for these? */ - case PRINT_BSTRING: - case PRINT_DYNAMIC_ARRAY: - case PRINT_DYNAMIC_ARRAY_LEN: - case PRINT_FUNC: - case PRINT_BITMASK: + case TEP_PRINT_BSTRING: + case TEP_PRINT_DYNAMIC_ARRAY: + case TEP_PRINT_DYNAMIC_ARRAY_LEN: + case TEP_PRINT_FUNC: + case TEP_PRINT_BITMASK: /* we should warn... */ return; } @@ -332,10 +332,10 @@ static void define_event_symbols(struct event_format *event, define_event_symbols(event, ev_name, args->next); } -static PyObject *get_field_numeric_entry(struct event_format *event, - struct format_field *field, void *data) +static PyObject *get_field_numeric_entry(struct tep_event_format *event, + struct tep_format_field *field, void *data) { - bool is_array = field->flags & FIELD_IS_ARRAY; + bool is_array = field->flags & TEP_FIELD_IS_ARRAY; PyObject *obj = NULL, *list = NULL; unsigned long long val; unsigned int item_size, n_items, i; @@ -353,7 +353,7 @@ static PyObject *get_field_numeric_entry(struct event_format *event, val = read_size(event, data + field->offset + i * item_size, item_size); - if (field->flags & FIELD_IS_SIGNED) { + if (field->flags & TEP_FIELD_IS_SIGNED) { if ((long long)val >= LONG_MIN && (long long)val <= LONG_MAX) obj = _PyLong_FromLong(val); @@ -790,11 +790,11 @@ static void python_process_tracepoint(struct perf_sample *sample, struct perf_evsel *evsel, struct addr_location *al) { - struct event_format *event = evsel->tp_format; + struct tep_event_format *event = evsel->tp_format; PyObject *handler, *context, *t, *obj = NULL, *callchain; PyObject *dict = NULL, *all_entries_dict = NULL; static char handler_name[256]; - struct format_field *field; + struct tep_format_field *field; unsigned long s, ns; unsigned n = 0; int pid; @@ -867,22 +867,22 @@ static void python_process_tracepoint(struct perf_sample *sample, unsigned int offset, len; unsigned long long val; - if (field->flags & FIELD_IS_ARRAY) { + if (field->flags & TEP_FIELD_IS_ARRAY) { offset = field->offset; len = field->size; - if (field->flags & FIELD_IS_DYNAMIC) { - val = pevent_read_number(scripting_context->pevent, - data + offset, len); + if (field->flags & TEP_FIELD_IS_DYNAMIC) { + val = tep_read_number(scripting_context->pevent, + data + offset, len); offset = val; len = offset >> 16; offset &= 0xffff; } - if (field->flags & FIELD_IS_STRING && + if (field->flags & TEP_FIELD_IS_STRING && is_printable_array(data + offset, len)) { obj = _PyUnicode_FromString((char *) data + offset); } else { obj = PyByteArray_FromStringAndSize((const char *) data + offset, len); - field->flags &= ~FIELD_IS_STRING; + field->flags &= ~TEP_FIELD_IS_STRING; } } else { /* FIELD_IS_NUMERIC */ obj = get_field_numeric_entry(event, field, data); @@ -1588,10 +1588,10 @@ static int python_stop_script(void) return 0; } -static int python_generate_script(struct pevent *pevent, const char *outfile) +static int python_generate_script(struct tep_handle *pevent, const char *outfile) { - struct event_format *event = NULL; - struct format_field *f; + struct tep_event_format *event = NULL; + struct tep_format_field *f; char fname[PATH_MAX]; int not_first, count; FILE *ofp; @@ -1686,12 +1686,12 @@ static int python_generate_script(struct pevent *pevent, const char *outfile) count++; fprintf(ofp, "%s=", f->name); - if (f->flags & FIELD_IS_STRING || - f->flags & FIELD_IS_FLAG || - f->flags & FIELD_IS_ARRAY || - f->flags & FIELD_IS_SYMBOLIC) + if (f->flags & TEP_FIELD_IS_STRING || + f->flags & TEP_FIELD_IS_FLAG || + f->flags & TEP_FIELD_IS_ARRAY || + f->flags & TEP_FIELD_IS_SYMBOLIC) fprintf(ofp, "%%s"); - else if (f->flags & FIELD_IS_SIGNED) + else if (f->flags & TEP_FIELD_IS_SIGNED) fprintf(ofp, "%%d"); else fprintf(ofp, "%%u"); @@ -1709,7 +1709,7 @@ static int python_generate_script(struct pevent *pevent, const char *outfile) if (++count % 5 == 0) fprintf(ofp, "\n\t\t"); - if (f->flags & FIELD_IS_FLAG) { + if (f->flags & TEP_FIELD_IS_FLAG) { if ((count - 1) % 5 != 0) { fprintf(ofp, "\n\t\t"); count = 4; @@ -1719,7 +1719,7 @@ static int python_generate_script(struct pevent *pevent, const char *outfile) event->name); fprintf(ofp, "\"%s\", %s)", f->name, f->name); - } else if (f->flags & FIELD_IS_SYMBOLIC) { + } else if (f->flags & TEP_FIELD_IS_SYMBOLIC) { if ((count - 1) % 5 != 0) { fprintf(ofp, "\n\t\t"); count = 4; diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 8b9369303561..7d2c8ce6cfad 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -199,12 +199,10 @@ void perf_session__delete(struct perf_session *session) free(session); } -static int process_event_synth_tracing_data_stub(struct perf_tool *tool +static int process_event_synth_tracing_data_stub(struct perf_session *session __maybe_unused, union perf_event *event - __maybe_unused, - struct perf_session *session - __maybe_unused) + __maybe_unused) { dump_printf(": unhandled!\n"); return 0; @@ -277,10 +275,8 @@ static int skipn(int fd, off_t n) return 0; } -static s64 process_event_auxtrace_stub(struct perf_tool *tool __maybe_unused, - union perf_event *event, - struct perf_session *session - __maybe_unused) +static s64 process_event_auxtrace_stub(struct perf_session *session __maybe_unused, + union perf_event *event) { dump_printf(": unhandled!\n"); if (perf_data__is_pipe(session->data)) @@ -288,9 +284,8 @@ static s64 process_event_auxtrace_stub(struct perf_tool *tool __maybe_unused, return event->auxtrace.size; } -static int process_event_op2_stub(struct perf_tool *tool __maybe_unused, - union perf_event *event __maybe_unused, - struct perf_session *session __maybe_unused) +static int process_event_op2_stub(struct perf_session *session __maybe_unused, + union perf_event *event __maybe_unused) { dump_printf(": unhandled!\n"); return 0; @@ -298,9 +293,8 @@ static int process_event_op2_stub(struct perf_tool *tool __maybe_unused, static -int process_event_thread_map_stub(struct perf_tool *tool __maybe_unused, - union perf_event *event __maybe_unused, - struct perf_session *session __maybe_unused) +int process_event_thread_map_stub(struct perf_session *session __maybe_unused, + union perf_event *event __maybe_unused) { if (dump_trace) perf_event__fprintf_thread_map(event, stdout); @@ -310,9 +304,8 @@ int process_event_thread_map_stub(struct perf_tool *tool __maybe_unused, } static -int process_event_cpu_map_stub(struct perf_tool *tool __maybe_unused, - union perf_event *event __maybe_unused, - struct perf_session *session __maybe_unused) +int process_event_cpu_map_stub(struct perf_session *session __maybe_unused, + union perf_event *event __maybe_unused) { if (dump_trace) perf_event__fprintf_cpu_map(event, stdout); @@ -322,9 +315,8 @@ int process_event_cpu_map_stub(struct perf_tool *tool __maybe_unused, } static -int process_event_stat_config_stub(struct perf_tool *tool __maybe_unused, - union perf_event *event __maybe_unused, - struct perf_session *session __maybe_unused) +int process_event_stat_config_stub(struct perf_session *session __maybe_unused, + union perf_event *event __maybe_unused) { if (dump_trace) perf_event__fprintf_stat_config(event, stdout); @@ -333,10 +325,8 @@ int process_event_stat_config_stub(struct perf_tool *tool __maybe_unused, return 0; } -static int process_stat_stub(struct perf_tool *tool __maybe_unused, - union perf_event *event __maybe_unused, - struct perf_session *perf_session - __maybe_unused) +static int process_stat_stub(struct perf_session *perf_session __maybe_unused, + union perf_event *event) { if (dump_trace) perf_event__fprintf_stat(event, stdout); @@ -345,10 +335,8 @@ static int process_stat_stub(struct perf_tool *tool __maybe_unused, return 0; } -static int process_stat_round_stub(struct perf_tool *tool __maybe_unused, - union perf_event *event __maybe_unused, - struct perf_session *perf_session - __maybe_unused) +static int process_stat_round_stub(struct perf_session *perf_session __maybe_unused, + union perf_event *event) { if (dump_trace) perf_event__fprintf_stat_round(event, stdout); @@ -1374,37 +1362,37 @@ static s64 perf_session__process_user_event(struct perf_session *session, case PERF_RECORD_HEADER_TRACING_DATA: /* setup for reading amidst mmap */ lseek(fd, file_offset, SEEK_SET); - return tool->tracing_data(tool, event, session); + return tool->tracing_data(session, event); case PERF_RECORD_HEADER_BUILD_ID: - return tool->build_id(tool, event, session); + return tool->build_id(session, event); case PERF_RECORD_FINISHED_ROUND: return tool->finished_round(tool, event, oe); case PERF_RECORD_ID_INDEX: - return tool->id_index(tool, event, session); + return tool->id_index(session, event); case PERF_RECORD_AUXTRACE_INFO: - return tool->auxtrace_info(tool, event, session); + return tool->auxtrace_info(session, event); case PERF_RECORD_AUXTRACE: /* setup for reading amidst mmap */ lseek(fd, file_offset + event->header.size, SEEK_SET); - return tool->auxtrace(tool, event, session); + return tool->auxtrace(session, event); case PERF_RECORD_AUXTRACE_ERROR: perf_session__auxtrace_error_inc(session, event); - return tool->auxtrace_error(tool, event, session); + return tool->auxtrace_error(session, event); case PERF_RECORD_THREAD_MAP: - return tool->thread_map(tool, event, session); + return tool->thread_map(session, event); case PERF_RECORD_CPU_MAP: - return tool->cpu_map(tool, event, session); + return tool->cpu_map(session, event); case PERF_RECORD_STAT_CONFIG: - return tool->stat_config(tool, event, session); + return tool->stat_config(session, event); case PERF_RECORD_STAT: - return tool->stat(tool, event, session); + return tool->stat(session, event); case PERF_RECORD_STAT_ROUND: - return tool->stat_round(tool, event, session); + return tool->stat_round(session, event); case PERF_RECORD_TIME_CONV: session->time_conv = event->time_conv; - return tool->time_conv(tool, event, session); + return tool->time_conv(session, event); case PERF_RECORD_HEADER_FEATURE: - return tool->feature(tool, event, session); + return tool->feature(session, event); default: return -EINVAL; } @@ -2133,9 +2121,8 @@ out: return err; } -int perf_event__process_id_index(struct perf_tool *tool __maybe_unused, - union perf_event *event, - struct perf_session *session) +int perf_event__process_id_index(struct perf_session *session, + union perf_event *event) { struct perf_evlist *evlist = session->evlist; struct id_index_event *ie = &event->id_index; diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index da40b4b380ca..d96eccd7d27f 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -120,9 +120,8 @@ int perf_session__deliver_synth_event(struct perf_session *session, union perf_event *event, struct perf_sample *sample); -int perf_event__process_id_index(struct perf_tool *tool, - union perf_event *event, - struct perf_session *session); +int perf_event__process_id_index(struct perf_session *session, + union perf_event *event); int perf_event__synthesize_id_index(struct perf_tool *tool, perf_event__handler_t process, diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py index 001be4f9d3b9..63f758c655d5 100644 --- a/tools/perf/util/setup.py +++ b/tools/perf/util/setup.py @@ -1,12 +1,22 @@ #!/usr/bin/python from os import getenv +from subprocess import Popen, PIPE +from re import sub + +def clang_has_option(option): + return [o for o in Popen(['clang', option], stderr=PIPE).stderr.readlines() if b"unknown argument" in o] == [ ] cc = getenv("CC") if cc == "clang": - from _sysconfigdata import build_time_vars - from re import sub - build_time_vars["CFLAGS"] = sub("-specs=[^ ]+", "", build_time_vars["CFLAGS"]) + from distutils.sysconfig import get_config_vars + vars = get_config_vars() + for var in ('CFLAGS', 'OPT'): + vars[var] = sub("-specs=[^ ]+", "", vars[var]) + if not clang_has_option("-mcet"): + vars[var] = sub("-mcet", "", vars[var]) + if not clang_has_option("-fcf-protection"): + vars[var] = sub("-fcf-protection", "", vars[var]) from distutils.core import setup, Extension @@ -27,7 +37,7 @@ 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' ] +cflags += ['-fno-strict-aliasing', '-Wno-write-strings', '-Wno-unused-parameter', '-Wno-redundant-decls' ] if cc != "clang": cflags += ['-Wno-cast-function-type' ] diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index fed2952ab45a..f96c005b3c41 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -601,7 +601,7 @@ static char *get_trace_output(struct hist_entry *he) { struct trace_seq seq; struct perf_evsel *evsel; - struct pevent_record rec = { + struct tep_record rec = { .data = he->raw_data, .size = he->raw_size, }; @@ -610,10 +610,10 @@ static char *get_trace_output(struct hist_entry *he) trace_seq_init(&seq); if (symbol_conf.raw_trace) { - pevent_print_fields(&seq, he->raw_data, he->raw_size, - evsel->tp_format); + tep_print_fields(&seq, he->raw_data, he->raw_size, + evsel->tp_format); } else { - pevent_event_info(&seq, evsel->tp_format, &rec); + tep_event_info(&seq, evsel->tp_format, &rec); } /* * Trim the buffer, it starts at 4KB and we're not going to @@ -1884,7 +1884,7 @@ static int __sort_dimension__add_hpp_output(struct sort_dimension *sd, struct hpp_dynamic_entry { struct perf_hpp_fmt hpp; struct perf_evsel *evsel; - struct format_field *field; + struct tep_format_field *field; unsigned dynamic_len; bool raw_trace; }; @@ -1899,7 +1899,7 @@ static int hde_width(struct hpp_dynamic_entry *hde) if (namelen > len) len = namelen; - if (!(hde->field->flags & FIELD_IS_STRING)) { + if (!(hde->field->flags & TEP_FIELD_IS_STRING)) { /* length for print hex numbers */ fieldlen = hde->field->size * 2 + 2; } @@ -1915,7 +1915,7 @@ static void update_dynamic_len(struct hpp_dynamic_entry *hde, struct hist_entry *he) { char *str, *pos; - struct format_field *field = hde->field; + struct tep_format_field *field = hde->field; size_t namelen; bool last = false; @@ -2000,7 +2000,7 @@ static int __sort__hde_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, struct hpp_dynamic_entry *hde; size_t len = fmt->user_len; char *str, *pos; - struct format_field *field; + struct tep_format_field *field; size_t namelen; bool last = false; int ret; @@ -2047,7 +2047,7 @@ static int __sort__hde_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, struct trace_seq seq; raw_field: trace_seq_init(&seq); - pevent_print_field(&seq, he->raw_data, hde->field); + tep_print_field(&seq, he->raw_data, hde->field); str = seq.buffer; } @@ -2060,7 +2060,7 @@ static int64_t __sort__hde_cmp(struct perf_hpp_fmt *fmt, struct hist_entry *a, struct hist_entry *b) { struct hpp_dynamic_entry *hde; - struct format_field *field; + struct tep_format_field *field; unsigned offset, size; hde = container_of(fmt, struct hpp_dynamic_entry, hpp); @@ -2071,10 +2071,10 @@ static int64_t __sort__hde_cmp(struct perf_hpp_fmt *fmt, } field = hde->field; - if (field->flags & FIELD_IS_DYNAMIC) { + if (field->flags & TEP_FIELD_IS_DYNAMIC) { unsigned long long dyn; - pevent_read_number_field(field, a->raw_data, &dyn); + tep_read_number_field(field, a->raw_data, &dyn); offset = dyn & 0xffff; size = (dyn >> 16) & 0xffff; @@ -2117,7 +2117,7 @@ static void hde_free(struct perf_hpp_fmt *fmt) } static struct hpp_dynamic_entry * -__alloc_dynamic_entry(struct perf_evsel *evsel, struct format_field *field, +__alloc_dynamic_entry(struct perf_evsel *evsel, struct tep_format_field *field, int level) { struct hpp_dynamic_entry *hde; @@ -2252,7 +2252,7 @@ static struct perf_evsel *find_evsel(struct perf_evlist *evlist, char *event_nam } static int __dynamic_dimension__add(struct perf_evsel *evsel, - struct format_field *field, + struct tep_format_field *field, bool raw_trace, int level) { struct hpp_dynamic_entry *hde; @@ -2270,7 +2270,7 @@ static int __dynamic_dimension__add(struct perf_evsel *evsel, static int add_evsel_fields(struct perf_evsel *evsel, bool raw_trace, int level) { int ret; - struct format_field *field; + struct tep_format_field *field; field = evsel->tp_format->format.fields; while (field) { @@ -2305,13 +2305,13 @@ static int add_all_matching_fields(struct perf_evlist *evlist, { int ret = -ESRCH; struct perf_evsel *evsel; - struct format_field *field; + struct tep_format_field *field; evlist__for_each_entry(evlist, evsel) { if (evsel->attr.type != PERF_TYPE_TRACEPOINT) continue; - field = pevent_find_any_field(evsel->tp_format, field_name); + field = tep_find_any_field(evsel->tp_format, field_name); if (field == NULL) continue; @@ -2327,7 +2327,7 @@ static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok, { char *str, *event_name, *field_name, *opt_name; struct perf_evsel *evsel; - struct format_field *field; + struct tep_format_field *field; bool raw_trace = symbol_conf.raw_trace; int ret = 0; @@ -2378,7 +2378,7 @@ static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok, if (!strcmp(field_name, "*")) { ret = add_evsel_fields(evsel, raw_trace, level); } else { - field = pevent_find_any_field(evsel->tp_format, field_name); + field = tep_find_any_field(evsel->tp_format, field_name); if (field == NULL) { pr_debug("Cannot find event field for %s.%s\n", event_name, field_name); diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 8bf302cafcec..a97cf8e6be86 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -276,7 +276,7 @@ extern struct sort_entry sort_thread; extern struct list_head hist_entry__sort_list; struct perf_evlist; -struct pevent; +struct tep_handle; int setup_sorting(struct perf_evlist *evlist); int setup_output_field(void); void reset_output_field(void); diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c index 09d6746e6ec8..e767c4a9d4d2 100644 --- a/tools/perf/util/srcline.c +++ b/tools/perf/util/srcline.c @@ -85,6 +85,9 @@ static struct symbol *new_inline_sym(struct dso *dso, struct symbol *inline_sym; char *demangled = NULL; + if (!funcname) + funcname = "??"; + if (dso) { demangled = dso__demangle_sym(dso, 0, funcname); if (demangled) diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c new file mode 100644 index 000000000000..e7b4c44ebb62 --- /dev/null +++ b/tools/perf/util/stat-display.c @@ -0,0 +1,1166 @@ +#include <stdio.h> +#include <inttypes.h> +#include <linux/time64.h> +#include <math.h> +#include "evlist.h" +#include "evsel.h" +#include "stat.h" +#include "top.h" +#include "thread_map.h" +#include "cpumap.h" +#include "string2.h" +#include "sane_ctype.h" +#include "cgroup.h" +#include <math.h> +#include <api/fs/fs.h> + +#define CNTR_NOT_SUPPORTED "<not supported>" +#define CNTR_NOT_COUNTED "<not counted>" + +static bool is_duration_time(struct perf_evsel *evsel) +{ + return !strcmp(evsel->name, "duration_time"); +} + +static void print_running(struct perf_stat_config *config, + u64 run, u64 ena) +{ + if (config->csv_output) { + fprintf(config->output, "%s%" PRIu64 "%s%.2f", + config->csv_sep, + run, + config->csv_sep, + ena ? 100.0 * run / ena : 100.0); + } else if (run != ena) { + fprintf(config->output, " (%.2f%%)", 100.0 * run / ena); + } +} + +static void print_noise_pct(struct perf_stat_config *config, + double total, double avg) +{ + double pct = rel_stddev_stats(total, avg); + + if (config->csv_output) + fprintf(config->output, "%s%.2f%%", config->csv_sep, pct); + else if (pct) + fprintf(config->output, " ( +-%6.2f%% )", pct); +} + +static void print_noise(struct perf_stat_config *config, + struct perf_evsel *evsel, double avg) +{ + struct perf_stat_evsel *ps; + + if (config->run_count == 1) + return; + + ps = evsel->stats; + print_noise_pct(config, stddev_stats(&ps->res_stats[0]), avg); +} + +static void aggr_printout(struct perf_stat_config *config, + struct perf_evsel *evsel, int id, int nr) +{ + switch (config->aggr_mode) { + case AGGR_CORE: + fprintf(config->output, "S%d-C%*d%s%*d%s", + cpu_map__id_to_socket(id), + config->csv_output ? 0 : -8, + cpu_map__id_to_cpu(id), + config->csv_sep, + config->csv_output ? 0 : 4, + nr, + config->csv_sep); + break; + case AGGR_SOCKET: + fprintf(config->output, "S%*d%s%*d%s", + config->csv_output ? 0 : -5, + id, + config->csv_sep, + config->csv_output ? 0 : 4, + nr, + config->csv_sep); + break; + case AGGR_NONE: + fprintf(config->output, "CPU%*d%s", + config->csv_output ? 0 : -4, + perf_evsel__cpus(evsel)->map[id], config->csv_sep); + break; + case AGGR_THREAD: + fprintf(config->output, "%*s-%*d%s", + config->csv_output ? 0 : 16, + thread_map__comm(evsel->threads, id), + config->csv_output ? 0 : -8, + thread_map__pid(evsel->threads, id), + config->csv_sep); + break; + case AGGR_GLOBAL: + case AGGR_UNSET: + default: + break; + } +} + +struct outstate { + FILE *fh; + bool newline; + const char *prefix; + int nfields; + int id, nr; + struct perf_evsel *evsel; +}; + +#define METRIC_LEN 35 + +static void new_line_std(struct perf_stat_config *config __maybe_unused, + void *ctx) +{ + struct outstate *os = ctx; + + os->newline = true; +} + +static void do_new_line_std(struct perf_stat_config *config, + struct outstate *os) +{ + fputc('\n', os->fh); + fputs(os->prefix, os->fh); + aggr_printout(config, os->evsel, os->id, os->nr); + if (config->aggr_mode == AGGR_NONE) + fprintf(os->fh, " "); + fprintf(os->fh, " "); +} + +static void print_metric_std(struct perf_stat_config *config, + void *ctx, const char *color, const char *fmt, + const char *unit, double val) +{ + struct outstate *os = ctx; + FILE *out = os->fh; + int n; + bool newline = os->newline; + + os->newline = false; + + if (unit == NULL || fmt == NULL) { + fprintf(out, "%-*s", METRIC_LEN, ""); + return; + } + + if (newline) + do_new_line_std(config, os); + + n = fprintf(out, " # "); + if (color) + n += color_fprintf(out, color, fmt, val); + else + n += fprintf(out, fmt, val); + fprintf(out, " %-*s", METRIC_LEN - n - 1, unit); +} + +static void new_line_csv(struct perf_stat_config *config, void *ctx) +{ + struct outstate *os = ctx; + int i; + + fputc('\n', os->fh); + if (os->prefix) + fprintf(os->fh, "%s%s", os->prefix, config->csv_sep); + aggr_printout(config, os->evsel, os->id, os->nr); + for (i = 0; i < os->nfields; i++) + fputs(config->csv_sep, os->fh); +} + +static void print_metric_csv(struct perf_stat_config *config __maybe_unused, + void *ctx, + const char *color __maybe_unused, + const char *fmt, const char *unit, double val) +{ + struct outstate *os = ctx; + FILE *out = os->fh; + char buf[64], *vals, *ends; + + if (unit == NULL || fmt == NULL) { + fprintf(out, "%s%s", config->csv_sep, config->csv_sep); + return; + } + snprintf(buf, sizeof(buf), fmt, val); + ends = vals = ltrim(buf); + while (isdigit(*ends) || *ends == '.') + ends++; + *ends = 0; + while (isspace(*unit)) + unit++; + fprintf(out, "%s%s%s%s", config->csv_sep, vals, config->csv_sep, unit); +} + +/* Filter out some columns that don't work well in metrics only mode */ + +static bool valid_only_metric(const char *unit) +{ + if (!unit) + return false; + if (strstr(unit, "/sec") || + strstr(unit, "hz") || + strstr(unit, "Hz") || + strstr(unit, "CPUs utilized")) + return false; + return true; +} + +static const char *fixunit(char *buf, struct perf_evsel *evsel, + const char *unit) +{ + if (!strncmp(unit, "of all", 6)) { + snprintf(buf, 1024, "%s %s", perf_evsel__name(evsel), + unit); + return buf; + } + return unit; +} + +static void print_metric_only(struct perf_stat_config *config, + void *ctx, const char *color, const char *fmt, + const char *unit, double val) +{ + struct outstate *os = ctx; + FILE *out = os->fh; + char buf[1024], str[1024]; + unsigned mlen = config->metric_only_len; + + if (!valid_only_metric(unit)) + return; + unit = fixunit(buf, os->evsel, unit); + if (mlen < strlen(unit)) + mlen = strlen(unit) + 1; + + if (color) + mlen += strlen(color) + sizeof(PERF_COLOR_RESET) - 1; + + color_snprintf(str, sizeof(str), color ?: "", fmt, val); + fprintf(out, "%*s ", mlen, str); +} + +static void print_metric_only_csv(struct perf_stat_config *config __maybe_unused, + void *ctx, const char *color __maybe_unused, + const char *fmt, + const char *unit, double val) +{ + struct outstate *os = ctx; + FILE *out = os->fh; + char buf[64], *vals, *ends; + char tbuf[1024]; + + if (!valid_only_metric(unit)) + return; + unit = fixunit(tbuf, os->evsel, unit); + snprintf(buf, sizeof buf, fmt, val); + ends = vals = ltrim(buf); + while (isdigit(*ends) || *ends == '.') + ends++; + *ends = 0; + fprintf(out, "%s%s", vals, config->csv_sep); +} + +static void new_line_metric(struct perf_stat_config *config __maybe_unused, + void *ctx __maybe_unused) +{ +} + +static void print_metric_header(struct perf_stat_config *config, + void *ctx, const char *color __maybe_unused, + const char *fmt __maybe_unused, + const char *unit, double val __maybe_unused) +{ + struct outstate *os = ctx; + char tbuf[1024]; + + if (!valid_only_metric(unit)) + return; + unit = fixunit(tbuf, os->evsel, unit); + if (config->csv_output) + fprintf(os->fh, "%s%s", unit, config->csv_sep); + else + fprintf(os->fh, "%*s ", config->metric_only_len, unit); +} + +static int first_shadow_cpu(struct perf_stat_config *config, + struct perf_evsel *evsel, int id) +{ + struct perf_evlist *evlist = evsel->evlist; + int i; + + if (!config->aggr_get_id) + return 0; + + if (config->aggr_mode == AGGR_NONE) + return id; + + if (config->aggr_mode == AGGR_GLOBAL) + return 0; + + for (i = 0; i < perf_evsel__nr_cpus(evsel); i++) { + int cpu2 = perf_evsel__cpus(evsel)->map[i]; + + if (config->aggr_get_id(config, evlist->cpus, cpu2) == id) + return cpu2; + } + return 0; +} + +static void abs_printout(struct perf_stat_config *config, + int id, int nr, struct perf_evsel *evsel, double avg) +{ + FILE *output = config->output; + double sc = evsel->scale; + const char *fmt; + + if (config->csv_output) { + fmt = floor(sc) != sc ? "%.2f%s" : "%.0f%s"; + } else { + if (config->big_num) + fmt = floor(sc) != sc ? "%'18.2f%s" : "%'18.0f%s"; + else + fmt = floor(sc) != sc ? "%18.2f%s" : "%18.0f%s"; + } + + aggr_printout(config, evsel, id, nr); + + fprintf(output, fmt, avg, config->csv_sep); + + if (evsel->unit) + fprintf(output, "%-*s%s", + config->csv_output ? 0 : config->unit_width, + evsel->unit, config->csv_sep); + + fprintf(output, "%-*s", config->csv_output ? 0 : 25, perf_evsel__name(evsel)); + + if (evsel->cgrp) + fprintf(output, "%s%s", config->csv_sep, evsel->cgrp->name); +} + +static bool is_mixed_hw_group(struct perf_evsel *counter) +{ + struct perf_evlist *evlist = counter->evlist; + u32 pmu_type = counter->attr.type; + struct perf_evsel *pos; + + if (counter->nr_members < 2) + return false; + + evlist__for_each_entry(evlist, pos) { + /* software events can be part of any hardware group */ + if (pos->attr.type == PERF_TYPE_SOFTWARE) + continue; + if (pmu_type == PERF_TYPE_SOFTWARE) { + pmu_type = pos->attr.type; + continue; + } + if (pmu_type != pos->attr.type) + return true; + } + + return false; +} + +static void printout(struct perf_stat_config *config, int id, int nr, + struct perf_evsel *counter, double uval, + char *prefix, u64 run, u64 ena, double noise, + struct runtime_stat *st) +{ + struct perf_stat_output_ctx out; + struct outstate os = { + .fh = config->output, + .prefix = prefix ? prefix : "", + .id = id, + .nr = nr, + .evsel = counter, + }; + print_metric_t pm = print_metric_std; + new_line_t nl; + + if (config->metric_only) { + nl = new_line_metric; + if (config->csv_output) + pm = print_metric_only_csv; + else + pm = print_metric_only; + } else + nl = new_line_std; + + if (config->csv_output && !config->metric_only) { + static int aggr_fields[] = { + [AGGR_GLOBAL] = 0, + [AGGR_THREAD] = 1, + [AGGR_NONE] = 1, + [AGGR_SOCKET] = 2, + [AGGR_CORE] = 2, + }; + + pm = print_metric_csv; + nl = new_line_csv; + os.nfields = 3; + os.nfields += aggr_fields[config->aggr_mode]; + if (counter->cgrp) + os.nfields++; + } + if (run == 0 || ena == 0 || counter->counts->scaled == -1) { + if (config->metric_only) { + pm(config, &os, NULL, "", "", 0); + return; + } + aggr_printout(config, counter, id, nr); + + fprintf(config->output, "%*s%s", + config->csv_output ? 0 : 18, + counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED, + config->csv_sep); + + if (counter->supported) { + config->print_free_counters_hint = 1; + if (is_mixed_hw_group(counter)) + config->print_mixed_hw_group_error = 1; + } + + fprintf(config->output, "%-*s%s", + config->csv_output ? 0 : config->unit_width, + counter->unit, config->csv_sep); + + fprintf(config->output, "%*s", + config->csv_output ? 0 : -25, + perf_evsel__name(counter)); + + if (counter->cgrp) + fprintf(config->output, "%s%s", + config->csv_sep, counter->cgrp->name); + + if (!config->csv_output) + pm(config, &os, NULL, NULL, "", 0); + print_noise(config, counter, noise); + print_running(config, run, ena); + if (config->csv_output) + pm(config, &os, NULL, NULL, "", 0); + return; + } + + if (!config->metric_only) + abs_printout(config, id, nr, counter, uval); + + out.print_metric = pm; + out.new_line = nl; + out.ctx = &os; + out.force_header = false; + + if (config->csv_output && !config->metric_only) { + print_noise(config, counter, noise); + print_running(config, run, ena); + } + + perf_stat__print_shadow_stats(config, counter, uval, + first_shadow_cpu(config, counter, id), + &out, &config->metric_events, st); + if (!config->csv_output && !config->metric_only) { + print_noise(config, counter, noise); + print_running(config, run, ena); + } +} + +static void aggr_update_shadow(struct perf_stat_config *config, + struct perf_evlist *evlist) +{ + int cpu, s2, id, s; + u64 val; + struct perf_evsel *counter; + + for (s = 0; s < config->aggr_map->nr; s++) { + id = config->aggr_map->map[s]; + evlist__for_each_entry(evlist, counter) { + val = 0; + for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) { + s2 = config->aggr_get_id(config, evlist->cpus, cpu); + if (s2 != id) + continue; + val += perf_counts(counter->counts, cpu, 0)->val; + } + perf_stat__update_shadow_stats(counter, val, + first_shadow_cpu(config, counter, id), + &rt_stat); + } + } +} + +static void uniquify_event_name(struct perf_evsel *counter) +{ + char *new_name; + char *config; + + if (counter->uniquified_name || + !counter->pmu_name || !strncmp(counter->name, counter->pmu_name, + strlen(counter->pmu_name))) + return; + + config = strchr(counter->name, '/'); + if (config) { + if (asprintf(&new_name, + "%s%s", counter->pmu_name, config) > 0) { + free(counter->name); + counter->name = new_name; + } + } else { + if (asprintf(&new_name, + "%s [%s]", counter->name, counter->pmu_name) > 0) { + free(counter->name); + counter->name = new_name; + } + } + + counter->uniquified_name = true; +} + +static void collect_all_aliases(struct perf_stat_config *config, struct perf_evsel *counter, + void (*cb)(struct perf_stat_config *config, struct perf_evsel *counter, void *data, + bool first), + void *data) +{ + struct perf_evlist *evlist = counter->evlist; + struct perf_evsel *alias; + + alias = list_prepare_entry(counter, &(evlist->entries), node); + list_for_each_entry_continue (alias, &evlist->entries, node) { + if (strcmp(perf_evsel__name(alias), perf_evsel__name(counter)) || + alias->scale != counter->scale || + alias->cgrp != counter->cgrp || + strcmp(alias->unit, counter->unit) || + perf_evsel__is_clock(alias) != perf_evsel__is_clock(counter)) + break; + alias->merged_stat = true; + cb(config, alias, data, false); + } +} + +static bool collect_data(struct perf_stat_config *config, struct perf_evsel *counter, + void (*cb)(struct perf_stat_config *config, struct perf_evsel *counter, void *data, + bool first), + void *data) +{ + if (counter->merged_stat) + return false; + cb(config, counter, data, true); + if (config->no_merge) + uniquify_event_name(counter); + else if (counter->auto_merge_stats) + collect_all_aliases(config, counter, cb, data); + return true; +} + +struct aggr_data { + u64 ena, run, val; + int id; + int nr; + int cpu; +}; + +static void aggr_cb(struct perf_stat_config *config, + struct perf_evsel *counter, void *data, bool first) +{ + struct aggr_data *ad = data; + int cpu, s2; + + for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) { + struct perf_counts_values *counts; + + s2 = config->aggr_get_id(config, perf_evsel__cpus(counter), cpu); + if (s2 != ad->id) + continue; + if (first) + ad->nr++; + counts = perf_counts(counter->counts, cpu, 0); + /* + * When any result is bad, make them all to give + * consistent output in interval mode. + */ + if (counts->ena == 0 || counts->run == 0 || + counter->counts->scaled == -1) { + ad->ena = 0; + ad->run = 0; + break; + } + ad->val += counts->val; + ad->ena += counts->ena; + ad->run += counts->run; + } +} + +static void print_aggr(struct perf_stat_config *config, + struct perf_evlist *evlist, + char *prefix) +{ + bool metric_only = config->metric_only; + FILE *output = config->output; + struct perf_evsel *counter; + int s, id, nr; + double uval; + u64 ena, run, val; + bool first; + + if (!(config->aggr_map || config->aggr_get_id)) + return; + + aggr_update_shadow(config, evlist); + + /* + * With metric_only everything is on a single line. + * Without each counter has its own line. + */ + for (s = 0; s < config->aggr_map->nr; s++) { + struct aggr_data ad; + if (prefix && metric_only) + fprintf(output, "%s", prefix); + + ad.id = id = config->aggr_map->map[s]; + first = true; + evlist__for_each_entry(evlist, counter) { + if (is_duration_time(counter)) + continue; + + ad.val = ad.ena = ad.run = 0; + ad.nr = 0; + if (!collect_data(config, counter, aggr_cb, &ad)) + continue; + nr = ad.nr; + ena = ad.ena; + run = ad.run; + val = ad.val; + if (first && metric_only) { + first = false; + aggr_printout(config, counter, id, nr); + } + if (prefix && !metric_only) + fprintf(output, "%s", prefix); + + uval = val * counter->scale; + printout(config, id, nr, counter, uval, prefix, + run, ena, 1.0, &rt_stat); + if (!metric_only) + fputc('\n', output); + } + if (metric_only) + fputc('\n', output); + } +} + +static int cmp_val(const void *a, const void *b) +{ + return ((struct perf_aggr_thread_value *)b)->val - + ((struct perf_aggr_thread_value *)a)->val; +} + +static struct perf_aggr_thread_value *sort_aggr_thread( + struct perf_evsel *counter, + int nthreads, int ncpus, + int *ret, + struct target *_target) +{ + int cpu, thread, i = 0; + double uval; + struct perf_aggr_thread_value *buf; + + buf = calloc(nthreads, sizeof(struct perf_aggr_thread_value)); + if (!buf) + return NULL; + + for (thread = 0; thread < nthreads; thread++) { + u64 ena = 0, run = 0, val = 0; + + for (cpu = 0; cpu < ncpus; cpu++) { + val += perf_counts(counter->counts, cpu, thread)->val; + ena += perf_counts(counter->counts, cpu, thread)->ena; + run += perf_counts(counter->counts, cpu, thread)->run; + } + + uval = val * counter->scale; + + /* + * Skip value 0 when enabling --per-thread globally, + * otherwise too many 0 output. + */ + if (uval == 0.0 && target__has_per_thread(_target)) + continue; + + buf[i].counter = counter; + buf[i].id = thread; + buf[i].uval = uval; + buf[i].val = val; + buf[i].run = run; + buf[i].ena = ena; + i++; + } + + qsort(buf, i, sizeof(struct perf_aggr_thread_value), cmp_val); + + if (ret) + *ret = i; + + return buf; +} + +static void print_aggr_thread(struct perf_stat_config *config, + struct target *_target, + struct perf_evsel *counter, char *prefix) +{ + FILE *output = config->output; + int nthreads = thread_map__nr(counter->threads); + int ncpus = cpu_map__nr(counter->cpus); + int thread, sorted_threads, id; + struct perf_aggr_thread_value *buf; + + buf = sort_aggr_thread(counter, nthreads, ncpus, &sorted_threads, _target); + if (!buf) { + perror("cannot sort aggr thread"); + return; + } + + for (thread = 0; thread < sorted_threads; thread++) { + if (prefix) + fprintf(output, "%s", prefix); + + id = buf[thread].id; + if (config->stats) + printout(config, id, 0, buf[thread].counter, buf[thread].uval, + prefix, buf[thread].run, buf[thread].ena, 1.0, + &config->stats[id]); + else + printout(config, id, 0, buf[thread].counter, buf[thread].uval, + prefix, buf[thread].run, buf[thread].ena, 1.0, + &rt_stat); + fputc('\n', output); + } + + free(buf); +} + +struct caggr_data { + double avg, avg_enabled, avg_running; +}; + +static void counter_aggr_cb(struct perf_stat_config *config __maybe_unused, + struct perf_evsel *counter, void *data, + bool first __maybe_unused) +{ + struct caggr_data *cd = data; + struct perf_stat_evsel *ps = counter->stats; + + cd->avg += avg_stats(&ps->res_stats[0]); + cd->avg_enabled += avg_stats(&ps->res_stats[1]); + cd->avg_running += avg_stats(&ps->res_stats[2]); +} + +/* + * Print out the results of a single counter: + * aggregated counts in system-wide mode + */ +static void print_counter_aggr(struct perf_stat_config *config, + struct perf_evsel *counter, char *prefix) +{ + bool metric_only = config->metric_only; + FILE *output = config->output; + double uval; + struct caggr_data cd = { .avg = 0.0 }; + + if (!collect_data(config, counter, counter_aggr_cb, &cd)) + return; + + if (prefix && !metric_only) + fprintf(output, "%s", prefix); + + uval = cd.avg * counter->scale; + printout(config, -1, 0, counter, uval, prefix, cd.avg_running, cd.avg_enabled, + cd.avg, &rt_stat); + if (!metric_only) + fprintf(output, "\n"); +} + +static void counter_cb(struct perf_stat_config *config __maybe_unused, + struct perf_evsel *counter, void *data, + bool first __maybe_unused) +{ + struct aggr_data *ad = data; + + ad->val += perf_counts(counter->counts, ad->cpu, 0)->val; + ad->ena += perf_counts(counter->counts, ad->cpu, 0)->ena; + ad->run += perf_counts(counter->counts, ad->cpu, 0)->run; +} + +/* + * Print out the results of a single counter: + * does not use aggregated count in system-wide + */ +static void print_counter(struct perf_stat_config *config, + struct perf_evsel *counter, char *prefix) +{ + FILE *output = config->output; + u64 ena, run, val; + double uval; + int cpu; + + for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) { + struct aggr_data ad = { .cpu = cpu }; + + if (!collect_data(config, counter, counter_cb, &ad)) + return; + val = ad.val; + ena = ad.ena; + run = ad.run; + + if (prefix) + fprintf(output, "%s", prefix); + + uval = val * counter->scale; + printout(config, cpu, 0, counter, uval, prefix, run, ena, 1.0, + &rt_stat); + + fputc('\n', output); + } +} + +static void print_no_aggr_metric(struct perf_stat_config *config, + struct perf_evlist *evlist, + char *prefix) +{ + int cpu; + int nrcpus = 0; + struct perf_evsel *counter; + u64 ena, run, val; + double uval; + + nrcpus = evlist->cpus->nr; + for (cpu = 0; cpu < nrcpus; cpu++) { + bool first = true; + + if (prefix) + fputs(prefix, config->output); + evlist__for_each_entry(evlist, counter) { + if (is_duration_time(counter)) + continue; + if (first) { + aggr_printout(config, counter, cpu, 0); + first = false; + } + val = perf_counts(counter->counts, cpu, 0)->val; + ena = perf_counts(counter->counts, cpu, 0)->ena; + run = perf_counts(counter->counts, cpu, 0)->run; + + uval = val * counter->scale; + printout(config, cpu, 0, counter, uval, prefix, run, ena, 1.0, + &rt_stat); + } + fputc('\n', config->output); + } +} + +static int aggr_header_lens[] = { + [AGGR_CORE] = 18, + [AGGR_SOCKET] = 12, + [AGGR_NONE] = 6, + [AGGR_THREAD] = 24, + [AGGR_GLOBAL] = 0, +}; + +static const char *aggr_header_csv[] = { + [AGGR_CORE] = "core,cpus,", + [AGGR_SOCKET] = "socket,cpus", + [AGGR_NONE] = "cpu,", + [AGGR_THREAD] = "comm-pid,", + [AGGR_GLOBAL] = "" +}; + +static void print_metric_headers(struct perf_stat_config *config, + struct perf_evlist *evlist, + const char *prefix, bool no_indent) +{ + struct perf_stat_output_ctx out; + struct perf_evsel *counter; + struct outstate os = { + .fh = config->output + }; + + if (prefix) + fprintf(config->output, "%s", prefix); + + if (!config->csv_output && !no_indent) + fprintf(config->output, "%*s", + aggr_header_lens[config->aggr_mode], ""); + if (config->csv_output) { + if (config->interval) + fputs("time,", config->output); + fputs(aggr_header_csv[config->aggr_mode], config->output); + } + + /* Print metrics headers only */ + evlist__for_each_entry(evlist, counter) { + if (is_duration_time(counter)) + continue; + os.evsel = counter; + out.ctx = &os; + out.print_metric = print_metric_header; + out.new_line = new_line_metric; + out.force_header = true; + os.evsel = counter; + perf_stat__print_shadow_stats(config, counter, 0, + 0, + &out, + &config->metric_events, + &rt_stat); + } + fputc('\n', config->output); +} + +static void print_interval(struct perf_stat_config *config, + struct perf_evlist *evlist, + char *prefix, struct timespec *ts) +{ + bool metric_only = config->metric_only; + unsigned int unit_width = config->unit_width; + FILE *output = config->output; + static int num_print_interval; + + if (config->interval_clear) + puts(CONSOLE_CLEAR); + + sprintf(prefix, "%6lu.%09lu%s", ts->tv_sec, ts->tv_nsec, config->csv_sep); + + if ((num_print_interval == 0 && !config->csv_output) || config->interval_clear) { + switch (config->aggr_mode) { + case AGGR_SOCKET: + fprintf(output, "# time socket cpus"); + if (!metric_only) + fprintf(output, " counts %*s events\n", unit_width, "unit"); + break; + case AGGR_CORE: + fprintf(output, "# time core cpus"); + if (!metric_only) + fprintf(output, " counts %*s events\n", unit_width, "unit"); + break; + case AGGR_NONE: + fprintf(output, "# time CPU "); + if (!metric_only) + fprintf(output, " counts %*s events\n", unit_width, "unit"); + break; + case AGGR_THREAD: + fprintf(output, "# time comm-pid"); + if (!metric_only) + fprintf(output, " counts %*s events\n", unit_width, "unit"); + break; + case AGGR_GLOBAL: + default: + fprintf(output, "# time"); + if (!metric_only) + fprintf(output, " counts %*s events\n", unit_width, "unit"); + case AGGR_UNSET: + break; + } + } + + if ((num_print_interval == 0 || config->interval_clear) && metric_only) + print_metric_headers(config, evlist, " ", true); + if (++num_print_interval == 25) + num_print_interval = 0; +} + +static void print_header(struct perf_stat_config *config, + struct target *_target, + int argc, const char **argv) +{ + FILE *output = config->output; + int i; + + fflush(stdout); + + if (!config->csv_output) { + fprintf(output, "\n"); + fprintf(output, " Performance counter stats for "); + if (_target->system_wide) + fprintf(output, "\'system wide"); + else if (_target->cpu_list) + fprintf(output, "\'CPU(s) %s", _target->cpu_list); + else if (!target__has_task(_target)) { + fprintf(output, "\'%s", argv ? argv[0] : "pipe"); + for (i = 1; argv && (i < argc); i++) + fprintf(output, " %s", argv[i]); + } else if (_target->pid) + fprintf(output, "process id \'%s", _target->pid); + else + fprintf(output, "thread id \'%s", _target->tid); + + fprintf(output, "\'"); + if (config->run_count > 1) + fprintf(output, " (%d runs)", config->run_count); + fprintf(output, ":\n\n"); + } +} + +static int get_precision(double num) +{ + if (num > 1) + return 0; + + return lround(ceil(-log10(num))); +} + +static void print_table(struct perf_stat_config *config, + FILE *output, int precision, double avg) +{ + char tmp[64]; + int idx, indent = 0; + + scnprintf(tmp, 64, " %17.*f", precision, avg); + while (tmp[indent] == ' ') + indent++; + + fprintf(output, "%*s# Table of individual measurements:\n", indent, ""); + + for (idx = 0; idx < config->run_count; idx++) { + double run = (double) config->walltime_run[idx] / NSEC_PER_SEC; + int h, n = 1 + abs((int) (100.0 * (run - avg)/run) / 5); + + fprintf(output, " %17.*f (%+.*f) ", + precision, run, precision, run - avg); + + for (h = 0; h < n; h++) + fprintf(output, "#"); + + fprintf(output, "\n"); + } + + fprintf(output, "\n%*s# Final result:\n", indent, ""); +} + +static double timeval2double(struct timeval *t) +{ + return t->tv_sec + (double) t->tv_usec/USEC_PER_SEC; +} + +static void print_footer(struct perf_stat_config *config) +{ + double avg = avg_stats(config->walltime_nsecs_stats) / NSEC_PER_SEC; + FILE *output = config->output; + int n; + + if (!config->null_run) + fprintf(output, "\n"); + + if (config->run_count == 1) { + fprintf(output, " %17.9f seconds time elapsed", avg); + + if (config->ru_display) { + double ru_utime = timeval2double(&config->ru_data.ru_utime); + double ru_stime = timeval2double(&config->ru_data.ru_stime); + + fprintf(output, "\n\n"); + fprintf(output, " %17.9f seconds user\n", ru_utime); + fprintf(output, " %17.9f seconds sys\n", ru_stime); + } + } else { + double sd = stddev_stats(config->walltime_nsecs_stats) / NSEC_PER_SEC; + /* + * Display at most 2 more significant + * digits than the stddev inaccuracy. + */ + int precision = get_precision(sd) + 2; + + if (config->walltime_run_table) + print_table(config, output, precision, avg); + + fprintf(output, " %17.*f +- %.*f seconds time elapsed", + precision, avg, precision, sd); + + print_noise_pct(config, sd, avg); + } + fprintf(output, "\n\n"); + + if (config->print_free_counters_hint && + sysctl__read_int("kernel/nmi_watchdog", &n) >= 0 && + n > 0) + fprintf(output, +"Some events weren't counted. Try disabling the NMI watchdog:\n" +" echo 0 > /proc/sys/kernel/nmi_watchdog\n" +" perf stat ...\n" +" echo 1 > /proc/sys/kernel/nmi_watchdog\n"); + + if (config->print_mixed_hw_group_error) + fprintf(output, + "The events in group usually have to be from " + "the same PMU. Try reorganizing the group.\n"); +} + +void +perf_evlist__print_counters(struct perf_evlist *evlist, + struct perf_stat_config *config, + struct target *_target, + struct timespec *ts, + int argc, const char **argv) +{ + bool metric_only = config->metric_only; + int interval = config->interval; + struct perf_evsel *counter; + char buf[64], *prefix = NULL; + + if (interval) + print_interval(config, evlist, prefix = buf, ts); + else + print_header(config, _target, argc, argv); + + if (metric_only) { + static int num_print_iv; + + if (num_print_iv == 0 && !interval) + print_metric_headers(config, evlist, prefix, false); + if (num_print_iv++ == 25) + num_print_iv = 0; + if (config->aggr_mode == AGGR_GLOBAL && prefix) + fprintf(config->output, "%s", prefix); + } + + switch (config->aggr_mode) { + case AGGR_CORE: + case AGGR_SOCKET: + print_aggr(config, evlist, prefix); + break; + case AGGR_THREAD: + evlist__for_each_entry(evlist, counter) { + if (is_duration_time(counter)) + continue; + print_aggr_thread(config, _target, counter, prefix); + } + break; + case AGGR_GLOBAL: + evlist__for_each_entry(evlist, counter) { + if (is_duration_time(counter)) + continue; + print_counter_aggr(config, counter, prefix); + } + if (metric_only) + fputc('\n', config->output); + break; + case AGGR_NONE: + if (metric_only) + print_no_aggr_metric(config, evlist, prefix); + else { + evlist__for_each_entry(evlist, counter) { + if (is_duration_time(counter)) + continue; + print_counter(config, counter, prefix); + } + } + break; + case AGGR_UNSET: + default: + break; + } + + if (!interval && !config->csv_output) + print_footer(config); + + fflush(config->output); +} diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index 594d14a02b67..8ad32763cfff 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -410,7 +410,8 @@ static double runtime_stat_n(struct runtime_stat *st, return v->stats.n; } -static void print_stalled_cycles_frontend(int cpu, +static void print_stalled_cycles_frontend(struct perf_stat_config *config, + int cpu, struct perf_evsel *evsel, double avg, struct perf_stat_output_ctx *out, struct runtime_stat *st) @@ -427,13 +428,14 @@ static void print_stalled_cycles_frontend(int cpu, color = get_ratio_color(GRC_STALLED_CYCLES_FE, ratio); if (ratio) - out->print_metric(out->ctx, color, "%7.2f%%", "frontend cycles idle", + out->print_metric(config, out->ctx, color, "%7.2f%%", "frontend cycles idle", ratio); else - out->print_metric(out->ctx, NULL, NULL, "frontend cycles idle", 0); + out->print_metric(config, out->ctx, NULL, NULL, "frontend cycles idle", 0); } -static void print_stalled_cycles_backend(int cpu, +static void print_stalled_cycles_backend(struct perf_stat_config *config, + int cpu, struct perf_evsel *evsel, double avg, struct perf_stat_output_ctx *out, struct runtime_stat *st) @@ -449,10 +451,11 @@ static void print_stalled_cycles_backend(int cpu, color = get_ratio_color(GRC_STALLED_CYCLES_BE, ratio); - out->print_metric(out->ctx, color, "%7.2f%%", "backend cycles idle", ratio); + out->print_metric(config, out->ctx, color, "%7.2f%%", "backend cycles idle", ratio); } -static void print_branch_misses(int cpu, +static void print_branch_misses(struct perf_stat_config *config, + int cpu, struct perf_evsel *evsel, double avg, struct perf_stat_output_ctx *out, @@ -469,10 +472,11 @@ static void print_branch_misses(int cpu, color = get_ratio_color(GRC_CACHE_MISSES, ratio); - out->print_metric(out->ctx, color, "%7.2f%%", "of all branches", ratio); + out->print_metric(config, out->ctx, color, "%7.2f%%", "of all branches", ratio); } -static void print_l1_dcache_misses(int cpu, +static void print_l1_dcache_misses(struct perf_stat_config *config, + int cpu, struct perf_evsel *evsel, double avg, struct perf_stat_output_ctx *out, @@ -490,10 +494,11 @@ static void print_l1_dcache_misses(int cpu, color = get_ratio_color(GRC_CACHE_MISSES, ratio); - out->print_metric(out->ctx, color, "%7.2f%%", "of all L1-dcache hits", ratio); + out->print_metric(config, out->ctx, color, "%7.2f%%", "of all L1-dcache hits", ratio); } -static void print_l1_icache_misses(int cpu, +static void print_l1_icache_misses(struct perf_stat_config *config, + int cpu, struct perf_evsel *evsel, double avg, struct perf_stat_output_ctx *out, @@ -510,10 +515,11 @@ static void print_l1_icache_misses(int cpu, ratio = avg / total * 100.0; color = get_ratio_color(GRC_CACHE_MISSES, ratio); - out->print_metric(out->ctx, color, "%7.2f%%", "of all L1-icache hits", ratio); + out->print_metric(config, out->ctx, color, "%7.2f%%", "of all L1-icache hits", ratio); } -static void print_dtlb_cache_misses(int cpu, +static void print_dtlb_cache_misses(struct perf_stat_config *config, + int cpu, struct perf_evsel *evsel, double avg, struct perf_stat_output_ctx *out, @@ -529,10 +535,11 @@ static void print_dtlb_cache_misses(int cpu, ratio = avg / total * 100.0; color = get_ratio_color(GRC_CACHE_MISSES, ratio); - out->print_metric(out->ctx, color, "%7.2f%%", "of all dTLB cache hits", ratio); + out->print_metric(config, out->ctx, color, "%7.2f%%", "of all dTLB cache hits", ratio); } -static void print_itlb_cache_misses(int cpu, +static void print_itlb_cache_misses(struct perf_stat_config *config, + int cpu, struct perf_evsel *evsel, double avg, struct perf_stat_output_ctx *out, @@ -548,10 +555,11 @@ static void print_itlb_cache_misses(int cpu, ratio = avg / total * 100.0; color = get_ratio_color(GRC_CACHE_MISSES, ratio); - out->print_metric(out->ctx, color, "%7.2f%%", "of all iTLB cache hits", ratio); + out->print_metric(config, out->ctx, color, "%7.2f%%", "of all iTLB cache hits", ratio); } -static void print_ll_cache_misses(int cpu, +static void print_ll_cache_misses(struct perf_stat_config *config, + int cpu, struct perf_evsel *evsel, double avg, struct perf_stat_output_ctx *out, @@ -567,7 +575,7 @@ static void print_ll_cache_misses(int cpu, ratio = avg / total * 100.0; color = get_ratio_color(GRC_CACHE_MISSES, ratio); - out->print_metric(out->ctx, color, "%7.2f%%", "of all LL-cache hits", ratio); + out->print_metric(config, out->ctx, color, "%7.2f%%", "of all LL-cache hits", ratio); } /* @@ -674,7 +682,8 @@ static double td_be_bound(int ctx, int cpu, struct runtime_stat *st) return sanitize_val(1.0 - sum); } -static void print_smi_cost(int cpu, struct perf_evsel *evsel, +static void print_smi_cost(struct perf_stat_config *config, + int cpu, struct perf_evsel *evsel, struct perf_stat_output_ctx *out, struct runtime_stat *st) { @@ -694,11 +703,12 @@ static void print_smi_cost(int cpu, struct perf_evsel *evsel, if (cost > 10) color = PERF_COLOR_RED; - out->print_metric(out->ctx, color, "%8.1f%%", "SMI cycles%", cost); - out->print_metric(out->ctx, NULL, "%4.0f", "SMI#", smi_num); + out->print_metric(config, out->ctx, color, "%8.1f%%", "SMI cycles%", cost); + out->print_metric(config, out->ctx, NULL, "%4.0f", "SMI#", smi_num); } -static void generic_metric(const char *metric_expr, +static void generic_metric(struct perf_stat_config *config, + const char *metric_expr, struct perf_evsel **metric_events, char *name, const char *metric_name, @@ -737,20 +747,21 @@ static void generic_metric(const char *metric_expr, const char *p = metric_expr; if (expr__parse(&ratio, &pctx, &p) == 0) - print_metric(ctxp, NULL, "%8.1f", + print_metric(config, ctxp, NULL, "%8.1f", metric_name ? metric_name : out->force_header ? name : "", ratio); else - print_metric(ctxp, NULL, NULL, + print_metric(config, ctxp, NULL, NULL, out->force_header ? (metric_name ? metric_name : name) : "", 0); } else - print_metric(ctxp, NULL, NULL, "", 0); + print_metric(config, ctxp, NULL, NULL, "", 0); } -void perf_stat__print_shadow_stats(struct perf_evsel *evsel, +void perf_stat__print_shadow_stats(struct perf_stat_config *config, + struct perf_evsel *evsel, double avg, int cpu, struct perf_stat_output_ctx *out, struct rblist *metric_events, @@ -769,10 +780,10 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel, if (total) { ratio = avg / total; - print_metric(ctxp, NULL, "%7.2f ", + print_metric(config, ctxp, NULL, "%7.2f ", "insn per cycle", ratio); } else { - print_metric(ctxp, NULL, NULL, "insn per cycle", 0); + print_metric(config, ctxp, NULL, NULL, "insn per cycle", 0); } total = runtime_stat_avg(st, STAT_STALLED_CYCLES_FRONT, @@ -783,20 +794,20 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel, ctx, cpu)); if (total && avg) { - out->new_line(ctxp); + out->new_line(config, ctxp); ratio = total / avg; - print_metric(ctxp, NULL, "%7.2f ", + print_metric(config, ctxp, NULL, "%7.2f ", "stalled cycles per insn", ratio); } else if (have_frontend_stalled) { - print_metric(ctxp, NULL, NULL, + print_metric(config, ctxp, NULL, NULL, "stalled cycles per insn", 0); } } else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES)) { if (runtime_stat_n(st, STAT_BRANCHES, ctx, cpu) != 0) - print_branch_misses(cpu, evsel, avg, out, st); + print_branch_misses(config, cpu, evsel, avg, out, st); else - print_metric(ctxp, NULL, NULL, "of all branches", 0); + print_metric(config, ctxp, NULL, NULL, "of all branches", 0); } else if ( evsel->attr.type == PERF_TYPE_HW_CACHE && evsel->attr.config == ( PERF_COUNT_HW_CACHE_L1D | @@ -804,9 +815,9 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel, ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { if (runtime_stat_n(st, STAT_L1_DCACHE, ctx, cpu) != 0) - print_l1_dcache_misses(cpu, evsel, avg, out, st); + print_l1_dcache_misses(config, cpu, evsel, avg, out, st); else - print_metric(ctxp, NULL, NULL, "of all L1-dcache hits", 0); + print_metric(config, ctxp, NULL, NULL, "of all L1-dcache hits", 0); } else if ( evsel->attr.type == PERF_TYPE_HW_CACHE && evsel->attr.config == ( PERF_COUNT_HW_CACHE_L1I | @@ -814,9 +825,9 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel, ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { if (runtime_stat_n(st, STAT_L1_ICACHE, ctx, cpu) != 0) - print_l1_icache_misses(cpu, evsel, avg, out, st); + print_l1_icache_misses(config, cpu, evsel, avg, out, st); else - print_metric(ctxp, NULL, NULL, "of all L1-icache hits", 0); + print_metric(config, ctxp, NULL, NULL, "of all L1-icache hits", 0); } else if ( evsel->attr.type == PERF_TYPE_HW_CACHE && evsel->attr.config == ( PERF_COUNT_HW_CACHE_DTLB | @@ -824,9 +835,9 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel, ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { if (runtime_stat_n(st, STAT_DTLB_CACHE, ctx, cpu) != 0) - print_dtlb_cache_misses(cpu, evsel, avg, out, st); + print_dtlb_cache_misses(config, cpu, evsel, avg, out, st); else - print_metric(ctxp, NULL, NULL, "of all dTLB cache hits", 0); + print_metric(config, ctxp, NULL, NULL, "of all dTLB cache hits", 0); } else if ( evsel->attr.type == PERF_TYPE_HW_CACHE && evsel->attr.config == ( PERF_COUNT_HW_CACHE_ITLB | @@ -834,9 +845,9 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel, ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { if (runtime_stat_n(st, STAT_ITLB_CACHE, ctx, cpu) != 0) - print_itlb_cache_misses(cpu, evsel, avg, out, st); + print_itlb_cache_misses(config, cpu, evsel, avg, out, st); else - print_metric(ctxp, NULL, NULL, "of all iTLB cache hits", 0); + print_metric(config, ctxp, NULL, NULL, "of all iTLB cache hits", 0); } else if ( evsel->attr.type == PERF_TYPE_HW_CACHE && evsel->attr.config == ( PERF_COUNT_HW_CACHE_LL | @@ -844,9 +855,9 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel, ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { if (runtime_stat_n(st, STAT_LL_CACHE, ctx, cpu) != 0) - print_ll_cache_misses(cpu, evsel, avg, out, st); + print_ll_cache_misses(config, cpu, evsel, avg, out, st); else - print_metric(ctxp, NULL, NULL, "of all LL-cache hits", 0); + print_metric(config, ctxp, NULL, NULL, "of all LL-cache hits", 0); } else if (perf_evsel__match(evsel, HARDWARE, HW_CACHE_MISSES)) { total = runtime_stat_avg(st, STAT_CACHEREFS, ctx, cpu); @@ -854,32 +865,32 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel, ratio = avg * 100 / total; if (runtime_stat_n(st, STAT_CACHEREFS, ctx, cpu) != 0) - print_metric(ctxp, NULL, "%8.3f %%", + print_metric(config, ctxp, NULL, "%8.3f %%", "of all cache refs", ratio); else - print_metric(ctxp, NULL, NULL, "of all cache refs", 0); + print_metric(config, ctxp, NULL, NULL, "of all cache refs", 0); } else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) { - print_stalled_cycles_frontend(cpu, evsel, avg, out, st); + print_stalled_cycles_frontend(config, cpu, evsel, avg, out, st); } else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) { - print_stalled_cycles_backend(cpu, evsel, avg, out, st); + print_stalled_cycles_backend(config, cpu, evsel, avg, out, st); } else if (perf_evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) { total = runtime_stat_avg(st, STAT_NSECS, 0, cpu); if (total) { ratio = avg / total; - print_metric(ctxp, NULL, "%8.3f", "GHz", ratio); + print_metric(config, ctxp, NULL, "%8.3f", "GHz", ratio); } else { - print_metric(ctxp, NULL, NULL, "Ghz", 0); + print_metric(config, ctxp, NULL, NULL, "Ghz", 0); } } else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX)) { total = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu); if (total) - print_metric(ctxp, NULL, + print_metric(config, ctxp, NULL, "%7.2f%%", "transactional cycles", 100.0 * (avg / total)); else - print_metric(ctxp, NULL, NULL, "transactional cycles", + print_metric(config, ctxp, NULL, NULL, "transactional cycles", 0); } else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX_CP)) { total = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu); @@ -888,10 +899,10 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel, if (total2 < avg) total2 = avg; if (total) - print_metric(ctxp, NULL, "%7.2f%%", "aborted cycles", + print_metric(config, ctxp, NULL, "%7.2f%%", "aborted cycles", 100.0 * ((total2-avg) / total)); else - print_metric(ctxp, NULL, NULL, "aborted cycles", 0); + print_metric(config, ctxp, NULL, NULL, "aborted cycles", 0); } else if (perf_stat_evsel__is(evsel, TRANSACTION_START)) { total = runtime_stat_avg(st, STAT_CYCLES_IN_TX, ctx, cpu); @@ -900,10 +911,10 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel, ratio = total / avg; if (runtime_stat_n(st, STAT_CYCLES_IN_TX, ctx, cpu) != 0) - print_metric(ctxp, NULL, "%8.0f", + print_metric(config, ctxp, NULL, "%8.0f", "cycles / transaction", ratio); else - print_metric(ctxp, NULL, NULL, "cycles / transaction", + print_metric(config, ctxp, NULL, NULL, "cycles / transaction", 0); } else if (perf_stat_evsel__is(evsel, ELISION_START)) { total = runtime_stat_avg(st, STAT_CYCLES_IN_TX, @@ -912,34 +923,33 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel, if (avg) ratio = total / avg; - print_metric(ctxp, NULL, "%8.0f", "cycles / elision", ratio); - } else if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK) || - perf_evsel__match(evsel, SOFTWARE, SW_CPU_CLOCK)) { + print_metric(config, ctxp, NULL, "%8.0f", "cycles / elision", ratio); + } else if (perf_evsel__is_clock(evsel)) { if ((ratio = avg_stats(&walltime_nsecs_stats)) != 0) - print_metric(ctxp, NULL, "%8.3f", "CPUs utilized", - avg / ratio); + print_metric(config, ctxp, NULL, "%8.3f", "CPUs utilized", + avg / (ratio * evsel->scale)); else - print_metric(ctxp, NULL, NULL, "CPUs utilized", 0); + print_metric(config, ctxp, NULL, NULL, "CPUs utilized", 0); } else if (perf_stat_evsel__is(evsel, TOPDOWN_FETCH_BUBBLES)) { double fe_bound = td_fe_bound(ctx, cpu, st); if (fe_bound > 0.2) color = PERF_COLOR_RED; - print_metric(ctxp, color, "%8.1f%%", "frontend bound", + print_metric(config, ctxp, color, "%8.1f%%", "frontend bound", fe_bound * 100.); } else if (perf_stat_evsel__is(evsel, TOPDOWN_SLOTS_RETIRED)) { double retiring = td_retiring(ctx, cpu, st); if (retiring > 0.7) color = PERF_COLOR_GREEN; - print_metric(ctxp, color, "%8.1f%%", "retiring", + print_metric(config, ctxp, color, "%8.1f%%", "retiring", retiring * 100.); } else if (perf_stat_evsel__is(evsel, TOPDOWN_RECOVERY_BUBBLES)) { double bad_spec = td_bad_spec(ctx, cpu, st); if (bad_spec > 0.1) color = PERF_COLOR_RED; - print_metric(ctxp, color, "%8.1f%%", "bad speculation", + print_metric(config, ctxp, color, "%8.1f%%", "bad speculation", bad_spec * 100.); } else if (perf_stat_evsel__is(evsel, TOPDOWN_SLOTS_ISSUED)) { double be_bound = td_be_bound(ctx, cpu, st); @@ -956,12 +966,12 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel, if (be_bound > 0.2) color = PERF_COLOR_RED; if (td_total_slots(ctx, cpu, st) > 0) - print_metric(ctxp, color, "%8.1f%%", name, + print_metric(config, ctxp, color, "%8.1f%%", name, be_bound * 100.); else - print_metric(ctxp, NULL, NULL, name, 0); + print_metric(config, ctxp, NULL, NULL, name, 0); } else if (evsel->metric_expr) { - generic_metric(evsel->metric_expr, evsel->metric_events, evsel->name, + generic_metric(config, evsel->metric_expr, evsel->metric_events, evsel->name, evsel->metric_name, avg, cpu, out, st); } else if (runtime_stat_n(st, STAT_NSECS, 0, cpu) != 0) { char unit = 'M'; @@ -976,9 +986,9 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel, unit = 'K'; } snprintf(unit_buf, sizeof(unit_buf), "%c/sec", unit); - print_metric(ctxp, NULL, "%8.3f", unit_buf, ratio); + print_metric(config, ctxp, NULL, "%8.3f", unit_buf, ratio); } else if (perf_stat_evsel__is(evsel, SMI_NUM)) { - print_smi_cost(cpu, evsel, out, st); + print_smi_cost(config, cpu, evsel, out, st); } else { num = 0; } @@ -988,12 +998,12 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel, list_for_each_entry (mexp, &me->head, nd) { if (num++ > 0) - out->new_line(ctxp); - generic_metric(mexp->metric_expr, mexp->metric_events, + out->new_line(config, ctxp); + generic_metric(config, mexp->metric_expr, mexp->metric_events, evsel->name, mexp->metric_name, avg, cpu, out, st); } } if (num == 0) - print_metric(ctxp, NULL, NULL, NULL, 0); + print_metric(config, ctxp, NULL, NULL, NULL, 0); } diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index a0061e0b0fad..4d40515307b8 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -374,9 +374,8 @@ int perf_stat_process_counter(struct perf_stat_config *config, return 0; } -int perf_event__process_stat_event(struct perf_tool *tool __maybe_unused, - union perf_event *event, - struct perf_session *session) +int perf_event__process_stat_event(struct perf_session *session, + union perf_event *event) { struct perf_counts_values count; struct stat_event *st = &event->stat; @@ -435,3 +434,98 @@ size_t perf_event__fprintf_stat_config(union perf_event *event, FILE *fp) return ret; } + +int create_perf_stat_counter(struct perf_evsel *evsel, + struct perf_stat_config *config, + struct target *target) +{ + struct perf_event_attr *attr = &evsel->attr; + struct perf_evsel *leader = evsel->leader; + + if (config->scale) { + attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED | + PERF_FORMAT_TOTAL_TIME_RUNNING; + } + + /* + * The event is part of non trivial group, let's enable + * the group read (for leader) and ID retrieval for all + * members. + */ + if (leader->nr_members > 1) + attr->read_format |= PERF_FORMAT_ID|PERF_FORMAT_GROUP; + + attr->inherit = !config->no_inherit; + + /* + * Some events get initialized with sample_(period/type) set, + * like tracepoints. Clear it up for counting. + */ + attr->sample_period = 0; + + if (config->identifier) + attr->sample_type = PERF_SAMPLE_IDENTIFIER; + + /* + * Disabling all counters initially, they will be enabled + * either manually by us or by kernel via enable_on_exec + * set later. + */ + if (perf_evsel__is_group_leader(evsel)) { + attr->disabled = 1; + + /* + * In case of initial_delay we enable tracee + * events manually. + */ + if (target__none(target) && !config->initial_delay) + attr->enable_on_exec = 1; + } + + if (target__has_cpu(target) && !target__has_per_thread(target)) + return perf_evsel__open_per_cpu(evsel, perf_evsel__cpus(evsel)); + + return perf_evsel__open_per_thread(evsel, evsel->threads); +} + +int perf_stat_synthesize_config(struct perf_stat_config *config, + struct perf_tool *tool, + struct perf_evlist *evlist, + perf_event__handler_t process, + bool attrs) +{ + int err; + + if (attrs) { + err = perf_event__synthesize_attrs(tool, evlist, process); + if (err < 0) { + pr_err("Couldn't synthesize attrs.\n"); + return err; + } + } + + err = perf_event__synthesize_extra_attr(tool, evlist, process, + attrs); + + err = perf_event__synthesize_thread_map2(tool, evlist->threads, + process, NULL); + if (err < 0) { + pr_err("Couldn't synthesize thread map.\n"); + return err; + } + + err = perf_event__synthesize_cpu_map(tool, evlist->cpus, + process, NULL); + if (err < 0) { + pr_err("Couldn't synthesize thread map.\n"); + return err; + } + + err = perf_event__synthesize_stat_config(tool, config, process, NULL); + if (err < 0) { + pr_err("Couldn't synthesize config.\n"); + return err; + } + + return 0; +} diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index 36efb986f7fc..2f9c9159a364 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -4,8 +4,14 @@ #include <linux/types.h> #include <stdio.h> +#include <sys/types.h> +#include <sys/time.h> +#include <sys/resource.h> +#include <sys/wait.h> #include "xyarray.h" #include "rblist.h" +#include "perf.h" +#include "event.h" struct stats { double n, mean, M2; @@ -84,15 +90,42 @@ struct runtime_stat { struct rblist value_list; }; +typedef int (*aggr_get_id_t)(struct perf_stat_config *config, + struct cpu_map *m, int cpu); + struct perf_stat_config { - enum aggr_mode aggr_mode; - bool scale; - FILE *output; - unsigned int interval; - unsigned int timeout; - int times; - struct runtime_stat *stats; - int stats_num; + enum aggr_mode aggr_mode; + bool scale; + bool no_inherit; + bool identifier; + bool csv_output; + bool interval_clear; + bool metric_only; + bool null_run; + bool ru_display; + bool big_num; + bool no_merge; + bool walltime_run_table; + FILE *output; + unsigned int interval; + unsigned int timeout; + unsigned int initial_delay; + unsigned int unit_width; + unsigned int metric_only_len; + int times; + int run_count; + int print_free_counters_hint; + int print_mixed_hw_group_error; + struct runtime_stat *stats; + int stats_num; + const char *csv_sep; + struct stats *walltime_nsecs_stats; + struct rusage ru_data; + struct cpu_map *aggr_map; + aggr_get_id_t aggr_get_id; + struct cpu_map *cpus_aggr_map; + u64 *walltime_run; + struct rblist metric_events; }; void update_stats(struct stats *stats, u64 val); @@ -130,9 +163,10 @@ bool __perf_evsel_stat__is(struct perf_evsel *evsel, extern struct runtime_stat rt_stat; extern struct stats walltime_nsecs_stats; -typedef void (*print_metric_t)(void *ctx, const char *color, const char *unit, +typedef void (*print_metric_t)(struct perf_stat_config *config, + void *ctx, const char *color, const char *unit, const char *fmt, double val); -typedef void (*new_line_t )(void *ctx); +typedef void (*new_line_t)(struct perf_stat_config *config, void *ctx); void runtime_stat__init(struct runtime_stat *st); void runtime_stat__exit(struct runtime_stat *st); @@ -148,7 +182,8 @@ struct perf_stat_output_ctx { bool force_header; }; -void perf_stat__print_shadow_stats(struct perf_evsel *evsel, +void perf_stat__print_shadow_stats(struct perf_stat_config *config, + struct perf_evsel *evsel, double avg, int cpu, struct perf_stat_output_ctx *out, struct rblist *metric_events, @@ -164,11 +199,25 @@ int perf_stat_process_counter(struct perf_stat_config *config, struct perf_tool; union perf_event; struct perf_session; -int perf_event__process_stat_event(struct perf_tool *tool, - union perf_event *event, - struct perf_session *session); +int perf_event__process_stat_event(struct perf_session *session, + union perf_event *event); size_t perf_event__fprintf_stat(union perf_event *event, FILE *fp); size_t perf_event__fprintf_stat_round(union perf_event *event, FILE *fp); size_t perf_event__fprintf_stat_config(union perf_event *event, FILE *fp); + +int create_perf_stat_counter(struct perf_evsel *evsel, + struct perf_stat_config *config, + struct target *target); +int perf_stat_synthesize_config(struct perf_stat_config *config, + struct perf_tool *tool, + struct perf_evlist *evlist, + perf_event__handler_t process, + bool attrs); +void +perf_evlist__print_counters(struct perf_evlist *evlist, + struct perf_stat_config *config, + struct target *_target, + struct timespec *ts, + int argc, const char **argv); #endif diff --git a/tools/perf/util/strbuf.c b/tools/perf/util/strbuf.c index 3d1cf5bf7f18..9005fbe0780e 100644 --- a/tools/perf/util/strbuf.c +++ b/tools/perf/util/strbuf.c @@ -98,19 +98,25 @@ static int strbuf_addv(struct strbuf *sb, const char *fmt, va_list ap) va_copy(ap_saved, ap); len = vsnprintf(sb->buf + sb->len, sb->alloc - sb->len, fmt, ap); - if (len < 0) + if (len < 0) { + va_end(ap_saved); return len; + } if (len > strbuf_avail(sb)) { ret = strbuf_grow(sb, len); - if (ret) + if (ret) { + va_end(ap_saved); return ret; + } len = vsnprintf(sb->buf + sb->len, sb->alloc - sb->len, fmt, ap_saved); va_end(ap_saved); if (len > strbuf_avail(sb)) { pr_debug("this should not happen, your vsnprintf is broken"); + va_end(ap_saved); return -EINVAL; } } + va_end(ap_saved); return strbuf_setlen(sb, sb->len + len); } diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 29770ea61768..0281d5e2cd67 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -1947,6 +1947,34 @@ void kcore_extract__delete(struct kcore_extract *kce) } #ifdef HAVE_GELF_GETNOTE_SUPPORT + +static void sdt_adjust_loc(struct sdt_note *tmp, GElf_Addr base_off) +{ + if (!base_off) + return; + + if (tmp->bit32) + tmp->addr.a32[SDT_NOTE_IDX_LOC] = + tmp->addr.a32[SDT_NOTE_IDX_LOC] + base_off - + tmp->addr.a32[SDT_NOTE_IDX_BASE]; + else + tmp->addr.a64[SDT_NOTE_IDX_LOC] = + tmp->addr.a64[SDT_NOTE_IDX_LOC] + base_off - + tmp->addr.a64[SDT_NOTE_IDX_BASE]; +} + +static void sdt_adjust_refctr(struct sdt_note *tmp, GElf_Addr base_addr, + GElf_Addr base_off) +{ + if (!base_off) + return; + + if (tmp->bit32 && tmp->addr.a32[SDT_NOTE_IDX_REFCTR]) + tmp->addr.a32[SDT_NOTE_IDX_REFCTR] -= (base_addr - base_off); + else if (tmp->addr.a64[SDT_NOTE_IDX_REFCTR]) + tmp->addr.a64[SDT_NOTE_IDX_REFCTR] -= (base_addr - base_off); +} + /** * populate_sdt_note : Parse raw data and identify SDT note * @elf: elf of the opened file @@ -1964,7 +1992,6 @@ static int populate_sdt_note(Elf **elf, const char *data, size_t len, const char *provider, *name, *args; struct sdt_note *tmp = NULL; GElf_Ehdr ehdr; - GElf_Addr base_off = 0; GElf_Shdr shdr; int ret = -EINVAL; @@ -2060,17 +2087,12 @@ static int populate_sdt_note(Elf **elf, const char *data, size_t len, * base address in the description of the SDT note. If its different, * then accordingly, adjust the note location. */ - if (elf_section_by_name(*elf, &ehdr, &shdr, SDT_BASE_SCN, NULL)) { - base_off = shdr.sh_offset; - if (base_off) { - if (tmp->bit32) - tmp->addr.a32[0] = tmp->addr.a32[0] + base_off - - tmp->addr.a32[1]; - else - tmp->addr.a64[0] = tmp->addr.a64[0] + base_off - - tmp->addr.a64[1]; - } - } + if (elf_section_by_name(*elf, &ehdr, &shdr, SDT_BASE_SCN, NULL)) + sdt_adjust_loc(tmp, shdr.sh_offset); + + /* Adjust reference counter offset */ + if (elf_section_by_name(*elf, &ehdr, &shdr, SDT_PROBES_SCN, NULL)) + sdt_adjust_refctr(tmp, shdr.sh_addr, shdr.sh_offset); list_add_tail(&tmp->note_list, sdt_notes); return 0; diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index f25fae4b5743..20f49779116b 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -379,12 +379,19 @@ int get_sdt_note_list(struct list_head *head, const char *target); int cleanup_sdt_note_list(struct list_head *sdt_notes); int sdt_notes__get_count(struct list_head *start); +#define SDT_PROBES_SCN ".probes" #define SDT_BASE_SCN ".stapsdt.base" #define SDT_NOTE_SCN ".note.stapsdt" #define SDT_NOTE_TYPE 3 #define SDT_NOTE_NAME "stapsdt" #define NR_ADDR 3 +enum { + SDT_NOTE_IDX_LOC = 0, + SDT_NOTE_IDX_BASE, + SDT_NOTE_IDX_REFCTR, +}; + struct mem_info *mem_info__new(void); struct mem_info *mem_info__get(struct mem_info *mi); void mem_info__put(struct mem_info *mi); diff --git a/tools/perf/util/syscalltbl.c b/tools/perf/util/syscalltbl.c index 0ee7f568d60c..3393d7ee9401 100644 --- a/tools/perf/util/syscalltbl.c +++ b/tools/perf/util/syscalltbl.c @@ -38,6 +38,10 @@ static const char **syscalltbl_native = syscalltbl_powerpc_64; #include <asm/syscalls_32.c> const int syscalltbl_native_max_id = SYSCALLTBL_POWERPC_32_MAX_ID; static const char **syscalltbl_native = syscalltbl_powerpc_32; +#elif defined(__aarch64__) +#include <asm/syscalls.c> +const int syscalltbl_native_max_id = SYSCALLTBL_ARM64_MAX_ID; +static const char **syscalltbl_native = syscalltbl_arm64; #endif struct syscall { diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c index dd17d6a38d3a..c091635bf7dc 100644 --- a/tools/perf/util/thread-stack.c +++ b/tools/perf/util/thread-stack.c @@ -36,6 +36,7 @@ * @branch_count: the branch count when the entry was created * @cp: call path * @no_call: a 'call' was not seen + * @trace_end: a 'call' but trace ended */ struct thread_stack_entry { u64 ret_addr; @@ -44,6 +45,7 @@ struct thread_stack_entry { u64 branch_count; struct call_path *cp; bool no_call; + bool trace_end; }; /** @@ -112,7 +114,8 @@ static struct thread_stack *thread_stack__new(struct thread *thread, return ts; } -static int thread_stack__push(struct thread_stack *ts, u64 ret_addr) +static int thread_stack__push(struct thread_stack *ts, u64 ret_addr, + bool trace_end) { int err = 0; @@ -124,6 +127,7 @@ static int thread_stack__push(struct thread_stack *ts, u64 ret_addr) } } + ts->stack[ts->cnt].trace_end = trace_end; ts->stack[ts->cnt++].ret_addr = ret_addr; return err; @@ -150,6 +154,18 @@ static void thread_stack__pop(struct thread_stack *ts, u64 ret_addr) } } +static void thread_stack__pop_trace_end(struct thread_stack *ts) +{ + size_t i; + + for (i = ts->cnt; i; ) { + if (ts->stack[--i].trace_end) + ts->cnt = i; + else + return; + } +} + static bool thread_stack__in_kernel(struct thread_stack *ts) { if (!ts->cnt) @@ -254,10 +270,19 @@ int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip, ret_addr = from_ip + insn_len; if (ret_addr == to_ip) return 0; /* Zero-length calls are excluded */ - return thread_stack__push(thread->ts, ret_addr); - } else if (flags & PERF_IP_FLAG_RETURN) { - if (!from_ip) - return 0; + return thread_stack__push(thread->ts, ret_addr, + flags & PERF_IP_FLAG_TRACE_END); + } else if (flags & PERF_IP_FLAG_TRACE_BEGIN) { + /* + * If the caller did not change the trace number (which would + * have flushed the stack) then try to make sense of the stack. + * Possibly, tracing began after returning to the current + * address, so try to pop that. Also, do not expect a call made + * when the trace ended, to return, so pop that. + */ + thread_stack__pop(thread->ts, to_ip); + thread_stack__pop_trace_end(thread->ts); + } else if ((flags & PERF_IP_FLAG_RETURN) && from_ip) { thread_stack__pop(thread->ts, to_ip); } @@ -332,7 +357,7 @@ void call_return_processor__free(struct call_return_processor *crp) static int thread_stack__push_cp(struct thread_stack *ts, u64 ret_addr, u64 timestamp, u64 ref, struct call_path *cp, - bool no_call) + bool no_call, bool trace_end) { struct thread_stack_entry *tse; int err; @@ -350,6 +375,7 @@ static int thread_stack__push_cp(struct thread_stack *ts, u64 ret_addr, tse->branch_count = ts->branch_count; tse->cp = cp; tse->no_call = no_call; + tse->trace_end = trace_end; return 0; } @@ -423,7 +449,7 @@ static int thread_stack__bottom(struct thread *thread, struct thread_stack *ts, return -ENOMEM; return thread_stack__push_cp(thread->ts, ip, sample->time, ref, cp, - true); + true, false); } static int thread_stack__no_call_return(struct thread *thread, @@ -455,7 +481,7 @@ static int thread_stack__no_call_return(struct thread *thread, if (!cp) return -ENOMEM; return thread_stack__push_cp(ts, 0, sample->time, ref, - cp, true); + cp, true, false); } } else if (thread_stack__in_kernel(ts) && sample->ip < ks) { /* Return to userspace, so pop all kernel addresses */ @@ -480,7 +506,7 @@ static int thread_stack__no_call_return(struct thread *thread, return -ENOMEM; err = thread_stack__push_cp(ts, sample->addr, sample->time, ref, cp, - true); + true, false); if (err) return err; @@ -500,7 +526,7 @@ static int thread_stack__trace_begin(struct thread *thread, /* Pop trace end */ tse = &ts->stack[ts->cnt - 1]; - if (tse->cp->sym == NULL && tse->cp->ip == 0) { + if (tse->trace_end) { err = thread_stack__call_return(thread, ts, --ts->cnt, timestamp, ref, false); if (err) @@ -529,7 +555,7 @@ static int thread_stack__trace_end(struct thread_stack *ts, ret_addr = sample->ip + sample->insn_len; return thread_stack__push_cp(ts, ret_addr, sample->time, ref, cp, - false); + false, true); } int thread_stack__process(struct thread *thread, struct comm *comm, @@ -579,6 +605,7 @@ int thread_stack__process(struct thread *thread, struct comm *comm, ts->last_time = sample->time; if (sample->flags & PERF_IP_FLAG_CALL) { + bool trace_end = sample->flags & PERF_IP_FLAG_TRACE_END; struct call_path_root *cpr = ts->crp->cpr; struct call_path *cp; u64 ret_addr; @@ -596,7 +623,7 @@ int thread_stack__process(struct thread *thread, struct comm *comm, if (!cp) return -ENOMEM; err = thread_stack__push_cp(ts, ret_addr, sample->time, ref, - cp, false); + cp, false, trace_end); } else if (sample->flags & PERF_IP_FLAG_RETURN) { if (!sample->ip || !sample->addr) return 0; diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h index 183c91453522..56e4ca54020a 100644 --- a/tools/perf/util/tool.h +++ b/tools/perf/util/tool.h @@ -26,15 +26,12 @@ typedef int (*event_attr_op)(struct perf_tool *tool, union perf_event *event, struct perf_evlist **pevlist); -typedef int (*event_op2)(struct perf_tool *tool, union perf_event *event, - struct perf_session *session); +typedef int (*event_op2)(struct perf_session *session, union perf_event *event); +typedef s64 (*event_op3)(struct perf_session *session, union perf_event *event); typedef int (*event_oe)(struct perf_tool *tool, union perf_event *event, struct ordered_events *oe); -typedef s64 (*event_op3)(struct perf_tool *tool, union perf_event *event, - struct perf_session *session); - enum show_feature_header { SHOW_FEAT_NO_HEADER = 0, SHOW_FEAT_HEADER, diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c index c85d0d1a65ed..8ad8e755127b 100644 --- a/tools/perf/util/trace-event-info.c +++ b/tools/perf/util/trace-event-info.c @@ -377,7 +377,7 @@ out: static int record_saved_cmdline(void) { - unsigned int size; + unsigned long long size; char *path; struct stat st; int ret, err = 0; @@ -531,12 +531,14 @@ struct tracing_data *tracing_data_get(struct list_head *pattrs, "/tmp/perf-XXXXXX"); if (!mkstemp(tdata->temp_file)) { pr_debug("Can't make temp file"); + free(tdata); return NULL; } temp_fd = open(tdata->temp_file, O_RDWR); if (temp_fd < 0) { pr_debug("Can't read '%s'", tdata->temp_file); + free(tdata); return NULL; } diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c index e0a6e9a6a053..32e558a65af3 100644 --- a/tools/perf/util/trace-event-parse.c +++ b/tools/perf/util/trace-event-parse.c @@ -32,23 +32,24 @@ static int get_common_field(struct scripting_context *context, int *offset, int *size, const char *type) { - struct pevent *pevent = context->pevent; - struct event_format *event; - struct format_field *field; + struct tep_handle *pevent = context->pevent; + struct tep_event_format *event; + struct tep_format_field *field; if (!*size) { - if (!pevent->events) + + event = tep_get_first_event(pevent); + if (!event) return 0; - event = pevent->events[0]; - field = pevent_find_common_field(event, type); + field = tep_find_common_field(event, type); if (!field) return 0; *offset = field->offset; *size = field->size; } - return pevent_read_number(pevent, context->event_data + *offset, *size); + return tep_read_number(pevent, context->event_data + *offset, *size); } int common_lock_depth(struct scripting_context *context) @@ -94,29 +95,29 @@ int common_pc(struct scripting_context *context) } unsigned long long -raw_field_value(struct event_format *event, const char *name, void *data) +raw_field_value(struct tep_event_format *event, const char *name, void *data) { - struct format_field *field; + struct tep_format_field *field; unsigned long long val; - field = pevent_find_any_field(event, name); + field = tep_find_any_field(event, name); if (!field) return 0ULL; - pevent_read_number_field(field, data, &val); + tep_read_number_field(field, data, &val); return val; } -unsigned long long read_size(struct event_format *event, void *ptr, int size) +unsigned long long read_size(struct tep_event_format *event, void *ptr, int size) { - return pevent_read_number(event->pevent, ptr, size); + return tep_read_number(event->pevent, ptr, size); } -void event_format__fprintf(struct event_format *event, +void event_format__fprintf(struct tep_event_format *event, int cpu, void *data, int size, FILE *fp) { - struct pevent_record record; + struct tep_record record; struct trace_seq s; memset(&record, 0, sizeof(record)); @@ -125,18 +126,18 @@ void event_format__fprintf(struct event_format *event, record.data = data; trace_seq_init(&s); - pevent_event_info(&s, event, &record); + tep_event_info(&s, event, &record); trace_seq_do_fprintf(&s, fp); trace_seq_destroy(&s); } -void event_format__print(struct event_format *event, +void event_format__print(struct tep_event_format *event, int cpu, void *data, int size) { return event_format__fprintf(event, cpu, data, size, stdout); } -void parse_ftrace_printk(struct pevent *pevent, +void parse_ftrace_printk(struct tep_handle *pevent, char *file, unsigned int size __maybe_unused) { unsigned long long addr; @@ -157,61 +158,65 @@ void parse_ftrace_printk(struct pevent *pevent, /* fmt still has a space, skip it */ printk = strdup(fmt+1); line = strtok_r(NULL, "\n", &next); - pevent_register_print_string(pevent, printk, addr); + tep_register_print_string(pevent, printk, addr); + free(printk); } } -void parse_saved_cmdline(struct pevent *pevent, +void parse_saved_cmdline(struct tep_handle *pevent, char *file, unsigned int size __maybe_unused) { - char *comm; + char comm[17]; /* Max comm length in the kernel is 16. */ char *line; char *next = NULL; int pid; line = strtok_r(file, "\n", &next); while (line) { - sscanf(line, "%d %ms", &pid, &comm); - pevent_register_comm(pevent, comm, pid); - free(comm); + if (sscanf(line, "%d %16s", &pid, comm) == 2) + tep_register_comm(pevent, comm, pid); line = strtok_r(NULL, "\n", &next); } } -int parse_ftrace_file(struct pevent *pevent, char *buf, unsigned long size) +int parse_ftrace_file(struct tep_handle *pevent, char *buf, unsigned long size) { - return pevent_parse_event(pevent, buf, size, "ftrace"); + return tep_parse_event(pevent, buf, size, "ftrace"); } -int parse_event_file(struct pevent *pevent, +int parse_event_file(struct tep_handle *pevent, char *buf, unsigned long size, char *sys) { - return pevent_parse_event(pevent, buf, size, sys); + return tep_parse_event(pevent, buf, size, sys); } -struct event_format *trace_find_next_event(struct pevent *pevent, - struct event_format *event) +struct tep_event_format *trace_find_next_event(struct tep_handle *pevent, + struct tep_event_format *event) { static int idx; + int events_count; + struct tep_event_format *all_events; - if (!pevent || !pevent->events) + all_events = tep_get_first_event(pevent); + events_count = tep_get_events_count(pevent); + if (!pevent || !all_events || events_count < 1) return NULL; if (!event) { idx = 0; - return pevent->events[0]; + return all_events; } - if (idx < pevent->nr_events && event == pevent->events[idx]) { + if (idx < events_count && event == (all_events + idx)) { idx++; - if (idx == pevent->nr_events) + if (idx == events_count) return NULL; - return pevent->events[idx]; + return (all_events + idx); } - for (idx = 1; idx < pevent->nr_events; idx++) { - if (event == pevent->events[idx - 1]) - return pevent->events[idx]; + for (idx = 1; idx < events_count; idx++) { + if (event == (all_events + (idx - 1))) + return (all_events + idx); } return NULL; } diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c index 40b425949aa3..76f12c705ef9 100644 --- a/tools/perf/util/trace-event-read.c +++ b/tools/perf/util/trace-event-read.c @@ -96,22 +96,22 @@ static void skip(int size) }; } -static unsigned int read4(struct pevent *pevent) +static unsigned int read4(struct tep_handle *pevent) { unsigned int data; if (do_read(&data, 4) < 0) return 0; - return __data2host4(pevent, data); + return __tep_data2host4(pevent, data); } -static unsigned long long read8(struct pevent *pevent) +static unsigned long long read8(struct tep_handle *pevent) { unsigned long long data; if (do_read(&data, 8) < 0) return 0; - return __data2host8(pevent, data); + return __tep_data2host8(pevent, data); } static char *read_string(void) @@ -158,7 +158,7 @@ out: return str; } -static int read_proc_kallsyms(struct pevent *pevent) +static int read_proc_kallsyms(struct tep_handle *pevent) { unsigned int size; @@ -181,7 +181,7 @@ static int read_proc_kallsyms(struct pevent *pevent) return 0; } -static int read_ftrace_printk(struct pevent *pevent) +static int read_ftrace_printk(struct tep_handle *pevent) { unsigned int size; char *buf; @@ -208,7 +208,7 @@ static int read_ftrace_printk(struct pevent *pevent) return 0; } -static int read_header_files(struct pevent *pevent) +static int read_header_files(struct tep_handle *pevent) { unsigned long long size; char *header_page; @@ -235,13 +235,13 @@ static int read_header_files(struct pevent *pevent) return -1; } - if (!pevent_parse_header_page(pevent, header_page, size, - pevent_get_long_size(pevent))) { + if (!tep_parse_header_page(pevent, header_page, size, + tep_get_long_size(pevent))) { /* * The commit field in the page is of type long, * use that instead, since it represents the kernel. */ - pevent_set_long_size(pevent, pevent->header_page_size_size); + tep_set_long_size(pevent, tep_get_header_page_size(pevent)); } free(header_page); @@ -259,7 +259,7 @@ static int read_header_files(struct pevent *pevent) return ret; } -static int read_ftrace_file(struct pevent *pevent, unsigned long long size) +static int read_ftrace_file(struct tep_handle *pevent, unsigned long long size) { int ret; char *buf; @@ -284,8 +284,8 @@ out: return ret; } -static int read_event_file(struct pevent *pevent, char *sys, - unsigned long long size) +static int read_event_file(struct tep_handle *pevent, char *sys, + unsigned long long size) { int ret; char *buf; @@ -297,10 +297,8 @@ static int read_event_file(struct pevent *pevent, char *sys, } ret = do_read(buf, size); - if (ret < 0) { - free(buf); + if (ret < 0) goto out; - } ret = parse_event_file(pevent, buf, size, sys); if (ret < 0) @@ -310,7 +308,7 @@ out: return ret; } -static int read_ftrace_files(struct pevent *pevent) +static int read_ftrace_files(struct tep_handle *pevent) { unsigned long long size; int count; @@ -328,7 +326,7 @@ static int read_ftrace_files(struct pevent *pevent) return 0; } -static int read_event_files(struct pevent *pevent) +static int read_event_files(struct tep_handle *pevent) { unsigned long long size; char *sys; @@ -349,14 +347,17 @@ static int read_event_files(struct pevent *pevent) for (x=0; x < count; x++) { size = read8(pevent); ret = read_event_file(pevent, sys, size); - if (ret) + if (ret) { + free(sys); return ret; + } } + free(sys); } return 0; } -static int read_saved_cmdline(struct pevent *pevent) +static int read_saved_cmdline(struct tep_handle *pevent) { unsigned long long size; char *buf; @@ -399,7 +400,7 @@ ssize_t trace_report(int fd, struct trace_event *tevent, bool __repipe) int host_bigendian; int file_long_size; int file_page_size; - struct pevent *pevent = NULL; + struct tep_handle *pevent = NULL; int err; repipe = __repipe; @@ -439,9 +440,9 @@ ssize_t trace_report(int fd, struct trace_event *tevent, bool __repipe) pevent = tevent->pevent; - pevent_set_flag(pevent, PEVENT_NSEC_OUTPUT); - pevent_set_file_bigendian(pevent, file_bigendian); - pevent_set_host_bigendian(pevent, host_bigendian); + tep_set_flag(pevent, TEP_NSEC_OUTPUT); + tep_set_file_bigendian(pevent, file_bigendian); + tep_set_host_bigendian(pevent, host_bigendian); if (do_read(buf, 1) < 0) goto out; @@ -451,8 +452,8 @@ ssize_t trace_report(int fd, struct trace_event *tevent, bool __repipe) if (!file_page_size) goto out; - pevent_set_long_size(pevent, file_long_size); - pevent_set_page_size(pevent, file_page_size); + tep_set_long_size(pevent, file_long_size); + tep_set_page_size(pevent, file_page_size); err = read_header_files(pevent); if (err) @@ -479,9 +480,9 @@ ssize_t trace_report(int fd, struct trace_event *tevent, bool __repipe) repipe = false; if (show_funcs) { - pevent_print_funcs(pevent); + tep_print_funcs(pevent); } else if (show_printk) { - pevent_print_printk(pevent); + tep_print_printk(pevent); } pevent = NULL; diff --git a/tools/perf/util/trace-event-scripting.c b/tools/perf/util/trace-event-scripting.c index b1e5c3a2b8e3..b749f812ac70 100644 --- a/tools/perf/util/trace-event-scripting.c +++ b/tools/perf/util/trace-event-scripting.c @@ -66,7 +66,7 @@ static int python_start_script_unsupported(const char *script __maybe_unused, return -1; } -static int python_generate_script_unsupported(struct pevent *pevent +static int python_generate_script_unsupported(struct tep_handle *pevent __maybe_unused, const char *outfile __maybe_unused) @@ -130,7 +130,7 @@ static int perl_start_script_unsupported(const char *script __maybe_unused, return -1; } -static int perl_generate_script_unsupported(struct pevent *pevent +static int perl_generate_script_unsupported(struct tep_handle *pevent __maybe_unused, const char *outfile __maybe_unused) { diff --git a/tools/perf/util/trace-event.c b/tools/perf/util/trace-event.c index 1aa368603268..95664b2f771e 100644 --- a/tools/perf/util/trace-event.c +++ b/tools/perf/util/trace-event.c @@ -28,10 +28,10 @@ static bool tevent_initialized; int trace_event__init(struct trace_event *t) { - struct pevent *pevent = pevent_alloc(); + struct tep_handle *pevent = tep_alloc(); if (pevent) { - t->plugin_list = traceevent_load_plugins(pevent); + t->plugin_list = tep_load_plugins(pevent); t->pevent = pevent; } @@ -40,44 +40,44 @@ int trace_event__init(struct trace_event *t) static int trace_event__init2(void) { - int be = traceevent_host_bigendian(); - struct pevent *pevent; + int be = tep_host_bigendian(); + struct tep_handle *pevent; if (trace_event__init(&tevent)) return -1; pevent = tevent.pevent; - pevent_set_flag(pevent, PEVENT_NSEC_OUTPUT); - pevent_set_file_bigendian(pevent, be); - pevent_set_host_bigendian(pevent, be); + tep_set_flag(pevent, TEP_NSEC_OUTPUT); + tep_set_file_bigendian(pevent, be); + tep_set_host_bigendian(pevent, be); tevent_initialized = true; return 0; } int trace_event__register_resolver(struct machine *machine, - pevent_func_resolver_t *func) + tep_func_resolver_t *func) { if (!tevent_initialized && trace_event__init2()) return -1; - return pevent_set_function_resolver(tevent.pevent, func, machine); + return tep_set_function_resolver(tevent.pevent, func, machine); } void trace_event__cleanup(struct trace_event *t) { - traceevent_unload_plugins(t->plugin_list, t->pevent); - pevent_free(t->pevent); + tep_unload_plugins(t->plugin_list, t->pevent); + tep_free(t->pevent); } /* * Returns pointer with encoded error via <linux/err.h> interface. */ -static struct event_format* +static struct tep_event_format* tp_format(const char *sys, const char *name) { char *tp_dir = get_events_file(sys); - struct pevent *pevent = tevent.pevent; - struct event_format *event = NULL; + struct tep_handle *pevent = tevent.pevent; + struct tep_event_format *event = NULL; char path[PATH_MAX]; size_t size; char *data; @@ -93,7 +93,7 @@ tp_format(const char *sys, const char *name) if (err) return ERR_PTR(err); - pevent_parse_format(pevent, &event, data, size, sys); + tep_parse_format(pevent, &event, data, size, sys); free(data); return event; @@ -102,7 +102,7 @@ tp_format(const char *sys, const char *name) /* * Returns pointer with encoded error via <linux/err.h> interface. */ -struct event_format* +struct tep_event_format* trace_event__tp_format(const char *sys, const char *name) { if (!tevent_initialized && trace_event__init2()) @@ -111,10 +111,10 @@ trace_event__tp_format(const char *sys, const char *name) return tp_format(sys, name); } -struct event_format *trace_event__tp_format_id(int id) +struct tep_event_format *trace_event__tp_format_id(int id) { if (!tevent_initialized && trace_event__init2()) return ERR_PTR(-ENOMEM); - return pevent_find_event(tevent.pevent, id); + return tep_find_event(tevent.pevent, id); } diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h index dcbdb53dc702..f024d73bfc40 100644 --- a/tools/perf/util/trace-event.h +++ b/tools/perf/util/trace-event.h @@ -3,6 +3,7 @@ #define _PERF_UTIL_TRACE_EVENT_H #include <traceevent/event-parse.h> +#include <traceevent/trace-seq.h> #include "parse-events.h" struct machine; @@ -10,46 +11,46 @@ struct perf_sample; union perf_event; struct perf_tool; struct thread; -struct plugin_list; +struct tep_plugin_list; struct trace_event { - struct pevent *pevent; - struct plugin_list *plugin_list; + struct tep_handle *pevent; + struct tep_plugin_list *plugin_list; }; int trace_event__init(struct trace_event *t); void trace_event__cleanup(struct trace_event *t); int trace_event__register_resolver(struct machine *machine, - pevent_func_resolver_t *func); -struct event_format* + tep_func_resolver_t *func); +struct tep_event_format* trace_event__tp_format(const char *sys, const char *name); -struct event_format *trace_event__tp_format_id(int id); +struct tep_event_format *trace_event__tp_format_id(int id); int bigendian(void); -void event_format__fprintf(struct event_format *event, +void event_format__fprintf(struct tep_event_format *event, int cpu, void *data, int size, FILE *fp); -void event_format__print(struct event_format *event, +void event_format__print(struct tep_event_format *event, int cpu, void *data, int size); -int parse_ftrace_file(struct pevent *pevent, char *buf, unsigned long size); -int parse_event_file(struct pevent *pevent, +int parse_ftrace_file(struct tep_handle *pevent, char *buf, unsigned long size); +int parse_event_file(struct tep_handle *pevent, char *buf, unsigned long size, char *sys); unsigned long long -raw_field_value(struct event_format *event, const char *name, void *data); +raw_field_value(struct tep_event_format *event, const char *name, void *data); -void parse_proc_kallsyms(struct pevent *pevent, char *file, unsigned int size); -void parse_ftrace_printk(struct pevent *pevent, char *file, unsigned int size); -void parse_saved_cmdline(struct pevent *pevent, char *file, unsigned int size); +void parse_proc_kallsyms(struct tep_handle *pevent, char *file, unsigned int size); +void parse_ftrace_printk(struct tep_handle *pevent, char *file, unsigned int size); +void parse_saved_cmdline(struct tep_handle *pevent, char *file, unsigned int size); ssize_t trace_report(int fd, struct trace_event *tevent, bool repipe); -struct event_format *trace_find_next_event(struct pevent *pevent, - struct event_format *event); -unsigned long long read_size(struct event_format *event, void *ptr, int size); +struct tep_event_format *trace_find_next_event(struct tep_handle *pevent, + struct tep_event_format *event); +unsigned long long read_size(struct tep_event_format *event, void *ptr, int size); unsigned long long eval_flag(const char *flag); int read_tracing_data(int fd, struct list_head *pattrs); @@ -83,7 +84,7 @@ struct scripting_ops { void (*process_stat)(struct perf_stat_config *config, struct perf_evsel *evsel, u64 tstamp); void (*process_stat_interval)(u64 tstamp); - int (*generate_script) (struct pevent *pevent, const char *outfile); + int (*generate_script) (struct tep_handle *pevent, const char *outfile); }; extern unsigned int scripting_max_stack; @@ -94,7 +95,7 @@ void setup_perl_scripting(void); void setup_python_scripting(void); struct scripting_context { - struct pevent *pevent; + struct tep_handle *pevent; void *event_data; }; diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c index 538db4e5d1e6..6f318b15950e 100644 --- a/tools/perf/util/unwind-libdw.c +++ b/tools/perf/util/unwind-libdw.c @@ -77,7 +77,7 @@ static int entry(u64 ip, struct unwind_info *ui) if (__report_module(&al, ip, ui)) return -1; - e->ip = al.addr; + e->ip = ip; e->map = al.map; e->sym = al.sym; diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c index 6a11bc7e6b27..79f521a552cf 100644 --- a/tools/perf/util/unwind-libunwind-local.c +++ b/tools/perf/util/unwind-libunwind-local.c @@ -575,7 +575,7 @@ static int entry(u64 ip, struct thread *thread, struct addr_location al; e.sym = thread__find_symbol(thread, PERF_RECORD_MISC_USER, ip, &al); - e.ip = al.addr; + e.ip = ip; e.map = al.map; pr_debug("unwind: %s:ip = 0x%" PRIx64 " (0x%" PRIx64 ")\n", diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index eac5b858a371..093352e93d50 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -221,7 +221,7 @@ out: return err; } -static int copyfile_offset(int ifd, loff_t off_in, int ofd, loff_t off_out, u64 size) +int copyfile_offset(int ifd, loff_t off_in, int ofd, loff_t off_out, u64 size) { void *ptr; loff_t pgoff; diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index dc58254a2b69..14508ee7707a 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -6,6 +6,7 @@ /* glibc 2.20 deprecates _BSD_SOURCE in favour of _DEFAULT_SOURCE */ #define _DEFAULT_SOURCE 1 +#include <fcntl.h> #include <stdbool.h> #include <stddef.h> #include <stdlib.h> @@ -35,6 +36,7 @@ bool lsdir_no_dot_filter(const char *name, struct dirent *d); int copyfile(const char *from, const char *to); int copyfile_mode(const char *from, const char *to, mode_t mode); int copyfile_ns(const char *from, const char *to, struct nsinfo *nsi); +int copyfile_offset(int ifd, loff_t off_in, int ofd, loff_t off_out, u64 size); ssize_t readn(int fd, void *buf, size_t n); ssize_t writen(int fd, const void *buf, size_t n); diff --git a/tools/perf/util/zlib.c b/tools/perf/util/zlib.c index a725b958cf31..902ce6384f57 100644 --- a/tools/perf/util/zlib.c +++ b/tools/perf/util/zlib.c @@ -5,6 +5,8 @@ #include <sys/stat.h> #include <sys/mman.h> #include <zlib.h> +#include <linux/compiler.h> +#include <unistd.h> #include "util/compress.h" #include "util/util.h" @@ -79,3 +81,19 @@ out_close: return ret == Z_STREAM_END ? 0 : -1; } + +bool gzip_is_compressed(const char *input) +{ + int fd = open(input, O_RDONLY); + const uint8_t magic[2] = { 0x1f, 0x8b }; + char buf[2] = { 0 }; + ssize_t rc; + + if (fd < 0) + return -1; + + rc = read(fd, buf, sizeof(buf)); + close(fd); + return rc == sizeof(buf) ? + memcmp(buf, magic, sizeof(buf)) == 0 : false; +} |
