diff options
55 files changed, 1675 insertions, 340 deletions
diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature index c1daf4d57518..d37e11732f44 100644 --- a/tools/build/Makefile.feature +++ b/tools/build/Makefile.feature @@ -38,9 +38,8 @@ FEATURE_TESTS_BASIC := \ get_current_dir_name \ gettid \ glibc \ - gtk2 \ - gtk2-infobar \ libbfd \ + libbfd-buildid \ libcap \ libelf \ libelf-getphdrnum \ @@ -81,6 +80,8 @@ FEATURE_TESTS_EXTRA := \ compile-32 \ compile-x32 \ cplus-demangle \ + gtk2 \ + gtk2-infobar \ hello \ libbabeltrace \ libbfd-liberty \ @@ -111,8 +112,8 @@ FEATURE_DISPLAY ?= \ dwarf \ dwarf_getlocations \ glibc \ - gtk2 \ libbfd \ + libbfd-buildid \ libcap \ libelf \ libnuma \ diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile index d220fe952747..ec815ffc7777 100644 --- a/tools/build/feature/Makefile +++ b/tools/build/feature/Makefile @@ -15,6 +15,7 @@ FILES= \ test-hello.bin \ test-libaudit.bin \ test-libbfd.bin \ + test-libbfd-buildid.bin \ test-disassembler-four-args.bin \ test-reallocarray.bin \ test-libbfd-liberty.bin \ @@ -90,7 +91,7 @@ __BUILDXX = $(CXX) $(CXXFLAGS) -MD -Wall -Werror -o $@ $(patsubst %.bin,%.cpp,$( ############################### $(OUTPUT)test-all.bin: - $(BUILD) -fstack-protector-all -O2 -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lelf -I/usr/include/slang -lslang $(shell $(PKG_CONFIG) --libs --cflags gtk+-2.0 2>/dev/null) $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl -lz -llzma + $(BUILD) -fstack-protector-all -O2 -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lelf -I/usr/include/slang -lslang $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl -lz -llzma -lzstd $(OUTPUT)test-hello.bin: $(BUILD) @@ -229,6 +230,9 @@ $(OUTPUT)test-libpython-version.bin: $(OUTPUT)test-libbfd.bin: $(BUILD) -DPACKAGE='"perf"' -lbfd -ldl +$(OUTPUT)test-libbfd-buildid.bin: + $(BUILD) -DPACKAGE='"perf"' -lbfd -ldl + $(OUTPUT)test-disassembler-four-args.bin: $(BUILD) -DPACKAGE='"perf"' -lbfd -lopcodes diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c index 5479e543b194..2c955628fc1a 100644 --- a/tools/build/feature/test-all.c +++ b/tools/build/feature/test-all.c @@ -78,18 +78,14 @@ # include "test-libslang.c" #undef main -#define main main_test_gtk2 -# include "test-gtk2.c" -#undef main - -#define main main_test_gtk2_infobar -# include "test-gtk2-infobar.c" -#undef main - #define main main_test_libbfd # include "test-libbfd.c" #undef main +#define main main_test_libbfd_buildid +# include "test-libbfd-buildid.c" +#undef main + #define main main_test_backtrace # include "test-backtrace.c" #undef main @@ -205,9 +201,8 @@ int main(int argc, char *argv[]) main_test_libelf_getshdrstrndx(); main_test_libunwind(); main_test_libslang(); - main_test_gtk2(argc, argv); - main_test_gtk2_infobar(argc, argv); main_test_libbfd(); + main_test_libbfd_buildid(); main_test_backtrace(); main_test_libnuma(); main_test_numa_num_possible_cpus(); diff --git a/tools/build/feature/test-libbfd-buildid.c b/tools/build/feature/test-libbfd-buildid.c new file mode 100644 index 000000000000..157644b04c05 --- /dev/null +++ b/tools/build/feature/test-libbfd-buildid.c @@ -0,0 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <bfd.h> + +int main(void) +{ + bfd *abfd = bfd_openr("Pedro", 0); + return abfd && (!abfd->build_id || abfd->build_id->size > 0x506564726f); +} diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt index 76408d986aed..31069d8a5304 100644 --- a/tools/perf/Documentation/perf-config.txt +++ b/tools/perf/Documentation/perf-config.txt @@ -242,6 +242,11 @@ annotate.*:: These are in control of addresses, jump function, source code in lines of assembly code from a specific program. + annotate.disassembler_style: + Use this to change the default disassembler style to some other value + supported by binutils, such as "intel", see the '-M' option help in the + 'objdump' man page. + annotate.hide_src_code:: If a program which is analyzed has source code, this option lets 'annotate' print a list of assembly code with the source code. diff --git a/tools/perf/Documentation/perf-ftrace.txt b/tools/perf/Documentation/perf-ftrace.txt index 78358af9a1c4..1e91121bac0f 100644 --- a/tools/perf/Documentation/perf-ftrace.txt +++ b/tools/perf/Documentation/perf-ftrace.txt @@ -33,7 +33,8 @@ OPTIONS -F:: --funcs:: - List all available functions to trace. + List available functions to trace. It accepts a pattern to + only list interested functions. -p:: --pid=:: diff --git a/tools/perf/Documentation/perf-intel-pt.txt b/tools/perf/Documentation/perf-intel-pt.txt index d5a266d7f15b..cb637e0d0743 100644 --- a/tools/perf/Documentation/perf-intel-pt.txt +++ b/tools/perf/Documentation/perf-intel-pt.txt @@ -558,7 +558,7 @@ The mmap size and auxtrace mmap size are displayed if the -vv option is used e.g Intel PT modes of operation ~~~~~~~~~~~~~~~~~~~~~~~~~~~ -Intel PT can be used in 2 modes: +Intel PT can be used in 3 modes: full-trace mode sample mode snapshot mode @@ -571,7 +571,8 @@ Sample mode attaches a Intel PT sample to other events e.g. perf record --aux-sample -e intel_pt//u -e branch-misses:u -Snapshot mode captures the available data when a signal is sent e.g. +Snapshot mode captures the available data when a signal is sent or "snapshot" +control command is issued. e.g. using a signal perf record -v -e intel_pt//u -S ./loopy 1000000000 & [1] 11435 @@ -582,7 +583,23 @@ Note that the signal sent is SIGUSR2. Note that "Recording AUX area tracing snapshot" is displayed because the -v option is used. -The 2 modes cannot be used together. +The advantage of using "snapshot" control command is that the access is +controlled by access to a FIFO e.g. + + $ mkfifo perf.control + $ mkfifo perf.ack + $ cat perf.ack & + [1] 15235 + $ sudo ~/bin/perf record --control fifo:perf.control,perf.ack -S -e intel_pt//u -- sleep 60 & + [2] 15243 + $ ps -e | grep perf + 15244 pts/1 00:00:00 perf + $ kill -USR2 15244 + bash: kill: (15244) - Operation not permitted + $ echo snapshot > perf.control + ack + +The 3 Intel PT modes of operation cannot be used together. Buffer handling diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index bd50cdff08a8..768888b9326a 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -631,43 +631,45 @@ option. The -e option and this one can be mixed and matched. Events can be grouped using the {} notation. endif::HAVE_LIBPFM[] ---control fd:ctl-fd[,ack-fd] +--control=fifo:ctl-fifo[,ack-fifo]:: +--control=fd:ctl-fd[,ack-fd]:: +ctl-fifo / ack-fifo are opened and used as ctl-fd / ack-fd as follows. Listen on ctl-fd descriptor for command to control measurement ('enable': enable events, -'disable': disable events). Measurements can be started with events disabled using ---delay=-1 option. Optionally send control command completion ('ack\n') to ack-fd descriptor -to synchronize with the controlling process. Example of bash shell script to enable and -disable events during measurements: +'disable': disable events, 'snapshot': AUX area tracing snapshot). Measurements can be +started with events disabled using --delay=-1 option. Optionally send control command +completion ('ack\n') to ack-fd descriptor to synchronize with the controlling process. +Example of bash shell script to enable and disable events during measurements: -#!/bin/bash + #!/bin/bash -ctl_dir=/tmp/ + ctl_dir=/tmp/ -ctl_fifo=${ctl_dir}perf_ctl.fifo -test -p ${ctl_fifo} && unlink ${ctl_fifo} -mkfifo ${ctl_fifo} -exec {ctl_fd}<>${ctl_fifo} + ctl_fifo=${ctl_dir}perf_ctl.fifo + test -p ${ctl_fifo} && unlink ${ctl_fifo} + mkfifo ${ctl_fifo} + exec {ctl_fd}<>${ctl_fifo} -ctl_ack_fifo=${ctl_dir}perf_ctl_ack.fifo -test -p ${ctl_ack_fifo} && unlink ${ctl_ack_fifo} -mkfifo ${ctl_ack_fifo} -exec {ctl_fd_ack}<>${ctl_ack_fifo} + ctl_ack_fifo=${ctl_dir}perf_ctl_ack.fifo + test -p ${ctl_ack_fifo} && unlink ${ctl_ack_fifo} + mkfifo ${ctl_ack_fifo} + exec {ctl_fd_ack}<>${ctl_ack_fifo} -perf record -D -1 -e cpu-cycles -a \ - --control fd:${ctl_fd},${ctl_fd_ack} \ - -- sleep 30 & -perf_pid=$! + perf record -D -1 -e cpu-cycles -a \ + --control fd:${ctl_fd},${ctl_fd_ack} \ + -- sleep 30 & + perf_pid=$! -sleep 5 && echo 'enable' >&${ctl_fd} && read -u ${ctl_fd_ack} e1 && echo "enabled(${e1})" -sleep 10 && echo 'disable' >&${ctl_fd} && read -u ${ctl_fd_ack} d1 && echo "disabled(${d1})" + sleep 5 && echo 'enable' >&${ctl_fd} && read -u ${ctl_fd_ack} e1 && echo "enabled(${e1})" + sleep 10 && echo 'disable' >&${ctl_fd} && read -u ${ctl_fd_ack} d1 && echo "disabled(${d1})" -exec {ctl_fd_ack}>&- -unlink ${ctl_ack_fifo} + exec {ctl_fd_ack}>&- + unlink ${ctl_ack_fifo} -exec {ctl_fd}>&- -unlink ${ctl_fifo} + exec {ctl_fd}>&- + unlink ${ctl_fifo} -wait -n ${perf_pid} -exit $? + wait -n ${perf_pid} + exit $? SEE ALSO diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt index db420dd75e43..7d18694e592a 100644 --- a/tools/perf/Documentation/perf-stat.txt +++ b/tools/perf/Documentation/perf-stat.txt @@ -180,43 +180,45 @@ with it. --append may be used here. Examples: 3>results perf stat --log-fd 3 -- $cmd 3>>results perf stat --log-fd 3 --append -- $cmd ---control fd:ctl-fd[,ack-fd] +--control=fifo:ctl-fifo[,ack-fifo]:: +--control=fd:ctl-fd[,ack-fd]:: +ctl-fifo / ack-fifo are opened and used as ctl-fd / ack-fd as follows. Listen on ctl-fd descriptor for command to control measurement ('enable': enable events, 'disable': disable events). Measurements can be started with events disabled using --delay=-1 option. Optionally send control command completion ('ack\n') to ack-fd descriptor to synchronize with the controlling process. Example of bash shell script to enable and disable events during measurements: -#!/bin/bash + #!/bin/bash -ctl_dir=/tmp/ + ctl_dir=/tmp/ -ctl_fifo=${ctl_dir}perf_ctl.fifo -test -p ${ctl_fifo} && unlink ${ctl_fifo} -mkfifo ${ctl_fifo} -exec {ctl_fd}<>${ctl_fifo} + ctl_fifo=${ctl_dir}perf_ctl.fifo + test -p ${ctl_fifo} && unlink ${ctl_fifo} + mkfifo ${ctl_fifo} + exec {ctl_fd}<>${ctl_fifo} -ctl_ack_fifo=${ctl_dir}perf_ctl_ack.fifo -test -p ${ctl_ack_fifo} && unlink ${ctl_ack_fifo} -mkfifo ${ctl_ack_fifo} -exec {ctl_fd_ack}<>${ctl_ack_fifo} + ctl_ack_fifo=${ctl_dir}perf_ctl_ack.fifo + test -p ${ctl_ack_fifo} && unlink ${ctl_ack_fifo} + mkfifo ${ctl_ack_fifo} + exec {ctl_fd_ack}<>${ctl_ack_fifo} -perf stat -D -1 -e cpu-cycles -a -I 1000 \ - --control fd:${ctl_fd},${ctl_fd_ack} \ - -- sleep 30 & -perf_pid=$! + perf stat -D -1 -e cpu-cycles -a -I 1000 \ + --control fd:${ctl_fd},${ctl_fd_ack} \ + -- sleep 30 & + perf_pid=$! -sleep 5 && echo 'enable' >&${ctl_fd} && read -u ${ctl_fd_ack} e1 && echo "enabled(${e1})" -sleep 10 && echo 'disable' >&${ctl_fd} && read -u ${ctl_fd_ack} d1 && echo "disabled(${d1})" + sleep 5 && echo 'enable' >&${ctl_fd} && read -u ${ctl_fd_ack} e1 && echo "enabled(${e1})" + sleep 10 && echo 'disable' >&${ctl_fd} && read -u ${ctl_fd_ack} d1 && echo "disabled(${d1})" -exec {ctl_fd_ack}>&- -unlink ${ctl_ack_fifo} + exec {ctl_fd_ack}>&- + unlink ${ctl_ack_fifo} -exec {ctl_fd}>&- -unlink ${ctl_fifo} + exec {ctl_fd}>&- + unlink ${ctl_fifo} -wait -n ${perf_pid} -exit $? + wait -n ${perf_pid} + exit $? --pre:: diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 190be4fa5c21..854da830b5ca 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -724,12 +724,14 @@ ifndef NO_SLANG endif endif -ifndef NO_GTK2 +ifdef GTK2 FLAGS_GTK2=$(CFLAGS) $(LDFLAGS) $(EXTLIBS) $(shell $(PKG_CONFIG) --libs --cflags gtk+-2.0 2>/dev/null) + $(call feature_check,gtk2) ifneq ($(feature-gtk2), 1) msg := $(warning GTK2 not found, disables GTK2 support. Please install gtk2-devel or libgtk2.0-dev); NO_GTK2 := 1 else + $(call feature_check,gtk2-infobar) ifeq ($(feature-gtk2-infobar), 1) GTK_CFLAGS := -DHAVE_GTK_INFO_BAR_SUPPORT endif @@ -825,6 +827,12 @@ else $(call feature_check,disassembler-four-args) endif +ifeq ($(feature-libbfd-buildid), 1) + CFLAGS += -DHAVE_LIBBFD_BUILDID_SUPPORT +else + msg := $(warning Old version of libbfd/binutils things like PE executable profiling will not be available); +endif + ifdef NO_DEMANGLE CFLAGS += -DNO_DEMANGLE else diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 6031167939ae..920d8afb9238 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -48,7 +48,7 @@ include ../scripts/utilities.mak # # Define NO_SLANG if you do not want TUI support. # -# Define NO_GTK2 if you do not want GTK+ GUI support. +# Define GTK2 if you want GTK+ GUI support. # # Define NO_DEMANGLE if you do not want C++ symbol demangling. # @@ -386,7 +386,7 @@ ifneq ($(OUTPUT),) CFLAGS += -I$(OUTPUT) endif -ifndef NO_GTK2 +ifdef GTK2 ALL_PROGRAMS += $(OUTPUT)libperf-gtk.so GTK_IN := $(OUTPUT)gtk-in.o endif @@ -886,7 +886,7 @@ check: $(OUTPUT)common-cmds.h ### Installation rules -ifndef NO_GTK2 +ifdef GTK2 install-gtk: $(OUTPUT)libperf-gtk.so $(call QUIET_INSTALL, 'GTK UI') \ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(libdir_SQ)'; \ @@ -961,6 +961,7 @@ install-tests: all install-gtk $(call QUIET_INSTALL, tests) \ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'; \ $(INSTALL) tests/attr.py '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'; \ + $(INSTALL) tests/pe-file.exe* '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'; \ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'; \ $(INSTALL) tests/attr/* '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'; \ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell'; \ diff --git a/tools/perf/arch/powerpc/util/header.c b/tools/perf/arch/powerpc/util/header.c index 1a950171a66f..58b2d610aadb 100644 --- a/tools/perf/arch/powerpc/util/header.c +++ b/tools/perf/arch/powerpc/util/header.c @@ -40,8 +40,11 @@ get_cpuid_str(struct perf_pmu *pmu __maybe_unused) return bufp; } -int arch_get_runtimeparam(void) +int arch_get_runtimeparam(struct pmu_event *pe) { int count; - return sysfs__read_int("/devices/hv_24x7/interface/sockets", &count) < 0 ? 1 : count; + char path[PATH_MAX] = "/devices/hv_24x7/interface/"; + + atoi(pe->aggr_mode) == PerChip ? strcat(path, "sockets") : strcat(path, "coresperchip"); + return sysfs__read_int(path, &count) < 0 ? 1 : count; } diff --git a/tools/perf/arch/x86/annotate/instructions.c b/tools/perf/arch/x86/annotate/instructions.c index 7eb5621c021d..24ea12ec7e02 100644 --- a/tools/perf/arch/x86/annotate/instructions.c +++ b/tools/perf/arch/x86/annotate/instructions.c @@ -110,6 +110,7 @@ static struct ins x86__instructions[] = { { .name = "por", .ops = &mov_ops, }, { .name = "rclb", .ops = &mov_ops, }, { .name = "rcll", .ops = &mov_ops, }, + { .name = "ret", .ops = &ret_ops, }, { .name = "retq", .ops = &ret_ops, }, { .name = "sbb", .ops = &mov_ops, }, { .name = "sbbl", .ops = &mov_ops, }, diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c index 1d44bc2f63d8..9366fad591dc 100644 --- a/tools/perf/builtin-ftrace.c +++ b/tools/perf/builtin-ftrace.c @@ -25,6 +25,7 @@ #include "target.h" #include "cpumap.h" #include "thread_map.h" +#include "strfilter.h" #include "util/cap.h" #include "util/config.h" #include "util/units.h" @@ -36,7 +37,6 @@ struct perf_ftrace { struct evlist *evlist; struct target target; const char *tracer; - bool list_avail_functions; struct list_head filters; struct list_head notrace; struct list_head graph_funcs; @@ -181,6 +181,40 @@ out: return ret; } +static int read_tracing_file_by_line(const char *name, + void (*cb)(char *str, void *arg), + void *cb_arg) +{ + char *line = NULL; + size_t len = 0; + char *file; + FILE *fp; + + file = get_tracing_file(name); + if (!file) { + pr_debug("cannot get tracing file: %s\n", name); + return -1; + } + + fp = fopen(file, "r"); + if (fp == NULL) { + pr_debug("cannot open tracing file: %s\n", name); + put_tracing_file(file); + return -1; + } + + while (getline(&line, &len, fp) != -1) { + cb(line, cb_arg); + } + + if (line) + free(line); + + fclose(fp); + put_tracing_file(file); + return 0; +} + static int write_tracing_file_int(const char *name, int value) { char buf[16]; @@ -557,9 +591,6 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv) signal(SIGCHLD, sig_handler); signal(SIGPIPE, sig_handler); - if (ftrace->list_avail_functions) - return read_tracing_file_to_stdout("available_filter_functions"); - if (reset_tracing_files(ftrace) < 0) { pr_err("failed to reset ftrace\n"); goto out; @@ -683,6 +714,46 @@ static int perf_ftrace_config(const char *var, const char *value, void *cb) return -1; } +static void list_function_cb(char *str, void *arg) +{ + struct strfilter *filter = (struct strfilter *)arg; + + if (strfilter__compare(filter, str)) + printf("%s", str); +} + +static int opt_list_avail_functions(const struct option *opt __maybe_unused, + const char *str, int unset) +{ + struct strfilter *filter; + const char *err = NULL; + int ret; + + if (unset || !str) + return -1; + + filter = strfilter__new(str, &err); + if (!filter) + return err ? -EINVAL : -ENOMEM; + + ret = strfilter__or(filter, str, &err); + if (ret == -EINVAL) { + pr_err("Filter parse error at %td.\n", err - str + 1); + pr_err("Source: \"%s\"\n", str); + pr_err(" %*c\n", (int)(err - str + 1), '^'); + strfilter__delete(filter); + return ret; + } + + ret = read_tracing_file_by_line("available_filter_functions", + list_function_cb, filter); + strfilter__delete(filter); + if (ret < 0) + return ret; + + exit(0); +} + static int parse_filter_func(const struct option *opt, const char *str, int unset __maybe_unused) { @@ -817,8 +888,9 @@ int cmd_ftrace(int argc, const char **argv) const struct option ftrace_options[] = { OPT_STRING('t', "tracer", &ftrace.tracer, "tracer", "Tracer to use: function_graph(default) or function"), - OPT_BOOLEAN('F', "funcs", &ftrace.list_avail_functions, - "Show available functions to filter"), + OPT_CALLBACK_DEFAULT('F', "funcs", NULL, "[FILTER]", + "Show available functions to filter", + opt_list_avail_functions, "*"), OPT_STRING('p', "pid", &ftrace.target.pid, "pid", "Trace on existing process id"), /* TODO: Add short option -t after -t/--tracer can be removed. */ diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c index 0a7fe4cb5555..10ab5e40a34f 100644 --- a/tools/perf/builtin-list.c +++ b/tools/perf/builtin-list.c @@ -92,13 +92,6 @@ int cmd_list(int argc, const char **argv) else if ((sep = strchr(argv[i], ':')) != NULL) { int sep_idx; - if (sep == NULL) { - print_events(argv[i], raw_dump, !desc_flag, - long_desc_flag, - details_flag, - deprecated); - continue; - } sep_idx = sep - argv[i]; s = strdup(argv[i]); if (s == NULL) diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 772f1057647f..adf311d15d3d 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -1593,6 +1593,16 @@ static int record__init_clock(struct record *rec) return 0; } +static void hit_auxtrace_snapshot_trigger(struct record *rec) +{ + if (trigger_is_ready(&auxtrace_snapshot_trigger)) { + trigger_hit(&auxtrace_snapshot_trigger); + auxtrace_record__snapshot_started = 1; + if (auxtrace_record__snapshot_start(rec->itr)) + trigger_error(&auxtrace_snapshot_trigger); + } +} + static int __cmd_record(struct record *rec, int argc, const char **argv) { int err; @@ -1937,6 +1947,10 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) case EVLIST_CTL_CMD_DISABLE: pr_info(EVLIST_DISABLED_MSG); break; + case EVLIST_CTL_CMD_SNAPSHOT: + hit_auxtrace_snapshot_trigger(rec); + evlist__ctlfd_ack(rec->evlist); + break; case EVLIST_CTL_CMD_ACK: case EVLIST_CTL_CMD_UNSUPPORTED: default: @@ -2234,27 +2248,9 @@ static int parse_control_option(const struct option *opt, const char *str, int unset __maybe_unused) { - char *comma = NULL, *endptr = NULL; - struct record_opts *config = (struct record_opts *)opt->value; - - if (strncmp(str, "fd:", 3)) - return -EINVAL; - - config->ctl_fd = strtoul(&str[3], &endptr, 0); - if (endptr == &str[3]) - return -EINVAL; - - comma = strchr(str, ','); - if (comma) { - if (endptr != comma) - return -EINVAL; - - config->ctl_fd_ack = strtoul(comma + 1, &endptr, 0); - if (endptr == comma + 1 || *endptr != '\0') - return -EINVAL; - } + struct record_opts *opts = opt->value; - return 0; + return evlist__parse_control(str, &opts->ctl_fd, &opts->ctl_fd_ack, &opts->ctl_fd_close); } static void switch_output_size_warn(struct record *rec) @@ -2596,9 +2592,11 @@ static struct option __record_options[] = { "libpfm4 event selector. use 'perf list' to list available events", parse_libpfm_events_option), #endif - OPT_CALLBACK(0, "control", &record.opts, "fd:ctl-fd[,ack-fd]", - "Listen on ctl-fd descriptor for command to control measurement ('enable': enable events, 'disable': disable events).\n" - "\t\t\t Optionally send control command completion ('ack\\n') to ack-fd descriptor.", + OPT_CALLBACK(0, "control", &record.opts, "fd:ctl-fd[,ack-fd] or fifo:ctl-fifo[,ack-fifo]", + "Listen on ctl-fd descriptor for command to control measurement ('enable': enable events, 'disable': disable events,\n" + "\t\t\t 'snapshot': AUX area tracing snapshot).\n" + "\t\t\t Optionally send control command completion ('ack\\n') to ack-fd descriptor.\n" + "\t\t\t Alternatively, ctl-fifo / ack-fifo will be opened and used as ctl-fd / ack-fd.", parse_control_option), OPT_END() }; @@ -2671,12 +2669,14 @@ int cmd_record(int argc, const char **argv) !perf_can_record_switch_events()) { ui__error("kernel does not support recording context switch events\n"); parse_options_usage(record_usage, record_options, "switch-events", 0); - return -EINVAL; + err = -EINVAL; + goto out_opts; } if (switch_output_setup(rec)) { parse_options_usage(record_usage, record_options, "switch-output", 0); - return -EINVAL; + err = -EINVAL; + goto out_opts; } if (rec->switch_output.time) { @@ -2687,8 +2687,10 @@ int cmd_record(int argc, const char **argv) if (rec->switch_output.num_files) { rec->switch_output.filenames = calloc(sizeof(char *), rec->switch_output.num_files); - if (!rec->switch_output.filenames) - return -EINVAL; + if (!rec->switch_output.filenames) { + err = -EINVAL; + goto out_opts; + } } /* @@ -2704,7 +2706,8 @@ int cmd_record(int argc, const char **argv) rec->affinity_mask.bits = bitmap_alloc(rec->affinity_mask.nbits); if (!rec->affinity_mask.bits) { pr_err("Failed to allocate thread mask for %zd cpus\n", rec->affinity_mask.nbits); - return -ENOMEM; + err = -ENOMEM; + goto out_opts; } pr_debug2("thread mask[%zd]: empty\n", rec->affinity_mask.nbits); } @@ -2835,6 +2838,8 @@ out: evlist__delete(rec->evlist); symbol__exit(); auxtrace_record__free(rec->itr); +out_opts: + evlist__close_control(rec->opts.ctl_fd, rec->opts.ctl_fd_ack, &rec->opts.ctl_fd_close); return err; } @@ -2842,12 +2847,7 @@ static void snapshot_sig_handler(int sig __maybe_unused) { struct record *rec = &record; - if (trigger_is_ready(&auxtrace_snapshot_trigger)) { - trigger_hit(&auxtrace_snapshot_trigger); - auxtrace_record__snapshot_started = 1; - if (auxtrace_record__snapshot_start(record.itr)) - trigger_error(&auxtrace_snapshot_trigger); - } + hit_auxtrace_snapshot_trigger(rec); if (switch_output_signal(rec)) trigger_hit(&switch_output_trigger); diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index fddc97cac984..7f8d756d9408 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -578,6 +578,7 @@ static void process_evlist(struct evlist *evlist, unsigned int interval) process_interval(); pr_info(EVLIST_DISABLED_MSG); break; + case EVLIST_CTL_CMD_SNAPSHOT: case EVLIST_CTL_CMD_ACK: case EVLIST_CTL_CMD_UNSUPPORTED: default: @@ -1045,27 +1046,9 @@ static int parse_control_option(const struct option *opt, const char *str, int unset __maybe_unused) { - char *comma = NULL, *endptr = NULL; - struct perf_stat_config *config = (struct perf_stat_config *)opt->value; + struct perf_stat_config *config = opt->value; - if (strncmp(str, "fd:", 3)) - return -EINVAL; - - config->ctl_fd = strtoul(&str[3], &endptr, 0); - if (endptr == &str[3]) - return -EINVAL; - - comma = strchr(str, ','); - if (comma) { - if (endptr != comma) - return -EINVAL; - - config->ctl_fd_ack = strtoul(comma + 1, &endptr, 0); - if (endptr == comma + 1 || *endptr != '\0') - return -EINVAL; - } - - return 0; + return evlist__parse_control(str, &config->ctl_fd, &config->ctl_fd_ack, &config->ctl_fd_close); } static struct option stat_options[] = { @@ -1171,9 +1154,10 @@ static struct option stat_options[] = { "libpfm4 event selector. use 'perf list' to list available events", parse_libpfm_events_option), #endif - OPT_CALLBACK(0, "control", &stat_config, "fd:ctl-fd[,ack-fd]", + OPT_CALLBACK(0, "control", &stat_config, "fd:ctl-fd[,ack-fd] or fifo:ctl-fifo[,ack-fifo]", "Listen on ctl-fd descriptor for command to control measurement ('enable': enable events, 'disable': disable events).\n" - "\t\t\t Optionally send control command completion ('ack\\n') to ack-fd descriptor.", + "\t\t\t Optionally send control command completion ('ack\\n') to ack-fd descriptor.\n" + "\t\t\t Alternatively, ctl-fifo / ack-fifo will be opened and used as ctl-fd / ack-fd.", parse_control_option), OPT_END() }; @@ -2416,6 +2400,7 @@ out: metricgroup__rblist_exit(&stat_config.metric_events); runtime_stat_delete(&stat_config); + evlist__close_control(stat_config.ctl_fd, stat_config.ctl_fd_ack, &stat_config.ctl_fd_close); return status; } diff --git a/tools/perf/builtin-version.c b/tools/perf/builtin-version.c index 05cf2af9e2c2..d09ec2f03071 100644 --- a/tools/perf/builtin-version.c +++ b/tools/perf/builtin-version.c @@ -60,7 +60,6 @@ static void library_status(void) STATUS(HAVE_DWARF_SUPPORT, dwarf); STATUS(HAVE_DWARF_GETLOCATIONS_SUPPORT, dwarf_getlocations); STATUS(HAVE_GLIBC_SUPPORT, glibc); - STATUS(HAVE_GTK2_SUPPORT, gtk2); #ifndef HAVE_SYSCALL_TABLE_SUPPORT STATUS(HAVE_LIBAUDIT_SUPPORT, libaudit); #endif diff --git a/tools/perf/perf-sys.h b/tools/perf/perf-sys.h index 15e458e150bd..7a2264e1e4e1 100644 --- a/tools/perf/perf-sys.h +++ b/tools/perf/perf-sys.h @@ -9,31 +9,13 @@ struct perf_event_attr; -extern bool test_attr__enabled; -void test_attr__ready(void); -void test_attr__init(void); -void test_attr__open(struct perf_event_attr *attr, pid_t pid, int cpu, - int fd, int group_fd, unsigned long flags); - -#ifndef HAVE_ATTR_TEST -#define HAVE_ATTR_TEST 1 -#endif - static inline int sys_perf_event_open(struct perf_event_attr *attr, pid_t pid, int cpu, int group_fd, unsigned long flags) { - int fd; - - fd = syscall(__NR_perf_event_open, attr, pid, cpu, - group_fd, flags); - -#if HAVE_ATTR_TEST - if (unlikely(test_attr__enabled)) - test_attr__open(attr, pid, cpu, fd, group_fd, flags); -#endif - return fd; + return syscall(__NR_perf_event_open, attr, pid, cpu, + group_fd, flags); } #endif /* _PERF_SYS_H */ diff --git a/tools/perf/pmu-events/arch/powerpc/power9/nest_metrics.json b/tools/perf/pmu-events/arch/powerpc/power9/nest_metrics.json index 8383a37647ad..7a5d1bf543f8 100644 --- a/tools/perf/pmu-events/arch/powerpc/power9/nest_metrics.json +++ b/tools/perf/pmu-events/arch/powerpc/power9/nest_metrics.json @@ -1,37 +1,46 @@ [ { - "MetricExpr": "(hv_24x7@PM_MCS01_128B_RD_DISP_PORT01\\,chip\\=?@ + hv_24x7@PM_MCS01_128B_RD_DISP_PORT23\\,chip\\=?@ + hv_24x7@PM_MCS23_128B_RD_DISP_PORT01\\,chip\\=?@ + hv_24x7@PM_MCS23_128B_RD_DISP_PORT23\\,chip\\=?@)", - "MetricName": "Memory_RD_BW_Chip", - "MetricGroup": "Memory_BW", - "ScaleUnit": "1.6e-2MB" + "MetricExpr": "(hv_24x7@PM_MCS01_128B_RD_DISP_PORT01\\,chip\\=?@ + hv_24x7@PM_MCS01_128B_RD_DISP_PORT23\\,chip\\=?@ + hv_24x7@PM_MCS23_128B_RD_DISP_PORT01\\,chip\\=?@ + hv_24x7@PM_MCS23_128B_RD_DISP_PORT23\\,chip\\=?@)", + "MetricName": "Memory_RD_BW_Chip", + "MetricGroup": "Memory_BW", + "ScaleUnit": "1.6e-2MB", + "AggregationMode": "PerChip" }, { "MetricExpr": "(hv_24x7@PM_MCS01_128B_WR_DISP_PORT01\\,chip\\=?@ + hv_24x7@PM_MCS01_128B_WR_DISP_PORT23\\,chip\\=?@ + hv_24x7@PM_MCS23_128B_WR_DISP_PORT01\\,chip\\=?@ + hv_24x7@PM_MCS23_128B_WR_DISP_PORT23\\,chip\\=?@ )", - "MetricName": "Memory_WR_BW_Chip", - "MetricGroup": "Memory_BW", - "ScaleUnit": "1.6e-2MB" + "MetricName": "Memory_WR_BW_Chip", + "MetricGroup": "Memory_BW", + "ScaleUnit": "1.6e-2MB", + "AggregationMode": "PerChip" }, { "MetricExpr": "(hv_24x7@PM_PB_CYC\\,chip\\=?@ )", - "MetricName": "PowerBUS_Frequency", - "ScaleUnit": "2.5e-7GHz" + "MetricName": "PowerBUS_Frequency", + "ScaleUnit": "2.5e-7GHz", + "AggregationMode": "PerChip" + }, + { + "MetricExpr": "(hv_24x7@CPM_CS_32MHZ_CYC\\,domain\\=3\\,core\\=?@ )", + "MetricName": "CPM_CS_32MHZ_CYC", + "ScaleUnit": "1MHz", + "AggregationMode": "PerCore" }, { "MetricExpr" : "nest_mcs01_imc@PM_MCS01_128B_RD_DISP_PORT01@ + nest_mcs01_imc@PM_MCS01_128B_RD_DISP_PORT23@", "MetricName" : "mcs01-read", - "MetricGroup" : "memory_bw", + "MetricGroup" : "memory-bandwidth", "ScaleUnit": "6.1e-5MB" }, { "MetricExpr" : "nest_mcs23_imc@PM_MCS23_128B_RD_DISP_PORT01@ + nest_mcs23_imc@PM_MCS23_128B_RD_DISP_PORT23@", "MetricName" : "mcs23-read", - "MetricGroup" : "memory_bw", + "MetricGroup" : "memory-bandwidth", "ScaleUnit": "6.1e-5MB" }, { "MetricExpr" : "nest_mcs01_imc@PM_MCS01_128B_WR_DISP_PORT01@ + nest_mcs01_imc@PM_MCS01_128B_WR_DISP_PORT23@", "MetricName" : "mcs01-write", - "MetricGroup" : "memory_bw", + "MetricGroup" : "memory-bandwidth", "ScaleUnit": "6.1e-5MB" }, { @@ -48,7 +57,7 @@ { "MetricExpr" : "(nest_mcs01_imc@PM_MCS01_128B_RD_DISP_PORT01@ + nest_mcs01_imc@PM_MCS01_128B_RD_DISP_PORT23@ + nest_mcs23_imc@PM_MCS23_128B_RD_DISP_PORT01@ + nest_mcs23_imc@PM_MCS23_128B_RD_DISP_PORT23@ + nest_mcs01_imc@PM_MCS01_128B_WR_DISP_PORT01@ + nest_mcs01_imc@PM_MCS01_128B_WR_DISP_PORT23@ + nest_mcs23_imc@PM_MCS23_128B_WR_DISP_PORT01@ + nest_mcs23_imc@PM_MCS23_128B_WR_DISP_PORT23@)", "MetricName" : "Memory-bandwidth-MCS", - "MetricGroup" : "memory_bw", + "MetricGroup" : "memory-bandwidth", "ScaleUnit": "6.1e-5MB" } ] diff --git a/tools/perf/pmu-events/arch/x86/amdzen1/branch.json b/tools/perf/pmu-events/arch/x86/amdzen1/branch.json index a9943eeb8d6b..4ceb67a0db21 100644 --- a/tools/perf/pmu-events/arch/x86/amdzen1/branch.json +++ b/tools/perf/pmu-events/arch/x86/amdzen1/branch.json @@ -19,5 +19,10 @@ "EventName": "bp_de_redirect", "EventCode": "0x91", "BriefDescription": "Decoder Overrides Existing Branch Prediction (speculative)." + }, + { + "EventName": "bp_l1_tlb_fetch_hit", + "EventCode": "0x94", + "BriefDescription": "The number of instruction fetches that hit in the L1 ITLB." } ] diff --git a/tools/perf/pmu-events/arch/x86/amdzen1/cache.json b/tools/perf/pmu-events/arch/x86/amdzen1/cache.json index 404d4c569c01..4ea7ec4f496e 100644 --- a/tools/perf/pmu-events/arch/x86/amdzen1/cache.json +++ b/tools/perf/pmu-events/arch/x86/amdzen1/cache.json @@ -118,6 +118,11 @@ "UMask": "0x1" }, { + "EventName": "l2_request_g1.all_no_prefetch", + "EventCode": "0x60", + "UMask": "0xf9" + }, + { "EventName": "l2_request_g2.group1", "EventCode": "0x61", "BriefDescription": "Miscellaneous events covered in more detail by l2_request_g1 (PMCx060).", @@ -244,12 +249,48 @@ "UMask": "0x1" }, { + "EventName": "l2_cache_req_stat.ic_access_in_l2", + "EventCode": "0x64", + "BriefDescription": "Core to L2 cacheable request access status (not including L2 Prefetch). Instruction cache requests in L2.", + "UMask": "0x7" + }, + { + "EventName": "l2_cache_req_stat.ic_dc_miss_in_l2", + "EventCode": "0x64", + "BriefDescription": "Core to L2 cacheable request access status (not including L2 Prefetch). Instruction cache request miss in L2 and Data cache request miss in L2 (all types).", + "UMask": "0x9" + }, + { + "EventName": "l2_cache_req_stat.ic_dc_hit_in_l2", + "EventCode": "0x64", + "BriefDescription": "Core to L2 cacheable request access status (not including L2 Prefetch). Instruction cache request hit in L2 and Data cache request hit in L2 (all types).", + "UMask": "0xf6" + }, + { "EventName": "l2_fill_pending.l2_fill_busy", "EventCode": "0x6d", "BriefDescription": "Cycles with fill pending from L2. Total cycles spent with one or more fill requests in flight from L2.", "UMask": "0x1" }, { + "EventName": "l2_pf_hit_l2", + "EventCode": "0x70", + "BriefDescription": "L2 prefetch hit in L2.", + "UMask": "0xff" + }, + { + "EventName": "l2_pf_miss_l2_hit_l3", + "EventCode": "0x71", + "BriefDescription": "L2 prefetcher hits in L3. Counts all L2 prefetches accepted by the L2 pipeline which miss the L2 cache and hit the L3.", + "UMask": "0xff" + }, + { + "EventName": "l2_pf_miss_l2_l3", + "EventCode": "0x72", + "BriefDescription": "L2 prefetcher misses in L3. All L2 prefetches accepted by the L2 pipeline which miss the L2 and the L3 caches.", + "UMask": "0xff" + }, + { "EventName": "l3_request_g1.caching_l3_cache_accesses", "EventCode": "0x01", "BriefDescription": "Caching: L3 cache accesses", diff --git a/tools/perf/pmu-events/arch/x86/amdzen1/data-fabric.json b/tools/perf/pmu-events/arch/x86/amdzen1/data-fabric.json new file mode 100644 index 000000000000..40271df40015 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/amdzen1/data-fabric.json @@ -0,0 +1,98 @@ +[ + { + "EventName": "remote_outbound_data_controller_0", + "PublicDescription": "Remote Link Controller Outbound Packet Types: Data (32B): Remote Link Controller 0", + "EventCode": "0x7c7", + "UMask": "0x02", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "remote_outbound_data_controller_1", + "PublicDescription": "Remote Link Controller Outbound Packet Types: Data (32B): Remote Link Controller 1", + "EventCode": "0x807", + "UMask": "0x02", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "remote_outbound_data_controller_2", + "PublicDescription": "Remote Link Controller Outbound Packet Types: Data (32B): Remote Link Controller 2", + "EventCode": "0x847", + "UMask": "0x02", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "remote_outbound_data_controller_3", + "PublicDescription": "Remote Link Controller Outbound Packet Types: Data (32B): Remote Link Controller 3", + "EventCode": "0x887", + "UMask": "0x02", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "dram_channel_data_controller_0", + "PublicDescription": "DRAM Channel Controller Request Types: Requests with Data (64B): DRAM Channel Controller 0", + "EventCode": "0x07", + "UMask": "0x38", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "dram_channel_data_controller_1", + "PublicDescription": "DRAM Channel Controller Request Types: Requests with Data (64B): DRAM Channel Controller 0", + "EventCode": "0x47", + "UMask": "0x38", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "dram_channel_data_controller_2", + "PublicDescription": "DRAM Channel Controller Request Types: Requests with Data (64B): DRAM Channel Controller 0", + "EventCode": "0x87", + "UMask": "0x38", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "dram_channel_data_controller_3", + "PublicDescription": "DRAM Channel Controller Request Types: Requests with Data (64B): DRAM Channel Controller 0", + "EventCode": "0xc7", + "UMask": "0x38", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "dram_channel_data_controller_4", + "PublicDescription": "DRAM Channel Controller Request Types: Requests with Data (64B): DRAM Channel Controller 0", + "EventCode": "0x107", + "UMask": "0x38", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "dram_channel_data_controller_5", + "PublicDescription": "DRAM Channel Controller Request Types: Requests with Data (64B): DRAM Channel Controller 0", + "EventCode": "0x147", + "UMask": "0x38", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "dram_channel_data_controller_6", + "PublicDescription": "DRAM Channel Controller Request Types: Requests with Data (64B): DRAM Channel Controller 0", + "EventCode": "0x187", + "UMask": "0x38", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "dram_channel_data_controller_7", + "PublicDescription": "DRAM Channel Controller Request Types: Requests with Data (64B): DRAM Channel Controller 0", + "EventCode": "0x1c7", + "UMask": "0x38", + "PerPkg": "1", + "Unit": "DFPMC" + } +] diff --git a/tools/perf/pmu-events/arch/x86/amdzen1/recommended.json b/tools/perf/pmu-events/arch/x86/amdzen1/recommended.json new file mode 100644 index 000000000000..2cfe2d2f3bfd --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/amdzen1/recommended.json @@ -0,0 +1,178 @@ +[ + { + "MetricName": "branch_misprediction_ratio", + "BriefDescription": "Execution-Time Branch Misprediction Ratio (Non-Speculative)", + "MetricExpr": "d_ratio(ex_ret_brn_misp, ex_ret_brn)", + "MetricGroup": "branch_prediction", + "ScaleUnit": "100%" + }, + { + "EventName": "all_dc_accesses", + "EventCode": "0x29", + "BriefDescription": "All L1 Data Cache Accesses", + "UMask": "0x7" + }, + { + "MetricName": "all_l2_cache_accesses", + "BriefDescription": "All L2 Cache Accesses", + "MetricExpr": "l2_request_g1.all_no_prefetch + l2_pf_hit_l2 + l2_pf_miss_l2_hit_l3 + l2_pf_miss_l2_l3", + "MetricGroup": "l2_cache" + }, + { + "EventName": "l2_cache_accesses_from_ic_misses", + "EventCode": "0x60", + "BriefDescription": "L2 Cache Accesses from L1 Instruction Cache Misses (including prefetch)", + "UMask": "0x10" + }, + { + "EventName": "l2_cache_accesses_from_dc_misses", + "EventCode": "0x60", + "BriefDescription": "L2 Cache Accesses from L1 Data Cache Misses (including prefetch)", + "UMask": "0xc8" + }, + { + "MetricName": "l2_cache_accesses_from_l2_hwpf", + "BriefDescription": "L2 Cache Accesses from L2 HWPF", + "MetricExpr": "l2_pf_hit_l2 + l2_pf_miss_l2_hit_l3 + l2_pf_miss_l2_l3", + "MetricGroup": "l2_cache" + }, + { + "MetricName": "all_l2_cache_misses", + "BriefDescription": "All L2 Cache Misses", + "MetricExpr": "l2_cache_req_stat.ic_dc_miss_in_l2 + l2_pf_miss_l2_hit_l3 + l2_pf_miss_l2_l3", + "MetricGroup": "l2_cache" + }, + { + "EventName": "l2_cache_misses_from_ic_miss", + "EventCode": "0x64", + "BriefDescription": "L2 Cache Misses from L1 Instruction Cache Misses", + "UMask": "0x01" + }, + { + "EventName": "l2_cache_misses_from_dc_misses", + "EventCode": "0x64", + "BriefDescription": "L2 Cache Misses from L1 Data Cache Misses", + "UMask": "0x08" + }, + { + "MetricName": "l2_cache_misses_from_l2_hwpf", + "BriefDescription": "L2 Cache Misses from L2 HWPF", + "MetricExpr": "l2_pf_miss_l2_hit_l3 + l2_pf_miss_l2_l3", + "MetricGroup": "l2_cache" + }, + { + "MetricName": "all_l2_cache_hits", + "BriefDescription": "All L2 Cache Hits", + "MetricExpr": "l2_cache_req_stat.ic_dc_hit_in_l2 + l2_pf_hit_l2", + "MetricGroup": "l2_cache" + }, + { + "EventName": "l2_cache_hits_from_ic_misses", + "EventCode": "0x64", + "BriefDescription": "L2 Cache Hits from L1 Instruction Cache Misses", + "UMask": "0x06" + }, + { + "EventName": "l2_cache_hits_from_dc_misses", + "EventCode": "0x64", + "BriefDescription": "L2 Cache Hits from L1 Data Cache Misses", + "UMask": "0x70" + }, + { + "MetricName": "l2_cache_hits_from_l2_hwpf", + "BriefDescription": "L2 Cache Hits from L2 HWPF", + "MetricExpr": "l2_pf_hit_l2 + l2_pf_miss_l2_hit_l3 + l2_pf_miss_l2_l3", + "MetricGroup": "l2_cache" + }, + { + "EventName": "l3_accesses", + "EventCode": "0x04", + "BriefDescription": "L3 Accesses", + "UMask": "0xff", + "Unit": "L3PMC" + }, + { + "EventName": "l3_misses", + "EventCode": "0x04", + "BriefDescription": "L3 Misses (includes Chg2X)", + "UMask": "0x01", + "Unit": "L3PMC" + }, + { + "MetricName": "l3_read_miss_latency", + "BriefDescription": "Average L3 Read Miss Latency (in core clocks)", + "MetricExpr": "(xi_sys_fill_latency * 16) / xi_ccx_sdp_req1.all_l3_miss_req_typs", + "MetricGroup": "l3_cache", + "ScaleUnit": "1core clocks" + }, + { + "MetricName": "ic_fetch_miss_ratio", + "BriefDescription": "L1 Instruction Cache (32B) Fetch Miss Ratio", + "MetricExpr": "d_ratio(l2_cache_req_stat.ic_access_in_l2, bp_l1_tlb_fetch_hit + bp_l1_tlb_miss_l2_hit + bp_l1_tlb_miss_l2_miss)", + "MetricGroup": "l2_cache", + "ScaleUnit": "100%" + }, + { + "MetricName": "l1_itlb_misses", + "BriefDescription": "L1 ITLB Misses", + "MetricExpr": "bp_l1_tlb_miss_l2_hit + bp_l1_tlb_miss_l2_miss", + "MetricGroup": "tlb" + }, + { + "EventName": "l2_itlb_misses", + "EventCode": "0x85", + "BriefDescription": "L2 ITLB Misses & Instruction page walks", + "UMask": "0x07" + }, + { + "EventName": "l1_dtlb_misses", + "EventCode": "0x45", + "BriefDescription": "L1 DTLB Misses", + "UMask": "0xff" + }, + { + "EventName": "l2_dtlb_misses", + "EventCode": "0x45", + "BriefDescription": "L2 DTLB Misses & Data page walks", + "UMask": "0xf0" + }, + { + "EventName": "all_tlbs_flushed", + "EventCode": "0x78", + "BriefDescription": "All TLBs Flushed", + "UMask": "0xdf" + }, + { + "EventName": "uops_dispatched", + "EventCode": "0xaa", + "BriefDescription": "Micro-ops Dispatched", + "UMask": "0x03" + }, + { + "EventName": "sse_avx_stalls", + "EventCode": "0x0e", + "BriefDescription": "Mixed SSE/AVX Stalls", + "UMask": "0x0e" + }, + { + "EventName": "uops_retired", + "EventCode": "0xc1", + "BriefDescription": "Micro-ops Retired" + }, + { + "MetricName": "all_remote_links_outbound", + "BriefDescription": "Approximate: Outbound data bytes for all Remote Links for a node (die)", + "MetricExpr": "remote_outbound_data_controller_0 + remote_outbound_data_controller_1 + remote_outbound_data_controller_2 + remote_outbound_data_controller_3", + "MetricGroup": "data_fabric", + "PerPkg": "1", + "ScaleUnit": "3e-5MiB" + }, + { + "MetricName": "nps1_die_to_dram", + "BriefDescription": "Approximate: Combined DRAM B/bytes of all channels on a NPS1 node (die) (may need --metric-no-group)", + "MetricExpr": "dram_channel_data_controller_0 + dram_channel_data_controller_1 + dram_channel_data_controller_2 + dram_channel_data_controller_3 + dram_channel_data_controller_4 + dram_channel_data_controller_5 + dram_channel_data_controller_6 + dram_channel_data_controller_7", + "MetricGroup": "data_fabric", + "PerPkg": "1", + "ScaleUnit": "6.1e-5MiB" + } +] diff --git a/tools/perf/pmu-events/arch/x86/amdzen2/cache.json b/tools/perf/pmu-events/arch/x86/amdzen2/cache.json index 1c60bfa0f00b..f61b982f83ca 100644 --- a/tools/perf/pmu-events/arch/x86/amdzen2/cache.json +++ b/tools/perf/pmu-events/arch/x86/amdzen2/cache.json @@ -48,6 +48,11 @@ "UMask": "0x1" }, { + "EventName": "l2_request_g1.all_no_prefetch", + "EventCode": "0x60", + "UMask": "0xf9" + }, + { "EventName": "l2_request_g2.group1", "EventCode": "0x61", "BriefDescription": "Miscellaneous events covered in more detail by l2_request_g1 (PMCx060).", @@ -174,6 +179,24 @@ "UMask": "0x1" }, { + "EventName": "l2_cache_req_stat.ic_access_in_l2", + "EventCode": "0x64", + "BriefDescription": "Core to L2 cacheable request access status (not including L2 Prefetch). Instruction cache requests in L2.", + "UMask": "0x7" + }, + { + "EventName": "l2_cache_req_stat.ic_dc_miss_in_l2", + "EventCode": "0x64", + "BriefDescription": "Core to L2 cacheable request access status (not including L2 Prefetch). Instruction cache request miss in L2 and Data cache request miss in L2 (all types).", + "UMask": "0x9" + }, + { + "EventName": "l2_cache_req_stat.ic_dc_hit_in_l2", + "EventCode": "0x64", + "BriefDescription": "Core to L2 cacheable request access status (not including L2 Prefetch). Instruction cache request hit in L2 and Data cache request hit in L2 (all types).", + "UMask": "0xf6" + }, + { "EventName": "l2_fill_pending.l2_fill_busy", "EventCode": "0x6d", "BriefDescription": "Cycles with fill pending from L2. Total cycles spent with one or more fill requests in flight from L2.", diff --git a/tools/perf/pmu-events/arch/x86/amdzen2/data-fabric.json b/tools/perf/pmu-events/arch/x86/amdzen2/data-fabric.json new file mode 100644 index 000000000000..40271df40015 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/amdzen2/data-fabric.json @@ -0,0 +1,98 @@ +[ + { + "EventName": "remote_outbound_data_controller_0", + "PublicDescription": "Remote Link Controller Outbound Packet Types: Data (32B): Remote Link Controller 0", + "EventCode": "0x7c7", + "UMask": "0x02", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "remote_outbound_data_controller_1", + "PublicDescription": "Remote Link Controller Outbound Packet Types: Data (32B): Remote Link Controller 1", + "EventCode": "0x807", + "UMask": "0x02", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "remote_outbound_data_controller_2", + "PublicDescription": "Remote Link Controller Outbound Packet Types: Data (32B): Remote Link Controller 2", + "EventCode": "0x847", + "UMask": "0x02", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "remote_outbound_data_controller_3", + "PublicDescription": "Remote Link Controller Outbound Packet Types: Data (32B): Remote Link Controller 3", + "EventCode": "0x887", + "UMask": "0x02", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "dram_channel_data_controller_0", + "PublicDescription": "DRAM Channel Controller Request Types: Requests with Data (64B): DRAM Channel Controller 0", + "EventCode": "0x07", + "UMask": "0x38", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "dram_channel_data_controller_1", + "PublicDescription": "DRAM Channel Controller Request Types: Requests with Data (64B): DRAM Channel Controller 0", + "EventCode": "0x47", + "UMask": "0x38", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "dram_channel_data_controller_2", + "PublicDescription": "DRAM Channel Controller Request Types: Requests with Data (64B): DRAM Channel Controller 0", + "EventCode": "0x87", + "UMask": "0x38", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "dram_channel_data_controller_3", + "PublicDescription": "DRAM Channel Controller Request Types: Requests with Data (64B): DRAM Channel Controller 0", + "EventCode": "0xc7", + "UMask": "0x38", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "dram_channel_data_controller_4", + "PublicDescription": "DRAM Channel Controller Request Types: Requests with Data (64B): DRAM Channel Controller 0", + "EventCode": "0x107", + "UMask": "0x38", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "dram_channel_data_controller_5", + "PublicDescription": "DRAM Channel Controller Request Types: Requests with Data (64B): DRAM Channel Controller 0", + "EventCode": "0x147", + "UMask": "0x38", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "dram_channel_data_controller_6", + "PublicDescription": "DRAM Channel Controller Request Types: Requests with Data (64B): DRAM Channel Controller 0", + "EventCode": "0x187", + "UMask": "0x38", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "dram_channel_data_controller_7", + "PublicDescription": "DRAM Channel Controller Request Types: Requests with Data (64B): DRAM Channel Controller 0", + "EventCode": "0x1c7", + "UMask": "0x38", + "PerPkg": "1", + "Unit": "DFPMC" + } +] diff --git a/tools/perf/pmu-events/arch/x86/amdzen2/recommended.json b/tools/perf/pmu-events/arch/x86/amdzen2/recommended.json new file mode 100644 index 000000000000..2ef91e25e661 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/amdzen2/recommended.json @@ -0,0 +1,178 @@ +[ + { + "MetricName": "branch_misprediction_ratio", + "BriefDescription": "Execution-Time Branch Misprediction Ratio (Non-Speculative)", + "MetricExpr": "d_ratio(ex_ret_brn_misp, ex_ret_brn)", + "MetricGroup": "branch_prediction", + "ScaleUnit": "100%" + }, + { + "EventName": "all_dc_accesses", + "EventCode": "0x29", + "BriefDescription": "All L1 Data Cache Accesses", + "UMask": "0x7" + }, + { + "MetricName": "all_l2_cache_accesses", + "BriefDescription": "All L2 Cache Accesses", + "MetricExpr": "l2_request_g1.all_no_prefetch + l2_pf_hit_l2 + l2_pf_miss_l2_hit_l3 + l2_pf_miss_l2_l3", + "MetricGroup": "l2_cache" + }, + { + "EventName": "l2_cache_accesses_from_ic_misses", + "EventCode": "0x60", + "BriefDescription": "L2 Cache Accesses from L1 Instruction Cache Misses (including prefetch)", + "UMask": "0x10" + }, + { + "EventName": "l2_cache_accesses_from_dc_misses", + "EventCode": "0x60", + "BriefDescription": "L2 Cache Accesses from L1 Data Cache Misses (including prefetch)", + "UMask": "0xc8" + }, + { + "MetricName": "l2_cache_accesses_from_l2_hwpf", + "BriefDescription": "L2 Cache Accesses from L2 HWPF", + "MetricExpr": "l2_pf_hit_l2 + l2_pf_miss_l2_hit_l3 + l2_pf_miss_l2_l3", + "MetricGroup": "l2_cache" + }, + { + "MetricName": "all_l2_cache_misses", + "BriefDescription": "All L2 Cache Misses", + "MetricExpr": "l2_cache_req_stat.ic_dc_miss_in_l2 + l2_pf_miss_l2_hit_l3 + l2_pf_miss_l2_l3", + "MetricGroup": "l2_cache" + }, + { + "EventName": "l2_cache_misses_from_ic_miss", + "EventCode": "0x64", + "BriefDescription": "L2 Cache Misses from L1 Instruction Cache Misses", + "UMask": "0x01" + }, + { + "EventName": "l2_cache_misses_from_dc_misses", + "EventCode": "0x64", + "BriefDescription": "L2 Cache Misses from L1 Data Cache Misses", + "UMask": "0x08" + }, + { + "MetricName": "l2_cache_misses_from_l2_hwpf", + "BriefDescription": "L2 Cache Misses from L2 HWPF", + "MetricExpr": "l2_pf_miss_l2_hit_l3 + l2_pf_miss_l2_l3", + "MetricGroup": "l2_cache" + }, + { + "MetricName": "all_l2_cache_hits", + "BriefDescription": "All L2 Cache Hits", + "MetricExpr": "l2_cache_req_stat.ic_dc_hit_in_l2 + l2_pf_hit_l2", + "MetricGroup": "l2_cache" + }, + { + "EventName": "l2_cache_hits_from_ic_misses", + "EventCode": "0x64", + "BriefDescription": "L2 Cache Hits from L1 Instruction Cache Misses", + "UMask": "0x06" + }, + { + "EventName": "l2_cache_hits_from_dc_misses", + "EventCode": "0x64", + "BriefDescription": "L2 Cache Hits from L1 Data Cache Misses", + "UMask": "0x70" + }, + { + "MetricName": "l2_cache_hits_from_l2_hwpf", + "BriefDescription": "L2 Cache Hits from L2 HWPF", + "MetricExpr": "l2_pf_hit_l2 + l2_pf_miss_l2_hit_l3 + l2_pf_miss_l2_l3", + "MetricGroup": "l2_cache" + }, + { + "EventName": "l3_accesses", + "EventCode": "0x04", + "BriefDescription": "L3 Accesses", + "UMask": "0xff", + "Unit": "L3PMC" + }, + { + "EventName": "l3_misses", + "EventCode": "0x04", + "BriefDescription": "L3 Misses (includes Chg2X)", + "UMask": "0x01", + "Unit": "L3PMC" + }, + { + "MetricName": "l3_read_miss_latency", + "BriefDescription": "Average L3 Read Miss Latency (in core clocks)", + "MetricExpr": "(xi_sys_fill_latency * 16) / xi_ccx_sdp_req1.all_l3_miss_req_typs", + "MetricGroup": "l3_cache", + "ScaleUnit": "1core clocks" + }, + { + "MetricName": "ic_fetch_miss_ratio", + "BriefDescription": "L1 Instruction Cache (32B) Fetch Miss Ratio", + "MetricExpr": "d_ratio(l2_cache_req_stat.ic_access_in_l2, bp_l1_tlb_fetch_hit + bp_l1_tlb_miss_l2_hit + bp_l1_tlb_miss_l2_tlb_miss)", + "MetricGroup": "l2_cache", + "ScaleUnit": "100%" + }, + { + "MetricName": "l1_itlb_misses", + "BriefDescription": "L1 ITLB Misses", + "MetricExpr": "bp_l1_tlb_miss_l2_hit + bp_l1_tlb_miss_l2_tlb_miss", + "MetricGroup": "tlb" + }, + { + "EventName": "l2_itlb_misses", + "EventCode": "0x85", + "BriefDescription": "L2 ITLB Misses & Instruction page walks", + "UMask": "0x07" + }, + { + "EventName": "l1_dtlb_misses", + "EventCode": "0x45", + "BriefDescription": "L1 DTLB Misses", + "UMask": "0xff" + }, + { + "EventName": "l2_dtlb_misses", + "EventCode": "0x45", + "BriefDescription": "L2 DTLB Misses & Data page walks", + "UMask": "0xf0" + }, + { + "EventName": "all_tlbs_flushed", + "EventCode": "0x78", + "BriefDescription": "All TLBs Flushed", + "UMask": "0xdf" + }, + { + "EventName": "uops_dispatched", + "EventCode": "0xaa", + "BriefDescription": "Micro-ops Dispatched", + "UMask": "0x03" + }, + { + "EventName": "sse_avx_stalls", + "EventCode": "0x0e", + "BriefDescription": "Mixed SSE/AVX Stalls", + "UMask": "0x0e" + }, + { + "EventName": "uops_retired", + "EventCode": "0xc1", + "BriefDescription": "Micro-ops Retired" + }, + { + "MetricName": "all_remote_links_outbound", + "BriefDescription": "Approximate: Outbound data bytes for all Remote Links for a node (die)", + "MetricExpr": "remote_outbound_data_controller_0 + remote_outbound_data_controller_1 + remote_outbound_data_controller_2 + remote_outbound_data_controller_3", + "MetricGroup": "data_fabric", + "PerPkg": "1", + "ScaleUnit": "3e-5MiB" + }, + { + "MetricName": "nps1_die_to_dram", + "BriefDescription": "Approximate: Combined DRAM B/bytes of all channels on a NPS1 node (die) (may need --metric-no-group)", + "MetricExpr": "dram_channel_data_controller_0 + dram_channel_data_controller_1 + dram_channel_data_controller_2 + dram_channel_data_controller_3 + dram_channel_data_controller_4 + dram_channel_data_controller_5 + dram_channel_data_controller_6 + dram_channel_data_controller_7", + "MetricGroup": "data_fabric", + "PerPkg": "1", + "ScaleUnit": "6.1e-5MiB" + } +] diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv index 25b06cf98747..2f2a209e87e1 100644 --- a/tools/perf/pmu-events/arch/x86/mapfile.csv +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv @@ -38,3 +38,4 @@ GenuineIntel-6-7E,v1,icelake,core GenuineIntel-6-86,v1,tremontx,core AuthenticAMD-23-([12][0-9A-F]|[0-9A-F]),v2,amdzen1,core AuthenticAMD-23-[[:xdigit:]]+,v1,amdzen2,core +AuthenticAMD-25-[[:xdigit:]]+,v1,amdzen2,core diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c index fc9c158bfa13..99df41a9543d 100644 --- a/tools/perf/pmu-events/jevents.c +++ b/tools/perf/pmu-events/jevents.c @@ -48,11 +48,40 @@ #include <linux/list.h> #include "jsmn.h" #include "json.h" -#include "jevents.h" +#include "pmu-events.h" int verbose; char *prog; +struct json_event { + char *name; + char *event; + char *desc; + char *long_desc; + char *pmu; + char *unit; + char *perpkg; + char *aggr_mode; + char *metric_expr; + char *metric_name; + char *metric_group; + char *deprecated; + char *metric_constraint; +}; + +enum aggr_mode_class convert(const char *aggr_mode) +{ + if (!strcmp(aggr_mode, "PerCore")) + return PerCore; + else if (!strcmp(aggr_mode, "PerChip")) + return PerChip; + + pr_err("%s: Wrong AggregationMode value '%s'\n", prog, aggr_mode); + return -1; +} + +typedef int (*func)(void *data, struct json_event *je); + int eprintf(int level, int var, const char *fmt, ...) { @@ -71,11 +100,6 @@ int eprintf(int level, int var, const char *fmt, ...) return ret; } -__attribute__((weak)) char *get_cpu_str(void) -{ - return NULL; -} - static void addfield(char *map, char **dst, const char *sep, const char *a, jsmntok_t *bt) { @@ -240,6 +264,7 @@ static struct map { { "hisi_sccl,hha", "hisi_sccl,hha" }, { "hisi_sccl,l3c", "hisi_sccl,l3c" }, { "L3PMC", "amd_l3" }, + { "DFPMC", "amd_df" }, {} }; @@ -318,12 +343,7 @@ static void print_events_table_prefix(FILE *fp, const char *tblname) close_table = 1; } -static int print_events_table_entry(void *data, char *name, char *event, - char *desc, char *long_desc, - char *pmu, char *unit, char *perpkg, - char *metric_expr, - char *metric_name, char *metric_group, - char *deprecated, char *metric_constraint) +static int print_events_table_entry(void *data, struct json_event *je) { struct perf_entry_data *pd = data; FILE *outfp = pd->outfp; @@ -335,30 +355,32 @@ static int print_events_table_entry(void *data, char *name, char *event, */ fprintf(outfp, "{\n"); - if (name) - fprintf(outfp, "\t.name = \"%s\",\n", name); - if (event) - fprintf(outfp, "\t.event = \"%s\",\n", event); - fprintf(outfp, "\t.desc = \"%s\",\n", desc); + if (je->name) + fprintf(outfp, "\t.name = \"%s\",\n", je->name); + if (je->event) + fprintf(outfp, "\t.event = \"%s\",\n", je->event); + fprintf(outfp, "\t.desc = \"%s\",\n", je->desc); fprintf(outfp, "\t.topic = \"%s\",\n", topic); - if (long_desc && long_desc[0]) - fprintf(outfp, "\t.long_desc = \"%s\",\n", long_desc); - if (pmu) - fprintf(outfp, "\t.pmu = \"%s\",\n", pmu); - if (unit) - fprintf(outfp, "\t.unit = \"%s\",\n", unit); - if (perpkg) - fprintf(outfp, "\t.perpkg = \"%s\",\n", perpkg); - if (metric_expr) - fprintf(outfp, "\t.metric_expr = \"%s\",\n", metric_expr); - if (metric_name) - fprintf(outfp, "\t.metric_name = \"%s\",\n", metric_name); - if (metric_group) - fprintf(outfp, "\t.metric_group = \"%s\",\n", metric_group); - if (deprecated) - fprintf(outfp, "\t.deprecated = \"%s\",\n", deprecated); - if (metric_constraint) - fprintf(outfp, "\t.metric_constraint = \"%s\",\n", metric_constraint); + if (je->long_desc && je->long_desc[0]) + fprintf(outfp, "\t.long_desc = \"%s\",\n", je->long_desc); + if (je->pmu) + fprintf(outfp, "\t.pmu = \"%s\",\n", je->pmu); + if (je->unit) + fprintf(outfp, "\t.unit = \"%s\",\n", je->unit); + if (je->perpkg) + fprintf(outfp, "\t.perpkg = \"%s\",\n", je->perpkg); + if (je->aggr_mode) + fprintf(outfp, "\t.aggr_mode = \"%d\",\n", convert(je->aggr_mode)); + if (je->metric_expr) + fprintf(outfp, "\t.metric_expr = \"%s\",\n", je->metric_expr); + if (je->metric_name) + fprintf(outfp, "\t.metric_name = \"%s\",\n", je->metric_name); + if (je->metric_group) + fprintf(outfp, "\t.metric_group = \"%s\",\n", je->metric_group); + if (je->deprecated) + fprintf(outfp, "\t.deprecated = \"%s\",\n", je->deprecated); + if (je->metric_constraint) + fprintf(outfp, "\t.metric_constraint = \"%s\",\n", je->metric_constraint); fprintf(outfp, "},\n"); return 0; @@ -373,6 +395,7 @@ struct event_struct { char *pmu; char *unit; char *perpkg; + char *aggr_mode; char *metric_expr; char *metric_name; char *metric_group; @@ -380,17 +403,17 @@ struct event_struct { char *metric_constraint; }; -#define ADD_EVENT_FIELD(field) do { if (field) { \ - es->field = strdup(field); \ +#define ADD_EVENT_FIELD(field) do { if (je->field) { \ + es->field = strdup(je->field); \ if (!es->field) \ goto out_free; \ } } while (0) #define FREE_EVENT_FIELD(field) free(es->field) -#define TRY_FIXUP_FIELD(field) do { if (es->field && !*field) {\ - *field = strdup(es->field); \ - if (!*field) \ +#define TRY_FIXUP_FIELD(field) do { if (es->field && !je->field) {\ + je->field = strdup(es->field); \ + if (!je->field) \ return -ENOMEM; \ } } while (0) @@ -402,6 +425,7 @@ struct event_struct { op(pmu); \ op(unit); \ op(perpkg); \ + op(aggr_mode); \ op(metric_expr); \ op(metric_name); \ op(metric_group); \ @@ -421,11 +445,7 @@ static void free_arch_std_events(void) } } -static int save_arch_std_events(void *data, char *name, char *event, - char *desc, char *long_desc, char *pmu, - char *unit, char *perpkg, char *metric_expr, - char *metric_name, char *metric_group, - char *deprecated, char *metric_constraint) +static int save_arch_std_events(void *data, struct json_event *je) { struct event_struct *es; @@ -485,11 +505,8 @@ static char *real_event(const char *name, char *event) } static int -try_fixup(const char *fn, char *arch_std, char **event, char **desc, - char **name, char **long_desc, char **pmu, char **filter, - char **perpkg, char **unit, char **metric_expr, char **metric_name, - char **metric_group, unsigned long long eventcode, - char **deprecated, char **metric_constraint) +try_fixup(const char *fn, char *arch_std, unsigned long long eventcode, + struct json_event *je) { /* try to find matching event from arch standard values */ struct event_struct *es; @@ -498,8 +515,8 @@ try_fixup(const char *fn, char *arch_std, char **event, char **desc, if (!strcmp(arch_std, es->name)) { if (!eventcode && es->event) { /* allow EventCode to be overridden */ - free(*event); - *event = NULL; + free(je->event); + je->event = NULL; } FOR_ALL_EVENT_STRUCT_FIELDS(TRY_FIXUP_FIELD); return 0; @@ -512,14 +529,9 @@ try_fixup(const char *fn, char *arch_std, char **event, char **desc, } /* Call func with each event in the json file */ -int json_events(const char *fn, - int (*func)(void *data, char *name, char *event, char *desc, - char *long_desc, - char *pmu, char *unit, char *perpkg, - char *metric_expr, - char *metric_name, char *metric_group, - char *deprecated, char *metric_constraint), - void *data) +static int json_events(const char *fn, + int (*func)(void *data, struct json_event *je), + void *data) { int err; size_t size; @@ -537,18 +549,10 @@ int json_events(const char *fn, EXPECT(tokens->type == JSMN_ARRAY, tokens, "expected top level array"); tok = tokens + 1; for (i = 0; i < tokens->size; i++) { - char *event = NULL, *desc = NULL, *name = NULL; - char *long_desc = NULL; + char *event = NULL; char *extra_desc = NULL; - char *pmu = NULL; char *filter = NULL; - char *perpkg = NULL; - char *unit = NULL; - char *metric_expr = NULL; - char *metric_name = NULL; - char *metric_group = NULL; - char *deprecated = NULL; - char *metric_constraint = NULL; + struct json_event je = {}; char *arch_std = NULL; unsigned long long eventcode = 0; struct msrmap *msr = NULL; @@ -583,14 +587,14 @@ int json_events(const char *fn, eventcode |= strtoul(code, NULL, 0) << 21; free(code); } else if (json_streq(map, field, "EventName")) { - addfield(map, &name, "", "", val); + addfield(map, &je.name, "", "", val); } else if (json_streq(map, field, "BriefDescription")) { - addfield(map, &desc, "", "", val); - fixdesc(desc); + addfield(map, &je.desc, "", "", val); + fixdesc(je.desc); } else if (json_streq(map, field, "PublicDescription")) { - addfield(map, &long_desc, "", "", val); - fixdesc(long_desc); + addfield(map, &je.long_desc, "", "", val); + fixdesc(je.long_desc); } else if (json_streq(map, field, "PEBS") && nz) { precise = val; } else if (json_streq(map, field, "MSRIndex") && nz) { @@ -610,34 +614,36 @@ int json_events(const char *fn, ppmu = field_to_perf(unit_to_pmu, map, val); if (ppmu) { - pmu = strdup(ppmu); + je.pmu = strdup(ppmu); } else { - if (!pmu) - pmu = strdup("uncore_"); - addfield(map, &pmu, "", "", val); - for (s = pmu; *s; s++) + if (!je.pmu) + je.pmu = strdup("uncore_"); + addfield(map, &je.pmu, "", "", val); + for (s = je.pmu; *s; s++) *s = tolower(*s); } - addfield(map, &desc, ". ", "Unit: ", NULL); - addfield(map, &desc, "", pmu, NULL); - addfield(map, &desc, "", " ", NULL); + addfield(map, &je.desc, ". ", "Unit: ", NULL); + addfield(map, &je.desc, "", je.pmu, NULL); + addfield(map, &je.desc, "", " ", NULL); } else if (json_streq(map, field, "Filter")) { addfield(map, &filter, "", "", val); } else if (json_streq(map, field, "ScaleUnit")) { - addfield(map, &unit, "", "", val); + addfield(map, &je.unit, "", "", val); } else if (json_streq(map, field, "PerPkg")) { - addfield(map, &perpkg, "", "", val); + addfield(map, &je.perpkg, "", "", val); + } else if (json_streq(map, field, "AggregationMode")) { + addfield(map, &je.aggr_mode, "", "", val); } else if (json_streq(map, field, "Deprecated")) { - addfield(map, &deprecated, "", "", val); + addfield(map, &je.deprecated, "", "", val); } else if (json_streq(map, field, "MetricName")) { - addfield(map, &metric_name, "", "", val); + addfield(map, &je.metric_name, "", "", val); } else if (json_streq(map, field, "MetricGroup")) { - addfield(map, &metric_group, "", "", val); + addfield(map, &je.metric_group, "", "", val); } else if (json_streq(map, field, "MetricConstraint")) { - addfield(map, &metric_constraint, "", "", val); + addfield(map, &je.metric_constraint, "", "", val); } else if (json_streq(map, field, "MetricExpr")) { - addfield(map, &metric_expr, "", "", val); - for (s = metric_expr; *s; s++) + addfield(map, &je.metric_expr, "", "", val); + for (s = je.metric_expr; *s; s++) *s = tolower(*s); } else if (json_streq(map, field, "ArchStdEvent")) { addfield(map, &arch_std, "", "", val); @@ -646,7 +652,7 @@ int json_events(const char *fn, } /* ignore unknown fields */ } - if (precise && desc && !strstr(desc, "(Precise Event)")) { + if (precise && je.desc && !strstr(je.desc, "(Precise Event)")) { if (json_streq(map, precise, "2")) addfield(map, &extra_desc, " ", "(Must be precise)", NULL); @@ -656,48 +662,44 @@ int json_events(const char *fn, } snprintf(buf, sizeof buf, "event=%#llx", eventcode); addfield(map, &event, ",", buf, NULL); - if (desc && extra_desc) - addfield(map, &desc, " ", extra_desc, NULL); - if (long_desc && extra_desc) - addfield(map, &long_desc, " ", extra_desc, NULL); + if (je.desc && extra_desc) + addfield(map, &je.desc, " ", extra_desc, NULL); + if (je.long_desc && extra_desc) + addfield(map, &je.long_desc, " ", extra_desc, NULL); if (filter) addfield(map, &event, ",", filter, NULL); if (msr != NULL) addfield(map, &event, ",", msr->pname, msrval); - if (name) - fixname(name); + if (je.name) + fixname(je.name); if (arch_std) { /* * An arch standard event is referenced, so try to * fixup any unassigned values. */ - err = try_fixup(fn, arch_std, &event, &desc, &name, - &long_desc, &pmu, &filter, &perpkg, - &unit, &metric_expr, &metric_name, - &metric_group, eventcode, - &deprecated, &metric_constraint); + err = try_fixup(fn, arch_std, eventcode, &je); if (err) goto free_strings; } - err = func(data, name, real_event(name, event), desc, long_desc, - pmu, unit, perpkg, metric_expr, metric_name, - metric_group, deprecated, metric_constraint); + je.event = real_event(je.name, event); + err = func(data, &je); free_strings: free(event); - free(desc); - free(name); - free(long_desc); + free(je.desc); + free(je.name); + free(je.long_desc); free(extra_desc); - free(pmu); + free(je.pmu); free(filter); - free(perpkg); - free(deprecated); - free(unit); - free(metric_expr); - free(metric_name); - free(metric_group); - free(metric_constraint); + free(je.perpkg); + free(je.aggr_mode); + free(je.deprecated); + free(je.unit); + free(je.metric_expr); + free(je.metric_name); + free(je.metric_group); + free(je.metric_constraint); free(arch_std); if (err) diff --git a/tools/perf/pmu-events/jevents.h b/tools/perf/pmu-events/jevents.h deleted file mode 100644 index 2afc8304529e..000000000000 --- a/tools/perf/pmu-events/jevents.h +++ /dev/null @@ -1,23 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef JEVENTS_H -#define JEVENTS_H 1 - -int json_events(const char *fn, - int (*func)(void *data, char *name, char *event, char *desc, - char *long_desc, - char *pmu, - char *unit, char *perpkg, char *metric_expr, - char *metric_name, char *metric_group, - char *deprecated, char *metric_constraint), - void *data); -char *get_cpu_str(void); - -#ifndef min -#define min(x, y) ({ \ - typeof(x) _min1 = (x); \ - typeof(y) _min2 = (y); \ - (void) (&_min1 == &_min2); \ - _min1 < _min2 ? _min1 : _min2; }) -#endif - -#endif diff --git a/tools/perf/pmu-events/pmu-events.h b/tools/perf/pmu-events/pmu-events.h index c8f306b572f4..7da1a3743b77 100644 --- a/tools/perf/pmu-events/pmu-events.h +++ b/tools/perf/pmu-events/pmu-events.h @@ -2,6 +2,11 @@ #ifndef PMU_EVENTS_H #define PMU_EVENTS_H +enum aggr_mode_class { + PerChip = 1, + PerCore +}; + /* * Describe each PMU event. Each CPU has a table of PMU events. */ @@ -14,6 +19,7 @@ struct pmu_event { const char *pmu; const char *unit; const char *perpkg; + const char *aggr_mode; const char *metric_expr; const char *metric_name; const char *metric_group; diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build index 84352fc49a20..69bea7996f18 100644 --- a/tools/perf/tests/Build +++ b/tools/perf/tests/Build @@ -60,6 +60,7 @@ perf-y += api-io.o perf-y += demangle-java-test.o perf-y += pfm.o perf-y += parse-metric.o +perf-y += pe-file-parsing.o $(OUTPUT)tests/llvm-src-base.c: tests/bpf-script-example.c tests/Build $(call rule_mkdir) diff --git a/tools/perf/tests/attr.c b/tools/perf/tests/attr.c index a9599ab8c471..ec972e0892ab 100644 --- a/tools/perf/tests/attr.c +++ b/tools/perf/tests/attr.c @@ -30,9 +30,9 @@ #include <sys/types.h> #include <sys/stat.h> #include <unistd.h> -#include "../perf-sys.h" #include <subcmd/exec-cmd.h> #include "event.h" +#include "util.h" #include "tests.h" #define ENV "PERF_TEST_ATTR" diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c index d328caaba45d..651b8ea3354a 100644 --- a/tools/perf/tests/builtin-test.c +++ b/tools/perf/tests/builtin-test.c @@ -342,6 +342,10 @@ static struct test generic_tests[] = { .func = test__parse_metric, }, { + .desc = "PE file support", + .func = test__pe_file_parsing, + }, + { .func = NULL, }, }; diff --git a/tools/perf/tests/make b/tools/perf/tests/make index 9b651dfe0a6b..a90fa043c066 100644 --- a/tools/perf/tests/make +++ b/tools/perf/tests/make @@ -91,6 +91,7 @@ make_no_sdt := NO_SDT=1 make_no_syscall_tbl := NO_SYSCALL_TABLE=1 make_with_clangllvm := LIBCLANGLLVM=1 make_with_libpfm4 := LIBPFM4=1 +make_with_gtk2 := GTK2=1 make_tags := tags make_cscope := cscope make_help := help @@ -154,6 +155,7 @@ run += make_no_syscall_tbl run += make_with_babeltrace run += make_with_clangllvm run += make_with_libpfm4 +run += make_with_gtk2 run += make_help run += make_doc run += make_perf_o diff --git a/tools/perf/tests/pe-file-parsing.c b/tools/perf/tests/pe-file-parsing.c new file mode 100644 index 000000000000..19eae3e8e229 --- /dev/null +++ b/tools/perf/tests/pe-file-parsing.c @@ -0,0 +1,98 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stdbool.h> +#include <inttypes.h> +#include <stdlib.h> +#include <string.h> +#include <linux/bitops.h> +#include <linux/kernel.h> +#include <linux/types.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <unistd.h> +#include <subcmd/exec-cmd.h> + +#include "debug.h" +#include "util/build-id.h" +#include "util/symbol.h" +#include "util/dso.h" + +#include "tests.h" + +#ifdef HAVE_LIBBFD_SUPPORT + +static int run_dir(const char *d) +{ + char filename[PATH_MAX]; + char debugfile[PATH_MAX]; + char build_id[BUILD_ID_SIZE]; + char debuglink[PATH_MAX]; + char expect_build_id[] = { + 0x5a, 0x0f, 0xd8, 0x82, 0xb5, 0x30, 0x84, 0x22, + 0x4b, 0xa4, 0x7b, 0x62, 0x4c, 0x55, 0xa4, 0x69, + }; + char expect_debuglink[PATH_MAX] = "pe-file.exe.debug"; + struct dso *dso; + struct symbol *sym; + int ret; + + scnprintf(filename, PATH_MAX, "%s/pe-file.exe", d); + ret = filename__read_build_id(filename, build_id, BUILD_ID_SIZE); + TEST_ASSERT_VAL("Failed to read build_id", + ret == sizeof(expect_build_id)); + TEST_ASSERT_VAL("Wrong build_id", !memcmp(build_id, expect_build_id, + sizeof(expect_build_id))); + + ret = filename__read_debuglink(filename, debuglink, PATH_MAX); + TEST_ASSERT_VAL("Failed to read debuglink", ret == 0); + TEST_ASSERT_VAL("Wrong debuglink", + !strcmp(debuglink, expect_debuglink)); + + scnprintf(debugfile, PATH_MAX, "%s/%s", d, debuglink); + ret = filename__read_build_id(debugfile, build_id, BUILD_ID_SIZE); + TEST_ASSERT_VAL("Failed to read debug file build_id", + ret == sizeof(expect_build_id)); + TEST_ASSERT_VAL("Wrong build_id", !memcmp(build_id, expect_build_id, + sizeof(expect_build_id))); + + dso = dso__new(filename); + TEST_ASSERT_VAL("Failed to get dso", dso); + + ret = dso__load_bfd_symbols(dso, debugfile); + TEST_ASSERT_VAL("Failed to load symbols", ret == 0); + + dso__sort_by_name(dso); + sym = dso__find_symbol_by_name(dso, "main"); + TEST_ASSERT_VAL("Failed to find main", sym); + dso__delete(dso); + + return TEST_OK; +} + +int test__pe_file_parsing(struct test *test __maybe_unused, + int subtest __maybe_unused) +{ + struct stat st; + char path_dir[PATH_MAX]; + + /* First try development tree tests. */ + if (!lstat("./tests", &st)) + return run_dir("./tests"); + + /* Then installed path. */ + snprintf(path_dir, PATH_MAX, "%s/tests", get_argv_exec_path()); + + if (!lstat(path_dir, &st)) + return run_dir(path_dir); + + return TEST_SKIP; +} + +#else + +int test__pe_file_parsing(struct test *test __maybe_unused, + int subtest __maybe_unused) +{ + return TEST_SKIP; +} + +#endif diff --git a/tools/perf/tests/pe-file.c b/tools/perf/tests/pe-file.c new file mode 100644 index 000000000000..eb3df5e9886f --- /dev/null +++ b/tools/perf/tests/pe-file.c @@ -0,0 +1,14 @@ +// SPDX-License-Identifier: GPL-2.0 + +// pe-file.exe and pe-file.exe.debug built with; +// x86_64-w64-mingw32-gcc -o pe-file.exe pe-file.c +// -Wl,--file-alignment,4096 -Wl,--build-id +// x86_64-w64-mingw32-objcopy --only-keep-debug +// --compress-debug-sections pe-file.exe pe-file.exe.debug +// x86_64-w64-mingw32-objcopy --strip-debug +// --add-gnu-debuglink=pe-file.exe.debug pe-file.exe + +int main(int argc, char const *argv[]) +{ + return 0; +} diff --git a/tools/perf/tests/pe-file.exe b/tools/perf/tests/pe-file.exe Binary files differnew file mode 100644 index 000000000000..838a46dae724 --- /dev/null +++ b/tools/perf/tests/pe-file.exe diff --git a/tools/perf/tests/pe-file.exe.debug b/tools/perf/tests/pe-file.exe.debug Binary files differnew file mode 100644 index 000000000000..287d6718d6c9 --- /dev/null +++ b/tools/perf/tests/pe-file.exe.debug diff --git a/tools/perf/tests/shell/test_arm_coresight.sh b/tools/perf/tests/shell/test_arm_coresight.sh new file mode 100755 index 000000000000..8d84fdbed6a6 --- /dev/null +++ b/tools/perf/tests/shell/test_arm_coresight.sh @@ -0,0 +1,183 @@ +#!/bin/sh +# Check Arm CoreSight trace data recording and synthesized samples + +# Uses the 'perf record' to record trace data with Arm CoreSight sinks; +# then verify if there have any branch samples and instruction samples +# are generated by CoreSight with 'perf script' and 'perf report' +# commands. + +# SPDX-License-Identifier: GPL-2.0 +# Leo Yan <[email protected]>, 2020 + +perfdata=$(mktemp /tmp/__perf_test.perf.data.XXXXX) +file=$(mktemp /tmp/temporary_file.XXXXX) + +skip_if_no_cs_etm_event() { + perf list | grep -q 'cs_etm//' && return 0 + + # cs_etm event doesn't exist + return 2 +} + +skip_if_no_cs_etm_event || exit 2 + +cleanup_files() +{ + rm -f ${perfdata} + rm -f ${file} +} + +trap cleanup_files exit + +record_touch_file() { + echo "Recording trace (only user mode) with path: CPU$2 => $1" + rm -f $file + perf record -o ${perfdata} -e cs_etm/@$1/u --per-thread \ + -- taskset -c $2 touch $file +} + +perf_script_branch_samples() { + echo "Looking at perf.data file for dumping branch samples:" + + # Below is an example of the branch samples dumping: + # touch 6512 1 branches:u: ffffb220824c strcmp+0xc (/lib/aarch64-linux-gnu/ld-2.27.so) + # touch 6512 1 branches:u: ffffb22082e0 strcmp+0xa0 (/lib/aarch64-linux-gnu/ld-2.27.so) + # touch 6512 1 branches:u: ffffb2208320 strcmp+0xe0 (/lib/aarch64-linux-gnu/ld-2.27.so) + perf script -F,-time -i ${perfdata} | \ + egrep " +$1 +[0-9]+ .* +branches:([u|k]:)? +" +} + +perf_report_branch_samples() { + echo "Looking at perf.data file for reporting branch samples:" + + # Below is an example of the branch samples reporting: + # 73.04% 73.04% touch libc-2.27.so [.] _dl_addr + # 7.71% 7.71% touch libc-2.27.so [.] getenv + # 2.59% 2.59% touch ld-2.27.so [.] strcmp + perf report --stdio -i ${perfdata} | \ + egrep " +[0-9]+\.[0-9]+% +[0-9]+\.[0-9]+% +$1 " +} + +perf_report_instruction_samples() { + echo "Looking at perf.data file for instruction samples:" + + # Below is an example of the instruction samples reporting: + # 68.12% touch libc-2.27.so [.] _dl_addr + # 5.80% touch libc-2.27.so [.] getenv + # 4.35% touch ld-2.27.so [.] _dl_fixup + perf report --itrace=i1000i --stdio -i ${perfdata} | \ + egrep " +[0-9]+\.[0-9]+% +$1" +} + +is_device_sink() { + # If the node of "enable_sink" is existed under the device path, this + # means the device is a sink device. Need to exclude 'tpiu' since it + # cannot support perf PMU. + echo "$1" | egrep -q -v "tpiu" + + if [ $? -eq 0 -a -e "$1/enable_sink" ]; then + + pmu_dev="/sys/bus/event_source/devices/cs_etm/sinks/$2" + + # Warn if the device is not supported by PMU + if ! [ -f $pmu_dev ]; then + echo "PMU doesn't support $pmu_dev" + fi + + return 0 + fi + + # Otherwise, it's not a sink device + return 1 +} + +arm_cs_iterate_devices() { + for dev in $1/connections/out\:*; do + + # Skip testing if it's not a directory + ! [ -d $dev ] && continue; + + # Read out its symbol link file name + path=`readlink -f $dev` + + # Extract device name from path, e.g. + # path = '/sys/devices/platform/20010000.etf/tmc_etf0' + # `> device_name = 'tmc_etf0' + device_name=$(basename $path) + + if is_device_sink $path $devce_name; then + + record_touch_file $device_name $2 && + perf_script_branch_samples touch && + perf_report_branch_samples touch && + perf_report_instruction_samples touch + + err=$? + + # Exit when find failure + [ $err != 0 ] && exit $err + fi + + arm_cs_iterate_devices $dev $2 + done +} + +arm_cs_etm_traverse_path_test() { + # Iterate for every ETM device + for dev in /sys/bus/coresight/devices/etm*; do + + # Find the ETM device belonging to which CPU + cpu=`cat $dev/cpu` + + echo $dev + echo $cpu + + # Use depth-first search (DFS) to iterate outputs + arm_cs_iterate_devices $dev $cpu + done +} + +arm_cs_etm_system_wide_test() { + echo "Recording trace with system wide mode" + perf record -o ${perfdata} -e cs_etm// -a -- ls + + perf_script_branch_samples perf && + perf_report_branch_samples perf && + perf_report_instruction_samples perf + + err=$? + + # Exit when find failure + [ $err != 0 ] && exit $err +} + +arm_cs_etm_snapshot_test() { + echo "Recording trace with snapshot mode" + perf record -o ${perfdata} -e cs_etm// -S \ + -- dd if=/dev/zero of=/dev/null & + PERFPID=$! + + # Wait for perf program + sleep 1 + + # Send signal to snapshot trace data + kill -USR2 $PERFPID + + # Stop perf program + kill $PERFPID + wait $PERFPID + + perf_script_branch_samples dd && + perf_report_branch_samples dd && + perf_report_instruction_samples dd + + err=$? + + # Exit when find failure + [ $err != 0 ] && exit $err +} + +arm_cs_etm_traverse_path_test +arm_cs_etm_system_wide_test +arm_cs_etm_snapshot_test +exit 0 diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h index 4447a516c689..ef0f33c6ba23 100644 --- a/tools/perf/tests/tests.h +++ b/tools/perf/tests/tests.h @@ -122,6 +122,7 @@ int test__pfm(struct test *test, int subtest); const char *test__pfm_subtest_get_desc(int subtest); int test__pfm_subtest_get_nr(void); int test__parse_metric(struct test *test, int subtest); +int test__pe_file_parsing(struct test *test, int subtest); bool test__bp_signal_is_supported(void); bool test__bp_account_is_supported(void); diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 0a1fcf787538..fc17af7ba845 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -3127,6 +3127,8 @@ static int annotation__config(const char *var, const char *value, void *data) value); } else if (!strcmp(var, "annotate.use_offset")) { opt->use_offset = perf_config_bool("use_offset", value); + } else if (!strcmp(var, "annotate.disassembler_style")) { + opt->disassembler_style = value; } else { pr_debug("%s variable unknown, ignoring...", var); } diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index c0768c61eb43..e971daf946d0 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -1732,6 +1732,91 @@ struct evsel *perf_evlist__reset_weak_group(struct evlist *evsel_list, return leader; } +static int evlist__parse_control_fifo(const char *str, int *ctl_fd, int *ctl_fd_ack, bool *ctl_fd_close) +{ + char *s, *p; + int ret = 0, fd; + + if (strncmp(str, "fifo:", 5)) + return -EINVAL; + + str += 5; + if (!*str || *str == ',') + return -EINVAL; + + s = strdup(str); + if (!s) + return -ENOMEM; + + p = strchr(s, ','); + if (p) + *p = '\0'; + + /* + * O_RDWR avoids POLLHUPs which is necessary to allow the other + * end of a FIFO to be repeatedly opened and closed. + */ + fd = open(s, O_RDWR | O_NONBLOCK | O_CLOEXEC); + if (fd < 0) { + pr_err("Failed to open '%s'\n", s); + ret = -errno; + goto out_free; + } + *ctl_fd = fd; + *ctl_fd_close = true; + + if (p && *++p) { + /* O_RDWR | O_NONBLOCK means the other end need not be open */ + fd = open(p, O_RDWR | O_NONBLOCK | O_CLOEXEC); + if (fd < 0) { + pr_err("Failed to open '%s'\n", p); + ret = -errno; + goto out_free; + } + *ctl_fd_ack = fd; + } + +out_free: + free(s); + return ret; +} + +int evlist__parse_control(const char *str, int *ctl_fd, int *ctl_fd_ack, bool *ctl_fd_close) +{ + char *comma = NULL, *endptr = NULL; + + *ctl_fd_close = false; + + if (strncmp(str, "fd:", 3)) + return evlist__parse_control_fifo(str, ctl_fd, ctl_fd_ack, ctl_fd_close); + + *ctl_fd = strtoul(&str[3], &endptr, 0); + if (endptr == &str[3]) + return -EINVAL; + + comma = strchr(str, ','); + if (comma) { + if (endptr != comma) + return -EINVAL; + + *ctl_fd_ack = strtoul(comma + 1, &endptr, 0); + if (endptr == comma + 1 || *endptr != '\0') + return -EINVAL; + } + + return 0; +} + +void evlist__close_control(int ctl_fd, int ctl_fd_ack, bool *ctl_fd_close) +{ + if (*ctl_fd_close) { + *ctl_fd_close = false; + close(ctl_fd); + if (ctl_fd_ack >= 0) + close(ctl_fd_ack); + } +} + int evlist__initialize_ctlfd(struct evlist *evlist, int fd, int ack) { if (fd == -1) { @@ -1783,6 +1868,7 @@ static int evlist__ctlfd_recv(struct evlist *evlist, enum evlist_ctl_cmd *cmd, char c; size_t bytes_read = 0; + *cmd = EVLIST_CTL_CMD_UNSUPPORTED; memset(cmd_data, 0, data_size); data_size--; @@ -1794,30 +1880,39 @@ static int evlist__ctlfd_recv(struct evlist *evlist, enum evlist_ctl_cmd *cmd, cmd_data[bytes_read++] = c; if (bytes_read == data_size) break; - } else { - if (err == -1) + continue; + } else if (err == -1) { + if (errno == EINTR) + continue; + if (errno == EAGAIN || errno == EWOULDBLOCK) + err = 0; + else pr_err("Failed to read from ctlfd %d: %m\n", evlist->ctl_fd.fd); - break; } + break; } while (1); pr_debug("Message from ctl_fd: \"%s%s\"\n", cmd_data, bytes_read == data_size ? "" : c == '\n' ? "\\n" : "\\0"); - if (err > 0) { + if (bytes_read > 0) { if (!strncmp(cmd_data, EVLIST_CTL_CMD_ENABLE_TAG, (sizeof(EVLIST_CTL_CMD_ENABLE_TAG)-1))) { *cmd = EVLIST_CTL_CMD_ENABLE; } else if (!strncmp(cmd_data, EVLIST_CTL_CMD_DISABLE_TAG, (sizeof(EVLIST_CTL_CMD_DISABLE_TAG)-1))) { *cmd = EVLIST_CTL_CMD_DISABLE; + } else if (!strncmp(cmd_data, EVLIST_CTL_CMD_SNAPSHOT_TAG, + (sizeof(EVLIST_CTL_CMD_SNAPSHOT_TAG)-1))) { + *cmd = EVLIST_CTL_CMD_SNAPSHOT; + pr_debug("is snapshot\n"); } } - return err; + return bytes_read ? (int)bytes_read : err; } -static int evlist__ctlfd_ack(struct evlist *evlist) +int evlist__ctlfd_ack(struct evlist *evlist) { int err; @@ -1853,13 +1948,16 @@ int evlist__ctlfd_process(struct evlist *evlist, enum evlist_ctl_cmd *cmd) case EVLIST_CTL_CMD_DISABLE: evlist__disable(evlist); break; + case EVLIST_CTL_CMD_SNAPSHOT: + break; case EVLIST_CTL_CMD_ACK: case EVLIST_CTL_CMD_UNSUPPORTED: default: pr_debug("ctlfd: unsupported %d\n", *cmd); break; } - if (!(*cmd == EVLIST_CTL_CMD_ACK || *cmd == EVLIST_CTL_CMD_UNSUPPORTED)) + if (!(*cmd == EVLIST_CTL_CMD_ACK || *cmd == EVLIST_CTL_CMD_UNSUPPORTED || + *cmd == EVLIST_CTL_CMD_SNAPSHOT)) evlist__ctlfd_ack(evlist); } } diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index c73f7f7f120b..bc38a53f6a1a 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -363,6 +363,7 @@ struct evsel *perf_evlist__reset_weak_group(struct evlist *evlist, #define EVLIST_CTL_CMD_ENABLE_TAG "enable" #define EVLIST_CTL_CMD_DISABLE_TAG "disable" #define EVLIST_CTL_CMD_ACK_TAG "ack\n" +#define EVLIST_CTL_CMD_SNAPSHOT_TAG "snapshot" #define EVLIST_CTL_CMD_MAX_LEN 64 @@ -370,13 +371,17 @@ enum evlist_ctl_cmd { EVLIST_CTL_CMD_UNSUPPORTED = 0, EVLIST_CTL_CMD_ENABLE, EVLIST_CTL_CMD_DISABLE, - EVLIST_CTL_CMD_ACK + EVLIST_CTL_CMD_ACK, + EVLIST_CTL_CMD_SNAPSHOT, }; +int evlist__parse_control(const char *str, int *ctl_fd, int *ctl_fd_ack, bool *ctl_fd_close); +void evlist__close_control(int ctl_fd, int ctl_fd_ack, bool *ctl_fd_close); int evlist__initialize_ctlfd(struct evlist *evlist, int ctl_fd, int ctl_fd_ack); int evlist__finalize_ctlfd(struct evlist *evlist); bool evlist__ctlfd_initialized(struct evlist *evlist); int evlist__ctlfd_process(struct evlist *evlist, enum evlist_ctl_cmd *cmd); +int evlist__ctlfd_ack(struct evlist *evlist); #define EVLIST_ENABLED_MSG "Events enabled\n" #define EVLIST_DISABLED_MSG "Events disabled\n" diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 459b51e90063..2ac19a2530a2 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -1684,6 +1684,11 @@ retry_open: FD(evsel, cpu, thread) = fd; + if (unlikely(test_attr__enabled)) { + test_attr__open(&evsel->core.attr, pid, cpus->map[cpu], + fd, group_fd, flags); + } + if (fd < 0) { err = -errno; diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index ab5030fcfed4..941702cb6a79 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -15,7 +15,6 @@ #include "rblist.h" #include <string.h> #include <errno.h> -#include "pmu-events/pmu-events.h" #include "strlist.h" #include <assert.h> #include <linux/ctype.h> @@ -151,7 +150,7 @@ static void expr_ids__exit(struct expr_ids *ids) } /** - * Find a group of events in perf_evlist that correpond to those from a parsed + * Find a group of events in perf_evlist that correspond to those from a parsed * metric expression. Note, as find_evsel_group is called in the same order as * perf_evlist was constructed, metric_no_merge doesn't need to test for * underfilling a group. @@ -540,10 +539,12 @@ void metricgroup__print(bool metrics, bool metricgroups, char *filter, } } - if (metricgroups && !raw) - printf("\nMetric Groups:\n\n"); - else if (metrics && !raw) - printf("\nMetrics:\n\n"); + if (!filter || !rblist__empty(&groups)) { + if (metricgroups && !raw) + printf("\nMetric Groups:\n\n"); + else if (metrics && !raw) + printf("\nMetrics:\n\n"); + } for (node = rb_first_cached(&groups.entries); node; node = next) { struct mep *me = container_of(node, struct mep, nd); @@ -639,7 +640,7 @@ static bool metricgroup__has_constraint(struct pmu_event *pe) return false; } -int __weak arch_get_runtimeparam(void) +int __weak arch_get_runtimeparam(struct pmu_event *pe __maybe_unused) { return 1; } @@ -910,7 +911,7 @@ static int add_metric(struct list_head *metric_list, } else { int j, count; - count = arch_get_runtimeparam(); + count = arch_get_runtimeparam(pe); /* This loop is added to create multiple * events depend on count value and add diff --git a/tools/perf/util/metricgroup.h b/tools/perf/util/metricgroup.h index 62623a39cbec..491a5d78252d 100644 --- a/tools/perf/util/metricgroup.h +++ b/tools/perf/util/metricgroup.h @@ -5,6 +5,7 @@ #include <linux/list.h> #include <linux/rbtree.h> #include <stdbool.h> +#include "pmu-events/pmu-events.h" struct evsel; struct evlist; @@ -52,6 +53,6 @@ int metricgroup__parse_groups_test(struct evlist *evlist, void metricgroup__print(bool metrics, bool groups, char *filter, bool raw, bool details); bool metricgroup__has_metric(const char *metric); -int arch_get_runtimeparam(void); +int arch_get_runtimeparam(struct pmu_event *pe __maybe_unused); void metricgroup__rblist_exit(struct rblist *metric_events); #endif diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index 75a9b1d62bba..74f85948d101 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -17,7 +17,7 @@ #include "mmap.h" #include "util/env.h" #include <internal/lib.h> -#include "../perf-sys.h" +#include "util.h" #if PY_MAJOR_VERSION < 3 #define _PyUnicode_FromString(arg) \ diff --git a/tools/perf/util/record.h b/tools/perf/util/record.h index 03678ff25539..266760ac9143 100644 --- a/tools/perf/util/record.h +++ b/tools/perf/util/record.h @@ -73,6 +73,7 @@ struct record_opts { unsigned int nr_threads_synthesize; int ctl_fd; int ctl_fd_ack; + bool ctl_fd_close; }; extern const char * const *record_usage; diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index 493ec372fdec..4b57c0c07632 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -946,7 +946,6 @@ static void print_metric_headers(struct perf_stat_config *config, 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, diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index aa3bed48511b..9911fc6adbfd 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -136,6 +136,7 @@ struct perf_stat_config { struct rblist metric_events; int ctl_fd; int ctl_fd_ack; + bool ctl_fd_close; }; void perf_stat__set_big_num(int set); diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 8cc4b0059fb0..94a156df22d5 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -50,6 +50,10 @@ typedef Elf64_Nhdr GElf_Nhdr; #define DMGL_ANSI (1 << 1) /* Include const, volatile, etc */ #endif +#ifdef HAVE_LIBBFD_SUPPORT +#define PACKAGE 'perf' +#include <bfd.h> +#else #ifdef HAVE_CPLUS_DEMANGLE_SUPPORT extern char *cplus_demangle(const char *, int); @@ -65,9 +69,7 @@ static inline char *bfd_demangle(void __maybe_unused *v, { return NULL; } -#else -#define PACKAGE 'perf' -#include <bfd.h> +#endif #endif #endif @@ -530,6 +532,36 @@ out: return err; } +#ifdef HAVE_LIBBFD_BUILDID_SUPPORT + +int filename__read_build_id(const char *filename, void *bf, size_t size) +{ + int err = -1; + bfd *abfd; + + abfd = bfd_openr(filename, NULL); + if (!abfd) + return -1; + + if (!bfd_check_format(abfd, bfd_object)) { + pr_debug2("%s: cannot read %s bfd file.\n", __func__, filename); + goto out_close; + } + + if (!abfd->build_id || abfd->build_id->size > size) + goto out_close; + + memcpy(bf, abfd->build_id->data, abfd->build_id->size); + memset(bf + abfd->build_id->size, 0, size - abfd->build_id->size); + err = abfd->build_id->size; + +out_close: + bfd_close(abfd); + return err; +} + +#else // HAVE_LIBBFD_BUILDID_SUPPORT + int filename__read_build_id(const char *filename, void *bf, size_t size) { int fd, err = -1; @@ -557,6 +589,8 @@ out: return err; } +#endif // HAVE_LIBBFD_BUILDID_SUPPORT + int sysfs__read_build_id(const char *filename, void *build_id, size_t size) { int fd, err = -1; @@ -608,6 +642,44 @@ out: return err; } +#ifdef HAVE_LIBBFD_SUPPORT + +int filename__read_debuglink(const char *filename, char *debuglink, + size_t size) +{ + int err = -1; + asection *section; + bfd *abfd; + + abfd = bfd_openr(filename, NULL); + if (!abfd) + return -1; + + if (!bfd_check_format(abfd, bfd_object)) { + pr_debug2("%s: cannot read %s bfd file.\n", __func__, filename); + goto out_close; + } + + section = bfd_get_section_by_name(abfd, ".gnu_debuglink"); + if (!section) + goto out_close; + + if (section->size > size) + goto out_close; + + if (!bfd_get_section_contents(abfd, section, debuglink, 0, + section->size)) + goto out_close; + + err = 0; + +out_close: + bfd_close(abfd); + return err; +} + +#else + int filename__read_debuglink(const char *filename, char *debuglink, size_t size) { @@ -660,6 +732,8 @@ out: return err; } +#endif + static int dso__swap_init(struct dso *dso, unsigned char eidata) { static unsigned int const endian = 1; diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 5151a8c0b791..5ddf76fb691c 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -1526,6 +1526,138 @@ out_failure: return -1; } +#ifdef HAVE_LIBBFD_SUPPORT +#define PACKAGE 'perf' +#include <bfd.h> + +static int bfd_symbols__cmpvalue(const void *a, const void *b) +{ + const asymbol *as = *(const asymbol **)a, *bs = *(const asymbol **)b; + + if (bfd_asymbol_value(as) != bfd_asymbol_value(bs)) + return bfd_asymbol_value(as) - bfd_asymbol_value(bs); + + return bfd_asymbol_name(as)[0] - bfd_asymbol_name(bs)[0]; +} + +static int bfd2elf_binding(asymbol *symbol) +{ + if (symbol->flags & BSF_WEAK) + return STB_WEAK; + if (symbol->flags & BSF_GLOBAL) + return STB_GLOBAL; + if (symbol->flags & BSF_LOCAL) + return STB_LOCAL; + return -1; +} + +int dso__load_bfd_symbols(struct dso *dso, const char *debugfile) +{ + int err = -1; + long symbols_size, symbols_count; + asection *section; + asymbol **symbols, *sym; + struct symbol *symbol; + bfd *abfd; + u_int i; + u64 start, len; + + abfd = bfd_openr(dso->long_name, NULL); + if (!abfd) + return -1; + + if (!bfd_check_format(abfd, bfd_object)) { + pr_debug2("%s: cannot read %s bfd file.\n", __func__, + dso->long_name); + goto out_close; + } + + if (bfd_get_flavour(abfd) == bfd_target_elf_flavour) + goto out_close; + + section = bfd_get_section_by_name(abfd, ".text"); + if (section) + dso->text_offset = section->vma - section->filepos; + + bfd_close(abfd); + + abfd = bfd_openr(debugfile, NULL); + if (!abfd) + return -1; + + if (!bfd_check_format(abfd, bfd_object)) { + pr_debug2("%s: cannot read %s bfd file.\n", __func__, + debugfile); + goto out_close; + } + + if (bfd_get_flavour(abfd) == bfd_target_elf_flavour) + goto out_close; + + symbols_size = bfd_get_symtab_upper_bound(abfd); + if (symbols_size == 0) { + bfd_close(abfd); + return 0; + } + + if (symbols_size < 0) + goto out_close; + + symbols = malloc(symbols_size); + if (!symbols) + goto out_close; + + symbols_count = bfd_canonicalize_symtab(abfd, symbols); + if (symbols_count < 0) + goto out_free; + + qsort(symbols, symbols_count, sizeof(asymbol *), bfd_symbols__cmpvalue); + +#ifdef bfd_get_section +#define bfd_asymbol_section bfd_get_section +#endif + for (i = 0; i < symbols_count; ++i) { + sym = symbols[i]; + section = bfd_asymbol_section(sym); + if (bfd2elf_binding(sym) < 0) + continue; + + while (i + 1 < symbols_count && + bfd_asymbol_section(symbols[i + 1]) == section && + bfd2elf_binding(symbols[i + 1]) < 0) + i++; + + if (i + 1 < symbols_count && + bfd_asymbol_section(symbols[i + 1]) == section) + len = symbols[i + 1]->value - sym->value; + else + len = section->size - sym->value; + + start = bfd_asymbol_value(sym) - dso->text_offset; + symbol = symbol__new(start, len, bfd2elf_binding(sym), STT_FUNC, + bfd_asymbol_name(sym)); + if (!symbol) + goto out_free; + + symbols__insert(&dso->symbols, symbol); + } +#ifdef bfd_get_section +#undef bfd_asymbol_section +#endif + + symbols__fixup_end(&dso->symbols); + symbols__fixup_duplicate(&dso->symbols); + dso->adjust_symbols = 1; + + err = 0; +out_free: + free(symbols); +out_close: + bfd_close(abfd); + return err; +} +#endif + static bool dso__is_compatible_symtab_type(struct dso *dso, bool kmod, enum dso_binary_type type) { @@ -1699,6 +1831,7 @@ int dso__load(struct dso *dso, struct map *map) bool next_slot = false; bool is_reg; bool nsexit; + int bfdrc = -1; int sirc = -1; enum dso_binary_type symtab_type = binary_type_symtab[i]; @@ -1717,12 +1850,19 @@ int dso__load(struct dso *dso, struct map *map) nsinfo__mountns_exit(&nsc); is_reg = is_regular_file(name); +#ifdef HAVE_LIBBFD_SUPPORT if (is_reg) + bfdrc = dso__load_bfd_symbols(dso, name); +#endif + if (is_reg && bfdrc < 0) sirc = symsrc__init(ss, dso, name, symtab_type); if (nsexit) nsinfo__mountns_enter(dso->nsinfo, &nsc); + if (bfdrc == 0) + break; + if (!is_reg || sirc < 0) continue; diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index ff4f4c47e148..11fe71f46d14 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -175,6 +175,10 @@ int symbol__config_symfs(const struct option *opt __maybe_unused, struct symsrc; +#ifdef HAVE_LIBBFD_SUPPORT +int dso__load_bfd_symbols(struct dso *dso, const char *debugfile); +#endif + int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, struct symsrc *runtime_ss, int kmodule); int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss); diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index f486fdd3a538..ad737052e597 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -62,4 +62,10 @@ char *perf_exe(char *buf, int len); #endif #endif +extern bool test_attr__enabled; +void test_attr__ready(void); +void test_attr__init(void); +struct perf_event_attr; +void test_attr__open(struct perf_event_attr *attr, pid_t pid, int cpu, + int fd, int group_fd, unsigned long flags); #endif /* GIT_COMPAT_UTIL_H */ |