diff options
Diffstat (limited to 'tools/perf')
68 files changed, 1309 insertions, 784 deletions
diff --git a/tools/perf/Documentation/perf-annotate.txt b/tools/perf/Documentation/perf-annotate.txt index 5ad07ef417f..e9cd39a92dc 100644 --- a/tools/perf/Documentation/perf-annotate.txt +++ b/tools/perf/Documentation/perf-annotate.txt @@ -93,6 +93,9 @@ OPTIONS --skip-missing:: Skip symbols that cannot be annotated. +--group:: + Show event group information together + SEE ALSO -------- linkperf:perf-record[1], linkperf:perf-report[1] diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt index faf4f4feebc..23e587ad549 100644 --- a/tools/perf/Documentation/perf-stat.txt +++ b/tools/perf/Documentation/perf-stat.txt @@ -52,7 +52,7 @@ OPTIONS -r:: --repeat=<n>:: - repeat command and print average + stddev (max: 100) + repeat command and print average + stddev (max: 100). 0 means forever. -B:: --big-num:: diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST index 39d41068484..025de796067 100644 --- a/tools/perf/MANIFEST +++ b/tools/perf/MANIFEST @@ -1,6 +1,7 @@ tools/perf tools/scripts tools/lib/traceevent +tools/lib/lk include/linux/const.h include/linux/perf_event.h include/linux/rbtree.h diff --git a/tools/perf/Makefile b/tools/perf/Makefile index bb74c79cd16..0230b75ed7f 100644 --- a/tools/perf/Makefile +++ b/tools/perf/Makefile @@ -215,6 +215,7 @@ BASIC_CFLAGS = \ -Iutil \ -I. \ -I$(TRACE_EVENT_DIR) \ + -I../lib/ \ -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE BASIC_LDFLAGS = @@ -240,19 +241,28 @@ SCRIPT_SH += perf-archive.sh grep-libs = $(filter -l%,$(1)) strip-libs = $(filter-out -l%,$(1)) +LK_DIR = ../lib/lk/ TRACE_EVENT_DIR = ../lib/traceevent/ +LK_PATH=$(LK_DIR) + ifneq ($(OUTPUT),) TE_PATH=$(OUTPUT) +ifneq ($(subdir),) + LK_PATH=$(OUTPUT)$(LK_DIR) +else + LK_PATH=$(OUTPUT) +endif else TE_PATH=$(TRACE_EVENT_DIR) endif LIBTRACEEVENT = $(TE_PATH)libtraceevent.a -TE_LIB := -L$(TE_PATH) -ltraceevent - export LIBTRACEEVENT +LIBLK = $(LK_PATH)liblk.a +export LIBLK + # python extension build directories PYTHON_EXTBUILD := $(OUTPUT)python_ext_build/ PYTHON_EXTBUILD_LIB := $(PYTHON_EXTBUILD)lib/ @@ -355,7 +365,6 @@ LIB_H += util/cache.h LIB_H += util/callchain.h LIB_H += util/build-id.h LIB_H += util/debug.h -LIB_H += util/debugfs.h LIB_H += util/sysfs.h LIB_H += util/pmu.h LIB_H += util/event.h @@ -416,7 +425,6 @@ LIB_OBJS += $(OUTPUT)util/annotate.o LIB_OBJS += $(OUTPUT)util/build-id.o LIB_OBJS += $(OUTPUT)util/config.o LIB_OBJS += $(OUTPUT)util/ctype.o -LIB_OBJS += $(OUTPUT)util/debugfs.o LIB_OBJS += $(OUTPUT)util/sysfs.o LIB_OBJS += $(OUTPUT)util/pmu.o LIB_OBJS += $(OUTPUT)util/environment.o @@ -503,6 +511,10 @@ LIB_OBJS += $(OUTPUT)tests/evsel-tp-sched.o LIB_OBJS += $(OUTPUT)tests/pmu.o LIB_OBJS += $(OUTPUT)tests/hists_link.o LIB_OBJS += $(OUTPUT)tests/python-use.o +LIB_OBJS += $(OUTPUT)tests/bp_signal.o +LIB_OBJS += $(OUTPUT)tests/bp_signal_overflow.o +LIB_OBJS += $(OUTPUT)tests/task-exit.o +LIB_OBJS += $(OUTPUT)tests/sw-clock.o BUILTIN_OBJS += $(OUTPUT)builtin-annotate.o BUILTIN_OBJS += $(OUTPUT)builtin-bench.o @@ -536,7 +548,7 @@ BUILTIN_OBJS += $(OUTPUT)builtin-kvm.o BUILTIN_OBJS += $(OUTPUT)builtin-inject.o BUILTIN_OBJS += $(OUTPUT)tests/builtin-test.o -PERFLIBS = $(LIB_FILE) $(LIBTRACEEVENT) +PERFLIBS = $(LIB_FILE) $(LIBLK) $(LIBTRACEEVENT) # # Platform specific tweaks @@ -1051,6 +1063,18 @@ $(LIBTRACEEVENT): $(LIBTRACEEVENT)-clean: $(QUIET_SUBDIR0)$(TRACE_EVENT_DIR) $(QUIET_SUBDIR1) O=$(OUTPUT) clean +# if subdir is set, we've been called from above so target has been built +# already +$(LIBLK): +ifeq ($(subdir),) + $(QUIET_SUBDIR0)$(LK_DIR) $(QUIET_SUBDIR1) O=$(OUTPUT) liblk.a +endif + +$(LIBLK)-clean: +ifeq ($(subdir),) + $(QUIET_SUBDIR0)$(LK_DIR) $(QUIET_SUBDIR1) O=$(OUTPUT) clean +endif + help: @echo 'Perf make targets:' @echo ' doc - make *all* documentation (see below)' @@ -1171,7 +1195,7 @@ $(INSTALL_DOC_TARGETS): ### Cleaning rules -clean: $(LIBTRACEEVENT)-clean +clean: $(LIBTRACEEVENT)-clean $(LIBLK)-clean $(RM) $(LIB_OBJS) $(BUILTIN_OBJS) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf.o $(LANG_BINDINGS) $(RM) $(ALL_PROGRAMS) perf $(RM) *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* @@ -1181,6 +1205,6 @@ clean: $(LIBTRACEEVENT)-clean $(RM) $(OUTPUT)util/*-flex* $(python-clean) -.PHONY: all install clean strip $(LIBTRACEEVENT) +.PHONY: all install clean strip $(LIBTRACEEVENT) $(LIBLK) .PHONY: shell_compatibility_test please_set_SHELL_PATH_to_a_more_modern_shell .PHONY: .FORCE-PERF-VERSION-FILE TAGS tags cscope .FORCE-PERF-CFLAGS diff --git a/tools/perf/arch/arm/util/dwarf-regs.c b/tools/perf/arch/arm/util/dwarf-regs.c index e8d5c551c69..33ec5b339da 100644 --- a/tools/perf/arch/arm/util/dwarf-regs.c +++ b/tools/perf/arch/arm/util/dwarf-regs.c @@ -8,10 +8,7 @@ * published by the Free Software Foundation. */ -#include <stdlib.h> -#ifndef __UCLIBC__ -#include <libio.h> -#endif +#include <stddef.h> #include <dwarf-regs.h> struct pt_regs_dwarfnum { diff --git a/tools/perf/arch/powerpc/util/dwarf-regs.c b/tools/perf/arch/powerpc/util/dwarf-regs.c index 7cdd61d0e27..733151cdf46 100644 --- a/tools/perf/arch/powerpc/util/dwarf-regs.c +++ b/tools/perf/arch/powerpc/util/dwarf-regs.c @@ -9,10 +9,7 @@ * 2 of the License, or (at your option) any later version. */ -#include <stdlib.h> -#ifndef __UCLIBC__ -#include <libio.h> -#endif +#include <stddef.h> #include <dwarf-regs.h> diff --git a/tools/perf/arch/s390/util/dwarf-regs.c b/tools/perf/arch/s390/util/dwarf-regs.c index e19653e025f..0469df02ee6 100644 --- a/tools/perf/arch/s390/util/dwarf-regs.c +++ b/tools/perf/arch/s390/util/dwarf-regs.c @@ -6,7 +6,7 @@ * */ -#include <libio.h> +#include <stddef.h> #include <dwarf-regs.h> #define NUM_GPRS 16 diff --git a/tools/perf/arch/sh/util/dwarf-regs.c b/tools/perf/arch/sh/util/dwarf-regs.c index a11edb007a6..0d0897f57a1 100644 --- a/tools/perf/arch/sh/util/dwarf-regs.c +++ b/tools/perf/arch/sh/util/dwarf-regs.c @@ -19,7 +19,7 @@ * */ -#include <libio.h> +#include <stddef.h> #include <dwarf-regs.h> /* diff --git a/tools/perf/arch/sparc/util/dwarf-regs.c b/tools/perf/arch/sparc/util/dwarf-regs.c index 0ab88483720..92eda412fed 100644 --- a/tools/perf/arch/sparc/util/dwarf-regs.c +++ b/tools/perf/arch/sparc/util/dwarf-regs.c @@ -9,7 +9,7 @@ * 2 of the License, or (at your option) any later version. */ -#include <libio.h> +#include <stddef.h> #include <dwarf-regs.h> #define SPARC_MAX_REGS 96 diff --git a/tools/perf/arch/x86/util/dwarf-regs.c b/tools/perf/arch/x86/util/dwarf-regs.c index a794d308192..be22dd46323 100644 --- a/tools/perf/arch/x86/util/dwarf-regs.c +++ b/tools/perf/arch/x86/util/dwarf-regs.c @@ -20,7 +20,7 @@ * */ -#include <libio.h> +#include <stddef.h> #include <dwarf-regs.h> /* diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index 2e6961ea318..ae36f3cb541 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -109,14 +109,16 @@ static int process_sample_event(struct perf_tool *tool, return 0; } -static int hist_entry__tty_annotate(struct hist_entry *he, int evidx, +static int hist_entry__tty_annotate(struct hist_entry *he, + struct perf_evsel *evsel, struct perf_annotate *ann) { - return symbol__tty_annotate(he->ms.sym, he->ms.map, evidx, + return symbol__tty_annotate(he->ms.sym, he->ms.map, evsel, ann->print_line, ann->full_paths, 0, 0); } -static void hists__find_annotations(struct hists *self, int evidx, +static void hists__find_annotations(struct hists *self, + struct perf_evsel *evsel, struct perf_annotate *ann) { struct rb_node *nd = rb_first(&self->entries), *next; @@ -142,14 +144,14 @@ find_next: if (use_browser == 2) { int ret; - ret = hist_entry__gtk_annotate(he, evidx, NULL); + ret = hist_entry__gtk_annotate(he, evsel, NULL); if (!ret || !ann->skip_missing) return; /* skip missing symbols */ nd = rb_next(nd); } else if (use_browser == 1) { - key = hist_entry__tui_annotate(he, evidx, NULL); + key = hist_entry__tui_annotate(he, evsel, NULL); switch (key) { case -1: if (!ann->skip_missing) @@ -168,7 +170,7 @@ find_next: if (next != NULL) nd = next; } else { - hist_entry__tty_annotate(he, evidx, ann); + hist_entry__tty_annotate(he, evsel, ann); nd = rb_next(nd); /* * Since we have a hist_entry per IP for the same @@ -230,7 +232,12 @@ static int __cmd_annotate(struct perf_annotate *ann) total_nr_samples += nr_samples; hists__collapse_resort(hists); hists__output_resort(hists); - hists__find_annotations(hists, pos->idx, ann); + + if (symbol_conf.event_group && + !perf_evsel__is_group_leader(pos)) + continue; + + hists__find_annotations(hists, pos, ann); } } @@ -312,6 +319,8 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused) "Specify disassembler style (e.g. -M intel for intel syntax)"), OPT_STRING(0, "objdump", &objdump_path, "path", "objdump binary to use for disassembly and annotations"), + OPT_BOOLEAN(0, "group", &symbol_conf.event_group, + "Show event group information together"), OPT_END() }; diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index 37a769d7f9f..533501e2b07 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -12,7 +12,7 @@ #include "util/parse-options.h" #include "util/trace-event.h" #include "util/debug.h" -#include "util/debugfs.h" +#include <lk/debugfs.h> #include "util/tool.h" #include "util/stat.h" diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c index de38a034b12..e8a66f9a671 100644 --- a/tools/perf/builtin-probe.c +++ b/tools/perf/builtin-probe.c @@ -37,7 +37,7 @@ #include "util/strfilter.h" #include "util/symbol.h" #include "util/debug.h" -#include "util/debugfs.h" +#include <lk/debugfs.h> #include "util/parse-options.h" #include "util/probe-finder.h" #include "util/probe-event.h" diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index f1a939ebc19..9f2344a2c50 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -474,7 +474,9 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv) } if (forks) { - err = perf_evlist__prepare_workload(evsel_list, opts, argv); + err = perf_evlist__prepare_workload(evsel_list, &opts->target, + argv, opts->pipe_output, + true); if (err < 0) { pr_err("Couldn't run the workload!\n"); goto out_delete_session; @@ -964,7 +966,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused) struct perf_record *rec = &record; char errbuf[BUFSIZ]; - evsel_list = perf_evlist__new(NULL, NULL); + evsel_list = perf_evlist__new(); if (evsel_list == NULL) return -ENOMEM; @@ -1026,7 +1028,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused) ui__error("%s", errbuf); err = -saved_errno; - goto out_free_fd; + goto out_symbol_exit; } err = -ENOMEM; @@ -1057,6 +1059,9 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused) } err = __cmd_record(&record, argc, argv); + + perf_evlist__munmap(evsel_list); + perf_evlist__close(evsel_list); out_free_fd: perf_evlist__delete_maps(evsel_list); out_symbol_exit: diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 96b5a7fee4b..296bd219977 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -13,7 +13,6 @@ #include "util/annotate.h" #include "util/color.h" #include <linux/list.h> -#include "util/cache.h" #include <linux/rbtree.h> #include "util/symbol.h" #include "util/callchain.h" @@ -314,7 +313,7 @@ static size_t hists__fprintf_nr_sample_events(struct hists *self, char buf[512]; size_t size = sizeof(buf); - if (symbol_conf.event_group && evsel->nr_members > 1) { + if (perf_evsel__is_group_event(evsel)) { struct perf_evsel *pos; perf_evsel__group_desc(evsel, buf, size); diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 99848761f57..ba0bdd87c27 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -94,6 +94,7 @@ static const char *pre_cmd = NULL; static const char *post_cmd = NULL; static bool sync_run = false; static unsigned int interval = 0; +static bool forever = false; static struct timespec ref_time; static struct cpu_map *sock_map; @@ -125,6 +126,11 @@ static inline int perf_evsel__nr_cpus(struct perf_evsel *evsel) return perf_evsel__cpus(evsel)->nr; } +static void perf_evsel__reset_stat_priv(struct perf_evsel *evsel) +{ + memset(evsel->priv, 0, sizeof(struct perf_stat)); +} + static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel) { evsel->priv = zalloc(sizeof(struct perf_stat)); @@ -160,6 +166,35 @@ static void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel) evsel->prev_raw_counts = NULL; } +static void perf_evlist__free_stats(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel; + + list_for_each_entry(evsel, &evlist->entries, node) { + perf_evsel__free_stat_priv(evsel); + perf_evsel__free_counts(evsel); + perf_evsel__free_prev_raw_counts(evsel); + } +} + +static int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw) +{ + struct perf_evsel *evsel; + + list_for_each_entry(evsel, &evlist->entries, node) { + if (perf_evsel__alloc_stat_priv(evsel) < 0 || + perf_evsel__alloc_counts(evsel, perf_evsel__nr_cpus(evsel)) < 0 || + (alloc_raw && perf_evsel__alloc_prev_raw_counts(evsel) < 0)) + goto out_free; + } + + return 0; + +out_free: + perf_evlist__free_stats(evlist); + return -1; +} + static struct stats runtime_nsecs_stats[MAX_NR_CPUS]; static struct stats runtime_cycles_stats[MAX_NR_CPUS]; static struct stats runtime_stalled_cycles_front_stats[MAX_NR_CPUS]; @@ -173,6 +208,29 @@ static struct stats runtime_itlb_cache_stats[MAX_NR_CPUS]; static struct stats runtime_dtlb_cache_stats[MAX_NR_CPUS]; static struct stats walltime_nsecs_stats; +static void perf_stat__reset_stats(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel; + + list_for_each_entry(evsel, &evlist->entries, node) { + perf_evsel__reset_stat_priv(evsel); + perf_evsel__reset_counts(evsel, perf_evsel__nr_cpus(evsel)); + } + + memset(runtime_nsecs_stats, 0, sizeof(runtime_nsecs_stats)); + memset(runtime_cycles_stats, 0, sizeof(runtime_cycles_stats)); + memset(runtime_stalled_cycles_front_stats, 0, sizeof(runtime_stalled_cycles_front_stats)); + memset(runtime_stalled_cycles_back_stats, 0, sizeof(runtime_stalled_cycles_back_stats)); + memset(runtime_branches_stats, 0, sizeof(runtime_branches_stats)); + memset(runtime_cacherefs_stats, 0, sizeof(runtime_cacherefs_stats)); + memset(runtime_l1_dcache_stats, 0, sizeof(runtime_l1_dcache_stats)); + memset(runtime_l1_icache_stats, 0, sizeof(runtime_l1_icache_stats)); + memset(runtime_ll_cache_stats, 0, sizeof(runtime_ll_cache_stats)); + memset(runtime_itlb_cache_stats, 0, sizeof(runtime_itlb_cache_stats)); + memset(runtime_dtlb_cache_stats, 0, sizeof(runtime_dtlb_cache_stats)); + memset(&walltime_nsecs_stats, 0, sizeof(walltime_nsecs_stats)); +} + static int create_perf_stat_counter(struct perf_evsel *evsel) { struct perf_event_attr *attr = &evsel->attr; @@ -249,7 +307,7 @@ static int read_counter_aggr(struct perf_evsel *counter) int i; if (__perf_evsel__read(counter, perf_evsel__nr_cpus(counter), - evsel_list->threads->nr, scale) < 0) + thread_map__nr(evsel_list->threads), scale) < 0) return -1; for (i = 0; i < 3; i++) @@ -337,16 +395,14 @@ static void print_interval(void) } } -static int __run_perf_stat(int argc __maybe_unused, const char **argv) +static int __run_perf_stat(int argc, const char **argv) { char msg[512]; unsigned long long t0, t1; struct perf_evsel *counter; struct timespec ts; int status = 0; - int child_ready_pipe[2], go_pipe[2]; const bool forks = (argc > 0); - char buf; if (interval) { ts.tv_sec = interval / 1000; @@ -362,55 +418,12 @@ static int __run_perf_stat(int argc __maybe_unused, const char **argv) return -1; } - if (forks && (pipe(child_ready_pipe) < 0 || pipe(go_pipe) < 0)) { - perror("failed to create pipes"); - return -1; - } - if (forks) { - if ((child_pid = fork()) < 0) - perror("failed to fork"); - - if (!child_pid) { - close(child_ready_pipe[0]); - close(go_pipe[1]); - fcntl(go_pipe[0], F_SETFD, FD_CLOEXEC); - - /* - * Do a dummy execvp to get the PLT entry resolved, - * so we avoid the resolver overhead on the real - * execvp call. - */ < |