Merge tag 'perf-core-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/core improvements from Arnaldo Carvalho de Melo:

 * perf inject changes to allow showing where a task sleeps, from Andrew Vagin.

 * Makefile improvements from Namhyung Kim.

 * Add --pre and --post command hooks in 'stat', from Peter Zijlstra.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

tools/lib/traceevent/Makefile

@@ -253,7 +253,7 @@ all_deps := $(all_objs:%.o=.%.d)
 # let .d file also depends on the source and header files
 define check_deps
 		@set -e; $(RM) $@; \
-		$(CC) -M $(CFLAGS) $< > $@.$$$$; \
+		$(CC) -MM $(CFLAGS) $< > $@.$$$$; \
 		sed 's,\($*\)\.o[ :]*,\1.o $@ : ,g' < $@.$$$$ > $@; \
 		$(RM) $@.$$$$
 endef

tools/perf/Documentation/perf-inject.txt

@@ -29,6 +29,17 @@ OPTIONS
 -v::
 --verbose::
 	Be more verbose.
+-i::
+--input=::
+	Input file name. (default: stdin)
+-o::
+--output=::
+	Output file name. (default: stdout)
+-s::
+--sched-stat::
+	Merge sched_stat and sched_switch for getting events where and how long
+	tasks slept. sched_switch contains a callchain where a task slept and
+	sched_stat contains a timeslice how long a task slept.
 
 SEE ALSO
 --------

tools/perf/Documentation/perf-stat.txt

@@ -108,6 +108,11 @@ 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
 
+--pre::
+--post::
+	Pre and post measurement hooks, e.g.:
+
+perf stat --repeat 10 --null --sync --pre 'make -s O=defconfig-build/clean' -- make -s -j64 O=defconfig-build/ bzImage
 
 
 EXAMPLES

tools/perf/Makefile

@@ -541,7 +541,8 @@ LIB_OBJS += $(OUTPUT)util/symbol-minimal.o
 else # NO_LIBELF
 BASIC_CFLAGS += -DLIBELF_SUPPORT
 
-ifeq ($(call try-cc,$(SOURCE_ELF_MMAP),$(FLAGS_COMMON),-DLIBELF_MMAP),y)
+FLAGS_LIBELF=$(ALL_CFLAGS) $(ALL_LDFLAGS) $(EXTLIBS)
+ifeq ($(call try-cc,$(SOURCE_ELF_MMAP),$(FLAGS_LIBELF),-DLIBELF_MMAP),y)
 	BASIC_CFLAGS += -DLIBELF_MMAP
 endif
 
@@ -977,20 +978,15 @@ help:
 	@echo 'Perf maintainer targets:'
 	@echo '  clean			- clean all binary objects and build output'
 
-doc:
-	$(MAKE) -C Documentation all
-
-man:
-	$(MAKE) -C Documentation man
 
-html:
-	$(MAKE) -C Documentation html
+DOC_TARGETS := doc man html info pdf
 
-info:
-	$(MAKE) -C Documentation info
+INSTALL_DOC_TARGETS := $(patsubst %,install-%,$(DOC_TARGETS)) try-install-man
+INSTALL_DOC_TARGETS += quick-install-doc quick-install-man quick-install-html
 
-pdf:
-	$(MAKE) -C Documentation pdf
+# 'make doc' should call 'make -C Documentation all'
+$(DOC_TARGETS):
+	$(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) $(@:doc=all)
 
 TAGS:
 	$(RM) TAGS
@@ -1061,32 +1057,9 @@ install: all try-install-man
 install-python_ext:
 	$(PYTHON_WORD) util/setup.py --quiet install --root='/$(DESTDIR_SQ)'
 
-install-doc:
-	$(MAKE) -C Documentation install
-
-install-man:
-	$(MAKE) -C Documentation install-man
-
-try-install-man:
-	$(MAKE) -C Documentation try-install-man
-
-install-html:
-	$(MAKE) -C Documentation install-html
-
-install-info:
-	$(MAKE) -C Documentation install-info
-
-install-pdf:
-	$(MAKE) -C Documentation install-pdf
-
-quick-install-doc:
-	$(MAKE) -C Documentation quick-install
-
-quick-install-man:
-	$(MAKE) -C Documentation quick-install-man
-
-quick-install-html:
-	$(MAKE) -C Documentation quick-install-html
+# 'make install-doc' should call 'make -C Documentation install'
+$(INSTALL_DOC_TARGETS):
+	$(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) $(@:-doc=)
 
 ### Cleaning rules
 
@@ -1094,7 +1067,7 @@ clean: $(LIBTRACEEVENT)-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*
-	$(MAKE) -C Documentation/ clean
+	$(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean
 	$(RM) $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)PERF-CFLAGS
 	$(RM) $(OUTPUT)util/*-bison*
 	$(RM) $(OUTPUT)util/*-flex*

tools/perf/builtin-inject.c

@@ -8,33 +8,53 @@
 #include "builtin.h"
 
 #include "perf.h"
+#include "util/color.h"
+#include "util/evlist.h"
+#include "util/evsel.h"
 #include "util/session.h"
 #include "util/tool.h"
 #include "util/debug.h"
+#include "util/build-id.h"
 
 #include "util/parse-options.h"
 
+#include <linux/list.h>
+
 struct perf_inject {
 	struct perf_tool tool;
 	bool		 build_ids;
+	bool		 sched_stat;
+	const char	 *input_name;
+	int		 pipe_output,
+			 output;
+	u64		 bytes_written;
+	struct list_head samples;
+};
+
+struct event_entry {
+	struct list_head node;
+	u32		 tid;
+	union perf_event event[0];
 };
 
-static int perf_event__repipe_synth(struct perf_tool *tool __maybe_unused,
+static int perf_event__repipe_synth(struct perf_tool *tool,
 				    union perf_event *event,
 				    struct machine *machine __maybe_unused)
 {
+	struct perf_inject *inject = container_of(tool, struct perf_inject, tool);
 	uint32_t size;
 	void *buf = event;
 
 	size = event->header.size;
 
 	while (size) {
-		int ret = write(STDOUT_FILENO, buf, size);
+		int ret = write(inject->output, buf, size);
 		if (ret < 0)
 			return -errno;
 
 		size -= ret;
 		buf += ret;
+		inject->bytes_written += ret;
 	}
 
 	return 0;
@@ -80,12 +100,25 @@ static int perf_event__repipe(struct perf_tool *tool,
 	return perf_event__repipe_synth(tool, event, machine);
 }
 
+typedef int (*inject_handler)(struct perf_tool *tool,
+			      union perf_event *event,
+			      struct perf_sample *sample,
+			      struct perf_evsel *evsel,
+			      struct machine *machine);
+
 static int perf_event__repipe_sample(struct perf_tool *tool,
 				     union perf_event *event,
-			      struct perf_sample *sample __maybe_unused,
-			      struct perf_evsel *evsel __maybe_unused,
-			      struct machine *machine)
+				     struct perf_sample *sample,
+				     struct perf_evsel *evsel,
+				     struct machine *machine)
 {
+	if (evsel->handler.func) {
+		inject_handler f = evsel->handler.func;
+		return f(tool, event, sample, evsel, machine);
+	}
+
+	build_id__mark_dso_hit(tool, event, sample, evsel, machine);
+
 	return perf_event__repipe_synth(tool, event, machine);
 }
 
@@ -210,6 +243,80 @@ repipe:
 	return 0;
 }
 
+static int perf_inject__sched_process_exit(struct perf_tool *tool,
+					   union perf_event *event __maybe_unused,
+					   struct perf_sample *sample,
+					   struct perf_evsel *evsel __maybe_unused,
+					   struct machine *machine __maybe_unused)
+{
+	struct perf_inject *inject = container_of(tool, struct perf_inject, tool);
+	struct event_entry *ent;
+
+	list_for_each_entry(ent, &inject->samples, node) {
+		if (sample->tid == ent->tid) {
+			list_del_init(&ent->node);
+			free(ent);
+			break;
+		}
+	}
+
+	return 0;
+}
+
+static int perf_inject__sched_switch(struct perf_tool *tool,
+				     union perf_event *event,
+				     struct perf_sample *sample,
+				     struct perf_evsel *evsel,
+				     struct machine *machine)
+{
+	struct perf_inject *inject = container_of(tool, struct perf_inject, tool);
+	struct event_entry *ent;
+
+	perf_inject__sched_process_exit(tool, event, sample, evsel, machine);
+
+	ent = malloc(event->header.size + sizeof(struct event_entry));
+	if (ent == NULL) {
+		color_fprintf(stderr, PERF_COLOR_RED,
+			     "Not enough memory to process sched switch event!");
+		return -1;
+	}
+
+	ent->tid = sample->tid;
+	memcpy(&ent->event, event, event->header.size);
+	list_add(&ent->node, &inject->samples);
+	return 0;
+}
+
+static int perf_inject__sched_stat(struct perf_tool *tool,
+				   union perf_event *event __maybe_unused,
+				   struct perf_sample *sample,
+				   struct perf_evsel *evsel,
+				   struct machine *machine)
+{
+	struct event_entry *ent;
+	union perf_event *event_sw;
+	struct perf_sample sample_sw;
+	struct perf_inject *inject = container_of(tool, struct perf_inject, tool);
+	u32 pid = perf_evsel__intval(evsel, sample, "pid");
+
+	list_for_each_entry(ent, &inject->samples, node) {
+		if (pid == ent->tid)
+			goto found;
+	}
+
+	return 0;
+found:
+	event_sw = &ent->event[0];
+	perf_evsel__parse_sample(evsel, event_sw, &sample_sw);
+
+	sample_sw.period = sample->period;
+	sample_sw.time	 = sample->time;
+	perf_event__synthesize_sample(event_sw, evsel->attr.sample_type,
+				      &sample_sw, false);
+	build_id__mark_dso_hit(tool, event_sw, &sample_sw, evsel, machine);
+	return perf_event__repipe(tool, event_sw, &sample_sw, machine);
+}
+
 extern volatile int session_done;
 
 static void sig_handler(int sig __maybe_unused)
@@ -217,6 +324,21 @@ static void sig_handler(int sig __maybe_unused)
 	session_done = 1;
 }
 
+static int perf_evsel__check_stype(struct perf_evsel *evsel,
+				   u64 sample_type, const char *sample_msg)
+{
+	struct perf_event_attr *attr = &evsel->attr;
+	const char *name = perf_evsel__name(evsel);
+
+	if (!(attr->sample_type & sample_type)) {
+		pr_err("Samples for %s event do not have %s attribute set.",
+			name, sample_msg);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static int __cmd_inject(struct perf_inject *inject)
 {
 	struct perf_session *session;
@@ -224,19 +346,48 @@ static int __cmd_inject(struct perf_inject *inject)
 
 	signal(SIGINT, sig_handler);
 
-	if (inject->build_ids) {
-		inject->tool.sample	  = perf_event__inject_buildid;
+	if (inject->build_ids || inject->sched_stat) {
 		inject->tool.mmap	  = perf_event__repipe_mmap;
 		inject->tool.fork	  = perf_event__repipe_fork;
 		inject->tool.tracing_data = perf_event__repipe_tracing_data;
 	}
 
-	session = perf_session__new("-", O_RDONLY, false, true, &inject->tool);
+	session = perf_session__new(inject->input_name, O_RDONLY, false, true, &inject->tool);
 	if (session == NULL)
 		return -ENOMEM;
 
+	if (inject->build_ids) {
+		inject->tool.sample = perf_event__inject_buildid;
+	} else if (inject->sched_stat) {
+		struct perf_evsel *evsel;
+
+		inject->tool.ordered_samples = true;
+
+		list_for_each_entry(evsel, &session->evlist->entries, node) {
+			const char *name = perf_evsel__name(evsel);
+
+			if (!strcmp(name, "sched:sched_switch")) {
+				if (perf_evsel__check_stype(evsel, PERF_SAMPLE_TID, "TID"))
+					return -EINVAL;
+
+				evsel->handler.func = perf_inject__sched_switch;
+			} else if (!strcmp(name, "sched:sched_process_exit"))
+				evsel->handler.func = perf_inject__sched_process_exit;
+			else if (!strncmp(name, "sched:sched_stat_", 17))
+				evsel->handler.func = perf_inject__sched_stat;
+		}
+	}
+
+	if (!inject->pipe_output)
+		lseek(inject->output, session->header.data_offset, SEEK_SET);
+
 	ret = perf_session__process_events(session, &inject->tool);
 
+	if (!inject->pipe_output) {
+		session->header.data_size = inject->bytes_written;
+		perf_session__write_header(session, session->evlist, inject->output, true);
+	}
+
 	perf_session__delete(session);
 
 	return ret;
@@ -260,10 +411,20 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
 			.tracing_data	= perf_event__repipe_tracing_data_synth,
 			.build_id	= perf_event__repipe_op2_synth,
 		},
+		.input_name  = "-",
+		.samples = LIST_HEAD_INIT(inject.samples),
 	};
+	const char *output_name = "-";
 	const struct option options[] = {
 		OPT_BOOLEAN('b', "build-ids", &inject.build_ids,
 			    "Inject build-ids into the output stream"),
+		OPT_STRING('i', "input", &inject.input_name, "file",
+			   "input file name"),
+		OPT_STRING('o', "output", &output_name, "file",
+			   "output file name"),
+		OPT_BOOLEAN('s', "sched-stat", &inject.sched_stat,
+			    "Merge sched-stat and sched-switch for getting events "
+			    "where and how long tasks slept"),
 		OPT_INCR('v', "verbose", &verbose,
 			 "be more verbose (show build ids, etc)"),
 		OPT_END()
@@ -281,6 +442,18 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (argc)
 		usage_with_options(inject_usage, options);
 
+	if (!strcmp(output_name, "-")) {
+		inject.pipe_output = 1;
+		inject.output = STDOUT_FILENO;
+	} else {
+		inject.output = open(output_name, O_CREAT | O_WRONLY | O_TRUNC,
+						  S_IRUSR | S_IWUSR);
+		if (inject.output < 0) {
+			perror("failed to create output file");
+			return -1;
+		}
+	}
+
 	if (symbol__init() < 0)
 		return -1;
 

tools/perf/builtin-stat.c

@@ -57,6 +57,7 @@
 #include "util/thread.h"
 #include "util/thread_map.h"
 
+#include <stdlib.h>
 #include <sys/prctl.h>
 #include <locale.h>
 
@@ -83,6 +84,9 @@ static const char		*csv_sep			= NULL;
 static bool			csv_output			= false;
 static bool			group				= false;
 static FILE			*output				= NULL;
+static const char		*pre_cmd			= NULL;
+static const char		*post_cmd			= NULL;
+static bool			sync_run			= false;
 
 static volatile int done = 0;
 
@@ -265,7 +269,7 @@ static int read_counter(struct perf_evsel *counter)
 	return 0;
 }
 
-static int run_perf_stat(int argc __maybe_unused, const char **argv)
+static int __run_perf_stat(int argc __maybe_unused, const char **argv)
 {
 	unsigned long long t0, t1;
 	struct perf_evsel *counter, *first;
@@ -405,6 +409,32 @@ static int run_perf_stat(int argc __maybe_unused, const char **argv)
 	return WEXITSTATUS(status);
 }
 
+static int run_perf_stat(int argc __maybe_unused, const char **argv)
+{
+	int ret;
+
+	if (pre_cmd) {
+		ret = system(pre_cmd);
+		if (ret)
+			return ret;
+	}
+
+	if (sync_run)
+		sync();
+
+	ret = __run_perf_stat(argc, argv);
+	if (ret)
+		return ret;
+
+	if (post_cmd) {
+		ret = system(post_cmd);
+		if (ret)
+			return ret;
+	}
+
+	return ret;
+}
+
 static void print_noise_pct(double total, double avg)
 {
 	double pct = rel_stddev_stats(total, avg);
@@ -1069,8 +1099,7 @@ static int add_default_attributes(void)
 
 int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 {
-	bool append_file = false,
-	     sync_run = false;
+	bool append_file = false;
 	int output_fd = 0;
 	const char *output_name	= NULL;
 	const struct option options[] = {
@@ -1114,6 +1143,10 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_BOOLEAN(0, "append", &append_file, "append to the output file"),
 	OPT_INTEGER(0, "log-fd", &output_fd,
 		    "log output to fd, instead of stderr"),
+	OPT_STRING(0, "pre", &pre_cmd, "command",
+			"command to run prior to the measured command"),
+	OPT_STRING(0, "post", &post_cmd, "command",
+			"command to run after to the measured command"),
 	OPT_END()
 	};
 	const char * const stat_usage[] = {
@@ -1238,9 +1271,6 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 			fprintf(output, "[ perf stat: executing run #%d ... ]\n",
 				run_idx + 1);
 
-		if (sync_run)
-			sync();
-
 		status = run_perf_stat(argc, argv);
 	}
 

tools/perf/config/utilities.mak

@@ -183,9 +183,8 @@ _gea_err  = $(if $(1),$(error Please set '$(1)' appropriately))
 # Usage: option = $(call try-cc, source-to-build, cc-options, msg)
 ifndef V
 TRY_CC_OUTPUT= > /dev/null 2>&1
-else
-TRY_CC_MSG=echo "CHK $(3)" 1>&2;
 endif
+TRY_CC_MSG=echo "    CHK $(3)" 1>&2;
 
 try-cc = $(shell sh -c						  \
 	'TMP="$(OUTPUT)$(TMPOUT).$$$$";				  \

tools/perf/util/build-id.c

@@ -16,11 +16,11 @@
 #include "session.h"
 #include "tool.h"
 
-static int build_id__mark_dso_hit(struct perf_tool *tool __maybe_unused,
-				  union perf_event *event,
-				  struct perf_sample *sample __maybe_unused,
-				  struct perf_evsel *evsel __maybe_unused,
-				  struct machine *machine)
+int build_id__mark_dso_hit(struct perf_tool *tool __maybe_unused,
+			   union perf_event *event,
+			   struct perf_sample *sample __maybe_unused,
+			   struct perf_evsel *evsel __maybe_unused,
+			   struct machine *machine)
 {
 	struct addr_location al;
 	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;

tools/perf/util/build-id.h

@@ -7,4 +7,8 @@ extern struct perf_tool build_id__mark_dso_hit_ops;
 
 char *dso__build_id_filename(struct dso *self, char *bf, size_t size);
 
+int build_id__mark_dso_hit(struct perf_tool *tool, union perf_event *event,
+			   struct perf_sample *sample, struct perf_evsel *evsel,
+			   struct machine *machine);
+
 #endif