perf/core improvements and fixes:

New user selectable features:
 
 - Support recording running/enabled time in 'perf record' (Andi Kleen)
 
 - New tool: 'perf data' for converting perf.data to other formats,
   initially for the CTF (Common Trace Format) from LTTng (Jiri Olsa, Sebastian Siewior)
 
 User visible:
 
 - Only insert blank duration bracket when tracing syscalls in 'perf trace' (Arnaldo Carvalho de Melo)
 
 - Filter out the trace pid when no threads are specified in 'perf trace' (Arnaldo Carvalho de Melo)
 
 - Add 'perf trace' man page entry for --event (Arnaldo Carvalho de Melo)
 
 - Dump stack on segfaults in 'perf trace' (Arnaldo Carvalho de Melo)
 
 Infrastructure:
 
 - Introduce set_filter_pid and set_filter_pids methods in the evlist class (Arnaldo Carvalho de Melo)
 
 - Some perf_session untanglement patches, removing the need to pass a
   perf_session instance for things that are related to evlists, so that
   tools that don't deal with perf.data files like trace in live mode can
   make use of the ordered_events class (Arnaldo Carvalho de Melo)
 
 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v1
 
 iQEcBAABAgAGBQJU7j2lAAoJEBpxZoYYoA71cxcH/2dqKGTtqucEgKwpOdo8uf5v
 uWFtLzHNxJXYYm1kpwxOj3aMIoEfyfTngLgumgzMVdeQ8+rZGWgF7FMz2Gdn0HJi
 5CWrT/keZz8iHxA6BI8NBAa4uO8ct4MHjHSsYuO8Fr4zQmQy9vprfl8D44BQFQr9
 6C35dTjP8chIUFLxL2Y5Wr1SATeZf+zJJVoGUES1xgk7iMCfgivg6vSQcGmgBbe6
 iJBqDpO+10j55X578d5WRV0UMKrHk25RdGBRaB9eA0KowJfKYva744coF7AHOoQR
 snc5Ti93w+ssTL6PSp+FFr81kJVOqQk2GaweMcnNpOP5A8SSS+47yicPUZ25Nng=
 =wb9I
 -----END PGP SIGNATURE-----

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 and fixes from Arnaldo Carvalho de Melo:

New user selectable features:

  - Support recording running/enabled time in 'perf record' (Andi Kleen)

  - New tool: 'perf data' for converting perf.data to other formats,
    initially for the CTF (Common Trace Format) from LTTng (Jiri Olsa, Sebastian Siewior)

User visible changes:

  - Only insert blank duration bracket when tracing syscalls in 'perf trace' (Arnaldo Carvalho de Melo)

  - Filter out the trace pid when no threads are specified in 'perf trace' (Arnaldo Carvalho de Melo)

  - Add 'perf trace' man page entry for --event (Arnaldo Carvalho de Melo)

  - Dump stack on segfaults in 'perf trace' (Arnaldo Carvalho de Melo)

Infrastructure changes:

  - Introduce set_filter_pid and set_filter_pids methods in the evlist class (Arnaldo Carvalho de Melo)

  - Some perf_session untanglement patches, removing the need to pass a
    perf_session instance for things that are related to evlists, so that
    tools that don't deal with perf.data files like trace in live mode can
    make use of the ordered_events class (Arnaldo Carvalho de Melo)

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

tools/perf/Build

@@ -18,6 +18,7 @@ perf-y += builtin-lock.o
 perf-y += builtin-kvm.o
 perf-y += builtin-inject.o
 perf-y += builtin-mem.o
+perf-y += builtin-data.o
 
 perf-$(CONFIG_AUDIT) += builtin-trace.o
 perf-$(CONFIG_LIBELF) += builtin-probe.o

tools/perf/Documentation/perf-data.txt

@@ -0,0 +1,40 @@
+perf-data(1)
+==============
+
+NAME
+----
+perf-data - Data file related processing
+
+SYNOPSIS
+--------
+[verse]
+'perf data' [<common options>] <command> [<options>]",
+
+DESCRIPTION
+-----------
+Data file related processing.
+
+COMMANDS
+--------
+convert::
+	Converts perf data file into another format (only CTF [1] format is support by now).
+	It's possible to set data-convert debug variable to get debug messages from conversion,
+	like:
+	  perf --debug data-convert data convert ...
+
+OPTIONS for 'convert'
+---------------------
+--to-ctf::
+	Triggers the CTF conversion, specify the path of CTF data directory.
+
+-i::
+	Specify input perf data file path.
+
+-v::
+--verbose::
+        Be more verbose (show counter open errors, etc).
+
+SEE ALSO
+--------
+linkperf:perf[1]
+[1] Common Trace Format - http://www.efficios.com/ctf

tools/perf/Documentation/perf-record.txt

@@ -241,6 +241,9 @@ Capture machine state (registers) at interrupt, i.e., on counter overflows for
 each sample. List of captured registers depends on the architecture. This option
 is off by default.
 
+--running-time::
+Record running and enabled time for read events (:S)
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-list[1]

tools/perf/Documentation/perf-trace.txt

@@ -55,6 +55,9 @@ OPTIONS
 --uid=::
         Record events in threads owned by uid. Name or number.
 
+--filter-pids=::
+	Filter out events for these pids and for 'trace' itself (comma separated list).
+
 -v::
 --verbose=::
         Verbosity level.
@@ -115,6 +118,9 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs.
 --syscalls::
 	Trace system calls. This options is enabled by default.
 
+--event::
+	Trace other events, see 'perf list' for a complete list.
+
 PAGEFAULTS
 ----------
 

tools/perf/Documentation/perf.txt

@@ -13,11 +13,16 @@ SYNOPSIS
 OPTIONS
 -------
 --debug::
-	Setup debug variable (just verbose for now) in value
+	Setup debug variable (see list below) in value
 	range (0, 10). Use like:
 	  --debug verbose   # sets verbose = 1
 	  --debug verbose=2 # sets verbose = 2
 
+	List of debug variables allowed to set:
+	  verbose          - general debug messages
+	  ordered-events   - ordered events object debug messages
+	  data-convert     - data convert command debug messages
+
 --buildid-dir::
 	Setup buildid cache directory. It has higher priority than
 	buildid.dir config file option.

tools/perf/Makefile.perf

@@ -68,7 +68,9 @@ include config/utilities.mak
 # for reading the x32 mode 32-bit compatibility VDSO in 64-bit mode
 #
 # Define NO_ZLIB if you do not want to support compressed kernel modules
-
+#
+# Define NO_LIBBABELTRACE if you do not want libbabeltrace support
+# for CTF data format.
 
 ifeq ($(srctree),)
 srctree := $(patsubst %/,%,$(dir $(shell pwd)))

tools/perf/builtin-data.c

@@ -0,0 +1,119 @@
+#include <linux/compiler.h>
+#include "builtin.h"
+#include "perf.h"
+#include "debug.h"
+#include "parse-options.h"
+#include "data-convert-bt.h"
+
+typedef int (*data_cmd_fn_t)(int argc, const char **argv, const char *prefix);
+
+struct data_cmd {
+	const char	*name;
+	const char	*summary;
+	data_cmd_fn_t	fn;
+};
+
+static struct data_cmd data_cmds[];
+
+#define for_each_cmd(cmd) \
+	for (cmd = data_cmds; cmd && cmd->name; cmd++)
+
+static const struct option data_options[] = {
+	OPT_END()
+};
+
+static const char * const data_usage[] = {
+	"perf data [<common options>] <command> [<options>]",
+	NULL
+};
+
+static void print_usage(void)
+{
+	struct data_cmd *cmd;
+
+	printf("Usage:\n");
+	printf("\t%s\n\n", data_usage[0]);
+	printf("\tAvailable commands:\n");
+
+	for_each_cmd(cmd) {
+		printf("\t %s\t- %s\n", cmd->name, cmd->summary);
+	}
+
+	printf("\n");
+}
+
+static const char * const data_convert_usage[] = {
+	"perf data convert [<options>]",
+	NULL
+};
+
+static int cmd_data_convert(int argc, const char **argv,
+			    const char *prefix __maybe_unused)
+{
+	const char *to_ctf     = NULL;
+	const struct option options[] = {
+		OPT_INCR('v', "verbose", &verbose, "be more verbose"),
+		OPT_STRING('i', "input", &input_name, "file", "input file name"),
+#ifdef HAVE_LIBBABELTRACE_SUPPORT
+		OPT_STRING(0, "to-ctf", &to_ctf, NULL, "Convert to CTF format"),
+#endif
+		OPT_END()
+	};
+
+#ifndef HAVE_LIBBABELTRACE_SUPPORT
+	pr_err("No conversion support compiled in.\n");
+	return -1;
+#endif
+
+	argc = parse_options(argc, argv, options,
+			     data_convert_usage, 0);
+	if (argc) {
+		usage_with_options(data_convert_usage, options);
+		return -1;
+	}
+
+	if (to_ctf) {
+#ifdef HAVE_LIBBABELTRACE_SUPPORT
+		return bt_convert__perf2ctf(input_name, to_ctf);
+#else
+		pr_err("The libbabeltrace support is not compiled in.\n");
+		return -1;
+#endif
+	}
+
+	return 0;
+}
+
+static struct data_cmd data_cmds[] = {
+	{ "convert", "converts data file between formats", cmd_data_convert },
+	{ NULL },
+};
+
+int cmd_data(int argc, const char **argv, const char *prefix)
+{
+	struct data_cmd *cmd;
+	const char *cmdstr;
+
+	/* No command specified. */
+	if (argc < 2)
+		goto usage;
+
+	argc = parse_options(argc, argv, data_options, data_usage,
+			     PARSE_OPT_STOP_AT_NON_OPTION);
+	if (argc < 1)
+		goto usage;
+
+	cmdstr = argv[0];
+
+	for_each_cmd(cmd) {
+		if (strcmp(cmd->name, cmdstr))
+			continue;
+
+		return cmd->fn(argc, argv, prefix);
+	}
+
+	pr_err("Unknown command: %s\n", cmdstr);
+usage:
+	print_usage();
+	return -1;
+}

tools/perf/builtin-record.c

@@ -839,6 +839,8 @@ struct option __record_options[] = {
 		    "use per-thread mmaps"),
 	OPT_BOOLEAN('I', "intr-regs", &record.opts.sample_intr_regs,
 		    "Sample machine registers on interrupt"),
+	OPT_BOOLEAN(0, "running-time", &record.opts.running_time,
+		    "Record running/enabled time of read (:S) events"),
 	OPT_END()
 };
 

tools/perf/builtin-sched.c

@@ -1473,9 +1473,9 @@ static int perf_sched__read_events(struct perf_sched *sched,
 			goto out_delete;
 		}
 
-		sched->nr_events      = session->stats.nr_events[0];
+		sched->nr_events      = session->evlist->stats.nr_events[0];
-		sched->nr_lost_events = session->stats.total_lost;
+		sched->nr_lost_events = session->evlist->stats.total_lost;
-		sched->nr_lost_chunks = session->stats.nr_events[PERF_RECORD_LOST];
+		sched->nr_lost_chunks = session->evlist->stats.nr_events[PERF_RECORD_LOST];
 	}
 
 	if (psession)

tools/perf/builtin-top.c

@@ -716,7 +716,7 @@ static void perf_event__process_sample(struct perf_tool *tool,
 
 	if (!machine) {
 		pr_err("%u unprocessable samples recorded.\r",
-		       top->session->stats.nr_unprocessable_samples++);
+		       top->session->evlist->stats.nr_unprocessable_samples++);
 		return;
 	}
 
@@ -856,7 +856,7 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx)
 			hists__inc_nr_events(evsel__hists(evsel), event->header.type);
 			machine__process_event(machine, event, &sample);
 		} else
-			++session->stats.nr_unknown_events;
+			++session->evlist->stats.nr_unknown_events;
 next_event:
 		perf_evlist__mmap_consume(top->evlist, idx);
 	}

tools/perf/builtin-trace.c

@@ -1229,6 +1229,10 @@ struct trace {
 	const char 		*last_vfs_getname;
 	struct intlist		*tid_list;
 	struct intlist		*pid_list;
+	struct {
+		size_t		nr;
+		pid_t		*entries;
+	}			filter_pids;
 	double			duration_filter;
 	double			runtime_ms;
 	struct {
@@ -1840,7 +1844,11 @@ static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel,
 {
 	trace__printf_interrupted_entry(trace, sample);
 	trace__fprintf_tstamp(trace, sample->time, trace->output);
-	fprintf(trace->output, "(%9.9s): %s:", " ", evsel->name);
+
+	if (trace->trace_syscalls)
+		fprintf(trace->output, "(         ): ");
+
+	fprintf(trace->output, "%s:", evsel->name);
 
 	if (evsel->tp_format) {
 		event_format__fprintf(evsel->tp_format, sample->cpu,
@@ -2084,10 +2092,39 @@ static int perf_evlist__add_pgfault(struct perf_evlist *evlist,
 	return 0;
 }
 
+static void trace__handle_event(struct trace *trace, union perf_event *event, struct perf_sample *sample)
+{
+	const u32 type = event->header.type;
+	struct perf_evsel *evsel;
+
+	if (!trace->full_time && trace->base_time == 0)
+		trace->base_time = sample->time;
+
+	if (type != PERF_RECORD_SAMPLE) {
+		trace__process_event(trace, trace->host, event, sample);
+		return;
+	}
+
+	evsel = perf_evlist__id2evsel(trace->evlist, sample->id);
+	if (evsel == NULL) {
+		fprintf(trace->output, "Unknown tp ID %" PRIu64 ", skipping...\n", sample->id);
+		return;
+	}
+
+	if (evsel->attr.type == PERF_TYPE_TRACEPOINT &&
+	    sample->raw_data == NULL) {
+		fprintf(trace->output, "%s sample with no payload for tid: %d, cpu %d, raw_size=%d, skipping...\n",
+		       perf_evsel__name(evsel), sample->tid,
+		       sample->cpu, sample->raw_size);
+	} else {
+		tracepoint_handler handler = evsel->handler;
+		handler(trace, evsel, event, sample);
+	}
+}
+
 static int trace__run(struct trace *trace, int argc, const char **argv)
 {
 	struct perf_evlist *evlist = trace->evlist;
-	struct perf_evsel *evsel;
 	int err = -1, i;
 	unsigned long before;
 	const bool forks = argc > 0;
@@ -2147,6 +2184,22 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 	if (err < 0)
 		goto out_error_open;
 
+	/*
+	 * Better not use !target__has_task() here because we need to cover the
+	 * case where no threads were specified in the command line, but a
+	 * workload was, and in that case we will fill in the thread_map when
+	 * we fork the workload in perf_evlist__prepare_workload.
+	 */
+	if (trace->filter_pids.nr > 0)
+		err = perf_evlist__set_filter_pids(evlist, trace->filter_pids.nr, trace->filter_pids.entries);
+	else if (evlist->threads->map[0] == -1)
+		err = perf_evlist__set_filter_pid(evlist, getpid());
+
+	if (err < 0) {
+		printf("err=%d,%s\n", -err, strerror(-err));
+		exit(1);
+	}
+
 	err = perf_evlist__mmap(evlist, trace->opts.mmap_pages, false);
 	if (err < 0)
 		goto out_error_mmap;
@@ -2166,8 +2219,6 @@ again:
 		union perf_event *event;
 
 		while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) {
-			const u32 type = event->header.type;
-			tracepoint_handler handler;
 			struct perf_sample sample;
 
 			++trace->nr_events;
@@ -2178,30 +2229,7 @@ again:
 				goto next_event;
 			}
 
-			if (!trace->full_time && trace->base_time == 0)
+			trace__handle_event(trace, event, &sample);
-				trace->base_time = sample.time;
-
-			if (type != PERF_RECORD_SAMPLE) {
-				trace__process_event(trace, trace->host, event, &sample);
-				continue;
-			}
-
-			evsel = perf_evlist__id2evsel(evlist, sample.id);
-			if (evsel == NULL) {
-				fprintf(trace->output, "Unknown tp ID %" PRIu64 ", skipping...\n", sample.id);
-				goto next_event;
-			}
-
-			if (evsel->attr.type == PERF_TYPE_TRACEPOINT &&
-			    sample.raw_data == NULL) {
-				fprintf(trace->output, "%s sample with no payload for tid: %d, cpu %d, raw_size=%d, skipping...\n",
-				       perf_evsel__name(evsel), sample.tid,
-				       sample.cpu, sample.raw_size);
-				goto next_event;
-			}
-
-			handler = evsel->handler;
-			handler(trace, evsel, event, &sample);
 next_event:
 			perf_evlist__mmap_consume(evlist, i);
 
@@ -2478,6 +2506,38 @@ static int trace__set_duration(const struct option *opt, const char *str,
 	return 0;
 }
 
+static int trace__set_filter_pids(const struct option *opt, const char *str,
+				  int unset __maybe_unused)
+{
+	int ret = -1;
+	size_t i;
+	struct trace *trace = opt->value;
+	/*
+	 * FIXME: introduce a intarray class, plain parse csv and create a
+	 * { int nr, int entries[] } struct...
+	 */
+	struct intlist *list = intlist__new(str);
+
+	if (list == NULL)
+		return -1;
+
+	i = trace->filter_pids.nr = intlist__nr_entries(list) + 1;
+	trace->filter_pids.entries = calloc(i, sizeof(pid_t));
+
+	if (trace->filter_pids.entries == NULL)
+		goto out;
+
+	trace->filter_pids.entries[0] = getpid();
+
+	for (i = 1; i < trace->filter_pids.nr; ++i)
+		trace->filter_pids.entries[i] = intlist__entry(list, i - 1)->i;
+
+	intlist__delete(list);
+	ret = 0;
+out:
+	return ret;
+}
+
 static int trace__open_output(struct trace *trace, const char *filename)
 {
 	struct stat st;
@@ -2568,6 +2628,8 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
 		    "trace events on existing process id"),
 	OPT_STRING('t', "tid", &trace.opts.target.tid, "tid",
 		    "trace events on existing thread id"),
+	OPT_CALLBACK(0, "filter-pids", &trace, "float",
+		     "show only events with duration > N.M ms", trace__set_filter_pids),
 	OPT_BOOLEAN('a', "all-cpus", &trace.opts.target.system_wide,
 		    "system-wide collection from all CPUs"),
 	OPT_STRING('C', "cpu", &trace.opts.target.cpu_list, "cpu",
@@ -2598,6 +2660,9 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
 	int err;
 	char bf[BUFSIZ];
 
+	signal(SIGSEGV, sighandler_dump_stack);
+	signal(SIGFPE, sighandler_dump_stack);
+
 	trace.evlist = perf_evlist__new();
 	if (trace.evlist == NULL)
 		return -ENOMEM;

tools/perf/builtin.h

@@ -37,6 +37,7 @@ extern int cmd_test(int argc, const char **argv, const char *prefix);
 extern int cmd_trace(int argc, const char **argv, const char *prefix);
 extern int cmd_inject(int argc, const char **argv, const char *prefix);
 extern int cmd_mem(int argc, const char **argv, const char *prefix);
+extern int cmd_data(int argc, const char **argv, const char *prefix);
 
 extern int find_scripts(char **scripts_array, char **scripts_path_array);
 #endif

tools/perf/command-list.txt

@@ -7,6 +7,7 @@ perf-archive			mainporcelain common
 perf-bench			mainporcelain common
 perf-buildid-cache		mainporcelain common
 perf-buildid-list		mainporcelain common
+perf-data			mainporcelain common
 perf-diff			mainporcelain common
 perf-evlist			mainporcelain common
 perf-inject			mainporcelain common

tools/perf/config/Makefile

@@ -96,6 +96,17 @@ ifndef NO_LIBELF
   FEATURE_CHECK_LDFLAGS-libdw-dwarf-unwind := $(LIBDW_LDFLAGS) -ldw
 endif
 
+ifndef NO_LIBBABELTRACE
+  # for linking with debug library, run like:
+  # make DEBUG=1 LIBBABELTRACE_DIR=/opt/libbabeltrace/
+  ifdef LIBBABELTRACE_DIR
+    LIBBABELTRACE_CFLAGS  := -I$(LIBBABELTRACE_DIR)/include
+    LIBBABELTRACE_LDFLAGS := -L$(LIBBABELTRACE_DIR)/lib
+  endif
+  FEATURE_CHECK_CFLAGS-libbabeltrace := $(LIBBABELTRACE_CFLAGS)
+  FEATURE_CHECK_LDFLAGS-libbabeltrace := $(LIBBABELTRACE_LDFLAGS) -lbabeltrace-ctf
+endif
+
 # include ARCH specific config
 -include $(src-perf)/arch/$(ARCH)/Makefile
 
@@ -216,6 +227,7 @@ CORE_FEATURE_TESTS =			\
 	stackprotector-all		\
 	timerfd				\
 	libdw-dwarf-unwind		\
+	libbabeltrace			\
 	zlib
 
 LIB_FEATURE_TESTS =			\
@@ -231,6 +243,7 @@ LIB_FEATURE_TESTS =			\
 	libslang			\
 	libunwind			\
 	libdw-dwarf-unwind		\
+	libbabeltrace			\
 	zlib
 
 VF_FEATURE_TESTS =			\
@@ -692,6 +705,18 @@ else
   NO_PERF_READ_VDSOX32 := 1
 endif
 
+ifndef NO_LIBBABELTRACE
+  ifeq ($(feature-libbabeltrace), 0)
+    msg := $(warning No libbabeltrace found, disables 'perf data' CTF format support, please install libbabeltrace-devel/libbabeltrace-ctf-dev);
+    NO_LIBBABELTRACE := 1
+  else
+    CFLAGS += -DHAVE_LIBBABELTRACE_SUPPORT $(LIBBABELTRACE_CFLAGS)
+    LDFLAGS += $(LIBBABELTRACE_LDFLAGS)
+    EXTLIBS += -lbabeltrace-ctf
+    $(call detected,CONFIG_LIBBABELTRACE)
+  endif
+endif
+
 # Among the variables below, these:
 #   perfexecdir
 #   template_dir

tools/perf/config/feature-checks/Makefile

@@ -29,6 +29,7 @@ FILES=					\
 	test-stackprotector-all.bin	\
 	test-timerfd.bin		\
 	test-libdw-dwarf-unwind.bin	\
+	test-libbabeltrace.bin		\
 	test-compile-32.bin		\
 	test-compile-x32.bin		\
 	test-zlib.bin
@@ -43,7 +44,7 @@ BUILD = $(CC) $(CFLAGS) -o $(OUTPUT)$@ $(patsubst %.bin,%.c,$@) $(LDFLAGS)
 ###############################
 
 test-all.bin:
-	$(BUILD) -Werror -fstack-protector-all -O2 -Werror -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lelf -laudit -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
+	$(BUILD) -Werror -fstack-protector-all -O2 -Werror -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lelf -laudit -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 -lbabeltrace
 
 test-hello.bin:
 	$(BUILD)
@@ -133,7 +134,10 @@ test-timerfd.bin:
 	$(BUILD)
 
 test-libdw-dwarf-unwind.bin:
-	$(BUILD)
+	$(BUILD) # -ldw provided by $(FEATURE_CHECK_LDFLAGS-libdw-dwarf-unwind)
+
+test-libbabeltrace.bin:
+	$(BUILD) # -lbabeltrace provided by $(FEATURE_CHECK_LDFLAGS-libbabeltrace)
 
 test-sync-compare-and-swap.bin:
 	$(BUILD) -Werror

tools/perf/config/feature-checks/test-all.c

@@ -101,6 +101,10 @@
 # include "test-pthread_attr_setaffinity_np.c"
 #undef main
 
+#define main main_test_libbabeltrace
+# include "test-libbabeltrace.c"
+#undef main
+
 int main(int argc, char *argv[])
 {
 	main_test_libpython();
@@ -126,6 +130,7 @@ int main(int argc, char *argv[])
 	main_test_sync_compare_and_swap(argc, argv);
 	main_test_zlib();
 	main_test_pthread_attr_setaffinity_np();
+	main_test_libbabeltrace();
 
 	return 0;
 }

tools/perf/config/feature-checks/test-libbabeltrace.c

@@ -0,0 +1,8 @@
+
+#include <babeltrace/ctf-writer/writer.h>
+
+int main(void)
+{
+	bt_ctf_stream_class_get_packet_context_type((void *) 0);
+	return 0;
+}

tools/perf/perf.c

@@ -62,6 +62,7 @@ static struct cmd_struct commands[] = {
 #endif
 	{ "inject",	cmd_inject,	0 },
 	{ "mem",	cmd_mem,	0 },
+	{ "data",	cmd_data,	0 },
 };
 
 struct pager_config {

tools/perf/perf.h

@@ -53,6 +53,7 @@ struct record_opts {
 	bool	     sample_time;
 	bool	     period;
 	bool	     sample_intr_regs;
+	bool	     running_time;
 	unsigned int freq;
 	unsigned int mmap_pages;
 	unsigned int user_freq;

tools/perf/util/Build

@@ -88,6 +88,8 @@ libperf-$(CONFIG_DWARF) += dwarf-aux.o
 libperf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
 libperf-$(CONFIG_LIBUNWIND)          += unwind-libunwind.o
 
+libperf-$(CONFIG_LIBBABELTRACE) += data-convert-bt.o
+
 libperf-y += scripting-engines/
 
 libperf-$(CONFIG_PERF_REGS) += perf_regs.o

tools/perf/util/data-convert-bt.c

@@ -0,0 +1,614 @@
+/*
+ * CTF writing support via babeltrace.
+ *
+ * Copyright (C) 2014, Jiri Olsa <jolsa@redhat.com>
+ * Copyright (C) 2014, Sebastian Andrzej Siewior <bigeasy@linutronix.de>
+ *
+ * Released under the GPL v2. (and only v2, not any later version)
+ */
+
+#include <linux/compiler.h>
+#include <babeltrace/ctf-writer/writer.h>
+#include <babeltrace/ctf-writer/clock.h>
+#include <babeltrace/ctf-writer/stream.h>
+#include <babeltrace/ctf-writer/event.h>
+#include <babeltrace/ctf-writer/event-types.h>
+#include <babeltrace/ctf-writer/event-fields.h>
+#include <babeltrace/ctf/events.h>
+#include <traceevent/event-parse.h>
+#include "asm/bug.h"
+#include "data-convert-bt.h"
+#include "session.h"
+#include "util.h"
+#include "debug.h"
+#include "tool.h"
+#include "evlist.h"
+#include "evsel.h"
+#include "machine.h"
+
+#define pr_N(n, fmt, ...) \
+	eprintf(n, debug_data_convert, fmt, ##__VA_ARGS__)
+
+#define pr(fmt, ...)  pr_N(1, pr_fmt(fmt), ##__VA_ARGS__)
+#define pr2(fmt, ...) pr_N(2, pr_fmt(fmt), ##__VA_ARGS__)
+
+#define pr_time2(t, fmt, ...) pr_time_N(2, debug_data_convert, t, pr_fmt(fmt), ##__VA_ARGS__)
+
+struct evsel_priv {
+	struct bt_ctf_event_class *event_class;
+};
+
+struct ctf_writer {
+	/* writer primitives */
+	struct bt_ctf_writer		*writer;
+	struct bt_ctf_stream		*stream;
+	struct bt_ctf_stream_class	*stream_class;
+	struct bt_ctf_clock		*clock;
+
+	/* data types */
+	union {
+		struct {
+			struct bt_ctf_field_type	*s64;
+			struct bt_ctf_field_type	*u64;
+			struct bt_ctf_field_type	*s32;
+			struct bt_ctf_field_type	*u32;
+			struct bt_ctf_field_type	*string;
+			struct bt_ctf_field_type	*u64_hex;
+		};
+		struct bt_ctf_field_type *array[6];
+	} data;
+};
+
+struct convert {
+	struct perf_tool	tool;
+	struct ctf_writer	writer;
+
+	u64			events_size;
+	u64			events_count;
+};
+
+static int value_set(struct bt_ctf_field_type *type,
+		     struct bt_ctf_event *event,
+		     const char *name, u64 val)
+{
+	struct bt_ctf_field *field;
+	bool sign = bt_ctf_field_type_integer_get_signed(type);
+	int ret;
+
+	field = bt_ctf_field_create(type);
+	if (!field) {
+		pr_err("failed to create a field %s\n", name);
+		return -1;
+	}
+
+	if (sign) {
+		ret = bt_ctf_field_signed_integer_set_value(field, val);
+		if (ret) {
+			pr_err("failed to set field value %s\n", name);
+			goto err;
+		}
+	} else {
+		ret = bt_ctf_field_unsigned_integer_set_value(field, val);
+		if (ret) {
+			pr_err("failed to set field value %s\n", name);
+			goto err;
+		}
+	}
+
+	ret = bt_ctf_event_set_payload(event, name, field);
+	if (ret) {
+		pr_err("failed to set payload %s\n", name);
+		goto err;
+	}
+
+	pr2("  SET [%s = %" PRIu64 "]\n", name, val);
+
+err:
+	bt_ctf_field_put(field);
+	return ret;
+}
+
+#define __FUNC_VALUE_SET(_name, _val_type)				\
+static __maybe_unused int value_set_##_name(struct ctf_writer *cw,	\
+			     struct bt_ctf_event *event,		\
+			     const char *name,				\
+			     _val_type val)				\
+{									\
+	struct bt_ctf_field_type *type = cw->data._name;		\
+	return value_set(type, event, name, (u64) val);			\
+}
+
+#define FUNC_VALUE_SET(_name) __FUNC_VALUE_SET(_name, _name)
+
+FUNC_VALUE_SET(s32)
+FUNC_VALUE_SET(u32)
+FUNC_VALUE_SET(s64)
+FUNC_VALUE_SET(u64)
+__FUNC_VALUE_SET(u64_hex, u64)
+
+static int add_generic_values(struct ctf_writer *cw,
+			      struct bt_ctf_event *event,
+			      struct perf_evsel *evsel,
+			      struct perf_sample *sample)
+{
+	u64 type = evsel->attr.sample_type;
+	int ret;
+
+	/*
+	 * missing:
+	 *   PERF_SAMPLE_TIME         - not needed as we have it in
+	 *                              ctf event header
+	 *   PERF_SAMPLE_READ         - TODO
+	 *   PERF_SAMPLE_CALLCHAIN    - TODO
+	 *   PERF_SAMPLE_RAW          - tracepoint fields are handled separately
+	 *   PERF_SAMPLE_BRANCH_STACK - TODO
+	 *   PERF_SAMPLE_REGS_USER    - TODO
+	 *   PERF_SAMPLE_STACK_USER   - TODO
+	 */
+
+	if (type & PERF_SAMPLE_IP) {
+		ret = value_set_u64_hex(cw, event, "perf_ip", sample->ip);
+		if (ret)
+			return -1;
+	}
+
+	if (type & PERF_SAMPLE_TID) {
+		ret = value_set_s32(cw, event, "perf_tid", sample->tid);
+		if (ret)
+			return -1;
+
+		ret = value_set_s32(cw, event, "perf_pid", sample->pid);
+		if (ret)
+			return -1;
+	}
+
+	if ((type & PERF_SAMPLE_ID) ||
+	    (type & PERF_SAMPLE_IDENTIFIER)) {
+		ret = value_set_u64(cw, event, "perf_id", sample->id);
+		if (ret)
+			return -1;
+	}
+
+	if (type & PERF_SAMPLE_STREAM_ID) {
+		ret = value_set_u64(cw, event, "perf_stream_id", sample->stream_id);
+		if (ret)
+			return -1;
+	}
+
+	if (type & PERF_SAMPLE_CPU) {
+		ret = value_set_u32(cw, event, "perf_cpu", sample->cpu);
+		if (ret)
+			return -1;
+	}
+
+	if (type & PERF_SAMPLE_PERIOD) {
+		ret = value_set_u64(cw, event, "perf_period", sample->period);
+		if (ret)
+			return -1;
+	}
+
+	if (type & PERF_SAMPLE_WEIGHT) {
+		ret = value_set_u64(cw, event, "perf_weight", sample->weight);
+		if (ret)
+			return -1;
+	}
+
+	if (type & PERF_SAMPLE_DATA_SRC) {
+		ret = value_set_u64(cw, event, "perf_data_src",
+				sample->data_src);
+		if (ret)
+			return -1;
+	}
+
+	if (type & PERF_SAMPLE_TRANSACTION) {
+		ret = value_set_u64(cw, event, "perf_transaction",
+				sample->transaction);
+		if (ret)
+			return -1;
+	}
+
+	return 0;
+}
+
+static int process_sample_event(struct perf_tool *tool,
+				union perf_event *_event __maybe_unused,
+				struct perf_sample *sample,
+				struct perf_evsel *evsel,
+				struct machine *machine __maybe_unused)
+{
+	struct convert *c = container_of(tool, struct convert, tool);
+	struct evsel_priv *priv = evsel->priv;
+	struct ctf_writer *cw = &c->writer;
+	struct bt_ctf_event_class *event_class;
+	struct bt_ctf_event *event;
+	int ret;
+
+	if (WARN_ONCE(!priv, "Failed to setup all events.\n"))
+		return 0;
+
+	event_class = priv->event_class;
+
+	/* update stats */
+	c->events_count++;
+	c->events_size += _event->header.size;
+
+	pr_time2(sample->time, "sample %" PRIu64 "\n", c->events_count);
+
+	event = bt_ctf_event_create(event_class);
+	if (!event) {
+		pr_err("Failed to create an CTF event\n");
+		return -1;
+	}
+
+	bt_ctf_clock_set_time(cw->clock, sample->time);
+
+	ret = add_generic_values(cw, event, evsel, sample);
+	if (ret)
+		return -1;
+
+	bt_ctf_stream_append_event(cw->stream, event);
+	bt_ctf_event_put(event);
+	return 0;
+}
+
+static int add_generic_types(struct ctf_writer *cw, struct perf_evsel *evsel,
+			     struct bt_ctf_event_class *event_class)
+{
+	u64 type = evsel->attr.sample_type;
+
+	/*
+	 * missing:
+	 *   PERF_SAMPLE_TIME         - not needed as we have it in
+	 *                              ctf event header
+	 *   PERF_SAMPLE_READ         - TODO
+	 *   PERF_SAMPLE_CALLCHAIN    - TODO
+	 *   PERF_SAMPLE_RAW          - tracepoint fields are handled separately
+	 *   PERF_SAMPLE_BRANCH_STACK - TODO
+	 *   PERF_SAMPLE_REGS_USER    - TODO
+	 *   PERF_SAMPLE_STACK_USER   - TODO
+	 */
+
+#define ADD_FIELD(cl, t, n)						\
+	do {								\
+		pr2("  field '%s'\n", n);				\
+		if (bt_ctf_event_class_add_field(cl, t, n)) {		\
+			pr_err("Failed to add field '%s;\n", n);	\
+			return -1;					\
+		}							\
+	} while (0)
+
+	if (type & PERF_SAMPLE_IP)
+		ADD_FIELD(event_class, cw->data.u64_hex, "perf_ip");
+
+	if (type & PERF_SAMPLE_TID) {
+		ADD_FIELD(event_class, cw->data.s32, "perf_tid");
+		ADD_FIELD(event_class, cw->data.s32, "perf_pid");
+	}
+
+	if ((type & PERF_SAMPLE_ID) ||
+	    (type & PERF_SAMPLE_IDENTIFIER))
+		ADD_FIELD(event_class, cw->data.u64, "perf_id");
+
+	if (type & PERF_SAMPLE_STREAM_ID)
+		ADD_FIELD(event_class, cw->data.u64, "perf_stream_id");
+
+	if (type & PERF_SAMPLE_CPU)
+		ADD_FIELD(event_class, cw->data.u32, "perf_cpu");
+
+	if (type & PERF_SAMPLE_PERIOD)
+		ADD_FIELD(event_class, cw->data.u64, "perf_period");
+
+	if (type & PERF_SAMPLE_WEIGHT)
+		ADD_FIELD(event_class, cw->data.u64, "perf_weight");
+
+	if (type & PERF_SAMPLE_DATA_SRC)
+		ADD_FIELD(event_class, cw->data.u64, "perf_data_src");
+
+	if (type & PERF_SAMPLE_TRANSACTION)
+		ADD_FIELD(event_class, cw->data.u64, "perf_transaction");
+
+#undef ADD_FIELD
+	return 0;
+}
+
+static int add_event(struct ctf_writer *cw, struct perf_evsel *evsel)
+{
+	struct bt_ctf_event_class *event_class;
+	struct evsel_priv *priv;
+	const char *name = perf_evsel__name(evsel);
+	int ret;
+
+	pr("Adding event '%s' (type %d)\n", name, evsel->attr.type);
+
+	event_class = bt_ctf_event_class_create(name);
+	if (!event_class)
+		return -1;
+
+	ret = add_generic_types(cw, evsel, event_class);
+	if (ret)
+		goto err;
+
+	ret = bt_ctf_stream_class_add_event_class(cw->stream_class, event_class);
+	if (ret) {
+		pr("Failed to add event class into stream.\n");
+		goto err;
+	}
+
+	priv = malloc(sizeof(*priv));
+	if (!priv)
+		goto err;
+
+	priv->event_class = event_class;
+	evsel->priv       = priv;
+	return 0;
+
+err:
+	bt_ctf_event_class_put(event_class);
+	pr_err("Failed to add event '%s'.\n", name);
+	return -1;
+}
+
+static int setup_events(struct ctf_writer *cw, struct perf_session *session)
+{
+	struct perf_evlist *evlist = session->evlist;
+	struct perf_evsel *evsel;
+	int ret;
+
+	evlist__for_each(evlist, evsel) {
+		ret = add_event(cw, evsel);
+		if (ret)
+			return ret;
+	}
+	return 0;
+}
+
+static int ctf_writer__setup_env(struct ctf_writer *cw,
+				 struct perf_session *session)
+{
+	struct perf_header *header = &session->header;
+	struct bt_ctf_writer *writer = cw->writer;
+
+#define ADD(__n, __v)							\
+do {									\
+	if (bt_ctf_writer_add_environment_field(writer, __n, __v))	\
+		return -1;						\
+} while (0)
+
+	ADD("host",    header->env.hostname);
+	ADD("sysname", "Linux");
+	ADD("release", header->env.os_release);
+	ADD("version", header->env.version);
+	ADD("machine", header->env.arch);
+	ADD("domain", "kernel");
+	ADD("tracer_name", "perf");
+
+#undef ADD
+	return 0;
+}
+
+static int ctf_writer__setup_clock(struct ctf_writer *cw)
+{
+	struct bt_ctf_clock *clock = cw->clock;
+
+	bt_ctf_clock_set_description(clock, "perf clock");
+
+#define SET(__n, __v)				\
+do {						\
+	if (bt_ctf_clock_set_##__n(clock, __v))	\
+		return -1;			\
+} while (0)
+
+	SET(frequency,   1000000000);
+	SET(offset_s,    0);
+	SET(offset,      0);
+	SET(precision,   10);
+	SET(is_absolute, 0);
+
+#undef SET
+	return 0;
+}
+
+static struct bt_ctf_field_type *create_int_type(int size, bool sign, bool hex)
+{
+	struct bt_ctf_field_type *type;
+
+	type = bt_ctf_field_type_integer_create(size);
+	if (!type)
+		return NULL;
+
+	if (sign &&
+	    bt_ctf_field_type_integer_set_signed(type, 1))
+		goto err;
+
+	if (hex &&
+	    bt_ctf_field_type_integer_set_base(type, BT_CTF_INTEGER_BASE_HEXADECIMAL))
+		goto err;
+
+	pr2("Created type: INTEGER %d-bit %ssigned %s\n",
+	    size, sign ? "un" : "", hex ? "hex" : "");
+	return type;
+
+err:
+	bt_ctf_field_type_put(type);
+	return NULL;
+}
+
+static void ctf_writer__cleanup_data(struct ctf_writer *cw)
+{
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(cw->data.array); i++)
+		bt_ctf_field_type_put(cw->data.array[i]);
+}
+
+static int ctf_writer__init_data(struct ctf_writer *cw)
+{
+#define CREATE_INT_TYPE(type, size, sign, hex)		\
+do {							\
+	(type) = create_int_type(size, sign, hex);	\
+	if (!(type))					\
+		goto err;				\
+} while (0)
+
+	CREATE_INT_TYPE(cw->data.s64, 64, true,  false);
+	CREATE_INT_TYPE(cw->data.u64, 64, false, false);
+	CREATE_INT_TYPE(cw->data.s32, 32, true,  false);
+	CREATE_INT_TYPE(cw->data.u32, 32, false, false);
+	CREATE_INT_TYPE(cw->data.u64_hex, 64, false, true);
+
+	cw->data.string  = bt_ctf_field_type_string_create();
+	if (cw->data.string)
+		return 0;
+
+err:
+	ctf_writer__cleanup_data(cw);
+	pr_err("Failed to create data types.\n");
+	return -1;
+}
+
+static void ctf_writer__cleanup(struct ctf_writer *cw)
+{
+	ctf_writer__cleanup_data(cw);
+
+	bt_ctf_clock_put(cw->clock);
+	bt_ctf_stream_put(cw->stream);
+	bt_ctf_stream_class_put(cw->stream_class);
+	bt_ctf_writer_put(cw->writer);
+
+	/* and NULL all the pointers */
+	memset(cw, 0, sizeof(*cw));
+}
+
+static int ctf_writer__init(struct ctf_writer *cw, const char *path)
+{
+	struct bt_ctf_writer		*writer;
+	struct bt_ctf_stream_class	*stream_class;
+	struct bt_ctf_stream		*stream;
+	struct bt_ctf_clock		*clock;
+
+	/* CTF writer */
+	writer = bt_ctf_writer_create(path);
+	if (!writer)
+		goto err;
+
+	cw->writer = writer;
+
+	/* CTF clock */
+	clock = bt_ctf_clock_create("perf_clock");
+	if (!clock) {
+		pr("Failed to create CTF clock.\n");
+		goto err_cleanup;
+	}
+
+	cw->clock = clock;
+
+	if (ctf_writer__setup_clock(cw)) {
+		pr("Failed to setup CTF clock.\n");
+		goto err_cleanup;
+	}
+
+	/* CTF stream class */
+	stream_class = bt_ctf_stream_class_create("perf_stream");
+	if (!stream_class) {
+		pr("Failed to create CTF stream class.\n");
+		goto err_cleanup;
+	}
+
+	cw->stream_class = stream_class;
+
+	/* CTF clock stream setup */
+	if (bt_ctf_stream_class_set_clock(stream_class, clock)) {
+		pr("Failed to assign CTF clock to stream class.\n");
+		goto err_cleanup;
+	}
+
+	if (ctf_writer__init_data(cw))
+		goto err_cleanup;
+
+	/* CTF stream instance */
+	stream = bt_ctf_writer_create_stream(writer, stream_class);
+	if (!stream) {
+		pr("Failed to create CTF stream.\n");
+		goto err_cleanup;
+	}
+
+	cw->stream = stream;
+
+	/* CTF clock writer setup */
+	if (bt_ctf_writer_add_clock(writer, clock)) {
+		pr("Failed to assign CTF clock to writer.\n");
+		goto err_cleanup;
+	}
+
+	return 0;
+
+err_cleanup:
+	ctf_writer__cleanup(cw);
+err:
+	pr_err("Failed to setup CTF writer.\n");
+	return -1;
+}
+
+int bt_convert__perf2ctf(const char *input, const char *path)
+{
+	struct perf_session *session;
+	struct perf_data_file file = {
+		.path = input,
+		.mode = PERF_DATA_MODE_READ,
+	};
+	struct convert c = {
+		.tool = {
+			.sample          = process_sample_event,
+			.mmap            = perf_event__process_mmap,
+			.mmap2           = perf_event__process_mmap2,
+			.comm            = perf_event__process_comm,
+			.exit            = perf_event__process_exit,
+			.fork            = perf_event__process_fork,
+			.lost            = perf_event__process_lost,
+			.tracing_data    = perf_event__process_tracing_data,
+			.build_id        = perf_event__process_build_id,
+			.ordered_events  = true,
+			.ordering_requires_timestamps = true,
+		},
+	};
+	struct ctf_writer *cw = &c.writer;
+	int err = -1;
+
+	/* CTF writer */
+	if (ctf_writer__init(cw, path))
+		return -1;
+
+	/* perf.data session */
+	session = perf_session__new(&file, 0, NULL);
+	if (!session)
+		goto free_writer;
+
+	/* CTF writer env/clock setup  */
+	if (ctf_writer__setup_env(cw, session))
+		goto free_session;
+
+	/* CTF events setup */
+	if (setup_events(cw, session))
+		goto free_session;
+
+	err = perf_session__process_events(session, &c.tool);
+	if (!err)
+		err = bt_ctf_stream_flush(cw->stream);
+
+	fprintf(stderr,
+		"[ perf data convert: Converted '%s' into CTF data '%s' ]\n",
+		file.path, path);
+
+	fprintf(stderr,
+		"[ perf data convert: Converted and wrote %.3f MB (%" PRIu64 " samples) ]\n",
+		(double) c.events_size / 1024.0 / 1024.0,
+		c.events_count);
+
+	/* its all good */
+free_session:
+	perf_session__delete(session);
+
+free_writer:
+	ctf_writer__cleanup(cw);
+	return err;
+}

tools/perf/util/data-convert-bt.h

@@ -0,0 +1,8 @@
+#ifndef __DATA_CONVERT_BT_H
+#define __DATA_CONVERT_BT_H
+#ifdef HAVE_LIBBABELTRACE_SUPPORT
+
+int bt_convert__perf2ctf(const char *input_name, const char *to_ctf);
+
+#endif /* HAVE_LIBBABELTRACE_SUPPORT */
+#endif /* __DATA_CONVERT_BT_H */

tools/perf/util/debug.c

@@ -20,6 +20,7 @@ int verbose;
 bool dump_trace = false, quiet = false;
 int debug_ordered_events;
 static int redirect_to_stderr;
+int debug_data_convert;
 
 static int _eprintf(int level, int var, const char *fmt, va_list args)
 {
@@ -147,6 +148,7 @@ static struct debug_variable {
 	{ .name = "verbose",		.ptr = &verbose },
 	{ .name = "ordered-events",	.ptr = &debug_ordered_events},
 	{ .name = "stderr",		.ptr = &redirect_to_stderr},
+	{ .name = "data-convert",	.ptr = &debug_data_convert },
 	{ .name = NULL, }
 };
 

tools/perf/util/debug.h

@@ -12,6 +12,7 @@
 extern int verbose;
 extern bool quiet, dump_trace;
 extern int debug_ordered_events;
+extern int debug_data_convert;
 
 #ifndef pr_fmt
 #define pr_fmt(fmt) fmt

tools/perf/util/event.c

@@ -615,7 +615,7 @@ size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp)
 	else
 		s = "";
 
-	return fprintf(fp, "%s: %s:%d\n", s, event->comm.comm, event->comm.tid);
+	return fprintf(fp, "%s: %s:%d/%d\n", s, event->comm.comm, event->comm.pid, event->comm.tid);
 }
 
 int perf_event__process_comm(struct perf_tool *tool __maybe_unused,

tools/perf/util/evlist.c

@@ -1085,6 +1085,38 @@ int perf_evlist__set_filter(struct perf_evlist *evlist, const char *filter)
 	return err;
 }
 
+int perf_evlist__set_filter_pids(struct perf_evlist *evlist, size_t npids, pid_t *pids)
+{
+	char *filter;
+	int ret = -1;
+	size_t i;
+
+	for (i = 0; i < npids; ++i) {
+		if (i == 0) {
+			if (asprintf(&filter, "common_pid != %d", pids[i]) < 0)
+				return -1;
+		} else {
+			char *tmp;
+
+			if (asprintf(&tmp, "%s && common_pid != %d", filter, pids[i]) < 0)
+				goto out_free;
+
+			free(filter);
+			filter = tmp;
+		}
+	}
+
+	ret = perf_evlist__set_filter(evlist, filter);
+out_free:
+	free(filter);
+	return ret;
+}
+
+int perf_evlist__set_filter_pid(struct perf_evlist *evlist, pid_t pid)
+{
+	return perf_evlist__set_filter_pids(evlist, 1, &pid);
+}
+
 bool perf_evlist__valid_sample_type(struct perf_evlist *evlist)
 {
 	struct perf_evsel *pos;

tools/perf/util/evlist.h

@@ -51,6 +51,7 @@ struct perf_evlist {
 	struct thread_map *threads;
 	struct cpu_map	  *cpus;
 	struct perf_evsel *selected;
+	struct events_stats stats;
 };
 
 struct perf_evsel_str_handler {
@@ -77,6 +78,8 @@ int perf_evlist__add_newtp(struct perf_evlist *evlist,
 			   const char *sys, const char *name, void *handler);
 
 int perf_evlist__set_filter(struct perf_evlist *evlist, const char *filter);
+int perf_evlist__set_filter_pid(struct perf_evlist *evlist, pid_t pid);
+int perf_evlist__set_filter_pids(struct perf_evlist *evlist, size_t npids, pid_t *pids);
 
 struct perf_evsel *
 perf_evlist__find_tracepoint_by_id(struct perf_evlist *evlist, int id);

tools/perf/util/evsel.c

@@ -734,6 +734,12 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
 	if (opts->sample_transaction)
 		perf_evsel__set_sample_bit(evsel, TRANSACTION);
 
+	if (opts->running_time) {
+		evsel->attr.read_format |=
+			PERF_FORMAT_TOTAL_TIME_ENABLED |
+			PERF_FORMAT_TOTAL_TIME_RUNNING;
+	}
+
 	/*
 	 * XXX see the function comment above
 	 *

tools/perf/util/ordered-events.c

@@ -166,7 +166,7 @@ static int __ordered_events__flush(struct perf_session *s,
 	struct ui_progress prog;
 	int ret;
 
-	if (!tool->ordered_events || !limit)
+	if (!limit)
 		return 0;
 
 	if (show_progress)
@@ -216,6 +216,9 @@ int ordered_events__flush(struct perf_session *s, struct perf_tool *tool,
 	};
 	int err;
 
+	if (oe->nr_events == 0)
+		return 0;
+
 	switch (how) {
 	case OE_FLUSH__FINAL:
 		oe->next_flush = ULLONG_MAX;

tools/perf/util/session.c

@@ -537,7 +537,7 @@ int perf_session_queue_event(struct perf_session *s, union perf_event *event,
 		pr_oe_time(oe->last_flush, "last flush, last_flush_type %d\n",
 			   oe->last_flush_type);
 
-		s->stats.nr_unordered_events++;
+		s->evlist->stats.nr_unordered_events++;
 	}
 
 	new = ordered_events__new(oe, timestamp, event);
@@ -688,14 +688,14 @@ static void stack_user__printf(struct stack_dump *dump)
 	       dump->size, dump->offset);
 }
 
-static void perf_session__print_tstamp(struct perf_session *session,
+static void perf_evlist__print_tstamp(struct perf_evlist *evlist,
 				       union perf_event *event,
 				       struct perf_sample *sample)
 {
-	u64 sample_type = __perf_evlist__combined_sample_type(session->evlist);
+	u64 sample_type = __perf_evlist__combined_sample_type(evlist);
 
 	if (event->header.type != PERF_RECORD_SAMPLE &&
-	    !perf_evlist__sample_id_all(session->evlist)) {
+	    !perf_evlist__sample_id_all(evlist)) {
 		fputs("-1 -1 ", stdout);
 		return;
 	}
@@ -737,7 +737,7 @@ static void sample_read__printf(struct perf_sample *sample, u64 read_format)
 			sample->read.one.id, sample->read.one.value);
 }
 
-static void dump_event(struct perf_session *session, union perf_event *event,
+static void dump_event(struct perf_evlist *evlist, union perf_event *event,
 		       u64 file_offset, struct perf_sample *sample)
 {
 	if (!dump_trace)
@@ -749,7 +749,7 @@ static void dump_event(struct perf_session *session, union perf_event *event,
 	trace_event(event);
 
 	if (sample)
-		perf_session__print_tstamp(session, event, sample);
+		perf_evlist__print_tstamp(evlist, event, sample);
 
 	printf("%#" PRIx64 " [%#x]: PERF_RECORD_%s", file_offset,
 	       event->header.size, perf_event__name(event->header.type));
@@ -797,8 +797,7 @@ static void dump_sample(struct perf_evsel *evsel, union perf_event *event,
 		sample_read__printf(sample, evsel->attr.read_format);
 }
 
-static struct machine *
+static struct machine *machines__find_for_cpumode(struct machines *machines,
-	perf_session__find_machine_for_cpumode(struct perf_session *session,
 					       union perf_event *event,
 					       struct perf_sample *sample)
 {
@@ -816,26 +815,24 @@ static struct machine *
 		else
 			pid = sample->pid;
 
-		machine = perf_session__find_machine(session, pid);
+		machine = machines__find(machines, pid);
 		if (!machine)
-			machine = perf_session__findnew_machine(session,
+			machine = machines__find(machines, DEFAULT_GUEST_KERNEL_ID);
-						DEFAULT_GUEST_KERNEL_ID);
 		return machine;
 	}
 
-	return &session->machines.host;
+	return &machines->host;
 }
 
-static int deliver_sample_value(struct perf_session *session,
+static int deliver_sample_value(struct perf_evlist *evlist,
 				struct perf_tool *tool,
 				union perf_event *event,
 				struct perf_sample *sample,
 				struct sample_read_value *v,
 				struct machine *machine)
 {
-	struct perf_sample_id *sid;
+	struct perf_sample_id *sid = perf_evlist__id2sid(evlist, v->id);
 
-	sid = perf_evlist__id2sid(session->evlist, v->id);
 	if (sid) {
 		sample->id     = v->id;
 		sample->period = v->value - sid->period;
@@ -843,14 +840,14 @@ static int deliver_sample_value(struct perf_session *session,
 	}
 
 	if (!sid || sid->evsel == NULL) {
-		++session->stats.nr_unknown_id;
+		++evlist->stats.nr_unknown_id;
 		return 0;
 	}
 
 	return tool->sample(tool, event, sample, sid->evsel, machine);
 }
 
-static int deliver_sample_group(struct perf_session *session,
+static int deliver_sample_group(struct perf_evlist *evlist,
 				struct perf_tool *tool,
 				union  perf_event *event,
 				struct perf_sample *sample,
@@ -860,7 +857,7 @@ static int deliver_sample_group(struct perf_session *session,
 	u64 i;
 
 	for (i = 0; i < sample->read.group.nr; i++) {
-		ret = deliver_sample_value(session, tool, event, sample,
+		ret = deliver_sample_value(evlist, tool, event, sample,
 					   &sample->read.group.values[i],
 					   machine);
 		if (ret)
@@ -871,7 +868,7 @@ static int deliver_sample_group(struct perf_session *session,
 }
 
 static int
-perf_session__deliver_sample(struct perf_session *session,
+ perf_evlist__deliver_sample(struct perf_evlist *evlist,
 			     struct perf_tool *tool,
 			     union  perf_event *event,
 			     struct perf_sample *sample,
@@ -888,10 +885,10 @@ perf_session__deliver_sample(struct perf_session *session,
 
 	/* For PERF_SAMPLE_READ we have either single or group mode. */
 	if (read_format & PERF_FORMAT_GROUP)
-		return deliver_sample_group(session, tool, event, sample,
+		return deliver_sample_group(evlist, tool, event, sample,
 					    machine);
 	else
-		return deliver_sample_value(session, tool, event, sample,
+		return deliver_sample_value(evlist, tool, event, sample,
 					    &sample->read.one, machine);
 }
 
@@ -900,29 +897,28 @@ int perf_session__deliver_event(struct perf_session *session,
 				struct perf_sample *sample,
 				struct perf_tool *tool, u64 file_offset)
 {
+	struct perf_evlist *evlist = session->evlist;
 	struct perf_evsel *evsel;
 	struct machine *machine;
 
-	dump_event(session, event, file_offset, sample);
+	dump_event(evlist, event, file_offset, sample);
 
-	evsel = perf_evlist__id2evsel(session->evlist, sample->id);
+	evsel = perf_evlist__id2evsel(evlist, sample->id);
 
-	machine = perf_session__find_machine_for_cpumode(session, event,
+	machine = machines__find_for_cpumode(&session->machines, event, sample);
-							 sample);
 
 	switch (event->header.type) {
 	case PERF_RECORD_SAMPLE:
 		dump_sample(evsel, event, sample);
 		if (evsel == NULL) {
-			++session->stats.nr_unknown_id;
+			++evlist->stats.nr_unknown_id;
 			return 0;
 		}
 		if (machine == NULL) {
-			++session->stats.nr_unprocessable_samples;
+			++evlist->stats.nr_unprocessable_samples;
 			return 0;
 		}
-		return perf_session__deliver_sample(session, tool, event,
+		return perf_evlist__deliver_sample(evlist, tool, event, sample, evsel, machine);
-						    sample, evsel, machine);
 	case PERF_RECORD_MMAP:
 		return tool->mmap(tool, event, sample, machine);
 	case PERF_RECORD_MMAP2:
@@ -935,7 +931,7 @@ int perf_session__deliver_event(struct perf_session *session,
 		return tool->exit(tool, event, sample, machine);
 	case PERF_RECORD_LOST:
 		if (tool->lost == perf_event__process_lost)
-			session->stats.total_lost += event->lost.lost;
+			evlist->stats.total_lost += event->lost.lost;
 		return tool->lost(tool, event, sample, machine);
 	case PERF_RECORD_READ:
 		return tool->read(tool, event, sample, evsel, machine);
@@ -944,7 +940,7 @@ int perf_session__deliver_event(struct perf_session *session,
 	case PERF_RECORD_UNTHROTTLE:
 		return tool->unthrottle(tool, event, sample, machine);
 	default:
-		++session->stats.nr_unknown_events;
+		++evlist->stats.nr_unknown_events;
 		return -1;
 	}
 }
@@ -957,7 +953,7 @@ static s64 perf_session__process_user_event(struct perf_session *session,
 	int fd = perf_data_file__fd(session->file);
 	int err;
 
-	dump_event(session, event, file_offset, NULL);
+	dump_event(session->evlist, event, file_offset, NULL);
 
 	/* These events are processed right away */
 	switch (event->header.type) {
@@ -994,7 +990,7 @@ int perf_session__deliver_synth_event(struct perf_session *session,
 				      struct perf_sample *sample,
 				      struct perf_tool *tool)
 {
-	events_stats__inc(&session->stats, event->header.type);
+	events_stats__inc(&session->evlist->stats, event->header.type);
 
 	if (event->header.type >= PERF_RECORD_USER_TYPE_START)
 		return perf_session__process_user_event(session, event, tool, 0);
@@ -1071,16 +1067,17 @@ static s64 perf_session__process_event(struct perf_session *session,
 				       struct perf_tool *tool,
 				       u64 file_offset)
 {
+	struct perf_evlist *evlist = session->evlist;
 	struct perf_sample sample;
 	int ret;
 
 	if (session->header.needs_swap)
-		event_swap(event, perf_evlist__sample_id_all(session->evlist));
+		event_swap(event, perf_evlist__sample_id_all(evlist));
 
 	if (event->header.type >= PERF_RECORD_HEADER_MAX)
 		return -EINVAL;
 
-	events_stats__inc(&session->stats, event->header.type);
+	events_stats__inc(&evlist->stats, event->header.type);
 
 	if (event->header.type >= PERF_RECORD_USER_TYPE_START)
 		return perf_session__process_user_event(session, event, tool, file_offset);
@@ -1088,7 +1085,7 @@ static s64 perf_session__process_event(struct perf_session *session,
 	/*
 	 * For all kernel events we get the sample data
 	 */
-	ret = perf_evlist__parse_sample(session->evlist, event, &sample);
+	ret = perf_evlist__parse_sample(evlist, event, &sample);
 	if (ret)
 		return ret;
 
@@ -1128,47 +1125,47 @@ static struct thread *perf_session__register_idle_thread(struct perf_session *se
 	return thread;
 }
 
-static void perf_session__warn_about_errors(const struct perf_session *session,
+static void perf_tool__warn_about_errors(const struct perf_tool *tool,
-					    const struct perf_tool *tool)
+					 const struct events_stats *stats)
 {
 	if (tool->lost == perf_event__process_lost &&
-	    session->stats.nr_events[PERF_RECORD_LOST] != 0) {
+	    stats->nr_events[PERF_RECORD_LOST] != 0) {
 		ui__warning("Processed %d events and lost %d chunks!\n\n"
 			    "Check IO/CPU overload!\n\n",
-			    session->stats.nr_events[0],
+			    stats->nr_events[0],
-			    session->stats.nr_events[PERF_RECORD_LOST]);
+			    stats->nr_events[PERF_RECORD_LOST]);
 	}
 
-	if (session->stats.nr_unknown_events != 0) {
+	if (stats->nr_unknown_events != 0) {
 		ui__warning("Found %u unknown events!\n\n"
 			    "Is this an older tool processing a perf.data "
 			    "file generated by a more recent tool?\n\n"
 			    "If that is not the case, consider "
 			    "reporting to linux-kernel@vger.kernel.org.\n\n",
-			    session->stats.nr_unknown_events);
+			    stats->nr_unknown_events);
 	}
 
-	if (session->stats.nr_unknown_id != 0) {
+	if (stats->nr_unknown_id != 0) {
 		ui__warning("%u samples with id not present in the header\n",
-			    session->stats.nr_unknown_id);
+			    stats->nr_unknown_id);
 	}
 
- 	if (session->stats.nr_invalid_chains != 0) {
+	if (stats->nr_invalid_chains != 0) {
- 		ui__warning("Found invalid callchains!\n\n"
+		ui__warning("Found invalid callchains!\n\n"
- 			    "%u out of %u events were discarded for this reason.\n\n"
+			    "%u out of %u events were discarded for this reason.\n\n"
- 			    "Consider reporting to linux-kernel@vger.kernel.org.\n\n",
+			    "Consider reporting to linux-kernel@vger.kernel.org.\n\n",
- 			    session->stats.nr_invalid_chains,
+			    stats->nr_invalid_chains,
- 			    session->stats.nr_events[PERF_RECORD_SAMPLE]);
+			    stats->nr_events[PERF_RECORD_SAMPLE]);
- 	}
+	}
 
-	if (session->stats.nr_unprocessable_samples != 0) {
+	if (stats->nr_unprocessable_samples != 0) {
 		ui__warning("%u unprocessable samples recorded.\n"
 			    "Do you have a KVM guest running and not using 'perf kvm'?\n",
-			    session->stats.nr_unprocessable_samples);
+			    stats->nr_unprocessable_samples);
 	}
 
-	if (session->stats.nr_unordered_events != 0)
+	if (stats->nr_unordered_events != 0)
-		ui__warning("%u out of order events recorded.\n", session->stats.nr_unordered_events);
+		ui__warning("%u out of order events recorded.\n", stats->nr_unordered_events);
 }
 
 volatile int session_done;
@@ -1258,7 +1255,7 @@ done:
 	err = ordered_events__flush(session, tool, OE_FLUSH__FINAL);
 out_err:
 	free(buf);
-	perf_session__warn_about_errors(session, tool);
+	perf_tool__warn_about_errors(tool, &session->evlist->stats);
 	ordered_events__free(&session->ordered_events);
 	return err;
 }
@@ -1403,7 +1400,7 @@ out:
 	err = ordered_events__flush(session, tool, OE_FLUSH__FINAL);
 out_err:
 	ui_progress__finish();
-	perf_session__warn_about_errors(session, tool);
+	perf_tool__warn_about_errors(tool, &session->evlist->stats);
 	ordered_events__free(&session->ordered_events);
 	session->one_mmap = false;
 	return err;
@@ -1488,7 +1485,7 @@ size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp)
 {
 	size_t ret = fprintf(fp, "Aggregated stats:\n");
 
-	ret += events_stats__fprintf(&session->stats, fp);
+	ret += events_stats__fprintf(&session->evlist->stats, fp);
 	return ret;
 }
 

tools/perf/util/session.h

@@ -20,7 +20,6 @@ struct perf_session {
 	struct machines		machines;
 	struct perf_evlist	*evlist;
 	struct trace_event	tevent;
-	struct events_stats	stats;
 	bool			repipe;
 	bool			one_mmap;
 	void			*one_mmap_addr;

tools/perf/util/util.c

@@ -269,6 +269,13 @@ void dump_stack(void)
 void dump_stack(void) {}
 #endif
 
+void sighandler_dump_stack(int sig)
+{
+	psignal(sig, "perf");
+	dump_stack();
+	exit(sig);
+}
+
 void get_term_dimensions(struct winsize *ws)
 {
 	char *s = getenv("LINES");

tools/perf/util/util.h

@@ -277,6 +277,7 @@ char *ltrim(char *s);
 char *rtrim(char *s);
 
 void dump_stack(void);
+void sighandler_dump_stack(int sig);
 
 extern unsigned int page_size;
 extern int cacheline_size;