perf: add perf-inject builtin

Currently, perf 'live mode' writes build-ids at the end of the
session, which isn't actually useful for processing live mode events.

What would be better would be to have the build-ids sent before any of
the samples that reference them, which can be done by processing the
event stream and retrieving the build-ids on the first hit.  Doing
that in perf-record itself, however, is off-limits.

This patch introduces perf-inject, which does the same job while
leaving perf-record untouched.  Normal mode perf still records the
build-ids at the end of the session as it should, but for live mode,
perf-inject can be injected in between the record and report steps
e.g.:

perf record -o - ./hackbench 10 | perf inject -v -b | perf report -v -i -

perf-inject reads a perf-record event stream and repipes it to stdout.
At any point the processing code can inject other events into the
event stream - in this case build-ids (-b option) are read and
injected as needed into the event stream.

Build-ids are just the first user of perf-inject - potentially
anything that needs userspace processing to augment the trace stream
with additional information could make use of this facility.

Cc: Ingo Molnar <mingo@elte.hu>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Frédéric Weisbecker <fweisbec@gmail.com>
LKML-Reference: <1272696080-16435-3-git-send-email-tzanussi@gmail.com>
Signed-off-by: Tom Zanussi <tzanussi@gmail.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
new file mode 100644
index 0000000..a5902a3
--- /dev/null
+++ b/tools/perf/builtin-inject.c
@@ -0,0 +1,228 @@
+/*
+ * builtin-inject.c
+ *
+ * Builtin inject command: Examine the live mode (stdin) event stream
+ * and repipe it to stdout while optionally injecting additional
+ * events into it.
+ */
+#include "builtin.h"
+
+#include "perf.h"
+#include "util/session.h"
+#include "util/debug.h"
+
+#include "util/parse-options.h"
+
+static char		const *input_name = "-";
+static bool		inject_build_ids;
+
+static int event__repipe(event_t *event __used,
+			 struct perf_session *session __used)
+{
+	uint32_t size;
+	void *buf = event;
+
+	size = event->header.size;
+
+	while (size) {
+		int ret = write(STDOUT_FILENO, buf, size);
+		if (ret < 0)
+			return -errno;
+
+		size -= ret;
+		buf += ret;
+	}
+
+	return 0;
+}
+
+static int event__repipe_mmap(event_t *self, struct perf_session *session)
+{
+	int err;
+
+	err = event__process_mmap(self, session);
+	event__repipe(self, session);
+
+	return err;
+}
+
+static int event__repipe_task(event_t *self, struct perf_session *session)
+{
+	int err;
+
+	err = event__process_task(self, session);
+	event__repipe(self, session);
+
+	return err;
+}
+
+static int event__repipe_tracing_data(event_t *self,
+				      struct perf_session *session)
+{
+	int err;
+
+	event__repipe(self, session);
+	err = event__process_tracing_data(self, session);
+
+	return err;
+}
+
+static int read_buildid(struct map *self, struct perf_session *session)
+{
+	const char *name = self->dso->long_name;
+	int err;
+
+	if (filename__read_build_id(self->dso->long_name, self->dso->build_id,
+				    sizeof(self->dso->build_id)) > 0) {
+		char sbuild_id[BUILD_ID_SIZE * 2 + 1];
+
+		self->dso->has_build_id = true;
+
+		build_id__sprintf(self->dso->build_id,
+				  sizeof(self->dso->build_id),
+				  sbuild_id);
+		pr_debug("build id found for %s: %s\n", self->dso->long_name,
+			 sbuild_id);
+	}
+
+	if (self->dso->has_build_id) {
+		u16 misc = PERF_RECORD_MISC_USER;
+		struct machine *machine;
+
+		misc = self->dso->kernel ? PERF_RECORD_MISC_KERNEL : misc;
+
+		machine = perf_session__find_host_machine(session);
+		if (!machine) {
+			pr_err("Can't find machine for session\n");
+			return -1;
+		}
+
+		err = event__synthesize_build_id(self->dso, misc,
+						 event__repipe, machine,
+						 session);
+		if (err) {
+			pr_err("Can't synthesize build_id event for %s\n",
+			       name);
+			return -1;
+		}
+	} else {
+		pr_debug("no build_id found for %s\n", name);
+		return -1;
+	}
+
+	return 0;
+}
+
+static int event__inject_buildid(event_t *event, struct perf_session *session)
+{
+	struct addr_location al;
+	struct thread *thread;
+	u8 cpumode;
+	int err = 0;
+
+	cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+
+	thread = perf_session__findnew(session, event->ip.pid);
+	if (thread == NULL) {
+		pr_err("problem processing %d event, skipping it.\n",
+		       event->header.type);
+		err = -1;
+		goto repipe;
+	}
+
+	thread__find_addr_map(thread, session, cpumode, MAP__FUNCTION,
+			      event->ip.pid, event->ip.ip, &al);
+
+	if (al.map != NULL) {
+		if (!al.map->dso->hit) {
+			al.map->dso->hit = 1;
+			if (map__load(al.map, NULL) >= 0)
+				read_buildid(al.map, session);
+			else
+				pr_warning("no symbols found in %s, maybe "
+					   "install a debug package?\n",
+					   al.map->dso->long_name);
+		}
+	}
+
+repipe:
+	event__repipe(event, session);
+	return err;
+}
+
+struct perf_event_ops inject_ops = {
+	.sample		= event__repipe,
+	.mmap		= event__repipe,
+	.comm		= event__repipe,
+	.fork		= event__repipe,
+	.exit		= event__repipe,
+	.lost		= event__repipe,
+	.read		= event__repipe,
+	.throttle	= event__repipe,
+	.unthrottle	= event__repipe,
+	.attr		= event__repipe,
+	.event_type 	= event__repipe,
+	.tracing_data 	= event__repipe,
+	.build_id 	= event__repipe,
+};
+
+extern volatile int session_done;
+
+static void sig_handler(int sig __attribute__((__unused__)))
+{
+	session_done = 1;
+}
+
+static int __cmd_inject(void)
+{
+	struct perf_session *session;
+	int ret = -EINVAL;
+
+	signal(SIGINT, sig_handler);
+
+	if (inject_build_ids) {
+		inject_ops.sample	= event__inject_buildid;
+		inject_ops.mmap		= event__repipe_mmap;
+		inject_ops.fork		= event__repipe_task;
+		inject_ops.tracing_data	= event__repipe_tracing_data;
+	}
+
+	session = perf_session__new(input_name, O_RDONLY, false, true);
+	if (session == NULL)
+		return -ENOMEM;
+
+	ret = perf_session__process_events(session, &inject_ops);
+
+	perf_session__delete(session);
+
+	return ret;
+}
+
+static const char * const report_usage[] = {
+	"perf inject [<options>]",
+	NULL
+};
+
+static const struct option options[] = {
+	OPT_BOOLEAN('b', "inject build-ids", &inject_build_ids,
+		    "Inject build-ids into the output stream"),
+	OPT_INCR('v', "verbose", &verbose,
+		 "be more verbose (show build ids, etc)"),
+	OPT_END()
+};
+
+int cmd_inject(int argc, const char **argv, const char *prefix __used)
+{
+	argc = parse_options(argc, argv, options, report_usage, 0);
+
+	/*
+	 * Any (unrecognized) arguments left?
+	 */
+	if (argc)
+		usage_with_options(report_usage, options);
+
+	if (symbol__init() < 0)
+		return -1;
+
+	return __cmd_inject();
+}