perf inject: Add --buildid-all option

Like 'perf record', we can even more speedup build-id processing by just
using all DSOs.  Then we don't need to look at all the sample events
anymore.  The following patch will update 'perf bench' to show the result
of the --buildid-all option too.
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Original-patch-by: Stephane Eranian <eranian@google.com>
Acked-by: Ian Rogers <irogers@google.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Link: https://lore.kernel.org/r/20201012070214.2074921-6-namhyung@kernel.orgSigned-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/Documentation/perf-inject.txt

@@ -24,8 +24,12 @@ information could make use of this facility.
 OPTIONS
 -------
 -b::
---build-ids=::
+--build-ids::
         Inject build-ids into the output stream
+
+--buildid-all:
+	Inject build-ids of all DSOs into the output stream
+
 -v::
 --verbose::
 	Be more verbose.

tools/perf/builtin-inject.c

@@ -10,6 +10,7 @@
 
 #include "util/color.h"
 #include "util/dso.h"
+#include "util/vdso.h"
 #include "util/evlist.h"
 #include "util/evsel.h"
 #include "util/map.h"
@@ -37,6 +38,7 @@ struct perf_inject {
 	struct perf_tool	tool;
 	struct perf_session	*session;
 	bool			build_ids;
+	bool			build_id_all;
 	bool			sched_stat;
 	bool			have_auxtrace;
 	bool			strip;
@@ -56,6 +58,9 @@ struct event_entry {
 	union perf_event event[];
 };
 
+static int dso__inject_build_id(struct dso *dso, struct perf_tool *tool,
+				struct machine *machine, u8 cpumode, u32 flags);
+
 static int output_bytes(struct perf_inject *inject, void *buf, size_t sz)
 {
 	ssize_t size;
@@ -319,6 +324,68 @@ static int perf_event__jit_repipe_mmap(struct perf_tool *tool,
 }
 #endif
 
+static struct dso *findnew_dso(int pid, int tid, const char *filename,
+			       struct dso_id *id, struct machine *machine)
+{
+	struct thread *thread;
+	struct nsinfo *nsi = NULL;
+	struct nsinfo *nnsi;
+	struct dso *dso;
+	bool vdso;
+
+	thread = machine__findnew_thread(machine, pid, tid);
+	if (thread == NULL) {
+		pr_err("cannot find or create a task %d/%d.\n", tid, pid);
+		return NULL;
+	}
+
+	vdso = is_vdso_map(filename);
+	nsi = nsinfo__get(thread->nsinfo);
+
+	if (vdso) {
+		/* The vdso maps are always on the host and not the
+		 * container.  Ensure that we don't use setns to look
+		 * them up.
+		 */
+		nnsi = nsinfo__copy(nsi);
+		if (nnsi) {
+			nsinfo__put(nsi);
+			nnsi->need_setns = false;
+			nsi = nnsi;
+		}
+		dso = machine__findnew_vdso(machine, thread);
+	} else {
+		dso = machine__findnew_dso_id(machine, filename, id);
+	}
+
+	if (dso)
+		dso->nsinfo = nsi;
+	else
+		nsinfo__put(nsi);
+
+	thread__put(thread);
+	return dso;
+}
+
+static int perf_event__repipe_buildid_mmap(struct perf_tool *tool,
+					   union perf_event *event,
+					   struct perf_sample *sample,
+					   struct machine *machine)
+{
+	struct dso *dso;
+
+	dso = findnew_dso(event->mmap.pid, event->mmap.tid,
+			  event->mmap.filename, NULL, machine);
+
+	if (dso && !dso->hit) {
+		dso->hit = 1;
+		dso__inject_build_id(dso, tool, machine, sample->cpumode, 0);
+		dso__put(dso);
+	}
+
+	return perf_event__repipe(tool, event, sample, machine);
+}
+
 static int perf_event__repipe_mmap2(struct perf_tool *tool,
 				   union perf_event *event,
 				   struct perf_sample *sample,
@@ -357,6 +424,34 @@ static int perf_event__jit_repipe_mmap2(struct perf_tool *tool,
 }
 #endif
 
+static int perf_event__repipe_buildid_mmap2(struct perf_tool *tool,
+					    union perf_event *event,
+					    struct perf_sample *sample,
+					    struct machine *machine)
+{
+	struct dso_id dso_id = {
+		.maj = event->mmap2.maj,
+		.min = event->mmap2.min,
+		.ino = event->mmap2.ino,
+		.ino_generation = event->mmap2.ino_generation,
+	};
+	struct dso *dso;
+
+	dso = findnew_dso(event->mmap2.pid, event->mmap2.tid,
+			  event->mmap2.filename, &dso_id, machine);
+
+	if (dso && !dso->hit) {
+		dso->hit = 1;
+		dso__inject_build_id(dso, tool, machine, sample->cpumode,
+				     event->mmap2.flags);
+		dso__put(dso);
+	}
+
+	perf_event__repipe(tool, event, sample, machine);
+
+	return 0;
+}
+
 static int perf_event__repipe_fork(struct perf_tool *tool,
 				   union perf_event *event,
 				   struct perf_sample *sample,
@@ -614,7 +709,7 @@ static int __cmd_inject(struct perf_inject *inject)
 	signal(SIGINT, sig_handler);
 
 	if (inject->build_ids || inject->sched_stat ||
-	    inject->itrace_synth_opts.set) {
+	    inject->itrace_synth_opts.set || inject->build_id_all) {
 		inject->tool.mmap	  = perf_event__repipe_mmap;
 		inject->tool.mmap2	  = perf_event__repipe_mmap2;
 		inject->tool.fork	  = perf_event__repipe_fork;
@@ -623,7 +718,10 @@ static int __cmd_inject(struct perf_inject *inject)
 
 	output_data_offset = session->header.data_offset;
 
-	if (inject->build_ids) {
+	if (inject->build_id_all) {
+		inject->tool.mmap	  = perf_event__repipe_buildid_mmap;
+		inject->tool.mmap2	  = perf_event__repipe_buildid_mmap2;
+	} else if (inject->build_ids) {
 		inject->tool.sample = perf_event__inject_buildid;
 	} else if (inject->sched_stat) {
 		struct evsel *evsel;
@@ -767,6 +865,8 @@ int cmd_inject(int argc, const char **argv)
 	struct option options[] = {
 		OPT_BOOLEAN('b', "build-ids", &inject.build_ids,
 			    "Inject build-ids into the output stream"),
+		OPT_BOOLEAN(0, "buildid-all", &inject.build_id_all,
+			    "Inject build-ids of all DSOs into the output stream"),
 		OPT_STRING('i', "input", &inject.input_name, "file",
 			   "input file name"),
 		OPT_STRING('o', "output", &inject.output.path, "file",
@@ -815,8 +915,6 @@ int cmd_inject(int argc, const char **argv)
 		return -1;
 	}
 
-	inject.tool.ordered_events = inject.sched_stat;
-
 	data.path = inject.input_name;
 	inject.session = perf_session__new(&data, true, &inject.tool);
 	if (IS_ERR(inject.session))
@@ -825,7 +923,7 @@ int cmd_inject(int argc, const char **argv)
 	if (zstd_init(&(inject.session->zstd_data), 0) < 0)
 		pr_warning("Decompression initialization failed.\n");
 
-	if (inject.build_ids) {
+	if (inject.build_ids && !inject.build_id_all) {
 		/*
 		 * to make sure the mmap records are ordered correctly
 		 * and so that the correct especially due to jitted code
@@ -835,6 +933,11 @@ int cmd_inject(int argc, const char **argv)
 		inject.tool.ordered_events = true;
 		inject.tool.ordering_requires_timestamps = true;
 	}
+
+	if (inject.sched_stat) {
+		inject.tool.ordered_events = true;
+	}
+
 #ifdef HAVE_JITDUMP
 	if (inject.jit_mode) {
 		inject.tool.mmap2	   = perf_event__jit_repipe_mmap2;