perf inject: Fix output from a file to a pipe

When the input is a regular file but the output is a pipe, it should
write a pipe header.  But just repiping would write a portion of the
existing header which is different in 'size' value.  So we need to
prevent it and write a new pipe header along with other information
like event attributes and features.

This can handle something like this:

  # perf record -a -B sleep 1

  # perf inject -b -i perf.data | perf report -i -

Factor out perf_event__synthesize_for_pipe() to be shared between perf
record and inject.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/20210719223153.1618812-5-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/builtin-inject.c

@@ -919,6 +919,7 @@ int cmd_inject(int argc, const char **argv)
 		.use_stdio = true,
 	};
 	int ret;
+	bool repipe = true;
 
 	struct option options[] = {
 		OPT_BOOLEAN('b', "build-ids", &inject.build_ids,
@@ -993,10 +994,18 @@ int cmd_inject(int argc, const char **argv)
 	}
 
 	data.path = inject.input_name;
-	if (!strcmp(inject.input_name, "-") || inject.output.is_pipe)
+	if (!strcmp(inject.input_name, "-") || inject.output.is_pipe) {
 		inject.is_pipe = true;
+		/*
+		 * Do not repipe header when input is a regular file
+		 * since either it can rewrite the header at the end
+		 * or write a new pipe header.
+		 */
+		if (strcmp(inject.input_name, "-"))
+			repipe = false;
+	}
 
-	inject.session = __perf_session__new(&data, inject.is_pipe,
+	inject.session = __perf_session__new(&data, repipe,
 					     perf_data__fd(&inject.output),
 					     &inject.tool);
 	if (IS_ERR(inject.session)) {
@@ -1007,6 +1016,21 @@ int cmd_inject(int argc, const char **argv)
 	if (zstd_init(&(inject.session->zstd_data), 0) < 0)
 		pr_warning("Decompression initialization failed.\n");
 
+	if (!data.is_pipe && inject.output.is_pipe) {
+		ret = perf_header__write_pipe(perf_data__fd(&inject.output));
+		if (ret < 0) {
+			pr_err("Couldn't write a new pipe header.\n");
+			goto out_delete;
+		}
+
+		ret = perf_event__synthesize_for_pipe(&inject.tool,
+						      inject.session,
+						      &inject.output,
+						      perf_event__repipe);
+		if (ret < 0)
+			goto out_delete;
+	}
+
 	if (inject.build_ids && !inject.build_id_all) {
 		/*
 		 * to make sure the mmap records are ordered correctly

tools/perf/builtin-record.c

@@ -1387,7 +1387,6 @@ static int record__synthesize(struct record *rec, bool tail)
 	struct perf_data *data = &rec->data;
 	struct record_opts *opts = &rec->opts;
 	struct perf_tool *tool = &rec->tool;
-	int fd = perf_data__fd(data);
 	int err = 0;
 	event_op f = process_synthesized_event;
 
@@ -1395,41 +1394,12 @@ static int record__synthesize(struct record *rec, bool tail)
 		return 0;
 
 	if (data->is_pipe) {
-		/*
-		 * We need to synthesize events first, because some
-		 * features works on top of them (on report side).
-		 */
-		err = perf_event__synthesize_attrs(tool, rec->evlist,
-						   process_synthesized_event);
-		if (err < 0) {
-			pr_err("Couldn't synthesize attrs.\n");
-			goto out;
-		}
-
-		err = perf_event__synthesize_features(tool, session, rec->evlist,
+		err = perf_event__synthesize_for_pipe(tool, session, data,
 						      process_synthesized_event);
-		if (err < 0) {
-			pr_err("Couldn't synthesize features.\n");
-			return err;
-		}
+		if (err < 0)
+			goto out;
 
-		if (have_tracepoints(&rec->evlist->core.entries)) {
-			/*
-			 * FIXME err <= 0 here actually means that
-			 * there were no tracepoints so its not really
-			 * an error, just that we don't need to
-			 * synthesize anything.  We really have to
-			 * return this more properly and also
-			 * propagate errors that now are calling die()
-			 */
-			err = perf_event__synthesize_tracing_data(tool,	fd, rec->evlist,
-								  process_synthesized_event);
-			if (err <= 0) {
-				pr_err("Couldn't record tracing data.\n");
-				goto out;
-			}
-			rec->bytes_written += err;
-		}
+		rec->bytes_written += err;
 	}
 
 	err = perf_event__synth_time_conv(record__pick_pc(rec), tool,

tools/perf/util/synthetic-events.c

@@ -1,5 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0-only 
 
+#include "util/cgroup.h"
+#include "util/data.h"
 #include "util/debug.h"
 #include "util/dso.h"
 #include "util/event.h"
@@ -16,7 +18,6 @@
 #include "util/synthetic-events.h"
 #include "util/target.h"
 #include "util/time-utils.h"
-#include "util/cgroup.h"
 #include <linux/bitops.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
@@ -2179,3 +2180,53 @@ int perf_event__synthesize_features(struct perf_tool *tool, struct perf_session
 	free(ff.buf);
 	return ret;
 }
+
+int perf_event__synthesize_for_pipe(struct perf_tool *tool,
+				    struct perf_session *session,
+				    struct perf_data *data,
+				    perf_event__handler_t process)
+{
+	int err;
+	int ret = 0;
+	struct evlist *evlist = session->evlist;
+
+	/*
+	 * We need to synthesize events first, because some
+	 * features works on top of them (on report side).
+	 */
+	err = perf_event__synthesize_attrs(tool, evlist, process);
+	if (err < 0) {
+		pr_err("Couldn't synthesize attrs.\n");
+		return err;
+	}
+	ret += err;
+
+	err = perf_event__synthesize_features(tool, session, evlist, process);
+	if (err < 0) {
+		pr_err("Couldn't synthesize features.\n");
+		return err;
+	}
+	ret += err;
+
+	if (have_tracepoints(&evlist->core.entries)) {
+		int fd = perf_data__fd(data);
+
+		/*
+		 * FIXME err <= 0 here actually means that
+		 * there were no tracepoints so its not really
+		 * an error, just that we don't need to
+		 * synthesize anything.  We really have to
+		 * return this more properly and also
+		 * propagate errors that now are calling die()
+		 */
+		err = perf_event__synthesize_tracing_data(tool,	fd, evlist,
+							  process);
+		if (err <= 0) {
+			pr_err("Couldn't record tracing data.\n");
+			return err;
+		}
+		ret += err;
+	}
+
+	return ret;
+}

tools/perf/util/synthetic-events.h

@@ -14,6 +14,7 @@ struct evsel;
 struct machine;
 struct perf_counts_values;
 struct perf_cpu_map;
+struct perf_data;
 struct perf_event_attr;
 struct perf_event_mmap_page;
 struct perf_sample;
@@ -101,4 +102,9 @@ static inline int perf_event__synthesize_bpf_events(struct perf_session *session
 }
 #endif // HAVE_LIBBPF_SUPPORT
 
+int perf_event__synthesize_for_pipe(struct perf_tool *tool,
+				    struct perf_session *session,
+				    struct perf_data *data,
+				    perf_event__handler_t process);
+
 #endif // __PERF_SYNTHETIC_EVENTS_H