Merge tag 'perf-tools-for-v5.15-2021-09-04' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull perf tool updates from Arnaldo Carvalho de Melo:
 "New features:

   - Improvements for the flamegraph python script, including:
       - Display perf.data header
       - Display PIDs of user stacks
       - Added option to change color scheme
       - Default to blue/green color scheme to improve accessibility
       - Correctly identify kernel stacks when debuginfo is available

   - Improvements for 'perf bench futex':
       - Add --mlockall parameter
       - Add --broadcast and --pi to the 'requeue' sub benchmark

   - Add support for PMU aliases.

   - Introduce an ARM Coresight ETE decoder.

   - Add a 'perf bench' entry for evlist open/close operations, to help
     quantify improvements with multithreading 'perf record'.

   - Allow reporting the [un]throttle PERF_RECORD_ meta event in 'perf
     script's python scripting.

   - Add a 'perf test' entry for PMU aliases.

   - Add a 'perf test' entry for 'perf record/perf report/perf script'
     pipe mode.

  Fixes:

   - perf script dlfilter (API for filtering via dynamically loaded
     shared object introduced in v5.14) fixes and a 'perf test' entry
     for it.

   - Fix get_current_dir_name() compilation on Android.

   - Fix issues with asciidoc and double dashes uses.

   - Fix memory leaks in the BTF handling code.

   - Fix leftover problems in the Documentation from the infrastructure
     originally lifted from the git codebase.

   - Fix *probe_vfs_getname.sh 'perf test' failures.

   - Handle fd gaps in 'perf test's test__dso_data_reopen().

   - Make sure to show disasembly warnings for 'perf annotate --stdio'.

   - Fix output from pipe to file and vice-versa in 'perf
     record/report/script'.

   - Correct 'perf data -h' output.

   - Fix wrong comm in system-wide mode with 'perf record --delay'.

   - Do not allow --for-each-cgroup without cpu in 'perf stat'

   - Make 'perf test --skip' work on shell tests.

   - Fix libperf's verbose printing.

  Misc improvements:

   - Preparatory patches for multithreading various 'perf record' phases
     (synthesizing, opening, recording, etc).

   - Add sparse context/locking annotations in compiler-types.h, also to
     help with the multithreading effort.

   - Optimize the generation of the arch specific erno tables used in
     'perf trace'.

   - Optimize libperf's perf_cpu_map__max().

   - Improve ARM's CoreSight warnings.

   - Report collisions in AUX records.

   - Improve warnings for the LLVM 'perf test' entry.

   - Improve the PMU events 'perf test' codebase.

   - perf test: Do not compare overheads in the zstd comp test

   - Better support annotation on ARM.

   - Update 'perf trace's cmd string table to decode sys_bpf() first
     arg.

  Vendor events:

   - Add JSON events and metrics for Intel's Ice Lake, Tiger Lake and
     Elhart Lake.

   - Update JSON eventsand metrics for Intel's Cascade Lake and Sky Lake
     servers.

  Hardware tracing:

   - Improvements for the ARM hardware tracing auxtrace support"

* tag 'perf-tools-for-v5.15-2021-09-04' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux: (130 commits)
  perf tests: Add test for PMU aliases
  perf pmu: Add PMU alias support
  perf session: Report collisions in AUX records
  perf script python: Allow reporting the [un]throttle PERF_RECORD_ meta event
  perf build: Report failure for testing feature libopencsd
  perf cs-etm: Show a warning for an unknown magic number
  perf cs-etm: Print the decoder name
  perf cs-etm: Create ETE decoder
  perf cs-etm: Update OpenCSD decoder for ETE
  perf cs-etm: Fix typo
  perf cs-etm: Save TRCDEVARCH register
  perf cs-etm: Refactor out ETMv4 header saving
  perf cs-etm: Initialise architecture based on TRCIDR1
  perf cs-etm: Refactor initialisation of decoder params.
  tools build: Fix feature detect clean for out of source builds
  perf evlist: Add evlist__for_each_entry_from() macro
  perf evsel: Handle precise_ip fallback in evsel__open_cpu()
  perf evsel: Move bpf_counter__install_pe() to success path in evsel__open_cpu()
  perf evsel: Move test_attr__open() to success path in evsel__open_cpu()
  perf evsel: Move ignore_missing_thread() to fallback code
  ...

1 files changed, 34 insertions, 4 deletions

diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index c88c61e7f8cc..6ad191e731fc 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -46,6 +46,7 @@ struct perf_inject {
 	bool			jit_mode;
 	bool			in_place_update;
 	bool			in_place_update_dry_run;
+	bool			is_pipe;
 	const char		*input_name;
 	struct perf_data	output;
 	u64			bytes_written;
@@ -126,7 +127,7 @@ static int perf_event__repipe_attr(struct perf_tool *tool,
 	if (ret)
 		return ret;
 
-	if (!inject->output.is_pipe)
+	if (!inject->is_pipe)
 		return 0;
 
 	return perf_event__repipe_synth(tool, event);
@@ -826,14 +827,14 @@ static int __cmd_inject(struct perf_inject *inject)
 	if (!inject->itrace_synth_opts.set)
 		auxtrace_index__free(&session->auxtrace_index);
 
-	if (!data_out->is_pipe && !inject->in_place_update)
+	if (!inject->is_pipe && !inject->in_place_update)
 		lseek(fd, output_data_offset, SEEK_SET);
 
 	ret = perf_session__process_events(session);
 	if (ret)
 		return ret;
 
-	if (!data_out->is_pipe && !inject->in_place_update) {
+	if (!inject->is_pipe && !inject->in_place_update) {
 		if (inject->build_ids)
 			perf_header__set_feat(&session->header,
 					      HEADER_BUILD_ID);
@@ -918,6 +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,
@@ -992,7 +994,20 @@ int cmd_inject(int argc, const char **argv)
 	}
 
 	data.path = inject.input_name;
-	inject.session = perf_session__new(&data, inject.output.is_pipe, &inject.tool);
+	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, repipe,
+					     perf_data__fd(&inject.output),
+					     &inject.tool);
 	if (IS_ERR(inject.session)) {
 		ret = PTR_ERR(inject.session);
 		goto out_close_output;
@@ -1001,6 +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