Merge tag 'perf-tools-for-v5.16-2021-11-07-without-bpftool-fix' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull perf tools updates from Arnaldo Carvalho de Melo:
 "perf annotate:
   - Add riscv64 support.
   - Add fusion logic for AMD microarchs.

  perf record:
   - Add an option to control the synthesizing behavior:
       --synth <no|all|task|mmap|cgroup>

  core:
   - Allow controlling synthesizing PERF_RECORD_ metadata events during
     record.
   - perf.data reader prep work for multithreaded processing.
   - Fix missing exclude_{host,guest} setting in PMUs that don't support
     it and that were causing the feature detection code to disable it
     for all events, even the ones in PMUs that support it.
   - Fix the default use of precise events on AMD, that were always
     falling back to non-precise because perf_event_attr.exclude_guest=1
     was set and IBS does not have filtering capability, refusing
     precise + exclude_guest.
   - Add bitfield_swap() to handle branch_stack endian issue.

  perf script:
   - Show binary offsets for userspace addresses in callchains.
   - Support instruction latency via new "ins_lat" selectable field.
   - Add dlfilter-show-cycles

  perf inject:
   - Add vmlinux and ignore-vmlinux arguments, similar to other tools.

  perf list:
   - Display PMU prefix for partially supported hybrid cache events.
   - Display hybrid PMU events with cpu type.

  perf stat:
   - Improve metrics documentation of data structures.
   - Fix memory leaks in the metric code.
   - Use NAN for missing event IDs.
   - Don't compute unused events.
   - Fix memory leak on error path.
   - Encode and use metric-id as a metric qualifier.
   - Allow metrics with no events.
   - Avoid events for an 'if' constant result.
   - Only add a referenced metric once.
   - Simplify metric_refs calculation.
   - Allow modifiers on metrics.

  perf test:
   - Add workload test of metric and metric groups.
   - Workload test of all PMUs.
   - vmlinux-kallsyms: Ignore hidden symbols.
   - Add pmu-event test for event described as "config=".
   - Verify more event members in pmu-events test.
   - Add endian test for struct branch_flags on the sample-parsing test.
   - Improve temp file cleanup in several tests.

  perf daemon:
   - Address MSAN warnings on send_cmd().

  perf kmem:
   - Improve man page for record options

  perf srcline:
   - Use long-running addr2line per DSO, greatly speeding up the
     'srcline' sort order.

  perf symbols:
   - Ignore $a/$d symbols for ARM modules.
   - Fix /proc/kcore access on 32 bit systems.

  Kernel UAPI copies:
   - Update copy of linux/socket.h with the kernel sources, no change in
     tooling output.

  libbpf:
   - Pull in bpf_program__get_prog_info_linear() from libbpf, too much
     specific to perf.
   - Deprecate bpf_map__resize() in favor of bpf_map_set_max_entries()
   - Install libbpf headers locally when building.
   - Bump minimum LLVM C++ std to GNU++14.

  libperf:
   - Use binary search in perf_cpu_map__idx() as array are sorted.

  libtracefs:
   - Enable libtracefs dynamic linking.

  libtraceevent:
   - Increase logging when verbose.

  Arch specific:

   * PowerPC:
      - Add support to expose instruction and data address registers as
        part of extended regs.

  Vendor events:

   * JSON parser:
      - Support ConfigCode to set the config= in PMUs
      - Make the JSON parser more conformant when in strict mode.

   * All JSON files:
      - Fix all remaining invalid JSON files.

   * ARM:
      - Syntax corrections in Neoverse N1 json.
      - Categorise the Neoverse V1 counters.
      - Add new armv8 PMU events.
      - Revise hip08 uncore events.

  Hardware tracing:

   * auxtrace:
      - Add missing Z option to ITRACE_HELP.
      - Add itrace A option to approximate IPC.
      - Add itrace d+o option to direct debug log to stdout.

   * Intel PT:
      - Add support for PERF_RECORD_AUX_OUTPUT_HW_ID
      - Support itrace A option to approximate IPC
      - Support itrace d+o option to direct debug log to stdout"

* tag 'perf-tools-for-v5.16-2021-11-07-without-bpftool-fix' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux: (120 commits)
  perf build: Install libbpf headers locally when building
  perf MANIFEST: Add bpftool files to allow building with BUILD_BPF_SKEL=1
  perf metric: Fix memory leaks
  perf parse-event: Add init and exit to parse_event_error
  perf parse-events: Rename parse_events_error functions
  perf stat: Fix memory leak on error path
  perf tools: Use __BYTE_ORDER__
  perf inject: Add vmlinux and ignore-vmlinux arguments
  perf tools: Check vmlinux/kallsyms arguments in all tools
  perf tools: Refactor out kernel symbol argument sanity checking
  perf symbols: Ignore $a/$d symbols for ARM modules
  perf evsel: Don't set exclude_guest by default
  perf evsel: Fix missing exclude_{host,guest} setting
  perf bpf: Add missing free to bpf_event__print_bpf_prog_info()
  perf beauty: Update copy of linux/socket.h with the kernel sources
  perf clang: Fixes for more recent LLVM/clang
  tools: Bump minimum LLVM C++ std to GNU++14
  perf bpf: Pull in bpf_program__get_prog_info_linear()
  Revert "perf bench futex: Add support for 32-bit systems with 64-bit time_t"
  perf test sample-parsing: Add endian test for struct branch_flags
  ...

1 files changed, 44 insertions, 8 deletions

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index b3509d9d20cc2..0338b813585aa 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -1255,6 +1255,7 @@ static int record__synthesize_workload(struct record *rec, bool tail)
 {
 	int err;
 	struct perf_thread_map *thread_map;
+	bool needs_mmap = rec->opts.synth & PERF_SYNTH_MMAP;
 
 	if (rec->opts.tail_synthesize != tail)
 		return 0;
@@ -1266,6 +1267,7 @@ static int record__synthesize_workload(struct record *rec, bool tail)
 	err = perf_event__synthesize_thread_map(&rec->tool, thread_map,
 						 process_synthesized_event,
 						 &rec->session->machines.host,
+						 needs_mmap,
 						 rec->opts.sample_address);
 	perf_thread_map__put(thread_map);
 	return err;
@@ -1409,7 +1411,7 @@ static int record__synthesize(struct record *rec, bool tail)
 		goto out;
 
 	/* Synthesize id_index before auxtrace_info */
-	if (rec->opts.auxtrace_sample_mode) {
+	if (rec->opts.auxtrace_sample_mode || rec->opts.full_auxtrace) {
 		err = perf_event__synthesize_id_index(tool,
 						      process_synthesized_event,
 						      session->evlist, machine);
@@ -1470,19 +1472,26 @@ static int record__synthesize(struct record *rec, bool tail)
 	if (err < 0)
 		pr_warning("Couldn't synthesize bpf events.\n");
 
-	err = perf_event__synthesize_cgroups(tool, process_synthesized_event,
-					     machine);
-	if (err < 0)
-		pr_warning("Couldn't synthesize cgroup events.\n");
+	if (rec->opts.synth & PERF_SYNTH_CGROUP) {
+		err = perf_event__synthesize_cgroups(tool, process_synthesized_event,
+						     machine);
+		if (err < 0)
+			pr_warning("Couldn't synthesize cgroup events.\n");
+	}
 
 	if (rec->opts.nr_threads_synthesize > 1) {
 		perf_set_multithreaded();
 		f = process_locked_synthesized_event;
 	}
 
-	err = __machine__synthesize_threads(machine, tool, &opts->target, rec->evlist->core.threads,
-					    f, opts->sample_address,
-					    rec->opts.nr_threads_synthesize);
+	if (rec->opts.synth & PERF_SYNTH_TASK) {
+		bool needs_mmap = rec->opts.synth & PERF_SYNTH_MMAP;
+
+		err = __machine__synthesize_threads(machine, tool, &opts->target,
+						    rec->evlist->core.threads,
+						    f, needs_mmap, opts->sample_address,
+						    rec->opts.nr_threads_synthesize);
+	}
 
 	if (rec->opts.nr_threads_synthesize > 1)
 		perf_set_singlethreaded();
@@ -2391,6 +2400,26 @@ static int process_timestamp_boundary(struct perf_tool *tool,
 	return 0;
 }
 
+static int parse_record_synth_option(const struct option *opt,
+				     const char *str,
+				     int unset __maybe_unused)
+{
+	struct record_opts *opts = opt->value;
+	char *p = strdup(str);
+
+	if (p == NULL)
+		return -1;
+
+	opts->synth = parse_synth_opt(p);
+	free(p);
+
+	if (opts->synth < 0) {
+		pr_err("Invalid synth option: %s\n", str);
+		return -1;
+	}
+	return 0;
+}
+
 /*
  * XXX Ideally would be local to cmd_record() and passed to a record__new
  * because we need to have access to it in record__exit, that is called
@@ -2416,6 +2445,7 @@ static struct record record = {
 		.nr_threads_synthesize = 1,
 		.ctl_fd              = -1,
 		.ctl_fd_ack          = -1,
+		.synth               = PERF_SYNTH_ALL,
 	},
 	.tool = {
 		.sample		= process_sample_event,
@@ -2631,6 +2661,8 @@ static struct option __record_options[] = {
 		     "\t\t\t  Optionally send control command completion ('ack\\n') to ack-fd descriptor.\n"
 		     "\t\t\t  Alternatively, ctl-fifo / ack-fifo will be opened and used as ctl-fd / ack-fd.",
 		      parse_control_option),
+	OPT_CALLBACK(0, "synth", &record.opts, "no|all|task|mmap|cgroup",
+		     "Fine-tune event synthesis: default=all", parse_record_synth_option),
 	OPT_END()
 };
 
@@ -2680,6 +2712,10 @@ int cmd_record(int argc, const char **argv)
 	if (quiet)
 		perf_quiet_option();
 
+	err = symbol__validate_sym_arguments();
+	if (err)
+		return err;
+
 	/* Make system wide (-a) the default target. */
 	if (!argc && target__none(&rec->opts.target))
 		rec->opts.target.system_wide = true;