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, 54 insertions, 19 deletions

diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c
index a7e981b2d7de..198982109f0f 100644
--- a/tools/perf/util/synthetic-events.c
+++ b/tools/perf/util/synthetic-events.c
@@ -715,7 +715,8 @@ static int __event__synthesize_thread(union perf_event *comm_event,
 				      union perf_event *fork_event,
 				      union perf_event *namespaces_event,
 				      pid_t pid, int full, perf_event__handler_t process,
-				      struct perf_tool *tool, struct machine *machine, bool mmap_data)
+				      struct perf_tool *tool, struct machine *machine,
+				      bool needs_mmap, bool mmap_data)
 {
 	char filename[PATH_MAX];
 	struct dirent **dirent;
@@ -739,7 +740,7 @@ static int __event__synthesize_thread(union perf_event *comm_event,
 		 * send mmap only for thread group leader
 		 * see thread__init_maps()
 		 */
-		if (pid == tgid &&
+		if (pid == tgid && needs_mmap &&
 		    perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid,
 						       process, machine, mmap_data))
 			return -1;
@@ -786,7 +787,7 @@ static int __event__synthesize_thread(union perf_event *comm_event,
 			break;
 
 		rc = 0;
-		if (_pid == pid && !kernel_thread) {
+		if (_pid == pid && !kernel_thread && needs_mmap) {
 			/* process the parent's maps too */
 			rc = perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid,
 						process, machine, mmap_data);
@@ -806,7 +807,7 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool,
 				      struct perf_thread_map *threads,
 				      perf_event__handler_t process,
 				      struct machine *machine,
-				      bool mmap_data)
+				      bool needs_mmap, bool mmap_data)
 {
 	union perf_event *comm_event, *mmap_event, *fork_event;
 	union perf_event *namespaces_event;
@@ -836,7 +837,7 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool,
 					       fork_event, namespaces_event,
 					       perf_thread_map__pid(threads, thread), 0,
 					       process, tool, machine,
-					       mmap_data)) {
+					       needs_mmap, mmap_data)) {
 			err = -1;
 			break;
 		}
@@ -862,7 +863,7 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool,
 						       fork_event, namespaces_event,
 						       comm_event->comm.pid, 0,
 						       process, tool, machine,
-						       mmap_data)) {
+						       needs_mmap, mmap_data)) {
 				err = -1;
 				break;
 			}
@@ -882,6 +883,7 @@ out:
 static int __perf_event__synthesize_threads(struct perf_tool *tool,
 					    perf_event__handler_t process,
 					    struct machine *machine,
+					    bool needs_mmap,
 					    bool mmap_data,
 					    struct dirent **dirent,
 					    int start,
@@ -926,7 +928,7 @@ static int __perf_event__synthesize_threads(struct perf_tool *tool,
 		 */
 		__event__synthesize_thread(comm_event, mmap_event, fork_event,
 					   namespaces_event, pid, 1, process,
-					   tool, machine, mmap_data);
+					   tool, machine, needs_mmap, mmap_data);
 	}
 	err = 0;
 
@@ -945,6 +947,7 @@ struct synthesize_threads_arg {
 	struct perf_tool *tool;
 	perf_event__handler_t process;
 	struct machine *machine;
+	bool needs_mmap;
 	bool mmap_data;
 	struct dirent **dirent;
 	int num;
@@ -956,7 +959,8 @@ static void *synthesize_threads_worker(void *arg)
 	struct synthesize_threads_arg *args = arg;
 
 	__perf_event__synthesize_threads(args->tool, args->process,
-					 args->machine, args->mmap_data,
+					 args->machine,
+					 args->needs_mmap, args->mmap_data,
 					 args->dirent,
 					 args->start, args->num);
 	return NULL;
@@ -965,7 +969,7 @@ static void *synthesize_threads_worker(void *arg)
 int perf_event__synthesize_threads(struct perf_tool *tool,
 				   perf_event__handler_t process,
 				   struct machine *machine,
-				   bool mmap_data,
+				   bool needs_mmap, bool mmap_data,
 				   unsigned int nr_threads_synthesize)
 {
 	struct synthesize_threads_arg *args = NULL;
@@ -994,7 +998,8 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
 
 	if (thread_nr <= 1) {
 		err = __perf_event__synthesize_threads(tool, process,
-						       machine, mmap_data,
+						       machine,
+						       needs_mmap, mmap_data,
 						       dirent, base, n);
 		goto free_dirent;
 	}
@@ -1015,6 +1020,7 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
 		args[i].tool = tool;
 		args[i].process = process;
 		args[i].machine = machine;
+		args[i].needs_mmap = needs_mmap;
 		args[i].mmap_data = mmap_data;
 		args[i].dirent = dirent;
 	}
@@ -1775,26 +1781,27 @@ out_err:
 
 int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool,
 				  struct target *target, struct perf_thread_map *threads,
-				  perf_event__handler_t process, bool data_mmap,
-				  unsigned int nr_threads_synthesize)
+				  perf_event__handler_t process, bool needs_mmap,
+				  bool data_mmap, unsigned int nr_threads_synthesize)
 {
 	if (target__has_task(target))
-		return perf_event__synthesize_thread_map(tool, threads, process, machine, data_mmap);
+		return perf_event__synthesize_thread_map(tool, threads, process, machine,
+							 needs_mmap, data_mmap);
 	else if (target__has_cpu(target))
-		return perf_event__synthesize_threads(tool, process,
-						      machine, data_mmap,
+		return perf_event__synthesize_threads(tool, process, machine,
+						      needs_mmap, data_mmap,
 						      nr_threads_synthesize);
 	/* command specified */
 	return 0;
 }
 
 int machine__synthesize_threads(struct machine *machine, struct target *target,
-				struct perf_thread_map *threads, bool data_mmap,
-				unsigned int nr_threads_synthesize)
+				struct perf_thread_map *threads, bool needs_mmap,
+				bool data_mmap, unsigned int nr_threads_synthesize)
 {
 	return __machine__synthesize_threads(machine, NULL, target, threads,
-					     perf_event__process, data_mmap,
-					     nr_threads_synthesize);
+					     perf_event__process, needs_mmap,
+					     data_mmap, nr_threads_synthesize);
 }
 
 static struct perf_record_event_update *event_update_event__new(size_t size, u64 type, u64 id)
@@ -2230,3 +2237,31 @@ int perf_event__synthesize_for_pipe(struct perf_tool *tool,
 
 	return ret;
 }
+
+int parse_synth_opt(char *synth)
+{
+	char *p, *q;
+	int ret = 0;
+
+	if (synth == NULL)
+		return -1;
+
+	for (q = synth; (p = strsep(&q, ",")); p = q) {
+		if (!strcasecmp(p, "no") || !strcasecmp(p, "none"))
+			return 0;
+
+		if (!strcasecmp(p, "all"))
+			return PERF_SYNTH_ALL;
+
+		if (!strcasecmp(p, "task"))
+			ret |= PERF_SYNTH_TASK;
+		else if (!strcasecmp(p, "mmap"))
+			ret |= PERF_SYNTH_TASK | PERF_SYNTH_MMAP;
+		else if (!strcasecmp(p, "cgroup"))
+			ret |= PERF_SYNTH_CGROUP;
+		else
+			return -1;
+	}
+
+	return ret;
+}