Merge tag 'perf-core-for-mingo-4.17-20180308' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

- Support to display the IPC/Cycle in 'annotate' TUI, for systems
  where this info can be obtained, like Intel's >= Skylake (Jin Yao)

- Support wildcards on PMU name in dynamic PMU events (Agustin Vega-Frias)

- Display pmu name when printing unmerged events in stat (Agustin Vega-Frias)

- Auto-merge PMU events created by prefix or glob match (Agustin Vega-Frias)

- Fix s390 'call' operations target function annotation (Thomas Richter)

- Handle s390 PC relative load and store instruction in the augmented
  'annotate', code, used so far in the TUI modes of 'perf report' and
  'perf annotate' (Thomas Richter)

- Provide libtraceevent with a kernel symbol resolver, so that
  symbols in tracepoint fields can be resolved when showing them in
  tools such as 'perf report' (Wang YanQing)

- Refactor the cgroups code to look more like other code in tools/perf,
  using cgroup__{put,get} for refcount operations instead of its
  open-coded equivalent, breaking larger functions, etc (Arnaldo Carvalho de Melo)

- Implement support for the -G/--cgroup target in 'perf trace', allowing
  strace like tracing (plus other events, backtraces, etc) for cgroups
  (Arnaldo Carvalho de Melo)

- Update thread shortname in 'perf sched map' when the thread's COMM
  changes (Changbin Du)

- refcount 'struct mem_info', for better sharing it over several
  users, avoid duplicating structs and fixing crashes related to
  use after free (Jiri Olsa)

- Display perf.data version, offsets in 'perf report --header' (Jiri Olsa)

- Record the machine's memory topology information in a perf.data
  feature section, to be used by tools such as 'perf c2c' (Jiri Olsa)

- Fix output of forced groups in the header for 'perf report' --stdio
  and --tui (Jiri Olsa)

- Better support llvm, clang, cxx make tests in the build process (Jiri Olsa)

- Streamline the 'struct perf_mmap' methods, storing some info in the
  struct instead of passing it via various methods, shortening its
  signatures (Kan Liang)

- Update the quipper perf.data parser library site information (Stephane Eranian)

- Correct perf's man pages title markers for asciidoctor (Takashi Iwai)

- Intel PT fixes and refactorings paving the way for implementing
  support for AUX area sampling (Adrian Hunter)

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 53 insertions, 4 deletions

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 1a93debc1e8d..87b95c9410b4 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -19,6 +19,7 @@
 #include <traceevent/event-parse.h>
 #include <api/fs/tracing_path.h>
 #include "builtin.h"
+#include "util/cgroup.h"
 #include "util/color.h"
 #include "util/debug.h"
 #include "util/env.h"
@@ -83,6 +84,7 @@ struct trace {
 	struct perf_evlist	*evlist;
 	struct machine		*host;
 	struct thread		*current;
+	struct cgroup		*cgroup;
 	u64			base_time;
 	FILE			*output;
 	unsigned long		nr_events;
@@ -2370,6 +2372,34 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 				   trace__sched_stat_runtime))
 		goto out_error_sched_stat_runtime;
 
+	/*
+	 * If a global cgroup was set, apply it to all the events without an
+	 * explicit cgroup. I.e.:
+	 *
+	 * 	trace -G A -e sched:*switch
+	 *
+	 * Will set all raw_syscalls:sys_{enter,exit}, pgfault, vfs_getname, etc
+	 * _and_ sched:sched_switch to the 'A' cgroup, while:
+	 *
+	 * trace -e sched:*switch -G A
+	 *
+	 * will only set the sched:sched_switch event to the 'A' cgroup, all the
+	 * other events (raw_syscalls:sys_{enter,exit}, etc are left "without"
+	 * a cgroup (on the root cgroup, sys wide, etc).
+	 *
+	 * Multiple cgroups:
+	 *
+	 * trace -G A -e sched:*switch -G B
+	 *
+	 * the syscall ones go to the 'A' cgroup, the sched:sched_switch goes
+	 * to the 'B' cgroup.
+	 *
+	 * evlist__set_default_cgroup() grabs a reference of the passed cgroup
+	 * only for the evsels still without a cgroup, i.e. evsel->cgroup == NULL.
+	 */
+	if (trace->cgroup)
+		evlist__set_default_cgroup(trace->evlist, trace->cgroup);
+
 	err = perf_evlist__create_maps(evlist, &trace->opts.target);
 	if (err < 0) {
 		fprintf(trace->output, "Problems parsing the target to trace, check your options!\n");
@@ -2473,13 +2503,12 @@ again:
 	for (i = 0; i < evlist->nr_mmaps; i++) {
 		union perf_event *event;
 		struct perf_mmap *md;
-		u64 end, start;
 
 		md = &evlist->mmap[i];
-		if (perf_mmap__read_init(md, false, &start, &end) < 0)
+		if (perf_mmap__read_init(md) < 0)
 			continue;
 
-		while ((event = perf_mmap__read_event(md, false, &start, end)) != NULL) {
+		while ((event = perf_mmap__read_event(md)) != NULL) {
 			struct perf_sample sample;
 
 			++trace->nr_events;
@@ -2492,7 +2521,7 @@ again:
 
 			trace__handle_event(trace, event, &sample);
 next_event:
-			perf_mmap__consume(md, false);
+			perf_mmap__consume(md);
 
 			if (interrupted)
 				goto out_disable;
@@ -2540,6 +2569,7 @@ out_delete_evlist:
 	trace__symbols__exit(trace);
 
 	perf_evlist__delete(evlist);
+	cgroup__put(trace->cgroup);
 	trace->evlist = NULL;
 	trace->live = false;
 	return err;
@@ -2979,6 +3009,18 @@ out:
 	return err;
 }
 
+static int trace__parse_cgroups(const struct option *opt, const char *str, int unset)
+{
+	struct trace *trace = opt->value;
+
+	if (!list_empty(&trace->evlist->entries))
+		return parse_cgroups(opt, str, unset);
+
+	trace->cgroup = evlist__findnew_cgroup(trace->evlist, str);
+
+	return 0;
+}
+
 int cmd_trace(int argc, const char **argv)
 {
 	const char *trace_usage[] = {
@@ -3069,6 +3111,8 @@ int cmd_trace(int argc, const char **argv)
 			"print the PERF_RECORD_SAMPLE PERF_SAMPLE_ info, for debugging"),
 	OPT_UINTEGER(0, "proc-map-timeout", &trace.opts.proc_map_timeout,
 			"per thread proc mmap processing timeout in ms"),
+	OPT_CALLBACK('G', "cgroup", &trace, "name", "monitor event in cgroup name only",
+		     trace__parse_cgroups),
 	OPT_UINTEGER('D', "delay", &trace.opts.initial_delay,
 		     "ms to wait before starting measurement after program "
 		     "start"),
@@ -3095,6 +3139,11 @@ int cmd_trace(int argc, const char **argv)
 	argc = parse_options_subcommand(argc, argv, trace_options, trace_subcommands,
 				 trace_usage, PARSE_OPT_STOP_AT_NON_OPTION);
 
+	if ((nr_cgroups || trace.cgroup) && !trace.opts.target.system_wide) {
+		usage_with_options_msg(trace_usage, trace_options,
+				       "cgroup monitoring only available in system-wide mode");
+	}
+
 	err = bpf__setup_stdout(trace.evlist);
 	if (err) {
 		bpf__strerror_setup_stdout(trace.evlist, err, bf, sizeof(bf));