Merge tag 'perf-tools-for-v5.10-2020-10-15' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull perf tools updates from Arnaldo Carvalho de Melo:

 - cgroup improvements for 'perf stat', allowing for compact
   specification of events and cgroups in the command line.

 - Support per thread topdown metrics in 'perf stat'.

 - Support sample-read topdown metric group in 'perf record'

 - Show start of latency in addition to its start in 'perf sched
   latency'.

 - Add min, max to 'perf script' futex-contention output, in addition to
   avg.

 - Allow usage of 'perf_event_attr->exclusive' attribute via the new
   ':e' event modifier.

 - Add 'snapshot' command to 'perf record --control', using it with
   Intel PT.

 - Support FIFO file names as alternative options to 'perf record
   --control'.

 - Introduce branch history "streams", to compare 'perf record' runs
   with 'perf diff' based on branch records and report hot streams.

 - Support PE executable symbol tables using libbfd, to profile, for
   instance, wine binaries.

 - Add filter support for option 'perf ftrace -F/--funcs'.

 - Allow configuring the 'disassembler_style' 'perf annotate' knob via
   'perf config'

 - Update CascadelakeX and SkylakeX JSON vendor events files.

 - Add support for parsing perchip/percore JSON vendor events.

 - Add power9 hv_24x7 core level metric events.

 - Add L2 prefetch, ITLB instruction fetch hits JSON events for AMD
   zen1.

 - Enable Family 19h users by matching Zen2 AMD vendor events.

 - Use debuginfod in 'perf probe' when required debug files not found
   locally.

 - Display negative tid in non-sample events in 'perf script'.

 - Make GTK2 support opt-in

 - Add build test with GTK+

 - Add missing -lzstd to the fast path feature detection

 - Add scripts to auto generate 'mmap', 'mremap' string<->id tables for
   use in 'perf trace'.

 - Show python test script in verbose mode.

 - Fix uncore metric expressions

 - Msan uninitialized use fixes.

 - Use condition variables in 'perf bench numa'

 - Autodetect python3 binary in systems without python2.

 - Support md5 build ids in addition to sha1.

 - Add build id 'perf test' regression test.

 - Fix printable strings in python3 scripts.

 - Fix off by ones in 'perf trace' in arches using libaudit.

 - Fix JSON event code for events referencing std arch events.

 - Introduce 'perf test' shell script for Arm CoreSight testing.

 - Add rdtsc() for Arm64 for used in the PERF_RECORD_TIME_CONV metadata
   event and in 'perf test tsc'.

 - 'perf c2c' improvements: Add "RMT Load Hit" metric, "Total Stores",
   fixes and documentation update.

 - Fix usage of reloc_sym in 'perf probe' when using both kallsyms and
   debuginfo files.

 - Do not print 'Metric Groups:' unnecessarily in 'perf list'

 - Refcounting fixes in the event parsing code.

 - Add expand cgroup event 'perf test' entry.

 - Fix out of bounds CPU map access when handling armv8_pmu events in
   'perf stat'.

 - Add build-id injection 'perf bench' benchmark.

 - Enter namespace when reading build-id in 'perf inject'.

 - Do not load map/dso when injecting build-id speeding up the 'perf
   inject' process.

 - Add --buildid-all option to avoid processing all samples, just the
   mmap metadata events.

 - Add feature test to check if libbfd has buildid support

 - Add 'perf test' entry for PE binary format support.

 - Fix typos in power8 PMU vendor events JSON files.

 - Hide libtraceevent non API functions.

* tag 'perf-tools-for-v5.10-2020-10-15' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux: (113 commits)
  perf c2c: Update documentation for metrics reorganization
  perf c2c: Add metrics "RMT Load Hit"
  perf c2c: Correct LLC load hit metrics
  perf c2c: Change header for LLC local hit
  perf c2c: Use more explicit headers for HITM
  perf c2c: Change header from "LLC Load Hitm" to "Load Hitm"
  perf c2c: Organize metrics based on memory hierarchy
  perf c2c: Display "Total Stores" as a standalone metrics
  perf c2c: Display the total numbers continuously
  perf bench: Use condition variables in numa.
  perf jevents: Fix event code for events referencing std arch events
  perf diff: Support hot streams comparison
  perf streams: Report hot streams
  perf streams: Calculate the sum of total streams hits
  perf streams: Link stream pair
  perf streams: Compare two streams
  perf streams: Get the evsel_streams by evsel_idx
  perf streams: Introduce branch history "streams"
  perf intel-pt: Improve PT documentation slightly
  perf tools: Add support for exclusive groups/events
  ...

1 files changed, 110 insertions, 5 deletions

diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
index 050dea9f1e88..b81324a13a2b 100644
--- a/tools/perf/util/cgroup.c
+++ b/tools/perf/util/cgroup.c
@@ -3,6 +3,9 @@
 #include "evsel.h"
 #include "cgroup.h"
 #include "evlist.h"
+#include "rblist.h"
+#include "metricgroup.h"
+#include "stat.h"
 #include <linux/zalloc.h>
 #include <sys/types.h>
 #include <sys/stat.h>
@@ -48,7 +51,7 @@ static struct cgroup *evlist__find_cgroup(struct evlist *evlist, const char *str
 	return NULL;
 }
 
-static struct cgroup *cgroup__new(const char *name)
+static struct cgroup *cgroup__new(const char *name, bool do_open)
 {
 	struct cgroup *cgroup = zalloc(sizeof(*cgroup));
 
@@ -58,9 +61,14 @@ static struct cgroup *cgroup__new(const char *name)
 		cgroup->name = strdup(name);
 		if (!cgroup->name)
 			goto out_err;
-		cgroup->fd = open_cgroup(name);
-		if (cgroup->fd == -1)
-			goto out_free_name;
+
+		if (do_open) {
+			cgroup->fd = open_cgroup(name);
+			if (cgroup->fd == -1)
+				goto out_free_name;
+		} else {
+			cgroup->fd = -1;
+		}
 	}
 
 	return cgroup;
@@ -76,7 +84,7 @@ struct cgroup *evlist__findnew_cgroup(struct evlist *evlist, const char *name)
 {
 	struct cgroup *cgroup = evlist__find_cgroup(evlist, name);
 
-	return cgroup ?: cgroup__new(name);
+	return cgroup ?: cgroup__new(name, true);
 }
 
 static int add_cgroup(struct evlist *evlist, const char *str)
@@ -193,6 +201,103 @@ int parse_cgroups(const struct option *opt, const char *str,
 	return 0;
 }
 
+int evlist__expand_cgroup(struct evlist *evlist, const char *str,
+			  struct rblist *metric_events, bool open_cgroup)
+{
+	struct evlist *orig_list, *tmp_list;
+	struct evsel *pos, *evsel, *leader;
+	struct rblist orig_metric_events;
+	struct cgroup *cgrp = NULL;
+	const char *p, *e, *eos = str + strlen(str);
+	int ret = -1;
+
+	if (evlist->core.nr_entries == 0) {
+		fprintf(stderr, "must define events before cgroups\n");
+		return -EINVAL;
+	}
+
+	orig_list = evlist__new();
+	tmp_list = evlist__new();
+	if (orig_list == NULL || tmp_list == NULL) {
+		fprintf(stderr, "memory allocation failed\n");
+		return -ENOMEM;
+	}
+
+	/* save original events and init evlist */
+	perf_evlist__splice_list_tail(orig_list, &evlist->core.entries);
+	evlist->core.nr_entries = 0;
+
+	if (metric_events) {
+		orig_metric_events = *metric_events;
+		rblist__init(metric_events);
+	} else {
+		rblist__init(&orig_metric_events);
+	}
+
+	for (;;) {
+		p = strchr(str, ',');
+		e = p ? p : eos;
+
+		/* allow empty cgroups, i.e., skip */
+		if (e - str) {
+			/* termination added */
+			char *name = strndup(str, e - str);
+			if (!name)
+				goto out_err;
+
+			cgrp = cgroup__new(name, open_cgroup);
+			free(name);
+			if (cgrp == NULL)
+				goto out_err;
+		} else {
+			cgrp = NULL;
+		}
+
+		leader = NULL;
+		evlist__for_each_entry(orig_list, pos) {
+			evsel = evsel__clone(pos);
+			if (evsel == NULL)
+				goto out_err;
+
+			cgroup__put(evsel->cgrp);
+			evsel->cgrp = cgroup__get(cgrp);
+
+			if (evsel__is_group_leader(pos))
+				leader = evsel;
+			evsel->leader = leader;
+
+			evlist__add(tmp_list, evsel);
+		}
+		/* cgroup__new() has a refcount, release it here */
+		cgroup__put(cgrp);
+		nr_cgroups++;
+
+		if (metric_events) {
+			perf_stat__collect_metric_expr(tmp_list);
+			if (metricgroup__copy_metric_events(tmp_list, cgrp,
+							    metric_events,
+							    &orig_metric_events) < 0)
+				break;
+		}
+
+		perf_evlist__splice_list_tail(evlist, &tmp_list->core.entries);
+		tmp_list->core.nr_entries = 0;
+
+		if (!p) {
+			ret = 0;
+			break;
+		}
+		str = p+1;
+	}
+
+out_err:
+	evlist__delete(orig_list);
+	evlist__delete(tmp_list);
+	rblist__exit(&orig_metric_events);
+
+	return ret;
+}
+
 static struct cgroup *__cgroup__findnew(struct rb_root *root, uint64_t id,
 					bool create, const char *path)
 {