perf test: Add event group test for events in multiple PMUs

Multiple events in a group can belong to one or more PMUs, however
there are some limitations.

One of the limitations is that perf doesn't allow creating a group of
events from different hw PMUs.

Write a simple test to create various combinations of hw, sw and uncore
PMU events and verify group creation succeeds or fails as expected.

Signed-off-by: Ravi Bangoria <ravi.bangoria@amd.com>
Acked-by: Ian Rogers <irogers@google.com>
Acked-by: Kan Liang <kan.liang@linux.intel.com>
Acked-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ananth Narayan <ananth.narayan@amd.com>
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Carsten Haitzler <carsten.haitzler@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Santosh Shukla <santosh.shukla@amd.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Link: https://lore.kernel.org/r/20221206043237.12159-3-ravi.bangoria@amd.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/tests/Build

@@ -67,6 +67,7 @@ perf-y += expand-cgroup.o
 perf-y += perf-time-to-tsc.o
 perf-y += dlfilter-test.o
 perf-y += sigtrap.o
+perf-y += event_groups.o
 
 $(OUTPUT)tests/llvm-src-base.c: tests/bpf-script-example.c tests/Build
 	$(call rule_mkdir)

tools/perf/tests/builtin-test.c

@@ -110,6 +110,7 @@ static struct test_suite *generic_tests[] = {
 	&suite__perf_time_to_tsc,
 	&suite__dlfilter,
 	&suite__sigtrap,
+	&suite__event_groups,
 	NULL,
 };
 

tools/perf/tests/event_groups.c

@@ -0,0 +1,127 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <string.h>
+#include <unistd.h>
+#include <stdio.h>
+#include "linux/perf_event.h"
+#include "tests.h"
+#include "debug.h"
+#include "pmu.h"
+#include "pmus.h"
+#include "header.h"
+#include "../perf-sys.h"
+
+/* hw: cycles, sw: context-switch, uncore: [arch dependent] */
+static int types[] = {0, 1, -1};
+static unsigned long configs[] = {0, 3, 0};
+
+#define NR_UNCORE_PMUS 5
+
+/* Uncore pmus that support more than 3 counters */
+static struct uncore_pmus {
+	const char *name;
+	__u64 config;
+} uncore_pmus[NR_UNCORE_PMUS] = {
+	{ "amd_l3", 0x0 },
+	{ "amd_df", 0x0 },
+	{ "uncore_imc_0", 0x1 },         /* Intel */
+	{ "core_imc", 0x318 },           /* PowerPC: core_imc/CPM_STCX_FIN/ */
+	{ "hv_24x7", 0x22000000003 },    /* PowerPC: hv_24x7/CPM_STCX_FIN/ */
+};
+
+static int event_open(int type, unsigned long config, int group_fd)
+{
+	struct perf_event_attr attr;
+
+	memset(&attr, 0, sizeof(struct perf_event_attr));
+	attr.type = type;
+	attr.size = sizeof(struct perf_event_attr);
+	attr.config = config;
+	/*
+	 * When creating an event group, typically the group leader is
+	 * initialized with disabled set to 1 and any child events are
+	 * initialized with disabled set to 0. Despite disabled being 0,
+	 * the child events will not start until the group leader is
+	 * enabled.
+	 */
+	attr.disabled = group_fd == -1 ? 1 : 0;
+
+	return sys_perf_event_open(&attr, -1, 0, group_fd, 0);
+}
+
+static int setup_uncore_event(void)
+{
+	struct perf_pmu *pmu;
+	int i;
+
+	if (list_empty(&pmus))
+		perf_pmu__scan(NULL);
+
+	perf_pmus__for_each_pmu(pmu) {
+		for (i = 0; i < NR_UNCORE_PMUS; i++) {
+			if (!strcmp(uncore_pmus[i].name, pmu->name)) {
+				pr_debug("Using %s for uncore pmu event\n", pmu->name);
+				types[2] = pmu->type;
+				configs[2] = uncore_pmus[i].config;
+				return 0;
+			}
+		}
+	}
+	return -1;
+}
+
+static int run_test(int i, int j, int k)
+{
+	int erroneous = ((((1 << i) | (1 << j) | (1 << k)) & 5) == 5);
+	int group_fd, sibling_fd1, sibling_fd2;
+
+	group_fd = event_open(types[i], configs[i], -1);
+	if (group_fd == -1)
+		return -1;
+
+	sibling_fd1 = event_open(types[j], configs[j], group_fd);
+	if (sibling_fd1 == -1) {
+		close(group_fd);
+		return erroneous ? 0 : -1;
+	}
+
+	sibling_fd2 = event_open(types[k], configs[k], group_fd);
+	if (sibling_fd2 == -1) {
+		close(sibling_fd1);
+		close(group_fd);
+		return erroneous ? 0 : -1;
+	}
+
+	close(sibling_fd2);
+	close(sibling_fd1);
+	close(group_fd);
+	return erroneous ? -1 : 0;
+}
+
+static int test__event_groups(struct test_suite *text __maybe_unused, int subtest __maybe_unused)
+{
+	int i, j, k;
+	int ret;
+	int r;
+
+	ret = setup_uncore_event();
+	if (ret || types[2] == -1)
+		return TEST_SKIP;
+
+	ret = TEST_OK;
+	for (i = 0; i < 3; i++) {
+		for (j = 0; j < 3; j++) {
+			for (k = 0; k < 3; k++) {
+				r = run_test(i, j, k);
+				if (r)
+					ret = TEST_FAIL;
+
+				pr_debug("0x%x 0x%lx, 0x%x 0x%lx, 0x%x 0x%lx: %s\n",
+					 types[i], configs[i], types[j], configs[j],
+					 types[k], configs[k], r ? "Fail" : "Pass");
+			}
+		}
+	}
+	return ret;
+}
+
+DEFINE_SUITE("Event groups", event_groups);

tools/perf/tests/tests.h

@@ -147,6 +147,7 @@ DECLARE_SUITE(expand_cgroup_events);
 DECLARE_SUITE(perf_time_to_tsc);
 DECLARE_SUITE(dlfilter);
 DECLARE_SUITE(sigtrap);
+DECLARE_SUITE(event_groups);
 
 /*
  * PowerPC and S390 do not support creation of instruction breakpoints using the