Event group test checks group creation for combinations of
hw, sw and uncore PMU events. Some of the uncore pmus may
require additional permission to access the counters.
For example, in case of hv_24x7, partition need to have
permissions to access hv_24x7 pmu counters. If not, event_open
will fail. Hence add a sanity check to see if event_open
succeeds before proceeding with the test.
Fixes: b20d9215a35f ("perf test: Add event group test for events in multiple
PMUs")
Signed-off-by: Athira Rajeev <[email protected]>
---
Note: The patch is based on tmp.perf/core branch
of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux.git
tools/perf/tests/event_groups.c | 14 +++++++++++++-
1 file changed, 13 insertions(+), 1 deletion(-)
diff --git a/tools/perf/tests/event_groups.c b/tools/perf/tests/event_groups.c
index 612c0444aaa8..029442b4e9c6 100644
--- a/tools/perf/tests/event_groups.c
+++ b/tools/perf/tests/event_groups.c
@@ -51,7 +51,7 @@ static int event_open(int type, unsigned long config, int
group_fd)
static int setup_uncore_event(void)
{
struct perf_pmu *pmu;
- int i;
+ int i, fd;
if (list_empty(&pmus))
perf_pmu__scan(NULL);
@@ -62,6 +62,18 @@ static int setup_uncore_event(void)
pr_debug("Using %s for uncore pmu event\n",
pmu->name);
types[2] = pmu->type;
configs[2] = uncore_pmus[i].config;
+ /*
+ * Check if the chosen uncore pmu event can be
+ * used in the test. For example, incase of
accessing
+ * hv_24x7 pmu counters, partition should have
+ * additional permissions. If not, event open
will
+ * fail. So check if the event open succeeds
+ * before proceeding.
+ */
+ fd = event_open(types[2], configs[2], -1);
+ if (fd < 0)
+ return -1;
+ close(fd);
return 0;
}
}
--
2.31.1