On 2017-06-09 08:22 AM, Arkadiusz Hiler wrote: > On Thu, Jun 08, 2017 at 04:06:44PM -0400, Bhawanpreet Lakha wrote: >> Test doesn't check if the property is immutable, and fails. >> Added conditions to detect if the property is immutable. >> >> Signed-off-by: Bhawanpreet Lakha <[email protected]> >> --- >> tests/kms_properties.c | 6 +++++- >> 1 file changed, 5 insertions(+), 1 deletion(-) >> >> diff --git a/tests/kms_properties.c b/tests/kms_properties.c >> index c15026b8..9585e8e9 100644 >> --- a/tests/kms_properties.c >> +++ b/tests/kms_properties.c >> @@ -138,7 +138,11 @@ static void test_properties(int fd, uint32_t type, >> uint32_t id, bool atomic) >> if (!atomic) { >> ret = drmModeObjectSetProperty(fd, id, type, prop_id, >> prop_value); >> >> - igt_assert_eq(ret, 0); >> + if (!(prop->flags & DRM_MODE_PROP_IMMUTABLE)) >> + igt_assert_eq(ret, 0); >> + else >> + igt_assert(ret != 0); >> + >> } else { >> ret = drmModeAtomicAddProperty(req, id, prop_id, >> prop_value); >> igt_assert(ret >= 0); > > > What about read only properties and setting them using the atomic calls > below? > > Do we have that scenario already? Seems lika a potential false fail as > well. >
Good point. We'll take a look at connector-properties-atomic test which should exercise the atomic code path. Harry _______________________________________________ amd-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/amd-gfx
