While the sdhci-of-aspeed KUnit tests do work when builtin, and do work
when KUnit itself is being built as a module, the two together break.

This is because the KUnit tests (understandably) depend on KUnit, so a
built-in test cannot build if KUnit is a module.

Fix this by adding a dependency on (MMC_SDHCI_OF_ASPEED=m || KUNIT=y),
which only excludes this one problematic configuration.

This was reported on a nasty openrisc-randconfig run by the kernel test
robot, though for some reason (compiler optimisations removing the test
code?) I wasn't able to reproduce it locally on x86:
https://lore.kernel.org/linux-mm/202207140122.fzhlf60k-lkp@intel.com/T/

Fixes: 291cd54e ("mmc: sdhci-of-aspeed: test: Use kunit_test_suite() macro")
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: David Gow <davidgow@google.com>
Acked-by: Andrew Jeffery <andrew@aj.id.au>
Acked-by: Ulf Hansson <ulf.hansson@linaro.org>
Acked-by: Brendan Higgins <brendanhiggins@google.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>