Thomas Huth <th...@redhat.com> writes: > On 24/05/2024 02.05, Nicholas Piggin wrote: >> On Wed May 22, 2024 at 7:12 PM AEST, Thomas Huth wrote: >>> On s390x, we recently had a regression that broke migration / savevm >>> (see commit bebe9603fc ("hw/intc/s390_flic: Fix crash that occurs when >>> saving the machine state"). The problem was merged without being noticed >>> since we currently do not run any migration / savevm related tests on >>> x86 hosts. >>> While we currently cannot run all migration tests for the s390x target >>> on x86 hosts yet (due to some unresolved issues with TCG), we can at >>> least run some of the non-live tests to avoid such problems in the future. >>> Thus enable the "analyze-script" and the "bad_dest" tests before checking >>> for KVM on s390x or ppc64 (this also fixes the problem that the >>> "analyze-script" test was not run on s390x at all anymore since it got >>> disabled again by accident in a previous refactoring of the code). >> >> ppc64 is working for me, can it be enabled fully, or is it still >> breaking somewhere? FWIW I have a patch to change it from using >> open-firmware commands to a boot file which speeds it up. > > IIRC last time that I tried it was working fine for me, too, but getting a > speedup here first would be very welcome since using the Forth code slows > down the whole testing quite a bit.
Yeah, we're all gonna get kicked from the project if we add 10m to make check in CI. =) @Nick, send us that patch and I'd be glad to reenable the tests.