mbox series

[0/3] testing/next: s390x gitlab updates

Message ID 20240426153938.1707723-1-alex.bennee@linaro.org
Headers show
Series testing/next: s390x gitlab updates | expand

Message

Alex Bennée April 26, 2024, 3:39 p.m. UTC
I was asked to update the custom gitlab runner from the aging 20.04 to
22.04 which has been done. However I needed to update the provisioning
scripts and clean-up some of the cruft. Sadly this doesn't seem to be
passing cleanly as we have:

  - qtest-s390x/migration-test ERROR           98.94s   killed by signal 6 SIGABRT
  - failing TCG tests (on s390x HW)
     - float_convd fails against a generated reference
     - clc returns 1

There are also lots of scary DSO warnings:

  BFD: warning: system-supplied DSO at 0x7fedb6479000 has a corrupt string table index

Can I leave that to the respective maintainers to investigate please
as I have a publishing deadline coming up.

Thanks,

Alex.

Alex Bennée (3):
  build-environment: make some packages optional
  gitlab: migrate the s390x custom machine to 22.04
  gitlab: remove stale s390x-all-linux-static conf hacks

 .gitlab-ci.d/custom-runners.yml               |  2 +-
 ...20.04-s390x.yml => ubuntu-22.04-s390x.yml} | 32 +++++++++----------
 scripts/ci/setup/build-environment.yml        | 16 ++++++++--
 3 files changed, 29 insertions(+), 21 deletions(-)
 rename .gitlab-ci.d/custom-runners/{ubuntu-20.04-s390x.yml => ubuntu-22.04-s390x.yml} (80%)

Comments

Richard Henderson May 4, 2024, 1:17 a.m. UTC | #1
On 4/26/24 08:39, Alex Bennée wrote:
> I was asked to update the custom gitlab runner from the aging 20.04 to
> 22.04 which has been done. However I needed to update the provisioning
> scripts and clean-up some of the cruft. Sadly this doesn't seem to be
> passing cleanly as we have:
> 
>    - qtest-s390x/migration-test ERROR           98.94s   killed by signal 6 SIGABRT
>    - failing TCG tests (on s390x HW)
>       - float_convd fails against a generated reference
>       - clc returns 1

I've had a look at the clc failure.

It fails because of bad address space layout, where the NULL page isn't unmapped, so the 
expected SIGSEGV does *not* happen.

This is unfortunate and we could do better.

However, with the upgrade, --static --enable-pie no longer works.
 From config.log,

cc -m64 -Werror -fPIE -DPIE -o config-temp/qemu-conf.exe config-temp/qemu-conf.c -static-pie
/usr/bin/ld: cannot find rcrt1.o: No such file or directory

which suggests a missing package.

Alternately, we could drop --static, as it's not really relevant to this testing.  With 
that, we get PIE dynamically linked executables, which do not trigger the bad layout.

But at some point we should make sure that the NULL page(s) are reserved PROT_NONE for the 
guest, which ensure this stays fixed.


r~