On Fri, Aug 05, 2022 at 12:06:35PM +0200, Paolo Bonzini wrote:
> The -M memory.* options do not have magic applied to them than the -m
> option, namely no "M" (for mebibytes) is tacked at the end of a
> suffixless value for "-M memory.size".
>
> This magic is performed by parse_memory_options, and we have to
> do it for both "-m" and the [memory] section of a config file.
> Storing [memory] sections directly to machine_opts_dict changed
> the meaning of
>
> [memory]
> size = "1024"
>
> in a -readconfig file from 1024MiB to 8KiB (1024 Bytes rounded up to
> 8KiB silently). To avoid this, the [memory] section has to be
> changed back to QemuOpts (combining [memory] and "-m" will work fine
> thanks to .merge_lists being true).
>
> Change parse_memory_options() so that, similar to the older function
> set_memory_options(), it operates after command line parsing is done;
> and also call it where set_memory_options() used to be.
>
> Note, the parsing code uses exit(1) instead of exit(EXIT_FAILURE) to
> match neighboring code.
>
> Reported-by: Markus Armbruster <arm...@redhat.com>
> Fixes: ce9d03fb3f ("machine: add mem compound property", 2022-05-12)
> Signed-off-by: Paolo Bonzini <pbonz...@redhat.com>
> ---
> softmmu/vl.c | 25 ++++++++++++++++---------
> 1 file changed, 16 insertions(+), 9 deletions(-)
I wrote a qtest (see cc'd separate mail) to validate -readconfig
handling of '[memory]' and this change makes the test pass, so
on that basis
Tested-by: Daniel P. Berrangé <berra...@redhat.com>
Reviewed-by: Daniel P. Berrangé <berra...@redhat.com>
With regards,
Daniel
--
|: https://berrange.com -o- https://www.flickr.com/photos/dberrange :|
|: https://libvirt.org -o- https://fstop138.berrange.com :|
|: https://entangle-photo.org -o- https://www.instagram.com/dberrange :|
