Re: [PATCH v2] vl: fix [memory] section with -readconfig

[Markus Armbruster]

Paolo Bonzini <pbonzini@redhat.com> writes:

> 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 sentence is confusing.  Do you mean "like the -m option"?

> 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 <armbru@redhat.com>
> Fixes: ce9d03fb3f ("machine: add mem compound property", 2022-05-12)
> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

Preferably with a clarified commit message:
Reviewed-by: Markus Armbruster <armbru@redhat.com>