Paolo Bonzini writes:
> On 8/5/22 15:40, Markus Armbruster wrote:
>>> +loc_push_none(&loc);
>>> +qemu_opts_loc_restore(opts);
>>> +
>>> prop = qdict_new();
>>> if (qemu_opt_get_size(opts, "size", 0) != 0) {
>>
>> This treats "size=0" like absent size. Before commit ce9d03fb
On 8/5/22 15:40, Markus Armbruster wrote:
+loc_push_none(&loc);
+qemu_opts_loc_restore(opts);
+
prop = qdict_new();
if (qemu_opt_get_size(opts, "size", 0) != 0) {
This treats "size=0" like absent size. Before commit ce9d03fb3f, we
instead checked
mem_str = qemu_o
Paolo Bonzini 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 pa
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
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
