Re: [Qemu-devel] Modeling x86 early initialization accurately

[Carl-Daniel Hailfinger]

On 26.11.2008 12:37, Paul Brook wrote:
>> - Start up with all RAM being readonly. Writes should be discarded,
>> reads will usually return 0xff or be undefined. The "undefined" variant
>> would allow the code to allocate RAM once and just switch write access
>> on/off.
>>     
>
> Does anything actually rely on this behavior?
>   

No, but it would model hardware more closely. And it may be needed for a
correct implementation of Suspend-to-RAM.

> I can see the need to the other bits, but it seems kinda strange that 
> anything 
> would rely on RAM being readonly. This seems more like a coreboot bug than 
> anything else.
>   

coreboot doesn't rely on this. Once you use Suspend-to-RAM on x86, the
need to avoid clobbering RAM contents during resume will strongly
suggest this change. Alas, this is not important for my current goal of
getting coreboot to run with actual i586 CPU code.

Regards,
Carl-Daniel

-- 
http://www.hailfinger.org/