Re: [patch 02/38] x86/cpu: Use native_wrmsrl() in load_percpu_segment()

[Thomas Gleixner]

On Mon, Jul 18 2022 at 11:31, Peter Zijlstra wrote:
> On Mon, Jul 18, 2022 at 10:55:29AM +0200, Thomas Gleixner wrote:
>> On Mon, Jul 18 2022 at 08:54, Thomas Gleixner wrote:
>> > On Mon, Jul 18 2022 at 07:11, Juergen Gross wrote:
>> >>> -	switch_to_new_gdt(cpu);
>> >>> +	switch_to_real_gdt(cpu);
>> >>
>> >> ... can't you use the paravirt variant of load_gdt in switch_to_real_gdt() ?
>> >
>> > That does not solve the problem of having a disagreement between GDT and
>> > GS_BASE. Let me dig into this some more.
>> 
>> Bah. The real problem is __loadsegment_simple(gs, 0). After that GS_BASE
>> is 0. So any per CPU access before setting MSR_GS_BASE back to working
>> state is going into lala land.
>> 
>> So it's not the GDT. It's the mov 0, %gs which makes stuff go south, but
>> as %gs is already 0, we can keep the paravirt load_gdt() and use
>> native_write_msr() and everything should be happy.
>
> How is the ret from xen_load_gdt() not going to explode?

This is only for the early boot _before_ all the patching happens. So
that goes through the default retthunk.

Secondary CPUs do not need that as they set up GDT and GS_BASE in the
low level asm code before coming out to C.

I'm still trying to figure out how this works on XENPV and on 32bit.

Sigh...