Re: TLB flushes on fixmap changes

[Nadav Amit]

at 12:31 PM, Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx> wrote:

> On Fri, Aug 24, 2018 at 11:36 AM Nadav Amit <nadav.amit@xxxxxxxxx> wrote:
>>> Urgh.. weren't the fixmaps per cpu? Bah, I remember looking at this
>>> during PTI, but I seem to have forgotten everything again.
>> 
>> [ Changed the title. Sorry for hijacking the thread. ]
>> 
>> Since:
>> 
>> native_set_fixmap()->set_pte_vaddr()->pgd_offset_k()
> 
> The fixmaps should be entirely fixed after bootup to constant
> mappings, except for the KMAP ones, and they are indexed per-cpu.
> 
> That's what my mental model is, at least.
> 
> Can you actually find something that changes the fixmaps after boot
> (again, ignoring kmap)?

At least the alternatives mechanism appears to do so.
 
IIUC the following path is possible when adding a module:

	jump_label_add_module()
	->__jump_label_update()
	->arch_jump_label_transform()
	->__jump_label_transform()
	->text_poke_bp()
	->text_poke()
	->set_fixmap()
	
And a similar path can happen when static_key_enable/disable() is called.