Re: [PATCH 11 of 11] x86: defer cr3 reload when doing pud_clear()

["H. Peter Anvin" <hpa@zytor.com>]

Jeremy Fitzhardinge wrote:
> 
>> Now, all of this reminds me of something somewhat messy: if we share 
>> the kernel page tables for trampoline page tables, as discussed 
>> elsewhere, we HAVE to do a complete, all-tlb-including-global-pages 
>> flush after use, since the kernel pages are global and otherwise will 
>> stick around.  Unlike the permissions pages, there aren't G enable 
>> bits on the higher levels, but only for the PTEs themselves.
> 
> That wouldn't happen to often though, would it.  The identity mapping is 
> only interested in a 1:1 view on RAM, and that's not going to change at 
> all?  Does the TLB cache PAT attributes?  Do you need to do a global 
> flush after changing a PTE's PAT bits to make sure that all that PTE's 
> mappings have a consistent view on memory?
> 

You do need to flush *that page* globally, yes.

As far as flushing after using the trampoline pagetables, we're talking 
about rare, expensive events here like suspend to ram.

	-hpa