Messages in this thread | | | From | Nick Piggin <> | Subject | Re: questions on how x86 uses IPI for tlb invalidates | Date | Wed, 19 Nov 2008 03:20:25 +1100 |
| |
On Wednesday 19 November 2008 03:06, Kumar Gala wrote: > On Nov 18, 2008, at 10:03 AM, Nick Piggin wrote:
> > You can't do the broadcast TLB invalidates in kunmap_atomic. > > All that's needed in that case is to just invalidate the local > > CPU. > > Agreed, I was planning on fixing that. I guess the high level > question is if a broadcast invalidate can occur in soft or hard irq > context.
x86 does them for unmapping KVA (except kunmap_atomic), and unmapping UVA. Unmapping KVA (eg. kunmap, vunmap) is not allowed in irq context.
So long as you fix kunmap_atomic, you shouldn't have a problems.
| |