On 02/22/2018 11:27 AM, Andy Lutomirski wrote:
> On Thu, Feb 22, 2018 at 7:19 PM, Dave Hansen <dave.han...@intel.com> wrote:
>> On 02/22/2018 11:01 AM, Andy Lutomirski wrote:
>>> On x86, if you shoot down the PTE for the current stack, you're dead.
>> *If* we were to go do this insanity for vmalloc()'d memory, we could
>> probably limit it to kswapd, and also make sure that kernel threads
>> don't get vmalloc()'d stacks or that we mark them in a way to say we
>> never muck with them.
> How does that help?  We need to make sure that the task whose stack
> we're migrating is (a) not running and (b) is not being switched in or
> out.  And we have to make sure that there isn't some *other* mm that
> has the task's stack in ASID's TLB space.
> Maybe we take some lock so the task can't run, then flush the world,
> then release the lock.

Oh, I was thinking only of the case where you try to muck with your
*own* stack.  But, I see what you are saying about doing it to another
task on another CPU that is actively using the stack.

I think what you're saying is that we do not want to handle faults that
are caused by %esp being unusable.  Whatever we do, we've got to make
sure that no CPU has a stack in %esp that we are messing with.

Reply via email to