Re: [PATCH] Use deltas to replace atomic inc

[Christoph Lameter <clameter@engr.sgi.com>]

On Sun, 21 Aug 2005, Linus Torvalds wrote:

> On Sun, 21 Aug 2005, Christoph Lameter wrote:
> > 
> > The thing that bothers me more is that schedule() can be called both by 
> > handle_mm_fault as well as during unuse_mm. We may need some flag 
> > PF_NO_COUNTER_UPDATES or so there to insure that schedule() does not add 
> > deltas to the current->mm.
> 
> Why? I don't think it's ever wrong to do the thing. We should be holding 
> no locks at the point (and we haven't grabbed he RQ lock yet), so it 
> should always be safe to get the page table lock. 

get_user_pages and unuse_mm may be working on an mm that is not 
current->mm. If schedule is called then the deltas are added to the wrong 
mm (current->mm). If we had PF_NO_COUNTER_UPDATES then we could force no 
counters updates to occur until get_user_pages or unuse_mm assigns the 
deltas to a specific mm using mm_counter_catchup(current, target_mm).

> I think the delta approach looks quite reasonable, although I think 
> somebody should check that the cache behaviour is ok (ie the deltas should 
> hopefully be in a cacheline that we need to look at anyway).

I put the deltas near to exit_state which is also checked in schedule().
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>