Re: [PATCH] add __GFP_ZERO to GFP_LEVEL_MASK

[Andrew Morton <akpm@linux-foundation.org>]

On Tue, 24 Jul 2007 12:36:59 -0700 (PDT)
Christoph Lameter <clameter@sgi.com> wrote:

> On Tue, 24 Jul 2007, Andrew Morton wrote:
> 
> > > __GFP_MOVABLE	The movability of a slab is determined by the
> > > 		options specified at kmem_cache_create time. If this is
> > > 		specified at kmalloc time then we will have some random
> > > 		slabs movable and others not. 
> > 
> > Yes, they seem inappropriate.  Especially the first two.
> 
> The third one would randomize __GFP_MOVABLE allocs from the page allocator 
> since one __GFP_MOVABLE alloc may allocate a slab that is then used for 
> !__GFP_MOVABLE allocs.
> 
> Maybe something like this? Note that we may get into some churn here 
> since slab allocations that any of these flags will BUG.
> 
> 
> 
> GFP_LEVEL_MASK: Remove __GFP_COLD, __GFP_COMP and __GFPMOVABLE
> 
> Add an explanation for the GFP_LEVEL_MASK and remove the flags
> that should not be passed through derived allocators.
> 
> Signed-off-by: Christoph Lameter <clameter@sgi.com>

I think I'll duck this for now.  Otherwise I have a suspicion that I'll
be the first person to run it and I'm too old for such excitement.