[PATCH 0/4] Demand faunting for huge pages

[Adam Litke <agl@us.ibm.com>]

The following patch set implements demand faulting for huge pages.  In
response to helpful feedback from Christoph Lameter, Kenneth Chen, and
Andi Kleen, I've split up the demand fault patch (previously posted on
LKML: http://lkml.org/lkml/2005/8/5/154 ) into a smaller, more
digestible set.

The first three patches should be pretty clear-cut and harmless and just
make way for a neater switch to demand faulting.  The code touched by
the x86 patches is either already present or (AFAICT) not needed for
other architectures.  Comments?  Anyone want to try this out on their
specific huge page workload and architecture combinati?

The patches are:
  x86-pte_huge - Create pte_huge() test function
  x86-move-stale-pgtable - Check for stale pte in huge_pte_alloc()
  x86-walk-check - Check for not present huge page table entries
  htlb-fault - Demand faulting for huge pages

Patches coming soon in reply to this message.

--
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>