[POWERPC] Don't use SLAB/SLUB for PTE pages
commit517e22638c282bb07c52a11f928961ed4822196b
authorHugh Dickins <hugh@veritas.com>
Wed, 9 May 2007 04:38:48 +0000 (9 14:38 +1000)
committerPaul Mackerras <paulus@samba.org>
Wed, 9 May 2007 06:35:00 +0000 (9 16:35 +1000)
tree7eab8eb1242ee18f75c325077f26bdcb86133512
parentf1fa74f4afe96b0e4ac2beaa61fa4f4667acdcbb
[POWERPC] Don't use SLAB/SLUB for PTE pages

The SLUB allocator relies on struct page fields first_page and slab,
overwritten by ptl when SPLIT_PTLOCK: so the SLUB allocator cannot then
be used for the lowest level of pagetable pages.  This was obstructing
SLUB on PowerPC, which uses kmem_caches for its pagetables.  So convert
its pte level to use normal gfp pages (whereas pmd, pud and 64k-page pgd
want partpages, so continue to use kmem_caches for pmd, pud and pgd).

Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
arch/powerpc/Kconfig
arch/powerpc/mm/init_64.c
include/asm-powerpc/pgalloc-64.h