path: root/arch/powerpc/mm/hash_utils_64.c
diff options
authorDavid Gibson <david@gibson.dropbear.id.au>2009-10-26 19:24:31 +0000
committerBenjamin Herrenschmidt <benh@kernel.crashing.org>2009-10-30 17:20:58 +1100
commita4fe3ce7699bfe1bd88f816b55d42d8fe1dac655 (patch)
treeb72c982ffbb9f05d78a952288d60c4dc2d31a4d9 /arch/powerpc/mm/hash_utils_64.c
parenta0668cdc154e54bf0c85182e0535eea237d53146 (diff)
powerpc/mm: Allow more flexible layouts for hugepage pagetables
Currently each available hugepage size uses a slightly different pagetable layout: that is, the bottem level table of pointers to hugepages is a different size, and may branch off from the normal page tables at a different level. Every hugepage aware path that needs to walk the pagetables must therefore look up the hugepage size from the slice info first, and work out the correct way to walk the pagetables accordingly. Future hardware is likely to add more possible hugepage sizes, more layout options and more mess. This patch, therefore reworks the handling of hugepage pagetables to reduce this complexity. In the new scheme, instead of having to consult the slice mask, pagetable walking code can check a flag in the PGD/PUD/PMD entries to see where to branch off to hugepage pagetables, and the entry also contains the information (eseentially hugepage shift) necessary to then interpret that table without recourse to the slice mask. This scheme can be extended neatly to handle multiple levels of self-describing "special" hugepage pagetables, although for now we assume only one level exists. This approach means that only the pagetable allocation path needs to know how the pagetables should be set out. All other (hugepage) pagetable walking paths can just interpret the structure as they go. There already was a flag bit in PGD/PUD/PMD entries for hugepage directory pointers, but it was only used for debug. We alter that flag bit to instead be a 0 in the MSB to indicate a hugepage pagetable pointer (normally it would be 1 since the pointer lies in the linear mapping). This means that asm pagetable walking can test for (and punt on) hugepage pointers with the same test that checks for unpopulated page directory entries (beq becomes bge), since hugepage pointers will always be positive, and normal pointers always negative. While we're at it, we get rid of the confusing (and grep defeating) #defining of hugepte_shift to be the same thing as mmu_huge_psizes. Signed-off-by: David Gibson <dwg@au1.ibm.com> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Diffstat (limited to 'arch/powerpc/mm/hash_utils_64.c')
1 files changed, 14 insertions, 12 deletions
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 1ade7eb6ae0..485dcd197a6 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -891,6 +891,7 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
unsigned long vsid;
struct mm_struct *mm;
pte_t *ptep;
+ unsigned hugeshift;
const struct cpumask *tmp;
int rc, user_region = 0, local = 0;
int psize, ssize;
@@ -943,30 +944,31 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
if (user_region && cpumask_equal(mm_cpumask(mm), tmp))
local = 1;
- /* Handle hugepage regions */
- if (HPAGE_SHIFT && mmu_huge_psizes[psize]) {
- DBG_LOW(" -> huge page !\n");
- return hash_huge_page(mm, access, ea, vsid, local, trap);
- }
- /* If we use 4K pages and our psize is not 4K, then we are hitting
- * a special driver mapping, we need to align the address before
- * we fetch the PTE
+ /* If we use 4K pages and our psize is not 4K, then we might
+ * be hitting a special driver mapping, and need to align the
+ * address before we fetch the PTE.
+ *
+ * It could also be a hugepage mapping, in which case this is
+ * not necessary, but it's not harmful, either.
if (psize != MMU_PAGE_4K)
ea &= ~((1ul << mmu_psize_defs[psize].shift) - 1);
#endif /* CONFIG_PPC_64K_PAGES */
/* Get PTE and page size from page tables */
- ptep = find_linux_pte(pgdir, ea);
+ ptep = find_linux_pte_or_hugepte(pgdir, ea, &hugeshift);
if (ptep == NULL || !pte_present(*ptep)) {
DBG_LOW(" no PTE !\n");
return 1;
+ if (hugeshift)
+ return __hash_page_huge(ea, access, vsid, ptep, trap, local,
+ ssize, hugeshift, psize);
DBG_LOW(" i-pte: %016lx\n", pte_val(*ptep));