Buglet in 16G page handling

[David Gibson]

When BenH and I were looking at the new code for handling 16G pages,
we noticed a small bug.  It doesn't actually break anything user
visible, but it's certainly not the way things are supposed to be.
The 16G patches didn't update the huge_pte_offset() and
huge_pte_alloc() functions, which means that the hugepte tables for
16G pages will be allocated much further down the page table tree than
they should be - allocating several levels of page table with a single
entry in them along the way.

The patch below is supposed to fix this, cleaning up the existing
handling of 64k vs 16M pages while its at it.  However, it needs some
testing.

I've checked that it doesn't break existing 16M support, either with
4k or 64k base pages.  I haven't figured out how to test with 64k
pages yet, at least until the multisize support goes into
libhugetlbfs.  For 16G pages, I just don't have access to a machine
with enough memory to test.  Jon, presumably you must have found such
a machine when you did the 16G page support in the first place.  Do
you still have access, and can you test this patch?

Index: working-2.6/arch/powerpc/mm/hugetlbpage.c
===================================================================
--- working-2.6.orig/arch/powerpc/mm/hugetlbpage.c	2008-09-02 13:39:52.000000000 +1000
+++ working-2.6/arch/powerpc/mm/hugetlbpage.c	2008-09-02 14:08:56.000000000 +1000
@@ -128,29 +128,37 @@ static int __hugepte_alloc(struct mm_str
 	return 0;
 }
 
-/* Base page size affects how we walk hugetlb page tables */
-#ifdef CONFIG_PPC_64K_PAGES
-#define hpmd_offset(pud, addr, h)	pmd_offset(pud, addr)
-#define hpmd_alloc(mm, pud, addr, h)	pmd_alloc(mm, pud, addr)
-#else
-static inline
-pmd_t *hpmd_offset(pud_t *pud, unsigned long addr, struct hstate *hstate)
+
+static pud_t *hpud_offset(pgd_t *pgd, unsigned long addr, struct hstate *hstate)
+{
+	if (huge_page_shift(hstate) < PUD_SHIFT)
+		return pud_offset(pgd, addr);
+	else
+		return (pud_t *) pgd;
+}
+static pud_t *hpud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long addr,
+			 struct hstate *hstate)
 {
-	if (huge_page_shift(hstate) == PAGE_SHIFT_64K)
+	if (huge_page_shift(hstate) < PUD_SHIFT)
+		return pud_alloc(mm, pgd, addr);
+	else
+		return (pud_t *) pgd;
+}
+static pmd_t *hpmd_offset(pud_t *pud, unsigned long addr, struct hstate *hstate)
+{
+	if (huge_page_shift(hstate) < PMD_SHIFT)
 		return pmd_offset(pud, addr);
 	else
 		return (pmd_t *) pud;
 }
-static inline
-pmd_t *hpmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long addr,
-		  struct hstate *hstate)
+static pmd_t *hpmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long addr,
+			 struct hstate *hstate)
 {
-	if (huge_page_shift(hstate) == PAGE_SHIFT_64K)
+	if (huge_page_shift(hstate) < PMD_SHIFT)
 		return pmd_alloc(mm, pud, addr);
 	else
 		return (pmd_t *) pud;
 }
-#endif
 
 /* Build list of addresses of gigantic pages.  This function is used in early
  * boot before the buddy or bootmem allocator is setup.
@@ -204,7 +212,7 @@ pte_t *huge_pte_offset(struct mm_struct 
 
 	pg = pgd_offset(mm, addr);
 	if (!pgd_none(*pg)) {
-		pu = pud_offset(pg, addr);
+		pu = hpud_offset(pg, addr, hstate);
 		if (!pud_none(*pu)) {
 			pm = hpmd_offset(pu, addr, hstate);
 			if (!pmd_none(*pm))
@@ -233,7 +241,7 @@ pte_t *huge_pte_alloc(struct mm_struct *
 	addr &= hstate->mask;
 
 	pg = pgd_offset(mm, addr);
-	pu = pud_alloc(mm, pg, addr);
+	pu = hpud_alloc(mm, pg, addr, hstate);
 
 	if (pu) {
 		pm = hpmd_alloc(mm, pu, addr, hstate);


-- 
David Gibson			| I'll have my music baroque, and my code
david AT gibson.dropbear.id.au	| minimalist, thank you.  NOT _the_ _other_
				| _way_ _around_!
http://www.ozlabs.org/~dgibson