Merge branch 'master' into percpu

Conflicts:
	arch/powerpc/platforms/pseries/hvCall.S
	include/linux/percpu.h

1 files changed, 290 insertions, 502 deletions

diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 90df6ffe3a4..123f7070238 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -7,29 +7,17 @@
  * Copyright (C) 2002, Rohit Seth <rohit.seth@intel.com>
  */
 
-#include <linux/init.h>
-#include <linux/fs.h>
 #include <linux/mm.h>
+#include <linux/io.h>
 #include <linux/hugetlb.h>
-#include <linux/pagemap.h>
-#include <linux/slab.h>
-#include <linux/err.h>
-#include <linux/sysctl.h>
-#include <asm/mman.h>
+#include <asm/pgtable.h>
 #include <asm/pgalloc.h>
 #include <asm/tlb.h>
-#include <asm/tlbflush.h>
-#include <asm/mmu_context.h>
-#include <asm/machdep.h>
-#include <asm/cputable.h>
-#include <asm/spu.h>
 
 #define PAGE_SHIFT_64K	16
 #define PAGE_SHIFT_16M	24
 #define PAGE_SHIFT_16G	34
 
-#define NUM_LOW_AREAS	(0x100000000UL >> SID_SHIFT)
-#define NUM_HIGH_AREAS	(PGTABLE_RANGE >> HTLB_AREA_SHIFT)
 #define MAX_NUMBER_GPAGES	1024
 
 /* Tracks the 16G pages after the device tree is scanned and before the
@@ -37,53 +25,17 @@
 static unsigned long gpage_freearray[MAX_NUMBER_GPAGES];
 static unsigned nr_gpages;
 
-/* Array of valid huge page sizes - non-zero value(hugepte_shift) is
- * stored for the huge page sizes that are valid.
- */
-unsigned int mmu_huge_psizes[MMU_PAGE_COUNT] = { }; /* initialize all to 0 */
-
-#define hugepte_shift			mmu_huge_psizes
-#define PTRS_PER_HUGEPTE(psize)		(1 << hugepte_shift[psize])
-#define HUGEPTE_TABLE_SIZE(psize)	(sizeof(pte_t) << hugepte_shift[psize])
-
-#define HUGEPD_SHIFT(psize)		(mmu_psize_to_shift(psize) \
-						+ hugepte_shift[psize])
-#define HUGEPD_SIZE(psize)		(1UL << HUGEPD_SHIFT(psize))
-#define HUGEPD_MASK(psize)		(~(HUGEPD_SIZE(psize)-1))
-
-/* Subtract one from array size because we don't need a cache for 4K since
- * is not a huge page size */
-#define HUGE_PGTABLE_INDEX(psize)	(HUGEPTE_CACHE_NUM + psize - 1)
-#define HUGEPTE_CACHE_NAME(psize)	(huge_pgtable_cache_name[psize])
-
-static const char *huge_pgtable_cache_name[MMU_PAGE_COUNT] = {
-	[MMU_PAGE_64K]	= "hugepte_cache_64K",
-	[MMU_PAGE_1M]	= "hugepte_cache_1M",
-	[MMU_PAGE_16M]	= "hugepte_cache_16M",
-	[MMU_PAGE_16G]	= "hugepte_cache_16G",
-};
-
 /* Flag to mark huge PD pointers.  This means pmd_bad() and pud_bad()
  * will choke on pointers to hugepte tables, which is handy for
  * catching screwups early. */
-#define HUGEPD_OK	0x1
-
-typedef struct { unsigned long pd; } hugepd_t;
-
-#define hugepd_none(hpd)	((hpd).pd == 0)
 
 static inline int shift_to_mmu_psize(unsigned int shift)
 {
-	switch (shift) {
-#ifndef CONFIG_PPC_64K_PAGES
-	case PAGE_SHIFT_64K:
-	    return MMU_PAGE_64K;
-#endif
-	case PAGE_SHIFT_16M:
-	    return MMU_PAGE_16M;
-	case PAGE_SHIFT_16G:
-	    return MMU_PAGE_16G;
-	}
+	int psize;
+
+	for (psize = 0; psize < MMU_PAGE_COUNT; ++psize)
+		if (mmu_psize_defs[psize].shift == shift)
+			return psize;
 	return -1;
 }
 
@@ -94,71 +46,126 @@ static inline unsigned int mmu_psize_to_shift(unsigned int mmu_psize)
 	BUG();
 }
 
+#define hugepd_none(hpd)	((hpd).pd == 0)
+
 static inline pte_t *hugepd_page(hugepd_t hpd)
 {
-	BUG_ON(!(hpd.pd & HUGEPD_OK));
-	return (pte_t *)(hpd.pd & ~HUGEPD_OK);
+	BUG_ON(!hugepd_ok(hpd));
+	return (pte_t *)((hpd.pd & ~HUGEPD_SHIFT_MASK) | 0xc000000000000000);
+}
+
+static inline unsigned int hugepd_shift(hugepd_t hpd)
+{
+	return hpd.pd & HUGEPD_SHIFT_MASK;
 }
 
-static inline pte_t *hugepte_offset(hugepd_t *hpdp, unsigned long addr,
-				    struct hstate *hstate)
+static inline pte_t *hugepte_offset(hugepd_t *hpdp, unsigned long addr, unsigned pdshift)
 {
-	unsigned int shift = huge_page_shift(hstate);
-	int psize = shift_to_mmu_psize(shift);
-	unsigned long idx = ((addr >> shift) & (PTRS_PER_HUGEPTE(psize)-1));
+	unsigned long idx = (addr & ((1UL << pdshift) - 1)) >> hugepd_shift(*hpdp);
 	pte_t *dir = hugepd_page(*hpdp);
 
 	return dir + idx;
 }
 
+pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, unsigned *shift)
+{
+	pgd_t *pg;
+	pud_t *pu;
+	pmd_t *pm;
+	hugepd_t *hpdp = NULL;
+	unsigned pdshift = PGDIR_SHIFT;
+
+	if (shift)
+		*shift = 0;
+
+	pg = pgdir + pgd_index(ea);
+	if (is_hugepd(pg)) {
+		hpdp = (hugepd_t *)pg;
+	} else if (!pgd_none(*pg)) {
+		pdshift = PUD_SHIFT;
+		pu = pud_offset(pg, ea);
+		if (is_hugepd(pu))
+			hpdp = (hugepd_t *)pu;
+		else if (!pud_none(*pu)) {
+			pdshift = PMD_SHIFT;
+			pm = pmd_offset(pu, ea);
+			if (is_hugepd(pm))
+				hpdp = (hugepd_t *)pm;
+			else if (!pmd_none(*pm)) {
+				return pte_offset_map(pm, ea);
+			}
+		}
+	}
+
+	if (!hpdp)
+		return NULL;
+
+	if (shift)
+		*shift = hugepd_shift(*hpdp);
+	return hugepte_offset(hpdp, ea, pdshift);
+}
+
+pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
+{
+	return find_linux_pte_or_hugepte(mm->pgd, addr, NULL);
+}
+
 static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,
-			   unsigned long address, unsigned int psize)
+			   unsigned long address, unsigned pdshift, unsigned pshift)
 {
-	pte_t *new = kmem_cache_zalloc(pgtable_cache[HUGE_PGTABLE_INDEX(psize)],
-				      GFP_KERNEL|__GFP_REPEAT);
+	pte_t *new = kmem_cache_zalloc(PGT_CACHE(pdshift - pshift),
+				       GFP_KERNEL|__GFP_REPEAT);
+
+	BUG_ON(pshift > HUGEPD_SHIFT_MASK);
+	BUG_ON((unsigned long)new & HUGEPD_SHIFT_MASK);
 
 	if (! new)
 		return -ENOMEM;
 
 	spin_lock(&mm->page_table_lock);
 	if (!hugepd_none(*hpdp))
-		kmem_cache_free(pgtable_cache[HUGE_PGTABLE_INDEX(psize)], new);
+		kmem_cache_free(PGT_CACHE(pdshift - pshift), new);
 	else
-		hpdp->pd = (unsigned long)new | HUGEPD_OK;
+		hpdp->pd = ((unsigned long)new & ~0x8000000000000000) | pshift;
 	spin_unlock(&mm->page_table_lock);
 	return 0;
 }
 
-
-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)
+pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz)
 {
-	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 pmd_t *hpmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long addr,
-			 struct hstate *hstate)
-{
-	if (huge_page_shift(hstate) < PMD_SHIFT)
-		return pmd_alloc(mm, pud, addr);
-	else
-		return (pmd_t *) pud;
+	pgd_t *pg;
+	pud_t *pu;
+	pmd_t *pm;
+	hugepd_t *hpdp = NULL;
+	unsigned pshift = __ffs(sz);
+	unsigned pdshift = PGDIR_SHIFT;
+
+	addr &= ~(sz-1);
+
+	pg = pgd_offset(mm, addr);
+	if (pshift >= PUD_SHIFT) {
+		hpdp = (hugepd_t *)pg;
+	} else {
+		pdshift = PUD_SHIFT;
+		pu = pud_alloc(mm, pg, addr);
+		if (pshift >= PMD_SHIFT) {
+			hpdp = (hugepd_t *)pu;
+		} else {
+			pdshift = PMD_SHIFT;
+			pm = pmd_alloc(mm, pu, addr);
+			hpdp = (hugepd_t *)pm;
+		}
+	}
+
+	if (!hpdp)
+		return NULL;
+
+	BUG_ON(!hugepd_none(*hpdp) && !hugepd_ok(*hpdp));
+
+	if (hugepd_none(*hpdp) && __hugepte_alloc(mm, hpdp, addr, pdshift, pshift))
+		return NULL;
+
+	return hugepte_offset(hpdp, addr, pdshift);
 }
 
 /* Build list of addresses of gigantic pages.  This function is used in early
@@ -192,94 +199,38 @@ int alloc_bootmem_huge_page(struct hstate *hstate)
 	return 1;
 }
 
-
-/* Modelled after find_linux_pte() */
-pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
-{
-	pgd_t *pg;
-	pud_t *pu;
-	pmd_t *pm;
-
-	unsigned int psize;
-	unsigned int shift;
-	unsigned long sz;
-	struct hstate *hstate;
-	psize = get_slice_psize(mm, addr);
-	shift = mmu_psize_to_shift(psize);
-	sz = ((1UL) << shift);
-	hstate = size_to_hstate(sz);
-
-	addr &= hstate->mask;
-
-	pg = pgd_offset(mm, addr);
-	if (!pgd_none(*pg)) {
-		pu = hpud_offset(pg, addr, hstate);
-		if (!pud_none(*pu)) {
-			pm = hpmd_offset(pu, addr, hstate);
-			if (!pmd_none(*pm))
-				return hugepte_offset((hugepd_t *)pm, addr,
-						      hstate);
-		}
-	}
-
-	return NULL;
-}
-
-pte_t *huge_pte_alloc(struct mm_struct *mm,
-			unsigned long addr, unsigned long sz)
-{
-	pgd_t *pg;
-	pud_t *pu;
-	pmd_t *pm;
-	hugepd_t *hpdp = NULL;
-	struct hstate *hstate;
-	unsigned int psize;
-	hstate = size_to_hstate(sz);
-
-	psize = get_slice_psize(mm, addr);
-	BUG_ON(!mmu_huge_psizes[psize]);
-
-	addr &= hstate->mask;
-
-	pg = pgd_offset(mm, addr);
-	pu = hpud_alloc(mm, pg, addr, hstate);
-
-	if (pu) {
-		pm = hpmd_alloc(mm, pu, addr, hstate);
-		if (pm)
-			hpdp = (hugepd_t *)pm;
-	}
-
-	if (! hpdp)
-		return NULL;
-
-	if (hugepd_none(*hpdp) && __hugepte_alloc(mm, hpdp, addr, psize))
-		return NULL;
-
-	return hugepte_offset(hpdp, addr, hstate);
-}
-
 int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
 {
 	return 0;
 }
 
-static void free_hugepte_range(struct mmu_gather *tlb, hugepd_t *hpdp,
-			       unsigned int psize)
+static void free_hugepd_range(struct mmu_gather *tlb, hugepd_t *hpdp, int pdshift,
+			      unsigned long start, unsigned long end,
+			      unsigned long floor, unsigned long ceiling)
 {
 	pte_t *hugepte = hugepd_page(*hpdp);
+	unsigned shift = hugepd_shift(*hpdp);
+	unsigned long pdmask = ~((1UL << pdshift) - 1);
+
+	start &= pdmask;
+	if (start < floor)
+		return;
+	if (ceiling) {
+		ceiling &= pdmask;
+		if (! ceiling)
+			return;
+	}
+	if (end - 1 > ceiling - 1)
+		return;
 
 	hpdp->pd = 0;
 	tlb->need_flush = 1;
-	pgtable_free_tlb(tlb, pgtable_free_cache(hugepte,
-						 HUGEPTE_CACHE_NUM+psize-1,
-						 PGF_CACHENUM_MASK));
+	pgtable_free_tlb(tlb, hugepte, pdshift - shift);
 }
 
 static void hugetlb_free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
 				   unsigned long addr, unsigned long end,
-				   unsigned long floor, unsigned long ceiling,
-				   unsigned int psize)
+				   unsigned long floor, unsigned long ceiling)
 {
 	pmd_t *pmd;
 	unsigned long next;
@@ -291,7 +242,8 @@ static void hugetlb_free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
 		next = pmd_addr_end(addr, end);
 		if (pmd_none(*pmd))
 			continue;
-		free_hugepte_range(tlb, (hugepd_t *)pmd, psize);
+		free_hugepd_range(tlb, (hugepd_t *)pmd, PMD_SHIFT,
+				  addr, next, floor, ceiling);
 	} while (pmd++, addr = next, addr != end);
 
 	start &= PUD_MASK;
@@ -317,23 +269,19 @@ static void hugetlb_free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
 	pud_t *pud;
 	unsigned long next;
 	unsigned long start;
-	unsigned int shift;
-	unsigned int psize = get_slice_psize(tlb->mm, addr);
-	shift = mmu_psize_to_shift(psize);
 
 	start = addr;
 	pud = pud_offset(pgd, addr);
 	do {
 		next = pud_addr_end(addr, end);
-		if (shift < PMD_SHIFT) {
+		if (!is_hugepd(pud)) {
 			if (pud_none_or_clear_bad(pud))
 				continue;
 			hugetlb_free_pmd_range(tlb, pud, addr, next, floor,
-					       ceiling, psize);
+					       ceiling);
 		} else {
-			if (pud_none(*pud))
-				continue;
-			free_hugepte_range(tlb, (hugepd_t *)pud, psize);
+			free_hugepd_range(tlb, (hugepd_t *)pud, PUD_SHIFT,
+					  addr, next, floor, ceiling);
 		}
 	} while (pud++, addr = next, addr != end);
 
@@ -364,121 +312,56 @@ void hugetlb_free_pgd_range(struct mmu_gather *tlb,
 {
 	pgd_t *pgd;
 	unsigned long next;
-	unsigned long start;
 
 	/*
-	 * Comments below take from the normal free_pgd_range().  They
-	 * apply here too.  The tests against HUGEPD_MASK below are
-	 * essential, because we *don't* test for this at the bottom
-	 * level.  Without them we'll attempt to free a hugepte table
-	 * when we unmap just part of it, even if there are other
-	 * active mappings using it.
-	 *
-	 * The next few lines have given us lots of grief...
-	 *
-	 * Why are we testing HUGEPD* at this top level?  Because
-	 * often there will be no work to do at all, and we'd prefer
-	 * not to go all the way down to the bottom just to discover
-	 * that.
-	 *
-	 * Why all these "- 1"s?  Because 0 represents both the bottom
-	 * of the address space and the top of it (using -1 for the
-	 * top wouldn't help much: the masks would do the wrong thing).
-	 * The rule is that addr 0 and floor 0 refer to the bottom of
-	 * the address space, but end 0 and ceiling 0 refer to the top
-	 * Comparisons need to use "end - 1" and "ceiling - 1" (though
-	 * that end 0 case should be mythical).
+	 * Because there are a number of different possible pagetable
+	 * layouts for hugepage ranges, we limit knowledge of how
+	 * things should be laid out to the allocation path
+	 * (huge_pte_alloc(), above).  Everything else works out the
+	 * structure as it goes from information in the hugepd
+	 * pointers.  That means that we can't here use the
+	 * optimization used in the normal page free_pgd_range(), of
+	 * checking whether we're actually covering a large enough
+	 * range to have to do anything at the top level of the walk
+	 * instead of at the bottom.
 	 *
-	 * Wherever addr is brought up or ceiling brought down, we
-	 * must be careful to reject "the opposite 0" before it
-	 * confuses the subsequent tests.  But what about where end is
-	 * brought down by HUGEPD_SIZE below? no, end can't go down to
-	 * 0 there.
-	 *
-	 * Whereas we round start (addr) and ceiling down, by different
-	 * masks at different levels, in order to test whether a table
-	 * now has no other vmas using it, so can be freed, we don't
-	 * bother to round floor or end up - the tests don't need that.
+	 * To make sense of this, you should probably go read the big
+	 * block comment at the top of the normal free_pgd_range(),
+	 * too.
 	 */
-	unsigned int psize = get_slice_psize(tlb->mm, addr);
-
-	addr &= HUGEPD_MASK(psize);
-	if (addr < floor) {
-		addr += HUGEPD_SIZE(psize);
-		if (!addr)
-			return;
-	}
-	if (ceiling) {
-		ceiling &= HUGEPD_MASK(psize);
-		if (!ceiling)
-			return;
-	}
-	if (end - 1 > ceiling - 1)
-		end -= HUGEPD_SIZE(psize);
-	if (addr > end - 1)
-		return;
 
-	start = addr;
 	pgd = pgd_offset(tlb->mm, addr);
 	do {
-		psize = get_slice_psize(tlb->mm, addr);
-		BUG_ON(!mmu_huge_psizes[psize]);
 		next = pgd_addr_end(addr, end);
-		if (mmu_psize_to_shift(psize) < PUD_SHIFT) {
+		if (!is_hugepd(pgd)) {
 			if (pgd_none_or_clear_bad(pgd))
 				continue;
 			hugetlb_free_pud_range(tlb, pgd, addr, next, floor, ceiling);
 		} else {
-			if (pgd_none(*pgd))
-				continue;
-			free_hugepte_range(tlb, (hugepd_t *)pgd, psize);
+			free_hugepd_range(tlb, (hugepd_t *)pgd, PGDIR_SHIFT,
+					  addr, next, floor, ceiling);
 		}
 	} while (pgd++, addr = next, addr != end);
 }
 
-void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
-		     pte_t *ptep, pte_t pte)
-{
-	if (pte_present(*ptep)) {
-		/* We open-code pte_clear because we need to pass the right
-		 * argument to hpte_need_flush (huge / !huge). Might not be
-		 * necessary anymore if we make hpte_need_flush() get the
-		 * page size from the slices
-		 */
-		unsigned int psize = get_slice_psize(mm, addr);
-		unsigned int shift = mmu_psize_to_shift(psize);
-		unsigned long sz = ((1UL) << shift);
-		struct hstate *hstate = size_to_hstate(sz);
-		pte_update(mm, addr & hstate->mask, ptep, ~0UL, 1);
-	}
-	*ptep = __pte(pte_val(pte) & ~_PAGE_HPTEFLAGS);
-}
-
-pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
-			      pte_t *ptep)
-{
-	unsigned long old = pte_update(mm, addr, ptep, ~0UL, 1);
-	return __pte(old);
-}
-
 struct page *
 follow_huge_addr(struct mm_struct *mm, unsigned long address, int write)
 {
 	pte_t *ptep;
 	struct page *page;
-	unsigned int mmu_psize = get_slice_psize(mm, address);
+	unsigned shift;
+	unsigned long mask;
+
+	ptep = find_linux_pte_or_hugepte(mm->pgd, address, &shift);
 
 	/* Verify it is a huge page else bail. */
-	if (!mmu_huge_psizes[mmu_psize])
+	if (!ptep || !shift)
 		return ERR_PTR(-EINVAL);
 
-	ptep = huge_pte_offset(mm, address);
+	mask = (1UL << shift) - 1;
 	page = pte_page(*ptep);
-	if (page) {
-		unsigned int shift = mmu_psize_to_shift(mmu_psize);
-		unsigned long sz = ((1UL) << shift);
-		page += (address % sz) / PAGE_SIZE;
-	}
+	if (page)
+		page += (address & mask) / PAGE_SIZE;
 
 	return page;
 }
@@ -501,6 +384,82 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 	return NULL;
 }
 
+static noinline int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
+		       unsigned long end, int write, struct page **pages, int *nr)
+{
+	unsigned long mask;
+	unsigned long pte_end;
+	struct page *head, *page;
+	pte_t pte;
+	int refs;
+
+	pte_end = (addr + sz) & ~(sz-1);
+	if (pte_end < end)
+		end = pte_end;
+
+	pte = *ptep;
+	mask = _PAGE_PRESENT | _PAGE_USER;
+	if (write)
+		mask |= _PAGE_RW;
+
+	if ((pte_val(pte) & mask) != mask)
+		return 0;
+
+	/* hugepages are never "special" */
+	VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
+
+	refs = 0;
+	head = pte_page(pte);
+
+	page = head + ((addr & (sz-1)) >> PAGE_SHIFT);
+	do {
+		VM_BUG_ON(compound_head(page) != head);
+		pages[*nr] = page;
+		(*nr)++;
+		page++;
+		refs++;
+	} while (addr += PAGE_SIZE, addr != end);
+
+	if (!page_cache_add_speculative(head, refs)) {
+		*nr -= refs;
+		return 0;
+	}
+
+	if (unlikely(pte_val(pte) != pte_val(*ptep))) {
+		/* Could be optimized better */
+		while (*nr) {
+			put_page(page);
+			(*nr)--;
+		}
+	}
+
+	return 1;
+}
+
+static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end,
+				      unsigned long sz)
+{
+	unsigned long __boundary = (addr + sz) & ~(sz-1);
+	return (__boundary - 1 < end - 1) ? __boundary : end;
+}
+
+int gup_hugepd(hugepd_t *hugepd, unsigned pdshift,
+	       unsigned long addr, unsigned long end,
+	       int write, struct page **pages, int *nr)
+{
+	pte_t *ptep;
+	unsigned long sz = 1UL << hugepd_shift(*hugepd);
+	unsigned long next;
+
+	ptep = hugepte_offset(hugepd, addr, pdshift);
+	do {
+		next = hugepte_addr_end(addr, end, sz);
+		if (!gup_hugepte(ptep, sz, addr, end, write, pages, nr))
+			return 0;
+	} while (ptep++, addr = next, addr != end);
+
+	return 1;
+}
 
 unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 					unsigned long len, unsigned long pgoff,
@@ -509,8 +468,6 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 	struct hstate *hstate = hstate_file(file);
 	int mmu_psize = shift_to_mmu_psize(huge_page_shift(hstate));
 
-	if (!mmu_huge_psizes[mmu_psize])
-		return -EINVAL;
 	return slice_get_unmapped_area(addr, len, flags, mmu_psize, 1, 0);
 }
 
@@ -521,229 +478,46 @@ unsigned long vma_mmu_pagesize(struct vm_area_struct *vma)
 	return 1UL << mmu_psize_to_shift(psize);
 }
 
-/*
- * Called by asm hashtable.S for doing lazy icache flush
- */
-static unsigned int hash_huge_page_do_lazy_icache(unsigned long rflags,
-					pte_t pte, int trap, unsigned long sz)
+static int __init add_huge_page_size(unsigned long long size)
 {
-	struct page *page;
-	int i;
-
-	if (!pfn_valid(pte_pfn(pte)))
-		return rflags;
-
-	page = pte_page(pte);
-
-	/* page is dirty */
-	if (!test_bit(PG_arch_1, &page->flags) && !PageReserved(page)) {
-		if (trap == 0x400) {
-			for (i = 0; i < (sz / PAGE_SIZE); i++)
-				__flush_dcache_icache(page_address(page+i));
-			set_bit(PG_arch_1, &page->flags);
-		} else {
-			rflags |= HPTE_R_N;
-		}
-	}
-	return rflags;
-}
+	int shift = __ffs(size);
+	int mmu_psize;
 
-int hash_huge_page(struct mm_struct *mm, unsigned long access,
-		   unsigned long ea, unsigned long vsid, int local,
-		   unsigned long trap)
-{
-	pte_t *ptep;
-	unsigned long old_pte, new_pte;
-	unsigned long va, rflags, pa, sz;
-	long slot;
-	int err = 1;
-	int ssize = user_segment_size(ea);
-	unsigned int mmu_psize;
-	int shift;
-	mmu_psize = get_slice_psize(mm, ea);
-
-	if (!mmu_huge_psizes[mmu_psize])
-		goto out;
-	ptep = huge_pte_offset(mm, ea);
-
-	/* Search the Linux page table for a match with va */
-	va = hpt_va(ea, vsid, ssize);
+	/* Check that it is a page size supported by the hardware and
+	 * that it fits within pagetable and slice limits. */
+	if (!is_power_of_2(size)
+	    || (shift > SLICE_HIGH_SHIFT) || (shift <= PAGE_SHIFT))
+		return -EINVAL;
 
-	/*
-	 * If no pte found or not present, send the problem up to
-	 * do_page_fault
-	 */
-	if (unlikely(!ptep || pte_none(*ptep)))
-		goto out;
+	if ((mmu_psize = shift_to_mmu_psize(shift)) < 0)
+		return -EINVAL;
 
-	/* 
-	 * Check the user's access rights to the page.  If access should be
-	 * prevented then send the problem up to do_page_fault.
+#ifdef CONFIG_SPU_FS_64K_LS
+	/* Disable support for 64K huge pages when 64K SPU local store
+	 * support is enabled as the current implementation conflicts.
 	 */
-	if (unlikely(access & ~pte_val(*ptep)))
-		goto out;
-	/*
-	 * At this point, we have a pte (old_pte) which can be used to build
-	 * or update an HPTE. There are 2 cases:
-	 *
-	 * 1. There is a valid (present) pte with no associated HPTE (this is 
-	 *	the most common case)
-	 * 2. There is a valid (present) pte with an associated HPTE. The
-	 *	current values of the pp bits in the HPTE prevent access
-	 *	because we are doing software DIRTY bit management and the
-	 *	page is currently not DIRTY. 
-	 */
-
-
-	do {
-		old_pte = pte_val(*ptep);
-		if (old_pte & _PAGE_BUSY)
-			goto out;
-		new_pte = old_pte | _PAGE_BUSY | _PAGE_ACCESSED;
-	} while(old_pte != __cmpxchg_u64((unsigned long *)ptep,
-					 old_pte, new_pte));
-
-	rflags = 0x2 | (!(new_pte & _PAGE_RW));
- 	/* _PAGE_EXEC -> HW_NO_EXEC since it's inverted */
-	rflags |= ((new_pte & _PAGE_EXEC) ? 0 : HPTE_R_N);
-	shift = mmu_psize_to_shift(mmu_psize);
-	sz = ((1UL) << shift);
-	if (!cpu_has_feature(CPU_FTR_COHERENT_ICACHE))
-		/* No CPU has hugepages but lacks no execute, so we
-		 * don't need to worry about that case */
-		rflags = hash_huge_page_do_lazy_icache(rflags, __pte(old_pte),
-						       trap, sz);
-
-	/* Check if pte already has an hpte (case 2) */
-	if (unlikely(old_pte & _PAGE_HASHPTE)) {
-		/* There MIGHT be an HPTE for this pte */
-		unsigned long hash, slot;
-
-		hash = hpt_hash(va, shift, ssize);
-		if (old_pte & _PAGE_F_SECOND)
-			hash = ~hash;
-		slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
-		slot += (old_pte & _PAGE_F_GIX) >> 12;
-
-		if (ppc_md.hpte_updatepp(slot, rflags, va, mmu_psize,
-					 ssize, local) == -1)
-			old_pte &= ~_PAGE_HPTEFLAGS;
-	}
-
-	if (likely(!(old_pte & _PAGE_HASHPTE))) {
-		unsigned long hash = hpt_hash(va, shift, ssize);
-		unsigned long hpte_group;
-
-		pa = pte_pfn(__pte(old_pte)) << PAGE_SHIFT;
-
-repeat:
-		hpte_group = ((hash & htab_hash_mask) *
-			      HPTES_PER_GROUP) & ~0x7UL;
-
-		/* clear HPTE slot informations in new PTE */
-#ifdef CONFIG_PPC_64K_PAGES
-		new_pte = (new_pte & ~_PAGE_HPTEFLAGS) | _PAGE_HPTE_SUB0;
-#else
-		new_pte = (new_pte & ~_PAGE_HPTEFLAGS) | _PAGE_HASHPTE;
-#endif
-		/* Add in WIMG bits */
-		rflags |= (new_pte & (_PAGE_WRITETHRU | _PAGE_NO_CACHE |
-				      _PAGE_COHERENT | _PAGE_GUARDED));
-
-		/* Insert into the hash table, primary slot */
-		slot = ppc_md.hpte_insert(hpte_group, va, pa, rflags, 0,
-					  mmu_psize, ssize);
-
-		/* Primary is full, try the secondary */
-		if (unlikely(slot == -1)) {
-			hpte_group = ((~hash & htab_hash_mask) *
-				      HPTES_PER_GROUP) & ~0x7UL; 
-			slot = ppc_md.hpte_insert(hpte_group, va, pa, rflags,
-						  HPTE_V_SECONDARY,
-						  mmu_psize, ssize);
-			if (slot == -1) {
-				if (mftb() & 0x1)
-					hpte_group = ((hash & htab_hash_mask) *
-						      HPTES_PER_GROUP)&~0x7UL;
-
-				ppc_md.hpte_remove(hpte_group);
-				goto repeat;
-                        }
-		}
-
-		if (unlikely(slot == -2))
-			panic("hash_huge_page: pte_insert failed\n");
-
-		new_pte |= (slot << 12) & (_PAGE_F_SECOND | _PAGE_F_GIX);
-	}
+	if (shift == PAGE_SHIFT_64K)
+		return -EINVAL;
+#endif /* CONFIG_SPU_FS_64K_LS */
 
-	/*
-	 * No need to use ldarx/stdcx here
-	 */
-	*ptep = __pte(new_pte & ~_PAGE_BUSY);
+	BUG_ON(mmu_psize_defs[mmu_psize].shift != shift);
 
-	err = 0;
+	/* Return if huge page size has already been setup */
+	if (size_to_hstate(size))
+		return 0;
 
- out:
-	return err;
-}
+	hugetlb_add_hstate(shift - PAGE_SHIFT);
 
-static void __init set_huge_psize(int psize)
-{
-	/* Check that it is a page size supported by the hardware and
-	 * that it fits within pagetable limits. */
-	if (mmu_psize_defs[psize].shift &&
-		mmu_psize_defs[psize].shift < SID_SHIFT_1T &&
-		(mmu_psize_defs[psize].shift > MIN_HUGEPTE_SHIFT ||
-		 mmu_psize_defs[psize].shift == PAGE_SHIFT_64K ||
-		 mmu_psize_defs[psize].shift == PAGE_SHIFT_16G)) {
-		/* Return if huge page size has already been setup or is the
-		 * same as the base page size. */
-		if (mmu_huge_psizes[psize] ||
-		   mmu_psize_defs[psize].shift == PAGE_SHIFT)
-			return;
-		if (WARN_ON(HUGEPTE_CACHE_NAME(psize) == NULL))
-			return;
-		hugetlb_add_hstate(mmu_psize_defs[psize].shift - PAGE_SHIFT);
-
-		switch (mmu_psize_defs[psize].shift) {
-		case PAGE_SHIFT_64K:
-		    /* We only allow 64k hpages with 4k base page,
-		     * which was checked above, and always put them
-		     * at the PMD */
-		    hugepte_shift[psize] = PMD_SHIFT;
-		    break;
-		case PAGE_SHIFT_16M:
-		    /* 16M pages can be at two different levels
-		     * of pagestables based on base page size */
-		    if (PAGE_SHIFT == PAGE_SHIFT_64K)
-			    hugepte_shift[psize] = PMD_SHIFT;
-		    else /* 4k base page */
-			    hugepte_shift[psize] = PUD_SHIFT;
-		    break;
-		case PAGE_SHIFT_16G:
-		    /* 16G pages are always at PGD level */
-		    hugepte_shift[psize] = PGDIR_SHIFT;
-		    break;
-		}
-		hugepte_shift[psize] -= mmu_psize_defs[psize].shift;
-	} else
-		hugepte_shift[psize] = 0;
+	return 0;
 }
 
 static int __init hugepage_setup_sz(char *str)
 {
 	unsigned long long size;
-	int mmu_psize;
-	int shift;
 
 	size = memparse(str, &str);
 
-	shift = __ffs(size);
-	mmu_psize = shift_to_mmu_psize(shift);
-	if (mmu_psize >= 0 && mmu_psize_defs[mmu_psize].shift)
-		set_huge_psize(mmu_psize);
-	else
+	if (add_huge_page_size(size) != 0)
 		printk(KERN_WARNING "Invalid huge page size specified(%llu)\n", size);
 
 	return 1;
@@ -752,41 +526,55 @@ __setup("hugepagesz=", hugepage_setup_sz);
 
 static int __init hugetlbpage_init(void)
 {
-	unsigned int psize;
+	int psize;
 
 	if (!cpu_has_feature(CPU_FTR_16M_PAGE))
 		return -ENODEV;
 
-	/* Add supported huge page sizes.  Need to change HUGE_MAX_HSTATE
-	 * and adjust PTE_NONCACHE_NUM if the number of supported huge page
-	 * sizes changes.
-	 */
-	set_huge_psize(MMU_PAGE_16M);
-	set_huge_psize(MMU_PAGE_16G);
+	for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
+		unsigned shift;
+		unsigned pdshift;
 
-	/* Temporarily disable support for 64K huge pages when 64K SPU local
-	 * store support is enabled as the current implementation conflicts.
-	 */
-#ifndef CONFIG_SPU_FS_64K_LS
-	set_huge_psize(MMU_PAGE_64K);
-#endif
+		if (!mmu_psize_defs[psize].shift)
+			continue;
 
-	for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
-		if (mmu_huge_psizes[psize]) {
-			pgtable_cache[HUGE_PGTABLE_INDEX(psize)] =
-				kmem_cache_create(
-					HUGEPTE_CACHE_NAME(psize),
-					HUGEPTE_TABLE_SIZE(psize),
-					HUGEPTE_TABLE_SIZE(psize),
-					0,
-					NULL);
-			if (!pgtable_cache[HUGE_PGTABLE_INDEX(psize)])
-				panic("hugetlbpage_init(): could not create %s"\
-				      "\n", HUGEPTE_CACHE_NAME(psize));
-		}
+		shift = mmu_psize_to_shift(psize);
+
+		if (add_huge_page_size(1ULL << shift) < 0)
+			continue;
+
+		if (shift < PMD_SHIFT)
+			pdshift = PMD_SHIFT;
+		else if (shift < PUD_SHIFT)
+			pdshift = PUD_SHIFT;
+		else
+			pdshift = PGDIR_SHIFT;
+
+		pgtable_cache_add(pdshift - shift, NULL);
+		if (!PGT_CACHE(pdshift - shift))
+			panic("hugetlbpage_init(): could not create "
+			      "pgtable cache for %d bit pagesize\n", shift);
 	}
 
+	/* Set default large page size. Currently, we pick 16M or 1M
+	 * depending on what is available
+	 */
+	if (mmu_psize_defs[MMU_PAGE_16M].shift)
+		HPAGE_SHIFT = mmu_psize_defs[MMU_PAGE_16M].shift;
+	else if (mmu_psize_defs[MMU_PAGE_1M].shift)
+		HPAGE_SHIFT = mmu_psize_defs[MMU_PAGE_1M].shift;
+
 	return 0;
 }
 
 module_init(hugetlbpage_init);
+
+void flush_dcache_icache_hugepage(struct page *page)
+{
+	int i;
+
+	BUG_ON(!PageCompound(page));
+
+	for (i = 0; i < (1UL << compound_order(page)); i++)
+		__flush_dcache_icache(page_address(page+i));
+}