CONFIG_HIGHPTE vs. sub-page page tables.

Background: I've implemented 1K/2K page tables for s390.  These sub-page
page tables are required to properly support the s390 virtualization
instruction with KVM.  The SIE instruction requires that the page tables
have 256 page table entries (pte) followed by 256 page status table entries
(pgste).  The pgstes are only required if the process is using the SIE
instruction.  The pgstes are updated by the hardware and by the hypervisor
for a number of reasons, one of them is dirty and reference bit tracking.
To avoid wasting memory the standard pte table allocation should return
1K/2K (31/64 bit) and 2K/4K if the process is using SIE.

Problem: Page size on s390 is 4K, page table size is 1K or 2K.  That means
the s390 version for pte_alloc_one cannot return a pointer to a struct
page.  Trouble is that with the CONFIG_HIGHPTE feature on x86 pte_alloc_one
cannot return a pointer to a pte either, since that would require more than
32 bit for the return value of pte_alloc_one (and the pte * would not be
accessible since its not kmapped).

Solution: The only solution I found to this dilemma is a new typedef: a
pgtable_t.  For s390 pgtable_t will be a (pte *) - to be introduced with a
later patch.  For everybody else it will be a (struct page *).  The
additional problem with the initialization of the ptl lock and the
NR_PAGETABLE accounting is solved with a constructor pgtable_page_ctor and
a destructor pgtable_page_dtor.  The page table allocation and free
functions need to call these two whenever a page table page is allocated or
freed.  pmd_populate will get a pgtable_t instead of a struct page pointer.
 To get the pgtable_t back from a pmd entry that has been installed with
pmd_populate a new function pmd_pgtable is added.  It replaces the pmd_page
call in free_pte_range and apply_to_pte_range.

Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: <linux-arch@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

53 files changed, 326 insertions, 132 deletions

diff --git a/arch/frv/mm/pgalloc.c b/arch/frv/mm/pgalloc.c
index 1a2e5c8d03a9..66f616fb4860 100644
--- a/arch/frv/mm/pgalloc.c
+++ b/arch/frv/mm/pgalloc.c
@@ -28,7 +28,7 @@ pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
         return pte;
 }
 
-struct page *pte_alloc_one(struct mm_struct *mm, unsigned long address)
+pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address)
 {
         struct page *page;
 
@@ -37,9 +37,11 @@ struct page *pte_alloc_one(struct mm_struct *mm, unsigned long address)
 #else
         page = alloc_pages(GFP_KERNEL|__GFP_REPEAT, 0);
 #endif
-        if (page)
+        if (page) {
                 clear_highpage(page);
-        flush_dcache_page(page);
+                pgtable_page_ctor(page);
+                flush_dcache_page(page);
+        }
         return page;
 }
 
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index f80f90c4d58b..ac3390f81900 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -107,19 +107,20 @@ __init_refok pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long add
         return pte;
 }
 
-struct page *pte_alloc_one(struct mm_struct *mm, unsigned long address)
+pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address)
 {
         struct page *ptepage;
 
 #ifdef CONFIG_HIGHPTE
-        gfp_t flags = GFP_KERNEL | __GFP_HIGHMEM | __GFP_REPEAT;
+        gfp_t flags = GFP_KERNEL | __GFP_HIGHMEM | __GFP_REPEAT | __GFP_ZERO;
 #else
-        gfp_t flags = GFP_KERNEL | __GFP_REPEAT;
+        gfp_t flags = GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO;
 #endif
 
         ptepage = alloc_pages(flags, 0);
-        if (ptepage)
-                clear_highpage(ptepage);
+        if (!ptepage)
+                return NULL;
+        pgtable_page_ctor(ptepage);
         return ptepage;
 }
 
@@ -131,11 +132,12 @@ void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
         free_page((unsigned long)pte);
 }
 
-void pte_free(struct mm_struct *mm, struct page *ptepage)
+void pte_free(struct mm_struct *mm, pgtable_t ptepage)
 {
 #ifdef CONFIG_SMP
         hash_page_sync();
 #endif
+        pgtable_page_dtor(ptepage);
         __free_page(ptepage);
 }
 
diff --git a/arch/ppc/mm/pgtable.c b/arch/ppc/mm/pgtable.c
index 409fcaa4994a..03a79bff1271 100644
--- a/arch/ppc/mm/pgtable.c
+++ b/arch/ppc/mm/pgtable.c
@@ -95,7 +95,7 @@ __init_refok pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long add
         return pte;
 }
 
-struct page *pte_alloc_one(struct mm_struct *mm, unsigned long address)
+pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address)
 {
         struct page *ptepage;
 
@@ -106,8 +106,10 @@ struct page *pte_alloc_one(struct mm_struct *mm, unsigned long address)
 #endif
 
         ptepage = alloc_pages(flags, 0);
-        if (ptepage)
+        if (ptepage) {
                 clear_highpage(ptepage);
+                pgtable_page_ctor(ptepage);
+        }
         return ptepage;
 }
 
@@ -119,11 +121,12 @@ void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
         free_page((unsigned long)pte);
 }
 
-void pte_free(struct mm_struct *mm, struct page *ptepage)
+void pte_free(struct mm_struct *mm, pgtable_t ptepage)
 {
 #ifdef CONFIG_SMP
         hash_page_sync();
 #endif
+        pgtable_page_dtor(ptepage);
         __free_page(ptepage);
 }
 
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index e60e0ae13402..019f518cd5a0 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -78,6 +78,7 @@ unsigned long *page_table_alloc(int noexec)
                 clear_table(table, _PAGE_TYPE_EMPTY, PAGE_SIZE);
                 page->index = (addr_t) table;
         }
+        pgtable_page_ctor(page);
         table = (unsigned long *) page_to_phys(page);
         clear_table(table, _PAGE_TYPE_EMPTY, PAGE_SIZE);
         return table;
@@ -87,6 +88,7 @@ void page_table_free(unsigned long *table)
 {
         unsigned long *shadow = get_shadow_pte(table);
 
+        pgtable_page_dtor(virt_to_page(table));
         if (shadow)
                 free_page((unsigned long) shadow);
         free_page((unsigned long) table);
diff --git a/arch/sparc/mm/srmmu.c b/arch/sparc/mm/srmmu.c
index dc98e3844a0a..23d3291a3e81 100644
--- a/arch/sparc/mm/srmmu.c
+++ b/arch/sparc/mm/srmmu.c
@@ -489,14 +489,17 @@ srmmu_pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
         return (pte_t *)srmmu_get_nocache(PTE_SIZE, PTE_SIZE);
 }
 
-static struct page *
+static pgtable_t
 srmmu_pte_alloc_one(struct mm_struct *mm, unsigned long address)
 {
         unsigned long pte;
+        struct page *page;
 
         if ((pte = (unsigned long)srmmu_pte_alloc_one_kernel(mm, address)) == 0)
                 return NULL;
-        return pfn_to_page( __nocache_pa(pte) >> PAGE_SHIFT );
+        page = pfn_to_page( __nocache_pa(pte) >> PAGE_SHIFT );
+        pgtable_page_ctor(page);
+        return page;
 }
 
 static void srmmu_free_pte_fast(pte_t *pte)
@@ -504,10 +507,11 @@ static void srmmu_free_pte_fast(pte_t *pte)
         srmmu_free_nocache((unsigned long)pte, PTE_SIZE);
 }
 
-static void srmmu_pte_free(struct page *pte)
+static void srmmu_pte_free(pgtable_t pte)
 {
         unsigned long p;
 
+        pgtable_page_dtor(pte);
         p = (unsigned long)page_address(pte);   /* Cached address (for test) */
         if (p == 0)
                 BUG();
diff --git a/arch/sparc/mm/sun4c.c b/arch/sparc/mm/sun4c.c
index 0729305f2f59..c0442e8c4b15 100644
--- a/arch/sparc/mm/sun4c.c
+++ b/arch/sparc/mm/sun4c.c
@@ -1947,12 +1947,17 @@ static pte_t *sun4c_pte_alloc_one_kernel(struct mm_struct *mm, unsigned long add
         return pte;
 }
 
-static struct page *sun4c_pte_alloc_one(struct mm_struct *mm, unsigned long address)
+static pgtable_t sun4c_pte_alloc_one(struct mm_struct *mm, unsigned long address)
 {
-        pte_t *pte = sun4c_pte_alloc_one_kernel(mm, address);
+        pte_t *pte;
+        struct page *page;
+
+        pte = sun4c_pte_alloc_one_kernel(mm, address);
         if (pte == NULL)
                 return NULL;
-        return virt_to_page(pte);
+        page = virt_to_page(pte);
+        pgtable_page_ctor(page);
+        return page;
 }
 
 static inline void sun4c_free_pte_fast(pte_t *pte)
@@ -1962,8 +1967,9 @@ static inline void sun4c_free_pte_fast(pte_t *pte)
         pgtable_cache_size++;
 }
 
-static void sun4c_pte_free(struct page *pte)
+static void sun4c_pte_free(pgtable_t pte)
 {
+        pgtable_page_dtor(pte);
         sun4c_free_pte_fast(page_address(pte));
 }
 
diff --git a/arch/um/kernel/mem.c b/arch/um/kernel/mem.c
index d872fdce1d7e..2627ce82e918 100644
--- a/arch/um/kernel/mem.c
+++ b/arch/um/kernel/mem.c
@@ -354,11 +354,13 @@ pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
         return pte;
 }
 
-struct page *pte_alloc_one(struct mm_struct *mm, unsigned long address)
+pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address)
 {
         struct page *pte;
 
         pte = alloc_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
+        if (pte)
+                pgtable_page_ctor(pte);
         return pte;
 }
 
diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c
index 6c1914622a88..73aba7125203 100644
--- a/arch/x86/mm/pgtable_32.c
+++ b/arch/x86/mm/pgtable_32.c
@@ -183,7 +183,7 @@ pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
         return (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
 }
 
-struct page *pte_alloc_one(struct mm_struct *mm, unsigned long address)
+pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address)
 {
         struct page *pte;
 
@@ -192,6 +192,8 @@ struct page *pte_alloc_one(struct mm_struct *mm, unsigned long address)
 #else
         pte = alloc_pages(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO, 0);
 #endif
+        if (pte)
+                pgtable_page_ctor(pte);
         return pte;
 }
 
@@ -365,6 +367,7 @@ void check_pgt_cache(void)
 
 void __pte_free_tlb(struct mmu_gather *tlb, struct page *pte)
 {
+        pgtable_page_dtor(pte);
         paravirt_release_pt(page_to_pfn(pte));
         tlb_remove_page(tlb, pte);
 }
diff --git a/include/asm-alpha/page.h b/include/asm-alpha/page.h
index 05f09f997d82..22ff9762d17b 100644
--- a/include/asm-alpha/page.h
+++ b/include/asm-alpha/page.h
@@ -62,6 +62,8 @@ typedef unsigned long pgprot_t;
 
 #endif /* STRICT_MM_TYPECHECKS */
 
+typedef struct page *pgtable_t;
+
 #ifdef USE_48_BIT_KSEG
 #define PAGE_OFFSET             0xffff800000000000UL
 #else
diff --git a/include/asm-alpha/pgalloc.h b/include/asm-alpha/pgalloc.h
index fdbedacc7375..fd090155dccd 100644
--- a/include/asm-alpha/pgalloc.h
+++ b/include/asm-alpha/pgalloc.h
@@ -11,10 +11,11 @@
  */
 
 static inline void
-pmd_populate(struct mm_struct *mm, pmd_t *pmd, struct page *pte)
+pmd_populate(struct mm_struct *mm, pmd_t *pmd, pgtable_t pte)
 {
         pmd_set(pmd, (pte_t *)(page_to_pa(pte) + PAGE_OFFSET));
 }
+#define pmd_pgtable(pmd) pmd_page(pmd)
 
 static inline void
 pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte)
@@ -57,18 +58,23 @@ pte_free_kernel(struct mm_struct *mm, pte_t *pte)
         free_page((unsigned long)pte);
 }
 
-static inline struct page *
-pte_alloc_one(struct mm_struct *mm, unsigned long addr)
+static inline pgtable_t
+pte_alloc_one(struct mm_struct *mm, unsigned long address)
 {
-        pte_t *pte = pte_alloc_one_kernel(mm, addr);
-        if (pte)
-                return virt_to_page(pte);
-        return NULL;
+        pte_t *pte = pte_alloc_one_kernel(mm, address);
+        struct page *page;
+
+        if (!pte)
+                return NULL;
+        page = virt_to_page(pte);
+        pgtable_page_ctor(page);
+        return page;
 }
 
 static inline void
-pte_free(struct mm_struct *mm, struct page *page)
+pte_free(struct mm_struct *mm, pgtable_t page)
 {
+        pgtable_page_dtor(page);
         __free_page(page);
 }
 
diff --git a/include/asm-arm/page.h b/include/asm-arm/page.h
index 31ff12f4ffb7..c86f68ee6511 100644
--- a/include/asm-arm/page.h
+++ b/include/asm-arm/page.h
@@ -171,6 +171,8 @@ typedef unsigned long pgprot_t;
 
 #endif /* STRICT_MM_TYPECHECKS */
 
+typedef struct page *pgtable_t;
+
 #endif /* CONFIG_MMU */
 
 #include <asm/memory.h>
diff --git a/include/asm-arm/pgalloc.h b/include/asm-arm/pgalloc.h
index fb6c6e3222bd..163b0305dd76 100644
--- a/include/asm-arm/pgalloc.h
+++ b/include/asm-arm/pgalloc.h
@@ -66,7 +66,7 @@ pte_alloc_one_kernel(struct mm_struct *mm, unsigned long addr)
         return pte;
 }
 
-static inline struct page *
+static inline pgtable_t
 pte_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
         struct page *pte;
@@ -75,6 +75,7 @@ pte_alloc_one(struct mm_struct *mm, unsigned long addr)
         if (pte) {
                 void *page = page_address(pte);
                 clean_dcache_area(page, sizeof(pte_t) * PTRS_PER_PTE);
+                pgtable_page_ctor(pte);
         }
 
         return pte;
@@ -91,8 +92,9 @@ static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
         }
 }
 
-static inline void pte_free(struct mm_struct *mm, struct page *pte)
+static inline void pte_free(struct mm_struct *mm, pgtable_t pte)
 {
+        pgtable_page_dtor(pte);
         __free_page(pte);
 }
 
@@ -123,10 +125,11 @@ pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmdp, pte_t *ptep)
 }
 
 static inline void
-pmd_populate(struct mm_struct *mm, pmd_t *pmdp, struct page *ptep)
+pmd_populate(struct mm_struct *mm, pmd_t *pmdp, pgtable_t ptep)
 {
         __pmd_populate(pmdp, page_to_pfn(ptep) << PAGE_SHIFT | _PAGE_USER_TABLE);
 }
+#define pmd_pgtable(pmd) pmd_page(pmd)
 
 #endif /* CONFIG_MMU */
 
diff --git a/include/asm-avr32/page.h b/include/asm-avr32/page.h
index ee23499cec34..5582968feee8 100644
--- a/include/asm-avr32/page.h
+++ b/include/asm-avr32/page.h
@@ -34,6 +34,7 @@ extern void copy_page(void *to, void *from);
 typedef struct { unsigned long pte; } pte_t;
 typedef struct { unsigned long pgd; } pgd_t;
 typedef struct { unsigned long pgprot; } pgprot_t;
+typedef struct page *pgtable_t;
 
 #define pte_val(x)              ((x).pte)
 #define pgd_val(x)              ((x).pgd)
diff --git a/include/asm-avr32/pgalloc.h b/include/asm-avr32/pgalloc.h
index b77e364b4c44..51fc1f6e4b17 100644
--- a/include/asm-avr32/pgalloc.h
+++ b/include/asm-avr32/pgalloc.h
@@ -17,10 +17,11 @@
         set_pmd(pmd, __pmd(_PAGE_TABLE + __pa(pte)))
 
 static __inline__ void pmd_populate(struct mm_struct *mm, pmd_t *pmd,
-                                    struct page *pte)
+                                    pgtable_t pte)
 {
         set_pmd(pmd, __pmd(_PAGE_TABLE + page_to_phys(pte)));
 }
+#define pmd_pgtable(pmd) pmd_page(pmd)
 
 /*
  * Allocate and free page tables
@@ -51,7 +52,9 @@ static inline struct page *pte_alloc_one(struct mm_struct *mm,
         struct page *pte;
 
         pte = alloc_page(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO);
-
+        if (!pte)
+                return NULL;
+        pgtable_page_ctor(pte);
         return pte;
 }
 
@@ -60,12 +63,17 @@ static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
         free_page((unsigned long)pte);
 }
 
-static inline void pte_free(struct mm_struct *mm, struct page *pte)
+static inline void pte_free(struct mm_struct *mm, pgtable_t pte)
 {
+        pgtable_page_dtor(pte);
         __free_page(pte);
 }
 
-#define __pte_free_tlb(tlb,pte) tlb_remove_page((tlb),(pte))
+#define __pte_free_tlb(tlb,pte)                         \
+do {                                                    \
+        pgtable_page_dtor(pte);                         \
+        tlb_remove_page((tlb), pte);                    \
+} while (0)
 
 #define check_pgt_cache() do { } while(0)
 
diff --git a/include/asm-cris/page.h b/include/asm-cris/page.h
index 3b0156c46311..c45bb1ef397c 100644
--- a/include/asm-cris/page.h
+++ b/include/asm-cris/page.h
@@ -26,6 +26,7 @@
 typedef struct { unsigned long pte; } pte_t;
 typedef struct { unsigned long pgd; } pgd_t;
 typedef struct { unsigned long pgprot; } pgprot_t;
+typedef struct page *pgtable_t;
 #endif
 
 #define pte_val(x)      ((x).pte)
diff --git a/include/asm-cris/pgalloc.h b/include/asm-cris/pgalloc.h
index 8ddd66f81773..a1ba761d0573 100644
--- a/include/asm-cris/pgalloc.h
+++ b/include/asm-cris/pgalloc.h
@@ -6,6 +6,7 @@
 
 #define pmd_populate_kernel(mm, pmd, pte) pmd_set(pmd, pte)
 #define pmd_populate(mm, pmd, pte) pmd_set(pmd, page_address(pte))
+#define pmd_pgtable(pmd) pmd_page(pmd)
 
 /*
  * Allocate and free page tables.
@@ -27,10 +28,11 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long ad
         return pte;
 }
 
-static inline struct page *pte_alloc_one(struct mm_struct *mm, unsigned long address)
+static inline pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address)
 {
         struct page *pte;
         pte = alloc_pages(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO, 0);
+        pgtable_page_ctor(pte);
         return pte;
 }
 
@@ -39,13 +41,17 @@ static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
         free_page((unsigned long)pte);
 }
 
-static inline void pte_free(struct mm_struct *mm, struct page *pte)
+static inline void pte_free(struct mm_struct *mm, pgtable_t pte)
 {
+        pgtable_page_dtor(pte);
         __free_page(pte);
 }
 
-
-#define __pte_free_tlb(tlb,pte) tlb_remove_page((tlb),(pte))
+#define __pte_free_tlb(tlb,pte)                         \
+do {                                                    \
+        pgtable_page_dtor(pte);                         \
+        tlb_remove_page((tlb), pte);                    \
+} while (0)
 
 #define check_pgt_cache()          do { } while (0)
 
diff --git a/include/asm-frv/page.h b/include/asm-frv/page.h
index cacc045700de..c2c1e89e747d 100644
--- a/include/asm-frv/page.h
+++ b/include/asm-frv/page.h
@@ -25,6 +25,7 @@ typedef struct { unsigned long	ste[64];} pmd_t;
 typedef struct { pmd_t          pue[1]; } pud_t;
 typedef struct { pud_t          pge[1]; } pgd_t;
 typedef struct { unsigned long  pgprot; } pgprot_t;
+typedef struct page *pgtable_t;
 
 #define pte_val(x)      ((x).pte)
 #define pmd_val(x)      ((x).ste[0])
diff --git a/include/asm-frv/pgalloc.h b/include/asm-frv/pgalloc.h
index e89620ef08ca..971e6addb009 100644
--- a/include/asm-frv/pgalloc.h
+++ b/include/asm-frv/pgalloc.h
@@ -25,6 +25,7 @@
 do {                                                                            \
         __set_pmd((PMD), page_to_pfn(PAGE) << PAGE_SHIFT | _PAGE_TABLE);        \
 } while(0)
+#define pmd_pgtable(pmd) pmd_page(pmd)
 
 /*
  * Allocate and free page tables.
@@ -35,19 +36,24 @@ extern void pgd_free(struct mm_struct *mm, pgd_t *);
 
 extern pte_t *pte_alloc_one_kernel(struct mm_struct *, unsigned long);
 
-extern struct page *pte_alloc_one(struct mm_struct *, unsigned long);
+extern pgtable_t pte_alloc_one(struct mm_struct *, unsigned long);
 
 static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
 {
         free_page((unsigned long)pte);
 }
 
-static inline void pte_free(struct mm_struct *mm, struct page *pte)
+static inline void pte_free(struct mm_struct *mm, pgtable_t pte)
 {
+        pgtable_page_dtor(pte);
         __free_page(pte);
 }
 
-#define __pte_free_tlb(tlb,pte)         tlb_remove_page((tlb),(pte))
+#define __pte_free_tlb(tlb,pte)                         \
+do {                                                    \
+        pgtable_page_dtor(pte);                         \
+        tlb_remove_page((tlb),(pte));                   \
+} while (0)
 
 /*
  * allocating and freeing a pmd is trivial: the 1-entry pmd is
diff --git a/include/asm-ia64/page.h b/include/asm-ia64/page.h
index 8a8aa3fd7cd4..4999a6c63775 100644
--- a/include/asm-ia64/page.h
+++ b/include/asm-ia64/page.h
@@ -185,6 +185,7 @@ get_order (unsigned long size)
 #endif
   typedef struct { unsigned long pgd; } pgd_t;
   typedef struct { unsigned long pgprot; } pgprot_t;
+  typedef struct page *pgtable_t;
 
 # define pte_val(x)     ((x).pte)
 # define pmd_val(x)     ((x).pmd)
@@ -206,6 +207,7 @@ get_order (unsigned long size)
     typedef unsigned long pmd_t;
     typedef unsigned long pgd_t;
     typedef unsigned long pgprot_t;
+    typedef struct page *pgtable_t;
 # endif
 
 # define pte_val(x)     (x)
diff --git a/include/asm-ia64/pgalloc.h b/include/asm-ia64/pgalloc.h
index 556d988123ac..b9ac1a6fc216 100644
--- a/include/asm-ia64/pgalloc.h
+++ b/include/asm-ia64/pgalloc.h
@@ -70,10 +70,11 @@ static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
 #define __pmd_free_tlb(tlb, pmd)        pmd_free((tlb)->mm, pmd)
 
 static inline void
-pmd_populate(struct mm_struct *mm, pmd_t * pmd_entry, struct page *pte)
+pmd_populate(struct mm_struct *mm, pmd_t * pmd_entry, pgtable_t pte)
 {
         pmd_val(*pmd_entry) = page_to_phys(pte);
 }
+#define pmd_pgtable(pmd) pmd_page(pmd)
 
 static inline void
 pmd_populate_kernel(struct mm_struct *mm, pmd_t * pmd_entry, pte_t * pte)
@@ -81,11 +82,17 @@ pmd_populate_kernel(struct mm_struct *mm, pmd_t * pmd_entry, pte_t * pte)
         pmd_val(*pmd_entry) = __pa(pte);
 }
 
-static inline struct page *pte_alloc_one(struct mm_struct *mm,
-                                         unsigned long addr)
+static inline pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
-        void *pg = quicklist_alloc(0, GFP_KERNEL, NULL);
-        return pg ? virt_to_page(pg) : NULL;
+        struct page *page;
+        void *pg;
+
+        pg = quicklist_alloc(0, GFP_KERNEL, NULL);
+        if (!pg)
+                return NULL;
+        page = virt_to_page(pg);
+        pgtable_page_ctor(page);
+        return page;
 }
 
 static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
@@ -94,8 +101,9 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
         return quicklist_alloc(0, GFP_KERNEL, NULL);
 }
 
-static inline void pte_free(struct mm_struct *mm, struct page *pte)
+static inline void pte_free(struct mm_struct *mm, pgtable_t pte)
 {
+        pgtable_page_dtor(pte);
         quicklist_free_page(0, NULL, pte);
 }
 
diff --git a/include/asm-m32r/page.h b/include/asm-m32r/page.h
index 05d43bbbf940..8a677f3fca68 100644
--- a/include/asm-m32r/page.h
+++ b/include/asm-m32r/page.h
@@ -28,6 +28,7 @@ typedef struct { unsigned long pgd; } pgd_t;
 #define PTE_MASK        PAGE_MASK
 
 typedef struct { unsigned long pgprot; } pgprot_t;
+typedef struct page *pgtable_t;
 
 #define pmd_val(x)      ((x).pmd)
 #define pgd_val(x)      ((x).pgd)
diff --git a/include/asm-m32r/pgalloc.h b/include/asm-m32r/pgalloc.h
index e5921adfad1b..f11a2b909cdb 100644
--- a/include/asm-m32r/pgalloc.h
+++ b/include/asm-m32r/pgalloc.h
@@ -9,10 +9,11 @@
         set_pmd(pmd, __pmd(_PAGE_TABLE + __pa(pte)))
 
 static __inline__ void pmd_populate(struct mm_struct *mm, pmd_t *pmd,
-        struct page *pte)
+        pgtable_t pte)
 {
         set_pmd(pmd, __pmd(_PAGE_TABLE + page_to_phys(pte)));
 }
+#define pmd_pgtable(pmd) pmd_page(pmd)
 
 /*
  * Allocate and free page tables.
@@ -37,12 +38,12 @@ static __inline__ pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
         return pte;
 }
 
-static __inline__ struct page *pte_alloc_one(struct mm_struct *mm,
+static __inline__ pgtable_t pte_alloc_one(struct mm_struct *mm,
         unsigned long address)
 {
         struct page *pte = alloc_page(GFP_KERNEL|__GFP_ZERO);
 
-
+        pgtable_page_ctor(pte);
         return pte;
 }
 
@@ -51,8 +52,9 @@ static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
         free_page((unsigned long)pte);
 }
 
-static inline void pte_free(struct mm_struct *mm, struct page *pte)
+static inline void pte_free(struct mm_struct *mm, pgtable_t pte)
 {
+        pgtable_page_dtor(pte);
         __free_page(pte);
 }
 
diff --git a/include/asm-m68k/motorola_pgalloc.h b/include/asm-m68k/motorola_pgalloc.h
index 500ec9b8b189..d08bf6261df8 100644
--- a/include/asm-m68k/motorola_pgalloc.h
+++ b/include/asm-m68k/motorola_pgalloc.h
@@ -7,7 +7,6 @@
 extern pmd_t *get_pointer_table(void);
 extern int free_pointer_table(pmd_t *);
 
-
 static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
 {
         pte_t *pte;
@@ -28,7 +27,7 @@ static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
         free_page((unsigned long) pte);
 }
 
-static inline struct page *pte_alloc_one(struct mm_struct *mm, unsigned long address)
+static inline pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address)
 {
         struct page *page = alloc_pages(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO, 0);
         pte_t *pte;
@@ -43,19 +42,21 @@ static inline struct page *pte_alloc_one(struct mm_struct *mm, unsigned long add
                 nocache_page(pte);
         }
         kunmap(pte);
-
+        pgtable_page_ctor(page);
         return page;
 }
 
-static inline void pte_free(struct mm_struct *mm, struct page *page)
+static inline void pte_free(struct mm_struct *mm, pgtable_t page)
 {
+        pgtable_page_dtor(page);
         cache_page(kmap(page));
         kunmap(page);
         __free_page(page);
 }
 
-static inline void __pte_free_tlb(struct mmu_gather *tlb, struct page *page)
+static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t page)
 {
+        pgtable_page_dtor(page);
         cache_page(kmap(page));
         kunmap(page);
         __free_page(page);
@@ -94,10 +95,11 @@ static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *
         pmd_set(pmd, pte);
 }
 
-static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, struct page *page)
+static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, pgtable_t page)
 {
         pmd_set(pmd, page_address(page));
 }
+#define pmd_pgtable(pmd) pmd_page(pmd)
 
 static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pmd_t *pmd)
 {
diff --git a/include/asm-m68k/page.h b/include/asm-m68k/page.h
index 3f29e2a03a43..880c2cbff8a6 100644
--- a/include/asm-m68k/page.h
+++ b/include/asm-m68k/page.h
@@ -91,6 +91,7 @@ typedef struct { unsigned long pte; } pte_t;
 typedef struct { unsigned long pmd[16]; } pmd_t;
 typedef struct { unsigned long pgd; } pgd_t;
 typedef struct { unsigned long pgprot; } pgprot_t;
+typedef struct page *pgtable_t;
 
 #define pte_val(x)      ((x).pte)
 #define pmd_val(x)      ((&x)->pmd[0])
diff --git a/include/asm-m68k/sun3_pgalloc.h b/include/asm-m68k/sun3_pgalloc.h
index a5a91e72714b..d4c83f143816 100644
--- a/include/asm-m68k/sun3_pgalloc.h
+++ b/include/asm-m68k/sun3_pgalloc.h
@@ -26,12 +26,17 @@ static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
         free_page((unsigned long) pte);
 }
 
-static inline void pte_free(struct mm_struct *mm, struct page *page)
+static inline void pte_free(struct mm_struct *mm, pgtable_t page)
 {
+        pgtable_page_dtor(page);
         __free_page(page);
 }
 
-#define __pte_free_tlb(tlb,pte) tlb_remove_page((tlb),(pte))
+#define __pte_free_tlb(tlb,pte)                         \
+do {                                                    \
+        pgtable_page_dtor(pte);                         \
+        tlb_remove_page((tlb), pte);                    \
+} while (0)
 
 static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
                                           unsigned long address)
@@ -45,8 +50,8 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
         return (pte_t *) (page);
 }
 
-static inline struct page *pte_alloc_one(struct mm_struct *mm,
-                                         unsigned long address)
+static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
+                                        unsigned long address)
 {
         struct page *page = alloc_pages(GFP_KERNEL|__GFP_REPEAT, 0);
 
@@ -54,6 +59,7 @@ static inline struct page *pte_alloc_one(struct mm_struct *mm,
                 return NULL;
 
         clear_highpage(page);
+        pgtable_page_ctor(page);
         return page;
 
 }
@@ -63,10 +69,11 @@ static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *
         pmd_val(*pmd) = __pa((unsigned long)pte);
 }
 
-static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, struct page *page)
+static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, pgtable_t page)
 {
         pmd_val(*pmd) = __pa((unsigned long)page_address(page));
 }
+#define pmd_pgtable(pmd) pmd_page(pmd)
 
 /*
  * allocating and freeing a pmd is trivial: the 1-entry pmd is
diff --git a/include/asm-mips/page.h b/include/asm-mips/page.h
index 635aa44d2290..8735aa0b8963 100644
--- a/include/asm-mips/page.h
+++ b/include/asm-mips/page.h
@@ -90,6 +90,7 @@ typedef struct { unsigned long pte; } pte_t;
 #define pte_val(x)      ((x).pte)
 #define __pte(x)        ((pte_t) { (x) } )
 #endif
+typedef struct page *pgtable_t;
 
 /*
  * For 3-level pagetables we defines these ourselves, for 2-level the
diff --git a/include/asm-mips/pgalloc.h b/include/asm-mips/pgalloc.h
index c4efeced8396..1275831dda29 100644
--- a/include/asm-mips/pgalloc.h
+++ b/include/asm-mips/pgalloc.h
@@ -20,10 +20,11 @@ static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd,
 }
 
 static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd,
-        struct page *pte)
+        pgtable_t pte)
 {
         set_pmd(pmd, __pmd((unsigned long)page_address(pte)));
 }
+#define pmd_pgtable(pmd) pmd_page(pmd)
 
 /*
  * Initialize a new pmd table with invalid pointers.
@@ -79,9 +80,10 @@ static inline struct page *pte_alloc_one(struct mm_struct *mm,
         struct page *pte;
 
         pte = alloc_pages(GFP_KERNEL | __GFP_REPEAT, PTE_ORDER);
-        if (pte)
+        if (pte) {
                 clear_highpage(pte);
-
+                pgtable_page_ctor(pte);
+        }
         return pte;
 }
 
@@ -90,12 +92,17 @@ static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
         free_pages((unsigned long)pte, PTE_ORDER);
 }
 
-static inline void pte_free(struct mm_struct *mm, struct page *pte)
+static inline void pte_free(struct mm_struct *mm, pgtable_t pte)
 {
+        pgtable_page_dtor(pte);
         __free_pages(pte, PTE_ORDER);
 }
 
-#define __pte_free_tlb(tlb, pte)        tlb_remove_page((tlb), (pte))
+#define __pte_free_tlb(tlb,pte)                         \
+do {                                                    \
+        pgtable_page_dtor(pte);                         \
+        tlb_remove_page((tlb), pte);                    \
+} while (0)
 
 #ifdef CONFIG_32BIT
 
diff --git a/include/asm-parisc/page.h b/include/asm-parisc/page.h
index b08d9151c71e..27d50b859541 100644
--- a/include/asm-parisc/page.h
+++ b/include/asm-parisc/page.h
@@ -91,6 +91,7 @@ typedef unsigned long pgprot_t;
 
 #endif /* STRICT_MM_TYPECHECKS */
 
+typedef struct page *pgtable_t;
 
 typedef struct __physmem_range {
         unsigned long start_pfn;
diff --git a/include/asm-parisc/pgalloc.h b/include/asm-parisc/pgalloc.h
index aab66f1bea14..3996dfc30a3f 100644
--- a/include/asm-parisc/pgalloc.h
+++ b/include/asm-parisc/pgalloc.h
@@ -115,11 +115,14 @@ pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte)
 
 #define pmd_populate(mm, pmd, pte_page) \
         pmd_populate_kernel(mm, pmd, page_address(pte_page))
+#define pmd_pgtable(pmd) pmd_page(pmd)
 
-static inline struct page *
+static inline pgtable_t
 pte_alloc_one(struct mm_struct *mm, unsigned long address)
 {
         struct page *page = alloc_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
+        if (page)
+                pgtable_page_ctor(page);
         return page;
 }
 
@@ -135,7 +138,11 @@ static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
         free_page((unsigned long)pte);
 }
 
-#define pte_free(mm, page) pte_free_kernel(page_address(page))
+static inline void pte_free_kernel(struct mm_struct *mm, struct page *pte)
+{
+        pgtable_page_dtor(pte);
+        pte_free_kernel(page_address((pte));
+}
 
 #define check_pgt_cache()       do { } while (0)
 
diff --git a/include/asm-powerpc/page.h b/include/asm-powerpc/page.h
index 61e3725bbd37..df47bbb6ea13 100644
--- a/include/asm-powerpc/page.h
+++ b/include/asm-powerpc/page.h
@@ -190,6 +190,8 @@ extern int page_is_ram(unsigned long pfn);
 
 struct vm_area_struct;
 
+typedef struct page *pgtable_t;
+
 #include <asm-generic/memory_model.h>
 #endif /* __ASSEMBLY__ */
 
diff --git a/include/asm-powerpc/pgalloc-32.h b/include/asm-powerpc/pgalloc-32.h
index c162a4c37b39..58c07147b3ea 100644
--- a/include/asm-powerpc/pgalloc-32.h
+++ b/include/asm-powerpc/pgalloc-32.h
@@ -22,17 +22,19 @@ extern void pgd_free(struct mm_struct *mm, pgd_t *pgd);
                 (pmd_val(*(pmd)) = __pa(pte) | _PMD_PRESENT)
 #define pmd_populate(mm, pmd, pte)      \
                 (pmd_val(*(pmd)) = (page_to_pfn(pte) << PAGE_SHIFT) | _PMD_PRESENT)
+#define pmd_pgtable(pmd) pmd_page(pmd)
 #else
 #define pmd_populate_kernel(mm, pmd, pte)       \
                 (pmd_val(*(pmd)) = (unsigned long)pte | _PMD_PRESENT)
 #define pmd_populate(mm, pmd, pte)      \
                 (pmd_val(*(pmd)) = (unsigned long)lowmem_page_address(pte) | _PMD_PRESENT)
+#define pmd_pgtable(pmd) pmd_page(pmd)
 #endif
 
 extern pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long addr);
-extern struct page *pte_alloc_one(struct mm_struct *mm, unsigned long addr);
+extern pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long addr);
 extern void pte_free_kernel(struct mm_struct *mm, pte_t *pte);
-extern void pte_free(struct mm_struct *mm, struct page *pte);
+extern void pte_free(struct mm_struct *mm, pgtable_t pte);
 
 #define __pte_free_tlb(tlb, pte)        pte_free((tlb)->mm, (pte))
 
diff --git a/include/asm-powerpc/pgalloc-64.h b/include/asm-powerpc/pgalloc-64.h
index 5afae8593931..68980990f62a 100644
--- a/include/asm-powerpc/pgalloc-64.h
+++ b/include/asm-powerpc/pgalloc-64.h
@@ -58,6 +58,7 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
 #define pmd_populate(mm, pmd, pte_page) \
         pmd_populate_kernel(mm, pmd, page_address(pte_page))
 #define pmd_populate_kernel(mm, pmd, pte) pmd_set(pmd, (unsigned long)(pte))
+#define pmd_pgtable(pmd) pmd_page(pmd)
 
 
 #else /* CONFIG_PPC_64K_PAGES */
@@ -72,6 +73,7 @@ static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd,
 
 #define pmd_populate(mm, pmd, pte_page) \
         pmd_populate_kernel(mm, pmd, page_address(pte_page))
+#define pmd_pgtable(pmd) pmd_page(pmd)
 
 #endif /* CONFIG_PPC_64K_PAGES */
 
@@ -92,11 +94,18 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
         return (pte_t *)__get_free_page(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO);
 }
 
-static inline struct page *pte_alloc_one(struct mm_struct *mm,
-                                         unsigned long address)
+static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
+                                        unsigned long address)
 {
-        pte_t *pte = pte_alloc_one_kernel(mm, address);
-        return pte ? virt_to_page(pte) : NULL;
+        struct page *page;
+        pte_t *pte;
+
+        pte = pte_alloc_one_kernel(mm, address);
+        if (!pte)
+                return NULL;
+        page = virt_to_page(pte);
+        pgtable_page_ctor(page);
+        return page;
 }
 
 static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
@@ -104,8 +113,9 @@ static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
         free_page((unsigned long)pte);
 }
 
-static inline void pte_free(struct mm_struct *mm, struct page *ptepage)
+static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
 {
+        pgtable_page_dtor(ptepage);
         __free_page(ptepage);
 }
 
@@ -136,9 +146,12 @@ static inline void pgtable_free(pgtable_free_t pgf)
 
 extern void pgtable_free_tlb(struct mmu_gather *tlb, pgtable_free_t pgf);
 
-#define __pte_free_tlb(tlb, ptepage)    \
+#define __pte_free_tlb(tlb,ptepage)     \
+do { \
+        pgtable_page_dtor(ptepage); \
         pgtable_free_tlb(tlb, pgtable_free_cache(page_address(ptepage), \
-                PTE_NONCACHE_NUM, PTE_TABLE_SIZE-1))
+                PTE_NONCACHE_NUM, PTE_TABLE_SIZE-1)); \
+} while (0)
 #define __pmd_free_tlb(tlb, pmd)        \
         pgtable_free_tlb(tlb, pgtable_free_cache(pmd, \
                 PMD_CACHE_NUM, PMD_TABLE_SIZE-1))
diff --git a/include/asm-ppc/pgalloc.h b/include/asm-ppc/pgalloc.h
index 7c39a95829c7..fd4d1d74cfb1 100644
--- a/include/asm-ppc/pgalloc.h
+++ b/include/asm-ppc/pgalloc.h
@@ -23,17 +23,19 @@ extern void pgd_free(struct mm_struct *mm, pgd_t *pgd);
                 (pmd_val(*(pmd)) = __pa(pte) | _PMD_PRESENT)
 #define pmd_populate(mm, pmd, pte)      \
                 (pmd_val(*(pmd)) = (page_to_pfn(pte) << PAGE_SHIFT) | _PMD_PRESENT)
+#define pmd_pgtable(pmd) pmd_page(pmd)
 #else
 #define pmd_populate_kernel(mm, pmd, pte)       \
                 (pmd_val(*(pmd)) = (unsigned long)pte | _PMD_PRESENT)
 #define pmd_populate(mm, pmd, pte)      \
                 (pmd_val(*(pmd)) = (unsigned long)lowmem_page_address(pte) | _PMD_PRESENT)
+#define pmd_pgtable(pmd) pmd_page(pmd)
 #endif
 
 extern pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long addr);
-extern struct page *pte_alloc_one(struct mm_struct *mm, unsigned long addr);
+extern pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long addr);
 extern void pte_free_kernel(struct mm_struct *mm, pte_t *pte);
-extern void pte_free(struct mm_struct *mm, struct page *pte);
+extern void pte_free(struct mm_struct *mm, pgtable_t pte);
 
 #define __pte_free_tlb(tlb, pte)        pte_free((tlb)->mm, (pte))
 
diff --git a/include/asm-s390/page.h b/include/asm-s390/page.h
index a55f9d979dfb..7f29a981f48c 100644
--- a/include/asm-s390/page.h
+++ b/include/asm-s390/page.h
@@ -109,6 +109,8 @@ typedef struct { unsigned long pgd; } pgd_t;
 
 #endif /* __s390x__ */
 
+typedef struct page *pgtable_t;
+
 #define __pte(x)        ((pte_t) { (x) } )
 #define __pmd(x)        ((pmd_t) { (x) } )
 #define __pgd(x)        ((pgd_t) { (x) } )
diff --git a/include/asm-s390/pgalloc.h b/include/asm-s390/pgalloc.h
index 6f6619ba8980..900d44807e10 100644
--- a/include/asm-s390/pgalloc.h
+++ b/include/asm-s390/pgalloc.h
@@ -132,7 +132,7 @@ pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte)
 }
 
 static inline void
-pmd_populate(struct mm_struct *mm, pmd_t *pmd, struct page *page)
+pmd_populate(struct mm_struct *mm, pmd_t *pmd, pgtable_t page)
 {
         pte_t *pte = (pte_t *)page_to_phys(page);
         pmd_t *shadow_pmd = get_shadow_table(pmd);
@@ -142,6 +142,7 @@ pmd_populate(struct mm_struct *mm, pmd_t *pmd, struct page *page)
         if (shadow_pmd && shadow_pte)
                 pmd_populate_kernel(mm, shadow_pmd, shadow_pte);
 }
+#define pmd_pgtable(pmd) pmd_page(pmd)
 
 /*
  * page table entry allocation/free routines.
diff --git a/include/asm-s390/tlb.h b/include/asm-s390/tlb.h
index 985de2b88279..3c8177fa9e06 100644
--- a/include/asm-s390/tlb.h
+++ b/include/asm-s390/tlb.h
@@ -95,7 +95,7 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
  * pte_free_tlb frees a pte table and clears the CRSTE for the
  * page table from the tlb.
  */
-static inline void pte_free_tlb(struct mmu_gather *tlb, struct page *page)
+static inline void pte_free_tlb(struct mmu_gather *tlb, pgtable_t page)
 {
         if (!tlb->fullmm) {
                 tlb->array[tlb->nr_ptes++] = page;
diff --git a/include/asm-sh/page.h b/include/asm-sh/page.h
index e0fe02950f52..134562dc8c45 100644
--- a/include/asm-sh/page.h
+++ b/include/asm-sh/page.h
@@ -100,6 +100,8 @@ typedef struct { unsigned long pgd; } pgd_t;
 #define __pgd(x) ((pgd_t) { (x) } )
 #define __pgprot(x)     ((pgprot_t) { (x) } )
 
+typedef struct page *pgtable_t;
+
 #endif /* !__ASSEMBLY__ */
 
 /*
diff --git a/include/asm-sh/pgalloc.h b/include/asm-sh/pgalloc.h
index 59ca16d77a1d..84dd2db7104c 100644
--- a/include/asm-sh/pgalloc.h
+++ b/include/asm-sh/pgalloc.h
@@ -14,10 +14,11 @@ static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd,
 }
 
 static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd,
-                                struct page *pte)
+                                pgtable_t pte)
 {
         set_pmd(pmd, __pmd((unsigned long)page_address(pte)));
 }
+#define pmd_pgtable(pmd) pmd_page(pmd)
 
 static inline void pgd_ctor(void *x)
 {
@@ -47,11 +48,18 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
         return quicklist_alloc(QUICK_PT, GFP_KERNEL | __GFP_REPEAT, NULL);
 }
 
-static inline struct page *pte_alloc_one(struct mm_struct *mm,
-                                         unsigned long address)
+static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
+                                        unsigned long address)
 {
-        void *pg = quicklist_alloc(QUICK_PT, GFP_KERNEL | __GFP_REPEAT, NULL);
-        return pg ? virt_to_page(pg) : NULL;
+        struct page *page;
+        void *pg;
+
+        pg = quicklist_alloc(QUICK_PT, GFP_KERNEL | __GFP_REPEAT, NULL);
+        if (!pg)
+                return NULL;
+        page = virt_to_page(pg);
+        pgtable_page_ctor(page);
+        return page;
 }
 
 static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
@@ -59,12 +67,17 @@ static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
         quicklist_free(QUICK_PT, NULL, pte);
 }
 
-static inline void pte_free(struct mm_struct *mm, struct page *pte)
+static inline void pte_free(struct mm_struct *mm, pgtable_t pte)
 {
+        pgtable_page_dtor(pte);
         quicklist_free_page(QUICK_PT, NULL, pte);
 }
 
-#define __pte_free_tlb(tlb,pte) tlb_remove_page((tlb),(pte))
+#define __pte_free_tlb(tlb,pte)                         \
+do {                                                    \
+        pgtable_page_dtor(pte);                         \
+        tlb_remove_page((tlb), (pte));                  \
+} while (0)
 
 /*
  * allocating and freeing a pmd is trivial: the 1-entry pmd is
diff --git a/include/asm-sparc/page.h b/include/asm-sparc/page.h
index cbc48c0c4e15..39ccf2da297c 100644
--- a/include/asm-sparc/page.h
+++ b/include/asm-sparc/page.h
@@ -123,6 +123,8 @@ typedef unsigned long iopgprot_t;
 
 #endif
 
+typedef struct page *pgtable_t;
+
 extern unsigned long sparc_unmapped_base;
 
 BTFIXUPDEF_SETHI(sparc_unmapped_base)
diff --git a/include/asm-sparc/pgalloc.h b/include/asm-sparc/pgalloc.h
index b5fbdd36447f..6292cd00e5af 100644
--- a/include/asm-sparc/pgalloc.h
+++ b/include/asm-sparc/pgalloc.h
@@ -50,10 +50,11 @@ BTFIXUPDEF_CALL(void, free_pmd_fast, pmd_t *)
 
 BTFIXUPDEF_CALL(void, pmd_populate, pmd_t *, struct page *)
 #define pmd_populate(MM, PMD, PTE)        BTFIXUP_CALL(pmd_populate)(PMD, PTE)
+#define pmd_pgtable(pmd) pmd_page(pmd)
 BTFIXUPDEF_CALL(void, pmd_set, pmd_t *, pte_t *)
 #define pmd_populate_kernel(MM, PMD, PTE) BTFIXUP_CALL(pmd_set)(PMD, PTE)
 
-BTFIXUPDEF_CALL(struct page *, pte_alloc_one, struct mm_struct *, unsigned long)
+BTFIXUPDEF_CALL(pgtable_t , pte_alloc_one, struct mm_struct *, unsigned long)
 #define pte_alloc_one(mm, address)      BTFIXUP_CALL(pte_alloc_one)(mm, address)
 BTFIXUPDEF_CALL(pte_t *, pte_alloc_one_kernel, struct mm_struct *, unsigned long)
 #define pte_alloc_one_kernel(mm, addr)  BTFIXUP_CALL(pte_alloc_one_kernel)(mm, addr)
@@ -61,7 +62,7 @@ BTFIXUPDEF_CALL(pte_t *, pte_alloc_one_kernel, struct mm_struct *, unsigned long
 BTFIXUPDEF_CALL(void, free_pte_fast, pte_t *)
 #define pte_free_kernel(mm, pte)        BTFIXUP_CALL(free_pte_fast)(pte)
 
-BTFIXUPDEF_CALL(void, pte_free, struct page *)
+BTFIXUPDEF_CALL(void, pte_free, pgtable_t )
 #define pte_free(mm, pte)       BTFIXUP_CALL(pte_free)(pte)
 #define __pte_free_tlb(tlb, pte)        pte_free((tlb)->mm, pte)
 
diff --git a/include/asm-sparc64/page.h b/include/asm-sparc64/page.h
index cdf950e017ee..e93a482aa24a 100644
--- a/include/asm-sparc64/page.h
+++ b/include/asm-sparc64/page.h
@@ -104,6 +104,8 @@ typedef unsigned long pgprot_t;
 
 #endif /* (STRICT_MM_TYPECHECKS) */
 
+typedef struct page *pgtable_t;
+
 #define TASK_UNMAPPED_BASE      (test_thread_flag(TIF_32BIT) ? \
                                  (_AC(0x0000000070000000,UL)) : \
                                  (_AC(0xfffff80000000000,UL) + (1UL << 32UL)))
diff --git a/include/asm-sparc64/pgalloc.h b/include/asm-sparc64/pgalloc.h
index b48f73c2274e..3ee2d406373b 100644
--- a/include/asm-sparc64/pgalloc.h
+++ b/include/asm-sparc64/pgalloc.h
@@ -43,11 +43,18 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
         return quicklist_alloc(0, GFP_KERNEL, NULL);
 }
 
-static inline struct page *pte_alloc_one(struct mm_struct *mm,
-                                         unsigned long address)
+static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
+                                        unsigned long address)
 {
-        void *pg = quicklist_alloc(0, GFP_KERNEL, NULL);
-        return pg ? virt_to_page(pg) : NULL;
+        struct page *page;
+        void *pg;
+
+        pg = quicklist_alloc(0, GFP_KERNEL, NULL);
+        if (!pg)
+                return NULL;
+        page = virt_to_page(pg);
+        pgtable_page_ctor(page);
+        return page;
 }
                 
 static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
@@ -55,8 +62,9 @@ static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
         quicklist_free(0, NULL, pte);
 }
 
-static inline void pte_free(struct mm_struct *mm, struct page *ptepage)
+static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
 {
+        pgtable_page_dtor(ptepage);
         quicklist_free_page(0, NULL, ptepage);
 }
 
@@ -64,6 +72,7 @@ static inline void pte_free(struct mm_struct *mm, struct page *ptepage)
 #define pmd_populate_kernel(MM, PMD, PTE)       pmd_set(PMD, PTE)
 #define pmd_populate(MM,PMD,PTE_PAGE)           \
         pmd_populate_kernel(MM,PMD,page_address(PTE_PAGE))
+#define pmd_pgtable(pmd) pmd_page(pmd)
 
 static inline void check_pgt_cache(void)
 {
diff --git a/include/asm-um/page.h b/include/asm-um/page.h
index fe2374d705d1..381f96b1c825 100644
--- a/include/asm-um/page.h
+++ b/include/asm-um/page.h
@@ -79,6 +79,8 @@ typedef unsigned long phys_t;
 
 typedef struct { unsigned long pgprot; } pgprot_t;
 
+typedef struct page *pgtable_t;
+
 #define pgd_val(x)      ((x).pgd)
 #define pgprot_val(x)   ((x).pgprot)
 
diff --git a/include/asm-um/pgalloc.h b/include/asm-um/pgalloc.h
index 4f3e62b02861..9062a6e72241 100644
--- a/include/asm-um/pgalloc.h
+++ b/include/asm-um/pgalloc.h
@@ -18,6 +18,7 @@
         set_pmd(pmd, __pmd(_PAGE_TABLE +                        \
                 ((unsigned long long)page_to_pfn(pte) <<        \
                         (unsigned long long) PAGE_SHIFT)))
+#define pmd_pgtable(pmd) pmd_page(pmd)
 
 /*
  * Allocate and free page tables.
@@ -26,19 +27,24 @@ extern pgd_t *pgd_alloc(struct mm_struct *);
 extern void pgd_free(struct mm_struct *mm, pgd_t *pgd);
 
 extern pte_t *pte_alloc_one_kernel(struct mm_struct *, unsigned long);
-extern struct page *pte_alloc_one(struct mm_struct *, unsigned long);
+extern pgtable_t pte_alloc_one(struct mm_struct *, unsigned long);
 
 static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
 {
         free_page((unsigned long) pte);
 }
 
-static inline void pte_free(struct mm_struct *mm, struct page *pte)
+static inline void pte_free(struct mm_struct *mm, pgtable_t pte)
 {
+        pgtable_page_dtor(pte);
         __free_page(pte);
 }
 
-#define __pte_free_tlb(tlb,pte) tlb_remove_page((tlb),(pte))
+#define __pte_free_tlb(tlb,pte)                         \
+do {                                                    \
+        pgtable_page_dtor(pte);                         \
+        tlb_remove_page((tlb),(pte));                   \
+} while (0)
 
 #ifdef CONFIG_3_LEVEL_PGTABLES
 
diff --git a/include/asm-x86/page_32.h b/include/asm-x86/page_32.h
index a6fd10f230d2..ba715d9798b0 100644
--- a/include/asm-x86/page_32.h
+++ b/include/asm-x86/page_32.h
@@ -50,6 +50,8 @@ typedef unsigned long	phys_addr_t;
 typedef union { pteval_t pte, pte_low; } pte_t;
 typedef pte_t boot_pte_t;
 
+typedef struct page *pgtable_t;
+
 #endif  /* __ASSEMBLY__ */
 #endif  /* CONFIG_X86_PAE */
 
diff --git a/include/asm-x86/page_64.h b/include/asm-x86/page_64.h
index dcf0c0746075..f7393bc516ef 100644
--- a/include/asm-x86/page_64.h
+++ b/include/asm-x86/page_64.h
@@ -71,6 +71,8 @@ typedef unsigned long	pgdval_t;
 typedef unsigned long   pgprotval_t;
 typedef unsigned long   phys_addr_t;
 
+typedef struct page *pgtable_t;
+
 typedef struct { pteval_t pte; } pte_t;
 
 #define vmemmap ((struct page *)VMEMMAP_START)
diff --git a/include/asm-x86/pgalloc_32.h b/include/asm-x86/pgalloc_32.h
index bab12718a913..6bea6e5b5ee5 100644
--- a/include/asm-x86/pgalloc_32.h
+++ b/include/asm-x86/pgalloc_32.h
@@ -31,6 +31,7 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, struct page *p
         paravirt_alloc_pt(mm, pfn);
         set_pmd(pmd, __pmd(((pteval_t)pfn << PAGE_SHIFT) | _PAGE_TABLE));
 }
+#define pmd_pgtable(pmd) pmd_page(pmd)
 
 /*
  * Allocate and free page tables.
@@ -39,15 +40,16 @@ extern pgd_t *pgd_alloc(struct mm_struct *);
 extern void pgd_free(struct mm_struct *mm, pgd_t *pgd);
 
 extern pte_t *pte_alloc_one_kernel(struct mm_struct *, unsigned long);
-extern struct page *pte_alloc_one(struct mm_struct *, unsigned long);
+extern pgtable_t pte_alloc_one(struct mm_struct *, unsigned long);
 
 static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
 {
         free_page((unsigned long)pte);
 }
 
-static inline void pte_free(struct mm_struct *mm, struct page *pte)
+static inline void pte_free(struct mm_struct *mm, pgtable_t pte)
 {
+        pgtable_page_dtor(pte);
         __free_page(pte);
 }
 
diff --git a/include/asm-x86/pgalloc_64.h b/include/asm-x86/pgalloc_64.h
index 4f6220db22b1..8d6722320dcc 100644
--- a/include/asm-x86/pgalloc_64.h
+++ b/include/asm-x86/pgalloc_64.h
@@ -12,6 +12,8 @@
 #define pgd_populate(mm, pgd, pud) \
                 set_pgd(pgd, __pgd(_PAGE_TABLE | __pa(pud)))
 
+#define pmd_pgtable(pmd) pmd_page(pmd)
+
 static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, struct page *pte)
 {
         set_pmd(pmd, __pmd(_PAGE_TABLE | (page_to_pfn(pte) << PAGE_SHIFT)));
@@ -91,12 +93,17 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long ad
         return (pte_t *)get_zeroed_page(GFP_KERNEL|__GFP_REPEAT);
 }
 
-static inline struct page *pte_alloc_one(struct mm_struct *mm, unsigned long address)
+static inline pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address)
 {
-        void *p = (void *)get_zeroed_page(GFP_KERNEL|__GFP_REPEAT);
+        struct page *page;
+        void *p;
+
+        p = (void *)get_zeroed_page(GFP_KERNEL|__GFP_REPEAT);
         if (!p)
                 return NULL;
-        return virt_to_page(p);
+        page = virt_to_page(p);
+        pgtable_page_ctor(page);
+        return page;
 }
 
 /* Should really implement gc for free page table pages. This could be
@@ -108,12 +115,17 @@ static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
         free_page((unsigned long)pte); 
 }
 
-static inline void pte_free(struct mm_struct *mm, struct page *pte)
+static inline void pte_free(struct mm_struct *mm, pgtable_t pte)
 {
+        pgtable_page_dtor(pte);
         __free_page(pte);
 } 
 
-#define __pte_free_tlb(tlb,pte) tlb_remove_page((tlb),(pte))
+#define __pte_free_tlb(tlb,pte)                         \
+do {                                                    \
+        pgtable_page_dtor((pte));                               \
+        tlb_remove_page((tlb), (pte));                  \
+} while (0)
 
 #define __pmd_free_tlb(tlb,x)   tlb_remove_page((tlb),virt_to_page(x))
 #define __pud_free_tlb(tlb,x)   tlb_remove_page((tlb),virt_to_page(x))
diff --git a/include/asm-xtensa/page.h b/include/asm-xtensa/page.h
index 1adedbf41d01..80a6ae0dd259 100644
--- a/include/asm-xtensa/page.h
+++ b/include/asm-xtensa/page.h
@@ -98,6 +98,7 @@
 typedef struct { unsigned long pte; } pte_t;            /* page table entry */
 typedef struct { unsigned long pgd; } pgd_t;            /* PGD table entry */
 typedef struct { unsigned long pgprot; } pgprot_t;
+typedef struct page *pgtable_t;
 
 #define pte_val(x)      ((x).pte)
 #define pgd_val(x)      ((x).pgd)
diff --git a/include/asm-xtensa/pgalloc.h b/include/asm-xtensa/pgalloc.h
index 1d51ba5463f9..8d1544eb461e 100644
--- a/include/asm-xtensa/pgalloc.h
+++ b/include/asm-xtensa/pgalloc.h
@@ -24,6 +24,7 @@
         (pmd_val(*(pmdp)) = ((unsigned long)ptep))
 #define pmd_populate(mm, pmdp, page)                                         \
         (pmd_val(*(pmdp)) = ((unsigned long)page_to_virt(page)))
+#define pmd_pgtable(pmd) pmd_page(pmd)
 
 static inline pgd_t*
 pgd_alloc(struct mm_struct *mm)
@@ -46,10 +47,14 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
         return kmem_cache_alloc(pgtable_cache, GFP_KERNEL|__GFP_REPEAT);
 }
 
-static inline struct page *pte_alloc_one(struct mm_struct *mm, 
-                                         unsigned long addr)
+static inline pte_token_t pte_alloc_one(struct mm_struct *mm,
+                                        unsigned long addr)
 {
-        return virt_to_page(pte_alloc_one_kernel(mm, addr));
+        struct page *page;
+
+        page = virt_to_page(pte_alloc_one_kernel(mm, addr));
+        pgtable_page_ctor(page);
+        return page;
 }
 
 static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
@@ -57,10 +62,12 @@ static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
         kmem_cache_free(pgtable_cache, pte);
 }
 
-static inline void pte_free(struct mm_struct *mm, struct page *page)
+static inline void pte_free(struct mm_struct *mm, pgtable_t pte)
 {
-        kmem_cache_free(pgtable_cache, page_address(page));
+        pgtable_page_dtor(pte);
+        kmem_cache_free(pgtable_cache, page_address(pte));
 }
+#define pmd_pgtable(pmd) pmd_page(pmd)
 
 #endif /* __KERNEL__ */
 #endif /* _XTENSA_PGALLOC_H */
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 89d7c691b93a..e8abb3814209 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -894,6 +894,18 @@ static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long a
 #define pte_lockptr(mm, pmd)    ({(void)(pmd); &(mm)->page_table_lock;})
 #endif /* NR_CPUS < CONFIG_SPLIT_PTLOCK_CPUS */
 
+static inline void pgtable_page_ctor(struct page *page)
+{
+        pte_lock_init(page);
+        inc_zone_page_state(page, NR_PAGETABLE);
+}
+
+static inline void pgtable_page_dtor(struct page *page)
+{
+        pte_lock_deinit(page);
+        dec_zone_page_state(page, NR_PAGETABLE);
+}
+
 #define pte_offset_map_lock(mm, pmd, address, ptlp)     \
 ({                                                      \
         spinlock_t *__ptl = pte_lockptr(mm, pmd);       \
@@ -1136,7 +1148,7 @@ struct page *follow_page(struct vm_area_struct *, unsigned long address,
 #define FOLL_GET        0x04    /* do get_page on page */
 #define FOLL_ANON       0x08    /* give ZERO_PAGE if no pgtable */
 
-typedef int (*pte_fn_t)(pte_t *pte, struct page *pmd_page, unsigned long addr,
+typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr,
                         void *data);
 extern int apply_to_page_range(struct mm_struct *mm, unsigned long address,
                                unsigned long size, pte_fn_t fn, void *data);
diff --git a/mm/memory.c b/mm/memory.c
index 153a54b2013c..e5628a5fd678 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -134,11 +134,9 @@ void pmd_clear_bad(pmd_t *pmd)
  */
 static void free_pte_range(struct mmu_gather *tlb, pmd_t *pmd)
 {
-        struct page *page = pmd_page(*pmd);
+        pgtable_t token = pmd_pgtable(*pmd);
         pmd_clear(pmd);
-        pte_lock_deinit(page);
-        pte_free_tlb(tlb, page);
-        dec_zone_page_state(page, NR_PAGETABLE);
+        pte_free_tlb(tlb, token);
         tlb->mm->nr_ptes--;
 }
 
@@ -309,21 +307,19 @@ void free_pgtables(struct mmu_gather **tlb, struct vm_area_struct *vma,
 
 int __pte_alloc(struct mm_struct *mm, pmd_t *pmd, unsigned long address)
 {
-        struct page *new = pte_alloc_one(mm, address);
+        pgtable_t new = pte_alloc_one(mm, address);
         if (!new)
                 return -ENOMEM;
 
-        pte_lock_init(new);
         spin_lock(&mm->page_table_lock);
-        if (pmd_present(*pmd)) {        /* Another has populated it */
-                pte_lock_deinit(new);
-                pte_free(mm, new);
-        } else {
+        if (!pmd_present(*pmd)) {       /* Has another populated it ? */
                 mm->nr_ptes++;
-                inc_zone_page_state(new, NR_PAGETABLE);
                 pmd_populate(mm, pmd, new);
+                new = NULL;
         }
         spin_unlock(&mm->page_table_lock);
+        if (new)
+                pte_free(mm, new);
         return 0;
 }
 
@@ -334,11 +330,13 @@ int __pte_alloc_kernel(pmd_t *pmd, unsigned long address)
                 return -ENOMEM;
 
         spin_lock(&init_mm.page_table_lock);
-        if (pmd_present(*pmd))          /* Another has populated it */
-                pte_free_kernel(&init_mm, new);
-        else
+        if (!pmd_present(*pmd)) {       /* Has another populated it ? */
                 pmd_populate_kernel(&init_mm, pmd, new);
+                new = NULL;
+        }
         spin_unlock(&init_mm.page_table_lock);
+        if (new)
+                pte_free_kernel(&init_mm, new);
         return 0;
 }
 
@@ -1390,7 +1388,7 @@ static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd,
 {
         pte_t *pte;
         int err;
-        struct page *pmd_page;
+        pgtable_t token;
         spinlock_t *uninitialized_var(ptl);
 
         pte = (mm == &init_mm) ?
@@ -1401,10 +1399,10 @@ static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd,
 
         BUG_ON(pmd_huge(*pmd));
 
-        pmd_page = pmd_page(*pmd);
+        token = pmd_pgtable(*pmd);
 
         do {
-                err = fn(pte, pmd_page, addr, data);
+                err = fn(pte, token, addr, data);
                 if (err)
                         break;
         } while (pte++, addr += PAGE_SIZE, addr != end);
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 0536dde139d1..950c0be9ca81 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -820,7 +820,7 @@ void  __attribute__((weak)) vmalloc_sync_all(void)
 }
 
 
-static int f(pte_t *pte, struct page *pmd_page, unsigned long addr, void *data)
+static int f(pte_t *pte, pgtable_t table, unsigned long addr, void *data)
 {
         /* apply_to_page_range() does all the hard work. */
         return 0;