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>

4 files changed, 25 insertions, 7 deletions

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))