[IA64] 4-level page tables

This patch introduces 4-level page tables to ia64.  I have run
some benchmarks and found nothing interesting.  Performance has
consistently fallen within the noise range.

It also introduces a config option (setting the default to 3
levels).  The config option prevents having 4 level page
tables with 64k base page size.

Signed-off-by: Robin Holt <holt@sgi.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>

3 files changed, 85 insertions, 18 deletions

diff --git a/include/asm-ia64/page.h b/include/asm-ia64/page.h
index 9d41548..9dd9da1 100644
--- a/include/asm-ia64/page.h
+++ b/include/asm-ia64/page.h
@@ -47,8 +47,6 @@
 #define PERCPU_PAGE_SHIFT	16	/* log2() of max. size of per-CPU area */
 #define PERCPU_PAGE_SIZE	(__IA64_UL_CONST(1) << PERCPU_PAGE_SHIFT)
 
-#define RGN_MAP_LIMIT	((1UL << (4*PAGE_SHIFT - 12)) - PAGE_SIZE)	/* per region addr limit */
-
 
 #ifdef CONFIG_HUGETLB_PAGE
 # define HPAGE_REGION_BASE	RGN_BASE(RGN_HPAGE)
@@ -175,11 +173,17 @@ get_order (unsigned long size)
    */
   typedef struct { unsigned long pte; } pte_t;
   typedef struct { unsigned long pmd; } pmd_t;
+#ifdef CONFIG_PGTABLE_4
+  typedef struct { unsigned long pud; } pud_t;
+#endif
   typedef struct { unsigned long pgd; } pgd_t;
   typedef struct { unsigned long pgprot; } pgprot_t;
 
 # define pte_val(x)	((x).pte)
 # define pmd_val(x)	((x).pmd)
+#ifdef CONFIG_PGTABLE_4
+# define pud_val(x)	((x).pud)
+#endif
 # define pgd_val(x)	((x).pgd)
 # define pgprot_val(x)	((x).pgprot)
 
diff --git a/include/asm-ia64/pgalloc.h b/include/asm-ia64/pgalloc.h
index a5f2145..f2f2338 100644
--- a/include/asm-ia64/pgalloc.h
+++ b/include/asm-ia64/pgalloc.h
@@ -86,6 +86,25 @@ static inline void pgd_free(pgd_t * pgd)
 	pgtable_quicklist_free(pgd);
 }
 
+#ifdef CONFIG_PGTABLE_4
+static inline void
+pgd_populate(struct mm_struct *mm, pgd_t * pgd_entry, pud_t * pud)
+{
+	pgd_val(*pgd_entry) = __pa(pud);
+}
+
+static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
+{
+	return pgtable_quicklist_alloc();
+}
+
+static inline void pud_free(pud_t * pud)
+{
+	pgtable_quicklist_free(pud);
+}
+#define __pud_free_tlb(tlb, pud)	pud_free(pud)
+#endif /* CONFIG_PGTABLE_4 */
+
 static inline void
 pud_populate(struct mm_struct *mm, pud_t * pud_entry, pmd_t * pmd)
 {
diff --git a/include/asm-ia64/pgtable.h b/include/asm-ia64/pgtable.h
index c34ba80..e2560c5 100644
--- a/include/asm-ia64/pgtable.h
+++ b/include/asm-ia64/pgtable.h
@@ -84,32 +84,55 @@
 #define __DIRTY_BITS		_PAGE_ED | __DIRTY_BITS_NO_ED
 
 /*
- * Definitions for first level:
- *
- * PGDIR_SHIFT determines what a first-level page table entry can map.
+ * How many pointers will a page table level hold expressed in shift
  */
-#define PGDIR_SHIFT		(PAGE_SHIFT + 2*(PAGE_SHIFT-3))
-#define PGDIR_SIZE		(__IA64_UL(1) << PGDIR_SHIFT)
-#define PGDIR_MASK		(~(PGDIR_SIZE-1))
-#define PTRS_PER_PGD		(1UL << (PAGE_SHIFT-3))
-#define USER_PTRS_PER_PGD	(5*PTRS_PER_PGD/8)	/* regions 0-4 are user regions */
-#define FIRST_USER_ADDRESS	0
+#define PTRS_PER_PTD_SHIFT	(PAGE_SHIFT-3)
 
 /*
- * Definitions for second level:
+ * Definitions for fourth level:
+ */
+#define PTRS_PER_PTE	(__IA64_UL(1) << (PTRS_PER_PTD_SHIFT))
+
+/*
+ * Definitions for third level:
  *
- * PMD_SHIFT determines the size of the area a second-level page table
+ * PMD_SHIFT determines the size of the area a third-level page table
  * can map.
  */
-#define PMD_SHIFT	(PAGE_SHIFT + (PAGE_SHIFT-3))
+#define PMD_SHIFT	(PAGE_SHIFT + (PTRS_PER_PTD_SHIFT))
 #define PMD_SIZE	(1UL << PMD_SHIFT)
 #define PMD_MASK	(~(PMD_SIZE-1))
-#define PTRS_PER_PMD	(1UL << (PAGE_SHIFT-3))
+#define PTRS_PER_PMD	(1UL << (PTRS_PER_PTD_SHIFT))
 
+#ifdef CONFIG_PGTABLE_4
 /*
- * Definitions for third level:
+ * Definitions for second level:
+ *
+ * PUD_SHIFT determines the size of the area a second-level page table
+ * can map.
  */
-#define PTRS_PER_PTE	(__IA64_UL(1) << (PAGE_SHIFT-3))
+#define PUD_SHIFT	(PMD_SHIFT + (PTRS_PER_PTD_SHIFT))
+#define PUD_SIZE	(1UL << PUD_SHIFT)
+#define PUD_MASK	(~(PUD_SIZE-1))
+#define PTRS_PER_PUD	(1UL << (PTRS_PER_PTD_SHIFT))
+#endif
+
+/*
+ * Definitions for first level:
+ *
+ * PGDIR_SHIFT determines what a first-level page table entry can map.
+ */
+#ifdef CONFIG_PGTABLE_4
+#define PGDIR_SHIFT		(PUD_SHIFT + (PTRS_PER_PTD_SHIFT))
+#else
+#define PGDIR_SHIFT		(PMD_SHIFT + (PTRS_PER_PTD_SHIFT))
+#endif
+#define PGDIR_SIZE		(__IA64_UL(1) << PGDIR_SHIFT)
+#define PGDIR_MASK		(~(PGDIR_SIZE-1))
+#define PTRS_PER_PGD_SHIFT	PTRS_PER_PTD_SHIFT
+#define PTRS_PER_PGD		(1UL << PTRS_PER_PGD_SHIFT)
+#define USER_PTRS_PER_PGD	(5*PTRS_PER_PGD/8)	/* regions 0-4 are user regions */
+#define FIRST_USER_ADDRESS	0
 
 /*
  * All the normal masks have the "page accessed" bits on, as any time
@@ -161,6 +184,9 @@
 #define __S111	__pgprot(__ACCESS_BITS | _PAGE_PL_3 | _PAGE_AR_RWX)
 
 #define pgd_ERROR(e)	printk("%s:%d: bad pgd %016lx.\n", __FILE__, __LINE__, pgd_val(e))
+#ifdef CONFIG_PGTABLE_4
+#define pud_ERROR(e)	printk("%s:%d: bad pud %016lx.\n", __FILE__, __LINE__, pud_val(e))
+#endif
 #define pmd_ERROR(e)	printk("%s:%d: bad pmd %016lx.\n", __FILE__, __LINE__, pmd_val(e))
 #define pte_ERROR(e)	printk("%s:%d: bad pte %016lx.\n", __FILE__, __LINE__, pte_val(e))
 
@@ -218,6 +244,9 @@ ia64_phys_addr_valid (unsigned long addr)
 #define	kc_vaddr_to_offset(v) ((v) - RGN_BASE(RGN_GATE))
 #define	kc_offset_to_vaddr(o) ((o) + RGN_BASE(RGN_GATE))
 
+#define RGN_MAP_SHIFT (PGDIR_SHIFT + PTRS_PER_PGD_SHIFT - 3)
+#define RGN_MAP_LIMIT	((1UL << RGN_MAP_SHIFT) - PAGE_SIZE)	/* per region addr limit */
+
 /*
  * Conversion functions: convert page frame number (pfn) and a protection value to a page
  * table entry (pte).
@@ -254,9 +283,16 @@ ia64_phys_addr_valid (unsigned long addr)
 #define pud_bad(pud)			(!ia64_phys_addr_valid(pud_val(pud)))
 #define pud_present(pud)		(pud_val(pud) != 0UL)
 #define pud_clear(pudp)			(pud_val(*(pudp)) = 0UL)
-
 #define pud_page(pud)			((unsigned long) __va(pud_val(pud) & _PFN_MASK))
 
+#ifdef CONFIG_PGTABLE_4
+#define pgd_none(pgd)			(!pgd_val(pgd))
+#define pgd_bad(pgd)			(!ia64_phys_addr_valid(pgd_val(pgd)))
+#define pgd_present(pgd)		(pgd_val(pgd) != 0UL)
+#define pgd_clear(pgdp)			(pgd_val(*(pgdp)) = 0UL)
+#define pgd_page(pgd)			((unsigned long) __va(pgd_val(pgd) & _PFN_MASK))
+#endif
+
 /*
  * The following have defined behavior only work if pte_present() is true.
  */
@@ -324,7 +360,13 @@ pgd_offset (struct mm_struct *mm, unsigned long address)
    here.  */
 #define pgd_offset_gate(mm, addr)	pgd_offset_k(addr)
 
+#ifdef CONFIG_PGTABLE_4
 /* Find an entry in the second-level page table.. */
+#define pud_offset(dir,addr) \
+	((pud_t *) pgd_page(*(dir)) + (((addr) >> PUD_SHIFT) & (PTRS_PER_PUD - 1)))
+#endif
+
+/* Find an entry in the third-level page table.. */
 #define pmd_offset(dir,addr) \
 	((pmd_t *) pud_page(*(dir)) + (((addr) >> PMD_SHIFT) & (PTRS_PER_PMD - 1)))
 
@@ -557,7 +599,9 @@ do {											\
 #define __HAVE_ARCH_PGD_OFFSET_GATE
 #define __HAVE_ARCH_LAZY_MMU_PROT_UPDATE
 
+#ifndef CONFIG_PGTABLE_4
 #include <asm-generic/pgtable-nopud.h>
+#endif
 #include <asm-generic/pgtable.h>
 
 #endif /* _ASM_IA64_PGTABLE_H */