[PATCH] Hugepage consolidation

A lot of the code in arch/*/mm/hugetlbpage.c is quite similar.  This patch
attempts to consolidate a lot of the code across the arch's, putting the
combined version in mm/hugetlb.c.  There are a couple of uglyish hacks in
order to covert all the hugepage archs, but the result is a very large
reduction in the total amount of code.  It also means things like hugepage
lazy allocation could be implemented in one place, instead of six.

Tested, at least a little, on ppc64, i386 and x86_64.

Notes:
	- this patch changes the meaning of set_huge_pte() to be more
	  analagous to set_pte()
	- does SH4 need s special huge_ptep_get_and_clear()??

Acked-by: William Lee Irwin <wli@holomorphy.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

12 files changed, 48 insertions, 8 deletions

diff --git a/include/asm-i386/page.h b/include/asm-i386/page.h
index ed13969fa2d6..41400d342d44 100644
--- a/include/asm-i386/page.h
+++ b/include/asm-i386/page.h
@@ -68,6 +68,7 @@ typedef struct { unsigned long pgprot; } pgprot_t;
 #define HPAGE_MASK      (~(HPAGE_SIZE - 1))
 #define HUGETLB_PAGE_ORDER      (HPAGE_SHIFT - PAGE_SHIFT)
 #define HAVE_ARCH_HUGETLB_UNMAPPED_AREA
+#define ARCH_HAS_HUGETLB_CLEAN_STALE_PGTABLE
 #endif
 
 #define pgd_val(x)      ((x).pgd)
diff --git a/include/asm-i386/pgtable.h b/include/asm-i386/pgtable.h
index 8d60c2b4b003..e9efe148fdf7 100644
--- a/include/asm-i386/pgtable.h
+++ b/include/asm-i386/pgtable.h
@@ -236,6 +236,7 @@ static inline pte_t pte_mkexec(pte_t pte)	{ (pte).pte_low |= _PAGE_USER; return
 static inline pte_t pte_mkdirty(pte_t pte)      { (pte).pte_low |= _PAGE_DIRTY; return pte; }
 static inline pte_t pte_mkyoung(pte_t pte)      { (pte).pte_low |= _PAGE_ACCESSED; return pte; }
 static inline pte_t pte_mkwrite(pte_t pte)      { (pte).pte_low |= _PAGE_RW; return pte; }
+static inline pte_t pte_mkhuge(pte_t pte)       { (pte).pte_low |= _PAGE_PRESENT | _PAGE_PSE; return pte; }
 
 #ifdef CONFIG_X86_PAE
 # include <asm/pgtable-3level.h>
@@ -275,7 +276,6 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr,
  */
 
 #define mk_pte(page, pgprot)    pfn_pte(page_to_pfn(page), (pgprot))
-#define mk_pte_huge(entry) ((entry).pte_low |= _PAGE_PRESENT | _PAGE_PSE)
 
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
diff --git a/include/asm-ia64/pgtable.h b/include/asm-ia64/pgtable.h
index fcc9c3344ab4..48586e08f432 100644
--- a/include/asm-ia64/pgtable.h
+++ b/include/asm-ia64/pgtable.h
@@ -283,6 +283,7 @@ ia64_phys_addr_valid (unsigned long addr)
 #define pte_mkyoung(pte)        (__pte(pte_val(pte) | _PAGE_A))
 #define pte_mkclean(pte)        (__pte(pte_val(pte) & ~_PAGE_D))
 #define pte_mkdirty(pte)        (__pte(pte_val(pte) | _PAGE_D))
+#define pte_mkhuge(pte)         (__pte(pte_val(pte) | _PAGE_P))
 
 /*
  * Macro to a page protection value as "uncacheable".  Note that "protection" is really a
diff --git a/include/asm-sh/page.h b/include/asm-sh/page.h
index 4c6d129e7d91..180467be8e7b 100644
--- a/include/asm-sh/page.h
+++ b/include/asm-sh/page.h
@@ -31,6 +31,7 @@
 #define HPAGE_SIZE              (1UL << HPAGE_SHIFT)
 #define HPAGE_MASK              (~(HPAGE_SIZE-1))
 #define HUGETLB_PAGE_ORDER      (HPAGE_SHIFT-PAGE_SHIFT)
+#define ARCH_HAS_SETCLEAR_HUGE_PTE
 #endif
 
 #ifdef __KERNEL__
diff --git a/include/asm-sh/pgtable.h b/include/asm-sh/pgtable.h
index cd847a47a9aa..ecb909572d3f 100644
--- a/include/asm-sh/pgtable.h
+++ b/include/asm-sh/pgtable.h
@@ -196,6 +196,7 @@ static inline pte_t pte_mkexec(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) | _
 static inline pte_t pte_mkdirty(pte_t pte)      { set_pte(&pte, __pte(pte_val(pte) | _PAGE_DIRTY)); return pte; }
 static inline pte_t pte_mkyoung(pte_t pte)      { set_pte(&pte, __pte(pte_val(pte) | _PAGE_ACCESSED)); return pte; }
 static inline pte_t pte_mkwrite(pte_t pte)      { set_pte(&pte, __pte(pte_val(pte) | _PAGE_RW)); return pte; }
+static inline pte_t pte_mkhuge(pte_t pte)       { set_pte(&pte, __pte(pte_val(pte) | _PAGE_SZHUGE)); return pte; }
 
 /*
  * Macro and implementation to make a page protection as uncachable.
diff --git a/include/asm-sh64/page.h b/include/asm-sh64/page.h
index e1f7f5a41210..d6167f1c0e99 100644
--- a/include/asm-sh64/page.h
+++ b/include/asm-sh64/page.h
@@ -41,6 +41,7 @@
 #define HPAGE_SIZE              (1UL << HPAGE_SHIFT)
 #define HPAGE_MASK              (~(HPAGE_SIZE-1))
 #define HUGETLB_PAGE_ORDER      (HPAGE_SHIFT-PAGE_SHIFT)
+#define ARCH_HAS_SETCLEAR_HUGE_PTE
 #endif
 
 #ifdef __KERNEL__
diff --git a/include/asm-sh64/pgtable.h b/include/asm-sh64/pgtable.h
index 525e1523ef5f..78ac6be2d9ef 100644
--- a/include/asm-sh64/pgtable.h
+++ b/include/asm-sh64/pgtable.h
@@ -430,6 +430,8 @@ extern inline pte_t pte_mkwrite(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) |
 extern inline pte_t pte_mkexec(pte_t pte)       { set_pte(&pte, __pte(pte_val(pte) | _PAGE_EXECUTE)); return pte; }
 extern inline pte_t pte_mkdirty(pte_t pte)      { set_pte(&pte, __pte(pte_val(pte) | _PAGE_DIRTY)); return pte; }
 extern inline pte_t pte_mkyoung(pte_t pte)      { set_pte(&pte, __pte(pte_val(pte) | _PAGE_ACCESSED)); return pte; }
+extern inline pte_t pte_mkhuge(pte_t pte)       { set_pte(&pte, __pte(pte_val(pte) | _PAGE_SZHUGE)); return pte; }
+
 
 /*
  * Conversion functions: convert a page and protection to a page entry.
diff --git a/include/asm-sparc64/page.h b/include/asm-sparc64/page.h
index 219ea043a14a..b87dbbd64bc9 100644
--- a/include/asm-sparc64/page.h
+++ b/include/asm-sparc64/page.h
@@ -95,6 +95,8 @@ typedef unsigned long pgprot_t;
 #define HPAGE_SIZE              (_AC(1,UL) << HPAGE_SHIFT)
 #define HPAGE_MASK              (~(HPAGE_SIZE - 1UL))
 #define HUGETLB_PAGE_ORDER      (HPAGE_SHIFT - PAGE_SHIFT)
+#define ARCH_HAS_SETCLEAR_HUGE_PTE
+#define ARCH_HAS_HUGETLB_PREFAULT_HOOK
 #endif
 
 #define TASK_UNMAPPED_BASE      (test_thread_flag(TIF_32BIT) ? \
diff --git a/include/asm-sparc64/pgtable.h b/include/asm-sparc64/pgtable.h
index ae2cd5b09a7c..1ae00c5087f1 100644
--- a/include/asm-sparc64/pgtable.h
+++ b/include/asm-sparc64/pgtable.h
@@ -286,6 +286,7 @@ static inline pte_t pte_modify(pte_t orig_pte, pgprot_t new_prot)
 #define pte_mkyoung(pte)        (__pte(pte_val(pte) | _PAGE_ACCESSED | _PAGE_R))
 #define pte_mkwrite(pte)        (__pte(pte_val(pte) | _PAGE_WRITE))
 #define pte_mkdirty(pte)        (__pte(pte_val(pte) | _PAGE_MODIFIED | _PAGE_W))
+#define pte_mkhuge(pte)         (__pte(pte_val(pte) | _PAGE_SZHUGE))
 
 /* to find an entry in a page-table-directory. */
 #define pgd_index(address)      (((address) >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1))
diff --git a/include/asm-x86_64/page.h b/include/asm-x86_64/page.h
index f43048035a03..9ce338c3a71e 100644
--- a/include/asm-x86_64/page.h
+++ b/include/asm-x86_64/page.h
@@ -28,6 +28,7 @@
 #define HPAGE_SIZE      ((1UL) << HPAGE_SHIFT)
 #define HPAGE_MASK      (~(HPAGE_SIZE - 1))
 #define HUGETLB_PAGE_ORDER      (HPAGE_SHIFT - PAGE_SHIFT)
+#define ARCH_HAS_HUGETLB_CLEAN_STALE_PGTABLE
 
 #ifdef __KERNEL__
 #ifndef __ASSEMBLY__
diff --git a/include/asm-x86_64/pgtable.h b/include/asm-x86_64/pgtable.h
index db2a0efbf573..4eec176c3c39 100644
--- a/include/asm-x86_64/pgtable.h
+++ b/include/asm-x86_64/pgtable.h
@@ -253,6 +253,7 @@ extern inline int pte_young(pte_t pte)		{ return pte_val(pte) & _PAGE_ACCESSED;
 extern inline int pte_write(pte_t pte)          { return pte_val(pte) & _PAGE_RW; }
 static inline int pte_file(pte_t pte)           { return pte_val(pte) & _PAGE_FILE; }
 
+#define __LARGE_PTE (_PAGE_PSE|_PAGE_PRESENT)
 extern inline pte_t pte_rdprotect(pte_t pte)    { set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_USER)); return pte; }
 extern inline pte_t pte_exprotect(pte_t pte)    { set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_USER)); return pte; }
 extern inline pte_t pte_mkclean(pte_t pte)      { set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_DIRTY)); return pte; }
@@ -263,6 +264,7 @@ extern inline pte_t pte_mkexec(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) | _
 extern inline pte_t pte_mkdirty(pte_t pte)      { set_pte(&pte, __pte(pte_val(pte) | _PAGE_DIRTY)); return pte; }
 extern inline pte_t pte_mkyoung(pte_t pte)      { set_pte(&pte, __pte(pte_val(pte) | _PAGE_ACCESSED)); return pte; }
 extern inline pte_t pte_mkwrite(pte_t pte)      { set_pte(&pte, __pte(pte_val(pte) | _PAGE_RW)); return pte; }
+extern inline pte_t pte_mkhuge(pte_t pte)       { set_pte(&pte, __pte(pte_val(pte) | __LARGE_PTE)); return pte; }
 
 struct vm_area_struct;
 
@@ -290,7 +292,6 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr,
  */
 #define pgprot_noncached(prot)  (__pgprot(pgprot_val(prot) | _PAGE_PCD | _PAGE_PWT))
 
-#define __LARGE_PTE (_PAGE_PSE|_PAGE_PRESENT) 
 static inline int pmd_large(pmd_t pte) { 
         return (pmd_val(pte) & __LARGE_PTE) == __LARGE_PTE; 
 }       
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 6af1ae4a8211..f529d1442815 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -4,6 +4,7 @@
 #ifdef CONFIG_HUGETLB_PAGE
 
 #include <linux/mempolicy.h>
+#include <asm/tlbflush.h>
 
 struct ctl_table;
 
@@ -22,12 +23,6 @@ int hugetlb_report_meminfo(char *);
 int hugetlb_report_node_meminfo(int, char *);
 int is_hugepage_mem_enough(size_t);
 unsigned long hugetlb_total_pages(void);
-struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address,
-                              int write);
-struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
-                                pmd_t *pmd, int write);
-int is_aligned_hugepage_range(unsigned long addr, unsigned long len);
-int pmd_huge(pmd_t pmd);
 struct page *alloc_huge_page(void);
 void free_huge_page(struct page *);
 
@@ -35,6 +30,17 @@ extern unsigned long max_huge_pages;
 extern const unsigned long hugetlb_zero, hugetlb_infinity;
 extern int sysctl_hugetlb_shm_group;
 
+/* arch callbacks */
+
+pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr);
+pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr);
+struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address,
+                              int write);
+struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
+                                pmd_t *pmd, int write);
+int is_aligned_hugepage_range(unsigned long addr, unsigned long len);
+int pmd_huge(pmd_t pmd);
+
 #ifndef ARCH_HAS_HUGEPAGE_ONLY_RANGE
 #define is_hugepage_only_range(mm, addr, len)   0
 #define hugetlb_free_pgd_range(tlb, addr, end, floor, ceiling) \
@@ -48,6 +54,28 @@ extern int sysctl_hugetlb_shm_group;
 int prepare_hugepage_range(unsigned long addr, unsigned long len);
 #endif
 
+#ifndef ARCH_HAS_SETCLEAR_HUGE_PTE
+#define set_huge_pte_at(mm, addr, ptep, pte)    set_pte_at(mm, addr, ptep, pte)
+#define huge_ptep_get_and_clear(mm, addr, ptep) ptep_get_and_clear(mm, addr, ptep)
+#else
+void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+                     pte_t *ptep, pte_t pte);
+pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
+                              pte_t *ptep);
+#endif
+
+#ifndef ARCH_HAS_HUGETLB_PREFAULT_HOOK
+#define hugetlb_prefault_arch_hook(mm)          do { } while (0)
+#else
+void hugetlb_prefault_arch_hook(struct mm_struct *mm);
+#endif
+
+#ifndef ARCH_HAS_HUGETLB_CLEAN_STALE_PGTABLE
+#define hugetlb_clean_stale_pgtable(pte)        BUG()
+#else
+void hugetlb_clean_stale_pgtable(pte_t *pte);
+#endif
+
 #else /* !CONFIG_HUGETLB_PAGE */
 
 static inline int is_vm_hugetlb_page(struct vm_area_struct *vma)