[patch 2/6] mm: introduce pte_special pte bit

[patch 2/6] mm: introduce pte_special pte bit

[npiggin-l3A5Bk7waGM]

[-- Attachment #1: mm-normal-pte-bit.patch --]
[-- Type: text/plain, Size: 31321 bytes --]

s390 for one, cannot implement VM_MIXEDMAP with pfn_valid, due to their
memory model (which is more dynamic than most). Instead, they had proposed
to implement it with an additional path through vm_normal_page(), using a
bit in the pte to determine whether or not the page should be refcounted:

vm_normal_page()
{
	...
        if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) {
                if (vma->vm_flags & VM_MIXEDMAP) {
#ifdef s390
			if (!mixedmap_refcount_pte(pte))
				return NULL;
#else
                        if (!pfn_valid(pfn))
                                return NULL;
#endif
                        goto out;
                }
	...
}

This is fine, however if we are allowed to use a bit in the pte to
determine refcountedness, we can use that to _completely_ replace all the
vma based schemes. So instead of adding more cases to the already complex
vma-based scheme, we can have a clearly seperate and simple pte-based scheme
(and get slightly better code generation in the process):

vm_normal_page()
{
#ifdef s390
	if (!mixedmap_refcount_pte(pte))
		return NULL;
	return pte_page(pte);
#else
	...
#endif
}

And finally, we may rather make this concept usable by any architecture
rather than making it s390 only, so implement a new type of pte state
for this. Unfortunately the old vma based code must stay, because some
architectures may not be able to spare pte bits. This makes vm_normal_page
a little bit more ugly than we would like, but the 2 cases are clearly
seperate.

So introduce a pte_special pte state, and use it in mm/memory.c. It is
currently a noop for all architectures, so this doesn't actually result
in any compiled code changes to mm/memory.o.

Signed-off-by: Nick Piggin <npiggin-l3A5Bk7waGM@public.gmane.org>
Cc: Linus Torvalds <torvalds-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org>
Cc: Hugh Dickins <hugh-DTz5qymZ9yRBDgjK7y7TUQ@public.gmane.org>
Cc: Jared Hulbert <jaredeh-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
Cc: Carsten Otte <cotte-tA70FqPdS9bQT0dZR+AlfA@public.gmane.org>
Cc: Martin Schwidefsky <schwidefsky-tA70FqPdS9bQT0dZR+AlfA@public.gmane.org>
Cc: Heiko Carstens <heiko.carstens-tA70FqPdS9bQT0dZR+AlfA@public.gmane.org>
Cc: linux-arch-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
Cc: linux-mm-Bw31MaZKKs3YtjvyW6yDsg@public.gmane.org
---
 include/asm-alpha/pgtable.h         |    2 
 include/asm-avr32/pgtable.h         |    8 ++
 include/asm-cris/pgtable.h          |    2 
 include/asm-frv/pgtable.h           |    2 
 include/asm-ia64/pgtable.h          |    3 +
 include/asm-m32r/pgtable.h          |   10 +++
 include/asm-m68k/motorola_pgtable.h |    2 
 include/asm-m68k/sun3_pgtable.h     |    2 
 include/asm-mips/pgtable.h          |    2 
 include/asm-parisc/pgtable.h        |    2 
 include/asm-powerpc/pgtable-ppc32.h |    3 +
 include/asm-powerpc/pgtable-ppc64.h |    3 +
 include/asm-ppc/pgtable.h           |    3 +
 include/asm-s390/pgtable.h          |   10 +++
 include/asm-sh64/pgtable.h          |    2 
 include/asm-sparc/pgtable.h         |    7 ++
 include/asm-sparc64/pgtable.h       |   10 +++
 include/asm-um/pgtable.h            |   10 +++
 include/asm-x86/pgtable_32.h        |    2 
 include/asm-x86/pgtable_64.h        |    2 
 include/asm-xtensa/pgtable.h        |    4 +
 include/linux/mm.h                  |    3 -
 mm/memory.c                         |   98 +++++++++++++++++++-----------------
 23 files changed, 147 insertions(+), 45 deletions(-)

Index: linux-2.6/include/asm-um/pgtable.h
===================================================================
--- linux-2.6.orig/include/asm-um/pgtable.h
+++ linux-2.6/include/asm-um/pgtable.h
@@ -220,6 +220,11 @@ static inline int pte_newprot(pte_t pte)
 	return(pte_present(pte) && (pte_get_bits(pte, _PAGE_NEWPROT)));
 }
 
+static inline int pte_special(pte_t pte)
+{
+	return 0;
+}
+
 /*
  * =================================
  * Flags setting section.
@@ -288,6 +293,11 @@ static inline pte_t pte_mknewpage(pte_t 
 	return(pte);
 }
 
+static inline pte_t pte_mkspecial(pte_t pte)
+{
+	return(pte);
+}
+
 static inline void set_pte(pte_t *pteptr, pte_t pteval)
 {
 	pte_copy(*pteptr, pteval);
Index: linux-2.6/include/asm-x86/pgtable_32.h
===================================================================
--- linux-2.6.orig/include/asm-x86/pgtable_32.h
+++ linux-2.6/include/asm-x86/pgtable_32.h
@@ -219,6 +219,7 @@ static inline int pte_dirty(pte_t pte)		
 static inline int pte_young(pte_t pte)		{ return (pte).pte_low & _PAGE_ACCESSED; }
 static inline int pte_write(pte_t pte)		{ return (pte).pte_low & _PAGE_RW; }
 static inline int pte_huge(pte_t pte)		{ return (pte).pte_low & _PAGE_PSE; }
+static inline int pte_special(pte_t pte)	{ return 0; }
 
 /*
  * The following only works if pte_present() is not true.
@@ -232,6 +233,7 @@ static inline pte_t pte_mkdirty(pte_t pt
 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_PSE; return pte; }
+static inline pte_t pte_mkspecial(pte_t pte)	{ return pte; }
 
 #ifdef CONFIG_X86_PAE
 # include <asm/pgtable-3level.h>
Index: linux-2.6/include/asm-x86/pgtable_64.h
===================================================================
--- linux-2.6.orig/include/asm-x86/pgtable_64.h
+++ linux-2.6/include/asm-x86/pgtable_64.h
@@ -272,6 +272,7 @@ static inline int pte_young(pte_t pte)		
 static 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; }
 static inline int pte_huge(pte_t pte)		{ return pte_val(pte) & _PAGE_PSE; }
+static inline int pte_special(pte_t pte)	{ return 0; }
 
 static inline pte_t pte_mkclean(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_DIRTY)); return pte; }
 static inline pte_t pte_mkold(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_ACCESSED)); return pte; }
@@ -282,6 +283,7 @@ static inline pte_t pte_mkyoung(pte_t pt
 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_PSE)); return pte; }
 static inline pte_t pte_clrhuge(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_PSE)); return pte; }
+static inline pte_t pte_mkspecial(pte_t pte)	{ return pte; }
 
 struct vm_area_struct;
 
Index: linux-2.6/include/linux/mm.h
===================================================================
--- linux-2.6.orig/include/linux/mm.h
+++ linux-2.6/include/linux/mm.h
@@ -699,7 +699,8 @@ struct zap_details {
 	unsigned long truncate_count;		/* Compare vm_truncate_count */
 };
 
-struct page *vm_normal_page(struct vm_area_struct *, unsigned long, pte_t);
+struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, pte_t pte);
+
 unsigned long zap_page_range(struct vm_area_struct *vma, unsigned long address,
 		unsigned long size, struct zap_details *);
 unsigned long unmap_vmas(struct mmu_gather **tlb,
Index: linux-2.6/mm/memory.c
===================================================================
--- linux-2.6.orig/mm/memory.c
+++ linux-2.6/mm/memory.c
@@ -361,34 +361,38 @@ static inline int is_cow_mapping(unsigne
 }
 
 /*
- * This function gets the "struct page" associated with a pte or returns
- * NULL if no "struct page" is associated with the pte.
+ * vm_normal_page -- This function gets the "struct page" associated with a pte.
  *
- * A raw VM_PFNMAP mapping (ie. one that is not COWed) may not have any "struct
- * page" backing, and even if they do, they are not refcounted. COWed pages of
- * a VM_PFNMAP do always have a struct page, and they are normally refcounted
- * (they are _normal_ pages).
- *
- * So a raw PFNMAP mapping will have each page table entry just pointing
- * to a page frame number, and as far as the VM layer is concerned, those do
- * not have pages associated with them - even if the PFN might point to memory
- * that otherwise is perfectly fine and has a "struct page".
+ * "Special" mappings do not wish to be associated with a "struct page" (either
+ * it doesn't exist, or it exists but they don't want to touch it). In this
+ * case, NULL is returned here. "Normal" mappings do have a struct page.
+ *
+ * There are 2 broad cases. Firstly, an architecture may define a pte_special()
+ * pte bit, in which case this function is trivial. Secondly, an architecture
+ * may not have a spare pte bit, which requires a more complicated scheme,
+ * described below.
+ *
+ * A raw VM_PFNMAP mapping (ie. one that is not COWed) is always considered a
+ * special mapping (even if there are underlying and valid "struct pages").
+ * COWed pages of a VM_PFNMAP are always normal.
  *
  * The way we recognize COWed pages within VM_PFNMAP mappings is through the
  * rules set up by "remap_pfn_range()": the vma will have the VM_PFNMAP bit
- * set, and the vm_pgoff will point to the first PFN mapped: thus every
- * page that is a raw mapping will always honor the rule
+ * set, and the vm_pgoff will point to the first PFN mapped: thus every special
+ * mapping will always honor the rule
  *
  *	pfn_of_page == vma->vm_pgoff + ((addr - vma->vm_start) >> PAGE_SHIFT)
  *
- * A call to vm_normal_page() will return NULL for such a page.
+ * And for normal mappings this is false.
  *
- * If the page doesn't follow the "remap_pfn_range()" rule in a VM_PFNMAP
- * then the page has been COW'ed.  A COW'ed page _does_ have a "struct page"
- * associated with it even if it is in a VM_PFNMAP range.  Calling
- * vm_normal_page() on such a page will therefore return the "struct page".
+ * This restricts such mappings to be a linear translation from virtual address
+ * to pfn. To get around this restriction, we allow arbitrary mappings so long
+ * as the vma is not a COW mapping; in that case, we know that all ptes are
+ * special (because none can have been COWed).
  *
  *
+ * In order to support COW of arbitrary special mappings, we have VM_MIXEDMAP.
+ *
  * VM_MIXEDMAP mappings can likewise contain memory with or without "struct
  * page" backing, however the difference is that _all_ pages with a struct
  * page (that is, those where pfn_valid is true) are refcounted and considered
@@ -397,16 +401,28 @@ static inline int is_cow_mapping(unsigne
  * advantage is that we don't have to follow the strict linearity rule of
  * PFNMAP mappings in order to support COWable mappings.
  *
- * A call to vm_normal_page() with a VM_MIXEDMAP mapping will return the
- * associated "struct page" or NULL for memory not backed by a "struct page".
- *
- *
- * All other mappings should have a valid struct page, which will be
- * returned by a call to vm_normal_page().
  */
+#ifdef __HAVE_ARCH_PTE_SPECIAL
+# define HAVE_PTE_SPECIAL 1
+#else
+# define HAVE_PTE_SPECIAL 0
+#endif
 struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, pte_t pte)
 {
-	unsigned long pfn = pte_pfn(pte);
+	unsigned long pfn;
+
+	if (HAVE_PTE_SPECIAL) {
+		if (likely(!pte_special(pte))) {
+			VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
+			return pte_page(pte);
+		}
+		VM_BUG_ON(!(vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP)));
+		return NULL;
+	}
+
+	/* !HAVE_PTE_SPECIAL case follows: */
+
+	pfn = pte_pfn(pte);
 
 	if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) {
 		if (vma->vm_flags & VM_MIXEDMAP) {
@@ -414,7 +430,8 @@ struct page *vm_normal_page(struct vm_ar
 				return NULL;
 			goto out;
 		} else {
-			unsigned long off = (addr-vma->vm_start) >> PAGE_SHIFT;
+			unsigned long off;
+			off = (addr - vma->vm_start) >> PAGE_SHIFT;
 			if (pfn == vma->vm_pgoff + off)
 				return NULL;
 			if (!is_cow_mapping(vma->vm_flags))
@@ -422,25 +439,12 @@ struct page *vm_normal_page(struct vm_ar
 		}
 	}
 
-#ifdef CONFIG_DEBUG_VM
-	/*
-	 * Add some anal sanity checks for now. Eventually,
-	 * we should just do "return pfn_to_page(pfn)", but
-	 * in the meantime we check that we get a valid pfn,
-	 * and that the resulting page looks ok.
-	 */
-	if (unlikely(!pfn_valid(pfn))) {
-		print_bad_pte(vma, pte, addr);
-		return NULL;
-	}
-#endif
+	VM_BUG_ON(!pfn_valid(pfn));
 
 	/*
-	 * NOTE! We still have PageReserved() pages in the page 
-	 * tables. 
+	 * NOTE! We still have PageReserved() pages in the page tables.
 	 *
-	 * The PAGE_ZERO() pages and various VDSO mappings can
-	 * cause them to exist.
+	 * eg. VDSO mappings can cause them to exist.
 	 */
 out:
 	return pfn_to_page(pfn);
@@ -1244,6 +1248,12 @@ int vm_insert_pfn(struct vm_area_struct 
 	pte_t *pte, entry;
 	spinlock_t *ptl;
 
+	/*
+	 * Technically, architectures with pte_special can avoid all these
+	 * restrictions (same for remap_pfn_range).  However we would like
+	 * consistency in testing and feature parity among all, so we should
+	 * try to keep these invariants in place for everybody.
+	 */
 	BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)));
 	BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) ==
 						(VM_PFNMAP|VM_MIXEDMAP));
@@ -1259,7 +1269,7 @@ int vm_insert_pfn(struct vm_area_struct 
 		goto out_unlock;
 
 	/* Ok, finally just insert the thing.. */
-	entry = pfn_pte(pfn, vma->vm_page_prot);
+	entry = pte_mkspecial(pfn_pte(pfn, vma->vm_page_prot));
 	set_pte_at(mm, addr, pte, entry);
 	update_mmu_cache(vma, addr, entry);
 
@@ -1290,7 +1300,7 @@ static int remap_pte_range(struct mm_str
 	arch_enter_lazy_mmu_mode();
 	do {
 		BUG_ON(!pte_none(*pte));
-		set_pte_at(mm, addr, pte, pfn_pte(pfn, prot));
+		set_pte_at(mm, addr, pte, pte_mkspecial(pfn_pte(pfn, prot)));
 		pfn++;
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 	arch_leave_lazy_mmu_mode();
Index: linux-2.6/include/asm-alpha/pgtable.h
===================================================================
--- linux-2.6.orig/include/asm-alpha/pgtable.h
+++ linux-2.6/include/asm-alpha/pgtable.h
@@ -268,6 +268,7 @@ extern inline int pte_write(pte_t pte)		
 extern inline int pte_dirty(pte_t pte)		{ return pte_val(pte) & _PAGE_DIRTY; }
 extern inline int pte_young(pte_t pte)		{ return pte_val(pte) & _PAGE_ACCESSED; }
 extern inline int pte_file(pte_t pte)		{ return pte_val(pte) & _PAGE_FILE; }
+extern inline int pte_special(pte_t pte)	{ return 0; }
 
 extern inline pte_t pte_wrprotect(pte_t pte)	{ pte_val(pte) |= _PAGE_FOW; return pte; }
 extern inline pte_t pte_mkclean(pte_t pte)	{ pte_val(pte) &= ~(__DIRTY_BITS); return pte; }
@@ -275,6 +276,7 @@ extern inline pte_t pte_mkold(pte_t pte)
 extern inline pte_t pte_mkwrite(pte_t pte)	{ pte_val(pte) &= ~_PAGE_FOW; return pte; }
 extern inline pte_t pte_mkdirty(pte_t pte)	{ pte_val(pte) |= __DIRTY_BITS; return pte; }
 extern inline pte_t pte_mkyoung(pte_t pte)	{ pte_val(pte) |= __ACCESS_BITS; return pte; }
+extern inline pte_t pte_mkspecial(pte_t pte)	{ return pte; }
 
 #define PAGE_DIR_OFFSET(tsk,address) pgd_offset((tsk),(address))
 
Index: linux-2.6/include/asm-avr32/pgtable.h
===================================================================
--- linux-2.6.orig/include/asm-avr32/pgtable.h
+++ linux-2.6/include/asm-avr32/pgtable.h
@@ -211,6 +211,10 @@ static inline int pte_young(pte_t pte)
 {
 	return pte_val(pte) & _PAGE_ACCESSED;
 }
+static inline int pte_special(pte_t pte)
+{
+	return 0;
+}
 
 /*
  * The following only work if pte_present() is not true.
@@ -251,6 +255,10 @@ static inline pte_t pte_mkyoung(pte_t pt
 	set_pte(&pte, __pte(pte_val(pte) | _PAGE_ACCESSED));
 	return pte;
 }
+static inline pte_t pte_mkspecial(pte_t pte)
+{
+	return pte;
+}
 
 #define pmd_none(x)	(!pmd_val(x))
 #define pmd_present(x)	(pmd_val(x) & _PAGE_PRESENT)
Index: linux-2.6/include/asm-cris/pgtable.h
===================================================================
--- linux-2.6.orig/include/asm-cris/pgtable.h
+++ linux-2.6/include/asm-cris/pgtable.h
@@ -115,6 +115,7 @@ static inline int pte_write(pte_t pte)  
 static inline int pte_dirty(pte_t pte)          { return pte_val(pte) & _PAGE_MODIFIED; }
 static inline int pte_young(pte_t pte)          { return pte_val(pte) & _PAGE_ACCESSED; }
 static inline int pte_file(pte_t pte)           { return pte_val(pte) & _PAGE_FILE; }
+static inline int pte_special(pte_t pte)	{ return 0; }
 
 static inline pte_t pte_wrprotect(pte_t pte)
 {
@@ -162,6 +163,7 @@ static inline pte_t pte_mkyoung(pte_t pt
         }
         return pte;
 }
+static inline pte_t pte_mkspecial(pte_t pte)	{ return pte; }
 
 /*
  * Conversion functions: convert a page and protection to a page entry,
Index: linux-2.6/include/asm-frv/pgtable.h
===================================================================
--- linux-2.6.orig/include/asm-frv/pgtable.h
+++ linux-2.6/include/asm-frv/pgtable.h
@@ -380,6 +380,7 @@ static inline pmd_t *pmd_offset(pud_t *d
 static inline int pte_dirty(pte_t pte)		{ return (pte).pte & _PAGE_DIRTY; }
 static inline int pte_young(pte_t pte)		{ return (pte).pte & _PAGE_ACCESSED; }
 static inline int pte_write(pte_t pte)		{ return !((pte).pte & _PAGE_WP); }
+static inline int pte_special(pte_t pte)	{ return 0; }
 
 static inline pte_t pte_mkclean(pte_t pte)	{ (pte).pte &= ~_PAGE_DIRTY; return pte; }
 static inline pte_t pte_mkold(pte_t pte)	{ (pte).pte &= ~_PAGE_ACCESSED; return pte; }
@@ -387,6 +388,7 @@ static inline pte_t pte_wrprotect(pte_t 
 static inline pte_t pte_mkdirty(pte_t pte)	{ (pte).pte |= _PAGE_DIRTY; return pte; }
 static inline pte_t pte_mkyoung(pte_t pte)	{ (pte).pte |= _PAGE_ACCESSED; return pte; }
 static inline pte_t pte_mkwrite(pte_t pte)	{ (pte).pte &= ~_PAGE_WP; return pte; }
+static inline pte_t pte_mkspecial(pte_t pte)	{ return pte; }
 
 static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep)
 {
Index: linux-2.6/include/asm-ia64/pgtable.h
===================================================================
--- linux-2.6.orig/include/asm-ia64/pgtable.h
+++ linux-2.6/include/asm-ia64/pgtable.h
@@ -302,6 +302,8 @@ ia64_phys_addr_valid (unsigned long addr
 #define pte_dirty(pte)		((pte_val(pte) & _PAGE_D) != 0)
 #define pte_young(pte)		((pte_val(pte) & _PAGE_A) != 0)
 #define pte_file(pte)		((pte_val(pte) & _PAGE_FILE) != 0)
+#define pte_special(pte)	0
+
 /*
  * Note: we convert AR_RWX to AR_RX and AR_RW to AR_R by clearing the 2nd bit in the
  * access rights:
@@ -313,6 +315,7 @@ ia64_phys_addr_valid (unsigned long addr
 #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)))
+#define pte_mkspecial(pte)	(pte)
 
 /*
  * Because ia64's Icache and Dcache is not coherent (on a cpu), we need to
Index: linux-2.6/include/asm-m32r/pgtable.h
===================================================================
--- linux-2.6.orig/include/asm-m32r/pgtable.h
+++ linux-2.6/include/asm-m32r/pgtable.h
@@ -214,6 +214,11 @@ static inline int pte_file(pte_t pte)
 	return pte_val(pte) & _PAGE_FILE;
 }
 
+static inline int pte_special(pte_t pte)
+{
+	return 0;
+}
+
 static inline pte_t pte_mkclean(pte_t pte)
 {
 	pte_val(pte) &= ~_PAGE_DIRTY;
@@ -250,6 +255,11 @@ static inline pte_t pte_mkwrite(pte_t pt
 	return pte;
 }
 
+static inline pte_t pte_mkspecial(pte_t pte)
+{
+	return pte;
+}
+
 static inline  int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep)
 {
 	return test_and_clear_bit(_PAGE_BIT_ACCESSED, ptep);
Index: linux-2.6/include/asm-m68k/motorola_pgtable.h
===================================================================
--- linux-2.6.orig/include/asm-m68k/motorola_pgtable.h
+++ linux-2.6/include/asm-m68k/motorola_pgtable.h
@@ -168,6 +168,7 @@ static inline int pte_write(pte_t pte)		
 static inline int pte_dirty(pte_t pte)		{ return pte_val(pte) & _PAGE_DIRTY; }
 static inline int pte_young(pte_t pte)		{ return pte_val(pte) & _PAGE_ACCESSED; }
 static inline int pte_file(pte_t pte)		{ return pte_val(pte) & _PAGE_FILE; }
+static inline int pte_special(pte_t pte)	{ return 0; }
 
 static inline pte_t pte_wrprotect(pte_t pte)	{ pte_val(pte) |= _PAGE_RONLY; return pte; }
 static inline pte_t pte_mkclean(pte_t pte)	{ pte_val(pte) &= ~_PAGE_DIRTY; return pte; }
@@ -185,6 +186,7 @@ static inline pte_t pte_mkcache(pte_t pt
 	pte_val(pte) = (pte_val(pte) & _CACHEMASK040) | m68k_supervisor_cachemode;
 	return pte;
 }
+static inline pte_t pte_mkspecial(pte_t pte)	{ return pte; }
 
 #define PAGE_DIR_OFFSET(tsk,address) pgd_offset((tsk),(address))
 
Index: linux-2.6/include/asm-m68k/sun3_pgtable.h
===================================================================
--- linux-2.6.orig/include/asm-m68k/sun3_pgtable.h
+++ linux-2.6/include/asm-m68k/sun3_pgtable.h
@@ -169,6 +169,7 @@ static inline int pte_write(pte_t pte)		
 static inline int pte_dirty(pte_t pte)		{ return pte_val(pte) & SUN3_PAGE_MODIFIED; }
 static inline int pte_young(pte_t pte)		{ return pte_val(pte) & SUN3_PAGE_ACCESSED; }
 static inline int pte_file(pte_t pte)		{ return pte_val(pte) & SUN3_PAGE_ACCESSED; }
+static inline int pte_special(pte_t pte)	{ return 0; }
 
 static inline pte_t pte_wrprotect(pte_t pte)	{ pte_val(pte) &= ~SUN3_PAGE_WRITEABLE; return pte; }
 static inline pte_t pte_mkclean(pte_t pte)	{ pte_val(pte) &= ~SUN3_PAGE_MODIFIED; return pte; }
@@ -181,6 +182,7 @@ static inline pte_t pte_mknocache(pte_t 
 //static inline pte_t pte_mkcache(pte_t pte)	{ pte_val(pte) &= SUN3_PAGE_NOCACHE; return pte; }
 // until then, use:
 static inline pte_t pte_mkcache(pte_t pte)	{ return pte; }
+static inline pte_t pte_mkspecial(pte_t pte)	{ return pte; }
 
 extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
 extern pgd_t kernel_pg_dir[PTRS_PER_PGD];
Index: linux-2.6/include/asm-mips/pgtable.h
===================================================================
--- linux-2.6.orig/include/asm-mips/pgtable.h
+++ linux-2.6/include/asm-mips/pgtable.h
@@ -285,6 +285,8 @@ static inline pte_t pte_mkyoung(pte_t pt
 	return pte;
 }
 #endif
+static inline int pte_special(pte_t pte)	{ return 0; }
+static inline pte_t pte_mkspecial(pte_t pte)	{ return pte; }
 
 /*
  * Macro to make mark a page protection value as "uncacheable".  Note
Index: linux-2.6/include/asm-parisc/pgtable.h
===================================================================
--- linux-2.6.orig/include/asm-parisc/pgtable.h
+++ linux-2.6/include/asm-parisc/pgtable.h
@@ -331,6 +331,7 @@ static inline int pte_dirty(pte_t pte)		
 static inline int pte_young(pte_t pte)		{ return pte_val(pte) & _PAGE_ACCESSED; }
 static inline int pte_write(pte_t pte)		{ return pte_val(pte) & _PAGE_WRITE; }
 static inline int pte_file(pte_t pte)		{ return pte_val(pte) & _PAGE_FILE; }
+static inline int pte_special(pte_t pte)	{ return 0; }
 
 static inline pte_t pte_mkclean(pte_t pte)	{ pte_val(pte) &= ~_PAGE_DIRTY; return pte; }
 static inline pte_t pte_mkold(pte_t pte)	{ pte_val(pte) &= ~_PAGE_ACCESSED; return pte; }
@@ -338,6 +339,7 @@ static inline pte_t pte_wrprotect(pte_t 
 static inline pte_t pte_mkdirty(pte_t pte)	{ pte_val(pte) |= _PAGE_DIRTY; return pte; }
 static inline pte_t pte_mkyoung(pte_t pte)	{ pte_val(pte) |= _PAGE_ACCESSED; return pte; }
 static inline pte_t pte_mkwrite(pte_t pte)	{ pte_val(pte) |= _PAGE_WRITE; return pte; }
+static inline pte_t pte_mkspecial(pte_t pte)	{ return pte; }
 
 /*
  * Conversion functions: convert a page and protection to a page entry,
Index: linux-2.6/include/asm-powerpc/pgtable-ppc32.h
===================================================================
--- linux-2.6.orig/include/asm-powerpc/pgtable-ppc32.h
+++ linux-2.6/include/asm-powerpc/pgtable-ppc32.h
@@ -514,6 +514,7 @@ static inline int pte_write(pte_t pte)		
 static inline int pte_dirty(pte_t pte)		{ return pte_val(pte) & _PAGE_DIRTY; }
 static inline int pte_young(pte_t pte)		{ return pte_val(pte) & _PAGE_ACCESSED; }
 static inline int pte_file(pte_t pte)		{ return pte_val(pte) & _PAGE_FILE; }
+static inline int pte_special(pte_t pte)	{ return 0; }
 
 static inline void pte_uncache(pte_t pte)       { pte_val(pte) |= _PAGE_NO_CACHE; }
 static inline void pte_cache(pte_t pte)         { pte_val(pte) &= ~_PAGE_NO_CACHE; }
@@ -531,6 +532,8 @@ static inline pte_t pte_mkdirty(pte_t pt
 	pte_val(pte) |= _PAGE_DIRTY; return pte; }
 static inline pte_t pte_mkyoung(pte_t pte) {
 	pte_val(pte) |= _PAGE_ACCESSED; return pte; }
+static inline pte_t pte_mkspecial(pte_t pte) {
+	return pte; }
 
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
Index: linux-2.6/include/asm-powerpc/pgtable-ppc64.h
===================================================================
--- linux-2.6.orig/include/asm-powerpc/pgtable-ppc64.h
+++ linux-2.6/include/asm-powerpc/pgtable-ppc64.h
@@ -239,6 +239,7 @@ static inline int pte_write(pte_t pte) {
 static inline int pte_dirty(pte_t pte) { return pte_val(pte) & _PAGE_DIRTY;}
 static inline int pte_young(pte_t pte) { return pte_val(pte) & _PAGE_ACCESSED;}
 static inline int pte_file(pte_t pte) { return pte_val(pte) & _PAGE_FILE;}
+static inline int pte_special(pte_t pte) { return 0; }
 
 static inline void pte_uncache(pte_t pte) { pte_val(pte) |= _PAGE_NO_CACHE; }
 static inline void pte_cache(pte_t pte)   { pte_val(pte) &= ~_PAGE_NO_CACHE; }
@@ -257,6 +258,8 @@ static inline pte_t pte_mkyoung(pte_t pt
 	pte_val(pte) |= _PAGE_ACCESSED; return pte; }
 static inline pte_t pte_mkhuge(pte_t pte) {
 	return pte; }
+static inline pte_t pte_mkspecial(pte_t pte) {
+	return pte; }
 
 /* Atomic PTE updates */
 static inline unsigned long pte_update(struct mm_struct *mm,
Index: linux-2.6/include/asm-ppc/pgtable.h
===================================================================
--- linux-2.6.orig/include/asm-ppc/pgtable.h
+++ linux-2.6/include/asm-ppc/pgtable.h
@@ -537,6 +537,7 @@ static inline int pte_write(pte_t pte)		
 static inline int pte_dirty(pte_t pte)		{ return pte_val(pte) & _PAGE_DIRTY; }
 static inline int pte_young(pte_t pte)		{ return pte_val(pte) & _PAGE_ACCESSED; }
 static inline int pte_file(pte_t pte)		{ return pte_val(pte) & _PAGE_FILE; }
+static inline int pte_special(pte_t pte)	{ return 0; }
 
 static inline void pte_uncache(pte_t pte)       { pte_val(pte) |= _PAGE_NO_CACHE; }
 static inline void pte_cache(pte_t pte)         { pte_val(pte) &= ~_PAGE_NO_CACHE; }
@@ -554,6 +555,8 @@ static inline pte_t pte_mkdirty(pte_t pt
 	pte_val(pte) |= _PAGE_DIRTY; return pte; }
 static inline pte_t pte_mkyoung(pte_t pte) {
 	pte_val(pte) |= _PAGE_ACCESSED; return pte; }
+static inline pte_t pte_mkspecial(pte_t pte) {
+	return pte; }
 
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
Index: linux-2.6/include/asm-s390/pgtable.h
===================================================================
--- linux-2.6.orig/include/asm-s390/pgtable.h
+++ linux-2.6/include/asm-s390/pgtable.h
@@ -504,6 +504,11 @@ static inline int pte_file(pte_t pte)
 	return (pte_val(pte) & mask) == _PAGE_TYPE_FILE;
 }
 
+static inline int pte_special(pte_t pte)
+{
+	return 0;
+}
+
 #define __HAVE_ARCH_PTE_SAME
 #define pte_same(a,b)  (pte_val(a) == pte_val(b))
 
@@ -654,6 +659,11 @@ static inline pte_t pte_mkyoung(pte_t pt
 	return pte;
 }
 
+static inline pte_t pte_mkspecial(pte_t pte)
+{
+	return pte;
+}
+
 #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
 static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
 					    unsigned long addr, pte_t *ptep)
Index: linux-2.6/include/asm-sh64/pgtable.h
===================================================================
--- linux-2.6.orig/include/asm-sh64/pgtable.h
+++ linux-2.6/include/asm-sh64/pgtable.h
@@ -419,6 +419,7 @@ static inline int pte_dirty(pte_t pte){ 
 static inline int pte_young(pte_t pte){ return pte_val(pte) & _PAGE_ACCESSED; }
 static inline int pte_file(pte_t pte) { return pte_val(pte) & _PAGE_FILE; }
 static inline int pte_write(pte_t pte){ return pte_val(pte) & _PAGE_WRITE; }
+static inline int pte_special(pte_t pte)	{ return 0; }
 
 static inline pte_t pte_wrprotect(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_WRITE)); return pte; }
 static inline pte_t pte_mkclean(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_DIRTY)); return pte; }
@@ -427,6 +428,7 @@ static inline pte_t pte_mkwrite(pte_t pt
 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_mkhuge(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) | _PAGE_SZHUGE)); return pte; }
+static inline pte_t pte_mkspecial(pte_t pte)	{ return pte; }
 
 
 /*
Index: linux-2.6/include/asm-sparc/pgtable.h
===================================================================
--- linux-2.6.orig/include/asm-sparc/pgtable.h
+++ linux-2.6/include/asm-sparc/pgtable.h
@@ -219,6 +219,11 @@ static inline int pte_file(pte_t pte)
 	return pte_val(pte) & BTFIXUP_HALF(pte_filei);
 }
 
+static inline int pte_special(pte_t pte)
+{
+	return 0;
+}
+
 /*
  */
 BTFIXUPDEF_HALF(pte_wrprotecti)
@@ -251,6 +256,8 @@ BTFIXUPDEF_CALL_CONST(pte_t, pte_mkyoung
 #define pte_mkdirty(pte) BTFIXUP_CALL(pte_mkdirty)(pte)
 #define pte_mkyoung(pte) BTFIXUP_CALL(pte_mkyoung)(pte)
 
+#define pte_mkspecial(pte_t pte)    (pte)
+
 #define pfn_pte(pfn, prot)		mk_pte(pfn_to_page(pfn), prot)
 
 BTFIXUPDEF_CALL(unsigned long,	 pte_pfn, pte_t)
Index: linux-2.6/include/asm-sparc64/pgtable.h
===================================================================
--- linux-2.6.orig/include/asm-sparc64/pgtable.h
+++ linux-2.6/include/asm-sparc64/pgtable.h
@@ -506,6 +506,11 @@ static inline pte_t pte_mkyoung(pte_t pt
 	return __pte(pte_val(pte) | mask);
 }
 
+static inline pte_t pte_mkspecial(pte_t pte)
+{
+	return pte;
+}
+
 static inline unsigned long pte_young(pte_t pte)
 {
 	unsigned long mask;
@@ -608,6 +613,11 @@ static inline unsigned long pte_present(
 	return val;
 }
 
+static inline int pte_special(pte_t pte)
+{
+	return 0;
+}
+
 #define pmd_set(pmdp, ptep)	\
 	(pmd_val(*(pmdp)) = (__pa((unsigned long) (ptep)) >> 11UL))
 #define pud_set(pudp, pmdp)	\
Index: linux-2.6/include/asm-xtensa/pgtable.h
===================================================================
--- linux-2.6.orig/include/asm-xtensa/pgtable.h
+++ linux-2.6/include/asm-xtensa/pgtable.h
@@ -212,6 +212,8 @@ static inline int pte_write(pte_t pte) {
 static inline int pte_dirty(pte_t pte) { return pte_val(pte) & _PAGE_DIRTY; }
 static inline int pte_young(pte_t pte) { return pte_val(pte) & _PAGE_ACCESSED; }
 static inline int pte_file(pte_t pte)  { return pte_val(pte) & _PAGE_FILE; }
+static inline int pte_special(pte_t pte) { return 0; }
+
 static inline pte_t pte_wrprotect(pte_t pte)	
 	{ pte_val(pte) &= ~(_PAGE_WRITABLE | _PAGE_HW_WRITE); return pte; }
 static inline pte_t pte_mkclean(pte_t pte)
@@ -224,6 +226,8 @@ static inline pte_t pte_mkyoung(pte_t pt
 	{ pte_val(pte) |= _PAGE_ACCESSED; return pte; }
 static inline pte_t pte_mkwrite(pte_t pte)
 	{ pte_val(pte) |= _PAGE_WRITABLE; return pte; }
+static inline pte_t pte_mkspecial(pte_t pte)
+	{ return pte; }
 
 /*
  * Conversion functions: convert a page and protection to a page entry,

-- 

--
To unsubscribe from this list: send the line "unsubscribe linux-arch" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[patch 2/6] mm: introduce pte_special pte bit

[npiggin]

[-- Attachment #1: mm-normal-pte-bit.patch --]
[-- Type: text/plain, Size: 30854 bytes --]

s390 for one, cannot implement VM_MIXEDMAP with pfn_valid, due to their
memory model (which is more dynamic than most). Instead, they had proposed
to implement it with an additional path through vm_normal_page(), using a
bit in the pte to determine whether or not the page should be refcounted:

vm_normal_page()
{
	...
        if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) {
                if (vma->vm_flags & VM_MIXEDMAP) {
#ifdef s390
			if (!mixedmap_refcount_pte(pte))
				return NULL;
#else
                        if (!pfn_valid(pfn))
                                return NULL;
#endif
                        goto out;
                }
	...
}

This is fine, however if we are allowed to use a bit in the pte to
determine refcountedness, we can use that to _completely_ replace all the
vma based schemes. So instead of adding more cases to the already complex
vma-based scheme, we can have a clearly seperate and simple pte-based scheme
(and get slightly better code generation in the process):

vm_normal_page()
{
#ifdef s390
	if (!mixedmap_refcount_pte(pte))
		return NULL;
	return pte_page(pte);
#else
	...
#endif
}

And finally, we may rather make this concept usable by any architecture
rather than making it s390 only, so implement a new type of pte state
for this. Unfortunately the old vma based code must stay, because some
architectures may not be able to spare pte bits. This makes vm_normal_page
a little bit more ugly than we would like, but the 2 cases are clearly
seperate.

So introduce a pte_special pte state, and use it in mm/memory.c. It is
currently a noop for all architectures, so this doesn't actually result
in any compiled code changes to mm/memory.o.

Signed-off-by: Nick Piggin <npiggin@suse.de>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Hugh Dickins <hugh@veritas.com>
Cc: Jared Hulbert <jaredeh@gmail.com>
Cc: Carsten Otte <cotte@de.ibm.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: linux-arch@vger.kernel.org
Cc: linux-mm@kvack.org
---
 include/asm-alpha/pgtable.h         |    2 
 include/asm-avr32/pgtable.h         |    8 ++
 include/asm-cris/pgtable.h          |    2 
 include/asm-frv/pgtable.h           |    2 
 include/asm-ia64/pgtable.h          |    3 +
 include/asm-m32r/pgtable.h          |   10 +++
 include/asm-m68k/motorola_pgtable.h |    2 
 include/asm-m68k/sun3_pgtable.h     |    2 
 include/asm-mips/pgtable.h          |    2 
 include/asm-parisc/pgtable.h        |    2 
 include/asm-powerpc/pgtable-ppc32.h |    3 +
 include/asm-powerpc/pgtable-ppc64.h |    3 +
 include/asm-ppc/pgtable.h           |    3 +
 include/asm-s390/pgtable.h          |   10 +++
 include/asm-sh64/pgtable.h          |    2 
 include/asm-sparc/pgtable.h         |    7 ++
 include/asm-sparc64/pgtable.h       |   10 +++
 include/asm-um/pgtable.h            |   10 +++
 include/asm-x86/pgtable_32.h        |    2 
 include/asm-x86/pgtable_64.h        |    2 
 include/asm-xtensa/pgtable.h        |    4 +
 include/linux/mm.h                  |    3 -
 mm/memory.c                         |   98 +++++++++++++++++++-----------------
 23 files changed, 147 insertions(+), 45 deletions(-)

Index: linux-2.6/include/asm-um/pgtable.h
===================================================================
--- linux-2.6.orig/include/asm-um/pgtable.h
+++ linux-2.6/include/asm-um/pgtable.h
@@ -220,6 +220,11 @@ static inline int pte_newprot(pte_t pte)
 	return(pte_present(pte) && (pte_get_bits(pte, _PAGE_NEWPROT)));
 }
 
+static inline int pte_special(pte_t pte)
+{
+	return 0;
+}
+
 /*
  * =================================
  * Flags setting section.
@@ -288,6 +293,11 @@ static inline pte_t pte_mknewpage(pte_t 
 	return(pte);
 }
 
+static inline pte_t pte_mkspecial(pte_t pte)
+{
+	return(pte);
+}
+
 static inline void set_pte(pte_t *pteptr, pte_t pteval)
 {
 	pte_copy(*pteptr, pteval);
Index: linux-2.6/include/asm-x86/pgtable_32.h
===================================================================
--- linux-2.6.orig/include/asm-x86/pgtable_32.h
+++ linux-2.6/include/asm-x86/pgtable_32.h
@@ -219,6 +219,7 @@ static inline int pte_dirty(pte_t pte)		
 static inline int pte_young(pte_t pte)		{ return (pte).pte_low & _PAGE_ACCESSED; }
 static inline int pte_write(pte_t pte)		{ return (pte).pte_low & _PAGE_RW; }
 static inline int pte_huge(pte_t pte)		{ return (pte).pte_low & _PAGE_PSE; }
+static inline int pte_special(pte_t pte)	{ return 0; }
 
 /*
  * The following only works if pte_present() is not true.
@@ -232,6 +233,7 @@ static inline pte_t pte_mkdirty(pte_t pt
 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_PSE; return pte; }
+static inline pte_t pte_mkspecial(pte_t pte)	{ return pte; }
 
 #ifdef CONFIG_X86_PAE
 # include <asm/pgtable-3level.h>
Index: linux-2.6/include/asm-x86/pgtable_64.h
===================================================================
--- linux-2.6.orig/include/asm-x86/pgtable_64.h
+++ linux-2.6/include/asm-x86/pgtable_64.h
@@ -272,6 +272,7 @@ static inline int pte_young(pte_t pte)		
 static 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; }
 static inline int pte_huge(pte_t pte)		{ return pte_val(pte) & _PAGE_PSE; }
+static inline int pte_special(pte_t pte)	{ return 0; }
 
 static inline pte_t pte_mkclean(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_DIRTY)); return pte; }
 static inline pte_t pte_mkold(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_ACCESSED)); return pte; }
@@ -282,6 +283,7 @@ static inline pte_t pte_mkyoung(pte_t pt
 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_PSE)); return pte; }
 static inline pte_t pte_clrhuge(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_PSE)); return pte; }
+static inline pte_t pte_mkspecial(pte_t pte)	{ return pte; }
 
 struct vm_area_struct;
 
Index: linux-2.6/include/linux/mm.h
===================================================================
--- linux-2.6.orig/include/linux/mm.h
+++ linux-2.6/include/linux/mm.h
@@ -699,7 +699,8 @@ struct zap_details {
 	unsigned long truncate_count;		/* Compare vm_truncate_count */
 };
 
-struct page *vm_normal_page(struct vm_area_struct *, unsigned long, pte_t);
+struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, pte_t pte);
+
 unsigned long zap_page_range(struct vm_area_struct *vma, unsigned long address,
 		unsigned long size, struct zap_details *);
 unsigned long unmap_vmas(struct mmu_gather **tlb,
Index: linux-2.6/mm/memory.c
===================================================================
--- linux-2.6.orig/mm/memory.c
+++ linux-2.6/mm/memory.c
@@ -361,34 +361,38 @@ static inline int is_cow_mapping(unsigne
 }
 
 /*
- * This function gets the "struct page" associated with a pte or returns
- * NULL if no "struct page" is associated with the pte.
+ * vm_normal_page -- This function gets the "struct page" associated with a pte.
  *
- * A raw VM_PFNMAP mapping (ie. one that is not COWed) may not have any "struct
- * page" backing, and even if they do, they are not refcounted. COWed pages of
- * a VM_PFNMAP do always have a struct page, and they are normally refcounted
- * (they are _normal_ pages).
- *
- * So a raw PFNMAP mapping will have each page table entry just pointing
- * to a page frame number, and as far as the VM layer is concerned, those do
- * not have pages associated with them - even if the PFN might point to memory
- * that otherwise is perfectly fine and has a "struct page".
+ * "Special" mappings do not wish to be associated with a "struct page" (either
+ * it doesn't exist, or it exists but they don't want to touch it). In this
+ * case, NULL is returned here. "Normal" mappings do have a struct page.
+ *
+ * There are 2 broad cases. Firstly, an architecture may define a pte_special()
+ * pte bit, in which case this function is trivial. Secondly, an architecture
+ * may not have a spare pte bit, which requires a more complicated scheme,
+ * described below.
+ *
+ * A raw VM_PFNMAP mapping (ie. one that is not COWed) is always considered a
+ * special mapping (even if there are underlying and valid "struct pages").
+ * COWed pages of a VM_PFNMAP are always normal.
  *
  * The way we recognize COWed pages within VM_PFNMAP mappings is through the
  * rules set up by "remap_pfn_range()": the vma will have the VM_PFNMAP bit
- * set, and the vm_pgoff will point to the first PFN mapped: thus every
- * page that is a raw mapping will always honor the rule
+ * set, and the vm_pgoff will point to the first PFN mapped: thus every special
+ * mapping will always honor the rule
  *
  *	pfn_of_page == vma->vm_pgoff + ((addr - vma->vm_start) >> PAGE_SHIFT)
  *
- * A call to vm_normal_page() will return NULL for such a page.
+ * And for normal mappings this is false.
  *
- * If the page doesn't follow the "remap_pfn_range()" rule in a VM_PFNMAP
- * then the page has been COW'ed.  A COW'ed page _does_ have a "struct page"
- * associated with it even if it is in a VM_PFNMAP range.  Calling
- * vm_normal_page() on such a page will therefore return the "struct page".
+ * This restricts such mappings to be a linear translation from virtual address
+ * to pfn. To get around this restriction, we allow arbitrary mappings so long
+ * as the vma is not a COW mapping; in that case, we know that all ptes are
+ * special (because none can have been COWed).
  *
  *
+ * In order to support COW of arbitrary special mappings, we have VM_MIXEDMAP.
+ *
  * VM_MIXEDMAP mappings can likewise contain memory with or without "struct
  * page" backing, however the difference is that _all_ pages with a struct
  * page (that is, those where pfn_valid is true) are refcounted and considered
@@ -397,16 +401,28 @@ static inline int is_cow_mapping(unsigne
  * advantage is that we don't have to follow the strict linearity rule of
  * PFNMAP mappings in order to support COWable mappings.
  *
- * A call to vm_normal_page() with a VM_MIXEDMAP mapping will return the
- * associated "struct page" or NULL for memory not backed by a "struct page".
- *
- *
- * All other mappings should have a valid struct page, which will be
- * returned by a call to vm_normal_page().
  */
+#ifdef __HAVE_ARCH_PTE_SPECIAL
+# define HAVE_PTE_SPECIAL 1
+#else
+# define HAVE_PTE_SPECIAL 0
+#endif
 struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, pte_t pte)
 {
-	unsigned long pfn = pte_pfn(pte);
+	unsigned long pfn;
+
+	if (HAVE_PTE_SPECIAL) {
+		if (likely(!pte_special(pte))) {
+			VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
+			return pte_page(pte);
+		}
+		VM_BUG_ON(!(vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP)));
+		return NULL;
+	}
+
+	/* !HAVE_PTE_SPECIAL case follows: */
+
+	pfn = pte_pfn(pte);
 
 	if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) {
 		if (vma->vm_flags & VM_MIXEDMAP) {
@@ -414,7 +430,8 @@ struct page *vm_normal_page(struct vm_ar
 				return NULL;
 			goto out;
 		} else {
-			unsigned long off = (addr-vma->vm_start) >> PAGE_SHIFT;
+			unsigned long off;
+			off = (addr - vma->vm_start) >> PAGE_SHIFT;
 			if (pfn == vma->vm_pgoff + off)
 				return NULL;
 			if (!is_cow_mapping(vma->vm_flags))
@@ -422,25 +439,12 @@ struct page *vm_normal_page(struct vm_ar
 		}
 	}
 
-#ifdef CONFIG_DEBUG_VM
-	/*
-	 * Add some anal sanity checks for now. Eventually,
-	 * we should just do "return pfn_to_page(pfn)", but
-	 * in the meantime we check that we get a valid pfn,
-	 * and that the resulting page looks ok.
-	 */
-	if (unlikely(!pfn_valid(pfn))) {
-		print_bad_pte(vma, pte, addr);
-		return NULL;
-	}
-#endif
+	VM_BUG_ON(!pfn_valid(pfn));
 
 	/*
-	 * NOTE! We still have PageReserved() pages in the page 
-	 * tables. 
+	 * NOTE! We still have PageReserved() pages in the page tables.
 	 *
-	 * The PAGE_ZERO() pages and various VDSO mappings can
-	 * cause them to exist.
+	 * eg. VDSO mappings can cause them to exist.
 	 */
 out:
 	return pfn_to_page(pfn);
@@ -1244,6 +1248,12 @@ int vm_insert_pfn(struct vm_area_struct 
 	pte_t *pte, entry;
 	spinlock_t *ptl;
 
+	/*
+	 * Technically, architectures with pte_special can avoid all these
+	 * restrictions (same for remap_pfn_range).  However we would like
+	 * consistency in testing and feature parity among all, so we should
+	 * try to keep these invariants in place for everybody.
+	 */
 	BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)));
 	BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) ==
 						(VM_PFNMAP|VM_MIXEDMAP));
@@ -1259,7 +1269,7 @@ int vm_insert_pfn(struct vm_area_struct 
 		goto out_unlock;
 
 	/* Ok, finally just insert the thing.. */
-	entry = pfn_pte(pfn, vma->vm_page_prot);
+	entry = pte_mkspecial(pfn_pte(pfn, vma->vm_page_prot));
 	set_pte_at(mm, addr, pte, entry);
 	update_mmu_cache(vma, addr, entry);
 
@@ -1290,7 +1300,7 @@ static int remap_pte_range(struct mm_str
 	arch_enter_lazy_mmu_mode();
 	do {
 		BUG_ON(!pte_none(*pte));
-		set_pte_at(mm, addr, pte, pfn_pte(pfn, prot));
+		set_pte_at(mm, addr, pte, pte_mkspecial(pfn_pte(pfn, prot)));
 		pfn++;
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 	arch_leave_lazy_mmu_mode();
Index: linux-2.6/include/asm-alpha/pgtable.h
===================================================================
--- linux-2.6.orig/include/asm-alpha/pgtable.h
+++ linux-2.6/include/asm-alpha/pgtable.h
@@ -268,6 +268,7 @@ extern inline int pte_write(pte_t pte)		
 extern inline int pte_dirty(pte_t pte)		{ return pte_val(pte) & _PAGE_DIRTY; }
 extern inline int pte_young(pte_t pte)		{ return pte_val(pte) & _PAGE_ACCESSED; }
 extern inline int pte_file(pte_t pte)		{ return pte_val(pte) & _PAGE_FILE; }
+extern inline int pte_special(pte_t pte)	{ return 0; }
 
 extern inline pte_t pte_wrprotect(pte_t pte)	{ pte_val(pte) |= _PAGE_FOW; return pte; }
 extern inline pte_t pte_mkclean(pte_t pte)	{ pte_val(pte) &= ~(__DIRTY_BITS); return pte; }
@@ -275,6 +276,7 @@ extern inline pte_t pte_mkold(pte_t pte)
 extern inline pte_t pte_mkwrite(pte_t pte)	{ pte_val(pte) &= ~_PAGE_FOW; return pte; }
 extern inline pte_t pte_mkdirty(pte_t pte)	{ pte_val(pte) |= __DIRTY_BITS; return pte; }
 extern inline pte_t pte_mkyoung(pte_t pte)	{ pte_val(pte) |= __ACCESS_BITS; return pte; }
+extern inline pte_t pte_mkspecial(pte_t pte)	{ return pte; }
 
 #define PAGE_DIR_OFFSET(tsk,address) pgd_offset((tsk),(address))
 
Index: linux-2.6/include/asm-avr32/pgtable.h
===================================================================
--- linux-2.6.orig/include/asm-avr32/pgtable.h
+++ linux-2.6/include/asm-avr32/pgtable.h
@@ -211,6 +211,10 @@ static inline int pte_young(pte_t pte)
 {
 	return pte_val(pte) & _PAGE_ACCESSED;
 }
+static inline int pte_special(pte_t pte)
+{
+	return 0;
+}
 
 /*
  * The following only work if pte_present() is not true.
@@ -251,6 +255,10 @@ static inline pte_t pte_mkyoung(pte_t pt
 	set_pte(&pte, __pte(pte_val(pte) | _PAGE_ACCESSED));
 	return pte;
 }
+static inline pte_t pte_mkspecial(pte_t pte)
+{
+	return pte;
+}
 
 #define pmd_none(x)	(!pmd_val(x))
 #define pmd_present(x)	(pmd_val(x) & _PAGE_PRESENT)
Index: linux-2.6/include/asm-cris/pgtable.h
===================================================================
--- linux-2.6.orig/include/asm-cris/pgtable.h
+++ linux-2.6/include/asm-cris/pgtable.h
@@ -115,6 +115,7 @@ static inline int pte_write(pte_t pte)  
 static inline int pte_dirty(pte_t pte)          { return pte_val(pte) & _PAGE_MODIFIED; }
 static inline int pte_young(pte_t pte)          { return pte_val(pte) & _PAGE_ACCESSED; }
 static inline int pte_file(pte_t pte)           { return pte_val(pte) & _PAGE_FILE; }
+static inline int pte_special(pte_t pte)	{ return 0; }
 
 static inline pte_t pte_wrprotect(pte_t pte)
 {
@@ -162,6 +163,7 @@ static inline pte_t pte_mkyoung(pte_t pt
         }
         return pte;
 }
+static inline pte_t pte_mkspecial(pte_t pte)	{ return pte; }
 
 /*
  * Conversion functions: convert a page and protection to a page entry,
Index: linux-2.6/include/asm-frv/pgtable.h
===================================================================
--- linux-2.6.orig/include/asm-frv/pgtable.h
+++ linux-2.6/include/asm-frv/pgtable.h
@@ -380,6 +380,7 @@ static inline pmd_t *pmd_offset(pud_t *d
 static inline int pte_dirty(pte_t pte)		{ return (pte).pte & _PAGE_DIRTY; }
 static inline int pte_young(pte_t pte)		{ return (pte).pte & _PAGE_ACCESSED; }
 static inline int pte_write(pte_t pte)		{ return !((pte).pte & _PAGE_WP); }
+static inline int pte_special(pte_t pte)	{ return 0; }
 
 static inline pte_t pte_mkclean(pte_t pte)	{ (pte).pte &= ~_PAGE_DIRTY; return pte; }
 static inline pte_t pte_mkold(pte_t pte)	{ (pte).pte &= ~_PAGE_ACCESSED; return pte; }
@@ -387,6 +388,7 @@ static inline pte_t pte_wrprotect(pte_t 
 static inline pte_t pte_mkdirty(pte_t pte)	{ (pte).pte |= _PAGE_DIRTY; return pte; }
 static inline pte_t pte_mkyoung(pte_t pte)	{ (pte).pte |= _PAGE_ACCESSED; return pte; }
 static inline pte_t pte_mkwrite(pte_t pte)	{ (pte).pte &= ~_PAGE_WP; return pte; }
+static inline pte_t pte_mkspecial(pte_t pte)	{ return pte; }
 
 static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep)
 {
Index: linux-2.6/include/asm-ia64/pgtable.h
===================================================================
--- linux-2.6.orig/include/asm-ia64/pgtable.h
+++ linux-2.6/include/asm-ia64/pgtable.h
@@ -302,6 +302,8 @@ ia64_phys_addr_valid (unsigned long addr
 #define pte_dirty(pte)		((pte_val(pte) & _PAGE_D) != 0)
 #define pte_young(pte)		((pte_val(pte) & _PAGE_A) != 0)
 #define pte_file(pte)		((pte_val(pte) & _PAGE_FILE) != 0)
+#define pte_special(pte)	0
+
 /*
  * Note: we convert AR_RWX to AR_RX and AR_RW to AR_R by clearing the 2nd bit in the
  * access rights:
@@ -313,6 +315,7 @@ ia64_phys_addr_valid (unsigned long addr
 #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)))
+#define pte_mkspecial(pte)	(pte)
 
 /*
  * Because ia64's Icache and Dcache is not coherent (on a cpu), we need to
Index: linux-2.6/include/asm-m32r/pgtable.h
===================================================================
--- linux-2.6.orig/include/asm-m32r/pgtable.h
+++ linux-2.6/include/asm-m32r/pgtable.h
@@ -214,6 +214,11 @@ static inline int pte_file(pte_t pte)
 	return pte_val(pte) & _PAGE_FILE;
 }
 
+static inline int pte_special(pte_t pte)
+{
+	return 0;
+}
+
 static inline pte_t pte_mkclean(pte_t pte)
 {
 	pte_val(pte) &= ~_PAGE_DIRTY;
@@ -250,6 +255,11 @@ static inline pte_t pte_mkwrite(pte_t pt
 	return pte;
 }
 
+static inline pte_t pte_mkspecial(pte_t pte)
+{
+	return pte;
+}
+
 static inline  int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep)
 {
 	return test_and_clear_bit(_PAGE_BIT_ACCESSED, ptep);
Index: linux-2.6/include/asm-m68k/motorola_pgtable.h
===================================================================
--- linux-2.6.orig/include/asm-m68k/motorola_pgtable.h
+++ linux-2.6/include/asm-m68k/motorola_pgtable.h
@@ -168,6 +168,7 @@ static inline int pte_write(pte_t pte)		
 static inline int pte_dirty(pte_t pte)		{ return pte_val(pte) & _PAGE_DIRTY; }
 static inline int pte_young(pte_t pte)		{ return pte_val(pte) & _PAGE_ACCESSED; }
 static inline int pte_file(pte_t pte)		{ return pte_val(pte) & _PAGE_FILE; }
+static inline int pte_special(pte_t pte)	{ return 0; }
 
 static inline pte_t pte_wrprotect(pte_t pte)	{ pte_val(pte) |= _PAGE_RONLY; return pte; }
 static inline pte_t pte_mkclean(pte_t pte)	{ pte_val(pte) &= ~_PAGE_DIRTY; return pte; }
@@ -185,6 +186,7 @@ static inline pte_t pte_mkcache(pte_t pt
 	pte_val(pte) = (pte_val(pte) & _CACHEMASK040) | m68k_supervisor_cachemode;
 	return pte;
 }
+static inline pte_t pte_mkspecial(pte_t pte)	{ return pte; }
 
 #define PAGE_DIR_OFFSET(tsk,address) pgd_offset((tsk),(address))
 
Index: linux-2.6/include/asm-m68k/sun3_pgtable.h
===================================================================
--- linux-2.6.orig/include/asm-m68k/sun3_pgtable.h
+++ linux-2.6/include/asm-m68k/sun3_pgtable.h
@@ -169,6 +169,7 @@ static inline int pte_write(pte_t pte)		
 static inline int pte_dirty(pte_t pte)		{ return pte_val(pte) & SUN3_PAGE_MODIFIED; }
 static inline int pte_young(pte_t pte)		{ return pte_val(pte) & SUN3_PAGE_ACCESSED; }
 static inline int pte_file(pte_t pte)		{ return pte_val(pte) & SUN3_PAGE_ACCESSED; }
+static inline int pte_special(pte_t pte)	{ return 0; }
 
 static inline pte_t pte_wrprotect(pte_t pte)	{ pte_val(pte) &= ~SUN3_PAGE_WRITEABLE; return pte; }
 static inline pte_t pte_mkclean(pte_t pte)	{ pte_val(pte) &= ~SUN3_PAGE_MODIFIED; return pte; }
@@ -181,6 +182,7 @@ static inline pte_t pte_mknocache(pte_t 
 //static inline pte_t pte_mkcache(pte_t pte)	{ pte_val(pte) &= SUN3_PAGE_NOCACHE; return pte; }
 // until then, use:
 static inline pte_t pte_mkcache(pte_t pte)	{ return pte; }
+static inline pte_t pte_mkspecial(pte_t pte)	{ return pte; }
 
 extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
 extern pgd_t kernel_pg_dir[PTRS_PER_PGD];
Index: linux-2.6/include/asm-mips/pgtable.h
===================================================================
--- linux-2.6.orig/include/asm-mips/pgtable.h
+++ linux-2.6/include/asm-mips/pgtable.h
@@ -285,6 +285,8 @@ static inline pte_t pte_mkyoung(pte_t pt
 	return pte;
 }
 #endif
+static inline int pte_special(pte_t pte)	{ return 0; }
+static inline pte_t pte_mkspecial(pte_t pte)	{ return pte; }
 
 /*
  * Macro to make mark a page protection value as "uncacheable".  Note
Index: linux-2.6/include/asm-parisc/pgtable.h
===================================================================
--- linux-2.6.orig/include/asm-parisc/pgtable.h
+++ linux-2.6/include/asm-parisc/pgtable.h
@@ -331,6 +331,7 @@ static inline int pte_dirty(pte_t pte)		
 static inline int pte_young(pte_t pte)		{ return pte_val(pte) & _PAGE_ACCESSED; }
 static inline int pte_write(pte_t pte)		{ return pte_val(pte) & _PAGE_WRITE; }
 static inline int pte_file(pte_t pte)		{ return pte_val(pte) & _PAGE_FILE; }
+static inline int pte_special(pte_t pte)	{ return 0; }
 
 static inline pte_t pte_mkclean(pte_t pte)	{ pte_val(pte) &= ~_PAGE_DIRTY; return pte; }
 static inline pte_t pte_mkold(pte_t pte)	{ pte_val(pte) &= ~_PAGE_ACCESSED; return pte; }
@@ -338,6 +339,7 @@ static inline pte_t pte_wrprotect(pte_t 
 static inline pte_t pte_mkdirty(pte_t pte)	{ pte_val(pte) |= _PAGE_DIRTY; return pte; }
 static inline pte_t pte_mkyoung(pte_t pte)	{ pte_val(pte) |= _PAGE_ACCESSED; return pte; }
 static inline pte_t pte_mkwrite(pte_t pte)	{ pte_val(pte) |= _PAGE_WRITE; return pte; }
+static inline pte_t pte_mkspecial(pte_t pte)	{ return pte; }
 
 /*
  * Conversion functions: convert a page and protection to a page entry,
Index: linux-2.6/include/asm-powerpc/pgtable-ppc32.h
===================================================================
--- linux-2.6.orig/include/asm-powerpc/pgtable-ppc32.h
+++ linux-2.6/include/asm-powerpc/pgtable-ppc32.h
@@ -514,6 +514,7 @@ static inline int pte_write(pte_t pte)		
 static inline int pte_dirty(pte_t pte)		{ return pte_val(pte) & _PAGE_DIRTY; }
 static inline int pte_young(pte_t pte)		{ return pte_val(pte) & _PAGE_ACCESSED; }
 static inline int pte_file(pte_t pte)		{ return pte_val(pte) & _PAGE_FILE; }
+static inline int pte_special(pte_t pte)	{ return 0; }
 
 static inline void pte_uncache(pte_t pte)       { pte_val(pte) |= _PAGE_NO_CACHE; }
 static inline void pte_cache(pte_t pte)         { pte_val(pte) &= ~_PAGE_NO_CACHE; }
@@ -531,6 +532,8 @@ static inline pte_t pte_mkdirty(pte_t pt
 	pte_val(pte) |= _PAGE_DIRTY; return pte; }
 static inline pte_t pte_mkyoung(pte_t pte) {
 	pte_val(pte) |= _PAGE_ACCESSED; return pte; }
+static inline pte_t pte_mkspecial(pte_t pte) {
+	return pte; }
 
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
Index: linux-2.6/include/asm-powerpc/pgtable-ppc64.h
===================================================================
--- linux-2.6.orig/include/asm-powerpc/pgtable-ppc64.h
+++ linux-2.6/include/asm-powerpc/pgtable-ppc64.h
@@ -239,6 +239,7 @@ static inline int pte_write(pte_t pte) {
 static inline int pte_dirty(pte_t pte) { return pte_val(pte) & _PAGE_DIRTY;}
 static inline int pte_young(pte_t pte) { return pte_val(pte) & _PAGE_ACCESSED;}
 static inline int pte_file(pte_t pte) { return pte_val(pte) & _PAGE_FILE;}
+static inline int pte_special(pte_t pte) { return 0; }
 
 static inline void pte_uncache(pte_t pte) { pte_val(pte) |= _PAGE_NO_CACHE; }
 static inline void pte_cache(pte_t pte)   { pte_val(pte) &= ~_PAGE_NO_CACHE; }
@@ -257,6 +258,8 @@ static inline pte_t pte_mkyoung(pte_t pt
 	pte_val(pte) |= _PAGE_ACCESSED; return pte; }
 static inline pte_t pte_mkhuge(pte_t pte) {
 	return pte; }
+static inline pte_t pte_mkspecial(pte_t pte) {
+	return pte; }
 
 /* Atomic PTE updates */
 static inline unsigned long pte_update(struct mm_struct *mm,
Index: linux-2.6/include/asm-ppc/pgtable.h
===================================================================
--- linux-2.6.orig/include/asm-ppc/pgtable.h
+++ linux-2.6/include/asm-ppc/pgtable.h
@@ -537,6 +537,7 @@ static inline int pte_write(pte_t pte)		
 static inline int pte_dirty(pte_t pte)		{ return pte_val(pte) & _PAGE_DIRTY; }
 static inline int pte_young(pte_t pte)		{ return pte_val(pte) & _PAGE_ACCESSED; }
 static inline int pte_file(pte_t pte)		{ return pte_val(pte) & _PAGE_FILE; }
+static inline int pte_special(pte_t pte)	{ return 0; }
 
 static inline void pte_uncache(pte_t pte)       { pte_val(pte) |= _PAGE_NO_CACHE; }
 static inline void pte_cache(pte_t pte)         { pte_val(pte) &= ~_PAGE_NO_CACHE; }
@@ -554,6 +555,8 @@ static inline pte_t pte_mkdirty(pte_t pt
 	pte_val(pte) |= _PAGE_DIRTY; return pte; }
 static inline pte_t pte_mkyoung(pte_t pte) {
 	pte_val(pte) |= _PAGE_ACCESSED; return pte; }
+static inline pte_t pte_mkspecial(pte_t pte) {
+	return pte; }
 
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
Index: linux-2.6/include/asm-s390/pgtable.h
===================================================================
--- linux-2.6.orig/include/asm-s390/pgtable.h
+++ linux-2.6/include/asm-s390/pgtable.h
@@ -504,6 +504,11 @@ static inline int pte_file(pte_t pte)
 	return (pte_val(pte) & mask) == _PAGE_TYPE_FILE;
 }
 
+static inline int pte_special(pte_t pte)
+{
+	return 0;
+}
+
 #define __HAVE_ARCH_PTE_SAME
 #define pte_same(a,b)  (pte_val(a) == pte_val(b))
 
@@ -654,6 +659,11 @@ static inline pte_t pte_mkyoung(pte_t pt
 	return pte;
 }
 
+static inline pte_t pte_mkspecial(pte_t pte)
+{
+	return pte;
+}
+
 #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
 static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
 					    unsigned long addr, pte_t *ptep)
Index: linux-2.6/include/asm-sh64/pgtable.h
===================================================================
--- linux-2.6.orig/include/asm-sh64/pgtable.h
+++ linux-2.6/include/asm-sh64/pgtable.h
@@ -419,6 +419,7 @@ static inline int pte_dirty(pte_t pte){ 
 static inline int pte_young(pte_t pte){ return pte_val(pte) & _PAGE_ACCESSED; }
 static inline int pte_file(pte_t pte) { return pte_val(pte) & _PAGE_FILE; }
 static inline int pte_write(pte_t pte){ return pte_val(pte) & _PAGE_WRITE; }
+static inline int pte_special(pte_t pte)	{ return 0; }
 
 static inline pte_t pte_wrprotect(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_WRITE)); return pte; }
 static inline pte_t pte_mkclean(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_DIRTY)); return pte; }
@@ -427,6 +428,7 @@ static inline pte_t pte_mkwrite(pte_t pt
 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_mkhuge(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) | _PAGE_SZHUGE)); return pte; }
+static inline pte_t pte_mkspecial(pte_t pte)	{ return pte; }
 
 
 /*
Index: linux-2.6/include/asm-sparc/pgtable.h
===================================================================
--- linux-2.6.orig/include/asm-sparc/pgtable.h
+++ linux-2.6/include/asm-sparc/pgtable.h
@@ -219,6 +219,11 @@ static inline int pte_file(pte_t pte)
 	return pte_val(pte) & BTFIXUP_HALF(pte_filei);
 }
 
+static inline int pte_special(pte_t pte)
+{
+	return 0;
+}
+
 /*
  */
 BTFIXUPDEF_HALF(pte_wrprotecti)
@@ -251,6 +256,8 @@ BTFIXUPDEF_CALL_CONST(pte_t, pte_mkyoung
 #define pte_mkdirty(pte) BTFIXUP_CALL(pte_mkdirty)(pte)
 #define pte_mkyoung(pte) BTFIXUP_CALL(pte_mkyoung)(pte)
 
+#define pte_mkspecial(pte_t pte)    (pte)
+
 #define pfn_pte(pfn, prot)		mk_pte(pfn_to_page(pfn), prot)
 
 BTFIXUPDEF_CALL(unsigned long,	 pte_pfn, pte_t)
Index: linux-2.6/include/asm-sparc64/pgtable.h
===================================================================
--- linux-2.6.orig/include/asm-sparc64/pgtable.h
+++ linux-2.6/include/asm-sparc64/pgtable.h
@@ -506,6 +506,11 @@ static inline pte_t pte_mkyoung(pte_t pt
 	return __pte(pte_val(pte) | mask);
 }
 
+static inline pte_t pte_mkspecial(pte_t pte)
+{
+	return pte;
+}
+
 static inline unsigned long pte_young(pte_t pte)
 {
 	unsigned long mask;
@@ -608,6 +613,11 @@ static inline unsigned long pte_present(
 	return val;
 }
 
+static inline int pte_special(pte_t pte)
+{
+	return 0;
+}
+
 #define pmd_set(pmdp, ptep)	\
 	(pmd_val(*(pmdp)) = (__pa((unsigned long) (ptep)) >> 11UL))
 #define pud_set(pudp, pmdp)	\
Index: linux-2.6/include/asm-xtensa/pgtable.h
===================================================================
--- linux-2.6.orig/include/asm-xtensa/pgtable.h
+++ linux-2.6/include/asm-xtensa/pgtable.h
@@ -212,6 +212,8 @@ static inline int pte_write(pte_t pte) {
 static inline int pte_dirty(pte_t pte) { return pte_val(pte) & _PAGE_DIRTY; }
 static inline int pte_young(pte_t pte) { return pte_val(pte) & _PAGE_ACCESSED; }
 static inline int pte_file(pte_t pte)  { return pte_val(pte) & _PAGE_FILE; }
+static inline int pte_special(pte_t pte) { return 0; }
+
 static inline pte_t pte_wrprotect(pte_t pte)	
 	{ pte_val(pte) &= ~(_PAGE_WRITABLE | _PAGE_HW_WRITE); return pte; }
 static inline pte_t pte_mkclean(pte_t pte)
@@ -224,6 +226,8 @@ static inline pte_t pte_mkyoung(pte_t pt
 	{ pte_val(pte) |= _PAGE_ACCESSED; return pte; }
 static inline pte_t pte_mkwrite(pte_t pte)
 	{ pte_val(pte) |= _PAGE_WRITABLE; return pte; }
+static inline pte_t pte_mkspecial(pte_t pte)
+	{ return pte; }
 
 /*
  * Conversion functions: convert a page and protection to a page entry,

-- 

Re: [patch 2/6] mm: introduce pte_special pte bit

[Linus Torvalds]

On Fri, 18 Jan 2008, npiggin@suse.de wrote:
>   */
> +#ifdef __HAVE_ARCH_PTE_SPECIAL
> +# define HAVE_PTE_SPECIAL 1
> +#else
> +# define HAVE_PTE_SPECIAL 0
> +#endif
>  struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, pte_t pte)
>  {
> -	unsigned long pfn = pte_pfn(pte);
> +	unsigned long pfn;
> +
> +	if (HAVE_PTE_SPECIAL) {

I really don't think this is *any* different from "#ifdefs in code".

#ifdef's in code is not about syntax, it's about abstraction. This is 
still the exact same thing as having an #ifdef around it, and in many ways 
it is *worse*, because now it's just made to look somewhat different with 
a particularly ugly #ifdef.

IOW, this didn't abstract the issue away, it just massaged it to look 
different.

I suspect that the nicest abstraction would be to simply make the whole 
function be a per-architecture thing. Not exposing a "pte_special()" bit 
at all, but instead having the interface simply be:

 - create special entries:
	pte_t pte_mkspecial(pte_t pte)

 - check if an entry is special:
	struct page *vm_normal_page(vma, addr, pte)

and now it's not while the naming is a bit odd (for historical reasons), 
at least it is properly *abstracted* and you don't have any #ifdef's in 
code (and we'd probably need to extend that abstraction then for the 
"locklessly look up page" case eventually).

[ To make it slightly more regular, we could make "pte_mkspecial()" take 
  the vma/addr thing too, even though it would never really use it except 
  to perhaps have a VM_BUG_ON() that it only happens within XIP/PFNMAP 
  vma's.

  The "pte_mkspecial()" definitely has more to to with "vm_normal_page()"
  than with the other "pte_mkxyzzy()" functions, so it really might make
  sense to instead make the thing

	void set_special_page(vma, addr, pte_t *, pfn, pgprot) 

  because it is never acceptable to do "pte_mkspecial()" on any existent 
  PTE *anyway*, so we might as well make the interface reflect that: it's 
  not that you make a pte "special", it's that you insert a special page 
  into the VM.

  So the operation really conceptually has more to do with "set_pte()" 
  than with "pte_mkxxx()", no? ]

Then, just have a library version of the long form, and make architectures 
that don't support it just use that (just so that you don't have to 
duplicate that silly thing). So an architecture that support special page 
flags would do somethiing like

	#define set_special_page(vma,addr,ptep,pfn,prot) \
		set_pte_at(vma, addr, ptep, mk_special_pte(pfn,prot))
	#define vm_normal_page(vma,addr,pte)
		(pte_special(pte) ? NULL : pte_page(pte))

and other architectures would just do

	#define set_special_page(vma,addr,ptep,pfn,prot) \
		set_pte_at(vma, addr, ptep, mk_pte(pfn,prot))
	#define vm_normal_page(vma,addr,pte) \
		generic_vm_normal_page(vma,addr,pte)

or something.

THAT is what I mean by "no #ifdef's in code" - that the selection is done 
at a higher level, the same way we have good interfaces with clear 
*conceptual* meaning for all the other PTE accessing stuff, rather than 
have conditionals in the architecture-independent code.

It's not about syntax - it's about having good conceptual abstractions.

			Linus

Re: [patch 2/6] mm: introduce pte_special pte bit

[Sam Ravnborg]

On Fri, Jan 18, 2008 at 08:41:22AM -0800, Linus Torvalds wrote:
> 
> 
> On Fri, 18 Jan 2008, npiggin@suse.de wrote:
> >   */
> > +#ifdef __HAVE_ARCH_PTE_SPECIAL
> > +# define HAVE_PTE_SPECIAL 1
> > +#else
> > +# define HAVE_PTE_SPECIAL 0
> > +#endif
> >  struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, pte_t pte)
> >  {
> > -	unsigned long pfn = pte_pfn(pte);
> > +	unsigned long pfn;
> > +
> > +	if (HAVE_PTE_SPECIAL) {
> 
> I really don't think this is *any* different from "#ifdefs in code".

One fundamental difference is that with the above syntax we always
compile both versions of the code - so we do not end up with one
version that builds and another version that dont.

This has always striked me as a good reason to do the above and
I think it is busybox that does so with success.

	Sam

Re: [patch 2/6] mm: introduce pte_special pte bit

[Linus Torvalds]

On Fri, 18 Jan 2008, Sam Ravnborg wrote:
> 
> One fundamental difference is that with the above syntax we always
> compile both versions of the code - so we do not end up with one
> version that builds and another version that dont.

Yes, in that sense it tends to be better to use C language constructs over 
preprocessor constructs, since error diagnostics and syntax checking is 
improved.

So yeah, I'll give you that it can be an improvement. It's just not what I 
was really hoping for.

		Linus

Re: [patch 2/6] mm: introduce pte_special pte bit

[Sam Ravnborg]

On Fri, Jan 18, 2008 at 10:28:39AM -0800, Linus Torvalds wrote:
> 
> 
> On Fri, 18 Jan 2008, Sam Ravnborg wrote:
> > 
> > One fundamental difference is that with the above syntax we always
> > compile both versions of the code - so we do not end up with one
> > version that builds and another version that dont.
> 
> Yes, in that sense it tends to be better to use C language constructs over 
> preprocessor constructs, since error diagnostics and syntax checking is 
> improved.
> 
> So yeah, I'll give you that it can be an improvement. It's just not what I 
> was really hoping for.

Just to clarify - my comment was solely related to the usage
of if (HAVE_*) versus #ifdef.
I had nothing to do with the actual discussion which I do not try to follw .

	Sam

Re: [patch 2/6] mm: introduce pte_special pte bit

[Nick Piggin]

On Fri, Jan 18, 2008 at 08:41:22AM -0800, Linus Torvalds wrote:
> 
> 
> On Fri, 18 Jan 2008, npiggin@suse.de wrote:
> >   */
> > +#ifdef __HAVE_ARCH_PTE_SPECIAL
> > +# define HAVE_PTE_SPECIAL 1
> > +#else
> > +# define HAVE_PTE_SPECIAL 0
> > +#endif
> >  struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, pte_t pte)
> >  {
> > -	unsigned long pfn = pte_pfn(pte);
> > +	unsigned long pfn;
> > +
> > +	if (HAVE_PTE_SPECIAL) {
> 
> I really don't think this is *any* different from "#ifdefs in code".
> 
> #ifdef's in code is not about syntax, it's about abstraction. This is 
> still the exact same thing as having an #ifdef around it, and in many ways 
> it is *worse*, because now it's just made to look somewhat different with 
> a particularly ugly #ifdef.
> 
> IOW, this didn't abstract the issue away, it just massaged it to look 
> different.

Yes, the if () is just to please Andrew, not you ;)

I thought in your last mail on the subject, that you had conceded the
vma-based scheme should stay, so I might have misunderstood that to mean
you would, reluctantly, go with the scheme. I guess I need to try a bit
harder ;)

 
> I suspect that the nicest abstraction would be to simply make the whole 
> function be a per-architecture thing. Not exposing a "pte_special()" bit 
> at all, but instead having the interface simply be:
> 
>  - create special entries:
> 	pte_t pte_mkspecial(pte_t pte)
> 
>  - check if an entry is special:
> 	struct page *vm_normal_page(vma, addr, pte)
> 
> and now it's not while the naming is a bit odd (for historical reasons), 
> at least it is properly *abstracted* and you don't have any #ifdef's in 
> code (and we'd probably need to extend that abstraction then for the 
> "locklessly look up page" case eventually).

Now I would have done this in a flash, except the existing vm_normal_page
code is quite a lot, and complex, to duplicate in every architecture.

 
> [ To make it slightly more regular, we could make "pte_mkspecial()" take 
>   the vma/addr thing too, even though it would never really use it except 
>   to perhaps have a VM_BUG_ON() that it only happens within XIP/PFNMAP 
>   vma's.
> 
>   The "pte_mkspecial()" definitely has more to to with "vm_normal_page()"
>   than with the other "pte_mkxyzzy()" functions, so it really might make
>   sense to instead make the thing
> 
> 	void set_special_page(vma, addr, pte_t *, pfn, pgprot) 
> 
>   because it is never acceptable to do "pte_mkspecial()" on any existent 
>   PTE *anyway*, so we might as well make the interface reflect that: it's 
>   not that you make a pte "special", it's that you insert a special page 
>   into the VM.
> 
>   So the operation really conceptually has more to do with "set_pte()" 
>   than with "pte_mkxxx()", no? ]

Possibly, although I think going that far is hiding things from mm/ a bit
much. If you have a look at the places that call pte_mkspecial, it isn't
too much I think...

 
> Then, just have a library version of the long form, and make architectures 
> that don't support it just use that (just so that you don't have to 
> duplicate that silly thing). So an architecture that support special page 
> flags would do somethiing like
> 
> 	#define set_special_page(vma,addr,ptep,pfn,prot) \
> 		set_pte_at(vma, addr, ptep, mk_special_pte(pfn,prot))
> 	#define vm_normal_page(vma,addr,pte)
> 		(pte_special(pte) ? NULL : pte_page(pte))
> 
> and other architectures would just do
> 
> 	#define set_special_page(vma,addr,ptep,pfn,prot) \
> 		set_pte_at(vma, addr, ptep, mk_pte(pfn,prot))
> 	#define vm_normal_page(vma,addr,pte) \
> 		generic_vm_normal_page(vma,addr,pte)
> 
> or something.
> 
> THAT is what I mean by "no #ifdef's in code" - that the selection is done 
> at a higher level, the same way we have good interfaces with clear 
> *conceptual* meaning for all the other PTE accessing stuff, rather than 
> have conditionals in the architecture-independent code.

OK, that gets around the "duplicate vm_normal_page everywhere" issue I
had. I'm still not quite happy with it ;)

How about taking a different approach. How about also having a pte_normal()
function. Each architecture that has a pte special bit would make this
!pte_special, and those that don't would return 0. They return 0 from both
pte_special and pte_normal because they don't know whether the pte is
special or normal.

Then vm_normal_page would become:

    if (pte_special(pte))
        return NULL;
    else if (pte_normal(pte))
        return pte_page(pte);

    ... /* vma based scheme */

Re: [patch 2/6] mm: introduce pte_special pte bit

[Linus Torvalds]

On Fri, 18 Jan 2008, Nick Piggin wrote:
> 
> I thought in your last mail on the subject, that you had conceded the
> vma-based scheme should stay, so I might have misunderstood that to mean
> you would, reluctantly, go with the scheme. I guess I need to try a bit
> harder ;)

Yes, I did concede that apparently we cannot just mandate "let's just use 
a bit in the pte".

So I do agree that we seem to be forced to have two different 
implementations: one for architectures where we can make use of a marker 
on the PTE itself (or perhaps some *other* way to distinguish things 
automatically), and one for the ones where we need to just be able 
to distinguish purely based on our own data structures.

I just then didn't like the lack of abstraction.

> How about taking a different approach. How about also having a pte_normal()
> function.

Well, one reason I'd prefer not to, is that I can well imagine an 
architecture that doesn't actually put the "normal" bit in the PTE itself, 
but in a separate data structure.

In particular, let's say that you decide that

 - the architecture really doesn't have any space in the hw page tables
 - but for various reasons you *really* don't want to use the tricky 
   "page->offset" logic etc
 - ..and you realize that PFNMAP and FIXMAP are actually very rare

so..

 - you just associate each PFNMAP/FIXMAP vma with a simple bitmap that 
   contains the "special" bit.

It's actually not that hard to do. If you have an architecture-specific 
interface like

	struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, pte_t pte);

then it wouldn't be too hard at all to create a hash lookup on the VMA (or 
perhaps on a "vma, 256-page-aligned(addr)" tuple) to look up a bitmap, and 
then use the address to see if it was marked special or not.

But yes, then you'd also need to have that extended

	set_special_pte_at(vma, addr, pfn, prot);

interface to set that bit in that bitmap.

See? 

Is it better than what we already have for the generic case? Possibly not. 
But I like abstractions that aren't tied to *one* particular 
implementation.

			Linus

Re: [patch 2/6] mm: introduce pte_special pte bit

[Nick Piggin]

On Fri, Jan 18, 2008 at 03:03:03PM -0800, Linus Torvalds wrote:
> 
> 
> On Fri, 18 Jan 2008, Nick Piggin wrote:
> > 
> > I thought in your last mail on the subject, that you had conceded the
> > vma-based scheme should stay, so I might have misunderstood that to mean
> > you would, reluctantly, go with the scheme. I guess I need to try a bit
> > harder ;)
> 
> Yes, I did concede that apparently we cannot just mandate "let's just use 
> a bit in the pte".
> 
> So I do agree that we seem to be forced to have two different 
> implementations: one for architectures where we can make use of a marker 
> on the PTE itself (or perhaps some *other* way to distinguish things 
> automatically), and one for the ones where we need to just be able 
> to distinguish purely based on our own data structures.

Yep, thanks for the clarification.


> I just then didn't like the lack of abstraction.
> 
> > How about taking a different approach. How about also having a pte_normal()
> > function.
> 
> Well, one reason I'd prefer not to, is that I can well imagine an 
> architecture that doesn't actually put the "normal" bit in the PTE itself, 
> but in a separate data structure.
> 
> In particular, let's say that you decide that
> 
>  - the architecture really doesn't have any space in the hw page tables
>  - but for various reasons you *really* don't want to use the tricky 
>    "page->offset" logic etc
>  - ..and you realize that PFNMAP and FIXMAP are actually very rare
> 
> so..
> 
>  - you just associate each PFNMAP/FIXMAP vma with a simple bitmap that 
>    contains the "special" bit.
> 
> It's actually not that hard to do. If you have an architecture-specific 
> interface like
> 
> 	struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, pte_t pte);
> 
> then it wouldn't be too hard at all to create a hash lookup on the VMA (or 
> perhaps on a "vma, 256-page-aligned(addr)" tuple) to look up a bitmap, and 
> then use the address to see if it was marked special or not.
> 
> But yes, then you'd also need to have that extended
> 
> 	set_special_pte_at(vma, addr, pfn, prot);
> 
> interface to set that bit in that bitmap.
> 
> See? 
> 
> Is it better than what we already have for the generic case? Possibly not. 
> But I like abstractions that aren't tied to *one* particular 
> implementation.

Well that's all true, but I would be a bit worried about architectures
inventing their own ways of doin gthings. I mean, _every_ implementation
needs to be understood by core mm/ developers; and conversely, none of
the architecture maintainers need to care a single bit about any of the
implementations if they provide some basic low level things to us.

So I'd argue that if someone really needed to invent another scheme, then
that should also be somehow folded into mm/ code if possible rather than
let the arch do it...

Re: [patch 2/6] mm: introduce pte_special pte bit

[Nick Piggin]

On Fri, Jan 18, 2008 at 11:46:22PM +0100, Nick Piggin wrote:
> On Fri, Jan 18, 2008 at 08:41:22AM -0800, Linus Torvalds wrote:
>  
> > Then, just have a library version of the long form, and make architectures 
> > that don't support it just use that (just so that you don't have to 
> > duplicate that silly thing). So an architecture that support special page 
> > flags would do somethiing like
> > 
> > 	#define set_special_page(vma,addr,ptep,pfn,prot) \
> > 		set_pte_at(vma, addr, ptep, mk_special_pte(pfn,prot))
> > 	#define vm_normal_page(vma,addr,pte)
> > 		(pte_special(pte) ? NULL : pte_page(pte))
> > 
> > and other architectures would just do
> > 
> > 	#define set_special_page(vma,addr,ptep,pfn,prot) \
> > 		set_pte_at(vma, addr, ptep, mk_pte(pfn,prot))
> > 	#define vm_normal_page(vma,addr,pte) \
> > 		generic_vm_normal_page(vma,addr,pte)
> > 
> > or something.
> > 
> > THAT is what I mean by "no #ifdef's in code" - that the selection is done 
> > at a higher level, the same way we have good interfaces with clear 
> > *conceptual* meaning for all the other PTE accessing stuff, rather than 
> > have conditionals in the architecture-independent code.
> 
> OK, that gets around the "duplicate vm_normal_page everywhere" issue I
> had. I'm still not quite happy with it ;)
> 
> How about taking a different approach. How about also having a pte_normal()
> function. Each architecture that has a pte special bit would make this
> !pte_special, and those that don't would return 0. They return 0 from both
> pte_special and pte_normal because they don't know whether the pte is
> special or normal.
> 
> Then vm_normal_page would become:
> 
>     if (pte_special(pte))
>         return NULL;
>     else if (pte_normal(pte))
>         return pte_page(pte);
> 
>     ... /* vma based scheme */

Hmm, it's not *quite* trivial as that for one important case:
vm_insert_mixed. Because we don't actually have a pte yet, so we can't
easily reuse insert_page / insert_pfn, rather we have to build the pte
first and then check it (patch attached, but I think it is a step
backwards)...

Really, I don't think either of my two approaches or your approach is
really a fundamentally different _abstraction_. It basically just has
to accommodate 2 different code paths no matter how you look at it. I
don't know how this is different to, say, conditionally compiling eg.
the FLATMEM/SPARSEMEM memory model code, or rwsem code, depending on
whether an architecture has defined some symbol. It happens all over
the kernel.

Actually, I'd argue it is _better_ than that, because the logic stays
in one place (one screenful, even), and away from abuse or divergence
by arch code.

If one actually came up with a new API that handles both cases better,
I'd say that is a different abstraction. Or if you could come up with
some different arch functions which would allow vm_normal_page to be
streamlined to read more like a regular C function, that should be a
different abstraction...

I'm still keen on my first patch. I know it isn't beautiful, but I
think it is better than the alternatives.

---

mm: add vm_insert_mixed

vm_insert_mixed will insert either a raw pfn or a refcounted struct page
into the page tables, depending on whether vm_normal_page() will return
the page or not. With the introduction of the new pte bit, this is now
a bit too tricky for drivers to be doing themselves.

filemap_xip uses this in a subsequent patch.

---
Index: linux-2.6/include/linux/mm.h
===================================================================
--- linux-2.6.orig/include/linux/mm.h
+++ linux-2.6/include/linux/mm.h
@@ -1097,6 +1097,8 @@ int remap_pfn_range(struct vm_area_struc
 int vm_insert_page(struct vm_area_struct *, unsigned long addr, struct page *);
 int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
 			unsigned long pfn);
+int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
+			unsigned long pfn);
 
 struct page *follow_page(struct vm_area_struct *, unsigned long address,
 			unsigned int foll_flags);
Index: linux-2.6/mm/memory.c
===================================================================
--- linux-2.6.orig/mm/memory.c
+++ linux-2.6/mm/memory.c
@@ -1282,6 +1282,53 @@ out:
 }
 EXPORT_SYMBOL(vm_insert_pfn);
 
+int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
+			unsigned long pfn)
+{
+	struct mm_struct *mm = vma->vm_mm;
+	int retval;
+	pte_t *pte, entry;
+	spinlock_t *ptl;
+
+	BUG_ON(!(vma->vm_flags & VM_MIXEDMAP));
+
+	if (addr < vma->vm_start || addr >= vma->vm_end)
+		return -EFAULT;
+
+	retval = -ENOMEM;
+	pte = get_locked_pte(mm, addr, &ptl);
+	if (!pte)
+		goto out;
+	retval = -EBUSY;
+	if (!pte_none(*pte))
+		goto out_unlock;
+
+	entry = pte_mkspecial(pfn_pte(pfn, prot));
+	/*
+	 * If we don't have pte special, then we have to use the pfn_valid()
+	 * based VM_MIXEDMAP scheme (see vm_normal_page), and thus we *must*
+	 * refcount the page if pfn_valid is true. Otherwise we can *always*
+	 * avoid refcounting the page if we have pte_special.
+	 */
+	if (!pte_special(entry) && pfn_valid(pfn)) {
+		struct page *page;
+
+		page = pfn_to_page(pfn);
+		get_page(page);
+		inc_mm_counter(mm, file_rss);
+		page_add_file_rmap(page);
+	}
+	/* Ok, finally just insert the thing.. */
+	set_pte_at(mm, addr, pte, entry);
+
+	retval = 0;
+out_unlock:
+	pte_unmap_unlock(pte, ptl);
+out:
+	return retval;
+}
+EXPORT_SYMBOL(vm_insert_mixed);
+
 /*
  * maps a range of physical memory into the requested pages. the old
  * mappings are removed. any references to nonexistent pages results