Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/x86/linux-2.6-xen-next

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/x86/linux-2.6-xen-next: (52 commits)
  xen: add balloon driver
  xen: allow compilation with non-flat memory
  xen: fold xen_sysexit into xen_iret
  xen: allow set_pte_at on init_mm to be lockless
  xen: disable preemption during tlb flush
  xen pvfb: Para-virtual framebuffer, keyboard and pointer driver
  xen: Add compatibility aliases for frontend drivers
  xen: Module autoprobing support for frontend drivers
  xen blkfront: Delay wait for block devices until after the disk is added
  xen/blkfront: use bdget_disk
  xen: Make xen-blkfront write its protocol ABI to xenstore
  xen: import arch generic part of xencomm
  xen: make grant table arch portable
  xen: replace callers of alloc_vm_area()/free_vm_area() with xen_ prefixed one
  xen: make include/xen/page.h portable moving those definitions under asm dir
  xen: add resend_irq_on_evtchn() definition into events.c
  Xen: make events.c portable for ia64/xen support
  xen: move events.c to drivers/xen for IA64/Xen support
  xen: move features.c from arch/x86/xen/features.c to drivers/xen
  xen: add missing definitions in include/xen/interface/vcpu.h which ia64/xen needs
  ...

12 files changed, 393 insertions, 294 deletions

diff --git a/include/asm-x86/paravirt.h b/include/asm-x86/paravirt.h
index 3d419398499b..0f13b945e240 100644
--- a/include/asm-x86/paravirt.h
+++ b/include/asm-x86/paravirt.h
@@ -220,11 +220,13 @@ struct pv_mmu_ops {
 				 unsigned long va);
 
 	/* Hooks for allocating/releasing pagetable pages */
-	void (*alloc_pt)(struct mm_struct *mm, u32 pfn);
-	void (*alloc_pd)(struct mm_struct *mm, u32 pfn);
-	void (*alloc_pd_clone)(u32 pfn, u32 clonepfn, u32 start, u32 count);
-	void (*release_pt)(u32 pfn);
-	void (*release_pd)(u32 pfn);
+	void (*alloc_pte)(struct mm_struct *mm, u32 pfn);
+	void (*alloc_pmd)(struct mm_struct *mm, u32 pfn);
+	void (*alloc_pmd_clone)(u32 pfn, u32 clonepfn, u32 start, u32 count);
+	void (*alloc_pud)(struct mm_struct *mm, u32 pfn);
+	void (*release_pte)(u32 pfn);
+	void (*release_pmd)(u32 pfn);
+	void (*release_pud)(u32 pfn);
 
 	/* Pagetable manipulation functions */
 	void (*set_pte)(pte_t *ptep, pte_t pteval);
@@ -910,28 +912,37 @@ static inline void flush_tlb_others(cpumask_t cpumask, struct mm_struct *mm,
 	PVOP_VCALL3(pv_mmu_ops.flush_tlb_others, &cpumask, mm, va);
 }
 
-static inline void paravirt_alloc_pt(struct mm_struct *mm, unsigned pfn)
+static inline void paravirt_alloc_pte(struct mm_struct *mm, unsigned pfn)
 {
-	PVOP_VCALL2(pv_mmu_ops.alloc_pt, mm, pfn);
+	PVOP_VCALL2(pv_mmu_ops.alloc_pte, mm, pfn);
 }
-static inline void paravirt_release_pt(unsigned pfn)
+static inline void paravirt_release_pte(unsigned pfn)
 {
-	PVOP_VCALL1(pv_mmu_ops.release_pt, pfn);
+	PVOP_VCALL1(pv_mmu_ops.release_pte, pfn);
 }
 
-static inline void paravirt_alloc_pd(struct mm_struct *mm, unsigned pfn)
+static inline void paravirt_alloc_pmd(struct mm_struct *mm, unsigned pfn)
 {
-	PVOP_VCALL2(pv_mmu_ops.alloc_pd, mm, pfn);
+	PVOP_VCALL2(pv_mmu_ops.alloc_pmd, mm, pfn);
 }
 
-static inline void paravirt_alloc_pd_clone(unsigned pfn, unsigned clonepfn,
-					   unsigned start, unsigned count)
+static inline void paravirt_alloc_pmd_clone(unsigned pfn, unsigned clonepfn,
+					    unsigned start, unsigned count)
 {
-	PVOP_VCALL4(pv_mmu_ops.alloc_pd_clone, pfn, clonepfn, start, count);
+	PVOP_VCALL4(pv_mmu_ops.alloc_pmd_clone, pfn, clonepfn, start, count);
 }
-static inline void paravirt_release_pd(unsigned pfn)
+static inline void paravirt_release_pmd(unsigned pfn)
 {
-	PVOP_VCALL1(pv_mmu_ops.release_pd, pfn);
+	PVOP_VCALL1(pv_mmu_ops.release_pmd, pfn);
+}
+
+static inline void paravirt_alloc_pud(struct mm_struct *mm, unsigned pfn)
+{
+	PVOP_VCALL2(pv_mmu_ops.alloc_pud, mm, pfn);
+}
+static inline void paravirt_release_pud(unsigned pfn)
+{
+	PVOP_VCALL1(pv_mmu_ops.release_pud, pfn);
 }
 
 #ifdef CONFIG_HIGHPTE
diff --git a/include/asm-x86/pgalloc.h b/include/asm-x86/pgalloc.h
index 5886eed05886..91e4641f3f31 100644
--- a/include/asm-x86/pgalloc.h
+++ b/include/asm-x86/pgalloc.h
@@ -1,5 +1,110 @@
-#ifdef CONFIG_X86_32
-# include "pgalloc_32.h"
+#ifndef _ASM_X86_PGALLOC_H
+#define _ASM_X86_PGALLOC_H
+
+#include <linux/threads.h>
+#include <linux/mm.h>		/* for struct page */
+#include <linux/pagemap.h>
+
+#ifdef CONFIG_PARAVIRT
+#include <asm/paravirt.h>
 #else
-# include "pgalloc_64.h"
+static inline void paravirt_alloc_pte(struct mm_struct *mm, unsigned long pfn)	{}
+static inline void paravirt_alloc_pmd(struct mm_struct *mm, unsigned long pfn)	{}
+static inline void paravirt_alloc_pmd_clone(unsigned long pfn, unsigned long clonepfn,
+					    unsigned long start, unsigned long count) {}
+static inline void paravirt_alloc_pud(struct mm_struct *mm, unsigned long pfn)	{}
+static inline void paravirt_release_pte(unsigned long pfn) {}
+static inline void paravirt_release_pmd(unsigned long pfn) {}
+static inline void paravirt_release_pud(unsigned long pfn) {}
 #endif
+
+/*
+ * Allocate and free page tables.
+ */
+extern pgd_t *pgd_alloc(struct mm_struct *);
+extern void pgd_free(struct mm_struct *mm, pgd_t *pgd);
+
+extern pte_t *pte_alloc_one_kernel(struct mm_struct *, unsigned long);
+extern pgtable_t pte_alloc_one(struct mm_struct *, unsigned long);
+
+/* Should really implement gc for free page table pages. This could be
+   done with a reference count in struct page. */
+
+static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
+{
+	BUG_ON((unsigned long)pte & (PAGE_SIZE-1));
+	free_page((unsigned long)pte);
+}
+
+static inline void pte_free(struct mm_struct *mm, struct page *pte)
+{
+	__free_page(pte);
+}
+
+extern void __pte_free_tlb(struct mmu_gather *tlb, struct page *pte);
+
+static inline void pmd_populate_kernel(struct mm_struct *mm,
+				       pmd_t *pmd, pte_t *pte)
+{
+	paravirt_alloc_pte(mm, __pa(pte) >> PAGE_SHIFT);
+	set_pmd(pmd, __pmd(__pa(pte) | _PAGE_TABLE));
+}
+
+static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd,
+				struct page *pte)
+{
+	unsigned long pfn = page_to_pfn(pte);
+
+	paravirt_alloc_pte(mm, pfn);
+	set_pmd(pmd, __pmd(((pteval_t)pfn << PAGE_SHIFT) | _PAGE_TABLE));
+}
+
+#define pmd_pgtable(pmd) pmd_page(pmd)
+
+#if PAGETABLE_LEVELS > 2
+static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
+{
+	return (pmd_t *)get_zeroed_page(GFP_KERNEL|__GFP_REPEAT);
+}
+
+static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
+{
+	BUG_ON((unsigned long)pmd & (PAGE_SIZE-1));
+	free_page((unsigned long)pmd);
+}
+
+extern void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd);
+
+#ifdef CONFIG_X86_PAE
+extern void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd);
+#else	/* !CONFIG_X86_PAE */
+static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
+{
+	paravirt_alloc_pmd(mm, __pa(pmd) >> PAGE_SHIFT);
+	set_pud(pud, __pud(_PAGE_TABLE | __pa(pmd)));
+}
+#endif	/* CONFIG_X86_PAE */
+
+#if PAGETABLE_LEVELS > 3
+static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud)
+{
+	paravirt_alloc_pud(mm, __pa(pud) >> PAGE_SHIFT);
+	set_pgd(pgd, __pgd(_PAGE_TABLE | __pa(pud)));
+}
+
+static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
+{
+	return (pud_t *)get_zeroed_page(GFP_KERNEL|__GFP_REPEAT);
+}
+
+static inline void pud_free(struct mm_struct *mm, pud_t *pud)
+{
+	BUG_ON((unsigned long)pud & (PAGE_SIZE-1));
+	free_page((unsigned long)pud);
+}
+
+extern void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud);
+#endif	/* PAGETABLE_LEVELS > 3 */
+#endif	/* PAGETABLE_LEVELS > 2 */
+
+#endif	/* _ASM_X86_PGALLOC_H */
diff --git a/include/asm-x86/pgalloc_32.h b/include/asm-x86/pgalloc_32.h
deleted file mode 100644
index 6bea6e5b5ee5..000000000000
--- a/include/asm-x86/pgalloc_32.h
+++ /dev/null
@@ -1,95 +0,0 @@
-#ifndef _I386_PGALLOC_H
-#define _I386_PGALLOC_H
-
-#include <linux/threads.h>
-#include <linux/mm.h>		/* for struct page */
-#include <linux/pagemap.h>
-#include <asm/tlb.h>
-#include <asm-generic/tlb.h>
-
-#ifdef CONFIG_PARAVIRT
-#include <asm/paravirt.h>
-#else
-#define paravirt_alloc_pt(mm, pfn) do { } while (0)
-#define paravirt_alloc_pd(mm, pfn) do { } while (0)
-#define paravirt_alloc_pd_clone(pfn, clonepfn, start, count) do { } while (0)
-#define paravirt_release_pt(pfn) do { } while (0)
-#define paravirt_release_pd(pfn) do { } while (0)
-#endif
-
-static inline void pmd_populate_kernel(struct mm_struct *mm,
-				       pmd_t *pmd, pte_t *pte)
-{
-	paravirt_alloc_pt(mm, __pa(pte) >> PAGE_SHIFT);
-	set_pmd(pmd, __pmd(__pa(pte) | _PAGE_TABLE));
-}
-
-static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, struct page *pte)
-{
-	unsigned long pfn = page_to_pfn(pte);
-
-	paravirt_alloc_pt(mm, pfn);
-	set_pmd(pmd, __pmd(((pteval_t)pfn << PAGE_SHIFT) | _PAGE_TABLE));
-}
-#define pmd_pgtable(pmd) pmd_page(pmd)
-
-/*
- * Allocate and free page tables.
- */
-extern pgd_t *pgd_alloc(struct mm_struct *);
-extern void pgd_free(struct mm_struct *mm, pgd_t *pgd);
-
-extern pte_t *pte_alloc_one_kernel(struct mm_struct *, unsigned long);
-extern pgtable_t pte_alloc_one(struct mm_struct *, unsigned long);
-
-static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
-{
-	free_page((unsigned long)pte);
-}
-
-static inline void pte_free(struct mm_struct *mm, pgtable_t pte)
-{
-	pgtable_page_dtor(pte);
-	__free_page(pte);
-}
-
-
-extern void __pte_free_tlb(struct mmu_gather *tlb, struct page *pte);
-
-#ifdef CONFIG_X86_PAE
-/*
- * In the PAE case we free the pmds as part of the pgd.
- */
-static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
-{
-	return (pmd_t *)get_zeroed_page(GFP_KERNEL|__GFP_REPEAT);
-}
-
-static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
-{
-	BUG_ON((unsigned long)pmd & (PAGE_SIZE-1));
-	free_page((unsigned long)pmd);
-}
-
-extern void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd);
-
-static inline void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd)
-{
-	paravirt_alloc_pd(mm, __pa(pmd) >> PAGE_SHIFT);
-
-	/* Note: almost everything apart from _PAGE_PRESENT is
-	   reserved at the pmd (PDPT) level. */
-	set_pud(pudp, __pud(__pa(pmd) | _PAGE_PRESENT));
-
-	/*
-	 * According to Intel App note "TLBs, Paging-Structure Caches,
-	 * and Their Invalidation", April 2007, document 317080-001,
-	 * section 8.1: in PAE mode we explicitly have to flush the
-	 * TLB via cr3 if the top-level pgd is changed...
-	 */
-	if (mm == current->active_mm)
-		write_cr3(read_cr3());
-}
-#endif	/* CONFIG_X86_PAE */
-
-#endif /* _I386_PGALLOC_H */
diff --git a/include/asm-x86/pgalloc_64.h b/include/asm-x86/pgalloc_64.h
deleted file mode 100644
index 8d6722320dcc..000000000000
--- a/include/asm-x86/pgalloc_64.h
+++ /dev/null
@@ -1,133 +0,0 @@
-#ifndef _X86_64_PGALLOC_H
-#define _X86_64_PGALLOC_H
-
-#include <asm/pda.h>
-#include <linux/threads.h>
-#include <linux/mm.h>
-
-#define pmd_populate_kernel(mm, pmd, pte) \
-		set_pmd(pmd, __pmd(_PAGE_TABLE | __pa(pte)))
-#define pud_populate(mm, pud, pmd) \
-		set_pud(pud, __pud(_PAGE_TABLE | __pa(pmd)))
-#define pgd_populate(mm, pgd, pud) \
-		set_pgd(pgd, __pgd(_PAGE_TABLE | __pa(pud)))
-
-#define pmd_pgtable(pmd) pmd_page(pmd)
-
-static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, struct page *pte)
-{
-	set_pmd(pmd, __pmd(_PAGE_TABLE | (page_to_pfn(pte) << PAGE_SHIFT)));
-}
-
-static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
-{
-	BUG_ON((unsigned long)pmd & (PAGE_SIZE-1));
-	free_page((unsigned long)pmd);
-}
-
-static inline pmd_t *pmd_alloc_one (struct mm_struct *mm, unsigned long addr)
-{
-	return (pmd_t *)get_zeroed_page(GFP_KERNEL|__GFP_REPEAT);
-}
-
-static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
-{
-	return (pud_t *)get_zeroed_page(GFP_KERNEL|__GFP_REPEAT);
-}
-
-static inline void pud_free(struct mm_struct *mm, pud_t *pud)
-{
-	BUG_ON((unsigned long)pud & (PAGE_SIZE-1));
-	free_page((unsigned long)pud);
-}
-
-static inline void pgd_list_add(pgd_t *pgd)
-{
-	struct page *page = virt_to_page(pgd);
-	unsigned long flags;
-
-	spin_lock_irqsave(&pgd_lock, flags);
-	list_add(&page->lru, &pgd_list);
-	spin_unlock_irqrestore(&pgd_lock, flags);
-}
-
-static inline void pgd_list_del(pgd_t *pgd)
-{
-	struct page *page = virt_to_page(pgd);
-	unsigned long flags;
-
-	spin_lock_irqsave(&pgd_lock, flags);
-	list_del(&page->lru);
-	spin_unlock_irqrestore(&pgd_lock, flags);
-}
-
-static inline pgd_t *pgd_alloc(struct mm_struct *mm)
-{
-	unsigned boundary;
-	pgd_t *pgd = (pgd_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT);
-	if (!pgd)
-		return NULL;
-	pgd_list_add(pgd);
-	/*
-	 * Copy kernel pointers in from init.
-	 * Could keep a freelist or slab cache of those because the kernel
-	 * part never changes.
-	 */
-	boundary = pgd_index(__PAGE_OFFSET);
-	memset(pgd, 0, boundary * sizeof(pgd_t));
-	memcpy(pgd + boundary,
-	       init_level4_pgt + boundary,
-	       (PTRS_PER_PGD - boundary) * sizeof(pgd_t));
-	return pgd;
-}
-
-static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
-{
-	BUG_ON((unsigned long)pgd & (PAGE_SIZE-1));
-	pgd_list_del(pgd);
-	free_page((unsigned long)pgd);
-}
-
-static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
-{
-	return (pte_t *)get_zeroed_page(GFP_KERNEL|__GFP_REPEAT);
-}
-
-static inline pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address)
-{
-	struct page *page;
-	void *p;
-
-	p = (void *)get_zeroed_page(GFP_KERNEL|__GFP_REPEAT);
-	if (!p)
-		return NULL;
-	page = virt_to_page(p);
-	pgtable_page_ctor(page);
-	return page;
-}
-
-/* Should really implement gc for free page table pages. This could be
-   done with a reference count in struct page. */
-
-static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
-{
-	BUG_ON((unsigned long)pte & (PAGE_SIZE-1));
-	free_page((unsigned long)pte); 
-}
-
-static inline void pte_free(struct mm_struct *mm, pgtable_t pte)
-{
-	pgtable_page_dtor(pte);
-	__free_page(pte);
-} 
-
-#define __pte_free_tlb(tlb,pte)				\
-do {							\
-	pgtable_page_dtor((pte));				\
-	tlb_remove_page((tlb), (pte));			\
-} while (0)
-
-#define __pmd_free_tlb(tlb,x)   tlb_remove_page((tlb),virt_to_page(x))
-#define __pud_free_tlb(tlb,x)   tlb_remove_page((tlb),virt_to_page(x))
-
-#endif /* _X86_64_PGALLOC_H */
diff --git a/include/asm-x86/pgtable.h b/include/asm-x86/pgtable.h
index f1d9f4a03f6f..b8a08bd7bd48 100644
--- a/include/asm-x86/pgtable.h
+++ b/include/asm-x86/pgtable.h
@@ -1,7 +1,6 @@
 #ifndef _ASM_X86_PGTABLE_H
 #define _ASM_X86_PGTABLE_H
 
-#define USER_PTRS_PER_PGD	((TASK_SIZE-1)/PGDIR_SIZE+1)
 #define FIRST_USER_ADDRESS	0
 
 #define _PAGE_BIT_PRESENT	0	/* is present */
@@ -330,6 +329,9 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 # include "pgtable_64.h"
 #endif
 
+#define KERNEL_PGD_BOUNDARY	pgd_index(PAGE_OFFSET)
+#define KERNEL_PGD_PTRS		(PTRS_PER_PGD - KERNEL_PGD_BOUNDARY)
+
 #ifndef __ASSEMBLY__
 
 enum {
@@ -389,37 +391,17 @@ static inline void native_set_pte_at(struct mm_struct *mm, unsigned long addr,
  * bit at the same time.
  */
 #define  __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
-#define ptep_set_access_flags(vma, address, ptep, entry, dirty)		\
-({									\
-	int __changed = !pte_same(*(ptep), entry);			\
-	if (__changed && dirty) {					\
-		*ptep = entry;						\
-		pte_update_defer((vma)->vm_mm, (address), (ptep));	\
-		flush_tlb_page(vma, address);				\
-	}								\
-	__changed;							\
-})
+extern int ptep_set_access_flags(struct vm_area_struct *vma,
+				 unsigned long address, pte_t *ptep,
+				 pte_t entry, int dirty);
 
 #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
-#define ptep_test_and_clear_young(vma, addr, ptep) ({			\
-	int __ret = 0;							\
-	if (pte_young(*(ptep)))						\
-		__ret = test_and_clear_bit(_PAGE_BIT_ACCESSED,		\
-					   &(ptep)->pte);		\
-	if (__ret)							\
-		pte_update((vma)->vm_mm, addr, ptep);			\
-	__ret;								\
-})
+extern int ptep_test_and_clear_young(struct vm_area_struct *vma,
+				     unsigned long addr, pte_t *ptep);
 
 #define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
-#define ptep_clear_flush_young(vma, address, ptep)			\
-({									\
-	int __young;							\
-	__young = ptep_test_and_clear_young((vma), (address), (ptep));	\
-	if (__young)							\
-		flush_tlb_page(vma, address);				\
-	__young;							\
-})
+extern int ptep_clear_flush_young(struct vm_area_struct *vma,
+				  unsigned long address, pte_t *ptep);
 
 #define __HAVE_ARCH_PTEP_GET_AND_CLEAR
 static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
@@ -456,6 +438,22 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm,
 	pte_update(mm, addr, ptep);
 }
 
+/*
+ * clone_pgd_range(pgd_t *dst, pgd_t *src, int count);
+ *
+ *  dst - pointer to pgd range anwhere on a pgd page
+ *  src - ""
+ *  count - the number of pgds to copy.
+ *
+ * dst and src can be on the same page, but the range must not overlap,
+ * and must not cross a page boundary.
+ */
+static inline void clone_pgd_range(pgd_t *dst, pgd_t *src, int count)
+{
+       memcpy(dst, src, count * sizeof(pgd_t));
+}
+
+
 #include <asm-generic/pgtable.h>
 #endif	/* __ASSEMBLY__ */
 
diff --git a/include/asm-x86/pgtable_32.h b/include/asm-x86/pgtable_32.h
index c4a643674458..168b6447cf18 100644
--- a/include/asm-x86/pgtable_32.h
+++ b/include/asm-x86/pgtable_32.h
@@ -48,9 +48,6 @@ void paging_init(void);
 #define PGDIR_SIZE	(1UL << PGDIR_SHIFT)
 #define PGDIR_MASK	(~(PGDIR_SIZE - 1))
 
-#define USER_PGD_PTRS (PAGE_OFFSET >> PGDIR_SHIFT)
-#define KERNEL_PGD_PTRS (PTRS_PER_PGD-USER_PGD_PTRS)
-
 /* Just any arbitrary offset to the start of the vmalloc VM area: the
  * current 8MB value just means that there will be a 8MB "hole" after the
  * physical memory until the kernel virtual memory starts.  That means that
@@ -109,21 +106,6 @@ extern int pmd_bad(pmd_t pmd);
 #endif
 
 /*
- * clone_pgd_range(pgd_t *dst, pgd_t *src, int count);
- *
- *  dst - pointer to pgd range anwhere on a pgd page
- *  src - ""
- *  count - the number of pgds to copy.
- *
- * dst and src can be on the same page, but the range must not overlap,
- * and must not cross a page boundary.
- */
-static inline void clone_pgd_range(pgd_t *dst, pgd_t *src, int count)
-{
-       memcpy(dst, src, count * sizeof(pgd_t));
-}
-
-/*
  * Macro to mark a page protection value as "uncacheable".
  * On processors which do not support it, this is a no-op.
  */
diff --git a/include/asm-x86/pgtable_64.h b/include/asm-x86/pgtable_64.h
index 9fd87d0b6477..a3bbf8766c1d 100644
--- a/include/asm-x86/pgtable_64.h
+++ b/include/asm-x86/pgtable_64.h
@@ -24,7 +24,7 @@ extern void paging_init(void);
 
 #endif /* !__ASSEMBLY__ */
 
-#define SHARED_KERNEL_PMD	1
+#define SHARED_KERNEL_PMD	0
 
 /*
  * PGDIR_SHIFT determines what a top-level page table entry can map
diff --git a/include/asm-x86/xen/events.h b/include/asm-x86/xen/events.h
new file mode 100644
index 000000000000..596312a7bfc9
--- /dev/null
+++ b/include/asm-x86/xen/events.h
@@ -0,0 +1,22 @@
+#ifndef __XEN_EVENTS_H
+#define __XEN_EVENTS_H
+
+enum ipi_vector {
+	XEN_RESCHEDULE_VECTOR,
+	XEN_CALL_FUNCTION_VECTOR,
+
+	XEN_NR_IPIS,
+};
+
+static inline int xen_irqs_disabled(struct pt_regs *regs)
+{
+	return raw_irqs_disabled_flags(regs->flags);
+}
+
+static inline void xen_do_IRQ(int irq, struct pt_regs *regs)
+{
+	regs->orig_ax = ~irq;
+	do_IRQ(regs);
+}
+
+#endif /* __XEN_EVENTS_H */
diff --git a/include/asm-x86/xen/grant_table.h b/include/asm-x86/xen/grant_table.h
new file mode 100644
index 000000000000..2444d4593a3b
--- /dev/null
+++ b/include/asm-x86/xen/grant_table.h
@@ -0,0 +1,7 @@
+#ifndef __XEN_GRANT_TABLE_H
+#define __XEN_GRANT_TABLE_H
+
+#define xen_alloc_vm_area(size)	alloc_vm_area(size)
+#define xen_free_vm_area(area)	free_vm_area(area)
+
+#endif /* __XEN_GRANT_TABLE_H */
diff --git a/include/asm-x86/xen/hypercall.h b/include/asm-x86/xen/hypercall.h
index bc0ee7d961ca..c2ccd997ed35 100644
--- a/include/asm-x86/xen/hypercall.h
+++ b/include/asm-x86/xen/hypercall.h
@@ -164,6 +164,12 @@ HYPERVISOR_set_callbacks(unsigned long event_selector,
 }
 
 static inline int
+HYPERVISOR_callback_op(int cmd, void *arg)
+{
+	return _hypercall2(int, callback_op, cmd, arg);
+}
+
+static inline int
 HYPERVISOR_fpu_taskswitch(int set)
 {
 	return _hypercall1(int, fpu_taskswitch, set);
diff --git a/include/asm-x86/xen/interface.h b/include/asm-x86/xen/interface.h
index 165c3968e138..6227000a1e84 100644
--- a/include/asm-x86/xen/interface.h
+++ b/include/asm-x86/xen/interface.h
@@ -22,6 +22,30 @@
 #define DEFINE_GUEST_HANDLE(name) __DEFINE_GUEST_HANDLE(name, name)
 #define GUEST_HANDLE(name)        __guest_handle_ ## name
 
+#ifdef __XEN__
+#if defined(__i386__)
+#define set_xen_guest_handle(hnd, val)			\
+	do {						\
+		if (sizeof(hnd) == 8)			\
+			*(uint64_t *)&(hnd) = 0;	\
+		(hnd).p = val;				\
+	} while (0)
+#elif defined(__x86_64__)
+#define set_xen_guest_handle(hnd, val)	do { (hnd).p = val; } while (0)
+#endif
+#else
+#if defined(__i386__)
+#define set_xen_guest_handle(hnd, val)			\
+	do {						\
+		if (sizeof(hnd) == 8)			\
+			*(uint64_t *)&(hnd) = 0;	\
+		(hnd) = val;				\
+	} while (0)
+#elif defined(__x86_64__)
+#define set_xen_guest_handle(hnd, val)	do { (hnd) = val; } while (0)
+#endif
+#endif
+
 #ifndef __ASSEMBLY__
 /* Guest handles for primitive C types. */
 __DEFINE_GUEST_HANDLE(uchar, unsigned char);
@@ -171,6 +195,10 @@ struct arch_vcpu_info {
     unsigned long pad[5]; /* sizeof(struct vcpu_info) == 64 */
 };
 
+struct xen_callback {
+	unsigned long cs;
+	unsigned long eip;
+};
 #endif /* !__ASSEMBLY__ */
 
 /*
diff --git a/include/asm-x86/xen/page.h b/include/asm-x86/xen/page.h
new file mode 100644
index 000000000000..01799305f02a
--- /dev/null
+++ b/include/asm-x86/xen/page.h
@@ -0,0 +1,168 @@
+#ifndef __XEN_PAGE_H
+#define __XEN_PAGE_H
+
+#include <linux/pfn.h>
+
+#include <asm/uaccess.h>
+#include <asm/pgtable.h>
+
+#include <xen/features.h>
+
+/* Xen machine address */
+typedef struct xmaddr {
+	phys_addr_t maddr;
+} xmaddr_t;
+
+/* Xen pseudo-physical address */
+typedef struct xpaddr {
+	phys_addr_t paddr;
+} xpaddr_t;
+
+#define XMADDR(x)	((xmaddr_t) { .maddr = (x) })
+#define XPADDR(x)	((xpaddr_t) { .paddr = (x) })
+
+/**** MACHINE <-> PHYSICAL CONVERSION MACROS ****/
+#define INVALID_P2M_ENTRY	(~0UL)
+#define FOREIGN_FRAME_BIT	(1UL<<31)
+#define FOREIGN_FRAME(m)	((m) | FOREIGN_FRAME_BIT)
+
+extern unsigned long *phys_to_machine_mapping;
+
+static inline unsigned long pfn_to_mfn(unsigned long pfn)
+{
+	if (xen_feature(XENFEAT_auto_translated_physmap))
+		return pfn;
+
+	return phys_to_machine_mapping[(unsigned int)(pfn)] &
+		~FOREIGN_FRAME_BIT;
+}
+
+static inline int phys_to_machine_mapping_valid(unsigned long pfn)
+{
+	if (xen_feature(XENFEAT_auto_translated_physmap))
+		return 1;
+
+	return (phys_to_machine_mapping[pfn] != INVALID_P2M_ENTRY);
+}
+
+static inline unsigned long mfn_to_pfn(unsigned long mfn)
+{
+	unsigned long pfn;
+
+	if (xen_feature(XENFEAT_auto_translated_physmap))
+		return mfn;
+
+#if 0
+	if (unlikely((mfn >> machine_to_phys_order) != 0))
+		return max_mapnr;
+#endif
+
+	pfn = 0;
+	/*
+	 * The array access can fail (e.g., device space beyond end of RAM).
+	 * In such cases it doesn't matter what we return (we return garbage),
+	 * but we must handle the fault without crashing!
+	 */
+	__get_user(pfn, &machine_to_phys_mapping[mfn]);
+
+	return pfn;
+}
+
+static inline xmaddr_t phys_to_machine(xpaddr_t phys)
+{
+	unsigned offset = phys.paddr & ~PAGE_MASK;
+	return XMADDR(PFN_PHYS((u64)pfn_to_mfn(PFN_DOWN(phys.paddr))) | offset);
+}
+
+static inline xpaddr_t machine_to_phys(xmaddr_t machine)
+{
+	unsigned offset = machine.maddr & ~PAGE_MASK;
+	return XPADDR(PFN_PHYS((u64)mfn_to_pfn(PFN_DOWN(machine.maddr))) | offset);
+}
+
+/*
+ * We detect special mappings in one of two ways:
+ *  1. If the MFN is an I/O page then Xen will set the m2p entry
+ *     to be outside our maximum possible pseudophys range.
+ *  2. If the MFN belongs to a different domain then we will certainly
+ *     not have MFN in our p2m table. Conversely, if the page is ours,
+ *     then we'll have p2m(m2p(MFN))==MFN.
+ * If we detect a special mapping then it doesn't have a 'struct page'.
+ * We force !pfn_valid() by returning an out-of-range pointer.
+ *
+ * NB. These checks require that, for any MFN that is not in our reservation,
+ * there is no PFN such that p2m(PFN) == MFN. Otherwise we can get confused if
+ * we are foreign-mapping the MFN, and the other domain as m2p(MFN) == PFN.
+ * Yikes! Various places must poke in INVALID_P2M_ENTRY for safety.
+ *
+ * NB2. When deliberately mapping foreign pages into the p2m table, you *must*
+ *      use FOREIGN_FRAME(). This will cause pte_pfn() to choke on it, as we
+ *      require. In all the cases we care about, the FOREIGN_FRAME bit is
+ *      masked (e.g., pfn_to_mfn()) so behaviour there is correct.
+ */
+static inline unsigned long mfn_to_local_pfn(unsigned long mfn)
+{
+	extern unsigned long max_mapnr;
+	unsigned long pfn = mfn_to_pfn(mfn);
+	if ((pfn < max_mapnr)
+	    && !xen_feature(XENFEAT_auto_translated_physmap)
+	    && (phys_to_machine_mapping[pfn] != mfn))
+		return max_mapnr; /* force !pfn_valid() */
+	return pfn;
+}
+
+static inline void set_phys_to_machine(unsigned long pfn, unsigned long mfn)
+{
+	if (xen_feature(XENFEAT_auto_translated_physmap)) {
+		BUG_ON(pfn != mfn && mfn != INVALID_P2M_ENTRY);
+		return;
+	}
+	phys_to_machine_mapping[pfn] = mfn;
+}
+
+/* VIRT <-> MACHINE conversion */
+#define virt_to_machine(v)	(phys_to_machine(XPADDR(__pa(v))))
+#define virt_to_mfn(v)		(pfn_to_mfn(PFN_DOWN(__pa(v))))
+#define mfn_to_virt(m)		(__va(mfn_to_pfn(m) << PAGE_SHIFT))
+
+static inline unsigned long pte_mfn(pte_t pte)
+{
+	return (pte.pte & ~_PAGE_NX) >> PAGE_SHIFT;
+}
+
+static inline pte_t mfn_pte(unsigned long page_nr, pgprot_t pgprot)
+{
+	pte_t pte;
+
+	pte.pte = ((phys_addr_t)page_nr << PAGE_SHIFT) |
+		(pgprot_val(pgprot) & __supported_pte_mask);
+
+	return pte;
+}
+
+static inline pteval_t pte_val_ma(pte_t pte)
+{
+	return pte.pte;
+}
+
+static inline pte_t __pte_ma(pteval_t x)
+{
+	return (pte_t) { .pte = x };
+}
+
+#ifdef CONFIG_X86_PAE
+#define pmd_val_ma(v) ((v).pmd)
+#define pud_val_ma(v) ((v).pgd.pgd)
+#define __pmd_ma(x)	((pmd_t) { (x) } )
+#else  /* !X86_PAE */
+#define pmd_val_ma(v)	((v).pud.pgd.pgd)
+#endif	/* CONFIG_X86_PAE */
+
+#define pgd_val_ma(x)	((x).pgd)
+
+
+xmaddr_t arbitrary_virt_to_machine(unsigned long address);
+void make_lowmem_page_readonly(void *vaddr);
+void make_lowmem_page_readwrite(void *vaddr);
+
+#endif /* __XEN_PAGE_H */