10 files changed, 1408 insertions, 371 deletions

diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index 8760cc60a21c..f25bdf238a33 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/arch/x86/include/asm/xen/page.h
@@ -42,6 +42,11 @@ extern unsigned int   machine_to_phys_order;
 extern unsigned long get_phys_to_machine(unsigned long pfn);
 extern bool set_phys_to_machine(unsigned long pfn, unsigned long mfn);
 
+extern int m2p_add_override(unsigned long mfn, struct page *page);
+extern int m2p_remove_override(struct page *page);
+extern struct page *m2p_find_override(unsigned long mfn);
+extern unsigned long m2p_find_override_pfn(unsigned long mfn, unsigned long pfn);
+
 static inline unsigned long pfn_to_mfn(unsigned long pfn)
 {
         unsigned long mfn;
@@ -72,9 +77,6 @@ static inline unsigned long mfn_to_pfn(unsigned long mfn)
         if (xen_feature(XENFEAT_auto_translated_physmap))
                 return mfn;
 
-        if (unlikely((mfn >> machine_to_phys_order) != 0))
-                return ~0;
-
         pfn = 0;
         /*
          * The array access can fail (e.g., device space beyond end of RAM).
@@ -83,6 +85,14 @@ static inline unsigned long mfn_to_pfn(unsigned long mfn)
          */
         __get_user(pfn, &machine_to_phys_mapping[mfn]);
 
+        /*
+         * If this appears to be a foreign mfn (because the pfn
+         * doesn't map back to the mfn), then check the local override
+         * table to see if there's a better pfn to use.
+         */
+        if (get_phys_to_machine(pfn) != mfn)
+                pfn = m2p_find_override_pfn(mfn, pfn);
+
         return pfn;
 }
 
diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile
index 779385158915..17c565de3d64 100644
--- a/arch/x86/xen/Makefile
+++ b/arch/x86/xen/Makefile
@@ -12,7 +12,8 @@ CFLAGS_mmu.o			:= $(nostackp)
 
 obj-y           := enlighten.o setup.o multicalls.o mmu.o irq.o \
                         time.o xen-asm.o xen-asm_$(BITS).o \
-                        grant-table.o suspend.o platform-pci-unplug.o
+                        grant-table.o suspend.o platform-pci-unplug.o \
+                        p2m.o
 
 obj-$(CONFIG_SMP)               += smp.o
 obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= spinlock.o
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 44924e551fde..7575e55cd52e 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -173,371 +173,6 @@ DEFINE_PER_CPU(unsigned long, xen_current_cr3);	 /* actual vcpu cr3 */
  */
 #define USER_LIMIT      ((STACK_TOP_MAX + PGDIR_SIZE - 1) & PGDIR_MASK)
 
-/*
- * Xen leaves the responsibility for maintaining p2m mappings to the
- * guests themselves, but it must also access and update the p2m array
- * during suspend/resume when all the pages are reallocated.
- *
- * The p2m table is logically a flat array, but we implement it as a
- * three-level tree to allow the address space to be sparse.
- *
- *                               Xen
- *                                |
- *     p2m_top              p2m_top_mfn
- *       /  \                   /   \
- * p2m_mid p2m_mid      p2m_mid_mfn p2m_mid_mfn
- *    / \      / \         /           /
- *  p2m p2m p2m p2m p2m p2m p2m ...
- *
- * The p2m_mid_mfn pages are mapped by p2m_top_mfn_p.
- *
- * The p2m_top and p2m_top_mfn levels are limited to 1 page, so the
- * maximum representable pseudo-physical address space is:
- *  P2M_TOP_PER_PAGE * P2M_MID_PER_PAGE * P2M_PER_PAGE pages
- *
- * P2M_PER_PAGE depends on the architecture, as a mfn is always
- * unsigned long (8 bytes on 64-bit, 4 bytes on 32), leading to
- * 512 and 1024 entries respectively. 
- */
-
-unsigned long xen_max_p2m_pfn __read_mostly;
-
-#define P2M_PER_PAGE            (PAGE_SIZE / sizeof(unsigned long))
-#define P2M_MID_PER_PAGE        (PAGE_SIZE / sizeof(unsigned long *))
-#define P2M_TOP_PER_PAGE        (PAGE_SIZE / sizeof(unsigned long **))
-
-#define MAX_P2M_PFN             (P2M_TOP_PER_PAGE * P2M_MID_PER_PAGE * P2M_PER_PAGE)
-
-/* Placeholders for holes in the address space */
-static RESERVE_BRK_ARRAY(unsigned long, p2m_missing, P2M_PER_PAGE);
-static RESERVE_BRK_ARRAY(unsigned long *, p2m_mid_missing, P2M_MID_PER_PAGE);
-static RESERVE_BRK_ARRAY(unsigned long, p2m_mid_missing_mfn, P2M_MID_PER_PAGE);
-
-static RESERVE_BRK_ARRAY(unsigned long **, p2m_top, P2M_TOP_PER_PAGE);
-static RESERVE_BRK_ARRAY(unsigned long, p2m_top_mfn, P2M_TOP_PER_PAGE);
-static RESERVE_BRK_ARRAY(unsigned long *, p2m_top_mfn_p, P2M_TOP_PER_PAGE);
-
-RESERVE_BRK(p2m_mid, PAGE_SIZE * (MAX_DOMAIN_PAGES / (P2M_PER_PAGE * P2M_MID_PER_PAGE)));
-RESERVE_BRK(p2m_mid_mfn, PAGE_SIZE * (MAX_DOMAIN_PAGES / (P2M_PER_PAGE * P2M_MID_PER_PAGE)));
-
-static inline unsigned p2m_top_index(unsigned long pfn)
-{
-        BUG_ON(pfn >= MAX_P2M_PFN);
-        return pfn / (P2M_MID_PER_PAGE * P2M_PER_PAGE);
-}
-
-static inline unsigned p2m_mid_index(unsigned long pfn)
-{
-        return (pfn / P2M_PER_PAGE) % P2M_MID_PER_PAGE;
-}
-
-static inline unsigned p2m_index(unsigned long pfn)
-{
-        return pfn % P2M_PER_PAGE;
-}
-
-static void p2m_top_init(unsigned long ***top)
-{
-        unsigned i;
-
-        for (i = 0; i < P2M_TOP_PER_PAGE; i++)
-                top[i] = p2m_mid_missing;
-}
-
-static void p2m_top_mfn_init(unsigned long *top)
-{
-        unsigned i;
-
-        for (i = 0; i < P2M_TOP_PER_PAGE; i++)
-                top[i] = virt_to_mfn(p2m_mid_missing_mfn);
-}
-
-static void p2m_top_mfn_p_init(unsigned long **top)
-{
-        unsigned i;
-
-        for (i = 0; i < P2M_TOP_PER_PAGE; i++)
-                top[i] = p2m_mid_missing_mfn;
-}
-
-static void p2m_mid_init(unsigned long **mid)
-{
-        unsigned i;
-
-        for (i = 0; i < P2M_MID_PER_PAGE; i++)
-                mid[i] = p2m_missing;
-}
-
-static void p2m_mid_mfn_init(unsigned long *mid)
-{
-        unsigned i;
-
-        for (i = 0; i < P2M_MID_PER_PAGE; i++)
-                mid[i] = virt_to_mfn(p2m_missing);
-}
-
-static void p2m_init(unsigned long *p2m)
-{
-        unsigned i;
-
-        for (i = 0; i < P2M_MID_PER_PAGE; i++)
-                p2m[i] = INVALID_P2M_ENTRY;
-}
-
-/*
- * Build the parallel p2m_top_mfn and p2m_mid_mfn structures
- *
- * This is called both at boot time, and after resuming from suspend:
- * - At boot time we're called very early, and must use extend_brk()
- *   to allocate memory.
- *
- * - After resume we're called from within stop_machine, but the mfn
- *   tree should alreay be completely allocated.
- */
-void xen_build_mfn_list_list(void)
-{
-        unsigned long pfn;
-
-        /* Pre-initialize p2m_top_mfn to be completely missing */