Merge commit 'v2.6.28-rc2' into x86/pci-ioapic-boot-irq-quirks

22 files changed, 1584 insertions, 761 deletions

diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 9873716e9f7..59f89b434b4 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -1,5 +1,5 @@
 obj-y	:=  init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \
-	    pat.o pgtable.o
+	    pat.o pgtable.o gup.o
 
 obj-$(CONFIG_X86_32)		+= pgtable_32.o
 
@@ -13,11 +13,8 @@ obj-$(CONFIG_MMIOTRACE)		+= mmiotrace.o
 mmiotrace-y			:= pf_in.o mmio-mod.o
 obj-$(CONFIG_MMIOTRACE_TEST)	+= testmmiotrace.o
 
-ifeq ($(CONFIG_X86_32),y)
-obj-$(CONFIG_NUMA)		+= discontig_32.o
-else
-obj-$(CONFIG_NUMA)		+= numa_64.o
+obj-$(CONFIG_NUMA)		+= numa_$(BITS).o
 obj-$(CONFIG_K8_NUMA)		+= k8topology_64.o
-endif
 obj-$(CONFIG_ACPI_NUMA)		+= srat_$(BITS).o
 
+obj-$(CONFIG_MEMTEST)		+= memtest.o
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index 0bb0caed897..e7277cbcfb4 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -148,8 +148,8 @@ static void note_page(struct seq_file *m, struct pg_state *st,
 	 * we have now. "break" is either changing perms, levels or
 	 * address space marker.
 	 */
-	prot = pgprot_val(new_prot) & ~(PTE_MASK);
-	cur = pgprot_val(st->current_prot) & ~(PTE_MASK);
+	prot = pgprot_val(new_prot) & PTE_FLAGS_MASK;
+	cur = pgprot_val(st->current_prot) & PTE_FLAGS_MASK;
 
 	if (!st->level) {
 		/* First entry */
@@ -221,7 +221,7 @@ static void walk_pmd_level(struct seq_file *m, struct pg_state *st, pud_t addr,
 	for (i = 0; i < PTRS_PER_PMD; i++) {
 		st->current_address = normalize_addr(P + i * PMD_LEVEL_MULT);
 		if (!pmd_none(*start)) {
-			pgprotval_t prot = pmd_val(*start) & ~PTE_MASK;
+			pgprotval_t prot = pmd_val(*start) & PTE_FLAGS_MASK;
 
 			if (pmd_large(*start) || !pmd_present(*start))
 				note_page(m, st, __pgprot(prot), 3);
@@ -253,7 +253,7 @@ static void walk_pud_level(struct seq_file *m, struct pg_state *st, pgd_t addr,
 	for (i = 0; i < PTRS_PER_PUD; i++) {
 		st->current_address = normalize_addr(P + i * PUD_LEVEL_MULT);
 		if (!pud_none(*start)) {
-			pgprotval_t prot = pud_val(*start) & ~PTE_MASK;
+			pgprotval_t prot = pud_val(*start) & PTE_FLAGS_MASK;
 
 			if (pud_large(*start) || !pud_present(*start))
 				note_page(m, st, __pgprot(prot), 2);
@@ -288,7 +288,7 @@ static void walk_pgd_level(struct seq_file *m)
 	for (i = 0; i < PTRS_PER_PGD; i++) {
 		st.current_address = normalize_addr(i * PGD_LEVEL_MULT);
 		if (!pgd_none(*start)) {
-			pgprotval_t prot = pgd_val(*start) & ~PTE_MASK;
+			pgprotval_t prot = pgd_val(*start) & PTE_FLAGS_MASK;
 
 			if (pgd_large(*start) || !pgd_present(*start))
 				note_page(m, &st, __pgprot(prot), 1);
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 455f3fe67b4..31e8730fa24 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -35,6 +35,7 @@
 #include <asm/tlbflush.h>
 #include <asm/proto.h>
 #include <asm-generic/sections.h>
+#include <asm/traps.h>
 
 /*
  * Page fault error code bits
@@ -357,8 +358,6 @@ static int is_errata100(struct pt_regs *regs, unsigned long address)
 	return 0;
 }
 
-void do_invalid_op(struct pt_regs *, unsigned long);
-
 static int is_f00f_bug(struct pt_regs *regs, unsigned long address)
 {
 #ifdef CONFIG_X86_F00F_BUG
@@ -593,11 +592,6 @@ void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code)
 	unsigned long flags;
 #endif
 
-	/*
-	 * We can fault from pretty much anywhere, with unknown IRQ state.
-	 */
-	trace_hardirqs_fixup();
-
 	tsk = current;
 	mm = tsk->mm;
 	prefetchw(&mm->mmap_sem);
@@ -646,24 +640,23 @@ void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code)
 	}
 
 
-#ifdef CONFIG_X86_32
-	/* It's safe to allow irq's after cr2 has been saved and the vmalloc
-	   fault has been handled. */
-	if (regs->flags & (X86_EFLAGS_IF | X86_VM_MASK))
-		local_irq_enable();
-
 	/*
-	 * If we're in an interrupt, have no user context or are running in an
-	 * atomic region then we must not take the fault.
+	 * It's safe to allow irq's after cr2 has been saved and the
+	 * vmalloc fault has been handled.
+	 *
+	 * User-mode registers count as a user access even for any
+	 * potential system fault or CPU buglet.
 	 */
-	if (in_atomic() || !mm)
-		goto bad_area_nosemaphore;
-#else /* CONFIG_X86_64 */
-	if (likely(regs->flags & X86_EFLAGS_IF))
+	if (user_mode_vm(regs)) {
+		local_irq_enable();
+		error_code |= PF_USER;
+	} else if (regs->flags & X86_EFLAGS_IF)
 		local_irq_enable();
 
+#ifdef CONFIG_X86_64
 	if (unlikely(error_code & PF_RSVD))
 		pgtable_bad(address, regs, error_code);
+#endif
 
 	/*
 	 * If we're in an interrupt, have no user context or are running in an
@@ -672,15 +665,9 @@ void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code)
 	if (unlikely(in_atomic() || !mm))
 		goto bad_area_nosemaphore;
 
-	/*
-	 * User-mode registers count as a user access even for any
-	 * potential system fault or CPU buglet.
-	 */
-	if (user_mode_vm(regs))
-		error_code |= PF_USER;
 again:
-#endif
-	/* When running in the kernel we expect faults to occur only to
+	/*
+	 * When running in the kernel we expect faults to occur only to
 	 * addresses in user space.  All other faults represent errors in the
 	 * kernel and should generate an OOPS.  Unfortunately, in the case of an
 	 * erroneous fault occurring in a code path which already holds mmap_sem
@@ -743,9 +730,6 @@ good_area:
 			goto bad_area;
 	}
 
-#ifdef CONFIG_X86_32
-survive:
-#endif
 	/*
 	 * If for any reason at all we couldn't handle the fault,
 	 * make sure we exit gracefully rather than endlessly redo
@@ -880,12 +864,11 @@ out_of_memory:
 	up_read(&mm->mmap_sem);
 	if (is_global_init(tsk)) {
 		yield();
-#ifdef CONFIG_X86_32
-		down_read(&mm->mmap_sem);
-		goto survive;
-#else
+		/*
+		 * Re-lookup the vma - in theory the vma tree might
+		 * have changed:
+		 */
 		goto again;
-#endif
 	}
 
 	printk("VM: killing process %s\n", tsk->comm);
@@ -915,15 +898,15 @@ LIST_HEAD(pgd_list);
 
 void vmalloc_sync_all(void)
 {
-#ifdef CONFIG_X86_32
-	unsigned long start = VMALLOC_START & PGDIR_MASK;
 	unsigned long address;
 
+#ifdef CONFIG_X86_32
 	if (SHARED_KERNEL_PMD)
 		return;
 
-	BUILD_BUG_ON(TASK_SIZE & ~PGDIR_MASK);
-	for (address = start; address >= TASK_SIZE; address += PGDIR_SIZE) {
+	for (address = VMALLOC_START & PMD_MASK;
+	     address >= TASK_SIZE && address < FIXADDR_TOP;
+	     address += PMD_SIZE) {
 		unsigned long flags;
 		struct page *page;
 
@@ -936,10 +919,8 @@ void vmalloc_sync_all(void)
 		spin_unlock_irqrestore(&pgd_lock, flags);
 	}
 #else /* CONFIG_X86_64 */
-	unsigned long start = VMALLOC_START & PGDIR_MASK;
-	unsigned long address;
-
-	for (address = start; address <= VMALLOC_END; address += PGDIR_SIZE) {
+	for (address = VMALLOC_START & PGDIR_MASK; address <= VMALLOC_END;
+	     address += PGDIR_SIZE) {
 		const pgd_t *pgd_ref = pgd_offset_k(address);
 		unsigned long flags;
 		struct page *page;
diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c
new file mode 100644
index 00000000000..4ba373c5b8c
--- /dev/null
+++ b/arch/x86/mm/gup.c
@@ -0,0 +1,298 @@
+/*
+ * Lockless get_user_pages_fast for x86
+ *
+ * Copyright (C) 2008 Nick Piggin
+ * Copyright (C) 2008 Novell Inc.
+ */
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/vmstat.h>
+#include <linux/highmem.h>
+
+#include <asm/pgtable.h>
+
+static inline pte_t gup_get_pte(pte_t *ptep)
+{
+#ifndef CONFIG_X86_PAE
+	return *ptep;
+#else
+	/*
+	 * With get_user_pages_fast, we walk down the pagetables without taking
+	 * any locks.  For this we would like to load the pointers atoimcally,
+	 * but that is not possible (without expensive cmpxchg8b) on PAE.  What
+	 * we do have is the guarantee that a pte will only either go from not
+	 * present to present, or present to not present or both -- it will not
+	 * switch to a completely different present page without a TLB flush in
+	 * between; something that we are blocking by holding interrupts off.
+	 *
+	 * Setting ptes from not present to present goes:
+	 * ptep->pte_high = h;
+	 * smp_wmb();
+	 * ptep->pte_low = l;
+	 *
+	 * And present to not present goes:
+	 * ptep->pte_low = 0;
+	 * smp_wmb();
+	 * ptep->pte_high = 0;
+	 *
+	 * We must ensure here that the load of pte_low sees l iff pte_high
+	 * sees h. We load pte_high *after* loading pte_low, which ensures we
+	 * don't see an older value of pte_high.  *Then* we recheck pte_low,
+	 * which ensures that we haven't picked up a changed pte high. We might
+	 * have got rubbish values from pte_low and pte_high, but we are
+	 * guaranteed that pte_low will not have the present bit set *unless*
+	 * it is 'l'. And get_user_pages_fast only operates on present ptes, so
+	 * we're safe.
+	 *
+	 * gup_get_pte should not be used or copied outside gup.c without being
+	 * very careful -- it does not atomically load the pte or anything that
+	 * is likely to be useful for you.
+	 */
+	pte_t pte;
+
+retry:
+	pte.pte_low = ptep->pte_low;
+	smp_rmb();
+	pte.pte_high = ptep->pte_high;
+	smp_rmb();
+	if (unlikely(pte.pte_low != ptep->pte_low))
+		goto retry;
+
+	return pte;
+#endif
+}
+
+/*
+ * The performance critical leaf functions are made noinline otherwise gcc
+ * inlines everything into a single function which results in too much
+ * register pressure.
+ */
+static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
+		unsigned long end, int write, struct page **pages, int *nr)
+{
+	unsigned long mask;
+	pte_t *ptep;
+
+	mask = _PAGE_PRESENT|_PAGE_USER;
+	if (write)
+		mask |= _PAGE_RW;
+
+	ptep = pte_offset_map(&pmd, addr);
+	do {
+		pte_t pte = gup_get_pte(ptep);
+		struct page *page;
+
+		if ((pte_flags(pte) & (mask | _PAGE_SPECIAL)) != mask) {
+			pte_unmap(ptep);
+			return 0;
+		}
+		VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
+		page = pte_page(pte);
+		get_page(page);
+		pages[*nr] = page;
+		(*nr)++;
+
+	} while (ptep++, addr += PAGE_SIZE, addr != end);
+	pte_unmap(ptep - 1);
+
+	return 1;
+}
+
+static inline void get_head_page_multiple(struct page *page, int nr)
+{
+	VM_BUG_ON(page != compound_head(page));
+	VM_BUG_ON(page_count(page) == 0);
+	atomic_add(nr, &page->_count);
+}
+
+static noinline int gup_huge_pmd(pmd_t pmd, unsigned long addr,
+		unsigned long end, int write, struct page **pages, int *nr)
+{
+	unsigned long mask;
+	pte_t pte = *(pte_t *)&pmd;
+	struct page *head, *page;
+	int refs;
+
+	mask = _PAGE_PRESENT|_PAGE_USER;
+	if (write)
+		mask |= _PAGE_RW;
+	if ((pte_flags(pte) & mask) != mask)
+		return 0;
+	/* hugepages are never "special" */
+	VM_BUG_ON(pte_flags(pte) & _PAGE_SPECIAL);
+	VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
+
+	refs = 0;
+	head = pte_page(pte);
+	page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
+	do {
+		VM_BUG_ON(compound_head(page) != head);
+		pages[*nr] = page;
+		(*nr)++;
+		page++;
+		refs++;
+	} while (addr += PAGE_SIZE, addr != end);
+	get_head_page_multiple(head, refs);
+
+	return 1;
+}
+
+static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
+		int write, struct page **pages, int *nr)
+{
+	unsigned long next;
+	pmd_t *pmdp;
+
+	pmdp = pmd_offset(&pud, addr);
+	do {
+		pmd_t pmd = *pmdp;
+
+		next = pmd_addr_end(addr, end);
+		if (pmd_none(pmd))
+			return 0;
+		if (unlikely(pmd_large(pmd))) {
+			if (!gup_huge_pmd(pmd, addr, next, write, pages, nr))
+				return 0;
+		} else {
+			if (!gup_pte_range(pmd, addr, next, write, pages, nr))
+				return 0;
+		}
+	} while (pmdp++, addr = next, addr != end);
+
+	return 1;
+}
+
+static noinline int gup_huge_pud(pud_t pud, unsigned long addr,
+		unsigned long end, int write, struct page **pages, int *nr)
+{
+	unsigned long mask;
+	pte_t pte = *(pte_t *)&pud;
+	struct page *head, *page;
+	int refs;
+
+	mask = _PAGE_PRESENT|_PAGE_USER;
+	if (write)
+		mask |= _PAGE_RW;
+	if ((pte_flags(pte) & mask) != mask)
+		return 0;
+	/* hugepages are never "special" */
+	VM_BUG_ON(pte_flags(pte) & _PAGE_SPECIAL);
+	VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
+
+	refs = 0;
+	head = pte_page(pte);
+	page = head + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
+	do {
+		VM_BUG_ON(compound_head(page) != head);
+		pages[*nr] = page;
+		(*nr)++;
+		page++;
+		refs++;
+	} while (addr += PAGE_SIZE, addr != end);
+	get_head_page_multiple(head, refs);
+
+	return 1;
+}
+
+static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end,
+			int write, struct page **pages, int *nr)
+{
+	unsigned long next;
+	pud_t *pudp;
+
+	pudp = pud_offset(&pgd, addr);
+	do {
+		pud_t pud = *pudp;
+
+		next = pud_addr_end(addr, end);
+		if (pud_none(pud))
+			return 0;
+		if (unlikely(pud_large(pud))) {
+			if (!gup_huge_pud(pud, addr, next, write, pages, nr))
+				return 0;
+		} else {
+			if (!gup_pmd_range(pud, addr, next, write, pages, nr))
+				return 0;
+		}
+	} while (pudp++, addr = next, addr != end);
+
+	return 1;
+}
+
+int get_user_pages_fast(unsigned long start, int nr_pages, int write,
+			struct page **pages)
+{
+	struct mm_struct *mm = current->mm;
+	unsigned long addr, len, end;
+	unsigned long next;
+	pgd_t *pgdp;
+	int nr = 0;
+
+	start &= PAGE_MASK;
+	addr = start;
+	len = (unsigned long) nr_pages << PAGE_SHIFT;
+	end = start + len;
+	if (unlikely(!access_ok(write ? VERIFY_WRITE : VERIFY_READ,
+					start, len)))
+		goto slow_irqon;
+
+	/*
+	 * XXX: batch / limit 'nr', to avoid large irq off latency
+	 * needs some instrumenting to determine the common sizes used by
+	 * important workloads (eg. DB2), and whether limiting the batch size
+	 * will decrease performance.
+	 *
+	 * It seems like we're in the clear for the moment. Direct-IO is
+	 * the main guy that batches up lots of get_user_pages, and even
+	 * they are limited to 64-at-a-time which is not so many.
+	 */
+	/*
+	 * This doesn't prevent pagetable teardown, but does prevent
+	 * the pagetables and pages from being freed on x86.
+	 *
+	 * So long as we atomically load page table pointers versus teardown
+	 * (which we do on x86, with the above PAE exception), we can follow the
+	 * address down to the the page and take a ref on it.
+	 */
+	local_irq_disable();
+	pgdp = pgd_offset(mm, addr);
+	do {
+		pgd_t pgd = *pgdp;
+
+		next = pgd_addr_end(addr, end);
+		if (pgd_none(pgd))
+			goto slow;
+		if (!gup_pud_range(pgd, addr, next, write, pages, &nr))
+			goto slow;
+	} while (pgdp++, addr = next, addr != end);
+	local_irq_enable();
+
+	VM_BUG_ON(nr != (end - start) >> PAGE_SHIFT);
+	return nr;
+
+	{
+		int ret;
+
+slow:
+		local_irq_enable();
+slow_irqon:
+		/* Try to get the remaining pages with get_user_pages */
+		start += nr << PAGE_SHIFT;
+		pages += nr;
+
+		down_read(&mm->mmap_sem);
+		ret = get_user_pages(current, mm, start,
+			(end - start) >> PAGE_SHIFT, write, 0, pages, NULL);
+		up_read(&mm->mmap_sem);
+
+		/* Have to be a bit careful with return values */
+		if (nr > 0) {
+			if (ret < 0)
+				ret = nr;
+			else
+				ret += nr;
+		}
+
+		return ret;
+	}
+}
diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c
index 165c871ba9a..bcc079c282d 100644
--- a/arch/x86/mm/highmem_32.c
+++ b/arch/x86/mm/highmem_32.c
@@ -137,6 +137,7 @@ void *kmap_atomic_pfn(unsigned long pfn, enum km_type type)
 
 	return (void*) vaddr;
 }
+EXPORT_SYMBOL_GPL(kmap_atomic_pfn); /* temporarily in use by i915 GEM until vmap */
 
 struct page *kmap_atomic_to_page(void *ptr)
 {
diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index 0b3d567e686..8f307d914c2 100644
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -124,7 +124,8 @@ int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
 	return 1;
 }
 
-pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr)
+pte_t *huge_pte_alloc(struct mm_struct *mm,
+			unsigned long addr, unsigned long sz)
 {
 	pgd_t *pgd;
 	pud_t *pud;
@@ -133,9 +134,14 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr)
 	pgd = pgd_offset(mm, addr);
 	pud = pud_alloc(mm, pgd, addr);
 	if (pud) {
-		if (pud_none(*pud))
-			huge_pmd_share(mm, addr, pud);
-		pte = (pte_t *) pmd_alloc(mm, pud, addr);
+		if (sz == PUD_SIZE) {
+			pte = (pte_t *)pud;
+		} else {
+			BUG_ON(sz != PMD_SIZE);
+			if (pud_none(*pud))
+				huge_pmd_share(mm, addr, pud);
+			pte = (pte_t *) pmd_alloc(mm, pud, addr);
+		}
 	}
 	BUG_ON(pte && !pte_none(*pte) && !pte_huge(*pte));
 
@@ -151,8 +157,11 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
 	pgd = pgd_offset(mm, addr);
 	if (pgd_present(*pgd)) {
 		pud = pud_offset(pgd, addr);
-		if (pud_present(*pud))
+		if (pud_present(*pud)) {
+			if (pud_large(*pud))
+				return (pte_t *)pud;
 			pmd = pmd_offset(pud, addr);
+		}
 	}
 	return (pte_t *) pmd;
 }
@@ -188,6 +197,11 @@ int pmd_huge(pmd_t pmd)
 	return 0;
 }
 
+int pud_huge(pud_t pud)
+{
+	return 0;
+}
+
 struct page *
 follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 		pmd_t *pmd, int write)
@@ -208,6 +222,11 @@ int pmd_huge(pmd_t pmd)
 	return !!(pmd_val(pmd) & _PAGE_PSE);
 }
 
+int pud_huge(pud_t pud)
+{
+	return !!(pud_val(pud) & _PAGE_PSE);
+}
+
 struct page *
 follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 		pmd_t *pmd, int write)
@@ -216,9 +235,22 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 
 	page = pte_page(*(pte_t *)pmd);
 	if (page)
-		page += ((address & ~HPAGE_MASK) >> PAGE_SHIFT);
+		page += ((address & ~PMD_MASK) >> PAGE_SHIFT);
+	return page;
+}
+
+struct page *
+follow_huge_pud(struct mm_struct *mm, unsigned long address,
+		pud_t *pud, int write)
+{
+	struct page *page;
+
+	page = pte_page(*(pte_t *)pud);
+	if (page)
+		page += ((address & ~PUD_MASK) >> PAGE_SHIFT);
 	return page;
 }
+
 #endif
 
 /* x86_64 also uses this file */
@@ -228,6 +260,7 @@ static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file,
 		unsigned long addr, unsigned long len,
 		unsigned long pgoff, unsigned long flags)
 {
+	struct hstate *h = hstate_file(file);
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
 	unsigned long start_addr;
@@ -240,7 +273,7 @@ static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file,
 	}
 
 full_search:
-	addr = ALIGN(start_addr, HPAGE_SIZE);
+	addr = ALIGN(start_addr, huge_page_size(h));
 
 	for (vma = find_vma(mm, addr); ; vma = vma->vm_next) {
 		/* At this point:  (!vma || addr < vma->vm_end). */
@@ -262,7 +295,7 @@ full_search:
 		}
 		if (addr + mm->cached_hole_size < vma->vm_start)
 		        mm->cached_hole_size = vma->vm_start - addr;
-		addr = ALIGN(vma->vm_end, HPAGE_SIZE);
+		addr = ALIGN(vma->vm_end, huge_page_size(h));
 	}
 }
 
@@ -270,6 +303,7 @@ static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file,
 		unsigned long addr0, unsigned long len,
 		unsigned long pgoff, unsigned long flags)
 {
+	struct hstate *h = hstate_file(file);
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma, *prev_vma;
 	unsigned long base = mm->mmap_base, addr = addr0;
@@ -290,7 +324,7 @@ try_again:
 		goto fail;
 
 	/* either no address requested or cant fit in requested address hole */
-	addr = (mm->free_area_cache - len) & HPAGE_MASK;
+	addr = (mm->free_area_cache - len) & huge_page_mask(h);
 	do {
 		/*
 		 * Lookup failure means no vma is above this address,
@@ -321,7 +355,7 @@ try_again:
 		        largest_hole = vma->vm_start - addr;
 
 		/* try just below the current vma->vm_start */
-		addr = (vma->vm_start - len) & HPAGE_MASK;
+		addr = (vma->vm_start - len) & huge_page_mask(h);
 	} while (len <= vma->vm_start);
 
 fail:
@@ -359,22 +393,23 @@ unsigned long
 hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 		unsigned long len, unsigned long pgoff, unsigned long flags)
 {
+	struct hstate *h = hstate_file(file);
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
 
-	if (len & ~HPAGE_MASK)
+	if (len & ~huge_page_mask(h))
 		return -EINVAL;
 	if (len > TASK_SIZE)
 		return -ENOMEM;
 
 	if (flags & MAP_FIXED) {
-		if (prepare_hugepage_range(addr, len))
+		if (prepare_hugepage_range(file, addr, len))
 			return -EINVAL;
 		return addr;
 	}
 
 	if (addr) {
-		addr = ALIGN(addr, HPAGE_SIZE);
+		addr = ALIGN(addr, huge_page_size(h));
 		vma = find_vma(mm, addr);
 		if (TASK_SIZE - len >= addr &&
 		    (!vma || addr + len <= vma->vm_start))
@@ -390,3 +425,20 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 
 #endif /*HAVE_ARCH_HUGETLB_UNMAPPED_AREA*/
 
+#ifdef CONFIG_X86_64
+static __init int setup_hugepagesz(char *opt)
+{
+	unsigned long ps = memparse(opt, &opt);
+	if (ps == PMD_SIZE) {
+		hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT);
+	} else if (ps == PUD_SIZE && cpu_has_gbpages) {
+		hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
+	} else {
+		printk(KERN_ERR "hugepagesz: Unsupported page size %lu M\n",
+			ps >> 20);
+		return 0;
+	}
+	return 1;
+}
+__setup("hugepagesz=", setup_hugepagesz);
+#endif
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 9689a5138e6..8396868e82c 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -31,6 +31,7 @@
 #include <linux/cpumask.h>
 
 #include <asm/asm.h>
+#include <asm/bios_ebda.h>
 #include <asm/processor.h>
 #include <asm/system.h>
 #include <asm/uaccess.h>
@@ -47,6 +48,7 @@
 #include <asm/paravirt.h>
 #include <asm/setup.h>
 #include <asm/cacheflush.h>
+#include <asm/smp.h>
 
 unsigned int __VMALLOC_RESERVE = 128 << 20;
 
@@ -194,11 +196,30 @@ static void __init kernel_physical_mapping_init(pgd_t *pgd_base,
 	pgd_t *pgd;
 	pmd_t *pmd;
 	pte_t *pte;
-	unsigned pages_2m = 0, pages_4k = 0;
+	unsigned pages_2m, pages_4k;
+	int mapping_iter;
+
+	/*
+	 * First iteration will setup identity mapping using large/small pages
+	 * based on use_pse, with other attributes same as set by
+	 * the early code in head_32.S
+	 *
+	 * Second iteration will setup the appropriate attributes (NX, GLOBAL..)
+	 * as desired for the kernel identity mapping.
+	 *
+	 * This two pass mechanism conforms to the TLB app note which says:
+	 *
+	 *     "Software should not write to a paging-structure entry in a way
+	 *      that would change, for any linear address, both the page size
+	 *      and either the page frame or attributes."
+	 */
+	mapping_iter = 1;
 
 	if (!cpu_has_pse)
 		use_pse = 0;
 
+repeat:
+	pages_2m = pages_4k = 0;
 	pfn = start_pfn;
 	pgd_idx = pgd_index((pfn<<PAGE_SHIFT) + PAGE_OFFSET);
 	pgd = pgd_base + pgd_idx;
@@ -224,6 +245,13 @@ static void __init kernel_physical_mapping_init(pgd_t *pgd_base,
 			if (use_pse) {
 				unsigned int addr2;
 				pgprot_t prot = PAGE_KERNEL_LARGE;
+				/*
+				 * first pass will use the same initial
+				 * identity mapping attribute + _PAGE_PSE.
+				 */
+				pgprot_t init_prot =
+					__pgprot(PTE_IDENT_ATTR |
+						 _PAGE_PSE);
 
 				addr2 = (pfn + PTRS_PER_PTE-1) * PAGE_SIZE +
 					PAGE_OFFSET + PAGE_SIZE-1;
@@ -233,7 +261,10 @@ static void __init kernel_physical_mapping_init(pgd_t *pgd_base,
 					prot = PAGE_KERNEL_LARGE_EXEC;
 
 				pages_2m++;
-				set_pmd(pmd, pfn_pmd(pfn, prot));
+				if (mapping_iter == 1)
+					set_pmd(pmd, pfn_pmd(pfn, init_prot));
+				else
+					set_pmd(pmd, pfn_pmd(pfn, prot));
 
 				pfn += PTRS_PER_PTE;
 				continue;
@@ -245,17 +276,43 @@ static void __init kernel_physical_mapping_init(pgd_t *pgd_base,
 			for (; pte_ofs < PTRS_PER_PTE && pfn < end_pfn;
 			     pte++, pfn++, pte_ofs++, addr += PAGE_SIZE) {
 				pgprot_t prot = PAGE_KERNEL;
+				/*
+				 * first pass will use the same initial
+				 * identity mapping attribute.
+				 */
+				pgprot_t init_prot = __pgprot(PTE_IDENT_ATTR);
 
 				if (is_kernel_text(addr))
 					prot = PAGE_KERNEL_EXEC;
 
 				pages_4k++;
-				set_pte(pte, pfn_pte(pfn, prot));
+				if (mapping_iter == 1)
+					set_pte(pte, pfn_pte(pfn, init_prot));
+				else
+					set_pte(pte, pfn_pte(pfn, prot));
 			}
 		}
 	}
-	update_page_count(PG_LEVEL_2M, pages_2m);
-	update_page_count(PG_LEVEL_4K, pages_4k);
+	if (mapping_iter == 1) {
+		/*
+		 * update direct mapping page count only in the first
+		 * iteration.
+		 */
+		update_page_count(PG_LEVEL_2M, pages_2m);
+		update_page_count(PG_LEVEL_4K, pages_4k);
+
+		/*
+		 * local global flush tlb, which will flush the previous
+		 * mappings present in both small and large page TLB's.
+		 */
+		__flush_tlb_all();
+
+		/*
+		 * Second iteration will set the actual desired PTE attributes.
+		 */
+		mapping_iter = 2;
+		goto repeat;
+	}
 }
 
 /*
@@ -458,11 +515,7 @@ static void __init pagetable_init(void)
 {
 	pgd_t *pgd_base = swapper_pg_dir;
 
-	paravirt_pagetable_setup_start(pgd_base);
-
 	permanent_kmaps_init(pgd_base);
-
-	paravirt_pagetable_setup_done(pgd_base);
 }
 
 #ifdef CONFIG_ACPI_SLEEP
@@ -505,7 +558,7 @@ void zap_low_mappings(void)
 
 int nx_enabled;
 
-pteval_t __supported_pte_mask __read_mostly = ~(_PAGE_NX | _PAGE_GLOBAL);
+pteval_t __supported_pte_mask __read_mostly = ~(_PAGE_NX | _PAGE_GLOBAL | _PAGE_IOMAP);
 EXPORT_SYMBOL_GPL(__supported_pte_mask);
 
 #ifdef CONFIG_X86_PAE
@@ -722,7 +775,7 @@ void __init setup_bootmem_allocator(void)
 	after_init_bootmem = 1;
 }
 
-static void __init find_early_table_space(unsigned long end)
+static void __init find_early_table_space(unsigned long end, int use_pse)
 {
 	unsigned long puds, pmds, ptes, tables, start;
 
@@ -732,7 +785,7 @@ static void __init find_early_table_space(unsigned long end)
 	pmds = (end + PMD_SIZE - 1) >> PMD_SHIFT;
 	tables += PAGE_ALIGN(pmds * sizeof(pmd_t));
 
-	if (cpu_has_pse) {
+	if (use_pse) {
 		unsigned long extra;
 
 		extra = end - ((end>>PMD_SHIFT) << PMD_SHIFT);
@@ -772,12 +825,22 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
 	pgd_t *pgd_base = swapper_pg_dir;
 	unsigned long start_pfn, end_pfn;
 	unsigned long big_page_start;
+#ifdef CONFIG_DEBUG_PAGEALLOC
+	/*
+	 * For CONFIG_DEBUG_PAGEALLOC, identity mapping will use small pages.
+	 * This will simplify cpa(), which otherwise needs to support splitting
+	 * large pages into small in interrupt context, etc.
+	 */
+	int use_pse = 0;
+#else
+	int use_pse = cpu_has_pse;
+#endif
 
 	/*
 	 * Find space for the kernel direct mapping tables.
 	 */
 	if (!after_init_bootmem)
-		find_early_table_space(end);
+		find_early_table_space(end, use_pse);
 
 #ifdef CONFIG_X86_PAE
 	set_nx();
@@ -823,7 +886,7 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
 	end_pfn = (end>>PMD_SHIFT) << (PMD_SHIFT - PAGE_SHIFT);
 	if (start_pfn < end_pfn)
 		kernel_physical_mapping_init(pgd_base, start_pfn, end_pfn,
-						cpu_has_pse);
+					     use_pse);
 
 	/* tail is not big page alignment ? */
 	start_pfn = end_pfn;
@@ -844,6 +907,9 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
 		reserve_early(table_start << PAGE_SHIFT,
 				 table_end << PAGE_SHIFT, "PGTABLE");
 
+	if (!after_init_bootmem)
+		early_memtest(start, end);
+
 	return end >> PAGE_SHIFT;
 }
 
@@ -868,8 +934,6 @@ void __init paging_init(void)
 	 */
 	sparse_init();
 	zone_sizes_init();
-
-	paravirt_post_allocator_init();
 }
 
 /*
@@ -906,6 +970,8 @@ void __init mem_init(void)
 	int codesize, reservedpages, datasize, initsize;
 	int tmp;
 
+	start_periodic_check_for_corruption();
+
 #ifdef CONFIG_FLATMEM
 	BUG_ON(!mem_map);
 #endif
@@ -985,7 +1051,6 @@ void __init mem_init(void)
 	if (boot_cpu_data.wp_works_ok < 0)
 		test_wp_bit();
 
-	cpa_init();
 	save_pg_dir();
 	zap_low_mappings();
 }
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 306049edd55..b8e461d4941 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -31,6 +31,7 @@
 #include <linux/nmi.h>
 
 #include <asm/processor.h>
+#include <asm/bios_ebda.h>
 #include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
@@ -60,7 +61,7 @@ static unsigned long dma_reserve __initdata;
 
 DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
 
-int direct_gbpages __meminitdata
+int direct_gbpages
 #ifdef CONFIG_DIRECT_GBPAGES
 				= 1
 #endif
@@ -86,46 +87,69 @@ early_param("gbpages", parse_direct_gbpages_on);
  * around without checking the pgd every time.
  */
 
-void show_mem(void)
-{
-	long i, total = 0, reserved = 0;
-	long shared = 0, cached = 0;
-	struct page *page;
-	pg_data_t *pgdat;
-
-	printk(KERN_INFO "Mem-info:\n");
-	show_free_areas();
-	for_each_online_pgdat(pgdat) {
-		for (i = 0; i < pgdat->node_spanned_pages; ++i) {
-			/*
-			 * This loop can take a while with 256 GB and
-			 * 4k pages so defer the NMI watchdog:
-			 */
-			if (unlikely(i % MAX_ORDER_NR_PAGES == 0))
-				touch_nmi_watchdog();
+int after_bootmem;
 
-			if (!pfn_valid(pgdat->node_start_pfn + i))
-				continue;
+pteval_t __supported_pte_mask __read_mostly = ~_PAGE_IOMAP;
+EXPORT_SYMBOL_GPL(__supported_pte_mask);
 
-			page = pfn_to_page(pgdat->node_start_pfn + i);
-			total++;
-			if (PageReserved(page))
-				reserved++;
-			else if (PageSwapCache(page))
-				cached++;
-			else if (page_count(page))
-				shared += page_count(page) - 1;
-		}
+static int do_not_nx __cpuinitdata;
+
+/*
+ * noexec=on|off
+ * Control non-executable mappings for 64-bit processes.
+ *
+ * on	Enable (default)
+ * off	Disable
+ */
+static int __init nonx_setup(char *str)
+{
+	if (!str)
+		return -EINVAL;
+	if (!strncmp(str, "on", 2)) {
+		__supported_pte_mask |= _PAGE_NX;
+		do_not_nx = 0;
+	} else if (!strncmp(str, "off", 3)) {
+		do_not_nx = 1;
+		__supported_pte_mask &= ~_PAGE_NX;
 	}
-	printk(KERN_INFO "%lu pages of RAM\n",		total);
-	printk(KERN_INFO "%lu reserved pages\n",	reserved);
-	printk(KERN_INFO "%lu pages shared\n",		shared);
-	printk(KERN_INFO "%lu pages swap cached\n",	cached);
+	return 0;
 }
+early_param("noexec", nonx_setup);
 
-int after_bootmem;
+void __cpuinit check_efer(void)
+{
+	unsigned long efer;
+
+	rdmsrl(MSR_EFER, efer);
+	if (!(efer & EFER_NX) || do_not_nx)
+		__supported_pte_mask &= ~_PAGE_NX;
+}
+
+int force_personality32;
+
+/*
+ * noexec32=on|off
+ * Control non executable heap for 32bit processes.
+ * To control the stack too use noexec=off
+ *
+ * on	PROT_READ does not imply PROT_EXEC for 32-bit processes (default)
+ * off	PROT_READ implies PROT_EXEC
+ */
+static int __init nonx32_setup(char *str)
+{
+	if (!strcmp(str, "on"))
+		force_personality32 &= ~READ_IMPLIES_EXEC;
+	else if (!strcmp(str, "off"))
+		force_personality32 |= READ_IMPLIES_EXEC;
+	return 1;
+}
+__setup("noexec32=", nonx32_setup);
 
-static __init void *spp_getpage(void)
+/*
+ * NOTE: This function is marked __ref because it calls __init function
+ * (alloc_bootmem_pages). It's safe to do it ONLY when after_bootmem == 0.
+ */
+static __ref void *spp_getpage(void)
 {
 	void *ptr;
 
@@ -172,9 +196,6 @@ set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte)
 	}
 
 	pte = pte_offset_kernel(pmd, vaddr);
-	if (!pte_none(*pte) && pte_val(new_pte) &&
-	    pte_val(*pte) != (pte_val(new_pte) & __supported_pte_mask))
-		pte_ERROR(*pte);
 	set_pte(pte, new_pte);
 
 	/*
@@ -258,7 +279,7 @@ void __init init_extra_mapping_uc(unsigned long phys, unsigned long size)
 void __init cleanup_highmap(void)
 {
 	unsigned long vaddr = __START_KERNEL_map;
-	unsigned long end = round_up((unsigned long)_end, PMD_SIZE) - 1;
+	unsigned long end = roundup((unsigned long)_end, PMD_SIZE) - 1;
 	pmd_t *pmd = level2_kernel_pgt;
 	pmd_t *last_pmd = pmd + PTRS_PER_PMD;
 
@@ -274,7 +295,7 @@ static unsigned long __initdata table_start;
 static unsigned long __meminitdata table_end;
 static unsigned long __meminitdata table_top;
 
-static __meminit void *alloc_low_page(unsigned long *phys)
+static __ref void *alloc_low_page(unsigned long *phys)
 {
 	unsigned long pfn = table_end++;
 	void *adr;
@@ -289,13 +310,13 @@ static __meminit void *alloc_low_page(unsigned long *phys)
 	if (pfn >= table_top)
 		panic("alloc_low_page: ran out of memory");
 
-	adr = early_ioremap(pfn * PAGE_SIZE, PAGE_SIZE);
+	adr = early_memremap(pfn * PAGE_SIZE, PAGE_SIZE);
 	memset(adr, 0, PAGE_SIZE);
 	*phys  = pfn * PAGE_SIZE;
 	return adr;
 }
 
-static __meminit void unmap_low_page(void *adr)
+static __ref void unmap_low_page(void *adr)
 {
 	if (after_bootmem)
 		return;
@@ -304,7 +325,8 @@ static __meminit void unmap_low_page(void *adr)
 }
 
 static unsigned long __meminit
-phys_pte_init(pte_t *pte_page, unsigned long addr, unsigned long end)
+phys_pte_init(pte_t *pte_page, unsigned long addr, unsigned long end,
+	      pgprot_t prot)
 {
 	unsigned pages = 0;
 	unsigned long last_map_addr = end;
@@ -322,32 +344,40 @@ phys_pte_init(pte_t *pte_page, unsigned long addr, unsigned long end)
 			break;
 		}
 
+		/*
+		 * We will re-use the existing mapping.
+		 * Xen for example has some special requirements, like mapping
+		 * pagetable pages as RO. So assume someone who pre-setup
+		 * these mappings are more intelligent.
+		 */
 		if (pte_val(*pte))
 			continue;
 
 		if (0)
 			printk("   pte=%p addr=%lx pte=%016lx\n",
 			       pte, addr, pfn_pte(addr >> PAGE_SHIFT, PAGE_KERNEL).pte);
-		set_pte(pte, pfn_pte(addr >> PAGE_SHIFT, PAGE_KERNEL));
-		last_map_addr = (addr & PAGE_MASK) + PAGE_SIZE;
 		pages++;
+		set_pte(pte, pfn_pte(addr >> PAGE_SHIFT, prot));
+		last_map_addr = (addr & PAGE_MASK) + PAGE_SIZE;
 	}
+
 	update_page_count(PG_LEVEL_4K, pages);
 
 	return last_map_addr;
 }
 
 static unsigned long __meminit
-phys_pte_update(pmd_t *pmd, unsigned long address, unsigned long end)
+phys_pte_update(pmd_t *pmd, unsigned long address, unsigned long end,
+		pgprot_t prot)
 {
 	pte_t *pte = (pte_t *)pmd_page_vaddr(*pmd);
 
-	return phys_pte_init(pte, address, end);
+	return phys_pte_init(pte, address, end, prot);
 }
 
 static unsigned long __meminit
 phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end,
-			 unsigned long page_size_mask)
+	      unsigned long page_size_mask, pgprot_t prot)
 {
 	unsigned long pages = 0;
 	unsigned long last_map_addr = end;
@@ -358,6 +388,7 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end,
 		unsigned long pte_phys;
 		pmd_t *pmd = pmd_page + pmd_index(address);
 		pte_t *pte;
+		pgprot_t new_prot = prot;
 
 		if (address >= end) {
 			if (!after_bootmem) {
@@ -368,25 +399,48 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end,
 		}
 
 		if (pmd_val(*pmd)) {
-			if (!pmd_large(*pmd))
+			if (!pmd_large(*pmd)) {
+				spin_lock(&init_mm.page_table_lock);
 				last_map_addr = phys_pte_update(pmd, address,
-								 end);
-			continue;
+								end, prot);
+				spin_unlock(&init_mm.page_table_lock);
+				continue;
+			}
+			/*
+			 * If we are ok with PG_LEVEL_2M mapping, then we will
+			 * use the existing mapping,
+			 *
+			 * Otherwise, we will split the large page mapping but
+			 * use the same existing protection bits except for
+			 * large page, so that we don't violate Intel's TLB
+			 * Application note (317080) which says, while changing
+			 * the page sizes, new and old translations should
+			 * not differ with respect to page frame and
+			 * attributes.
+			 */
+			if (page_size_mask & (1 << PG_LEVEL_2M))
+				continue;
+			new_prot = pte_pgprot(pte_clrhuge(*(pte_t *)pmd));
 		}
 
 		if (page_size_mask & (1<<PG_LEVEL_2M)) {
 			pages++;
+			spin_lock(&init_mm.page_table_lock);
 			set_pte((pte_t *)pmd,
-				pfn_pte(address >> PAGE_SHIFT, PAGE_KERNEL_LARGE));
+				pfn_pte(address >> PAGE_SHIFT,
+					__pgprot(pgprot_val(prot) | _PAGE_PSE)));
+			spin_unlock(&init_mm.page_table_lock);
 			last_map_addr = (address & PMD_MASK) + PMD_SIZE;
 			continue;
 		}
 
 		pte = alloc_low_page(&pte_phys);
-		last_map_addr = phys_pte_init(pte, address, end);
+		last_map_addr = phys_pte_init(pte, address, end, new_prot);
 		unmap_low_page(pte);
 
+		spin_lock(&init_mm.page_table_lock);
 		pmd_populate_kernel(&init_mm, pmd, __va(pte_phys));
+		spin_unlock(&init_mm.page_table_lock);
 	}
 	update_page_count(PG_LEVEL_2M, pages);
 	return last_map_addr;
@@ -394,14 +448,12 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end,
 
 static unsigned long __meminit
 phys_pmd_update(pud_t *pud, unsigned long address, unsigned long end,
-			 unsigned long page_size_mask)
+		unsigned long page_size_mask, pgprot_t prot)
 {
 	pmd_t *pmd = pmd_offset(pud, 0);
 	unsigned long last_map_addr;
 
-	spin_lock(&init_mm.page_table_lock);
-	last_map_addr = phys_pmd_init(pmd, address, end, page_size_mask);
-	spin_unlock(&init_mm.page_table_lock);
+	last_map_addr = phys_pmd_init(pmd, address, end, page_size_mask, prot);
 	__flush_tlb_all();
 	return last_map_addr;
 }
@@ -418,6 +470,7 @@ phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end,
 		unsigned long pmd_phys;
 		pud_t *pud = pud_page + pud_index(addr);
 		pmd_t *pmd;
+		pgprot_t prot = PAGE_KERNEL;
 
 		if (addr >= end)
 			break;
@@ -429,30 +482,49 @@ phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end,
 		}
 
 		if (pud_val(*pud)) {
-			if (!pud_large(*pud))
+			if (!pud_large(*pud)) {
 				last_map_addr = phys_pmd_update(pud, addr, end,
-							 page_size_mask);
-			continue;
+							 page_size_mask, prot);
+				continue;
+			}
+			/*
+			 * If we are ok with PG_LEVEL_1G mapping, then we will
+			 * use the existing mapping.
+			 *
+			 * Otherwise, we will split the gbpage mapping but use
+			 * the same existing protection  bits except for large
+			 * page, so that we don't violate Intel's TLB
+			 * Application note (317080) which says, while changing
+			 * the page sizes, new and old translations should
+			 * not differ with respect to page frame and
+			 * attributes.
+			 */
+			if (page_size_mask & (1 << PG_LEVEL_1G))
+				continue;
+			prot = pte_pgprot(pte_clrhuge(*(pte_t *)pud));
 		}
 
 		if (page_size_mask & (1<<PG_LEVEL_1G)) {
 			pages++;
+			spin_lock(&init_mm.page_table_lock);
 			set_pte((pte_t *)pud,
 				pfn_pte(addr >> PAGE_SHIFT, PAGE_KERNEL_LARGE));
+			spin_unlock(&init_mm.page_table_lock);
 			last_map_addr = (addr & PUD_MASK) + PUD_SIZE;
 			continue;
 		}
 
 		pmd = alloc_low_page(&pmd_phys);
+		last_map_addr = phys_pmd_init(pmd, addr, end, page_size_mask,
+					      prot);
+		unmap_low_page(pmd);
 
 		spin_lock(&init_mm.page_table_lock);
-		last_map_addr = phys_pmd_init(pmd, addr, end, page_size_mask);
-		unmap_low_page(pmd);
 		pud_populate(&init_mm, pud, __va(pmd_phys));
 		spin_unlock(&init_mm.page_table_lock);
-
 	}
 	__flush_tlb_all();
+
 	update_page_count(PG_LEVEL_1G, pages);
 
 	return last_map_addr;
@@ -469,27 +541,28 @@ phys_pud_update(pgd_t *pgd, unsigned long addr, unsigned long end,
 	return phys_pud_init(pud, addr, end, page_size_mask);
 }
 
-static void __init find_early_table_space(unsigned long end)
+static void __init find_early_table_space(unsigned long end, int use_pse,
+					  int use_gbpages)
 {
 	unsigned long puds, pmds, ptes, tables, start;
 
 	puds = (end + PUD_SIZE - 1) >> PUD_SHIFT;
-	tables = round_up(puds * sizeof(pud_t), PAGE_SIZE);
-	if (direct_gbpages) {
+	tables = roundup(puds * sizeof(pud_t), PAGE_SIZE);
+	if (use_gbpages) {
 		unsigned long extra;
 		extra = end - ((end>>PUD_SHIFT) << PUD_SHIFT);
 		pmds = (extra + PMD_SIZE - 1) >> PMD_SHIFT;
 	} else
 		pmds = (end + PMD_SIZE - 1) >> PMD_SHIFT;
-	tables += round_up(pmds * sizeof(pmd_t), PAGE_SIZE);
+	tables += roundup(pmds * sizeof(pmd_t), PAGE_SIZE);
 
-	if (cpu_has_pse) {
+	if (use_pse) {
 		unsigned long extra;
 		extra = end - ((end>>PMD_SHIFT) << PMD_SHIFT);
 		ptes = (extra + PAGE_SIZE - 1) >> PAGE_SHIFT;
 	} else
 		ptes = (end + PAGE_SIZE - 1) >> PAGE_SHIFT;
-	tables += round_up(ptes * sizeof(pte_t), PAGE_SIZE);
+	tables += roundup(ptes * sizeof(pte_t), PAGE_SIZE);
 
 	/*
 	 * RED-PEN putting page tables only on node 0 could
@@ -517,118 +590,6 @@ static void __init init_gbpages(void)
 		direct_gbpages = 0;
 }
 
-#ifdef CONFIG_MEMTEST
-
-static void __init memtest(unsigned long start_phys, unsigned long size,
-				 unsigned pattern)
-{
-	unsigned long i;
-	unsigned long *start;
-	unsigned long start_bad;
-	unsigned long last_bad;
-	unsigned long val;
-	unsigned long start_phys_aligned;
-	unsigned long count;
-	unsigned long incr;
-
-	switch (pattern) {
-	case 0:
-		val = 0UL;
-		break;
-	case 1:
-		val = -1UL;
-		break;
-	case 2:
-		val = 0x5555555555555555UL;
-		break;
-	case 3:
-		val = 0xaaaaaaaaaaaaaaaaUL;
-		break;
-	default:
-		return;
-	}
-
-	incr = sizeof(unsigned long);
-	start_phys_aligned = ALIGN(start_phys, incr);
-	count = (size - (start_phys_aligned - start_phys))/incr;
-	start = __va(start_phys_aligned);
-	start_bad = 0;
-	last_bad = 0;
-
-	for (i = 0; i < count; i++)
-		start[i] = val;
-	for (i = 0; i < count; i++, start++, start_phys_aligned += incr) {
-		if (*start != val) {
-			if (start_phys_aligned == last_bad + incr) {
-				last_bad += incr;
-			} else {
-				if (start_bad) {
-					printk(KERN_CONT "\n  %016lx bad mem addr %016lx - %016lx reserved",
-						val, start_bad, last_bad + incr);
-					reserve_early(start_bad, last_bad - start_bad, "BAD RAM");
-				}
-				start_bad = last_bad = start_phys_aligned;
-			}
-		}
-	}
-	if (start_bad) {
-		printk(KERN_CONT "\n  %016lx bad mem addr %016lx - %016lx reserved",
-			val, start_bad, last_bad + incr);
-		reserve_early(start_bad, last_bad - start_bad, "BAD RAM");
-	}
-
-}
-
-/* default is disabled */
-static int memtest_pattern __initdata;
-
-static int __init parse_memtest(char *arg)
-{
-	if (arg)
-		memtest_pattern = simple_strtoul(arg, NULL, 0);
-	return 0;
-}
-
-early_param("memtest", parse_memtest);
-
-static void __init early_memtest(unsigned long start, unsigned long end)
-{
-	u64 t_start, t_size;
-	unsigned pattern;
-
-	if (!memtest_pattern)
-		return;
-
-	printk(KERN_INFO "early_memtest: pattern num %d", memtest_pattern);
-	for (pattern = 0; pattern < memtest_pattern; pattern++) {
-		t_start = start;
-		t_size = 0;
-		while (t_start < end) {
-			t_start = find_e820_area_size(t_start, &t_size, 1);
-
-			/* done ? */
-			if (t_start >= end)
-				break;
-			if (t_start + t_size > end)
-				t_size = end - t_start;
-
-			printk(KERN_CONT "\n  %016llx - %016llx pattern %d",
-				(unsigned long long)t_start,
-				(unsigned long long)t_start + t_size, pattern);
-
-			memtest(t_start, t_size, pattern);
-
-			t_start += t_size;
-		}
-	}
-	printk(KERN_CONT "\n");
-}
-#else
-static void __init early_memtest(unsigned long start, unsigned long end)
-{
-}
-#endif
-
 static unsigned long __init kernel_physical_mapping_init(unsigned long start,
 						unsigned long end,
 						unsigned long page_size_mask)
@@ -654,17 +615,16 @@ static unsigned long __init kernel_physical_mapping_init(unsigned long start,
 			continue;
 		}
 
-		if (after_bootmem)
-			pud = pud_offset(pgd, start & PGDIR_MASK);
-		else
-			pud = alloc_low_page(&pud_phys);
-
+		pud = alloc_low_page(&pud_phys);
 		last_map_addr = phys_pud_init(pud, __pa(start), __pa(next),
 						 page_size_mask);
 		unmap_low_page(pud);
-		pgd_populate(&init_mm, pgd_offset_k(start),
-			     __va(pud_phys));
+
+		spin_lock(&init_mm.page_table_lock);
+		pgd_populate(&init_mm, pgd, __va(pud_phys));
+		spin_unlock(&init_mm.page_table_lock);
 	}
+	__flush_tlb_all();
 
 	return last_map_addr;
 }
@@ -708,6 +668,7 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
 
 	struct map_range mr[NR_RANGE_MR];
 	int nr_range, i;
+	int use_pse, use_gbpages;
 
 	printk(KERN_INFO "init_memory_mapping\n");
 
@@ -721,9 +682,21 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
 	if (!after_bootmem)
 		init_gbpages();
 
-	if (direct_gbpages)
+#ifdef CONFIG_DEBUG_PAGEALLOC
+	/*
+	 * For CONFIG_DEBUG_PAGEALLOC, identity mapping will use small pages.
+	 * This will simplify cpa(), which otherwise needs to support splitting
+	 * large pages into small in interrupt context, etc.
+	 */
+	use_pse = use_gbpages = 0;
+#else
+	use_pse = cpu_has_pse;
+	use_gbpages = direct_gbpages;
+#endif
+
+	if (use_gbpages)
 		page_size_mask |= 1 << PG_LEVEL_1G;
-	if (cpu_has_pse)
+	if (use_pse)
 		page_size_mask |= 1 << PG_LEVEL_2M;
 
 	memset(mr, 0, sizeof(mr));
@@ -773,7 +746,7 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
 		old_start = mr[i].start;
 		memmove(&mr[i], &mr[i+1],
 			 (nr_range - 1 - i) * sizeof (struct map_range));
-		mr[i].start = old_start;
+		mr[i--].start = old_start;
 		nr_range--;
 	}
 
@@ -784,7 +757,7 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
 			 (mr[i].page_size_mask & (1<<PG_LEVEL_2M))?"2M":"4k"));
 
 	if (!after_bootmem)
-		find_early_table_space(end);
+		find_early_table_space(end, use_pse, use_gbpages);
 
 	for (i = 0; i < nr_range; i++)
 		last_map_addr = kernel_physical_mapping_init(
@@ -906,6 +879,8 @@ void __init mem_init(void)
 {
 	long codesize, reservedpages, datasize, initsize;
 
+	start_periodic_check_for_corruption();
+
 	pci_iommu_alloc();
 
 	/* clear_bss() already clear the empty_zero_page */
@@ -943,8 +918,6 @@ void __init mem_init(void)
 		reservedpages << (PAGE_SHIFT-10),
 		datasize >> 10,
 		initsize >> 10);
-
-	cpa_init();
 }
 
 void free_init_pages(char *what, unsigned long begin, unsigned long end)
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 24c1d3c3018..ae71e11eb3e 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -24,18 +24,47 @@
 
 #ifdef CONFIG_X86_64
 
+static inline int phys_addr_valid(unsigned long addr)
+{
+	return addr < (1UL << boot_cpu_data.x86_phys_bits);
+}
+
 unsigned long __phys_addr(unsigned long x)
 {
-	if (x >= __START_KERNEL_map)
-		return x - __START_KERNEL_map + phys_base;
-	return x - PAGE_OFFSET;
+	if (x >= __START_KERNEL_map) {
+		x -= __START_KERNEL_map;
+		VIRTUAL_BUG_ON(x >= KERNEL_IMAGE_SIZE);
+		x += phys_base;
+	} else {
+		VIRTUAL_BUG_ON(x < PAGE_OFFSET);
+		x -= PAGE_OFFSET;
+		VIRTUAL_BUG_ON(system_state == SYSTEM_BOOTING ? x > MAXMEM :
+					!phys_addr_valid(x));
+	}
+	return x;
 }
 EXPORT_SYMBOL(__phys_addr);
 
-static inline int phys_addr_valid(unsigned long addr)
+bool __virt_addr_valid(unsigned long x)
 {
-	return addr < (1UL << boot_cpu_data.x86_phys_bits);
+	if (x >= __START_KERNEL_map) {
+		x -= __START_KERNEL_map;
+		if (x >= KERNEL_IMAGE_SIZE)
+			return false;
+		x += phys_base;
+	} else {
+		if (x < PAGE_OFFSET)
+			return false;
+		x -= PAGE_OFFSET;
+		if (system_state == SYSTEM_BOOTING ?
+				x > MAXMEM : !phys_addr_valid(x)) {
+			return false;
+		}
+	}
+
+	return pfn_valid(x >> PAGE_SHIFT);
 }
+EXPORT_SYMBOL(__virt_addr_valid);
 
 #else
 
@@ -44,6 +73,28 @@ static inline int phys_addr_valid(unsigned long addr)
 	return 1;
 }
 
+#ifdef CONFIG_DEBUG_VIRTUAL
+unsigned long __phys_addr(unsigned long x)
+{
+	/* VMALLOC_* aren't constants; not available at the boot time */
+	VIRTUAL_BUG_ON(x < PAGE_OFFSET);
+	VIRTUAL_BUG_ON(system_state != SYSTEM_BOOTING &&
+		is_vmalloc_addr((void *) x));
+	return x - PAGE_OFFSET;
+}
+EXPORT_SYMBOL(__phys_addr);
+#endif
+
+bool __virt_addr_valid(unsigned long x)
+{
+	if (x < PAGE_OFFSET)
+		return false;
+	if (system_state != SYSTEM_BOOTING && is_vmalloc_addr((void *) x))
+		return false;
+	return pfn_valid((x - PAGE_OFFSET) >> PAGE_SHIFT);
+}
+EXPORT_SYMBOL(__virt_addr_valid);
+
 #endif
 
 int page_is_ram(unsigned long pagenr)
@@ -83,6 +134,25 @@ int page_is_ram(unsigned long pagenr)
 	return 0;
 }
 
+int pagerange_is_ram(unsigned long start, unsigned long end)
+{
+	int ram_page = 0, not_rampage = 0;
+	unsigned long page_nr;
+
+	for (page_nr = (start >> PAGE_SHIFT); page_nr < (end >> PAGE_SHIFT);
+	     ++page_nr) {
+		if (page_is_ram(page_nr))
+			ram_page = 1;
+		else
+			not_rampage = 1;
+
+		if (ram_page == not_rampage)
+			return -1;
+	}
+
+	return ram_page;
+}
+
 /*
  * Fix up the linear direct mapping of the kernel to avoid cache attribute
  * conflicts.
@@ -150,6 +220,12 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr,
 		return (__force void __iomem *)phys_to_virt(phys_addr);
 
 	/*
+	 * Check if the request spans more than any BAR in the iomem resource
+	 * tree.
+	 */
+	WARN_ON(iomem_map_sanity_check(phys_addr, size));
+
+	/*
 	 * Don't allow anybody to remap normal RAM that we're using..
 	 */
 	for (pfn = phys_addr >> PAGE_SHIFT;
@@ -170,7 +246,7 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr,
 	phys_addr &= PAGE_MASK;
 	size = PAGE_ALIGN(last_addr+1) - phys_addr;
 
-	retval = reserve_memtype(phys_addr, phys_addr + size,
+	retval = reserve_memtype(phys_addr, (u64)phys_addr + size,
 						prot_val, &new_prot_val);
 	if (retval) {
 		pr_debug("Warning: reserve_memtype returned %d\n", retval);
@@ -204,16 +280,16 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr,
 	switch (prot_val) {
 	case _PAGE_CACHE_UC:
 	default:
-		prot = PAGE_KERNEL_NOCACHE;
+		prot = PAGE_KERNEL_IO_NOCACHE;
 		break;
 	case _PAGE_CACHE_UC_MINUS:
-		prot = PAGE_KERNEL_UC_MINUS;
+		prot = PAGE_KERNEL_IO_UC_MINUS;
 		break;
 	case _PAGE_CACHE_WC:
-		prot = PAGE_KERNEL_WC;
+		prot = PAGE_KERNEL_IO_WC;
 		break;
 	case _PAGE_CACHE_WB:
-		prot = PAGE_KERNEL;
+		prot = PAGE_KERNEL_IO;
 		break;
 	}
 
@@ -330,6 +406,14 @@ static void __iomem *ioremap_default(resource_size_t phys_addr,
 	return (void __iomem *)ret;
 }
 
+void __iomem *ioremap_prot(resource_size_t phys_addr, unsigned long size,
+				unsigned long prot_val)
+{
+	return __ioremap_caller(phys_addr, size, (prot_val & _PAGE_CACHE_MASK),
+				__builtin_return_address(0));
+}
+EXPORT_SYMBOL(ioremap_prot);
+
 /**
  * iounmap - Free a IO remapping
  * @addr: virtual address from ioremap_*
@@ -413,7 +497,7 @@ void unxlate_dev_mem_ptr(unsigned long phys, void *addr)
 	return;
 }
 
-int __initdata early_ioremap_debug;
+static int __initdata early_ioremap_debug;
 
 static int __init early_ioremap_debug_setup(char *str)
 {
@@ -522,12 +606,12 @@ static void __init __early_set_fixmap(enum fixed_addresses idx,
 }
 
 static inline void __init early_set_fixmap(enum fixed_addresses idx,
-					unsigned long phys)
+					   unsigned long phys, pgprot_t prot)
 {
 	if (after_paging_init)
-		set_fixmap(idx, phys);
+		__set_fixmap(idx, phys, prot);
 	else
-		__early_set_fixmap(idx, phys, PAGE_KERNEL);
+		__early_set_fixmap(idx, phys, prot);
 }
 
 static inline void __init early_clear_fixmap(enum fixed_addresses idx)
@@ -538,37 +622,56 @@ static inline void __init early_clear_fixmap(enum fixed_addresses idx)
 		__early_set_fixmap(idx, 0, __pgprot(0));
 }
 
-
-int __initdata early_ioremap_nested;
-
+static void *prev_map[FIX_BTMAPS_SLOTS] __initdata;
+static unsigned long prev_size[FIX_BTMAPS_SLOTS] __initdata;
 static int __init check_early_ioremap_leak(void)
 {
-	if (!early_ioremap_nested)
-		return 0;
+	int count = 0;
+	int i;
 
-	printk(KERN_WARNING
+	for (i = 0; i < FIX_BTMAPS_SLOTS; i++)
+		if (prev_map[i])
+			count++;
+
+	if (!count)
+		return 0;
+	WARN(1, KERN_WARNING
 	       "Debug warning: early ioremap leak of %d areas detected.\n",
-	       early_ioremap_nested);
+		count);
 	printk(KERN_WARNING
-	       "please boot with early_ioremap_debug and report the dmesg.\n");
-	WARN_ON(1);
+		"please boot with early_ioremap_debug and report the dmesg.\n");
 
 	return 1;
 }
 late_initcall(check_early_ioremap_leak);
 
-void __init *early_ioremap(unsigned long phys_addr, unsigned long size)
+static void __init *__early_ioremap(unsigned long phys_addr, unsigned long size, pgprot_t prot)
 {
 	unsigned long offset, last_addr;
-	unsigned int nrpages, nesting;
+	unsigned int nrpages;
 	enum fixed_addresses idx0, idx;
+	int i, slot;
 
 	WARN_ON(system_state != SYSTEM_BOOTING);
 
-	nesting = early_ioremap_nested;
+	slot = -1;
+	for (i = 0; i < FIX_BTMAPS_SLOTS; i++) {
+		if (!prev_map[i]) {
+			slot = i;
+			break;
+		}
+	}
+
+	if (slot < 0) {
+		printk(KERN_INFO "early_iomap(%08lx, %08lx) not found slot\n",
+			 phys_addr, size);
+		WARN_ON(1);
+		return NULL;
+	}
+
 	if (early_ioremap_debug) {
 		printk(KERN_INFO "early_ioremap(%08lx, %08lx) [%d] => ",
-		       phys_addr, size, nesting);
+		       phys_addr, size, slot);
 		dump_stack();
 	}
 
@@ -579,17 +682,13 @@ void __init *early_ioremap(unsigned long phys_addr, unsigned long size)
 		return NULL;
 	}
 
-	if (nesting >= FIX_BTMAPS_NESTING) {
-		WARN_ON(1);
-		return NULL;
-	}
-	early_ioremap_nested++;
+	prev_size[slot] = size;
 	/*
 	 * Mappings have to be page-aligned
 	 */
 	offset = phys_addr & ~PAGE_MASK;
 	phys_addr &= PAGE_MASK;
-	size = PAGE_ALIGN(last_addr) - phys_addr;
+	size = PAGE_ALIGN(last_addr + 1) - phys_addr;
 
 	/*
 	 * Mappings have to fit in the FIX_BTMAP area.
@@ -603,10 +702,10 @@ void __init *early_ioremap(unsigned long phys_addr, unsigned long size)
 	/*
 	 * Ok, go for it..
 	 */
-	idx0 = FIX_BTMAP_BEGIN - NR_FIX_BTMAPS*nesting;
+	idx0 = FIX_BTMAP_BEGIN - NR_FIX_BTMAPS*slot;
 	idx = idx0;
 	while (nrpages > 0) {
-		early_set_fixmap(idx, phys_addr);
+		early_set_fixmap(idx, phys_addr, prot);
 		phys_addr += PAGE_SIZE;
 		--idx;
 		--nrpages;
@@ -614,7 +713,20 @@ void __init *early_ioremap(unsigned long phys_addr, unsigned long size)
 	if (early_ioremap_debug)
 		printk(KERN_CONT "%08lx + %08lx\n", offset, fix_to_virt(idx0));
 
-	return (void *) (offset + fix_to_virt(idx0));
+	prev_map[slot] = (void *) (offset + fix_to_virt(idx0));
+	return prev_map[slot];
+}
+
+/* Remap an IO device */
+void __init *early_ioremap(unsigned long phys_addr, unsigned long size)
+{
+	return __early_ioremap(phys_addr, size, PAGE_KERNEL_IO);
+}
+
+/* Remap memory */
+void __init *early_memremap(unsigned long phys_addr, unsigned long size)
+{
+	return __early_ioremap(phys_addr, size, PAGE_KERNEL);
 }
 
 void __init early_iounmap(void *addr, unsigned long size)
@@ -623,15 +735,33 @@ void __init early_iounmap(void *addr, unsigned long size)
 	unsigned long offset;
 	unsigned int nrpages;
 	enum fixed_addresses idx;
-	int nesting;
+	int i, slot;
+
+	slot = -1;
+	for (i = 0; i < FIX_BTMAPS_SLOTS; i++) {
+		if (prev_map[i] == addr) {
+			slot = i;
+			break;
+		}
+	}
 
-	nesting = --early_ioremap_nested;
-	if (WARN_ON(nesting < 0))
+	if (slot < 0) {
+		printk(KERN_INFO "early_iounmap(%p, %08lx) not found slot\n",
+			 addr, size);
+		WARN_ON(1);
 		return;
+	}
+
+	if (prev_size[slot] != size) {
+		printk(KERN_INFO "early_iounmap(%p, %08lx) [%d] size not consistent %08lx\n",
+			 addr, size, slot, prev_size[slot]);
+		WARN_ON(1);
+		return;
+	}
 
 	if (early_ioremap_debug) {
 		printk(KERN_INFO "early_iounmap(%p, %08lx) [%d]\n", addr,
-		       size, nesting);
+		       size, slot);
 		dump_stack();
 	}
 
@@ -643,12 +773,13 @@ void __init early_iounmap(void *addr, unsigned long size)
 	offset = virt_addr & ~PAGE_MASK;
 	nrpages = PAGE_ALIGN(offset + size - 1) >> PAGE_SHIFT;
 
-	idx = FIX_BTMAP_BEGIN - NR_FIX_BTMAPS*nesting;
+	idx = FIX_BTMAP_BEGIN - NR_FIX_BTMAPS*slot;
 	while (nrpages > 0) {
 		early_clear_fixmap(idx);
 		--idx;
 		--nrpages;
 	}
+	prev_map[slot] = 0;
 }
 
 void __this_fixmap_does_not_exist(void)
diff --git a/arch/x86/mm/memtest.c b/arch/x86/mm/memtest.c
new file mode 100644
index 00000000000..9cab18b0b85
--- /dev/null
+++ b/arch/x86/mm/memtest.c
@@ -0,0 +1,122 @@
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/init.h>
+#include <linux/pfn.h>
+
+#include <asm/e820.h>
+
+static void __init memtest(unsigned long start_phys, unsigned long size,
+				 unsigned pattern)
+{
+	unsigned long i;
+	unsigned long *start;
+	unsigned long start_bad;
+	unsigned long last_bad;
+	unsigned long val;
+	unsigned long start_phys_aligned;
+	unsigned long count;
+	unsigned long incr;
+
+	switch (pattern) {
+	case 0:
+		val = 0UL;
+		break;
+	case 1:
+		val = -1UL;
+		break;
+	case 2:
+#ifdef CONFIG_X86_64
+		val = 0x5555555555555555UL;
+#else
+		val = 0x55555555UL;
+#endif
+		break;
+	case 3:
+#ifdef CONFIG_X86_64
+		val = 0xaaaaaaaaaaaaaaaaUL;
+#else
+		val = 0xaaaaaaaaUL;
+#endif
+		break;
+	default:
+		return;
+	}
+
+	incr = sizeof(unsigned long);
+	start_phys_aligned = ALIGN(start_phys, incr);
+	count = (size - (start_phys_aligned - start_phys))/incr;
+	start = __va(start_phys_aligned);
+	start_bad = 0;
+	last_bad = 0;
+
+	for (i = 0; i < count; i++)
+		start[i] = val;
+	for (i = 0; i < count; i++, start++, start_phys_aligned += incr) {
+		if (*start != val) {
+			if (start_phys_aligned == last_bad + incr) {
+				last_bad += incr;
+			} else {
+				if (start_bad) {
+					printk(KERN_CONT "\n  %016lx bad mem addr %010lx - %010lx reserved",
+						val, start_bad, last_bad + incr);
+					reserve_early(start_bad, last_bad + incr, "BAD RAM");
+				}
+				start_bad = last_bad = start_phys_aligned;
+			}
+		}
+	}
+	if (start_bad) {
+		printk(KERN_CONT "\n  %016lx bad mem addr %010lx - %010lx reserved",
+			val, start_bad, last_bad + incr);
+		reserve_early(start_bad, last_bad + incr, "BAD RAM");
+	}
+}
+
+/* default is disabled */
+static int memtest_pattern __initdata;
+
+static int __init parse_memtest(char *arg)
+{
+	if (arg)
+		memtest_pattern = simple_strtoul(arg, NULL, 0);
+	return 0;
+}
+
+early_param("memtest", parse_memtest);
+
+void __init early_memtest(unsigned long start, unsigned long end)
+{
+	u64 t_start, t_size;
+	unsigned pattern;
+
+	if (!memtest_pattern)
+		return;
+
+	printk(KERN_INFO "early_memtest: pattern num %d", memtest_pattern);
+	for (pattern = 0; pattern < memtest_pattern; pattern++) {
+		t_start = start;
+		t_size = 0;
+		while (t_start < end) {
+			t_start = find_e820_area_size(t_start, &t_size, 1);
+
+			/* done ? */
+			if (t_start >= end)
+				break;
+			if (t_start + t_size > end)
+				t_size = end - t_start;
+
+			printk(KERN_CONT "\n  %010llx - %010llx pattern %d",
+				(unsigned long long)t_start,
+				(unsigned long long)t_start + t_size, pattern);
+
+			memtest(t_start, t_size, pattern);
+
+			t_start += t_size;
+		}
+	}
+	printk(KERN_CONT "\n");
+}
diff --git a/arch/x86/mm/mmio-mod.c b/arch/x86/mm/mmio-mod.c
index e7397e108be..2c4baa88f2c 100644
--- a/arch/x86/mm/mmio-mod.c
+++ b/arch/x86/mm/mmio-mod.c
@@ -56,13 +56,6 @@ struct remap_trace {
 static DEFINE_PER_CPU(struct trap_reason, pf_reason);
 static DEFINE_PER_CPU(struct mmiotrace_rw, cpu_trace);
 
-#if 0 /* XXX: no way gather this info anymore */
-/* Access to this is not per-cpu. */
-static DEFINE_PER_CPU(atomic_t, dropped);
-#endif
-
-static struct dentry *marker_file;
-
 static DEFINE_MUTEX(mmiotrace_mutex);
 static DEFINE_SPINLOCK(trace_lock);
 static atomic_t mmiotrace_enabled;
@@ -75,7 +68,7 @@ static LIST_HEAD(trace_list);		/* struct remap_trace */
  *   and trace_lock.
  * - Routines depending on is_enabled() must take trace_lock.
  * - trace_list users must hold trace_lock.
- * - is_enabled() guarantees that mmio_trace_record is allowed.
+ * - is_enabled() guarantees that mmio_trace_{rw,mapping} are allowed.
  * - pre/post callbacks assume the effect of is_enabled() being true.
  */
 
@@ -97,44 +90,6 @@ static bool is_enabled(void)
 	return atomic_read(&mmiotrace_enabled);
 }
 
-#if 0 /* XXX: needs rewrite */
-/*
- * Write callback for the debugfs entry:
- * Read a marker and write it to the mmio trace log
- */
-static ssize_t write_marker(struct file *file, const char __user *buffer,
-						size_t count, loff_t *ppos)
-{
-	char *event = NULL;
-	struct mm_io_header *headp;
-	ssize_t len = (count > 65535) ? 65535 : count;
-
-	event = kzalloc(sizeof(*headp) + len, GFP_KERNEL);
-	if (!event)
-		return -ENOMEM;
-
-	headp = (struct mm_io_header *)event;
-	headp->type = MMIO_MAGIC | (MMIO_MARKER << MMIO_OPCODE_SHIFT);
-	headp->data_len = len;
-
-	if (copy_from_user(event + sizeof(*headp), buffer, len)) {
-		kfree(event);
-		return -EFAULT;
-	}
-
-	spin_lock_irq(&trace_lock);
-#if 0 /* XXX: convert this to use tracing */
-	if (is_enabled())
-		relay_write(chan, event, sizeof(*headp) + len);
-	else
-#endif
-		len = -EINVAL;
-	spin_unlock_irq(&trace_lock);
-	kfree(event);
-	return len;
-}
-#endif
-
 static void print_pte(unsigned long address)
 {
 	unsigned int level;
@@ -307,8 +262,10 @@ static void ioremap_trace_core(resource_size_t offset, unsigned long size,
 	map.map_id = trace->id;
 
 	spin_lock_irq(&trace_lock);
-	if (!is_enabled())
+	if (!is_enabled()) {
+		kfree(trace);
 		goto not_enabled;
+	}
 
 	mmio_trace_mapping(&map);
 	list_add_tail(&trace->list, &trace_list);
@@ -377,6 +334,23 @@ void mmiotrace_iounmap(volatile void __iomem *addr)
 		iounmap_trace_core(addr);
 }
 
+int mmiotrace_printk(const char *fmt, ...)
+{
+	int ret = 0;
+	va_list args;
+	unsigned long flags;
+	va_start(args, fmt);
+
+	spin_lock_irqsave(&trace_lock, flags);
+	if (is_enabled())
+		ret = mmio_trace_printk(fmt, args);
+	spin_unlock_irqrestore(&trace_lock, flags);
+
+	va_end(args);
+	return ret;
+}
+EXPORT_SYMBOL(mmiotrace_printk);
+
 static void clear_trace_list(void)
 {
 	struct remap_trace *trace;
@@ -430,7 +404,9 @@ static void enter_uniprocessor(void)
 						"may miss events.\n");
 }
 
-static void leave_uniprocessor(void)
+/* __ref because leave_uniprocessor calls cpu_up which is __cpuinit,
+   but this whole function is ifdefed CONFIG_HOTPLUG_CPU */
+static void __ref leave_uniprocessor(void)
 {
 	int cpu;
 	int err;
@@ -460,26 +436,12 @@ static void leave_uniprocessor(void)
 }
 #endif
 
-#if 0 /* XXX: out of order */
-static struct file_operations fops_marker = {
-	.owner =	THIS_MODULE,
-	.write =	write_marker
-};
-#endif
-
 void enable_mmiotrace(void)
 {
 	mutex_lock(&mmiotrace_mutex);
 	if (is_enabled())
 		goto out;
 
-#if 0 /* XXX: tracing does not support text entries */
-	marker_file = debugfs_create_file("marker", 0660, dir, NULL,
-								&fops_marker);
-	if (!marker_file)
-		pr_err(NAME "marker file creation failed.\n");
-#endif
-
 	if (nommiotrace)
 		pr_info(NAME "MMIO tracing disabled.\n");
 	enter_uniprocessor();
@@ -504,11 +466,6 @@ void disable_mmiotrace(void)
 
 	clear_trace_list(); /* guarantees: no more kmmio callbacks */
 	leave_uniprocessor();
-	if (marker_file) {
-		debugfs_remove(marker_file);
-		marker_file = NULL;
-	}
-
 	pr_info(NAME "disabled.\n");
 out:
 	mutex_unlock(&mmiotrace_mutex);
diff --git a/arch/x86/mm/discontig_32.c b/arch/x86/mm/numa_32.c
index 5dfef9fa061..847c164725f 100644
--- a/arch/x86/mm/discontig_32.c
+++ b/arch/x86/mm/numa_32.c
@@ -42,7 +42,6 @@
 
 struct pglist_data *node_data[MAX_NUMNODES] __read_mostly;
 EXPORT_SYMBOL(node_data);
-static bootmem_data_t node0_bdata;
 
 /*
  * numa interface - we expect the numa architecture specific code to have
@@ -329,7 +328,7 @@ void __init initmem_init(unsigned long start_pfn,
 
 	get_memcfg_numa();
 
-	kva_pages = round_up(calculate_numa_remap_pages(), PTRS_PER_PTE);
+	kva_pages = roundup(calculate_numa_remap_pages(), PTRS_PER_PTE);
 
 	kva_target_pfn = round_down(max_low_pfn - kva_pages, PTRS_PER_PTE);
 	do {
@@ -385,7 +384,7 @@ void __init initmem_init(unsigned long start_pfn,
 	for_each_online_node(nid)
 		memset(NODE_DATA(nid), 0, sizeof(struct pglist_data));
 
-	NODE_DATA(0)->bdata = &node0_bdata;
+	NODE_DATA(0)->bdata = &bootmem_node_data[0];
 	setup_bootmem_allocator();
 }
 
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index b432d578177..cebcbf152d4 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -20,15 +20,9 @@
 #include <asm/acpi.h>
 #include <asm/k8.h>
 
-#ifndef Dprintk
-#define Dprintk(x...)
-#endif
-
 struct pglist_data *node_data[MAX_NUMNODES] __read_mostly;
 EXPORT_SYMBOL(node_data);
 
-static bootmem_data_t plat_node_bdata[MAX_NUMNODES];
-
 struct memnode memnode;
 
 s16 apicid_to_node[MAX_LOCAL_APIC] __cpuinitdata = {
@@ -85,7 +79,7 @@ static int __init allocate_cachealigned_memnodemap(void)
 		return 0;
 
 	addr = 0x8000;
-	nodemap_size = round_up(sizeof(s16) * memnodemapsize, L1_CACHE_BYTES);
+	nodemap_size = roundup(sizeof(s16) * memnodemapsize, L1_CACHE_BYTES);
 	nodemap_addr = find_e820_area(addr, max_pfn<<PAGE_SHIFT,
 				      nodemap_size, L1_CACHE_BYTES);
 	if (nodemap_addr == -1UL) {
@@ -182,10 +176,10 @@ void __init setup_node_bootmem(int nodeid, unsigned long start,
 	unsigned long start_pfn, last_pfn, bootmap_pages, bootmap_size;
 	unsigned long bootmap_start, nodedata_phys;
 	void *bootmap;
-	const int pgdat_size = round_up(sizeof(pg_data_t), PAGE_SIZE);
+	const int pgdat_size = roundup(sizeof(pg_data_t), PAGE_SIZE);
 	int nid;
 
-	start = round_up(start, ZONE_ALIGN);
+	start = roundup(start, ZONE_ALIGN);
 
 	printk(KERN_INFO "Bootmem setup node %d %016lx-%016lx\n", nodeid,
 	       start, end);
@@ -202,7 +196,7 @@ void __init setup_node_bootmem(int nodeid, unsigned long start,
 		nodedata_phys + pgdat_size - 1);
 
 	memset(NODE_DATA(nodeid), 0, sizeof(pg_data_t));
-	NODE_DATA(nodeid)->bdata = &plat_node_bdata[nodeid];
+	NODE_DATA(nodeid)->bdata = &bootmem_node_data[nodeid];
 	NODE_DATA(nodeid)->node_start_pfn = start_pfn;
 	NODE_DATA(nodeid)->node_spanned_pages = last_pfn - start_pfn;
 
@@ -216,9 +210,9 @@ void __init setup_node_bootmem(int nodeid, unsigned long start,
 	bootmap_pages = bootmem_bootmap_pages(last_pfn - start_pfn);
 	nid = phys_to_nid(nodedata_phys);
 	if (nid == nodeid)
-		bootmap_start = round_up(nodedata_phys + pgdat_size, PAGE_SIZE);
+		bootmap_start = roundup(nodedata_phys + pgdat_size, PAGE_SIZE);
 	else
-		bootmap_start = round_up(start, PAGE_SIZE);
+		bootmap_start = roundup(start, PAGE_SIZE);
 	/*
 	 * SMP_CACHE_BYTES could be enough, but init_bootmem_node like
 	 * to use that to align to PAGE_SIZE
diff --git a/arch/x86/mm/pageattr-test.c b/arch/x86/mm/pageattr-test.c
index 0dcd42eb94e..e1d10690921 100644
--- a/arch/x86/mm/pageattr-test.c
+++ b/arch/x86/mm/pageattr-test.c
@@ -32,7 +32,7 @@ enum {
 	GPS			= (1<<30)
 };
 
-#define PAGE_TESTBIT	__pgprot(_PAGE_UNUSED1)
+#define PAGE_CPA_TEST	__pgprot(_PAGE_CPA_TEST)
 
 static int pte_testbit(pte_t pte)
 {
@@ -118,6 +118,7 @@ static int pageattr_test(void)
 	unsigned int level;
 	int i, k;
 	int err;
+	unsigned long test_addr;
 
 	if (print)
 		printk(KERN_INFO "CPA self-test:\n");
@@ -172,7 +173,8 @@ static int pageattr_test(void)
 			continue;
 		}
 
-		err = change_page_attr_set(addr[i], len[i], PAGE_TESTBIT);
+		test_addr = addr[i];
+		err = change_page_attr_set(&test_addr, len[i], PAGE_CPA_TEST, 0);
 		if (err < 0) {
 			printk(KERN_ERR "CPA %d failed %d\n", i, err);
 			failed++;
@@ -204,7 +206,8 @@ static int pageattr_test(void)
 			failed++;
 			continue;
 		}
-		err = change_page_attr_clear(addr[i], len[i], PAGE_TESTBIT);
+		test_addr = addr[i];
+		err = change_page_attr_clear(&test_addr, len[i], PAGE_CPA_TEST, 0);
 		if (err < 0) {
 			printk(KERN_ERR "CPA reverting failed: %d\n", err);
 			failed++;
@@ -221,8 +224,7 @@ static int pageattr_test(void)
 	failed += print_split(&sc);
 
 	if (failed) {
-		printk(KERN_ERR "NOT PASSED. Please report.\n");
-		WARN_ON(1);
+		WARN(1, KERN_ERR "NOT PASSED. Please report.\n");
 		return -EINVAL;
 	} else {
 		if (print)
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 65c6e46bf05..f1dc1b75d16 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -25,15 +25,27 @@
  * The current flushing context - we pass it instead of 5 arguments:
  */
 struct cpa_data {
-	unsigned long	vaddr;
+	unsigned long	*vaddr;
 	pgprot_t	mask_set;
 	pgprot_t	mask_clr;
 	int		numpages;
-	int		flushtlb;
+	int		flags;
 	unsigned long	pfn;
 	unsigned	force_split : 1;
+	int		curpage;
 };
 
+/*
+ * Serialize cpa() (for !DEBUG_PAGEALLOC which uses large identity mappings)
+ * using cpa_lock. So that we don't allow any other cpu, with stale large tlb
+ * entries change the page attribute in parallel to some other cpu
+ * splitting a large page entry along with changing the attribute.
+ */
+static DEFINE_SPINLOCK(cpa_lock);
+
+#define CPA_FLUSHTLB 1
+#define CPA_ARRAY 2
+
 #ifdef CONFIG_PROC_FS
 static unsigned long direct_pages_count[PG_LEVEL_NUM];
 
@@ -53,17 +65,22 @@ static void split_page_count(int level)
 	direct_pages_count[level - 1] += PTRS_PER_PTE;
 }
 
-int arch_report_meminfo(char *page)
+void arch_report_meminfo(struct seq_file *m)
 {
-	int n = sprintf(page, "DirectMap4k:  %8lu\n"
-			"DirectMap2M:  %8lu\n",
-			direct_pages_count[PG_LEVEL_4K],
-			direct_pages_count[PG_LEVEL_2M]);
+	seq_printf(m, "DirectMap4k:  %8lu kB\n",
+			direct_pages_count[PG_LEVEL_4K] << 2);
+#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
+	seq_printf(m, "DirectMap2M:  %8lu kB\n",
+			direct_pages_count[PG_LEVEL_2M] << 11);
+#else
+	seq_printf(m, "DirectMap4M:  %8lu kB\n",
+			direct_pages_count[PG_LEVEL_2M] << 12);
+#endif
 #ifdef CONFIG_X86_64
-	n += sprintf(page + n, "DirectMap1G:  %8lu\n",
-		     direct_pages_count[PG_LEVEL_1G]);
+	if (direct_gbpages)
+		seq_printf(m, "DirectMap1G:  %8lu kB\n",
+			direct_pages_count[PG_LEVEL_1G] << 20);
 #endif
-	return n;
 }
 #else
 static inline void split_page_count(int level) { }
@@ -78,7 +95,7 @@ static inline unsigned long highmap_start_pfn(void)
 
 static inline unsigned long highmap_end_pfn(void)
 {
-	return __pa(round_up((unsigned long)_end, PMD_SIZE)) >> PAGE_SHIFT;
+	return __pa(roundup((unsigned long)_end, PMD_SIZE)) >> PAGE_SHIFT;
 }
 
 #endif
@@ -184,6 +201,41 @@ static void cpa_flush_range(unsigned long start, int numpages, int cache)
 	}
 }
 
+static void cpa_flush_array(unsigned long *start, int numpages, int cache)
+{
+	unsigned int i, level;
+	unsigned long *addr;
+
+	BUG_ON(irqs_disabled());
+
+	on_each_cpu(__cpa_flush_range, NULL, 1);
+
+	if (!cache)
+		return;
+
+	/* 4M threshold */
+	if (numpages >= 1024) {
+		if (boot_cpu_data.x86_model >= 4)
+			wbinvd();
+		return;
+	}
+	/*
+	 * We only need to flush on one CPU,
+	 * clflush is a MESI-coherent instruction that
+	 * will cause all other CPUs to flush the same
+	 * cachelines:
+	 */
+	for (i = 0, addr = start; i < numpages; i++, addr++) {
+		pte_t *pte = lookup_address(*addr, &level);
+
+		/*
+		 * Only flush present addresses:
+		 */
+		if (pte && (pte_val(*pte) & _PAGE_PRESENT))
+			clflush_cache_range((void *) *addr, PAGE_SIZE);
+	}
+}
+
 /*
  * Certain areas of memory on x86 require very specific protection flags,
  * for example the BIOS area or kernel text. Callers don't always get this
@@ -392,7 +444,7 @@ try_preserve_large_page(pte_t *kpte, unsigned long address,
 		 */
 		new_pte = pfn_pte(pte_pfn(old_pte), canon_pgprot(new_prot));
 		__set_pmd_pte(kpte, address, new_pte);
-		cpa->flushtlb = 1;
+		cpa->flags |= CPA_FLUSHTLB;
 		do_split = 0;
 	}
 
@@ -402,84 +454,6 @@ out_unlock:
 	return do_split;
 }
 
-static LIST_HEAD(page_pool);
-static unsigned long pool_size, pool_pages, pool_low;
-static unsigned long pool_used, pool_failed;
-
-static void cpa_fill_pool(struct page **ret)
-{
-	gfp_t gfp = GFP_KERNEL;
-	unsigned long flags;
-	struct page *p;
-
-	/*
-	 * Avoid recursion (on debug-pagealloc) and also signal
-	 * our priority to get to these pagetables:
-	 */
-	if (current->flags & PF_MEMALLOC)
-		return;
-	current->flags |= PF_MEMALLOC;
-
-	/*
-	 * Allocate atomically from atomic contexts:
-	 */
-	if (in_atomic() || irqs_disabled() || debug_pagealloc)
-		gfp =  GFP_ATOMIC | __GFP_NORETRY | __GFP_NOWARN;
-
-	while (pool_pages < pool_size || (ret && !*ret)) {
-		p = alloc_pages(gfp, 0);
-		if (!p) {
-			pool_failed++;
-			break;
-		}
-		/*
-		 * If the call site needs a page right now, provide it:
-		 */
-		if (ret && !*ret) {
-			*ret = p;
-			continue;
-		}
-		spin_lock_irqsave(&pgd_lock, flags);
-		list_add(&p->lru, &page_pool);
-		pool_pages++;
-		spin_unlock_irqrestore(&pgd_lock, flags);
-	}
-
-	current->flags &= ~PF_MEMALLOC;
-}
-
-#define SHIFT_MB		(20 - PAGE_SHIFT)
-#define ROUND_MB_GB		((1 << 10) - 1)
-#define SHIFT_MB_GB		10
-#define POOL_PAGES_PER_GB	16
-
-void __init cpa_init(void)
-{
-	struct sysinfo si;
-	unsigned long gb;
-
-	si_meminfo(&si);
-	/*
-	 * Calculate the number of pool pages:
-	 *
-	 * Convert totalram (nr of pages) to MiB and round to the next
-	 * GiB. Shift MiB to Gib and multiply the result by
-	 * POOL_PAGES_PER_GB:
-	 */
-	if (debug_pagealloc) {
-		gb = ((si.totalram >> SHIFT_MB) + ROUND_MB_GB) >> SHIFT_MB_GB;
-		pool_size = POOL_PAGES_PER_GB * gb;
-	} else {
-		pool_size = 1;
-	}
-	pool_low = pool_size;
-
-	cpa_fill_pool(NULL);
-	printk(KERN_DEBUG
-	       "CPA: page pool initialized %lu of %lu pages preallocated\n",
-	       pool_pages, pool_size);
-}
-
 static int split_large_page(pte_t *kpte, unsigned long address)
 {
 	unsigned long flags, pfn, pfninc = 1;
@@ -488,28 +462,15 @@ static int split_large_page(pte_t *kpte, unsigned long address)
 	pgprot_t ref_prot;
 	struct page *base;
 
-	/*
-	 * Get a page from the pool. The pool list is protected by the
-	 * pgd_lock, which we have to take anyway for the split
-	 * operation:
-	 */
-	spin_lock_irqsave(&pgd_lock, flags);
-	if (list_empty(&page_pool)) {
-		spin_unlock_irqrestore(&pgd_lock, flags);
-		base = NULL;
-		cpa_fill_pool(&base);
-		if (!base)
-			return -ENOMEM;
-		spin_lock_irqsave(&pgd_lock, flags);
-	} else {
-		base = list_first_entry(&page_pool, struct page, lru);
-		list_del(&base->lru);
-		pool_pages--;
-
-		if (pool_pages < pool_low)
-			pool_low = pool_pages;
-	}
+	if (!debug_pagealloc)
+		spin_unlock(&cpa_lock);
+	base = alloc_pages(GFP_KERNEL, 0);
+	if (!debug_pagealloc)
+		spin_lock(&cpa_lock);
+	if (!base)
+		return -ENOMEM;
 
+	spin_lock_irqsave(&pgd_lock, flags);
 	/*
 	 * Check for races, another CPU might have split this page
 	 * up for us already:
@@ -566,11 +527,8 @@ out_unlock:
 	 * If we dropped out via the lookup_address check under
 	 * pgd_lock then stick the page back into the pool:
 	 */
-	if (base) {
-		list_add(&base->lru, &page_pool);
-		pool_pages++;
-	} else
-		pool_used++;
+	if (base)
+		__free_page(base);
 	spin_unlock_irqrestore(&pgd_lock, flags);
 
 	return 0;
@@ -578,11 +536,16 @@ out_unlock:
 
 static int __change_page_attr(struct cpa_data *cpa, int primary)
 {
-	unsigned long address = cpa->vaddr;
+	unsigned long address;
 	int do_split, err;
 	unsigned int level;
 	pte_t *kpte, old_pte;
 
+	if (cpa->flags & CPA_ARRAY)
+		address = cpa->vaddr[cpa->curpage];
+	else
+		address = *cpa->vaddr;
+
 repeat:
 	kpte = lookup_address(address, &level);
 	if (!kpte)
@@ -592,10 +555,9 @@ repeat:
 	if (!pte_val(old_pte)) {
 		if (!primary)
 			return 0;
-		printk(KERN_WARNING "CPA: called for zero pte. "
+		WARN(1, KERN_WARNING "CPA: called for zero pte. "
 		       "vaddr = %lx cpa->vaddr = %lx\n", address,
-		       cpa->vaddr);
-		WARN_ON(1);
+		       *cpa->vaddr);
 		return -EINVAL;
 	}
 
@@ -621,7 +583,7 @@ repeat:
 		 */
 		if (pte_val(old_pte) != pte_val(new_pte)) {
 			set_pte_atomic(kpte, new_pte);
-			cpa->flushtlb = 1;
+			cpa->flags |= CPA_FLUSHTLB;
 		}
 		cpa->numpages = 1;
 		return 0;
@@ -645,7 +607,25 @@ repeat:
 	 */
 	err = split_large_page(kpte, address);
 	if (!err) {
-		cpa->flushtlb = 1;
+		/*
+	 	 * Do a global flush tlb after splitting the large page
+	 	 * and before we do the actual change page attribute in the PTE.
+	 	 *
+	 	 * With out this, we violate the TLB application note, that says
+	 	 * "The TLBs may contain both ordinary and large-page
+		 *  translations for a 4-KByte range of linear addresses. This
+		 *  may occur if software modifies the paging structures so that
+		 *  the page size used for the address range changes. If the two
+		 *  translations differ with respect to page frame or attributes
+		 *  (e.g., permissions), processor behavior is undefined and may
+		 *  be implementation-specific."
+	 	 *
+	 	 * We do this global tlb flush inside the cpa_lock, so that we
+		 * don't allow any other cpu, with stale tlb entries change the
+		 * page attribute in parallel, that also falls into the
+		 * just split large page entry.
+	 	 */
+		flush_tlb_all();
 		goto repeat;
 	}
 
@@ -658,6 +638,7 @@ static int cpa_process_alias(struct cpa_data *cpa)
 {
 	struct cpa_data alias_cpa;
 	int ret = 0;
+	unsigned long temp_cpa_vaddr, vaddr;
 
 	if (cpa->pfn >= max_pfn_mapped)
 		return 0;
@@ -670,16 +651,24 @@ static int cpa_process_alias(struct cpa_data *cpa)
 	 * No need to redo, when the primary call touched the direct
 	 * mapping already:
 	 */
-	if (!(within(cpa->vaddr, PAGE_OFFSET,
+	if (cpa->flags & CPA_ARRAY)
+		vaddr = cpa->vaddr[cpa->curpage];
+	else
+		vaddr = *cpa->vaddr;
+
+	if (!(within(vaddr, PAGE_OFFSET,
 		    PAGE_OFFSET + (max_low_pfn_mapped << PAGE_SHIFT))
 #ifdef CONFIG_X86_64
-		|| within(cpa->vaddr, PAGE_OFFSET + (1UL<<32),
+		|| within(vaddr, PAGE_OFFSET + (1UL<<32),
 		    PAGE_OFFSET + (max_pfn_mapped << PAGE_SHIFT))
 #endif
 	)) {
 
 		alias_cpa = *cpa;
-		alias_cpa.vaddr = (unsigned long) __va(cpa->pfn << PAGE_SHIFT);
+		temp_cpa_vaddr = (unsigned long) __va(cpa->pfn << PAGE_SHIFT);
+		alias_cpa.vaddr = &temp_cpa_vaddr;
+		alias_cpa.flags &= ~CPA_ARRAY;
+
 
 		ret = __change_page_attr_set_clr(&alias_cpa, 0);
 	}
@@ -691,7 +680,7 @@ static int cpa_process_alias(struct cpa_data *cpa)
 	 * No need to redo, when the primary call touched the high
 	 * mapping already:
 	 */
-	if (within(cpa->vaddr, (unsigned long) _text, (unsigned long) _end))
+	if (within(vaddr, (unsigned long) _text, (unsigned long) _end))
 		return 0;
 
 	/*
@@ -702,8 +691,9 @@ static int cpa_process_alias(struct cpa_data *cpa)
 		return 0;
 
 	alias_cpa = *cpa;
-	alias_cpa.vaddr =
-		(cpa->pfn << PAGE_SHIFT) + __START_KERNEL_map - phys_base;
+	temp_cpa_vaddr = (cpa->pfn << PAGE_SHIFT) + __START_KERNEL_map - phys_base;
+	alias_cpa.vaddr = &temp_cpa_vaddr;
+	alias_cpa.flags &= ~CPA_ARRAY;
 
 	/*
 	 * The high mapping range is imprecise, so ignore the return value.
@@ -723,8 +713,15 @@ static int __change_page_attr_set_clr(struct cpa_data *cpa, int checkalias)
 		 * preservation check.
 		 */
 		cpa->numpages = numpages;
+		/* for array changes, we can't use large page */
+		if (cpa->flags & CPA_ARRAY)
+			cpa->numpages = 1;
 
+		if (!debug_pagealloc)
+			spin_lock(&cpa_lock);
 		ret = __change_page_attr(cpa, checkalias);
+		if (!debug_pagealloc)
+			spin_unlock(&cpa_lock);
 		if (ret)
 			return ret;
 
@@ -741,7 +738,11 @@ static int __change_page_attr_set_clr(struct cpa_data *cpa, int checkalias)
 		 */
 		BUG_ON(cpa->numpages > numpages);
 		numpages -= cpa->numpages;
-		cpa->vaddr += cpa->numpages * PAGE_SIZE;
+		if (cpa->flags & CPA_ARRAY)
+			cpa->curpage++;
+		else
+			*cpa->vaddr += cpa->numpages * PAGE_SIZE;
+
 	}
 	return 0;
 }
@@ -752,9 +753,9 @@ static inline int cache_attr(pgprot_t attr)
 		(_PAGE_PAT | _PAGE_PAT_LARGE | _PAGE_PWT | _PAGE_PCD);
 }
 
-static int change_page_attr_set_clr(unsigned long addr, int numpages,
+static int change_page_attr_set_clr(unsigned long *addr, int numpages,
 				    pgprot_t mask_set, pgprot_t mask_clr,
-				    int force_split)
+				    int force_split, int array)
 {
 	struct cpa_data cpa;
 	int ret, cache, checkalias;
@@ -769,21 +770,40 @@ static int change_page_attr_set_clr(unsigned long addr, int numpages,
 		return 0;
 
 	/* Ensure we are PAGE_SIZE aligned */
-	if (addr & ~PAGE_MASK) {
-		addr &= PAGE_MASK;
-		/*
-		 * People should not be passing in unaligned addresses:
-		 */
-		WARN_ON_ONCE(1);
+	if (!array) {
+		if (*addr & ~PAGE_MASK) {
+			*addr &= PAGE_MASK;
+			/*
+			 * People should not be passing in unaligned addresses:
+			 */
+			WARN_ON_ONCE(1);
+		}
+	} else {
+		int i;
+		for (i = 0; i < numpages; i++) {
+			if (addr[i] & ~PAGE_MASK) {
+				addr[i] &= PAGE_MASK;
+				WARN_ON_ONCE(1);
+			}
+		}
 	}
 
+	/* Must avoid aliasing mappings in the highmem code */
+	kmap_flush_unused();
+
+	vm_unmap_aliases();
+
 	cpa.vaddr = addr;
 	cpa.numpages = numpages;
 	cpa.mask_set = mask_set;
 	cpa.mask_clr = mask_clr;
-	cpa.flushtlb = 0;
+	cpa.flags = 0;
+	cpa.curpage = 0;
 	cpa.force_split = force_split;
 
+	if (array)
+		cpa.flags |= CPA_ARRAY;
+
 	/* No alias checking for _NX bit modifications */
 	checkalias = (pgprot_val(mask_set) | pgprot_val(mask_clr)) != _PAGE_NX;
 
@@ -792,7 +812,7 @@ static int change_page_attr_set_clr(unsigned long addr, int numpages,
 	/*
 	 * Check whether we really changed something:
 	 */
-	if (!cpa.flushtlb)
+	if (!(cpa.flags & CPA_FLUSHTLB))
 		goto out;
 
 	/*
@@ -807,27 +827,30 @@ static int change_page_attr_set_clr(unsigned long addr, int numpages,
 	 * error case we fall back to cpa_flush_all (which uses
 	 * wbindv):
 	 */
-	if (!ret && cpu_has_clflush)
-		cpa_flush_range(addr, numpages, cache);
-	else
+	if (!ret && cpu_has_clflush) {
+		if (cpa.flags & CPA_ARRAY)
+			cpa_flush_array(addr, numpages, cache);
+		else
+			cpa_flush_range(*addr, numpages, cache);
+	} else
 		cpa_flush_all(cache);
 
 out:
-	cpa_fill_pool(NULL);
-
 	return ret;
 }
 
-static inline int change_page_attr_set(unsigned long addr, int numpages,
-				       pgprot_t mask)
+static inline int change_page_attr_set(unsigned long *addr, int numpages,
+				       pgprot_t mask, int array)
 {
-	return change_page_attr_set_clr(addr, numpages, mask, __pgprot(0), 0);
+	return change_page_attr_set_clr(addr, numpages, mask, __pgprot(0), 0,
+		array);
 }
 
-static inline int change_page_attr_clear(unsigned long addr, int numpages,
-					 pgprot_t mask)
+static inline int change_page_attr_clear(unsigned long *addr, int numpages,
+					 pgprot_t mask, int array)
 {
-	return change_page_attr_set_clr(addr, numpages, __pgprot(0), mask, 0);
+	return change_page_attr_set_clr(addr, numpages, __pgprot(0), mask, 0,
+		array);
 }
 
 int _set_memory_uc(unsigned long addr, int numpages)
@@ -835,8 +858,8 @@ int _set_memory_uc(unsigned long addr, int numpages)
 	/*
 	 * for now UC MINUS. see comments in ioremap_nocache()
 	 */
-	return change_page_attr_set(addr, numpages,
-				    __pgprot(_PAGE_CACHE_UC_MINUS));
+	return change_page_attr_set(&addr, numpages,
+				    __pgprot(_PAGE_CACHE_UC_MINUS), 0);
 }
 
 int set_memory_uc(unsigned long addr, int numpages)
@@ -844,7 +867,7 @@ int set_memory_uc(unsigned long addr, int numpages)
 	/*
 	 * for now UC MINUS. see comments in ioremap_nocache()
 	 */
-	if (reserve_memtype(addr, addr + numpages * PAGE_SIZE,
+	if (reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE,
 			    _PAGE_CACHE_UC_MINUS, NULL))
 		return -EINVAL;
 
@@ -852,10 +875,48 @@ int set_memory_uc(unsigned long addr, int numpages)
 }
 EXPORT_SYMBOL(set_memory_uc);
 
+int set_memory_array_uc(unsigned long *addr, int addrinarray)
+{
+	unsigned long start;
+	unsigned long end;
+	int i;
+	/*
+	 * for now UC MINUS. see comments in ioremap_nocache()
+	 */
+	for (i = 0; i < addrinarray; i++) {
+		start = __pa(addr[i]);
+		for (end = start + PAGE_SIZE; i < addrinarray - 1; end += PAGE_SIZE) {
+			if (end != __pa(addr[i + 1]))
+				break;
+			i++;
+		}
+		if (reserve_memtype(start, end, _PAGE_CACHE_UC_MINUS, NULL))
+			goto out;
+	}
+
+	return change_page_attr_set(addr, addrinarray,
+				    __pgprot(_PAGE_CACHE_UC_MINUS), 1);
+out:
+	for (i = 0; i < addrinarray; i++) {
+		unsigned long tmp = __pa(addr[i]);
+
+		if (tmp == start)
+			break;
+		for (end = tmp + PAGE_SIZE; i < addrinarray - 1; end += PAGE_SIZE) {
+			if (end != __pa(addr[i + 1]))
+				break;
+			i++;
+		}
+		free_memtype(tmp, end);
+	}
+	return -EINVAL;
+}
+EXPORT_SYMBOL(set_memory_array_uc);
+
 int _set_memory_wc(unsigned long addr, int numpages)
 {
-	return change_page_attr_set(addr, numpages,
-				    __pgprot(_PAGE_CACHE_WC));
+	return change_page_attr_set(&addr, numpages,
+				    __pgprot(_PAGE_CACHE_WC), 0);
 }
 
 int set_memory_wc(unsigned long addr, int numpages)
@@ -863,7 +924,7 @@ int set_memory_wc(unsigned long addr, int numpages)
 	if (!pat_enabled)
 		return set_memory_uc(addr, numpages);
 
-	if (reserve_memtype(addr, addr + numpages * PAGE_SIZE,
+	if (reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE,
 		_PAGE_CACHE_WC, NULL))
 		return -EINVAL;
 
@@ -873,49 +934,71 @@ EXPORT_SYMBOL(set_memory_wc);
 
 int _set_memory_wb(unsigned long addr, int numpages)
 {
-	return change_page_attr_clear(addr, numpages,
-				      __pgprot(_PAGE_CACHE_MASK));
+	return change_page_attr_clear(&addr, numpages,
+				      __pgprot(_PAGE_CACHE_MASK), 0);
 }
 
 int set_memory_wb(unsigned long addr, int numpages)
 {
-	free_memtype(addr, addr + numpages * PAGE_SIZE);
+	free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE);
 
 	return _set_memory_wb(addr, numpages);
 }
 EXPORT_SYMBOL(set_memory_wb);
 
+int set_memory_array_wb(unsigned long *addr, int addrinarray)
+{
+	int i;
+
+	for (i = 0; i < addrinarray; i++) {
+		unsigned long start = __pa(addr[i]);
+		unsigned long end;
+
+		for (end = start + PAGE_SIZE; i < addrinarray - 1; end += PAGE_SIZE) {
+			if (end != __pa(addr[i + 1]))
+				break;
+			i++;
+		}
+		free_memtype(start, end);
+	}
+	return change_page_attr_clear(addr, addrinarray,
+				      __pgprot(_PAGE_CACHE_MASK), 1);
+}
+EXPORT_SYMBOL(set_memory_array_wb);
+
 int set_memory_x(unsigned long addr, int numpages)
 {
-	return change_page_attr_clear(addr, numpages, __pgprot(_PAGE_NX));
+	return change_page_attr_clear(&addr, numpages, __pgprot(_PAGE_NX), 0);
 }
 EXPORT_SYMBOL(set_memory_x);
 
 int set_memory_nx(unsigned long addr, int numpages)
 {
-	return change_page_attr_set(addr, numpages, __pgprot(_PAGE_NX));
+	return change_page_attr_set(&addr, numpages, __pgprot(_PAGE_NX), 0);
 }
 EXPORT_SYMBOL(set_memory_nx);
 
 int set_memory_ro(unsigned long addr, int numpages)
 {
-	return change_page_attr_clear(addr, numpages, __pgprot(_PAGE_RW));
+	return change_page_attr_clear(&addr, numpages, __pgprot(_PAGE_RW), 0);
 }
+EXPORT_SYMBOL_GPL(set_memory_ro);
 
 int set_memory_rw(unsigned long addr, int numpages)
 {
-	return change_page_attr_set(addr, numpages, __pgprot(_PAGE_RW));
+	return change_page_attr_set(&addr, numpages, __pgprot(_PAGE_RW), 0);
 }
+EXPORT_SYMBOL_GPL(set_memory_rw);
 
 int set_memory_np(unsigned long addr, int numpages)
 {
-	return change_page_attr_clear(addr, numpages, __pgprot(_PAGE_PRESENT));
+	return change_page_attr_clear(&addr, numpages, __pgprot(_PAGE_PRESENT), 0);
 }
 
 int set_memory_4k(unsigned long addr, int numpages)
 {
-	return change_page_attr_set_clr(addr, numpages, __pgprot(0),
-					__pgprot(0), 1);
+	return change_page_attr_set_clr(&addr, numpages, __pgprot(0),
+					__pgprot(0), 1, 0);
 }
 
 int set_pages_uc(struct page *page, int numpages)
@@ -968,22 +1051,38 @@ int set_pages_rw(struct page *page, int numpages)
 
 static int __set_pages_p(struct page *page, int numpages)
 {
-	struct cpa_data cpa = { .vaddr = (unsigned long) page_address(page),
+	unsigned long tempaddr = (unsigned long) page_address(page);
+	struct cpa_data cpa = { .vaddr = &tempaddr,
 				.numpages = numpages,
 				.mask_set = __pgprot(_PAGE_PRESENT | _PAGE_RW),
-				.mask_clr = __pgprot(0)};
+				.mask_clr = __pgprot(0),
+				.flags = 0};
 
-	return __change_page_attr_set_clr(&cpa, 1);
+	/*
+	 * No alias checking needed for setting present flag. otherwise,
+	 * we may need to break large pages for 64-bit kernel text
+	 * mappings (this adds to complexity if we want to do this from
+	 * atomic context especially). Let's keep it simple!
+	 */
+	return __change_page_attr_set_clr(&cpa, 0);
 }
 
 static int __set_pages_np(struct page *page, int numpages)
 {
-	struct cpa_data cpa = { .vaddr = (unsigned long) page_address(page),
+	unsigned long tempaddr = (unsigned long) page_address(page);
+	struct cpa_data cpa = { .vaddr = &tempaddr,
 				.numpages = numpages,
 				.mask_set = __pgprot(0),
-				.mask_clr = __pgprot(_PAGE_PRESENT | _PAGE_RW)};
+				.mask_clr = __pgprot(_PAGE_PRESENT | _PAGE_RW),
+				.flags = 0};
 
-	return __change_page_attr_set_clr(&cpa, 1);
+	/*
+	 * No alias checking needed for setting not present flag. otherwise,
+	 * we may need to break large pages for 64-bit kernel text
+	 * mappings (this adds to complexity if we want to do this from
+	 * atomic context especially). Let's keep it simple!
+	 */
+	return __change_page_attr_set_clr(&cpa, 0);
 }
 
 void kernel_map_pages(struct page *page, int numpages, int enable)
@@ -1003,11 +1102,8 @@ void kernel_map_pages(struct page *page, int numpages, int enable)
 
 	/*
 	 * The return value is ignored as the calls cannot fail.
-	 * Large pages are kept enabled at boot time, and are
-	 * split up quickly with DEBUG_PAGEALLOC. If a splitup
-	 * fails here (due to temporary memory shortage) no damage
-	 * is done because we just keep the largepage intact up
-	 * to the next attempt when it will likely be split up:
+	 * Large pages for identity mappings are not used at boot time
+	 * and hence no memory allocations during large page split.
 	 */
 	if (enable)
 		__set_pages_p(page, numpages);
@@ -1019,53 +1115,8 @@ void kernel_map_pages(struct page *page, int numpages, int enable)
 	 * but that can deadlock->flush only current cpu:
 	 */
 	__flush_tlb_all();
-
-	/*
-	 * Try to refill the page pool here. We can do this only after
-	 * the tlb flush.
-	 */
-	cpa_fill_pool(NULL);
-}
-
-#ifdef CONFIG_DEBUG_FS
-static int dpa_show(struct seq_file *m, void *v)
-{
-	seq_puts(m, "DEBUG_PAGEALLOC\n");
-	seq_printf(m, "pool_size     : %lu\n", pool_size);
-	seq_printf(m, "pool_pages    : %lu\n", pool_pages);
-	seq_printf(m, "pool_low      : %lu\n", pool_low);
-	seq_printf(m, "pool_used     : %lu\n", pool_used);
-	seq_printf(m, "pool_failed   : %lu\n", pool_failed);
-
-	return 0;
 }
 
-static int dpa_open(struct inode *inode, struct file *filp)
-{
-	return single_open(filp, dpa_show, NULL);
-}
-
-static const struct file_operations dpa_fops = {
-	.open		= dpa_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
-static int __init debug_pagealloc_proc_init(void)
-{
-	struct dentry *de;
-
-	de = debugfs_create_file("debug_pagealloc", 0600, NULL, NULL,
-				 &dpa_fops);
-	if (!de)
-		return -ENOMEM;
-
-	return 0;
-}
-__initcall(debug_pagealloc_proc_init);
-#endif
-
 #ifdef CONFIG_HIBERNATION
 
 bool kernel_page_present(struct page *page)
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index d4585077977..738fd0f2495 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -7,22 +7,24 @@
  * Loosely based on earlier PAT patchset from Eric Biederman and Andi Kleen.
  */
 
-#include <linux/mm.h>
+#include <linux/seq_file.h>
+#include <linux/bootmem.h>
+#include <linux/debugfs.h>
 #include <linux/kernel.h>
 #include <linux/gfp.h>
+#include <linux/mm.h>
 #include <linux/fs.h>
-#include <linux/bootmem.h>
 
-#include <asm/msr.h>
-#include <asm/tlbflush.h>
+#include <asm/cacheflush.h>
 #include <asm/processor.h>
-#include <asm/page.h>
+#include <asm/tlbflush.h>
 #include <asm/pgtable.h>
-#include <asm/pat.h>
-#include <asm/e820.h>
-#include <asm/cacheflush.h>
 #include <asm/fcntl.h>
+#include <asm/e820.h>
 #include <asm/mtrr.h>
+#include <asm/page.h>
+#include <asm/msr.h>
+#include <asm/pat.h>
 #include <asm/io.h>
 
 #ifdef CONFIG_X86_PAT
@@ -44,6 +46,7 @@ early_param("nopat", nopat);
 
 
 static int debug_enable;
+
 static int __init pat_debug_setup(char *str)
 {
 	debug_enable = 1;
@@ -143,14 +146,14 @@ static char *cattr_name(unsigned long flags)
  */
 
 struct memtype {
-	u64 start;
-	u64 end;
-	unsigned long type;
-	struct list_head nd;
+	u64			start;
+	u64			end;
+	unsigned long		type;
+	struct list_head	nd;
 };
 
 static LIST_HEAD(memtype_list);
-static DEFINE_SPINLOCK(memtype_lock); 	/* protects memtype list */
+static DEFINE_SPINLOCK(memtype_lock);	/* protects memtype list */
 
 /*
  * Does intersection of PAT memory type and MTRR memory type and returns
@@ -178,8 +181,8 @@ static unsigned long pat_x_mtrr_type(u64 start, u64 end, unsigned long req_type)
 	return req_type;
 }
 
-static int chk_conflict(struct memtype *new, struct memtype *entry,
-			unsigned long *type)
+static int
+chk_conflict(struct memtype *new, struct memtype *entry, unsigned long *type)
 {
 	if (new->type != entry->type) {
 		if (type) {
@@ -205,6 +208,69 @@ static int chk_conflict(struct memtype *new, struct memtype *entry,
 	return -EBUSY;
 }
 
+static struct memtype *cached_entry;
+static u64 cached_start;
+
+/*
+ * For RAM pages, mark the pages as non WB memory type using
+ * PageNonWB (PG_arch_1). We allow only one set_memory_uc() or
+ * set_memory_wc() on a RAM page at a time before marking it as WB again.
+ * This is ok, because only one driver will be owning the page and
+ * doing set_memory_*() calls.
+ *
+ * For now, we use PageNonWB to track that the RAM page is being mapped
+ * as non WB. In future, we will have to use one more flag
+ * (or some other mechanism in page_struct) to distinguish between
+ * UC and WC mapping.
+ */
+static int reserve_ram_pages_type(u64 start, u64 end, unsigned long req_type,
+				  unsigned long *new_type)
+{
+	struct page *page;
+	u64 pfn, end_pfn;
+
+	for (pfn = (start >> PAGE_SHIFT); pfn < (end >> PAGE_SHIFT); ++pfn) {
+		page = pfn_to_page(pfn);
+		if (page_mapped(page) || PageNonWB(page))
+			goto out;
+
+		SetPageNonWB(page);
+	}
+	return 0;
+
+out:
+	end_pfn = pfn;
+	for (pfn = (start >> PAGE_SHIFT); pfn < end_pfn; ++pfn) {
+		page = pfn_to_page(pfn);
+		ClearPageNonWB(page);
+	}
+
+	return -EINVAL;
+}
+
+static int free_ram_pages_type(u64 start, u64 end)
+{
+	struct page *page;
+	u64 pfn, end_pfn;
+
+	for (pfn = (start >> PAGE_SHIFT); pfn < (end >> PAGE_SHIFT); ++pfn) {
+		page = pfn_to_page(pfn);
+		if (page_mapped(page) || !PageNonWB(page))
+			goto out;
+
+		ClearPageNonWB(page);
+	}
+	return 0;
+
+out:
+	end_pfn = pfn;
+	for (pfn = (start >> PAGE_SHIFT); pfn < end_pfn; ++pfn) {
+		page = pfn_to_page(pfn);
+		SetPageNonWB(page);
+	}
+	return -EINVAL;
+}
+
 /*
  * req_type typically has one of the:
  * - _PAGE_CACHE_WB
@@ -221,14 +287,15 @@ static int chk_conflict(struct memtype *new, struct memtype *entry,
  * it will return a negative return value.
  */
 int reserve_memtype(u64 start, u64 end, unsigned long req_type,
-			unsigned long *new_type)
+		    unsigned long *new_type)
 {
 	struct memtype *new, *entry;
 	unsigned long actual_type;
 	struct list_head *where;
+	int is_range_ram;
 	int err = 0;
 
- 	BUG_ON(start >= end); /* end is exclusive */
+	BUG_ON(start >= end); /* end is exclusive */
 
 	if (!pat_enabled) {
 		/* This is identical to page table setting without PAT */
@@ -261,28 +328,41 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 			actual_type = _PAGE_CACHE_WB;
 		else
 			actual_type = _PAGE_CACHE_UC_MINUS;
-	} else
+	} else {
 		actual_type = pat_x_mtrr_type(start, end,
 					      req_type & _PAGE_CACHE_MASK);
+	}
+
+	is_range_ram = pagerange_is_ram(start, end);
+	if (is_range_ram == 1)
+		return reserve_ram_pages_type(start, end, req_type, new_type);
+	else if (is_range_ram < 0)
+		return -EINVAL;
 
 	new  = kmalloc(sizeof(struct memtype), GFP_KERNEL);
 	if (!new)
 		return -ENOMEM;
 
-	new->start = start;
-	new->end = end;
-	new->type = actual_type;
+	new->start	= start;
+	new->end	= end;
+	new->type	= actual_type;
 
 	if (new_type)
 		*new_type = actual_type;
 
 	spin_lock(&memtype_lock);
 
+	if (cached_entry && start >= cached_start)
+		entry = cached_entry;
+	else
+		entry = list_entry(&memtype_list, struct memtype, nd);
+
 	/* Search for existing mapping that overlaps the current range */
 	where = NULL;
-	list_for_each_entry(entry, &memtype_list, nd) {
+	list_for_each_entry_continue(entry, &memtype_list, nd) {
 		if (end <= entry->start) {
 			where = entry->nd.prev;
+			cached_entry = list_entry(where, struct memtype, nd);
 			break;
 		} else if (start <= entry->start) { /* end > entry->start */
 			err = chk_conflict(new, entry, new_type);
@@ -290,6 +370,8 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 				dprintk("Overlap at 0x%Lx-0x%Lx\n",
 					entry->start, entry->end);
 				where = entry->nd.prev;
+				cached_entry = list_entry(where,
+							struct memtype, nd);
 			}
 			break;
 		} else if (start < entry->end) { /* start > entry->start */
@@ -297,7 +379,20 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 			if (!err) {
 				dprintk("Overlap at 0x%Lx-0x%Lx\n",
 					entry->start, entry->end);
-				where = &entry->nd;
+				cached_entry = list_entry(entry->nd.prev,
+							struct memtype, nd);
+
+				/*
+				 * Move to right position in the linked
+				 * list to add this new entry
+				 */
+				list_for_each_entry_continue(entry,
+							&memtype_list, nd) {
+					if (start <= entry->start) {
+						where = entry->nd.prev;
+						break;
+					}
+				}
 			}
 			break;
 		}
@@ -309,9 +404,12 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 		       start, end, cattr_name(new->type), cattr_name(req_type));
 		kfree(new);
 		spin_unlock(&memtype_lock);
+
 		return err;
 	}
 
+	cached_start = start;
+
 	if (where)
 		list_add(&new->nd, where);
 	else
@@ -330,6 +428,7 @@ int free_memtype(u64 start, u64 end)
 {
 	struct memtype *entry;
 	int err = -EINVAL;
+	int is_range_ram;
 
 	if (!pat_enabled)
 		return 0;
@@ -338,9 +437,18 @@ int free_memtype(u64 start, u64 end)
 	if (is_ISA_range(start, end - 1))
 		return 0;
 
+	is_range_ram = pagerange_is_ram(start, end);
+	if (is_range_ram == 1)
+		return free_ram_pages_type(start, end);
+	else if (is_range_ram < 0)
+		return -EINVAL;
+
 	spin_lock(&memtype_lock);
 	list_for_each_entry(entry, &memtype_list, nd) {
 		if (entry->start == start && entry->end == end) {
+			if (cached_entry == entry || cached_start == start)
+				cached_entry = NULL;
+
 			list_del(&entry->nd);
 			kfree(entry);
 			err = 0;
@@ -355,26 +463,19 @@ int free_memtype(u64 start, u64 end)
 	}
 
 	dprintk("free_memtype request 0x%Lx-0x%Lx\n", start, end);
+
 	return err;
 }
 
 
-/*
- * /dev/mem mmap interface. The memtype used for mapping varies:
- * - Use UC for mappings with O_SYNC flag
- * - Without O_SYNC flag, if there is any conflict in reserve_memtype,
- *   inherit the memtype from existing mapping.
- * - Else use UC_MINUS memtype (for backward compatibility with existing
- *   X drivers.
- */
 pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
 				unsigned long size, pgprot_t vma_prot)
 {
 	return vma_prot;
 }
 
-#ifdef CONFIG_NONPROMISC_DEVMEM
-/* This check is done in drivers/char/mem.c in case of NONPROMISC_DEVMEM*/
+#ifdef CONFIG_STRICT_DEVMEM
+/* This check is done in drivers/char/mem.c in case of STRICT_DEVMEM*/
 static inline int range_is_allowed(unsigned long pfn, unsigned long size)
 {
 	return 1;
@@ -398,20 +499,20 @@ static inline int range_is_allowed(unsigned long pfn, unsigned long size)
 	}
 	return 1;
 }
-#endif /* CONFIG_NONPROMISC_DEVMEM */
+#endif /* CONFIG_STRICT_DEVMEM */
 
 int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
 				unsigned long size, pgprot_t *vma_prot)
 {
 	u64 offset = ((u64) pfn) << PAGE_SHIFT;
-	unsigned long flags = _PAGE_CACHE_UC_MINUS;
+	unsigned long flags = -1;
 	int retval;
 
 	if (!range_is_allowed(pfn, size))
 		return 0;
 
 	if (file->f_flags & O_SYNC) {
-		flags = _PAGE_CACHE_UC;
+		flags = _PAGE_CACHE_UC_MINUS;
 	}
 
 #ifdef CONFIG_X86_32
@@ -434,13 +535,14 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
 #endif
 
 	/*
-	 * With O_SYNC, we can only take UC mapping. Fail if we cannot.
+	 * With O_SYNC, we can only take UC_MINUS mapping. Fail if we cannot.
+	 *
 	 * Without O_SYNC, we want to get
 	 * - WB for WB-able memory and no other conflicting mappings
 	 * - UC_MINUS for non-WB-able memory with no other conflicting mappings
 	 * - Inherit from confliting mappings otherwise
 	 */
-	if (flags != _PAGE_CACHE_UC_MINUS) {
+	if (flags != -1) {
 		retval = reserve_memtype(offset, offset + size, flags, NULL);
 	} else {
 		retval = reserve_memtype(offset, offset + size, -1, &flags);
@@ -468,9 +570,9 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
 
 void map_devmem(unsigned long pfn, unsigned long size, pgprot_t vma_prot)
 {
+	unsigned long want_flags = (pgprot_val(vma_prot) & _PAGE_CACHE_MASK);
 	u64 addr = (u64)pfn << PAGE_SHIFT;
 	unsigned long flags;
-	unsigned long want_flags = (pgprot_val(vma_prot) & _PAGE_CACHE_MASK);
 
 	reserve_memtype(addr, addr + size, want_flags, &flags);
 	if (flags != want_flags) {
@@ -489,3 +591,91 @@ void unmap_devmem(unsigned long pfn, unsigned long size, pgprot_t vma_prot)
 
 	free_memtype(addr, addr + size);
 }
+
+#if defined(CONFIG_DEBUG_FS) && defined(CONFIG_X86_PAT)
+
+/* get Nth element of the linked list */
+static struct memtype *memtype_get_idx(loff_t pos)
+{
+	struct memtype *list_node, *print_entry;
+	int i = 1;
+
+	print_entry  = kmalloc(sizeof(struct memtype), GFP_KERNEL);
+	if (!print_entry)
+		return NULL;
+
+	spin_lock(&memtype_lock);
+	list_for_each_entry(list_node, &memtype_list, nd) {
+		if (pos == i) {
+			*print_entry = *list_node;
+			spin_unlock(&memtype_lock);
+			return print_entry;
+		}
+		++i;
+	}
+	spin_unlock(&memtype_lock);
+	kfree(print_entry);
+
+	return NULL;
+}
+
+static void *memtype_seq_start(struct seq_file *seq, loff_t *pos)
+{
+	if (*pos == 0) {
+		++*pos;
+		seq_printf(seq, "PAT memtype list:\n");
+	}
+
+	return memtype_get_idx(*pos);
+}
+
+static void *memtype_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	++*pos;
+	return memtype_get_idx(*pos);
+}
+
+static void memtype_seq_stop(struct seq_file *seq, void *v)
+{
+}
+
+static int memtype_seq_show(struct seq_file *seq, void *v)
+{
+	struct memtype *print_entry = (struct memtype *)v;
+
+	seq_printf(seq, "%s @ 0x%Lx-0x%Lx\n", cattr_name(print_entry->type),
+			print_entry->start, print_entry->end);
+	kfree(print_entry);
+
+	return 0;
+}
+
+static struct seq_operations memtype_seq_ops = {
+	.start = memtype_seq_start,
+	.next  = memtype_seq_next,
+	.stop  = memtype_seq_stop,
+	.show  = memtype_seq_show,
+};
+
+static int memtype_seq_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &memtype_seq_ops);
+}
+
+static const struct file_operations memtype_fops = {
+	.open    = memtype_seq_open,
+	.read    = seq_read,
+	.llseek  = seq_lseek,
+	.release = seq_release,
+};
+
+static int __init pat_memtype_list_init(void)
+{
+	debugfs_create_file("pat_memtype_list", S_IRUSR, arch_debugfs_dir,
+				NULL, &memtype_fops);
+	return 0;
+}
+
+late_initcall(pat_memtype_list_init);
+
+#endif /* CONFIG_DEBUG_FS && CONFIG_X86_PAT */
diff --git a/arch/x86/mm/pf_in.c b/arch/x86/mm/pf_in.c
index efa1911e20c..df3d5c861cd 100644
--- a/arch/x86/mm/pf_in.c
+++ b/arch/x86/mm/pf_in.c
@@ -79,25 +79,34 @@ static unsigned int mw32[] = { 0xC7 };
 static unsigned int mw64[] = { 0x89, 0x8B };
 #endif /* not __i386__ */
 
-static int skip_prefix(unsigned char *addr, int *shorted, int *enlarged,
-								int *rexr)
+struct prefix_bits {
+	unsigned shorted:1;
+	unsigned enlarged:1;
+	unsigned rexr:1;
+	unsigned rex:1;
+};
+
+static int skip_prefix(unsigned char *addr, struct prefix_bits *prf)
 {
 	int i;
 	unsigned char *p = addr;
-	*shorted = 0;
-	*enlarged = 0;
-	*rexr = 0;
+	prf->shorted = 0;
+	prf->enlarged = 0;
+	prf->rexr = 0;
+	prf->rex = 0;
 
 restart:
 	for (i = 0; i < ARRAY_SIZE(prefix_codes); i++) {
 		if (*p == prefix_codes[i]) {
 			if (*p == 0x66)
-				*shorted = 1;
+				prf->shorted = 1;
 #ifdef __amd64__
 			if ((*p & 0xf8) == 0x48)
-				*enlarged = 1;
+				prf->enlarged = 1;
 			if ((*p & 0xf4) == 0x44)
-				*rexr = 1;
+				prf->rexr = 1;
+			if ((*p & 0xf0) == 0x40)
+				prf->rex = 1;
 #endif
 			p++;
 			goto restart;
@@ -135,12 +144,12 @@ enum reason_type get_ins_type(unsigned long ins_addr)
 {
 	unsigned int opcode;
 	unsigned char *p;
-	int shorted, enlarged, rexr;
+	struct prefix_bits prf;
 	int i;
 	enum reason_type rv = OTHERS;
 
 	p = (unsigned char *)ins_addr;
-	p += skip_prefix(p, &shorted, &enlarged, &rexr);
+	p += skip_prefix(p, &prf);
 	p += get_opcode(p, &opcode);
 
 	CHECK_OP_TYPE(opcode, reg_rop, REG_READ);
@@ -156,10 +165,11 @@ static unsigned int get_ins_reg_width(unsigned long ins_addr)
 {
 	unsigned int opcode;
 	unsigned char *p;
-	int i, shorted, enlarged, rexr;
+	struct prefix_bits prf;
+	int i;
 
 	p = (unsigned char *)ins_addr;
-	p += skip_prefix(p, &shorted, &enlarged, &rexr);
+	p += skip_prefix(p, &prf);
 	p += get_opcode(p, &opcode);
 
 	for (i = 0; i < ARRAY_SIZE(rw8); i++)
@@ -168,7 +178,7 @@ static unsigned int get_ins_reg_width(unsigned long ins_addr)
 
 	for (i = 0; i < ARRAY_SIZE(rw32); i++)
 		if (rw32[i] == opcode)
-			return (shorted ? 2 : (enlarged ? 8 : 4));
+			return prf.shorted ? 2 : (prf.enlarged ? 8 : 4);
 
 	printk(KERN_ERR "mmiotrace: Unknown opcode 0x%02x\n", opcode);
 	return 0;
@@ -178,10 +188,11 @@ unsigned int get_ins_mem_width(unsigned long ins_addr)
 {
 	unsigned int opcode;
 	unsigned char *p;
-	int i, shorted, enlarged, rexr;
+	struct prefix_bits prf;
+	int i;
 
 	p = (unsigned char *)ins_addr;
-	p += skip_prefix(p, &shorted, &enlarged, &rexr);
+	p += skip_prefix(p, &prf);
 	p += get_opcode(p, &opcode);
 
 	for (i = 0; i < ARRAY_SIZE(mw8); i++)
@@ -194,11 +205,11 @@ unsigned int get_ins_mem_width(unsigned long ins_addr)
 
 	for (i = 0; i < ARRAY_SIZE(mw32); i++)
 		if (mw32[i] == opcode)
-			return shorted ? 2 : 4;
+			return prf.shorted ? 2 : 4;
 
 	for (i = 0; i < ARRAY_SIZE(mw64); i++)
 		if (mw64[i] == opcode)
-			return shorted ? 2 : (enlarged ? 8 : 4);
+			return prf.shorted ? 2 : (prf.enlarged ? 8 : 4);
 
 	printk(KERN_ERR "mmiotrace: Unknown opcode 0x%02x\n", opcode);
 	return 0;
@@ -238,7 +249,7 @@ enum {
 #endif
 };
 
-static unsigned char *get_reg_w8(int no, struct pt_regs *regs)
+static unsigned char *get_reg_w8(int no, int rex, struct pt_regs *regs)
 {
 	unsigned char *rv = NULL;
 
@@ -255,18 +266,6 @@ static unsigned char *get_reg_w8(int no, struct pt_regs *regs)
 	case arg_DL:
 		rv = (unsigned char *)&regs->dx;
 		break;
-	case arg_AH:
-		rv = 1 + (unsigned char *)&regs->ax;
-		break;
-	case arg_BH:
-		rv = 1 + (unsigned char *)&regs->bx;
-		break;
-	case arg_CH:
-		rv = 1 + (unsigned char *)&regs->cx;
-		break;
-	case arg_DH:
-		rv = 1 + (unsigned char *)&regs->dx;
-		break;
 #ifdef __amd64__
 	case arg_R8:
 		rv = (unsigned char *)&regs->r8;
@@ -294,9 +293,55 @@ static unsigned char *get_reg_w8(int no, struct pt_regs *regs)
 		break;
 #endif
 	default:
-		printk(KERN_ERR "mmiotrace: Error reg no# %d\n", no);
 		break;
 	}
+
+	if (rv)
+		return rv;
+
+	if (rex) {
+		/*
+		 * If REX prefix exists, access low bytes of SI etc.
+		 * instead of AH etc.
+		 */
+		switch (no) {
+		case arg_SI:
+			rv = (unsigned char *)&regs->si;
+			break;
+		case arg_DI:
+			rv = (unsigned char *)&regs->di;
+			break;
+		case arg_BP:
+			rv = (unsigned char *)&regs->bp;
+			break;
+		case arg_SP:
+			rv = (unsigned char *)&regs->sp;
+			break;
+		default:
+			break;
+		}
+	} else {
+		switch (no) {
+		case arg_AH:
+			rv = 1 + (unsigned char *)&regs->ax;
+			break;
+		case arg_BH:
+			rv = 1 + (unsigned char *)&regs->bx;
+			break;
+		case arg_CH:
+			rv = 1 + (unsigned char *)&regs->cx;
+			break;
+		case arg_DH:
+			rv = 1 + (unsigned char *)&regs->dx;
+			break;
+		default:
+			break;
+		}
+	}
+
+	if (!rv)
+		printk(KERN_ERR "mmiotrace: Error reg no# %d\n", no);
+
 	return rv;
 }
 
@@ -368,11 +413,12 @@ unsigned long get_ins_reg_val(unsigned long ins_addr, struct pt_regs *regs)
 	unsigned char mod_rm;
 	int reg;
 	unsigned char *p;
-	int i, shorted, enlarged, rexr;
+	struct prefix_bits prf;
+	int i;
 	unsigned long rv;
 
 	p = (unsigned char *)ins_addr;
-	p += skip_prefix(p, &shorted, &enlarged, &rexr);
+	p += skip_prefix(p, &prf);
 	p += get_opcode(p, &opcode);
 	for (i = 0; i < ARRAY_SIZE(reg_rop); i++)
 		if (reg_rop[i] == opcode) {
@@ -392,10 +438,10 @@ unsigned long get_ins_reg_val(unsigned long ins_addr, struct pt_regs *regs)
 
 do_work:
 	mod_rm = *p;
-	reg = ((mod_rm >> 3) & 0x7) | (rexr << 3);
+	reg = ((mod_rm >> 3) & 0x7) | (prf.rexr << 3);
 	switch (get_ins_reg_width(ins_addr)) {
 	case 1:
-		return *get_reg_w8(reg, regs);
+		return *get_reg_w8(reg, prf.rex, regs);
 
 	case 2:
 		return *(unsigned short *)get_reg_w32(reg, regs);
@@ -422,11 +468,12 @@ unsigned long get_ins_imm_val(unsigned long ins_addr)
 	unsigned char mod_rm;
 	unsigned char mod;
 	unsigned char *p;
-	int i, shorted, enlarged, rexr;
+	struct prefix_bits prf;
+	int i;
 	unsigned long rv;
 
 	p = (unsigned char *)ins_addr;
-	p += skip_prefix(p, &shorted, &enlarged, &rexr);
+	p += skip_prefix(p, &prf);
 	p += get_opcode(p, &opcode);
 	for (i = 0; i < ARRAY_SIZE(imm_wop); i++)
 		if (imm_wop[i] == opcode) {
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 557b2abceef..86f2ffc43c3 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -63,10 +63,8 @@ static inline void pgd_list_del(pgd_t *pgd)
 #define UNSHARED_PTRS_PER_PGD				\
 	(SHARED_KERNEL_PMD ? KERNEL_PGD_BOUNDARY : PTRS_PER_PGD)
 
-static void pgd_ctor(void *p)
+static void pgd_ctor(pgd_t *pgd)
 {
-	pgd_t *pgd = p;
-
 	/* If the pgd points to a shared pagetable level (either the
 	   ptes in non-PAE, or shared PMD in PAE), then just copy the
 	   references from swapper_pg_dir. */
@@ -87,7 +85,7 @@ static void pgd_ctor(void *p)
 		pgd_list_add(pgd);
 }
 
-static void pgd_dtor(void *pgd)
+static void pgd_dtor(pgd_t *pgd)
 {
 	unsigned long flags; /* can be called from interrupt context */
 
@@ -207,6 +205,9 @@ static void pgd_prepopulate_pmd(struct mm_struct *mm, pgd_t *pgd, pmd_t *pmds[])
 	unsigned long addr;
 	int i;
 
+	if (PREALLOCATED_PMDS == 0) /* Work around gcc-3.4.x bug */
+		return;
+
 	pud = pud_offset(pgd, 0);
 
  	for (addr = i = 0; i < PREALLOCATED_PMDS;
diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c
index b4becbf8c57..0951db9ee51 100644
--- a/arch/x86/mm/pgtable_32.c
+++ b/arch/x86/mm/pgtable_32.c
@@ -20,53 +20,6 @@
 #include <asm/tlb.h>
 #include <asm/tlbflush.h>
 
-void show_mem(void)
-{
-	int total = 0, reserved = 0;
-	int shared = 0, cached = 0;
-	int highmem = 0;
-	struct page *page;
-	pg_data_t *pgdat;
-	unsigned long i;
-	unsigned long flags;
-
-	printk(KERN_INFO "Mem-info:\n");
-	show_free_areas();
-	for_each_online_pgdat(pgdat) {
-		pgdat_resize_lock(pgdat, &flags);
-		for (i = 0; i < pgdat->node_spanned_pages; ++i) {
-			if (unlikely(i % MAX_ORDER_NR_PAGES == 0))
-				touch_nmi_watchdog();
-			page = pgdat_page_nr(pgdat, i);
-			total++;
-			if (PageHighMem(page))
-				highmem++;
-			if (PageReserved(page))
-				reserved++;
-			else if (PageSwapCache(page))
-				cached++;
-			else if (page_count(page))
-				shared += page_count(page) - 1;
-		}
-		pgdat_resize_unlock(pgdat, &flags);
-	}
-	printk(KERN_INFO "%d pages of RAM\n", total);
-	printk(KERN_INFO "%d pages of HIGHMEM\n", highmem);
-	printk(KERN_INFO "%d reserved pages\n", reserved);
-	printk(KERN_INFO "%d pages shared\n", shared);
-	printk(KERN_INFO "%d pages swap cached\n", cached);
-
-	printk(KERN_INFO "%lu pages dirty\n", global_page_state(NR_FILE_DIRTY));
-	printk(KERN_INFO "%lu pages writeback\n",
-					global_page_state(NR_WRITEBACK));
-	printk(KERN_INFO "%lu pages mapped\n", global_page_state(NR_FILE_MAPPED));
-	printk(KERN_INFO "%lu pages slab\n",
-		global_page_state(NR_SLAB_RECLAIMABLE) +
-		global_page_state(NR_SLAB_UNRECLAIMABLE));
-	printk(KERN_INFO "%lu pages pagetables\n",
-					global_page_state(NR_PAGETABLE));
-}
-
 /*
  * Associate a virtual page frame with a given physical page frame 
  * and protection flags for that frame.
@@ -170,7 +123,8 @@ static int __init parse_vmalloc(char *arg)
 	if (!arg)
 		return -EINVAL;
 
-	__VMALLOC_RESERVE = memparse(arg, &arg);
+	/* Add VMALLOC_OFFSET to the parsed value due to vm area guard hole*/
+	__VMALLOC_RESERVE = memparse(arg, &arg) + VMALLOC_OFFSET;
 	return 0;
 }
 early_param("vmalloc", parse_vmalloc);
diff --git a/arch/x86/mm/srat_32.c b/arch/x86/mm/srat_32.c
index 1eb2973a301..16ae70fc57e 100644
--- a/arch/x86/mm/srat_32.c
+++ b/arch/x86/mm/srat_32.c
@@ -178,7 +178,7 @@ void acpi_numa_arch_fixup(void)
  * start of the node, and that the current "end" address is after
  * the previous one.
  */
-static __init void node_read_chunk(int nid, struct node_memory_chunk_s *memory_chunk)
+static __init int node_read_chunk(int nid, struct node_memory_chunk_s *memory_chunk)
 {
 	/*
 	 * Only add present memory as told by the e820.
@@ -189,10 +189,10 @@ static __init void node_read_chunk(int nid, struct node_memory_chunk_s *memory_c
 	if (memory_chunk->start_pfn >= max_pfn) {
 		printk(KERN_INFO "Ignoring SRAT pfns: %08lx - %08lx\n",
 			memory_chunk->start_pfn, memory_chunk->end_pfn);
-		return;
+		return -1;
 	}
 	if (memory_chunk->nid != nid)
-		return;
+		return -1;
 
 	if (!node_has_online_mem(nid))
 		node_start_pfn[nid] = memory_chunk->start_pfn;
@@ -202,6 +202,8 @@ static __init void node_read_chunk(int nid, struct node_memory_chunk_s *memory_c
 
 	if (node_end_pfn[nid] < memory_chunk->end_pfn)
 		node_end_pfn[nid] = memory_chunk->end_pfn;
+
+	return 0;
 }
 
 int __init get_memcfg_from_srat(void)
@@ -259,7 +261,9 @@ int __init get_memcfg_from_srat(void)
 		printk(KERN_DEBUG
 			"chunk %d nid %d start_pfn %08lx end_pfn %08lx\n",
 		       j, chunk->nid, chunk->start_pfn, chunk->end_pfn);
-		node_read_chunk(chunk->nid, chunk);
+		if (node_read_chunk(chunk->nid, chunk))
+			continue;
+
 		e820_register_active_regions(chunk->nid, chunk->start_pfn,
 					     min(chunk->end_pfn, max_pfn));
 	}
diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c
index 1b4763e26ea..51c0a2fc14f 100644
--- a/arch/x86/mm/srat_64.c
+++ b/arch/x86/mm/srat_64.c
@@ -138,7 +138,7 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa)
 		return;
 	}
 
-	if (is_uv_system())
+	if (get_uv_system_type() >= UV_X2APIC)
 		apic_id = (pa->apic_id << 8) | pa->local_sapic_eid;
 	else
 		apic_id = pa->apic_id;
diff --git a/arch/x86/mm/testmmiotrace.c b/arch/x86/mm/testmmiotrace.c
index d877c5b423e..ab50a8d7402 100644
--- a/arch/x86/mm/testmmiotrace.c
+++ b/arch/x86/mm/testmmiotrace.c
@@ -3,6 +3,7 @@
  */
 #include <linux/module.h>
 #include <linux/io.h>
+#include <linux/mmiotrace.h>
 
 #define MODULE_NAME "testmmiotrace"
 
@@ -13,6 +14,7 @@ MODULE_PARM_DESC(mmio_address, "Start address of the mapping of 16 kB.");
 static void do_write_test(void __iomem *p)
 {
 	unsigned int i;
+	mmiotrace_printk("Write test.\n");
 	for (i = 0; i < 256; i++)
 		iowrite8(i, p + i);
 	for (i = 1024; i < (5 * 1024); i += 2)
@@ -24,6 +26,7 @@ static void do_write_test(void __iomem *p)
 static void do_read_test(void __iomem *p)
 {
 	unsigned int i;
+	mmiotrace_printk("Read test.\n");
 	for (i = 0; i < 256; i++)
 		ioread8(p + i);
 	for (i = 1024; i < (5 * 1024); i += 2)
@@ -39,6 +42,7 @@ static void do_test(void)
 		pr_err(MODULE_NAME ": could not ioremap, aborting.\n");
 		return;
 	}
+	mmiotrace_printk("ioremap returned %p.\n", p);
 	do_write_test(p);
 	do_read_test(p);
 	iounmap(p);