14 files changed, 216 insertions, 346 deletions

diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index e7277cbcfb4..a725b7f760a 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -161,13 +161,14 @@ static void note_page(struct seq_file *m, struct pg_state *st,
 		   st->current_address >= st->marker[1].start_address) {
 		const char *unit = units;
 		unsigned long delta;
+		int width = sizeof(unsigned long) * 2;
 
 		/*
 		 * Now print the actual finished series
 		 */
-		seq_printf(m, "0x%p-0x%p   ",
-			   (void *)st->start_address,
-			   (void *)st->current_address);
+		seq_printf(m, "0x%0*lx-0x%0*lx   ",
+			   width, st->start_address,
+			   width, st->current_address);
 
 		delta = (st->current_address - st->start_address) >> 10;
 		while (!(delta & 1023) && unit[1]) {
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index a03b7279efa..c6acc632637 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -3,40 +3,17 @@
  *  Copyright (C) 2001, 2002 Andi Kleen, SuSE Labs.
  *  Copyright (C) 2008-2009, Red Hat Inc., Ingo Molnar
  */
-#include <linux/interrupt.h>
-#include <linux/mmiotrace.h>
-#include <linux/bootmem.h>
-#include <linux/compiler.h>
-#include <linux/highmem.h>
-#include <linux/kprobes.h>
-#include <linux/uaccess.h>
-#include <linux/vmalloc.h>
-#include <linux/vt_kern.h>
-#include <linux/signal.h>
-#include <linux/kernel.h>
-#include <linux/ptrace.h>
-#include <linux/string.h>
-#include <linux/module.h>
-#include <linux/kdebug.h>
-#include <linux/errno.h>
-#include <linux/magic.h>
-#include <linux/sched.h>
-#include <linux/types.h>
-#include <linux/init.h>
-#include <linux/mman.h>
-#include <linux/tty.h>
-#include <linux/smp.h>
-#include <linux/mm.h>
-
-#include <asm-generic/sections.h>
-
-#include <asm/tlbflush.h>
-#include <asm/pgalloc.h>
-#include <asm/segment.h>
-#include <asm/system.h>
-#include <asm/proto.h>
-#include <asm/traps.h>
-#include <asm/desc.h>
+#include <linux/magic.h>		/* STACK_END_MAGIC		*/
+#include <linux/sched.h>		/* test_thread_flag(), ...	*/
+#include <linux/kdebug.h>		/* oops_begin/end, ...		*/
+#include <linux/module.h>		/* search_exception_table	*/
+#include <linux/bootmem.h>		/* max_low_pfn			*/
+#include <linux/kprobes.h>		/* __kprobes, ...		*/
+#include <linux/mmiotrace.h>		/* kmmio_handler, ...		*/
+#include <linux/perf_counter.h>		/* perf_swcounter_event		*/
+
+#include <asm/traps.h>			/* dotraplinkage, ...		*/
+#include <asm/pgalloc.h>		/* pgd_*(), ...			*/
 
 /*
  * Page fault error code bits:
@@ -225,12 +202,10 @@ static inline pmd_t *vmalloc_sync_one(pgd_t *pgd, unsigned long address)
 	if (!pmd_present(*pmd_k))
 		return NULL;
 
-	if (!pmd_present(*pmd)) {
+	if (!pmd_present(*pmd))
 		set_pmd(pmd, *pmd_k);
-		arch_flush_lazy_mmu_mode();
-	} else {
+	else
 		BUG_ON(pmd_page(*pmd) != pmd_page(*pmd_k));
-	}
 
 	return pmd_k;
 }
@@ -538,8 +513,6 @@ bad:
 static int is_errata93(struct pt_regs *regs, unsigned long address)
 {
 #ifdef CONFIG_X86_64
-	static int once;
-
 	if (address != regs->ip)
 		return 0;
 
@@ -549,10 +522,7 @@ static int is_errata93(struct pt_regs *regs, unsigned long address)
 	address |= 0xffffffffUL << 32;
 	if ((address >= (u64)_stext && address <= (u64)_etext) ||
 	    (address >= MODULES_VADDR && address <= MODULES_END)) {
-		if (!once) {
-			printk(errata93_warning);
-			once = 1;
-		}
+		printk_once(errata93_warning);
 		regs->ip = address;
 		return 1;
 	}
@@ -1044,6 +1014,8 @@ do_page_fault(struct pt_regs *regs, unsigned long error_code)
 	if (unlikely(error_code & PF_RSVD))
 		pgtable_bad(regs, error_code, address);
 
+	perf_swcounter_event(PERF_COUNT_SW_PAGE_FAULTS, 1, 0, regs, address);
+
 	/*
 	 * If we're in an interrupt, have no user context or are running
 	 * in an atomic region then we must not take the fault:
@@ -1137,10 +1109,15 @@ good_area:
 		return;
 	}
 
-	if (fault & VM_FAULT_MAJOR)
+	if (fault & VM_FAULT_MAJOR) {
 		tsk->maj_flt++;
-	else
+		perf_swcounter_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, 0,
+				     regs, address);
+	} else {
 		tsk->min_flt++;
+		perf_swcounter_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, 0,
+				     regs, address);
+	}
 
 	check_v8086_mode(regs, address, tsk);
 
diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c
index 8126e8d1a2a..58f621e8191 100644
--- a/arch/x86/mm/highmem_32.c
+++ b/arch/x86/mm/highmem_32.c
@@ -44,7 +44,6 @@ void *kmap_atomic_prot(struct page *page, enum km_type type, pgprot_t prot)
 	vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
 	BUG_ON(!pte_none(*(kmap_pte-idx)));
 	set_pte(kmap_pte-idx, mk_pte(page, prot));
-	arch_flush_lazy_mmu_mode();
 
 	return (void *)vaddr;
 }
@@ -74,7 +73,6 @@ void kunmap_atomic(void *kvaddr, enum km_type type)
 #endif
 	}
 
-	arch_flush_lazy_mmu_mode();
 	pagefault_enable();
 }
 
diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index 8f307d914c2..f46c340727b 100644
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -26,12 +26,16 @@ static unsigned long page_table_shareable(struct vm_area_struct *svma,
 	unsigned long sbase = saddr & PUD_MASK;
 	unsigned long s_end = sbase + PUD_SIZE;
 
+	/* Allow segments to share if only one is marked locked */
+	unsigned long vm_flags = vma->vm_flags & ~VM_LOCKED;
+	unsigned long svm_flags = svma->vm_flags & ~VM_LOCKED;
+
 	/*
 	 * match the virtual addresses, permission and the alignment of the
 	 * page table page.
 	 */
 	if (pmd_index(addr) != pmd_index(saddr) ||
-	    vma->vm_flags != svma->vm_flags ||
+	    vm_flags != svm_flags ||
 	    sbase < svma->vm_start || svma->vm_end < s_end)
 		return 0;
 
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index ae4f7b5d710..34c1bfb64f1 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -1,3 +1,4 @@
+#include <linux/initrd.h>
 #include <linux/ioport.h>
 #include <linux/swap.h>
 
@@ -10,6 +11,9 @@
 #include <asm/setup.h>
 #include <asm/system.h>
 #include <asm/tlbflush.h>
+#include <asm/tlb.h>
+
+DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
 
 unsigned long __initdata e820_table_start;
 unsigned long __meminitdata e820_table_end;
@@ -23,6 +27,69 @@ int direct_gbpages
 #endif
 ;
 
+int nx_enabled;
+
+#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
+static int disable_nx __cpuinitdata;
+
+/*
+ * noexec = on|off
+ *
+ * Control non-executable mappings for processes.
+ *
+ * on      Enable
+ * off     Disable
+ */
+static int __init noexec_setup(char *str)
+{
+	if (!str)
+		return -EINVAL;
+	if (!strncmp(str, "on", 2)) {
+		__supported_pte_mask |= _PAGE_NX;
+		disable_nx = 0;
+	} else if (!strncmp(str, "off", 3)) {
+		disable_nx = 1;
+		__supported_pte_mask &= ~_PAGE_NX;
+	}
+	return 0;
+}
+early_param("noexec", noexec_setup);
+#endif
+
+#ifdef CONFIG_X86_PAE
+static void __init set_nx(void)
+{
+	unsigned int v[4], l, h;
+
+	if (cpu_has_pae && (cpuid_eax(0x80000000) > 0x80000001)) {
+		cpuid(0x80000001, &v[0], &v[1], &v[2], &v[3]);
+
+		if ((v[3] & (1 << 20)) && !disable_nx) {
+			rdmsr(MSR_EFER, l, h);
+			l |= EFER_NX;
+			wrmsr(MSR_EFER, l, h);
+			nx_enabled = 1;
+			__supported_pte_mask |= _PAGE_NX;
+		}
+	}
+}
+#else
+static inline void set_nx(void)
+{
+}
+#endif
+
+#ifdef CONFIG_X86_64
+void __cpuinit check_efer(void)
+{
+	unsigned long efer;
+
+	rdmsrl(MSR_EFER, efer);
+	if (!(efer & EFER_NX) || disable_nx)
+		__supported_pte_mask &= ~_PAGE_NX;
+}
+#endif
+
 static void __init find_early_table_space(unsigned long end, int use_pse,
 					  int use_gbpages)
 {
@@ -66,12 +133,11 @@ static void __init find_early_table_space(unsigned long end, int use_pse,
 	 */
 #ifdef CONFIG_X86_32
 	start = 0x7000;
-	e820_table_start = find_e820_area(start, max_pfn_mapped<<PAGE_SHIFT,
-					tables, PAGE_SIZE);
-#else /* CONFIG_X86_64 */
+#else
 	start = 0x8000;
-	e820_table_start = find_e820_area(start, end, tables, PAGE_SIZE);
 #endif
+	e820_table_start = find_e820_area(start, max_pfn_mapped<<PAGE_SHIFT,
+					tables, PAGE_SIZE);
 	if (e820_table_start == -1UL)
 		panic("Cannot find space for the kernel page tables");
 
@@ -159,12 +225,9 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
 	use_gbpages = direct_gbpages;
 #endif
 
-#ifdef CONFIG_X86_32
-#ifdef CONFIG_X86_PAE
 	set_nx();
 	if (nx_enabled)
 		printk(KERN_INFO "NX (Execute Disable) protection: active\n");
-#endif
 
 	/* Enable PSE if available */
 	if (cpu_has_pse)
@@ -175,7 +238,6 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
 		set_in_cr4(X86_CR4_PGE);
 		__supported_pte_mask |= _PAGE_GLOBAL;
 	}
-#endif
 
 	if (use_gbpages)
 		page_size_mask |= 1 << PG_LEVEL_1G;
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 749559ed80f..9ff3c0816d1 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -49,12 +49,9 @@
 #include <asm/paravirt.h>
 #include <asm/setup.h>
 #include <asm/cacheflush.h>
+#include <asm/page_types.h>
 #include <asm/init.h>
 
-unsigned long max_low_pfn_mapped;
-unsigned long max_pfn_mapped;
-
-DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
 unsigned long highstart_pfn, highend_pfn;
 
 static noinline int do_test_wp_bit(void);
@@ -567,7 +564,7 @@ static inline void save_pg_dir(void)
 }
 #endif /* !CONFIG_ACPI_SLEEP */
 
-void zap_low_mappings(void)
+void zap_low_mappings(bool early)
 {
 	int i;
 
@@ -584,64 +581,16 @@ void zap_low_mappings(void)
 		set_pgd(swapper_pg_dir+i, __pgd(0));
 #endif
 	}
-	flush_tlb_all();
-}
 
-int nx_enabled;
+	if (early)
+		__flush_tlb();
+	else
+		flush_tlb_all();
+}
 
 pteval_t __supported_pte_mask __read_mostly = ~(_PAGE_NX | _PAGE_GLOBAL | _PAGE_IOMAP);
 EXPORT_SYMBOL_GPL(__supported_pte_mask);
 
-#ifdef CONFIG_X86_PAE
-
-static int disable_nx __initdata;
-
-/*
- * noexec = on|off
- *
- * Control non executable mappings.
- *
- * on      Enable
- * off     Disable
- */
-static int __init noexec_setup(char *str)
-{
-	if (!str || !strcmp(str, "on")) {
-		if (cpu_has_nx) {
-			__supported_pte_mask |= _PAGE_NX;
-			disable_nx = 0;
-		}
-	} else {
-		if (!strcmp(str, "off")) {
-			disable_nx = 1;
-			__supported_pte_mask &= ~_PAGE_NX;
-		} else {
-			return -EINVAL;
-		}
-	}
-
-	return 0;
-}
-early_param("noexec", noexec_setup);
-
-void __init set_nx(void)
-{
-	unsigned int v[4], l, h;
-
-	if (cpu_has_pae && (cpuid_eax(0x80000000) > 0x80000001)) {
-		cpuid(0x80000001, &v[0], &v[1], &v[2], &v[3]);
-
-		if ((v[3] & (1 << 20)) && !disable_nx) {
-			rdmsr(MSR_EFER, l, h);
-			l |= EFER_NX;
-			wrmsr(MSR_EFER, l, h);
-			nx_enabled = 1;
-			__supported_pte_mask |= _PAGE_NX;
-		}
-	}
-}
-#endif
-
 /* user-defined highmem size */
 static unsigned int highmem_pages = -1;
 
@@ -761,15 +710,15 @@ void __init initmem_init(unsigned long start_pfn,
 	highstart_pfn = highend_pfn = max_pfn;
 	if (max_pfn > max_low_pfn)
 		highstart_pfn = max_low_pfn;
-	memory_present(0, 0, highend_pfn);
 	e820_register_active_regions(0, 0, highend_pfn);
+	sparse_memory_present_with_active_regions(0);
 	printk(KERN_NOTICE "%ldMB HIGHMEM available.\n",
 		pages_to_mb(highend_pfn - highstart_pfn));
 	num_physpages = highend_pfn;
 	high_memory = (void *) __va(highstart_pfn * PAGE_SIZE - 1) + 1;
 #else
-	memory_present(0, 0, max_low_pfn);
 	e820_register_active_regions(0, 0, max_low_pfn);
+	sparse_memory_present_with_active_regions(0);
 	num_physpages = max_low_pfn;
 	high_memory = (void *) __va(max_low_pfn * PAGE_SIZE - 1) + 1;
 #endif
@@ -1011,7 +960,7 @@ void __init mem_init(void)
 		test_wp_bit();
 
 	save_pg_dir();
-	zap_low_mappings();
+	zap_low_mappings(true);
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 1753e8020df..52bb9519bb8 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -50,18 +50,8 @@
 #include <asm/cacheflush.h>
 #include <asm/init.h>
 
-/*
- * end_pfn only includes RAM, while max_pfn_mapped includes all e820 entries.
- * The direct mapping extends to max_pfn_mapped, so that we can directly access
- * apertures, ACPI and other tables without having to play with fixmaps.
- */
-unsigned long max_low_pfn_mapped;
-unsigned long max_pfn_mapped;
-
 static unsigned long dma_reserve __initdata;
 
-DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
-
 static int __init parse_direct_gbpages_off(char *arg)
 {
 	direct_gbpages = 0;
@@ -85,39 +75,6 @@ early_param("gbpages", parse_direct_gbpages_on);
 pteval_t __supported_pte_mask __read_mostly = ~_PAGE_IOMAP;
 EXPORT_SYMBOL_GPL(__supported_pte_mask);
 
-static int disable_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;
-		disable_nx = 0;
-	} else if (!strncmp(str, "off", 3)) {
-		disable_nx = 1;
-		__supported_pte_mask &= ~_PAGE_NX;
-	}
-	return 0;
-}
-early_param("noexec", nonx_setup);
-
-void __cpuinit check_efer(void)
-{
-	unsigned long efer;
-
-	rdmsrl(MSR_EFER, efer);
-	if (!(efer & EFER_NX) || disable_nx)
-		__supported_pte_mask &= ~_PAGE_NX;
-}
-
 int force_personality32;
 
 /*
@@ -628,6 +585,7 @@ void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn)
 	early_res_to_bootmem(0, end_pfn<<PAGE_SHIFT);
 	reserve_bootmem(bootmap, bootmap_size, BOOTMEM_DEFAULT);
 }
+#endif
 
 void __init paging_init(void)
 {
@@ -638,11 +596,10 @@ void __init paging_init(void)
 	max_zone_pfns[ZONE_DMA32] = MAX_DMA32_PFN;
 	max_zone_pfns[ZONE_NORMAL] = max_pfn;
 
-	memory_present(0, 0, max_pfn);
+	sparse_memory_present_with_active_regions(MAX_NUMNODES);
 	sparse_init();
 	free_area_init_nodes(max_zone_pfns);
 }
-#endif
 
 /*
  * Memory hotplug specific functions
diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c
index 8056545e2d3..fe6f84ca121 100644
--- a/arch/x86/mm/iomap_32.c
+++ b/arch/x86/mm/iomap_32.c
@@ -82,7 +82,6 @@ iounmap_atomic(void *kvaddr, enum km_type type)
 	if (vaddr == __fix_to_virt(FIX_KMAP_BEGIN+idx))
 		kpte_clear_flush(kmap_pte-idx, vaddr);
 
-	arch_flush_lazy_mmu_mode();
 	pagefault_enable();
 }
 EXPORT_SYMBOL_GPL(iounmap_atomic);
diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c
index 50dc802a1c4..16ccbd77917 100644
--- a/arch/x86/mm/kmmio.c
+++ b/arch/x86/mm/kmmio.c
@@ -32,7 +32,7 @@ struct kmmio_fault_page {
 	struct list_head list;
 	struct kmmio_fault_page *release_next;
 	unsigned long page; /* location of the fault page */
-	bool old_presence; /* page presence prior to arming */
+	pteval_t old_presence; /* page presence prior to arming */
 	bool armed;
 
 	/*
@@ -97,60 +97,62 @@ static struct kmmio_probe *get_kmmio_probe(unsigned long addr)
 static struct kmmio_fault_page *get_kmmio_fault_page(unsigned long page)
 {
 	struct list_head *head;
-	struct kmmio_fault_page *p;
+	struct kmmio_fault_page *f;
 
 	page &= PAGE_MASK;
 	head = kmmio_page_list(page);
-	list_for_each_entry_rcu(p, head, list) {
-		if (p->page == page)
-			return p;
+	list_for_each_entry_rcu(f, head, list) {
+		if (f->page == page)
+			return f;
 	}
 	return NULL;
 }
 
-static void set_pmd_presence(pmd_t *pmd, bool present, bool *old)
+static void clear_pmd_presence(pmd_t *pmd, bool clear, pmdval_t *old)
 {
 	pmdval_t v = pmd_val(*pmd);
-	*old = !!(v & _PAGE_PRESENT);
-	v &= ~_PAGE_PRESENT;
-	if (present)
-		v |= _PAGE_PRESENT;
+	if (clear) {
+		*old = v & _PAGE_PRESENT;
+		v &= ~_PAGE_PRESENT;
+	} else	/* presume this has been called with clear==true previously */
+		v |= *old;
 	set_pmd(pmd, __pmd(v));
 }
 
-static void set_pte_presence(pte_t *pte, bool present, bool *old)
+static void clear_pte_presence(pte_t *pte, bool clear, pteval_t *old)
 {
 	pteval_t v = pte_val(*pte);
-	*old = !!(v & _PAGE_PRESENT);
-	v &= ~_PAGE_PRESENT;
-	if (present)
-		v |= _PAGE_PRESENT;
+	if (clear) {
+		*old = v & _PAGE_PRESENT;
+		v &= ~_PAGE_PRESENT;
+	} else	/* presume this has been called with clear==true previously */
+		v |= *old;
 	set_pte_atomic(pte, __pte(v));
 }
 
-static int set_page_presence(unsigned long addr, bool present, bool *old)
+static int clear_page_presence(struct kmmio_fault_page *f, bool clear)
 {
 	unsigned int level;
-	pte_t *pte = lookup_address(addr, &level);
+	pte_t *pte = lookup_address(f->page, &level);
 
 	if (!pte) {
-		pr_err("kmmio: no pte for page 0x%08lx\n", addr);
+		pr_err("kmmio: no pte for page 0x%08lx\n", f->page);
 		return -1;
 	}
 
 	switch (level) {
 	case PG_LEVEL_2M:
-		set_pmd_presence((pmd_t *)pte, present, old);
+		clear_pmd_presence((pmd_t *)pte, clear, &f->old_presence);
 		break;
 	case PG_LEVEL_4K:
-		set_pte_presence(pte, present, old);
+		clear_pte_presence(pte, clear, &f->old_presence);
 		break;
 	default:
 		pr_err("kmmio: unexpected page level 0x%x.\n", level);
 		return -1;
 	}
 
-	__flush_tlb_one(addr);
+	__flush_tlb_one(f->page);
 	return 0;
 }
 
@@ -171,9 +173,9 @@ static int arm_kmmio_fault_page(struct kmmio_fault_page *f)
 	WARN_ONCE(f->armed, KERN_ERR "kmmio page already armed.\n");
 	if (f->armed) {
 		pr_warning("kmmio double-arm: page 0x%08lx, ref %d, old %d\n",
-					f->page, f->count, f->old_presence);
+					f->page, f->count, !!f->old_presence);
 	}
-	ret = set_page_presence(f->page, false, &f->old_presence);
+	ret = clear_page_presence(f, true);
 	WARN_ONCE(ret < 0, KERN_ERR "kmmio arming 0x%08lx failed.\n", f->page);
 	f->armed = true;
 	return ret;
@@ -182,8 +184,7 @@ static int arm_kmmio_fault_page(struct kmmio_fault_page *f)
 /** Restore the given page to saved presence state. */
 static void disarm_kmmio_fault_page(struct kmmio_fault_page *f)
 {
-	bool tmp;
-	int ret = set_page_presence(f->page, f->old_presence, &tmp);
+	int ret = clear_page_presence(f, false);
 	WARN_ONCE(ret < 0,
 			KERN_ERR "kmmio disarming 0x%08lx failed.\n", f->page);
 	f->armed = false;
@@ -310,7 +311,12 @@ static int post_kmmio_handler(unsigned long condition, struct pt_regs *regs)
 	struct kmmio_context *ctx = &get_cpu_var(kmmio_ctx);
 
 	if (!ctx->active) {
-		pr_debug("kmmio: spurious debug trap on CPU %d.\n",
+		/*
+		 * debug traps without an active context are due to either
+		 * something external causing them (f.e. using a debugger while
+		 * mmio tracing enabled), or erroneous behaviour
+		 */
+		pr_warning("kmmio: unexpected debug trap on CPU %d.\n",
 							smp_processor_id());
 		goto out;
 	}
@@ -439,12 +445,12 @@ static void rcu_free_kmmio_fault_pages(struct rcu_head *head)
 						head,
 						struct kmmio_delayed_release,
 						rcu);
-	struct kmmio_fault_page *p = dr->release_list;
-	while (p) {
-		struct kmmio_fault_page *next = p->release_next;
-		BUG_ON(p->count);
-		kfree(p);
-		p = next;
+	struct kmmio_fault_page *f = dr->release_list;
+	while (f) {
+		struct kmmio_fault_page *next = f->release_next;
+		BUG_ON(f->count);
+		kfree(f);
+		f = next;
 	}
 	kfree(dr);
 }
@@ -453,19 +459,19 @@ static void remove_kmmio_fault_pages(struct rcu_head *head)
 {
 	struct kmmio_delayed_release *dr =
 		container_of(head, struct kmmio_delayed_release, rcu);
-	struct kmmio_fault_page *p = dr->release_list;
+	struct kmmio_fault_page *f = dr->release_list;
 	struct kmmio_fault_page **prevp = &dr->release_list;
 	unsigned long flags;
 
 	spin_lock_irqsave(&kmmio_lock, flags);
-	while (p) {
-		if (!p->count) {
-			list_del_rcu(&p->list);
-			prevp = &p->release_next;
+	while (f) {
+		if (!f->count) {
+			list_del_rcu(&f->list);
+			prevp = &f->release_next;
 		} else {
-			*prevp = p->release_next;
+			*prevp = f->release_next;
 		}
-		p = p->release_next;
+		f = f->release_next;
 	}
 	spin_unlock_irqrestore(&kmmio_lock, flags);
 
@@ -528,8 +534,8 @@ void unregister_kmmio_probe(struct kmmio_probe *p)
 }
 EXPORT_SYMBOL(unregister_kmmio_probe);
 
-static int kmmio_die_notifier(struct notifier_block *nb, unsigned long val,
-								void *args)
+static int
+kmmio_die_notifier(struct notifier_block *nb, unsigned long val, void *args)
 {
 	struct die_args *arg = args;
 
@@ -544,11 +550,23 @@ static struct notifier_block nb_die = {
 	.notifier_call = kmmio_die_notifier
 };
 
-static int __init init_kmmio(void)
+int kmmio_init(void)
 {
 	int i;
+
 	for (i = 0; i < KMMIO_PAGE_TABLE_SIZE; i++)
 		INIT_LIST_HEAD(&kmmio_page_table[i]);
+
 	return register_die_notifier(&nb_die);
 }
-fs_initcall(init_kmmio); /* should be before device_initcall() */
+
+void kmmio_cleanup(void)
+{
+	int i;
+
+	unregister_die_notifier(&nb_die);
+	for (i = 0; i < KMMIO_PAGE_TABLE_SIZE; i++) {
+		WARN_ONCE(!list_empty(&kmmio_page_table[i]),
+			KERN_ERR "kmmio_page_table not empty at cleanup, any further tracing will leak memory.\n");
+	}
+}
diff --git a/arch/x86/mm/memtest.c b/arch/x86/mm/memtest.c
index 605c8be0621..18d244f7020 100644
--- a/arch/x86/mm/memtest.c
+++ b/arch/x86/mm/memtest.c
@@ -40,23 +40,22 @@ static void __init reserve_bad_mem(u64 pattern, u64 start_bad, u64 end_bad)
 
 static void __init memtest(u64 pattern, u64 start_phys, u64 size)
 {
-	u64 i, count;
-	u64 *start;
+	u64 *p, *start, *end;
 	u64 start_bad, last_bad;
 	u64 start_phys_aligned;
-	size_t incr;
+	const size_t incr = sizeof(pattern);
 
-	incr = sizeof(pattern);
 	start_phys_aligned = ALIGN(start_phys, incr);
-	count = (size - (start_phys_aligned - start_phys))/incr;
 	start = __va(start_phys_aligned);
+	end = start + (size - (start_phys_aligned - start_phys)) / incr;
 	start_bad = 0;
 	last_bad = 0;
 
-	for (i = 0; i < count; i++)
-		start[i] = pattern;
-	for (i = 0; i < count; i++, start++, start_phys_aligned += incr) {
-		if (*start == pattern)
+	for (p = start; p < end; p++)
+		*p = pattern;
+
+	for (p = start; p < end; p++, start_phys_aligned += incr) {
+		if (*p == pattern)
 			continue;
 		if (start_phys_aligned == last_bad + incr) {
 			last_bad += incr;
diff --git a/arch/x86/mm/mmio-mod.c b/arch/x86/mm/mmio-mod.c
index c9342ed8b40..132772a8ec5 100644
--- a/arch/x86/mm/mmio-mod.c
+++ b/arch/x86/mm/mmio-mod.c
@@ -451,6 +451,7 @@ void enable_mmiotrace(void)
 
 	if (nommiotrace)
 		pr_info(NAME "MMIO tracing disabled.\n");
+	kmmio_init();
 	enter_uniprocessor();
 	spin_lock_irq(&trace_lock);
 	atomic_inc(&mmiotrace_enabled);
@@ -473,6 +474,7 @@ void disable_mmiotrace(void)
 
 	clear_trace_list(); /* guarantees: no more kmmio callbacks */
 	leave_uniprocessor();
+	kmmio_cleanup();
 	pr_info(NAME "disabled.\n");
 out:
 	mutex_unlock(&mmiotrace_mutex);
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index 2d05a12029d..459913beac7 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -179,18 +179,25 @@ static void * __init early_node_mem(int nodeid, unsigned long start,
 }
 
 /* Initialize bootmem allocator for a node */
-void __init setup_node_bootmem(int nodeid, unsigned long start,
-			       unsigned long end)
+void __init
+setup_node_bootmem(int nodeid, unsigned long start, unsigned long end)
 {
 	unsigned long start_pfn, last_pfn, bootmap_pages, bootmap_size;
+	const int pgdat_size = roundup(sizeof(pg_data_t), PAGE_SIZE);
 	unsigned long bootmap_start, nodedata_phys;
 	void *bootmap;
-	const int pgdat_size = roundup(sizeof(pg_data_t), PAGE_SIZE);
 	int nid;
 
 	if (!end)
 		return;
 
+	/*
+	 * Don't confuse VM with a node that doesn't have the
+	 * minimum amount of memory:
+	 */
+	if (end && (end - start) < NODE_MIN_SIZE)
+		return;
+
 	start = roundup(start, ZONE_ALIGN);
 
 	printk(KERN_INFO "Bootmem setup node %d %016lx-%016lx\n", nodeid,
@@ -272,9 +279,6 @@ void __init setup_node_bootmem(int nodeid, unsigned long start,
 		reserve_bootmem_node(NODE_DATA(nodeid), bootmap_start,
 				 bootmap_pages<<PAGE_SHIFT, BOOTMEM_DEFAULT);
 
-#ifdef CONFIG_ACPI_NUMA
-	srat_reserve_add_area(nodeid);
-#endif
 	node_set_online(nodeid);
 }
 
@@ -578,21 +582,6 @@ unsigned long __init numa_free_all_bootmem(void)
 	return pages;
 }
 
-void __init paging_init(void)
-{
-	unsigned long max_zone_pfns[MAX_NR_ZONES];
-
-	memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
-	max_zone_pfns[ZONE_DMA] = MAX_DMA_PFN;
-	max_zone_pfns[ZONE_DMA32] = MAX_DMA32_PFN;
-	max_zone_pfns[ZONE_NORMAL] = max_pfn;
-
-	sparse_memory_present_with_active_regions(MAX_NUMNODES);
-	sparse_init();
-
-	free_area_init_nodes(max_zone_pfns);
-}
-
 static __init int numa_setup(char *opt)
 {
 	if (!opt)
@@ -606,8 +595,6 @@ static __init int numa_setup(char *opt)
 #ifdef CONFIG_ACPI_NUMA
 	if (!strncmp(opt, "noacpi", 6))
 		acpi_numa = -1;
-	if (!strncmp(opt, "hotadd=", 7))
-		hotadd_percent = simple_strtoul(opt+7, NULL, 10);
 #endif
 	return 0;
 }
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 797f9f107cb..6ce9518fe2a 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -153,7 +153,7 @@ static void __cpa_flush_all(void *arg)
 	 */
 	__flush_tlb_all();
 
-	if (cache && boot_cpu_data.x86_model >= 4)
+	if (cache && boot_cpu_data.x86 >= 4)
 		wbinvd();
 }
 
@@ -208,20 +208,15 @@ static void cpa_flush_array(unsigned long *start, int numpages, int cache,
 			    int in_flags, struct page **pages)
 {
 	unsigned int i, level;
+	unsigned long do_wbinvd = cache && numpages >= 1024; /* 4M threshold */
 
 	BUG_ON(irqs_disabled());
 
-	on_each_cpu(__cpa_flush_range, NULL, 1);
+	on_each_cpu(__cpa_flush_all, (void *) do_wbinvd, 1);
 
-	if (!cache)
+	if (!cache || do_wbinvd)
 		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
@@ -844,13 +839,6 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages,
 
 	vm_unmap_aliases();
 
-	/*
-	 * If we're called with lazy mmu updates enabled, the
-	 * in-memory pte state may be stale.  Flush pending updates to
-	 * bring them up to date.
-	 */
-	arch_flush_lazy_mmu_mode();
-
 	cpa.vaddr = addr;
 	cpa.pages = pages;
 	cpa.numpages = numpages;
@@ -895,13 +883,6 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages,
 	} else
 		cpa_flush_all(cache);
 
-	/*
-	 * If we've been called with lazy mmu updates enabled, then
-	 * make sure that everything gets flushed out before we
-	 * return.
-	 */
-	arch_flush_lazy_mmu_mode();
-
 out:
 	return ret;
 }
diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c
index 01765955baa..2dfcbf9df2a 100644
--- a/arch/x86/mm/srat_64.c
+++ b/arch/x86/mm/srat_64.c
@@ -31,17 +31,11 @@ static nodemask_t nodes_parsed __initdata;
 static nodemask_t cpu_nodes_parsed __initdata;
 static struct bootnode nodes[MAX_NUMNODES] __initdata;
 static struct bootnode nodes_add[MAX_NUMNODES];
-static int found_add_area __initdata;
-int hotadd_percent __initdata = 0;
 
 static int num_node_memblks __initdata;
 static struct bootnode node_memblk_range[NR_NODE_MEMBLKS] __initdata;
 static int memblk_nodeid[NR_NODE_MEMBLKS] __initdata;
 
-/* Too small nodes confuse the VM badly. Usually they result
-   from BIOS bugs. */
-#define NODE_MIN_SIZE (4*1024*1024)
-
 static __init int setup_node(int pxm)
 {
 	return acpi_map_pxm_to_node(pxm);
@@ -66,9 +60,6 @@ static __init void cutoff_node(int i, unsigned long start, unsigned long end)
 {
 	struct bootnode *nd = &nodes[i];
 
-	if (found_add_area)
-		return;
-
 	if (nd->start < start) {
 		nd->start = start;
 		if (nd->end < nd->start)
@@ -86,7 +77,6 @@ static __init void bad_srat(void)
 	int i;
 	printk(KERN_ERR "SRAT: SRAT not used.\n");
 	acpi_numa = -1;
-	found_add_area = 0;
 	for (i = 0; i < MAX_LOCAL_APIC; i++)
 		apicid_to_node[i] = NUMA_NO_NODE;
 	for (i = 0; i < MAX_NUMNODES; i++)
@@ -182,24 +172,21 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa)
 	       pxm, apic_id, node);
 }
 
-static int update_end_of_memory(unsigned long end) {return -1;}
-static int hotadd_enough_memory(struct bootnode *nd) {return 1;}
 #ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
 static inline int save_add_info(void) {return 1;}
 #else
 static inline int save_add_info(void) {return 0;}
 #endif
 /*
- * Update nodes_add and decide if to include add are in the zone.
- * Both SPARSE and RESERVE need nodes_add information.
- * This code supports one contiguous hot add area per node.
+ * Update nodes_add[]
+ * This code supports one contiguous hot add area per node
  */
-static int __init
-reserve_hotadd(int node, unsigned long start, unsigned long end)
+static void __init
+update_nodes_add(int node, unsigned long start, unsigned long end)
 {
 	unsigned long s_pfn = start >> PAGE_SHIFT;
 	unsigned long e_pfn = end >> PAGE_SHIFT;
-	int ret = 0, changed = 0;
+	int changed = 0;
 	struct bootnode *nd = &nodes_add[node];
 
 	/* I had some trouble with strange memory hotadd regions breaking
@@ -210,7 +197,7 @@ reserve_hotadd(int node, unsigned long start, unsigned long end)
 	   mistakes */
 	if ((signed long)(end - start) < NODE_MIN_SIZE) {
 		printk(KERN_ERR "SRAT: Hotplug area too small\n");
-		return -1;
+		return;
 	}
 
 	/* This check might be a bit too strict, but I'm keeping it for now. */
@@ -218,12 +205,7 @@ reserve_hotadd(int node, unsigned long start, unsigned long end)
 		printk(KERN_ERR
 			"SRAT: Hotplug area %lu -> %lu has existing memory\n",
 			s_pfn, e_pfn);
-		return -1;
-	}
-
-	if (!hotadd_enough_memory(&nodes_add[node]))  {
-		printk(KERN_ERR "SRAT: Hotplug area too large\n");
-		return -1;
+		return;
 	}
 
 	/* Looks good */
@@ -245,11 +227,9 @@ reserve_hotadd(int node, unsigned long start, unsigned long end)
 			printk(KERN_ERR "SRAT: Hotplug zone not continuous. Partly ignored\n");
 	}
 
-	ret = update_end_of_memory(nd->end);
-
 	if (changed)
-	 	printk(KERN_INFO "SRAT: hot plug zone found %Lx - %Lx\n", nd->start, nd->end);
-	return ret;
+		printk(KERN_INFO "SRAT: hot plug zone found %Lx - %Lx\n",
+				 nd->start, nd->end);
 }
 
 /* Callback for parsing of the Proximity Domain <-> Memory Area mappings */
@@ -310,13 +290,10 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
 	       start, end);
 	e820_register_active_regions(node, start >> PAGE_SHIFT,
 				     end >> PAGE_SHIFT);
-	push_node_boundaries(node, nd->start >> PAGE_SHIFT,
-						nd->end >> PAGE_SHIFT);
 
-	if ((ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE) &&
-	    (reserve_hotadd(node, start, end) < 0)) {
-		/* Ignore hotadd region. Undo damage */
-		printk(KERN_NOTICE "SRAT: Hotplug region ignored\n");
+	if (ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE) {
+		update_nodes_add(node, start, end);
+		/* restore nodes[node] */
 		*nd = oldnode;
 		if ((nd->start | nd->end) == 0)
 			node_clear(node, nodes_parsed);
@@ -345,9 +322,9 @@ static int __init nodes_cover_memory(const struct bootnode *nodes)
 			pxmram = 0;
 	}
 
-	e820ram = max_pfn - absent_pages_in_range(0, max_pfn);
-	/* We seem to lose 3 pages somewhere. Allow a bit of slack. */
-	if ((long)(e820ram - pxmram) >= 1*1024*1024) {
+	e820ram = max_pfn - (e820_hole_size(0, max_pfn<<PAGE_SHIFT)>>PAGE_SHIFT);
+	/* We seem to lose 3 pages somewhere. Allow 1M of slack. */
+	if ((long)(e820ram - pxmram) >= (1<<(20 - PAGE_SHIFT))) {
 		printk(KERN_ERR
 	"SRAT: PXMs only cover %luMB of your %luMB e820 RAM. Not used.\n",
 			(pxmram << PAGE_SHIFT) >> 20,
@@ -357,17 +334,6 @@ static int __init nodes_cover_memory(const struct bootnode *nodes)
 	return 1;
 }
 
-static void __init unparse_node(int node)
-{
-	int i;
-	node_clear(node, nodes_parsed);
-	node_clear(node, cpu_nodes_parsed);
-	for (i = 0; i < MAX_LOCAL_APIC; i++) {
-		if (apicid_to_node[i] == node)
-			apicid_to_node[i] = NUMA_NO_NODE;
-	}
-}
-
 void __init acpi_numa_arch_fixup(void) {}
 
 /* Use the information discovered above to actually set up the nodes. */
@@ -379,18 +345,8 @@ int __init acpi_scan_nodes(unsigned long start, unsigned long end)
 		return -1;
 
 	/* First clean up the node list */
-	for (i = 0; i < MAX_NUMNODES; i++) {
+	for (i = 0; i < MAX_NUMNODES; i++)
 		cutoff_node(i, start, end);
-		/*
-		 * don't confuse VM with a node that doesn't have the
-		 * minimum memory.
-		 */
-		if (nodes[i].end &&
-			(nodes[i].end - nodes[i].start) < NODE_MIN_SIZE) {
-			unparse_node(i);
-			node_set_offline(i);
-		}
-	}
 
 	if (!nodes_cover_memory(nodes)) {
 		bad_srat();
@@ -423,7 +379,7 @@ int __init acpi_scan_nodes(unsigned long start, unsigned long end)
 
 		if (node == NUMA_NO_NODE)
 			continue;
-		if (!node_isset(node, node_possible_map))
+		if (!node_online(node))
 			numa_clear_node(i);
 	}
 	numa_init_array();
@@ -510,26 +466,6 @@ static int null_slit_node_compare(int a, int b)
 }
 #endif /* CONFIG_NUMA_EMU */
 
-void __init srat_reserve_add_area(int nodeid)
-{
-	if (found_add_area && nodes_add[nodeid].end) {
-		u64 total_mb;
-
-		printk(KERN_INFO "SRAT: Reserving hot-add memory space "
-				"for node %d at %Lx-%Lx\n",
-			nodeid, nodes_add[nodeid].start, nodes_add[nodeid].end);
-		total_mb = (nodes_add[nodeid].end - nodes_add[nodeid].start)
-					>> PAGE_SHIFT;
-		total_mb *= sizeof(struct page);
-		total_mb >>= 20;
-		printk(KERN_INFO "SRAT: This will cost you %Lu MB of "
-				"pre-allocated memory.\n", (unsigned long long)total_mb);
-		reserve_bootmem_node(NODE_DATA(nodeid), nodes_add[nodeid].start,
-			       nodes_add[nodeid].end - nodes_add[nodeid].start,
-			       BOOTMEM_DEFAULT);
-	}
-}
-
 int __node_distance(int a, int b)
 {
 	int index;