Merge branch 'linus' into x86/mm

Merge reason: refresh the topic: there's been 290 non-merges commits upstream
              to arch/x86 alone.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

14 files changed, 334 insertions, 386 deletions

diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 08537747cb58..fdd30d08ab52 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -14,7 +14,7 @@ obj-$(CONFIG_MMIOTRACE)		+= mmiotrace.o
 mmiotrace-y			:= kmmio.o pf_in.o mmio-mod.o
 obj-$(CONFIG_MMIOTRACE_TEST)	+= testmmiotrace.o
 
-obj-$(CONFIG_NUMA)		+= numa_$(BITS).o
+obj-$(CONFIG_NUMA)		+= numa.o numa_$(BITS).o
 obj-$(CONFIG_K8_NUMA)		+= k8topology_64.o
 obj-$(CONFIG_ACPI_NUMA)		+= srat_$(BITS).o
 
diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c
index be54176e9eb2..6340cef6798a 100644
--- a/arch/x86/mm/gup.c
+++ b/arch/x86/mm/gup.c
@@ -219,6 +219,22 @@ static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end,
 	return 1;
 }
 
+/**
+ * get_user_pages_fast() - pin user pages in memory
+ * @start:	starting user address
+ * @nr_pages:	number of pages from start to pin
+ * @write:	whether pages will be written to
+ * @pages:	array that receives pointers to the pages pinned.
+ * 		Should be at least nr_pages long.
+ *
+ * Attempt to pin user pages in memory without taking mm->mmap_sem.
+ * If not successful, it will fall back to taking the lock and
+ * calling get_user_pages().
+ *
+ * Returns number of pages pinned. This may be fewer than the number
+ * requested. If nr_pages is 0 or negative, returns 0. If no pages
+ * were pinned, returns -errno.
+ */
 int get_user_pages_fast(unsigned long start, int nr_pages, int write,
 			struct page **pages)
 {
diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c
index 522db5e3d0bf..8126e8d1a2a4 100644
--- a/arch/x86/mm/highmem_32.c
+++ b/arch/x86/mm/highmem_32.c
@@ -19,49 +19,6 @@ void kunmap(struct page *page)
 	kunmap_high(page);
 }
 
-static void debug_kmap_atomic_prot(enum km_type type)
-{
-#ifdef CONFIG_DEBUG_HIGHMEM
-	static unsigned warn_count = 10;
-
-	if (unlikely(warn_count == 0))
-		return;
-
-	if (unlikely(in_interrupt())) {
-		if (in_irq()) {
-			if (type != KM_IRQ0 && type != KM_IRQ1 &&
-			    type != KM_BIO_SRC_IRQ && type != KM_BIO_DST_IRQ &&
-			    type != KM_BOUNCE_READ) {
-				WARN_ON(1);
-				warn_count--;
-			}
-		} else if (!irqs_disabled()) {	/* softirq */
-			if (type != KM_IRQ0 && type != KM_IRQ1 &&
-			    type != KM_SOFTIRQ0 && type != KM_SOFTIRQ1 &&
-			    type != KM_SKB_SUNRPC_DATA &&
-			    type != KM_SKB_DATA_SOFTIRQ &&
-			    type != KM_BOUNCE_READ) {
-				WARN_ON(1);
-				warn_count--;
-			}
-		}
-	}
-
-	if (type == KM_IRQ0 || type == KM_IRQ1 || type == KM_BOUNCE_READ ||
-			type == KM_BIO_SRC_IRQ || type == KM_BIO_DST_IRQ) {
-		if (!irqs_disabled()) {
-			WARN_ON(1);
-			warn_count--;
-		}
-	} else if (type == KM_SOFTIRQ0 || type == KM_SOFTIRQ1) {
-		if (irq_count() == 0 && !irqs_disabled()) {
-			WARN_ON(1);
-			warn_count--;
-		}
-	}
-#endif
-}
-
 /*
  * kmap_atomic/kunmap_atomic is significantly faster than kmap/kunmap because
  * no global lock is needed and because the kmap code must perform a global TLB
@@ -81,7 +38,7 @@ void *kmap_atomic_prot(struct page *page, enum km_type type, pgprot_t prot)
 	if (!PageHighMem(page))
 		return page_address(page);
 
-	debug_kmap_atomic_prot(type);
+	debug_kmap_atomic(type);
 
 	idx = type + KM_TYPE_NR*smp_processor_id();
 	vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index db81e9a8556b..749559ed80f5 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -1054,17 +1054,47 @@ static noinline int do_test_wp_bit(void)
 const int rodata_test_data = 0xC3;
 EXPORT_SYMBOL_GPL(rodata_test_data);
 
+static int kernel_set_to_readonly;
+
+void set_kernel_text_rw(void)
+{
+	unsigned long start = PFN_ALIGN(_text);
+	unsigned long size = PFN_ALIGN(_etext) - start;
+
+	if (!kernel_set_to_readonly)
+		return;
+
+	pr_debug("Set kernel text: %lx - %lx for read write\n",
+		 start, start+size);
+
+	set_pages_rw(virt_to_page(start), size >> PAGE_SHIFT);
+}
+
+void set_kernel_text_ro(void)
+{
+	unsigned long start = PFN_ALIGN(_text);
+	unsigned long size = PFN_ALIGN(_etext) - start;
+
+	if (!kernel_set_to_readonly)
+		return;
+
+	pr_debug("Set kernel text: %lx - %lx for read only\n",
+		 start, start+size);
+
+	set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT);
+}
+
 void mark_rodata_ro(void)
 {
 	unsigned long start = PFN_ALIGN(_text);
 	unsigned long size = PFN_ALIGN(_etext) - start;
 
-#ifndef CONFIG_DYNAMIC_FTRACE
-	/* Dynamic tracing modifies the kernel text section */
 	set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT);
 	printk(KERN_INFO "Write protecting the kernel text: %luk\n",
 		size >> 10);
 
+	kernel_set_to_readonly = 1;
+
 #ifdef CONFIG_CPA_DEBUG
 	printk(KERN_INFO "Testing CPA: Reverting %lx-%lx\n",
 		start, start+size);
@@ -1073,7 +1103,6 @@ void mark_rodata_ro(void)
 	printk(KERN_INFO "Testing CPA: write protecting again\n");
 	set_pages_ro(virt_to_page(start), size>>PAGE_SHIFT);
 #endif
-#endif /* CONFIG_DYNAMIC_FTRACE */
 
 	start += size;
 	size = (unsigned long)__end_rodata - start;
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 54efa57d1c03..1753e8020df6 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -734,21 +734,48 @@ void __init mem_init(void)
 const int rodata_test_data = 0xC3;
 EXPORT_SYMBOL_GPL(rodata_test_data);
 
+static int kernel_set_to_readonly;
+
+void set_kernel_text_rw(void)
+{
+	unsigned long start = PFN_ALIGN(_stext);
+	unsigned long end = PFN_ALIGN(__start_rodata);
+
+	if (!kernel_set_to_readonly)
+		return;
+
+	pr_debug("Set kernel text: %lx - %lx for read write\n",
+		 start, end);
+
+	set_memory_rw(start, (end - start) >> PAGE_SHIFT);
+}
+
+void set_kernel_text_ro(void)
+{
+	unsigned long start = PFN_ALIGN(_stext);
+	unsigned long end = PFN_ALIGN(__start_rodata);
+
+	if (!kernel_set_to_readonly)
+		return;
+
+	pr_debug("Set kernel text: %lx - %lx for read only\n",
+		 start, end);
+
+	set_memory_ro(start, (end - start) >> PAGE_SHIFT);
+}
+
 void mark_rodata_ro(void)
 {
 	unsigned long start = PFN_ALIGN(_stext), end = PFN_ALIGN(__end_rodata);
 	unsigned long rodata_start =
 		((unsigned long)__start_rodata + PAGE_SIZE - 1) & PAGE_MASK;
 
-#ifdef CONFIG_DYNAMIC_FTRACE
-	/* Dynamic tracing modifies the kernel text section */
-	start = rodata_start;
-#endif
-
 	printk(KERN_INFO "Write protecting the kernel read-only data: %luk\n",
 	       (end - start) >> 10);
 	set_memory_ro(start, (end - start) >> PAGE_SHIFT);
 
+	kernel_set_to_readonly = 1;
+
 	/*
 	 * The rodata section (but not the kernel text!) should also be
 	 * not-executable.
diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c
index 699c9b2895ae..8056545e2d39 100644
--- a/arch/x86/mm/iomap_32.c
+++ b/arch/x86/mm/iomap_32.c
@@ -19,10 +19,11 @@
 #include <asm/iomap.h>
 #include <asm/pat.h>
 #include <linux/module.h>
+#include <linux/highmem.h>
 
 int is_io_mapping_possible(resource_size_t base, unsigned long size)
 {
-#ifndef CONFIG_X86_PAE
+#if !defined(CONFIG_X86_PAE) && defined(CONFIG_PHYS_ADDR_T_64BIT)
 	/* There is no way to map greater than 1 << 32 address without PAE */
 	if (base + size > 0x100000000ULL)
 		return 0;
@@ -38,6 +39,7 @@ void *kmap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot)
 
 	pagefault_disable();
 
+	debug_kmap_atomic(type);
 	idx = type + KM_TYPE_NR * smp_processor_id();
 	vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
 	set_pte(kmap_pte - idx, pfn_pte(pfn, prot));
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 0dfa09d69e80..8a450930834f 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -280,15 +280,16 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr,
 		return NULL;
 	area->phys_addr = phys_addr;
 	vaddr = (unsigned long) area->addr;
-	if (ioremap_page_range(vaddr, vaddr + size, phys_addr, prot)) {
+
+	if (kernel_map_sync_memtype(phys_addr, size, prot_val)) {
 		free_memtype(phys_addr, phys_addr + size);
 		free_vm_area(area);
 		return NULL;
 	}
 
-	if (ioremap_change_attr(vaddr, size, prot_val) < 0) {
+	if (ioremap_page_range(vaddr, vaddr + size, phys_addr, prot)) {
 		free_memtype(phys_addr, phys_addr + size);
-		vunmap(area->addr);
+		free_vm_area(area);
 		return NULL;
 	}
 
@@ -374,7 +375,8 @@ static void __iomem *ioremap_default(resource_size_t phys_addr,
 	 * - UC_MINUS for non-WB-able memory with no other conflicting mappings
 	 * - Inherit from confliting mappings otherwise
 	 */
-	err = reserve_memtype(phys_addr, phys_addr + size, -1, &flags);
+	err = reserve_memtype(phys_addr, phys_addr + size,
+				_PAGE_CACHE_WB, &flags);
 	if (err < 0)
 		return NULL;
 
@@ -547,7 +549,7 @@ void __init early_ioremap_reset(void)
 }
 
 static void __init __early_set_fixmap(enum fixed_addresses idx,
-				   unsigned long phys, pgprot_t flags)
+				      phys_addr_t phys, pgprot_t flags)
 {
 	unsigned long addr = __fix_to_virt(idx);
 	pte_t *pte;
@@ -566,7 +568,7 @@ static void __init __early_set_fixmap(enum fixed_addresses idx,
 }
 
 static inline void __init early_set_fixmap(enum fixed_addresses idx,
-					   unsigned long phys, pgprot_t prot)
+					   phys_addr_t phys, pgprot_t prot)
 {
 	if (after_paging_init)
 		__set_fixmap(idx, phys, prot);
@@ -607,9 +609,10 @@ static int __init check_early_ioremap_leak(void)
 late_initcall(check_early_ioremap_leak);
 
 static void __init __iomem *
-__early_ioremap(unsigned long phys_addr, unsigned long size, pgprot_t prot)
+__early_ioremap(resource_size_t phys_addr, unsigned long size, pgprot_t prot)
 {
-	unsigned long offset, last_addr;
+	unsigned long offset;
+	resource_size_t last_addr;
 	unsigned int nrpages;
 	enum fixed_addresses idx0, idx;
 	int i, slot;
@@ -625,15 +628,15 @@ __early_ioremap(unsigned long phys_addr, unsigned long size, pgprot_t prot)
 	}
 
 	if (slot < 0) {
-		printk(KERN_INFO "early_iomap(%08lx, %08lx) not found slot\n",
-			 phys_addr, size);
+		printk(KERN_INFO "early_iomap(%08llx, %08lx) not found slot\n",
+			 (u64)phys_addr, size);
 		WARN_ON(1);
 		return NULL;
 	}
 
 	if (early_ioremap_debug) {
-		printk(KERN_INFO "early_ioremap(%08lx, %08lx) [%d] => ",
-		       phys_addr, size, slot);
+		printk(KERN_INFO "early_ioremap(%08llx, %08lx) [%d] => ",
+		       (u64)phys_addr, size, slot);
 		dump_stack();
 	}
 
@@ -680,13 +683,15 @@ __early_ioremap(unsigned long phys_addr, unsigned long size, pgprot_t prot)
 }
 
 /* Remap an IO device */
-void __init __iomem *early_ioremap(unsigned long phys_addr, unsigned long size)
+void __init __iomem *
+early_ioremap(resource_size_t phys_addr, unsigned long size)
 {
 	return __early_ioremap(phys_addr, size, PAGE_KERNEL_IO);
 }
 
 /* Remap memory */
-void __init __iomem *early_memremap(unsigned long phys_addr, unsigned long size)
+void __init __iomem *
+early_memremap(resource_size_t phys_addr, unsigned long size)
 {
 	return __early_ioremap(phys_addr, size, PAGE_KERNEL);
 }
diff --git a/arch/x86/mm/mmio-mod.c b/arch/x86/mm/mmio-mod.c
index 2c4baa88f2cb..c9342ed8b402 100644
--- a/arch/x86/mm/mmio-mod.c
+++ b/arch/x86/mm/mmio-mod.c
@@ -378,27 +378,34 @@ static void clear_trace_list(void)
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
-static cpumask_t downed_cpus;
+static cpumask_var_t downed_cpus;
 
 static void enter_uniprocessor(void)
 {
 	int cpu;
 	int err;
 
+	if (downed_cpus == NULL &&
+	    !alloc_cpumask_var(&downed_cpus, GFP_KERNEL)) {
+		pr_notice(NAME "Failed to allocate mask\n");
+		goto out;
+	}
+
 	get_online_cpus();
-	downed_cpus = cpu_online_map;
-	cpu_clear(first_cpu(cpu_online_map), downed_cpus);
+	cpumask_copy(downed_cpus, cpu_online_mask);
+	cpumask_clear_cpu(cpumask_first(cpu_online_mask), downed_cpus);
 	if (num_online_cpus() > 1)
 		pr_notice(NAME "Disabling non-boot CPUs...\n");
 	put_online_cpus();
 
-	for_each_cpu_mask(cpu, downed_cpus) {
+	for_each_cpu(cpu, downed_cpus) {
 		err = cpu_down(cpu);
 		if (!err)
 			pr_info(NAME "CPU%d is down.\n", cpu);
 		else
 			pr_err(NAME "Error taking CPU%d down: %d\n", cpu, err);
 	}
+out:
 	if (num_online_cpus() > 1)
 		pr_warning(NAME "multiple CPUs still online, "
 						"may miss events.\n");
@@ -411,10 +418,10 @@ static void __ref leave_uniprocessor(void)
 	int cpu;
 	int err;
 
-	if (cpus_weight(downed_cpus) == 0)
+	if (downed_cpus == NULL || cpumask_weight(downed_cpus) == 0)
 		return;
 	pr_notice(NAME "Re-enabling CPUs...\n");
-	for_each_cpu_mask(cpu, downed_cpus) {
+	for_each_cpu(cpu, downed_cpus) {
 		err = cpu_up(cpu);
 		if (!err)
 			pr_info(NAME "enabled CPU%d.\n", cpu);
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
new file mode 100644
index 000000000000..550df481accd
--- /dev/null
+++ b/arch/x86/mm/numa.c
@@ -0,0 +1,67 @@
+/* Common code for 32 and 64-bit NUMA */
+#include <linux/topology.h>
+#include <linux/module.h>
+#include <linux/bootmem.h>
+
+#ifdef CONFIG_DEBUG_PER_CPU_MAPS
+# define DBG(x...) printk(KERN_DEBUG x)
+#else
+# define DBG(x...)
+#endif
+
+/*
+ * Which logical CPUs are on which nodes
+ */
+cpumask_var_t node_to_cpumask_map[MAX_NUMNODES];
+EXPORT_SYMBOL(node_to_cpumask_map);
+
+/*
+ * Allocate node_to_cpumask_map based on number of available nodes
+ * Requires node_possible_map to be valid.
+ *
+ * Note: node_to_cpumask() is not valid until after this is done.
+ * (Use CONFIG_DEBUG_PER_CPU_MAPS to check this.)
+ */
+void __init setup_node_to_cpumask_map(void)
+{
+	unsigned int node, num = 0;
+
+	/* setup nr_node_ids if not done yet */
+	if (nr_node_ids == MAX_NUMNODES) {
+		for_each_node_mask(node, node_possible_map)
+			num = node;
+		nr_node_ids = num + 1;
+	}
+
+	/* allocate the map */
+	for (node = 0; node < nr_node_ids; node++)
+		alloc_bootmem_cpumask_var(&node_to_cpumask_map[node]);
+
+	/* cpumask_of_node() will now work */
+	pr_debug("Node to cpumask map for %d nodes\n", nr_node_ids);
+}
+
+#ifdef CONFIG_DEBUG_PER_CPU_MAPS
+/*
+ * Returns a pointer to the bitmask of CPUs on Node 'node'.
+ */
+const struct cpumask *cpumask_of_node(int node)
+{
+	if (node >= nr_node_ids) {
+		printk(KERN_WARNING
+			"cpumask_of_node(%d): node > nr_node_ids(%d)\n",
+			node, nr_node_ids);
+		dump_stack();
+		return cpu_none_mask;
+	}
+	if (node_to_cpumask_map[node] == NULL) {
+		printk(KERN_WARNING
+			"cpumask_of_node(%d): no node_to_cpumask_map!\n",
+			node);
+		dump_stack();
+		return cpu_online_mask;
+	}
+	return node_to_cpumask_map[node];
+}
+EXPORT_SYMBOL(cpumask_of_node);
+#endif
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index 64c9cf043cdd..d73aaa892371 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -20,12 +20,6 @@
 #include <asm/acpi.h>
 #include <asm/k8.h>
 
-#ifdef CONFIG_DEBUG_PER_CPU_MAPS
-# define DBG(x...) printk(KERN_DEBUG x)
-#else
-# define DBG(x...)
-#endif
-
 struct pglist_data *node_data[MAX_NUMNODES] __read_mostly;
 EXPORT_SYMBOL(node_data);
 
@@ -49,12 +43,6 @@ DEFINE_EARLY_PER_CPU(int, x86_cpu_to_node_map, NUMA_NO_NODE);
 EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_node_map);
 
 /*
- * Which logical CPUs are on which nodes
- */
-cpumask_t *node_to_cpumask_map;
-EXPORT_SYMBOL(node_to_cpumask_map);
-
-/*
  * Given a shift value, try to populate memnodemap[]
  * Returns :
  * 1 if OK
@@ -661,36 +649,6 @@ void __init init_cpu_to_node(void)
 #endif
 
 
-/*
- * Allocate node_to_cpumask_map based on number of available nodes
- * Requires node_possible_map to be valid.
- *
- * Note: node_to_cpumask() is not valid until after this is done.
- * (Use CONFIG_DEBUG_PER_CPU_MAPS to check this.)
- */
-void __init setup_node_to_cpumask_map(void)
-{
-	unsigned int node, num = 0;
-	cpumask_t *map;
-
-	/* setup nr_node_ids if not done yet */
-	if (nr_node_ids == MAX_NUMNODES) {
-		for_each_node_mask(node, node_possible_map)
-			num = node;
-		nr_node_ids = num + 1;
-	}
-
-	/* allocate the map */
-	map = alloc_bootmem_low(nr_node_ids * sizeof(cpumask_t));
-	DBG("node_to_cpumask_map at %p for %d nodes\n", map, nr_node_ids);
-
-	pr_debug("Node to cpumask map at %p for %d nodes\n",
-		 map, nr_node_ids);
-
-	/* node_to_cpumask() will now work */
-	node_to_cpumask_map = map;
-}
-
 void __cpuinit numa_set_node(int cpu, int node)
 {
 	int *cpu_to_node_map = early_per_cpu_ptr(x86_cpu_to_node_map);
@@ -723,12 +681,12 @@ void __cpuinit numa_clear_node(int cpu)
 
 void __cpuinit numa_add_cpu(int cpu)
 {
-	cpu_set(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]);
+	cpumask_set_cpu(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]);
 }
 
 void __cpuinit numa_remove_cpu(int cpu)
 {
-	cpu_clear(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]);
+	cpumask_clear_cpu(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]);
 }
 
 #else /* CONFIG_DEBUG_PER_CPU_MAPS */
@@ -739,20 +697,20 @@ void __cpuinit numa_remove_cpu(int cpu)
 static void __cpuinit numa_set_cpumask(int cpu, int enable)
 {
 	int node = early_cpu_to_node(cpu);
-	cpumask_t *mask;
+	struct cpumask *mask;
 	char buf[64];
 
-	if (node_to_cpumask_map == NULL) {
-		printk(KERN_ERR "node_to_cpumask_map NULL\n");
+	mask = node_to_cpumask_map[node];
+	if (mask == NULL) {
+		printk(KERN_ERR "node_to_cpumask_map[%i] NULL\n", node);
 		dump_stack();
 		return;
 	}
 
-	mask = &node_to_cpumask_map[node];
 	if (enable)
-		cpu_set(cpu, *mask);
+		cpumask_set_cpu(cpu, mask);
 	else
-		cpu_clear(cpu, *mask);
+		cpumask_clear_cpu(cpu, mask);
 
 	cpulist_scnprintf(buf, sizeof(buf), mask);
 	printk(KERN_DEBUG "%s cpu %d node %d: mask now %s\n",
@@ -799,59 +757,6 @@ int early_cpu_to_node(int cpu)
 	return per_cpu(x86_cpu_to_node_map, cpu);
 }
 
-
-/* empty cpumask */
-static const cpumask_t cpu_mask_none;
-
-/*
- * Returns a pointer to the bitmask of CPUs on Node 'node'.
- */
-const cpumask_t *cpumask_of_node(int node)
-{
-	if (node_to_cpumask_map == NULL) {
-		printk(KERN_WARNING
-			"cpumask_of_node(%d): no node_to_cpumask_map!\n",
-			node);
-		dump_stack();
-		return (const cpumask_t *)&cpu_online_map;
-	}
-	if (node >= nr_node_ids) {
-		printk(KERN_WARNING
-			"cpumask_of_node(%d): node > nr_node_ids(%d)\n",
-			node, nr_node_ids);
-		dump_stack();
-		return &cpu_mask_none;
-	}
-	return &node_to_cpumask_map[node];
-}
-EXPORT_SYMBOL(cpumask_of_node);
-
-/*
- * Returns a bitmask of CPUs on Node 'node'.
- *
- * Side note: this function creates the returned cpumask on the stack
- * so with a high NR_CPUS count, excessive stack space is used.  The
- * node_to_cpumask_ptr function should be used whenever possible.
- */
-cpumask_t node_to_cpumask(int node)
-{
-	if (node_to_cpumask_map == NULL) {
-		printk(KERN_WARNING
-			"node_to_cpumask(%d): no node_to_cpumask_map!\n", node);
-		dump_stack();
-		return cpu_online_map;
-	}
-	if (node >= nr_node_ids) {
-		printk(KERN_WARNING
-			"node_to_cpumask(%d): node > nr_node_ids(%d)\n",
-			node, nr_node_ids);
-		dump_stack();
-		return cpu_mask_none;
-	}
-	return node_to_cpumask_map[node];
-}
-EXPORT_SYMBOL(node_to_cpumask);
-
 /*
  * --------- end of debug versions of the numa functions ---------
  */
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index d71e1b636ce6..797f9f107cb6 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -945,71 +945,94 @@ int _set_memory_uc(unsigned long addr, int numpages)
 
 int set_memory_uc(unsigned long addr, int numpages)
 {
+	int ret;
+
 	/*
 	 * for now UC MINUS. see comments in ioremap_nocache()
 	 */
-	if (reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE,
-			    _PAGE_CACHE_UC_MINUS, NULL))
-		return -EINVAL;
+	ret = reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE,
+			    _PAGE_CACHE_UC_MINUS, NULL);
+	if (ret)
+		goto out_err;
+
+	ret = _set_memory_uc(addr, numpages);
+	if (ret)
+		goto out_free;
 
-	return _set_memory_uc(addr, numpages);
+	return 0;
+
+out_free:
+	free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE);
+out_err:
+	return ret;
 }
 EXPORT_SYMBOL(set_memory_uc);
 
 int set_memory_array_uc(unsigned long *addr, int addrinarray)
 {
-	unsigned long start;
-	unsigned long end;
-	int i;
+	int i, j;
+	int ret;
+
 	/*
 	 * 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;
+		ret = reserve_memtype(__pa(addr[i]), __pa(addr[i]) + PAGE_SIZE,
+					_PAGE_CACHE_UC_MINUS, NULL);
+		if (ret)
+			goto out_free;
 	}
 
-	return change_page_attr_set(addr, addrinarray,
+	ret = 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;
+	if (ret)
+		goto out_free;
+
+	return 0;
+
+out_free:
+	for (j = 0; j < i; j++)
+		free_memtype(__pa(addr[j]), __pa(addr[j]) + PAGE_SIZE);
+
+	return ret;
 }
 EXPORT_SYMBOL(set_memory_array_uc);
 
 int _set_memory_wc(unsigned long addr, int numpages)
 {
-	return change_page_attr_set(&addr, numpages,
+	int ret;
+	ret = change_page_attr_set(&addr, numpages,
+				    __pgprot(_PAGE_CACHE_UC_MINUS), 0);
+
+	if (!ret) {
+		ret = change_page_attr_set(&addr, numpages,
 				    __pgprot(_PAGE_CACHE_WC), 0);
+	}
+	return ret;
 }
 
 int set_memory_wc(unsigned long addr, int numpages)
 {
+	int ret;
+
 	if (!pat_enabled)
 		return set_memory_uc(addr, numpages);
 
-	if (reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE,
-		_PAGE_CACHE_WC, NULL))
-		return -EINVAL;
+	ret = reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE,
+		_PAGE_CACHE_WC, NULL);
+	if (ret)
+		goto out_err;
+
+	ret = _set_memory_wc(addr, numpages);
+	if (ret)
+		goto out_free;
+
+	return 0;
 
-	return _set_memory_wc(addr, numpages);
+out_free:
+	free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE);
+out_err:
+	return ret;
 }
 EXPORT_SYMBOL(set_memory_wc);
 
@@ -1021,29 +1044,31 @@ int _set_memory_wb(unsigned long addr, int numpages)
 
 int set_memory_wb(unsigned long addr, int numpages)
 {
-	free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE);
+	int ret;
+
+	ret = _set_memory_wb(addr, numpages);
+	if (ret)
+		return ret;
 
-	return _set_memory_wb(addr, numpages);
+	free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE);
+	return 0;
 }
 EXPORT_SYMBOL(set_memory_wb);
 
 int set_memory_array_wb(unsigned long *addr, int addrinarray)
 {
 	int i;
+	int ret;
 
-	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,
+	ret = change_page_attr_clear(addr, addrinarray,
 				      __pgprot(_PAGE_CACHE_MASK), 1);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < addrinarray; i++)
+		free_memtype(__pa(addr[i]), __pa(addr[i]) + PAGE_SIZE);
+
+	return 0;
 }
 EXPORT_SYMBOL(set_memory_array_wb);
 
@@ -1136,6 +1161,8 @@ int set_pages_array_wb(struct page **pages, int addrinarray)
 
 	retval = cpa_clear_pages_array(pages, addrinarray,
 			__pgprot(_PAGE_CACHE_MASK));
+	if (retval)
+		return retval;
 
 	for (i = 0; i < addrinarray; i++) {
 		start = (unsigned long)page_address(pages[i]);
@@ -1143,7 +1170,7 @@ int set_pages_array_wb(struct page **pages, int addrinarray)
 		free_memtype(start, end);
 	}
 
-	return retval;
+	return 0;
 }
 EXPORT_SYMBOL(set_pages_array_wb);
 
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index 640339ee4fb2..e6718bb28065 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -31,7 +31,7 @@
 #ifdef CONFIG_X86_PAT
 int __read_mostly pat_enabled = 1;
 
-void __cpuinit pat_disable(const char *reason)
+static inline void pat_disable(const char *reason)
 {
 	pat_enabled = 0;
 	printk(KERN_INFO "%s\n", reason);
@@ -182,10 +182,10 @@ static unsigned long pat_x_mtrr_type(u64 start, u64 end, unsigned long req_type)
 		u8 mtrr_type;
 
 		mtrr_type = mtrr_type_lookup(start, end);
-		if (mtrr_type == MTRR_TYPE_UNCACHABLE)
-			return _PAGE_CACHE_UC;
-		if (mtrr_type == MTRR_TYPE_WRCOMB)
-			return _PAGE_CACHE_WC;
+		if (mtrr_type != MTRR_TYPE_WRBACK)
+			return _PAGE_CACHE_UC_MINUS;
+
+		return _PAGE_CACHE_WB;
 	}
 
 	return req_type;
@@ -352,23 +352,13 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 		return 0;
 	}
 
-	if (req_type == -1) {
-		/*
-		 * Call mtrr_lookup to get the type hint. This is an
-		 * optimization for /dev/mem mmap'ers into WB memory (BIOS
-		 * tools and ACPI tools). Use WB request for WB memory and use
-		 * UC_MINUS otherwise.
-		 */
-		u8 mtrr_type = mtrr_type_lookup(start, end);
-
-		if (mtrr_type == MTRR_TYPE_WRBACK)
-			actual_type = _PAGE_CACHE_WB;
-		else
-			actual_type = _PAGE_CACHE_UC_MINUS;
-	} else {
-		actual_type = pat_x_mtrr_type(start, end,
-					      req_type & _PAGE_CACHE_MASK);
-	}
+	/*
+	 * Call mtrr_lookup to get the type hint. This is an
+	 * optimization for /dev/mem mmap'ers into WB memory (BIOS
+	 * tools and ACPI tools). Use WB request for WB memory and use
+	 * UC_MINUS otherwise.
+	 */
+	actual_type = pat_x_mtrr_type(start, end, req_type & _PAGE_CACHE_MASK);
 
 	if (new_type)
 		*new_type = actual_type;
@@ -546,9 +536,7 @@ static inline int range_is_allowed(unsigned long pfn, unsigned long size)
 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 = -1;
-	int retval;
+	unsigned long flags = _PAGE_CACHE_WB;
 
 	if (!range_is_allowed(pfn, size))
 		return 0;
@@ -576,64 +564,11 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
 	}
 #endif
 
-	/*
-	 * 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 != -1) {
-		retval = reserve_memtype(offset, offset + size, flags, NULL);
-	} else {
-		retval = reserve_memtype(offset, offset + size, -1, &flags);
-	}
-
-	if (retval < 0)
-		return 0;
-
-	if (((pfn < max_low_pfn_mapped) ||
-	     (pfn >= (1UL<<(32 - PAGE_SHIFT)) && pfn < max_pfn_mapped)) &&
-	    ioremap_change_attr((unsigned long)__va(offset), size, flags) < 0) {
-		free_memtype(offset, offset + size);
-		printk(KERN_INFO
-		"%s:%d /dev/mem ioremap_change_attr failed %s for %Lx-%Lx\n",
-			current->comm, current->pid,
-			cattr_name(flags),
-			offset, (unsigned long long)(offset + size));
-		return 0;
-	}
-
 	*vma_prot = __pgprot((pgprot_val(*vma_prot) & ~_PAGE_CACHE_MASK) |
 			     flags);
 	return 1;
 }
 
-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;
-
-	reserve_memtype(addr, addr + size, want_flags, &flags);
-	if (flags != want_flags) {
-		printk(KERN_INFO
-		"%s:%d /dev/mem expected mapping type %s for %Lx-%Lx, got %s\n",
-			current->comm, current->pid,
-			cattr_name(want_flags),
-			addr, (unsigned long long)(addr + size),
-			cattr_name(flags));
-	}
-}
-
-void unmap_devmem(unsigned long pfn, unsigned long size, pgprot_t vma_prot)
-{
-	u64 addr = (u64)pfn << PAGE_SHIFT;
-
-	free_memtype(addr, addr + size);
-}
-
 /*
  * Change the memory type for the physial address range in kernel identity
  * mapping space if that range is a part of identity map.
@@ -671,8 +606,8 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot,
 {
 	int is_ram = 0;
 	int ret;
-	unsigned long flags;
 	unsigned long want_flags = (pgprot_val(*vma_prot) & _PAGE_CACHE_MASK);
+	unsigned long flags = want_flags;
 
 	is_ram = pat_pagerange_is_ram(paddr, paddr + size);
 
@@ -734,29 +669,28 @@ static void free_pfn_range(u64 paddr, unsigned long size)
  *
  * If the vma has a linear pfn mapping for the entire range, we get the prot
  * from pte and reserve the entire vma range with single reserve_pfn_range call.
- * Otherwise, we reserve the entire vma range, my ging through the PTEs page
- * by page to get physical address and protection.
  */
 int track_pfn_vma_copy(struct vm_area_struct *vma)
 {
-	int retval = 0;
-	unsigned long i, j;
 	resource_size_t paddr;
 	unsigned long prot;
-	unsigned long vma_start = vma->vm_start;
-	unsigned long vma_end = vma->vm_end;
-	unsigned long vma_size = vma_end - vma_start;
+	unsigned long vma_size = vma->vm_end - vma->vm_start;
 	pgprot_t pgprot;
 
 	if (!pat_enabled)
 		return 0;
 
+	/*
+	 * For now, only handle remap_pfn_range() vmas where
+	 * is_linear_pfn_mapping() == TRUE. Handling of
+	 * vm_insert_pfn() is TBD.
+	 */
 	if (is_linear_pfn_mapping(vma)) {
 		/*
 		 * reserve the whole chunk covered by vma. We need the
 		 * starting address and protection from pte.
 		 */
-		if (follow_phys(vma, vma_start, 0, &prot, &paddr)) {
+		if (follow_phys(vma, vma->vm_start, 0, &prot, &paddr)) {
 			WARN_ON_ONCE(1);
 			return -EINVAL;
 		}
@@ -764,28 +698,7 @@ int track_pfn_vma_copy(struct vm_area_struct *vma)
 		return reserve_pfn_range(paddr, vma_size, &pgprot, 1);
 	}
 
-	/* reserve entire vma page by page, using pfn and prot from pte */
-	for (i = 0; i < vma_size; i += PAGE_SIZE) {
-		if (follow_phys(vma, vma_start + i, 0, &prot, &paddr))
-			continue;
-
-		pgprot = __pgprot(prot);
-		retval = reserve_pfn_range(paddr, PAGE_SIZE, &pgprot, 1);
-		if (retval)
-			goto cleanup_ret;
-	}
 	return 0;
-
-cleanup_ret:
-	/* Reserve error: Cleanup partial reservation and return error */
-	for (j = 0; j < i; j += PAGE_SIZE) {
-		if (follow_phys(vma, vma_start + j, 0, &prot, &paddr))
-			continue;
-
-		free_pfn_range(paddr, PAGE_SIZE);
-	}
-
-	return retval;
 }
 
 /*
@@ -795,50 +708,28 @@ cleanup_ret:
  * prot is passed in as a parameter for the new mapping. If the vma has a
  * linear pfn mapping for the entire range reserve the entire vma range with
  * single reserve_pfn_range call.
- * Otherwise, we look t the pfn and size and reserve only the specified range
- * page by page.
- *
- * Note that this function can be called with caller trying to map only a
- * subrange/page inside the vma.
  */
 int track_pfn_vma_new(struct vm_area_struct *vma, pgprot_t *prot,
 			unsigned long pfn, unsigned long size)
 {
-	int retval = 0;
-	unsigned long i, j;
-	resource_size_t base_paddr;
 	resource_size_t paddr;
-	unsigned long vma_start = vma->vm_start;
-	unsigned long vma_end = vma->vm_end;
-	unsigned long vma_size = vma_end - vma_start;
+	unsigned long vma_size = vma->vm_end - vma->vm_start;
 
 	if (!pat_enabled)
 		return 0;
 
+	/*
+	 * For now, only handle remap_pfn_range() vmas where
+	 * is_linear_pfn_mapping() == TRUE. Handling of
+	 * vm_insert_pfn() is TBD.
+	 */
 	if (is_linear_pfn_mapping(vma)) {
 		/* reserve the whole chunk starting from vm_pgoff */
 		paddr = (resource_size_t)vma->vm_pgoff << PAGE_SHIFT;
 		return reserve_pfn_range(paddr, vma_size, prot, 0);
 	}
 
-	/* reserve page by page using pfn and size */
-	base_paddr = (resource_size_t)pfn << PAGE_SHIFT;
-	for (i = 0; i < size; i += PAGE_SIZE) {
-		paddr = base_paddr + i;
-		retval = reserve_pfn_range(paddr, PAGE_SIZE, prot, 0);
-		if (retval)
-			goto cleanup_ret;
-	}
 	return 0;
-
-cleanup_ret:
-	/* Reserve error: Cleanup partial reservation and return error */
-	for (j = 0; j < i; j += PAGE_SIZE) {
-		paddr = base_paddr + j;
-		free_pfn_range(paddr, PAGE_SIZE);
-	}
-
-	return retval;
 }
 
 /*
@@ -849,39 +740,23 @@ cleanup_ret:
 void untrack_pfn_vma(struct vm_area_struct *vma, unsigned long pfn,
 			unsigned long size)
 {
-	unsigned long i;
 	resource_size_t paddr;
-	unsigned long prot;
-	unsigned long vma_start = vma->vm_start;
-	unsigned long vma_end = vma->vm_end;
-	unsigned long vma_size = vma_end - vma_start;
+	unsigned long vma_size = vma->vm_end - vma->vm_start;
 
 	if (!pat_enabled)
 		return;
 
+	/*
+	 * For now, only handle remap_pfn_range() vmas where
+	 * is_linear_pfn_mapping() == TRUE. Handling of
+	 * vm_insert_pfn() is TBD.
+	 */
 	if (is_linear_pfn_mapping(vma)) {
 		/* free the whole chunk starting from vm_pgoff */
 		paddr = (resource_size_t)vma->vm_pgoff << PAGE_SHIFT;
 		free_pfn_range(paddr, vma_size);
 		return;
 	}
-
-	if (size != 0 && size != vma_size) {
-		/* free page by page, using pfn and size */
-		paddr = (resource_size_t)pfn << PAGE_SHIFT;
-		for (i = 0; i < size; i += PAGE_SIZE) {
-			paddr = paddr + i;
-			free_pfn_range(paddr, PAGE_SIZE);
-		}
-	} else {
-		/* free entire vma, page by page, using the pfn from pte */
-		for (i = 0; i < vma_size; i += PAGE_SIZE) {
-			if (follow_phys(vma, vma_start + i, 0, &prot, &paddr))
-				continue;
-
-			free_pfn_range(paddr, PAGE_SIZE);
-		}
-	}
 }
 
 pgprot_t pgprot_writecombine(pgprot_t prot)
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 5b7c7c8464fe..7aa03a5389f5 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -345,7 +345,8 @@ void __native_set_fixmap(enum fixed_addresses idx, pte_t pte)
 	fixmaps_set++;
 }
 
-void native_set_fixmap(enum fixed_addresses idx, unsigned long phys, pgprot_t flags)
+void native_set_fixmap(enum fixed_addresses idx, phys_addr_t phys,
+		       pgprot_t flags)
 {
 	__native_set_fixmap(idx, pfn_pte(phys >> PAGE_SHIFT, flags));
 }
diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c
index 574c8bc95ef0..c7d272b8574c 100644
--- a/arch/x86/mm/srat_64.c
+++ b/arch/x86/mm/srat_64.c
@@ -116,6 +116,36 @@ void __init acpi_numa_slit_init(struct acpi_table_slit *slit)
 	reserve_early(phys, phys + length, "ACPI SLIT");
 }
 
+/* Callback for Proximity Domain -> x2APIC mapping */
+void __init
+acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa)
+{
+	int pxm, node;
+	int apic_id;
+
+	if (srat_disabled())
+		return;
+	if (pa->header.length < sizeof(struct acpi_srat_x2apic_cpu_affinity)) {
+		bad_srat();
+		return;
+	}
+	if ((pa->flags & ACPI_SRAT_CPU_ENABLED) == 0)
+		return;
+	pxm = pa->proximity_domain;
+	node = setup_node(pxm);
+	if (node < 0) {
+		printk(KERN_ERR "SRAT: Too many proximity domains %x\n", pxm);
+		bad_srat();
+		return;
+	}
+
+	apic_id = pa->apic_id;
+	apicid_to_node[apic_id] = node;
+	acpi_numa = 1;
+	printk(KERN_INFO "SRAT: PXM %u -> APIC %u -> Node %u\n",
+	       pxm, apic_id, node);
+}
+
 /* Callback for Proximity Domain -> LAPIC mapping */
 void __init
 acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa)