Merge branch 'devicetree/for-x86' of git://git.secretlab.ca/git/linux-2.6 into x86/platform

Reason: x86 devicetree support for ce4100 depends on those device tree
	changes scheduled for .39.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

14 files changed, 411 insertions, 110 deletions

diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 55543397a8a7..09df2f9a3d69 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -23,7 +23,7 @@ mmiotrace-y			:= kmmio.o pf_in.o mmio-mod.o
 obj-$(CONFIG_MMIOTRACE_TEST)	+= testmmiotrace.o
 
 obj-$(CONFIG_NUMA)		+= numa.o numa_$(BITS).o
-obj-$(CONFIG_K8_NUMA)		+= k8topology_64.o
+obj-$(CONFIG_AMD_NUMA)		+= amdtopology_64.o
 obj-$(CONFIG_ACPI_NUMA)		+= srat_$(BITS).o
 
 obj-$(CONFIG_HAVE_MEMBLOCK)		+= memblock.o
diff --git a/arch/x86/mm/k8topology_64.c b/arch/x86/mm/amdtopology_64.c
index 804a3b6c6e14..f21962c435ed 100644
--- a/arch/x86/mm/k8topology_64.c
+++ b/arch/x86/mm/amdtopology_64.c
@@ -1,8 +1,8 @@
 /*
- * AMD K8 NUMA support.
+ * AMD NUMA support.
  * Discover the memory map and associated nodes.
  *
- * This version reads it directly from the K8 northbridge.
+ * This version reads it directly from the AMD northbridge.
  *
  * Copyright 2002,2003 Andi Kleen, SuSE Labs.
  */
@@ -27,6 +27,7 @@
 #include <asm/amd_nb.h>
 
 static struct bootnode __initdata nodes[8];
+static unsigned char __initdata nodeids[8];
 static nodemask_t __initdata nodes_parsed = NODE_MASK_NONE;
 
 static __init int find_northbridge(void)
@@ -57,7 +58,7 @@ static __init void early_get_boot_cpu_id(void)
 {
 	/*
 	 * need to get the APIC ID of the BSP so can use that to
-	 * create apicid_to_node in k8_scan_nodes()
+	 * create apicid_to_node in amd_scan_nodes()
 	 */
 #ifdef CONFIG_X86_MPPARSE
 	/*
@@ -66,23 +67,9 @@ static __init void early_get_boot_cpu_id(void)
 	if (smp_found_config)
 		early_get_smp_config();
 #endif
-	early_init_lapic_mapping();
 }
 
-int __init k8_get_nodes(struct bootnode *physnodes)
-{
-	int i;
-	int ret = 0;
-
-	for_each_node_mask(i, nodes_parsed) {
-		physnodes[ret].start = nodes[i].start;
-		physnodes[ret].end = nodes[i].end;
-		ret++;
-	}
-	return ret;
-}
-
-int __init k8_numa_init(unsigned long start_pfn, unsigned long end_pfn)
+int __init amd_numa_init(unsigned long start_pfn, unsigned long end_pfn)
 {
 	unsigned long start = PFN_PHYS(start_pfn);
 	unsigned long end = PFN_PHYS(end_pfn);
@@ -114,7 +101,7 @@ int __init k8_numa_init(unsigned long start_pfn, unsigned long end_pfn)
 		base = read_pci_config(0, nb, 1, 0x40 + i*8);
 		limit = read_pci_config(0, nb, 1, 0x44 + i*8);
 
-		nodeid = limit & 7;
+		nodeids[i] = nodeid = limit & 7;
 		if ((base & 3) == 0) {
 			if (i < numnodes)
 				pr_info("Skipping disabled node %d\n", i);
@@ -194,7 +181,77 @@ int __init k8_numa_init(unsigned long start_pfn, unsigned long end_pfn)
 	return 0;
 }
 
-int __init k8_scan_nodes(void)
+#ifdef CONFIG_NUMA_EMU
+static s16 fake_apicid_to_node[MAX_LOCAL_APIC] __initdata = {
+	[0 ... MAX_LOCAL_APIC-1] = NUMA_NO_NODE
+};
+
+void __init amd_get_nodes(struct bootnode *physnodes)
+{
+	int i;
+
+	for_each_node_mask(i, nodes_parsed) {
+		physnodes[i].start = nodes[i].start;
+		physnodes[i].end = nodes[i].end;
+	}
+}
+
+static int __init find_node_by_addr(unsigned long addr)
+{
+	int ret = NUMA_NO_NODE;
+	int i;
+
+	for (i = 0; i < 8; i++)
+		if (addr >= nodes[i].start && addr < nodes[i].end) {
+			ret = i;
+			break;
+		}
+	return ret;
+}
+
+/*
+ * For NUMA emulation, fake proximity domain (_PXM) to node id mappings must be
+ * setup to represent the physical topology but reflect the emulated
+ * environment.  For each emulated node, the real node which it appears on is
+ * found and a fake pxm to nid mapping is created which mirrors the actual
+ * locality.  node_distance() then represents the correct distances between
+ * emulated nodes by using the fake acpi mappings to pxms.
+ */
+void __init amd_fake_nodes(const struct bootnode *nodes, int nr_nodes)
+{
+	unsigned int bits;
+	unsigned int cores;
+	unsigned int apicid_base = 0;
+	int i;
+
+	bits = boot_cpu_data.x86_coreid_bits;
+	cores = 1 << bits;
+	early_get_boot_cpu_id();
+	if (boot_cpu_physical_apicid > 0)
+		apicid_base = boot_cpu_physical_apicid;
+
+	for (i = 0; i < nr_nodes; i++) {
+		int index;
+		int nid;
+		int j;
+
+		nid = find_node_by_addr(nodes[i].start);
+		if (nid == NUMA_NO_NODE)
+			continue;
+
+		index = nodeids[nid] << bits;
+		if (fake_apicid_to_node[index + apicid_base] == NUMA_NO_NODE)
+			for (j = apicid_base; j < cores + apicid_base; j++)
+				fake_apicid_to_node[index + j] = i;
+#ifdef CONFIG_ACPI_NUMA
+		__acpi_map_pxm_to_node(nid, i);
+#endif
+	}
+	memcpy(apicid_to_node, fake_apicid_to_node, sizeof(apicid_to_node));
+}
+#endif /* CONFIG_NUMA_EMU */
+
+int __init amd_scan_nodes(void)
 {
 	unsigned int bits;
 	unsigned int cores;
diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c
index 738e6593799d..dbe34b931374 100644
--- a/arch/x86/mm/gup.c
+++ b/arch/x86/mm/gup.c
@@ -8,6 +8,7 @@
 #include <linux/mm.h>
 #include <linux/vmstat.h>
 #include <linux/highmem.h>
+#include <linux/swap.h>
 
 #include <asm/pgtable.h>
 
@@ -89,6 +90,7 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
 		VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
 		page = pte_page(pte);
 		get_page(page);
+		SetPageReferenced(page);
 		pages[*nr] = page;
 		(*nr)++;
 
@@ -103,6 +105,17 @@ 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);
+	SetPageReferenced(page);
+}
+
+static inline void get_huge_page_tail(struct page *page)
+{
+	/*
+	 * __split_huge_page_refcount() cannot run
+	 * from under us.
+	 */
+	VM_BUG_ON(atomic_read(&page->_count) < 0);
+	atomic_inc(&page->_count);
 }
 
 static noinline int gup_huge_pmd(pmd_t pmd, unsigned long addr,
@@ -128,6 +141,8 @@ static noinline int gup_huge_pmd(pmd_t pmd, unsigned long addr,
 	do {
 		VM_BUG_ON(compound_head(page) != head);
 		pages[*nr] = page;
+		if (PageTail(page))
+			get_huge_page_tail(page);
 		(*nr)++;
 		page++;
 		refs++;
@@ -148,7 +163,18 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
 		pmd_t pmd = *pmdp;
 
 		next = pmd_addr_end(addr, end);
-		if (pmd_none(pmd))
+		/*
+		 * The pmd_trans_splitting() check below explains why
+		 * pmdp_splitting_flush has to flush the tlb, to stop
+		 * this gup-fast code from running while we set the
+		 * splitting bit in the pmd. Returning zero will take
+		 * the slow path that will call wait_split_huge_page()
+		 * if the pmd is still in splitting state. gup-fast
+		 * can't because it has irq disabled and
+		 * wait_split_huge_page() would never return as the
+		 * tlb flush IPI wouldn't run.
+		 */
+		if (pmd_none(pmd) || pmd_trans_splitting(pmd))
 			return 0;
 		if (unlikely(pmd_large(pmd))) {
 			if (!gup_huge_pmd(pmd, addr, next, write, pages, nr))
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index c0e28a13de7d..947f42abe820 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -364,8 +364,9 @@ void free_init_pages(char *what, unsigned long begin, unsigned long end)
 	/*
 	 * We just marked the kernel text read only above, now that
 	 * we are going to free part of that, we need to make that
-	 * writeable first.
+	 * writeable and non-executable first.
 	 */
+	set_memory_nx(begin, (end - begin) >> PAGE_SHIFT);
 	set_memory_rw(begin, (end - begin) >> PAGE_SHIFT);
 
 	printk(KERN_INFO "Freeing %s: %luk freed\n", what, (end - begin) >> 10);
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 0e969f9f401b..c821074b7f0b 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -45,6 +45,7 @@
 #include <asm/bugs.h>
 #include <asm/tlb.h>
 #include <asm/tlbflush.h>
+#include <asm/olpc_ofw.h>
 #include <asm/pgalloc.h>
 #include <asm/sections.h>
 #include <asm/paravirt.h>
@@ -226,7 +227,7 @@ page_table_range_init(unsigned long start, unsigned long end, pgd_t *pgd_base)
 
 static inline int is_kernel_text(unsigned long addr)
 {
-	if (addr >= PAGE_OFFSET && addr <= (unsigned long)__init_end)
+	if (addr >= (unsigned long)_text && addr <= (unsigned long)__init_end)
 		return 1;
 	return 0;
 }
@@ -715,6 +716,7 @@ void __init paging_init(void)
 	/*
 	 * NOTE: at this point the bootmem allocator is fully available.
 	 */
+	olpc_dt_build_devicetree();
 	sparse_init();
 	zone_sizes_init();
 }
@@ -912,6 +914,23 @@ void set_kernel_text_ro(void)
 	set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT);
 }
 
+static void mark_nxdata_nx(void)
+{
+	/*
+	 * When this called, init has already been executed and released,
+	 * so everything past _etext sould be NX.
+	 */
+	unsigned long start = PFN_ALIGN(_etext);
+	/*
+	 * This comes from is_kernel_text upper limit. Also HPAGE where used:
+	 */
+	unsigned long size = (((unsigned long)__init_end + HPAGE_SIZE) & HPAGE_MASK) - start;
+
+	if (__supported_pte_mask & _PAGE_NX)
+		printk(KERN_INFO "NX-protecting the kernel data: %luk\n", size >> 10);
+	set_pages_nx(virt_to_page(start), size >> PAGE_SHIFT);
+}
+
 void mark_rodata_ro(void)
 {
 	unsigned long start = PFN_ALIGN(_text);
@@ -946,6 +965,7 @@ 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
+	mark_nxdata_nx();
 }
 #endif
 
diff --git a/arch/x86/mm/kmemcheck/error.c b/arch/x86/mm/kmemcheck/error.c
index af3b6c8a436f..704a37cedddb 100644
--- a/arch/x86/mm/kmemcheck/error.c
+++ b/arch/x86/mm/kmemcheck/error.c
@@ -185,7 +185,7 @@ void kmemcheck_error_save(enum kmemcheck_shadow state,
 	e->trace.entries = e->trace_entries;
 	e->trace.max_entries = ARRAY_SIZE(e->trace_entries);
 	e->trace.skip = 0;
-	save_stack_trace_bp(&e->trace, regs->bp);
+	save_stack_trace_regs(&e->trace, regs);
 
 	/* Round address down to nearest 16 bytes */
 	shadow_copy = kmemcheck_shadow_lookup(address
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 787c52ca49c3..ebf6d7887a38 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -2,6 +2,28 @@
 #include <linux/topology.h>
 #include <linux/module.h>
 #include <linux/bootmem.h>
+#include <asm/numa.h>
+#include <asm/acpi.h>
+
+int __initdata numa_off;
+
+static __init int numa_setup(char *opt)
+{
+	if (!opt)
+		return -EINVAL;
+	if (!strncmp(opt, "off", 3))
+		numa_off = 1;
+#ifdef CONFIG_NUMA_EMU
+	if (!strncmp(opt, "fake=", 5))
+		numa_emu_cmdline(opt + 5);
+#endif
+#ifdef CONFIG_ACPI_NUMA
+	if (!strncmp(opt, "noacpi", 6))
+		acpi_numa = -1;
+#endif
+	return 0;
+}
+early_param("numa", numa_setup);
 
 /*
  * Which logical CPUs are on which nodes
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index 7ffc9b727efd..95ea1551eebc 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -30,7 +30,6 @@ s16 apicid_to_node[MAX_LOCAL_APIC] __cpuinitdata = {
 	[0 ... MAX_LOCAL_APIC-1] = NUMA_NO_NODE
 };
 
-int numa_off __initdata;
 static unsigned long __initdata nodemap_addr;
 static unsigned long __initdata nodemap_size;
 
@@ -260,30 +259,35 @@ void __init numa_init_array(void)
 #ifdef CONFIG_NUMA_EMU
 /* Numa emulation */
 static struct bootnode nodes[MAX_NUMNODES] __initdata;
-static struct bootnode physnodes[MAX_NUMNODES] __initdata;
+static struct bootnode physnodes[MAX_NUMNODES] __cpuinitdata;
 static char *cmdline __initdata;
 
+void __init numa_emu_cmdline(char *str)
+{
+	cmdline = str;
+}
+
 static int __init setup_physnodes(unsigned long start, unsigned long end,
-					int acpi, int k8)
+					int acpi, int amd)
 {
-	int nr_nodes = 0;
 	int ret = 0;
 	int i;
 
+	memset(physnodes, 0, sizeof(physnodes));
 #ifdef CONFIG_ACPI_NUMA
 	if (acpi)
-		nr_nodes = acpi_get_nodes(physnodes);
+		acpi_get_nodes(physnodes, start, end);
 #endif
-#ifdef CONFIG_K8_NUMA
-	if (k8)
-		nr_nodes = k8_get_nodes(physnodes);
+#ifdef CONFIG_AMD_NUMA
+	if (amd)
+		amd_get_nodes(physnodes);
 #endif
 	/*
 	 * Basic sanity checking on the physical node map: there may be errors
-	 * if the SRAT or K8 incorrectly reported the topology or the mem=
+	 * if the SRAT or AMD code incorrectly reported the topology or the mem=
 	 * kernel parameter is used.
 	 */
-	for (i = 0; i < nr_nodes; i++) {
+	for (i = 0; i < MAX_NUMNODES; i++) {
 		if (physnodes[i].start == physnodes[i].end)
 			continue;
 		if (physnodes[i].start > end) {
@@ -298,17 +302,6 @@ static int __init setup_physnodes(unsigned long start, unsigned long end,
 			physnodes[i].start = start;
 		if (physnodes[i].end > end)
 			physnodes[i].end = end;
-	}
-
-	/*
-	 * Remove all nodes that have no memory or were truncated because of the
-	 * limited address range.
-	 */
-	for (i = 0; i < nr_nodes; i++) {
-		if (physnodes[i].start == physnodes[i].end)
-			continue;
-		physnodes[ret].start = physnodes[i].start;
-		physnodes[ret].end = physnodes[i].end;
 		ret++;
 	}
 
@@ -324,6 +317,24 @@ static int __init setup_physnodes(unsigned long start, unsigned long end,
 	return ret;
 }
 
+static void __init fake_physnodes(int acpi, int amd, int nr_nodes)
+{
+	int i;
+
+	BUG_ON(acpi && amd);
+#ifdef CONFIG_ACPI_NUMA
+	if (acpi)
+		acpi_fake_nodes(nodes, nr_nodes);
+#endif
+#ifdef CONFIG_AMD_NUMA
+	if (amd)
+		amd_fake_nodes(nodes, nr_nodes);
+#endif
+	if (!acpi && !amd)
+		for (i = 0; i < nr_cpu_ids; i++)
+			numa_set_node(i, 0);
+}
+
 /*
  * Setups up nid to range from addr to addr + size.  If the end
  * boundary is greater than max_addr, then max_addr is used instead.
@@ -352,8 +363,7 @@ static int __init setup_node_range(int nid, u64 *addr, u64 size, u64 max_addr)
  * Sets up nr_nodes fake nodes interleaved over physical nodes ranging from addr
  * to max_addr.  The return value is the number of nodes allocated.
  */
-static int __init split_nodes_interleave(u64 addr, u64 max_addr,
-						int nr_phys_nodes, int nr_nodes)
+static int __init split_nodes_interleave(u64 addr, u64 max_addr, int nr_nodes)
 {
 	nodemask_t physnode_mask = NODE_MASK_NONE;
 	u64 size;
@@ -384,7 +394,7 @@ static int __init split_nodes_interleave(u64 addr, u64 max_addr,
 		return -1;
 	}
 
-	for (i = 0; i < nr_phys_nodes; i++)
+	for (i = 0; i < MAX_NUMNODES; i++)
 		if (physnodes[i].start != physnodes[i].end)
 			node_set(i, physnode_mask);
 
@@ -549,15 +559,13 @@ static int __init split_nodes_size_interleave(u64 addr, u64 max_addr, u64 size)
  * numa=fake command-line option.
  */
 static int __init numa_emulation(unsigned long start_pfn,
-			unsigned long last_pfn, int acpi, int k8)
+			unsigned long last_pfn, int acpi, int amd)
 {
 	u64 addr = start_pfn << PAGE_SHIFT;
 	u64 max_addr = last_pfn << PAGE_SHIFT;
-	int num_phys_nodes;
 	int num_nodes;
 	int i;
 
-	num_phys_nodes = setup_physnodes(addr, max_addr, acpi, k8);
 	/*
 	 * If the numa=fake command-line contains a 'M' or 'G', it represents
 	 * the fixed node size.  Otherwise, if it is just a single number N,
@@ -572,7 +580,7 @@ static int __init numa_emulation(unsigned long start_pfn,
 		unsigned long n;
 
 		n = simple_strtoul(cmdline, NULL, 0);
-		num_nodes = split_nodes_interleave(addr, max_addr, num_phys_nodes, n);
+		num_nodes = split_nodes_interleave(addr, max_addr, n);
 	}
 
 	if (num_nodes < 0)
@@ -595,14 +603,15 @@ static int __init numa_emulation(unsigned long start_pfn,
 						nodes[i].end >> PAGE_SHIFT);
 		setup_node_bootmem(i, nodes[i].start, nodes[i].end);
 	}
-	acpi_fake_nodes(nodes, num_nodes);
+	setup_physnodes(addr, max_addr, acpi, amd);
+	fake_physnodes(acpi, amd, num_nodes);
 	numa_init_array();
 	return 0;
 }
 #endif /* CONFIG_NUMA_EMU */
 
 void __init initmem_init(unsigned long start_pfn, unsigned long last_pfn,
-				int acpi, int k8)
+				int acpi, int amd)
 {
 	int i;
 
@@ -610,8 +619,12 @@ void __init initmem_init(unsigned long start_pfn, unsigned long last_pfn,
 	nodes_clear(node_online_map);
 
 #ifdef CONFIG_NUMA_EMU
-	if (cmdline && !numa_emulation(start_pfn, last_pfn, acpi, k8))
+	setup_physnodes(start_pfn << PAGE_SHIFT, last_pfn << PAGE_SHIFT,
+			acpi, amd);
+	if (cmdline && !numa_emulation(start_pfn, last_pfn, acpi, amd))
 		return;
+	setup_physnodes(start_pfn << PAGE_SHIFT, last_pfn << PAGE_SHIFT,
+			acpi, amd);
 	nodes_clear(node_possible_map);
 	nodes_clear(node_online_map);
 #endif
@@ -624,8 +637,8 @@ void __init initmem_init(unsigned long start_pfn, unsigned long last_pfn,
 	nodes_clear(node_online_map);
 #endif
 
-#ifdef CONFIG_K8_NUMA
-	if (!numa_off && k8 && !k8_scan_nodes())
+#ifdef CONFIG_AMD_NUMA
+	if (!numa_off && amd && !amd_scan_nodes())
 		return;
 	nodes_clear(node_possible_map);
 	nodes_clear(node_online_map);
@@ -661,24 +674,6 @@ unsigned long __init numa_free_all_bootmem(void)
 	return pages;
 }
 
-static __init int numa_setup(char *opt)
-{
-	if (!opt)
-		return -EINVAL;
-	if (!strncmp(opt, "off", 3))
-		numa_off = 1;
-#ifdef CONFIG_NUMA_EMU
-	if (!strncmp(opt, "fake=", 5))
-		cmdline = opt + 5;
-#endif
-#ifdef CONFIG_ACPI_NUMA
-	if (!strncmp(opt, "noacpi", 6))
-		acpi_numa = -1;
-#endif
-	return 0;
-}
-early_param("numa", numa_setup);
-
 #ifdef CONFIG_NUMA
 
 static __init int find_near_online_node(int node)
@@ -767,6 +762,7 @@ void __cpuinit numa_clear_node(int cpu)
 
 #ifndef CONFIG_DEBUG_PER_CPU_MAPS
 
+#ifndef CONFIG_NUMA_EMU
 void __cpuinit numa_add_cpu(int cpu)
 {
 	cpumask_set_cpu(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]);
@@ -776,34 +772,115 @@ void __cpuinit numa_remove_cpu(int cpu)
 {
 	cpumask_clear_cpu(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]);
 }
+#else
+void __cpuinit numa_add_cpu(int cpu)
+{
+	unsigned long addr;
+	u16 apicid;
+	int physnid;
+	int nid = NUMA_NO_NODE;
+
+	apicid = early_per_cpu(x86_cpu_to_apicid, cpu);
+	if (apicid != BAD_APICID)
+		nid = apicid_to_node[apicid];
+	if (nid == NUMA_NO_NODE)
+		nid = early_cpu_to_node(cpu);
+	BUG_ON(nid == NUMA_NO_NODE || !node_online(nid));
+
+	/*
+	 * Use the starting address of the emulated node to find which physical
+	 * node it is allocated on.
+	 */
+	addr = node_start_pfn(nid) << PAGE_SHIFT;
+	for (physnid = 0; physnid < MAX_NUMNODES; physnid++)
+		if (addr >= physnodes[physnid].start &&
+		    addr < physnodes[physnid].end)
+			break;
+
+	/*
+	 * Map the cpu to each emulated node that is allocated on the physical
+	 * node of the cpu's apic id.
+	 */
+	for_each_online_node(nid) {
+		addr = node_start_pfn(nid) << PAGE_SHIFT;
+		if (addr >= physnodes[physnid].start &&
+		    addr < physnodes[physnid].end)
+			cpumask_set_cpu(cpu, node_to_cpumask_map[nid]);
+	}
+}
+
+void __cpuinit numa_remove_cpu(int cpu)
+{
+	int i;
+
+	for_each_online_node(i)
+		cpumask_clear_cpu(cpu, node_to_cpumask_map[i]);
+}
+#endif /* !CONFIG_NUMA_EMU */
 
 #else /* CONFIG_DEBUG_PER_CPU_MAPS */
+static struct cpumask __cpuinit *debug_cpumask_set_cpu(int cpu, int enable)
+{
+	int node = early_cpu_to_node(cpu);
+	struct cpumask *mask;
+	char buf[64];
+
+	mask = node_to_cpumask_map[node];
+	if (!mask) {
+		pr_err("node_to_cpumask_map[%i] NULL\n", node);
+		dump_stack();
+		return NULL;
+	}
+
+	cpulist_scnprintf(buf, sizeof(buf), mask);
+	printk(KERN_DEBUG "%s cpu %d node %d: mask now %s\n",
+		enable ? "numa_add_cpu" : "numa_remove_cpu",
+		cpu, node, buf);
+	return mask;
+}
 
 /*
  * --------- debug versions of the numa functions ---------
  */
+#ifndef CONFIG_NUMA_EMU
 static void __cpuinit numa_set_cpumask(int cpu, int enable)
 {
-	int node = early_cpu_to_node(cpu);
 	struct cpumask *mask;
-	char buf[64];
 
-	mask = node_to_cpumask_map[node];
-	if (mask == NULL) {
-		printk(KERN_ERR "node_to_cpumask_map[%i] NULL\n", node);
-		dump_stack();
+	mask = debug_cpumask_set_cpu(cpu, enable);
+	if (!mask)
 		return;
-	}
 
 	if (enable)
 		cpumask_set_cpu(cpu, mask);
 	else
 		cpumask_clear_cpu(cpu, mask);
+}
+#else
+static void __cpuinit numa_set_cpumask(int cpu, int enable)
+{
+	int node = early_cpu_to_node(cpu);
+	struct cpumask *mask;
+	int i;
 
-	cpulist_scnprintf(buf, sizeof(buf), mask);
-	printk(KERN_DEBUG "%s cpu %d node %d: mask now %s\n",
-		enable ? "numa_add_cpu" : "numa_remove_cpu", cpu, node, buf);
+	for_each_online_node(i) {
+		unsigned long addr;
+
+		addr = node_start_pfn(i) << PAGE_SHIFT;
+		if (addr < physnodes[node].start ||
+					addr >= physnodes[node].end)
+			continue;
+		mask = debug_cpumask_set_cpu(cpu, enable);
+		if (!mask)
+			return;
+
+		if (enable)
+			cpumask_set_cpu(cpu, mask);
+		else
+			cpumask_clear_cpu(cpu, mask);
+	}
 }
+#endif /* CONFIG_NUMA_EMU */
 
 void __cpuinit numa_add_cpu(int cpu)
 {
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 532e7933d606..8b830ca14ac4 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -13,6 +13,7 @@
 #include <linux/pfn.h>
 #include <linux/percpu.h>
 #include <linux/gfp.h>
+#include <linux/pci.h>
 
 #include <asm/e820.h>
 #include <asm/processor.h>
@@ -255,13 +256,16 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long address,
 				   unsigned long pfn)
 {
 	pgprot_t forbidden = __pgprot(0);
+	pgprot_t required = __pgprot(0);
 
 	/*
 	 * The BIOS area between 640k and 1Mb needs to be executable for
 	 * PCI BIOS based config access (CONFIG_PCI_GOBIOS) support.
 	 */
-	if (within(pfn, BIOS_BEGIN >> PAGE_SHIFT, BIOS_END >> PAGE_SHIFT))
+#ifdef CONFIG_PCI_BIOS
+	if (pcibios_enabled && within(pfn, BIOS_BEGIN >> PAGE_SHIFT, BIOS_END >> PAGE_SHIFT))
 		pgprot_val(forbidden) |= _PAGE_NX;
+#endif
 
 	/*
 	 * The kernel text needs to be executable for obvious reasons
@@ -278,6 +282,12 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long address,
 	if (within(pfn, __pa((unsigned long)__start_rodata) >> PAGE_SHIFT,
 		   __pa((unsigned long)__end_rodata) >> PAGE_SHIFT))
 		pgprot_val(forbidden) |= _PAGE_RW;
+	/*
+	 * .data and .bss should always be writable.
+	 */
+	if (within(address, (unsigned long)_sdata, (unsigned long)_edata) ||
+	    within(address, (unsigned long)__bss_start, (unsigned long)__bss_stop))
+		pgprot_val(required) |= _PAGE_RW;
 
 #if defined(CONFIG_X86_64) && defined(CONFIG_DEBUG_RODATA)
 	/*
@@ -317,6 +327,7 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long address,
 #endif
 
 	prot = __pgprot(pgprot_val(prot) & ~pgprot_val(forbidden));
+	prot = __pgprot(pgprot_val(prot) | pgprot_val(required));
 
 	return prot;
 }
@@ -393,7 +404,7 @@ try_preserve_large_page(pte_t *kpte, unsigned long address,
 {
 	unsigned long nextpage_addr, numpages, pmask, psize, flags, addr, pfn;
 	pte_t new_pte, old_pte, *tmp;
-	pgprot_t old_prot, new_prot;
+	pgprot_t old_prot, new_prot, req_prot;
 	int i, do_split = 1;
 	unsigned int level;
 
@@ -438,10 +449,10 @@ try_preserve_large_page(pte_t *kpte, unsigned long address,
 	 * We are safe now. Check whether the new pgprot is the same:
 	 */
 	old_pte = *kpte;
-	old_prot = new_prot = pte_pgprot(old_pte);
+	old_prot = new_prot = req_prot = pte_pgprot(old_pte);
 
-	pgprot_val(new_prot) &= ~pgprot_val(cpa->mask_clr);
-	pgprot_val(new_prot) |= pgprot_val(cpa->mask_set);
+	pgprot_val(req_prot) &= ~pgprot_val(cpa->mask_clr);
+	pgprot_val(req_prot) |= pgprot_val(cpa->mask_set);
 
 	/*
 	 * old_pte points to the large page base address. So we need
@@ -450,17 +461,17 @@ try_preserve_large_page(pte_t *kpte, unsigned long address,
 	pfn = pte_pfn(old_pte) + ((address & (psize - 1)) >> PAGE_SHIFT);
 	cpa->pfn = pfn;
 
-	new_prot = static_protections(new_prot, address, pfn);
+	new_prot = static_protections(req_prot, address, pfn);
 
 	/*
 	 * We need to check the full range, whether
 	 * static_protection() requires a different pgprot for one of
 	 * the pages in the range we try to preserve:
 	 */
-	addr = address + PAGE_SIZE;
-	pfn++;
-	for (i = 1; i < cpa->numpages; i++, addr += PAGE_SIZE, pfn++) {
-		pgprot_t chk_prot = static_protections(new_prot, addr, pfn);
+	addr = address & pmask;
+	pfn = pte_pfn(old_pte);
+	for (i = 0; i < (psize >> PAGE_SHIFT); i++, addr += PAGE_SIZE, pfn++) {
+		pgprot_t chk_prot = static_protections(req_prot, addr, pfn);
 
 		if (pgprot_val(chk_prot) != pgprot_val(new_prot))
 			goto out_unlock;
@@ -483,7 +494,7 @@ try_preserve_large_page(pte_t *kpte, unsigned long address,
 	 * that we limited the number of possible pages already to
 	 * the number of pages in the large page.
 	 */
-	if (address == (nextpage_addr - psize) && cpa->numpages == numpages) {
+	if (address == (address & pmask) && cpa->numpages == (psize >> PAGE_SHIFT)) {
 		/*
 		 * The address is aligned and the number of pages
 		 * covers the full page.
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 8be8c7d7bc89..500242d3c96d 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -320,6 +320,25 @@ int ptep_set_access_flags(struct vm_area_struct *vma,
 	return changed;
 }
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+int pmdp_set_access_flags(struct vm_area_struct *vma,
+			  unsigned long address, pmd_t *pmdp,
+			  pmd_t entry, int dirty)
+{
+	int changed = !pmd_same(*pmdp, entry);
+
+	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
+
+	if (changed && dirty) {
+		*pmdp = entry;
+		pmd_update_defer(vma->vm_mm, address, pmdp);
+		flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
+	}
+
+	return changed;
+}
+#endif
+
 int ptep_test_and_clear_young(struct vm_area_struct *vma,
 			      unsigned long addr, pte_t *ptep)
 {
@@ -335,6 +354,23 @@ int ptep_test_and_clear_young(struct vm_area_struct *vma,
 	return ret;
 }
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+int pmdp_test_and_clear_young(struct vm_area_struct *vma,
+			      unsigned long addr, pmd_t *pmdp)
+{
+	int ret = 0;
+
+	if (pmd_young(*pmdp))
+		ret = test_and_clear_bit(_PAGE_BIT_ACCESSED,
+					 (unsigned long *)pmdp);
+
+	if (ret)
+		pmd_update(vma->vm_mm, addr, pmdp);
+
+	return ret;
+}
+#endif
+
 int ptep_clear_flush_young(struct vm_area_struct *vma,
 			   unsigned long address, pte_t *ptep)
 {
@@ -347,6 +383,36 @@ int ptep_clear_flush_young(struct vm_area_struct *vma,
 	return young;
 }
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+int pmdp_clear_flush_young(struct vm_area_struct *vma,
+			   unsigned long address, pmd_t *pmdp)
+{
+	int young;
+
+	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
+
+	young = pmdp_test_and_clear_young(vma, address, pmdp);
+	if (young)
+		flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
+
+	return young;
+}
+
+void pmdp_splitting_flush(struct vm_area_struct *vma,
+			  unsigned long address, pmd_t *pmdp)
+{
+	int set;
+	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
+	set = !test_and_set_bit(_PAGE_BIT_SPLITTING,
+				(unsigned long *)pmdp);
+	if (set) {
+		pmd_update(vma->vm_mm, address, pmdp);
+		/* need tlb flush only to serialize against gup-fast */
+		flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
+	}
+}
+#endif
+
 /**
  * reserve_top_address - reserves a hole in the top of kernel address space
  * @reserve - size of hole to reserve
diff --git a/arch/x86/mm/setup_nx.c b/arch/x86/mm/setup_nx.c
index a3250aa34086..410531d3c292 100644
--- a/arch/x86/mm/setup_nx.c
+++ b/arch/x86/mm/setup_nx.c
@@ -41,7 +41,7 @@ void __init x86_report_nx(void)
 {
 	if (!cpu_has_nx) {
 		printk(KERN_NOTICE "Notice: NX (Execute Disable) protection "
-		       "missing in CPU or disabled in BIOS!\n");
+		       "missing in CPU!\n");
 	} else {
 #if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
 		if (disable_nx) {
diff --git a/arch/x86/mm/srat_32.c b/arch/x86/mm/srat_32.c
index a17dffd136c1..ae96e7b8051d 100644
--- a/arch/x86/mm/srat_32.c
+++ b/arch/x86/mm/srat_32.c
@@ -59,7 +59,6 @@ static struct node_memory_chunk_s __initdata node_memory_chunk[MAXCHUNKS];
 static int __initdata num_memory_chunks; /* total number of memory chunks */
 static u8 __initdata apicid_to_pxm[MAX_APICID];
 
-int numa_off __initdata;
 int acpi_numa __initdata;
 
 static __init void bad_srat(void)
@@ -92,6 +91,7 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *cpu_affinity)
 	/* mark this node as "seen" in node bitmap */
 	BMAP_SET(pxm_bitmap, cpu_affinity->proximity_domain_lo);
 
+	/* don't need to check apic_id here, because it is always 8 bits */
 	apicid_to_pxm[cpu_affinity->apic_id] = cpu_affinity->proximity_domain_lo;
 
 	printk(KERN_DEBUG "CPU %02x in proximity domain %02x\n",
diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c
index a35cb9d8b060..603d285d1daa 100644
--- a/arch/x86/mm/srat_64.c
+++ b/arch/x86/mm/srat_64.c
@@ -134,6 +134,10 @@ acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa)
 	}
 
 	apic_id = pa->apic_id;
+	if (apic_id >= MAX_LOCAL_APIC) {
+		printk(KERN_INFO "SRAT: PXM %u -> APIC 0x%04x -> Node %u skipped apicid that is too big\n", pxm, apic_id, node);
+		return;
+	}
 	apicid_to_node[apic_id] = node;
 	node_set(node, cpu_nodes_parsed);
 	acpi_numa = 1;
@@ -168,6 +172,12 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa)
 		apic_id = (pa->apic_id << 8) | pa->local_sapic_eid;
 	else
 		apic_id = pa->apic_id;
+
+	if (apic_id >= MAX_LOCAL_APIC) {
+		printk(KERN_INFO "SRAT: PXM %u -> APIC 0x%02x -> Node %u skipped apicid that is too big\n", pxm, apic_id, node);
+		return;
+	}
+
 	apicid_to_node[apic_id] = node;
 	node_set(node, cpu_nodes_parsed);
 	acpi_numa = 1;
@@ -339,18 +349,19 @@ static int __init nodes_cover_memory(const struct bootnode *nodes)
 
 void __init acpi_numa_arch_fixup(void) {}
 
-int __init acpi_get_nodes(struct bootnode *physnodes)
+#ifdef CONFIG_NUMA_EMU
+void __init acpi_get_nodes(struct bootnode *physnodes, unsigned long start,
+				unsigned long end)
 {
 	int i;
-	int ret = 0;
 
 	for_each_node_mask(i, nodes_parsed) {
-		physnodes[ret].start = nodes[i].start;
-		physnodes[ret].end = nodes[i].end;
-		ret++;
+		cutoff_node(i, start, end);
+		physnodes[i].start = nodes[i].start;
+		physnodes[i].end = nodes[i].end;
 	}
-	return ret;
 }
+#endif /* CONFIG_NUMA_EMU */
 
 /* Use the information discovered above to actually set up the nodes. */
 int __init acpi_scan_nodes(unsigned long start, unsigned long end)
@@ -495,8 +506,6 @@ void __init acpi_fake_nodes(const struct bootnode *fake_nodes, int num_nodes)
 {
 	int i, j;
 
-	printk(KERN_INFO "Faking PXM affinity for fake nodes on real "
-			 "topology.\n");
 	for (i = 0; i < num_nodes; i++) {
 		int nid, pxm;
 
@@ -516,6 +525,17 @@ void __init acpi_fake_nodes(const struct bootnode *fake_nodes, int num_nodes)
 			    fake_apicid_to_node[j] == NUMA_NO_NODE)
 				fake_apicid_to_node[j] = i;
 	}
+
+	/*
+	 * If there are apicid-to-node mappings for physical nodes that do not
+	 * have a corresponding emulated node, it should default to a guaranteed
+	 * value.
+	 */
+	for (i = 0; i < MAX_LOCAL_APIC; i++)
+		if (apicid_to_node[i] != NUMA_NO_NODE &&
+		    fake_apicid_to_node[i] == NUMA_NO_NODE)
+			fake_apicid_to_node[i] = 0;
+
 	for (i = 0; i < num_nodes; i++)
 		__acpi_map_pxm_to_node(fake_node_to_pxm_map[i], i);
 	memcpy(apicid_to_node, fake_apicid_to_node, sizeof(apicid_to_node));
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 49358481c733..6acc724d5d8f 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -223,7 +223,7 @@ void native_flush_tlb_others(const struct cpumask *cpumask,
 
 static void __cpuinit calculate_tlb_offset(void)
 {
-	int cpu, node, nr_node_vecs;
+	int cpu, node, nr_node_vecs, idx = 0;
 	/*
 	 * we are changing tlb_vector_offset for each CPU in runtime, but this
 	 * will not cause inconsistency, as the write is atomic under X86. we
@@ -239,7 +239,7 @@ static void __cpuinit calculate_tlb_offset(void)
 		nr_node_vecs = NUM_INVALIDATE_TLB_VECTORS/nr_online_nodes;
 
 	for_each_online_node(node) {
-		int node_offset = (node % NUM_INVALIDATE_TLB_VECTORS) *
+		int node_offset = (idx % NUM_INVALIDATE_TLB_VECTORS) *
 			nr_node_vecs;
 		int cpu_offset = 0;
 		for_each_cpu(cpu, cpumask_of_node(node)) {
@@ -248,10 +248,11 @@ static void __cpuinit calculate_tlb_offset(void)
 			cpu_offset++;
 			cpu_offset = cpu_offset % nr_node_vecs;
 		}
+		idx++;
 	}
 }
 
-static int tlb_cpuhp_notify(struct notifier_block *n,
+static int __cpuinit tlb_cpuhp_notify(struct notifier_block *n,
 		unsigned long action, void *hcpu)
 {
 	switch (action & 0xf) {