Merge branch 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (36 commits)
  x86, mm: Correct the implementation of is_untracked_pat_range()
  x86/pat: Trivial: don't create debugfs for memtype if pat is disabled
  x86, mtrr: Fix sorting of mtrr after subtracting
  x86: Move find_smp_config() earlier and avoid bootmem usage
  x86, platform: Change is_untracked_pat_range() to bool; cleanup init
  x86: Change is_ISA_range() into an inline function
  x86, mm: is_untracked_pat_range() takes a normal semiclosed range
  x86, mm: Call is_untracked_pat_range() rather than is_ISA_range()
  x86: UV SGI: Don't track GRU space in PAT
  x86: SGI UV: Fix BAU initialization
  x86, numa: Use near(er) online node instead of roundrobin for NUMA
  x86, numa, bootmem: Only free bootmem on NUMA failure path
  x86: Change crash kernel to reserve via reserve_early()
  x86: Eliminate redundant/contradicting cache line size config options
  x86: When cleaning MTRRs, do not fold WP into UC
  x86: remove "extern" from function prototypes in <asm/proto.h>
  x86, mm: Report state of NX protections during boot
  x86, mm: Clean up and simplify NX enablement
  x86, pageattr: Make set_memory_(x|nx) aware of NX support
  x86, sleep: Always save the value of EFER
  ...

Fix up conflicts (added both iommu_shutdown and is_untracked_pat_range)
to 'struct x86_platform_ops') in
	arch/x86/include/asm/x86_init.h
	arch/x86/kernel/x86_init.c

16 files changed, 200 insertions, 147 deletions

diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index ca93638ba43..82e508677b9 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -78,12 +78,9 @@ int acpi_save_state_mem(void)
 #ifndef CONFIG_64BIT
 	store_gdt((struct desc_ptr *)&header->pmode_gdt);
 
-	header->pmode_efer_low = nx_enabled;
-	if (header->pmode_efer_low & 1) {
-		/* This is strange, why not save efer, always? */
-		rdmsr(MSR_EFER, header->pmode_efer_low,
-			header->pmode_efer_high);
-	}
+	if (rdmsr_safe(MSR_EFER, &header->pmode_efer_low,
+		       &header->pmode_efer_high))
+		header->pmode_efer_low = header->pmode_efer_high = 0;
 #endif /* !CONFIG_64BIT */
 
 	header->pmode_cr0 = read_cr0();
@@ -119,29 +116,32 @@ void acpi_restore_state_mem(void)
 
 
 /**
- * acpi_reserve_bootmem - do _very_ early ACPI initialisation
+ * acpi_reserve_wakeup_memory - do _very_ early ACPI initialisation
  *
  * We allocate a page from the first 1MB of memory for the wakeup
  * routine for when we come back from a sleep state. The
  * runtime allocator allows specification of <16MB pages, but not
  * <1MB pages.
  */
-void __init acpi_reserve_bootmem(void)
+void __init acpi_reserve_wakeup_memory(void)
 {
+	unsigned long mem;
+
 	if ((&wakeup_code_end - &wakeup_code_start) > WAKEUP_SIZE) {
 		printk(KERN_ERR
 		       "ACPI: Wakeup code way too big, S3 disabled.\n");
 		return;
 	}
 
-	acpi_realmode = (unsigned long)alloc_bootmem_low(WAKEUP_SIZE);
+	mem = find_e820_area(0, 1<<20, WAKEUP_SIZE, PAGE_SIZE);
 
-	if (!acpi_realmode) {
+	if (mem == -1L) {
 		printk(KERN_ERR "ACPI: Cannot allocate lowmem, S3 disabled.\n");
 		return;
 	}
-
-	acpi_wakeup_address = virt_to_phys((void *)acpi_realmode);
+	acpi_realmode = (unsigned long) phys_to_virt(mem);
+	acpi_wakeup_address = mem;
+	reserve_early(mem, mem + WAKEUP_SIZE, "ACPI WAKEUP");
 }
 
 
diff --git a/arch/x86/kernel/apic/numaq_32.c b/arch/x86/kernel/apic/numaq_32.c
index 07cdbdcd7a9..98c4665f251 100644
--- a/arch/x86/kernel/apic/numaq_32.c
+++ b/arch/x86/kernel/apic/numaq_32.c
@@ -264,11 +264,6 @@ static void __init smp_read_mpc_oem(struct mpc_table *mpc)
 static __init void early_check_numaq(void)
 {
 	/*
-	 * Find possible boot-time SMP configuration:
-	 */
-	early_find_smp_config();
-
-	/*
 	 * get boot-time SMP configuration:
 	 */
 	if (smp_found_config)
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 130c4b93487..b684bb303cb 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -30,10 +30,22 @@
 #include <asm/apic.h>
 #include <asm/ipi.h>
 #include <asm/smp.h>
+#include <asm/x86_init.h>
 
 DEFINE_PER_CPU(int, x2apic_extra_bits);
 
 static enum uv_system_type uv_system_type;
+static u64 gru_start_paddr, gru_end_paddr;
+
+static inline bool is_GRU_range(u64 start, u64 end)
+{
+	return start >= gru_start_paddr && end <= gru_end_paddr;
+}
+
+static bool uv_is_untracked_pat_range(u64 start, u64 end)
+{
+	return is_ISA_range(start, end) || is_GRU_range(start, end);
+}
 
 static int early_get_nodeid(void)
 {
@@ -49,6 +61,7 @@ static int early_get_nodeid(void)
 static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 {
 	if (!strcmp(oem_id, "SGI")) {
+		x86_platform.is_untracked_pat_range =  uv_is_untracked_pat_range;
 		if (!strcmp(oem_table_id, "UVL"))
 			uv_system_type = UV_LEGACY_APIC;
 		else if (!strcmp(oem_table_id, "UVX"))
@@ -385,8 +398,12 @@ static __init void map_gru_high(int max_pnode)
 	int shift = UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_SHFT;
 
 	gru.v = uv_read_local_mmr(UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR);
-	if (gru.s.enable)
+	if (gru.s.enable) {
 		map_high("GRU", gru.s.base, shift, max_pnode, map_wb);
+		gru_start_paddr = ((u64)gru.s.base << shift);
+		gru_end_paddr = gru_start_paddr + (1UL << shift) * (max_pnode + 1);
+
+	}
 }
 
 static __init void map_mmr_high(int max_pnode)
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index a4ec8b64754..c1afa990a6c 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1136,7 +1136,7 @@ void __cpuinit cpu_init(void)
 	wrmsrl(MSR_KERNEL_GS_BASE, 0);
 	barrier();
 
-	check_efer();
+	x86_configure_nx();
 	if (cpu != 0)
 		enable_x2apic();
 
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 40e1835b35e..c900b73f922 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -263,8 +263,12 @@ static void __cpuinit srat_detect_node(struct cpuinfo_x86 *c)
 	/* Don't do the funky fallback heuristics the AMD version employs
 	   for now. */
 	node = apicid_to_node[apicid];
-	if (node == NUMA_NO_NODE || !node_online(node))
+	if (node == NUMA_NO_NODE)
 		node = first_node(node_online_map);
+	else if (!node_online(node)) {
+		/* reuse the value from init_cpu_to_node() */
+		node = cpu_to_node(cpu);
+	}
 	numa_set_node(cpu, node);
 
 	printk(KERN_INFO "CPU %d/0x%x -> Node %d\n", cpu, apicid, node);
diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c
index 73c86db5acb..09b1698e046 100644
--- a/arch/x86/kernel/cpu/mtrr/cleanup.c
+++ b/arch/x86/kernel/cpu/mtrr/cleanup.c
@@ -170,6 +170,41 @@ static int __init cmp_range(const void *x1, const void *x2)
 	return start1 - start2;
 }
 
+static int __init clean_sort_range(struct res_range *range, int az)
+{
+	int i, j, k = az - 1, nr_range = 0;
+
+	for (i = 0; i < k; i++) {
+		if (range[i].end)
+			continue;
+		for (j = k; j > i; j--) {
+			if (range[j].end) {
+				k = j;
+				break;
+			}
+		}
+		if (j == i)
+			break;
+		range[i].start = range[k].start;
+		range[i].end   = range[k].end;
+		range[k].start = 0;
+		range[k].end   = 0;
+		k--;
+	}
+	/* count it */
+	for (i = 0; i < az; i++) {
+		if (!range[i].end) {
+			nr_range = i;
+			break;
+		}
+	}
+
+	/* sort them */
+	sort(range, nr_range, sizeof(struct res_range), cmp_range, NULL);
+
+	return nr_range;
+}
+
 #define BIOS_BUG_MSG KERN_WARNING \
 	"WARNING: BIOS bug: VAR MTRR %d contains strange UC entry under 1M, check with your system vendor!\n"
 
@@ -223,22 +258,18 @@ x86_get_mtrr_mem_range(struct res_range *range, int nr_range,
 		subtract_range(range, extra_remove_base,
 				 extra_remove_base + extra_remove_size  - 1);
 
-	/* get new range num */
-	nr_range = 0;
-	for (i = 0; i < RANGE_NUM; i++) {
-		if (!range[i].end)
-			continue;
-		nr_range++;
-	}
 	if  (debug_print) {
 		printk(KERN_DEBUG "After UC checking\n");
-		for (i = 0; i < nr_range; i++)
+		for (i = 0; i < RANGE_NUM; i++) {
+			if (!range[i].end)
+				continue;
 			printk(KERN_DEBUG "MTRR MAP PFN: %016lx - %016lx\n",
 				 range[i].start, range[i].end + 1);
+		}
 	}
 
 	/* sort the ranges */
-	sort(range, nr_range, sizeof(struct res_range), cmp_range, NULL);
+	nr_range = clean_sort_range(range, RANGE_NUM);
 	if  (debug_print) {
 		printk(KERN_DEBUG "After sorting\n");
 		for (i = 0; i < nr_range; i++)
@@ -689,8 +720,6 @@ static int __init mtrr_need_cleanup(void)
 			continue;
 		if (!size)
 			type = MTRR_NUM_TYPES;
-		if (type == MTRR_TYPE_WRPROT)
-			type = MTRR_TYPE_UNCACHABLE;
 		num[type]++;
 	}
 
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 5a1b9758fd6..30968924543 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -189,9 +189,26 @@ static void wait_for_nmi(void)
 	nmi_wait_count++;
 }
 
+static inline int
+within(unsigned long addr, unsigned long start, unsigned long end)
+{
+	return addr >= start && addr < end;
+}
+
 static int
 do_ftrace_mod_code(unsigned long ip, void *new_code)
 {
+	/*
+	 * On x86_64, kernel text mappings are mapped read-only with
+	 * CONFIG_DEBUG_RODATA. So we use the kernel identity mapping instead
+	 * of the kernel text mapping to modify the kernel text.
+	 *
+	 * For 32bit kernels, these mappings are same and we can use
+	 * kernel identity mapping to modify code.
+	 */
+	if (within(ip, (unsigned long)_text, (unsigned long)_etext))
+		ip = (unsigned long)__va(__pa(ip));
+
 	mod_code_ip = (void *)ip;
 	mod_code_newcode = new_code;
 
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 050c278481b..7fd318bac59 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -18,6 +18,8 @@
 #include <asm/asm-offsets.h>
 #include <asm/setup.h>
 #include <asm/processor-flags.h>
+#include <asm/msr-index.h>
+#include <asm/cpufeature.h>
 #include <asm/percpu.h>
 
 /* Physical address */
@@ -297,25 +299,27 @@ ENTRY(startup_32_smp)
 	orl %edx,%eax
 	movl %eax,%cr4
 
-	btl $5, %eax		# check if PAE is enabled
-	jnc 6f
+	testb $X86_CR4_PAE, %al		# check if PAE is enabled
+	jz 6f
 
 	/* Check if extended functions are implemented */
 	movl $0x80000000, %eax
 	cpuid
-	cmpl $0x80000000, %eax
-	jbe 6f
+	/* Value must be in the range 0x80000001 to 0x8000ffff */
+	subl $0x80000001, %eax
+	cmpl $(0x8000ffff-0x80000001), %eax
+	ja 6f
 	mov $0x80000001, %eax
 	cpuid
 	/* Execute Disable bit supported? */
-	btl $20, %edx
+	btl $(X86_FEATURE_NX & 31), %edx
 	jnc 6f
 
 	/* Setup EFER (Extended Feature Enable Register) */
-	movl $0xc0000080, %ecx
+	movl $MSR_EFER, %ecx
 	rdmsr
 
-	btsl $11, %eax
+	btsl $_EFER_NX, %eax
 	/* Make changes effective */
 	wrmsr
 
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 22db86a3764..2d8b5035371 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -262,11 +262,11 @@ ENTRY(secondary_startup_64)
 	.quad	x86_64_start_kernel
 	ENTRY(initial_gs)
 	.quad	INIT_PER_CPU_VAR(irq_stack_union)
-	__FINITDATA
 
 	ENTRY(stack_start)
 	.quad  init_thread_union+THREAD_SIZE-8
 	.word  0
+	__FINITDATA
 
 bad_address:
 	jmp bad_address
@@ -340,6 +340,7 @@ ENTRY(name)
 	i = i + 1 ;					\
 	.endr
 
+	.data
 	/*
 	 * This default setting generates an ident mapping at address 0x100000
 	 * and a mapping for the kernel that precisely maps virtual address
diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c
index c843f8406da..a3fa43ba5d3 100644
--- a/arch/x86/kernel/machine_kexec_32.c
+++ b/arch/x86/kernel/machine_kexec_32.c
@@ -158,8 +158,7 @@ int machine_kexec_prepare(struct kimage *image)
 {
 	int error;
 
-	if (nx_enabled)
-		set_pages_x(image->control_code_page, 1);
+	set_pages_x(image->control_code_page, 1);
 	error = machine_kexec_alloc_page_tables(image);
 	if (error)
 		return error;
@@ -173,8 +172,7 @@ int machine_kexec_prepare(struct kimage *image)
  */
 void machine_kexec_cleanup(struct kimage *image)
 {
-	if (nx_enabled)
-		set_pages_nx(image->control_code_page, 1);
+	set_pages_nx(image->control_code_page, 1);
 	machine_kexec_free_page_tables(image);
 }
 
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index 5be95ef4ffe..35a57c963df 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -667,36 +667,18 @@ void __init default_get_smp_config(unsigned int early)
 	 */
 }
 
-static void __init smp_reserve_bootmem(struct mpf_intel *mpf)
+static void __init smp_reserve_memory(struct mpf_intel *mpf)
 {
 	unsigned long size = get_mpc_size(mpf->physptr);
-#ifdef CONFIG_X86_32
-	/*
-	 * We cannot access to MPC table to compute table size yet,
-	 * as only few megabytes from the bottom is mapped now.
-	 * PC-9800's MPC table places on the very last of physical
-	 * memory; so that simply reserving PAGE_SIZE from mpf->physptr
-	 * yields BUG() in reserve_bootmem.
-	 * also need to make sure physptr is below than max_low_pfn
-	 * we don't need reserve the area above max_low_pfn
-	 */
-	unsigned long end = max_low_pfn * PAGE_SIZE;
 
-	if (mpf->physptr < end) {
-		if (mpf->physptr + size > end)
-			size = end - mpf->physptr;
-		reserve_bootmem_generic(mpf->physptr, size, BOOTMEM_DEFAULT);
-	}
-#else
-	reserve_bootmem_generic(mpf->physptr, size, BOOTMEM_DEFAULT);
-#endif
+	reserve_early(mpf->physptr, mpf->physptr+size, "MP-table mpc");
 }
 
-static int __init smp_scan_config(unsigned long base, unsigned long length,
-				  unsigned reserve)
+static int __init smp_scan_config(unsigned long base, unsigned long length)
 {
 	unsigned int *bp = phys_to_virt(base);
 	struct mpf_intel *mpf;
+	unsigned long mem;
 
 	apic_printk(APIC_VERBOSE, "Scan SMP from %p for %ld bytes.\n",
 			bp, length);
@@ -717,12 +699,10 @@ static int __init smp_scan_config(unsigned long base, unsigned long length,
 			printk(KERN_INFO "found SMP MP-table at [%p] %llx\n",
 			       mpf, (u64)virt_to_phys(mpf));
 
-			if (!reserve)
-				return 1;
-			reserve_bootmem_generic(virt_to_phys(mpf), sizeof(*mpf),
-						BOOTMEM_DEFAULT);
+			mem = virt_to_phys(mpf);
+			reserve_early(mem, mem + sizeof(*mpf), "MP-table mpf");
 			if (mpf->physptr)
-				smp_reserve_bootmem(mpf);
+				smp_reserve_memory(mpf);
 
 			return 1;
 		}
@@ -732,7 +712,7 @@ static int __init smp_scan_config(unsigned long base, unsigned long length,
 	return 0;
 }
 
-void __init default_find_smp_config(unsigned int reserve)
+void __init default_find_smp_config(void)
 {
 	unsigned int address;
 
@@ -744,9 +724,9 @@ void __init default_find_smp_config(unsigned int reserve)
 	 * 2) Scan the top 1K of base RAM
 	 * 3) Scan the 64K of bios
 	 */
-	if (smp_scan_config(0x0, 0x400, reserve) ||
-	    smp_scan_config(639 * 0x400, 0x400, reserve) ||
-	    smp_scan_config(0xF0000, 0x10000, reserve))
+	if (smp_scan_config(0x0, 0x400) ||
+	    smp_scan_config(639 * 0x400, 0x400) ||
+	    smp_scan_config(0xF0000, 0x10000))
 		return;
 	/*
 	 * If it is an SMP machine we should know now, unless the
@@ -767,7 +747,7 @@ void __init default_find_smp_config(unsigned int reserve)
 
 	address = get_bios_ebda();
 	if (address)
-		smp_scan_config(address, 0x400, reserve);
+		smp_scan_config(address, 0x400);
 }
 
 #ifdef CONFIG_X86_IO_APIC
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 82e88cdda9b..946a311a25c 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -106,6 +106,7 @@
 #include <asm/percpu.h>
 #include <asm/topology.h>
 #include <asm/apicdef.h>
+#include <asm/k8.h>
 #ifdef CONFIG_X86_64
 #include <asm/numa_64.h>
 #endif
@@ -487,42 +488,11 @@ static void __init reserve_early_setup_data(void)
 
 #ifdef CONFIG_KEXEC
 
-/**
- * Reserve @size bytes of crashkernel memory at any suitable offset.
- *
- * @size: Size of the crashkernel memory to reserve.
- * Returns the base address on success, and -1ULL on failure.
- */
-static
-unsigned long long __init find_and_reserve_crashkernel(unsigned long long size)
-{
-	const unsigned long long alignment = 16<<20; 	/* 16M */
-	unsigned long long start = 0LL;
-
-	while (1) {
-		int ret;
-
-		start = find_e820_area(start, ULONG_MAX, size, alignment);
-		if (start == -1ULL)
-			return start;
-
-		/* try to reserve it */
-		ret = reserve_bootmem_generic(start, size, BOOTMEM_EXCLUSIVE);
-		if (ret >= 0)
-			return start;
-
-		start += alignment;
-	}
-}
-
 static inline unsigned long long get_total_mem(void)
 {
 	unsigned long long total;
 
-	total = max_low_pfn - min_low_pfn;
-#ifdef CONFIG_HIGHMEM
-	total += highend_pfn - highstart_pfn;
-#endif
+	total = max_pfn - min_low_pfn;
 
 	return total << PAGE_SHIFT;
 }
@@ -542,21 +512,25 @@ static void __init reserve_crashkernel(void)
 
 	/* 0 means: find the address automatically */
 	if (crash_base <= 0) {
-		crash_base = find_and_reserve_crashkernel(crash_size);
+		const unsigned long long alignment = 16<<20;	/* 16M */
+
+		crash_base = find_e820_area(alignment, ULONG_MAX, crash_size,
+				 alignment);
 		if (crash_base == -1ULL) {
-			pr_info("crashkernel reservation failed. "
-				"No suitable area found.\n");
+			pr_info("crashkernel reservation failed - No suitable area found.\n");
 			return;
 		}
 	} else {
-		ret = reserve_bootmem_generic(crash_base, crash_size,
-					BOOTMEM_EXCLUSIVE);
-		if (ret < 0) {
-			pr_info("crashkernel reservation failed - "
-				"memory is in use\n");
+		unsigned long long start;
+
+		start = find_e820_area(crash_base, ULONG_MAX, crash_size,
+				 1<<20);
+		if (start != crash_base) {
+			pr_info("crashkernel reservation failed - memory is in use.\n");
 			return;
 		}
 	}
+	reserve_early(crash_base, crash_base + crash_size, "CRASH KERNEL");
 
 	printk(KERN_INFO "Reserving %ldMB of memory at %ldMB "
 			"for crashkernel (System RAM: %ldMB)\n",
@@ -699,6 +673,9 @@ static struct dmi_system_id __initdata bad_bios_dmi_table[] = {
 
 void __init setup_arch(char **cmdline_p)
 {
+	int acpi = 0;
+	int k8 = 0;
+
 #ifdef CONFIG_X86_32
 	memcpy(&boot_cpu_data, &new_cpu_data, sizeof(new_cpu_data));
 	visws_early_detect();
@@ -791,21 +768,18 @@ void __init setup_arch(char **cmdline_p)
 	strlcpy(command_line, boot_command_line, COMMAND_LINE_SIZE);
 	*cmdline_p = command_line;
 
-#ifdef CONFIG_X86_64
 	/*
-	 * Must call this twice: Once just to detect whether hardware doesn't
-	 * support NX (so that the early EHCI debug console setup can safely
-	 * call set_fixmap(), and then again after parsing early parameters to
-	 * honor the respective command line option.
+	 * x86_configure_nx() is called before parse_early_param() to detect
+	 * whether hardware doesn't support NX (so that the early EHCI debug
+	 * console setup can safely call set_fixmap()). It may then be called
+	 * again from within noexec_setup() during parsing early parameters
+	 * to honor the respective command line option.
 	 */
-	check_efer();
-#endif
+	x86_configure_nx();
 
 	parse_early_param();
 
-#ifdef CONFIG_X86_64
-	check_efer();
-#endif
+	x86_report_nx();
 
 	/* Must be before kernel pagetables are setup */
 	vmi_activate();
@@ -901,6 +875,13 @@ void __init setup_arch(char **cmdline_p)
 
 	reserve_brk();
 
+#ifdef CONFIG_ACPI_SLEEP
+	/*
+	 * Reserve low memory region for sleep support.
+	 * even before init_memory_mapping
+	 */
+	acpi_reserve_wakeup_memory();
+#endif
 	init_gbpages();
 
 	/* max_pfn_mapped is updated here */
@@ -927,6 +908,8 @@ void __init setup_arch(char **cmdline_p)
 
 	reserve_initrd();
 
+	reserve_crashkernel();
+
 	vsmp_init();
 
 	io_delay_init();
@@ -938,27 +921,24 @@ void __init setup_arch(char **cmdline_p)
 
 	early_acpi_boot_init();
 
+	/*
+	 * Find and reserve possible boot-time SMP configuration:
+	 */
+	find_smp_config();
+
 #ifdef CONFIG_ACPI_NUMA
 	/*
 	 * Parse SRAT to discover nodes.
 	 */
-	acpi_numa_init();
+	acpi = acpi_numa_init();
 #endif
 
-	initmem_init(0, max_pfn);
-
-#ifdef CONFIG_ACPI_SLEEP
-	/*
-	 * Reserve low memory region for sleep support.
-	 */
-	acpi_reserve_bootmem();
+#ifdef CONFIG_K8_NUMA
+	if (!acpi)
+		k8 = !k8_numa_init(0, max_pfn);
 #endif
-	/*
-	 * Find and reserve possible boot-time SMP configuration:
-	 */
-	find_smp_config();
 
-	reserve_crashkernel();
+	initmem_init(0, max_pfn, acpi, k8);
 
 #ifdef CONFIG_X86_64
 	/*
diff --git a/arch/x86/kernel/tlb_uv.c b/arch/x86/kernel/tlb_uv.c
index 1740c85e24b..364d015efeb 100644
--- a/arch/x86/kernel/tlb_uv.c
+++ b/arch/x86/kernel/tlb_uv.c
@@ -817,10 +817,8 @@ static int __init uv_init_blade(int blade)
 	 */
 	apicid = blade_to_first_apicid(blade);
 	pa = uv_read_global_mmr64(pnode, UVH_BAU_DATA_CONFIG);
-	if ((pa & 0xff) != UV_BAU_MESSAGE) {
-		uv_write_global_mmr64(pnode, UVH_BAU_DATA_CONFIG,
+	uv_write_global_mmr64(pnode, UVH_BAU_DATA_CONFIG,
 				      ((apicid << 32) | UV_BAU_MESSAGE));
-	}
 	return 0;
 }
 
diff --git a/arch/x86/kernel/visws_quirks.c b/arch/x86/kernel/visws_quirks.c
index abda6f53e71..34a279a7471 100644
--- a/arch/x86/kernel/visws_quirks.c
+++ b/arch/x86/kernel/visws_quirks.c
@@ -197,7 +197,7 @@ static void __init MP_processor_info(struct mpc_cpu *m)
 	apic_version[m->apicid] = ver;
 }
 
-static void __init visws_find_smp_config(unsigned int reserve)
+static void __init visws_find_smp_config(void)
 {
 	struct mpc_cpu *mp = phys_to_virt(CO_CPU_TAB_PHYS);
 	unsigned short ncpus = readw(phys_to_virt(CO_CPU_NUM_PHYS));
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 3c68fe2d46c..f3f2104408d 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -41,6 +41,32 @@ ENTRY(phys_startup_64)
 jiffies_64 = jiffies;
 #endif
 
+#if defined(CONFIG_X86_64) && defined(CONFIG_DEBUG_RODATA)
+/*
+ * On 64-bit, align RODATA to 2MB so that even with CONFIG_DEBUG_RODATA
+ * we retain large page mappings for boundaries spanning kernel text, rodata
+ * and data sections.
+ *
+ * However, kernel identity mappings will have different RWX permissions
+ * to the pages mapping to text and to the pages padding (which are freed) the
+ * text section. Hence kernel identity mappings will be broken to smaller
+ * pages. For 64-bit, kernel text and kernel identity mappings are different,
+ * so we can enable protection checks that come with CONFIG_DEBUG_RODATA,
+ * as well as retain 2MB large page mappings for kernel text.
+ */
+#define X64_ALIGN_DEBUG_RODATA_BEGIN	. = ALIGN(HPAGE_SIZE);
+
+#define X64_ALIGN_DEBUG_RODATA_END				\
+		. = ALIGN(HPAGE_SIZE);				\
+		__end_rodata_hpage_align = .;
+
+#else
+
+#define X64_ALIGN_DEBUG_RODATA_BEGIN
+#define X64_ALIGN_DEBUG_RODATA_END
+
+#endif
+
 PHDRS {
 	text PT_LOAD FLAGS(5);          /* R_E */
 	data PT_LOAD FLAGS(7);          /* RWE */
@@ -90,7 +116,9 @@ SECTIONS
 
 	EXCEPTION_TABLE(16) :text = 0x9090
 
+	X64_ALIGN_DEBUG_RODATA_BEGIN
 	RO_DATA(PAGE_SIZE)
+	X64_ALIGN_DEBUG_RODATA_END
 
 	/* Data */
 	.data : AT(ADDR(.data) - LOAD_OFFSET) {
@@ -107,13 +135,13 @@ SECTIONS
 
 		PAGE_ALIGNED_DATA(PAGE_SIZE)
 
-		CACHELINE_ALIGNED_DATA(CONFIG_X86_L1_CACHE_BYTES)
+		CACHELINE_ALIGNED_DATA(L1_CACHE_BYTES)
 
 		DATA_DATA
 		CONSTRUCTORS
 
 		/* rarely changed data like cpu maps */
-		READ_MOSTLY_DATA(CONFIG_X86_INTERNODE_CACHE_BYTES)
+		READ_MOSTLY_DATA(INTERNODE_CACHE_BYTES)
 
 		/* End of data section */
 		_edata = .;
@@ -137,12 +165,12 @@ SECTIONS
 		*(.vsyscall_0)
 	} :user
 
-	. = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
+	. = ALIGN(L1_CACHE_BYTES);
 	.vsyscall_fn : AT(VLOAD(.vsyscall_fn)) {
 		*(.vsyscall_fn)
 	}
 
-	. = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
+	. = ALIGN(L1_CACHE_BYTES);
 	.vsyscall_gtod_data : AT(VLOAD(.vsyscall_gtod_data)) {
 		*(.vsyscall_gtod_data)
 	}
@@ -166,7 +194,7 @@ SECTIONS
 	}
 	vgetcpu_mode = VVIRT(.vgetcpu_mode);
 
-	. = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
+	. = ALIGN(L1_CACHE_BYTES);
 	.jiffies : AT(VLOAD(.jiffies)) {
 		*(.jiffies)
 	}
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index d11c5ff7c65..ccd179dec36 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -13,6 +13,7 @@
 #include <asm/e820.h>
 #include <asm/time.h>
 #include <asm/irq.h>
+#include <asm/pat.h>
 #include <asm/tsc.h>
 #include <asm/iommu.h>
 
@@ -80,4 +81,5 @@ struct x86_platform_ops x86_platform = {
 	.get_wallclock			= mach_get_cmos_time,
 	.set_wallclock			= mach_set_rtc_mmss,
 	.iommu_shutdown			= iommu_shutdown_noop,
+	.is_untracked_pat_range		= is_ISA_range,
 };