Merge git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6 into for-linus

47 files changed, 518 insertions, 866 deletions

diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 21dc1a061bf1..76ec0f8f138a 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -84,8 +84,6 @@ ifeq ($(CONFIG_X86_64),y)
         obj-y				+= genapic_64.o genapic_flat_64.o
         obj-$(CONFIG_X86_PM_TIMER)	+= pmtimer_64.o
         obj-$(CONFIG_AUDIT)		+= audit_64.o
-        obj-$(CONFIG_PM)		+= suspend_64.o
-        obj-$(CONFIG_HIBERNATION)	+= suspend_asm_64.o
 
         obj-$(CONFIG_GART_IOMMU)	+= pci-gart_64.o aperture_64.o
         obj-$(CONFIG_CALGARY_IOMMU)	+= pci-calgary_64.o tce_64.o
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index d2a58431a074..680b7300a489 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -78,7 +78,6 @@ int acpi_ht __initdata = 1;	/* enable HT */
 int acpi_lapic;
 int acpi_ioapic;
 int acpi_strict;
-EXPORT_SYMBOL(acpi_strict);
 
 u8 acpi_sci_flags __initdata;
 int acpi_sci_override_gsi __initdata;
@@ -106,7 +105,7 @@ enum acpi_irq_model_id acpi_irq_model = ACPI_IRQ_MODEL_PIC;
 #ifdef	CONFIG_X86_64
 
 /* rely on all ACPI tables being in the direct mapping */
-char *__acpi_map_table(unsigned long phys_addr, unsigned long size)
+char *__init __acpi_map_table(unsigned long phys_addr, unsigned long size)
 {
 	if (!phys_addr || !size)
 		return NULL;
@@ -131,7 +130,7 @@ char *__acpi_map_table(unsigned long phys_addr, unsigned long size)
  * from the fixed base.  That's why we start at FIX_IO_APIC_BASE_END and
  * count idx down while incrementing the phys address.
  */
-char *__acpi_map_table(unsigned long phys, unsigned long size)
+char *__init __acpi_map_table(unsigned long phys, unsigned long size)
 {
 	unsigned long base, offset, mapped_size;
 	int idx;
@@ -490,8 +489,6 @@ int acpi_register_gsi(u32 gsi, int triggering, int polarity)
 	return irq;
 }
 
-EXPORT_SYMBOL(acpi_register_gsi);
-
 /*
  *  ACPI based hotplug support for CPU
  */
@@ -587,25 +584,6 @@ int acpi_unregister_ioapic(acpi_handle handle, u32 gsi_base)
 
 EXPORT_SYMBOL(acpi_unregister_ioapic);
 
-static unsigned long __init
-acpi_scan_rsdp(unsigned long start, unsigned long length)
-{
-	unsigned long offset = 0;
-	unsigned long sig_len = sizeof("RSD PTR ") - 1;
-
-	/*
-	 * Scan all 16-byte boundaries of the physical memory region for the
-	 * RSDP signature.
-	 */
-	for (offset = 0; offset < length; offset += 16) {
-		if (strncmp((char *)(phys_to_virt(start) + offset), "RSD PTR ", sig_len))
-			continue;
-		return (start + offset);
-	}
-
-	return 0;
-}
-
 static int __init acpi_parse_sbf(struct acpi_table_header *table)
 {
 	struct acpi_table_boot *sb;
@@ -748,27 +726,6 @@ static int __init acpi_parse_fadt(struct acpi_table_header *table)
 	return 0;
 }
 
-unsigned long __init acpi_find_rsdp(void)
-{
-	unsigned long rsdp_phys = 0;
-
-	if (efi_enabled) {
-		if (efi.acpi20 != EFI_INVALID_TABLE_ADDR)
-			return efi.acpi20;
-		else if (efi.acpi != EFI_INVALID_TABLE_ADDR)
-			return efi.acpi;
-	}
-	/*
-	 * Scan memory looking for the RSDP signature. First search EBDA (low
-	 * memory) paragraphs and then search upper memory (E0000-FFFFF).
-	 */
-	rsdp_phys = acpi_scan_rsdp(0, 0x400);
-	if (!rsdp_phys)
-		rsdp_phys = acpi_scan_rsdp(0xE0000, 0x20000);
-
-	return rsdp_phys;
-}
-
 #ifdef	CONFIG_X86_LOCAL_APIC
 /*
  * Parse LAPIC entries in MADT
diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c
index 10b67170b133..8ca3557a6d59 100644
--- a/arch/x86/kernel/acpi/cstate.c
+++ b/arch/x86/kernel/acpi/cstate.c
@@ -126,6 +126,8 @@ int acpi_processor_ffh_cstate_probe(unsigned int cpu,
 		printk(KERN_DEBUG "Monitor-Mwait will be used to enter C-%d "
 		       "state\n", cx->type);
 	}
+	snprintf(cx->desc, ACPI_CX_DESC_LEN, "ACPI FFH INTEL MWAIT 0x%x",
+		 cx->address);
 
 out:
 	set_cpus_allowed(current, saved_mask);
diff --git a/arch/x86/kernel/acpi/processor.c b/arch/x86/kernel/acpi/processor.c
index a25db514c719..324eb0cab19c 100644
--- a/arch/x86/kernel/acpi/processor.c
+++ b/arch/x86/kernel/acpi/processor.c
@@ -46,6 +46,12 @@ static void init_intel_pdc(struct acpi_processor *pr, struct cpuinfo_x86 *c)
 	buf[1] = 1;
 	buf[2] = ACPI_PDC_C_CAPABILITY_SMP;
 
+	/*
+	 * The default of PDC_SMP_T_SWCOORD bit is set for intel x86 cpu so
+	 * that OSPM is capable of native ACPI throttling software
+	 * coordination using BIOS supplied _TSD info.
+	 */
+	buf[2] |= ACPI_PDC_SMP_T_SWCOORD;
 	if (cpu_has(c, X86_FEATURE_EST))
 		buf[2] |= ACPI_PDC_EST_CAPABILITY_SWSMP;
 
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index d9313d9adced..f86a3c4a2669 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -637,7 +637,7 @@ void __init early_cpu_init(void)
 }
 
 /* Make sure %fs is initialized properly in idle threads */
-struct pt_regs * __devinit idle_regs(struct pt_regs *regs)
+struct pt_regs * __cpuinit idle_regs(struct pt_regs *regs)
 {
 	memset(regs, 0, sizeof(struct pt_regs));
 	regs->fs = __KERNEL_PERCPU;
diff --git a/arch/x86/kernel/cpu/cpufreq/Kconfig b/arch/x86/kernel/cpu/cpufreq/Kconfig
index 151eda0a23fc..cb7a5715596d 100644
--- a/arch/x86/kernel/cpu/cpufreq/Kconfig
+++ b/arch/x86/kernel/cpu/cpufreq/Kconfig
@@ -29,7 +29,7 @@ config X86_ACPI_CPUFREQ
 config ELAN_CPUFREQ
 	tristate "AMD Elan SC400 and SC410"
 	select CPU_FREQ_TABLE
-	depends on X86_32 && X86_ELAN
+	depends on X86_ELAN
 	---help---
 	  This adds the CPUFreq driver for AMD Elan SC400 and SC410
 	  processors.
@@ -45,7 +45,7 @@ config ELAN_CPUFREQ
 config SC520_CPUFREQ
 	tristate "AMD Elan SC520"
 	select CPU_FREQ_TABLE
-	depends on X86_32 && X86_ELAN
+	depends on X86_ELAN
 	---help---
 	  This adds the CPUFreq driver for AMD Elan SC520 processor.
 
diff --git a/arch/x86/kernel/cpu/cpufreq/e_powersaver.c b/arch/x86/kernel/cpu/cpufreq/e_powersaver.c
index 326a4c81f684..39f8cb18296c 100644
--- a/arch/x86/kernel/cpu/cpufreq/e_powersaver.c
+++ b/arch/x86/kernel/cpu/cpufreq/e_powersaver.c
@@ -23,6 +23,7 @@
 #define EPS_BRAND_C7	1
 #define EPS_BRAND_EDEN	2
 #define EPS_BRAND_C3	3
+#define EPS_BRAND_C7D	4
 
 struct eps_cpu_data {
 	u32 fsb;
@@ -54,6 +55,7 @@ static int eps_set_state(struct eps_cpu_data *centaur,
 {
 	struct cpufreq_freqs freqs;
 	u32 lo, hi;
+	u8 current_multiplier, current_voltage;
 	int err = 0;
 	int i;
 
@@ -93,6 +95,15 @@ postchange:
 	rdmsr(MSR_IA32_PERF_STATUS, lo, hi);
 	freqs.new = centaur->fsb * ((lo >> 8) & 0xff);
 
+	/* Print voltage and multiplier */
+	rdmsr(MSR_IA32_PERF_STATUS, lo, hi);
+	current_voltage = lo & 0xff;
+	printk(KERN_INFO "eps: Current voltage = %dmV\n",
+		current_voltage * 16 + 700);
+	current_multiplier = (lo >> 8) & 0xff;
+	printk(KERN_INFO "eps: Current multiplier = %d\n",
+		current_multiplier);
+
 	cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
 	return err;
 }
@@ -141,9 +152,10 @@ static int eps_cpu_init(struct cpufreq_policy *policy)
 	u8 current_multiplier, current_voltage;
 	u8 max_multiplier, max_voltage;
 	u8 min_multiplier, min_voltage;
-	u8 brand;
+	u8 brand = 0;
 	u32 fsb;
 	struct eps_cpu_data *centaur;
+	struct cpuinfo_x86 *c = &cpu_data(0);
 	struct cpufreq_frequency_table *f_table;
 	int k, step, voltage;
 	int ret;
@@ -153,21 +165,36 @@ static int eps_cpu_init(struct cpufreq_policy *policy)
 		return -ENODEV;
 
 	/* Check brand */
-	printk("eps: Detected VIA ");
-	rdmsr(0x1153, lo, hi);
-	brand = (((lo >> 2) ^ lo) >> 18) & 3;
+	printk(KERN_INFO "eps: Detected VIA ");
+
+	switch (c->x86_model) {
+	case 10:
+		rdmsr(0x1153, lo, hi);
+		brand = (((lo >> 2) ^ lo) >> 18) & 3;
+		printk(KERN_CONT "Model A ");
+		break;
+	case 13:
+		rdmsr(0x1154, lo, hi);
+		brand = (((lo >> 4) ^ (lo >> 2))) & 0x000000ff;
+		printk(KERN_CONT "Model D ");
+		break;
+	}
+
 	switch(brand) {
 	case EPS_BRAND_C7M:
-		printk("C7-M\n");
+		printk(KERN_CONT "C7-M\n");
 		break;
 	case EPS_BRAND_C7:
-		printk("C7\n");
+		printk(KERN_CONT "C7\n");
 		break;
 	case EPS_BRAND_EDEN:
-		printk("Eden\n");
+		printk(KERN_CONT "Eden\n");
+		break;
+	case EPS_BRAND_C7D:
+		printk(KERN_CONT "C7-D\n");
 		break;
 	case EPS_BRAND_C3:
-		printk("C3\n");
+		printk(KERN_CONT "C3\n");
 		return -ENODEV;
 		break;
 	}
@@ -179,7 +206,7 @@ static int eps_cpu_init(struct cpufreq_policy *policy)
 		/* Can be locked at 0 */
 		rdmsrl(MSR_IA32_MISC_ENABLE, val);
 		if (!(val & 1 << 16)) {
-			printk("eps: Can't enable Enhanced PowerSaver\n");
+			printk(KERN_INFO "eps: Can't enable Enhanced PowerSaver\n");
 			return -ENODEV;
 		}
 	}
@@ -187,19 +214,19 @@ static int eps_cpu_init(struct cpufreq_policy *policy)
 	/* Print voltage and multiplier */
 	rdmsr(MSR_IA32_PERF_STATUS, lo, hi);
 	current_voltage = lo & 0xff;
-	printk("eps: Current voltage = %dmV\n", current_voltage * 16 + 700);
+	printk(KERN_INFO "eps: Current voltage = %dmV\n", current_voltage * 16 + 700);
 	current_multiplier = (lo >> 8) & 0xff;
-	printk("eps: Current multiplier = %d\n", current_multiplier);
+	printk(KERN_INFO "eps: Current multiplier = %d\n", current_multiplier);
 
 	/* Print limits */
 	max_voltage = hi & 0xff;
-	printk("eps: Highest voltage = %dmV\n", max_voltage * 16 + 700);
+	printk(KERN_INFO "eps: Highest voltage = %dmV\n", max_voltage * 16 + 700);
 	max_multiplier = (hi >> 8) & 0xff;
-	printk("eps: Highest multiplier = %d\n", max_multiplier);
+	printk(KERN_INFO "eps: Highest multiplier = %d\n", max_multiplier);
 	min_voltage = (hi >> 16) & 0xff;
-	printk("eps: Lowest voltage = %dmV\n", min_voltage * 16 + 700);
+	printk(KERN_INFO "eps: Lowest voltage = %dmV\n", min_voltage * 16 + 700);
 	min_multiplier = (hi >> 24) & 0xff;
-	printk("eps: Lowest multiplier = %d\n", min_multiplier);
+	printk(KERN_INFO "eps: Lowest multiplier = %d\n", min_multiplier);
 
 	/* Sanity checks */
 	if (current_multiplier == 0 || max_multiplier == 0
@@ -208,7 +235,7 @@ static int eps_cpu_init(struct cpufreq_policy *policy)
 	if (current_multiplier > max_multiplier
 	    || max_multiplier <= min_multiplier)
 		return -EINVAL;
-	if (current_voltage > 0x1c || max_voltage > 0x1c)
+	if (current_voltage > 0x1f || max_voltage > 0x1f)
 		return -EINVAL;
 	if (max_voltage < min_voltage)
 		return -EINVAL;
@@ -310,7 +337,7 @@ static int __init eps_init(void)
 	/* This driver will work only on Centaur C7 processors with
 	 * Enhanced SpeedStep/PowerSaver registers */
 	if (c->x86_vendor != X86_VENDOR_CENTAUR
-	    || c->x86 != 6 || c->x86_model != 10)
+	    || c->x86 != 6 || c->x86_model < 10)
 		return -ENODEV;
 	if (!cpu_has(c, X86_FEATURE_EST))
 		return -ENODEV;
diff --git a/arch/x86/kernel/cpu/cpufreq/gx-suspmod.c b/arch/x86/kernel/cpu/cpufreq/gx-suspmod.c
index 2ed7db2fd257..9d9eae82e60f 100644
--- a/arch/x86/kernel/cpu/cpufreq/gx-suspmod.c
+++ b/arch/x86/kernel/cpu/cpufreq/gx-suspmod.c
@@ -181,8 +181,8 @@ static __init struct pci_dev *gx_detect_chipset(void)
 	struct pci_dev *gx_pci = NULL;
 
 	/* check if CPU is a MediaGX or a Geode. */
-	if ((current_cpu_data.x86_vendor != X86_VENDOR_NSC) &&
-	    (current_cpu_data.x86_vendor != X86_VENDOR_CYRIX)) {
+	if ((boot_cpu_data.x86_vendor != X86_VENDOR_NSC) &&
+	    (boot_cpu_data.x86_vendor != X86_VENDOR_CYRIX)) {
 		dprintk("error: no MediaGX/Geode processor found!\n");
 		return NULL;
 	}
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k7.c b/arch/x86/kernel/cpu/cpufreq/powernow-k7.c
index b5a9863d6cdc..0a61159d7b71 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k7.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k7.c
@@ -460,7 +460,7 @@ static int powernow_decode_bios (int maxfid, int startvid)
 
 			latency = psb->settlingtime;
 			if (latency < 100) {
-				printk (KERN_INFO PFX "BIOS set settling time to %d microseconds."
+				printk(KERN_INFO PFX "BIOS set settling time to %d microseconds. "
 						"Should be at least 100. Correcting.\n", latency);
 				latency = 100;
 			}
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
index a0522735dd9d..c99d59d8ef2e 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
@@ -578,10 +578,9 @@ static void print_basics(struct powernow_k8_data *data)
 	for (j = 0; j < data->numps; j++) {
 		if (data->powernow_table[j].frequency != CPUFREQ_ENTRY_INVALID) {
 			if (cpu_family == CPU_HW_PSTATE) {
-				printk(KERN_INFO PFX "   %d : fid 0x%x did 0x%x (%d MHz)\n",
+				printk(KERN_INFO PFX "   %d : pstate %d (%d MHz)\n",
 					j,
-					(data->powernow_table[j].index & 0xff00) >> 8,
-					(data->powernow_table[j].index & 0xff0000) >> 16,
+					data->powernow_table[j].index,
 					data->powernow_table[j].frequency/1000);
 			} else {
 				printk(KERN_INFO PFX "   %d : fid 0x%x (%d MHz), vid 0x%x\n",
@@ -827,7 +826,6 @@ static int fill_powernow_table_pstate(struct powernow_k8_data *data, struct cpuf
 
 	for (i = 0; i < data->acpi_data.state_count; i++) {
 		u32 index;
-		u32 hi = 0, lo = 0;
 
 		index = data->acpi_data.states[i].control & HW_PSTATE_MASK;
 		if (index > data->max_hw_pstate) {
@@ -1236,8 +1234,10 @@ static unsigned int powernowk8_get (unsigned int cpu)
 	struct powernow_k8_data *data;
 	cpumask_t oldmask = current->cpus_allowed;
 	unsigned int khz = 0;
+	unsigned int first;
 
-	data = per_cpu(powernow_data, first_cpu(per_cpu(cpu_core_map, cpu)));
+	first = first_cpu(per_cpu(cpu_core_map, cpu));
+	data = per_cpu(powernow_data, first);
 
 	if (!data)
 		return -EINVAL;
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.h b/arch/x86/kernel/cpu/cpufreq/powernow-k8.h
index afd2b520d35c..ab48cfed4d96 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.h
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.h
@@ -47,7 +47,7 @@ struct powernow_k8_data {
 #define CPUID_XFAM			0x0ff00000	/* extended family */
 #define CPUID_XFAM_K8			0
 #define CPUID_XMOD			0x000f0000	/* extended model */
-#define CPUID_XMOD_REV_MASK		0x00080000
+#define CPUID_XMOD_REV_MASK		0x000c0000
 #define CPUID_XFAM_10H			0x00100000	/* family 0x10 */
 #define CPUID_USE_XFAM_XMOD		0x00000f00
 #define CPUID_GET_MAX_CAPABILITIES	0x80000000
diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-lib.c b/arch/x86/kernel/cpu/cpufreq/speedstep-lib.c
index 76c3ab0da468..98d4fdb7dc04 100644
--- a/arch/x86/kernel/cpu/cpufreq/speedstep-lib.c
+++ b/arch/x86/kernel/cpu/cpufreq/speedstep-lib.c
@@ -189,10 +189,7 @@ static unsigned int pentium4_get_frequency(void)
 		printk(KERN_DEBUG "speedstep-lib: couldn't detect FSB speed. Please send an e-mail to <linux@brodo.de>\n");
 
 	/* Multiplier. */
-	if (c->x86_model < 2)
-		mult = msr_lo >> 27;
-	else
-		mult = msr_lo >> 24;
+	mult = msr_lo >> 24;
 
 	dprintk("P4 - FSB %u kHz; Multiplier %u; Speed %u kHz\n", fsb, mult, (fsb * mult));
 
diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c
index 404a6a2d4016..7139b0262703 100644
--- a/arch/x86/kernel/cpu/cyrix.c
+++ b/arch/x86/kernel/cpu/cyrix.c
@@ -83,8 +83,6 @@ static char cyrix_model_mult2[] __cpuinitdata = "12233445";
  * FIXME: our newer udelay uses the tsc. We don't need to frob with SLOP
  */
 
-extern void calibrate_delay(void) __init;
-
 static void __cpuinit check_cx686_slop(struct cpuinfo_x86 *c)
 {
 	unsigned long flags;
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index 24885be5c48c..9b7e01daa1ca 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -118,7 +118,7 @@ static __cpuinit int thermal_throttle_add_dev(struct sys_device *sys_dev)
 
 static __cpuinit void thermal_throttle_remove_dev(struct sys_device *sys_dev)
 {
-	return sysfs_remove_group(&sys_dev->kobj, &thermal_throttle_attr_group);
+	sysfs_remove_group(&sys_dev->kobj, &thermal_throttle_attr_group);
 }
 
 /* Mutex protecting device creation against CPU hotplug */
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index 1e27b69a7a0e..b6e136f23d3d 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -659,7 +659,7 @@ static __init int amd_special_default_mtrr(void)
  */
 int __init mtrr_trim_uncached_memory(unsigned long end_pfn)
 {
-	unsigned long i, base, size, highest_addr = 0, def, dummy;
+	unsigned long i, base, size, highest_pfn = 0, def, dummy;
 	mtrr_type type;
 	u64 trim_start, trim_size;
 
@@ -682,28 +682,27 @@ int __init mtrr_trim_uncached_memory(unsigned long end_pfn)
 		mtrr_if->get(i, &base, &size, &type);
 		if (type != MTRR_TYPE_WRBACK)
 			continue;
-		base <<= PAGE_SHIFT;
-		size <<= PAGE_SHIFT;
-		if (highest_addr < base + size)
-			highest_addr = base + size;
+		if (highest_pfn < base + size)
+			highest_pfn = base + size;
 	}
 
 	/* kvm/qemu doesn't have mtrr set right, don't trim them all */
-	if (!highest_addr) {
+	if (!highest_pfn) {
 		printk(KERN_WARNING "WARNING: strange, CPU MTRRs all blank?\n");
 		WARN_ON(1);
 		return 0;
 	}
 
-	if ((highest_addr >> PAGE_SHIFT) < end_pfn) {
+	if (highest_pfn < end_pfn) {
 		printk(KERN_WARNING "WARNING: BIOS bug: CPU MTRRs don't cover"
-			" all of memory, losing %LdMB of RAM.\n",
-			(((u64)end_pfn << PAGE_SHIFT) - highest_addr) >> 20);
+			" all of memory, losing %luMB of RAM.\n",
+			(end_pfn - highest_pfn) >> (20 - PAGE_SHIFT));
 
 		WARN_ON(1);
 
 		printk(KERN_INFO "update e820 for mtrr\n");
-		trim_start = highest_addr;
+		trim_start = highest_pfn;
+		trim_start <<= PAGE_SHIFT;
 		trim_size = end_pfn;
 		trim_size <<= PAGE_SHIFT;
 		trim_size -= trim_start;
diff --git a/arch/x86/kernel/efi.c b/arch/x86/kernel/efi.c
index 32dd62b36ff7..0c0eeb163d90 100644
--- a/arch/x86/kernel/efi.c
+++ b/arch/x86/kernel/efi.c
@@ -384,9 +384,6 @@ static void __init runtime_code_page_mkexec(void)
 	efi_memory_desc_t *md;
 	void *p;
 
-	if (!(__supported_pte_mask & _PAGE_NX))
-		return;
-
 	/* Make EFI runtime service code area executable */
 	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
 		md = p;
@@ -394,7 +391,7 @@ static void __init runtime_code_page_mkexec(void)
 		if (md->type != EFI_RUNTIME_SERVICES_CODE)
 			continue;
 
-		set_memory_x(md->virt_addr, md->num_pages << EFI_PAGE_SHIFT);
+		set_memory_x(md->virt_addr, md->num_pages);
 	}
 }
 
@@ -428,9 +425,6 @@ void __init efi_enter_virtual_mode(void)
 		else
 			va = efi_ioremap(md->phys_addr, size);
 
-		if (md->attribute & EFI_MEMORY_WB)
-			set_memory_uc(md->virt_addr, size);
-
 		md->virt_addr = (u64) (unsigned long) va;
 
 		if (!va) {
@@ -439,6 +433,9 @@ void __init efi_enter_virtual_mode(void)
 			continue;
 		}
 
+		if (!(md->attribute & EFI_MEMORY_WB))
+			set_memory_uc(md->virt_addr, md->num_pages);
+
 		systab = (u64) (unsigned long) efi_phys.systab;
 		if (md->phys_addr <= systab && systab < end) {
 			systab += md->virt_addr - md->phys_addr;
@@ -476,7 +473,8 @@ void __init efi_enter_virtual_mode(void)
 	efi.get_next_high_mono_count = virt_efi_get_next_high_mono_count;
 	efi.reset_system = virt_efi_reset_system;
 	efi.set_virtual_address_map = virt_efi_set_virtual_address_map;
-	runtime_code_page_mkexec();
+	if (__supported_pte_mask & _PAGE_NX)
+		runtime_code_page_mkexec();
 	early_iounmap(memmap.map, memmap.nr_map * memmap.desc_size);
 	memmap.map = NULL;
 }
diff --git a/arch/x86/kernel/efi_64.c b/arch/x86/kernel/efi_64.c
index 09d5c2330934..d143a1e76b30 100644
--- a/arch/x86/kernel/efi_64.c
+++ b/arch/x86/kernel/efi_64.c
@@ -35,6 +35,7 @@
 #include <asm/tlbflush.h>
 #include <asm/proto.h>
 #include <asm/efi.h>
+#include <asm/cacheflush.h>
 
 static pgd_t save_pgd __initdata;
 static unsigned long efi_flags __initdata;
@@ -43,22 +44,15 @@ static void __init early_mapping_set_exec(unsigned long start,
 					  unsigned long end,
 					  int executable)
 {
-	pte_t *kpte;
-	unsigned int level;
-
-	while (start < end) {
-		kpte = lookup_address((unsigned long)__va(start), &level);
-		BUG_ON(!kpte);
-		if (executable)
-			set_pte(kpte, pte_mkexec(*kpte));
-		else
-			set_pte(kpte, __pte((pte_val(*kpte) | _PAGE_NX) & \
-					    __supported_pte_mask));
-		if (level == PG_LEVEL_4K)
-			start = (start + PAGE_SIZE) & PAGE_MASK;
-		else
-			start = (start + PMD_SIZE) & PMD_MASK;
-	}
+	unsigned long num_pages;
+
+	start &= PMD_MASK;
+	end = (end + PMD_SIZE - 1) & PMD_MASK;
+	num_pages = (end - start) >> PAGE_SHIFT;
+	if (executable)
+		set_memory_x((unsigned long)__va(start), num_pages);
+	else
+		set_memory_nx((unsigned long)__va(start), num_pages);
 }
 
 static void __init early_runtime_code_mapping_set_exec(int executable)
@@ -74,7 +68,7 @@ static void __init early_runtime_code_mapping_set_exec(int executable)
 		md = p;
 		if (md->type == EFI_RUNTIME_SERVICES_CODE) {
 			unsigned long end;
-			end = md->phys_addr + (md->num_pages << PAGE_SHIFT);
+			end = md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT);
 			early_mapping_set_exec(md->phys_addr, end, executable);
 		}
 	}
@@ -84,8 +78,8 @@ void __init efi_call_phys_prelog(void)
 {
 	unsigned long vaddress;
 
-	local_irq_save(efi_flags);
 	early_runtime_code_mapping_set_exec(1);
+	local_irq_save(efi_flags);
 	vaddress = (unsigned long)__va(0x0UL);
 	save_pgd = *pgd_offset_k(0x0UL);
 	set_pgd(pgd_offset_k(0x0UL), *pgd_offset_k(vaddress));
@@ -98,9 +92,9 @@ void __init efi_call_phys_epilog(void)
 	 * After the lock is released, the original page table is restored.
 	 */
 	set_pgd(pgd_offset_k(0x0UL), save_pgd);
-	early_runtime_code_mapping_set_exec(0);
 	__flush_tlb_all();
 	local_irq_restore(efi_flags);
+	early_runtime_code_mapping_set_exec(0);
 }
 
 void __init efi_reserve_bootmem(void)
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index be5c31d04884..824e21b80aad 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -409,7 +409,8 @@ restore_nocheck_notrace:
 	RESTORE_REGS
 	addl $4, %esp			# skip orig_eax/error_code
 	CFI_ADJUST_CFA_OFFSET -4
-1:	INTERRUPT_RETURN
+ENTRY(irq_return)
+	INTERRUPT_RETURN
 .section .fixup,"ax"
 iret_exc:
 	pushl $0			# no error code
@@ -418,7 +419,7 @@ iret_exc:
 .previous
 .section __ex_table,"a"
 	.align 4
-	.long 1b,iret_exc
+	.long irq_return,iret_exc
 .previous
 
 	CFI_RESTORE_STATE
@@ -865,20 +866,16 @@ nmi_espfix_stack:
 	RESTORE_REGS
 	lss 12+4(%esp), %esp		# back to espfix stack
 	CFI_ADJUST_CFA_OFFSET -24
-1:	INTERRUPT_RETURN
+	jmp irq_return
 	CFI_ENDPROC
-.section __ex_table,"a"
-	.align 4
-	.long 1b,iret_exc
-.previous
 KPROBE_END(nmi)
 
 #ifdef CONFIG_PARAVIRT
 ENTRY(native_iret)
-1:	iret
+	iret
 .section __ex_table,"a"
 	.align 4
-	.long 1b,iret_exc
+	.long native_iret, iret_exc
 .previous
 END(native_iret)
 
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index bea8474744ff..6be39a387c5a 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -581,25 +581,41 @@ retint_restore_args:	/* return to kernel space */
 	 */
 	TRACE_IRQS_IRETQ
 restore_args:
-	RESTORE_ARGS 0,8,0						
-iret_label:	
-#ifdef CONFIG_PARAVIRT
+	RESTORE_ARGS 0,8,0
+
+ENTRY(irq_return)
 	INTERRUPT_RETURN
-#endif
+
+	.section __ex_table, "a"
+	.quad irq_return, bad_iret
+	.previous
+
+#ifdef CONFIG_PARAVIRT
 ENTRY(native_iret)
 	iretq
 
 	.section __ex_table,"a"
 	.quad native_iret, bad_iret
 	.previous
+#endif
+
 	.section .fixup,"ax"
-	/* force a signal here? this matches i386 behaviour */
-	/* running with kernel gs */
 bad_iret:
-	movq $11,%rdi	/* SIGSEGV */
-	TRACE_IRQS_ON
-	ENABLE_INTERRUPTS(CLBR_ANY | ~(CLBR_RDI))
-	jmp do_exit
+	/*
+	 * The iret traps when the %cs or %ss being restored is bogus.
+	 * We've lost the original trap vector and error code.
+	 * #GPF is the most likely one to get for an invalid selector.
+	 * So pretend we completed the iret and took the #GPF in user mode.
+	 *
+	 * We are now running with the kernel GS after exception recovery.
+	 * But error_entry expects us to have user GS to match the user %cs,
+	 * so swap back.
+	 */
+	pushq $0
+
+	SWAPGS
+	jmp general_protection
+
 	.previous
 
 	/* edi: workmask, edx: work */
@@ -796,7 +812,7 @@ paranoid_swapgs\trace:
 	SWAPGS_UNSAFE_STACK
 paranoid_restore\trace:
 	RESTORE_ALL 8
-	INTERRUPT_RETURN
+	jmp irq_return
 paranoid_userspace\trace:
 	GET_THREAD_INFO(%rcx)
 	movl threadinfo_flags(%rcx),%ebx
@@ -911,7 +927,7 @@ error_kernelspace:
 	   iret run with kernel gs again, so don't set the user space flag.
 	   B stepping K8s sometimes report an truncated RIP for IRET 
 	   exceptions returning to compat mode. Check for these here too. */
-	leaq iret_label(%rip),%rbp
+	leaq irq_return(%rip),%rbp
 	cmpq %rbp,RIP(%rsp) 
 	je   error_swapgs
 	movl %ebp,%ebp	/* zero extend */
diff --git a/arch/x86/kernel/geode_32.c b/arch/x86/kernel/geode_32.c
index 9c7f7d395968..9dad6ca6cd70 100644
--- a/arch/x86/kernel/geode_32.c
+++ b/arch/x86/kernel/geode_32.c
@@ -163,14 +163,11 @@ EXPORT_SYMBOL_GPL(geode_gpio_setup_event);
 
 static int __init geode_southbridge_init(void)
 {
-	int timers;
-
 	if (!is_geode())
 		return -ENODEV;
 
 	init_lbars();
-	timers = geode_mfgpt_detect();
-	printk(KERN_INFO "geode:  %d MFGPT timers available.\n", timers);
+	(void) mfgpt_timer_setup();
 	return 0;
 }
 
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 5d8c5730686b..74ef4a41f224 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -19,6 +19,10 @@
 #include <asm/thread_info.h>
 #include <asm/asm-offsets.h>
 #include <asm/setup.h>
+#include <asm/processor-flags.h>
+
+/* Physical address */
+#define pa(X) ((X) - __PAGE_OFFSET)
 
 /*
  * References to members of the new_cpu_data structure.
@@ -80,10 +84,6 @@ INIT_MAP_BEYOND_END = BOOTBITMAP_SIZE + (PAGE_TABLE_SIZE + ALLOCATOR_SLOP)*PAGE_
  */
 .section .text.head,"ax",@progbits
 ENTRY(startup_32)
-	/* check to see if KEEP_SEGMENTS flag is meaningful */
-	cmpw $0x207, BP_version(%esi)
-	jb 1f
-
 	/* test KEEP_SEGMENTS flag to see if the bootloader is asking
 		us to not reload segments */
 	testb $(1<<6), BP_loadflags(%esi)
@@ -92,7 +92,7 @@ ENTRY(startup_32)
 /*
  * Set segments to known values.
  */
-1:	lgdt boot_gdt_descr - __PAGE_OFFSET
+	lgdt pa(boot_gdt_descr)
 	movl $(__BOOT_DS),%eax
 	movl %eax,%ds
 	movl %eax,%es
@@ -105,8 +105,8 @@ ENTRY(startup_32)
  */
 	cld
 	xorl %eax,%eax
-	movl $__bss_start - __PAGE_OFFSET,%edi
-	movl $__bss_stop - __PAGE_OFFSET,%ecx
+	movl $pa(__bss_start),%edi
+	movl $pa(__bss_stop),%ecx
 	subl %edi,%ecx
 	shrl $2,%ecx
 	rep ; stosl
@@ -118,31 +118,32 @@ ENTRY(startup_32)
  * (kexec on panic case). Hence copy out the parameters before initializing
  * page tables.
  */
-	movl $(boot_params - __PAGE_OFFSET),%edi
+	movl $pa(boot_params),%edi
 	movl $(PARAM_SIZE/4),%ecx
 	cld
 	rep
 	movsl
-	movl boot_params - __PAGE_OFFSET + NEW_CL_POINTER,%esi
+	movl pa(boot_params) + NEW_CL_POINTER,%esi
 	andl %esi,%esi
 	jz 1f			# No comand line
-	movl $(boot_command_line - __PAGE_OFFSET),%edi
+	movl $pa(boot_command_line),%edi
 	movl $(COMMAND_LINE_SIZE/4),%ecx
 	rep
 	movsl
 1:
 
 #ifdef CONFIG_PARAVIRT
-	cmpw $0x207, (boot_params + BP_version - __PAGE_OFFSET)
+	/* This is can only trip for a broken bootloader... */
+	cmpw $0x207, pa(boot_params + BP_version)
 	jb default_entry
 
 	/* Paravirt-compatible boot parameters.  Look to see what architecture
 		we're booting under. */
-	movl (boot_params + BP_hardware_subarch - __PAGE_OFFSET), %eax
+	movl pa(boot_params + BP_hardware_subarch), %eax
 	cmpl $num_subarch_entries, %eax
 	jae bad_subarch
 
-	movl subarch_entries - __PAGE_OFFSET(,%eax,4), %eax
+	movl pa(subarch_entries)(,%eax,4), %eax
 	subl $__PAGE_OFFSET, %eax
 	jmp *%eax
 
@@ -170,17 +171,68 @@ num_subarch_entries = (. - subarch_entries) / 4
  * Mappings are created both at virtual address 0 (identity mapping)
  * and PAGE_OFFSET for up to _end+sizeof(page tables)+INIT_MAP_BEYOND_END.
  *
- * Warning: don't use %esi or the stack in this code.  However, %esp
- * can be used as a GPR if you really need it...
+ * Note that the stack is not yet set up!
  */
-page_pde_offset = (__PAGE_OFFSET >> 20);
+#define PTE_ATTR	0x007		/* PRESENT+RW+USER */
+#define PDE_ATTR	0x067		/* PRESENT+RW+USER+DIRTY+ACCESSED */
+#define PGD_ATTR	0x001		/* PRESENT (no other attributes) */
 
 default_entry:
-	movl $(pg0 - __PAGE_OFFSET), %edi
-	movl $(swapper_pg_dir - __PAGE_OFFSET), %edx
-	movl $0x007, %eax			/* 0x007 = PRESENT+RW+USER */
+#ifdef CONFIG_X86_PAE
+
+	/*
+	 * In PAE mode swapper_pg_dir is statically defined to contain enough
+	 * entries to cover the VMSPLIT option (that is the top 1, 2 or 3
+	 * entries). The identity mapping is handled by pointing two PGD
+	 * entries to the first kernel PMD.
+	 *
+	 * Note the upper half of each PMD or PTE are always zero at
+	 * this stage.
+	 */
+
+#define KPMDS ((0x100000000-__PAGE_OFFSET) >> 30) /* Number of kernel PMDs */
+
+	xorl %ebx,%ebx				/* %ebx is kept at zero */
+
+	movl $pa(pg0), %edi
+	movl $pa(swapper_pg_pmd), %edx
+	movl $PTE_ATTR, %eax
+10:
+	leal PDE_ATTR(%edi),%ecx		/* Create PMD entry */
+	movl %ecx,(%edx)			/* Store PMD entry */
+						/* Upper half already zero */
+	addl $8,%edx
+	movl $512,%ecx
+11:
+	stosl
+	xchgl %eax,%ebx
+	stosl
+	xchgl %eax,%ebx
+	addl $0x1000,%eax
+	loop 11b
+
+	/*
+	 * End condition: we must map up to and including INIT_MAP_BEYOND_END
+	 * bytes beyond the end of our own page tables.
+	 */
+	leal (INIT_MAP_BEYOND_END+PTE_ATTR)(%edi),%ebp
+	cmpl %ebp,%eax
+	jb 10b
+1:
+	movl %edi,pa(init_pg_tables_end)
+
+	/* Do early initialization of the fixmap area */
+	movl $pa(swapper_pg_fixmap)+PDE_ATTR,%eax
+	movl %eax,pa(swapper_pg_pmd+0x1000*KPMDS-8)
+#else	/* Not PAE */
+
+page_pde_offset = (__PAGE_OFFSET >> 20);
+
+	movl $pa(pg0), %edi
+	movl $pa(swapper_pg_dir), %edx
+	movl $PTE_ATTR, %eax
 10:
-	leal 0x007(%edi),%ecx			/* Create PDE entry */
+	leal PDE_ATTR(%edi),%ecx		/* Create PDE entry */
 	movl %ecx,(%edx)			/* Store identity PDE entry */
 	movl %ecx,page_pde_offset(%edx)		/* Store kernel PDE entry */
 	addl $4,%edx
@@ -189,19 +241,20 @@ default_entry:
 	stosl
 	addl $0x1000,%eax
 	loop 11b
-	/* End condition: we must map up to and including INIT_MAP_BEYOND_END */
-	/* bytes beyond the end of our own page tables; the +0x007 is the attribute bits */
-	leal (INIT_MAP_BEYOND_END+0x007)(%edi),%ebp
+	/*
+	 * End condition: we must map up to and including INIT_MAP_BEYOND_END
+	 * bytes beyond the end of our own page tables; the +0x007 is
+	 * the attribute bits
+	 */
+	leal (INIT_MAP_BEYOND_END+PTE_ATTR)(%edi),%ebp
 	cmpl %ebp,%eax
 	jb 10b
-	movl %edi,(init_pg_tables_end - __PAGE_OFFSET)
-
-	/* Do an early initialization of the fixmap area */
-	movl $(swapper_pg_dir - __PAGE_OFFSET), %edx
-	movl $(swapper_pg_pmd - __PAGE_OFFSET), %eax
-	addl $0x67, %eax			/* 0x67 == _PAGE_TABLE */
-	movl %eax, 4092(%edx)
+	movl %edi,pa(init_pg_tables_end)
 
+	/* Do early initialization of the fixmap area */
+	movl $pa(swapper_pg_fixmap)+PDE_ATTR,%eax
+	movl %eax,pa(swapper_pg_dir+0xffc)
+#endif
 	jmp 3f
 /*
  * Non-boot CPU entry point; entered from trampoline.S
@@ -241,7 +294,7 @@ ENTRY(startup_32_smp)
  *	NOTE! We have to correct for the fact that we're
  *	not yet offset PAGE_OFFSET..
  */
-#define cr4_bits mmu_cr4_features-__PAGE_OFFSET
+#define cr4_bits pa(mmu_cr4_features)
 	movl cr4_bits,%edx
 	andl %edx,%edx
 	jz 6f
@@ -276,10 +329,10 @@ ENTRY(startup_32_smp)
 /*
  * Enable paging
  */
-	movl $swapper_pg_dir-__PAGE_OFFSET,%eax
+	movl $pa(swapper_pg_dir),%eax
 	movl %eax,%cr3		/* set the page table pointer.. */
 	movl %cr0,%eax
-	orl $0x80000000,%eax
+	orl  $X86_CR0_PG,%eax
 	movl %eax,%cr0		/* ..and set paging (PG) bit */
 	ljmp $__BOOT_CS,$1f	/* Clear prefetch and normalize %eip */
 1:
@@ -552,16 +605,44 @@ ENTRY(_stext)
  */
 .section ".bss.page_aligned","wa"
 	.align PAGE_SIZE_asm
+#ifdef CONFIG_X86_PAE
+ENTRY(swapper_pg_pmd)
+	.fill 1024*KPMDS,4,0
+#else
 ENTRY(swapper_pg_dir)
 	.fill 1024,4,0
-ENTRY(swapper_pg_pmd)
+#endif
+ENTRY(swapper_pg_fixmap)
 	.fill 1024,4,0
 ENTRY(empty_zero_page)
 	.fill 4096,1,0
-
 /*
  * This starts the data section.
  */
+#ifdef CONFIG_X86_PAE
+.section ".data.page_aligned","wa"
+	/* Page-aligned for the benefit of paravirt? */
+	.align PAGE_SIZE_asm
+ENTRY(swapper_pg_dir)
+	.long	pa(swapper_pg_pmd+PGD_ATTR),0		/* low identity map */
+# if KPMDS == 3
+	.long	pa(swapper_pg_pmd+PGD_ATTR),0
+	.long	pa(swapper_pg_pmd+PGD_ATTR+0x1000),0
+	.long	pa(swapper_pg_pmd+PGD_ATTR+0x2000),0
+# elif KPMDS == 2
+	.long	0,0
+	.long	pa(swapper_pg_pmd+PGD_ATTR),0
+	.long	pa(swapper_pg_pmd+PGD_ATTR+0x1000),0
+# elif KPMDS == 1
+	.long	0,0
+	.long	0,0
+	.long	pa(swapper_pg_pmd+PGD_ATTR),0
+# else
+#  error "Kernel PMDs should be 1, 2 or 3"
+# endif
+	.align PAGE_SIZE_asm		/* needs to be page-sized too */
+#endif
+
 .data
 ENTRY(stack_start)
 	.long init_thread_union+THREAD_SIZE
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 4f283ad215ec..09b38d539b09 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -250,18 +250,13 @@ ENTRY(secondary_startup_64)
 	lretq
 
 	/* SMP bootup changes these two */
-#ifndef CONFIG_HOTPLUG_CPU
-	.pushsection .init.data
-#endif
+	__CPUINITDATA
 	.align	8
-	.globl	initial_code
-initial_code:
+	ENTRY(initial_code)
 	.quad	x86_64_start_kernel
-#ifndef CONFIG_HOTPLUG_CPU
-	.popsection
-#endif
-	.globl init_rsp
-init_rsp:
+	__FINITDATA
+
+	ENTRY(init_rsp)
 	.quad  init_thread_union+THREAD_SIZE-8
 
 bad_address:
diff --git a/arch/x86/kernel/i8253.c b/arch/x86/kernel/i8253.c
index ef62b07b2b48..8540abe86ade 100644
--- a/arch/x86/kernel/i8253.c
+++ b/arch/x86/kernel/i8253.c
@@ -95,7 +95,7 @@ static int pit_next_event(unsigned long delta, struct clock_event_device *evt)
  * registered. This mechanism replaces the previous #ifdef LOCAL_APIC -
  * !using_apic_timer decisions in do_timer_interrupt_hook()
  */
-struct clock_event_device pit_clockevent = {
+static struct clock_event_device pit_clockevent = {
 	.name		= "pit",
 	.features	= CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
 	.set_mode	= init_pit_timer,
diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c
index c1cfd60639d4..d0b234c9fc31 100644
--- a/arch/x86/kernel/machine_kexec_32.c
+++ b/arch/x86/kernel/machine_kexec_32.c
@@ -151,7 +151,7 @@ NORET_TYPE void machine_kexec(struct kimage *image)
 
 void arch_crash_save_vmcoreinfo(void)
 {
-#ifdef CONFIG_ARCH_DISCONTIGMEM_ENABLE
+#ifdef CONFIG_NUMA
 	VMCOREINFO_SYMBOL(node_data);
 	VMCOREINFO_LENGTH(node_data, MAX_NUMNODES);
 #endif
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index a1fef42f8cdb..236d2f8f7ddc 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -234,5 +234,10 @@ NORET_TYPE void machine_kexec(struct kimage *image)
 void arch_crash_save_vmcoreinfo(void)
 {
 	VMCOREINFO_SYMBOL(init_level4_pgt);
+
+#ifdef CONFIG_NUMA
+	VMCOREINFO_SYMBOL(node_data);
+	VMCOREINFO_LENGTH(node_data, MAX_NUMNODES);
+#endif
 }
 
diff --git a/arch/x86/kernel/mfgpt_32.c b/arch/x86/kernel/mfgpt_32.c
index 219f86eb6123..027fc067b399 100644
--- a/arch/x86/kernel/mfgpt_32.c
+++ b/arch/x86/kernel/mfgpt_32.c
@@ -12,48 +12,37 @@
  */
 
 /*
- * We are using the 32Khz input clock - its the only one that has the
+ * We are using the 32.768kHz input clock - it's the only one that has the
  * ranges we find desirable.  The following table lists the suitable
- * divisors and the associated hz, minimum interval
- * and the maximum interval:
+ * divisors and the associated Hz, minimum interval and the maximum interval:
  *
- *  Divisor   Hz      Min Delta (S) Max Delta (S)
- *   1        32000     .0005          2.048
- *   2        16000      .001          4.096
- *   4         8000      .002          8.192
- *   8         4000      .004         16.384
- *   16        2000      .008         32.768
- *   32        1000      .016         65.536
- *   64         500      .032        131.072
- *  128         250      .064        262.144
- *  256         125      .128        524.288
+ *  Divisor   Hz      Min Delta (s)  Max Delta (s)
+ *   1        32768   .00048828125      2.000
+ *   2        16384   .0009765625       4.000
+ *   4         8192   .001953125        8.000
+ *   8         4096   .00390625        16.000
+ *   16        2048   .0078125         32.000
+ *   32        1024   .015625          64.000
+ *   64         512   .03125          128.000
+ *  128         256   .0625           256.000
+ *  256         128   .125            512.000
  */
 
 #include <linux/kernel.h>
 #include <linux/interrupt.h>
-#include <linux/module.h>
 #include <asm/geode.h>
 
-#define F_AVAIL    0x01
-
 static struct mfgpt_timer_t {
-	int flags;
-	struct module *owner;
+	unsigned int avail:1;
 } mfgpt_timers[MFGPT_MAX_TIMERS];
 
 /* Selected from the table above */
 
 #define MFGPT_DIVISOR 16
 #define MFGPT_SCALE  4     /* divisor = 2^(scale) */
-#define MFGPT_HZ  (32000 / MFGPT_DIVISOR)
+#define MFGPT_HZ  (32768 / MFGPT_DIVISOR)
 #define MFGPT_PERIODIC (MFGPT_HZ / HZ)
 
-#ifdef CONFIG_GEODE_MFGPT_TIMER
-static int __init mfgpt_timer_setup(void);
-#else
-#define mfgpt_timer_setup() (0)
-#endif
-
 /* Allow for disabling of MFGPTs */
 static int disable;
 static int __init mfgpt_disable(char *s)
@@ -85,28 +74,37 @@ __setup("mfgptfix", mfgpt_fix);
  * In other cases (such as with VSAless OpenFirmware), the system firmware
  * leaves timers available for us to use.
  */
-int __init geode_mfgpt_detect(void)
+
+
+static int timers = -1;
+
+static void geode_mfgpt_detect(void)
 {
-	int count = 0, i;
+	int i;
 	u16 val;
 
+	timers = 0;
+
 	if (disable) {
-		printk(KERN_INFO "geode-mfgpt:  Skipping MFGPT setup\n");
-		return 0;
+		printk(KERN_INFO "geode-mfgpt:  MFGPT support is disabled\n");
+		goto done;
+	}
+
+	if (!geode_get_dev_base(GEODE_DEV_MFGPT)) {
+		printk(KERN_INFO "geode-mfgpt:  MFGPT LBAR is not set up\n");
+		goto done;
 	}
 
 	for (i = 0; i < MFGPT_MAX_TIMERS; i++) {
 		val = geode_mfgpt_read(i, MFGPT_REG_SETUP);
 		if (!(val & MFGPT_SETUP_SETUP)) {
-			mfgpt_timers[i].flags = F_AVAIL;
-			count++;
+			mfgpt_timers[i].avail = 1;
+			timers++;
 		}
 	}
 
-	/* set up clock event device, if desired */
-	i = mfgpt_timer_setup();
-
-	return count;
+done:
+	printk(KERN_INFO "geode-mfgpt:  %d MFGPT timers available.\n", timers);
 }
 
 int geode_mfgpt_toggle_event(int timer, int cmp, int event, int enable)
@@ -183,36 +181,41 @@ int geode_mfgpt_set_irq(int timer, int cmp, int irq, int enable)
 	return 0;
 }
 
-static int mfgpt_get(int timer, struct module *owner)
+static int mfgpt_get(int timer)
 {
-	mfgpt_timers[timer].flags &= ~F_AVAIL;
-	mfgpt_timers[timer].owner = owner;
+	mfgpt_timers[timer].avail = 0;
 	printk(KERN_INFO "geode-mfgpt:  Registered timer %d\n", timer);
 	return timer;
 }
 
-int geode_mfgpt_alloc_timer(int timer, int domain, struct module *owner)
+int geode_mfgpt_alloc_timer(int timer, int domain)
 {
 	int i;
 
-	if (!geode_get_dev_base(GEODE_DEV_MFGPT))
-		return -ENODEV;
+	if (timers == -1) {
+		/* timers haven't been detected yet */
+		geode_mfgpt_detect();
+	}
+
+	if (!timers)
+		return -1;
+
 	if (timer >= MFGPT_MAX_TIMERS)
-		return -EIO;
+		return -1;
 
 	if (timer < 0) {
 		/* Try to find an available timer */
 		for (i = 0; i < MFGPT_MAX_TIMERS; i++) {
-			if (mfgpt_timers[i].flags & F_AVAIL)
-				return mfgpt_get(i, owner);
+			if (mfgpt_timers[i].avail)
+				return mfgpt_get(i);
 
 			if (i == 5 && domain == MFGPT_DOMAIN_WORKING)
 				break;
 		}
 	} else {
 		/* If they requested a specific timer, try to honor that */
-		if (mfgpt_timers[timer].flags & F_AVAIL)
-			return mfgpt_get(timer, owner);
+		if (mfgpt_timers[timer].avail)
+			return mfgpt_get(timer);
 	}
 
 	/* No timers available - too bad */
@@ -244,10 +247,11 @@ static int __init mfgpt_setup(char *str)
 }
 __setup("mfgpt_irq=", mfgpt_setup);
 
-static inline void mfgpt_disable_timer(u16 clock)
+static void mfgpt_disable_timer(u16 clock)
 {
-	u16 val = geode_mfgpt_read(clock, MFGPT_REG_SETUP);
-	geode_mfgpt_write(clock, MFGPT_REG_SETUP, val & ~MFGPT_SETUP_CNTEN);
+	/* avoid races by clearing CMP1 and CMP2 unconditionally */
+	geode_mfgpt_write(clock, MFGPT_REG_SETUP, (u16) ~MFGPT_SETUP_CNTEN |
+			MFGPT_SETUP_CMP1 | MFGPT_SETUP_CMP2);
 }
 
 static int mfgpt_next_event(unsigned long, struct clock_event_device *);
@@ -263,7 +267,7 @@ static struct clock_event_device mfgpt_clockevent = {
 	.shift = 32
 };
 
-static inline void mfgpt_start_timer(u16 clock, u16 delta)
+static void mfgpt_start_timer(u16 delta)
 {
 	geode_mfgpt_write(mfgpt_event_clock, MFGPT_REG_CMP2, (u16) delta);
 	geode_mfgpt_write(mfgpt_event_clock, MFGPT_REG_COUNTER, 0);
@@ -278,21 +282,25 @@ static void mfgpt_set_mode(enum clock_event_mode mode,
 	mfgpt_disable_timer(mfgpt_event_clock);
 
 	if (mode == CLOCK_EVT_MODE_PERIODIC)
-		mfgpt_start_timer(mfgpt_event_clock, MFGPT_PERIODIC);
+		mfgpt_start_timer(MFGPT_PERIODIC);
 
 	mfgpt_tick_mode = mode;
 }
 
 static int mfgpt_next_event(unsigned long delta, struct clock_event_device *evt)
 {
-	mfgpt_start_timer(mfgpt_event_clock, delta);
+	mfgpt_start_timer(delta);
 	return 0;
 }
 
-/* Assume (foolishly?), that this interrupt was due to our tick */
-
 static irqreturn_t mfgpt_tick(int irq, void *dev_id)
 {
+	u16 val = geode_mfgpt_read(mfgpt_event_clock, MFGPT_REG_SETUP);
+
+	/* See if the interrupt was for us */
+	if (!(val & (MFGPT_SETUP_SETUP  | MFGPT_SETUP_CMP2 | MFGPT_SETUP_CMP1)))
+		return IRQ_NONE;
+
 	/* Turn off the clock (and clear the event) */
 	mfgpt_disable_timer(mfgpt_event_clock);
 
@@ -320,13 +328,12 @@ static struct irqaction mfgptirq  = {
 	.name = "mfgpt-timer"
 };
 
-static int __init mfgpt_timer_setup(void)
+int __init mfgpt_timer_setup(void)
 {
 	int timer, ret;
 	u16 val;
 
-	timer = geode_mfgpt_alloc_timer(MFGPT_TIMER_ANY, MFGPT_DOMAIN_WORKING,
-			THIS_MODULE);
+	timer = geode_mfgpt_alloc_timer(MFGPT_TIMER_ANY, MFGPT_DOMAIN_WORKING);
 	if (timer < 0) {
 		printk(KERN_ERR
 		       "mfgpt-timer:  Could not allocate a MFPGT timer\n");
@@ -363,7 +370,7 @@ static int __init mfgpt_timer_setup(void)
 			&mfgpt_clockevent);
 
 	printk(KERN_INFO
-	       "mfgpt-timer:  registering the MFGT timer as a clock event.\n");
+	       "mfgpt-timer:  registering the MFGPT timer as a clock event.\n");
 	clockevents_register_device(&mfgpt_clockevent);
 
 	return 0;
diff --git a/arch/x86/kernel/mpparse_32.c b/arch/x86/kernel/mpparse_32.c
index 67009cdd5eca..f349e68e45a0 100644
--- a/arch/x86/kernel/mpparse_32.c
+++ b/arch/x86/kernel/mpparse_32.c
@@ -736,7 +736,8 @@ static int __init smp_scan_config (unsigned long base, unsigned long length)
 			smp_found_config = 1;
 			printk(KERN_INFO "found SMP MP-table at [%p] %08lx\n",
 				mpf, virt_to_phys(mpf));
-			reserve_bootmem(virt_to_phys(mpf), PAGE_SIZE);
+			reserve_bootmem(virt_to_phys(mpf), PAGE_SIZE,
+					BOOTMEM_DEFAULT);
 			if (mpf->mpf_physptr) {
 				/*
 				 * We cannot access to MPC table to compute
@@ -751,7 +752,8 @@ static int __init smp_scan_config (unsigned long base, unsigned long length)
 				unsigned long end = max_low_pfn * PAGE_SIZE;
 				if (mpf->mpf_physptr + size > end)
 					size = end - mpf->mpf_physptr;
-				reserve_bootmem(mpf->mpf_physptr, size);
+				reserve_bootmem(mpf->mpf_physptr, size,
+						BOOTMEM_DEFAULT);
 			}
 
 			mpf_found = mpf;
diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c
index 1fe7f043ebde..1b5464c2434f 100644
--- a/arch/x86/kernel/pci-calgary_64.c
+++ b/arch/x86/kernel/pci-calgary_64.c
@@ -35,6 +35,7 @@
 #include <linux/pci.h>
 #include <linux/delay.h>
 #include <linux/scatterlist.h>
+#include <linux/iommu-helper.h>
 #include <asm/gart.h>
 #include <asm/calgary.h>
 #include <asm/tce.h>
@@ -260,22 +261,28 @@ static void iommu_range_reserve(struct iommu_table *tbl,
 	spin_unlock_irqrestore(&tbl->it_lock, flags);
 }
 
-static unsigned long iommu_range_alloc(struct iommu_table *tbl,
-	unsigned int npages)
+static unsigned long iommu_range_alloc(struct device *dev,
+				       struct iommu_table *tbl,
+				       unsigned int npages)
 {
 	unsigned long flags;
 	unsigned long offset;
+	unsigned long boundary_size;
+
+	boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1,
+			      PAGE_SIZE) >> PAGE_SHIFT;
 
 	BUG_ON(npages == 0);
 
 	spin_lock_irqsave(&tbl->it_lock, flags);
 
-	offset = find_next_zero_string(tbl->it_map, tbl->it_hint,
-				       tbl->it_size, npages);
+	offset = iommu_area_alloc(tbl->it_map, tbl->it_size, tbl->it_hint,
+				  npages, 0, boundary_size, 0);
 	if (offset == ~0UL) {
 		tbl->chip_ops->tce_cache_blast(tbl);
-		offset = find_next_zero_string(tbl->it_map, 0,
-					       tbl->it_size, npages);
+
+		offset = iommu_area_alloc(tbl->it_map, tbl->it_size, 0,
+					  npages, 0, boundary_size, 0);
 		if (offset == ~0UL) {
 			printk(KERN_WARNING "Calgary: IOMMU full.\n");
 			spin_unlock_irqrestore(&tbl->it_lock, flags);
@@ -286,7 +293,6 @@ static unsigned long iommu_range_alloc(struct iommu_table *tbl,
 		}
 	}
 
-	set_bit_string(tbl->it_map, offset, npages);
 	tbl->it_hint = offset + npages;
 	BUG_ON(tbl->it_hint > tbl->it_size);
 
@@ -295,13 +301,13 @@ static unsigned long iommu_range_alloc(struct iommu_table *tbl,
 	return offset;
 }
 
-static dma_addr_t iommu_alloc(struct iommu_table *tbl, void *vaddr,
-	unsigned int npages, int direction)
+static dma_addr_t iommu_alloc(struct device *dev, struct iommu_table *tbl,
+			      void *vaddr, unsigned int npages, int direction)
 {
 	unsigned long entry;
 	dma_addr_t ret = bad_dma_address;
 
-	entry = iommu_range_alloc(tbl, npages);
+	entry = iommu_range_alloc(dev, tbl, npages);
 
 	if (unlikely(entry == bad_dma_address))
 		goto error;
@@ -354,7 +360,7 @@ static void iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr,
 			       badbit, tbl, dma_addr, entry, npages);
 	}
 
-	__clear_bit_string(tbl->it_map, entry, npages);
+	iommu_area_free(tbl->it_map, entry, npages);
 
 	spin_unlock_irqrestore(&tbl->it_lock, flags);
 }
@@ -438,7 +444,7 @@ static int calgary_map_sg(struct device *dev, struct scatterlist *sg,
 		vaddr = (unsigned long) sg_virt(s);
 		npages = num_dma_pages(vaddr, s->length);
 
-		entry = iommu_range_alloc(tbl, npages);
+		entry = iommu_range_alloc(dev, tbl, npages);
 		if (entry == bad_dma_address) {
 			/* makes sure unmap knows to stop */
 			s->dma_length = 0;
@@ -476,7 +482,7 @@ static dma_addr_t calgary_map_single(struct device *dev, void *vaddr,
 	npages = num_dma_pages(uaddr, size);
 
 	if (translation_enabled(tbl))
-		dma_handle = iommu_alloc(tbl, vaddr, npages, direction);
+		dma_handle = iommu_alloc(dev, tbl, vaddr, npages, direction);
 	else
 		dma_handle = virt_to_bus(vaddr);
 
@@ -516,7 +522,7 @@ static void* calgary_alloc_coherent(struct device *dev, size_t size,
 
 	if (translation_enabled(tbl)) {
 		/* set up tces to cover the allocated range */
-		mapping = iommu_alloc(tbl, ret, npages, DMA_BIDIRECTIONAL);
+		mapping = iommu_alloc(dev, tbl, ret, npages, DMA_BIDIRECTIONAL);
 		if (mapping == bad_dma_address)
 			goto free;
 
diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index 845cbecd68e9..faf3229f8fb3 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -25,6 +25,7 @@
 #include <linux/bitops.h>
 #include <linux/kdebug.h>
 #include <linux/scatterlist.h>
+#include <linux/iommu-helper.h>
 #include <asm/atomic.h>
 #include <asm/io.h>
 #include <asm/mtrr.h>
@@ -82,17 +83,24 @@ AGPEXTERN __u32 *agp_gatt_table;
 static unsigned long next_bit;  /* protected by iommu_bitmap_lock */
 static int need_flush;		/* global flush state. set for each gart wrap */
 
-static unsigned long alloc_iommu(int size)
+static unsigned long alloc_iommu(struct device *dev, int size)
 {
 	unsigned long offset, flags;
+	unsigned long boundary_size;
+	unsigned long base_index;
+
+	base_index = ALIGN(iommu_bus_base & dma_get_seg_boundary(dev),
+			   PAGE_SIZE) >> PAGE_SHIFT;
+	boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1,
+			      PAGE_SIZE) >> PAGE_SHIFT;
 
 	spin_lock_irqsave(&iommu_bitmap_lock, flags);
-	offset = find_next_zero_string(iommu_gart_bitmap, next_bit,
-					iommu_pages, size);
+	offset = iommu_area_alloc(iommu_gart_bitmap, iommu_pages, next_bit,
+				  size, base_index, boundary_size, 0);
 	if (offset == -1) {
 		need_flush = 1;
-		offset = find_next_zero_string(iommu_gart_bitmap, 0,
-						iommu_pages, size);
+		offset = iommu_area_alloc(iommu_gart_bitmap, iommu_pages, 0,
+					  size, base_index, boundary_size, 0);
 	}
 	if (offset != -1) {
 		set_bit_string(iommu_gart_bitmap, offset, size);
@@ -114,7 +122,7 @@ static void free_iommu(unsigned long offset, int size)
 	unsigned long flags;
 
 	spin_lock_irqsave(&iommu_bitmap_lock, flags);
-	__clear_bit_string(iommu_gart_bitmap, offset, size);
+	iommu_area_free(iommu_gart_bitmap, offset, size);
 	spin_unlock_irqrestore(&iommu_bitmap_lock, flags);
 }
 
@@ -235,7 +243,7 @@ static dma_addr_t dma_map_area(struct device *dev, dma_addr_t phys_mem,
 				size_t size, int dir)
 {
 	unsigned long npages = to_pages(phys_mem, size);
-	unsigned long iommu_page = alloc_iommu(npages);
+	unsigned long iommu_page = alloc_iommu(dev, npages);
 	int i;
 
 	if (iommu_page == -1) {
@@ -355,10 +363,11 @@ static int dma_map_sg_nonforce(struct device *dev, struct scatterlist *sg,
 }
 
 /* Map multiple scatterlist entries continuous into the first. */
-static int __dma_map_cont(struct scatterlist *start, int nelems,
-			  struct scatterlist *sout, unsigned long pages)
+static int __dma_map_cont(struct device *dev, struct scatterlist *start,
+			  int nelems, struct scatterlist *sout,
+			  unsigned long pages)
 {
-	unsigned long iommu_start = alloc_iommu(pages);
+	unsigned long iommu_start = alloc_iommu(dev, pages);
 	unsigned long iommu_page = iommu_start;
 	struct scatterlist *s;
 	int i;
@@ -394,8 +403,8 @@ static int __dma_map_cont(struct scatterlist *start, int nelems,
 }
 
 static inline int
-dma_map_cont(struct scatterlist *start, int nelems, struct scatterlist *sout,
-	     unsigned long pages, int need)
+dma_map_cont(struct device *dev, struct scatterlist *start, int nelems,
+	     struct scatterlist *sout, unsigned long pages, int need)
 {
 	if (!need) {
 		BUG_ON(nelems != 1);
@@ -403,7 +412,7 @@ dma_map_cont(struct scatterlist *start, int nelems, struct scatterlist *sout,
 		sout->dma_length = start->length;
 		return 0;
 	}
-	return __dma_map_cont(start, nelems, sout, pages);
+	return __dma_map_cont(dev, start, nelems, sout, pages);
 }
 
 /*
@@ -416,6 +425,8 @@ gart_map_sg(struct device *dev, struct scatterlist *sg, int nents, int dir)
 	struct scatterlist *s, *ps, *start_sg, *sgmap;
 	int need = 0, nextneed, i, out, start;
 	unsigned long pages = 0;
+	unsigned int seg_size;
+	unsigned int max_seg_size;
 
 	if (nents == 0)
 		return 0;
@@ -426,6 +437,8 @@ gart_map_sg(struct device *dev, struct scatterlist *sg, int nents, int dir)
 	out = 0;
 	start = 0;
 	start_sg = sgmap = sg;
+	seg_size = 0;
+	max_seg_size = dma_get_max_seg_size(dev);
 	ps = NULL; /* shut up gcc */
 	for_each_sg(sg, s, nents, i) {
 		dma_addr_t addr = sg_phys(s);
@@ -443,11 +456,13 @@ gart_map_sg(struct device *dev, struct scatterlist *sg, int nents, int dir)
 			 * offset.
 			 */
 			if (!iommu_merge || !nextneed || !need || s->offset ||
+			    (s->length + seg_size > max_seg_size) ||
 			    (ps->offset + ps->length) % PAGE_SIZE) {
-				if (dma_map_cont(start_sg, i - start, sgmap,
-						  pages, need) < 0)
+				if (dma_map_cont(dev, start_sg, i - start,
+						 sgmap, pages, need) < 0)
 					goto error;
 				out++;
+				seg_size = 0;
 				sgmap = sg_next(sgmap);
 				pages = 0;
 				start = i;
@@ -455,11 +470,12 @@ gart_map_sg(struct device *dev, struct scatterlist *sg, int nents, int dir)
 			}
 		}
 
+		seg_size += s->length;
 		need = nextneed;
 		pages += to_pages(s->offset, s->length);
 		ps = s;
 	}
-	if (dma_map_cont(start_sg, i - start, sgmap, pages, need) < 0)
+	if (dma_map_cont(dev, start_sg, i - start, sgmap, pages, need) < 0)
 		goto error;
 	out++;
 	flush_gart();
@@ -733,6 +749,15 @@ void __init gart_iommu_init(void)
 	 */
 	set_memory_np((unsigned long)__va(iommu_bus_base),
 				iommu_size >> PAGE_SHIFT);
+	/*
+	 * Tricky. The GART table remaps the physical memory range,
+	 * so the CPU wont notice potential aliases and if the memory
+	 * is remapped to UC later on, we might surprise the PCI devices
+	 * with a stray writeout of a cacheline. So play it sure and
+	 * do an explicit, full-scale wbinvd() _after_ having marked all
+	 * the pages as Not-Present:
+	 */
+	wbinvd();
 
 	/*
 	 * Try to workaround a bug (thanks to BenH)
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index dabdbeff1f77..a7d50a547dc2 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -23,7 +23,6 @@
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/user.h>
-#include <linux/a.out.h>
 #include <linux/interrupt.h>
 #include <linux/utsname.h>
 #include <linux/delay.h>
@@ -539,55 +538,6 @@ int copy_thread(int nr, unsigned long clone_flags, unsigned long sp,
 	return err;
 }
 
-/*
- * fill in the user structure for a core dump..
- */
-void dump_thread(struct pt_regs * regs, struct user * dump)
-{
-	u16 gs;
-
-/* changed the size calculations - should hopefully work better. lbt */
-	dump->magic = CMAGIC;
-	dump->start_code = 0;
-	dump->start_stack = regs->sp & ~(PAGE_SIZE - 1);
-	dump->u_tsize = ((unsigned long) current->mm->end_code) >> PAGE_SHIFT;
-	dump->u_dsize = ((unsigned long) (current->mm->brk + (PAGE_SIZE-1))) >> PAGE_SHIFT;
-	dump->u_dsize -= dump->u_tsize;
-	dump->u_ssize = 0;
-	dump->u_debugreg[0] = current->thread.debugreg0;
-	dump->u_debugreg[1] = current->thread.debugreg1;
-	dump->u_debugreg[2] = current->thread.debugreg2;
-	dump->u_debugreg[3] = current->thread.debugreg3;
-	dump->u_debugreg[4] = 0;
-	dump->u_debugreg[5] = 0;
-	dump->u_debugreg[6] = current->thread.debugreg6;
-	dump->u_debugreg[7] = current->thread.debugreg7;
-
-	if (dump->start_stack < TASK_SIZE)
-		dump->u_ssize = ((unsigned long) (TASK_SIZE - dump->start_stack)) >> PAGE_SHIFT;
-
-	dump->regs.bx = regs->bx;
-	dump->regs.cx = regs->cx;
-	dump->regs.dx = regs->dx;
-	dump->regs.si = regs->si;
-	dump->regs.di = regs->di;
-	dump->regs.bp = regs->bp;
-	dump->regs.ax = regs->ax;
-	dump->regs.ds = (u16)regs->ds;
-	dump->regs.es = (u16)regs->es;
-	dump->regs.fs = (u16)regs->fs;
-	savesegment(gs,gs);
-	dump->regs.orig_ax = regs->orig_ax;
-	dump->regs.ip = regs->ip;
-	dump->regs.cs = (u16)regs->cs;
-	dump->regs.flags = regs->flags;
-	dump->regs.sp = regs->sp;
-	dump->regs.ss = (u16)regs->ss;
-
-	dump->u_fpvalid = dump_fpu (regs, &dump->i387);
-}
-EXPORT_SYMBOL(dump_thread);
-
 #ifdef CONFIG_SECCOMP
 static void hard_disable_TSC(void)
 {
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 137a86171c39..b0cc8f0136d8 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -26,7 +26,6 @@
 #include <linux/smp.h>
 #include <linux/slab.h>
 #include <linux/user.h>
-#include <linux/a.out.h>
 #include <linux/interrupt.h>
 #include <linux/utsname.h>
 #include <linux/delay.h>
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 96286df1bb81..702c33efea84 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -103,9 +103,26 @@ static int set_segment_reg(struct task_struct *task,
 	if (invalid_selector(value))
 		return -EIO;
 
-	if (offset != offsetof(struct user_regs_struct, gs))
+	/*
+	 * For %cs and %ss we cannot permit a null selector.
+	 * We can permit a bogus selector as long as it has USER_RPL.
+	 * Null selectors are fine for other segment registers, but
+	 * we will never get back to user mode with invalid %cs or %ss
+	 * and will take the trap in iret instead.  Much code relies
+	 * on user_mode() to distinguish a user trap frame (which can
+	 * safely use invalid selectors) from a kernel trap frame.
+	 */
+	switch (offset) {
+	case offsetof(struct user_regs_struct, cs):
+	case offsetof(struct user_regs_struct, ss):
+		if (unlikely(value == 0))
+			return -EIO;
+
+	default:
 		*pt_regs_access(task_pt_regs(task), offset) = value;
-	else {
+		break;
+
+	case offsetof(struct user_regs_struct, gs):
 		task->thread.gs = value;
 		if (task == current)
 			/*
@@ -227,12 +244,16 @@ static int set_segment_reg(struct task_struct *task,
 		 * Can't actually change these in 64-bit mode.
 		 */
 	case offsetof(struct user_regs_struct,cs):
+		if (unlikely(value == 0))
+			return -EIO;
 #ifdef CONFIG_IA32_EMULATION
 		if (test_tsk_thread_flag(task, TIF_IA32))
 			task_pt_regs(task)->cs = value;
 #endif
 		break;
 	case offsetof(struct user_regs_struct,ss):
+		if (unlikely(value == 0))
+			return -EIO;
 #ifdef CONFIG_IA32_EMULATION
 		if (test_tsk_thread_flag(task, TIF_IA32))
 			task_pt_regs(task)->ss = value;
diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c
index 3cd7a2dcd4fe..c47208fc5932 100644
--- a/arch/x86/kernel/quirks.c
+++ b/arch/x86/kernel/quirks.c
@@ -11,7 +11,7 @@
 static void __devinit quirk_intel_irqbalance(struct pci_dev *dev)
 {
 	u8 config, rev;
-	u32 word;
+	u16 word;
 
 	/* BIOS may enable hardware IRQ balancing for
 	 * E7520/E7320/E7525(revision ID 0x9 and below)
@@ -26,8 +26,11 @@ static void __devinit quirk_intel_irqbalance(struct pci_dev *dev)
 	pci_read_config_byte(dev, 0xf4, &config);
 	pci_write_config_byte(dev, 0xf4, config|0x2);
 
-	/* read xTPR register */
-	raw_pci_ops->read(0, 0, 0x40, 0x4c, 2, &word);
+	/*
+	 * read xTPR register.  We may not have a pci_dev for device 8
+	 * because it might be hidden until the above write.
+	 */
+	pci_bus_read_config_word(dev->bus, PCI_DEVFN(8, 0), 0x4c, &word);
 
 	if (!(word & (1 << 13))) {
 		dev_info(&dev->dev, "Intel E7520/7320/7525 detected; "
@@ -380,19 +383,19 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NVIDIA, 0x0367,
 void force_hpet_resume(void)
 {
 	switch (force_hpet_resume_type) {
-	    case ICH_FORCE_HPET_RESUME:
-		return ich_force_hpet_resume();
-
-	    case OLD_ICH_FORCE_HPET_RESUME:
-		return old_ich_force_hpet_resume();
-
-	    case VT8237_FORCE_HPET_RESUME:
-		return vt8237_force_hpet_resume();
-
-	    case NVIDIA_FORCE_HPET_RESUME:
-		return nvidia_force_hpet_resume();
-
-	    default:
+	case ICH_FORCE_HPET_RESUME:
+		ich_force_hpet_resume();
+		return;
+	case OLD_ICH_FORCE_HPET_RESUME:
+		old_ich_force_hpet_resume();
+		return;
+	case VT8237_FORCE_HPET_RESUME:
+		vt8237_force_hpet_resume();
+		return;
+	case NVIDIA_FORCE_HPET_RESUME:
+		nvidia_force_hpet_resume();
+		return;
+	default:
 		break;
 	}
 }
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 5818dc28167d..7fd6ac43e4a1 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -326,7 +326,7 @@ static inline void kb_wait(void)
 	}
 }
 
-void machine_emergency_restart(void)
+static void native_machine_emergency_restart(void)
 {
 	int i;
 
@@ -376,7 +376,7 @@ void machine_emergency_restart(void)
 	}
 }
 
-void machine_shutdown(void)
+static void native_machine_shutdown(void)
 {
 	/* Stop the cpus and apics */
 #ifdef CONFIG_SMP
@@ -420,7 +420,7 @@ void machine_shutdown(void)
 #endif
 }
 
-void machine_restart(char *__unused)
+static void native_machine_restart(char *__unused)
 {
 	printk("machine restart\n");
 
@@ -429,11 +429,11 @@ void machine_restart(char *__unused)
 	machine_emergency_restart();
 }
 
-void machine_halt(void)
+static void native_machine_halt(void)
 {
 }
 
-void machine_power_off(void)
+static void native_machine_power_off(void)
 {
 	if (pm_power_off) {
 		if (!reboot_force)
@@ -443,9 +443,35 @@ void machine_power_off(void)
 }
 
 struct machine_ops machine_ops = {
-	.power_off = machine_power_off,
-	.shutdown = machine_shutdown,
-	.emergency_restart = machine_emergency_restart,
-	.restart = machine_restart,
-	.halt = machine_halt
+	.power_off = native_machine_power_off,
+	.shutdown = native_machine_shutdown,
+	.emergency_restart = native_machine_emergency_restart,
+	.restart = native_machine_restart,
+	.halt = native_machine_halt
 };
+
+void machine_power_off(void)
+{
+	machine_ops.power_off();
+}
+
+void machine_shutdown(void)
+{
+	machine_ops.shutdown();
+}
+
+void machine_emergency_restart(void)
+{
+	machine_ops.emergency_restart();
+}
+
+void machine_restart(char *cmd)
+{
+	machine_ops.restart(cmd);
+}
+
+void machine_halt(void)
+{
+	machine_ops.halt();
+}
+
diff --git a/arch/x86/kernel/setup_32.c b/arch/x86/kernel/setup_32.c
index 62adc5f20be5..691ab4cb167b 100644
--- a/arch/x86/kernel/setup_32.c
+++ b/arch/x86/kernel/setup_32.c
@@ -154,7 +154,11 @@ struct cpuinfo_x86 new_cpu_data __cpuinitdata = { 0, 0, 0, 0, -1, 1, 0, 0, -1 };
 struct cpuinfo_x86 boot_cpu_data __read_mostly = { 0, 0, 0, 0, -1, 1, 0, 0, -1 };
 EXPORT_SYMBOL(boot_cpu_data);
 
+#ifndef CONFIG_X86_PAE
 unsigned long mmu_cr4_features;
+#else
+unsigned long mmu_cr4_features = X86_CR4_PAE;
+#endif
 
 /* for MCA, but anyone else can use it if they want */
 unsigned int machine_id;
@@ -390,7 +394,7 @@ static void __init reserve_ebda_region(void)
 	unsigned int addr;
 	addr = get_bios_ebda();
 	if (addr)
-		reserve_bootmem(addr, PAGE_SIZE);
+		reserve_bootmem(addr, PAGE_SIZE, BOOTMEM_DEFAULT);
 }
 
 #ifndef CONFIG_NEED_MULTIPLE_NODES
@@ -484,7 +488,8 @@ static void __init reserve_crashkernel(void)
 					(unsigned long)(total_mem >> 20));
 			crashk_res.start = crash_base;
 			crashk_res.end   = crash_base + crash_size - 1;
-			reserve_bootmem(crash_base, crash_size);
+			reserve_bootmem(crash_base, crash_size,
+					BOOTMEM_DEFAULT);
 		} else
 			printk(KERN_INFO "crashkernel reservation failed - "
 					"you have to specify a base address\n");
@@ -525,7 +530,7 @@ static void __init reserve_initrd(void)
 	}
 	if (ramdisk_end <= end_of_lowmem) {
 		/* All in lowmem, easy case */
-		reserve_bootmem(ramdisk_image, ramdisk_size);
+		reserve_bootmem(ramdisk_image, ramdisk_size, BOOTMEM_DEFAULT);
 		initrd_start = ramdisk_image + PAGE_OFFSET;
 		initrd_end = initrd_start+ramdisk_size;
 		return;
@@ -536,7 +541,7 @@ static void __init reserve_initrd(void)
 
 	/* Note: this includes all the lowmem currently occupied by
 	   the initrd, we rely on that fact to keep the data intact. */
-	reserve_bootmem(ramdisk_here, ramdisk_size);
+	reserve_bootmem(ramdisk_here, ramdisk_size, BOOTMEM_DEFAULT);
 	initrd_start = ramdisk_here + PAGE_OFFSET;
 	initrd_end   = initrd_start + ramdisk_size;
 
@@ -606,13 +611,14 @@ void __init setup_bootmem_allocator(void)
 	 * bootmem allocator with an invalid RAM area.
 	 */
 	reserve_bootmem(__pa_symbol(_text), (PFN_PHYS(min_low_pfn) +
-			 bootmap_size + PAGE_SIZE-1) - __pa_symbol(_text));
+			 bootmap_size + PAGE_SIZE-1) - __pa_symbol(_text),
+			 BOOTMEM_DEFAULT);
 
 	/*
 	 * reserve physical page 0 - it's a special BIOS page on many boxes,
 	 * enabling clean reboots, SMP operation, laptop functions.
 	 */
-	reserve_bootmem(0, PAGE_SIZE);
+	reserve_bootmem(0, PAGE_SIZE, BOOTMEM_DEFAULT);
 
 	/* reserve EBDA region, it's a 4K region */
 	reserve_ebda_region();
@@ -622,7 +628,7 @@ void __init setup_bootmem_allocator(void)
        unless you have no PS/2 mouse plugged in. */
 	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD &&
 	    boot_cpu_data.x86 == 6)
-	     reserve_bootmem(0xa0000 - 4096, 4096);
+	     reserve_bootmem(0xa0000 - 4096, 4096, BOOTMEM_DEFAULT);
 
 #ifdef CONFIG_SMP
 	/*
@@ -630,7 +636,7 @@ void __init setup_bootmem_allocator(void)
 	 * FIXME: Don't need the extra page at 4K, but need to fix
 	 * trampoline before removing it. (see the GDT stuff)
 	 */
-	reserve_bootmem(PAGE_SIZE, PAGE_SIZE);
+	reserve_bootmem(PAGE_SIZE, PAGE_SIZE, BOOTMEM_DEFAULT);
 #endif
 #ifdef CONFIG_ACPI_SLEEP
 	/*
diff --git a/arch/x86/kernel/setup_64.c b/arch/x86/kernel/setup_64.c
index c8939dfddfba..c0d8208af12a 100644
--- a/arch/x86/kernel/setup_64.c
+++ b/arch/x86/kernel/setup_64.c
@@ -15,7 +15,6 @@
 #include <linux/ptrace.h>
 #include <linux/slab.h>
 #include <linux/user.h>
-#include <linux/a.out.h>
 #include <linux/screen_info.h>
 #include <linux/ioport.h>
 #include <linux/delay.h>
@@ -189,7 +188,7 @@ contig_initmem_init(unsigned long start_pfn, unsigned long end_pfn)
 	bootmap_size = init_bootmem(bootmap >> PAGE_SHIFT, end_pfn);
 	e820_register_active_regions(0, start_pfn, end_pfn);
 	free_bootmem_with_active_regions(0, end_pfn);
-	reserve_bootmem(bootmap, bootmap_size);
+	reserve_bootmem(bootmap, bootmap_size, BOOTMEM_DEFAULT);
 }
 #endif
 
@@ -220,28 +219,35 @@ static inline void copy_edd(void)
 #ifdef CONFIG_KEXEC
 static void __init reserve_crashkernel(void)
 {
-	unsigned long long free_mem;
+	unsigned long long total_mem;
 	unsigned long long crash_size, crash_base;
 	int ret;
 
-	free_mem =
-		((unsigned long long)max_low_pfn - min_low_pfn) << PAGE_SHIFT;
+	total_mem = ((unsigned long long)max_low_pfn - min_low_pfn) << PAGE_SHIFT;
 
-	ret = parse_crashkernel(boot_command_line, free_mem,
+	ret = parse_crashkernel(boot_command_line, total_mem,
 			&crash_size, &crash_base);
 	if (ret == 0 && crash_size) {
-		if (crash_base > 0) {
-			printk(KERN_INFO "Reserving %ldMB of memory at %ldMB "
-					"for crashkernel (System RAM: %ldMB)\n",
-					(unsigned long)(crash_size >> 20),
-					(unsigned long)(crash_base >> 20),
-					(unsigned long)(free_mem >> 20));
-			crashk_res.start = crash_base;
-			crashk_res.end   = crash_base + crash_size - 1;
-			reserve_bootmem(crash_base, crash_size);
-		} else
+		if (crash_base <= 0) {
 			printk(KERN_INFO "crashkernel reservation failed - "
 					"you have to specify a base address\n");
+			return;
+		}
+
+		if (reserve_bootmem(crash_base, crash_size,
+					BOOTMEM_EXCLUSIVE) < 0) {
+			printk(KERN_INFO "crashkernel reservation failed - "
+					"memory is in use\n");
+			return;
+		}
+
+		printk(KERN_INFO "Reserving %ldMB of memory at %ldMB "
+				"for crashkernel (System RAM: %ldMB)\n",
+				(unsigned long)(crash_size >> 20),
+				(unsigned long)(crash_base >> 20),
+				(unsigned long)(total_mem >> 20));
+		crashk_res.start = crash_base;
+		crashk_res.end   = crash_base + crash_size - 1;
 	}
 }
 #else
diff --git a/arch/x86/kernel/smpboot_32.c b/arch/x86/kernel/smpboot_32.c
index 5787a0c3e296..579b9b740c7c 100644
--- a/arch/x86/kernel/smpboot_32.c
+++ b/arch/x86/kernel/smpboot_32.c
@@ -202,8 +202,6 @@ valid_k7:
 	;
 }
 
-extern void calibrate_delay(void);
-
 static atomic_t init_deasserted;
 
 static void __cpuinit smp_callin(void)
diff --git a/arch/x86/kernel/srat_32.c b/arch/x86/kernel/srat_32.c
index 2bf6903cb444..b72e61359c36 100644
--- a/arch/x86/kernel/srat_32.c
+++ b/arch/x86/kernel/srat_32.c
@@ -274,7 +274,7 @@ int __init get_memcfg_from_srat(void)
 	int tables = 0;
 	int i = 0;
 
-	rsdp_address = acpi_find_rsdp();
+	rsdp_address = acpi_os_get_root_pointer();
 	if (!rsdp_address) {
 		printk("%s: System description tables not found\n",
 		       __FUNCTION__);
diff --git a/arch/x86/kernel/suspend_64.c b/arch/x86/kernel/suspend_64.c
deleted file mode 100644
index 7ac7130022f1..000000000000
--- a/arch/x86/kernel/suspend_64.c
+++ /dev/null
@@ -1,320 +0,0 @@
-/*
- * Suspend support specific for i386.
- *
- * Distribute under GPLv2
- *
- * Copyright (c) 2002 Pavel Machek <pavel@suse.cz>
- * Copyright (c) 2001 Patrick Mochel <mochel@osdl.org>
- */
-
-#include <linux/smp.h>
-#include <linux/suspend.h>
-#include <asm/proto.h>
-#include <asm/page.h>
-#include <asm/pgtable.h>
-#include <asm/mtrr.h>
-
-/* References to section boundaries */
-extern const void __nosave_begin, __nosave_end;
-
-static void fix_processor_context(void);
-
-struct saved_context saved_context;
-
-/**
- *	__save_processor_state - save CPU registers before creating a
- *		hibernation image and before restoring the memory state from it
- *	@ctxt - structure to store the registers contents in
- *
- *	NOTE: If there is a CPU register the modification of which by the
- *	boot kernel (ie. the kernel used for loading the hibernation image)
- *	might affect the operations of the restored target kernel (ie. the one
- *	saved in the hibernation image), then its contents must be saved by this
- *	function.  In other words, if kernel A is hibernated and different
- *	kernel B is used for loading the hibernation image into memory, the
- *	kernel A's __save_processor_state() function must save all registers
- *	needed by kernel A, so that it can operate correctly after the resume
- *	regardless of what kernel B does in the meantime.
- */
-static void __save_processor_state(struct saved_context *ctxt)
-{
-	kernel_fpu_begin();
-
-	/*
-	 * descriptor tables
-	 */
-	store_gdt((struct desc_ptr *)&ctxt->gdt_limit);
-	store_idt((struct desc_ptr *)&ctxt->idt_limit);
-	store_tr(ctxt->tr);
-
-	/* XMM0..XMM15 should be handled by kernel_fpu_begin(). */
-	/*
-	 * segment registers
-	 */
-	asm volatile ("movw %%ds, %0" : "=m" (ctxt->ds));
-	asm volatile ("movw %%es, %0" : "=m" (ctxt->es));
-	asm volatile ("movw %%fs, %0" : "=m" (ctxt->fs));
-	asm volatile ("movw %%gs, %0" : "=m" (ctxt->gs));
-	asm volatile ("movw %%ss, %0" : "=m" (ctxt->ss));
-
-	rdmsrl(MSR_FS_BASE, ctxt->fs_base);
-	rdmsrl(MSR_GS_BASE, ctxt->gs_base);
-	rdmsrl(MSR_KERNEL_GS_BASE, ctxt->gs_kernel_base);
-	mtrr_save_fixed_ranges(NULL);
-
-	/*
-	 * control registers 
-	 */
-	rdmsrl(MSR_EFER, ctxt->efer);
-	ctxt->cr0 = read_cr0();
-	ctxt->cr2 = read_cr2();
-	ctxt->cr3 = read_cr3();
-	ctxt->cr4 = read_cr4();
-	ctxt->cr8 = read_cr8();
-}
-
-void save_processor_state(void)
-{
-	__save_processor_state(&saved_context);
-}
-
-static void do_fpu_end(void)
-{
-	/*
-	 * Restore FPU regs if necessary
-	 */
-	kernel_fpu_end();
-}
-
-/**
- *	__restore_processor_state - restore the contents of CPU registers saved
- *		by __save_processor_state()
- *	@ctxt - structure to load the registers contents from
- */
-static void __restore_processor_state(struct saved_context *ctxt)
-{
-	/*
-	 * control registers
-	 */
-	wrmsrl(MSR_EFER, ctxt->efer);
-	write_cr8(ctxt->cr8);
-	write_cr4(ctxt->cr4);
-	write_cr3(ctxt->cr3);
-	write_cr2(ctxt->cr2);
-	write_cr0(ctxt->cr0);
-
-	/*
-	 * now restore the descriptor tables to their proper values
-	 * ltr is done i fix_processor_context().
-	 */
-	load_gdt((const struct desc_ptr *)&ctxt->gdt_limit);
-	load_idt((const struct desc_ptr *)&ctxt->idt_limit);
-
-
-	/*
-	 * segment registers
-	 */
-	asm volatile ("movw %0, %%ds" :: "r" (ctxt->ds));
-	asm volatile ("movw %0, %%es" :: "r" (ctxt->es));
-	asm volatile ("movw %0, %%fs" :: "r" (ctxt->fs));
-	load_gs_index(ctxt->gs);
-	asm volatile ("movw %0, %%ss" :: "r" (ctxt->ss));
-
-	wrmsrl(MSR_FS_BASE, ctxt->fs_base);
-	wrmsrl(MSR_GS_BASE, ctxt->gs_base);
-	wrmsrl(MSR_KERNEL_GS_BASE, ctxt->gs_kernel_base);
-
-	fix_processor_context();
-
-	do_fpu_end();
-	mtrr_ap_init();
-}
-
-void restore_processor_state(void)
-{
-	__restore_processor_state(&saved_context);
-}
-
-static void fix_processor_context(void)
-{
-	int cpu = smp_processor_id();
-	struct tss_struct *t = &per_cpu(init_tss, cpu);
-
-	/*
-	 * This just modifies memory; should not be necessary. But... This
-	 * is necessary, because 386 hardware has concept of busy TSS or some
-	 * similar stupidity.
-	 */
-	set_tss_desc(cpu, t);
-
-	get_cpu_gdt_table(cpu)[GDT_ENTRY_TSS].type = 9;
-
-	syscall_init();                         /* This sets MSR_*STAR and related */
-	load_TR_desc();				/* This does ltr */
-	load_LDT(&current->active_mm->context);	/* This does lldt */
-
-	/*
-	 * Now maybe reload the debug registers
-	 */
-	if (current->thread.debugreg7){
-                loaddebug(&current->thread, 0);
-                loaddebug(&current->thread, 1);
-                loaddebug(&current->thread, 2);
-                loaddebug(&current->thread, 3);
-                /* no 4 and 5 */
-                loaddebug(&current->thread, 6);
-                loaddebug(&current->thread, 7);
-	}
-}
-
-#ifdef CONFIG_HIBERNATION
-/* Defined in arch/x86_64/kernel/suspend_asm.S */
-extern int restore_image(void);
-
-/*
- * Address to jump to in the last phase of restore in order to get to the image
- * kernel's text (this value is passed in the image header).
- */
-unsigned long restore_jump_address;
-
-/*
- * Value of the cr3 register from before the hibernation (this value is passed
- * in the image header).
- */
-unsigned long restore_cr3;
-
-pgd_t *temp_level4_pgt;
-
-void *relocated_restore_code;
-
-static int res_phys_pud_init(pud_t *pud, unsigned long address, unsigned long end)
-{
-	long i, j;
-
-	i = pud_index(address);
-	pud = pud + i;
-	for (; i < PTRS_PER_PUD; pud++, i++) {
-		unsigned long paddr;
-		pmd_t *pmd;
-
-		paddr = address + i*PUD_SIZE;
-		if (paddr >= end)
-			break;
-
-		pmd = (pmd_t *)get_safe_page(GFP_ATOMIC);
-		if (!pmd)
-			return -ENOMEM;
-		set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE));
-		for (j = 0; j < PTRS_PER_PMD; pmd++, j++, paddr += PMD_SIZE) {
-			unsigned long pe;
-
-			if (paddr >= end)
-				break;
-			pe = __PAGE_KERNEL_LARGE_EXEC | paddr;
-			pe &= __supported_pte_mask;
-			set_pmd(pmd, __pmd(pe));
-		}
-	}
-	return 0;
-}
-
-static int set_up_temporary_mappings(void)
-{
-	unsigned long start, end, next;
-	int error;
-
-	temp_level4_pgt = (pgd_t *)get_safe_page(GFP_ATOMIC);
-	if (!temp_level4_pgt)
-		return -ENOMEM;
-
-	/* It is safe to reuse the original kernel mapping */
-	set_pgd(temp_level4_pgt + pgd_index(__START_KERNEL_map),
-		init_level4_pgt[pgd_index(__START_KERNEL_map)]);
-
-	/* Set up the direct mapping from scratch */
-	start = (unsigned long)pfn_to_kaddr(0);
-	end = (unsigned long)pfn_to_kaddr(end_pfn);
-
-	for (; start < end; start = next) {
-		pud_t *pud = (pud_t *)get_safe_page(GFP_ATOMIC);
-		if (!pud)
-			return -ENOMEM;
-		next = start + PGDIR_SIZE;
-		if (next > end)
-			next = end;
-		if ((error = res_phys_pud_init(pud, __pa(start), __pa(next))))
-			return error;
-		set_pgd(temp_level4_pgt + pgd_index(start),
-			mk_kernel_pgd(__pa(pud)));
-	}
-	return 0;
-}
-
-int swsusp_arch_resume(void)
-{
-	int error;
-
-	/* We have got enough memory and from now on we cannot recover */
-	if ((error = set_up_temporary_mappings()))
-		return error;
-
-	relocated_restore_code = (void *)get_safe_page(GFP_ATOMIC);
-	if (!relocated_restore_code)
-		return -ENOMEM;
-	memcpy(relocated_restore_code, &core_restore_code,
-	       &restore_registers - &core_restore_code);
-
-	restore_image();
-	return 0;
-}
-
-/*
- *	pfn_is_nosave - check if given pfn is in the 'nosave' section
- */
-
-int pfn_is_nosave(unsigned long pfn)
-{
-	unsigned long nosave_begin_pfn = __pa_symbol(&__nosave_begin) >> PAGE_SHIFT;
-	unsigned long nosave_end_pfn = PAGE_ALIGN(__pa_symbol(&__nosave_end)) >> PAGE_SHIFT;
-	return (pfn >= nosave_begin_pfn) && (pfn < nosave_end_pfn);
-}
-
-struct restore_data_record {
-	unsigned long jump_address;
-	unsigned long cr3;
-	unsigned long magic;
-};
-
-#define RESTORE_MAGIC	0x0123456789ABCDEFUL
-
-/**
- *	arch_hibernation_header_save - populate the architecture specific part
- *		of a hibernation image header
- *	@addr: address to save the data at
- */
-int arch_hibernation_header_save(void *addr, unsigned int max_size)
-{
-	struct restore_data_record *rdr = addr;
-
-	if (max_size < sizeof(struct restore_data_record))
-		return -EOVERFLOW;
-	rdr->jump_address = restore_jump_address;
-	rdr->cr3 = restore_cr3;
-	rdr->magic = RESTORE_MAGIC;
-	return 0;
-}
-
-/**
- *	arch_hibernation_header_restore - read the architecture specific data
- *		from the hibernation image header
- *	@addr: address to read the data from
- */
-int arch_hibernation_header_restore(void *addr)
-{
-	struct restore_data_record *rdr = addr;
-
-	restore_jump_address = rdr->jump_address;
-	restore_cr3 = rdr->cr3;
-	return (rdr->magic == RESTORE_MAGIC) ? 0 : -EINVAL;
-}
-#endif /* CONFIG_HIBERNATION */
diff --git a/arch/x86/kernel/suspend_asm_64.S b/arch/x86/kernel/suspend_asm_64.S
deleted file mode 100644
index aeb9a4d7681e..000000000000
--- a/arch/x86/kernel/suspend_asm_64.S
+++ /dev/null
@@ -1,141 +0,0 @@
-/* Copyright 2004,2005 Pavel Machek <pavel@suse.cz>, Andi Kleen <ak@suse.de>, Rafael J. Wysocki <rjw@sisk.pl>
- *
- * Distribute under GPLv2.
- *
- * swsusp_arch_resume must not use any stack or any nonlocal variables while
- * copying pages:
- *
- * Its rewriting one kernel image with another. What is stack in "old"
- * image could very well be data page in "new" image, and overwriting
- * your own stack under you is bad idea.
- */
-	
-	.text
-#include <linux/linkage.h>
-#include <asm/segment.h>
-#include <asm/page.h>
-#include <asm/asm-offsets.h>
-
-ENTRY(swsusp_arch_suspend)
-	movq	$saved_context, %rax
-	movq	%rsp, pt_regs_sp(%rax)
-	movq	%rbp, pt_regs_bp(%rax)
-	movq	%rsi, pt_regs_si(%rax)
-	movq	%rdi, pt_regs_di(%rax)
-	movq	%rbx, pt_regs_bx(%rax)
-	movq	%rcx, pt_regs_cx(%rax)
-	movq	%rdx, pt_regs_dx(%rax)
-	movq	%r8, pt_regs_r8(%rax)
-	movq	%r9, pt_regs_r9(%rax)
-	movq	%r10, pt_regs_r10(%rax)
-	movq	%r11, pt_regs_r11(%rax)
-	movq	%r12, pt_regs_r12(%rax)
-	movq	%r13, pt_regs_r13(%rax)
-	movq	%r14, pt_regs_r14(%rax)
-	movq	%r15, pt_regs_r15(%rax)
-	pushfq
-	popq	pt_regs_flags(%rax)
-
-	/* save the address of restore_registers */
-	movq	$restore_registers, %rax
-	movq	%rax, restore_jump_address(%rip)
-	/* save cr3 */
-	movq	%cr3, %rax
-	movq	%rax, restore_cr3(%rip)
-
-	call swsusp_save
-	ret
-
-ENTRY(restore_image)
-	/* switch to temporary page tables */
-	movq	$__PAGE_OFFSET, %rdx
-	movq	temp_level4_pgt(%rip), %rax
-	subq	%rdx, %rax
-	movq	%rax, %cr3
-	/* Flush TLB */
-	movq	mmu_cr4_features(%rip), %rax
-	movq	%rax, %rdx
-	andq	$~(1<<7), %rdx	# PGE
-	movq	%rdx, %cr4;  # turn off PGE
-	movq	%cr3, %rcx;  # flush TLB
-	movq	%rcx, %cr3;
-	movq	%rax, %cr4;  # turn PGE back on
-
-	/* prepare to jump to the image kernel */
-	movq	restore_jump_address(%rip), %rax
-	movq	restore_cr3(%rip), %rbx
-
-	/* prepare to copy image data to their original locations */
-	movq	restore_pblist(%rip), %rdx
-	movq	relocated_restore_code(%rip), %rcx
-	jmpq	*%rcx
-
-	/* code below has been relocated to a safe page */
-ENTRY(core_restore_code)
-loop:
-	testq	%rdx, %rdx
-	jz	done
-
-	/* get addresses from the pbe and copy the page */
-	movq	pbe_address(%rdx), %rsi
-	movq	pbe_orig_address(%rdx), %rdi
-	movq	$(PAGE_SIZE >> 3), %rcx
-	rep
-	movsq
-
-	/* progress to the next pbe */
-	movq	pbe_next(%rdx), %rdx
-	jmp	loop
-done:
-	/* jump to the restore_registers address from the image header */
-	jmpq	*%rax
-	/*
-	 * NOTE: This assumes that the boot kernel's text mapping covers the
-	 * image kernel's page containing restore_registers and the address of
-	 * this page is the same as in the image kernel's text mapping (it
-	 * should always be true, because the text mapping is linear, starting
-	 * from 0, and is supposed to cover the entire kernel text for every
-	 * kernel).
-	 *
-	 * code below belongs to the image kernel
-	 */
-
-ENTRY(restore_registers)
-	/* go back to the original page tables */
-	movq    %rbx, %cr3
-
-	/* Flush TLB, including "global" things (vmalloc) */
-	movq	mmu_cr4_features(%rip), %rax
-	movq	%rax, %rdx
-	andq	$~(1<<7), %rdx;  # PGE
-	movq	%rdx, %cr4;  # turn off PGE
-	movq	%cr3, %rcx;  # flush TLB
-	movq	%rcx, %cr3
-	movq	%rax, %cr4;  # turn PGE back on
-
-	/* We don't restore %rax, it must be 0 anyway */
-	movq	$saved_context, %rax
-	movq	pt_regs_sp(%rax), %rsp
-	movq	pt_regs_bp(%rax), %rbp
-	movq	pt_regs_si(%rax), %rsi
-	movq	pt_regs_di(%rax), %rdi
-	movq	pt_regs_bx(%rax), %rbx
-	movq	pt_regs_cx(%rax), %rcx
-	movq	pt_regs_dx(%rax), %rdx
-	movq	pt_regs_r8(%rax), %r8
-	movq	pt_regs_r9(%rax), %r9
-	movq	pt_regs_r10(%rax), %r10
-	movq	pt_regs_r11(%rax), %r11
-	movq	pt_regs_r12(%rax), %r12
-	movq	pt_regs_r13(%rax), %r13
-	movq	pt_regs_r14(%rax), %r14
-	movq	pt_regs_r15(%rax), %r15
-	pushq	pt_regs_flags(%rax)
-	popfq
-
-	xorq	%rax, %rax
-
-	/* tell the hibernation core that we've just restored the memory */
-	movq	%rax, in_suspend(%rip)
-
-	ret
diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S
index 8344c70adf61..adff5562f5fd 100644
--- a/arch/x86/kernel/syscall_table_32.S
+++ b/arch/x86/kernel/syscall_table_32.S
@@ -321,6 +321,8 @@ ENTRY(sys_call_table)
 	.long sys_epoll_pwait
 	.long sys_utimensat		/* 320 */
 	.long sys_signalfd
-	.long sys_timerfd
+	.long sys_timerfd_create
 	.long sys_eventfd
 	.long sys_fallocate
+	.long sys_timerfd_settime	/* 325 */
+	.long sys_timerfd_gettime
diff --git a/arch/x86/kernel/test_nx.c b/arch/x86/kernel/test_nx.c
index 36c100c323aa..10b8a6f69f84 100644
--- a/arch/x86/kernel/test_nx.c
+++ b/arch/x86/kernel/test_nx.c
@@ -139,7 +139,6 @@ static int test_NX(void)
 	 * Until then, don't run them to avoid too many people getting scared
 	 * by the error message
 	 */
-#if 0
 
 #ifdef CONFIG_DEBUG_RODATA
 	/* Test 3: Check if the .rodata section is executable */
@@ -152,6 +151,7 @@ static int test_NX(void)
 	}
 #endif
 
+#if 0
 	/* Test 4: Check if the .data section of a module is executable */
 	if (test_address(&test_data)) {
 		printk(KERN_ERR "test_nx: .data section is executable\n");
diff --git a/arch/x86/kernel/test_rodata.c b/arch/x86/kernel/test_rodata.c
index 4c163772000e..c29e235792af 100644
--- a/arch/x86/kernel/test_rodata.c
+++ b/arch/x86/kernel/test_rodata.c
@@ -10,8 +10,8 @@
  * of the License.
  */
 #include <linux/module.h>
+#include <asm/cacheflush.h>
 #include <asm/sections.h>
-extern int rodata_test_data;
 
 int rodata_test(void)
 {
diff --git a/arch/x86/kernel/time_64.c b/arch/x86/kernel/time_64.c
index 0380795121a6..c737849e2ef7 100644
--- a/arch/x86/kernel/time_64.c
+++ b/arch/x86/kernel/time_64.c
@@ -77,7 +77,7 @@ unsigned long __init native_calculate_cpu_khz(void)
 		reserve_evntsel_nmi(MSR_K7_EVNTSEL0 + i);
 	}
 	local_irq_save(flags);
-	/* start meauring cycles, incrementing from 0 */
+	/* start measuring cycles, incrementing from 0 */
 	wrmsrl(MSR_K7_PERFCTR0 + i, 0);
 	wrmsrl(MSR_K7_EVNTSEL0 + i, 1 << 22 | 3 << 16 | 0x76);
 	rdtscl(tsc_start);
diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c
index e6757aaa202b..a40051b71d9b 100644
--- a/arch/x86/kernel/topology.c
+++ b/arch/x86/kernel/topology.c
@@ -53,7 +53,7 @@ EXPORT_SYMBOL(arch_register_cpu);
 
 void arch_unregister_cpu(int num)
 {
-	return unregister_cpu(&per_cpu(cpu_devices, num).cpu);
+	unregister_cpu(&per_cpu(cpu_devices, num).cpu);
 }
 EXPORT_SYMBOL(arch_unregister_cpu);
 #else
diff --git a/arch/x86/kernel/traps_32.c b/arch/x86/kernel/traps_32.c
index 3cf72977d012..b22c01e05a18 100644
--- a/arch/x86/kernel/traps_32.c
+++ b/arch/x86/kernel/traps_32.c
@@ -1176,17 +1176,12 @@ void __init trap_init(void)
 #endif
 	set_trap_gate(19,&simd_coprocessor_error);
 
+	/*
+	 * Verify that the FXSAVE/FXRSTOR data will be 16-byte aligned.
+	 * Generate a build-time error if the alignment is wrong.
+	 */
+	BUILD_BUG_ON(offsetof(struct task_struct, thread.i387.fxsave) & 15);
 	if (cpu_has_fxsr) {
-		/*
-		 * Verify that the FXSAVE/FXRSTOR data will be 16-byte aligned.
-		 * Generates a compile-time "error: zero width for bit-field" if
-		 * the alignment is wrong.
-		 */
-		struct fxsrAlignAssert {
-			int _:!(offsetof(struct task_struct,
-					thread.i387.fxsave) & 15);
-		};
-
 		printk(KERN_INFO "Enabling fast FPU save and restore... ");
 		set_in_cr4(X86_CR4_OSFXSR);
 		printk("done.\n");
diff --git a/arch/x86/kernel/traps_64.c b/arch/x86/kernel/traps_64.c
index efc66df728b6..045466681911 100644
--- a/arch/x86/kernel/traps_64.c
+++ b/arch/x86/kernel/traps_64.c
@@ -84,7 +84,7 @@ static inline void conditional_sti(struct pt_regs *regs)
 
 static inline void preempt_conditional_sti(struct pt_regs *regs)
 {
-	preempt_disable();
+	inc_preempt_count();
 	if (regs->flags & X86_EFLAGS_IF)
 		local_irq_enable();
 }
@@ -95,7 +95,7 @@ static inline void preempt_conditional_cli(struct pt_regs *regs)
 		local_irq_disable();
 	/* Make sure to not schedule here because we could be running
 	   on an exception stack. */
-	preempt_enable_no_resched();
+	dec_preempt_count();
 }
 
 int kstack_depth_to_print = 12;