Merge commit 'v2.6.30-rc1' into core/urgent

Merge reason: need latest upstream to queue up dependent fix

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

43 files changed, 874 insertions, 528 deletions

diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index c611ad64137f..145cce75cda7 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -66,7 +66,8 @@ obj-$(CONFIG_X86_MPPARSE)	+= mpparse.o
 obj-y				+= apic/
 obj-$(CONFIG_X86_REBOOTFIXUPS)	+= reboot_fixups_32.o
 obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o
-obj-$(CONFIG_FUNCTION_GRAPH_TRACER)	+= ftrace.o
+obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o
+obj-$(CONFIG_FTRACE_SYSCALLS)	+= ftrace.o
 obj-$(CONFIG_KEXEC)		+= machine_kexec_$(BITS).o
 obj-$(CONFIG_KEXEC)		+= relocate_kernel_$(BITS).o crash.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump_$(BITS).o
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index a18eb7ce2236..723989d7f802 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -230,6 +230,35 @@ static void __cpuinit acpi_register_lapic(int id, u8 enabled)
 }
 
 static int __init
+acpi_parse_x2apic(struct acpi_subtable_header *header, const unsigned long end)
+{
+	struct acpi_madt_local_x2apic *processor = NULL;
+
+	processor = (struct acpi_madt_local_x2apic *)header;
+
+	if (BAD_MADT_ENTRY(processor, end))
+		return -EINVAL;
+
+	acpi_table_print_madt_entry(header);
+
+#ifdef CONFIG_X86_X2APIC
+	/*
+	 * We need to register disabled CPU as well to permit
+	 * counting disabled CPUs. This allows us to size
+	 * cpus_possible_map more accurately, to permit
+	 * to not preallocating memory for all NR_CPUS
+	 * when we use CPU hotplug.
+	 */
+	acpi_register_lapic(processor->local_apic_id,	/* APIC ID */
+			    processor->lapic_flags & ACPI_MADT_ENABLED);
+#else
+	printk(KERN_WARNING PREFIX "x2apic entry ignored\n");
+#endif
+
+	return 0;
+}
+
+static int __init
 acpi_parse_lapic(struct acpi_subtable_header * header, const unsigned long end)
 {
 	struct acpi_madt_local_apic *processor = NULL;
@@ -289,6 +318,25 @@ acpi_parse_lapic_addr_ovr(struct acpi_subtable_header * header,
 }
 
 static int __init
+acpi_parse_x2apic_nmi(struct acpi_subtable_header *header,
+		      const unsigned long end)
+{
+	struct acpi_madt_local_x2apic_nmi *x2apic_nmi = NULL;
+
+	x2apic_nmi = (struct acpi_madt_local_x2apic_nmi *)header;
+
+	if (BAD_MADT_ENTRY(x2apic_nmi, end))
+		return -EINVAL;
+
+	acpi_table_print_madt_entry(header);
+
+	if (x2apic_nmi->lint != 1)
+		printk(KERN_WARNING PREFIX "NMI not connected to LINT 1!\n");
+
+	return 0;
+}
+
+static int __init
 acpi_parse_lapic_nmi(struct acpi_subtable_header * header, const unsigned long end)
 {
 	struct acpi_madt_local_apic_nmi *lapic_nmi = NULL;
@@ -793,6 +841,7 @@ static int __init early_acpi_parse_madt_lapic_addr_ovr(void)
 static int __init acpi_parse_madt_lapic_entries(void)
 {
 	int count;
+	int x2count = 0;
 
 	if (!cpu_has_apic)
 		return -ENODEV;
@@ -816,22 +865,28 @@ static int __init acpi_parse_madt_lapic_entries(void)
 	count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_SAPIC,
 				      acpi_parse_sapic, MAX_APICS);
 
-	if (!count)
+	if (!count) {
+		x2count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_X2APIC,
+						acpi_parse_x2apic, MAX_APICS);
 		count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_APIC,
 					      acpi_parse_lapic, MAX_APICS);
-	if (!count) {
+	}
+	if (!count && !x2count) {
 		printk(KERN_ERR PREFIX "No LAPIC entries present\n");
 		/* TBD: Cleanup to allow fallback to MPS */
 		return -ENODEV;
-	} else if (count < 0) {
+	} else if (count < 0 || x2count < 0) {
 		printk(KERN_ERR PREFIX "Error parsing LAPIC entry\n");
 		/* TBD: Cleanup to allow fallback to MPS */
 		return count;
 	}
 
+	x2count =
+	    acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_X2APIC_NMI,
+				  acpi_parse_x2apic_nmi, 0);
 	count =
 	    acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_APIC_NMI, acpi_parse_lapic_nmi, 0);
-	if (count < 0) {
+	if (count < 0 || x2count < 0) {
 		printk(KERN_ERR PREFIX "Error parsing LAPIC NMI entry\n");
 		/* TBD: Cleanup to allow fallback to MPS */
 		return count;
@@ -1470,7 +1525,7 @@ static int __init dmi_ignore_irq0_timer_override(const struct dmi_system_id *d)
 
 /*
  * If your system is blacklisted here, but you find that acpi=force
- * works for you, please contact acpi-devel@sourceforge.net
+ * works for you, please contact linux-acpi@vger.kernel.org
  */
 static struct dmi_system_id __initdata acpi_dmi_table[] = {
 	/*
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 4c80f1557433..f57658702571 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -5,6 +5,7 @@
 #include <linux/kprobes.h>
 #include <linux/mm.h>
 #include <linux/vmalloc.h>
+#include <linux/memory.h>
 #include <asm/alternative.h>
 #include <asm/sections.h>
 #include <asm/pgtable.h>
@@ -12,7 +13,9 @@
 #include <asm/nmi.h>
 #include <asm/vsyscall.h>
 #include <asm/cacheflush.h>
+#include <asm/tlbflush.h>
 #include <asm/io.h>
+#include <asm/fixmap.h>
 
 #define MAX_PATCH_LEN (255-1)
 
@@ -226,6 +229,7 @@ static void alternatives_smp_lock(u8 **start, u8 **end, u8 *text, u8 *text_end)
 {
 	u8 **ptr;
 
+	mutex_lock(&text_mutex);
 	for (ptr = start; ptr < end; ptr++) {
 		if (*ptr < text)
 			continue;
@@ -234,6 +238,7 @@ static void alternatives_smp_lock(u8 **start, u8 **end, u8 *text, u8 *text_end)
 		/* turn DS segment override prefix into lock prefix */
 		text_poke(*ptr, ((unsigned char []){0xf0}), 1);
 	};
+	mutex_unlock(&text_mutex);
 }
 
 static void alternatives_smp_unlock(u8 **start, u8 **end, u8 *text, u8 *text_end)
@@ -243,6 +248,7 @@ static void alternatives_smp_unlock(u8 **start, u8 **end, u8 *text, u8 *text_end
 	if (noreplace_smp)
 		return;
 
+	mutex_lock(&text_mutex);
 	for (ptr = start; ptr < end; ptr++) {
 		if (*ptr < text)
 			continue;
@@ -251,6 +257,7 @@ static void alternatives_smp_unlock(u8 **start, u8 **end, u8 *text, u8 *text_end
 		/* turn lock prefix into DS segment override prefix */
 		text_poke(*ptr, ((unsigned char []){0x3E}), 1);
 	};
+	mutex_unlock(&text_mutex);
 }
 
 struct smp_alt_module {
@@ -500,15 +507,16 @@ void *text_poke_early(void *addr, const void *opcode, size_t len)
  * It means the size must be writable atomically and the address must be aligned
  * in a way that permits an atomic write. It also makes sure we fit on a single
  * page.
+ *
+ * Note: Must be called under text_mutex.
  */
 void *__kprobes text_poke(void *addr, const void *opcode, size_t len)
 {
+	unsigned long flags;
 	char *vaddr;
-	int nr_pages = 2;
 	struct page *pages[2];
 	int i;
 
-	might_sleep();
 	if (!core_kernel_text((unsigned long)addr)) {
 		pages[0] = vmalloc_to_page(addr);
 		pages[1] = vmalloc_to_page(addr + PAGE_SIZE);
@@ -518,18 +526,21 @@ void *__kprobes text_poke(void *addr, const void *opcode, size_t len)
 		pages[1] = virt_to_page(addr + PAGE_SIZE);
 	}
 	BUG_ON(!pages[0]);
-	if (!pages[1])
-		nr_pages = 1;
-	vaddr = vmap(pages, nr_pages, VM_MAP, PAGE_KERNEL);
-	BUG_ON(!vaddr);
-	local_irq_disable();
+	local_irq_save(flags);
+	set_fixmap(FIX_TEXT_POKE0, page_to_phys(pages[0]));
+	if (pages[1])
+		set_fixmap(FIX_TEXT_POKE1, page_to_phys(pages[1]));
+	vaddr = (char *)fix_to_virt(FIX_TEXT_POKE0);
 	memcpy(&vaddr[(unsigned long)addr & ~PAGE_MASK], opcode, len);
-	local_irq_enable();
-	vunmap(vaddr);
+	clear_fixmap(FIX_TEXT_POKE0);
+	if (pages[1])
+		clear_fixmap(FIX_TEXT_POKE1);
+	local_flush_tlb();
 	sync_core();
 	/* Could also do a CLFLUSH here to speed up CPU recovery; but
 	   that causes hangs on some VIA CPUs. */
 	for (i = 0; i < len; i++)
 		BUG_ON(((char *)addr)[i] != ((char *)opcode)[i]);
+	local_irq_restore(flags);
 	return addr;
 }
diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c
index c5962fe3796f..a97db99dad52 100644
--- a/arch/x86/kernel/amd_iommu.c
+++ b/arch/x86/kernel/amd_iommu.c
@@ -1928,6 +1928,12 @@ static phys_addr_t amd_iommu_iova_to_phys(struct iommu_domain *dom,
 	return paddr;
 }
 
+static int amd_iommu_domain_has_cap(struct iommu_domain *domain,
+				    unsigned long cap)
+{
+	return 0;
+}
+
 static struct iommu_ops amd_iommu_ops = {
 	.domain_init = amd_iommu_domain_init,
 	.domain_destroy = amd_iommu_domain_destroy,
@@ -1936,5 +1942,6 @@ static struct iommu_ops amd_iommu_ops = {
 	.map = amd_iommu_map_range,
 	.unmap = amd_iommu_unmap_range,
 	.iova_to_phys = amd_iommu_iova_to_phys,
+	.domain_has_cap = amd_iommu_domain_has_cap,
 };
 
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 85eb8e100818..098ec84b8c00 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1304,6 +1304,7 @@ void __init enable_IR_x2apic(void)
 #ifdef CONFIG_INTR_REMAP
 	int ret;
 	unsigned long flags;
+	struct IO_APIC_route_entry **ioapic_entries = NULL;
 
 	if (!cpu_has_x2apic)
 		return;
@@ -1334,17 +1335,23 @@ void __init enable_IR_x2apic(void)
 		return;
 	}
 
-	ret = save_IO_APIC_setup();
+	ioapic_entries = alloc_ioapic_entries();
+	if (!ioapic_entries) {
+		pr_info("Allocate ioapic_entries failed: %d\n", ret);
+		goto end;
+	}
+
+	ret = save_IO_APIC_setup(ioapic_entries);
 	if (ret) {
 		pr_info("Saving IO-APIC state failed: %d\n", ret);
 		goto end;
 	}
 
 	local_irq_save(flags);
-	mask_IO_APIC_setup();
+	mask_IO_APIC_setup(ioapic_entries);
 	mask_8259A();
 
-	ret = enable_intr_remapping(1);
+	ret = enable_intr_remapping(EIM_32BIT_APIC_ID);
 
 	if (ret && x2apic_preenabled) {
 		local_irq_restore(flags);
@@ -1364,9 +1371,9 @@ end_restore:
 		/*
 		 * IR enabling failed
 		 */
-		restore_IO_APIC_setup();
+		restore_IO_APIC_setup(ioapic_entries);
 	else
-		reinit_intr_remapped_IO_APIC(x2apic_preenabled);
+		reinit_intr_remapped_IO_APIC(x2apic_preenabled, ioapic_entries);
 
 	unmask_8259A();
 	local_irq_restore(flags);
@@ -1379,6 +1386,8 @@ end:
 			pr_info("Enabled Interrupt-remapping\n");
 	} else
 		pr_err("Failed to enable Interrupt-remapping and x2apic\n");
+	if (ioapic_entries)
+		free_ioapic_entries(ioapic_entries);
 #else
 	if (!cpu_has_x2apic)
 		return;
@@ -1954,6 +1963,10 @@ static int lapic_suspend(struct sys_device *dev, pm_message_t state)
 
 	local_irq_save(flags);
 	disable_local_APIC();
+#ifdef CONFIG_INTR_REMAP
+	if (intr_remapping_enabled)
+		disable_intr_remapping();
+#endif
 	local_irq_restore(flags);
 	return 0;
 }
@@ -1964,15 +1977,41 @@ static int lapic_resume(struct sys_device *dev)
 	unsigned long flags;
 	int maxlvt;
 
+#ifdef CONFIG_INTR_REMAP
+	int ret;
+	struct IO_APIC_route_entry **ioapic_entries = NULL;
+
 	if (!apic_pm_state.active)
 		return 0;
 
-	maxlvt = lapic_get_maxlvt();
-
 	local_irq_save(flags);
+	if (x2apic) {
+		ioapic_entries = alloc_ioapic_entries();
+		if (!ioapic_entries) {
+			WARN(1, "Alloc ioapic_entries in lapic resume failed.");
+			return -ENOMEM;
+		}
+
+		ret = save_IO_APIC_setup(ioapic_entries);
+		if (ret) {
+			WARN(1, "Saving IO-APIC state failed: %d\n", ret);
+			free_ioapic_entries(ioapic_entries);
+			return ret;
+		}
+
+		mask_IO_APIC_setup(ioapic_entries);
+		mask_8259A();
+		enable_x2apic();
+	}
+#else
+	if (!apic_pm_state.active)
+		return 0;
 
+	local_irq_save(flags);
 	if (x2apic)
 		enable_x2apic();
+#endif
+
 	else {
 		/*
 		 * Make sure the APICBASE points to the right address
@@ -1986,6 +2025,7 @@ static int lapic_resume(struct sys_device *dev)
 		wrmsr(MSR_IA32_APICBASE, l, h);
 	}
 
+	maxlvt = lapic_get_maxlvt();
 	apic_write(APIC_LVTERR, ERROR_APIC_VECTOR | APIC_LVT_MASKED);
 	apic_write(APIC_ID, apic_pm_state.apic_id);
 	apic_write(APIC_DFR, apic_pm_state.apic_dfr);
@@ -2009,8 +2049,20 @@ static int lapic_resume(struct sys_device *dev)
 	apic_write(APIC_ESR, 0);
 	apic_read(APIC_ESR);
 
+#ifdef CONFIG_INTR_REMAP
+	if (intr_remapping_enabled)
+		reenable_intr_remapping(EIM_32BIT_APIC_ID);
+
+	if (x2apic) {
+		unmask_8259A();
+		restore_IO_APIC_setup(ioapic_entries);
+		free_ioapic_entries(ioapic_entries);
+	}
+#endif
+
 	local_irq_restore(flags);
 
+
 	return 0;
 }
 
@@ -2048,7 +2100,9 @@ static int __init init_lapic_sysfs(void)
 		error = sysdev_register(&device_lapic);
 	return error;
 }
-device_initcall(init_lapic_sysfs);
+
+/* local apic needs to resume before other devices access its registers. */
+core_initcall(init_lapic_sysfs);
 
 #else	/* CONFIG_PM */
 
diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c
index d806ecaa948f..676cdac385c0 100644
--- a/arch/x86/kernel/apic/bigsmp_32.c
+++ b/arch/x86/kernel/apic/bigsmp_32.c
@@ -26,12 +26,12 @@ static int bigsmp_apic_id_registered(void)
 	return 1;
 }
 
-static const cpumask_t *bigsmp_target_cpus(void)
+static const struct cpumask *bigsmp_target_cpus(void)
 {
 #ifdef CONFIG_SMP
-	return &cpu_online_map;
+	return cpu_online_mask;
 #else
-	return &cpumask_of_cpu(0);
+	return cpumask_of(0);
 #endif
 }
 
@@ -118,9 +118,9 @@ static int bigsmp_check_phys_apicid_present(int boot_cpu_physical_apicid)
 }
 
 /* As we are using single CPU as destination, pick only one CPU here */
-static unsigned int bigsmp_cpu_mask_to_apicid(const cpumask_t *cpumask)
+static unsigned int bigsmp_cpu_mask_to_apicid(const struct cpumask *cpumask)
 {
-	return bigsmp_cpu_to_logical_apicid(first_cpu(*cpumask));
+	return bigsmp_cpu_to_logical_apicid(cpumask_first(cpumask));
 }
 
 static unsigned int bigsmp_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
@@ -188,10 +188,10 @@ static const struct dmi_system_id bigsmp_dmi_table[] = {
 	{ } /* NULL entry stops DMI scanning */
 };
 
-static void bigsmp_vector_allocation_domain(int cpu, cpumask_t *retmask)
+static void bigsmp_vector_allocation_domain(int cpu, struct cpumask *retmask)
 {
-	cpus_clear(*retmask);
-	cpu_set(cpu, *retmask);
+	cpumask_clear(retmask);
+	cpumask_set_cpu(cpu, retmask);
 }
 
 static int probe_bigsmp(void)
diff --git a/arch/x86/kernel/apic/es7000_32.c b/arch/x86/kernel/apic/es7000_32.c
index 19588f2770ee..1c11b819f245 100644
--- a/arch/x86/kernel/apic/es7000_32.c
+++ b/arch/x86/kernel/apic/es7000_32.c
@@ -410,7 +410,7 @@ static void es7000_enable_apic_mode(void)
 		WARN(1, "Command failed, status = %x\n", mip_status);
 }
 
-static void es7000_vector_allocation_domain(int cpu, cpumask_t *retmask)
+static void es7000_vector_allocation_domain(int cpu, struct cpumask *retmask)
 {
 	/* Careful. Some cpus do not strictly honor the set of cpus
 	 * specified in the interrupt destination when using lowest
@@ -420,7 +420,8 @@ static void es7000_vector_allocation_domain(int cpu, cpumask_t *retmask)
 	 * deliver interrupts to the wrong hyperthread when only one
 	 * hyperthread was specified in the interrupt desitination.
 	 */
-	*retmask = (cpumask_t){ { [0] = APIC_ALL_CPUS, } };
+	cpumask_clear(retmask);
+	cpumask_bits(retmask)[0] = APIC_ALL_CPUS;
 }
 
 
@@ -455,14 +456,14 @@ static int es7000_apic_id_registered(void)
 	return 1;
 }
 
-static const cpumask_t *target_cpus_cluster(void)
+static const struct cpumask *target_cpus_cluster(void)
 {
-	return &CPU_MASK_ALL;
+	return cpu_all_mask;
 }
 
-static const cpumask_t *es7000_target_cpus(void)
+static const struct cpumask *es7000_target_cpus(void)
 {
-	return &cpumask_of_cpu(smp_processor_id());
+	return cpumask_of(smp_processor_id());
 }
 
 static unsigned long
@@ -517,7 +518,7 @@ static void es7000_setup_apic_routing(void)
 	  "Enabling APIC mode:  %s. Using %d I/O APICs, target cpus %lx\n",
 		(apic_version[apic] == 0x14) ?
 			"Physical Cluster" : "Logical Cluster",
-		nr_ioapics, cpus_addr(*es7000_target_cpus())[0]);
+		nr_ioapics, cpumask_bits(es7000_target_cpus())[0]);
 }
 
 static int es7000_apicid_to_node(int logical_apicid)
@@ -572,7 +573,7 @@ static int es7000_check_phys_apicid_present(int cpu_physical_apicid)
 	return 1;
 }
 
-static unsigned int es7000_cpu_mask_to_apicid(const cpumask_t *cpumask)
+static unsigned int es7000_cpu_mask_to_apicid(const struct cpumask *cpumask)
 {
 	unsigned int round = 0;
 	int cpu, uninitialized_var(apicid);
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 1bb5c6cee3eb..767fe7e46d68 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -851,63 +851,74 @@ __setup("pirq=", ioapic_pirq_setup);
 #endif /* CONFIG_X86_32 */
 
 #ifdef CONFIG_INTR_REMAP
-/* I/O APIC RTE contents at the OS boot up */
-static struct IO_APIC_route_entry *early_ioapic_entries[MAX_IO_APICS];
+struct IO_APIC_route_entry **alloc_ioapic_entries(void)
+{
+	int apic;
+	struct IO_APIC_route_entry **ioapic_entries;
+
+	ioapic_entries = kzalloc(sizeof(*ioapic_entries) * nr_ioapics,
+				GFP_ATOMIC);
+	if (!ioapic_entries)
+		return 0;
+
+	for (apic = 0; apic < nr_ioapics; apic++) {
+		ioapic_entries[apic] =
+			kzalloc(sizeof(struct IO_APIC_route_entry) *
+				nr_ioapic_registers[apic], GFP_ATOMIC);
+		if (!ioapic_entries[apic])
+			goto nomem;
+	}
+
+	return ioapic_entries;
+
+nomem:
+	while (--apic >= 0)
+		kfree(ioapic_entries[apic]);
+	kfree(ioapic_entries);
+
+	return 0;
+}
 
 /*
  * Saves all the IO-APIC RTE's
  */
-int save_IO_APIC_setup(void)
+int save_IO_APIC_setup(struct IO_APIC_route_entry **ioapic_entries)
 {
-	union IO_APIC_reg_01 reg_01;
-	unsigned long flags;
 	int apic, pin;
 
-	/*
-	 * The number of IO-APIC IRQ registers (== #pins):
-	 */
-	for (apic = 0; apic < nr_ioapics; apic++) {
-		spin_lock_irqsave(&ioapic_lock, flags);
-		reg_01.raw = io_apic_read(apic, 1);
-		spin_unlock_irqrestore(&ioapic_lock, flags);
-		nr_ioapic_registers[apic] = reg_01.bits.entries+1;
-	}
+	if (!ioapic_entries)
+		return -ENOMEM;
 
 	for (apic = 0; apic < nr_ioapics; apic++) {
-		early_ioapic_entries[apic] =
-			kzalloc(sizeof(struct IO_APIC_route_entry) *
-				nr_ioapic_registers[apic], GFP_KERNEL);
-		if (!early_ioapic_entries[apic])
-			goto nomem;
-	}
+		if (!ioapic_entries[apic])
+			return -ENOMEM;
 
-	for (apic = 0; apic < nr_ioapics; apic++)
 		for (pin = 0; pin < nr_ioapic_registers[apic]; pin++)
-			early_ioapic_entries[apic][pin] =
+			ioapic_entries[apic][pin] =
 				ioapic_read_entry(apic, pin);
+	}
 
 	return 0;
-
-nomem:
-	while (apic >= 0)
-		kfree(early_ioapic_entries[apic--]);
-	memset(early_ioapic_entries, 0,
-		ARRAY_SIZE(early_ioapic_entries));
-
-	return -ENOMEM;
 }
 
-void mask_IO_APIC_setup(void)
+/*
+ * Mask all IO APIC entries.
+ */
+void mask_IO_APIC_setup(struct IO_APIC_route_entry **ioapic_entries)
 {
 	int apic, pin;
 
+	if (!ioapic_entries)
+		return;
+
 	for (apic = 0; apic < nr_ioapics; apic++) {
-		if (!early_ioapic_entries[apic])
+		if (!ioapic_entries[apic])
 			break;
+
 		for (pin = 0; pin < nr_ioapic_registers[apic]; pin++) {
 			struct IO_APIC_route_entry entry;
 
-			entry = early_ioapic_entries[apic][pin];
+			entry = ioapic_entries[apic][pin];
 			if (!entry.mask) {
 				entry.mask = 1;
 				ioapic_write_entry(apic, pin, entry);
@@ -916,22 +927,30 @@ void mask_IO_APIC_setup(void)
 	}
 }
 
-void restore_IO_APIC_setup(void)
+/*
+ * Restore IO APIC entries which was saved in ioapic_entries.
+ */
+int restore_IO_APIC_setup(struct IO_APIC_route_entry **ioapic_entries)
 {
 	int apic, pin;
 
+	if (!ioapic_entries)
+		return -ENOMEM;
+
 	for (apic = 0; apic < nr_ioapics; apic++) {
-		if (!early_ioapic_entries[apic])
-			break;
+		if (!ioapic_entries[apic])
+			return -ENOMEM;
+
 		for (pin = 0; pin < nr_ioapic_registers[apic]; pin++)
 			ioapic_write_entry(apic, pin,
-					   early_ioapic_entries[apic][pin]);
-		kfree(early_ioapic_entries[apic]);
-		early_ioapic_entries[apic] = NULL;
+					ioapic_entries[apic][pin]);
 	}
+	return 0;
 }
 
-void reinit_intr_remapped_IO_APIC(int intr_remapping)
+void reinit_intr_remapped_IO_APIC(int intr_remapping,
+	struct IO_APIC_route_entry **ioapic_entries)
+
 {
 	/*
 	 * for now plain restore of previous settings.
@@ -940,7 +959,17 @@ void reinit_intr_remapped_IO_APIC(int intr_remapping)
 	 * table entries. for now, do a plain restore, and wait for
 	 * the setup_IO_APIC_irqs() to do proper initialization.
 	 */
-	restore_IO_APIC_setup();
+	restore_IO_APIC_setup(ioapic_entries);
+}
+
+void free_ioapic_entries(struct IO_APIC_route_entry **ioapic_entries)
+{
+	int apic;
+
+	for (apic = 0; apic < nr_ioapics; apic++)
+		kfree(ioapic_entries[apic]);
+
+	kfree(ioapic_entries);
 }
 #endif
 
@@ -2495,7 +2524,7 @@ static void irq_complete_move(struct irq_desc **descp)
 static inline void irq_complete_move(struct irq_desc **descp) {}
 #endif
 
-#ifdef CONFIG_INTR_REMAP
+#ifdef CONFIG_X86_X2APIC
 static void __eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg)
 {
 	int apic, pin;
@@ -2540,7 +2569,6 @@ static void ack_x2apic_edge(unsigned int irq)
 {
 	ack_x2APIC_irq();
 }
-
 #endif
 
 static void ack_apic_edge(unsigned int irq)
@@ -2651,6 +2679,26 @@ static void ack_apic_level(unsigned int irq)
 #endif
 }
 
+#ifdef CONFIG_INTR_REMAP
+static void ir_ack_apic_edge(unsigned int irq)
+{
+#ifdef CONFIG_X86_X2APIC
+       if (x2apic_enabled())
+               return ack_x2apic_edge(irq);
+#endif
+       return ack_apic_edge(irq);
+}
+
+static void ir_ack_apic_level(unsigned int irq)
+{
+#ifdef CONFIG_X86_X2APIC
+       if (x2apic_enabled())
+               return ack_x2apic_level(irq);
+#endif
+       return ack_apic_level(irq);
+}
+#endif /* CONFIG_INTR_REMAP */
+
 static struct irq_chip ioapic_chip __read_mostly = {
 	.name		= "IO-APIC",
 	.startup	= startup_ioapic_irq,
@@ -2670,8 +2718,8 @@ static struct irq_chip ir_ioapic_chip __read_mostly = {
 	.mask		= mask_IO_APIC_irq,
 	.unmask		= unmask_IO_APIC_irq,
 #ifdef CONFIG_INTR_REMAP
-	.ack		= ack_x2apic_edge,
-	.eoi		= ack_x2apic_level,
+	.ack		= ir_ack_apic_edge,
+	.eoi		= ir_ack_apic_level,
 #ifdef CONFIG_SMP
 	.set_affinity	= set_ir_ioapic_affinity_irq,
 #endif
@@ -3397,7 +3445,7 @@ static struct irq_chip msi_ir_chip = {
 	.unmask		= unmask_msi_irq,
 	.mask		= mask_msi_irq,
 #ifdef CONFIG_INTR_REMAP
-	.ack		= ack_x2apic_edge,
+	.ack		= ir_ack_apic_edge,
 #ifdef CONFIG_SMP
 	.set_affinity	= ir_set_msi_irq_affinity,
 #endif
diff --git a/arch/x86/kernel/apic/nmi.c b/arch/x86/kernel/apic/nmi.c
index bdfad80c3cf1..d6bd62407152 100644
--- a/arch/x86/kernel/apic/nmi.c
+++ b/arch/x86/kernel/apic/nmi.c
@@ -39,7 +39,7 @@
 int unknown_nmi_panic;
 int nmi_watchdog_enabled;
 
-static cpumask_t backtrace_mask = CPU_MASK_NONE;
+static cpumask_var_t backtrace_mask;
 
 /* nmi_active:
  * >0: the lapic NMI watchdog is active, but can be disabled
@@ -138,6 +138,7 @@ int __init check_nmi_watchdog(void)
 	if (!prev_nmi_count)
 		goto error;
 
+	alloc_cpumask_var(&backtrace_mask, GFP_KERNEL);
 	printk(KERN_INFO "Testing NMI watchdog ... ");
 
 #ifdef CONFIG_SMP
@@ -413,14 +414,14 @@ nmi_watchdog_tick(struct pt_regs *regs, unsigned reason)
 		touched = 1;
 	}
 
-	if (cpu_isset(cpu, backtrace_mask)) {
+	if (cpumask_test_cpu(cpu, backtrace_mask)) {
 		static DEFINE_SPINLOCK(lock);	/* Serialise the printks */
 
 		spin_lock(&lock);
 		printk(KERN_WARNING "NMI backtrace for cpu %d\n", cpu);
 		dump_stack();
 		spin_unlock(&lock);
-		cpu_clear(cpu, backtrace_mask);
+		cpumask_clear_cpu(cpu, backtrace_mask);
 	}
 
 	/* Could check oops_in_progress here too, but it's safer not to */
@@ -554,10 +555,10 @@ void __trigger_all_cpu_backtrace(void)
 {
 	int i;
 
-	backtrace_mask = cpu_online_map;
+	cpumask_copy(backtrace_mask, cpu_online_mask);
 	/* Wait for up to 10 seconds for all CPUs to do the backtrace */
 	for (i = 0; i < 10 * 1000; i++) {
-		if (cpus_empty(backtrace_mask))
+		if (cpumask_empty(backtrace_mask))
 			break;
 		mdelay(1);
 	}
diff --git a/arch/x86/kernel/apic/numaq_32.c b/arch/x86/kernel/apic/numaq_32.c
index ba2fc6465534..533e59c6fc82 100644
--- a/arch/x86/kernel/apic/numaq_32.c
+++ b/arch/x86/kernel/apic/numaq_32.c
@@ -334,9 +334,9 @@ static inline void numaq_smp_callin_clear_local_apic(void)
 	clear_local_APIC();
 }
 
-static inline const cpumask_t *numaq_target_cpus(void)
+static inline const struct cpumask *numaq_target_cpus(void)
 {
-	return &CPU_MASK_ALL;
+	return cpu_all_mask;
 }
 
 static inline unsigned long
@@ -427,7 +427,7 @@ static inline int numaq_check_phys_apicid_present(int boot_cpu_physical_apicid)
  * We use physical apicids here, not logical, so just return the default
  * physical broadcast to stop people from breaking us
  */
-static inline unsigned int numaq_cpu_mask_to_apicid(const cpumask_t *cpumask)
+static unsigned int numaq_cpu_mask_to_apicid(const struct cpumask *cpumask)
 {
 	return 0x0F;
 }
@@ -462,7 +462,7 @@ static int probe_numaq(void)
 	return found_numaq;
 }
 
-static void numaq_vector_allocation_domain(int cpu, cpumask_t *retmask)
+static void numaq_vector_allocation_domain(int cpu, struct cpumask *retmask)
 {
 	/* Careful. Some cpus do not strictly honor the set of cpus
 	 * specified in the interrupt destination when using lowest
@@ -472,7 +472,8 @@ static void numaq_vector_allocation_domain(int cpu, cpumask_t *retmask)
 	 * deliver interrupts to the wrong hyperthread when only one
 	 * hyperthread was specified in the interrupt desitination.
 	 */
-	*retmask = (cpumask_t){ { [0] = APIC_ALL_CPUS, } };
+	cpumask_clear(retmask);
+	cpumask_bits(retmask)[0] = APIC_ALL_CPUS;
 }
 
 static void numaq_setup_portio_remap(void)
diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c
index 141c99a1c264..01eda2ac65e4 100644
--- a/arch/x86/kernel/apic/probe_32.c
+++ b/arch/x86/kernel/apic/probe_32.c
@@ -83,7 +83,8 @@ static void default_vector_allocation_domain(int cpu, struct cpumask *retmask)
 	 * deliver interrupts to the wrong hyperthread when only one
 	 * hyperthread was specified in the interrupt desitination.
 	 */
-	*retmask = (cpumask_t) { { [0] = APIC_ALL_CPUS } };
+	cpumask_clear(retmask);
+	cpumask_bits(retmask)[0] = APIC_ALL_CPUS;
 }
 
 /* should be called last. */
diff --git a/arch/x86/kernel/apic/summit_32.c b/arch/x86/kernel/apic/summit_32.c
index aac52fa873ff..9cfe1f415d81 100644
--- a/arch/x86/kernel/apic/summit_32.c
+++ b/arch/x86/kernel/apic/summit_32.c
@@ -53,23 +53,19 @@ static unsigned summit_get_apic_id(unsigned long x)
 	return (x >> 24) & 0xFF;
 }
 
-static inline void summit_send_IPI_mask(const cpumask_t *mask, int vector)
+static inline void summit_send_IPI_mask(const struct cpumask *mask, int vector)
 {
 	default_send_IPI_mask_sequence_logical(mask, vector);
 }
 
 static void summit_send_IPI_allbutself(int vector)
 {
-	cpumask_t mask = cpu_online_map;
-	cpu_clear(smp_processor_id(), mask);
-
-	if (!cpus_empty(mask))
-		summit_send_IPI_mask(&mask, vector);
+	default_send_IPI_mask_allbutself_logical(cpu_online_mask, vector);
 }
 
 static void summit_send_IPI_all(int vector)
 {
-	summit_send_IPI_mask(&cpu_online_map, vector);
+	summit_send_IPI_mask(cpu_online_mask, vector);
 }
 
 #include <asm/tsc.h>
@@ -186,13 +182,13 @@ static inline int is_WPEG(struct rio_detail *rio){
 
 #define SUMMIT_APIC_DFR_VALUE	(APIC_DFR_CLUSTER)
 
-static const cpumask_t *summit_target_cpus(void)
+static const struct cpumask *summit_target_cpus(void)
 {
 	/* CPU_MASK_ALL (0xff) has undefined behaviour with
 	 * dest_LowestPrio mode logical clustered apic interrupt routing
 	 * Just start on cpu 0.  IRQ balancing will spread load
 	 */
-	return &cpumask_of_cpu(0);
+	return cpumask_of(0);
 }
 
 static unsigned long summit_check_apicid_used(physid_mask_t bitmap, int apicid)
@@ -289,7 +285,7 @@ static int summit_check_phys_apicid_present(int boot_cpu_physical_apicid)
 	return 1;
 }
 
-static unsigned int summit_cpu_mask_to_apicid(const cpumask_t *cpumask)
+static unsigned int summit_cpu_mask_to_apicid(const struct cpumask *cpumask)
 {
 	unsigned int round = 0;
 	int cpu, apicid = 0;
@@ -346,7 +342,7 @@ static int probe_summit(void)
 	return 0;
 }
 
-static void summit_vector_allocation_domain(int cpu, cpumask_t *retmask)
+static void summit_vector_allocation_domain(int cpu, struct cpumask *retmask)
 {
 	/* Careful. Some cpus do not strictly honor the set of cpus
 	 * specified in the interrupt destination when using lowest
@@ -356,7 +352,8 @@ static void summit_vector_allocation_domain(int cpu, cpumask_t *retmask)
 	 * deliver interrupts to the wrong hyperthread when only one
 	 * hyperthread was specified in the interrupt desitination.
 	 */
-	*retmask = (cpumask_t){ { [0] = APIC_ALL_CPUS, } };
+	cpumask_clear(retmask);
+	cpumask_bits(retmask)[0] = APIC_ALL_CPUS;
 }
 
 #ifdef CONFIG_X86_SUMMIT_NUMA
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 1bd6da1f8fad..1248318436e8 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -118,17 +118,12 @@ static int uv_wakeup_secondary(int phys_apicid, unsigned long start_rip)
 
 static void uv_send_IPI_one(int cpu, int vector)
 {
-	unsigned long val, apicid;
+	unsigned long apicid;
 	int pnode;
 
 	apicid = per_cpu(x86_cpu_to_apicid, cpu);
 	pnode = uv_apicid_to_pnode(apicid);
-
-	val = (1UL << UVH_IPI_INT_SEND_SHFT) |
-	      (apicid << UVH_IPI_INT_APIC_ID_SHFT) |
-	      (vector << UVH_IPI_INT_VECTOR_SHFT);
-
-	uv_write_global_mmr64(pnode, UVH_IPI_INT, val);
+	uv_hub_send_ipi(pnode, apicid, vector);
 }
 
 static void uv_send_IPI_mask(const struct cpumask *mask, int vector)
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index ac7783a67432..49e0939bac42 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -466,7 +466,7 @@ static const lookup_t error_table[] = {
  *	@err: APM BIOS return code
  *
  *	Write a meaningful log entry to the kernel log in the event of
- *	an APM error.
+ *	an APM error.  Note that this also handles (negative) kernel errors.
  */
 
 static void apm_error(char *str, int err)
@@ -478,43 +478,14 @@ static void apm_error(char *str, int err)
 			break;
 	if (i < ERROR_COUNT)
 		printk(KERN_NOTICE "apm: %s: %s\n", str, error_table[i].msg);
+	else if (err < 0)
+		printk(KERN_NOTICE "apm: %s: linux error code %i\n", str, err);
 	else
 		printk(KERN_NOTICE "apm: %s: unknown error code %#2.2x\n",
 		       str, err);
 }
 
 /*
- * Lock APM functionality to physical CPU 0
- */
-
-#ifdef CONFIG_SMP
-
-static cpumask_t apm_save_cpus(void)
-{
-	cpumask_t x = current->cpus_allowed;
-	/* Some bioses don't like being called from CPU != 0 */
-	set_cpus_allowed(current, cpumask_of_cpu(0));
-	BUG_ON(smp_processor_id() != 0);
-	return x;
-}
-
-static inline void apm_restore_cpus(cpumask_t mask)
-{
-	set_cpus_allowed(current, mask);
-}
-
-#else
-
-/*
- *	No CPU lockdown needed on a uniprocessor
- */
-
-#define apm_save_cpus()		(current->cpus_allowed)
-#define apm_restore_cpus(x)	(void)(x)
-
-#endif
-
-/*
  * These are the actual BIOS calls.  Depending on APM_ZERO_SEGS and
  * apm_info.allow_ints, we are being really paranoid here!  Not only
  * are interrupts disabled, but all the segment registers (except SS)
@@ -568,16 +539,23 @@ static inline void apm_irq_restore(unsigned long flags)
 #	define APM_DO_RESTORE_SEGS
 #endif
 
+struct apm_bios_call {
+	u32 func;
+	/* In and out */
+	u32 ebx;
+	u32 ecx;
+	/* Out only */
+	u32 eax;
+	u32 edx;
+	u32 esi;
+
+	/* Error: -ENOMEM, or bits 8-15 of eax */
+	int err;
+};
+
 /**
- *	apm_bios_call	-	Make an APM BIOS 32bit call
- *	@func: APM function to execute
- *	@ebx_in: EBX register for call entry
- *	@ecx_in: ECX register for call entry
- *	@eax: EAX register return
- *	@ebx: EBX register return
- *	@ecx: ECX register return
- *	@edx: EDX register return
- *	@esi: ESI register return
+ *	__apm_bios_call - Make an APM BIOS 32bit call
+ *	@_call: pointer to struct apm_bios_call.
  *
  *	Make an APM call using the 32bit protected mode interface. The
  *	caller is responsible for knowing if APM BIOS is configured and
@@ -586,80 +564,142 @@ static inline void apm_irq_restore(unsigned long flags)
  *	flag is loaded into AL.  If there is an error, then the error
  *	code is returned in AH (bits 8-15 of eax) and this function
  *	returns non-zero.
+ *
+ *	Note: this makes the call on the current CPU.
  */
-
-static u8 apm_bios_call(u32 func, u32 ebx_in, u32 ecx_in,
-	u32 *eax, u32 *ebx, u32 *ecx, u32 *edx, u32 *esi)
+static long __apm_bios_call(void *_call)
 {
 	APM_DECL_SEGS
 	unsigned long		flags;
-	cpumask_t		cpus;
 	int			cpu;
 	struct desc_struct	save_desc_40;
 	struct desc_struct	*gdt;
-
-	cpus = apm_save_cpus();
+	struct apm_bios_call	*call = _call;
 
 	cpu = get_cpu();
+	BUG_ON(cpu != 0);
 	gdt = get_cpu_gdt_table(cpu);
 	save_desc_40 = gdt[0x40 / 8];
 	gdt[0x40 / 8] = bad_bios_desc;
 
 	apm_irq_save(flags);
 	APM_DO_SAVE_SEGS;
-	apm_bios_call_asm(func, ebx_in, ecx_in, eax, ebx, ecx, edx, esi);
+	apm_bios_call_asm(call->func, call->ebx, call->ecx,
+			  &call->eax, &call->ebx, &call->ecx, &call->edx,
+			  &call->esi);
 	APM_DO_RESTORE_SEGS;
 	apm_irq_restore(flags);
 	gdt[0x40 / 8] = save_desc_40;
 	put_cpu();
-	apm_restore_cpus(cpus);
 
-	return *eax & 0xff;
+	return call->eax & 0xff;
+}
+
+/* Run __apm_bios_call or __apm_bios_call_simple on CPU 0 */
+static int on_cpu0(long (*fn)(void *), struct apm_bios_call *call)
+{
+	int ret;
+
+	/* Don't bother with work_on_cpu in the common case, so we don't
+	 * have to worry about OOM or overhead. */
+	if (get_cpu() == 0) {
+		ret = fn(call);
+		put_cpu();
+	} else {
+		put_cpu();
+		ret = work_on_cpu(0, fn, call);
+	}
+
+	/* work_on_cpu can fail with -ENOMEM */
+	if (ret < 0)
+		call->err = ret;
+	else
+		call->err = (call->eax >> 8) & 0xff;
+
+	return ret;
 }
 
 /**
- *	apm_bios_call_simple	-	make a simple APM BIOS 32bit call
- *	@func: APM function to invoke
- *	@ebx_in: EBX register value for BIOS call
- *	@ecx_in: ECX register value for BIOS call
- *	@eax: EAX register on return from the BIOS call
+ *	apm_bios_call	-	Make an APM BIOS 32bit call (on CPU 0)
+ *	@call: the apm_bios_call registers.
+ *
+ *	If there is an error, it is returned in @call.err.
+ */
+static int apm_bios_call(struct apm_bios_call *call)
+{
+	return on_cpu0(__apm_bios_call, call);
+}
+
+/**
+ *	__apm_bios_call_simple - Make an APM BIOS 32bit call (on CPU 0)
+ *	@_call: pointer to struct apm_bios_call.
  *
  *	Make a BIOS call that returns one value only, or just status.
  *	If there is an error, then the error code is returned in AH
- *	(bits 8-15 of eax) and this function returns non-zero. This is
- *	used for simpler BIOS operations. This call may hold interrupts
- *	off for a long time on some laptops.
+ *	(bits 8-15 of eax) and this function returns non-zero (it can
+ *	also return -ENOMEM). This is used for simpler BIOS operations.
+ *	This call may hold interrupts off for a long time on some laptops.
+ *
+ *	Note: this makes the call on the current CPU.
  */
-
-static u8 apm_bios_call_simple(u32 func, u32 ebx_in, u32 ecx_in, u32 *eax)
+static long __apm_bios_call_simple(void *_call)
 {
 	u8			error;
 	APM_DECL_SEGS
 	unsigned long		flags;
-	cpumask_t		cpus;
 	int			cpu;
 	struct desc_struct	save_desc_40;
 	struct desc_struct	*gdt;
-
-	cpus = apm_save_cpus();
+	struct apm_bios_call	*call = _call;
 
 	cpu = get_cpu();
+	BUG_ON(cpu != 0);
 	gdt = get_cpu_gdt_table(cpu);
 	save_desc_40 = gdt[0x40 / 8];
 	gdt[0x40 / 8] = bad_bios_desc;
 
 	apm_irq_save(flags);
 	APM_DO_SAVE_SEGS;
-	error = apm_bios_call_simple_asm(func, ebx_in, ecx_in, eax);
+	error = apm_bios_call_simple_asm(call->func, call->ebx, call->ecx,
+					 &call->eax);
 	APM_DO_RESTORE_SEGS;
 	apm_irq_restore(flags);
 	gdt[0x40 / 8] = save_desc_40;
 	put_cpu();
-	apm_restore_cpus(cpus);
 	return error;
 }
 
 /**
+ *	apm_bios_call_simple	-	make a simple APM BIOS 32bit call
+ *	@func: APM function to invoke
+ *	@ebx_in: EBX register value for BIOS call
+ *	@ecx_in: ECX register value for BIOS call
+ *	@eax: EAX register on return from the BIOS call
+ *	@err: bits
+ *
+ *	Make a BIOS call that returns one value only, or just status.
+ *	If there is an error, then the error code is returned in @err
+ *	and this function returns non-zero. This is used for simpler
+ *	BIOS operations.  This call may hold interrupts off for a long
+ *	time on some laptops.
+ */
+static int apm_bios_call_simple(u32 func, u32 ebx_in, u32 ecx_in, u32 *eax,
+				int *err)
+{
+	struct apm_bios_call call;
+	int ret;
+
+	call.func = func;
+	call.ebx = ebx_in;
+	call.ecx = ecx_in;
+
+	ret = on_cpu0(__apm_bios_call_simple, &call);
+	*eax = call.eax;
+	*err = call.err;
+	return ret;
+}
+
+/**
  *	apm_driver_version	-	APM driver version
  *	@val:	loaded with the APM version on return
  *
@@ -678,9 +718,10 @@ static u8 apm_bios_call_simple(u32 func, u32 ebx_in, u32 ecx_in, u32 *eax)
 static int apm_driver_version(u_short *val)
 {
 	u32 eax;
+	int err;
 
-	if (apm_bios_call_simple(APM_FUNC_VERSION, 0, *val, &eax))
-		return (eax >> 8) & 0xff;
+	if (apm_bios_call_simple(APM_FUNC_VERSION, 0, *val, &eax, &err))
+		return err;
 	*val = eax;
 	return APM_SUCCESS;
 }
@@ -701,22 +742,21 @@ static int apm_driver_version(u_short *val)
  *	that APM 1.2 is in use. If no messges are pending the value 0x80
  *	is returned (No power management events pending).
  */
-
 static int apm_get_event(apm_event_t *event, apm_eventinfo_t *info)
 {
-	u32 eax;
-	u32 ebx;
-	u32 ecx;
-	u32 dummy;
+	struct apm_bios_call call;
 
-	if (apm_bios_call(APM_FUNC_GET_EVENT, 0, 0, &eax, &ebx, &ecx,
-			  &dummy, &dummy))
-		return (eax >> 8) & 0xff;
-	*event = ebx;
+	call.func = APM_FUNC_GET_EVENT;
+	call.ebx = call.ecx = 0;
+
+	if (apm_bios_call(&call))
+		return call.err;
+
+	*event = call.ebx;
 	if (apm_info.connection_version < 0x0102)
 		*info = ~0; /* indicate info not valid */
 	else
-		*info = ecx;
+		*info = call.ecx;
 	return APM_SUCCESS;
 }
 
@@ -737,9 +777,10 @@ static int apm_get_event(apm_event_t *event, apm_eventinfo_t *info)
 static int set_power_state(u_short what, u_short state)
 {
 	u32 eax;
+	int err;
 
-	if (apm_bios_call_simple(APM_FUNC_SET_STATE, what, state, &eax))
-		return (eax >> 8) & 0xff;
+	if (apm_bios_call_simple(APM_FUNC_SET_STATE, what, state, &eax, &err))
+		return err;
 	return APM_SUCCESS;
 }
 
@@ -770,6 +811,7 @@ static int apm_do_idle(void)
 	u8 ret = 0;
 	int idled = 0;
 	int polling;
+	int err;
 
 	polling = !!(current_thread_info()->status & TS_POLLING);
 	if (polling) {
@@ -782,7 +824,7 @@ static int apm_do_idle(void)
 	}
 	if (!need_resched()) {
 		idled = 1;
-		ret = apm_bios_call_simple(APM_FUNC_IDLE, 0, 0, &eax);
+		ret = apm_bios_call_simple(APM_FUNC_IDLE, 0, 0, &eax, &err);
 	}
 	if (polling)
 		current_thread_info()->status |= TS_POLLING;
@@ -797,8 +839,7 @@ static int apm_do_idle(void)
 		 * Only report the failure the first 5 times.
 		 */
 		if (++t < 5) {
-			printk(KERN_DEBUG "apm_do_idle failed (%d)\n",
-			       (eax >> 8) & 0xff);
+			printk(KERN_DEBUG "apm_do_idle failed (%d)\n", err);
 			t = jiffies;
 		}
 		return -1;
@@ -816,9 +857,10 @@ static int apm_do_idle(void)
 static void apm_do_busy(void)
 {
 	u32 dummy;
+	int err;
 
 	if (clock_slowed || ALWAYS_CALL_BUSY) {
-		(void)apm_bios_call_simple(APM_FUNC_BUSY, 0, 0, &dummy);
+		(void)apm_bios_call_simple(APM_FUNC_BUSY, 0, 0, &dummy, &err);
 		clock_slowed = 0;
 	}
 }
@@ -937,7 +979,7 @@ static void apm_power_off(void)
 
 	/* Some bioses don't like being called from CPU != 0 */
 	if (apm_info.realmode_power_off) {
-		(void)apm_save_cpus();
+		set_cpus_allowed_ptr(current, cpumask_of(0));
 		machine_real_restart(po_bios_call, sizeof(po_bios_call));
 	} else {
 		(void)set_system_power_state(APM_STATE_OFF);
@@ -956,12 +998,13 @@ static void apm_power_off(void)
 static int apm_enable_power_management(int enable)
 {
 	u32 eax;
+	int err;
 
 	if ((enable == 0) && (apm_info.bios.flags & APM_BIOS_DISENGAGED))
 		return APM_NOT_ENGAGED;
 	if (apm_bios_call_simple(APM_FUNC_ENABLE_PM, APM_DEVICE_BALL,
-				 enable, &eax))
-		return (eax >> 8) & 0xff;
+				 enable, &eax, &err))
+		return err;
 	if (enable)
 		apm_info.bios.flags &= ~APM_BIOS_DISABLED;
 	else
@@ -986,24 +1029,23 @@ static int apm_enable_power_management(int enable)
 
 static int apm_get_power_status(u_short *status, u_short *bat, u_short *life)
 {
-	u32 eax;
-	u32 ebx;
-	u32 ecx;
-	u32 edx;
-	u32 dummy;
+	struct apm_bios_call call;
+
+	call.func = APM_FUNC_GET_STATUS;
+	call.ebx = APM_DEVICE_ALL;
+	call.ecx = 0;
 
 	if (apm_info.get_power_status_broken)
 		return APM_32_UNSUPPORTED;
-	if (apm_bios_call(APM_FUNC_GET_STATUS, APM_DEVICE_ALL, 0,
-			  &eax, &ebx, &ecx, &edx, &dummy))
-		return (eax >> 8) & 0xff;
-	*status = ebx;
-	*bat = ecx;
+	if (apm_bios_call(&call))
+		return call.err;
+	*status = call.ebx;
+	*bat = call.ecx;
 	if (apm_info.get_power_status_swabinminutes) {
-		*life = swab16((u16)edx);
+		*life = swab16((u16)call.edx);
 		*life |= 0x8000;
 	} else
-		*life = edx;
+		*life = call.edx;
 	return APM_SUCCESS;
 }
 
@@ -1048,12 +1090,14 @@ static int apm_get_battery_status(u_short which, u_short *status,
 static int apm_engage_power_management(u_short device, int enable)
 {
 	u32 eax;
+	int err;
 
 	if ((enable == 0) && (device == APM_DEVICE_ALL)
 	    && (apm_info.bios.flags & APM_BIOS_DISABLED))
 		return APM_DISABLED;
-	if (apm_bios_call_simple(APM_FUNC_ENGAGE_PM, device, enable, &eax))
-		return (eax >> 8) & 0xff;
+	if (apm_bios_call_simple(APM_FUNC_ENGAGE_PM, device, enable,
+				 &eax, &err))
+		return err;
 	if (device == APM_DEVICE_ALL) {
 		if (enable)
 			apm_info.bios.flags &= ~APM_BIOS_DISENGAGED;
@@ -1689,16 +1733,14 @@ static int apm(void *unused)
 	char 		*power_stat;
 	char 		*bat_stat;
 
-#ifdef CONFIG_SMP
 	/* 2002/08/01 - WT
 	 * This is to avoid random crashes at boot time during initialization
 	 * on SMP systems in case of "apm=power-off" mode. Seen on ASUS A7M266D.
 	 * Some bioses don't like being called from CPU != 0.
 	 * Method suggested by Ingo Molnar.
 	 */
-	set_cpus_allowed(current, cpumask_of_cpu(0));
+	set_cpus_allowed_ptr(current, cpumask_of(0));
 	BUG_ON(smp_processor_id() != 0);
-#endif
 
 	if (apm_info.connection_version == 0) {
 		apm_info.connection_version = apm_info.bios.version;
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index e2962cc1e27b..c4f667896c28 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -41,8 +41,6 @@
 
 #include "cpu.h"
 
-#ifdef CONFIG_X86_64
-
 /* all of these masks are initialized in setup_cpu_local_masks() */
 cpumask_var_t cpu_initialized_mask;
 cpumask_var_t cpu_callout_mask;
@@ -60,16 +58,6 @@ void __init setup_cpu_local_masks(void)
 	alloc_bootmem_cpumask_var(&cpu_sibling_setup_mask);
 }
 
-#else /* CONFIG_X86_32 */
-
-cpumask_t cpu_sibling_setup_map;
-cpumask_t cpu_callout_map;
-cpumask_t cpu_initialized;
-cpumask_t cpu_callin_map;
-
-#endif /* CONFIG_X86_32 */
-
-
 static const struct cpu_dev *this_cpu __cpuinitdata;
 
 DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = {
@@ -859,6 +847,7 @@ static void vgetcpu_set_mode(void)
 void __init identify_boot_cpu(void)
 {
 	identify_cpu(&boot_cpu_data);
+	init_c1e_mask();
 #ifdef CONFIG_X86_32
 	sysenter_setup();
 	enable_sep_cpu();
diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
index 23da96e57b17..19f6b9d27e83 100644
--- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
+++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
@@ -33,7 +33,7 @@
 #include <linux/cpufreq.h>
 #include <linux/compiler.h>
 #include <linux/dmi.h>
-#include <linux/ftrace.h>
+#include <trace/power.h>
 
 #include <linux/acpi.h>
 #include <linux/io.h>
@@ -72,6 +72,8 @@ struct acpi_cpufreq_data {
 
 static DEFINE_PER_CPU(struct acpi_cpufreq_data *, drv_data);
 
+DEFINE_TRACE(power_mark);
+
 /* acpi_perf_data is a pointer to percpu data. */
 static struct acpi_processor_performance *acpi_perf_data;
 
@@ -680,6 +682,18 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
 			    perf->states[i].transition_latency * 1000;
 	}
 
+	/* Check for high latency (>20uS) from buggy BIOSes, like on T42 */
+	if (perf->control_register.space_id == ACPI_ADR_SPACE_FIXED_HARDWARE &&
+	    policy->cpuinfo.transition_latency > 20 * 1000) {
+		static int print_once;
+		policy->cpuinfo.transition_latency = 20 * 1000;
+		if (!print_once) {
+			print_once = 1;
+			printk(KERN_INFO "Capping off P-state tranision latency"
+				" at 20 uS\n");
+		}
+	}
+
 	data->max_freq = perf->states[0].core_frequency * 1000;
 	/* table init */
 	for (i = 0; i < perf->state_count; i++) {
diff --git a/arch/x86/kernel/cpu/cpufreq/longhaul.c b/arch/x86/kernel/cpu/cpufreq/longhaul.c
index f1c51aea064d..0bd48e65a0ca 100644
--- a/arch/x86/kernel/cpu/cpufreq/longhaul.c
+++ b/arch/x86/kernel/cpu/cpufreq/longhaul.c
@@ -305,7 +305,7 @@ retry_loop:
 		outb(3, 0x22);
 	} else if ((pr != NULL) && pr->flags.bm_control) {
 		/* Disable bus master arbitration */
-		acpi_set_register(ACPI_BITREG_ARB_DISABLE, 1);
+		acpi_write_bit_register(ACPI_BITREG_ARB_DISABLE, 1);
 	}
 	switch (longhaul_version) {
 
@@ -328,7 +328,7 @@ retry_loop:
 	case TYPE_POWERSAVER:
 		if (longhaul_flags & USE_ACPI_C3) {
 			/* Don't allow wakeup */
-			acpi_set_register(ACPI_BITREG_BUS_MASTER_RLD, 0);
+			acpi_write_bit_register(ACPI_BITREG_BUS_MASTER_RLD, 0);
 			do_powersaver(cx->address, mults_index, dir);
 		} else {
 			do_powersaver(0, mults_index, dir);
@@ -341,7 +341,7 @@ retry_loop:
 		outb(0, 0x22);
 	} else if ((pr != NULL) && pr->flags.bm_control) {
 		/* Enable bus master arbitration */
-		acpi_set_register(ACPI_BITREG_ARB_DISABLE, 0);
+		acpi_write_bit_register(ACPI_BITREG_ARB_DISABLE, 0);
 	}
 	outb(pic2_mask, 0xA1);	/* restore mask */
 	outb(pic1_mask, 0x21);
diff --git a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c
index 41ed94915f97..6ac55bd341ae 100644
--- a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c
+++ b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c
@@ -211,7 +211,7 @@ static int cpufreq_p4_cpu_init(struct cpufreq_policy *policy)
 	unsigned int i;
 
 #ifdef CONFIG_SMP
-	cpumask_copy(policy->cpus, &per_cpu(cpu_sibling_map, policy->cpu));
+	cpumask_copy(policy->cpus, cpu_sibling_mask(policy->cpu));
 #endif
 
 	/* Errata workaround */
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
index a15ac94e0b9b..4709ead2db52 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
@@ -54,7 +54,10 @@ static DEFINE_PER_CPU(struct powernow_k8_data *, powernow_data);
 static int cpu_family = CPU_OPTERON;
 
 #ifndef CONFIG_SMP
-DEFINE_PER_CPU(cpumask_t, cpu_core_map);
+static inline const struct cpumask *cpu_core_mask(int cpu)
+{
+	return cpumask_of(0);
+}
 #endif
 
 /* Return a frequency in MHz, given an input fid */
@@ -699,7 +702,7 @@ static int fill_powernow_table(struct powernow_k8_data *data,
 
 	dprintk("cfid 0x%x, cvid 0x%x\n", data->currfid, data->currvid);
 	data->powernow_table = powernow_table;
-	if (first_cpu(per_cpu(cpu_core_map, data->cpu)) == data->cpu)
+	if (cpumask_first(cpu_core_mask(data->cpu)) == data->cpu)
 		print_basics(data);
 
 	for (j = 0; j < data->numps; j++)
@@ -862,7 +865,7 @@ static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data)
 
 	/* fill in data */
 	data->numps = data->acpi_data.state_count;
-	if (first_cpu(per_cpu(cpu_core_map, data->cpu)) == data->cpu)
+	if (cpumask_first(cpu_core_mask(data->cpu)) == data->cpu)
 		print_basics(data);
 	powernow_k8_acpi_pst_values(data, 0);
 
@@ -1300,7 +1303,7 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
 	if (cpu_family == CPU_HW_PSTATE)
 		cpumask_copy(pol->cpus, cpumask_of(pol->cpu));
 	else
-		cpumask_copy(pol->cpus, &per_cpu(cpu_core_map, pol->cpu));
+		cpumask_copy(pol->cpus, cpu_core_mask(pol->cpu));
 	data->available_cores = pol->cpus;
 
 	if (cpu_family == CPU_HW_PSTATE)
@@ -1365,7 +1368,7 @@ static unsigned int powernowk8_get(unsigned int cpu)
 	unsigned int khz = 0;
 	unsigned int first;
 
-	first = first_cpu(per_cpu(cpu_core_map, cpu));
+	first = cpumask_first(cpu_core_mask(cpu));
 	data = per_cpu(powernow_data, first);
 
 	if (!data)
diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c b/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c
index 8bbb11adb315..016c1a4fa3fc 100644
--- a/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c
+++ b/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c
@@ -321,7 +321,7 @@ static int speedstep_cpu_init(struct cpufreq_policy *policy)
 
 	/* only run on CPU to be set, or on its sibling */
 #ifdef CONFIG_SMP
-	cpumask_copy(policy->cpus, &per_cpu(cpu_sibling_map, policy->cpu));
+	cpumask_copy(policy->cpus, cpu_sibling_mask(policy->cpu));
 #endif
 
 	cpus_allowed = current->cpus_allowed;
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index c471eb1a389c..483eda96e102 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -159,7 +159,7 @@ struct _cpuid4_info_regs {
 	unsigned long can_disable;
 };
 
-#ifdef CONFIG_PCI
+#if defined(CONFIG_PCI) && defined(CONFIG_SYSFS)
 static struct pci_device_id k8_nb_id[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, 0x1103) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, 0x1203) },
@@ -324,15 +324,6 @@ __cpuinit cpuid4_cache_lookup_regs(int index,
 	return 0;
 }
 
-static int
-__cpuinit cpuid4_cache_lookup(int index, struct _cpuid4_info *this_leaf)
-{
-	struct _cpuid4_info_regs *leaf_regs =
-		(struct _cpuid4_info_regs *)this_leaf;
-
-	return cpuid4_cache_lookup_regs(index, leaf_regs);
-}
-
 static int __cpuinit find_num_cache_leaves(void)
 {
 	unsigned int		eax, ebx, ecx, edx;
@@ -508,6 +499,8 @@ unsigned int __cpuinit init_intel_cacheinfo(struct cpuinfo_x86 *c)
 	return l2;
 }
 
+#ifdef CONFIG_SYSFS
+
 /* pointer to _cpuid4_info array (for each cache leaf) */
 static DEFINE_PER_CPU(struct _cpuid4_info *, cpuid4_info);
 #define CPUID4_INFO_IDX(x, y)	(&((per_cpu(cpuid4_info, x))[y]))
@@ -571,6 +564,15 @@ static void __cpuinit free_cache_attributes(unsigned int cpu)
 	per_cpu(cpuid4_info, cpu) = NULL;
 }
 
+static int
+__cpuinit cpuid4_cache_lookup(int index, struct _cpuid4_info *this_leaf)
+{
+	struct _cpuid4_info_regs *leaf_regs =
+		(struct _cpuid4_info_regs *)this_leaf;
+
+	return cpuid4_cache_lookup_regs(index, leaf_regs);
+}
+
 static void __cpuinit get_cpu_leaves(void *_retval)
 {
 	int j, *retval = _retval, cpu = smp_processor_id();
@@ -612,8 +614,6 @@ static int __cpuinit detect_cache_attributes(unsigned int cpu)
 	return retval;
 }
 
-#ifdef CONFIG_SYSFS
-
 #include <linux/kobject.h>
 #include <linux/sysfs.h>
 
diff --git a/arch/x86/kernel/cpu/mcheck/mce_64.c b/arch/x86/kernel/cpu/mcheck/mce_64.c
index ca14604611ec..863f89568b1a 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_64.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_64.c
@@ -990,7 +990,7 @@ static struct sysdev_attribute *mce_attributes[] = {
 	NULL
 };
 
-static cpumask_t mce_device_initialized = CPU_MASK_NONE;
+static cpumask_var_t mce_device_initialized;
 
 /* Per cpu sysdev init.  All of the cpus still share the same ctl bank */
 static __cpuinit int mce_create_device(unsigned int cpu)
@@ -1021,7 +1021,7 @@ static __cpuinit int mce_create_device(unsigned int cpu)
 		if (err)
 			goto error2;
 	}
-	cpu_set(cpu, mce_device_initialized);
+	cpumask_set_cpu(cpu, mce_device_initialized);
 
 	return 0;
 error2:
@@ -1043,7 +1043,7 @@ static __cpuinit void mce_remove_device(unsigned int cpu)
 {
 	int i;
 
-	if (!cpu_isset(cpu, mce_device_initialized))
+	if (!cpumask_test_cpu(cpu, mce_device_initialized))
 		return;
 
 	for (i = 0; mce_attributes[i]; i++)
@@ -1053,7 +1053,7 @@ static __cpuinit void mce_remove_device(unsigned int cpu)
 		sysdev_remove_file(&per_cpu(device_mce, cpu),
 			&bank_attrs[i]);
 	sysdev_unregister(&per_cpu(device_mce,cpu));
-	cpu_clear(cpu, mce_device_initialized);
+	cpumask_clear_cpu(cpu, mce_device_initialized);
 }
 
 /* Make sure there are no machine checks on offlined CPUs. */
@@ -1162,6 +1162,8 @@ static __init int mce_init_device(void)
 	if (!mce_available(&boot_cpu_data))
 		return -EIO;
 
+	alloc_cpumask_var(&mce_device_initialized, GFP_KERNEL);
+
 	err = mce_init_banks();
 	if (err)
 		return err;
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd_64.c b/arch/x86/kernel/cpu/mcheck/mce_amd_64.c
index 7d01be868870..56dde9c4bc96 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd_64.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd_64.c
@@ -485,7 +485,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
 
 #ifdef CONFIG_SMP
 	if (cpu_data(cpu).cpu_core_id && shared_bank[bank]) {	/* symlink */
-		i = cpumask_first(&per_cpu(cpu_core_map, cpu));
+		i = cpumask_first(cpu_core_mask(cpu));
 
 		/* first core not up yet */
 		if (cpu_data(i).cpu_core_id)
@@ -505,7 +505,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
 		if (err)
 			goto out;
 
-		cpumask_copy(b->cpus, &per_cpu(cpu_core_map, cpu));
+		cpumask_copy(b->cpus, cpu_core_mask(cpu));
 		per_cpu(threshold_banks, cpu)[bank] = b;
 		goto out;
 	}
@@ -529,7 +529,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
 #ifndef CONFIG_SMP
 	cpumask_setall(b->cpus);
 #else
-	cpumask_copy(b->cpus, &per_cpu(cpu_core_map, cpu));
+	cpumask_copy(b->cpus, cpu_core_mask(cpu));
 #endif
 
 	per_cpu(threshold_banks, cpu)[bank] = b;
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel_64.c b/arch/x86/kernel/cpu/mcheck/mce_intel_64.c
index 57df3d383470..d6b72df89d69 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel_64.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel_64.c
@@ -249,7 +249,7 @@ void cmci_rediscover(int dying)
 	for_each_online_cpu (cpu) {
 		if (cpu == dying)
 			continue;
-		if (set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu)))
+		if (set_cpus_allowed_ptr(current, cpumask_of(cpu)))
 			continue;
 		/* Recheck banks in case CPUs don't all have the same */
 		if (cmci_supported(&banks))
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index 37f28fc7cf95..0b776c09aff3 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -462,9 +462,6 @@ static void generic_get_mtrr(unsigned int reg, unsigned long *base,
 	*base = base_hi << (32 - PAGE_SHIFT) | base_lo >> PAGE_SHIFT;
 	*type = base_lo & 0xff;
 
-	printk(KERN_DEBUG "  get_mtrr: cpu%d reg%02d base=%010lx size=%010lx %s\n",
-			cpu, reg, *base, *size,
-			mtrr_attrib_to_str(*type & 0xff));
 out_put_cpu:
 	put_cpu();
 }
diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c
index d67e0e48bc2d..f93047fed791 100644
--- a/arch/x86/kernel/cpu/proc.c
+++ b/arch/x86/kernel/cpu/proc.c
@@ -14,7 +14,7 @@ static void show_cpuinfo_core(struct seq_file *m, struct cpuinfo_x86 *c,
 	if (c->x86_max_cores * smp_num_siblings > 1) {
 		seq_printf(m, "physical id\t: %d\n", c->phys_proc_id);
 		seq_printf(m, "siblings\t: %d\n",
-			   cpus_weight(per_cpu(cpu_core_map, cpu)));
+			   cpumask_weight(cpu_sibling_mask(cpu)));
 		seq_printf(m, "core id\t\t: %d\n", c->cpu_core_id);
 		seq_printf(m, "cpu cores\t: %d\n", c->booted_cores);
 		seq_printf(m, "apicid\t\t: %d\n", c->apicid);
@@ -143,9 +143,9 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 static void *c_start(struct seq_file *m, loff_t *pos)
 {
 	if (*pos == 0)	/* just in case, cpu 0 is not the first */
-		*pos = first_cpu(cpu_online_map);
+		*pos = cpumask_first(cpu_online_mask);
 	else
-		*pos = next_cpu_nr(*pos - 1, cpu_online_map);
+		*pos = cpumask_next(*pos - 1, cpu_online_mask);
 	if ((*pos) < nr_cpu_ids)
 		return &cpu_data(*pos);
 	return NULL;
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index dd2130b0fb3e..95ea5fa7d444 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -15,6 +15,7 @@
 #include <linux/bug.h>
 #include <linux/nmi.h>
 #include <linux/sysfs.h>
+#include <linux/ftrace.h>
 
 #include <asm/stacktrace.h>
 
@@ -196,6 +197,11 @@ unsigned __kprobes long oops_begin(void)
 	int cpu;
 	unsigned long flags;
 
+	/* notify the hw-branch tracer so it may disable tracing and
+	   add the last trace to the trace buffer -
+	   the earlier this happens, the more useful the trace. */
+	trace_hw_branch_oops();
+
 	oops_enter();
 
 	/* racy, but better than risking deadlock. */
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 76f7141e0f91..70a10ca100f6 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -18,14 +18,26 @@
 #include <linux/init.h>
 #include <linux/list.h>
 
+#include <asm/cacheflush.h>
 #include <asm/ftrace.h>
-#include <linux/ftrace.h>
 #include <asm/nops.h>
 #include <asm/nmi.h>
 
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 
+int ftrace_arch_code_modify_prepare(void)
+{
+	set_kernel_text_rw();
+	return 0;
+}
+
+int ftrace_arch_code_modify_post_process(void)
+{
+	set_kernel_text_ro();
+	return 0;
+}
+
 union ftrace_code_union {
 	char code[MCOUNT_INSN_SIZE];
 	struct {
@@ -66,11 +78,11 @@ static unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
  *
  * 1) Put the instruction pointer into the IP buffer
  *    and the new code into the "code" buffer.
- * 2) Set a flag that says we are modifying code
- * 3) Wait for any running NMIs to finish.
- * 4) Write the code
- * 5) clear the flag.
- * 6) Wait for any running NMIs to finish.
+ * 2) Wait for any running NMIs to finish and set a flag that says
+ *    we are modifying code, it is done in an atomic operation.
+ * 3) Write the code
+ * 4) clear the flag.
+ * 5) Wait for any running NMIs to finish.
  *
  * If an NMI is executed, the first thing it does is to call
  * "ftrace_nmi_enter". This will check if the flag is set to write
@@ -82,9 +94,9 @@ static unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
  * are the same as what exists.
  */
 
-static atomic_t in_nmi = ATOMIC_INIT(0);
+#define MOD_CODE_WRITE_FLAG (1 << 31)	/* set when NMI should do the write */
+static atomic_t nmi_running = ATOMIC_INIT(0);
 static int mod_code_status;		/* holds return value of text write */
-static int mod_code_write;		/* set when NMI should do the write */
 static void *mod_code_ip;		/* holds the IP to write to */
 static void *mod_code_newcode;		/* holds the text to write to the IP */
 
@@ -101,6 +113,20 @@ int ftrace_arch_read_dyn_info(char *buf, int size)
 	return r;
 }
 
+static void clear_mod_flag(void)
+{
+	int old = atomic_read(&nmi_running);
+
+	for (;;) {
+		int new = old & ~MOD_CODE_WRITE_FLAG;
+
+		if (old == new)
+			break;
+
+		old = atomic_cmpxchg(&nmi_running, old, new);
+	}
+}
+
 static void ftrace_mod_code(void)
 {
 	/*
@@ -111,37 +137,52 @@ static void ftrace_mod_code(void)
 	 */
 	mod_code_status = probe_kernel_write(mod_code_ip, mod_code_newcode,
 					     MCOUNT_INSN_SIZE);
+
+	/* if we fail, then kill any new writers */
+	if (mod_code_status)
+		clear_mod_flag();
 }
 
 void ftrace_nmi_enter(void)
 {
-	atomic_inc(&in_nmi);
-	/* Must have in_nmi seen before reading write flag */
-	smp_mb();
-	if (mod_code_write) {
+	if (atomic_inc_return(&nmi_running) & MOD_CODE_WRITE_FLAG) {
+		smp_rmb();
 		ftrace_mod_code();
 		atomic_inc(&nmi_update_count);
 	}
+	/* Must have previous changes seen before executions */
+	smp_mb();
 }
 
 void ftrace_nmi_exit(void)
 {
-	/* Finish all executions before clearing in_nmi */
-	smp_wmb();
-	atomic_dec(&in_nmi);
+	/* Finish all executions before clearing nmi_running */
+	smp_mb();
+	atomic_dec(&nmi_running);
+}
+
+static void wait_for_nmi_and_set_mod_flag(void)
+{
+	if (!atomic_cmpxchg(&nmi_running, 0, MOD_CODE_WRITE_FLAG))
+		return;
+
+	do {
+		cpu_relax();
+	} while (atomic_cmpxchg(&nmi_running, 0, MOD_CODE_WRITE_FLAG));
+
+	nmi_wait_count++;
 }
 
 static void wait_for_nmi(void)
 {
-	int waited = 0;
+	if (!atomic_read(&nmi_running))
+		return;
 
-	while (atomic_read(&in_nmi)) {
-		waited = 1;
+	do {
 		cpu_relax();
-	}
+	} while (atomic_read(&nmi_running));
 
-	if (waited)
-		nmi_wait_count++;
+	nmi_wait_count++;
 }
 
 static int
@@ -151,14 +192,9 @@ do_ftrace_mod_code(unsigned long ip, void *new_code)
 	mod_code_newcode = new_code;
 
 	/* The buffers need to be visible before we let NMIs write them */
-	smp_wmb();
-
-	mod_code_write = 1;
-
-	/* Make sure write bit is visible before we wait on NMIs */
 	smp_mb();
 
-	wait_for_nmi();
+	wait_for_nmi_and_set_mod_flag();
 
 	/* Make sure all running NMIs have finished before we write the code */
 	smp_mb();
@@ -166,13 +202,9 @@ do_ftrace_mod_code(unsigned long ip, void *new_code)
 	ftrace_mod_code();
 
 	/* Make sure the write happens before clearing the bit */
-	smp_wmb();
-
-	mod_code_write = 0;
-
-	/* make sure NMIs see the cleared bit */
 	smp_mb();
 
+	clear_mod_flag();
 	wait_for_nmi();
 
 	return mod_code_status;
@@ -368,25 +400,6 @@ int ftrace_disable_ftrace_graph_caller(void)
 	return ftrace_mod_jmp(ip, old_offset, new_offset);
 }
 
-#else /* CONFIG_DYNAMIC_FTRACE */
-
-/*
- * These functions are picked from those used on
- * this page for dynamic ftrace. They have been
- * simplified to ignore all traces in NMI context.
- */
-static atomic_t in_nmi;
-
-void ftrace_nmi_enter(void)
-{
-	atomic_inc(&in_nmi);
-}
-
-void ftrace_nmi_exit(void)
-{
-	atomic_dec(&in_nmi);
-}
-
 #endif /* !CONFIG_DYNAMIC_FTRACE */
 
 /*
@@ -396,14 +409,13 @@ void ftrace_nmi_exit(void)
 void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr)
 {
 	unsigned long old;
-	unsigned long long calltime;
 	int faulted;
 	struct ftrace_graph_ent trace;
 	unsigned long return_hooker = (unsigned long)
 				&return_to_handler;
 
 	/* Nmi's are currently unsupported */
-	if (unlikely(atomic_read(&in_nmi)))
+	if (unlikely(in_nmi()))
 		return;
 
 	if (unlikely(atomic_read(&current->tracing_graph_pause)))
@@ -439,17 +451,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr)
 		return;
 	}
 
-	if (unlikely(!__kernel_text_address(old))) {
-		ftrace_graph_stop();
-		*parent = old;
-		WARN_ON(1);
-		return;
-	}
-
-	calltime = cpu_clock(raw_smp_processor_id());
-
-	if (ftrace_push_return_trace(old, calltime,
-				self_addr, &trace.depth) == -EBUSY) {
+	if (ftrace_push_return_trace(old, self_addr, &trace.depth) == -EBUSY) {
 		*parent = old;
 		return;
 	}
@@ -463,3 +465,66 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr)
 	}
 }
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
+#ifdef CONFIG_FTRACE_SYSCALLS
+
+extern unsigned long __start_syscalls_metadata[];
+extern unsigned long __stop_syscalls_metadata[];
+extern unsigned long *sys_call_table;
+
+static struct syscall_metadata **syscalls_metadata;
+
+static struct syscall_metadata *find_syscall_meta(unsigned long *syscall)
+{
+	struct syscall_metadata *start;
+	struct syscall_metadata *stop;
+	char str[KSYM_SYMBOL_LEN];
+
+
+	start = (struct syscall_metadata *)__start_syscalls_metadata;
+	stop = (struct syscall_metadata *)__stop_syscalls_metadata;
+	kallsyms_lookup((unsigned long) syscall, NULL, NULL, NULL, str);
+
+	for ( ; start < stop; start++) {
+		if (start->name && !strcmp(start->name, str))
+			return start;
+	}
+	return NULL;
+}
+
+struct syscall_metadata *syscall_nr_to_meta(int nr)
+{
+	if (!syscalls_metadata || nr >= FTRACE_SYSCALL_MAX || nr < 0)
+		return NULL;
+
+	return syscalls_metadata[nr];
+}
+
+void arch_init_ftrace_syscalls(void)
+{
+	int i;
+	struct syscall_metadata *meta;
+	unsigned long **psys_syscall_table = &sys_call_table;
+	static atomic_t refs;
+
+	if (atomic_inc_return(&refs) != 1)
+		goto end;
+
+	syscalls_metadata = kzalloc(sizeof(*syscalls_metadata) *
+					FTRACE_SYSCALL_MAX, GFP_KERNEL);
+	if (!syscalls_metadata) {
+		WARN_ON(1);
+		return;
+	}
+
+	for (i = 0; i < FTRACE_SYSCALL_MAX; i++) {
+		meta = find_syscall_meta(psys_syscall_table[i]);
+		syscalls_metadata[i] = meta;
+	}
+	return;
+
+	/* Paranoid: avoid overflow */
+end:
+	atomic_dec(&refs);
+}
+#endif
diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c
index 55b94614e348..7b5169d2b000 100644
--- a/arch/x86/kernel/kprobes.c
+++ b/arch/x86/kernel/kprobes.c
@@ -638,13 +638,13 @@ static void __used __kprobes kretprobe_trampoline_holder(void)
 #else
 			"	pushf\n"
 			/*
-			 * Skip cs, ip, orig_ax.
+			 * Skip cs, ip, orig_ax and gs.
 			 * trampoline_handler() will plug in these values
 			 */
-			"	subl $12, %esp\n"
+			"	subl $16, %esp\n"
 			"	pushl %fs\n"
-			"	pushl %ds\n"
 			"	pushl %es\n"
+			"	pushl %ds\n"
 			"	pushl %eax\n"
 			"	pushl %ebp\n"
 			"	pushl %edi\n"
@@ -655,10 +655,10 @@ static void __used __kprobes kretprobe_trampoline_holder(void)
 			"	movl %esp, %eax\n"
 			"	call trampoline_handler\n"
 			/* Move flags to cs */
-			"	movl 52(%esp), %edx\n"
-			"	movl %edx, 48(%esp)\n"
+			"	movl 56(%esp), %edx\n"
+			"	movl %edx, 52(%esp)\n"
 			/* Replace saved flags with true return address. */
-			"	movl %eax, 52(%esp)\n"
+			"	movl %eax, 56(%esp)\n"
 			"	popl %ebx\n"
 			"	popl %ecx\n"
 			"	popl %edx\n"
@@ -666,8 +666,8 @@ static void __used __kprobes kretprobe_trampoline_holder(void)
 			"	popl %edi\n"
 			"	popl %ebp\n"
 			"	popl %eax\n"
-			/* Skip ip, orig_ax, es, ds, fs */
-			"	addl $20, %esp\n"
+			/* Skip ds, es, fs, gs, orig_ax and ip */
+			"	addl $24, %esp\n"
 			"	popf\n"
 #endif
 			"	ret\n");
@@ -691,6 +691,7 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs)
 	regs->cs = __KERNEL_CS;
 #else
 	regs->cs = __KERNEL_CS | get_kernel_rpl();
+	regs->gs = 0;
 #endif
 	regs->ip = trampoline_address;
 	regs->orig_ax = ~0UL;
diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c
index c25fdb382292..453b5795a5c6 100644
--- a/arch/x86/kernel/microcode_amd.c
+++ b/arch/x86/kernel/microcode_amd.c
@@ -12,31 +12,30 @@
  *
  *  Licensed under the terms of the GNU General Public
  *  License version 2. See file COPYING for details.
-*/
-
+ */
+#include <linux/platform_device.h>
 #include <linux/capability.h>
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/sched.h>
-#include <linux/cpumask.h>
-#include <linux/module.h>
-#include <linux/slab.h>
-#include <linux/vmalloc.h>
 #include <linux/miscdevice.h>
+#include <linux/firmware.h>
 #include <linux/spinlock.h>
-#include <linux/mm.h>
-#include <linux/fs.h>
+#include <linux/cpumask.h>
+#include <linux/pci_ids.h>
+#include <linux/uaccess.h>
+#include <linux/vmalloc.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
 #include <linux/mutex.h>
+#include <linux/sched.h>
+#include <linux/init.h>
+#include <linux/slab.h>
 #include <linux/cpu.h>
-#include <linux/firmware.h>
-#include <linux/platform_device.h>
 #include <linux/pci.h>
-#include <linux/pci_ids.h>
-#include <linux/uaccess.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
 
-#include <asm/msr.h>
-#include <asm/processor.h>
 #include <asm/microcode.h>
+#include <asm/processor.h>
+#include <asm/msr.h>
 
 MODULE_DESCRIPTION("AMD Microcode Update Driver");
 MODULE_AUTHOR("Peter Oruba");
@@ -72,8 +71,8 @@ struct microcode_header_amd {
 } __attribute__((packed));
 
 struct microcode_amd {
-	struct microcode_header_amd hdr;
-	unsigned int mpb[0];
+	struct microcode_header_amd	hdr;
+	unsigned int			mpb[0];
 };
 
 #define UCODE_MAX_SIZE			2048
@@ -184,8 +183,8 @@ static int get_ucode_data(void *to, const u8 *from, size_t n)
 	return 0;
 }
 
-static void *get_next_ucode(const u8 *buf, unsigned int size,
-			    unsigned int *mc_size)
+static void *
+get_next_ucode(const u8 *buf, unsigned int size, unsigned int *mc_size)
 {
 	unsigned int total_size;
 	u8 section_hdr[UCODE_CONTAINER_SECTION_HDR];
@@ -223,7 +222,6 @@ static void *get_next_ucode(const u8 *buf, unsigned int size,
 	return mc;
 }
 
-
 static int install_equiv_cpu_table(const u8 *buf)
 {
 	u8 *container_hdr[UCODE_CONTAINER_HEADER_SIZE];
@@ -372,4 +370,3 @@ struct microcode_ops * __init init_amd_microcode(void)
 {
 	return &microcode_amd_ops;
 }
-
diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c
index c9b721ba968c..a0f3851ef310 100644
--- a/arch/x86/kernel/microcode_core.c
+++ b/arch/x86/kernel/microcode_core.c
@@ -70,67 +70,78 @@
  *		Fix sigmatch() macro to handle old CPUs with pf == 0.
  *		Thanks to Stuart Swales for pointing out this bug.
  */
+#include <linux/platform_device.h>
 #include <linux/capability.h>
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/sched.h>
+#include <linux/miscdevice.h>
+#include <linux/firmware.h>
 #include <linux/smp_lock.h>
+#include <linux/spinlock.h>
 #include <linux/cpumask.h>
-#include <linux/module.h>
-#include <linux/slab.h>
+#include <linux/uaccess.h>
 #include <linux/vmalloc.h>
-#include <linux/miscdevice.h>
-#include <linux/spinlock.h>
-#include <linux/mm.h>
-#include <linux/fs.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
 #include <linux/mutex.h>
+#include <linux/sched.h>
+#include <linux/init.h>
+#include <linux/slab.h>
 #include <linux/cpu.h>
-#include <linux/firmware.h>
-#include <linux/platform_device.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
 
-#include <asm/msr.h>
-#include <asm/uaccess.h>
-#include <asm/processor.h>
 #include <asm/microcode.h>
+#include <asm/processor.h>
+#include <asm/msr.h>
 
 MODULE_DESCRIPTION("Microcode Update Driver");
 MODULE_AUTHOR("Tigran Aivazian <tigran@aivazian.fsnet.co.uk>");
 MODULE_LICENSE("GPL");
 
-#define MICROCODE_VERSION 	"2.00"
+#define MICROCODE_VERSION	"2.00"
 
-static struct microcode_ops *microcode_ops;
+static struct microcode_ops	*microcode_ops;
 
 /* no concurrent ->write()s are allowed on /dev/cpu/microcode */
 static DEFINE_MUTEX(microcode_mutex);
 
-struct ucode_cpu_info ucode_cpu_info[NR_CPUS];
+struct ucode_cpu_info		ucode_cpu_info[NR_CPUS];
 EXPORT_SYMBOL_GPL(ucode_cpu_info);
 
 #ifdef CONFIG_MICROCODE_OLD_INTERFACE
+struct update_for_cpu {
+	const void __user	*buf;
+	size_t			size;
+};
+
+static long update_for_cpu(void *_ufc)
+{
+	struct update_for_cpu *ufc = _ufc;
+	int error;
+
+	error = microcode_ops->request_microcode_user(smp_processor_id(),
+						      ufc->buf, ufc->size);
+	if (error < 0)
+		return error;
+	if (!error)
+		microcode_ops->apply_microcode(smp_processor_id());
+	return error;
+}
+
 static int do_microcode_update(const void __user *buf, size_t size)
 {
-	cpumask_t old;
 	int error = 0;
 	int cpu;
-
-	old = current->cpus_allowed;
+	struct update_for_cpu ufc = { .buf = buf, .size = size };
 
 	for_each_online_cpu(cpu) {
 		struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
 
 		if (!uci->valid)
 			continue;
-
-		set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu));
-		error = microcode_ops->request_microcode_user(cpu, buf, size);
+		error = work_on_cpu(cpu, update_for_cpu, &ufc);
 		if (error < 0)
-			goto out;
-		if (!error)
-			microcode_ops->apply_microcode(cpu);
+			break;
 	}
-out:
-	set_cpus_allowed_ptr(current, &old);
 	return error;
 }
 
@@ -198,18 +209,33 @@ static void microcode_dev_exit(void)
 
 MODULE_ALIAS_MISCDEV(MICROCODE_MINOR);
 #else
-#define microcode_dev_init() 0
-#define microcode_dev_exit() do { } while (0)
+#define microcode_dev_init()	0
+#define microcode_dev_exit()	do { } while (0)
 #endif
 
 /* fake device for request_firmware */
-static struct platform_device *microcode_pdev;
+static struct platform_device	*microcode_pdev;
+
+static long reload_for_cpu(void *unused)
+{
+	struct ucode_cpu_info *uci = ucode_cpu_info + smp_processor_id();
+	int err = 0;
+
+	mutex_lock(&microcode_mutex);
+	if (uci->valid) {
+		err = microcode_ops->request_microcode_fw(smp_processor_id(),
+							  &microcode_pdev->dev);
+		if (!err)
+			microcode_ops->apply_microcode(smp_processor_id());
+	}
+	mutex_unlock(&microcode_mutex);
+	return err;
+}
 
 static ssize_t reload_store(struct sys_device *dev,
 			    struct sysdev_attribute *attr,
 			    const char *buf, size_t sz)
 {
-	struct ucode_cpu_info *uci = ucode_cpu_info + dev->id;
 	char *end;
 	unsigned long val = simple_strtoul(buf, &end, 0);
 	int err = 0;
@@ -218,21 +244,9 @@ static ssize_t reload_store(struct sys_device *dev,
 	if (end == buf)
 		return -EINVAL;
 	if (val == 1) {
-		cpumask_t old = current->cpus_allowed;
-
 		get_online_cpus();
-		if (cpu_online(cpu)) {
-			set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu));
-			mutex_lock(&microcode_mutex);
-			if (uci->valid) {
-				err = microcode_ops->request_microcode_fw(cpu,
-						&microcode_pdev->dev);
-				if (!err)
-					microcode_ops->apply_microcode(cpu);
-			}
-			mutex_unlock(&microcode_mutex);
-			set_cpus_allowed_ptr(current, &old);
-		}
+		if (cpu_online(cpu))
+			err = work_on_cpu(cpu, reload_for_cpu, NULL);
 		put_online_cpus();
 	}
 	if (err)
@@ -268,8 +282,8 @@ static struct attribute *mc_default_attrs[] = {
 };
 
 static struct attribute_group mc_attr_group = {
-	.attrs = mc_default_attrs,
-	.name = "microcode",
+	.attrs		= mc_default_attrs,
+	.name		= "microcode",
 };
 
 static void __microcode_fini_cpu(int cpu)
@@ -328,9 +342,9 @@ static int microcode_resume_cpu(int cpu)
 	return 0;
 }
 
-static void microcode_update_cpu(int cpu)
+static long microcode_update_cpu(void *unused)
 {
-	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
+	struct ucode_cpu_info *uci = ucode_cpu_info + smp_processor_id();
 	int err = 0;
 
 	/*
@@ -338,30 +352,27 @@ static void microcode_update_cpu(int cpu)
 	 * otherwise just request a firmware:
 	 */
 	if (uci->valid) {
-		err = microcode_resume_cpu(cpu);
-	} else {	
-		collect_cpu_info(cpu);
+		err = microcode_resume_cpu(smp_processor_id());
+	} else {
+		collect_cpu_info(smp_processor_id());
 		if (uci->valid && system_state == SYSTEM_RUNNING)
-			err = microcode_ops->request_microcode_fw(cpu,
+			err = microcode_ops->request_microcode_fw(
+					smp_processor_id(),
 					&microcode_pdev->dev);
 	}
 	if (!err)
-		microcode_ops->apply_microcode(cpu);
+		microcode_ops->apply_microcode(smp_processor_id());
+	return err;
 }
 
-static void microcode_init_cpu(int cpu)
+static int microcode_init_cpu(int cpu)
 {
-	cpumask_t old = current->cpus_allowed;
-
-	set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu));
-	/* We should bind the task to the CPU */
-	BUG_ON(raw_smp_processor_id() != cpu);
-
+	int err;
 	mutex_lock(&microcode_mutex);
-	microcode_update_cpu(cpu);
+	err = work_on_cpu(cpu, microcode_update_cpu, NULL);
 	mutex_unlock(&microcode_mutex);
 
-	set_cpus_allowed_ptr(current, &old);
+	return err;
 }
 
 static int mc_sysdev_add(struct sys_device *sys_dev)
@@ -379,8 +390,11 @@ static int mc_sysdev_add(struct sys_device *sys_dev)
 	if (err)
 		return err;
 
-	microcode_init_cpu(cpu);
-	return 0;
+	err = microcode_init_cpu(cpu);
+	if (err)
+		sysfs_remove_group(&sys_dev->kobj, &mc_attr_group);
+
+	return err;
 }
 
 static int mc_sysdev_remove(struct sys_device *sys_dev)
@@ -404,14 +418,14 @@ static int mc_sysdev_resume(struct sys_device *dev)
 		return 0;
 
 	/* only CPU 0 will apply ucode here */
-	microcode_update_cpu(0);
+	microcode_update_cpu(NULL);
 	return 0;
 }
 
 static struct sysdev_driver mc_sysdev_driver = {
-	.add = mc_sysdev_add,
-	.remove = mc_sysdev_remove,
-	.resume = mc_sysdev_resume,
+	.add		= mc_sysdev_add,
+	.remove		= mc_sysdev_remove,
+	.resume		= mc_sysdev_resume,
 };
 
 static __cpuinit int
@@ -424,7 +438,9 @@ mc_cpu_callback(struct notifier_block *nb, unsigned long action, void *hcpu)
 	switch (action) {
 	case CPU_ONLINE:
 	case CPU_ONLINE_FROZEN:
-		microcode_init_cpu(cpu);
+		if (microcode_init_cpu(cpu))
+			printk(KERN_ERR "microcode: failed to init CPU%d\n",
+			       cpu);
 	case CPU_DOWN_FAILED:
 	case CPU_DOWN_FAILED_FROZEN:
 		pr_debug("microcode: CPU%d added\n", cpu);
@@ -448,7 +464,7 @@ mc_cpu_callback(struct notifier_block *nb, unsigned long action, void *hcpu)
 }
 
 static struct notifier_block __refdata mc_cpu_notifier = {
-	.notifier_call = mc_cpu_callback,
+	.notifier_call	= mc_cpu_callback,
 };
 
 static int __init microcode_init(void)
diff --git a/arch/x86/kernel/microcode_intel.c b/arch/x86/kernel/microcode_intel.c
index 5e9f4fc51385..149b9ec7c1ab 100644
--- a/arch/x86/kernel/microcode_intel.c
+++ b/arch/x86/kernel/microcode_intel.c
@@ -70,28 +70,28 @@
  *		Fix sigmatch() macro to handle old CPUs with pf == 0.
  *		Thanks to Stuart Swales for pointing out this bug.
  */
+#include <linux/platform_device.h>
 #include <linux/capability.h>
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/sched.h>
+#include <linux/miscdevice.h>
+#include <linux/firmware.h>
 #include <linux/smp_lock.h>
+#include <linux/spinlock.h>
 #include <linux/cpumask.h>
-#include <linux/module.h>
-#include <linux/slab.h>
+#include <linux/uaccess.h>
 #include <linux/vmalloc.h>
-#include <linux/miscdevice.h>
-#include <linux/spinlock.h>
-#include <linux/mm.h>
-#include <linux/fs.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
 #include <linux/mutex.h>
+#include <linux/sched.h>
+#include <linux/init.h>
+#include <linux/slab.h>
 #include <linux/cpu.h>
-#include <linux/firmware.h>
-#include <linux/platform_device.h>
-#include <linux/uaccess.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
 
-#include <asm/msr.h>
-#include <asm/processor.h>
 #include <asm/microcode.h>
+#include <asm/processor.h>
+#include <asm/msr.h>
 
 MODULE_DESCRIPTION("Microcode Update Driver");
 MODULE_AUTHOR("Tigran Aivazian <tigran@aivazian.fsnet.co.uk>");
@@ -129,12 +129,13 @@ struct extended_sigtable {
 	struct extended_signature sigs[0];
 };
 
-#define DEFAULT_UCODE_DATASIZE 	(2000)
+#define DEFAULT_UCODE_DATASIZE	(2000)
 #define MC_HEADER_SIZE		(sizeof(struct microcode_header_intel))
 #define DEFAULT_UCODE_TOTALSIZE (DEFAULT_UCODE_DATASIZE + MC_HEADER_SIZE)
 #define EXT_HEADER_SIZE		(sizeof(struct extended_sigtable))
 #define EXT_SIGNATURE_SIZE	(sizeof(struct extended_signature))
 #define DWSIZE			(sizeof(u32))
+
 #define get_totalsize(mc) \
 	(((struct microcode_intel *)mc)->hdr.totalsize ? \
 	 ((struct microcode_intel *)mc)->hdr.totalsize : \
@@ -197,30 +198,31 @@ static inline int update_match_cpu(struct cpu_signature *csig, int sig, int pf)
 }
 
 static inline int
-update_match_revision(struct microcode_header_intel *mc_header,	int rev)
+update_match_revision(struct microcode_header_intel *mc_header, int rev)
 {
 	return (mc_header->rev <= rev) ? 0 : 1;
 }
 
 static int microcode_sanity_check(void *mc)
 {
+	unsigned long total_size, data_size, ext_table_size;
 	struct microcode_header_intel *mc_header = mc;
 	struct extended_sigtable *ext_header = NULL;
-	struct extended_signature *ext_sig;
-	unsigned long total_size, data_size, ext_table_size;
 	int sum, orig_sum, ext_sigcount = 0, i;
+	struct extended_signature *ext_sig;
 
 	total_size = get_totalsize(mc_header);
 	data_size = get_datasize(mc_header);
+
 	if (data_size + MC_HEADER_SIZE > total_size) {
 		printk(KERN_ERR "microcode: error! "
-			"Bad data size in microcode data file\n");
+				"Bad data size in microcode data file\n");
 		return -EINVAL;
 	}
 
 	if (mc_header->ldrver != 1 || mc_header->hdrver != 1) {
 		printk(KERN_ERR "microcode: error! "
-			"Unknown microcode update format\n");
+				"Unknown microcode update format\n");
 		return -EINVAL;
 	}
 	ext_table_size = total_size - (MC_HEADER_SIZE + data_size);
@@ -318,11 +320,15 @@ get_matching_microcode(struct cpu_signature *cpu_sig, void *mc, int rev)
 
 static void apply_microcode(int cpu)
 {
+	struct microcode_intel *mc_intel;
+	struct ucode_cpu_info *uci;
 	unsigned long flags;
 	unsigned int val[2];
-	int cpu_num = raw_smp_processor_id();
-	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
-	struct microcode_intel *mc_intel = uci->mc;
+	int cpu_num;
+
+	cpu_num = raw_smp_processor_id();
+	uci = ucode_cpu_info + cpu;
+	mc_intel = uci->mc;
 
 	/* We should bind the task to the CPU */
 	BUG_ON(cpu_num != cpu);
@@ -348,15 +354,17 @@ static void apply_microcode(int cpu)
 	spin_unlock_irqrestore(&microcode_update_lock, flags);
 	if (val[1] != mc_intel->hdr.rev) {
 		printk(KERN_ERR "microcode: CPU%d update from revision "
-			"0x%x to 0x%x failed\n", cpu_num, uci->cpu_sig.rev, val[1]);
+				"0x%x to 0x%x failed\n",
+			cpu_num, uci->cpu_sig.rev, val[1]);
 		return;
 	}
 	printk(KERN_INFO "microcode: CPU%d updated from revision "
-	       "0x%x to 0x%x, date = %04x-%02x-%02x \n",
+			 "0x%x to 0x%x, date = %04x-%02x-%02x \n",
 		cpu_num, uci->cpu_sig.rev, val[1],
 		mc_intel->hdr.date & 0xffff,
 		mc_intel->hdr.date >> 24,
 		(mc_intel->hdr.date >> 16) & 0xff);
+
 	uci->cpu_sig.rev = val[1];
 }
 
@@ -404,18 +412,23 @@ static int generic_load_microcode(int cpu, void *data, size_t size,
 		leftover  -= mc_size;
 	}
 
-	if (new_mc) {
-		if (!leftover) {
-			if (uci->mc)
-				vfree(uci->mc);
-			uci->mc = (struct microcode_intel *)new_mc;
-			pr_debug("microcode: CPU%d found a matching microcode update with"
-				 " version 0x%x (current=0x%x)\n",
-				cpu, new_rev, uci->cpu_sig.rev);
-		} else
-			vfree(new_mc);
+	if (!new_mc)
+		goto out;
+
+	if (leftover) {
+		vfree(new_mc);
+		goto out;
 	}
 
+	if (uci->mc)
+		vfree(uci->mc);
+	uci->mc = (struct microcode_intel *)new_mc;
+
+	pr_debug("microcode: CPU%d found a matching microcode update with"
+		 " version 0x%x (current=0x%x)\n",
+			cpu, new_rev, uci->cpu_sig.rev);
+
+ out:
 	return (int)leftover;
 }
 
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 90f5b9ef5def..745579bc8256 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -40,7 +40,7 @@ EXPORT_SYMBOL(bad_dma_address);
    to older i386. */
 struct device x86_dma_fallback_dev = {
 	.init_name = "fallback device",
-	.coherent_dma_mask = DMA_32BIT_MASK,
+	.coherent_dma_mask = DMA_BIT_MASK(32),
 	.dma_mask = &x86_dma_fallback_dev.coherent_dma_mask,
 };
 EXPORT_SYMBOL(x86_dma_fallback_dev);
@@ -148,7 +148,7 @@ again:
 	if (!is_buffer_dma_capable(dma_mask, addr, size)) {
 		__free_pages(page, get_order(size));
 
-		if (dma_mask < DMA_32BIT_MASK && !(flag & GFP_DMA)) {
+		if (dma_mask < DMA_BIT_MASK(32) && !(flag & GFP_DMA)) {
 			flag = (flag & ~GFP_DMA32) | GFP_DMA;
 			goto again;
 		}
@@ -243,7 +243,7 @@ int dma_supported(struct device *dev, u64 mask)
 	/* Copied from i386. Doesn't make much sense, because it will
 	   only work for pci_alloc_coherent.
 	   The caller just has to use GFP_DMA in this case. */
-	if (mask < DMA_24BIT_MASK)
+	if (mask < DMA_BIT_MASK(24))
 		return 0;
 
 	/* Tell the device to use SAC when IOMMU force is on.  This
@@ -258,7 +258,7 @@ int dma_supported(struct device *dev, u64 mask)
 	   SAC for these.  Assume all masks <= 40 bits are of this
 	   type. Normally this doesn't make any difference, but gives
 	   more gentle handling of IOMMU overflow. */
-	if (iommu_sac_force && (mask >= DMA_40BIT_MASK)) {
+	if (iommu_sac_force && (mask >= DMA_BIT_MASK(40))) {
 		dev_info(dev, "Force SAC with mask %Lx\n", mask);
 		return 0;
 	}
diff --git a/arch/x86/kernel/pci-nommu.c b/arch/x86/kernel/pci-nommu.c
index c6d703b39326..71d412a09f30 100644
--- a/arch/x86/kernel/pci-nommu.c
+++ b/arch/x86/kernel/pci-nommu.c
@@ -15,7 +15,7 @@ static int
 check_addr(char *name, struct device *hwdev, dma_addr_t bus, size_t size)
 {
 	if (hwdev && !is_buffer_dma_capable(*hwdev->dma_mask, bus, size)) {
-		if (*hwdev->dma_mask >= DMA_32BIT_MASK)
+		if (*hwdev->dma_mask >= DMA_BIT_MASK(32))
 			printk(KERN_ERR
 			    "nommu_%s: overflow %Lx+%zu of device mask %Lx\n",
 				name, (long long)bus, size,
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 156f87582c6c..ca989158e847 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -8,7 +8,7 @@
 #include <linux/module.h>
 #include <linux/pm.h>
 #include <linux/clockchips.h>
-#include <linux/ftrace.h>
+#include <trace/power.h>
 #include <asm/system.h>
 #include <asm/apic.h>
 #include <asm/idle.h>
@@ -22,6 +22,9 @@ EXPORT_SYMBOL(idle_nomwait);
 
 struct kmem_cache *task_xstate_cachep;
 
+DEFINE_TRACE(power_start);
+DEFINE_TRACE(power_end);
+
 int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 {
 	*dst = *src;
@@ -325,7 +328,7 @@ void stop_this_cpu(void *dummy)
 	/*
 	 * Remove this CPU:
 	 */
-	cpu_clear(smp_processor_id(), cpu_online_map);
+	set_cpu_online(smp_processor_id(), false);
 	disable_local_APIC();
 
 	for (;;) {
@@ -475,12 +478,13 @@ static int __cpuinit check_c1e_idle(const struct cpuinfo_x86 *c)
 	return 1;
 }
 
-static cpumask_t c1e_mask = CPU_MASK_NONE;
+static cpumask_var_t c1e_mask;
 static int c1e_detected;
 
 void c1e_remove_cpu(int cpu)
 {
-	cpu_clear(cpu, c1e_mask);
+	if (c1e_mask != NULL)
+		cpumask_clear_cpu(cpu, c1e_mask);
 }
 
 /*
@@ -509,8 +513,8 @@ static void c1e_idle(void)
 	if (c1e_detected) {
 		int cpu = smp_processor_id();
 
-		if (!cpu_isset(cpu, c1e_mask)) {
-			cpu_set(cpu, c1e_mask);
+		if (!cpumask_test_cpu(cpu, c1e_mask)) {
+			cpumask_set_cpu(cpu, c1e_mask);
 			/*
 			 * Force broadcast so ACPI can not interfere. Needs
 			 * to run with interrupts enabled as it uses
@@ -562,6 +566,15 @@ void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c)
 		pm_idle = default_idle;
 }
 
+void __init init_c1e_mask(void)
+{
+	/* If we're using c1e_idle, we need to allocate c1e_mask. */
+	if (pm_idle == c1e_idle) {
+		alloc_cpumask_var(&c1e_mask, GFP_KERNEL);
+		cpumask_clear(c1e_mask);
+	}
+}
+
 static int __init idle_setup(char *str)
 {
 	if (!str)
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 14014d766cad..76f8f84043a2 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -245,7 +245,7 @@ void prepare_to_copy(struct task_struct *tsk)
 	unlazy_fpu(tsk);
 }
 
-int copy_thread(int nr, unsigned long clone_flags, unsigned long sp,
+int copy_thread(unsigned long clone_flags, unsigned long sp,
 	unsigned long unused,
 	struct task_struct *p, struct pt_regs *regs)
 {
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index abb7e6a7f0c6..b751a41392b1 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -278,7 +278,7 @@ void prepare_to_copy(struct task_struct *tsk)
 	unlazy_fpu(tsk);
 }
 
-int copy_thread(int nr, unsigned long clone_flags, unsigned long sp,
+int copy_thread(unsigned long clone_flags, unsigned long sp,
 		unsigned long unused,
 	struct task_struct *p, struct pt_regs *regs)
 {
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 19378715f415..fe9345c967de 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -21,6 +21,7 @@
 #include <linux/audit.h>
 #include <linux/seccomp.h>
 #include <linux/signal.h>
+#include <linux/ftrace.h>
 
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
@@ -1415,6 +1416,9 @@ asmregparm long syscall_trace_enter(struct pt_regs *regs)
 	    tracehook_report_syscall_entry(regs))
 		ret = -1L;
 
+	if (unlikely(test_thread_flag(TIF_SYSCALL_FTRACE)))
+		ftrace_syscall_enter(regs);
+
 	if (unlikely(current->audit_context)) {
 		if (IS_IA32)
 			audit_syscall_entry(AUDIT_ARCH_I386,
@@ -1438,6 +1442,9 @@ asmregparm void syscall_trace_leave(struct pt_regs *regs)
 	if (unlikely(current->audit_context))
 		audit_syscall_exit(AUDITSC_RESULT(regs->ax), regs->ax);
 
+	if (unlikely(test_thread_flag(TIF_SYSCALL_FTRACE)))
+		ftrace_syscall_exit(regs);
+
 	if (test_thread_flag(TIF_SYSCALL_TRACE))
 		tracehook_report_syscall_exit(regs, 0);
 
@@ -1455,6 +1462,6 @@ asmregparm void syscall_trace_leave(struct pt_regs *regs)
 	 * system call instruction.
 	 */
 	if (test_thread_flag(TIF_SINGLESTEP) &&
-	    tracehook_consider_fatal_signal(current, SIGTRAP, SIG_DFL))
+	    tracehook_consider_fatal_signal(current, SIGTRAP))
 		send_sigtrap(current, regs, 0, TRAP_BRKPT);
 }
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 400331b50a53..3a97a4cf1872 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -153,7 +153,6 @@ static struct page * __init pcpur_get_page(unsigned int cpu, int pageno)
 static ssize_t __init setup_pcpu_remap(size_t static_size)
 {
 	static struct vm_struct vm;
-	pg_data_t *last;
 	size_t ptrs_size, dyn_size;
 	unsigned int cpu;
 	ssize_t ret;
@@ -162,22 +161,9 @@ static ssize_t __init setup_pcpu_remap(size_t static_size)
 	 * If large page isn't supported, there's no benefit in doing
 	 * this.  Also, on non-NUMA, embedding is better.
 	 */
-	if (!cpu_has_pse || pcpu_need_numa())
+	if (!cpu_has_pse || !pcpu_need_numa())
 		return -EINVAL;
 
-	last = NULL;
-	for_each_possible_cpu(cpu) {
-		int node = early_cpu_to_node(cpu);
-
-		if (node_online(node) && NODE_DATA(node) &&
-		    last && last != NODE_DATA(node))
-			goto proceed;
-
-		last = NODE_DATA(node);
-	}
-	return -EINVAL;
-
-proceed:
 	/*
 	 * Currently supports only single page.  Supporting multiple
 	 * pages won't be too difficult if it ever becomes necessary.
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index dfcc74ab0ab6..14425166b8e3 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -221,7 +221,7 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size,
 	if (!onsigstack) {
 		/* This is the X/Open sanctioned signal stack switching.  */
 		if (ka->sa.sa_flags & SA_ONSTACK) {
-			if (sas_ss_flags(sp) == 0)
+			if (current->sas_ss_size)
 				sp = current->sas_ss_sp + current->sas_ss_size;
 		} else {
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index ef7d10170c30..58d24ef917d8 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -101,11 +101,11 @@ EXPORT_SYMBOL(smp_num_siblings);
 DEFINE_PER_CPU(u16, cpu_llc_id) = BAD_APICID;
 
 /* representing HT siblings of each logical CPU */
-DEFINE_PER_CPU(cpumask_t, cpu_sibling_map);
+DEFINE_PER_CPU(cpumask_var_t, cpu_sibling_map);
 EXPORT_PER_CPU_SYMBOL(cpu_sibling_map);
 
 /* representing HT and core siblings of each logical CPU */
-DEFINE_PER_CPU(cpumask_t, cpu_core_map);
+DEFINE_PER_CPU(cpumask_var_t, cpu_core_map);
 EXPORT_PER_CPU_SYMBOL(cpu_core_map);
 
 /* Per CPU bogomips and other parameters */
@@ -115,11 +115,6 @@ EXPORT_PER_CPU_SYMBOL(cpu_info);
 atomic_t init_deasserted;
 
 #if defined(CONFIG_NUMA) && defined(CONFIG_X86_32)
-
-/* which logical CPUs are on which nodes */
-cpumask_t node_to_cpumask_map[MAX_NUMNODES] __read_mostly =
-				{ [0 ... MAX_NUMNODES-1] = CPU_MASK_NONE };
-EXPORT_SYMBOL(node_to_cpumask_map);
 /* which node each logical CPU is on */
 int cpu_to_node_map[NR_CPUS] __read_mostly = { [0 ... NR_CPUS-1] = 0 };
 EXPORT_SYMBOL(cpu_to_node_map);
@@ -128,7 +123,7 @@ EXPORT_SYMBOL(cpu_to_node_map);
 static void map_cpu_to_node(int cpu, int node)
 {
 	printk(KERN_INFO "Mapping cpu %d to node %d\n", cpu, node);
-	cpumask_set_cpu(cpu, &node_to_cpumask_map[node]);
+	cpumask_set_cpu(cpu, node_to_cpumask_map[node]);
 	cpu_to_node_map[cpu] = node;
 }
 
@@ -139,7 +134,7 @@ static void unmap_cpu_to_node(int cpu)
 
 	printk(KERN_INFO "Unmapping cpu %d from all nodes\n", cpu);
 	for (node = 0; node < MAX_NUMNODES; node++)
-		cpumask_clear_cpu(cpu, &node_to_cpumask_map[node]);
+		cpumask_clear_cpu(cpu, node_to_cpumask_map[node]);
 	cpu_to_node_map[cpu] = 0;
 }
 #else /* !(CONFIG_NUMA && CONFIG_X86_32) */
@@ -301,7 +296,7 @@ notrace static void __cpuinit start_secondary(void *unused)
 	__flush_tlb_all();
 #endif
 
-	/* This must be done before setting cpu_online_map */
+	/* This must be done before setting cpu_online_mask */
 	set_cpu_sibling_map(raw_smp_processor_id());
 	wmb();
 
@@ -334,6 +329,23 @@ notrace static void __cpuinit start_secondary(void *unused)
 	cpu_idle();
 }
 
+#ifdef CONFIG_CPUMASK_OFFSTACK
+/* In this case, llc_shared_map is a pointer to a cpumask. */
+static inline void copy_cpuinfo_x86(struct cpuinfo_x86 *dst,
+				    const struct cpuinfo_x86 *src)
+{
+	struct cpumask *llc = dst->llc_shared_map;
+	*dst = *src;
+	dst->llc_shared_map = llc;
+}
+#else
+static inline void copy_cpuinfo_x86(struct cpuinfo_x86 *dst,
+				    const struct cpuinfo_x86 *src)
+{
+	*dst = *src;
+}
+#endif /* CONFIG_CPUMASK_OFFSTACK */
+
 /*
  * The bootstrap kernel entry code has set these up. Save them for
  * a given CPU
@@ -343,7 +355,7 @@ void __cpuinit smp_store_cpu_info(int id)
 {
 	struct cpuinfo_x86 *c = &cpu_data(id);
 
-	*c = boot_cpu_data;
+	copy_cpuinfo_x86(c, &boot_cpu_data);
 	c->cpu_index = id;
 	if (id != 0)
 		identify_secondary_cpu(c);
@@ -367,15 +379,15 @@ void __cpuinit set_cpu_sibling_map(int cpu)
 				cpumask_set_cpu(cpu, cpu_sibling_mask(i));
 				cpumask_set_cpu(i, cpu_core_mask(cpu));
 				cpumask_set_cpu(cpu, cpu_core_mask(i));
-				cpumask_set_cpu(i, &c->llc_shared_map);
-				cpumask_set_cpu(cpu, &o->llc_shared_map);
+				cpumask_set_cpu(i, c->llc_shared_map);
+				cpumask_set_cpu(cpu, o->llc_shared_map);
 			}
 		}
 	} else {
 		cpumask_set_cpu(cpu, cpu_sibling_mask(cpu));
 	}
 
-	cpumask_set_cpu(cpu, &c->llc_shared_map);
+	cpumask_set_cpu(cpu, c->llc_shared_map);
 
 	if (current_cpu_data.x86_max_cores == 1) {
 		cpumask_copy(cpu_core_mask(cpu), cpu_sibling_mask(cpu));
@@ -386,8 +398,8 @@ void __cpuinit set_cpu_sibling_map(int cpu)
 	for_each_cpu(i, cpu_sibling_setup_mask) {
 		if (per_cpu(cpu_llc_id, cpu) != BAD_APICID &&
 		    per_cpu(cpu_llc_id, cpu) == per_cpu(cpu_llc_id, i)) {
-			cpumask_set_cpu(i, &c->llc_shared_map);
-			cpumask_set_cpu(cpu, &cpu_data(i).llc_shared_map);
+			cpumask_set_cpu(i, c->llc_shared_map);
+			cpumask_set_cpu(cpu, cpu_data(i).llc_shared_map);
 		}
 		if (c->phys_proc_id == cpu_data(i).phys_proc_id) {
 			cpumask_set_cpu(i, cpu_core_mask(cpu));
@@ -425,12 +437,7 @@ const struct cpumask *cpu_coregroup_mask(int cpu)
 	if (sched_mc_power_savings || sched_smt_power_savings)
 		return cpu_core_mask(cpu);
 	else
-		return &c->llc_shared_map;
-}
-
-cpumask_t cpu_coregroup_map(int cpu)
-{
-	return *cpu_coregroup_mask(cpu);
+		return c->llc_shared_map;
 }
 
 static void impress_friends(void)
@@ -897,9 +904,8 @@ int __cpuinit native_cpu_up(unsigned int cpu)
  */
 static __init void disable_smp(void)
 {
-	/* use the read/write pointers to the present and possible maps */
-	cpumask_copy(&cpu_present_map, cpumask_of(0));
-	cpumask_copy(&cpu_possible_map, cpumask_of(0));
+	init_cpu_present(cpumask_of(0));
+	init_cpu_possible(cpumask_of(0));
 	smpboot_clear_io_apic_irqs();
 
 	if (smp_found_config)
@@ -1031,6 +1037,8 @@ static void __init smp_cpu_index_default(void)
  */
 void __init native_smp_prepare_cpus(unsigned int max_cpus)
 {
+	unsigned int i;
+
 	preempt_disable();
 	smp_cpu_index_default();
 	current_cpu_data = boot_cpu_data;
@@ -1044,6 +1052,14 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 	boot_cpu_logical_apicid = logical_smp_processor_id();
 #endif
 	current_thread_info()->cpu = 0;  /* needed? */
+	for_each_possible_cpu(i) {
+		alloc_cpumask_var(&per_cpu(cpu_sibling_map, i), GFP_KERNEL);
+		alloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL);
+		alloc_cpumask_var(&cpu_data(i).llc_shared_map, GFP_KERNEL);
+		cpumask_clear(per_cpu(cpu_core_map, i));
+		cpumask_clear(per_cpu(cpu_sibling_map, i));
+		cpumask_clear(cpu_data(i).llc_shared_map);
+	}
 	set_cpu_sibling_map(0);
 
 	enable_IR_x2apic();
@@ -1132,11 +1148,11 @@ early_param("possible_cpus", _setup_possible_cpus);
 
 
 /*
- * cpu_possible_map should be static, it cannot change as cpu's
+ * cpu_possible_mask should be static, it cannot change as cpu's
  * are onlined, or offlined. The reason is per-cpu data-structures
  * are allocated by some modules at init time, and dont expect to
  * do this dynamically on cpu arrival/departure.
- * cpu_present_map on the other hand can change dynamically.
+ * cpu_present_mask on the other hand can change dynamically.
  * In case when cpu_hotplug is not compiled, then we resort to current
  * behaviour, which is cpu_possible == cpu_present.
  * - Ashok Raj
diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S
index 3bdb64829b82..ff5c8736b491 100644
--- a/arch/x86/kernel/syscall_table_32.S
+++ b/arch/x86/kernel/syscall_table_32.S
@@ -332,3 +332,5 @@ ENTRY(sys_call_table)
 	.long sys_dup3			/* 330 */
 	.long sys_pipe2
 	.long sys_inotify_init1
+	.long sys_preadv
+	.long sys_pwritev
diff --git a/arch/x86/kernel/tlb_uv.c b/arch/x86/kernel/tlb_uv.c
index 79c073247284..deb5ebb32c3b 100644
--- a/arch/x86/kernel/tlb_uv.c
+++ b/arch/x86/kernel/tlb_uv.c
@@ -275,6 +275,8 @@ const struct cpumask *uv_flush_send_and_wait(int cpu, int this_blade,
 	return NULL;
 }
 
+static DEFINE_PER_CPU(cpumask_var_t, uv_flush_tlb_mask);
+
 /**
  * uv_flush_tlb_others - globally purge translation cache of a virtual
  * address or all TLB's
@@ -304,8 +306,7 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
 					  struct mm_struct *mm,
 					  unsigned long va, unsigned int cpu)
 {
-	static DEFINE_PER_CPU(cpumask_t, flush_tlb_mask);
-	struct cpumask *flush_mask = &__get_cpu_var(flush_tlb_mask);
+	struct cpumask *flush_mask = __get_cpu_var(uv_flush_tlb_mask);
 	int i;
 	int bit;
 	int blade;
@@ -755,6 +756,10 @@ static int __init uv_bau_init(void)
 	if (!is_uv_system())
 		return 0;
 
+	for_each_possible_cpu(cur_cpu)
+		alloc_cpumask_var_node(&per_cpu(uv_flush_tlb_mask, cur_cpu),
+				       GFP_KERNEL, cpu_to_node(cur_cpu));
+
 	uv_bau_retry_limit = 1;
 	uv_nshift = uv_hub_info->n_val;
 	uv_mmask = (1UL << uv_hub_info->n_val) - 1;